mm, x86/vdso: Special IO mapping improvements

index 66df22b2e0c9..fdcc04020636 100644
@@ -4,7 +4,7 @@
 #include <linux/clocksource.h>
 #include <asm/pvclock-abi.h>
 
-#ifdef CONFIG_PARAVIRT_CLOCK
+#ifdef CONFIG_KVM_GUEST
 extern struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void);
 #else
 static inline struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void)

index f8d1492a114f..c88e48a3c155 100644
@@ -568,10 +568,26 @@ static inline void clear_tlb_flush_pending(struct mm_struct *mm)
 }
 #endif
 
-struct vm_special_mapping
-{
-	const char *name;
+struct vm_fault;
+
+struct vm_special_mapping {
+	const char *name;	/* The name, e.g. "[vdso]". */
+
+	/*
+	 * If .fault is not provided, this points to a
+	 * NULL-terminated array of pages that back the special mapping.
+	 *
+	 * This must not be NULL unless .fault is provided.
+	 */
 	struct page **pages;
+
+	/*
+	 * If non-NULL, then this is called to resolve page faults
+	 * on the special mapping.  If used, .pages is not checked.
+	 */
+	int (*fault)(const struct vm_special_mapping *sm,
+		     struct vm_area_struct *vma,
+		     struct vm_fault *vmf);
 };
 
 enum tlb_flush_reason {

index 2ce04a649f6b..f717453b1a57 100644
@@ -3030,11 +3030,16 @@ static int special_mapping_fault(struct vm_area_struct *vma,
 	pgoff_t pgoff;
 	struct page **pages;
 
-	if (vma->vm_ops == &legacy_special_mapping_vmops)
+	if (vma->vm_ops == &legacy_special_mapping_vmops) {
 		pages = vma->vm_private_data;
-	else
-		pages = ((struct vm_special_mapping *)vma->vm_private_data)->
-			pages;
+	} else {
+		struct vm_special_mapping *sm = vma->vm_private_data;
+
+		if (sm->fault)
+			return sm->fault(sm, vma, vmf);
+
+		pages = sm->pages;
+	}
 
 	for (pgoff = vmf->pgoff; pgoff && *pages; ++pages)
 		pgoff--;

index 00bad7793788..87ef1d7730ba 100644
@@ -2080,6 +2080,8 @@ int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
 int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
 int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn);
+int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
+			unsigned long pfn, pgprot_t pgprot);
 int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn);
 int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len);

index c387430f06c3..a29f0b90fc56 100644
@@ -1564,8 +1564,29 @@ out:
 int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn)
 {
+	return vm_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot);
+}
+EXPORT_SYMBOL(vm_insert_pfn);
+
+/**
+ * vm_insert_pfn_prot - insert single pfn into user vma with specified pgprot
+ * @vma: user vma to map to
+ * @addr: target user address of this page
+ * @pfn: source kernel pfn
+ * @pgprot: pgprot flags for the inserted page
+ *
+ * This is exactly like vm_insert_pfn, except that it allows drivers to
+ * to override pgprot on a per-page basis.
+ *
+ * This only makes sense for IO mappings, and it makes no sense for
+ * cow mappings.  In general, using multiple vmas is preferable;
+ * vm_insert_pfn_prot should only be used if using multiple VMAs is
+ * impractical.
+ */
+int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
+			unsigned long pfn, pgprot_t pgprot)
+{
 	int ret;
-	pgprot_t pgprot = vma->vm_page_prot;
 	/*
 	 * Technically, architectures with pte_special can avoid all these
 	 * restrictions (same for remap_pfn_range).  However we would like

@@ -1587,7 +1608,7 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 
 	return ret;
 }
-EXPORT_SYMBOL(vm_insert_pfn);
+EXPORT_SYMBOL(vm_insert_pfn_prot);
 
 int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn)

index b8f69e264ac4..80b021067bd6 100644
@@ -121,6 +121,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 
 	text_start = addr - image->sym_vvar_start;
 	current->mm->context.vdso = (void __user *)text_start;
+	current->mm->context.vdso_image = image;
 
 	/*
 	 * MAYWRITE to allow gdb to COW and set breakpoints

index 55234d5e7160..1ea0baef1175 100644
@@ -19,7 +19,8 @@ typedef struct {
 #endif
 
 	struct mutex lock;
-	void __user *vdso;
+	void __user *vdso;			/* vdso base address */
+	const struct vdso_image *vdso_image;	/* vdso image in use */
 
 	atomic_t perf_rdpmc_allowed;	/* nonzero if rdpmc is allowed */
 } mm_context_t;

index 0224987556ce..abe961c7c71c 100644
@@ -150,16 +150,9 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 	}
 	fprintf(outfile, "\n};\n\n");
 
-	fprintf(outfile, "static struct page *pages[%lu];\n\n",
-		mapping_size / 4096);
-
 	fprintf(outfile, "const struct vdso_image %s = {\n", name);
 	fprintf(outfile, "\t.data = raw_data,\n");
 	fprintf(outfile, "\t.size = %lu,\n", mapping_size);
-	fprintf(outfile, "\t.text_mapping = {\n");
-	fprintf(outfile, "\t\t.name = \"[vdso]\",\n");
-	fprintf(outfile, "\t\t.pages = pages,\n");
-	fprintf(outfile, "\t},\n");
 	if (alt_sec) {
 		fprintf(outfile, "\t.alt = %lu,\n",
 			(unsigned long)GET_LE(&alt_sec->sh_offset));

index 80b021067bd6..eb50d7c1f161 100644
@@ -27,13 +27,7 @@ unsigned int __read_mostly vdso64_enabled = 1;
 
 void __init init_vdso_image(const struct vdso_image *image)
 {
-	int i;
-	int npages = (image->size) / PAGE_SIZE;
-
 	BUG_ON(image->size % PAGE_SIZE != 0);
-	for (i = 0; i < npages; i++)
-		image->text_mapping.pages[i] =
-			virt_to_page(image->data + i*PAGE_SIZE);
 
 	apply_alternatives((struct alt_instr *)(image->data + image->alt),
 			   (struct alt_instr *)(image->data + image->alt +

@@ -90,6 +84,24 @@ static unsigned long vdso_addr(unsigned long start, unsigned len)
 #endif
 }
 
+static int vdso_fault(const struct vm_special_mapping *sm,
+		      struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	const struct vdso_image *image = vma->vm_mm->context.vdso_image;
+
+	if (!image || (vmf->pgoff << PAGE_SHIFT) >= image->size)
+		return VM_FAULT_SIGBUS;
+
+	vmf->page = virt_to_page(image->data + (vmf->pgoff << PAGE_SHIFT));
+	get_page(vmf->page);
+	return 0;
+}
+
+static const struct vm_special_mapping text_mapping = {
+	.name = "[vdso]",
+	.fault = vdso_fault,
+};
+
 static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 {
 	struct mm_struct *mm = current->mm;

@@ -131,7 +143,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 				       image->size,
 				       VM_READ|VM_EXEC|
 				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
-				       &image->text_mapping);
+				       &text_mapping);
 
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);

index deabaf9759b6..43dc55be524e 100644
@@ -13,9 +13,6 @@ struct vdso_image {
 	void *data;
 	unsigned long size;   /* Always a multiple of PAGE_SIZE */
 
-	/* text_mapping.pages is big enough for data/size page pointers */
-	struct vm_special_mapping text_mapping;
-
 	unsigned long alt, alt_len;
 
 	long sym_vvar_start;  /* Negative offset to the vvar area */

index eb50d7c1f161..4b5461ba4f6b 100644
@@ -102,18 +102,69 @@ static const struct vm_special_mapping text_mapping = {
 	.fault = vdso_fault,
 };
 
+static int vvar_fault(const struct vm_special_mapping *sm,
+		      struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	const struct vdso_image *image = vma->vm_mm->context.vdso_image;
+	long sym_offset;
+	int ret = -EFAULT;
+
+	if (!image)
+		return VM_FAULT_SIGBUS;
+
+	sym_offset = (long)(vmf->pgoff << PAGE_SHIFT) +
+		image->sym_vvar_start;
+
+	/*
+	 * Sanity check: a symbol offset of zero means that the page
+	 * does not exist for this vdso image, not that the page is at
+	 * offset zero relative to the text mapping.  This should be
+	 * impossible here, because sym_offset should only be zero for
+	 * the page past the end of the vvar mapping.
+	 */
+	if (sym_offset == 0)
+		return VM_FAULT_SIGBUS;
+
+	if (sym_offset == image->sym_vvar_page) {
+		ret = vm_insert_pfn(vma, (unsigned long)vmf->virtual_address,
+				    __pa_symbol(&__vvar_page) >> PAGE_SHIFT);
+	} else if (sym_offset == image->sym_hpet_page) {
+#ifdef CONFIG_HPET_TIMER
+		if (hpet_address) {
+			ret = vm_insert_pfn_prot(
+				vma,
+				(unsigned long)vmf->virtual_address,
+				hpet_address >> PAGE_SHIFT,
+				pgprot_noncached(PAGE_READONLY));
+		}
+#endif
+	} else if (sym_offset == image->sym_pvclock_page) {
+		struct pvclock_vsyscall_time_info *pvti =
+			pvclock_pvti_cpu0_va();
+		if (pvti) {
+			ret = vm_insert_pfn(
+				vma,
+				(unsigned long)vmf->virtual_address,
+				__pa(pvti) >> PAGE_SHIFT);
+		}
+	}
+
+	if (ret == 0 || ret == -EBUSY)
+		return VM_FAULT_NOPAGE;
+
+	return VM_FAULT_SIGBUS;
+}
+
 static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	unsigned long addr, text_start;
 	int ret = 0;
-	static struct page *no_pages[] = {NULL};
-	static struct vm_special_mapping vvar_mapping = {
+	static const struct vm_special_mapping vvar_mapping = {
 		.name = "[vvar]",
-		.pages = no_pages,
+		.fault = vvar_fault,
 	};
-	struct pvclock_vsyscall_time_info *pvti;
 
 	if (calculate_addr) {
 		addr = vdso_addr(current->mm->start_stack,

@@ -153,7 +204,8 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 	vma = _install_special_mapping(mm,
 				       addr,
 				       -image->sym_vvar_start,
-				       VM_READ|VM_MAYREAD,
+				       VM_READ|VM_MAYREAD|VM_IO|VM_DONTDUMP|
+				       VM_PFNMAP,
 				       &vvar_mapping);
 
 	if (IS_ERR(vma)) {

@@ -161,41 +213,6 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 		goto up_fail;
 	}
 
-	if (image->sym_vvar_page)
-		ret = remap_pfn_range(vma,
-				      text_start + image->sym_vvar_page,
-				      __pa_symbol(&__vvar_page) >> PAGE_SHIFT,
-				      PAGE_SIZE,
-				      PAGE_READONLY);
-
-	if (ret)
-		goto up_fail;
-
-#ifdef CONFIG_HPET_TIMER
-	if (hpet_address && image->sym_hpet_page) {
-		ret = io_remap_pfn_range(vma,
-			text_start + image->sym_hpet_page,
-			hpet_address >> PAGE_SHIFT,
-			PAGE_SIZE,
-			pgprot_noncached(PAGE_READONLY));
-
-		if (ret)
-			goto up_fail;
-	}
-#endif
-
-	pvti = pvclock_pvti_cpu0_va();
-	if (pvti && image->sym_pvclock_page) {
-		ret = remap_pfn_range(vma,
-				      text_start + image->sym_pvclock_page,
-				      __pa(pvti) >> PAGE_SHIFT,
-				      PAGE_SIZE,
-				      PAGE_READONLY);
-
-		if (ret)
-			goto up_fail;
-	}
-
 up_fail:
 	if (ret)
 		current->mm->context.vdso = NULL;

index 4b5461ba4f6b..7c912fefe79b 100644
@@ -130,7 +130,7 @@ static int vvar_fault(const struct vm_special_mapping *sm,
 				    __pa_symbol(&__vvar_page) >> PAGE_SHIFT);
 	} else if (sym_offset == image->sym_hpet_page) {
 #ifdef CONFIG_HPET_TIMER
-		if (hpet_address) {
+		if (hpet_address && vclock_was_used(VCLOCK_HPET)) {
 			ret = vm_insert_pfn_prot(
 				vma,
 				(unsigned long)vmf->virtual_address,

@@ -141,7 +141,7 @@ static int vvar_fault(const struct vm_special_mapping *sm,
 	} else if (sym_offset == image->sym_pvclock_page) {
 		struct pvclock_vsyscall_time_info *pvti =
 			pvclock_pvti_cpu0_va();
-		if (pvti) {
+		if (pvti && vclock_was_used(VCLOCK_PVCLOCK)) {
 			ret = vm_insert_pfn(
 				vma,
 				(unsigned long)vmf->virtual_address,

index 51e330416995..0fb3a104ac62 100644
@@ -16,6 +16,8 @@
 #include <asm/vgtod.h>
 #include <asm/vvar.h>
 
+int vclocks_used __read_mostly;
+
 DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data);
 
 void update_vsyscall_tz(void)

@@ -26,12 +28,17 @@ void update_vsyscall_tz(void)
 
 void update_vsyscall(struct timekeeper *tk)
 {
+	int vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode;
 	struct vsyscall_gtod_data *vdata = &vsyscall_gtod_data;
 
+	/* Mark the new vclock used. */
+	BUILD_BUG_ON(VCLOCK_MAX >= 32);
+	WRITE_ONCE(vclocks_used, READ_ONCE(vclocks_used) | (1 << vclock_mode));
+
 	gtod_write_begin(vdata);
 
 	/* copy vsyscall data */
-	vdata->vclock_mode	= tk->tkr_mono.clock->archdata.vclock_mode;
+	vdata->vclock_mode	= vclock_mode;
 	vdata->cycle_last	= tk->tkr_mono.cycle_last;
 	vdata->mask		= tk->tkr_mono.mask;
 	vdata->mult		= tk->tkr_mono.mult;

index eda81dc0f4ae..d194266acb28 100644
@@ -3,10 +3,11 @@
 #ifndef _ASM_X86_CLOCKSOURCE_H
 #define _ASM_X86_CLOCKSOURCE_H
 
-#define VCLOCK_NONE 0  /* No vDSO clock available.	*/
-#define VCLOCK_TSC  1  /* vDSO should use vread_tsc.	*/
-#define VCLOCK_HPET 2  /* vDSO should use vread_hpet.	*/
-#define VCLOCK_PVCLOCK 3 /* vDSO should use vread_pvclock. */
+#define VCLOCK_NONE	0  /* No vDSO clock available.	*/
+#define VCLOCK_TSC	1  /* vDSO should use vread_tsc.	*/
+#define VCLOCK_HPET	2  /* vDSO should use vread_hpet.	*/
+#define VCLOCK_PVCLOCK	3 /* vDSO should use vread_pvclock. */
+#define VCLOCK_MAX	3
 
 struct arch_clocksource_data {
 	int vclock_mode;

index f556c4843aa1..e728699db774 100644
@@ -37,6 +37,12 @@ struct vsyscall_gtod_data {
 };
 extern struct vsyscall_gtod_data vsyscall_gtod_data;
 
+extern int vclocks_used;
+static inline bool vclock_was_used(int vclock)
+{
+	return READ_ONCE(vclocks_used) & (1 << vclock);
+}
+
 static inline unsigned gtod_read_begin(const struct vsyscall_gtod_data *s)
 {
 	unsigned ret;