Merge tag 'x86_core_for_v5.19_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull core x86 updates from Borislav Petkov:

 - Remove all the code around GS switching on 32-bit now that it is not
   needed anymore

 - Other misc improvements

* tag 'x86_core_for_v5.19_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  bug: Use normal relative pointers in 'struct bug_entry'
  x86/nmi: Make register_nmi_handler() more robust
  x86/asm: Merge load_gs_index()
  x86/32: Remove lazy GS macros
  ELF: Remove elf_core_copy_kernel_regs()
  x86/32: Simplify ELF_CORE_COPY_REGS

arch/arm64/include/asm/asm-bug.h

@@ -14,7 +14,7 @@
 	14472:	.string file;					\
 		.popsection;					\
 								\
-		.long 14472b - 14470b;				\
+		.long 14472b - .;				\
 		.short line;
 #else
 #define _BUGVERBOSE_LOCATION(file, line)
@@ -25,7 +25,7 @@
 #define __BUG_ENTRY(flags) 				\
 		.pushsection __bug_table,"aw";		\
 		.align 2;				\
-	14470:	.long 14471f - 14470b;			\
+	14470:	.long 14471f - .;			\
 _BUGVERBOSE_LOCATION(__FILE__, __LINE__)		\
 		.short flags; 				\
 		.popsection;				\

arch/powerpc/include/asm/bug.h

@@ -13,7 +13,8 @@
 #ifdef CONFIG_DEBUG_BUGVERBOSE
 .macro __EMIT_BUG_ENTRY addr,file,line,flags
 	 .section __bug_table,"aw"
-5001:	 .4byte \addr - 5001b, 5002f - 5001b
+5001:	 .4byte \addr - .
+	 .4byte 5002f - .
 	 .short \line, \flags
 	 .org 5001b+BUG_ENTRY_SIZE
 	 .previous
@@ -24,7 +25,7 @@
 #else
 .macro __EMIT_BUG_ENTRY addr,file,line,flags
 	 .section __bug_table,"aw"
-5001:	 .4byte \addr - 5001b
+5001:	 .4byte \addr - .
 	 .short \flags
 	 .org 5001b+BUG_ENTRY_SIZE
 	 .previous
@@ -49,15 +50,16 @@
 #ifdef CONFIG_DEBUG_BUGVERBOSE
 #define _EMIT_BUG_ENTRY				\
 	".section __bug_table,\"aw\"\n"		\
-	"2:\t.4byte 1b - 2b, %0 - 2b\n"		\
-	"\t.short %1, %2\n"			\
+	"2:	.4byte 1b - .\n"		\
+	"	.4byte %0 - .\n"		\
+	"	.short %1, %2\n"		\
 	".org 2b+%3\n"				\
 	".previous\n"
 #else
 #define _EMIT_BUG_ENTRY				\
 	".section __bug_table,\"aw\"\n"		\
-	"2:\t.4byte 1b - 2b\n"			\
-	"\t.short %2\n"				\
+	"2:	.4byte 1b - .\n"		\
+	"	.short %2\n"			\
 	".org 2b+%3\n"				\
 	".previous\n"
 #endif

arch/powerpc/kernel/fadump.c

@@ -752,7 +752,7 @@ u32 *__init fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs)
 	 * FIXME: How do i get PID? Do I really need it?
 	 * prstatus.pr_pid = ????
 	 */
-	elf_core_copy_kernel_regs(&prstatus.pr_reg, regs);
+	elf_core_copy_regs(&prstatus.pr_reg, regs);
 	buf = append_elf_note(buf, CRASH_CORE_NOTE_NAME, NT_PRSTATUS,
 			      &prstatus, sizeof(prstatus));
 	return buf;

arch/powerpc/platforms/powernv/opal-core.c

@@ -112,7 +112,7 @@ static void __init fill_prstatus(struct elf_prstatus *prstatus, int pir,
 			  struct pt_regs *regs)
 {
 	memset(prstatus, 0, sizeof(struct elf_prstatus));
-	elf_core_copy_kernel_regs(&(prstatus->pr_reg), regs);
+	elf_core_copy_regs(&(prstatus->pr_reg), regs);
 
 	/*
 	 * Overload PID with PIR value.

arch/riscv/include/asm/bug.h

@@ -30,8 +30,8 @@
 typedef u32 bug_insn_t;
 
 #ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
-#define __BUG_ENTRY_ADDR	RISCV_INT " 1b - 2b"
-#define __BUG_ENTRY_FILE	RISCV_INT " %0 - 2b"
+#define __BUG_ENTRY_ADDR	RISCV_INT " 1b - ."
+#define __BUG_ENTRY_FILE	RISCV_INT " %0 - ."
 #else
 #define __BUG_ENTRY_ADDR	RISCV_PTR " 1b"
 #define __BUG_ENTRY_FILE	RISCV_PTR " %0"

arch/s390/include/asm/bug.h

@@ -15,7 +15,8 @@
 		"1:	.asciz	\""__FILE__"\"\n"		\
 		".previous\n"					\
 		".section __bug_table,\"awM\",@progbits,%2\n"	\
-		"2:	.long	0b-2b,1b-2b\n"			\
+		"2:	.long	0b-.\n"				\
+		"	.long	1b-.\n"				\
 		"	.short	%0,%1\n"			\
 		"	.org	2b+%2\n"			\
 		".previous\n"					\
@@ -30,7 +31,7 @@
 	asm_inline volatile(					\
 		"0:	mc	0,0\n"				\
 		".section __bug_table,\"awM\",@progbits,%1\n"	\
-		"1:	.long	0b-1b\n"			\
+		"1:	.long	0b-.\n"				\
 		"	.short	%0\n"				\
 		"	.org	1b+%1\n"			\
 		".previous\n"					\

arch/x86/include/asm/bug.h

@@ -18,7 +18,7 @@
 #ifdef CONFIG_X86_32
 # define __BUG_REL(val)	".long " __stringify(val)
 #else
-# define __BUG_REL(val)	".long " __stringify(val) " - 2b"
+# define __BUG_REL(val)	".long " __stringify(val) " - ."
 #endif
 
 #ifdef CONFIG_DEBUG_BUGVERBOSE

arch/x86/include/asm/elf.h

@@ -116,7 +116,7 @@ extern unsigned int vdso32_enabled;
  * now struct_user_regs, they are different)
  */
 
-#define ELF_CORE_COPY_REGS_COMMON(pr_reg, regs)	\
+#define ELF_CORE_COPY_REGS(pr_reg, regs)	\
 do {						\
 	pr_reg[0] = regs->bx;			\
 	pr_reg[1] = regs->cx;			\
@@ -128,6 +128,7 @@ do {						\
 	pr_reg[7] = regs->ds;			\
 	pr_reg[8] = regs->es;			\
 	pr_reg[9] = regs->fs;			\
+	savesegment(gs, pr_reg[10]);		\
 	pr_reg[11] = regs->orig_ax;		\
 	pr_reg[12] = regs->ip;			\
 	pr_reg[13] = regs->cs;			\
@@ -136,18 +137,6 @@ do {						\
 	pr_reg[16] = regs->ss;			\
 } while (0);
 
-#define ELF_CORE_COPY_REGS(pr_reg, regs)	\
-do {						\
-	ELF_CORE_COPY_REGS_COMMON(pr_reg, regs);\
-	pr_reg[10] = get_user_gs(regs);		\
-} while (0);
-
-#define ELF_CORE_COPY_KERNEL_REGS(pr_reg, regs)	\
-do {						\
-	ELF_CORE_COPY_REGS_COMMON(pr_reg, regs);\
-	savesegment(gs, pr_reg[10]);		\
-} while (0);
-
 #define ELF_PLATFORM	(utsname()->machine)
 #define set_personality_64bit()	do { } while (0)
 

arch/x86/include/asm/mmu_context.h

@@ -141,7 +141,7 @@ do {						\
 #ifdef CONFIG_X86_32
 #define deactivate_mm(tsk, mm)			\
 do {						\
-	lazy_load_gs(0);			\
+	loadsegment(gs, 0);			\
 } while (0)
 #else
 #define deactivate_mm(tsk, mm)			\

arch/x86/include/asm/nmi.h

@@ -47,6 +47,7 @@ struct nmiaction {
 #define register_nmi_handler(t, fn, fg, n, init...)	\
 ({							\
 	static struct nmiaction init fn##_na = {	\
+		.list = LIST_HEAD_INIT(fn##_na.list),	\
 		.handler = (fn),			\
 		.name = (n),				\
 		.flags = (fg),				\

arch/x86/include/asm/segment.h

@@ -350,18 +350,6 @@ static inline void __loadsegment_fs(unsigned short value)
 #define savesegment(seg, value)				\
 	asm("mov %%" #seg ",%0":"=r" (value) : : "memory")
 
-/*
- * x86-32 user GS accessors.  This is ugly and could do with some cleaning up.
- */
-#ifdef CONFIG_X86_32
-# define get_user_gs(regs)		(u16)({ unsigned long v; savesegment(gs, v); v; })
-# define set_user_gs(regs, v)		loadsegment(gs, (unsigned long)(v))
-# define task_user_gs(tsk)		((tsk)->thread.gs)
-# define lazy_save_gs(v)		savesegment(gs, (v))
-# define lazy_load_gs(v)		loadsegment(gs, (v))
-# define load_gs_index(v)		loadsegment(gs, (v))
-#endif	/* X86_32 */
-
 #endif /* !__ASSEMBLY__ */
 #endif /* __KERNEL__ */
 

arch/x86/include/asm/special_insns.h

@@ -184,14 +184,15 @@ static inline void wbinvd(void)
 	native_wbinvd();
 }
 
-#ifdef CONFIG_X86_64
 
 static inline void load_gs_index(unsigned int selector)
 {
+#ifdef CONFIG_X86_64
 	native_load_gs_index(selector);
-}
-
+#else
+	loadsegment(gs, selector);
 #endif
+}
 
 #endif /* CONFIG_PARAVIRT_XXL */
 

arch/x86/kernel/nmi.c

@@ -157,7 +157,7 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action)
 	struct nmi_desc *desc = nmi_to_desc(type);
 	unsigned long flags;
 
-	if (!action->handler)
+	if (WARN_ON_ONCE(!action->handler || !list_empty(&action->list)))
 		return -EINVAL;
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
@@ -177,7 +177,7 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action)
 		list_add_rcu(&action->list, &desc->head);
 	else
 		list_add_tail_rcu(&action->list, &desc->head);
-	
+
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 	return 0;
 }
@@ -186,7 +186,7 @@ EXPORT_SYMBOL(__register_nmi_handler);
 void unregister_nmi_handler(unsigned int type, const char *name)
 {
 	struct nmi_desc *desc = nmi_to_desc(type);
-	struct nmiaction *n;
+	struct nmiaction *n, *found = NULL;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
@@ -200,12 +200,16 @@ void unregister_nmi_handler(unsigned int type, const char *name)
 			WARN(in_nmi(),
 				"Trying to free NMI (%s) from NMI context!\n", n->name);
 			list_del_rcu(&n->list);
+			found = n;
 			break;
 		}
 	}
 
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	synchronize_rcu();
+	if (found) {
+		synchronize_rcu();
+		INIT_LIST_HEAD(&found->list);
+	}
 }
 EXPORT_SYMBOL_GPL(unregister_nmi_handler);
 

arch/x86/kernel/process.c

@@ -161,6 +161,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
 	savesegment(ds, p->thread.ds);
 #else
 	p->thread.sp0 = (unsigned long) (childregs + 1);
+	savesegment(gs, p->thread.gs);
 	/*
 	 * Clear all status flags including IF and set fixed bit. 64bit
 	 * does not have this initialization as the frame does not contain
@@ -192,10 +193,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
 	if (sp)
 		childregs->sp = sp;
 
-#ifdef CONFIG_X86_32
-	task_user_gs(p) = get_user_gs(current_pt_regs());
-#endif
-
 	if (unlikely(p->flags & PF_IO_WORKER)) {
 		/*
 		 * An IO thread is a user space thread, but it doesn't

arch/x86/kernel/process_32.c

@@ -63,10 +63,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode,
 	unsigned long d0, d1, d2, d3, d6, d7;
 	unsigned short gs;
 
-	if (user_mode(regs))
-		gs = get_user_gs(regs);
-	else
-		savesegment(gs, gs);
+	savesegment(gs, gs);
 
 	show_ip(regs, log_lvl);
 
@@ -114,7 +111,7 @@ void release_thread(struct task_struct *dead_task)
 void
 start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
 {
-	set_user_gs(regs, 0);
+	loadsegment(gs, 0);
 	regs->fs		= 0;
 	regs->ds		= __USER_DS;
 	regs->es		= __USER_DS;
@@ -177,7 +174,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 * used %fs or %gs (it does not today), or if the kernel is
 	 * running inside of a hypervisor layer.
 	 */
-	lazy_save_gs(prev->gs);
+	savesegment(gs, prev->gs);
 
 	/*
 	 * Load the per-thread Thread-Local Storage descriptor.
@@ -208,7 +205,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 * Restore %gs if needed (which is common)
 	 */
 	if (prev->gs | next->gs)
-		lazy_load_gs(next->gs);
+		loadsegment(gs, next->gs);
 
 	this_cpu_write(current_task, next_p);
 

arch/x86/kernel/ptrace.c

@@ -170,9 +170,9 @@ static u16 get_segment_reg(struct task_struct *task, unsigned long offset)
 		retval = *pt_regs_access(task_pt_regs(task), offset);
 	else {
 		if (task == current)
-			retval = get_user_gs(task_pt_regs(task));
+			savesegment(gs, retval);
 		else
-			retval = task_user_gs(task);
+			retval = task->thread.gs;
 	}
 	return retval;
 }
@@ -210,7 +210,7 @@ static int set_segment_reg(struct task_struct *task,
 		break;
 
 	case offsetof(struct user_regs_struct, gs):
-		task_user_gs(task) = value;
+		task->thread.gs = value;
 	}
 
 	return 0;

arch/x86/kernel/signal.c

@@ -93,7 +93,7 @@ static bool restore_sigcontext(struct pt_regs *regs,
 		return false;
 
 #ifdef CONFIG_X86_32
-	set_user_gs(regs, sc.gs);
+	loadsegment(gs, sc.gs);
 	regs->fs = sc.fs;
 	regs->es = sc.es;
 	regs->ds = sc.ds;
@@ -146,8 +146,10 @@ __unsafe_setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
 		     struct pt_regs *regs, unsigned long mask)
 {
 #ifdef CONFIG_X86_32
-	unsafe_put_user(get_user_gs(regs),
-				  (unsigned int __user *)&sc->gs, Efault);
+	unsigned int gs;
+	savesegment(gs, gs);
+
+	unsafe_put_user(gs,	  (unsigned int __user *)&sc->gs, Efault);
 	unsafe_put_user(regs->fs, (unsigned int __user *)&sc->fs, Efault);
 	unsafe_put_user(regs->es, (unsigned int __user *)&sc->es, Efault);
 	unsafe_put_user(regs->ds, (unsigned int __user *)&sc->ds, Efault);

arch/x86/kernel/vm86_32.c

@@ -151,7 +151,7 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval)
 
 	memcpy(&regs->pt, &vm86->regs32, sizeof(struct pt_regs));
 
-	lazy_load_gs(vm86->regs32.gs);
+	loadsegment(gs, vm86->regs32.gs);
 
 	regs->pt.ax = retval;
 	return;
@@ -325,7 +325,7 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus)
  * Save old state
  */
 	vm86->saved_sp0 = tsk->thread.sp0;
-	lazy_save_gs(vm86->regs32.gs);
+	savesegment(gs, vm86->regs32.gs);
 
 	/* make room for real-mode segments */
 	preempt_disable();

arch/x86/lib/insn-eval.c

@@ -342,9 +342,9 @@ static int resolve_seg_reg(struct insn *insn, struct pt_regs *regs, int regoff)
  */
 static short get_segment_selector(struct pt_regs *regs, int seg_reg_idx)
 {
-#ifdef CONFIG_X86_64
 	unsigned short sel;
 
+#ifdef CONFIG_X86_64
 	switch (seg_reg_idx) {
 	case INAT_SEG_REG_IGNORE:
 		return 0;
@@ -402,7 +402,8 @@ static short get_segment_selector(struct pt_regs *regs, int seg_reg_idx)
 	case INAT_SEG_REG_FS:
 		return (unsigned short)(regs->fs & 0xffff);
 	case INAT_SEG_REG_GS:
-		return get_user_gs(regs);
+		savesegment(gs, sel);
+		return sel;
 	case INAT_SEG_REG_IGNORE:
 	default:
 		return -EINVAL;

arch/x86/math-emu/get_address.c

@@ -153,7 +153,7 @@ static long pm_address(u_char FPU_modrm, u_char segment,
 	switch (segment) {
 	case PREFIX_GS_ - 1:
 		/* user gs handling can be lazy, use special accessors */
-		addr->selector = get_user_gs(FPU_info->regs);
+		savesegment(gs, addr->selector);
 		break;
 	default:
 		addr->selector = PM_REG_(segment);

include/linux/elfcore.h

@@ -84,15 +84,6 @@ static inline void elf_core_copy_regs(elf_gregset_t *elfregs, struct pt_regs *re
 #endif
 }
 
-static inline void elf_core_copy_kernel_regs(elf_gregset_t *elfregs, struct pt_regs *regs)
-{
-#ifdef ELF_CORE_COPY_KERNEL_REGS
-	ELF_CORE_COPY_KERNEL_REGS((*elfregs), regs);
-#else
-	elf_core_copy_regs(elfregs, regs);
-#endif
-}
-
 static inline int elf_core_copy_task_regs(struct task_struct *t, elf_gregset_t* elfregs)
 {
 #if defined (ELF_CORE_COPY_TASK_REGS)

kernel/kexec_core.c

@@ -1078,7 +1078,7 @@ void crash_save_cpu(struct pt_regs *regs, int cpu)
 		return;
 	memset(&prstatus, 0, sizeof(prstatus));
 	prstatus.common.pr_pid = current->pid;
-	elf_core_copy_kernel_regs(&prstatus.pr_reg, regs);
+	elf_core_copy_regs(&prstatus.pr_reg, regs);
 	buf = append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS,
 			      &prstatus, sizeof(prstatus));
 	final_note(buf);

lib/bug.c

@@ -6,8 +6,7 @@
 
   CONFIG_BUG - emit BUG traps.  Nothing happens without this.
   CONFIG_GENERIC_BUG - enable this code.
-  CONFIG_GENERIC_BUG_RELATIVE_POINTERS - use 32-bit pointers relative to
-	the containing struct bug_entry for bug_addr and file.
+  CONFIG_GENERIC_BUG_RELATIVE_POINTERS - use 32-bit relative pointers for bug_addr and file
   CONFIG_DEBUG_BUGVERBOSE - emit full file+line information for each BUG
 
   CONFIG_BUG and CONFIG_DEBUG_BUGVERBOSE are potentially user-settable
@@ -53,10 +52,10 @@ extern struct bug_entry __start___bug_table[], __stop___bug_table[];
 
 static inline unsigned long bug_addr(const struct bug_entry *bug)
 {
-#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
-	return bug->bug_addr;
+#ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
+	return (unsigned long)&bug->bug_addr_disp + bug->bug_addr_disp;
 #else
-	return (unsigned long)bug + bug->bug_addr_disp;
+	return bug->bug_addr;
 #endif
 }
 
@@ -131,10 +130,10 @@ void bug_get_file_line(struct bug_entry *bug, const char **file,
 		       unsigned int *line)
 {
 #ifdef CONFIG_DEBUG_BUGVERBOSE
-#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
-	*file = bug->file;
+#ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
+	*file = (const char *)&bug->file_disp + bug->file_disp;
 #else
-	*file = (const char *)bug + bug->file_disp;
+	*file = bug->file;
 #endif
 	*line = bug->line;
 #else