[RFC PATCH] PCI MMCONFIG: add validation against ACPI motherboard resources

[Robert Hancock <hancockr@shaw.ca>]

This path adds validation of the MMCONFIG table against the ACPI reserved
motherboard resources. If the MMCONFIG table is found to be reserved in
ACPI, we don't bother checking the E820 table. The PCI Express firmware spec
apparently tells BIOS developers that reservation in ACPI is required and
E820 reservation is optional, so checking against ACPI first makes sense.
Many BIOSes don't reserve the MMCONFIG region in E820 even though it is
perfectly functional, the existing check needlessly disables MMCONFIG in
these cases.

In order to do this, MMCONFIG setup has been split into two phases. If PCI
configuration type 1 is not available (like on EFI Macs) then MMCONFIG is
enabled early as before. Otherwise, it is enabled later after the ACPI
interpreter is enabled, since we need to be able to execute control methods
in order to check the ACPI reserved resources. Presently this is just triggered
off the end of ACPI interpreter initialization.

There are a few other behavioral changes here:

-Validate all MMCONFIG configurations provided, not just the first one.

-Validate the entire required length of each configuration according to the
provided ending bus number is reserved, not just the minimum required allocation.

-Validate that the area is reserved even if we read it from the chipset directly
and not from the MCFG table. This catches the case where the BIOS didn't set the
location properly in the chipset and has mapped it over other things it shouldn't have.
This might be overly pessimistic - we might be able to instead verify that no other
reserved resources (like chipset registers) are inside this memory range.

Some testing is needed to see if this rejects MMCONFIG on all systems where it
is problematic. There were some patches floating around to read the table
location out of the chipset for Intel 915 and 965, I think the author found the
latter to be problematic since the chipset had the table mapped over top of
motherboard resources. The extra checking here may catch that case if we add
that chipset-specific support.

Applies to 2.6.21.1.

Signed-off-by: Robert Hancock <hancockr@shaw.ca>

diff -up linux-2.6.21.1/arch/i386/pci/init.c linux-2.6.21.1edit/arch/i386/pci/init.c
--- linux-2.6.21.1/arch/i386/pci/init.c	2007-04-27 15:49:26.000000000 -0600
+++ linux-2.6.21.1edit/arch/i386/pci/init.c	2007-04-29 18:36:32.000000000 -0600
@@ -12,7 +12,7 @@ static __init int pci_access_init(void)
	type = pci_direct_probe();
#endif
#ifdef CONFIG_PCI_MMCONFIG
-	pci_mmcfg_init(type);
+	pci_mmcfg_early_init(type);
#endif
	if (raw_pci_ops)
		return 0;
diff -up linux-2.6.21.1/arch/i386/pci/mmconfig-shared.c linux-2.6.21.1edit/arch/i386/pci/mmconfig-shared.c
--- linux-2.6.21.1/arch/i386/pci/mmconfig-shared.c	2007-04-27 15:49:26.000000000 -0600
+++ linux-2.6.21.1edit/arch/i386/pci/mmconfig-shared.c	2007-04-29 19:47:57.000000000 -0600
@@ -191,9 +191,77 @@ static void __init pci_mmcfg_insert_reso
	}
}

-static void __init pci_mmcfg_reject_broken(int type)
+static acpi_status __init check_mcfg_resource(struct acpi_resource *res,
+		void *data)
+{
+	struct resource *mcfg_res = data;
+	struct acpi_resource_address64 address;
+	acpi_status status;
+
+	if (res->type == ACPI_RESOURCE_TYPE_FIXED_MEMORY32) {
+		struct acpi_resource_fixed_memory32 *fixmem32 =
+			&res->data.fixed_memory32;
+		if (!fixmem32)
+			return AE_OK;
+		if ((mcfg_res->start >= fixmem32->address) &&
+			(mcfg_res->end <= (fixmem32->address +
+					   fixmem32->address_length))) {
+			mcfg_res->flags = 1;
+			return AE_CTRL_TERMINATE;
+		}
+	}
+	if ((res->type != ACPI_RESOURCE_TYPE_ADDRESS32) &&
+			(res->type != ACPI_RESOURCE_TYPE_ADDRESS64))
+		return AE_OK;
+
+	status = acpi_resource_to_address64(res, &address);
+	if (ACPI_FAILURE(status) || (address.address_length <= 0) ||
+			(address.resource_type != ACPI_MEMORY_RANGE))
+		return AE_OK;
+
+	if ((mcfg_res->start >= address.minimum) &&
+			(mcfg_res->end <=
+			 (address.minimum +address.address_length))) {
+		mcfg_res->flags = 1;
+		return AE_CTRL_TERMINATE;
+	}
+	return AE_OK;
+}
+
+static acpi_status __init find_mboard_resource(acpi_handle handle, u32 lvl,
+		void *context, void **rv)
+{
+	struct resource *mcfg_res = context;
+
+	acpi_walk_resources(handle, METHOD_NAME__CRS,
+	  		    check_mcfg_resource, context);
+
+	if (mcfg_res->flags)
+		return AE_CTRL_TERMINATE;
+
+	return AE_OK;
+}
+
+static int __init is_acpi_reserved(unsigned long start, unsigned long end)
+{
+	struct resource mcfg_res;
+	
+	mcfg_res.start = start;
+	mcfg_res.end = end;
+	mcfg_res.flags = 0;
+
+	acpi_get_devices("PNP0C01", find_mboard_resource, &mcfg_res, NULL);
+	
+	if( !mcfg_res.flags )
+		acpi_get_devices("PNP0C02", find_mboard_resource, &mcfg_res, NULL);
+
+	return mcfg_res.flags;
+}
+
+static void __init pci_mmcfg_reject_broken(void)
{
	typeof(pci_mmcfg_config[0]) *cfg;
+	int i;

	if ((pci_mmcfg_config_num == 0) ||
	    (pci_mmcfg_config == NULL) ||
@@ -213,18 +281,36 @@ static void __init pci_mmcfg_reject_brok
		       "Rejected as broken MCFG.\n");
		goto reject;
	}
-
-	/*
-	 * Only do this check when type 1 works. If it doesn't work
-	 * assume we run on a Mac and always use MCFG
-	 */
-	if (type == 1 && !e820_all_mapped(cfg->address,
-					  cfg->address + MMCONFIG_APER_MIN,
-					  E820_RESERVED)) {
-		printk(KERN_ERR "PCI: BIOS Bug: MCFG area at %Lx is not"
-		       " E820-reserved\n", cfg->address);
-		goto reject;
+	
+	for(i=0; i < pci_mmcfg_config_num; i++) {
+		u32 size = (cfg->end_bus_number + 1) << 20;
+		cfg = &pci_mmcfg_config[i];
+		printk(KERN_NOTICE "PCI: MCFG configuration %d: base %p segment %hu buses %u - %u\n",
+			i, (void*)cfg->address, cfg->pci_segment, 
+			(unsigned int)cfg->start_bus_number,
+			(unsigned int)cfg->end_bus_number);
+		if(is_acpi_reserved(cfg->address,
+				    cfg->address + size - 1))
+			printk(KERN_NOTICE "PCI: MCFG area at %Lx reserved "
+				"in ACPI motherboard resources\n",
+				cfg->address);
+		else {
+			printk(KERN_ERR "PCI: BIOS Bug: MCFG area at %Lx is not "
+				"reserved in ACPI motherboard resources\n",
+				cfg->address);
+			/* Don't try to do this check unless configuration type 1 is
+			   available. */
+			if((pci_probe & PCI_PROBE_CONF1) && 
+			   e820_all_mapped(cfg->address,
+					   cfg->address + size - 1,
+					   E820_RESERVED))
+				printk(KERN_NOTICE "PCI: MCFG area at %Lx reserved in E820\n",
+					cfg->address);
+			else
+				goto reject;
+		}
	}
+
	return;

reject:
@@ -234,20 +320,46 @@ reject:
	pci_mmcfg_config_num = 0;
}

-void __init pci_mmcfg_init(int type)
+void __init pci_mmcfg_early_init(int type)
+{
+	if ((pci_probe & PCI_PROBE_MMCONF) == 0)
+		return;
+	
+	/* If type 1 access is available, no need to enable MMCONFIG yet, we can
+	   defer until later when the ACPI interpreter is available to better
+	   validate things. */
+	if( type == 1 )
+		return;
+
+	acpi_table_parse(ACPI_SIG_MCFG, acpi_parse_mcfg);
+
+	if ((pci_mmcfg_config_num == 0) ||
+	    (pci_mmcfg_config == NULL) ||
+	    (pci_mmcfg_config[0].address == 0))
+		return;
+
+	if (pci_mmcfg_arch_init())
+		pci_probe = (pci_probe & ~PCI_PROBE_MASK) | PCI_PROBE_MMCONF;
+}
+
+void __init pci_mmcfg_late_init(void)
{
	int known_bridge = 0;

+	/* MMCONFIG disabled */
	if ((pci_probe & PCI_PROBE_MMCONF) == 0)
		return;
+		
+	/* MMCONFIG already enabled */
+	if (!(pci_probe & PCI_PROBE_MASK & ~PCI_PROBE_MMCONF))
+		return;

-	if (type == 1 && pci_mmcfg_check_hostbridge())
+	if ((pci_probe & PCI_PROBE_CONF1) && pci_mmcfg_check_hostbridge())
		known_bridge = 1;
-
-	if (!known_bridge) {
+	else
		acpi_table_parse(ACPI_SIG_MCFG, acpi_parse_mcfg);
-		pci_mmcfg_reject_broken(type);
-	}
+
+	pci_mmcfg_reject_broken();

	if ((pci_mmcfg_config_num == 0) ||
	    (pci_mmcfg_config == NULL) ||
@@ -255,7 +367,7 @@ void __init pci_mmcfg_init(int type)
		return;

	if (pci_mmcfg_arch_init()) {
-		if (type == 1)
+		if (pci_probe & PCI_PROBE_CONF1)
			unreachable_devices();
		if (known_bridge)
			pci_mmcfg_insert_resources();
diff -up linux-2.6.21.1/arch/i386/pci/pci.h linux-2.6.21.1edit/arch/i386/pci/pci.h
--- linux-2.6.21.1/arch/i386/pci/pci.h	2007-04-27 15:49:26.000000000 -0600
+++ linux-2.6.21.1edit/arch/i386/pci/pci.h	2007-04-29 18:33:21.000000000 -0600
@@ -91,7 +91,8 @@ extern int pci_conf1_read(unsigned int s
extern int pci_direct_probe(void);
extern void pci_direct_init(int type);
extern void pci_pcbios_init(void);
-extern void pci_mmcfg_init(int type);
+extern void pci_mmcfg_early_init(int type);
+extern void pci_mmcfg_late_init(void);
extern void pcibios_sort(void);

/* pci-mmconfig.c */
diff -ruw linux-2.6.21.1/drivers/acpi/bus.c linux-2.6.21.1edit/drivers/acpi/bus.c
--- linux-2.6.21.1/drivers/acpi/bus.c	2007-04-27 15:49:26.000000000 -0600
+++ linux-2.6.21.1edit/drivers/acpi/bus.c	2007-04-29 19:22:07.000000000 -0600
@@ -42,6 +42,7 @@
ACPI_MODULE_NAME("bus");
#ifdef	CONFIG_X86
extern void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger);
+extern void __init pci_mmcfg_late_init(void);
#endif

struct acpi_device *acpi_root;
@@ -753,6 +754,9 @@
	result = acpi_bus_init();

	if (!result) {
+#ifdef CONFIG_X86
+		pci_mmcfg_late_init();
+#endif		
#ifdef CONFIG_PM_LEGACY
		if (!PM_IS_ACTIVE())
			pm_active = 1;
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/