[PATCH v8 00/25] PCI: Convert all dynamic sysfs attributes to static

[PATCH v8 00/25] PCI: Convert all dynamic sysfs attributes to static

[Krzysztof Wilczyński]

Hello,

This series converts every dynamically allocated PCI sysfs attribute to
a static const definition.  After the full series, pci_sysfs_init() and
sysfs_initialized are gone, and every sysfs file is created by the
driver model at device_add() time.

Currently, the PCI resource files (resourceN, resourceN_wc) and the
legacy bus files (legacy_io, legacy_mem) are created dynamically
from two unsynchronised paths:

Path A: late_initcall

  pci_sysfs_init()                        (late_initcall)
    sysfs_initialized = 1
    for_each_pci_dev()
      pci_create_sysfs_dev_files()
        sysfs_create_bin_file()           (resourceN, resourceN_wc)
    pci_find_next_bus()
      pci_create_legacy_files()
        sysfs_create_bin_file()           (legacy_io, legacy_mem)

Path B: device registration / hotplug

  pci_bus_add_devices()
    pci_bus_add_device()
      pci_create_sysfs_dev_files()
        if (!sysfs_initialized)           <- only guard
          return
        sysfs_create_bin_file()           (resourceN, resourceN_wc)

On most ACPI systems this does not race because PCI enumeration
completes at subsys_initcall time, before pci_sysfs_init() runs:

  subsys_initcall (level 4):
    acpi_pci_root_add()
      pci_bus_add_device()
        pci_create_sysfs_dev_files()
          if (!sysfs_initialized)         <- variable not yet set
            return -EACCES

  late_initcall (level 7):
    pci_sysfs_init()
      sysfs_initialized = 1
      for_each_pci_dev()
        pci_create_sysfs_dev_files()      <- creates the files, no race

On Devicetree platforms the host controller is a platform driver that
probes via the driver model, often on a workqueue, and overlaps with the
late_initcall:

  CPU 0 (late_initcall)                CPU 1 (driver probe)
  ---------------------------          ----------------------------
  pci_sysfs_init()
    sysfs_initialized = 1
    for_each_pci_dev()                 pci_bus_add_device()
      pci_create_sysfs_dev_files()       pci_create_sysfs_dev_files()
        sysfs_create_bin_file()            sysfs_create_bin_file()
                                             -> "duplicate filename"

The same happens on ACPI when probing is asynchronous (hv_pci on
Azure, RISC-V with ACPI).

The duplicate causes sysfs_create_bin_file() to fail with -EEXIST.
pci_create_resource_files() then calls pci_remove_resource_files() in
its error unwind, tearing down files the other thread created and
still references through pdev->res_attr[].  This has caused kernel
panics on i.MX6 and boot failures on other platforms.

Several different fixes have been proposed over the years: reordering
the sysfs_initialized assignment, adding locks, checking
pci_dev_is_added(), setting pdev->res_attr[] to NULL after kfree
(which only prevents a double-free on the teardown path, not the
error unwind removing the other thread's files).  None would address the
root cause.

This has been reported a few times:

  - https://lore.kernel.org/linux-pci/20250702155112.40124-1-heshuan@bytedance.com/
  - https://lore.kernel.org/linux-pci/b51519d6-ce45-4b6d-8135-c70169bd110e@h-partners.com/
  - https://lore.kernel.org/linux-pci/1702093576-30405-1-git-send-email-ssengar@linux.microsoft.com/
  - https://lore.kernel.org/linux-pci/SY0P300MB04687548090B73E40AF97D8897B82@SY0P300MB0468.AUSP300.PROD.OUTLOOK.COM/
  - https://lore.kernel.org/linux-pci/20230105174736.GA1154719@bhelgaas/
  - https://lore.kernel.org/linux-pci/m3eebg9puj.fsf@t19.piap.pl/
  - https://lore.kernel.org/linux-pci/20200716110423.xtfyb3n6tn5ixedh@pali/
  - https://lore.kernel.org/linux-pci/1366196798-15929-1-git-send-email-artem.savkov@gmail.com/
  - https://bugzilla.kernel.org/show_bug.cgi?id=215515
  - https://bugzilla.kernel.org/show_bug.cgi?id=216888

With static attributes the driver model creates sysfs entries once per
device at device_add() time, under the device lock, eliminating the
late_initcall iteration and the race along with it.

	Krzysztof

---
Changes in v8:
  https://lore.kernel.org/linux-pci/20260508043543.217179-1-kwilczynski@kernel.org/

  - Renamed the generic resource attributes from dev_resourceN_{io,uc,wc}_attr
    to pci_dev_resourceN_{io,uc,wc}_attr, for consistency, and cleaned up
    resource macros definitions.
  - Changed resource macros argument order to fix checkpatch.pl
    complaint.
  - Added two new macros, pci_legacy_resource_io_attr() and
    pci_legacy_resource_mem_attr(), used for the legacy I/O and memory
    conversion instead of open-coding each struct bin_attribute.  No
    functional changes intended.

Changes in v7:
  https://lore.kernel.org/linux-pci/20260422161407.118748-1-kwilczynski@kernel.org/

  - Addded Alex Williamson (author of the resource resize sysfs
    attributes) to the list of recipients for visibility.
  - Split pci_llseek_resource() into pci_llseek_resource() and
    pci_llseek_resource_legacy() since legacy attributes operate
    on a struct pci_bus where to_pci_dev() would be invalid,
    as per Bjorn Helgaas' feedback.
  - Moved each llseek variant inside its respective #ifdef guard
    during the corresponding dynamic-to-static conversion commit,
    dropping the __maybe_unused annotations.
  - Extended the WARN macro removal to also cover __legacy_mmap_fits().
  - Updated commit message of patch 18, so that it correctly mentions
    pci_stop_dev() rather than pci_stop_bus_device().
  - Updated commit message of patch 24 to clarify the indirect
    relationship between ReBAR and the HAVE_PCI_MMAP and/or
    ARCH_GENERIC_PCI_MMAP_RESOURCE guards.

Changes in v6:
  https://lore.kernel.org/linux-pci/20260416180107.777065-1-kwilczynski@kernel.org/

   - Fixed commit message for patch 13, removing reference to
     pci_resource_flags() which was no longer changed there.
   - Added a new patch (24) to move the BAR resource resize
     (ReBAR) support behind existing PCI mmap #ifdef guard,
     so that the code is not included on architectures that
     do not support resource resizing (i.e., Alpha, etc.).

Changes in v5:
  https://lore.kernel.org/linux-pci/20260411080148.471335-1-kwilczynski@kernel.org/
  
   - Added new Tested-by, Reviewed-by, and Acked-by tags.
   - Used the existing _io function names in the static macro
     definitions, deferring the rename to the conversion commit
     where it belongs, to avoid a forward reference across
     commits. This was reported by Sashiko, see:
     https://sashiko.dev/#/patchset/20260411080148.471335-1-kwilczynski%40kernel.org?part=6
   - Folded the __resource_resize_store() conversion into the
     main static attributes commit so the resize path is never
     broken between commits. This was reported by Sashiko, see:
     https://sashiko.dev/#/patchset/20260410055040.39233-1-kwilczynski%40kernel.org?part=6
     https://sashiko.dev/#/patchset/20260411080148.471335-1-kwilczynski%40kernel.org?part=7
   - Dropped the unnecessary parentheses cleanup from the Alpha
     BAR index commit, as the line is replaced two commits later
     anyway, as per Ilpo Järvinen's feedback.
   - Squashed the Alpha accessor macro and cleanup commits into
     one, using pci_resource_is_mem() directly instead of the
     intermediate pci_resource_flags() step, as per Ilpo
     Järvinen's feedback.
   - Moved the raw literal conversion in pci_create_legacy_files()
     into the macro definition commit, so the macros and their
     usage are introduced together, as per Ilpo Järvinen's
     feedback.
   - Removed unnecessary backslash line continuation from the
     ternary in pci_mmap_legacy_page_range().
   - Kept pci_resource_len() for visibility checks instead of
     resource_assigned().  The static is_visible() callback
     runs at device_add() time during the PCI enumeration,
     before the pci_assign_unassigned_bus_resources() populates
     res->parent, as such, resource_assigned() returned false
     for every BAR, hiding all resource files.  This is related
     to review feedback from Ilpo Järvinen.

Changes in v4:
  https://lore.kernel.org/linux-pci/20260410055040.39233-1-kwilczynski@kernel.org/

   - Added new Reviewed-by tags.
   - Added pci_resource_is_io() and pci_resource_is_mem() helpers
     for resource type checks, replacing the open-coded bitwise
     flag tests in pci_mmap_resource(), pci_resource_io(), and
     Alpha's pci_mmap_resource(), as per Ilpo Järvinen's
     suggestion.
   - Split the __pci_mmap_fits() cleanup into two patches.  An
     overflow fix for zero-length BARs, which now includes a
     Fixes: tag referencing the original Alpha PCI sysfs commit,
     and the WARN macro removal is a separate cleanup as per Ilpo
     Järvinen's suggestion.
   - Added a missing Fixes: tag to the Alpha lockdown check,
     referencing the commit that added the check to the generic
     path but missed Alpha's implementation.
   - Added PCI_LEGACY_IO_SIZE and PCI_LEGACY_MEM_SIZE macros to
     replace the raw literals used for legacy address space sizes.
     These are used in both Alpha's pci_mmap_legacy_page_range()
     and the static legacy attribute definitions, as per Ilpo
     Järvinen's suggestion.
   - Replaced sysfs_update_groups() in the BAR resize path with
     sysfs_remove_groups() before the resize and sysfs_create_groups()
     after, restoring the original teardown before BAR resize
     ordering.  This was reported by Sashiko, see:
     https://sashiko.dev/#/patchset/20260410055040.39233-1-kwilczynski%40kernel.org?part=7
   - Defined pci_dev_resource_attr_groups as a NULL macro when
     HAVE_PCI_MMAP and ARCH_GENERIC_PCI_MMAP_RESOURCE are both
     absent, so the resize path compiles unconditionally without
     #ifdef guards in the function body.  This was reported by
     Sashiko, see:
     https://sashiko.dev/#/patchset/20260410055040.39233-1-kwilczynski%40kernel.org?part=7
   - Moved the pci_legacy_has_sparse() prototype into the patch
     that introduces the function, alongside the existing
     pci_adjust_legacy_attr() declaration, to fix a bisection
     issue where Alpha would warn on -Wmissing-prototypes.
     This was reported by Sashiko, see:
     https://sashiko.dev/#/patchset/20260410055040.39233-1-kwilczynski%40kernel.org?part=18

Changes in v3:
  https://lore.kernel.org/linux-pci/20210910202623.2293708-1-kw@linux.com/

  - Updated for modern kernel releases and expanded scope.  The
    v2 only covered the generic resource files.  This version
    also converts Alpha's sparse/dense resource files and the
    legacy bus attributes, removing pci_sysfs_init() entirely.
  - Split the single macro definition into three distinct ones
    (per I/O, UC, and WC), to make sure that each carries only
    the callbacks its resource type needs.
  - Updated to use the new .bin_size callback, as the attributes
    are const, to replace using a->size directly, which was not
    ideal.  This required changes to pci_llseek_resource(), to
    ensure that it would work for device and bus-level attributes.
  - Updated the __resource_resize_store() to include CAP_SYS_ADMIN
    capabilities check.
  - Added the security_locked_down() check to Alpha's
    pci_mmap_resource(), to align with other architectures.

Changes in v2:
  https://lore.kernel.org/linux-pci/20210825212255.878043-1-kw@linux.com/

  - Refactored code so that the macros, helpers and internal
    functions can be used to correctly leverage the read(),
    write() and mmap() callbacks rather than to use the
    .is_bin_visible() callback to set up sysfs objects
    internals as this is not supported.
  - Refactored some if-statements to check for a resource
    flag first, and then call either arch_can_pci_mmap_io()
    or arch_can_pci_mmap_wc(), plus store result of testing
    for IORESOURCE_MEM and IORESOURCE_PREFETCH flags into
    a boolean variable, as per Bjorn Helgaas' suggestion.
  - Renamed pci_read_resource_io() and pci_write_resource_io()
    callbacks so that these are not specifically tied to I/O
    BARs read() and write() operations also as per Bjorn
    Helgaas' suggestion.
  - Updated style for code handling bitwise operations to
    match the style that is preferred as per Bjorn Helgaas'
    suggestion.
  - Updated commit messages adding more details about the
    implementation as requested by Bjorn Helgaas.

Krzysztof Wilczyński (25):
  PCI/sysfs: Use PCI resource accessor macros
  PCI: Add pci_resource_is_io() and pci_resource_is_mem() helpers
  PCI/sysfs: Only allow supported resource types in I/O and MMIO helpers
  PCI/sysfs: Split pci_llseek_resource() for device and legacy
    attributes
  PCI/sysfs: Add CAP_SYS_ADMIN check to __resource_resize_store()
  PCI/sysfs: Add static PCI resource attribute macros
  PCI/sysfs: Convert PCI resource files to static attributes
  PCI/sysfs: Warn about BAR resize failure in __resource_resize_store()
  PCI/sysfs: Add stubs for pci_{create,remove}_sysfs_dev_files()
  PCI/sysfs: Limit pci_sysfs_init() late_initcall compile scope
  alpha/PCI: Add security_locked_down() check to pci_mmap_resource()
  alpha/PCI: Use BAR index in sysfs attr->private instead of resource
    pointer
  alpha/PCI: Use PCI resource accessor macros
  alpha/PCI: Fix __pci_mmap_fits() overflow for zero-length BARs
  alpha/PCI: Remove WARN from __pci_mmap_fits() and __legacy_mmap_fits()
  alpha/PCI: Add static PCI resource attribute macros
  alpha/PCI: Convert resource files to static attributes
  PCI/sysfs: Remove pci_{create,remove}_sysfs_dev_files()
  PCI: Add macros for legacy I/O and memory address space sizes
  alpha/PCI: Compute legacy size in pci_mmap_legacy_page_range()
  PCI/sysfs: Add __weak pci_legacy_has_sparse() helper
  PCI/sysfs: Add legacy I/O and memory attribute macros
  PCI/sysfs: Convert legacy I/O and memory attributes to static
    definitions
  PCI/sysfs: Remove pci_create_legacy_files() and pci_sysfs_init()
  PCI/sysfs: Limit BAR resize attribute scope to platforms with PCI mmap

 arch/alpha/include/asm/pci.h   |  13 +-
 arch/alpha/kernel/pci-sysfs.c  | 388 ++++++++++++----------
 arch/powerpc/include/asm/pci.h |   2 -
 drivers/pci/bus.c              |   1 -
 drivers/pci/pci-sysfs.c        | 581 ++++++++++++++++++---------------
 drivers/pci/pci.h              |  16 +-
 drivers/pci/probe.c            |   6 -
 drivers/pci/remove.c           |   3 -
 include/linux/pci.h            |  39 ++-
 9 files changed, 580 insertions(+), 469 deletions(-)

-- 
2.54.0

[PATCH v8 01/25] PCI/sysfs: Use PCI resource accessor macros

[Krzysztof Wilczyński]

Replace direct pdev->resource[] accesses with pci_resource_n(),
and pdev->resource[].flags accesses with pci_resource_flags().

No functional changes intended.

Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/pci-sysfs.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index d37860841260..1fbc3daf87cc 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -177,7 +177,7 @@ static ssize_t resource_show(struct device *dev, struct device_attribute *attr,
 		max = PCI_BRIDGE_RESOURCES;
 
 	for (i = 0; i < max; i++) {
-		struct resource *res =  &pci_dev->resource[i];
+		struct resource *res = pci_resource_n(pci_dev, i);
 		struct resource zerores = {};
 
 		/* For backwards compatibility */
@@ -689,7 +689,7 @@ static ssize_t boot_vga_show(struct device *dev, struct device_attribute *attr,
 		return sysfs_emit(buf, "%u\n", (pdev == vga_dev));
 
 	return sysfs_emit(buf, "%u\n",
-			  !!(pdev->resource[PCI_ROM_RESOURCE].flags &
+			  !!(pci_resource_flags(pdev, PCI_ROM_RESOURCE) &
 			     IORESOURCE_ROM_SHADOW));
 }
 static DEVICE_ATTR_RO(boot_vga);
@@ -1082,7 +1082,7 @@ static int pci_mmap_resource(struct kobject *kobj, const struct bin_attribute *a
 	struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj));
 	int bar = (unsigned long)attr->private;
 	enum pci_mmap_state mmap_type;
-	struct resource *res = &pdev->resource[bar];
+	struct resource *res = pci_resource_n(pdev, bar);
 	int ret;
 
 	ret = security_locked_down(LOCKDOWN_PCI_ACCESS);
@@ -1286,7 +1286,7 @@ static int pci_create_resource_files(struct pci_dev *pdev)
 		retval = pci_create_attr(pdev, i, 0);
 		/* for prefetchable resources, create a WC mappable file */
 		if (!retval && arch_can_pci_mmap_wc() &&
-		    pdev->resource[i].flags & IORESOURCE_PREFETCH)
+		    pci_resource_flags(pdev, i) & IORESOURCE_PREFETCH)
 			retval = pci_create_attr(pdev, i, 1);
 		if (retval) {
 			pci_remove_resource_files(pdev);
-- 
2.54.0

[PATCH v8 02/25] PCI: Add pci_resource_is_io() and pci_resource_is_mem() helpers

[Krzysztof Wilczyński]

Add helpers to check whether a PCI resource is of I/O port or
memory type.  These replace the open-coded pci_resource_flags()
with IORESOURCE_IO and IORESOURCE_MEM pattern used across the
tree.

Suggested-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 include/linux/pci.h | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/include/linux/pci.h b/include/linux/pci.h
index 2c4454583c11..e93fbe6b57fe 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -2300,6 +2300,31 @@ int pci_iobar_pfn(struct pci_dev *pdev, int bar, struct vm_area_struct *vma);
 	CONCATENATE(__pci_dev_for_each_res, COUNT_ARGS(__VA_ARGS__)) 	\
 		    (dev, res, __VA_ARGS__)
 
+/**
+ * pci_resource_is_io - check if a PCI resource is of I/O port type.
+ * @dev: PCI device to check.
+ * @resno: The resource number (BAR index) to check.
+ *
+ * Returns true if the resource type is I/O port.
+ */
+static inline bool pci_resource_is_io(const struct pci_dev *dev, int resno)
+{
+	return resource_type(pci_resource_n(dev, resno)) == IORESOURCE_IO;
+}
+
+/**
+ * pci_resource_is_mem - check if a PCI resource is of memory type.
+ * @dev: PCI device to check.
+ * @resno: The resource number (BAR index) to check.
+ *
+ * Returns true if the resource type is memory, including
+ * prefetchable memory.
+ */
+static inline bool pci_resource_is_mem(const struct pci_dev *dev, int resno)
+{
+	return resource_type(pci_resource_n(dev, resno)) == IORESOURCE_MEM;
+}
+
 /*
  * Similar to the helpers above, these manipulate per-pci_dev
  * driver-specific data.  They are really just a wrapper around
-- 
2.54.0

[PATCH v8 03/25] PCI/sysfs: Only allow supported resource types in I/O and MMIO helpers

[Krzysztof Wilczyński]

Currently, when the sysfs attributes for PCI resources are added
dynamically, the resource access callbacks are only set when the
underlying BAR type matches, using .read and .write for IORESOURCE_IO,
and .mmap for IORESOURCE_MEM or IORESOURCE_IO with arch_can_pci_mmap_io()
support.  As such, when the callback is not set, the operation inherently
fails.

After the conversion to static attributes, visibility callbacks will
control which resource files appear for each BAR, but the callbacks
themselves will always be set.

Thus, add a type check to pci_resource_io() and pci_mmap_resource()
to return -EIO for an unsupported resource type.

Use the new pci_resource_is_io() and pci_resource_is_mem() helpers
for the type checks, replacing the open-coded bitwise flag tests and
also drop the local struct resource pointer in pci_mmap_resource().

Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/pci-sysfs.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 1fbc3daf87cc..2e4e226e78d4 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -1082,20 +1082,24 @@ static int pci_mmap_resource(struct kobject *kobj, const struct bin_attribute *a
 	struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj));
 	int bar = (unsigned long)attr->private;
 	enum pci_mmap_state mmap_type;
-	struct resource *res = pci_resource_n(pdev, bar);
 	int ret;
 
 	ret = security_locked_down(LOCKDOWN_PCI_ACCESS);
 	if (ret)
 		return ret;
 
-	if (res->flags & IORESOURCE_MEM && iomem_is_exclusive(res->start))
+	if (!pci_resource_is_mem(pdev, bar) &&
+	    !(pci_resource_is_io(pdev, bar) && arch_can_pci_mmap_io()))
+		return -EIO;
+
+	if (pci_resource_is_mem(pdev, bar) &&
+	    iomem_is_exclusive(pci_resource_start(pdev, bar)))
 		return -EINVAL;
 
 	if (!pci_mmap_fits(pdev, bar, vma, PCI_MMAP_SYSFS))
 		return -EINVAL;
 
-	mmap_type = res->flags & IORESOURCE_MEM ? pci_mmap_mem : pci_mmap_io;
+	mmap_type = pci_resource_is_mem(pdev, bar) ? pci_mmap_mem : pci_mmap_io;
 
 	return pci_mmap_resource_range(pdev, bar, vma, mmap_type, write_combine);
 }
@@ -1123,6 +1127,9 @@ static ssize_t pci_resource_io(struct file *filp, struct kobject *kobj,
 	int bar = (unsigned long)attr->private;
 	unsigned long port = off;
 
+	if (!pci_resource_is_io(pdev, bar))
+		return -EIO;
+
 	port += pci_resource_start(pdev, bar);
 
 	if (port > pci_resource_end(pdev, bar))
-- 
2.54.0

[PATCH v8 04/25] PCI/sysfs: Split pci_llseek_resource() for device and legacy attributes

[Krzysztof Wilczyński]

Both legacy and resource attributes set .f_mapping = iomem_get_mapping,
so the default generic_file_llseek() would consult iomem_inode for the
file size, which knows nothing about the attribute.  That is why custom
llseek callbacks exist.

Currently, the legacy and resource attributes have .size set at creation
time, as such, using the attr->size is sufficient.  However, the upcoming
static resource attributes will have .size == 0 set, since they are const,
and the .bin_size callback will be used to provide the real size to kernfs
instead.

The legacy attributes operate on a struct pci_bus, not struct pci_dev,
so calling to_pci_dev() on them would be invalid.

Thus, split pci_llseek_resource() into two functions:

  - pci_llseek_resource(), which derives the file size from the BAR
    using pci_resource_len().

  - pci_llseek_resource_legacy(), which uses attr->size directly.

Update the dynamic legacy attribute creation to use the new
pci_llseek_resource_legacy() callback.

The original pci_llseek_resource() was added in commit 24de09c16f97
("PCI: Implement custom llseek for sysfs resource entries").

Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/pci-sysfs.c | 21 +++++++++++++++++----
 1 file changed, 17 insertions(+), 4 deletions(-)

diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 2e4e226e78d4..2280b7edb41f 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -881,13 +881,26 @@ static const struct attribute_group pci_dev_config_attr_group = {
  * llseek operation for mmappable PCI resources.
  * May be left unused if the arch doesn't provide them.
  */
+static __maybe_unused loff_t
+pci_llseek_resource_legacy(struct file *filep,
+			   struct kobject *kobj __always_unused,
+			   const struct bin_attribute *attr,
+			   loff_t offset, int whence)
+{
+	return fixed_size_llseek(filep, offset, whence, attr->size);
+}
+
 static __maybe_unused loff_t
 pci_llseek_resource(struct file *filep,
-		    struct kobject *kobj __always_unused,
+		    struct kobject *kobj,
 		    const struct bin_attribute *attr,
 		    loff_t offset, int whence)
 {
-	return fixed_size_llseek(filep, offset, whence, attr->size);
+	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
@@ -1022,7 +1035,7 @@ void pci_create_legacy_files(struct pci_bus *b)
 	b->legacy_io->read = pci_read_legacy_io;
 	b->legacy_io->write = pci_write_legacy_io;
 	/* See pci_create_attr() for motivation */
-	b->legacy_io->llseek = pci_llseek_resource;
+	b->legacy_io->llseek = pci_llseek_resource_legacy;
 	b->legacy_io->mmap = pci_mmap_legacy_io;
 	b->legacy_io->f_mapping = iomem_get_mapping;
 	pci_adjust_legacy_attr(b, pci_mmap_io);
@@ -1038,7 +1051,7 @@ void pci_create_legacy_files(struct pci_bus *b)
 	b->legacy_mem->attr.mode = 0600;
 	b->legacy_mem->mmap = pci_mmap_legacy_mem;
 	/* See pci_create_attr() for motivation */
-	b->legacy_mem->llseek = pci_llseek_resource;
+	b->legacy_mem->llseek = pci_llseek_resource_legacy;
 	b->legacy_mem->f_mapping = iomem_get_mapping;
 	pci_adjust_legacy_attr(b, pci_mmap_mem);
 	error = device_create_bin_file(&b->dev, b->legacy_mem);
-- 
2.54.0

[PATCH v8 05/25] PCI/sysfs: Add CAP_SYS_ADMIN check to __resource_resize_store()

[Krzysztof Wilczyński]

Currently, the __resource_resize_store() allows writing to the
resourceN_resize sysfs attribute to change a BAR's size without
checking for capabilities, currently relying only on the file
access check.

Resizing a BAR modifies PCI device configuration and can disrupt
active drivers.  After the upcoming conversion to static attributes,
it will also trigger resource file updates via sysfs_update_groups().

Thus, add a CAP_SYS_ADMIN check to prevent unprivileged users from
performing BAR resize operations.

Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/pci-sysfs.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 2280b7edb41f..dac780597727 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -1596,6 +1596,9 @@ static ssize_t __resource_resize_store(struct device *dev, int n,
 	int ret;
 	u16 cmd;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	if (kstrtoul(buf, 0, &size) < 0)
 		return -EINVAL;
 
-- 
2.54.0

[PATCH v8 06/25] PCI/sysfs: Add static PCI resource attribute macros

[Krzysztof Wilczyński]

Add three macros for declaring static binary attributes for PCI
resource files:

  - pci_dev_resource_io_attr(), for I/O BAR resources (read/write)
  - pci_dev_resource_uc_attr(), for memory BAR resources (mmap uncached)
  - pci_dev_resource_wc_attr(), for write-combine resources (mmap WC)

Each macro only sets the callbacks its resource type needs.  The I/O
macro conditionally includes mmap support via __PCI_RESOURCE_IO_MMAP_ATTRS
on architectures where arch_can_pci_mmap_io() is true at compile time
(such as PowerPC, SPARC, and Xtensa).

Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/pci-sysfs.c | 41 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 41 insertions(+)

diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index dac780597727..793d149fe157 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -1197,6 +1197,47 @@ static ssize_t pci_write_resource_io(struct file *filp, struct kobject *kobj,
 	return pci_resource_io(filp, kobj, attr, buf, off, count, true);
 }
 
+/*
+ * 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.
+ */
+#if arch_can_pci_mmap_io()
+# define __PCI_RESOURCE_IO_MMAP_ATTRS	\
+	.f_mapping = iomem_get_mapping,	\
+	.llseek = pci_llseek_resource,	\
+	.mmap = pci_mmap_resource_uc,
+#else
+# define __PCI_RESOURCE_IO_MMAP_ATTRS
+#endif
+
+#define pci_dev_resource_io_attr(_bar)					\
+static const struct bin_attribute pci_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,					\
+	__PCI_RESOURCE_IO_MMAP_ATTRS					\
+}
+
+#define pci_dev_resource_uc_attr(_bar)					\
+static const struct bin_attribute pci_dev_resource##_bar##_uc_attr = {	\
+	.attr = { .name = "resource" __stringify(_bar), .mode = 0600 },	\
+	.private = (void *)(unsigned long)(_bar),			\
+	.f_mapping = iomem_get_mapping,					\
+	.llseek = pci_llseek_resource,					\
+	.mmap = pci_mmap_resource_uc,					\
+}
+
+#define pci_dev_resource_wc_attr(_bar)						\
+static const struct bin_attribute pci_dev_resource##_bar##_wc_attr = {		\
+	.attr = { .name = "resource" __stringify(_bar) "_wc", .mode = 0600 },	\
+	.private = (void *)(unsigned long)(_bar),				\
+	.f_mapping = iomem_get_mapping,						\
+	.llseek = pci_llseek_resource,						\
+	.mmap = pci_mmap_resource_wc,						\
+}
+
 /**
  * pci_remove_resource_files - cleanup resource files
  * @pdev: dev to cleanup
-- 
2.54.0

[PATCH v8 07/25] PCI/sysfs: Convert PCI resource files to static attributes

[Krzysztof Wilczyński]

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 "duplicate filename" warnings and boot panics when both
paths race on the same device.

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.

Thus, 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").

Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/pci-sysfs.c | 285 +++++++++++++++++++++-------------------
 include/linux/pci.h     |   2 -
 2 files changed, 152 insertions(+), 135 deletions(-)

diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 793d149fe157..615bbee1a1c8 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 pci_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 pci_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;
-
-		res_attr = pdev->res_attr[i];
-		if (res_attr) {
-			sysfs_remove_bin_file(&pdev->dev.kobj, res_attr);
-			kfree(res_attr);
-		}
-
-		res_attr = pdev->res_attr_wc[i];
-		if (res_attr) {
-			sysfs_remove_bin_file(&pdev->dev.kobj, res_attr);
-			kfree(res_attr);
-		}
-	}
-}
-
-static int pci_create_attr(struct pci_dev *pdev, int num, int write_combine)
-{
-	/* allocate attribute structure, piggyback attribute name */
-	int name_len = write_combine ? 13 : 10;
-	struct bin_attribute *res_attr;
-	char *res_attr_name;
-	int retval;
-
-	res_attr = kzalloc(sizeof(*res_attr) + name_len, GFP_ATOMIC);
-	if (!res_attr)
-		return -ENOMEM;
-
-	res_attr_name = (char *)(res_attr + 1);
-
-	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;
-	}
-
-	if (write_combine)
-		pdev->res_attr_wc[num] = res_attr;
-	else
-		pdev->res_attr[num] = res_attr;
-
-	return 0;
-}
-
-/**
- * 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;
-
-	/* 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++) {
+	if (!pci_resource_len(pdev, bar))
+		return 0;
 
-		/* skip empty resources */
-		if (!pci_resource_len(pdev, i))
-			continue;
+	if ((pci_resource_flags(pdev, bar) & flags) != flags)
+		return 0;
 
-		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;
+	if (write_combine && !arch_can_pci_mmap_wc())
+		return 0;
+
+	return a->attr.mode;
 }
-#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 umode_t pci_dev_resource_io_is_visible(struct kobject *kobj,
+					      const struct bin_attribute *a,
+					      int n)
+{
+	return __pci_resource_attr_is_visible(kobj, a, n, false,
+					      IORESOURCE_IO);
+}
+
+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);
+}
+
+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);
+}
+
+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));
+
+	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[] = {
+	&pci_dev_resource0_io_attr,
+	&pci_dev_resource1_io_attr,
+	&pci_dev_resource2_io_attr,
+	&pci_dev_resource3_io_attr,
+	&pci_dev_resource4_io_attr,
+	&pci_dev_resource5_io_attr,
+	NULL,
+};
+
+static const struct bin_attribute *const pci_dev_resource_uc_attrs[] = {
+	&pci_dev_resource0_uc_attr,
+	&pci_dev_resource1_uc_attr,
+	&pci_dev_resource2_uc_attr,
+	&pci_dev_resource3_uc_attr,
+	&pci_dev_resource4_uc_attr,
+	&pci_dev_resource5_uc_attr,
+	NULL,
+};
+
+static const struct bin_attribute *const pci_dev_resource_wc_attrs[] = {
+	&pci_dev_resource0_wc_attr,
+	&pci_dev_resource1_wc_attr,
+	&pci_dev_resource2_wc_attr,
+	&pci_dev_resource3_wc_attr,
+	&pci_dev_resource4_wc_attr,
+	&pci_dev_resource5_wc_attr,
+	NULL,
+};
+
+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,
+};
+
+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,
+};
+
+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,
+};
+
+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);
-- 
2.54.0

[PATCH v8 08/25] PCI/sysfs: Warn about BAR resize failure in __resource_resize_store()

[Krzysztof Wilczyński]

Add a pci_warn() to __resource_resize_store(), so that BAR resize
failures are visible to the user, which can help troubleshoot any
potential resource resize issues.

While at it, rename the resource_resize_is_visible() to
resource_resize_attr_is_visible() along with the corresponding
group variable to align with the naming convention used by the
resource attribute groups.

Also, change the order of pci_dev_groups[] such that the resize
group is now located alongside the other resource groups.

Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/pci-sysfs.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 615bbee1a1c8..b8b7fb809c69 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -1679,6 +1679,9 @@ static ssize_t __resource_resize_store(struct device *dev, int n,
 	sysfs_remove_groups(&pdev->dev.kobj, pci_dev_resource_attr_groups);
 
 	ret = pci_resize_resource(pdev, n, size, 0);
+	if (ret)
+		pci_warn(pdev, "Failed to resize BAR %d: %pe\n",
+			 n, ERR_PTR(ret));
 
 	pci_assign_unassigned_bus_resources(bus);
 
@@ -1726,7 +1729,7 @@ static struct attribute *resource_resize_attrs[] = {
 	NULL,
 };
 
-static umode_t resource_resize_is_visible(struct kobject *kobj,
+static umode_t resource_resize_attr_is_visible(struct kobject *kobj,
 					  struct attribute *a, int n)
 {
 	struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj));
@@ -1734,9 +1737,9 @@ static umode_t resource_resize_is_visible(struct kobject *kobj,
 	return pci_rebar_get_current_size(pdev, n) < 0 ? 0 : a->mode;
 }
 
-static const struct attribute_group pci_dev_resource_resize_group = {
+static const struct attribute_group pci_dev_resource_resize_attr_group = {
 	.attrs = resource_resize_attrs,
-	.is_visible = resource_resize_is_visible,
+	.is_visible = resource_resize_attr_is_visible,
 };
 
 int __must_check pci_create_sysfs_dev_files(struct pci_dev *pdev)
@@ -1857,6 +1860,7 @@ const struct attribute_group *pci_dev_groups[] = {
 	&pci_dev_resource_uc_attr_group,
 	&pci_dev_resource_wc_attr_group,
 #endif
+	&pci_dev_resource_resize_attr_group,
 	&pci_dev_config_attr_group,
 	&pci_dev_rom_attr_group,
 	&pci_dev_reset_attr_group,
@@ -1868,7 +1872,6 @@ const struct attribute_group *pci_dev_groups[] = {
 #ifdef CONFIG_ACPI
 	&pci_dev_acpi_attr_group,
 #endif
-	&pci_dev_resource_resize_group,
 	ARCH_PCI_DEV_GROUPS
 	NULL,
 };
-- 
2.54.0

[PATCH v8 09/25] PCI/sysfs: Add stubs for pci_{create,remove}_sysfs_dev_files()

[Krzysztof Wilczyński]

On platforms with HAVE_PCI_MMAP or ARCH_GENERIC_PCI_MMAP_RESOURCE,
resource files are now handled by static attribute groups registered
via pci_dev_groups[].

Thus, the pci_create_sysfs_dev_files() and pci_remove_sysfs_dev_files()
can now be stubbed out, as the dynamic resource file creation is no
longer needed.

Also, simplify pci_sysfs_init() on these platforms to only iterate
buses for legacy attributes creation, skipping the per-device loop.

Move the __weak stubs for pci_create_resource_files() and
pci_remove_resource_files() into the #else branch since only platforms
without HAVE_PCI_MMAP (such as Alpha architecture) still need them.
Guard the res_attr[] and res_attr_wc[] fields in struct pci_dev the
same way.

Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/pci-sysfs.c | 15 ++++++++++++---
 include/linux/pci.h     |  4 ++++
 2 files changed, 16 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index b8b7fb809c69..208ec7057b50 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -1370,10 +1370,9 @@ static const struct attribute_group *pci_dev_resource_attr_groups[] = {
 };
 #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) { }
+#endif
 
 /**
  * pci_write_rom - used to enable access to the PCI ROM display
@@ -1742,6 +1741,10 @@ static const struct attribute_group pci_dev_resource_resize_attr_group = {
 	.is_visible = resource_resize_attr_is_visible,
 };
 
+#if defined(HAVE_PCI_MMAP) || defined(ARCH_GENERIC_PCI_MMAP_RESOURCE)
+int pci_create_sysfs_dev_files(struct pci_dev *pdev) { return 0; }
+void pci_remove_sysfs_dev_files(struct pci_dev *pdev) { }
+#else
 int __must_check pci_create_sysfs_dev_files(struct pci_dev *pdev)
 {
 	if (!sysfs_initialized)
@@ -1763,9 +1766,15 @@ void pci_remove_sysfs_dev_files(struct pci_dev *pdev)
 
 	pci_remove_resource_files(pdev);
 }
+#endif
 
 static int __init pci_sysfs_init(void)
 {
+#if defined(HAVE_PCI_MMAP) || defined(ARCH_GENERIC_PCI_MMAP_RESOURCE)
+	struct pci_bus *pbus = NULL;
+
+	sysfs_initialized = 1;
+#else
 	struct pci_dev *pdev = NULL;
 	struct pci_bus *pbus = NULL;
 	int retval;
@@ -1778,7 +1787,7 @@ static int __init pci_sysfs_init(void)
 			return retval;
 		}
 	}
-
+#endif
 	while ((pbus = pci_find_next_bus(pbus)))
 		pci_create_legacy_files(pbus);
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 974605c9fce2..b998a56f6010 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -515,8 +515,10 @@ struct pci_dev {
 	spinlock_t	pcie_cap_lock;		/* Protects RMW ops in capability accessors */
 	u32		saved_config_space[16]; /* Config space saved at suspend time */
 	struct hlist_head saved_cap_space;
+#if !defined(HAVE_PCI_MMAP) && !defined(ARCH_GENERIC_PCI_MMAP_RESOURCE)
 	struct bin_attribute *res_attr[DEVICE_COUNT_RESOURCE]; /* sysfs file for resources */
 	struct bin_attribute *res_attr_wc[DEVICE_COUNT_RESOURCE]; /* sysfs file for WC mapping of resources */
+#endif
 
 #ifdef CONFIG_HOTPLUG_PCI_PCIE
 	unsigned int	broken_cmd_compl:1;	/* No compl for some cmds */
@@ -2531,8 +2533,10 @@ 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);
-- 
2.54.0

[PATCH v8 10/25] PCI/sysfs: Limit pci_sysfs_init() late_initcall compile scope

[Krzysztof Wilczyński]

Currently, pci_sysfs_init() and sysfs_initialized compile
unconditionally, even on platforms where static attribute
groups handle all resource file creation.

Thus, place them behind a new HAVE_PCI_SYSFS_INIT macro,
especially as the late_initcall is only needed when:

  - HAVE_PCI_LEGACY is set, to iterate buses and create legacy
    I/O and memory files.

  - Neither HAVE_PCI_MMAP nor ARCH_GENERIC_PCI_MMAP_RESOURCE is
    set, to iterate devices and create resource files via the
    __weak pci_create_resource_files() stub override (this is
    how the Alpha architecture handles this currently).

On most systems both conditions are false and the entire
late_initcall compiles away.

Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/pci-sysfs.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 208ec7057b50..57d89e12bfec 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -37,7 +37,14 @@
 #define ARCH_PCI_DEV_GROUPS
 #endif
 
+#if defined(HAVE_PCI_LEGACY) || \
+	!defined(HAVE_PCI_MMAP) && !defined(ARCH_GENERIC_PCI_MMAP_RESOURCE)
+#define HAVE_PCI_SYSFS_INIT
+#endif
+
+#ifdef HAVE_PCI_SYSFS_INIT
 static int sysfs_initialized;	/* = 0 */
+#endif
 
 /* show configuration fields */
 #define pci_config_attr(field, format_string)				\
@@ -1768,6 +1775,7 @@ void pci_remove_sysfs_dev_files(struct pci_dev *pdev)
 }
 #endif
 
+#ifdef HAVE_PCI_SYSFS_INIT
 static int __init pci_sysfs_init(void)
 {
 #if defined(HAVE_PCI_MMAP) || defined(ARCH_GENERIC_PCI_MMAP_RESOURCE)
@@ -1794,6 +1802,7 @@ static int __init pci_sysfs_init(void)
 	return 0;
 }
 late_initcall(pci_sysfs_init);
+#endif
 
 static struct attribute *pci_dev_dev_attrs[] = {
 	&dev_attr_boot_vga.attr,
-- 
2.54.0

[PATCH v8 11/25] alpha/PCI: Add security_locked_down() check to pci_mmap_resource()

[Krzysztof Wilczyński]

Currently, Alpha's pci_mmap_resource() does not check
security_locked_down(LOCKDOWN_PCI_ACCESS) before allowing
userspace to mmap PCI BARs.

The generic version has had this check since commit eb627e17727e
("PCI: Lock down BAR access when the kernel is locked down") to
prevent DMA attacks when the kernel is locked down.

Add the same check to Alpha's pci_mmap_resource().

Fixes: eb627e17727e ("PCI: Lock down BAR access when the kernel is locked down")
Tested-by: Magnus Lindholm <linmag7@gmail.com>
Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Acked-by: Magnus Lindholm <linmag7@gmail.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 arch/alpha/kernel/pci-sysfs.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/alpha/kernel/pci-sysfs.c b/arch/alpha/kernel/pci-sysfs.c
index 3048758304b5..2324720c3e83 100644
--- a/arch/alpha/kernel/pci-sysfs.c
+++ b/arch/alpha/kernel/pci-sysfs.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/security.h>
 #include <linux/stat.h>
 #include <linux/slab.h>
 #include <linux/pci.h>
@@ -71,7 +72,11 @@ static int pci_mmap_resource(struct kobject *kobj,
 	struct resource *res = attr->private;
 	enum pci_mmap_state mmap_type;
 	struct pci_bus_region bar;
-	int i;
+	int i, ret;
+
+	ret = security_locked_down(LOCKDOWN_PCI_ACCESS);
+	if (ret)
+		return ret;
 
 	for (i = 0; i < PCI_STD_NUM_BARS; i++)
 		if (res == &pdev->resource[i])
-- 
2.54.0

[PATCH v8 12/25] alpha/PCI: Use BAR index in sysfs attr->private instead of resource pointer

[Krzysztof Wilczyński]

Currently, Alpha's pci_create_one_attr() stores a resource pointer in
attr->private, and pci_mmap_resource() loops through all BARs to find
the matching index.

Thus, store the BAR index directly in attr->private and retrieve the
resource via pci_resource_n().  This eliminates the loop and aligns
with the convention used by the generic PCI sysfs code.

The PCI core change was first added in the commit dca40b186b75 ("PCI:
Use BAR index in sysfs attr->private instead of resource pointer").

Tested-by: Magnus Lindholm <linmag7@gmail.com>
Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Acked-by: Magnus Lindholm <linmag7@gmail.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 arch/alpha/kernel/pci-sysfs.c | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/arch/alpha/kernel/pci-sysfs.c b/arch/alpha/kernel/pci-sysfs.c
index 2324720c3e83..2330ab84d59c 100644
--- a/arch/alpha/kernel/pci-sysfs.c
+++ b/arch/alpha/kernel/pci-sysfs.c
@@ -69,25 +69,20 @@ static int pci_mmap_resource(struct kobject *kobj,
 			     struct vm_area_struct *vma, int sparse)
 {
 	struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj));
-	struct resource *res = attr->private;
+	int barno = (unsigned long)attr->private;
+	struct resource *res = pci_resource_n(pdev, barno);
 	enum pci_mmap_state mmap_type;
 	struct pci_bus_region bar;
-	int i, ret;
+	int ret;
 
 	ret = security_locked_down(LOCKDOWN_PCI_ACCESS);
 	if (ret)
 		return ret;
 
-	for (i = 0; i < PCI_STD_NUM_BARS; i++)
-		if (res == &pdev->resource[i])
-			break;
-	if (i >= PCI_STD_NUM_BARS)
-		return -ENODEV;
-
 	if (res->flags & IORESOURCE_MEM && iomem_is_exclusive(res->start))
 		return -EINVAL;
 
-	if (!__pci_mmap_fits(pdev, i, vma, sparse))
+	if (!__pci_mmap_fits(pdev, barno, vma, sparse))
 		return -EINVAL;
 
 	pcibios_resource_to_bus(pdev->bus, &bar, res);
@@ -170,7 +165,7 @@ static int pci_create_one_attr(struct pci_dev *pdev, int num, char *name,
 	res_attr->attr.name = name;
 	res_attr->attr.mode = S_IRUSR | S_IWUSR;
 	res_attr->size = sparse ? size << 5 : size;
-	res_attr->private = &pdev->resource[num];
+	res_attr->private = (void *)(unsigned long)num;
 	return sysfs_create_bin_file(&pdev->dev.kobj, res_attr);
 }
 
-- 
2.54.0

[PATCH v8 13/25] alpha/PCI: Use PCI resource accessor macros

[Krzysztof Wilczyński]

Replace direct pdev->resource[] accesses with pci_resource_n(),
and open-coded res->flags type checks with pci_resource_is_mem()
and pci_resource_start() helpers.

While at it, move the pci_resource_n() call directly into
pcibios_resource_to_bus() and drop the local struct
resource pointer.

No functional changes intended.

Tested-by: Magnus Lindholm <linmag7@gmail.com>
Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Acked-by: Magnus Lindholm <linmag7@gmail.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 arch/alpha/kernel/pci-sysfs.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/alpha/kernel/pci-sysfs.c b/arch/alpha/kernel/pci-sysfs.c
index 2330ab84d59c..5c29f1d2821c 100644
--- a/arch/alpha/kernel/pci-sysfs.c
+++ b/arch/alpha/kernel/pci-sysfs.c
@@ -70,7 +70,6 @@ static int pci_mmap_resource(struct kobject *kobj,
 {
 	struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj));
 	int barno = (unsigned long)attr->private;
-	struct resource *res = pci_resource_n(pdev, barno);
 	enum pci_mmap_state mmap_type;
 	struct pci_bus_region bar;
 	int ret;
@@ -79,15 +78,16 @@ static int pci_mmap_resource(struct kobject *kobj,
 	if (ret)
 		return ret;
 
-	if (res->flags & IORESOURCE_MEM && iomem_is_exclusive(res->start))
+	if (pci_resource_is_mem(pdev, barno) &&
+	    iomem_is_exclusive(pci_resource_start(pdev, barno)))
 		return -EINVAL;
 
 	if (!__pci_mmap_fits(pdev, barno, vma, sparse))
 		return -EINVAL;
 
-	pcibios_resource_to_bus(pdev->bus, &bar, res);
+	pcibios_resource_to_bus(pdev->bus, &bar, pci_resource_n(pdev, barno));
 	vma->vm_pgoff += bar.start >> (PAGE_SHIFT - (sparse ? 5 : 0));
-	mmap_type = res->flags & IORESOURCE_MEM ? pci_mmap_mem : pci_mmap_io;
+	mmap_type = pci_resource_is_mem(pdev, barno) ? pci_mmap_mem : pci_mmap_io;
 
 	return hose_mmap_page_range(pdev->sysdata, vma, mmap_type, sparse);
 }
@@ -141,7 +141,7 @@ static int sparse_mem_mmap_fits(struct pci_dev *pdev, int num)
 	long dense_offset;
 	unsigned long sparse_size;
 
-	pcibios_resource_to_bus(pdev->bus, &bar, &pdev->resource[num]);
+	pcibios_resource_to_bus(pdev->bus, &bar, pci_resource_n(pdev, num));
 
 	/* All core logic chips have 4G sparse address space, except
 	   CIA which has 16G (see xxx_SPARSE_MEM and xxx_DENSE_MEM
@@ -181,7 +181,7 @@ static int pci_create_attr(struct pci_dev *pdev, int num)
 	suffix = "";	/* Assume bwx machine, normal resourceN files. */
 	nlen1 = 10;
 
-	if (pdev->resource[num].flags & IORESOURCE_MEM) {
+	if (pci_resource_is_mem(pdev, num)) {
 		sparse_base = hose->sparse_mem_base;
 		dense_base = hose->dense_mem_base;
 		if (sparse_base && !sparse_mem_mmap_fits(pdev, num)) {
-- 
2.54.0

[PATCH v8 14/25] alpha/PCI: Fix __pci_mmap_fits() overflow for zero-length BARs

[Krzysztof Wilczyński]

Currently, __pci_mmap_fits() computes the BAR size using
pci_resource_len() - 1, which wraps to a large value when the
BAR length is zero, causing the bounds check to incorrectly
succeed.

Thus, add an early return for empty resources.

Fixes: 10a0ef39fbd1 ("PCI/alpha: pci sysfs resources")
Tested-by: Magnus Lindholm <linmag7@gmail.com>
Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Acked-by: Magnus Lindholm <linmag7@gmail.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 arch/alpha/kernel/pci-sysfs.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/alpha/kernel/pci-sysfs.c b/arch/alpha/kernel/pci-sysfs.c
index 5c29f1d2821c..8802f955256e 100644
--- a/arch/alpha/kernel/pci-sysfs.c
+++ b/arch/alpha/kernel/pci-sysfs.c
@@ -37,12 +37,16 @@ static int hose_mmap_page_range(struct pci_controller *hose,
 static int __pci_mmap_fits(struct pci_dev *pdev, int num,
 			   struct vm_area_struct *vma, int sparse)
 {
+	resource_size_t len = pci_resource_len(pdev, num);
 	unsigned long nr, start, size;
 	int shift = sparse ? 5 : 0;
 
+	if (!len)
+		return 0;
+
 	nr = vma_pages(vma);
 	start = vma->vm_pgoff;
-	size = ((pci_resource_len(pdev, num) - 1) >> (PAGE_SHIFT - shift)) + 1;
+	size = ((len - 1) >> (PAGE_SHIFT - shift)) + 1;
 
 	if (start < size && size - start >= nr)
 		return 1;
-- 
2.54.0

[PATCH v8 15/25] alpha/PCI: Remove WARN from __pci_mmap_fits() and __legacy_mmap_fits()

[Krzysztof Wilczyński]

Remove the WARN() that fires when userspace attempts to mmap beyond
the BAR bounds.  The check still returns 0 to reject the mapping,
but the warning is excessive for normal operation.

A similar warning was removed from the PCI core in the commit
3b519e4ea618 ("PCI: fix size checks for mmap() on /proc/bus/pci files").

Tested-by: Magnus Lindholm <linmag7@gmail.com>
Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Acked-by: Magnus Lindholm <linmag7@gmail.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 arch/alpha/kernel/pci-sysfs.c | 23 +++++------------------
 1 file changed, 5 insertions(+), 18 deletions(-)

diff --git a/arch/alpha/kernel/pci-sysfs.c b/arch/alpha/kernel/pci-sysfs.c
index 8802f955256e..6cf688621ea9 100644
--- a/arch/alpha/kernel/pci-sysfs.c
+++ b/arch/alpha/kernel/pci-sysfs.c
@@ -48,13 +48,7 @@ static int __pci_mmap_fits(struct pci_dev *pdev, int num,
 	start = vma->vm_pgoff;
 	size = ((len - 1) >> (PAGE_SHIFT - shift)) + 1;
 
-	if (start < size && size - start >= nr)
-		return 1;
-	WARN(1, "process \"%s\" tried to map%s 0x%08lx-0x%08lx on %s BAR %d "
-		"(size 0x%08lx)\n",
-		current->comm, sparse ? " sparse" : "", start, start + nr,
-		pci_name(pdev), num, size);
-	return 0;
+	return start < size && size - start >= nr;
 }
 
 /**
@@ -257,9 +251,8 @@ int pci_create_resource_files(struct pci_dev *pdev)
 
 /* Legacy I/O bus mapping stuff. */
 
-static int __legacy_mmap_fits(struct pci_controller *hose,
-			      struct vm_area_struct *vma,
-			      unsigned long res_size, int sparse)
+static int __legacy_mmap_fits(struct vm_area_struct *vma,
+			      unsigned long res_size)
 {
 	unsigned long nr, start, size;
 
@@ -267,13 +260,7 @@ static int __legacy_mmap_fits(struct pci_controller *hose,
 	start = vma->vm_pgoff;
 	size = ((res_size - 1) >> PAGE_SHIFT) + 1;
 
-	if (start < size && size - start >= nr)
-		return 1;
-	WARN(1, "process \"%s\" tried to map%s 0x%08lx-0x%08lx on hose %d "
-		"(size 0x%08lx)\n",
-		current->comm, sparse ? " sparse" : "", start, start + nr,
-		hose->index, size);
-	return 0;
+	return start < size && size - start >= nr;
 }
 
 static inline int has_sparse(struct pci_controller *hose,
@@ -296,7 +283,7 @@ int pci_mmap_legacy_page_range(struct pci_bus *bus, struct vm_area_struct *vma,
 
 	res_size = (mmap_type == pci_mmap_mem) ? bus->legacy_mem->size :
 						 bus->legacy_io->size;
-	if (!__legacy_mmap_fits(hose, vma, res_size, sparse))
+	if (!__legacy_mmap_fits(vma, res_size))
 		return -EINVAL;
 
 	return hose_mmap_page_range(hose, vma, mmap_type, sparse);
-- 
2.54.0

[PATCH v8 16/25] alpha/PCI: Add static PCI resource attribute macros

[Krzysztof Wilczyński]

Add macros for declaring static binary attributes for Alpha's PCI
resource files:

  - pci_dev_resource_attr(),        for dense/BWX systems (mmap dense)
  - pci_dev_resource_sparse_attr(), for sparse systems (mmap sparse)
  - pci_dev_resource_dense_attr(),  for dense companion files (mmap dense)

Each macro creates a const bin_attribute with the BAR index stored in
the .private property and the appropriate .mmap callback.

Tested-by: Magnus Lindholm <linmag7@gmail.com>
Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Acked-by: Magnus Lindholm <linmag7@gmail.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 arch/alpha/kernel/pci-sysfs.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/arch/alpha/kernel/pci-sysfs.c b/arch/alpha/kernel/pci-sysfs.c
index 6cf688621ea9..650f7795cc40 100644
--- a/arch/alpha/kernel/pci-sysfs.c
+++ b/arch/alpha/kernel/pci-sysfs.c
@@ -104,6 +104,26 @@ static int pci_mmap_resource_dense(struct file *filp, struct kobject *kobj,
 	return pci_mmap_resource(kobj, attr, vma, 0);
 }
 
+#define __pci_dev_resource_attr(_suffix, _bar, _name, _mmap)	\
+static const struct bin_attribute				\
+pci_dev_resource##_bar##_suffix##_attr = {			\
+	.attr = { .name = __stringify(_name), .mode = 0600 },	\
+	.private = (void *)(unsigned long)(_bar),		\
+	.mmap = (_mmap),					\
+}
+
+#define pci_dev_resource_attr(_bar)			\
+	__pci_dev_resource_attr(, _bar, resource##_bar,	\
+				pci_mmap_resource_dense)
+
+#define pci_dev_resource_sparse_attr(_bar)				\
+	__pci_dev_resource_attr(_sparse, _bar, resource##_bar##_sparse,	\
+				pci_mmap_resource_sparse)
+
+#define pci_dev_resource_dense_attr(_bar)				\
+	__pci_dev_resource_attr(_dense, _bar, resource##_bar##_dense,	\
+				pci_mmap_resource_dense)
+
 /**
  * pci_remove_resource_files - cleanup resource files
  * @pdev: pci_dev to cleanup
-- 
2.54.0

[PATCH v8 17/25] alpha/PCI: Convert resource files to static attributes

[Krzysztof Wilczyński]

Currently, Alpha's PCI resource files (resourceN, resourceN_sparse,
resourceN_dense) are dynamically created by pci_create_resource_files(),
which overrides the generic __weak implementation.  The current code
allocates bin_attributes at runtime and manages them via the res_attr[]
and res_attr_wc[] fields in struct pci_dev.

Thus, convert to static const attributes with three attribute groups
(plain, sparse, dense), each with an .is_bin_visible callback that
checks resource length, has_sparse(), and sparse_mem_mmap_fits().  A
.bin_size callback provides the resource size to the kernfs node, with
the sparse variant shifting by 5 bits for byte-level addressing.

Register the groups via ARCH_PCI_DEV_GROUPS so the driver model handles
creation and removal automatically.

Use the new pci_resource_is_mem() helper for the type check, replacing
the open-coded bitwise flag test.

Finally, remove pci_create_resource_files(), pci_remove_resource_files(),
pci_create_attr(), and pci_create_one_attr() which are no longer needed.

Tested-by: Magnus Lindholm <linmag7@gmail.com>
Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Acked-by: Magnus Lindholm <linmag7@gmail.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 arch/alpha/include/asm/pci.h  |   9 ++
 arch/alpha/kernel/pci-sysfs.c | 291 +++++++++++++++++++---------------
 2 files changed, 172 insertions(+), 128 deletions(-)

diff --git a/arch/alpha/include/asm/pci.h b/arch/alpha/include/asm/pci.h
index 6c04fcbdc8ed..ef19295f2e33 100644
--- a/arch/alpha/include/asm/pci.h
+++ b/arch/alpha/include/asm/pci.h
@@ -88,4 +88,13 @@ extern void pci_adjust_legacy_attr(struct pci_bus *bus,
 				   enum pci_mmap_state mmap_type);
 #define HAVE_PCI_LEGACY	1
 
+extern const struct attribute_group pci_dev_resource_attr_group;
+extern const struct attribute_group pci_dev_resource_sparse_attr_group;
+extern const struct attribute_group pci_dev_resource_dense_attr_group;
+
+#define ARCH_PCI_DEV_GROUPS		\
+	&pci_dev_resource_attr_group,	\
+	&pci_dev_resource_sparse_attr_group,	\
+	&pci_dev_resource_dense_attr_group,
+
 #endif /* __ALPHA_PCI_H */
diff --git a/arch/alpha/kernel/pci-sysfs.c b/arch/alpha/kernel/pci-sysfs.c
index 650f7795cc40..ae448a2e40c5 100644
--- a/arch/alpha/kernel/pci-sysfs.c
+++ b/arch/alpha/kernel/pci-sysfs.c
@@ -12,8 +12,6 @@
 
 #include <linux/sched.h>
 #include <linux/security.h>
-#include <linux/stat.h>
-#include <linux/slab.h>
 #include <linux/pci.h>
 
 static int hose_mmap_page_range(struct pci_controller *hose,
@@ -124,34 +122,6 @@ pci_dev_resource##_bar##_suffix##_attr = {			\
 	__pci_dev_resource_attr(_dense, _bar, resource##_bar##_dense,	\
 				pci_mmap_resource_dense)
 
-/**
- * pci_remove_resource_files - cleanup resource files
- * @pdev: pci_dev to cleanup
- *
- * If we created resource files for @dev, remove them from sysfs and
- * free their resources.
- */
-void pci_remove_resource_files(struct pci_dev *pdev)
-{
-	int i;
-
-	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
-		struct bin_attribute *res_attr;
-
-		res_attr = pdev->res_attr[i];
-		if (res_attr) {
-			sysfs_remove_bin_file(&pdev->dev.kobj, res_attr);
-			kfree(res_attr);
-		}
-
-		res_attr = pdev->res_attr_wc[i];
-		if (res_attr) {
-			sysfs_remove_bin_file(&pdev->dev.kobj, res_attr);
-			kfree(res_attr);
-		}
-	}
-}
-
 static int sparse_mem_mmap_fits(struct pci_dev *pdev, int num)
 {
 	struct pci_bus_region bar;
@@ -171,104 +141,6 @@ static int sparse_mem_mmap_fits(struct pci_dev *pdev, int num)
 	return bar.end < sparse_size;
 }
 
-static int pci_create_one_attr(struct pci_dev *pdev, int num, char *name,
-			       char *suffix, struct bin_attribute *res_attr,
-			       unsigned long sparse)
-{
-	size_t size = pci_resource_len(pdev, num);
-
-	sprintf(name, "resource%d%s", num, suffix);
-	res_attr->mmap = sparse ? pci_mmap_resource_sparse :
-				  pci_mmap_resource_dense;
-	res_attr->attr.name = name;
-	res_attr->attr.mode = S_IRUSR | S_IWUSR;
-	res_attr->size = sparse ? size << 5 : size;
-	res_attr->private = (void *)(unsigned long)num;
-	return sysfs_create_bin_file(&pdev->dev.kobj, res_attr);
-}
-
-static int pci_create_attr(struct pci_dev *pdev, int num)
-{
-	/* allocate attribute structure, piggyback attribute name */
-	int retval, nlen1, nlen2 = 0, res_count = 1;
-	unsigned long sparse_base, dense_base;
-	struct bin_attribute *attr;
-	struct pci_controller *hose = pdev->sysdata;
-	char *suffix, *attr_name;
-
-	suffix = "";	/* Assume bwx machine, normal resourceN files. */
-	nlen1 = 10;
-
-	if (pci_resource_is_mem(pdev, num)) {
-		sparse_base = hose->sparse_mem_base;
-		dense_base = hose->dense_mem_base;
-		if (sparse_base && !sparse_mem_mmap_fits(pdev, num)) {
-			sparse_base = 0;
-			suffix = "_dense";
-			nlen1 = 16;	/* resourceN_dense */
-		}
-	} else {
-		sparse_base = hose->sparse_io_base;
-		dense_base = hose->dense_io_base;
-	}
-
-	if (sparse_base) {
-		suffix = "_sparse";
-		nlen1 = 17;
-		if (dense_base) {
-			nlen2 = 16;	/* resourceN_dense */
-			res_count = 2;
-		}
-	}
-
-	attr = kzalloc(sizeof(*attr) * res_count + nlen1 + nlen2, GFP_ATOMIC);
-	if (!attr)
-		return -ENOMEM;
-
-	/* Create bwx, sparse or single dense file */
-	attr_name = (char *)(attr + res_count);
-	pdev->res_attr[num] = attr;
-	retval = pci_create_one_attr(pdev, num, attr_name, suffix, attr,
-				     sparse_base);
-	if (retval || res_count == 1)
-		return retval;
-
-	/* Create dense file */
-	attr_name += nlen1;
-	attr++;
-	pdev->res_attr_wc[num] = attr;
-	return pci_create_one_attr(pdev, num, attr_name, "_dense", attr, 0);
-}
-
-/**
- * pci_create_resource_files - create resource files in sysfs for @pdev
- * @pdev: pci_dev in question
- *
- * Walk the resources in @dev creating files for each resource available.
- *
- * Return: %0 on success, or negative error code
- */
-int pci_create_resource_files(struct pci_dev *pdev)
-{
-	int i;
-	int retval;
-
-	/* Expose the PCI resources from this device as files */
-	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
-
-		/* skip empty resources */
-		if (!pci_resource_len(pdev, i))
-			continue;
-
-		retval = pci_create_attr(pdev, i);
-		if (retval) {
-			pci_remove_resource_files(pdev);
-			return retval;
-		}
-	}
-	return 0;
-}
-
 /* Legacy I/O bus mapping stuff. */
 
 static int __legacy_mmap_fits(struct vm_area_struct *vma,
@@ -381,3 +253,166 @@ int pci_legacy_write(struct pci_bus *bus, loff_t port, u32 val, size_t size)
 	}
 	return -EINVAL;
 }
+
+pci_dev_resource_attr(0);
+pci_dev_resource_attr(1);
+pci_dev_resource_attr(2);
+pci_dev_resource_attr(3);
+pci_dev_resource_attr(4);
+pci_dev_resource_attr(5);
+
+pci_dev_resource_sparse_attr(0);
+pci_dev_resource_sparse_attr(1);
+pci_dev_resource_sparse_attr(2);
+pci_dev_resource_sparse_attr(3);
+pci_dev_resource_sparse_attr(4);
+pci_dev_resource_sparse_attr(5);
+
+pci_dev_resource_dense_attr(0);
+pci_dev_resource_dense_attr(1);
+pci_dev_resource_dense_attr(2);
+pci_dev_resource_dense_attr(3);
+pci_dev_resource_dense_attr(4);
+pci_dev_resource_dense_attr(5);
+
+static inline enum pci_mmap_state pci_bar_mmap_type(struct pci_dev *pdev,
+						    int bar)
+{
+	return pci_resource_is_mem(pdev, bar) ? pci_mmap_mem : pci_mmap_io;
+}
+
+static inline umode_t __pci_resource_attr_is_visible(struct kobject *kobj,
+						     const struct bin_attribute *a,
+						     int bar)
+{
+	struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj));
+
+	if (!pci_resource_len(pdev, bar))
+		return 0;
+
+	return a->attr.mode;
+}
+
+static umode_t pci_dev_resource_is_visible(struct kobject *kobj,
+					   const struct bin_attribute *a,
+					   int bar)
+{
+	struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj));
+	struct pci_controller *hose = pdev->sysdata;
+
+	if (has_sparse(hose, pci_bar_mmap_type(pdev, bar)))
+		return 0;
+
+	return __pci_resource_attr_is_visible(kobj, a, bar);
+}
+
+static umode_t pci_dev_resource_sparse_is_visible(struct kobject *kobj,
+						  const struct bin_attribute *a,
+						  int bar)
+{
+	struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj));
+	struct pci_controller *hose = pdev->sysdata;
+	enum pci_mmap_state type = pci_bar_mmap_type(pdev, bar);
+
+	if (!has_sparse(hose, type))
+		return 0;
+
+	if (type == pci_mmap_mem && !sparse_mem_mmap_fits(pdev, bar))
+		return 0;
+
+	return __pci_resource_attr_is_visible(kobj, a, bar);
+}
+
+static umode_t pci_dev_resource_dense_is_visible(struct kobject *kobj,
+						 const struct bin_attribute *a,
+						 int bar)
+{
+	struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj));
+	struct pci_controller *hose = pdev->sysdata;
+	enum pci_mmap_state type = pci_bar_mmap_type(pdev, bar);
+	unsigned long dense_base;
+
+	if (!has_sparse(hose, type))
+		return 0;
+
+	if (type == pci_mmap_mem && !sparse_mem_mmap_fits(pdev, bar))
+		return __pci_resource_attr_is_visible(kobj, a, bar);
+
+	dense_base = (type == pci_mmap_mem) ? hose->dense_mem_base :
+					      hose->dense_io_base;
+	if (!dense_base)
+		return 0;
+
+	return __pci_resource_attr_is_visible(kobj, a, bar);
+}
+
+static inline size_t __pci_dev_resource_bin_size(struct kobject *kobj,
+						 int bar, bool sparse)
+{
+	struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj));
+	size_t size = pci_resource_len(pdev, bar);
+
+	return sparse ? size << 5 : size;
+}
+
+static size_t pci_dev_resource_bin_size(struct kobject *kobj,
+					const struct bin_attribute *a,
+					int bar)
+{
+	return __pci_dev_resource_bin_size(kobj, bar, false);
+}
+
+static size_t pci_dev_resource_sparse_bin_size(struct kobject *kobj,
+					       const struct bin_attribute *a,
+					       int bar)
+{
+	return __pci_dev_resource_bin_size(kobj, bar, true);
+}
+
+static const struct bin_attribute *const pci_dev_resource_attrs[] = {
+	&pci_dev_resource0_attr,
+	&pci_dev_resource1_attr,
+	&pci_dev_resource2_attr,
+	&pci_dev_resource3_attr,
+	&pci_dev_resource4_attr,
+	&pci_dev_resource5_attr,
+	NULL,
+};
+
+static const struct bin_attribute *const pci_dev_resource_sparse_attrs[] = {
+	&pci_dev_resource0_sparse_attr,
+	&pci_dev_resource1_sparse_attr,
+	&pci_dev_resource2_sparse_attr,
+	&pci_dev_resource3_sparse_attr,
+	&pci_dev_resource4_sparse_attr,
+	&pci_dev_resource5_sparse_attr,
+	NULL,
+};
+
+static const struct bin_attribute *const pci_dev_resource_dense_attrs[] = {
+	&pci_dev_resource0_dense_attr,
+	&pci_dev_resource1_dense_attr,
+	&pci_dev_resource2_dense_attr,
+	&pci_dev_resource3_dense_attr,
+	&pci_dev_resource4_dense_attr,
+	&pci_dev_resource5_dense_attr,
+	NULL,
+};
+
+const struct attribute_group pci_dev_resource_attr_group = {
+	.bin_attrs = pci_dev_resource_attrs,
+	.is_bin_visible = pci_dev_resource_is_visible,
+	.bin_size = pci_dev_resource_bin_size,
+};
+
+const struct attribute_group pci_dev_resource_sparse_attr_group = {
+	.bin_attrs = pci_dev_resource_sparse_attrs,
+	.is_bin_visible = pci_dev_resource_sparse_is_visible,
+	.bin_size = pci_dev_resource_sparse_bin_size,
+};
+
+const struct attribute_group pci_dev_resource_dense_attr_group = {
+	.bin_attrs = pci_dev_resource_dense_attrs,
+	.is_bin_visible = pci_dev_resource_dense_is_visible,
+	.bin_size = pci_dev_resource_bin_size,
+};
-- 
2.54.0

[PATCH v8 18/25] PCI/sysfs: Remove pci_{create,remove}_sysfs_dev_files()

[Krzysztof Wilczyński]

Currently, pci_create_sysfs_dev_files() and pci_remove_sysfs_dev_files()
are no-op stubs.  With both the generic and Alpha resource files now
handled by static attribute groups, no platform needs dynamic per-device
sysfs file creation.

Thus, remove both functions, their declarations, and the call sites in
pci_bus_add_device() and pci_stop_dev().

Remove __weak pci_create_resource_files() and pci_remove_resource_files()
stubs and their declarations in pci.h, as no architecture overrides them
anymore.

Remove the res_attr[] and res_attr_wc[] fields from struct pci_dev
which were used to track dynamically allocated resource attributes.

Finally, simplify pci_sysfs_init() to only handle legacy file creation
under HAVE_PCI_LEGACY, removing the per-device loop and the
HAVE_PCI_SYSFS_INIT helper added earlier.

Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/bus.c       |  1 -
 drivers/pci/pci-sysfs.c | 52 ++---------------------------------------
 drivers/pci/pci.h       |  4 ----
 drivers/pci/remove.c    |  1 -
 include/linux/pci.h     |  9 -------
 5 files changed, 2 insertions(+), 65 deletions(-)

diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 6c1ad1f542d9..655ed53436d3 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -354,7 +354,6 @@ void pci_bus_add_device(struct pci_dev *dev)
 	pci_fixup_device(pci_fixup_final, dev);
 	if (pci_is_bridge(dev))
 		of_pci_make_dev_node(dev);
-	pci_create_sysfs_dev_files(dev);
 	pci_proc_attach_device(dev);
 	pci_bridge_d3_update(dev);
 
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 57d89e12bfec..9d1378700c3a 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -37,12 +37,7 @@
 #define ARCH_PCI_DEV_GROUPS
 #endif
 
-#if defined(HAVE_PCI_LEGACY) || \
-	!defined(HAVE_PCI_MMAP) && !defined(ARCH_GENERIC_PCI_MMAP_RESOURCE)
-#define HAVE_PCI_SYSFS_INIT
-#endif
-
-#ifdef HAVE_PCI_SYSFS_INIT
+#ifdef HAVE_PCI_LEGACY
 static int sysfs_initialized;	/* = 0 */
 #endif
 
@@ -1377,8 +1372,6 @@ static const struct attribute_group *pci_dev_resource_attr_groups[] = {
 };
 #else
 #define pci_dev_resource_attr_groups NULL
-int __weak pci_create_resource_files(struct pci_dev *dev) { return 0; }
-void __weak pci_remove_resource_files(struct pci_dev *dev) { }
 #endif
 
 /**
@@ -1748,54 +1741,13 @@ static const struct attribute_group pci_dev_resource_resize_attr_group = {
 	.is_visible = resource_resize_attr_is_visible,
 };
 
-#if defined(HAVE_PCI_MMAP) || defined(ARCH_GENERIC_PCI_MMAP_RESOURCE)
-int pci_create_sysfs_dev_files(struct pci_dev *pdev) { return 0; }
-void pci_remove_sysfs_dev_files(struct pci_dev *pdev) { }
-#else
-int __must_check pci_create_sysfs_dev_files(struct pci_dev *pdev)
-{
-	if (!sysfs_initialized)
-		return -EACCES;
-
-	return pci_create_resource_files(pdev);
-}
-
-/**
- * pci_remove_sysfs_dev_files - cleanup PCI specific sysfs files
- * @pdev: device whose entries we should free
- *
- * Cleanup when @pdev is removed from sysfs.
- */
-void pci_remove_sysfs_dev_files(struct pci_dev *pdev)
-{
-	if (!sysfs_initialized)
-		return;
-
-	pci_remove_resource_files(pdev);
-}
-#endif
-
-#ifdef HAVE_PCI_SYSFS_INIT
+#ifdef HAVE_PCI_LEGACY
 static int __init pci_sysfs_init(void)
 {
-#if defined(HAVE_PCI_MMAP) || defined(ARCH_GENERIC_PCI_MMAP_RESOURCE)
 	struct pci_bus *pbus = NULL;
 
 	sysfs_initialized = 1;
-#else
-	struct pci_dev *pdev = NULL;
-	struct pci_bus *pbus = NULL;
-	int retval;
 
-	sysfs_initialized = 1;
-	for_each_pci_dev(pdev) {
-		retval = pci_create_sysfs_dev_files(pdev);
-		if (retval) {
-			pci_dev_put(pdev);
-			return retval;
-		}
-	}
-#endif
 	while ((pbus = pci_find_next_bus(pbus)))
 		pci_create_legacy_files(pbus);
 
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 4a14f88e543a..71a1fde1e505 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -393,16 +393,12 @@ static inline int pci_no_d1d2(struct pci_dev *dev)
 }
 
 #ifdef CONFIG_SYSFS
-int pci_create_sysfs_dev_files(struct pci_dev *pdev);
-void pci_remove_sysfs_dev_files(struct pci_dev *pdev);
 extern const struct attribute_group *pci_dev_groups[];
 extern const struct attribute_group *pci_dev_attr_groups[];
 extern const struct attribute_group *pcibus_groups[];
 extern const struct attribute_group *pci_bus_groups[];
 extern const struct attribute_group pci_doe_sysfs_group;
 #else
-static inline int pci_create_sysfs_dev_files(struct pci_dev *pdev) { return 0; }
-static inline void pci_remove_sysfs_dev_files(struct pci_dev *pdev) { }
 #define pci_dev_groups NULL
 #define pci_dev_attr_groups NULL
 #define pcibus_groups NULL
diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c
index e9d519993853..6e796dbc5b29 100644
--- a/drivers/pci/remove.c
+++ b/drivers/pci/remove.c
@@ -26,7 +26,6 @@ static void pci_stop_dev(struct pci_dev *dev)
 
 	device_release_driver(&dev->dev);
 	pci_proc_detach_device(dev);
-	pci_remove_sysfs_dev_files(dev);
 	of_pci_remove_node(dev);
 }
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index b998a56f6010..c56f2cf0d2ab 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -515,10 +515,6 @@ struct pci_dev {
 	spinlock_t	pcie_cap_lock;		/* Protects RMW ops in capability accessors */
 	u32		saved_config_space[16]; /* Config space saved at suspend time */
 	struct hlist_head saved_cap_space;
-#if !defined(HAVE_PCI_MMAP) && !defined(ARCH_GENERIC_PCI_MMAP_RESOURCE)
-	struct bin_attribute *res_attr[DEVICE_COUNT_RESOURCE]; /* sysfs file for resources */
-	struct bin_attribute *res_attr_wc[DEVICE_COUNT_RESOURCE]; /* sysfs file for WC mapping of resources */
-#endif
 
 #ifdef CONFIG_HOTPLUG_PCI_PCIE
 	unsigned int	broken_cmd_compl:1;	/* No compl for some cmds */
@@ -2533,11 +2529,6 @@ 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);
 void __init pci_mmcfg_late_init(void);
-- 
2.54.0

[PATCH v8 19/25] PCI: Add macros for legacy I/O and memory address space sizes

[Krzysztof Wilczyński]

Add defines for the standard PCI legacy address space sizes,
replacing the raw literals used by the legacy sysfs attributes.

Then, replace open-coded values with the newly added macros.

No functional changes intended.

Suggested-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/pci-sysfs.c | 4 ++--
 include/linux/pci.h     | 5 +++++
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 9d1378700c3a..b8986a735a46 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -1019,7 +1019,7 @@ void pci_create_legacy_files(struct pci_bus *b)
 
 	sysfs_bin_attr_init(b->legacy_io);
 	b->legacy_io->attr.name = "legacy_io";
-	b->legacy_io->size = 0xffff;
+	b->legacy_io->size = PCI_LEGACY_IO_SIZE;
 	b->legacy_io->attr.mode = 0600;
 	b->legacy_io->read = pci_read_legacy_io;
 	b->legacy_io->write = pci_write_legacy_io;
@@ -1036,7 +1036,7 @@ void pci_create_legacy_files(struct pci_bus *b)
 	b->legacy_mem = b->legacy_io + 1;
 	sysfs_bin_attr_init(b->legacy_mem);
 	b->legacy_mem->attr.name = "legacy_mem";
-	b->legacy_mem->size = 1024*1024;
+	b->legacy_mem->size = PCI_LEGACY_MEM_SIZE;
 	b->legacy_mem->attr.mode = 0600;
 	b->legacy_mem->mmap = pci_mmap_legacy_mem;
 	/* See pci_create_attr() for motivation */
diff --git a/include/linux/pci.h b/include/linux/pci.h
index c56f2cf0d2ab..e37677a8dd3c 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -27,6 +27,7 @@
 #include <linux/mod_devicetable.h>
 
 #include <linux/types.h>
+#include <linux/sizes.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
 #include <linux/list.h>
@@ -1169,6 +1170,10 @@ enum {
 /* These external functions are only available when PCI support is enabled */
 #ifdef CONFIG_PCI
 
+/* PCI legacy I/O port and memory address space sizes. */
+#define PCI_LEGACY_IO_SIZE	(SZ_64K - 1)
+#define PCI_LEGACY_MEM_SIZE	SZ_1M
+
 extern unsigned int pci_flags;
 
 static inline void pci_set_flags(int flags) { pci_flags = flags; }
-- 
2.54.0

[PATCH v8 20/25] alpha/PCI: Compute legacy size in pci_mmap_legacy_page_range()

[Krzysztof Wilczyński]

Currently, pci_mmap_legacy_page_range() reads the legacy resource
size from bus->legacy_mem->size or bus->legacy_io->size.  This
couples the mmap bounds check to the struct pci_bus fields that
will be removed when legacy attributes are converted to static
definitions.

Compute the size directly using PCI_LEGACY_MEM_SIZE (0x100000) and
PCI_LEGACY_IO_SIZE (0xffff) macros, and shift by 5 bits for sparse
systems.

Tested-by: Magnus Lindholm <linmag7@gmail.com>
Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Acked-by: Magnus Lindholm <linmag7@gmail.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 arch/alpha/kernel/pci-sysfs.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/alpha/kernel/pci-sysfs.c b/arch/alpha/kernel/pci-sysfs.c
index ae448a2e40c5..74c9145e0253 100644
--- a/arch/alpha/kernel/pci-sysfs.c
+++ b/arch/alpha/kernel/pci-sysfs.c
@@ -173,8 +173,11 @@ int pci_mmap_legacy_page_range(struct pci_bus *bus, struct vm_area_struct *vma,
 	int sparse = has_sparse(hose, mmap_type);
 	unsigned long res_size;
 
-	res_size = (mmap_type == pci_mmap_mem) ? bus->legacy_mem->size :
-						 bus->legacy_io->size;
+	res_size = (mmap_type == pci_mmap_mem) ? PCI_LEGACY_MEM_SIZE :
+						 PCI_LEGACY_IO_SIZE;
+	if (sparse)
+		res_size <<= 5;
+
 	if (!__legacy_mmap_fits(vma, res_size))
 		return -EINVAL;
 
-- 
2.54.0

[PATCH v8 21/25] PCI/sysfs: Add __weak pci_legacy_has_sparse() helper

[Krzysztof Wilczyński]

Currently, Alpha's sparse/dense legacy attribute handling is done via
pci_adjust_legacy_attr(), which updates dynamically allocated attributes
at runtime.  The upcoming conversion to static attributes needs a way
to determine sparse support at visibility check time.

Add a __weak pci_legacy_has_sparse() that returns false by default.
Alpha overrides it to check has_sparse() on the bus host controller.

Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 arch/alpha/include/asm/pci.h  | 2 ++
 arch/alpha/kernel/pci-sysfs.c | 7 +++++++
 drivers/pci/pci-sysfs.c       | 6 ++++++
 drivers/pci/pci.h             | 4 ++++
 4 files changed, 19 insertions(+)

diff --git a/arch/alpha/include/asm/pci.h b/arch/alpha/include/asm/pci.h
index ef19295f2e33..95de7ffd59e8 100644
--- a/arch/alpha/include/asm/pci.h
+++ b/arch/alpha/include/asm/pci.h
@@ -86,6 +86,8 @@ extern int pci_mmap_legacy_page_range(struct pci_bus *bus,
 				      enum pci_mmap_state mmap_state);
 extern void pci_adjust_legacy_attr(struct pci_bus *bus,
 				   enum pci_mmap_state mmap_type);
+extern bool pci_legacy_has_sparse(struct pci_bus *bus,
+				  enum pci_mmap_state type);
 #define HAVE_PCI_LEGACY	1
 
 extern const struct attribute_group pci_dev_resource_attr_group;
diff --git a/arch/alpha/kernel/pci-sysfs.c b/arch/alpha/kernel/pci-sysfs.c
index 74c9145e0253..2d878b310629 100644
--- a/arch/alpha/kernel/pci-sysfs.c
+++ b/arch/alpha/kernel/pci-sysfs.c
@@ -184,6 +184,13 @@ int pci_mmap_legacy_page_range(struct pci_bus *bus, struct vm_area_struct *vma,
 	return hose_mmap_page_range(hose, vma, mmap_type, sparse);
 }
 
+bool pci_legacy_has_sparse(struct pci_bus *bus, enum pci_mmap_state type)
+{
+	struct pci_controller *hose = bus->sysdata;
+
+	return has_sparse(hose, type);
+}
+
 /**
  * pci_adjust_legacy_attr - adjustment of legacy file attributes
  * @bus: bus to create files under
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index b8986a735a46..a861484ac0c0 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -983,6 +983,12 @@ static int pci_mmap_legacy_io(struct file *filp, struct kobject *kobj,
 	return pci_mmap_legacy_page_range(bus, vma, pci_mmap_io);
 }
 
+bool __weak pci_legacy_has_sparse(struct pci_bus *bus,
+				  enum pci_mmap_state type)
+{
+	return false;
+}
+
 /**
  * pci_adjust_legacy_attr - adjustment of legacy file attributes
  * @b: bus to create files under
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 71a1fde1e505..c64c7f5f0bcf 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -392,6 +392,10 @@ static inline int pci_no_d1d2(struct pci_dev *dev)
 
 }
 
+#ifdef HAVE_PCI_LEGACY
+bool pci_legacy_has_sparse(struct pci_bus *bus, enum pci_mmap_state type);
+#endif
+
 #ifdef CONFIG_SYSFS
 extern const struct attribute_group *pci_dev_groups[];
 extern const struct attribute_group *pci_dev_attr_groups[];
-- 
2.54.0

[PATCH v8 22/25] PCI/sysfs: Add legacy I/O and memory attribute macros

[Krzysztof Wilczyński]

Add two macros for declaring static binary attributes for PCI legacy
I/O port and ISA memory space files:

  - pci_legacy_resource_io_attr(), for legacy I/O port space (read/write)
  - pci_legacy_resource_mem_attr(), for legacy memory space (mmap)

Each macro sets the fixed attribute size.

Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/pci-sysfs.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index a861484ac0c0..7f1d8e07924f 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -893,6 +893,27 @@ pci_llseek_resource_legacy(struct file *filep,
 }
 
 #ifdef HAVE_PCI_LEGACY
+
+#define pci_legacy_resource_io_attr(_suffix, _size)				\
+static const struct bin_attribute pci_legacy_io##_suffix##_attr = {		\
+	.attr = { .name = "legacy_io" __stringify(_suffix), .mode = 0600 },	\
+	.size = (_size),							\
+	.read = pci_read_legacy_io,						\
+	.write = pci_write_legacy_io,						\
+	.f_mapping = iomem_get_mapping,						\
+	.llseek = pci_llseek_resource_legacy,					\
+	.mmap = pci_mmap_legacy_io,						\
+}
+
+#define pci_legacy_resource_mem_attr(_suffix, _size)				\
+static const struct bin_attribute pci_legacy_mem##_suffix##_attr = {		\
+	.attr = { .name = "legacy_mem" __stringify(_suffix), .mode = 0600 },	\
+	.size = (_size),							\
+	.f_mapping = iomem_get_mapping,						\
+	.llseek = pci_llseek_resource_legacy,					\
+	.mmap = pci_mmap_legacy_mem,						\
+}
+
 /**
  * pci_read_legacy_io - read byte(s) from legacy I/O port space
  * @filp: open sysfs file
-- 
2.54.0

[PATCH v8 23/25] PCI/sysfs: Convert legacy I/O and memory attributes to static definitions

[Krzysztof Wilczyński]

Currently, legacy_io and legacy_mem are dynamically allocated and
created by pci_create_legacy_files(), with pci_adjust_legacy_attr()
updating the attributes at runtime on Alpha to rename them and shift
the size for sparse addressing.

Convert to four static const attributes (legacy_io, legacy_io_sparse,
legacy_mem, legacy_mem_sparse) with is_bin_visible() callbacks that
use pci_legacy_has_sparse() to select the appropriate variant per bus.
The sizes are compile-time constants and .size is set directly on
each attribute.

Register the groups in pcibus_groups[] under a HAVE_PCI_LEGACY guard
so the driver model handles creation and removal automatically.

Stub out pci_create_legacy_files() and pci_remove_legacy_files() as
the dynamic creation is no longer needed.  Remove the __weak
pci_adjust_legacy_attr(), Alpha's override, and its declaration from
both Alpha and PowerPC asm/pci.h headers.

Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 arch/alpha/include/asm/pci.h   |   2 -
 arch/alpha/kernel/pci-sysfs.c  |  24 -----
 arch/powerpc/include/asm/pci.h |   2 -
 drivers/pci/pci-sysfs.c        | 191 +++++++++++++++++----------------
 4 files changed, 98 insertions(+), 121 deletions(-)

diff --git a/arch/alpha/include/asm/pci.h b/arch/alpha/include/asm/pci.h
index 95de7ffd59e8..ad5d1391e1fa 100644
--- a/arch/alpha/include/asm/pci.h
+++ b/arch/alpha/include/asm/pci.h
@@ -84,8 +84,6 @@ extern int pci_legacy_write(struct pci_bus *bus, loff_t port, u32 val,
 extern int pci_mmap_legacy_page_range(struct pci_bus *bus,
 				      struct vm_area_struct *vma,
 				      enum pci_mmap_state mmap_state);
-extern void pci_adjust_legacy_attr(struct pci_bus *bus,
-				   enum pci_mmap_state mmap_type);
 extern bool pci_legacy_has_sparse(struct pci_bus *bus,
 				  enum pci_mmap_state type);
 #define HAVE_PCI_LEGACY	1
diff --git a/arch/alpha/kernel/pci-sysfs.c b/arch/alpha/kernel/pci-sysfs.c
index 2d878b310629..37cba711ade5 100644
--- a/arch/alpha/kernel/pci-sysfs.c
+++ b/arch/alpha/kernel/pci-sysfs.c
@@ -191,30 +191,6 @@ bool pci_legacy_has_sparse(struct pci_bus *bus, enum pci_mmap_state type)
 	return has_sparse(hose, type);
 }
 
-/**
- * pci_adjust_legacy_attr - adjustment of legacy file attributes
- * @bus: bus to create files under
- * @mmap_type: I/O port or memory
- *
- * Adjust file name and size for sparse mappings.
- */
-void pci_adjust_legacy_attr(struct pci_bus *bus, enum pci_mmap_state mmap_type)
-{
-	struct pci_controller *hose = bus->sysdata;
-
-	if (!has_sparse(hose, mmap_type))
-		return;
-
-	if (mmap_type == pci_mmap_mem) {
-		bus->legacy_mem->attr.name = "legacy_mem_sparse";
-		bus->legacy_mem->size <<= 5;
-	} else {
-		bus->legacy_io->attr.name = "legacy_io_sparse";
-		bus->legacy_io->size <<= 5;
-	}
-	return;
-}
-
 /* Legacy I/O bus read/write functions */
 int pci_legacy_read(struct pci_bus *bus, loff_t port, u32 *val, size_t size)
 {
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index 46a9c4491ed0..72f286e74786 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -82,8 +82,6 @@ extern int pci_legacy_write(struct pci_bus *bus, loff_t port, u32 val,
 extern int pci_mmap_legacy_page_range(struct pci_bus *bus,
 				      struct vm_area_struct *vma,
 				      enum pci_mmap_state mmap_state);
-extern void pci_adjust_legacy_attr(struct pci_bus *bus,
-				   enum pci_mmap_state mmap_type);
 #define HAVE_PCI_LEGACY	1
 
 extern void pcibios_claim_one_bus(struct pci_bus *b);
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 7f1d8e07924f..dfb4e06677fc 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -676,11 +676,6 @@ static const struct attribute_group pcibus_group = {
 	.attrs = pcibus_attrs,
 };
 
-const struct attribute_group *pcibus_groups[] = {
-	&pcibus_group,
-	NULL,
-};
-
 static ssize_t boot_vga_show(struct device *dev, struct device_attribute *attr,
 			     char *buf)
 {
@@ -879,19 +874,6 @@ static const struct attribute_group pci_dev_config_attr_group = {
 	.bin_size = pci_dev_config_attr_bin_size,
 };
 
-/*
- * llseek operation for mmappable PCI resources.
- * May be left unused if the arch doesn't provide them.
- */
-static __maybe_unused loff_t
-pci_llseek_resource_legacy(struct file *filep,
-			   struct kobject *kobj __always_unused,
-			   const struct bin_attribute *attr,
-			   loff_t offset, int whence)
-{
-	return fixed_size_llseek(filep, offset, whence, attr->size);
-}
-
 #ifdef HAVE_PCI_LEGACY
 
 #define pci_legacy_resource_io_attr(_suffix, _size)				\
@@ -1010,91 +992,114 @@ bool __weak pci_legacy_has_sparse(struct pci_bus *bus,
 	return false;
 }
 
-/**
- * pci_adjust_legacy_attr - adjustment of legacy file attributes
- * @b: bus to create files under
- * @mmap_type: I/O port or memory
- *
- * Stub implementation. Can be overridden by arch if necessary.
- */
-void __weak pci_adjust_legacy_attr(struct pci_bus *b,
-				   enum pci_mmap_state mmap_type)
+static inline umode_t __pci_legacy_is_visible(struct kobject *kobj,
+					      const struct bin_attribute *a,
+					      enum pci_mmap_state type,
+					      bool sparse)
 {
+	struct pci_bus *bus = to_pci_bus(kobj_to_dev(kobj));
+
+	if (pci_legacy_has_sparse(bus, type) != sparse)
+		return 0;
+
+	return a->attr.mode;
 }
 
-/**
- * pci_create_legacy_files - create legacy I/O port and memory files
- * @b: bus to create files under
- *
- * Some platforms allow access to legacy I/O port and ISA memory space on
- * a per-bus basis.  This routine creates the files and ties them into
- * their associated read, write and mmap files from pci-sysfs.c
- *
- * On error unwind, but don't propagate the error to the caller
- * as it is ok to set up the PCI bus without these files.
- */
-void pci_create_legacy_files(struct pci_bus *b)
+static umode_t pci_legacy_io_is_visible(struct kobject *kobj,
+					const struct bin_attribute *a, int n)
 {
-	int error;
-
-	if (!sysfs_initialized)
-		return;
-
-	b->legacy_io = kzalloc_objs(struct bin_attribute, 2, GFP_ATOMIC);
-	if (!b->legacy_io)
-		goto kzalloc_err;
-
-	sysfs_bin_attr_init(b->legacy_io);
-	b->legacy_io->attr.name = "legacy_io";
-	b->legacy_io->size = PCI_LEGACY_IO_SIZE;
-	b->legacy_io->attr.mode = 0600;
-	b->legacy_io->read = pci_read_legacy_io;
-	b->legacy_io->write = pci_write_legacy_io;
-	/* See pci_create_attr() for motivation */
-	b->legacy_io->llseek = pci_llseek_resource_legacy;
-	b->legacy_io->mmap = pci_mmap_legacy_io;
-	b->legacy_io->f_mapping = iomem_get_mapping;
-	pci_adjust_legacy_attr(b, pci_mmap_io);
-	error = device_create_bin_file(&b->dev, b->legacy_io);
-	if (error)
-		goto legacy_io_err;
-
-	/* Allocated above after the legacy_io struct */
-	b->legacy_mem = b->legacy_io + 1;
-	sysfs_bin_attr_init(b->legacy_mem);
-	b->legacy_mem->attr.name = "legacy_mem";
-	b->legacy_mem->size = PCI_LEGACY_MEM_SIZE;
-	b->legacy_mem->attr.mode = 0600;
-	b->legacy_mem->mmap = pci_mmap_legacy_mem;
-	/* See pci_create_attr() for motivation */
-	b->legacy_mem->llseek = pci_llseek_resource_legacy;
-	b->legacy_mem->f_mapping = iomem_get_mapping;
-	pci_adjust_legacy_attr(b, pci_mmap_mem);
-	error = device_create_bin_file(&b->dev, b->legacy_mem);
-	if (error)
-		goto legacy_mem_err;
-
-	return;
-
-legacy_mem_err:
-	device_remove_bin_file(&b->dev, b->legacy_io);
-legacy_io_err:
-	kfree(b->legacy_io);
-	b->legacy_io = NULL;
-kzalloc_err:
-	dev_warn(&b->dev, "could not create legacy I/O port and ISA memory resources in sysfs\n");
+	return __pci_legacy_is_visible(kobj, a, pci_mmap_io, false);
 }
 
-void pci_remove_legacy_files(struct pci_bus *b)
+static umode_t pci_legacy_io_sparse_is_visible(struct kobject *kobj,
+					       const struct bin_attribute *a,
+					       int n)
 {
-	if (b->legacy_io) {
-		device_remove_bin_file(&b->dev, b->legacy_io);
-		device_remove_bin_file(&b->dev, b->legacy_mem);
-		kfree(b->legacy_io); /* both are allocated here */
-	}
+	return __pci_legacy_is_visible(kobj, a, pci_mmap_io, true);
 }
+
+static umode_t pci_legacy_mem_is_visible(struct kobject *kobj,
+					 const struct bin_attribute *a, int n)
+{
+	return __pci_legacy_is_visible(kobj, a, pci_mmap_mem, false);
+}
+
+static umode_t pci_legacy_mem_sparse_is_visible(struct kobject *kobj,
+						const struct bin_attribute *a,
+						int n)
+{
+	return __pci_legacy_is_visible(kobj, a, pci_mmap_mem, true);
+}
+
+static loff_t pci_llseek_resource_legacy(struct file *filep,
+					 struct kobject *kobj __always_unused,
+					 const struct bin_attribute *attr,
+					 loff_t offset, int whence)
+{
+	return fixed_size_llseek(filep, offset, whence, attr->size);
+}
+
+pci_legacy_resource_io_attr(, PCI_LEGACY_IO_SIZE);
+pci_legacy_resource_io_attr(_sparse, PCI_LEGACY_IO_SIZE << 5);
+
+pci_legacy_resource_mem_attr(, PCI_LEGACY_MEM_SIZE);
+pci_legacy_resource_mem_attr(_sparse, PCI_LEGACY_MEM_SIZE << 5);
+
+static const struct bin_attribute *const pci_legacy_io_attrs[] = {
+	&pci_legacy_io_attr,
+	NULL,
+};
+
+static const struct bin_attribute *const pci_legacy_io_sparse_attrs[] = {
+	&pci_legacy_io_sparse_attr,
+	NULL,
+};
+
+static const struct bin_attribute *const pci_legacy_mem_attrs[] = {
+	&pci_legacy_mem_attr,
+	NULL,
+};
+
+static const struct bin_attribute *const pci_legacy_mem_sparse_attrs[] = {
+	&pci_legacy_mem_sparse_attr,
+	NULL,
+};
+
+static const struct attribute_group pci_legacy_io_group = {
+	.bin_attrs = pci_legacy_io_attrs,
+	.is_bin_visible = pci_legacy_io_is_visible,
+};
+
+static const struct attribute_group pci_legacy_io_sparse_group = {
+	.bin_attrs = pci_legacy_io_sparse_attrs,
+	.is_bin_visible = pci_legacy_io_sparse_is_visible,
+};
+
+static const struct attribute_group pci_legacy_mem_group = {
+	.bin_attrs = pci_legacy_mem_attrs,
+	.is_bin_visible = pci_legacy_mem_is_visible,
+};
+
+static const struct attribute_group pci_legacy_mem_sparse_group = {
+	.bin_attrs = pci_legacy_mem_sparse_attrs,
+	.is_bin_visible = pci_legacy_mem_sparse_is_visible,
+};
+
+void pci_create_legacy_files(struct pci_bus *b) { }
+void pci_remove_legacy_files(struct pci_bus *b) { }
 #endif /* HAVE_PCI_LEGACY */
 
+const struct attribute_group *pcibus_groups[] = {
+	&pcibus_group,
+#ifdef HAVE_PCI_LEGACY
+	&pci_legacy_io_group,
+	&pci_legacy_io_sparse_group,
+	&pci_legacy_mem_group,
+	&pci_legacy_mem_sparse_group,
+#endif
+	NULL,
+};
+
 #if defined(HAVE_PCI_MMAP) || defined(ARCH_GENERIC_PCI_MMAP_RESOURCE)
 /**
  * pci_mmap_resource - map a PCI resource into user memory space
-- 
2.54.0

[PATCH v8 24/25] PCI/sysfs: Remove pci_create_legacy_files() and pci_sysfs_init()

[Krzysztof Wilczyński]

Currently, pci_create_legacy_files() and pci_remove_legacy_files() are
no-op stubs.  With legacy attributes now handled by static groups
registered via pcibus_groups[], no call site needs them.

Remove both functions, their declarations, and the call sites in
pci_register_host_bridge(), pci_alloc_child_bus(), and pci_remove_bus().

Remove the pci_sysfs_init() late_initcall and sysfs_initialized.  The
late_initcall originally existed to create all the dynamic PCI sysfs
files, but with both resource and legacy attributes now handled by
static groups, it is no longer needed.

Remove the legacy_io and legacy_mem fields from struct pci_bus which
were used to track the dynamically allocated legacy attributes.

Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/pci-sysfs.c | 21 ---------------------
 drivers/pci/pci.h       |  8 --------
 drivers/pci/probe.c     |  6 ------
 drivers/pci/remove.c    |  2 --
 include/linux/pci.h     |  2 --
 5 files changed, 39 deletions(-)

diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index dfb4e06677fc..dd87b83ba3a9 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -37,10 +37,6 @@
 #define ARCH_PCI_DEV_GROUPS
 #endif
 
-#ifdef HAVE_PCI_LEGACY
-static int sysfs_initialized;	/* = 0 */
-#endif
-
 /* show configuration fields */
 #define pci_config_attr(field, format_string)				\
 static ssize_t								\
@@ -1085,8 +1081,6 @@ static const struct attribute_group pci_legacy_mem_sparse_group = {
 	.is_bin_visible = pci_legacy_mem_sparse_is_visible,
 };
 
-void pci_create_legacy_files(struct pci_bus *b) { }
-void pci_remove_legacy_files(struct pci_bus *b) { }
 #endif /* HAVE_PCI_LEGACY */
 
 const struct attribute_group *pcibus_groups[] = {
@@ -1773,21 +1767,6 @@ static const struct attribute_group pci_dev_resource_resize_attr_group = {
 	.is_visible = resource_resize_attr_is_visible,
 };
 
-#ifdef HAVE_PCI_LEGACY
-static int __init pci_sysfs_init(void)
-{
-	struct pci_bus *pbus = NULL;
-
-	sysfs_initialized = 1;
-
-	while ((pbus = pci_find_next_bus(pbus)))
-		pci_create_legacy_files(pbus);
-
-	return 0;
-}
-late_initcall(pci_sysfs_init);
-#endif
-
 static struct attribute *pci_dev_dev_attrs[] = {
 	&dev_attr_boot_vga.attr,
 	&dev_attr_serial_number.attr,
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index c64c7f5f0bcf..4d17dab4662c 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -358,14 +358,6 @@ static inline int pci_proc_detach_bus(struct pci_bus *bus) { return 0; }
 int pci_hp_add_bridge(struct pci_dev *dev);
 bool pci_hp_spurious_link_change(struct pci_dev *pdev);
 
-#if defined(CONFIG_SYSFS) && defined(HAVE_PCI_LEGACY)
-void pci_create_legacy_files(struct pci_bus *bus);
-void pci_remove_legacy_files(struct pci_bus *bus);
-#else
-static inline void pci_create_legacy_files(struct pci_bus *bus) { }
-static inline void pci_remove_legacy_files(struct pci_bus *bus) { }
-#endif
-
 /* Lock for read/write access to pci device and bus lists */
 extern struct rw_semaphore pci_bus_sem;
 extern struct mutex pci_slot_mutex;
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index b63cd0c310bc..748c7a198262 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -1073,9 +1073,6 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge)
 			dev_err(&bus->dev, "failed to add bus: %d\n", err);
 	}
 
-	/* Create legacy_io and legacy_mem files for this bus */
-	pci_create_legacy_files(bus);
-
 	if (parent)
 		dev_info(parent, "PCI host bridge to bus %s\n", name);
 	else
@@ -1281,9 +1278,6 @@ static struct pci_bus *pci_alloc_child_bus(struct pci_bus *parent,
 			dev_err(&child->dev, "failed to add bus: %d\n", ret);
 	}
 
-	/* Create legacy_io and legacy_mem files for this bus */
-	pci_create_legacy_files(child);
-
 	return child;
 }
 
diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c
index 6e796dbc5b29..d8bffa21498a 100644
--- a/drivers/pci/remove.c
+++ b/drivers/pci/remove.c
@@ -65,8 +65,6 @@ void pci_remove_bus(struct pci_bus *bus)
 	list_del(&bus->node);
 	pci_bus_release_busn_res(bus);
 	up_write(&pci_bus_sem);
-	pci_remove_legacy_files(bus);
-
 	if (bus->ops->remove_bus)
 		bus->ops->remove_bus(bus);
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index e37677a8dd3c..74b767012766 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -726,8 +726,6 @@ struct pci_bus {
 	pci_bus_flags_t bus_flags;	/* Inherited by child buses */
 	struct device		*bridge;
 	struct device		dev;
-	struct bin_attribute	*legacy_io;	/* Legacy I/O for this bus */
-	struct bin_attribute	*legacy_mem;	/* Legacy mem */
 	unsigned int		is_added:1;
 	unsigned int		unsafe_warn:1;	/* warned about RW1C config write */
 	unsigned int		flit_mode:1;	/* Link in Flit mode */
-- 
2.54.0

[PATCH v8 25/25] PCI/sysfs: Limit BAR resize attribute scope to platforms with PCI mmap

[Krzysztof Wilczyński]

Currently, __resource_resize_store() uses sysfs_remove_groups()
and sysfs_create_groups() on pci_dev_resource_attr_groups to
tear down and recreate the resourceN files after a BAR resize,
so the updated BAR sizes are visible in sysfs.

The resourceN files only exist on platforms that define
HAVE_PCI_MMAP or ARCH_GENERIC_PCI_MMAP_RESOURCE.  On platforms
that define neither, pci_dev_resource_attr_groups is NULL and
the sysfs_remove_groups() and sysfs_create_groups() calls in
__resource_resize_store() become no-ops.

Resizable BAR (ReBAR) is a PCI Express extended capability
(PCI_EXT_CAP_ID_REBAR) that requires PCIe extended config
space.  Every PCIe-capable architecture defines HAVE_PCI_MMAP
or ARCH_GENERIC_PCI_MMAP_RESOURCE (via arch headers or the
asm-generic/pci.h fallback).  Architectures without either
only support conventional PCI and cannot have any ReBAR-capable
devices.

Thus, move the resize show and store helpers, the per-BAR attribute
definitions, and the attribute group behind the existing #ifdef
HAVE_PCI_MMAP || ARCH_GENERIC_PCI_MMAP_RESOURCE guard, and fold the
group reference in pci_dev_groups[] into the existing #if block.

Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 drivers/pci/pci-sysfs.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index dd87b83ba3a9..4216ed520d41 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -1652,6 +1652,7 @@ static const struct attribute_group pci_dev_reset_method_attr_group = {
 	.is_visible = pci_dev_reset_attr_is_visible,
 };
 
+#if defined(HAVE_PCI_MMAP) || defined(ARCH_GENERIC_PCI_MMAP_RESOURCE)
 static ssize_t __resource_resize_show(struct device *dev, int n, char *buf)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
@@ -1766,6 +1767,7 @@ static const struct attribute_group pci_dev_resource_resize_attr_group = {
 	.attrs = resource_resize_attrs,
 	.is_visible = resource_resize_attr_is_visible,
 };
+#endif
 
 static struct attribute *pci_dev_dev_attrs[] = {
 	&dev_attr_boot_vga.attr,
@@ -1840,8 +1842,8 @@ const struct attribute_group *pci_dev_groups[] = {
 	&pci_dev_resource_io_attr_group,
 	&pci_dev_resource_uc_attr_group,
 	&pci_dev_resource_wc_attr_group,
-#endif
 	&pci_dev_resource_resize_attr_group,
+#endif
 	&pci_dev_config_attr_group,
 	&pci_dev_rom_attr_group,
 	&pci_dev_reset_attr_group,
-- 
2.54.0

Re: [PATCH v8 15/25] alpha/PCI: Remove WARN from __pci_mmap_fits() and __legacy_mmap_fits()

[sashiko-bot]

> Remove the WARN() that fires when userspace attempts to mmap beyond
> the BAR bounds.  The check still returns 0 to reject the mapping,
> but the warning is excessive for normal operation.
> 
> A similar warning was removed from the PCI core in the commit
> 3b519e4ea618 ("PCI: fix size checks for mmap() on /proc/bus/pci files").
> 
> Tested-by: Magnus Lindholm <linmag7@gmail.com>
> Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
> Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
> Acked-by: Magnus Lindholm <linmag7@gmail.com>
> Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619085200.3729431-1-kwilczynski@kernel.org?part=15

Re: [PATCH v8 02/25] PCI: Add pci_resource_is_io() and pci_resource_is_mem() helpers

[sashiko-bot]

> Add helpers to check whether a PCI resource is of I/O port or
> memory type.  These replace the open-coded pci_resource_flags()
> with IORESOURCE_IO and IORESOURCE_MEM pattern used across the
> tree.
> 
> Suggested-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
> Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
> Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
> Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619085200.3729431-1-kwilczynski@kernel.org?part=2

Re: [PATCH v8 05/25] PCI/sysfs: Add CAP_SYS_ADMIN check to __resource_resize_store()

[sashiko-bot]

> Currently, the __resource_resize_store() allows writing to the
> resourceN_resize sysfs attribute to change a BAR's size without
> checking for capabilities, currently relying only on the file
> access check.
> 
> Resizing a BAR modifies PCI device configuration and can disrupt
> active drivers.  After the upcoming conversion to static attributes,
> it will also trigger resource file updates via sysfs_update_groups().
> 
> Thus, add a CAP_SYS_ADMIN check to prevent unprivileged users from
> performing BAR resize operations.
> 
> Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
> Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
> Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619085200.3729431-1-kwilczynski@kernel.org?part=5

Re: [PATCH v8 03/25] PCI/sysfs: Only allow supported resource types in I/O and MMIO helpers

[sashiko-bot]

> Currently, when the sysfs attributes for PCI resources are added
> dynamically, the resource access callbacks are only set when the
> underlying BAR type matches, using .read and .write for IORESOURCE_IO,
> and .mmap for IORESOURCE_MEM or IORESOURCE_IO with arch_can_pci_mmap_io()
> support.  As such, when the callback is not set, the operation inherently
> fails.
> 
> After the conversion to static attributes, visibility callbacks will
> control which resource files appear for each BAR, but the callbacks
> themselves will always be set.
> 
> Thus, add a type check to pci_resource_io() and pci_mmap_resource()
> to return -EIO for an unsupported resource type.
> 
> Use the new pci_resource_is_io() and pci_resource_is_mem() helpers
> for the type checks, replacing the open-coded bitwise flag tests and
> also drop the local struct resource pointer in pci_mmap_resource().
> 
> Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
> Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
> Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619085200.3729431-1-kwilczynski@kernel.org?part=3

Re: [PATCH v8 12/25] alpha/PCI: Use BAR index in sysfs attr->private instead of resource pointer

[sashiko-bot]

> Currently, Alpha's pci_create_one_attr() stores a resource pointer in
> attr->private, and pci_mmap_resource() loops through all BARs to find
> the matching index.
> 
> Thus, store the BAR index directly in attr->private and retrieve the
> resource via pci_resource_n().  This eliminates the loop and aligns
> with the convention used by the generic PCI sysfs code.
> 
> The PCI core change was first added in the commit dca40b186b75 ("PCI:
> Use BAR index in sysfs attr->private instead of resource pointer").
> 
> Tested-by: Magnus Lindholm <linmag7@gmail.com>
> Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
> Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
> Acked-by: Magnus Lindholm <linmag7@gmail.com>
> Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619085200.3729431-1-kwilczynski@kernel.org?part=12

Re: [PATCH v8 04/25] PCI/sysfs: Split pci_llseek_resource() for device and legacy attributes

[sashiko-bot]

> Both legacy and resource attributes set .f_mapping = iomem_get_mapping,
> so the default generic_file_llseek() would consult iomem_inode for the
> file size, which knows nothing about the attribute.  That is why custom
> llseek callbacks exist.
> 
> Currently, the legacy and resource attributes have .size set at creation
> time, as such, using the attr->size is sufficient.  However, the upcoming
> static resource attributes will have .size == 0 set, since they are const,
> and the .bin_size callback will be used to provide the real size to kernfs
> instead.
> 
> The legacy attributes operate on a struct pci_bus, not struct pci_dev,
> so calling to_pci_dev() on them would be invalid.
> 
> Thus, split pci_llseek_resource() into two functions:
> 
>   - pci_llseek_resource(), which derives the file size from the BAR
>     using pci_resource_len().
> 
>   - pci_llseek_resource_legacy(), which uses attr->size directly.
> 
> Update the dynamic legacy attribute creation to use the new
> pci_llseek_resource_legacy() callback.
> 
> The original pci_llseek_resource() was added in commit 24de09c16f97
> ("PCI: Implement custom llseek for sysfs resource entries").
> 
> Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
> Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619085200.3729431-1-kwilczynski@kernel.org?part=4

Re: [PATCH v8 08/25] PCI/sysfs: Warn about BAR resize failure in __resource_resize_store()

[sashiko-bot]

> Add a pci_warn() to __resource_resize_store(), so that BAR resize
> failures are visible to the user, which can help troubleshoot any
> potential resource resize issues.
> 
> While at it, rename the resource_resize_is_visible() to
> resource_resize_attr_is_visible() along with the corresponding
> group variable to align with the naming convention used by the
> resource attribute groups.
> 
> Also, change the order of pci_dev_groups[] such that the resize
> group is now located alongside the other resource groups.
> 
> Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
> Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619085200.3729431-1-kwilczynski@kernel.org?part=8

Re: [PATCH v8 16/25] alpha/PCI: Add static PCI resource attribute macros

[sashiko-bot]

> Add macros for declaring static binary attributes for Alpha's PCI
> resource files:
> 
>   - pci_dev_resource_attr(),        for dense/BWX systems (mmap dense)
>   - pci_dev_resource_sparse_attr(), for sparse systems (mmap sparse)
>   - pci_dev_resource_dense_attr(),  for dense companion files (mmap dense)
> 
> Each macro creates a const bin_attribute with the BAR index stored in
> the .private property and the appropriate .mmap callback.
> 
> Tested-by: Magnus Lindholm <linmag7@gmail.com>
> Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
> Acked-by: Magnus Lindholm <linmag7@gmail.com>
> Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619085200.3729431-1-kwilczynski@kernel.org?part=16

Re: [PATCH v8 13/25] alpha/PCI: Use PCI resource accessor macros

[sashiko-bot]

> Replace direct pdev->resource[] accesses with pci_resource_n(),
> and open-coded res->flags type checks with pci_resource_is_mem()
> and pci_resource_start() helpers.
> 
> While at it, move the pci_resource_n() call directly into
> pcibios_resource_to_bus() and drop the local struct
> resource pointer.
> 
> No functional changes intended.
> 
> Tested-by: Magnus Lindholm <linmag7@gmail.com>
> Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
> Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
> Acked-by: Magnus Lindholm <linmag7@gmail.com>
> Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619085200.3729431-1-kwilczynski@kernel.org?part=13

Re: [PATCH v8 11/25] alpha/PCI: Add security_locked_down() check to pci_mmap_resource()

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:

Pre-existing issues:
- [High] Legacy PCI memory and I/O sysfs files lack lockdown checks, allowing userspace to bypass LOCKDOWN_PCI_ACCESS.
--

commit 332567893d71a88b42f9b02db5e578329ecec29f
Author: Krzysztof Wilczyński <kwilczynski@kernel.org>

alpha/PCI: Add security_locked_down() check to pci_mmap_resource()

Currently, Alpha's pci_mmap_resource() does not check
security_locked_down(LOCKDOWN_PCI_ACCESS) before allowing userspace to mmap
PCI BARs. The generic version has had this check to prevent DMA attacks
when the kernel is locked down, so this commit adds the same check to
Alpha's pci_mmap_resource().

> diff --git a/arch/alpha/kernel/pci-sysfs.c b/arch/alpha/kernel/pci-sysfs.c
> index 3048758304b57..2324720c3e83f 100644
> --- a/arch/alpha/kernel/pci-sysfs.c
> +++ b/arch/alpha/kernel/pci-sysfs.c
[ ... ]
> @@ -71,7 +72,11 @@ static int pci_mmap_resource(struct kobject *kobj,
>  	struct resource *res = attr->private;
>  	enum pci_mmap_state mmap_type;
>  	struct pci_bus_region bar;
> -	int i;
> +	int i, ret;
> +
> +	ret = security_locked_down(LOCKDOWN_PCI_ACCESS);
> +	if (ret)
> +		return ret;

[Severity: High]
This is a pre-existing issue, but since we are adding lockdown checks here
to prevent DMA attacks, do we also need similar checks in the legacy PCI
memory and I/O sysfs handlers?

For example, arch/alpha/kernel/pci-sysfs.c:pci_mmap_legacy_page_range()
allows mapping PCI memory/IO but doesn't seem to check kernel lockdown
status.

Additionally, the generic legacy handlers in drivers/pci/pci-sysfs.c
(pci_write_legacy_io(), pci_mmap_legacy_mem(), and pci_mmap_legacy_io())
also appear to lack security_locked_down() checks. Can a privileged user
bypass kernel lockdown using these legacy interfaces?

>  
>  	for (i = 0; i < PCI_STD_NUM_BARS; i++)
>  		if (res == &pdev->resource[i])

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619085200.3729431-1-kwilczynski@kernel.org?part=11

Re: [PATCH v8 21/25] PCI/sysfs: Add __weak pci_legacy_has_sparse() helper

[sashiko-bot]

> Currently, Alpha's sparse/dense legacy attribute handling is done via
> pci_adjust_legacy_attr(), which updates dynamically allocated attributes
> at runtime.  The upcoming conversion to static attributes needs a way
> to determine sparse support at visibility check time.
> 
> Add a __weak pci_legacy_has_sparse() that returns false by default.
> Alpha overrides it to check has_sparse() on the bus host controller.
> 
> Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
> Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619085200.3729431-1-kwilczynski@kernel.org?part=21

Re: [PATCH v8 07/25] PCI/sysfs: Convert PCI resource files to static attributes

[sashiko-bot]

> 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 "duplicate filename" warnings and boot panics when both
> paths race on the same device.
> 
> 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.
> 
> Thus, 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
> [ ... ]
> The write-combine support was added in commit 45aec1ae72fc ("x86: PAT
> export resource_wc in pci sysfs").
> 
> Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
> Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619085200.3729431-1-kwilczynski@kernel.org?part=7

Re: [PATCH v8 01/25] PCI/sysfs: Use PCI resource accessor macros

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:

Pre-existing issues:
- [High] Lockless access to the global `vga_default` pointer leads to a Use-After-Free.
--

commit be1111a7de2552597e9d80551a60eee90c47b957
Author: Krzysztof Wilczyński <kwilczynski@kernel.org>

PCI/sysfs: Use PCI resource accessor macros

Replace direct pdev->resource[] accesses with pci_resource_n(),
and pdev->resource[].flags accesses with pci_resource_flags().

No functional changes intended.

Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>

> diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
> index d37860841260c..1fbc3daf87cc5 100644
> --- a/drivers/pci/pci-sysfs.c
> +++ b/drivers/pci/pci-sysfs.c

[ ... ]

> @@ -689,7 +689,7 @@ static ssize_t boot_vga_show(struct device *dev, struct device_attribute *attr,
>  		return sysfs_emit(buf, "%u\n", (pdev == vga_dev));
>  
>  	return sysfs_emit(buf, "%u\n",
> -			  !!(pdev->resource[PCI_ROM_RESOURCE].flags &
> +			  !!(pci_resource_flags(pdev, PCI_ROM_RESOURCE) &
>  			     IORESOURCE_ROM_SHADOW));

[Severity: High]
This isn't a bug introduced by this patch, but I noticed a lockless access
pattern here involving vga_default_device() that could lead to a Use-After-Free
elsewhere in the code.

For example, in drivers/pci/vgaarb.c:vga_arb_write():

    if (!strncmp(curr_pos, "default", 7))
        pdev = pci_dev_get(vga_default_device());

Could this race with device removal? If vga_arbiter_del_pci_device() takes
vga_lock, updates vga_default to NULL, and drops its reference with
pci_dev_put():

    void vga_set_default_device(struct pci_dev *pdev)
    {
        if (vga_default == pdev)
            return;

        pci_dev_put(vga_default);
        vga_default = pci_dev_get(pdev);
    }

If the thread executing vga_arb_write() reads vga_default but is preempted
before incrementing the reference count in pci_dev_get(), couldn't the device
be entirely freed before pci_dev_get() executes, leading to a Use-After-Free?

>  }

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619085200.3729431-1-kwilczynski@kernel.org?part=1

Re: [PATCH v8 17/25] alpha/PCI: Convert resource files to static attributes

[sashiko-bot]

> Currently, Alpha's PCI resource files (resourceN, resourceN_sparse,
> resourceN_dense) are dynamically created by pci_create_resource_files(),
> which overrides the generic __weak implementation.  The current code
> allocates bin_attributes at runtime and manages them via the res_attr[]
> and res_attr_wc[] fields in struct pci_dev.
> 
> Thus, convert to static const attributes with three attribute groups
> (plain, sparse, dense), each with an .is_bin_visible callback that
> checks resource length, has_sparse(), and sparse_mem_mmap_fits().  A
> .bin_size callback provides the resource size to the kernfs node, with
> the sparse variant shifting by 5 bits for byte-level addressing.
> 
> Register the groups via ARCH_PCI_DEV_GROUPS so the driver model handles
> creation and removal automatically.
> 
> Use the new pci_resource_is_mem() helper for the type check, replacing
> the open-coded bitwise flag test.
> 
> Finally, remove pci_create_resource_files(), pci_remove_resource_files(),
> pci_create_attr(), and pci_create_one_attr() which are no longer needed.
> 
> Tested-by: Magnus Lindholm <linmag7@gmail.com>
> Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
> Acked-by: Magnus Lindholm <linmag7@gmail.com>
> Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619085200.3729431-1-kwilczynski@kernel.org?part=17

Re: [PATCH v8 24/25] PCI/sysfs: Remove pci_create_legacy_files() and pci_sysfs_init()

[sashiko-bot]

> Currently, pci_create_legacy_files() and pci_remove_legacy_files() are
> no-op stubs.  With legacy attributes now handled by static groups
> registered via pcibus_groups[], no call site needs them.
> 
> Remove both functions, their declarations, and the call sites in
> pci_register_host_bridge(), pci_alloc_child_bus(), and pci_remove_bus().
> 
> Remove the pci_sysfs_init() late_initcall and sysfs_initialized.  The
> late_initcall originally existed to create all the dynamic PCI sysfs
> files, but with both resource and legacy attributes now handled by
> static groups, it is no longer needed.
> 
> Remove the legacy_io and legacy_mem fields from struct pci_bus which
> were used to track the dynamically allocated legacy attributes.
> 
> Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
> Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619085200.3729431-1-kwilczynski@kernel.org?part=24

Re: [PATCH v8 06/25] PCI/sysfs: Add static PCI resource attribute macros

[sashiko-bot]

> Add three macros for declaring static binary attributes for PCI
> resource files:
> 
>   - pci_dev_resource_io_attr(), for I/O BAR resources (read/write)
>   - pci_dev_resource_uc_attr(), for memory BAR resources (mmap uncached)
>   - pci_dev_resource_wc_attr(), for write-combine resources (mmap WC)
> 
> Each macro only sets the callbacks its resource type needs.  The I/O
> macro conditionally includes mmap support via __PCI_RESOURCE_IO_MMAP_ATTRS
> on architectures where arch_can_pci_mmap_io() is true at compile time
> (such as PowerPC, SPARC, and Xtensa).
> 
> Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
> Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619085200.3729431-1-kwilczynski@kernel.org?part=6

Re: [PATCH v8 14/25] alpha/PCI: Fix __pci_mmap_fits() overflow for zero-length BARs

[sashiko-bot]

> Currently, __pci_mmap_fits() computes the BAR size using
> pci_resource_len() - 1, which wraps to a large value when the
> BAR length is zero, causing the bounds check to incorrectly
> succeed.
> 
> Thus, add an early return for empty resources.
> 
> Fixes: 10a0ef39fbd1 ("PCI/alpha: pci sysfs resources")
> Tested-by: Magnus Lindholm <linmag7@gmail.com>
> Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
> Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
> Acked-by: Magnus Lindholm <linmag7@gmail.com>
> Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619085200.3729431-1-kwilczynski@kernel.org?part=14

Re: [PATCH v8 20/25] alpha/PCI: Compute legacy size in pci_mmap_legacy_page_range()

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:

Pre-existing issues:
- [High] Legacy PCI sysfs interfaces (legacy_mem and legacy_io) bypass the `security_locked_down(LOCKDOWN_PCI_ACCESS)` check.
--

commit db07f943a60b56a40842995e84a339a8791f8af6
Author: Krzysztof Wilczyński <kwilczynski@kernel.org>

alpha/PCI: Compute legacy size in pci_mmap_legacy_page_range()

This commit updates pci_mmap_legacy_page_range() to compute the legacy
resource size directly using PCI_LEGACY_MEM_SIZE and PCI_LEGACY_IO_SIZE
macros. This decouples the bounds check from struct pci_bus fields that
are planned for removal.

> diff --git a/arch/alpha/kernel/pci-sysfs.c b/arch/alpha/kernel/pci-sysfs.c
> index ae448a2e40c54..74c9145e02536 100644
> --- a/arch/alpha/kernel/pci-sysfs.c
> +++ b/arch/alpha/kernel/pci-sysfs.c
> @@ -173,8 +173,11 @@ int pci_mmap_legacy_page_range(struct pci_bus *bus, struct vm_area_struct *vma,
>  	int sparse = has_sparse(hose, mmap_type);
>  	unsigned long res_size;
>  
> -	res_size = (mmap_type == pci_mmap_mem) ? bus->legacy_mem->size :
> -						 bus->legacy_io->size;
> +	res_size = (mmap_type == pci_mmap_mem) ? PCI_LEGACY_MEM_SIZE :
> +						 PCI_LEGACY_IO_SIZE;
> +	if (sparse)
> +		res_size <<= 5;
> +

[Severity: High]
This is a pre-existing issue, but since we are updating the legacy PCI
mmap paths here, I noticed that the generic legacy sysfs interfaces
appear to bypass kernel lockdown restrictions.

Looking at drivers/pci/pci-sysfs.c, functions like pci_mmap_legacy_mem()
and pci_read_legacy_io() do not seem to verify the lockdown status before
granting userspace access to raw PCI memory and I/O ports.

Standard PCI resources correctly check
security_locked_down(LOCKDOWN_PCI_ACCESS) in pci_mmap_resource(), but
the legacy handlers seem to omit this verification.

Could this allow a privileged user to bypass Secure Boot kernel lockdown
by mapping and accessing raw hardware resources directly through these
legacy interfaces?

>  	if (!__legacy_mmap_fits(vma, res_size))
>  		return -EINVAL;
>

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619085200.3729431-1-kwilczynski@kernel.org?part=20

Re: [PATCH v8 19/25] PCI: Add macros for legacy I/O and memory address space sizes

[sashiko-bot]

> Add defines for the standard PCI legacy address space sizes,
> replacing the raw literals used by the legacy sysfs attributes.
> 
> Then, replace open-coded values with the newly added macros.
> 
> No functional changes intended.
> 
> Suggested-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
> Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
> Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619085200.3729431-1-kwilczynski@kernel.org?part=19

Re: [PATCH v8 23/25] PCI/sysfs: Convert legacy I/O and memory attributes to static definitions

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Low] Unused fields `legacy_io` and `legacy_mem` in `struct pci_bus`.
--

commit 7da0447cc07dd2c8c43599562ff0122344fb1754
Author: Krzysztof Wilczyński <kwilczynski@kernel.org>

PCI/sysfs: Convert legacy I/O and memory attributes to static definitions

This commit converts legacy_io and legacy_mem sysfs attributes from dynamic
allocation to static definitions. It leverages static attribute groups and
is_bin_visible() callbacks to handle sysfs creation and removal automatically.

> diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
> index 7f1d8e07924f5..dfb4e06677fce 100644
> --- a/drivers/pci/pci-sysfs.c
> +++ b/drivers/pci/pci-sysfs.c
[ ... ]
> -void pci_create_legacy_files(struct pci_bus *b)
> -{
> -	int error;
> -
> -	if (!sysfs_initialized)
> -		return;
> -
> -	b->legacy_io = kzalloc_objs(struct bin_attribute, 2, GFP_ATOMIC);

[Severity: Low]
Since this patch removes the dynamic allocation and assignments to
b->legacy_io and b->legacy_mem, are these fields in struct pci_bus
(defined in include/linux/pci.h) now completely unused?

If they are dead code, should they also be removed from struct pci_bus
to reduce the size of the structure?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619085200.3729431-1-kwilczynski@kernel.org?part=23

Re: [PATCH v8 22/25] PCI/sysfs: Add legacy I/O and memory attribute macros

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:

Pre-existing issues:
- [High] An out-of-bounds heap read occurs in `pci_write_legacy_io` when a user writes 1 or 2 bytes to the `legacy_io` sysfs file.
--

commit 9cf38c5cdfc69788fc6aaf6dcdc29d5b5da5960b
Author: Krzysztof Wilczyński <kwilczynski@kernel.org>

PCI/sysfs: Add legacy I/O and memory attribute macros

Add two macros for declaring static binary attributes for PCI legacy
I/O port and ISA memory space files.

> diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
> index a861484ac0c08..7f1d8e07924f5 100644
> --- a/drivers/pci/pci-sysfs.c
> +++ b/drivers/pci/pci-sysfs.c
> @@ -893,6 +893,27 @@ pci_llseek_resource_legacy(struct file *filep,
>  }
>  
>  #ifdef HAVE_PCI_LEGACY
> +
> +#define pci_legacy_resource_io_attr(_suffix, _size)				\
> +static const struct bin_attribute pci_legacy_io##_suffix##_attr = {		\
> +	.attr = { .name = "legacy_io" __stringify(_suffix), .mode = 0600 },	\
> +	.size = (_size),							\
> +	.read = pci_read_legacy_io,						\
> +	.write = pci_write_legacy_io,						\

[Severity: High]
This isn't a bug introduced by this patch, but can the use of
pci_write_legacy_io() here trigger an out-of-bounds heap read?

When a user writes 1 or 2 bytes to a legacy_io sysfs file,
kernfs_fop_write_iter() allocates a buffer of count + 1 bytes.

In pci_write_legacy_io(), after validating count is 1, 2, or 4, the buffer is
cast and unconditionally dereferenced as a u32:

drivers/pci/pci-sysfs.c:pci_write_legacy_io() {
        /* Only support 1, 2 or 4 byte accesses */
        if (count != 1 && count != 2 && count != 4)
                return -EINVAL;

        return pci_legacy_write(bus, off, *(u32 *)buf, count);
}

Does the *(u32 *)buf dereference cause a 4-byte read from the smaller 2-byte
or 3-byte buffer, potentially triggering a KASAN slab-out-of-bounds read?

> +	.f_mapping = iomem_get_mapping,						\
> +	.llseek = pci_llseek_resource_legacy,					\
> +	.mmap = pci_mmap_legacy_io,						\
> +}

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619085200.3729431-1-kwilczynski@kernel.org?part=22

Re: [PATCH v8 18/25] PCI/sysfs: Remove pci_{create,remove}_sysfs_dev_files()

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] PCI resource sysfs files are exposed to userspace before their resources are assigned.
--

commit 650a832c0afdbb810823f509ec90847d6a613433
Author: Krzysztof Wilczyński <kwilczynski@kernel.org>

PCI/sysfs: Remove pci_{create,remove}_sysfs_dev_files()

Currently, pci_create_sysfs_dev_files() and pci_remove_sysfs_dev_files()
are no-op stubs. With both the generic and Alpha resource files now
handled by static attribute groups, no platform needs dynamic per-device
sysfs file creation.

> diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
> index 6c1ad1f542d9b..655ed53436d3e 100644
> --- a/drivers/pci/bus.c
> +++ b/drivers/pci/bus.c
> @@ -354,7 +354,6 @@ void pci_bus_add_device(struct pci_dev *dev)
>  	pci_fixup_device(pci_fixup_final, dev);
>  	if (pci_is_bridge(dev))
>  		of_pci_make_dev_node(dev);
> -	pci_create_sysfs_dev_files(dev);

[Severity: High]
With the transition to static attribute groups handling the resource files,
are the resources being exposed to userspace before they are actually assigned?

Static attribute groups are created early during device_add() in
pci_device_add(). If firmware has not programmed the BARs at this stage, the
resources remain unassigned with start = 0 and the IORESOURCE_UNSET flag.

Looking at the visibility callback in drivers/pci/pci-sysfs.c:

__pci_resource_attr_is_visible()
{
	...
	if (!pci_resource_len(pdev, bar))
		return 0;

	if ((pci_resource_flags(pdev, bar) & flags) != flags)
		return 0;
	...
}

There is no check for IORESOURCE_UNSET.

Since device_add() triggers a KOBJ_ADD uevent, could userspace immediately open
these files before pci_assign_unassigned_bus_resources() assigns the actual
addresses?

If userspace reads or writes an I/O resource file during this window,
pci_resource_io() would use start = 0, which could allow arbitrary root writes
to I/O port 0 and potentially crash the system.

>  	pci_proc_attach_device(dev);
>  	pci_bridge_d3_update(dev);
>  

[ ... ]

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619085200.3729431-1-kwilczynski@kernel.org?part=18

Re: [PATCH v8 09/25] PCI/sysfs: Add stubs for pci_{create,remove}_sysfs_dev_files()

[sashiko-bot]

> On platforms with HAVE_PCI_MMAP or ARCH_GENERIC_PCI_MMAP_RESOURCE,
> resource files are now handled by static attribute groups registered
> via pci_dev_groups[].
> 
> Thus, the pci_create_sysfs_dev_files() and pci_remove_sysfs_dev_files()
> can now be stubbed out, as the dynamic resource file creation is no
> longer needed.
> 
> Also, simplify pci_sysfs_init() on these platforms to only iterate
> buses for legacy attributes creation, skipping the per-device loop.
> 
> Move the __weak stubs for pci_create_resource_files() and
> pci_remove_resource_files() into the #else branch since only platforms
> without HAVE_PCI_MMAP (such as Alpha architecture) still need them.
> Guard the res_attr[] and res_attr_wc[] fields in struct pci_dev the
> same way.
> 
> Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
> Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619085200.3729431-1-kwilczynski@kernel.org?part=9

Re: [PATCH v8 25/25] PCI/sysfs: Limit BAR resize attribute scope to platforms with PCI mmap

[sashiko-bot]

> Currently, __resource_resize_store() uses sysfs_remove_groups()
> and sysfs_create_groups() on pci_dev_resource_attr_groups to
> tear down and recreate the resourceN files after a BAR resize,
> so the updated BAR sizes are visible in sysfs.
> 
> The resourceN files only exist on platforms that define
> HAVE_PCI_MMAP or ARCH_GENERIC_PCI_MMAP_RESOURCE.  On platforms
> that define neither, pci_dev_resource_attr_groups is NULL and
> the sysfs_remove_groups() and sysfs_create_groups() calls in
> __resource_resize_store() become no-ops.
> 
> Resizable BAR (ReBAR) is a PCI Express extended capability
> (PCI_EXT_CAP_ID_REBAR) that requires PCIe extended config
> space.  Every PCIe-capable architecture defines HAVE_PCI_MMAP
> or ARCH_GENERIC_PCI_MMAP_RESOURCE (via arch headers or the
> asm-generic/pci.h fallback).  Architectures without either
> only support conventional PCI and cannot have any ReBAR-capable
> devices.
> 
> Thus, move the resize show and store helpers, the per-BAR attribute
> definitions, and the attribute group behind the existing #ifdef
> HAVE_PCI_MMAP || ARCH_GENERIC_PCI_MMAP_RESOURCE guard, and fold the
> group reference in pci_dev_groups[] into the existing #if block.
> 
> Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
> Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619085200.3729431-1-kwilczynski@kernel.org?part=25

Re: [PATCH v8 10/25] PCI/sysfs: Limit pci_sysfs_init() late_initcall compile scope

[sashiko-bot]

> Currently, pci_sysfs_init() and sysfs_initialized compile
> unconditionally, even on platforms where static attribute
> groups handle all resource file creation.
> 
> Thus, place them behind a new HAVE_PCI_SYSFS_INIT macro,
> especially as the late_initcall is only needed when:
> 
>   - HAVE_PCI_LEGACY is set, to iterate buses and create legacy
>     I/O and memory files.
> 
>   - Neither HAVE_PCI_MMAP nor ARCH_GENERIC_PCI_MMAP_RESOURCE is
>     set, to iterate devices and create resource files via the
>     __weak pci_create_resource_files() stub override (this is
>     how the Alpha architecture handles this currently).
> 
> On most systems both conditions are false and the entire
> late_initcall compiles away.
> 
> Tested-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
> Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260619085200.3729431-1-kwilczynski@kernel.org?part=10

Re: [PATCH v8 22/25] PCI/sysfs: Add legacy I/O and memory attribute macros

[Krzysztof Wilczyński]

Hello,

> [Severity: High]
> This isn't a bug introduced by this patch, but can the use of
> pci_write_legacy_io() here trigger an out-of-bounds heap read?
> 
> When a user writes 1 or 2 bytes to a legacy_io sysfs file,
> kernfs_fop_write_iter() allocates a buffer of count + 1 bytes.
> 
> In pci_write_legacy_io(), after validating count is 1, 2, or 4, the buffer is
> cast and unconditionally dereferenced as a u32:
> 
> drivers/pci/pci-sysfs.c:pci_write_legacy_io() {
>         /* Only support 1, 2 or 4 byte accesses */
>         if (count != 1 && count != 2 && count != 4)
>                 return -EINVAL;
> 
>         return pci_legacy_write(bus, off, *(u32 *)buf, count);
> }
> 
> Does the *(u32 *)buf dereference cause a 4-byte read from the smaller 2-byte
> or 3-byte buffer, potentially triggering a KASAN slab-out-of-bounds read?

A known issue for which a patch with a fix has been sent.

Thank you!

	Krzysztof

Re: [PATCH v8 23/25] PCI/sysfs: Convert legacy I/O and memory attributes to static definitions

[Krzysztof Wilczyński]

Hello,

> > diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
> > index 7f1d8e07924f5..dfb4e06677fce 100644
> > --- a/drivers/pci/pci-sysfs.c
> > +++ b/drivers/pci/pci-sysfs.c
> [ ... ]
> > -void pci_create_legacy_files(struct pci_bus *b)
> > -{
> > -	int error;
> > -
> > -	if (!sysfs_initialized)
> > -		return;
> > -
> > -	b->legacy_io = kzalloc_objs(struct bin_attribute, 2, GFP_ATOMIC);
> 
> [Severity: Low]
> Since this patch removes the dynamic allocation and assignments to
> b->legacy_io and b->legacy_mem, are these fields in struct pci_bus
> (defined in include/linux/pci.h) now completely unused?
> 
> If they are dead code, should they also be removed from struct pci_bus
> to reduce the size of the structure?

Both of these struct pci_bus members are removed. The next patch does
exactly that.

Thank you,

	Krzysztof

Re: [PATCH v8 00/25] PCI: Convert all dynamic sysfs attributes to static

[Krzysztof Wilczyński]

Hello,

> This series converts every dynamically allocated PCI sysfs attribute to
> a static const definition.  After the full series, pci_sysfs_init() and
> sysfs_initialized are gone, and every sysfs file is created by the
> driver model at device_add() time.
[...]
> Changes in v8:
>   https://lore.kernel.org/linux-pci/20260508043543.217179-1-kwilczynski@kernel.org/
> 
>   - Renamed the generic resource attributes from dev_resourceN_{io,uc,wc}_attr
>     to pci_dev_resourceN_{io,uc,wc}_attr, for consistency, and cleaned up
>     resource macros definitions.
>   - Changed resource macros argument order to fix checkpatch.pl
>     complaint.
>   - Added two new macros, pci_legacy_resource_io_attr() and
>     pci_legacy_resource_mem_attr(), used for the legacy I/O and memory
>     conversion instead of open-coding each struct bin_attribute.  No
>     functional changes intended.

Updated the sysfs branch with this revision to get some testing coverage.

Changes here are mainly to clean some things up before the code potentially
lands in the mainline.  No functional changes whatsoever.

Thank you!

	Krzysztof