1 files changed, 46 insertions, 119 deletions

diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 6d83ceb7f1ba..adb299d3b6a1 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -14,29 +14,20 @@
 #include <linux/elf.h>
 #include <linux/cpu.h>
 #include <linux/ptrace.h>
-#include <linux/time_namespace.h>
+#include <linux/vdso_datastore.h>
 
 #include <asm/pvclock.h>
 #include <asm/vgtod.h>
 #include <asm/proto.h>
 #include <asm/vdso.h>
-#include <asm/vvar.h>
 #include <asm/tlb.h>
 #include <asm/page.h>
 #include <asm/desc.h>
 #include <asm/cpufeature.h>
+#include <asm/vdso/vsyscall.h>
 #include <clocksource/hyperv_timer.h>
 
-#undef _ASM_X86_VVAR_H
-#define EMIT_VVAR(name, offset)	\
-	const size_t name ## _offset = offset;
-#include <asm/vvar.h>
-
-struct vdso_data *arch_get_vdso_data(void *vvar_page)
-{
-	return (struct vdso_data *)(vvar_page + _vdso_data_offset);
-}
-#undef EMIT_VVAR
+static_assert(VDSO_NR_PAGES + VDSO_NR_VCLOCK_PAGES == __VDSO_PAGES);
 
 unsigned int vclocks_used __read_mostly;
 
@@ -56,7 +47,6 @@ int __init init_vdso_image(const struct vdso_image *image)
 	return 0;
 }
 
-static const struct vm_special_mapping vvar_mapping;
 struct linux_binprm;
 
 static vm_fault_t vdso_fault(const struct vm_special_mapping *sm,
@@ -100,106 +90,32 @@ static int vdso_mremap(const struct vm_special_mapping *sm,
 	return 0;
 }
 
-#ifdef CONFIG_TIME_NS
-/*
- * The vvar page layout depends on whether a task belongs to the root or
- * non-root time namespace. Whenever a task changes its namespace, the VVAR
- * page tables are cleared and then they will re-faulted with a
- * corresponding layout.
- * See also the comment near timens_setup_vdso_data() for details.
- */
-int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
-{
-	struct mm_struct *mm = task->mm;
-	struct vm_area_struct *vma;
-	VMA_ITERATOR(vmi, mm, 0);
-
-	mmap_read_lock(mm);
-	for_each_vma(vmi, vma) {
-		if (vma_is_special_mapping(vma, &vvar_mapping))
-			zap_vma_pages(vma);
-	}
-	mmap_read_unlock(mm);
-
-	return 0;
-}
-#endif
-
-static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
-		      struct vm_area_struct *vma, struct vm_fault *vmf)
+static vm_fault_t vvar_vclock_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;
-	unsigned long pfn;
-	long sym_offset;
-
-	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) {
-		struct page *timens_page = find_timens_vvar_page(vma);
-
-		pfn = __pa_symbol(&__vvar_page) >> PAGE_SHIFT;
-
-		/*
-		 * If a task belongs to a time namespace then a namespace
-		 * specific VVAR is mapped with the sym_vvar_page offset and
-		 * the real VVAR page is mapped with the sym_timens_page
-		 * offset.
-		 * See also the comment near timens_setup_vdso_data().
-		 */
-		if (timens_page) {
-			unsigned long addr;
-			vm_fault_t err;
-
-			/*
-			 * Optimization: inside time namespace pre-fault
-			 * VVAR page too. As on timens page there are only
-			 * offsets for clocks on VVAR, it'll be faulted
-			 * shortly by VDSO code.
-			 */
-			addr = vmf->address + (image->sym_timens_page - sym_offset);
-			err = vmf_insert_pfn(vma, addr, pfn);
-			if (unlikely(err & VM_FAULT_ERROR))
-				return err;
-
-			pfn = page_to_pfn(timens_page);
-		}
-
-		return vmf_insert_pfn(vma, vmf->address, pfn);
-	} else if (sym_offset == image->sym_pvclock_page) {
+	switch (vmf->pgoff) {
+#ifdef CONFIG_PARAVIRT_CLOCK
+	case VDSO_PAGE_PVCLOCK_OFFSET:
+	{
 		struct pvclock_vsyscall_time_info *pvti =
 			pvclock_get_pvti_cpu0_va();
-		if (pvti && vclock_was_used(VDSO_CLOCKMODE_PVCLOCK)) {
+
+		if (pvti && vclock_was_used(VDSO_CLOCKMODE_PVCLOCK))
 			return vmf_insert_pfn_prot(vma, vmf->address,
 					__pa(pvti) >> PAGE_SHIFT,
 					pgprot_decrypted(vma->vm_page_prot));
-		}
-	} else if (sym_offset == image->sym_hvclock_page) {
-		pfn = hv_get_tsc_pfn();
-
+		break;
+	}
+#endif /* CONFIG_PARAVIRT_CLOCK */
+#ifdef CONFIG_HYPERV_TIMER
+	case VDSO_PAGE_HVCLOCK_OFFSET:
+	{
+		unsigned long pfn = hv_get_tsc_pfn();
 		if (pfn && vclock_was_used(VDSO_CLOCKMODE_HVCLOCK))
 			return vmf_insert_pfn(vma, vmf->address, pfn);
-	} else if (sym_offset == image->sym_timens_page) {
-		struct page *timens_page = find_timens_vvar_page(vma);
-
-		if (!timens_page)
-			return VM_FAULT_SIGBUS;
-
-		pfn = __pa_symbol(&__vvar_page) >> PAGE_SHIFT;
-		return vmf_insert_pfn(vma, vmf->address, pfn);
+		break;
+	}
+#endif /* CONFIG_HYPERV_TIMER */
 	}
 
 	return VM_FAULT_SIGBUS;
@@ -210,9 +126,9 @@ static const struct vm_special_mapping vdso_mapping = {
 	.fault = vdso_fault,
 	.mremap = vdso_mremap,
 };
-static const struct vm_special_mapping vvar_mapping = {
-	.name = "[vvar]",
-	.fault = vvar_fault,
+static const struct vm_special_mapping vvar_vclock_mapping = {
+	.name = "[vvar_vclock]",
+	.fault = vvar_vclock_fault,
 };
 
 /*
@@ -231,13 +147,13 @@ static int map_vdso(const struct vdso_image *image, unsigned long addr)
 		return -EINTR;
 
 	addr = get_unmapped_area(NULL, addr,
-				 image->size - image->sym_vvar_start, 0, 0);
+				 image->size + __VDSO_PAGES * PAGE_SIZE, 0, 0);
 	if (IS_ERR_VALUE(addr)) {
 		ret = addr;
 		goto up_fail;
 	}
 
-	text_start = addr - image->sym_vvar_start;
+	text_start = addr + __VDSO_PAGES * PAGE_SIZE;
 
 	/*
 	 * MAYWRITE to allow gdb to COW and set breakpoints
@@ -246,7 +162,8 @@ static int map_vdso(const struct vdso_image *image, unsigned long addr)
 				       text_start,
 				       image->size,
 				       VM_READ|VM_EXEC|
-				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
+				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
+				       VM_SEALED_SYSMAP,
 				       &vdso_mapping);
 
 	if (IS_ERR(vma)) {
@@ -254,21 +171,30 @@ static int map_vdso(const struct vdso_image *image, unsigned long addr)
 		goto up_fail;
 	}
 
+	vma = vdso_install_vvar_mapping(mm, addr);
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+		do_munmap(mm, text_start, image->size, NULL);
+		goto up_fail;
+	}
+
 	vma = _install_special_mapping(mm,
-				       addr,
-				       -image->sym_vvar_start,
+				       VDSO_VCLOCK_PAGES_START(addr),
+				       VDSO_NR_VCLOCK_PAGES * PAGE_SIZE,
 				       VM_READ|VM_MAYREAD|VM_IO|VM_DONTDUMP|
-				       VM_PFNMAP,
-				       &vvar_mapping);
+				       VM_PFNMAP|VM_SEALED_SYSMAP,
+				       &vvar_vclock_mapping);
 
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		do_munmap(mm, text_start, image->size, NULL);
-	} else {
-		current->mm->context.vdso = (void __user *)text_start;
-		current->mm->context.vdso_image = image;
+		do_munmap(mm, addr, image->size, NULL);
+		goto up_fail;
 	}
 
+	current->mm->context.vdso = (void __user *)text_start;
+	current->mm->context.vdso_image = image;
+
 up_fail:
 	mmap_write_unlock(mm);
 	return ret;
@@ -290,7 +216,8 @@ int map_vdso_once(const struct vdso_image *image, unsigned long addr)
 	 */
 	for_each_vma(vmi, vma) {
 		if (vma_is_special_mapping(vma, &vdso_mapping) ||
-				vma_is_special_mapping(vma, &vvar_mapping)) {
+				vma_is_special_mapping(vma, &vdso_vvar_mapping) ||
+				vma_is_special_mapping(vma, &vvar_vclock_mapping)) {
 			mmap_write_unlock(mm);
 			return -EEXIST;
 		}