arch/mm/fault: fix major fault accounting when retrying under per-VMA lock

A test [1] in Android test suite started failing after [2] was merged.  It
turns out that after handling a major fault under per-VMA lock, the
process major fault counter does not register that fault as major.  Before
[2] read faults would be done under mmap_lock, in which case
FAULT_FLAG_TRIED flag is set before retrying.  That in turn causes
mm_account_fault() to account the fault as major once retry completes.
With per-VMA locks we often retry because a fault can't be handled without
locking the whole mm using mmap_lock.  Therefore such retries do not set
FAULT_FLAG_TRIED flag.  This logic does not work after [2] because we can
now handle read major faults under per-VMA lock and upon retry the fact
there was a major fault gets lost.  Fix this by setting FAULT_FLAG_TRIED
after retrying under per-VMA lock if VM_FAULT_MAJOR was returned.  Ideally
we would use an additional VM_FAULT bit to indicate the reason for the
retry (could not handle under per-VMA lock vs other reason) but this
simpler solution seems to work, so keeping it simple.

[1] https://cs.android.com/android/platform/superproject/+/master:test/vts-testcase/kernel/api/drop_caches_prop/drop_caches_test.cpp
[2] https://lore.kernel.org/all/20231006195318.4087158-6-willy@infradead.org/

Link: https://lkml.kernel.org/r/20231226214610.109282-1-surenb@google.com
Fixes: 12214eba1992 ("mm: handle read faults under the VMA lock")
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 460d799..55f6455 100644 (file)
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -607,6 +607,8 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
                goto done;
        }
        count_vm_vma_lock_event(VMA_LOCK_RETRY);
+       if (fault & VM_FAULT_MAJOR)
+               mm_flags |= FAULT_FLAG_TRIED;
 
        /* Quick path to respond to signals */
        if (fault_signal_pending(fault, regs)) {

diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 9e49ede..53335ae 100644 (file)
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -497,6 +497,8 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
                goto done;
        }
        count_vm_vma_lock_event(VMA_LOCK_RETRY);
+       if (fault & VM_FAULT_MAJOR)
+               flags |= FAULT_FLAG_TRIED;
 
        if (fault_signal_pending(fault, regs))
                return user_mode(regs) ? 0 : SIGBUS;

diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 90d4ba3..081339d 100644 (file)
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -304,6 +304,8 @@ void handle_page_fault(struct pt_regs *regs)
                goto done;
        }
        count_vm_vma_lock_event(VMA_LOCK_RETRY);
+       if (fault & VM_FAULT_MAJOR)
+               flags |= FAULT_FLAG_TRIED;
 
        if (fault_signal_pending(fault, regs)) {
                if (!user_mode(regs))

diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 249aefc..ab40988 100644 (file)
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -337,6 +337,9 @@ static void do_exception(struct pt_regs *regs, int access)
                return;
        }
        count_vm_vma_lock_event(VMA_LOCK_RETRY);
+       if (fault & VM_FAULT_MAJOR)
+               flags |= FAULT_FLAG_TRIED;
+
        /* Quick path to respond to signals */
        if (fault_signal_pending(fault, regs)) {
                if (!user_mode(regs))

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index ab778ea..679b09c 100644 (file)
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1370,6 +1370,8 @@ void do_user_addr_fault(struct pt_regs *regs,
                goto done;
        }
        count_vm_vma_lock_event(VMA_LOCK_RETRY);
+       if (fault & VM_FAULT_MAJOR)
+               flags |= FAULT_FLAG_TRIED;
 
        /* Quick path to respond to signals */
        if (fault_signal_pending(fault, regs)) {