Merge branch 'x86/entry' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip into tif-task_work.arch

* 'x86/entry' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86: Wire up TIF_NOTIFY_SIGNAL
  x86: Reclaim TIF_IA32 and TIF_X32
  x86/mm: Convert mmu context ia32_compat into a proper flags field
  x86/elf: Use e_machine to check for x32/ia32 in setup_additional_pages()
  elf: Expose ELF header on arch_setup_additional_pages()
  x86/elf: Use e_machine to select start_thread for x32
  elf: Expose ELF header in compat_start_thread()
  x86/elf: Use e_machine to choose DLINFO in compat
  x86/oprofile: Avoid TIF_IA32 when checking 64bit mode
  x86/compat: Simplify compat syscall userspace allocation
  perf/x86: Avoid TIF_IA32 when checking 64bit mode

arch/x86/entry/vdso/vma.c

@@ -413,10 +413,10 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 
 #ifdef CONFIG_COMPAT
 int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
-				       int uses_interp)
+				       int uses_interp, bool x32)
 {
 #ifdef CONFIG_X86_X32_ABI
-	if (test_thread_flag(TIF_X32)) {
+	if (x32) {
 		if (!vdso64_enabled)
 			return 0;
 		return map_vdso_randomized(&vdso_image_x32);

arch/x86/entry/vsyscall/vsyscall_64.c

@@ -316,7 +316,7 @@ static struct vm_area_struct gate_vma __ro_after_init = {
 struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
 {
 #ifdef CONFIG_COMPAT
-	if (!mm || mm->context.ia32_compat)
+	if (!mm || !(mm->context.flags & MM_CONTEXT_HAS_VSYSCALL))
 		return NULL;
 #endif
 	if (vsyscall_mode == NONE)

arch/x86/events/core.c

@@ -2602,7 +2602,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent
 	struct stack_frame_ia32 frame;
 	const struct stack_frame_ia32 __user *fp;
 
-	if (!test_thread_flag(TIF_IA32))
+	if (user_64bit_mode(regs))
 		return 0;
 
 	cs_base = get_segment_base(regs->cs);

arch/x86/events/intel/ds.c

@@ -1259,7 +1259,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 		old_to = to;
 
 #ifdef CONFIG_X86_64
-		is_64bit = kernel_ip(to) || !test_thread_flag(TIF_IA32);
+		is_64bit = kernel_ip(to) || any_64bit_mode(regs);
 #endif
 		insn_init(&insn, kaddr, size, is_64bit);
 		insn_get_length(&insn);

arch/x86/events/intel/lbr.c

@@ -1221,7 +1221,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
 	 * on 64-bit systems running 32-bit apps
 	 */
 #ifdef CONFIG_X86_64
-	is64 = kernel_ip((unsigned long)addr) || !test_thread_flag(TIF_IA32);
+	is64 = kernel_ip((unsigned long)addr) || any_64bit_mode(current_pt_regs());
 #endif
 	insn_init(&insn, addr, bytes_read, is64);
 	insn_get_opcode(&insn);

arch/x86/include/asm/compat.h

@@ -177,14 +177,13 @@ typedef struct user_regs_struct compat_elf_gregset_t;
 
 static inline void __user *arch_compat_alloc_user_space(long len)
 {
-	compat_uptr_t sp;
+	compat_uptr_t sp = task_pt_regs(current)->sp;
 
-	if (test_thread_flag(TIF_IA32)) {
+	/*
-		sp = task_pt_regs(current)->sp;
+	 * -128 for the x32 ABI redzone.  For IA32, it is not strictly
-	} else {
+	 * necessary, but not harmful.
-		/* -128 for the x32 ABI redzone */
+	 */
-		sp = task_pt_regs(current)->sp - 128;
+	sp -= 128;
-	}
 
 	return (void __user *)round_down(sp - len, 16);
 }

arch/x86/include/asm/elf.h

@@ -186,8 +186,9 @@ static inline void elf_common_init(struct thread_struct *t,
 #define	COMPAT_ELF_PLAT_INIT(regs, load_addr)		\
 	elf_common_init(&current->thread, regs, __USER_DS)
 
-void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp);
+void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp, bool x32);
-#define compat_start_thread compat_start_thread
+#define COMPAT_START_THREAD(ex, regs, new_ip, new_sp)	\
+	compat_start_thread(regs, new_ip, new_sp, ex->e_machine == EM_X86_64)
 
 void set_personality_ia32(bool);
 #define COMPAT_SET_PERSONALITY(ex)			\
@@ -361,7 +362,7 @@ do {									\
 #define AT_SYSINFO		32
 
 #define COMPAT_ARCH_DLINFO						\
-if (test_thread_flag(TIF_X32))						\
+if (exec->e_machine == EM_X86_64)					\
 	ARCH_DLINFO_X32;						\
 else									\
 	ARCH_DLINFO_IA32
@@ -382,8 +383,10 @@ struct linux_binprm;
 extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 				       int uses_interp);
 extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
-					      int uses_interp);
+					      int uses_interp, bool x32);
-#define compat_arch_setup_additional_pages compat_arch_setup_additional_pages
+#define COMPAT_ARCH_SETUP_ADDITIONAL_PAGES(bprm, ex, interpreter)	\
+	compat_arch_setup_additional_pages(bprm, interpreter,		\
+					   (ex->e_machine == EM_X86_64))
 
 /* Do not change the values. See get_align_mask() */
 enum align_flags {

arch/x86/include/asm/mmu.h

@@ -6,6 +6,12 @@
 #include <linux/rwsem.h>
 #include <linux/mutex.h>
 #include <linux/atomic.h>
+#include <linux/bits.h>
+
+/* Uprobes on this MM assume 32-bit code */
+#define MM_CONTEXT_UPROBE_IA32	BIT(0)
+/* vsyscall page is accessible on this MM */
+#define MM_CONTEXT_HAS_VSYSCALL	BIT(1)
 
 /*
  * x86 has arch-specific MMU state beyond what lives in mm_struct.
@@ -33,8 +39,7 @@ typedef struct {
 #endif
 
 #ifdef CONFIG_X86_64
-	/* True if mm supports a task running in 32 bit compatibility mode. */
+	unsigned short flags;
-	unsigned short ia32_compat;
 #endif
 
 	struct mutex lock;

arch/x86/include/asm/mmu_context.h

@@ -177,7 +177,7 @@ static inline void arch_exit_mmap(struct mm_struct *mm)
 static inline bool is_64bit_mm(struct mm_struct *mm)
 {
 	return	!IS_ENABLED(CONFIG_IA32_EMULATION) ||
-		!(mm->context.ia32_compat == TIF_IA32);
+		!(mm->context.flags & MM_CONTEXT_UPROBE_IA32);
 }
 #else
 static inline bool is_64bit_mm(struct mm_struct *mm)

arch/x86/include/asm/thread_info.h

@@ -91,7 +91,7 @@ struct thread_info {
 #define TIF_NEED_FPU_LOAD	14	/* load FPU on return to userspace */
 #define TIF_NOCPUID		15	/* CPUID is not accessible in userland */
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
-#define TIF_IA32		17	/* IA32 compatibility process */
+#define TIF_NOTIFY_SIGNAL	17	/* signal notifications exist */
 #define TIF_SLD			18	/* Restore split lock detection on context switch */
 #define TIF_MEMDIE		20	/* is terminating due to OOM killer */
 #define TIF_POLLING_NRFLAG	21	/* idle is polling for TIF_NEED_RESCHED */
@@ -101,7 +101,6 @@ struct thread_info {
 #define TIF_LAZY_MMU_UPDATES	27	/* task is updating the mmu lazily */
 #define TIF_SYSCALL_TRACEPOINT	28	/* syscall tracepoint instrumentation */
 #define TIF_ADDR32		29	/* 32-bit address space on 64 bits */
-#define TIF_X32			30	/* 32-bit native x86-64 binary */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
@@ -120,7 +119,7 @@ struct thread_info {
 #define _TIF_NEED_FPU_LOAD	(1 << TIF_NEED_FPU_LOAD)
 #define _TIF_NOCPUID		(1 << TIF_NOCPUID)
 #define _TIF_NOTSC		(1 << TIF_NOTSC)
-#define _TIF_IA32		(1 << TIF_IA32)
+#define _TIF_NOTIFY_SIGNAL	(1 << TIF_NOTIFY_SIGNAL)
 #define _TIF_SLD		(1 << TIF_SLD)
 #define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
 #define _TIF_IO_BITMAP		(1 << TIF_IO_BITMAP)
@@ -129,7 +128,6 @@ struct thread_info {
 #define _TIF_LAZY_MMU_UPDATES	(1 << TIF_LAZY_MMU_UPDATES)
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
 #define _TIF_ADDR32		(1 << TIF_ADDR32)
-#define _TIF_X32		(1 << TIF_X32)
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW_BASE					\

arch/x86/kernel/perf_regs.c

@@ -123,7 +123,7 @@ int perf_reg_validate(u64 mask)
 
 u64 perf_reg_abi(struct task_struct *task)
 {
-	if (test_tsk_thread_flag(task, TIF_IA32))
+	if (!user_64bit_mode(task_pt_regs(task)))
 		return PERF_SAMPLE_REGS_ABI_32;
 	else
 		return PERF_SAMPLE_REGS_ABI_64;

arch/x86/kernel/process_64.c

@@ -511,11 +511,10 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
 EXPORT_SYMBOL_GPL(start_thread);
 
 #ifdef CONFIG_COMPAT
-void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp)
+void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp, bool x32)
 {
 	start_thread_common(regs, new_ip, new_sp,
-			    test_thread_flag(TIF_X32)
+			    x32 ? __USER_CS : __USER32_CS,
-			    ? __USER_CS : __USER32_CS,
 			    __USER_DS, __USER_DS);
 }
 #endif
@@ -641,16 +640,12 @@ void set_personality_64bit(void)
 	/* inherit personality from parent */
 
 	/* Make sure to be in 64bit mode */
-	clear_thread_flag(TIF_IA32);
 	clear_thread_flag(TIF_ADDR32);
-	clear_thread_flag(TIF_X32);
 	/* Pretend that this comes from a 64bit execve */
 	task_pt_regs(current)->orig_ax = __NR_execve;
 	current_thread_info()->status &= ~TS_COMPAT;
-
-	/* Ensure the corresponding mm is not marked. */
 	if (current->mm)
-		current->mm->context.ia32_compat = 0;
+		current->mm->context.flags = MM_CONTEXT_HAS_VSYSCALL;
 
 	/* TBD: overwrites user setup. Should have two bits.
 	   But 64bit processes have always behaved this way,
@@ -662,10 +657,9 @@ void set_personality_64bit(void)
 static void __set_personality_x32(void)
 {
 #ifdef CONFIG_X86_X32
-	clear_thread_flag(TIF_IA32);
-	set_thread_flag(TIF_X32);
 	if (current->mm)
-		current->mm->context.ia32_compat = TIF_X32;
+		current->mm->context.flags = 0;
+
 	current->personality &= ~READ_IMPLIES_EXEC;
 	/*
 	 * in_32bit_syscall() uses the presence of the x32 syscall bit
@@ -683,10 +677,14 @@ static void __set_personality_x32(void)
 static void __set_personality_ia32(void)
 {
 #ifdef CONFIG_IA32_EMULATION
-	set_thread_flag(TIF_IA32);
+	if (current->mm) {
-	clear_thread_flag(TIF_X32);
+		/*
-	if (current->mm)
+		 * uprobes applied to this MM need to know this and
-		current->mm->context.ia32_compat = TIF_IA32;
+		 * cannot use user_64bit_mode() at that time.
+		 */
+		current->mm->context.flags = MM_CONTEXT_UPROBE_IA32;
+	}
+
 	current->personality |= force_personality32;
 	/* Prepare the first "return" to user space */
 	task_pt_regs(current)->orig_ax = __NR_ia32_execve;

arch/x86/oprofile/backtrace.c

@@ -49,7 +49,7 @@ x86_backtrace_32(struct pt_regs * const regs, unsigned int depth)
 	struct stack_frame_ia32 *head;
 
 	/* User process is IA32 */
-	if (!current || !test_thread_flag(TIF_IA32))
+	if (!current || user_64bit_mode(regs))
 		return 0;
 
 	head = (struct stack_frame_ia32 *) regs->bp;

fs/binfmt_elf.c

@@ -1246,7 +1246,7 @@ out_free_interp:
 	set_binfmt(&elf_format);
 
 #ifdef ARCH_HAS_SETUP_ADDITIONAL_PAGES
-	retval = arch_setup_additional_pages(bprm, !!interpreter);
+	retval = ARCH_SETUP_ADDITIONAL_PAGES(bprm, elf_ex, !!interpreter);
 	if (retval < 0)
 		goto out;
 #endif /* ARCH_HAS_SETUP_ADDITIONAL_PAGES */
@@ -1307,7 +1307,7 @@ out_free_interp:
 #endif
 
 	finalize_exec(bprm);
-	start_thread(regs, elf_entry, bprm->p);
+	START_THREAD(elf_ex, regs, elf_entry, bprm->p);
 	retval = 0;
 out:
 	return retval;

fs/compat_binfmt_elf.c

@@ -106,15 +106,25 @@
 #endif
 
 #ifdef	compat_start_thread
-#undef	start_thread
+#define COMPAT_START_THREAD(ex, regs, new_ip, new_sp)	\
-#define	start_thread		compat_start_thread
+	compat_start_thread(regs, new_ip, new_sp)
 #endif
 
-#ifdef	compat_arch_setup_additional_pages
+#ifdef	COMPAT_START_THREAD
+#undef	START_THREAD
+#define START_THREAD		COMPAT_START_THREAD
+#endif
+
+#ifdef compat_arch_setup_additional_pages
+#define COMPAT_ARCH_SETUP_ADDITIONAL_PAGES(bprm, ex, interpreter) \
+	compat_arch_setup_additional_pages(bprm, interpreter)
+#endif
+
+#ifdef	COMPAT_ARCH_SETUP_ADDITIONAL_PAGES
 #undef	ARCH_HAS_SETUP_ADDITIONAL_PAGES
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
-#undef	arch_setup_additional_pages
+#undef	ARCH_SETUP_ADDITIONAL_PAGES
-#define	arch_setup_additional_pages compat_arch_setup_additional_pages
+#define	ARCH_SETUP_ADDITIONAL_PAGES COMPAT_ARCH_SETUP_ADDITIONAL_PAGES
 #endif
 
 #ifdef	compat_elf_read_implies_exec

include/linux/elf.h

@@ -22,6 +22,16 @@
 	SET_PERSONALITY(ex)
 #endif
 
+#ifndef START_THREAD
+#define START_THREAD(elf_ex, regs, elf_entry, start_stack)	\
+	start_thread(regs, elf_entry, start_stack)
+#endif
+
+#if defined(ARCH_HAS_SETUP_ADDITIONAL_PAGES) && !defined(ARCH_SETUP_ADDITIONAL_PAGES)
+#define ARCH_SETUP_ADDITIONAL_PAGES(bprm, ex, interpreter) \
+	arch_setup_additional_pages(bprm, interpreter)
+#endif
+
 #define ELF32_GNU_PROPERTY_ALIGN	4
 #define ELF64_GNU_PROPERTY_ALIGN	8