x86: mm: accelerate pagefault when badaccess

The access_error() of vma is already checked under per-VMA lock, if it is
a bad access, directly handle error, no need to retry with mmap_lock
again.  In order to release the correct lock, pass the mm_struct into
bad_area_access_error().  If mm is NULL, release vma lock, or release
mmap_lock.  Since the page faut is handled under per-VMA lock, count it as
a vma lock event with VMA_LOCK_SUCCESS.

Link: https://lkml.kernel.org/r/20240403083805.1818160-8-wangkefeng.wang@huawei.com
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
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: Nicholas Piggin <npiggin@gmail.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index a4cc20d0036d4a7a8538381935cb62e55179bfc6..67b18adc75ddc12d89513ac71b411c8f33561fdd 100644 (file)
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -866,14 +866,17 @@ bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 
 static void
 __bad_area(struct pt_regs *regs, unsigned long error_code,
-          unsigned long address, u32 pkey, int si_code)
+          unsigned long address, struct mm_struct *mm,
+          struct vm_area_struct *vma, u32 pkey, int si_code)
 {
-       struct mm_struct *mm = current->mm;
        /*
         * Something tried to access memory that isn't in our memory map..
         * Fix it, but check if it's kernel or user first..
         */
-       mmap_read_unlock(mm);
+       if (mm)
+               mmap_read_unlock(mm);
+       else
+               vma_end_read(vma);
 
        __bad_area_nosemaphore(regs, error_code, address, pkey, si_code);
 }
@@ -897,7 +900,8 @@ static inline bool bad_area_access_from_pkeys(unsigned long error_code,
 
 static noinline void
 bad_area_access_error(struct pt_regs *regs, unsigned long error_code,
-                     unsigned long address, struct vm_area_struct *vma)
+                     unsigned long address, struct mm_struct *mm,
+                     struct vm_area_struct *vma)
 {
        /*
         * This OSPKE check is not strictly necessary at runtime.
@@ -927,9 +931,9 @@ bad_area_access_error(struct pt_regs *regs, unsigned long error_code,
                 */
                u32 pkey = vma_pkey(vma);
 
-               __bad_area(regs, error_code, address, pkey, SEGV_PKUERR);
+               __bad_area(regs, error_code, address, mm, vma, pkey, SEGV_PKUERR);
        } else {
-               __bad_area(regs, error_code, address, 0, SEGV_ACCERR);
+               __bad_area(regs, error_code, address, mm, vma, 0, SEGV_ACCERR);
        }
 }
 
@@ -1357,8 +1361,9 @@ void do_user_addr_fault(struct pt_regs *regs,
                goto lock_mmap;
 
        if (unlikely(access_error(error_code, vma))) {
-               vma_end_read(vma);
-               goto lock_mmap;
+               bad_area_access_error(regs, error_code, address, NULL, vma);
+               count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+               return;
        }
        fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs);
        if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED)))
@@ -1394,7 +1399,7 @@ retry:
         * we can handle it..
         */
        if (unlikely(access_error(error_code, vma))) {
-               bad_area_access_error(regs, error_code, address, vma);
+               bad_area_access_error(regs, error_code, address, mm, vma);
                return;
        }