Merge branch 'master' into x86/memblock
Conflicts & resolutions:
* arch/x86/xen/setup.c
dc91c728fd "xen: allow extra memory to be in multiple regions"
24aa07882b "memblock, x86: Replace memblock_x86_reserve/free..."
conflicted on xen_add_extra_mem() updates. The resolution is
trivial as the latter just want to replace
memblock_x86_reserve_range() with memblock_reserve().
* drivers/pci/intel-iommu.c
166e9278a3f "x86/ia64: intel-iommu: move to drivers/iommu/"
5dfe8660a3d "bootmem: Replace work_with_active_regions() with..."
conflicted as the former moved the file under drivers/iommu/.
Resolved by applying the chnages from the latter on the moved
file.
* mm/Kconfig
6661672053a "memblock: add NO_BOOTMEM config symbol"
c378ddd53f9 "memblock, x86: Make ARCH_DISCARD_MEMBLOCK a config option"
conflicted trivially. Both added config options. Just
letting both add their own options resolves the conflict.
* mm/memblock.c
d1f0ece6cdc "mm/memblock.c: small function definition fixes"
ed7b56a799c "memblock: Remove memblock_memory_can_coalesce()"
confliected. The former updates function removed by the
latter. Resolution is trivial.
Signed-off-by: Tejun Heo <tj@kernel.org>
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 73daaf7..f5e1362 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -9,6 +9,7 @@
#include <linux/mm.h>
#include <linux/pm.h>
#include <linux/memblock.h>
+#include <linux/cpuidle.h>
#include <asm/elf.h>
#include <asm/vdso.h>
@@ -36,7 +37,10 @@
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;
+struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
+
+/* Number of pages released from the initial allocation. */
+unsigned long xen_released_pages;
/*
* The maximum amount of extra memory compared to the base size. The
@@ -50,50 +54,47 @@
*/
#define EXTRA_MEM_RATIO (10)
-static void __init xen_add_extra_mem(unsigned long pages)
+static void __init xen_add_extra_mem(u64 start, u64 size)
{
unsigned long pfn;
+ int i;
- u64 size = (u64)pages * PAGE_SIZE;
- u64 extra_start = xen_extra_mem_start + xen_extra_mem_size;
+ for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
+ /* Add new region. */
+ if (xen_extra_mem[i].size == 0) {
+ xen_extra_mem[i].start = start;
+ xen_extra_mem[i].size = size;
+ break;
+ }
+ /* Append to existing region. */
+ if (xen_extra_mem[i].start + xen_extra_mem[i].size == start) {
+ xen_extra_mem[i].size += size;
+ break;
+ }
+ }
+ if (i == XEN_EXTRA_MEM_MAX_REGIONS)
+ printk(KERN_WARNING "Warning: not enough extra memory regions\n");
- if (!pages)
- return;
+ memblock_reserve(start, size);
- e820_add_region(extra_start, size, E820_RAM);
- sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+ xen_max_p2m_pfn = PFN_DOWN(start + size);
- memblock_reserve(extra_start, size);
-
- xen_extra_mem_size += size;
-
- xen_max_p2m_pfn = PFN_DOWN(extra_start + size);
-
- for (pfn = PFN_DOWN(extra_start); pfn <= xen_max_p2m_pfn; pfn++)
+ for (pfn = PFN_DOWN(start); pfn <= xen_max_p2m_pfn; pfn++)
__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
}
-static unsigned long __init xen_release_chunk(phys_addr_t start_addr,
- phys_addr_t end_addr)
+static unsigned long __init xen_release_chunk(unsigned long start,
+ unsigned long end)
{
struct xen_memory_reservation reservation = {
.address_bits = 0,
.extent_order = 0,
.domid = DOMID_SELF
};
- unsigned long start, end;
unsigned long len = 0;
unsigned long pfn;
int ret;
- start = PFN_UP(start_addr);
- end = PFN_DOWN(end_addr);
-
- if (end <= start)
- return 0;
-
- printk(KERN_INFO "xen_release_chunk: looking at area pfn %lx-%lx: ",
- start, end);
for(pfn = start; pfn < end; pfn++) {
unsigned long mfn = pfn_to_mfn(pfn);
@@ -106,100 +107,104 @@
ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation,
&reservation);
- WARN(ret != 1, "Failed to release memory %lx-%lx err=%d\n",
- start, end, ret);
+ WARN(ret != 1, "Failed to release pfn %lx err=%d\n", pfn, ret);
if (ret == 1) {
__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
len++;
}
}
- printk(KERN_CONT "%ld pages freed\n", len);
+ printk(KERN_INFO "Freeing %lx-%lx pfn range: %lu pages freed\n",
+ start, end, len);
return len;
}
-static unsigned long __init xen_return_unused_memory(unsigned long max_pfn,
- const struct e820map *e820)
+static unsigned long __init xen_set_identity_and_release(
+ const struct e820entry *list, size_t map_size, unsigned long nr_pages)
{
- phys_addr_t max_addr = PFN_PHYS(max_pfn);
- phys_addr_t last_end = ISA_END_ADDRESS;
+ phys_addr_t start = 0;
unsigned long released = 0;
+ unsigned long identity = 0;
+ const struct e820entry *entry;
int i;
- /* Free any unused memory above the low 1Mbyte. */
- for (i = 0; i < e820->nr_map && last_end < max_addr; i++) {
- phys_addr_t end = e820->map[i].addr;
- end = min(max_addr, end);
+ /*
+ * Combine non-RAM regions and gaps until a RAM region (or the
+ * end of the map) is reached, then set the 1:1 map and
+ * release the pages (if available) in those non-RAM regions.
+ *
+ * The combined non-RAM regions are rounded to a whole number
+ * of pages so any partial pages are accessible via the 1:1
+ * mapping. This is needed for some BIOSes that put (for
+ * example) the DMI tables in a reserved region that begins on
+ * a non-page boundary.
+ */
+ for (i = 0, entry = list; i < map_size; i++, entry++) {
+ phys_addr_t end = entry->addr + entry->size;
- if (last_end < end)
- released += xen_release_chunk(last_end, end);
- last_end = max(last_end, e820->map[i].addr + e820->map[i].size);
+ if (entry->type == E820_RAM || i == map_size - 1) {
+ unsigned long start_pfn = PFN_DOWN(start);
+ unsigned long end_pfn = PFN_UP(end);
+
+ if (entry->type == E820_RAM)
+ end_pfn = PFN_UP(entry->addr);
+
+ if (start_pfn < end_pfn) {
+ if (start_pfn < nr_pages)
+ released += xen_release_chunk(
+ start_pfn, min(end_pfn, nr_pages));
+
+ identity += set_phys_range_identity(
+ start_pfn, end_pfn);
+ }
+ start = end;
+ }
}
- if (last_end < max_addr)
- released += xen_release_chunk(last_end, max_addr);
+ printk(KERN_INFO "Released %lu pages of unused memory\n", released);
+ printk(KERN_INFO "Set %ld page(s) to 1-1 mapping\n", identity);
- printk(KERN_INFO "released %ld pages of unused memory\n", released);
return released;
}
-static unsigned long __init xen_set_identity(const struct e820entry *list,
- ssize_t map_size)
+static unsigned long __init xen_get_max_pages(void)
{
- 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;
+ unsigned long max_pages = MAX_DOMAIN_PAGES;
+ domid_t domid = DOMID_SELF;
+ int ret;
- 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) || (entry->type == E820_UNUSABLE)) {
- 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;
+ ret = HYPERVISOR_memory_op(XENMEM_maximum_reservation, &domid);
+ if (ret > 0)
+ max_pages = ret;
+ return min(max_pages, MAX_DOMAIN_PAGES);
}
+
+static void xen_align_and_add_e820_region(u64 start, u64 size, int type)
+{
+ u64 end = start + size;
+
+ /* Align RAM regions to page boundaries. */
+ if (type == E820_RAM) {
+ start = PAGE_ALIGN(start);
+ end &= ~((u64)PAGE_SIZE - 1);
+ }
+
+ e820_add_region(start, end - start, type);
+}
+
/**
* 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;
int rc;
struct xen_memory_map memmap;
+ unsigned long max_pages;
unsigned long extra_pages = 0;
- unsigned long extra_limit;
- unsigned long identity_pages = 0;
int i;
int op;
@@ -225,58 +230,65 @@
}
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++) {
- unsigned long long end;
+ /* Make sure the Xen-supplied memory map is well-ordered. */
+ sanitize_e820_map(map, memmap.nr_entries, &memmap.nr_entries);
- /* Guard against non-page aligned E820 entries. */
- if (map[i].type == E820_RAM)
- map[i].size -= (map[i].size + map[i].addr) % PAGE_SIZE;
+ max_pages = xen_get_max_pages();
+ if (max_pages > max_pfn)
+ extra_pages += max_pages - max_pfn;
- end = map[i].addr + map[i].size;
- if (map[i].type == E820_RAM && end > mem_end) {
- /* RAM off the end - may be partially included */
- u64 delta = min(map[i].size, end - mem_end);
+ /*
+ * Set P2M for all non-RAM pages and E820 gaps to be identity
+ * type PFNs. Any RAM pages that would be made inaccesible by
+ * this are first released.
+ */
+ xen_released_pages = xen_set_identity_and_release(
+ map, memmap.nr_entries, max_pfn);
+ extra_pages += xen_released_pages;
- map[i].size -= delta;
- end -= delta;
+ /*
+ * 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_pages = min(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
+ extra_pages);
- extra_pages += PFN_DOWN(delta);
- /*
- * Set RAM below 4GB that is not for us to be unusable.
- * This prevents "System RAM" address space from being
- * used as potential resource for I/O address (happens
- * when 'allocate_resource' is called).
- */
- if (delta &&
- (xen_initial_domain() && end < 0x100000000ULL))
- e820_add_region(end, delta, E820_UNUSABLE);
+ i = 0;
+ while (i < memmap.nr_entries) {
+ u64 addr = map[i].addr;
+ u64 size = map[i].size;
+ u32 type = map[i].type;
+
+ if (type == E820_RAM) {
+ if (addr < mem_end) {
+ size = min(size, mem_end - addr);
+ } else if (extra_pages) {
+ size = min(size, (u64)extra_pages * PAGE_SIZE);
+ extra_pages -= size / PAGE_SIZE;
+ xen_add_extra_mem(addr, size);
+ } else
+ type = E820_UNUSABLE;
}
- if (map[i].size > 0 && end > xen_extra_mem_start)
- xen_extra_mem_start = end;
+ xen_align_and_add_e820_region(addr, size, type);
- /* Add region if any remains */
- if (map[i].size > 0)
- e820_add_region(map[i].addr, map[i].size, map[i].type);
+ map[i].addr += size;
+ map[i].size -= size;
+ if (map[i].size == 0)
+ i++;
}
- /* Align the balloon area so that max_low_pfn does not get set
- * to be at the _end_ of the PCI gap at the far end (fee01000).
- * Note that xen_extra_mem_start gets set in the loop above to be
- * past the last E820 region. */
- if (xen_initial_domain() && (xen_extra_mem_start < (1ULL<<32)))
- xen_extra_mem_start = (1ULL<<32);
/*
* In domU, the ISA region is normal, usable memory, but we
* reserve ISA memory anyway because too many things poke
* about in there.
- *
- * In Dom0, the host E820 information can leave gaps in the
- * ISA range, which would cause us to release those pages. To
- * avoid this, we unconditionally reserve them here.
*/
e820_add_region(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS,
E820_RESERVED);
@@ -292,36 +304,6 @@
sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
- 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;
-
- 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";
}
@@ -425,7 +407,7 @@
#ifdef CONFIG_X86_32
boot_cpu_data.hlt_works_ok = 1;
#endif
- pm_idle = default_idle;
+ disable_cpuidle();
boot_option_idle_override = IDLE_HALT;
fiddle_vdso();