Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Mon,  9 Jan 2023 12:53:29 -0800
In-Reply-To: <20230109205336.3665937-1-surenb@google.com>
Mime-Version: 1.0
References: <20230109205336.3665937-1-surenb@google.com>
Message-ID: <20230109205336.3665937-35-surenb@google.com>
Subject: [PATCH 34/41] x86/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,
        laurent.dufour@fr.ibm.com, paulmck@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,
        jannh@google.com, shakeelb@google.com, tatashin@google.com,
        edumazet@google.com, gthelen@google.com, gurua@google.com,
        arjunroy@google.com, soheil@google.com, hughlynch@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/x86/Kconfig    |  1 +
 arch/x86/mm/fault.c | 36 ++++++++++++++++++++++++++++++++++++
 2 files changed, 37 insertions(+)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 3604074a878b..3647f7bdb110 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -27,6 +27,7 @@ config X86_64
 	# Options that are inherently 64-bit kernel only:
 	select ARCH_HAS_GIGANTIC_PAGE
 	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128
+	select ARCH_SUPPORTS_PER_VMA_LOCK
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select HAVE_ARCH_SOFT_DIRTY
 	select MODULES_USE_ELF_RELA
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 7b0d4ab894c8..983266e7c49b 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, ...		*/
@@ -1354,6 +1355,38 @@ void do_user_addr_fault(struct pt_regs *regs,
 	}
 #endif
 
+#ifdef CONFIG_PER_VMA_LOCK
+	if (!(flags & FAULT_FLAG_USER) || atomic_read(&mm->mm_users) == 1)
+		goto lock_mmap;
+
+	vma = lock_vma_under_rcu(mm, address);
+	if (!vma)
+		goto lock_mmap;
+
+	if (unlikely(access_error(error_code, vma))) {
+		vma_read_unlock(vma);
+		goto lock_mmap;
+	}
+	fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs);
+	vma_read_unlock(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
@@ -1454,6 +1487,9 @@ void do_user_addr_fault(struct pt_regs *regs,
 	}
 
 	mmap_read_unlock(mm);
+#ifdef CONFIG_PER_VMA_LOCK
+done:
+#endif
 	if (likely(!(fault & VM_FAULT_ERROR)))
 		return;
 
-- 
2.39.0