Attempt VMA lock-based page fault handling first, and fall back to the
existing mmap_lock-based handling if that fails.
Signed-off-by: Suren Baghdasaryan <surenb@xxxxxxxxxx>
---
arch/arm64/Kconfig | 1 +
arch/arm64/mm/fault.c | 36 ++++++++++++++++++++++++++++++++++++
2 files changed, 37 insertions(+)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index c5ccca26a408..9f2c0e352da3 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -95,6 +95,7 @@ config ARM64
select ARCH_SUPPORTS_INT128 if CC_HAS_INT128
select ARCH_SUPPORTS_NUMA_BALANCING
select ARCH_SUPPORTS_PAGE_TABLE_CHECK
+ select ARCH_SUPPORTS_PER_VMA_LOCK
select ARCH_WANT_COMPAT_IPC_PARSE_VERSION if COMPAT
select ARCH_WANT_DEFAULT_BPF_JIT
select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index f4cb0f85ccf4..16588dda9258 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -535,6 +535,9 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
unsigned long vm_flags;
unsigned int mm_flags = FAULT_FLAG_DEFAULT;
unsigned long addr = untagged_addr(far);
+#ifdef CONFIG_PER_VMA_LOCK
+ struct vm_area_struct *vma;
+#endif
if (kprobe_page_fault(regs, esr))
return 0;
@@ -585,6 +588,36 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
+#ifdef CONFIG_PER_VMA_LOCK
+ if (!(mm_flags & FAULT_FLAG_USER) || atomic_read(&mm->mm_users) == 1)
+ goto lock_mmap;
+
+ vma = lock_vma_under_rcu(mm, addr);
+ if (!vma)
+ goto lock_mmap;
+
+ if (!(vma->vm_flags & vm_flags)) {
+ vma_end_read(vma);
+ goto lock_mmap;
+ }
+ fault = handle_mm_fault(vma, addr & PAGE_MASK,
+ mm_flags | FAULT_FLAG_VMA_LOCK, regs);
+ vma_end_read(vma);
+
+ if (!(fault & VM_FAULT_RETRY)) {
+ count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+ goto done;
+ }
+ count_vm_vma_lock_event(VMA_LOCK_RETRY);
+
+ /* Quick path to respond to signals */
+ if (fault_signal_pending(fault, regs)) {
+ if (!user_mode(regs))
+ goto no_context;
+ return 0;
+ }
+lock_mmap:
+#endif /* CONFIG_PER_VMA_LOCK */
/*
* As per x86, we may deadlock here. However, since the kernel only
* validly references user space from well defined areas of the code,
@@ -628,6 +661,9 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
}
mmap_read_unlock(mm);
+#ifdef CONFIG_PER_VMA_LOCK
+done:
+#endif
/*
* Handle the "normal" (no error) case first.
*/
--
2.39.1
