Merge branch 'pci/resource-mmap' into next

* pci/resource-mmap: ia64: Use generic pci_mmap_resource_range() ia64: Remove redundant checks for WC in pci_mmap_page_range() ia64: Remove redundant valid_mmap_phys_addr_range() from pci_mmap_page_range() PCI: Add I/O BAR support to generic pci_mmap_resource_range() x86/PCI: Use generic pci_mmap_resource_range() unicore32/PCI: Use generic pci_mmap_resource_range() sh/PCI: Use generic pci_mmap_resource_range() parisc: Use generic pci_mmap_resource_range() mn10300/PCI: Use generic pci_mmap_resource_range() MIPS: PCI: Use generic pci_mmap_resource_range() cris/PCI: Use generic pci_mmap_resource_range() ARM/PCI: Use generic pci_mmap_resource_range() PCI: Add pci_mmap_resource_range() and use it for ARM64 PCI: Add BAR index argument to pci_mmap_page_range() PCI: Use BAR index in sysfs attr->private instead of resource pointer PCI: Add arch_can_pci_mmap_io() on architectures which can mmap() I/O space PCI: Move multiple declarations of pci_mmap_page_range() to <linux/pci.h> PCI: Add arch_can_pci_mmap_wc() macro xtensa/PCI: Do not mmap PCI BARs to userspace as write-through PCI: Only allow WC mmap on prefetchable resources PCI: Fix another sanity check bug in /proc/pci mmap PCI: Fix pci_mmap_fits() for HAVE_PCI_RESOURCE_TO_USER platforms
2017-04-28 10:34:34 -05:00
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -4,7 +4,7 @@

 obj-y		+= access.o bus.o probe.o host-bridge.o remove.o pci.o \
 			pci-driver.o search.o pci-sysfs.o rom.o setup-res.o \
-			irq.o vpd.o setup-bus.o vc.o
+			irq.o vpd.o setup-bus.o vc.o mmap.o
 obj-$(CONFIG_PROC_FS) += proc.o
 obj-$(CONFIG_SYSFS) += slot.o

--- a/drivers/pci/mmap.c
+++ b/drivers/pci/mmap.c
@@ -0,0 +1,99 @@
+/*
+ * mmap.c — generic PCI resource mmap helper
+ *
+ * Copyright © 2017 Amazon.com, Inc. or its affiliates.
+ *
+ * Author: David Woodhouse <dwmw2@infradead.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/pci.h>
+
+#ifdef ARCH_GENERIC_PCI_MMAP_RESOURCE
+
+/*
+ * Modern setup: generic pci_mmap_resource_range(), and implement the legacy
+ * pci_mmap_page_range() (if needed) as a wrapper round it.
+ */
+
+#ifdef HAVE_PCI_MMAP
+int pci_mmap_page_range(struct pci_dev *pdev, int bar,
+			struct vm_area_struct *vma,
+			enum pci_mmap_state mmap_state, int write_combine)
+{
+	resource_size_t start, end;
+
+	pci_resource_to_user(pdev, bar, &pdev->resource[bar], &start, &end);
+
+	/* Adjust vm_pgoff to be the offset within the resource */
+	vma->vm_pgoff -= start >> PAGE_SHIFT;
+	return pci_mmap_resource_range(pdev, bar, vma, mmap_state,
+				       write_combine);
+}
+#endif
+
+static const struct vm_operations_struct pci_phys_vm_ops = {
+#ifdef CONFIG_HAVE_IOREMAP_PROT
+	.access = generic_access_phys,
+#endif
+};
+
+int pci_mmap_resource_range(struct pci_dev *pdev, int bar,
+			    struct vm_area_struct *vma,
+			    enum pci_mmap_state mmap_state, int write_combine)
+{
+	unsigned long size;
+	int ret;
+
+	size = ((pci_resource_len(pdev, bar) - 1) >> PAGE_SHIFT) + 1;
+	if (vma->vm_pgoff + vma_pages(vma) > size)
+		return -EINVAL;
+
+	if (write_combine)
+		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+	else
+		vma->vm_page_prot = pgprot_device(vma->vm_page_prot);
+
+	if (mmap_state == pci_mmap_io) {
+		ret = pci_iobar_pfn(pdev, bar, vma);
+		if (ret)
+			return ret;
+	} else
+		vma->vm_pgoff += (pci_resource_start(pdev, bar) >> PAGE_SHIFT);
+
+	vma->vm_ops = &pci_phys_vm_ops;
+
+	return io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+				  vma->vm_end - vma->vm_start,
+				  vma->vm_page_prot);
+}
+
+#elif defined(HAVE_PCI_MMAP) /* && !ARCH_GENERIC_PCI_MMAP_RESOURCE */
+
+/*
+ * Legacy setup: Impement pci_mmap_resource_range() as a wrapper around
+ * the architecture's pci_mmap_page_range(), converting to "user visible"
+ * addresses as necessary.
+ */
+
+int pci_mmap_resource_range(struct pci_dev *pdev, int bar,
+			    struct vm_area_struct *vma,
+			    enum pci_mmap_state mmap_state, int write_combine)
+{
+	resource_size_t start, end;
+
+	/*
+	 * 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, bar, &pdev->resource[bar], &start, &end);
+	vma->vm_pgoff += start >> PAGE_SHIFT;
+	return pci_mmap_page_range(pdev, bar, vma, mmap_state, write_combine);
+}
+#endif
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -980,20 +980,24 @@ void pci_remove_legacy_files(struct pci_bus *b)
 }
 #endif /* HAVE_PCI_LEGACY */

-#ifdef HAVE_PCI_MMAP
+#if defined(HAVE_PCI_MMAP) || defined(ARCH_GENERIC_PCI_MMAP_RESOURCE)

 int pci_mmap_fits(struct pci_dev *pdev, int resno, struct vm_area_struct *vma,
 		  enum pci_mmap_api mmap_api)
 {
-	unsigned long nr, start, size, pci_start;
+	unsigned long nr, start, size;
+	resource_size_t pci_start = 0, pci_end;

 	if (pci_resource_len(pdev, resno) == 0)
 		return 0;
 	nr = vma_pages(vma);
 	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 (mmap_api == PCI_MMAP_PROCFS) {
+		pci_resource_to_user(pdev, resno, &pdev->resource[resno],
+				     &pci_start, &pci_end);
+		pci_start >>= PAGE_SHIFT;
+	}
 	if (start >= pci_start && start < pci_start + size &&
 			start + nr <= pci_start + size)
 		return 1;
@@ -1013,37 +1017,24 @@ static int pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr,
 			     struct vm_area_struct *vma, int write_combine)
 {
 	struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj));
-	struct resource *res = attr->private;
+	int bar = (unsigned long)attr->private;
 	enum pci_mmap_state mmap_type;
-	resource_size_t start, end;
-	int i;
-
-	for (i = 0; i < PCI_ROM_RESOURCE; i++)
-		if (res == &pdev->resource[i])
-			break;
-	if (i >= PCI_ROM_RESOURCE)
-		return -ENODEV;
+	struct resource *res = &pdev->resource[bar];

 	if (res->flags & IORESOURCE_MEM && iomem_is_exclusive(res->start))
 		return -EINVAL;

-	if (!pci_mmap_fits(pdev, i, vma, PCI_MMAP_SYSFS)) {
+	if (!pci_mmap_fits(pdev, bar, vma, 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,
-			(u64)pci_resource_start(pdev, i),
-			(u64)pci_resource_len(pdev, i));
+			pci_name(pdev), bar,
+			(u64)pci_resource_start(pdev, bar),
+			(u64)pci_resource_len(pdev, bar));
 		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;
-	return pci_mmap_page_range(pdev, vma, mmap_type, write_combine);
+
+	return pci_mmap_resource_range(pdev, bar, vma, mmap_type, write_combine);
 }

 static int pci_mmap_resource_uc(struct file *filp, struct kobject *kobj,
@@ -1065,22 +1056,18 @@ static ssize_t pci_resource_io(struct file *filp, struct kobject *kobj,
 			       loff_t off, size_t count, bool write)
 {
 	struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj));
-	struct resource *res = attr->private;
+	int bar = (unsigned long)attr->private;
+	struct resource *res;
 	unsigned long port = off;
-	int i;

-	for (i = 0; i < PCI_ROM_RESOURCE; i++)
-		if (res == &pdev->resource[i])
-			break;
-	if (i >= PCI_ROM_RESOURCE)
-		return -ENODEV;
+	res = &pdev->resource[bar];

-	port += pci_resource_start(pdev, i);
+	port += pci_resource_start(pdev, bar);

-	if (port > pci_resource_end(pdev, i))
+	if (port > pci_resource_end(pdev, bar))
 		return 0;

-	if (port + count - 1 > pci_resource_end(pdev, i))
+	if (port + count - 1 > pci_resource_end(pdev, bar))
 		return -EINVAL;

 	switch (count) {
@@ -1170,16 +1157,19 @@ static int pci_create_attr(struct pci_dev *pdev, int num, int write_combine)
 	} else {
 		pdev->res_attr[num] = res_attr;
 		sprintf(res_attr_name, "resource%d", num);
-		res_attr->mmap = pci_mmap_resource_uc;
-	}
-	if (pci_resource_flags(pdev, num) & IORESOURCE_IO) {
-		res_attr->read = pci_read_resource_io;
-		res_attr->write = pci_write_resource_io;
+		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;
+		}
 	}
 	res_attr->attr.name = res_attr_name;
 	res_attr->attr.mode = S_IRUSR | S_IWUSR;
 	res_attr->size = pci_resource_len(pdev, num);
-	res_attr->private = &pdev->resource[num];
+	res_attr->private = (void *)(unsigned long)num;
 	retval = sysfs_create_bin_file(&pdev->dev.kobj, res_attr);
 	if (retval)
 		kfree(res_attr);
@@ -1207,9 +1197,9 @@ 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 && pdev->resource[i].flags & IORESOURCE_PREFETCH)
+		if (!retval && arch_can_pci_mmap_wc() &&
+		    pdev->resource[i].flags & IORESOURCE_PREFETCH)
 			retval = pci_create_attr(pdev, i, 1);
-
 		if (retval) {
 			pci_remove_resource_files(pdev);
 			return retval;
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -21,14 +21,14 @@ void pci_create_firmware_label_files(struct pci_dev *pdev);
 void pci_remove_firmware_label_files(struct pci_dev *pdev);
 #endif
 void pci_cleanup_rom(struct pci_dev *dev);
-#ifdef HAVE_PCI_MMAP
+
 enum pci_mmap_api {
 	PCI_MMAP_SYSFS,	/* mmap on /sys/bus/pci/devices/<BDF>/resource<N> */
 	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);
-#endif
+
 int pci_probe_reset_function(struct pci_dev *dev);

 /**
--- a/drivers/pci/proc.c
+++ b/drivers/pci/proc.c
@@ -202,6 +202,8 @@ static long proc_bus_pci_ioctl(struct file *file, unsigned int cmd,

 #ifdef HAVE_PCI_MMAP
 	case PCIIOC_MMAP_IS_IO:
+		if (!arch_can_pci_mmap_io())
+			return -EINVAL;
 		fpriv->mmap_state = pci_mmap_io;
 		break;

@@ -210,14 +212,15 @@ static long proc_bus_pci_ioctl(struct file *file, unsigned int cmd,
 		break;

 	case PCIIOC_WRITE_COMBINE:
-		if (arg)
-			fpriv->write_combine = 1;
-		else
-			fpriv->write_combine = 0;
-		break;
-
+		if (arch_can_pci_mmap_wc()) {
+			if (arg)
+				fpriv->write_combine = 1;
+			else
+				fpriv->write_combine = 0;
+			break;
+		}
+		/* If arch decided it can't, fall through... */
 #endif /* HAVE_PCI_MMAP */
-
 	default:
 		ret = -EINVAL;
 		break;
@@ -231,25 +234,35 @@ 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, write_combine;
+	int i, ret, write_combine = 0, res_bit = IORESOURCE_MEM;

 	if (!capable(CAP_SYS_RAWIO))
 		return -EPERM;

+	if (fpriv->mmap_state == pci_mmap_io) {
+		if (!arch_can_pci_mmap_io())
+			return -EINVAL;
+		res_bit = IORESOURCE_IO;
+	}
+
 	/* 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))
+		if (dev->resource[i].flags & res_bit &&
+		    pci_mmap_fits(dev, i, vma,  PCI_MMAP_PROCFS))
 			break;
 	}

 	if (i >= PCI_ROM_RESOURCE)
 		return -ENODEV;

-	if (fpriv->mmap_state == pci_mmap_mem)
-		write_combine = fpriv->write_combine;
-	else
-		write_combine = 0;
-	ret = pci_mmap_page_range(dev, vma,
+	if (fpriv->mmap_state == pci_mmap_mem &&
+	    fpriv->write_combine) {
+		if (dev->resource[i].flags & IORESOURCE_PREFETCH)
+			write_combine = 1;
+		else
+			return -EINVAL;
+	}
+	ret = pci_mmap_page_range(dev, i, vma,
 				  fpriv->mmap_state, write_combine);
 	if (ret < 0)
 		return ret;