return val;
}
- static pteval_t xen_pte_val(pte_t pte)
+ __visible pteval_t xen_pte_val(pte_t pte)
{
pteval_t pteval = pte.pte;
#if 0
}
PV_CALLEE_SAVE_REGS_THUNK(xen_pte_val);
- static pgdval_t xen_pgd_val(pgd_t pgd)
+ __visible pgdval_t xen_pgd_val(pgd_t pgd)
{
return pte_mfn_to_pfn(pgd.pgd);
}
WARN_ON(pat != 0x0007010600070106ull);
}
- static pte_t xen_make_pte(pteval_t pte)
+ __visible pte_t xen_make_pte(pteval_t pte)
{
phys_addr_t addr = (pte & PTE_PFN_MASK);
#if 0
}
PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte);
- static pgd_t xen_make_pgd(pgdval_t pgd)
+ __visible 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);
- static pmdval_t xen_pmd_val(pmd_t pmd)
+ __visible pmdval_t xen_pmd_val(pmd_t pmd)
{
return pte_mfn_to_pfn(pmd.pmd);
}
}
#endif /* CONFIG_X86_PAE */
- static pmd_t xen_make_pmd(pmdval_t pmd)
+ __visible 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
- static pudval_t xen_pud_val(pud_t pud)
+ __visible pudval_t xen_pud_val(pud_t pud)
{
return pte_mfn_to_pfn(pud.pud);
}
PV_CALLEE_SAVE_REGS_THUNK(xen_pud_val);
- static pud_t xen_make_pud(pudval_t pud)
+ __visible pud_t xen_make_pud(pudval_t pud)
{
pud = pte_pfn_to_mfn(pud);
* instead of somewhere later and be confusing. */
xen_mc_flush();
}
-#endif
-static void __init xen_pagetable_init(void)
+static void __init xen_pagetable_p2m_copy(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;
- }
+ unsigned long new_mfn_list;
+
+ if (xen_feature(XENFEAT_auto_translated_physmap))
+ return;
+
+ size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
+
+ new_mfn_list = xen_revector_p2m_tree();
+ /* No memory or already called. */
+ if (!new_mfn_list || new_mfn_list == xen_start_info->mfn_list)
+ return;
+
+ /* 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;
+
/* 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
* anything at this stage. */
xen_cleanhighmap(MODULES_VADDR, roundup(MODULES_VADDR, PUD_SIZE) - 1);
#endif
-skip:
+}
+#endif
+
+static void __init xen_pagetable_init(void)
+{
+ paging_init();
+ xen_setup_shared_info();
+#ifdef CONFIG_X86_64
+ xen_pagetable_p2m_copy();
#endif
xen_post_allocator_init();
}
unsigned long pfn = __pa(addr) >> PAGE_SHIFT;
pte_t pte = pfn_pte(pfn, prot);
+ /* For PVH no need to set R/O or R/W to pin them or unpin them. */
+ if (xen_feature(XENFEAT_auto_translated_physmap))
+ return;
+
if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, flags))
BUG();
}
* 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.
+ * NOTE: for PVH, the page tables are native.
*/
void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
{
/* 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);
-
+ if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+ /* 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);
copy_page(level2_fixmap_pgt, l2);
/* Note that we don't do anything with level1_fixmap_pgt which
* we don't need. */
+ if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+ /* 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);
+
+ /* Pin down new L4 */
+ pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE,
+ PFN_DOWN(__pa_symbol(init_level4_pgt)));
+
+ /* Unpin Xen-provided one */
+ pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
- /* 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);
-
- /* Pin down new L4 */
- pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE,
- PFN_DOWN(__pa_symbol(init_level4_pgt)));
-
- /* Unpin Xen-provided one */
- pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
-
- /*
- * 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_level4_pgt));
- xen_mc_issue(PARAVIRT_LAZY_CPU);
+ /*
+ * 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_level4_pgt));
+ xen_mc_issue(PARAVIRT_LAZY_CPU);
+ } else
+ native_write_cr3(__pa(init_level4_pgt));
/* 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
static void __init xen_post_allocator_init(void)
{
+ if (xen_feature(XENFEAT_auto_translated_physmap))
+ return;
+
pv_mmu_ops.set_pte = xen_set_pte;
pv_mmu_ops.set_pmd = xen_set_pmd;
pv_mmu_ops.set_pud = xen_set_pud;
void __init xen_init_mmu_ops(void)
{
x86_init.paging.pagetable_init = xen_pagetable_init;
+
+ /* Optimization - we can use the HVM one but it has no idea which
+ * VCPUs are descheduled - which means that it will needlessly IPI
+ * them. Xen knows so let it do the job.
+ */
+ if (xen_feature(XENFEAT_auto_translated_physmap)) {
+ pv_mmu_ops.flush_tlb_others = xen_flush_tlb_others;
+ return;
+ }
pv_mmu_ops = xen_mmu_ops;
memset(dummy_mapping, 0xff, PAGE_SIZE);
#include <xen/interface/memory.h>
#include <xen/interface/physdev.h>
#include <xen/features.h>
+#include "mmu.h"
#include "xen-ops.h"
#include "vdso.h"
extern const char xen_hypervisor_callback[];
extern const char xen_failsafe_callback[];
#ifdef CONFIG_X86_64
- extern const char nmi[];
+ extern asmlinkage void nmi(void);
#endif
extern void xen_sysenter_target(void);
extern void xen_syscall_target(void);
memblock_reserve(start, size);
+ if (xen_feature(XENFEAT_auto_translated_physmap))
+ return;
+
xen_max_p2m_pfn = PFN_DOWN(start + size);
for (pfn = PFN_DOWN(start); pfn < xen_max_p2m_pfn; pfn++) {
unsigned long mfn = pfn_to_mfn(pfn);
.domid = DOMID_SELF
};
unsigned long len = 0;
+ int xlated_phys = xen_feature(XENFEAT_auto_translated_physmap);
unsigned long pfn;
int ret;
continue;
frame = mfn;
} else {
- if (mfn != INVALID_P2M_ENTRY)
+ if (!xlated_phys && mfn != INVALID_P2M_ENTRY)
continue;
frame = pfn;
}
static unsigned long __init xen_release_chunk(unsigned long start,
unsigned long end)
{
+ /*
+ * Xen already ballooned out the E820 non RAM regions for us
+ * and set them up properly in EPT.
+ */
+ if (xen_feature(XENFEAT_auto_translated_physmap))
+ return end - start;
+
return xen_do_chunk(start, end, true);
}
* (except for the ISA region which must be 1:1 mapped) to
* release the refcounts (in Xen) on the original frames.
*/
- for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++) {
+
+ /*
+ * PVH E820 matches the hypervisor's P2M which means we need to
+ * account for the proper values of *release and *identity.
+ */
+ for (pfn = start_pfn; !xen_feature(XENFEAT_auto_translated_physmap) &&
+ pfn <= max_pfn_mapped && pfn < end_pfn; pfn++) {
pte_t pte = __pte_ma(0);
if (pfn < PFN_UP(ISA_END_ADDRESS))
void xen_enable_nmi(void)
{
#ifdef CONFIG_X86_64
- if (register_callback(CALLBACKTYPE_nmi, nmi))
+ if (register_callback(CALLBACKTYPE_nmi, (char *)nmi))
BUG();
#endif
}
-void __init xen_arch_setup(void)
+void __init xen_pvmmu_arch_setup(void)
{
- xen_panic_handler_init();
-
HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_4gb_segments);
HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_writable_pagetables);
- if (!xen_feature(XENFEAT_auto_translated_physmap))
- HYPERVISOR_vm_assist(VMASST_CMD_enable,
- VMASST_TYPE_pae_extended_cr3);
+ HYPERVISOR_vm_assist(VMASST_CMD_enable,
+ VMASST_TYPE_pae_extended_cr3);
if (register_callback(CALLBACKTYPE_event, xen_hypervisor_callback) ||
register_callback(CALLBACKTYPE_failsafe, xen_failsafe_callback))
xen_enable_sysenter();
xen_enable_syscall();
xen_enable_nmi();
+}
+
+/* This function is not called for HVM domains */
+void __init xen_arch_setup(void)
+{
+ xen_panic_handler_init();
+ if (!xen_feature(XENFEAT_auto_translated_physmap))
+ xen_pvmmu_arch_setup();
+
#ifdef CONFIG_ACPI
if (!(xen_start_info->flags & SIF_INITDOMAIN)) {
printk(KERN_INFO "ACPI in unprivileged domain disabled\n");