powerpc/mm/book3s: Update pmd_present to look at _PAGE_PRESENT bit
PATCH v3 2/6 powerpc/mm/hugetlb/book3s: add _PAGE_PRESENT to hugepd pointer.
In reply to Aneesh Kumar K.VThis make hugetlb directory pointer similar to other page able entries. A hugepd entry is identified by lack of _PAGE_PTE bit set and directory size stored in HUGEPD_SHIFT_MASK. We update that to also look at _PAGE_PRESENT
--- arch/powerpc/include/asm/book3s/64/hash-4k.h | 2 +- arch/powerpc/include/asm/book3s/64/hugetlb.h | 3 +++ arch/powerpc/mm/hugetlbpage.c | 2 +- 3 files changed, 5 insertions(+), 2 deletions(-)
arch/powerpc/include/asm/book3s/64/hash-4k.h +1 -1
@@ -66,7 +66,7 @@ static inline int hash__hugepd_ok(hugepd_t hpd)* if it is not a pte and have hugepd shift mask * set, then it is a hugepd directory pointer */ -if (!(hpdval & _PAGE_PTE) && +if (!(hpdval & _PAGE_PTE) && (hpdval & _PAGE_PRESENT) && ((hpdval &HUGEPD_SHIFT_MASK ) !=0 ))return true;return false;
arch/powerpc/include/asm/book3s/64/hugetlb.h +3 -0
@@ -39,4 +39,7 @@ static inline bool gigantic_page_supported(void) }#endif +/* hugepd entry valid bit */ +#define HUGEPD_VAL_BITS (0x8000000000000000UL) +#endif
arch/powerpc/mm/hugetlbpage.c +1 -1
@@ -95,7 +95,7 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,break ; else {#ifdef CONFIG_PPC_BOOK3S_64 - *hpdp =__hugepd (__pa (new) | + *hpdp =__hugepd (__pa (new) |HUGEPD_VAL_BITS | (shift_to_mmu_psize (pshift) <<2 ));#elif defined(CONFIG_PPC_8xx) *hpdp = __hugepd(__pa(new) | _PMD_USER |
Signature · 1 line
2.17.1
PATCH v3 3/6 powerpc/mm/book3s: Check for pmd_large instead of pmd_trans_huge
In reply to Aneesh Kumar K.VUpdate few code paths to check for pmd_large.
set_pmd_at:
We want to use this to store swap pte at pmd level. For swap ptes we don't want to set H_PAGE_THP_HUGE. Hence check for pmd_large in set_pmd_at. This remove the false WARN_ON when using this with swap pmd entry.
pmd_page:
We don't really use them on pmd migration entries. But they can also work with migration entries and we don't differentiate at the pte level. Hence update pmd_page to work with pmd migration entries too
__find_linux_pte:
lockless page table walk need to handle pmd migration entries. pmd_trans_huge check will return false on them. We don't set thp = 1 for such entries, but update hpage_shift correctly. Without this we will walk pmd migration entries as a pte page pointer which is wrong.
--- arch/powerpc/mm/hugetlbpage.c | 8 ++++++-- arch/powerpc/mm/pgtable-book3s64.c | 2 +- arch/powerpc/mm/pgtable_64.c | 2 +- 3 files changed, 8 insertions(+), 4 deletions(-)
arch/powerpc/mm/hugetlbpage.c +6 -2
@@ -837,8 +837,12 @@ pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea, ret_pte = (pte_t *) pmdp; goto out; } - -if (pmd_huge (pmd)) { +/* +* pmd_large check below will handle the swap pmd pte +* we need to do both the check because they are config +* dependent. +*/ +if (pmd_huge (pmd) ||pmd_large (pmd)) { ret_pte = (pte_t *) pmdp; goto out; }else if (is_hugepd (__hugepd (pmd_val (pmd))))
arch/powerpc/mm/pgtable-book3s64.c +1 -1
@@ -76,7 +76,7 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,WARN_ON ((pte_raw (pmd_pte (*pmdp)) &cpu_to_be64 (_PAGE_PRESENT)) && !pte_protnone (pmd_pte (*pmdp)));assert_spin_locked (pmd_lockptr (mm, pmdp)); -WARN_ON (!(pmd_trans_huge (pmd) ||pmd_devmap (pmd))); +WARN_ON (!(pmd_large (pmd) ||pmd_devmap (pmd)));#endif trace_hugepage_set_pmd (addr,pmd_val (pmd));return set_pte_at (mm, addr,pmdp_ptep (pmdp),pmd_pte (pmd));
arch/powerpc/mm/pgtable_64.c +1 -1
@@ -306,7 +306,7 @@ struct page *pud_page(pud_t pud)*/ struct page *pmd_page (pmd_t pmd) { -if (pmd_trans_huge (pmd) ||pmd_huge (pmd) ||pmd_devmap (pmd)) +if (pmd_large (pmd) ||pmd_huge (pmd) ||pmd_devmap (pmd))return pte_page (pmd_pte (pmd));return virt_to_page (pmd_page_vaddr (pmd)); }
Signature · 1 line
2.17.1
PATCH v3 4/6 arch/powerpc/mm/hash: validate the pte entries before handling the hash fault
In reply to Aneesh Kumar K.VMake sure we are operating on THP and hugetlb entries in the respective hash fault handling routines.
No functional change in this patch. If we walked the table wrongly before, we will retry the access.
--- arch/powerpc/mm/hugepage-hash64.c | 6 ++++++ arch/powerpc/mm/hugetlbpage-hash64.c | 4 ++++ 2 files changed, 10 insertions(+)
arch/powerpc/mm/hugepage-hash64.c +6 -0
@@ -51,6 +51,12 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, new_pmd |= _PAGE_DIRTY; }while (!pmd_xchg (pmdp,__pmd (old_pmd),__pmd (new_pmd))); +/* +* Make sure this is thp or devmap entry +*/ +if (!(old_pmd & (H_PAGE_THP_HUGE | _PAGE_DEVMAP))) +return 0 ; + rflags =htab_convert_pte_flags (new_pmd);#if 0
arch/powerpc/mm/hugetlbpage-hash64.c +4 -0
@@ -62,6 +62,10 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, new_pte |= _PAGE_DIRTY; }while (!pte_xchg (ptep,__pte (old_pte),__pte (new_pte))); +/* Make sure this is a hugetlb entry */ +if (old_pte & (H_PAGE_THP_HUGE | _PAGE_DEVMAP)) +return 0 ; + rflags =htab_convert_pte_flags (new_pte);if (unlikely (mmu_psize ==MMU_PAGE_16G )) offset =PTRS_PER_PUD ;
Signature · 1 line
2.17.1
PATCH v3 5/6 powerpc/mm/thp: update pmd_trans_huge to check for pmd_present
In reply to Aneesh Kumar K.VWe need to make sure pmd_trans_huge returns false for a pmd migration entry. We mark the migration entry by clearing the _PAGE_PRESENT bit. We keep the _PAGE_PTE bit set to indicate a leaf page table entry. Hence we need to make sure we check for pmd_present() so that pmd_trans_huge won't return true on pmd migration entry.
--- .../include/asm/book3s/64/pgtable-64k.h | 3 +++ arch/powerpc/include/asm/book3s/64/pgtable.h | 18 ++++++++++++++++++ 2 files changed, 21 insertions(+)
arch/powerpc/include/asm/book3s/64/pgtable-64k.h +3 -0
@@ -10,6 +10,9 @@* * Defined in such a way that we can optimize away code block at build time * if CONFIG_HUGETLB_PAGE=n. +* +* returns true for pmd migration entries, THP, devmap, hugetlb +* But compile time dependent on CONFIG_HUGETLB_PAGE */ static inline int pmd_huge (pmd_t pmd) {
arch/powerpc/include/asm/book3s/64/pgtable.h +18 -0
@@ -1136,6 +1136,10 @@ pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp,return hash__pmd_hugepage_update (mm, addr, pmdp, clr, set); } +/* +* returns true for pmd migration entries, THP, devmap, hugetlb +* But compile time dependent on THP config +*/ static inline int pmd_large (pmd_t pmd) {return !!(pmd_raw (pmd) &cpu_to_be64 (_PAGE_PTE));
@@ -1170,8 +1174,22 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,pmd_hugepage_update (mm, addr, pmdp,0 , _PAGE_PRIVILEGED); } +/* +* Only returns true for a THP. False for pmd migration entry. +* We also need to return true when we come across a pte that +* in between a thp split. While splitting THP, we mark the pmd +* invalid (pmdp_invalidate()) before we set it with pte page +* address. A pmd_trans_huge() check against a pmd entry during that time +* should return true. +* We should not call this on a hugetlb entry. We should check for HugeTLB +* entry using vma->vm_flags +* The page table walk rule is explained in Documentation/vm/transhuge.rst +*/ static inline int pmd_trans_huge (pmd_t pmd) { +if (!pmd_present (pmd)) +return false; +if (radix_enabled ())return radix__pmd_trans_huge (pmd);return hash__pmd_trans_huge (pmd);
Signature · 1 line
2.17.1
PATCH v3 6/6 powerpc/mm:book3s: Enable THP migration support
In reply to Aneesh Kumar K.V--- arch/powerpc/include/asm/book3s/64/pgtable.h | 8 ++++++++ arch/powerpc/platforms/Kconfig.cputype | 1 + 2 files changed, 9 insertions(+)
arch/powerpc/include/asm/book3s/64/pgtable.h +8 -0
@@ -741,6 +741,8 @@ static inline bool pte_user(pte_t pte)*/ #define __pte_to_swp_entry (pte) ((swp_entry_t) { pte_val((pte)) & ~_PAGE_PTE })#define __swp_entry_to_pte (x) __pte((x).val | _PAGE_PTE) +#define __pmd_to_swp_entry (pmd) (__pte_to_swp_entry(pmd_pte(pmd))) +#define __swp_entry_to_pmd (x) (pte_pmd(__swp_entry_to_pte(x)))#ifdef CONFIG_MEM_SOFT_DIRTY #define _PAGE_SWP_SOFT_DIRTY (1UL << (SWP_TYPE_BITS + _PAGE_BIT_SWAP_TYPE))
@@ -1091,6 +1093,12 @@ static inline pte_t *pmdp_ptep(pmd_t *pmd)#define pmd_soft_dirty (pmd) pte_soft_dirty(pmd_pte(pmd))#define pmd_mksoft_dirty (pmd) pte_pmd(pte_mksoft_dirty(pmd_pte(pmd)))#define pmd_clear_soft_dirty (pmd) pte_pmd(pte_clear_soft_dirty(pmd_pte(pmd))) + +#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION +#define pmd_swp_mksoft_dirty (pmd) pte_pmd(pte_swp_mksoft_dirty(pmd_pte(pmd))) +#define pmd_swp_soft_dirty (pmd) pte_swp_soft_dirty(pmd_pte(pmd)) +#define pmd_swp_clear_soft_dirty (pmd) pte_pmd(pte_swp_clear_soft_dirty(pmd_pte(pmd))) +#endif #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ #ifdef CONFIG_NUMA_BALANCING
arch/powerpc/platforms/Kconfig.cputype +1 -0
@@ -72,6 +72,7 @@ config PPC_BOOK3S_64 select PPC_HAVE_PMU_SUPPORT select SYS_SUPPORTS_HUGETLBFS select HAVE_ARCH_TRANSPARENT_HUGEPAGE + select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE select ARCH_SUPPORTS_NUMA_BALANCING select IRQ_WORK
Signature · 1 line
2.17.1
Quoted 11 lines · Aneesh Kumar K.V
With this patch we use
0x8000000000000000UL(_PAGE_PRESENT) to indicate a valid pgd/pud/pmd entry. We also switch the p**_present() to look at this bit.With
pmd_present, we have a special case. We need to make sure we consider a pmd marked invalid during THP split as present. Right now we clear the_PAGE_PRESENTbit during apmdp_invalidate. Inorder to consider this special case we add a new pte bit_PAGE_INVALID(mapped to_RPAGE_SW0). This bit is only used with_PAGE_PRESENTcleared. Hence we are not really losing a pte bit for this special case.pmd_presentis also updated to look at_PAGE_INVALID.Signed-off-by Aneesh Kumar K.V <[email protected]>
Changese from V2:
* Rebased to mpe/merge
* Also fixup new WARN_ON with pte_present looking at _PAGE_INVALID now.
-aneesh
PATCH v3 1/6 powerpc/mm/book3s: Update pmd_present to look at _PAGE_PRESENT bit
With this patch we use 0x8000000000000000UL (_PAGE_PRESENT) to indicate a valid pgd/pud/pmd entry. We also switch the p**_present() to look at this bit.
With pmd_present, we have a special case. We need to make sure we consider a pmd marked invalid during THP split as present. Right now we clear the _PAGE_PRESENT bit during a pmdp_invalidate. Inorder to consider this special case we add a new pte bit _PAGE_INVALID (mapped to _RPAGE_SW0). This bit is only used with _PAGE_PRESENT cleared. Hence we are not really losing a pte bit for this special case. pmd_present is also updated to look at _PAGE_INVALID.
--- arch/powerpc/include/asm/book3s/64/hash.h | 5 +++++ arch/powerpc/include/asm/book3s/64/pgtable.h | 14 +++++++++++--- arch/powerpc/mm/hash_utils_64.c | 6 +++--- arch/powerpc/mm/pgtable-book3s64.c | 9 +++++++-- arch/powerpc/mm/pgtable.c | 3 ++- 5 files changed, 28 insertions(+), 9 deletions(-)
arch/powerpc/include/asm/book3s/64/hash.h +5 -0
@@ -18,6 +18,11 @@#include <asm/book3s/64/hash-4k.h> #endif +/* Bits to set in a PMD/PUD/PGD entry valid bit*/ +#define HASH_PMD_VAL_BITS (0x8000000000000000UL) +#define HASH_PUD_VAL_BITS (0x8000000000000000UL) +#define HASH_PGD_VAL_BITS (0x8000000000000000UL) +/* * Size of EA range mapped by our pagetables. */
arch/powerpc/include/asm/book3s/64/pgtable.h +11 -3
@@ -875,8 +875,16 @@ static inline int pmd_none(pmd_t pmd)static inline int pmd_present (pmd_t pmd) { +/* +* A pmd is considerent present if _PAGE_PRESENT is set. +* We also need to consider the pmd present which is marked +* invalid during a split. Hence we look for _PAGE_INVALID +* if we find _PAGE_PRESENT cleared. +*/ +if (pmd_raw (pmd) &cpu_to_be64 (_PAGE_PRESENT | _PAGE_INVALID)) +return true; -return !pmd_none (pmd); +return false; }static inline int pmd_bad (pmd_t pmd)
@@ -903,7 +911,7 @@ static inline int pud_none(pud_t pud)static inline int pud_present (pud_t pud) { -return !pud_none (pud); +return (pud_raw (pud) &cpu_to_be64 (_PAGE_PRESENT)); }extern struct page *pud_page (pud_t pud);
@@ -950,7 +958,7 @@ static inline int pgd_none(pgd_t pgd)static inline int pgd_present (pgd_t pgd) { -return !pgd_none (pgd); +return (pgd_raw (pgd) &cpu_to_be64 (_PAGE_PRESENT)); }static inline pte_t pgd_pte (pgd_t pgd)
arch/powerpc/mm/hash_utils_64.c +3 -3
@@ -1001,9 +1001,9 @@ void __init hash__early_init_mmu(void)* 4k use hugepd format, so for hash set then to * zero */ - __pmd_val_bits =0 ; - __pud_val_bits =0 ; - __pgd_val_bits =0 ; + __pmd_val_bits =HASH_PMD_VAL_BITS ; + __pud_val_bits =HASH_PUD_VAL_BITS ; + __pgd_val_bits =HASH_PGD_VAL_BITS ; __kernel_virt_start =H_KERN_VIRT_START ; __kernel_virt_size =H_KERN_VIRT_SIZE ;
arch/powerpc/mm/pgtable-book3s64.c +7 -2
@@ -69,7 +69,12 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) {#ifdef CONFIG_DEBUG_VM -WARN_ON (pte_present (pmd_pte (*pmdp)) && !pte_protnone (pmd_pte (*pmdp))); +/* +* pmd during temporary invalidate will be considered present. +* So check for _PAGE_PRESENT explicitly. +*/ +WARN_ON ((pte_raw (pmd_pte (*pmdp)) &cpu_to_be64 (_PAGE_PRESENT)) && + !pte_protnone (pmd_pte (*pmdp)));assert_spin_locked (pmd_lockptr (mm, pmdp));WARN_ON (!(pmd_trans_huge (pmd) ||pmd_devmap (pmd)));#endif
@@ -106,7 +111,7 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, {unsigned long old_pmd; - old_pmd =pmd_hugepage_update (vma->vm_mm, address, pmdp, _PAGE_PRESENT,0 ); + old_pmd =pmd_hugepage_update (vma->vm_mm, address, pmdp, _PAGE_PRESENT, _PAGE_INVALID);flush_pmd_tlb_range (vma, address, address +HPAGE_PMD_SIZE );/* * This ensures that generic code that rely on IRQ disabling
arch/powerpc/mm/pgtable.c +2 -1
@@ -192,7 +192,8 @@ void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,* _PAGE_PRESENT, but we can be sure that it is not in hpte. * Hence we can use set_pte_at for them. */ -VM_WARN_ON (pte_present (*ptep) && !pte_protnone (*ptep)); +VM_WARN_ON ((pte_raw (*ptep) &cpu_to_be64 (_PAGE_PRESENT)) && + !pte_protnone (*ptep));/* Add the pte bit when trying to set a pte */ pte =__pte (pte_val (pte) | _PAGE_PTE);
Signature · 1 line
2.17.1
kbuild test robot
build botThank you for the patch! Yet something to improve:
Hi Aneesh,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on powerpc/next]
[also build test ERROR on v4.18 next-20180822]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
url: https://github.com/0day-ci/linux/commits/Aneesh-Kumar-K-V/powerpc-mm-book3s-Update-pmd_present-to-look-at-_PAGE_PRESENT-bit/20180824-141837 base: https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git next config: powerpc-allnoconfig (attached as .config) compiler: powerpc-linux-gnu-gcc (Debian 7.2.0-11) 7.2.0
reproduce:
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross chmod +x ~/bin/make.cross
# save the attached .config to linux build tree
GCC_VERSION=7.2.0 make.cross ARCH=powerpc
All errors (new ones prefixed by >>):
In file included from include/linux/kernel.h:15:0,
from arch/powerpc/mm/pgtable.c:24:
arch/powerpc/mm/pgtable.c: In function 'set_pte_at':
>> arch/powerpc/mm/pgtable.c:195:14: error: implicit declaration of function 'pte_raw'; did you mean 'pte_read'? [-Werror=implicit-function-declaration]
VM_WARN_ON((pte_raw(*ptep) & cpu_to_be64(_PAGE_PRESENT)) &&
^
include/linux/build_bug.h:36:63: note: in definition of macro 'BUILD_BUG_ON_INVALID'
#define BUILD_BUG_ON_INVALID(e) ((void)(sizeof((__force long)(e))))
^
arch/powerpc/mm/pgtable.c:195:2: note: in expansion of macro 'VM_WARN_ON'
VM_WARN_ON((pte_raw(*ptep) & cpu_to_be64(_PAGE_PRESENT)) &&
^~~~~~~~~~cc1: all warnings being treated as errors
vim +195 arch/powerpc/mm/pgtable.c
> 24 #include <linux/kernel.h>
25 #include <linux/gfp.h>
26 #include <linux/mm.h>
27 #include <linux/percpu.h>
28 #include <linux/hardirq.h>
29 #include <linux/hugetlb.h>
30 #include <asm/pgalloc.h>
31 #include <asm/tlbflush.h>
32 #include <asm/tlb.h>
33
34 static inline int is_exec_fault(void)
35 {
36 return current->thread.regs && TRAP(current->thread.regs) == 0x400;
37 }
38
39 /* We only try to do i/d cache coherency on stuff that looks like
40 * reasonably "normal" PTEs. We currently require a PTE to be present
41 * and we avoid _PAGE_SPECIAL and cache inhibited pte. We also only do that
42 * on userspace PTEs
43 */
44 static inline int pte_looks_normal(pte_t pte)
45 {
46
47 #if defined(CONFIG_PPC_BOOK3S_64)
48 if ((pte_val(pte) & (_PAGE_PRESENT | _PAGE_SPECIAL)) == _PAGE_PRESENT) {
49 if (pte_ci(pte))
50 return 0;
51 if (pte_user(pte))
52 return 1;
53 }
54 return 0;
55 #else
56 return (pte_val(pte) &
57 (_PAGE_PRESENT | _PAGE_SPECIAL | _PAGE_NO_CACHE | _PAGE_USER |
58 _PAGE_PRIVILEGED)) ==
59 (_PAGE_PRESENT | _PAGE_USER);
60 #endif
61 }
62
63 static struct page *maybe_pte_to_page(pte_t pte)
64 {
65 unsigned long pfn = pte_pfn(pte);
66 struct page *page;
67
68 if (unlikely(!pfn_valid(pfn)))
69 return NULL;
70 page = pfn_to_page(pfn);
71 if (PageReserved(page))
72 return NULL;
73 return page;
74 }
75
76 #if defined(CONFIG_PPC_STD_MMU) || _PAGE_EXEC == 0
77
78 /* Server-style MMU handles coherency when hashing if HW exec permission
79 * is supposed per page (currently 64-bit only). If not, then, we always
80 * flush the cache for valid PTEs in set_pte. Embedded CPU without HW exec
81 * support falls into the same category.
82 */
83
84 static pte_t set_pte_filter(pte_t pte)
85 {
86 if (radix_enabled())
87 return pte;
88
89 pte = __pte(pte_val(pte) & ~_PAGE_HPTEFLAGS);
90 if (pte_looks_normal(pte) && !(cpu_has_feature(CPU_FTR_COHERENT_ICACHE) ||
91 cpu_has_feature(CPU_FTR_NOEXECUTE))) {
92 struct page *pg = maybe_pte_to_page(pte);
93 if (!pg)
94 return pte;
95 if (!test_bit(PG_arch_1, &pg->flags)) {
96 flush_dcache_icache_page(pg);
97 set_bit(PG_arch_1, &pg->flags);
98 }
99 }
100 return pte;
101 }
102
103 static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
104 int dirty)
105 {
106 return pte;
107 }
108
109 #else /* defined(CONFIG_PPC_STD_MMU) || _PAGE_EXEC == 0 */
110
111 /* Embedded type MMU with HW exec support. This is a bit more complicated
112 * as we don't have two bits to spare for _PAGE_EXEC and _PAGE_HWEXEC so
113 * instead we "filter out" the exec permission for non clean pages.
114 */
115 static pte_t set_pte_filter(pte_t pte)
116 {
117 struct page *pg;
118
119 /* No exec permission in the first place, move on */
120 if (!(pte_val(pte) & _PAGE_EXEC) || !pte_looks_normal(pte))
121 return pte;
122
123 /* If you set _PAGE_EXEC on weird pages you're on your own */
124 pg = maybe_pte_to_page(pte);
125 if (unlikely(!pg))
126 return pte;
127
128 /* If the page clean, we move on */
129 if (test_bit(PG_arch_1, &pg->flags))
130 return pte;
131
132 /* If it's an exec fault, we flush the cache and make it clean */
133 if (is_exec_fault()) {
134 flush_dcache_icache_page(pg);
135 set_bit(PG_arch_1, &pg->flags);
136 return pte;
137 }
138
139 /* Else, we filter out _PAGE_EXEC */
140 return __pte(pte_val(pte) & ~_PAGE_EXEC);
141 }
142
143 static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
144 int dirty)
145 {
146 struct page *pg;
147
148 /* So here, we only care about exec faults, as we use them
149 * to recover lost _PAGE_EXEC and perform I$/D$ coherency
150 * if necessary. Also if _PAGE_EXEC is already set, same deal,
151 * we just bail out
152 */
153 if (dirty || (pte_val(pte) & _PAGE_EXEC) || !is_exec_fault())
154 return pte;
155
156 #ifdef CONFIG_DEBUG_VM
157 /* So this is an exec fault, _PAGE_EXEC is not set. If it was
158 * an error we would have bailed out earlier in do_page_fault()
159 * but let's make sure of it
160 */
161 if (WARN_ON(!(vma->vm_flags & VM_EXEC)))
162 return pte;
163 #endif /* CONFIG_DEBUG_VM */
164
165 /* If you set _PAGE_EXEC on weird pages you're on your own */
166 pg = maybe_pte_to_page(pte);
167 if (unlikely(!pg))
168 goto bail;
169
170 /* If the page is already clean, we move on */
171 if (test_bit(PG_arch_1, &pg->flags))
172 goto bail;
173
174 /* Clean the page and set PG_arch_1 */
175 flush_dcache_icache_page(pg);
176 set_bit(PG_arch_1, &pg->flags);
177
178 bail:
179 return __pte(pte_val(pte) | _PAGE_EXEC);
180 }
181
182 #endif /* !(defined(CONFIG_PPC_STD_MMU) || _PAGE_EXEC == 0) */
183
184 /*
185 * set_pte stores a linux PTE into the linux page table.
186 */
187 void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
188 pte_t pte)
189 {
190 /*
191 * When handling numa faults, we already have the pte marked
192 * _PAGE_PRESENT, but we can be sure that it is not in hpte.
193 * Hence we can use set_pte_at for them.
194 */
> 195 VM_WARN_ON((pte_raw(*ptep) & cpu_to_be64(_PAGE_PRESENT)) && 196 !pte_protnone(*ptep));
197
198 /* Add the pte bit when trying to set a pte */
199 pte = __pte(pte_val(pte) | _PAGE_PTE);
200
201 /* Note: mm->context.id might not yet have been assigned as
202 * this context might not have been activated yet when this
203 * is called.
204 */
205 pte = set_pte_filter(pte);
206
207 /* Perform the setting of the PTE */
208 __set_pte_at(mm, addr, ptep, pte, 0);
209 }
210
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
kbuild test robot
build botThank you for the patch! Perhaps something to improve:
Hi Aneesh,
Thank you for the patch! Perhaps something to improve:
[auto build test WARNING on powerpc/next]
[also build test WARNING on v4.18 next-20180822]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
url: https://github.com/0day-ci/linux/commits/Aneesh-Kumar-K-V/powerpc-mm-book3s-Update-pmd_present-to-look-at-_PAGE_PRESENT-bit/20180824-141837 base: https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git next config: powerpc-obs600_defconfig (attached as .config) compiler: powerpc-linux-gnu-gcc (Debian 7.2.0-11) 7.2.0
reproduce:
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross chmod +x ~/bin/make.cross
# save the attached .config to linux build tree
GCC_VERSION=7.2.0 make.cross ARCH=powerpc
All warnings (new ones prefixed by >>):
In file included from include/linux/kernel.h:15:0,
from arch/powerpc/mm/pgtable.c:24:
arch/powerpc/mm/pgtable.c: In function 'set_pte_at':
arch/powerpc/mm/pgtable.c:195:14: error: implicit declaration of function 'pte_raw'; did you mean 'pte_read'? [-Werror=implicit-function-declaration]
VM_WARN_ON((pte_raw(*ptep) & cpu_to_be64(_PAGE_PRESENT)) &&
^
include/linux/build_bug.h:36:63: note: in definition of macro 'BUILD_BUG_ON_INVALID'
#define BUILD_BUG_ON_INVALID(e) ((void)(sizeof((__force long)(e))))
^
>> arch/powerpc/mm/pgtable.c:195:2: note: in expansion of macro 'VM_WARN_ON'
VM_WARN_ON((pte_raw(*ptep) & cpu_to_be64(_PAGE_PRESENT)) &&
^~~~~~~~~~cc1: all warnings being treated as errors
vim +/VM_WARN_ON +195 arch/powerpc/mm/pgtable.c
> 24 #include <linux/kernel.h>
25 #include <linux/gfp.h>
26 #include <linux/mm.h>
27 #include <linux/percpu.h>
28 #include <linux/hardirq.h>
29 #include <linux/hugetlb.h>
30 #include <asm/pgalloc.h>
31 #include <asm/tlbflush.h>
32 #include <asm/tlb.h>
33
34 static inline int is_exec_fault(void)
35 {
36 return current->thread.regs && TRAP(current->thread.regs) == 0x400;
37 }
38
39 /* We only try to do i/d cache coherency on stuff that looks like
40 * reasonably "normal" PTEs. We currently require a PTE to be present
41 * and we avoid _PAGE_SPECIAL and cache inhibited pte. We also only do that
42 * on userspace PTEs
43 */
44 static inline int pte_looks_normal(pte_t pte)
45 {
46
47 #if defined(CONFIG_PPC_BOOK3S_64)
48 if ((pte_val(pte) & (_PAGE_PRESENT | _PAGE_SPECIAL)) == _PAGE_PRESENT) {
49 if (pte_ci(pte))
50 return 0;
51 if (pte_user(pte))
52 return 1;
53 }
54 return 0;
55 #else
56 return (pte_val(pte) &
57 (_PAGE_PRESENT | _PAGE_SPECIAL | _PAGE_NO_CACHE | _PAGE_USER |
58 _PAGE_PRIVILEGED)) ==
59 (_PAGE_PRESENT | _PAGE_USER);
60 #endif
61 }
62
63 static struct page *maybe_pte_to_page(pte_t pte)
64 {
65 unsigned long pfn = pte_pfn(pte);
66 struct page *page;
67
68 if (unlikely(!pfn_valid(pfn)))
69 return NULL;
70 page = pfn_to_page(pfn);
71 if (PageReserved(page))
72 return NULL;
73 return page;
74 }
75
76 #if defined(CONFIG_PPC_STD_MMU) || _PAGE_EXEC == 0
77
78 /* Server-style MMU handles coherency when hashing if HW exec permission
79 * is supposed per page (currently 64-bit only). If not, then, we always
80 * flush the cache for valid PTEs in set_pte. Embedded CPU without HW exec
81 * support falls into the same category.
82 */
83
84 static pte_t set_pte_filter(pte_t pte)
85 {
86 if (radix_enabled())
87 return pte;
88
89 pte = __pte(pte_val(pte) & ~_PAGE_HPTEFLAGS);
90 if (pte_looks_normal(pte) && !(cpu_has_feature(CPU_FTR_COHERENT_ICACHE) ||
91 cpu_has_feature(CPU_FTR_NOEXECUTE))) {
92 struct page *pg = maybe_pte_to_page(pte);
93 if (!pg)
94 return pte;
95 if (!test_bit(PG_arch_1, &pg->flags)) {
96 flush_dcache_icache_page(pg);
97 set_bit(PG_arch_1, &pg->flags);
98 }
99 }
100 return pte;
101 }
102
103 static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
104 int dirty)
105 {
106 return pte;
107 }
108
109 #else /* defined(CONFIG_PPC_STD_MMU) || _PAGE_EXEC == 0 */
110
111 /* Embedded type MMU with HW exec support. This is a bit more complicated
112 * as we don't have two bits to spare for _PAGE_EXEC and _PAGE_HWEXEC so
113 * instead we "filter out" the exec permission for non clean pages.
114 */
115 static pte_t set_pte_filter(pte_t pte)
116 {
117 struct page *pg;
118
119 /* No exec permission in the first place, move on */
120 if (!(pte_val(pte) & _PAGE_EXEC) || !pte_looks_normal(pte))
121 return pte;
122
123 /* If you set _PAGE_EXEC on weird pages you're on your own */
124 pg = maybe_pte_to_page(pte);
125 if (unlikely(!pg))
126 return pte;
127
128 /* If the page clean, we move on */
129 if (test_bit(PG_arch_1, &pg->flags))
130 return pte;
131
132 /* If it's an exec fault, we flush the cache and make it clean */
133 if (is_exec_fault()) {
134 flush_dcache_icache_page(pg);
135 set_bit(PG_arch_1, &pg->flags);
136 return pte;
137 }
138
139 /* Else, we filter out _PAGE_EXEC */
140 return __pte(pte_val(pte) & ~_PAGE_EXEC);
141 }
142
143 static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
144 int dirty)
145 {
146 struct page *pg;
147
148 /* So here, we only care about exec faults, as we use them
149 * to recover lost _PAGE_EXEC and perform I$/D$ coherency
150 * if necessary. Also if _PAGE_EXEC is already set, same deal,
151 * we just bail out
152 */
153 if (dirty || (pte_val(pte) & _PAGE_EXEC) || !is_exec_fault())
154 return pte;
155
156 #ifdef CONFIG_DEBUG_VM
157 /* So this is an exec fault, _PAGE_EXEC is not set. If it was
158 * an error we would have bailed out earlier in do_page_fault()
159 * but let's make sure of it
160 */
161 if (WARN_ON(!(vma->vm_flags & VM_EXEC)))
162 return pte;
163 #endif /* CONFIG_DEBUG_VM */
164
165 /* If you set _PAGE_EXEC on weird pages you're on your own */
166 pg = maybe_pte_to_page(pte);
167 if (unlikely(!pg))
168 goto bail;
169
170 /* If the page is already clean, we move on */
171 if (test_bit(PG_arch_1, &pg->flags))
172 goto bail;
173
174 /* Clean the page and set PG_arch_1 */
175 flush_dcache_icache_page(pg);
176 set_bit(PG_arch_1, &pg->flags);
177
178 bail:
179 return __pte(pte_val(pte) | _PAGE_EXEC);
180 }
181
182 #endif /* !(defined(CONFIG_PPC_STD_MMU) || _PAGE_EXEC == 0) */
183
184 /*
185 * set_pte stores a linux PTE into the linux page table.
186 */
187 void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
188 pte_t pte)
189 {
190 /*
191 * When handling numa faults, we already have the pte marked
192 * _PAGE_PRESENT, but we can be sure that it is not in hpte.
193 * Hence we can use set_pte_at for them.
194 */
> 195 VM_WARN_ON((pte_raw(*ptep) & cpu_to_be64(_PAGE_PRESENT)) && 196 !pte_protnone(*ptep));
197
198 /* Add the pte bit when trying to set a pte */
199 pte = __pte(pte_val(pte) | _PAGE_PTE);
200
201 /* Note: mm->context.id might not yet have been assigned as
202 * this context might not have been activated yet when this
203 * is called.
204 */
205 pte = set_pte_filter(pte);
206
207 /* Perform the setting of the PTE */
208 __set_pte_at(mm, addr, ptep, pte, 0);
209 }
210
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation