Date:   Fri, 27 Jan 2023 11:41:07 -0800
In-Reply-To: <20230127194110.533103-1-surenb@google.com>
Mime-Version: 1.0
References: <20230127194110.533103-1-surenb@google.com>
Message-ID: <20230127194110.533103-31-surenb@google.com>
Subject: [PATCH v2 30/33] arm64/mm: try VMA lock-based page fault handling first
From:   Suren Baghdasaryan <surenb@google.com>
To:     akpm@linux-foundation.org
Cc:     michel@lespinasse.org, jglisse@google.com, mhocko@suse.com,
        vbabka@suse.cz, hannes@cmpxchg.org, mgorman@techsingularity.net,
        dave@stgolabs.net, willy@infradead.org, liam.howlett@oracle.com,
        peterz@infradead.org, ldufour@linux.ibm.com, paulmck@kernel.org,
        mingo@redhat.com, will@kernel.org, luto@kernel.org,
        songliubraving@fb.com, peterx@redhat.com, david@redhat.com,
        dhowells@redhat.com, hughd@google.com, bigeasy@linutronix.de,
        kent.overstreet@linux.dev, punit.agrawal@bytedance.com,
        lstoakes@gmail.com, peterjung1337@gmail.com, rientjes@google.com,
        axelrasmussen@google.com, joelaf@google.com, minchan@google.com,
        rppt@kernel.org, jannh@google.com, shakeelb@google.com,
        tatashin@google.com, edumazet@google.com, gthelen@google.com,
        gurua@google.com, arjunroy@google.com, soheil@google.com,
        leewalsh@google.com, posk@google.com, linux-mm@kvack.org,
        linux-arm-kernel@lists.infradead.org,
        linuxppc-dev@lists.ozlabs.org, x86@kernel.org,
        linux-kernel@vger.kernel.org, kernel-team@android.com,
        surenb@google.com
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

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@google.com>
---
 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