linux-kernel - [PATCH 31/31] powerpc/mm: attempt speculative mm faults 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: <20210430195232.30491-32-michel@lespinasse.org>
Date:   Fri, 30 Apr 2021 12:52:32 -0700
From:   Michel Lespinasse <michel@...pinasse.org>
To:     Linux-MM <linux-mm@...ck.org>,
        Linux-Kernel <linux-kernel@...r.kernel.org>
Cc:     Laurent Dufour <ldufour@...ux.ibm.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Michal Hocko <mhocko@...e.com>,
        Matthew Wilcox <willy@...radead.org>,
        Rik van Riel <riel@...riel.com>,
        Paul McKenney <paulmck@...nel.org>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Suren Baghdasaryan <surenb@...gle.com>,
        Joel Fernandes <joelaf@...gle.com>,
        Andy Lutomirski <luto@...nel.org>,
        Michel Lespinasse <michel@...pinasse.org>
Subject: [PATCH 31/31] powerpc/mm: attempt speculative mm faults first

Attempt speculative mm fault handling first, and fall back to the
existing (non-speculative) code if that fails.

This follows the lines of the x86 speculative fault handling code,
but with some minor arch differences such as the way that the
access_pkey_error case is handled

Signed-off-by: Michel Lespinasse <michel@...pinasse.org>
---
 arch/powerpc/mm/fault.c | 65 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 65 insertions(+)

diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index bb368257b55c..d7c820751a58 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -398,6 +398,10 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
 	int is_write = page_fault_is_write(error_code);
 	vm_fault_t fault, major = 0;
 	bool kprobe_fault = kprobe_page_fault(regs, 11);
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+	struct vm_area_struct pvma;
+	unsigned long seq;
+#endif
 
 	if (unlikely(debugger_fault_handler(regs) || kprobe_fault))
 		return 0;
@@ -450,6 +454,64 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (is_exec)
 		flags |= FAULT_FLAG_INSTRUCTION;
 
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+
+	/*
+	 * No need to try speculative faults for kernel or
+	 * single threaded user space.
+	 */
+	if (!(flags & FAULT_FLAG_USER) || atomic_read(&mm->mm_users) == 1)
+		goto no_spf;
+
+	count_vm_event(SPF_ATTEMPT);
+	seq = mmap_seq_read_start(mm);
+	if (seq & 1) {
+		count_vm_spf_event(SPF_ABORT_ODD);
+		goto spf_abort;
+	}
+	rcu_read_lock();
+	vma = find_vma(mm, address);
+	if (!vma || vma->vm_start > address) {
+		rcu_read_unlock();
+		count_vm_spf_event(SPF_ABORT_UNMAPPED);
+		goto spf_abort;
+	}
+	if (!vma_is_anonymous(vma)) {
+		rcu_read_unlock();
+		count_vm_spf_event(SPF_ABORT_NO_SPECULATE);
+		goto spf_abort;
+	}
+	pvma = *vma;
+	rcu_read_unlock();
+	if (!mmap_seq_read_check(mm, seq, SPF_ABORT_VMA_COPY))
+		goto spf_abort;
+	vma = &pvma;
+#ifdef CONFIG_PPC_MEM_KEYS
+	if (unlikely(access_pkey_error(is_write, is_exec,
+				       (error_code & DSISR_KEYFAULT), vma))) {
+		count_vm_spf_event(SPF_ABORT_ACCESS_ERROR);
+		goto spf_abort;
+	}
+#endif /* CONFIG_PPC_MEM_KEYS */
+	if (unlikely(access_error(is_write, is_exec, vma))) {
+		count_vm_spf_event(SPF_ABORT_ACCESS_ERROR);
+		goto spf_abort;
+	}
+	fault = do_handle_mm_fault(vma, address,
+				   flags | FAULT_FLAG_SPECULATIVE, seq, regs);
+	major |= fault & VM_FAULT_MAJOR;
+
+	if (fault_signal_pending(fault, regs))
+		return user_mode(regs) ? 0 : SIGBUS;
+	if (!(fault & VM_FAULT_RETRY))
+		goto done;
+
+spf_abort:
+	count_vm_event(SPF_ABORT);
+no_spf:
+
+#endif	/* CONFIG_SPECULATIVE_PAGE_FAULT */
+
 	/* When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in the
 	 * kernel and should generate an OOPS.  Unfortunately, in the case of an
@@ -525,6 +587,9 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
 	}
 
 	mmap_read_unlock(current->mm);
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+done:
+#endif
 
 	if (unlikely(fault & VM_FAULT_ERROR))
 		return mm_fault_error(regs, address, fault);
-- 
2.20.1