Merge branch 'perf/uprobes' into perf/core

These bits from Oleg are fully cooked, ship them to Linus.
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/include/asm/traps.h

@@ -98,7 +98,6 @@ static inline int get_si_code(unsigned long condition)
 
 extern int panic_on_unrecovered_nmi;
 
-void math_error(struct pt_regs *, int, int);
 void math_emulate(struct math_emu_info *);
 #ifndef CONFIG_X86_32
 asmlinkage void smp_thermal_interrupt(void);

arch/x86/include/asm/uprobes.h

@@ -41,18 +41,18 @@ struct arch_uprobe {
 		u8			ixol[MAX_UINSN_BYTES];
 	};
 
-	u16				fixups;
 	const struct uprobe_xol_ops	*ops;
 
 	union {
-#ifdef CONFIG_X86_64
-		unsigned long			rip_rela_target_address;
-#endif
 		struct {
 			s32	offs;
 			u8	ilen;
 			u8	opc1;
 		}			branch;
+		struct {
+			u8	fixups;
+			u8	ilen;
+		} 			def;
 	};
 };
 

arch/x86/kernel/process_64.c

@@ -413,12 +413,11 @@ void set_personality_ia32(bool x32)
 	set_thread_flag(TIF_ADDR32);
 
 	/* Mark the associated mm as containing 32-bit tasks. */
-	if (current->mm)
-		current->mm->context.ia32_compat = 1;
-
 	if (x32) {
 		clear_thread_flag(TIF_IA32);
 		set_thread_flag(TIF_X32);
+		if (current->mm)
+			current->mm->context.ia32_compat = TIF_X32;
 		current->personality &= ~READ_IMPLIES_EXEC;
 		/* is_compat_task() uses the presence of the x32
 		   syscall bit flag to determine compat status */
@@ -426,6 +425,8 @@ void set_personality_ia32(bool x32)
 	} else {
 		set_thread_flag(TIF_IA32);
 		clear_thread_flag(TIF_X32);
+		if (current->mm)
+			current->mm->context.ia32_compat = TIF_IA32;
 		current->personality |= force_personality32;
 		/* Prepare the first "return" to user space */
 		current_thread_info()->status |= TS_COMPAT;

arch/x86/kernel/traps.c

@@ -23,6 +23,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/ptrace.h>
+#include <linux/uprobes.h>
 #include <linux/string.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
@@ -136,6 +137,37 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
 	return -1;
 }
 
+static siginfo_t *fill_trap_info(struct pt_regs *regs, int signr, int trapnr,
+				siginfo_t *info)
+{
+	unsigned long siaddr;
+	int sicode;
+
+	switch (trapnr) {
+	default:
+		return SEND_SIG_PRIV;
+
+	case X86_TRAP_DE:
+		sicode = FPE_INTDIV;
+		siaddr = uprobe_get_trap_addr(regs);
+		break;
+	case X86_TRAP_UD:
+		sicode = ILL_ILLOPN;
+		siaddr = uprobe_get_trap_addr(regs);
+		break;
+	case X86_TRAP_AC:
+		sicode = BUS_ADRALN;
+		siaddr = 0;
+		break;
+	}
+
+	info->si_signo = signr;
+	info->si_errno = 0;
+	info->si_code = sicode;
+	info->si_addr = (void __user *)siaddr;
+	return info;
+}
+
 static void __kprobes
 do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
 	long error_code, siginfo_t *info)
@@ -168,60 +200,42 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
 	}
 #endif
 
-	if (info)
-		force_sig_info(signr, info, tsk);
-	else
-		force_sig(signr, tsk);
+	force_sig_info(signr, info ?: SEND_SIG_PRIV, tsk);
 }
 
-#define DO_ERROR(trapnr, signr, str, name)				\
-dotraplinkage void do_##name(struct pt_regs *regs, long error_code)	\
-{									\
-	enum ctx_state prev_state;					\
-									\
-	prev_state = exception_enter();					\
-	if (notify_die(DIE_TRAP, str, regs, error_code,			\
-			trapnr, signr) == NOTIFY_STOP) {		\
-		exception_exit(prev_state);				\
-		return;							\
-	}								\
-	conditional_sti(regs);						\
-	do_trap(trapnr, signr, str, regs, error_code, NULL);		\
-	exception_exit(prev_state);					\
+static void do_error_trap(struct pt_regs *regs, long error_code, char *str,
+			  unsigned long trapnr, int signr)
+{
+	enum ctx_state prev_state = exception_enter();
+	siginfo_t info;
+
+	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) !=
+			NOTIFY_STOP) {
+		conditional_sti(regs);
+		do_trap(trapnr, signr, str, regs, error_code,
+			fill_trap_info(regs, signr, trapnr, &info));
+	}
+
+	exception_exit(prev_state);
 }
 
-#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr)		\
+#define DO_ERROR(trapnr, signr, str, name)				\
 dotraplinkage void do_##name(struct pt_regs *regs, long error_code)	\
 {									\
-	siginfo_t info;							\
-	enum ctx_state prev_state;					\
-									\
-	info.si_signo = signr;						\
-	info.si_errno = 0;						\
-	info.si_code = sicode;						\
-	info.si_addr = (void __user *)siaddr;				\
-	prev_state = exception_enter();					\
-	if (notify_die(DIE_TRAP, str, regs, error_code,			\
-			trapnr, signr) == NOTIFY_STOP) {		\
-		exception_exit(prev_state);				\
-		return;							\
-	}								\
-	conditional_sti(regs);						\
-	do_trap(trapnr, signr, str, regs, error_code, &info);		\
-	exception_exit(prev_state);					\
+	do_error_trap(regs, error_code, str, trapnr, signr);		\
 }
 
-DO_ERROR_INFO(X86_TRAP_DE,     SIGFPE,  "divide error",			divide_error,		     FPE_INTDIV, regs->ip )
-DO_ERROR     (X86_TRAP_OF,     SIGSEGV, "overflow",			overflow					  )
-DO_ERROR     (X86_TRAP_BR,     SIGSEGV, "bounds",			bounds						  )
-DO_ERROR_INFO(X86_TRAP_UD,     SIGILL,  "invalid opcode",		invalid_op,		     ILL_ILLOPN, regs->ip )
-DO_ERROR     (X86_TRAP_OLD_MF, SIGFPE,  "coprocessor segment overrun",	coprocessor_segment_overrun			  )
-DO_ERROR     (X86_TRAP_TS,     SIGSEGV, "invalid TSS",			invalid_TSS					  )
-DO_ERROR     (X86_TRAP_NP,     SIGBUS,  "segment not present",		segment_not_present				  )
+DO_ERROR(X86_TRAP_DE,     SIGFPE,  "divide error",		divide_error)
+DO_ERROR(X86_TRAP_OF,     SIGSEGV, "overflow",			overflow)
+DO_ERROR(X86_TRAP_BR,     SIGSEGV, "bounds",			bounds)
+DO_ERROR(X86_TRAP_UD,     SIGILL,  "invalid opcode",		invalid_op)
+DO_ERROR(X86_TRAP_OLD_MF, SIGFPE,  "coprocessor segment overrun",coprocessor_segment_overrun)
+DO_ERROR(X86_TRAP_TS,     SIGSEGV, "invalid TSS",		invalid_TSS)
+DO_ERROR(X86_TRAP_NP,     SIGBUS,  "segment not present",	segment_not_present)
 #ifdef CONFIG_X86_32
-DO_ERROR     (X86_TRAP_SS,     SIGBUS,  "stack segment",		stack_segment					  )
+DO_ERROR(X86_TRAP_SS,     SIGBUS,  "stack segment",		stack_segment)
 #endif
-DO_ERROR_INFO(X86_TRAP_AC,     SIGBUS,  "alignment check",		alignment_check,	     BUS_ADRALN, 0	  )
+DO_ERROR(X86_TRAP_AC,     SIGBUS,  "alignment check",		alignment_check)
 
 #ifdef CONFIG_X86_64
 /* Runs on IST stack */
@@ -305,7 +319,7 @@ do_general_protection(struct pt_regs *regs, long error_code)
 		pr_cont("\n");
 	}
 
-	force_sig(SIGSEGV, tsk);
+	force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk);
 exit:
 	exception_exit(prev_state);
 }
@@ -488,7 +502,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
  * the correct behaviour even in the presence of the asynchronous
  * IRQ13 behaviour
  */
-void math_error(struct pt_regs *regs, int error_code, int trapnr)
+static void math_error(struct pt_regs *regs, int error_code, int trapnr)
 {
 	struct task_struct *task = current;
 	siginfo_t info;
@@ -518,7 +532,7 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr)
 	task->thread.error_code = error_code;
 	info.si_signo = SIGFPE;
 	info.si_errno = 0;
-	info.si_addr = (void __user *)regs->ip;
+	info.si_addr = (void __user *)uprobe_get_trap_addr(regs);
 	if (trapnr == X86_TRAP_MF) {
 		unsigned short cwd, swd;
 		/*
@@ -645,7 +659,7 @@ void math_state_restore(void)
 	 */
 	if (unlikely(restore_fpu_checking(tsk))) {
 		drop_init_fpu(tsk);
-		force_sig(SIGSEGV, tsk);
+		force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk);
 		return;
 	}
 

include/linux/uprobes.h

@@ -102,6 +102,7 @@ extern int __weak set_orig_insn(struct arch_uprobe *aup, struct mm_struct *mm, u
 extern bool __weak is_swbp_insn(uprobe_opcode_t *insn);
 extern bool __weak is_trap_insn(uprobe_opcode_t *insn);
 extern unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs);
+extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs);
 extern int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t);
 extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);
 extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool);
@@ -130,6 +131,9 @@ extern bool __weak arch_uprobe_ignore(struct arch_uprobe *aup, struct pt_regs *r
 #else /* !CONFIG_UPROBES */
 struct uprobes_state {
 };
+
+#define uprobe_get_trap_addr(regs)	instruction_pointer(regs)
+
 static inline int
 uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc)
 {

kernel/events/uprobes.c

@@ -127,7 +127,7 @@ struct xol_area {
  */
 static bool valid_vma(struct vm_area_struct *vma, bool is_register)
 {
-	vm_flags_t flags = VM_HUGETLB | VM_MAYEXEC | VM_SHARED;
+	vm_flags_t flags = VM_HUGETLB | VM_MAYEXEC | VM_MAYSHARE;
 
 	if (is_register)
 		flags |= VM_WRITE;
@@ -279,18 +279,13 @@ static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t
  * supported by that architecture then we need to modify is_trap_at_addr and
  * uprobe_write_opcode accordingly. This would never be a problem for archs
  * that have fixed length instructions.
- */
-
-/*
+ *
  * uprobe_write_opcode - write the opcode at a given virtual address.
  * @mm: the probed process address space.
  * @vaddr: the virtual address to store the opcode.
  * @opcode: opcode to be written at @vaddr.
  *
- * Called with mm->mmap_sem held (for read and with a reference to
- * mm).
- *
- * For mm @mm, write the opcode at @vaddr.
+ * Called with mm->mmap_sem held for write.
  * Return 0 (success) or a negative errno.
  */
 int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr,
@@ -310,21 +305,25 @@ int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr,
 	if (ret <= 0)
 		goto put_old;
 
+	ret = anon_vma_prepare(vma);
+	if (ret)
+		goto put_old;
+
 	ret = -ENOMEM;
 	new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr);
 	if (!new_page)
 		goto put_old;
 
-	__SetPageUptodate(new_page);
+	if (mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL))
+		goto put_new;
 
+	__SetPageUptodate(new_page);
 	copy_highpage(new_page, old_page);
 	copy_to_page(new_page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
 
-	ret = anon_vma_prepare(vma);
-	if (ret)
-		goto put_new;
-
 	ret = __replace_page(vma, vaddr, old_page, new_page);
+	if (ret)
+		mem_cgroup_uncharge_page(new_page);
 
 put_new:
 	page_cache_release(new_page);
@@ -1352,6 +1351,16 @@ unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs)
 	return instruction_pointer(regs) - UPROBE_SWBP_INSN_SIZE;
 }
 
+unsigned long uprobe_get_trap_addr(struct pt_regs *regs)
+{
+	struct uprobe_task *utask = current->utask;
+
+	if (unlikely(utask && utask->active_uprobe))
+		return utask->vaddr;
+
+	return instruction_pointer(regs);
+}
+
 /*
  * Called with no locks held.
  * Called in context of a exiting or a exec-ing thread.

kernel/trace/trace_uprobe.c

@@ -1009,56 +1009,60 @@ uprobe_filter_event(struct trace_uprobe *tu, struct perf_event *event)
 	return __uprobe_perf_filter(&tu->filter, event->hw.tp_target->mm);
 }
 
-static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event)
+static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event)
 {
 	bool done;
 
 	write_lock(&tu->filter.rwlock);
 	if (event->hw.tp_target) {
-		/*
-		 * event->parent != NULL means copy_process(), we can avoid
-		 * uprobe_apply(). current->mm must be probed and we can rely
-		 * on dup_mmap() which preserves the already installed bp's.
-		 *
-		 * attr.enable_on_exec means that exec/mmap will install the
-		 * breakpoints we need.
-		 */
+		list_del(&event->hw.tp_list);
 		done = tu->filter.nr_systemwide ||
-			event->parent || event->attr.enable_on_exec ||
+			(event->hw.tp_target->flags & PF_EXITING) ||
 			uprobe_filter_event(tu, event);
-		list_add(&event->hw.tp_list, &tu->filter.perf_events);
 	} else {
+		tu->filter.nr_systemwide--;
 		done = tu->filter.nr_systemwide;
-		tu->filter.nr_systemwide++;
 	}
 	write_unlock(&tu->filter.rwlock);
 
 	if (!done)
-		uprobe_apply(tu->inode, tu->offset, &tu->consumer, true);
+		return uprobe_apply(tu->inode, tu->offset, &tu->consumer, false);
 
 	return 0;
 }
 
-static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event)
+static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event)
 {
 	bool done;
+	int err;
 
 	write_lock(&tu->filter.rwlock);
 	if (event->hw.tp_target) {
-		list_del(&event->hw.tp_list);
+		/*
+		 * event->parent != NULL means copy_process(), we can avoid
+		 * uprobe_apply(). current->mm must be probed and we can rely
+		 * on dup_mmap() which preserves the already installed bp's.
+		 *
+		 * attr.enable_on_exec means that exec/mmap will install the
+		 * breakpoints we need.
+		 */
 		done = tu->filter.nr_systemwide ||
-			(event->hw.tp_target->flags & PF_EXITING) ||
+			event->parent || event->attr.enable_on_exec ||
 			uprobe_filter_event(tu, event);
+		list_add(&event->hw.tp_list, &tu->filter.perf_events);
 	} else {
-		tu->filter.nr_systemwide--;
 		done = tu->filter.nr_systemwide;
+		tu->filter.nr_systemwide++;
 	}
 	write_unlock(&tu->filter.rwlock);
 
-	if (!done)
-		uprobe_apply(tu->inode, tu->offset, &tu->consumer, false);
-
-	return 0;
+	err = 0;
+	if (!done) {
+		err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true);
+		if (err)
+			uprobe_perf_close(tu, event);
+	}
+	return err;
 }
 
 static bool uprobe_perf_filter(struct uprobe_consumer *uc,