mm/fault, arch: Use pagefault_disable() to check for disabled pagefaults in the handler

Introduce faulthandler_disabled() and use it to check for irq context and
disabled pagefaults (via pagefault_disable()) in the pagefault handlers.

Please note that we keep the in_atomic() checks in place - to detect
whether in irq context (in which case preemption is always properly
disabled).

In contrast, preempt_disable() should never be used to disable pagefaults.
With !CONFIG_PREEMPT_COUNT, preempt_disable() doesn't modify the preempt
counter, and therefore the result of in_atomic() differs.
We validate that condition by using might_fault() checks when calling
might_sleep().

Therefore, add a comment to faulthandler_disabled(), describing why this
is needed.

faulthandler_disabled() and pagefault_disable() are defined in
linux/uaccess.h, so let's properly add that include to all relevant files.

This patch is based on a patch from Thomas Gleixner.

Reviewed-and-tested-by: Thomas Gleixner <[e-mail]>
Signed-off-by: David Hildenbrand <[e-mail]>
Signed-off-by: Peter Zijlstra (Intel) <[e-mail]>
Cc: [e-mail]
Cc: Linus Torvalds <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Thomas Gleixner <[e-mail]>
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Link: http://lkml.kernel.org/r/[e-mail]
Signed-off-by: Ingo Molnar <[e-mail]>

arch/alpha/mm/fault.c

···
 #include <linux/smp.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
-
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 extern void die_if_kernel(char *,struct pt_regs *,long, unsigned long *);
 
···
 
 	/* If we're in an interrupt context, or have no user context,
 	   we must not take the fault.  */
-	if (!mm || in_atomic())
+	if (!mm || faulthandler_disabled())
 		goto no_context;
 
 #ifdef CONFIG_ALPHA_LARGE_VMALLOC

arch/arc/mm/fault.c

···
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))

arch/arm/mm/fault.c

···
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))

arch/arm64/mm/fault.c

···
 	 * If we're in an interrupt or have no user context, we must not take
 	 * the fault.
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))

arch/avr32/mm/fault.c

···
 #include <linux/pagemap.h>
 #include <linux/kdebug.h>
 #include <linux/kprobes.h>
+#include <linux/uaccess.h>
 
 #include <asm/mmu_context.h>
 #include <asm/sysreg.h>
 #include <asm/tlb.h>
-#include <asm/uaccess.h>
 
 #ifdef CONFIG_KPROBES
 static inline int notify_page_fault(struct pt_regs *regs, int trap)
···
 	 * If we're in an interrupt or have no user context, we must
 	 * not take the fault...
 	 */
-	if (in_atomic() || !mm || regs->sr & SYSREG_BIT(GM))
+	if (faulthandler_disabled() || !mm || regs->sr & SYSREG_BIT(GM))
 		goto no_context;
 
 	local_irq_enable();

arch/cris/mm/fault.c

···
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/wait.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <arch/system.h>
 
 extern int find_fixup_code(struct pt_regs *);
···
 	info.si_code = SEGV_MAPERR;
 
 	/*
-	 * If we're in an interrupt or "atomic" operation or have no
+	 * If we're in an interrupt, have pagefaults disabled or have no
 	 * user context, we must not take the fault.
 	 */
 
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))

arch/frv/mm/fault.c

···
 #include <linux/kernel.h>
 #include <linux/ptrace.h>
 #include <linux/hardirq.h>
+#include <linux/uaccess.h>
 
 #include <asm/pgtable.h>
-#include <asm/uaccess.h>
 #include <asm/gdb-stub.h>
 
 /*****************************************************************************/
···
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(__frame))

arch/ia64/mm/fault.c

···
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
 #include <linux/prefetch.h>
+#include <linux/uaccess.h>
 
 #include <asm/pgtable.h>
 #include <asm/processor.h>
-#include <asm/uaccess.h>
 
 extern int die(char *, struct pt_regs *, long);
 
···
 	/*
 	 * If we're in an interrupt or have no user context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP

arch/m32r/mm/fault.c

···
 #include <linux/vt_kern.h>		/* For unblank_screen() */
 #include <linux/highmem.h>
 #include <linux/module.h>
+#include <linux/uaccess.h>
 
 #include <asm/m32r.h>
-#include <asm/uaccess.h>
 #include <asm/hardirq.h>
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
···
 	mm = tsk->mm;
 
 	/*
-	 * If we're in an interrupt or have no user context or are running in an
-	 * atomic region then we must not take the fault..
+	 * If we're in an interrupt or have no user context or have pagefaults
+	 * disabled then we must not take the fault.
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto bad_area_nosemaphore;
 
 	if (error_code & ACE_USERMODE)

arch/m68k/mm/fault.c

···
 #include <linux/ptrace.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
+#include <linux/uaccess.h>
 
 #include <asm/setup.h>
 #include <asm/traps.h>
-#include <asm/uaccess.h>
 #include <asm/pgalloc.h>
 
 extern void die_if_kernel(char *, struct pt_regs *, long);
···
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))

arch/metag/mm/fault.c

···
 
 	mm = tsk->mm;
 
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))

arch/microblaze/mm/fault.c

···
 	if ((error_code & 0x13) == 0x13 || (error_code & 0x11) == 0x11)
 		is_write = 0;
 
-	if (unlikely(in_atomic() || !mm)) {
+	if (unlikely(faulthandler_disabled() || !mm)) {
 		if (kernel_mode(regs))
 			goto bad_area_nosemaphore;
 
-		/* in_atomic() in user mode is really bad,
+		/* faulthandler_disabled() in user mode is really bad,
 		   as is current->mm == NULL. */
-		pr_emerg("Page fault in user mode with in_atomic(), mm = %p\n",
-									mm);
+		pr_emerg("Page fault in user mode with faulthandler_disabled(), mm = %p\n",
+			 mm);
 		pr_emerg("r15 = %lx  MSR = %lx\n",
 		       regs->r15, regs->msr);
 		die("Weird page fault", regs, SIGSEGV);

arch/mips/mm/fault.c

···
 #include <linux/module.h>
 #include <linux/kprobes.h>
 #include <linux/perf_event.h>
+#include <linux/uaccess.h>
 
 #include <asm/branch.h>
 #include <asm/mmu_context.h>
-#include <asm/uaccess.h>
 #include <asm/ptrace.h>
 #include <asm/highmem.h>		/* For VMALLOC_END */
 #include <linux/kdebug.h>
···
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto bad_area_nosemaphore;
 
 	if (user_mode(regs))

arch/mn10300/mm/fault.c

···
 #include <linux/interrupt.h>
 #include <linux/init.h>
 #include <linux/vt_kern.h>		/* For unblank_screen() */
+#include <linux/uaccess.h>
 
-#include <asm/uaccess.h>
 #include <asm/pgalloc.h>
 #include <asm/hardirq.h>
 #include <asm/cpu-regs.h>
···
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR)

arch/nios2/mm/fault.c

···
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto bad_area_nosemaphore;
 
 	if (user_mode(regs))

arch/parisc/kernel/traps.c

···
 #include <linux/console.h>
 #include <linux/bug.h>
 #include <linux/ratelimit.h>
+#include <linux/uaccess.h>
 
 #include <asm/assembly.h>
-#include <asm/uaccess.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/traps.h>
···
 	     * unless pagefault_disable() was called before.
 	     */
 
-	    if (fault_space == 0 && !in_atomic())
+	    if (fault_space == 0 && !faulthandler_disabled())
 	    {
 		pdc_chassis_send_status(PDC_CHASSIS_DIRECT_PANIC);
 		parisc_terminate("Kernel Fault", regs, code, fault_address);

arch/parisc/mm/fault.c

···
 #include <linux/sched.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
+#include <linux/uaccess.h>
 
-#include <asm/uaccess.h>
 #include <asm/traps.h>
 
 /* Various important other fields */
···
 	int fault;
 	unsigned int flags;
 
-	if (in_atomic())
+	if (pagefault_disabled())
 		goto no_context;
 
 	tsk = current;

arch/powerpc/mm/fault.c

···
 #include <linux/ratelimit.h>
 #include <linux/context_tracking.h>
 #include <linux/hugetlb.h>
+#include <linux/uaccess.h>
 
 #include <asm/firmware.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
-#include <asm/uaccess.h>
 #include <asm/tlbflush.h>
 #include <asm/siginfo.h>
 #include <asm/debug.h>
···
 	if (!arch_irq_disabled_regs(regs))
 		local_irq_enable();
 
-	if (in_atomic() || mm == NULL) {
+	if (faulthandler_disabled() || mm == NULL) {
 		if (!user_mode(regs)) {
 			rc = SIGSEGV;
 			goto bail;
 		}
-		/* in_atomic() in user mode is really bad,
+		/* faulthandler_disabled() in user mode is really bad,
 		   as is current->mm == NULL. */
 		printk(KERN_EMERG "Page fault in user mode with "
-		       "in_atomic() = %d mm = %p\n", in_atomic(), mm);
+		       "faulthandler_disabled() = %d mm = %p\n",
+		       faulthandler_disabled(), mm);
 		printk(KERN_EMERG "NIP = %lx  MSR = %lx\n",
 		       regs->nip, regs->msr);
 		die("Weird page fault", regs, SIGSEGV);

arch/s390/mm/fault.c

···
 	 * user context.
 	 */
 	fault = VM_FAULT_BADCONTEXT;
-	if (unlikely(!user_space_fault(regs) || in_atomic() || !mm))
+	if (unlikely(!user_space_fault(regs) || faulthandler_disabled() || !mm))
 		goto out;
 
 	address = trans_exc_code & __FAIL_ADDR_MASK;

arch/score/mm/fault.c

···
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/ptrace.h>
+#include <linux/uaccess.h>
 
 /*
  * This routine handles page faults.  It determines the address,
···
 	* If we're in an interrupt or have no user
 	* context, we must not take the fault..
 	*/
-	if (in_atomic() || !mm)
+	if (pagefault_disabled() || !mm)
 		goto bad_area_nosemaphore;
 
 	if (user_mode(regs))

arch/sh/mm/fault.c

···
 #include <linux/kprobes.h>
 #include <linux/perf_event.h>
 #include <linux/kdebug.h>
+#include <linux/uaccess.h>
 #include <asm/io_trapped.h>
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
···
 
 	/*
 	 * If we're in an interrupt, have no user context or are running
-	 * in an atomic region then we must not take the fault:
+	 * with pagefaults disabled then we must not take the fault:
 	 */
-	if (unlikely(in_atomic() || !mm)) {
+	if (unlikely(faulthandler_disabled() || !mm)) {
 		bad_area_nosemaphore(regs, error_code, address);
 		return;
 	}

arch/sparc/mm/fault_32.c

···
 #include <linux/perf_event.h>
 #include <linux/interrupt.h>
 #include <linux/kdebug.h>
+#include <linux/uaccess.h>
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
···
 #include <asm/setup.h>
 #include <asm/smp.h>
 #include <asm/traps.h>
-#include <asm/uaccess.h>
 
 #include "mm_32.h"
 
···
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (pagefault_disabled() || !mm)
 		goto no_context;
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);

arch/sparc/mm/fault_64.c

···
 #include <linux/kdebug.h>
 #include <linux/percpu.h>
 #include <linux/context_tracking.h>
+#include <linux/uaccess.h>
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/openprom.h>
 #include <asm/oplib.h>
-#include <asm/uaccess.h>
 #include <asm/asi.h>
 #include <asm/lsu.h>
 #include <asm/sections.h>
···
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto intr_or_no_mm;
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);

arch/sparc/mm/init_64.c

···
 	struct mm_struct *mm = current->mm;
 	struct tsb_config *tp;
 
-	if (in_atomic() || !mm) {
+	if (faulthandler_disabled() || !mm) {
 		const struct exception_table_entry *entry;
 
 		entry = search_exception_tables(regs->tpc);

arch/tile/mm/fault.c

···
 
 	/*
 	 * If we're in an interrupt, have no user context or are running in an
-	 * atomic region then we must not take the fault.
+	 * region with pagefaults disabled then we must not take the fault.
 	 */
-	if (in_atomic() || !mm) {
+	if (pagefault_disabled() || !mm) {
 		vma = NULL;  /* happy compiler */
 		goto bad_area_nosemaphore;
 	}

arch/um/kernel/trap.c

···
 	*code_out = SEGV_MAPERR;
 
 	/*
-	 * If the fault was during atomic operation, don't take the fault, just
+	 * If the fault was with pagefaults disabled, don't take the fault, just
 	 * fail.
 	 */
-	if (in_atomic())
+	if (faulthandler_disabled())
 		goto out_nosemaphore;
 
 	if (is_user)

arch/unicore32/mm/fault.c

···
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))

arch/x86/mm/fault.c

···
 #include <linux/hugetlb.h>		/* hstate_index_to_shift	*/
 #include <linux/prefetch.h>		/* prefetchw			*/
 #include <linux/context_tracking.h>	/* exception_enter(), ...	*/
+#include <linux/uaccess.h>		/* faulthandler_disabled()	*/
 
 #include <asm/traps.h>			/* dotraplinkage, ...		*/
 #include <asm/pgalloc.h>		/* pgd_*(), ...			*/
···
 
 	/*
 	 * If we're in an interrupt, have no user context or are running
-	 * in an atomic region then we must not take the fault:
+	 * in a region with pagefaults disabled then we must not take the fault
 	 */
-	if (unlikely(in_atomic() || !mm)) {
+	if (unlikely(faulthandler_disabled() || !mm)) {
 		bad_area_nosemaphore(regs, error_code, address);
 		return;
 	}

arch/xtensa/mm/fault.c

···
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/hardirq.h>
+#include <linux/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
 #include <asm/hardirq.h>
-#include <asm/uaccess.h>
 #include <asm/pgalloc.h>
 
 DEFINE_PER_CPU(unsigned long, asid_cache) = ASID_USER_FIRST;
···
 	/* If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm) {
+	if (faulthandler_disabled() || !mm) {
 		bad_page_fault(regs, address, SIGSEGV);
 		return;
 	}

include/linux/uaccess.h

···
  */
 #define pagefault_disabled() (current->pagefault_disabled != 0)
 
+/*
+ * The pagefault handler is in general disabled by pagefault_disable() or
+ * when in irq context (via in_atomic()).
+ *
+ * This function should only be used by the fault handlers. Other users should
+ * stick to pagefault_disabled().
+ * Please NEVER use preempt_disable() to disable the fault handler. With
+ * !CONFIG_PREEMPT_COUNT, this is like a NOP. So the handler won't be disabled.
+ * in_atomic() will report different values based on !CONFIG_PREEMPT_COUNT.
+ */
+#define faulthandler_disabled() (pagefault_disabled() || in_atomic())
+
 #ifndef ARCH_HAS_NOCACHE_UACCESS
 
 static inline unsigned long __copy_from_user_inatomic_nocache(void *to,