linux-kernel - [PATCH rfc v2 10/10] loongarch: mm: try VMA lock-based page fault handling first

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20230821123056.2109942-11-wangkefeng.wang@huawei.com>
Date:   Mon, 21 Aug 2023 20:30:56 +0800
From:   Kefeng Wang <wangkefeng.wang@...wei.com>
To:     Andrew Morton <akpm@...ux-foundation.org>, <linux-mm@...ck.org>
CC:     <surenb@...gle.com>, <willy@...radead.org>,
        Russell King <linux@...linux.org.uk>,
        Catalin Marinas <catalin.marinas@....com>,
        Will Deacon <will@...nel.org>,
        Huacai Chen <chenhuacai@...nel.org>,
        WANG Xuerui <kernel@...0n.name>,
        Michael Ellerman <mpe@...erman.id.au>,
        Nicholas Piggin <npiggin@...il.com>,
        Christophe Leroy <christophe.leroy@...roup.eu>,
        Paul Walmsley <paul.walmsley@...ive.com>,
        Palmer Dabbelt <palmer@...belt.com>,
        Albert Ou <aou@...s.berkeley.edu>,
        Alexander Gordeev <agordeev@...ux.ibm.com>,
        Gerald Schaefer <gerald.schaefer@...ux.ibm.com>,
        Heiko Carstens <hca@...ux.ibm.com>,
        Vasily Gorbik <gor@...ux.ibm.com>,
        Christian Borntraeger <borntraeger@...ux.ibm.com>,
        Sven Schnelle <svens@...ux.ibm.com>,
        Dave Hansen <dave.hansen@...ux.intel.com>,
        Andy Lutomirski <luto@...nel.org>,
        Peter Zijlstra <peterz@...radead.org>,
        Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
        <x86@...nel.org>, "H . Peter Anvin" <hpa@...or.com>,
        <linux-arm-kernel@...ts.infradead.org>,
        <linux-kernel@...r.kernel.org>, <loongarch@...ts.linux.dev>,
        <linuxppc-dev@...ts.ozlabs.org>, <linux-riscv@...ts.infradead.org>,
        <linux-s390@...r.kernel.org>,
        Kefeng Wang <wangkefeng.wang@...wei.com>
Subject: [PATCH rfc v2 10/10] loongarch: 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.

Signed-off-by: Kefeng Wang <wangkefeng.wang@...wei.com>
---
 arch/loongarch/Kconfig    |  1 +
 arch/loongarch/mm/fault.c | 37 +++++++++++++++++++++++++++++++------
 2 files changed, 32 insertions(+), 6 deletions(-)

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 2b27b18a63af..6b821f621920 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -56,6 +56,7 @@ config LOONGARCH
 	select ARCH_SUPPORTS_LTO_CLANG
 	select ARCH_SUPPORTS_LTO_CLANG_THIN
 	select ARCH_SUPPORTS_NUMA_BALANCING
+	select ARCH_SUPPORTS_PER_VMA_LOCK
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_USE_QUEUED_RWLOCKS
diff --git a/arch/loongarch/mm/fault.c b/arch/loongarch/mm/fault.c
index 2a45e9f3a485..f7ac3a14bb06 100644
--- a/arch/loongarch/mm/fault.c
+++ b/arch/loongarch/mm/fault.c
@@ -142,6 +142,13 @@ static inline bool access_error(unsigned int flags, struct pt_regs *regs,
 	return false;
 }
 
+#ifdef CONFIG_PER_VMA_LOCK
+bool arch_vma_access_error(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	return access_error(vmf->flags, vmf->regs, vmf->real_address, vma);
+}
+#endif
+
 /*
  * This routine handles page faults.  It determines the address,
  * and the problem, and then passes it off to one of the appropriate
@@ -151,11 +158,15 @@ static void __kprobes __do_page_fault(struct pt_regs *regs,
 			unsigned long write, unsigned long address)
 {
 	int si_code = SEGV_MAPERR;
-	unsigned int flags = FAULT_FLAG_DEFAULT;
 	struct task_struct *tsk = current;
 	struct mm_struct *mm = tsk->mm;
 	struct vm_area_struct *vma = NULL;
 	vm_fault_t fault;
+	struct vm_fault vmf = {
+		.real_address = address,
+		.regs = regs,
+		.flags = FAULT_FLAG_DEFAULT,
+	};
 
 	if (kprobe_page_fault(regs, current->thread.trap_nr))
 		return;
@@ -184,11 +195,24 @@ static void __kprobes __do_page_fault(struct pt_regs *regs,
 		goto bad_area_nosemaphore;
 
 	if (user_mode(regs))
-		flags |= FAULT_FLAG_USER;
+		vmf.flags |= FAULT_FLAG_USER;
 	if (write)
-		flags |= FAULT_FLAG_WRITE;
+		vmf.flags |= FAULT_FLAG_WRITE;
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
+
+	fault = try_vma_locked_page_fault(&vmf);
+	if (fault == VM_FAULT_NONE)
+		goto retry;
+	if (!(fault & VM_FAULT_RETRY))
+		goto done;
+
+	if (fault_signal_pending(fault, regs)) {
+		if (!user_mode(regs))
+			no_context(regs, write, address);
+		return;
+	}
+
 retry:
 	vma = lock_mm_and_find_vma(mm, address, regs);
 	if (unlikely(!vma))
@@ -196,7 +220,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs,
 
 	si_code = SEGV_ACCERR;
 
-	if (access_error(flags, regs, vma))
+	if (access_error(vmf.flags, regs, address, vma))
 		goto bad_area;
 
 	/*
@@ -204,7 +228,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs,
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, address, flags, regs);
+	fault = handle_mm_fault(vma, address, vmf.flags, regs);
 
 	if (fault_signal_pending(fault, regs)) {
 		if (!user_mode(regs))
@@ -217,7 +241,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs,
 		return;
 
 	if (unlikely(fault & VM_FAULT_RETRY)) {
-		flags |= FAULT_FLAG_TRIED;
+		vmf.flags |= FAULT_FLAG_TRIED;
 
 		/*
 		 * No need to mmap_read_unlock(mm) as we would
@@ -229,6 +253,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs,
 
 	mmap_read_unlock(mm);
 
+done:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			do_out_of_memory(regs, write, address);
-- 
2.27.0