* Re: [PATCH v4 16/20] powerpc/mm: Extend pte_fragment functionality to nohash/32
From: Christophe LEROY @ 2018-09-25 16:48 UTC (permalink / raw)
To: Aneesh Kumar K.V, Benjamin Herrenschmidt, Paul Mackerras,
Michael Ellerman, aneesh.kumar
Cc: linux-kernel, linuxppc-dev
In-Reply-To: <89038b3e-f1cd-a4a0-481b-46cef2b5e388@linux.ibm.com>
Le 19/09/2018 à 05:03, Aneesh Kumar K.V a écrit :
> On 9/18/18 10:27 PM, Christophe Leroy wrote:
>> In order to allow the 8xx to handle pte_fragments, this patch
>> extends the use of pte_fragments to nohash/32 platforms.
>>
>> Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
>> ---
>> arch/powerpc/include/asm/mmu-40x.h | 1 +
>> arch/powerpc/include/asm/mmu-44x.h | 1 +
>> arch/powerpc/include/asm/mmu-8xx.h | 1 +
>> arch/powerpc/include/asm/mmu-book3e.h | 1 +
>> arch/powerpc/include/asm/mmu_context.h | 2 +-
>> arch/powerpc/include/asm/nohash/32/pgalloc.h | 43
>> +++++++++++-----------------
>> arch/powerpc/include/asm/nohash/32/pgtable.h | 7 +++--
>> arch/powerpc/include/asm/page.h | 6 +---
>> arch/powerpc/include/asm/pgtable.h | 8 ++++++
>> arch/powerpc/mm/Makefile | 3 ++
>> arch/powerpc/mm/mmu_context_nohash.c | 1 +
>> arch/powerpc/mm/pgtable-frag.c | 6 ++++
>> arch/powerpc/mm/pgtable_32.c | 8 ++++--
>> 13 files changed, 51 insertions(+), 37 deletions(-)
>>
>> diff --git a/arch/powerpc/include/asm/mmu-40x.h
>> b/arch/powerpc/include/asm/mmu-40x.h
>> index 74f4edb5916e..7c77ceed71d6 100644
>> --- a/arch/powerpc/include/asm/mmu-40x.h
>> +++ b/arch/powerpc/include/asm/mmu-40x.h
>> @@ -58,6 +58,7 @@ typedef struct {
>> unsigned int id;
>> unsigned int active;
>> unsigned long vdso_base;
>> + void *pte_frag;
>> } mm_context_t;
>>
>> #endif /* !__ASSEMBLY__ */
>> diff --git a/arch/powerpc/include/asm/mmu-44x.h
>> b/arch/powerpc/include/asm/mmu-44x.h
>> index 295b3dbb2698..3d72e889ae7b 100644
>> --- a/arch/powerpc/include/asm/mmu-44x.h
>> +++ b/arch/powerpc/include/asm/mmu-44x.h
>> @@ -109,6 +109,7 @@ typedef struct {
>> unsigned int id;
>> unsigned int active;
>> unsigned long vdso_base;
>> + void *pte_frag;
>> } mm_context_t;
>>
>> #endif /* !__ASSEMBLY__ */
>> diff --git a/arch/powerpc/include/asm/mmu-8xx.h
>> b/arch/powerpc/include/asm/mmu-8xx.h
>> index fa05aa566ece..750cef6f65e3 100644
>> --- a/arch/powerpc/include/asm/mmu-8xx.h
>> +++ b/arch/powerpc/include/asm/mmu-8xx.h
>> @@ -179,6 +179,7 @@ typedef struct {
>> unsigned int id;
>> unsigned int active;
>> unsigned long vdso_base;
>> + void *pte_frag;
>> #ifdef CONFIG_PPC_MM_SLICES
>> u16 user_psize; /* page size index */
>> unsigned char low_slices_psize[SLICE_ARRAY_SIZE];
>> diff --git a/arch/powerpc/include/asm/mmu-book3e.h
>> b/arch/powerpc/include/asm/mmu-book3e.h
>> index e20072972e35..8e8aad5172ab 100644
>> --- a/arch/powerpc/include/asm/mmu-book3e.h
>> +++ b/arch/powerpc/include/asm/mmu-book3e.h
>> @@ -230,6 +230,7 @@ typedef struct {
>> unsigned int id;
>> unsigned int active;
>> unsigned long vdso_base;
>> + void *pte_frag;
>> } mm_context_t;
>>
>> /* Page size definitions, common between 32 and 64-bit
>> diff --git a/arch/powerpc/include/asm/mmu_context.h
>> b/arch/powerpc/include/asm/mmu_context.h
>> index b2f89b621b15..7f2c37a3f99d 100644
>> --- a/arch/powerpc/include/asm/mmu_context.h
>> +++ b/arch/powerpc/include/asm/mmu_context.h
>> @@ -222,7 +222,7 @@ static inline int arch_dup_mmap(struct mm_struct
>> *oldmm,
>> return 0;
>> }
>>
>> -#ifndef CONFIG_PPC_BOOK3S_64
>> +#if defined(CONFIG_PPC_BOOK3E_64) || defined(CONFIG_PPC_BOOK3S_32)
>> static inline void arch_exit_mmap(struct mm_struct *mm)
>> {
>> }
>> diff --git a/arch/powerpc/include/asm/nohash/32/pgalloc.h
>> b/arch/powerpc/include/asm/nohash/32/pgalloc.h
>> index f3fec9052f31..e69423ad8e2e 100644
>> --- a/arch/powerpc/include/asm/nohash/32/pgalloc.h
>> +++ b/arch/powerpc/include/asm/nohash/32/pgalloc.h
>> @@ -27,6 +27,9 @@ extern void __bad_pte(pmd_t *pmd);
>> extern struct kmem_cache *pgtable_cache[];
>> #define PGT_CACHE(shift) pgtable_cache[shift]
>>
>> +pte_t *pte_fragment_alloc(struct mm_struct *mm, unsigned long vmaddr,
>> int kernel);
>> +void pte_fragment_free(unsigned long *table, int kernel);
>> +
>> static inline pgd_t *pgd_alloc(struct mm_struct *mm)
>> {
>> return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
>> @@ -58,11 +61,10 @@ static inline void pmd_populate_kernel(struct
>> mm_struct *mm, pmd_t *pmdp,
>> static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp,
>> pgtable_t pte_page)
>> {
>> - *pmdp = __pmd((page_to_pfn(pte_page) << PAGE_SHIFT) | _PMD_USER |
>> - _PMD_PRESENT);
>> + *pmdp = __pmd(__pa(pte_page) | _PMD_USER | _PMD_PRESENT);
>> }
>>
>> -#define pmd_pgtable(pmd) pmd_page(pmd)
>> +#define pmd_pgtable(pmd) ((pgtable_t)pmd_page_vaddr(pmd))
>> #else
>>
>> static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t
>> *pmdp,
>> @@ -74,49 +76,38 @@ static inline void pmd_populate_kernel(struct
>> mm_struct *mm, pmd_t *pmdp,
>> static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp,
>> pgtable_t pte_page)
>> {
>> - *pmdp = __pmd((unsigned long)lowmem_page_address(pte_page) |
>> _PMD_PRESENT);
>> + *pmdp = __pmd((unsigned long)pte_page | _PMD_PRESENT);
>> }
>>
>> -#define pmd_pgtable(pmd) pmd_page(pmd)
>> +#define pmd_pgtable(pmd) ((pgtable_t)pmd_page_vaddr(pmd))
>> #endif
>>
>> -static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
>> unsigned long address)
>> +static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
>> + unsigned long address)
>> {
>> - return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
>> + return (pte_t *)pte_fragment_alloc(mm, address, 1);
>> }
>>
>> -static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned
>> long address)
>> +static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
>> + unsigned long address)
>> {
>> - struct page *ptepage;
>> -
>> - gfp_t flags = GFP_KERNEL | __GFP_ZERO | __GFP_ACCOUNT;
>> -
>> - ptepage = alloc_pages(flags, 0);
>> - if (!ptepage)
>> - return NULL;
>> - if (!pgtable_page_ctor(ptepage)) {
>> - __free_page(ptepage);
>> - return NULL;
>> - }
>> - return ptepage;
>> + return (pgtable_t)pte_fragment_alloc(mm, address, 0);
>> }
>>
>> static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
>> {
>> - free_page((unsigned long)pte);
>> + pte_fragment_free((unsigned long *)pte, 1);
>> }
>>
>> static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
>> {
>> - pgtable_page_dtor(ptepage);
>> - __free_page(ptepage);
>> + pte_fragment_free((unsigned long *)ptepage, 0);
>> }
>>
>> static inline void pgtable_free(void *table, unsigned index_size)
>> {
>> if (!index_size) {
>> - pgtable_page_dtor(virt_to_page(table));
>> - free_page((unsigned long)table);
>> + pte_fragment_free((unsigned long *)table, 0);
>> } else {
>> BUG_ON(index_size > MAX_PGTABLE_INDEX_SIZE);
>> kmem_cache_free(PGT_CACHE(index_size), table);
>> @@ -155,6 +146,6 @@ static inline void __pte_free_tlb(struct
>> mmu_gather *tlb, pgtable_t table,
>> unsigned long address)
>> {
>> tlb_flush_pgtable(tlb, address);
>> - pgtable_free_tlb(tlb, page_address(table), 0);
>> + pgtable_free_tlb(tlb, table, 0);
>> }
>> #endif /* _ASM_POWERPC_PGALLOC_32_H */
>> diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h
>> b/arch/powerpc/include/asm/nohash/32/pgtable.h
>> index d2908a8038e8..73e2b1fbdb36 100644
>> --- a/arch/powerpc/include/asm/nohash/32/pgtable.h
>> +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
>> @@ -336,12 +336,12 @@ static inline int pte_young(pte_t pte)
>> */
>> #ifndef CONFIG_BOOKE
>> #define pmd_page_vaddr(pmd) \
>> - ((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
>> + ((unsigned long)__va(pmd_val(pmd) & ~(PTE_TABLE_SIZE - 1)))
>> #define pmd_page(pmd) \
>> pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)
>> #else
>> #define pmd_page_vaddr(pmd) \
>> - ((unsigned long) (pmd_val(pmd) & PAGE_MASK))
>> + ((unsigned long)(pmd_val(pmd) & ~(PTE_TABLE_SIZE - 1)))
>> #define pmd_page(pmd) \
>> pfn_to_page((__pa(pmd_val(pmd)) >> PAGE_SHIFT))
>> #endif
>> @@ -360,7 +360,8 @@ static inline int pte_young(pte_t pte)
>> (pmd_bad(*(dir)) ? NULL : (pte_t *)pmd_page_vaddr(*(dir)) + \
>> pte_index(addr))
>> #define pte_offset_map(dir, addr) \
>> - ((pte_t *) kmap_atomic(pmd_page(*(dir))) + pte_index(addr))
>> + ((pte_t *)(kmap_atomic(pmd_page(*(dir))) + \
>> + (pmd_page_vaddr(*(dir)) & ~PAGE_MASK)) + pte_index(addr))
>> #define pte_unmap(pte) kunmap_atomic(pte)
>>
>> /*
>> diff --git a/arch/powerpc/include/asm/page.h
>> b/arch/powerpc/include/asm/page.h
>> index f6a1265face2..27d1c16601ee 100644
>> --- a/arch/powerpc/include/asm/page.h
>> +++ b/arch/powerpc/include/asm/page.h
>> @@ -335,7 +335,7 @@ void arch_free_page(struct page *page, int order);
>> #endif
>>
>> struct vm_area_struct;
>> -#ifdef CONFIG_PPC_BOOK3S_64
>> +#if !defined(CONFIG_PPC_BOOK3E_64) && !defined(CONFIG_PPC_BOOK3S_32)
>> /*
>> * For BOOK3s 64 with 4k and 64K linux page size
>> * we want to use pointers, because the page table
>> @@ -343,12 +343,8 @@ struct vm_area_struct;
>> */
>> typedef pte_t *pgtable_t;
>> #else
>> -#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC64)
>> -typedef pte_t *pgtable_t;
>> -#else
>> typedef struct page *pgtable_t;
>> #endif
>> -#endif
>>
>
>
> Now that is getting complicated. Is there a way to move that to platform
> header instead of that complicated #if?
Ok, added two new patches for that in v5 (one distributes mmu-xxx.h in
platform dirs, the other moves pgtable_t typedefs in relevant files)
>
>> #include <asm-generic/memory_model.h>
>> #endif /* __ASSEMBLY__ */
>> diff --git a/arch/powerpc/include/asm/pgtable.h
>> b/arch/powerpc/include/asm/pgtable.h
>> index 8b38f7730211..1865a3e4ab8c 100644
>> --- a/arch/powerpc/include/asm/pgtable.h
>> +++ b/arch/powerpc/include/asm/pgtable.h
>> @@ -94,12 +94,20 @@ unsigned long vmalloc_to_phys(void *vmalloc_addr);
>> void pgtable_cache_add(unsigned int shift);
>> void pgtable_cache_init(void);
>>
>> +pte_t *early_alloc_pte(void);
>> +
>> #if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_PPC32)
>> void mark_initmem_nx(void);
>> #else
>> static inline void mark_initmem_nx(void) { }
>> #endif
>>
>> +#ifndef PTE_FRAG_NR
>> +#define PTE_FRAG_NR 1
>> +#define PTE_FRAG_SIZE_SHIFT PAGE_SHIFT
>> +#define PTE_FRAG_SIZE PAGE_SIZE
>> +#endif
>> +
>
> IMHO we should avoid that. The #ifndef challenge is that we should
> always make sure the header inclusion is correct so that platform
> headers get included before. Why not move it to the platform that want
> to use pte fragmentation?
Ok, in v5 functions using it now defined static inline in platform
headers so moved them there are well.
>
>
>> #endif /* __ASSEMBLY__ */
>>
>> #endif /* _ASM_POWERPC_PGTABLE_H */
>> diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
>> index bd43b3ee52cb..e1deb15fe85e 100644
>> --- a/arch/powerpc/mm/Makefile
>> +++ b/arch/powerpc/mm/Makefile
>> @@ -18,6 +18,9 @@ obj-$(CONFIG_PPC_BOOK3E_64) += pgtable-book3e.o
>> obj-$(CONFIG_PPC_BOOK3S_64) += pgtable-hash64.o hash_utils_64.o
>> slb_low.o slb.o \
>> $(hash64-y) mmu_context_book3s64.o
>> pgtable-book3s64.o \
>> pgtable-frag.o
>> +ifndef CONFIG_PPC_BOOK3S_32
>> +obj-$(CONFIG_PPC32) += pgtable-frag.o
>> +endif
>> obj-$(CONFIG_PPC_RADIX_MMU) += pgtable-radix.o tlb-radix.o
>> obj-$(CONFIG_PPC_STD_MMU_32) += ppc_mmu_32.o hash_low_32.o
>> mmu_context_hash32.o
>> obj-$(CONFIG_PPC_STD_MMU) += tlb_hash$(BITS).o
>> diff --git a/arch/powerpc/mm/mmu_context_nohash.c
>> b/arch/powerpc/mm/mmu_context_nohash.c
>> index 4d80239ef83c..98f0ef463dc8 100644
>> --- a/arch/powerpc/mm/mmu_context_nohash.c
>> +++ b/arch/powerpc/mm/mmu_context_nohash.c
>> @@ -385,6 +385,7 @@ int init_new_context(struct task_struct *t, struct
>> mm_struct *mm)
>> #endif
>> mm->context.id = MMU_NO_CONTEXT;
>> mm->context.active = 0;
>> + mm->context.pte_frag = NULL;
>> return 0;
>> }
>>
>> diff --git a/arch/powerpc/mm/pgtable-frag.c
>> b/arch/powerpc/mm/pgtable-frag.c
>> index ab4910e92aaf..d554a1cbc56d 100644
>> --- a/arch/powerpc/mm/pgtable-frag.c
>> +++ b/arch/powerpc/mm/pgtable-frag.c
>> @@ -30,6 +30,7 @@ static void pte_frag_destroy(void *pte_frag)
>> }
>> }
>>
>> +#ifdef CONFIG_PPC_BOOK3S_64
>> static void pmd_frag_destroy(void *pmd_frag)
>> {
>> int count;
>> @@ -44,6 +45,7 @@ static void pmd_frag_destroy(void *pmd_frag)
>> __free_page(page);
>> }
>> }
>> +#endif
>>
>> static void destroy_pagetable_cache(struct mm_struct *mm)
>> {
>> @@ -53,15 +55,18 @@ static void destroy_pagetable_cache(struct
>> mm_struct *mm)
>> if (frag)
>> pte_frag_destroy(frag);
>>
>> +#ifdef CONFIG_PPC_BOOK3S_64
>> frag = mm->context.pmd_frag;
>> if (frag)
>> pmd_frag_destroy(frag);
>> +#endif
>> }
>>
>> void arch_exit_mmap(struct mm_struct *mm)
>> {
>> destroy_pagetable_cache(mm);
>>
>> +#ifdef CONFIG_PPC_BOOK3S_64
>> if (radix_enabled()) {
>> /*
>> * Radix doesn't have a valid bit in the process table
>> @@ -79,6 +84,7 @@ void arch_exit_mmap(struct mm_struct *mm)
>> */
>> process_tb[mm->context.id].prtb0 = 0;
>> }
>> +#endif
>> }
>>
>
> is there a way to avoid all that #ifdef? May be redo the frag code such
> that we have few helpers that is platform independent?
Yes, in v5 reworked to keep platform specific arch_exit_mmap() and
destroy_pagetable_cache().
Christophe
>
>> static pte_t *get_pte_from_cache(struct mm_struct *mm)
>> diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
>> index 7900b613e6e5..81e6b18d1955 100644
>> --- a/arch/powerpc/mm/pgtable_32.c
>> +++ b/arch/powerpc/mm/pgtable_32.c
>> @@ -195,12 +195,16 @@ EXPORT_SYMBOL(iounmap);
>> static __init pte_t *early_pte_alloc_kernel(pmd_t *pmdp, unsigned
>> long va)
>> {
>> if (!pmd_present(*pmdp)) {
>> - pte_t *ptep = __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE));
>> + pte_t *ptep = __va(memblock_alloc(PTE_FRAG_SIZE,
>> PTE_FRAG_SIZE));
>>
>> if (!ptep)
>> return NULL;
>>
>> - clear_page(ptep);
>> + if (PTE_FRAG_SIZE == PAGE_SIZE)
>> + clear_page(ptep);
>> + else
>> + memset(ptep, 0, PTE_FRAG_SIZE);
>> +
>> pmd_populate_kernel(&init_mm, pmdp, ptep);
>> }
>> return pte_offset_kernel(pmdp, va);
>>
^ permalink raw reply
* Re: [PATCH v3 2/2] powerpc/64: add stack protector support
From: Christophe LEROY @ 2018-09-25 15:56 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
Andrew Donnellan
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <e84d65fb4744cf8260eb2fc9474765a7f3a60573.1537801613.git.christophe.leroy@c-s.fr>
Snowpatch reports failure on pmac32_defconfig, as follows:
arch/powerpc/platforms/powermac/bootx_init.o: In function `bootx_printf':
/var/lib/jenkins-slave/workspace/snowpatch/snowpatch-linux-sparse/linux/arch/powerpc/platforms/powermac/bootx_init.c:88:
undefined reference to `__stack_chk_fail_local'
arch/powerpc/platforms/powermac/bootx_init.o: In function
`bootx_add_display_props':
/var/lib/jenkins-slave/workspace/snowpatch/snowpatch-linux-sparse/linux/arch/powerpc/platforms/powermac/bootx_init.c:211:
undefined reference to `__stack_chk_fail_local'
arch/powerpc/platforms/powermac/bootx_init.o: In function
`bootx_scan_dt_build_struct':
/var/lib/jenkins-slave/workspace/snowpatch/snowpatch-linux-sparse/linux/arch/powerpc/platforms/powermac/bootx_init.c:350:
undefined reference to `__stack_chk_fail_local'
arch/powerpc/platforms/powermac/bootx_init.o: In function `bootx_init':
/var/lib/jenkins-slave/workspace/snowpatch/snowpatch-linux-sparse/linux/arch/powerpc/platforms/powermac/bootx_init.c:598:
undefined reference to `__stack_chk_fail_local'
ld: .tmp_vmlinux1: hidden symbol `__stack_chk_fail_local' isn't defined
ld: final link failed: Bad value
Makefile:1040: recipe for target 'vmlinux' failed
make: *** [vmlinux] Error 1
I don't have this issue with GCC 8.1, bootx_init.o has references to
__stack_chk_fail, not to __stack_chk_fail_local
Looking online, it may be due to an old build and a lack of 'make
clean', could it be the case here ?
Otherwise, can you retry the build to see if it's happen again ?
Christophe
Le 24/09/2018 à 17:15, Christophe Leroy a écrit :
> On PPC64, as register r13 points to the paca_struct at all time,
> this patch adds a copy of the canary there, which is copied at
> task_switch.
> That new canary is then used by using the following GCC options:
> -mstack-protector-guard=tls
> -mstack-protector-guard-reg=r13
> -mstack-protector-guard-offset=offsetof(struct paca_struct, canary))
>
> Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
> ---
> arch/powerpc/Kconfig | 2 +-
> arch/powerpc/Makefile | 8 ++++++++
> arch/powerpc/include/asm/paca.h | 3 +++
> arch/powerpc/include/asm/stackprotector.h | 3 +++
> arch/powerpc/kernel/asm-offsets.c | 3 +++
> arch/powerpc/kernel/entry_64.S | 4 ++++
> 6 files changed, 22 insertions(+), 1 deletion(-)
>
> diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
> index 3bcb05929931..602eea723624 100644
> --- a/arch/powerpc/Kconfig
> +++ b/arch/powerpc/Kconfig
> @@ -180,7 +180,7 @@ config PPC
> select HAVE_ARCH_SECCOMP_FILTER
> select HAVE_ARCH_TRACEHOOK
> select HAVE_CBPF_JIT if !PPC64
> - select HAVE_STACKPROTECTOR if $(cc-option,-mstack-protector-guard=tls) && PPC32
> + select HAVE_STACKPROTECTOR if $(cc-option,-mstack-protector-guard=tls)
> select HAVE_CONTEXT_TRACKING if PPC64
> select HAVE_DEBUG_KMEMLEAK
> select HAVE_DEBUG_STACKOVERFLOW
> diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
> index 45b8eb4d8fe7..81552c7b46eb 100644
> --- a/arch/powerpc/Makefile
> +++ b/arch/powerpc/Makefile
> @@ -113,7 +113,11 @@ KBUILD_ARFLAGS += --target=elf$(BITS)-$(GNUTARGET)
> endif
>
> cflags-$(CONFIG_STACKPROTECTOR) += -mstack-protector-guard=tls
> +ifdef CONFIG_PPC64
> +cflags-$(CONFIG_STACKPROTECTOR) += -mstack-protector-guard-reg=r13
> +else
> cflags-$(CONFIG_STACKPROTECTOR) += -mstack-protector-guard-reg=r2
> +endif
>
> LDFLAGS_vmlinux-y := -Bstatic
> LDFLAGS_vmlinux-$(CONFIG_RELOCATABLE) := -pie
> @@ -411,8 +415,12 @@ ifdef CONFIG_STACKPROTECTOR
> prepare: stack_protector_prepare
>
> stack_protector_prepare: prepare0
> +ifdef CONFIG_PPC64
> + $(eval KBUILD_CFLAGS += -mstack-protector-guard-offset=$(shell awk '{if ($$2 == "PACA_CANARY") print $$3;}' include/generated/asm-offsets.h))
> +else
> $(eval KBUILD_CFLAGS += -mstack-protector-guard-offset=$(shell awk '{if ($$2 == "TASK_CANARY") print $$3;}' include/generated/asm-offsets.h))
> endif
> +endif
>
> # Use the file '.tmp_gas_check' for binutils tests, as gas won't output
> # to stdout and these checks are run even on install targets.
> diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
> index 6d6b3706232c..98d883e58945 100644
> --- a/arch/powerpc/include/asm/paca.h
> +++ b/arch/powerpc/include/asm/paca.h
> @@ -246,6 +246,9 @@ struct paca_struct {
> struct slb_entry *mce_faulty_slbs;
> u16 slb_save_cache_ptr;
> #endif /* CONFIG_PPC_BOOK3S_64 */
> +#ifdef CONFIG_STACKPROTECTOR
> + unsigned long canary;
> +#endif
> } ____cacheline_aligned;
>
> extern struct paca_struct **paca_ptrs;
> diff --git a/arch/powerpc/include/asm/stackprotector.h b/arch/powerpc/include/asm/stackprotector.h
> index 263e2aab1862..e81991955c0d 100644
> --- a/arch/powerpc/include/asm/stackprotector.h
> +++ b/arch/powerpc/include/asm/stackprotector.h
> @@ -29,6 +29,9 @@ static __always_inline void boot_init_stack_canary(void)
> canary ^= LINUX_VERSION_CODE;
>
> current->stack_canary = canary;
> +#ifdef CONFIG_PPC64
> + get_paca()->canary = canary;
> +#endif
> }
>
> #endif /* _ASM_STACKPROTECTOR_H */
> diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
> index a992f7a53cf3..773dee55b3f6 100644
> --- a/arch/powerpc/kernel/asm-offsets.c
> +++ b/arch/powerpc/kernel/asm-offsets.c
> @@ -81,6 +81,9 @@ int main(void)
> OFFSET(MM, task_struct, mm);
> #ifdef CONFIG_STACKPROTECTOR
> OFFSET(TASK_CANARY, task_struct, stack_canary);
> +#ifdef CONFIG_PPC64
> + OFFSET(PACA_CANARY, paca_struct, canary);
> +#endif
> #endif
> OFFSET(MMCONTEXTID, mm_struct, context.id);
> #ifdef CONFIG_PPC64
> diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
> index 77a888bfcb53..573fa879d785 100644
> --- a/arch/powerpc/kernel/entry_64.S
> +++ b/arch/powerpc/kernel/entry_64.S
> @@ -624,6 +624,10 @@ _GLOBAL(_switch)
>
> addi r6,r4,-THREAD /* Convert THREAD to 'current' */
> std r6,PACACURRENT(r13) /* Set new 'current' */
> +#if defined(CONFIG_STACKPROTECTOR)
> + ld r6, TASK_CANARY(r6)
> + std r6, PACA_CANARY(r13)
> +#endif
>
> ld r8,KSP(r4) /* new stack pointer */
> #ifdef CONFIG_PPC_BOOK3S_64
>
^ permalink raw reply
* Re: [PATCH] powerpc/tm: Fix userspace r13 corruption
From: Breno Leitao @ 2018-09-25 14:32 UTC (permalink / raw)
To: Michael Neuling, mpe
Cc: linuxppc-dev, Nicholas Piggin, paulus, benh, aneesh.kumar
In-Reply-To: <1b3db7935304e6c468365562e127821306d3c7b2.camel@neuling.org>
Hi Mikey,
On 09/25/2018 02:24 AM, Michael Neuling wrote:
> On Mon, 2018-09-24 at 11:32 -0300, Breno Leitao wrote:
>> Hi Mikey,
>>
>> On 09/24/2018 04:27 AM, Michael Neuling wrote:
>>> When we treclaim we store the userspace checkpointed r13 to a scratch
>>> SPR and then later save the scratch SPR to the user thread struct.
>>>
>>> Unfortunately, this doesn't work as accessing the user thread struct
>>> can take an SLB fault and the SLB fault handler will write the same
>>> scratch SPRG that now contains the userspace r13.
>>>
>>> To fix this, we store r13 to the kernel stack (which can't fault)
>>> before we access the user thread struct.
>>>
>>> Found by running P8 guest + powervm + disable_1tb_segments + TM. Seen
>>> as a random userspace segfault with r13 looking like a kernel address.
>>>
>>> Signed-off-by: Michael Neuling <mikey@neuling.org>
>>
>> Reviewed-by: Breno Leitao <leitao@debian.org>
>>
>> I am wondering if the same problem could not happen with r1 as well, since r1
>> is kept in the paca->tm_scratch after MSR[RI] is enabled, in a code similar
>> to this:
>>
>> std r1, PACATMSCRATCH(r13)
>> ..
>> li r11, MSR_RI
>> mtmsrd r11, 1
>> ....
>> ld r3, PACATMSCRATCH(r13) /* user r1 */
>> std r3, GPR1(r7)
>>
>> There might be a corruption if the exception that is raised just after
>> MSR[RI] is enabled somehow exits through 'fast_exception_return' (being
>> called by most of the exception handlers as I understand) which will
>> overwrite paca->tm_scratch with the upcoming MSR (aka SRR1) just before the
>> SRR1, as:
>>
>> ld r3,_MSR(r1)
>>
>> ...
>> std r3, PACATMSCRATCH(r13) /* Stash returned-to MSR */
>>
>>
>> It seems that slb_miss_common and instruction_access_slb does not go through
>> this path, but handle_page_fault calls
>> ret_from_except_lite->fast_exception_return, which might cause this
>> 'possible' issue.
>
> Yeah, good catch! I think we are ok but it's delicate.
>
> I'll store it in the kernel stack and avoid PACATMSCRATCH before I turn RI on.
>
> This look ok?
Yes, That is exactly what I though when I looked at the code. Thanks for
fixing it.
^ permalink raw reply
* [PATCH] powerpc/powernv: Mark function as __noreturn
From: Breno Leitao @ 2018-09-25 14:29 UTC (permalink / raw)
To: linuxppc-dev; +Cc: npiggin, Breno Leitao
There is a mismatch between function pnv_platform_error_reboot() definition
and declaration regarding function modifiers. In the declaration part, it
contains the function attribute __noreturn, while function definition
itself lacks it.
This was reported by sparse tool as an error:
arch/powerpc/platforms/powernv/opal.c:538:6: error: symbol 'pnv_platform_error_reboot' redeclared with different type (originally declared at arch/powerpc/platforms/powernv/powernv.h:11) - different modifiers
I checked and the function is already being considered as being 'noreturn'
by the compiler, thus, I understand this patch does not change any code
being generated.
Signed-off-by: Breno Leitao <leitao@debian.org>
---
arch/powerpc/platforms/powernv/opal.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 38fe4087484a..a4641515956f 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -535,7 +535,7 @@ static int opal_recover_mce(struct pt_regs *regs,
return recovered;
}
-void pnv_platform_error_reboot(struct pt_regs *regs, const char *msg)
+void __noreturn pnv_platform_error_reboot(struct pt_regs *regs, const char *msg)
{
panic_flush_kmsg_start();
--
2.17.1
^ permalink raw reply related
* [PATCH v2] powerpc/traps: merge unrecoverable_exception() and nonrecoverable_exception()
From: Christophe Leroy @ 2018-09-25 14:10 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linux-kernel, linuxppc-dev
PPC32 uses nonrecoverable_exception() while PPC64 uses
unrecoverable_exception().
Both functions are doing almost the same thing.
This patch removes nonrecoverable_exception()
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
v2: Removed call to debugger() as die() already calls debugger()
arch/powerpc/include/asm/asm-prototypes.h | 1 -
arch/powerpc/kernel/entry_32.S | 4 ++--
arch/powerpc/kernel/traps.c | 12 ++----------
3 files changed, 4 insertions(+), 13 deletions(-)
diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index 78ed3c3f879a..2741831482f4 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -63,7 +63,6 @@ void program_check_exception(struct pt_regs *regs);
void alignment_exception(struct pt_regs *regs);
void slb_miss_bad_addr(struct pt_regs *regs);
void StackOverflow(struct pt_regs *regs);
-void nonrecoverable_exception(struct pt_regs *regs);
void kernel_fp_unavailable_exception(struct pt_regs *regs);
void altivec_unavailable_exception(struct pt_regs *regs);
void vsx_unavailable_exception(struct pt_regs *regs);
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index e58c3f467db5..77decded1175 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -794,7 +794,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_601)
lis r10,MSR_KERNEL@h
ori r10,r10,MSR_KERNEL@l
bl transfer_to_handler_full
- .long nonrecoverable_exception
+ .long unrecoverable_exception
.long ret_from_except
#endif
@@ -1297,7 +1297,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_601)
rlwinm r3,r3,0,0,30
stw r3,_TRAP(r1)
4: addi r3,r1,STACK_FRAME_OVERHEAD
- bl nonrecoverable_exception
+ bl unrecoverable_exception
/* shouldn't return */
b 4b
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 6ab66a88db14..a29575215198 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1547,14 +1547,6 @@ void StackOverflow(struct pt_regs *regs)
panic("kernel stack overflow");
}
-void nonrecoverable_exception(struct pt_regs *regs)
-{
- printk(KERN_ERR "Non-recoverable exception at PC=%lx MSR=%lx\n",
- regs->nip, regs->msr);
- debugger(regs);
- die("nonrecoverable exception", regs, SIGKILL);
-}
-
void kernel_fp_unavailable_exception(struct pt_regs *regs)
{
enum ctx_state prev_state = exception_enter();
@@ -2090,8 +2082,8 @@ void SPEFloatingPointRoundException(struct pt_regs *regs)
*/
void unrecoverable_exception(struct pt_regs *regs)
{
- printk(KERN_EMERG "Unrecoverable exception %lx at %lx\n",
- regs->trap, regs->nip);
+ pr_emerg("Unrecoverable exception %lx at %lx (msr=%lx)\n",
+ regs->trap, regs->nip, regs->msr);
die("Unrecoverable exception", regs, SIGABRT);
}
NOKPROBE_SYMBOL(unrecoverable_exception);
--
2.13.3
^ permalink raw reply related
* Re: [PATCH 1/2] iommu: Tidy up window attributes
From: Joerg Roedel @ 2018-09-25 12:55 UTC (permalink / raw)
To: Robin Murphy; +Cc: iommu, linuxppc-dev
In-Reply-To: <96e8371cc3143a58c7a142d9ff1134ba7331dd0a.1537351779.git.robin.murphy@arm.com>
On Wed, Sep 19, 2018 at 11:12:57AM +0100, Robin Murphy wrote:
> The external interface to get/set window attributes is already
> abstracted behind iommu_domain_{get,set}_attr(), so there's no real
> reason for the internal interface to be different. Since we only have
> one window-based driver anyway, clean up the core code by just moving
> the DOMAIN_ATTR_WINDOWS handling directly into the PAMU driver.
>
> Signed-off-by: Robin Murphy <robin.murphy@arm.com>
> ---
>
> Just a cleanup opportunity I spotted whilst poking around in the area.
>
> drivers/iommu/fsl_pamu_domain.c | 20 ++++++++++++++++++++
> drivers/iommu/iommu.c | 20 --------------------
> 2 files changed, 20 insertions(+), 20 deletions(-)
Nice cleanup, applied both patches, thanks Robin.
^ permalink raw reply
* Re: How to define some additional KBUILD_CFLAGS after building include/generated/asm-offsets.h ?
From: Michael Ellerman @ 2018-09-25 12:39 UTC (permalink / raw)
To: Christophe LEROY, linuxppc-dev, linux-kbuild, Masahiro Yamada,
Michal Marek, Segher Boessenkool
Cc: LKML
In-Reply-To: <87bm8m5qbs.fsf@concordia.ellerman.id.au>
Michael Ellerman <mpe@ellerman.id.au> writes:
> Christophe LEROY <christophe.leroy@c-s.fr> writes:
>> Le 24/09/2018 =C3=A0 14:10, Michael Ellerman a =C3=A9crit=C2=A0:
>>> Christophe Leroy <christophe.leroy@c-s.fr> writes:
>>>> I'm trying to implement TLS based stack protector in the Linux Kernel.
>>>> For that I need to give to GCC the offset at which it will find the
>>>> canary (register r2 is pointing to the current task struct).
>>>>
>>>> I have been able to do it with the below patch, but it only works when
>>>> include/generated/asm-offsets.h already exists from the start of the b=
uild.
>>>>
>>>> Is there a way to evaluate CANARY_OFFSET and add the stack-protector
>>>> flags to KBUILD_FLAGS only after include/generated/asm-offsets.h is bu=
ilt ?
>>>>
>>>> Or another way of add -mstack-protector-guard-offset=3Doffsetof(struct
>>>> task_struct, stack_canary) ?
>>>=20
>>> This seems to work, at least I see the value in CFLAGS:
>>>=20
>>> diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
>>> index 07d9dce..39ee113 100644
>>> --- a/arch/powerpc/Makefile
>>> +++ b/arch/powerpc/Makefile
>>> @@ -404,6 +394,11 @@ archclean:
>>>=20=20=20
>>> archprepare: checkbin
>>>=20=20=20
>>> +prepare: stack_protector_prepare
>>> +
>>> +stack_protector_prepare: prepare0
>>> + $(eval KBUILD_CFLAGS +=3D -mstack-protector-guard-offset=3D$(shell aw=
k '{if ($$2 =3D=3D "TSK_STACK_CANARY") print $$3;}' include/generated/asm-o=
ffsets.h))
>>> +
>>
>> Great, it works !
>> Thanks, I have sent v3 of the patches.
>
> Cool.
>
> It would be good to here from someone who knows Kbuild better than me if
^
hear
Still learning English.
cheers
^ permalink raw reply
* [PATCH] powerpc/numa: Use associativity if VPHN hcall is successful
From: Srikar Dronamraju @ 2018-09-25 12:25 UTC (permalink / raw)
To: Michael Ellerman, Paul Mackerras
Cc: Michael Bringmann, Satheesh Rajendran, linuxppc-dev, Harish,
Srikar Dronamraju
Currently associativity is used to lookup node-id even if the preceding
VPHN hcall failed. However this can cause CPU to be made part of the
wrong node, (most likely to be node 0). This is because VPHN is not
enabled on kvm guests.
With 2ea6263 ("powerpc/topology: Get topology for shared processors at
boot"), associativity is used to set to the wrong node. Hence KVM guest
topology is broken.
For example : A 4 node KVM guest before would have reported.
[root@localhost ~]# numactl -H
available: 4 nodes (0-3)
node 0 cpus: 0 1 2 3
node 0 size: 1746 MB
node 0 free: 1604 MB
node 1 cpus: 4 5 6 7
node 1 size: 2044 MB
node 1 free: 1765 MB
node 2 cpus: 8 9 10 11
node 2 size: 2044 MB
node 2 free: 1837 MB
node 3 cpus: 12 13 14 15
node 3 size: 2044 MB
node 3 free: 1903 MB
node distances:
node 0 1 2 3
0: 10 40 40 40
1: 40 10 40 40
2: 40 40 10 40
3: 40 40 40 10
would now report
[root@localhost ~]# numactl -H
available: 4 nodes (0-3)
node 0 cpus: 0 2 3 4 5 6 7 8 9 10 11 12 13 14 15
node 0 size: 1746 MB
node 0 free: 1244 MB
node 1 cpus:
node 1 size: 2044 MB
node 1 free: 2032 MB
node 2 cpus: 1
node 2 size: 2044 MB
node 2 free: 2028 MB
node 3 cpus:
node 3 size: 2044 MB
node 3 free: 2032 MB
node distances:
node 0 1 2 3
0: 10 40 40 40
1: 40 10 40 40
2: 40 40 10 40
3: 40 40 40 10
Fix this by skipping associativity lookup if the VPHN hcall failed.
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
---
arch/powerpc/mm/numa.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 35ac5422903a..e94148a1d7e4 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1204,7 +1204,9 @@ int find_and_online_cpu_nid(int cpu)
int new_nid;
/* Use associativity from first thread for all siblings */
- vphn_get_associativity(cpu, associativity);
+ if (vphn_get_associativity(cpu, associativity))
+ return cpu_to_node(cpu);
+
new_nid = associativity_to_nid(associativity);
if (new_nid < 0 || !node_possible(new_nid))
new_nid = first_online_node;
--
2.12.3
^ permalink raw reply related
* Re: [PATCH 2/3] powerpc: Add system call table generation support
From: Michael Ellerman @ 2018-09-25 12:25 UTC (permalink / raw)
To: Arnd Bergmann
Cc: Firoz Khan, linuxppc-dev, Benjamin Herrenschmidt, Paul Mackerras,
linuxram, leitao, Boqun Feng, gregkh, Philippe Ombredanne,
Thomas Gleixner, Kate Stewart, y2038 Mailman List,
Linux Kernel Mailing List, linux-arch, Deepa Dinamani,
Marcin Juszkiewicz
In-Reply-To: <CAK8P3a2=kxoum6hcPR2UN_St2PaFtZud_NNVkK9rHaf=N7ym-g@mail.gmail.com>
Arnd Bergmann <arnd@arndb.de> writes:
> On Tue, Sep 25, 2018 at 2:48 AM Michael Ellerman <mpe@ellerman.id.au> wrote:
>> Arnd Bergmann <arnd@arndb.de> writes:
>> > On Tue, Sep 18, 2018 at 2:15 PM Firoz Khan <firoz.khan@linaro.org> wrote:
>> >> On 14 September 2018 at 15:31, Arnd Bergmann <arnd@arndb.de> wrote:
>> >> > On Fri, Sep 14, 2018 at 10:33 AM Firoz Khan <firoz.khan@linaro.org> wrote:
>> >
>> > But all three existing architectures (x86, s390 and arm) already
>> > have the capability to parse the table and generate different output
>> > from that.
>>
>> Yeah, we want that on powerpc too.
>>
>> If the script needs to be more complex that's fine, if it can't be
>> shared across arches that's fine, the main thing for me is that wiring
>> up a syscall can be done by adding a single line in a single file.
>
> Yes, that's definitely the idea, we want to make it easier for everyone.
> We need at least a special case for mips, which needs three separate
> input files (the tables are completely different) to generate four versions
> of the output, plus a future extension to use the generic table for their
> new one.
>
> For powerpc, I'm hoping that both the table format and script can be
> completely generic and not need a special case that is different
> from the others, but if we need some extra magic to handle the SPU
> syscalls, we can still do that with a private script.
Sounds good.
cheers
^ permalink raw reply
* Re: [RFC PATCH v1 1/9] timer: fix circular header dependency
From: Christophe LEROY @ 2018-09-25 12:15 UTC (permalink / raw)
To: Mark Rutland
Cc: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar, npiggin, Thomas Gleixner, Alexander Viro,
John Stultz, Stephen Boyd, linux-fsdevel, linuxppc-dev,
linux-kernel
In-Reply-To: <20180925121104.zrz4m45sbnt5h2ht@lakrids.cambridge.arm.com>
Le 25/09/2018 à 14:11, Mark Rutland a écrit :
> On Tue, Sep 25, 2018 at 07:34:15AM +0200, Christophe LEROY wrote:
>>
>>
>> Le 24/09/2018 à 17:52, Christophe Leroy a écrit :
>>> When switching powerpc to CONFIG_THREAD_INFO_IN_TASK, include/sched.h
>>> has to be included in asm/smp.h for the following change, in order
>>> to avoid uncomplete definition of task_struct:
>>>
>>> -#define raw_smp_processor_id() (current_thread_info()->cpu)
>>> +#define raw_smp_processor_id() (current->cpu)
>>>
>>> But this generates the following compilation error, due to circular
>>> header dependency.
>>>
>>> CC kernel/time/alarmtimer.o
>>> In file included from ./arch/powerpc/include/asm/smp.h:31,
>>> from ./include/linux/smp.h:64,
>>> from ./include/linux/percpu.h:7,
>>> from ./include/linux/hrtimer.h:22,
>>> from kernel/time/alarmtimer.c:19:
>>> ./include/linux/sched.h:558:19: error: field 'dl_timer' has incomplete type
>>> struct hrtimer dl_timer;
>>> ^~~~~~~~
>>> ./include/linux/sched.h:567:17: error: field 'inactive_timer' has incomplete type
>>> struct hrtimer inactive_timer;
>>> ^~~~~~~~~~~~~~
>>> make[1]: *** [kernel/time/alarmtimer.o] Error 1
>>> make: *** [kernel/time/alarmtimer.o] Error 2
>>>
>>> CC fs/timerfd.o
>>> In file included from ./arch/powerpc/include/asm/smp.h:31,
>>> from ./include/linux/smp.h:64,
>>> from ./include/linux/percpu.h:7,
>>> from ./include/linux/hrtimer.h:22,
>>> from ./include/linux/alarmtimer.h:6,
>>> from fs/timerfd.c:12:
>>> ./include/linux/sched.h:558:19: error: field 'dl_timer' has incomplete type
>>> struct hrtimer dl_timer;
>>> ^~~~~~~~
>>> ./include/linux/sched.h:567:17: error: field 'inactive_timer' has incomplete type
>>> struct hrtimer inactive_timer;
>>> ^~~~~~~~~~~~~~
>>> make[1]: *** [fs/timerfd.o] Error 1
>>> make: *** [fs/timerfd.o] Error 2
>>>
>>> This patch fixes it by including linux/hrtimer.h after linux/sched.h
>>>
>>> Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
>>> ---
>>> Should it be fixed in powerpc instead ? In that case, how ? Any idea ?
>>
>>
>> Looks like there are several other places where the problem occurs, so it
>> has to be fixed in the powerpc headers instead.
>>
>> Seems like RISC arch faced the same issue, and fixed it the following way:
>>
>> /*
>> * This is particularly ugly: it appears we can't actually get the
>> definition
>> * of task_struct here, but we need access to the CPU this task is running
>> on.
>> * Instead of using C we're using asm-offsets.h to get the current processor
>> * ID.
>> */
>> #define raw_smp_processor_id() (*((int*)((char*)get_current() +
>> TASK_TI_CPU)))
>>
>>
>> Unless someone has a better idea, I'll fixed it that way.
>
> To solve this on arm64 we made the cpu number a percpu variable; see
> commit:
>
> 57c82954e77fa12c ("arm64: make cpu number a percpu variable")
Thanks, I'll have a look
> IIUC, you could do that by placing it in paca_struct.
By the way, it is already in PACA struct for PPC64.
The issue is with PPC32, up to now it was in current_thread_info:
#ifdef CONFIG_PPC64
#define raw_smp_processor_id() (local_paca->paca_index)
#define hard_smp_processor_id() (get_paca()->hw_cpu_id)
#else
/* 32-bit */
extern int smp_hw_index[];
#define raw_smp_processor_id() (current_thread_info()->cpu)
#define hard_smp_processor_id() (smp_hw_index[smp_processor_id()])
[..]
#endif
Christophe
^ permalink raw reply
* Re: [PATCH v2 5/6] powerpc/powernv: hold device_hotplug_lock when calling memtrace_offline_pages()
From: Balbir Singh @ 2018-09-25 12:15 UTC (permalink / raw)
To: David Hildenbrand
Cc: linux-mm, linux-kernel, linux-doc, linuxppc-dev, linux-acpi,
xen-devel, devel, Benjamin Herrenschmidt, Paul Mackerras,
Michael Ellerman, Rashmica Gupta, Michael Neuling
In-Reply-To: <20180925091457.28651-6-david@redhat.com>
On Tue, Sep 25, 2018 at 11:14:56AM +0200, David Hildenbrand wrote:
> Let's perform all checking + offlining + removing under
> device_hotplug_lock, so nobody can mess with these devices via
> sysfs concurrently.
>
> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
> Cc: Paul Mackerras <paulus@samba.org>
> Cc: Michael Ellerman <mpe@ellerman.id.au>
> Cc: Rashmica Gupta <rashmica.g@gmail.com>
> Cc: Balbir Singh <bsingharora@gmail.com>
> Cc: Michael Neuling <mikey@neuling.org>
> Reviewed-by: Pavel Tatashin <pavel.tatashin@microsoft.com>
> Reviewed-by: Rashmica Gupta <rashmica.g@gmail.com>
> Signed-off-by: David Hildenbrand <david@redhat.com>
> ---
> arch/powerpc/platforms/powernv/memtrace.c | 4 +++-
> 1 file changed, 3 insertions(+), 1 deletion(-)
>
> diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c
> index fdd48f1a39f7..d84d09c56af9 100644
> --- a/arch/powerpc/platforms/powernv/memtrace.c
> +++ b/arch/powerpc/platforms/powernv/memtrace.c
> @@ -70,6 +70,7 @@ static int change_memblock_state(struct memory_block *mem, void *arg)
> return 0;
> }
>
> +/* called with device_hotplug_lock held */
> static bool memtrace_offline_pages(u32 nid, u64 start_pfn, u64 nr_pages)
> {
> u64 end_pfn = start_pfn + nr_pages - 1;
> @@ -111,6 +112,7 @@ static u64 memtrace_alloc_node(u32 nid, u64 size)
> end_pfn = round_down(end_pfn - nr_pages, nr_pages);
>
> for (base_pfn = end_pfn; base_pfn > start_pfn; base_pfn -= nr_pages) {
> + lock_device_hotplug();
Why not grab the lock before the for loop? That way we can avoid bad cases like a
large node being scanned for a small number of pages (nr_pages). Ideally we need
a cond_resched() in the loop, but I guess offline_pages() has one.
Acked-by: Balbir Singh <bsingharora@gmail.com>
^ permalink raw reply
* Re: [RFC PATCH v1 1/9] timer: fix circular header dependency
From: Mark Rutland @ 2018-09-25 12:11 UTC (permalink / raw)
To: Christophe LEROY
Cc: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar, npiggin, Thomas Gleixner, Alexander Viro,
John Stultz, Stephen Boyd, linux-fsdevel, linuxppc-dev,
linux-kernel
In-Reply-To: <5c9530da-f5c8-e0b2-61ab-294a0da7f3fc@c-s.fr>
On Tue, Sep 25, 2018 at 07:34:15AM +0200, Christophe LEROY wrote:
>
>
> Le 24/09/2018 à 17:52, Christophe Leroy a écrit :
> > When switching powerpc to CONFIG_THREAD_INFO_IN_TASK, include/sched.h
> > has to be included in asm/smp.h for the following change, in order
> > to avoid uncomplete definition of task_struct:
> >
> > -#define raw_smp_processor_id() (current_thread_info()->cpu)
> > +#define raw_smp_processor_id() (current->cpu)
> >
> > But this generates the following compilation error, due to circular
> > header dependency.
> >
> > CC kernel/time/alarmtimer.o
> > In file included from ./arch/powerpc/include/asm/smp.h:31,
> > from ./include/linux/smp.h:64,
> > from ./include/linux/percpu.h:7,
> > from ./include/linux/hrtimer.h:22,
> > from kernel/time/alarmtimer.c:19:
> > ./include/linux/sched.h:558:19: error: field 'dl_timer' has incomplete type
> > struct hrtimer dl_timer;
> > ^~~~~~~~
> > ./include/linux/sched.h:567:17: error: field 'inactive_timer' has incomplete type
> > struct hrtimer inactive_timer;
> > ^~~~~~~~~~~~~~
> > make[1]: *** [kernel/time/alarmtimer.o] Error 1
> > make: *** [kernel/time/alarmtimer.o] Error 2
> >
> > CC fs/timerfd.o
> > In file included from ./arch/powerpc/include/asm/smp.h:31,
> > from ./include/linux/smp.h:64,
> > from ./include/linux/percpu.h:7,
> > from ./include/linux/hrtimer.h:22,
> > from ./include/linux/alarmtimer.h:6,
> > from fs/timerfd.c:12:
> > ./include/linux/sched.h:558:19: error: field 'dl_timer' has incomplete type
> > struct hrtimer dl_timer;
> > ^~~~~~~~
> > ./include/linux/sched.h:567:17: error: field 'inactive_timer' has incomplete type
> > struct hrtimer inactive_timer;
> > ^~~~~~~~~~~~~~
> > make[1]: *** [fs/timerfd.o] Error 1
> > make: *** [fs/timerfd.o] Error 2
> >
> > This patch fixes it by including linux/hrtimer.h after linux/sched.h
> >
> > Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
> > ---
> > Should it be fixed in powerpc instead ? In that case, how ? Any idea ?
>
>
> Looks like there are several other places where the problem occurs, so it
> has to be fixed in the powerpc headers instead.
>
> Seems like RISC arch faced the same issue, and fixed it the following way:
>
> /*
> * This is particularly ugly: it appears we can't actually get the
> definition
> * of task_struct here, but we need access to the CPU this task is running
> on.
> * Instead of using C we're using asm-offsets.h to get the current processor
> * ID.
> */
> #define raw_smp_processor_id() (*((int*)((char*)get_current() +
> TASK_TI_CPU)))
>
>
> Unless someone has a better idea, I'll fixed it that way.
To solve this on arm64 we made the cpu number a percpu variable; see
commit:
57c82954e77fa12c ("arm64: make cpu number a percpu variable")
IIUC, you could do that by placing it in paca_struct.
Thanks,
Mark.
^ permalink raw reply
* [RFC PATCH v2 9/9] powerpc/64: Modify CURRENT_THREAD_INFO()
From: Christophe Leroy @ 2018-09-25 12:10 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar, npiggin
Cc: linux-kernel, linuxppc-dev
In-Reply-To: <cover.1537877134.git.christophe.leroy@c-s.fr>
CURRENT_THREAD_INFO() now uses the PACA to retrieve 'current' pointer,
it doesn't use 'sp' anymore.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/exception-64s.h | 4 ++--
arch/powerpc/include/asm/thread_info.h | 2 +-
arch/powerpc/kernel/entry_64.S | 10 +++++-----
arch/powerpc/kernel/exceptions-64e.S | 2 +-
arch/powerpc/kernel/exceptions-64s.S | 2 +-
arch/powerpc/kernel/idle_book3e.S | 2 +-
arch/powerpc/kernel/idle_power4.S | 2 +-
arch/powerpc/kernel/trace/ftrace_64_mprofile.S | 6 +++---
8 files changed, 15 insertions(+), 15 deletions(-)
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 47578b79f0fb..e38d84c267b8 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -672,7 +672,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
#define RUNLATCH_ON \
BEGIN_FTR_SECTION \
- CURRENT_THREAD_INFO(r3, r1); \
+ CURRENT_THREAD_INFO(r3); \
ld r4,TI_LOCAL_FLAGS(r3); \
andi. r0,r4,_TLF_RUNLATCH; \
beql ppc64_runlatch_on_trampoline; \
@@ -722,7 +722,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CTRL)
#ifdef CONFIG_PPC_970_NAP
#define FINISH_NAP \
BEGIN_FTR_SECTION \
- CURRENT_THREAD_INFO(r11, r1); \
+ CURRENT_THREAD_INFO(r11); \
ld r9,TI_LOCAL_FLAGS(r11); \
andi. r10,r9,_TLF_NAPPING; \
bnel power4_fixup_nap; \
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 1c42df627bf3..a339de87806b 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -18,7 +18,7 @@
#define THREAD_SIZE (1 << THREAD_SHIFT)
#ifdef CONFIG_PPC64
-#define CURRENT_THREAD_INFO(dest, sp) stringify_in_c(ld dest, PACACURRENT(r13))
+#define CURRENT_THREAD_INFO(dest) stringify_in_c(ld dest, PACACURRENT(r13))
#endif
#ifndef __ASSEMBLY__
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 697406572592..331b9e9b6d78 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -158,7 +158,7 @@ system_call: /* label this so stack traces look sane */
li r10,IRQS_ENABLED
std r10,SOFTE(r1)
- CURRENT_THREAD_INFO(r11, r1)
+ CURRENT_THREAD_INFO(r11)
ld r10,TI_FLAGS(r11)
andi. r11,r10,_TIF_SYSCALL_DOTRACE
bne .Lsyscall_dotrace /* does not return */
@@ -205,7 +205,7 @@ system_call: /* label this so stack traces look sane */
ld r3,RESULT(r1)
#endif
- CURRENT_THREAD_INFO(r12, r1)
+ CURRENT_THREAD_INFO(r12)
ld r8,_MSR(r1)
#ifdef CONFIG_PPC_BOOK3S
@@ -336,7 +336,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
/* Repopulate r9 and r10 for the syscall path */
addi r9,r1,STACK_FRAME_OVERHEAD
- CURRENT_THREAD_INFO(r10, r1)
+ CURRENT_THREAD_INFO(r10)
ld r10,TI_FLAGS(r10)
cmpldi r0,NR_syscalls
@@ -731,7 +731,7 @@ _GLOBAL(ret_from_except_lite)
mtmsrd r10,1 /* Update machine state */
#endif /* CONFIG_PPC_BOOK3E */
- CURRENT_THREAD_INFO(r9, r1)
+ CURRENT_THREAD_INFO(r9)
ld r3,_MSR(r1)
#ifdef CONFIG_PPC_BOOK3E
ld r10,PACACURRENT(r13)
@@ -845,7 +845,7 @@ resume_kernel:
1: bl preempt_schedule_irq
/* Re-test flags and eventually loop */
- CURRENT_THREAD_INFO(r9, r1)
+ CURRENT_THREAD_INFO(r9)
ld r4,TI_FLAGS(r9)
andi. r0,r4,_TIF_NEED_RESCHED
bne 1b
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 231d066b4a3d..f48d9aa07a73 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -469,7 +469,7 @@ exc_##n##_bad_stack: \
* interrupts happen before the wait instruction.
*/
#define CHECK_NAPPING() \
- CURRENT_THREAD_INFO(r11, r1); \
+ CURRENT_THREAD_INFO(r11); \
ld r10,TI_LOCAL_FLAGS(r11); \
andi. r9,r10,_TLF_NAPPING; \
beq+ 1f; \
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 89d32bb79d5e..07701063d36e 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1620,7 +1620,7 @@ do_hash_page:
ori r0,r0,DSISR_BAD_FAULT_64S@l
and. r0,r4,r0 /* weird error? */
bne- handle_page_fault /* if not, try to insert a HPTE */
- CURRENT_THREAD_INFO(r11, r1)
+ CURRENT_THREAD_INFO(r11)
lwz r0,TI_PREEMPT(r11) /* If we're in an "NMI" */
andis. r0,r0,NMI_MASK@h /* (i.e. an irq when soft-disabled) */
bne 77f /* then don't call hash_page now */
diff --git a/arch/powerpc/kernel/idle_book3e.S b/arch/powerpc/kernel/idle_book3e.S
index 4e0d94d02030..23f3d927ea4f 100644
--- a/arch/powerpc/kernel/idle_book3e.S
+++ b/arch/powerpc/kernel/idle_book3e.S
@@ -63,7 +63,7 @@ _GLOBAL(\name)
1: /* Let's set the _TLF_NAPPING flag so interrupts make us return
* to the right spot
*/
- CURRENT_THREAD_INFO(r11, r1)
+ CURRENT_THREAD_INFO(r11)
ld r10,TI_LOCAL_FLAGS(r11)
ori r10,r10,_TLF_NAPPING
std r10,TI_LOCAL_FLAGS(r11)
diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S
index a09b3c7ca176..80e09f4ec056 100644
--- a/arch/powerpc/kernel/idle_power4.S
+++ b/arch/powerpc/kernel/idle_power4.S
@@ -68,7 +68,7 @@ BEGIN_FTR_SECTION
DSSALL
sync
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
- CURRENT_THREAD_INFO(r9, r1)
+ CURRENT_THREAD_INFO(r9)
ld r8,TI_LOCAL_FLAGS(r9) /* set napping bit */
ori r8,r8,_TLF_NAPPING /* so when we take an exception */
std r8,TI_LOCAL_FLAGS(r9) /* it will return to our caller */
diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
index 32476a6e4e9c..5ba39ec48cdd 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
+++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
@@ -229,7 +229,7 @@ ftrace_call:
* - r0, r11 & r12 are free
*/
livepatch_handler:
- CURRENT_THREAD_INFO(r12, r1)
+ CURRENT_THREAD_INFO(r12)
/* Allocate 3 x 8 bytes */
ld r11, TI_livepatch_sp(r12)
@@ -256,7 +256,7 @@ livepatch_handler:
* restore it.
*/
- CURRENT_THREAD_INFO(r12, r1)
+ CURRENT_THREAD_INFO(r12)
ld r11, TI_livepatch_sp(r12)
@@ -273,7 +273,7 @@ livepatch_handler:
ld r2, -24(r11)
/* Pop livepatch stack frame */
- CURRENT_THREAD_INFO(r12, r1)
+ CURRENT_THREAD_INFO(r12)
subi r11, r11, 24
std r11, TI_livepatch_sp(r12)
--
2.13.3
^ permalink raw reply related
* [RFC PATCH v2 8/9] powerpc/32: Remove CURRENT_THREAD_INFO and rename TI_CPU
From: Christophe Leroy @ 2018-09-25 12:10 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar, npiggin
Cc: linux-kernel, linuxppc-dev
In-Reply-To: <cover.1537877134.git.christophe.leroy@c-s.fr>
Now that thread_info is similar to task_struct, it's address is in r2
so CURRENT_THREAD_INFO() macro is useless. This patch removes it.
At the same time, as the 'cpu' field is not anymore in thread_info,
this patch renames it to TASK_CPU.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/smp.h | 2 +-
arch/powerpc/include/asm/thread_info.h | 2 --
arch/powerpc/kernel/asm-offsets.c | 2 +-
arch/powerpc/kernel/entry_32.S | 43 ++++++++++++----------------------
arch/powerpc/kernel/epapr_hcalls.S | 5 ++--
arch/powerpc/kernel/head_fsl_booke.S | 5 ++--
arch/powerpc/kernel/idle_6xx.S | 8 +++----
arch/powerpc/kernel/idle_e500.S | 8 +++----
arch/powerpc/kernel/misc_32.S | 3 +--
arch/powerpc/mm/hash_low_32.S | 14 ++++-------
arch/powerpc/sysdev/6xx-suspend.S | 5 ++--
11 files changed, 35 insertions(+), 62 deletions(-)
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index 202924a7c98c..1096633d0574 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -93,7 +93,7 @@ extern int smp_hw_index[];
#define raw_smp_processor_id() 0
#else
#include <asm/asm-offsets.h>
-#define raw_smp_processor_id() (*(unsigned int*)((void*)current + TI_CPU))
+#define raw_smp_processor_id() (*(unsigned int*)((void*)current + TASK_CPU))
#endif
#define hard_smp_processor_id() (smp_hw_index[smp_processor_id()])
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 62eb9ff31292..1c42df627bf3 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -19,8 +19,6 @@
#ifdef CONFIG_PPC64
#define CURRENT_THREAD_INFO(dest, sp) stringify_in_c(ld dest, PACACURRENT(r13))
-#else
-#define CURRENT_THREAD_INFO(dest, sp) stringify_in_c(mr dest, r2)
#endif
#ifndef __ASSEMBLY__
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 7bdd9fc21117..4d3aca1c9343 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -91,7 +91,7 @@ int main(void)
#endif /* CONFIG_PPC64 */
OFFSET(TASK_STACK, task_struct, stack);
#ifdef CONFIG_SMP
- OFFSET(TI_CPU, task_struct, cpu);
+ OFFSET(TASK_CPU, task_struct, cpu);
#endif
#ifdef CONFIG_LIVEPATCH
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 380c93b28090..f867885e43a2 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -168,8 +168,7 @@ transfer_to_handler:
tophys(r11,r11)
addi r11,r11,global_dbcr0@l
#ifdef CONFIG_SMP
- CURRENT_THREAD_INFO(r9, r1)
- lwz r9,TI_CPU(r9)
+ lwz r9,TASK_CPU(r2)
slwi r9,r9,3
add r11,r11,r9
#endif
@@ -180,8 +179,7 @@ transfer_to_handler:
stw r12,4(r11)
#endif
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
- CURRENT_THREAD_INFO(r9, r1)
- tophys(r9, r9)
+ tophys(r9, r2)
ACCOUNT_CPU_USER_ENTRY(r9, r11, r12)
#endif
@@ -195,8 +193,7 @@ transfer_to_handler:
ble- stack_ovf /* then the kernel stack overflowed */
5:
#if defined(CONFIG_6xx) || defined(CONFIG_E500)
- CURRENT_THREAD_INFO(r9, r1)
- tophys(r9,r9) /* check local flags */
+ tophys(r9,r2) /* check local flags */
lwz r12,TI_LOCAL_FLAGS(r9)
mtcrf 0x01,r12
bt- 31-TLF_NAPPING,4f
@@ -345,8 +342,7 @@ _GLOBAL(DoSyscall)
mtmsr r11
1:
#endif /* CONFIG_TRACE_IRQFLAGS */
- CURRENT_THREAD_INFO(r10, r1)
- lwz r11,TI_FLAGS(r10)
+ lwz r11,TI_FLAGS(r2)
andi. r11,r11,_TIF_SYSCALL_DOTRACE
bne- syscall_dotrace
syscall_dotrace_cont:
@@ -379,13 +375,12 @@ ret_from_syscall:
lwz r3,GPR3(r1)
#endif
mr r6,r3
- CURRENT_THREAD_INFO(r12, r1)
/* disable interrupts so current_thread_info()->flags can't change */
LOAD_MSR_KERNEL(r10,MSR_KERNEL) /* doesn't include MSR_EE */
/* Note: We don't bother telling lockdep about it */
SYNC
MTMSRD(r10)
- lwz r9,TI_FLAGS(r12)
+ lwz r9,TI_FLAGS(r2)
li r8,-MAX_ERRNO
andi. r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
bne- syscall_exit_work
@@ -432,8 +427,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
andi. r4,r8,MSR_PR
beq 3f
- CURRENT_THREAD_INFO(r4, r1)
- ACCOUNT_CPU_USER_EXIT(r4, r5, r7)
+ ACCOUNT_CPU_USER_EXIT(r2, r5, r7)
3:
#endif
lwz r4,_LINK(r1)
@@ -526,7 +520,7 @@ syscall_exit_work:
/* Clear per-syscall TIF flags if any are set. */
li r11,_TIF_PERSYSCALL_MASK
- addi r12,r12,TI_FLAGS
+ addi r12,r2,TI_FLAGS
3: lwarx r8,0,r12
andc r8,r8,r11
#ifdef CONFIG_IBM405_ERR77
@@ -534,7 +528,6 @@ syscall_exit_work:
#endif
stwcx. r8,0,r12
bne- 3b
- subi r12,r12,TI_FLAGS
4: /* Anything which requires enabling interrupts? */
andi. r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP)
@@ -813,8 +806,7 @@ ret_from_except:
user_exc_return: /* r10 contains MSR_KERNEL here */
/* Check current_thread_info()->flags */
- CURRENT_THREAD_INFO(r9, r1)
- lwz r9,TI_FLAGS(r9)
+ lwz r9,TI_FLAGS(r2)
andi. r0,r9,_TIF_USER_WORK_MASK
bne do_work
@@ -827,8 +819,7 @@ restore_user:
bnel- load_dbcr0
#endif
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
- CURRENT_THREAD_INFO(r9, r1)
- ACCOUNT_CPU_USER_EXIT(r9, r10, r11)
+ ACCOUNT_CPU_USER_EXIT(r2, r10, r11)
#endif
b restore
@@ -836,8 +827,7 @@ restore_user:
/* N.B. the only way to get here is from the beq following ret_from_except. */
resume_kernel:
/* check current_thread_info, _TIF_EMULATE_STACK_STORE */
- CURRENT_THREAD_INFO(r9, r1)
- lwz r8,TI_FLAGS(r9)
+ lwz r8,TI_FLAGS(r2)
andis. r0,r8,_TIF_EMULATE_STACK_STORE@h
beq+ 1f
@@ -863,7 +853,7 @@ resume_kernel:
/* Clear _TIF_EMULATE_STACK_STORE flag */
lis r11,_TIF_EMULATE_STACK_STORE@h
- addi r5,r9,TI_FLAGS
+ addi r5,r2,TI_FLAGS
0: lwarx r8,0,r5
andc r8,r8,r11
#ifdef CONFIG_IBM405_ERR77
@@ -875,7 +865,7 @@ resume_kernel:
#ifdef CONFIG_PREEMPT
/* check current_thread_info->preempt_count */
- lwz r0,TI_PREEMPT(r9)
+ lwz r0,TI_PREEMPT(r2)
cmpwi 0,r0,0 /* if non-zero, just restore regs and return */
bne restore
andi. r8,r8,_TIF_NEED_RESCHED
@@ -891,8 +881,7 @@ resume_kernel:
bl trace_hardirqs_off
#endif
1: bl preempt_schedule_irq
- CURRENT_THREAD_INFO(r9, r1)
- lwz r3,TI_FLAGS(r9)
+ lwz r3,TI_FLAGS(r2)
andi. r0,r3,_TIF_NEED_RESCHED
bne- 1b
#ifdef CONFIG_TRACE_IRQFLAGS
@@ -1191,8 +1180,7 @@ load_dbcr0:
lis r11,global_dbcr0@ha
addi r11,r11,global_dbcr0@l
#ifdef CONFIG_SMP
- CURRENT_THREAD_INFO(r9, r1)
- lwz r9,TI_CPU(r9)
+ lwz r9,TASK_CPU(r2)
slwi r9,r9,3
add r11,r11,r9
#endif
@@ -1232,8 +1220,7 @@ recheck:
LOAD_MSR_KERNEL(r10,MSR_KERNEL)
SYNC
MTMSRD(r10) /* disable interrupts */
- CURRENT_THREAD_INFO(r9, r1)
- lwz r9,TI_FLAGS(r9)
+ lwz r9,TI_FLAGS(r2)
andi. r0,r9,_TIF_NEED_RESCHED
bne- do_resched
andi. r0,r9,_TIF_USER_WORK_MASK
diff --git a/arch/powerpc/kernel/epapr_hcalls.S b/arch/powerpc/kernel/epapr_hcalls.S
index 52ca2471ee1a..d252f4663a23 100644
--- a/arch/powerpc/kernel/epapr_hcalls.S
+++ b/arch/powerpc/kernel/epapr_hcalls.S
@@ -21,10 +21,9 @@
#ifndef CONFIG_PPC64
/* epapr_ev_idle() was derived from e500_idle() */
_GLOBAL(epapr_ev_idle)
- CURRENT_THREAD_INFO(r3, r1)
- PPC_LL r4, TI_LOCAL_FLAGS(r3) /* set napping bit */
+ PPC_LL r4, TI_LOCAL_FLAGS(r2) /* set napping bit */
ori r4, r4,_TLF_NAPPING /* so when we take an exception */
- PPC_STL r4, TI_LOCAL_FLAGS(r3) /* it will return to our caller */
+ PPC_STL r4, TI_LOCAL_FLAGS(r2) /* it will return to our caller */
wrteei 1
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 21819bd64912..b5f8d0899ddc 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -244,8 +244,7 @@ set_ivor:
stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1)
#ifdef CONFIG_SMP
- CURRENT_THREAD_INFO(r22, r1)
- stw r24, TI_CPU(r22)
+ stw r24, TASK_CPU(r2)
#endif
bl early_init
@@ -704,7 +703,7 @@ finish_tlb_load:
/* Get the next_tlbcam_idx percpu var */
#ifdef CONFIG_SMP
- lwz r15, TI_CPU-THREAD(r12)
+ lwz r15, TASK_CPU-THREAD(r12)
lis r14, __per_cpu_offset@h
ori r14, r14, __per_cpu_offset@l
rlwinm r15, r15, 2, 0, 29
diff --git a/arch/powerpc/kernel/idle_6xx.S b/arch/powerpc/kernel/idle_6xx.S
index ff026c9d3cab..5afd2e236990 100644
--- a/arch/powerpc/kernel/idle_6xx.S
+++ b/arch/powerpc/kernel/idle_6xx.S
@@ -136,10 +136,9 @@ BEGIN_FTR_SECTION
DSSALL
sync
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
- CURRENT_THREAD_INFO(r9, r1)
- lwz r8,TI_LOCAL_FLAGS(r9) /* set napping bit */
+ lwz r8,TI_LOCAL_FLAGS(r2) /* set napping bit */
ori r8,r8,_TLF_NAPPING /* so when we take an exception */
- stw r8,TI_LOCAL_FLAGS(r9) /* it will return to our caller */
+ stw r8,TI_LOCAL_FLAGS(r2) /* it will return to our caller */
mfmsr r7
ori r7,r7,MSR_EE
oris r7,r7,MSR_POW@h
@@ -159,8 +158,7 @@ _GLOBAL(power_save_ppc32_restore)
stw r9,_NIP(r11) /* make it do a blr */
#ifdef CONFIG_SMP
- CURRENT_THREAD_INFO(r12, r11)
- lwz r11,TI_CPU(r12) /* get cpu number * 4 */
+ lwz r11,TASK_CPU(r2) /* get cpu number * 4 */
slwi r11,r11,2
#else
li r11,0
diff --git a/arch/powerpc/kernel/idle_e500.S b/arch/powerpc/kernel/idle_e500.S
index 583e55ac7d26..69dfcd2ca011 100644
--- a/arch/powerpc/kernel/idle_e500.S
+++ b/arch/powerpc/kernel/idle_e500.S
@@ -22,10 +22,9 @@
.text
_GLOBAL(e500_idle)
- CURRENT_THREAD_INFO(r3, r1)
- lwz r4,TI_LOCAL_FLAGS(r3) /* set napping bit */
+ lwz r4,TI_LOCAL_FLAGS(r2) /* set napping bit */
ori r4,r4,_TLF_NAPPING /* so when we take an exception */
- stw r4,TI_LOCAL_FLAGS(r3) /* it will return to our caller */
+ stw r4,TI_LOCAL_FLAGS(r2) /* it will return to our caller */
#ifdef CONFIG_PPC_E500MC
wrteei 1
@@ -88,8 +87,7 @@ _GLOBAL(power_save_ppc32_restore)
stw r9,_NIP(r11) /* make it do a blr */
#ifdef CONFIG_SMP
- CURRENT_THREAD_INFO(r12, r1)
- lwz r11,TI_CPU(r12) /* get cpu number * 4 */
+ lwz r11,TASK_CPU(r2) /* get cpu number * 4 */
slwi r11,r11,2
#else
li r11,0
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index d3ba56307eb4..0509c9a215a7 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -183,8 +183,7 @@ _GLOBAL(low_choose_750fx_pll)
#ifdef CONFIG_SMP
/* Store new HID1 image */
- CURRENT_THREAD_INFO(r6, r1)
- lwz r6,TI_CPU(r6)
+ lwz r6,TASK_CPU(r2)
slwi r6,r6,2
#else
li r6, 0
diff --git a/arch/powerpc/mm/hash_low_32.S b/arch/powerpc/mm/hash_low_32.S
index 26acf6c8c20c..27edbfddebaa 100644
--- a/arch/powerpc/mm/hash_low_32.S
+++ b/arch/powerpc/mm/hash_low_32.S
@@ -185,8 +185,7 @@ _GLOBAL(add_hash_page)
add r3,r3,r0 /* note create_hpte trims to 24 bits */
#ifdef CONFIG_SMP
- CURRENT_THREAD_INFO(r8, r1) /* use cpu number to make tag */
- lwz r8,TI_CPU(r8) /* to go in mmu_hash_lock */
+ lwz r8,TASK_CPU(r2) /* to go in mmu_hash_lock */
oris r8,r8,12
#endif /* CONFIG_SMP */
@@ -546,9 +545,8 @@ _GLOBAL(flush_hash_pages)
#ifdef CONFIG_SMP
addis r9,r7,mmu_hash_lock@ha
addi r9,r9,mmu_hash_lock@l
- CURRENT_THREAD_INFO(r8, r1)
- add r8,r8,r7
- lwz r8,TI_CPU(r8)
+ add r8,r2,r7
+ lwz r8,TASK_CPU(r8)
oris r8,r8,9
10: lwarx r0,0,r9
cmpi 0,r0,0
@@ -641,8 +639,7 @@ EXPORT_SYMBOL(flush_hash_pages)
*/
_GLOBAL(_tlbie)
#ifdef CONFIG_SMP
- CURRENT_THREAD_INFO(r8, r1)
- lwz r8,TI_CPU(r8)
+ lwz r8,TASK_CPU(r2)
oris r8,r8,11
mfmsr r10
SYNC
@@ -679,8 +676,7 @@ _GLOBAL(_tlbie)
*/
_GLOBAL(_tlbia)
#if defined(CONFIG_SMP)
- CURRENT_THREAD_INFO(r8, r1)
- lwz r8,TI_CPU(r8)
+ lwz r8,TASK_CPU(r2)
oris r8,r8,10
mfmsr r10
SYNC
diff --git a/arch/powerpc/sysdev/6xx-suspend.S b/arch/powerpc/sysdev/6xx-suspend.S
index cf48e9cb2575..6c4aec25c4ba 100644
--- a/arch/powerpc/sysdev/6xx-suspend.S
+++ b/arch/powerpc/sysdev/6xx-suspend.S
@@ -29,10 +29,9 @@ _GLOBAL(mpc6xx_enter_standby)
ori r5, r5, ret_from_standby@l
mtlr r5
- CURRENT_THREAD_INFO(r5, r1)
- lwz r6, TI_LOCAL_FLAGS(r5)
+ lwz r6, TI_LOCAL_FLAGS(r2)
ori r6, r6, _TLF_SLEEPING
- stw r6, TI_LOCAL_FLAGS(r5)
+ stw r6, TI_LOCAL_FLAGS(r2)
mfmsr r5
ori r5, r5, MSR_EE
--
2.13.3
^ permalink raw reply related
* [RFC PATCH v2 7/9] powerpc: 'current_set' is now a table of task_struct pointers
From: Christophe Leroy @ 2018-09-25 12:10 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar, npiggin
Cc: linux-kernel, linuxppc-dev
In-Reply-To: <cover.1537877134.git.christophe.leroy@c-s.fr>
The table of pointers 'current_set' has been used for retrieving
the stack and current. They used to be thread_info pointers as
they were pointing to the stack and current was taken from the
'task' field of the thread_info.
Now, the pointers of 'current_set' table are now both pointers
to task_struct and pointers to thread_info.
As they are used to get current, and the stack pointer is
retrieved from current's stack field, this patch changes
their type to task_struct, and renames secondary_ti to
secondary_current.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/asm-prototypes.h | 4 ++--
arch/powerpc/kernel/head_32.S | 6 +++---
arch/powerpc/kernel/head_44x.S | 4 ++--
arch/powerpc/kernel/head_fsl_booke.S | 4 ++--
arch/powerpc/kernel/smp.c | 10 ++++------
5 files changed, 13 insertions(+), 15 deletions(-)
diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index 78ed3c3f879a..e74d24821931 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -23,8 +23,8 @@
#include <uapi/asm/ucontext.h>
/* SMP */
-extern struct thread_info *current_set[NR_CPUS];
-extern struct thread_info *secondary_ti;
+extern struct task_struct *current_set[NR_CPUS];
+extern struct task_struct *secondary_current;
void start_secondary(void *unused);
/* kexec */
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 48beee7dc18b..d96f595f6c62 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -842,9 +842,9 @@ __secondary_start:
#endif /* CONFIG_6xx */
/* get current's stack and current */
- lis r1,secondary_ti@ha
- tophys(r1,r1)
- lwz r2,secondary_ti@l(r1)
+ lis r2,secondary_current@ha
+ tophys(r2,r2)
+ lwz r2,secondary_current@l(r2)
tophys(r1,r2)
lwz r1,TASK_STACK(r1)
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index 54891096f9f1..39e21ea1111d 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -1021,8 +1021,8 @@ _GLOBAL(start_secondary_47x)
/* Now we can get our task struct and real stack pointer */
/* Get current's stack and current */
- lis r1,secondary_ti@ha
- lwz r2,secondary_ti@l(r1)
+ lis r2,secondary_current@ha
+ lwz r2,secondary_current@l(r2)
lwz r1,TASK_STACK(r2)
/* Current stack pointer */
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index a0a26895e177..21819bd64912 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -1076,8 +1076,8 @@ __secondary_start:
bl call_setup_cpu
/* get current's stack and current */
- lis r1,secondary_ti@ha
- lwz r2,secondary_ti@l(r1)
+ lis r2,secondary_current@ha
+ lwz r2,secondary_current@l(r2)
lwz r1,TASK_STACK(r2)
/* stack */
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index f22fcbeb9898..00193643f0da 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -74,7 +74,7 @@
static DEFINE_PER_CPU(int, cpu_state) = { 0 };
#endif
-struct thread_info *secondary_ti;
+struct task_struct *secondary_current;
DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
DEFINE_PER_CPU(cpumask_var_t, cpu_l2_cache_map);
@@ -644,7 +644,7 @@ void smp_send_stop(void)
}
#endif /* CONFIG_NMI_IPI */
-struct thread_info *current_set[NR_CPUS];
+struct task_struct *current_set[NR_CPUS];
static void smp_store_cpu_info(int id)
{
@@ -724,7 +724,7 @@ void smp_prepare_boot_cpu(void)
paca_ptrs[boot_cpuid]->__current = current;
#endif
set_numa_node(numa_cpu_lookup_table[boot_cpuid]);
- current_set[boot_cpuid] = task_thread_info(current);
+ current_set[boot_cpuid] = current;
}
#ifdef CONFIG_HOTPLUG_CPU
@@ -809,15 +809,13 @@ static bool secondaries_inhibited(void)
static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle)
{
- struct thread_info *ti = task_thread_info(idle);
-
#ifdef CONFIG_PPC64
paca_ptrs[cpu]->__current = idle;
paca_ptrs[cpu]->kstack = (unsigned long)task_stack_page(idle) +
THREAD_SIZE - STACK_FRAME_OVERHEAD;
#endif
idle->cpu = cpu;
- secondary_ti = current_set[cpu] = ti;
+ secondary_current = current_set[cpu] = idle;
}
int __cpu_up(unsigned int cpu, struct task_struct *tidle)
--
2.13.3
^ permalink raw reply related
* [RFC PATCH v2 6/9] powerpc: regain entire stack space
From: Christophe Leroy @ 2018-09-25 12:10 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar, npiggin
Cc: linux-kernel, linuxppc-dev
In-Reply-To: <cover.1537877134.git.christophe.leroy@c-s.fr>
thread_info is not anymore in the stack, so the entire stack
can now be used.
In the meantime, all pointers to the stacks are not anymore
pointers to thread_info so this patch changes them to void*
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/irq.h | 10 +++++-----
arch/powerpc/include/asm/processor.h | 3 +--
arch/powerpc/kernel/asm-offsets.c | 1 -
arch/powerpc/kernel/entry_32.S | 14 ++++----------
arch/powerpc/kernel/irq.c | 19 +++++++++----------
arch/powerpc/kernel/misc_32.S | 6 ++----
arch/powerpc/kernel/process.c | 9 +++------
arch/powerpc/kernel/setup_64.c | 8 ++++----
8 files changed, 28 insertions(+), 42 deletions(-)
diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index 8108d1fe33ca..3987929408d3 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -48,9 +48,9 @@ struct pt_regs;
* Per-cpu stacks for handling critical, debug and machine check
* level interrupts.
*/
-extern struct thread_info *critirq_ctx[NR_CPUS];
-extern struct thread_info *dbgirq_ctx[NR_CPUS];
-extern struct thread_info *mcheckirq_ctx[NR_CPUS];
+extern void *critirq_ctx[NR_CPUS];
+extern void *dbgirq_ctx[NR_CPUS];
+extern void *mcheckirq_ctx[NR_CPUS];
extern void exc_lvl_ctx_init(void);
#else
#define exc_lvl_ctx_init()
@@ -59,8 +59,8 @@ extern void exc_lvl_ctx_init(void);
/*
* Per-cpu stacks for handling hard and soft interrupts.
*/
-extern struct thread_info *hardirq_ctx[NR_CPUS];
-extern struct thread_info *softirq_ctx[NR_CPUS];
+extern void *hardirq_ctx[NR_CPUS];
+extern void *softirq_ctx[NR_CPUS];
extern void irq_ctx_init(void);
extern void call_do_softirq(void *tp);
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 31873614392f..834d0d701e19 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -332,8 +332,7 @@ struct thread_struct {
#define ARCH_MIN_TASKALIGN 16
#define INIT_SP (sizeof(init_stack) + (unsigned long) &init_stack)
-#define INIT_SP_LIMIT \
- (_ALIGN_UP(sizeof(struct thread_info), 16) + (unsigned long) &init_stack)
+#define INIT_SP_LIMIT ((unsigned long) &init_stack)
#ifdef CONFIG_SPE
#define SPEFSCR_INIT \
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index f8abb7501704..7bdd9fc21117 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -87,7 +87,6 @@ int main(void)
DEFINE(NMI_MASK, NMI_MASK);
OFFSET(TASKTHREADPPR, task_struct, thread.ppr);
#else
- DEFINE(THREAD_INFO_GAP, _ALIGN_UP(sizeof(struct thread_info), 16));
OFFSET(KSP_LIMIT, thread_struct, ksp_limit);
#endif /* CONFIG_PPC64 */
OFFSET(TASK_STACK, task_struct, stack);
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index ec71c93589da..380c93b28090 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -97,14 +97,11 @@ crit_transfer_to_handler:
mfspr r0,SPRN_SRR1
stw r0,_SRR1(r11)
- /* set the stack limit to the current stack
- * and set the limit to protect the thread_info
- * struct
- */
+ /* set the stack limit to the current stack */
mfspr r8,SPRN_SPRG_THREAD
lwz r0,KSP_LIMIT(r8)
stw r0,SAVED_KSP_LIMIT(r11)
- rlwimi r0,r1,0,0,(31-THREAD_SHIFT)
+ rlwinm r0,r1,0,0,(31 - THREAD_SHIFT)
stw r0,KSP_LIMIT(r8)
/* fall through */
#endif
@@ -121,14 +118,11 @@ crit_transfer_to_handler:
mfspr r0,SPRN_SRR1
stw r0,crit_srr1@l(0)
- /* set the stack limit to the current stack
- * and set the limit to protect the thread_info
- * struct
- */
+ /* set the stack limit to the current stack */
mfspr r8,SPRN_SPRG_THREAD
lwz r0,KSP_LIMIT(r8)
stw r0,saved_ksp_limit@l(0)
- rlwimi r0,r1,0,0,(31-THREAD_SHIFT)
+ rlwinm r0,r1,0,0,(31 - THREAD_SHIFT)
stw r0,KSP_LIMIT(r8)
/* fall through */
#endif
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 699f0f816687..00dbee440bc2 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -618,9 +618,8 @@ static inline void check_stack_overflow(void)
sp = current_stack_pointer() & (THREAD_SIZE-1);
/* check for stack overflow: is there less than 2KB free? */
- if (unlikely(sp < (sizeof(struct thread_info) + 2048))) {
- pr_err("do_IRQ: stack overflow: %ld\n",
- sp - sizeof(struct thread_info));
+ if (unlikely(sp < 2048)) {
+ pr_err("do_IRQ: stack overflow: %ld\n", sp);
dump_stack();
}
#endif
@@ -660,7 +659,7 @@ void __do_irq(struct pt_regs *regs)
void do_IRQ(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
- struct thread_info *curtp, *irqtp, *sirqtp;
+ void *curtp, *irqtp, *sirqtp;
/* Switch to the irq stack to handle this */
curtp = (void*)(current_stack_pointer() & ~(THREAD_SIZE - 1));
@@ -690,9 +689,9 @@ void __init init_IRQ(void)
}
#if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
-struct thread_info *critirq_ctx[NR_CPUS] __read_mostly;
-struct thread_info *dbgirq_ctx[NR_CPUS] __read_mostly;
-struct thread_info *mcheckirq_ctx[NR_CPUS] __read_mostly;
+void *critirq_ctx[NR_CPUS] __read_mostly;
+void *dbgirq_ctx[NR_CPUS] __read_mostly;
+void *mcheckirq_ctx[NR_CPUS] __read_mostly;
void exc_lvl_ctx_init(void)
{
@@ -718,8 +717,8 @@ void exc_lvl_ctx_init(void)
}
#endif
-struct thread_info *softirq_ctx[NR_CPUS] __read_mostly;
-struct thread_info *hardirq_ctx[NR_CPUS] __read_mostly;
+void *softirq_ctx[NR_CPUS] __read_mostly;
+void *hardirq_ctx[NR_CPUS] __read_mostly;
void irq_ctx_init(void)
{
@@ -733,7 +732,7 @@ void irq_ctx_init(void)
void do_softirq_own_stack(void)
{
- struct thread_info *irqtp;
+ void *irqtp;
irqtp = softirq_ctx[smp_processor_id()];
call_do_softirq(irqtp);
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 24a7f18ea10c..d3ba56307eb4 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -46,11 +46,10 @@ _GLOBAL(call_do_softirq)
mflr r0
stw r0,4(r1)
lwz r10,THREAD+KSP_LIMIT(r2)
- addi r11,r3,THREAD_INFO_GAP
+ stw r3, THREAD+KSP_LIMIT(r2)
stwu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3)
mr r1,r3
stw r10,8(r1)
- stw r11,THREAD+KSP_LIMIT(r2)
bl __do_softirq
lwz r10,8(r1)
lwz r1,0(r1)
@@ -66,11 +65,10 @@ _GLOBAL(call_do_irq)
mflr r0
stw r0,4(r1)
lwz r10,THREAD+KSP_LIMIT(r2)
- addi r11,r4,THREAD_INFO_GAP
+ stw r4, THREAD+KSP_LIMIT(r2)
stwu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
mr r1,r4
stw r10,8(r1)
- stw r11,THREAD+KSP_LIMIT(r2)
bl __do_irq
lwz r10,8(r1)
lwz r1,0(r1)
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 111abb4df2ec..1e01bf42dc82 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1691,8 +1691,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
sp -= STACK_FRAME_OVERHEAD;
p->thread.ksp = sp;
#ifdef CONFIG_PPC32
- p->thread.ksp_limit = (unsigned long)task_stack_page(p) +
- _ALIGN_UP(sizeof(struct thread_info), 16);
+ p->thread.ksp_limit = (unsigned long)task_stack_page(p);
#endif
#ifdef CONFIG_HAVE_HW_BREAKPOINT
p->thread.ptrace_bps[0] = NULL;
@@ -2001,13 +2000,11 @@ static inline int valid_irq_stack(unsigned long sp, struct task_struct *p,
*/
if (cpu < NR_CPUS && cpu_possible(cpu)) {
stack_page = (unsigned long) hardirq_ctx[cpu];
- if (sp >= stack_page + sizeof(struct thread_struct)
- && sp <= stack_page + THREAD_SIZE - nbytes)
+ if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
return 1;
stack_page = (unsigned long) softirq_ctx[cpu];
- if (sp >= stack_page + sizeof(struct thread_struct)
- && sp <= stack_page + THREAD_SIZE - nbytes)
+ if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
return 1;
}
return 0;
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 2d682f3e31c6..6792e9c90689 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -717,22 +717,22 @@ void __init emergency_stack_init(void)
limit = min(ppc64_bolted_size(), ppc64_rma_size);
for_each_possible_cpu(i) {
- struct thread_info *ti;
+ void *ti;
ti = alloc_stack(limit, i);
memset(ti, 0, THREAD_SIZE);
- paca_ptrs[i]->emergency_sp = (void *)ti + THREAD_SIZE;
+ paca_ptrs[i]->emergency_sp = ti + THREAD_SIZE;
#ifdef CONFIG_PPC_BOOK3S_64
/* emergency stack for NMI exception handling. */
ti = alloc_stack(limit, i);
memset(ti, 0, THREAD_SIZE);
- paca_ptrs[i]->nmi_emergency_sp = (void *)ti + THREAD_SIZE;
+ paca_ptrs[i]->nmi_emergency_sp = ti + THREAD_SIZE;
/* emergency stack for machine check exception handling. */
ti = alloc_stack(limit, i);
memset(ti, 0, THREAD_SIZE);
- paca_ptrs[i]->mc_emergency_sp = (void *)ti + THREAD_SIZE;
+ paca_ptrs[i]->mc_emergency_sp = ti + THREAD_SIZE;
#endif
}
}
--
2.13.3
^ permalink raw reply related
* [RFC PATCH v2 5/9] powerpc: Activate CONFIG_THREAD_INFO_IN_TASK
From: Christophe Leroy @ 2018-09-25 12:10 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar, npiggin
Cc: linux-kernel, linuxppc-dev
In-Reply-To: <cover.1537877134.git.christophe.leroy@c-s.fr>
This patch activates CONFIG_THREAD_INFO_IN_TASK which
moves the thread_info into task_struct.
Moving thread_info into task_struct has the following advantages:
- It protects thread_info from corruption in the case of stack
overflows.
- Its address is harder to determine if stack addresses are
leaked, making a number of attacks more difficult.
This has the following consequences:
- thread_info is now located at the top of task_struct.
- The 'cpu' field is now in task_struct, and only exists when
CONFIG_SMP is active.
- thread_info doesn't have anymore the 'task' field.
This patch:
- Removes all recopy of thread_info struct when the stack changes.
- Changes the CURRENT_THREAD_INFO() macro to point to current.
- Selects CONFIG_THREAD_INFO_IN_TASK
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/Kconfig | 1 +
arch/powerpc/include/asm/smp.h | 14 +++++++++-
arch/powerpc/include/asm/thread_info.h | 17 ++----------
arch/powerpc/kernel/asm-offsets.c | 7 +++--
arch/powerpc/kernel/entry_32.S | 9 +++----
arch/powerpc/kernel/exceptions-64e.S | 11 --------
arch/powerpc/kernel/head_32.S | 6 ++---
arch/powerpc/kernel/head_44x.S | 4 +--
arch/powerpc/kernel/head_64.S | 1 +
arch/powerpc/kernel/head_booke.h | 8 +-----
arch/powerpc/kernel/head_fsl_booke.S | 7 +++--
arch/powerpc/kernel/irq.c | 47 +---------------------------------
arch/powerpc/kernel/kgdb.c | 28 --------------------
arch/powerpc/kernel/machine_kexec_64.c | 6 ++---
arch/powerpc/kernel/setup-common.c | 2 +-
arch/powerpc/kernel/setup_64.c | 21 ---------------
arch/powerpc/kernel/smp.c | 2 +-
17 files changed, 40 insertions(+), 151 deletions(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index a80669209155..c6c0b91ebd33 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -237,6 +237,7 @@ config PPC
select RTC_LIB
select SPARSE_IRQ
select SYSCTL_EXCEPTION_TRACE
+ select THREAD_INFO_IN_TASK
select VIRT_TO_BUS if !PPC64
#
# Please keep this list sorted alphabetically.
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index 95b66a0c639b..202924a7c98c 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -83,7 +83,19 @@ int is_cpu_dead(unsigned int cpu);
/* 32-bit */
extern int smp_hw_index[];
-#define raw_smp_processor_id() (current_thread_info()->cpu)
+/*
+ * This is particularly ugly: it appears we can't actually get the definition
+ * of task_struct here, but we need access to the CPU this task is running on.
+ * Instead of using task_struct we're using asm-offsets.h to get the current
+ * processor ID.
+ */
+#ifdef GENERATING_ASM_OFFSETS
+#define raw_smp_processor_id() 0
+#else
+#include <asm/asm-offsets.h>
+#define raw_smp_processor_id() (*(unsigned int*)((void*)current + TI_CPU))
+#endif
+
#define hard_smp_processor_id() (smp_hw_index[smp_processor_id()])
static inline int get_hard_smp_processor_id(int cpu)
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 406eb952b808..62eb9ff31292 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -18,9 +18,9 @@
#define THREAD_SIZE (1 << THREAD_SHIFT)
#ifdef CONFIG_PPC64
-#define CURRENT_THREAD_INFO(dest, sp) stringify_in_c(clrrdi dest, sp, THREAD_SHIFT)
+#define CURRENT_THREAD_INFO(dest, sp) stringify_in_c(ld dest, PACACURRENT(r13))
#else
-#define CURRENT_THREAD_INFO(dest, sp) stringify_in_c(rlwinm dest, sp, 0, 0, 31-THREAD_SHIFT)
+#define CURRENT_THREAD_INFO(dest, sp) stringify_in_c(mr dest, r2)
#endif
#ifndef __ASSEMBLY__
@@ -34,8 +34,6 @@
* low level task data.
*/
struct thread_info {
- struct task_struct *task; /* main task structure */
- int cpu; /* cpu we're on */
int preempt_count; /* 0 => preemptable,
<0 => BUG */
unsigned long local_flags; /* private flags for thread */
@@ -58,8 +56,6 @@ struct thread_info {
*/
#define INIT_THREAD_INFO(tsk) \
{ \
- .task = &tsk, \
- .cpu = 0, \
.preempt_count = INIT_PREEMPT_COUNT, \
.flags = 0, \
}
@@ -67,15 +63,6 @@ struct thread_info {
#define THREAD_SIZE_ORDER (THREAD_SHIFT - PAGE_SHIFT)
/* how to get the thread information struct from C */
-static inline struct thread_info *current_thread_info(void)
-{
- unsigned long val;
-
- asm (CURRENT_THREAD_INFO(%0,1) : "=r" (val));
-
- return (struct thread_info *)val;
-}
-
extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
#ifdef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 3c649a6529eb..f8abb7501704 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -13,6 +13,8 @@
* 2 of the License, or (at your option) any later version.
*/
+#define GENERATING_ASM_OFFSETS
+
#include <linux/compat.h>
#include <linux/signal.h>
#include <linux/sched.h>
@@ -89,6 +91,9 @@ int main(void)
OFFSET(KSP_LIMIT, thread_struct, ksp_limit);
#endif /* CONFIG_PPC64 */
OFFSET(TASK_STACK, task_struct, stack);
+#ifdef CONFIG_SMP
+ OFFSET(TI_CPU, task_struct, cpu);
+#endif
#ifdef CONFIG_LIVEPATCH
OFFSET(TI_livepatch_sp, thread_info, livepatch_sp);
@@ -156,8 +161,6 @@ int main(void)
OFFSET(TI_FLAGS, thread_info, flags);
OFFSET(TI_LOCAL_FLAGS, thread_info, local_flags);
OFFSET(TI_PREEMPT, thread_info, preempt_count);
- OFFSET(TI_TASK, thread_info, task);
- OFFSET(TI_CPU, thread_info, cpu);
#ifdef CONFIG_PPC64
OFFSET(DCACHEL1BLOCKSIZE, ppc64_caches, l1d.block_size);
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 83f3d3e977a9..ec71c93589da 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -1166,10 +1166,6 @@ ret_from_debug_exc:
mfspr r9,SPRN_SPRG_THREAD
lwz r10,SAVED_KSP_LIMIT(r1)
stw r10,KSP_LIMIT(r9)
- lwz r9,TASK_STACK-THREAD(r9)
- CURRENT_THREAD_INFO(r10, r1)
- lwz r10,TI_PREEMPT(r10)
- stw r10,TI_PREEMPT(r9)
RESTORE_xSRR(SRR0,SRR1);
RESTORE_xSRR(CSRR0,CSRR1);
RESTORE_MMU_REGS;
@@ -1292,10 +1288,13 @@ BEGIN_FTR_SECTION
END_FTR_SECTION_IFSET(CPU_FTR_601)
lwz r3,_TRAP(r1)
andi. r0,r3,1
- beq 4f
+ beq 5f
SAVE_NVGPRS(r1)
rlwinm r3,r3,0,0,30
stw r3,_TRAP(r1)
+5: mfspr r2,SPRN_SPRG_THREAD
+ addi r2,r2,-THREAD
+ tovirt(r2,r2) /* set back r2 to current */
4: addi r3,r1,STACK_FRAME_OVERHEAD
bl nonrecoverable_exception
/* shouldn't return */
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 6d6e144a28ce..231d066b4a3d 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -77,17 +77,6 @@ special_reg_save:
andi. r3,r3,MSR_PR
bnelr
- /* Copy info into temporary exception thread info */
- ld r11,PACAKSAVE(r13)
- CURRENT_THREAD_INFO(r11, r11)
- CURRENT_THREAD_INFO(r12, r1)
- ld r10,TI_FLAGS(r11)
- std r10,TI_FLAGS(r12)
- ld r10,TI_PREEMPT(r11)
- std r10,TI_PREEMPT(r12)
- ld r10,TI_TASK(r11)
- std r10,TI_TASK(r12)
-
/*
* Advance to the next TLB exception frame for handler
* types that don't do it automatically.
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 8fdb8c8bb1b4..48beee7dc18b 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -844,9 +844,9 @@ __secondary_start:
/* get current's stack and current */
lis r1,secondary_ti@ha
tophys(r1,r1)
- lwz r1,secondary_ti@l(r1)
- tophys(r2,r1)
- lwz r2,TI_TASK(r2)
+ lwz r2,secondary_ti@l(r1)
+ tophys(r1,r2)
+ lwz r1,TASK_STACK(r1)
/* stack */
addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index d033311e18d9..54891096f9f1 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -1022,8 +1022,8 @@ _GLOBAL(start_secondary_47x)
/* Get current's stack and current */
lis r1,secondary_ti@ha
- lwz r1,secondary_ti@l(r1)
- lwz r2,TI_TASK(r1)
+ lwz r2,secondary_ti@l(r1)
+ lwz r1,TASK_STACK(r2)
/* Current stack pointer */
addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index cf9437aafe58..2ecd5625030e 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -805,6 +805,7 @@ __secondary_start:
LOAD_REG_ADDR(r3, current_set)
sldi r28,r24,3 /* get current_set[cpu#] */
ldx r14,r3,r28
+ ld r14,TASK_STACK(r14)
addi r14,r14,THREAD_SIZE-STACK_FRAME_OVERHEAD
std r14,PACAKSAVE(r13)
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index 20fe0c93a0bd..9f7f10896928 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -143,13 +143,7 @@
stw r10,GPR11(r11); \
b 2f; \
/* COMING FROM PRIV MODE */ \
-1: lwz r9,TI_FLAGS-EXC_LVL_FRAME_OVERHEAD(r11); \
- lwz r10,TI_PREEMPT-EXC_LVL_FRAME_OVERHEAD(r11); \
- stw r9,TI_FLAGS-EXC_LVL_FRAME_OVERHEAD(r8); \
- stw r10,TI_PREEMPT-EXC_LVL_FRAME_OVERHEAD(r8); \
- lwz r9,TI_TASK-EXC_LVL_FRAME_OVERHEAD(r11); \
- stw r9,TI_TASK-EXC_LVL_FRAME_OVERHEAD(r8); \
- mr r11,r8; \
+1: mr r11,r8; \
2: mfspr r8,SPRN_SPRG_RSCRATCH_##exc_level; \
stw r12,GPR12(r11); /* save various registers */\
mflr r10; \
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 27243aff1722..a0a26895e177 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -704,8 +704,7 @@ finish_tlb_load:
/* Get the next_tlbcam_idx percpu var */
#ifdef CONFIG_SMP
- lwz r12, TASK_STACK-THREAD(r12)
- lwz r15, TI_CPU(r12)
+ lwz r15, TI_CPU-THREAD(r12)
lis r14, __per_cpu_offset@h
ori r14, r14, __per_cpu_offset@l
rlwinm r15, r15, 2, 0, 29
@@ -1078,8 +1077,8 @@ __secondary_start:
/* get current's stack and current */
lis r1,secondary_ti@ha
- lwz r1,secondary_ti@l(r1)
- lwz r2,TI_TASK(r1)
+ lwz r2,secondary_ti@l(r1)
+ lwz r1,TASK_STACK(r2)
/* stack */
addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index aa53db3ba6e7..699f0f816687 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -673,24 +673,9 @@ void do_IRQ(struct pt_regs *regs)
set_irq_regs(old_regs);
return;
}
-
- /* Prepare the thread_info in the irq stack */
- irqtp->task = curtp->task;
- irqtp->flags = 0;
-
- /* Copy the preempt_count so that the [soft]irq checks work. */
- irqtp->preempt_count = curtp->preempt_count;
-
/* Switch stack and call */
call_do_irq(regs, irqtp);
- /* Restore stack limit */
- irqtp->task = NULL;
-
- /* Copy back updates to the thread_info */
- if (irqtp->flags)
- set_bits(irqtp->flags, &curtp->flags);
-
set_irq_regs(old_regs);
}
@@ -711,7 +696,6 @@ struct thread_info *mcheckirq_ctx[NR_CPUS] __read_mostly;
void exc_lvl_ctx_init(void)
{
- struct thread_info *tp;
int i, cpu_nr;
for_each_possible_cpu(i) {
@@ -726,20 +710,9 @@ void exc_lvl_ctx_init(void)
#endif
memset((void *)critirq_ctx[cpu_nr], 0, THREAD_SIZE);
- tp = critirq_ctx[cpu_nr];
- tp->cpu = cpu_nr;
- tp->preempt_count = 0;
-
#ifdef CONFIG_BOOKE
memset((void *)dbgirq_ctx[cpu_nr], 0, THREAD_SIZE);
- tp = dbgirq_ctx[cpu_nr];
- tp->cpu = cpu_nr;
- tp->preempt_count = 0;
-
memset((void *)mcheckirq_ctx[cpu_nr], 0, THREAD_SIZE);
- tp = mcheckirq_ctx[cpu_nr];
- tp->cpu = cpu_nr;
- tp->preempt_count = HARDIRQ_OFFSET;
#endif
}
}
@@ -750,38 +723,20 @@ struct thread_info *hardirq_ctx[NR_CPUS] __read_mostly;
void irq_ctx_init(void)
{
- struct thread_info *tp;
int i;
for_each_possible_cpu(i) {
memset((void *)softirq_ctx[i], 0, THREAD_SIZE);
- tp = softirq_ctx[i];
- tp->cpu = i;
- klp_init_thread_info(tp);
-
memset((void *)hardirq_ctx[i], 0, THREAD_SIZE);
- tp = hardirq_ctx[i];
- tp->cpu = i;
- klp_init_thread_info(tp);
}
}
void do_softirq_own_stack(void)
{
- struct thread_info *curtp, *irqtp;
+ struct thread_info *irqtp;
- curtp = current_thread_info();
irqtp = softirq_ctx[smp_processor_id()];
- irqtp->task = curtp->task;
- irqtp->flags = 0;
call_do_softirq(irqtp);
- irqtp->task = NULL;
-
- /* Set any flag that may have been set on the
- * alternate stack
- */
- if (irqtp->flags)
- set_bits(irqtp->flags, &curtp->flags);
}
irq_hw_number_t virq_to_hw(unsigned int virq)
diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c
index 59c578f865aa..5056e54b5239 100644
--- a/arch/powerpc/kernel/kgdb.c
+++ b/arch/powerpc/kernel/kgdb.c
@@ -151,41 +151,13 @@ static int kgdb_handle_breakpoint(struct pt_regs *regs)
return 1;
}
-static DEFINE_PER_CPU(struct thread_info, kgdb_thread_info);
static int kgdb_singlestep(struct pt_regs *regs)
{
- struct thread_info *thread_info, *exception_thread_info;
- struct thread_info *backup_current_thread_info =
- this_cpu_ptr(&kgdb_thread_info);
-
if (user_mode(regs))
return 0;
- /*
- * On Book E and perhaps other processors, singlestep is handled on
- * the critical exception stack. This causes current_thread_info()
- * to fail, since it it locates the thread_info by masking off
- * the low bits of the current stack pointer. We work around
- * this issue by copying the thread_info from the kernel stack
- * before calling kgdb_handle_exception, and copying it back
- * afterwards. On most processors the copy is avoided since
- * exception_thread_info == thread_info.
- */
- thread_info = (struct thread_info *)(regs->gpr[1] & ~(THREAD_SIZE-1));
- exception_thread_info = current_thread_info();
-
- if (thread_info != exception_thread_info) {
- /* Save the original current_thread_info. */
- memcpy(backup_current_thread_info, exception_thread_info, sizeof *thread_info);
- memcpy(exception_thread_info, thread_info, sizeof *thread_info);
- }
-
kgdb_handle_exception(0, SIGTRAP, 0, regs);
- if (thread_info != exception_thread_info)
- /* Restore current_thread_info lastly. */
- memcpy(exception_thread_info, backup_current_thread_info, sizeof *thread_info);
-
return 1;
}
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index a0f6f45005bd..75692c327ba0 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -317,10 +317,8 @@ void default_machine_kexec(struct kimage *image)
* We setup preempt_count to avoid using VMX in memcpy.
* XXX: the task struct will likely be invalid once we do the copy!
*/
- kexec_stack.thread_info.task = current_thread_info()->task;
- kexec_stack.thread_info.flags = 0;
- kexec_stack.thread_info.preempt_count = HARDIRQ_OFFSET;
- kexec_stack.thread_info.cpu = current_thread_info()->cpu;
+ current_thread_info()->flags = 0;
+ current_thread_info()->preempt_count = HARDIRQ_OFFSET;
/* We need a static PACA, too; copy this CPU's PACA over and switch to
* it. Also poison per_cpu_offset and NULL lppaca to catch anyone using
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 93fa0c99681e..d84351ad1379 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -939,7 +939,7 @@ void __init setup_arch(char **cmdline_p)
/* Reserve large chunks of memory for use by CMA for KVM. */
kvm_cma_reserve();
- klp_init_thread_info(&init_thread_info);
+ klp_init_thread_info(&init_task.thread_info);
init_mm.start_code = (unsigned long)_stext;
init_mm.end_code = (unsigned long) _etext;
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index faf00222b324..2d682f3e31c6 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -691,24 +691,6 @@ void __init exc_lvl_early_init(void)
#endif
/*
- * Emergency stacks are used for a range of things, from asynchronous
- * NMIs (system reset, machine check) to synchronous, process context.
- * We set preempt_count to zero, even though that isn't necessarily correct. To
- * get the right value we'd need to copy it from the previous thread_info, but
- * doing that might fault causing more problems.
- * TODO: what to do with accounting?
- */
-static void emerg_stack_init_thread_info(struct thread_info *ti, int cpu)
-{
- ti->task = NULL;
- ti->cpu = cpu;
- ti->preempt_count = 0;
- ti->local_flags = 0;
- ti->flags = 0;
- klp_init_thread_info(ti);
-}
-
-/*
* Stack space used when we detect a bad kernel stack pointer, and
* early in SMP boots before relocation is enabled. Exclusive emergency
* stack for machine checks.
@@ -739,20 +721,17 @@ void __init emergency_stack_init(void)
ti = alloc_stack(limit, i);
memset(ti, 0, THREAD_SIZE);
- emerg_stack_init_thread_info(ti, i);
paca_ptrs[i]->emergency_sp = (void *)ti + THREAD_SIZE;
#ifdef CONFIG_PPC_BOOK3S_64
/* emergency stack for NMI exception handling. */
ti = alloc_stack(limit, i);
memset(ti, 0, THREAD_SIZE);
- emerg_stack_init_thread_info(ti, i);
paca_ptrs[i]->nmi_emergency_sp = (void *)ti + THREAD_SIZE;
/* emergency stack for machine check exception handling. */
ti = alloc_stack(limit, i);
memset(ti, 0, THREAD_SIZE);
- emerg_stack_init_thread_info(ti, i);
paca_ptrs[i]->mc_emergency_sp = (void *)ti + THREAD_SIZE;
#endif
}
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 19dd0ea55714..f22fcbeb9898 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -816,7 +816,7 @@ static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle)
paca_ptrs[cpu]->kstack = (unsigned long)task_stack_page(idle) +
THREAD_SIZE - STACK_FRAME_OVERHEAD;
#endif
- ti->cpu = cpu;
+ idle->cpu = cpu;
secondary_ti = current_set[cpu] = ti;
}
--
2.13.3
^ permalink raw reply related
* [RFC PATCH v2 4/9] powerpc: Prepare for moving thread_info into task_struct
From: Christophe Leroy @ 2018-09-25 12:10 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar, npiggin
Cc: linux-kernel, linuxppc-dev
In-Reply-To: <cover.1537877134.git.christophe.leroy@c-s.fr>
This patch cleans the powerpc kernel before activating
CONFIG_THREAD_INFO_IN_TASK:
- The purpose of the pointer given to call_do_softirq() and
call_do_irq() is to point the new stack ==> change it to void*
- current_pt_regs() is in the stack, not in thread_info.
- Don't use CURRENT_THREAD_INFO() to locate the stack.
- Fixed a few comments.
- TI_CPU is only used when CONFIG_SMP is set.
- Replace current_thread_info()->task by current
- Remove unnecessary casts to thread_info, as they'll become
invalid once thread_info is not in stack anymore.
- Ensure task_struct 'cpu' fields is not used directly out of SMP code
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/irq.h | 4 ++--
arch/powerpc/include/asm/livepatch.h | 2 +-
arch/powerpc/include/asm/processor.h | 4 ++--
arch/powerpc/include/asm/ptrace.h | 2 +-
arch/powerpc/include/asm/reg.h | 2 +-
arch/powerpc/kernel/entry_64.S | 2 +-
arch/powerpc/kernel/head_32.S | 2 +-
arch/powerpc/kernel/head_44x.S | 2 +-
arch/powerpc/kernel/head_fsl_booke.S | 4 +++-
arch/powerpc/kernel/irq.c | 2 +-
arch/powerpc/kernel/misc_32.S | 8 ++++++--
arch/powerpc/kernel/process.c | 6 +++---
arch/powerpc/kernel/setup_32.c | 15 +++++----------
arch/powerpc/kernel/smp.c | 4 +++-
arch/powerpc/xmon/xmon.c | 2 +-
15 files changed, 32 insertions(+), 29 deletions(-)
diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index ee39ce56b2a2..8108d1fe33ca 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -63,8 +63,8 @@ extern struct thread_info *hardirq_ctx[NR_CPUS];
extern struct thread_info *softirq_ctx[NR_CPUS];
extern void irq_ctx_init(void);
-extern void call_do_softirq(struct thread_info *tp);
-extern void call_do_irq(struct pt_regs *regs, struct thread_info *tp);
+extern void call_do_softirq(void *tp);
+extern void call_do_irq(struct pt_regs *regs, void *tp);
extern void do_IRQ(struct pt_regs *regs);
extern void __init init_IRQ(void);
extern void __do_irq(struct pt_regs *regs);
diff --git a/arch/powerpc/include/asm/livepatch.h b/arch/powerpc/include/asm/livepatch.h
index 47a03b9b528b..818451bf629c 100644
--- a/arch/powerpc/include/asm/livepatch.h
+++ b/arch/powerpc/include/asm/livepatch.h
@@ -49,7 +49,7 @@ static inline void klp_init_thread_info(struct thread_info *ti)
ti->livepatch_sp = (unsigned long *)(ti + 1) + 1;
}
#else
-static void klp_init_thread_info(struct thread_info *ti) { }
+static inline void klp_init_thread_info(struct thread_info *ti) { }
#endif /* CONFIG_LIVEPATCH */
#endif /* _ASM_POWERPC_LIVEPATCH_H */
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 353879db3e98..31873614392f 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -40,7 +40,7 @@
#ifndef __ASSEMBLY__
#include <linux/types.h>
-#include <asm/thread_info.h>
+#include <linux/thread_info.h>
#include <asm/ptrace.h>
#include <asm/hw_breakpoint.h>
@@ -333,7 +333,7 @@ struct thread_struct {
#define INIT_SP (sizeof(init_stack) + (unsigned long) &init_stack)
#define INIT_SP_LIMIT \
- (_ALIGN_UP(sizeof(init_thread_info), 16) + (unsigned long) &init_stack)
+ (_ALIGN_UP(sizeof(struct thread_info), 16) + (unsigned long) &init_stack)
#ifdef CONFIG_SPE
#define SPEFSCR_INIT \
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index 447cbd1bee99..3a7e5561630b 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -120,7 +120,7 @@ extern int ptrace_put_reg(struct task_struct *task, int regno,
unsigned long data);
#define current_pt_regs() \
- ((struct pt_regs *)((unsigned long)current_thread_info() + THREAD_SIZE) - 1)
+ ((struct pt_regs *)((unsigned long)task_stack_page(current) + THREAD_SIZE) - 1)
/*
* We use the least-significant bit of the trap field to indicate
* whether we have saved the full set of registers, or only a
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index e5b314ed054e..f3a9cf19a986 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -1053,7 +1053,7 @@
* - SPRG9 debug exception scratch
*
* All 32-bit:
- * - SPRG3 current thread_info pointer
+ * - SPRG3 current thread_struct physical addr pointer
* (virtual on BookE, physical on others)
*
* 32-bit classic:
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 77a888bfcb53..697406572592 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -680,7 +680,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
2:
#endif /* CONFIG_PPC_BOOK3S_64 */
- CURRENT_THREAD_INFO(r7, r8) /* base of new stack */
+ clrrdi r7, r8, THREAD_SHIFT /* base of new stack */
/* Note: this uses SWITCH_FRAME_SIZE rather than INT_FRAME_SIZE
because we don't need to leave the 288-byte ABI gap at the
top of the kernel stack. */
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 0c380c7ab82c..8fdb8c8bb1b4 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -841,7 +841,7 @@ __secondary_start:
bl init_idle_6xx
#endif /* CONFIG_6xx */
- /* get current_thread_info and current */
+ /* get current's stack and current */
lis r1,secondary_ti@ha
tophys(r1,r1)
lwz r1,secondary_ti@l(r1)
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index 612c0d42ce1c..d033311e18d9 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -1020,7 +1020,7 @@ _GLOBAL(start_secondary_47x)
/* Now we can get our task struct and real stack pointer */
- /* Get current_thread_info and current */
+ /* Get current's stack and current */
lis r1,secondary_ti@ha
lwz r1,secondary_ti@l(r1)
lwz r2,TI_TASK(r1)
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 611426977693..27243aff1722 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -243,8 +243,10 @@ set_ivor:
li r0,0
stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1)
+#ifdef CONFIG_SMP
CURRENT_THREAD_INFO(r22, r1)
stw r24, TI_CPU(r22)
+#endif
bl early_init
@@ -1074,7 +1076,7 @@ __secondary_start:
mr r4,r24 /* Why? */
bl call_setup_cpu
- /* get current_thread_info and current */
+ /* get current's stack and current */
lis r1,secondary_ti@ha
lwz r1,secondary_ti@l(r1)
lwz r2,TI_TASK(r1)
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 916ddc4aac44..aa53db3ba6e7 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -663,7 +663,7 @@ void do_IRQ(struct pt_regs *regs)
struct thread_info *curtp, *irqtp, *sirqtp;
/* Switch to the irq stack to handle this */
- curtp = current_thread_info();
+ curtp = (void*)(current_stack_pointer() & ~(THREAD_SIZE - 1));
irqtp = hardirq_ctx[raw_smp_processor_id()];
sirqtp = softirq_ctx[raw_smp_processor_id()];
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 695b24a2d954..24a7f18ea10c 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -60,7 +60,7 @@ _GLOBAL(call_do_softirq)
blr
/*
- * void call_do_irq(struct pt_regs *regs, struct thread_info *irqtp);
+ * void call_do_irq(struct pt_regs *regs, void *irqtp);
*/
_GLOBAL(call_do_irq)
mflr r0
@@ -183,10 +183,14 @@ _GLOBAL(low_choose_750fx_pll)
or r4,r4,r5
mtspr SPRN_HID1,r4
+#ifdef CONFIG_SMP
/* Store new HID1 image */
CURRENT_THREAD_INFO(r6, r1)
lwz r6,TI_CPU(r6)
slwi r6,r6,2
+#else
+ li r6, 0
+#endif
addis r6,r6,nap_save_hid1@ha
stw r4,nap_save_hid1@l(r6)
@@ -599,7 +603,7 @@ EXPORT_SYMBOL(__bswapdi2)
#ifdef CONFIG_SMP
_GLOBAL(start_secondary_resume)
/* Reset stack */
- CURRENT_THREAD_INFO(r1, r1)
+ rlwinm r1, r1, 0, 0, 31 - THREAD_SHIFT
addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
li r3,0
stw r3,0(r1) /* Zero the stack frame pointer */
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 03c2e1f134bc..111abb4df2ec 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1240,8 +1240,8 @@ struct task_struct *__switch_to(struct task_struct *prev,
batch->active = 1;
}
- if (current_thread_info()->task->thread.regs) {
- restore_math(current_thread_info()->task->thread.regs);
+ if (current->thread.regs) {
+ restore_math(current->thread.regs);
/*
* The copy-paste buffer can only store into foreign real
@@ -1251,7 +1251,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
* mappings, we must issue a cp_abort to clear any state and
* prevent snooping, corruption or a covert channel.
*/
- if (current_thread_info()->task->thread.used_vas)
+ if (current->thread.used_vas)
asm volatile(PPC_CP_ABORT);
}
#endif /* CONFIG_PPC_BOOK3S_64 */
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 8c507be12c3c..81ebf7d6f526 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -205,10 +205,8 @@ void __init irqstack_early_init(void)
/* interrupt stacks must be in lowmem, we get that for free on ppc32
* as the memblock is limited to lowmem by default */
for_each_possible_cpu(i) {
- softirq_ctx[i] = (struct thread_info *)
- __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
- hardirq_ctx[i] = (struct thread_info *)
- __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
+ softirq_ctx[i] = __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
+ hardirq_ctx[i] = __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
}
}
@@ -226,13 +224,10 @@ void __init exc_lvl_early_init(void)
hw_cpu = 0;
#endif
- critirq_ctx[hw_cpu] = (struct thread_info *)
- __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
+ critirq_ctx[hw_cpu] = __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
#ifdef CONFIG_BOOKE
- dbgirq_ctx[hw_cpu] = (struct thread_info *)
- __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
- mcheckirq_ctx[hw_cpu] = (struct thread_info *)
- __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
+ dbgirq_ctx[hw_cpu] = __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
+ mcheckirq_ctx[hw_cpu] = __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
#endif
}
}
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 61c1fadbc644..19dd0ea55714 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -20,6 +20,7 @@
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/sched/mm.h>
+#include <linux/sched/task_stack.h>
#include <linux/sched/topology.h>
#include <linux/smp.h>
#include <linux/interrupt.h>
@@ -812,7 +813,8 @@ static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle)
#ifdef CONFIG_PPC64
paca_ptrs[cpu]->__current = idle;
- paca_ptrs[cpu]->kstack = (unsigned long)ti + THREAD_SIZE - STACK_FRAME_OVERHEAD;
+ paca_ptrs[cpu]->kstack = (unsigned long)task_stack_page(idle) +
+ THREAD_SIZE - STACK_FRAME_OVERHEAD;
#endif
ti->cpu = cpu;
secondary_ti = current_set[cpu] = ti;
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 694c1d92e796..0d8d6fee892a 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -2988,7 +2988,7 @@ static void show_task(struct task_struct *tsk)
printf("%px %016lx %6d %6d %c %2d %s\n", tsk,
tsk->thread.ksp,
tsk->pid, tsk->parent->pid,
- state, task_thread_info(tsk)->cpu,
+ state, task_cpu(tsk),
tsk->comm);
}
--
2.13.3
^ permalink raw reply related
* [RFC PATCH v2 3/9] powerpc: clear redundancies in asm-offset.c
From: Christophe Leroy @ 2018-09-25 12:10 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar, npiggin
Cc: linux-kernel, linuxppc-dev
In-Reply-To: <cover.1537877134.git.christophe.leroy@c-s.fr>
In order to be able to include asm-offset.h in smp.h for PPC32,
all definitions which are conflicting with C need new names.
TASK_SIZE is nowhere used in asm.
PPC_DBELL_SERVER_SERVER and PPC_DBELL_SERVER_MSGTYPE are only
needed on PPC64 in asm.
MAS0 ... MAS7 conflict with 'struct tlbcam' fields.
NSEC_PER_SEC, PGD_TABLE_SIZE, PGD_T_LOG2 and PTE_T_LOG2
conflict with themselves.
This patch:
- Removes TASK_SIZE
- Encloses PPC_DBELL_SERVER_... in #ifdef CONFIG_PPC64
- Adds ASM_PTE_SHIFT as its definition uses PTE_T_LOG2
- Adds ASM_PGDIR_SHIFT as its definition uses PGD_T_LOG2
- Prefixes all other with ASM_
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/mmu-44x.h | 8 ++++----
arch/powerpc/kernel/asm-offsets.c | 27 +++++++++++++++------------
arch/powerpc/kernel/entry_32.S | 22 +++++++++++-----------
arch/powerpc/kernel/head_32.S | 2 +-
arch/powerpc/kernel/head_40x.S | 2 +-
arch/powerpc/kernel/head_44x.S | 2 +-
arch/powerpc/kernel/head_64.S | 2 +-
arch/powerpc/kernel/head_8xx.S | 2 +-
arch/powerpc/kernel/head_fsl_booke.S | 2 +-
arch/powerpc/kernel/vdso32/gettimeofday.S | 4 ++--
10 files changed, 38 insertions(+), 35 deletions(-)
diff --git a/arch/powerpc/include/asm/mmu-44x.h b/arch/powerpc/include/asm/mmu-44x.h
index 295b3dbb2698..c9a355944f9e 100644
--- a/arch/powerpc/include/asm/mmu-44x.h
+++ b/arch/powerpc/include/asm/mmu-44x.h
@@ -145,9 +145,9 @@ typedef struct {
#define mmu_linear_psize MMU_PAGE_256M
-#define PPC44x_PGD_OFF_SHIFT (32 - PGDIR_SHIFT + PGD_T_LOG2)
-#define PPC44x_PGD_OFF_MASK_BIT (PGDIR_SHIFT - PGD_T_LOG2)
-#define PPC44x_PTE_ADD_SHIFT (32 - PGDIR_SHIFT + PTE_SHIFT + PTE_T_LOG2)
-#define PPC44x_PTE_ADD_MASK_BIT (32 - PTE_T_LOG2 - PTE_SHIFT)
+#define PPC44x_PGD_OFF_SHIFT (32 - ASM_PGDIR_SHIFT + ASM_PGD_T_LOG2)
+#define PPC44x_PGD_OFF_MASK_BIT (ASM_PGDIR_SHIFT - ASM_PGD_T_LOG2)
+#define PPC44x_PTE_ADD_SHIFT (32 - ASM_PGDIR_SHIFT + ASM_PTE_SHIFT + ASM_PTE_T_LOG2)
+#define PPC44x_PTE_ADD_MASK_BIT (32 - ASM_PTE_T_LOG2 - ASM_PTE_SHIFT)
#endif /* _ASM_POWERPC_MMU_44X_H_ */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index d1f161e48945..3c649a6529eb 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -322,14 +322,14 @@ int main(void)
#if defined(CONFIG_PPC32)
#if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
DEFINE(EXC_LVL_SIZE, STACK_EXC_LVL_FRAME_SIZE);
- DEFINE(MAS0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas0));
+ DEFINE(ASM_MAS0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas0));
/* we overload MMUCR for 44x on MAS0 since they are mutually exclusive */
DEFINE(MMUCR, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas0));
- DEFINE(MAS1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas1));
- DEFINE(MAS2, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas2));
- DEFINE(MAS3, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas3));
- DEFINE(MAS6, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas6));
- DEFINE(MAS7, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas7));
+ DEFINE(ASM_MAS1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas1));
+ DEFINE(ASM_MAS2, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas2));
+ DEFINE(ASM_MAS3, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas3));
+ DEFINE(ASM_MAS6, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas6));
+ DEFINE(ASM_MAS7, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas7));
DEFINE(_SRR0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, srr0));
DEFINE(_SRR1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, srr1));
DEFINE(_CSRR0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, csrr0));
@@ -354,7 +354,6 @@ int main(void)
OFFSET(pbe_next, pbe, next);
#ifndef CONFIG_PPC64
- DEFINE(TASK_SIZE, TASK_SIZE);
DEFINE(NUM_USER_SEGMENTS, TASK_SIZE>>28);
#endif /* ! CONFIG_PPC64 */
@@ -399,7 +398,7 @@ int main(void)
DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC);
DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
DEFINE(CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
- DEFINE(NSEC_PER_SEC, NSEC_PER_SEC);
+ DEFINE(ASM_NSEC_PER_SEC, NSEC_PER_SEC);
DEFINE(CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC);
#ifdef CONFIG_BUG
@@ -407,9 +406,9 @@ int main(void)
#endif
#ifdef CONFIG_PPC_BOOK3S_64
- DEFINE(PGD_TABLE_SIZE, (sizeof(pgd_t) << max(RADIX_PGD_INDEX_SIZE, H_PGD_INDEX_SIZE)));
+ DEFINE(ASM_PGD_TABLE_SIZE, (sizeof(pgd_t) << max(RADIX_PGD_INDEX_SIZE, H_PGD_INDEX_SIZE)));
#else
- DEFINE(PGD_TABLE_SIZE, PGD_TABLE_SIZE);
+ DEFINE(ASM_PGD_TABLE_SIZE, PGD_TABLE_SIZE);
#endif
DEFINE(PTE_SIZE, sizeof(pte_t));
@@ -710,8 +709,10 @@ int main(void)
#endif
#ifdef CONFIG_44x
- DEFINE(PGD_T_LOG2, PGD_T_LOG2);
- DEFINE(PTE_T_LOG2, PTE_T_LOG2);
+ DEFINE(ASM_PGD_T_LOG2, PGD_T_LOG2);
+ DEFINE(ASM_PTE_T_LOG2, PTE_T_LOG2);
+ DEFINE(ASM_PTE_SHIFT, PTE_SHIFT);
+ DEFINE(ASM_PGDIR_SHIFT, PGDIR_SHIFT);
#endif
#ifdef CONFIG_PPC_FSL_BOOK3E
DEFINE(TLBCAM_SIZE, sizeof(struct tlbcam));
@@ -769,8 +770,10 @@ int main(void)
STOP_SPR(STOP_MMCRA, mmcra);
#endif
+#ifdef CONFIG_PPC64
DEFINE(PPC_DBELL_SERVER, PPC_DBELL_SERVER);
DEFINE(PPC_DBELL_MSGTYPE, PPC_DBELL_MSGTYPE);
+#endif
#ifdef CONFIG_PPC_8xx
DEFINE(VIRT_IMMR_BASE, (u64)__fix_to_virt(FIX_IMMR_BASE));
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 12c0721f65ea..83f3d3e977a9 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -74,18 +74,18 @@ debug_transfer_to_handler:
crit_transfer_to_handler:
#ifdef CONFIG_PPC_BOOK3E_MMU
mfspr r0,SPRN_MAS0
- stw r0,MAS0(r11)
+ stw r0,ASM_MAS0(r11)
mfspr r0,SPRN_MAS1
- stw r0,MAS1(r11)
+ stw r0,ASM_MAS1(r11)
mfspr r0,SPRN_MAS2
- stw r0,MAS2(r11)
+ stw r0,ASM_MAS2(r11)
mfspr r0,SPRN_MAS3
- stw r0,MAS3(r11)
+ stw r0,ASM_MAS3(r11)
mfspr r0,SPRN_MAS6
- stw r0,MAS6(r11)
+ stw r0,ASM_MAS6(r11)
#ifdef CONFIG_PHYS_64BIT
mfspr r0,SPRN_MAS7
- stw r0,MAS7(r11)
+ stw r0,ASM_MAS7(r11)
#endif /* CONFIG_PHYS_64BIT */
#endif /* CONFIG_PPC_BOOK3E_MMU */
#ifdef CONFIG_44x
@@ -1115,13 +1115,13 @@ exc_exit_restart_end:
#define RESTORE_MAS7
#endif /* CONFIG_PHYS_64BIT */
#define RESTORE_MMU_REGS \
- lwz r9,MAS0(r1); \
- lwz r10,MAS1(r1); \
- lwz r11,MAS2(r1); \
+ lwz r9,ASM_MAS0(r1); \
+ lwz r10,ASM_MAS1(r1); \
+ lwz r11,ASM_MAS2(r1); \
mtspr SPRN_MAS0,r9; \
- lwz r9,MAS3(r1); \
+ lwz r9,ASM_MAS3(r1); \
mtspr SPRN_MAS1,r10; \
- lwz r10,MAS6(r1); \
+ lwz r10,ASM_MAS6(r1); \
mtspr SPRN_MAS2,r11; \
mtspr SPRN_MAS3,r9; \
mtspr SPRN_MAS6,r10; \
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index dbb096c32332..0c380c7ab82c 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -1273,7 +1273,7 @@ EXPORT_SYMBOL(empty_zero_page)
.globl swapper_pg_dir
swapper_pg_dir:
- .space PGD_TABLE_SIZE
+ .space ASM_PGD_TABLE_SIZE
/* Room for two PTE pointers, usually the kernel and current user pointers
* to their respective root page table.
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
index 3088c9f29f5e..bc44775c442c 100644
--- a/arch/powerpc/kernel/head_40x.S
+++ b/arch/powerpc/kernel/head_40x.S
@@ -976,7 +976,7 @@ empty_zero_page:
EXPORT_SYMBOL(empty_zero_page)
.globl swapper_pg_dir
swapper_pg_dir:
- .space PGD_TABLE_SIZE
+ .space ASM_PGD_TABLE_SIZE
/* Room for two PTE pointers, usually the kernel and current user pointers
* to their respective root page table.
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index 37e4a7cf0065..612c0d42ce1c 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -1262,7 +1262,7 @@ EXPORT_SYMBOL(empty_zero_page)
*/
.globl swapper_pg_dir
swapper_pg_dir:
- .space PGD_TABLE_SIZE
+ .space ASM_PGD_TABLE_SIZE
/*
* Room for two PTE pointers, usually the kernel and current user pointers
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 4898e9491a1c..cf9437aafe58 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -1015,7 +1015,7 @@ start_here_common:
.globl swapper_pg_dir
swapper_pg_dir:
- .space PGD_TABLE_SIZE
+ .space ASM_PGD_TABLE_SIZE
.globl empty_zero_page
empty_zero_page:
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index e56e36aa2b3d..561e441c883d 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -1041,7 +1041,7 @@ EXPORT_SYMBOL(empty_zero_page)
.globl swapper_pg_dir
swapper_pg_dir:
- .space PGD_TABLE_SIZE
+ .space ASM_PGD_TABLE_SIZE
/* Room for two PTE table poiners, usually the kernel and current user
* pointer to their respective root page table (pgdir).
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 35d35067acf7..611426977693 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -1228,7 +1228,7 @@ empty_zero_page:
EXPORT_SYMBOL(empty_zero_page)
.globl swapper_pg_dir
swapper_pg_dir:
- .space PGD_TABLE_SIZE
+ .space ASM_PGD_TABLE_SIZE
/*
* Room for two PTE pointers, usually the kernel and current user pointers
diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index 1e0bc5955a40..cd77c6f22f8f 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -82,8 +82,8 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
mr r11,r4 /* r11 saves tp */
bl __get_datapage@local /* get data page */
mr r9,r3 /* datapage ptr in r9 */
- lis r7,NSEC_PER_SEC@h /* want nanoseconds */
- ori r7,r7,NSEC_PER_SEC@l
+ lis r7,ASM_NSEC_PER_SEC@h /* want nanoseconds */
+ ori r7,r7,ASM_NSEC_PER_SEC@l
50: bl __do_get_tspec@local /* get sec/nsec from tb & kernel */
bne cr1,80f /* not monotonic -> all done */
--
2.13.3
^ permalink raw reply related
* [RFC PATCH v2 2/9] powerpc: change name THREAD_INFO to TASK_STACK
From: Christophe Leroy @ 2018-09-25 12:10 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar, npiggin
Cc: linux-kernel, linuxppc-dev
In-Reply-To: <cover.1537877134.git.christophe.leroy@c-s.fr>
At the time being, the thread_info struct is located in the beginning
of the stack. There is an asm const called THREAD_INFO which is the
offset of the stack pointer in the task_struct.
In preparation of moving thread_info into task_struct, this patch
renames the THREAD_INFO const to TASK_STACK.
It also makes it available to PPC64, as it will also be needed
there to get the stack pointer from current.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/kernel/asm-offsets.c | 2 +-
arch/powerpc/kernel/entry_32.S | 2 +-
arch/powerpc/kernel/head_32.S | 2 +-
arch/powerpc/kernel/head_40x.S | 4 ++--
arch/powerpc/kernel/head_8xx.S | 2 +-
arch/powerpc/kernel/head_booke.h | 4 ++--
arch/powerpc/kernel/head_fsl_booke.S | 2 +-
7 files changed, 9 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index ba9d0fc98730..d1f161e48945 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -85,10 +85,10 @@ int main(void)
DEFINE(NMI_MASK, NMI_MASK);
OFFSET(TASKTHREADPPR, task_struct, thread.ppr);
#else
- OFFSET(THREAD_INFO, task_struct, stack);
DEFINE(THREAD_INFO_GAP, _ALIGN_UP(sizeof(struct thread_info), 16));
OFFSET(KSP_LIMIT, thread_struct, ksp_limit);
#endif /* CONFIG_PPC64 */
+ OFFSET(TASK_STACK, task_struct, stack);
#ifdef CONFIG_LIVEPATCH
OFFSET(TI_livepatch_sp, thread_info, livepatch_sp);
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index e58c3f467db5..12c0721f65ea 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -1166,7 +1166,7 @@ ret_from_debug_exc:
mfspr r9,SPRN_SPRG_THREAD
lwz r10,SAVED_KSP_LIMIT(r1)
stw r10,KSP_LIMIT(r9)
- lwz r9,THREAD_INFO-THREAD(r9)
+ lwz r9,TASK_STACK-THREAD(r9)
CURRENT_THREAD_INFO(r10, r1)
lwz r10,TI_PREEMPT(r10)
stw r10,TI_PREEMPT(r9)
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 61ca27929355..dbb096c32332 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -261,7 +261,7 @@ __secondary_hold_acknowledge:
tophys(r11,r1); /* use tophys(r1) if kernel */ \
beq 1f; \
mfspr r11,SPRN_SPRG_THREAD; \
- lwz r11,THREAD_INFO-THREAD(r11); \
+ lwz r11,TASK_STACK-THREAD(r11); \
addi r11,r11,THREAD_SIZE; \
tophys(r11,r11); \
1: subi r11,r11,INT_FRAME_SIZE /* alloc exc. frame */
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
index b19d78410511..3088c9f29f5e 100644
--- a/arch/powerpc/kernel/head_40x.S
+++ b/arch/powerpc/kernel/head_40x.S
@@ -115,7 +115,7 @@ _ENTRY(saved_ksp_limit)
andi. r11,r11,MSR_PR; \
beq 1f; \
mfspr r1,SPRN_SPRG_THREAD; /* if from user, start at top of */\
- lwz r1,THREAD_INFO-THREAD(r1); /* this thread's kernel stack */\
+ lwz r1,TASK_STACK-THREAD(r1); /* this thread's kernel stack */\
addi r1,r1,THREAD_SIZE; \
1: subi r1,r1,INT_FRAME_SIZE; /* Allocate an exception frame */\
tophys(r11,r1); \
@@ -158,7 +158,7 @@ _ENTRY(saved_ksp_limit)
beq 1f; \
/* COMING FROM USER MODE */ \
mfspr r11,SPRN_SPRG_THREAD; /* if from user, start at top of */\
- lwz r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\
+ lwz r11,TASK_STACK-THREAD(r11); /* this thread's kernel stack */\
1: addi r11,r11,THREAD_SIZE-INT_FRAME_SIZE; /* Alloc an excpt frm */\
tophys(r11,r11); \
stw r10,_CCR(r11); /* save various registers */\
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 6582f824d620..e56e36aa2b3d 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -124,7 +124,7 @@ turn_on_mmu:
tophys(r11,r1); /* use tophys(r1) if kernel */ \
beq 1f; \
mfspr r11,SPRN_SPRG_THREAD; \
- lwz r11,THREAD_INFO-THREAD(r11); \
+ lwz r11,TASK_STACK-THREAD(r11); \
addi r11,r11,THREAD_SIZE; \
tophys(r11,r11); \
1: subi r11,r11,INT_FRAME_SIZE /* alloc exc. frame */
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index d0862a100d29..20fe0c93a0bd 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -44,7 +44,7 @@
mr r11, r1; \
beq 1f; \
/* if from user, start at top of this thread's kernel stack */ \
- lwz r11, THREAD_INFO-THREAD(r10); \
+ lwz r11, TASK_STACK-THREAD(r10); \
ALLOC_STACK_FRAME(r11, THREAD_SIZE); \
1 : subi r11, r11, INT_FRAME_SIZE; /* Allocate exception frame */ \
stw r13, _CCR(r11); /* save various registers */ \
@@ -130,7 +130,7 @@
DO_KVM BOOKE_INTERRUPT_##intno exc_level_srr1; \
andi. r11,r11,MSR_PR; \
mfspr r11,SPRN_SPRG_THREAD; /* if from user, start at top of */\
- lwz r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\
+ lwz r11,TASK_STACK-THREAD(r11); /* this thread's kernel stack */\
addi r11,r11,EXC_LVL_FRAME_OVERHEAD; /* allocate stack frame */\
beq 1f; \
/* COMING FROM USER MODE */ \
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index e2750b856c8f..35d35067acf7 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -702,7 +702,7 @@ finish_tlb_load:
/* Get the next_tlbcam_idx percpu var */
#ifdef CONFIG_SMP
- lwz r12, THREAD_INFO-THREAD(r12)
+ lwz r12, TASK_STACK-THREAD(r12)
lwz r15, TI_CPU(r12)
lis r14, __per_cpu_offset@h
ori r14, r14, __per_cpu_offset@l
--
2.13.3
^ permalink raw reply related
* [RFC PATCH v2 1/9] book3s/64: avoid circular header inclusion in mmu-hash.h
From: Christophe Leroy @ 2018-09-25 12:10 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar, npiggin
Cc: linux-kernel, linuxppc-dev
In-Reply-To: <cover.1537877134.git.christophe.leroy@c-s.fr>
When activating CONFIG_THREAD_INFO_IN_TASK, linux/sched.h
includes asm/current.h. This generates a circular dependency.
To avoid that, asm/processor.h shall not be included in mmu-hash.h
In order to do that, this patch moves into a new header called
asm/task_size.h the information from asm/processor.h requires by
mmu-hash.h
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/book3s/64/mmu-hash.h | 2 +-
arch/powerpc/include/asm/processor.h | 34 +---------------------
arch/powerpc/include/asm/task_size.h | 42 +++++++++++++++++++++++++++
arch/powerpc/kvm/book3s_hv_hmi.c | 1 +
4 files changed, 45 insertions(+), 34 deletions(-)
create mode 100644 arch/powerpc/include/asm/task_size.h
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index bbeaf6adf93c..7788e35f19f0 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -23,7 +23,7 @@
*/
#include <asm/book3s/64/pgtable.h>
#include <asm/bug.h>
-#include <asm/processor.h>
+#include <asm/task_size.h>
#include <asm/cpu_has_feature.h>
/*
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 350c584ca179..353879db3e98 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -101,40 +101,8 @@ void release_thread(struct task_struct *);
#endif
#ifdef CONFIG_PPC64
-/*
- * 64-bit user address space can have multiple limits
- * For now supported values are:
- */
-#define TASK_SIZE_64TB (0x0000400000000000UL)
-#define TASK_SIZE_128TB (0x0000800000000000UL)
-#define TASK_SIZE_512TB (0x0002000000000000UL)
-#define TASK_SIZE_1PB (0x0004000000000000UL)
-#define TASK_SIZE_2PB (0x0008000000000000UL)
-/*
- * With 52 bits in the address we can support
- * upto 4PB of range.
- */
-#define TASK_SIZE_4PB (0x0010000000000000UL)
-/*
- * For now 512TB is only supported with book3s and 64K linux page size.
- */
-#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_64K_PAGES)
-/*
- * Max value currently used:
- */
-#define TASK_SIZE_USER64 TASK_SIZE_4PB
-#define DEFAULT_MAP_WINDOW_USER64 TASK_SIZE_128TB
-#define TASK_CONTEXT_SIZE TASK_SIZE_512TB
-#else
-#define TASK_SIZE_USER64 TASK_SIZE_64TB
-#define DEFAULT_MAP_WINDOW_USER64 TASK_SIZE_64TB
-/*
- * We don't need to allocate extended context ids for 4K page size, because
- * we limit the max effective address on this config to 64TB.
- */
-#define TASK_CONTEXT_SIZE TASK_SIZE_64TB
-#endif
+#include <asm/task_size.h>
/*
* 32-bit user address space is 4GB - 1 page
diff --git a/arch/powerpc/include/asm/task_size.h b/arch/powerpc/include/asm/task_size.h
new file mode 100644
index 000000000000..ca45638617b0
--- /dev/null
+++ b/arch/powerpc/include/asm/task_size.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_TASK_SIZE_H
+#define _ASM_POWERPC_TASK_SIZE_H
+
+#ifdef CONFIG_PPC64
+/*
+ * 64-bit user address space can have multiple limits
+ * For now supported values are:
+ */
+#define TASK_SIZE_64TB (0x0000400000000000UL)
+#define TASK_SIZE_128TB (0x0000800000000000UL)
+#define TASK_SIZE_512TB (0x0002000000000000UL)
+#define TASK_SIZE_1PB (0x0004000000000000UL)
+#define TASK_SIZE_2PB (0x0008000000000000UL)
+/*
+ * With 52 bits in the address we can support
+ * upto 4PB of range.
+ */
+#define TASK_SIZE_4PB (0x0010000000000000UL)
+
+/*
+ * For now 512TB is only supported with book3s and 64K linux page size.
+ */
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_64K_PAGES)
+/*
+ * Max value currently used:
+ */
+#define TASK_SIZE_USER64 TASK_SIZE_4PB
+#define DEFAULT_MAP_WINDOW_USER64 TASK_SIZE_128TB
+#define TASK_CONTEXT_SIZE TASK_SIZE_512TB
+#else
+#define TASK_SIZE_USER64 TASK_SIZE_64TB
+#define DEFAULT_MAP_WINDOW_USER64 TASK_SIZE_64TB
+/*
+ * We don't need to allocate extended context ids for 4K page size, because
+ * we limit the max effective address on this config to 64TB.
+ */
+#define TASK_CONTEXT_SIZE TASK_SIZE_64TB
+#endif
+
+#endif /* CONFIG_PPC64 */
+#endif /* _ASM_POWERPC_TASK_SIZE_H */
diff --git a/arch/powerpc/kvm/book3s_hv_hmi.c b/arch/powerpc/kvm/book3s_hv_hmi.c
index e3f738eb1cac..64b5011475c7 100644
--- a/arch/powerpc/kvm/book3s_hv_hmi.c
+++ b/arch/powerpc/kvm/book3s_hv_hmi.c
@@ -24,6 +24,7 @@
#include <linux/compiler.h>
#include <asm/paca.h>
#include <asm/hmi.h>
+#include <asm/processor.h>
void wait_for_subcore_guest_exit(void)
{
--
2.13.3
^ permalink raw reply related
* [RFC PATCH v2 0/9] powerpc: Switch to CONFIG_THREAD_INFO_IN_TASK
From: Christophe Leroy @ 2018-09-25 12:10 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar, npiggin
Cc: linux-kernel, linuxppc-dev
The purpose of this serie is to activate CONFIG_THREAD_INFO_IN_TASK which
moves the thread_info into task_struct.
Moving thread_info into task_struct has the following advantages:
- It protects thread_info from corruption in the case of stack
overflows.
- Its address is harder to determine if stack addresses are
leaked, making a number of attacks more difficult.
Changes since v1:
- Removed the first patch which was modifying header inclusion order in timer
- Modified some names in asm-offsets to avoid conflicts when including asm-offsets in C files
- Modified asm/smp.h to avoid having to include linux/sched.h (using asm-offsets instead)
- Moved some changes from the activation patch to the preparation patch.
Christophe Leroy (9):
book3s/64: avoid circular header inclusion in mmu-hash.h
powerpc: change name THREAD_INFO to TASK_STACK
powerpc: clear redundancies in asm-offset.c
powerpc: Prepare for moving thread_info into task_struct
powerpc: Activate CONFIG_THREAD_INFO_IN_TASK
powerpc: regain entire stack space
powerpc: 'current_set' is now a table of task_struct pointers
powerpc/32: Remove CURRENT_THREAD_INFO and rename TI_CPU
powerpc/64: Modify CURRENT_THREAD_INFO()
arch/powerpc/Kconfig | 1 +
arch/powerpc/include/asm/asm-prototypes.h | 4 +-
arch/powerpc/include/asm/book3s/64/mmu-hash.h | 2 +-
arch/powerpc/include/asm/exception-64s.h | 4 +-
arch/powerpc/include/asm/irq.h | 14 ++--
arch/powerpc/include/asm/livepatch.h | 2 +-
arch/powerpc/include/asm/mmu-44x.h | 8 +--
arch/powerpc/include/asm/processor.h | 39 +-----------
arch/powerpc/include/asm/ptrace.h | 2 +-
arch/powerpc/include/asm/reg.h | 2 +-
arch/powerpc/include/asm/smp.h | 14 +++-
arch/powerpc/include/asm/task_size.h | 42 ++++++++++++
arch/powerpc/include/asm/thread_info.h | 17 +----
arch/powerpc/kernel/asm-offsets.c | 37 ++++++-----
arch/powerpc/kernel/entry_32.S | 88 ++++++++++----------------
arch/powerpc/kernel/entry_64.S | 12 ++--
arch/powerpc/kernel/epapr_hcalls.S | 5 +-
arch/powerpc/kernel/exceptions-64e.S | 13 +---
arch/powerpc/kernel/exceptions-64s.S | 2 +-
arch/powerpc/kernel/head_32.S | 16 ++---
arch/powerpc/kernel/head_40x.S | 6 +-
arch/powerpc/kernel/head_44x.S | 10 +--
arch/powerpc/kernel/head_64.S | 3 +-
arch/powerpc/kernel/head_8xx.S | 4 +-
arch/powerpc/kernel/head_booke.h | 12 +---
arch/powerpc/kernel/head_fsl_booke.S | 18 +++---
arch/powerpc/kernel/idle_6xx.S | 8 +--
arch/powerpc/kernel/idle_book3e.S | 2 +-
arch/powerpc/kernel/idle_e500.S | 8 +--
arch/powerpc/kernel/idle_power4.S | 2 +-
arch/powerpc/kernel/irq.c | 66 +++----------------
arch/powerpc/kernel/kgdb.c | 28 --------
arch/powerpc/kernel/machine_kexec_64.c | 6 +-
arch/powerpc/kernel/misc_32.S | 17 ++---
arch/powerpc/kernel/process.c | 15 ++---
arch/powerpc/kernel/setup-common.c | 2 +-
arch/powerpc/kernel/setup_32.c | 15 ++---
arch/powerpc/kernel/setup_64.c | 29 ++-------
arch/powerpc/kernel/smp.c | 16 ++---
arch/powerpc/kernel/trace/ftrace_64_mprofile.S | 6 +-
arch/powerpc/kernel/vdso32/gettimeofday.S | 4 +-
arch/powerpc/kvm/book3s_hv_hmi.c | 1 +
arch/powerpc/mm/hash_low_32.S | 14 ++--
arch/powerpc/sysdev/6xx-suspend.S | 5 +-
arch/powerpc/xmon/xmon.c | 2 +-
45 files changed, 243 insertions(+), 380 deletions(-)
create mode 100644 arch/powerpc/include/asm/task_size.h
--
2.13.3
^ permalink raw reply
* Re: [PATCH] powerpc/tm: Avoid possible userspace r1 corruption on reclaim
From: Michael Ellerman @ 2018-09-25 12:00 UTC (permalink / raw)
To: Michael Neuling
Cc: linuxppc-dev, Nicholas Piggin, paulus, benh, Breno Leitao,
aneesh.kumar, Michael Neuling
In-Reply-To: <20180925093647.23723-1-mikey@neuling.org>
Michael Neuling <mikey@neuling.org> writes:
> Current we store the userspace r1 to PACATMSCRATCH before finally
> saving it to the thread struct.
>
> In theory an exception could be taken here (like a machine check or
> SLB miss) that could write PACATMSCRATCH and hence corrupt the
> userspace r1. The SLB fault currently doesn't touch PACATMSCRATCH, but
> others do.
>
> We've never actually seen this happen but it's theoretically
> possible. Either way, the code is fragile as it is.
>
> This patch saves r1 to the kernel stack (which can't fault) before we
> turn MSR[RI] back on. PACATMSCRATCH is still used but only with
> MSR[RI] off. We then copy r1 from the kernel stack to the thread
> struct once we have MSR[RI] back on.
>
> Suggested-by: Breno Leitao <leitao@debian.org>
> Signed-off-by: Michael Neuling <mikey@neuling.org>
> ---
> arch/powerpc/kernel/tm.S | 8 +++++++-
> 1 file changed, 7 insertions(+), 1 deletion(-)
>
> diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
> index 701b0f5b09..8207816a1e 100644
> --- a/arch/powerpc/kernel/tm.S
> +++ b/arch/powerpc/kernel/tm.S
> @@ -178,6 +178,12 @@ _GLOBAL(tm_reclaim)
>
> std r11, GPR11(r1) /* Temporary stash */
>
> + /* Move r1 to kernel stack in case PACATMSCRATCH is used once
> + * we turn on RI
> + */
I see we still need to send you to Comment Formatting Re-Education Camp.
I rewrote it a bit too, to hopefully be clearer?
/*
* Move the saved user r1 to the kernel stack in case PACATMSCRATCH is
* clobbered by an exception once we turn on MSR_RI below.
*/
ld r11, PACATMSCRATCH(r13)
std r11, GPR1(r1)
cheers
^ permalink raw reply
* [PATCH] powerpc/tm: Avoid possible userspace r1 corruption on reclaim
From: Michael Neuling @ 2018-09-25 9:36 UTC (permalink / raw)
To: mpe
Cc: linuxppc-dev, Nicholas Piggin, paulus, benh, Breno Leitao,
aneesh.kumar, Michael Neuling
Current we store the userspace r1 to PACATMSCRATCH before finally
saving it to the thread struct.
In theory an exception could be taken here (like a machine check or
SLB miss) that could write PACATMSCRATCH and hence corrupt the
userspace r1. The SLB fault currently doesn't touch PACATMSCRATCH, but
others do.
We've never actually seen this happen but it's theoretically
possible. Either way, the code is fragile as it is.
This patch saves r1 to the kernel stack (which can't fault) before we
turn MSR[RI] back on. PACATMSCRATCH is still used but only with
MSR[RI] off. We then copy r1 from the kernel stack to the thread
struct once we have MSR[RI] back on.
Suggested-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
arch/powerpc/kernel/tm.S | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 701b0f5b09..8207816a1e 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -178,6 +178,12 @@ _GLOBAL(tm_reclaim)
std r11, GPR11(r1) /* Temporary stash */
+ /* Move r1 to kernel stack in case PACATMSCRATCH is used once
+ * we turn on RI
+ */
+ ld r11, PACATMSCRATCH(r13)
+ std r11, GPR1(r1)
+
/* Store r13 away so we can free up the scratch SPR for the
* SLB fault handler (needed once we start access the
* thread_struct)
@@ -214,7 +220,7 @@ _GLOBAL(tm_reclaim)
SAVE_GPR(8, r7) /* user r8 */
SAVE_GPR(9, r7) /* user r9 */
SAVE_GPR(10, r7) /* user r10 */
- ld r3, PACATMSCRATCH(r13) /* user r1 */
+ ld r3, GPR1(r1) /* user r1 */
ld r4, GPR7(r1) /* user r7 */
ld r5, GPR11(r1) /* user r11 */
ld r6, GPR12(r1) /* user r12 */
--
2.17.1
^ permalink raw reply related
* [PATCH v2 6/6] memory-hotplug.txt: Add some details about locking internals
From: David Hildenbrand @ 2018-09-25 9:14 UTC (permalink / raw)
To: linux-mm
Cc: linux-kernel, linux-doc, linuxppc-dev, linux-acpi, xen-devel,
devel, David Hildenbrand, Jonathan Corbet, Michal Hocko,
Andrew Morton
In-Reply-To: <20180925091457.28651-1-david@redhat.com>
Let's document the magic a bit, especially why device_hotplug_lock is
required when adding/removing memory and how it all play together with
requests to online/offline memory from user space.
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Pavel Tatashin <pavel.tatashin@microsoft.com>
Reviewed-by: Rashmica Gupta <rashmica.g@gmail.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
Documentation/memory-hotplug.txt | 42 +++++++++++++++++++++++++++++++-
1 file changed, 41 insertions(+), 1 deletion(-)
diff --git a/Documentation/memory-hotplug.txt b/Documentation/memory-hotplug.txt
index 7f49ebf3ddb2..ce4faa5530fa 100644
--- a/Documentation/memory-hotplug.txt
+++ b/Documentation/memory-hotplug.txt
@@ -3,7 +3,7 @@ Memory Hotplug
==============
:Created: Jul 28 2007
-:Updated: Add description of notifier of memory hotplug: Oct 11 2007
+:Updated: Add some details about locking internals: Aug 20 2018
This document is about memory hotplug including how-to-use and current status.
Because Memory Hotplug is still under development, contents of this text will
@@ -495,6 +495,46 @@ further processing of the notification queue.
NOTIFY_STOP stops further processing of the notification queue.
+
+Locking Internals
+=================
+
+When adding/removing memory that uses memory block devices (i.e. ordinary RAM),
+the device_hotplug_lock should be held to:
+
+- synchronize against online/offline requests (e.g. via sysfs). This way, memory
+ block devices can only be accessed (.online/.state attributes) by user
+ space once memory has been fully added. And when removing memory, we
+ know nobody is in critical sections.
+- synchronize against CPU hotplug and similar (e.g. relevant for ACPI and PPC)
+
+Especially, there is a possible lock inversion that is avoided using
+device_hotplug_lock when adding memory and user space tries to online that
+memory faster than expected:
+
+- device_online() will first take the device_lock(), followed by
+ mem_hotplug_lock
+- add_memory_resource() will first take the mem_hotplug_lock, followed by
+ the device_lock() (while creating the devices, during bus_add_device()).
+
+As the device is visible to user space before taking the device_lock(), this
+can result in a lock inversion.
+
+onlining/offlining of memory should be done via device_online()/
+device_offline() - to make sure it is properly synchronized to actions
+via sysfs. Holding device_hotplug_lock is advised (to e.g. protect online_type)
+
+When adding/removing/onlining/offlining memory or adding/removing
+heterogeneous/device memory, we should always hold the mem_hotplug_lock in
+write mode to serialise memory hotplug (e.g. access to global/zone
+variables).
+
+In addition, mem_hotplug_lock (in contrast to device_hotplug_lock) in read
+mode allows for a quite efficient get_online_mems/put_online_mems
+implementation, so code accessing memory can protect from that memory
+vanishing.
+
+
Future Work
===========
--
2.17.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox