#include <linux/highmem.h>
#include <linux/debugfs.h>
#include <linux/bug.h>
+#include <linux/vmalloc.h>
#include <linux/module.h>
#include <linux/gfp.h>
#include <asm/mmu_context.h>
#include <asm/setup.h>
#include <asm/paravirt.h>
+#include <asm/e820.h>
#include <asm/linkage.h>
+#include <asm/page.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/hypervisor.h>
+#include <xen/xen.h>
#include <xen/page.h>
#include <xen/interface/xen.h>
#include <xen/interface/hvm/hvm_op.h>
#include <xen/interface/version.h>
+#include <xen/interface/memory.h>
#include <xen/hvc-console.h>
#include "multicalls.h"
#define MMU_UPDATE_HISTO 30
+/*
+ * Protects atomic reservation decrease/increase against concurrent increases.
+ * Also protects non-atomic updates of current_pages and driver_pages, and
+ * balloon lists.
+ */
+DEFINE_SPINLOCK(xen_reservation_lock);
+
#ifdef CONFIG_XEN_DEBUG_FS
static struct {
* large enough to allocate page table pages to allocate the rest.
* Each page can map 2MB.
*/
-static pte_t level1_ident_pgt[PTRS_PER_PTE * 4] __page_aligned_bss;
+#define LEVEL1_IDENT_ENTRIES (PTRS_PER_PTE * 4)
+static RESERVE_BRK_ARRAY(pte_t, level1_ident_pgt, LEVEL1_IDENT_ENTRIES);
#ifdef CONFIG_X86_64
/* l3 pud for userspace vsyscall mapping */
*/
#define USER_LIMIT ((STACK_TOP_MAX + PGDIR_SIZE - 1) & PGDIR_MASK)
+/*
+ * Xen leaves the responsibility for maintaining p2m mappings to the
+ * guests themselves, but it must also access and update the p2m array
+ * during suspend/resume when all the pages are reallocated.
+ *
+ * The p2m table is logically a flat array, but we implement it as a
+ * three-level tree to allow the address space to be sparse.
+ *
+ * Xen
+ * |
+ * p2m_top p2m_top_mfn
+ * / \ / \
+ * p2m_mid p2m_mid p2m_mid_mfn p2m_mid_mfn
+ * / \ / \ / /
+ * p2m p2m p2m p2m p2m p2m p2m ...
+ *
+ * The p2m_top and p2m_top_mfn levels are limited to 1 page, so the
+ * maximum representable pseudo-physical address space is:
+ * P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE pages
+ *
+ * P2M_PER_PAGE depends on the architecture, as a mfn is always
+ * unsigned long (8 bytes on 64-bit, 4 bytes on 32), leading to
+ * 512 and 1024 entries respectively.
+ */
+
+static unsigned long max_p2m_pfn __read_mostly;
-#define P2M_ENTRIES_PER_PAGE (PAGE_SIZE / sizeof(unsigned long))
-#define TOP_ENTRIES (MAX_DOMAIN_PAGES / P2M_ENTRIES_PER_PAGE)
+#define P2M_PER_PAGE (PAGE_SIZE / sizeof(unsigned long))
+#define P2M_MID_PER_PAGE (PAGE_SIZE / sizeof(unsigned long *))
+#define P2M_TOP_PER_PAGE (PAGE_SIZE / sizeof(unsigned long **))
-/* Placeholder for holes in the address space */
-static unsigned long p2m_missing[P2M_ENTRIES_PER_PAGE] __page_aligned_data =
- { [ 0 ... P2M_ENTRIES_PER_PAGE-1 ] = ~0UL };
+#define MAX_P2M_PFN (P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE)
- /* Array of pointers to pages containing p2m entries */
-static unsigned long *p2m_top[TOP_ENTRIES] __page_aligned_data =
- { [ 0 ... TOP_ENTRIES - 1] = &p2m_missing[0] };
+/* Placeholders for holes in the address space */
+static RESERVE_BRK_ARRAY(unsigned long, p2m_missing, P2M_PER_PAGE);
+static RESERVE_BRK_ARRAY(unsigned long *, p2m_mid_missing, P2M_MID_PER_PAGE);
+static RESERVE_BRK_ARRAY(unsigned long, p2m_mid_missing_mfn, P2M_MID_PER_PAGE);
-/* Arrays of p2m arrays expressed in mfns used for save/restore */
-static unsigned long p2m_top_mfn[TOP_ENTRIES] __page_aligned_bss;
+static RESERVE_BRK_ARRAY(unsigned long **, p2m_top, P2M_TOP_PER_PAGE);
+static RESERVE_BRK_ARRAY(unsigned long, p2m_top_mfn, P2M_TOP_PER_PAGE);
-static unsigned long p2m_top_mfn_list[TOP_ENTRIES / P2M_ENTRIES_PER_PAGE]
- __page_aligned_bss;
+RESERVE_BRK(p2m_mid, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
+RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
static inline unsigned p2m_top_index(unsigned long pfn)
{
- BUG_ON(pfn >= MAX_DOMAIN_PAGES);
- return pfn / P2M_ENTRIES_PER_PAGE;
+ BUG_ON(pfn >= MAX_P2M_PFN);
+ return pfn / (P2M_MID_PER_PAGE * P2M_PER_PAGE);
+}
+
+static inline unsigned p2m_mid_index(unsigned long pfn)
+{
+ return (pfn / P2M_PER_PAGE) % P2M_MID_PER_PAGE;
}
static inline unsigned p2m_index(unsigned long pfn)
{
- return pfn % P2M_ENTRIES_PER_PAGE;
+ return pfn % P2M_PER_PAGE;
+}
+
+static void p2m_top_init(unsigned long ***top)
+{
+ unsigned i;
+
+ for (i = 0; i < P2M_TOP_PER_PAGE; i++)
+ top[i] = p2m_mid_missing;
+}
+
+static void p2m_top_mfn_init(unsigned long *top)
+{
+ unsigned i;
+
+ for (i = 0; i < P2M_TOP_PER_PAGE; i++)
+ top[i] = virt_to_mfn(p2m_mid_missing_mfn);
+}
+
+static void p2m_mid_init(unsigned long **mid)
+{
+ unsigned i;
+
+ for (i = 0; i < P2M_MID_PER_PAGE; i++)
+ mid[i] = p2m_missing;
}
-/* Build the parallel p2m_top_mfn structures */
+static void p2m_mid_mfn_init(unsigned long *mid)
+{
+ unsigned i;
+
+ for (i = 0; i < P2M_MID_PER_PAGE; i++)
+ mid[i] = virt_to_mfn(p2m_missing);
+}
+
+static void p2m_init(unsigned long *p2m)
+{
+ unsigned i;
+
+ for (i = 0; i < P2M_MID_PER_PAGE; i++)
+ p2m[i] = INVALID_P2M_ENTRY;
+}
+
+/*
+ * Build the parallel p2m_top_mfn and p2m_mid_mfn structures
+ *
+ * This is called both at boot time, and after resuming from suspend:
+ * - At boot time we're called very early, and must use extend_brk()
+ * to allocate memory.
+ *
+ * - After resume we're called from within stop_machine, but the mfn
+ * tree should alreay be completely allocated.
+ */
void xen_build_mfn_list_list(void)
{
- unsigned pfn, idx;
+ unsigned pfn;
- for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_ENTRIES_PER_PAGE) {
- unsigned topidx = p2m_top_index(pfn);
+ /* Pre-initialize p2m_top_mfn to be completely missing */
+ if (p2m_top_mfn == NULL) {
+ p2m_mid_missing_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE);
+ p2m_mid_mfn_init(p2m_mid_missing_mfn);
- p2m_top_mfn[topidx] = virt_to_mfn(p2m_top[topidx]);
+ p2m_top_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE);
+ p2m_top_mfn_init(p2m_top_mfn);
}
- for (idx = 0; idx < ARRAY_SIZE(p2m_top_mfn_list); idx++) {
- unsigned topidx = idx * P2M_ENTRIES_PER_PAGE;
- p2m_top_mfn_list[idx] = virt_to_mfn(&p2m_top_mfn[topidx]);
+ for (pfn = 0; pfn < max_p2m_pfn; pfn += P2M_PER_PAGE) {
+ unsigned topidx = p2m_top_index(pfn);
+ unsigned mididx = p2m_mid_index(pfn);
+ unsigned long **mid;
+ unsigned long mid_mfn;
+ unsigned long *mid_mfn_p;
+
+ mid = p2m_top[topidx];
+
+ /* Don't bother allocating any mfn mid levels if
+ they're just missing */
+ if (mid[mididx] == p2m_missing)
+ continue;
+
+ mid_mfn = p2m_top_mfn[topidx];
+ mid_mfn_p = mfn_to_virt(mid_mfn);
+
+ if (mid_mfn_p == p2m_mid_missing_mfn) {
+ /*
+ * XXX boot-time only! We should never find
+ * missing parts of the mfn tree after
+ * runtime. extend_brk() will BUG if we call
+ * it too late.
+ */
+ mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
+ p2m_mid_mfn_init(mid_mfn_p);
+
+ mid_mfn = virt_to_mfn(mid_mfn_p);
+
+ p2m_top_mfn[topidx] = mid_mfn;
+ }
+
+ mid_mfn_p[mididx] = virt_to_mfn(mid[mididx]);
}
}
BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);
HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list =
- virt_to_mfn(p2m_top_mfn_list);
- HYPERVISOR_shared_info->arch.max_pfn = xen_start_info->nr_pages;
+ virt_to_mfn(p2m_top_mfn);
+ HYPERVISOR_shared_info->arch.max_pfn = max_p2m_pfn;
}
/* Set up p2m_top to point to the domain-builder provided p2m pages */
unsigned long max_pfn = min(MAX_DOMAIN_PAGES, xen_start_info->nr_pages);
unsigned pfn;
- for (pfn = 0; pfn < max_pfn; pfn += P2M_ENTRIES_PER_PAGE) {
+ max_p2m_pfn = max_pfn;
+
+ p2m_missing = extend_brk(PAGE_SIZE, PAGE_SIZE);
+ p2m_init(p2m_missing);
+
+ p2m_mid_missing = extend_brk(PAGE_SIZE, PAGE_SIZE);
+ p2m_mid_init(p2m_mid_missing);
+
+ p2m_top = extend_brk(PAGE_SIZE, PAGE_SIZE);
+ p2m_top_init(p2m_top);
+
+ /*
+ * The domain builder gives us a pre-constructed p2m array in
+ * mfn_list for all the pages initially given to us, so we just
+ * need to graft that into our tree structure.
+ */
+ for (pfn = 0; pfn < max_pfn; pfn += P2M_PER_PAGE) {
unsigned topidx = p2m_top_index(pfn);
+ unsigned mididx = p2m_mid_index(pfn);
- p2m_top[topidx] = &mfn_list[pfn];
- }
+ if (p2m_top[topidx] == p2m_mid_missing) {
+ unsigned long **mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
+ p2m_mid_init(mid);
- xen_build_mfn_list_list();
+ p2m_top[topidx] = mid;
+ }
+
+ p2m_top[topidx][mididx] = &mfn_list[pfn];
+ }
}
unsigned long get_phys_to_machine(unsigned long pfn)
{
- unsigned topidx, idx;
+ unsigned topidx, mididx, idx;
- if (unlikely(pfn >= MAX_DOMAIN_PAGES))
+ if (unlikely(pfn >= MAX_P2M_PFN))
return INVALID_P2M_ENTRY;
topidx = p2m_top_index(pfn);
+ mididx = p2m_mid_index(pfn);
idx = p2m_index(pfn);
- return p2m_top[topidx][idx];
+
+ return p2m_top[topidx][mididx][idx];
}
EXPORT_SYMBOL_GPL(get_phys_to_machine);
-/* install a new p2m_top page */
-bool install_p2mtop_page(unsigned long pfn, unsigned long *p)
+static void *alloc_p2m_page(void)
{
- unsigned topidx = p2m_top_index(pfn);
- unsigned long **pfnp, *mfnp;
- unsigned i;
+ return (void *)__get_free_page(GFP_KERNEL | __GFP_REPEAT);
+}
- pfnp = &p2m_top[topidx];
- mfnp = &p2m_top_mfn[topidx];
+static void free_p2m_page(void *p)
+{
+ free_page((unsigned long)p);
+}
- for (i = 0; i < P2M_ENTRIES_PER_PAGE; i++)
- p[i] = INVALID_P2M_ENTRY;
+/*
+ * Fully allocate the p2m structure for a given pfn. We need to check
+ * that both the top and mid levels are allocated, and make sure the
+ * parallel mfn tree is kept in sync. We may race with other cpus, so
+ * the new pages are installed with cmpxchg; if we lose the race then
+ * simply free the page we allocated and use the one that's there.
+ */
+static bool alloc_p2m(unsigned long pfn)
+{
+ unsigned topidx, mididx;
+ unsigned long ***top_p, **mid;
+ unsigned long *top_mfn_p, *mid_mfn;
- if (cmpxchg(pfnp, p2m_missing, p) == p2m_missing) {
- *mfnp = virt_to_mfn(p);
- return true;
+ topidx = p2m_top_index(pfn);
+ mididx = p2m_mid_index(pfn);
+
+ top_p = &p2m_top[topidx];
+ mid = *top_p;
+
+ if (mid == p2m_mid_missing) {
+ /* Mid level is missing, allocate a new one */
+ mid = alloc_p2m_page();
+ if (!mid)
+ return false;
+
+ p2m_mid_init(mid);
+
+ if (cmpxchg(top_p, p2m_mid_missing, mid) != p2m_mid_missing)
+ free_p2m_page(mid);
}
- return false;
-}
+ top_mfn_p = &p2m_top_mfn[topidx];
+ mid_mfn = mfn_to_virt(*top_mfn_p);
-static void alloc_p2m(unsigned long pfn)
-{
- unsigned long *p;
+ if (mid_mfn == p2m_mid_missing_mfn) {
+ /* Separately check the mid mfn level */
+ unsigned long missing_mfn;
+ unsigned long mid_mfn_mfn;
- p = (void *)__get_free_page(GFP_KERNEL | __GFP_NOFAIL);
- BUG_ON(p == NULL);
+ mid_mfn = alloc_p2m_page();
+ if (!mid_mfn)
+ return false;
- if (!install_p2mtop_page(pfn, p))
- free_page((unsigned long)p);
+ p2m_mid_mfn_init(mid_mfn);
+
+ missing_mfn = virt_to_mfn(p2m_mid_missing_mfn);
+ mid_mfn_mfn = virt_to_mfn(mid_mfn);
+ if (cmpxchg(top_mfn_p, missing_mfn, mid_mfn_mfn) != missing_mfn)
+ free_p2m_page(mid_mfn);
+ }
+
+ if (p2m_top[topidx][mididx] == p2m_missing) {
+ /* p2m leaf page is missing */
+ unsigned long *p2m;
+
+ p2m = alloc_p2m_page();
+ if (!p2m)
+ return false;
+
+ p2m_init(p2m);
+
+ if (cmpxchg(&mid[mididx], p2m_missing, p2m) != p2m_missing)
+ free_p2m_page(p2m);
+ else
+ mid_mfn[mididx] = virt_to_mfn(p2m);
+ }
+
+ return true;
}
/* Try to install p2m mapping; fail if intermediate bits missing */
bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
{
- unsigned topidx, idx;
+ unsigned topidx, mididx, idx;
- if (unlikely(pfn >= MAX_DOMAIN_PAGES)) {
+ if (unlikely(pfn >= MAX_P2M_PFN)) {
BUG_ON(mfn != INVALID_P2M_ENTRY);
return true;
}
topidx = p2m_top_index(pfn);
- if (p2m_top[topidx] == p2m_missing) {
- if (mfn == INVALID_P2M_ENTRY)
- return true;
- return false;
- }
-
+ mididx = p2m_mid_index(pfn);
idx = p2m_index(pfn);
- p2m_top[topidx][idx] = mfn;
+
+ if (p2m_top[topidx][mididx] == p2m_missing)
+ return mfn == INVALID_P2M_ENTRY;
+
+ p2m_top[topidx][mididx][idx] = mfn;
return true;
}
-void set_phys_to_machine(unsigned long pfn, unsigned long mfn)
+bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
{
if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) {
BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
- return;
+ return true;
}
if (unlikely(!__set_phys_to_machine(pfn, mfn))) {
- alloc_p2m(pfn);
+ if (!alloc_p2m(pfn))
+ return false;
if (!__set_phys_to_machine(pfn, mfn))
- BUG();
+ return false;
}
+
+ return true;
}
unsigned long arbitrary_virt_to_mfn(void *vaddr)
return PagePinned(page);
}
+static bool xen_iomap_pte(pte_t pte)
+{
+ return pte_flags(pte) & _PAGE_IOMAP;
+}
+
+static void xen_set_iomap_pte(pte_t *ptep, pte_t pteval)
+{
+ struct multicall_space mcs;
+ struct mmu_update *u;
+
+ mcs = xen_mc_entry(sizeof(*u));
+ u = mcs.args;
+
+ /* ptep might be kmapped when using 32-bit HIGHPTE */
+ u->ptr = arbitrary_virt_to_machine(ptep).maddr;
+ u->val = pte_val_ma(pteval);
+
+ MULTI_mmu_update(mcs.mc, mcs.args, 1, NULL, DOMID_IO);
+
+ xen_mc_issue(PARAVIRT_LAZY_MMU);
+}
+
static void xen_extend_mmu_update(const struct mmu_update *update)
{
struct multicall_space mcs;
void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pteval)
{
+ if (xen_iomap_pte(pteval)) {
+ xen_set_iomap_pte(ptep, pteval);
+ goto out;
+ }
+
ADD_STATS(set_pte_at, 1);
// ADD_STATS(set_pte_at_pinned, xen_page_pinned(ptep));
ADD_STATS(set_pte_at_current, mm == current->mm);
return val;
}
+static pteval_t iomap_pte(pteval_t val)
+{
+ if (val & _PAGE_PRESENT) {
+ unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
+ pteval_t flags = val & PTE_FLAGS_MASK;
+
+ /* We assume the pte frame number is a MFN, so
+ just use it as-is. */
+ val = ((pteval_t)pfn << PAGE_SHIFT) | flags;
+ }
+
+ return val;
+}
+
pteval_t xen_pte_val(pte_t pte)
{
+ if (xen_initial_domain() && (pte.pte & _PAGE_IOMAP))
+ return pte.pte;
+
return pte_mfn_to_pfn(pte.pte);
}
PV_CALLEE_SAVE_REGS_THUNK(xen_pte_val);
pte_t xen_make_pte(pteval_t pte)
{
- pte = pte_pfn_to_mfn(pte);
+ phys_addr_t addr = (pte & PTE_PFN_MASK);
+
+ /*
+ * Unprivileged domains are allowed to do IOMAPpings for
+ * PCI passthrough, but not map ISA space. The ISA
+ * mappings are just dummy local mappings to keep other
+ * parts of the kernel happy.
+ */
+ if (unlikely(pte & _PAGE_IOMAP) &&
+ (xen_initial_domain() || addr >= ISA_END_ADDRESS)) {
+ pte = iomap_pte(pte);
+ } else {
+ pte &= ~_PAGE_IOMAP;
+ pte = pte_pfn_to_mfn(pte);
+ }
+
return native_make_pte(pte);
}
PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte);
void xen_set_pte(pte_t *ptep, pte_t pte)
{
+ if (xen_iomap_pte(pte)) {
+ xen_set_iomap_pte(ptep, pte);
+ return;
+ }
+
ADD_STATS(pte_update, 1);
// ADD_STATS(pte_update_pinned, xen_page_pinned(ptep));
ADD_STATS(pte_update_batched, paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU);
#ifdef CONFIG_X86_PAE
void xen_set_pte_atomic(pte_t *ptep, pte_t pte)
{
+ if (xen_iomap_pte(pte)) {
+ xen_set_iomap_pte(ptep, pte);
+ return;
+ }
+
set_64bit((u64 *)ptep, native_pte_val(pte));
}
read-only, and can be pinned. */
static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd)
{
- vm_unmap_aliases();
-
xen_mc_batch();
if (__xen_pgd_walk(mm, pgd, xen_pin_page, USER_LIMIT)) {
if (PagePinned(virt_to_page(mm->pgd))) {
SetPagePinned(page);
- vm_unmap_aliases();
if (!PageHighMem(page)) {
make_lowmem_page_readonly(__va(PFN_PHYS((unsigned long)pfn)));
if (level == PT_PTE && USE_SPLIT_PTLOCKS)
unsigned ident_pte;
unsigned long pfn;
+ level1_ident_pgt = extend_brk(sizeof(pte_t) * LEVEL1_IDENT_ENTRIES,
+ PAGE_SIZE);
+
ident_pte = 0;
pfn = 0;
for (pmdidx = 0; pmdidx < PTRS_PER_PMD && pfn < max_pfn; pmdidx++) {
pte_page = m2v(pmd[pmdidx].pmd);
else {
/* Check for free pte pages */
- if (ident_pte == ARRAY_SIZE(level1_ident_pgt))
+ if (ident_pte == LEVEL1_IDENT_ENTRIES)
break;
pte_page = &level1_ident_pgt[ident_pte];
return pgd;
}
#else /* !CONFIG_X86_64 */
-static pmd_t level2_kernel_pgt[PTRS_PER_PMD] __page_aligned_bss;
+static RESERVE_BRK_ARRAY(pmd_t, level2_kernel_pgt, PTRS_PER_PMD);
__init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
unsigned long max_pfn)
{
pmd_t *kernel_pmd;
+ level2_kernel_pgt = extend_brk(sizeof(pmd_t *) * PTRS_PER_PMD, PAGE_SIZE);
+
max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) +
xen_start_info->nr_pt_frames * PAGE_SIZE +
512*1024);
pte = pfn_pte(phys, prot);
break;
- default:
+ case FIX_PARAVIRT_BOOTMAP:
+ /* This is an MFN, but it isn't an IO mapping from the
+ IO domain */
pte = mfn_pte(phys, prot);
break;
+
+ default:
+ /* By default, set_fixmap is used for hardware mappings */
+ pte = mfn_pte(phys, __pgprot(pgprot_val(prot) | _PAGE_IOMAP));
+ break;
}
__native_set_fixmap(idx, pte);
x86_init.paging.pagetable_setup_start = xen_pagetable_setup_start;
x86_init.paging.pagetable_setup_done = xen_pagetable_setup_done;
pv_mmu_ops = xen_mmu_ops;
+
+ vmap_lazy_unmap = false;
+}
+
+/* Protected by xen_reservation_lock. */
+#define MAX_CONTIG_ORDER 9 /* 2MB */
+static unsigned long discontig_frames[1<<MAX_CONTIG_ORDER];
+
+#define VOID_PTE (mfn_pte(0, __pgprot(0)))
+static void xen_zap_pfn_range(unsigned long vaddr, unsigned int order,
+ unsigned long *in_frames,
+ unsigned long *out_frames)
+{
+ int i;
+ struct multicall_space mcs;
+
+ xen_mc_batch();
+ for (i = 0; i < (1UL<<order); i++, vaddr += PAGE_SIZE) {
+ mcs = __xen_mc_entry(0);
+
+ if (in_frames)
+ in_frames[i] = virt_to_mfn(vaddr);
+
+ MULTI_update_va_mapping(mcs.mc, vaddr, VOID_PTE, 0);
+ set_phys_to_machine(virt_to_pfn(vaddr), INVALID_P2M_ENTRY);
+
+ if (out_frames)
+ out_frames[i] = virt_to_pfn(vaddr);
+ }
+ xen_mc_issue(0);
+}
+
+/*
+ * Update the pfn-to-mfn mappings for a virtual address range, either to
+ * point to an array of mfns, or contiguously from a single starting
+ * mfn.
+ */
+static void xen_remap_exchanged_ptes(unsigned long vaddr, int order,
+ unsigned long *mfns,
+ unsigned long first_mfn)
+{
+ unsigned i, limit;
+ unsigned long mfn;
+
+ xen_mc_batch();
+
+ limit = 1u << order;
+ for (i = 0; i < limit; i++, vaddr += PAGE_SIZE) {
+ struct multicall_space mcs;
+ unsigned flags;
+
+ mcs = __xen_mc_entry(0);
+ if (mfns)
+ mfn = mfns[i];
+ else
+ mfn = first_mfn + i;
+
+ if (i < (limit - 1))
+ flags = 0;
+ else {
+ if (order == 0)
+ flags = UVMF_INVLPG | UVMF_ALL;
+ else
+ flags = UVMF_TLB_FLUSH | UVMF_ALL;
+ }
+
+ MULTI_update_va_mapping(mcs.mc, vaddr,
+ mfn_pte(mfn, PAGE_KERNEL), flags);
+
+ set_phys_to_machine(virt_to_pfn(vaddr), mfn);
+ }
+
+ xen_mc_issue(0);
+}
+
+/*
+ * Perform the hypercall to exchange a region of our pfns to point to
+ * memory with the required contiguous alignment. Takes the pfns as
+ * input, and populates mfns as output.
+ *
+ * Returns a success code indicating whether the hypervisor was able to
+ * satisfy the request or not.
+ */
+static int xen_exchange_memory(unsigned long extents_in, unsigned int order_in,
+ unsigned long *pfns_in,
+ unsigned long extents_out,
+ unsigned int order_out,
+ unsigned long *mfns_out,
+ unsigned int address_bits)
+{
+ long rc;
+ int success;
+
+ struct xen_memory_exchange exchange = {
+ .in = {
+ .nr_extents = extents_in,
+ .extent_order = order_in,
+ .extent_start = pfns_in,
+ .domid = DOMID_SELF
+ },
+ .out = {
+ .nr_extents = extents_out,
+ .extent_order = order_out,
+ .extent_start = mfns_out,
+ .address_bits = address_bits,
+ .domid = DOMID_SELF
+ }
+ };
+
+ BUG_ON(extents_in << order_in != extents_out << order_out);
+
+ rc = HYPERVISOR_memory_op(XENMEM_exchange, &exchange);
+ success = (exchange.nr_exchanged == extents_in);
+
+ BUG_ON(!success && ((exchange.nr_exchanged != 0) || (rc == 0)));
+ BUG_ON(success && (rc != 0));
+
+ return success;
+}
+
+int xen_create_contiguous_region(unsigned long vstart, unsigned int order,
+ unsigned int address_bits)
+{
+ unsigned long *in_frames = discontig_frames, out_frame;
+ unsigned long flags;
+ int success;
+
+ /*
+ * Currently an auto-translated guest will not perform I/O, nor will
+ * it require PAE page directories below 4GB. Therefore any calls to
+ * this function are redundant and can be ignored.
+ */
+
+ if (xen_feature(XENFEAT_auto_translated_physmap))
+ return 0;
+
+ if (unlikely(order > MAX_CONTIG_ORDER))
+ return -ENOMEM;
+
+ memset((void *) vstart, 0, PAGE_SIZE << order);
+
+ spin_lock_irqsave(&xen_reservation_lock, flags);
+
+ /* 1. Zap current PTEs, remembering MFNs. */
+ xen_zap_pfn_range(vstart, order, in_frames, NULL);
+
+ /* 2. Get a new contiguous memory extent. */
+ out_frame = virt_to_pfn(vstart);
+ success = xen_exchange_memory(1UL << order, 0, in_frames,
+ 1, order, &out_frame,
+ address_bits);
+
+ /* 3. Map the new extent in place of old pages. */
+ if (success)
+ xen_remap_exchanged_ptes(vstart, order, NULL, out_frame);
+ else
+ xen_remap_exchanged_ptes(vstart, order, in_frames, 0);
+
+ spin_unlock_irqrestore(&xen_reservation_lock, flags);
+
+ return success ? 0 : -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(xen_create_contiguous_region);
+
+void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order)
+{
+ unsigned long *out_frames = discontig_frames, in_frame;
+ unsigned long flags;
+ int success;
+
+ if (xen_feature(XENFEAT_auto_translated_physmap))
+ return;
+
+ if (unlikely(order > MAX_CONTIG_ORDER))
+ return;
+
+ memset((void *) vstart, 0, PAGE_SIZE << order);
+
+ spin_lock_irqsave(&xen_reservation_lock, flags);
+
+ /* 1. Find start MFN of contiguous extent. */
+ in_frame = virt_to_mfn(vstart);
+
+ /* 2. Zap current PTEs. */
+ xen_zap_pfn_range(vstart, order, NULL, out_frames);
+
+ /* 3. Do the exchange for non-contiguous MFNs. */
+ success = xen_exchange_memory(1, order, &in_frame, 1UL << order,
+ 0, out_frames, 0);
+
+ /* 4. Map new pages in place of old pages. */
+ if (success)
+ xen_remap_exchanged_ptes(vstart, order, out_frames, 0);
+ else
+ xen_remap_exchanged_ptes(vstart, order, NULL, in_frame);
+
+ spin_unlock_irqrestore(&xen_reservation_lock, flags);
}
+EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region);
#ifdef CONFIG_XEN_PVHVM
static void xen_hvm_exit_mmap(struct mm_struct *mm)
projects / deliverable / linux.git / blobdiff