diff options
Diffstat (limited to 'arch')
54 files changed, 965 insertions, 133 deletions
diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index 838eac1..89bbe5b 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -200,7 +200,6 @@ show_regs(struct pt_regs *regs) void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long sp) { - set_fs(USER_DS); regs->pc = pc; regs->ps = 8; wrusp(sp); diff --git a/arch/arm/mach-ux500/board-u5500.c b/arch/arm/mach-ux500/board-u5500.c index 44fd3b5..e58f0f5 100644 --- a/arch/arm/mach-ux500/board-u5500.c +++ b/arch/arm/mach-ux500/board-u5500.c @@ -10,16 +10,97 @@ #include <linux/amba/bus.h> #include <linux/gpio.h> #include <linux/irq.h> +#include <linux/i2c.h> #include <asm/mach/arch.h> #include <asm/mach-types.h> +#include <plat/pincfg.h> +#include <plat/i2c.h> + #include <mach/hardware.h> #include <mach/devices.h> #include <mach/setup.h> +#include "pins-db5500.h" #include "devices-db5500.h" +#include <linux/led-lm3530.h> + +/* + * GPIO + */ + +static pin_cfg_t u5500_pins[] = { + /* I2C */ + GPIO218_I2C2_SCL | PIN_INPUT_PULLUP, + GPIO219_I2C2_SDA | PIN_INPUT_PULLUP, + + /* DISPLAY_ENABLE */ + GPIO226_GPIO | PIN_OUTPUT_LOW, + + /* Backlight Enbale */ + GPIO224_GPIO | PIN_OUTPUT_HIGH, +}; +/* + * I2C + */ + +#define U5500_I2C_CONTROLLER(id, _slsu, _tft, _rft, clk, _sm) \ +static struct nmk_i2c_controller u5500_i2c##id##_data = { \ + /* \ + * slave data setup time, which is \ + * 250 ns,100ns,10ns which is 14,6,2 \ + * respectively for a 48 Mhz \ + * i2c clock \ + */ \ + .slsu = _slsu, \ + /* Tx FIFO threshold */ \ + .tft = _tft, \ + /* Rx FIFO threshold */ \ + .rft = _rft, \ + /* std. mode operation */ \ + .clk_freq = clk, \ + .sm = _sm, \ +} +/* + * The board uses TODO <3> i2c controllers, initialize all of + * them with slave data setup time of 250 ns, + * Tx & Rx FIFO threshold values as 1 and standard + * mode of operation + */ + +U5500_I2C_CONTROLLER(2, 0xe, 1, 1, 400000, I2C_FREQ_MODE_FAST); + +static struct lm3530_platform_data u5500_als_platform_data = { + .mode = LM3530_BL_MODE_MANUAL, + .als_input_mode = LM3530_INPUT_ALS1, + .max_current = LM3530_FS_CURR_26mA, + .pwm_pol_hi = true, + .als_avrg_time = LM3530_ALS_AVRG_TIME_512ms, + .brt_ramp_law = 1, /* Linear */ + .brt_ramp_fall = LM3530_RAMP_TIME_8s, + .brt_ramp_rise = LM3530_RAMP_TIME_8s, + .als1_resistor_sel = LM3530_ALS_IMPD_13_53kOhm, + .als2_resistor_sel = LM3530_ALS_IMPD_Z, + .als_vmin = 730, /* mV */ + .als_vmax = 1020, /* mV */ + .brt_val = 0x7F, /* Max brightness */ +}; + +static struct i2c_board_info __initdata u5500_i2c2_devices[] = { + { + /* Backlight */ + I2C_BOARD_INFO("lm3530-led", 0x36), + .platform_data = &u5500_als_platform_data, + }, +}; + +static void __init u5500_i2c_init(void) +{ + db5500_add_i2c2(&u5500_i2c2_data); + i2c_register_board_info(2, ARRAY_AND_SIZE(u5500_i2c2_devices)); +} static void __init u5500_uart_init(void) { db5500_add_uart0(NULL); @@ -30,7 +111,8 @@ static void __init u5500_uart_init(void) static void __init u5500_init_machine(void) { u5500_init_devices(); - + nmk_config_pins(u5500_pins, ARRAY_SIZE(u5500_pins)); + u5500_i2c_init(); u5500_sdi_init(); u5500_uart_init(); } diff --git a/arch/cris/arch-v32/mach-a3/pinmux.c b/arch/cris/arch-v32/mach-a3/pinmux.c index 18648ef..591f775 100644 --- a/arch/cris/arch-v32/mach-a3/pinmux.c +++ b/arch/cris/arch-v32/mach-a3/pinmux.c @@ -85,6 +85,8 @@ crisv32_pinmux_alloc_fixed(enum fixed_function function) int ret = -EINVAL; char saved[sizeof pins]; unsigned long flags; + reg_pinmux_rw_hwprot hwprot; + reg_clkgen_rw_clk_ctrl clk_ctrl; spin_lock_irqsave(&pinmux_lock, flags); @@ -93,9 +95,8 @@ crisv32_pinmux_alloc_fixed(enum fixed_function function) crisv32_pinmux_init(); /* must be done before we read rw_hwprot */ - reg_pinmux_rw_hwprot hwprot = REG_RD(pinmux, regi_pinmux, rw_hwprot); - reg_clkgen_rw_clk_ctrl clk_ctrl = REG_RD(clkgen, regi_clkgen, - rw_clk_ctrl); + hwprot = REG_RD(pinmux, regi_pinmux, rw_hwprot); + clk_ctrl = REG_RD(clkgen, regi_clkgen, rw_clk_ctrl); switch (function) { case pinmux_eth: @@ -262,6 +263,7 @@ crisv32_pinmux_dealloc_fixed(enum fixed_function function) int ret = -EINVAL; char saved[sizeof pins]; unsigned long flags; + reg_pinmux_rw_hwprot hwprot; spin_lock_irqsave(&pinmux_lock, flags); @@ -270,7 +272,7 @@ crisv32_pinmux_dealloc_fixed(enum fixed_function function) crisv32_pinmux_init(); /* must be done before we read rw_hwprot */ - reg_pinmux_rw_hwprot hwprot = REG_RD(pinmux, regi_pinmux, rw_hwprot); + hwprot = REG_RD(pinmux, regi_pinmux, rw_hwprot); switch (function) { case pinmux_eth: diff --git a/arch/cris/include/arch-v10/arch/processor.h b/arch/cris/include/arch-v10/arch/processor.h index cc692c7..93feb2a 100644 --- a/arch/cris/include/arch-v10/arch/processor.h +++ b/arch/cris/include/arch-v10/arch/processor.h @@ -53,7 +53,6 @@ struct thread_struct { */ #define start_thread(regs, ip, usp) do { \ - set_fs(USER_DS); \ regs->irp = ip; \ regs->dccr |= 1 << U_DCCR_BITNR; \ wrusp(usp); \ diff --git a/arch/cris/include/arch-v32/arch/processor.h b/arch/cris/include/arch-v32/arch/processor.h index f80b477..9603c90 100644 --- a/arch/cris/include/arch-v32/arch/processor.h +++ b/arch/cris/include/arch-v32/arch/processor.h @@ -47,7 +47,6 @@ struct thread_struct { */ #define start_thread(regs, ip, usp) \ do { \ - set_fs(USER_DS); \ regs->erp = ip; \ regs->ccs |= 1 << (U_CCS_BITNR + CCS_SHIFT); \ wrusp(usp); \ diff --git a/arch/h8300/include/asm/processor.h b/arch/h8300/include/asm/processor.h index 69e8a34..e834b60 100644 --- a/arch/h8300/include/asm/processor.h +++ b/arch/h8300/include/asm/processor.h @@ -81,7 +81,6 @@ struct thread_struct { #if defined(__H8300H__) #define start_thread(_regs, _pc, _usp) \ do { \ - set_fs(USER_DS); /* reads from user space */ \ (_regs)->pc = (_pc); \ (_regs)->ccr = 0x00; /* clear all flags */ \ (_regs)->er5 = current->mm->start_data; /* GOT base */ \ @@ -91,7 +90,6 @@ do { \ #if defined(__H8300S__) #define start_thread(_regs, _pc, _usp) \ do { \ - set_fs(USER_DS); /* reads from user space */ \ (_regs)->pc = (_pc); \ (_regs)->ccr = 0x00; /* clear kernel flag */ \ (_regs)->exr = 0x78; /* enable all interrupts */ \ diff --git a/arch/m32r/include/asm/processor.h b/arch/m32r/include/asm/processor.h index 8397c24..e1f46d7 100644 --- a/arch/m32r/include/asm/processor.h +++ b/arch/m32r/include/asm/processor.h @@ -106,7 +106,6 @@ struct thread_struct { #define start_thread(regs, new_pc, new_spu) \ do { \ - set_fs(USER_DS); \ regs->psw = (regs->psw | USERPS_BPSW) & 0x0000FFFFUL; \ regs->bpc = new_pc; \ regs->spu = new_spu; \ diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h index f111b02..d8ef53a 100644 --- a/arch/m68k/include/asm/processor.h +++ b/arch/m68k/include/asm/processor.h @@ -105,9 +105,6 @@ struct thread_struct { static inline void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long usp) { - /* reads from user space */ - set_fs(USER_DS); - regs->pc = pc; regs->sr &= ~0x2000; wrusp(usp); @@ -129,7 +126,6 @@ extern int handle_kernel_fault(struct pt_regs *regs); #define start_thread(_regs, _pc, _usp) \ do { \ - set_fs(USER_DS); /* reads from user space */ \ (_regs)->pc = (_pc); \ ((struct switch_stack *)(_regs))[-1].a6 = 0; \ reformat(_regs); \ diff --git a/arch/m68k/kernel/process_mm.c b/arch/m68k/kernel/process_mm.c index c2a1fc2..1bc223a 100644 --- a/arch/m68k/kernel/process_mm.c +++ b/arch/m68k/kernel/process_mm.c @@ -185,7 +185,7 @@ EXPORT_SYMBOL(kernel_thread); void flush_thread(void) { unsigned long zero = 0; - set_fs(USER_DS); + current->thread.fs = __USER_DS; if (!FPU_IS_EMU) asm volatile (".chip 68k/68881\n\t" diff --git a/arch/m68k/kernel/process_no.c b/arch/m68k/kernel/process_no.c index 9b86ad1..69c1803 100644 --- a/arch/m68k/kernel/process_no.c +++ b/arch/m68k/kernel/process_no.c @@ -158,7 +158,7 @@ void flush_thread(void) #ifdef CONFIG_FPU unsigned long zero = 0; #endif - set_fs(USER_DS); + current->thread.fs = __USER_DS; #ifdef CONFIG_FPU if (!FPU_IS_EMU) diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 271ff63..0e0ea94 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -24,6 +24,7 @@ #include <linux/cpumask.h> #include <linux/memblock.h> #include <linux/slab.h> +#include <linux/reboot.h> #include <asm/prom.h> #include <asm/rtas.h> diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index bf5f5ce..e037c74 100644 --- a/arch/powerpc/kernel/rtas_flash.c +++ b/arch/powerpc/kernel/rtas_flash.c @@ -17,6 +17,7 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/proc_fs.h> +#include <linux/reboot.h> #include <asm/delay.h> #include <asm/uaccess.h> #include <asm/rtas.h> diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 253986b..1074ddd 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -41,6 +41,7 @@ config SPARC64 select HAVE_FUNCTION_TRACE_MCOUNT_TEST select HAVE_KRETPROBES select HAVE_KPROBES + select HAVE_RCU_TABLE_FREE if SMP select HAVE_MEMBLOCK select HAVE_SYSCALL_WRAPPERS select HAVE_DYNAMIC_FTRACE @@ -81,10 +82,6 @@ config IOMMU_HELPER bool default y if SPARC64 -config QUICKLIST - bool - default y if SPARC64 - config STACKTRACE_SUPPORT bool default y if SPARC64 diff --git a/arch/sparc/include/asm/pgalloc_64.h b/arch/sparc/include/asm/pgalloc_64.h index 4e5e087..40b2d7a 100644 --- a/arch/sparc/include/asm/pgalloc_64.h +++ b/arch/sparc/include/asm/pgalloc_64.h @@ -5,7 +5,6 @@ #include <linux/sched.h> #include <linux/mm.h> #include <linux/slab.h> -#include <linux/quicklist.h> #include <asm/spitfire.h> #include <asm/cpudata.h> @@ -14,71 +13,114 @@ /* Page table allocation/freeing. */ +extern struct kmem_cache *pgtable_cache; + static inline pgd_t *pgd_alloc(struct mm_struct *mm) { - return quicklist_alloc(0, GFP_KERNEL, NULL); + return kmem_cache_alloc(pgtable_cache, GFP_KERNEL); } static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) { - quicklist_free(0, NULL, pgd); + kmem_cache_free(pgtable_cache, pgd); } #define pud_populate(MM, PUD, PMD) pud_set(PUD, PMD) static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { - return quicklist_alloc(0, GFP_KERNEL, NULL); + return kmem_cache_alloc(pgtable_cache, + GFP_KERNEL|__GFP_REPEAT); } static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { - quicklist_free(0, NULL, pmd); + kmem_cache_free(pgtable_cache, pmd); } static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - return quicklist_alloc(0, GFP_KERNEL, NULL); + return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO); } static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) { struct page *page; - void *pg; + pte_t *pte; - pg = quicklist_alloc(0, GFP_KERNEL, NULL); - if (!pg) + pte = pte_alloc_one_kernel(mm, address); + if (!pte) return NULL; - page = virt_to_page(pg); + page = virt_to_page(pte); pgtable_page_ctor(page); return page; } static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { - quicklist_free(0, NULL, pte); + free_page((unsigned long)pte); } static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage) { pgtable_page_dtor(ptepage); - quicklist_free_page(0, NULL, ptepage); + __free_page(ptepage); } - #define pmd_populate_kernel(MM, PMD, PTE) pmd_set(PMD, PTE) #define pmd_populate(MM,PMD,PTE_PAGE) \ pmd_populate_kernel(MM,PMD,page_address(PTE_PAGE)) #define pmd_pgtable(pmd) pmd_page(pmd) -static inline void check_pgt_cache(void) +#define check_pgt_cache() do { } while (0) + +static inline void pgtable_free(void *table, bool is_page) +{ + if (is_page) + free_page((unsigned long)table); + else + kmem_cache_free(pgtable_cache, table); +} + +#ifdef CONFIG_SMP + +struct mmu_gather; +extern void tlb_remove_table(struct mmu_gather *, void *); + +static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, bool is_page) +{ + unsigned long pgf = (unsigned long)table; + if (is_page) + pgf |= 0x1UL; + tlb_remove_table(tlb, (void *)pgf); +} + +static inline void __tlb_remove_table(void *_table) +{ + void *table = (void *)((unsigned long)_table & ~0x1UL); + bool is_page = false; + + if ((unsigned long)_table & 0x1UL) + is_page = true; + pgtable_free(table, is_page); +} +#else /* CONFIG_SMP */ +static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, bool is_page) { - quicklist_trim(0, NULL, 25, 16); + pgtable_free(table, is_page); +} +#endif /* !CONFIG_SMP */ + +static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *ptepage, + unsigned long address) +{ + pgtable_page_dtor(ptepage); + pgtable_free_tlb(tlb, page_address(ptepage), true); } -#define __pte_free_tlb(tlb, pte, addr) pte_free((tlb)->mm, pte) -#define __pmd_free_tlb(tlb, pmd, addr) pmd_free((tlb)->mm, pmd) +#define __pmd_free_tlb(tlb, pmd, addr) \ + pgtable_free_tlb(tlb, pmd, false) #endif /* _SPARC64_PGALLOC_H */ diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 1e03c5a..adf8932 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -95,6 +95,10 @@ /* PTE bits which are the same in SUN4U and SUN4V format. */ #define _PAGE_VALID _AC(0x8000000000000000,UL) /* Valid TTE */ #define _PAGE_R _AC(0x8000000000000000,UL) /* Keep ref bit uptodate*/ +#define _PAGE_SPECIAL _AC(0x0200000000000000,UL) /* Special page */ + +/* Advertise support for _PAGE_SPECIAL */ +#define __HAVE_ARCH_PTE_SPECIAL /* SUN4U pte bits... */ #define _PAGE_SZ4MB_4U _AC(0x6000000000000000,UL) /* 4MB Page */ @@ -104,6 +108,7 @@ #define _PAGE_NFO_4U _AC(0x1000000000000000,UL) /* No Fault Only */ #define _PAGE_IE_4U _AC(0x0800000000000000,UL) /* Invert Endianness */ #define _PAGE_SOFT2_4U _AC(0x07FC000000000000,UL) /* Software bits, set 2 */ +#define _PAGE_SPECIAL_4U _AC(0x0200000000000000,UL) /* Special page */ #define _PAGE_RES1_4U _AC(0x0002000000000000,UL) /* Reserved */ #define _PAGE_SZ32MB_4U _AC(0x0001000000000000,UL) /* (Panther) 32MB page */ #define _PAGE_SZ256MB_4U _AC(0x2001000000000000,UL) /* (Panther) 256MB page */ @@ -133,6 +138,7 @@ #define _PAGE_ACCESSED_4V _AC(0x1000000000000000,UL) /* Accessed (ref'd) */ #define _PAGE_READ_4V _AC(0x0800000000000000,UL) /* Readable SW Bit */ #define _PAGE_WRITE_4V _AC(0x0400000000000000,UL) /* Writable SW Bit */ +#define _PAGE_SPECIAL_4V _AC(0x0200000000000000,UL) /* Special page */ #define _PAGE_PADDR_4V _AC(0x00FFFFFFFFFFE000,UL) /* paddr[55:13] */ #define _PAGE_IE_4V _AC(0x0000000000001000,UL) /* Invert Endianness */ #define _PAGE_E_4V _AC(0x0000000000000800,UL) /* side-Effect */ @@ -302,10 +308,10 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t prot) : "=r" (mask), "=r" (tmp) : "i" (_PAGE_PADDR_4U | _PAGE_MODIFIED_4U | _PAGE_ACCESSED_4U | _PAGE_CP_4U | _PAGE_CV_4U | _PAGE_E_4U | _PAGE_PRESENT_4U | - _PAGE_SZBITS_4U), + _PAGE_SZBITS_4U | _PAGE_SPECIAL), "i" (_PAGE_PADDR_4V | _PAGE_MODIFIED_4V | _PAGE_ACCESSED_4V | _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_E_4V | _PAGE_PRESENT_4V | - _PAGE_SZBITS_4V)); + _PAGE_SZBITS_4V | _PAGE_SPECIAL)); return __pte((pte_val(pte) & mask) | (pgprot_val(prot) & ~mask)); } @@ -502,6 +508,7 @@ static inline pte_t pte_mkyoung(pte_t pte) static inline pte_t pte_mkspecial(pte_t pte) { + pte_val(pte) |= _PAGE_SPECIAL; return pte; } @@ -607,9 +614,9 @@ static inline unsigned long pte_present(pte_t pte) return val; } -static inline int pte_special(pte_t pte) +static inline unsigned long pte_special(pte_t pte) { - return 0; + return pte_val(pte) & _PAGE_SPECIAL; } #define pmd_set(pmdp, ptep) \ diff --git a/arch/sparc/mm/Makefile b/arch/sparc/mm/Makefile index 79836a7..e3cda21 100644 --- a/arch/sparc/mm/Makefile +++ b/arch/sparc/mm/Makefile @@ -4,7 +4,7 @@ asflags-y := -ansi ccflags-y := -Werror -obj-$(CONFIG_SPARC64) += ultra.o tlb.o tsb.o +obj-$(CONFIG_SPARC64) += ultra.o tlb.o tsb.o gup.o obj-y += fault_$(BITS).o obj-y += init_$(BITS).o obj-$(CONFIG_SPARC32) += loadmmu.o diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c new file mode 100644 index 0000000..a986b5d --- /dev/null +++ b/arch/sparc/mm/gup.c @@ -0,0 +1,181 @@ +/* + * Lockless get_user_pages_fast for sparc, cribbed from powerpc + * + * Copyright (C) 2008 Nick Piggin + * Copyright (C) 2008 Novell Inc. + */ + +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/vmstat.h> +#include <linux/pagemap.h> +#include <linux/rwsem.h> +#include <asm/pgtable.h> + +/* + * The performance critical leaf functions are made noinline otherwise gcc + * inlines everything into a single function which results in too much + * register pressure. + */ +static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, + unsigned long end, int write, struct page **pages, int *nr) +{ + unsigned long mask, result; + pte_t *ptep; + + if (tlb_type == hypervisor) { + result = _PAGE_PRESENT_4V|_PAGE_P_4V; + if (write) + result |= _PAGE_WRITE_4V; + } else { + result = _PAGE_PRESENT_4U|_PAGE_P_4U; + if (write) + result |= _PAGE_WRITE_4U; + } + mask = result | _PAGE_SPECIAL; + + ptep = pte_offset_kernel(&pmd, addr); + do { + struct page *page, *head; + pte_t pte = *ptep; + + if ((pte_val(pte) & mask) != result) + return 0; + VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + + /* The hugepage case is simplified on sparc64 because + * we encode the sub-page pfn offsets into the + * hugepage PTEs. We could optimize this in the future + * use page_cache_add_speculative() for the hugepage case. + */ + page = pte_page(pte); + head = compound_head(page); + if (!page_cache_get_speculative(head)) + return 0; + if (unlikely(pte_val(pte) != pte_val(*ptep))) { + put_page(head); + return 0; + } + + pages[*nr] = page; + (*nr)++; + } while (ptep++, addr += PAGE_SIZE, addr != end); + + return 1; +} + +static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, + int write, struct page **pages, int *nr) +{ + unsigned long next; + pmd_t *pmdp; + + pmdp = pmd_offset(&pud, addr); + do { + pmd_t pmd = *pmdp; + + next = pmd_addr_end(addr, end); + if (pmd_none(pmd)) + return 0; + if (!gup_pte_range(pmd, addr, next, write, pages, nr)) + return 0; + } while (pmdp++, addr = next, addr != end); + + return 1; +} + +static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, + int write, struct page **pages, int *nr) +{ + unsigned long next; + pud_t *pudp; + + pudp = pud_offset(&pgd, addr); + do { + pud_t pud = *pudp; + + next = pud_addr_end(addr, end); + if (pud_none(pud)) + return 0; + if (!gup_pmd_range(pud, addr, next, write, pages, nr)) + return 0; + } while (pudp++, addr = next, addr != end); + + return 1; +} + +int get_user_pages_fast(unsigned long start, int nr_pages, int write, + struct page **pages) +{ + struct mm_struct *mm = current->mm; + unsigned long addr, len, end; + unsigned long next; + pgd_t *pgdp; + int nr = 0; + + start &= PAGE_MASK; + addr = start; + len = (unsigned long) nr_pages << PAGE_SHIFT; + end = start + len; + + /* + * XXX: batch / limit 'nr', to avoid large irq off latency + * needs some instrumenting to determine the common sizes used by + * important workloads (eg. DB2), and whether limiting the batch size + * will decrease performance. + * + * It seems like we're in the clear for the moment. Direct-IO is + * the main guy that batches up lots of get_user_pages, and even + * they are limited to 64-at-a-time which is not so many. + */ + /* + * This doesn't prevent pagetable teardown, but does prevent + * the pagetables from being freed on sparc. + * + * So long as we atomically load page table pointers versus teardown, + * we can follow the address down to the the page and take a ref on it. + */ + local_irq_disable(); + + pgdp = pgd_offset(mm, addr); + do { + pgd_t pgd = *pgdp; + + next = pgd_addr_end(addr, end); + if (pgd_none(pgd)) + goto slow; + if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) + goto slow; + } while (pgdp++, addr = next, addr != end); + + local_irq_enable(); + + VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT); + return nr; + + { + int ret; + +slow: + local_irq_enable(); + + /* Try to get the remaining pages with get_user_pages */ + start += nr << PAGE_SHIFT; + pages += nr; + + down_read(&mm->mmap_sem); + ret = get_user_pages(current, mm, start, + (end - start) >> PAGE_SHIFT, write, 0, pages, NULL); + up_read(&mm->mmap_sem); + + /* Have to be a bit careful with return values */ + if (nr > 0) { + if (ret < 0) + ret = nr; + else + ret += nr; + } + + return ret; + } +} diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index a5f51b2..536412d 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -236,6 +236,8 @@ static void setup_tsb_params(struct mm_struct *mm, unsigned long tsb_idx, unsign } } +struct kmem_cache *pgtable_cache __read_mostly; + static struct kmem_cache *tsb_caches[8] __read_mostly; static const char *tsb_cache_names[8] = { @@ -253,6 +255,15 @@ void __init pgtable_cache_init(void) { unsigned long i; + pgtable_cache = kmem_cache_create("pgtable_cache", + PAGE_SIZE, PAGE_SIZE, + 0, + _clear_page); + if (!pgtable_cache) { + prom_printf("pgtable_cache_init(): Could not create!\n"); + prom_halt(); + } + for (i = 0; i < 8; i++) { unsigned long size = 8192 << i; const char *name = tsb_cache_names[i]; diff --git a/arch/um/Kconfig.x86 b/arch/um/Kconfig.x86 index 8aae429..d31ecf3 100644 --- a/arch/um/Kconfig.x86 +++ b/arch/um/Kconfig.x86 @@ -1,3 +1,5 @@ +mainmenu "User Mode Linux/$SUBARCH $KERNELVERSION Kernel Configuration" + source "arch/um/Kconfig.common" menu "UML-specific options" diff --git a/arch/um/drivers/chan_kern.c b/arch/um/drivers/chan_kern.c index 25e1965..d4191fe 100644 --- a/arch/um/drivers/chan_kern.c +++ b/arch/um/drivers/chan_kern.c @@ -543,11 +543,10 @@ int parse_chan_pair(char *str, struct line *line, int device, const struct chan_opts *opts, char **error_out) { struct list_head *chans = &line->chan_list; - struct chan *new, *chan; + struct chan *new; char *in, *out; if (!list_empty(chans)) { - chan = list_entry(chans->next, struct chan, list); free_chan(chans, 0); INIT_LIST_HEAD(chans); } diff --git a/arch/um/drivers/cow_user.c b/arch/um/drivers/cow_user.c index 93f227a..9cbb426 100644 --- a/arch/um/drivers/cow_user.c +++ b/arch/um/drivers/cow_user.c @@ -186,7 +186,11 @@ static int absolutize(char *to, int size, char *from) strcat(to, "/"); strcat(to, from); } - chdir(save_cwd); + if (chdir(save_cwd)) { + cow_printf("absolutize : Can't cd to '%s' - " + "errno = %d\n", save_cwd, errno); + return -1; + } return 0; } diff --git a/arch/um/drivers/harddog_user.c b/arch/um/drivers/harddog_user.c index b56f8e0..84dce3f 100644 --- a/arch/um/drivers/harddog_user.c +++ b/arch/um/drivers/harddog_user.c @@ -32,7 +32,7 @@ int start_watchdog(int *in_fd_ret, int *out_fd_ret, char *sock) { struct dog_data data; int in_fds[2], out_fds[2], pid, n, err; - char pid_buf[sizeof("nnnnn\0")], c; + char pid_buf[sizeof("nnnnnnn\0")], c; char *pid_args[] = { "/usr/bin/uml_watchdog", "-pid", pid_buf, NULL }; char *mconsole_args[] = { "/usr/bin/uml_watchdog", "-mconsole", NULL, NULL }; diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c index 35dd0b8..d51c404 100644 --- a/arch/um/drivers/line.c +++ b/arch/um/drivers/line.c @@ -176,10 +176,9 @@ void line_flush_buffer(struct tty_struct *tty) { struct line *line = tty->driver_data; unsigned long flags; - int err; spin_lock_irqsave(&line->lock, flags); - err = flush_buffer(line); + flush_buffer(line); spin_unlock_irqrestore(&line->lock, flags); } diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c index 47d0c37..22745b4 100644 --- a/arch/um/drivers/net_kern.c +++ b/arch/um/drivers/net_kern.c @@ -262,6 +262,15 @@ static int uml_net_change_mtu(struct net_device *dev, int new_mtu) return 0; } +#ifdef CONFIG_NET_POLL_CONTROLLER +static void uml_net_poll_controller(struct net_device *dev) +{ + disable_irq(dev->irq); + uml_net_interrupt(dev->irq, dev); + enable_irq(dev->irq); +} +#endif + static void uml_net_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { @@ -364,6 +373,9 @@ static const struct net_device_ops uml_netdev_ops = { .ndo_set_mac_address = eth_mac_addr, .ndo_change_mtu = uml_net_change_mtu, .ndo_validate_addr = eth_validate_addr, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = uml_net_poll_controller, +#endif }; /* diff --git a/arch/um/drivers/net_user.c b/arch/um/drivers/net_user.c index 9415dd9..5201188 100644 --- a/arch/um/drivers/net_user.c +++ b/arch/um/drivers/net_user.c @@ -228,7 +228,10 @@ static void change(char *dev, char *what, unsigned char *addr, "buffer\n"); pid = change_tramp(argv, output, output_len); - if (pid < 0) return; + if (pid < 0) { + kfree(output); + return; + } if (output != NULL) { printk("%s", output); diff --git a/arch/um/drivers/slip_user.c b/arch/um/drivers/slip_user.c index a1c2d2c..cbacfc4 100644 --- a/arch/um/drivers/slip_user.c +++ b/arch/um/drivers/slip_user.c @@ -102,7 +102,7 @@ static int slip_tramp(char **argv, int fd) "buffer\n"); os_kill_process(pid, 1); err = -ENOMEM; - goto out_free; + goto out_close; } close(fds[1]); @@ -112,7 +112,6 @@ static int slip_tramp(char **argv, int fd) err = helper_wait(pid); close(fds[0]); -out_free: kfree(output); return err; diff --git a/arch/um/include/asm/delay.h b/arch/um/include/asm/delay.h index c71e32b..8a5576d 100644 --- a/arch/um/include/asm/delay.h +++ b/arch/um/include/asm/delay.h @@ -1,20 +1,18 @@ #ifndef __UM_DELAY_H #define __UM_DELAY_H -#define MILLION 1000000 - /* Undefined on purpose */ extern void __bad_udelay(void); +extern void __bad_ndelay(void); extern void __udelay(unsigned long usecs); +extern void __ndelay(unsigned long usecs); extern void __delay(unsigned long loops); #define udelay(n) ((__builtin_constant_p(n) && (n) > 20000) ? \ __bad_udelay() : __udelay(n)) -/* It appears that ndelay is not used at all for UML, and has never been - * implemented. */ -extern void __unimplemented_ndelay(void); -#define ndelay(n) __unimplemented_ndelay() +#define ndelay(n) ((__builtin_constant_p(n) && (n) > 20000) ? \ + __bad_ndelay() : __ndelay(n)) #endif diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c index 09bd7b5..939a4a6 100644 --- a/arch/um/kernel/exec.c +++ b/arch/um/kernel/exec.c @@ -38,7 +38,6 @@ void flush_thread(void) void start_thread(struct pt_regs *regs, unsigned long eip, unsigned long esp) { - set_fs(USER_DS); PT_REGS_IP(regs) = eip; PT_REGS_SP(regs) = esp; } diff --git a/arch/um/kernel/reboot.c b/arch/um/kernel/reboot.c index 869bec9..4d93dff 100644 --- a/arch/um/kernel/reboot.c +++ b/arch/um/kernel/reboot.c @@ -20,9 +20,8 @@ static void kill_off_processes(void) os_kill_ptraced_process(userspace_pid[0], 1); else { struct task_struct *p; - int pid, me; + int pid; - me = os_getpid(); for_each_process(p) { if (p->mm == NULL) continue; diff --git a/arch/um/os-Linux/Makefile b/arch/um/os-Linux/Makefile index d66f038..b33f4df 100644 --- a/arch/um/os-Linux/Makefile +++ b/arch/um/os-Linux/Makefile @@ -3,10 +3,12 @@ # Licensed under the GPL # -obj-y = aio.o elf_aux.o execvp.o file.o helper.o irq.o main.o mem.o process.o \ +obj-y = aio.o execvp.o file.o helper.o irq.o main.o mem.o process.o \ registers.o sigio.o signal.o start_up.o time.o tty.o uaccess.o \ umid.o tls.o user_syms.o util.o drivers/ sys-$(SUBARCH)/ skas/ +obj-$(CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA) += elf_aux.o + USER_OBJS := $(user-objs-y) aio.o elf_aux.o execvp.o file.o helper.o irq.o \ main.o mem.o process.o registers.o sigio.o signal.o start_up.o time.o \ tty.o tls.o uaccess.o umid.o util.o diff --git a/arch/um/os-Linux/elf_aux.c b/arch/um/os-Linux/elf_aux.c index 608784d..9533237 100644 --- a/arch/um/os-Linux/elf_aux.c +++ b/arch/um/os-Linux/elf_aux.c @@ -14,16 +14,11 @@ #include "mem_user.h" #include <kern_constants.h> -/* Use the one from the kernel - the host may miss it, if having old headers. */ -#if UM_ELF_CLASS == UM_ELFCLASS32 typedef Elf32_auxv_t elf_auxv_t; -#else -typedef Elf64_auxv_t elf_auxv_t; -#endif /* These are initialized very early in boot and never changed */ char * elf_aux_platform; -long elf_aux_hwcap; +extern long elf_aux_hwcap; unsigned long vsyscall_ehdr; unsigned long vsyscall_end; unsigned long __kernel_vsyscall; diff --git a/arch/um/os-Linux/helper.c b/arch/um/os-Linux/helper.c index b6b1096..feff22d 100644 --- a/arch/um/os-Linux/helper.c +++ b/arch/um/os-Linux/helper.c @@ -28,14 +28,14 @@ static int helper_child(void *arg) { struct helper_data *data = arg; char **argv = data->argv; - int err; + int err, ret; if (data->pre_exec != NULL) (*data->pre_exec)(data->pre_data); err = execvp_noalloc(data->buf, argv[0], argv); /* If the exec succeeds, we don't get here */ - write(data->fd, &err, sizeof(err)); + CATCH_EINTR(ret = write(data->fd, &err, sizeof(err))); return 0; } diff --git a/arch/um/os-Linux/main.c b/arch/um/os-Linux/main.c index fb2a97a..8471b81 100644 --- a/arch/um/os-Linux/main.c +++ b/arch/um/os-Linux/main.c @@ -21,6 +21,8 @@ #define STACKSIZE (8 * 1024 * 1024) #define THREAD_NAME_LEN (256) +long elf_aux_hwcap; + static void set_stklim(void) { struct rlimit lim; @@ -143,7 +145,9 @@ int __init main(int argc, char **argv, char **envp) install_fatal_handler(SIGINT); install_fatal_handler(SIGTERM); +#ifdef CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA scan_elf_aux(envp); +#endif do_uml_initcalls(); ret = linux_main(argc, argv); diff --git a/arch/um/os-Linux/mem.c b/arch/um/os-Linux/mem.c index e696144..62878cf 100644 --- a/arch/um/os-Linux/mem.c +++ b/arch/um/os-Linux/mem.c @@ -176,7 +176,7 @@ static int __init make_tempfile(const char *template, char **out_tempname, find_tempdir(); if ((tempdir == NULL) || (strlen(tempdir) >= MAXPATHLEN)) - return -1; + goto out; if (template[0] != '/') strcpy(tempname, tempdir); @@ -191,13 +191,15 @@ static int __init make_tempfile(const char *template, char **out_tempname, } if (do_unlink && (unlink(tempname) < 0)) { perror("unlink"); - goto out; + goto close; } if (out_tempname) { *out_tempname = tempname; } else free(tempname); return fd; +close: + close(fd); out: free(tempname); return -1; diff --git a/arch/um/os-Linux/user_syms.c b/arch/um/os-Linux/user_syms.c index 05f5ea8..45ffe46 100644 --- a/arch/um/os-Linux/user_syms.c +++ b/arch/um/os-Linux/user_syms.c @@ -113,3 +113,8 @@ EXPORT_SYMBOL(__stack_smash_handler); extern long __guard __attribute__((weak)); EXPORT_SYMBOL(__guard); + +#ifdef _FORTIFY_SOURCE +extern int __sprintf_chk(char *str, int flag, size_t strlen, const char *format); +EXPORT_SYMBOL(__sprintf_chk); +#endif diff --git a/arch/um/sys-i386/Makefile b/arch/um/sys-i386/Makefile index 87b659d..3923cfb 100644 --- a/arch/um/sys-i386/Makefile +++ b/arch/um/sys-i386/Makefile @@ -4,7 +4,7 @@ obj-y = bug.o bugs.o checksum.o delay.o fault.o ksyms.o ldt.o ptrace.o \ ptrace_user.o setjmp.o signal.o stub.o stub_segv.o syscalls.o sysrq.o \ - sys_call_table.o tls.o atomic64_cx8_32.o + sys_call_table.o tls.o atomic64_cx8_32.o mem.o obj-$(CONFIG_BINFMT_ELF) += elfcore.o diff --git a/arch/um/sys-i386/asm/elf.h b/arch/um/sys-i386/asm/elf.h index d964a41..4230555 100644 --- a/arch/um/sys-i386/asm/elf.h +++ b/arch/um/sys-i386/asm/elf.h @@ -105,6 +105,8 @@ extern unsigned long __kernel_vsyscall; #define FIXADDR_USER_START VSYSCALL_BASE #define FIXADDR_USER_END VSYSCALL_END +#define __HAVE_ARCH_GATE_AREA 1 + /* * Architecture-neutral AT_ values in 0-17, leave some room * for more of them, start the x86-specific ones at 32. diff --git a/arch/um/sys-i386/delay.c b/arch/um/sys-i386/delay.c index d623e07..f3fe1a6 100644 --- a/arch/um/sys-i386/delay.c +++ b/arch/um/sys-i386/delay.c @@ -1,29 +1,60 @@ +/* + * Copyright (C) 2011 Richard Weinberger <richrd@nod.at> + * Mostly copied from arch/x86/lib/delay.c + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + #include <linux/module.h> #include <linux/kernel.h> #include <linux/delay.h> #include <asm/param.h> -void __delay(unsigned long time) +void __delay(unsigned long loops) { - /* Stolen from the i386 __loop_delay */ - int d0; - __asm__ __volatile__( - "\tjmp 1f\n" + asm volatile( + "test %0,%0\n" + "jz 3f\n" + "jmp 1f\n" + ".align 16\n" - "1:\tjmp 2f\n" + "1: jmp 2f\n" + ".align 16\n" - "2:\tdecl %0\n\tjns 2b" - :"=&a" (d0) - :"0" (time)); + "2: dec %0\n" + " jnz 2b\n" + "3: dec %0\n" + + : /* we don't need output */ + : "a" (loops) + ); } +EXPORT_SYMBOL(__delay); -void __udelay(unsigned long usecs) +inline void __const_udelay(unsigned long xloops) { - int i, n; + int d0; - n = (loops_per_jiffy * HZ * usecs) / MILLION; - for(i=0;i<n;i++) - cpu_relax(); + xloops *= 4; + asm("mull %%edx" + : "=d" (xloops), "=&a" (d0) + : "1" (xloops), "0" + (loops_per_jiffy * (HZ/4))); + + __delay(++xloops); } +EXPORT_SYMBOL(__const_udelay); +void __udelay(unsigned long usecs) +{ + __const_udelay(usecs * 0x000010c7); /* 2**32 / 1000000 (rounded up) */ +} EXPORT_SYMBOL(__udelay); + +void __ndelay(unsigned long nsecs) +{ + __const_udelay(nsecs * 0x00005); /* 2**32 / 1000000000 (rounded up) */ +} +EXPORT_SYMBOL(__ndelay); diff --git a/arch/um/sys-i386/mem.c b/arch/um/sys-i386/mem.c new file mode 100644 index 0000000..639900a --- /dev/null +++ b/arch/um/sys-i386/mem.c @@ -0,0 +1,62 @@ +/* + * Copyright (C) 2011 Richard Weinberger <richrd@nod.at> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/mm.h> +#include <asm/page.h> +#include <asm/mman.h> + +static struct vm_area_struct gate_vma; + +static int __init gate_vma_init(void) +{ + if (!FIXADDR_USER_START) + return 0; + + gate_vma.vm_mm = NULL; + gate_vma.vm_start = FIXADDR_USER_START; + gate_vma.vm_end = FIXADDR_USER_END; + gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; + gate_vma.vm_page_prot = __P101; + + /* + * Make sure the vDSO gets into every core dump. + * Dumping its contents makes post-mortem fully interpretable later + * without matching up the same kernel and hardware config to see + * what PC values meant. + */ + gate_vma.vm_flags |= VM_ALWAYSDUMP; + + return 0; +} +__initcall(gate_vma_init); + +struct vm_area_struct *get_gate_vma(struct mm_struct *mm) +{ + return FIXADDR_USER_START ? &gate_vma : NULL; +} + +int in_gate_area_no_mm(unsigned long addr) +{ + if (!FIXADDR_USER_START) + return 0; + + if ((addr >= FIXADDR_USER_START) && (addr < FIXADDR_USER_END)) + return 1; + + return 0; +} + +int in_gate_area(struct mm_struct *mm, unsigned long addr) +{ + struct vm_area_struct *vma = get_gate_vma(mm); + + if (!vma) + return 0; + + return (addr >= vma->vm_start) && (addr < vma->vm_end); +} diff --git a/arch/um/sys-x86_64/Makefile b/arch/um/sys-x86_64/Makefile index 61fc99a..bd4d1d3 100644 --- a/arch/um/sys-x86_64/Makefile +++ b/arch/um/sys-x86_64/Makefile @@ -4,10 +4,12 @@ # Licensed under the GPL # -obj-y = bug.o bugs.o delay.o fault.o ldt.o mem.o ptrace.o ptrace_user.o \ +obj-y = bug.o bugs.o delay.o fault.o ldt.o ptrace.o ptrace_user.o mem.o \ setjmp.o signal.o stub.o stub_segv.o syscalls.o syscall_table.o \ sysrq.o ksyms.o tls.o +obj-y += vdso/ + subarch-obj-y = lib/csum-partial_64.o lib/memcpy_64.o lib/thunk_64.o \ lib/rwsem.o subarch-obj-$(CONFIG_MODULES) += kernel/module.o diff --git a/arch/um/sys-x86_64/asm/elf.h b/arch/um/sys-x86_64/asm/elf.h index d6d5af3..11a2bfb 100644 --- a/arch/um/sys-x86_64/asm/elf.h +++ b/arch/um/sys-x86_64/asm/elf.h @@ -119,4 +119,14 @@ extern long elf_aux_hwcap; #define SET_PERSONALITY(ex) do ; while(0) +#define __HAVE_ARCH_GATE_AREA 1 +#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1 +struct linux_binprm; +extern int arch_setup_additional_pages(struct linux_binprm *bprm, + int uses_interp); + +extern unsigned long um_vdso_addr; +#define AT_SYSINFO_EHDR 33 +#define ARCH_DLINFO NEW_AUX_ENT(AT_SYSINFO_EHDR, um_vdso_addr) + #endif diff --git a/arch/um/sys-x86_64/delay.c b/arch/um/sys-x86_64/delay.c index dee5be6..f3fe1a6 100644 --- a/arch/um/sys-x86_64/delay.c +++ b/arch/um/sys-x86_64/delay.c @@ -1,30 +1,60 @@ /* - * Copyright 2003 PathScale, Inc. - * Copied from arch/x86_64 + * Copyright (C) 2011 Richard Weinberger <richrd@nod.at> + * Mostly copied from arch/x86/lib/delay.c * - * Licensed under the GPL + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. */ #include <linux/module.h> +#include <linux/kernel.h> #include <linux/delay.h> -#include <asm/processor.h> #include <asm/param.h> void __delay(unsigned long loops) { - unsigned long i; + asm volatile( + "test %0,%0\n" + "jz 3f\n" + "jmp 1f\n" - for(i = 0; i < loops; i++) - cpu_relax(); + ".align 16\n" + "1: jmp 2f\n" + + ".align 16\n" + "2: dec %0\n" + " jnz 2b\n" + "3: dec %0\n" + + : /* we don't need output */ + : "a" (loops) + ); } +EXPORT_SYMBOL(__delay); -void __udelay(unsigned long usecs) +inline void __const_udelay(unsigned long xloops) { - unsigned long i, n; + int d0; - n = (loops_per_jiffy * HZ * usecs) / MILLION; - for(i=0;i<n;i++) - cpu_relax(); + xloops *= 4; + asm("mull %%edx" + : "=d" (xloops), "=&a" (d0) + : "1" (xloops), "0" + (loops_per_jiffy * (HZ/4))); + + __delay(++xloops); } +EXPORT_SYMBOL(__const_udelay); +void __udelay(unsigned long usecs) +{ + __const_udelay(usecs * 0x000010c7); /* 2**32 / 1000000 (rounded up) */ +} EXPORT_SYMBOL(__udelay); + +void __ndelay(unsigned long nsecs) +{ + __const_udelay(nsecs * 0x00005); /* 2**32 / 1000000000 (rounded up) */ +} +EXPORT_SYMBOL(__ndelay); diff --git a/arch/um/sys-x86_64/mem.c b/arch/um/sys-x86_64/mem.c index 3f8df8a..5465187 100644 --- a/arch/um/sys-x86_64/mem.c +++ b/arch/um/sys-x86_64/mem.c @@ -1,16 +1,26 @@ -/* - * Copyright 2003 PathScale, Inc. - * - * Licensed under the GPL - */ - #include "linux/mm.h" #include "asm/page.h" #include "asm/mman.h" -unsigned long vm_stack_flags = __VM_STACK_FLAGS; -unsigned long vm_stack_flags32 = __VM_STACK_FLAGS; -unsigned long vm_data_default_flags = __VM_DATA_DEFAULT_FLAGS; -unsigned long vm_data_default_flags32 = __VM_DATA_DEFAULT_FLAGS; -unsigned long vm_force_exec32 = PROT_EXEC; +const char *arch_vma_name(struct vm_area_struct *vma) +{ + if (vma->vm_mm && vma->vm_start == um_vdso_addr) + return "[vdso]"; + + return NULL; +} + +struct vm_area_struct *get_gate_vma(struct mm_struct *mm) +{ + return NULL; +} + +int in_gate_area(struct mm_struct *mm, unsigned long addr) +{ + return 0; +} +int in_gate_area_no_mm(unsigned long addr) +{ + return 0; +} diff --git a/arch/um/sys-x86_64/shared/sysdep/vm-flags.h b/arch/um/sys-x86_64/shared/sysdep/vm-flags.h index 3213edf..3978e55 100644 --- a/arch/um/sys-x86_64/shared/sysdep/vm-flags.h +++ b/arch/um/sys-x86_64/shared/sysdep/vm-flags.h @@ -7,27 +7,9 @@ #ifndef __VM_FLAGS_X86_64_H #define __VM_FLAGS_X86_64_H -#define __VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_EXEC | \ - VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) -#define __VM_STACK_FLAGS (VM_GROWSDOWN | VM_READ | VM_WRITE | \ - VM_EXEC | VM_MAYREAD | VM_MAYWRITE | \ - VM_MAYEXEC) - -extern unsigned long vm_stack_flags, vm_stack_flags32; -extern unsigned long vm_data_default_flags, vm_data_default_flags32; -extern unsigned long vm_force_exec32; - -#ifdef TIF_IA32 -#define VM_DATA_DEFAULT_FLAGS \ - (test_thread_flag(TIF_IA32) ? vm_data_default_flags32 : \ - vm_data_default_flags) - -#define VM_STACK_DEFAULT_FLAGS \ - (test_thread_flag(TIF_IA32) ? vm_stack_flags32 : vm_stack_flags) -#endif - -#define VM_DATA_DEFAULT_FLAGS vm_data_default_flags - -#define VM_STACK_DEFAULT_FLAGS vm_stack_flags +#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_EXEC | \ + VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) +#define VM_STACK_DEFAULT_FLAGS (VM_GROWSDOWN | VM_READ | VM_WRITE | \ + VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) #endif diff --git a/arch/um/sys-x86_64/vdso/Makefile b/arch/um/sys-x86_64/vdso/Makefile new file mode 100644 index 0000000..5dffe6d --- /dev/null +++ b/arch/um/sys-x86_64/vdso/Makefile @@ -0,0 +1,90 @@ +# +# Building vDSO images for x86. +# + +VDSO64-y := y + +vdso-install-$(VDSO64-y) += vdso.so + + +# files to link into the vdso +vobjs-y := vdso-note.o um_vdso.o + +# files to link into kernel +obj-$(VDSO64-y) += vdso.o vma.o + +vobjs := $(foreach F,$(vobjs-y),$(obj)/$F) + +$(obj)/vdso.o: $(obj)/vdso.so + +targets += vdso.so vdso.so.dbg vdso.lds $(vobjs-y) + +export CPPFLAGS_vdso.lds += -P -C + +VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \ + -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 + +$(obj)/vdso.o: $(src)/vdso.S $(obj)/vdso.so + +$(obj)/vdso.so.dbg: $(src)/vdso.lds $(vobjs) FORCE + $(call if_changed,vdso) + +$(obj)/%.so: OBJCOPYFLAGS := -S +$(obj)/%.so: $(obj)/%.so.dbg FORCE + $(call if_changed,objcopy) + +# +# Don't omit frame pointers for ease of userspace debugging, but do +# optimize sibling calls. +# +CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \ + $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \ + -fno-omit-frame-pointer -foptimize-sibling-calls + +$(vobjs): KBUILD_CFLAGS += $(CFL) + +# +# vDSO code runs in userspace and -pg doesn't help with profiling anyway. +# +CFLAGS_REMOVE_vdso-note.o = -pg +CFLAGS_REMOVE_um_vdso.o = -pg + +targets += vdso-syms.lds +obj-$(VDSO64-y) += vdso-syms.lds + +# +# Match symbols in the DSO that look like VDSO*; produce a file of constants. +# +sed-vdsosym := -e 's/^00*/0/' \ + -e 's/^\([0-9a-fA-F]*\) . \(VDSO[a-zA-Z0-9_]*\)$$/\2 = 0x\1;/p' +quiet_cmd_vdsosym = VDSOSYM $@ +define cmd_vdsosym + $(NM) $< | LC_ALL=C sed -n $(sed-vdsosym) | LC_ALL=C sort > $@ +endef + +$(obj)/%-syms.lds: $(obj)/%.so.dbg FORCE + $(call if_changed,vdsosym) + +# +# The DSO images are built using a special linker script. +# +quiet_cmd_vdso = VDSO $@ + cmd_vdso = $(CC) -nostdlib -o $@ \ + $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \ + -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \ + sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@' + +VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) +GCOV_PROFILE := n + +# +# Install the unstripped copy of vdso*.so listed in $(vdso-install-y). +# +quiet_cmd_vdso_install = INSTALL $@ + cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ +$(vdso-install-y): %.so: $(obj)/%.so.dbg FORCE + @mkdir -p $(MODLIB)/vdso + $(call cmd,vdso_install) + +PHONY += vdso_install $(vdso-install-y) +vdso_install: $(vdso-install-y) diff --git a/arch/um/sys-x86_64/vdso/checkundef.sh b/arch/um/sys-x86_64/vdso/checkundef.sh new file mode 100644 index 0000000..7ee90a9 --- /dev/null +++ b/arch/um/sys-x86_64/vdso/checkundef.sh @@ -0,0 +1,10 @@ +#!/bin/sh +nm="$1" +file="$2" +$nm "$file" | grep '^ *U' > /dev/null 2>&1 +if [ $? -eq 1 ]; then + exit 0 +else + echo "$file: undefined symbols found" >&2 + exit 1 +fi diff --git a/arch/um/sys-x86_64/vdso/um_vdso.c b/arch/um/sys-x86_64/vdso/um_vdso.c new file mode 100644 index 0000000..7c441b5 --- /dev/null +++ b/arch/um/sys-x86_64/vdso/um_vdso.c @@ -0,0 +1,71 @@ +/* + * Copyright (C) 2011 Richard Weinberger <richrd@nod.at> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This vDSO turns all calls into a syscall so that UML can trap them. + */ + + +/* Disable profiling for userspace code */ +#define DISABLE_BRANCH_PROFILING + +#include <linux/time.h> +#include <linux/getcpu.h> +#include <asm/unistd.h> + +int __vdso_clock_gettime(clockid_t clock, struct timespec *ts) +{ + long ret; + + asm("syscall" : "=a" (ret) : + "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : "memory"); + + return ret; +} +int clock_gettime(clockid_t, struct timespec *) + __attribute__((weak, alias("__vdso_clock_gettime"))); + +int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) +{ + long ret; + + asm("syscall" : "=a" (ret) : + "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory"); + + return ret; +} +int gettimeofday(struct timeval *, struct timezone *) + __attribute__((weak, alias("__vdso_gettimeofday"))); + +time_t __vdso_time(time_t *t) +{ + long secs; + + asm volatile("syscall" + : "=a" (secs) + : "0" (__NR_time), "D" (t) : "cc", "r11", "cx", "memory"); + + return secs; +} +int time(time_t *t) __attribute__((weak, alias("__vdso_time"))); + +long +__vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused) +{ + /* + * UML does not support SMP, we can cheat here. :) + */ + + if (cpu) + *cpu = 0; + if (node) + *node = 0; + + return 0; +} + +long getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache) + __attribute__((weak, alias("__vdso_getcpu"))); diff --git a/arch/um/sys-x86_64/vdso/vdso-layout.lds.S b/arch/um/sys-x86_64/vdso/vdso-layout.lds.S new file mode 100644 index 0000000..634a2cf --- /dev/null +++ b/arch/um/sys-x86_64/vdso/vdso-layout.lds.S @@ -0,0 +1,64 @@ +/* + * Linker script for vDSO. This is an ELF shared object prelinked to + * its virtual address, and with only one read-only segment. + * This script controls its layout. + */ + +SECTIONS +{ + . = VDSO_PRELINK + SIZEOF_HEADERS; + + .hash : { *(.hash) } :text + .gnu.hash : { *(.gnu.hash) } + .dynsym : { *(.dynsym) } + .dynstr : { *(.dynstr) } + .gnu.version : { *(.gnu.version) } + .gnu.version_d : { *(.gnu.version_d) } + .gnu.version_r : { *(.gnu.version_r) } + + .note : { *(.note.*) } :text :note + + .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr + .eh_frame : { KEEP (*(.eh_frame)) } :text + + .dynamic : { *(.dynamic) } :text :dynamic + + .rodata : { *(.rodata*) } :text + .data : { + *(.data*) + *(.sdata*) + *(.got.plt) *(.got) + *(.gnu.linkonce.d.*) + *(.bss*) + *(.dynbss*) + *(.gnu.linkonce.b.*) + } + + .altinstructions : { *(.altinstructions) } + .altinstr_replacement : { *(.altinstr_replacement) } + + /* + * Align the actual code well away from the non-instruction data. + * This is the best thing for the I-cache. + */ + . = ALIGN(0x100); + + .text : { *(.text*) } :text =0x90909090 +} + +/* + * Very old versions of ld do not recognize this name token; use the constant. + */ +#define PT_GNU_EH_FRAME 0x6474e550 + +/* + * We must supply the ELF program headers explicitly to get just one + * PT_LOAD segment, and set the flags explicitly to make segments read-only. + */ +PHDRS +{ + text PT_LOAD FLAGS(5) FILEHDR PHDRS; /* PF_R|PF_X */ + dynamic PT_DYNAMIC FLAGS(4); /* PF_R */ + note PT_NOTE FLAGS(4); /* PF_R */ + eh_frame_hdr PT_GNU_EH_FRAME; +} diff --git a/arch/um/sys-x86_64/vdso/vdso-note.S b/arch/um/sys-x86_64/vdso/vdso-note.S new file mode 100644 index 0000000..79a071e --- /dev/null +++ b/arch/um/sys-x86_64/vdso/vdso-note.S @@ -0,0 +1,12 @@ +/* + * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text. + * Here we can supply some information useful to userland. + */ + +#include <linux/uts.h> +#include <linux/version.h> +#include <linux/elfnote.h> + +ELFNOTE_START(Linux, 0, "a") + .long LINUX_VERSION_CODE +ELFNOTE_END diff --git a/arch/um/sys-x86_64/vdso/vdso.S b/arch/um/sys-x86_64/vdso/vdso.S new file mode 100644 index 0000000..ec82c16 --- /dev/null +++ b/arch/um/sys-x86_64/vdso/vdso.S @@ -0,0 +1,10 @@ +#include <linux/init.h> + +__INITDATA + + .globl vdso_start, vdso_end +vdso_start: + .incbin "arch/um/sys-x86_64/vdso/vdso.so" +vdso_end: + +__FINIT diff --git a/arch/um/sys-x86_64/vdso/vdso.lds.S b/arch/um/sys-x86_64/vdso/vdso.lds.S new file mode 100644 index 0000000..b96b267 --- /dev/null +++ b/arch/um/sys-x86_64/vdso/vdso.lds.S @@ -0,0 +1,32 @@ +/* + * Linker script for 64-bit vDSO. + * We #include the file to define the layout details. + * Here we only choose the prelinked virtual address. + * + * This file defines the version script giving the user-exported symbols in + * the DSO. We can define local symbols here called VDSO* to make their + * values visible using the asm-x86/vdso.h macros from the kernel proper. + */ + +#define VDSO_PRELINK 0xffffffffff700000 +#include "vdso-layout.lds.S" + +/* + * This controls what userland symbols we export from the vDSO. + */ +VERSION { + LINUX_2.6 { + global: + clock_gettime; + __vdso_clock_gettime; + gettimeofday; + __vdso_gettimeofday; + getcpu; + __vdso_getcpu; + time; + __vdso_time; + local: *; + }; +} + +VDSO64_PRELINK = VDSO_PRELINK; diff --git a/arch/um/sys-x86_64/vdso/vma.c b/arch/um/sys-x86_64/vdso/vma.c new file mode 100644 index 0000000..9495c8d --- /dev/null +++ b/arch/um/sys-x86_64/vdso/vma.c @@ -0,0 +1,74 @@ +/* + * Copyright (C) 2011 Richard Weinberger <richrd@nod.at> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/slab.h> +#include <linux/sched.h> +#include <linux/mm.h> +#include <asm/page.h> +#include <linux/init.h> + +unsigned int __read_mostly vdso_enabled = 1; +unsigned long um_vdso_addr; + +extern unsigned long task_size; +extern char vdso_start[], vdso_end[]; + +static struct page **vdsop; + +static int __init init_vdso(void) +{ + struct page *um_vdso; + + BUG_ON(vdso_end - vdso_start > PAGE_SIZE); + + um_vdso_addr = task_size - PAGE_SIZE; + + vdsop = kmalloc(GFP_KERNEL, sizeof(struct page *)); + if (!vdsop) + goto oom; + + um_vdso = alloc_page(GFP_KERNEL); + if (!um_vdso) { + kfree(vdsop); + + goto oom; + } + + copy_page(page_address(um_vdso), vdso_start); + *vdsop = um_vdso; + + return 0; + +oom: + printk(KERN_ERR "Cannot allocate vdso\n"); + vdso_enabled = 0; + + return -ENOMEM; +} +subsys_initcall(init_vdso); + +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) +{ + int err; + struct mm_struct *mm = current->mm; + + if (!vdso_enabled) + return 0; + + down_write(&mm->mmap_sem); + + err = install_special_mapping(mm, um_vdso_addr, PAGE_SIZE, + VM_READ|VM_EXEC| + VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC| + VM_ALWAYSDUMP, + vdsop); + + up_write(&mm->mmap_sem); + + return err; +} diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h index 82d4e38..3fa526f 100644 --- a/arch/xtensa/include/asm/uaccess.h +++ b/arch/xtensa/include/asm/uaccess.h @@ -17,6 +17,7 @@ #define _XTENSA_UACCESS_H #include <linux/errno.h> +#include <linux/prefetch.h> #include <asm/types.h> #define VERIFY_READ 0 diff --git a/arch/xtensa/kernel/ptrace.c b/arch/xtensa/kernel/ptrace.c index c72c947..a0d042a 100644 --- a/arch/xtensa/kernel/ptrace.c +++ b/arch/xtensa/kernel/ptrace.c @@ -147,6 +147,9 @@ int ptrace_setxregs(struct task_struct *child, void __user *uregs) elf_xtregs_t *xtregs = uregs; int ret = 0; + if (!access_ok(VERIFY_READ, uregs, sizeof(elf_xtregs_t))) + return -EFAULT; + #if XTENSA_HAVE_COPROCESSORS /* Flush all coprocessors before we overwrite them. */ coprocessor_flush_all(ti); |