[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20240809160909.1023470-7-peterx@redhat.com>
Date: Fri, 9 Aug 2024 12:08:56 -0400
From: Peter Xu <peterx@...hat.com>
To: linux-mm@...ck.org,
linux-kernel@...r.kernel.org
Cc: Sean Christopherson <seanjc@...gle.com>,
Oscar Salvador <osalvador@...e.de>,
Jason Gunthorpe <jgg@...dia.com>,
Axel Rasmussen <axelrasmussen@...gle.com>,
linux-arm-kernel@...ts.infradead.org,
x86@...nel.org,
peterx@...hat.com,
Will Deacon <will@...nel.org>,
Gavin Shan <gshan@...hat.com>,
Paolo Bonzini <pbonzini@...hat.com>,
Zi Yan <ziy@...dia.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Catalin Marinas <catalin.marinas@....com>,
Ingo Molnar <mingo@...hat.com>,
Alistair Popple <apopple@...dia.com>,
Borislav Petkov <bp@...en8.de>,
David Hildenbrand <david@...hat.com>,
Thomas Gleixner <tglx@...utronix.de>,
kvm@...r.kernel.org,
Dave Hansen <dave.hansen@...ux.intel.com>,
Alex Williamson <alex.williamson@...hat.com>,
Yan Zhao <yan.y.zhao@...el.com>
Subject: [PATCH 06/19] mm/pagewalk: Check pfnmap early for folio_walk_start()
Pfnmaps can always be identified with special bits in the ptes/pmds/puds.
However that's unnecessary if the vma is stable, and when it's mapped under
VM_PFNMAP | VM_IO.
Instead of adding similar checks in all the levels for huge pfnmaps, let
folio_walk_start() fail even earlier for these mappings. It's also
something gup-slow already does, so make them match.
Cc: David Hildenbrand <david@...hat.com>
Signed-off-by: Peter Xu <peterx@...hat.com>
---
mm/pagewalk.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index cd79fb3b89e5..fd3965efe773 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -727,6 +727,11 @@ struct folio *folio_walk_start(struct folio_walk *fw,
p4d_t *p4dp;
mmap_assert_locked(vma->vm_mm);
+
+ /* It has no folio backing the mappings at all.. */
+ if (vma->vm_flags & (VM_IO | VM_PFNMAP))
+ return NULL;
+
vma_pgtable_walk_begin(vma);
if (WARN_ON_ONCE(addr < vma->vm_start || addr >= vma->vm_end))
--
2.45.0
Powered by blists - more mailing lists