Skip to contentSkip to conversation

ARM: mm: HugeTLB + THP support.

PATCH Superseded Steve Capper 3 participants 14 messages May 23, 2013 – Jun 4, 2013

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

v2 cover ARM: mm: HugeTLB + THP support.

The following patches bring both HugeTLB support and Transparent HugePage (THP) support to ARM.

Only long descriptors (LPAE) are supported in this series.

The code has been tested on an Arndale board (Exynos 5250).

This patch set is based on 3.10-rc2.

Major changes since the Patch:
* LPAE code has been separated from non-LPAE code (this series is the LPAE code).
* PROT_NONE support for HugeTLB and THP has been implemented.

Major changes since the RFC:
* huge pmd sharing removed from the 3-level code as this was found to be very rarely, if ever?, used. This allowed for some code simplification.

* hardware pmd bits for 2-levels of paging are now taken from mmu.c. Also the mapping code now uses pte/pmd bit helper functions rather than the custom pre-processor logic.

Cheers,

Signature · 30 lines
Steve

Catalin Marinas (2):
  ARM: mm: HugeTLB support for LPAE systems.
  ARM: mm: Transparent huge page support for LPAE systems.

Steve Capper (2):
  ARM: mm: correct pte_same behaviour for LPAE.
  ARM: mm: Add support for flushing HugeTLB pages.

 arch/arm/Kconfig                            |   8 +++
 arch/arm/include/asm/hugetlb-3level.h       |  71 +++++++++++++++++++
 arch/arm/include/asm/hugetlb.h              |  84 +++++++++++++++++++++++
 arch/arm/include/asm/pgtable-3level-hwdef.h |   4 ++
 arch/arm/include/asm/pgtable-3level.h       |  88 ++++++++++++++++++++++++
 arch/arm/include/asm/pgtable.h              |   3 +
 arch/arm/include/asm/tlb.h                  |   6 ++
 arch/arm/include/asm/tlbflush.h             |   2 +
 arch/arm/mm/Makefile                        |   1 +
 arch/arm/mm/dma-mapping.c                   |   2 +-
 arch/arm/mm/flush.c                         |  25 ++++---
 arch/arm/mm/fsr-3level.c                    |   4 +-
 arch/arm/mm/hugetlbpage.c                   | 101 ++++++++++++++++++++++++++++
 13 files changed, 386 insertions(+), 13 deletions(-)
 create mode 100644 arch/arm/include/asm/hugetlb-3level.h
 create mode 100644 arch/arm/include/asm/hugetlb.h
 create mode 100644 arch/arm/mm/hugetlbpage.c

-- 
1.8.1.4
#1 lore raw

PATCH v2 1/4 ARM: mm: correct pte_same behaviour for LPAE.

For 3 levels of paging the PTE_EXT_NG bit will be set for user address ptes that are written to a page table but not for ptes created with mk_pte.

This can cause some comparison tests made by pte_same to fail spuriously and lead to other problems.

To correct this behaviour, we mask off PTE_EXT_NG for any pte that is present before running the comparison.

---
 arch/arm/include/asm/pgtable-3level.h | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)
arch/arm/include/asm/pgtable-3level.h +17 -0
index 86b8fe3..70f041c 100644
@@ -166,6 +166,23 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 		clean_pmd_entry(pmdp);	\
 	} while (0)
 
+/*
+ * For 3 levels of paging the PTE_EXT_NG bit will be set for user address ptes
+ * that are written to a page table but not for ptes created with mk_pte.
+ *
+ * In hugetlb_no_page, a new huge pte (new_pte) is generated and passed to
+ * hugetlb_cow, where it is compared with an entry in a page table.
+ * This comparison test fails erroneously leading ultimately to a memory leak.
+ *
+ * To correct this behaviour, we mask off PTE_EXT_NG for any pte that is
+ * present before running the comparison.
+ */
+#define __HAVE_ARCH_PTE_SAME
+#define pte_same(pte_a,pte_b)	((pte_present(pte_a) ? pte_val(pte_a) & ~PTE_EXT_NG	\
+					: pte_val(pte_a))				\
+				== (pte_present(pte_b) ? pte_val(pte_b) & ~PTE_EXT_NG	\
+					: pte_val(pte_b)))
+
 #define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,__pte(pte_val(pte)|(ext)))
 
 #endif /* __ASSEMBLY__ */
Signature · 1 line
1.8.1.4
#2 lore raw

PATCH v2 1/4 ARM: mm: correct pte_same behaviour for LPAE.

Quoted 4 lines · Steve Capper

For 3 levels of paging the PTE_EXT_NG bit will be set for user address ptes that are written to a page table but not for ptes created with mk_pte.

Quoted 8 lines

This can cause some comparison tests made by pte_same to fail spuriously and lead to other problems.

To correct this behaviour, we mask off PTE_EXT_NG for any pte that is present before running the comparison.

#3 lore raw

PATCH v2 2/4 ARM: mm: Add support for flushing HugeTLB pages.

In reply to Steve Capper

On ARM we use the __flush_dcache_page function to flush the dcache of pages when needed; usually when the PG_dcache_clean bit is unset and we are setting a PTE.

A HugeTLB page is represented as a compound page consisting of an array of pages. Thus to flush the dcache of a HugeTLB page, one must flush more than a single page.

This patch modifies __flush_dcache_page such that all constituent pages of a HugeTLB page are flushed.

---
 arch/arm/mm/flush.c | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)
arch/arm/mm/flush.c +15 -10
index 0d473cc..3706407 100644
@@ -17,6 +17,7 @@
 #include <asm/highmem.h>
 #include <asm/smp_plat.h>
 #include <asm/tlbflush.h>
+#include <linux/hugetlb.h>
 
 #include "mm.h"
 
@@ -168,19 +169,23 @@ void __flush_dcache_page(struct address_space *mapping, struct page *page)
 	 * coherent with the kernels mapping.
 	 */
 	if (!PageHighMem(page)) {
-		__cpuc_flush_dcache_area(page_address(page), PAGE_SIZE);
+		size_t page_size = PAGE_SIZE << compound_order(page);
+		__cpuc_flush_dcache_area(page_address(page), page_size);
 	} else {
-		void *addr;
-
+		unsigned long i;
 		if (cache_is_vipt_nonaliasing()) {
-			addr = kmap_atomic(page);
-			__cpuc_flush_dcache_area(addr, PAGE_SIZE);
-			kunmap_atomic(addr);
-		} else {
-			addr = kmap_high_get(page);
-			if (addr) {
+			for (i = 0; i < (1 << compound_order(page)); i++) {
+				void *addr = kmap_atomic(page);
 				__cpuc_flush_dcache_area(addr, PAGE_SIZE);
-				kunmap_high(page);
+				kunmap_atomic(addr);
+			}
+		} else {
+			for (i = 0; i < (1 << compound_order(page)); i++) {
+				void *addr = kmap_high_get(page);
+				if (addr) {
+					__cpuc_flush_dcache_area(addr, PAGE_SIZE);
+					kunmap_high(page);
+				}
 			}
 		}
 	}
Signature · 1 line
1.8.1.4
#4 lore raw

PATCH v2 2/4 ARM: mm: Add support for flushing HugeTLB pages.

Quoted 8 lines · Steve Capper

On ARM we use the __flush_dcache_page function to flush the dcache of pages when needed; usually when the PG_dcache_clean bit is unset and we are setting a PTE.

A HugeTLB page is represented as a compound page consisting of an array of pages. Thus to flush the dcache of a HugeTLB page, one must flush more than a single page.

Quoted 5 lines

This patch modifies __flush_dcache_page such that all constituent pages of a HugeTLB page are flushed.

#5 lore raw

PATCH v2 3/4 ARM: mm: HugeTLB support for LPAE systems.

In reply to Steve Capper

From: Catalin Marinas <[email protected]>

This patch adds support for hugetlbfs based on the x86 implementation. It allows mapping of 2MB sections (see Documentation/vm/hugetlbpage.txt for usage). The 64K pages configuration is not supported (section size is 512MB in this case).

[steve.capper at linaro.org: symbolic constants replace numbers in places. Split up into multiple files, to simplify future non-LPAE support, removed huge_pmd_share code, as this is very rarely executed, Added PROT_NONE support].

---
 arch/arm/Kconfig                            |   4 ++
 arch/arm/include/asm/hugetlb-3level.h       |  71 +++++++++++++++++++
 arch/arm/include/asm/hugetlb.h              |  84 +++++++++++++++++++++++
 arch/arm/include/asm/pgtable-3level-hwdef.h |   2 +
 arch/arm/include/asm/pgtable-3level.h       |  11 +++
 arch/arm/mm/Makefile                        |   1 +
 arch/arm/mm/dma-mapping.c                   |   2 +-
 arch/arm/mm/fsr-3level.c                    |   2 +-
 arch/arm/mm/hugetlbpage.c                   | 101 ++++++++++++++++++++++++++++
 9 files changed, 276 insertions(+), 2 deletions(-)
 create mode 100644 arch/arm/include/asm/hugetlb-3level.h
 create mode 100644 arch/arm/include/asm/hugetlb.h
 create mode 100644 arch/arm/mm/hugetlbpage.c
arch/arm/Kconfig +4 -0
index 49d993c..860f034 100644
@@ -1707,6 +1707,10 @@ config HW_PERF_EVENTS
 	  Enable hardware performance counter support for perf events. If
 	  disabled, perf events will use software events only.
 
+config SYS_SUPPORTS_HUGETLBFS
+       def_bool y
+       depends on ARM_LPAE
+
 source "mm/Kconfig"
 
 config FORCE_MAX_ZONEORDER
arch/arm/include/asm/hugetlb-3level.h new file +71 -0

71 lines not on this page · raw message

arch/arm/include/asm/hugetlb.h new file +84 -0

84 lines not on this page · raw message

arch/arm/include/asm/pgtable-3level-hwdef.h +2 -0
index 18f5cef..42df407 100644
@@ -30,6 +30,7 @@
 #define PMD_TYPE_FAULT		(_AT(pmdval_t, 0) << 0)
 #define PMD_TYPE_TABLE		(_AT(pmdval_t, 3) << 0)
 #define PMD_TYPE_SECT		(_AT(pmdval_t, 1) << 0)
+#define PMD_TABLE_BIT		(_AT(pmdval_t, 1) << 1)
 #define PMD_BIT4		(_AT(pmdval_t, 0))
 #define PMD_DOMAIN(x)		(_AT(pmdval_t, 0))
 #define PMD_APTABLE_SHIFT	(61)
@@ -66,6 +67,7 @@
 #define PTE_TYPE_MASK		(_AT(pteval_t, 3) << 0)
 #define PTE_TYPE_FAULT		(_AT(pteval_t, 0) << 0)
 #define PTE_TYPE_PAGE		(_AT(pteval_t, 3) << 0)
+#define PTE_TABLE_BIT		(_AT(pteval_t, 1) << 1)
 #define PTE_BUFFERABLE		(_AT(pteval_t, 1) << 2)		/* AttrIndx[0] */
 #define PTE_CACHEABLE		(_AT(pteval_t, 1) << 3)		/* AttrIndx[1] */
 #define PTE_EXT_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */
arch/arm/include/asm/pgtable-3level.h +11 -0
index 70f041c..d1bcd82 100644
@@ -62,6 +62,14 @@
 #define USER_PTRS_PER_PGD	(PAGE_OFFSET / PGDIR_SIZE)
 
 /*
+ * Hugetlb definitions.
+ */
+#define HPAGE_SHIFT		PMD_SHIFT
+#define HPAGE_SIZE		(_AC(1, UL) << HPAGE_SHIFT)
+#define HPAGE_MASK		(~(HPAGE_SIZE - 1))
+#define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
+
+/*
  * "Linux" PTE definitions for LPAE.
  *
  * These bits overlap with the hardware bits but the naming is preserved for
@@ -185,6 +193,9 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 
 #define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,__pte(pte_val(pte)|(ext)))
 
+#define pte_huge(pte)		(pte_val(pte) && !(pte_val(pte) & PTE_TABLE_BIT))
+#define pte_mkhuge(pte)		(__pte(pte_val(pte) & ~PTE_TABLE_BIT))
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_PGTABLE_3LEVEL_H */
arch/arm/mm/Makefile +1 -0
index 9e51be9..224a9cc 100644
@@ -16,6 +16,7 @@ obj-$(CONFIG_MODULES)		+= proc-syms.o
 
 obj-$(CONFIG_ALIGNMENT_TRAP)	+= alignment.o
 obj-$(CONFIG_HIGHMEM)		+= highmem.o
+obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 
 obj-$(CONFIG_CPU_ABRT_NOMMU)	+= abort-nommu.o
 obj-$(CONFIG_CPU_ABRT_EV4)	+= abort-ev4.o
arch/arm/mm/dma-mapping.c +1 -1
index 7857f0b..38b78ef 100644
@@ -250,7 +250,7 @@ static void __dma_free_buffer(struct page *page, size_t size)
 
 #ifdef CONFIG_MMU
 #ifdef CONFIG_HUGETLB_PAGE
-#error ARM Coherent DMA allocator does not (yet) support huge TLB
+#warning ARM Coherent DMA allocator does not (yet) support huge TLB
 #endif
 
 static void *__alloc_from_contiguous(struct device *dev, size_t size,
arch/arm/mm/fsr-3level.c +1 -1
index 05a4e94..e115fc7 100644
@@ -13,7 +13,7 @@ static struct fsr_info fsr_info[] = {
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 access flag fault"	},
 	{ do_bad,		SIGBUS,  0,		"reserved permission fault"	},
 	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 1 permission fault"	},
-	{ do_sect_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 permission fault"	},
+	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 permission fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 permission fault"	},
 	{ do_bad,		SIGBUS,  0,		"synchronous external abort"	},
 	{ do_bad,		SIGBUS,  0,		"asynchronous external abort"	},
arch/arm/mm/hugetlbpage.c new file +101 -0

101 lines not on this page · raw message

Signature · 1 line
1.8.1.4
#6 lore raw

PATCH v2 3/4 ARM: mm: HugeTLB support for LPAE systems.

Quoted 3 lines · Steve Capper

From: Catalin Marinas <[email protected]>

This patch adds support for hugetlbfs based on the x86 implementation.

Can we not share the x86 code as you are proposing for arm64 already?

Signature · 1 line
Catalin
#7 lore raw

PATCH v2 3/4 ARM: mm: HugeTLB support for LPAE systems.

Quoted 7 lines · Catalin Marinas
Quoted 3 lines · Steve Capper

From: Catalin Marinas <[email protected]>

This patch adds support for hugetlbfs based on the x86 implementation.

Can we not share the x86 code as you are proposing for arm64 already?

Yes, we can. I didn't want one patch set dependent on another so opted to make the ARMv7 one self-contained for now. I was planning on changing this with a future patch.

Cheers,

Signature · 1 line
Steve
Quoted 2 lines
Signature · 1 line
Catalin
#8 lore raw

PATCH v2 4/4 ARM: mm: Transparent huge page support for LPAE systems.

In reply to Steve Capper

From: Catalin Marinas <[email protected]>

The patch adds support for THP (transparent huge pages) to LPAE systems. When this feature is enabled, the kernel tries to map anonymous pages as 2MB sections where possible.

[steve.capper at linaro.org: symbolic constants used, value of PMD_SECT_SPLITTING adjusted, tlbflush.h included in pgtable.h, added PROT_NONE support.]

---
 arch/arm/Kconfig                            |  4 ++
 arch/arm/include/asm/pgtable-3level-hwdef.h |  2 +
 arch/arm/include/asm/pgtable-3level.h       | 60 +++++++++++++++++++++++++++++
 arch/arm/include/asm/pgtable.h              |  3 ++
 arch/arm/include/asm/tlb.h                  |  6 +++
 arch/arm/include/asm/tlbflush.h             |  2 +
 arch/arm/mm/fsr-3level.c                    |  2 +-
 7 files changed, 78 insertions(+), 1 deletion(-)
arch/arm/Kconfig +4 -0
index 860f034..f07a462 100644
@@ -1711,6 +1711,10 @@ config SYS_SUPPORTS_HUGETLBFS
        def_bool y
        depends on ARM_LPAE
 
+config HAVE_ARCH_TRANSPARENT_HUGEPAGE
+       def_bool y
+       depends on ARM_LPAE
+
 source "mm/Kconfig"
 
 config FORCE_MAX_ZONEORDER
arch/arm/include/asm/pgtable-3level-hwdef.h +2 -0
index 42df407..f088c86 100644
@@ -42,6 +42,8 @@
  */
 #define PMD_SECT_BUFFERABLE	(_AT(pmdval_t, 1) << 2)
 #define PMD_SECT_CACHEABLE	(_AT(pmdval_t, 1) << 3)
+#define PMD_SECT_USER		(_AT(pmdval_t, 1) << 6)		/* AP[1] */
+#define PMD_SECT_RDONLY		(_AT(pmdval_t, 1) << 7)		/* AP[2] */
 #define PMD_SECT_S		(_AT(pmdval_t, 3) << 8)
 #define PMD_SECT_AF		(_AT(pmdval_t, 1) << 10)
 #define PMD_SECT_nG		(_AT(pmdval_t, 1) << 11)
arch/arm/include/asm/pgtable-3level.h +60 -0

72 lines not on this page · raw message

arch/arm/include/asm/pgtable.h +3 -0
index 9bcd262..eaedce7 100644
@@ -24,6 +24,9 @@
 #include <asm/memory.h>
 #include <asm/pgtable-hwdef.h>
 
+
+#include <asm/tlbflush.h>
+
 #ifdef CONFIG_ARM_LPAE
 #include <asm/pgtable-3level.h>
 #else
arch/arm/include/asm/tlb.h +6 -0
index 99a1951..bdc62da 100644
@@ -223,6 +223,12 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 #endif
 }
 
+static inline void
+tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
+{
+	tlb_add_flush(tlb, addr);
+}
+
 #define pte_free_tlb(tlb, ptep, addr)	__pte_free_tlb(tlb, ptep, addr)
 #define pmd_free_tlb(tlb, pmdp, addr)	__pmd_free_tlb(tlb, pmdp, addr)
 #define pud_free_tlb(tlb, pudp, addr)	pud_free((tlb)->mm, pudp)
arch/arm/include/asm/tlbflush.h +2 -0
index a3625d1..c374592 100644
@@ -535,6 +535,8 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 }
 #endif
 
+#define update_mmu_cache_pmd(vma, address, pmd) do { } while (0)
+
 #endif
 
 #endif /* CONFIG_MMU */
arch/arm/mm/fsr-3level.c +1 -1
index e115fc7..ab4409a 100644
@@ -9,7 +9,7 @@ static struct fsr_info fsr_info[] = {
 	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"level 3 translation fault"	},
 	{ do_bad,		SIGBUS,  0,		"reserved access flag fault"	},
 	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 1 access flag fault"	},
-	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 2 access flag fault"	},
+	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 access flag fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 access flag fault"	},
 	{ do_bad,		SIGBUS,  0,		"reserved permission fault"	},
 	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 1 permission fault"	},
Signature · 1 line
1.8.1.4
#9 lore raw

v2 cover ARM: mm: HugeTLB + THP support.

In reply to Steve Capper
Quoted 19 lines · Steve Capper

The following patches bring both HugeTLB support and Transparent HugePage (THP) support to ARM.

Only long descriptors (LPAE) are supported in this series.

The code has been tested on an Arndale board (Exynos 5250).

This patch set is based on 3.10-rc2.

Major changes since the Patch:
* LPAE code has been separated from non-LPAE code (this series is the LPAE code).
* PROT_NONE support for HugeTLB and THP has been implemented.

Major changes since the RFC:
* huge pmd sharing removed from the 3-level code as this was found to be very rarely, if ever?, used. This allowed for some code simplification.

Quoted 8 lines

* hardware pmd bits for 2-levels of paging are now taken from mmu.c. Also the mapping code now uses pte/pmd bit helper functions rather than the custom pre-processor logic.

Cheers,

Signature · 1 line
Steve

Hello,
I was wondering if anyone had any further comments on this series?

Russell,
Are you happy for these to go into your patch system, or should anything be changed?

Thanks,

Signature · 1 line
Steve 
#10 lore raw

v2 cover ARM: mm: HugeTLB + THP support.

Quoted 29 lines · Steve Capper
Quoted 19 lines · Steve Capper

The following patches bring both HugeTLB support and Transparent HugePage (THP) support to ARM.

Only long descriptors (LPAE) are supported in this series.

The code has been tested on an Arndale board (Exynos 5250).

This patch set is based on 3.10-rc2.

Major changes since the Patch:
* LPAE code has been separated from non-LPAE code (this series is the LPAE code).
* PROT_NONE support for HugeTLB and THP has been implemented.

Major changes since the RFC:
* huge pmd sharing removed from the 3-level code as this was found to be very rarely, if ever?, used. This allowed for some code simplification.

Quoted 8 lines

* hardware pmd bits for 2-levels of paging are now taken from mmu.c. Also the mapping code now uses pte/pmd bit helper functions rather than the custom pre-processor logic.

Cheers,

Signature · 1 line
Steve
Quoted 10 lines

Hello,
I was wondering if anyone had any further comments on this series?

Russell,
Are you happy for these to go into your patch system, or should anything be changed?

Thanks,

Signature · 1 line
Steve 

Just a polite ping on the above.

Are people happy to have this patch set merged?

Thanks,

Signature · 1 line
Steve
#11 lore raw

v2 cover ARM: mm: HugeTLB + THP support.

Quoted 37 lines · Steve Capper
Quoted 36 lines · Steve Capper
Quoted 19 lines · Steve Capper

The following patches bring both HugeTLB support and Transparent HugePage (THP) support to ARM.

Only long descriptors (LPAE) are supported in this series.

The code has been tested on an Arndale board (Exynos 5250).

This patch set is based on 3.10-rc2.

Major changes since the Patch:
* LPAE code has been separated from non-LPAE code (this series is the LPAE code).
* PROT_NONE support for HugeTLB and THP has been implemented.

Major changes since the RFC:
* huge pmd sharing removed from the 3-level code as this was found to be very rarely, if ever?, used. This allowed for some code simplification.

Quoted 8 lines

* hardware pmd bits for 2-levels of paging are now taken from mmu.c. Also the mapping code now uses pte/pmd bit helper functions rather than the custom pre-processor logic.

Cheers,

Signature · 1 line
Steve

Hello,
I was wondering if anyone had any further comments on this series?

Russell,
Are you happy for these to go into your patch system, or should anything be changed?

Quoted 7 lines
Quoted 3 lines

Thanks,

Signature · 1 line
Steve 

Just a polite ping on the above.

Are people happy to have this patch set merged?

Looks good to me, but worth checking that it doesn't conflict with the LPAE fixes I plan to send for 3.11 (since they're not terribly critical):

https://git.kernel.org/cgit/linux/kernel/git/will/linux.git/log/?h=for-rmk/lpae

Of course, I can fix things up in my branch if necessary (just send me a pointer to your git repo).

Cheers,

Will

#12 lore raw

v2 cover ARM: mm: HugeTLB + THP support.

Quoted 30 lines · Will Deacon
Quoted 29 lines · Steve Capper
Quoted 28 lines · Steve Capper
Quoted 27 lines · Steve Capper

The following patches bring both HugeTLB support and Transparent HugePage (THP) support to ARM.

Only long descriptors (LPAE) are supported in this series.

The code has been tested on an Arndale board (Exynos 5250).

This patch set is based on 3.10-rc2.

Major changes since the Patch:
* LPAE code has been separated from non-LPAE code (this series is the LPAE code).
* PROT_NONE support for HugeTLB and THP has been implemented.

Major changes since the RFC:
* huge pmd sharing removed from the 3-level code as this was found to be very rarely, if ever?, used. This allowed for some code simplification.

* hardware pmd bits for 2-levels of paging are now taken from mmu.c. Also the mapping code now uses pte/pmd bit helper functions rather than the custom pre-processor logic.

Cheers,

Signature · 1 line
Steve

[ ... ]

Quoted 5 lines
Quoted 4 lines

Just a polite ping on the above.

Are people happy to have this patch set merged?

Quoted 7 lines

Looks good to me, but worth checking that it doesn't conflict with the LPAE fixes I plan to send for 3.11 (since they're not terribly critical):

https://git.kernel.org/cgit/linux/kernel/git/will/linux.git/log/?h=for-rmk/lpae

Of course, I can fix things up in my branch if necessary (just send me a pointer to your git repo).

Thanks, I'll take a look at the above now.

For reference these patches can be found at:
git://git.linaro.org/people/stevecapper/linux.git arm-hugepages-20130523

Cheers,

Signature · 1 line
Steve
#13 lore raw

v2 cover ARM: mm: HugeTLB + THP support.

In reply to Will Deacon
Quoted 31 lines · Will Deacon
Quoted 30 lines · Steve Capper
Quoted 29 lines · Steve Capper
Quoted 27 lines · Steve Capper

The following patches bring both HugeTLB support and Transparent HugePage (THP) support to ARM.

Only long descriptors (LPAE) are supported in this series.

The code has been tested on an Arndale board (Exynos 5250).

This patch set is based on 3.10-rc2.

Major changes since the Patch:
* LPAE code has been separated from non-LPAE code (this series is the LPAE code).
* PROT_NONE support for HugeTLB and THP has been implemented.

Major changes since the RFC:
* huge pmd sharing removed from the 3-level code as this was found to be very rarely, if ever?, used. This allowed for some code simplification.

* hardware pmd bits for 2-levels of paging are now taken from mmu.c. Also the mapping code now uses pte/pmd bit helper functions rather than the custom pre-processor logic.

Cheers,

Signature · 1 line
Steve

[ ... ]

Quoted 5 lines
Quoted 4 lines

Just a polite ping on the above.

Are people happy to have this patch set merged?

Quoted 7 lines

Looks good to me, but worth checking that it doesn't conflict with the LPAE fixes I plan to send for 3.11 (since they're not terribly critical):

https://git.kernel.org/cgit/linux/kernel/git/will/linux.git/log/?h=for-rmk/lpae

Of course, I can fix things up in my branch if necessary (just send me a pointer to your git repo).

Hey Will,
I've rebased the series against to 3.10-rc4, and merged in your for-rmk/lpae branch.

It builds, and I've run my way through the libhugetlbfs unit tests successfully on a Versatile Express (TC2 tile). I get THP collapses, splits and allocs too when I rebuild the test suite.

It looks good to me so far.

Thanks,

Signature · 1 line
Steve