From 0bff0aaea03e2a3ed6bfa302155cca8a432a1829 Mon Sep 17 00:00:00 2001
From: Suren Baghdasaryan <surenb@google.com>
Date: Mon, 27 Feb 2023 09:36:28 -0800
Subject: x86/mm: try VMA lock-based page fault handling first

Attempt VMA lock-based page fault handling first, and fall back to the
existing mmap_lock-based handling if that fails.

Link: https://lkml.kernel.org/r/20230227173632.3292573-30-surenb@google.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/x86/mm/fault.c | 36 ++++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

(limited to 'arch/x86/mm')

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index a498ae1fbe66..e4399983c50c 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -19,6 +19,7 @@
 #include <linux/uaccess.h>		/* faulthandler_disabled()	*/
 #include <linux/efi.h>			/* efi_crash_gracefully_on_page_fault()*/
 #include <linux/mm_types.h>
+#include <linux/mm.h>			/* find_and_lock_vma() */
 
 #include <asm/cpufeature.h>		/* boot_cpu_has, ...		*/
 #include <asm/traps.h>			/* dotraplinkage, ...		*/
@@ -1333,6 +1334,38 @@ void do_user_addr_fault(struct pt_regs *regs,
 	}
 #endif
 
+#ifdef CONFIG_PER_VMA_LOCK
+	if (!(flags & FAULT_FLAG_USER))
+		goto lock_mmap;
+
+	vma = lock_vma_under_rcu(mm, address);
+	if (!vma)
+		goto lock_mmap;
+
+	if (unlikely(access_error(error_code, vma))) {
+		vma_end_read(vma);
+		goto lock_mmap;
+	}
+	fault = handle_mm_fault(vma, address, 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))
+			kernelmode_fixup_or_oops(regs, error_code, address,
+						 SIGBUS, BUS_ADRERR,
+						 ARCH_DEFAULT_PKEY);
+		return;
+	}
+lock_mmap:
+#endif /* CONFIG_PER_VMA_LOCK */
+
 	/*
 	 * Kernel-mode access to the user address space should only occur
 	 * on well-defined single instructions listed in the exception
@@ -1433,6 +1466,9 @@ good_area:
 	}
 
 	mmap_read_unlock(mm);
+#ifdef CONFIG_PER_VMA_LOCK
+done:
+#endif
 	if (likely(!(fault & VM_FAULT_ERROR)))
 		return;
 
-- 
cgit v1.2.3