linux-kernel - [PATCH v2 19/35] mm: enable speculative fault handling through do_anonymous

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]

Date:   Fri, 28 Jan 2022 05:09:50 -0800
From:   Michel Lespinasse <michel@...pinasse.org>
To:     Linux-MM <linux-mm@...ck.org>, linux-kernel@...r.kernel.org,
        Andrew Morton <akpm@...ux-foundation.org>
Cc:     kernel-team@...com, Laurent Dufour <ldufour@...ux.ibm.com>,
        Jerome Glisse <jglisse@...gle.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Michal Hocko <mhocko@...e.com>,
        Vlastimil Babka <vbabka@...e.cz>,
        Davidlohr Bueso <dave@...olabs.net>,
        Matthew Wilcox <willy@...radead.org>,
        Liam Howlett <liam.howlett@...cle.com>,
        Rik van Riel <riel@...riel.com>,
        Paul McKenney <paulmck@...nel.org>,
        Song Liu <songliubraving@...com>,
        Suren Baghdasaryan <surenb@...gle.com>,
        Minchan Kim <minchan@...gle.com>,
        Joel Fernandes <joelaf@...gle.com>,
        David Rientjes <rientjes@...gle.com>,
        Axel Rasmussen <axelrasmussen@...gle.com>,
        Andy Lutomirski <luto@...nel.org>,
        Michel Lespinasse <michel@...pinasse.org>
Subject: [PATCH v2 19/35] mm: enable speculative fault handling through do_anonymous_page()

in x86 fault handler, only attempt spf if the vma is anonymous.

In do_handle_mm_fault(), let speculative page faults proceed as long
as they fall into anonymous vmas. This enables the speculative
handling code in __handle_mm_fault() and do_anonymous_page().

In handle_pte_fault(), if vmf->pte is set (the original pte was not
pte_none), catch speculative faults and return VM_FAULT_RETRY as
those cases are not implemented yet. Also assert that do_fault()
is not reached in the speculative case.

Signed-off-by: Michel Lespinasse <michel@...pinasse.org>
---
 arch/x86/mm/fault.c |  2 +-
 mm/memory.c         | 16 ++++++++++++----
 2 files changed, 13 insertions(+), 5 deletions(-)

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 99b0a358154e..6ba109413396 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1334,7 +1334,7 @@ void do_user_addr_fault(struct pt_regs *regs,
 		goto spf_abort;
 	rcu_read_lock();
 	vma = __find_vma(mm, address);
-	if (!vma || vma->vm_start > address) {
+	if (!vma || vma->vm_start > address || !vma_is_anonymous(vma)) {
 		rcu_read_unlock();
 		goto spf_abort;
 	}
diff --git a/mm/memory.c b/mm/memory.c
index 8d036140634d..74b51aae8166 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4365,6 +4365,8 @@ static vm_fault_t do_fault(struct vm_fault *vmf)
 	struct mm_struct *vm_mm = vma->vm_mm;
 	vm_fault_t ret;
 
+	VM_BUG_ON(vmf->flags & FAULT_FLAG_SPECULATIVE);
+
 	/*
 	 * The VMA was not fully populated on mmap() or missing VM_DONTEXPAND
 	 */
@@ -4609,6 +4611,11 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
 			return do_fault(vmf);
 	}
 
+	if (vmf->flags & FAULT_FLAG_SPECULATIVE) {
+		pte_unmap(vmf->pte);
+		return VM_FAULT_RETRY;
+	}
+
 	if (!pte_present(vmf->orig_pte))
 		return do_swap_page(vmf);
 
@@ -4937,8 +4944,7 @@ vm_fault_t do_handle_mm_fault(struct vm_area_struct *vma,
 {
 	vm_fault_t ret;
 
-	if (flags & FAULT_FLAG_SPECULATIVE)
-		return VM_FAULT_RETRY;
+	VM_BUG_ON((flags & FAULT_FLAG_SPECULATIVE) && !vma_is_anonymous(vma));
 
 	__set_current_state(TASK_RUNNING);
 
@@ -4960,10 +4966,12 @@ vm_fault_t do_handle_mm_fault(struct vm_area_struct *vma,
 	if (flags & FAULT_FLAG_USER)
 		mem_cgroup_enter_user_fault();
 
-	if (unlikely(is_vm_hugetlb_page(vma)))
+	if (unlikely(is_vm_hugetlb_page(vma))) {
+		VM_BUG_ON(flags & FAULT_FLAG_SPECULATIVE);
 		ret = hugetlb_fault(vma->vm_mm, vma, address, flags);
-	else
+	} else {
 		ret = __handle_mm_fault(vma, address, flags, seq);
+	}
 
 	if (flags & FAULT_FLAG_USER) {
 		mem_cgroup_exit_user_fault();
-- 
2.20.1