Merge branches 'upstream/xenfs' and 'upstream/core' of git://git.kernel.org/pub/scm/linux/kernel/git/jeremy/xen
* 'upstream/xenfs' of git://git.kernel.org/pub/scm/linux/kernel/git/jeremy/xen:
xen/privcmd: make privcmd visible in domU
xen/privcmd: move remap_domain_mfn_range() to core xen code and export.
privcmd: MMAPBATCH: Fix error handling/reporting
xenbus: export xen_store_interface for xenfs
xen/privcmd: make sure vma is ours before doing anything to it
xen/privcmd: print SIGBUS faults
xen/xenfs: set_page_dirty is supposed to return true if it dirties
xen/privcmd: create address space to allow writable mmaps
xen: add privcmd driver
xen: add variable hypercall caller
xen: add xen_set_domain_pte()
xen: add /proc/xen/xsd_{kva,port} to xenfs
* 'upstream/core' of git://git.kernel.org/pub/scm/linux/kernel/git/jeremy/xen: (29 commits)
xen: include xen/xen.h for definition of xen_initial_domain()
xen: use host E820 map for dom0
xen: correctly rebuild mfn list list after migration.
xen: improvements to VIRQ_DEBUG output
xen: set up IRQ before binding virq to evtchn
xen: ensure that all event channels start off bound to VCPU 0
xen/hvc: only notify if we actually sent something
xen: don't add extra_pages for RAM after mem_end
xen: add support for PAT
xen: make sure xen_max_p2m_pfn is up to date
xen: limit extra memory to a certain ratio of base
xen: add extra pages for E820 RAM regions, even if beyond mem_end
xen: make sure xen_extra_mem_start is beyond all non-RAM e820
xen: implement "extra" memory to reserve space for pages not present at boot
xen: Use host-provided E820 map
xen: don't map missing memory
xen: defer building p2m mfn structures until kernel is mapped
xen: add return value to set_phys_to_machine()
xen: convert p2m to a 3 level tree
xen: make install_p2mtop_page() static
...
Fix up trivial conflict in arch/x86/xen/mmu.c, and fix the use of
'reserve_early()' - in the new memblock world order it is now
'memblock_x86_reserve_range()' instead. Pointed out by Jeremy.
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 9729c90..105db25 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -18,8 +18,10 @@
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
+#include <xen/xen.h>
#include <xen/page.h>
#include <xen/interface/callback.h>
+#include <xen/interface/memory.h>
#include <xen/interface/physdev.h>
#include <xen/interface/memory.h>
#include <xen/features.h>
@@ -34,6 +36,39 @@
extern void xen_syscall_target(void);
extern void xen_syscall32_target(void);
+/* Amount of extra memory space we add to the e820 ranges */
+phys_addr_t xen_extra_mem_start, xen_extra_mem_size;
+
+/*
+ * The maximum amount of extra memory compared to the base size. The
+ * main scaling factor is the size of struct page. At extreme ratios
+ * of base:extra, all the base memory can be filled with page
+ * structures for the extra memory, leaving no space for anything
+ * else.
+ *
+ * 10x seems like a reasonable balance between scaling flexibility and
+ * leaving a practically usable system.
+ */
+#define EXTRA_MEM_RATIO (10)
+
+static __init void xen_add_extra_mem(unsigned long pages)
+{
+ u64 size = (u64)pages * PAGE_SIZE;
+ u64 extra_start = xen_extra_mem_start + xen_extra_mem_size;
+
+ if (!pages)
+ return;
+
+ e820_add_region(extra_start, size, E820_RAM);
+ sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+
+ memblock_x86_reserve_range(extra_start, extra_start + size, "XEN EXTRA");
+
+ xen_extra_mem_size += size;
+
+ xen_max_p2m_pfn = PFN_DOWN(extra_start + size);
+}
+
static unsigned long __init xen_release_chunk(phys_addr_t start_addr,
phys_addr_t end_addr)
{
@@ -105,16 +140,65 @@
/**
* machine_specific_memory_setup - Hook for machine specific memory setup.
**/
-
char * __init xen_memory_setup(void)
{
+ static struct e820entry map[E820MAX] __initdata;
+
unsigned long max_pfn = xen_start_info->nr_pages;
+ unsigned long long mem_end;
+ int rc;
+ struct xen_memory_map memmap;
+ unsigned long extra_pages = 0;
+ unsigned long extra_limit;
+ int i;
+ int op;
max_pfn = min(MAX_DOMAIN_PAGES, max_pfn);
+ mem_end = PFN_PHYS(max_pfn);
+
+ memmap.nr_entries = E820MAX;
+ set_xen_guest_handle(memmap.buffer, map);
+
+ op = xen_initial_domain() ?
+ XENMEM_machine_memory_map :
+ XENMEM_memory_map;
+ rc = HYPERVISOR_memory_op(op, &memmap);
+ if (rc == -ENOSYS) {
+ memmap.nr_entries = 1;
+ map[0].addr = 0ULL;
+ map[0].size = mem_end;
+ /* 8MB slack (to balance backend allocations). */
+ map[0].size += 8ULL << 20;
+ map[0].type = E820_RAM;
+ rc = 0;
+ }
+ BUG_ON(rc);
e820.nr_map = 0;
+ xen_extra_mem_start = mem_end;
+ for (i = 0; i < memmap.nr_entries; i++) {
+ unsigned long long end = map[i].addr + map[i].size;
- e820_add_region(0, PFN_PHYS((u64)max_pfn), E820_RAM);
+ if (map[i].type == E820_RAM) {
+ if (map[i].addr < mem_end && end > mem_end) {
+ /* Truncate region to max_mem. */
+ u64 delta = end - mem_end;
+
+ map[i].size -= delta;
+ extra_pages += PFN_DOWN(delta);
+
+ end = mem_end;
+ }
+ }
+
+ if (end > xen_extra_mem_start)
+ xen_extra_mem_start = end;
+
+ /* If region is non-RAM or below mem_end, add what remains */
+ if ((map[i].type != E820_RAM || map[i].addr < mem_end) &&
+ map[i].size > 0)
+ e820_add_region(map[i].addr, map[i].size, map[i].type);
+ }
/*
* Even though this is normal, usable memory under Xen, reserve
@@ -136,7 +220,29 @@
sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
- xen_return_unused_memory(xen_start_info->nr_pages, &e820);
+ extra_pages += xen_return_unused_memory(xen_start_info->nr_pages, &e820);
+
+ /*
+ * Clamp the amount of extra memory to a EXTRA_MEM_RATIO
+ * factor the base size. On non-highmem systems, the base
+ * size is the full initial memory allocation; on highmem it
+ * is limited to the max size of lowmem, so that it doesn't
+ * get completely filled.
+ *
+ * In principle there could be a problem in lowmem systems if
+ * the initial memory is also very large with respect to
+ * lowmem, but we won't try to deal with that here.
+ */
+ extra_limit = min(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
+ max_pfn + extra_pages);
+
+ if (extra_limit >= max_pfn)
+ extra_pages = extra_limit - max_pfn;
+ else
+ extra_pages = 0;
+
+ if (!xen_initial_domain())
+ xen_add_extra_mem(extra_pages);
return "Xen";
}