Merge branch 'pci/resource'

- Remove EfiMemoryMappedIO regions from the E820 map to allow PCI core to
  allocate BARs from them.  The only purpose of EfiMemoryMappedIO is to
  tell the OS to map things needed by EFI runtime services, so it's often
  used for PCI host bridge apertures.  If we can't allocate from those
  apertures, we can't hot-add devices (Bjorn Helgaas)

* pci/resource:
  x86/PCI: Use pr_info() when possible
  x86/PCI: Fix log message typo
  x86/PCI: Tidy E820 removal messages
  PCI: Skip allocate_resource() if too little space available
  efi/x86: Remove EfiMemoryMappedIO from E820 map

4 files changed, 78 insertions, 23 deletions

diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c
index bba1abd05bfe..79bc8a97a083 100644
--- a/arch/x86/kernel/resource.c
+++ b/arch/x86/kernel/resource.c
@@ -42,8 +42,16 @@ static void remove_e820_regions(struct resource *avail)
 
 		resource_clip(avail, e820_start, e820_end);
 		if (orig.start != avail->start || orig.end != avail->end) {
-			pr_info("clipped %pR to %pR for e820 entry [mem %#010Lx-%#010Lx]\n",
-				 &orig, avail, e820_start, e820_end);
+			pr_info("resource: avoiding allocation from e820 entry [mem %#010Lx-%#010Lx]\n",
+				e820_start, e820_end);
+			if (avail->end > avail->start)
+				/*
+				 * Use %pa instead of %pR because "avail"
+				 * is typically IORESOURCE_UNSET, so %pR
+				 * shows the size instead of addresses.
+				 */
+				pr_info("resource: remaining [mem %pa-%pa] available\n",
+					&avail->start, &avail->end);
 			orig = *avail;
 		}
 	}
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 2f82480fd430..ea2eb2ec90e2 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -1,4 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
+
+#define pr_fmt(fmt) "PCI: " fmt
+
 #include <linux/pci.h>
 #include <linux/acpi.h>
 #include <linux/init.h>
@@ -37,15 +40,15 @@ static int __init set_nouse_crs(const struct dmi_system_id *id)
 
 static int __init set_ignore_seg(const struct dmi_system_id *id)
 {
-	printk(KERN_INFO "PCI: %s detected: ignoring ACPI _SEG\n", id->ident);
+	pr_info("%s detected: ignoring ACPI _SEG\n", id->ident);
 	pci_ignore_seg = true;
 	return 0;
 }
 
 static int __init set_no_e820(const struct dmi_system_id *id)
 {
-	printk(KERN_INFO "PCI: %s detected: not clipping E820 regions from _CRS\n",
-	       id->ident);
+	pr_info("%s detected: not clipping E820 regions from _CRS\n",
+	        id->ident);
 	pci_use_e820 = false;
 	return 0;
 }
@@ -231,10 +234,9 @@ void __init pci_acpi_crs_quirks(void)
 	else if (pci_probe & PCI_USE__CRS)
 		pci_use_crs = true;
 
-	printk(KERN_INFO "PCI: %s host bridge windows from ACPI; "
-	       "if necessary, use \"pci=%s\" and report a bug\n",
-	       pci_use_crs ? "Using" : "Ignoring",
-	       pci_use_crs ? "nocrs" : "use_crs");
+	pr_info("%s host bridge windows from ACPI; if necessary, use \"pci=%s\" and report a bug\n",
+	        pci_use_crs ? "Using" : "Ignoring",
+	        pci_use_crs ? "nocrs" : "use_crs");
 
 	/* "pci=use_e820"/"pci=no_e820" on the kernel cmdline takes precedence */
 	if (pci_probe & PCI_NO_E820)
@@ -242,19 +244,17 @@ void __init pci_acpi_crs_quirks(void)
 	else if (pci_probe & PCI_USE_E820)
 		pci_use_e820 = true;
 
-	printk(KERN_INFO "PCI: %s E820 reservations for host bridge windows\n",
-	       pci_use_e820 ? "Using" : "Ignoring");
+	pr_info("%s E820 reservations for host bridge windows\n",
+	        pci_use_e820 ? "Using" : "Ignoring");
 	if (pci_probe & (PCI_NO_E820 | PCI_USE_E820))
-		printk(KERN_INFO "PCI: Please notify linux-pci@vger.kernel.org so future kernels can this automatically\n");
+		pr_info("Please notify linux-pci@vger.kernel.org so future kernels can do this automatically\n");
 }
 
 #ifdef	CONFIG_PCI_MMCONFIG
 static int check_segment(u16 seg, struct device *dev, char *estr)
 {
 	if (seg) {
-		dev_err(dev,
-			"%s can't access PCI configuration "
-			"space under this host bridge.\n",
+		dev_err(dev, "%s can't access configuration space under this host bridge\n",
 			estr);
 		return -EIO;
 	}
@@ -264,9 +264,7 @@ static int check_segment(u16 seg, struct device *dev, char *estr)
 	 * just can't access extended configuration space of
 	 * devices under this host bridge.
 	 */
-	dev_warn(dev,
-		 "%s can't access extended PCI configuration "
-		 "space under this bridge.\n",
+	dev_warn(dev, "%s can't access extended configuration space under this bridge\n",
 		 estr);
 
 	return 0;
@@ -421,9 +419,8 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
 		root->segment = domain = 0;
 
 	if (domain && !pci_domains_supported) {
-		printk(KERN_WARNING "pci_bus %04x:%02x: "
-		       "ignored (multiple domains not supported)\n",
-		       domain, busnum);
+		pr_warn("pci_bus %04x:%02x: ignored (multiple domains not supported)\n",
+		        domain, busnum);
 		return NULL;
 	}
 
@@ -491,7 +488,7 @@ int __init pci_acpi_init(void)
 	if (acpi_noirq)
 		return -ENODEV;
 
-	printk(KERN_INFO "PCI: Using ACPI for IRQ routing\n");
+	pr_info("Using ACPI for IRQ routing\n");
 	acpi_irq_penalty_init();
 	pcibios_enable_irq = acpi_pci_irq_enable;
 	pcibios_disable_irq = acpi_pci_irq_disable;
@@ -503,7 +500,7 @@ int __init pci_acpi_init(void)
 		 * also do it here in case there are still broken drivers that
 		 * don't use pci_enable_device().
 		 */
-		printk(KERN_INFO "PCI: Routing PCI interrupts for all devices because \"pci=routeirq\" specified\n");
+		pr_info("Routing PCI interrupts for all devices because \"pci=routeirq\" specified\n");
 		for_each_pci_dev(dev)
 			acpi_pci_irq_enable(dev);
 	}
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index ebc98a68c400..75bf0e56bb53 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -303,6 +303,50 @@ static void __init efi_clean_memmap(void)
 	}
 }
 
+/*
+ * Firmware can use EfiMemoryMappedIO to request that MMIO regions be
+ * mapped by the OS so they can be accessed by EFI runtime services, but
+ * should have no other significance to the OS (UEFI r2.10, sec 7.2).
+ * However, most bootloaders and EFI stubs convert EfiMemoryMappedIO
+ * regions to E820_TYPE_RESERVED entries, which prevent Linux from
+ * allocating space from them (see remove_e820_regions()).
+ *
+ * Some platforms use EfiMemoryMappedIO entries for PCI MMCONFIG space and
+ * PCI host bridge windows, which means Linux can't allocate BAR space for
+ * hot-added devices.
+ *
+ * Remove large EfiMemoryMappedIO regions from the E820 map to avoid this
+ * problem.
+ *
+ * Retain small EfiMemoryMappedIO regions because on some platforms, these
+ * describe non-window space that's included in host bridge _CRS.  If we
+ * assign that space to PCI devices, they don't work.
+ */
+static void __init efi_remove_e820_mmio(void)
+{
+	efi_memory_desc_t *md;
+	u64 size, start, end;
+	int i = 0;
+
+	for_each_efi_memory_desc(md) {
+		if (md->type == EFI_MEMORY_MAPPED_IO) {
+			size = md->num_pages << EFI_PAGE_SHIFT;
+			start = md->phys_addr;
+			end = start + size - 1;
+			if (size >= 256*1024) {
+				pr_info("Remove mem%02u: MMIO range=[0x%08llx-0x%08llx] (%lluMB) from e820 map\n",
+					i, start, end, size >> 20);
+				e820__range_remove(start, size,
+						   E820_TYPE_RESERVED, 1);
+			} else {
+				pr_info("Not removing mem%02u: MMIO range=[0x%08llx-0x%08llx] (%lluKB) from e820 map\n",
+					i, start, end, size >> 10);
+			}
+		}
+		i++;
+	}
+}
+
 void __init efi_print_memmap(void)
 {
 	efi_memory_desc_t *md;
@@ -474,6 +518,8 @@ void __init efi_init(void)
 	set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
 	efi_clean_memmap();
 
+	efi_remove_e820_mmio();
+
 	if (efi_enabled(EFI_DBG))
 		efi_print_memmap();
 }
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 3cef835b375f..83ae838ceb5f 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -197,6 +197,10 @@ static int pci_bus_alloc_from_region(struct pci_bus *bus, struct resource *res,
 
 		max = avail.end;
 
+		/* Don't bother if available space isn't large enough */
+		if (size > max - min_used + 1)
+			continue;
+
 		/* Ok, try it out.. */
 		ret = allocate_resource(r, res, size, min_used, max,
 					align, alignf, alignf_data);