#include <xen/interface/sched.h>
#include <xen/features.h>
#include <xen/page.h>
+#include <xen/hvc-console.h>
#include <asm/paravirt.h>
#include <asm/page.h>
loadsegment(gs, 0);
}
+#ifdef CONFIG_X86_64
+static void xen_load_gs_index(unsigned int idx)
+{
+ if (HYPERVISOR_set_segment_base(SEGBASE_GS_USER_SEL, idx))
+ BUG();
+}
+#endif
+
static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum,
const void *ptr)
{
preempt_enable();
}
-static int cvt_gate_to_trap(int vector, u32 low, u32 high,
+static int cvt_gate_to_trap(int vector, const gate_desc *val,
struct trap_info *info)
{
- u8 type, dpl;
-
- type = (high >> 8) & 0x1f;
- dpl = (high >> 13) & 3;
-
- if (type != 0xf && type != 0xe)
+ if (val->type != 0xf && val->type != 0xe)
return 0;
info->vector = vector;
- info->address = (high & 0xffff0000) | (low & 0x0000ffff);
- info->cs = low >> 16;
- info->flags = dpl;
+ info->address = gate_offset(*val);
+ info->cs = gate_segment(*val);
+ info->flags = val->dpl;
/* interrupt gates clear IF */
- if (type == 0xe)
+ if (val->type == 0xe)
info->flags |= 4;
return 1;
if (p >= start && (p + 8) <= end) {
struct trap_info info[2];
- u32 *desc = (u32 *)g;
info[1].address = 0;
- if (cvt_gate_to_trap(entrynum, desc[0], desc[1], &info[0]))
+ if (cvt_gate_to_trap(entrynum, g, &info[0]))
if (HYPERVISOR_set_trap_table(info))
BUG();
}
{
unsigned in, out, count;
- count = (desc->size+1) / 8;
+ count = (desc->size+1) / sizeof(gate_desc);
BUG_ON(count > 256);
for (in = out = 0; in < count; in++) {
- const u32 *entry = (u32 *)(desc->address + in * 8);
+ gate_desc *entry = (gate_desc*)(desc->address) + in;
- if (cvt_gate_to_trap(in, entry[0], entry[1], &traps[out]))
+ if (cvt_gate_to_trap(in, entry, &traps[out]))
out++;
}
traps[out].address = 0;
static __init void xen_pagetable_setup_start(pgd_t *base)
{
-#ifdef CONFIG_X86_32
- pgd_t *xen_pgd = (pgd_t *)xen_start_info->pt_base;
- int i;
-
- init_mm.pgd = base;
- /*
- * copy top-level of Xen-supplied pagetable into place. This
- * is a stand-in while we copy the pmd pages.
- */
- memcpy(base, xen_pgd, PTRS_PER_PGD * sizeof(pgd_t));
-
- /*
- * For PAE, need to allocate new pmds, rather than
- * share Xen's, since Xen doesn't like pmd's being
- * shared between address spaces.
- */
- for (i = 0; i < PTRS_PER_PGD; i++) {
- if (pgd_val_ma(xen_pgd[i]) & _PAGE_PRESENT) {
- pmd_t *pmd = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE);
-
- memcpy(pmd, (void *)pgd_page_vaddr(xen_pgd[i]),
- PAGE_SIZE);
-
- make_lowmem_page_readonly(pmd);
-
- set_pgd(&base[i], __pgd(1 + __pa(pmd)));
- } else
- pgd_clear(&base[i]);
- }
-
- /* make sure zero_page is mapped RO so we can use it in pagetables */
- make_lowmem_page_readonly(empty_zero_page);
- make_lowmem_page_readonly(base);
- /*
- * Switch to new pagetable. This is done before
- * pagetable_init has done anything so that the new pages
- * added to the table can be prepared properly for Xen.
- */
- xen_write_cr3(__pa(base));
-
- /* Unpin initial Xen pagetable */
- pin_pagetable_pfn(MMUEXT_UNPIN_TABLE,
- PFN_DOWN(__pa(xen_start_info->pt_base)));
-#endif /* CONFIG_X86_32 */
}
void xen_setup_shared_info(void)
{
if (!xen_feature(XENFEAT_auto_translated_physmap)) {
- unsigned long addr = fix_to_virt(FIX_PARAVIRT_BOOTMAP);
-
- /*
- * Create a mapping for the shared info page.
- * Should be set_fixmap(), but shared_info is a machine
- * address with no corresponding pseudo-phys address.
- */
- set_pte_mfn(addr,
- PFN_DOWN(xen_start_info->shared_info),
- PAGE_KERNEL);
-
- HYPERVISOR_shared_info = (struct shared_info *)addr;
+ set_fixmap(FIX_PARAVIRT_BOOTMAP,
+ xen_start_info->shared_info);
+
+ HYPERVISOR_shared_info =
+ (struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
} else
HYPERVISOR_shared_info =
(struct shared_info *)__va(xen_start_info->shared_info);
static __init void xen_pagetable_setup_done(pgd_t *base)
{
- /* This will work as long as patching hasn't happened yet
- (which it hasn't) */
- pv_mmu_ops.alloc_pte = xen_alloc_pte;
- pv_mmu_ops.alloc_pmd = xen_alloc_pmd;
- pv_mmu_ops.release_pte = xen_release_pte;
- pv_mmu_ops.release_pmd = xen_release_pmd;
-#if PAGETABLE_LEVELS == 4
- pv_mmu_ops.alloc_pud = xen_alloc_pud;
- pv_mmu_ops.release_pud = xen_release_pud;
-#endif
-
- pv_mmu_ops.set_pte = xen_set_pte;
-
xen_setup_shared_info();
-
-#ifdef CONFIG_X86_32
- /* Actually pin the pagetable down, but we can't set PG_pinned
- yet because the page structures don't exist yet. */
- pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(base)));
-#endif
}
static __init void xen_post_allocator_init(void)
{
+ pv_mmu_ops.set_pte = xen_set_pte;
pv_mmu_ops.set_pmd = xen_set_pmd;
pv_mmu_ops.set_pud = xen_set_pud;
#if PAGETABLE_LEVELS == 4
pv_mmu_ops.set_pgd = xen_set_pgd;
#endif
+ /* This will work as long as patching hasn't happened yet
+ (which it hasn't) */
+ pv_mmu_ops.alloc_pte = xen_alloc_pte;
+ pv_mmu_ops.alloc_pmd = xen_alloc_pmd;
+ pv_mmu_ops.release_pte = xen_release_pte;
+ pv_mmu_ops.release_pmd = xen_release_pmd;
+#if PAGETABLE_LEVELS == 4
+ pv_mmu_ops.alloc_pud = xen_alloc_pud;
+ pv_mmu_ops.release_pud = xen_release_pud;
+#endif
+
xen_mark_init_mm_pinned();
}
/* xen_vcpu_setup managed to place the vcpu_info within the
percpu area for all cpus, so make use of it */
+#ifdef CONFIG_X86_32
if (have_vcpu_info_placement) {
printk(KERN_INFO "Xen: using vcpu_info placement\n");
pv_irq_ops.irq_enable = xen_irq_enable_direct;
pv_mmu_ops.read_cr2 = xen_read_cr2_direct;
}
+#endif
}
static unsigned xen_patch(u8 type, u16 clobbers, void *insnbuf,
goto patch_site
switch (type) {
+#ifdef CONFIG_X86_32
SITE(pv_irq_ops, irq_enable);
SITE(pv_irq_ops, irq_disable);
SITE(pv_irq_ops, save_fl);
SITE(pv_irq_ops, restore_fl);
+#endif /* CONFIG_X86_32 */
#undef SITE
patch_site:
#ifdef CONFIG_X86_F00F_BUG
case FIX_F00F_IDT:
#endif
+#ifdef CONFIG_X86_32
case FIX_WP_TEST:
case FIX_VDSO:
+ case FIX_KMAP_BEGIN ... FIX_KMAP_END:
+#else
+ case VSYSCALL_LAST_PAGE ... VSYSCALL_FIRST_PAGE:
+#endif
#ifdef CONFIG_X86_LOCAL_APIC
case FIX_APIC_BASE: /* maps dummy local APIC */
#endif
.load_gdt = xen_load_gdt,
.load_idt = xen_load_idt,
.load_tls = xen_load_tls,
+#ifdef CONFIG_X86_64
+ .load_gs_index = xen_load_gs_index,
+#endif
.store_gdt = native_store_gdt,
.store_idt = native_store_idt,
.set_iopl_mask = xen_set_iopl_mask,
.io_delay = xen_io_delay,
+ /* Xen takes care of %gs when switching to usermode for us */
+ .swapgs = paravirt_nop,
+
.lazy_mode = {
.enter = paravirt_enter_lazy_cpu,
.leave = xen_leave_lazy,
},
};
+static void __init __xen_init_IRQ(void)
+{
+#ifdef CONFIG_X86_64
+ int i;
+
+ /* Create identity vector->irq map */
+ for(i = 0; i < NR_VECTORS; i++) {
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ per_cpu(vector_irq, cpu)[i] = i;
+ }
+#endif /* CONFIG_X86_64 */
+
+ xen_init_IRQ();
+}
+
static const struct pv_irq_ops xen_irq_ops __initdata = {
- .init_IRQ = xen_init_IRQ,
+ .init_IRQ = __xen_init_IRQ,
.save_fl = xen_save_fl,
.restore_fl = xen_restore_fl,
.irq_disable = xen_irq_disable,
.safe_halt = xen_safe_halt,
.halt = xen_halt,
#ifdef CONFIG_X86_64
- .adjust_exception_frame = paravirt_nop,
+ .adjust_exception_frame = xen_adjust_exception_frame,
#endif
};
.kmap_atomic_pte = xen_kmap_atomic_pte,
#endif
+#ifdef CONFIG_X86_64
+ .set_pte = xen_set_pte,
+#else
.set_pte = xen_set_pte_init,
+#endif
.set_pte_at = xen_set_pte_at,
.set_pmd = xen_set_pmd_hyper,
#endif /* CONFIG_X86_32 */
}
+/*
+ * Like __va(), but returns address in the kernel mapping (which is
+ * all we have until the physical memory mapping has been set up.
+ */
+static void *__ka(phys_addr_t paddr)
+{
+#ifdef CONFIG_X86_64
+ return (void *)(paddr + __START_KERNEL_map);
+#else
+ return __va(paddr);
+#endif
+}
+
+/* Convert a machine address to physical address */
+static unsigned long m2p(phys_addr_t maddr)
+{
+ phys_addr_t paddr;
+
+ maddr &= PTE_MASK;
+ paddr = mfn_to_pfn(maddr >> PAGE_SHIFT) << PAGE_SHIFT;
+
+ return paddr;
+}
+
+/* Convert a machine address to kernel virtual */
+static void *m2v(phys_addr_t maddr)
+{
+ return __ka(m2p(maddr));
+}
+
+#ifdef CONFIG_X86_64
+static void walk(pgd_t *pgd, unsigned long addr)
+{
+ unsigned l4idx = pgd_index(addr);
+ unsigned l3idx = pud_index(addr);
+ unsigned l2idx = pmd_index(addr);
+ unsigned l1idx = pte_index(addr);
+ pgd_t l4;
+ pud_t l3;
+ pmd_t l2;
+ pte_t l1;
+
+ xen_raw_printk("walk %p, %lx -> %d %d %d %d\n",
+ pgd, addr, l4idx, l3idx, l2idx, l1idx);
+
+ l4 = pgd[l4idx];
+ xen_raw_printk(" l4: %016lx\n", l4.pgd);
+ xen_raw_printk(" %016lx\n", pgd_val(l4));
+
+ l3 = ((pud_t *)(m2v(l4.pgd)))[l3idx];
+ xen_raw_printk(" l3: %016lx\n", l3.pud);
+ xen_raw_printk(" %016lx\n", pud_val(l3));
+
+ l2 = ((pmd_t *)(m2v(l3.pud)))[l2idx];
+ xen_raw_printk(" l2: %016lx\n", l2.pmd);
+ xen_raw_printk(" %016lx\n", pmd_val(l2));
+
+ l1 = ((pte_t *)(m2v(l2.pmd)))[l1idx];
+ xen_raw_printk(" l1: %016lx\n", l1.pte);
+ xen_raw_printk(" %016lx\n", pte_val(l1));
+}
+#endif
+
+static void set_page_prot(void *addr, pgprot_t prot)
+{
+ unsigned long pfn = __pa(addr) >> PAGE_SHIFT;
+ pte_t pte = pfn_pte(pfn, prot);
+
+ xen_raw_printk("addr=%p pfn=%lx mfn=%lx prot=%016llx pte=%016llx\n",
+ addr, pfn, get_phys_to_machine(pfn),
+ pgprot_val(prot), pte.pte);
+
+ if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, 0))
+ 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;
+ unsigned ident_pte;
+ unsigned long pfn;
+
+ ident_pte = 0;
+ pfn = 0;
+ for(pmdidx = 0; pmdidx < PTRS_PER_PMD && pfn < max_pfn; pmdidx++) {
+ pte_t *pte_page;
+
+ /* Reuse or allocate a page of ptes */
+ if (pmd_present(pmd[pmdidx]))
+ pte_page = m2v(pmd[pmdidx].pmd);
+ else {
+ /* Check for free pte pages */
+ if (ident_pte == ARRAY_SIZE(level1_ident_pgt))
+ break;
+
+ pte_page = &level1_ident_pgt[ident_pte];
+ ident_pte += PTRS_PER_PTE;
+
+ pmd[pmdidx] = __pmd(__pa(pte_page) | _PAGE_TABLE);
+ }
+
+ /* Install mappings */
+ for(pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) {
+ pte_t pte;
+
+ if (pfn > max_pfn_mapped)
+ max_pfn_mapped = pfn;
+
+ if (!pte_none(pte_page[pteidx]))
+ continue;
+
+ pte = pfn_pte(pfn, PAGE_KERNEL_EXEC);
+ pte_page[pteidx] = pte;
+ }
+ }
+
+ for(pteidx = 0; pteidx < ident_pte; pteidx += PTRS_PER_PTE)
+ set_page_prot(&level1_ident_pgt[pteidx], PAGE_KERNEL_RO);
+
+ set_page_prot(pmd, PAGE_KERNEL_RO);
+}
+
+#ifdef CONFIG_X86_64
+static void convert_pfn_mfn(void *v)
+{
+ pte_t *pte = v;
+ int i;
+
+ /* 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);
+}
+
+/*
+ * Set up the inital 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, level2_kernel_pgt and level2_fixmap_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.
+ */
+static __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
+{
+ pud_t *l3;
+ pmd_t *l2;
+
+ /* Zap identity mapping */
+ init_level4_pgt[0] = __pgd(0);
+
+ /* Pre-constructed entries are in pfn, so convert to mfn */
+ convert_pfn_mfn(init_level4_pgt);
+ convert_pfn_mfn(level3_ident_pgt);
+ convert_pfn_mfn(level3_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);
+
+ 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);
+
+ /* 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(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)));
+
+ /* Switch over */
+ pgd = init_level4_pgt;
+ xen_write_cr3(__pa(pgd));
+
+ reserve_early(__pa(xen_start_info->pt_base),
+ __pa(xen_start_info->pt_base +
+ xen_start_info->nr_pt_frames * PAGE_SIZE),
+ "XEN PAGETABLES");
+
+ return pgd;
+}
+#else /* !CONFIG_X86_64 */
+static pmd_t level2_kernel_pgt[PTRS_PER_PMD] __page_aligned_bss;
+
+static __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
+{
+ pmd_t *kernel_pmd;
+
+ init_pg_tables_start = __pa(pgd);
+ init_pg_tables_end = __pa(pgd) + xen_start_info->nr_pt_frames*PAGE_SIZE;
+ max_pfn_mapped = PFN_DOWN(init_pg_tables_end + 512*1024);
+
+ kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
+ memcpy(level2_kernel_pgt, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD);
+
+ xen_map_identity_early(level2_kernel_pgt, max_pfn);
+
+ memcpy(swapper_pg_dir, pgd, sizeof(pgd_t) * PTRS_PER_PGD);
+ set_pgd(&swapper_pg_dir[KERNEL_PGD_BOUNDARY],
+ __pgd(__pa(level2_kernel_pgt) | _PAGE_PRESENT));
+
+ set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
+ set_page_prot(swapper_pg_dir, PAGE_KERNEL_RO);
+ set_page_prot(empty_zero_page, PAGE_KERNEL_RO);
+
+ pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
+
+ xen_write_cr3(__pa(swapper_pg_dir));
+
+ pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir)));
+
+ return swapper_pg_dir;
+}
+#endif /* CONFIG_X86_64 */
+
/* First C function to be called on Xen boot */
asmlinkage void __init xen_start_kernel(void)
{
#ifdef CONFIG_X86_64
/* Disable until direct per-cpu data access. */
have_vcpu_info_placement = 0;
+ x86_64_init_pda();
#endif
xen_smp_init();
pgd = (pgd_t *)xen_start_info->pt_base;
-#ifdef CONFIG_X86_32
- init_pg_tables_start = __pa(pgd);
- init_pg_tables_end = __pa(pgd) + xen_start_info->nr_pt_frames*PAGE_SIZE;
- max_pfn_mapped = (init_pg_tables_end + 512*1024) >> PAGE_SHIFT;
-#endif
-
- init_mm.pgd = pgd; /* use the Xen pagetables to start */
-
- /* keep using Xen gdt for now; no urgent need to change it */
-
- x86_write_percpu(xen_cr3, __pa(pgd));
- x86_write_percpu(xen_current_cr3, __pa(pgd));
+ /* Prevent unwanted bits from being set in PTEs. */
+ __supported_pte_mask &= ~_PAGE_GLOBAL;
+ if (!is_initial_xendomain())
+ __supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
/* Don't do the full vcpu_info placement stuff until we have a
possible map and a non-dummy shared_info. */
per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0];
+ xen_raw_console_write("mapping kernel into physical memory\n");
+ pgd = xen_setup_kernel_pagetable(pgd, xen_start_info->nr_pages);
+
+ init_mm.pgd = pgd;
+
+ /* keep using Xen gdt for now; no urgent need to change it */
+
pv_info.kernel_rpl = 1;
if (xen_feature(XENFEAT_supervisor_mode_kernel))
pv_info.kernel_rpl = 0;
- /* Prevent unwanted bits from being set in PTEs. */
- __supported_pte_mask &= ~_PAGE_GLOBAL;
- if (!is_initial_xendomain())
- __supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
-
/* set the limit of our address space */
xen_reserve_top();
+#ifdef CONFIG_X86_32
/* set up basic CPUID stuff */
cpu_detect(&new_cpu_data);
-#ifdef CONFIG_X86_32
new_cpu_data.hard_math = 1;
-#endif
new_cpu_data.x86_capability[0] = cpuid_edx(1);
+#endif
/* Poke various useful things into boot_params */
boot_params.hdr.type_of_loader = (9 << 4) | 0;
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);
add_preferred_console("hvc", 0, NULL);
}
+ xen_raw_console_write("about to get started...\n");
+
+#if 0
+ xen_raw_printk("&boot_params=%p __pa(&boot_params)=%lx __va(__pa(&boot_params))=%lx\n",
+ &boot_params, __pa_symbol(&boot_params),
+ __va(__pa_symbol(&boot_params)));
+
+ walk(pgd, &boot_params);
+ walk(pgd, __va(__pa(&boot_params)));
+#endif
+
/* Start the world */
#ifdef CONFIG_X86_32
i386_start_kernel();
#else
- x86_64_start_kernel((char *)&boot_params);
+ x86_64_start_reservations((char *)__pa_symbol(&boot_params));
#endif
}