Merge branch 'x86-vdso-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 vdso updates from Ingo Molnar:
 "The main changes in this cycle centered around adding support for
  32-bit compatible C/R of the vDSO on 64-bit kernels, by Dmitry
  Safonov"

* 'x86-vdso-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/vdso: Use CONFIG_X86_X32_ABI to enable vdso prctl
  x86/vdso: Only define map_vdso_randomized() if CONFIG_X86_64
  x86/vdso: Only define prctl_map_vdso() if CONFIG_CHECKPOINT_RESTORE
  x86/signal: Add SA_{X32,IA32}_ABI sa_flags
  x86/ptrace: Down with test_thread_flag(TIF_IA32)
  x86/coredump: Use pr_reg size, rather that TIF_IA32 flag
  x86/arch_prctl/vdso: Add ARCH_MAP_VDSO_*
  x86/vdso: Replace calculate_addr in map_vdso() with addr
  x86/vdso: Unmap vdso blob on vvar mapping failure

arch/x86/entry/vdso/vma.c

@@ -37,54 +37,6 @@ void __init init_vdso_image(const struct vdso_image *image)
 
 struct linux_binprm;
 
-/*
- * Put the vdso above the (randomized) stack with another randomized
- * offset.  This way there is no hole in the middle of address space.
- * To save memory make sure it is still in the same PTE as the stack
- * top.  This doesn't give that many random bits.
- *
- * Note that this algorithm is imperfect: the distribution of the vdso
- * start address within a PMD is biased toward the end.
- *
- * Only used for the 64-bit and x32 vdsos.
- */
-static unsigned long vdso_addr(unsigned long start, unsigned len)
-{
-#ifdef CONFIG_X86_32
-	return 0;
-#else
-	unsigned long addr, end;
-	unsigned offset;
-
-	/*
-	 * 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 >= TASK_SIZE_MAX)
-		end = TASK_SIZE_MAX;
-	end -= len;
-
-	if (end > start) {
-		offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1);
-		addr = start + (offset << PAGE_SHIFT);
-	} else {
-		addr = start;
-	}
-
-	/*
-	 * Forcibly align the final address in case we have a hardware
-	 * issue that requires alignment for performance reasons.
-	 */
-	addr = align_vdso_addr(addr);
-
-	return addr;
-#endif
-}
-
 static int vdso_fault(const struct vm_special_mapping *sm,
 		      struct vm_area_struct *vma, struct vm_fault *vmf)
 {
@@ -176,30 +128,28 @@ static int vvar_fault(const struct vm_special_mapping *sm,
 	return VM_FAULT_SIGBUS;
 }
 
-static int map_vdso(const struct vdso_image *image, bool calculate_addr)
+static const struct vm_special_mapping vdso_mapping = {
+	.name = "[vdso]",
+	.fault = vdso_fault,
+	.mremap = vdso_mremap,
+};
+static const struct vm_special_mapping vvar_mapping = {
+	.name = "[vvar]",
+	.fault = vvar_fault,
+};
+
+/*
+ * Add vdso and vvar mappings to current process.
+ * @image          - blob to map
+ * @addr           - request a specific address (zero to map at free addr)
+ */
+static int map_vdso(const struct vdso_image *image, unsigned long addr)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
-	unsigned long addr, text_start;
+	unsigned long text_start;
 	int ret = 0;
 
-	static const struct vm_special_mapping vdso_mapping = {
-		.name = "[vdso]",
-		.fault = vdso_fault,
-		.mremap = vdso_mremap,
-	};
-	static const struct vm_special_mapping vvar_mapping = {
-		.name = "[vvar]",
-		.fault = vvar_fault,
-	};
-
-	if (calculate_addr) {
-		addr = vdso_addr(current->mm->start_stack,
-				 image->size - image->sym_vvar_start);
-	} else {
-		addr = 0;
-	}
-
 	if (down_write_killable(&mm->mmap_sem))
 		return -EINTR;
 
@@ -238,24 +188,104 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
-		goto up_fail;
+		do_munmap(mm, text_start, image->size);
 	}
 
 up_fail:
-	if (ret)
+	if (ret) {
 		current->mm->context.vdso = NULL;
+		current->mm->context.vdso_image = NULL;
+	}
 
 	up_write(&mm->mmap_sem);
 	return ret;
 }
 
+#ifdef CONFIG_X86_64
+/*
+ * Put the vdso above the (randomized) stack with another randomized
+ * offset.  This way there is no hole in the middle of address space.
+ * To save memory make sure it is still in the same PTE as the stack
+ * top.  This doesn't give that many random bits.
+ *
+ * Note that this algorithm is imperfect: the distribution of the vdso
+ * start address within a PMD is biased toward the end.
+ *
+ * Only used for the 64-bit and x32 vdsos.
+ */
+static unsigned long vdso_addr(unsigned long start, unsigned len)
+{
+	unsigned long addr, end;
+	unsigned offset;
+
+	/*
+	 * 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 >= TASK_SIZE_MAX)
+		end = TASK_SIZE_MAX;
+	end -= len;
+
+	if (end > start) {
+		offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1);
+		addr = start + (offset << PAGE_SHIFT);
+	} else {
+		addr = start;
+	}
+
+	/*
+	 * Forcibly align the final address in case we have a hardware
+	 * issue that requires alignment for performance reasons.
+	 */
+	addr = align_vdso_addr(addr);
+
+	return addr;
+}
+
+static int map_vdso_randomized(const struct vdso_image *image)
+{
+	unsigned long addr = vdso_addr(current->mm->start_stack, image->size-image->sym_vvar_start);
+
+	return map_vdso(image, addr);
+}
+#endif
+
+int map_vdso_once(const struct vdso_image *image, unsigned long addr)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+
+	down_write(&mm->mmap_sem);
+	/*
+	 * Check if we have already mapped vdso blob - fail to prevent
+	 * abusing from userspace install_speciall_mapping, which may
+	 * not do accounting and rlimit right.
+	 * We could search vma near context.vdso, but it's a slowpath,
+	 * so let's explicitely check all VMAs to be completely sure.
+	 */
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		if (vma_is_special_mapping(vma, &vdso_mapping) ||
+				vma_is_special_mapping(vma, &vvar_mapping)) {
+			up_write(&mm->mmap_sem);
+			return -EEXIST;
+		}
+	}
+	up_write(&mm->mmap_sem);
+
+	return map_vdso(image, addr);
+}
+
 #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
 static int load_vdso32(void)
 {
 	if (vdso32_enabled != 1)  /* Other values all mean "disabled" */
 		return 0;
 
-	return map_vdso(&vdso_image_32, false);
+	return map_vdso(&vdso_image_32, 0);
 }
 #endif
 
@@ -265,7 +295,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	if (!vdso64_enabled)
 		return 0;
 
-	return map_vdso(&vdso_image_64, true);
+	return map_vdso_randomized(&vdso_image_64);
 }
 
 #ifdef CONFIG_COMPAT
@@ -276,8 +306,7 @@ int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
 	if (test_thread_flag(TIF_X32)) {
 		if (!vdso64_enabled)
 			return 0;
-
-		return map_vdso(&vdso_image_x32, true);
+		return map_vdso_randomized(&vdso_image_x32);
 	}
 #endif
 #ifdef CONFIG_IA32_EMULATION

arch/x86/ia32/ia32_signal.c

@@ -378,7 +378,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig,
 		put_user_ex(*((u64 *)&code), (u64 __user *)frame->retcode);
 	} put_user_catch(err);
 
-	err |= copy_siginfo_to_user32(&frame->info, &ksig->info);
+	err |= __copy_siginfo_to_user32(&frame->info, &ksig->info, false);
 	err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
 				     regs, set->sig[0]);
 	err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));

arch/x86/include/asm/compat.h

@@ -275,10 +275,10 @@ struct compat_shmid64_ds {
 #ifdef CONFIG_X86_X32_ABI
 typedef struct user_regs_struct compat_elf_gregset_t;
 
-#define PR_REG_SIZE(S) (test_thread_flag(TIF_IA32) ? 68 : 216)
-#define PRSTATUS_SIZE(S) (test_thread_flag(TIF_IA32) ? 144 : 296)
-#define SET_PR_FPVALID(S,V) \
-  do { *(int *) (((void *) &((S)->pr_reg)) + PR_REG_SIZE(0)) = (V); } \
+/* Full regset -- prstatus on x32, otherwise on ia32 */
+#define PRSTATUS_SIZE(S, R) (R != sizeof(S.pr_reg) ? 144 : 296)
+#define SET_PR_FPVALID(S, V, R) \
+  do { *(int *) (((void *) &((S)->pr_reg)) + R) = (V); } \
   while (0)
 
 #define COMPAT_USE_64BIT_TIME \

arch/x86/include/asm/fpu/signal.h

@@ -19,6 +19,12 @@ int ia32_setup_frame(int sig, struct ksignal *ksig,
 # define ia32_setup_rt_frame	__setup_rt_frame
 #endif
 
+#ifdef CONFIG_COMPAT
+int __copy_siginfo_to_user32(compat_siginfo_t __user *to,
+		const siginfo_t *from, bool x32_ABI);
+#endif
+
+
 extern void convert_from_fxsr(struct user_i387_ia32_struct *env,
 			      struct task_struct *tsk);
 extern void convert_to_fxsr(struct task_struct *tsk,

arch/x86/include/asm/signal.h

@@ -23,6 +23,10 @@ typedef struct {
 	unsigned long sig[_NSIG_WORDS];
 } sigset_t;
 
+/* non-uapi in-kernel SA_FLAGS for those indicates ABI for a signal frame */
+#define SA_IA32_ABI	0x02000000u
+#define SA_X32_ABI	0x01000000u
+
 #ifndef CONFIG_COMPAT
 typedef sigset_t compat_sigset_t;
 #endif

arch/x86/include/asm/vdso.h

@@ -41,6 +41,8 @@ extern const struct vdso_image vdso_image_32;
 
 extern void __init init_vdso_image(const struct vdso_image *image);
 
+extern int map_vdso_once(const struct vdso_image *image, unsigned long addr);
+
 #endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_X86_VDSO_H */

arch/x86/include/uapi/asm/prctl.h

@@ -6,4 +6,10 @@
 #define ARCH_GET_FS 0x1003
 #define ARCH_GET_GS 0x1004
 
+#ifdef CONFIG_CHECKPOINT_RESTORE
+# define ARCH_MAP_VDSO_X32	0x2001
+# define ARCH_MAP_VDSO_32	0x2002
+# define ARCH_MAP_VDSO_64	0x2003
+#endif
+
 #endif /* _ASM_X86_PRCTL_H */

arch/x86/kernel/process_64.c

@@ -49,6 +49,7 @@
 #include <asm/debugreg.h>
 #include <asm/switch_to.h>
 #include <asm/xen/hypervisor.h>
+#include <asm/vdso.h>
 
 __visible DEFINE_PER_CPU(unsigned long, rsp_scratch);
 
@@ -523,6 +524,19 @@ void set_personality_ia32(bool x32)
 }
 EXPORT_SYMBOL_GPL(set_personality_ia32);
 
+#ifdef CONFIG_CHECKPOINT_RESTORE
+static long prctl_map_vdso(const struct vdso_image *image, unsigned long addr)
+{
+	int ret;
+
+	ret = map_vdso_once(image, addr);
+	if (ret)
+		return ret;
+
+	return (long)image->size;
+}
+#endif
+
 long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
 {
 	int ret = 0;
@@ -576,6 +590,19 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
 		break;
 	}
 
+#ifdef CONFIG_CHECKPOINT_RESTORE
+# ifdef CONFIG_X86_X32_ABI
+	case ARCH_MAP_VDSO_X32:
+		return prctl_map_vdso(&vdso_image_x32, addr);
+# endif
+# if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
+	case ARCH_MAP_VDSO_32:
+		return prctl_map_vdso(&vdso_image_32, addr);
+# endif
+	case ARCH_MAP_VDSO_64:
+		return prctl_map_vdso(&vdso_image_64, addr);
+#endif
+
 	default:
 		ret = -EINVAL;
 		break;

arch/x86/kernel/ptrace.c

@@ -1358,7 +1358,7 @@ void __init update_regset_xstate_info(unsigned int size, u64 xstate_mask)
 const struct user_regset_view *task_user_regset_view(struct task_struct *task)
 {
 #ifdef CONFIG_IA32_EMULATION
-	if (test_tsk_thread_flag(task, TIF_IA32))
+	if (!user_64bit_mode(task_pt_regs(task)))
 #endif
 #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
 		return &user_x86_32_view;

arch/x86/kernel/signal.c

@@ -42,6 +42,7 @@
 #include <asm/syscalls.h>
 
 #include <asm/sigframe.h>
+#include <asm/signal.h>
 
 #define COPY(x)			do {			\
 	get_user_ex(regs->x, &sc->x);			\
@@ -547,7 +548,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig,
 		return -EFAULT;
 
 	if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
-		if (copy_siginfo_to_user32(&frame->info, &ksig->info))
+		if (__copy_siginfo_to_user32(&frame->info, &ksig->info, true))
 			return -EFAULT;
 	}
 
@@ -660,20 +661,21 @@ asmlinkage long sys_rt_sigreturn(void)
 	return 0;
 }
 
-static inline int is_ia32_compat_frame(void)
+static inline int is_ia32_compat_frame(struct ksignal *ksig)
 {
 	return IS_ENABLED(CONFIG_IA32_EMULATION) &&
-	       test_thread_flag(TIF_IA32);
+		ksig->ka.sa.sa_flags & SA_IA32_ABI;
 }
 
-static inline int is_ia32_frame(void)
+static inline int is_ia32_frame(struct ksignal *ksig)
 {
-	return IS_ENABLED(CONFIG_X86_32) || is_ia32_compat_frame();
+	return IS_ENABLED(CONFIG_X86_32) || is_ia32_compat_frame(ksig);
 }
 
-static inline int is_x32_frame(void)
+static inline int is_x32_frame(struct ksignal *ksig)
 {
-	return IS_ENABLED(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32);
+	return IS_ENABLED(CONFIG_X86_X32_ABI) &&
+		ksig->ka.sa.sa_flags & SA_X32_ABI;
 }
 
 static int
@@ -684,12 +686,12 @@ setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs)
 	compat_sigset_t *cset = (compat_sigset_t *) set;
 
 	/* Set up the stack frame */
-	if (is_ia32_frame()) {
+	if (is_ia32_frame(ksig)) {
 		if (ksig->ka.sa.sa_flags & SA_SIGINFO)
 			return ia32_setup_rt_frame(usig, ksig, cset, regs);
 		else
 			return ia32_setup_frame(usig, ksig, cset, regs);
-	} else if (is_x32_frame()) {
+	} else if (is_x32_frame(ksig)) {
 		return x32_setup_rt_frame(ksig, cset, regs);
 	} else {
 		return __setup_rt_frame(ksig->sig, ksig, set, regs);

arch/x86/kernel/signal_compat.c

@@ -1,5 +1,6 @@
 #include <linux/compat.h>
 #include <linux/uaccess.h>
+#include <linux/ptrace.h>
 
 /*
  * The compat_siginfo_t structure and handing code is very easy
@@ -92,10 +93,31 @@ static inline void signal_compat_build_tests(void)
 	/* any new si_fields should be added here */
 }
 
-int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
+void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact)
+{
+	/* Don't leak in-kernel non-uapi flags to user-space */
+	if (oact)
+		oact->sa.sa_flags &= ~(SA_IA32_ABI | SA_X32_ABI);
+
+	if (!act)
+		return;
+
+	/* Don't let flags to be set from userspace */
+	act->sa.sa_flags &= ~(SA_IA32_ABI | SA_X32_ABI);
+
+	if (user_64bit_mode(current_pt_regs()))
+		return;
+
+	if (in_ia32_syscall())
+		act->sa.sa_flags |= SA_IA32_ABI;
+	if (in_x32_syscall())
+		act->sa.sa_flags |= SA_X32_ABI;
+}
+
+int __copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from,
+		bool x32_ABI)
 {
 	int err = 0;
-	bool ia32 = test_thread_flag(TIF_IA32);
 
 	signal_compat_build_tests();
 
@@ -146,7 +168,7 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 				put_user_ex(from->si_arch, &to->si_arch);
 				break;
 			case __SI_CHLD >> 16:
-				if (ia32) {
+				if (!x32_ABI) {
 					put_user_ex(from->si_utime, &to->si_utime);
 					put_user_ex(from->si_stime, &to->si_stime);
 				} else {
@@ -180,6 +202,12 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 	return err;
 }
 
+/* from syscall's path, where we know the ABI */
+int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
+{
+	return __copy_siginfo_to_user32(to, from, in_x32_syscall());
+}
+
 int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 {
 	int err = 0;

fs/binfmt_elf.c

@@ -1624,20 +1624,12 @@ static void do_thread_regset_writeback(struct task_struct *task,
 		regset->writeback(task, regset, 1);
 }
 
-#ifndef PR_REG_SIZE
-#define PR_REG_SIZE(S) sizeof(S)
-#endif
-
 #ifndef PRSTATUS_SIZE
-#define PRSTATUS_SIZE(S) sizeof(S)
-#endif
-
-#ifndef PR_REG_PTR
-#define PR_REG_PTR(S) (&((S)->pr_reg))
+#define PRSTATUS_SIZE(S, R) sizeof(S)
 #endif
 
 #ifndef SET_PR_FPVALID
-#define SET_PR_FPVALID(S, V) ((S)->pr_fpvalid = (V))
+#define SET_PR_FPVALID(S, V, R) ((S)->pr_fpvalid = (V))
 #endif
 
 static int fill_thread_core_info(struct elf_thread_core_info *t,
@@ -1645,6 +1637,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
 				 long signr, size_t *total)
 {
 	unsigned int i;
+	unsigned int regset_size = view->regsets[0].n * view->regsets[0].size;
 
 	/*
 	 * NT_PRSTATUS is the one special case, because the regset data
@@ -1653,12 +1646,11 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
 	 * We assume that regset 0 is NT_PRSTATUS.
 	 */
 	fill_prstatus(&t->prstatus, t->task, signr);
-	(void) view->regsets[0].get(t->task, &view->regsets[0],
-				    0, PR_REG_SIZE(t->prstatus.pr_reg),
-				    PR_REG_PTR(&t->prstatus), NULL);
+	(void) view->regsets[0].get(t->task, &view->regsets[0], 0, regset_size,
+				    &t->prstatus.pr_reg, NULL);
 
 	fill_note(&t->notes[0], "CORE", NT_PRSTATUS,
-		  PRSTATUS_SIZE(t->prstatus), &t->prstatus);
+		  PRSTATUS_SIZE(t->prstatus, regset_size), &t->prstatus);
 	*total += notesize(&t->notes[0]);
 
 	do_thread_regset_writeback(t->task, &view->regsets[0]);
@@ -1688,7 +1680,8 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
 						  regset->core_note_type,
 						  size, data);
 				else {
-					SET_PR_FPVALID(&t->prstatus, 1);
+					SET_PR_FPVALID(&t->prstatus,
+							1, regset_size);
 					fill_note(&t->notes[i], "CORE",
 						  NT_PRFPREG, size, data);
 				}

include/linux/mm.h

@@ -2019,6 +2019,8 @@ extern struct file *get_task_exe_file(struct task_struct *task);
 extern bool may_expand_vm(struct mm_struct *, vm_flags_t, unsigned long npages);
 extern void vm_stat_account(struct mm_struct *, vm_flags_t, long npages);
 
+extern bool vma_is_special_mapping(const struct vm_area_struct *vma,
+				   const struct vm_special_mapping *sm);
 extern struct vm_area_struct *_install_special_mapping(struct mm_struct *mm,
 				   unsigned long addr, unsigned long len,
 				   unsigned long flags,

kernel/signal.c

@@ -3044,6 +3044,11 @@ void kernel_sigaction(int sig, __sighandler_t action)
 }
 EXPORT_SYMBOL(kernel_sigaction);
 
+void __weak sigaction_compat_abi(struct k_sigaction *act,
+		struct k_sigaction *oact)
+{
+}
+
 int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact)
 {
 	struct task_struct *p = current, *t;
@@ -3059,6 +3064,8 @@ int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact)
 	if (oact)
 		*oact = *k;
 
+	sigaction_compat_abi(act, oact);
+
 	if (act) {
 		sigdelsetmask(&act->sa.sa_mask,
 			      sigmask(SIGKILL) | sigmask(SIGSTOP));

mm/mmap.c

@@ -3068,6 +3068,14 @@ static struct vm_area_struct *__install_special_mapping(
 	return ERR_PTR(ret);
 }
 
+bool vma_is_special_mapping(const struct vm_area_struct *vma,
+	const struct vm_special_mapping *sm)
+{
+	return vma->vm_private_data == sm &&
+		(vma->vm_ops == &special_mapping_vmops ||
+		 vma->vm_ops == &legacy_special_mapping_vmops);
+}
+
 /*
  * Called with mm->mmap_sem held for writing.
  * Insert a new vma covering the given region, with the given flags.