From fb50b020c5331c8c4bee0eb875865f5f8be6c03a Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 16 Nov 2012 13:53:09 -0800 Subject: x86: Move some contents of page_64_types.h into pgtable_64.h and page_64.h This patch is meant to clean-up the fact that we have several functions in page_64_types.h which really don't belong there. I found this issue when I had tried to replace __phys_addr with an inline function. It resulted in the realmode bits generating compile warnings about types. In order to resolve that I am relocating the address translation to page_64.h since this is in keeping with where these functions are located in 32 bit. In addtion I have relocated several functions defined in init_64.c to pgtable_64.h as this seems to be where most of the functions related to memory initialization were already located. [ hpa: added missing #include to apic_numachip.c, as reported by Yinghai Lu. ] Signed-off-by: Alexander Duyck Link: http://lkml.kernel.org/r/20121116215244.8521.31505.stgit@ahduyck-cp1.jf.intel.com Signed-off-by: H. Peter Anvin Cc: Yinghai Lu Cc: Daniel J Blueman --- arch/x86/include/asm/page_64.h | 19 +++++++++++++++++++ arch/x86/include/asm/page_64_types.h | 22 ---------------------- arch/x86/include/asm/pgtable_64.h | 5 +++++ 3 files changed, 24 insertions(+), 22 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index 072694ed81a5..4150999fc20e 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -3,4 +3,23 @@ #include +#ifndef __ASSEMBLY__ + +/* duplicated to the one in bootmem.h */ +extern unsigned long max_pfn; +extern unsigned long phys_base; + +extern unsigned long __phys_addr(unsigned long); + +#define __phys_reloc_hide(x) (x) + +#ifdef CONFIG_FLATMEM +#define pfn_valid(pfn) ((pfn) < max_pfn) +#endif + +void clear_page(void *page); +void copy_page(void *to, void *from); + +#endif /* !__ASSEMBLY__ */ + #endif /* _ASM_X86_PAGE_64_H */ diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 320f7bb95f76..8b491e66eaa8 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -50,26 +50,4 @@ #define KERNEL_IMAGE_SIZE (512 * 1024 * 1024) #define KERNEL_IMAGE_START _AC(0xffffffff80000000, UL) -#ifndef __ASSEMBLY__ -void clear_page(void *page); -void copy_page(void *to, void *from); - -/* duplicated to the one in bootmem.h */ -extern unsigned long max_pfn; -extern unsigned long phys_base; - -extern unsigned long __phys_addr(unsigned long); -#define __phys_reloc_hide(x) (x) - -#define vmemmap ((struct page *)VMEMMAP_START) - -extern void init_extra_mapping_uc(unsigned long phys, unsigned long size); -extern void init_extra_mapping_wb(unsigned long phys, unsigned long size); - -#endif /* !__ASSEMBLY__ */ - -#ifdef CONFIG_FLATMEM -#define pfn_valid(pfn) ((pfn) < max_pfn) -#endif - #endif /* _ASM_X86_PAGE_64_DEFS_H */ diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 47356f9df82e..b5d30ad39022 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -183,6 +183,11 @@ extern void cleanup_highmap(void); #define __HAVE_ARCH_PTE_SAME +#define vmemmap ((struct page *)VMEMMAP_START) + +extern void init_extra_mapping_uc(unsigned long phys, unsigned long size); +extern void init_extra_mapping_wb(unsigned long phys, unsigned long size); + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_64_H */ -- cgit v1.2.3 From 0bdf525f04afd3a32c14e5a8778771f9c9e0f074 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 16 Nov 2012 13:53:51 -0800 Subject: x86: Improve __phys_addr performance by making use of carry flags and inlining This patch is meant to improve overall system performance when making use of the __phys_addr call. To do this I have implemented several changes. First if CONFIG_DEBUG_VIRTUAL is not defined __phys_addr is made an inline, similar to how this is currently handled in 32 bit. However in order to do this it is required to export phys_base so that it is available if __phys_addr is used in kernel modules. The second change was to streamline the code by making use of the carry flag on an add operation instead of performing a compare on a 64 bit value. The advantage to this is that it allows us to significantly reduce the overall size of the call. On my Xeon E5 system the entire __phys_addr inline call consumes a little less than 32 bytes and 5 instructions. I also applied similar logic to the debug version of the function. My testing shows that the debug version of the function with this patch applied is slightly faster than the non-debug version without the patch. Finally I also applied the same logic changes to __virt_addr_valid since it used the same general code flow as __phys_addr and could achieve similar gains though these changes. Signed-off-by: Alexander Duyck Link: http://lkml.kernel.org/r/20121116215315.8521.46270.stgit@ahduyck-cp1.jf.intel.com Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/page_64.h | 14 ++++++++++++++ arch/x86/kernel/x8664_ksyms_64.c | 3 +++ arch/x86/mm/physaddr.c | 40 +++++++++++++++++++++++++--------------- 3 files changed, 42 insertions(+), 15 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index 4150999fc20e..5138174c2101 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -9,7 +9,21 @@ extern unsigned long max_pfn; extern unsigned long phys_base; +static inline unsigned long __phys_addr_nodebug(unsigned long x) +{ + unsigned long y = x - __START_KERNEL_map; + + /* use the carry flag to determine if x was < __START_KERNEL_map */ + x = y + ((x > y) ? phys_base : (__START_KERNEL_map - PAGE_OFFSET)); + + return x; +} + +#ifdef CONFIG_DEBUG_VIRTUAL extern unsigned long __phys_addr(unsigned long); +#else +#define __phys_addr(x) __phys_addr_nodebug(x) +#endif #define __phys_reloc_hide(x) (x) diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index 1330dd102950..b014d9414d08 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -59,6 +59,9 @@ EXPORT_SYMBOL(memcpy); EXPORT_SYMBOL(__memcpy); EXPORT_SYMBOL(memmove); +#ifndef CONFIG_DEBUG_VIRTUAL +EXPORT_SYMBOL(phys_base); +#endif EXPORT_SYMBOL(empty_zero_page); #ifndef CONFIG_PARAVIRT EXPORT_SYMBOL(native_load_gs_index); diff --git a/arch/x86/mm/physaddr.c b/arch/x86/mm/physaddr.c index d2e2735327b4..fd40d75109ef 100644 --- a/arch/x86/mm/physaddr.c +++ b/arch/x86/mm/physaddr.c @@ -8,33 +8,43 @@ #ifdef CONFIG_X86_64 +#ifdef CONFIG_DEBUG_VIRTUAL unsigned long __phys_addr(unsigned long x) { - if (x >= __START_KERNEL_map) { - x -= __START_KERNEL_map; - VIRTUAL_BUG_ON(x >= KERNEL_IMAGE_SIZE); - x += phys_base; + unsigned long y = x - __START_KERNEL_map; + + /* use the carry flag to determine if x was < __START_KERNEL_map */ + if (unlikely(x > y)) { + x = y + phys_base; + + VIRTUAL_BUG_ON(y >= KERNEL_IMAGE_SIZE); } else { - VIRTUAL_BUG_ON(x < PAGE_OFFSET); - x -= PAGE_OFFSET; - VIRTUAL_BUG_ON(!phys_addr_valid(x)); + x = y + (__START_KERNEL_map - PAGE_OFFSET); + + /* carry flag will be set if starting x was >= PAGE_OFFSET */ + VIRTUAL_BUG_ON((x > y) || !phys_addr_valid(x)); } + return x; } EXPORT_SYMBOL(__phys_addr); +#endif bool __virt_addr_valid(unsigned long x) { - if (x >= __START_KERNEL_map) { - x -= __START_KERNEL_map; - if (x >= KERNEL_IMAGE_SIZE) + unsigned long y = x - __START_KERNEL_map; + + /* use the carry flag to determine if x was < __START_KERNEL_map */ + if (unlikely(x > y)) { + x = y + phys_base; + + if (y >= KERNEL_IMAGE_SIZE) return false; - x += phys_base; } else { - if (x < PAGE_OFFSET) - return false; - x -= PAGE_OFFSET; - if (!phys_addr_valid(x)) + x = y + (__START_KERNEL_map - PAGE_OFFSET); + + /* carry flag will be set if starting x was >= PAGE_OFFSET */ + if ((x > y) || !phys_addr_valid(x)) return false; } -- cgit v1.2.3 From 7d74275d39def4d3ccc8cf4725388bf79ef13861 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 16 Nov 2012 13:55:46 -0800 Subject: x86: Make it so that __pa_symbol can only process kernel symbols on x86_64 I submitted an earlier patch that make __phys_addr an inline. This obviously results in an increase in the code size. One step I can take to reduce that is to make it so that the __pa_symbol call does a direct translation for kernel addresses instead of covering all of virtual memory. On my system this reduced the size for __pa_symbol from 5 instructions totalling 30 bytes to 3 instructions totalling 16 bytes. Signed-off-by: Alexander Duyck Link: http://lkml.kernel.org/r/20121116215356.8521.92472.stgit@ahduyck-cp1.jf.intel.com Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/page.h | 3 ++- arch/x86/include/asm/page_32.h | 1 + arch/x86/include/asm/page_64.h | 3 +++ arch/x86/mm/physaddr.c | 11 +++++++++++ 4 files changed, 17 insertions(+), 1 deletion(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h index 8ca82839288a..3698a6a0a940 100644 --- a/arch/x86/include/asm/page.h +++ b/arch/x86/include/asm/page.h @@ -44,7 +44,8 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr, * case properly. Once all supported versions of gcc understand it, we can * remove this Voodoo magic stuff. (i.e. once gcc3.x is deprecated) */ -#define __pa_symbol(x) __pa(__phys_reloc_hide((unsigned long)(x))) +#define __pa_symbol(x) \ + __phys_addr_symbol(__phys_reloc_hide((unsigned long)(x))) #define __va(x) ((void *)((unsigned long)(x)+PAGE_OFFSET)) diff --git a/arch/x86/include/asm/page_32.h b/arch/x86/include/asm/page_32.h index da4e762406f7..4d550d04b609 100644 --- a/arch/x86/include/asm/page_32.h +++ b/arch/x86/include/asm/page_32.h @@ -15,6 +15,7 @@ extern unsigned long __phys_addr(unsigned long); #else #define __phys_addr(x) __phys_addr_nodebug(x) #endif +#define __phys_addr_symbol(x) __phys_addr(x) #define __phys_reloc_hide(x) RELOC_HIDE((x), 0) #ifdef CONFIG_FLATMEM diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index 5138174c2101..0f1ddee6a0ce 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -21,8 +21,11 @@ static inline unsigned long __phys_addr_nodebug(unsigned long x) #ifdef CONFIG_DEBUG_VIRTUAL extern unsigned long __phys_addr(unsigned long); +extern unsigned long __phys_addr_symbol(unsigned long); #else #define __phys_addr(x) __phys_addr_nodebug(x) +#define __phys_addr_symbol(x) \ + ((unsigned long)(x) - __START_KERNEL_map + phys_base) #endif #define __phys_reloc_hide(x) (x) diff --git a/arch/x86/mm/physaddr.c b/arch/x86/mm/physaddr.c index fd40d75109ef..c73feddd518d 100644 --- a/arch/x86/mm/physaddr.c +++ b/arch/x86/mm/physaddr.c @@ -28,6 +28,17 @@ unsigned long __phys_addr(unsigned long x) return x; } EXPORT_SYMBOL(__phys_addr); + +unsigned long __phys_addr_symbol(unsigned long x) +{ + unsigned long y = x - __START_KERNEL_map; + + /* only check upper bounds since lower bounds will trigger carry */ + VIRTUAL_BUG_ON(y >= KERNEL_IMAGE_SIZE); + + return y + phys_base; +} +EXPORT_SYMBOL(__phys_addr_symbol); #endif bool __virt_addr_valid(unsigned long x) -- cgit v1.2.3 From 4cbeb51b860c57ba8b2ae50c4016ee7a41f5fbd5 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Tue, 22 Jan 2013 13:24:31 -0800 Subject: x86, mm: Pagetable level size/shift/mask helpers I plan to use lookup_address() to walk the kernel pagetables in a later patch. It returns a "pte" and the level in the pagetables where the "pte" was found. The level is just an enum and needs to be converted to a useful value in order to do address calculations with it. These helpers will be used in at least two places. This also gives the anonymous enum a real name so that no one gets confused about what they should be passing in to these helpers. "PTE_SHIFT" was chosen for naming consistency with the other pagetable levels (PGD/PUD/PMD_SHIFT). Cc: H. Peter Anvin Signed-off-by: Dave Hansen Link: http://lkml.kernel.org/r/20130122212431.405D3A8C@kernel.stglabs.ibm.com Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/pgtable.h | 14 ++++++++++++++ arch/x86/include/asm/pgtable_types.h | 2 +- 2 files changed, 15 insertions(+), 1 deletion(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 5199db2923d3..bc28e6fe7052 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -390,6 +390,7 @@ pte_t *populate_extra_pte(unsigned long vaddr); #ifndef __ASSEMBLY__ #include +#include static inline int pte_none(pte_t pte) { @@ -781,6 +782,19 @@ static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count) memcpy(dst, src, count * sizeof(pgd_t)); } +#define PTE_SHIFT ilog2(PTRS_PER_PTE) +static inline int page_level_shift(enum pg_level level) +{ + return (PAGE_SHIFT - PTE_SHIFT) + level * PTE_SHIFT; +} +static inline unsigned long page_level_size(enum pg_level level) +{ + return 1UL << page_level_shift(level); +} +static inline unsigned long page_level_mask(enum pg_level level) +{ + return ~(page_level_size(level) - 1); +} #include #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 3c32db8c539d..6c297e7998cc 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -331,7 +331,7 @@ extern void native_pagetable_init(void); struct seq_file; extern void arch_report_meminfo(struct seq_file *m); -enum { +enum pg_level { PG_LEVEL_NONE, PG_LEVEL_4K, PG_LEVEL_2M, -- cgit v1.2.3 From d765653445129b7c476758040e3079480775f80a Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Tue, 22 Jan 2013 13:24:33 -0800 Subject: x86, mm: Create slow_virt_to_phys() This is necessary because __pa() does not work on some kinds of memory, like vmalloc() or the alloc_remap() areas on 32-bit NUMA systems. We have some functions to do conversions _like_ this in the vmalloc() code (like vmalloc_to_page()), but they do not work on sizes other than 4k pages. We would potentially need to be able to handle all the page sizes that we use for the kernel linear mapping (4k, 2M, 1G). In practice, on 32-bit NUMA systems, the percpu areas get stuck in the alloc_remap() area. Any __pa() call on them will break and basically return garbage. This patch introduces a new function slow_virt_to_phys(), which walks the kernel page tables on x86 and should do precisely the same logical thing as __pa(), but actually work on a wider range of memory. It should work on the normal linear mapping, vmalloc(), kmap(), etc... Signed-off-by: Dave Hansen Link: http://lkml.kernel.org/r/20130122212433.4D1FCA62@kernel.stglabs.ibm.com Acked-by: Rik van Riel Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/pgtable_types.h | 1 + arch/x86/mm/pageattr.c | 31 +++++++++++++++++++++++++++++++ 2 files changed, 32 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 6c297e7998cc..9f82690f81ed 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -352,6 +352,7 @@ static inline void update_page_count(int level, unsigned long pages) { } * as a pte too. */ extern pte_t *lookup_address(unsigned long address, unsigned int *level); +extern phys_addr_t slow_virt_to_phys(void *__address); #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 2a5c9ab710b9..6d13d2a3f825 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -363,6 +363,37 @@ pte_t *lookup_address(unsigned long address, unsigned int *level) } EXPORT_SYMBOL_GPL(lookup_address); +/* + * This is necessary because __pa() does not work on some + * kinds of memory, like vmalloc() or the alloc_remap() + * areas on 32-bit NUMA systems. The percpu areas can + * end up in this kind of memory, for instance. + * + * This could be optimized, but it is only intended to be + * used at inititalization time, and keeping it + * unoptimized should increase the testing coverage for + * the more obscure platforms. + */ +phys_addr_t slow_virt_to_phys(void *__virt_addr) +{ + unsigned long virt_addr = (unsigned long)__virt_addr; + phys_addr_t phys_addr; + unsigned long offset; + enum pg_level level; + unsigned long psize; + unsigned long pmask; + pte_t *pte; + + pte = lookup_address(virt_addr, &level); + BUG_ON(!pte); + psize = page_level_size(level); + pmask = page_level_mask(level); + offset = virt_addr & ~pmask; + phys_addr = pte_pfn(*pte) << PAGE_SHIFT; + return (phys_addr | offset); +} +EXPORT_SYMBOL_GPL(slow_virt_to_phys); + /* * Set the new pmd in all the pgds we know about: */ -- cgit v1.2.3 From bb112aec5ee41427e9b9726e3d57b896709598ed Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Thu, 31 Jan 2013 13:53:10 -0800 Subject: x86-32, mm: Remove reference to resume_map_numa_kva() Remove reference to removed function resume_map_numa_kva(). Signed-off-by: H. Peter Anvin Cc: Dave Hansen Cc: Link: http://lkml.kernel.org/r/20130131005616.1C79F411@kernel.stglabs.ibm.com --- arch/x86/include/asm/mmzone_32.h | 6 ------ arch/x86/power/hibernate_32.c | 2 -- 2 files changed, 8 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h index eb05fb3b02fb..8a9b3e288cb4 100644 --- a/arch/x86/include/asm/mmzone_32.h +++ b/arch/x86/include/asm/mmzone_32.h @@ -14,12 +14,6 @@ extern struct pglist_data *node_data[]; #include -extern void resume_map_numa_kva(pgd_t *pgd); - -#else /* !CONFIG_NUMA */ - -static inline void resume_map_numa_kva(pgd_t *pgd) {} - #endif /* CONFIG_NUMA */ #ifdef CONFIG_DISCONTIGMEM diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c index 74202c1910cd..7d28c885d238 100644 --- a/arch/x86/power/hibernate_32.c +++ b/arch/x86/power/hibernate_32.c @@ -129,8 +129,6 @@ static int resume_physical_mapping_init(pgd_t *pgd_base) } } - resume_map_numa_kva(pgd_base); - return 0; } -- cgit v1.2.3