1 files changed, 131 insertions, 218 deletions

diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index bcc9bdb39ba2..430feb1a5013 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -6,269 +6,182 @@
  *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
  */
 
-#include <linux/init.h>
+#include <linux/binfmts.h>
+#include <linux/compat.h>
+#include <linux/elf.h>
 #include <linux/errno.h>
-#include <linux/sched.h>
+#include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/mm.h>
-#include <linux/smp.h>
-#include <linux/stddef.h>
-#include <linux/unistd.h>
 #include <linux/slab.h>
-#include <linux/user.h>
-#include <linux/elf.h>
-#include <linux/security.h>
-#include <linux/memblock.h>
-#include <linux/compat.h>
-#include <asm/asm-offsets.h>
-#include <asm/pgtable.h>
-#include <asm/processor.h>
-#include <asm/mmu.h>
-#include <asm/mmu_context.h>
-#include <asm/sections.h>
+#include <linux/smp.h>
+#include <linux/random.h>
+#include <linux/vdso_datastore.h>
+#include <vdso/datapage.h>
+#include <asm/vdso/vsyscall.h>
+#include <asm/alternative.h>
 #include <asm/vdso.h>
-#include <asm/facility.h>
-
-extern char vdso64_start, vdso64_end;
-static void *vdso64_kbase = &vdso64_start;
-static unsigned int vdso64_pages;
-static struct page **vdso64_pagelist;
-
-/*
- * Should the kernel map a VDSO page into processes and pass its
- * address down to glibc upon exec()?
- */
-unsigned int __read_mostly vdso_enabled = 1;
 
-static vm_fault_t vdso_fault(const struct vm_special_mapping *sm,
-		      struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	struct page **vdso_pagelist;
-	unsigned long vdso_pages;
-
-	vdso_pagelist = vdso64_pagelist;
-	vdso_pages = vdso64_pages;
-
-	if (vmf->pgoff >= vdso_pages)
-		return VM_FAULT_SIGBUS;
-
-	vmf->page = vdso_pagelist[vmf->pgoff];
-	get_page(vmf->page);
-	return 0;
-}
+extern char vdso64_start[], vdso64_end[];
+extern char vdso32_start[], vdso32_end[];
 
 static int vdso_mremap(const struct vm_special_mapping *sm,
 		       struct vm_area_struct *vma)
 {
-	unsigned long vdso_pages;
-
-	vdso_pages = vdso64_pages;
-
-	if ((vdso_pages << PAGE_SHIFT) != vma->vm_end - vma->vm_start)
-		return -EINVAL;
-
-	if (WARN_ON_ONCE(current->mm != vma->vm_mm))
-		return -EFAULT;
-
 	current->mm->context.vdso_base = vma->vm_start;
 	return 0;
 }
 
-static const struct vm_special_mapping vdso_mapping = {
+static struct vm_special_mapping vdso64_mapping = {
 	.name = "[vdso]",
-	.fault = vdso_fault,
 	.mremap = vdso_mremap,
 };
 
-static int __init vdso_setup(char *str)
-{
-	bool enabled;
-
-	if (!kstrtobool(str, &enabled))
-		vdso_enabled = enabled;
-	return 1;
-}
-__setup("vdso=", vdso_setup);
-
-/*
- * The vdso data page
- */
-static union {
-	struct vdso_data	data;
-	u8			page[PAGE_SIZE];
-} vdso_data_store __page_aligned_data;
-struct vdso_data *vdso_data = &vdso_data_store.data;
+static struct vm_special_mapping vdso32_mapping = {
+	.name = "[vdso]",
+	.mremap = vdso_mremap,
+};
 
-/*
- * Setup vdso data page.
- */
-static void __init vdso_init_data(struct vdso_data *vd)
+int vdso_getcpu_init(void)
 {
-	vd->ectg_available = test_facility(31);
+	set_tod_programmable_field(smp_processor_id());
+	return 0;
 }
+early_initcall(vdso_getcpu_init); /* Must be called before SMP init */
 
-/*
- * Allocate/free per cpu vdso data.
- */
-#define SEGMENT_ORDER	2
-
-/*
- * The initial vdso_data structure for the boot CPU. Eventually
- * it is replaced with a properly allocated structure in vdso_init.
- * This is necessary because a valid S390_lowcore.vdso_per_cpu_data
- * pointer is required to be able to return from an interrupt or
- * program check. See the exit paths in entry.S.
- */
-struct vdso_data boot_vdso_data __initdata;
-
-void __init vdso_alloc_boot_cpu(struct lowcore *lowcore)
+static int map_vdso(unsigned long addr, unsigned long vdso_mapping_len)
 {
-	lowcore->vdso_per_cpu_data = (unsigned long) &boot_vdso_data;
-}
+	unsigned long vvar_start, vdso_text_start, vdso_text_len;
+	struct vm_special_mapping *vdso_mapping;
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	int rc;
 
-int vdso_alloc_per_cpu(struct lowcore *lowcore)
-{
-	unsigned long segment_table, page_table, page_frame;
-	struct vdso_per_cpu_data *vd;
+	BUILD_BUG_ON(VDSO_NR_PAGES != __VDSO_PAGES);
+	if (mmap_write_lock_killable(mm))
+		return -EINTR;
 
-	segment_table = __get_free_pages(GFP_KERNEL, SEGMENT_ORDER);
-	page_table = get_zeroed_page(GFP_KERNEL);
-	page_frame = get_zeroed_page(GFP_KERNEL);
-	if (!segment_table || !page_table || !page_frame)
+	if (is_compat_task()) {
+		vdso_text_len = vdso32_end - vdso32_start;
+		vdso_mapping = &vdso32_mapping;
+	} else {
+		vdso_text_len = vdso64_end - vdso64_start;
+		vdso_mapping = &vdso64_mapping;
+	}
+	vvar_start = get_unmapped_area(NULL, addr, vdso_mapping_len, 0, 0);
+	rc = vvar_start;
+	if (IS_ERR_VALUE(vvar_start))
 		goto out;
-	arch_set_page_dat(virt_to_page(segment_table), SEGMENT_ORDER);
-	arch_set_page_dat(virt_to_page(page_table), 0);
-
-	/* Initialize per-cpu vdso data page */
-	vd = (struct vdso_per_cpu_data *) page_frame;
-	vd->cpu_nr = lowcore->cpu_nr;
-	vd->node_id = cpu_to_node(vd->cpu_nr);
-
-	/* Set up page table for the vdso address space */
-	memset64((u64 *)segment_table, _SEGMENT_ENTRY_EMPTY, _CRST_ENTRIES);
-	memset64((u64 *)page_table, _PAGE_INVALID, PTRS_PER_PTE);
-
-	*(unsigned long *) segment_table = _SEGMENT_ENTRY + page_table;
-	*(unsigned long *) page_table = _PAGE_PROTECT + page_frame;
-
-	lowcore->vdso_asce = segment_table +
-		_ASCE_TABLE_LENGTH + _ASCE_USER_BITS + _ASCE_TYPE_SEGMENT;
-	lowcore->vdso_per_cpu_data = page_frame;
-
-	return 0;
-
+	vma = vdso_install_vvar_mapping(mm, vvar_start);
+	rc = PTR_ERR(vma);
+	if (IS_ERR(vma))
+		goto out;
+	vdso_text_start = vvar_start + VDSO_NR_PAGES * PAGE_SIZE;
+	/* VM_MAYWRITE for COW so gdb can set breakpoints */
+	vma = _install_special_mapping(mm, vdso_text_start, vdso_text_len,
+				       VM_READ|VM_EXEC|VM_SEALED_SYSMAP|
+				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
+				       vdso_mapping);
+	if (IS_ERR(vma)) {
+		do_munmap(mm, vvar_start, PAGE_SIZE, NULL);
+		rc = PTR_ERR(vma);
+	} else {
+		current->mm->context.vdso_base = vdso_text_start;
+		rc = 0;
+	}
 out:
-	free_page(page_frame);
-	free_page(page_table);
-	free_pages(segment_table, SEGMENT_ORDER);
-	return -ENOMEM;
+	mmap_write_unlock(mm);
+	return rc;
 }
 
-void vdso_free_per_cpu(struct lowcore *lowcore)
+static unsigned long vdso_addr(unsigned long start, unsigned long len)
 {
-	unsigned long segment_table, page_table, page_frame;
+	unsigned long addr, end, offset;
 
-	segment_table = lowcore->vdso_asce & PAGE_MASK;
-	page_table = *(unsigned long *) segment_table;
-	page_frame = *(unsigned long *) page_table;
-
-	free_page(page_frame);
-	free_page(page_table);
-	free_pages(segment_table, SEGMENT_ORDER);
+	/*
+	 * Round up the start address. It can start out unaligned as a result
+	 * of stack start randomization.
+	 */
+	start = PAGE_ALIGN(start);
+
+	/* Round the lowest possible end address up to a PMD boundary. */
+	end = (start + len + PMD_SIZE - 1) & PMD_MASK;
+	if (end >= VDSO_BASE)
+		end = VDSO_BASE;
+	end -= len;
+
+	if (end > start) {
+		offset = get_random_u32_below(((end - start) >> PAGE_SHIFT) + 1);
+		addr = start + (offset << PAGE_SHIFT);
+	} else {
+		addr = start;
+	}
+	return addr;
 }
 
-/*
- * This is called from binfmt_elf, we create the special vma for the
- * vDSO and insert it into the mm struct tree
- */
-int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+unsigned long vdso_text_size(void)
 {
-	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma;
-	unsigned long vdso_pages;
-	unsigned long vdso_base;
-	int rc;
-
-	if (!vdso_enabled)
-		return 0;
+	unsigned long size;
 
 	if (is_compat_task())
-		return 0;
-
-	vdso_pages = vdso64_pages;
-	/*
-	 * vDSO has a problem and was disabled, just don't "enable" it for
-	 * the process
-	 */
-	if (vdso_pages == 0)
-		return 0;
-
-	/*
-	 * pick a base address for the vDSO in process space. We try to put
-	 * it at vdso_base which is the "natural" base for it, but we might
-	 * fail and end up putting it elsewhere.
-	 */
-	if (down_write_killable(&mm->mmap_sem))
-		return -EINTR;
-	vdso_base = get_unmapped_area(NULL, 0, vdso_pages << PAGE_SHIFT, 0, 0);
-	if (IS_ERR_VALUE(vdso_base)) {
-		rc = vdso_base;
-		goto out_up;
-	}
+		size = vdso32_end - vdso32_start;
+	else
+		size = vdso64_end - vdso64_start;
+	return PAGE_ALIGN(size);
+}
 
-	/*
-	 * our vma flags don't have VM_WRITE so by default, the process
-	 * isn't allowed to write those pages.
-	 * gdb can break that with ptrace interface, and thus trigger COW
-	 * on those pages but it's then your responsibility to never do that
-	 * on the "data" page of the vDSO or you'll stop getting kernel
-	 * updates and your nice userland gettimeofday will be totally dead.
-	 * It's fine to use that for setting breakpoints in the vDSO code
-	 * pages though.
-	 */
-	vma = _install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT,
-				       VM_READ|VM_EXEC|
-				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
-				       &vdso_mapping);
-	if (IS_ERR(vma)) {
-		rc = PTR_ERR(vma);
-		goto out_up;
-	}
+unsigned long vdso_size(void)
+{
+	return vdso_text_size() + VDSO_NR_PAGES * PAGE_SIZE;
+}
 
-	current->mm->context.vdso_base = vdso_base;
-	rc = 0;
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+	unsigned long addr = VDSO_BASE;
+	unsigned long size = vdso_size();
 
-out_up:
-	up_write(&mm->mmap_sem);
-	return rc;
+	if (current->flags & PF_RANDOMIZE)
+		addr = vdso_addr(current->mm->start_stack + PAGE_SIZE, size);
+	return map_vdso(addr, size);
 }
 
-static int __init vdso_init(void)
+static struct page ** __init vdso_setup_pages(void *start, void *end)
 {
+	int pages = (end - start) >> PAGE_SHIFT;
+	struct page **pagelist;
 	int i;
 
-	vdso_init_data(vdso_data);
-
-	/* Calculate the size of the 64 bit vDSO */
-	vdso64_pages = ((&vdso64_end - &vdso64_start
-			 + PAGE_SIZE - 1) >> PAGE_SHIFT) + 1;
-
-	/* Make sure pages are in the correct state */
-	vdso64_pagelist = kcalloc(vdso64_pages + 1, sizeof(struct page *),
-				  GFP_KERNEL);
-	BUG_ON(vdso64_pagelist == NULL);
-	for (i = 0; i < vdso64_pages - 1; i++) {
-		struct page *pg = virt_to_page(vdso64_kbase + i*PAGE_SIZE);
-		get_page(pg);
-		vdso64_pagelist[i] = pg;
-	}
-	vdso64_pagelist[vdso64_pages - 1] = virt_to_page(vdso_data);
-	vdso64_pagelist[vdso64_pages] = NULL;
-	if (vdso_alloc_per_cpu(&S390_lowcore))
-		BUG();
+	pagelist = kcalloc(pages + 1, sizeof(struct page *), GFP_KERNEL);
+	if (!pagelist)
+		panic("%s: Cannot allocate page list for VDSO", __func__);
+	for (i = 0; i < pages; i++)
+		pagelist[i] = virt_to_page(start + i * PAGE_SIZE);
+	return pagelist;
+}
 
-	get_page(virt_to_page(vdso_data));
+static void vdso_apply_alternatives(void)
+{
+	const struct elf64_shdr *alt, *shdr;
+	struct alt_instr *start, *end;
+	const struct elf64_hdr *hdr;
+
+	hdr = (struct elf64_hdr *)vdso64_start;
+	shdr = (void *)hdr + hdr->e_shoff;
+	alt = find_section(hdr, shdr, ".altinstructions");
+	if (!alt)
+		return;
+	start = (void *)hdr + alt->sh_offset;
+	end = (void *)hdr + alt->sh_offset + alt->sh_size;
+	apply_alternatives(start, end);
+}
 
+static int __init vdso_init(void)
+{
+	vdso_apply_alternatives();
+	vdso64_mapping.pages = vdso_setup_pages(vdso64_start, vdso64_end);
+	if (IS_ENABLED(CONFIG_COMPAT))
+		vdso32_mapping.pages = vdso_setup_pages(vdso32_start, vdso32_end);
 	return 0;
 }
-early_initcall(vdso_init);
+arch_initcall(vdso_init);