mm: pagewalk: add p4d_entry() and pgd_entry()
pgd_entry() and pud_entry() were removed by commit 0b1fbfe50006c410
("mm/pagewalk: remove pgd_entry() and pud_entry()") because there were no
users. We're about to add users so reintroduce them, along with
p4d_entry() as we now have 5 levels of tables.
Note that commit a00cc7d9dd93d66a ("mm, x86: add support for PUD-sized
transparent hugepages") already re-added pud_entry() but with different
semantics to the other callbacks. This commit reverts the semantics back
to match the other callbacks.
To support hmm.c which now uses the new semantics of pud_entry() a new
member ('action') of struct mm_walk is added which allows the callbacks to
either descend (ACTION_SUBTREE, the default), skip (ACTION_CONTINUE) or
repeat the callback (ACTION_AGAIN). hmm.c is then updated to call
pud_trans_huge_lock() itself and make use of the splitting/retry logic of
the core code.
After this change pud_entry() is called for all entries, not just
transparent huge pages.
[arnd@arndb.de: fix unused variable warning]
Link: http://lkml.kernel.org/r/20200107204607.1533842-1-arnd@arndb.de
Link: http://lkml.kernel.org/r/20191218162402.45610-12-steven.price@arm.com
Signed-off-by: Steven Price <steven.price@arm.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Hogan <jhogan@kernel.org>
Cc: James Morse <james.morse@arm.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Liang, Kan" <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Burton <paul.burton@mips.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Will Deacon <will@kernel.org>
Cc: Zong Li <zong.li@sifive.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index ea0b9e6..690af44 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -46,6 +46,9 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
break;
continue;
}
+
+ walk->action = ACTION_SUBTREE;
+
/*
* This implies that each ->pmd_entry() handler
* needs to know about pmd_trans_huge() pmds
@@ -55,16 +58,21 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
if (err)
break;
+ if (walk->action == ACTION_AGAIN)
+ goto again;
+
/*
* Check this here so we only break down trans_huge
* pages when we _need_ to
*/
- if (!ops->pte_entry)
+ if (walk->action == ACTION_CONTINUE ||
+ !(ops->pte_entry))
continue;
split_huge_pmd(walk->vma, pmd, addr);
if (pmd_trans_unstable(pmd))
goto again;
+
err = walk_pte_range(pmd, addr, next, walk);
if (err)
break;
@@ -93,24 +101,25 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
continue;
}
- if (ops->pud_entry) {
- spinlock_t *ptl = pud_trans_huge_lock(pud, walk->vma);
+ walk->action = ACTION_SUBTREE;
- if (ptl) {
- err = ops->pud_entry(pud, addr, next, walk);
- spin_unlock(ptl);
- if (err)
- break;
- continue;
- }
- }
+ if (ops->pud_entry)
+ err = ops->pud_entry(pud, addr, next, walk);
+ if (err)
+ break;
+
+ if (walk->action == ACTION_AGAIN)
+ goto again;
+
+ if (walk->action == ACTION_CONTINUE ||
+ !(ops->pmd_entry || ops->pte_entry))
+ continue;
split_huge_pud(walk->vma, pud, addr);
if (pud_none(*pud))
goto again;
- if (ops->pmd_entry || ops->pte_entry)
- err = walk_pmd_range(pud, addr, next, walk);
+ err = walk_pmd_range(pud, addr, next, walk);
if (err)
break;
} while (pud++, addr = next, addr != end);
@@ -136,7 +145,12 @@ static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
break;
continue;
}
- if (ops->pmd_entry || ops->pte_entry)
+ if (ops->p4d_entry) {
+ err = ops->p4d_entry(p4d, addr, next, walk);
+ if (err)
+ break;
+ }
+ if (ops->pud_entry || ops->pmd_entry || ops->pte_entry)
err = walk_pud_range(p4d, addr, next, walk);
if (err)
break;
@@ -163,7 +177,13 @@ static int walk_pgd_range(unsigned long addr, unsigned long end,
break;
continue;
}
- if (ops->pmd_entry || ops->pte_entry)
+ if (ops->pgd_entry) {
+ err = ops->pgd_entry(pgd, addr, next, walk);
+ if (err)
+ break;
+ }
+ if (ops->p4d_entry || ops->pud_entry || ops->pmd_entry ||
+ ops->pte_entry)
err = walk_p4d_range(pgd, addr, next, walk);
if (err)
break;