xen/setup: Set identity mapping for non-RAM E820 and E820 gaps.

We walk the E820 region and start at 0 (for PV guests we start
at ISA_END_ADDRESS) and skip any E820 RAM regions. For all other
regions and as well the gaps we set them to be identity mappings.

The reasons we do not want to set the identity mapping from 0->
ISA_END_ADDRESS when running as PV is b/c that the kernel would
try to read DMI information and fail (no permissions to read that).
There is a lot of gnarly code to deal with that weird region so
we won't try to do a cleanup in this patch.

This code ends up calling 'set_phys_to_identity' with the start
and end PFN of the the E820 that are non-RAM or have gaps.
On 99% of machines that means one big region right underneath the
4GB mark. Usually starts at 0xc0000 (or 0x80000) and goes to
0x100000.

[v2: Fix for E820 crossing 1MB region and clamp the start]
[v3: Squshed in code that does this over ranges]
[v4: Moved the comment to the correct spot]
[v5: Use the "raw" E820 from the hypervisor]
[v6: Added Review-by tag]

Reviewed-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

1 files changed, 52 insertions, 0 deletions

diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 7201800..54d9379 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -143,12 +143,55 @@ static unsigned long __init xen_return_unused_memory(unsigned long max_pfn,
 	return released;
 }
 
+static unsigned long __init xen_set_identity(const struct e820entry *list,
+					     ssize_t map_size)
+{
+	phys_addr_t last = xen_initial_domain() ? 0 : ISA_END_ADDRESS;
+	phys_addr_t start_pci = last;
+	const struct e820entry *entry;
+	unsigned long identity = 0;
+	int i;
+
+	for (i = 0, entry = list; i < map_size; i++, entry++) {
+		phys_addr_t start = entry->addr;
+		phys_addr_t end = start + entry->size;
+
+		if (start < last)
+			start = last;
+
+		if (end <= start)
+			continue;
+
+		/* Skip over the 1MB region. */
+		if (last > end)
+			continue;
+
+		if (entry->type == E820_RAM) {
+			if (start > start_pci)
+				identity += set_phys_range_identity(
+						PFN_UP(start_pci), PFN_DOWN(start));
+
+			/* Without saving 'last' we would gooble RAM too
+			 * at the end of the loop. */
+			last = end;
+			start_pci = end;
+			continue;
+		}
+		start_pci = min(start, start_pci);
+		last = end;
+	}
+	if (last > start_pci)
+		identity += set_phys_range_identity(
+					PFN_UP(start_pci), PFN_DOWN(last));
+	return identity;
+}
 /**
  * machine_specific_memory_setup - Hook for machine specific memory setup.
  **/
 char * __init xen_memory_setup(void)
 {
 	static struct e820entry map[E820MAX] __initdata;
+	static struct e820entry map_raw[E820MAX] __initdata;
 
 	unsigned long max_pfn = xen_start_info->nr_pages;
 	unsigned long long mem_end;
@@ -156,6 +199,7 @@ char * __init xen_memory_setup(void)
 	struct xen_memory_map memmap;
 	unsigned long extra_pages = 0;
 	unsigned long extra_limit;
+	unsigned long identity_pages = 0;
 	int i;
 	int op;
 
@@ -181,6 +225,7 @@ char * __init xen_memory_setup(void)
 	}
 	BUG_ON(rc);
 
+	memcpy(map_raw, map, sizeof(map));
 	e820.nr_map = 0;
 	xen_extra_mem_start = mem_end;
 	for (i = 0; i < memmap.nr_entries; i++) {
@@ -251,6 +296,13 @@ char * __init xen_memory_setup(void)
 
 	xen_add_extra_mem(extra_pages);
 
+	/*
+	 * Set P2M for all non-RAM pages and E820 gaps to be identity
+	 * type PFNs. We supply it with the non-sanitized version
+	 * of the E820.
+	 */
+	identity_pages = xen_set_identity(map_raw, memmap.nr_entries);
+	printk(KERN_INFO "Set %ld page(s) to 1-1 mapping.\n", identity_pages);
 	return "Xen";
 }