* [PATCH v3 1/5] ARC: mm: remove __ARCH_USE_5LEVEL_HACK
2019-10-16 16:23 [PATCH v3 0/5] elide extraneous generated code for folded p4d/pud/pmd Vineet Gupta
@ 2019-10-16 16:23 ` Vineet Gupta
2019-10-16 16:23 ` [PATCH v3 2/5] asm-generic/tlb: stub out pud_free_tlb() if nopud Vineet Gupta
` (3 subsequent siblings)
4 siblings, 0 replies; 6+ messages in thread
From: Vineet Gupta @ 2019-10-16 16:23 UTC (permalink / raw)
To: linux-mm
Cc: linux-snps-arc, linux-kernel, linux-arch, Arnd Bergmann,
Will Deacon, Aneesh Kumar K . V, Andrew Morton, Nick Piggin,
Peter Zijlstra, Kirill A . Shutemov, Linus Torvalds,
Vineet Gupta
With paging code made 5-level compliant, this is no longer needed.
ARC has software page walker with 2 lookup levels (pgd -> pte)
This was expected to be non functional change but ended with slight
code bloat due to needless inclusions of p*d_free_tlb() macros which
will be addressed in further patches.
| bloat-o-meter2 vmlinux-[AB]*
| add/remove: 0/0 grow/shrink: 2/0 up/down: 128/0 (128)
| function old new delta
| free_pgd_range 546 656 +110
| p4d_clear_bad 2 20 +18
| Total: Before=4137148, After=4137276, chg 0.000000%
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
---
arch/arc/include/asm/pgtable.h | 1 -
arch/arc/mm/fault.c | 10 ++++++++--
arch/arc/mm/highmem.c | 4 +++-
3 files changed, 11 insertions(+), 4 deletions(-)
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 7addd0301c51..b917b596f7fb 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -33,7 +33,6 @@
#define _ASM_ARC_PGTABLE_H
#include <linux/bits.h>
-#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
#include <asm/page.h>
#include <asm/mmu.h> /* to propagate CONFIG_ARC_MMU_VER <n> */
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index 3861543b66a0..fb86bc3e9b35 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -30,6 +30,7 @@ noinline static int handle_kernel_vaddr_fault(unsigned long address)
* with the 'reference' page table.
*/
pgd_t *pgd, *pgd_k;
+ p4d_t *p4d, *p4d_k;
pud_t *pud, *pud_k;
pmd_t *pmd, *pmd_k;
@@ -39,8 +40,13 @@ noinline static int handle_kernel_vaddr_fault(unsigned long address)
if (!pgd_present(*pgd_k))
goto bad_area;
- pud = pud_offset(pgd, address);
- pud_k = pud_offset(pgd_k, address);
+ p4d = p4d_offset(pgd, address);
+ p4d_k = p4d_offset(pgd_k, address);
+ if (!p4d_present(*p4d_k))
+ goto bad_area;
+
+ pud = pud_offset(p4d, address);
+ pud_k = pud_offset(p4d_k, address);
if (!pud_present(*pud_k))
goto bad_area;
diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c
index a4856bfaedf3..fc8849e4f72e 100644
--- a/arch/arc/mm/highmem.c
+++ b/arch/arc/mm/highmem.c
@@ -111,12 +111,14 @@ EXPORT_SYMBOL(__kunmap_atomic);
static noinline pte_t * __init alloc_kmap_pgtable(unsigned long kvaddr)
{
pgd_t *pgd_k;
+ p4d_t *p4d_k;
pud_t *pud_k;
pmd_t *pmd_k;
pte_t *pte_k;
pgd_k = pgd_offset_k(kvaddr);
- pud_k = pud_offset(pgd_k, kvaddr);
+ p4d_k = p4d_offset(pgd_k, kvaddr);
+ pud_k = pud_offset(p4d_k, kvaddr);
pmd_k = pmd_offset(pud_k, kvaddr);
pte_k = (pte_t *)memblock_alloc_low(PAGE_SIZE, PAGE_SIZE);
--
2.20.1
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH v3 2/5] asm-generic/tlb: stub out pud_free_tlb() if nopud ...
2019-10-16 16:23 [PATCH v3 0/5] elide extraneous generated code for folded p4d/pud/pmd Vineet Gupta
2019-10-16 16:23 ` [PATCH v3 1/5] ARC: mm: remove __ARCH_USE_5LEVEL_HACK Vineet Gupta
@ 2019-10-16 16:23 ` Vineet Gupta
2019-10-16 16:23 ` [PATCH v3 3/5] asm-generic/tlb: stub out p4d_free_tlb() if nop4d Vineet Gupta
` (2 subsequent siblings)
4 siblings, 0 replies; 6+ messages in thread
From: Vineet Gupta @ 2019-10-16 16:23 UTC (permalink / raw)
To: linux-mm
Cc: linux-snps-arc, linux-kernel, linux-arch, Arnd Bergmann,
Will Deacon, Aneesh Kumar K . V, Andrew Morton, Nick Piggin,
Peter Zijlstra, Kirill A . Shutemov, Linus Torvalds,
Vineet Gupta
... independent of __ARCH_HAS_4LEVEL_HACK
This came up when removing __ARCH_HAS_5LEVEL_HACK for ARC as code bloat.
With this patch we see the following code reduction
| bloat-o-meter2 vmlinux-B-elide-ARCH_USE_5LEVEL_HACK vmlinux-C-elide-pud_free_tlb
| add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-104 (-104)
| function old new delta
| free_pgd_range 656 552 -104
| Total: Before=4137276, After=4137172, chg -1.000000%
Note: The primary change is alternate defintion for pud_free_tlb() but
while there also removed empty stubs for __pud_free_tlb, which is anyhow
called only from pud_free_tlb()
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
---
include/asm-generic/4level-fixup.h | 1 -
include/asm-generic/pgtable-nopud.h | 2 +-
include/asm-generic/tlb.h | 2 --
3 files changed, 1 insertion(+), 4 deletions(-)
diff --git a/include/asm-generic/4level-fixup.h b/include/asm-generic/4level-fixup.h
index e3667c9a33a5..c86cf7cb4bba 100644
--- a/include/asm-generic/4level-fixup.h
+++ b/include/asm-generic/4level-fixup.h
@@ -30,7 +30,6 @@
#undef pud_free_tlb
#define pud_free_tlb(tlb, x, addr) do { } while (0)
#define pud_free(mm, x) do { } while (0)
-#define __pud_free_tlb(tlb, x, addr) do { } while (0)
#undef pud_addr_end
#define pud_addr_end(addr, end) (end)
diff --git a/include/asm-generic/pgtable-nopud.h b/include/asm-generic/pgtable-nopud.h
index c77a1d301155..d3776cb494c0 100644
--- a/include/asm-generic/pgtable-nopud.h
+++ b/include/asm-generic/pgtable-nopud.h
@@ -59,7 +59,7 @@ static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
*/
#define pud_alloc_one(mm, address) NULL
#define pud_free(mm, x) do { } while (0)
-#define __pud_free_tlb(tlb, x, a) do { } while (0)
+#define pud_free_tlb(tlb, x, a) do { } while (0)
#undef pud_addr_end
#define pud_addr_end(addr, end) (end)
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 04c0644006fd..5e0c2d01e656 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -584,7 +584,6 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
} while (0)
#endif
-#ifndef __ARCH_HAS_4LEVEL_HACK
#ifndef pud_free_tlb
#define pud_free_tlb(tlb, pudp, address) \
do { \
@@ -594,7 +593,6 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
__pud_free_tlb(tlb, pudp, address); \
} while (0)
#endif
-#endif
#ifndef __ARCH_HAS_5LEVEL_HACK
#ifndef p4d_free_tlb
--
2.20.1
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH v3 3/5] asm-generic/tlb: stub out p4d_free_tlb() if nop4d ...
2019-10-16 16:23 [PATCH v3 0/5] elide extraneous generated code for folded p4d/pud/pmd Vineet Gupta
2019-10-16 16:23 ` [PATCH v3 1/5] ARC: mm: remove __ARCH_USE_5LEVEL_HACK Vineet Gupta
2019-10-16 16:23 ` [PATCH v3 2/5] asm-generic/tlb: stub out pud_free_tlb() if nopud Vineet Gupta
@ 2019-10-16 16:23 ` Vineet Gupta
2019-10-16 16:23 ` [PATCH v3 4/5] asm-generic/tlb: stub out pmd_free_tlb() if nopmd Vineet Gupta
2019-10-16 16:24 ` [PATCH v3 5/5] asm-generic/mm: stub out p{4,u}d_clear_bad() if __PAGETABLE_P{4,U}D_FOLDED Vineet Gupta
4 siblings, 0 replies; 6+ messages in thread
From: Vineet Gupta @ 2019-10-16 16:23 UTC (permalink / raw)
To: linux-mm
Cc: linux-snps-arc, linux-kernel, linux-arch, Arnd Bergmann,
Will Deacon, Aneesh Kumar K . V, Andrew Morton, Nick Piggin,
Peter Zijlstra, Kirill A . Shutemov, Linus Torvalds,
Vineet Gupta
... independent of __ARCH_HAS_5LEVEL_HACK
This came up when removing __ARCH_HAS_5LEVEL_HACK for ARC as code bloat.
With this patch we see the following code reduction
| bloat-o-meter2 vmlinux-C-elide-pud_free_tlb vmlinux-D-elide-p4d_free_tlb
| add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-104 (-104)
| function old new delta
| free_pgd_range 552 422 -130
| Total: Before=4137172, After=4137042, chg -1.000000%
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
---
include/asm-generic/5level-fixup.h | 1 -
include/asm-generic/pgtable-nop4d.h | 2 +-
include/asm-generic/tlb.h | 2 --
3 files changed, 1 insertion(+), 4 deletions(-)
diff --git a/include/asm-generic/5level-fixup.h b/include/asm-generic/5level-fixup.h
index f6947da70d71..4c74b1c1d13b 100644
--- a/include/asm-generic/5level-fixup.h
+++ b/include/asm-generic/5level-fixup.h
@@ -51,7 +51,6 @@ static inline int p4d_present(p4d_t p4d)
#undef p4d_free_tlb
#define p4d_free_tlb(tlb, x, addr) do { } while (0)
#define p4d_free(mm, x) do { } while (0)
-#define __p4d_free_tlb(tlb, x, addr) do { } while (0)
#undef p4d_addr_end
#define p4d_addr_end(addr, end) (end)
diff --git a/include/asm-generic/pgtable-nop4d.h b/include/asm-generic/pgtable-nop4d.h
index aebab905e6cd..ce2cbb3c380f 100644
--- a/include/asm-generic/pgtable-nop4d.h
+++ b/include/asm-generic/pgtable-nop4d.h
@@ -50,7 +50,7 @@ static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
*/
#define p4d_alloc_one(mm, address) NULL
#define p4d_free(mm, x) do { } while (0)
-#define __p4d_free_tlb(tlb, x, a) do { } while (0)
+#define p4d_free_tlb(tlb, x, a) do { } while (0)
#undef p4d_addr_end
#define p4d_addr_end(addr, end) (end)
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 5e0c2d01e656..05dddc17522b 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -594,7 +594,6 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
} while (0)
#endif
-#ifndef __ARCH_HAS_5LEVEL_HACK
#ifndef p4d_free_tlb
#define p4d_free_tlb(tlb, pudp, address) \
do { \
@@ -603,7 +602,6 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
__p4d_free_tlb(tlb, pudp, address); \
} while (0)
#endif
-#endif
#endif /* CONFIG_MMU */
--
2.20.1
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH v3 4/5] asm-generic/tlb: stub out pmd_free_tlb() if nopmd
2019-10-16 16:23 [PATCH v3 0/5] elide extraneous generated code for folded p4d/pud/pmd Vineet Gupta
` (2 preceding siblings ...)
2019-10-16 16:23 ` [PATCH v3 3/5] asm-generic/tlb: stub out p4d_free_tlb() if nop4d Vineet Gupta
@ 2019-10-16 16:23 ` Vineet Gupta
2019-10-16 16:24 ` [PATCH v3 5/5] asm-generic/mm: stub out p{4,u}d_clear_bad() if __PAGETABLE_P{4,U}D_FOLDED Vineet Gupta
4 siblings, 0 replies; 6+ messages in thread
From: Vineet Gupta @ 2019-10-16 16:23 UTC (permalink / raw)
To: linux-mm
Cc: linux-snps-arc, linux-kernel, linux-arch, Arnd Bergmann,
Will Deacon, Aneesh Kumar K . V, Andrew Morton, Nick Piggin,
Peter Zijlstra, Kirill A . Shutemov, Linus Torvalds,
Vineet Gupta
This came up when removing __ARCH_HAS_5LEVEL_HACK for ARC as code bloat.
With this patch we see the following code reduction.
| bloat-o-meter2 vmlinux-E-elide-p?d_clear_bad vmlinux-F-elide-pmd_free_tlb
| add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-112 (-112)
| function old new delta
| free_pgd_range 422 310 -112
| Total: Before=4137042, After=4136930, chg -1.000000%
Note that pmd folding can be tricky: In 2-level setup (where pmd is
conceptually folded) most pmd routines are valid and refer to upper levels.
In this patch we can, but see next patch for example where we can't
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
---
include/asm-generic/pgtable-nopmd.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/asm-generic/pgtable-nopmd.h b/include/asm-generic/pgtable-nopmd.h
index b85b8271a73d..0d9b28cba16d 100644
--- a/include/asm-generic/pgtable-nopmd.h
+++ b/include/asm-generic/pgtable-nopmd.h
@@ -60,7 +60,7 @@ static inline pmd_t * pmd_offset(pud_t * pud, unsigned long address)
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
{
}
-#define __pmd_free_tlb(tlb, x, a) do { } while (0)
+#define pmd_free_tlb(tlb, x, a) do { } while (0)
#undef pmd_addr_end
#define pmd_addr_end(addr, end) (end)
--
2.20.1
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH v3 5/5] asm-generic/mm: stub out p{4,u}d_clear_bad() if __PAGETABLE_P{4,U}D_FOLDED
2019-10-16 16:23 [PATCH v3 0/5] elide extraneous generated code for folded p4d/pud/pmd Vineet Gupta
` (3 preceding siblings ...)
2019-10-16 16:23 ` [PATCH v3 4/5] asm-generic/tlb: stub out pmd_free_tlb() if nopmd Vineet Gupta
@ 2019-10-16 16:24 ` Vineet Gupta
4 siblings, 0 replies; 6+ messages in thread
From: Vineet Gupta @ 2019-10-16 16:24 UTC (permalink / raw)
To: linux-mm
Cc: linux-snps-arc, linux-kernel, linux-arch, Arnd Bergmann,
Will Deacon, Aneesh Kumar K . V, Andrew Morton, Nick Piggin,
Peter Zijlstra, Kirill A . Shutemov, Linus Torvalds,
Vineet Gupta
This came up when removing __ARCH_HAS_5LEVEL_HACK for ARC as code bloat.
With this patch we see the following code reduction.
| bloat-o-meter2 vmlinux-D-elide-p4d_free_tlb vmlinux-E-elide-p?d_clear_bad
| add/remove: 0/2 grow/shrink: 0/0 up/down: 0/-40 (-40)
| function old new delta
| pud_clear_bad 20 - -20
| p4d_clear_bad 20 - -20
| Total: Before=4136930, After=4136890, chg -1.000000%
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
---
include/asm-generic/pgtable.h | 11 +++++++++++
mm/pgtable-generic.c | 9 +++++++++
2 files changed, 20 insertions(+)
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 818691846c90..9cdcbc7c0b7b 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -558,8 +558,19 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
* Do the tests inline, but report and clear the bad entry in mm/memory.c.
*/
void pgd_clear_bad(pgd_t *);
+
+#ifndef __PAGETABLE_P4D_FOLDED
void p4d_clear_bad(p4d_t *);
+#else
+#define p4d_clear_bad(p4d) do { } while (0)
+#endif
+
+#ifndef __PAGETABLE_PUD_FOLDED
void pud_clear_bad(pud_t *);
+#else
+#define pud_clear_bad(p4d) do { } while (0)
+#endif
+
void pmd_clear_bad(pmd_t *);
static inline int pgd_none_or_clear_bad(pgd_t *pgd)
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 532c29276fce..3d7c01e76efc 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -24,18 +24,27 @@ void pgd_clear_bad(pgd_t *pgd)
pgd_clear(pgd);
}
+#ifndef __PAGETABLE_P4D_FOLDED
void p4d_clear_bad(p4d_t *p4d)
{
p4d_ERROR(*p4d);
p4d_clear(p4d);
}
+#endif
+#ifndef __PAGETABLE_PUD_FOLDED
void pud_clear_bad(pud_t *pud)
{
pud_ERROR(*pud);
pud_clear(pud);
}
+#endif
+/*
+ * Note that the pmd variant below can't be stub'ed out just as for p4d/pud
+ * above. pmd folding is special and typically pmd_* macros refer to upper
+ * level even when folded
+ */
void pmd_clear_bad(pmd_t *pmd)
{
pmd_ERROR(*pmd);
--
2.20.1
^ permalink raw reply related [flat|nested] 6+ messages in thread