x86/PCI: Add kernel cmdline options to use/ignore E820 reserved regions

Some firmware supplies PCI host bridge _CRS that includes address space
unusable by PCI devices, e.g., space occupied by host bridge registers or
used by hidden PCI devices.

To avoid this unusable space, Linux currently excludes E820 reserved
regions from _CRS windows; see 4dc2287c1805 ("x86: avoid E820 regions when
allocating address space").

However, this use of E820 reserved regions to clip things out of _CRS is
not supported by ACPI, UEFI, or PCI Firmware specs, and some systems have
E820 reserved regions that cover the entire memory window from _CRS.
4dc2287c1805 clips the entire window, leaving no space for hot-added or
uninitialized PCI devices.

For example, from a Lenovo IdeaPad 3 15IIL 81WE:

  BIOS-e820: [mem 0x4bc50000-0xcfffffff] reserved
  pci_bus 0000:00: root bus resource [mem 0x65400000-0xbfffffff window]
  pci 0000:00:15.0: BAR 0: [mem 0x00000000-0x00000fff 64bit]
  pci 0000:00:15.0: BAR 0: no space for [mem size 0x00001000 64bit]

Future patches will add quirks to enable/disable E820 clipping
automatically.

Add a "pci=no_e820" kernel command line option to disable clipping with
E820 reserved regions.  Also add a matching "pci=use_e820" option to enable
clipping with E820 reserved regions if that has been disabled by default by
further patches in this patch-set.

Both options taint the kernel because they are intended for debugging and
workaround purposes until a quirk can set them automatically.

[bhelgaas: commit log, add printk]
Link: https://bugzilla.redhat.com/show_bug.cgi?id=1868899 Lenovo IdeaPad 3
Link: https://lore.kernel.org/r/20220519152150.6135-2-hdegoede@redhat.com
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Benoit Grégoire <benoitg@coeus.ca>
Cc: Hui Wang <hui.wang@canonical.com>

2 files changed, 24 insertions, 2 deletions

diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 562c81a51ea0..c61c815efedb 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -20,6 +20,7 @@ struct pci_root_info {
 #endif
 };
 
+static bool pci_use_e820 = true;
 static bool pci_use_crs = true;
 static bool pci_ignore_seg;
 
@@ -161,6 +162,17 @@ void __init pci_acpi_crs_quirks(void)
 	       "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)
+		pci_use_e820 = false;
+	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");
+	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");
 }
 
 #ifdef	CONFIG_PCI_MMCONFIG
@@ -301,8 +313,10 @@ static int pci_acpi_root_prepare_resources(struct acpi_pci_root_info *ci)
 
 	status = acpi_pci_probe_root_resources(ci);
 
-	resource_list_for_each_entry(entry, &ci->resources)
-		remove_e820_regions(&device->dev, entry->res);
+	if (pci_use_e820) {
+		resource_list_for_each_entry(entry, &ci->resources)
+			remove_e820_regions(&device->dev, entry->res);
+	}
 
 	if (pci_use_crs) {
 		resource_list_for_each_entry_safe(entry, tmp, &ci->resources)
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 9e1e6b8d8876..ddb798603201 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -595,6 +595,14 @@ char *__init pcibios_setup(char *str)
 	} else if (!strcmp(str, "nocrs")) {
 		pci_probe |= PCI_ROOT_NO_CRS;
 		return NULL;
+	} else if (!strcmp(str, "use_e820")) {
+		pci_probe |= PCI_USE_E820;
+		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
+		return NULL;
+	} else if (!strcmp(str, "no_e820")) {
+		pci_probe |= PCI_NO_E820;
+		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
+		return NULL;
 #ifdef CONFIG_PHYS_ADDR_T_64BIT
 	} else if (!strcmp(str, "big_root_window")) {
 		pci_probe |= PCI_BIG_ROOT_WINDOW;