/* * Xen mmu operations * * This file contains the various mmu fetch and update operations. * The most important job they must perform is the mapping between the * domain's pfn and the overall machine mfns. * * Xen allows guests to directly update the pagetable, in a controlled * fashion. In other words, the guest modifies the same pagetable * that the CPU actually uses, which eliminates the overhead of having * a separate shadow pagetable. * * In order to allow this, it falls on the guest domain to map its * notion of a "physical" pfn - which is just a domain-local linear * address - into a real "machine address" which the CPU's MMU can * use. * * A pgd_t/pmd_t/pte_t will typically contain an mfn, and so can be * inserted directly into the pagetable. When creating a new * pte/pmd/pgd, it converts the passed pfn into an mfn. Conversely, * when reading the content back with __(pgd|pmd|pte)_val, it converts * the mfn back into a pfn. * * The other constraint is that all pages which make up a pagetable * must be mapped read-only in the guest. This prevents uncontrolled * guest updates to the pagetable. Xen strictly enforces this, and * will disallow any pagetable update which will end up mapping a * pagetable page RW, and will disallow using any writable page as a * pagetable. * * Naively, when loading %cr3 with the base of a new pagetable, Xen * would need to validate the whole pagetable before going on. * Naturally, this is quite slow. The solution is to "pin" a * pagetable, which enforces all the constraints on the pagetable even * when it is not actively in use. This means that Xen can be assured * that it is still valid when you do load it into %cr3, and doesn't * need to revalidate it. * * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007
*/ #include <linux/sched/mm.h> #include <linux/debugfs.h> #include <linux/bug.h> #include <linux/vmalloc.h> #include <linux/export.h> #include <linux/init.h> #include <linux/gfp.h> #include <linux/memblock.h> #include <linux/seq_file.h> #include <linux/crash_dump.h> #include <linux/pgtable.h> #ifdef CONFIG_KEXEC_CORE #include <linux/kexec.h> #endif
/* * Note about cr3 (pagetable base) values: * * xen_cr3 contains the current logical cr3 value; it contains the * last set cr3. This may not be the current effective cr3, because * its update may be being lazily deferred. However, a vcpu looking * at its own cr3 can use this value knowing that it everything will * be self-consistent. * * xen_current_cr3 contains the actual vcpu cr3; it is set once the * hypercall to set the vcpu cr3 is complete (so it may be a little * out of date, but it will never be set early). If one vcpu is * looking at another vcpu's cr3 value, it should use this variable.
*/
DEFINE_PER_CPU(unsignedlong, xen_cr3); /* cr3 stored as physaddr */ static DEFINE_PER_CPU(unsignedlong, xen_current_cr3); /* actual vcpu cr3 */
/* * Just beyond the highest usermode address. STACK_TOP_MAX has a * redzone above it, so round it up to a PGD boundary.
*/ #define USER_LIMIT ((STACK_TOP_MAX + PGDIR_SIZE - 1) & PGDIR_MASK)
if (HYPERVISOR_update_va_mapping(address, ptev, 0))
BUG();
}
/* * During early boot all page table pages are pinned, but we do not have struct * pages, so return true until struct pages are ready.
*/ staticbool xen_page_pinned(void *ptr)
{ if (static_branch_likely(&xen_struct_pages_ready)) { struct page *page = virt_to_page(ptr);
/* If page is not pinned, we can just update the entry
directly */ if (!xen_page_pinned(ptr)) {
*ptr = val; return;
}
xen_set_pmd_hyper(ptr, val);
}
/* * Associate a virtual page frame with a given physical page frame * and protection flags for that frame.
*/ void __init set_pte_mfn(unsignedlong vaddr, unsignedlong mfn, pgprot_t flags)
{ if (HYPERVISOR_update_va_mapping(vaddr, mfn_pte(mfn, flags),
UVMF_INVLPG))
BUG();
}
staticinlinevoid __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 a hypercall is much cheaper.
*/ struct mmu_update u;
/* * If there's no mfn for the pfn, then just create an * empty non-present pte. Unfortunately this loses * information about the original pfn, so * pte_mfn_to_pfn is asymmetric.
*/ if (unlikely(mfn == INVALID_P2M_ENTRY)) {
mfn = 0;
flags = 0;
} else
mfn &= ~(FOREIGN_FRAME_BIT | IDENTITY_FRAME_BIT);
val = ((pteval_t)mfn << PAGE_SHIFT) | flags;
}
/* * Raw hypercall-based set_p4d, intended for in early boot before * there's a page structure. This implies: * 1. The only existing pagetable is the kernel's * 2. It is always pinned * 3. It has no user pagetable attached to it
*/ staticvoid __init xen_set_p4d_hyper(p4d_t *ptr, p4d_t val)
{
preempt_disable();
/* If page is not pinned, we can just update the entry
directly */ if (!xen_page_pinned(ptr)) {
*ptr = val; if (user_ptr) {
WARN_ON(xen_page_pinned(user_ptr));
pgd_val.pgd = p4d_val_ma(val);
*user_ptr = pgd_val;
} return;
}
/* If it's pinned, then we can at least batch the kernel and
user updates together. */
xen_mc_batch();
__xen_set_p4d_hyper(ptr, val); if (user_ptr)
__xen_set_p4d_hyper((p4d_t *)user_ptr, val);
pud = pud_offset(p4d, 0); if (PTRS_PER_PUD > 1)
(*func)(mm, virt_to_page(pud), PT_PUD);
xen_pud_walk(mm, pud, func, last, limit);
}
/* * (Yet another) pagetable walker. This one is intended for pinning a * pagetable. This means that it walks a pagetable and calls the * callback function on each page it finds making up the page table, * at every level. It walks the entire pagetable, but it only bothers * pinning pte pages which are below limit. In the normal case this * will be STACK_TOP_MAX, but at boot we need to pin up to * FIXADDR_TOP. * * We must skip the Xen hole in the middle of the address space, just after * the big x86-64 virtual hole.
*/ staticvoid __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd, void (*func)(struct mm_struct *mm, struct page *, enum pt_level), unsignedlong limit)
{ int i, nr; unsigned hole_low = 0, hole_high = 0;
/* The limit is the last byte to be touched */
limit--;
BUG_ON(limit >= FIXADDR_TOP);
/* * 64-bit has a great big hole in the middle of the address * space, which contains the Xen mappings.
*/
hole_low = pgd_index(GUARD_HOLE_BASE_ADDR);
hole_high = pgd_index(GUARD_HOLE_END_ADDR);
nr = pgd_index(limit) + 1; for (i = 0; i < nr; i++) {
p4d_t *p4d;
if (i >= hole_low && i < hole_high) continue;
if (pgd_none(pgd[i])) continue;
p4d = p4d_offset(&pgd[i], 0);
xen_p4d_walk(mm, p4d, func, i == nr - 1, limit);
}
/* Do the top level last, so that the callbacks can use it as
a cue to do final things like tlb flushes. */
(*func)(mm, virt_to_page(pgd), PT_PGD);
}
/* If we're using split pte locks, then take the page's lock and
return a pointer to it. Otherwise return NULL. */ static spinlock_t *xen_pte_lock(struct page *page, struct mm_struct *mm)
{
spinlock_t *ptl = NULL;
/* * We need to hold the pagetable lock between the time * we make the pagetable RO and when we actually pin * it. If we don't, then other users may come in and * attempt to update the pagetable by writing it, * which will fail because the memory is RO but not * pinned, so Xen won't do the trap'n'emulate. * * If we're using split pte locks, we can't hold the * entire pagetable's worth of locks during the * traverse, because we may wrap the preempt count (8 * bits). The solution is to mark RO and pin each PTE * page while holding the lock. This means the number * of locks we end up holding is never more than a * batch size (~32 entries, at present). * * If we're not using split pte locks, we needn't pin * the PTE pages independently, because we're * protected by the overall pagetable lock.
*/
ptl = NULL; if (level == PT_PTE)
ptl = xen_pte_lock(page, mm);
/* Queue a deferred unlock for when this batch
is completed. */
xen_mc_callback(xen_pte_unlock, ptl);
}
}
}
/* This is called just after a mm has been created, but it has not been used yet. We need to make sure that its pagetable is all
read-only, and can be pinned. */ staticvoid __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd)
{
pgd_t *user_pgd = xen_get_user_pgd(pgd);
/* * On save, we need to pin all pagetables to make sure they get their * mfns turned into pfns. Search the list for any unpinned pgds and pin * them (unpinned pgds are not currently in use, probably because the * process is under construction or destruction). * * Expected to be called in stop_machine() ("equivalent to taking * every spinlock in the system"), so the locking doesn't really * matter all that much.
*/ void xen_mm_pin_all(void)
{ struct page *page;
/* * The init_mm pagetable is really pinned as soon as its created, but * that's before we have page structures to store the bits. So do all * the book-keeping now once struct pages for allocated pages are * initialized. This happens only after memblock_free_all() is called.
*/ staticvoid __init xen_after_bootmem(void)
{
static_branch_enable(&xen_struct_pages_ready); #ifdef CONFIG_X86_VSYSCALL_EMULATION
SetPagePinned(virt_to_page(level3_user_vsyscall)); #endif
xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP);
if (alloc_discontig_frames(MIN_CONTIG_ORDER))
BUG();
}
/* * Do the converse to pin_page. If we're using split * pte locks, we must be holding the lock for while * the pte page is unpinned but still RO to prevent * concurrent updates from seeing it in this * partially-pinned state.
*/ if (level == PT_PTE) {
ptl = xen_pte_lock(page, mm);
/* * On resume, undo any pinning done at save, so that the rest of the * kernel doesn't see any unexpected pinned pagetables.
*/ void xen_mm_unpin_all(void)
{ struct page *page;
if (this_cpu_read(cpu_tlbstate.loaded_mm) == mm)
leave_mm();
/* * If this cpu still has a stale cr3 reference, then make sure * it has been flushed.
*/ if (this_cpu_read(xen_current_cr3) == __pa(mm->pgd))
xen_mc_flush();
}
#ifdef CONFIG_SMP /* * Another cpu may still have their %cr3 pointing at the pagetable, so * we need to repoint it somewhere else before we can unpin it.
*/ staticvoid xen_drop_mm_ref(struct mm_struct *mm)
{
cpumask_var_t mask; unsigned cpu;
drop_mm_ref_this_cpu(mm);
/* Get the "official" set of cpus referring to our pagetable. */ if (!alloc_cpumask_var(&mask, GFP_ATOMIC)) {
for_each_online_cpu(cpu) { if (per_cpu(xen_current_cr3, cpu) != __pa(mm->pgd)) continue;
smp_call_function_single(cpu, drop_mm_ref_this_cpu, mm, 1);
} return;
}
/* * It's possible that a vcpu may have a stale reference to our * cr3, because its in lazy mode, and it hasn't yet flushed * its set of pending hypercalls yet. In this case, we can * look at its actual current cr3 value, and force it to flush * if needed.
*/
cpumask_clear(mask);
for_each_online_cpu(cpu) { if (per_cpu(xen_current_cr3, cpu) == __pa(mm->pgd))
cpumask_set_cpu(cpu, mask);
}
/* * While a process runs, Xen pins its pagetables, which means that the * hypervisor forces it to be read-only, and it controls all updates * to it. This means that all pagetable updates have to go via the * hypervisor, which is moderately expensive. * * Since we're pulling the pagetable down, we switch to use init_mm, * unpin old process pagetable and mark it all read-write, which * allows further operations on it to be simple memory accesses. * * The only subtle point is that another CPU may be still using the * pagetable because of lazy tlb flushing. This means we need need to * switch all CPUs off this pagetable before we can unpin it.
*/ staticvoid xen_exit_mmap(struct mm_struct *mm)
{
get_cpu(); /* make sure we don't move around */
xen_drop_mm_ref(mm);
put_cpu();
spin_lock(&mm->page_table_lock);
/* pgd may not be pinned in the error exit path of execve */ if (xen_page_pinned(mm->pgd))
xen_pgd_unpin(mm);
/* 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 + PTRS_PER_PMD));
pmd++, vaddr += PMD_SIZE) { if (pmd_none(*pmd)) continue; if (vaddr < (unsignedlong) _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();
}
/* * Make a page range writeable and free it.
*/ staticvoid __init xen_free_ro_pages(unsignedlong paddr, unsignedlong size)
{ void *vaddr = __va(paddr); void *vaddr_end = vaddr + size;
for (; vaddr < vaddr_end; vaddr += PAGE_SIZE)
make_lowmem_page_readwrite(vaddr);
if (p4d_leaf(*p4d)) {
pa = p4d_val(*p4d) & PHYSICAL_PAGE_MASK;
xen_free_ro_pages(pa, P4D_SIZE); return;
}
pud_tbl = pud_offset(p4d, 0); for (i = 0; i < PTRS_PER_PUD; i++) { if (pud_none(pud_tbl[i])) continue;
xen_cleanmfnmap_pud(pud_tbl + i, unpin);
}
set_p4d(p4d, __p4d(0));
xen_cleanmfnmap_free_pgtbl(pud_tbl, unpin);
}
/* * Since it is well isolated we can (and since it is perhaps large we should) * also free the page tables mapping the initial P->M table.
*/ staticvoid __init xen_cleanmfnmap(unsignedlong vaddr)
{
pgd_t *pgd;
p4d_t *p4d; bool unpin;
/* No memory or already called. */ if ((unsignedlong)xen_p2m_addr == xen_start_info->mfn_list) return;
/* using __ka address and sticking INVALID_P2M_ENTRY! */
memset((void *)xen_start_info->mfn_list, 0xff, size);
addr = xen_start_info->mfn_list; /* * We could be in __ka space. * 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. Fortunately * we have already revectored in xen_setup_kernel_pagetable.
*/
size = roundup(size, PMD_SIZE);
/* 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. * As Xen is aligning the memory end to a 4MB boundary, for good * measure we also round up to PMD_SIZE * 2 - 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 = xen_start_info->nr_pt_frames * PAGE_SIZE;
/* And revector! Bye bye old array */
xen_start_info->mfn_list = (unsignedlong)xen_p2m_addr;
}
staticvoid __init xen_pagetable_init(void)
{ /* * The majority of further PTE writes is to pagetables already * announced as such to Xen. Hence it is more efficient to use * hypercalls for these updates.
*/
pv_ops.mmu.set_pte = __xen_set_pte;
paging_init();
xen_post_allocator_init();
xen_pagetable_p2m_setup();
/* Allocate and initialize top and mid mfn levels for p2m structure */
xen_build_mfn_list_list();
/* Remap memory freed due to conflicts with E820 map */
xen_remap_memory();
xen_setup_mfn_list_list();
}
/* * 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 appropriate them in the * init_top_pgt and its friends. Then when we are happy we load * the new init_top_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.
*/ staticvoid __init xen_write_cr3_init(unsignedlong 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);
if (user_pgd)
free_page((unsignedlong)user_pgd);
}
/* * 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 rarely possible to tell if a page is pinned, so * mostly write the PTE directly and rely on Xen trapping and * emulating any updates as necessary.
*/ staticvoid __init xen_set_pte_init(pte_t *ptep, pte_t pte)
{ if (unlikely(is_early_ioremap_ptep(ptep)))
__xen_set_pte(ptep, pte); else
native_set_pte(ptep, pte);
}
/* * Pages belonging to the initial p2m list mapped outside the default * address range must be mapped read-only. This region contains the * page tables for mapping the p2m list, too, and page tables MUST be * mapped read-only.
*/
pfn = (pte & PTE_PFN_MASK) >> PAGE_SHIFT; if (xen_start_info->mfn_list < __START_KERNEL_map &&
pfn >= xen_start_info->first_p2m_pfn &&
pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames)
pte &= ~_PAGE_RW;
/* Early in boot, while setting up the initial pagetable, assume
everything is pinned. */ staticvoid __init xen_alloc_pte_init(struct mm_struct *mm, unsignedlong pfn)
{ #ifdef CONFIG_FLATMEM
BUG_ON(mem_map); /* should only be used early */ #endif
make_lowmem_page_readonly(__va(PFN_PHYS(pfn)));
pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
}
/* Used for pmd and pud */ staticvoid __init xen_alloc_pmd_init(struct mm_struct *mm, unsignedlong pfn)
{ #ifdef CONFIG_FLATMEM
BUG_ON(mem_map); /* should only be used early */ #endif
make_lowmem_page_readonly(__va(PFN_PHYS(pfn)));
}
/* Early release_pte assumes that all pts are pinned, since there's
only init_mm and anything attached to that is pinned. */ staticvoid __init xen_release_pte_init(unsignedlong pfn)
{
pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
}
/* This needs to make sure the new pte page is pinned iff its being
attached to a pinned pagetable. */ staticinlinevoid xen_alloc_ptpage(struct mm_struct *mm, unsignedlong pfn, unsigned level)
{ bool pinned = xen_page_pinned(mm->pgd);
/* This should never happen until we're OK to use struct page */ staticinlinevoid xen_release_ptpage(unsignedlong pfn, unsigned level)
{ struct page *page = pfn_to_page(pfn); bool pinned = PagePinned(page);
trace_xen_mmu_release_ptpage(pfn, level, pinned);
if (pinned) {
xen_mc_batch();
if (level == PT_PTE && IS_ENABLED(CONFIG_SPLIT_PTE_PTLOCKS))
__pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
/* * Like __va(), but returns address in the kernel mapping (which is * all we have until the physical memory mapping has been set up.
*/ staticvoid * __init __ka(phys_addr_t paddr)
{ return (void *)(paddr + __START_KERNEL_map);
}
/* Convert a machine address to physical address */ staticunsignedlong __init m2p(phys_addr_t maddr)
{
phys_addr_t paddr;
/* All levels are converted the same way, so just treat them
as ptes. */ for (i = 0; i < PTRS_PER_PTE; i++)
pte[i] = xen_make_pte(pte[i].pte);
} staticvoid __init check_pt_base(unsignedlong *pt_base, unsignedlong *pt_end, unsignedlong addr)
{ if (*pt_base == PFN_DOWN(__pa(addr))) {
set_page_prot_flags((void *)addr, PAGE_KERNEL, UVMF_INVLPG);
clear_page((void *)addr);
(*pt_base)++;
} if (*pt_end == PFN_DOWN(__pa(addr))) {
set_page_prot_flags((void *)addr, PAGE_KERNEL, UVMF_INVLPG);
clear_page((void *)addr);
(*pt_end)--;
}
} /* * Set up the initial kernel pagetable. * * We can construct this by grafting the Xen provided pagetable into * head_64.S's preconstructed pagetables. We copy the Xen L2's into * level2_ident_pgt, and level2_kernel_pgt. This means that only the * kernel has a physical mapping to start with - but that's enough to * get __va working. We need to fill in the rest of the physical * mapping once some sort of allocator has been set up.
*/ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsignedlong max_pfn)
{
pud_t *l3;
pmd_t *l2; unsignedlong addr[3]; unsignedlong 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 * have the mappings of some pages that don't exist in pfn space, we
* set max_pfn_mapped to the last real pfn mapped. */ if (xen_start_info->mfn_list < __START_KERNEL_map)
max_pfn_mapped = xen_start_info->first_p2m_pfn; else
max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list));
/* 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);
addr[0] = (unsignedlong)pgd;
addr[1] = (unsignedlong)l3;
addr[2] = (unsignedlong)l2; /* Graft it onto L4[273][0]. Note that we creating an aliasing problem: * Both L4[273][0] and L4[511][510] 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][510] */
copy_page(level2_kernel_pgt, l2);
/* * Zap execute permission from the ident map. Due to the sharing of * L1 entries we need to do this in the L2.
*/ if (__supported_pte_mask & _PAGE_NX) { for (i = 0; i < PTRS_PER_PMD; ++i) { if (pmd_none(level2_ident_pgt[i])) continue;
level2_ident_pgt[i] = pmd_set_flags(level2_ident_pgt[i], _PAGE_NX);
}
}
/* Copy the initial P->M table mappings if necessary. */
i = pgd_index(xen_start_info->mfn_list); if (i && i < pgd_index(__START_KERNEL_map))
init_top_pgt[i] = ((pgd_t *)xen_start_info->pt_base)[i];
/* * 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(init_top_pgt));
xen_mc_issue(XEN_LAZY_CPU);
/* 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]);
/* Our (by three pages) smaller Xen pagetable that we are using */
xen_pt_base = PFN_PHYS(pt_base);
xen_pt_size = (pt_end - pt_base) * PAGE_SIZE;
memblock_reserve(xen_pt_base, xen_pt_size);
/* * Translate a virtual address to a physical one without relying on mapped * page tables. Don't rely on big pages being aligned in (guest) physical * space!
*/ static phys_addr_t __init xen_early_virt_to_phys(unsignedlong vaddr)
{
phys_addr_t pa;
pgd_t pgd;
pud_t pud;
pmd_t pmd;
pte_t pte;
pa = read_cr3_pa();
pgd = native_make_pgd(xen_read_phys_ulong(pa + pgd_index(vaddr) * sizeof(pgd))); if (!pgd_present(pgd)) return 0;
pa = pgd_val(pgd) & PTE_PFN_MASK;
pud = native_make_pud(xen_read_phys_ulong(pa + pud_index(vaddr) * sizeof(pud))); if (!pud_present(pud)) return 0;
pa = pud_val(pud) & PTE_PFN_MASK; if (pud_leaf(pud)) return pa + (vaddr & ~PUD_MASK);
pmd = native_make_pmd(xen_read_phys_ulong(pa + pmd_index(vaddr) * sizeof(pmd))); if (!pmd_present(pmd)) return 0;
pa = pmd_val(pmd) & PTE_PFN_MASK; if (pmd_leaf(pmd)) return pa + (vaddr & ~PMD_MASK);
pte = native_make_pte(xen_read_phys_ulong(pa + pte_index(vaddr) * sizeof(pte))); if (!pte_present(pte)) return 0;
pa = pte_pfn(pte) << PAGE_SHIFT;
return pa | (vaddr & ~PAGE_MASK);
}
/* * Find a new area for the hypervisor supplied p2m list and relocate the p2m to * this area.
*/ void __init xen_relocate_p2m(void)
{
phys_addr_t size, new_area, pt_phys, pmd_phys, pud_phys; unsignedlong p2m_pfn, p2m_pfn_end, n_frames, pfn, pfn_end; int n_pte, n_pt, n_pmd, n_pud, idx_pte, idx_pt, idx_pmd, idx_pud;
pte_t *pt;
pmd_t *pmd;
pud_t *pud;
pgd_t *pgd; unsignedlong *new_p2m;
new_area = xen_find_free_area(PFN_PHYS(n_frames)); if (!new_area) {
xen_raw_console_write("Can't find new memory area for p2m needed due to E820 map conflict\n");
BUG();
}
/* * Setup the page tables for addressing the new p2m list. * We have asked the hypervisor to map the p2m list at the user address * PUD_SIZE. It may have done so, or it may have used a kernel space * address depending on the Xen version. * To avoid any possible virtual address collision, just use * 2 * PUD_SIZE for the new area.
*/
pud_phys = new_area;
pmd_phys = pud_phys + PFN_PHYS(n_pud);
pt_phys = pmd_phys + PFN_PHYS(n_pmd);
p2m_pfn = PFN_DOWN(pt_phys) + n_pt;
/* Now copy the old p2m info to the new area. */
memcpy(new_p2m, xen_p2m_addr, size);
xen_p2m_addr = new_p2m;
/* Release the old p2m list and set new list info. */
p2m_pfn = PFN_DOWN(xen_early_virt_to_phys(xen_start_info->mfn_list));
BUG_ON(!p2m_pfn);
p2m_pfn_end = p2m_pfn + PFN_DOWN(size);
switch (idx) { case FIX_BTMAP_END ... FIX_BTMAP_BEGIN: #ifdef CONFIG_X86_VSYSCALL_EMULATION case VSYSCALL_PAGE: #endif /* All local page mappings */
pte = pfn_pte(phys, prot); break;
#ifdef CONFIG_X86_LOCAL_APIC case FIX_APIC_BASE: /* maps dummy local APIC */
pte = pfn_pte(PFN_DOWN(__pa(dummy_mapping)), PAGE_KERNEL); break; #endif
#ifdef CONFIG_X86_IO_APIC case FIX_IO_APIC_BASE_0 ... FIX_IO_APIC_BASE_END: /* * We just don't map the IO APIC - all access is via * hypercalls. Keep the address in the pte for reference.
*/
pte = pfn_pte(PFN_DOWN(__pa(dummy_mapping)), PAGE_KERNEL); break; #endif
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, prot); break;
}
vaddr = __fix_to_virt(idx); if (HYPERVISOR_update_va_mapping(vaddr, pte, UVMF_INVLPG))
BUG();
#ifdef CONFIG_X86_VSYSCALL_EMULATION /* Replicate changes to map the vsyscall page into the user
pagetable vsyscall mapping. */ if (idx == VSYSCALL_PAGE)
set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte); #endif
}
if (out_frames)
out_frames[i] = virt_to_pfn((void *)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.
*/ staticvoid xen_remap_exchanged_ptes(unsignedlong vaddr, int order, unsignedlong *mfns, unsignedlong first_mfn)
{ unsigned i, limit; unsignedlong mfn;
xen_mc_batch();
limit = 1u << order; for (i = 0; i < limit; i++, vaddr += PAGE_SIZE) { struct multicall_space mcs; unsigned flags;
/* * 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.
*/ staticint xen_exchange_memory(unsignedlong extents_in, unsignedint order_in, unsignedlong *pfns_in, unsignedlong extents_out, unsignedint order_out, unsignedlong *mfns_out, unsignedint address_bits)
{ long rc; int success;
/* 2. Get a new contiguous memory extent. */
out_frame = virt_to_pfn((void *)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);
/* 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);
/* * If we have a contiguous range, just update the pfn itself, * else update pointer to be "next pfn".
*/ if (rmd->contiguous)
(*rmd->pfn)++; else
rmd->pfn++;
rmd.pfn = pfn;
rmd.prot = prot; /* * We use the err_ptr to indicate if there we are doing a contiguous * mapping or a discontiguous mapping.
*/
rmd.contiguous = !err_ptr;
rmd.no_translate = no_translate;
while (nr) { int index = 0; int done = 0; int batch = min(REMAP_BATCH_SIZE, nr);
--> --------------------
--> maximum size reached
--> --------------------
Messung V0.5
¤ Dauer der Verarbeitung: 0.11 Sekunden
(vorverarbeitet)
¤
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.