1 files changed, 87 insertions, 26 deletions

diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index ef2859f9fcce..769321185a08 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Firmware replacement code.
  *
@@ -13,6 +14,7 @@
 #define pr_fmt(fmt) "AGP: " fmt
 
 #include <linux/kernel.h>
+#include <linux/kcore.h>
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/memblock.h>
@@ -27,13 +29,14 @@
 #include <asm/gart.h>
 #include <asm/pci-direct.h>
 #include <asm/dma.h>
-#include <asm/amd_nb.h>
+#include <asm/amd/nb.h>
 #include <asm/x86_init.h>
+#include <linux/crash_dump.h>
 
 /*
  * Using 512M as goal, in case kexec will load kernel_big
  * that will do the on-position decompress, and could overlap with
- * with the gart aperture that is used.
+ * the gart aperture that is used.
  * Sequence:
  * kernel_small
  * ==> kexec (with kdump trigger path or gart still enabled)
@@ -55,6 +58,49 @@ int fallback_aper_force __initdata;
 
 int fix_aperture __initdata = 1;
 
+#if defined(CONFIG_PROC_VMCORE) || defined(CONFIG_PROC_KCORE)
+/*
+ * If the first kernel maps the aperture over e820 RAM, the kdump kernel will
+ * use the same range because it will remain configured in the northbridge.
+ * Trying to dump this area via /proc/vmcore may crash the machine, so exclude
+ * it from vmcore.
+ */
+static unsigned long aperture_pfn_start, aperture_page_count;
+
+static int gart_mem_pfn_is_ram(unsigned long pfn)
+{
+	return likely((pfn < aperture_pfn_start) ||
+		      (pfn >= aperture_pfn_start + aperture_page_count));
+}
+
+#ifdef CONFIG_PROC_VMCORE
+static bool gart_oldmem_pfn_is_ram(struct vmcore_cb *cb, unsigned long pfn)
+{
+	return !!gart_mem_pfn_is_ram(pfn);
+}
+
+static struct vmcore_cb gart_vmcore_cb = {
+	.pfn_is_ram = gart_oldmem_pfn_is_ram,
+};
+#endif
+
+static void __init exclude_from_core(u64 aper_base, u32 aper_order)
+{
+	aperture_pfn_start = aper_base >> PAGE_SHIFT;
+	aperture_page_count = (32 * 1024 * 1024) << aper_order >> PAGE_SHIFT;
+#ifdef CONFIG_PROC_VMCORE
+	register_vmcore_cb(&gart_vmcore_cb);
+#endif
+#ifdef CONFIG_PROC_KCORE
+	WARN_ON(register_mem_pfn_is_ram(&gart_mem_pfn_is_ram));
+#endif
+}
+#else
+static void exclude_from_core(u64 aper_base, u32 aper_order)
+{
+}
+#endif
+
 /* This code runs before the PCI subsystem is initialized, so just
    access the northbridge directly. */
 
@@ -74,14 +120,13 @@ static u32 __init allocate_aperture(void)
 	 * memory. Unfortunately we cannot move it up because that would
 	 * make the IOMMU useless.
 	 */
-	addr = memblock_find_in_range(GART_MIN_ADDR, GART_MAX_ADDR,
-				      aper_size, aper_size);
+	addr = memblock_phys_alloc_range(aper_size, aper_size,
+					 GART_MIN_ADDR, GART_MAX_ADDR);
 	if (!addr) {
 		pr_err("Cannot allocate aperture memory hole [mem %#010lx-%#010lx] (%uKB)\n",
 		       addr, addr + aper_size - 1, aper_size >> 10);
 		return 0;
 	}
-	memblock_reserve(addr, aper_size);
 	pr_info("Mapping aperture over RAM [mem %#010lx-%#010lx] (%uKB)\n",
 		addr, addr + aper_size - 1, aper_size >> 10);
 	register_nosave_region(addr >> PAGE_SHIFT,
@@ -214,10 +259,9 @@ static u32 __init search_agp_bridge(u32 *order, int *valid_agp)
 							order);
 				}
 
-				/* No multi-function device? */
 				type = read_pci_config_byte(bus, slot, func,
 							       PCI_HEADER_TYPE);
-				if (!(type & 0x80))
+				if (!(type & PCI_HEADER_TYPE_MFD))
 					break;
 			}
 		}
@@ -235,18 +279,23 @@ static int __init parse_gart_mem(char *p)
 }
 early_param("gart_fix_e820", parse_gart_mem);
 
+/*
+ * With kexec/kdump, if the first kernel doesn't shut down the GART and the
+ * second kernel allocates a different GART region, there might be two
+ * overlapping GART regions present:
+ *
+ * - the first still used by the GART initialized in the first kernel.
+ * - (sub-)set of it used as normal RAM by the second kernel.
+ *
+ * which leads to memory corruptions and a kernel panic eventually.
+ *
+ * This can also happen if the BIOS has forgotten to mark the GART region
+ * as reserved.
+ *
+ * Try to update the e820 map to mark that new region as reserved.
+ */
 void __init early_gart_iommu_check(void)
 {
-	/*
-	 * in case it is enabled before, esp for kexec/kdump,
-	 * previous kernel already enable that. memset called
-	 * by allocate_aperture/__alloc_bootmem_nopanic cause restart.
-	 * or second kernel have different position for GART hole. and new
-	 * kernel could use hole as RAM that is still used by GART set by
-	 * first kernel
-	 * or BIOS forget to put that in reserved.
-	 * try to update e820 to make that region as reserved.
-	 */
 	u32 agp_aper_order = 0;
 	int i, fix, slot, valid_agp = 0;
 	u32 ctl;
@@ -342,7 +391,7 @@ void __init early_gart_iommu_check(void)
 
 static int __initdata printed_gart_size_msg;
 
-int __init gart_iommu_hole_init(void)
+void __init gart_iommu_hole_init(void)
 {
 	u32 agp_aper_base = 0, agp_aper_order = 0;
 	u32 aper_size, aper_alloc = 0, aper_order = 0, last_aper_order = 0;
@@ -351,11 +400,11 @@ int __init gart_iommu_hole_init(void)
 	int i, node;
 
 	if (!amd_gart_present())
-		return -ENODEV;
+		return;
 
 	if (gart_iommu_aperture_disabled || !fix_aperture ||
 	    !early_pci_allowed())
-		return -ENODEV;
+		return;
 
 	pr_info("Checking aperture...\n");
 
@@ -434,9 +483,15 @@ int __init gart_iommu_hole_init(void)
 
 out:
 	if (!fix && !fallback_aper_force) {
-		if (last_aper_base)
-			return 1;
-		return 0;
+		if (last_aper_base) {
+			/*
+			 * If this is the kdump kernel, the first kernel
+			 * may have allocated the range over its e820 RAM
+			 * and fixed up the northbridge
+			 */
+			exclude_from_core(last_aper_base, last_aper_order);
+		}
+		return;
 	}
 
 	if (!fallback_aper_force) {
@@ -469,9 +524,17 @@ out:
 			panic("Not enough memory for aperture");
 		}
 	} else {
-		return 0;
+		return;
 	}
 
+	/*
+	 * If this is the kdump kernel _and_ the first kernel did not
+	 * configure the aperture in the northbridge, this range may
+	 * overlap with the first kernel's memory. We can't access the
+	 * range through vmcore even though it should be part of the dump.
+	 */
+	exclude_from_core(aper_alloc, aper_order);
+
 	/* Fix up the north bridges */
 	for (i = 0; i < amd_nb_bus_dev_ranges[i].dev_limit; i++) {
 		int bus, dev_base, dev_limit;
@@ -495,6 +558,4 @@ out:
 	}
 
 	set_up_gart_resume(aper_order, aper_alloc);
-
-	return 1;
 }