[PATCH v12 01/15] PCI: Let pci_mmap_page_range() take extra resource pointer

[PATCH v12 01/15] PCI: Let pci_mmap_page_range() take extra resource pointer

[Yinghai Lu]

This one is preparing patch for next one:
  PCI: Let pci_mmap_page_range() take resource addr

We need to pass extra resource pointer to avoid searching that again
for powerpc and microblaze prot set operation.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-cris-kernel@axis.com
Cc: linux-ia64@vger.kernel.org
Cc: linux-mips@linux-mips.org
Cc: linux-am33-list@redhat.com
Cc: linux-parisc@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-sh@vger.kernel.org
Cc: sparclinux@vger.kernel.org
Cc: linux-xtensa@linux-xtensa.org
---
 arch/arm/include/asm/pci.h              | 2 --
 arch/arm/kernel/bios32.c                | 3 ++-
 arch/cris/arch-v32/drivers/pci/bios.c   | 3 ++-
 arch/cris/include/asm/pci.h             | 3 ---
 arch/ia64/include/asm/pci.h             | 2 --
 arch/ia64/pci/pci.c                     | 3 ++-
 arch/microblaze/include/asm/pci.h       | 3 ---
 arch/microblaze/pci/pci-common.c        | 3 ++-
 arch/mips/include/asm/pci.h             | 3 ---
 arch/mips/pci/pci.c                     | 3 ++-
 arch/mn10300/include/asm/pci.h          | 3 ---
 arch/mn10300/unit-asb2305/pci-asb2305.c | 3 ++-
 arch/parisc/include/asm/pci.h           | 3 ---
 arch/parisc/kernel/pci.c                | 3 ++-
 arch/powerpc/include/asm/pci.h          | 3 ---
 arch/powerpc/kernel/pci-common.c        | 3 ++-
 arch/sh/drivers/pci/pci.c               | 3 ++-
 arch/sh/include/asm/pci.h               | 2 --
 arch/sparc/include/asm/pci_64.h         | 4 ----
 arch/sparc/kernel/pci.c                 | 3 ++-
 arch/unicore32/include/asm/pci.h        | 2 --
 arch/unicore32/kernel/pci.c             | 3 ++-
 arch/x86/include/asm/pci.h              | 4 ----
 arch/x86/pci/i386.c                     | 3 ++-
 arch/xtensa/include/asm/pci.h           | 4 ----
 arch/xtensa/kernel/pci.c                | 3 ++-
 drivers/pci/pci-sysfs.c                 | 2 +-
 drivers/pci/pci.h                       | 2 +-
 drivers/pci/proc.c                      | 2 +-
 include/linux/pci.h                     | 6 ++++++
 30 files changed, 35 insertions(+), 54 deletions(-)

diff --git a/arch/arm/include/asm/pci.h b/arch/arm/include/asm/pci.h
index 057d381..51118a0 100644
--- a/arch/arm/include/asm/pci.h
+++ b/arch/arm/include/asm/pci.h
@@ -29,8 +29,6 @@ static inline int pci_proc_domain(struct pci_bus *bus)
 #define PCI_DMA_BUS_IS_PHYS     (1)
 
 #define HAVE_PCI_MMAP
-extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
-                               enum pci_mmap_state mmap_state, int write_combine);
 
 static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 {
diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index 05e61a2..d3245d1 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -602,7 +602,8 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
 	return pci_enable_resources(dev, mask);
 }
 
-int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+int pci_mmap_page_range(struct pci_dev *dev, struct resource *res,
+			struct vm_area_struct *vma,
 			enum pci_mmap_state mmap_state, int write_combine)
 {
 	if (mmap_state == pci_mmap_io)
diff --git a/arch/cris/arch-v32/drivers/pci/bios.c b/arch/cris/arch-v32/drivers/pci/bios.c
index 64a5fb9..082efb9 100644
--- a/arch/cris/arch-v32/drivers/pci/bios.c
+++ b/arch/cris/arch-v32/drivers/pci/bios.c
@@ -14,7 +14,8 @@ void pcibios_set_master(struct pci_dev *dev)
 	pci_write_config_byte(dev, PCI_LATENCY_TIMER, lat);
 }
 
-int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+int pci_mmap_page_range(struct pci_dev *dev, struct resource *res,
+			struct vm_area_struct *vma,
 			enum pci_mmap_state mmap_state, int write_combine)
 {
 	unsigned long prot;
diff --git a/arch/cris/include/asm/pci.h b/arch/cris/include/asm/pci.h
index b1b289d..65198cb 100644
--- a/arch/cris/include/asm/pci.h
+++ b/arch/cris/include/asm/pci.h
@@ -42,9 +42,6 @@ struct pci_dev;
 #define PCI_DMA_BUS_IS_PHYS	(1)
 
 #define HAVE_PCI_MMAP
-extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
-			       enum pci_mmap_state mmap_state, int write_combine);
-
 
 #endif /* __KERNEL__ */
 
diff --git a/arch/ia64/include/asm/pci.h b/arch/ia64/include/asm/pci.h
index c0835b0..6a2f5d8 100644
--- a/arch/ia64/include/asm/pci.h
+++ b/arch/ia64/include/asm/pci.h
@@ -51,8 +51,6 @@ extern unsigned long ia64_max_iommu_merge_mask;
 #define PCI_DMA_BUS_IS_PHYS	(ia64_max_iommu_merge_mask == ~0UL)
 
 #define HAVE_PCI_MMAP
-extern int pci_mmap_page_range (struct pci_dev *dev, struct vm_area_struct *vma,
-				enum pci_mmap_state mmap_state, int write_combine);
 #define HAVE_PCI_LEGACY
 extern int pci_mmap_legacy_page_range(struct pci_bus *bus,
 				      struct vm_area_struct *vma,
diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c
index 8f6ac2f..1518d66 100644
--- a/arch/ia64/pci/pci.c
+++ b/arch/ia64/pci/pci.c
@@ -419,7 +419,8 @@ pcibios_align_resource (void *data, const struct resource *res,
 }
 
 int
-pci_mmap_page_range (struct pci_dev *dev, struct vm_area_struct *vma,
+pci_mmap_page_range(struct pci_dev *dev, struct resource *res,
+		     struct vm_area_struct *vma,
 		     enum pci_mmap_state mmap_state, int write_combine)
 {
 	unsigned long size = vma->vm_end - vma->vm_start;
diff --git a/arch/microblaze/include/asm/pci.h b/arch/microblaze/include/asm/pci.h
index fc3ecb5..1b93824 100644
--- a/arch/microblaze/include/asm/pci.h
+++ b/arch/microblaze/include/asm/pci.h
@@ -46,9 +46,6 @@ extern int pci_domain_nr(struct pci_bus *bus);
 extern int pci_proc_domain(struct pci_bus *bus);
 
 struct vm_area_struct;
-/* Map a range of PCI memory or I/O space for a device into user space */
-int pci_mmap_page_range(struct pci_dev *pdev, struct vm_area_struct *vma,
-			enum pci_mmap_state mmap_state, int write_combine);
 
 /* Tell drivers/pci/proc.c that we have pci_mmap_page_range() */
 #define HAVE_PCI_MMAP	1
diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c
index 14cba60..95146b0 100644
--- a/arch/microblaze/pci/pci-common.c
+++ b/arch/microblaze/pci/pci-common.c
@@ -304,7 +304,8 @@ pgprot_t pci_phys_mem_access_prot(struct file *file,
  *
  * Returns a negative error code on failure, zero on success.
  */
-int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+int pci_mmap_page_range(struct pci_dev *dev, struct resource *rp,
+			struct vm_area_struct *vma,
 			enum pci_mmap_state mmap_state, int write_combine)
 {
 	resource_size_t offset =
diff --git a/arch/mips/include/asm/pci.h b/arch/mips/include/asm/pci.h
index 86b239d..71d2c3b 100644
--- a/arch/mips/include/asm/pci.h
+++ b/arch/mips/include/asm/pci.h
@@ -75,9 +75,6 @@ extern void pcibios_set_master(struct pci_dev *dev);
 
 #define HAVE_PCI_MMAP
 
-extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
-	enum pci_mmap_state mmap_state, int write_combine);
-
 #define HAVE_ARCH_PCI_RESOURCE_TO_USER
 
 static inline void pci_resource_to_user(const struct pci_dev *dev, int bar,
diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c
index f1b11f0..e620333 100644
--- a/arch/mips/pci/pci.c
+++ b/arch/mips/pci/pci.c
@@ -319,7 +319,8 @@ void pcibios_fixup_bus(struct pci_bus *bus)
 EXPORT_SYMBOL(PCIBIOS_MIN_IO);
 EXPORT_SYMBOL(PCIBIOS_MIN_MEM);
 
-int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+int pci_mmap_page_range(struct pci_dev *dev, struct resource *res,
+			struct vm_area_struct *vma,
 			enum pci_mmap_state mmap_state, int write_combine)
 {
 	unsigned long prot;
diff --git a/arch/mn10300/include/asm/pci.h b/arch/mn10300/include/asm/pci.h
index 51159ff..082b6de 100644
--- a/arch/mn10300/include/asm/pci.h
+++ b/arch/mn10300/include/asm/pci.h
@@ -74,9 +74,6 @@ static inline int pci_controller_num(struct pci_dev *dev)
 }
 
 #define HAVE_PCI_MMAP
-extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
-			       enum pci_mmap_state mmap_state,
-			       int write_combine);
 
 #endif /* __KERNEL__ */
 
diff --git a/arch/mn10300/unit-asb2305/pci-asb2305.c b/arch/mn10300/unit-asb2305/pci-asb2305.c
index b7ab837..40efdc6 100644
--- a/arch/mn10300/unit-asb2305/pci-asb2305.c
+++ b/arch/mn10300/unit-asb2305/pci-asb2305.c
@@ -211,7 +211,8 @@ void __init pcibios_resource_survey(void)
 	pcibios_allocate_resources(1);
 }
 
-int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+int pci_mmap_page_range(struct pci_dev *dev, struct resource *res,
+			struct vm_area_struct *vma,
 			enum pci_mmap_state mmap_state, int write_combine)
 {
 	unsigned long prot;
diff --git a/arch/parisc/include/asm/pci.h b/arch/parisc/include/asm/pci.h
index defebd9..bb9ea90 100644
--- a/arch/parisc/include/asm/pci.h
+++ b/arch/parisc/include/asm/pci.h
@@ -201,7 +201,4 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 
 #define HAVE_PCI_MMAP
 
-extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
-	enum pci_mmap_state mmap_state, int write_combine);
-
 #endif /* __ASM_PARISC_PCI_H */
diff --git a/arch/parisc/kernel/pci.c b/arch/parisc/kernel/pci.c
index 0903c6a..8d5c34c 100644
--- a/arch/parisc/kernel/pci.c
+++ b/arch/parisc/kernel/pci.c
@@ -228,7 +228,8 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res,
 }
 
 
-int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+int pci_mmap_page_range(struct pci_dev *dev, struct resource *res,
+			struct vm_area_struct *vma,
 			enum pci_mmap_state mmap_state, int write_combine)
 {
 	unsigned long prot;
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index a6f3ac0..662c1ef 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -77,9 +77,6 @@ extern int pci_domain_nr(struct pci_bus *bus);
 extern int pci_proc_domain(struct pci_bus *bus);
 
 struct vm_area_struct;
-/* Map a range of PCI memory or I/O space for a device into user space */
-int pci_mmap_page_range(struct pci_dev *pdev, struct vm_area_struct *vma,
-			enum pci_mmap_state mmap_state, int write_combine);
 
 /* Tell drivers/pci/proc.c that we have pci_mmap_page_range() */
 #define HAVE_PCI_MMAP	1
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 0f7a60f..6720b81 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -445,7 +445,8 @@ pgprot_t pci_phys_mem_access_prot(struct file *file,
  *
  * Returns a negative error code on failure, zero on success.
  */
-int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+int pci_mmap_page_range(struct pci_dev *dev, struct resource *rp,
+			struct vm_area_struct *vma,
 			enum pci_mmap_state mmap_state, int write_combine)
 {
 	resource_size_t offset =
diff --git a/arch/sh/drivers/pci/pci.c b/arch/sh/drivers/pci/pci.c
index d5462b7..a1bc7ba 100644
--- a/arch/sh/drivers/pci/pci.c
+++ b/arch/sh/drivers/pci/pci.c
@@ -269,7 +269,8 @@ void __init_refok pcibios_report_status(unsigned int status_mask, int warn)
 	}
 }
 
-int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+int pci_mmap_page_range(struct pci_dev *dev, struct resource *res,
+			struct vm_area_struct *vma,
 			enum pci_mmap_state mmap_state, int write_combine)
 {
 	/*
diff --git a/arch/sh/include/asm/pci.h b/arch/sh/include/asm/pci.h
index 644314f..8e0fdb9 100644
--- a/arch/sh/include/asm/pci.h
+++ b/arch/sh/include/asm/pci.h
@@ -66,8 +66,6 @@ extern unsigned long PCIBIOS_MIN_IO, PCIBIOS_MIN_MEM;
 struct pci_dev;
 
 #define HAVE_PCI_MMAP
-extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
-	enum pci_mmap_state mmap_state, int write_combine);
 extern void pcibios_set_master(struct pci_dev *dev);
 
 /* Dynamic DMA mapping stuff.
diff --git a/arch/sparc/include/asm/pci_64.h b/arch/sparc/include/asm/pci_64.h
index 022d160..f7a93df 100644
--- a/arch/sparc/include/asm/pci_64.h
+++ b/arch/sparc/include/asm/pci_64.h
@@ -45,10 +45,6 @@ static inline int pci_proc_domain(struct pci_bus *bus)
 #define HAVE_ARCH_PCI_GET_UNMAPPED_AREA
 #define get_pci_unmapped_area get_fb_unmapped_area
 
-int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
-			enum pci_mmap_state mmap_state,
-			int write_combine);
-
 static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 {
 	return PCI_IRQ_NONE;
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index c2b202d..86d7dda 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -862,7 +862,8 @@ static void __pci_mmap_set_pgprot(struct pci_dev *dev, struct vm_area_struct *vm
  *
  * Returns a negative error code on failure, zero on success.
  */
-int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+int pci_mmap_page_range(struct pci_dev *dev, struct resource *res,
+			struct vm_area_struct *vma,
 			enum pci_mmap_state mmap_state,
 			int write_combine)
 {
diff --git a/arch/unicore32/include/asm/pci.h b/arch/unicore32/include/asm/pci.h
index 37e55d0..a5129086 100644
--- a/arch/unicore32/include/asm/pci.h
+++ b/arch/unicore32/include/asm/pci.h
@@ -17,8 +17,6 @@
 #include <mach/hardware.h> /* for PCIBIOS_MIN_* */
 
 #define HAVE_PCI_MMAP
-extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
-	enum pci_mmap_state mmap_state, int write_combine);
 
 #endif /* __KERNEL__ */
 #endif
diff --git a/arch/unicore32/kernel/pci.c b/arch/unicore32/kernel/pci.c
index d45fa5f..ff1b7ef 100644
--- a/arch/unicore32/kernel/pci.c
+++ b/arch/unicore32/kernel/pci.c
@@ -362,7 +362,8 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
 	return 0;
 }
 
-int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+int pci_mmap_page_range(struct pci_dev *dev, struct resource *res,
+			struct vm_area_struct *vma,
 			enum pci_mmap_state mmap_state, int write_combine)
 {
 	unsigned long phys;
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 9ab7507..eb87481 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -88,10 +88,6 @@ int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq);
 
 
 #define HAVE_PCI_MMAP
-extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
-			       enum pci_mmap_state mmap_state,
-			       int write_combine);
-
 
 #ifdef CONFIG_PCI
 extern void early_quirks(void);
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 0a9f2ca..36463c7 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -411,7 +411,8 @@ static const struct vm_operations_struct pci_mmap_ops = {
 	.access = generic_access_phys,
 };
 
-int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+int pci_mmap_page_range(struct pci_dev *dev, struct resource *res,
+			struct vm_area_struct *vma,
 			enum pci_mmap_state mmap_state, int write_combine)
 {
 	unsigned long prot;
diff --git a/arch/xtensa/include/asm/pci.h b/arch/xtensa/include/asm/pci.h
index 5d6bd93..bb5510b 100644
--- a/arch/xtensa/include/asm/pci.h
+++ b/arch/xtensa/include/asm/pci.h
@@ -46,10 +46,6 @@ struct pci_dev;
 
 #define PCI_DMA_BUS_IS_PHYS	(1)
 
-/* Map a range of PCI memory or I/O space for a device into user space */
-int pci_mmap_page_range(struct pci_dev *pdev, struct vm_area_struct *vma,
-			enum pci_mmap_state mmap_state, int write_combine);
-
 /* Tell drivers/pci/proc.c that we have pci_mmap_page_range() */
 #define HAVE_PCI_MMAP	1
 
diff --git a/arch/xtensa/kernel/pci.c b/arch/xtensa/kernel/pci.c
index b848cc3..89c8687 100644
--- a/arch/xtensa/kernel/pci.c
+++ b/arch/xtensa/kernel/pci.c
@@ -362,7 +362,8 @@ __pci_mmap_set_pgprot(struct pci_dev *dev, struct vm_area_struct *vma,
  *
  * Returns a negative error code on failure, zero on success.
  */
-int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+int pci_mmap_page_range(struct pci_dev *dev, struct resource *res,
+			struct vm_area_struct *vma,
 			enum pci_mmap_state mmap_state,
 			int write_combine)
 {
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index d319a9c..5bbe20c 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -1027,7 +1027,7 @@ static int pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr,
 	pci_resource_to_user(pdev, i, res, &start, &end);
 	vma->vm_pgoff += start >> PAGE_SHIFT;
 	mmap_type = res->flags & IORESOURCE_MEM ? pci_mmap_mem : pci_mmap_io;
-	return pci_mmap_page_range(pdev, vma, mmap_type, write_combine);
+	return pci_mmap_page_range(pdev, res, vma, mmap_type, write_combine);
 }
 
 static int pci_mmap_resource_uc(struct file *filp, struct kobject *kobj,
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index a814bbb..7d339c3 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -30,7 +30,7 @@ enum pci_mmap_api {
 	PCI_MMAP_PROCFS	/* mmap on /proc/bus/pci/<BDF> */
 };
 int pci_mmap_fits(struct pci_dev *pdev, int resno, struct vm_area_struct *vmai,
-		  enum pci_mmap_api mmap_api);
+		  enum pci_mmap_state mmap_type, enum pci_mmap_api mmap_api);
 #endif
 int pci_probe_reset_function(struct pci_dev *dev);
 
diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c
index 3f155e7..f19ee2a 100644
--- a/drivers/pci/proc.c
+++ b/drivers/pci/proc.c
@@ -245,7 +245,7 @@ static int proc_bus_pci_mmap(struct file *file, struct vm_area_struct *vma)
 	if (i >= PCI_ROM_RESOURCE)
 		return -ENODEV;
 
-	ret = pci_mmap_page_range(dev, vma,
+	ret = pci_mmap_page_range(dev, &dev->resource[i], vma,
 				  fpriv->mmap_state,
 				  fpriv->write_combine);
 	if (ret < 0)
diff --git a/include/linux/pci.h b/include/linux/pci.h
index b67e4df..3c1a0f4 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -70,6 +70,12 @@ enum pci_mmap_state {
 	pci_mmap_mem
 };
 
+struct vm_area_struct;
+/* Map a range of PCI memory or I/O space for a device into user space */
+int pci_mmap_page_range(struct pci_dev *dev, struct resource *res,
+			struct vm_area_struct *vma,
+			enum pci_mmap_state mmap_state, int write_combine);
+
 /*
  *  For PCI devices, the region numbers are assigned this way:
  */
-- 
2.8.3

[PATCH v12 02/15] PCI: Let pci_mmap_page_range() take resource address

[Yinghai Lu]

In 8c05cd08a7 ("PCI: fix offset check for sysfs mmapped files"), try
to check exposed value with resource start/end in proc mmap path.

|        start = vma->vm_pgoff;
|        size = ((pci_resource_len(pdev, resno) - 1) >> PAGE_SHIFT) + 1;
|        pci_start = (mmap_api == PCI_MMAP_PROCFS) ?
|                        pci_resource_start(pdev, resno) >> PAGE_SHIFT : 0;
|        if (start >= pci_start && start < pci_start + size &&
|                        start + nr <= pci_start + size)

That breaks sparc that exposed value is BAR value, and need to be offseted
to resource address.

Original pci_mmap_page_range() is taking PCI BAR value aka usr_address.

Bjorn found out that it would be much simple to pass resource address
directly and avoid extra those __pci_mmap_make_offset.

In this patch:
1. in proc path: proc_bus_pci_mmap, try convert back to resource
   before calling pci_mmap_page_range
2. in sysfs path: pci_mmap_resource will just offset with resource start.
3. all pci_mmap_page_range will have vma->vm_pgoff with in resource
   range instead of BAR value.
4. remove __pci_mmap_make_offset, as the checking is done
   in pci_mmap_fits().

-v2: add pci_user_to_resource and remove __pci_mmap_make_offset
-v3: pass resource pointer with pci_mmap_page_range()

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Cc: sparclinux@vger.kernel.org
Cc: linux-xtensa@linux-xtensa.org
---
 arch/microblaze/pci/pci-common.c |  78 +++-----------------------
 arch/powerpc/kernel/pci-common.c |  78 +++-----------------------
 arch/sparc/kernel/pci.c          | 117 ---------------------------------------
 arch/xtensa/kernel/pci.c         |  75 ++++---------------------
 drivers/pci/pci-sysfs.c          |  33 ++++++++---
 drivers/pci/proc.c               |  63 ++++++++++++++++++---
 6 files changed, 104 insertions(+), 340 deletions(-)

diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c
index 95146b0..4e21993 100644
--- a/arch/microblaze/pci/pci-common.c
+++ b/arch/microblaze/pci/pci-common.c
@@ -156,69 +156,6 @@ void pcibios_set_master(struct pci_dev *dev)
  */
 
 /*
- * Adjust vm_pgoff of VMA such that it is the physical page offset
- * corresponding to the 32-bit pci bus offset for DEV requested by the user.
- *
- * Basically, the user finds the base address for his device which he wishes
- * to mmap.  They read the 32-bit value from the config space base register,
- * add whatever PAGE_SIZE multiple offset they wish, and feed this into the
- * offset parameter of mmap on /proc/bus/pci/XXX for that device.
- *
- * Returns negative error code on failure, zero on success.
- */
-static struct resource *__pci_mmap_make_offset(struct pci_dev *dev,
-					       resource_size_t *offset,
-					       enum pci_mmap_state mmap_state)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	unsigned long io_offset = 0;
-	int i, res_bit;
-
-	if (!hose)
-		return NULL;		/* should never happen */
-
-	/* If memory, add on the PCI bridge address offset */
-	if (mmap_state == pci_mmap_mem) {
-#if 0 /* See comment in pci_resource_to_user() for why this is disabled */
-		*offset += hose->pci_mem_offset;
-#endif
-		res_bit = IORESOURCE_MEM;
-	} else {
-		io_offset = (unsigned long)hose->io_base_virt - _IO_BASE;
-		*offset += io_offset;
-		res_bit = IORESOURCE_IO;
-	}
-
-	/*
-	 * Check that the offset requested corresponds to one of the
-	 * resources of the device.
-	 */
-	for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
-		struct resource *rp = &dev->resource[i];
-		int flags = rp->flags;
-
-		/* treat ROM as memory (should be already) */
-		if (i == PCI_ROM_RESOURCE)
-			flags |= IORESOURCE_MEM;
-
-		/* Active and same type? */
-		if ((flags & res_bit) == 0)
-			continue;
-
-		/* In the range of this resource? */
-		if (*offset < (rp->start & PAGE_MASK) || *offset > rp->end)
-			continue;
-
-		/* found it! construct the final physical address */
-		if (mmap_state == pci_mmap_io)
-			*offset += hose->io_base_phys - io_offset;
-		return rp;
-	}
-
-	return NULL;
-}
-
-/*
  * Set vm_page_prot of VMA, as appropriate for this architecture, for a pci
  * device mapping.
  */
@@ -310,12 +247,15 @@ int pci_mmap_page_range(struct pci_dev *dev, struct resource *rp,
 {
 	resource_size_t offset =
 		((resource_size_t)vma->vm_pgoff) << PAGE_SHIFT;
-	struct resource *rp;
 	int ret;
 
-	rp = __pci_mmap_make_offset(dev, &offset, mmap_state);
-	if (rp == NULL)
-		return -EINVAL;
+	if (mmap_state == pci_mmap_io) {
+		struct pci_controller *hose = pci_bus_to_host(dev->bus);
+
+		/* hose should never be NULL */
+		*offset += hose->io_base_phys -
+			 ((unsigned long)hose->io_base_virt - _IO_BASE);
+	}
 
 	vma->vm_pgoff = offset >> PAGE_SHIFT;
 	vma->vm_page_prot = __pci_mmap_set_pgprot(dev, rp,
@@ -494,9 +434,7 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar,
 	 *
 	 * Hopefully, the sysfs insterface is immune to that gunk. Once X
 	 * has been fixed (and the fix spread enough), we can re-enable the
-	 * 2 lines below and pass down a BAR value to userland. In that case
-	 * we'll also have to re-enable the matching code in
-	 * __pci_mmap_make_offset().
+	 * 2 lines below and pass down a BAR value to userland.
 	 *
 	 * BenH.
 	 */
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 6720b81..7c7f652 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -293,69 +293,6 @@ static int pci_read_irq_line(struct pci_dev *pci_dev)
  */
 
 /*
- * Adjust vm_pgoff of VMA such that it is the physical page offset
- * corresponding to the 32-bit pci bus offset for DEV requested by the user.
- *
- * Basically, the user finds the base address for his device which he wishes
- * to mmap.  They read the 32-bit value from the config space base register,
- * add whatever PAGE_SIZE multiple offset they wish, and feed this into the
- * offset parameter of mmap on /proc/bus/pci/XXX for that device.
- *
- * Returns negative error code on failure, zero on success.
- */
-static struct resource *__pci_mmap_make_offset(struct pci_dev *dev,
-					       resource_size_t *offset,
-					       enum pci_mmap_state mmap_state)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	unsigned long io_offset = 0;
-	int i, res_bit;
-
-	if (hose == NULL)
-		return NULL;		/* should never happen */
-
-	/* If memory, add on the PCI bridge address offset */
-	if (mmap_state == pci_mmap_mem) {
-#if 0 /* See comment in pci_resource_to_user() for why this is disabled */
-		*offset += hose->pci_mem_offset;
-#endif
-		res_bit = IORESOURCE_MEM;
-	} else {
-		io_offset = (unsigned long)hose->io_base_virt - _IO_BASE;
-		*offset += io_offset;
-		res_bit = IORESOURCE_IO;
-	}
-
-	/*
-	 * Check that the offset requested corresponds to one of the
-	 * resources of the device.
-	 */
-	for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
-		struct resource *rp = &dev->resource[i];
-		int flags = rp->flags;
-
-		/* treat ROM as memory (should be already) */
-		if (i == PCI_ROM_RESOURCE)
-			flags |= IORESOURCE_MEM;
-
-		/* Active and same type? */
-		if ((flags & res_bit) == 0)
-			continue;
-
-		/* In the range of this resource? */
-		if (*offset < (rp->start & PAGE_MASK) || *offset > rp->end)
-			continue;
-
-		/* found it! construct the final physical address */
-		if (mmap_state == pci_mmap_io)
-			*offset += hose->io_base_phys - io_offset;
-		return rp;
-	}
-
-	return NULL;
-}
-
-/*
  * Set vm_page_prot of VMA, as appropriate for this architecture, for a pci
  * device mapping.
  */
@@ -451,12 +388,15 @@ int pci_mmap_page_range(struct pci_dev *dev, struct resource *rp,
 {
 	resource_size_t offset =
 		((resource_size_t)vma->vm_pgoff) << PAGE_SHIFT;
-	struct resource *rp;
 	int ret;
 
-	rp = __pci_mmap_make_offset(dev, &offset, mmap_state);
-	if (rp == NULL)
-		return -EINVAL;
+	if (mmap_state == pci_mmap_io) {
+		struct pci_controller *hose = pci_bus_to_host(dev->bus);
+
+		/* hose should never be NULL */
+		offset += hose->io_base_phys -
+			  ((unsigned long)hose->io_base_virt - _IO_BASE);
+	}
 
 	vma->vm_pgoff = offset >> PAGE_SHIFT;
 	vma->vm_page_prot = __pci_mmap_set_pgprot(dev, rp,
@@ -631,9 +571,7 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar,
 	 *
 	 * Hopefully, the sysfs insterface is immune to that gunk. Once X
 	 * has been fixed (and the fix spread enough), we can re-enable the
-	 * 2 lines below and pass down a BAR value to userland. In that case
-	 * we'll also have to re-enable the matching code in
-	 * __pci_mmap_make_offset().
+	 * 2 lines below and pass down a BAR value to userland.
 	 *
 	 * BenH.
 	 */
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index 86d7dda..4dbdad4 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -732,119 +732,6 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
 
 /* Platform support for /proc/bus/pci/X/Y mmap()s. */
 
-/* If the user uses a host-bridge as the PCI device, he may use
- * this to perform a raw mmap() of the I/O or MEM space behind
- * that controller.
- *
- * This can be useful for execution of x86 PCI bios initialization code
- * on a PCI card, like the xfree86 int10 stuff does.
- */
-static int __pci_mmap_make_offset_bus(struct pci_dev *pdev, struct vm_area_struct *vma,
-				      enum pci_mmap_state mmap_state)
-{
-	struct pci_pbm_info *pbm = pdev->dev.archdata.host_controller;
-	unsigned long space_size, user_offset, user_size;
-
-	if (mmap_state == pci_mmap_io) {
-		space_size = resource_size(&pbm->io_space);
-	} else {
-		space_size = resource_size(&pbm->mem_space);
-	}
-
-	/* Make sure the request is in range. */
-	user_offset = vma->vm_pgoff << PAGE_SHIFT;
-	user_size = vma->vm_end - vma->vm_start;
-
-	if (user_offset >= space_size ||
-	    (user_offset + user_size) > space_size)
-		return -EINVAL;
-
-	if (mmap_state == pci_mmap_io) {
-		vma->vm_pgoff = (pbm->io_space.start +
-				 user_offset) >> PAGE_SHIFT;
-	} else {
-		vma->vm_pgoff = (pbm->mem_space.start +
-				 user_offset) >> PAGE_SHIFT;
-	}
-
-	return 0;
-}
-
-/* Adjust vm_pgoff of VMA such that it is the physical page offset
- * corresponding to the 32-bit pci bus offset for DEV requested by the user.
- *
- * Basically, the user finds the base address for his device which he wishes
- * to mmap.  They read the 32-bit value from the config space base register,
- * add whatever PAGE_SIZE multiple offset they wish, and feed this into the
- * offset parameter of mmap on /proc/bus/pci/XXX for that device.
- *
- * Returns negative error code on failure, zero on success.
- */
-static int __pci_mmap_make_offset(struct pci_dev *pdev,
-				  struct vm_area_struct *vma,
-				  enum pci_mmap_state mmap_state)
-{
-	unsigned long user_paddr, user_size;
-	int i, err;
-
-	/* First compute the physical address in vma->vm_pgoff,
-	 * making sure the user offset is within range in the
-	 * appropriate PCI space.
-	 */
-	err = __pci_mmap_make_offset_bus(pdev, vma, mmap_state);
-	if (err)
-		return err;
-
-	/* If this is a mapping on a host bridge, any address
-	 * is OK.
-	 */
-	if ((pdev->class >> 8) == PCI_CLASS_BRIDGE_HOST)
-		return err;
-
-	/* Otherwise make sure it's in the range for one of the
-	 * device's resources.
-	 */
-	user_paddr = vma->vm_pgoff << PAGE_SHIFT;
-	user_size = vma->vm_end - vma->vm_start;
-
-	for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
-		struct resource *rp = &pdev->resource[i];
-		resource_size_t aligned_end;
-
-		/* Active? */
-		if (!rp->flags)
-			continue;
-
-		/* Same type? */
-		if (i == PCI_ROM_RESOURCE) {
-			if (mmap_state != pci_mmap_mem)
-				continue;
-		} else {
-			if ((mmap_state == pci_mmap_io &&
-			     (rp->flags & IORESOURCE_IO) == 0) ||
-			    (mmap_state == pci_mmap_mem &&
-			     (rp->flags & IORESOURCE_MEM) == 0))
-				continue;
-		}
-
-		/* Align the resource end to the next page address.
-		 * PAGE_SIZE intentionally added instead of (PAGE_SIZE - 1),
-		 * because actually we need the address of the next byte
-		 * after rp->end.
-		 */
-		aligned_end = (rp->end + PAGE_SIZE) & PAGE_MASK;
-
-		if ((rp->start <= user_paddr) &&
-		    (user_paddr + user_size) <= aligned_end)
-			break;
-	}
-
-	if (i > PCI_ROM_RESOURCE)
-		return -EINVAL;
-
-	return 0;
-}
-
 /* Set vm_page_prot of VMA, as appropriate for this architecture, for a pci
  * device mapping.
  */
@@ -869,10 +756,6 @@ int pci_mmap_page_range(struct pci_dev *dev, struct resource *res,
 {
 	int ret;
 
-	ret = __pci_mmap_make_offset(dev, vma, mmap_state);
-	if (ret < 0)
-		return ret;
-
 	__pci_mmap_set_pgprot(dev, vma, mmap_state);
 
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
diff --git a/arch/xtensa/kernel/pci.c b/arch/xtensa/kernel/pci.c
index 89c8687..a0e5d8d 100644
--- a/arch/xtensa/kernel/pci.c
+++ b/arch/xtensa/kernel/pci.c
@@ -272,68 +272,6 @@ pci_controller_num(struct pci_dev *dev)
  */
 
 /*
- * Adjust vm_pgoff of VMA such that it is the physical page offset
- * corresponding to the 32-bit pci bus offset for DEV requested by the user.
- *
- * Basically, the user finds the base address for his device which he wishes
- * to mmap.  They read the 32-bit value from the config space base register,
- * add whatever PAGE_SIZE multiple offset they wish, and feed this into the
- * offset parameter of mmap on /proc/bus/pci/XXX for that device.
- *
- * Returns negative error code on failure, zero on success.
- */
-static __inline__ int
-__pci_mmap_make_offset(struct pci_dev *dev, struct vm_area_struct *vma,
-		       enum pci_mmap_state mmap_state)
-{
-	struct pci_controller *pci_ctrl = (struct pci_controller*) dev->sysdata;
-	unsigned long offset = vma->vm_pgoff << PAGE_SHIFT;
-	unsigned long io_offset = 0;
-	int i, res_bit;
-
-	if (pci_ctrl == 0)
-		return -EINVAL;		/* should never happen */
-
-	/* If memory, add on the PCI bridge address offset */
-	if (mmap_state == pci_mmap_mem) {
-		res_bit = IORESOURCE_MEM;
-	} else {
-		io_offset = (unsigned long)pci_ctrl->io_space.base;
-		offset += io_offset;
-		res_bit = IORESOURCE_IO;
-	}
-
-	/*
-	 * Check that the offset requested corresponds to one of the
-	 * resources of the device.
-	 */
-	for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
-		struct resource *rp = &dev->resource[i];
-		int flags = rp->flags;
-
-		/* treat ROM as memory (should be already) */
-		if (i == PCI_ROM_RESOURCE)
-			flags |= IORESOURCE_MEM;
-
-		/* Active and same type? */
-		if ((flags & res_bit) == 0)
-			continue;
-
-		/* In the range of this resource? */
-		if (offset < (rp->start & PAGE_MASK) || offset > rp->end)
-			continue;
-
-		/* found it! construct the final physical address */
-		if (mmap_state == pci_mmap_io)
-			offset += pci_ctrl->io_space.start - io_offset;
-		vma->vm_pgoff = offset >> PAGE_SHIFT;
-		return 0;
-	}
-
-	return -EINVAL;
-}
-
-/*
  * Set vm_page_prot of VMA, as appropriate for this architecture, for a pci
  * device mapping.
  */
@@ -367,11 +305,18 @@ int pci_mmap_page_range(struct pci_dev *dev, struct resource *res,
 			enum pci_mmap_state mmap_state,
 			int write_combine)
 {
+	unsigned long offset = vma->vm_pgoff << PAGE_SHIFT;
 	int ret;
 
-	ret = __pci_mmap_make_offset(dev, vma, mmap_state);
-	if (ret < 0)
-		return ret;
+	if (mmap_state == pci_mmap_io) {
+		struct pci_controller *pci_ctrl =
+					 (struct pci_controller *)dev->sysdata;
+
+		/* pci_ctrl should never be NULL */
+		offset += pci_ctrl->io_space.start - pci_ctrl->io_space.base;
+	}
+
+	vma->vm_pgoff = offset >> PAGE_SHIFT;
 
 	__pci_mmap_set_pgprot(dev, vma, mmap_state, write_combine);
 
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 5bbe20c..307b3c0 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -967,12 +967,23 @@ void pci_remove_legacy_files(struct pci_bus *b)
 #ifdef HAVE_PCI_MMAP
 
 int pci_mmap_fits(struct pci_dev *pdev, int resno, struct vm_area_struct *vma,
+		  enum pci_mmap_state mmap_type,
 		  enum pci_mmap_api mmap_api)
 {
 	unsigned long nr, start, size, pci_start;
+	int flags;
 
 	if (pci_resource_len(pdev, resno) == 0)
 		return 0;
+
+	if (mmap_type == pci_mmap_mem)
+		flags = IORESOURCE_MEM;
+	else
+		flags = IORESOURCE_IO;
+
+	if (!(pci_resource_flags(pdev, resno) & flags))
+		return 0;
+
 	nr = vma_pages(vma);
 	start = vma->vm_pgoff;
 	size = ((pci_resource_len(pdev, resno) - 1) >> PAGE_SHIFT) + 1;
@@ -999,7 +1010,6 @@ static int pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr,
 	struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj));
 	struct resource *res = attr->private;
 	enum pci_mmap_state mmap_type;
-	resource_size_t start, end;
 	int i;
 
 	for (i = 0; i < PCI_ROM_RESOURCE; i++)
@@ -1008,10 +1018,21 @@ static int pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr,
 	if (i >= PCI_ROM_RESOURCE)
 		return -ENODEV;
 
+	/*
+	 * resource start have to be PAGE_SIZE aligned, as we pass
+	 * back virt address include round down of resource_start,
+	 * that caller can not figure out directly.
+	 * when it is not aligned, that mean it is io port, should go
+	 * pci_read_resource_io()/pci_write_resource_io() path.
+	 */
+	if (res->start & ~PAGE_MASK)
+		return -EINVAL;
+
 	if (res->flags & IORESOURCE_MEM && iomem_is_exclusive(res->start))
 		return -EINVAL;
 
-	if (!pci_mmap_fits(pdev, i, vma, PCI_MMAP_SYSFS)) {
+	mmap_type = res->flags & IORESOURCE_MEM ? pci_mmap_mem : pci_mmap_io;
+	if (!pci_mmap_fits(pdev, i, vma, mmap_type, PCI_MMAP_SYSFS)) {
 		WARN(1, "process \"%s\" tried to map 0x%08lx bytes at page 0x%08lx on %s BAR %d (start 0x%16Lx, size 0x%16Lx)\n",
 			current->comm, vma->vm_end-vma->vm_start, vma->vm_pgoff,
 			pci_name(pdev), i,
@@ -1020,13 +1041,7 @@ static int pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr,
 		return -EINVAL;
 	}
 
-	/* pci_mmap_page_range() expects the same kind of entry as coming
-	 * from /proc/bus/pci/ which is a "user visible" value. If this is
-	 * different from the resource itself, arch will do necessary fixup.
-	 */
-	pci_resource_to_user(pdev, i, res, &start, &end);
-	vma->vm_pgoff += start >> PAGE_SHIFT;
-	mmap_type = res->flags & IORESOURCE_MEM ? pci_mmap_mem : pci_mmap_io;
+	vma->vm_pgoff += res->start >> PAGE_SHIFT;
 	return pci_mmap_page_range(pdev, res, vma, mmap_type, write_combine);
 }
 
diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c
index f19ee2a..7291635 100644
--- a/drivers/pci/proc.c
+++ b/drivers/pci/proc.c
@@ -227,26 +227,71 @@ static long proc_bus_pci_ioctl(struct file *file, unsigned int cmd,
 }
 
 #ifdef HAVE_PCI_MMAP
+
+static int pci_user_to_resource(struct pci_dev *dev, resource_size_t *offset,
+				int flags)
+{
+	int i;
+
+	for (i = 0; i < PCI_ROM_RESOURCE; i++) {
+		resource_size_t start, end;
+		struct resource *res = &dev->resource[i];
+
+		if (!(res->flags & flags))
+			continue;
+
+		if (pci_resource_len(dev, i) == 0)
+			continue;
+
+		/*
+		 * here *offset is PAGE_SIZE aligned from caller.
+		 * need align start/end for io port resource that is
+		 * usually not PAGE_SIZE aligned.
+		 * that means we let it go if they falls in same page.
+		 */
+		pci_resource_to_user(dev, i, res, &start, &end);
+		if ((start & PAGE_MASK) <= *offset &&
+		     *offset <= (end & PAGE_MASK)) {
+			*offset = res->start + (*offset - start);
+			return i;
+		}
+	}
+
+	return -ENODEV;
+}
+
 static int proc_bus_pci_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct pci_dev *dev = PDE_DATA(file_inode(file));
 	struct pci_filp_private *fpriv = file->private_data;
-	int i, ret;
+	enum pci_mmap_state mmap_type = fpriv->mmap_state;
+	resource_size_t offset;
+	int i, ret, flags;
 
 	if (!capable(CAP_SYS_RAWIO))
 		return -EPERM;
 
-	/* Make sure the caller is mapping a real resource for this device */
-	for (i = 0; i < PCI_ROM_RESOURCE; i++) {
-		if (pci_mmap_fits(dev, i, vma,  PCI_MMAP_PROCFS))
-			break;
-	}
-
-	if (i >= PCI_ROM_RESOURCE)
+	offset = vma->vm_pgoff << PAGE_SHIFT;
+	if (mmap_type == pci_mmap_mem)
+		flags = IORESOURCE_MEM;
+	else
+		flags = IORESOURCE_IO;
+	i = pci_user_to_resource(dev, &offset, flags);
+	if (i < 0)
 		return -ENODEV;
 
+	vma->vm_pgoff = offset >> PAGE_SHIFT;
+	if (!pci_mmap_fits(dev, i, vma, mmap_type, PCI_MMAP_PROCFS)) {
+		WARN(1, "process \"%s\" tried to map 0x%08lx bytes at page 0x%08lx on %s BAR %d (start 0x%16Lx, size 0x%16Lx)\n",
+			current->comm, vma->vm_end-vma->vm_start, vma->vm_pgoff,
+			pci_name(dev), i,
+			(u64)pci_resource_start(dev, i),
+			(u64)pci_resource_len(dev, i));
+		return -EINVAL;
+	}
+
 	ret = pci_mmap_page_range(dev, &dev->resource[i], vma,
-				  fpriv->mmap_state,
+				  mmap_type,
 				  fpriv->write_combine);
 	if (ret < 0)
 		return ret;
-- 
2.8.3

[PATCH v12 08/15] powerpc/PCI: Keep resource idx order with bridge register number

[Yinghai Lu]

Same as sparc version.

Make resource with consistent sequence
like other arch or directly from pci_read_bridge_bases(),
even when non-pref mmio is missing, or out of ordering in firmware reporting.

Just hold i = 1 for non pref mmio, and i = 2 for pref mmio.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
---
 arch/powerpc/kernel/pci_of_scan.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index 526ac67..719f225 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -252,7 +252,7 @@ void of_scan_pci_bridge(struct pci_dev *dev)
 		bus->resource[i] = res;
 		++res;
 	}
-	i = 1;
+	i = 3;
 	for (; len >= 32; len -= 32, ranges += 8) {
 		flags = pci_parse_of_flags(of_read_number(ranges, 1), 1);
 		size = of_read_number(&ranges[6], 2);
@@ -265,6 +265,12 @@ void of_scan_pci_bridge(struct pci_dev *dev)
 				       " for bridge %s\n", node->full_name);
 				continue;
 			}
+		} else if ((flags & IORESOURCE_PREFETCH) &&
+			   !bus->resource[2]->flags) {
+			res = bus->resource[2];
+		} else if (((flags & (IORESOURCE_MEM | IORESOURCE_PREFETCH)) ==
+			    IORESOURCE_MEM) && !bus->resource[1]->flags) {
+			res = bus->resource[1];
 		} else {
 			if (i >= PCI_NUM_RESOURCES - PCI_BRIDGE_RESOURCES) {
 				printk(KERN_ERR "PCI: too many memory ranges"
-- 
2.8.3

[PATCH v12 09/15] powerpc/PCI: Add IORESOURCE_MEM_64 for 64-bit resource in OF parsing

[Yinghai Lu]

For device resource PREF bit setting under bridge 64-bit pref resource,
we need to make sure only set PREF for 64bit resource.

This patch set IORESOUCE_MEM_64 for 64bit resource during OF device resource
flags parsing.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=96261
Link: https://bugzilla.kernel.org/show_bug.cgi?id=96241
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Gavin Shan <gwshan@linux.vnet.ibm.com>
Cc: Yijing Wang <wangyijing@huawei.com>
Cc: Anton Blanchard <anton@samba.org>
Cc: linuxppc-dev@lists.ozlabs.org
---
 arch/powerpc/kernel/pci_of_scan.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index 719f225..476b8ac5 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -44,8 +44,10 @@ static unsigned int pci_parse_of_flags(u32 addr0, int bridge)
 
 	if (addr0 & 0x02000000) {
 		flags = IORESOURCE_MEM | PCI_BASE_ADDRESS_SPACE_MEMORY;
-		flags |= (addr0 >> 22) & PCI_BASE_ADDRESS_MEM_TYPE_64;
 		flags |= (addr0 >> 28) & PCI_BASE_ADDRESS_MEM_TYPE_1M;
+		if (addr0 & 0x01000000)
+			flags |= IORESOURCE_MEM_64
+				 | PCI_BASE_ADDRESS_MEM_TYPE_64;
 		if (addr0 & 0x40000000)
 			flags |= IORESOURCE_PREFETCH
 				 | PCI_BASE_ADDRESS_MEM_PREFETCH;
-- 
2.8.3

Re: [PATCH v12 01/15] PCI: Let pci_mmap_page_range() take extra resource pointer

[Jesper Nilsson]

On Fri, Jun 03, 2016 at 05:06:28PM -0700, Yinghai Lu wrote:
> This one is preparing patch for next one:
>   PCI: Let pci_mmap_page_range() take resource addr
> 
> We need to pass extra resource pointer to avoid searching that again
> for powerpc and microblaze prot set operation.
> 
> Signed-off-by: Yinghai Lu <yinghai@kernel.org>
> Cc: linux-arm-kernel@lists.infradead.org

For the CRIS part:

Acked-by: Jesper Nilsson <jesper.nilsson@axis.com>

> diff --git a/arch/cris/arch-v32/drivers/pci/bios.c b/arch/cris/arch-v32/drivers/pci/bios.c
> index 64a5fb9..082efb9 100644
> --- a/arch/cris/arch-v32/drivers/pci/bios.c
> +++ b/arch/cris/arch-v32/drivers/pci/bios.c
> @@ -14,7 +14,8 @@ void pcibios_set_master(struct pci_dev *dev)
>  	pci_write_config_byte(dev, PCI_LATENCY_TIMER, lat);
>  }
>  
> -int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
> +int pci_mmap_page_range(struct pci_dev *dev, struct resource *res,
> +			struct vm_area_struct *vma,
>  			enum pci_mmap_state mmap_state, int write_combine)
>  {
>  	unsigned long prot;
> diff --git a/arch/cris/include/asm/pci.h b/arch/cris/include/asm/pci.h
> index b1b289d..65198cb 100644
> --- a/arch/cris/include/asm/pci.h
> +++ b/arch/cris/include/asm/pci.h
> @@ -42,9 +42,6 @@ struct pci_dev;
>  #define PCI_DMA_BUS_IS_PHYS	(1)
>  
>  #define HAVE_PCI_MMAP
> -extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
> -			       enum pci_mmap_state mmap_state, int write_combine);
> -
>  
>  #endif /* __KERNEL__ */

/^JN - Jesper Nilsson
-- 
               Jesper Nilsson -- jesper.nilsson@axis.com

Re: [PATCH v12 01/15] PCI: Let pci_mmap_page_range() take extra resource pointer

[Bjorn Helgaas]

On Fri, Jun 03, 2016 at 05:06:28PM -0700, Yinghai Lu wrote:
> This one is preparing patch for next one:
>   PCI: Let pci_mmap_page_range() take resource addr
> 
> We need to pass extra resource pointer to avoid searching that again
> for powerpc and microblaze prot set operation.

I'm not convinced yet that the extra resource pointer is necessary.

Microblaze does look up the resource in pci_mmap_page_range(), but it
never actually uses it.  It *looks* like it uses it, but that code is
actually dead and I think we should apply the first patch below.

That leaves powerpc as the only arch that would use this extra
resource pointer.  It uses it in __pci_mmap_set_pgprot() to help
decide whether to make a normal uncacheable mapping or a write-
combining one.  There's nothing here that's specific to the powerpc
architecture, and I don't think we should add this parameter just to
cater to powerpc.

There are two cases where __pci_mmap_set_pgprot() on powerpc does
something based on the resource:

  1) We're using procfs to mmap I/O port space after we requested
     write-combining, e.g., we did this:

       ioctl(fd, PCIIOC_MMAP_IS_IO);           # request I/O port space
       ioctl(fd, PCIIOC_WRITE_COMBINE, 1);     # request write-combining
       mmap(fd, ...)

     On powerpc, we ignore the write-combining request in this case.

     I think we can handle this case by applying the second patch
     below to ignore write-combining on I/O space for all arches, not
     just powerpc.

  2) We're using sysfs to mmap resourceN (not resourceN_wc), and
     the resource is prefetchable.  On powerpc, we turn *on*
     write-combining, even though the user didn't ask for it.

     I'm not sure this case is actually safe, because it changes the
     ordering properties.  If it *is* safe, we could enable write-
     combining in pci_mmap_resource(), where we already have the
     resource and it could be done for all arches.

     This case is not strictly necessary, except to avoid a
     performance regression, because the user could have mapped
     resourceN_wc to explicitly request write-combining.

> diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
> index d319a9c..5bbe20c 100644
> --- a/drivers/pci/pci-sysfs.c
> +++ b/drivers/pci/pci-sysfs.c
> @@ -1027,7 +1027,7 @@ static int pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr,
>  	pci_resource_to_user(pdev, i, res, &start, &end);
>  	vma->vm_pgoff += start >> PAGE_SHIFT;
>  	mmap_type = res->flags & IORESOURCE_MEM ? pci_mmap_mem : pci_mmap_io;
> -	return pci_mmap_page_range(pdev, vma, mmap_type, write_combine);
> +	return pci_mmap_page_range(pdev, res, vma, mmap_type, write_combine);
>  }
>  
>  static int pci_mmap_resource_uc(struct file *filp, struct kobject *kobj,
> diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c
> index 3f155e7..f19ee2a 100644
> --- a/drivers/pci/proc.c
> +++ b/drivers/pci/proc.c
> @@ -245,7 +245,7 @@ static int proc_bus_pci_mmap(struct file *file, struct vm_area_struct *vma)
>  	if (i >= PCI_ROM_RESOURCE)
>  		return -ENODEV;
>  
> -	ret = pci_mmap_page_range(dev, vma,
> +	ret = pci_mmap_page_range(dev, &dev->resource[i], vma,
>  				  fpriv->mmap_state,
>  				  fpriv->write_combine);
>  	if (ret < 0)
> diff --git a/include/linux/pci.h b/include/linux/pci.h
> index b67e4df..3c1a0f4 100644
> --- a/include/linux/pci.h
> +++ b/include/linux/pci.h
> @@ -70,6 +70,12 @@ enum pci_mmap_state {
>  	pci_mmap_mem
>  };
>  
> +struct vm_area_struct;
> +/* Map a range of PCI memory or I/O space for a device into user space */
> +int pci_mmap_page_range(struct pci_dev *dev, struct resource *res,
> +			struct vm_area_struct *vma,
> +			enum pci_mmap_state mmap_state, int write_combine);
> +
>  /*
>   *  For PCI devices, the region numbers are assigned this way:
>   */


commit 4e712b691abc5b579e3e4327f56b0b7988bdd1cb
Author: Bjorn Helgaas <bhelgaas@google.com>
Date:   Wed Jun 8 14:00:14 2016 -0500

    microblaze/PCI: Remove useless __pci_mmap_set_pgprot()
    
    The microblaze __pci_mmap_set_pgprot() was apparently copied from powerpc,
    where it computes either an uncacheable pgprot_t or a write-combining one.
    But on microblaze, we always use the regular uncacheable pgprot_t.
    
    Remove the useless code in __pci_mmap_set_pgprot() and inline the
    pgprot_noncached() at the only caller.
    
    Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>

diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c
index 14cba60..1974567 100644
--- a/arch/microblaze/pci/pci-common.c
+++ b/arch/microblaze/pci/pci-common.c
@@ -219,33 +219,6 @@ static struct resource *__pci_mmap_make_offset(struct pci_dev *dev,
 }
 
 /*
- * Set vm_page_prot of VMA, as appropriate for this architecture, for a pci
- * device mapping.
- */
-static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp,
-				      pgprot_t protection,
-				      enum pci_mmap_state mmap_state,
-				      int write_combine)
-{
-	pgprot_t prot = protection;
-
-	/* Write combine is always 0 on non-memory space mappings. On
-	 * memory space, if the user didn't pass 1, we check for a
-	 * "prefetchable" resource. This is a bit hackish, but we use
-	 * this to workaround the inability of /sysfs to provide a write
-	 * combine bit
-	 */
-	if (mmap_state != pci_mmap_mem)
-		write_combine = 0;
-	else if (write_combine == 0) {
-		if (rp->flags & IORESOURCE_PREFETCH)
-			write_combine = 1;
-	}
-
-	return pgprot_noncached(prot);
-}
-
-/*
  * This one is used by /dev/mem and fbdev who have no clue about the
  * PCI device, it tries to find the PCI device first and calls the
  * above routine
@@ -317,9 +290,7 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 		return -EINVAL;
 
 	vma->vm_pgoff = offset >> PAGE_SHIFT;
-	vma->vm_page_prot = __pci_mmap_set_pgprot(dev, rp,
-						  vma->vm_page_prot,
-						  mmap_state, write_combine);
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 
 	ret = remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
 			       vma->vm_end - vma->vm_start, vma->vm_page_prot);



commit 962972ee5e0ba6ceb680cb182bad65f8886586a6
Author: Bjorn Helgaas <bhelgaas@google.com>
Date:   Wed Jun 8 14:46:54 2016 -0500

    PCI: Ignore write-combining when mapping I/O port space
    
    PCI exposes files like /proc/bus/pci/00/00.0 in procfs.  These files
    support operations like this:
    
      ioctl(fd, PCIIOC_MMAP_IS_IO);           # request I/O port space
      ioctl(fd, PCIIOC_WRITE_COMBINE, 1);     # request write-combining
      mmap(fd, ...)
    
    Many architectures don't allow mmap of I/O port space at all, but I don't
    think it makes sense to do a write-combining mapping on the ones that do.
    We could change proc_bus_pci_ioctl() so the user could never enable write-
    combining for I/O port space, but that would break the following sequence,
    which is currently legal:
    
      mmap(fd, ...)                           # default is I/O, non-combining
      ioctl(fd, PCIIOC_WRITE_COMBINE, 1);     # request write-combining
      ioctl(fd, PCIIOC_MMAP_IS_MEM);          # request memory space
      mmap(fd, ...)
    
    Ignore the write-combining flag when mapping I/O port space.
    
    Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>

diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c
index 3f155e7..21f8d613 100644
--- a/drivers/pci/proc.c
+++ b/drivers/pci/proc.c
@@ -247,7 +247,8 @@ static int proc_bus_pci_mmap(struct file *file, struct vm_area_struct *vma)
 
 	ret = pci_mmap_page_range(dev, vma,
 				  fpriv->mmap_state,
-				  fpriv->write_combine);
+				  (fpriv->mmap_state == pci_mmap_mem) ?
+					fpriv->write_combine : 0);
 	if (ret < 0)
 		return ret;
 

Re: [PATCH v12 01/15] PCI: Let pci_mmap_page_range() take extra resource pointer

[Yinghai Lu]

On Wed, Jun 8, 2016 at 2:03 PM, Bjorn Helgaas <helgaas@kernel.org> wrote:
>
> Microblaze does look up the resource in pci_mmap_page_range(), but it
> never actually uses it.  It *looks* like it uses it, but that code is
> actually dead and I think we should apply the first patch below.

Good one.

>
> That leaves powerpc as the only arch that would use this extra
> resource pointer.  It uses it in __pci_mmap_set_pgprot() to help
> decide whether to make a normal uncacheable mapping or a write-
> combining one.  There's nothing here that's specific to the powerpc
> architecture, and I don't think we should add this parameter just to
> cater to powerpc.
>
> There are two cases where __pci_mmap_set_pgprot() on powerpc does
> something based on the resource:
>
>   1) We're using procfs to mmap I/O port space after we requested
>      write-combining, e.g., we did this:
>
>        ioctl(fd, PCIIOC_MMAP_IS_IO);           # request I/O port space
>        ioctl(fd, PCIIOC_WRITE_COMBINE, 1);     # request write-combining
>        mmap(fd, ...)
>
>      On powerpc, we ignore the write-combining request in this case.
>
>      I think we can handle this case by applying the second patch
>      below to ignore write-combining on I/O space for all arches, not
>      just powerpc.
>
>   2) We're using sysfs to mmap resourceN (not resourceN_wc), and
>      the resource is prefetchable.  On powerpc, we turn *on*
>      write-combining, even though the user didn't ask for it.
>
>      I'm not sure this case is actually safe, because it changes the
>      ordering properties.  If it *is* safe, we could enable write-
>      combining in pci_mmap_resource(), where we already have the
>      resource and it could be done for all arches.
>
>      This case is not strictly necessary, except to avoid a
>      performance regression, because the user could have mapped
>      resourceN_wc to explicitly request write-combining.
>

Agreed.

>
> commit 4e712b691abc5b579e3e4327f56b0b7988bdd1cb
> Author: Bjorn Helgaas <bhelgaas@google.com>
> Date:   Wed Jun 8 14:00:14 2016 -0500
>
>     microblaze/PCI: Remove useless __pci_mmap_set_pgprot()
>
>     The microblaze __pci_mmap_set_pgprot() was apparently copied from powerpc,
>     where it computes either an uncacheable pgprot_t or a write-combining one.
>     But on microblaze, we always use the regular uncacheable pgprot_t.
>
>     Remove the useless code in __pci_mmap_set_pgprot() and inline the
>     pgprot_noncached() at the only caller.
>
>     Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
>
> diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c
> index 14cba60..1974567 100644
> --- a/arch/microblaze/pci/pci-common.c
> +++ b/arch/microblaze/pci/pci-common.c
> @@ -219,33 +219,6 @@ static struct resource *__pci_mmap_make_offset(struct pci_dev *dev,
>  }
>
>  /*
> - * Set vm_page_prot of VMA, as appropriate for this architecture, for a pci
> - * device mapping.
> - */
> -static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp,
> -                                     pgprot_t protection,
> -                                     enum pci_mmap_state mmap_state,
> -                                     int write_combine)
> -{
> -       pgprot_t prot = protection;
> -
> -       /* Write combine is always 0 on non-memory space mappings. On
> -        * memory space, if the user didn't pass 1, we check for a
> -        * "prefetchable" resource. This is a bit hackish, but we use
> -        * this to workaround the inability of /sysfs to provide a write
> -        * combine bit
> -        */
> -       if (mmap_state != pci_mmap_mem)
> -               write_combine = 0;
> -       else if (write_combine == 0) {
> -               if (rp->flags & IORESOURCE_PREFETCH)
> -                       write_combine = 1;
> -       }
> -
> -       return pgprot_noncached(prot);
> -}
> -
> -/*
>   * This one is used by /dev/mem and fbdev who have no clue about the
>   * PCI device, it tries to find the PCI device first and calls the
>   * above routine
> @@ -317,9 +290,7 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
>                 return -EINVAL;
>
>         vma->vm_pgoff = offset >> PAGE_SHIFT;
> -       vma->vm_page_prot = __pci_mmap_set_pgprot(dev, rp,
> -                                                 vma->vm_page_prot,
> -                                                 mmap_state, write_combine);
> +       vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
>
>         ret = remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
>                                vma->vm_end - vma->vm_start, vma->vm_page_prot);
>

Acked-by: Yinghai Lu <yinghai@kernel.org>

>
>
> commit 962972ee5e0ba6ceb680cb182bad65f8886586a6
> Author: Bjorn Helgaas <bhelgaas@google.com>
> Date:   Wed Jun 8 14:46:54 2016 -0500
>
>     PCI: Ignore write-combining when mapping I/O port space
>
>     PCI exposes files like /proc/bus/pci/00/00.0 in procfs.  These files
>     support operations like this:
>
>       ioctl(fd, PCIIOC_MMAP_IS_IO);           # request I/O port space
>       ioctl(fd, PCIIOC_WRITE_COMBINE, 1);     # request write-combining
>       mmap(fd, ...)
>
>     Many architectures don't allow mmap of I/O port space at all, but I don't
>     think it makes sense to do a write-combining mapping on the ones that do.
>     We could change proc_bus_pci_ioctl() so the user could never enable write-
>     combining for I/O port space, but that would break the following sequence,
>     which is currently legal:
>
>       mmap(fd, ...)                           # default is I/O, non-combining
>       ioctl(fd, PCIIOC_WRITE_COMBINE, 1);     # request write-combining
>       ioctl(fd, PCIIOC_MMAP_IS_MEM);          # request memory space
>       mmap(fd, ...)
>
>     Ignore the write-combining flag when mapping I/O port space.
>
>     Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
>
> diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c
> index 3f155e7..21f8d613 100644
> --- a/drivers/pci/proc.c
> +++ b/drivers/pci/proc.c
> @@ -247,7 +247,8 @@ static int proc_bus_pci_mmap(struct file *file, struct vm_area_struct *vma)
>
>         ret = pci_mmap_page_range(dev, vma,
>                                   fpriv->mmap_state,
> -                                 fpriv->write_combine);
> +                                 (fpriv->mmap_state == pci_mmap_mem) ?
> +                                       fpriv->write_combine : 0);
>         if (ret < 0)
>                 return ret;
>

ok to me.

At the same time, can you kill __pci_mmap_set_pgprot() for powerpc.

diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 0f7a60f..0d0148d 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -356,36 +356,6 @@ static struct resource
*__pci_mmap_make_offset(struct pci_dev *dev,
 }

 /*
- * Set vm_page_prot of VMA, as appropriate for this architecture, for a pci
- * device mapping.
- */
-static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp,
-                      pgprot_t protection,
-                      enum pci_mmap_state mmap_state,
-                      int write_combine)
-{
-
-    /* Write combine is always 0 on non-memory space mappings. On
-     * memory space, if the user didn't pass 1, we check for a
-     * "prefetchable" resource. This is a bit hackish, but we use
-     * this to workaround the inability of /sysfs to provide a write
-     * combine bit
-     */
-    if (mmap_state != pci_mmap_mem)
-        write_combine = 0;
-    else if (write_combine == 0) {
-        if (rp->flags & IORESOURCE_PREFETCH)
-            write_combine = 1;
-    }
-
-    /* XXX would be nice to have a way to ask for write-through */
-    if (write_combine)
-        return pgprot_noncached_wc(protection);
-    else
-        return pgprot_noncached(protection);
-}
-
-/*
  * This one is used by /dev/mem and fbdev who have no clue about the
  * PCI device, it tries to find the PCI device first and calls the
  * above routine
@@ -458,9 +428,10 @@ int pci_mmap_page_range(struct pci_dev *dev,
struct vm_area_struct *vma,
         return -EINVAL;

     vma->vm_pgoff = offset >> PAGE_SHIFT;
-    vma->vm_page_prot = __pci_mmap_set_pgprot(dev, rp,
-                          vma->vm_page_prot,
-                          mmap_state, write_combine);
+    if (write_combine)
+        vma->vm_page_prot = pgprot_noncached_wc(protection);
+    else
+        vma->vm_page_prot = pgprot_noncached(protection);

     ret = remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
                    vma->vm_end - vma->vm_start, vma->vm_page_prot);

Re: [PATCH v12 01/15] PCI: Let pci_mmap_page_range() take extra resource pointer

[Yinghai Lu]

[-- Attachment #1: Type: text/plain, Size: 317 bytes --]

On Wed, Jun 8, 2016 at 3:35 PM, Yinghai Lu <yinghai@kernel.org> wrote:

> At the same time, can you kill __pci_mmap_set_pgprot() for powerpc.

Can you please put your two patches and this attached one into to pci/next?

Then I could send updated PCI: Let pci_mmap_page_range() take resource address.

Thanks

Yinghai

[-- Attachment #2: remove_powerpc_pci_prot.patch --]
[-- Type: text/x-patch, Size: 2652 bytes --]

From: Bjorn Helgaas <bhelgaas@google.com>
Subject: [PATCH] powerpc/PCI: Remove __pci_mmap_set_pgprot()

  PCI: Ignore write-combining when mapping I/O port space
already handle the io port mmap path.

For mmio mmap path, caller should state that correctly if write_combine
is really needed.

via proc path it should look like:
  mmap(fd, ...)                           # default is I/O, non-combining
  ioctl(fd, PCIIOC_WRITE_COMBINE, 1);     # request write-combining
  ioctl(fd, PCIIOC_MMAP_IS_MEM);          # request memory space
  mmap(fd, ...)

sysfs path, it should use resource]?]_wc.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>

---
 arch/powerpc/kernel/pci-common.c |   37 ++++---------------------------------
 1 file changed, 4 insertions(+), 33 deletions(-)

Index: linux-2.6/arch/powerpc/kernel/pci-common.c
===================================================================
--- linux-2.6.orig/arch/powerpc/kernel/pci-common.c
+++ linux-2.6/arch/powerpc/kernel/pci-common.c
@@ -356,36 +356,6 @@ static struct resource *__pci_mmap_make_
 }
 
 /*
- * Set vm_page_prot of VMA, as appropriate for this architecture, for a pci
- * device mapping.
- */
-static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp,
-				      pgprot_t protection,
-				      enum pci_mmap_state mmap_state,
-				      int write_combine)
-{
-
-	/* Write combine is always 0 on non-memory space mappings. On
-	 * memory space, if the user didn't pass 1, we check for a
-	 * "prefetchable" resource. This is a bit hackish, but we use
-	 * this to workaround the inability of /sysfs to provide a write
-	 * combine bit
-	 */
-	if (mmap_state != pci_mmap_mem)
-		write_combine = 0;
-	else if (write_combine == 0) {
-		if (rp->flags & IORESOURCE_PREFETCH)
-			write_combine = 1;
-	}
-
-	/* XXX would be nice to have a way to ask for write-through */
-	if (write_combine)
-		return pgprot_noncached_wc(protection);
-	else
-		return pgprot_noncached(protection);
-}
-
-/*
  * This one is used by /dev/mem and fbdev who have no clue about the
  * PCI device, it tries to find the PCI device first and calls the
  * above routine
@@ -458,9 +428,10 @@ int pci_mmap_page_range(struct pci_dev *
 		return -EINVAL;
 
 	vma->vm_pgoff = offset >> PAGE_SHIFT;
-	vma->vm_page_prot = __pci_mmap_set_pgprot(dev, rp,
-						  vma->vm_page_prot,
-						  mmap_state, write_combine);
+	if (write_combine)
+		vma->vm_page_prot = pgprot_noncached_wc(vma->vm_page_prot);
+	else
+		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 
 	ret = remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
 			       vma->vm_end - vma->vm_start, vma->vm_page_prot);

Re: [PATCH v12 01/15] PCI: Let pci_mmap_page_range() take extra resource pointer

[Yinghai Lu]

On Wed, Jun 8, 2016 at 5:00 PM, Yinghai Lu <yinghai@kernel.org> wrote:
> On Wed, Jun 8, 2016 at 3:35 PM, Yinghai Lu <yinghai@kernel.org> wrote:
>
>> At the same time, can you kill __pci_mmap_set_pgprot() for powerpc.
>
> Can you please put your two patches and this attached one into to pci/next?
>
> Then I could send updated PCI: Let pci_mmap_page_range() take resource address.

Thanks for putting those patches in pci/resource branch.

I just re post updated for second patch.

[v12.update2,02/15] PCI: Let pci_mmap_page_range() take resource address
http://patchwork.ozlabs.org/patch/633399/

And the [v12 01/15] is not needed anymore.

patch3 to patch15 should still can be applied to pci/resource without problem.

Thanks

Yinghai