From 69111bac42f5ceacdd22e30947837ceb2c4493ed Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Tue, 21 Oct 2014 15:23:25 -0500 Subject: powerpc: Replace __get_cpu_var uses This still has not been merged and now powerpc is the only arch that does not have this change. Sorry about missing linuxppc-dev before. V2->V2 - Fix up to work against 3.18-rc1 __get_cpu_var() is used for multiple purposes in the kernel source. One of them is address calculation via the form &__get_cpu_var(x). This calculates the address for the instance of the percpu variable of the current processor based on an offset. Other use cases are for storing and retrieving data from the current processors percpu area. __get_cpu_var() can be used as an lvalue when writing data or on the right side of an assignment. __get_cpu_var() is defined as : __get_cpu_var() always only does an address determination. However, store and retrieve operations could use a segment prefix (or global register on other platforms) to avoid the address calculation. this_cpu_write() and this_cpu_read() can directly take an offset into a percpu area and use optimized assembly code to read and write per cpu variables. This patch converts __get_cpu_var into either an explicit address calculation using this_cpu_ptr() or into a use of this_cpu operations that use the offset. Thereby address calculations are avoided and less registers are used when code is generated. At the end of the patch set all uses of __get_cpu_var have been removed so the macro is removed too. The patch set includes passes over all arches as well. Once these operations are used throughout then specialized macros can be defined in non -x86 arches as well in order to optimize per cpu access by f.e. using a global register that may be set to the per cpu base. Transformations done to __get_cpu_var() 1. Determine the address of the percpu instance of the current processor. DEFINE_PER_CPU(int, y); int *x = &__get_cpu_var(y); Converts to int *x = this_cpu_ptr(&y); 2. Same as #1 but this time an array structure is involved. DEFINE_PER_CPU(int, y[20]); int *x = __get_cpu_var(y); Converts to int *x = this_cpu_ptr(y); 3. Retrieve the content of the current processors instance of a per cpu variable. DEFINE_PER_CPU(int, y); int x = __get_cpu_var(y) Converts to int x = __this_cpu_read(y); 4. Retrieve the content of a percpu struct DEFINE_PER_CPU(struct mystruct, y); struct mystruct x = __get_cpu_var(y); Converts to memcpy(&x, this_cpu_ptr(&y), sizeof(x)); 5. Assignment to a per cpu variable DEFINE_PER_CPU(int, y) __get_cpu_var(y) = x; Converts to __this_cpu_write(y, x); 6. Increment/Decrement etc of a per cpu variable DEFINE_PER_CPU(int, y); __get_cpu_var(y)++ Converts to __this_cpu_inc(y) Cc: Benjamin Herrenschmidt CC: Paul Mackerras Signed-off-by: Christoph Lameter [mpe: Fix build errors caused by set/or_softirq_pending(), and rework assignment in __set_breakpoint() to use memcpy().] Signed-off-by: Michael Ellerman --- arch/powerpc/mm/hugetlbpage.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/mm/hugetlbpage.c') diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 7e70ae968e5f..8aa04f03fd31 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -462,7 +462,7 @@ static void hugepd_free(struct mmu_gather *tlb, void *hugepte) { struct hugepd_freelist **batchp; - batchp = &get_cpu_var(hugepd_freelist_cur); + batchp = this_cpu_ptr(&hugepd_freelist_cur); if (atomic_read(&tlb->mm->mm_users) < 2 || cpumask_equal(mm_cpumask(tlb->mm), -- cgit v1.2.1 From 14ed740957704e8768523899e0fa31972577bf65 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Wed, 17 Sep 2014 22:15:34 +1000 Subject: powerpc: Remove some old bootmem related comments Now bootmem is gone from powerpc we can remove comments mentioning it. Signed-off-by: Anton Blanchard Tested-by: Emil Medve Signed-off-by: Michael Ellerman --- arch/powerpc/mm/hugetlbpage.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/mm/hugetlbpage.c') diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 8aa04f03fd31..b460e723f0ec 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -276,7 +276,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz #ifdef CONFIG_PPC_FSL_BOOK3E /* Build list of addresses of gigantic pages. This function is used in early - * boot before the buddy or bootmem allocator is setup. + * boot before the buddy allocator is setup. */ void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages) { @@ -399,7 +399,7 @@ void __init reserve_hugetlb_gpages(void) #else /* !PPC_FSL_BOOK3E */ /* Build list of addresses of gigantic pages. This function is used in early - * boot before the buddy or bootmem allocator is setup. + * boot before the buddy allocator is setup. */ void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages) { -- cgit v1.2.1 From 06743521d0eae1263a09bccb1a92a9fbb94660b3 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 5 Nov 2014 21:57:39 +0530 Subject: powerpc/mm: Add missing pmd accessors This patch add documentation and missing accessors. Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman --- arch/powerpc/mm/hugetlbpage.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/powerpc/mm/hugetlbpage.c') diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index b460e723f0ec..2b8e5ed28831 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -62,6 +62,9 @@ static unsigned nr_gpages; /* * We have PGD_INDEX_SIZ = 12 and PTE_INDEX_SIZE = 8, so that we can have * 16GB hugepage pte in PGD and 16MB hugepage pte at PMD; + * + * Defined in such a way that we can optimize away code block at build time + * if CONFIG_HUGETLB_PAGE=n. */ int pmd_huge(pmd_t pmd) { -- cgit v1.2.1 From b30e759072c182538abb6908681cfd49978ba5e2 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 5 Nov 2014 21:57:41 +0530 Subject: powerpc/mm: Switch to generic RCU get_user_pages_fast This patch switch the ppc arch to use the generic RCU based gup implementation. Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman --- arch/powerpc/mm/hugetlbpage.c | 33 ++++++++++++--------------------- 1 file changed, 12 insertions(+), 21 deletions(-) (limited to 'arch/powerpc/mm/hugetlbpage.c') diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 2b8e5ed28831..af56de82375d 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -233,7 +233,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr, pdshift, pshift)) return NULL; - return hugepte_offset(hpdp, addr, pdshift); + return hugepte_offset(*hpdp, addr, pdshift); } #else @@ -273,7 +273,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr, pdshift, pshift)) return NULL; - return hugepte_offset(hpdp, addr, pdshift); + return hugepte_offset(*hpdp, addr, pdshift); } #endif @@ -541,7 +541,7 @@ static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud, do { pmd = pmd_offset(pud, addr); next = pmd_addr_end(addr, end); - if (!is_hugepd(pmd)) { + if (!is_hugepd(__hugepd(pmd_val(*pmd)))) { /* * if it is not hugepd pointer, we should already find * it cleared. @@ -590,7 +590,7 @@ static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, do { pud = pud_offset(pgd, addr); next = pud_addr_end(addr, end); - if (!is_hugepd(pud)) { + if (!is_hugepd(__hugepd(pud_val(*pud)))) { if (pud_none_or_clear_bad(pud)) continue; hugetlb_free_pmd_range(tlb, pud, addr, next, floor, @@ -656,7 +656,7 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb, do { next = pgd_addr_end(addr, end); pgd = pgd_offset(tlb->mm, addr); - if (!is_hugepd(pgd)) { + if (!is_hugepd(__hugepd(pgd_val(*pgd)))) { if (pgd_none_or_clear_bad(pgd)) continue; hugetlb_free_pud_range(tlb, pgd, addr, next, floor, ceiling); @@ -716,12 +716,11 @@ static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end, return (__boundary - 1 < end - 1) ? __boundary : end; } -int gup_hugepd(hugepd_t *hugepd, unsigned pdshift, - unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) +int gup_huge_pd(hugepd_t hugepd, unsigned long addr, unsigned pdshift, + unsigned long end, int write, struct page **pages, int *nr) { pte_t *ptep; - unsigned long sz = 1UL << hugepd_shift(*hugepd); + unsigned long sz = 1UL << hugepd_shift(hugepd); unsigned long next; ptep = hugepte_offset(hugepd, addr, pdshift); @@ -964,7 +963,7 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift else if (pgd_huge(pgd)) { ret_pte = (pte_t *) pgdp; goto out; - } else if (is_hugepd(&pgd)) + } else if (is_hugepd(__hugepd(pgd_val(pgd)))) hpdp = (hugepd_t *)&pgd; else { /* @@ -981,7 +980,7 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift else if (pud_huge(pud)) { ret_pte = (pte_t *) pudp; goto out; - } else if (is_hugepd(&pud)) + } else if (is_hugepd(__hugepd(pud_val(pud)))) hpdp = (hugepd_t *)&pud; else { pdshift = PMD_SHIFT; @@ -1002,7 +1001,7 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift if (pmd_huge(pmd) || pmd_large(pmd)) { ret_pte = (pte_t *) pmdp; goto out; - } else if (is_hugepd(&pmd)) + } else if (is_hugepd(__hugepd(pmd_val(pmd)))) hpdp = (hugepd_t *)&pmd; else return pte_offset_kernel(&pmd, ea); @@ -1011,7 +1010,7 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift if (!hpdp) return NULL; - ret_pte = hugepte_offset(hpdp, ea, pdshift); + ret_pte = hugepte_offset(*hpdp, ea, pdshift); pdshift = hugepd_shift(*hpdp); out: if (shift) @@ -1041,14 +1040,6 @@ int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, if ((pte_val(pte) & mask) != mask) return 0; -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - /* - * check for splitting here - */ - if (pmd_trans_splitting(pte_pmd(pte))) - return 0; -#endif - /* hugepages are never "special" */ VM_BUG_ON(!pfn_valid(pte_pfn(pte))); -- cgit v1.2.1 From e39f223fc93580c86ccf6b3422033e349f57f0dd Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 18 Nov 2014 16:47:35 +1100 Subject: powerpc: Remove more traces of bootmem Although we are now selecting NO_BOOTMEM, we still have some traces of bootmem lying around. That is because even with NO_BOOTMEM there is still a shim that converts bootmem calls into memblock calls, but ultimately we want to remove all traces of bootmem. Most of the patch is conversions from alloc_bootmem() to memblock_virt_alloc(). In general a call such as: p = (struct foo *)alloc_bootmem(x); Becomes: p = memblock_virt_alloc(x, 0); We don't need the cast because memblock_virt_alloc() returns a void *. The alignment value of zero tells memblock to use the default alignment, which is SMP_CACHE_BYTES, the same value alloc_bootmem() uses. We remove a number of NULL checks on the result of memblock_virt_alloc(). That is because memblock_virt_alloc() will panic if it can't allocate, in exactly the same way as alloc_bootmem(), so the NULL checks are and always have been redundant. The memory returned by memblock_virt_alloc() is already zeroed, so we remove several memsets of the result of memblock_virt_alloc(). Finally we convert a few uses of __alloc_bootmem(x, y, MAX_DMA_ADDRESS) to just plain memblock_virt_alloc(). We don't use memblock_alloc_base() because MAX_DMA_ADDRESS is ~0ul on powerpc, so limiting the allocation to that is pointless, 16XB ought to be enough for anyone. Signed-off-by: Michael Ellerman --- arch/powerpc/mm/hugetlbpage.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/mm/hugetlbpage.c') diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index af56de82375d..8c9b8115867c 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -315,7 +315,7 @@ int alloc_bootmem_huge_page(struct hstate *hstate) * If gpages can be in highmem we can't use the trick of storing the * data structure in the page; allocate space for this */ - m = alloc_bootmem(sizeof(struct huge_bootmem_page)); + m = memblock_virt_alloc(sizeof(struct huge_bootmem_page), 0); m->phys = gpage_freearray[idx].gpage_list[--nr_gpages]; #else m = phys_to_virt(gpage_freearray[idx].gpage_list[--nr_gpages]); -- cgit v1.2.1 From c4f3eb5fc527b749d6fb0d47ffdcfe83706dbe2f Mon Sep 17 00:00:00 2001 From: James Yang Date: Fri, 14 Nov 2014 12:32:24 -0600 Subject: powerpc/mm/hugetlb: Sanity check gigantic hugepage count Limit the number of gigantic hugepages specified by the hugepages= parameter to MAX_NUMBER_GPAGES. Signed-off-by: James Yang Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/mm/hugetlbpage.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'arch/powerpc/mm/hugetlbpage.c') diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index af56de82375d..747e0c616526 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -355,6 +355,13 @@ static int __init do_gpage_early_setup(char *param, char *val, if (size != 0) { if (sscanf(val, "%lu", &npages) <= 0) npages = 0; + if (npages > MAX_NUMBER_GPAGES) { + pr_warn("MMU: %lu pages requested for page " + "size %llu KB, limiting to " + __stringify(MAX_NUMBER_GPAGES) "\n", + npages, size / 1024); + npages = MAX_NUMBER_GPAGES; + } gpage_npages[shift_to_mmu_psize(__ffs(size))] = npages; size = 0; } -- cgit v1.2.1