Merge tag 'x86_cleanups_for_v5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 cleanups from Borislav Petkov:
 "Another branch with a nicely negative diffstat, just the way I
  like 'em:

   - Remove all uses of TIF_IA32 and TIF_X32 and reclaim the two bits in
     the end (Gabriel Krisman Bertazi)

   - All kinds of minor cleanups all over the tree"

* tag 'x86_cleanups_for_v5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
  x86/ia32_signal: Propagate __user annotation properly
  x86/alternative: Update text_poke_bp() kernel-doc comment
  x86/PCI: Make a kernel-doc comment a normal one
  x86/asm: Drop unused RDPID macro
  x86/boot/compressed/64: Use TEST %reg,%reg instead of CMP $0,%reg
  x86/head64: Remove duplicate include
  x86/mm: Declare 'start' variable where it is used
  x86/head/64: Remove unused GET_CR2_INTO() macro
  x86/boot: Remove unused finalize_identity_maps()
  x86/uaccess: Document copy_from_user_nmi()
  x86/dumpstack: Make show_trace_log_lvl() static
  x86/mtrr: Fix a kernel-doc markup
  x86/setup: Remove unused MCA variables
  x86, libnvdimm/test: Remove COPY_MC_TEST
  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()
  ...

37 files changed, 105 insertions, 317 deletions

diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 27b5e2bc6a01..80b57e7f4947 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -62,9 +62,6 @@ config EARLY_PRINTK_USB_XDBC
 	  You should normally say N here, unless you want to debug early
 	  crashes or need a very simple printk logging facility.
 
-config COPY_MC_TEST
-	def_bool n
-
 config EFI_PGT_DUMP
 	bool "Dump the EFI pagetable"
 	depends on EFI
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 017de6cc87dc..e94874f4bbc1 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -241,12 +241,12 @@ SYM_FUNC_START(startup_32)
 	leal	rva(startup_64)(%ebp), %eax
 #ifdef CONFIG_EFI_MIXED
 	movl	rva(efi32_boot_args)(%ebp), %edi
-	cmp	$0, %edi
+	testl	%edi, %edi
 	jz	1f
 	leal	rva(efi64_stub_entry)(%ebp), %eax
 	movl	rva(efi32_boot_args+4)(%ebp), %esi
 	movl	rva(efi32_boot_args+8)(%ebp), %edx	// saved bootparams pointer
-	cmpl	$0, %edx
+	testl	%edx, %edx
 	jnz	1f
 	/*
 	 * efi_pe_entry uses MS calling convention, which requires 32 bytes of
@@ -592,7 +592,7 @@ SYM_CODE_START(trampoline_32bit_src)
 	movl	%eax, %cr0
 
 	/* Check what paging mode we want to be in after the trampoline */
-	cmpl	$0, %edx
+	testl	%edx, %edx
 	jz	1f
 
 	/* We want 5-level paging: don't touch CR3 if it already points to 5-level page tables */
@@ -622,7 +622,7 @@ SYM_CODE_START(trampoline_32bit_src)
 
 	/* Enable PAE and LA57 (if required) paging modes */
 	movl	$X86_CR4_PAE, %eax
-	cmpl	$0, %edx
+	testl	%edx, %edx
 	jz	1f
 	orl	$X86_CR4_LA57, %eax
 1:
diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c
index 39b2eded7bc2..f7213d0943b8 100644
--- a/arch/x86/boot/compressed/ident_map_64.c
+++ b/arch/x86/boot/compressed/ident_map_64.c
@@ -168,16 +168,6 @@ void initialize_identity_maps(void *rmode)
 	write_cr3(top_level_pgt);
 }
 
-/*
- * This switches the page tables to the new level4 that has been built
- * via calls to add_identity_map() above. If booted via startup_32(),
- * this is effectively a no-op.
- */
-void finalize_identity_maps(void)
-{
-	write_cr3(top_level_pgt);
-}
-
 static pte_t *split_large_pmd(struct x86_mapping_info *info,
 			      pmd_t *pmdp, unsigned long __address)
 {
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 9185cb1d13b9..50e5d3a2e70a 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/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);
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index 44c33103a955..1b40b9297083 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/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)
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index a88c94d65693..77b963e5e70a 100644
--- a/arch/x86/events/core.c
+++ b/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);
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 485c5066f8b8..a5c6ff5f1b4c 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1261,7 +1261,7 @@ 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);
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 8961653c5dd2..1aadb253d296 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/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);
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 81cf22398cd1..5e3d9b7fd5fb 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -347,7 +347,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig,
 	 */
 	unsafe_put_user(*((u64 *)&code), (u64 __user *)frame->retcode, Efault);
 	unsafe_put_sigcontext32(&frame->uc.uc_mcontext, fp, regs, set, Efault);
-	unsafe_put_user(*(__u64 *)set, (__u64 *)&frame->uc.uc_sigmask, Efault);
+	unsafe_put_user(*(__u64 *)set, (__u64 __user *)&frame->uc.uc_sigmask, Efault);
 	user_access_end();
 
 	if (__copy_siginfo_to_user32(&frame->info, &ksig->info))
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index 0e327a01f50f..f145e3326c6d 100644
--- a/arch/x86/include/asm/compat.h
+++ b/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;
-
-	if (test_thread_flag(TIF_IA32)) {
-		sp = task_pt_regs(current)->sp;
-	} else {
-		/* -128 for the x32 ABI redzone */
-		sp = task_pt_regs(current)->sp - 128;
-	}
+	compat_uptr_t sp = task_pt_regs(current)->sp;
+
+	/*
+	 * -128 for the x32 ABI redzone.  For IA32, it is not strictly
+	 * necessary, but not harmful.
+	 */
+	sp -= 128;
 
 	return (void __user *)round_down(sp - len, 16);
 }
diff --git a/arch/x86/include/asm/copy_mc_test.h b/arch/x86/include/asm/copy_mc_test.h
deleted file mode 100644
index e4991ba96726..000000000000
--- a/arch/x86/include/asm/copy_mc_test.h
+++ /dev/null
@@ -1,75 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _COPY_MC_TEST_H_
-#define _COPY_MC_TEST_H_
-
-#ifndef __ASSEMBLY__
-#ifdef CONFIG_COPY_MC_TEST
-extern unsigned long copy_mc_test_src;
-extern unsigned long copy_mc_test_dst;
-
-static inline void copy_mc_inject_src(void *addr)
-{
-	if (addr)
-		copy_mc_test_src = (unsigned long) addr;
-	else
-		copy_mc_test_src = ~0UL;
-}
-
-static inline void copy_mc_inject_dst(void *addr)
-{
-	if (addr)
-		copy_mc_test_dst = (unsigned long) addr;
-	else
-		copy_mc_test_dst = ~0UL;
-}
-#else /* CONFIG_COPY_MC_TEST */
-static inline void copy_mc_inject_src(void *addr)
-{
-}
-
-static inline void copy_mc_inject_dst(void *addr)
-{
-}
-#endif /* CONFIG_COPY_MC_TEST */
-
-#else /* __ASSEMBLY__ */
-#include <asm/export.h>
-
-#ifdef CONFIG_COPY_MC_TEST
-.macro COPY_MC_TEST_CTL
-	.pushsection .data
-	.align 8
-	.globl copy_mc_test_src
-	copy_mc_test_src:
-		.quad 0
-	EXPORT_SYMBOL_GPL(copy_mc_test_src)
-	.globl copy_mc_test_dst
-	copy_mc_test_dst:
-		.quad 0
-	EXPORT_SYMBOL_GPL(copy_mc_test_dst)
-	.popsection
-.endm
-
-.macro COPY_MC_TEST_SRC reg count target
-	leaq \count(\reg), %r9
-	cmp copy_mc_test_src, %r9
-	ja \target
-.endm
-
-.macro COPY_MC_TEST_DST reg count target
-	leaq \count(\reg), %r9
-	cmp copy_mc_test_dst, %r9
-	ja \target
-.endm
-#else
-.macro COPY_MC_TEST_CTL
-.endm
-
-.macro COPY_MC_TEST_SRC reg count target
-.endm
-
-.macro COPY_MC_TEST_DST reg count target
-.endm
-#endif /* CONFIG_COPY_MC_TEST */
-#endif /* __ASSEMBLY__ */
-#endif /* _COPY_MC_TEST_H_ */
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index b9a5d488f1a5..44a9b9940535 100644
--- a/arch/x86/include/asm/elf.h
+++ b/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);
-#define compat_start_thread compat_start_thread
+void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp, bool x32);
+#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);
-#define compat_arch_setup_additional_pages compat_arch_setup_additional_pages
+					      int uses_interp, bool x32);
+#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 {
diff --git a/arch/x86/include/asm/inst.h b/arch/x86/include/asm/inst.h
index bd7f02480ca1..438ccd4f3cc4 100644
--- a/arch/x86/include/asm/inst.h
+++ b/arch/x86/include/asm/inst.h
@@ -143,21 +143,6 @@
 	.macro MODRM mod opd1 opd2
 	.byte \mod | (\opd1 & 7) | ((\opd2 & 7) << 3)
 	.endm
-
-.macro RDPID opd
-	REG_TYPE rdpid_opd_type \opd
-	.if rdpid_opd_type == REG_TYPE_R64
-	R64_NUM rdpid_opd \opd
-	.else
-	R32_NUM rdpid_opd \opd
-	.endif
-	.byte 0xf3
-	.if rdpid_opd > 7
-	PFX_REX rdpid_opd 0
-	.endif
-	.byte 0x0f, 0xc7
-	MODRM 0xc0 rdpid_opd 0x7
-.endm
 #endif
 
 #endif
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 9257667d13c5..5d7494631ea9 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/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 ia32_compat;
+	unsigned short flags;
 #endif
 
 	struct mutex lock;
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index d98016b83755..054a79157323 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/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)
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index d25cc6830e89..f8dce11d2bc1 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -812,17 +812,6 @@ extern void default_banner(void);
 #endif /* CONFIG_PARAVIRT_XXL */
 #endif	/* CONFIG_X86_64 */
 
-#ifdef CONFIG_PARAVIRT_XXL
-
-#define GET_CR2_INTO_AX							\
-	PARA_SITE(PARA_PATCH(PV_MMU_read_cr2),				\
-		  ANNOTATE_RETPOLINE_SAFE;				\
-		  call PARA_INDIRECT(pv_ops+PV_MMU_read_cr2);		\
-		 )
-
-#endif /* CONFIG_PARAVIRT_XXL */
-
-
 #endif /* __ASSEMBLY__ */
 #else  /* CONFIG_PARAVIRT */
 # define default_banner x86_init_noop
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 49600643faba..f248eb2ac2d4 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -88,9 +88,6 @@ get_stack_pointer(struct task_struct *task, struct pt_regs *regs)
 	return (unsigned long *)task->thread.sp;
 }
 
-void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
-			unsigned long *stack, const char *log_lvl);
-
 /* The form of the top of the frame on the stack */
 struct stack_frame {
 	struct stack_frame *next_frame;
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 44733a4bfc42..a12b9644193b 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -91,7 +91,6 @@ 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_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 +100,6 @@ 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 +118,6 @@ 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_SLD		(1 << TIF_SLD)
 #define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
 #define _TIF_IO_BITMAP		(1 << TIF_IO_BITMAP)
@@ -129,7 +126,6 @@ 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					\
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 2400ad62f330..8d778e46725d 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -1374,7 +1374,7 @@ void __ref text_poke_queue(void *addr, const void *opcode, size_t len, const voi
  * @addr:	address to patch
  * @opcode:	opcode of new instruction
  * @len:	length to copy
- * @handler:	address to jump to when the temporary breakpoint is hit
+ * @emulate:	instruction to be emulated
  *
  * Update a single instruction with the vector in the stack, avoiding
  * dynamically allocated memory. This function should be used when it is
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 70b7154f4bdd..60b9f42ce3c1 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -66,7 +66,6 @@ static void __used common(void)
 	OFFSET(PV_IRQ_irq_disable, paravirt_patch_template, irq.irq_disable);
 	OFFSET(PV_IRQ_irq_enable, paravirt_patch_template, irq.irq_enable);
 	OFFSET(PV_CPU_iret, paravirt_patch_template, cpu.iret);
-	OFFSET(PV_MMU_read_cr2, paravirt_patch_template, mmu.read_cr2);
 #endif
 
 #ifdef CONFIG_XEN
diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c
index 6a80f36b5d59..08a30c8e9431 100644
--- a/arch/x86/kernel/cpu/mtrr/mtrr.c
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.c
@@ -813,7 +813,8 @@ void mtrr_ap_init(void)
 }
 
 /**
- * Save current fixed-range MTRR state of the first cpu in cpu_online_mask.
+ * mtrr_save_state - Save current fixed-range MTRR state of the first
+ *	cpu in cpu_online_mask.
  */
 void mtrr_save_state(void)
 {
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 97aa900386cb..299c20f0a38b 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -183,7 +183,7 @@ static void show_regs_if_on_stack(struct stack_info *info, struct pt_regs *regs,
 	}
 }
 
-void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
+static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 			unsigned long *stack, const char *log_lvl)
 {
 	struct unwind_state state;
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 05e117137b45..5e9beb77cafd 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -37,7 +37,6 @@
 #include <asm/kasan.h>
 #include <asm/fixmap.h>
 #include <asm/realmode.h>
-#include <asm/desc.h>
 #include <asm/extable.h>
 #include <asm/trapnr.h>
 #include <asm/sev-es.h>
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 3c417734790f..29889ff3f46a 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -26,15 +26,6 @@
 #include <asm/nospec-branch.h>
 #include <asm/fixmap.h>
 
-#ifdef CONFIG_PARAVIRT_XXL
-#include <asm/asm-offsets.h>
-#include <asm/paravirt.h>
-#define GET_CR2_INTO(reg) GET_CR2_INTO_AX ; _ASM_MOV %_ASM_AX, reg
-#else
-#define INTERRUPT_RETURN iretq
-#define GET_CR2_INTO(reg) _ASM_MOV %cr2, reg
-#endif
-
 /*
  * We are not able to switch in one step to the final KERNEL ADDRESS SPACE
  * because we need identity-mapped pages.
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index f9e5352b3bef..624703af80a1 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -122,7 +122,7 @@ 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;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index df342bedea88..ad582f9ac5a6 100644
--- a/arch/x86/kernel/process_64.c
+++ b/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)
-			    ? __USER_CS : __USER32_CS,
+			    x32 ? __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);
-	clear_thread_flag(TIF_X32);
-	if (current->mm)
-		current->mm->context.ia32_compat = TIF_IA32;
+	if (current->mm) {
+		/*
+		 * uprobes applied to this MM need to know this and
+		 * 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;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 84f581c91db4..a23130c86bdd 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -119,11 +119,6 @@ EXPORT_SYMBOL(boot_cpu_data);
 
 unsigned int def_to_bigsmp;
 
-/* For MCA, but anyone else can use it if they want */
-unsigned int machine_id;
-unsigned int machine_submodel_id;
-unsigned int BIOS_revision;
-
 struct apm_info apm_info;
 EXPORT_SYMBOL(apm_info);
 
diff --git a/arch/x86/lib/copy_mc.c b/arch/x86/lib/copy_mc.c
index c13e8c9ee926..80efd45a7761 100644
--- a/arch/x86/lib/copy_mc.c
+++ b/arch/x86/lib/copy_mc.c
@@ -10,10 +10,6 @@
 #include <asm/mce.h>
 
 #ifdef CONFIG_X86_MCE
-/*
- * See COPY_MC_TEST for self-test of the copy_mc_fragile()
- * implementation.
- */
 static DEFINE_STATIC_KEY_FALSE(copy_mc_fragile_key);
 
 void enable_copy_mc_fragile(void)
diff --git a/arch/x86/lib/copy_mc_64.S b/arch/x86/lib/copy_mc_64.S
index 892d8915f609..e5f77e293034 100644
--- a/arch/x86/lib/copy_mc_64.S
+++ b/arch/x86/lib/copy_mc_64.S
@@ -2,14 +2,11 @@
 /* Copyright(c) 2016-2020 Intel Corporation. All rights reserved. */
 
 #include <linux/linkage.h>
-#include <asm/copy_mc_test.h>
-#include <asm/export.h>
 #include <asm/asm.h>
 
 #ifndef CONFIG_UML
 
 #ifdef CONFIG_X86_MCE
-COPY_MC_TEST_CTL
 
 /*
  * copy_mc_fragile - copy memory with indication if an exception / fault happened
@@ -38,8 +35,6 @@ SYM_FUNC_START(copy_mc_fragile)
 	subl %ecx, %edx
 .L_read_leading_bytes:
 	movb (%rsi), %al
-	COPY_MC_TEST_SRC %rsi 1 .E_leading_bytes
-	COPY_MC_TEST_DST %rdi 1 .E_leading_bytes
 .L_write_leading_bytes:
 	movb %al, (%rdi)
 	incq %rsi
@@ -55,8 +50,6 @@ SYM_FUNC_START(copy_mc_fragile)
 
 .L_read_words:
 	movq (%rsi), %r8
-	COPY_MC_TEST_SRC %rsi 8 .E_read_words
-	COPY_MC_TEST_DST %rdi 8 .E_write_words
 .L_write_words:
 	movq %r8, (%rdi)
 	addq $8, %rsi
@@ -73,8 +66,6 @@ SYM_FUNC_START(copy_mc_fragile)
 	movl %edx, %ecx
 .L_read_trailing_bytes:
 	movb (%rsi), %al
-	COPY_MC_TEST_SRC %rsi 1 .E_trailing_bytes
-	COPY_MC_TEST_DST %rdi 1 .E_trailing_bytes
 .L_write_trailing_bytes:
 	movb %al, (%rdi)
 	incq %rsi
@@ -88,7 +79,6 @@ SYM_FUNC_START(copy_mc_fragile)
 .L_done:
 	ret
 SYM_FUNC_END(copy_mc_fragile)
-EXPORT_SYMBOL_GPL(copy_mc_fragile)
 
 	.section .fixup, "ax"
 	/*
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index 3f435d7fca5e..c3e8a62ca561 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -9,9 +9,23 @@
 
 #include <asm/tlbflush.h>
 
-/*
- * We rely on the nested NMI work to allow atomic faults from the NMI path; the
- * nested NMI paths are careful to preserve CR2.
+/**
+ * copy_from_user_nmi - NMI safe copy from user
+ * @to:		Pointer to the destination buffer
+ * @from:	Pointer to a user space address of the current task
+ * @n:		Number of bytes to copy
+ *
+ * Returns: The number of not copied bytes. 0 is success, i.e. all bytes copied
+ *
+ * Contrary to other copy_from_user() variants this function can be called
+ * from NMI context. Despite the name it is not restricted to be called
+ * from NMI context. It is safe to be called from any other context as
+ * well. It disables pagefaults across the copy which means a fault will
+ * abort the copy.
+ *
+ * For NMI context invocations this relies on the nested NMI work to allow
+ * atomic faults from the NMI path; the nested NMI paths are careful to
+ * preserve CR2.
  */
 unsigned long
 copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
@@ -27,7 +41,7 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 	/*
 	 * Even though this function is typically called from NMI/IRQ context
 	 * disable pagefaults so that its behaviour is consistent even when
-	 * called form other contexts.
+	 * called from other contexts.
 	 */
 	pagefault_disable();
 	ret = __copy_from_user_inatomic(to, from, n);
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index c7a47603537f..e26f5c5c6565 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -596,7 +596,7 @@ static unsigned long __init get_new_step_size(unsigned long step_size)
 static void __init memory_map_top_down(unsigned long map_start,
 				       unsigned long map_end)
 {
-	unsigned long real_end, start, last_start;
+	unsigned long real_end, last_start;
 	unsigned long step_size;
 	unsigned long addr;
 	unsigned long mapped_ram_size = 0;
@@ -609,7 +609,7 @@ static void __init memory_map_top_down(unsigned long map_start,
 	step_size = PMD_SIZE;
 	max_pfn_mapped = 0; /* will get exact value next */
 	min_pfn_mapped = real_end >> PAGE_SHIFT;
-	last_start = start = real_end;
+	last_start = real_end;
 
 	/*
 	 * We start from the top (end of memory) and go to the bottom.
@@ -618,6 +618,8 @@ static void __init memory_map_top_down(unsigned long map_start,
 	 * for page table.
 	 */
 	while (last_start > map_start) {
+		unsigned long start;
+
 		if (last_start > step_size) {
 			start = round_down(last_start - 1, step_size);
 			if (start < map_start)
diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c
index a2488b6e27d6..1d8391fcca68 100644
--- a/arch/x86/oprofile/backtrace.c
+++ b/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;
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index fa855bbaebaf..f2f4a5d50b27 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -366,9 +366,9 @@ static int __init pcibios_assign_resources(void)
 	return 0;
 }
 
-/**
- * called in fs_initcall (one below subsys_initcall),
- * give a chance for motherboard reserve resources
+/*
+ * This is an fs_initcall (one below subsys_initcall) in order to reserve
+ * resources properly.
  */
 fs_initcall(pcibios_assign_resources);
 
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index fa50e8936f5f..ac0b5fc30ea6 100644
--- a/fs/binfmt_elf.c
+++ b/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;
diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c
index 2d24c765cbd7..2c557229696a 100644
--- a/fs/compat_binfmt_elf.c
+++ b/fs/compat_binfmt_elf.c
@@ -106,15 +106,25 @@
 #endif
 
 #ifdef	compat_start_thread
-#undef	start_thread
-#define	start_thread		compat_start_thread
+#define COMPAT_START_THREAD(ex, regs, new_ip, new_sp)	\
+	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
-#define	arch_setup_additional_pages compat_arch_setup_additional_pages
+#undef	ARCH_SETUP_ADDITIONAL_PAGES
+#define	ARCH_SETUP_ADDITIONAL_PAGES COMPAT_ARCH_SETUP_ADDITIONAL_PAGES
 #endif
 
 #ifdef	compat_elf_read_implies_exec
diff --git a/include/linux/elf.h b/include/linux/elf.h
index 5d5b0321da0b..c9a46c4e183b 100644
--- a/include/linux/elf.h
+++ b/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
 
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 2ac0fff6dad8..9b185bf82da8 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -23,7 +23,6 @@
 #include "nfit_test.h"
 #include "../watermark.h"
 
-#include <asm/copy_mc_test.h>
 #include <asm/mce.h>
 
 /*
@@ -3284,107 +3283,6 @@ static struct platform_driver nfit_test_driver = {
 	.id_table = nfit_test_id,
 };
 
-static char copy_mc_buf[PAGE_SIZE] __attribute__((__aligned__(PAGE_SIZE)));
-
-enum INJECT {
-	INJECT_NONE,
-	INJECT_SRC,
-	INJECT_DST,
-};
-
-static void copy_mc_test_init(char *dst, char *src, size_t size)
-{
-	size_t i;
-
-	memset(dst, 0xff, size);
-	for (i = 0; i < size; i++)
-		src[i] = (char) i;
-}
-
-static bool copy_mc_test_validate(unsigned char *dst, unsigned char *src,
-		size_t size, unsigned long rem)
-{
-	size_t i;
-
-	for (i = 0; i < size - rem; i++)
-		if (dst[i] != (unsigned char) i) {
-			pr_info_once("%s:%d: offset: %zd got: %#x expect: %#x\n",
-					__func__, __LINE__, i, dst[i],
-					(unsigned char) i);
-			return false;
-		}
-	for (i = size - rem; i < size; i++)
-		if (dst[i] != 0xffU) {
-			pr_info_once("%s:%d: offset: %zd got: %#x expect: 0xff\n",
-					__func__, __LINE__, i, dst[i]);
-			return false;
-		}
-	return true;
-}
-
-void copy_mc_test(void)
-{
-	char *inject_desc[] = { "none", "source", "destination" };
-	enum INJECT inj;
-
-	if (IS_ENABLED(CONFIG_COPY_MC_TEST)) {
-		pr_info("%s: run...\n", __func__);
-	} else {
-		pr_info("%s: disabled, skip.\n", __func__);
-		return;
-	}
-
-	for (inj = INJECT_NONE; inj <= INJECT_DST; inj++) {
-		int i;
-
-		pr_info("%s: inject: %s\n", __func__, inject_desc[inj]);
-		for (i = 0; i < 512; i++) {
-			unsigned long expect, rem;
-			void *src, *dst;
-			bool valid;
-
-			switch (inj) {
-			case INJECT_NONE:
-				copy_mc_inject_src(NULL);
-				copy_mc_inject_dst(NULL);
-				dst = &copy_mc_buf[2048];
-				src = &copy_mc_buf[1024 - i];
-				expect = 0;
-				break;
-			case INJECT_SRC:
-				copy_mc_inject_src(&copy_mc_buf[1024]);
-				copy_mc_inject_dst(NULL);
-				dst = &copy_mc_buf[2048];
-				src = &copy_mc_buf[1024 - i];
-				expect = 512 - i;
-				break;
-			case INJECT_DST:
-				copy_mc_inject_src(NULL);
-				copy_mc_inject_dst(&copy_mc_buf[2048]);
-				dst = &copy_mc_buf[2048 - i];
-				src = &copy_mc_buf[1024];
-				expect = 512 - i;
-				break;
-			}
-
-			copy_mc_test_init(dst, src, 512);
-			rem = copy_mc_fragile(dst, src, 512);
-			valid = copy_mc_test_validate(dst, src, 512, expect);
-			if (rem == expect && valid)
-				continue;
-			pr_info("%s: copy(%#lx, %#lx, %d) off: %d rem: %ld %s expect: %ld\n",
-					__func__,
-					((unsigned long) dst) & ~PAGE_MASK,
-					((unsigned long ) src) & ~PAGE_MASK,
-					512, i, rem, valid ? "valid" : "bad",
-					expect);
-		}
-	}
-
-	copy_mc_inject_src(NULL);
-	copy_mc_inject_dst(NULL);
-}
-
 static __init int nfit_test_init(void)
 {
 	int rc, i;
@@ -3393,7 +3291,6 @@ static __init int nfit_test_init(void)
 	libnvdimm_test();
 	acpi_nfit_test();
 	device_dax_test();
-	copy_mc_test();
 	dax_pmem_test();
 	dax_pmem_core_test();
 #ifdef CONFIG_DEV_DAX_PMEM_COMPAT