#include <xen/hvc-console.h>
#include "xen-ops.h"
#include "vdso.h"
-#include "p2m.h"
#include "mmu.h"
+#define GB(x) ((uint64_t)(x) * 1024 * 1024 * 1024)
+
/* Amount of extra memory space we add to the e820 ranges */
struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
*/
#define EXTRA_MEM_RATIO (10)
-static void __init xen_add_extra_mem(phys_addr_t start, phys_addr_t size)
+static bool xen_512gb_limit __initdata = IS_ENABLED(CONFIG_XEN_512GB);
+
+static void __init xen_parse_512gb(void)
+{
+ bool val = false;
+ char *arg;
+
+ arg = strstr(xen_start_info->cmd_line, "xen_512gb_limit");
+ if (!arg)
+ return;
+
+ arg = strstr(xen_start_info->cmd_line, "xen_512gb_limit=");
+ if (!arg)
+ val = true;
+ else if (strtobool(arg + strlen("xen_512gb_limit="), &val))
+ return;
+
+ xen_512gb_limit = val;
+}
+
+static void __init xen_add_extra_mem(unsigned long start_pfn,
+ unsigned long n_pfns)
{
int i;
+ /*
+ * No need to check for zero size, should happen rarely and will only
+ * write a new entry regarded to be unused due to zero 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;
+ if (xen_extra_mem[i].n_pfns == 0) {
+ xen_extra_mem[i].start_pfn = start_pfn;
+ xen_extra_mem[i].n_pfns = n_pfns;
break;
}
/* Append to existing region. */
- if (xen_extra_mem[i].start + xen_extra_mem[i].size == start) {
- xen_extra_mem[i].size += size;
+ if (xen_extra_mem[i].start_pfn + xen_extra_mem[i].n_pfns ==
+ start_pfn) {
+ xen_extra_mem[i].n_pfns += n_pfns;
break;
}
}
if (i == XEN_EXTRA_MEM_MAX_REGIONS)
printk(KERN_WARNING "Warning: not enough extra memory regions\n");
- memblock_reserve(start, size);
+ memblock_reserve(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns));
}
-static void __init xen_del_extra_mem(phys_addr_t start, phys_addr_t size)
+static void __init xen_del_extra_mem(unsigned long start_pfn,
+ unsigned long n_pfns)
{
int i;
- phys_addr_t start_r, size_r;
+ unsigned long start_r, size_r;
for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
- start_r = xen_extra_mem[i].start;
- size_r = xen_extra_mem[i].size;
+ start_r = xen_extra_mem[i].start_pfn;
+ size_r = xen_extra_mem[i].n_pfns;
/* Start of region. */
- if (start_r == start) {
- BUG_ON(size > size_r);
- xen_extra_mem[i].start += size;
- xen_extra_mem[i].size -= size;
+ if (start_r == start_pfn) {
+ BUG_ON(n_pfns > size_r);
+ xen_extra_mem[i].start_pfn += n_pfns;
+ xen_extra_mem[i].n_pfns -= n_pfns;
break;
}
/* End of region. */
- if (start_r + size_r == start + size) {
- BUG_ON(size > size_r);
- xen_extra_mem[i].size -= size;
+ if (start_r + size_r == start_pfn + n_pfns) {
+ BUG_ON(n_pfns > size_r);
+ xen_extra_mem[i].n_pfns -= n_pfns;
break;
}
/* Mid of region. */
- if (start > start_r && start < start_r + size_r) {
- BUG_ON(start + size > start_r + size_r);
- xen_extra_mem[i].size = start - start_r;
+ if (start_pfn > start_r && start_pfn < start_r + size_r) {
+ BUG_ON(start_pfn + n_pfns > start_r + size_r);
+ xen_extra_mem[i].n_pfns = start_pfn - start_r;
/* Calling memblock_reserve() again is okay. */
- xen_add_extra_mem(start + size, start_r + size_r -
- (start + size));
+ xen_add_extra_mem(start_pfn + n_pfns, start_r + size_r -
+ (start_pfn + n_pfns));
break;
}
}
- memblock_free(start, size);
+ memblock_free(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns));
}
/*
unsigned long __ref xen_chk_extra_mem(unsigned long pfn)
{
int i;
- phys_addr_t addr = PFN_PHYS(pfn);
for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
- if (addr >= xen_extra_mem[i].start &&
- addr < xen_extra_mem[i].start + xen_extra_mem[i].size)
+ if (pfn >= xen_extra_mem[i].start_pfn &&
+ pfn < xen_extra_mem[i].start_pfn + xen_extra_mem[i].n_pfns)
return INVALID_P2M_ENTRY;
}
int i;
for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
- if (!xen_extra_mem[i].size)
+ if (!xen_extra_mem[i].n_pfns)
continue;
- pfn_s = PFN_DOWN(xen_extra_mem[i].start);
- pfn_e = PFN_UP(xen_extra_mem[i].start + xen_extra_mem[i].size);
+ pfn_s = xen_extra_mem[i].start_pfn;
+ pfn_e = pfn_s + xen_extra_mem[i].n_pfns;
for (pfn = pfn_s; pfn < pfn_e; pfn++)
set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
}
} else if (pfn_s + len == xen_remap_buf.target_pfn) {
len += xen_remap_buf.size;
} else {
- xen_del_extra_mem(PFN_PHYS(pfn_s), PFN_PHYS(len));
+ xen_del_extra_mem(pfn_s, len);
pfn_s = xen_remap_buf.target_pfn;
len = xen_remap_buf.size;
}
}
if (pfn_s != ~0UL && len)
- xen_del_extra_mem(PFN_PHYS(pfn_s), PFN_PHYS(len));
+ xen_del_extra_mem(pfn_s, len);
set_pte_mfn(buf, mfn_save, PAGE_KERNEL);
pr_info("Remapped %ld page(s)\n", remapped);
}
+static unsigned long __init xen_get_pages_limit(void)
+{
+ unsigned long limit;
+
+#ifdef CONFIG_X86_32
+ limit = GB(64) / PAGE_SIZE;
+#else
+ limit = MAXMEM / PAGE_SIZE;
+ if (!xen_initial_domain() && xen_512gb_limit)
+ limit = GB(512) / PAGE_SIZE;
+#endif
+ return limit;
+}
+
static unsigned long __init xen_get_max_pages(void)
{
- unsigned long max_pages = MAX_DOMAIN_PAGES;
+ unsigned long max_pages, limit;
domid_t domid = DOMID_SELF;
int ret;
+ limit = xen_get_pages_limit();
+ max_pages = limit;
+
/*
* For the initial domain we use the maximum reservation as
* the maximum page.
max_pages = ret;
}
- return min(max_pages, MAX_DOMAIN_PAGES);
+ return min(max_pages, limit);
}
static void __init xen_align_and_add_e820_region(phys_addr_t start,
static unsigned long __init xen_count_remap_pages(unsigned long max_pfn)
{
unsigned long extra = 0;
+ unsigned long start_pfn, end_pfn;
const struct e820entry *entry = xen_e820_map;
int i;
+ end_pfn = 0;
for (i = 0; i < xen_e820_map_entries; i++, entry++) {
- unsigned long start_pfn = PFN_DOWN(entry->addr);
- unsigned long end_pfn = PFN_UP(entry->addr + entry->size);
+ start_pfn = PFN_DOWN(entry->addr);
+ /* Adjacent regions on non-page boundaries handling! */
+ end_pfn = min(end_pfn, start_pfn);
if (start_pfn >= max_pfn)
- break;
- if (entry->type == E820_RAM)
- continue;
- if (end_pfn >= max_pfn)
- end_pfn = max_pfn;
- extra += end_pfn - start_pfn;
+ return extra + max_pfn - end_pfn;
+
+ /* Add any holes in map to result. */
+ extra += start_pfn - end_pfn;
+
+ end_pfn = PFN_UP(entry->addr + entry->size);
+ end_pfn = min(end_pfn, max_pfn);
+
+ if (entry->type != E820_RAM)
+ extra += end_pfn - start_pfn;
}
return extra;
/*
* Reserve Xen mfn_list.
- * See comment above "struct start_info" in <xen/interface/xen.h>
- * We tried to make the the memblock_reserve more selective so
- * that it would be clear what region is reserved. Sadly we ran
- * in the problem wherein on a 64-bit hypervisor with a 32-bit
- * initial domain, the pt_base has the cr3 value which is not
- * neccessarily where the pagetable starts! As Jan put it: "
- * Actually, the adjustment turns out to be correct: The page
- * tables for a 32-on-64 dom0 get allocated in the order "first L1",
- * "first L2", "first L3", so the offset to the page table base is
- * indeed 2. When reading xen/include/public/xen.h's comment
- * very strictly, this is not a violation (since there nothing is said
- * that the first thing in the page table space is pointed to by
- * pt_base; I admit that this seems to be implied though, namely
- * do I think that it is implied that the page table space is the
- * range [pt_base, pt_base + nt_pt_frames), whereas that
- * range here indeed is [pt_base - 2, pt_base - 2 + nt_pt_frames),
- * which - without a priori knowledge - the kernel would have
- * difficulty to figure out)." - so lets just fall back to the
- * easy way and reserve the whole region.
*/
static void __init xen_reserve_xen_mfnlist(void)
{
+ phys_addr_t start, size;
+
if (xen_start_info->mfn_list >= __START_KERNEL_map) {
- memblock_reserve(__pa(xen_start_info->mfn_list),
- xen_start_info->pt_base -
- xen_start_info->mfn_list);
+ start = __pa(xen_start_info->mfn_list);
+ size = PFN_ALIGN(xen_start_info->nr_pages *
+ sizeof(unsigned long));
+ } else {
+ start = PFN_PHYS(xen_start_info->first_p2m_pfn);
+ size = PFN_PHYS(xen_start_info->nr_p2m_frames);
+ }
+
+ if (!xen_is_e820_reserved(start, size)) {
+ memblock_reserve(start, size);
return;
}
- memblock_reserve(PFN_PHYS(xen_start_info->first_p2m_pfn),
- PFN_PHYS(xen_start_info->nr_p2m_frames));
+#ifdef CONFIG_X86_32
+ /*
+ * Relocating the p2m on 32 bit system to an arbitrary virtual address
+ * is not supported, so just give up.
+ */
+ xen_raw_console_write("Xen hypervisor allocated p2m list conflicts with E820 map\n");
+ BUG();
+#else
+ xen_relocate_p2m();
+#endif
}
/**
**/
char * __init xen_memory_setup(void)
{
- unsigned long max_pfn = xen_start_info->nr_pages;
+ unsigned long max_pfn, pfn_s, n_pfns;
phys_addr_t mem_end, addr, size, chunk_size;
u32 type;
int rc;
int i;
int op;
- max_pfn = min(MAX_DOMAIN_PAGES, max_pfn);
+ xen_parse_512gb();
+ max_pfn = xen_get_pages_limit();
+ max_pfn = min(max_pfn, xen_start_info->nr_pages);
mem_end = PFN_PHYS(max_pfn);
memmap.nr_entries = E820MAX;
&xen_e820_map_entries);
max_pages = xen_get_max_pages();
- if (max_pages > max_pfn)
- extra_pages += max_pages - max_pfn;
/* How many extra pages do we need due to remapping? */
- extra_pages += xen_count_remap_pages(max_pfn);
+ max_pages += xen_count_remap_pages(max_pfn);
+
+ if (max_pages > max_pfn)
+ extra_pages += max_pages - max_pfn;
/*
* Clamp the amount of extra memory to a EXTRA_MEM_RATIO
* is limited to the max size of lowmem, so that it doesn't
* get completely filled.
*
+ * Make sure we have no memory above max_pages, as this area
+ * isn't handled by the p2m management.
+ *
* 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 = min3(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
+ extra_pages, max_pages - max_pfn);
i = 0;
addr = xen_e820_map[0].addr;
size = xen_e820_map[0].size;
chunk_size = min(size, mem_end - addr);
} else if (extra_pages) {
chunk_size = min(size, PFN_PHYS(extra_pages));
- extra_pages -= PFN_DOWN(chunk_size);
- xen_add_extra_mem(addr, chunk_size);
- xen_max_p2m_pfn = PFN_DOWN(addr + chunk_size);
+ pfn_s = PFN_UP(addr);
+ n_pfns = PFN_DOWN(addr + chunk_size) - pfn_s;
+ extra_pages -= n_pfns;
+ xen_add_extra_mem(pfn_s, n_pfns);
+ xen_max_p2m_pfn = pfn_s + n_pfns;
} else
type = E820_UNUSABLE;
}
/*
* Set the rest as identity mapped, in case PCI BARs are
* located here.
- *
- * PFNs above MAX_P2M_PFN are considered identity mapped as
- * well.
*/
set_phys_range_identity(addr / PAGE_SIZE, ~0ul);
e820_add_region(xen_e820_map[i].addr, xen_e820_map[i].size,
xen_e820_map[i].type);
- xen_reserve_xen_mfnlist();
+ /* Remove p2m info, it is not needed. */
+ xen_start_info->mfn_list = 0;
+ xen_start_info->first_p2m_pfn = 0;
+ xen_start_info->nr_p2m_frames = 0;
return "Xen";
}