From 77ef50a522717fa040636ee1017179ceba12ff62 Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Wed, 18 Jun 2008 17:08:48 +0200 Subject: x86: consolidate header guards This patch is the result of an automatic script that consolidates the format of all the headers in include/asm-x86/. The format: 1. No leading underscore. Names with leading underscores are reserved. 2. Pathname components are separated by two underscores. So we can distinguish between mm_types.h and mm/types.h. 3. Everything except letters and numbers are turned into single underscores. Signed-off-by: Vegard Nossum --- include/asm-x86/page.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/asm-x86/page.h') diff --git a/include/asm-x86/page.h b/include/asm-x86/page.h index 28d7b4533b1a..068a636e0bb1 100644 --- a/include/asm-x86/page.h +++ b/include/asm-x86/page.h @@ -1,5 +1,5 @@ -#ifndef _ASM_X86_PAGE_H -#define _ASM_X86_PAGE_H +#ifndef ASM_X86__PAGE_H +#define ASM_X86__PAGE_H #include @@ -192,4 +192,4 @@ static inline pteval_t native_pte_val(pte_t pte) #define __HAVE_ARCH_GATE_AREA 1 #endif /* __KERNEL__ */ -#endif /* _ASM_X86_PAGE_H */ +#endif /* ASM_X86__PAGE_H */ -- cgit v1.2.3 From 9542ada803198e6eba29d3289abb39ea82047b92 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Wed, 24 Sep 2008 08:53:33 -0700 Subject: x86: track memtype for RAM in page struct Track the memtype for RAM pages in page struct instead of using the memtype list. This avoids the explosion in the number of entries in memtype list (of the order of 20,000 with AGP) and makes the PAT tracking simpler. We are using PG_arch_1 bit in page->flags. We still use the memtype list for non RAM pages. Signed-off-by: Suresh Siddha Signed-off-by: Venkatesh Pallipadi Signed-off-by: Ingo Molnar --- arch/x86/mm/ioremap.c | 19 ++++++++++ arch/x86/mm/pat.c | 83 ++++++++++++++++++++++++++++++++++++++++++++ include/asm-x86/cacheflush.h | 2 ++ include/asm-x86/page.h | 1 + 4 files changed, 105 insertions(+) (limited to 'include/asm-x86/page.h') diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index d4b6e6a29ae3..d03c461e045e 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -83,6 +83,25 @@ int page_is_ram(unsigned long pagenr) return 0; } +int pagerange_is_ram(unsigned long start, unsigned long end) +{ + int ram_page = 0, not_rampage = 0; + unsigned long page_nr; + + for (page_nr = (start >> PAGE_SHIFT); page_nr < (end >> PAGE_SHIFT); + ++page_nr) { + if (page_is_ram(page_nr)) + ram_page = 1; + else + not_rampage = 1; + + if (ram_page == not_rampage) + return -1; + } + + return ram_page; +} + /* * Fix up the linear direct mapping of the kernel to avoid cache attribute * conflicts. diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index f049b1d6ebdf..aceb6c7c6dba 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -210,6 +210,75 @@ static int chk_conflict(struct memtype *new, struct memtype *entry, static struct memtype *cached_entry; static u64 cached_start; +/* + * RED-PEN: TODO: Add PageReserved() check as well here, + * once we add SetPageReserved() to all the drivers using + * set_memory_* or set_pages_*. + * + * This will help prevent accidentally freeing pages + * before setting the attribute back to WB. + */ + +/* + * For RAM pages, mark the pages as non WB memory type using + * PageNonWB (PG_arch_1). We allow only one set_memory_uc() or + * set_memory_wc() on a RAM page at a time before marking it as WB again. + * This is ok, because only one driver will be owning the page and + * doing set_memory_*() calls. + * + * For now, we use PageNonWB to track that the RAM page is being mapped + * as non WB. In future, we will have to use one more flag + * (or some other mechanism in page_struct) to distinguish between + * UC and WC mapping. + */ +static int reserve_ram_pages_type(u64 start, u64 end, unsigned long req_type, + unsigned long *new_type) +{ + struct page *page; + u64 pfn, end_pfn; + + for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) { + page = pfn_to_page(pfn); + if (page_mapped(page) || PageNonWB(page)) + goto out; + + SetPageNonWB(page); + } + return 0; + +out: + end_pfn = pfn; + for (pfn = (start >> PAGE_SHIFT); pfn < end_pfn; ++pfn) { + page = pfn_to_page(pfn); + ClearPageNonWB(page); + } + + return -EINVAL; +} + +static int free_ram_pages_type(u64 start, u64 end) +{ + struct page *page; + u64 pfn, end_pfn; + + for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) { + page = pfn_to_page(pfn); + if (page_mapped(page) || !PageNonWB(page)) + goto out; + + ClearPageNonWB(page); + } + return 0; + +out: + end_pfn = pfn; + for (pfn = (start >> PAGE_SHIFT); pfn < end_pfn; ++pfn) { + page = pfn_to_page(pfn); + SetPageNonWB(page); + } + return -EINVAL; +} + /* * req_type typically has one of the: * - _PAGE_CACHE_WB @@ -232,6 +301,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, unsigned long actual_type; struct list_head *where; int err = 0; + int is_range_ram; BUG_ON(start >= end); /* end is exclusive */ @@ -270,6 +340,12 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, actual_type = pat_x_mtrr_type(start, end, req_type & _PAGE_CACHE_MASK); + is_range_ram = pagerange_is_ram(start, end); + if (is_range_ram == 1) + return reserve_ram_pages_type(start, end, req_type, new_type); + else if (is_range_ram < 0) + return -EINVAL; + new = kmalloc(sizeof(struct memtype), GFP_KERNEL); if (!new) return -ENOMEM; @@ -358,6 +434,7 @@ int free_memtype(u64 start, u64 end) { struct memtype *entry; int err = -EINVAL; + int is_range_ram; if (!pat_enabled) return 0; @@ -366,6 +443,12 @@ int free_memtype(u64 start, u64 end) if (is_ISA_range(start, end - 1)) return 0; + is_range_ram = pagerange_is_ram(start, end); + if (is_range_ram == 1) + return free_ram_pages_type(start, end); + else if (is_range_ram < 0) + return -EINVAL; + spin_lock(&memtype_lock); list_for_each_entry(entry, &memtype_list, nd) { if (entry->start == start && entry->end == end) { diff --git a/include/asm-x86/cacheflush.h b/include/asm-x86/cacheflush.h index 8e205a131250..092b9b4eb003 100644 --- a/include/asm-x86/cacheflush.h +++ b/include/asm-x86/cacheflush.h @@ -24,6 +24,8 @@ #define copy_from_user_page(vma, page, vaddr, dst, src, len) \ memcpy((dst), (src), (len)) +#define PG_non_WB PG_arch_1 +PAGEFLAG(NonWB, non_WB) /* * The set_memory_* API can be used to change various attributes of a virtual diff --git a/include/asm-x86/page.h b/include/asm-x86/page.h index 49982110e4d9..3407ac12ba34 100644 --- a/include/asm-x86/page.h +++ b/include/asm-x86/page.h @@ -57,6 +57,7 @@ typedef struct { pgdval_t pgd; } pgd_t; typedef struct { pgprotval_t pgprot; } pgprot_t; extern int page_is_ram(unsigned long pagenr); +extern int pagerange_is_ram(unsigned long start, unsigned long end); extern int devmem_is_allowed(unsigned long pagenr); extern void map_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot); -- cgit v1.2.3 From af5c2bd16ac2e5688c3bf46ea1f95112d696d294 Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Fri, 3 Oct 2008 17:54:25 +0200 Subject: x86: fix virt_addr_valid() with CONFIG_DEBUG_VIRTUAL=y, v2 virt_addr_valid() calls __pa(), which calls __phys_addr(). With CONFIG_DEBUG_VIRTUAL=y, __phys_addr() will kill the kernel if the address *isn't* valid. That's clearly wrong for virt_addr_valid(). We also incorporate the debugging checks into virt_addr_valid(). Signed-off-by: Vegard Nossum Acked-by: Jiri Slaby Signed-off-by: Ingo Molnar --- arch/x86/kernel/doublefault_32.c | 2 +- arch/x86/mm/ioremap.c | 36 ++++++++++++++++++++++++++++++++++-- include/asm-x86/page.h | 8 +++++++- include/asm-x86/page_32.h | 4 ++-- 4 files changed, 44 insertions(+), 6 deletions(-) (limited to 'include/asm-x86/page.h') diff --git a/arch/x86/kernel/doublefault_32.c b/arch/x86/kernel/doublefault_32.c index 395acb12b0d1..b4f14c6c09d9 100644 --- a/arch/x86/kernel/doublefault_32.c +++ b/arch/x86/kernel/doublefault_32.c @@ -66,6 +66,6 @@ struct tss_struct doublefault_tss __cacheline_aligned = { .ds = __USER_DS, .fs = __KERNEL_PERCPU, - .__cr3 = __phys_addr_const((unsigned long)swapper_pg_dir) + .__cr3 = __pa_nodebug(swapper_pg_dir), } }; diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 7fb737c6b54f..8876220d906b 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -45,6 +45,27 @@ unsigned long __phys_addr(unsigned long x) } EXPORT_SYMBOL(__phys_addr); +bool __virt_addr_valid(unsigned long x) +{ + if (x >= __START_KERNEL_map) { + x -= __START_KERNEL_map; + if (x >= KERNEL_IMAGE_SIZE) + return false; + x += phys_base; + } else { + if (x < PAGE_OFFSET) + return false; + x -= PAGE_OFFSET; + if (system_state == SYSTEM_BOOTING ? + x > MAXMEM : !phys_addr_valid(x)) { + return false; + } + } + + return pfn_valid(x >> PAGE_SHIFT); +} +EXPORT_SYMBOL(__virt_addr_valid); + #else static inline int phys_addr_valid(unsigned long addr) @@ -56,13 +77,24 @@ static inline int phys_addr_valid(unsigned long addr) unsigned long __phys_addr(unsigned long x) { /* VMALLOC_* aren't constants; not available at the boot time */ - VIRTUAL_BUG_ON(x < PAGE_OFFSET || (system_state != SYSTEM_BOOTING && - is_vmalloc_addr((void *)x))); + VIRTUAL_BUG_ON(x < PAGE_OFFSET); + VIRTUAL_BUG_ON(system_state != SYSTEM_BOOTING && + is_vmalloc_addr((void *) x)); return x - PAGE_OFFSET; } EXPORT_SYMBOL(__phys_addr); #endif +bool __virt_addr_valid(unsigned long x) +{ + if (x < PAGE_OFFSET) + return false; + if (system_state != SYSTEM_BOOTING && is_vmalloc_addr((void *) x)) + return false; + return pfn_valid((x - PAGE_OFFSET) >> PAGE_SHIFT); +} +EXPORT_SYMBOL(__virt_addr_valid); + #endif int page_is_ram(unsigned long pagenr) diff --git a/include/asm-x86/page.h b/include/asm-x86/page.h index c91574776751..d4f1d5791fc1 100644 --- a/include/asm-x86/page.h +++ b/include/asm-x86/page.h @@ -179,6 +179,7 @@ static inline pteval_t native_pte_flags(pte_t pte) #endif /* CONFIG_PARAVIRT */ #define __pa(x) __phys_addr((unsigned long)(x)) +#define __pa_nodebug(x) __phys_addr_nodebug((unsigned long)(x)) /* __pa_symbol should be used for C visible symbols. This seems to be the official gcc blessed way to do such arithmetic. */ #define __pa_symbol(x) __pa(__phys_reloc_hide((unsigned long)(x))) @@ -188,9 +189,14 @@ static inline pteval_t native_pte_flags(pte_t pte) #define __boot_va(x) __va(x) #define __boot_pa(x) __pa(x) +/* + * virt_to_page(kaddr) returns a valid pointer if and only if + * virt_addr_valid(kaddr) returns true. + */ #define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) #define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) -#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT) +extern bool __virt_addr_valid(unsigned long kaddr); +#define virt_addr_valid(kaddr) __virt_addr_valid((unsigned long) (kaddr)) #endif /* __ASSEMBLY__ */ diff --git a/include/asm-x86/page_32.h b/include/asm-x86/page_32.h index 9c5a737a9af9..5d6a68a1067a 100644 --- a/include/asm-x86/page_32.h +++ b/include/asm-x86/page_32.h @@ -73,11 +73,11 @@ typedef struct page *pgtable_t; #endif #ifndef __ASSEMBLY__ -#define __phys_addr_const(x) ((x) - PAGE_OFFSET) +#define __phys_addr_nodebug(x) ((x) - PAGE_OFFSET) #ifdef CONFIG_DEBUG_VIRTUAL extern unsigned long __phys_addr(unsigned long); #else -#define __phys_addr(x) ((x) - PAGE_OFFSET) +#define __phys_addr(x) __phys_addr_nodebug(x) #endif #define __phys_reloc_hide(x) RELOC_HIDE((x), 0) -- cgit v1.2.3