#include <linux/gfp.h>
#include <linux/memblock.h>
#include <linux/seq_file.h>
+#include <linux/crash_dump.h>
+
+#include <trace/events/xen.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/page.h>
#include <asm/init.h>
#include <asm/pat.h>
+#include <asm/smp.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/hypervisor.h>
#include "mmu.h"
#include "debugfs.h"
-#define MMU_UPDATE_HISTO 30
-
/*
* Protects atomic reservation decrease/increase against concurrent increases.
* Also protects non-atomic updates of current_pages and balloon lists.
*/
DEFINE_SPINLOCK(xen_reservation_lock);
-#ifdef CONFIG_XEN_DEBUG_FS
-
-static struct {
- u32 pgd_update;
- u32 pgd_update_pinned;
- u32 pgd_update_batched;
-
- u32 pud_update;
- u32 pud_update_pinned;
- u32 pud_update_batched;
-
- u32 pmd_update;
- u32 pmd_update_pinned;
- u32 pmd_update_batched;
-
- u32 pte_update;
- u32 pte_update_pinned;
- u32 pte_update_batched;
-
- u32 mmu_update;
- u32 mmu_update_extended;
- u32 mmu_update_histo[MMU_UPDATE_HISTO];
-
- u32 prot_commit;
- u32 prot_commit_batched;
-
- u32 set_pte_at;
- u32 set_pte_at_batched;
- u32 set_pte_at_pinned;
- u32 set_pte_at_current;
- u32 set_pte_at_kernel;
-} mmu_stats;
-
-static u8 zero_stats;
-
-static inline void check_zero(void)
-{
- if (unlikely(zero_stats)) {
- memset(&mmu_stats, 0, sizeof(mmu_stats));
- zero_stats = 0;
- }
-}
-
-#define ADD_STATS(elem, val) \
- do { check_zero(); mmu_stats.elem += (val); } while(0)
-
-#else /* !CONFIG_XEN_DEBUG_FS */
-
-#define ADD_STATS(elem, val) do { (void)(val); } while(0)
-
-#endif /* CONFIG_XEN_DEBUG_FS */
-
-
+#ifdef CONFIG_X86_32
/*
* Identity map, in addition to plain kernel map. This needs to be
* large enough to allocate page table pages to allocate the rest.
*/
#define LEVEL1_IDENT_ENTRIES (PTRS_PER_PTE * 4)
static RESERVE_BRK_ARRAY(pte_t, level1_ident_pgt, LEVEL1_IDENT_ENTRIES);
-
+#endif
#ifdef CONFIG_X86_64
/* l3 pud for userspace vsyscall mapping */
static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss;
return PagePinned(page);
}
-static bool xen_iomap_pte(pte_t pte)
-{
- return pte_flags(pte) & _PAGE_IOMAP;
-}
-
void xen_set_domain_pte(pte_t *ptep, pte_t pteval, unsigned domid)
{
struct multicall_space mcs;
struct mmu_update *u;
+ trace_xen_mmu_set_domain_pte(ptep, pteval, domid);
+
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->ptr = virt_to_machine(ptep).maddr;
u->val = pte_val_ma(pteval);
MULTI_mmu_update(mcs.mc, mcs.args, 1, NULL, domid);
}
EXPORT_SYMBOL_GPL(xen_set_domain_pte);
-static void xen_set_iomap_pte(pte_t *ptep, pte_t pteval)
-{
- xen_set_domain_pte(ptep, pteval, DOMID_IO);
-}
-
static void xen_extend_mmu_update(const struct mmu_update *update)
{
struct multicall_space mcs;
mcs = xen_mc_extend_args(__HYPERVISOR_mmu_update, sizeof(*u));
if (mcs.mc != NULL) {
- ADD_STATS(mmu_update_extended, 1);
- ADD_STATS(mmu_update_histo[mcs.mc->args[1]], -1);
-
mcs.mc->args[1]++;
-
- if (mcs.mc->args[1] < MMU_UPDATE_HISTO)
- ADD_STATS(mmu_update_histo[mcs.mc->args[1]], 1);
- else
- ADD_STATS(mmu_update_histo[0], 1);
} else {
- ADD_STATS(mmu_update, 1);
mcs = __xen_mc_entry(sizeof(*u));
MULTI_mmu_update(mcs.mc, mcs.args, 1, NULL, DOMID_SELF);
- ADD_STATS(mmu_update_histo[1], 1);
}
u = mcs.args;
*u = *update;
}
-void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val)
+static void xen_extend_mmuext_op(const struct mmuext_op *op)
+{
+ struct multicall_space mcs;
+ struct mmuext_op *u;
+
+ mcs = xen_mc_extend_args(__HYPERVISOR_mmuext_op, sizeof(*u));
+
+ if (mcs.mc != NULL) {
+ mcs.mc->args[1]++;
+ } else {
+ mcs = __xen_mc_entry(sizeof(*u));
+ MULTI_mmuext_op(mcs.mc, mcs.args, 1, NULL, DOMID_SELF);
+ }
+
+ u = mcs.args;
+ *u = *op;
+}
+
+static void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val)
{
struct mmu_update u;
u.val = pmd_val_ma(val);
xen_extend_mmu_update(&u);
- ADD_STATS(pmd_update_batched, paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU);
-
xen_mc_issue(PARAVIRT_LAZY_MMU);
preempt_enable();
}
-void xen_set_pmd(pmd_t *ptr, pmd_t val)
+static void xen_set_pmd(pmd_t *ptr, pmd_t val)
{
- ADD_STATS(pmd_update, 1);
+ trace_xen_mmu_set_pmd(ptr, val);
/* If page is not pinned, we can just update the entry
directly */
return;
}
- ADD_STATS(pmd_update_pinned, 1);
-
xen_set_pmd_hyper(ptr, val);
}
set_pte_vaddr(vaddr, mfn_pte(mfn, flags));
}
-void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t pteval)
+static bool xen_batched_set_pte(pte_t *ptep, pte_t pteval)
{
- if (xen_iomap_pte(pteval)) {
- xen_set_iomap_pte(ptep, pteval);
- goto out;
- }
+ struct mmu_update u;
- 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);
- ADD_STATS(set_pte_at_kernel, mm == &init_mm);
+ if (paravirt_get_lazy_mode() != PARAVIRT_LAZY_MMU)
+ return false;
- if (mm == current->mm || mm == &init_mm) {
- if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
- struct multicall_space mcs;
- mcs = xen_mc_entry(0);
+ xen_mc_batch();
- MULTI_update_va_mapping(mcs.mc, addr, pteval, 0);
- ADD_STATS(set_pte_at_batched, 1);
- xen_mc_issue(PARAVIRT_LAZY_MMU);
- goto out;
- } else
- if (HYPERVISOR_update_va_mapping(addr, pteval, 0) == 0)
- goto out;
+ u.ptr = virt_to_machine(ptep).maddr | MMU_NORMAL_PT_UPDATE;
+ u.val = pte_val_ma(pteval);
+ xen_extend_mmu_update(&u);
+
+ xen_mc_issue(PARAVIRT_LAZY_MMU);
+
+ return true;
+}
+
+static inline void __xen_set_pte(pte_t *ptep, pte_t pteval)
+{
+ if (!xen_batched_set_pte(ptep, pteval)) {
+ /*
+ * Could call native_set_pte() here and trap and
+ * emulate the PTE write but with 32-bit guests this
+ * needs two traps (one for each of the two 32-bit
+ * words in the PTE) so do one hypercall directly
+ * instead.
+ */
+ struct mmu_update u;
+
+ u.ptr = virt_to_machine(ptep).maddr | MMU_NORMAL_PT_UPDATE;
+ u.val = pte_val_ma(pteval);
+ HYPERVISOR_mmu_update(&u, 1, NULL, DOMID_SELF);
}
- xen_set_pte(ptep, pteval);
+}
-out: return;
+static void xen_set_pte(pte_t *ptep, pte_t pteval)
+{
+ trace_xen_mmu_set_pte(ptep, pteval);
+ __xen_set_pte(ptep, pteval);
+}
+
+static void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pteval)
+{
+ trace_xen_mmu_set_pte_at(mm, addr, ptep, pteval);
+ __xen_set_pte(ptep, pteval);
}
pte_t xen_ptep_modify_prot_start(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
/* Just return the pte as-is. We preserve the bits on commit */
+ trace_xen_mmu_ptep_modify_prot_start(mm, addr, ptep, *ptep);
return *ptep;
}
{
struct mmu_update u;
+ trace_xen_mmu_ptep_modify_prot_commit(mm, addr, ptep, pte);
xen_mc_batch();
- u.ptr = arbitrary_virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD;
+ u.ptr = virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD;
u.val = pte_val_ma(pte);
xen_extend_mmu_update(&u);
- ADD_STATS(prot_commit, 1);
- ADD_STATS(prot_commit_batched, paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU);
-
xen_mc_issue(PARAVIRT_LAZY_MMU);
}
{
if (val & _PAGE_PRESENT) {
unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
+ unsigned long pfn = mfn_to_pfn(mfn);
+
pteval_t flags = val & PTE_FLAGS_MASK;
- val = ((pteval_t)mfn_to_pfn(mfn) << PAGE_SHIFT) | flags;
+ if (unlikely(pfn == ~0))
+ val = flags & ~_PAGE_PRESENT;
+ else
+ val = ((pteval_t)pfn << PAGE_SHIFT) | flags;
}
return val;
return val;
}
-pteval_t xen_pte_val(pte_t pte)
+static pteval_t xen_pte_val(pte_t pte)
{
pteval_t pteval = pte.pte;
-
+#if 0
/* If this is a WC pte, convert back from Xen WC to Linux WC */
if ((pteval & (_PAGE_PAT | _PAGE_PCD | _PAGE_PWT)) == _PAGE_PAT) {
WARN_ON(!pat_enabled);
pteval = (pteval & ~_PAGE_PAT) | _PAGE_PWT;
}
-
+#endif
if (xen_initial_domain() && (pteval & _PAGE_IOMAP))
return pteval;
}
PV_CALLEE_SAVE_REGS_THUNK(xen_pte_val);
-pgdval_t xen_pgd_val(pgd_t pgd)
+static pgdval_t xen_pgd_val(pgd_t pgd)
{
return pte_mfn_to_pfn(pgd.pgd);
}
WARN_ON(pat != 0x0007010600070106ull);
}
-pte_t xen_make_pte(pteval_t pte)
+static pte_t xen_make_pte(pteval_t pte)
{
phys_addr_t addr = (pte & PTE_PFN_MASK);
-
+#if 0
/* If Linux is trying to set a WC pte, then map to the Xen WC.
* If _PAGE_PAT is set, then it probably means it is really
* _PAGE_PSE, so avoid fiddling with the PAT mapping and hope
if ((pte & (_PAGE_PCD | _PAGE_PWT)) == _PAGE_PWT)
pte = (pte & ~(_PAGE_PCD | _PAGE_PWT)) | _PAGE_PAT;
}
-
+#endif
/*
* Unprivileged domains are allowed to do IOMAPpings for
* PCI passthrough, but not map ISA space. The ISA
}
PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte);
-#ifdef CONFIG_XEN_DEBUG
-pte_t xen_make_pte_debug(pteval_t pte)
-{
- phys_addr_t addr = (pte & PTE_PFN_MASK);
- phys_addr_t other_addr;
- bool io_page = false;
- pte_t _pte;
-
- if (pte & _PAGE_IOMAP)
- io_page = true;
-
- _pte = xen_make_pte(pte);
-
- if (!addr)
- return _pte;
-
- if (io_page &&
- (xen_initial_domain() || addr >= ISA_END_ADDRESS)) {
- other_addr = pfn_to_mfn(addr >> PAGE_SHIFT) << PAGE_SHIFT;
- WARN_ONCE(addr != other_addr,
- "0x%lx is using VM_IO, but it is 0x%lx!\n",
- (unsigned long)addr, (unsigned long)other_addr);
- } else {
- pteval_t iomap_set = (_pte.pte & PTE_FLAGS_MASK) & _PAGE_IOMAP;
- other_addr = (_pte.pte & PTE_PFN_MASK);
- WARN_ONCE((addr == other_addr) && (!io_page) && (!iomap_set),
- "0x%lx is missing VM_IO (and wasn't fixed)!\n",
- (unsigned long)addr);
- }
-
- return _pte;
-}
-PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_debug);
-#endif
-
-pgd_t xen_make_pgd(pgdval_t pgd)
+static pgd_t xen_make_pgd(pgdval_t pgd)
{
pgd = pte_pfn_to_mfn(pgd);
return native_make_pgd(pgd);
}
PV_CALLEE_SAVE_REGS_THUNK(xen_make_pgd);
-pmdval_t xen_pmd_val(pmd_t pmd)
+static pmdval_t xen_pmd_val(pmd_t pmd)
{
return pte_mfn_to_pfn(pmd.pmd);
}
PV_CALLEE_SAVE_REGS_THUNK(xen_pmd_val);
-void xen_set_pud_hyper(pud_t *ptr, pud_t val)
+static void xen_set_pud_hyper(pud_t *ptr, pud_t val)
{
struct mmu_update u;
u.val = pud_val_ma(val);
xen_extend_mmu_update(&u);
- ADD_STATS(pud_update_batched, paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU);
-
xen_mc_issue(PARAVIRT_LAZY_MMU);
preempt_enable();
}
-void xen_set_pud(pud_t *ptr, pud_t val)
+static void xen_set_pud(pud_t *ptr, pud_t val)
{
- ADD_STATS(pud_update, 1);
+ trace_xen_mmu_set_pud(ptr, val);
/* If page is not pinned, we can just update the entry
directly */
return;
}
- ADD_STATS(pud_update_pinned, 1);
-
xen_set_pud_hyper(ptr, val);
}
-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
- ptep->pte_high = pte.pte_high;
- smp_wmb();
- ptep->pte_low = pte.pte_low;
-#else
- *ptep = pte;
-#endif
-}
-
#ifdef CONFIG_X86_PAE
-void xen_set_pte_atomic(pte_t *ptep, pte_t pte)
+static void xen_set_pte_atomic(pte_t *ptep, pte_t pte)
{
- if (xen_iomap_pte(pte)) {
- xen_set_iomap_pte(ptep, pte);
- return;
- }
-
+ trace_xen_mmu_set_pte_atomic(ptep, pte);
set_64bit((u64 *)ptep, native_pte_val(pte));
}
-void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+static void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
{
- ptep->pte_low = 0;
- smp_wmb(); /* make sure low gets written first */
- ptep->pte_high = 0;
+ trace_xen_mmu_pte_clear(mm, addr, ptep);
+ if (!xen_batched_set_pte(ptep, native_make_pte(0)))
+ native_pte_clear(mm, addr, ptep);
}
-void xen_pmd_clear(pmd_t *pmdp)
+static void xen_pmd_clear(pmd_t *pmdp)
{
+ trace_xen_mmu_pmd_clear(pmdp);
set_pmd(pmdp, __pmd(0));
}
#endif /* CONFIG_X86_PAE */
-pmd_t xen_make_pmd(pmdval_t pmd)
+static pmd_t xen_make_pmd(pmdval_t pmd)
{
pmd = pte_pfn_to_mfn(pmd);
return native_make_pmd(pmd);
PV_CALLEE_SAVE_REGS_THUNK(xen_make_pmd);
#if PAGETABLE_LEVELS == 4
-pudval_t xen_pud_val(pud_t pud)
+static pudval_t xen_pud_val(pud_t pud)
{
return pte_mfn_to_pfn(pud.pud);
}
PV_CALLEE_SAVE_REGS_THUNK(xen_pud_val);
-pud_t xen_make_pud(pudval_t pud)
+static pud_t xen_make_pud(pudval_t pud)
{
pud = pte_pfn_to_mfn(pud);
}
PV_CALLEE_SAVE_REGS_THUNK(xen_make_pud);
-pgd_t *xen_get_user_pgd(pgd_t *pgd)
+static pgd_t *xen_get_user_pgd(pgd_t *pgd)
{
pgd_t *pgd_page = (pgd_t *)(((unsigned long)pgd) & PAGE_MASK);
unsigned offset = pgd - pgd_page;
* 2. It is always pinned
* 3. It has no user pagetable attached to it
*/
-void __init xen_set_pgd_hyper(pgd_t *ptr, pgd_t val)
+static void __init xen_set_pgd_hyper(pgd_t *ptr, pgd_t val)
{
preempt_disable();
preempt_enable();
}
-void xen_set_pgd(pgd_t *ptr, pgd_t val)
+static void xen_set_pgd(pgd_t *ptr, pgd_t val)
{
pgd_t *user_ptr = xen_get_user_pgd(ptr);
- ADD_STATS(pgd_update, 1);
+ trace_xen_mmu_set_pgd(ptr, user_ptr, val);
/* If page is not pinned, we can just update the entry
directly */
return;
}
- ADD_STATS(pgd_update_pinned, 1);
- ADD_STATS(pgd_update_batched, paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU);
-
/* If it's pinned, then we can at least batch the kernel and
user updates together. */
xen_mc_batch();
static void xen_do_pin(unsigned level, unsigned long pfn)
{
- struct mmuext_op *op;
- struct multicall_space mcs;
+ struct mmuext_op op;
- mcs = __xen_mc_entry(sizeof(*op));
- op = mcs.args;
- op->cmd = level;
- op->arg1.mfn = pfn_to_mfn(pfn);
- MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+ op.cmd = level;
+ op.arg1.mfn = pfn_to_mfn(pfn);
+
+ xen_extend_mmuext_op(&op);
}
static int xen_pin_page(struct mm_struct *mm, struct page *page,
read-only, and can be pinned. */
static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd)
{
+ trace_xen_mmu_pgd_pin(mm, pgd);
+
xen_mc_batch();
if (__xen_pgd_walk(mm, pgd, xen_pin_page, USER_LIMIT)) {
/* Release a pagetables pages back as normal RW */
static void __xen_pgd_unpin(struct mm_struct *mm, pgd_t *pgd)
{
+ trace_xen_mmu_pgd_unpin(mm, pgd);
+
xen_mc_batch();
xen_do_pin(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
spin_unlock(&pgd_lock);
}
-void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next)
+static void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next)
{
spin_lock(&next->page_table_lock);
xen_pgd_pin(next);
spin_unlock(&next->page_table_lock);
}
-void xen_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
+static void xen_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
{
spin_lock(&mm->page_table_lock);
xen_pgd_pin(mm);
struct mm_struct *mm = info;
struct mm_struct *active_mm;
- active_mm = percpu_read(cpu_tlbstate.active_mm);
+ active_mm = this_cpu_read(cpu_tlbstate.active_mm);
- if (active_mm == mm)
+ if (active_mm == mm && this_cpu_read(cpu_tlbstate.state) != TLBSTATE_OK)
leave_mm(smp_processor_id());
/* If this cpu still has a stale cr3 reference, then make sure
it has been flushed. */
- if (percpu_read(xen_current_cr3) == __pa(mm->pgd))
+ if (this_cpu_read(xen_current_cr3) == __pa(mm->pgd))
load_cr3(swapper_pg_dir);
}
* pagetable because of lazy tlb flushing. This means we need need to
* switch all CPUs off this pagetable before we can unpin it.
*/
-void xen_exit_mmap(struct mm_struct *mm)
+static void xen_exit_mmap(struct mm_struct *mm)
{
get_cpu(); /* make sure we don't move around */
xen_drop_mm_ref(mm);
spin_unlock(&mm->page_table_lock);
}
-static void __init xen_pagetable_setup_start(pgd_t *base)
-{
-}
+static void xen_post_allocator_init(void);
-static __init void xen_mapping_pagetable_reserve(u64 start, u64 end)
+#ifdef CONFIG_X86_64
+static void __init xen_cleanhighmap(unsigned long vaddr,
+ unsigned long vaddr_end)
{
- /* reserve the range used */
- native_pagetable_reserve(start, end);
+ unsigned long kernel_end = roundup((unsigned long)_brk_end, PMD_SIZE) - 1;
+ pmd_t *pmd = level2_kernel_pgt + pmd_index(vaddr);
- /* set as RW the rest */
- printk(KERN_DEBUG "xen: setting RW the range %llx - %llx\n", end,
- PFN_PHYS(pgt_buf_top));
- while (end < PFN_PHYS(pgt_buf_top)) {
- make_lowmem_page_readwrite(__va(end));
- end += PAGE_SIZE;
+ /* NOTE: The loop is more greedy than the cleanup_highmap variant.
+ * We include the PMD passed in on _both_ boundaries. */
+ for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PAGE_SIZE));
+ pmd++, vaddr += PMD_SIZE) {
+ if (pmd_none(*pmd))
+ continue;
+ if (vaddr < (unsigned long) _text || vaddr > kernel_end)
+ set_pmd(pmd, __pmd(0));
}
+ /* In case we did something silly, we should crash in this function
+ * instead of somewhere later and be confusing. */
+ xen_mc_flush();
}
-
-static void xen_post_allocator_init(void);
-
-static void __init xen_pagetable_setup_done(pgd_t *base)
+#endif
+static void __init xen_pagetable_init(void)
{
+#ifdef CONFIG_X86_64
+ unsigned long size;
+ unsigned long addr;
+#endif
+ paging_init();
xen_setup_shared_info();
+#ifdef CONFIG_X86_64
+ if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+ unsigned long new_mfn_list;
+
+ size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
+
+ /* On 32-bit, we get zero so this never gets executed. */
+ new_mfn_list = xen_revector_p2m_tree();
+ if (new_mfn_list && new_mfn_list != xen_start_info->mfn_list) {
+ /* using __ka address and sticking INVALID_P2M_ENTRY! */
+ memset((void *)xen_start_info->mfn_list, 0xff, size);
+
+ /* We should be in __ka space. */
+ BUG_ON(xen_start_info->mfn_list < __START_KERNEL_map);
+ addr = xen_start_info->mfn_list;
+ /* We roundup to the PMD, which means that if anybody at this stage is
+ * using the __ka address of xen_start_info or xen_start_info->shared_info
+ * they are in going to crash. Fortunatly we have already revectored
+ * in xen_setup_kernel_pagetable and in xen_setup_shared_info. */
+ size = roundup(size, PMD_SIZE);
+ xen_cleanhighmap(addr, addr + size);
+
+ size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
+ memblock_free(__pa(xen_start_info->mfn_list), size);
+ /* And revector! Bye bye old array */
+ xen_start_info->mfn_list = new_mfn_list;
+ } else
+ goto skip;
+ }
+ /* At this stage, cleanup_highmap has already cleaned __ka space
+ * from _brk_limit way up to the max_pfn_mapped (which is the end of
+ * the ramdisk). We continue on, erasing PMD entries that point to page
+ * tables - do note that they are accessible at this stage via __va.
+ * For good measure we also round up to the PMD - which means that if
+ * anybody is using __ka address to the initial boot-stack - and try
+ * to use it - they are going to crash. The xen_start_info has been
+ * taken care of already in xen_setup_kernel_pagetable. */
+ addr = xen_start_info->pt_base;
+ size = roundup(xen_start_info->nr_pt_frames * PAGE_SIZE, PMD_SIZE);
+
+ xen_cleanhighmap(addr, addr + size);
+ xen_start_info->pt_base = (unsigned long)__va(__pa(xen_start_info->pt_base));
+#ifdef DEBUG
+ /* This is superflous and is not neccessary, but you know what
+ * lets do it. The MODULES_VADDR -> MODULES_END should be clear of
+ * anything at this stage. */
+ xen_cleanhighmap(MODULES_VADDR, roundup(MODULES_VADDR, PUD_SIZE) - 1);
+#endif
+skip:
+#endif
xen_post_allocator_init();
}
-
static void xen_write_cr2(unsigned long cr2)
{
- percpu_read(xen_vcpu)->arch.cr2 = cr2;
+ this_cpu_read(xen_vcpu)->arch.cr2 = cr2;
}
static unsigned long xen_read_cr2(void)
{
- return percpu_read(xen_vcpu)->arch.cr2;
+ return this_cpu_read(xen_vcpu)->arch.cr2;
}
unsigned long xen_read_cr2_direct(void)
{
- return percpu_read(xen_vcpu_info.arch.cr2);
+ return this_cpu_read(xen_vcpu_info.arch.cr2);
}
+void xen_flush_tlb_all(void)
+{
+ struct mmuext_op *op;
+ struct multicall_space mcs;
+
+ trace_xen_mmu_flush_tlb_all(0);
+
+ preempt_disable();
+
+ mcs = xen_mc_entry(sizeof(*op));
+
+ op = mcs.args;
+ op->cmd = MMUEXT_TLB_FLUSH_ALL;
+ MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+
+ xen_mc_issue(PARAVIRT_LAZY_MMU);
+
+ preempt_enable();
+}
static void xen_flush_tlb(void)
{
struct mmuext_op *op;
struct multicall_space mcs;
+ trace_xen_mmu_flush_tlb(0);
+
preempt_disable();
mcs = xen_mc_entry(sizeof(*op));
struct mmuext_op *op;
struct multicall_space mcs;
+ trace_xen_mmu_flush_tlb_single(addr);
+
preempt_disable();
mcs = xen_mc_entry(sizeof(*op));
}
static void xen_flush_tlb_others(const struct cpumask *cpus,
- struct mm_struct *mm, unsigned long va)
+ struct mm_struct *mm, unsigned long start,
+ unsigned long end)
{
struct {
struct mmuext_op op;
+#ifdef CONFIG_SMP
+ DECLARE_BITMAP(mask, num_processors);
+#else
DECLARE_BITMAP(mask, NR_CPUS);
+#endif
} *args;
struct multicall_space mcs;
+ trace_xen_mmu_flush_tlb_others(cpus, mm, start, end);
+
if (cpumask_empty(cpus))
return; /* nothing to do */
cpumask_and(to_cpumask(args->mask), cpus, cpu_online_mask);
cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask));
- if (va == TLB_FLUSH_ALL) {
- args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
- } else {
+ args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
+ if (end != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) {
args->op.cmd = MMUEXT_INVLPG_MULTI;
- args->op.arg1.linear_addr = va;
+ args->op.arg1.linear_addr = start;
}
MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF);
static unsigned long xen_read_cr3(void)
{
- return percpu_read(xen_cr3);
+ return this_cpu_read(xen_cr3);
}
static void set_current_cr3(void *v)
{
- percpu_write(xen_current_cr3, (unsigned long)v);
+ this_cpu_write(xen_current_cr3, (unsigned long)v);
}
static void __xen_write_cr3(bool kernel, unsigned long cr3)
{
- struct mmuext_op *op;
- struct multicall_space mcs;
+ struct mmuext_op op;
unsigned long mfn;
+ trace_xen_mmu_write_cr3(kernel, cr3);
+
if (cr3)
mfn = pfn_to_mfn(PFN_DOWN(cr3));
else
WARN_ON(mfn == 0 && kernel);
- mcs = __xen_mc_entry(sizeof(*op));
+ op.cmd = kernel ? MMUEXT_NEW_BASEPTR : MMUEXT_NEW_USER_BASEPTR;
+ op.arg1.mfn = mfn;
- op = mcs.args;
- op->cmd = kernel ? MMUEXT_NEW_BASEPTR : MMUEXT_NEW_USER_BASEPTR;
- op->arg1.mfn = mfn;
-
- MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+ xen_extend_mmuext_op(&op);
if (kernel) {
- percpu_write(xen_cr3, cr3);
+ this_cpu_write(xen_cr3, cr3);
/* Update xen_current_cr3 once the batch has actually
been submitted. */
xen_mc_callback(set_current_cr3, (void *)cr3);
}
}
-
static void xen_write_cr3(unsigned long cr3)
{
BUG_ON(preemptible());
/* Update while interrupts are disabled, so its atomic with
respect to ipis */
- percpu_write(xen_cr3, cr3);
+ this_cpu_write(xen_cr3, cr3);
__xen_write_cr3(true, cr3);
xen_mc_issue(PARAVIRT_LAZY_CPU); /* interrupts restored */
}
+#ifdef CONFIG_X86_64
+/*
+ * At the start of the day - when Xen launches a guest, it has already
+ * built pagetables for the guest. We diligently look over them
+ * in xen_setup_kernel_pagetable and graft as appropiate them in the
+ * init_level4_pgt and its friends. Then when we are happy we load
+ * the new init_level4_pgt - and continue on.
+ *
+ * The generic code starts (start_kernel) and 'init_mem_mapping' sets
+ * up the rest of the pagetables. When it has completed it loads the cr3.
+ * N.B. that baremetal would start at 'start_kernel' (and the early
+ * #PF handler would create bootstrap pagetables) - so we are running
+ * with the same assumptions as what to do when write_cr3 is executed
+ * at this point.
+ *
+ * Since there are no user-page tables at all, we have two variants
+ * of xen_write_cr3 - the early bootup (this one), and the late one
+ * (xen_write_cr3). The reason we have to do that is that in 64-bit
+ * the Linux kernel and user-space are both in ring 3 while the
+ * hypervisor is in ring 0.
+ */
+static void __init xen_write_cr3_init(unsigned long cr3)
+{
+ BUG_ON(preemptible());
+
+ xen_mc_batch(); /* disables interrupts */
+
+ /* Update while interrupts are disabled, so its atomic with
+ respect to ipis */
+ this_cpu_write(xen_cr3, cr3);
+
+ __xen_write_cr3(true, cr3);
+
+ xen_mc_issue(PARAVIRT_LAZY_CPU); /* interrupts restored */
+}
+#endif
+
static int xen_pgd_alloc(struct mm_struct *mm)
{
pgd_t *pgd = mm->pgd;
#else /* CONFIG_X86_64 */
static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
{
- unsigned long pfn = pte_pfn(pte);
-
- /*
- * If the new pfn is within the range of the newly allocated
- * kernel pagetable, and it isn't being mapped into an
- * early_ioremap fixmap slot as a freshly allocated page, make sure
- * it is RO.
- */
- if (((!is_early_ioremap_ptep(ptep) &&
- pfn >= pgt_buf_start && pfn < pgt_buf_top)) ||
- (is_early_ioremap_ptep(ptep) && pfn != (pgt_buf_end - 1)))
- pte = pte_wrprotect(pte);
-
return pte;
}
#endif /* CONFIG_X86_64 */
-/* Init-time set_pte while constructing initial pagetables, which
- doesn't allow RO pagetable pages to be remapped RW */
+/*
+ * Init-time set_pte while constructing initial pagetables, which
+ * doesn't allow RO page table pages to be remapped RW.
+ *
+ * If there is no MFN for this PFN then this page is initially
+ * ballooned out so clear the PTE (as in decrease_reservation() in
+ * drivers/xen/balloon.c).
+ *
+ * Many of these PTE updates are done on unpinned and writable pages
+ * and doing a hypercall for these is unnecessary and expensive. At
+ * this point it is not possible to tell if a page is pinned or not,
+ * so always write the PTE directly and rely on Xen trapping and
+ * emulating any updates as necessary.
+ */
static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
{
- pte = mask_rw_pte(ptep, pte);
+ if (pte_mfn(pte) != INVALID_P2M_ENTRY)
+ pte = mask_rw_pte(ptep, pte);
+ else
+ pte = __pte_ma(0);
- xen_set_pte(ptep, pte);
+ native_set_pte(ptep, pte);
}
static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
}
+static inline void __pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
+{
+ struct multicall_space mcs;
+ struct mmuext_op *op;
+
+ mcs = __xen_mc_entry(sizeof(*op));
+ op = mcs.args;
+ op->cmd = cmd;
+ op->arg1.mfn = pfn_to_mfn(pfn);
+
+ MULTI_mmuext_op(mcs.mc, mcs.args, 1, NULL, DOMID_SELF);
+}
+
+static inline void __set_pfn_prot(unsigned long pfn, pgprot_t prot)
+{
+ struct multicall_space mcs;
+ unsigned long addr = (unsigned long)__va(pfn << PAGE_SHIFT);
+
+ mcs = __xen_mc_entry(0);
+ MULTI_update_va_mapping(mcs.mc, (unsigned long)addr,
+ pfn_pte(pfn, prot), 0);
+}
+
/* This needs to make sure the new pte page is pinned iff its being
attached to a pinned pagetable. */
-static void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, unsigned level)
+static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn,
+ unsigned level)
{
- struct page *page = pfn_to_page(pfn);
+ bool pinned = PagePinned(virt_to_page(mm->pgd));
+
+ trace_xen_mmu_alloc_ptpage(mm, pfn, level, pinned);
+
+ if (pinned) {
+ struct page *page = pfn_to_page(pfn);
- if (PagePinned(virt_to_page(mm->pgd))) {
SetPagePinned(page);
if (!PageHighMem(page)) {
- make_lowmem_page_readonly(__va(PFN_PHYS((unsigned long)pfn)));
+ xen_mc_batch();
+
+ __set_pfn_prot(pfn, PAGE_KERNEL_RO);
+
if (level == PT_PTE && USE_SPLIT_PTLOCKS)
- pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
+ __pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
+
+ xen_mc_issue(PARAVIRT_LAZY_MMU);
} else {
/* make sure there are no stray mappings of
this page */
}
/* This should never happen until we're OK to use struct page */
-static void xen_release_ptpage(unsigned long pfn, unsigned level)
+static inline void xen_release_ptpage(unsigned long pfn, unsigned level)
{
struct page *page = pfn_to_page(pfn);
+ bool pinned = PagePinned(page);
- if (PagePinned(page)) {
+ trace_xen_mmu_release_ptpage(pfn, level, pinned);
+
+ if (pinned) {
if (!PageHighMem(page)) {
+ xen_mc_batch();
+
if (level == PT_PTE && USE_SPLIT_PTLOCKS)
- pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
- make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
+ __pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
+
+ __set_pfn_prot(pfn, PAGE_KERNEL);
+
+ xen_mc_issue(PARAVIRT_LAZY_MMU);
}
ClearPagePinned(page);
}
if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, 0))
BUG();
}
-
+#ifdef CONFIG_X86_32
static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
{
unsigned pmdidx, pteidx;
for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) {
pte_t pte;
+#ifdef CONFIG_X86_32
+ if (pfn > max_pfn_mapped)
+ max_pfn_mapped = pfn;
+#endif
+
if (!pte_none(pte_page[pteidx]))
continue;
set_page_prot(pmd, PAGE_KERNEL_RO);
}
-
+#endif
void __init xen_setup_machphys_mapping(void)
{
struct xen_machphys_mapping mapping;
- unsigned long machine_to_phys_nr_ents;
if (HYPERVISOR_memory_op(XENMEM_machphys_mapping, &mapping) == 0) {
machine_to_phys_mapping = (unsigned long *)mapping.v_start;
- machine_to_phys_nr_ents = mapping.max_mfn + 1;
+ machine_to_phys_nr = mapping.max_mfn + 1;
} else {
- machine_to_phys_nr_ents = MACH2PHYS_NR_ENTRIES;
+ machine_to_phys_nr = MACH2PHYS_NR_ENTRIES;
}
- machine_to_phys_order = fls(machine_to_phys_nr_ents - 1);
+#ifdef CONFIG_X86_32
+ WARN_ON((machine_to_phys_mapping + (machine_to_phys_nr - 1))
+ < machine_to_phys_mapping);
+#endif
}
#ifdef CONFIG_X86_64
for (i = 0; i < PTRS_PER_PTE; i++)
pte[i] = xen_make_pte(pte[i].pte);
}
-
+static void __init check_pt_base(unsigned long *pt_base, unsigned long *pt_end,
+ unsigned long addr)
+{
+ if (*pt_base == PFN_DOWN(__pa(addr))) {
+ set_page_prot((void *)addr, PAGE_KERNEL);
+ clear_page((void *)addr);
+ (*pt_base)++;
+ }
+ if (*pt_end == PFN_DOWN(__pa(addr))) {
+ set_page_prot((void *)addr, PAGE_KERNEL);
+ clear_page((void *)addr);
+ (*pt_end)--;
+ }
+}
/*
* Set up the initial kernel pagetable.
*
* of the physical mapping once some sort of allocator has been set
* up.
*/
-pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
- unsigned long max_pfn)
+void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
{
pud_t *l3;
pmd_t *l2;
+ unsigned long addr[3];
+ unsigned long pt_base, pt_end;
+ unsigned i;
/* max_pfn_mapped is the last pfn mapped in the initial memory
* mappings. Considering that on Xen after the kernel mappings we
* set max_pfn_mapped to the last real pfn mapped. */
max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list));
+ pt_base = PFN_DOWN(__pa(xen_start_info->pt_base));
+ pt_end = pt_base + xen_start_info->nr_pt_frames;
+
/* Zap identity mapping */
init_level4_pgt[0] = __pgd(0);
/* Pre-constructed entries are in pfn, so convert to mfn */
+ /* L4[272] -> level3_ident_pgt
+ * L4[511] -> level3_kernel_pgt */
convert_pfn_mfn(init_level4_pgt);
+
+ /* L3_i[0] -> level2_ident_pgt */
convert_pfn_mfn(level3_ident_pgt);
+ /* L3_k[510] -> level2_kernel_pgt
+ * L3_i[511] -> level2_fixmap_pgt */
convert_pfn_mfn(level3_kernel_pgt);
+ /* We get [511][511] and have Xen's version of level2_kernel_pgt */
l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd);
l2 = m2v(l3[pud_index(__START_KERNEL_map)].pud);
- memcpy(level2_ident_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
- memcpy(level2_kernel_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
-
+ addr[0] = (unsigned long)pgd;
+ addr[1] = (unsigned long)l3;
+ addr[2] = (unsigned long)l2;
+ /* Graft it onto L4[272][0]. Note that we creating an aliasing problem:
+ * Both L4[272][0] and L4[511][511] have entries that point to the same
+ * L2 (PMD) tables. Meaning that if you modify it in __va space
+ * it will be also modified in the __ka space! (But if you just
+ * modify the PMD table to point to other PTE's or none, then you
+ * are OK - which is what cleanup_highmap does) */
+ copy_page(level2_ident_pgt, l2);
+ /* Graft it onto L4[511][511] */
+ copy_page(level2_kernel_pgt, l2);
+
+ /* Get [511][510] and graft that in level2_fixmap_pgt */
l3 = m2v(pgd[pgd_index(__START_KERNEL_map + PMD_SIZE)].pgd);
l2 = m2v(l3[pud_index(__START_KERNEL_map + PMD_SIZE)].pud);
- memcpy(level2_fixmap_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
-
- /* Set up identity map */
- xen_map_identity_early(level2_ident_pgt, max_pfn);
+ copy_page(level2_fixmap_pgt, l2);
+ /* Note that we don't do anything with level1_fixmap_pgt which
+ * we don't need. */
/* Make pagetable pieces RO */
set_page_prot(init_level4_pgt, PAGE_KERNEL_RO);
set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO);
set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO);
set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO);
+ set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO);
set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
/* Unpin Xen-provided one */
pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
- /* Switch over */
- pgd = init_level4_pgt;
-
/*
* At this stage there can be no user pgd, and no page
* structure to attach it to, so make sure we just set kernel
* pgd.
*/
xen_mc_batch();
- __xen_write_cr3(true, __pa(pgd));
+ __xen_write_cr3(true, __pa(init_level4_pgt));
xen_mc_issue(PARAVIRT_LAZY_CPU);
- memblock_x86_reserve_range(__pa(xen_start_info->pt_base),
- __pa(xen_start_info->pt_base +
- xen_start_info->nr_pt_frames * PAGE_SIZE),
- "XEN PAGETABLES");
+ /* We can't that easily rip out L3 and L2, as the Xen pagetables are
+ * set out this way: [L4], [L1], [L2], [L3], [L1], [L1] ... for
+ * the initial domain. For guests using the toolstack, they are in:
+ * [L4], [L3], [L2], [L1], [L1], order .. So for dom0 we can only
+ * rip out the [L4] (pgd), but for guests we shave off three pages.
+ */
+ for (i = 0; i < ARRAY_SIZE(addr); i++)
+ check_pt_base(&pt_base, &pt_end, addr[i]);
- return pgd;
+ /* Our (by three pages) smaller Xen pagetable that we are using */
+ memblock_reserve(PFN_PHYS(pt_base), (pt_end - pt_base) * PAGE_SIZE);
+ /* Revector the xen_start_info */
+ xen_start_info = (struct start_info *)__va(__pa(xen_start_info));
}
#else /* !CONFIG_X86_64 */
static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD);
*/
swapper_kernel_pmd =
extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
- memcpy(swapper_kernel_pmd, initial_kernel_pmd,
- sizeof(pmd_t) * PTRS_PER_PMD);
+ copy_page(swapper_kernel_pmd, initial_kernel_pmd);
swapper_pg_dir[KERNEL_PGD_BOUNDARY] =
__pgd(__pa(swapper_kernel_pmd) | _PAGE_PRESENT);
set_page_prot(swapper_kernel_pmd, PAGE_KERNEL_RO);
pv_mmu_ops.write_cr3 = &xen_write_cr3;
}
-pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
- unsigned long max_pfn)
+void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
{
pmd_t *kernel_pmd;
initial_kernel_pmd =
extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
- max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list));
+ max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) +
+ xen_start_info->nr_pt_frames * PAGE_SIZE +
+ 512*1024);
kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
- memcpy(initial_kernel_pmd, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD);
+ copy_page(initial_kernel_pmd, kernel_pmd);
xen_map_identity_early(initial_kernel_pmd, max_pfn);
- memcpy(initial_page_table, pgd, sizeof(pgd_t) * PTRS_PER_PGD);
+ copy_page(initial_page_table, pgd);
initial_page_table[KERNEL_PGD_BOUNDARY] =
__pgd(__pa(initial_kernel_pmd) | _PAGE_PRESENT);
PFN_DOWN(__pa(initial_page_table)));
xen_write_cr3(__pa(initial_page_table));
- memblock_x86_reserve_range(__pa(xen_start_info->pt_base),
- __pa(xen_start_info->pt_base +
- xen_start_info->nr_pt_frames * PAGE_SIZE),
- "XEN PAGETABLES");
-
- return initial_page_table;
+ memblock_reserve(__pa(xen_start_info->pt_base),
+ xen_start_info->nr_pt_frames * PAGE_SIZE);
}
#endif /* CONFIG_X86_64 */
# endif
#else
case VSYSCALL_LAST_PAGE ... VSYSCALL_FIRST_PAGE:
+ case VVAR_PAGE:
#endif
case FIX_TEXT_POKE0:
case FIX_TEXT_POKE1:
#ifdef CONFIG_X86_64
/* Replicate changes to map the vsyscall page into the user
pagetable vsyscall mapping. */
- if (idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) {
+ if ((idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) ||
+ idx == VVAR_PAGE) {
unsigned long vaddr = __fix_to_virt(idx);
set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte);
}
#endif
}
-void __init xen_ident_map_ISA(void)
-{
- unsigned long pa;
-
- /*
- * If we're dom0, then linear map the ISA machine addresses into
- * the kernel's address space.
- */
- if (!xen_initial_domain())
- return;
-
- xen_raw_printk("Xen: setup ISA identity maps\n");
-
- for (pa = ISA_START_ADDRESS; pa < ISA_END_ADDRESS; pa += PAGE_SIZE) {
- pte_t pte = mfn_pte(PFN_DOWN(pa), PAGE_KERNEL_IO);
-
- if (HYPERVISOR_update_va_mapping(PAGE_OFFSET + pa, pte, 0))
- BUG();
- }
-
- xen_flush_tlb();
-}
-
static void __init xen_post_allocator_init(void)
{
-#ifdef CONFIG_XEN_DEBUG
- pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte_debug);
-#endif
pv_mmu_ops.set_pte = xen_set_pte;
pv_mmu_ops.set_pmd = xen_set_pmd;
pv_mmu_ops.set_pud = xen_set_pud;
#endif
#ifdef CONFIG_X86_64
+ pv_mmu_ops.write_cr3 = &xen_write_cr3;
SetPagePinned(virt_to_page(level3_user_vsyscall));
#endif
xen_mark_init_mm_pinned();
.write_cr2 = xen_write_cr2,
.read_cr3 = xen_read_cr3,
-#ifdef CONFIG_X86_32
.write_cr3 = xen_write_cr3_init,
-#else
- .write_cr3 = xen_write_cr3,
-#endif
.flush_tlb_user = xen_flush_tlb,
.flush_tlb_kernel = xen_flush_tlb,
.lazy_mode = {
.enter = paravirt_enter_lazy_mmu,
.leave = xen_leave_lazy_mmu,
+ .flush = paravirt_flush_lazy_mmu,
},
.set_fixmap = xen_set_fixmap,
void __init xen_init_mmu_ops(void)
{
- x86_init.mapping.pagetable_reserve = xen_mapping_pagetable_reserve;
- x86_init.paging.pagetable_setup_start = xen_pagetable_setup_start;
- x86_init.paging.pagetable_setup_done = xen_pagetable_setup_done;
+ x86_init.paging.pagetable_init = xen_pagetable_init;
pv_mmu_ops = xen_mmu_ops;
memset(dummy_mapping, 0xff, PAGE_SIZE);
EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region);
#ifdef CONFIG_XEN_PVHVM
+#ifdef CONFIG_PROC_VMCORE
+/*
+ * This function is used in two contexts:
+ * - the kdump kernel has to check whether a pfn of the crashed kernel
+ * was a ballooned page. vmcore is using this function to decide
+ * whether to access a pfn of the crashed kernel.
+ * - the kexec kernel has to check whether a pfn was ballooned by the
+ * previous kernel. If the pfn is ballooned, handle it properly.
+ * Returns 0 if the pfn is not backed by a RAM page, the caller may
+ * handle the pfn special in this case.
+ */
+static int xen_oldmem_pfn_is_ram(unsigned long pfn)
+{
+ struct xen_hvm_get_mem_type a = {
+ .domid = DOMID_SELF,
+ .pfn = pfn,
+ };
+ int ram;
+
+ if (HYPERVISOR_hvm_op(HVMOP_get_mem_type, &a))
+ return -ENXIO;
+
+ switch (a.mem_type) {
+ case HVMMEM_mmio_dm:
+ ram = 0;
+ break;
+ case HVMMEM_ram_rw:
+ case HVMMEM_ram_ro:
+ default:
+ ram = 1;
+ break;
+ }
+
+ return ram;
+}
+#endif
+
static void xen_hvm_exit_mmap(struct mm_struct *mm)
{
struct xen_hvm_pagetable_dying a;
{
if (is_pagetable_dying_supported())
pv_mmu_ops.exit_mmap = xen_hvm_exit_mmap;
+#ifdef CONFIG_PROC_VMCORE
+ register_oldmem_pfn_is_ram(&xen_oldmem_pfn_is_ram);
+#endif
}
#endif
struct remap_data *rmd = data;
pte_t pte = pte_mkspecial(pfn_pte(rmd->mfn++, rmd->prot));
- rmd->mmu_update->ptr = arbitrary_virt_to_machine(ptep).maddr;
+ rmd->mmu_update->ptr = virt_to_machine(ptep).maddr;
rmd->mmu_update->val = pte_val_ma(pte);
rmd->mmu_update++;
int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
unsigned long addr,
- unsigned long mfn, int nr,
- pgprot_t prot, unsigned domid)
+ xen_pfn_t mfn, int nr,
+ pgprot_t prot, unsigned domid,
+ struct page **pages)
+
{
struct remap_data rmd;
struct mmu_update mmu_update[REMAP_BATCH_SIZE];
unsigned long range;
int err = 0;
+ if (xen_feature(XENFEAT_auto_translated_physmap))
+ return -EINVAL;
+
prot = __pgprot(pgprot_val(prot) | _PAGE_IOMAP);
- BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_RESERVED | VM_IO)) ==
- (VM_PFNMAP | VM_RESERVED | VM_IO)));
+ BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_IO)) == (VM_PFNMAP | VM_IO)));
rmd.mfn = mfn;
rmd.prot = prot;
if (err)
goto out;
- err = -EFAULT;
- if (HYPERVISOR_mmu_update(mmu_update, batch, NULL, domid) < 0)
+ err = HYPERVISOR_mmu_update(mmu_update, batch, NULL, domid);
+ if (err < 0)
goto out;
nr -= batch;
err = 0;
out:
- flush_tlb_all();
+ xen_flush_tlb_all();
return err;
}
EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_range);
-#ifdef CONFIG_XEN_DEBUG_FS
-
-static int p2m_dump_open(struct inode *inode, struct file *filp)
-{
- return single_open(filp, p2m_dump_show, NULL);
-}
-
-static const struct file_operations p2m_dump_fops = {
- .open = p2m_dump_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
-static struct dentry *d_mmu_debug;
-
-static int __init xen_mmu_debugfs(void)
+/* Returns: 0 success */
+int xen_unmap_domain_mfn_range(struct vm_area_struct *vma,
+ int numpgs, struct page **pages)
{
- struct dentry *d_xen = xen_init_debugfs();
-
- if (d_xen == NULL)
- return -ENOMEM;
+ if (!pages || !xen_feature(XENFEAT_auto_translated_physmap))
+ return 0;
- d_mmu_debug = debugfs_create_dir("mmu", d_xen);
-
- debugfs_create_u8("zero_stats", 0644, d_mmu_debug, &zero_stats);
-
- debugfs_create_u32("pgd_update", 0444, d_mmu_debug, &mmu_stats.pgd_update);
- debugfs_create_u32("pgd_update_pinned", 0444, d_mmu_debug,
- &mmu_stats.pgd_update_pinned);
- debugfs_create_u32("pgd_update_batched", 0444, d_mmu_debug,
- &mmu_stats.pgd_update_pinned);
-
- debugfs_create_u32("pud_update", 0444, d_mmu_debug, &mmu_stats.pud_update);
- debugfs_create_u32("pud_update_pinned", 0444, d_mmu_debug,
- &mmu_stats.pud_update_pinned);
- debugfs_create_u32("pud_update_batched", 0444, d_mmu_debug,
- &mmu_stats.pud_update_pinned);
-
- debugfs_create_u32("pmd_update", 0444, d_mmu_debug, &mmu_stats.pmd_update);
- debugfs_create_u32("pmd_update_pinned", 0444, d_mmu_debug,
- &mmu_stats.pmd_update_pinned);
- debugfs_create_u32("pmd_update_batched", 0444, d_mmu_debug,
- &mmu_stats.pmd_update_pinned);
-
- debugfs_create_u32("pte_update", 0444, d_mmu_debug, &mmu_stats.pte_update);
-// debugfs_create_u32("pte_update_pinned", 0444, d_mmu_debug,
-// &mmu_stats.pte_update_pinned);
- debugfs_create_u32("pte_update_batched", 0444, d_mmu_debug,
- &mmu_stats.pte_update_pinned);
-
- debugfs_create_u32("mmu_update", 0444, d_mmu_debug, &mmu_stats.mmu_update);
- debugfs_create_u32("mmu_update_extended", 0444, d_mmu_debug,
- &mmu_stats.mmu_update_extended);
- xen_debugfs_create_u32_array("mmu_update_histo", 0444, d_mmu_debug,
- mmu_stats.mmu_update_histo, 20);
-
- debugfs_create_u32("set_pte_at", 0444, d_mmu_debug, &mmu_stats.set_pte_at);
- debugfs_create_u32("set_pte_at_batched", 0444, d_mmu_debug,
- &mmu_stats.set_pte_at_batched);
- debugfs_create_u32("set_pte_at_current", 0444, d_mmu_debug,
- &mmu_stats.set_pte_at_current);
- debugfs_create_u32("set_pte_at_kernel", 0444, d_mmu_debug,
- &mmu_stats.set_pte_at_kernel);
-
- debugfs_create_u32("prot_commit", 0444, d_mmu_debug, &mmu_stats.prot_commit);
- debugfs_create_u32("prot_commit_batched", 0444, d_mmu_debug,
- &mmu_stats.prot_commit_batched);
-
- debugfs_create_file("p2m", 0600, d_mmu_debug, NULL, &p2m_dump_fops);
- return 0;
+ return -EINVAL;
}
-fs_initcall(xen_mmu_debugfs);
-
-#endif /* CONFIG_XEN_DEBUG_FS */
+EXPORT_SYMBOL_GPL(xen_unmap_domain_mfn_range);
Code Review / linux-3.10.git / blobdiff