diff options
Diffstat (limited to 'arch/x86')
| -rw-r--r-- | arch/x86/Kconfig | 2 | ||||
| -rw-r--r-- | arch/x86/boot/compressed/Makefile | 6 | ||||
| -rw-r--r-- | arch/x86/boot/compressed/misc.c | 4 | ||||
| -rw-r--r-- | arch/x86/ia32/ia32_aout.c | 2 | ||||
| -rw-r--r-- | arch/x86/include/asm/e820.h | 2 | ||||
| -rw-r--r-- | arch/x86/include/asm/pgtable.h | 24 | ||||
| -rw-r--r-- | arch/x86/include/asm/pgtable_types.h | 12 | ||||
| -rw-r--r-- | arch/x86/kernel/e820.c | 72 | ||||
| -rw-r--r-- | arch/x86/mm/init.c | 19 | ||||
| -rw-r--r-- | arch/x86/mm/mmap.c | 2 | ||||
| -rw-r--r-- | arch/x86/net/bpf_jit_comp.c | 4 | ||||
| -rw-r--r-- | arch/x86/platform/efi/efi.c | 15 |
12 files changed, 144 insertions, 20 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 6a154a91c7e7..08bffb2bb962 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -65,6 +65,7 @@ config X86 select HAVE_KERNEL_LZMA select HAVE_KERNEL_XZ select HAVE_KERNEL_LZO + select HAVE_KERNEL_LZ4 select HAVE_HW_BREAKPOINT select HAVE_MIXED_BREAKPOINTS_REGS select PERF_EVENTS @@ -102,6 +103,7 @@ config X86 select HAVE_ARCH_SECCOMP_FILTER select BUILDTIME_EXTABLE_SORT select GENERIC_CMOS_UPDATE + select HAVE_ARCH_SOFT_DIRTY select CLOCKSOURCE_WATCHDOG select GENERIC_CLOCKEVENTS select ARCH_CLOCKSOURCE_DATA if X86_64 diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 5ef205c5f37b..dcd90df10ab4 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -4,7 +4,8 @@ # create a compressed vmlinux image from the original vmlinux # -targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.xz vmlinux.bin.lzo +targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \ + vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4 KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2 KBUILD_CFLAGS += -fno-strict-aliasing -fPIC @@ -63,12 +64,15 @@ $(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y) FORCE $(call if_changed,xzkern) $(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) FORCE $(call if_changed,lzo) +$(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y) FORCE + $(call if_changed,lz4) suffix-$(CONFIG_KERNEL_GZIP) := gz suffix-$(CONFIG_KERNEL_BZIP2) := bz2 suffix-$(CONFIG_KERNEL_LZMA) := lzma suffix-$(CONFIG_KERNEL_XZ) := xz suffix-$(CONFIG_KERNEL_LZO) := lzo +suffix-$(CONFIG_KERNEL_LZ4) := lz4 quiet_cmd_mkpiggy = MKPIGGY $@ cmd_mkpiggy = $(obj)/mkpiggy $< > $@ || ( rm -f $@ ; false ) diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 7cb56c6ca351..0319c88290a5 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -145,6 +145,10 @@ static int lines, cols; #include "../../../../lib/decompress_unlzo.c" #endif +#ifdef CONFIG_KERNEL_LZ4 +#include "../../../../lib/decompress_unlz4.c" +#endif + static void scroll(void) { int i; diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index 805078e08013..fbeba82c703b 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -308,8 +308,6 @@ static int load_aout_binary(struct linux_binprm *bprm) (current->mm->start_data = N_DATADDR(ex)); current->mm->brk = ex.a_bss + (current->mm->start_brk = N_BSSADDR(ex)); - current->mm->free_area_cache = TASK_UNMAPPED_BASE; - current->mm->cached_hole_size = 0; retval = setup_arg_pages(bprm, IA32_STACK_TOP, EXSTACK_DEFAULT); if (retval < 0) { diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index cccd07fa5e3a..b8e9224f0b45 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -17,6 +17,8 @@ extern unsigned long pci_mem_start; extern int e820_any_mapped(u64 start, u64 end, unsigned type); extern int e820_all_mapped(u64 start, u64 end, unsigned type); extern void e820_add_region(u64 start, u64 size, int type); +extern void e820_add_limit_region(u64 start, u64 size, int type); +extern void e820_adjust_region(u64 *start, u64 *size); extern void e820_print_map(char *who); extern int sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, u32 *pnr_map); diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 1e672234c4ff..ebf937362479 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -207,7 +207,7 @@ static inline pte_t pte_mkexec(pte_t pte) static inline pte_t pte_mkdirty(pte_t pte) { - return pte_set_flags(pte, _PAGE_DIRTY); + return pte_set_flags(pte, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); } static inline pte_t pte_mkyoung(pte_t pte) @@ -271,7 +271,7 @@ static inline pmd_t pmd_wrprotect(pmd_t pmd) static inline pmd_t pmd_mkdirty(pmd_t pmd) { - return pmd_set_flags(pmd, _PAGE_DIRTY); + return pmd_set_flags(pmd, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); } static inline pmd_t pmd_mkhuge(pmd_t pmd) @@ -294,6 +294,26 @@ static inline pmd_t pmd_mknotpresent(pmd_t pmd) return pmd_clear_flags(pmd, _PAGE_PRESENT); } +static inline int pte_soft_dirty(pte_t pte) +{ + return pte_flags(pte) & _PAGE_SOFT_DIRTY; +} + +static inline int pmd_soft_dirty(pmd_t pmd) +{ + return pmd_flags(pmd) & _PAGE_SOFT_DIRTY; +} + +static inline pte_t pte_mksoft_dirty(pte_t pte) +{ + return pte_set_flags(pte, _PAGE_SOFT_DIRTY); +} + +static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) +{ + return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY); +} + /* * Mask out unsupported bits in a present pgprot. Non-present pgprots * can use those bits for other purposes, so leave them be. diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index e6423002c10b..c98ac63aae48 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -55,6 +55,18 @@ #define _PAGE_HIDDEN (_AT(pteval_t, 0)) #endif +/* + * The same hidden bit is used by kmemcheck, but since kmemcheck + * works on kernel pages while soft-dirty engine on user space, + * they do not conflict with each other. + */ + +#ifdef CONFIG_MEM_SOFT_DIRTY +#define _PAGE_SOFT_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_HIDDEN) +#else +#define _PAGE_SOFT_DIRTY (_AT(pteval_t, 0)) +#endif + #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) #define _PAGE_NX (_AT(pteval_t, 1) << _PAGE_BIT_NX) #else diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index d32abeabbda5..0d5bb689649a 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -47,6 +47,7 @@ unsigned long pci_mem_start = 0xaeedbabe; #ifdef CONFIG_PCI EXPORT_SYMBOL(pci_mem_start); #endif +static u64 mem_limit = ~0ULL; /* * This function checks if any part of the range <start,end> is mapped @@ -108,7 +109,7 @@ int __init e820_all_mapped(u64 start, u64 end, unsigned type) * Add a memory region to the kernel e820 map. */ static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size, - int type) + int type, bool limited) { int x = e820x->nr_map; @@ -119,6 +120,22 @@ static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size, return; } + if (limited) { + if (start >= mem_limit) { + printk(KERN_ERR "e820: ignoring [mem %#010llx-%#010llx]\n", + (unsigned long long)start, + (unsigned long long)(start + size - 1)); + return; + } + + if (mem_limit - start < size) { + printk(KERN_ERR "e820: ignoring [mem %#010llx-%#010llx]\n", + (unsigned long long)mem_limit, + (unsigned long long)(start + size - 1)); + size = mem_limit - start; + } + } + e820x->map[x].addr = start; e820x->map[x].size = size; e820x->map[x].type = type; @@ -127,7 +144,37 @@ static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size, void __init e820_add_region(u64 start, u64 size, int type) { - __e820_add_region(&e820, start, size, type); + __e820_add_region(&e820, start, size, type, false); +} + +/* + * do_add_efi_memmap() calls this function(). + * + * Note: BOOT_SERVICES_{CODE,DATA} regions on some efi machines are marked + * as E820_RAM, and they are needed to be mapped. Please use e820_add_region() + * to add BOOT_SERVICES_{CODE,DATA} regions. + */ +void __init e820_add_limit_region(u64 start, u64 size, int type) +{ + /* + * efi_init() is called after finish_e820_parsing(), so we should + * check whether [start, start + size) contains address above + * mem_limit if the type is E820_RAM. + */ + __e820_add_region(&e820, start, size, type, type == E820_RAM); +} + +void __init e820_adjust_region(u64 *start, u64 *size) +{ + if (*start >= mem_limit) { + *size = 0; + return; + } + + if (mem_limit - *start < *size) + *size = mem_limit - *start; + + return; } static void __init e820_print_type(u32 type) @@ -455,8 +502,9 @@ static u64 __init __e820_update_range(struct e820map *e820x, u64 start, /* new range is totally covered? */ if (ei->addr < start && ei_end > end) { - __e820_add_region(e820x, start, size, new_type); - __e820_add_region(e820x, end, ei_end - end, ei->type); + __e820_add_region(e820x, start, size, new_type, false); + __e820_add_region(e820x, end, ei_end - end, ei->type, + false); ei->size = start - ei->addr; real_updated_size += size; continue; @@ -469,7 +517,7 @@ static u64 __init __e820_update_range(struct e820map *e820x, u64 start, continue; __e820_add_region(e820x, final_start, final_end - final_start, - new_type); + new_type, false); real_updated_size += final_end - final_start; @@ -809,7 +857,7 @@ static int userdef __initdata; /* "mem=nopentium" disables the 4MB page tables. */ static int __init parse_memopt(char *p) { - u64 mem_size; + char *oldp; if (!p) return -EINVAL; @@ -825,11 +873,11 @@ static int __init parse_memopt(char *p) } userdef = 1; - mem_size = memparse(p, &p); + oldp = p; + mem_limit = memparse(p, &p); /* don't remove all of memory when handling "mem={invalid}" param */ - if (mem_size == 0) + if (mem_limit == 0 || p == oldp) return -EINVAL; - e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1); return 0; } @@ -895,6 +943,12 @@ early_param("memmap", parse_memmap_opt); void __init finish_e820_parsing(void) { + if (mem_limit != ~0ULL) { + userdef = 1; + e820_remove_range(mem_limit, ULLONG_MAX - mem_limit, + E820_RAM, 1); + } + if (userdef) { u32 nr = e820.nr_map; diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index fdc5dca14fb3..fed9993d0c5b 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -359,7 +359,17 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, } /* - * would have hole in the middle or ends, and only ram parts will be mapped. + * We need to iterate through E820 memory map and create direct mappings + * for only E820_RAM and E820_KERN_RESERVED regions. We cannot simply + * create direct mappings for all pfns from [0 to max_low_pfn) and + * [4GB to max_pfn) because of possible memory holes in high addresses + * that cannot be marked as UC by fixed/variable range MTRRs. + * Depending on the alignment of E820 ranges, this may possibly result + * in using smaller size (i.e. 4K instead of 2M or 1G) page tables. + * + * init_mem_mapping call init_range_memory_mapping with big range. + * That range would have hole in the middle or ends, and only ram parts + * will be mapped in init_range_memory_mapping. */ static unsigned long __init init_range_memory_mapping( unsigned long r_start, @@ -419,6 +429,13 @@ void __init init_mem_mapping(void) max_pfn_mapped = 0; /* will get exact value next */ min_pfn_mapped = real_end >> PAGE_SHIFT; last_start = start = real_end; + + /* + * We start from the top (end of memory) and go to the bottom. + * The memblock_find_in_range gets us a block of RAM from the + * end of RAM in [min_pfn_mapped, max_pfn_mapped) as new pages + * for page table. + */ while (last_start > ISA_END_ADDRESS) { if (last_start > step_size) { start = round_down(last_start - 1, step_size); diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 845df6835f9f..62c29a5bfe26 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -115,10 +115,8 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (mmap_is_legacy()) { mm->mmap_base = mmap_legacy_base(); mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index f66b54086ce5..96598170c074 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -749,6 +749,10 @@ static void jit_free_defer(struct work_struct *arg) void bpf_jit_free(struct sk_filter *fp) { if (fp->bpf_func != sk_run_filter) { + /* + * bpf_jit_free() can be called from softirq; module_free() + * requires process context. + */ struct work_struct *work = (struct work_struct *)fp->bpf_func; INIT_WORK(work, jit_free_defer); diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 55856b2310d3..83e5cc472752 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -419,10 +419,17 @@ static void __init do_add_efi_memmap(void) int e820_type; switch (md->type) { - case EFI_LOADER_CODE: - case EFI_LOADER_DATA: case EFI_BOOT_SERVICES_CODE: case EFI_BOOT_SERVICES_DATA: + /* EFI_BOOT_SERVICES_{CODE,DATA} needs to be mapped */ + if (md->attribute & EFI_MEMORY_WB) + e820_type = E820_RAM; + else + e820_type = E820_RESERVED; + e820_add_region(start, size, e820_type); + continue; + case EFI_LOADER_CODE: + case EFI_LOADER_DATA: case EFI_CONVENTIONAL_MEMORY: if (md->attribute & EFI_MEMORY_WB) e820_type = E820_RAM; @@ -447,7 +454,7 @@ static void __init do_add_efi_memmap(void) e820_type = E820_RESERVED; break; } - e820_add_region(start, size, e820_type); + e820_add_limit_region(start, size, e820_type); } sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); } @@ -555,6 +562,8 @@ void __init efi_free_boot_services(void) md->type != EFI_BOOT_SERVICES_DATA) continue; + e820_adjust_region(&start, &size); + /* Could not reserve boot area */ if (!size) continue; |