Merge branch 'pci/bjorn-p2p-bridge-windows' into next

* pci/bjorn-p2p-bridge-windows:
  sparc/PCI: replace pci_cfg_fake_ranges() with pci_read_bridge_bases()
  PCI: support sizing P2P bridge I/O windows with 1K granularity
  PCI: reimplement P2P bridge 1K I/O windows (Intel P64H2)
  PCI: allow P2P bridge windows starting at PCI bus address zero

Conflicts:
	drivers/pci/probe.c
	include/linux/pci.h
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index 52ee0c7..065b88c 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -375,93 +375,6 @@
 	*last_p = last;
 }
 
-/* For PCI bus devices which lack a 'ranges' property we interrogate
- * the config space values to set the resources, just like the generic
- * Linux PCI probing code does.
- */
-static void __devinit pci_cfg_fake_ranges(struct pci_dev *dev,
-					  struct pci_bus *bus,
-					  struct pci_pbm_info *pbm)
-{
-	struct pci_bus_region region;
-	struct resource *res, res2;
-	u8 io_base_lo, io_limit_lo;
-	u16 mem_base_lo, mem_limit_lo;
-	unsigned long base, limit;
-
-	pci_read_config_byte(dev, PCI_IO_BASE, &io_base_lo);
-	pci_read_config_byte(dev, PCI_IO_LIMIT, &io_limit_lo);
-	base = (io_base_lo & PCI_IO_RANGE_MASK) << 8;
-	limit = (io_limit_lo & PCI_IO_RANGE_MASK) << 8;
-
-	if ((io_base_lo & PCI_IO_RANGE_TYPE_MASK) == PCI_IO_RANGE_TYPE_32) {
-		u16 io_base_hi, io_limit_hi;
-
-		pci_read_config_word(dev, PCI_IO_BASE_UPPER16, &io_base_hi);
-		pci_read_config_word(dev, PCI_IO_LIMIT_UPPER16, &io_limit_hi);
-		base |= (io_base_hi << 16);
-		limit |= (io_limit_hi << 16);
-	}
-
-	res = bus->resource[0];
-	if (base <= limit) {
-		res->flags = (io_base_lo & PCI_IO_RANGE_TYPE_MASK) | IORESOURCE_IO;
-		res2.flags = res->flags;
-		region.start = base;
-		region.end = limit + 0xfff;
-		pcibios_bus_to_resource(dev, &res2, &region);
-		if (!res->start)
-			res->start = res2.start;
-		if (!res->end)
-			res->end = res2.end;
-	}
-
-	pci_read_config_word(dev, PCI_MEMORY_BASE, &mem_base_lo);
-	pci_read_config_word(dev, PCI_MEMORY_LIMIT, &mem_limit_lo);
-	base = (mem_base_lo & PCI_MEMORY_RANGE_MASK) << 16;
-	limit = (mem_limit_lo & PCI_MEMORY_RANGE_MASK) << 16;
-
-	res = bus->resource[1];
-	if (base <= limit) {
-		res->flags = ((mem_base_lo & PCI_MEMORY_RANGE_TYPE_MASK) |
-			      IORESOURCE_MEM);
-		region.start = base;
-		region.end = limit + 0xfffff;
-		pcibios_bus_to_resource(dev, res, &region);
-	}
-
-	pci_read_config_word(dev, PCI_PREF_MEMORY_BASE, &mem_base_lo);
-	pci_read_config_word(dev, PCI_PREF_MEMORY_LIMIT, &mem_limit_lo);
-	base = (mem_base_lo & PCI_PREF_RANGE_MASK) << 16;
-	limit = (mem_limit_lo & PCI_PREF_RANGE_MASK) << 16;
-
-	if ((mem_base_lo & PCI_PREF_RANGE_TYPE_MASK) == PCI_PREF_RANGE_TYPE_64) {
-		u32 mem_base_hi, mem_limit_hi;
-
-		pci_read_config_dword(dev, PCI_PREF_BASE_UPPER32, &mem_base_hi);
-		pci_read_config_dword(dev, PCI_PREF_LIMIT_UPPER32, &mem_limit_hi);
-
-		/*
-		 * Some bridges set the base > limit by default, and some
-		 * (broken) BIOSes do not initialize them.  If we find
-		 * this, just assume they are not being used.
-		 */
-		if (mem_base_hi <= mem_limit_hi) {
-			base |= ((long) mem_base_hi) << 32;
-			limit |= ((long) mem_limit_hi) << 32;
-		}
-	}
-
-	res = bus->resource[2];
-	if (base <= limit) {
-		res->flags = ((mem_base_lo & PCI_MEMORY_RANGE_TYPE_MASK) |
-			      IORESOURCE_MEM | IORESOURCE_PREFETCH);
-		region.start = base;
-		region.end = limit + 0xfffff;
-		pcibios_bus_to_resource(dev, res, &region);
-	}
-}
-
 /* Cook up fake bus resources for SUNW,simba PCI bridges which lack
  * a proper 'ranges' property.
  */
@@ -550,7 +463,7 @@
 		apb_fake_ranges(dev, bus, pbm);
 		goto after_ranges;
 	} else if (ranges == NULL) {
-		pci_cfg_fake_ranges(dev, bus, pbm);
+		pci_read_bridge_bases(bus);
 		goto after_ranges;
 	}
 	i = 1;
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 5e5358a..6c143b4 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -306,15 +306,23 @@
 {
 	struct pci_dev *dev = child->self;
 	u8 io_base_lo, io_limit_lo;
-	unsigned long base, limit;
+	unsigned long io_mask, io_granularity, base, limit;
 	struct pci_bus_region region;
-	struct resource *res, res2;
+	struct resource *res;
+
+	io_mask = PCI_IO_RANGE_MASK;
+	io_granularity = 0x1000;
+	if (dev->io_window_1k) {
+		/* Support 1K I/O space granularity */
+		io_mask = PCI_IO_1K_RANGE_MASK;
+		io_granularity = 0x400;
+	}
 
 	res = child->resource[0];
 	pci_read_config_byte(dev, PCI_IO_BASE, &io_base_lo);
 	pci_read_config_byte(dev, PCI_IO_LIMIT, &io_limit_lo);
-	base = (io_base_lo & PCI_IO_RANGE_MASK) << 8;
-	limit = (io_limit_lo & PCI_IO_RANGE_MASK) << 8;
+	base = (io_base_lo & io_mask) << 8;
+	limit = (io_limit_lo & io_mask) << 8;
 
 	if ((io_base_lo & PCI_IO_RANGE_TYPE_MASK) == PCI_IO_RANGE_TYPE_32) {
 		u16 io_base_hi, io_limit_hi;
@@ -325,16 +333,11 @@
 		limit |= ((unsigned long) io_limit_hi << 16);
 	}
 
-	if (base && base <= limit) {
+	if (base <= limit) {
 		res->flags = (io_base_lo & PCI_IO_RANGE_TYPE_MASK) | IORESOURCE_IO;
-		res2.flags = res->flags;
 		region.start = base;
-		region.end = limit + 0xfff;
-		pcibios_bus_to_resource(dev, &res2, &region);
-		if (!res->start)
-			res->start = res2.start;
-		if (!res->end)
-			res->end = res2.end;
+		region.end = limit + io_granularity - 1;
+		pcibios_bus_to_resource(dev, res, &region);
 		dev_printk(KERN_DEBUG, &dev->dev, "  bridge window %pR\n", res);
 	}
 }
@@ -352,7 +355,7 @@
 	pci_read_config_word(dev, PCI_MEMORY_LIMIT, &mem_limit_lo);
 	base = ((unsigned long) mem_base_lo & PCI_MEMORY_RANGE_MASK) << 16;
 	limit = ((unsigned long) mem_limit_lo & PCI_MEMORY_RANGE_MASK) << 16;
-	if (base && base <= limit) {
+	if (base <= limit) {
 		res->flags = (mem_base_lo & PCI_MEMORY_RANGE_TYPE_MASK) | IORESOURCE_MEM;
 		region.start = base;
 		region.end = limit + 0xfffff;
@@ -399,7 +402,7 @@
 #endif
 		}
 	}
-	if (base && base <= limit) {
+	if (base <= limit) {
 		res->flags = (mem_base_lo & PCI_PREF_RANGE_TYPE_MASK) |
 					 IORESOURCE_MEM | IORESOURCE_PREFETCH;
 		if (res->flags & PCI_PREF_RANGE_TYPE_64)
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 17741d3..52f44b5 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -1938,53 +1938,16 @@
 static void __devinit quirk_p64h2_1k_io(struct pci_dev *dev)
 {
 	u16 en1k;
-	u8 io_base_lo, io_limit_lo;
-	unsigned long base, limit;
-	struct resource *res = dev->resource + PCI_BRIDGE_RESOURCES;
 
 	pci_read_config_word(dev, 0x40, &en1k);
 
 	if (en1k & 0x200) {
 		dev_info(&dev->dev, "Enable I/O Space to 1KB granularity\n");
-
-		pci_read_config_byte(dev, PCI_IO_BASE, &io_base_lo);
-		pci_read_config_byte(dev, PCI_IO_LIMIT, &io_limit_lo);
-		base = (io_base_lo & (PCI_IO_RANGE_MASK | 0x0c)) << 8;
-		limit = (io_limit_lo & (PCI_IO_RANGE_MASK | 0x0c)) << 8;
-
-		if (base <= limit) {
-			res->start = base;
-			res->end = limit + 0x3ff;
-		}
+		dev->io_window_1k = 1;
 	}
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	0x1460,		quirk_p64h2_1k_io);
 
-/* Fix the IOBL_ADR for 1k I/O space granularity on the Intel P64H2
- * The IOBL_ADR gets re-written to 4k boundaries in pci_setup_bridge()
- * in drivers/pci/setup-bus.c
- */
-static void __devinit quirk_p64h2_1k_io_fix_iobl(struct pci_dev *dev)
-{
-	u16 en1k, iobl_adr, iobl_adr_1k;
-	struct resource *res = dev->resource + PCI_BRIDGE_RESOURCES;
-
-	pci_read_config_word(dev, 0x40, &en1k);
-
-	if (en1k & 0x200) {
-		pci_read_config_word(dev, PCI_IO_BASE, &iobl_adr);
-
-		iobl_adr_1k = iobl_adr | (res->start >> 8) | (res->end & 0xfc00);
-
-		if (iobl_adr != iobl_adr_1k) {
-			dev_info(&dev->dev, "Fixing P64H2 IOBL_ADR from 0x%x to 0x%x for 1KB granularity\n",
-				iobl_adr,iobl_adr_1k);
-			pci_write_config_word(dev, PCI_IO_BASE, iobl_adr_1k);
-		}
-	}
-}
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x1460,		quirk_p64h2_1k_io_fix_iobl);
-
 /* Under some circumstances, AER is not linked with extended capabilities.
  * Force it to be linked by setting the corresponding control bit in the
  * config space.
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 561e41c..fdb1177 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -469,16 +469,23 @@
 	struct pci_dev *bridge = bus->self;
 	struct resource *res;
 	struct pci_bus_region region;
+	unsigned long io_mask;
+	u8 io_base_lo, io_limit_lo;
 	u32 l, io_upper16;
 
+	io_mask = PCI_IO_RANGE_MASK;
+	if (bridge->io_window_1k)
+		io_mask = PCI_IO_1K_RANGE_MASK;
+
 	/* Set up the top and bottom of the PCI I/O segment for this bus. */
 	res = bus->resource[0];
 	pcibios_resource_to_bus(bridge, &region, res);
 	if (res->flags & IORESOURCE_IO) {
 		pci_read_config_dword(bridge, PCI_IO_BASE, &l);
 		l &= 0xffff0000;
-		l |= (region.start >> 8) & 0x00f0;
-		l |= region.end & 0xf000;
+		io_base_lo = (region.start >> 8) & io_mask;
+		io_limit_lo = (region.end >> 8) & io_mask;
+		l |= ((u32) io_limit_lo << 8) | io_base_lo;
 		/* Set up upper 16 bits of I/O base/limit. */
 		io_upper16 = (region.end & 0xffff0000) | (region.start >> 16);
 		dev_info(&bridge->dev, "  bridge window %pR\n", res);
@@ -699,7 +706,7 @@
  * @realloc_head : track the additional io window on this list
  *
  * Sizing the IO windows of the PCI-PCI bridge is trivial,
- * since these windows have 4K granularity and the IO ranges
+ * since these windows have 1K or 4K granularity and the IO ranges
  * of non-bridge PCI devices are limited to 256 bytes.
  * We must be careful with the ISA aliasing though.
  */
@@ -710,10 +717,17 @@
 	struct resource *b_res = find_free_bus_resource(bus, IORESOURCE_IO);
 	unsigned long size = 0, size0 = 0, size1 = 0;
 	resource_size_t children_add_size = 0;
+	resource_size_t min_align = 4096, align;
 
 	if (!b_res)
  		return;
 
+	/*
+	 * Per spec, I/O windows are 4K-aligned, but some bridges have an
+	 * extension to support 1K alignment.
+	 */
+	if (bus->self->io_window_1k)
+		min_align = 1024;
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		int i;
 
@@ -731,17 +745,25 @@
 			else
 				size1 += r_size;
 
+			align = pci_resource_alignment(dev, r);
+			if (align > min_align)
+				min_align = align;
+
 			if (realloc_head)
 				children_add_size += get_res_add_size(realloc_head, r);
 		}
 	}
+
+	if (min_align > 4096)
+		min_align = 4096;
+
 	size0 = calculate_iosize(size, min_size, size1,
-			resource_size(b_res), 4096);
+			resource_size(b_res), min_align);
 	if (children_add_size > add_size)
 		add_size = children_add_size;
 	size1 = (!realloc_head || (realloc_head && !add_size)) ? size0 :
 		calculate_iosize(size, min_size, add_size + size1,
-			resource_size(b_res), 4096);
+			resource_size(b_res), min_align);
 	if (!size0 && !size1) {
 		if (b_res->start || b_res->end)
 			dev_info(&bus->self->dev, "disabling bridge window "
@@ -750,12 +772,13 @@
 		b_res->flags = 0;
 		return;
 	}
-	/* Alignment of the IO window is always 4K */
-	b_res->start = 4096;
+
+	b_res->start = min_align;
 	b_res->end = b_res->start + size0 - 1;
 	b_res->flags |= IORESOURCE_STARTALIGN;
 	if (size1 > size0 && realloc_head) {
-		add_to_list(realloc_head, bus->self, b_res, size1-size0, 4096);
+		add_to_list(realloc_head, bus->self, b_res, size1-size0,
+			    min_align);
 		dev_printk(KERN_DEBUG, &bus->self->dev, "bridge window "
 				 "%pR to %pR add_size %lx\n", b_res,
 				 &bus->busn_res, size1-size0);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 85cffb8..5faa831 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -333,6 +333,7 @@
 	unsigned int    __aer_firmware_first_valid:1;
 	unsigned int	__aer_firmware_first:1;
 	unsigned int	broken_intx_masking:1;
+	unsigned int	io_window_1k:1;	/* Intel P2P bridge 1K I/O windows */
 	pci_dev_flags_t dev_flags;
 	atomic_t	enable_cnt;	/* pci_enable_device has been called */
 
diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h
index 80e8605..53274bf 100644
--- a/include/linux/pci_regs.h
+++ b/include/linux/pci_regs.h
@@ -126,7 +126,8 @@
 #define  PCI_IO_RANGE_TYPE_MASK	0x0fUL	/* I/O bridging type */
 #define  PCI_IO_RANGE_TYPE_16	0x00
 #define  PCI_IO_RANGE_TYPE_32	0x01
-#define  PCI_IO_RANGE_MASK	(~0x0fUL)
+#define  PCI_IO_RANGE_MASK	(~0x0fUL) /* Standard 4K I/O windows */
+#define  PCI_IO_1K_RANGE_MASK	(~0x03UL) /* Intel 1K I/O windows */
 #define PCI_SEC_STATUS		0x1e	/* Secondary status register, only bit 14 used */
 #define PCI_MEMORY_BASE		0x20	/* Memory range behind */
 #define PCI_MEMORY_LIMIT	0x22