4 files changed, 64 insertions, 106 deletions

diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index a732bc2b9dfc..f33eef4ebd12 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -142,9 +142,7 @@ static void __init xen_banner(void)
 	struct xen_extraversion extra;
 	HYPERVISOR_xen_version(XENVER_extraversion, &extra);
 
-	pr_info("Booting paravirtualized kernel %son %s\n",
-		xen_feature(XENFEAT_auto_translated_physmap) ?
-			"with PVH extensions " : "", pv_info.name);
+	pr_info("Booting paravirtualized kernel on %s\n", pv_info.name);
 	printk(KERN_INFO "Xen version: %d.%d%s%s\n",
 	       version >> 16, version & 0xffff, extra.extraversion,
 	       xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
@@ -277,31 +275,19 @@ static bool __init xen_check_mwait(void)
 
 static bool __init xen_check_xsave(void)
 {
-	unsigned int err, eax, edx;
+	unsigned int cx, xsave_mask;
 
-	/*
-	 * Xen 4.0 and older accidentally leaked the host XSAVE flag into guest
-	 * view, despite not being able to support guests using the
-	 * functionality. Probe for the actual availability of XSAVE by seeing
-	 * whether xgetbv executes successfully or raises #UD.
-	 */
-	asm volatile("1: .byte 0x0f,0x01,0xd0\n\t" /* xgetbv */
-		     "xor %[err], %[err]\n"
-		     "2:\n\t"
-		     ".pushsection .fixup,\"ax\"\n\t"
-		     "3: movl $1,%[err]\n\t"
-		     "jmp 2b\n\t"
-		     ".popsection\n\t"
-		     _ASM_EXTABLE(1b, 3b)
-		     : [err] "=r" (err), "=a" (eax), "=d" (edx)
-		     : "c" (0));
-
-	return err == 0;
+	cx = cpuid_ecx(1);
+
+	xsave_mask = (1 << (X86_FEATURE_XSAVE % 32)) |
+		     (1 << (X86_FEATURE_OSXSAVE % 32));
+
+	/* Xen will set CR4.OSXSAVE if supported and not disabled by force */
+	return (cx & xsave_mask) == xsave_mask;
 }
 
 static void __init xen_init_capabilities(void)
 {
-	setup_clear_cpu_cap(X86_BUG_SYSRET_SS_ATTRS);
 	setup_force_cpu_cap(X86_FEATURE_XENPV);
 	setup_clear_cpu_cap(X86_FEATURE_DCA);
 	setup_clear_cpu_cap(X86_FEATURE_APERFMPERF);
@@ -317,10 +303,7 @@ static void __init xen_init_capabilities(void)
 	else
 		setup_clear_cpu_cap(X86_FEATURE_MWAIT);
 
-	if (xen_check_xsave()) {
-		setup_force_cpu_cap(X86_FEATURE_XSAVE);
-		setup_force_cpu_cap(X86_FEATURE_OSXSAVE);
-	} else {
+	if (!xen_check_xsave()) {
 		setup_clear_cpu_cap(X86_FEATURE_XSAVE);
 		setup_clear_cpu_cap(X86_FEATURE_OSXSAVE);
 	}
@@ -972,15 +955,10 @@ static void xen_write_msr(unsigned int msr, unsigned low, unsigned high)
 
 void xen_setup_shared_info(void)
 {
-	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
-		set_fixmap(FIX_PARAVIRT_BOOTMAP,
-			   xen_start_info->shared_info);
+	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);
+	HYPERVISOR_shared_info =
+		(struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
 
 #ifndef CONFIG_SMP
 	/* In UP this is as good a place as any to set up shared info */
@@ -988,6 +966,13 @@ void xen_setup_shared_info(void)
 #endif
 
 	xen_setup_mfn_list_list();
+
+	/*
+	 * Now that shared info is set up we can start using routines that
+	 * point to pvclock area.
+	 */
+	if (system_state == SYSTEM_BOOTING)
+		xen_init_time_ops();
 }
 
 /* This is called once we have the cpu_possible_mask */
@@ -1286,8 +1271,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	x86_init.oem.arch_setup = xen_arch_setup;
 	x86_init.oem.banner = xen_banner;
 
-	xen_init_time_ops();
-
 	/*
 	 * Set up some pagetable state before starting to set any ptes.
 	 */
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 5e375a5e815f..3be06f3caf3c 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -42,7 +42,7 @@ xmaddr_t arbitrary_virt_to_machine(void *vaddr)
 }
 EXPORT_SYMBOL_GPL(arbitrary_virt_to_machine);
 
-void xen_flush_tlb_all(void)
+static void xen_flush_tlb_all(void)
 {
 	struct mmuext_op *op;
 	struct multicall_space mcs;
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 9d9ae6650aa1..1f386d7fdf70 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -355,10 +355,8 @@ static pteval_t pte_pfn_to_mfn(pteval_t val)
 		pteval_t flags = val & PTE_FLAGS_MASK;
 		unsigned long mfn;
 
-		if (!xen_feature(XENFEAT_auto_translated_physmap))
-			mfn = __pfn_to_mfn(pfn);
-		else
-			mfn = pfn;
+		mfn = __pfn_to_mfn(pfn);
+
 		/*
 		 * If there's no mfn for the pfn, then just create an
 		 * empty non-present pte.  Unfortunately this loses
@@ -647,9 +645,6 @@ static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd,
 	limit--;
 	BUG_ON(limit >= FIXADDR_TOP);
 
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return 0;
-
 	/*
 	 * 64-bit has a great big hole in the middle of the address
 	 * space, which contains the Xen mappings.  On 32-bit these
@@ -1289,9 +1284,6 @@ static void __init xen_pagetable_cleanhighmap(void)
 
 static void __init xen_pagetable_p2m_setup(void)
 {
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return;
-
 	xen_vmalloc_p2m_tree();
 
 #ifdef CONFIG_X86_64
@@ -1314,8 +1306,7 @@ static void __init xen_pagetable_init(void)
 	xen_build_mfn_list_list();
 
 	/* Remap memory freed due to conflicts with E820 map */
-	if (!xen_feature(XENFEAT_auto_translated_physmap))
-		xen_remap_memory();
+	xen_remap_memory();
 
 	xen_setup_shared_info();
 }
@@ -1925,21 +1916,20 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	/* Zap identity mapping */
 	init_level4_pgt[0] = __pgd(0);
 
-	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);
+	/* 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_k[511] -> level2_fixmap_pgt */
-		convert_pfn_mfn(level3_kernel_pgt);
+	/* L3_i[0] -> level2_ident_pgt */
+	convert_pfn_mfn(level3_ident_pgt);
+	/* L3_k[510] -> level2_kernel_pgt */
+	/* L3_k[511] -> level2_fixmap_pgt */
+	convert_pfn_mfn(level3_kernel_pgt);
+
+	/* L3_k[511][506] -> level1_fixmap_pgt */
+	convert_pfn_mfn(level2_fixmap_pgt);
 
-		/* L3_k[511][506] -> level1_fixmap_pgt */
-		convert_pfn_mfn(level2_fixmap_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);
@@ -1962,34 +1952,30 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	if (i && i < pgd_index(__START_KERNEL_map))
 		init_level4_pgt[i] = ((pgd_t *)xen_start_info->pt_base)[i];
 
-	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);
-		set_page_prot(level1_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);
+	set_page_prot(level1_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);
-	} else
-		native_write_cr3(__pa(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(init_level4_pgt));
+	xen_mc_issue(PARAVIRT_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
@@ -2025,7 +2011,8 @@ static unsigned long __init xen_read_phys_ulong(phys_addr_t addr)
 
 /*
  * Translate a virtual address to a physical one without relying on mapped
- * page tables.
+ * page tables. Don't rely on big pages being aligned in (guest) physical
+ * space!
  */
 static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr)
 {
@@ -2046,7 +2033,7 @@ static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr)
 						       sizeof(pud)));
 	if (!pud_present(pud))
 		return 0;
-	pa = pud_pfn(pud) << PAGE_SHIFT;
+	pa = pud_val(pud) & PTE_PFN_MASK;
 	if (pud_large(pud))
 		return pa + (vaddr & ~PUD_MASK);
 
@@ -2054,7 +2041,7 @@ static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr)
 						       sizeof(pmd)));
 	if (!pmd_present(pmd))
 		return 0;
-	pa = pmd_pfn(pmd) << PAGE_SHIFT;
+	pa = pmd_val(pmd) & PTE_PFN_MASK;
 	if (pmd_large(pmd))
 		return pa + (vaddr & ~PMD_MASK);
 
@@ -2402,9 +2389,6 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 
 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;
@@ -2510,9 +2494,6 @@ void __init xen_init_mmu_ops(void)
 {
 	x86_init.paging.pagetable_init = xen_pagetable_init;
 
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return;
-
 	pv_mmu_ops = xen_mmu_ops;
 
 	memset(dummy_mapping, 0xff, PAGE_SIZE);
@@ -2649,9 +2630,6 @@ int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
 	 * this function are redundant and can be ignored.
 	 */
 
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return 0;
-
 	if (unlikely(order > MAX_CONTIG_ORDER))
 		return -ENOMEM;
 
@@ -2688,9 +2666,6 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
 	int success;
 	unsigned long vstart;
 
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return;
-
 	if (unlikely(order > MAX_CONTIG_ORDER))
 		return;
 
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 090c7eb4dca9..a1895a8e85c1 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -406,7 +406,7 @@ static void __init xen_time_init(void)
 		pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
 }
 
-void __init xen_init_time_ops(void)
+void __ref xen_init_time_ops(void)
 {
 	pv_time_ops = xen_time_ops;