[RFCv2 08/13] mm/gup: Add FOLL_ALLOW_POISONED

From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
To: Dave Hansen <dave.hansen@linux.intel.com>,
	Andy Lutomirski <luto@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Sean Christopherson <seanjc@google.com>,
	Jim Mattson <jmattson@google.com>
Cc: David Rientjes <rientjes@google.com>,
	"Edgecombe, Rick P" <rick.p.edgecombe@intel.com>,
	"Kleen, Andi" <andi.kleen@intel.com>,
	"Yamahata, Isaku" <isaku.yamahata@intel.com>,
	Erdem Aktas <erdemaktas@google.com>,
	Steve Rutherford <srutherford@google.com>,
	Peter Gonda <pgonda@google.com>,
	David Hildenbrand <david@redhat.com>,
	x86@kernel.org, kvm@vger.kernel.org, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org,
	"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Subject: [RFCv2 08/13] mm/gup: Add FOLL_ALLOW_POISONED
Date: Fri, 16 Apr 2021 18:41:01 +0300	[thread overview]
Message-ID: <20210416154106.23721-9-kirill.shutemov@linux.intel.com> (raw)
In-Reply-To: <20210416154106.23721-1-kirill.shutemov@linux.intel.com>

The new flag allows to bypass check if the page is poisoned and get
reference on it.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 include/linux/mm.h |  1 +
 mm/gup.c           | 29 ++++++++++++++++++-----------
 2 files changed, 19 insertions(+), 11 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index ecdf8a8cd6ae..378a94481fd1 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2802,6 +2802,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 #define FOLL_SPLIT_PMD	0x20000	/* split huge pmd before returning */
 #define FOLL_PIN	0x40000	/* pages must be released via unpin_user_page */
 #define FOLL_FAST_ONLY	0x80000	/* gup_fast: prevent fall-back to slow gup */
+#define FOLL_ALLOW_POISONED 0x100000 /* bypass poison check */
 
 /*
  * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each
diff --git a/mm/gup.c b/mm/gup.c
index e4c224cd9661..dd3b79b03eb5 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -384,22 +384,29 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
 	pte = *ptep;
 	if (!pte_present(pte)) {
-		swp_entry_t entry;
+		swp_entry_t entry = pte_to_swp_entry(pte);
+
+		if (pte_none(pte))
+			goto no_page;
+
 		/*
 		 * KSM's break_ksm() relies upon recognizing a ksm page
 		 * even while it is being migrated, so for that case we
 		 * need migration_entry_wait().
 		 */
-		if (likely(!(flags & FOLL_MIGRATION)))
-			goto no_page;
-		if (pte_none(pte))
-			goto no_page;
-		entry = pte_to_swp_entry(pte);
-		if (!is_migration_entry(entry))
-			goto no_page;
-		pte_unmap_unlock(ptep, ptl);
-		migration_entry_wait(mm, pmd, address);
-		goto retry;
+		if (is_migration_entry(entry) && (flags & FOLL_MIGRATION)) {
+			pte_unmap_unlock(ptep, ptl);
+			migration_entry_wait(mm, pmd, address);
+			goto retry;
+		}
+
+		if (is_hwpoison_entry(entry) && (flags & FOLL_ALLOW_POISONED)) {
+			page = hwpoison_entry_to_page(entry);
+			get_page(page);
+			goto out;
+		}
+
+		goto no_page;
 	}
 	if ((flags & FOLL_NUMA) && pte_protnone(pte))
 		goto no_page;
-- 
2.26.3

