#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/reboot.h>
-#include <asm/pgalloc.h>
#include "xen-ops.h"
#include "mmu.h"
DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);
+/*
+ * Identity map, in addition to plain kernel map. This needs to be
+ * 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;
+
+#ifdef CONFIG_X86_64
+/* l3 pud for userspace vsyscall mapping */
+static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss;
+#endif /* CONFIG_X86_64 */
+
/*
* Note about cr3 (pagetable base) values:
*
static void xen_load_tls(struct thread_struct *t, unsigned int cpu)
{
- xen_mc_batch();
-
- load_TLS_descriptor(t, cpu, 0);
- load_TLS_descriptor(t, cpu, 1);
- load_TLS_descriptor(t, cpu, 2);
-
- xen_mc_issue(PARAVIRT_LAZY_CPU);
-
/*
* XXX sleazy hack: If we're being called in a lazy-cpu zone,
* it means we're in a context switch, and %gs has just been
* Either way, it has been saved, and the new value will get
* loaded properly. This will go away as soon as Xen has been
* modified to not save/restore %gs for normal hypercalls.
+ *
+ * On x86_64, this hack is not used for %gs, because gs points
+ * to KERNEL_GS_BASE (and uses it for PDA references), so we
+ * must not zero %gs on x86_64
+ *
+ * For x86_64, we need to zero %fs, otherwise we may get an
+ * exception between the new %fs descriptor being loaded and
+ * %fs being effectively cleared at __switch_to().
*/
- if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU)
+ if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) {
+#ifdef CONFIG_X86_32
loadsegment(gs, 0);
+#else
+ loadsegment(fs, 0);
+#endif
+ }
+
+ xen_mc_batch();
+
+ load_TLS_descriptor(t, cpu, 0);
+ load_TLS_descriptor(t, cpu, 1);
+ load_TLS_descriptor(t, cpu, 2);
+
+ xen_mc_issue(PARAVIRT_LAZY_CPU);
}
#ifdef CONFIG_X86_64
x86_write_percpu(xen_current_cr3, (unsigned long)v);
}
-static void xen_write_cr3(unsigned long cr3)
+static void __xen_write_cr3(bool kernel, unsigned long cr3)
{
struct mmuext_op *op;
struct multicall_space mcs;
- unsigned long mfn = pfn_to_mfn(PFN_DOWN(cr3));
+ unsigned long mfn;
- BUG_ON(preemptible());
+ if (cr3)
+ mfn = pfn_to_mfn(PFN_DOWN(cr3));
+ else
+ mfn = 0;
- mcs = xen_mc_entry(sizeof(*op)); /* disables interrupts */
+ WARN_ON(mfn == 0 && kernel);
- /* Update while interrupts are disabled, so its atomic with
- respect to ipis */
- x86_write_percpu(xen_cr3, cr3);
+ mcs = __xen_mc_entry(sizeof(*op));
op = mcs.args;
- op->cmd = MMUEXT_NEW_BASEPTR;
+ op->cmd = kernel ? MMUEXT_NEW_BASEPTR : MMUEXT_NEW_USER_BASEPTR;
op->arg1.mfn = mfn;
MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
- /* Update xen_update_cr3 once the batch has actually
- been submitted. */
- xen_mc_callback(set_current_cr3, (void *)cr3);
+ if (kernel) {
+ x86_write_percpu(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());
+
+ xen_mc_batch(); /* disables interrupts */
+
+ /* Update while interrupts are disabled, so its atomic with
+ respect to ipis */
+ x86_write_percpu(xen_cr3, cr3);
+
+ __xen_write_cr3(true, cr3);
+
+#ifdef CONFIG_X86_64
+ {
+ pgd_t *user_pgd = xen_get_user_pgd(__va(cr3));
+ if (user_pgd)
+ __xen_write_cr3(false, __pa(user_pgd));
+ else
+ __xen_write_cr3(false, 0);
+ }
+#endif
xen_mc_issue(PARAVIRT_LAZY_CPU); /* interrupts restored */
}
xen_alloc_ptpage(mm, pfn, PT_PMD);
}
+static int xen_pgd_alloc(struct mm_struct *mm)
+{
+ pgd_t *pgd = mm->pgd;
+ int ret = 0;
+
+ BUG_ON(PagePinned(virt_to_page(pgd)));
+
+#ifdef CONFIG_X86_64
+ {
+ struct page *page = virt_to_page(pgd);
+ pgd_t *user_pgd;
+
+ BUG_ON(page->private != 0);
+
+ ret = -ENOMEM;
+
+ user_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+ page->private = (unsigned long)user_pgd;
+
+ if (user_pgd != NULL) {
+ user_pgd[pgd_index(VSYSCALL_START)] =
+ __pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE);
+ ret = 0;
+ }
+
+ BUG_ON(PagePinned(virt_to_page(xen_get_user_pgd(pgd))));
+ }
+#endif
+
+ return ret;
+}
+
+static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+#ifdef CONFIG_X86_64
+ pgd_t *user_pgd = xen_get_user_pgd(pgd);
+
+ if (user_pgd)
+ free_page((unsigned long)user_pgd);
+#endif
+}
+
/* This should never happen until we're OK to use struct page */
static void xen_release_ptpage(u32 pfn, unsigned level)
{
pv_mmu_ops.release_pud = xen_release_pud;
#endif
+#ifdef CONFIG_X86_64
+ SetPagePinned(virt_to_page(level3_user_vsyscall));
+#endif
xen_mark_init_mm_pinned();
}
}
__native_set_fixmap(idx, pte);
+
+#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) {
+ unsigned long vaddr = __fix_to_virt(idx);
+ set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte);
+ }
+#endif
}
static const struct pv_info xen_info __initdata = {
.iret = xen_iret,
.irq_enable_sysexit = xen_sysexit,
+#ifdef CONFIG_X86_64
+ .usergs_sysret32 = xen_sysret32,
+ .usergs_sysret64 = xen_sysret64,
+#endif
.load_tr_desc = paravirt_nop,
.set_ldt = xen_set_ldt,
.pte_update = paravirt_nop,
.pte_update_defer = paravirt_nop,
- .pgd_alloc = __paravirt_pgd_alloc,
- .pgd_free = paravirt_nop,
+ .pgd_alloc = xen_pgd_alloc,
+ .pgd_free = xen_pgd_free,
.alloc_pte = xen_alloc_pte_init,
.release_pte = xen_release_pte_init,
BUG();
}
-/*
- * Identity map, in addition to plain kernel map. This needs to be
- * 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;
-
static __init void xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
{
unsigned pmdidx, pteidx;
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_kernel_pgt, PAGE_KERNEL_RO);
set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
/* Switch over */
pgd = init_level4_pgt;
- xen_write_cr3(__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(pgd));
+ xen_mc_issue(PARAVIRT_LAZY_CPU);
reserve_early(__pa(xen_start_info->pt_base),
__pa(xen_start_info->pt_base +
boot_params.hdr.ramdisk_image = xen_start_info->mod_start
? __pa(xen_start_info->mod_start) : 0;
boot_params.hdr.ramdisk_size = xen_start_info->mod_len;
+ boot_params.hdr.cmd_line_ptr = __pa(xen_start_info->cmd_line);
if (!is_initial_xendomain()) {
add_preferred_console("xenboot", 0, NULL);