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/hmm.c b/mm/hmm.c
index d379cb6..c49e9df 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -474,23 +474,32 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
- unsigned long addr = start, next;
- pmd_t *pmdp;
+ unsigned long addr = start;
pud_t pud;
- int ret;
+ int ret = 0;
+ spinlock_t *ptl = pud_trans_huge_lock(pudp, walk->vma);
-again:
+ if (!ptl)
+ return 0;
+
+ /* Normally we don't want to split the huge page */
+ walk->action = ACTION_CONTINUE;
+
pud = READ_ONCE(*pudp);
- if (pud_none(pud))
- return hmm_vma_walk_hole(start, end, walk);
+ if (pud_none(pud)) {
+ ret = hmm_vma_walk_hole(start, end, walk);
+ goto out_unlock;
+ }
if (pud_huge(pud) && pud_devmap(pud)) {
unsigned long i, npages, pfn;
uint64_t *pfns, cpu_flags;
bool fault, write_fault;
- if (!pud_present(pud))
- return hmm_vma_walk_hole(start, end, walk);
+ if (!pud_present(pud)) {
+ ret = hmm_vma_walk_hole(start, end, walk);
+ goto out_unlock;
+ }
i = (addr - range->start) >> PAGE_SHIFT;
npages = (end - addr) >> PAGE_SHIFT;
@@ -499,16 +508,20 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
cpu_flags = pud_to_hmm_pfn_flags(range, pud);
hmm_range_need_fault(hmm_vma_walk, pfns, npages,
cpu_flags, &fault, &write_fault);
- if (fault || write_fault)
- return hmm_vma_walk_hole_(addr, end, fault,
- write_fault, walk);
+ if (fault || write_fault) {
+ ret = hmm_vma_walk_hole_(addr, end, fault,
+ write_fault, walk);
+ goto out_unlock;
+ }
pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
for (i = 0; i < npages; ++i, ++pfn) {
hmm_vma_walk->pgmap = get_dev_pagemap(pfn,
hmm_vma_walk->pgmap);
- if (unlikely(!hmm_vma_walk->pgmap))
- return -EBUSY;
+ if (unlikely(!hmm_vma_walk->pgmap)) {
+ ret = -EBUSY;
+ goto out_unlock;
+ }
pfns[i] = hmm_device_entry_from_pfn(range, pfn) |
cpu_flags;
}
@@ -517,22 +530,15 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
hmm_vma_walk->pgmap = NULL;
}
hmm_vma_walk->last = end;
- return 0;
+ goto out_unlock;
}
- split_huge_pud(walk->vma, pudp, addr);
- if (pud_none(*pudp))
- goto again;
+ /* Ask for the PUD to be split */
+ walk->action = ACTION_SUBTREE;
- pmdp = pmd_offset(pudp, addr);
- do {
- next = pmd_addr_end(addr, end);
- ret = hmm_vma_walk_pmd(pmdp, addr, next, walk);
- if (ret)
- return ret;
- } while (pmdp++, addr = next, addr != end);
-
- return 0;
+out_unlock:
+ spin_unlock(ptl);
+ return ret;
}
#else
#define hmm_vma_walk_pud NULL
