From 2ef43ec772551e975a6ea7cf22b59c84955aadf9 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 22 Sep 2009 16:45:41 -0700 Subject: kcore: use usual list for kclist This patchset is for /proc/kcore. With this, - many per-arch hooks are removed. - /proc/kcore will know really valid physical memory area. - /proc/kcore will be aware of memory hotplug. - /proc/kcore will be architecture independent i.e. if an arch supports CONFIG_MMU, it can use /proc/kcore. (if the arch uses usual memory layout.) This patch: /proc/kcore uses its own list handling codes. It's better to use generic list codes. No changes in logic. just clean up. Signed-off-by: KAMEZAWA Hiroyuki Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: WANG Cong Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/proc_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/proc_fs.h') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index e6e77d31c418..0aff2a62eba9 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -79,7 +79,7 @@ struct proc_dir_entry { }; struct kcore_list { - struct kcore_list *next; + struct list_head list; unsigned long addr; size_t size; }; -- cgit v1.2.3 From c30bb2a25fcfde6157e6154a32c14686fb0bedbe Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 22 Sep 2009 16:45:43 -0700 Subject: kcore: add kclist types Presently, kclist_add() only eats start address and size as its arguments. Considering to make kclist dynamically reconfigulable, it's necessary to know which kclists are for System RAM and which are not. This patch add kclist types as KCORE_RAM KCORE_VMALLOC KCORE_TEXT KCORE_OTHER This "type" is used in a patch following this for detecting KCORE_RAM. Signed-off-by: KAMEZAWA Hiroyuki Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: WANG Cong Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/mm/init.c | 7 ++++--- arch/mips/mm/init.c | 7 ++++--- arch/powerpc/mm/init_32.c | 4 ++-- arch/powerpc/mm/init_64.c | 5 +++-- arch/sh/mm/init.c | 4 ++-- arch/x86/mm/init_32.c | 4 ++-- arch/x86/mm/init_64.c | 11 ++++++----- fs/proc/kcore.c | 3 ++- include/linux/proc_fs.h | 13 +++++++++++-- 9 files changed, 36 insertions(+), 22 deletions(-) (limited to 'include/linux/proc_fs.h') diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 1d286244a562..f6a3c21a2826 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -639,9 +639,10 @@ mem_init (void) high_memory = __va(max_low_pfn * PAGE_SIZE); - kclist_add(&kcore_mem, __va(0), max_low_pfn * PAGE_SIZE); - kclist_add(&kcore_vmem, (void *)VMALLOC_START, VMALLOC_END-VMALLOC_START); - kclist_add(&kcore_kernel, _stext, _end - _stext); + kclist_add(&kcore_mem, __va(0), max_low_pfn * PAGE_SIZE, KCORE_RAM); + kclist_add(&kcore_vmem, (void *)VMALLOC_START, + VMALLOC_END-VMALLOC_START, KCORE_VMALLOC); + kclist_add(&kcore_kernel, _stext, _end - _stext, KCORE_TEXT); for_each_online_pgdat(pgdat) if (pgdat->bdata->node_bootmem_map) diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 1f4ee4797a6e..f8661985bff6 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -409,11 +409,12 @@ void __init mem_init(void) if ((unsigned long) &_text > (unsigned long) CKSEG0) /* The -4 is a hack so that user tools don't have to handle the overflow. */ - kclist_add(&kcore_kseg0, (void *) CKSEG0, 0x80000000 - 4); + kclist_add(&kcore_kseg0, (void *) CKSEG0, + 0x80000000 - 4, KCORE_TEXT); #endif - kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT); + kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT, KCORE_RAM); kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, - VMALLOC_END-VMALLOC_START); + VMALLOC_END-VMALLOC_START, KCORE_VMALLOC); printk(KERN_INFO "Memory: %luk/%luk available (%ldk kernel code, " "%ldk reserved, %ldk data, %ldk init, %ldk highmem)\n", diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index 3ef5084b90ca..e91add90ec54 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -268,11 +268,11 @@ static int __init setup_kcore(void) size); } - kclist_add(kcore_mem, __va(base), size); + kclist_add(kcore_mem, __va(base), size, KCORE_RAM); } kclist_add(&kcore_vmem, (void *)VMALLOC_START, - VMALLOC_END-VMALLOC_START); + VMALLOC_END-VMALLOC_START, KCORE_VMALLOC); return 0; } diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 31582329cd67..9ee563101b56 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -128,10 +128,11 @@ static int __init setup_kcore(void) if (!kcore_mem) panic("%s: kmalloc failed\n", __func__); - kclist_add(kcore_mem, __va(base), size); + kclist_add(kcore_mem, __va(base), size, KCORE_RAM); } - kclist_add(&kcore_vmem, (void *)VMALLOC_START, VMALLOC_END-VMALLOC_START); + kclist_add(&kcore_vmem, (void *)VMALLOC_START, + VMALLOC_END-VMALLOC_START, KCORE_VMALLOC); return 0; } diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index fabb7c6f48d2..ef56c9f9d7ba 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -226,9 +226,9 @@ void __init mem_init(void) datasize = (unsigned long) &_edata - (unsigned long) &_etext; initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin; - kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT); + kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT, KCORE_RAM); kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, - VMALLOC_END - VMALLOC_START); + VMALLOC_END - VMALLOC_START, KCORE_VMALLOC); printk(KERN_INFO "Memory: %luk/%luk available (%dk kernel code, " "%dk data, %dk init)\n", diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index b49b4f67453d..2cbc40112932 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -886,9 +886,9 @@ void __init mem_init(void) datasize = (unsigned long) &_edata - (unsigned long) &_etext; initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin; - kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT); + kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT, KCORE_RAM); kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, - VMALLOC_END-VMALLOC_START); + VMALLOC_END-VMALLOC_START, KCORE_VMALLOC); printk(KERN_INFO "Memory: %luk/%luk available (%dk kernel code, " "%dk reserved, %dk data, %dk init, %ldk highmem)\n", diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 810bd31e7f5f..c05810b614fe 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -677,13 +677,14 @@ void __init mem_init(void) initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin; /* Register memory areas for /proc/kcore */ - kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT); + kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT, KCORE_RAM); kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, - VMALLOC_END-VMALLOC_START); - kclist_add(&kcore_kernel, &_stext, _end - _stext); - kclist_add(&kcore_modules, (void *)MODULES_VADDR, MODULES_LEN); + VMALLOC_END-VMALLOC_START, KCORE_VMALLOC); + kclist_add(&kcore_kernel, &_stext, _end - _stext, KCORE_TEXT); + kclist_add(&kcore_modules, (void *)MODULES_VADDR, MODULES_LEN, + KCORE_OTHER); kclist_add(&kcore_vsyscall, (void *)VSYSCALL_START, - VSYSCALL_END - VSYSCALL_START); + VSYSCALL_END - VSYSCALL_START, KCORE_OTHER); printk(KERN_INFO "Memory: %luk/%luk available (%ldk kernel code, " "%ldk absent, %ldk reserved, %ldk data, %ldk init)\n", diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index f9327e51ce99..659c1635db81 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -62,10 +62,11 @@ static LIST_HEAD(kclist_head); static DEFINE_RWLOCK(kclist_lock); void -kclist_add(struct kcore_list *new, void *addr, size_t size) +kclist_add(struct kcore_list *new, void *addr, size_t size, int type) { new->addr = (unsigned long)addr; new->size = size; + new->type = type; write_lock(&kclist_lock); list_add_tail(&new->list, &kclist_head); diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 0aff2a62eba9..bd7b840765a0 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -78,10 +78,18 @@ struct proc_dir_entry { struct list_head pde_openers; /* who did ->open, but not ->release */ }; +enum kcore_type { + KCORE_TEXT, + KCORE_VMALLOC, + KCORE_RAM, + KCORE_OTHER, +}; + struct kcore_list { struct list_head list; unsigned long addr; size_t size; + int type; }; struct vmcore { @@ -233,11 +241,12 @@ static inline void dup_mm_exe_file(struct mm_struct *oldmm, #endif /* CONFIG_PROC_FS */ #if !defined(CONFIG_PROC_KCORE) -static inline void kclist_add(struct kcore_list *new, void *addr, size_t size) +static inline void +kclist_add(struct kcore_list *new, void *addr, size_t size, int type) { } #else -extern void kclist_add(struct kcore_list *, void *, size_t); +extern void kclist_add(struct kcore_list *, void *, size_t, int type); #endif union proc_op { -- cgit v1.2.3 From 26562c59fa9111ae3ea7b78045889662aac9e5ac Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 22 Sep 2009 16:45:49 -0700 Subject: kcore: register vmemmap range Benjamin Herrenschmidt pointed out that vmemmap range is not included in KCORE_RAM, KCORE_VMALLOC .... This adds KCORE_VMEMMAP if SPARSEMEM_VMEMMAP is used. By this, vmemmap can be readable via /proc/kcore Because it's not vmalloc area, vread/vwrite cannot be used. But the range is static against the memory layout, this patch handles vmemmap area by the same scheme with physical memory. This patch assumes SPARSEMEM_VMEMMAP range is not in VMALLOC range. It's correct now. [akpm@linux-foundation.org: fix typo] Signed-off-by: KAMEZAWA Hiroyuki Cc: Jiri Slaby Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: WANG Cong Cc: Benjamin Herrenschmidt Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/kcore.c | 52 +++++++++++++++++++++++++++++++++++++++++++++++-- include/linux/proc_fs.h | 1 + 2 files changed, 51 insertions(+), 2 deletions(-) (limited to 'include/linux/proc_fs.h') diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 802de33d6341..78970e6f715c 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -103,7 +103,7 @@ static void free_kclist_ents(struct list_head *head) } } /* - * Replace all KCORE_RAM information with passed list. + * Replace all KCORE_RAM/KCORE_VMEMMAP information with passed list. */ static void __kcore_update_ram(struct list_head *list) { @@ -113,7 +113,8 @@ static void __kcore_update_ram(struct list_head *list) write_lock(&kclist_lock); if (kcore_need_update) { list_for_each_entry_safe(pos, tmp, &kclist_head, list) { - if (pos->type == KCORE_RAM) + if (pos->type == KCORE_RAM + || pos->type == KCORE_VMEMMAP) list_move(&pos->list, &garbage); } list_splice_tail(list, &kclist_head); @@ -151,6 +152,47 @@ static int kcore_update_ram(void) #else /* !CONFIG_HIGHMEM */ +#ifdef CONFIG_SPARSEMEM_VMEMMAP +/* calculate vmemmap's address from given system ram pfn and register it */ +int get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head) +{ + unsigned long pfn = __pa(ent->addr) >> PAGE_SHIFT; + unsigned long nr_pages = ent->size >> PAGE_SHIFT; + unsigned long start, end; + struct kcore_list *vmm, *tmp; + + + start = ((unsigned long)pfn_to_page(pfn)) & PAGE_MASK; + end = ((unsigned long)pfn_to_page(pfn + nr_pages)) - 1; + end = ALIGN(end, PAGE_SIZE); + /* overlap check (because we have to align page */ + list_for_each_entry(tmp, head, list) { + if (tmp->type != KCORE_VMEMMAP) + continue; + if (start < tmp->addr + tmp->size) + if (end > tmp->addr) + end = tmp->addr; + } + if (start < end) { + vmm = kmalloc(sizeof(*vmm), GFP_KERNEL); + if (!vmm) + return 0; + vmm->addr = start; + vmm->size = end - start; + vmm->type = KCORE_VMEMMAP; + list_add_tail(&vmm->list, head); + } + return 1; + +} +#else +int get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head) +{ + return 1; +} + +#endif + static int kclist_add_private(unsigned long pfn, unsigned long nr_pages, void *arg) { @@ -181,6 +223,12 @@ kclist_add_private(unsigned long pfn, unsigned long nr_pages, void *arg) ent->type = KCORE_RAM; list_add_tail(&ent->list, head); + + if (!get_sparsemem_vmemmap_info(ent, head)) { + list_del(&ent->list); + goto free_out; + } + return 0; free_out: kfree(ent); diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index bd7b840765a0..379eaed72d4b 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -82,6 +82,7 @@ enum kcore_type { KCORE_TEXT, KCORE_VMALLOC, KCORE_RAM, + KCORE_VMEMMAP, KCORE_OTHER, }; -- cgit v1.2.3