THP support for PPC64
Subsystems (10)
cover THP support for PPC64
Hi,
This is an early RFC version adding transparent huge page support for PPC64. I am sharing the changes, so that we can have early review on the approach taken. The TODOs include
*) Compile issues with different config option
*) HugeTLBfs is disabled now (mostly compile issues)
*) PPC32 and other sub architecture details need to be worked out. *) 4K page size details need to be worked out
*) Closer review of PMD* flags.
Some numbers:
The latency measurements code from Anton found at
http://ozlabs.org/~anton/junkcode/latency2001.c
THP disabled 64K page size
------------------------
[root@llmp24l02 ~]# ./latency2001 8G
8589934592 731.73 cycles 205.77 ns
[root@llmp24l02 ~]# ./latency2001 8G
8589934592 743.39 cycles 209.05 ns
[root@llmp24l02 ~]#
THP disabled large page via hugetlbfs
-------------------------------------
[root@llmp24l02 ~]# ./latency2001 -l 8G
8589934592 416.09 cycles 117.01 ns
[root@llmp24l02 ~]# ./latency2001 -l 8G
8589934592 415.74 cycles 116.91 ns
THP enabled 64K page size.
----------------
[root@llmp24l02 ~]# ./latency2001 8G
8589934592 405.07 cycles 113.91 ns
[root@llmp24l02 ~]# ./latency2001 8G
8589934592 411.82 cycles 115.81 ns
[root@llmp24l02 ~]#
We are close to hugetlbfs in latency and we can achieve this with zero config/page reservation. Most of the allocations above are fault allocated. I haven't really measured the collapse alloc impact.
Another test that does 50000000 random access over 1GB area goes from 2.65 seconds to 1.07 seconds with this patchset.
Thanks,
-aneesh
RFC PATCH 1/17 powerpc: Don't hard code the size of pte page
From: "Aneesh Kumar K.V" <[email protected]>
USE PTRS_PER_PTE to indicate the size of pte page.
--- arch/powerpc/include/asm/pgtable.h | 6 ++++++ arch/powerpc/mm/hash_low_64.S | 4 ++-- 2 files changed, 8 insertions(+), 2 deletions(-)
arch/powerpc/include/asm/pgtable.h +6 -0
@@ -17,6 +17,12 @@ struct mm_struct;# include <asm/pgtable-ppc32.h> #endif +/* +* hidx is in the second half of the page table. We use the +* 8 bytes per each pte entry. +*/ +#define PTE_PAGE_HIDX_OFFSET (PTRS_PER_PTE * 8) +#ifndef __ASSEMBLY__#include <asm/tlbflush.h>
arch/powerpc/mm/hash_low_64.S +2 -2
@@ -490,7 +490,7 @@ END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE) beq htab_inval_old_hpte ld r6,STK_PARAM(R6)(r1) - ori r26,r6,0x8000 /* Load the hidx mask */ + ori r26,r6,PTE_PAGE_HIDX_OFFSET /* Load the hidx mask. */ ld r26,0(r26) addi r5,r25,36 /* Check actual HPTE_SUB bit, this */ rldcr. r0,r31,r5,0 /* must match pgtable.h definition */
@@ -607,7 +607,7 @@ htab_pte_insert_ok: sld r4,r4,r5 andc r26,r26,r4 or r26,r26,r3 - ori r5,r6,0x8000 + ori r5,r6,PTE_PAGE_HIDX_OFFSET std r26,0(r5) lwsync std r30,0(r6)
Signature · 1 line
1.7.10
RFC PATCH 2/17 arch/powerpc: Reduce the PTE_INDEX_SIZE
In reply to Aneesh Kumar K.VFrom: "Aneesh Kumar K.V" <[email protected]>
This make one PMD cover 16MB range. That helps in easier implementation of THP on power. THP core code make use of one pmd entry to track the huge page and the range mapped by a single pmd entry should be equal to the huge page size supported by the hardware.
--- arch/powerpc/include/asm/pgtable-ppc64-64k.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
arch/powerpc/include/asm/pgtable-ppc64-64k.h +2 -2
@@ -4,10 +4,10 @@#include <asm-generic/pgtable-nopud.h> -#define PTE_INDEX_SIZE 12 +#define PTE_INDEX_SIZE 8#define PMD_INDEX_SIZE 12#define PUD_INDEX_SIZE 0 -#define PGD_INDEX_SIZE 6 +#define PGD_INDEX_SIZE 10#ifndef __ASSEMBLY__#define PTE_TABLE_SIZE (sizeof(real_pte_t) << PTE_INDEX_SIZE)
Signature · 1 line
1.7.10
RFC PATCH 3/17 powerpc: Reduce PTE table memory wastage
In reply to Aneesh Kumar K.VFrom: "Aneesh Kumar K.V" <[email protected]>
We now have PTE page consuming only 2K of the 64K page.This is in order to facilitate transparent huge page support, which works much better if our PMDs cover 16MB instead of 256MB.
Inorder to reduce the wastage, we now have multiple PTE page fragment from the same PTE page.
--- arch/powerpc/include/asm/mmu-book3e.h | 4 + arch/powerpc/include/asm/mmu-hash64.h | 4 + arch/powerpc/include/asm/page.h | 4 + arch/powerpc/include/asm/pgalloc-32.h | 45 ++++++++ arch/powerpc/include/asm/pgalloc-64.h | 143 ++++++++++++++++++++----- arch/powerpc/include/asm/pgalloc.h | 46 +------- arch/powerpc/kernel/setup_64.c | 4 +- arch/powerpc/mm/mmu_context_hash64.c | 12 +++ arch/powerpc/mm/pgtable_64.c | 189 +++++++++++++++++++++++++++++++++ 9 files changed, 377 insertions(+), 74 deletions(-)
arch/powerpc/include/asm/mmu-book3e.h +4 -0
@@ -231,6 +231,10 @@ typedef struct {u64 high_slices_psize;/* 4 bits per slice for now */ u16 user_psize;/* page size index */ #endif +#ifdef CONFIG_PPC_64K_PAGES +/* for 2K page table support */ +struct list_head pgtable_list; +#endif } mm_context_t;/* Page size definitions, common between 32 and 64-bit
arch/powerpc/include/asm/mmu-hash64.h +4 -0
@@ -498,6 +498,10 @@ typedef struct {unsigned long acop;/* mask of enabled coprocessor types */ unsigned int cop_pid;/* pid value used with coprocessors */ #endif /* CONFIG_PPC_ICSWX */ +#ifdef CONFIG_PPC_64K_PAGES +/* for 2K page table support */ +struct list_head pgtable_list; +#endif } mm_context_t;
arch/powerpc/include/asm/page.h +4 -0
@@ -378,7 +378,11 @@ void arch_free_page(struct page *page, int order);struct vm_area_struct ; +#ifdef CONFIG_PPC_64K_PAGES +typedef pte_t *pgtable_t ; +#else typedef struct page *pgtable_t ; +#endif #include <asm-generic/memory_model.h> #endif /* __ASSEMBLY__ */
arch/powerpc/include/asm/pgalloc-32.h +45 -0
55 lines not on this page · raw message
arch/powerpc/include/asm/pgalloc-64.h +115 -28
175 lines not on this page · raw message
arch/powerpc/include/asm/pgalloc.h +1 -45
63 lines not on this page · raw message
arch/powerpc/kernel/setup_64.c +3 -1
@@ -575,7 +575,9 @@ void __init setup_arch(char **cmdline_p) init_mm.end_code = (unsigned long ) _etext; init_mm.end_data = (unsigned long ) _edata; init_mm.brk = klimit; - +#ifdef CONFIG_PPC_64K_PAGES +INIT_LIST_HEAD (&init_mm.context.pgtable_list); +#endif irqstack_early_init ();exc_lvl_early_init ();emergency_stack_init ();
arch/powerpc/mm/mmu_context_hash64.c +12 -0
@@ -86,6 +86,8 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)spin_lock_init (mm->context.cop_lockp);#endif /* CONFIG_PPC_ICSWX */ +INIT_LIST_HEAD (&mm->context.pgtable_list); +return 0 ; }
@@ -99,11 +101,21 @@ EXPORT_SYMBOL_GPL(__destroy_context);void destroy_context (struct mm_struct *mm) { +struct page *page; +struct list_head *item, *tmp; +#ifdef CONFIG_PPC_ICSWX drop_cop (mm->context.acop, mm);kfree (mm->context.cop_lockp); mm->context.cop_lockp =NULL ;#endif /* CONFIG_PPC_ICSWX */ +list_for_each_safe (item, tmp, &mm->context.pgtable_list) { + page = list_entry(item, struct page, lru); +list_del (&page->lru); +pgtable_page_dtor (page); +atomic_set (&page->_mapcount,-1 ); +__free_page (page); + }__destroy_context (mm->context.id);subpage_prot_free (mm); mm->context.id =MMU_NO_CONTEXT ;
arch/powerpc/mm/pgtable_64.c +189 -0
198 lines not on this page · raw message
Signature · 1 line
1.7.10
RFC PATCH 4/17 mm/THP: Add pmd args to pgtable deposit and withdraw APIs
In reply to Aneesh Kumar K.VFrom: "Aneesh Kumar K.V" <[email protected]>
This will be later used by powerpc THP support. In powerpc we want to use pgtable for storing the hash index values. So instead of adding them to mm_context list, we would like to store them in the second half of pmd
--- arch/s390/include/asm/pgtable.h | 5 +++-- arch/s390/mm/pgtable.c | 5 +++-- arch/sparc/include/asm/pgtable_64.h | 5 +++-- arch/sparc/mm/tlb.c | 5 +++-- include/asm-generic/pgtable.h | 5 +++-- mm/huge_memory.c | 12 ++++++------ mm/pgtable-generic.c | 5 +++-- 7 files changed, 24 insertions(+), 18 deletions(-)
arch/s390/include/asm/pgtable.h +3 -2
@@ -1232,10 +1232,11 @@ static inline void __pmd_idte(unsigned long address, pmd_t *pmdp)#define SEGMENT_RW __pgprot(_HPAGE_TYPE_RW)#define __HAVE_ARCH_PGTABLE_DEPOSIT -extern void pgtable_trans_huge_deposit (struct mm_struct *mm,pgtable_t pgtable); +extern void pgtable_trans_huge_deposit (struct mm_struct *mm,pmd_t *pmdp, +pgtable_t pgtable);#define __HAVE_ARCH_PGTABLE_WITHDRAW -extern pgtable_t pgtable_trans_huge_withdraw (struct mm_struct *mm); +extern pgtable_t pgtable_trans_huge_withdraw (struct mm_struct *mm,pmd_t *pmdp);static inline int pmd_trans_splitting (pmd_t pmd) {
arch/s390/mm/pgtable.c +3 -2
@@ -920,7 +920,8 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, } } -void pgtable_trans_huge_deposit (struct mm_struct *mm,pgtable_t pgtable) +void pgtable_trans_huge_deposit (struct mm_struct *mm,pmd_t *pmdp, +pgtable_t pgtable) {struct list_head *lh = (struct list_head *) pgtable;
@@ -934,7 +935,7 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable) mm->pmd_huge_pte = pgtable; } -pgtable_t pgtable_trans_huge_withdraw (struct mm_struct *mm) +pgtable_t pgtable_trans_huge_withdraw (struct mm_struct *mm,pmd_t *pmdp) {struct list_head *lh;pgtable_t pgtable;
arch/sparc/include/asm/pgtable_64.h +3 -2
@@ -855,10 +855,11 @@ extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd);#define __HAVE_ARCH_PGTABLE_DEPOSIT -extern void pgtable_trans_huge_deposit (struct mm_struct *mm,pgtable_t pgtable); +extern void pgtable_trans_huge_deposit (struct mm_struct *mm,pmd_t *pmdp, +pgtable_t pgtable);#define __HAVE_ARCH_PGTABLE_WITHDRAW -extern pgtable_t pgtable_trans_huge_withdraw (struct mm_struct *mm); +extern pgtable_t pgtable_trans_huge_withdraw (struct mm_struct *mm,pmd_t *pmdp);#endif /* Encode and de-code a swap entry */
arch/sparc/mm/tlb.c +3 -2
@@ -150,7 +150,8 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, } } -void pgtable_trans_huge_deposit (struct mm_struct *mm,pgtable_t pgtable) +void pgtable_trans_huge_deposit (struct mm_struct *mm,pmd_t *pmdp, +pgtable_t pgtable) {struct list_head *lh = (struct list_head *) pgtable;
@@ -164,7 +165,7 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable) mm->pmd_huge_pte = pgtable; } -pgtable_t pgtable_trans_huge_withdraw (struct mm_struct *mm) +pgtable_t pgtable_trans_huge_withdraw (struct mm_struct *mm,pmd_t *pmdp) {struct list_head *lh;pgtable_t pgtable;
include/asm-generic/pgtable.h +3 -2
@@ -163,11 +163,12 @@ extern void pmdp_splitting_flush(struct vm_area_struct *vma,#endif #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT -extern void pgtable_trans_huge_deposit (struct mm_struct *mm,pgtable_t pgtable); +extern void pgtable_trans_huge_deposit (struct mm_struct *mm,pmd_t *pmdp, +pgtable_t pgtable);#endif #ifndef __HAVE_ARCH_PGTABLE_WITHDRAW -extern pgtable_t pgtable_trans_huge_withdraw (struct mm_struct *mm); +extern pgtable_t pgtable_trans_huge_withdraw (struct mm_struct *mm,pmd_t *pmdp);#endif #ifndef __HAVE_ARCH_PMDP_INVALIDATE
mm/huge_memory.c +6 -6
@@ -739,7 +739,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,*/ page_add_new_anon_rmap (page, vma, haddr);set_pmd_at (mm, haddr, pmd, entry); -pgtable_trans_huge_deposit (mm, pgtable); +pgtable_trans_huge_deposit (mm, pmd, pgtable);add_mm_counter (mm,MM_ANONPAGES ,HPAGE_PMD_NR ); mm->nr_ptes++;spin_unlock (&mm->page_table_lock);
@@ -926,7 +926,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,pmdp_set_wrprotect (src_mm, addr, src_pmd); pmd =pmd_mkold (pmd_wrprotect (pmd));set_pmd_at (dst_mm, addr, dst_pmd, pmd); -pgtable_trans_huge_deposit (dst_mm, pgtable); +pgtable_trans_huge_deposit (dst_mm, dst_pmd, pgtable); dst_mm->nr_ptes++; ret =0 ;
@@ -1091,10 +1091,10 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, goto out_free_pages;VM_BUG_ON (!PageHead (page)); + pgtable =pgtable_trans_huge_withdraw (mm, pmd);pmdp_clear_flush (vma, haddr, pmd);/* leave pmd empty until pte is filled */ - pgtable =pgtable_trans_huge_withdraw (mm);pmd_populate (mm, &_pmd, pgtable);for (i =0 ; i <HPAGE_PMD_NR ; i++, haddr +=PAGE_SIZE ) {
@@ -1373,7 +1373,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,struct page *page;pgtable_t pgtable;pmd_t orig_pmd; - pgtable =pgtable_trans_huge_withdraw (tlb->mm); + pgtable =pgtable_trans_huge_withdraw (tlb->mm, pmd); orig_pmd =pmdp_get_and_clear (tlb->mm, addr, pmd);tlb_remove_pmd_tlb_entry (tlb, pmd, addr);if (is_huge_zero_pmd (orig_pmd)) {
@@ -1705,7 +1705,7 @@ static int __split_huge_page_map(struct page *page, pmd =page_check_address_pmd (page, mm, address,PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG );if (pmd) { - pgtable =pgtable_trans_huge_withdraw (mm); + pgtable =pgtable_trans_huge_withdraw (mm, pmd);pmd_populate (mm, &_pmd, pgtable); haddr = address;
@@ -2393,7 +2393,7 @@ static void collapse_huge_page(struct mm_struct *mm,page_add_new_anon_rmap (new_page, vma, address);set_pmd_at (mm, address, pmd, _pmd);update_mmu_cache_pmd (vma, address, pmd); -pgtable_trans_huge_deposit (mm, pgtable); +pgtable_trans_huge_deposit (mm, pmd, pgtable);spin_unlock (&mm->page_table_lock); *hpage =NULL ;
mm/pgtable-generic.c +3 -2
@@ -124,7 +124,8 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT #ifdef CONFIG_TRANSPARENT_HUGEPAGE -void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable) +void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pgtable) { assert_spin_locked(&mm->page_table_lock);
@@ -141,7 +142,7 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable) #ifndef __HAVE_ARCH_PGTABLE_WITHDRAW #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* no "address" argument so destroys page coloring of some arch */ -pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm) +pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) { pgtable_t pgtable;
Signature · 1 line
1.7.10
RFC PATCH 5/17 powerpc: Add size argument to pgtable_cache_add
In reply to Aneesh Kumar K.VFrom: "Aneesh Kumar K.V" <[email protected]>
We will use this later with THP changes. With THP we want to create PMD with twice the size. The second half will be used to depoist pgtable, which will carry the hpte hash index value
--- arch/powerpc/include/asm/pgtable-ppc64.h | 7 ++++++- arch/powerpc/mm/init_64.c | 16 ++++++++-------- 2 files changed, 14 insertions(+), 9 deletions(-)
arch/powerpc/include/asm/pgtable-ppc64.h +6 -1
@@ -338,8 +338,13 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)#define pgoff_to_pte (off) ((pte_t) {((off) << PTE_RPN_SHIFT)|_PAGE_FILE})#define PTE_FILE_MAX_BITS (BITS_PER_LONG - PTE_RPN_SHIFT) -void pgtable_cache_add (unsigned shift,void (*ctor)(void *)); +extern void __pgtable_cache_add (unsigned index,unsigned long table_size, +void (*ctor)(void *));void pgtable_cache_init (void ); +static inline void pgtable_cache_add (unsigned shift,void (*ctor)(void *)) +{ +return __pgtable_cache_add (shift,sizeof (void *) << shift, ctor); +}/* * find_linux_pte returns the address of a linux pte for a given
arch/powerpc/mm/init_64.c +8 -8
@@ -100,10 +100,10 @@ struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE];* everything else. Caches created by this function are used for all * the higher level pagetables, and for hugepage pagetables. */ -void pgtable_cache_add (unsigned shift,void (*ctor)(void *)) +void __pgtable_cache_add (unsigned int index,unsigned long table_size, +void (*ctor)(void *)) {char *name; -unsigned long table_size =sizeof (void *) << shift;unsigned long align = table_size;/* When batching pgtable pointers for RCU freeing, we store
@@ -111,7 +111,7 @@ void pgtable_cache_add(unsigned shift, void (*ctor)(void *))* big enough to fit it. * * Likewise, hugeapge pagetable pointers contain a (different) -* shift value in the low bits. All tables must be aligned so +* huge page size in the low bits. All tables must be aligned so * as to leave enough 0 bits in the address to contain it. */ unsigned long minalign =max (MAX_PGTABLE_INDEX_SIZE +1 ,HUGEPD_SHIFT_MASK +1 );
@@ -121,17 +121,17 @@ void pgtable_cache_add(unsigned shift, void (*ctor)(void *))* moment, gcc doesn't seem to recognize is_power_of_2 as a * constant expression, so so much for that. */ BUG_ON (!is_power_of_2 (minalign)); -BUG_ON ((shift <1 ) || (shift >MAX_PGTABLE_INDEX_SIZE )); +BUG_ON ((index <1 ) || (index >MAX_PGTABLE_INDEX_SIZE )); -if (PGT_CACHE (shift)) +if (PGT_CACHE (index))return ;/* Already have a cache of this size */ align = max_t(unsigned long, align, minalign); - name =kasprintf (GFP_KERNEL ,"pgtable-2^%d" , shift); + name =kasprintf (GFP_KERNEL ,"pgtable-2^%d" , index); new =kmem_cache_create (name, table_size, align,0 , ctor); -PGT_CACHE (shift) = new; +PGT_CACHE (index) = new; -pr_debug ("Allocated pgtable cache for order %d\n" , shift); +pr_debug ("Allocated pgtable cache for order %d\n" , index); }
Signature · 1 line
1.7.10
RFC PATCH 6/17 powerpc/mm: Decode the pte-lp-encoding bits correctly.
In reply to Aneesh Kumar K.VFrom: "Aneesh Kumar K.V" <[email protected]>
We look at both the segment base page size and actual page size and store the pte-lp-encodings in an array per base page size.
--- arch/powerpc/include/asm/machdep.h | 3 +- arch/powerpc/include/asm/mmu-hash64.h | 12 ++-- arch/powerpc/mm/hash_low_64.S | 18 ++++-- arch/powerpc/mm/hash_native_64.c | 105 ++++++++++++++++++++++++--------- arch/powerpc/mm/hash_utils_64.c | 103 +++++++++++++++++++------------- arch/powerpc/platforms/pseries/lpar.c | 4 +- 6 files changed, 163 insertions(+), 82 deletions(-)
arch/powerpc/include/asm/machdep.h +2 -1
@@ -50,7 +50,8 @@ struct machdep_calls {unsigned long prpn, unsigned long rflags, unsigned long vflags, - int psize, int ssize); + int psize, int apsize, + int ssize);long (*hpte_remove)(unsigned long hpte_group);void (*hpte_removebolted)(unsigned long ea,int psize,int ssize);
arch/powerpc/include/asm/mmu-hash64.h +7 -5
@@ -154,7 +154,7 @@ extern unsigned long htab_hash_mask;struct mmu_psize_def {unsigned int shift;/* number of bits */ -unsigned int penc;/* HPTE encoding */ +unsigned int penc[MMU_PAGE_COUNT ];/* HPTE encoding */ unsigned int tlbiel;/* tlbiel supported for that page size */ unsigned long avpnm;/* bits to mask out in AVPN in the HPTE */ unsigned long sllp;/* SLB L||LP (exact mask to use in slbmte) */
@@ -254,16 +254,18 @@ static inline unsigned long hpte_encode_v(unsigned long vpn,* for the page size. We assume the pa is already "clean" that is properly * aligned for the requested page size */ -static inline unsigned long hpte_encode_r (unsigned long pa,int psize) +static inline unsigned long hpte_encode_r (unsigned long pa,int base_psize, +int actual_psize) {unsigned long r;/* A 4K page needs no special encoding */ -if (psize ==MMU_PAGE_4K ) +if (actual_psize ==MMU_PAGE_4K )return pa &HPTE_R_RPN ;else { -unsigned int penc = mmu_psize_defs[psize].penc; -unsigned int shift = mmu_psize_defs[psize].shift; +unsigned int penc = mmu_psize_defs[base_psize].penc[actual_psize]; +unsigned int shift = mmu_psize_defs[actual_psize].shift; +/* FIXME!! replace 12 by LP_SHIFT ? */ return (pa & ~((1ul << shift) -1 )) | (penc <<12 ); }return r;
arch/powerpc/mm/hash_low_64.S +12 -6
@@ -196,7 +196,8 @@ htab_insert_pte: mr r4,r29 /* Retrieve vpn */ li r7,0 /* !bolted, !secondary */ li r8,MMU_PAGE_4K /* page size */ - ld r9,STK_PARAM(R9)(r1) /* segment size */ + li r9,MMU_PAGE_4K /* actual page size */ + ld r10,STK_PARAM(R9)(r1) /* segment size */ _GLOBAL(htab_call_hpte_insert1) bl . /* Patched by htab_finish_init() */ cmpdi 0,r3,0
@@ -219,7 +220,8 @@ _GLOBAL(htab_call_hpte_insert1) mr r4,r29 /* Retrieve vpn */ li r7,HPTE_V_SECONDARY /* !bolted, secondary */ li r8,MMU_PAGE_4K /* page size */ - ld r9,STK_PARAM(R9)(r1) /* segment size */ + li r9,MMU_PAGE_4K /* actual page size */ + ld r10,STK_PARAM(R9)(r1) /* segment size */ _GLOBAL(htab_call_hpte_insert2) bl . /* Patched by htab_finish_init() */ cmpdi 0,r3,0
@@ -515,7 +517,8 @@ htab_special_pfn: mr r4,r29 /* Retrieve vpn */ li r7,0 /* !bolted, !secondary */ li r8,MMU_PAGE_4K /* page size */ - ld r9,STK_PARAM(R9)(r1) /* segment size */ + li r9,MMU_PAGE_4K /* actual page size */ + ld r10,STK_PARAM(R9)(r1) /* segment size */ _GLOBAL(htab_call_hpte_insert1) bl . /* patched by htab_finish_init() */ cmpdi 0,r3,0
@@ -542,7 +545,8 @@ _GLOBAL(htab_call_hpte_insert1) mr r4,r29 /* Retrieve vpn */ li r7,HPTE_V_SECONDARY /* !bolted, secondary */ li r8,MMU_PAGE_4K /* page size */ - ld r9,STK_PARAM(R9)(r1) /* segment size */ + li r9,MMU_PAGE_4K /* actual page size */ + ld r10,STK_PARAM(R9)(r1) /* segment size */ _GLOBAL(htab_call_hpte_insert2) bl . /* patched by htab_finish_init() */ cmpdi 0,r3,0
@@ -840,7 +844,8 @@ ht64_insert_pte: mr r4,r29 /* Retrieve vpn */ li r7,0 /* !bolted, !secondary */ li r8,MMU_PAGE_64K - ld r9,STK_PARAM(R9)(r1) /* segment size */ + li r9,MMU_PAGE_64K /* actual page size */ + ld r10,STK_PARAM(R9)(r1) /* segment size */ _GLOBAL(ht64_call_hpte_insert1) bl . /* patched by htab_finish_init() */ cmpdi 0,r3,0
@@ -863,7 +868,8 @@ _GLOBAL(ht64_call_hpte_insert1) mr r4,r29 /* Retrieve vpn */ li r7,HPTE_V_SECONDARY /* !bolted, secondary */ li r8,MMU_PAGE_64K - ld r9,STK_PARAM(R9)(r1) /* segment size */ + li r9,MMU_PAGE_64K /* actual page size */ + ld r10,STK_PARAM(R9)(r1) /* segment size */ _GLOBAL(ht64_call_hpte_insert2) bl . /* patched by htab_finish_init() */ cmpdi 0,r3,0
arch/powerpc/mm/hash_native_64.c +78 -27
274 lines not on this page · raw message
arch/powerpc/mm/hash_utils_64.c +62 -41
156 lines not on this page · raw message
arch/powerpc/platforms/pseries/lpar.c +2 -2
@@ -109,7 +109,7 @@ void vpa_init(int cpu)static long pSeries_lpar_hpte_insert (unsigned long hpte_group,unsigned long vpn,unsigned long pa,unsigned long rflags,unsigned long vflags, -int psize,int ssize) +int psize,int apsize,int ssize) {unsigned long lpar_rc;unsigned long flags;
@@ -122,7 +122,7 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group, hpte_group, vpn, pa, rflags, vflags, psize); hpte_v =hpte_encode_v (vpn, psize, ssize) | vflags |HPTE_V_VALID ; - hpte_r =hpte_encode_r (pa, psize) | rflags; + hpte_r =hpte_encode_r (pa, psize, apsize) | rflags;if (!(vflags &HPTE_V_BOLTED ))pr_devel (" hpte_v=%016lx, hpte_r=%016lx\n" , hpte_v, hpte_r);
Signature · 1 line
1.7.10
RFC PATCH 7/17 powerpc: Update tlbie/tlbiel as per ISA doc
In reply to Aneesh Kumar K.VFrom: "Aneesh Kumar K.V" <[email protected]>
This make sure we handle Multiple page size segment correctly.
--- arch/powerpc/mm/hash_native_64.c | 52 +++++++++++++++++++++++++++++--------- 1 file changed, 40 insertions(+), 12 deletions(-)
arch/powerpc/mm/hash_native_64.c +40 -12
@@ -43,7 +43,7 @@DEFINE_RAW_SPINLOCK (native_tlbie_lock); -static inline void __tlbie (unsigned long vpn,int psize,int apsize,int ssize) +static inline void __tlbie (unsigned long vpn,int bpsize,int apsize,int ssize) {unsigned long va;unsigned int penc;
@@ -63,19 +63,33 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)*/ va &= ~(0xffffULL <<48 ); -switch (psize) { +switch (bpsize) {case MMU_PAGE_4K : +/* clear out bits after (52) [0....52.....63] */ + va &= ~((1ul << (64 -52 )) -1 ); va |= ssize <<8 ; + va |= mmu_psize_defs[apsize].sllp <<6 ; asm volatile(ASM_FTR_IFCLR("tlbie %0,0", PPC_TLBIE(%1,%0), %2) : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206) : "memory");break ;default :/* We need 14 to 14 + i bits of va */ - penc = mmu_psize_defs[psize].penc[apsize]; - va &= ~((1ul << mmu_psize_defs[psize].shift) -1 ); + penc = mmu_psize_defs[bpsize].penc[apsize]; +/* clear out bits after (44) [0....44.....63] */ + va &= ~((1ul << (64 -44 )) -1 ); va |= penc <<12 ; va |= ssize <<8 ; +/* Add AVAL part */ +if (bpsize != apsize) { +/* +* MPSS, 64K base page size and 16MB parge page size +* We don't need all the bits, but this seems to work. +* vpn cover upto 65 bits of va. (0...65) and we need +* 56..62 bits of va. +*/ + va |= ((vpn >>2 ) &0xfe ); + } va |=1 ;/* L */ asm volatile(ASM_FTR_IFCLR("tlbie %0,1", PPC_TLBIE(%1,%0), %2) : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206)
@@ -84,7 +98,7 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize) } } -static inline void __tlbiel (unsigned long vpn,int psize,int apsize,int ssize) +static inline void __tlbiel (unsigned long vpn,int bpsize,int apsize,int ssize) {unsigned long va;unsigned int penc;
@@ -98,18 +112,32 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)*/ va &= ~(0xffffULL <<48 ); -switch (psize) { +switch (bpsize) {case MMU_PAGE_4K : +/* clear out bits after(52) [0....52.....63] */ + va &= ~((1ul << (64 -52 )) -1 ); va |= ssize <<8 ; + va |= mmu_psize_defs[apsize].sllp <<6 ; asmvolatile (".long 0x7c000224 | (%0 << 11) | (0 << 21)" : :"r" (va) :"memory" );break ;default :/* We need 14 to 14 + i bits of va */ - penc = mmu_psize_defs[psize].penc[apsize]; - va &= ~((1ul << mmu_psize_defs[psize].shift) -1 ); + penc = mmu_psize_defs[bpsize].penc[apsize]; +/* clear out bits after(44) [0....44.....63] */ + va &= ~((1ul << (64 -44 )) -1 ); va |= penc <<12 ; va |= ssize <<8 ; +/* Add AVAL part */ +if (bpsize != apsize) { +/* +* MPSS, 64K base page size and 16MB parge page size +* We don't need all the bits, but this seems to work. +* vpn cover upto 65 bits of va. (0...65) and we need +* 56..62 bits of va. +*/ + va |= ((vpn >>2 ) &0xfe ); + } va |=1 ;/* L */ asmvolatile (".long 0x7c000224 | (%0 << 11) | (1 << 21)" : :"r" (va) :"memory" );
@@ -118,22 +146,22 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize) } -static inline void tlbie (unsigned long vpn,int psize,int apsize, +static inline void tlbie (unsigned long vpn,int bpsize,int apsize,int ssize,int local) {unsigned int use_local = local &&mmu_has_feature (MMU_FTR_TLBIEL );int lock_tlbie = !mmu_has_feature (MMU_FTR_LOCKLESS_TLBIE );if (use_local) - use_local = mmu_psize_defs[psize].tlbiel; + use_local = mmu_psize_defs[bpsize].tlbiel;if (lock_tlbie && !use_local)raw_spin_lock (&native_tlbie_lock); asmvolatile ("ptesync" : : :"memory" );if (use_local) { -__tlbiel (vpn, psize, apsize, ssize); +__tlbiel (vpn, bpsize, apsize, ssize); asmvolatile ("ptesync" : : :"memory" ); }else { -__tlbie (vpn, psize, apsize, ssize); +__tlbie (vpn, bpsize, apsize, ssize); asmvolatile ("eieio; tlbsync; ptesync" : : :"memory" ); }if (lock_tlbie && !use_local)
Signature · 1 line
1.7.10
RFC PATCH 8/17 powerpc: print both base and actual page size on hash failure
In reply to Aneesh Kumar K.VFrom: "Aneesh Kumar K.V" <[email protected]>
--- arch/powerpc/include/asm/mmu-hash64.h | 3 ++- arch/powerpc/mm/hash_utils_64.c | 12 +++++++----- arch/powerpc/mm/hugetlbpage-hash64.c | 2 +- 3 files changed, 10 insertions(+), 7 deletions(-)
arch/powerpc/include/asm/mmu-hash64.h +2 -1
@@ -321,7 +321,8 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, unsigned int shift, unsigned int mmu_psize);extern void hash_failure_debug (unsigned long ea,unsigned long access,unsigned long vsid,unsigned long trap, -int ssize,int psize,unsigned long pte); +int ssize,int psize,int lpsize, +unsigned long pte);extern int htab_bolt_mapping (unsigned long vstart,unsigned long vend,unsigned long pstart,unsigned long prot,int psize,int ssize);
arch/powerpc/mm/hash_utils_64.c +7 -5
@@ -917,14 +917,14 @@ static inline int subpage_protection(struct mm_struct *mm, unsigned long ea)void hash_failure_debug (unsigned long ea,unsigned long access,unsigned long vsid,unsigned long trap, -int ssize,int psize,unsigned long pte) +int ssize,int psize,int lpsize,unsigned long pte) {if (!printk_ratelimit ())return ;pr_info ("mm: Hashing failure ! EA=0x%lx access=0x%lx current=%s\n" , ea, access, current->comm); -pr_info (" trap=0x%lx vsid=0x%lx ssize=%d psize=%d pte=0x%lx\n" , - trap, vsid, ssize, psize, pte); +pr_info (" trap=0x%lx vsid=0x%lx ssize=%d base psize=%d psize %d pte=0x%lx\n" , + trap, vsid, ssize, psize, lpsize, pte); }/* Result code is:
@@ -1097,7 +1097,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)*/ if (rc ==-1 )hash_failure_debug (ea, access, vsid, trap, ssize, psize, -pte_val (*ptep)); + psize,pte_val (*ptep));#ifndef CONFIG_PPC_64K_PAGES DBG_LOW (" o-pte: %016lx\n" ,pte_val (*ptep));#else
@@ -1175,7 +1175,9 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,*/ if (rc ==-1 )hash_failure_debug (ea, access, vsid, trap, ssize, - mm->context.user_psize,pte_val (*ptep)); + mm->context.user_psize, + mm->context.user_psize, +pte_val (*ptep));local_irq_restore (flags); }
arch/powerpc/mm/hugetlbpage-hash64.c +1 -1
@@ -129,7 +129,7 @@ repeat:if (unlikely (slot ==-2 )) { *ptep =__pte (old_pte);hash_failure_debug (ea, access, vsid, trap, ssize, - mmu_psize, old_pte); + mmu_psize, mmu_psize, old_pte);return -1 ; }
Signature · 1 line
1.7.10
RFC PATCH 9/17 powerpc/mm: Use encode avpn where we need only avpn values
In reply to Aneesh Kumar K.VFrom: "Aneesh Kumar K.V" <[email protected]>
--- arch/powerpc/include/asm/mmu-hash64.h | 8 ++++---- arch/powerpc/mm/hash_native_64.c | 10 +++++----- arch/powerpc/platforms/pseries/lpar.c | 2 +- 3 files changed, 10 insertions(+), 10 deletions(-)
arch/powerpc/include/asm/mmu-hash64.h +4 -4
@@ -237,14 +237,14 @@ static inline unsigned long hpte_encode_avpn(unsigned long vpn, int psize,/* * This function sets the AVPN and L fields of the HPTE appropriately -* for the page size +* using the base page size and actual page size. */ -static inline unsigned long hpte_encode_v (unsigned long vpn, -int psize,int ssize) +static inline unsigned long hpte_encode_v (unsigned long vpn,int psize, +int apsize,int ssize) {unsigned long v; v =hpte_encode_avpn (vpn, psize, ssize); -if (psize !=MMU_PAGE_4K ) +if (apsize !=MMU_PAGE_4K ) v |=HPTE_V_LARGE ;return v; }
arch/powerpc/mm/hash_native_64.c +5 -5
@@ -216,7 +216,7 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,if (i ==HPTES_PER_GROUP )return -1 ; - hpte_v =hpte_encode_v (vpn, psize, ssize) | vflags |HPTE_V_VALID ; + hpte_v =hpte_encode_v (vpn, psize, apsize, ssize) | vflags |HPTE_V_VALID ; hpte_r =hpte_encode_r (pa, psize, apsize) | rflags;if (!(vflags &HPTE_V_BOLTED )) {
@@ -327,7 +327,7 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,int ret =0 ;int actual_psize; - want_v =hpte_encode_v (vpn, psize, ssize); + want_v =hpte_encode_avpn (vpn, psize, ssize);DBG_LOW (" update(vpn=%016lx, avpnv=%016lx, group=%lx, newpp=%lx)" , vpn, want_v &HPTE_V_AVPN , slot, newpp);
@@ -364,7 +364,7 @@ static long native_hpte_find(unsigned long vpn, int psize, int ssize)unsigned long want_v, hpte_v; hash =hpt_hash (vpn, mmu_psize_defs[psize].shift, ssize); - want_v =hpte_encode_v (vpn, psize, ssize); + want_v =hpte_encode_avpn (vpn, psize, ssize);/* Bolted mappings are only ever in the primary group */ slot = (hash & htab_hash_mask) *HPTES_PER_GROUP ;
@@ -427,7 +427,7 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,DBG_LOW (" invalidate(vpn=%016lx, hash: %lx)\n" , vpn, slot); - want_v =hpte_encode_v (vpn, psize, ssize); + want_v =hpte_encode_avpn (vpn, psize, ssize);native_lock_hpte (hptep); hpte_v = hptep->v;
@@ -599,7 +599,7 @@ static void native_flush_hash_range(unsigned long number, int local) slot = (hash & htab_hash_mask) *HPTES_PER_GROUP ; slot += hidx & _PTEIDX_GROUP_IX; hptep = htab_address + slot; - want_v =hpte_encode_v (vpn, psize, ssize); + want_v =hpte_encode_avpn (vpn, psize, ssize);native_lock_hpte (hptep); hpte_v = hptep->v; if (!HPTE_V_COMPARE(hpte_v, want_v) ||
arch/powerpc/platforms/pseries/lpar.c +1 -1
@@ -121,7 +121,7 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group,"pa=%016lx, rflags=%lx, vflags=%lx, psize=%d)\n" , hpte_group, vpn, pa, rflags, vflags, psize); - hpte_v =hpte_encode_v (vpn, psize, ssize) | vflags |HPTE_V_VALID ; + hpte_v =hpte_encode_v (vpn, psize, apsize, ssize) | vflags |HPTE_V_VALID ; hpte_r =hpte_encode_r (pa, psize, apsize) | rflags;if (!(vflags &HPTE_V_BOLTED ))
Signature · 1 line
1.7.10
RFC PATCH 10/17 powerpc/mm: Fix hpte_decode to use the correct decoding for page sizes
In reply to Aneesh Kumar K.VFrom: "Aneesh Kumar K.V" <[email protected]>
As per ISA doc, we encode base and actual page size in the LP bits of PTE. The number of bit used to encode the page sizes depend on actual page size. ISA doc lists this as
PTE LP actual page size
rrrr rrrz ≥8KB
rrrr rrzz ≥16KB
rrrr rzzz ≥32KB
rrrr zzzz ≥64KB
rrrz zzzz ≥128KB
rrzz zzzz ≥256KB
rzzz zzzz ≥512KB
zzzz zzzz ≥1MB
ISA doc also says
"The values of the “z” bits used to specify each size, along with all possible values of “r” bits in the LP field, must result in LP values distinct from other LP values for other sizes."
based on the above update hpte_decode to use the correct decoding for LP bits.
--- arch/powerpc/mm/hash_native_64.c | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-)
arch/powerpc/mm/hash_native_64.c +16 -10
@@ -449,19 +449,14 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot, int *psize, int *apsize, int *ssize, unsigned long *vpn) { unsigned long avpn, pteg, vpi; -unsigned long hpte_r = hpte->r;unsigned long hpte_v = hpte->v;unsigned long vsid, seg_off; -int i, size, a_size =MMU_PAGE_4K , shift, penc; +int size, a_size =MMU_PAGE_4K , shift, mask; +unsigned int lp = (hpte->r >>LP_SHIFT ) &LP_BITS ;if (!(hpte_v &HPTE_V_LARGE )) size =MMU_PAGE_4K ;else { -for (i =0 ; i <LP_BITS ; i++) { -if ((hpte_r &LP_MASK (i+1 )) ==LP_MASK (i+1 )) -break ; - } - penc =LP_MASK (i+1 ) >>LP_SHIFT ;for (size =0 ; size <MMU_PAGE_COUNT ; size++) {/* 4K pages are not represented by LP */
@@ -471,12 +466,23 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,/* valid entries have a shift value */ if (!mmu_psize_defs[size].shift)continue ; -for (a_size =0 ; a_size <MMU_PAGE_COUNT ; a_size++) -if (penc == mmu_psize_defs[size].penc[a_size]) + +for (a_size =0 ; a_size <MMU_PAGE_COUNT ; a_size++) { +/* valid entries have a shift value */ +if (!mmu_psize_defs[a_size].shift) +continue ; + + shift = mmu_psize_defs[a_size].shift -11 ; +if (shift >9 ) + shift =9 ; + mask = (1 << shift) -1 ; +if ((lp & mask) == + mmu_psize_defs[size].penc[a_size]) { goto out; + } + } } } - out:/* This works for all page sizes, and for 256M and 1T segments */ *ssize = hpte_v >>HPTE_V_SSIZE_SHIFT ;
Signature · 1 line
1.7.10
RFC PATCH 11/17 powerpc: Print page size info during boot
In reply to Aneesh Kumar K.VFrom: "Aneesh Kumar K.V" <[email protected]>
This gives hint about different base and actual page size combination supported by the platform.
--- arch/powerpc/mm/hash_utils_64.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)
arch/powerpc/mm/hash_utils_64.c +5 -5
@@ -314,7 +314,7 @@ static int __init htab_dt_scan_page_sizes(unsigned long node, prop = (u32 *)of_get_flat_dt_prop (node,"ibm,segment-page-sizes" , &size);if (prop !=NULL ) { -DBG ("Page sizes from device-tree:\n" ); +pr_info ("Page sizes from device-tree:\n" ); size /=4 ; cur_cpu_spec->mmu_features &= ~(MMU_FTR_16M_PAGE );while (size >0 ) {
@@ -364,10 +364,10 @@ static int __init htab_dt_scan_page_sizes(unsigned long node,continue ; def->penc[idx] = penc; -DBG (" %d: shift=%02x, sllp=%04lx, " -"avpnm=%08lx, tlbiel=%d, penc=%d\n" , - idx, shift, def->sllp, def->avpnm, - def->tlbiel, def->penc[idx]); +pr_info ("base_shift=%d: shift=%d, sllp=0x%04lx," +" avpnm=0x%08lx, tlbiel=%d, penc=%d\n" , + base_shift, shift, def->sllp, + def->avpnm, def->tlbiel, def->penc[idx]); } }return 1 ;
Signature · 1 line
1.7.10
RFC PATCH 12/17 powerpc/THP: Implement transparent huge pages for ppc64
In reply to Aneesh Kumar K.VFrom: "Aneesh Kumar K.V" <[email protected]>
We now have pmd entries covering to 16MB range. To implement THP on powerpc, we double the size of PMD. The second half is used to deposit the pgtable (PTE page). We also use the depoisted PTE page for tracking the HPTE information. The information include [ secondary group | 3 bit hidx | valid ]. We use one byte per each HPTE entry. With 16MB huge page and 64K HPTE we need 256 entries and with 4K HPTE we need 4096 entries. Both will fit in a 4K PTE page.
--- arch/powerpc/include/asm/page.h | 2 +- arch/powerpc/include/asm/pgtable-ppc64-64k.h | 3 +- arch/powerpc/include/asm/pgtable-ppc64.h | 6 +- arch/powerpc/include/asm/pgtable.h | 247 +++++++++++++++++++ arch/powerpc/mm/init_64.c | 14 ++ arch/powerpc/mm/pgtable.c | 340 ++++++++++++++++++++++++++ arch/powerpc/platforms/Kconfig.cputype | 1 + 7 files changed, 610 insertions(+), 3 deletions(-)
arch/powerpc/include/asm/page.h +1 -1
@@ -40,7 +40,7 @@#ifdef CONFIG_HUGETLB_PAGE extern unsigned int HPAGE_SHIFT ;#else -#define HPAGE_SHIFT PAGE_SHIFT +#define HPAGE_SHIFT PMD_SHIFT#endif #define HPAGE_SIZE ((1UL) << HPAGE_SHIFT)#define HPAGE_MASK (~(HPAGE_SIZE - 1))
arch/powerpc/include/asm/pgtable-ppc64-64k.h +2 -1
@@ -33,7 +33,8 @@#define PGDIR_MASK (~(PGDIR_SIZE-1))/* Bits to mask out from a PMD to get to the PTE page */ -#define PMD_MASKED_BITS 0x1ff +/* PMDs point to PTE table fragments which are 4K aligned. */ +#define PMD_MASKED_BITS 0xfff/* Bits to mask out from a PGD/PUD to get to the PMD page */ #define PUD_MASKED_BITS 0x1ff
arch/powerpc/include/asm/pgtable-ppc64.h +5 -1
@@ -149,8 +149,12 @@ || (pmd_val(pmd) & PMD_BAD_BITS))#define pmd_present (pmd) (pmd_val(pmd) != 0)#define pmd_clear (pmdp) (pmd_val(*(pmdp)) = 0) +/* +* FIXME PMD_MASKED_BITS should include all of PMD_HUGE_PROTBITS +* should only be called for non huge pages. +*/ #define pmd_page_vaddr (pmd) (pmd_val(pmd) & ~PMD_MASKED_BITS) -#define pmd_page (pmd) virt_to_page(pmd_page_vaddr(pmd)) +extern struct page *pmd_page (pmd_t pmd);#define pud_set (pudp, pudval) (pud_val(*(pudp)) = (pudval))#define pud_none (pud) (!pud_val(pud))
arch/powerpc/include/asm/pgtable.h +247 -0
253 lines not on this page · raw message
arch/powerpc/mm/init_64.c +14 -0
@@ -88,7 +88,12 @@ static void pgd_ctor(void *addr)static void pmd_ctor (void *addr) { +/* FIXME may be we can take size as arg ? */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +memset (addr,0 ,PMD_TABLE_SIZE *2 ); +#else memset (addr,0 ,PMD_TABLE_SIZE ); +#endif }struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE ];
@@ -138,7 +143,16 @@ void __pgtable_cache_add(unsigned int index, unsigned long table_size,void pgtable_cache_init (void ) {pgtable_cache_add (PGD_INDEX_SIZE , pgd_ctor); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +/* +* we store the pgtable details in the second half of PMD +*/ +if (PGT_CACHE (PMD_INDEX_SIZE )) +pr_err ("PMD Page cache already initialized with different size\n" ); +__pgtable_cache_add (PMD_INDEX_SIZE ,PMD_TABLE_SIZE *2 , pmd_ctor); +#else pgtable_cache_add (PMD_INDEX_SIZE , pmd_ctor); +#endif if (!PGT_CACHE (PGD_INDEX_SIZE ) || !PGT_CACHE (PMD_INDEX_SIZE ))panic ("Couldn't allocate pgtable caches" );
arch/powerpc/mm/pgtable.c +340 -0
349 lines not on this page · raw message
arch/powerpc/platforms/Kconfig.cputype +1 -0
@@ -71,6 +71,7 @@ config PPC_BOOK3S_64 select PPC_FPU select PPC_HAVE_PMU_SUPPORT select SYS_SUPPORTS_HUGETLBFS + select HAVE_ARCH_TRANSPARENT_HUGEPAGE if PPC_64K_PAGES config PPC_BOOK3E_64 bool "Embedded processors"
Signature · 1 line
1.7.10
RFC PATCH 13/17 powerpc/THP: Add code to handle HPTE faults for large pages
In reply to Aneesh Kumar K.VFrom: "Aneesh Kumar K.V" <[email protected]>
We now have pmd entries covering to 16MB range. To implement THP on powerpc, we double the size of PMD. The second half is used to deposit the pgtable (PTE page). We also use the depoisted PTE page for tracking the HPTE information. The information include [ secondary group | 3 bit hidx | valid ]. We use one byte per each HPTE entry. With 16MB huge page and 64K HPTE we need 256 entries and with 4K HPTE we need 4096 entries. Both will fit in a 4K PTE page.
--- arch/powerpc/include/asm/mmu-hash64.h | 5 + arch/powerpc/include/asm/pgtable-ppc64.h | 33 ++---- arch/powerpc/kernel/io-workarounds.c | 2 +- arch/powerpc/kvm/book3s_64_mmu_hv.c | 2 +- arch/powerpc/kvm/book3s_hv_rm_mmu.c | 5 +- arch/powerpc/mm/Makefile | 1 + arch/powerpc/mm/hash_utils_64.c | 12 ++- arch/powerpc/mm/hugetlbpage.c | 19 +++- arch/powerpc/mm/largepage-hash64.c | 170 ++++++++++++++++++++++++++++++ arch/powerpc/mm/pgtable.c | 34 ++++++ arch/powerpc/mm/tlb_hash64.c | 2 +- arch/powerpc/perf/callchain.c | 2 +- arch/powerpc/platforms/pseries/eeh.c | 2 +- 13 files changed, 248 insertions(+), 41 deletions(-) create mode 100644 arch/powerpc/mm/largepage-hash64.c
arch/powerpc/include/asm/mmu-hash64.h +5 -0
@@ -319,6 +319,11 @@ extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap)int __hash_page_huge (unsigned long ea,unsigned long access,unsigned long vsid,pte_t *ptep,unsigned long trap,int local,int ssize,unsigned int shift,unsigned int mmu_psize); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +extern int __hash_page_thp (unsigned long ea,unsigned long access, +unsigned long vsid,pmd_t *pmdp,unsigned long trap, +int local,int ssize,unsigned int psize); +#endif extern void hash_failure_debug(unsigned long ea, unsigned long access, unsigned long vsid, unsigned long trap, int ssize, int psize, int lpsize,
arch/powerpc/include/asm/pgtable-ppc64.h +6 -27
@@ -350,39 +350,18 @@ static inline void pgtable_cache_add(unsigned shift, void (*ctor)(void *))return __pgtable_cache_add (shift,sizeof (void *) << shift, ctor); } -/* -* find_linux_pte returns the address of a linux pte for a given -* effective address and directory. If not found, it returns zero. -*/ -static inline pte_t *find_linux_pte (pgd_t *pgdir,unsigned long ea) -{ -pgd_t *pg; -pud_t *pu; -pmd_t *pm; -pte_t *pt =NULL ; - - pg = pgdir +pgd_index (ea); -if (!pgd_none (*pg)) { - pu =pud_offset (pg, ea); -if (!pud_none (*pu)) { - pm =pmd_offset (pu, ea); -if (pmd_present (*pm)) - pt =pte_offset_kernel (pm, ea); - } - } -return pt; -} - -#ifdef CONFIG_HUGETLB_PAGE +#if defined(CONFIG_HUGETLB_PAGE )pte_t *find_linux_pte_or_hugepte (pgd_t *pgdir,unsigned long ea, -unsigned *shift); +unsigned *shift,unsigned int *thp);#else +pte_t *find_linux_pte (pgd_t *pgdir,unsigned long ea,unsigned int *thp);static inline pte_t *find_linux_pte_or_hugepte (pgd_t *pgdir,unsigned long ea, -unsigned *shift) +unsigned *shift, +unsigned int *thp) {if (shift) *shift =0 ; -return find_linux_pte (pgdir, ea); +return find_linux_pte (pgdir, ea, thp); }#endif /* !CONFIG_HUGETLB_PAGE */
arch/powerpc/kernel/io-workarounds.c +1 -1
@@ -70,7 +70,7 @@ struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)if (vaddr <PHB_IO_BASE || vaddr >=PHB_IO_END )return NULL ; - ptep =find_linux_pte (init_mm.pgd, vaddr); + ptep =find_linux_pte (init_mm.pgd, vaddr,NULL );if (ptep ==NULL ) paddr =0 ;else
arch/powerpc/kvm/book3s_64_mmu_hv.c +1 -1
@@ -683,7 +683,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,*/ rcu_read_lock_sched (); ptep =find_linux_pte_or_hugepte (current->mm->pgd, - hva,NULL ); + hva,NULL ,NULL );if (ptep &&pte_present (*ptep)) { pte =kvmppc_read_update_linux_pte (ptep,1 );if (pte_write (pte))
arch/powerpc/kvm/book3s_hv_rm_mmu.c +3 -2
@@ -27,7 +27,7 @@ static void *real_vmalloc_addr(void *x)unsigned long addr = (unsigned long ) x;pte_t *p; - p =find_linux_pte (swapper_pg_dir, addr); + p =find_linux_pte (swapper_pg_dir, addr,NULL );if (!p || !pte_present (*p))return NULL ;/* assume we don't have huge pages in vmalloc space... */
@@ -145,6 +145,7 @@ static void remove_revmap_chain(struct kvm *kvm, long pte_index,unlock_rmap (rmap); } +/* FIXME!! check */ static pte_t lookup_linux_pte (pgd_t *pgdir,unsigned long hva,int writing,unsigned long *pte_sizep) {
@@ -152,7 +153,7 @@ static pte_t lookup_linux_pte(pgd_t *pgdir, unsigned long hva,unsigned long ps = *pte_sizep;unsigned int shift; - ptep =find_linux_pte_or_hugepte (pgdir, hva, &shift); + ptep =find_linux_pte_or_hugepte (pgdir, hva, &shift,NULL );if (!ptep)return __pte (0 );if (shift)
arch/powerpc/mm/Makefile +1 -0
@@ -33,6 +33,7 @@ obj-y += hugetlbpage.o obj-$(CONFIG_PPC_STD_MMU_64) += hugetlbpage-hash64.o obj-$(CONFIG_PPC_BOOK3E_MMU) += hugetlbpage-book3e.o endif +obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += largepage-hash64.o obj-$(CONFIG_PPC_SUBPAGE_PROT) += subpage-prot.o obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o obj-$(CONFIG_HIGHMEM) += highmem.o
arch/powerpc/mm/hash_utils_64.c +9 -3
@@ -939,7 +939,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)unsigned long vsid;struct mm_struct *mm;pte_t *ptep; -unsigned hugeshift; +unsigned hugeshift, thp;const struct cpumask *tmp;int rc, user_region =0 , local =0 ;int psize, ssize;
@@ -1005,7 +1005,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)#endif /* CONFIG_PPC_64K_PAGES */ /* Get PTE and page size from page tables */ - ptep =find_linux_pte_or_hugepte (pgdir, ea, &hugeshift); + ptep =find_linux_pte_or_hugepte (pgdir, ea, &hugeshift, &thp);if (ptep ==NULL || !pte_present (*ptep)) {DBG_LOW (" no PTE !\n" );return 1 ;
@@ -1028,6 +1028,12 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) ssize, hugeshift, psize);#endif /* CONFIG_HUGETLB_PAGE */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +if (thp) +return __hash_page_thp (ea, access, vsid, (pmd_t *)ptep, + trap, local, ssize, psize); +#endif +#ifndef CONFIG_PPC_64K_PAGES DBG_LOW (" i-pte: %016lx\n" ,pte_val (*ptep));#else
@@ -1133,7 +1139,7 @@ void hash_preload(struct mm_struct *mm, unsigned long ea, pgdir = mm->pgd;if (pgdir ==NULL )return ; - ptep =find_linux_pte (pgdir, ea); + ptep =find_linux_pte (pgdir, ea,NULL );if (!ptep)return ;
arch/powerpc/mm/hugetlbpage.c +15 -4
@@ -67,7 +67,8 @@ static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize)#define hugepd_none (hpd) ((hpd).pd == 0) -pte_t *find_linux_pte_or_hugepte (pgd_t *pgdir,unsigned long ea,unsigned *shift) +pte_t *find_linux_pte_or_hugepte (pgd_t *pgdir,unsigned long ea, +unsigned *shift,unsigned int *thp) {pgd_t *pg;pud_t *pu;
@@ -77,6 +78,8 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shiftif (shift) *shift =0 ; +if (thp) + *thp =0 ; pg = pgdir +pgd_index (ea);if (is_hugepd (pg)) {
@@ -91,12 +94,20 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift pm =pmd_offset (pu, ea);if (is_hugepd (pm)) hpdp = (hugepd_t *)pm; -else if (!pmd_none (*pm)) { +else if (pmd_large (*pm)) { +/* THP page */ +if (thp) + *thp =1 ; +/* +* This should be ok, except for few flags +* most of the pte, large page pmd bits map +*/ +return (pte_t *)pm; + }else if (!pmd_none (*pm)) {return pte_offset_kernel (pm, ea); } } } -if (!hpdp)return NULL ;
@@ -614,7 +625,7 @@ follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)unsigned shift;unsigned long mask; - ptep =find_linux_pte_or_hugepte (mm->pgd, address, &shift); + ptep =find_linux_pte_or_hugepte (mm->pgd, address, &shift,NULL );/* Verify it is a huge page else bail. */ if (!ptep || !shift)
arch/powerpc/mm/largepage-hash64.c new file +170 -0
170 lines not on this page · raw message
arch/powerpc/mm/pgtable.c +34 -0
@@ -580,3 +580,37 @@ struct page *pmd_page(pmd_t pmd) }#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +/* +* find_linux_pte returns the address of a linux pte for a given +* effective address and directory. If not found, it returns zero. +*/ +pte_t *find_linux_pte (pgd_t *pgdir,unsigned long ea,unsigned int *thp) +{ +pgd_t *pg; +pud_t *pu; +pmd_t *pm; +pte_t *pt =NULL ; + +if (thp) + *thp =0 ; + pg = pgdir +pgd_index (ea); +if (!pgd_none (*pg)) { + pu =pud_offset (pg, ea); +if (!pud_none (*pu)) { + pm =pmd_offset (pu, ea); +if (pmd_large (*pm)) { +/* THP page */ +if (thp) + *thp =1 ; +/* +* This should be ok, except for few flags +* most of the pte, large page pmd bits map +*/ +return (pte_t *)pm; + }else if (pmd_present (*pm)) + pt =pte_offset_kernel (pm, ea); + } + } +return pt; +}
arch/powerpc/mm/tlb_hash64.c +1 -1
@@ -206,7 +206,7 @@ void __flush_hash_table_range(struct mm_struct *mm, unsigned long start,local_irq_save (flags);arch_enter_lazy_mmu_mode ();for (; start < end; start +=PAGE_SIZE ) { -pte_t *ptep =find_linux_pte (mm->pgd, start); +pte_t *ptep =find_linux_pte (mm->pgd, start,NULL );unsigned long pte;if (ptep ==NULL )
arch/powerpc/perf/callchain.c +1 -1
@@ -125,7 +125,7 @@ static int read_user_stack_slow(void __user *ptr, void *ret, int nb)if (!pgdir)return -EFAULT ; - ptep =find_linux_pte_or_hugepte (pgdir, addr, &shift); + ptep =find_linux_pte_or_hugepte (pgdir, addr, &shift,NULL );if (!shift) shift =PAGE_SHIFT ;
arch/powerpc/platforms/pseries/eeh.c +1 -1
@@ -261,7 +261,7 @@ static inline unsigned long eeh_token_to_phys(unsigned long token)pte_t *ptep;unsigned long pa; - ptep =find_linux_pte (init_mm.pgd, token); + ptep =find_linux_pte (init_mm.pgd, token,NULL );if (!ptep)return token; pa =pte_pfn (*ptep) <<PAGE_SHIFT ;
Signature · 1 line
1.7.10
RFC PATCH 14/17 powerpc: support for zerout withdraw.
In reply to Aneesh Kumar K.VFrom: "Aneesh Kumar K.V" <[email protected]>
Need changes to other archs. This need to be fixed further
--- arch/powerpc/include/asm/pgtable.h | 3 ++- arch/powerpc/mm/pgtable.c | 11 ++++++++--- mm/huge_memory.c | 18 ++++++++++++------ 3 files changed, 22 insertions(+), 10 deletions(-)
arch/powerpc/include/asm/pgtable.h +2 -1
@@ -262,7 +262,8 @@ extern void pmdp_splitting_flush(struct vm_area_struct *vma,extern void pgtable_trans_huge_deposit (struct mm_struct *mm,pmd_t *pmdp,pgtable_t pgtable);#define __HAVE_ARCH_PGTABLE_WITHDRAW -extern pgtable_t pgtable_trans_huge_withdraw (struct mm_struct *mm,pmd_t *pmdp); +extern pgtable_t pgtable_trans_huge_withdraw (struct mm_struct *mm, +pmd_t *pmdp,int tozero);#define __HAVE_ARCH_PMDP_INVALIDATE extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
arch/powerpc/mm/pgtable.c +8 -3
@@ -355,7 +355,7 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,/* FIXME!! May be all this should be in pgtable_64.c ? */ #define PTE_FRAG_SIZE (2 * PTRS_PER_PTE * sizeof(pte_t)) -pgtable_t pgtable_trans_huge_withdraw (struct mm_struct *mm,pmd_t *pmdp) +pgtable_t pgtable_trans_huge_withdraw (struct mm_struct *mm,pmd_t *pmdp,int tozero) {pgtable_t pgtable;unsigned long *pgtable_slot;
@@ -368,8 +368,13 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)* Make sure we are invalidating all the entries. So that * we fault and create new entries later */ -/* zero out the table before returning */ -memset (pgtable,0 ,PTE_FRAG_SIZE ); +/* FIXME!! this is not correct. zero out the table before returning +* because we are using this for other things. +* zap_huge_pmd +*/ +if (tozero) +/* Not needed, because we depoist a zeroed table ? */ +memset (pgtable,0 ,PTE_FRAG_SIZE );return pgtable; }
mm/huge_memory.c +12 -6
@@ -781,7 +781,7 @@ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm, entry =pmd_wrprotect (entry); entry =pmd_mkhuge (entry);set_pmd_at (mm, haddr, pmd, entry); -pgtable_trans_huge_deposit (mm, pgtable); +pgtable_trans_huge_deposit (mm, pmd, pgtable); mm->nr_ptes++;return true; }
@@ -996,7 +996,7 @@ static int do_huge_pmd_wp_zero_page_fallback(struct mm_struct *mm,pmdp_clear_flush (vma, haddr, pmd);/* leave pmd empty until pte is filled */ - pgtable =pgtable_trans_huge_withdraw (mm); + pgtable =pgtable_trans_huge_withdraw (mm, pmd,1 );pmd_populate (mm, &_pmd, pgtable);for (i =0 ; i <HPAGE_PMD_NR ; i++, haddr +=PAGE_SIZE ) {
@@ -1091,7 +1091,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, goto out_free_pages;VM_BUG_ON (!PageHead (page)); - pgtable =pgtable_trans_huge_withdraw (mm, pmd); + pgtable =pgtable_trans_huge_withdraw (mm, pmd,1 );pmdp_clear_flush (vma, haddr, pmd);/* leave pmd empty until pte is filled */
@@ -1373,7 +1373,13 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,struct page *page;pgtable_t pgtable;pmd_t orig_pmd; - pgtable =pgtable_trans_huge_withdraw (tlb->mm, pmd); +/* +* Withdraw the pgtable without zero out, because +* the following pmd_get_and_clear will look at +* pgtable contents, in case of some architectures +* like ppc64 +*/ + pgtable =pgtable_trans_huge_withdraw (tlb->mm, pmd,0 ); orig_pmd =pmdp_get_and_clear (tlb->mm, addr, pmd);tlb_remove_pmd_tlb_entry (tlb, pmd, addr);if (is_huge_zero_pmd (orig_pmd)) {
@@ -1705,7 +1711,7 @@ static int __split_huge_page_map(struct page *page, pmd =page_check_address_pmd (page, mm, address,PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG );if (pmd) { - pgtable =pgtable_trans_huge_withdraw (mm, pmd); + pgtable =pgtable_trans_huge_withdraw (mm, pmd,1 );pmd_populate (mm, &_pmd, pgtable); haddr = address;
@@ -2699,7 +2705,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,pmdp_clear_flush (vma, haddr, pmd);/* leave pmd empty until pte is filled */ - pgtable =pgtable_trans_huge_withdraw (mm); + pgtable =pgtable_trans_huge_withdraw (mm, pmd,1 );pmd_populate (mm, &_pmd, pgtable);for (i =0 ; i <HPAGE_PMD_NR ; i++, haddr +=PAGE_SIZE ) {
Signature · 1 line
1.7.10
RFC PATCH 15/17 powerpc: hypervisor require few WIMG bit set
In reply to Aneesh Kumar K.VFrom: "Aneesh Kumar K.V" <[email protected]>
Without this insert will return H_PARAMETER error. Also use the signed variant when printing error.
--- arch/powerpc/mm/largepage-hash64.c | 2 ++ arch/powerpc/platforms/pseries/lpar.c | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-)
arch/powerpc/mm/largepage-hash64.c +2 -0
@@ -123,6 +123,8 @@ repeat:/* Add in WIMG bits. FIXME!! enabled by default */ rflags |= (new_pmd & (_PAGE_WRITETHRU | _PAGE_NO_CACHE | _PAGE_COHERENT | _PAGE_GUARDED)); +#else + rflags |= _PAGE_COHERENT;#endif /* Insert into the hash table, primary slot */ slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0,
arch/powerpc/platforms/pseries/lpar.c +1 -1
@@ -155,7 +155,7 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group,*/ if (unlikely (lpar_rc !=H_SUCCESS )) {if (!(vflags &HPTE_V_BOLTED )) -pr_devel (" lpar err %lu\n" , lpar_rc); +pr_devel (" lpar err %ld\n" , lpar_rc);return -2 ; }if (!(vflags &HPTE_V_BOLTED ))
Signature · 1 line
1.7.10
RFC PATCH 16/17 powerpc: get_user_pages_fast changes
In reply to Aneesh Kumar K.VFrom: "Aneesh Kumar K.V" <[email protected]>
handle large pages for get_user_pages_fast. Also take care of large page splitting.
--- arch/powerpc/mm/gup.c | 76 +++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 74 insertions(+), 2 deletions(-)
arch/powerpc/mm/gup.c +74 -2
@@ -55,6 +55,64 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,return 1 ; } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline int gup_huge_pmd (pmd_t *pmdp,unsigned long addr, +unsigned long end,int write, +struct page **pages,int *nr) +{ +int refs; +pmd_t pmd; +unsigned long mask; +struct page *head, *page, *tail; + + pmd = *pmdp; + mask =PMD_HUGE_PRESENT |PMD_HUGE_USER ; +if (write) + mask |=PMD_HUGE_RW ; + +if ((pmd_val (pmd) & mask) != mask) +return 0 ; + +/* FIXME!! large pages are never "special" */ +VM_BUG_ON (!pfn_valid (pmd_pfn (pmd))); + + refs =0 ; + head =pmd_page (pmd); + page = head + ((addr & ~PMD_MASK ) >>PAGE_SHIFT ); + tail = page; +do { +VM_BUG_ON (compound_head (page) != head); + pages[*nr] = page; + (*nr)++; + page++; + refs++; + }while (addr +=PAGE_SIZE , addr != end); + +if (!page_cache_add_speculative (head, refs)) { + *nr -= refs; +return 0 ; + } + +if (unlikely (pmd_val (pmd) !=pmd_val (*pmdp))) { + *nr -= refs; +while (refs--) +put_page (head); +return 0 ; + } +/* +* Any tail page need their mapcount reference taken before we +* return. +*/ +while (refs--) { +if (PageTail (tail)) +get_huge_page_tail (tail); + tail++; + } + +return 1 ; +} +#endif +static int gup_pmd_range (pud_t pud,unsigned long addr,unsigned long end,int write,struct page **pages,int *nr) {
@@ -66,9 +124,23 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,pmd_t pmd = *pmdp; next =pmd_addr_end (addr, end); -if (pmd_none (pmd)) +/* +* The pmd_trans_splitting() check below explains why +* pmdp_splitting_flush has to flush the tlb, to stop +* this gup-fast code from running while we set the +* splitting bit in the pmd. Returning zero will take +* the slow path that will call wait_split_huge_page() +* if the pmd is still in splitting state. gup-fast +* can't because it has irq disabled and +* wait_split_huge_page() would never return as the +* tlb flush IPI wouldn't run. +*/ +if (pmd_none (pmd) ||pmd_trans_splitting (pmd))return 0 ; -if (is_hugepd (pmdp)) { +if (unlikely (pmd_large (pmd))) { +if (!gup_huge_pmd (pmdp, addr, next, write, pages, nr)) +return 0 ; + }else if (is_hugepd (pmdp)) {if (!gup_hugepd ((hugepd_t *)pmdp,PMD_SHIFT , addr, next, write, pages, nr))return 0 ;
Signature · 1 line
1.7.10
RFC PATCH 17/17 powerpc: Save DAR and DSISR in pt_regs on MCE
In reply to Aneesh Kumar K.VFrom: "Aneesh Kumar K.V" <[email protected]>
We were not saving DAR and DSISR on MCE. Save then and also print the values along with exception details in xmon.
--- arch/powerpc/kernel/exceptions-64s.S | 9 +++++++++ arch/powerpc/xmon/xmon.c | 2 +- 2 files changed, 10 insertions(+), 1 deletion(-)
arch/powerpc/kernel/exceptions-64s.S +9 -0
@@ -640,9 +640,18 @@ slb_miss_user_pseries: .align 7 .globl machine_check_common machine_check_common: + + mfspr r10,SPRN_DAR + std r10,PACA_EXGEN+EX_DAR(r13) + mfspr r10,SPRN_DSISR + stw r10,PACA_EXGEN+EX_DSISR(r13) EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC) FINISH_NAP DISABLE_INTS + ld r3,PACA_EXGEN+EX_DAR(r13) + lwz r4,PACA_EXGEN+EX_DSISR(r13) + std r3,_DAR(r1) + std r4,_DSISR(r1) bl .save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD bl .machine_check_exception
arch/powerpc/xmon/xmon.c +1 -1
@@ -1423,7 +1423,7 @@ static void excprint(struct pt_regs *fp)printf (" sp: %lx\n" , fp->gpr[1 ]);printf (" msr: %lx\n" , fp->msr); -if (trap ==0x300 || trap ==0x380 || trap ==0x600 ) { +if (trap ==0x300 || trap ==0x380 || trap ==0x600 || trap ==0x200 ) {printf (" dar: %lx\n" , fp->dar);if (trap !=0x380 )printf (" dsisr: %lx\n" , fp->dsisr);
Signature · 1 line
1.7.10