diff options
Diffstat (limited to 'arch')
35 files changed, 465 insertions, 274 deletions
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index a750c1425c3a..1c5021002fe4 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1693,6 +1693,12 @@ config HIGHMEM config HIGHPTE bool "Allocate 2nd-level pagetables from highmem" depends on HIGHMEM + help + The VM uses one page of physical memory for each page table. + For systems with a lot of processes, this can use a lot of + precious low memory, eventually leading to low memory being + consumed by page tables. Setting this option will allow + user-space 2nd level page tables to reside in high memory. config HW_PERF_EVENTS bool "Enable hardware performance counter support for perf events" diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug index f1b157971366..a2e16f940394 100644 --- a/arch/arm/Kconfig.debug +++ b/arch/arm/Kconfig.debug @@ -1635,7 +1635,7 @@ config PID_IN_CONTEXTIDR config DEBUG_SET_MODULE_RONX bool "Set loadable kernel module data as NX and text as RO" - depends on MODULES + depends on MODULES && MMU ---help--- This option helps catch unintended modifications to loadable kernel module's text and read-only data. It also prevents execution diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h index 1c3938f26beb..485982084fe9 100644 --- a/arch/arm/include/asm/io.h +++ b/arch/arm/include/asm/io.h @@ -140,16 +140,11 @@ static inline u32 __raw_readl(const volatile void __iomem *addr) * The _caller variety takes a __builtin_return_address(0) value for * /proc/vmalloc to use - and should only be used in non-inline functions. */ -extern void __iomem *__arm_ioremap_pfn_caller(unsigned long, unsigned long, - size_t, unsigned int, void *); extern void __iomem *__arm_ioremap_caller(phys_addr_t, size_t, unsigned int, void *); - extern void __iomem *__arm_ioremap_pfn(unsigned long, unsigned long, size_t, unsigned int); -extern void __iomem *__arm_ioremap(phys_addr_t, size_t, unsigned int); extern void __iomem *__arm_ioremap_exec(phys_addr_t, size_t, bool cached); extern void __iounmap(volatile void __iomem *addr); -extern void __arm_iounmap(volatile void __iomem *addr); extern void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t, unsigned int, void *); @@ -321,21 +316,24 @@ extern void _memset_io(volatile void __iomem *, int, size_t); static inline void memset_io(volatile void __iomem *dst, unsigned c, size_t count) { - memset((void __force *)dst, c, count); + extern void mmioset(void *, unsigned int, size_t); + mmioset((void __force *)dst, c, count); } #define memset_io(dst,c,count) memset_io(dst,c,count) static inline void memcpy_fromio(void *to, const volatile void __iomem *from, size_t count) { - memcpy(to, (const void __force *)from, count); + extern void mmiocpy(void *, const void *, size_t); + mmiocpy(to, (const void __force *)from, count); } #define memcpy_fromio(to,from,count) memcpy_fromio(to,from,count) static inline void memcpy_toio(volatile void __iomem *to, const void *from, size_t count) { - memcpy((void __force *)to, from, count); + extern void mmiocpy(void *, const void *, size_t); + mmiocpy((void __force *)to, from, count); } #define memcpy_toio(to,from,count) memcpy_toio(to,from,count) @@ -348,18 +346,61 @@ static inline void memcpy_toio(volatile void __iomem *to, const void *from, #endif /* readl */ /* - * ioremap and friends. + * ioremap() and friends. + * + * ioremap() takes a resource address, and size. Due to the ARM memory + * types, it is important to use the correct ioremap() function as each + * mapping has specific properties. + * + * Function Memory type Cacheability Cache hint + * ioremap() Device n/a n/a + * ioremap_nocache() Device n/a n/a + * ioremap_cache() Normal Writeback Read allocate + * ioremap_wc() Normal Non-cacheable n/a + * ioremap_wt() Normal Non-cacheable n/a + * + * All device mappings have the following properties: + * - no access speculation + * - no repetition (eg, on return from an exception) + * - number, order and size of accesses are maintained + * - unaligned accesses are "unpredictable" + * - writes may be delayed before they hit the endpoint device * - * ioremap takes a PCI memory address, as specified in - * Documentation/io-mapping.txt. + * ioremap_nocache() is the same as ioremap() as there are too many device + * drivers using this for device registers, and documentation which tells + * people to use it for such for this to be any different. This is not a + * safe fallback for memory-like mappings, or memory regions where the + * compiler may generate unaligned accesses - eg, via inlining its own + * memcpy. * + * All normal memory mappings have the following properties: + * - reads can be repeated with no side effects + * - repeated reads return the last value written + * - reads can fetch additional locations without side effects + * - writes can be repeated (in certain cases) with no side effects + * - writes can be merged before accessing the target + * - unaligned accesses can be supported + * - ordering is not guaranteed without explicit dependencies or barrier + * instructions + * - writes may be delayed before they hit the endpoint memory + * + * The cache hint is only a performance hint: CPUs may alias these hints. + * Eg, a CPU not implementing read allocate but implementing write allocate + * will provide a write allocate mapping instead. */ -#define ioremap(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE) -#define ioremap_nocache(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE) -#define ioremap_cache(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE_CACHED) -#define ioremap_wc(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE_WC) -#define ioremap_wt(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE) -#define iounmap __arm_iounmap +void __iomem *ioremap(resource_size_t res_cookie, size_t size); +#define ioremap ioremap +#define ioremap_nocache ioremap + +void __iomem *ioremap_cache(resource_size_t res_cookie, size_t size); +#define ioremap_cache ioremap_cache + +void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size); +#define ioremap_wc ioremap_wc +#define ioremap_wt ioremap_wc + +void iounmap(volatile void __iomem *iomem_cookie); +#define iounmap iounmap /* * io{read,write}{16,32}be() macros diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index 3a72d69b3255..6f225acc07c5 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -275,7 +275,7 @@ static inline void *phys_to_virt(phys_addr_t x) */ #define __pa(x) __virt_to_phys((unsigned long)(x)) #define __va(x) ((void *)__phys_to_virt((phys_addr_t)(x))) -#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) +#define pfn_to_kaddr(pfn) __va((phys_addr_t)(pfn) << PAGE_SHIFT) extern phys_addr_t (*arch_virt_to_idmap)(unsigned long x); diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h index bfd662e49a25..aeddd28b3595 100644 --- a/arch/arm/include/asm/pgtable-2level.h +++ b/arch/arm/include/asm/pgtable-2level.h @@ -129,7 +129,36 @@ /* * These are the memory types, defined to be compatible with - * pre-ARMv6 CPUs cacheable and bufferable bits: XXCB + * pre-ARMv6 CPUs cacheable and bufferable bits: n/a,n/a,C,B + * ARMv6+ without TEX remapping, they are a table index. + * ARMv6+ with TEX remapping, they correspond to n/a,TEX(0),C,B + * + * MT type Pre-ARMv6 ARMv6+ type / cacheable status + * UNCACHED Uncached Strongly ordered + * BUFFERABLE Bufferable Normal memory / non-cacheable + * WRITETHROUGH Writethrough Normal memory / write through + * WRITEBACK Writeback Normal memory / write back, read alloc + * MINICACHE Minicache N/A + * WRITEALLOC Writeback Normal memory / write back, write alloc + * DEV_SHARED Uncached Device memory (shared) + * DEV_NONSHARED Uncached Device memory (non-shared) + * DEV_WC Bufferable Normal memory / non-cacheable + * DEV_CACHED Writeback Normal memory / write back, read alloc + * VECTORS Variable Normal memory / variable + * + * All normal memory mappings have the following properties: + * - reads can be repeated with no side effects + * - repeated reads return the last value written + * - reads can fetch additional locations without side effects + * - writes can be repeated (in certain cases) with no side effects + * - writes can be merged before accessing the target + * - unaligned accesses can be supported + * + * All device mappings have the following properties: + * - no access speculation + * - no repetition (eg, on return from an exception) + * - number, order and size of accesses are maintained + * - unaligned accesses are "unpredictable" */ #define L_PTE_MT_UNCACHED (_AT(pteval_t, 0x00) << 2) /* 0000 */ #define L_PTE_MT_BUFFERABLE (_AT(pteval_t, 0x01) << 2) /* 0001 */ diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c index a88671cfe1ff..5e5a51a99e68 100644 --- a/arch/arm/kernel/armksyms.c +++ b/arch/arm/kernel/armksyms.c @@ -50,6 +50,9 @@ extern void __aeabi_ulcmp(void); extern void fpundefinstr(void); +void mmioset(void *, unsigned int, size_t); +void mmiocpy(void *, const void *, size_t); + /* platform dependent support */ EXPORT_SYMBOL(arm_delay_ops); @@ -88,6 +91,9 @@ EXPORT_SYMBOL(memmove); EXPORT_SYMBOL(memchr); EXPORT_SYMBOL(__memzero); +EXPORT_SYMBOL(mmioset); +EXPORT_SYMBOL(mmiocpy); + #ifdef CONFIG_MMU EXPORT_SYMBOL(copy_page); diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 7dac3086e361..cb4fb1e69778 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -410,7 +410,7 @@ ENDPROC(__fiq_abt) zero_fp .if \trace -#ifdef CONFIG_IRQSOFF_TRACER +#ifdef CONFIG_TRACE_IRQFLAGS bl trace_hardirqs_off #endif ct_user_exit save = 0 diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 90dfbedfbfb8..3d6b7821cff8 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -578,7 +578,7 @@ void handle_IPI(int ipinr, struct pt_regs *regs) struct pt_regs *old_regs = set_irq_regs(regs); if ((unsigned)ipinr < NR_IPI) { - trace_ipi_entry(ipi_types[ipinr]); + trace_ipi_entry_rcuidle(ipi_types[ipinr]); __inc_irq_stat(cpu, ipi_irqs[ipinr]); } @@ -637,7 +637,7 @@ void handle_IPI(int ipinr, struct pt_regs *regs) } if ((unsigned)ipinr < NR_IPI) - trace_ipi_exit(ipi_types[ipinr]); + trace_ipi_exit_rcuidle(ipi_types[ipinr]); set_irq_regs(old_regs); } diff --git a/arch/arm/lib/memcpy.S b/arch/arm/lib/memcpy.S index 7797e81e40e0..64111bd4440b 100644 --- a/arch/arm/lib/memcpy.S +++ b/arch/arm/lib/memcpy.S @@ -61,8 +61,10 @@ /* Prototype: void *memcpy(void *dest, const void *src, size_t n); */ +ENTRY(mmiocpy) ENTRY(memcpy) #include "copy_template.S" ENDPROC(memcpy) +ENDPROC(mmiocpy) diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S index a4ee97b5a2bf..3c65e3bd790f 100644 --- a/arch/arm/lib/memset.S +++ b/arch/arm/lib/memset.S @@ -16,6 +16,7 @@ .text .align 5 +ENTRY(mmioset) ENTRY(memset) UNWIND( .fnstart ) ands r3, r0, #3 @ 1 unaligned? @@ -133,3 +134,4 @@ UNWIND( .fnstart ) b 1b UNWIND( .fnend ) ENDPROC(memset) +ENDPROC(mmioset) diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index d1e5ad7ab3bc..0c81056c1dd7 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -255,7 +255,7 @@ remap_area_supersections(unsigned long virt, unsigned long pfn, } #endif -void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn, +static void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn, unsigned long offset, size_t size, unsigned int mtype, void *caller) { const struct mem_type *type; @@ -363,7 +363,7 @@ __arm_ioremap_pfn(unsigned long pfn, unsigned long offset, size_t size, unsigned int mtype) { return __arm_ioremap_pfn_caller(pfn, offset, size, mtype, - __builtin_return_address(0)); + __builtin_return_address(0)); } EXPORT_SYMBOL(__arm_ioremap_pfn); @@ -371,13 +371,26 @@ void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t, unsigned int, void *) = __arm_ioremap_caller; -void __iomem * -__arm_ioremap(phys_addr_t phys_addr, size_t size, unsigned int mtype) +void __iomem *ioremap(resource_size_t res_cookie, size_t size) +{ + return arch_ioremap_caller(res_cookie, size, MT_DEVICE, + __builtin_return_address(0)); +} +EXPORT_SYMBOL(ioremap); + +void __iomem *ioremap_cache(resource_size_t res_cookie, size_t size) +{ + return arch_ioremap_caller(res_cookie, size, MT_DEVICE_CACHED, + __builtin_return_address(0)); +} +EXPORT_SYMBOL(ioremap_cache); + +void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size) { - return arch_ioremap_caller(phys_addr, size, mtype, - __builtin_return_address(0)); + return arch_ioremap_caller(res_cookie, size, MT_DEVICE_WC, + __builtin_return_address(0)); } -EXPORT_SYMBOL(__arm_ioremap); +EXPORT_SYMBOL(ioremap_wc); /* * Remap an arbitrary physical address space into the kernel virtual @@ -431,11 +444,11 @@ void __iounmap(volatile void __iomem *io_addr) void (*arch_iounmap)(volatile void __iomem *) = __iounmap; -void __arm_iounmap(volatile void __iomem *io_addr) +void iounmap(volatile void __iomem *cookie) { - arch_iounmap(io_addr); + arch_iounmap(cookie); } -EXPORT_SYMBOL(__arm_iounmap); +EXPORT_SYMBOL(iounmap); #ifdef CONFIG_PCI static int pci_ioremap_mem_type = MT_DEVICE; diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 6ca7d9aa896f..870838a46d52 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -1072,6 +1072,7 @@ void __init sanity_check_meminfo(void) int highmem = 0; phys_addr_t vmalloc_limit = __pa(vmalloc_min - 1) + 1; struct memblock_region *reg; + bool should_use_highmem = false; for_each_memblock(memory, reg) { phys_addr_t block_start = reg->base; @@ -1090,6 +1091,7 @@ void __init sanity_check_meminfo(void) pr_notice("Ignoring RAM at %pa-%pa (!CONFIG_HIGHMEM)\n", &block_start, &block_end); memblock_remove(reg->base, reg->size); + should_use_highmem = true; continue; } @@ -1100,6 +1102,7 @@ void __init sanity_check_meminfo(void) &block_start, &block_end, &vmalloc_limit); memblock_remove(vmalloc_limit, overlap_size); block_end = vmalloc_limit; + should_use_highmem = true; } } @@ -1134,6 +1137,9 @@ void __init sanity_check_meminfo(void) } } + if (should_use_highmem) + pr_notice("Consider using a HIGHMEM enabled kernel.\n"); + high_memory = __va(arm_lowmem_limit - 1) + 1; /* @@ -1494,6 +1500,7 @@ void __init paging_init(const struct machine_desc *mdesc) build_mem_type_table(); prepare_page_table(); map_lowmem(); + memblock_set_current_limit(arm_lowmem_limit); dma_contiguous_remap(); devicemaps_init(mdesc); kmap_init(); diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index afd7e05d95f1..1dd10936d68d 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -351,30 +351,43 @@ void __iomem *__arm_ioremap_pfn(unsigned long pfn, unsigned long offset, } EXPORT_SYMBOL(__arm_ioremap_pfn); -void __iomem *__arm_ioremap_pfn_caller(unsigned long pfn, unsigned long offset, - size_t size, unsigned int mtype, void *caller) +void __iomem *__arm_ioremap_caller(phys_addr_t phys_addr, size_t size, + unsigned int mtype, void *caller) { - return __arm_ioremap_pfn(pfn, offset, size, mtype); + return (void __iomem *)phys_addr; } -void __iomem *__arm_ioremap(phys_addr_t phys_addr, size_t size, - unsigned int mtype) +void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t, unsigned int, void *); + +void __iomem *ioremap(resource_size_t res_cookie, size_t size) { - return (void __iomem *)phys_addr; + return __arm_ioremap_caller(res_cookie, size, MT_DEVICE, + __builtin_return_address(0)); } -EXPORT_SYMBOL(__arm_ioremap); +EXPORT_SYMBOL(ioremap); -void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t, unsigned int, void *); +void __iomem *ioremap_cache(resource_size_t res_cookie, size_t size) +{ + return __arm_ioremap_caller(res_cookie, size, MT_DEVICE_CACHED, + __builtin_return_address(0)); +} +EXPORT_SYMBOL(ioremap_cache); -void __iomem *__arm_ioremap_caller(phys_addr_t phys_addr, size_t size, - unsigned int mtype, void *caller) +void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size) +{ + return __arm_ioremap_caller(res_cookie, size, MT_DEVICE_WC, + __builtin_return_address(0)); +} +EXPORT_SYMBOL(ioremap_wc); + +void __iounmap(volatile void __iomem *addr) { - return __arm_ioremap(phys_addr, size, mtype); } +EXPORT_SYMBOL(__iounmap); void (*arch_iounmap)(volatile void __iomem *); -void __arm_iounmap(volatile void __iomem *addr) +void iounmap(volatile void __iomem *addr) { } -EXPORT_SYMBOL(__arm_iounmap); +EXPORT_SYMBOL(iounmap); diff --git a/arch/arm/vdso/vdsomunge.c b/arch/arm/vdso/vdsomunge.c index 9005b07296c8..aedec81d1198 100644 --- a/arch/arm/vdso/vdsomunge.c +++ b/arch/arm/vdso/vdsomunge.c @@ -45,13 +45,11 @@ * it does. */ -#define _GNU_SOURCE - #include <byteswap.h> #include <elf.h> #include <errno.h> -#include <error.h> #include <fcntl.h> +#include <stdarg.h> #include <stdbool.h> #include <stdio.h> #include <stdlib.h> @@ -82,11 +80,25 @@ #define EF_ARM_ABI_FLOAT_HARD 0x400 #endif +static int failed; +static const char *argv0; static const char *outfile; +static void fail(const char *fmt, ...) +{ + va_list ap; + + failed = 1; + fprintf(stderr, "%s: ", argv0); + va_start(ap, fmt); + vfprintf(stderr, fmt, ap); + va_end(ap); + exit(EXIT_FAILURE); +} + static void cleanup(void) { - if (error_message_count > 0 && outfile != NULL) + if (failed && outfile != NULL) unlink(outfile); } @@ -119,68 +131,66 @@ int main(int argc, char **argv) int infd; atexit(cleanup); + argv0 = argv[0]; if (argc != 3) - error(EXIT_FAILURE, 0, "Usage: %s [infile] [outfile]", argv[0]); + fail("Usage: %s [infile] [outfile]\n", argv[0]); infile = argv[1]; outfile = argv[2]; infd = open(infile, O_RDONLY); if (infd < 0) - error(EXIT_FAILURE, errno, "Cannot open %s", infile); + fail("Cannot open %s: %s\n", infile, strerror(errno)); if (fstat(infd, &stat) != 0) - error(EXIT_FAILURE, errno, "Failed stat for %s", infile); + fail("Failed stat for %s: %s\n", infile, strerror(errno)); inbuf = mmap(NULL, stat.st_size, PROT_READ, MAP_PRIVATE, infd, 0); if (inbuf == MAP_FAILED) - error(EXIT_FAILURE, errno, "Failed to map %s", infile); + fail("Failed to map %s: %s\n", infile, strerror(errno)); close(infd); inhdr = inbuf; if (memcmp(&inhdr->e_ident, ELFMAG, SELFMAG) != 0) - error(EXIT_FAILURE, 0, "Not an ELF file"); + fail("Not an ELF file\n"); if (inhdr->e_ident[EI_CLASS] != ELFCLASS32) - error(EXIT_FAILURE, 0, "Unsupported ELF class"); + fail("Unsupported ELF class\n"); swap = inhdr->e_ident[EI_DATA] != HOST_ORDER; if (read_elf_half(inhdr->e_type, swap) != ET_DYN) - error(EXIT_FAILURE, 0, "Not a shared object"); + fail("Not a shared object\n"); - if (read_elf_half(inhdr->e_machine, swap) != EM_ARM) { - error(EXIT_FAILURE, 0, "Unsupported architecture %#x", - inhdr->e_machine); - } + if (read_elf_half(inhdr->e_machine, swap) != EM_ARM) + fail("Unsupported architecture %#x\n", inhdr->e_machine); e_flags = read_elf_word(inhdr->e_flags, swap); if (EF_ARM_EABI_VERSION(e_flags) != EF_ARM_EABI_VER5) { - error(EXIT_FAILURE, 0, "Unsupported EABI version %#x", - EF_ARM_EABI_VERSION(e_flags)); + fail("Unsupported EABI version %#x\n", + EF_ARM_EABI_VERSION(e_flags)); } if (e_flags & EF_ARM_ABI_FLOAT_HARD) - error(EXIT_FAILURE, 0, - "Unexpected hard-float flag set in e_flags"); + fail("Unexpected hard-float flag set in e_flags\n"); clear_soft_float = !!(e_flags & EF_ARM_ABI_FLOAT_SOFT); outfd = open(outfile, O_RDWR | O_CREAT | O_TRUNC, S_IRUSR | S_IWUSR); if (outfd < 0) - error(EXIT_FAILURE, errno, "Cannot open %s", outfile); + fail("Cannot open %s: %s\n", outfile, strerror(errno)); if (ftruncate(outfd, stat.st_size) != 0) - error(EXIT_FAILURE, errno, "Cannot truncate %s", outfile); + fail("Cannot truncate %s: %s\n", outfile, strerror(errno)); outbuf = mmap(NULL, stat.st_size, PROT_READ | PROT_WRITE, MAP_SHARED, outfd, 0); if (outbuf == MAP_FAILED) - error(EXIT_FAILURE, errno, "Failed to map %s", outfile); + fail("Failed to map %s: %s\n", outfile, strerror(errno)); close(outfd); @@ -195,7 +205,7 @@ int main(int argc, char **argv) } if (msync(outbuf, stat.st_size, MS_SYNC) != 0) - error(EXIT_FAILURE, errno, "Failed to sync %s", outfile); + fail("Failed to sync %s: %s\n", outfile, strerror(errno)); return EXIT_SUCCESS; } diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 0f6edb14b7e4..318175f62c24 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -23,9 +23,9 @@ config ARM64 select BUILDTIME_EXTABLE_SORT select CLONE_BACKWARDS select COMMON_CLK - select EDAC_SUPPORT select CPU_PM if (SUSPEND || CPU_IDLE) select DCACHE_WORD_ACCESS + select EDAC_SUPPORT select GENERIC_ALLOCATOR select GENERIC_CLOCKEVENTS select GENERIC_CLOCKEVENTS_BROADCAST if SMP diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index f38c94f1d898..4e17e7ede33d 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -83,6 +83,7 @@ CONFIG_BLK_DEV_SD=y CONFIG_ATA=y CONFIG_SATA_AHCI=y CONFIG_SATA_AHCI_PLATFORM=y +CONFIG_AHCI_CEVA=y CONFIG_AHCI_XGENE=y CONFIG_PATA_PLATFORM=y CONFIG_PATA_OF_PLATFORM=y diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h index 39248d3adf5d..406485ed110a 100644 --- a/arch/arm64/include/asm/acpi.h +++ b/arch/arm64/include/asm/acpi.h @@ -19,6 +19,14 @@ #include <asm/psci.h> #include <asm/smp_plat.h> +/* Macros for consistency checks of the GICC subtable of MADT */ +#define ACPI_MADT_GICC_LENGTH \ + (acpi_gbl_FADT.header.revision < 6 ? 76 : 80) + +#define BAD_MADT_GICC_ENTRY(entry, end) \ + (!(entry) || (unsigned long)(entry) + sizeof(*(entry)) > (end) || \ + (entry)->header.length != ACPI_MADT_GICC_LENGTH) + /* Basic configuration for ACPI */ #ifdef CONFIG_ACPI /* ACPI table mapping after acpi_gbl_permanent_mmap is set */ diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index a7691a378668..f860bfda454a 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -352,8 +352,8 @@ el1_inv: // TODO: add support for undefined instructions in kernel mode enable_dbg mov x0, sp + mov x2, x1 mov x1, #BAD_SYNC - mrs x2, esr_el1 b bad_mode ENDPROC(el1_sync) @@ -553,7 +553,7 @@ el0_inv: ct_user_exit mov x0, sp mov x1, #BAD_SYNC - mrs x2, esr_el1 + mov x2, x25 bl bad_mode b ret_to_user ENDPROC(el0_sync) diff --git a/arch/arm64/kernel/entry32.S b/arch/arm64/kernel/entry32.S index bd9bfaa9269b..f332d5d1f6b4 100644 --- a/arch/arm64/kernel/entry32.S +++ b/arch/arm64/kernel/entry32.S @@ -32,13 +32,11 @@ ENTRY(compat_sys_sigreturn_wrapper) mov x0, sp - mov x27, #0 // prevent syscall restart handling (why) b compat_sys_sigreturn ENDPROC(compat_sys_sigreturn_wrapper) ENTRY(compat_sys_rt_sigreturn_wrapper) mov x0, sp - mov x27, #0 // prevent syscall restart handling (why) b compat_sys_rt_sigreturn ENDPROC(compat_sys_rt_sigreturn_wrapper) diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 695801a54ca5..50fb4696654e 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -438,7 +438,7 @@ acpi_parse_gic_cpu_interface(struct acpi_subtable_header *header, struct acpi_madt_generic_interrupt *processor; processor = (struct acpi_madt_generic_interrupt *)header; - if (BAD_MADT_ENTRY(processor, end)) + if (BAD_MADT_GICC_ENTRY(processor, end)) return -EINVAL; acpi_table_print_madt_entry(header); diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile index 9d84feb41a16..773d37a14039 100644 --- a/arch/arm64/mm/Makefile +++ b/arch/arm64/mm/Makefile @@ -4,5 +4,3 @@ obj-y := dma-mapping.o extable.o fault.o init.o \ context.o proc.o pageattr.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o obj-$(CONFIG_ARM64_PTDUMP) += dump.o - -CFLAGS_mmu.o := -I$(srctree)/scripts/dtc/libfdt/ diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 0a183756d6ec..f93c4a4e6580 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -16,7 +16,7 @@ #include <asm/processor.h> #include <asm/cache.h> -extern spinlock_t pa_dbit_lock; +extern spinlock_t pa_tlb_lock; /* * kern_addr_valid(ADDR) tests if ADDR is pointing to valid kernel @@ -33,6 +33,19 @@ extern spinlock_t pa_dbit_lock; */ #define kern_addr_valid(addr) (1) +/* Purge data and instruction TLB entries. Must be called holding + * the pa_tlb_lock. The TLB purge instructions are slow on SMP + * machines since the purge must be broadcast to all CPUs. + */ + +static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) +{ + mtsp(mm->context, 1); + pdtlb(addr); + if (unlikely(split_tlb)) + pitlb(addr); +} + /* Certain architectures need to do special things when PTEs * within a page table are directly modified. Thus, the following * hook is made available. @@ -42,15 +55,20 @@ extern spinlock_t pa_dbit_lock; *(pteptr) = (pteval); \ } while(0) -extern void purge_tlb_entries(struct mm_struct *, unsigned long); +#define pte_inserted(x) \ + ((pte_val(x) & (_PAGE_PRESENT|_PAGE_ACCESSED)) \ + == (_PAGE_PRESENT|_PAGE_ACCESSED)) -#define set_pte_at(mm, addr, ptep, pteval) \ - do { \ +#define set_pte_at(mm, addr, ptep, pteval) \ + do { \ + pte_t old_pte; \ unsigned long flags; \ - spin_lock_irqsave(&pa_dbit_lock, flags); \ - set_pte(ptep, pteval); \ - purge_tlb_entries(mm, addr); \ - spin_unlock_irqrestore(&pa_dbit_lock, flags); \ + spin_lock_irqsave(&pa_tlb_lock, flags); \ + old_pte = *ptep; \ + set_pte(ptep, pteval); \ + if (pte_inserted(old_pte)) \ + purge_tlb_entries(mm, addr); \ + spin_unlock_irqrestore(&pa_tlb_lock, flags); \ } while (0) #endif /* !__ASSEMBLY__ */ @@ -268,7 +286,7 @@ extern unsigned long *empty_zero_page; #define pte_none(x) (pte_val(x) == 0) #define pte_present(x) (pte_val(x) & _PAGE_PRESENT) -#define pte_clear(mm,addr,xp) do { pte_val(*(xp)) = 0; } while (0) +#define pte_clear(mm, addr, xp) set_pte_at(mm, addr, xp, __pte(0)) #define pmd_flag(x) (pmd_val(x) & PxD_FLAG_MASK) #define pmd_address(x) ((unsigned long)(pmd_val(x) &~ PxD_FLAG_MASK) << PxD_VALUE_SHIFT) @@ -435,15 +453,15 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned if (!pte_young(*ptep)) return 0; - spin_lock_irqsave(&pa_dbit_lock, flags); + spin_lock_irqsave(&pa_tlb_lock, flags); pte = *ptep; if (!pte_young(pte)) { - spin_unlock_irqrestore(&pa_dbit_lock, flags); + spin_unlock_irqrestore(&pa_tlb_lock, flags); return 0; } set_pte(ptep, pte_mkold(pte)); purge_tlb_entries(vma->vm_mm, addr); - spin_unlock_irqrestore(&pa_dbit_lock, flags); + spin_unlock_irqrestore(&pa_tlb_lock, flags); return 1; } @@ -453,11 +471,12 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t old_pte; unsigned long flags; - spin_lock_irqsave(&pa_dbit_lock, flags); + spin_lock_irqsave(&pa_tlb_lock, flags); old_pte = *ptep; - pte_clear(mm,addr,ptep); - purge_tlb_entries(mm, addr); - spin_unlock_irqrestore(&pa_dbit_lock, flags); + set_pte(ptep, __pte(0)); + if (pte_inserted(old_pte)) + purge_tlb_entries(mm, addr); + spin_unlock_irqrestore(&pa_tlb_lock, flags); return old_pte; } @@ -465,10 +484,10 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { unsigned long flags; - spin_lock_irqsave(&pa_dbit_lock, flags); + spin_lock_irqsave(&pa_tlb_lock, flags); set_pte(ptep, pte_wrprotect(*ptep)); purge_tlb_entries(mm, addr); - spin_unlock_irqrestore(&pa_dbit_lock, flags); + spin_unlock_irqrestore(&pa_tlb_lock, flags); } #define pte_same(A,B) (pte_val(A) == pte_val(B)) diff --git a/arch/parisc/include/asm/tlbflush.h b/arch/parisc/include/asm/tlbflush.h index 9d086a599fa0..e84b96478193 100644 --- a/arch/parisc/include/asm/tlbflush.h +++ b/arch/parisc/include/asm/tlbflush.h @@ -13,6 +13,9 @@ * active at any one time on the Merced bus. This tlb purge * synchronisation is fairly lightweight and harmless so we activate * it on all systems not just the N class. + + * It is also used to ensure PTE updates are atomic and consistent + * with the TLB. */ extern spinlock_t pa_tlb_lock; @@ -24,20 +27,24 @@ extern void flush_tlb_all_local(void *); #define smp_flush_tlb_all() flush_tlb_all() +int __flush_tlb_range(unsigned long sid, + unsigned long start, unsigned long end); + +#define flush_tlb_range(vma, start, end) \ + __flush_tlb_range((vma)->vm_mm->context, start, end) + +#define flush_tlb_kernel_range(start, end) \ + __flush_tlb_range(0, start, end) + /* * flush_tlb_mm() * - * XXX This code is NOT valid for HP-UX compatibility processes, - * (although it will probably work 99% of the time). HP-UX - * processes are free to play with the space id's and save them - * over long periods of time, etc. so we have to preserve the - * space and just flush the entire tlb. We need to check the - * personality in order to do that, but the personality is not - * currently being set correctly. - * - * Of course, Linux processes could do the same thing, but - * we don't support that (and the compilers, dynamic linker, - * etc. do not do that). + * The code to switch to a new context is NOT valid for processes + * which play with the space id's. Thus, we have to preserve the + * space and just flush the entire tlb. However, the compilers, + * dynamic linker, etc, do not manipulate space id's, so there + * could be a significant performance benefit in switching contexts + * and not flushing the whole tlb. */ static inline void flush_tlb_mm(struct mm_struct *mm) @@ -45,10 +52,18 @@ static inline void flush_tlb_mm(struct mm_struct *mm) BUG_ON(mm == &init_mm); /* Should never happen */ #if 1 || defined(CONFIG_SMP) + /* Except for very small threads, flushing the whole TLB is + * faster than using __flush_tlb_range. The pdtlb and pitlb + * instructions are very slow because of the TLB broadcast. + * It might be faster to do local range flushes on all CPUs + * on PA 2.0 systems. + */ flush_tlb_all(); #else /* FIXME: currently broken, causing space id and protection ids - * to go out of sync, resulting in faults on userspace accesses. + * to go out of sync, resulting in faults on userspace accesses. + * This approach needs further investigation since running many + * small applications (e.g., GCC testsuite) is faster on HP-UX. */ if (mm) { if (mm->context != 0) @@ -65,22 +80,12 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, { unsigned long flags, sid; - /* For one page, it's not worth testing the split_tlb variable */ - - mb(); sid = vma->vm_mm->context; purge_tlb_start(flags); mtsp(sid, 1); pdtlb(addr); - pitlb(addr); + if (unlikely(split_tlb)) + pitlb(addr); purge_tlb_end(flags); } - -void __flush_tlb_range(unsigned long sid, - unsigned long start, unsigned long end); - -#define flush_tlb_range(vma,start,end) __flush_tlb_range((vma)->vm_mm->context,start,end) - -#define flush_tlb_kernel_range(start, end) __flush_tlb_range(0,start,end) - #endif diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index f6448c7c62b5..cda6dbbe9842 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -342,12 +342,15 @@ EXPORT_SYMBOL(flush_data_cache_local); EXPORT_SYMBOL(flush_kernel_icache_range_asm); #define FLUSH_THRESHOLD 0x80000 /* 0.5MB */ -int parisc_cache_flush_threshold __read_mostly = FLUSH_THRESHOLD; +static unsigned long parisc_cache_flush_threshold __read_mostly = FLUSH_THRESHOLD; + +#define FLUSH_TLB_THRESHOLD (2*1024*1024) /* 2MB initial TLB threshold */ +static unsigned long parisc_tlb_flush_threshold __read_mostly = FLUSH_TLB_THRESHOLD; void __init parisc_setup_cache_timing(void) { unsigned long rangetime, alltime; - unsigned long size; + unsigned long size, start; alltime = mfctl(16); flush_data_cache(); @@ -364,14 +367,43 @@ void __init parisc_setup_cache_timing(void) /* Racy, but if we see an intermediate value, it's ok too... */ parisc_cache_flush_threshold = size * alltime / rangetime; - parisc_cache_flush_threshold = (parisc_cache_flush_threshold + L1_CACHE_BYTES - 1) &~ (L1_CACHE_BYTES - 1); + parisc_cache_flush_threshold = L1_CACHE_ALIGN(parisc_cache_flush_threshold); if (!parisc_cache_flush_threshold) parisc_cache_flush_threshold = FLUSH_THRESHOLD; if (parisc_cache_flush_threshold > cache_info.dc_size) parisc_cache_flush_threshold = cache_info.dc_size; - printk(KERN_INFO "Setting cache flush threshold to %x (%d CPUs online)\n", parisc_cache_flush_threshold, num_online_cpus()); + printk(KERN_INFO "Setting cache flush threshold to %lu kB\n", + parisc_cache_flush_threshold/1024); + + /* calculate TLB flush threshold */ + + alltime = mfctl(16); + flush_tlb_all(); + alltime = mfctl(16) - alltime; + + size = PAGE_SIZE; + start = (unsigned long) _text; + rangetime = mfctl(16); + while (start < (unsigned long) _end) { + flush_tlb_kernel_range(start, start + PAGE_SIZE); + start += PAGE_SIZE; + size += PAGE_SIZE; + } + rangetime = mfctl(16) - rangetime; + + printk(KERN_DEBUG "Whole TLB flush %lu cycles, flushing %lu bytes %lu cycles\n", + alltime, size, rangetime); + + parisc_tlb_flush_threshold = size * alltime / rangetime; + parisc_tlb_flush_threshold *= num_online_cpus(); + parisc_tlb_flush_threshold = PAGE_ALIGN(parisc_tlb_flush_threshold); + if (!parisc_tlb_flush_threshold) + parisc_tlb_flush_threshold = FLUSH_TLB_THRESHOLD; + + printk(KERN_INFO "Setting TLB flush threshold to %lu kB\n", + parisc_tlb_flush_threshold/1024); } extern void purge_kernel_dcache_page_asm(unsigned long); @@ -403,48 +435,45 @@ void copy_user_page(void *vto, void *vfrom, unsigned long vaddr, } EXPORT_SYMBOL(copy_user_page); -void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) -{ - unsigned long flags; - - /* Note: purge_tlb_entries can be called at startup with - no context. */ - - purge_tlb_start(flags); - mtsp(mm->context, 1); - pdtlb(addr); - pitlb(addr); - purge_tlb_end(flags); -} -EXPORT_SYMBOL(purge_tlb_entries); - -void __flush_tlb_range(unsigned long sid, unsigned long start, - unsigned long end) +/* __flush_tlb_range() + * + * returns 1 if all TLBs were flushed. + */ +int __flush_tlb_range(unsigned long sid, unsigned long start, + unsigned long end) { - unsigned long npages; + unsigned long flags, size; - npages = ((end - (start & PAGE_MASK)) + (PAGE_SIZE - 1)) >> PAGE_SHIFT; - if (npages >= 512) /* 2MB of space: arbitrary, should be tuned */ + size = (end - start); + if (size >= parisc_tlb_flush_threshold) { flush_tlb_all(); - else { - unsigned long flags; + return 1; + } + /* Purge TLB entries for small ranges using the pdtlb and + pitlb instructions. These instructions execute locally + but cause a purge request to be broadcast to other TLBs. */ + if (likely(!split_tlb)) { + while (start < end) { + purge_tlb_start(flags); + mtsp(sid, 1); + pdtlb(start); + purge_tlb_end(flags); + start += PAGE_SIZE; + } + return 0; + } + + /* split TLB case */ + while (start < end) { purge_tlb_start(flags); mtsp(sid, 1); - if (split_tlb) { - while (npages--) { - pdtlb(start); - pitlb(start); - start += PAGE_SIZE; - } - } else { - while (npages--) { - pdtlb(start); - start += PAGE_SIZE; - } - } + pdtlb(start); + pitlb(start); purge_tlb_end(flags); + start += PAGE_SIZE; } + return 0; } static void cacheflush_h_tmp_function(void *dummy) diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index 75819617f93b..c5ef4081b01d 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -45,7 +45,7 @@ .level 2.0 #endif - .import pa_dbit_lock,data + .import pa_tlb_lock,data /* space_to_prot macro creates a prot id from a space id */ @@ -420,8 +420,8 @@ SHLREG %r9,PxD_VALUE_SHIFT,\pmd extru \va,31-PAGE_SHIFT,ASM_BITS_PER_PTE,\index dep %r0,31,PAGE_SHIFT,\pmd /* clear offset */ - shladd \index,BITS_PER_PTE_ENTRY,\pmd,\pmd - LDREG %r0(\pmd),\pte /* pmd is now pte */ + shladd \index,BITS_PER_PTE_ENTRY,\pmd,\pmd /* pmd is now pte */ + LDREG %r0(\pmd),\pte bb,>=,n \pte,_PAGE_PRESENT_BIT,\fault .endm @@ -453,57 +453,53 @@ L2_ptep \pgd,\pte,\index,\va,\fault .endm - /* Acquire pa_dbit_lock lock. */ - .macro dbit_lock spc,tmp,tmp1 + /* Acquire pa_tlb_lock lock and recheck page is still present. */ + .macro tlb_lock spc,ptp,pte,tmp,tmp1,fault #ifdef CONFIG_SMP cmpib,COND(=),n 0,\spc,2f - load32 PA(pa_dbit_lock),\tmp + load32 PA(pa_tlb_lock),\tmp 1: LDCW 0(\tmp),\tmp1 cmpib,COND(=) 0,\tmp1,1b nop + LDREG 0(\ptp),\pte + bb,<,n \pte,_PAGE_PRESENT_BIT,2f + b \fault + stw \spc,0(\tmp) 2: #endif .endm - /* Release pa_dbit_lock lock without reloading lock address. */ - .macro dbit_unlock0 spc,tmp + /* Release pa_tlb_lock lock without reloading lock address. */ + .macro tlb_unlock0 spc,tmp #ifdef CONFIG_SMP or,COND(=) %r0,\spc,%r0 stw \spc,0(\tmp) #endif .endm - /* Release pa_dbit_lock lock. */ - .macro dbit_unlock1 spc,tmp + /* Release pa_tlb_lock lock. */ + .macro tlb_unlock1 spc,tmp #ifdef CONFIG_SMP - load32 PA(pa_dbit_lock),\tmp - dbit_unlock0 \spc,\tmp + load32 PA(pa_tlb_lock),\tmp + tlb_unlock0 \spc,\tmp #endif .endm /* Set the _PAGE_ACCESSED bit of the PTE. Be clever and * don't needlessly dirty the cache line if it was already set */ - .macro update_ptep spc,ptep,pte,tmp,tmp1 -#ifdef CONFIG_SMP - or,COND(=) %r0,\spc,%r0 - LDREG 0(\ptep),\pte -#endif + .macro update_accessed ptp,pte,tmp,tmp1 ldi _PAGE_ACCESSED,\tmp1 or \tmp1,\pte,\tmp and,COND(<>) \tmp1,\pte,%r0 - STREG \tmp,0(\ptep) + STREG \tmp,0(\ptp) .endm /* Set the dirty bit (and accessed bit). No need to be * clever, this is only used from the dirty fault */ - .macro update_dirty spc,ptep,pte,tmp -#ifdef CONFIG_SMP - or,COND(=) %r0,\spc,%r0 - LDREG 0(\ptep),\pte -#endif + .macro update_dirty ptp,pte,tmp ldi _PAGE_ACCESSED|_PAGE_DIRTY,\tmp or \tmp,\pte,\pte - STREG \pte,0(\ptep) + STREG \pte,0(\ptp) .endm /* bitshift difference between a PFN (based on kernel's PAGE_SIZE) @@ -1148,14 +1144,14 @@ dtlb_miss_20w: L3_ptep ptp,pte,t0,va,dtlb_check_alias_20w - dbit_lock spc,t0,t1 - update_ptep spc,ptp,pte,t0,t1 + tlb_lock spc,ptp,pte,t0,t1,dtlb_check_alias_20w + update_accessed ptp,pte,t0,t1 make_insert_tlb spc,pte,prot idtlbt pte,prot - dbit_unlock1 spc,t0 + tlb_unlock1 spc,t0 rfir nop @@ -1174,14 +1170,14 @@ nadtlb_miss_20w: L3_ptep ptp,pte,t0,va,nadtlb_check_alias_20w - dbit_lock spc,t0,t1 - update_ptep spc,ptp,pte,t0,t1 + tlb_lock spc,ptp,pte,t0,t1,nadtlb_check_alias_20w + update_accessed ptp,pte,t0,t1 make_insert_tlb spc,pte,prot idtlbt pte,prot - dbit_unlock1 spc,t0 + tlb_unlock1 spc,t0 rfir nop @@ -1202,20 +1198,20 @@ dtlb_miss_11: L2_ptep ptp,pte,t0,va,dtlb_check_alias_11 - dbit_lock spc,t0,t1 - update_ptep spc,ptp,pte,t0,t1 + tlb_lock spc,ptp,pte,t0,t1,dtlb_check_alias_11 + update_accessed ptp,pte,t0,t1 make_insert_tlb_11 spc,pte,prot - mfsp %sr1,t0 /* Save sr1 so we can use it in tlb inserts */ + mfsp %sr1,t1 /* Save sr1 so we can use it in tlb inserts */ mtsp spc,%sr1 idtlba pte,(%sr1,va) idtlbp prot,(%sr1,va) - mtsp t0, %sr1 /* Restore sr1 */ - dbit_unlock1 spc,t0 + mtsp t1, %sr1 /* Restore sr1 */ + tlb_unlock1 spc,t0 rfir nop @@ -1235,21 +1231,20 @@ nadtlb_miss_11: L2_ptep ptp,pte,t0,va,nadtlb_check_alias_11 - dbit_lock spc,t0,t1 - update_ptep spc,ptp,pte,t0,t1 + tlb_lock spc,ptp,pte,t0,t1,nadtlb_check_alias_11 + update_accessed ptp,pte,t0,t1 make_insert_tlb_11 spc,pte,prot - - mfsp %sr1,t0 /* Save sr1 so we can use it in tlb inserts */ + mfsp %sr1,t1 /* Save sr1 so we can use it in tlb inserts */ mtsp spc,%sr1 idtlba pte,(%sr1,va) idtlbp prot,(%sr1,va) - mtsp t0, %sr1 /* Restore sr1 */ - dbit_unlock1 spc,t0 + mtsp t1, %sr1 /* Restore sr1 */ + tlb_unlock1 spc,t0 rfir nop @@ -1269,16 +1264,16 @@ dtlb_miss_20: L2_ptep ptp,pte,t0,va,dtlb_check_alias_20 - dbit_lock spc,t0,t1 - update_ptep spc,ptp,pte,t0,t1 + tlb_lock spc,ptp,pte,t0,t1,dtlb_check_alias_20 + update_accessed ptp,pte,t0,t1 make_insert_tlb spc,pte,prot - f_extend pte,t0 + f_extend pte,t1 idtlbt pte,prot - dbit_unlock1 spc,t0 + tlb_unlock1 spc,t0 rfir nop @@ -1297,16 +1292,16 @@ nadtlb_miss_20: L2_ptep ptp,pte,t0,va,nadtlb_check_alias_20 - dbit_lock spc,t0,t1 - update_ptep spc,ptp,pte,t0,t1 + tlb_lock spc,ptp,pte,t0,t1,nadtlb_check_alias_20 + update_accessed ptp,pte,t0,t1 make_insert_tlb spc,pte,prot - f_extend pte,t0 + f_extend pte,t1 - idtlbt pte,prot - dbit_unlock1 spc,t0 + idtlbt pte,prot + tlb_unlock1 spc,t0 rfir nop @@ -1406,14 +1401,14 @@ itlb_miss_20w: L3_ptep ptp,pte,t0,va,itlb_fault - dbit_lock spc,t0,t1 - update_ptep spc,ptp,pte,t0,t1 + tlb_lock spc,ptp,pte,t0,t1,itlb_fault + update_accessed ptp,pte,t0,t1 make_insert_tlb spc,pte,prot iitlbt pte,prot - dbit_unlock1 spc,t0 + tlb_unlock1 spc,t0 rfir nop @@ -1430,14 +1425,14 @@ naitlb_miss_20w: L3_ptep ptp,pte,t0,va,naitlb_check_alias_20w - dbit_lock spc,t0,t1 - update_ptep spc,ptp,pte,t0,t1 + tlb_lock spc,ptp,pte,t0,t1,naitlb_check_alias_20w + update_accessed ptp,pte,t0,t1 make_insert_tlb spc,pte,prot iitlbt pte,prot - dbit_unlock1 spc,t0 + tlb_unlock1 spc,t0 rfir nop @@ -1458,20 +1453,20 @@ itlb_miss_11: L2_ptep ptp,pte,t0,va,itlb_fault - dbit_lock spc,t0,t1 - update_ptep spc,ptp,pte,t0,t1 + tlb_lock spc,ptp,pte,t0,t1,itlb_fault + update_accessed ptp,pte,t0,t1 make_insert_tlb_11 spc,pte,prot - mfsp %sr1,t0 /* Save sr1 so we can use it in tlb inserts */ + mfsp %sr1,t1 /* Save sr1 so we can use it in tlb inserts */ mtsp spc,%sr1 iitlba pte,(%sr1,va) iitlbp prot,(%sr1,va) - mtsp t0, %sr1 /* Restore sr1 */ - dbit_unlock1 spc,t0 + mtsp t1, %sr1 /* Restore sr1 */ + tlb_unlock1 spc,t0 rfir nop @@ -1482,20 +1477,20 @@ naitlb_miss_11: L2_ptep ptp,pte,t0,va,naitlb_check_alias_11 - dbit_lock spc,t0,t1 - update_ptep spc,ptp,pte,t0,t1 + tlb_lock spc,ptp,pte,t0,t1,naitlb_check_alias_11 + update_accessed ptp,pte,t0,t1 make_insert_tlb_11 spc,pte,prot - mfsp %sr1,t0 /* Save sr1 so we can use it in tlb inserts */ + mfsp %sr1,t1 /* Save sr1 so we can use it in tlb inserts */ mtsp spc,%sr1 iitlba pte,(%sr1,va) iitlbp prot,(%sr1,va) - mtsp t0, %sr1 /* Restore sr1 */ - dbit_unlock1 spc,t0 + mtsp t1, %sr1 /* Restore sr1 */ + tlb_unlock1 spc,t0 rfir nop @@ -1516,16 +1511,16 @@ itlb_miss_20: L2_ptep ptp,pte,t0,va,itlb_fault - dbit_lock spc,t0,t1 - update_ptep spc,ptp,pte,t0,t1 + tlb_lock spc,ptp,pte,t0,t1,itlb_fault + update_accessed ptp,pte,t0,t1 make_insert_tlb spc,pte,prot - f_extend pte,t0 + f_extend pte,t1 iitlbt pte,prot - dbit_unlock1 spc,t0 + tlb_unlock1 spc,t0 rfir nop @@ -1536,16 +1531,16 @@ naitlb_miss_20: L2_ptep ptp,pte,t0,va,naitlb_check_alias_20 - dbit_lock spc,t0,t1 - update_ptep spc,ptp,pte,t0,t1 + tlb_lock spc,ptp,pte,t0,t1,naitlb_check_alias_20 + update_accessed ptp,pte,t0,t1 make_insert_tlb spc,pte,prot - f_extend pte,t0 + f_extend pte,t1 iitlbt pte,prot - dbit_unlock1 spc,t0 + tlb_unlock1 spc,t0 rfir nop @@ -1568,14 +1563,14 @@ dbit_trap_20w: L3_ptep ptp,pte,t0,va,dbit_fault - dbit_lock spc,t0,t1 - update_dirty spc,ptp,pte,t1 + tlb_lock spc,ptp,pte,t0,t1,dbit_fault + update_dirty ptp,pte,t1 make_insert_tlb spc,pte,prot idtlbt pte,prot - dbit_unlock0 spc,t0 + tlb_unlock0 spc,t0 rfir nop #else @@ -1588,8 +1583,8 @@ dbit_trap_11: L2_ptep ptp,pte,t0,va,dbit_fault - dbit_lock spc,t0,t1 - update_dirty spc,ptp,pte,t1 + tlb_lock spc,ptp,pte,t0,t1,dbit_fault + update_dirty ptp,pte,t1 make_insert_tlb_11 spc,pte,prot @@ -1600,8 +1595,8 @@ dbit_trap_11: idtlbp prot,(%sr1,va) mtsp t1, %sr1 /* Restore sr1 */ - dbit_unlock0 spc,t0 + tlb_unlock0 spc,t0 rfir nop @@ -1612,16 +1607,16 @@ dbit_trap_20: L2_ptep ptp,pte,t0,va,dbit_fault - dbit_lock spc,t0,t1 - update_dirty spc,ptp,pte,t1 + tlb_lock spc,ptp,pte,t0,t1,dbit_fault + update_dirty ptp,pte,t1 make_insert_tlb spc,pte,prot f_extend pte,t1 - idtlbt pte,prot - dbit_unlock0 spc,t0 + idtlbt pte,prot + tlb_unlock0 spc,t0 rfir nop #endif diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index 6548fd1d2e62..b99b39f1da02 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -43,10 +43,6 @@ #include "../math-emu/math-emu.h" /* for handle_fpe() */ -#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) -DEFINE_SPINLOCK(pa_dbit_lock); -#endif - static void parisc_show_stack(struct task_struct *task, unsigned long *sp, struct pt_regs *regs); diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S index ccde8f084ce4..112ccf497562 100644 --- a/arch/powerpc/kernel/idle_power7.S +++ b/arch/powerpc/kernel/idle_power7.S @@ -52,6 +52,22 @@ .text /* + * Used by threads when the lock bit of core_idle_state is set. + * Threads will spin in HMT_LOW until the lock bit is cleared. + * r14 - pointer to core_idle_state + * r15 - used to load contents of core_idle_state + */ + +core_idle_lock_held: + HMT_LOW +3: lwz r15,0(r14) + andi. r15,r15,PNV_CORE_IDLE_LOCK_BIT + bne 3b + HMT_MEDIUM + lwarx r15,0,r14 + blr + +/* * Pass requested state in r3: * r3 - PNV_THREAD_NAP/SLEEP/WINKLE * @@ -150,6 +166,10 @@ power7_enter_nap_mode: ld r14,PACA_CORE_IDLE_STATE_PTR(r13) lwarx_loop1: lwarx r15,0,r14 + + andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT + bnel core_idle_lock_held + andc r15,r15,r7 /* Clear thread bit */ andi. r15,r15,PNV_CORE_IDLE_THREAD_BITS @@ -294,7 +314,7 @@ lwarx_loop2: * workaround undo code or resyncing timebase or restoring context * In either case loop until the lock bit is cleared. */ - bne core_idle_lock_held + bnel core_idle_lock_held cmpwi cr2,r15,0 lbz r4,PACA_SUBCORE_SIBLING_MASK(r13) @@ -319,15 +339,6 @@ lwarx_loop2: isync b common_exit -core_idle_lock_held: - HMT_LOW -core_idle_lock_loop: - lwz r15,0(14) - andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT - bne core_idle_lock_loop - HMT_MEDIUM - b lwarx_loop2 - first_thread_in_subcore: /* First thread in subcore to wakeup */ ori r15,r15,PNV_CORE_IDLE_LOCK_BIT diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 6530f1b8874d..37de90f8a845 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -297,6 +297,8 @@ long machine_check_early(struct pt_regs *regs) __this_cpu_inc(irq_stat.mce_exceptions); + add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); + if (cur_cpu_spec && cur_cpu_spec->machine_check_early) handled = cur_cpu_spec->machine_check_early(regs); return handled; diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 6d535973b200..a67c6d781c52 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -529,6 +529,10 @@ void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig) printk(KERN_ALERT "Unable to handle kernel paging request for " "instruction fetch\n"); break; + case 0x600: + printk(KERN_ALERT "Unable to handle kernel paging request for " + "unaligned access at address 0x%08lx\n", regs->dar); + break; default: printk(KERN_ALERT "Unable to handle kernel paging request for " "unknown fault\n"); diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index ec2eb20631d1..df956295c2a7 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -320,6 +320,8 @@ static struct attribute *device_str_attr_create_(char *name, char *str) if (!attr) return NULL; + sysfs_attr_init(&attr->attr.attr); + attr->var = str; attr->attr.attr.name = name; attr->attr.attr.mode = 0444; diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c index 4949ef0d9400..37f959bf392e 100644 --- a/arch/powerpc/platforms/powernv/opal-elog.c +++ b/arch/powerpc/platforms/powernv/opal-elog.c @@ -237,7 +237,7 @@ static struct elog_obj *create_elog_obj(uint64_t id, size_t size, uint64_t type) return elog; } -static void elog_work_fn(struct work_struct *work) +static irqreturn_t elog_event(int irq, void *data) { __be64 size; __be64 id; @@ -251,7 +251,7 @@ static void elog_work_fn(struct work_struct *work) rc = opal_get_elog_size(&id, &size, &type); if (rc != OPAL_SUCCESS) { pr_err("ELOG: OPAL log info read failed\n"); - return; + return IRQ_HANDLED; } elog_size = be64_to_cpu(size); @@ -270,16 +270,10 @@ static void elog_work_fn(struct work_struct *work) * entries. */ if (kset_find_obj(elog_kset, name)) - return; + return IRQ_HANDLED; create_elog_obj(log_id, elog_size, elog_type); -} - -static DECLARE_WORK(elog_work, elog_work_fn); -static irqreturn_t elog_event(int irq, void *data) -{ - schedule_work(&elog_work); return IRQ_HANDLED; } @@ -304,8 +298,8 @@ int __init opal_elog_init(void) return irq; } - rc = request_irq(irq, elog_event, - IRQ_TYPE_LEVEL_HIGH, "opal-elog", NULL); + rc = request_threaded_irq(irq, NULL, elog_event, + IRQF_TRIGGER_HIGH | IRQF_ONESHOT, "opal-elog", NULL); if (rc) { pr_err("%s: Can't request OPAL event irq (%d)\n", __func__, rc); diff --git a/arch/powerpc/platforms/powernv/opal-prd.c b/arch/powerpc/platforms/powernv/opal-prd.c index 46cb3feb0a13..4ece8e40dd54 100644 --- a/arch/powerpc/platforms/powernv/opal-prd.c +++ b/arch/powerpc/platforms/powernv/opal-prd.c @@ -112,6 +112,7 @@ static int opal_prd_open(struct inode *inode, struct file *file) static int opal_prd_mmap(struct file *file, struct vm_area_struct *vma) { size_t addr, size; + pgprot_t page_prot; int rc; pr_devel("opal_prd_mmap(0x%016lx, 0x%016lx, 0x%lx, 0x%lx)\n", @@ -125,13 +126,11 @@ static int opal_prd_mmap(struct file *file, struct vm_area_struct *vma) if (!opal_prd_range_is_valid(addr, size)) return -EINVAL; - vma->vm_page_prot = __pgprot(pgprot_val(phys_mem_access_prot(file, - vma->vm_pgoff, - size, vma->vm_page_prot)) - | _PAGE_SPECIAL); + page_prot = phys_mem_access_prot(file, vma->vm_pgoff, + size, vma->vm_page_prot); rc = remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, size, - vma->vm_page_prot); + page_prot); return rc; } diff --git a/arch/powerpc/sysdev/ppc4xx_hsta_msi.c b/arch/powerpc/sysdev/ppc4xx_hsta_msi.c index 2bc33674ebfc..87f9623ca805 100644 --- a/arch/powerpc/sysdev/ppc4xx_hsta_msi.c +++ b/arch/powerpc/sysdev/ppc4xx_hsta_msi.c @@ -18,6 +18,7 @@ #include <linux/pci.h> #include <linux/semaphore.h> #include <asm/msi_bitmap.h> +#include <asm/ppc-pci.h> struct ppc4xx_hsta_msi { struct device *dev; diff --git a/arch/tile/lib/memcpy_user_64.c b/arch/tile/lib/memcpy_user_64.c index 88c7016492c4..97bbb6060b25 100644 --- a/arch/tile/lib/memcpy_user_64.c +++ b/arch/tile/lib/memcpy_user_64.c @@ -28,7 +28,7 @@ #define _ST(p, inst, v) \ ({ \ asm("1: " #inst " %0, %1;" \ - ".pushsection .coldtext.memcpy,\"ax\";" \ + ".pushsection .coldtext,\"ax\";" \ "2: { move r0, %2; jrp lr };" \ ".section __ex_table,\"a\";" \ ".align 8;" \ @@ -41,7 +41,7 @@ ({ \ unsigned long __v; \ asm("1: " #inst " %0, %1;" \ - ".pushsection .coldtext.memcpy,\"ax\";" \ + ".pushsection .coldtext,\"ax\";" \ "2: { move r0, %2; jrp lr };" \ ".section __ex_table,\"a\";" \ ".align 8;" \ diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c index ddf9ecb53cc3..e342586db6e4 100644 --- a/arch/x86/lib/usercopy.c +++ b/arch/x86/lib/usercopy.c @@ -20,7 +20,7 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n) unsigned long ret; if (__range_not_ok(from, n, TASK_SIZE)) - return 0; + return n; /* * Even though this function is typically called from NMI/IRQ context |