1 files changed, 110 insertions, 294 deletions

diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index b89d19f6f2ab..a27a90a199be 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -1,349 +1,165 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * vdso setup for s390
  *
  *  Copyright IBM Corp. 2008
  *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
  */
 
-#include <linux/init.h>
+#include <linux/binfmts.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/bootmem.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>
 
-#ifdef CONFIG_COMPAT
-extern char vdso32_start, vdso32_end;
-static void *vdso32_kbase = &vdso32_start;
-static unsigned int vdso32_pages;
-static struct page **vdso32_pagelist;
-#endif
-
-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 int 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;
-#ifdef CONFIG_COMPAT
-	if (is_compat_task()) {
-		vdso_pagelist = vdso32_pagelist;
-		vdso_pages = vdso32_pages;
-	}
-#endif
-
-	if (vmf->pgoff >= vdso_pages)
-		return VM_FAULT_SIGBUS;
-
-	vmf->page = vdso_pagelist[vmf->pgoff];
-	get_page(vmf->page);
-	return 0;
-}
+extern char vdso_start[], vdso_end[];
 
 static int vdso_mremap(const struct vm_special_mapping *sm,
 		       struct vm_area_struct *vma)
 {
-	unsigned long vdso_pages;
-
-	vdso_pages = vdso64_pages;
-#ifdef CONFIG_COMPAT
-	if (is_compat_task())
-		vdso_pages = vdso32_pages;
-#endif
-
-	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 vdso_mapping = {
 	.name = "[vdso]",
-	.fault = vdso_fault,
 	.mremap = vdso_mremap,
 };
 
-static int __init vdso_setup(char *s)
-{
-	unsigned long val;
-	int rc;
-
-	rc = 0;
-	if (strncmp(s, "on", 3) == 0)
-		vdso_enabled = 1;
-	else if (strncmp(s, "off", 4) == 0)
-		vdso_enabled = 0;
-	else {
-		rc = kstrtoul(s, 0, &val);
-		vdso_enabled = rc ? 0 : !!val;
-	}
-	return !rc;
-}
-__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;
-
-/*
- * 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
-
-int vdso_alloc_per_cpu(struct lowcore *lowcore)
+static int map_vdso(unsigned long addr, unsigned long vdso_mapping_len)
 {
-	unsigned long segment_table, page_table, page_frame;
-	struct vdso_per_cpu_data *vd;
-	u32 *psal, *aste;
-	int i;
-
-	lowcore->vdso_per_cpu_data = __LC_PASTE;
+	unsigned long vvar_start, vdso_text_start, vdso_text_len;
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	int rc;
 
-	if (!vdso_enabled)
-		return 0;
+	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 | GFP_DMA);
-	page_frame = get_zeroed_page(GFP_KERNEL);
-	if (!segment_table || !page_table || !page_frame)
+	vdso_text_len = vdso_end - vdso_start;
+	vvar_start = get_unmapped_area(NULL, addr, vdso_mapping_len, 0, 0);
+	rc = vvar_start;
+	if (IS_ERR_VALUE(vvar_start))
 		goto out;
-
-	/* 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 access register mode page table */
-	clear_table((unsigned long *) segment_table, _SEGMENT_ENTRY_EMPTY,
-		    PAGE_SIZE << SEGMENT_ORDER);
-	clear_table((unsigned long *) page_table, _PAGE_INVALID,
-		    256*sizeof(unsigned long));
-
-	*(unsigned long *) segment_table = _SEGMENT_ENTRY + page_table;
-	*(unsigned long *) page_table = _PAGE_PROTECT + page_frame;
-
-	psal = (u32 *) (page_table + 256*sizeof(unsigned long));
-	aste = psal + 32;
-
-	for (i = 4; i < 32; i += 4)
-		psal[i] = 0x80000000;
-
-	lowcore->paste[4] = (u32)(addr_t) psal;
-	psal[0] = 0x02000000;
-	psal[2] = (u32)(addr_t) aste;
-	*(unsigned long *) (aste + 2) = segment_table +
-		_ASCE_TABLE_LENGTH + _ASCE_USER_BITS + _ASCE_TYPE_SEGMENT;
-	aste[4] = (u32)(addr_t) psal;
-	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;
-	u32 *psal, *aste;
-
-	if (!vdso_enabled)
-		return;
-
-	psal = (u32 *)(addr_t) lowcore->paste[4];
-	aste = (u32 *)(addr_t) psal[2];
-	segment_table = *(unsigned long *)(aste + 2) & PAGE_MASK;
-	page_table = *(unsigned long *) segment_table;
-	page_frame = *(unsigned long *) page_table;
+	unsigned long addr, end, offset;
 
-	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;
 }
 
-static void vdso_init_cr5(void)
+unsigned long vdso_text_size(void)
 {
-	unsigned long cr5;
+	return PAGE_ALIGN(vdso_end - vdso_start);
+}
 
-	if (!vdso_enabled)
-		return;
-	cr5 = offsetof(struct lowcore, paste);
-	__ctl_load(cr5, 5, 5);
+unsigned long vdso_size(void)
+{
+	return vdso_text_size() + VDSO_NR_PAGES * PAGE_SIZE;
 }
 
-/*
- * 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)
 {
-	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma;
-	unsigned long vdso_pages;
-	unsigned long vdso_base;
-	int rc;
+	unsigned long addr = VDSO_BASE;
+	unsigned long size = vdso_size();
 
-	if (!vdso_enabled)
-		return 0;
-	/*
-	 * Only map the vdso for dynamically linked elf binaries.
-	 */
-	if (!uses_interp)
-		return 0;
-
-	vdso_pages = vdso64_pages;
-#ifdef CONFIG_COMPAT
-	if (is_compat_task())
-		vdso_pages = vdso32_pages;
-#endif
-	/*
-	 * 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;
-	}
-
-	/*
-	 * 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;
-	}
-
-	current->mm->context.vdso_base = vdso_base;
-	rc = 0;
-
-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;
 
-	if (!vdso_enabled)
-		return 0;
-	vdso_init_data(vdso_data);
-#ifdef CONFIG_COMPAT
-	/* Calculate the size of the 32 bit vDSO */
-	vdso32_pages = ((&vdso32_end - &vdso32_start
-			 + PAGE_SIZE - 1) >> PAGE_SHIFT) + 1;
-
-	/* Make sure pages are in the correct state */
-	vdso32_pagelist = kzalloc(sizeof(struct page *) * (vdso32_pages + 1),
-				  GFP_KERNEL);
-	BUG_ON(vdso32_pagelist == NULL);
-	for (i = 0; i < vdso32_pages - 1; i++) {
-		struct page *pg = virt_to_page(vdso32_kbase + i*PAGE_SIZE);
-		ClearPageReserved(pg);
-		get_page(pg);
-		vdso32_pagelist[i] = pg;
-	}
-	vdso32_pagelist[vdso32_pages - 1] = virt_to_page(vdso_data);
-	vdso32_pagelist[vdso32_pages] = NULL;
-#endif
-
-	/* 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 = kzalloc(sizeof(struct page *) * (vdso64_pages + 1),
-				  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);
-		ClearPageReserved(pg);
-		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();
-	vdso_init_cr5();
+	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 *)vdso_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();
+	vdso_mapping.pages = vdso_setup_pages(vdso_start, vdso_end);
 	return 0;
 }
-early_initcall(vdso_init);
+arch_initcall(vdso_init);