[PATCH v2 2/2] mm: prevent gup_fast from racing with COW during fork

[Jason Gunthorpe <jgg@nvidia.com>]

Since commit 70e806e4e645 ("mm: Do early cow for pinned pages during
fork() for ptes") pages under a FOLL_PIN will not be write protected
during COW for fork. This means that pages returned from
pin_user_pages(FOLL_WRITE) should not become write protected while the pin
is active.

However, there is a small race where get_user_pages_fast(FOLL_PIN) can
establish a FOLL_PIN at the same time copy_present_page() is write
protecting it:

        CPU 0                             CPU 1
   get_user_pages_fast()
    internal_get_user_pages_fast()
                                       copy_page_range()
                                         pte_alloc_map_lock()
                                           copy_present_page()
                                             atomic_read(has_pinned) == 0
					     page_maybe_dma_pinned() == false
     atomic_set(has_pinned, 1);
     gup_pgd_range()
      gup_pte_range()
       pte_t pte = gup_get_pte(ptep)
       pte_access_permitted(pte)
       try_grab_compound_head()
                                             pte = pte_wrprotect(pte)
	                                     set_pte_at();
                                         pte_unmap_unlock()
      // GUP now returns with a write protected page

The first attempt to resolve this by using the write protect caused
problems (and was missing a barrrier), see commit f3c64eda3e50 ("mm: avoid
early COW write protect games during fork()")

Instead wrap copy_p4d_range() with the write side of a seqcount and check
the read side around gup_pgd_range(). If there is a collision then
get_user_pages_fast() fails and falls back to slow GUP.

Slow GUP is safe against this race because copy_page_range() is only
called while holding the exclusive side of the mmap_lock on the src
mm_struct.

Fixes: f3c64eda3e50 ("mm: avoid early COW write protect games during fork()")
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/CAHk-=wi=iCnYCARbPGjkVJu9eyYeZ13N64tZYLdOB8CP5Q_PLw@mail.gmail.com
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 arch/x86/kernel/tboot.c    |  1 +
 drivers/firmware/efi/efi.c |  1 +
 include/linux/mm_types.h   |  7 +++++++
 kernel/fork.c              |  1 +
 mm/gup.c                   | 19 +++++++++++++++++++
 mm/init-mm.c               |  1 +
 mm/memory.c                | 10 +++++++++-
 7 files changed, 39 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index 992fb1415c0f1f..6a2f542d9588a4 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -93,6 +93,7 @@ static struct mm_struct tboot_mm = {
 	.pgd            = swapper_pg_dir,
 	.mm_users       = ATOMIC_INIT(2),
 	.mm_count       = ATOMIC_INIT(1),
+	.write_protect_seq = SEQCNT_ZERO(tboot_mm.write_protect_seq),
 	MMAP_LOCK_INITIALIZER(init_mm)
 	.page_table_lock =  __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock),
 	.mmlist         = LIST_HEAD_INIT(init_mm.mmlist),
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 5e5480a0a32d7d..2520f6e05f4d44 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -57,6 +57,7 @@ struct mm_struct efi_mm = {
 	.mm_rb			= RB_ROOT,
 	.mm_users		= ATOMIC_INIT(2),
 	.mm_count		= ATOMIC_INIT(1),
+	.write_protect_seq      = SEQCNT_ZERO(efi_mm.write_protect_seq),
 	MMAP_LOCK_INITIALIZER(efi_mm)
 	.page_table_lock	= __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock),
 	.mmlist			= LIST_HEAD_INIT(efi_mm.mmlist),
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 5a9238f6caad97..f13beacda6fd23 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -14,6 +14,7 @@
 #include <linux/uprobes.h>
 #include <linux/page-flags-layout.h>
 #include <linux/workqueue.h>
+#include <linux/seqlock.h>
 
 #include <asm/mmu.h>
 
@@ -446,6 +447,12 @@ struct mm_struct {
 		 */
 		atomic_t has_pinned;
 
+		/**
+		 * @write_protect_seq: Odd when any thread is write protecting
+		 * pages in this mm, for instance during fork().
+		 */
+		seqcount_t write_protect_seq;
+
 #ifdef CONFIG_MMU
 		atomic_long_t pgtables_bytes;	/* PTE page table pages */
 #endif
diff --git a/kernel/fork.c b/kernel/fork.c
index 32083db7a2a23e..6fd934a6d60d96 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1007,6 +1007,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	mm->vmacache_seqnum = 0;
 	atomic_set(&mm->mm_users, 1);
 	atomic_set(&mm->mm_count, 1);
+	seqcount_init(&mm->write_protect_seq);
 	mmap_init_lock(mm);
 	INIT_LIST_HEAD(&mm->mmlist);
 	mm->core_state = NULL;
diff --git a/mm/gup.c b/mm/gup.c
index 150cc962c99201..7944749ed7252f 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2678,11 +2678,18 @@ static unsigned long lockless_pages_from_mm(unsigned long start,
 {
 	unsigned long flags;
 	int nr_pinned = 0;
+	unsigned seq;
 
 	if (!IS_ENABLED(CONFIG_HAVE_FAST_GUP) ||
 	    !gup_fast_permitted(start, end))
 		return 0;
 
+	if (gup_flags & FOLL_PIN) {
+		seq = raw_read_seqcount(&current->mm->write_protect_seq);
+		if (seq & 1)
+			return 0;
+	}
+
 	/*
 	 * Disable interrupts. The nested form is used, in order to allow full,
 	 * general purpose use of this routine.
@@ -2697,6 +2704,18 @@ static unsigned long lockless_pages_from_mm(unsigned long start,
 	local_irq_save(flags);
 	gup_pgd_range(start, end, gup_flags, pages, &nr_pinned);
 	local_irq_restore(flags);
+
+	/*
+	 * When pinning pages for DMA there could be a concurrent write protect
+	 * from fork() via copy_page_range(), in this case always fail fast GUP.
+	 */
+	if (gup_flags & FOLL_PIN) {
+		if (read_seqcount_t_retry(&current->mm->write_protect_seq,
+					  seq)) {
+			unpin_user_pages(pages, nr_pinned);
+			return 0;
+		}
+	}
 	return nr_pinned;
 }
 
diff --git a/mm/init-mm.c b/mm/init-mm.c
index 3a613c85f9ede2..153162669f8062 100644
--- a/mm/init-mm.c
+++ b/mm/init-mm.c
@@ -31,6 +31,7 @@ struct mm_struct init_mm = {
 	.pgd		= swapper_pg_dir,
 	.mm_users	= ATOMIC_INIT(2),
 	.mm_count	= ATOMIC_INIT(1),
+	.write_protect_seq = SEQCNT_ZERO(init_mm.write_protect_seq),
 	MMAP_LOCK_INITIALIZER(init_mm)
 	.page_table_lock =  __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock),
 	.arg_lock	=  __SPIN_LOCK_UNLOCKED(init_mm.arg_lock),
diff --git a/mm/memory.c b/mm/memory.c
index c48f8df6e50268..294c2c3c4fe00d 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1171,6 +1171,12 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 		mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE,
 					0, src_vma, src_mm, addr, end);
 		mmu_notifier_invalidate_range_start(&range);
+		/*
+		 * The read side doesn't spin, it goes to the mmap_lock, so the
+		 * raw version is used to avoid disabling preemption here
+		 */
+		mmap_assert_write_locked(src_mm);
+		raw_write_seqcount_t_begin(&src_mm->write_protect_seq);
 	}
 
 	ret = 0;
@@ -1187,8 +1193,10 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 		}
 	} while (dst_pgd++, src_pgd++, addr = next, addr != end);
 
-	if (is_cow)
+	if (is_cow) {
+		raw_write_seqcount_t_end(&src_mm->write_protect_seq);
 		mmu_notifier_invalidate_range_end(&range);
+	}
 	return ret;
 }
 
-- 
2.28.0