[GIT pull] x86/mm updates for 4.16

[GIT pull] x86/mm updates for 4.16

[Thomas Gleixner]

Linus,

please pull the latest x86-mm-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-mm-for-linus

A single patch which excludes the GART aperture from vmcore as accessing
that area from a dump kernel can crash the kernel. Not necessarily the
nicest way to fix this, but curing this from ground up requires a more
thorough rewrite of the whole kexec/kdump magic.

Thanks,

	tglx

------------------>
Jiri Bohac (1):
      x86/gart: Exclude GART aperture from vmcore


 arch/x86/kernel/aperture_64.c | 46 ++++++++++++++++++++++++++++++++++++++++++-
 arch/x86/xen/mmu_hvm.c        |  2 +-
 2 files changed, 46 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index f5d92bc3b884..2c4d5ece7456 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -30,6 +30,7 @@
 #include <asm/dma.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
@@ -56,6 +57,33 @@ int fallback_aper_force __initdata;
 
 int fix_aperture __initdata = 1;
 
+#ifdef CONFIG_PROC_VMCORE
+/*
+ * 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_oldmem_pfn_is_ram(unsigned long pfn)
+{
+	return likely((pfn < aperture_pfn_start) ||
+		      (pfn >= aperture_pfn_start + aperture_page_count));
+}
+
+static void exclude_from_vmcore(u64 aper_base, u32 aper_order)
+{
+	aperture_pfn_start = aper_base >> PAGE_SHIFT;
+	aperture_page_count = (32 * 1024 * 1024) << aper_order >> PAGE_SHIFT;
+	WARN_ON(register_oldmem_pfn_is_ram(&gart_oldmem_pfn_is_ram));
+}
+#else
+static void exclude_from_vmcore(u64 aper_base, u32 aper_order)
+{
+}
+#endif
+
 /* This code runs before the PCI subsystem is initialized, so just
    access the northbridge directly. */
 
@@ -435,8 +463,16 @@ int __init gart_iommu_hole_init(void)
 
 out:
 	if (!fix && !fallback_aper_force) {
-		if (last_aper_base)
+		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_vmcore(last_aper_base, last_aper_order);
+
 			return 1;
+		}
 		return 0;
 	}
 
@@ -473,6 +509,14 @@ int __init gart_iommu_hole_init(void)
 		return 0;
 	}
 
+	/*
+	 * 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_vmcore(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;
diff --git a/arch/x86/xen/mmu_hvm.c b/arch/x86/xen/mmu_hvm.c
index 2cfcfe4f6b2a..dd2ad82eee80 100644
--- a/arch/x86/xen/mmu_hvm.c
+++ b/arch/x86/xen/mmu_hvm.c
@@ -75,6 +75,6 @@ void __init xen_hvm_init_mmu_ops(void)
 	if (is_pagetable_dying_supported())
 		pv_mmu_ops.exit_mmap = xen_hvm_exit_mmap;
 #ifdef CONFIG_PROC_VMCORE
-	register_oldmem_pfn_is_ram(&xen_oldmem_pfn_is_ram);
+	WARN_ON(register_oldmem_pfn_is_ram(&xen_oldmem_pfn_is_ram));
 #endif
 }