Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Michel Lespinasse <michel@lespinasse.org>
To:     Linux-MM <linux-mm@kvack.org>,
        Linux-Kernel <linux-kernel@vger.kernel.org>
Cc:     Laurent Dufour <ldufour@linux.ibm.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Michal Hocko <mhocko@suse.com>,
        Matthew Wilcox <willy@infradead.org>,
        Rik van Riel <riel@surriel.com>,
        Paul McKenney <paulmck@kernel.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        Suren Baghdasaryan <surenb@google.com>,
        Joel Fernandes <joelaf@google.com>,
        Andy Lutomirski <luto@kernel.org>,
        Michel Lespinasse <michel@lespinasse.org>
Subject: [PATCH 21/29] mm: implement speculative handling in wp_page_copy()
Date:   Fri, 30 Apr 2021 12:52:22 -0700
Message-Id: <20210430195232.30491-22-michel@lespinasse.org>
In-Reply-To: <20210430195232.30491-1-michel@lespinasse.org>
References: <20210430195232.30491-1-michel@lespinasse.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Change wp_page_copy() to handle the speculative case.
This involves aborting speculative faults if they have to allocate an
anon_vma, and using pte_map_lock() instead of pte_offset_map_lock()
to complete the page fault.

Also change call sites to clear vmf->pte after unmapping the page table,
in order to satisfy pte_map_lock()'s preconditions.

Signed-off-by: Michel Lespinasse <michel@lespinasse.org>
---
 mm/memory.c | 31 ++++++++++++++++++++++---------
 1 file changed, 22 insertions(+), 9 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index 286776b7795b..cb66585f5145 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2928,20 +2928,27 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 	pte_t entry;
 	int page_copied = 0;
 	struct mmu_notifier_range range;
+	vm_fault_t ret = VM_FAULT_OOM;
 
-	if (unlikely(anon_vma_prepare(vma)))
-		goto oom;
+	if (unlikely(!vma->anon_vma)) {
+		if (vmf->flags & FAULT_FLAG_SPECULATIVE) {
+			ret = VM_FAULT_RETRY;
+			goto out;
+		}
+		if (__anon_vma_prepare(vma))
+			goto out;
+	}
 
 	if (is_zero_pfn(pte_pfn(vmf->orig_pte))) {
 		new_page = alloc_zeroed_user_highpage_movable(vma,
 							      vmf->address);
 		if (!new_page)
-			goto oom;
+			goto out;
 	} else {
 		new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma,
 				vmf->address);
 		if (!new_page)
-			goto oom;
+			goto out;
 
 		if (!cow_user_page(new_page, old_page, vmf)) {
 			/*
@@ -2958,7 +2965,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 	}
 
 	if (mem_cgroup_charge(new_page, mm, GFP_KERNEL))
-		goto oom_free_new;
+		goto out_free_new;
 	cgroup_throttle_swaprate(new_page, GFP_KERNEL);
 
 	__SetPageUptodate(new_page);
@@ -2971,7 +2978,11 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 	/*
 	 * Re-check the pte - we dropped the lock
 	 */
-	vmf->pte = pte_offset_map_lock(mm, vmf->pmd, vmf->address, &vmf->ptl);
+	if (!pte_map_lock(vmf)) {
+		ret = VM_FAULT_RETRY;
+		/* put_page() will uncharge the page */
+		goto out_free_new;
+	}
 	if (likely(pte_same(*vmf->pte, vmf->orig_pte))) {
 		if (old_page) {
 			if (!PageAnon(old_page)) {
@@ -3059,12 +3070,12 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 		put_page(old_page);
 	}
 	return page_copied ? VM_FAULT_WRITE : 0;
-oom_free_new:
+out_free_new:
 	put_page(new_page);
-oom:
+out:
 	if (old_page)
 		put_page(old_page);
-	return VM_FAULT_OOM;
+	return ret;
 }
 
 /**
@@ -3207,6 +3218,7 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 			return wp_pfn_shared(vmf);
 
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
+		vmf->pte = NULL;
 		return wp_page_copy(vmf);
 	}
 
@@ -3245,6 +3257,7 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 	get_page(vmf->page);
 
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
+	vmf->pte = NULL;
 	return wp_page_copy(vmf);
 }
 
-- 
2.20.1