arch: mm: pass userspace fault flag to generic fault handler

commit 759496ba6407c6994d6a5ce3a5e74937d7816208 upstream.

Unlike global OOM handling, memory cgroup code will invoke the OOM killer
in any OOM situation because it has no way of telling faults occuring in
kernel context - which could be handled more gracefully - from
user-triggered faults.

Pass a flag that identifies faults originating in user space from the
architecture-specific fault handlers to generic code so that memcg OOM
handling can be improved.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: azurIt <azurit@pobox.sk>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index 0c4132dd3507a0b62b3c40c2fc6fd4065a325262..98838a05ba6d89f0459742131010f57c38cbed05 100644 (file)
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -89,8 +89,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
        const struct exception_table_entry *fixup;
        int fault, si_code = SEGV_MAPERR;
        siginfo_t info;
-       unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-                             (cause > 0 ? FAULT_FLAG_WRITE : 0));
+       unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
        /* As of EV6, a load into $31/$f31 is a prefetch, and never faults
           (or is suppressed by the PALcode).  Support that for older CPUs
@@ -115,7 +114,8 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
        if (address >= TASK_SIZE)
                goto vmalloc_fault;
 #endif
-
+       if (user_mode(regs))
+               flags |= FAULT_FLAG_USER;
 retry:
        down_read(&mm->mmap_sem);
        vma = find_vma(mm, address);
@@ -142,6 +142,7 @@ retry:
        } else {
                if (!(vma->vm_flags & VM_WRITE))
                        goto bad_area;
+               flags |= FAULT_FLAG_WRITE;
        }
 
        /* If for any reason at all we couldn't handle the fault,

diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index 87f4281a4b6439b7a6c3097303798db6807eb5e2..50533b750a99d88dfd7e0fa1d89deb87717f9095 100644 (file)
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -59,8 +59,7 @@ void do_page_fault(struct pt_regs *regs, int write, unsigned long address,
        struct mm_struct *mm = tsk->mm;
        siginfo_t info;
        int fault, ret;
-       unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-                               (write ? FAULT_FLAG_WRITE : 0);
+       unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
        /*
         * We fault-in kernel-space virtual memory on-demand. The
@@ -88,6 +87,8 @@ void do_page_fault(struct pt_regs *regs, int write, unsigned long address,
        if (in_atomic() || !mm)
                goto no_context;
 
+       if (user_mode(regs))
+               flags |= FAULT_FLAG_USER;
 retry:
        down_read(&mm->mmap_sem);
        vma = find_vma(mm, address);
@@ -115,6 +116,7 @@ good_area:
        if (write) {
                if (!(vma->vm_flags & VM_WRITE))
                        goto bad_area;
+               flags |= FAULT_FLAG_WRITE;
        } else {
                if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
                        goto bad_area;

diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 2ebf4f6dc026d8f152b6675cd26d2c2a61d07a2c..160da6d655467cb68ed837433b4d74fae3f33086 100644 (file)
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -261,9 +261,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
        struct task_struct *tsk;
        struct mm_struct *mm;
        int fault, sig, code;
-       int write = fsr & FSR_WRITE;
-       unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-                               (write ? FAULT_FLAG_WRITE : 0);
+       unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
        if (notify_page_fault(regs, fsr))
                return 0;
@@ -282,6 +280,11 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
        if (in_atomic() || !mm)
                goto no_context;
 
+       if (user_mode(regs))
+               flags |= FAULT_FLAG_USER;
+       if (fsr & FSR_WRITE)
+               flags |= FAULT_FLAG_WRITE;
+
        /*
         * As per x86, we may deadlock here.  However, since the kernel only
         * validly references user space from well defined areas of the code,

diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index f5f0c70da7a155f1b94628a0cd617bea34995724..b5d458769b655dfbbcfc7e04eacda68ed99720d2 100644 (file)
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -199,13 +199,6 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
        unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC;
        unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
-       if (esr & ESR_LNX_EXEC) {
-               vm_flags = VM_EXEC;
-       } else if ((esr & ESR_WRITE) && !(esr & ESR_CM)) {
-               vm_flags = VM_WRITE;
-               mm_flags |= FAULT_FLAG_WRITE;
-       }
-
        tsk = current;
        mm  = tsk->mm;
 
@@ -220,6 +213,16 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
        if (in_atomic() || !mm)
                goto no_context;
 
+       if (user_mode(regs))
+               mm_flags |= FAULT_FLAG_USER;
+
+       if (esr & ESR_LNX_EXEC) {
+               vm_flags = VM_EXEC;
+       } else if ((esr & ESR_WRITE) && !(esr & ESR_CM)) {
+               vm_flags = VM_WRITE;
+               mm_flags |= FAULT_FLAG_WRITE;
+       }
+
        /*
         * As per x86, we may deadlock here. However, since the kernel only
         * validly references user space from well defined areas of the code,

diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c
index 2ca27b0558254bba3ae8210cd0945ee527b77621..0eca93327195077ec16bdfd99efd7294c6ab2de6 100644 (file)
--- a/arch/avr32/mm/fault.c
+++ b/arch/avr32/mm/fault.c
@@ -86,6 +86,8 @@ asmlinkage void do_page_fault(unsigned long ecr, struct pt_regs *regs)
 
        local_irq_enable();
 
+       if (user_mode(regs))
+               flags |= FAULT_FLAG_USER;
 retry:
        down_read(&mm->mmap_sem);
 

diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c
index 73312ab6c696c160f7fd58df02a50890390ad650..1790f22e71a21a859b2b7b1942cbbc503c2d557e 100644 (file)
--- a/arch/cris/mm/fault.c
+++ b/arch/cris/mm/fault.c
@@ -58,8 +58,7 @@ do_page_fault(unsigned long address, struct pt_regs *regs,
        struct vm_area_struct * vma;
        siginfo_t info;
        int fault;
-       unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-                               ((writeaccess & 1) ? FAULT_FLAG_WRITE : 0);
+       unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
        D(printk(KERN_DEBUG
                 "Page fault for %lX on %X at %lX, prot %d write %d\n",
@@ -117,6 +116,8 @@ do_page_fault(unsigned long address, struct pt_regs *regs,
        if (in_atomic() || !mm)
                goto no_context;
 
+       if (user_mode(regs))
+               flags |= FAULT_FLAG_USER;
 retry:
        down_read(&mm->mmap_sem);
        vma = find_vma(mm, address);
@@ -155,6 +156,7 @@ retry:
        } else if (writeaccess == 1) {
                if (!(vma->vm_flags & VM_WRITE))
                        goto bad_area;
+               flags |= FAULT_FLAG_WRITE;
        } else {
                if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
                        goto bad_area;

diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c
index 331c1e2cfb6760ee7ed3f38d4e5c92a2526d44bf..9a66372fc7c76019ca874a9c3780c2fc8392266c 100644 (file)
--- a/arch/frv/mm/fault.c
+++ b/arch/frv/mm/fault.c
@@ -34,11 +34,11 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
        struct vm_area_struct *vma;
        struct mm_struct *mm;
        unsigned long _pme, lrai, lrad, fixup;
+       unsigned long flags = 0;
        siginfo_t info;
        pgd_t *pge;
        pud_t *pue;
        pte_t *pte;
-       int write;
        int fault;
 
 #if 0
@@ -81,6 +81,9 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
        if (in_atomic() || !mm)
                goto no_context;
 
+       if (user_mode(__frame))
+               flags |= FAULT_FLAG_USER;
+
        down_read(&mm->mmap_sem);
 
        vma = find_vma(mm, ear0);
@@ -129,7 +132,6 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
  */
  good_area:
        info.si_code = SEGV_ACCERR;
-       write = 0;
        switch (esr0 & ESR0_ATXC) {
        default:
                /* handle write to write protected page */
@@ -140,7 +142,7 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
 #endif
                if (!(vma->vm_flags & VM_WRITE))
                        goto bad_area;
-               write = 1;
+               flags |= FAULT_FLAG_WRITE;
                break;
 
                 /* handle read from protected page */
@@ -162,7 +164,7 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
         * make sure we exit gracefully rather than endlessly redo
         * the fault.
         */
-       fault = handle_mm_fault(mm, vma, ear0, write ? FAULT_FLAG_WRITE : 0);
+       fault = handle_mm_fault(mm, vma, ear0, flags);
        if (unlikely(fault & VM_FAULT_ERROR)) {
                if (fault & VM_FAULT_OOM)
                        goto out_of_memory;

diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c
index 1bd276dbec7d3503f92a19fc7cb5a39df1051621..8704c9320032705cf7de10d6a94f3c4d70cf8b12 100644 (file)
--- a/arch/hexagon/mm/vm_fault.c
+++ b/arch/hexagon/mm/vm_fault.c
@@ -53,8 +53,7 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
        int si_code = SEGV_MAPERR;
        int fault;
        const struct exception_table_entry *fixup;
-       unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-                                (cause > 0 ? FAULT_FLAG_WRITE : 0);
+       unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
        /*
         * If we're in an interrupt or have no user context,
@@ -65,6 +64,8 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
 
        local_irq_enable();
 
+       if (user_mode(regs))
+               flags |= FAULT_FLAG_USER;
 retry:
        down_read(&mm->mmap_sem);
        vma = find_vma(mm, address);
@@ -96,6 +97,7 @@ good_area:
        case FLT_STORE:
                if (!(vma->vm_flags & VM_WRITE))
                        goto bad_area;
+               flags |= FAULT_FLAG_WRITE;
                break;
        }
 

diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index 6cf0341f978e59ddf235c44e70dcf615799390ed..7225dad87094d81e89459e5a61909fa5b2d10ca0 100644 (file)
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -90,8 +90,6 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
        mask = ((((isr >> IA64_ISR_X_BIT) & 1UL) << VM_EXEC_BIT)
                | (((isr >> IA64_ISR_W_BIT) & 1UL) << VM_WRITE_BIT));
 
-       flags |= ((mask & VM_WRITE) ? FAULT_FLAG_WRITE : 0);
-
        /* mmap_sem is performance critical.... */
        prefetchw(&mm->mmap_sem);
 
@@ -119,6 +117,10 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
        if (notify_page_fault(regs, TRAP_BRKPT))
                return;
 
+       if (user_mode(regs))
+               flags |= FAULT_FLAG_USER;
+       if (mask & VM_WRITE)
+               flags |= FAULT_FLAG_WRITE;
 retry:
        down_read(&mm->mmap_sem);
 

diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c
index 3cdfa9c1d0915b71969c0943b27da64e64156d53..e9c6a8014bd647eec50a66afb5bc75b076b35e4d 100644 (file)
--- a/arch/m32r/mm/fault.c
+++ b/arch/m32r/mm/fault.c
@@ -78,7 +78,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code,
        struct mm_struct *mm;
        struct vm_area_struct * vma;
        unsigned long page, addr;
-       int write;
+       unsigned long flags = 0;
        int fault;
        siginfo_t info;
 
@@ -117,6 +117,9 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code,
        if (in_atomic() || !mm)
                goto bad_area_nosemaphore;
 
+       if (error_code & ACE_USERMODE)
+               flags |= FAULT_FLAG_USER;
+
        /* When running in the kernel we expect faults to occur only to
         * addresses in user space.  All other faults represent errors in the
         * kernel and should generate an OOPS.  Unfortunately, in the case of an
@@ -166,14 +169,13 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code,
  */
 good_area:
        info.si_code = SEGV_ACCERR;
-       write = 0;
        switch (error_code & (ACE_WRITE|ACE_PROTECTION)) {
                default:        /* 3: write, present */
                        /* fall through */
                case ACE_WRITE: /* write, not present */
                        if (!(vma->vm_flags & VM_WRITE))
                                goto bad_area;
-                       write++;
+                       flags |= FAULT_FLAG_WRITE;
                        break;
                case ACE_PROTECTION:    /* read, present */
                case 0:         /* read, not present */
@@ -194,7 +196,7 @@ good_area:
         */
        addr = (address & PAGE_MASK);
        set_thread_fault_code(error_code);
-       fault = handle_mm_fault(mm, vma, addr, write ? FAULT_FLAG_WRITE : 0);
+       fault = handle_mm_fault(mm, vma, addr, flags);
        if (unlikely(fault & VM_FAULT_ERROR)) {
                if (fault & VM_FAULT_OOM)
                        goto out_of_memory;

diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index a563727806bf922b5b3315559b9b46b5bbb9d7fc..eb1d61f6872549991dae7d5e491a74627d8456d0 100644 (file)
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -88,6 +88,8 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
        if (in_atomic() || !mm)
                goto no_context;
 
+       if (user_mode(regs))
+               flags |= FAULT_FLAG_USER;
 retry:
        down_read(&mm->mmap_sem);
 

diff --git a/arch/metag/mm/fault.c b/arch/metag/mm/fault.c
index 8fddf46e6c62f3d7570a65d5d0034a185e46985e..332680e5ebf23c7909b796c415c2273efd77ba3c 100644 (file)
--- a/arch/metag/mm/fault.c
+++ b/arch/metag/mm/fault.c
@@ -53,8 +53,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
        struct vm_area_struct *vma, *prev_vma;
        siginfo_t info;
        int fault;
-       unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-                               (write_access ? FAULT_FLAG_WRITE : 0);
+       unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
        tsk = current;
 
@@ -109,6 +108,8 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
        if (in_atomic() || !mm)
                goto no_context;
 
+       if (user_mode(regs))
+               flags |= FAULT_FLAG_USER;
 retry:
        down_read(&mm->mmap_sem);
 
@@ -121,6 +122,7 @@ good_area:
        if (write_access) {
                if (!(vma->vm_flags & VM_WRITE))
                        goto bad_area;
+               flags |= FAULT_FLAG_WRITE;
        } else {
                if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
                        goto bad_area;

diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index 731f739d17a1be6c485a7759f9479adc592377d1..fa4cf52aa7a6d386711690005a314ece7d67fc53 100644 (file)
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -92,8 +92,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
        int code = SEGV_MAPERR;
        int is_write = error_code & ESR_S;
        int fault;
-       unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-                                        (is_write ? FAULT_FLAG_WRITE : 0);
+       unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
        regs->ear = address;
        regs->esr = error_code;
@@ -121,6 +120,9 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
                die("Weird page fault", regs, SIGSEGV);
        }
 
+       if (user_mode(regs))
+               flags |= FAULT_FLAG_USER;
+
        /* When running in the kernel we expect faults to occur only to
         * addresses in user space.  All other faults represent errors in the
         * kernel and should generate an OOPS.  Unfortunately, in the case of an
@@ -199,6 +201,7 @@ good_area:
        if (unlikely(is_write)) {
                if (unlikely(!(vma->vm_flags & VM_WRITE)))
                        goto bad_area;
+               flags |= FAULT_FLAG_WRITE;
        /* a read */
        } else {
                /* protection fault */

diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index da47e9b7f425ba106008a116fbe579b1596249c6..0214a43b9911b00e552d99c3396b07f9f12f6481 100644 (file)
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -41,8 +41,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, unsigned long writ
        const int field = sizeof(unsigned long) * 2;
        siginfo_t info;
        int fault;
-       unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-                                                (write ? FAULT_FLAG_WRITE : 0);
+       unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 #if 0
        printk("Cpu%d[%s:%d:%0*lx:%ld:%0*lx]\n", raw_smp_processor_id(),
@@ -92,6 +91,8 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, unsigned long writ
        if (in_atomic() || !mm)
                goto bad_area_nosemaphore;
 
+       if (user_mode(regs))
+               flags |= FAULT_FLAG_USER;
 retry:
        down_read(&mm->mmap_sem);
        vma = find_vma(mm, address);
@@ -113,6 +114,7 @@ good_area:
        if (write) {
                if (!(vma->vm_flags & VM_WRITE))
                        goto bad_area;
+               flags |= FAULT_FLAG_WRITE;
        } else {
                if (cpu_has_rixi) {
                        if (address == regs->cp0_epc && !(vma->vm_flags & VM_EXEC)) {

diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c
index 8a2e6ded9a4465e247890166f6a9ddadd25c7987..3516cbdf1ee93acb82ebef6428f79df9af104514 100644 (file)
--- a/arch/mn10300/mm/fault.c
+++ b/arch/mn10300/mm/fault.c
@@ -171,6 +171,8 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long fault_code,
        if (in_atomic() || !mm)
                goto no_context;
 
+       if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR)
+               flags |= FAULT_FLAG_USER;
 retry:
        down_read(&mm->mmap_sem);
 

diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index 4a41f8493ab0b4d9276a05315884d076fb440db9..0703acf7d3276811919fd3d398ada99b1b9c6d50 100644 (file)
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -86,6 +86,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
        if (user_mode(regs)) {
                /* Exception was in userspace: reenable interrupts */
                local_irq_enable();
+               flags |= FAULT_FLAG_USER;
        } else {
                /* If exception was in a syscall, then IRQ's may have
                 * been enabled or disabled.  If they were enabled,

diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index f247a3480e8e0cd7e276f4fd04004cbb608b3e11..d10d27a720c0d1f323c2248f01cc93193e73ca1e 100644 (file)
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -180,6 +180,10 @@ void do_page_fault(struct pt_regs *regs, unsigned long code,
        if (in_atomic() || !mm)
                goto no_context;
 
+       if (user_mode(regs))
+               flags |= FAULT_FLAG_USER;
+       if (acc_type & VM_WRITE)
+               flags |= FAULT_FLAG_WRITE;
 retry:
        down_read(&mm->mmap_sem);
        vma = find_vma_prev(mm, address, &prev_vma);
@@ -203,8 +207,7 @@ good_area:
         * fault.
         */
 
-       fault = handle_mm_fault(mm, vma, address,
-                       flags | ((acc_type & VM_WRITE) ? FAULT_FLAG_WRITE : 0));
+       fault = handle_mm_fault(mm, vma, address, flags);
 
        if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
                return;

diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 8726779e1409b5da36c1e1ea852276cf47d4252c..d9196c9f93d9dd7c1cb075fa3e0b732cd0ba9993 100644 (file)
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -223,9 +223,6 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
        is_write = error_code & ESR_DST;
 #endif /* CONFIG_4xx || CONFIG_BOOKE */
 
-       if (is_write)
-               flags |= FAULT_FLAG_WRITE;
-
 #ifdef CONFIG_PPC_ICSWX
        /*
         * we need to do this early because this "data storage
@@ -280,6 +277,9 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 
        perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 
+       if (user_mode(regs))
+               flags |= FAULT_FLAG_USER;
+
        /* When running in the kernel we expect faults to occur only to
         * addresses in user space.  All other faults represent errors in the
         * kernel and should generate an OOPS.  Unfortunately, in the case of an
@@ -408,6 +408,7 @@ good_area:
        } else if (is_write) {
                if (!(vma->vm_flags & VM_WRITE))
                        goto bad_area;
+               flags |= FAULT_FLAG_WRITE;
        /* a read */
        } else {
                /* protection fault */

diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 047c3e4c59a2e4ad03ea7812b8a5da8a6ab20f9a..416facec4a332eea5c33b6ffad24eb80643b5e2c 100644 (file)
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -302,6 +302,8 @@ static inline int do_exception(struct pt_regs *regs, int access)
        address = trans_exc_code & __FAIL_ADDR_MASK;
        perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
        flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+       if (user_mode(regs))
+               flags |= FAULT_FLAG_USER;
        if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400)
                flags |= FAULT_FLAG_WRITE;
        down_read(&mm->mmap_sem);

diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c
index 4b71a626d41e8196b3fe1dd7ed9cad750ee560b6..52238983527d605914853fd5415ea39617944ffe 100644 (file)
--- a/arch/score/mm/fault.c
+++ b/arch/score/mm/fault.c
@@ -47,6 +47,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long write,
        struct task_struct *tsk = current;
        struct mm_struct *mm = tsk->mm;
        const int field = sizeof(unsigned long) * 2;
+       unsigned long flags = 0;
        siginfo_t info;
        int fault;
 
@@ -75,6 +76,9 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long write,
        if (in_atomic() || !mm)
                goto bad_area_nosemaphore;
 
+       if (user_mode(regs))
+               flags |= FAULT_FLAG_USER;
+
        down_read(&mm->mmap_sem);
        vma = find_vma(mm, address);
        if (!vma)
@@ -95,6 +99,7 @@ good_area:
        if (write) {
                if (!(vma->vm_flags & VM_WRITE))
                        goto bad_area;
+               flags |= FAULT_FLAG_WRITE;
        } else {
                if (!(vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)))
                        goto bad_area;
@@ -105,7 +110,7 @@ good_area:
        * make sure we exit gracefully rather than endlessly redo
        * the fault.
        */
-       fault = handle_mm_fault(mm, vma, address, write);
+       fault = handle_mm_fault(mm, vma, address, flags);
        if (unlikely(fault & VM_FAULT_ERROR)) {
                if (fault & VM_FAULT_OOM)
                        goto out_of_memory;

diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index 1f49c28affa90495047c6b82577b2d5221bc089b..541dc610150888e706977c7944c42ab1d61d7437 100644 (file)
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -400,9 +400,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
        struct mm_struct *mm;
        struct vm_area_struct * vma;
        int fault;
-       int write = error_code & FAULT_CODE_WRITE;
-       unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-                             (write ? FAULT_FLAG_WRITE : 0));
+       unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
        tsk = current;
        mm = tsk->mm;
@@ -476,6 +474,11 @@ good_area:
 
        set_thread_fault_code(error_code);
 
+       if (user_mode(regs))
+               flags |= FAULT_FLAG_USER;
+       if (error_code & FAULT_CODE_WRITE)
+               flags |= FAULT_FLAG_WRITE;
+
        /*
         * If for any reason at all we couldn't handle the fault,
         * make sure we exit gracefully rather than endlessly redo

diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index e98bfda205a2beb97bcaa49a27d5a9412bf03dc3..59dbd46457250b050ce84a48370a4f96afa3746d 100644 (file)
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -177,8 +177,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
        unsigned long g2;
        int from_user = !(regs->psr & PSR_PS);
        int fault, code;
-       unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-                             (write ? FAULT_FLAG_WRITE : 0));
+       unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
        if (text_fault)
                address = regs->pc;
@@ -235,6 +234,11 @@ good_area:
                        goto bad_area;
        }
 
+       if (from_user)
+               flags |= FAULT_FLAG_USER;
+       if (write)
+               flags |= FAULT_FLAG_WRITE;
+
        /*
         * If for any reason at all we couldn't handle the fault,
         * make sure we exit gracefully rather than endlessly redo
@@ -383,6 +387,7 @@ static void force_user_fault(unsigned long address, int write)
        struct vm_area_struct *vma;
        struct task_struct *tsk = current;
        struct mm_struct *mm = tsk->mm;
+       unsigned int flags = FAULT_FLAG_USER;
        int code;
 
        code = SEGV_MAPERR;
@@ -402,11 +407,12 @@ good_area:
        if (write) {
                if (!(vma->vm_flags & VM_WRITE))
                        goto bad_area;
+               flags |= FAULT_FLAG_WRITE;
        } else {
                if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
                        goto bad_area;
        }
-       switch (handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0)) {
+       switch (handle_mm_fault(mm, vma, address, flags)) {
        case VM_FAULT_SIGBUS:
        case VM_FAULT_OOM:
                goto do_sigbus;

diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index ea83f82464dab8c8de95b3b9e66e30916a9b820e..3841a081beb3967d9f2f08d0c6d1b4abf5390ff0 100644 (file)
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -323,7 +323,8 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
                        bad_kernel_pc(regs, address);
                        return;
                }
-       }
+       } else
+               flags |= FAULT_FLAG_USER;
 
        /*
         * If we're in an interrupt or have no user
@@ -426,13 +427,14 @@ good_area:
                    vma->vm_file != NULL)
                        set_thread_fault_code(fault_code |
                                              FAULT_CODE_BLKCOMMIT);
+
+               flags |= FAULT_FLAG_WRITE;
        } else {
                /* Allow reads even for write-only mappings */
                if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
                        goto bad_area;
        }
 
-       flags |= ((fault_code & FAULT_CODE_WRITE) ? FAULT_FLAG_WRITE : 0);
        fault = handle_mm_fault(mm, vma, address, flags);
 
        if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))

diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index ac553eed639060b7e4e0f344013192e896f426f0..3ff289f422e635cdf74280f86488733c0f88c55f 100644 (file)
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -280,8 +280,7 @@ static int handle_page_fault(struct pt_regs *regs,
        if (!is_page_fault)
                write = 1;
 
-       flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-                (write ? FAULT_FLAG_WRITE : 0));
+       flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
        is_kernel_mode = (EX1_PL(regs->ex1) != USER_PL);
 
@@ -365,6 +364,9 @@ static int handle_page_fault(struct pt_regs *regs,
                goto bad_area_nosemaphore;
        }
 
+       if (!is_kernel_mode)
+               flags |= FAULT_FLAG_USER;
+
        /*
         * When running in the kernel we expect faults to occur only to
         * addresses in user space.  All other faults represent errors in the
@@ -425,6 +427,7 @@ good_area:
 #endif
                if (!(vma->vm_flags & VM_WRITE))
                        goto bad_area;
+               flags |= FAULT_FLAG_WRITE;
        } else {
                if (!is_page_fault || !(vma->vm_flags & VM_READ))
                        goto bad_area;

diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index b2f5adf838dd6324f5c44ee54864f0d84d36fc03..5c3aef74237ffda72a0b252d4ee4b118d14a969a 100644 (file)
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -30,8 +30,7 @@ int handle_page_fault(unsigned long address, unsigned long ip,
        pmd_t *pmd;
        pte_t *pte;
        int err = -EFAULT;
-       unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-                                (is_write ? FAULT_FLAG_WRITE : 0);
+       unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
        *code_out = SEGV_MAPERR;
 
@@ -42,6 +41,8 @@ int handle_page_fault(unsigned long address, unsigned long ip,
        if (in_atomic())
                goto out_nosemaphore;
 
+       if (is_user)
+               flags |= FAULT_FLAG_USER;
 retry:
        down_read(&mm->mmap_sem);
        vma = find_vma(mm, address);
@@ -58,12 +59,15 @@ retry:
 
 good_area:
        *code_out = SEGV_ACCERR;
-       if (is_write && !(vma->vm_flags & VM_WRITE))
-               goto out;
-
-       /* Don't require VM_READ|VM_EXEC for write faults! */
-       if (!is_write && !(vma->vm_flags & (VM_READ | VM_EXEC)))
-               goto out;
+       if (is_write) {
+               if (!(vma->vm_flags & VM_WRITE))
+                       goto out;
+               flags |= FAULT_FLAG_WRITE;
+       } else {
+               /* Don't require VM_READ|VM_EXEC for write faults! */
+               if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
+                       goto out;
+       }
 
        do {
                int fault;

diff --git a/arch/unicore32/mm/fault.c b/arch/unicore32/mm/fault.c
index 8ed3c4509d846d3089f34466ed2ffebee23cf890..0dc922dba9154d7cfcfe5352ec8ec77169e8082f 100644 (file)
--- a/arch/unicore32/mm/fault.c
+++ b/arch/unicore32/mm/fault.c
@@ -209,8 +209,7 @@ static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
        struct task_struct *tsk;
        struct mm_struct *mm;
        int fault, sig, code;
-       unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-                                ((!(fsr ^ 0x12)) ? FAULT_FLAG_WRITE : 0);
+       unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
        tsk = current;
        mm = tsk->mm;
@@ -222,6 +221,11 @@ static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
        if (in_atomic() || !mm)
                goto no_context;
 
+       if (user_mode(regs))
+               flags |= FAULT_FLAG_USER;
+       if (!(fsr ^ 0x12))
+               flags |= FAULT_FLAG_WRITE;
+
        /*
         * As per x86, we may deadlock here.  However, since the kernel only
         * validly references user space from well defined areas of the code,

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index c1e9e4cbbd76d4aa1835e1e96715e098a003b6d0..78dee3ef04d1f34e1820f928ee79179474f4acea 100644 (file)
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1017,9 +1017,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
        unsigned long address;
        struct mm_struct *mm;
        int fault;
-       int write = error_code & PF_WRITE;
-       unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-                                       (write ? FAULT_FLAG_WRITE : 0);
+       unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
        tsk = current;
        mm = tsk->mm;
@@ -1089,6 +1087,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
        if (user_mode_vm(regs)) {
                local_irq_enable();
                error_code |= PF_USER;
+               flags |= FAULT_FLAG_USER;
        } else {
                if (regs->flags & X86_EFLAGS_IF)
                        local_irq_enable();
@@ -1113,6 +1112,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
                return;
        }
 
+       if (error_code & PF_WRITE)
+               flags |= FAULT_FLAG_WRITE;
+
        /*
         * When running in the kernel we expect faults to occur only to
         * addresses in user space.  All other faults represent errors in

diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index 4b7bc8db170ff8ac6befadb8246ac15938b74cae..70fa7bc42b4a0853012af6f6daaeb254f9c5a086 100644 (file)
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -72,6 +72,8 @@ void do_page_fault(struct pt_regs *regs)
               address, exccause, regs->pc, is_write? "w":"", is_exec? "x":"");
 #endif
 
+       if (user_mode(regs))
+               flags |= FAULT_FLAG_USER;
 retry:
        down_read(&mm->mmap_sem);
        vma = find_vma(mm, address);

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7da14357aa762717a35fc99a4ba1084e608f5a85..d4cdac903468ca38c2fc2b62304e89d774d14779 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -167,6 +167,7 @@ extern pgprot_t protection_map[16];
 #define FAULT_FLAG_RETRY_NOWAIT        0x10    /* Don't drop mmap_sem and wait when retrying */
 #define FAULT_FLAG_KILLABLE    0x20    /* The fault task is in SIGKILL killable region */
 #define FAULT_FLAG_TRIED       0x40    /* second try */
+#define FAULT_FLAG_USER                0x80    /* The fault originated in userspace */
 
 /*
  * vm_fault is filled by the the pagefault handler and passed to the vma's