diff options
Diffstat (limited to 'arch')
234 files changed, 3461 insertions, 7525 deletions
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 5917099470ea..4a0e54fc01b2 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -184,6 +184,7 @@ config ARC_CACHE_PAGES config ARC_CACHE_VIPT_ALIASING bool "Support VIPT Aliasing D$" + depends on ARC_HAS_DCACHE default n endif #ARC_CACHE @@ -361,13 +362,6 @@ config ARC_MISALIGN_ACCESS Use ONLY-IF-ABS-NECESSARY as it will be very slow and also can hide potential bugs in code -config ARC_STACK_NONEXEC - bool "Make stack non-executable" - default n - help - To disable the execute permissions of stack/heap of processes - which are enabled by default. - config HZ int "Timer Frequency" default 100 diff --git a/arch/arc/Makefile b/arch/arc/Makefile index 183397fd289e..8c0b1aa56f7e 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -9,25 +9,27 @@ UTS_MACHINE := arc ifeq ($(CROSS_COMPILE),) -CROSS_COMPILE := arc-elf32- +CROSS_COMPILE := arc-linux-uclibc- endif KBUILD_DEFCONFIG := fpga_defconfig cflags-y += -mA7 -fno-common -pipe -fno-builtin -D__linux__ -LINUXINCLUDE += -include ${src}/arch/arc/include/asm/defines.h - ifdef CONFIG_ARC_CURR_IN_REG # For a global register defintion, make sure it gets passed to every file # We had a customer reported bug where some code built in kernel was NOT using # any kernel headers, and missing the r25 global register -# Can't do unconditionally (like above) because of recursive include issues +# Can't do unconditionally because of recursive include issues # due to <linux/thread_info.h> LINUXINCLUDE += -include ${src}/arch/arc/include/asm/current.h endif -atleast_gcc44 := $(call cc-ifversion, -gt, 0402, y) +upto_gcc42 := $(call cc-ifversion, -le, 0402, y) +upto_gcc44 := $(call cc-ifversion, -le, 0404, y) +atleast_gcc44 := $(call cc-ifversion, -ge, 0404, y) +atleast_gcc48 := $(call cc-ifversion, -ge, 0408, y) + cflags-$(atleast_gcc44) += -fsection-anchors cflags-$(CONFIG_ARC_HAS_LLSC) += -mlock @@ -35,6 +37,11 @@ cflags-$(CONFIG_ARC_HAS_SWAPE) += -mswape cflags-$(CONFIG_ARC_HAS_RTSC) += -mrtsc cflags-$(CONFIG_ARC_DW2_UNWIND) += -fasynchronous-unwind-tables +# By default gcc 4.8 generates dwarf4 which kernel unwinder can't grok +ifeq ($(atleast_gcc48),y) +cflags-$(CONFIG_ARC_DW2_UNWIND) += -gdwarf-2 +endif + ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE # Generic build system uses -O2, we want -O3 cflags-y += -O3 @@ -48,11 +55,10 @@ cflags-$(disable_small_data) += -mno-sdata -fcall-used-gp cflags-$(CONFIG_CPU_BIG_ENDIAN) += -mbig-endian ldflags-$(CONFIG_CPU_BIG_ENDIAN) += -EB -# STAR 9000518362: +# STAR 9000518362: (fixed with binutils shipping with gcc 4.8) # arc-linux-uclibc-ld (buildroot) or arceb-elf32-ld (EZChip) don't accept -# --build-id w/o "-marclinux". -# Default arc-elf32-ld is OK -ldflags-y += -marclinux +# --build-id w/o "-marclinux". Default arc-elf32-ld is OK +ldflags-$(upto_gcc44) += -marclinux ARC_LIBGCC := -mA7 cflags-$(CONFIG_ARC_HAS_HW_MPY) += -multcost=16 @@ -66,8 +72,8 @@ ifndef CONFIG_ARC_HAS_HW_MPY # With gcc 4.4.7, -mno-mpy is enough to make any other related adjustments, # e.g. increased cost of MPY. With gcc 4.2.1 this had to be explicitly hinted - ARC_LIBGCC := -marc600 - ifneq ($(atleast_gcc44),y) + ifeq ($(upto_gcc42),y) + ARC_LIBGCC := -marc600 cflags-y += -multcost=30 endif endif diff --git a/arch/arc/configs/fpga_defconfig b/arch/arc/configs/fpga_defconfig index 95350be6ef6f..c109af320274 100644 --- a/arch/arc/configs/fpga_defconfig +++ b/arch/arc/configs/fpga_defconfig @@ -1,4 +1,4 @@ -CONFIG_CROSS_COMPILE="arc-elf32-" +CONFIG_CROSS_COMPILE="arc-linux-uclibc-" # CONFIG_LOCALVERSION_AUTO is not set CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig index 446c96c24eff..451af30914f6 100644 --- a/arch/arc/configs/nsimosci_defconfig +++ b/arch/arc/configs/nsimosci_defconfig @@ -1,4 +1,4 @@ -CONFIG_CROSS_COMPILE="arc-elf32-" +CONFIG_CROSS_COMPILE="arc-linux-uclibc-" # CONFIG_LOCALVERSION_AUTO is not set CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig index 4fa5cd9f2202..6be6492442d6 100644 --- a/arch/arc/configs/tb10x_defconfig +++ b/arch/arc/configs/tb10x_defconfig @@ -1,4 +1,4 @@ -CONFIG_CROSS_COMPILE="arc-elf32-" +CONFIG_CROSS_COMPILE="arc-linux-uclibc-" # CONFIG_LOCALVERSION_AUTO is not set CONFIG_DEFAULT_HOSTNAME="tb10x" CONFIG_SYSVIPC=y diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h index 1b907c465666..355cb470c2a4 100644 --- a/arch/arc/include/asm/arcregs.h +++ b/arch/arc/include/asm/arcregs.h @@ -20,7 +20,6 @@ #define ARC_REG_PERIBASE_BCR 0x69 #define ARC_REG_FP_BCR 0x6B /* Single-Precision FPU */ #define ARC_REG_DPFP_BCR 0x6C /* Dbl Precision FPU */ -#define ARC_REG_MMU_BCR 0x6f #define ARC_REG_DCCM_BCR 0x74 /* DCCM Present + SZ */ #define ARC_REG_TIMERS_BCR 0x75 #define ARC_REG_ICCM_BCR 0x78 @@ -34,22 +33,12 @@ #define ARC_REG_D_UNCACH_BCR 0x6A /* status32 Bits Positions */ -#define STATUS_H_BIT 0 /* CPU Halted */ -#define STATUS_E1_BIT 1 /* Int 1 enable */ -#define STATUS_E2_BIT 2 /* Int 2 enable */ -#define STATUS_A1_BIT 3 /* Int 1 active */ -#define STATUS_A2_BIT 4 /* Int 2 active */ #define STATUS_AE_BIT 5 /* Exception active */ #define STATUS_DE_BIT 6 /* PC is in delay slot */ #define STATUS_U_BIT 7 /* User/Kernel mode */ #define STATUS_L_BIT 12 /* Loop inhibit */ /* These masks correspond to the status word(STATUS_32) bits */ -#define STATUS_H_MASK (1<<STATUS_H_BIT) -#define STATUS_E1_MASK (1<<STATUS_E1_BIT) -#define STATUS_E2_MASK (1<<STATUS_E2_BIT) -#define STATUS_A1_MASK (1<<STATUS_A1_BIT) -#define STATUS_A2_MASK (1<<STATUS_A2_BIT) #define STATUS_AE_MASK (1<<STATUS_AE_BIT) #define STATUS_DE_MASK (1<<STATUS_DE_BIT) #define STATUS_U_MASK (1<<STATUS_U_BIT) @@ -71,6 +60,7 @@ #define ECR_V_ITLB_MISS 0x21 #define ECR_V_DTLB_MISS 0x22 #define ECR_V_PROTV 0x23 +#define ECR_V_TRAP 0x25 /* Protection Violation Exception Cause Code Values */ #define ECR_C_PROTV_INST_FETCH 0x00 @@ -79,94 +69,23 @@ #define ECR_C_PROTV_XCHG 0x03 #define ECR_C_PROTV_MISALIG_DATA 0x04 +#define ECR_C_BIT_PROTV_MISALIG_DATA 10 + +/* Machine Check Cause Code Values */ +#define ECR_C_MCHK_DUP_TLB 0x01 + /* DTLB Miss Exception Cause Code Values */ #define ECR_C_BIT_DTLB_LD_MISS 8 #define ECR_C_BIT_DTLB_ST_MISS 9 +/* Dummy ECR values for Interrupts */ +#define event_IRQ1 0x0031abcd +#define event_IRQ2 0x0032abcd /* Auxiliary registers */ #define AUX_IDENTITY 4 #define AUX_INTR_VEC_BASE 0x25 -#define AUX_IRQ_LEV 0x200 /* IRQ Priority: L1 or L2 */ -#define AUX_IRQ_HINT 0x201 /* For generating Soft Interrupts */ -#define AUX_IRQ_LV12 0x43 /* interrupt level register */ - -#define AUX_IENABLE 0x40c -#define AUX_ITRIGGER 0x40d -#define AUX_IPULSE 0x415 - -/* Timer related Aux registers */ -#define ARC_REG_TIMER0_LIMIT 0x23 /* timer 0 limit */ -#define ARC_REG_TIMER0_CTRL 0x22 /* timer 0 control */ -#define ARC_REG_TIMER0_CNT 0x21 /* timer 0 count */ -#define ARC_REG_TIMER1_LIMIT 0x102 /* timer 1 limit */ -#define ARC_REG_TIMER1_CTRL 0x101 /* timer 1 control */ -#define ARC_REG_TIMER1_CNT 0x100 /* timer 1 count */ - -#define TIMER_CTRL_IE (1 << 0) /* Interupt when Count reachs limit */ -#define TIMER_CTRL_NH (1 << 1) /* Count only when CPU NOT halted */ - -/* MMU Management regs */ -#define ARC_REG_TLBPD0 0x405 -#define ARC_REG_TLBPD1 0x406 -#define ARC_REG_TLBINDEX 0x407 -#define ARC_REG_TLBCOMMAND 0x408 -#define ARC_REG_PID 0x409 -#define ARC_REG_SCRATCH_DATA0 0x418 - -/* Bits in MMU PID register */ -#define MMU_ENABLE (1 << 31) /* Enable MMU for process */ - -/* Error code if probe fails */ -#define TLB_LKUP_ERR 0x80000000 - -/* TLB Commands */ -#define TLBWrite 0x1 -#define TLBRead 0x2 -#define TLBGetIndex 0x3 -#define TLBProbe 0x4 - -#if (CONFIG_ARC_MMU_VER >= 2) -#define TLBWriteNI 0x5 /* write JTLB without inv uTLBs */ -#define TLBIVUTLB 0x6 /* explicitly inv uTLBs */ -#else -#undef TLBWriteNI /* These cmds don't exist on older MMU */ -#undef TLBIVUTLB -#endif -/* Instruction cache related Auxiliary registers */ -#define ARC_REG_IC_BCR 0x77 /* Build Config reg */ -#define ARC_REG_IC_IVIC 0x10 -#define ARC_REG_IC_CTRL 0x11 -#define ARC_REG_IC_IVIL 0x19 -#if (CONFIG_ARC_MMU_VER > 2) -#define ARC_REG_IC_PTAG 0x1E -#endif - -/* Bit val in IC_CTRL */ -#define IC_CTRL_CACHE_DISABLE 0x1 - -/* Data cache related Auxiliary registers */ -#define ARC_REG_DC_BCR 0x72 -#define ARC_REG_DC_IVDC 0x47 -#define ARC_REG_DC_CTRL 0x48 -#define ARC_REG_DC_IVDL 0x4A -#define ARC_REG_DC_FLSH 0x4B -#define ARC_REG_DC_FLDL 0x4C -#if (CONFIG_ARC_MMU_VER > 2) -#define ARC_REG_DC_PTAG 0x5C -#endif - -/* Bit val in DC_CTRL */ -#define DC_CTRL_INV_MODE_FLUSH 0x40 -#define DC_CTRL_FLUSH_STATUS 0x100 - -/* MMU Management regs */ -#define ARC_REG_PID 0x409 -#define ARC_REG_SCRATCH_DATA0 0x418 - -/* Bits in MMU PID register */ -#define MMU_ENABLE (1 << 31) /* Enable MMU for process */ /* * Floating Pt Registers @@ -293,24 +212,6 @@ struct bcr_identity { #endif }; -struct bcr_mmu_1_2 { -#ifdef CONFIG_CPU_BIG_ENDIAN - unsigned int ver:8, ways:4, sets:4, u_itlb:8, u_dtlb:8; -#else - unsigned int u_dtlb:8, u_itlb:8, sets:4, ways:4, ver:8; -#endif -}; - -struct bcr_mmu_3 { -#ifdef CONFIG_CPU_BIG_ENDIAN - unsigned int ver:8, ways:4, sets:4, osm:1, reserv:3, pg_sz:4, - u_itlb:4, u_dtlb:4; -#else - unsigned int u_dtlb:4, u_itlb:4, pg_sz:4, reserv:3, osm:1, sets:4, - ways:4, ver:8; -#endif -}; - #define EXTN_SWAP_VALID 0x1 #define EXTN_NORM_VALID 0x2 #define EXTN_MINMAX_VALID 0x2 @@ -343,14 +244,6 @@ struct bcr_extn_xymem { #endif }; -struct bcr_cache { -#ifdef CONFIG_CPU_BIG_ENDIAN - unsigned int pad:12, line_len:4, sz:4, config:4, ver:8; -#else - unsigned int ver:8, config:4, sz:4, line_len:4, pad:12; -#endif -}; - struct bcr_perip { #ifdef CONFIG_CPU_BIG_ENDIAN unsigned int start:8, pad2:8, sz:8, pad:8; @@ -403,7 +296,7 @@ struct cpuinfo_arc_mmu { }; struct cpuinfo_arc_cache { - unsigned int has_aliasing, sz, line_len, assoc, ver; + unsigned int sz, line_len, assoc, ver; }; struct cpuinfo_arc_ccm { diff --git a/arch/arc/include/asm/bug.h b/arch/arc/include/asm/bug.h index 2ad8f9b1c54b..5b18e94c6678 100644 --- a/arch/arc/include/asm/bug.h +++ b/arch/arc/include/asm/bug.h @@ -18,9 +18,8 @@ struct task_struct; void show_regs(struct pt_regs *regs); void show_stacktrace(struct task_struct *tsk, struct pt_regs *regs); void show_kernel_fault_diag(const char *str, struct pt_regs *regs, - unsigned long address, unsigned long cause_reg); -void die(const char *str, struct pt_regs *regs, unsigned long address, - unsigned long cause_reg); + unsigned long address); +void die(const char *str, struct pt_regs *regs, unsigned long address); #define BUG() do { \ dump_stack(); \ diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h index d5555fe4742a..5802849a6cae 100644 --- a/arch/arc/include/asm/cache.h +++ b/arch/arc/include/asm/cache.h @@ -18,21 +18,19 @@ #define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT) -#define ARC_ICACHE_WAYS 2 -#define ARC_DCACHE_WAYS 4 - -/* Helpers */ +/* For a rare case where customers have differently config I/D */ #define ARC_ICACHE_LINE_LEN L1_CACHE_BYTES #define ARC_DCACHE_LINE_LEN L1_CACHE_BYTES #define ICACHE_LINE_MASK (~(ARC_ICACHE_LINE_LEN - 1)) #define DCACHE_LINE_MASK (~(ARC_DCACHE_LINE_LEN - 1)) -#if ARC_ICACHE_LINE_LEN != ARC_DCACHE_LINE_LEN -#error "Need to fix some code as I/D cache lines not same" -#else -#define is_not_cache_aligned(p) ((unsigned long)p & (~DCACHE_LINE_MASK)) -#endif +/* + * ARC700 doesn't cache any access in top 256M. + * Ideal for wiring memory mapped peripherals as we don't need to do + * explicit uncached accesses (LD.di/ST.di) hence more portable drivers + */ +#define ARC_UNCACHED_ADDR_SPACE 0xc0000000 #ifndef __ASSEMBLY__ @@ -57,16 +55,10 @@ #define ARCH_DMA_MINALIGN L1_CACHE_BYTES -/* - * ARC700 doesn't cache any access in top 256M. - * Ideal for wiring memory mapped peripherals as we don't need to do - * explicit uncached accesses (LD.di/ST.di) hence more portable drivers - */ -#define ARC_UNCACHED_ADDR_SPACE 0xc0000000 - extern void arc_cache_init(void); extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len); extern void __init read_decode_cache_bcr(void); -#endif + +#endif /* !__ASSEMBLY__ */ #endif /* _ASM_CACHE_H */ diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h index ef62682e8d95..6abc4972bc93 100644 --- a/arch/arc/include/asm/cacheflush.h +++ b/arch/arc/include/asm/cacheflush.h @@ -81,16 +81,19 @@ void flush_anon_page(struct vm_area_struct *vma, #endif /* CONFIG_ARC_CACHE_VIPT_ALIASING */ /* + * A new pagecache page has PG_arch_1 clear - thus dcache dirty by default + * This works around some PIO based drivers which don't call flush_dcache_page + * to record that they dirtied the dcache + */ +#define PG_dc_clean PG_arch_1 + +/* * Simple wrapper over config option * Bootup code ensures that hardware matches kernel configuration */ static inline int cache_is_vipt_aliasing(void) { -#ifdef CONFIG_ARC_CACHE_VIPT_ALIASING - return 1; -#else - return 0; -#endif + return IS_ENABLED(CONFIG_ARC_CACHE_VIPT_ALIASING); } #define CACHE_COLOR(addr) (((unsigned long)(addr) >> (PAGE_SHIFT)) & 1) diff --git a/arch/arc/include/asm/defines.h b/arch/arc/include/asm/defines.h deleted file mode 100644 index 6097bb439cc5..000000000000 --- a/arch/arc/include/asm/defines.h +++ /dev/null @@ -1,56 +0,0 @@ -/* - * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) - * - * 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. - */ - -#ifndef __ARC_ASM_DEFINES_H__ -#define __ARC_ASM_DEFINES_H__ - -#if defined(CONFIG_ARC_MMU_V1) -#define CONFIG_ARC_MMU_VER 1 -#elif defined(CONFIG_ARC_MMU_V2) -#define CONFIG_ARC_MMU_VER 2 -#elif defined(CONFIG_ARC_MMU_V3) -#define CONFIG_ARC_MMU_VER 3 -#endif - -#ifdef CONFIG_ARC_HAS_LLSC -#define __CONFIG_ARC_HAS_LLSC_VAL 1 -#else -#define __CONFIG_ARC_HAS_LLSC_VAL 0 -#endif - -#ifdef CONFIG_ARC_HAS_SWAPE -#define __CONFIG_ARC_HAS_SWAPE_VAL 1 -#else -#define __CONFIG_ARC_HAS_SWAPE_VAL 0 -#endif - -#ifdef CONFIG_ARC_HAS_RTSC -#define __CONFIG_ARC_HAS_RTSC_VAL 1 -#else -#define __CONFIG_ARC_HAS_RTSC_VAL 0 -#endif - -#ifdef CONFIG_ARC_MMU_SASID -#define __CONFIG_ARC_MMU_SASID_VAL 1 -#else -#define __CONFIG_ARC_MMU_SASID_VAL 0 -#endif - -#ifdef CONFIG_ARC_HAS_ICACHE -#define __CONFIG_ARC_HAS_ICACHE 1 -#else -#define __CONFIG_ARC_HAS_ICACHE 0 -#endif - -#ifdef CONFIG_ARC_HAS_DCACHE -#define __CONFIG_ARC_HAS_DCACHE 1 -#else -#define __CONFIG_ARC_HAS_DCACHE 0 -#endif - -#endif /* __ARC_ASM_DEFINES_H__ */ diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h index eb2ae53187d9..8943c028d4bb 100644 --- a/arch/arc/include/asm/entry.h +++ b/arch/arc/include/asm/entry.h @@ -50,194 +50,177 @@ * Eff Addr for load = [reg2] */ +.macro PUSH reg + st.a \reg, [sp, -4] +.endm + +.macro PUSHAX aux + lr r9, [\aux] + PUSH r9 +.endm + +.macro POP reg + ld.ab \reg, [sp, 4] +.endm + +.macro POPAX aux + POP r9 + sr r9, [\aux] +.endm + /*-------------------------------------------------------------- - * Save caller saved registers (scratch registers) ( r0 - r12 ) - * Registers are pushed / popped in the order defined in struct ptregs - * in asm/ptrace.h + * Helpers to save/restore Scratch Regs: + * used by Interrupt/Exception Prologue/Epilogue *-------------------------------------------------------------*/ -.macro SAVE_CALLER_SAVED - st.a r0, [sp, -4] - st.a r1, [sp, -4] - st.a r2, [sp, -4] - st.a r3, [sp, -4] - st.a r4, [sp, -4] - st.a r5, [sp, -4] - st.a r6, [sp, -4] - st.a r7, [sp, -4] - st.a r8, [sp, -4] - st.a r9, [sp, -4] - st.a r10, [sp, -4] - st.a r11, [sp, -4] - st.a r12, [sp, -4] +.macro SAVE_R0_TO_R12 + PUSH r0 + PUSH r1 + PUSH r2 + PUSH r3 + PUSH r4 + PUSH r5 + PUSH r6 + PUSH r7 + PUSH r8 + PUSH r9 + PUSH r10 + PUSH r11 + PUSH r12 +.endm + +.macro RESTORE_R12_TO_R0 + POP r12 + POP r11 + POP r10 + POP r9 + POP r8 + POP r7 + POP r6 + POP r5 + POP r4 + POP r3 + POP r2 + POP r1 + POP r0 + +#ifdef CONFIG_ARC_CURR_IN_REG + ld r25, [sp, 12] +#endif .endm /*-------------------------------------------------------------- - * Restore caller saved registers (scratch registers) + * Helpers to save/restore callee-saved regs: + * used by several macros below *-------------------------------------------------------------*/ -.macro RESTORE_CALLER_SAVED - ld.ab r12, [sp, 4] - ld.ab r11, [sp, 4] - ld.ab r10, [sp, 4] - ld.ab r9, [sp, 4] - ld.ab r8, [sp, 4] - ld.ab r7, [sp, 4] - ld.ab r6, [sp, 4] - ld.ab r5, [sp, 4] - ld.ab r4, [sp, 4] - ld.ab r3, [sp, 4] - ld.ab r2, [sp, 4] - ld.ab r1, [sp, 4] - ld.ab r0, [sp, 4] +.macro SAVE_R13_TO_R24 + PUSH r13 + PUSH r14 + PUSH r15 + PUSH r16 + PUSH r17 + PUSH r18 + PUSH r19 + PUSH r20 + PUSH r21 + PUSH r22 + PUSH r23 + PUSH r24 +.endm + +.macro RESTORE_R24_TO_R13 + POP r24 + POP r23 + POP r22 + POP r21 + POP r20 + POP r19 + POP r18 + POP r17 + POP r16 + POP r15 + POP r14 + POP r13 .endm +#define OFF_USER_R25_FROM_R24 (SZ_CALLEE_REGS + SZ_PT_REGS - 8)/4 /*-------------------------------------------------------------- - * Save callee saved registers (non scratch registers) ( r13 - r25 ) - * on kernel stack. - * User mode callee regs need to be saved in case of - * -fork and friends for replicating from parent to child - * -before going into do_signal( ) for ptrace/core-dump - * Special case handling is required for r25 in case it is used by kernel - * for caching task ptr. Low level exception/ISR save user mode r25 - * into task->thread.user_r25. So it needs to be retrieved from there and - * saved into kernel stack with rest of callee reg-file + * Collect User Mode callee regs as struct callee_regs - needed by + * fork/do_signal/unaligned-access-emulation. + * (By default only scratch regs are saved on entry to kernel) + * + * Special handling for r25 if used for caching Task Pointer. + * It would have been saved in task->thread.user_r25 already, but to keep + * the interface same it is copied into regular r25 placeholder in + * struct callee_regs. *-------------------------------------------------------------*/ .macro SAVE_CALLEE_SAVED_USER - st.a r13, [sp, -4] - st.a r14, [sp, -4] - st.a r15, [sp, -4] - st.a r16, [sp, -4] - st.a r17, [sp, -4] - st.a r18, [sp, -4] - st.a r19, [sp, -4] - st.a r20, [sp, -4] - st.a r21, [sp, -4] - st.a r22, [sp, -4] - st.a r23, [sp, -4] - st.a r24, [sp, -4] + + SAVE_R13_TO_R24 #ifdef CONFIG_ARC_CURR_IN_REG ; Retrieve orig r25 and save it on stack - ld r12, [r25, TASK_THREAD + THREAD_USER_R25] + ld.as r12, [sp, OFF_USER_R25_FROM_R24] st.a r12, [sp, -4] #else - st.a r25, [sp, -4] + PUSH r25 #endif - /* move up by 1 word to "create" callee_regs->"stack_place_holder" */ - sub sp, sp, 4 .endm /*-------------------------------------------------------------- - * Save callee saved registers (non scratch registers) ( r13 - r25 ) - * kernel mode callee regs needed to be saved in case of context switch - * If r25 is used for caching task pointer then that need not be saved - * as it can be re-created from current task global + * Save kernel Mode callee regs at the time of Contect Switch. + * + * Special handling for r25 if used for caching Task Pointer. + * Kernel simply skips saving it since it will be loaded with + * incoming task pointer anyways *-------------------------------------------------------------*/ .macro SAVE_CALLEE_SAVED_KERNEL - st.a r13, [sp, -4] - st.a r14, [sp, -4] - st.a r15, [sp, -4] - st.a r16, [sp, -4] - st.a r17, [sp, -4] - st.a r18, [sp, -4] - st.a r19, [sp, -4] - st.a r20, [sp, -4] - st.a r21, [sp, -4] - st.a r22, [sp, -4] - st.a r23, [sp, -4] - st.a r24, [sp, -4] + + SAVE_R13_TO_R24 + #ifdef CONFIG_ARC_CURR_IN_REG - sub sp, sp, 8 -#else - st.a r25, [sp, -4] sub sp, sp, 4 +#else + PUSH r25 #endif .endm /*-------------------------------------------------------------- - * RESTORE_CALLEE_SAVED_KERNEL: - * Loads callee (non scratch) Reg File by popping from Kernel mode stack. - * This is reverse of SAVE_CALLEE_SAVED, - * - * NOTE: - * Ideally this shd only be called in switch_to for loading - * switched-IN task's CALLEE Reg File. - * For all other cases RESTORE_CALLEE_SAVED_FAST must be used - * which simply pops the stack w/o touching regs. + * Opposite of SAVE_CALLEE_SAVED_KERNEL *-------------------------------------------------------------*/ .macro RESTORE_CALLEE_SAVED_KERNEL - #ifdef CONFIG_ARC_CURR_IN_REG - add sp, sp, 8 /* skip callee_reg gutter and user r25 placeholder */ + add sp, sp, 4 /* skip usual r25 placeholder */ #else - add sp, sp, 4 /* skip "callee_regs->stack_place_holder" */ - ld.ab r25, [sp, 4] + POP r25 #endif - - ld.ab r24, [sp, 4] - ld.ab r23, [sp, 4] - ld.ab r22, [sp, 4] - ld.ab r21, [sp, 4] - ld.ab r20, [sp, 4] - ld.ab r19, [sp, 4] - ld.ab r18, [sp, 4] - ld.ab r17, [sp, 4] - ld.ab r16, [sp, 4] - ld.ab r15, [sp, 4] - ld.ab r14, [sp, 4] - ld.ab r13, [sp, 4] - + RESTORE_R24_TO_R13 .endm /*-------------------------------------------------------------- - * RESTORE_CALLEE_SAVED_USER: - * This is called after do_signal where tracer might have changed callee regs - * thus we need to restore the reg file. - * Special case handling is required for r25 in case it is used by kernel - * for caching task ptr. Ptrace would have modified on-kernel-stack value of - * r25, which needs to be shoved back into task->thread.user_r25 where from - * Low level exception/ISR return code will retrieve to populate with rest of - * callee reg-file. + * Opposite of SAVE_CALLEE_SAVED_USER + * + * ptrace tracer or unaligned-access fixup might have changed a user mode + * callee reg which is saved back to usual r25 storage location *-------------------------------------------------------------*/ .macro RESTORE_CALLEE_SAVED_USER - add sp, sp, 4 /* skip "callee_regs->stack_place_holder" */ - #ifdef CONFIG_ARC_CURR_IN_REG ld.ab r12, [sp, 4] - st r12, [r25, TASK_THREAD + THREAD_USER_R25] + st.as r12, [sp, OFF_USER_R25_FROM_R24] #else - ld.ab r25, [sp, 4] + POP r25 #endif - - ld.ab r24, [sp, 4] - ld.ab r23, [sp, 4] - ld.ab r22, [sp, 4] - ld.ab r21, [sp, 4] - ld.ab r20, [sp, 4] - ld.ab r19, [sp, 4] - ld.ab r18, [sp, 4] - ld.ab r17, [sp, 4] - ld.ab r16, [sp, 4] - ld.ab r15, [sp, 4] - ld.ab r14, [sp, 4] - ld.ab r13, [sp, 4] + RESTORE_R24_TO_R13 .endm /*-------------------------------------------------------------- * Super FAST Restore callee saved regs by simply re-adjusting SP *-------------------------------------------------------------*/ .macro DISCARD_CALLEE_SAVED_USER - add sp, sp, 14 * 4 -.endm - -/*-------------------------------------------------------------- - * Restore User mode r25 saved in task_struct->thread.user_r25 - *-------------------------------------------------------------*/ -.macro RESTORE_USER_R25 - ld r25, [r25, TASK_THREAD + THREAD_USER_R25] + add sp, sp, SZ_CALLEE_REGS .endm /*------------------------------------------------------------- @@ -252,7 +235,7 @@ ld \out, [\tsk, TASK_THREAD_INFO] /* Go to end of page where stack begins (grows upwards) */ - add2 \out, \out, (THREAD_SIZE - 4)/4 /* one word GUTTER */ + add2 \out, \out, (THREAD_SIZE)/4 .endm @@ -305,33 +288,28 @@ * safe-keeping not really needed, but it keeps the epilogue code * (SP restore) simpler/uniform. */ - b.d 77f - - st.a sp, [sp, -12] ; Make room for orig_r0 and orig_r8 + b.d 66f + mov r9, sp 88: /*------Intr/Ecxp happened in user mode, "switch" stack ------ */ GET_CURR_TASK_ON_CPU r9 -#ifdef CONFIG_ARC_CURR_IN_REG - - /* If current task pointer cached in r25, time to - * -safekeep USER r25 in task->thread_struct->user_r25 - * -load r25 with current task ptr - */ - st.as r25, [r9, (TASK_THREAD + THREAD_USER_R25)/4] - mov r25, r9 -#endif - /* With current tsk in r9, get it's kernel mode stack base */ GET_TSK_STACK_BASE r9, r9 -#ifdef PT_REGS_CANARY - st 0xabcdabcd, [r9, 0] +66: +#ifdef CONFIG_ARC_CURR_IN_REG + /* + * Treat r25 as scratch reg, save it on stack first + * Load it with current task pointer + */ + st r25, [r9, -4] + GET_CURR_TASK_ON_CPU r25 #endif /* Save Pre Intr/Exception User SP on kernel stack */ - st.a sp, [r9, -12] ; Make room for orig_r0 and orig_r8 + st.a sp, [r9, -16] ; Make room for orig_r0, ECR, user_r25 /* CAUTION: * SP should be set at the very end when we are done with everything @@ -342,7 +320,7 @@ /* set SP to point to kernel mode stack */ mov sp, r9 -77: /* ----- Stack Switched to kernel Mode, Now save REG FILE ----- */ + /* ----- Stack Switched to kernel Mode, Now save REG FILE ----- */ .endm @@ -369,7 +347,7 @@ * @reg [OUT] &thread_info of "current" */ .macro GET_CURR_THR_INFO_FROM_SP reg - and \reg, sp, ~(THREAD_SIZE - 1) + bic \reg, sp, (THREAD_SIZE - 1) .endm /* @@ -413,62 +391,25 @@ * Note that syscalls are implemented via TRAP which is also a exception * from CPU's point of view *-------------------------------------------------------------*/ -.macro SAVE_ALL_EXCEPTION marker +.macro SAVE_ALL_SYS - st \marker, [sp, 8] /* orig_r8 */ + lr r9, [ecr] + st r9, [sp, 8] /* ECR */ st r0, [sp, 4] /* orig_r0, needed only for sys calls */ /* Restore r9 used to code the early prologue */ EXCPN_PROLOG_RESTORE_REG r9 - SAVE_CALLER_SAVED - st.a r26, [sp, -4] /* gp */ - st.a fp, [sp, -4] - st.a blink, [sp, -4] - lr r9, [eret] - st.a r9, [sp, -4] - lr r9, [erstatus] - st.a r9, [sp, -4] - st.a lp_count, [sp, -4] - lr r9, [lp_end] - st.a r9, [sp, -4] - lr r9, [lp_start] - st.a r9, [sp, -4] - lr r9, [erbta] - st.a r9, [sp, -4] - -#ifdef PT_REGS_CANARY - mov r9, 0xdeadbeef - st r9, [sp, -4] -#endif - - /* move up by 1 word to "create" pt_regs->"stack_place_holder" */ - sub sp, sp, 4 -.endm - -/*-------------------------------------------------------------- - * Save scratch regs for exceptions - *-------------------------------------------------------------*/ -.macro SAVE_ALL_SYS - SAVE_ALL_EXCEPTION orig_r8_IS_EXCPN -.endm - -/*-------------------------------------------------------------- - * Save scratch regs for sys calls - *-------------------------------------------------------------*/ -.macro SAVE_ALL_TRAP - /* - * Setup pt_regs->orig_r8. - * Encode syscall number (r8) in upper short word of event type (r9) - * N.B. #1: This is already endian safe (see ptrace.h) - * #2: Only r9 can be used as scratch as it is already clobbered - * and it's contents are no longer needed by the latter part - * of exception prologue - */ - lsl r9, r8, 16 - or r9, r9, orig_r8_IS_SCALL - - SAVE_ALL_EXCEPTION r9 + SAVE_R0_TO_R12 + PUSH gp + PUSH fp + PUSH blink + PUSHAX eret + PUSHAX erstatus + PUSH lp_count + PUSHAX lp_end + PUSHAX lp_start + PUSHAX erbta .endm /*-------------------------------------------------------------- @@ -483,28 +424,22 @@ * by hardware and that is not good. *-------------------------------------------------------------*/ .macro RESTORE_ALL_SYS + POPAX erbta + POPAX lp_start + POPAX lp_end + + POP r9 + mov lp_count, r9 ;LD to lp_count is not allowed - add sp, sp, 4 /* hop over unused "pt_regs->stack_place_holder" */ - - ld.ab r9, [sp, 4] - sr r9, [erbta] - ld.ab r9, [sp, 4] - sr r9, [lp_start] - ld.ab r9, [sp, 4] - sr r9, [lp_end] - ld.ab r9, [sp, 4] - mov lp_count, r9 - ld.ab r9, [sp, 4] - sr r9, [erstatus] - ld.ab r9, [sp, 4] - sr r9, [eret] - ld.ab blink, [sp, 4] - ld.ab fp, [sp, 4] - ld.ab r26, [sp, 4] /* gp */ - RESTORE_CALLER_SAVED + POPAX erstatus + POPAX eret + POP blink + POP fp + POP gp + RESTORE_R12_TO_R0 ld sp, [sp] /* restore original sp */ - /* orig_r0 and orig_r8 skipped automatically */ + /* orig_r0, ECR, user_r25 skipped automatically */ .endm @@ -513,9 +448,7 @@ *-------------------------------------------------------------*/ .macro SAVE_ALL_INT1 - /* restore original r9 , saved in int1_saved_reg - * It will be saved on stack in macro: SAVE_CALLER_SAVED - */ + /* restore original r9 to be saved as part of reg-file */ #ifdef CONFIG_SMP lr r9, [ARC_REG_SCRATCH_DATA0] #else @@ -523,29 +456,19 @@ #endif /* now we are ready to save the remaining context :) */ - st orig_r8_IS_IRQ1, [sp, 8] /* Event Type */ + st event_IRQ1, [sp, 8] /* Dummy ECR */ st 0, [sp, 4] /* orig_r0 , N/A for IRQ */ - SAVE_CALLER_SAVED - st.a r26, [sp, -4] /* gp */ - st.a fp, [sp, -4] - st.a blink, [sp, -4] - st.a ilink1, [sp, -4] - lr r9, [status32_l1] - st.a r9, [sp, -4] - st.a lp_count, [sp, -4] - lr r9, [lp_end] - st.a r9, [sp, -4] - lr r9, [lp_start] - st.a r9, [sp, -4] - lr r9, [bta_l1] - st.a r9, [sp, -4] - -#ifdef PT_REGS_CANARY - mov r9, 0xdeadbee1 - st r9, [sp, -4] -#endif - /* move up by 1 word to "create" pt_regs->"stack_place_holder" */ - sub sp, sp, 4 + + SAVE_R0_TO_R12 + PUSH gp + PUSH fp + PUSH blink + PUSH ilink1 + PUSHAX status32_l1 + PUSH lp_count + PUSHAX lp_end + PUSHAX lp_start + PUSHAX bta_l1 .endm .macro SAVE_ALL_INT2 @@ -558,30 +481,19 @@ ld r9, [@int2_saved_reg] /* now we are ready to save the remaining context :) */ - st orig_r8_IS_IRQ2, [sp, 8] /* Event Type */ + st event_IRQ2, [sp, 8] /* Dummy ECR */ st 0, [sp, 4] /* orig_r0 , N/A for IRQ */ - SAVE_CALLER_SAVED - st.a r26, [sp, -4] /* gp */ - st.a fp, [sp, -4] - st.a blink, [sp, -4] - st.a ilink2, [sp, -4] - lr r9, [status32_l2] - st.a r9, [sp, -4] - st.a lp_count, [sp, -4] - lr r9, [lp_end] - st.a r9, [sp, -4] - lr r9, [lp_start] - st.a r9, [sp, -4] - lr r9, [bta_l2] - st.a r9, [sp, -4] - -#ifdef PT_REGS_CANARY - mov r9, 0xdeadbee2 - st r9, [sp, -4] -#endif - /* move up by 1 word to "create" pt_regs->"stack_place_holder" */ - sub sp, sp, 4 + SAVE_R0_TO_R12 + PUSH gp + PUSH fp + PUSH blink + PUSH ilink2 + PUSHAX status32_l2 + PUSH lp_count + PUSHAX lp_end + PUSHAX lp_start + PUSHAX bta_l2 .endm /*-------------------------------------------------------------- @@ -595,52 +507,41 @@ *-------------------------------------------------------------*/ .macro RESTORE_ALL_INT1 - add sp, sp, 4 /* hop over unused "pt_regs->stack_place_holder" */ - - ld.ab r9, [sp, 4] /* Actual reg file */ - sr r9, [bta_l1] - ld.ab r9, [sp, 4] - sr r9, [lp_start] - ld.ab r9, [sp, 4] - sr r9, [lp_end] - ld.ab r9, [sp, 4] - mov lp_count, r9 - ld.ab r9, [sp, 4] - sr r9, [status32_l1] - ld.ab r9, [sp, 4] - mov ilink1, r9 - ld.ab blink, [sp, 4] - ld.ab fp, [sp, 4] - ld.ab r26, [sp, 4] /* gp */ - RESTORE_CALLER_SAVED + POPAX bta_l1 + POPAX lp_start + POPAX lp_end + + POP r9 + mov lp_count, r9 ;LD to lp_count is not allowed + + POPAX status32_l1 + POP ilink1 + POP blink + POP fp + POP gp + RESTORE_R12_TO_R0 ld sp, [sp] /* restore original sp */ - /* orig_r0 and orig_r8 skipped automatically */ + /* orig_r0, ECR, user_r25 skipped automatically */ .endm .macro RESTORE_ALL_INT2 - add sp, sp, 4 /* hop over unused "pt_regs->stack_place_holder" */ - - ld.ab r9, [sp, 4] - sr r9, [bta_l2] - ld.ab r9, [sp, 4] - sr r9, [lp_start] - ld.ab r9, [sp, 4] - sr r9, [lp_end] - ld.ab r9, [sp, 4] - mov lp_count, r9 - ld.ab r9, [sp, 4] - sr r9, [status32_l2] - ld.ab r9, [sp, 4] - mov ilink2, r9 - ld.ab blink, [sp, 4] - ld.ab fp, [sp, 4] - ld.ab r26, [sp, 4] /* gp */ - RESTORE_CALLER_SAVED + POPAX bta_l2 + POPAX lp_start + POPAX lp_end - ld sp, [sp] /* restore original sp */ - /* orig_r0 and orig_r8 skipped automatically */ + POP r9 + mov lp_count, r9 ;LD to lp_count is not allowed + POPAX status32_l2 + POP ilink2 + POP blink + POP fp + POP gp + RESTORE_R12_TO_R0 + + ld sp, [sp] /* restore original sp */ + /* orig_r0, ECR, user_r25 skipped automatically */ .endm diff --git a/arch/arc/include/asm/irq.h b/arch/arc/include/asm/irq.h index 57898a17eb82..c0a72105ee0b 100644 --- a/arch/arc/include/asm/irq.h +++ b/arch/arc/include/asm/irq.h @@ -21,6 +21,6 @@ extern void __init arc_init_IRQ(void); extern int __init get_hw_config_num_irq(void); -void __cpuinit arc_local_timer_setup(unsigned int cpu); +void arc_local_timer_setup(unsigned int cpu); #endif diff --git a/arch/arc/include/asm/irqflags.h b/arch/arc/include/asm/irqflags.h index eac071668201..d99f79bcf865 100644 --- a/arch/arc/include/asm/irqflags.h +++ b/arch/arc/include/asm/irqflags.h @@ -19,6 +19,26 @@ #include <asm/arcregs.h> +/* status32 Reg bits related to Interrupt Handling */ +#define STATUS_E1_BIT 1 /* Int 1 enable */ +#define STATUS_E2_BIT 2 /* Int 2 enable */ +#define STATUS_A1_BIT 3 /* Int 1 active */ +#define STATUS_A2_BIT 4 /* Int 2 active */ + +#define STATUS_E1_MASK (1<<STATUS_E1_BIT) +#define STATUS_E2_MASK (1<<STATUS_E2_BIT) +#define STATUS_A1_MASK (1<<STATUS_A1_BIT) +#define STATUS_A2_MASK (1<<STATUS_A2_BIT) + +/* Other Interrupt Handling related Aux regs */ +#define AUX_IRQ_LEV 0x200 /* IRQ Priority: L1 or L2 */ +#define AUX_IRQ_HINT 0x201 /* For generating Soft Interrupts */ +#define AUX_IRQ_LV12 0x43 /* interrupt level register */ + +#define AUX_IENABLE 0x40c +#define AUX_ITRIGGER 0x40d +#define AUX_IPULSE 0x415 + #ifndef __ASSEMBLY__ /****************************************************************** diff --git a/arch/arc/include/asm/kgdb.h b/arch/arc/include/asm/kgdb.h index 4930957ca3d3..b65fca7ffeb5 100644 --- a/arch/arc/include/asm/kgdb.h +++ b/arch/arc/include/asm/kgdb.h @@ -31,7 +31,7 @@ static inline void arch_kgdb_breakpoint(void) __asm__ __volatile__ ("trap_s 0x4\n"); } -extern void kgdb_trap(struct pt_regs *regs, int param); +extern void kgdb_trap(struct pt_regs *regs); enum arc700_linux_regnums { _R0 = 0, @@ -53,7 +53,7 @@ enum arc700_linux_regnums { }; #else -#define kgdb_trap(regs, param) +#define kgdb_trap(regs) #endif #endif /* __ARC_KGDB_H__ */ diff --git a/arch/arc/include/asm/kprobes.h b/arch/arc/include/asm/kprobes.h index 4d9c211fce70..944dbedb38b5 100644 --- a/arch/arc/include/asm/kprobes.h +++ b/arch/arc/include/asm/kprobes.h @@ -50,11 +50,9 @@ struct kprobe_ctlblk { int kprobe_fault_handler(struct pt_regs *regs, unsigned long cause); void kretprobe_trampoline(void); -void trap_is_kprobe(unsigned long cause, unsigned long address, - struct pt_regs *regs); +void trap_is_kprobe(unsigned long address, struct pt_regs *regs); #else -static void trap_is_kprobe(unsigned long cause, unsigned long address, - struct pt_regs *regs) +static void trap_is_kprobe(unsigned long address, struct pt_regs *regs) { } #endif diff --git a/arch/arc/include/asm/mmu.h b/arch/arc/include/asm/mmu.h index 56b02320f1a9..7c03fe61759c 100644 --- a/arch/arc/include/asm/mmu.h +++ b/arch/arc/include/asm/mmu.h @@ -9,6 +9,40 @@ #ifndef _ASM_ARC_MMU_H #define _ASM_ARC_MMU_H +#if defined(CONFIG_ARC_MMU_V1) +#define CONFIG_ARC_MMU_VER 1 +#elif defined(CONFIG_ARC_MMU_V2) +#define CONFIG_ARC_MMU_VER 2 +#elif defined(CONFIG_ARC_MMU_V3) +#define CONFIG_ARC_MMU_VER 3 +#endif + +/* MMU Management regs */ +#define ARC_REG_MMU_BCR 0x06f +#define ARC_REG_TLBPD0 0x405 +#define ARC_REG_TLBPD1 0x406 +#define ARC_REG_TLBINDEX 0x407 +#define ARC_REG_TLBCOMMAND 0x408 +#define ARC_REG_PID 0x409 +#define ARC_REG_SCRATCH_DATA0 0x418 + +/* Bits in MMU PID register */ +#define MMU_ENABLE (1 << 31) /* Enable MMU for process */ + +/* Error code if probe fails */ +#define TLB_LKUP_ERR 0x80000000 + +/* TLB Commands */ +#define TLBWrite 0x1 +#define TLBRead 0x2 +#define TLBGetIndex 0x3 +#define TLBProbe 0x4 + +#if (CONFIG_ARC_MMU_VER >= 2) +#define TLBWriteNI 0x5 /* write JTLB without inv uTLBs */ +#define TLBIVUTLB 0x6 /* explicitly inv uTLBs */ +#endif + #ifndef __ASSEMBLY__ typedef struct { @@ -18,6 +52,16 @@ typedef struct { #endif } mm_context_t; +#ifdef CONFIG_ARC_DBG_TLB_PARANOIA +void tlb_paranoid_check(unsigned int pid_sw, unsigned long address); +#else +#define tlb_paranoid_check(a, b) #endif +void arc_mmu_init(void); +extern char *arc_mmu_mumbojumbo(int cpu_id, char *buf, int len); +void __init read_decode_mmu_bcr(void); + +#endif /* !__ASSEMBLY__ */ + #endif diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h index ab84bf131fe1..9c8aa41e45c2 100644 --- a/arch/arc/include/asm/page.h +++ b/arch/arc/include/asm/page.h @@ -96,13 +96,8 @@ typedef unsigned long pgtable_t; #define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT) -/* Default Permissions for page, used in mmap.c */ -#ifdef CONFIG_ARC_STACK_NONEXEC +/* Default Permissions for stack/heaps pages (Non Executable) */ #define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE) -#else -#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_EXEC | \ - VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) -#endif #define WANT_PAGE_VIRTUAL 1 diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index c110ac87d22b..4749a0eee1cf 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -135,6 +135,12 @@ /* ioremap */ #define PAGE_KERNEL_NO_CACHE __pgprot(_K_PAGE_PERMS) +/* Masks for actual TLB "PD"s */ +#define PTE_BITS_IN_PD0 (_PAGE_GLOBAL | _PAGE_PRESENT) +#define PTE_BITS_IN_PD1 (PAGE_MASK | _PAGE_CACHEABLE | \ + _PAGE_U_EXECUTE | _PAGE_U_WRITE | _PAGE_U_READ | \ + _PAGE_K_EXECUTE | _PAGE_K_WRITE | _PAGE_K_READ) + /************************************************************************** * Mapping of vm_flags (Generic VM) to PTE flags (arch specific) * diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h index 5f26b2c1cba0..15334ab66b56 100644 --- a/arch/arc/include/asm/processor.h +++ b/arch/arc/include/asm/processor.h @@ -19,6 +19,7 @@ #ifndef __ASSEMBLY__ #include <asm/arcregs.h> /* for STATUS_E1_MASK et all */ +#include <asm/ptrace.h> /* Arch specific stuff which needs to be saved per task. * However these items are not so important so as to earn a place in @@ -28,10 +29,6 @@ struct thread_struct { unsigned long ksp; /* kernel mode stack pointer */ unsigned long callee_reg; /* pointer to callee regs */ unsigned long fault_address; /* dbls as brkpt holder as well */ - unsigned long cause_code; /* Exception Cause Code (ECR) */ -#ifdef CONFIG_ARC_CURR_IN_REG - unsigned long user_r25; -#endif #ifdef CONFIG_ARC_FPU_SAVE_RESTORE struct arc_fpu fpu; #endif @@ -50,7 +47,7 @@ struct task_struct; unsigned long thread_saved_pc(struct task_struct *t); #define task_pt_regs(p) \ - ((struct pt_regs *)(THREAD_SIZE - 4 + (void *)task_stack_page(p)) - 1) + ((struct pt_regs *)(THREAD_SIZE + (void *)task_stack_page(p)) - 1) /* Free all resources held by a thread. */ #define release_thread(thread) do { } while (0) @@ -75,11 +72,15 @@ unsigned long thread_saved_pc(struct task_struct *t); /* * Where abouts of Task's sp, fp, blink when it was last seen in kernel mode. - * These can't be derived from pt_regs as that would give correp user-mode val + * Look in process.c for details of kernel stack layout */ #define KSTK_ESP(tsk) (tsk->thread.ksp) -#define KSTK_BLINK(tsk) (*((unsigned int *)((KSTK_ESP(tsk)) + (13+1+1)*4))) -#define KSTK_FP(tsk) (*((unsigned int *)((KSTK_ESP(tsk)) + (13+1)*4))) + +#define KSTK_REG(tsk, off) (*((unsigned int *)(KSTK_ESP(tsk) + \ + sizeof(struct callee_regs) + off))) + +#define KSTK_BLINK(tsk) KSTK_REG(tsk, 4) +#define KSTK_FP(tsk) KSTK_REG(tsk, 0) /* * Do necessary setup to start up a newly executed thread. diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h index 6179de7e07c2..c9938e7a7dbd 100644 --- a/arch/arc/include/asm/ptrace.h +++ b/arch/arc/include/asm/ptrace.h @@ -17,12 +17,6 @@ /* THE pt_regs: Defines how regs are saved during entry into kernel */ struct pt_regs { - /* - * 1 word gutter after reg-file has been saved - * Technically not needed, Since SP always points to a "full" location - * (vs. "empty"). But pt_regs is shared with tools.... - */ - long res; /* Real registers */ long bta; /* bta_l1, bta_l2, erbta */ @@ -50,22 +44,32 @@ struct pt_regs { long sp; /* user/kernel sp depending on where we came from */ long orig_r0; - /*to distinguish bet excp, syscall, irq */ + /* + * To distinguish bet excp, syscall, irq + * For traps and exceptions, Exception Cause Register. + * ECR: <00> <VV> <CC> <PP> + * Last word used by Linux for extra state mgmt (syscall-restart) + * For interrupts, use artificial ECR values to note current prio-level + */ union { + struct { #ifdef CONFIG_CPU_BIG_ENDIAN - /* so that assembly code is same for LE/BE */ - unsigned long orig_r8:16, event:16; + unsigned long state:8, ecr_vec:8, + ecr_cause:8, ecr_param:8; #else - unsigned long event:16, orig_r8:16; + unsigned long ecr_param:8, ecr_cause:8, + ecr_vec:8, state:8; #endif - long orig_r8_word; + }; + unsigned long event; }; + + long user_r25; }; /* Callee saved registers - need to be saved only when you are scheduled out */ struct callee_regs { - long res; /* Again this is not needed */ long r25; long r24; long r23; @@ -99,18 +103,20 @@ struct callee_regs { /* return 1 if PC in delay slot */ #define delay_mode(regs) ((regs->status32 & STATUS_DE_MASK) == STATUS_DE_MASK) -#define in_syscall(regs) (regs->event & orig_r8_IS_SCALL) -#define in_brkpt_trap(regs) (regs->event & orig_r8_IS_BRKPT) +#define in_syscall(regs) ((regs->ecr_vec == ECR_V_TRAP) && !regs->ecr_param) +#define in_brkpt_trap(regs) ((regs->ecr_vec == ECR_V_TRAP) && regs->ecr_param) + +#define STATE_SCALL_RESTARTED 0x01 -#define syscall_wont_restart(regs) (regs->event |= orig_r8_IS_SCALL_RESTARTED) -#define syscall_restartable(regs) !(regs->event & orig_r8_IS_SCALL_RESTARTED) +#define syscall_wont_restart(reg) (reg->state |= STATE_SCALL_RESTARTED) +#define syscall_restartable(reg) !(reg->state & STATE_SCALL_RESTARTED) #define current_pt_regs() \ ({ \ /* open-coded current_thread_info() */ \ register unsigned long sp asm ("sp"); \ unsigned long pg_start = (sp & ~(THREAD_SIZE - 1)); \ - (struct pt_regs *)(pg_start + THREAD_SIZE - 4) - 1; \ + (struct pt_regs *)(pg_start + THREAD_SIZE) - 1; \ }) static inline long regs_return_value(struct pt_regs *regs) @@ -120,11 +126,4 @@ static inline long regs_return_value(struct pt_regs *regs) #endif /* !__ASSEMBLY__ */ -#define orig_r8_IS_SCALL 0x0001 -#define orig_r8_IS_SCALL_RESTARTED 0x0002 -#define orig_r8_IS_BRKPT 0x0004 -#define orig_r8_IS_EXCPN 0x0008 -#define orig_r8_IS_IRQ1 0x0010 -#define orig_r8_IS_IRQ2 0x0020 - #endif /* __ASM_PTRACE_H */ diff --git a/arch/arc/include/asm/syscall.h b/arch/arc/include/asm/syscall.h index 33ab3048e9b2..29de09804306 100644 --- a/arch/arc/include/asm/syscall.h +++ b/arch/arc/include/asm/syscall.h @@ -18,7 +18,7 @@ static inline long syscall_get_nr(struct task_struct *task, struct pt_regs *regs) { if (user_mode(regs) && in_syscall(regs)) - return regs->orig_r8; + return regs->r8; else return -1; } @@ -26,8 +26,7 @@ syscall_get_nr(struct task_struct *task, struct pt_regs *regs) static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { - /* XXX: I can't fathom how pt_regs->r8 will be clobbered ? */ - regs->r8 = regs->orig_r8; + regs->r0 = regs->orig_r0; } static inline long diff --git a/arch/arc/include/asm/tlb-mmu1.h b/arch/arc/include/asm/tlb-mmu1.h index a5ff961b1efc..8a1ec96012ae 100644 --- a/arch/arc/include/asm/tlb-mmu1.h +++ b/arch/arc/include/asm/tlb-mmu1.h @@ -9,9 +9,9 @@ #ifndef __ASM_TLB_MMU_V1_H__ #define __ASM_TLB_MMU_V1_H__ -#if defined(__ASSEMBLY__) && defined(CONFIG_ARC_MMU_VER == 1) +#include <asm/mmu.h> -#include <asm/tlb.h> +#if defined(__ASSEMBLY__) && (CONFIG_ARC_MMU_VER == 1) .macro TLB_WRITE_HEURISTICS diff --git a/arch/arc/include/asm/tlb.h b/arch/arc/include/asm/tlb.h index cb0c708ca665..a9db5f62aaf3 100644 --- a/arch/arc/include/asm/tlb.h +++ b/arch/arc/include/asm/tlb.h @@ -9,18 +9,6 @@ #ifndef _ASM_ARC_TLB_H #define _ASM_ARC_TLB_H -#ifdef __KERNEL__ - -#include <asm/pgtable.h> - -/* Masks for actual TLB "PD"s */ -#define PTE_BITS_IN_PD0 (_PAGE_GLOBAL | _PAGE_PRESENT) -#define PTE_BITS_IN_PD1 (PAGE_MASK | _PAGE_CACHEABLE | \ - _PAGE_U_EXECUTE | _PAGE_U_WRITE | _PAGE_U_READ | \ - _PAGE_K_EXECUTE | _PAGE_K_WRITE | _PAGE_K_READ) - -#ifndef __ASSEMBLY__ - #define tlb_flush(tlb) \ do { \ if (tlb->fullmm) \ @@ -56,18 +44,4 @@ do { \ #include <linux/pagemap.h> #include <asm-generic/tlb.h> -#ifdef CONFIG_ARC_DBG_TLB_PARANOIA -void tlb_paranoid_check(unsigned int pid_sw, unsigned long address); -#else -#define tlb_paranoid_check(a, b) -#endif - -void arc_mmu_init(void); -extern char *arc_mmu_mumbojumbo(int cpu_id, char *buf, int len); -void __init read_decode_mmu_bcr(void); - -#endif /* __ASSEMBLY__ */ - -#endif /* __KERNEL__ */ - #endif /* _ASM_ARC_TLB_H */ diff --git a/arch/arc/include/asm/unaligned.h b/arch/arc/include/asm/unaligned.h index 5dbe63f17b66..60702f3751d2 100644 --- a/arch/arc/include/asm/unaligned.h +++ b/arch/arc/include/asm/unaligned.h @@ -16,11 +16,11 @@ #ifdef CONFIG_ARC_MISALIGN_ACCESS int misaligned_fixup(unsigned long address, struct pt_regs *regs, - unsigned long cause, struct callee_regs *cregs); + struct callee_regs *cregs); #else static inline int misaligned_fixup(unsigned long address, struct pt_regs *regs, - unsigned long cause, struct callee_regs *cregs) + struct callee_regs *cregs) { return 0; } diff --git a/arch/arc/include/uapi/asm/ptrace.h b/arch/arc/include/uapi/asm/ptrace.h index 30333cec0fef..2618cc13ba75 100644 --- a/arch/arc/include/uapi/asm/ptrace.h +++ b/arch/arc/include/uapi/asm/ptrace.h @@ -20,28 +20,31 @@ * * This is to decouple pt_regs from user-space ABI, to be able to change it * w/o affecting the ABI. - * Although the layout (initial padding) is similar to pt_regs to have some - * optimizations when copying pt_regs to/from user_regs_struct. + * + * The intermediate pad,pad2 are relics of initial layout based on pt_regs + * for optimizations when copying pt_regs to/from user_regs_struct. + * We no longer need them, but can't be changed as they are part of ABI now. * * Also, sigcontext only care about the scratch regs as that is what we really - * save/restore for signal handling. + * save/restore for signal handling. However gdb also uses the same struct + * hence callee regs need to be in there too. */ struct user_regs_struct { + long pad; struct { - long pad; long bta, lp_start, lp_end, lp_count; long status32, ret, blink, fp, gp; long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0; long sp; } scratch; + long pad2; struct { - long pad; long r25, r24, r23, r22, r21, r20; long r19, r18, r17, r16, r15, r14, r13; } callee; long efa; /* break pt addr, for break points in delay slots */ - long stop_pc; /* give dbg stop_pc directly after checking orig_r8 */ + long stop_pc; /* give dbg stop_pc after ensuring brkpt trap */ }; #endif /* !__ASSEMBLY__ */ diff --git a/arch/arc/kernel/asm-offsets.c b/arch/arc/kernel/asm-offsets.c index 7dcda7025241..6c3aa0edb9b5 100644 --- a/arch/arc/kernel/asm-offsets.c +++ b/arch/arc/kernel/asm-offsets.c @@ -24,9 +24,6 @@ int main(void) DEFINE(THREAD_KSP, offsetof(struct thread_struct, ksp)); DEFINE(THREAD_CALLEE_REG, offsetof(struct thread_struct, callee_reg)); -#ifdef CONFIG_ARC_CURR_IN_REG - DEFINE(THREAD_USER_R25, offsetof(struct thread_struct, user_r25)); -#endif DEFINE(THREAD_FAULT_ADDR, offsetof(struct thread_struct, fault_address)); @@ -49,7 +46,7 @@ int main(void) BLANK(); DEFINE(PT_status32, offsetof(struct pt_regs, status32)); - DEFINE(PT_orig_r8, offsetof(struct pt_regs, orig_r8_word)); + DEFINE(PT_event, offsetof(struct pt_regs, event)); DEFINE(PT_sp, offsetof(struct pt_regs, sp)); DEFINE(PT_r0, offsetof(struct pt_regs, r0)); DEFINE(PT_r1, offsetof(struct pt_regs, r1)); @@ -60,5 +57,7 @@ int main(void) DEFINE(PT_r6, offsetof(struct pt_regs, r6)); DEFINE(PT_r7, offsetof(struct pt_regs, r7)); + DEFINE(SZ_CALLEE_REGS, sizeof(struct callee_regs)); + DEFINE(SZ_PT_REGS, sizeof(struct pt_regs)); return 0; } diff --git a/arch/arc/kernel/ctx_sw.c b/arch/arc/kernel/ctx_sw.c index 60844dac6132..34410eb1a308 100644 --- a/arch/arc/kernel/ctx_sw.c +++ b/arch/arc/kernel/ctx_sw.c @@ -23,10 +23,6 @@ __switch_to(struct task_struct *prev_task, struct task_struct *next_task) unsigned int tmp; unsigned int prev = (unsigned int)prev_task; unsigned int next = (unsigned int)next_task; - int num_words_to_skip = 1; -#ifdef CONFIG_ARC_CURR_IN_REG - num_words_to_skip++; -#endif __asm__ __volatile__( /* FP/BLINK save generated by gcc (standard function prologue */ @@ -44,8 +40,9 @@ __switch_to(struct task_struct *prev_task, struct task_struct *next_task) "st.a r24, [sp, -4] \n\t" #ifndef CONFIG_ARC_CURR_IN_REG "st.a r25, [sp, -4] \n\t" +#else + "sub sp, sp, 4 \n\t" /* usual r25 placeholder */ #endif - "sub sp, sp, %4 \n\t" /* create gutter at top */ /* set ksp of outgoing task in tsk->thread.ksp */ "st.as sp, [%3, %1] \n\t" @@ -76,10 +73,10 @@ __switch_to(struct task_struct *prev_task, struct task_struct *next_task) /* start loading it's CALLEE reg file */ - "add sp, sp, %4 \n\t" /* skip gutter at top */ - #ifndef CONFIG_ARC_CURR_IN_REG "ld.ab r25, [sp, 4] \n\t" +#else + "add sp, sp, 4 \n\t" #endif "ld.ab r24, [sp, 4] \n\t" "ld.ab r23, [sp, 4] \n\t" @@ -100,8 +97,7 @@ __switch_to(struct task_struct *prev_task, struct task_struct *next_task) /* FP/BLINK restore generated by gcc (standard func epilogue */ : "=r"(tmp) - : "n"((TASK_THREAD + THREAD_KSP) / 4), "r"(next), "r"(prev), - "n"(num_words_to_skip * 4) + : "n"((TASK_THREAD + THREAD_KSP) / 4), "r"(next), "r"(prev) : "blink" ); diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index 0c6d664d4a83..1d7165156e17 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -142,7 +142,7 @@ VECTOR reserved ; Reserved Exceptions .endr #include <linux/linkage.h> /* ARC_{EXTRY,EXIT} */ -#include <asm/entry.h> /* SAVE_ALL_{INT1,INT2,TRAP...} */ +#include <asm/entry.h> /* SAVE_ALL_{INT1,INT2,SYS...} */ #include <asm/errno.h> #include <asm/arcregs.h> #include <asm/irqflags.h> @@ -274,10 +274,8 @@ ARC_ENTRY instr_service SWITCH_TO_KERNEL_STK SAVE_ALL_SYS - lr r0, [ecr] - lr r1, [efa] - - mov r2, sp + lr r0, [efa] + mov r1, sp FAKE_RET_FROM_EXCPN r9 @@ -298,9 +296,8 @@ ARC_ENTRY mem_service SWITCH_TO_KERNEL_STK SAVE_ALL_SYS - lr r0, [ecr] - lr r1, [efa] - mov r2, sp + lr r0, [efa] + mov r1, sp bl do_memory_error b ret_from_exception ARC_EXIT mem_service @@ -317,11 +314,14 @@ ARC_ENTRY EV_MachineCheck SWITCH_TO_KERNEL_STK SAVE_ALL_SYS - lr r0, [ecr] - lr r1, [efa] - mov r2, sp + lr r2, [ecr] + lr r0, [efa] + mov r1, sp + + lsr r3, r2, 8 + bmsk r3, r3, 7 + brne r3, ECR_C_MCHK_DUP_TLB, 1f - brne r0, 0x200100, 1f bl do_tlb_overlap_fault b ret_from_exception @@ -355,8 +355,8 @@ ARC_ENTRY EV_TLBProtV ; ecr and efa were not saved in case an Intr sneaks in ; after fake rtie ; - lr r3, [ecr] - lr r4, [efa] + lr r2, [ecr] + lr r1, [efa] ; Faulting Data address ; --------(4) Return from CPU Exception Mode --------- ; Fake a rtie, but rtie to next label @@ -368,31 +368,25 @@ ARC_ENTRY EV_TLBProtV ;------ (5) Type of Protection Violation? ---------- ; ; ProtV Hardware Exception is triggered for Access Faults of 2 types - ; -Access Violaton (WRITE to READ ONLY Page) - for linux COW - ; -Unaligned Access (READ/WRITE on odd boundary) + ; -Access Violaton : 00_23_(00|01|02|03)_00 + ; x r w r+w + ; -Unaligned Access : 00_23_04_00 ; - cmp r3, 0x230400 ; Misaligned data access ? - beq 4f + bbit1 r2, ECR_C_BIT_PROTV_MISALIG_DATA, 4f ;========= (6a) Access Violation Processing ======== - cmp r3, 0x230100 - mov r1, 0x0 ; if LD exception ? write = 0 - mov.ne r1, 0x1 ; else write = 1 - - mov r2, r4 ; faulting address mov r0, sp ; pt_regs bl do_page_fault b ret_from_exception ;========== (6b) Non aligned access ============ 4: - mov r0, r3 ; cause code - mov r1, r4 ; faulting address - mov r2, sp ; pt_regs + mov r0, r1 + mov r1, sp ; pt_regs #ifdef CONFIG_ARC_MISALIGN_ACCESS SAVE_CALLEE_SAVED_USER - mov r3, sp ; callee_regs + mov r2, sp ; callee_regs bl do_misaligned_access @@ -419,9 +413,8 @@ ARC_ENTRY EV_PrivilegeV SWITCH_TO_KERNEL_STK SAVE_ALL_SYS - lr r0, [ecr] - lr r1, [efa] - mov r2, sp + lr r0, [efa] + mov r1, sp FAKE_RET_FROM_EXCPN r9 @@ -440,9 +433,8 @@ ARC_ENTRY EV_Extension SWITCH_TO_KERNEL_STK SAVE_ALL_SYS - lr r0, [ecr] - lr r1, [efa] - mov r2, sp + lr r0, [efa] + mov r1, sp bl do_extension_fault b ret_from_exception ARC_EXIT EV_Extension @@ -498,11 +490,8 @@ tracesys_exit: trap_with_param: ; stop_pc info by gdb needs this info - stw orig_r8_IS_BRKPT, [sp, PT_orig_r8] - - mov r0, r12 - lr r1, [efa] - mov r2, sp + lr r0, [efa] + mov r1, sp ; Now that we have read EFA, its safe to do "fake" rtie ; and get out of CPU exception mode @@ -544,11 +533,11 @@ ARC_ENTRY EV_Trap lr r9, [erstatus] SWITCH_TO_KERNEL_STK - SAVE_ALL_TRAP + SAVE_ALL_SYS ;------- (4) What caused the Trap -------------- lr r12, [ecr] - and.f 0, r12, ECR_PARAM_MASK + bmsk.f 0, r12, 7 bnz trap_with_param ; ======= (5a) Trap is due to System Call ======== @@ -589,11 +578,7 @@ ARC_ENTRY ret_from_exception ; Pre-{IRQ,Trap,Exception} K/U mode from pt_regs->status32 ld r8, [sp, PT_status32] ; returning to User/Kernel Mode -#ifdef CONFIG_PREEMPT bbit0 r8, STATUS_U_BIT, resume_kernel_mode -#else - bbit0 r8, STATUS_U_BIT, restore_regs -#endif ; Before returning to User mode check-for-and-complete any pending work ; such as rescheduling/signal-delivery etc. @@ -653,10 +638,10 @@ resume_user_mode_begin: b resume_user_mode_begin ; unconditionally back to U mode ret chks ; for single exit point from this block -#ifdef CONFIG_PREEMPT - resume_kernel_mode: +#ifdef CONFIG_PREEMPT + ; Can't preempt if preemption disabled GET_CURR_THR_INFO_FROM_SP r10 ld r8, [r10, THREAD_INFO_PREEMPT_COUNT] @@ -687,17 +672,6 @@ restore_regs : ; XXX can this be optimised out IRQ_DISABLE_SAVE r9, r10 ;@r10 has prisitine (pre-disable) copy -#ifdef CONFIG_ARC_CURR_IN_REG - ; Restore User R25 - ; Earlier this used to be only for returning to user mode - ; However with 2 levels of IRQ this can also happen even if - ; in kernel mode - ld r9, [sp, PT_sp] - brhs r9, VMALLOC_START, 8f - RESTORE_USER_R25 -8: -#endif - ; Restore REG File. In case multiple Events outstanding, ; use the same priorty as rtie: EXCPN, L2 IRQ, L1 IRQ, None ; Note that we use realtime STATUS32 (not pt_regs->status32) to @@ -714,28 +688,33 @@ not_exception: #ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS + ; Level 2 interrupt return Path - from hardware standpoint bbit0 r10, STATUS_A2_BIT, not_level2_interrupt ;------------------------------------------------------------------ + ; However the context returning might not have taken L2 intr itself + ; e.g. Task'A' user-code -> L2 intr -> schedule -> 'B' user-code ret + ; Special considerations needed for the context which took L2 intr + + ld r9, [sp, PT_event] ; Ensure this is L2 intr context + brne r9, event_IRQ2, 149f + + ;------------------------------------------------------------------ ; if L2 IRQ interrupted a L1 ISR, we'd disbaled preemption earlier ; so that sched doesnt move to new task, causing L1 to be delayed ; undeterministically. Now that we've achieved that, lets reset ; things to what they were, before returning from L2 context ;---------------------------------------------------------------- - ldw r9, [sp, PT_orig_r8] ; get orig_r8 to make sure it is - brne r9, orig_r8_IS_IRQ2, 149f ; infact a L2 ISR ret path - ld r9, [sp, PT_status32] ; get statu32_l2 (saved in pt_regs) bbit0 r9, STATUS_A1_BIT, 149f ; L1 not active when L2 IRQ, so normal - ; A1 is set in status32_l2 ; decrement thread_info->preempt_count (re-enable preemption) GET_CURR_THR_INFO_FROM_SP r10 ld r9, [r10, THREAD_INFO_PREEMPT_COUNT] ; paranoid check, given A1 was active when A2 happened, preempt count - ; must not be 0 beccause we would have incremented it. + ; must not be 0 because we would have incremented it. ; If this does happen we simply HALT as it means a BUG !!! cmp r9, 0 bnz 2f diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S index 006dec3fc353..2a913f85a747 100644 --- a/arch/arc/kernel/head.S +++ b/arch/arc/kernel/head.S @@ -27,6 +27,8 @@ stext: ; Don't clobber r0-r4 yet. It might have bootloader provided info ;------------------------------------------------------------------- + sr @_int_vec_base_lds, [AUX_INTR_VEC_BASE] + #ifdef CONFIG_SMP ; Only Boot (Master) proceeds. Others wait in platform dependent way ; IDENTITY Reg [ 3 2 1 0 ] diff --git a/arch/arc/kernel/irq.c b/arch/arc/kernel/irq.c index 8115fa531575..305b3f866aa7 100644 --- a/arch/arc/kernel/irq.c +++ b/arch/arc/kernel/irq.c @@ -28,25 +28,17 @@ * -Disable all IRQs (on CPU side) * -Optionally, setup the High priority Interrupts as Level 2 IRQs */ -void __cpuinit arc_init_IRQ(void) +void arc_init_IRQ(void) { int level_mask = 0; - write_aux_reg(AUX_INTR_VEC_BASE, _int_vec_base_lds); - /* Disable all IRQs: enable them as devices request */ write_aux_reg(AUX_IENABLE, 0); /* setup any high priority Interrupts (Level2 in ARCompact jargon) */ -#ifdef CONFIG_ARC_IRQ3_LV2 - level_mask |= (1 << 3); -#endif -#ifdef CONFIG_ARC_IRQ5_LV2 - level_mask |= (1 << 5); -#endif -#ifdef CONFIG_ARC_IRQ6_LV2 - level_mask |= (1 << 6); -#endif + level_mask |= IS_ENABLED(CONFIG_ARC_IRQ3_LV2) << 3; + level_mask |= IS_ENABLED(CONFIG_ARC_IRQ5_LV2) << 5; + level_mask |= IS_ENABLED(CONFIG_ARC_IRQ6_LV2) << 6; if (level_mask) { pr_info("Level-2 interrupts bitset %x\n", level_mask); diff --git a/arch/arc/kernel/kgdb.c b/arch/arc/kernel/kgdb.c index 52bdc83c1495..a7698fb14818 100644 --- a/arch/arc/kernel/kgdb.c +++ b/arch/arc/kernel/kgdb.c @@ -169,7 +169,7 @@ int kgdb_arch_init(void) return 0; } -void kgdb_trap(struct pt_regs *regs, int param) +void kgdb_trap(struct pt_regs *regs) { /* trap_s 3 is used for breakpoints that overwrite existing * instructions, while trap_s 4 is used for compiled breakpoints. @@ -181,7 +181,7 @@ void kgdb_trap(struct pt_regs *regs, int param) * with trap_s 4 (compiled) breakpoints, continuation needs to * start after the breakpoint. */ - if (param == 3) + if (regs->ecr_param == 3) instruction_pointer(regs) -= BREAK_INSTR_SIZE; kgdb_handle_exception(1, SIGTRAP, 0, regs); diff --git a/arch/arc/kernel/kprobes.c b/arch/arc/kernel/kprobes.c index 5a7b80e2d883..72f97822784a 100644 --- a/arch/arc/kernel/kprobes.c +++ b/arch/arc/kernel/kprobes.c @@ -517,8 +517,7 @@ int __kprobes arch_trampoline_kprobe(struct kprobe *p) return 0; } -void trap_is_kprobe(unsigned long cause, unsigned long address, - struct pt_regs *regs) +void trap_is_kprobe(unsigned long address, struct pt_regs *regs) { - notify_die(DIE_TRAP, "kprobe_trap", regs, address, cause, SIGTRAP); + notify_die(DIE_TRAP, "kprobe_trap", regs, address, 0, SIGTRAP); } diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index cad66851e0c4..07a3a968fe49 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -55,10 +55,8 @@ asmlinkage void ret_from_fork(void); * | ... | * | unused | * | | - * ------------------ <==== top of Stack (thread.ksp) - * | UNUSED 1 word| * ------------------ - * | r25 | + * | r25 | <==== top of Stack (thread.ksp) * ~ ~ * | --to-- | (CALLEE Regs of user mode) * | r13 | @@ -76,7 +74,10 @@ asmlinkage void ret_from_fork(void); * | --to-- | (scratch Regs of user mode) * | r0 | * ------------------ - * | UNUSED 1 word| + * | SP | + * | orig_r0 | + * | event/ECR | + * | user_r25 | * ------------------ <===== END of PAGE */ int copy_thread(unsigned long clone_flags, diff --git a/arch/arc/kernel/ptrace.c b/arch/arc/kernel/ptrace.c index c6a81c58d0f3..333238564b67 100644 --- a/arch/arc/kernel/ptrace.c +++ b/arch/arc/kernel/ptrace.c @@ -40,7 +40,15 @@ static int genregs_get(struct task_struct *target, offsetof(struct user_regs_struct, LOC), \ offsetof(struct user_regs_struct, LOC) + 4); +#define REG_O_ZERO(LOC) \ + if (!ret) \ + ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf, \ + offsetof(struct user_regs_struct, LOC), \ + offsetof(struct user_regs_struct, LOC) + 4); + + REG_O_ZERO(pad); REG_O_CHUNK(scratch, callee, ptregs); + REG_O_ZERO(pad2); REG_O_CHUNK(callee, efa, cregs); REG_O_CHUNK(efa, stop_pc, &target->thread.fault_address); @@ -88,8 +96,10 @@ static int genregs_set(struct task_struct *target, offsetof(struct user_regs_struct, LOC), \ offsetof(struct user_regs_struct, LOC) + 4); - /* TBD: disallow updates to STATUS32, orig_r8 etc*/ - REG_IN_CHUNK(scratch, callee, ptregs); /* pt_regs[bta..orig_r8] */ + REG_IGNORE_ONE(pad); + /* TBD: disallow updates to STATUS32 etc*/ + REG_IN_CHUNK(scratch, pad2, ptregs); /* pt_regs[bta..sp] */ + REG_IGNORE_ONE(pad2); REG_IN_CHUNK(callee, efa, cregs); /* callee_regs[r25..r13] */ REG_IGNORE_ONE(efa); /* efa update invalid */ REG_IN_ONE(stop_pc, &ptregs->ret); /* stop_pc: PC update */ diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index b2b3731dd1e9..6b083454d039 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -31,14 +31,14 @@ int running_on_hw = 1; /* vs. on ISS */ char __initdata command_line[COMMAND_LINE_SIZE]; -struct machine_desc *machine_desc __cpuinitdata; +struct machine_desc *machine_desc; struct task_struct *_current_task[NR_CPUS]; /* For stack switching */ struct cpuinfo_arc cpuinfo_arc700[NR_CPUS]; -void __cpuinit read_arc_build_cfg_regs(void) +void read_arc_build_cfg_regs(void) { struct bcr_perip uncached_space; struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()]; @@ -182,7 +182,7 @@ char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len) FIX_PTR(cpu); #define IS_AVAIL1(var, str) ((var) ? str : "") #define IS_AVAIL2(var, str) ((var == 0x2) ? str : "") -#define IS_USED(var) ((var) ? "(in-use)" : "(not used)") +#define IS_USED(cfg) (IS_ENABLED(cfg) ? "(in-use)" : "(not used)") n += scnprintf(buf + n, len - n, "Extn [700-Base]\t: %s %s %s %s %s %s\n", @@ -202,9 +202,9 @@ char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len) if (cpu->core.family == 0x34) { n += scnprintf(buf + n, len - n, "Extn [700-4.10]\t: LLOCK/SCOND %s, SWAPE %s, RTSC %s\n", - IS_USED(__CONFIG_ARC_HAS_LLSC_VAL), - IS_USED(__CONFIG_ARC_HAS_SWAPE_VAL), - IS_USED(__CONFIG_ARC_HAS_RTSC_VAL)); + IS_USED(CONFIG_ARC_HAS_LLSC), + IS_USED(CONFIG_ARC_HAS_SWAPE), + IS_USED(CONFIG_ARC_HAS_RTSC)); } n += scnprintf(buf + n, len - n, "Extn [CCM]\t: %s", @@ -237,7 +237,7 @@ char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len) return buf; } -void __cpuinit arc_chk_ccms(void) +void arc_chk_ccms(void) { #if defined(CONFIG_ARC_HAS_DCCM) || defined(CONFIG_ARC_HAS_ICCM) struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()]; @@ -272,7 +272,7 @@ void __cpuinit arc_chk_ccms(void) * hardware has dedicated regs which need to be saved/restored on ctx-sw * (Single Precision uses core regs), thus kernel is kind of oblivious to it */ -void __cpuinit arc_chk_fpu(void) +void arc_chk_fpu(void) { struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()]; @@ -293,7 +293,7 @@ void __cpuinit arc_chk_fpu(void) * such as only for boot CPU etc */ -void __cpuinit setup_processor(void) +void setup_processor(void) { char str[512]; int cpu_id = smp_processor_id(); diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index 5c7fd603d216..bca3052c956d 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -117,7 +117,7 @@ const char *arc_platform_smp_cpuinfo(void) * Called from asm stub in head.S * "current"/R25 already setup by low level boot code */ -void __cpuinit start_kernel_secondary(void) +void start_kernel_secondary(void) { struct mm_struct *mm = &init_mm; unsigned int cpu = smp_processor_id(); @@ -154,7 +154,7 @@ void __cpuinit start_kernel_secondary(void) * * Essential requirements being where to run from (PC) and stack (SP) */ -int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *idle) +int __cpu_up(unsigned int cpu, struct task_struct *idle) { unsigned long wait_till; diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c index ca0207b9d5b6..f8b7d880304d 100644 --- a/arch/arc/kernel/stacktrace.c +++ b/arch/arc/kernel/stacktrace.c @@ -79,7 +79,7 @@ static void seed_unwind_frame_info(struct task_struct *tsk, * assembly code */ frame_info->regs.r27 = 0; - frame_info->regs.r28 += 64; + frame_info->regs.r28 += 60; frame_info->call_frame = 0; } else { diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c index 09f4309aa2c0..0e51e69cf30d 100644 --- a/arch/arc/kernel/time.c +++ b/arch/arc/kernel/time.c @@ -44,13 +44,24 @@ #include <asm/clk.h> #include <asm/mach_desc.h> +/* Timer related Aux registers */ +#define ARC_REG_TIMER0_LIMIT 0x23 /* timer 0 limit */ +#define ARC_REG_TIMER0_CTRL 0x22 /* timer 0 control */ +#define ARC_REG_TIMER0_CNT 0x21 /* timer 0 count */ +#define ARC_REG_TIMER1_LIMIT 0x102 /* timer 1 limit */ +#define ARC_REG_TIMER1_CTRL 0x101 /* timer 1 control */ +#define ARC_REG_TIMER1_CNT 0x100 /* timer 1 count */ + +#define TIMER_CTRL_IE (1 << 0) /* Interupt when Count reachs limit */ +#define TIMER_CTRL_NH (1 << 1) /* Count only when CPU NOT halted */ + #define ARC_TIMER_MAX 0xFFFFFFFF /********** Clock Source Device *********/ #ifdef CONFIG_ARC_HAS_RTSC -int __cpuinit arc_counter_setup(void) +int arc_counter_setup(void) { /* RTSC insn taps into cpu clk, needs no setup */ @@ -105,7 +116,7 @@ static bool is_usable_as_clocksource(void) /* * set 32bit TIMER1 to keep counting monotonically and wraparound */ -int __cpuinit arc_counter_setup(void) +int arc_counter_setup(void) { write_aux_reg(ARC_REG_TIMER1_LIMIT, ARC_TIMER_MAX); write_aux_reg(ARC_REG_TIMER1_CNT, 0); @@ -212,7 +223,7 @@ static struct irqaction arc_timer_irq = { * Setup the local event timer for @cpu * N.B. weak so that some exotic ARC SoCs can completely override it */ -void __attribute__((weak)) __cpuinit arc_local_timer_setup(unsigned int cpu) +void __attribute__((weak)) arc_local_timer_setup(unsigned int cpu) { struct clock_event_device *clk = &per_cpu(arc_clockevent_device, cpu); diff --git a/arch/arc/kernel/traps.c b/arch/arc/kernel/traps.c index 0471d9c9dd54..e21692d2fdab 100644 --- a/arch/arc/kernel/traps.c +++ b/arch/arc/kernel/traps.c @@ -28,10 +28,9 @@ void __init trap_init(void) return; } -void die(const char *str, struct pt_regs *regs, unsigned long address, - unsigned long cause_reg) +void die(const char *str, struct pt_regs *regs, unsigned long address) { - show_kernel_fault_diag(str, regs, address, cause_reg); + show_kernel_fault_diag(str, regs, address); /* DEAD END */ __asm__("flag 1"); @@ -42,14 +41,13 @@ void die(const char *str, struct pt_regs *regs, unsigned long address, * -for user faults enqueues requested signal * -for kernel, chk if due to copy_(to|from)_user, otherwise die() */ -static noinline int handle_exception(unsigned long cause, char *str, - struct pt_regs *regs, siginfo_t *info) +static noinline int +handle_exception(const char *str, struct pt_regs *regs, siginfo_t *info) { if (user_mode(regs)) { struct task_struct *tsk = current; tsk->thread.fault_address = (__force unsigned int)info->si_addr; - tsk->thread.cause_code = cause; force_sig_info(info->si_signo, info, tsk); @@ -58,14 +56,14 @@ static noinline int handle_exception(unsigned long cause, char *str, if (fixup_exception(regs)) return 0; - die(str, regs, (unsigned long)info->si_addr, cause); + die(str, regs, (unsigned long)info->si_addr); } return 1; } #define DO_ERROR_INFO(signr, str, name, sicode) \ -int name(unsigned long cause, unsigned long address, struct pt_regs *regs) \ +int name(unsigned long address, struct pt_regs *regs) \ { \ siginfo_t info = { \ .si_signo = signr, \ @@ -73,7 +71,7 @@ int name(unsigned long cause, unsigned long address, struct pt_regs *regs) \ .si_code = sicode, \ .si_addr = (void __user *)address, \ }; \ - return handle_exception(cause, str, regs, &info);\ + return handle_exception(str, regs, &info);\ } /* @@ -90,11 +88,11 @@ DO_ERROR_INFO(SIGBUS, "Misaligned Access", do_misaligned_error, BUS_ADRALN) /* * Entry Point for Misaligned Data access Exception, for emulating in software */ -int do_misaligned_access(unsigned long cause, unsigned long address, - struct pt_regs *regs, struct callee_regs *cregs) +int do_misaligned_access(unsigned long address, struct pt_regs *regs, + struct callee_regs *cregs) { - if (misaligned_fixup(address, regs, cause, cregs) != 0) - return do_misaligned_error(cause, address, regs); + if (misaligned_fixup(address, regs, cregs) != 0) + return do_misaligned_error(address, regs); return 0; } @@ -104,10 +102,9 @@ int do_misaligned_access(unsigned long cause, unsigned long address, * Entry point for miscll errors such as Nested Exceptions * -Duplicate TLB entry is handled seperately though */ -void do_machine_check_fault(unsigned long cause, unsigned long address, - struct pt_regs *regs) +void do_machine_check_fault(unsigned long address, struct pt_regs *regs) { - die("Machine Check Exception", regs, address, cause); + die("Machine Check Exception", regs, address); } @@ -120,23 +117,22 @@ void do_machine_check_fault(unsigned long cause, unsigned long address, * -1 used for software breakpointing (gdb) * -2 used by kprobes */ -void do_non_swi_trap(unsigned long cause, unsigned long address, - struct pt_regs *regs) +void do_non_swi_trap(unsigned long address, struct pt_regs *regs) { - unsigned int param = cause & 0xff; + unsigned int param = regs->ecr_param; switch (param) { case 1: - trap_is_brkpt(cause, address, regs); + trap_is_brkpt(address, regs); break; case 2: - trap_is_kprobe(param, address, regs); + trap_is_kprobe(address, regs); break; case 3: case 4: - kgdb_trap(regs, param); + kgdb_trap(regs); break; default: @@ -149,14 +145,14 @@ void do_non_swi_trap(unsigned long cause, unsigned long address, * -For a corner case, ARC kprobes implementation resorts to using * this exception, hence the check */ -void do_insterror_or_kprobe(unsigned long cause, - unsigned long address, - struct pt_regs *regs) +void do_insterror_or_kprobe(unsigned long address, struct pt_regs *regs) { + int rc; + /* Check if this exception is caused by kprobes */ - if (notify_die(DIE_IERR, "kprobe_ierr", regs, address, - cause, SIGILL) == NOTIFY_STOP) + rc = notify_die(DIE_IERR, "kprobe_ierr", regs, address, 0, SIGILL); + if (rc == NOTIFY_STOP) return; - insterror_is_error(cause, address, regs); + insterror_is_error(address, regs); } diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c index a03528ecd276..73a7450ee622 100644 --- a/arch/arc/kernel/troubleshoot.c +++ b/arch/arc/kernel/troubleshoot.c @@ -117,23 +117,22 @@ static void show_faulting_vma(unsigned long address, char *buf) static void show_ecr_verbose(struct pt_regs *regs) { - unsigned int vec, cause_code, cause_reg; + unsigned int vec, cause_code; unsigned long address; - cause_reg = current->thread.cause_code; - pr_info("\n[ECR ]: 0x%08x => ", cause_reg); + pr_info("\n[ECR ]: 0x%08lx => ", regs->event); /* For Data fault, this is data address not instruction addr */ address = current->thread.fault_address; - vec = cause_reg >> 16; - cause_code = (cause_reg >> 8) & 0xFF; + vec = regs->ecr_vec; + cause_code = regs->ecr_cause; /* For DTLB Miss or ProtV, display the memory involved too */ if (vec == ECR_V_DTLB_MISS) { - pr_cont("Invalid %s 0x%08lx by insn @ 0x%08lx\n", - (cause_code == 0x01) ? "Read From" : - ((cause_code == 0x02) ? "Write to" : "EX"), + pr_cont("Invalid %s @ 0x%08lx by insn @ 0x%08lx\n", + (cause_code == 0x01) ? "Read" : + ((cause_code == 0x02) ? "Write" : "EX"), address, regs->ret); } else if (vec == ECR_V_ITLB_MISS) { pr_cont("Insn could not be fetched\n"); @@ -144,14 +143,12 @@ static void show_ecr_verbose(struct pt_regs *regs) } else if (vec == ECR_V_PROTV) { if (cause_code == ECR_C_PROTV_INST_FETCH) pr_cont("Execute from Non-exec Page\n"); - else if (cause_code == ECR_C_PROTV_LOAD) - pr_cont("Read from Non-readable Page\n"); - else if (cause_code == ECR_C_PROTV_STORE) - pr_cont("Write to Non-writable Page\n"); - else if (cause_code == ECR_C_PROTV_XCHG) - pr_cont("Data exchange protection violation\n"); else if (cause_code == ECR_C_PROTV_MISALIG_DATA) pr_cont("Misaligned r/w from 0x%08lx\n", address); + else + pr_cont("%s access not allowed on page\n", + (cause_code == 0x01) ? "Read" : + ((cause_code == 0x02) ? "Write" : "EX")); } else if (vec == ECR_V_INSN_ERR) { pr_cont("Illegal Insn\n"); } else { @@ -176,8 +173,7 @@ void show_regs(struct pt_regs *regs) print_task_path_n_nm(tsk, buf); show_regs_print_info(KERN_INFO); - if (current->thread.cause_code) - show_ecr_verbose(regs); + show_ecr_verbose(regs); pr_info("[EFA ]: 0x%08lx\n[BLINK ]: %pS\n[ERET ]: %pS\n", current->thread.fault_address, @@ -213,10 +209,9 @@ void show_regs(struct pt_regs *regs) } void show_kernel_fault_diag(const char *str, struct pt_regs *regs, - unsigned long address, unsigned long cause_reg) + unsigned long address) { current->thread.fault_address = address; - current->thread.cause_code = cause_reg; /* Caller and Callee regs */ show_regs(regs); diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c index 4cd81633febd..c0f832f595d3 100644 --- a/arch/arc/kernel/unaligned.c +++ b/arch/arc/kernel/unaligned.c @@ -187,7 +187,7 @@ fault: state->fault = 1; * Returns 0 if successfully handled, 1 if some error happened */ int misaligned_fixup(unsigned long address, struct pt_regs *regs, - unsigned long cause, struct callee_regs *cregs) + struct callee_regs *cregs) { struct disasm_state state; char buf[TASK_COMM_LEN]; diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index a8d02223da44..e550b117ec4f 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -289,6 +289,8 @@ static void __init setup_unwind_table(struct unwind_table *table, * instead of the initial loc addr * return; */ + WARN(1, "unwinder: FDE->initial_location NULL %p\n", + (const u8 *)(fde + 1) + *fde); } ++n; } diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S index d3c92f52d444..2555f5886af6 100644 --- a/arch/arc/kernel/vmlinux.lds.S +++ b/arch/arc/kernel/vmlinux.lds.S @@ -125,6 +125,11 @@ SECTIONS *(.debug_frame) __end_unwind = .; } + /* + * gcc 4.8 generates this for -fasynchonous-unwind-tables, + * while we still use the .debug_frame based unwinder + */ + /DISCARD/ : { *(.eh_frame) } #else /DISCARD/ : { *(.debug_frame) } #endif @@ -142,15 +147,18 @@ SECTIONS *(.arcextmap.*) } +#ifndef CONFIG_DEBUG_INFO /* open-coded because we need .debug_frame seperately for unwinding */ - .debug_aranges 0 : { *(.debug_aranges) } - .debug_pubnames 0 : { *(.debug_pubnames) } - .debug_info 0 : { *(.debug_info) } - .debug_abbrev 0 : { *(.debug_abbrev) } - .debug_line 0 : { *(.debug_line) } - .debug_str 0 : { *(.debug_str) } - .debug_loc 0 : { *(.debug_loc) } - .debug_macinfo 0 : { *(.debug_macinfo) } + /DISCARD/ : { *(.debug_aranges) } + /DISCARD/ : { *(.debug_pubnames) } + /DISCARD/ : { *(.debug_info) } + /DISCARD/ : { *(.debug_abbrev) } + /DISCARD/ : { *(.debug_line) } + /DISCARD/ : { *(.debug_str) } + /DISCARD/ : { *(.debug_loc) } + /DISCARD/ : { *(.debug_macinfo) } + /DISCARD/ : { *(.debug_ranges) } +#endif #ifdef CONFIG_ARC_HAS_DCCM . = CONFIG_ARC_DCCM_BASE; diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache_arc700.c index aedce1905441..f415d851b765 100644 --- a/arch/arc/mm/cache_arc700.c +++ b/arch/arc/mm/cache_arc700.c @@ -73,6 +73,33 @@ #include <asm/cachectl.h> #include <asm/setup.h> +/* Instruction cache related Auxiliary registers */ +#define ARC_REG_IC_BCR 0x77 /* Build Config reg */ +#define ARC_REG_IC_IVIC 0x10 +#define ARC_REG_IC_CTRL 0x11 +#define ARC_REG_IC_IVIL 0x19 +#if (CONFIG_ARC_MMU_VER > 2) +#define ARC_REG_IC_PTAG 0x1E +#endif + +/* Bit val in IC_CTRL */ +#define IC_CTRL_CACHE_DISABLE 0x1 + +/* Data cache related Auxiliary registers */ +#define ARC_REG_DC_BCR 0x72 /* Build Config reg */ +#define ARC_REG_DC_IVDC 0x47 +#define ARC_REG_DC_CTRL 0x48 +#define ARC_REG_DC_IVDL 0x4A +#define ARC_REG_DC_FLSH 0x4B +#define ARC_REG_DC_FLDL 0x4C +#if (CONFIG_ARC_MMU_VER > 2) +#define ARC_REG_DC_PTAG 0x5C +#endif + +/* Bit val in DC_CTRL */ +#define DC_CTRL_INV_MODE_FLUSH 0x40 +#define DC_CTRL_FLUSH_STATUS 0x100 + char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len) { int n = 0; @@ -89,8 +116,10 @@ char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len) enb ? "" : "DISABLED (kernel-build)"); \ } - PR_CACHE(&cpuinfo_arc700[c].icache, __CONFIG_ARC_HAS_ICACHE, "I-Cache"); - PR_CACHE(&cpuinfo_arc700[c].dcache, __CONFIG_ARC_HAS_DCACHE, "D-Cache"); + PR_CACHE(&cpuinfo_arc700[c].icache, IS_ENABLED(CONFIG_ARC_HAS_ICACHE), + "I-Cache"); + PR_CACHE(&cpuinfo_arc700[c].dcache, IS_ENABLED(CONFIG_ARC_HAS_DCACHE), + "D-Cache"); return buf; } @@ -100,17 +129,23 @@ char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len) * the cpuinfo structure for later use. * No Validation done here, simply read/convert the BCRs */ -void __cpuinit read_decode_cache_bcr(void) +void read_decode_cache_bcr(void) { - struct bcr_cache ibcr, dbcr; struct cpuinfo_arc_cache *p_ic, *p_dc; unsigned int cpu = smp_processor_id(); + struct bcr_cache { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int pad:12, line_len:4, sz:4, config:4, ver:8; +#else + unsigned int ver:8, config:4, sz:4, line_len:4, pad:12; +#endif + } ibcr, dbcr; p_ic = &cpuinfo_arc700[cpu].icache; READ_BCR(ARC_REG_IC_BCR, ibcr); - if (ibcr.config == 0x3) - p_ic->assoc = 2; + BUG_ON(ibcr.config != 3); + p_ic->assoc = 2; /* Fixed to 2w set assoc */ p_ic->line_len = 8 << ibcr.line_len; p_ic->sz = 0x200 << ibcr.sz; p_ic->ver = ibcr.ver; @@ -118,8 +153,8 @@ void __cpuinit read_decode_cache_bcr(void) p_dc = &cpuinfo_arc700[cpu].dcache; READ_BCR(ARC_REG_DC_BCR, dbcr); - if (dbcr.config == 0x2) - p_dc->assoc = 4; + BUG_ON(dbcr.config != 2); + p_dc->assoc = 4; /* Fixed to 4w set assoc */ p_dc->line_len = 16 << dbcr.line_len; p_dc->sz = 0x200 << dbcr.sz; p_dc->ver = dbcr.ver; @@ -132,14 +167,12 @@ void __cpuinit read_decode_cache_bcr(void) * 3. Enable the Caches, setup default flush mode for D-Cache * 3. Calculate the SHMLBA used by user space */ -void __cpuinit arc_cache_init(void) +void arc_cache_init(void) { - unsigned int temp; unsigned int cpu = smp_processor_id(); struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache; struct cpuinfo_arc_cache *dc = &cpuinfo_arc700[cpu].dcache; - int way_pg_ratio = way_pg_ratio; - int dcache_does_alias; + unsigned int dcache_does_alias, temp; char str[256]; printk(arc_cache_mumbojumbo(0, str, sizeof(str))); @@ -149,20 +182,11 @@ void __cpuinit arc_cache_init(void) #ifdef CONFIG_ARC_HAS_ICACHE /* 1. Confirm some of I-cache params which Linux assumes */ - if ((ic->assoc != ARC_ICACHE_WAYS) || - (ic->line_len != ARC_ICACHE_LINE_LEN)) { + if (ic->line_len != ARC_ICACHE_LINE_LEN) panic("Cache H/W doesn't match kernel Config"); - } -#if (CONFIG_ARC_MMU_VER > 2) - if (ic->ver != 3) { - if (running_on_hw) - panic("Cache ver doesn't match MMU ver\n"); - - /* For ISS - suggest the toggles to use */ - pr_err("Use -prop=icache_version=3,-prop=dcache_version=3\n"); - } -#endif + if (ic->ver != CONFIG_ARC_MMU_VER) + panic("Cache ver doesn't match MMU ver\n"); #endif /* Enable/disable I-Cache */ @@ -181,14 +205,12 @@ chk_dc: return; #ifdef CONFIG_ARC_HAS_DCACHE - if ((dc->assoc != ARC_DCACHE_WAYS) || - (dc->line_len != ARC_DCACHE_LINE_LEN)) { + if (dc->line_len != ARC_DCACHE_LINE_LEN) panic("Cache H/W doesn't match kernel Config"); - } - - dcache_does_alias = (dc->sz / ARC_DCACHE_WAYS) > PAGE_SIZE; /* check for D-Cache aliasing */ + dcache_does_alias = (dc->sz / dc->assoc) > PAGE_SIZE; + if (dcache_does_alias && !cache_is_vipt_aliasing()) panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n"); else if (!dcache_does_alias && cache_is_vipt_aliasing()) @@ -239,11 +261,9 @@ static inline void wait_for_flush(void) */ static inline void __dc_entire_op(const int cacheop) { - unsigned long flags, tmp = tmp; + unsigned int tmp = tmp; int aux; - local_irq_save(flags); - if (cacheop == OP_FLUSH_N_INV) { /* Dcache provides 2 cmd: FLUSH or INV * INV inturn has sub-modes: DISCARD or FLUSH-BEFORE @@ -267,8 +287,6 @@ static inline void __dc_entire_op(const int cacheop) /* Switch back the DISCARD ONLY Invalidate mode */ if (cacheop == OP_FLUSH_N_INV) write_aux_reg(ARC_REG_DC_CTRL, tmp & ~DC_CTRL_INV_MODE_FLUSH); - - local_irq_restore(flags); } /* @@ -459,8 +477,15 @@ static void __ic_line_inv_vaddr(unsigned long paddr, unsigned long vaddr, local_irq_restore(flags); } +static inline void __ic_entire_inv(void) +{ + write_aux_reg(ARC_REG_IC_IVIC, 1); + read_aux_reg(ARC_REG_IC_CTRL); /* blocks */ +} + #else +#define __ic_entire_inv() #define __ic_line_inv_vaddr(pstart, vstart, sz) #endif /* CONFIG_ARC_HAS_ICACHE */ @@ -487,7 +512,7 @@ void flush_dcache_page(struct page *page) struct address_space *mapping; if (!cache_is_vipt_aliasing()) { - set_bit(PG_arch_1, &page->flags); + clear_bit(PG_dc_clean, &page->flags); return; } @@ -501,7 +526,7 @@ void flush_dcache_page(struct page *page) * Make a note that K-mapping is dirty */ if (!mapping_mapped(mapping)) { - set_bit(PG_arch_1, &page->flags); + clear_bit(PG_dc_clean, &page->flags); } else if (page_mapped(page)) { /* kernel reading from page with U-mapping */ @@ -629,26 +654,13 @@ void ___flush_dcache_page(unsigned long paddr, unsigned long vaddr) __dc_line_op(paddr, vaddr & PAGE_MASK, PAGE_SIZE, OP_FLUSH_N_INV); } -void flush_icache_all(void) -{ - unsigned long flags; - - local_irq_save(flags); - - write_aux_reg(ARC_REG_IC_IVIC, 1); - - /* lr will not complete till the icache inv operation is not over */ - read_aux_reg(ARC_REG_IC_CTRL); - local_irq_restore(flags); -} - noinline void flush_cache_all(void) { unsigned long flags; local_irq_save(flags); - flush_icache_all(); + __ic_entire_inv(); __dc_entire_op(OP_FLUSH_N_INV); local_irq_restore(flags); @@ -667,7 +679,12 @@ void flush_cache_page(struct vm_area_struct *vma, unsigned long u_vaddr, { unsigned int paddr = pfn << PAGE_SHIFT; - __sync_icache_dcache(paddr, u_vaddr, PAGE_SIZE); + u_vaddr &= PAGE_MASK; + + ___flush_dcache_page(paddr, u_vaddr); + + if (vma->vm_flags & VM_EXEC) + __inv_icache_page(paddr, u_vaddr); } void flush_cache_range(struct vm_area_struct *vma, unsigned long start, @@ -717,7 +734,7 @@ void copy_user_highpage(struct page *to, struct page *from, * non copied user pages (e.g. read faults which wire in pagecache page * directly). */ - set_bit(PG_arch_1, &to->flags); + clear_bit(PG_dc_clean, &to->flags); /* * if SRC was already usermapped and non-congruent to kernel mapping @@ -725,15 +742,16 @@ void copy_user_highpage(struct page *to, struct page *from, */ if (clean_src_k_mappings) { __flush_dcache_page(kfrom, kfrom); + set_bit(PG_dc_clean, &from->flags); } else { - set_bit(PG_arch_1, &from->flags); + clear_bit(PG_dc_clean, &from->flags); } } void clear_user_page(void *to, unsigned long u_vaddr, struct page *page) { clear_page(to); - set_bit(PG_arch_1, &page->flags); + clear_bit(PG_dc_clean, &page->flags); } diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index 689ffd86d5e9..318164cabdfc 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -15,6 +15,7 @@ #include <linux/uaccess.h> #include <linux/kdebug.h> #include <asm/pgalloc.h> +#include <asm/mmu.h> static int handle_vmalloc_fault(struct mm_struct *mm, unsigned long address) { @@ -51,14 +52,14 @@ bad_area: return 1; } -void do_page_fault(struct pt_regs *regs, int write, unsigned long address, - unsigned long cause_code) +void do_page_fault(struct pt_regs *regs, unsigned long address) { struct vm_area_struct *vma = NULL; struct task_struct *tsk = current; struct mm_struct *mm = tsk->mm; siginfo_t info; int fault, ret; + int write = regs->ecr_cause & ECR_C_PROTV_STORE; /* ST/EX */ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE | (write ? FAULT_FLAG_WRITE : 0); @@ -109,7 +110,8 @@ good_area: /* Handle protection violation, execute on heap or stack */ - if (cause_code == ((ECR_V_PROTV << 16) | ECR_C_PROTV_INST_FETCH)) + if ((regs->ecr_vec == ECR_V_PROTV) && + (regs->ecr_cause == ECR_C_PROTV_INST_FETCH)) goto bad_area; if (write) { @@ -176,7 +178,6 @@ bad_area_nosemaphore: /* User mode accesses just cause a SIGSEGV */ if (user_mode(regs)) { tsk->thread.fault_address = address; - tsk->thread.cause_code = cause_code; info.si_signo = SIGSEGV; info.si_errno = 0; /* info.si_code has been set above */ @@ -197,7 +198,7 @@ no_context: if (fixup_exception(regs)) return; - die("Oops", regs, address, cause_code); + die("Oops", regs, address); out_of_memory: if (is_global_init(tsk)) { @@ -218,7 +219,6 @@ do_sigbus: goto no_context; tsk->thread.fault_address = address; - tsk->thread.cause_code = cause_code; info.si_signo = SIGBUS; info.si_errno = 0; info.si_code = BUS_ADRERR; diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c index fe1c5a073afe..7957dc4e4d4a 100644 --- a/arch/arc/mm/tlb.c +++ b/arch/arc/mm/tlb.c @@ -55,7 +55,7 @@ #include <asm/arcregs.h> #include <asm/setup.h> #include <asm/mmu_context.h> -#include <asm/tlb.h> +#include <asm/mmu.h> /* Need for ARC MMU v2 * @@ -97,6 +97,7 @@ * J-TLB entry got evicted/replaced. */ + /* A copy of the ASID from the PID reg is kept in asid_cache */ int asid_cache = FIRST_ASID; @@ -432,9 +433,14 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long vaddr_unaligned, { unsigned long vaddr = vaddr_unaligned & PAGE_MASK; unsigned long paddr = pte_val(*ptep) & PAGE_MASK; + struct page *page = pfn_to_page(pte_pfn(*ptep)); create_tlb(vma, vaddr, ptep); + if (page == ZERO_PAGE(0)) { + return; + } + /* * Exec page : Independent of aliasing/page-color considerations, * since icache doesn't snoop dcache on ARC, any dirty @@ -446,9 +452,8 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long vaddr_unaligned, */ if ((vma->vm_flags & VM_EXEC) || addr_not_cache_congruent(paddr, vaddr)) { - struct page *page = pfn_to_page(pte_pfn(*ptep)); - int dirty = test_and_clear_bit(PG_arch_1, &page->flags); + int dirty = !test_and_set_bit(PG_dc_clean, &page->flags); if (dirty) { /* wback + inv dcache lines */ __flush_dcache_page(paddr, paddr); @@ -464,12 +469,27 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long vaddr_unaligned, * the cpuinfo structure for later use. * No Validation is done here, simply read/convert the BCRs */ -void __cpuinit read_decode_mmu_bcr(void) +void read_decode_mmu_bcr(void) { - unsigned int tmp; - struct bcr_mmu_1_2 *mmu2; /* encoded MMU2 attr */ - struct bcr_mmu_3 *mmu3; /* encoded MMU3 attr */ struct cpuinfo_arc_mmu *mmu = &cpuinfo_arc700[smp_processor_id()].mmu; + unsigned int tmp; + struct bcr_mmu_1_2 { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int ver:8, ways:4, sets:4, u_itlb:8, u_dtlb:8; +#else + unsigned int u_dtlb:8, u_itlb:8, sets:4, ways:4, ver:8; +#endif + } *mmu2; + + struct bcr_mmu_3 { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int ver:8, ways:4, sets:4, osm:1, reserv:3, pg_sz:4, + u_itlb:4, u_dtlb:4; +#else + unsigned int u_dtlb:4, u_itlb:4, pg_sz:4, reserv:3, osm:1, sets:4, + ways:4, ver:8; +#endif + } *mmu3; tmp = read_aux_reg(ARC_REG_MMU_BCR); mmu->ver = (tmp >> 24); @@ -505,12 +525,12 @@ char *arc_mmu_mumbojumbo(int cpu_id, char *buf, int len) "J-TLB %d (%dx%d), uDTLB %d, uITLB %d, %s\n", p_mmu->num_tlb, p_mmu->sets, p_mmu->ways, p_mmu->u_dtlb, p_mmu->u_itlb, - __CONFIG_ARC_MMU_SASID_VAL ? "SASID" : ""); + IS_ENABLED(CONFIG_ARC_MMU_SASID) ? "SASID" : ""); return buf; } -void __cpuinit arc_mmu_init(void) +void arc_mmu_init(void) { char str[256]; struct cpuinfo_arc_mmu *mmu = &cpuinfo_arc700[smp_processor_id()].mmu; diff --git a/arch/arc/mm/tlbex.S b/arch/arc/mm/tlbex.S index 3357d26ffe54..5c5bb23001b0 100644 --- a/arch/arc/mm/tlbex.S +++ b/arch/arc/mm/tlbex.S @@ -39,7 +39,7 @@ #include <linux/linkage.h> #include <asm/entry.h> -#include <asm/tlb.h> +#include <asm/mmu.h> #include <asm/pgtable.h> #include <asm/arcregs.h> #include <asm/cache.h> @@ -147,9 +147,9 @@ ex_saved_reg1: #ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT and.f 0, r0, _PAGE_PRESENT bz 1f - ld r2, [num_pte_not_present] - add r2, r2, 1 - st r2, [num_pte_not_present] + ld r3, [num_pte_not_present] + add r3, r3, 1 + st r3, [num_pte_not_present] 1: #endif @@ -271,22 +271,22 @@ ARC_ENTRY EV_TLBMissI #endif ;---------------------------------------------------------------- - ; Get the PTE corresponding to V-addr accessed + ; Get the PTE corresponding to V-addr accessed, r2 is setup with EFA LOAD_FAULT_PTE ;---------------------------------------------------------------- ; VERIFY_PTE: Check if PTE permissions approp for executing code cmp_s r2, VMALLOC_START - mov.lo r2, (_PAGE_PRESENT | _PAGE_U_READ | _PAGE_U_EXECUTE) - mov.hs r2, (_PAGE_PRESENT | _PAGE_K_READ | _PAGE_K_EXECUTE) + mov.lo r2, (_PAGE_PRESENT | _PAGE_U_EXECUTE) + mov.hs r2, (_PAGE_PRESENT | _PAGE_K_EXECUTE) and r3, r0, r2 ; Mask out NON Flag bits from PTE xor.f r3, r3, r2 ; check ( ( pte & flags_test ) == flags_test ) bnz do_slow_path_pf ; Let Linux VM know that the page was accessed - or r0, r0, (_PAGE_PRESENT | _PAGE_ACCESSED) ; set Accessed Bit - st_s r0, [r1] ; Write back PTE + or r0, r0, _PAGE_ACCESSED ; set Accessed Bit + st_s r0, [r1] ; Write back PTE CONV_PTE_TO_TLB COMMIT_ENTRY_TO_MMU @@ -311,7 +311,7 @@ ARC_ENTRY EV_TLBMissD ;---------------------------------------------------------------- ; Get the PTE corresponding to V-addr accessed - ; If PTE exists, it will setup, r0 = PTE, r1 = Ptr to PTE + ; If PTE exists, it will setup, r0 = PTE, r1 = Ptr to PTE, r2 = EFA LOAD_FAULT_PTE ;---------------------------------------------------------------- @@ -345,7 +345,7 @@ ARC_ENTRY EV_TLBMissD ;---------------------------------------------------------------- ; UPDATE_PTE: Let Linux VM know that page was accessed/dirty lr r3, [ecr] - or r0, r0, (_PAGE_PRESENT | _PAGE_ACCESSED) ; Accessed bit always + or r0, r0, _PAGE_ACCESSED ; Accessed bit always btst_s r3, ECR_C_BIT_DTLB_ST_MISS ; See if it was a Write Access ? or.nz r0, r0, _PAGE_MODIFIED ; if Write, set Dirty bit as well st_s r0, [r1] ; Write back PTE @@ -381,18 +381,7 @@ do_slow_path_pf: ; ------- setup args for Linux Page fault Hanlder --------- mov_s r0, sp - lr r2, [efa] - lr r3, [ecr] - - ; Both st and ex imply WRITE access of some sort, hence do_page_fault( ) - ; invoked with write=1 for DTLB-st/ex Miss and write=0 for ITLB miss or - ; DTLB-ld Miss - ; DTLB Miss Cause code is ld = 0x01 , st = 0x02, ex = 0x03 - ; Following code uses that fact that st/ex have one bit in common - - btst_s r3, ECR_C_BIT_DTLB_ST_MISS - mov.z r1, 0 - mov.nz r1, 1 + lr r1, [efa] ; We don't want exceptions to be disabled while the fault is handled. ; Now that we have saved the context we return from exception hence diff --git a/arch/arc/plat-arcfpga/platform.c b/arch/arc/plat-arcfpga/platform.c index b3700c064c06..d71f3c3bcf24 100644 --- a/arch/arc/plat-arcfpga/platform.c +++ b/arch/arc/plat-arcfpga/platform.c @@ -77,6 +77,7 @@ static void __init setup_bvci_lat_unit(void) /*----------------------- Platform Devices -----------------------------*/ +#if IS_ENABLED(CONFIG_SERIAL_ARC) static unsigned long arc_uart_info[] = { 0, /* uart->is_emulated (runtime @running_on_hw) */ 0, /* uart->port.uartclk */ @@ -115,7 +116,7 @@ static struct platform_device arc_uart0_dev = { static struct platform_device *fpga_early_devs[] __initdata = { &arc_uart0_dev, }; -#endif +#endif /* CONFIG_SERIAL_ARC_CONSOLE */ static void arc_fpga_serial_init(void) { @@ -152,8 +153,13 @@ static void arc_fpga_serial_init(void) * otherwise the early console never gets a chance to run. */ add_preferred_console("ttyARC", 0, "115200"); -#endif +#endif /* CONFIG_SERIAL_ARC_CONSOLE */ +} +#else /* !IS_ENABLED(CONFIG_SERIAL_ARC) */ +static void arc_fpga_serial_init(void) +{ } +#endif static void __init plat_fpga_early_init(void) { @@ -169,7 +175,7 @@ static void __init plat_fpga_early_init(void) } static struct of_dev_auxdata plat_auxdata_lookup[] __initdata = { -#if defined(CONFIG_SERIAL_ARC) || defined(CONFIG_SERIAL_ARC_MODULE) +#if IS_ENABLED(CONFIG_SERIAL_ARC) OF_DEV_AUXDATA("snps,arc-uart", UART0_BASE, "arc-uart", arc_uart_info), #endif {} diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index 120b83bfde20..48d0a44270bd 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -27,7 +27,7 @@ OBJS += misc.o decompress.o ifeq ($(CONFIG_DEBUG_UNCOMPRESS),y) OBJS += debug.o endif -FONTC = $(srctree)/drivers/video/console/font_acorn_8x8.c +FONTC = $(srctree)/lib/fonts/font_acorn_8x8.c # string library code (-Os is enforced to keep it much smaller) OBJS += string.o diff --git a/arch/arm/include/asm/kvm_arch_timer.h b/arch/arm/include/asm/kvm_arch_timer.h deleted file mode 100644 index 68cb9e1dfb81..000000000000 --- a/arch/arm/include/asm/kvm_arch_timer.h +++ /dev/null @@ -1,85 +0,0 @@ -/* - * Copyright (C) 2012 ARM Ltd. - * Author: Marc Zyngier <marc.zyngier@arm.com> - * - * 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 program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#ifndef __ASM_ARM_KVM_ARCH_TIMER_H -#define __ASM_ARM_KVM_ARCH_TIMER_H - -#include <linux/clocksource.h> -#include <linux/hrtimer.h> -#include <linux/workqueue.h> - -struct arch_timer_kvm { -#ifdef CONFIG_KVM_ARM_TIMER - /* Is the timer enabled */ - bool enabled; - - /* Virtual offset */ - cycle_t cntvoff; -#endif -}; - -struct arch_timer_cpu { -#ifdef CONFIG_KVM_ARM_TIMER - /* Registers: control register, timer value */ - u32 cntv_ctl; /* Saved/restored */ - cycle_t cntv_cval; /* Saved/restored */ - - /* - * Anything that is not used directly from assembly code goes - * here. - */ - - /* Background timer used when the guest is not running */ - struct hrtimer timer; - - /* Work queued with the above timer expires */ - struct work_struct expired; - - /* Background timer active */ - bool armed; - - /* Timer IRQ */ - const struct kvm_irq_level *irq; -#endif -}; - -#ifdef CONFIG_KVM_ARM_TIMER -int kvm_timer_hyp_init(void); -int kvm_timer_init(struct kvm *kvm); -void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu); -void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu); -void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu); -void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu); -#else -static inline int kvm_timer_hyp_init(void) -{ - return 0; -}; - -static inline int kvm_timer_init(struct kvm *kvm) -{ - return 0; -} - -static inline void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) {} -static inline void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu) {} -static inline void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu) {} -static inline void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu) {} -#endif - -#endif diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h index 124623e5ef14..64e96960de29 100644 --- a/arch/arm/include/asm/kvm_arm.h +++ b/arch/arm/include/asm/kvm_arm.h @@ -135,7 +135,6 @@ #define KVM_PHYS_MASK (KVM_PHYS_SIZE - 1ULL) #define PTRS_PER_S2_PGD (1ULL << (KVM_PHYS_SHIFT - 30)) #define S2_PGD_ORDER get_order(PTRS_PER_S2_PGD * sizeof(pgd_t)) -#define S2_PGD_SIZE (1 << S2_PGD_ORDER) /* Virtualization Translation Control Register (VTCR) bits */ #define VTCR_SH0 (3 << 12) diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h index 18d50322a9e2..a2f43ddcc300 100644 --- a/arch/arm/include/asm/kvm_asm.h +++ b/arch/arm/include/asm/kvm_asm.h @@ -37,16 +37,18 @@ #define c5_AIFSR 15 /* Auxilary Instrunction Fault Status R */ #define c6_DFAR 16 /* Data Fault Address Register */ #define c6_IFAR 17 /* Instruction Fault Address Register */ -#define c9_L2CTLR 18 /* Cortex A15 L2 Control Register */ -#define c10_PRRR 19 /* Primary Region Remap Register */ -#define c10_NMRR 20 /* Normal Memory Remap Register */ -#define c12_VBAR 21 /* Vector Base Address Register */ -#define c13_CID 22 /* Context ID Register */ -#define c13_TID_URW 23 /* Thread ID, User R/W */ -#define c13_TID_URO 24 /* Thread ID, User R/O */ -#define c13_TID_PRIV 25 /* Thread ID, Privileged */ -#define c14_CNTKCTL 26 /* Timer Control Register (PL1) */ -#define NR_CP15_REGS 27 /* Number of regs (incl. invalid) */ +#define c7_PAR 18 /* Physical Address Register */ +#define c7_PAR_high 19 /* PAR top 32 bits */ +#define c9_L2CTLR 20 /* Cortex A15 L2 Control Register */ +#define c10_PRRR 21 /* Primary Region Remap Register */ +#define c10_NMRR 22 /* Normal Memory Remap Register */ +#define c12_VBAR 23 /* Vector Base Address Register */ +#define c13_CID 24 /* Context ID Register */ +#define c13_TID_URW 25 /* Thread ID, User R/W */ +#define c13_TID_URO 26 /* Thread ID, User R/O */ +#define c13_TID_PRIV 27 /* Thread ID, Privileged */ +#define c14_CNTKCTL 28 /* Timer Control Register (PL1) */ +#define NR_CP15_REGS 29 /* Number of regs (incl. invalid) */ #define ARM_EXCEPTION_RESET 0 #define ARM_EXCEPTION_UNDEFINED 1 @@ -72,8 +74,6 @@ extern char __kvm_hyp_vector[]; extern char __kvm_hyp_code_start[]; extern char __kvm_hyp_code_end[]; -extern void __kvm_tlb_flush_vmid(struct kvm *kvm); - extern void __kvm_flush_vm_context(void); extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa); diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h index 82b4babead2c..a464e8d7b6c5 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -65,11 +65,6 @@ static inline bool vcpu_mode_priv(struct kvm_vcpu *vcpu) return cpsr_mode > USR_MODE;; } -static inline bool kvm_vcpu_reg_is_pc(struct kvm_vcpu *vcpu, int reg) -{ - return reg == 15; -} - static inline u32 kvm_vcpu_get_hsr(struct kvm_vcpu *vcpu) { return vcpu->arch.fault.hsr; diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 57cb786a6203..7d22517d8071 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -23,9 +23,14 @@ #include <asm/kvm_asm.h> #include <asm/kvm_mmio.h> #include <asm/fpstate.h> -#include <asm/kvm_arch_timer.h> +#include <kvm/arm_arch_timer.h> +#if defined(CONFIG_KVM_ARM_MAX_VCPUS) #define KVM_MAX_VCPUS CONFIG_KVM_ARM_MAX_VCPUS +#else +#define KVM_MAX_VCPUS 0 +#endif + #define KVM_USER_MEM_SLOTS 32 #define KVM_PRIVATE_MEM_SLOTS 4 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 @@ -38,7 +43,7 @@ #define KVM_NR_PAGE_SIZES 1 #define KVM_PAGES_PER_HPAGE(x) (1UL<<31) -#include <asm/kvm_vgic.h> +#include <kvm/arm_vgic.h> struct kvm_vcpu; u32 *kvm_vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num, u32 mode); @@ -190,8 +195,8 @@ int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, int exception_index); -static inline void __cpu_init_hyp_mode(unsigned long long boot_pgd_ptr, - unsigned long long pgd_ptr, +static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr, + phys_addr_t pgd_ptr, unsigned long hyp_stack_ptr, unsigned long vector_ptr) { diff --git a/arch/arm/include/asm/kvm_vgic.h b/arch/arm/include/asm/kvm_vgic.h deleted file mode 100644 index 343744e4809c..000000000000 --- a/arch/arm/include/asm/kvm_vgic.h +++ /dev/null @@ -1,220 +0,0 @@ -/* - * Copyright (C) 2012 ARM Ltd. - * Author: Marc Zyngier <marc.zyngier@arm.com> - * - * 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 program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#ifndef __ASM_ARM_KVM_VGIC_H -#define __ASM_ARM_KVM_VGIC_H - -#include <linux/kernel.h> -#include <linux/kvm.h> -#include <linux/irqreturn.h> -#include <linux/spinlock.h> -#include <linux/types.h> -#include <linux/irqchip/arm-gic.h> - -#define VGIC_NR_IRQS 128 -#define VGIC_NR_SGIS 16 -#define VGIC_NR_PPIS 16 -#define VGIC_NR_PRIVATE_IRQS (VGIC_NR_SGIS + VGIC_NR_PPIS) -#define VGIC_NR_SHARED_IRQS (VGIC_NR_IRQS - VGIC_NR_PRIVATE_IRQS) -#define VGIC_MAX_CPUS KVM_MAX_VCPUS -#define VGIC_MAX_LRS (1 << 6) - -/* Sanity checks... */ -#if (VGIC_MAX_CPUS > 8) -#error Invalid number of CPU interfaces -#endif - -#if (VGIC_NR_IRQS & 31) -#error "VGIC_NR_IRQS must be a multiple of 32" -#endif - -#if (VGIC_NR_IRQS > 1024) -#error "VGIC_NR_IRQS must be <= 1024" -#endif - -/* - * The GIC distributor registers describing interrupts have two parts: - * - 32 per-CPU interrupts (SGI + PPI) - * - a bunch of shared interrupts (SPI) - */ -struct vgic_bitmap { - union { - u32 reg[VGIC_NR_PRIVATE_IRQS / 32]; - DECLARE_BITMAP(reg_ul, VGIC_NR_PRIVATE_IRQS); - } percpu[VGIC_MAX_CPUS]; - union { - u32 reg[VGIC_NR_SHARED_IRQS / 32]; - DECLARE_BITMAP(reg_ul, VGIC_NR_SHARED_IRQS); - } shared; -}; - -struct vgic_bytemap { - u32 percpu[VGIC_MAX_CPUS][VGIC_NR_PRIVATE_IRQS / 4]; - u32 shared[VGIC_NR_SHARED_IRQS / 4]; -}; - -struct vgic_dist { -#ifdef CONFIG_KVM_ARM_VGIC - spinlock_t lock; - bool ready; - - /* Virtual control interface mapping */ - void __iomem *vctrl_base; - - /* Distributor and vcpu interface mapping in the guest */ - phys_addr_t vgic_dist_base; - phys_addr_t vgic_cpu_base; - - /* Distributor enabled */ - u32 enabled; - - /* Interrupt enabled (one bit per IRQ) */ - struct vgic_bitmap irq_enabled; - - /* Interrupt 'pin' level */ - struct vgic_bitmap irq_state; - - /* Level-triggered interrupt in progress */ - struct vgic_bitmap irq_active; - - /* Interrupt priority. Not used yet. */ - struct vgic_bytemap irq_priority; - - /* Level/edge triggered */ - struct vgic_bitmap irq_cfg; - - /* Source CPU per SGI and target CPU */ - u8 irq_sgi_sources[VGIC_MAX_CPUS][VGIC_NR_SGIS]; - - /* Target CPU for each IRQ */ - u8 irq_spi_cpu[VGIC_NR_SHARED_IRQS]; - struct vgic_bitmap irq_spi_target[VGIC_MAX_CPUS]; - - /* Bitmap indicating which CPU has something pending */ - unsigned long irq_pending_on_cpu; -#endif -}; - -struct vgic_cpu { -#ifdef CONFIG_KVM_ARM_VGIC - /* per IRQ to LR mapping */ - u8 vgic_irq_lr_map[VGIC_NR_IRQS]; - - /* Pending interrupts on this VCPU */ - DECLARE_BITMAP( pending_percpu, VGIC_NR_PRIVATE_IRQS); - DECLARE_BITMAP( pending_shared, VGIC_NR_SHARED_IRQS); - - /* Bitmap of used/free list registers */ - DECLARE_BITMAP( lr_used, VGIC_MAX_LRS); - - /* Number of list registers on this CPU */ - int nr_lr; - - /* CPU vif control registers for world switch */ - u32 vgic_hcr; - u32 vgic_vmcr; - u32 vgic_misr; /* Saved only */ - u32 vgic_eisr[2]; /* Saved only */ - u32 vgic_elrsr[2]; /* Saved only */ - u32 vgic_apr; - u32 vgic_lr[VGIC_MAX_LRS]; -#endif -}; - -#define LR_EMPTY 0xff - -struct kvm; -struct kvm_vcpu; -struct kvm_run; -struct kvm_exit_mmio; - -#ifdef CONFIG_KVM_ARM_VGIC -int kvm_vgic_set_addr(struct kvm *kvm, unsigned long type, u64 addr); -int kvm_vgic_hyp_init(void); -int kvm_vgic_init(struct kvm *kvm); -int kvm_vgic_create(struct kvm *kvm); -int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu); -void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu); -void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu); -int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num, - bool level); -int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu); -bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run, - struct kvm_exit_mmio *mmio); - -#define irqchip_in_kernel(k) (!!((k)->arch.vgic.vctrl_base)) -#define vgic_initialized(k) ((k)->arch.vgic.ready) - -#else -static inline int kvm_vgic_hyp_init(void) -{ - return 0; -} - -static inline int kvm_vgic_set_addr(struct kvm *kvm, unsigned long type, u64 addr) -{ - return 0; -} - -static inline int kvm_vgic_init(struct kvm *kvm) -{ - return 0; -} - -static inline int kvm_vgic_create(struct kvm *kvm) -{ - return 0; -} - -static inline int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) -{ - return 0; -} - -static inline void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) {} -static inline void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) {} - -static inline int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, - unsigned int irq_num, bool level) -{ - return 0; -} - -static inline int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu) -{ - return 0; -} - -static inline bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run, - struct kvm_exit_mmio *mmio) -{ - return false; -} - -static inline int irqchip_in_kernel(struct kvm *kvm) -{ - return 0; -} - -static inline bool vgic_initialized(struct kvm *kvm) -{ - return true; -} -#endif - -#endif diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig index 370e1a8af6ac..ebf5015508b5 100644 --- a/arch/arm/kvm/Kconfig +++ b/arch/arm/kvm/Kconfig @@ -41,9 +41,9 @@ config KVM_ARM_HOST Provides host support for ARM processors. config KVM_ARM_MAX_VCPUS - int "Number maximum supported virtual CPUs per VM" if KVM_ARM_HOST - default 4 if KVM_ARM_HOST - default 0 + int "Number maximum supported virtual CPUs per VM" + depends on KVM_ARM_HOST + default 4 help Static number of max supported virtual CPUs per VM. @@ -67,6 +67,4 @@ config KVM_ARM_TIMER ---help--- Adds support for the Architected Timers in virtual machines -source drivers/virtio/Kconfig - endif # VIRTUALIZATION diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile index 53c5ed83d16f..d99bee4950e5 100644 --- a/arch/arm/kvm/Makefile +++ b/arch/arm/kvm/Makefile @@ -14,10 +14,11 @@ CFLAGS_mmu.o := -I. AFLAGS_init.o := -Wa,-march=armv7-a$(plus_virt) AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt) -kvm-arm-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o) +KVM := ../../../virt/kvm +kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o obj-y += kvm-arm.o init.o interrupts.o obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o obj-y += coproc.o coproc_a15.o mmio.o psci.o perf.o -obj-$(CONFIG_KVM_ARM_VGIC) += vgic.o -obj-$(CONFIG_KVM_ARM_TIMER) += arch_timer.o +obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic.o +obj-$(CONFIG_KVM_ARM_TIMER) += $(KVM)/arm/arch_timer.o diff --git a/arch/arm/kvm/arch_timer.c b/arch/arm/kvm/arch_timer.c deleted file mode 100644 index 49a7516d81c7..000000000000 --- a/arch/arm/kvm/arch_timer.c +++ /dev/null @@ -1,273 +0,0 @@ -/* - * Copyright (C) 2012 ARM Ltd. - * Author: Marc Zyngier <marc.zyngier@arm.com> - * - * 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 program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#include <linux/cpu.h> -#include <linux/of_irq.h> -#include <linux/kvm.h> -#include <linux/kvm_host.h> -#include <linux/interrupt.h> - -#include <clocksource/arm_arch_timer.h> -#include <asm/arch_timer.h> - -#include <asm/kvm_vgic.h> -#include <asm/kvm_arch_timer.h> - -static struct timecounter *timecounter; -static struct workqueue_struct *wqueue; -static struct kvm_irq_level timer_irq = { - .level = 1, -}; - -static cycle_t kvm_phys_timer_read(void) -{ - return timecounter->cc->read(timecounter->cc); -} - -static bool timer_is_armed(struct arch_timer_cpu *timer) -{ - return timer->armed; -} - -/* timer_arm: as in "arm the timer", not as in ARM the company */ -static void timer_arm(struct arch_timer_cpu *timer, u64 ns) -{ - timer->armed = true; - hrtimer_start(&timer->timer, ktime_add_ns(ktime_get(), ns), - HRTIMER_MODE_ABS); -} - -static void timer_disarm(struct arch_timer_cpu *timer) -{ - if (timer_is_armed(timer)) { - hrtimer_cancel(&timer->timer); - cancel_work_sync(&timer->expired); - timer->armed = false; - } -} - -static void kvm_timer_inject_irq(struct kvm_vcpu *vcpu) -{ - struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; - - timer->cntv_ctl |= ARCH_TIMER_CTRL_IT_MASK; - kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id, - vcpu->arch.timer_cpu.irq->irq, - vcpu->arch.timer_cpu.irq->level); -} - -static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id) -{ - struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)dev_id; - - /* - * We disable the timer in the world switch and let it be - * handled by kvm_timer_sync_hwstate(). Getting a timer - * interrupt at this point is a sure sign of some major - * breakage. - */ - pr_warn("Unexpected interrupt %d on vcpu %p\n", irq, vcpu); - return IRQ_HANDLED; -} - -static void kvm_timer_inject_irq_work(struct work_struct *work) -{ - struct kvm_vcpu *vcpu; - - vcpu = container_of(work, struct kvm_vcpu, arch.timer_cpu.expired); - vcpu->arch.timer_cpu.armed = false; - kvm_timer_inject_irq(vcpu); -} - -static enum hrtimer_restart kvm_timer_expire(struct hrtimer *hrt) -{ - struct arch_timer_cpu *timer; - timer = container_of(hrt, struct arch_timer_cpu, timer); - queue_work(wqueue, &timer->expired); - return HRTIMER_NORESTART; -} - -/** - * kvm_timer_flush_hwstate - prepare to move the virt timer to the cpu - * @vcpu: The vcpu pointer - * - * Disarm any pending soft timers, since the world-switch code will write the - * virtual timer state back to the physical CPU. - */ -void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu) -{ - struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; - - /* - * We're about to run this vcpu again, so there is no need to - * keep the background timer running, as we're about to - * populate the CPU timer again. - */ - timer_disarm(timer); -} - -/** - * kvm_timer_sync_hwstate - sync timer state from cpu - * @vcpu: The vcpu pointer - * - * Check if the virtual timer was armed and either schedule a corresponding - * soft timer or inject directly if already expired. - */ -void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu) -{ - struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; - cycle_t cval, now; - u64 ns; - - if ((timer->cntv_ctl & ARCH_TIMER_CTRL_IT_MASK) || - !(timer->cntv_ctl & ARCH_TIMER_CTRL_ENABLE)) - return; - - cval = timer->cntv_cval; - now = kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff; - - BUG_ON(timer_is_armed(timer)); - - if (cval <= now) { - /* - * Timer has already expired while we were not - * looking. Inject the interrupt and carry on. - */ - kvm_timer_inject_irq(vcpu); - return; - } - - ns = cyclecounter_cyc2ns(timecounter->cc, cval - now); - timer_arm(timer, ns); -} - -void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) -{ - struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; - - INIT_WORK(&timer->expired, kvm_timer_inject_irq_work); - hrtimer_init(&timer->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); - timer->timer.function = kvm_timer_expire; - timer->irq = &timer_irq; -} - -static void kvm_timer_init_interrupt(void *info) -{ - enable_percpu_irq(timer_irq.irq, 0); -} - - -static int kvm_timer_cpu_notify(struct notifier_block *self, - unsigned long action, void *cpu) -{ - switch (action) { - case CPU_STARTING: - case CPU_STARTING_FROZEN: - kvm_timer_init_interrupt(NULL); - break; - case CPU_DYING: - case CPU_DYING_FROZEN: - disable_percpu_irq(timer_irq.irq); - break; - } - - return NOTIFY_OK; -} - -static struct notifier_block kvm_timer_cpu_nb = { - .notifier_call = kvm_timer_cpu_notify, -}; - -static const struct of_device_id arch_timer_of_match[] = { - { .compatible = "arm,armv7-timer", }, - { .compatible = "arm,armv8-timer", }, - {}, -}; - -int kvm_timer_hyp_init(void) -{ - struct device_node *np; - unsigned int ppi; - int err; - - timecounter = arch_timer_get_timecounter(); - if (!timecounter) - return -ENODEV; - - np = of_find_matching_node(NULL, arch_timer_of_match); - if (!np) { - kvm_err("kvm_arch_timer: can't find DT node\n"); - return -ENODEV; - } - - ppi = irq_of_parse_and_map(np, 2); - if (!ppi) { - kvm_err("kvm_arch_timer: no virtual timer interrupt\n"); - err = -EINVAL; - goto out; - } - - err = request_percpu_irq(ppi, kvm_arch_timer_handler, - "kvm guest timer", kvm_get_running_vcpus()); - if (err) { - kvm_err("kvm_arch_timer: can't request interrupt %d (%d)\n", - ppi, err); - goto out; - } - - timer_irq.irq = ppi; - - err = register_cpu_notifier(&kvm_timer_cpu_nb); - if (err) { - kvm_err("Cannot register timer CPU notifier\n"); - goto out_free; - } - - wqueue = create_singlethread_workqueue("kvm_arch_timer"); - if (!wqueue) { - err = -ENOMEM; - goto out_free; - } - - kvm_info("%s IRQ%d\n", np->name, ppi); - on_each_cpu(kvm_timer_init_interrupt, NULL, 1); - - goto out; -out_free: - free_percpu_irq(ppi, kvm_get_running_vcpus()); -out: - of_node_put(np); - return err; -} - -void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu) -{ - struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; - - timer_disarm(timer); -} - -int kvm_timer_init(struct kvm *kvm) -{ - if (timecounter && wqueue) { - kvm->arch.timer.cntvoff = kvm_phys_timer_read(); - kvm->arch.timer.enabled = 1; - } - - return 0; -} diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index ef1703b9587b..741f66a2edbd 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -800,8 +800,8 @@ long kvm_arch_vm_ioctl(struct file *filp, static void cpu_init_hyp_mode(void *dummy) { - unsigned long long boot_pgd_ptr; - unsigned long long pgd_ptr; + phys_addr_t boot_pgd_ptr; + phys_addr_t pgd_ptr; unsigned long hyp_stack_ptr; unsigned long stack_page; unsigned long vector_ptr; @@ -809,8 +809,8 @@ static void cpu_init_hyp_mode(void *dummy) /* Switch from the HYP stub to our own HYP init vector */ __hyp_set_vectors(kvm_get_idmap_vector()); - boot_pgd_ptr = (unsigned long long)kvm_mmu_get_boot_httbr(); - pgd_ptr = (unsigned long long)kvm_mmu_get_httbr(); + boot_pgd_ptr = kvm_mmu_get_boot_httbr(); + pgd_ptr = kvm_mmu_get_httbr(); stack_page = __get_cpu_var(kvm_arm_hyp_stack_page); hyp_stack_ptr = stack_page + PAGE_SIZE; vector_ptr = (unsigned long)__kvm_hyp_vector; diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c index 8eea97be1ed5..4a5199070430 100644 --- a/arch/arm/kvm/coproc.c +++ b/arch/arm/kvm/coproc.c @@ -180,6 +180,10 @@ static const struct coproc_reg cp15_regs[] = { NULL, reset_unknown, c6_DFAR }, { CRn( 6), CRm( 0), Op1( 0), Op2( 2), is32, NULL, reset_unknown, c6_IFAR }, + + /* PAR swapped by interrupt.S */ + { CRn( 7), Op1( 0), is64, NULL, reset_unknown64, c7_PAR }, + /* * DC{C,I,CI}SW operations: */ diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c index 3d74a0be47db..df4c82d47ad7 100644 --- a/arch/arm/kvm/handle_exit.c +++ b/arch/arm/kvm/handle_exit.c @@ -52,9 +52,6 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run) { - if (kvm_psci_call(vcpu)) - return 1; - kvm_inject_undefined(vcpu); return 1; } diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S index f7793df62f58..16cd4ba5d7fd 100644 --- a/arch/arm/kvm/interrupts.S +++ b/arch/arm/kvm/interrupts.S @@ -49,6 +49,7 @@ __kvm_hyp_code_start: ENTRY(__kvm_tlb_flush_vmid_ipa) push {r2, r3} + dsb ishst add r0, r0, #KVM_VTTBR ldrd r2, r3, [r0] mcrr p15, 6, r2, r3, c2 @ Write VTTBR @@ -291,6 +292,7 @@ THUMB( orr r2, r2, #PSR_T_BIT ) ldr r2, =BSYM(panic) msr ELR_hyp, r2 ldr r0, =\panic_str + clrex @ Clear exclusive monitor eret .endm @@ -414,6 +416,10 @@ guest_trap: mrcne p15, 4, r2, c6, c0, 4 @ HPFAR bne 3f + /* Preserve PAR */ + mrrc p15, 0, r0, r1, c7 @ PAR + push {r0, r1} + /* Resolve IPA using the xFAR */ mcr p15, 0, r2, c7, c8, 0 @ ATS1CPR isb @@ -424,13 +430,20 @@ guest_trap: lsl r2, r2, #4 orr r2, r2, r1, lsl #24 + /* Restore PAR */ + pop {r0, r1} + mcrr p15, 0, r0, r1, c7 @ PAR + 3: load_vcpu @ Load VCPU pointer to r0 str r2, [r0, #VCPU_HPFAR] 1: mov r1, #ARM_EXCEPTION_HVC b __kvm_vcpu_return -4: pop {r0, r1, r2} @ Failed translation, return to guest +4: pop {r0, r1} @ Failed translation, return to guest + mcrr p15, 0, r0, r1, c7 @ PAR + clrex + pop {r0, r1, r2} eret /* @@ -456,6 +469,7 @@ switch_to_guest_vfp: pop {r3-r7} pop {r0-r2} + clrex eret #endif diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S index d43cfb5b37c4..6f18695a09cb 100644 --- a/arch/arm/kvm/interrupts_head.S +++ b/arch/arm/kvm/interrupts_head.S @@ -302,11 +302,14 @@ vcpu .req r0 @ vcpu pointer always in r0 .endif mrc p15, 0, r2, c14, c1, 0 @ CNTKCTL + mrrc p15, 0, r4, r5, c7 @ PAR .if \store_to_vcpu == 0 - push {r2} + push {r2,r4-r5} .else str r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)] + add r12, vcpu, #CP15_OFFSET(c7_PAR) + strd r4, r5, [r12] .endif .endm @@ -319,12 +322,15 @@ vcpu .req r0 @ vcpu pointer always in r0 */ .macro write_cp15_state read_from_vcpu .if \read_from_vcpu == 0 - pop {r2} + pop {r2,r4-r5} .else ldr r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)] + add r12, vcpu, #CP15_OFFSET(c7_PAR) + ldrd r4, r5, [r12] .endif mcr p15, 0, r2, c14, c1, 0 @ CNTKCTL + mcrr p15, 0, r4, r5, c7 @ PAR .if \read_from_vcpu == 0 pop {r2-r12} diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c index 72a12f2171b2..b8e06b7a2833 100644 --- a/arch/arm/kvm/mmio.c +++ b/arch/arm/kvm/mmio.c @@ -86,12 +86,6 @@ static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, sign_extend = kvm_vcpu_dabt_issext(vcpu); rt = kvm_vcpu_dabt_get_rd(vcpu); - if (kvm_vcpu_reg_is_pc(vcpu, rt)) { - /* IO memory trying to read/write pc */ - kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu)); - return 1; - } - mmio->is_write = is_write; mmio->phys_addr = fault_ipa; mmio->len = len; diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 84ba67b982c0..ca6bea4859b4 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -382,9 +382,6 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm) if (!pgd) return -ENOMEM; - /* stage-2 pgd must be aligned to its size */ - VM_BUG_ON((unsigned long)pgd & (S2_PGD_SIZE - 1)); - memset(pgd, 0, PTRS_PER_S2_PGD * sizeof(pgd_t)); kvm_clean_pgd(pgd); kvm->arch.pgd = pgd; diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c index 7ee5bb7a3667..86a693a02ba3 100644 --- a/arch/arm/kvm/psci.c +++ b/arch/arm/kvm/psci.c @@ -75,7 +75,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) * kvm_psci_call - handle PSCI call if r0 value is in range * @vcpu: Pointer to the VCPU struct * - * Handle PSCI calls from guests through traps from HVC or SMC instructions. + * Handle PSCI calls from guests through traps from HVC instructions. * The calling convention is similar to SMC calls to the secure world where * the function number is placed in r0 and this function returns true if the * function number specified in r0 is withing the PSCI range, and false diff --git a/arch/arm/kvm/reset.c b/arch/arm/kvm/reset.c index b80256b554cd..b7840e7aa452 100644 --- a/arch/arm/kvm/reset.c +++ b/arch/arm/kvm/reset.c @@ -27,6 +27,8 @@ #include <asm/kvm_arm.h> #include <asm/kvm_coproc.h> +#include <kvm/arm_arch_timer.h> + /****************************************************************************** * Cortex-A15 Reset Values */ @@ -37,6 +39,11 @@ static struct kvm_regs a15_regs_reset = { .usr_regs.ARM_cpsr = SVC_MODE | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT, }; +static const struct kvm_irq_level a15_vtimer_irq = { + .irq = 27, + .level = 1, +}; + /******************************************************************************* * Exported reset function @@ -52,6 +59,7 @@ static struct kvm_regs a15_regs_reset = { int kvm_reset_vcpu(struct kvm_vcpu *vcpu) { struct kvm_regs *cpu_reset; + const struct kvm_irq_level *cpu_vtimer_irq; switch (vcpu->arch.target) { case KVM_ARM_TARGET_CORTEX_A15: @@ -59,6 +67,7 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) return -EINVAL; cpu_reset = &a15_regs_reset; vcpu->arch.midr = read_cpuid_id(); + cpu_vtimer_irq = &a15_vtimer_irq; break; default: return -ENODEV; @@ -70,5 +79,8 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) /* Reset CP15 registers */ kvm_reset_coprocs(vcpu); + /* Reset arch_timer context */ + kvm_timer_vcpu_reset(vcpu, cpu_vtimer_irq); + return 0; } diff --git a/arch/arm/kvm/vgic.c b/arch/arm/kvm/vgic.c deleted file mode 100644 index 17c5ac7d10ed..000000000000 --- a/arch/arm/kvm/vgic.c +++ /dev/null @@ -1,1499 +0,0 @@ -/* - * Copyright (C) 2012 ARM Ltd. - * Author: Marc Zyngier <marc.zyngier@arm.com> - * - * 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 program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#include <linux/cpu.h> -#include <linux/kvm.h> -#include <linux/kvm_host.h> -#include <linux/interrupt.h> -#include <linux/io.h> -#include <linux/of.h> -#include <linux/of_address.h> -#include <linux/of_irq.h> - -#include <linux/irqchip/arm-gic.h> - -#include <asm/kvm_emulate.h> -#include <asm/kvm_arm.h> -#include <asm/kvm_mmu.h> - -/* - * How the whole thing works (courtesy of Christoffer Dall): - * - * - At any time, the dist->irq_pending_on_cpu is the oracle that knows if - * something is pending - * - VGIC pending interrupts are stored on the vgic.irq_state vgic - * bitmap (this bitmap is updated by both user land ioctls and guest - * mmio ops, and other in-kernel peripherals such as the - * arch. timers) and indicate the 'wire' state. - * - Every time the bitmap changes, the irq_pending_on_cpu oracle is - * recalculated - * - To calculate the oracle, we need info for each cpu from - * compute_pending_for_cpu, which considers: - * - PPI: dist->irq_state & dist->irq_enable - * - SPI: dist->irq_state & dist->irq_enable & dist->irq_spi_target - * - irq_spi_target is a 'formatted' version of the GICD_ICFGR - * registers, stored on each vcpu. We only keep one bit of - * information per interrupt, making sure that only one vcpu can - * accept the interrupt. - * - The same is true when injecting an interrupt, except that we only - * consider a single interrupt at a time. The irq_spi_cpu array - * contains the target CPU for each SPI. - * - * The handling of level interrupts adds some extra complexity. We - * need to track when the interrupt has been EOIed, so we can sample - * the 'line' again. This is achieved as such: - * - * - When a level interrupt is moved onto a vcpu, the corresponding - * bit in irq_active is set. As long as this bit is set, the line - * will be ignored for further interrupts. The interrupt is injected - * into the vcpu with the GICH_LR_EOI bit set (generate a - * maintenance interrupt on EOI). - * - When the interrupt is EOIed, the maintenance interrupt fires, - * and clears the corresponding bit in irq_active. This allow the - * interrupt line to be sampled again. - */ - -#define VGIC_ADDR_UNDEF (-1) -#define IS_VGIC_ADDR_UNDEF(_x) ((_x) == VGIC_ADDR_UNDEF) - -/* Physical address of vgic virtual cpu interface */ -static phys_addr_t vgic_vcpu_base; - -/* Virtual control interface base address */ -static void __iomem *vgic_vctrl_base; - -static struct device_node *vgic_node; - -#define ACCESS_READ_VALUE (1 << 0) -#define ACCESS_READ_RAZ (0 << 0) -#define ACCESS_READ_MASK(x) ((x) & (1 << 0)) -#define ACCESS_WRITE_IGNORED (0 << 1) -#define ACCESS_WRITE_SETBIT (1 << 1) -#define ACCESS_WRITE_CLEARBIT (2 << 1) -#define ACCESS_WRITE_VALUE (3 << 1) -#define ACCESS_WRITE_MASK(x) ((x) & (3 << 1)) - -static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu); -static void vgic_update_state(struct kvm *kvm); -static void vgic_kick_vcpus(struct kvm *kvm); -static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg); -static u32 vgic_nr_lr; - -static unsigned int vgic_maint_irq; - -static u32 *vgic_bitmap_get_reg(struct vgic_bitmap *x, - int cpuid, u32 offset) -{ - offset >>= 2; - if (!offset) - return x->percpu[cpuid].reg; - else - return x->shared.reg + offset - 1; -} - -static int vgic_bitmap_get_irq_val(struct vgic_bitmap *x, - int cpuid, int irq) -{ - if (irq < VGIC_NR_PRIVATE_IRQS) - return test_bit(irq, x->percpu[cpuid].reg_ul); - - return test_bit(irq - VGIC_NR_PRIVATE_IRQS, x->shared.reg_ul); -} - -static void vgic_bitmap_set_irq_val(struct vgic_bitmap *x, int cpuid, - int irq, int val) -{ - unsigned long *reg; - - if (irq < VGIC_NR_PRIVATE_IRQS) { - reg = x->percpu[cpuid].reg_ul; - } else { - reg = x->shared.reg_ul; - irq -= VGIC_NR_PRIVATE_IRQS; - } - - if (val) - set_bit(irq, reg); - else - clear_bit(irq, reg); -} - -static unsigned long *vgic_bitmap_get_cpu_map(struct vgic_bitmap *x, int cpuid) -{ - if (unlikely(cpuid >= VGIC_MAX_CPUS)) - return NULL; - return x->percpu[cpuid].reg_ul; -} - -static unsigned long *vgic_bitmap_get_shared_map(struct vgic_bitmap *x) -{ - return x->shared.reg_ul; -} - -static u32 *vgic_bytemap_get_reg(struct vgic_bytemap *x, int cpuid, u32 offset) -{ - offset >>= 2; - BUG_ON(offset > (VGIC_NR_IRQS / 4)); - if (offset < 4) - return x->percpu[cpuid] + offset; - else - return x->shared + offset - 8; -} - -#define VGIC_CFG_LEVEL 0 -#define VGIC_CFG_EDGE 1 - -static bool vgic_irq_is_edge(struct kvm_vcpu *vcpu, int irq) -{ - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - int irq_val; - - irq_val = vgic_bitmap_get_irq_val(&dist->irq_cfg, vcpu->vcpu_id, irq); - return irq_val == VGIC_CFG_EDGE; -} - -static int vgic_irq_is_enabled(struct kvm_vcpu *vcpu, int irq) -{ - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - - return vgic_bitmap_get_irq_val(&dist->irq_enabled, vcpu->vcpu_id, irq); -} - -static int vgic_irq_is_active(struct kvm_vcpu *vcpu, int irq) -{ - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - - return vgic_bitmap_get_irq_val(&dist->irq_active, vcpu->vcpu_id, irq); -} - -static void vgic_irq_set_active(struct kvm_vcpu *vcpu, int irq) -{ - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - - vgic_bitmap_set_irq_val(&dist->irq_active, vcpu->vcpu_id, irq, 1); -} - -static void vgic_irq_clear_active(struct kvm_vcpu *vcpu, int irq) -{ - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - - vgic_bitmap_set_irq_val(&dist->irq_active, vcpu->vcpu_id, irq, 0); -} - -static int vgic_dist_irq_is_pending(struct kvm_vcpu *vcpu, int irq) -{ - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - - return vgic_bitmap_get_irq_val(&dist->irq_state, vcpu->vcpu_id, irq); -} - -static void vgic_dist_irq_set(struct kvm_vcpu *vcpu, int irq) -{ - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - - vgic_bitmap_set_irq_val(&dist->irq_state, vcpu->vcpu_id, irq, 1); -} - -static void vgic_dist_irq_clear(struct kvm_vcpu *vcpu, int irq) -{ - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - - vgic_bitmap_set_irq_val(&dist->irq_state, vcpu->vcpu_id, irq, 0); -} - -static void vgic_cpu_irq_set(struct kvm_vcpu *vcpu, int irq) -{ - if (irq < VGIC_NR_PRIVATE_IRQS) - set_bit(irq, vcpu->arch.vgic_cpu.pending_percpu); - else - set_bit(irq - VGIC_NR_PRIVATE_IRQS, - vcpu->arch.vgic_cpu.pending_shared); -} - -static void vgic_cpu_irq_clear(struct kvm_vcpu *vcpu, int irq) -{ - if (irq < VGIC_NR_PRIVATE_IRQS) - clear_bit(irq, vcpu->arch.vgic_cpu.pending_percpu); - else - clear_bit(irq - VGIC_NR_PRIVATE_IRQS, - vcpu->arch.vgic_cpu.pending_shared); -} - -static u32 mmio_data_read(struct kvm_exit_mmio *mmio, u32 mask) -{ - return *((u32 *)mmio->data) & mask; -} - -static void mmio_data_write(struct kvm_exit_mmio *mmio, u32 mask, u32 value) -{ - *((u32 *)mmio->data) = value & mask; -} - -/** - * vgic_reg_access - access vgic register - * @mmio: pointer to the data describing the mmio access - * @reg: pointer to the virtual backing of vgic distributor data - * @offset: least significant 2 bits used for word offset - * @mode: ACCESS_ mode (see defines above) - * - * Helper to make vgic register access easier using one of the access - * modes defined for vgic register access - * (read,raz,write-ignored,setbit,clearbit,write) - */ -static void vgic_reg_access(struct kvm_exit_mmio *mmio, u32 *reg, - phys_addr_t offset, int mode) -{ - int word_offset = (offset & 3) * 8; - u32 mask = (1UL << (mmio->len * 8)) - 1; - u32 regval; - - /* - * Any alignment fault should have been delivered to the guest - * directly (ARM ARM B3.12.7 "Prioritization of aborts"). - */ - - if (reg) { - regval = *reg; - } else { - BUG_ON(mode != (ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED)); - regval = 0; - } - - if (mmio->is_write) { - u32 data = mmio_data_read(mmio, mask) << word_offset; - switch (ACCESS_WRITE_MASK(mode)) { - case ACCESS_WRITE_IGNORED: - return; - - case ACCESS_WRITE_SETBIT: - regval |= data; - break; - - case ACCESS_WRITE_CLEARBIT: - regval &= ~data; - break; - - case ACCESS_WRITE_VALUE: - regval = (regval & ~(mask << word_offset)) | data; - break; - } - *reg = regval; - } else { - switch (ACCESS_READ_MASK(mode)) { - case ACCESS_READ_RAZ: - regval = 0; - /* fall through */ - - case ACCESS_READ_VALUE: - mmio_data_write(mmio, mask, regval >> word_offset); - } - } -} - -static bool handle_mmio_misc(struct kvm_vcpu *vcpu, - struct kvm_exit_mmio *mmio, phys_addr_t offset) -{ - u32 reg; - u32 word_offset = offset & 3; - - switch (offset & ~3) { - case 0: /* CTLR */ - reg = vcpu->kvm->arch.vgic.enabled; - vgic_reg_access(mmio, ®, word_offset, - ACCESS_READ_VALUE | ACCESS_WRITE_VALUE); - if (mmio->is_write) { - vcpu->kvm->arch.vgic.enabled = reg & 1; - vgic_update_state(vcpu->kvm); - return true; - } - break; - - case 4: /* TYPER */ - reg = (atomic_read(&vcpu->kvm->online_vcpus) - 1) << 5; - reg |= (VGIC_NR_IRQS >> 5) - 1; - vgic_reg_access(mmio, ®, word_offset, - ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED); - break; - - case 8: /* IIDR */ - reg = 0x4B00043B; - vgic_reg_access(mmio, ®, word_offset, - ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED); - break; - } - - return false; -} - -static bool handle_mmio_raz_wi(struct kvm_vcpu *vcpu, - struct kvm_exit_mmio *mmio, phys_addr_t offset) -{ - vgic_reg_access(mmio, NULL, offset, - ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED); - return false; -} - -static bool handle_mmio_set_enable_reg(struct kvm_vcpu *vcpu, - struct kvm_exit_mmio *mmio, - phys_addr_t offset) -{ - u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_enabled, - vcpu->vcpu_id, offset); - vgic_reg_access(mmio, reg, offset, - ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT); - if (mmio->is_write) { - vgic_update_state(vcpu->kvm); - return true; - } - - return false; -} - -static bool handle_mmio_clear_enable_reg(struct kvm_vcpu *vcpu, - struct kvm_exit_mmio *mmio, - phys_addr_t offset) -{ - u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_enabled, - vcpu->vcpu_id, offset); - vgic_reg_access(mmio, reg, offset, - ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT); - if (mmio->is_write) { - if (offset < 4) /* Force SGI enabled */ - *reg |= 0xffff; - vgic_retire_disabled_irqs(vcpu); - vgic_update_state(vcpu->kvm); - return true; - } - - return false; -} - -static bool handle_mmio_set_pending_reg(struct kvm_vcpu *vcpu, - struct kvm_exit_mmio *mmio, - phys_addr_t offset) -{ - u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_state, - vcpu->vcpu_id, offset); - vgic_reg_access(mmio, reg, offset, - ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT); - if (mmio->is_write) { - vgic_update_state(vcpu->kvm); - return true; - } - - return false; -} - -static bool handle_mmio_clear_pending_reg(struct kvm_vcpu *vcpu, - struct kvm_exit_mmio *mmio, - phys_addr_t offset) -{ - u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_state, - vcpu->vcpu_id, offset); - vgic_reg_access(mmio, reg, offset, - ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT); - if (mmio->is_write) { - vgic_update_state(vcpu->kvm); - return true; - } - - return false; -} - -static bool handle_mmio_priority_reg(struct kvm_vcpu *vcpu, - struct kvm_exit_mmio *mmio, - phys_addr_t offset) -{ - u32 *reg = vgic_bytemap_get_reg(&vcpu->kvm->arch.vgic.irq_priority, - vcpu->vcpu_id, offset); - vgic_reg_access(mmio, reg, offset, - ACCESS_READ_VALUE | ACCESS_WRITE_VALUE); - return false; -} - -#define GICD_ITARGETSR_SIZE 32 -#define GICD_CPUTARGETS_BITS 8 -#define GICD_IRQS_PER_ITARGETSR (GICD_ITARGETSR_SIZE / GICD_CPUTARGETS_BITS) -static u32 vgic_get_target_reg(struct kvm *kvm, int irq) -{ - struct vgic_dist *dist = &kvm->arch.vgic; - struct kvm_vcpu *vcpu; - int i, c; - unsigned long *bmap; - u32 val = 0; - - irq -= VGIC_NR_PRIVATE_IRQS; - - kvm_for_each_vcpu(c, vcpu, kvm) { - bmap = vgic_bitmap_get_shared_map(&dist->irq_spi_target[c]); - for (i = 0; i < GICD_IRQS_PER_ITARGETSR; i++) - if (test_bit(irq + i, bmap)) - val |= 1 << (c + i * 8); - } - - return val; -} - -static void vgic_set_target_reg(struct kvm *kvm, u32 val, int irq) -{ - struct vgic_dist *dist = &kvm->arch.vgic; - struct kvm_vcpu *vcpu; - int i, c; - unsigned long *bmap; - u32 target; - - irq -= VGIC_NR_PRIVATE_IRQS; - - /* - * Pick the LSB in each byte. This ensures we target exactly - * one vcpu per IRQ. If the byte is null, assume we target - * CPU0. - */ - for (i = 0; i < GICD_IRQS_PER_ITARGETSR; i++) { - int shift = i * GICD_CPUTARGETS_BITS; - target = ffs((val >> shift) & 0xffU); - target = target ? (target - 1) : 0; - dist->irq_spi_cpu[irq + i] = target; - kvm_for_each_vcpu(c, vcpu, kvm) { - bmap = vgic_bitmap_get_shared_map(&dist->irq_spi_target[c]); - if (c == target) - set_bit(irq + i, bmap); - else - clear_bit(irq + i, bmap); - } - } -} - -static bool handle_mmio_target_reg(struct kvm_vcpu *vcpu, - struct kvm_exit_mmio *mmio, - phys_addr_t offset) -{ - u32 reg; - - /* We treat the banked interrupts targets as read-only */ - if (offset < 32) { - u32 roreg = 1 << vcpu->vcpu_id; - roreg |= roreg << 8; - roreg |= roreg << 16; - - vgic_reg_access(mmio, &roreg, offset, - ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED); - return false; - } - - reg = vgic_get_target_reg(vcpu->kvm, offset & ~3U); - vgic_reg_access(mmio, ®, offset, - ACCESS_READ_VALUE | ACCESS_WRITE_VALUE); - if (mmio->is_write) { - vgic_set_target_reg(vcpu->kvm, reg, offset & ~3U); - vgic_update_state(vcpu->kvm); - return true; - } - - return false; -} - -static u32 vgic_cfg_expand(u16 val) -{ - u32 res = 0; - int i; - - /* - * Turn a 16bit value like abcd...mnop into a 32bit word - * a0b0c0d0...m0n0o0p0, which is what the HW cfg register is. - */ - for (i = 0; i < 16; i++) - res |= ((val >> i) & VGIC_CFG_EDGE) << (2 * i + 1); - - return res; -} - -static u16 vgic_cfg_compress(u32 val) -{ - u16 res = 0; - int i; - - /* - * Turn a 32bit word a0b0c0d0...m0n0o0p0 into 16bit value like - * abcd...mnop which is what we really care about. - */ - for (i = 0; i < 16; i++) - res |= ((val >> (i * 2 + 1)) & VGIC_CFG_EDGE) << i; - - return res; -} - -/* - * The distributor uses 2 bits per IRQ for the CFG register, but the - * LSB is always 0. As such, we only keep the upper bit, and use the - * two above functions to compress/expand the bits - */ -static bool handle_mmio_cfg_reg(struct kvm_vcpu *vcpu, - struct kvm_exit_mmio *mmio, phys_addr_t offset) -{ - u32 val; - u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_cfg, - vcpu->vcpu_id, offset >> 1); - if (offset & 2) - val = *reg >> 16; - else - val = *reg & 0xffff; - - val = vgic_cfg_expand(val); - vgic_reg_access(mmio, &val, offset, - ACCESS_READ_VALUE | ACCESS_WRITE_VALUE); - if (mmio->is_write) { - if (offset < 4) { - *reg = ~0U; /* Force PPIs/SGIs to 1 */ - return false; - } - - val = vgic_cfg_compress(val); - if (offset & 2) { - *reg &= 0xffff; - *reg |= val << 16; - } else { - *reg &= 0xffff << 16; - *reg |= val; - } - } - - return false; -} - -static bool handle_mmio_sgi_reg(struct kvm_vcpu *vcpu, - struct kvm_exit_mmio *mmio, phys_addr_t offset) -{ - u32 reg; - vgic_reg_access(mmio, ®, offset, - ACCESS_READ_RAZ | ACCESS_WRITE_VALUE); - if (mmio->is_write) { - vgic_dispatch_sgi(vcpu, reg); - vgic_update_state(vcpu->kvm); - return true; - } - - return false; -} - -/* - * I would have liked to use the kvm_bus_io_*() API instead, but it - * cannot cope with banked registers (only the VM pointer is passed - * around, and we need the vcpu). One of these days, someone please - * fix it! - */ -struct mmio_range { - phys_addr_t base; - unsigned long len; - bool (*handle_mmio)(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio, - phys_addr_t offset); -}; - -static const struct mmio_range vgic_ranges[] = { - { - .base = GIC_DIST_CTRL, - .len = 12, - .handle_mmio = handle_mmio_misc, - }, - { - .base = GIC_DIST_IGROUP, - .len = VGIC_NR_IRQS / 8, - .handle_mmio = handle_mmio_raz_wi, - }, - { - .base = GIC_DIST_ENABLE_SET, - .len = VGIC_NR_IRQS / 8, - .handle_mmio = handle_mmio_set_enable_reg, - }, - { - .base = GIC_DIST_ENABLE_CLEAR, - .len = VGIC_NR_IRQS / 8, - .handle_mmio = handle_mmio_clear_enable_reg, - }, - { - .base = GIC_DIST_PENDING_SET, - .len = VGIC_NR_IRQS / 8, - .handle_mmio = handle_mmio_set_pending_reg, - }, - { - .base = GIC_DIST_PENDING_CLEAR, - .len = VGIC_NR_IRQS / 8, - .handle_mmio = handle_mmio_clear_pending_reg, - }, - { - .base = GIC_DIST_ACTIVE_SET, - .len = VGIC_NR_IRQS / 8, - .handle_mmio = handle_mmio_raz_wi, - }, - { - .base = GIC_DIST_ACTIVE_CLEAR, - .len = VGIC_NR_IRQS / 8, - .handle_mmio = handle_mmio_raz_wi, - }, - { - .base = GIC_DIST_PRI, - .len = VGIC_NR_IRQS, - .handle_mmio = handle_mmio_priority_reg, - }, - { - .base = GIC_DIST_TARGET, - .len = VGIC_NR_IRQS, - .handle_mmio = handle_mmio_target_reg, - }, - { - .base = GIC_DIST_CONFIG, - .len = VGIC_NR_IRQS / 4, - .handle_mmio = handle_mmio_cfg_reg, - }, - { - .base = GIC_DIST_SOFTINT, - .len = 4, - .handle_mmio = handle_mmio_sgi_reg, - }, - {} -}; - -static const -struct mmio_range *find_matching_range(const struct mmio_range *ranges, - struct kvm_exit_mmio *mmio, - phys_addr_t base) -{ - const struct mmio_range *r = ranges; - phys_addr_t addr = mmio->phys_addr - base; - - while (r->len) { - if (addr >= r->base && - (addr + mmio->len) <= (r->base + r->len)) - return r; - r++; - } - - return NULL; -} - -/** - * vgic_handle_mmio - handle an in-kernel MMIO access - * @vcpu: pointer to the vcpu performing the access - * @run: pointer to the kvm_run structure - * @mmio: pointer to the data describing the access - * - * returns true if the MMIO access has been performed in kernel space, - * and false if it needs to be emulated in user space. - */ -bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run, - struct kvm_exit_mmio *mmio) -{ - const struct mmio_range *range; - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - unsigned long base = dist->vgic_dist_base; - bool updated_state; - unsigned long offset; - - if (!irqchip_in_kernel(vcpu->kvm) || - mmio->phys_addr < base || - (mmio->phys_addr + mmio->len) > (base + KVM_VGIC_V2_DIST_SIZE)) - return false; - - /* We don't support ldrd / strd or ldm / stm to the emulated vgic */ - if (mmio->len > 4) { - kvm_inject_dabt(vcpu, mmio->phys_addr); - return true; - } - - range = find_matching_range(vgic_ranges, mmio, base); - if (unlikely(!range || !range->handle_mmio)) { - pr_warn("Unhandled access %d %08llx %d\n", - mmio->is_write, mmio->phys_addr, mmio->len); - return false; - } - - spin_lock(&vcpu->kvm->arch.vgic.lock); - offset = mmio->phys_addr - range->base - base; - updated_state = range->handle_mmio(vcpu, mmio, offset); - spin_unlock(&vcpu->kvm->arch.vgic.lock); - kvm_prepare_mmio(run, mmio); - kvm_handle_mmio_return(vcpu, run); - - if (updated_state) - vgic_kick_vcpus(vcpu->kvm); - - return true; -} - -static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg) -{ - struct kvm *kvm = vcpu->kvm; - struct vgic_dist *dist = &kvm->arch.vgic; - int nrcpus = atomic_read(&kvm->online_vcpus); - u8 target_cpus; - int sgi, mode, c, vcpu_id; - - vcpu_id = vcpu->vcpu_id; - - sgi = reg & 0xf; - target_cpus = (reg >> 16) & 0xff; - mode = (reg >> 24) & 3; - - switch (mode) { - case 0: - if (!target_cpus) - return; - - case 1: - target_cpus = ((1 << nrcpus) - 1) & ~(1 << vcpu_id) & 0xff; - break; - - case 2: - target_cpus = 1 << vcpu_id; - break; - } - - kvm_for_each_vcpu(c, vcpu, kvm) { - if (target_cpus & 1) { - /* Flag the SGI as pending */ - vgic_dist_irq_set(vcpu, sgi); - dist->irq_sgi_sources[c][sgi] |= 1 << vcpu_id; - kvm_debug("SGI%d from CPU%d to CPU%d\n", sgi, vcpu_id, c); - } - - target_cpus >>= 1; - } -} - -static int compute_pending_for_cpu(struct kvm_vcpu *vcpu) -{ - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - unsigned long *pending, *enabled, *pend_percpu, *pend_shared; - unsigned long pending_private, pending_shared; - int vcpu_id; - - vcpu_id = vcpu->vcpu_id; - pend_percpu = vcpu->arch.vgic_cpu.pending_percpu; - pend_shared = vcpu->arch.vgic_cpu.pending_shared; - - pending = vgic_bitmap_get_cpu_map(&dist->irq_state, vcpu_id); - enabled = vgic_bitmap_get_cpu_map(&dist->irq_enabled, vcpu_id); - bitmap_and(pend_percpu, pending, enabled, VGIC_NR_PRIVATE_IRQS); - - pending = vgic_bitmap_get_shared_map(&dist->irq_state); - enabled = vgic_bitmap_get_shared_map(&dist->irq_enabled); - bitmap_and(pend_shared, pending, enabled, VGIC_NR_SHARED_IRQS); - bitmap_and(pend_shared, pend_shared, - vgic_bitmap_get_shared_map(&dist->irq_spi_target[vcpu_id]), - VGIC_NR_SHARED_IRQS); - - pending_private = find_first_bit(pend_percpu, VGIC_NR_PRIVATE_IRQS); - pending_shared = find_first_bit(pend_shared, VGIC_NR_SHARED_IRQS); - return (pending_private < VGIC_NR_PRIVATE_IRQS || - pending_shared < VGIC_NR_SHARED_IRQS); -} - -/* - * Update the interrupt state and determine which CPUs have pending - * interrupts. Must be called with distributor lock held. - */ -static void vgic_update_state(struct kvm *kvm) -{ - struct vgic_dist *dist = &kvm->arch.vgic; - struct kvm_vcpu *vcpu; - int c; - - if (!dist->enabled) { - set_bit(0, &dist->irq_pending_on_cpu); - return; - } - - kvm_for_each_vcpu(c, vcpu, kvm) { - if (compute_pending_for_cpu(vcpu)) { - pr_debug("CPU%d has pending interrupts\n", c); - set_bit(c, &dist->irq_pending_on_cpu); - } - } -} - -#define LR_CPUID(lr) \ - (((lr) & GICH_LR_PHYSID_CPUID) >> GICH_LR_PHYSID_CPUID_SHIFT) -#define MK_LR_PEND(src, irq) \ - (GICH_LR_PENDING_BIT | ((src) << GICH_LR_PHYSID_CPUID_SHIFT) | (irq)) - -/* - * An interrupt may have been disabled after being made pending on the - * CPU interface (the classic case is a timer running while we're - * rebooting the guest - the interrupt would kick as soon as the CPU - * interface gets enabled, with deadly consequences). - * - * The solution is to examine already active LRs, and check the - * interrupt is still enabled. If not, just retire it. - */ -static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu) -{ - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - int lr; - - for_each_set_bit(lr, vgic_cpu->lr_used, vgic_cpu->nr_lr) { - int irq = vgic_cpu->vgic_lr[lr] & GICH_LR_VIRTUALID; - - if (!vgic_irq_is_enabled(vcpu, irq)) { - vgic_cpu->vgic_irq_lr_map[irq] = LR_EMPTY; - clear_bit(lr, vgic_cpu->lr_used); - vgic_cpu->vgic_lr[lr] &= ~GICH_LR_STATE; - if (vgic_irq_is_active(vcpu, irq)) - vgic_irq_clear_active(vcpu, irq); - } - } -} - -/* - * Queue an interrupt to a CPU virtual interface. Return true on success, - * or false if it wasn't possible to queue it. - */ -static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq) -{ - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - int lr; - - /* Sanitize the input... */ - BUG_ON(sgi_source_id & ~7); - BUG_ON(sgi_source_id && irq >= VGIC_NR_SGIS); - BUG_ON(irq >= VGIC_NR_IRQS); - - kvm_debug("Queue IRQ%d\n", irq); - - lr = vgic_cpu->vgic_irq_lr_map[irq]; - - /* Do we have an active interrupt for the same CPUID? */ - if (lr != LR_EMPTY && - (LR_CPUID(vgic_cpu->vgic_lr[lr]) == sgi_source_id)) { - kvm_debug("LR%d piggyback for IRQ%d %x\n", - lr, irq, vgic_cpu->vgic_lr[lr]); - BUG_ON(!test_bit(lr, vgic_cpu->lr_used)); - vgic_cpu->vgic_lr[lr] |= GICH_LR_PENDING_BIT; - return true; - } - - /* Try to use another LR for this interrupt */ - lr = find_first_zero_bit((unsigned long *)vgic_cpu->lr_used, - vgic_cpu->nr_lr); - if (lr >= vgic_cpu->nr_lr) - return false; - - kvm_debug("LR%d allocated for IRQ%d %x\n", lr, irq, sgi_source_id); - vgic_cpu->vgic_lr[lr] = MK_LR_PEND(sgi_source_id, irq); - vgic_cpu->vgic_irq_lr_map[irq] = lr; - set_bit(lr, vgic_cpu->lr_used); - - if (!vgic_irq_is_edge(vcpu, irq)) - vgic_cpu->vgic_lr[lr] |= GICH_LR_EOI; - - return true; -} - -static bool vgic_queue_sgi(struct kvm_vcpu *vcpu, int irq) -{ - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - unsigned long sources; - int vcpu_id = vcpu->vcpu_id; - int c; - - sources = dist->irq_sgi_sources[vcpu_id][irq]; - - for_each_set_bit(c, &sources, VGIC_MAX_CPUS) { - if (vgic_queue_irq(vcpu, c, irq)) - clear_bit(c, &sources); - } - - dist->irq_sgi_sources[vcpu_id][irq] = sources; - - /* - * If the sources bitmap has been cleared it means that we - * could queue all the SGIs onto link registers (see the - * clear_bit above), and therefore we are done with them in - * our emulated gic and can get rid of them. - */ - if (!sources) { - vgic_dist_irq_clear(vcpu, irq); - vgic_cpu_irq_clear(vcpu, irq); - return true; - } - - return false; -} - -static bool vgic_queue_hwirq(struct kvm_vcpu *vcpu, int irq) -{ - if (vgic_irq_is_active(vcpu, irq)) - return true; /* level interrupt, already queued */ - - if (vgic_queue_irq(vcpu, 0, irq)) { - if (vgic_irq_is_edge(vcpu, irq)) { - vgic_dist_irq_clear(vcpu, irq); - vgic_cpu_irq_clear(vcpu, irq); - } else { - vgic_irq_set_active(vcpu, irq); - } - - return true; - } - - return false; -} - -/* - * Fill the list registers with pending interrupts before running the - * guest. - */ -static void __kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) -{ - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - int i, vcpu_id; - int overflow = 0; - - vcpu_id = vcpu->vcpu_id; - - /* - * We may not have any pending interrupt, or the interrupts - * may have been serviced from another vcpu. In all cases, - * move along. - */ - if (!kvm_vgic_vcpu_pending_irq(vcpu)) { - pr_debug("CPU%d has no pending interrupt\n", vcpu_id); - goto epilog; - } - - /* SGIs */ - for_each_set_bit(i, vgic_cpu->pending_percpu, VGIC_NR_SGIS) { - if (!vgic_queue_sgi(vcpu, i)) - overflow = 1; - } - - /* PPIs */ - for_each_set_bit_from(i, vgic_cpu->pending_percpu, VGIC_NR_PRIVATE_IRQS) { - if (!vgic_queue_hwirq(vcpu, i)) - overflow = 1; - } - - /* SPIs */ - for_each_set_bit(i, vgic_cpu->pending_shared, VGIC_NR_SHARED_IRQS) { - if (!vgic_queue_hwirq(vcpu, i + VGIC_NR_PRIVATE_IRQS)) - overflow = 1; - } - -epilog: - if (overflow) { - vgic_cpu->vgic_hcr |= GICH_HCR_UIE; - } else { - vgic_cpu->vgic_hcr &= ~GICH_HCR_UIE; - /* - * We're about to run this VCPU, and we've consumed - * everything the distributor had in store for - * us. Claim we don't have anything pending. We'll - * adjust that if needed while exiting. - */ - clear_bit(vcpu_id, &dist->irq_pending_on_cpu); - } -} - -static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) -{ - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - bool level_pending = false; - - kvm_debug("MISR = %08x\n", vgic_cpu->vgic_misr); - - if (vgic_cpu->vgic_misr & GICH_MISR_EOI) { - /* - * Some level interrupts have been EOIed. Clear their - * active bit. - */ - int lr, irq; - - for_each_set_bit(lr, (unsigned long *)vgic_cpu->vgic_eisr, - vgic_cpu->nr_lr) { - irq = vgic_cpu->vgic_lr[lr] & GICH_LR_VIRTUALID; - - vgic_irq_clear_active(vcpu, irq); - vgic_cpu->vgic_lr[lr] &= ~GICH_LR_EOI; - - /* Any additional pending interrupt? */ - if (vgic_dist_irq_is_pending(vcpu, irq)) { - vgic_cpu_irq_set(vcpu, irq); - level_pending = true; - } else { - vgic_cpu_irq_clear(vcpu, irq); - } - - /* - * Despite being EOIed, the LR may not have - * been marked as empty. - */ - set_bit(lr, (unsigned long *)vgic_cpu->vgic_elrsr); - vgic_cpu->vgic_lr[lr] &= ~GICH_LR_ACTIVE_BIT; - } - } - - if (vgic_cpu->vgic_misr & GICH_MISR_U) - vgic_cpu->vgic_hcr &= ~GICH_HCR_UIE; - - return level_pending; -} - -/* - * Sync back the VGIC state after a guest run. The distributor lock is - * needed so we don't get preempted in the middle of the state processing. - */ -static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) -{ - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - int lr, pending; - bool level_pending; - - level_pending = vgic_process_maintenance(vcpu); - - /* Clear mappings for empty LRs */ - for_each_set_bit(lr, (unsigned long *)vgic_cpu->vgic_elrsr, - vgic_cpu->nr_lr) { - int irq; - - if (!test_and_clear_bit(lr, vgic_cpu->lr_used)) - continue; - - irq = vgic_cpu->vgic_lr[lr] & GICH_LR_VIRTUALID; - - BUG_ON(irq >= VGIC_NR_IRQS); - vgic_cpu->vgic_irq_lr_map[irq] = LR_EMPTY; - } - - /* Check if we still have something up our sleeve... */ - pending = find_first_zero_bit((unsigned long *)vgic_cpu->vgic_elrsr, - vgic_cpu->nr_lr); - if (level_pending || pending < vgic_cpu->nr_lr) - set_bit(vcpu->vcpu_id, &dist->irq_pending_on_cpu); -} - -void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) -{ - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - - if (!irqchip_in_kernel(vcpu->kvm)) - return; - - spin_lock(&dist->lock); - __kvm_vgic_flush_hwstate(vcpu); - spin_unlock(&dist->lock); -} - -void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) -{ - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - - if (!irqchip_in_kernel(vcpu->kvm)) - return; - - spin_lock(&dist->lock); - __kvm_vgic_sync_hwstate(vcpu); - spin_unlock(&dist->lock); -} - -int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu) -{ - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - - if (!irqchip_in_kernel(vcpu->kvm)) - return 0; - - return test_bit(vcpu->vcpu_id, &dist->irq_pending_on_cpu); -} - -static void vgic_kick_vcpus(struct kvm *kvm) -{ - struct kvm_vcpu *vcpu; - int c; - - /* - * We've injected an interrupt, time to find out who deserves - * a good kick... - */ - kvm_for_each_vcpu(c, vcpu, kvm) { - if (kvm_vgic_vcpu_pending_irq(vcpu)) - kvm_vcpu_kick(vcpu); - } -} - -static int vgic_validate_injection(struct kvm_vcpu *vcpu, int irq, int level) -{ - int is_edge = vgic_irq_is_edge(vcpu, irq); - int state = vgic_dist_irq_is_pending(vcpu, irq); - - /* - * Only inject an interrupt if: - * - edge triggered and we have a rising edge - * - level triggered and we change level - */ - if (is_edge) - return level > state; - else - return level != state; -} - -static bool vgic_update_irq_state(struct kvm *kvm, int cpuid, - unsigned int irq_num, bool level) -{ - struct vgic_dist *dist = &kvm->arch.vgic; - struct kvm_vcpu *vcpu; - int is_edge, is_level; - int enabled; - bool ret = true; - - spin_lock(&dist->lock); - - vcpu = kvm_get_vcpu(kvm, cpuid); - is_edge = vgic_irq_is_edge(vcpu, irq_num); - is_level = !is_edge; - - if (!vgic_validate_injection(vcpu, irq_num, level)) { - ret = false; - goto out; - } - - if (irq_num >= VGIC_NR_PRIVATE_IRQS) { - cpuid = dist->irq_spi_cpu[irq_num - VGIC_NR_PRIVATE_IRQS]; - vcpu = kvm_get_vcpu(kvm, cpuid); - } - - kvm_debug("Inject IRQ%d level %d CPU%d\n", irq_num, level, cpuid); - - if (level) - vgic_dist_irq_set(vcpu, irq_num); - else - vgic_dist_irq_clear(vcpu, irq_num); - - enabled = vgic_irq_is_enabled(vcpu, irq_num); - - if (!enabled) { - ret = false; - goto out; - } - - if (is_level && vgic_irq_is_active(vcpu, irq_num)) { - /* - * Level interrupt in progress, will be picked up - * when EOId. - */ - ret = false; - goto out; - } - - if (level) { - vgic_cpu_irq_set(vcpu, irq_num); - set_bit(cpuid, &dist->irq_pending_on_cpu); - } - -out: - spin_unlock(&dist->lock); - - return ret; -} - -/** - * kvm_vgic_inject_irq - Inject an IRQ from a device to the vgic - * @kvm: The VM structure pointer - * @cpuid: The CPU for PPIs - * @irq_num: The IRQ number that is assigned to the device - * @level: Edge-triggered: true: to trigger the interrupt - * false: to ignore the call - * Level-sensitive true: activates an interrupt - * false: deactivates an interrupt - * - * The GIC is not concerned with devices being active-LOW or active-HIGH for - * level-sensitive interrupts. You can think of the level parameter as 1 - * being HIGH and 0 being LOW and all devices being active-HIGH. - */ -int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num, - bool level) -{ - if (vgic_update_irq_state(kvm, cpuid, irq_num, level)) - vgic_kick_vcpus(kvm); - - return 0; -} - -static irqreturn_t vgic_maintenance_handler(int irq, void *data) -{ - /* - * We cannot rely on the vgic maintenance interrupt to be - * delivered synchronously. This means we can only use it to - * exit the VM, and we perform the handling of EOIed - * interrupts on the exit path (see vgic_process_maintenance). - */ - return IRQ_HANDLED; -} - -int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) -{ - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - int i; - - if (!irqchip_in_kernel(vcpu->kvm)) - return 0; - - if (vcpu->vcpu_id >= VGIC_MAX_CPUS) - return -EBUSY; - - for (i = 0; i < VGIC_NR_IRQS; i++) { - if (i < VGIC_NR_PPIS) - vgic_bitmap_set_irq_val(&dist->irq_enabled, - vcpu->vcpu_id, i, 1); - if (i < VGIC_NR_PRIVATE_IRQS) - vgic_bitmap_set_irq_val(&dist->irq_cfg, - vcpu->vcpu_id, i, VGIC_CFG_EDGE); - - vgic_cpu->vgic_irq_lr_map[i] = LR_EMPTY; - } - - /* - * By forcing VMCR to zero, the GIC will restore the binary - * points to their reset values. Anything else resets to zero - * anyway. - */ - vgic_cpu->vgic_vmcr = 0; - - vgic_cpu->nr_lr = vgic_nr_lr; - vgic_cpu->vgic_hcr = GICH_HCR_EN; /* Get the show on the road... */ - - return 0; -} - -static void vgic_init_maintenance_interrupt(void *info) -{ - enable_percpu_irq(vgic_maint_irq, 0); -} - -static int vgic_cpu_notify(struct notifier_block *self, - unsigned long action, void *cpu) -{ - switch (action) { - case CPU_STARTING: - case CPU_STARTING_FROZEN: - vgic_init_maintenance_interrupt(NULL); - break; - case CPU_DYING: - case CPU_DYING_FROZEN: - disable_percpu_irq(vgic_maint_irq); - break; - } - - return NOTIFY_OK; -} - -static struct notifier_block vgic_cpu_nb = { - .notifier_call = vgic_cpu_notify, -}; - -int kvm_vgic_hyp_init(void) -{ - int ret; - struct resource vctrl_res; - struct resource vcpu_res; - - vgic_node = of_find_compatible_node(NULL, NULL, "arm,cortex-a15-gic"); - if (!vgic_node) { - kvm_err("error: no compatible vgic node in DT\n"); - return -ENODEV; - } - - vgic_maint_irq = irq_of_parse_and_map(vgic_node, 0); - if (!vgic_maint_irq) { - kvm_err("error getting vgic maintenance irq from DT\n"); - ret = -ENXIO; - goto out; - } - - ret = request_percpu_irq(vgic_maint_irq, vgic_maintenance_handler, - "vgic", kvm_get_running_vcpus()); - if (ret) { - kvm_err("Cannot register interrupt %d\n", vgic_maint_irq); - goto out; - } - - ret = register_cpu_notifier(&vgic_cpu_nb); - if (ret) { - kvm_err("Cannot register vgic CPU notifier\n"); - goto out_free_irq; - } - - ret = of_address_to_resource(vgic_node, 2, &vctrl_res); - if (ret) { - kvm_err("Cannot obtain VCTRL resource\n"); - goto out_free_irq; - } - - vgic_vctrl_base = of_iomap(vgic_node, 2); - if (!vgic_vctrl_base) { - kvm_err("Cannot ioremap VCTRL\n"); - ret = -ENOMEM; - goto out_free_irq; - } - - vgic_nr_lr = readl_relaxed(vgic_vctrl_base + GICH_VTR); - vgic_nr_lr = (vgic_nr_lr & 0x3f) + 1; - - ret = create_hyp_io_mappings(vgic_vctrl_base, - vgic_vctrl_base + resource_size(&vctrl_res), - vctrl_res.start); - if (ret) { - kvm_err("Cannot map VCTRL into hyp\n"); - goto out_unmap; - } - - kvm_info("%s@%llx IRQ%d\n", vgic_node->name, - vctrl_res.start, vgic_maint_irq); - on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1); - - if (of_address_to_resource(vgic_node, 3, &vcpu_res)) { - kvm_err("Cannot obtain VCPU resource\n"); - ret = -ENXIO; - goto out_unmap; - } - vgic_vcpu_base = vcpu_res.start; - - goto out; - -out_unmap: - iounmap(vgic_vctrl_base); -out_free_irq: - free_percpu_irq(vgic_maint_irq, kvm_get_running_vcpus()); -out: - of_node_put(vgic_node); - return ret; -} - -int kvm_vgic_init(struct kvm *kvm) -{ - int ret = 0, i; - - mutex_lock(&kvm->lock); - - if (vgic_initialized(kvm)) - goto out; - - if (IS_VGIC_ADDR_UNDEF(kvm->arch.vgic.vgic_dist_base) || - IS_VGIC_ADDR_UNDEF(kvm->arch.vgic.vgic_cpu_base)) { - kvm_err("Need to set vgic cpu and dist addresses first\n"); - ret = -ENXIO; - goto out; - } - - ret = kvm_phys_addr_ioremap(kvm, kvm->arch.vgic.vgic_cpu_base, - vgic_vcpu_base, KVM_VGIC_V2_CPU_SIZE); - if (ret) { - kvm_err("Unable to remap VGIC CPU to VCPU\n"); - goto out; - } - - for (i = VGIC_NR_PRIVATE_IRQS; i < VGIC_NR_IRQS; i += 4) - vgic_set_target_reg(kvm, 0, i); - - kvm_timer_init(kvm); - kvm->arch.vgic.ready = true; -out: - mutex_unlock(&kvm->lock); - return ret; -} - -int kvm_vgic_create(struct kvm *kvm) -{ - int ret = 0; - - mutex_lock(&kvm->lock); - - if (atomic_read(&kvm->online_vcpus) || kvm->arch.vgic.vctrl_base) { - ret = -EEXIST; - goto out; - } - - spin_lock_init(&kvm->arch.vgic.lock); - kvm->arch.vgic.vctrl_base = vgic_vctrl_base; - kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF; - kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF; - -out: - mutex_unlock(&kvm->lock); - return ret; -} - -static bool vgic_ioaddr_overlap(struct kvm *kvm) -{ - phys_addr_t dist = kvm->arch.vgic.vgic_dist_base; - phys_addr_t cpu = kvm->arch.vgic.vgic_cpu_base; - - if (IS_VGIC_ADDR_UNDEF(dist) || IS_VGIC_ADDR_UNDEF(cpu)) - return 0; - if ((dist <= cpu && dist + KVM_VGIC_V2_DIST_SIZE > cpu) || - (cpu <= dist && cpu + KVM_VGIC_V2_CPU_SIZE > dist)) - return -EBUSY; - return 0; -} - -static int vgic_ioaddr_assign(struct kvm *kvm, phys_addr_t *ioaddr, - phys_addr_t addr, phys_addr_t size) -{ - int ret; - - if (!IS_VGIC_ADDR_UNDEF(*ioaddr)) - return -EEXIST; - if (addr + size < addr) - return -EINVAL; - - ret = vgic_ioaddr_overlap(kvm); - if (ret) - return ret; - *ioaddr = addr; - return ret; -} - -int kvm_vgic_set_addr(struct kvm *kvm, unsigned long type, u64 addr) -{ - int r = 0; - struct vgic_dist *vgic = &kvm->arch.vgic; - - if (addr & ~KVM_PHYS_MASK) - return -E2BIG; - - if (addr & (SZ_4K - 1)) - return -EINVAL; - - mutex_lock(&kvm->lock); - switch (type) { - case KVM_VGIC_V2_ADDR_TYPE_DIST: - r = vgic_ioaddr_assign(kvm, &vgic->vgic_dist_base, - addr, KVM_VGIC_V2_DIST_SIZE); - break; - case KVM_VGIC_V2_ADDR_TYPE_CPU: - r = vgic_ioaddr_assign(kvm, &vgic->vgic_cpu_base, - addr, KVM_VGIC_V2_CPU_SIZE); - break; - default: - r = -ENODEV; - } - - mutex_unlock(&kvm->lock); - return r; -} diff --git a/arch/arm/mach-davinci/Kconfig b/arch/arm/mach-davinci/Kconfig index a075b3e0c5c7..e026b19b23ea 100644 --- a/arch/arm/mach-davinci/Kconfig +++ b/arch/arm/mach-davinci/Kconfig @@ -40,6 +40,7 @@ config ARCH_DAVINCI_DA850 bool "DA850/OMAP-L138/AM18x based system" select ARCH_DAVINCI_DA8XX select ARCH_HAS_CPUFREQ + select CPU_FREQ_TABLE select CP_INTC config ARCH_DAVINCI_DA8XX diff --git a/arch/arm/mach-davinci/da850.c b/arch/arm/mach-davinci/da850.c index 4d6933848abf..a0d4f6038b60 100644 --- a/arch/arm/mach-davinci/da850.c +++ b/arch/arm/mach-davinci/da850.c @@ -1004,7 +1004,7 @@ static const struct da850_opp da850_opp_96 = { #define OPP(freq) \ { \ - .index = (unsigned int) &da850_opp_##freq, \ + .driver_data = (unsigned int) &da850_opp_##freq, \ .frequency = freq * 1000, \ } @@ -1016,7 +1016,7 @@ static struct cpufreq_frequency_table da850_freq_table[] = { OPP(200), OPP(96), { - .index = 0, + .driver_data = 0, .frequency = CPUFREQ_TABLE_END, }, }; @@ -1044,7 +1044,7 @@ static int da850_set_voltage(unsigned int index) if (!cvdd) return -ENODEV; - opp = (struct da850_opp *) cpufreq_info.freq_table[index].index; + opp = (struct da850_opp *) cpufreq_info.freq_table[index].driver_data; return regulator_set_voltage(cvdd, opp->cvdd_min, opp->cvdd_max); } @@ -1125,7 +1125,7 @@ static int da850_set_pll0rate(struct clk *clk, unsigned long index) struct pll_data *pll = clk->pll_data; int ret; - opp = (struct da850_opp *) cpufreq_info.freq_table[index].index; + opp = (struct da850_opp *) cpufreq_info.freq_table[index].driver_data; prediv = opp->prediv; mult = opp->mult; postdiv = opp->postdiv; diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c index 68be532f8688..5cc92874be7e 100644 --- a/arch/arm/mach-omap2/omap_device.c +++ b/arch/arm/mach-omap2/omap_device.c @@ -588,11 +588,6 @@ static int _od_runtime_suspend(struct device *dev) return ret; } -static int _od_runtime_idle(struct device *dev) -{ - return pm_generic_runtime_idle(dev); -} - static int _od_runtime_resume(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); @@ -648,7 +643,7 @@ static int _od_resume_noirq(struct device *dev) struct dev_pm_domain omap_device_pm_domain = { .ops = { SET_RUNTIME_PM_OPS(_od_runtime_suspend, _od_runtime_resume, - _od_runtime_idle) + NULL) USE_PLATFORM_PM_SLEEP_OPS .suspend_noirq = _od_suspend_noirq, .resume_noirq = _od_resume_noirq, diff --git a/arch/arm/mach-omap2/smartreflex-class3.c b/arch/arm/mach-omap2/smartreflex-class3.c index aee3c8940a30..7a42e1960c3b 100644 --- a/arch/arm/mach-omap2/smartreflex-class3.c +++ b/arch/arm/mach-omap2/smartreflex-class3.c @@ -26,14 +26,14 @@ static int sr_class3_enable(struct omap_sr *sr) } omap_vp_enable(sr->voltdm); - return sr_enable(sr->voltdm, volt); + return sr_enable(sr, volt); } static int sr_class3_disable(struct omap_sr *sr, int is_volt_reset) { - sr_disable_errgen(sr->voltdm); + sr_disable_errgen(sr); omap_vp_disable(sr->voltdm); - sr_disable(sr->voltdm); + sr_disable(sr); if (is_volt_reset) voltdm_reset(sr->voltdm); @@ -42,7 +42,7 @@ static int sr_class3_disable(struct omap_sr *sr, int is_volt_reset) static int sr_class3_configure(struct omap_sr *sr) { - return sr_configure_errgen(sr->voltdm); + return sr_configure_errgen(sr); } /* SR class3 structure */ diff --git a/arch/arm/mach-pxa/Kconfig b/arch/arm/mach-pxa/Kconfig index 96100dbf5a2e..a8427115ee07 100644 --- a/arch/arm/mach-pxa/Kconfig +++ b/arch/arm/mach-pxa/Kconfig @@ -615,12 +615,14 @@ endmenu config PXA25x bool select CPU_XSCALE + select CPU_FREQ_TABLE if CPU_FREQ help Select code specific to PXA21x/25x/26x variants config PXA27x bool select CPU_XSCALE + select CPU_FREQ_TABLE if CPU_FREQ help Select code specific to PXA27x variants @@ -633,6 +635,7 @@ config CPU_PXA26x config PXA3xx bool select CPU_XSC3 + select CPU_FREQ_TABLE if CPU_FREQ help Select code specific to PXA3xx variants diff --git a/arch/arm/mach-s3c24xx/cpufreq-utils.c b/arch/arm/mach-s3c24xx/cpufreq-utils.c index ddd8280e3875..2a0aa5684e72 100644 --- a/arch/arm/mach-s3c24xx/cpufreq-utils.c +++ b/arch/arm/mach-s3c24xx/cpufreq-utils.c @@ -60,5 +60,5 @@ void s3c2410_cpufreq_setrefresh(struct s3c_cpufreq_config *cfg) */ void s3c2410_set_fvco(struct s3c_cpufreq_config *cfg) { - __raw_writel(cfg->pll.index, S3C2410_MPLLCON); + __raw_writel(cfg->pll.driver_data, S3C2410_MPLLCON); } diff --git a/arch/arm/mach-s3c24xx/pll-s3c2410.c b/arch/arm/mach-s3c24xx/pll-s3c2410.c index dcf3420a3271..5e37d368594b 100644 --- a/arch/arm/mach-s3c24xx/pll-s3c2410.c +++ b/arch/arm/mach-s3c24xx/pll-s3c2410.c @@ -33,36 +33,36 @@ #include <plat/cpu-freq-core.h> static struct cpufreq_frequency_table pll_vals_12MHz[] = { - { .frequency = 34000000, .index = PLLVAL(82, 2, 3), }, - { .frequency = 45000000, .index = PLLVAL(82, 1, 3), }, - { .frequency = 51000000, .index = PLLVAL(161, 3, 3), }, - { .frequency = 48000000, .index = PLLVAL(120, 2, 3), }, - { .frequency = 56000000, .index = PLLVAL(142, 2, 3), }, - { .frequency = 68000000, .index = PLLVAL(82, 2, 2), }, - { .frequency = 79000000, .index = PLLVAL(71, 1, 2), }, - { .frequency = 85000000, .index = PLLVAL(105, 2, 2), }, - { .frequency = 90000000, .index = PLLVAL(112, 2, 2), }, - { .frequency = 101000000, .index = PLLVAL(127, 2, 2), }, - { .frequency = 113000000, .index = PLLVAL(105, 1, 2), }, - { .frequency = 118000000, .index = PLLVAL(150, 2, 2), }, - { .frequency = 124000000, .index = PLLVAL(116, 1, 2), }, - { .frequency = 135000000, .index = PLLVAL(82, 2, 1), }, - { .frequency = 147000000, .index = PLLVAL(90, 2, 1), }, - { .frequency = 152000000, .index = PLLVAL(68, 1, 1), }, - { .frequency = 158000000, .index = PLLVAL(71, 1, 1), }, - { .frequency = 170000000, .index = PLLVAL(77, 1, 1), }, - { .frequency = 180000000, .index = PLLVAL(82, 1, 1), }, - { .frequency = 186000000, .index = PLLVAL(85, 1, 1), }, - { .frequency = 192000000, .index = PLLVAL(88, 1, 1), }, - { .frequency = 203000000, .index = PLLVAL(161, 3, 1), }, + { .frequency = 34000000, .driver_data = PLLVAL(82, 2, 3), }, + { .frequency = 45000000, .driver_data = PLLVAL(82, 1, 3), }, + { .frequency = 51000000, .driver_data = PLLVAL(161, 3, 3), }, + { .frequency = 48000000, .driver_data = PLLVAL(120, 2, 3), }, + { .frequency = 56000000, .driver_data = PLLVAL(142, 2, 3), }, + { .frequency = 68000000, .driver_data = PLLVAL(82, 2, 2), }, + { .frequency = 79000000, .driver_data = PLLVAL(71, 1, 2), }, + { .frequency = 85000000, .driver_data = PLLVAL(105, 2, 2), }, + { .frequency = 90000000, .driver_data = PLLVAL(112, 2, 2), }, + { .frequency = 101000000, .driver_data = PLLVAL(127, 2, 2), }, + { .frequency = 113000000, .driver_data = PLLVAL(105, 1, 2), }, + { .frequency = 118000000, .driver_data = PLLVAL(150, 2, 2), }, + { .frequency = 124000000, .driver_data = PLLVAL(116, 1, 2), }, + { .frequency = 135000000, .driver_data = PLLVAL(82, 2, 1), }, + { .frequency = 147000000, .driver_data = PLLVAL(90, 2, 1), }, + { .frequency = 152000000, .driver_data = PLLVAL(68, 1, 1), }, + { .frequency = 158000000, .driver_data = PLLVAL(71, 1, 1), }, + { .frequency = 170000000, .driver_data = PLLVAL(77, 1, 1), }, + { .frequency = 180000000, .driver_data = PLLVAL(82, 1, 1), }, + { .frequency = 186000000, .driver_data = PLLVAL(85, 1, 1), }, + { .frequency = 192000000, .driver_data = PLLVAL(88, 1, 1), }, + { .frequency = 203000000, .driver_data = PLLVAL(161, 3, 1), }, /* 2410A extras */ - { .frequency = 210000000, .index = PLLVAL(132, 2, 1), }, - { .frequency = 226000000, .index = PLLVAL(105, 1, 1), }, - { .frequency = 266000000, .index = PLLVAL(125, 1, 1), }, - { .frequency = 268000000, .index = PLLVAL(126, 1, 1), }, - { .frequency = 270000000, .index = PLLVAL(127, 1, 1), }, + { .frequency = 210000000, .driver_data = PLLVAL(132, 2, 1), }, + { .frequency = 226000000, .driver_data = PLLVAL(105, 1, 1), }, + { .frequency = 266000000, .driver_data = PLLVAL(125, 1, 1), }, + { .frequency = 268000000, .driver_data = PLLVAL(126, 1, 1), }, + { .frequency = 270000000, .driver_data = PLLVAL(127, 1, 1), }, }; static int s3c2410_plls_add(struct device *dev, struct subsys_interface *sif) diff --git a/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c b/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c index 673781758319..a19460e6e7b0 100644 --- a/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c +++ b/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c @@ -21,33 +21,33 @@ #include <plat/cpu-freq-core.h> static struct cpufreq_frequency_table s3c2440_plls_12[] __initdata = { - { .frequency = 75000000, .index = PLLVAL(0x75, 3, 3), }, /* FVco 600.000000 */ - { .frequency = 80000000, .index = PLLVAL(0x98, 4, 3), }, /* FVco 640.000000 */ - { .frequency = 90000000, .index = PLLVAL(0x70, 2, 3), }, /* FVco 720.000000 */ - { .frequency = 100000000, .index = PLLVAL(0x5c, 1, 3), }, /* FVco 800.000000 */ - { .frequency = 110000000, .index = PLLVAL(0x66, 1, 3), }, /* FVco 880.000000 */ - { .frequency = 120000000, .index = PLLVAL(0x70, 1, 3), }, /* FVco 960.000000 */ - { .frequency = 150000000, .index = PLLVAL(0x75, 3, 2), }, /* FVco 600.000000 */ - { .frequency = 160000000, .index = PLLVAL(0x98, 4, 2), }, /* FVco 640.000000 */ - { .frequency = 170000000, .index = PLLVAL(0x4d, 1, 2), }, /* FVco 680.000000 */ - { .frequency = 180000000, .index = PLLVAL(0x70, 2, 2), }, /* FVco 720.000000 */ - { .frequency = 190000000, .index = PLLVAL(0x57, 1, 2), }, /* FVco 760.000000 */ - { .frequency = 200000000, .index = PLLVAL(0x5c, 1, 2), }, /* FVco 800.000000 */ - { .frequency = 210000000, .index = PLLVAL(0x84, 2, 2), }, /* FVco 840.000000 */ - { .frequency = 220000000, .index = PLLVAL(0x66, 1, 2), }, /* FVco 880.000000 */ - { .frequency = 230000000, .index = PLLVAL(0x6b, 1, 2), }, /* FVco 920.000000 */ - { .frequency = 240000000, .index = PLLVAL(0x70, 1, 2), }, /* FVco 960.000000 */ - { .frequency = 300000000, .index = PLLVAL(0x75, 3, 1), }, /* FVco 600.000000 */ - { .frequency = 310000000, .index = PLLVAL(0x93, 4, 1), }, /* FVco 620.000000 */ - { .frequency = 320000000, .index = PLLVAL(0x98, 4, 1), }, /* FVco 640.000000 */ - { .frequency = 330000000, .index = PLLVAL(0x66, 2, 1), }, /* FVco 660.000000 */ - { .frequency = 340000000, .index = PLLVAL(0x4d, 1, 1), }, /* FVco 680.000000 */ - { .frequency = 350000000, .index = PLLVAL(0xa7, 4, 1), }, /* FVco 700.000000 */ - { .frequency = 360000000, .index = PLLVAL(0x70, 2, 1), }, /* FVco 720.000000 */ - { .frequency = 370000000, .index = PLLVAL(0xb1, 4, 1), }, /* FVco 740.000000 */ - { .frequency = 380000000, .index = PLLVAL(0x57, 1, 1), }, /* FVco 760.000000 */ - { .frequency = 390000000, .index = PLLVAL(0x7a, 2, 1), }, /* FVco 780.000000 */ - { .frequency = 400000000, .index = PLLVAL(0x5c, 1, 1), }, /* FVco 800.000000 */ + { .frequency = 75000000, .driver_data = PLLVAL(0x75, 3, 3), }, /* FVco 600.000000 */ + { .frequency = 80000000, .driver_data = PLLVAL(0x98, 4, 3), }, /* FVco 640.000000 */ + { .frequency = 90000000, .driver_data = PLLVAL(0x70, 2, 3), }, /* FVco 720.000000 */ + { .frequency = 100000000, .driver_data = PLLVAL(0x5c, 1, 3), }, /* FVco 800.000000 */ + { .frequency = 110000000, .driver_data = PLLVAL(0x66, 1, 3), }, /* FVco 880.000000 */ + { .frequency = 120000000, .driver_data = PLLVAL(0x70, 1, 3), }, /* FVco 960.000000 */ + { .frequency = 150000000, .driver_data = PLLVAL(0x75, 3, 2), }, /* FVco 600.000000 */ + { .frequency = 160000000, .driver_data = PLLVAL(0x98, 4, 2), }, /* FVco 640.000000 */ + { .frequency = 170000000, .driver_data = PLLVAL(0x4d, 1, 2), }, /* FVco 680.000000 */ + { .frequency = 180000000, .driver_data = PLLVAL(0x70, 2, 2), }, /* FVco 720.000000 */ + { .frequency = 190000000, .driver_data = PLLVAL(0x57, 1, 2), }, /* FVco 760.000000 */ + { .frequency = 200000000, .driver_data = PLLVAL(0x5c, 1, 2), }, /* FVco 800.000000 */ + { .frequency = 210000000, .driver_data = PLLVAL(0x84, 2, 2), }, /* FVco 840.000000 */ + { .frequency = 220000000, .driver_data = PLLVAL(0x66, 1, 2), }, /* FVco 880.000000 */ + { .frequency = 230000000, .driver_data = PLLVAL(0x6b, 1, 2), }, /* FVco 920.000000 */ + { .frequency = 240000000, .driver_data = PLLVAL(0x70, 1, 2), }, /* FVco 960.000000 */ + { .frequency = 300000000, .driver_data = PLLVAL(0x75, 3, 1), }, /* FVco 600.000000 */ + { .frequency = 310000000, .driver_data = PLLVAL(0x93, 4, 1), }, /* FVco 620.000000 */ + { .frequency = 320000000, .driver_data = PLLVAL(0x98, 4, 1), }, /* FVco 640.000000 */ + { .frequency = 330000000, .driver_data = PLLVAL(0x66, 2, 1), }, /* FVco 660.000000 */ + { .frequency = 340000000, .driver_data = PLLVAL(0x4d, 1, 1), }, /* FVco 680.000000 */ + { .frequency = 350000000, .driver_data = PLLVAL(0xa7, 4, 1), }, /* FVco 700.000000 */ + { .frequency = 360000000, .driver_data = PLLVAL(0x70, 2, 1), }, /* FVco 720.000000 */ + { .frequency = 370000000, .driver_data = PLLVAL(0xb1, 4, 1), }, /* FVco 740.000000 */ + { .frequency = 380000000, .driver_data = PLLVAL(0x57, 1, 1), }, /* FVco 760.000000 */ + { .frequency = 390000000, .driver_data = PLLVAL(0x7a, 2, 1), }, /* FVco 780.000000 */ + { .frequency = 400000000, .driver_data = PLLVAL(0x5c, 1, 1), }, /* FVco 800.000000 */ }; static int s3c2440_plls12_add(struct device *dev, struct subsys_interface *sif) diff --git a/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c b/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c index debfa106289b..1191b2905625 100644 --- a/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c +++ b/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c @@ -21,61 +21,61 @@ #include <plat/cpu-freq-core.h> static struct cpufreq_frequency_table s3c2440_plls_169344[] __initdata = { - { .frequency = 78019200, .index = PLLVAL(121, 5, 3), }, /* FVco 624.153600 */ - { .frequency = 84067200, .index = PLLVAL(131, 5, 3), }, /* FVco 672.537600 */ - { .frequency = 90115200, .index = PLLVAL(141, 5, 3), }, /* FVco 720.921600 */ - { .frequency = 96163200, .index = PLLVAL(151, 5, 3), }, /* FVco 769.305600 */ - { .frequency = 102135600, .index = PLLVAL(185, 6, 3), }, /* FVco 817.084800 */ - { .frequency = 108259200, .index = PLLVAL(171, 5, 3), }, /* FVco 866.073600 */ - { .frequency = 114307200, .index = PLLVAL(127, 3, 3), }, /* FVco 914.457600 */ - { .frequency = 120234240, .index = PLLVAL(134, 3, 3), }, /* FVco 961.873920 */ - { .frequency = 126161280, .index = PLLVAL(141, 3, 3), }, /* FVco 1009.290240 */ - { .frequency = 132088320, .index = PLLVAL(148, 3, 3), }, /* FVco 1056.706560 */ - { .frequency = 138015360, .index = PLLVAL(155, 3, 3), }, /* FVco 1104.122880 */ - { .frequency = 144789120, .index = PLLVAL(163, 3, 3), }, /* FVco 1158.312960 */ - { .frequency = 150100363, .index = PLLVAL(187, 9, 2), }, /* FVco 600.401454 */ - { .frequency = 156038400, .index = PLLVAL(121, 5, 2), }, /* FVco 624.153600 */ - { .frequency = 162086400, .index = PLLVAL(126, 5, 2), }, /* FVco 648.345600 */ - { .frequency = 168134400, .index = PLLVAL(131, 5, 2), }, /* FVco 672.537600 */ - { .frequency = 174048000, .index = PLLVAL(177, 7, 2), }, /* FVco 696.192000 */ - { .frequency = 180230400, .index = PLLVAL(141, 5, 2), }, /* FVco 720.921600 */ - { .frequency = 186278400, .index = PLLVAL(124, 4, 2), }, /* FVco 745.113600 */ - { .frequency = 192326400, .index = PLLVAL(151, 5, 2), }, /* FVco 769.305600 */ - { .frequency = 198132480, .index = PLLVAL(109, 3, 2), }, /* FVco 792.529920 */ - { .frequency = 204271200, .index = PLLVAL(185, 6, 2), }, /* FVco 817.084800 */ - { .frequency = 210268800, .index = PLLVAL(141, 4, 2), }, /* FVco 841.075200 */ - { .frequency = 216518400, .index = PLLVAL(171, 5, 2), }, /* FVco 866.073600 */ - { .frequency = 222264000, .index = PLLVAL(97, 2, 2), }, /* FVco 889.056000 */ - { .frequency = 228614400, .index = PLLVAL(127, 3, 2), }, /* FVco 914.457600 */ - { .frequency = 234259200, .index = PLLVAL(158, 4, 2), }, /* FVco 937.036800 */ - { .frequency = 240468480, .index = PLLVAL(134, 3, 2), }, /* FVco 961.873920 */ - { .frequency = 246960000, .index = PLLVAL(167, 4, 2), }, /* FVco 987.840000 */ - { .frequency = 252322560, .index = PLLVAL(141, 3, 2), }, /* FVco 1009.290240 */ - { .frequency = 258249600, .index = PLLVAL(114, 2, 2), }, /* FVco 1032.998400 */ - { .frequency = 264176640, .index = PLLVAL(148, 3, 2), }, /* FVco 1056.706560 */ - { .frequency = 270950400, .index = PLLVAL(120, 2, 2), }, /* FVco 1083.801600 */ - { .frequency = 276030720, .index = PLLVAL(155, 3, 2), }, /* FVco 1104.122880 */ - { .frequency = 282240000, .index = PLLVAL(92, 1, 2), }, /* FVco 1128.960000 */ - { .frequency = 289578240, .index = PLLVAL(163, 3, 2), }, /* FVco 1158.312960 */ - { .frequency = 294235200, .index = PLLVAL(131, 2, 2), }, /* FVco 1176.940800 */ - { .frequency = 300200727, .index = PLLVAL(187, 9, 1), }, /* FVco 600.401454 */ - { .frequency = 306358690, .index = PLLVAL(191, 9, 1), }, /* FVco 612.717380 */ - { .frequency = 312076800, .index = PLLVAL(121, 5, 1), }, /* FVco 624.153600 */ - { .frequency = 318366720, .index = PLLVAL(86, 3, 1), }, /* FVco 636.733440 */ - { .frequency = 324172800, .index = PLLVAL(126, 5, 1), }, /* FVco 648.345600 */ - { .frequency = 330220800, .index = PLLVAL(109, 4, 1), }, /* FVco 660.441600 */ - { .frequency = 336268800, .index = PLLVAL(131, 5, 1), }, /* FVco 672.537600 */ - { .frequency = 342074880, .index = PLLVAL(93, 3, 1), }, /* FVco 684.149760 */ - { .frequency = 348096000, .index = PLLVAL(177, 7, 1), }, /* FVco 696.192000 */ - { .frequency = 355622400, .index = PLLVAL(118, 4, 1), }, /* FVco 711.244800 */ - { .frequency = 360460800, .index = PLLVAL(141, 5, 1), }, /* FVco 720.921600 */ - { .frequency = 366206400, .index = PLLVAL(165, 6, 1), }, /* FVco 732.412800 */ - { .frequency = 372556800, .index = PLLVAL(124, 4, 1), }, /* FVco 745.113600 */ - { .frequency = 378201600, .index = PLLVAL(126, 4, 1), }, /* FVco 756.403200 */ - { .frequency = 384652800, .index = PLLVAL(151, 5, 1), }, /* FVco 769.305600 */ - { .frequency = 391608000, .index = PLLVAL(177, 6, 1), }, /* FVco 783.216000 */ - { .frequency = 396264960, .index = PLLVAL(109, 3, 1), }, /* FVco 792.529920 */ - { .frequency = 402192000, .index = PLLVAL(87, 2, 1), }, /* FVco 804.384000 */ + { .frequency = 78019200, .driver_data = PLLVAL(121, 5, 3), }, /* FVco 624.153600 */ + { .frequency = 84067200, .driver_data = PLLVAL(131, 5, 3), }, /* FVco 672.537600 */ + { .frequency = 90115200, .driver_data = PLLVAL(141, 5, 3), }, /* FVco 720.921600 */ + { .frequency = 96163200, .driver_data = PLLVAL(151, 5, 3), }, /* FVco 769.305600 */ + { .frequency = 102135600, .driver_data = PLLVAL(185, 6, 3), }, /* FVco 817.084800 */ + { .frequency = 108259200, .driver_data = PLLVAL(171, 5, 3), }, /* FVco 866.073600 */ + { .frequency = 114307200, .driver_data = PLLVAL(127, 3, 3), }, /* FVco 914.457600 */ + { .frequency = 120234240, .driver_data = PLLVAL(134, 3, 3), }, /* FVco 961.873920 */ + { .frequency = 126161280, .driver_data = PLLVAL(141, 3, 3), }, /* FVco 1009.290240 */ + { .frequency = 132088320, .driver_data = PLLVAL(148, 3, 3), }, /* FVco 1056.706560 */ + { .frequency = 138015360, .driver_data = PLLVAL(155, 3, 3), }, /* FVco 1104.122880 */ + { .frequency = 144789120, .driver_data = PLLVAL(163, 3, 3), }, /* FVco 1158.312960 */ + { .frequency = 150100363, .driver_data = PLLVAL(187, 9, 2), }, /* FVco 600.401454 */ + { .frequency = 156038400, .driver_data = PLLVAL(121, 5, 2), }, /* FVco 624.153600 */ + { .frequency = 162086400, .driver_data = PLLVAL(126, 5, 2), }, /* FVco 648.345600 */ + { .frequency = 168134400, .driver_data = PLLVAL(131, 5, 2), }, /* FVco 672.537600 */ + { .frequency = 174048000, .driver_data = PLLVAL(177, 7, 2), }, /* FVco 696.192000 */ + { .frequency = 180230400, .driver_data = PLLVAL(141, 5, 2), }, /* FVco 720.921600 */ + { .frequency = 186278400, .driver_data = PLLVAL(124, 4, 2), }, /* FVco 745.113600 */ + { .frequency = 192326400, .driver_data = PLLVAL(151, 5, 2), }, /* FVco 769.305600 */ + { .frequency = 198132480, .driver_data = PLLVAL(109, 3, 2), }, /* FVco 792.529920 */ + { .frequency = 204271200, .driver_data = PLLVAL(185, 6, 2), }, /* FVco 817.084800 */ + { .frequency = 210268800, .driver_data = PLLVAL(141, 4, 2), }, /* FVco 841.075200 */ + { .frequency = 216518400, .driver_data = PLLVAL(171, 5, 2), }, /* FVco 866.073600 */ + { .frequency = 222264000, .driver_data = PLLVAL(97, 2, 2), }, /* FVco 889.056000 */ + { .frequency = 228614400, .driver_data = PLLVAL(127, 3, 2), }, /* FVco 914.457600 */ + { .frequency = 234259200, .driver_data = PLLVAL(158, 4, 2), }, /* FVco 937.036800 */ + { .frequency = 240468480, .driver_data = PLLVAL(134, 3, 2), }, /* FVco 961.873920 */ + { .frequency = 246960000, .driver_data = PLLVAL(167, 4, 2), }, /* FVco 987.840000 */ + { .frequency = 252322560, .driver_data = PLLVAL(141, 3, 2), }, /* FVco 1009.290240 */ + { .frequency = 258249600, .driver_data = PLLVAL(114, 2, 2), }, /* FVco 1032.998400 */ + { .frequency = 264176640, .driver_data = PLLVAL(148, 3, 2), }, /* FVco 1056.706560 */ + { .frequency = 270950400, .driver_data = PLLVAL(120, 2, 2), }, /* FVco 1083.801600 */ + { .frequency = 276030720, .driver_data = PLLVAL(155, 3, 2), }, /* FVco 1104.122880 */ + { .frequency = 282240000, .driver_data = PLLVAL(92, 1, 2), }, /* FVco 1128.960000 */ + { .frequency = 289578240, .driver_data = PLLVAL(163, 3, 2), }, /* FVco 1158.312960 */ + { .frequency = 294235200, .driver_data = PLLVAL(131, 2, 2), }, /* FVco 1176.940800 */ + { .frequency = 300200727, .driver_data = PLLVAL(187, 9, 1), }, /* FVco 600.401454 */ + { .frequency = 306358690, .driver_data = PLLVAL(191, 9, 1), }, /* FVco 612.717380 */ + { .frequency = 312076800, .driver_data = PLLVAL(121, 5, 1), }, /* FVco 624.153600 */ + { .frequency = 318366720, .driver_data = PLLVAL(86, 3, 1), }, /* FVco 636.733440 */ + { .frequency = 324172800, .driver_data = PLLVAL(126, 5, 1), }, /* FVco 648.345600 */ + { .frequency = 330220800, .driver_data = PLLVAL(109, 4, 1), }, /* FVco 660.441600 */ + { .frequency = 336268800, .driver_data = PLLVAL(131, 5, 1), }, /* FVco 672.537600 */ + { .frequency = 342074880, .driver_data = PLLVAL(93, 3, 1), }, /* FVco 684.149760 */ + { .frequency = 348096000, .driver_data = PLLVAL(177, 7, 1), }, /* FVco 696.192000 */ + { .frequency = 355622400, .driver_data = PLLVAL(118, 4, 1), }, /* FVco 711.244800 */ + { .frequency = 360460800, .driver_data = PLLVAL(141, 5, 1), }, /* FVco 720.921600 */ + { .frequency = 366206400, .driver_data = PLLVAL(165, 6, 1), }, /* FVco 732.412800 */ + { .frequency = 372556800, .driver_data = PLLVAL(124, 4, 1), }, /* FVco 745.113600 */ + { .frequency = 378201600, .driver_data = PLLVAL(126, 4, 1), }, /* FVco 756.403200 */ + { .frequency = 384652800, .driver_data = PLLVAL(151, 5, 1), }, /* FVco 769.305600 */ + { .frequency = 391608000, .driver_data = PLLVAL(177, 6, 1), }, /* FVco 783.216000 */ + { .frequency = 396264960, .driver_data = PLLVAL(109, 3, 1), }, /* FVco 792.529920 */ + { .frequency = 402192000, .driver_data = PLLVAL(87, 2, 1), }, /* FVco 804.384000 */ }; static int s3c2440_plls169344_add(struct device *dev, diff --git a/arch/arm/mach-shmobile/clock-sh7372.c b/arch/arm/mach-shmobile/clock-sh7372.c index 7e105932c09d..5390c6bbbc02 100644 --- a/arch/arm/mach-shmobile/clock-sh7372.c +++ b/arch/arm/mach-shmobile/clock-sh7372.c @@ -142,15 +142,15 @@ static void pllc2_table_rebuild(struct clk *clk) /* Initialise PLLC2 frequency table */ for (i = 0; i < ARRAY_SIZE(pllc2_freq_table) - 2; i++) { pllc2_freq_table[i].frequency = clk->parent->rate * (i + 20) * 2; - pllc2_freq_table[i].index = i; + pllc2_freq_table[i].driver_data = i; } /* This is a special entry - switching PLL off makes it a repeater */ pllc2_freq_table[i].frequency = clk->parent->rate; - pllc2_freq_table[i].index = i; + pllc2_freq_table[i].driver_data = i; pllc2_freq_table[++i].frequency = CPUFREQ_TABLE_END; - pllc2_freq_table[i].index = i; + pllc2_freq_table[i].driver_data = i; } static unsigned long pllc2_recalc(struct clk *clk) diff --git a/arch/arm/mach-tegra/Kconfig b/arch/arm/mach-tegra/Kconfig index 65c5ae6fa386..ef3a8da49b2d 100644 --- a/arch/arm/mach-tegra/Kconfig +++ b/arch/arm/mach-tegra/Kconfig @@ -28,7 +28,6 @@ config ARCH_TEGRA_2x_SOC select ARM_ERRATA_754327 if SMP select ARM_ERRATA_764369 if SMP select ARM_GIC - select CPU_FREQ_TABLE if CPU_FREQ select CPU_V7 select PINCTRL select PINCTRL_TEGRA20 @@ -46,7 +45,6 @@ config ARCH_TEGRA_3x_SOC select ARM_ERRATA_754322 select ARM_ERRATA_764369 if SMP select ARM_GIC - select CPU_FREQ_TABLE if CPU_FREQ select CPU_V7 select PINCTRL select PINCTRL_TEGRA30 @@ -63,7 +61,6 @@ config ARCH_TEGRA_114_SOC select HAVE_ARM_ARCH_TIMER select ARM_GIC select ARM_L1_CACHE_SHIFT_6 - select CPU_FREQ_TABLE if CPU_FREQ select CPU_V7 select PINCTRL select PINCTRL_TEGRA114 diff --git a/arch/arm/mach-tegra/common.c b/arch/arm/mach-tegra/common.c index ec5836b1e713..b25153e2ebaa 100644 --- a/arch/arm/mach-tegra/common.c +++ b/arch/arm/mach-tegra/common.c @@ -23,7 +23,7 @@ #include <linux/clk.h> #include <linux/delay.h> #include <linux/irqchip.h> -#include <linux/clk/tegra.h> +#include <linux/clk-provider.h> #include <asm/hardware/cache-l2x0.h> @@ -60,7 +60,7 @@ u32 tegra_uart_config[4] = { #ifdef CONFIG_OF void __init tegra_dt_init_irq(void) { - tegra_clocks_init(); + of_clk_init(NULL); tegra_pmc_init(); tegra_init_irq(); irqchip_init(); diff --git a/arch/arm/mach-ux500/cpu.c b/arch/arm/mach-ux500/cpu.c index b6145ea51641..e6fb0239151b 100644 --- a/arch/arm/mach-ux500/cpu.c +++ b/arch/arm/mach-ux500/cpu.c @@ -76,13 +76,15 @@ void __init ux500_init_irq(void) } else if (cpu_is_u9540()) { prcmu_early_init(U8500_PRCMU_BASE, SZ_8K - 1); ux500_pm_init(U8500_PRCMU_BASE, SZ_8K - 1); - u8500_clk_init(U8500_CLKRST1_BASE, U8500_CLKRST2_BASE, + u9540_clk_init(U8500_CLKRST1_BASE, U8500_CLKRST2_BASE, U8500_CLKRST3_BASE, U8500_CLKRST5_BASE, U8500_CLKRST6_BASE); } else if (cpu_is_u8540()) { prcmu_early_init(U8500_PRCMU_BASE, SZ_8K + SZ_4K - 1); ux500_pm_init(U8500_PRCMU_BASE, SZ_8K + SZ_4K - 1); - u8540_clk_init(); + u8540_clk_init(U8500_CLKRST1_BASE, U8500_CLKRST2_BASE, + U8500_CLKRST3_BASE, U8500_CLKRST5_BASE, + U8500_CLKRST6_BASE); } } diff --git a/arch/arm/plat-samsung/include/plat/cpu-freq-core.h b/arch/arm/plat-samsung/include/plat/cpu-freq-core.h index d7e17150028a..7231c8e4975e 100644 --- a/arch/arm/plat-samsung/include/plat/cpu-freq-core.h +++ b/arch/arm/plat-samsung/include/plat/cpu-freq-core.h @@ -285,7 +285,7 @@ static inline int s3c_cpufreq_addfreq(struct cpufreq_frequency_table *table, s3c_freq_dbg("%s: { %d = %u kHz }\n", __func__, index, freq); - table[index].index = index; + table[index].driver_data = index; table[index].frequency = freq; } diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c index 7c2f6685bf43..7f8759a8a92a 100644 --- a/arch/avr32/mach-at32ap/at32ap700x.c +++ b/arch/avr32/mach-at32ap/at32ap700x.c @@ -1060,7 +1060,9 @@ struct platform_device *__init at32_add_device_usart(unsigned int id) void __init at32_setup_serial_console(unsigned int usart_id) { +#ifdef CONFIG_SERIAL_ATMEL atmel_default_console_device = at32_usarts[usart_id]; +#endif } /* -------------------------------------------------------------------- diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild index 4258b088aa93..e49f918531ad 100644 --- a/arch/c6x/include/asm/Kbuild +++ b/arch/c6x/include/asm/Kbuild @@ -55,3 +55,4 @@ generic-y += types.h generic-y += ucontext.h generic-y += user.h generic-y += vga.h +generic-y += xor.h diff --git a/arch/cris/Kconfig b/arch/cris/Kconfig index 8769a9045a54..3201ddb8da6a 100644 --- a/arch/cris/Kconfig +++ b/arch/cris/Kconfig @@ -134,11 +134,13 @@ config SVINTO_SIM config ETRAXFS bool "ETRAX-FS-V32" + select CPU_FREQ_TABLE if CPU_FREQ help Support CRIS V32. config CRIS_MACH_ARTPEC3 bool "ARTPEC-3" + select CPU_FREQ_TABLE if CPU_FREQ help Support Axis ARTPEC-3. @@ -637,40 +639,10 @@ endchoice endmenu -source "drivers/base/Kconfig" - -# standard linux drivers -source "drivers/mtd/Kconfig" - -source "drivers/parport/Kconfig" - -source "drivers/pnp/Kconfig" - -source "drivers/block/Kconfig" - -source "drivers/ide/Kconfig" - -source "drivers/net/Kconfig" - -source "drivers/i2c/Kconfig" - -source "drivers/rtc/Kconfig" - -# -# input before char - char/joystick depends on it. As does USB. -# -source "drivers/input/Kconfig" - -source "drivers/char/Kconfig" +source "drivers/Kconfig" source "fs/Kconfig" -source "drivers/usb/Kconfig" - -source "drivers/uwb/Kconfig" - -source "drivers/staging/Kconfig" - source "arch/cris/Kconfig.debug" source "security/Kconfig" diff --git a/arch/cris/arch-v10/kernel/kgdb.c b/arch/cris/arch-v10/kernel/kgdb.c index 37e6d2c50b76..22d846bfc570 100644 --- a/arch/cris/arch-v10/kernel/kgdb.c +++ b/arch/cris/arch-v10/kernel/kgdb.c @@ -230,46 +230,6 @@ struct register_image unsigned int usp; /* 0x66 User mode stack pointer */ } registers; -/************** Prototypes for local library functions ***********************/ - -/* Copy of strcpy from libc. */ -static char *gdb_cris_strcpy (char *s1, const char *s2); - -/* Copy of strlen from libc. */ -static int gdb_cris_strlen (const char *s); - -/* Copy of memchr from libc. */ -static void *gdb_cris_memchr (const void *s, int c, int n); - -/* Copy of strtol from libc. Does only support base 16. */ -static int gdb_cris_strtol (const char *s, char **endptr, int base); - -/********************** Prototypes for local functions. **********************/ -/* Copy the content of a register image into another. The size n is - the size of the register image. Due to struct assignment generation of - memcpy in libc. */ -static void copy_registers (registers *dptr, registers *sptr, int n); - -/* Copy the stored registers from the stack. Put the register contents - of thread thread_id in the struct reg. */ -static void copy_registers_from_stack (int thread_id, registers *reg); - -/* Copy the registers to the stack. Put the register contents of thread - thread_id from struct reg to the stack. */ -static void copy_registers_to_stack (int thread_id, registers *reg); - -/* Write a value to a specified register regno in the register image - of the current thread. */ -static int write_register (int regno, char *val); - -/* Write a value to a specified register in the stack of a thread other - than the current thread. */ -static int write_stack_register(int thread_id, int regno, char *valptr); - -/* Read a value from a specified register in the register image. Returns the - status of the read operation. The register value is returned in valptr. */ -static int read_register (char regno, unsigned int *valptr); - /* Serial port, reads one character. ETRAX 100 specific. from debugport.c */ int getDebugChar (void); @@ -278,42 +238,6 @@ void putDebugChar (int val); void enableDebugIRQ (void); -/* Returns the integer equivalent of a hexadecimal character. */ -static int hex (char ch); - -/* Convert the memory, pointed to by mem into hexadecimal representation. - Put the result in buf, and return a pointer to the last character - in buf (null). */ -static char *mem2hex (char *buf, unsigned char *mem, int count); - -/* Convert the array, in hexadecimal representation, pointed to by buf into - binary representation. Put the result in mem, and return a pointer to - the character after the last byte written. */ -static unsigned char *hex2mem (unsigned char *mem, char *buf, int count); - -/* Put the content of the array, in binary representation, pointed to by buf - into memory pointed to by mem, and return a pointer to - the character after the last byte written. */ -static unsigned char *bin2mem (unsigned char *mem, unsigned char *buf, int count); - -/* Await the sequence $<data>#<checksum> and store <data> in the array buffer - returned. */ -static void getpacket (char *buffer); - -/* Send $<data>#<checksum> from the <data> in the array buffer. */ -static void putpacket (char *buffer); - -/* Build and send a response packet in order to inform the host the - stub is stopped. */ -static void stub_is_stopped (int sigval); - -/* All expected commands are sent from remote.c. Send a response according - to the description in remote.c. */ -static void handle_exception (int sigval); - -/* Performs a complete re-start from scratch. ETRAX specific. */ -static void kill_restart (void); - /******************** Prototypes for global functions. ***********************/ /* The string str is prepended with the GDB printout token and sent. */ @@ -336,10 +260,6 @@ extern unsigned char executing_task; /* The number of characters used for a 64 bit thread identifier. */ #define HEXCHARS_IN_THREAD_ID 16 -/* Avoid warning as the internal_stack is not used in the C-code. */ -#define USEDVAR(name) { if (name) { ; } } -#define USEDFUN(name) { void (*pf)(void) = (void *)name; USEDVAR(pf) } - /********************************** Packet I/O ******************************/ /* BUFMAX defines the maximum number of characters in inbound/outbound buffers */ @@ -405,7 +325,7 @@ static int register_size[] = /* Contains the register image of the executing thread in the assembler part of the code in order to avoid horrible addressing modes. */ -static registers reg; +registers cris_reg; /* FIXME: Should this be used? Delete otherwise. */ /* Contains the assumed consistency state of the register image. Uses the @@ -413,7 +333,7 @@ static registers reg; static int consistency_status = SUCCESS; /********************************** Handle exceptions ************************/ -/* The variable reg contains the register image associated with the +/* The variable cris_reg contains the register image associated with the current_thread_c variable. It is a complete register image created at entry. The reg_g contains a register image of a task where the general registers are taken from the stack and all special registers are taken @@ -421,18 +341,10 @@ static int consistency_status = SUCCESS; in order to provide access mainly for 'g', 'G' and 'P'. */ -/* Need two task id pointers in order to handle Hct and Hgt commands. */ -static int current_thread_c = 0; -static int current_thread_g = 0; - -/* Need two register images in order to handle Hct and Hgt commands. The - variable reg_g is in addition to reg above. */ -static registers reg_g; - /********************************** Breakpoint *******************************/ /* Use an internal stack in the breakpoint and interrupt response routines */ #define INTERNAL_STACK_SIZE 1024 -static char internal_stack[INTERNAL_STACK_SIZE]; +char internal_stack[INTERNAL_STACK_SIZE]; /* Due to the breakpoint return pointer, a state variable is needed to keep track of whether it is a static (compiled) or dynamic (gdb-invoked) @@ -500,164 +412,6 @@ gdb_cris_strtol (const char *s, char **endptr, int base) return x; } -/********************************* Register image ****************************/ -/* Copy the content of a register image into another. The size n is - the size of the register image. Due to struct assignment generation of - memcpy in libc. */ -static void -copy_registers (registers *dptr, registers *sptr, int n) -{ - unsigned char *dreg; - unsigned char *sreg; - - for (dreg = (unsigned char*)dptr, sreg = (unsigned char*)sptr; n > 0; n--) - *dreg++ = *sreg++; -} - -#ifdef PROCESS_SUPPORT -/* Copy the stored registers from the stack. Put the register contents - of thread thread_id in the struct reg. */ -static void -copy_registers_from_stack (int thread_id, registers *regptr) -{ - int j; - stack_registers *s = (stack_registers *)stack_list[thread_id]; - unsigned int *d = (unsigned int *)regptr; - - for (j = 13; j >= 0; j--) - *d++ = s->r[j]; - regptr->sp = (unsigned int)stack_list[thread_id]; - regptr->pc = s->pc; - regptr->dccr = s->dccr; - regptr->srp = s->srp; -} - -/* Copy the registers to the stack. Put the register contents of thread - thread_id from struct reg to the stack. */ -static void -copy_registers_to_stack (int thread_id, registers *regptr) -{ - int i; - stack_registers *d = (stack_registers *)stack_list[thread_id]; - unsigned int *s = (unsigned int *)regptr; - - for (i = 0; i < 14; i++) { - d->r[i] = *s++; - } - d->pc = regptr->pc; - d->dccr = regptr->dccr; - d->srp = regptr->srp; -} -#endif - -/* Write a value to a specified register in the register image of the current - thread. Returns status code SUCCESS, E02 or E05. */ -static int -write_register (int regno, char *val) -{ - int status = SUCCESS; - registers *current_reg = ® - - if (regno >= R0 && regno <= PC) { - /* 32-bit register with simple offset. */ - hex2mem ((unsigned char *)current_reg + regno * sizeof(unsigned int), - val, sizeof(unsigned int)); - } - else if (regno == P0 || regno == VR || regno == P4 || regno == P8) { - /* Do not support read-only registers. */ - status = E02; - } - else if (regno == CCR) { - /* 16 bit register with complex offset. (P4 is read-only, P6 is not implemented, - and P7 (MOF) is 32 bits in ETRAX 100LX. */ - hex2mem ((unsigned char *)&(current_reg->ccr) + (regno-CCR) * sizeof(unsigned short), - val, sizeof(unsigned short)); - } - else if (regno >= MOF && regno <= USP) { - /* 32 bit register with complex offset. (P8 has been taken care of.) */ - hex2mem ((unsigned char *)&(current_reg->ibr) + (regno-IBR) * sizeof(unsigned int), - val, sizeof(unsigned int)); - } - else { - /* Do not support nonexisting or unimplemented registers (P2, P3, and P6). */ - status = E05; - } - return status; -} - -#ifdef PROCESS_SUPPORT -/* Write a value to a specified register in the stack of a thread other - than the current thread. Returns status code SUCCESS or E07. */ -static int -write_stack_register (int thread_id, int regno, char *valptr) -{ - int status = SUCCESS; - stack_registers *d = (stack_registers *)stack_list[thread_id]; - unsigned int val; - - hex2mem ((unsigned char *)&val, valptr, sizeof(unsigned int)); - if (regno >= R0 && regno < SP) { - d->r[regno] = val; - } - else if (regno == SP) { - stack_list[thread_id] = val; - } - else if (regno == PC) { - d->pc = val; - } - else if (regno == SRP) { - d->srp = val; - } - else if (regno == DCCR) { - d->dccr = val; - } - else { - /* Do not support registers in the current thread. */ - status = E07; - } - return status; -} -#endif - -/* Read a value from a specified register in the register image. Returns the - value in the register or -1 for non-implemented registers. - Should check consistency_status after a call which may be E05 after changes - in the implementation. */ -static int -read_register (char regno, unsigned int *valptr) -{ - registers *current_reg = ® - - if (regno >= R0 && regno <= PC) { - /* 32-bit register with simple offset. */ - *valptr = *(unsigned int *)((char *)current_reg + regno * sizeof(unsigned int)); - return SUCCESS; - } - else if (regno == P0 || regno == VR) { - /* 8 bit register with complex offset. */ - *valptr = (unsigned int)(*(unsigned char *) - ((char *)&(current_reg->p0) + (regno-P0) * sizeof(char))); - return SUCCESS; - } - else if (regno == P4 || regno == CCR) { - /* 16 bit register with complex offset. */ - *valptr = (unsigned int)(*(unsigned short *) - ((char *)&(current_reg->p4) + (regno-P4) * sizeof(unsigned short))); - return SUCCESS; - } - else if (regno >= MOF && regno <= USP) { - /* 32 bit register with complex offset. */ - *valptr = *(unsigned int *)((char *)&(current_reg->p8) - + (regno-P8) * sizeof(unsigned int)); - return SUCCESS; - } - else { - /* Do not support nonexisting or unimplemented registers (P2, P3, and P6). */ - consistency_status = E05; - return E05; - } -} - /********************************** Packet I/O ******************************/ /* Returns the integer equivalent of a hexadecimal character. */ static int @@ -676,8 +430,6 @@ hex (char ch) Put the result in buf, and return a pointer to the last character in buf (null). */ -static int do_printk = 0; - static char * mem2hex(char *buf, unsigned char *mem, int count) { @@ -761,7 +513,7 @@ getpacket (char *buffer) xmitcsum = -1; count = 0; /* Read until a # or the end of the buffer is reached */ - while (count < BUFMAX) { + while (count < BUFMAX - 1) { ch = getDebugChar (); if (ch == '#') break; @@ -845,6 +597,81 @@ putDebugString (const unsigned char *str, int length) putpacket(remcomOutBuffer); } +/********************************* Register image ****************************/ +/* Write a value to a specified register in the register image of the current + thread. Returns status code SUCCESS, E02 or E05. */ +static int +write_register (int regno, char *val) +{ + int status = SUCCESS; + registers *current_reg = &cris_reg; + + if (regno >= R0 && regno <= PC) { + /* 32-bit register with simple offset. */ + hex2mem ((unsigned char *)current_reg + regno * sizeof(unsigned int), + val, sizeof(unsigned int)); + } + else if (regno == P0 || regno == VR || regno == P4 || regno == P8) { + /* Do not support read-only registers. */ + status = E02; + } + else if (regno == CCR) { + /* 16 bit register with complex offset. (P4 is read-only, P6 is not implemented, + and P7 (MOF) is 32 bits in ETRAX 100LX. */ + hex2mem ((unsigned char *)&(current_reg->ccr) + (regno-CCR) * sizeof(unsigned short), + val, sizeof(unsigned short)); + } + else if (regno >= MOF && regno <= USP) { + /* 32 bit register with complex offset. (P8 has been taken care of.) */ + hex2mem ((unsigned char *)&(current_reg->ibr) + (regno-IBR) * sizeof(unsigned int), + val, sizeof(unsigned int)); + } + else { + /* Do not support nonexisting or unimplemented registers (P2, P3, and P6). */ + status = E05; + } + return status; +} + +/* Read a value from a specified register in the register image. Returns the + value in the register or -1 for non-implemented registers. + Should check consistency_status after a call which may be E05 after changes + in the implementation. */ +static int +read_register (char regno, unsigned int *valptr) +{ + registers *current_reg = &cris_reg; + + if (regno >= R0 && regno <= PC) { + /* 32-bit register with simple offset. */ + *valptr = *(unsigned int *)((char *)current_reg + regno * sizeof(unsigned int)); + return SUCCESS; + } + else if (regno == P0 || regno == VR) { + /* 8 bit register with complex offset. */ + *valptr = (unsigned int)(*(unsigned char *) + ((char *)&(current_reg->p0) + (regno-P0) * sizeof(char))); + return SUCCESS; + } + else if (regno == P4 || regno == CCR) { + /* 16 bit register with complex offset. */ + *valptr = (unsigned int)(*(unsigned short *) + ((char *)&(current_reg->p4) + (regno-P4) * sizeof(unsigned short))); + return SUCCESS; + } + else if (regno >= MOF && regno <= USP) { + /* 32 bit register with complex offset. */ + *valptr = *(unsigned int *)((char *)&(current_reg->p8) + + (regno-P8) * sizeof(unsigned int)); + return SUCCESS; + } + else { + /* Do not support nonexisting or unimplemented registers (P2, P3, and P6). */ + consistency_status = E05; + return E05; + } +} + /********************************** Handle exceptions ************************/ /* Build and send a response packet in order to inform the host the stub is stopped. TAAn...:r...;n...:r...;n...:r...; @@ -891,26 +718,6 @@ stub_is_stopped(int sigval) } -#ifdef PROCESS_SUPPORT - /* Store the registers of the executing thread. Assume that both step, - continue, and register content requests are with respect to this - thread. The executing task is from the operating system scheduler. */ - - current_thread_c = executing_task; - current_thread_g = executing_task; - - /* A struct assignment translates into a libc memcpy call. Avoid - all libc functions in order to prevent recursive break points. */ - copy_registers (®_g, ®, sizeof(registers)); - - /* Store thread:r...; with the executing task TID. */ - gdb_cris_strcpy (&remcomOutBuffer[pos], "thread:"); - pos += gdb_cris_strlen ("thread:"); - remcomOutBuffer[pos++] = hex_asc_hi(executing_task); - remcomOutBuffer[pos++] = hex_asc_lo(executing_task); - gdb_cris_strcpy (&remcomOutBuffer[pos], ";"); -#endif - /* null-terminate and send it off */ *ptr = 0; @@ -918,16 +725,18 @@ stub_is_stopped(int sigval) putpacket (remcomOutBuffer); } +/* Performs a complete re-start from scratch. */ +static void +kill_restart (void) +{ + machine_restart(""); +} + /* All expected commands are sent from remote.c. Send a response according to the description in remote.c. */ -static void +void handle_exception (int sigval) { - /* Avoid warning of not used. */ - - USEDFUN(handle_exception); - USEDVAR(internal_stack[0]); - /* Send response. */ stub_is_stopped (sigval); @@ -943,19 +752,7 @@ handle_exception (int sigval) in a register are in the same order the machine uses. Failure: void. */ - { -#ifdef PROCESS_SUPPORT - /* Use the special register content in the executing thread. */ - copy_registers (®_g, ®, sizeof(registers)); - /* Replace the content available on the stack. */ - if (current_thread_g != executing_task) { - copy_registers_from_stack (current_thread_g, ®_g); - } - mem2hex ((unsigned char *)remcomOutBuffer, (unsigned char *)®_g, sizeof(registers)); -#else - mem2hex(remcomOutBuffer, (char *)®, sizeof(registers)); -#endif - } + mem2hex(remcomOutBuffer, (char *)&cris_reg, sizeof(registers)); break; case 'G': @@ -963,17 +760,7 @@ handle_exception (int sigval) Each byte of register data is described by two hex digits. Success: OK Failure: void. */ -#ifdef PROCESS_SUPPORT - hex2mem ((unsigned char *)®_g, &remcomInBuffer[1], sizeof(registers)); - if (current_thread_g == executing_task) { - copy_registers (®, ®_g, sizeof(registers)); - } - else { - copy_registers_to_stack(current_thread_g, ®_g); - } -#else - hex2mem((char *)®, &remcomInBuffer[1], sizeof(registers)); -#endif + hex2mem((char *)&cris_reg, &remcomInBuffer[1], sizeof(registers)); gdb_cris_strcpy (remcomOutBuffer, "OK"); break; @@ -989,12 +776,7 @@ handle_exception (int sigval) char *suffix; int regno = gdb_cris_strtol (&remcomInBuffer[1], &suffix, 16); int status; -#ifdef PROCESS_SUPPORT - if (current_thread_g != executing_task) - status = write_stack_register (current_thread_g, regno, suffix+1); - else -#endif - status = write_register (regno, suffix+1); + status = write_register (regno, suffix+1); switch (status) { case E02: @@ -1073,7 +855,7 @@ handle_exception (int sigval) Success: return to the executing thread. Failure: will never know. */ if (remcomInBuffer[1] != '\0') { - reg.pc = gdb_cris_strtol (&remcomInBuffer[1], 0, 16); + cris_reg.pc = gdb_cris_strtol (&remcomInBuffer[1], 0, 16); } enableDebugIRQ(); return; @@ -1129,119 +911,6 @@ handle_exception (int sigval) Not supported: E04 */ gdb_cris_strcpy (remcomOutBuffer, error_message[E04]); break; -#ifdef PROCESS_SUPPORT - - case 'T': - /* Thread alive. TXX - Is thread XX alive? - Success: OK, thread XX is alive. - Failure: E03, thread XX is dead. */ - { - int thread_id = (int)gdb_cris_strtol (&remcomInBuffer[1], 0, 16); - /* Cannot tell whether it is alive or not. */ - if (thread_id >= 0 && thread_id < number_of_tasks) - gdb_cris_strcpy (remcomOutBuffer, "OK"); - } - break; - - case 'H': - /* Set thread for subsequent operations: Hct - c = 'c' for thread used in step and continue; - t can be -1 for all threads. - c = 'g' for thread used in other operations. - t = 0 means pick any thread. - Success: OK - Failure: E01 */ - { - int thread_id = gdb_cris_strtol (&remcomInBuffer[2], 0, 16); - if (remcomInBuffer[1] == 'c') { - /* c = 'c' for thread used in step and continue */ - /* Do not change current_thread_c here. It would create a mess in - the scheduler. */ - gdb_cris_strcpy (remcomOutBuffer, "OK"); - } - else if (remcomInBuffer[1] == 'g') { - /* c = 'g' for thread used in other operations. - t = 0 means pick any thread. Impossible since the scheduler does - not allow that. */ - if (thread_id >= 0 && thread_id < number_of_tasks) { - current_thread_g = thread_id; - gdb_cris_strcpy (remcomOutBuffer, "OK"); - } - else { - /* Not expected - send an error message. */ - gdb_cris_strcpy (remcomOutBuffer, error_message[E01]); - } - } - else { - /* Not expected - send an error message. */ - gdb_cris_strcpy (remcomOutBuffer, error_message[E01]); - } - } - break; - - case 'q': - case 'Q': - /* Query of general interest. qXXXX - Set general value XXXX. QXXXX=yyyy */ - { - int pos; - int nextpos; - int thread_id; - - switch (remcomInBuffer[1]) { - case 'C': - /* Identify the remote current thread. */ - gdb_cris_strcpy (&remcomOutBuffer[0], "QC"); - remcomOutBuffer[2] = hex_asc_hi(current_thread_c); - remcomOutBuffer[3] = hex_asc_lo(current_thread_c); - remcomOutBuffer[4] = '\0'; - break; - case 'L': - gdb_cris_strcpy (&remcomOutBuffer[0], "QM"); - /* Reply with number of threads. */ - if (os_is_started()) { - remcomOutBuffer[2] = hex_asc_hi(number_of_tasks); - remcomOutBuffer[3] = hex_asc_lo(number_of_tasks); - } - else { - remcomOutBuffer[2] = hex_asc_hi(0); - remcomOutBuffer[3] = hex_asc_lo(1); - } - /* Done with the reply. */ - remcomOutBuffer[4] = hex_asc_lo(1); - pos = 5; - /* Expects the argument thread id. */ - for (; pos < (5 + HEXCHARS_IN_THREAD_ID); pos++) - remcomOutBuffer[pos] = remcomInBuffer[pos]; - /* Reply with the thread identifiers. */ - if (os_is_started()) { - /* Store the thread identifiers of all tasks. */ - for (thread_id = 0; thread_id < number_of_tasks; thread_id++) { - nextpos = pos + HEXCHARS_IN_THREAD_ID - 1; - for (; pos < nextpos; pos ++) - remcomOutBuffer[pos] = hex_asc_lo(0); - remcomOutBuffer[pos++] = hex_asc_lo(thread_id); - } - } - else { - /* Store the thread identifier of the boot task. */ - nextpos = pos + HEXCHARS_IN_THREAD_ID - 1; - for (; pos < nextpos; pos ++) - remcomOutBuffer[pos] = hex_asc_lo(0); - remcomOutBuffer[pos++] = hex_asc_lo(current_thread_c); - } - remcomOutBuffer[pos] = '\0'; - break; - default: - /* Not supported: "" */ - /* Request information about section offsets: qOffsets. */ - remcomOutBuffer[0] = 0; - break; - } - } - break; -#endif /* PROCESS_SUPPORT */ default: /* The stub should ignore other request and send an empty @@ -1254,13 +923,6 @@ handle_exception (int sigval) } } -/* Performs a complete re-start from scratch. */ -static void -kill_restart () -{ - machine_restart(""); -} - /********************************** Breakpoint *******************************/ /* The hook for both a static (compiled) and a dynamic breakpoint set by GDB. An internal stack is used by the stub. The register image of the caller is @@ -1270,93 +932,93 @@ kill_restart () void kgdb_handle_breakpoint(void); -asm (" - .global kgdb_handle_breakpoint -kgdb_handle_breakpoint: -;; -;; Response to the break-instruction -;; -;; Create a register image of the caller -;; - move $dccr,[reg+0x5E] ; Save the flags in DCCR before disable interrupts - di ; Disable interrupts - move.d $r0,[reg] ; Save R0 - move.d $r1,[reg+0x04] ; Save R1 - move.d $r2,[reg+0x08] ; Save R2 - move.d $r3,[reg+0x0C] ; Save R3 - move.d $r4,[reg+0x10] ; Save R4 - move.d $r5,[reg+0x14] ; Save R5 - move.d $r6,[reg+0x18] ; Save R6 - move.d $r7,[reg+0x1C] ; Save R7 - move.d $r8,[reg+0x20] ; Save R8 - move.d $r9,[reg+0x24] ; Save R9 - move.d $r10,[reg+0x28] ; Save R10 - move.d $r11,[reg+0x2C] ; Save R11 - move.d $r12,[reg+0x30] ; Save R12 - move.d $r13,[reg+0x34] ; Save R13 - move.d $sp,[reg+0x38] ; Save SP (R14) -;; Due to the old assembler-versions BRP might not be recognized - .word 0xE670 ; move brp,$r0 - subq 2,$r0 ; Set to address of previous instruction. - move.d $r0,[reg+0x3c] ; Save the address in PC (R15) - clear.b [reg+0x40] ; Clear P0 - move $vr,[reg+0x41] ; Save special register P1 - clear.w [reg+0x42] ; Clear P4 - move $ccr,[reg+0x44] ; Save special register CCR - move $mof,[reg+0x46] ; P7 - clear.d [reg+0x4A] ; Clear P8 - move $ibr,[reg+0x4E] ; P9, - move $irp,[reg+0x52] ; P10, - move $srp,[reg+0x56] ; P11, - move $dtp0,[reg+0x5A] ; P12, register BAR, assembler might not know BAR - ; P13, register DCCR already saved -;; Due to the old assembler-versions BRP might not be recognized - .word 0xE670 ; move brp,r0 -;; Static (compiled) breakpoints must return to the next instruction in order -;; to avoid infinite loops. Dynamic (gdb-invoked) must restore the instruction -;; in order to execute it when execution is continued. - test.b [is_dyn_brkp] ; Is this a dynamic breakpoint? - beq is_static ; No, a static breakpoint - nop - subq 2,$r0 ; rerun the instruction the break replaced -is_static: - moveq 1,$r1 - move.b $r1,[is_dyn_brkp] ; Set the state variable to dynamic breakpoint - move.d $r0,[reg+0x62] ; Save the return address in BRP - move $usp,[reg+0x66] ; USP -;; -;; Handle the communication -;; - move.d internal_stack+1020,$sp ; Use the internal stack which grows upward - moveq 5,$r10 ; SIGTRAP - jsr handle_exception ; Interactive routine -;; -;; Return to the caller -;; - move.d [reg],$r0 ; Restore R0 - move.d [reg+0x04],$r1 ; Restore R1 - move.d [reg+0x08],$r2 ; Restore R2 - move.d [reg+0x0C],$r3 ; Restore R3 - move.d [reg+0x10],$r4 ; Restore R4 - move.d [reg+0x14],$r5 ; Restore R5 - move.d [reg+0x18],$r6 ; Restore R6 - move.d [reg+0x1C],$r7 ; Restore R7 - move.d [reg+0x20],$r8 ; Restore R8 - move.d [reg+0x24],$r9 ; Restore R9 - move.d [reg+0x28],$r10 ; Restore R10 - move.d [reg+0x2C],$r11 ; Restore R11 - move.d [reg+0x30],$r12 ; Restore R12 - move.d [reg+0x34],$r13 ; Restore R13 -;; -;; FIXME: Which registers should be restored? -;; - move.d [reg+0x38],$sp ; Restore SP (R14) - move [reg+0x56],$srp ; Restore the subroutine return pointer. - move [reg+0x5E],$dccr ; Restore DCCR - move [reg+0x66],$usp ; Restore USP - jump [reg+0x62] ; A jump to the content in register BRP works. - nop ; -"); +asm ("\n" +" .global kgdb_handle_breakpoint\n" +"kgdb_handle_breakpoint:\n" +";;\n" +";; Response to the break-instruction\n" +";;\n" +";; Create a register image of the caller\n" +";;\n" +" move $dccr,[cris_reg+0x5E] ; Save the flags in DCCR before disable interrupts\n" +" di ; Disable interrupts\n" +" move.d $r0,[cris_reg] ; Save R0\n" +" move.d $r1,[cris_reg+0x04] ; Save R1\n" +" move.d $r2,[cris_reg+0x08] ; Save R2\n" +" move.d $r3,[cris_reg+0x0C] ; Save R3\n" +" move.d $r4,[cris_reg+0x10] ; Save R4\n" +" move.d $r5,[cris_reg+0x14] ; Save R5\n" +" move.d $r6,[cris_reg+0x18] ; Save R6\n" +" move.d $r7,[cris_reg+0x1C] ; Save R7\n" +" move.d $r8,[cris_reg+0x20] ; Save R8\n" +" move.d $r9,[cris_reg+0x24] ; Save R9\n" +" move.d $r10,[cris_reg+0x28] ; Save R10\n" +" move.d $r11,[cris_reg+0x2C] ; Save R11\n" +" move.d $r12,[cris_reg+0x30] ; Save R12\n" +" move.d $r13,[cris_reg+0x34] ; Save R13\n" +" move.d $sp,[cris_reg+0x38] ; Save SP (R14)\n" +";; Due to the old assembler-versions BRP might not be recognized\n" +" .word 0xE670 ; move brp,$r0\n" +" subq 2,$r0 ; Set to address of previous instruction.\n" +" move.d $r0,[cris_reg+0x3c] ; Save the address in PC (R15)\n" +" clear.b [cris_reg+0x40] ; Clear P0\n" +" move $vr,[cris_reg+0x41] ; Save special register P1\n" +" clear.w [cris_reg+0x42] ; Clear P4\n" +" move $ccr,[cris_reg+0x44] ; Save special register CCR\n" +" move $mof,[cris_reg+0x46] ; P7\n" +" clear.d [cris_reg+0x4A] ; Clear P8\n" +" move $ibr,[cris_reg+0x4E] ; P9,\n" +" move $irp,[cris_reg+0x52] ; P10,\n" +" move $srp,[cris_reg+0x56] ; P11,\n" +" move $dtp0,[cris_reg+0x5A] ; P12, register BAR, assembler might not know BAR\n" +" ; P13, register DCCR already saved\n" +";; Due to the old assembler-versions BRP might not be recognized\n" +" .word 0xE670 ; move brp,r0\n" +";; Static (compiled) breakpoints must return to the next instruction in order\n" +";; to avoid infinite loops. Dynamic (gdb-invoked) must restore the instruction\n" +";; in order to execute it when execution is continued.\n" +" test.b [is_dyn_brkp] ; Is this a dynamic breakpoint?\n" +" beq is_static ; No, a static breakpoint\n" +" nop\n" +" subq 2,$r0 ; rerun the instruction the break replaced\n" +"is_static:\n" +" moveq 1,$r1\n" +" move.b $r1,[is_dyn_brkp] ; Set the state variable to dynamic breakpoint\n" +" move.d $r0,[cris_reg+0x62] ; Save the return address in BRP\n" +" move $usp,[cris_reg+0x66] ; USP\n" +";;\n" +";; Handle the communication\n" +";;\n" +" move.d internal_stack+1020,$sp ; Use the internal stack which grows upward\n" +" moveq 5,$r10 ; SIGTRAP\n" +" jsr handle_exception ; Interactive routine\n" +";;\n" +";; Return to the caller\n" +";;\n" +" move.d [cris_reg],$r0 ; Restore R0\n" +" move.d [cris_reg+0x04],$r1 ; Restore R1\n" +" move.d [cris_reg+0x08],$r2 ; Restore R2\n" +" move.d [cris_reg+0x0C],$r3 ; Restore R3\n" +" move.d [cris_reg+0x10],$r4 ; Restore R4\n" +" move.d [cris_reg+0x14],$r5 ; Restore R5\n" +" move.d [cris_reg+0x18],$r6 ; Restore R6\n" +" move.d [cris_reg+0x1C],$r7 ; Restore R7\n" +" move.d [cris_reg+0x20],$r8 ; Restore R8\n" +" move.d [cris_reg+0x24],$r9 ; Restore R9\n" +" move.d [cris_reg+0x28],$r10 ; Restore R10\n" +" move.d [cris_reg+0x2C],$r11 ; Restore R11\n" +" move.d [cris_reg+0x30],$r12 ; Restore R12\n" +" move.d [cris_reg+0x34],$r13 ; Restore R13\n" +";;\n" +";; FIXME: Which registers should be restored?\n" +";;\n" +" move.d [cris_reg+0x38],$sp ; Restore SP (R14)\n" +" move [cris_reg+0x56],$srp ; Restore the subroutine return pointer.\n" +" move [cris_reg+0x5E],$dccr ; Restore DCCR\n" +" move [cris_reg+0x66],$usp ; Restore USP\n" +" jump [cris_reg+0x62] ; A jump to the content in register BRP works.\n" +" nop ;\n" +"\n"); /* The hook for an interrupt generated by GDB. An internal stack is used by the stub. The register image of the caller is stored in the structure @@ -1367,94 +1029,94 @@ is_static: void kgdb_handle_serial(void); -asm (" - .global kgdb_handle_serial -kgdb_handle_serial: -;; -;; Response to a serial interrupt -;; - - move $dccr,[reg+0x5E] ; Save the flags in DCCR - di ; Disable interrupts - move.d $r0,[reg] ; Save R0 - move.d $r1,[reg+0x04] ; Save R1 - move.d $r2,[reg+0x08] ; Save R2 - move.d $r3,[reg+0x0C] ; Save R3 - move.d $r4,[reg+0x10] ; Save R4 - move.d $r5,[reg+0x14] ; Save R5 - move.d $r6,[reg+0x18] ; Save R6 - move.d $r7,[reg+0x1C] ; Save R7 - move.d $r8,[reg+0x20] ; Save R8 - move.d $r9,[reg+0x24] ; Save R9 - move.d $r10,[reg+0x28] ; Save R10 - move.d $r11,[reg+0x2C] ; Save R11 - move.d $r12,[reg+0x30] ; Save R12 - move.d $r13,[reg+0x34] ; Save R13 - move.d $sp,[reg+0x38] ; Save SP (R14) - move $irp,[reg+0x3c] ; Save the address in PC (R15) - clear.b [reg+0x40] ; Clear P0 - move $vr,[reg+0x41] ; Save special register P1, - clear.w [reg+0x42] ; Clear P4 - move $ccr,[reg+0x44] ; Save special register CCR - move $mof,[reg+0x46] ; P7 - clear.d [reg+0x4A] ; Clear P8 - move $ibr,[reg+0x4E] ; P9, - move $irp,[reg+0x52] ; P10, - move $srp,[reg+0x56] ; P11, - move $dtp0,[reg+0x5A] ; P12, register BAR, assembler might not know BAR - ; P13, register DCCR already saved -;; Due to the old assembler-versions BRP might not be recognized - .word 0xE670 ; move brp,r0 - move.d $r0,[reg+0x62] ; Save the return address in BRP - move $usp,[reg+0x66] ; USP - -;; get the serial character (from debugport.c) and check if it is a ctrl-c - - jsr getDebugChar - cmp.b 3, $r10 - bne goback - nop - - move.d [reg+0x5E], $r10 ; Get DCCR - btstq 8, $r10 ; Test the U-flag. - bmi goback - nop - -;; -;; Handle the communication -;; - move.d internal_stack+1020,$sp ; Use the internal stack - moveq 2,$r10 ; SIGINT - jsr handle_exception ; Interactive routine - -goback: -;; -;; Return to the caller -;; - move.d [reg],$r0 ; Restore R0 - move.d [reg+0x04],$r1 ; Restore R1 - move.d [reg+0x08],$r2 ; Restore R2 - move.d [reg+0x0C],$r3 ; Restore R3 - move.d [reg+0x10],$r4 ; Restore R4 - move.d [reg+0x14],$r5 ; Restore R5 - move.d [reg+0x18],$r6 ; Restore R6 - move.d [reg+0x1C],$r7 ; Restore R7 - move.d [reg+0x20],$r8 ; Restore R8 - move.d [reg+0x24],$r9 ; Restore R9 - move.d [reg+0x28],$r10 ; Restore R10 - move.d [reg+0x2C],$r11 ; Restore R11 - move.d [reg+0x30],$r12 ; Restore R12 - move.d [reg+0x34],$r13 ; Restore R13 -;; -;; FIXME: Which registers should be restored? -;; - move.d [reg+0x38],$sp ; Restore SP (R14) - move [reg+0x56],$srp ; Restore the subroutine return pointer. - move [reg+0x5E],$dccr ; Restore DCCR - move [reg+0x66],$usp ; Restore USP - reti ; Return from the interrupt routine - nop -"); +asm ("\n" +" .global kgdb_handle_serial\n" +"kgdb_handle_serial:\n" +";;\n" +";; Response to a serial interrupt\n" +";;\n" +"\n" +" move $dccr,[cris_reg+0x5E] ; Save the flags in DCCR\n" +" di ; Disable interrupts\n" +" move.d $r0,[cris_reg] ; Save R0\n" +" move.d $r1,[cris_reg+0x04] ; Save R1\n" +" move.d $r2,[cris_reg+0x08] ; Save R2\n" +" move.d $r3,[cris_reg+0x0C] ; Save R3\n" +" move.d $r4,[cris_reg+0x10] ; Save R4\n" +" move.d $r5,[cris_reg+0x14] ; Save R5\n" +" move.d $r6,[cris_reg+0x18] ; Save R6\n" +" move.d $r7,[cris_reg+0x1C] ; Save R7\n" +" move.d $r8,[cris_reg+0x20] ; Save R8\n" +" move.d $r9,[cris_reg+0x24] ; Save R9\n" +" move.d $r10,[cris_reg+0x28] ; Save R10\n" +" move.d $r11,[cris_reg+0x2C] ; Save R11\n" +" move.d $r12,[cris_reg+0x30] ; Save R12\n" +" move.d $r13,[cris_reg+0x34] ; Save R13\n" +" move.d $sp,[cris_reg+0x38] ; Save SP (R14)\n" +" move $irp,[cris_reg+0x3c] ; Save the address in PC (R15)\n" +" clear.b [cris_reg+0x40] ; Clear P0\n" +" move $vr,[cris_reg+0x41] ; Save special register P1,\n" +" clear.w [cris_reg+0x42] ; Clear P4\n" +" move $ccr,[cris_reg+0x44] ; Save special register CCR\n" +" move $mof,[cris_reg+0x46] ; P7\n" +" clear.d [cris_reg+0x4A] ; Clear P8\n" +" move $ibr,[cris_reg+0x4E] ; P9,\n" +" move $irp,[cris_reg+0x52] ; P10,\n" +" move $srp,[cris_reg+0x56] ; P11,\n" +" move $dtp0,[cris_reg+0x5A] ; P12, register BAR, assembler might not know BAR\n" +" ; P13, register DCCR already saved\n" +";; Due to the old assembler-versions BRP might not be recognized\n" +" .word 0xE670 ; move brp,r0\n" +" move.d $r0,[cris_reg+0x62] ; Save the return address in BRP\n" +" move $usp,[cris_reg+0x66] ; USP\n" +"\n" +";; get the serial character (from debugport.c) and check if it is a ctrl-c\n" +"\n" +" jsr getDebugChar\n" +" cmp.b 3, $r10\n" +" bne goback\n" +" nop\n" +"\n" +" move.d [cris_reg+0x5E], $r10 ; Get DCCR\n" +" btstq 8, $r10 ; Test the U-flag.\n" +" bmi goback\n" +" nop\n" +"\n" +";;\n" +";; Handle the communication\n" +";;\n" +" move.d internal_stack+1020,$sp ; Use the internal stack\n" +" moveq 2,$r10 ; SIGINT\n" +" jsr handle_exception ; Interactive routine\n" +"\n" +"goback:\n" +";;\n" +";; Return to the caller\n" +";;\n" +" move.d [cris_reg],$r0 ; Restore R0\n" +" move.d [cris_reg+0x04],$r1 ; Restore R1\n" +" move.d [cris_reg+0x08],$r2 ; Restore R2\n" +" move.d [cris_reg+0x0C],$r3 ; Restore R3\n" +" move.d [cris_reg+0x10],$r4 ; Restore R4\n" +" move.d [cris_reg+0x14],$r5 ; Restore R5\n" +" move.d [cris_reg+0x18],$r6 ; Restore R6\n" +" move.d [cris_reg+0x1C],$r7 ; Restore R7\n" +" move.d [cris_reg+0x20],$r8 ; Restore R8\n" +" move.d [cris_reg+0x24],$r9 ; Restore R9\n" +" move.d [cris_reg+0x28],$r10 ; Restore R10\n" +" move.d [cris_reg+0x2C],$r11 ; Restore R11\n" +" move.d [cris_reg+0x30],$r12 ; Restore R12\n" +" move.d [cris_reg+0x34],$r13 ; Restore R13\n" +";;\n" +";; FIXME: Which registers should be restored?\n" +";;\n" +" move.d [cris_reg+0x38],$sp ; Restore SP (R14)\n" +" move [cris_reg+0x56],$srp ; Restore the subroutine return pointer.\n" +" move [cris_reg+0x5E],$dccr ; Restore DCCR\n" +" move [cris_reg+0x66],$usp ; Restore USP\n" +" reti ; Return from the interrupt routine\n" +" nop\n" +"\n"); /* Use this static breakpoint in the start-up only. */ diff --git a/arch/cris/arch-v32/drivers/Kconfig b/arch/cris/arch-v32/drivers/Kconfig index ab725edbc680..acff3df8c43f 100644 --- a/arch/cris/arch-v32/drivers/Kconfig +++ b/arch/cris/arch-v32/drivers/Kconfig @@ -640,8 +640,6 @@ config ETRAX_STREAMCOPROC This option enables a driver for the stream co-processor for cryptographic operations. -source drivers/mmc/Kconfig - config ETRAX_MMC_IOP tristate "MMC/SD host driver using IO-processor" depends on ETRAX_ARCH_V32 && MMC @@ -833,9 +831,4 @@ config ETRAX_SPI_MMC_WP_GPIO_PIN The pin to use for the SD/MMC write-protect signal for a memory card. If defined as " " (space), the card is considered writable. -# Avoid choices causing non-working configs by conditionalizing the inclusion. -if ETRAX_SPI_MMC -source drivers/spi/Kconfig -endif - endif diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild index f1e79edc9dd2..c8325455520e 100644 --- a/arch/cris/include/asm/Kbuild +++ b/arch/cris/include/asm/Kbuild @@ -5,5 +5,9 @@ header-y += arch-v32/ generic-y += clkdev.h generic-y += exec.h +generic-y += kvm_para.h +generic-y += linkage.h generic-y += module.h generic-y += trace_clock.h +generic-y += vga.h +generic-y += xor.h diff --git a/arch/cris/include/asm/io.h b/arch/cris/include/asm/io.h index ac12ae2b9286..5d3047e5563b 100644 --- a/arch/cris/include/asm/io.h +++ b/arch/cris/include/asm/io.h @@ -167,6 +167,9 @@ static inline void outsl(unsigned int port, const void *addr, cris_iops->write_io(port, (void *)addr, 4, count); } +#define inb_p(port) inb(port) +#define outb_p(val, port) outb((val), (port)) + /* * Convert a physical pointer to a virtual kernel pointer for /dev/mem * access diff --git a/arch/cris/include/asm/linkage.h b/arch/cris/include/asm/linkage.h deleted file mode 100644 index 291c2d01c44f..000000000000 --- a/arch/cris/include/asm/linkage.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ASM_LINKAGE_H -#define __ASM_LINKAGE_H - -/* Nothing to see here... */ - -#endif diff --git a/arch/frv/kernel/head.S b/arch/frv/kernel/head.S index e9a8cc63ac94..a7d0bea9c036 100644 --- a/arch/frv/kernel/head.S +++ b/arch/frv/kernel/head.S @@ -479,11 +479,6 @@ __head_mmu_enabled: LEDS 0x000c - # initialise the processor and the peripherals - #call SYMBOL_NAME(processor_init) - #call SYMBOL_NAME(unit_init) - #LEDS 0x0aff - sethi.p #0xe5e5,gr3 setlo #0xe5e5,gr3 or.p gr3,gr0,gr4 diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig index 303e4f9a79d1..3d6759ee382f 100644 --- a/arch/h8300/Kconfig +++ b/arch/h8300/Kconfig @@ -94,126 +94,10 @@ endmenu source "net/Kconfig" -source "drivers/base/Kconfig" - -source "drivers/mtd/Kconfig" - -source "drivers/block/Kconfig" - -source "drivers/ide/Kconfig" +source "drivers/Kconfig" source "arch/h8300/Kconfig.ide" -source "drivers/net/Kconfig" - -# -# input - input/joystick depends on it. As does USB. -# -source "drivers/input/Kconfig" - -menu "Character devices" - -config VT - bool "Virtual terminal" - ---help--- - If you say Y here, you will get support for terminal devices with - display and keyboard devices. These are called "virtual" because you - can run several virtual terminals (also called virtual consoles) on - one physical terminal. This is rather useful, for example one - virtual terminal can collect system messages and warnings, another - one can be used for a text-mode user session, and a third could run - an X session, all in parallel. Switching between virtual terminals - is done with certain key combinations, usually Alt-<function key>. - - The setterm command ("man setterm") can be used to change the - properties (such as colors or beeping) of a virtual terminal. The - man page console_codes(4) ("man console_codes") contains the special - character sequences that can be used to change those properties - directly. The fonts used on virtual terminals can be changed with - the setfont ("man setfont") command and the key bindings are defined - with the loadkeys ("man loadkeys") command. - - You need at least one virtual terminal device in order to make use - of your keyboard and monitor. Therefore, only people configuring an - embedded system would want to say N here in order to save some - memory; the only way to log into such a system is then via a serial - or network connection. - - If unsure, say Y, or else you won't be able to do much with your new - shiny Linux system :-) - -config VT_CONSOLE - bool "Support for console on virtual terminal" - depends on VT - ---help--- - The system console is the device which receives all kernel messages - and warnings and which allows logins in single user mode. If you - answer Y here, a virtual terminal (the device used to interact with - a physical terminal) can be used as system console. This is the most - common mode of operations, so you should say Y here unless you want - the kernel messages be output only to a serial port (in which case - you should say Y to "Console on serial port", below). - - If you do say Y here, by default the currently visible virtual - terminal (/dev/tty0) will be used as system console. You can change - that with a kernel command line option such as "console=tty3" which - would use the third virtual terminal as system console. (Try "man - bootparam" or see the documentation of your boot loader (lilo or - loadlin) about how to pass options to the kernel at boot time.) - - If unsure, say Y. - -config HW_CONSOLE - bool - depends on VT - default y - -comment "Unix98 PTY support" - -config UNIX98_PTYS - bool "Unix98 PTY support" - ---help--- - A pseudo terminal (PTY) is a software device consisting of two - halves: a master and a slave. The slave device behaves identical to - a physical terminal; the master device is used by a process to - read data from and write data to the slave, thereby emulating a - terminal. Typical programs for the master side are telnet servers - and xterms. - - Linux has traditionally used the BSD-like names /dev/ptyxx for - masters and /dev/ttyxx for slaves of pseudo terminals. This scheme - has a number of problems. The GNU C library glibc 2.1 and later, - however, supports the Unix98 naming standard: in order to acquire a - pseudo terminal, a process opens /dev/ptmx; the number of the pseudo - terminal is then made available to the process and the pseudo - terminal slave can be accessed as /dev/pts/<number>. What was - traditionally /dev/ttyp2 will then be /dev/pts/2, for example. - - The entries in /dev/pts/ are created on the fly by a virtual - file system; therefore, if you say Y here you should say Y to - "/dev/pts file system for Unix98 PTYs" as well. - - If you want to say Y here, you need to have the C library glibc 2.1 - or later (equal to libc-6.1, check with "ls -l /lib/libc.so.*"). - Read the instructions in <file:Documentation/Changes> pertaining to - pseudo terminals. It's safe to say N. - -source "drivers/char/pcmcia/Kconfig" - -source "drivers/tty/serial/Kconfig" - -source "drivers/i2c/Kconfig" - -source "drivers/hwmon/Kconfig" - -source "drivers/usb/Kconfig" - -source "drivers/uwb/Kconfig" - -endmenu - -source "drivers/staging/Kconfig" - source "fs/Kconfig" source "arch/h8300/Kconfig.debug" diff --git a/arch/h8300/Kconfig.cpu b/arch/h8300/Kconfig.cpu index 321f3922728b..cdee771460ed 100644 --- a/arch/h8300/Kconfig.cpu +++ b/arch/h8300/Kconfig.cpu @@ -64,6 +64,7 @@ choice config H83002 bool "H8/3001,3002,3003" + depends on BROKEN select CPU_H8300H config H83007 @@ -72,6 +73,7 @@ config H83007 config H83048 bool "H8/3044,3045,3046,3047,3048,3052" + depends on BROKEN select CPU_H8300H config H83068 @@ -155,10 +157,12 @@ config H8300_TIMER16_CH config H8300_ITU_CH int "ITU channel" depends on H8300_ITU + range 0 4 config H8300_TPU_CH int "TPU channel" depends on H8300_TPU + range 0 4 source "kernel/Kconfig.preempt" diff --git a/arch/h8300/boot/compressed/Makefile b/arch/h8300/boot/compressed/Makefile index 6745cb1ffb4f..a6c98fe3bbc3 100644 --- a/arch/h8300/boot/compressed/Makefile +++ b/arch/h8300/boot/compressed/Makefile @@ -16,7 +16,7 @@ OBJECTS = $(obj)/head.o $(obj)/misc.o # CONFIG_MEMORY_START ?= 0x00400000 CONFIG_BOOT_LINK_OFFSET ?= 0x00140000 -IMAGE_OFFSET := $(shell printf "0x%08x" $$[$(CONFIG_MEMORY_START)+$(CONFIG_BOOT_LINK_OFFSET)]) +IMAGE_OFFSET := $(shell printf "0x%08x" $$(($(CONFIG_MEMORY_START)+$(CONFIG_BOOT_LINK_OFFSET)))) LDFLAGS_vmlinux := -Ttext $(IMAGE_OFFSET) -estartup $(obj)/vmlinux.lds diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild index 995eb47e01bb..8ada3cf0c98d 100644 --- a/arch/h8300/include/asm/Kbuild +++ b/arch/h8300/include/asm/Kbuild @@ -1,6 +1,8 @@ generic-y += clkdev.h generic-y += exec.h +generic-y += linkage.h generic-y += mmu.h generic-y += module.h generic-y += trace_clock.h +generic-y += xor.h diff --git a/arch/h8300/include/asm/barrier.h b/arch/h8300/include/asm/barrier.h index c7283c343c55..9e0aa9fc195d 100644 --- a/arch/h8300/include/asm/barrier.h +++ b/arch/h8300/include/asm/barrier.h @@ -12,6 +12,8 @@ #define wmb() asm volatile ("" : : :"memory") #define set_mb(var, value) do { xchg(&var, value); } while (0) +#define read_barrier_depends() do { } while (0) + #ifdef CONFIG_SMP #define smp_mb() mb() #define smp_rmb() rmb() diff --git a/arch/h8300/include/asm/linkage.h b/arch/h8300/include/asm/linkage.h deleted file mode 100644 index 1d81604fb0ad..000000000000 --- a/arch/h8300/include/asm/linkage.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _H8300_LINKAGE_H -#define _H8300_LINKAGE_H - -#undef SYMBOL_NAME_LABEL -#define SYMBOL_NAME_LABEL(_name_) _##_name_##: -#endif diff --git a/arch/h8300/include/asm/tlb.h b/arch/h8300/include/asm/tlb.h index 3dea80ad9e6f..7f0743051ad5 100644 --- a/arch/h8300/include/asm/tlb.h +++ b/arch/h8300/include/asm/tlb.h @@ -1,16 +1,3 @@ -/* - include/asm-h8300/tlb.h -*/ - -#ifndef __H8300_TLB_H__ -#define __H8300_TLB_H__ - -#define tlb_flush(tlb) do { } while(0) - -/* - include/asm-h8300/tlb.h -*/ - #ifndef __H8300_TLB_H__ #define __H8300_TLB_H__ @@ -19,5 +6,3 @@ #include <asm-generic/tlb.h> #endif - -#endif diff --git a/arch/h8300/kernel/entry.S b/arch/h8300/kernel/entry.S index 617a6878787f..94bd30f11df6 100644 --- a/arch/h8300/kernel/entry.S +++ b/arch/h8300/kernel/entry.S @@ -87,13 +87,13 @@ INTERRUPTS = 128 bne 5f /* user mode */ - mov.l sp,@SYMBOL_NAME(sw_usp) + mov.l sp,@_sw_usp mov.l @sp,er0 /* restore saved er0 */ orc #0x10,ccr /* switch kernel stack */ - mov.l @SYMBOL_NAME(sw_ksp),sp + mov.l @_sw_ksp,sp sub.l #(LRET-LORIG),sp /* allocate LORIG - LRET */ SAVEREGS - mov.l @SYMBOL_NAME(sw_usp),er0 + mov.l @_sw_usp,er0 mov.l @(USERRET:16,er0),er1 /* copy the RET addr */ mov.l er1,@(LRET-LER3:16,sp) SAVEEXR @@ -128,7 +128,7 @@ INTERRUPTS = 128 bne 7f orc #0x80,ccr - mov.l @SYMBOL_NAME(sw_usp),er0 + mov.l @_sw_usp,er0 mov.l @(LER0-LER1:16,sp),er1 /* restore ER0 */ mov.l er1,@er0 RESTOREEXR @@ -141,7 +141,7 @@ INTERRUPTS = 128 mov.l @sp+,er1 add.l #(LRET-LER1),sp /* remove LORIG - LRET */ - mov.l sp,@SYMBOL_NAME(sw_ksp) + mov.l sp,@_sw_ksp andc #0xef,ccr /* switch to user mode */ mov.l er0,sp bra 8f @@ -155,20 +155,20 @@ INTERRUPTS = 128 rte .endm -.globl SYMBOL_NAME(system_call) -.globl SYMBOL_NAME(ret_from_exception) -.globl SYMBOL_NAME(ret_from_fork) -.globl SYMBOL_NAME(ret_from_kernel_thread) -.globl SYMBOL_NAME(ret_from_interrupt) -.globl SYMBOL_NAME(interrupt_redirect_table) -.globl SYMBOL_NAME(sw_ksp),SYMBOL_NAME(sw_usp) -.globl SYMBOL_NAME(resume) -.globl SYMBOL_NAME(interrupt_entry) -.globl SYMBOL_NAME(trace_break) +.globl _system_call +.globl _ret_from_exception +.globl _ret_from_fork +.globl _ret_from_kernel_thread +.globl _ret_from_interrupt +.globl _interrupt_redirect_table +.globl _sw_ksp,_sw_usp +.globl _resume +.globl _interrupt_entry +.globl _trace_break #if defined(CONFIG_ROMKERNEL) .section .int_redirect,"ax" -SYMBOL_NAME_LABEL(interrupt_redirect_table) +_interrupt_redirect_table: #if defined(CONFIG_CPU_H8300H) .rept 7 .long 0 @@ -178,54 +178,54 @@ SYMBOL_NAME_LABEL(interrupt_redirect_table) .rept 5 .long 0 .endr - jmp @SYMBOL_NAME(trace_break) + jmp @_trace_break .long 0 #endif - jsr @SYMBOL_NAME(interrupt_entry) /* NMI */ - jmp @SYMBOL_NAME(system_call) /* TRAPA #0 (System call) */ + jsr @_interrupt_entry /* NMI */ + jmp @_system_call /* TRAPA #0 (System call) */ .long 0 .long 0 - jmp @SYMBOL_NAME(trace_break) /* TRAPA #3 (breakpoint) */ + jmp @_trace_break /* TRAPA #3 (breakpoint) */ .rept INTERRUPTS-12 - jsr @SYMBOL_NAME(interrupt_entry) + jsr @_interrupt_entry .endr #endif #if defined(CONFIG_RAMKERNEL) -.globl SYMBOL_NAME(interrupt_redirect_table) +.globl _interrupt_redirect_table .section .bss -SYMBOL_NAME_LABEL(interrupt_redirect_table) +_interrupt_redirect_table: .space 4 #endif .section .text .align 2 -SYMBOL_NAME_LABEL(interrupt_entry) +_interrupt_entry: SAVE_ALL mov.l sp,er0 add.l #LVEC,er0 btst #4,r1l bne 1f /* user LVEC */ - mov.l @SYMBOL_NAME(sw_usp),er0 + mov.l @_sw_usp,er0 adds #4,er0 1: mov.l @er0,er0 /* LVEC address */ #if defined(CONFIG_ROMKERNEL) - sub.l #SYMBOL_NAME(interrupt_redirect_table),er0 + sub.l #_interrupt_redirect_table,er0 #endif #if defined(CONFIG_RAMKERNEL) - mov.l @SYMBOL_NAME(interrupt_redirect_table),er1 + mov.l @_interrupt_redirect_table,er1 sub.l er1,er0 #endif SHLR2 er0 dec.l #1,er0 mov.l sp,er1 subs #4,er1 /* adjust ret_pc */ - jsr @SYMBOL_NAME(do_IRQ) - jmp @SYMBOL_NAME(ret_from_interrupt) + jsr @_do_IRQ + jmp @_ret_from_interrupt -SYMBOL_NAME_LABEL(system_call) +_system_call: subs #4,sp /* dummy LVEC */ SAVE_ALL andc #0x7f,ccr @@ -233,21 +233,21 @@ SYMBOL_NAME_LABEL(system_call) /* save top of frame */ mov.l sp,er0 - jsr @SYMBOL_NAME(set_esp0) + jsr @_set_esp0 mov.l sp,er2 and.w #0xe000,r2 mov.b @((TI_FLAGS+3-(TIF_SYSCALL_TRACE >> 3)):16,er2),r2l btst #(TIF_SYSCALL_TRACE & 7),r2l beq 1f - jsr @SYMBOL_NAME(do_syscall_trace) + jsr @_do_syscall_trace 1: cmp.l #NR_syscalls,er4 bcc badsys SHLL2 er4 - mov.l #SYMBOL_NAME(sys_call_table),er0 + mov.l #_sys_call_table,er0 add.l er4,er0 mov.l @er0,er4 - beq SYMBOL_NAME(ret_from_exception):16 + beq _ret_from_exception:16 mov.l @(LER1:16,sp),er0 mov.l @(LER2:16,sp),er1 mov.l @(LER3:16,sp),er2 @@ -258,10 +258,10 @@ SYMBOL_NAME_LABEL(system_call) mov.b @((TI_FLAGS+3-(TIF_SYSCALL_TRACE >> 3)):16,er2),r2l btst #(TIF_SYSCALL_TRACE & 7),r2l beq 2f - jsr @SYMBOL_NAME(do_syscall_trace) + jsr @_do_syscall_trace 2: #if defined(CONFIG_SYSCALL_PRINT) - jsr @SYMBOL_NAME(syscall_print) + jsr @_syscall_print #endif orc #0x80,ccr bra resume_userspace @@ -275,11 +275,11 @@ badsys: #define resume_kernel restore_all #endif -SYMBOL_NAME_LABEL(ret_from_exception) +_ret_from_exception: #if defined(CONFIG_PREEMPT) orc #0x80,ccr #endif -SYMBOL_NAME_LABEL(ret_from_interrupt) +_ret_from_interrupt: mov.b @(LCCR+1:16,sp),r0l btst #4,r0l bne resume_kernel:8 /* return from kernel */ @@ -296,12 +296,12 @@ work_pending: /* work notifysig */ mov.l sp,er0 subs #4,er0 /* er0: pt_regs */ - jsr @SYMBOL_NAME(do_notify_resume) + jsr @_do_notify_resume bra restore_all:8 work_resched: mov.l sp,er0 - jsr @SYMBOL_NAME(set_esp0) - jsr @SYMBOL_NAME(schedule) + jsr @_set_esp0 + jsr @_schedule bra resume_userspace:8 restore_all: RESTORE_ALL /* Does RTE */ @@ -320,26 +320,26 @@ need_resched: mov.l er0,@(TI_PRE_COUNT:16,er4) andc #0x7f,ccr mov.l sp,er0 - jsr @SYMBOL_NAME(set_esp0) - jsr @SYMBOL_NAME(schedule) + jsr @_set_esp0 + jsr @_schedule orc #0x80,ccr bra need_resched:8 #endif -SYMBOL_NAME_LABEL(ret_from_fork) +_ret_from_fork: mov.l er2,er0 - jsr @SYMBOL_NAME(schedule_tail) - jmp @SYMBOL_NAME(ret_from_exception) + jsr @_schedule_tail + jmp @_ret_from_exception -SYMBOL_NAME_LABEL(ret_from_kernel_thread) +_ret_from_kernel_thread: mov.l er2,er0 - jsr @SYMBOL_NAME(schedule_tail) + jsr @_schedule_tail mov.l @(LER4:16,sp),er0 mov.l @(LER5:16,sp),er1 jsr @er1 - jmp @SYMBOL_NAME(ret_from_exception) + jmp @_ret_from_exception -SYMBOL_NAME_LABEL(resume) +_resume: /* * Beware - when entering resume, offset of tss is in d1, * prev (the current task) is in a0, next (the new task) @@ -355,7 +355,7 @@ SYMBOL_NAME_LABEL(resume) /* disable interrupts */ orc #0x80,ccr - mov.l @SYMBOL_NAME(sw_usp),er3 + mov.l @_sw_usp,er3 mov.l er3,@(THREAD_USP:16,er0) mov.l sp,@(THREAD_KSP:16,er0) @@ -363,7 +363,7 @@ SYMBOL_NAME_LABEL(resume) /* FIXME: what did we hack out of here, this does nothing! */ mov.l @(THREAD_USP:16,er1),er0 - mov.l er0,@SYMBOL_NAME(sw_usp) + mov.l er0,@_sw_usp mov.l @(THREAD_KSP:16,er1),sp /* restore status register */ @@ -372,15 +372,15 @@ SYMBOL_NAME_LABEL(resume) ldc r3l,ccr rts -SYMBOL_NAME_LABEL(trace_break) +_trace_break: subs #4,sp SAVE_ALL sub.l er1,er1 dec.l #1,er1 mov.l er1,@(LORIG,sp) mov.l sp,er0 - jsr @SYMBOL_NAME(set_esp0) - mov.l @SYMBOL_NAME(sw_usp),er0 + jsr @_set_esp0 + mov.l @_sw_usp,er0 mov.l @er0,er1 mov.w @(-2:16,er1),r2 cmp.w #0x5730,r2 @@ -390,13 +390,13 @@ SYMBOL_NAME_LABEL(trace_break) 1: and.w #0xff,e1 mov.l er1,er0 - jsr @SYMBOL_NAME(trace_trap) - jmp @SYMBOL_NAME(ret_from_exception) + jsr @_trace_trap + jmp @_ret_from_exception .section .bss -SYMBOL_NAME_LABEL(sw_ksp) +_sw_ksp: .space 4 -SYMBOL_NAME_LABEL(sw_usp) +_sw_usp: .space 4 .end diff --git a/arch/h8300/kernel/syscalls.S b/arch/h8300/kernel/syscalls.S index 5c2168fb9b9e..c55e0ed270d5 100644 --- a/arch/h8300/kernel/syscalls.S +++ b/arch/h8300/kernel/syscalls.S @@ -2,8 +2,10 @@ #include <linux/sys.h> #include <asm/linkage.h> #include <asm/unistd.h> - -.globl SYMBOL_NAME(sys_call_table) + +#define CALL(x) .long _ ## x + +.globl _sys_call_table #if defined(CONFIG_CPU_H8300H) .h8300h @@ -13,324 +15,324 @@ #endif .section .text .align 2 -SYMBOL_NAME_LABEL(sys_call_table) - .long SYMBOL_NAME(sys_ni_syscall) /* 0 - old "setup()" system call*/ - .long SYMBOL_NAME(sys_exit) - .long SYMBOL_NAME(sys_fork) - .long SYMBOL_NAME(sys_read) - .long SYMBOL_NAME(sys_write) - .long SYMBOL_NAME(sys_open) /* 5 */ - .long SYMBOL_NAME(sys_close) - .long SYMBOL_NAME(sys_waitpid) - .long SYMBOL_NAME(sys_creat) - .long SYMBOL_NAME(sys_link) - .long SYMBOL_NAME(sys_unlink) /* 10 */ - .long SYMBOL_NAME(sys_execve) - .long SYMBOL_NAME(sys_chdir) - .long SYMBOL_NAME(sys_time) - .long SYMBOL_NAME(sys_mknod) - .long SYMBOL_NAME(sys_chmod) /* 15 */ - .long SYMBOL_NAME(sys_chown16) - .long SYMBOL_NAME(sys_ni_syscall) /* old break syscall holder */ - .long SYMBOL_NAME(sys_stat) - .long SYMBOL_NAME(sys_lseek) - .long SYMBOL_NAME(sys_getpid) /* 20 */ - .long SYMBOL_NAME(sys_mount) - .long SYMBOL_NAME(sys_oldumount) - .long SYMBOL_NAME(sys_setuid16) - .long SYMBOL_NAME(sys_getuid16) - .long SYMBOL_NAME(sys_stime) /* 25 */ - .long SYMBOL_NAME(sys_ptrace) - .long SYMBOL_NAME(sys_alarm) - .long SYMBOL_NAME(sys_fstat) - .long SYMBOL_NAME(sys_pause) - .long SYMBOL_NAME(sys_utime) /* 30 */ - .long SYMBOL_NAME(sys_ni_syscall) /* old stty syscall holder */ - .long SYMBOL_NAME(sys_ni_syscall) /* old gtty syscall holder */ - .long SYMBOL_NAME(sys_access) - .long SYMBOL_NAME(sys_nice) - .long SYMBOL_NAME(sys_ni_syscall) /* 35 old ftime syscall holder */ - .long SYMBOL_NAME(sys_sync) - .long SYMBOL_NAME(sys_kill) - .long SYMBOL_NAME(sys_rename) - .long SYMBOL_NAME(sys_mkdir) - .long SYMBOL_NAME(sys_rmdir) /* 40 */ - .long SYMBOL_NAME(sys_dup) - .long SYMBOL_NAME(sys_pipe) - .long SYMBOL_NAME(sys_times) - .long SYMBOL_NAME(sys_ni_syscall) /* old prof syscall holder */ - .long SYMBOL_NAME(sys_brk) /* 45 */ - .long SYMBOL_NAME(sys_setgid16) - .long SYMBOL_NAME(sys_getgid16) - .long SYMBOL_NAME(sys_signal) - .long SYMBOL_NAME(sys_geteuid16) - .long SYMBOL_NAME(sys_getegid16) /* 50 */ - .long SYMBOL_NAME(sys_acct) - .long SYMBOL_NAME(sys_umount) /* recycled never used phys() */ - .long SYMBOL_NAME(sys_ni_syscall) /* old lock syscall holder */ - .long SYMBOL_NAME(sys_ioctl) - .long SYMBOL_NAME(sys_fcntl) /* 55 */ - .long SYMBOL_NAME(sys_ni_syscall) /* old mpx syscall holder */ - .long SYMBOL_NAME(sys_setpgid) - .long SYMBOL_NAME(sys_ni_syscall) /* old ulimit syscall holder */ - .long SYMBOL_NAME(sys_ni_syscall) - .long SYMBOL_NAME(sys_umask) /* 60 */ - .long SYMBOL_NAME(sys_chroot) - .long SYMBOL_NAME(sys_ustat) - .long SYMBOL_NAME(sys_dup2) - .long SYMBOL_NAME(sys_getppid) - .long SYMBOL_NAME(sys_getpgrp) /* 65 */ - .long SYMBOL_NAME(sys_setsid) - .long SYMBOL_NAME(sys_sigaction) - .long SYMBOL_NAME(sys_sgetmask) - .long SYMBOL_NAME(sys_ssetmask) - .long SYMBOL_NAME(sys_setreuid16) /* 70 */ - .long SYMBOL_NAME(sys_setregid16) - .long SYMBOL_NAME(sys_sigsuspend) - .long SYMBOL_NAME(sys_sigpending) - .long SYMBOL_NAME(sys_sethostname) - .long SYMBOL_NAME(sys_setrlimit) /* 75 */ - .long SYMBOL_NAME(sys_old_getrlimit) - .long SYMBOL_NAME(sys_getrusage) - .long SYMBOL_NAME(sys_gettimeofday) - .long SYMBOL_NAME(sys_settimeofday) - .long SYMBOL_NAME(sys_getgroups16) /* 80 */ - .long SYMBOL_NAME(sys_setgroups16) - .long SYMBOL_NAME(sys_old_select) - .long SYMBOL_NAME(sys_symlink) - .long SYMBOL_NAME(sys_lstat) - .long SYMBOL_NAME(sys_readlink) /* 85 */ - .long SYMBOL_NAME(sys_uselib) - .long SYMBOL_NAME(sys_swapon) - .long SYMBOL_NAME(sys_reboot) - .long SYMBOL_NAME(sys_old_readdir) - .long SYMBOL_NAME(sys_old_mmap) /* 90 */ - .long SYMBOL_NAME(sys_munmap) - .long SYMBOL_NAME(sys_truncate) - .long SYMBOL_NAME(sys_ftruncate) - .long SYMBOL_NAME(sys_fchmod) - .long SYMBOL_NAME(sys_fchown16) /* 95 */ - .long SYMBOL_NAME(sys_getpriority) - .long SYMBOL_NAME(sys_setpriority) - .long SYMBOL_NAME(sys_ni_syscall) /* old profil syscall holder */ - .long SYMBOL_NAME(sys_statfs) - .long SYMBOL_NAME(sys_fstatfs) /* 100 */ - .long SYMBOL_NAME(sys_ni_syscall) /* ioperm for i386 */ - .long SYMBOL_NAME(sys_socketcall) - .long SYMBOL_NAME(sys_syslog) - .long SYMBOL_NAME(sys_setitimer) - .long SYMBOL_NAME(sys_getitimer) /* 105 */ - .long SYMBOL_NAME(sys_newstat) - .long SYMBOL_NAME(sys_newlstat) - .long SYMBOL_NAME(sys_newfstat) - .long SYMBOL_NAME(sys_ni_syscall) - .long SYMBOL_NAME(sys_ni_syscall) /* iopl for i386 */ /* 110 */ - .long SYMBOL_NAME(sys_vhangup) - .long SYMBOL_NAME(sys_ni_syscall) /* obsolete idle() syscall */ - .long SYMBOL_NAME(sys_ni_syscall) /* vm86old for i386 */ - .long SYMBOL_NAME(sys_wait4) - .long SYMBOL_NAME(sys_swapoff) /* 115 */ - .long SYMBOL_NAME(sys_sysinfo) - .long SYMBOL_NAME(sys_ipc) - .long SYMBOL_NAME(sys_fsync) - .long SYMBOL_NAME(sys_sigreturn) - .long SYMBOL_NAME(sys_clone) /* 120 */ - .long SYMBOL_NAME(sys_setdomainname) - .long SYMBOL_NAME(sys_newuname) - .long SYMBOL_NAME(sys_cacheflush) /* modify_ldt for i386 */ - .long SYMBOL_NAME(sys_adjtimex) - .long SYMBOL_NAME(sys_ni_syscall) /* 125 sys_mprotect */ - .long SYMBOL_NAME(sys_sigprocmask) - .long SYMBOL_NAME(sys_ni_syscall) /* sys_create_module */ - .long SYMBOL_NAME(sys_init_module) - .long SYMBOL_NAME(sys_delete_module) - .long SYMBOL_NAME(sys_ni_syscall) /* 130 sys_get_kernel_syms */ - .long SYMBOL_NAME(sys_quotactl) - .long SYMBOL_NAME(sys_getpgid) - .long SYMBOL_NAME(sys_fchdir) - .long SYMBOL_NAME(sys_bdflush) - .long SYMBOL_NAME(sys_sysfs) /* 135 */ - .long SYMBOL_NAME(sys_personality) - .long SYMBOL_NAME(sys_ni_syscall) /* for afs_syscall */ - .long SYMBOL_NAME(sys_setfsuid16) - .long SYMBOL_NAME(sys_setfsgid16) - .long SYMBOL_NAME(sys_llseek) /* 140 */ - .long SYMBOL_NAME(sys_getdents) - .long SYMBOL_NAME(sys_select) - .long SYMBOL_NAME(sys_flock) - .long SYMBOL_NAME(sys_ni_syscall) /* sys_msync */ - .long SYMBOL_NAME(sys_readv) /* 145 */ - .long SYMBOL_NAME(sys_writev) - .long SYMBOL_NAME(sys_getsid) - .long SYMBOL_NAME(sys_fdatasync) - .long SYMBOL_NAME(sys_sysctl) - .long SYMBOL_NAME(sys_ni_syscall) /* 150 sys_mlock */ - .long SYMBOL_NAME(sys_ni_syscall) /* sys_munlock */ - .long SYMBOL_NAME(sys_ni_syscall) /* sys_mlockall */ - .long SYMBOL_NAME(sys_ni_syscall) /* sys_munlockall */ - .long SYMBOL_NAME(sys_sched_setparam) - .long SYMBOL_NAME(sys_sched_getparam) /* 155 */ - .long SYMBOL_NAME(sys_sched_setscheduler) - .long SYMBOL_NAME(sys_sched_getscheduler) - .long SYMBOL_NAME(sys_sched_yield) - .long SYMBOL_NAME(sys_sched_get_priority_max) - .long SYMBOL_NAME(sys_sched_get_priority_min) /* 160 */ - .long SYMBOL_NAME(sys_sched_rr_get_interval) - .long SYMBOL_NAME(sys_nanosleep) - .long SYMBOL_NAME(sys_ni_syscall) /* sys_mremap */ - .long SYMBOL_NAME(sys_setresuid16) - .long SYMBOL_NAME(sys_getresuid16) /* 165 */ - .long SYMBOL_NAME(sys_ni_syscall) /* for vm86 */ - .long SYMBOL_NAME(sys_ni_syscall) /* sys_query_module */ - .long SYMBOL_NAME(sys_poll) - .long SYMBOL_NAME(sys_ni_syscall) /* old nfsservctl */ - .long SYMBOL_NAME(sys_setresgid16) /* 170 */ - .long SYMBOL_NAME(sys_getresgid16) - .long SYMBOL_NAME(sys_prctl) - .long SYMBOL_NAME(sys_rt_sigreturn) - .long SYMBOL_NAME(sys_rt_sigaction) - .long SYMBOL_NAME(sys_rt_sigprocmask) /* 175 */ - .long SYMBOL_NAME(sys_rt_sigpending) - .long SYMBOL_NAME(sys_rt_sigtimedwait) - .long SYMBOL_NAME(sys_rt_sigqueueinfo) - .long SYMBOL_NAME(sys_rt_sigsuspend) - .long SYMBOL_NAME(sys_pread64) /* 180 */ - .long SYMBOL_NAME(sys_pwrite64) - .long SYMBOL_NAME(sys_lchown16); - .long SYMBOL_NAME(sys_getcwd) - .long SYMBOL_NAME(sys_capget) - .long SYMBOL_NAME(sys_capset) /* 185 */ - .long SYMBOL_NAME(sys_sigaltstack) - .long SYMBOL_NAME(sys_sendfile) - .long SYMBOL_NAME(sys_ni_syscall) /* streams1 */ - .long SYMBOL_NAME(sys_ni_syscall) /* streams2 */ - .long SYMBOL_NAME(sys_vfork) /* 190 */ - .long SYMBOL_NAME(sys_getrlimit) - .long SYMBOL_NAME(sys_mmap_pgoff) - .long SYMBOL_NAME(sys_truncate64) - .long SYMBOL_NAME(sys_ftruncate64) - .long SYMBOL_NAME(sys_stat64) /* 195 */ - .long SYMBOL_NAME(sys_lstat64) - .long SYMBOL_NAME(sys_fstat64) - .long SYMBOL_NAME(sys_chown) - .long SYMBOL_NAME(sys_getuid) - .long SYMBOL_NAME(sys_getgid) /* 200 */ - .long SYMBOL_NAME(sys_geteuid) - .long SYMBOL_NAME(sys_getegid) - .long SYMBOL_NAME(sys_setreuid) - .long SYMBOL_NAME(sys_setregid) - .long SYMBOL_NAME(sys_getgroups) /* 205 */ - .long SYMBOL_NAME(sys_setgroups) - .long SYMBOL_NAME(sys_fchown) - .long SYMBOL_NAME(sys_setresuid) - .long SYMBOL_NAME(sys_getresuid) - .long SYMBOL_NAME(sys_setresgid) /* 210 */ - .long SYMBOL_NAME(sys_getresgid) - .long SYMBOL_NAME(sys_lchown) - .long SYMBOL_NAME(sys_setuid) - .long SYMBOL_NAME(sys_setgid) - .long SYMBOL_NAME(sys_setfsuid) /* 215 */ - .long SYMBOL_NAME(sys_setfsgid) - .long SYMBOL_NAME(sys_pivot_root) - .long SYMBOL_NAME(sys_ni_syscall) - .long SYMBOL_NAME(sys_ni_syscall) - .long SYMBOL_NAME(sys_getdents64) /* 220 */ - .long SYMBOL_NAME(sys_fcntl64) - .long SYMBOL_NAME(sys_ni_syscall) /* reserved TUX */ - .long SYMBOL_NAME(sys_ni_syscall) /* reserved Security */ - .long SYMBOL_NAME(sys_gettid) - .long SYMBOL_NAME(sys_readahead) /* 225 */ - .long SYMBOL_NAME(sys_setxattr) - .long SYMBOL_NAME(sys_lsetxattr) - .long SYMBOL_NAME(sys_fsetxattr) - .long SYMBOL_NAME(sys_getxattr) - .long SYMBOL_NAME(sys_lgetxattr) /* 230 */ - .long SYMBOL_NAME(sys_fgetxattr) - .long SYMBOL_NAME(sys_listxattr) - .long SYMBOL_NAME(sys_llistxattr) - .long SYMBOL_NAME(sys_flistxattr) - .long SYMBOL_NAME(sys_removexattr) /* 235 */ - .long SYMBOL_NAME(sys_lremovexattr) - .long SYMBOL_NAME(sys_fremovexattr) - .long SYMBOL_NAME(sys_tkill) - .long SYMBOL_NAME(sys_sendfile64) - .long SYMBOL_NAME(sys_futex) /* 240 */ - .long SYMBOL_NAME(sys_sched_setaffinity) - .long SYMBOL_NAME(sys_sched_getaffinity) - .long SYMBOL_NAME(sys_ni_syscall) - .long SYMBOL_NAME(sys_ni_syscall) - .long SYMBOL_NAME(sys_io_setup) /* 245 */ - .long SYMBOL_NAME(sys_io_destroy) - .long SYMBOL_NAME(sys_io_getevents) - .long SYMBOL_NAME(sys_io_submit) - .long SYMBOL_NAME(sys_io_cancel) - .long SYMBOL_NAME(sys_fadvise64) /* 250 */ - .long SYMBOL_NAME(sys_ni_syscall) - .long SYMBOL_NAME(sys_exit_group) - .long SYMBOL_NAME(sys_lookup_dcookie) - .long SYMBOL_NAME(sys_epoll_create) - .long SYMBOL_NAME(sys_epoll_ctl) /* 255 */ - .long SYMBOL_NAME(sys_epoll_wait) - .long SYMBOL_NAME(sys_ni_syscall) /* sys_remap_file_pages */ - .long SYMBOL_NAME(sys_set_tid_address) - .long SYMBOL_NAME(sys_timer_create) - .long SYMBOL_NAME(sys_timer_settime) /* 260 */ - .long SYMBOL_NAME(sys_timer_gettime) - .long SYMBOL_NAME(sys_timer_getoverrun) - .long SYMBOL_NAME(sys_timer_delete) - .long SYMBOL_NAME(sys_clock_settime) - .long SYMBOL_NAME(sys_clock_gettime) /* 265 */ - .long SYMBOL_NAME(sys_clock_getres) - .long SYMBOL_NAME(sys_clock_nanosleep) - .long SYMBOL_NAME(sys_statfs64) - .long SYMBOL_NAME(sys_fstatfs64) - .long SYMBOL_NAME(sys_tgkill) /* 270 */ - .long SYMBOL_NAME(sys_utimes) - .long SYMBOL_NAME(sys_fadvise64_64) - .long SYMBOL_NAME(sys_ni_syscall) /* sys_vserver */ - .long SYMBOL_NAME(sys_ni_syscall) - .long SYMBOL_NAME(sys_get_mempolicy) /* 275 */ - .long SYMBOL_NAME(sys_set_mempolicy) - .long SYMBOL_NAME(sys_mq_open) - .long SYMBOL_NAME(sys_mq_unlink) - .long SYMBOL_NAME(sys_mq_timedsend) - .long SYMBOL_NAME(sys_mq_timedreceive) /* 280 */ - .long SYMBOL_NAME(sys_mq_notify) - .long SYMBOL_NAME(sys_mq_getsetattr) - .long SYMBOL_NAME(sys_waitid) - .long SYMBOL_NAME(sys_ni_syscall) /* sys_kexec_load */ - .long SYMBOL_NAME(sys_add_key) /* 285 */ - .long SYMBOL_NAME(sys_request_key) - .long SYMBOL_NAME(sys_keyctl) - .long SYMBOL_NAME(sys_ioprio_set) - .long SYMBOL_NAME(sys_ioprio_get) /* 290 */ - .long SYMBOL_NAME(sys_inotify_init) - .long SYMBOL_NAME(sys_inotify_add_watch) - .long SYMBOL_NAME(sys_inotify_rm_watch) - .long SYMBOL_NAME(sys_migrate_pages) - .long SYMBOL_NAME(sys_openat) /* 295 */ - .long SYMBOL_NAME(sys_mkdirat) - .long SYMBOL_NAME(sys_mknodat) - .long SYMBOL_NAME(sys_fchownat) - .long SYMBOL_NAME(sys_futimesat) - .long SYMBOL_NAME(sys_fstatat64) /* 300 */ - .long SYMBOL_NAME(sys_unlinkat) - .long SYMBOL_NAME(sys_renameat) - .long SYMBOL_NAME(sys_linkat) - .long SYMBOL_NAME(sys_symlinkat) - .long SYMBOL_NAME(sys_readlinkat) /* 305 */ - .long SYMBOL_NAME(sys_fchmodat) - .long SYMBOL_NAME(sys_faccessat) - .long SYMBOL_NAME(sys_ni_syscall) /* sys_pselect6 */ - .long SYMBOL_NAME(sys_ni_syscall) /* sys_ppoll */ - .long SYMBOL_NAME(sys_unshare) /* 310 */ - .long SYMBOL_NAME(sys_set_robust_list) - .long SYMBOL_NAME(sys_get_robust_list) - .long SYMBOL_NAME(sys_splice) - .long SYMBOL_NAME(sys_sync_file_range) - .long SYMBOL_NAME(sys_tee) /* 315 */ - .long SYMBOL_NAME(sys_vmsplice) - .long SYMBOL_NAME(sys_ni_syscall) /* sys_move_pages */ - .long SYMBOL_NAME(sys_getcpu) - .long SYMBOL_NAME(sys_ni_syscall) /* sys_epoll_pwait */ - .long SYMBOL_NAME(sys_setns) /* 320 */ +_sys_call_table: + CALL(sys_ni_syscall) /* 0 - old "setup()" system call*/ + CALL(sys_exit) + CALL(sys_fork) + CALL(sys_read) + CALL(sys_write) + CALL(sys_open) /* 5 */ + CALL(sys_close) + CALL(sys_waitpid) + CALL(sys_creat) + CALL(sys_link) + CALL(sys_unlink) /* 10 */ + CALL(sys_execve) + CALL(sys_chdir) + CALL(sys_time) + CALL(sys_mknod) + CALL(sys_chmod) /* 15 */ + CALL(sys_chown16) + CALL(sys_ni_syscall) /* old break syscall holder */ + CALL(sys_stat) + CALL(sys_lseek) + CALL(sys_getpid) /* 20 */ + CALL(sys_mount) + CALL(sys_oldumount) + CALL(sys_setuid16) + CALL(sys_getuid16) + CALL(sys_stime) /* 25 */ + CALL(sys_ptrace) + CALL(sys_alarm) + CALL(sys_fstat) + CALL(sys_pause) + CALL(sys_utime) /* 30 */ + CALL(sys_ni_syscall) /* old stty syscall holder */ + CALL(sys_ni_syscall) /* old gtty syscall holder */ + CALL(sys_access) + CALL(sys_nice) + CALL(sys_ni_syscall) /* 35 old ftime syscall holder */ + CALL(sys_sync) + CALL(sys_kill) + CALL(sys_rename) + CALL(sys_mkdir) + CALL(sys_rmdir) /* 40 */ + CALL(sys_dup) + CALL(sys_pipe) + CALL(sys_times) + CALL(sys_ni_syscall) /* old prof syscall holder */ + CALL(sys_brk) /* 45 */ + CALL(sys_setgid16) + CALL(sys_getgid16) + CALL(sys_signal) + CALL(sys_geteuid16) + CALL(sys_getegid16) /* 50 */ + CALL(sys_acct) + CALL(sys_umount) /* recycled never used phys() */ + CALL(sys_ni_syscall) /* old lock syscall holder */ + CALL(sys_ioctl) + CALL(sys_fcntl) /* 55 */ + CALL(sys_ni_syscall) /* old mpx syscall holder */ + CALL(sys_setpgid) + CALL(sys_ni_syscall) /* old ulimit syscall holder */ + CALL(sys_ni_syscall) + CALL(sys_umask) /* 60 */ + CALL(sys_chroot) + CALL(sys_ustat) + CALL(sys_dup2) + CALL(sys_getppid) + CALL(sys_getpgrp) /* 65 */ + CALL(sys_setsid) + CALL(sys_sigaction) + CALL(sys_sgetmask) + CALL(sys_ssetmask) + CALL(sys_setreuid16) /* 70 */ + CALL(sys_setregid16) + CALL(sys_sigsuspend) + CALL(sys_sigpending) + CALL(sys_sethostname) + CALL(sys_setrlimit) /* 75 */ + CALL(sys_old_getrlimit) + CALL(sys_getrusage) + CALL(sys_gettimeofday) + CALL(sys_settimeofday) + CALL(sys_getgroups16) /* 80 */ + CALL(sys_setgroups16) + CALL(sys_old_select) + CALL(sys_symlink) + CALL(sys_lstat) + CALL(sys_readlink) /* 85 */ + CALL(sys_uselib) + CALL(sys_swapon) + CALL(sys_reboot) + CALL(sys_old_readdir) + CALL(sys_old_mmap) /* 90 */ + CALL(sys_munmap) + CALL(sys_truncate) + CALL(sys_ftruncate) + CALL(sys_fchmod) + CALL(sys_fchown16) /* 95 */ + CALL(sys_getpriority) + CALL(sys_setpriority) + CALL(sys_ni_syscall) /* old profil syscall holder */ + CALL(sys_statfs) + CALL(sys_fstatfs) /* 100 */ + CALL(sys_ni_syscall) /* ioperm for i386 */ + CALL(sys_socketcall) + CALL(sys_syslog) + CALL(sys_setitimer) + CALL(sys_getitimer) /* 105 */ + CALL(sys_newstat) + CALL(sys_newlstat) + CALL(sys_newfstat) + CALL(sys_ni_syscall) + CALL(sys_ni_syscall) /* iopl for i386 */ /* 110 */ + CALL(sys_vhangup) + CALL(sys_ni_syscall) /* obsolete idle() syscall */ + CALL(sys_ni_syscall) /* vm86old for i386 */ + CALL(sys_wait4) + CALL(sys_swapoff) /* 115 */ + CALL(sys_sysinfo) + CALL(sys_ipc) + CALL(sys_fsync) + CALL(sys_sigreturn) + CALL(sys_clone) /* 120 */ + CALL(sys_setdomainname) + CALL(sys_newuname) + CALL(sys_cacheflush) /* modify_ldt for i386 */ + CALL(sys_adjtimex) + CALL(sys_ni_syscall) /* 125 sys_mprotect */ + CALL(sys_sigprocmask) + CALL(sys_ni_syscall) /* sys_create_module */ + CALL(sys_init_module) + CALL(sys_delete_module) + CALL(sys_ni_syscall) /* 130 sys_get_kernel_syms */ + CALL(sys_quotactl) + CALL(sys_getpgid) + CALL(sys_fchdir) + CALL(sys_bdflush) + CALL(sys_sysfs) /* 135 */ + CALL(sys_personality) + CALL(sys_ni_syscall) /* for afs_syscall */ + CALL(sys_setfsuid16) + CALL(sys_setfsgid16) + CALL(sys_llseek) /* 140 */ + CALL(sys_getdents) + CALL(sys_select) + CALL(sys_flock) + CALL(sys_ni_syscall) /* sys_msync */ + CALL(sys_readv) /* 145 */ + CALL(sys_writev) + CALL(sys_getsid) + CALL(sys_fdatasync) + CALL(sys_sysctl) + CALL(sys_ni_syscall) /* 150 sys_mlock */ + CALL(sys_ni_syscall) /* sys_munlock */ + CALL(sys_ni_syscall) /* sys_mlockall */ + CALL(sys_ni_syscall) /* sys_munlockall */ + CALL(sys_sched_setparam) + CALL(sys_sched_getparam) /* 155 */ + CALL(sys_sched_setscheduler) + CALL(sys_sched_getscheduler) + CALL(sys_sched_yield) + CALL(sys_sched_get_priority_max) + CALL(sys_sched_get_priority_min) /* 160 */ + CALL(sys_sched_rr_get_interval) + CALL(sys_nanosleep) + CALL(sys_ni_syscall) /* sys_mremap */ + CALL(sys_setresuid16) + CALL(sys_getresuid16) /* 165 */ + CALL(sys_ni_syscall) /* for vm86 */ + CALL(sys_ni_syscall) /* sys_query_module */ + CALL(sys_poll) + CALL(sys_ni_syscall) /* old nfsservctl */ + CALL(sys_setresgid16) /* 170 */ + CALL(sys_getresgid16) + CALL(sys_prctl) + CALL(sys_rt_sigreturn) + CALL(sys_rt_sigaction) + CALL(sys_rt_sigprocmask) /* 175 */ + CALL(sys_rt_sigpending) + CALL(sys_rt_sigtimedwait) + CALL(sys_rt_sigqueueinfo) + CALL(sys_rt_sigsuspend) + CALL(sys_pread64) /* 180 */ + CALL(sys_pwrite64) + CALL(sys_lchown16); + CALL(sys_getcwd) + CALL(sys_capget) + CALL(sys_capset) /* 185 */ + CALL(sys_sigaltstack) + CALL(sys_sendfile) + CALL(sys_ni_syscall) /* streams1 */ + CALL(sys_ni_syscall) /* streams2 */ + CALL(sys_vfork) /* 190 */ + CALL(sys_getrlimit) + CALL(sys_mmap_pgoff) + CALL(sys_truncate64) + CALL(sys_ftruncate64) + CALL(sys_stat64) /* 195 */ + CALL(sys_lstat64) + CALL(sys_fstat64) + CALL(sys_chown) + CALL(sys_getuid) + CALL(sys_getgid) /* 200 */ + CALL(sys_geteuid) + CALL(sys_getegid) + CALL(sys_setreuid) + CALL(sys_setregid) + CALL(sys_getgroups) /* 205 */ + CALL(sys_setgroups) + CALL(sys_fchown) + CALL(sys_setresuid) + CALL(sys_getresuid) + CALL(sys_setresgid) /* 210 */ + CALL(sys_getresgid) + CALL(sys_lchown) + CALL(sys_setuid) + CALL(sys_setgid) + CALL(sys_setfsuid) /* 215 */ + CALL(sys_setfsgid) + CALL(sys_pivot_root) + CALL(sys_ni_syscall) + CALL(sys_ni_syscall) + CALL(sys_getdents64) /* 220 */ + CALL(sys_fcntl64) + CALL(sys_ni_syscall) /* reserved TUX */ + CALL(sys_ni_syscall) /* reserved Security */ + CALL(sys_gettid) + CALL(sys_readahead) /* 225 */ + CALL(sys_setxattr) + CALL(sys_lsetxattr) + CALL(sys_fsetxattr) + CALL(sys_getxattr) + CALL(sys_lgetxattr) /* 230 */ + CALL(sys_fgetxattr) + CALL(sys_listxattr) + CALL(sys_llistxattr) + CALL(sys_flistxattr) + CALL(sys_removexattr) /* 235 */ + CALL(sys_lremovexattr) + CALL(sys_fremovexattr) + CALL(sys_tkill) + CALL(sys_sendfile64) + CALL(sys_futex) /* 240 */ + CALL(sys_sched_setaffinity) + CALL(sys_sched_getaffinity) + CALL(sys_ni_syscall) + CALL(sys_ni_syscall) + CALL(sys_io_setup) /* 245 */ + CALL(sys_io_destroy) + CALL(sys_io_getevents) + CALL(sys_io_submit) + CALL(sys_io_cancel) + CALL(sys_fadvise64) /* 250 */ + CALL(sys_ni_syscall) + CALL(sys_exit_group) + CALL(sys_lookup_dcookie) + CALL(sys_epoll_create) + CALL(sys_epoll_ctl) /* 255 */ + CALL(sys_epoll_wait) + CALL(sys_ni_syscall) /* sys_remap_file_pages */ + CALL(sys_set_tid_address) + CALL(sys_timer_create) + CALL(sys_timer_settime) /* 260 */ + CALL(sys_timer_gettime) + CALL(sys_timer_getoverrun) + CALL(sys_timer_delete) + CALL(sys_clock_settime) + CALL(sys_clock_gettime) /* 265 */ + CALL(sys_clock_getres) + CALL(sys_clock_nanosleep) + CALL(sys_statfs64) + CALL(sys_fstatfs64) + CALL(sys_tgkill) /* 270 */ + CALL(sys_utimes) + CALL(sys_fadvise64_64) + CALL(sys_ni_syscall) /* sys_vserver */ + CALL(sys_ni_syscall) + CALL(sys_get_mempolicy) /* 275 */ + CALL(sys_set_mempolicy) + CALL(sys_mq_open) + CALL(sys_mq_unlink) + CALL(sys_mq_timedsend) + CALL(sys_mq_timedreceive) /* 280 */ + CALL(sys_mq_notify) + CALL(sys_mq_getsetattr) + CALL(sys_waitid) + CALL(sys_ni_syscall) /* sys_kexec_load */ + CALL(sys_add_key) /* 285 */ + CALL(sys_request_key) + CALL(sys_keyctl) + CALL(sys_ioprio_set) + CALL(sys_ioprio_get) /* 290 */ + CALL(sys_inotify_init) + CALL(sys_inotify_add_watch) + CALL(sys_inotify_rm_watch) + CALL(sys_migrate_pages) + CALL(sys_openat) /* 295 */ + CALL(sys_mkdirat) + CALL(sys_mknodat) + CALL(sys_fchownat) + CALL(sys_futimesat) + CALL(sys_fstatat64) /* 300 */ + CALL(sys_unlinkat) + CALL(sys_renameat) + CALL(sys_linkat) + CALL(sys_symlinkat) + CALL(sys_readlinkat) /* 305 */ + CALL(sys_fchmodat) + CALL(sys_faccessat) + CALL(sys_ni_syscall) /* sys_pselect6 */ + CALL(sys_ni_syscall) /* sys_ppoll */ + CALL(sys_unshare) /* 310 */ + CALL(sys_set_robust_list) + CALL(sys_get_robust_list) + CALL(sys_splice) + CALL(sys_sync_file_range) + CALL(sys_tee) /* 315 */ + CALL(sys_vmsplice) + CALL(sys_ni_syscall) /* sys_move_pages */ + CALL(sys_getcpu) + CALL(sys_ni_syscall) /* sys_epoll_pwait */ + CALL(sys_setns) /* 320 */ diff --git a/arch/h8300/lib/abs.S b/arch/h8300/lib/abs.S index cabdd46b41db..ddd1fb3d01ad 100644 --- a/arch/h8300/lib/abs.S +++ b/arch/h8300/lib/abs.S @@ -9,10 +9,10 @@ .h8300s #endif .text -.global SYMBOL_NAME(abs) +.global _abs ;;; int abs(int n) -SYMBOL_NAME_LABEL(abs) +_abs: mov.l er0,er0 bpl 1f neg.l er0 diff --git a/arch/h8300/lib/memcpy.S b/arch/h8300/lib/memcpy.S index fdcbc1ee673c..cad325e2c0e8 100644 --- a/arch/h8300/lib/memcpy.S +++ b/arch/h8300/lib/memcpy.S @@ -10,10 +10,10 @@ #endif .text -.global SYMBOL_NAME(memcpy) +.global _memcpy ;;; void *memcpy(void *to, void *from, size_t n) -SYMBOL_NAME_LABEL(memcpy) +_memcpy: mov.l er2,er2 bne 1f rts diff --git a/arch/h8300/lib/memset.S b/arch/h8300/lib/memset.S index 59abdf9485a5..4549a64c5b79 100644 --- a/arch/h8300/lib/memset.S +++ b/arch/h8300/lib/memset.S @@ -10,13 +10,13 @@ #endif .text -.global SYMBOL_NAME(memset) +.global _memset ;;void *memset(*ptr, int c, size_t count) ;; ptr = er0 ;; c = er1(r1l) ;; count = er2 -SYMBOL_NAME_LABEL(memset) +_memset: btst #0,r0l beq 2f diff --git a/arch/h8300/platform/h8300h/aki3068net/crt0_ram.S b/arch/h8300/platform/h8300h/aki3068net/crt0_ram.S index ecaeb31ae9a4..b2ad0f2d0417 100644 --- a/arch/h8300/platform/h8300h/aki3068net/crt0_ram.S +++ b/arch/h8300/platform/h8300h/aki3068net/crt0_ram.S @@ -22,10 +22,10 @@ #define RAMEND CONFIG_BLKDEV_RESERVE_ADDRESS #endif - .global SYMBOL_NAME(_start) - .global SYMBOL_NAME(command_line) - .global SYMBOL_NAME(_platform_gpio_table) - .global SYMBOL_NAME(_target_name) + .global __start + .global _command_line + .global __platform_gpio_table + .global __target_name .h8300h @@ -33,7 +33,7 @@ .file "crt0_ram.S" /* CPU Reset entry */ -SYMBOL_NAME_LABEL(_start) +__start: mov.l #RAMEND,sp ldc #0x80,ccr @@ -59,13 +59,13 @@ SYMBOL_NAME_LABEL(_start) /* copy kernel commandline */ mov.l #COMMAND_START,er5 - mov.l #SYMBOL_NAME(command_line),er6 + mov.l #_command_line,er6 mov.w #512,r4 eepmov.w /* uClinux kernel start */ ldc #0x90,ccr /* running kernel */ - mov.l #SYMBOL_NAME(init_thread_union),sp + mov.l #_init_thread_union,sp add.l #0x2000,sp jsr @_start_kernel _exit: @@ -107,4 +107,4 @@ __target_name: .asciz "AE-3068" .section .bootvec,"ax" - jmp @SYMBOL_NAME(_start) + jmp @__start diff --git a/arch/h8300/platform/h8300h/generic/crt0_ram.S b/arch/h8300/platform/h8300h/generic/crt0_ram.S index 80d0e16a4499..5ab7d9c12910 100644 --- a/arch/h8300/platform/h8300h/generic/crt0_ram.S +++ b/arch/h8300/platform/h8300h/generic/crt0_ram.S @@ -22,10 +22,10 @@ #define RAMEND CONFIG_BLKDEV_RESERVE_ADDRESS #endif - .global SYMBOL_NAME(_start) - .global SYMBOL_NAME(command_line) - .global SYMBOL_NAME(_platform_gpio_table) - .global SYMBOL_NAME(_target_name) + .global __start + .global _command_line + .global __platform_gpio_table + .global __target_name .h8300h @@ -33,7 +33,7 @@ .file "crt0_ram.S" /* CPU Reset entry */ -SYMBOL_NAME_LABEL(_start) +__start: mov.l #RAMEND,sp ldc #0x80,ccr @@ -59,13 +59,13 @@ SYMBOL_NAME_LABEL(_start) /* copy kernel commandline */ mov.l #COMMAND_START,er5 - mov.l #SYMBOL_NAME(command_line),er6 + mov.l #_command_line,er6 mov.w #512,r4 eepmov.w /* uClinux kernel start */ ldc #0x90,ccr /* running kernel */ - mov.l #SYMBOL_NAME(init_thread_union),sp + mov.l #_init_thread_union,sp add.l #0x2000,sp jsr @_start_kernel _exit: diff --git a/arch/h8300/platform/h8300h/generic/crt0_rom.S b/arch/h8300/platform/h8300h/generic/crt0_rom.S index 120add7ca832..dda1dfa15a5e 100644 --- a/arch/h8300/platform/h8300h/generic/crt0_rom.S +++ b/arch/h8300/platform/h8300h/generic/crt0_rom.S @@ -12,17 +12,17 @@ #include <asm/linkage.h> - .global SYMBOL_NAME(_start) - .global SYMBOL_NAME(_command_line) - .global SYMBOL_NAME(_platform_gpio_table) - .global SYMBOL_NAME(_target_name) + .global __start + .global __command_line + .global __platform_gpio_table + .global __target_name .h8300h .section .text .file "crt0_rom.S" /* CPU Reset entry */ -SYMBOL_NAME_LABEL(_start) +__start: mov.l #__ramend,sp ldc #0x80,ccr @@ -60,13 +60,13 @@ SYMBOL_NAME_LABEL(_start) /* copy kernel commandline */ mov.l #COMMAND_START,er5 - mov.l #SYMBOL_NAME(_command_line),er6 + mov.l #__command_line,er6 mov.w #512,r4 eepmov.w /* linux kernel start */ ldc #0x90,ccr /* running kernel */ - mov.l #SYMBOL_NAME(init_thread_union),sp + mov.l #_init_thread_union,sp add.l #0x2000,sp jsr @_start_kernel _exit: diff --git a/arch/h8300/platform/h8300h/h8max/crt0_ram.S b/arch/h8300/platform/h8300h/h8max/crt0_ram.S index efcbefb91b67..6a0d4e2d9ec6 100644 --- a/arch/h8300/platform/h8300h/h8max/crt0_ram.S +++ b/arch/h8300/platform/h8300h/h8max/crt0_ram.S @@ -22,10 +22,10 @@ #define RAMEND CONFIG_BLKDEV_RESERVE_ADDRESS #endif - .global SYMBOL_NAME(_start) - .global SYMBOL_NAME(command_line) - .global SYMBOL_NAME(_platform_gpio_table) - .global SYMBOL_NAME(_target_name) + .global __start + .global _command_line + .global __platform_gpio_table + .global __target_name .h8300h @@ -33,7 +33,7 @@ .file "crt0_ram.S" /* CPU Reset entry */ -SYMBOL_NAME_LABEL(_start) +__start: mov.l #RAMEND,sp ldc #0x80,ccr @@ -59,13 +59,13 @@ SYMBOL_NAME_LABEL(_start) /* copy kernel commandline */ mov.l #COMMAND_START,er5 - mov.l #SYMBOL_NAME(command_line),er6 + mov.l #_command_line,er6 mov.w #512,r4 eepmov.w /* uClinux kernel start */ ldc #0x90,ccr /* running kernel */ - mov.l #SYMBOL_NAME(init_thread_union),sp + mov.l #_init_thread_union,sp add.l #0x2000,sp jsr @_start_kernel _exit: @@ -107,4 +107,4 @@ __target_name: .asciz "H8MAX" .section .bootvec,"ax" - jmp @SYMBOL_NAME(_start) + jmp @__start diff --git a/arch/h8300/platform/h8s/edosk2674/crt0_ram.S b/arch/h8300/platform/h8s/edosk2674/crt0_ram.S index d12b0debe478..5ed191b37cde 100644 --- a/arch/h8300/platform/h8s/edosk2674/crt0_ram.S +++ b/arch/h8300/platform/h8s/edosk2674/crt0_ram.S @@ -23,10 +23,10 @@ #define RAMEND CONFIG_BLKDEV_RESERVE_ADDRESS #endif - .global SYMBOL_NAME(_start) - .global SYMBOL_NAME(_command_line) - .global SYMBOL_NAME(_platform_gpio_table) - .global SYMBOL_NAME(_target_name) + .global __start + .global __command_line + .global __platform_gpio_table + .global __target_name .h8300s @@ -34,7 +34,7 @@ .file "crt0_ram.S" /* CPU Reset entry */ -SYMBOL_NAME_LABEL(_start) +__start: mov.l #RAMEND,sp ldc #0x80,ccr ldc #0x00,exr @@ -66,13 +66,13 @@ SYMBOL_NAME_LABEL(_start) /* copy kernel commandline */ mov.l #COMMAND_START,er5 - mov.l #SYMBOL_NAME(command_line),er6 + mov.l #_command_line,er6 mov.w #512,r4 eepmov.w /* uClinux kernel start */ ldc #0x90,ccr /* running kernel */ - mov.l #SYMBOL_NAME(init_thread_union),sp + mov.l #_init_thread_union,sp add.l #0x2000,sp jsr @_start_kernel _exit: @@ -127,4 +127,4 @@ __target_name: .asciz "EDOSK-2674" .section .bootvec,"ax" - jmp @SYMBOL_NAME(_start) + jmp @__start diff --git a/arch/h8300/platform/h8s/edosk2674/crt0_rom.S b/arch/h8300/platform/h8s/edosk2674/crt0_rom.S index c03d23c6fe12..06d1d7f324ca 100644 --- a/arch/h8300/platform/h8s/edosk2674/crt0_rom.S +++ b/arch/h8300/platform/h8s/edosk2674/crt0_rom.S @@ -13,17 +13,17 @@ #include <asm/linkage.h> #include <asm/regs267x.h> - .global SYMBOL_NAME(_start) - .global SYMBOL_NAME(_command_line) - .global SYMBOL_NAME(_platform_gpio_table) - .global SYMBOL_NAME(_target_name) + .global __start + .global __command_line + .global __platform_gpio_table + .global __target_name .h8300s .section .text .file "crt0_rom.S" /* CPU Reset entry */ -SYMBOL_NAME_LABEL(_start) +__start: mov.l #__ramend,sp ldc #0x80,ccr ldc #0,exr @@ -82,13 +82,13 @@ SYMBOL_NAME_LABEL(_start) /* copy kernel commandline */ mov.l #COMMAND_START,er5 - mov.l #SYMBOL_NAME(_command_line),er6 + mov.l #__command_line,er6 mov.w #512,r4 eepmov.w /* linux kernel start */ ldc #0x90,ccr /* running kernel */ - mov.l #SYMBOL_NAME(init_thread_union),sp + mov.l #_init_thread_union,sp add.l #0x2000,sp jsr @_start_kernel _exit: diff --git a/arch/h8300/platform/h8s/generic/crt0_ram.S b/arch/h8300/platform/h8s/generic/crt0_ram.S index b04541069976..7018915de74f 100644 --- a/arch/h8300/platform/h8s/generic/crt0_ram.S +++ b/arch/h8300/platform/h8s/generic/crt0_ram.S @@ -23,10 +23,10 @@ #define RAMEND CONFIG_BLKDEV_RESERVE_ADDRESS #endif - .global SYMBOL_NAME(_start) - .global SYMBOL_NAME(_command_line) - .global SYMBOL_NAME(_platform_gpio_table) - .global SYMBOL_NAME(_target_name) + .global __start + .global __command_line + .global __platform_gpio_table + .global __target_name .h8300s @@ -34,7 +34,7 @@ .file "crt0_ram.S" /* CPU Reset entry */ -SYMBOL_NAME_LABEL(_start) +__start: mov.l #RAMEND,sp ldc #0x80,ccr ldc #0x00,exr @@ -63,13 +63,13 @@ SYMBOL_NAME_LABEL(_start) /* copy kernel commandline */ mov.l #COMMAND_START,er5 - mov.l #SYMBOL_NAME(command_line),er6 + mov.l #_command_line,er6 mov.w #512,r4 eepmov.w /* uClinux kernel start */ ldc #0x90,ccr /* running kernel */ - mov.l #SYMBOL_NAME(init_thread_union),sp + mov.l #_init_thread_union,sp add.l #0x2000,sp jsr @_start_kernel _exit: @@ -124,4 +124,4 @@ __target_name: .asciz "generic" .section .bootvec,"ax" - jmp @SYMBOL_NAME(_start) + jmp @__start diff --git a/arch/h8300/platform/h8s/generic/crt0_rom.S b/arch/h8300/platform/h8s/generic/crt0_rom.S index 95b6f2898f52..623ba7828193 100644 --- a/arch/h8300/platform/h8s/generic/crt0_rom.S +++ b/arch/h8300/platform/h8s/generic/crt0_rom.S @@ -13,17 +13,17 @@ #include <asm/linkage.h> #include <asm/regs267x.h> - .global SYMBOL_NAME(_start) - .global SYMBOL_NAME(_command_line) - .global SYMBOL_NAME(_platform_gpio_table) - .global SYMBOL_NAME(_target_name) + .global __start + .global __command_line + .global __platform_gpio_table + .global __target_name .h8300s .section .text .file "crt0_rom.S" /* CPU Reset entry */ -SYMBOL_NAME_LABEL(_start) +__start: mov.l #__ramend,sp ldc #0x80,ccr ldc #0,exr @@ -61,7 +61,7 @@ SYMBOL_NAME_LABEL(_start) /* linux kernel start */ ldc #0x90,ccr /* running kernel */ - mov.l #SYMBOL_NAME(init_thread_union),sp + mov.l #_init_thread_union,sp add.l #0x2000,sp jsr @_start_kernel _exit: diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c index bcda5b2d121a..d43daf192b21 100644 --- a/arch/ia64/hp/common/sba_iommu.c +++ b/arch/ia64/hp/common/sba_iommu.c @@ -2042,7 +2042,8 @@ sba_map_ioc_to_node(struct ioc *ioc, acpi_handle handle) #endif static int __init -acpi_sba_ioc_add(struct acpi_device *device) +acpi_sba_ioc_add(struct acpi_device *device, + const struct acpi_device_id *not_used) { struct ioc *ioc; acpi_status status; @@ -2090,14 +2091,18 @@ static const struct acpi_device_id hp_ioc_iommu_device_ids[] = { {"HWP0004", 0}, {"", 0}, }; -static struct acpi_driver acpi_sba_ioc_driver = { - .name = "IOC IOMMU Driver", - .ids = hp_ioc_iommu_device_ids, - .ops = { - .add = acpi_sba_ioc_add, - }, +static struct acpi_scan_handler acpi_sba_ioc_handler = { + .ids = hp_ioc_iommu_device_ids, + .attach = acpi_sba_ioc_add, }; +static int __init acpi_sba_ioc_init_acpi(void) +{ + return acpi_scan_add_handler(&acpi_sba_ioc_handler); +} +/* This has to run before acpi_scan_init(). */ +arch_initcall(acpi_sba_ioc_init_acpi); + extern struct dma_map_ops swiotlb_dma_ops; static int __init @@ -2122,7 +2127,10 @@ sba_init(void) } #endif - acpi_bus_register_driver(&acpi_sba_ioc_driver); + /* + * ioc_list should be populated by the acpi_sba_ioc_handler's .attach() + * routine, but that only happens if acpi_scan_init() has already run. + */ if (!ioc_list) { #ifdef CONFIG_IA64_GENERIC /* diff --git a/arch/ia64/hp/sim/simscsi.c b/arch/ia64/hp/sim/simscsi.c index 331de723c676..3a428f19a001 100644 --- a/arch/ia64/hp/sim/simscsi.c +++ b/arch/ia64/hp/sim/simscsi.c @@ -88,8 +88,8 @@ simscsi_setup (char *s) if (strlen(s) > MAX_ROOT_LEN) { printk(KERN_ERR "simscsi_setup: prefix too long---using default %s\n", simscsi_root); - } - simscsi_root = s; + } else + simscsi_root = s; return 1; } diff --git a/arch/ia64/include/asm/pci.h b/arch/ia64/include/asm/pci.h index 5e04b591e423..80775f55f03f 100644 --- a/arch/ia64/include/asm/pci.h +++ b/arch/ia64/include/asm/pci.h @@ -89,9 +89,9 @@ extern int pci_mmap_legacy_page_range(struct pci_bus *bus, #define pci_legacy_read platform_pci_legacy_read #define pci_legacy_write platform_pci_legacy_write -struct pci_window { - struct resource resource; - u64 offset; +struct iospace_resource { + struct list_head list; + struct resource res; }; struct pci_controller { @@ -100,12 +100,10 @@ struct pci_controller { int segment; int node; /* nearest node with memory or -1 for global allocation */ - unsigned int windows; - struct pci_window *window; - void *platform_data; }; + #define PCI_CONTROLLER(busdev) ((struct pci_controller *) busdev->sysdata) #define pci_domain_nr(busdev) (PCI_CONTROLLER(busdev)->segment) diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index 335eb07480fe..5eb71d22c3d5 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -807,7 +807,7 @@ int acpi_isa_irq_to_gsi(unsigned isa_irq, u32 *gsi) * ACPI based hotplug CPU support */ #ifdef CONFIG_ACPI_HOTPLUG_CPU -static __cpuinit +static int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) { #ifdef CONFIG_ACPI_NUMA @@ -882,7 +882,7 @@ __init void prefill_possible_map(void) set_cpu_possible(i, true); } -static int __cpuinit _acpi_map_lsapic(acpi_handle handle, int *pcpu) +static int _acpi_map_lsapic(acpi_handle handle, int *pcpu) { struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; union acpi_object *obj; diff --git a/arch/ia64/kernel/err_inject.c b/arch/ia64/kernel/err_inject.c index 2d67317a1ec2..f59c0b844e88 100644 --- a/arch/ia64/kernel/err_inject.c +++ b/arch/ia64/kernel/err_inject.c @@ -225,17 +225,17 @@ static struct attribute_group err_inject_attr_group = { .name = "err_inject" }; /* Add/Remove err_inject interface for CPU device */ -static int __cpuinit err_inject_add_dev(struct device * sys_dev) +static int err_inject_add_dev(struct device *sys_dev) { return sysfs_create_group(&sys_dev->kobj, &err_inject_attr_group); } -static int __cpuinit err_inject_remove_dev(struct device * sys_dev) +static int err_inject_remove_dev(struct device *sys_dev) { sysfs_remove_group(&sys_dev->kobj, &err_inject_attr_group); return 0; } -static int __cpuinit err_inject_cpu_callback(struct notifier_block *nfb, +static int err_inject_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { unsigned int cpu = (unsigned long)hcpu; @@ -256,7 +256,7 @@ static int __cpuinit err_inject_cpu_callback(struct notifier_block *nfb, return NOTIFY_OK; } -static struct notifier_block __cpuinitdata err_inject_cpu_notifier = +static struct notifier_block err_inject_cpu_notifier = { .notifier_call = err_inject_cpu_callback, }; diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index d7396dbb07bb..b8edfa75a83f 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -631,7 +631,7 @@ ia64_mca_register_cpev (int cpev) * Outputs * None */ -void __cpuinit +void ia64_mca_cmc_vector_setup (void) { cmcv_reg_t cmcv; @@ -1814,7 +1814,7 @@ static struct irqaction mca_cpep_irqaction = { * format most of the fields. */ -static void __cpuinit +static void format_mca_init_stack(void *mca_data, unsigned long offset, const char *type, int cpu) { @@ -1844,7 +1844,7 @@ static void * __init_refok mca_bootmem(void) } /* Do per-CPU MCA-related initialization. */ -void __cpuinit +void ia64_mca_cpu_init(void *cpu_data) { void *pal_vaddr; @@ -1896,7 +1896,7 @@ ia64_mca_cpu_init(void *cpu_data) PAGE_KERNEL)); } -static void __cpuinit ia64_mca_cmc_vector_adjust(void *dummy) +static void ia64_mca_cmc_vector_adjust(void *dummy) { unsigned long flags; @@ -1906,7 +1906,7 @@ static void __cpuinit ia64_mca_cmc_vector_adjust(void *dummy) local_irq_restore(flags); } -static int __cpuinit mca_cpu_callback(struct notifier_block *nfb, +static int mca_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { @@ -1922,7 +1922,7 @@ static int __cpuinit mca_cpu_callback(struct notifier_block *nfb, return NOTIFY_OK; } -static struct notifier_block mca_cpu_notifier __cpuinitdata = { +static struct notifier_block mca_cpu_notifier = { .notifier_call = mca_cpu_callback }; diff --git a/arch/ia64/kernel/numa.c b/arch/ia64/kernel/numa.c index c93420c97409..d288cde93606 100644 --- a/arch/ia64/kernel/numa.c +++ b/arch/ia64/kernel/numa.c @@ -30,7 +30,7 @@ EXPORT_SYMBOL(cpu_to_node_map); cpumask_t node_to_cpu_mask[MAX_NUMNODES] __cacheline_aligned; EXPORT_SYMBOL(node_to_cpu_mask); -void __cpuinit map_cpu_to_node(int cpu, int nid) +void map_cpu_to_node(int cpu, int nid) { int oldnid; if (nid < 0) { /* just initialize by zero */ @@ -51,7 +51,7 @@ void __cpuinit map_cpu_to_node(int cpu, int nid) return; } -void __cpuinit unmap_cpu_from_node(int cpu, int nid) +void unmap_cpu_from_node(int cpu, int nid) { WARN_ON(!cpu_isset(cpu, node_to_cpu_mask[nid])); WARN_ON(cpu_to_node_map[cpu] != nid); diff --git a/arch/ia64/kernel/palinfo.c b/arch/ia64/kernel/palinfo.c index 2b3c2d79256f..ab333284f4b2 100644 --- a/arch/ia64/kernel/palinfo.c +++ b/arch/ia64/kernel/palinfo.c @@ -932,7 +932,7 @@ static const struct file_operations proc_palinfo_fops = { .release = single_release, }; -static void __cpuinit +static void create_palinfo_proc_entries(unsigned int cpu) { pal_func_cpu_u_t f; @@ -962,7 +962,7 @@ remove_palinfo_proc_entries(unsigned int hcpu) remove_proc_subtree(cpustr, palinfo_dir); } -static int __cpuinit palinfo_cpu_callback(struct notifier_block *nfb, +static int palinfo_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { unsigned int hotcpu = (unsigned long)hcpu; diff --git a/arch/ia64/kernel/pci-dma.c b/arch/ia64/kernel/pci-dma.c index 1ddcfe5ef353..992c1098c522 100644 --- a/arch/ia64/kernel/pci-dma.c +++ b/arch/ia64/kernel/pci-dma.c @@ -33,15 +33,6 @@ int force_iommu __read_mostly; int iommu_pass_through; -/* Dummy device used for NULL arguments (normally ISA). Better would - be probably a smaller DMA mask, but this is bug-to-bug compatible - to i386. */ -struct device fallback_dev = { - .init_name = "fallback device", - .coherent_dma_mask = DMA_BIT_MASK(32), - .dma_mask = &fallback_dev.coherent_dma_mask, -}; - extern struct dma_map_ops intel_dma_ops; static int __init pci_iommu_init(void) diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index 9ea25fce06d5..5a9ff1c3c3e9 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -5647,24 +5647,8 @@ pfm_proc_show_header(struct seq_file *m) list_for_each(pos, &pfm_buffer_fmt_list) { entry = list_entry(pos, pfm_buffer_fmt_t, fmt_list); - seq_printf(m, "format : %02x-%02x-%02x-%02x-%02x-%02x-%02x-%02x-%02x-%02x-%02x-%02x-%02x-%02x-%02x-%02x %s\n", - entry->fmt_uuid[0], - entry->fmt_uuid[1], - entry->fmt_uuid[2], - entry->fmt_uuid[3], - entry->fmt_uuid[4], - entry->fmt_uuid[5], - entry->fmt_uuid[6], - entry->fmt_uuid[7], - entry->fmt_uuid[8], - entry->fmt_uuid[9], - entry->fmt_uuid[10], - entry->fmt_uuid[11], - entry->fmt_uuid[12], - entry->fmt_uuid[13], - entry->fmt_uuid[14], - entry->fmt_uuid[15], - entry->fmt_name); + seq_printf(m, "format : %16phD %s\n", + entry->fmt_uuid, entry->fmt_name); } spin_unlock(&pfm_buffer_fmt_lock); diff --git a/arch/ia64/kernel/salinfo.c b/arch/ia64/kernel/salinfo.c index 4bc580af67b3..960a396f5929 100644 --- a/arch/ia64/kernel/salinfo.c +++ b/arch/ia64/kernel/salinfo.c @@ -568,7 +568,7 @@ static const struct file_operations salinfo_data_fops = { .llseek = default_llseek, }; -static int __cpuinit +static int salinfo_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu) { unsigned int i, cpu = (unsigned long)hcpu; @@ -609,7 +609,7 @@ salinfo_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu return NOTIFY_OK; } -static struct notifier_block salinfo_cpu_notifier __cpuinitdata = +static struct notifier_block salinfo_cpu_notifier = { .notifier_call = salinfo_cpu_callback, .priority = 0, diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index 13bfdd22afc8..4fc2e9569bb2 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -748,7 +748,7 @@ const struct seq_operations cpuinfo_op = { #define MAX_BRANDS 8 static char brandname[MAX_BRANDS][128]; -static char * __cpuinit +static char * get_model_name(__u8 family, __u8 model) { static int overflow; @@ -778,7 +778,7 @@ get_model_name(__u8 family, __u8 model) return "Unknown"; } -static void __cpuinit +static void identify_cpu (struct cpuinfo_ia64 *c) { union { @@ -850,7 +850,7 @@ identify_cpu (struct cpuinfo_ia64 *c) * 2. the minimum of the i-cache stride sizes for "flush_icache_range()". * 3. the minimum of the cache stride sizes for "clflush_cache_range()". */ -static void __cpuinit +static void get_cache_info(void) { unsigned long line_size, max = 1; @@ -915,10 +915,10 @@ get_cache_info(void) * cpu_init() initializes state that is per-CPU. This function acts * as a 'CPU state barrier', nothing should get across. */ -void __cpuinit +void cpu_init (void) { - extern void __cpuinit ia64_mmu_init (void *); + extern void ia64_mmu_init(void *); static unsigned long max_num_phys_stacked = IA64_NUM_PHYS_STACK_REG; unsigned long num_phys_stacked; pal_vm_info_2_u_t vmi; diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c index 8d87168d218d..547a48d78bd7 100644 --- a/arch/ia64/kernel/smpboot.c +++ b/arch/ia64/kernel/smpboot.c @@ -351,7 +351,7 @@ static inline void smp_setup_percpu_timer(void) { } -static void __cpuinit +static void smp_callin (void) { int cpuid, phys_id, itc_master; @@ -442,7 +442,7 @@ smp_callin (void) /* * Activate a secondary processor. head.S calls this. */ -int __cpuinit +int start_secondary (void *unused) { /* Early console may use I/O ports */ @@ -459,7 +459,7 @@ start_secondary (void *unused) return 0; } -static int __cpuinit +static int do_boot_cpu (int sapicid, int cpu, struct task_struct *idle) { int timeout; @@ -728,7 +728,7 @@ static inline void set_cpu_sibling_map(int cpu) } } -int __cpuinit +int __cpu_up(unsigned int cpu, struct task_struct *tidle) { int ret; diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c index dc00b2c1b42a..ca69a5a96dcc 100644 --- a/arch/ia64/kernel/topology.c +++ b/arch/ia64/kernel/topology.c @@ -135,11 +135,11 @@ struct cpu_cache_info { struct kobject kobj; }; -static struct cpu_cache_info all_cpu_cache_info[NR_CPUS] __cpuinitdata; +static struct cpu_cache_info all_cpu_cache_info[NR_CPUS]; #define LEAF_KOBJECT_PTR(x,y) (&all_cpu_cache_info[x].cache_leaves[y]) #ifdef CONFIG_SMP -static void __cpuinit cache_shared_cpu_map_setup( unsigned int cpu, +static void cache_shared_cpu_map_setup(unsigned int cpu, struct cache_info * this_leaf) { pal_cache_shared_info_t csi; @@ -174,7 +174,7 @@ static void __cpuinit cache_shared_cpu_map_setup( unsigned int cpu, &csi) == PAL_STATUS_SUCCESS); } #else -static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, +static void cache_shared_cpu_map_setup(unsigned int cpu, struct cache_info * this_leaf) { cpu_set(cpu, this_leaf->shared_cpu_map); @@ -298,7 +298,7 @@ static struct kobj_type cache_ktype_percpu_entry = { .sysfs_ops = &cache_sysfs_ops, }; -static void __cpuinit cpu_cache_sysfs_exit(unsigned int cpu) +static void cpu_cache_sysfs_exit(unsigned int cpu) { kfree(all_cpu_cache_info[cpu].cache_leaves); all_cpu_cache_info[cpu].cache_leaves = NULL; @@ -307,7 +307,7 @@ static void __cpuinit cpu_cache_sysfs_exit(unsigned int cpu) return; } -static int __cpuinit cpu_cache_sysfs_init(unsigned int cpu) +static int cpu_cache_sysfs_init(unsigned int cpu) { unsigned long i, levels, unique_caches; pal_cache_config_info_t cci; @@ -351,7 +351,7 @@ static int __cpuinit cpu_cache_sysfs_init(unsigned int cpu) } /* Add cache interface for CPU device */ -static int __cpuinit cache_add_dev(struct device * sys_dev) +static int cache_add_dev(struct device *sys_dev) { unsigned int cpu = sys_dev->id; unsigned long i, j; @@ -401,7 +401,7 @@ static int __cpuinit cache_add_dev(struct device * sys_dev) } /* Remove cache interface for CPU device */ -static int __cpuinit cache_remove_dev(struct device * sys_dev) +static int cache_remove_dev(struct device *sys_dev) { unsigned int cpu = sys_dev->id; unsigned long i; @@ -425,7 +425,7 @@ static int __cpuinit cache_remove_dev(struct device * sys_dev) * When a cpu is hot-plugged, do a check and initiate * cache kobject if necessary */ -static int __cpuinit cache_cpu_callback(struct notifier_block *nfb, +static int cache_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { unsigned int cpu = (unsigned long)hcpu; @@ -445,7 +445,7 @@ static int __cpuinit cache_cpu_callback(struct notifier_block *nfb, return NOTIFY_OK; } -static struct notifier_block __cpuinitdata cache_cpu_notifier = +static struct notifier_block cache_cpu_notifier = { .notifier_call = cache_cpu_callback }; diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c index f7f9f9c6caf0..d3636e67a98e 100644 --- a/arch/ia64/kernel/traps.c +++ b/arch/ia64/kernel/traps.c @@ -630,7 +630,7 @@ ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa, printk(KERN_ERR " iip - 0x%lx, ifa - 0x%lx, isr - 0x%lx\n", iip, ifa, isr); force_sig(SIGSEGV, current); - break; + return; case 46: printk(KERN_ERR "Unexpected IA-32 intercept trap (Trap 46)\n"); diff --git a/arch/ia64/kvm/Makefile b/arch/ia64/kvm/Makefile index 1a4053789d01..18e45ec49bbf 100644 --- a/arch/ia64/kvm/Makefile +++ b/arch/ia64/kvm/Makefile @@ -47,12 +47,13 @@ FORCE : $(obj)/$(offsets-file) ccflags-y := -Ivirt/kvm -Iarch/ia64/kvm/ asflags-y := -Ivirt/kvm -Iarch/ia64/kvm/ +KVM := ../../../virt/kvm -common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \ - coalesced_mmio.o irq_comm.o) +common-objs = $(KVM)/kvm_main.o $(KVM)/ioapic.o \ + $(KVM)/coalesced_mmio.o $(KVM)/irq_comm.o ifeq ($(CONFIG_KVM_DEVICE_ASSIGNMENT),y) -common-objs += $(addprefix ../../../virt/kvm/, assigned-dev.o iommu.o) +common-objs += $(KVM)/assigned-dev.o $(KVM)/iommu.o endif kvm-objs := $(common-objs) kvm-ia64.o kvm_fw.o diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c index e4a6a5366dea..da5237d636d6 100644 --- a/arch/ia64/mm/contig.c +++ b/arch/ia64/mm/contig.c @@ -156,8 +156,7 @@ static void *cpu_data; * * Allocate and setup per-cpu data areas. */ -void * __cpuinit -per_cpu_init (void) +void *per_cpu_init(void) { static bool first_time = true; void *cpu0_data = __cpu0_per_cpu; diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index 58550b8f7d40..2de08f4d9930 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -592,7 +592,7 @@ void __init find_memory(void) * find_pernode_space() does most of this already, we just need to set * local_per_cpu_offset */ -void __cpuinit *per_cpu_init(void) +void *per_cpu_init(void) { int cpu; static int first_time = 1; diff --git a/arch/ia64/mm/numa.c b/arch/ia64/mm/numa.c index 4248492b9321..ea21d4cad540 100644 --- a/arch/ia64/mm/numa.c +++ b/arch/ia64/mm/numa.c @@ -86,7 +86,7 @@ int __meminit __early_pfn_to_nid(unsigned long pfn) return -1; } -void __cpuinit numa_clear_node(int cpu) +void numa_clear_node(int cpu) { unmap_cpu_from_node(cpu, NUMA_NO_NODE); } diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c index de1474ff0bc5..2326790b7d8b 100644 --- a/arch/ia64/pci/pci.c +++ b/arch/ia64/pci/pci.c @@ -134,6 +134,10 @@ struct pci_root_info { struct acpi_device *bridge; struct pci_controller *controller; struct list_head resources; + struct resource *res; + resource_size_t *res_offset; + unsigned int res_num; + struct list_head io_resources; char *name; }; @@ -153,7 +157,7 @@ new_space (u64 phys_base, int sparse) return i; if (num_io_spaces == MAX_IO_SPACES) { - printk(KERN_ERR "PCI: Too many IO port spaces " + pr_err("PCI: Too many IO port spaces " "(MAX_IO_SPACES=%lu)\n", MAX_IO_SPACES); return ~0; } @@ -168,25 +172,22 @@ new_space (u64 phys_base, int sparse) static u64 add_io_space(struct pci_root_info *info, struct acpi_resource_address64 *addr) { + struct iospace_resource *iospace; struct resource *resource; char *name; unsigned long base, min, max, base_port; unsigned int sparse = 0, space_nr, len; - resource = kzalloc(sizeof(*resource), GFP_KERNEL); - if (!resource) { - printk(KERN_ERR "PCI: No memory for %s I/O port space\n", - info->name); + len = strlen(info->name) + 32; + iospace = kzalloc(sizeof(*iospace) + len, GFP_KERNEL); + if (!iospace) { + dev_err(&info->bridge->dev, + "PCI: No memory for %s I/O port space\n", + info->name); goto out; } - len = strlen(info->name) + 32; - name = kzalloc(len, GFP_KERNEL); - if (!name) { - printk(KERN_ERR "PCI: No memory for %s I/O port space name\n", - info->name); - goto free_resource; - } + name = (char *)(iospace + 1); min = addr->minimum; max = min + addr->address_length - 1; @@ -195,7 +196,7 @@ static u64 add_io_space(struct pci_root_info *info, space_nr = new_space(addr->translation_offset, sparse); if (space_nr == ~0) - goto free_name; + goto free_resource; base = __pa(io_space[space_nr].mmio_base); base_port = IO_SPACE_BASE(space_nr); @@ -210,18 +211,23 @@ static u64 add_io_space(struct pci_root_info *info, if (space_nr == 0) sparse = 1; + resource = &iospace->res; resource->name = name; resource->flags = IORESOURCE_MEM; resource->start = base + (sparse ? IO_SPACE_SPARSE_ENCODING(min) : min); resource->end = base + (sparse ? IO_SPACE_SPARSE_ENCODING(max) : max); - insert_resource(&iomem_resource, resource); + if (insert_resource(&iomem_resource, resource)) { + dev_err(&info->bridge->dev, + "can't allocate host bridge io space resource %pR\n", + resource); + goto free_resource; + } + list_add_tail(&iospace->list, &info->io_resources); return base_port; -free_name: - kfree(name); free_resource: - kfree(resource); + kfree(iospace); out: return ~0; } @@ -265,7 +271,7 @@ static acpi_status count_window(struct acpi_resource *resource, void *data) static acpi_status add_window(struct acpi_resource *res, void *data) { struct pci_root_info *info = data; - struct pci_window *window; + struct resource *resource; struct acpi_resource_address64 addr; acpi_status status; unsigned long flags, offset = 0; @@ -289,55 +295,146 @@ static acpi_status add_window(struct acpi_resource *res, void *data) } else return AE_OK; - window = &info->controller->window[info->controller->windows++]; - window->resource.name = info->name; - window->resource.flags = flags; - window->resource.start = addr.minimum + offset; - window->resource.end = window->resource.start + addr.address_length - 1; - window->offset = offset; + resource = &info->res[info->res_num]; + resource->name = info->name; + resource->flags = flags; + resource->start = addr.minimum + offset; + resource->end = resource->start + addr.address_length - 1; + info->res_offset[info->res_num] = offset; - if (insert_resource(root, &window->resource)) { + if (insert_resource(root, resource)) { dev_err(&info->bridge->dev, "can't allocate host bridge window %pR\n", - &window->resource); + resource); } else { if (offset) dev_info(&info->bridge->dev, "host bridge window %pR " "(PCI address [%#llx-%#llx])\n", - &window->resource, - window->resource.start - offset, - window->resource.end - offset); + resource, + resource->start - offset, + resource->end - offset); else dev_info(&info->bridge->dev, - "host bridge window %pR\n", - &window->resource); + "host bridge window %pR\n", resource); } - /* HP's firmware has a hack to work around a Windows bug. * Ignore these tiny memory ranges */ - if (!((window->resource.flags & IORESOURCE_MEM) && - (window->resource.end - window->resource.start < 16))) - pci_add_resource_offset(&info->resources, &window->resource, - window->offset); + if (!((resource->flags & IORESOURCE_MEM) && + (resource->end - resource->start < 16))) + pci_add_resource_offset(&info->resources, resource, + info->res_offset[info->res_num]); + info->res_num++; return AE_OK; } +static void free_pci_root_info_res(struct pci_root_info *info) +{ + struct iospace_resource *iospace, *tmp; + + list_for_each_entry_safe(iospace, tmp, &info->io_resources, list) + kfree(iospace); + + kfree(info->name); + kfree(info->res); + info->res = NULL; + kfree(info->res_offset); + info->res_offset = NULL; + info->res_num = 0; + kfree(info->controller); + info->controller = NULL; +} + +static void __release_pci_root_info(struct pci_root_info *info) +{ + int i; + struct resource *res; + struct iospace_resource *iospace; + + list_for_each_entry(iospace, &info->io_resources, list) + release_resource(&iospace->res); + + for (i = 0; i < info->res_num; i++) { + res = &info->res[i]; + + if (!res->parent) + continue; + + if (!(res->flags & (IORESOURCE_MEM | IORESOURCE_IO))) + continue; + + release_resource(res); + } + + free_pci_root_info_res(info); + kfree(info); +} + +static void release_pci_root_info(struct pci_host_bridge *bridge) +{ + struct pci_root_info *info = bridge->release_data; + + __release_pci_root_info(info); +} + +static int +probe_pci_root_info(struct pci_root_info *info, struct acpi_device *device, + int busnum, int domain) +{ + char *name; + + name = kmalloc(16, GFP_KERNEL); + if (!name) + return -ENOMEM; + + sprintf(name, "PCI Bus %04x:%02x", domain, busnum); + info->bridge = device; + info->name = name; + + acpi_walk_resources(device->handle, METHOD_NAME__CRS, count_window, + &info->res_num); + if (info->res_num) { + info->res = + kzalloc_node(sizeof(*info->res) * info->res_num, + GFP_KERNEL, info->controller->node); + if (!info->res) { + kfree(name); + return -ENOMEM; + } + + info->res_offset = + kzalloc_node(sizeof(*info->res_offset) * info->res_num, + GFP_KERNEL, info->controller->node); + if (!info->res_offset) { + kfree(name); + kfree(info->res); + info->res = NULL; + return -ENOMEM; + } + + info->res_num = 0; + acpi_walk_resources(device->handle, METHOD_NAME__CRS, + add_window, info); + } else + kfree(name); + + return 0; +} + struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) { struct acpi_device *device = root->device; int domain = root->segment; int bus = root->secondary.start; struct pci_controller *controller; - unsigned int windows = 0; - struct pci_root_info info; + struct pci_root_info *info = NULL; + int busnum = root->secondary.start; struct pci_bus *pbus; - char *name; - int pxm; + int pxm, ret; controller = alloc_pci_controller(domain); if (!controller) - goto out1; + return NULL; controller->acpi_handle = device->handle; @@ -347,29 +444,27 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) controller->node = pxm_to_node(pxm); #endif - INIT_LIST_HEAD(&info.resources); - /* insert busn resource at first */ - pci_add_resource(&info.resources, &root->secondary); - acpi_walk_resources(device->handle, METHOD_NAME__CRS, count_window, - &windows); - if (windows) { - controller->window = - kzalloc_node(sizeof(*controller->window) * windows, - GFP_KERNEL, controller->node); - if (!controller->window) - goto out2; - - name = kmalloc(16, GFP_KERNEL); - if (!name) - goto out3; - - sprintf(name, "PCI Bus %04x:%02x", domain, bus); - info.bridge = device; - info.controller = controller; - info.name = name; - acpi_walk_resources(device->handle, METHOD_NAME__CRS, - add_window, &info); + info = kzalloc(sizeof(*info), GFP_KERNEL); + if (!info) { + dev_err(&device->dev, + "pci_bus %04x:%02x: ignored (out of memory)\n", + domain, busnum); + kfree(controller); + return NULL; } + + info->controller = controller; + INIT_LIST_HEAD(&info->io_resources); + INIT_LIST_HEAD(&info->resources); + + ret = probe_pci_root_info(info, device, busnum, domain); + if (ret) { + kfree(info->controller); + kfree(info); + return NULL; + } + /* insert busn resource at first */ + pci_add_resource(&info->resources, &root->secondary); /* * See arch/x86/pci/acpi.c. * The desired pci bus might already be scanned in a quirk. We @@ -377,21 +472,17 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) * such quirk. So we just ignore the case now. */ pbus = pci_create_root_bus(NULL, bus, &pci_root_ops, controller, - &info.resources); + &info->resources); if (!pbus) { - pci_free_resource_list(&info.resources); + pci_free_resource_list(&info->resources); + __release_pci_root_info(info); return NULL; } + pci_set_host_bridge_release(to_pci_host_bridge(pbus->bridge), + release_pci_root_info, info); pci_scan_child_bus(pbus); return pbus; - -out3: - kfree(controller->window); -out2: - kfree(controller); -out1: - return NULL; } int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge) @@ -691,7 +782,7 @@ static void __init set_pci_dfl_cacheline_size(void) status = ia64_pal_cache_summary(&levels, &unique_caches); if (status != 0) { - printk(KERN_ERR "%s: ia64_pal_cache_summary() failed " + pr_err("%s: ia64_pal_cache_summary() failed " "(status=%ld)\n", __func__, status); return; } @@ -699,7 +790,7 @@ static void __init set_pci_dfl_cacheline_size(void) status = ia64_pal_cache_config_info(levels - 1, /* cache_type (data_or_unified)= */ 2, &cci); if (status != 0) { - printk(KERN_ERR "%s: ia64_pal_cache_config_info() failed " + pr_err("%s: ia64_pal_cache_config_info() failed " "(status=%ld)\n", __func__, status); return; } diff --git a/arch/ia64/sn/kernel/io_init.c b/arch/ia64/sn/kernel/io_init.c index 238e2c511d94..0b5ce82d203d 100644 --- a/arch/ia64/sn/kernel/io_init.c +++ b/arch/ia64/sn/kernel/io_init.c @@ -118,76 +118,26 @@ static void __init sn_fixup_ionodes(void) } /* - * sn_pci_legacy_window_fixup - Create PCI controller windows for + * sn_pci_legacy_window_fixup - Setup PCI resources for * legacy IO and MEM space. This needs to * be done here, as the PROM does not have * ACPI support defining the root buses * and their resources (_CRS), */ static void -sn_legacy_pci_window_fixup(struct pci_controller *controller, - u64 legacy_io, u64 legacy_mem) +sn_legacy_pci_window_fixup(struct resource *res, + u64 legacy_io, u64 legacy_mem) { - controller->window = kcalloc(2, sizeof(struct pci_window), - GFP_KERNEL); - BUG_ON(controller->window == NULL); - controller->window[0].offset = legacy_io; - controller->window[0].resource.name = "legacy_io"; - controller->window[0].resource.flags = IORESOURCE_IO; - controller->window[0].resource.start = legacy_io; - controller->window[0].resource.end = - controller->window[0].resource.start + 0xffff; - controller->window[0].resource.parent = &ioport_resource; - controller->window[1].offset = legacy_mem; - controller->window[1].resource.name = "legacy_mem"; - controller->window[1].resource.flags = IORESOURCE_MEM; - controller->window[1].resource.start = legacy_mem; - controller->window[1].resource.end = - controller->window[1].resource.start + (1024 * 1024) - 1; - controller->window[1].resource.parent = &iomem_resource; - controller->windows = 2; -} - -/* - * sn_pci_window_fixup() - Create a pci_window for each device resource. - * It will setup pci_windows for use by - * pcibios_bus_to_resource(), pcibios_resource_to_bus(), - * etc. - */ -static void -sn_pci_window_fixup(struct pci_dev *dev, unsigned int count, - s64 * pci_addrs) -{ - struct pci_controller *controller = PCI_CONTROLLER(dev->bus); - unsigned int i; - unsigned int idx; - unsigned int new_count; - struct pci_window *new_window; - - if (count == 0) - return; - idx = controller->windows; - new_count = controller->windows + count; - new_window = kcalloc(new_count, sizeof(struct pci_window), GFP_KERNEL); - BUG_ON(new_window == NULL); - if (controller->window) { - memcpy(new_window, controller->window, - sizeof(struct pci_window) * controller->windows); - kfree(controller->window); - } - - /* Setup a pci_window for each device resource. */ - for (i = 0; i <= PCI_ROM_RESOURCE; i++) { - if (pci_addrs[i] == -1) - continue; - - new_window[idx].offset = dev->resource[i].start - pci_addrs[i]; - new_window[idx].resource = dev->resource[i]; - idx++; - } - - controller->windows = new_count; - controller->window = new_window; + res[0].name = "legacy_io"; + res[0].flags = IORESOURCE_IO; + res[0].start = legacy_io; + res[0].end = res[0].start + 0xffff; + res[0].parent = &ioport_resource; + res[1].name = "legacy_mem"; + res[1].flags = IORESOURCE_MEM; + res[1].start = legacy_mem; + res[1].end = res[1].start + (1024 * 1024) - 1; + res[1].parent = &iomem_resource; } /* @@ -199,9 +149,7 @@ sn_pci_window_fixup(struct pci_dev *dev, unsigned int count, void sn_io_slot_fixup(struct pci_dev *dev) { - unsigned int count = 0; int idx; - s64 pci_addrs[PCI_ROM_RESOURCE + 1]; unsigned long addr, end, size, start; struct pcidev_info *pcidev_info; struct sn_irq_info *sn_irq_info; @@ -229,7 +177,6 @@ sn_io_slot_fixup(struct pci_dev *dev) for (idx = 0; idx <= PCI_ROM_RESOURCE; idx++) { if (!pcidev_info->pdi_pio_mapped_addr[idx]) { - pci_addrs[idx] = -1; continue; } @@ -237,11 +184,8 @@ sn_io_slot_fixup(struct pci_dev *dev) end = dev->resource[idx].end; size = end - start; if (size == 0) { - pci_addrs[idx] = -1; continue; } - pci_addrs[idx] = start; - count++; addr = pcidev_info->pdi_pio_mapped_addr[idx]; addr = ((addr << 4) >> 4) | __IA64_UNCACHED_OFFSET; dev->resource[idx].start = addr; @@ -276,11 +220,6 @@ sn_io_slot_fixup(struct pci_dev *dev) IORESOURCE_ROM_BIOS_COPY; } } - /* Create a pci_window in the pci_controller struct for - * each device resource. - */ - if (count > 0) - sn_pci_window_fixup(dev, count, pci_addrs); sn_pci_fixup_slot(dev, pcidev_info, sn_irq_info); } @@ -297,8 +236,8 @@ sn_pci_controller_fixup(int segment, int busnum, struct pci_bus *bus) s64 status = 0; struct pci_controller *controller; struct pcibus_bussoft *prom_bussoft_ptr; + struct resource *res; LIST_HEAD(resources); - int i; status = sal_get_pcibus_info((u64) segment, (u64) busnum, (u64) ia64_tpa(&prom_bussoft_ptr)); @@ -310,32 +249,29 @@ sn_pci_controller_fixup(int segment, int busnum, struct pci_bus *bus) BUG_ON(!controller); controller->segment = segment; + res = kcalloc(2, sizeof(struct resource), GFP_KERNEL); + BUG_ON(!res); + /* * Temporarily save the prom_bussoft_ptr for use by sn_bus_fixup(). * (platform_data will be overwritten later in sn_common_bus_fixup()) */ controller->platform_data = prom_bussoft_ptr; - sn_legacy_pci_window_fixup(controller, - prom_bussoft_ptr->bs_legacy_io, - prom_bussoft_ptr->bs_legacy_mem); - for (i = 0; i < controller->windows; i++) - pci_add_resource_offset(&resources, - &controller->window[i].resource, - controller->window[i].offset); + sn_legacy_pci_window_fixup(res, + prom_bussoft_ptr->bs_legacy_io, + prom_bussoft_ptr->bs_legacy_mem); + pci_add_resource_offset(&resources, &res[0], + prom_bussoft_ptr->bs_legacy_io); + pci_add_resource_offset(&resources, &res[1], + prom_bussoft_ptr->bs_legacy_mem); + bus = pci_scan_root_bus(NULL, busnum, &pci_root_ops, controller, &resources); - if (bus == NULL) - goto error_return; /* error, or bus already scanned */ - - bus->sysdata = controller; - - return; - -error_return: - - kfree(controller); - return; + if (bus == NULL) { + kfree(res); + kfree(controller); + } } /* diff --git a/arch/ia64/sn/kernel/setup.c b/arch/ia64/sn/kernel/setup.c index f82e7b462b7b..53b01b8e2f19 100644 --- a/arch/ia64/sn/kernel/setup.c +++ b/arch/ia64/sn/kernel/setup.c @@ -192,7 +192,7 @@ void __init early_sn_setup(void) } extern int platform_intr_list[]; -static int __cpuinitdata shub_1_1_found; +static int shub_1_1_found; /* * sn_check_for_wars @@ -200,7 +200,7 @@ static int __cpuinitdata shub_1_1_found; * Set flag for enabling shub specific wars */ -static inline int __cpuinit is_shub_1_1(int nasid) +static inline int is_shub_1_1(int nasid) { unsigned long id; int rev; @@ -212,7 +212,7 @@ static inline int __cpuinit is_shub_1_1(int nasid) return rev <= 2; } -static void __cpuinit sn_check_for_wars(void) +static void sn_check_for_wars(void) { int cnode; @@ -558,7 +558,7 @@ static void __init sn_init_pdas(char **cmdline_p) * Also sets up a few fields in the nodepda. Also known as * platform_cpu_init() by the ia64 machvec code. */ -void __cpuinit sn_cpu_init(void) +void sn_cpu_init(void) { int cpuid; int cpuphyid; diff --git a/arch/ia64/xen/hypervisor.c b/arch/ia64/xen/hypervisor.c index 52172eee8591..fab62528a80b 100644 --- a/arch/ia64/xen/hypervisor.c +++ b/arch/ia64/xen/hypervisor.c @@ -74,7 +74,7 @@ void __init xen_setup_vcpu_info_placement(void) xen_vcpu_setup(cpu); } -void __cpuinit +void xen_cpu_init(void) { xen_smp_intr_init(); diff --git a/arch/m68k/Kconfig.debug b/arch/m68k/Kconfig.debug index fa12283d58fc..229682721240 100644 --- a/arch/m68k/Kconfig.debug +++ b/arch/m68k/Kconfig.debug @@ -11,9 +11,8 @@ config BOOTPARAM_STRING depends on BOOTPARAM config EARLY_PRINTK - bool "Early printk" if EMBEDDED + bool "Early printk" depends on MVME16x || MAC - default y help Write kernel log output directly to a serial port. diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index 0f795d8e65fa..b17a8837f0e1 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -214,6 +214,7 @@ CONFIG_DEVTMPFS=y # CONFIG_FW_LOADER_USER_HELPER is not set CONFIG_CONNECTOR=m CONFIG_PARPORT=m +CONFIG_PARPORT_PC=m CONFIG_PARPORT_AMIGA=m CONFIG_PARPORT_MFC3=m CONFIG_PARPORT_ATARI=m @@ -325,6 +326,7 @@ CONFIG_ZORRO8390=y # CONFIG_NET_VENDOR_SEEQ is not set # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_WIZNET is not set +CONFIG_PLIP=m CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index 8982370e8b42..be1496ed9b66 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -199,6 +199,9 @@ CONFIG_DEVTMPFS=y # CONFIG_FIRMWARE_IN_KERNEL is not set # CONFIG_FW_LOADER_USER_HELPER is not set CONFIG_CONNECTOR=m +CONFIG_PARPORT=m +CONFIG_PARPORT_PC=m +CONFIG_PARPORT_1284=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_CRYPTOLOOP=m CONFIG_BLK_DEV_DRBD=m @@ -267,6 +270,7 @@ CONFIG_NE2000=m # CONFIG_NET_VENDOR_SMSC is not set # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_WIZNET is not set +CONFIG_PLIP=m CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -292,9 +296,11 @@ CONFIG_SERIO_Q40KBD=y CONFIG_VT_HW_CONSOLE_BINDING=y # CONFIG_LEGACY_PTYS is not set # CONFIG_DEVKMEM is not set +CONFIG_PRINTER=m # CONFIG_HW_RANDOM is not set CONFIG_NTP_PPS=y CONFIG_PPS_CLIENT_LDISC=m +CONFIG_PPS_CLIENT_PARPORT=m CONFIG_PTP_1588_CLOCK=m # CONFIG_HWMON is not set CONFIG_FB=y diff --git a/arch/m68k/include/asm/parport.h b/arch/m68k/include/asm/parport.h index 5ea75e6a7399..c85cece778e8 100644 --- a/arch/m68k/include/asm/parport.h +++ b/arch/m68k/include/asm/parport.h @@ -11,6 +11,8 @@ #ifndef _ASM_M68K_PARPORT_H #define _ASM_M68K_PARPORT_H 1 +#undef insl +#undef outsl #define insl(port,buf,len) isa_insb(port,buf,(len)<<2) #define outsl(port,buf,len) isa_outsb(port,buf,(len)<<2) diff --git a/arch/m68k/include/asm/string.h b/arch/m68k/include/asm/string.h index 9aea9f11fa25..c30c03d98581 100644 --- a/arch/m68k/include/asm/string.h +++ b/arch/m68k/include/asm/string.h @@ -4,20 +4,6 @@ #include <linux/types.h> #include <linux/compiler.h> -static inline char *__kernel_strcpy(char *dest, const char *src) -{ - char *xdest = dest; - - asm volatile ("\n" - "1: move.b (%1)+,(%0)+\n" - " jne 1b" - : "+a" (dest), "+a" (src) - : : "memory"); - return xdest; -} - -#ifndef __IN_STRING_C - #define __HAVE_ARCH_STRNLEN static inline size_t strnlen(const char *s, size_t count) { @@ -34,16 +20,6 @@ static inline size_t strnlen(const char *s, size_t count) return sc - s; } -#define __HAVE_ARCH_STRCPY -#if __GNUC__ >= 4 -#define strcpy(d, s) (__builtin_constant_p(s) && \ - __builtin_strlen(s) <= 32 ? \ - __builtin_strcpy(d, s) : \ - __kernel_strcpy(d, s)) -#else -#define strcpy(d, s) __kernel_strcpy(d, s) -#endif - #define __HAVE_ARCH_STRNCPY static inline char *strncpy(char *dest, const char *src, size_t n) { @@ -61,12 +37,6 @@ static inline char *strncpy(char *dest, const char *src, size_t n) return xdest; } -#define __HAVE_ARCH_STRCAT -#define strcat(d, s) ({ \ - char *__d = (d); \ - strcpy(__d + strlen(__d), (s)); \ -}) - #ifndef CONFIG_COLDFIRE #define __HAVE_ARCH_STRCMP static inline int strcmp(const char *cs, const char *ct) @@ -100,6 +70,4 @@ extern void *memset(void *, int, __kernel_size_t); extern void *memcpy(void *, const void *, __kernel_size_t); #define memcpy(d, s, n) __builtin_memcpy(d, s, n) -#endif - #endif /* _M68K_STRING_H_ */ diff --git a/arch/m68k/include/asm/uaccess_mm.h b/arch/m68k/include/asm/uaccess_mm.h index 472c891a4aee..15901db435b9 100644 --- a/arch/m68k/include/asm/uaccess_mm.h +++ b/arch/m68k/include/asm/uaccess_mm.h @@ -90,7 +90,7 @@ asm volatile ("\n" \ __put_user_asm(__pu_err, __pu_val, ptr, b, d, -EFAULT); \ break; \ case 2: \ - __put_user_asm(__pu_err, __pu_val, ptr, w, d, -EFAULT); \ + __put_user_asm(__pu_err, __pu_val, ptr, w, r, -EFAULT); \ break; \ case 4: \ __put_user_asm(__pu_err, __pu_val, ptr, l, r, -EFAULT); \ @@ -158,7 +158,7 @@ asm volatile ("\n" \ __get_user_asm(__gu_err, x, ptr, u8, b, d, -EFAULT); \ break; \ case 2: \ - __get_user_asm(__gu_err, x, ptr, u16, w, d, -EFAULT); \ + __get_user_asm(__gu_err, x, ptr, u16, w, r, -EFAULT); \ break; \ case 4: \ __get_user_asm(__gu_err, x, ptr, u32, l, r, -EFAULT); \ @@ -245,7 +245,7 @@ __constant_copy_from_user(void *to, const void __user *from, unsigned long n) __get_user_asm(res, *(u8 *)to, (u8 __user *)from, u8, b, d, 1); break; case 2: - __get_user_asm(res, *(u16 *)to, (u16 __user *)from, u16, w, d, 2); + __get_user_asm(res, *(u16 *)to, (u16 __user *)from, u16, w, r, 2); break; case 3: __constant_copy_from_user_asm(res, to, from, tmp, 3, w, b,); @@ -326,7 +326,7 @@ __constant_copy_to_user(void __user *to, const void *from, unsigned long n) __put_user_asm(res, *(u8 *)from, (u8 __user *)to, b, d, 1); break; case 2: - __put_user_asm(res, *(u16 *)from, (u16 __user *)to, w, d, 2); + __put_user_asm(res, *(u16 *)from, (u16 __user *)to, w, r, 2); break; case 3: __constant_copy_to_user_asm(res, to, from, tmp, 3, w, b,); diff --git a/arch/m68k/kernel/asm-offsets.c b/arch/m68k/kernel/asm-offsets.c index a972b00cd77d..8b7b22846366 100644 --- a/arch/m68k/kernel/asm-offsets.c +++ b/arch/m68k/kernel/asm-offsets.c @@ -77,7 +77,7 @@ int main(void) DEFINE(BIR_SIZE, offsetof(struct bi_record, size)); DEFINE(BIR_DATA, offsetof(struct bi_record, data)); - /* offsets into font_desc (drivers/video/console/font.h) */ + /* offsets into the font_desc struct */ DEFINE(FONT_DESC_IDX, offsetof(struct font_desc, idx)); DEFINE(FONT_DESC_NAME, offsetof(struct font_desc, name)); DEFINE(FONT_DESC_WIDTH, offsetof(struct font_desc, width)); diff --git a/arch/m68k/kernel/ints.c b/arch/m68k/kernel/ints.c index 6b32b64bac35..4d7da384eea0 100644 --- a/arch/m68k/kernel/ints.c +++ b/arch/m68k/kernel/ints.c @@ -101,7 +101,7 @@ void __init m68k_setup_user_interrupt(unsigned int vec, unsigned int cnt) BUG_ON(IRQ_USER + cnt > NR_IRQS); m68k_first_user_vec = vec; for (i = 0; i < cnt; i++) - irq_set_chip(IRQ_USER + i, &user_irq_chip); + irq_set_chip_and_handler(i, &user_irq_chip, handle_simple_irq); *user_irqvec_fixup = vec - IRQ_USER; flush_icache(); } diff --git a/arch/m68k/lib/Makefile b/arch/m68k/lib/Makefile index a9d782d34276..fcd8eb1d7c7d 100644 --- a/arch/m68k/lib/Makefile +++ b/arch/m68k/lib/Makefile @@ -6,7 +6,7 @@ lib-y := ashldi3.o ashrdi3.o lshrdi3.o muldi3.o \ memcpy.o memset.o memmove.o -lib-$(CONFIG_MMU) += string.o uaccess.o +lib-$(CONFIG_MMU) += uaccess.o lib-$(CONFIG_CPU_HAS_NO_MULDIV64) += mulsi3.o divsi3.o udivsi3.o lib-$(CONFIG_CPU_HAS_NO_MULDIV64) += modsi3.o umodsi3.o diff --git a/arch/m68k/lib/string.c b/arch/m68k/lib/string.c deleted file mode 100644 index 4d61fa8a112c..000000000000 --- a/arch/m68k/lib/string.c +++ /dev/null @@ -1,22 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file COPYING in the main directory of this archive - * for more details. - */ - -#define __IN_STRING_C - -#include <linux/module.h> -#include <linux/string.h> - -char *strcpy(char *dest, const char *src) -{ - return __kernel_strcpy(dest, src); -} -EXPORT_SYMBOL(strcpy); - -char *strcat(char *dest, const char *src) -{ - return __kernel_strcpy(dest + strlen(dest), src); -} -EXPORT_SYMBOL(strcat); diff --git a/arch/m68k/lib/uaccess.c b/arch/m68k/lib/uaccess.c index 5e97f2ee7c11..35d1442dee89 100644 --- a/arch/m68k/lib/uaccess.c +++ b/arch/m68k/lib/uaccess.c @@ -52,7 +52,7 @@ unsigned long __generic_copy_from_user(void *to, const void __user *from, " .long 3b,30b\n" " .long 5b,50b\n" " .previous" - : "=d" (res), "+a" (from), "+a" (to), "=&r" (tmp) + : "=d" (res), "+a" (from), "+a" (to), "=&d" (tmp) : "0" (n / 4), "d" (n & 3)); return res; @@ -96,7 +96,7 @@ unsigned long __generic_copy_to_user(void __user *to, const void *from, " .long 7b,50b\n" " .long 8b,50b\n" " .previous" - : "=d" (res), "+a" (from), "+a" (to), "=&r" (tmp) + : "=d" (res), "+a" (from), "+a" (to), "=&d" (tmp) : "0" (n / 4), "d" (n & 3)); return res; @@ -141,7 +141,7 @@ unsigned long __clear_user(void __user *to, unsigned long n) " .long 7b,40b\n" " .previous" : "=d" (res), "+a" (to) - : "r" (0), "0" (n / 4), "d" (n & 3)); + : "d" (0), "0" (n / 4), "d" (n & 3)); return res; } diff --git a/arch/m68k/math-emu/fp_arith.c b/arch/m68k/math-emu/fp_arith.c index 08f286db3c5a..239eb1990184 100644 --- a/arch/m68k/math-emu/fp_arith.c +++ b/arch/m68k/math-emu/fp_arith.c @@ -519,7 +519,7 @@ static void fp_roundint(struct fp_ext *dest, int mode) return; break; case 0x401e: - if (!(oldmant.m32[1] >= 0)) + if (oldmant.m32[1] & 0x80000000) return; if (oldmant.m32[0] & 1) break; diff --git a/arch/m68k/platform/coldfire/pci.c b/arch/m68k/platform/coldfire/pci.c index 8572246db84d..b33f97a13e6d 100644 --- a/arch/m68k/platform/coldfire/pci.c +++ b/arch/m68k/platform/coldfire/pci.c @@ -320,7 +320,6 @@ static int __init mcf_pci_init(void) pci_bus_size_bridges(rootbus); pci_bus_assign_resources(rootbus); pci_enable_bridges(rootbus); - pci_bus_add_devices(rootbus); return 0; } diff --git a/arch/m68k/sun3/sun3dvma.c b/arch/m68k/sun3/sun3dvma.c index ca0966cac72a..cab54482ca34 100644 --- a/arch/m68k/sun3/sun3dvma.c +++ b/arch/m68k/sun3/sun3dvma.c @@ -275,7 +275,7 @@ void dvma_init(void) } -inline unsigned long dvma_map_align(unsigned long kaddr, int len, int align) +unsigned long dvma_map_align(unsigned long kaddr, int len, int align) { unsigned long baddr; diff --git a/arch/mips/loongson/lemote-2f/clock.c b/arch/mips/loongson/lemote-2f/clock.c index bc739d4bab2e..4dc2f5fa3f67 100644 --- a/arch/mips/loongson/lemote-2f/clock.c +++ b/arch/mips/loongson/lemote-2f/clock.c @@ -121,7 +121,8 @@ int clk_set_rate(struct clk *clk, unsigned long rate) clk->rate = rate; regval = LOONGSON_CHIPCFG0; - regval = (regval & ~0x7) | (loongson2_clockmod_table[i].index - 1); + regval = (regval & ~0x7) | + (loongson2_clockmod_table[i].driver_data - 1); LOONGSON_CHIPCFG0 = regval; return ret; diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild index f20d01d9aaf9..195653e851da 100644 --- a/arch/openrisc/include/asm/Kbuild +++ b/arch/openrisc/include/asm/Kbuild @@ -66,3 +66,4 @@ generic-y += types.h generic-y += ucontext.h generic-y += user.h generic-y += word-at-a-time.h +generic-y += xor.h diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 349ed85c7d61..08891d07aeb6 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -107,8 +107,9 @@ struct kvmppc_vcpu_book3s { #define CONTEXT_GUEST 1 #define CONTEXT_GUEST_END 2 -#define VSID_REAL 0x1fffffffffc00000ULL -#define VSID_BAT 0x1fffffffffb00000ULL +#define VSID_REAL 0x0fffffffffc00000ULL +#define VSID_BAT 0x0fffffffffb00000ULL +#define VSID_1T 0x1000000000000000ULL #define VSID_REAL_DR 0x2000000000000000ULL #define VSID_REAL_IR 0x4000000000000000ULL #define VSID_PR 0x8000000000000000ULL @@ -123,6 +124,7 @@ extern void kvmppc_mmu_book3s_32_init(struct kvm_vcpu *vcpu); extern void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu); extern int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte); extern int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr); +extern void kvmppc_mmu_flush_segment(struct kvm_vcpu *vcpu, ulong eaddr, ulong seg_size); extern void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu); extern int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned long addr, diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index 2a67e9baa59f..6b0ba5854d99 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -128,7 +128,7 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, const char *type; struct pci_slot *slot; - dev = alloc_pci_dev(); + dev = pci_alloc_dev(bus); if (!dev) return NULL; type = of_get_property(node, "device_type", NULL); @@ -137,7 +137,6 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, pr_debug(" create device, devfn: %x, type: %s\n", devfn, type); - dev->bus = bus; dev->dev.of_node = of_node_get(node); dev->dev.parent = bus->bridge; dev->dev.bus = &pci_bus_type; @@ -165,7 +164,7 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, pr_debug(" class: 0x%x\n", dev->class); pr_debug(" revision: 0x%x\n", dev->revision); - dev->current_state = 4; /* unknown power state */ + dev->current_state = PCI_UNKNOWN; /* unknown power state */ dev->error_state = pci_channel_io_normal; dev->dma_mask = 0xffffffff; diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 422de3f4d46c..008cd856c5b5 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -5,9 +5,10 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror ccflags-y := -Ivirt/kvm -Iarch/powerpc/kvm +KVM := ../../../virt/kvm -common-objs-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o \ - eventfd.o) +common-objs-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \ + $(KVM)/eventfd.o CFLAGS_44x_tlb.o := -I. CFLAGS_e500_mmu.o := -I. @@ -53,7 +54,7 @@ kvm-e500mc-objs := \ kvm-objs-$(CONFIG_KVM_E500MC) := $(kvm-e500mc-objs) kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_PR) := \ - ../../../virt/kvm/coalesced_mmio.o \ + $(KVM)/coalesced_mmio.o \ fpu.o \ book3s_paired_singles.o \ book3s_pr.o \ @@ -86,8 +87,8 @@ kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \ book3s_xics.o kvm-book3s_64-module-objs := \ - ../../../virt/kvm/kvm_main.o \ - ../../../virt/kvm/eventfd.o \ + $(KVM)/kvm_main.o \ + $(KVM)/eventfd.o \ powerpc.o \ emulate.o \ book3s.o \ @@ -111,7 +112,7 @@ kvm-book3s_32-objs := \ kvm-objs-$(CONFIG_KVM_BOOK3S_32) := $(kvm-book3s_32-objs) kvm-objs-$(CONFIG_KVM_MPIC) += mpic.o -kvm-objs-$(CONFIG_HAVE_KVM_IRQ_ROUTING) += $(addprefix ../../../virt/kvm/, irqchip.o) +kvm-objs-$(CONFIG_HAVE_KVM_IRQ_ROUTING) += $(KVM)/irqchip.o kvm-objs := $(kvm-objs-m) $(kvm-objs-y) diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index b871721c0050..739bfbadb85e 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -26,6 +26,7 @@ #include <asm/tlbflush.h> #include <asm/kvm_ppc.h> #include <asm/kvm_book3s.h> +#include <asm/mmu-hash64.h> /* #define DEBUG_MMU */ @@ -76,6 +77,24 @@ static struct kvmppc_slb *kvmppc_mmu_book3s_64_find_slbe( return NULL; } +static int kvmppc_slb_sid_shift(struct kvmppc_slb *slbe) +{ + return slbe->tb ? SID_SHIFT_1T : SID_SHIFT; +} + +static u64 kvmppc_slb_offset_mask(struct kvmppc_slb *slbe) +{ + return (1ul << kvmppc_slb_sid_shift(slbe)) - 1; +} + +static u64 kvmppc_slb_calc_vpn(struct kvmppc_slb *slb, gva_t eaddr) +{ + eaddr &= kvmppc_slb_offset_mask(slb); + + return (eaddr >> VPN_SHIFT) | + ((slb->vsid) << (kvmppc_slb_sid_shift(slb) - VPN_SHIFT)); +} + static u64 kvmppc_mmu_book3s_64_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr, bool data) { @@ -85,11 +104,7 @@ static u64 kvmppc_mmu_book3s_64_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr, if (!slb) return 0; - if (slb->tb) - return (((u64)eaddr >> 12) & 0xfffffff) | - (((u64)slb->vsid) << 28); - - return (((u64)eaddr >> 12) & 0xffff) | (((u64)slb->vsid) << 16); + return kvmppc_slb_calc_vpn(slb, eaddr); } static int kvmppc_mmu_book3s_64_get_pagesize(struct kvmppc_slb *slbe) @@ -100,7 +115,8 @@ static int kvmppc_mmu_book3s_64_get_pagesize(struct kvmppc_slb *slbe) static u32 kvmppc_mmu_book3s_64_get_page(struct kvmppc_slb *slbe, gva_t eaddr) { int p = kvmppc_mmu_book3s_64_get_pagesize(slbe); - return ((eaddr & 0xfffffff) >> p); + + return ((eaddr & kvmppc_slb_offset_mask(slbe)) >> p); } static hva_t kvmppc_mmu_book3s_64_get_pteg( @@ -109,13 +125,15 @@ static hva_t kvmppc_mmu_book3s_64_get_pteg( bool second) { u64 hash, pteg, htabsize; - u32 page; + u32 ssize; hva_t r; + u64 vpn; - page = kvmppc_mmu_book3s_64_get_page(slbe, eaddr); htabsize = ((1 << ((vcpu_book3s->sdr1 & 0x1f) + 11)) - 1); - hash = slbe->vsid ^ page; + vpn = kvmppc_slb_calc_vpn(slbe, eaddr); + ssize = slbe->tb ? MMU_SEGSIZE_1T : MMU_SEGSIZE_256M; + hash = hpt_hash(vpn, kvmppc_mmu_book3s_64_get_pagesize(slbe), ssize); if (second) hash = ~hash; hash &= ((1ULL << 39ULL) - 1ULL); @@ -146,7 +164,7 @@ static u64 kvmppc_mmu_book3s_64_get_avpn(struct kvmppc_slb *slbe, gva_t eaddr) u64 avpn; avpn = kvmppc_mmu_book3s_64_get_page(slbe, eaddr); - avpn |= slbe->vsid << (28 - p); + avpn |= slbe->vsid << (kvmppc_slb_sid_shift(slbe) - p); if (p < 24) avpn >>= ((80 - p) - 56) - 8; @@ -167,7 +185,6 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, int i; u8 key = 0; bool found = false; - bool perm_err = false; int second = 0; ulong mp_ea = vcpu->arch.magic_page_ea; @@ -190,13 +207,15 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, if (!slbe) goto no_seg_found; + avpn = kvmppc_mmu_book3s_64_get_avpn(slbe, eaddr); + if (slbe->tb) + avpn |= SLB_VSID_B_1T; + do_second: ptegp = kvmppc_mmu_book3s_64_get_pteg(vcpu_book3s, slbe, eaddr, second); if (kvm_is_error_hva(ptegp)) goto no_page_found; - avpn = kvmppc_mmu_book3s_64_get_avpn(slbe, eaddr); - if(copy_from_user(pteg, (void __user *)ptegp, sizeof(pteg))) { printk(KERN_ERR "KVM can't copy data from 0x%lx!\n", ptegp); goto no_page_found; @@ -219,7 +238,7 @@ do_second: continue; /* AVPN compare */ - if (HPTE_V_AVPN_VAL(avpn) == HPTE_V_AVPN_VAL(v)) { + if (HPTE_V_COMPARE(avpn, v)) { u8 pp = (r & HPTE_R_PP) | key; int eaddr_mask = 0xFFF; @@ -248,11 +267,6 @@ do_second: break; } - if (!gpte->may_read) { - perm_err = true; - continue; - } - dprintk("KVM MMU: Translated 0x%lx [0x%llx] -> 0x%llx " "-> 0x%lx\n", eaddr, avpn, gpte->vpage, gpte->raddr); @@ -281,6 +295,8 @@ do_second: if (pteg[i+1] != oldr) copy_to_user((void __user *)ptegp, pteg, sizeof(pteg)); + if (!gpte->may_read) + return -EPERM; return 0; } else { dprintk("KVM MMU: No PTE found (ea=0x%lx sdr1=0x%llx " @@ -296,13 +312,7 @@ do_second: } } - no_page_found: - - - if (perm_err) - return -EPERM; - return -ENOENT; no_seg_found: @@ -334,7 +344,7 @@ static void kvmppc_mmu_book3s_64_slbmte(struct kvm_vcpu *vcpu, u64 rs, u64 rb) slbe->large = (rs & SLB_VSID_L) ? 1 : 0; slbe->tb = (rs & SLB_VSID_B_1T) ? 1 : 0; slbe->esid = slbe->tb ? esid_1t : esid; - slbe->vsid = rs >> 12; + slbe->vsid = (rs & ~SLB_VSID_B) >> (kvmppc_slb_sid_shift(slbe) - 16); slbe->valid = (rb & SLB_ESID_V) ? 1 : 0; slbe->Ks = (rs & SLB_VSID_KS) ? 1 : 0; slbe->Kp = (rs & SLB_VSID_KP) ? 1 : 0; @@ -375,6 +385,7 @@ static u64 kvmppc_mmu_book3s_64_slbmfev(struct kvm_vcpu *vcpu, u64 slb_nr) static void kvmppc_mmu_book3s_64_slbie(struct kvm_vcpu *vcpu, u64 ea) { struct kvmppc_slb *slbe; + u64 seg_size; dprintk("KVM MMU: slbie(0x%llx)\n", ea); @@ -386,8 +397,11 @@ static void kvmppc_mmu_book3s_64_slbie(struct kvm_vcpu *vcpu, u64 ea) dprintk("KVM MMU: slbie(0x%llx, 0x%llx)\n", ea, slbe->esid); slbe->valid = false; + slbe->orige = 0; + slbe->origv = 0; - kvmppc_mmu_map_segment(vcpu, ea); + seg_size = 1ull << kvmppc_slb_sid_shift(slbe); + kvmppc_mmu_flush_segment(vcpu, ea & ~(seg_size - 1), seg_size); } static void kvmppc_mmu_book3s_64_slbia(struct kvm_vcpu *vcpu) @@ -396,8 +410,11 @@ static void kvmppc_mmu_book3s_64_slbia(struct kvm_vcpu *vcpu) dprintk("KVM MMU: slbia()\n"); - for (i = 1; i < vcpu->arch.slb_nr; i++) + for (i = 1; i < vcpu->arch.slb_nr; i++) { vcpu->arch.slb[i].valid = false; + vcpu->arch.slb[i].orige = 0; + vcpu->arch.slb[i].origv = 0; + } if (vcpu->arch.shared->msr & MSR_IR) { kvmppc_mmu_flush_segments(vcpu); @@ -467,8 +484,14 @@ static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid, if (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) { slb = kvmppc_mmu_book3s_64_find_slbe(vcpu, ea); - if (slb) + if (slb) { gvsid = slb->vsid; + if (slb->tb) { + gvsid <<= SID_SHIFT_1T - SID_SHIFT; + gvsid |= esid & ((1ul << (SID_SHIFT_1T - SID_SHIFT)) - 1); + gvsid |= VSID_1T; + } + } } switch (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) { diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c index 3a9a1aceb14f..b350d9494b26 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_host.c +++ b/arch/powerpc/kvm/book3s_64_mmu_host.c @@ -301,6 +301,23 @@ out: return r; } +void kvmppc_mmu_flush_segment(struct kvm_vcpu *vcpu, ulong ea, ulong seg_size) +{ + struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); + ulong seg_mask = -seg_size; + int i; + + for (i = 1; i < svcpu->slb_max; i++) { + if ((svcpu->slb[i].esid & SLB_ESID_V) && + (svcpu->slb[i].esid & seg_mask) == ea) { + /* Invalidate this entry */ + svcpu->slb[i].esid = 0; + } + } + + svcpu_put(svcpu); +} + void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu) { struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); @@ -325,9 +342,9 @@ int kvmppc_mmu_init(struct kvm_vcpu *vcpu) return -1; vcpu3s->context_id[0] = err; - vcpu3s->proto_vsid_max = ((vcpu3s->context_id[0] + 1) + vcpu3s->proto_vsid_max = ((u64)(vcpu3s->context_id[0] + 1) << ESID_BITS) - 1; - vcpu3s->proto_vsid_first = vcpu3s->context_id[0] << ESID_BITS; + vcpu3s->proto_vsid_first = (u64)vcpu3s->context_id[0] << ESID_BITS; vcpu3s->proto_vsid_next = vcpu3s->proto_vsid_first; kvmppc_mmu_hpte_init(vcpu); diff --git a/arch/powerpc/kvm/book3s_64_slb.S b/arch/powerpc/kvm/book3s_64_slb.S index 56b983e7b738..4f0caecc0f9d 100644 --- a/arch/powerpc/kvm/book3s_64_slb.S +++ b/arch/powerpc/kvm/book3s_64_slb.S @@ -66,10 +66,6 @@ slb_exit_skip_ ## num: ld r12, PACA_SLBSHADOWPTR(r13) - /* Save off the first entry so we can slbie it later */ - ld r10, SHADOW_SLB_ESID(0)(r12) - ld r11, SHADOW_SLB_VSID(0)(r12) - /* Remove bolted entries */ UNBOLT_SLB_ENTRY(0) UNBOLT_SLB_ENTRY(1) @@ -81,15 +77,10 @@ slb_exit_skip_ ## num: /* Flush SLB */ + li r10, 0 + slbmte r10, r10 slbia - /* r0 = esid & ESID_MASK */ - rldicr r10, r10, 0, 35 - /* r0 |= CLASS_BIT(VSID) */ - rldic r12, r11, 56 - 36, 36 - or r10, r10, r12 - slbie r10 - /* Fill SLB with our shadow */ lbz r12, SVCPU_SLB_MAX(r3) diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index bdc40b8e77d9..19498a567a81 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -1239,8 +1239,7 @@ out: #ifdef CONFIG_PPC64 int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info) { - /* No flags */ - info->flags = 0; + info->flags = KVM_PPC_1T_SEGMENTS; /* SLB is always 64 entries */ info->slb_size = 64; diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 1a1b51189773..dcc94f016007 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -796,7 +796,7 @@ static void kvmppc_restart_interrupt(struct kvm_vcpu *vcpu, kvmppc_fill_pt_regs(®s); timer_interrupt(®s); break; -#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_BOOK3E_64) +#if defined(CONFIG_PPC_DOORBELL) case BOOKE_INTERRUPT_DOORBELL: kvmppc_fill_pt_regs(®s); doorbell_exception(®s); diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c index 631a2650e4e4..2c52ada30775 100644 --- a/arch/powerpc/kvm/emulate.c +++ b/arch/powerpc/kvm/emulate.c @@ -169,6 +169,9 @@ static int kvmppc_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs) vcpu->arch.shared->sprg3 = spr_val; break; + /* PIR can legally be written, but we ignore it */ + case SPRN_PIR: break; + default: emulated = kvmppc_core_emulate_mtspr(vcpu, sprn, spr_val); diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index b62aab3e22ec..e17cdfc5ba40 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -193,37 +193,6 @@ config PPC_IO_WORKAROUNDS source "drivers/cpufreq/Kconfig" -menu "CPU Frequency drivers" - depends on CPU_FREQ - -config CPU_FREQ_PMAC - bool "Support for Apple PowerBooks" - depends on ADB_PMU && PPC32 - select CPU_FREQ_TABLE - help - This adds support for frequency switching on Apple PowerBooks, - this currently includes some models of iBook & Titanium - PowerBook. - -config CPU_FREQ_PMAC64 - bool "Support for some Apple G5s" - depends on PPC_PMAC && PPC64 - select CPU_FREQ_TABLE - help - This adds support for frequency switching on Apple iMac G5, - and some of the more recent desktop G5 machines as well. - -config PPC_PASEMI_CPUFREQ - bool "Support for PA Semi PWRficient" - depends on PPC_PASEMI - default y - select CPU_FREQ_TABLE - help - This adds the support for frequency switching on PA Semi - PWRficient processors. - -endmenu - menu "CPUIdle driver" source "drivers/cpuidle/Kconfig" diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 54f3936001aa..7819c40a6bc3 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -158,6 +158,7 @@ config E500 config PPC_E500MC bool "e500mc Support" select PPC_FPU + select COMMON_CLK depends on E500 help This must be enabled for running on e500mc (and derivatives diff --git a/arch/powerpc/platforms/pasemi/Makefile b/arch/powerpc/platforms/pasemi/Makefile index ce6d789e0741..8e8d4cae5ebe 100644 --- a/arch/powerpc/platforms/pasemi/Makefile +++ b/arch/powerpc/platforms/pasemi/Makefile @@ -1,3 +1,2 @@ obj-y += setup.o pci.o time.o idle.o powersave.o iommu.o dma_lib.o misc.o obj-$(CONFIG_PPC_PASEMI_MDIO) += gpio_mdio.o -obj-$(CONFIG_PPC_PASEMI_CPUFREQ) += cpufreq.o diff --git a/arch/powerpc/platforms/pasemi/cpufreq.c b/arch/powerpc/platforms/pasemi/cpufreq.c deleted file mode 100644 index be1e7958909e..000000000000 --- a/arch/powerpc/platforms/pasemi/cpufreq.c +++ /dev/null @@ -1,330 +0,0 @@ -/* - * Copyright (C) 2007 PA Semi, Inc - * - * Authors: Egor Martovetsky <egor@pasemi.com> - * Olof Johansson <olof@lixom.net> - * - * Maintained by: Olof Johansson <olof@lixom.net> - * - * Based on arch/powerpc/platforms/cell/cbe_cpufreq.c: - * (C) Copyright IBM Deutschland Entwicklung GmbH 2005 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2, or (at your option) - * any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - * - */ - -#include <linux/cpufreq.h> -#include <linux/timer.h> -#include <linux/module.h> - -#include <asm/hw_irq.h> -#include <asm/io.h> -#include <asm/prom.h> -#include <asm/time.h> -#include <asm/smp.h> - -#define SDCASR_REG 0x0100 -#define SDCASR_REG_STRIDE 0x1000 -#define SDCPWR_CFGA0_REG 0x0100 -#define SDCPWR_PWST0_REG 0x0000 -#define SDCPWR_GIZTIME_REG 0x0440 - -/* SDCPWR_GIZTIME_REG fields */ -#define SDCPWR_GIZTIME_GR 0x80000000 -#define SDCPWR_GIZTIME_LONGLOCK 0x000000ff - -/* Offset of ASR registers from SDC base */ -#define SDCASR_OFFSET 0x120000 - -static void __iomem *sdcpwr_mapbase; -static void __iomem *sdcasr_mapbase; - -static DEFINE_MUTEX(pas_switch_mutex); - -/* Current astate, is used when waking up from power savings on - * one core, in case the other core has switched states during - * the idle time. - */ -static int current_astate; - -/* We support 5(A0-A4) power states excluding turbo(A5-A6) modes */ -static struct cpufreq_frequency_table pas_freqs[] = { - {0, 0}, - {1, 0}, - {2, 0}, - {3, 0}, - {4, 0}, - {0, CPUFREQ_TABLE_END}, -}; - -static struct freq_attr *pas_cpu_freqs_attr[] = { - &cpufreq_freq_attr_scaling_available_freqs, - NULL, -}; - -/* - * hardware specific functions - */ - -static int get_astate_freq(int astate) -{ - u32 ret; - ret = in_le32(sdcpwr_mapbase + SDCPWR_CFGA0_REG + (astate * 0x10)); - - return ret & 0x3f; -} - -static int get_cur_astate(int cpu) -{ - u32 ret; - - ret = in_le32(sdcpwr_mapbase + SDCPWR_PWST0_REG); - ret = (ret >> (cpu * 4)) & 0x7; - - return ret; -} - -static int get_gizmo_latency(void) -{ - u32 giztime, ret; - - giztime = in_le32(sdcpwr_mapbase + SDCPWR_GIZTIME_REG); - - /* just provide the upper bound */ - if (giztime & SDCPWR_GIZTIME_GR) - ret = (giztime & SDCPWR_GIZTIME_LONGLOCK) * 128000; - else - ret = (giztime & SDCPWR_GIZTIME_LONGLOCK) * 1000; - - return ret; -} - -static void set_astate(int cpu, unsigned int astate) -{ - unsigned long flags; - - /* Return if called before init has run */ - if (unlikely(!sdcasr_mapbase)) - return; - - local_irq_save(flags); - - out_le32(sdcasr_mapbase + SDCASR_REG + SDCASR_REG_STRIDE*cpu, astate); - - local_irq_restore(flags); -} - -int check_astate(void) -{ - return get_cur_astate(hard_smp_processor_id()); -} - -void restore_astate(int cpu) -{ - set_astate(cpu, current_astate); -} - -/* - * cpufreq functions - */ - -static int pas_cpufreq_cpu_init(struct cpufreq_policy *policy) -{ - const u32 *max_freqp; - u32 max_freq; - int i, cur_astate; - struct resource res; - struct device_node *cpu, *dn; - int err = -ENODEV; - - cpu = of_get_cpu_node(policy->cpu, NULL); - - if (!cpu) - goto out; - - dn = of_find_compatible_node(NULL, NULL, "1682m-sdc"); - if (!dn) - dn = of_find_compatible_node(NULL, NULL, - "pasemi,pwrficient-sdc"); - if (!dn) - goto out; - err = of_address_to_resource(dn, 0, &res); - of_node_put(dn); - if (err) - goto out; - sdcasr_mapbase = ioremap(res.start + SDCASR_OFFSET, 0x2000); - if (!sdcasr_mapbase) { - err = -EINVAL; - goto out; - } - - dn = of_find_compatible_node(NULL, NULL, "1682m-gizmo"); - if (!dn) - dn = of_find_compatible_node(NULL, NULL, - "pasemi,pwrficient-gizmo"); - if (!dn) { - err = -ENODEV; - goto out_unmap_sdcasr; - } - err = of_address_to_resource(dn, 0, &res); - of_node_put(dn); - if (err) - goto out_unmap_sdcasr; - sdcpwr_mapbase = ioremap(res.start, 0x1000); - if (!sdcpwr_mapbase) { - err = -EINVAL; - goto out_unmap_sdcasr; - } - - pr_debug("init cpufreq on CPU %d\n", policy->cpu); - - max_freqp = of_get_property(cpu, "clock-frequency", NULL); - if (!max_freqp) { - err = -EINVAL; - goto out_unmap_sdcpwr; - } - - /* we need the freq in kHz */ - max_freq = *max_freqp / 1000; - - pr_debug("max clock-frequency is at %u kHz\n", max_freq); - pr_debug("initializing frequency table\n"); - - /* initialize frequency table */ - for (i=0; pas_freqs[i].frequency!=CPUFREQ_TABLE_END; i++) { - pas_freqs[i].frequency = get_astate_freq(pas_freqs[i].index) * 100000; - pr_debug("%d: %d\n", i, pas_freqs[i].frequency); - } - - policy->cpuinfo.transition_latency = get_gizmo_latency(); - - cur_astate = get_cur_astate(policy->cpu); - pr_debug("current astate is at %d\n",cur_astate); - - policy->cur = pas_freqs[cur_astate].frequency; - cpumask_copy(policy->cpus, cpu_online_mask); - - ppc_proc_freq = policy->cur * 1000ul; - - cpufreq_frequency_table_get_attr(pas_freqs, policy->cpu); - - /* this ensures that policy->cpuinfo_min and policy->cpuinfo_max - * are set correctly - */ - return cpufreq_frequency_table_cpuinfo(policy, pas_freqs); - -out_unmap_sdcpwr: - iounmap(sdcpwr_mapbase); - -out_unmap_sdcasr: - iounmap(sdcasr_mapbase); -out: - return err; -} - -static int pas_cpufreq_cpu_exit(struct cpufreq_policy *policy) -{ - /* - * We don't support CPU hotplug. Don't unmap after the system - * has already made it to a running state. - */ - if (system_state != SYSTEM_BOOTING) - return 0; - - if (sdcasr_mapbase) - iounmap(sdcasr_mapbase); - if (sdcpwr_mapbase) - iounmap(sdcpwr_mapbase); - - cpufreq_frequency_table_put_attr(policy->cpu); - return 0; -} - -static int pas_cpufreq_verify(struct cpufreq_policy *policy) -{ - return cpufreq_frequency_table_verify(policy, pas_freqs); -} - -static int pas_cpufreq_target(struct cpufreq_policy *policy, - unsigned int target_freq, - unsigned int relation) -{ - struct cpufreq_freqs freqs; - int pas_astate_new; - int i; - - cpufreq_frequency_table_target(policy, - pas_freqs, - target_freq, - relation, - &pas_astate_new); - - freqs.old = policy->cur; - freqs.new = pas_freqs[pas_astate_new].frequency; - - mutex_lock(&pas_switch_mutex); - cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE); - - pr_debug("setting frequency for cpu %d to %d kHz, 1/%d of max frequency\n", - policy->cpu, - pas_freqs[pas_astate_new].frequency, - pas_freqs[pas_astate_new].index); - - current_astate = pas_astate_new; - - for_each_online_cpu(i) - set_astate(i, pas_astate_new); - - cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE); - mutex_unlock(&pas_switch_mutex); - - ppc_proc_freq = freqs.new * 1000ul; - return 0; -} - -static struct cpufreq_driver pas_cpufreq_driver = { - .name = "pas-cpufreq", - .owner = THIS_MODULE, - .flags = CPUFREQ_CONST_LOOPS, - .init = pas_cpufreq_cpu_init, - .exit = pas_cpufreq_cpu_exit, - .verify = pas_cpufreq_verify, - .target = pas_cpufreq_target, - .attr = pas_cpu_freqs_attr, -}; - -/* - * module init and destoy - */ - -static int __init pas_cpufreq_init(void) -{ - if (!of_machine_is_compatible("PA6T-1682M") && - !of_machine_is_compatible("pasemi,pwrficient")) - return -ENODEV; - - return cpufreq_register_driver(&pas_cpufreq_driver); -} - -static void __exit pas_cpufreq_exit(void) -{ - cpufreq_unregister_driver(&pas_cpufreq_driver); -} - -module_init(pas_cpufreq_init); -module_exit(pas_cpufreq_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Egor Martovetsky <egor@pasemi.com>, Olof Johansson <olof@lixom.net>"); diff --git a/arch/powerpc/platforms/powermac/Makefile b/arch/powerpc/platforms/powermac/Makefile index ea47df66fee5..52c6ce1cc985 100644 --- a/arch/powerpc/platforms/powermac/Makefile +++ b/arch/powerpc/platforms/powermac/Makefile @@ -9,8 +9,6 @@ obj-y += pic.o setup.o time.o feature.o pci.o \ sleep.o low_i2c.o cache.o pfunc_core.o \ pfunc_base.o udbg_scc.o udbg_adb.o obj-$(CONFIG_PMAC_BACKLIGHT) += backlight.o -obj-$(CONFIG_CPU_FREQ_PMAC) += cpufreq_32.o -obj-$(CONFIG_CPU_FREQ_PMAC64) += cpufreq_64.o # CONFIG_NVRAM is an arch. independent tristate symbol, for pmac32 we really # need this to be a bool. Cheat here and pretend CONFIG_NVRAM=m is really # CONFIG_NVRAM=y diff --git a/arch/powerpc/platforms/powermac/cpufreq_32.c b/arch/powerpc/platforms/powermac/cpufreq_32.c deleted file mode 100644 index 3104fad82480..000000000000 --- a/arch/powerpc/platforms/powermac/cpufreq_32.c +++ /dev/null @@ -1,721 +0,0 @@ -/* - * Copyright (C) 2002 - 2005 Benjamin Herrenschmidt <benh@kernel.crashing.org> - * Copyright (C) 2004 John Steele Scott <toojays@toojays.net> - * - * 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. - * - * TODO: Need a big cleanup here. Basically, we need to have different - * cpufreq_driver structures for the different type of HW instead of the - * current mess. We also need to better deal with the detection of the - * type of machine. - * - */ - -#include <linux/module.h> -#include <linux/types.h> -#include <linux/errno.h> -#include <linux/kernel.h> -#include <linux/delay.h> -#include <linux/sched.h> -#include <linux/adb.h> -#include <linux/pmu.h> -#include <linux/cpufreq.h> -#include <linux/init.h> -#include <linux/device.h> -#include <linux/hardirq.h> -#include <asm/prom.h> -#include <asm/machdep.h> -#include <asm/irq.h> -#include <asm/pmac_feature.h> -#include <asm/mmu_context.h> -#include <asm/sections.h> -#include <asm/cputable.h> -#include <asm/time.h> -#include <asm/mpic.h> -#include <asm/keylargo.h> -#include <asm/switch_to.h> - -/* WARNING !!! This will cause calibrate_delay() to be called, - * but this is an __init function ! So you MUST go edit - * init/main.c to make it non-init before enabling DEBUG_FREQ - */ -#undef DEBUG_FREQ - -extern void low_choose_7447a_dfs(int dfs); -extern void low_choose_750fx_pll(int pll); -extern void low_sleep_handler(void); - -/* - * Currently, PowerMac cpufreq supports only high & low frequencies - * that are set by the firmware - */ -static unsigned int low_freq; -static unsigned int hi_freq; -static unsigned int cur_freq; -static unsigned int sleep_freq; -static unsigned long transition_latency; - -/* - * Different models uses different mechanisms to switch the frequency - */ -static int (*set_speed_proc)(int low_speed); -static unsigned int (*get_speed_proc)(void); - -/* - * Some definitions used by the various speedprocs - */ -static u32 voltage_gpio; -static u32 frequency_gpio; -static u32 slew_done_gpio; -static int no_schedule; -static int has_cpu_l2lve; -static int is_pmu_based; - -/* There are only two frequency states for each processor. Values - * are in kHz for the time being. - */ -#define CPUFREQ_HIGH 0 -#define CPUFREQ_LOW 1 - -static struct cpufreq_frequency_table pmac_cpu_freqs[] = { - {CPUFREQ_HIGH, 0}, - {CPUFREQ_LOW, 0}, - {0, CPUFREQ_TABLE_END}, -}; - -static struct freq_attr* pmac_cpu_freqs_attr[] = { - &cpufreq_freq_attr_scaling_available_freqs, - NULL, -}; - -static inline void local_delay(unsigned long ms) -{ - if (no_schedule) - mdelay(ms); - else - msleep(ms); -} - -#ifdef DEBUG_FREQ -static inline void debug_calc_bogomips(void) -{ - /* This will cause a recalc of bogomips and display the - * result. We backup/restore the value to avoid affecting the - * core cpufreq framework's own calculation. - */ - unsigned long save_lpj = loops_per_jiffy; - calibrate_delay(); - loops_per_jiffy = save_lpj; -} -#endif /* DEBUG_FREQ */ - -/* Switch CPU speed under 750FX CPU control - */ -static int cpu_750fx_cpu_speed(int low_speed) -{ - u32 hid2; - - if (low_speed == 0) { - /* ramping up, set voltage first */ - pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, voltage_gpio, 0x05); - /* Make sure we sleep for at least 1ms */ - local_delay(10); - - /* tweak L2 for high voltage */ - if (has_cpu_l2lve) { - hid2 = mfspr(SPRN_HID2); - hid2 &= ~0x2000; - mtspr(SPRN_HID2, hid2); - } - } -#ifdef CONFIG_6xx - low_choose_750fx_pll(low_speed); -#endif - if (low_speed == 1) { - /* tweak L2 for low voltage */ - if (has_cpu_l2lve) { - hid2 = mfspr(SPRN_HID2); - hid2 |= 0x2000; - mtspr(SPRN_HID2, hid2); - } - - /* ramping down, set voltage last */ - pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, voltage_gpio, 0x04); - local_delay(10); - } - - return 0; -} - -static unsigned int cpu_750fx_get_cpu_speed(void) -{ - if (mfspr(SPRN_HID1) & HID1_PS) - return low_freq; - else - return hi_freq; -} - -/* Switch CPU speed using DFS */ -static int dfs_set_cpu_speed(int low_speed) -{ - if (low_speed == 0) { - /* ramping up, set voltage first */ - pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, voltage_gpio, 0x05); - /* Make sure we sleep for at least 1ms */ - local_delay(1); - } - - /* set frequency */ -#ifdef CONFIG_6xx - low_choose_7447a_dfs(low_speed); -#endif - udelay(100); - - if (low_speed == 1) { - /* ramping down, set voltage last */ - pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, voltage_gpio, 0x04); - local_delay(1); - } - - return 0; -} - -static unsigned int dfs_get_cpu_speed(void) -{ - if (mfspr(SPRN_HID1) & HID1_DFS) - return low_freq; - else - return hi_freq; -} - - -/* Switch CPU speed using slewing GPIOs - */ -static int gpios_set_cpu_speed(int low_speed) -{ - int gpio, timeout = 0; - - /* If ramping up, set voltage first */ - if (low_speed == 0) { - pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, voltage_gpio, 0x05); - /* Delay is way too big but it's ok, we schedule */ - local_delay(10); - } - - /* Set frequency */ - gpio = pmac_call_feature(PMAC_FTR_READ_GPIO, NULL, frequency_gpio, 0); - if (low_speed == ((gpio & 0x01) == 0)) - goto skip; - - pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, frequency_gpio, - low_speed ? 0x04 : 0x05); - udelay(200); - do { - if (++timeout > 100) - break; - local_delay(1); - gpio = pmac_call_feature(PMAC_FTR_READ_GPIO, NULL, slew_done_gpio, 0); - } while((gpio & 0x02) == 0); - skip: - /* If ramping down, set voltage last */ - if (low_speed == 1) { - pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, voltage_gpio, 0x04); - /* Delay is way too big but it's ok, we schedule */ - local_delay(10); - } - -#ifdef DEBUG_FREQ - debug_calc_bogomips(); -#endif - - return 0; -} - -/* Switch CPU speed under PMU control - */ -static int pmu_set_cpu_speed(int low_speed) -{ - struct adb_request req; - unsigned long save_l2cr; - unsigned long save_l3cr; - unsigned int pic_prio; - unsigned long flags; - - preempt_disable(); - -#ifdef DEBUG_FREQ - printk(KERN_DEBUG "HID1, before: %x\n", mfspr(SPRN_HID1)); -#endif - pmu_suspend(); - - /* Disable all interrupt sources on openpic */ - pic_prio = mpic_cpu_get_priority(); - mpic_cpu_set_priority(0xf); - - /* Make sure the decrementer won't interrupt us */ - asm volatile("mtdec %0" : : "r" (0x7fffffff)); - /* Make sure any pending DEC interrupt occurring while we did - * the above didn't re-enable the DEC */ - mb(); - asm volatile("mtdec %0" : : "r" (0x7fffffff)); - - /* We can now disable MSR_EE */ - local_irq_save(flags); - - /* Giveup the FPU & vec */ - enable_kernel_fp(); - -#ifdef CONFIG_ALTIVEC - if (cpu_has_feature(CPU_FTR_ALTIVEC)) - enable_kernel_altivec(); -#endif /* CONFIG_ALTIVEC */ - - /* Save & disable L2 and L3 caches */ - save_l3cr = _get_L3CR(); /* (returns -1 if not available) */ - save_l2cr = _get_L2CR(); /* (returns -1 if not available) */ - - /* Send the new speed command. My assumption is that this command - * will cause PLL_CFG[0..3] to be changed next time CPU goes to sleep - */ - pmu_request(&req, NULL, 6, PMU_CPU_SPEED, 'W', 'O', 'O', 'F', low_speed); - while (!req.complete) - pmu_poll(); - - /* Prepare the northbridge for the speed transition */ - pmac_call_feature(PMAC_FTR_SLEEP_STATE,NULL,1,1); - - /* Call low level code to backup CPU state and recover from - * hardware reset - */ - low_sleep_handler(); - - /* Restore the northbridge */ - pmac_call_feature(PMAC_FTR_SLEEP_STATE,NULL,1,0); - - /* Restore L2 cache */ - if (save_l2cr != 0xffffffff && (save_l2cr & L2CR_L2E) != 0) - _set_L2CR(save_l2cr); - /* Restore L3 cache */ - if (save_l3cr != 0xffffffff && (save_l3cr & L3CR_L3E) != 0) - _set_L3CR(save_l3cr); - - /* Restore userland MMU context */ - switch_mmu_context(NULL, current->active_mm); - -#ifdef DEBUG_FREQ - printk(KERN_DEBUG "HID1, after: %x\n", mfspr(SPRN_HID1)); -#endif - - /* Restore low level PMU operations */ - pmu_unlock(); - - /* - * Restore decrementer; we'll take a decrementer interrupt - * as soon as interrupts are re-enabled and the generic - * clockevents code will reprogram it with the right value. - */ - set_dec(1); - - /* Restore interrupts */ - mpic_cpu_set_priority(pic_prio); - - /* Let interrupts flow again ... */ - local_irq_restore(flags); - -#ifdef DEBUG_FREQ - debug_calc_bogomips(); -#endif - - pmu_resume(); - - preempt_enable(); - - return 0; -} - -static int do_set_cpu_speed(struct cpufreq_policy *policy, int speed_mode, - int notify) -{ - struct cpufreq_freqs freqs; - unsigned long l3cr; - static unsigned long prev_l3cr; - - freqs.old = cur_freq; - freqs.new = (speed_mode == CPUFREQ_HIGH) ? hi_freq : low_freq; - - if (freqs.old == freqs.new) - return 0; - - if (notify) - cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE); - if (speed_mode == CPUFREQ_LOW && - cpu_has_feature(CPU_FTR_L3CR)) { - l3cr = _get_L3CR(); - if (l3cr & L3CR_L3E) { - prev_l3cr = l3cr; - _set_L3CR(0); - } - } - set_speed_proc(speed_mode == CPUFREQ_LOW); - if (speed_mode == CPUFREQ_HIGH && - cpu_has_feature(CPU_FTR_L3CR)) { - l3cr = _get_L3CR(); - if ((prev_l3cr & L3CR_L3E) && l3cr != prev_l3cr) - _set_L3CR(prev_l3cr); - } - if (notify) - cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE); - cur_freq = (speed_mode == CPUFREQ_HIGH) ? hi_freq : low_freq; - - return 0; -} - -static unsigned int pmac_cpufreq_get_speed(unsigned int cpu) -{ - return cur_freq; -} - -static int pmac_cpufreq_verify(struct cpufreq_policy *policy) -{ - return cpufreq_frequency_table_verify(policy, pmac_cpu_freqs); -} - -static int pmac_cpufreq_target( struct cpufreq_policy *policy, - unsigned int target_freq, - unsigned int relation) -{ - unsigned int newstate = 0; - int rc; - - if (cpufreq_frequency_table_target(policy, pmac_cpu_freqs, - target_freq, relation, &newstate)) - return -EINVAL; - - rc = do_set_cpu_speed(policy, newstate, 1); - - ppc_proc_freq = cur_freq * 1000ul; - return rc; -} - -static int pmac_cpufreq_cpu_init(struct cpufreq_policy *policy) -{ - if (policy->cpu != 0) - return -ENODEV; - - policy->cpuinfo.transition_latency = transition_latency; - policy->cur = cur_freq; - - cpufreq_frequency_table_get_attr(pmac_cpu_freqs, policy->cpu); - return cpufreq_frequency_table_cpuinfo(policy, pmac_cpu_freqs); -} - -static u32 read_gpio(struct device_node *np) -{ - const u32 *reg = of_get_property(np, "reg", NULL); - u32 offset; - - if (reg == NULL) - return 0; - /* That works for all keylargos but shall be fixed properly - * some day... The problem is that it seems we can't rely - * on the "reg" property of the GPIO nodes, they are either - * relative to the base of KeyLargo or to the base of the - * GPIO space, and the device-tree doesn't help. - */ - offset = *reg; - if (offset < KEYLARGO_GPIO_LEVELS0) - offset += KEYLARGO_GPIO_LEVELS0; - return offset; -} - -static int pmac_cpufreq_suspend(struct cpufreq_policy *policy) -{ - /* Ok, this could be made a bit smarter, but let's be robust for now. We - * always force a speed change to high speed before sleep, to make sure - * we have appropriate voltage and/or bus speed for the wakeup process, - * and to make sure our loops_per_jiffies are "good enough", that is will - * not cause too short delays if we sleep in low speed and wake in high - * speed.. - */ - no_schedule = 1; - sleep_freq = cur_freq; - if (cur_freq == low_freq && !is_pmu_based) - do_set_cpu_speed(policy, CPUFREQ_HIGH, 0); - return 0; -} - -static int pmac_cpufreq_resume(struct cpufreq_policy *policy) -{ - /* If we resume, first check if we have a get() function */ - if (get_speed_proc) - cur_freq = get_speed_proc(); - else - cur_freq = 0; - - /* We don't, hrm... we don't really know our speed here, best - * is that we force a switch to whatever it was, which is - * probably high speed due to our suspend() routine - */ - do_set_cpu_speed(policy, sleep_freq == low_freq ? - CPUFREQ_LOW : CPUFREQ_HIGH, 0); - - ppc_proc_freq = cur_freq * 1000ul; - - no_schedule = 0; - return 0; -} - -static struct cpufreq_driver pmac_cpufreq_driver = { - .verify = pmac_cpufreq_verify, - .target = pmac_cpufreq_target, - .get = pmac_cpufreq_get_speed, - .init = pmac_cpufreq_cpu_init, - .suspend = pmac_cpufreq_suspend, - .resume = pmac_cpufreq_resume, - .flags = CPUFREQ_PM_NO_WARN, - .attr = pmac_cpu_freqs_attr, - .name = "powermac", - .owner = THIS_MODULE, -}; - - -static int pmac_cpufreq_init_MacRISC3(struct device_node *cpunode) -{ - struct device_node *volt_gpio_np = of_find_node_by_name(NULL, - "voltage-gpio"); - struct device_node *freq_gpio_np = of_find_node_by_name(NULL, - "frequency-gpio"); - struct device_node *slew_done_gpio_np = of_find_node_by_name(NULL, - "slewing-done"); - const u32 *value; - - /* - * Check to see if it's GPIO driven or PMU only - * - * The way we extract the GPIO address is slightly hackish, but it - * works well enough for now. We need to abstract the whole GPIO - * stuff sooner or later anyway - */ - - if (volt_gpio_np) - voltage_gpio = read_gpio(volt_gpio_np); - if (freq_gpio_np) - frequency_gpio = read_gpio(freq_gpio_np); - if (slew_done_gpio_np) - slew_done_gpio = read_gpio(slew_done_gpio_np); - - /* If we use the frequency GPIOs, calculate the min/max speeds based - * on the bus frequencies - */ - if (frequency_gpio && slew_done_gpio) { - int lenp, rc; - const u32 *freqs, *ratio; - - freqs = of_get_property(cpunode, "bus-frequencies", &lenp); - lenp /= sizeof(u32); - if (freqs == NULL || lenp != 2) { - printk(KERN_ERR "cpufreq: bus-frequencies incorrect or missing\n"); - return 1; - } - ratio = of_get_property(cpunode, "processor-to-bus-ratio*2", - NULL); - if (ratio == NULL) { - printk(KERN_ERR "cpufreq: processor-to-bus-ratio*2 missing\n"); - return 1; - } - - /* Get the min/max bus frequencies */ - low_freq = min(freqs[0], freqs[1]); - hi_freq = max(freqs[0], freqs[1]); - - /* Grrrr.. It _seems_ that the device-tree is lying on the low bus - * frequency, it claims it to be around 84Mhz on some models while - * it appears to be approx. 101Mhz on all. Let's hack around here... - * fortunately, we don't need to be too precise - */ - if (low_freq < 98000000) - low_freq = 101000000; - - /* Convert those to CPU core clocks */ - low_freq = (low_freq * (*ratio)) / 2000; - hi_freq = (hi_freq * (*ratio)) / 2000; - - /* Now we get the frequencies, we read the GPIO to see what is out current - * speed - */ - rc = pmac_call_feature(PMAC_FTR_READ_GPIO, NULL, frequency_gpio, 0); - cur_freq = (rc & 0x01) ? hi_freq : low_freq; - - set_speed_proc = gpios_set_cpu_speed; - return 1; - } - - /* If we use the PMU, look for the min & max frequencies in the - * device-tree - */ - value = of_get_property(cpunode, "min-clock-frequency", NULL); - if (!value) - return 1; - low_freq = (*value) / 1000; - /* The PowerBook G4 12" (PowerBook6,1) has an error in the device-tree - * here */ - if (low_freq < 100000) - low_freq *= 10; - - value = of_get_property(cpunode, "max-clock-frequency", NULL); - if (!value) - return 1; - hi_freq = (*value) / 1000; - set_speed_proc = pmu_set_cpu_speed; - is_pmu_based = 1; - - return 0; -} - -static int pmac_cpufreq_init_7447A(struct device_node *cpunode) -{ - struct device_node *volt_gpio_np; - - if (of_get_property(cpunode, "dynamic-power-step", NULL) == NULL) - return 1; - - volt_gpio_np = of_find_node_by_name(NULL, "cpu-vcore-select"); - if (volt_gpio_np) - voltage_gpio = read_gpio(volt_gpio_np); - if (!voltage_gpio){ - printk(KERN_ERR "cpufreq: missing cpu-vcore-select gpio\n"); - return 1; - } - - /* OF only reports the high frequency */ - hi_freq = cur_freq; - low_freq = cur_freq/2; - - /* Read actual frequency from CPU */ - cur_freq = dfs_get_cpu_speed(); - set_speed_proc = dfs_set_cpu_speed; - get_speed_proc = dfs_get_cpu_speed; - - return 0; -} - -static int pmac_cpufreq_init_750FX(struct device_node *cpunode) -{ - struct device_node *volt_gpio_np; - u32 pvr; - const u32 *value; - - if (of_get_property(cpunode, "dynamic-power-step", NULL) == NULL) - return 1; - - hi_freq = cur_freq; - value = of_get_property(cpunode, "reduced-clock-frequency", NULL); - if (!value) - return 1; - low_freq = (*value) / 1000; - - volt_gpio_np = of_find_node_by_name(NULL, "cpu-vcore-select"); - if (volt_gpio_np) - voltage_gpio = read_gpio(volt_gpio_np); - - pvr = mfspr(SPRN_PVR); - has_cpu_l2lve = !((pvr & 0xf00) == 0x100); - - set_speed_proc = cpu_750fx_cpu_speed; - get_speed_proc = cpu_750fx_get_cpu_speed; - cur_freq = cpu_750fx_get_cpu_speed(); - - return 0; -} - -/* Currently, we support the following machines: - * - * - Titanium PowerBook 1Ghz (PMU based, 667Mhz & 1Ghz) - * - Titanium PowerBook 800 (PMU based, 667Mhz & 800Mhz) - * - Titanium PowerBook 400 (PMU based, 300Mhz & 400Mhz) - * - Titanium PowerBook 500 (PMU based, 300Mhz & 500Mhz) - * - iBook2 500/600 (PMU based, 400Mhz & 500/600Mhz) - * - iBook2 700 (CPU based, 400Mhz & 700Mhz, support low voltage) - * - Recent MacRISC3 laptops - * - All new machines with 7447A CPUs - */ -static int __init pmac_cpufreq_setup(void) -{ - struct device_node *cpunode; - const u32 *value; - - if (strstr(cmd_line, "nocpufreq")) - return 0; - - /* Assume only one CPU */ - cpunode = of_find_node_by_type(NULL, "cpu"); - if (!cpunode) - goto out; - - /* Get current cpu clock freq */ - value = of_get_property(cpunode, "clock-frequency", NULL); - if (!value) - goto out; - cur_freq = (*value) / 1000; - transition_latency = CPUFREQ_ETERNAL; - - /* Check for 7447A based MacRISC3 */ - if (of_machine_is_compatible("MacRISC3") && - of_get_property(cpunode, "dynamic-power-step", NULL) && - PVR_VER(mfspr(SPRN_PVR)) == 0x8003) { - pmac_cpufreq_init_7447A(cpunode); - transition_latency = 8000000; - /* Check for other MacRISC3 machines */ - } else if (of_machine_is_compatible("PowerBook3,4") || - of_machine_is_compatible("PowerBook3,5") || - of_machine_is_compatible("MacRISC3")) { - pmac_cpufreq_init_MacRISC3(cpunode); - /* Else check for iBook2 500/600 */ - } else if (of_machine_is_compatible("PowerBook4,1")) { - hi_freq = cur_freq; - low_freq = 400000; - set_speed_proc = pmu_set_cpu_speed; - is_pmu_based = 1; - } - /* Else check for TiPb 550 */ - else if (of_machine_is_compatible("PowerBook3,3") && cur_freq == 550000) { - hi_freq = cur_freq; - low_freq = 500000; - set_speed_proc = pmu_set_cpu_speed; - is_pmu_based = 1; - } - /* Else check for TiPb 400 & 500 */ - else if (of_machine_is_compatible("PowerBook3,2")) { - /* We only know about the 400 MHz and the 500Mhz model - * they both have 300 MHz as low frequency - */ - if (cur_freq < 350000 || cur_freq > 550000) - goto out; - hi_freq = cur_freq; - low_freq = 300000; - set_speed_proc = pmu_set_cpu_speed; - is_pmu_based = 1; - } - /* Else check for 750FX */ - else if (PVR_VER(mfspr(SPRN_PVR)) == 0x7000) - pmac_cpufreq_init_750FX(cpunode); -out: - of_node_put(cpunode); - if (set_speed_proc == NULL) - return -ENODEV; - - pmac_cpu_freqs[CPUFREQ_LOW].frequency = low_freq; - pmac_cpu_freqs[CPUFREQ_HIGH].frequency = hi_freq; - ppc_proc_freq = cur_freq * 1000ul; - - printk(KERN_INFO "Registering PowerMac CPU frequency driver\n"); - printk(KERN_INFO "Low: %d Mhz, High: %d Mhz, Boot: %d Mhz\n", - low_freq/1000, hi_freq/1000, cur_freq/1000); - - return cpufreq_register_driver(&pmac_cpufreq_driver); -} - -module_init(pmac_cpufreq_setup); - diff --git a/arch/powerpc/platforms/powermac/cpufreq_64.c b/arch/powerpc/platforms/powermac/cpufreq_64.c deleted file mode 100644 index 7ba423431cfe..000000000000 --- a/arch/powerpc/platforms/powermac/cpufreq_64.c +++ /dev/null @@ -1,746 +0,0 @@ -/* - * Copyright (C) 2002 - 2005 Benjamin Herrenschmidt <benh@kernel.crashing.org> - * and Markus Demleitner <msdemlei@cl.uni-heidelberg.de> - * - * 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 driver adds basic cpufreq support for SMU & 970FX based G5 Macs, - * that is iMac G5 and latest single CPU desktop. - */ - -#undef DEBUG - -#include <linux/module.h> -#include <linux/types.h> -#include <linux/errno.h> -#include <linux/kernel.h> -#include <linux/delay.h> -#include <linux/sched.h> -#include <linux/cpufreq.h> -#include <linux/init.h> -#include <linux/completion.h> -#include <linux/mutex.h> -#include <asm/prom.h> -#include <asm/machdep.h> -#include <asm/irq.h> -#include <asm/sections.h> -#include <asm/cputable.h> -#include <asm/time.h> -#include <asm/smu.h> -#include <asm/pmac_pfunc.h> - -#define DBG(fmt...) pr_debug(fmt) - -/* see 970FX user manual */ - -#define SCOM_PCR 0x0aa001 /* PCR scom addr */ - -#define PCR_HILO_SELECT 0x80000000U /* 1 = PCR, 0 = PCRH */ -#define PCR_SPEED_FULL 0x00000000U /* 1:1 speed value */ -#define PCR_SPEED_HALF 0x00020000U /* 1:2 speed value */ -#define PCR_SPEED_QUARTER 0x00040000U /* 1:4 speed value */ -#define PCR_SPEED_MASK 0x000e0000U /* speed mask */ -#define PCR_SPEED_SHIFT 17 -#define PCR_FREQ_REQ_VALID 0x00010000U /* freq request valid */ -#define PCR_VOLT_REQ_VALID 0x00008000U /* volt request valid */ -#define PCR_TARGET_TIME_MASK 0x00006000U /* target time */ -#define PCR_STATLAT_MASK 0x00001f00U /* STATLAT value */ -#define PCR_SNOOPLAT_MASK 0x000000f0U /* SNOOPLAT value */ -#define PCR_SNOOPACC_MASK 0x0000000fU /* SNOOPACC value */ - -#define SCOM_PSR 0x408001 /* PSR scom addr */ -/* warning: PSR is a 64 bits register */ -#define PSR_CMD_RECEIVED 0x2000000000000000U /* command received */ -#define PSR_CMD_COMPLETED 0x1000000000000000U /* command completed */ -#define PSR_CUR_SPEED_MASK 0x0300000000000000U /* current speed */ -#define PSR_CUR_SPEED_SHIFT (56) - -/* - * The G5 only supports two frequencies (Quarter speed is not supported) - */ -#define CPUFREQ_HIGH 0 -#define CPUFREQ_LOW 1 - -static struct cpufreq_frequency_table g5_cpu_freqs[] = { - {CPUFREQ_HIGH, 0}, - {CPUFREQ_LOW, 0}, - {0, CPUFREQ_TABLE_END}, -}; - -static struct freq_attr* g5_cpu_freqs_attr[] = { - &cpufreq_freq_attr_scaling_available_freqs, - NULL, -}; - -/* Power mode data is an array of the 32 bits PCR values to use for - * the various frequencies, retrieved from the device-tree - */ -static int g5_pmode_cur; - -static void (*g5_switch_volt)(int speed_mode); -static int (*g5_switch_freq)(int speed_mode); -static int (*g5_query_freq)(void); - -static DEFINE_MUTEX(g5_switch_mutex); - -static unsigned long transition_latency; - -#ifdef CONFIG_PMAC_SMU - -static const u32 *g5_pmode_data; -static int g5_pmode_max; - -static struct smu_sdbp_fvt *g5_fvt_table; /* table of op. points */ -static int g5_fvt_count; /* number of op. points */ -static int g5_fvt_cur; /* current op. point */ - -/* - * SMU based voltage switching for Neo2 platforms - */ - -static void g5_smu_switch_volt(int speed_mode) -{ - struct smu_simple_cmd cmd; - - DECLARE_COMPLETION_ONSTACK(comp); - smu_queue_simple(&cmd, SMU_CMD_POWER_COMMAND, 8, smu_done_complete, - &comp, 'V', 'S', 'L', 'E', 'W', - 0xff, g5_fvt_cur+1, speed_mode); - wait_for_completion(&comp); -} - -/* - * Platform function based voltage/vdnap switching for Neo2 - */ - -static struct pmf_function *pfunc_set_vdnap0; -static struct pmf_function *pfunc_vdnap0_complete; - -static void g5_vdnap_switch_volt(int speed_mode) -{ - struct pmf_args args; - u32 slew, done = 0; - unsigned long timeout; - - slew = (speed_mode == CPUFREQ_LOW) ? 1 : 0; - args.count = 1; - args.u[0].p = &slew; - - pmf_call_one(pfunc_set_vdnap0, &args); - - /* It's an irq GPIO so we should be able to just block here, - * I'll do that later after I've properly tested the IRQ code for - * platform functions - */ - timeout = jiffies + HZ/10; - while(!time_after(jiffies, timeout)) { - args.count = 1; - args.u[0].p = &done; - pmf_call_one(pfunc_vdnap0_complete, &args); - if (done) - break; - msleep(1); - } - if (done == 0) - printk(KERN_WARNING "cpufreq: Timeout in clock slewing !\n"); -} - - -/* - * SCOM based frequency switching for 970FX rev3 - */ -static int g5_scom_switch_freq(int speed_mode) -{ - unsigned long flags; - int to; - - /* If frequency is going up, first ramp up the voltage */ - if (speed_mode < g5_pmode_cur) - g5_switch_volt(speed_mode); - - local_irq_save(flags); - - /* Clear PCR high */ - scom970_write(SCOM_PCR, 0); - /* Clear PCR low */ - scom970_write(SCOM_PCR, PCR_HILO_SELECT | 0); - /* Set PCR low */ - scom970_write(SCOM_PCR, PCR_HILO_SELECT | - g5_pmode_data[speed_mode]); - - /* Wait for completion */ - for (to = 0; to < 10; to++) { - unsigned long psr = scom970_read(SCOM_PSR); - - if ((psr & PSR_CMD_RECEIVED) == 0 && - (((psr >> PSR_CUR_SPEED_SHIFT) ^ - (g5_pmode_data[speed_mode] >> PCR_SPEED_SHIFT)) & 0x3) - == 0) - break; - if (psr & PSR_CMD_COMPLETED) - break; - udelay(100); - } - - local_irq_restore(flags); - - /* If frequency is going down, last ramp the voltage */ - if (speed_mode > g5_pmode_cur) - g5_switch_volt(speed_mode); - - g5_pmode_cur = speed_mode; - ppc_proc_freq = g5_cpu_freqs[speed_mode].frequency * 1000ul; - - return 0; -} - -static int g5_scom_query_freq(void) -{ - unsigned long psr = scom970_read(SCOM_PSR); - int i; - - for (i = 0; i <= g5_pmode_max; i++) - if ((((psr >> PSR_CUR_SPEED_SHIFT) ^ - (g5_pmode_data[i] >> PCR_SPEED_SHIFT)) & 0x3) == 0) - break; - return i; -} - -/* - * Fake voltage switching for platforms with missing support - */ - -static void g5_dummy_switch_volt(int speed_mode) -{ -} - -#endif /* CONFIG_PMAC_SMU */ - -/* - * Platform function based voltage switching for PowerMac7,2 & 7,3 - */ - -static struct pmf_function *pfunc_cpu0_volt_high; -static struct pmf_function *pfunc_cpu0_volt_low; -static struct pmf_function *pfunc_cpu1_volt_high; -static struct pmf_function *pfunc_cpu1_volt_low; - -static void g5_pfunc_switch_volt(int speed_mode) -{ - if (speed_mode == CPUFREQ_HIGH) { - if (pfunc_cpu0_volt_high) - pmf_call_one(pfunc_cpu0_volt_high, NULL); - if (pfunc_cpu1_volt_high) - pmf_call_one(pfunc_cpu1_volt_high, NULL); - } else { - if (pfunc_cpu0_volt_low) - pmf_call_one(pfunc_cpu0_volt_low, NULL); - if (pfunc_cpu1_volt_low) - pmf_call_one(pfunc_cpu1_volt_low, NULL); - } - msleep(10); /* should be faster , to fix */ -} - -/* - * Platform function based frequency switching for PowerMac7,2 & 7,3 - */ - -static struct pmf_function *pfunc_cpu_setfreq_high; -static struct pmf_function *pfunc_cpu_setfreq_low; -static struct pmf_function *pfunc_cpu_getfreq; -static struct pmf_function *pfunc_slewing_done; - -static int g5_pfunc_switch_freq(int speed_mode) -{ - struct pmf_args args; - u32 done = 0; - unsigned long timeout; - int rc; - - DBG("g5_pfunc_switch_freq(%d)\n", speed_mode); - - /* If frequency is going up, first ramp up the voltage */ - if (speed_mode < g5_pmode_cur) - g5_switch_volt(speed_mode); - - /* Do it */ - if (speed_mode == CPUFREQ_HIGH) - rc = pmf_call_one(pfunc_cpu_setfreq_high, NULL); - else - rc = pmf_call_one(pfunc_cpu_setfreq_low, NULL); - - if (rc) - printk(KERN_WARNING "cpufreq: pfunc switch error %d\n", rc); - - /* It's an irq GPIO so we should be able to just block here, - * I'll do that later after I've properly tested the IRQ code for - * platform functions - */ - timeout = jiffies + HZ/10; - while(!time_after(jiffies, timeout)) { - args.count = 1; - args.u[0].p = &done; - pmf_call_one(pfunc_slewing_done, &args); - if (done) - break; - msleep(1); - } - if (done == 0) - printk(KERN_WARNING "cpufreq: Timeout in clock slewing !\n"); - - /* If frequency is going down, last ramp the voltage */ - if (speed_mode > g5_pmode_cur) - g5_switch_volt(speed_mode); - - g5_pmode_cur = speed_mode; - ppc_proc_freq = g5_cpu_freqs[speed_mode].frequency * 1000ul; - - return 0; -} - -static int g5_pfunc_query_freq(void) -{ - struct pmf_args args; - u32 val = 0; - - args.count = 1; - args.u[0].p = &val; - pmf_call_one(pfunc_cpu_getfreq, &args); - return val ? CPUFREQ_HIGH : CPUFREQ_LOW; -} - - -/* - * Common interface to the cpufreq core - */ - -static int g5_cpufreq_verify(struct cpufreq_policy *policy) -{ - return cpufreq_frequency_table_verify(policy, g5_cpu_freqs); -} - -static int g5_cpufreq_target(struct cpufreq_policy *policy, - unsigned int target_freq, unsigned int relation) -{ - unsigned int newstate = 0; - struct cpufreq_freqs freqs; - int rc; - - if (cpufreq_frequency_table_target(policy, g5_cpu_freqs, - target_freq, relation, &newstate)) - return -EINVAL; - - if (g5_pmode_cur == newstate) - return 0; - - mutex_lock(&g5_switch_mutex); - - freqs.old = g5_cpu_freqs[g5_pmode_cur].frequency; - freqs.new = g5_cpu_freqs[newstate].frequency; - - cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE); - rc = g5_switch_freq(newstate); - cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE); - - mutex_unlock(&g5_switch_mutex); - - return rc; -} - -static unsigned int g5_cpufreq_get_speed(unsigned int cpu) -{ - return g5_cpu_freqs[g5_pmode_cur].frequency; -} - -static int g5_cpufreq_cpu_init(struct cpufreq_policy *policy) -{ - policy->cpuinfo.transition_latency = transition_latency; - policy->cur = g5_cpu_freqs[g5_query_freq()].frequency; - /* secondary CPUs are tied to the primary one by the - * cpufreq core if in the secondary policy we tell it that - * it actually must be one policy together with all others. */ - cpumask_copy(policy->cpus, cpu_online_mask); - cpufreq_frequency_table_get_attr(g5_cpu_freqs, policy->cpu); - - return cpufreq_frequency_table_cpuinfo(policy, - g5_cpu_freqs); -} - - -static struct cpufreq_driver g5_cpufreq_driver = { - .name = "powermac", - .owner = THIS_MODULE, - .flags = CPUFREQ_CONST_LOOPS, - .init = g5_cpufreq_cpu_init, - .verify = g5_cpufreq_verify, - .target = g5_cpufreq_target, - .get = g5_cpufreq_get_speed, - .attr = g5_cpu_freqs_attr, -}; - - -#ifdef CONFIG_PMAC_SMU - -static int __init g5_neo2_cpufreq_init(struct device_node *cpus) -{ - struct device_node *cpunode; - unsigned int psize, ssize; - unsigned long max_freq; - char *freq_method, *volt_method; - const u32 *valp; - u32 pvr_hi; - int use_volts_vdnap = 0; - int use_volts_smu = 0; - int rc = -ENODEV; - - /* Check supported platforms */ - if (of_machine_is_compatible("PowerMac8,1") || - of_machine_is_compatible("PowerMac8,2") || - of_machine_is_compatible("PowerMac9,1")) - use_volts_smu = 1; - else if (of_machine_is_compatible("PowerMac11,2")) - use_volts_vdnap = 1; - else - return -ENODEV; - - /* Get first CPU node */ - for (cpunode = NULL; - (cpunode = of_get_next_child(cpus, cpunode)) != NULL;) { - const u32 *reg = of_get_property(cpunode, "reg", NULL); - if (reg == NULL || (*reg) != 0) - continue; - if (!strcmp(cpunode->type, "cpu")) - break; - } - if (cpunode == NULL) { - printk(KERN_ERR "cpufreq: Can't find any CPU 0 node\n"); - return -ENODEV; - } - - /* Check 970FX for now */ - valp = of_get_property(cpunode, "cpu-version", NULL); - if (!valp) { - DBG("No cpu-version property !\n"); - goto bail_noprops; - } - pvr_hi = (*valp) >> 16; - if (pvr_hi != 0x3c && pvr_hi != 0x44) { - printk(KERN_ERR "cpufreq: Unsupported CPU version\n"); - goto bail_noprops; - } - - /* Look for the powertune data in the device-tree */ - g5_pmode_data = of_get_property(cpunode, "power-mode-data",&psize); - if (!g5_pmode_data) { - DBG("No power-mode-data !\n"); - goto bail_noprops; - } - g5_pmode_max = psize / sizeof(u32) - 1; - - if (use_volts_smu) { - const struct smu_sdbp_header *shdr; - - /* Look for the FVT table */ - shdr = smu_get_sdb_partition(SMU_SDB_FVT_ID, NULL); - if (!shdr) - goto bail_noprops; - g5_fvt_table = (struct smu_sdbp_fvt *)&shdr[1]; - ssize = (shdr->len * sizeof(u32)) - - sizeof(struct smu_sdbp_header); - g5_fvt_count = ssize / sizeof(struct smu_sdbp_fvt); - g5_fvt_cur = 0; - - /* Sanity checking */ - if (g5_fvt_count < 1 || g5_pmode_max < 1) - goto bail_noprops; - - g5_switch_volt = g5_smu_switch_volt; - volt_method = "SMU"; - } else if (use_volts_vdnap) { - struct device_node *root; - - root = of_find_node_by_path("/"); - if (root == NULL) { - printk(KERN_ERR "cpufreq: Can't find root of " - "device tree\n"); - goto bail_noprops; - } - pfunc_set_vdnap0 = pmf_find_function(root, "set-vdnap0"); - pfunc_vdnap0_complete = - pmf_find_function(root, "slewing-done"); - if (pfunc_set_vdnap0 == NULL || - pfunc_vdnap0_complete == NULL) { - printk(KERN_ERR "cpufreq: Can't find required " - "platform function\n"); - goto bail_noprops; - } - - g5_switch_volt = g5_vdnap_switch_volt; - volt_method = "GPIO"; - } else { - g5_switch_volt = g5_dummy_switch_volt; - volt_method = "none"; - } - - /* - * From what I see, clock-frequency is always the maximal frequency. - * The current driver can not slew sysclk yet, so we really only deal - * with powertune steps for now. We also only implement full freq and - * half freq in this version. So far, I haven't yet seen a machine - * supporting anything else. - */ - valp = of_get_property(cpunode, "clock-frequency", NULL); - if (!valp) - return -ENODEV; - max_freq = (*valp)/1000; - g5_cpu_freqs[0].frequency = max_freq; - g5_cpu_freqs[1].frequency = max_freq/2; - - /* Set callbacks */ - transition_latency = 12000; - g5_switch_freq = g5_scom_switch_freq; - g5_query_freq = g5_scom_query_freq; - freq_method = "SCOM"; - - /* Force apply current frequency to make sure everything is in - * sync (voltage is right for example). Firmware may leave us with - * a strange setting ... - */ - g5_switch_volt(CPUFREQ_HIGH); - msleep(10); - g5_pmode_cur = -1; - g5_switch_freq(g5_query_freq()); - - printk(KERN_INFO "Registering G5 CPU frequency driver\n"); - printk(KERN_INFO "Frequency method: %s, Voltage method: %s\n", - freq_method, volt_method); - printk(KERN_INFO "Low: %d Mhz, High: %d Mhz, Cur: %d MHz\n", - g5_cpu_freqs[1].frequency/1000, - g5_cpu_freqs[0].frequency/1000, - g5_cpu_freqs[g5_pmode_cur].frequency/1000); - - rc = cpufreq_register_driver(&g5_cpufreq_driver); - - /* We keep the CPU node on hold... hopefully, Apple G5 don't have - * hotplug CPU with a dynamic device-tree ... - */ - return rc; - - bail_noprops: - of_node_put(cpunode); - - return rc; -} - -#endif /* CONFIG_PMAC_SMU */ - - -static int __init g5_pm72_cpufreq_init(struct device_node *cpus) -{ - struct device_node *cpuid = NULL, *hwclock = NULL, *cpunode = NULL; - const u8 *eeprom = NULL; - const u32 *valp; - u64 max_freq, min_freq, ih, il; - int has_volt = 1, rc = 0; - - DBG("cpufreq: Initializing for PowerMac7,2, PowerMac7,3 and" - " RackMac3,1...\n"); - - /* Get first CPU node */ - for (cpunode = NULL; - (cpunode = of_get_next_child(cpus, cpunode)) != NULL;) { - if (!strcmp(cpunode->type, "cpu")) - break; - } - if (cpunode == NULL) { - printk(KERN_ERR "cpufreq: Can't find any CPU node\n"); - return -ENODEV; - } - - /* Lookup the cpuid eeprom node */ - cpuid = of_find_node_by_path("/u3@0,f8000000/i2c@f8001000/cpuid@a0"); - if (cpuid != NULL) - eeprom = of_get_property(cpuid, "cpuid", NULL); - if (eeprom == NULL) { - printk(KERN_ERR "cpufreq: Can't find cpuid EEPROM !\n"); - rc = -ENODEV; - goto bail; - } - - /* Lookup the i2c hwclock */ - for (hwclock = NULL; - (hwclock = of_find_node_by_name(hwclock, "i2c-hwclock")) != NULL;){ - const char *loc = of_get_property(hwclock, - "hwctrl-location", NULL); - if (loc == NULL) - continue; - if (strcmp(loc, "CPU CLOCK")) - continue; - if (!of_get_property(hwclock, "platform-get-frequency", NULL)) - continue; - break; - } - if (hwclock == NULL) { - printk(KERN_ERR "cpufreq: Can't find i2c clock chip !\n"); - rc = -ENODEV; - goto bail; - } - - DBG("cpufreq: i2c clock chip found: %s\n", hwclock->full_name); - - /* Now get all the platform functions */ - pfunc_cpu_getfreq = - pmf_find_function(hwclock, "get-frequency"); - pfunc_cpu_setfreq_high = - pmf_find_function(hwclock, "set-frequency-high"); - pfunc_cpu_setfreq_low = - pmf_find_function(hwclock, "set-frequency-low"); - pfunc_slewing_done = - pmf_find_function(hwclock, "slewing-done"); - pfunc_cpu0_volt_high = - pmf_find_function(hwclock, "set-voltage-high-0"); - pfunc_cpu0_volt_low = - pmf_find_function(hwclock, "set-voltage-low-0"); - pfunc_cpu1_volt_high = - pmf_find_function(hwclock, "set-voltage-high-1"); - pfunc_cpu1_volt_low = - pmf_find_function(hwclock, "set-voltage-low-1"); - - /* Check we have minimum requirements */ - if (pfunc_cpu_getfreq == NULL || pfunc_cpu_setfreq_high == NULL || - pfunc_cpu_setfreq_low == NULL || pfunc_slewing_done == NULL) { - printk(KERN_ERR "cpufreq: Can't find platform functions !\n"); - rc = -ENODEV; - goto bail; - } - - /* Check that we have complete sets */ - if (pfunc_cpu0_volt_high == NULL || pfunc_cpu0_volt_low == NULL) { - pmf_put_function(pfunc_cpu0_volt_high); - pmf_put_function(pfunc_cpu0_volt_low); - pfunc_cpu0_volt_high = pfunc_cpu0_volt_low = NULL; - has_volt = 0; - } - if (!has_volt || - pfunc_cpu1_volt_high == NULL || pfunc_cpu1_volt_low == NULL) { - pmf_put_function(pfunc_cpu1_volt_high); - pmf_put_function(pfunc_cpu1_volt_low); - pfunc_cpu1_volt_high = pfunc_cpu1_volt_low = NULL; - } - - /* Note: The device tree also contains a "platform-set-values" - * function for which I haven't quite figured out the usage. It - * might have to be called on init and/or wakeup, I'm not too sure - * but things seem to work fine without it so far ... - */ - - /* Get max frequency from device-tree */ - valp = of_get_property(cpunode, "clock-frequency", NULL); - if (!valp) { - printk(KERN_ERR "cpufreq: Can't find CPU frequency !\n"); - rc = -ENODEV; - goto bail; - } - - max_freq = (*valp)/1000; - - /* Now calculate reduced frequency by using the cpuid input freq - * ratio. This requires 64 bits math unless we are willing to lose - * some precision - */ - ih = *((u32 *)(eeprom + 0x10)); - il = *((u32 *)(eeprom + 0x20)); - - /* Check for machines with no useful settings */ - if (il == ih) { - printk(KERN_WARNING "cpufreq: No low frequency mode available" - " on this model !\n"); - rc = -ENODEV; - goto bail; - } - - min_freq = 0; - if (ih != 0 && il != 0) - min_freq = (max_freq * il) / ih; - - /* Sanity check */ - if (min_freq >= max_freq || min_freq < 1000) { - printk(KERN_ERR "cpufreq: Can't calculate low frequency !\n"); - rc = -ENXIO; - goto bail; - } - g5_cpu_freqs[0].frequency = max_freq; - g5_cpu_freqs[1].frequency = min_freq; - - /* Set callbacks */ - transition_latency = CPUFREQ_ETERNAL; - g5_switch_volt = g5_pfunc_switch_volt; - g5_switch_freq = g5_pfunc_switch_freq; - g5_query_freq = g5_pfunc_query_freq; - - /* Force apply current frequency to make sure everything is in - * sync (voltage is right for example). Firmware may leave us with - * a strange setting ... - */ - g5_switch_volt(CPUFREQ_HIGH); - msleep(10); - g5_pmode_cur = -1; - g5_switch_freq(g5_query_freq()); - - printk(KERN_INFO "Registering G5 CPU frequency driver\n"); - printk(KERN_INFO "Frequency method: i2c/pfunc, " - "Voltage method: %s\n", has_volt ? "i2c/pfunc" : "none"); - printk(KERN_INFO "Low: %d Mhz, High: %d Mhz, Cur: %d MHz\n", - g5_cpu_freqs[1].frequency/1000, - g5_cpu_freqs[0].frequency/1000, - g5_cpu_freqs[g5_pmode_cur].frequency/1000); - - rc = cpufreq_register_driver(&g5_cpufreq_driver); - bail: - if (rc != 0) { - pmf_put_function(pfunc_cpu_getfreq); - pmf_put_function(pfunc_cpu_setfreq_high); - pmf_put_function(pfunc_cpu_setfreq_low); - pmf_put_function(pfunc_slewing_done); - pmf_put_function(pfunc_cpu0_volt_high); - pmf_put_function(pfunc_cpu0_volt_low); - pmf_put_function(pfunc_cpu1_volt_high); - pmf_put_function(pfunc_cpu1_volt_low); - } - of_node_put(hwclock); - of_node_put(cpuid); - of_node_put(cpunode); - - return rc; -} - -static int __init g5_cpufreq_init(void) -{ - struct device_node *cpus; - int rc = 0; - - cpus = of_find_node_by_path("/cpus"); - if (cpus == NULL) { - DBG("No /cpus node !\n"); - return -ENODEV; - } - - if (of_machine_is_compatible("PowerMac7,2") || - of_machine_is_compatible("PowerMac7,3") || - of_machine_is_compatible("RackMac3,1")) - rc = g5_pm72_cpufreq_init(cpus); -#ifdef CONFIG_PMAC_SMU - else - rc = g5_neo2_cpufreq_init(cpus); -#endif /* CONFIG_PMAC_SMU */ - - of_node_put(cpus); - return rc; -} - -module_init(g5_cpufreq_init); - - -MODULE_LICENSE("GPL"); diff --git a/arch/s390/appldata/appldata_mem.c b/arch/s390/appldata/appldata_mem.c index 7ef60b52d6e0..42be53743133 100644 --- a/arch/s390/appldata/appldata_mem.c +++ b/arch/s390/appldata/appldata_mem.c @@ -32,7 +32,7 @@ * book: * http://oss.software.ibm.com/developerworks/opensource/linux390/index.shtml */ -static struct appldata_mem_data { +struct appldata_mem_data { u64 timestamp; u32 sync_count_1; /* after VM collected the record data, */ u32 sync_count_2; /* sync_count_1 and sync_count_2 should be the @@ -63,7 +63,7 @@ static struct appldata_mem_data { u64 pgmajfault; /* page faults (major only) */ // <-- New in 2.6 -} __attribute__((packed)) appldata_mem_data; +} __packed; /* @@ -118,7 +118,6 @@ static struct appldata_ops ops = { .record_nr = APPLDATA_RECORD_MEM_ID, .size = sizeof(struct appldata_mem_data), .callback = &appldata_get_mem_data, - .data = &appldata_mem_data, .owner = THIS_MODULE, .mod_lvl = {0xF0, 0xF0}, /* EBCDIC "00" */ }; @@ -131,7 +130,17 @@ static struct appldata_ops ops = { */ static int __init appldata_mem_init(void) { - return appldata_register_ops(&ops); + int ret; + + ops.data = kzalloc(sizeof(struct appldata_mem_data), GFP_KERNEL); + if (!ops.data) + return -ENOMEM; + + ret = appldata_register_ops(&ops); + if (ret) + kfree(ops.data); + + return ret; } /* @@ -142,6 +151,7 @@ static int __init appldata_mem_init(void) static void __exit appldata_mem_exit(void) { appldata_unregister_ops(&ops); + kfree(ops.data); } diff --git a/arch/s390/appldata/appldata_net_sum.c b/arch/s390/appldata/appldata_net_sum.c index 2d224b945355..66037d2622b4 100644 --- a/arch/s390/appldata/appldata_net_sum.c +++ b/arch/s390/appldata/appldata_net_sum.c @@ -29,7 +29,7 @@ * book: * http://oss.software.ibm.com/developerworks/opensource/linux390/index.shtml */ -static struct appldata_net_sum_data { +struct appldata_net_sum_data { u64 timestamp; u32 sync_count_1; /* after VM collected the record data, */ u32 sync_count_2; /* sync_count_1 and sync_count_2 should be the @@ -51,7 +51,7 @@ static struct appldata_net_sum_data { u64 rx_dropped; /* no space in linux buffers */ u64 tx_dropped; /* no space available in linux */ u64 collisions; /* collisions while transmitting */ -} __attribute__((packed)) appldata_net_sum_data; +} __packed; /* @@ -121,7 +121,6 @@ static struct appldata_ops ops = { .record_nr = APPLDATA_RECORD_NET_SUM_ID, .size = sizeof(struct appldata_net_sum_data), .callback = &appldata_get_net_sum_data, - .data = &appldata_net_sum_data, .owner = THIS_MODULE, .mod_lvl = {0xF0, 0xF0}, /* EBCDIC "00" */ }; @@ -134,7 +133,17 @@ static struct appldata_ops ops = { */ static int __init appldata_net_init(void) { - return appldata_register_ops(&ops); + int ret; + + ops.data = kzalloc(sizeof(struct appldata_net_sum_data), GFP_KERNEL); + if (!ops.data) + return -ENOMEM; + + ret = appldata_register_ops(&ops); + if (ret) + kfree(ops.data); + + return ret; } /* @@ -145,6 +154,7 @@ static int __init appldata_net_init(void) static void __exit appldata_net_exit(void) { appldata_unregister_ops(&ops); + kfree(ops.data); } diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c index 7fd3690b6760..138893e5f736 100644 --- a/arch/s390/hypfs/hypfs_diag.c +++ b/arch/s390/hypfs/hypfs_diag.c @@ -651,9 +651,7 @@ static int hypfs_create_cpu_files(struct super_block *sb, } diag224_idx2name(cpu_info__ctidx(diag204_info_type, cpu_info), buffer); rc = hypfs_create_str(sb, cpu_dir, "type", buffer); - if (IS_ERR(rc)) - return PTR_ERR(rc); - return 0; + return PTR_RET(rc); } static void *hypfs_create_lpar_files(struct super_block *sb, @@ -702,9 +700,7 @@ static int hypfs_create_phys_cpu_files(struct super_block *sb, return PTR_ERR(rc); diag224_idx2name(phys_cpu__ctidx(diag204_info_type, cpu_info), buffer); rc = hypfs_create_str(sb, cpu_dir, "type", buffer); - if (IS_ERR(rc)) - return PTR_ERR(rc); - return 0; + return PTR_RET(rc); } static void *hypfs_create_phys_files(struct super_block *sb, diff --git a/arch/s390/include/asm/airq.h b/arch/s390/include/asm/airq.h index 9819891ed7a2..4066cee0c2d2 100644 --- a/arch/s390/include/asm/airq.h +++ b/arch/s390/include/asm/airq.h @@ -9,9 +9,18 @@ #ifndef _ASM_S390_AIRQ_H #define _ASM_S390_AIRQ_H -typedef void (*adapter_int_handler_t)(void *, void *); +struct airq_struct { + struct hlist_node list; /* Handler queueing. */ + void (*handler)(struct airq_struct *); /* Thin-interrupt handler */ + u8 *lsi_ptr; /* Local-Summary-Indicator pointer */ + u8 lsi_mask; /* Local-Summary-Indicator mask */ + u8 isc; /* Interrupt-subclass */ + u8 flags; +}; -void *s390_register_adapter_interrupt(adapter_int_handler_t, void *, u8); -void s390_unregister_adapter_interrupt(void *, u8); +#define AIRQ_PTR_ALLOCATED 0x01 + +int register_adapter_interrupt(struct airq_struct *airq); +void unregister_adapter_interrupt(struct airq_struct *airq); #endif /* _ASM_S390_AIRQ_H */ diff --git a/arch/s390/include/asm/dma-mapping.h b/arch/s390/include/asm/dma-mapping.h index 2f8c1abeb086..3fbc67d9e197 100644 --- a/arch/s390/include/asm/dma-mapping.h +++ b/arch/s390/include/asm/dma-mapping.h @@ -53,7 +53,7 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) debug_dma_mapping_error(dev, dma_addr); if (dma_ops->mapping_error) return dma_ops->mapping_error(dev, dma_addr); - return (dma_addr == DMA_ERROR_CODE); + return dma_addr == DMA_ERROR_CODE; } static inline void *dma_alloc_coherent(struct device *dev, size_t size, diff --git a/arch/s390/include/asm/facility.h b/arch/s390/include/asm/facility.h index 2ee66a65f2d4..0aa6a7ed95a3 100644 --- a/arch/s390/include/asm/facility.h +++ b/arch/s390/include/asm/facility.h @@ -13,6 +13,16 @@ #define MAX_FACILITY_BIT (256*8) /* stfle_fac_list has 256 bytes */ +static inline int __test_facility(unsigned long nr, void *facilities) +{ + unsigned char *ptr; + + if (nr >= MAX_FACILITY_BIT) + return 0; + ptr = (unsigned char *) facilities + (nr >> 3); + return (*ptr & (0x80 >> (nr & 7))) != 0; +} + /* * The test_facility function uses the bit odering where the MSB is bit 0. * That makes it easier to query facility bits with the bit number as @@ -20,12 +30,7 @@ */ static inline int test_facility(unsigned long nr) { - unsigned char *ptr; - - if (nr >= MAX_FACILITY_BIT) - return 0; - ptr = (unsigned char *) &S390_lowcore.stfle_fac_list + (nr >> 3); - return (*ptr & (0x80 >> (nr & 7))) != 0; + return __test_facility(nr, &S390_lowcore.stfle_fac_list); } /** diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h index fd9be010f9b2..cd6b9ee7b69c 100644 --- a/arch/s390/include/asm/io.h +++ b/arch/s390/include/asm/io.h @@ -13,28 +13,6 @@ #include <asm/page.h> #include <asm/pci_io.h> -/* - * Change virtual addresses to physical addresses and vv. - * These are pretty trivial - */ -static inline unsigned long virt_to_phys(volatile void * address) -{ - unsigned long real_address; - asm volatile( - " lra %0,0(%1)\n" - " jz 0f\n" - " la %0,0\n" - "0:" - : "=a" (real_address) : "a" (address) : "cc"); - return real_address; -} -#define virt_to_phys virt_to_phys - -static inline void * phys_to_virt(unsigned long address) -{ - return (void *) address; -} - void *xlate_dev_mem_ptr(unsigned long phys); #define xlate_dev_mem_ptr xlate_dev_mem_ptr void unxlate_dev_mem_ptr(unsigned long phys, void *addr); diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 16bd5d169cdb..3238d4004e84 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -62,13 +62,20 @@ struct sca_block { #define CPUSTAT_MCDS 0x00000100 #define CPUSTAT_SM 0x00000080 #define CPUSTAT_G 0x00000008 +#define CPUSTAT_GED 0x00000004 #define CPUSTAT_J 0x00000002 #define CPUSTAT_P 0x00000001 struct kvm_s390_sie_block { atomic_t cpuflags; /* 0x0000 */ __u32 prefix; /* 0x0004 */ - __u8 reserved8[32]; /* 0x0008 */ + __u8 reserved08[4]; /* 0x0008 */ +#define PROG_IN_SIE (1<<0) + __u32 prog0c; /* 0x000c */ + __u8 reserved10[16]; /* 0x0010 */ +#define PROG_BLOCK_SIE 0x00000001 + atomic_t prog20; /* 0x0020 */ + __u8 reserved24[4]; /* 0x0024 */ __u64 cputm; /* 0x0028 */ __u64 ckc; /* 0x0030 */ __u64 epoch; /* 0x0038 */ @@ -90,7 +97,8 @@ struct kvm_s390_sie_block { __u32 scaoh; /* 0x005c */ __u8 reserved60; /* 0x0060 */ __u8 ecb; /* 0x0061 */ - __u8 reserved62[2]; /* 0x0062 */ + __u8 ecb2; /* 0x0062 */ + __u8 reserved63[1]; /* 0x0063 */ __u32 scaol; /* 0x0064 */ __u8 reserved68[4]; /* 0x0068 */ __u32 todpr; /* 0x006c */ @@ -130,6 +138,7 @@ struct kvm_vcpu_stat { u32 deliver_program_int; u32 deliver_io_int; u32 exit_wait_state; + u32 instruction_pfmf; u32 instruction_stidp; u32 instruction_spx; u32 instruction_stpx; @@ -166,7 +175,7 @@ struct kvm_s390_ext_info { }; #define PGM_OPERATION 0x01 -#define PGM_PRIVILEGED_OPERATION 0x02 +#define PGM_PRIVILEGED_OP 0x02 #define PGM_EXECUTE 0x03 #define PGM_PROTECTION 0x04 #define PGM_ADDRESSING 0x05 @@ -219,7 +228,7 @@ struct kvm_s390_local_interrupt { atomic_t active; struct kvm_s390_float_interrupt *float_int; int timer_due; /* event indicator for waitqueue below */ - wait_queue_head_t wq; + wait_queue_head_t *wq; atomic_t *cpuflags; unsigned int action_bits; }; @@ -266,4 +275,5 @@ struct kvm_arch{ }; extern int sie64a(struct kvm_s390_sie_block *, u64 *); +extern char sie_exit; #endif diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index 6c1801235db9..6e577ba0e5da 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -120,7 +120,6 @@ struct zpci_dev { struct dentry *debugfs_dev; struct dentry *debugfs_perf; - struct dentry *debugfs_debug; }; struct pci_hp_callback_ops { @@ -143,7 +142,6 @@ int zpci_enable_device(struct zpci_dev *); int zpci_disable_device(struct zpci_dev *); void zpci_stop_device(struct zpci_dev *); void zpci_free_device(struct zpci_dev *); -int zpci_scan_device(struct zpci_dev *); int zpci_register_ioat(struct zpci_dev *, u8, u64, u64, u64); int zpci_unregister_ioat(struct zpci_dev *, u8); diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h index 5f0173a31693..1141fb3e7b21 100644 --- a/arch/s390/include/asm/perf_event.h +++ b/arch/s390/include/asm/perf_event.h @@ -14,3 +14,13 @@ /* Per-CPU flags for PMU states */ #define PMU_F_RESERVED 0x1000 #define PMU_F_ENABLED 0x2000 + +#ifdef CONFIG_64BIT + +/* Perf callbacks */ +struct pt_regs; +extern unsigned long perf_instruction_pointer(struct pt_regs *regs); +extern unsigned long perf_misc_flags(struct pt_regs *regs); +#define perf_misc_flags(regs) perf_misc_flags(regs) + +#endif /* CONFIG_64BIT */ diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index 590c3219c634..e1408ddb94f8 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -22,6 +22,9 @@ unsigned long *page_table_alloc(struct mm_struct *, unsigned long); void page_table_free(struct mm_struct *, unsigned long *); void page_table_free_rcu(struct mmu_gather *, unsigned long *); +int set_guest_storage_key(struct mm_struct *mm, unsigned long addr, + unsigned long key, bool nq); + static inline void clear_table(unsigned long *s, unsigned long val, size_t n) { typedef struct { char _[n]; } addrtype; diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 9aefa3c64eb2..0ea4e591fa78 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -296,18 +296,16 @@ extern unsigned long MODULES_END; #define _SEGMENT_ENTRY_EMPTY (_SEGMENT_ENTRY_INV) /* Page status table bits for virtualization */ -#define RCP_ACC_BITS 0xf0000000UL -#define RCP_FP_BIT 0x08000000UL -#define RCP_PCL_BIT 0x00800000UL -#define RCP_HR_BIT 0x00400000UL -#define RCP_HC_BIT 0x00200000UL -#define RCP_GR_BIT 0x00040000UL -#define RCP_GC_BIT 0x00020000UL -#define RCP_IN_BIT 0x00002000UL /* IPTE notify bit */ - -/* User dirty / referenced bit for KVM's migration feature */ -#define KVM_UR_BIT 0x00008000UL -#define KVM_UC_BIT 0x00004000UL +#define PGSTE_ACC_BITS 0xf0000000UL +#define PGSTE_FP_BIT 0x08000000UL +#define PGSTE_PCL_BIT 0x00800000UL +#define PGSTE_HR_BIT 0x00400000UL +#define PGSTE_HC_BIT 0x00200000UL +#define PGSTE_GR_BIT 0x00040000UL +#define PGSTE_GC_BIT 0x00020000UL +#define PGSTE_UR_BIT 0x00008000UL +#define PGSTE_UC_BIT 0x00004000UL /* user dirty (migration) */ +#define PGSTE_IN_BIT 0x00002000UL /* IPTE notify bit */ #else /* CONFIG_64BIT */ @@ -364,18 +362,16 @@ extern unsigned long MODULES_END; | _SEGMENT_ENTRY_SPLIT | _SEGMENT_ENTRY_CO) /* Page status table bits for virtualization */ -#define RCP_ACC_BITS 0xf000000000000000UL -#define RCP_FP_BIT 0x0800000000000000UL -#define RCP_PCL_BIT 0x0080000000000000UL -#define RCP_HR_BIT 0x0040000000000000UL -#define RCP_HC_BIT 0x0020000000000000UL -#define RCP_GR_BIT 0x0004000000000000UL -#define RCP_GC_BIT 0x0002000000000000UL -#define RCP_IN_BIT 0x0000200000000000UL /* IPTE notify bit */ - -/* User dirty / referenced bit for KVM's migration feature */ -#define KVM_UR_BIT 0x0000800000000000UL -#define KVM_UC_BIT 0x0000400000000000UL +#define PGSTE_ACC_BITS 0xf000000000000000UL +#define PGSTE_FP_BIT 0x0800000000000000UL +#define PGSTE_PCL_BIT 0x0080000000000000UL +#define PGSTE_HR_BIT 0x0040000000000000UL +#define PGSTE_HC_BIT 0x0020000000000000UL +#define PGSTE_GR_BIT 0x0004000000000000UL +#define PGSTE_GC_BIT 0x0002000000000000UL +#define PGSTE_UR_BIT 0x0000800000000000UL +#define PGSTE_UC_BIT 0x0000400000000000UL /* user dirty (migration) */ +#define PGSTE_IN_BIT 0x0000200000000000UL /* IPTE notify bit */ #endif /* CONFIG_64BIT */ @@ -615,8 +611,8 @@ static inline pgste_t pgste_get_lock(pte_t *ptep) asm( " lg %0,%2\n" "0: lgr %1,%0\n" - " nihh %0,0xff7f\n" /* clear RCP_PCL_BIT in old */ - " oihh %1,0x0080\n" /* set RCP_PCL_BIT in new */ + " nihh %0,0xff7f\n" /* clear PCL bit in old */ + " oihh %1,0x0080\n" /* set PCL bit in new */ " csg %0,%1,%2\n" " jl 0b\n" : "=&d" (old), "=&d" (new), "=Q" (ptep[PTRS_PER_PTE]) @@ -629,7 +625,7 @@ static inline void pgste_set_unlock(pte_t *ptep, pgste_t pgste) { #ifdef CONFIG_PGSTE asm( - " nihh %1,0xff7f\n" /* clear RCP_PCL_BIT */ + " nihh %1,0xff7f\n" /* clear PCL bit */ " stg %1,%0\n" : "=Q" (ptep[PTRS_PER_PTE]) : "d" (pgste_val(pgste)), "Q" (ptep[PTRS_PER_PTE]) @@ -662,14 +658,14 @@ static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste) else if (bits) page_reset_referenced(address); /* Transfer page changed & referenced bit to guest bits in pgste */ - pgste_val(pgste) |= bits << 48; /* RCP_GR_BIT & RCP_GC_BIT */ + pgste_val(pgste) |= bits << 48; /* GR bit & GC bit */ /* Get host changed & referenced bits from pgste */ - bits |= (pgste_val(pgste) & (RCP_HR_BIT | RCP_HC_BIT)) >> 52; + bits |= (pgste_val(pgste) & (PGSTE_HR_BIT | PGSTE_HC_BIT)) >> 52; /* Transfer page changed & referenced bit to kvm user bits */ - pgste_val(pgste) |= bits << 45; /* KVM_UR_BIT & KVM_UC_BIT */ + pgste_val(pgste) |= bits << 45; /* PGSTE_UR_BIT & PGSTE_UC_BIT */ /* Clear relevant host bits in pgste. */ - pgste_val(pgste) &= ~(RCP_HR_BIT | RCP_HC_BIT); - pgste_val(pgste) &= ~(RCP_ACC_BITS | RCP_FP_BIT); + pgste_val(pgste) &= ~(PGSTE_HR_BIT | PGSTE_HC_BIT); + pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT); /* Copy page access key and fetch protection bit to pgste */ pgste_val(pgste) |= (unsigned long) (skey & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56; @@ -690,15 +686,15 @@ static inline pgste_t pgste_update_young(pte_t *ptep, pgste_t pgste) /* Get referenced bit from storage key */ young = page_reset_referenced(pte_val(*ptep) & PAGE_MASK); if (young) - pgste_val(pgste) |= RCP_GR_BIT; + pgste_val(pgste) |= PGSTE_GR_BIT; /* Get host referenced bit from pgste */ - if (pgste_val(pgste) & RCP_HR_BIT) { - pgste_val(pgste) &= ~RCP_HR_BIT; + if (pgste_val(pgste) & PGSTE_HR_BIT) { + pgste_val(pgste) &= ~PGSTE_HR_BIT; young = 1; } /* Transfer referenced bit to kvm user bits and pte */ if (young) { - pgste_val(pgste) |= KVM_UR_BIT; + pgste_val(pgste) |= PGSTE_UR_BIT; pte_val(*ptep) |= _PAGE_SWR; } #endif @@ -720,7 +716,7 @@ static inline void pgste_set_key(pte_t *ptep, pgste_t pgste, pte_t entry) * The guest C/R information is still in the PGSTE, set real * key C/R to 0. */ - nkey = (pgste_val(pgste) & (RCP_ACC_BITS | RCP_FP_BIT)) >> 56; + nkey = (pgste_val(pgste) & (PGSTE_ACC_BITS | PGSTE_FP_BIT)) >> 56; page_set_storage_key(address, nkey, 0); #endif } @@ -750,6 +746,7 @@ struct gmap { struct mm_struct *mm; unsigned long *table; unsigned long asce; + void *private; struct list_head crst_list; }; @@ -808,8 +805,8 @@ static inline pgste_t pgste_ipte_notify(struct mm_struct *mm, pte_t *ptep, pgste_t pgste) { #ifdef CONFIG_PGSTE - if (pgste_val(pgste) & RCP_IN_BIT) { - pgste_val(pgste) &= ~RCP_IN_BIT; + if (pgste_val(pgste) & PGSTE_IN_BIT) { + pgste_val(pgste) &= ~PGSTE_IN_BIT; gmap_do_ipte_notify(mm, addr, ptep); } #endif @@ -977,8 +974,8 @@ static inline int ptep_test_and_clear_user_dirty(struct mm_struct *mm, if (mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); pgste = pgste_update_all(ptep, pgste); - dirty = !!(pgste_val(pgste) & KVM_UC_BIT); - pgste_val(pgste) &= ~KVM_UC_BIT; + dirty = !!(pgste_val(pgste) & PGSTE_UC_BIT); + pgste_val(pgste) &= ~PGSTE_UC_BIT; pgste_set_unlock(ptep, pgste); return dirty; } @@ -997,8 +994,8 @@ static inline int ptep_test_and_clear_user_young(struct mm_struct *mm, if (mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); pgste = pgste_update_young(ptep, pgste); - young = !!(pgste_val(pgste) & KVM_UR_BIT); - pgste_val(pgste) &= ~KVM_UR_BIT; + young = !!(pgste_val(pgste) & PGSTE_UR_BIT); + pgste_val(pgste) &= ~PGSTE_UR_BIT; pgste_set_unlock(ptep, pgste); } return young; diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index 559512a455da..52b56533c57c 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -24,6 +24,7 @@ struct pt_regs unsigned long gprs[NUM_GPRS]; unsigned long orig_gpr2; unsigned int int_code; + unsigned int int_parm; unsigned long int_parm_long; }; diff --git a/arch/s390/include/uapi/asm/Kbuild b/arch/s390/include/uapi/asm/Kbuild index 9ccd1905bdad..6a9a9eb645f5 100644 --- a/arch/s390/include/uapi/asm/Kbuild +++ b/arch/s390/include/uapi/asm/Kbuild @@ -35,6 +35,7 @@ header-y += siginfo.h header-y += signal.h header-y += socket.h header-y += sockios.h +header-y += sclp_ctl.h header-y += stat.h header-y += statfs.h header-y += swab.h diff --git a/arch/s390/include/uapi/asm/chsc.h b/arch/s390/include/uapi/asm/chsc.h index 1c6a7f85a581..65dc694725a8 100644 --- a/arch/s390/include/uapi/asm/chsc.h +++ b/arch/s390/include/uapi/asm/chsc.h @@ -29,6 +29,16 @@ struct chsc_async_area { __u8 data[CHSC_SIZE - sizeof(struct chsc_async_header)]; } __attribute__ ((packed)); +struct chsc_header { + __u16 length; + __u16 code; +} __attribute__ ((packed)); + +struct chsc_sync_area { + struct chsc_header header; + __u8 data[CHSC_SIZE - sizeof(struct chsc_header)]; +} __attribute__ ((packed)); + struct chsc_response_struct { __u16 length; __u16 code; @@ -126,5 +136,8 @@ struct chsc_cpd_info { #define CHSC_INFO_CCL _IOWR(CHSC_IOCTL_MAGIC, 0x86, struct chsc_comp_list) #define CHSC_INFO_CPD _IOWR(CHSC_IOCTL_MAGIC, 0x87, struct chsc_cpd_info) #define CHSC_INFO_DCAL _IOWR(CHSC_IOCTL_MAGIC, 0x88, struct chsc_dcal) +#define CHSC_START_SYNC _IOWR(CHSC_IOCTL_MAGIC, 0x89, struct chsc_sync_area) +#define CHSC_ON_CLOSE_SET _IOWR(CHSC_IOCTL_MAGIC, 0x8a, struct chsc_async_area) +#define CHSC_ON_CLOSE_REMOVE _IO(CHSC_IOCTL_MAGIC, 0x8b) #endif diff --git a/arch/s390/include/uapi/asm/dasd.h b/arch/s390/include/uapi/asm/dasd.h index 38eca3ba40e2..5812a3b2df9e 100644 --- a/arch/s390/include/uapi/asm/dasd.h +++ b/arch/s390/include/uapi/asm/dasd.h @@ -261,6 +261,10 @@ struct dasd_snid_ioctl_data { #define BIODASDQUIESCE _IO(DASD_IOCTL_LETTER,6) /* Resume IO on device */ #define BIODASDRESUME _IO(DASD_IOCTL_LETTER,7) +/* Abort all I/O on a device */ +#define BIODASDABORTIO _IO(DASD_IOCTL_LETTER, 240) +/* Allow I/O on a device */ +#define BIODASDALLOWIO _IO(DASD_IOCTL_LETTER, 241) /* retrieve API version number */ diff --git a/arch/s390/include/uapi/asm/sclp_ctl.h b/arch/s390/include/uapi/asm/sclp_ctl.h new file mode 100644 index 000000000000..f2818613ee41 --- /dev/null +++ b/arch/s390/include/uapi/asm/sclp_ctl.h @@ -0,0 +1,24 @@ +/* + * IOCTL interface for SCLP + * + * Copyright IBM Corp. 2012 + * + * Author: Michael Holzheu <holzheu@linux.vnet.ibm.com> + */ + +#ifndef _ASM_SCLP_CTL_H +#define _ASM_SCLP_CTL_H + +#include <linux/types.h> + +struct sclp_ctl_sccb { + __u32 cmdw; + __u64 sccb; +} __attribute__((packed)); + +#define SCLP_CTL_IOCTL_MAGIC 0x10 + +#define SCLP_CTL_SCCB \ + _IOWR(SCLP_CTL_IOCTL_MAGIC, 0x10, struct sclp_ctl_sccb) + +#endif diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 7a82f9f70100..2416138ebd3e 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -7,6 +7,7 @@ #define ASM_OFFSETS_C #include <linux/kbuild.h> +#include <linux/kvm_host.h> #include <linux/sched.h> #include <asm/cputime.h> #include <asm/vdso.h> @@ -47,6 +48,7 @@ int main(void) DEFINE(__PT_GPRS, offsetof(struct pt_regs, gprs)); DEFINE(__PT_ORIG_GPR2, offsetof(struct pt_regs, orig_gpr2)); DEFINE(__PT_INT_CODE, offsetof(struct pt_regs, int_code)); + DEFINE(__PT_INT_PARM, offsetof(struct pt_regs, int_parm)); DEFINE(__PT_INT_PARM_LONG, offsetof(struct pt_regs, int_parm_long)); DEFINE(__PT_SIZE, sizeof(struct pt_regs)); BLANK(); @@ -161,6 +163,8 @@ int main(void) DEFINE(__LC_PGM_TDB, offsetof(struct _lowcore, pgm_tdb)); DEFINE(__THREAD_trap_tdb, offsetof(struct task_struct, thread.trap_tdb)); DEFINE(__GMAP_ASCE, offsetof(struct gmap, asce)); + DEFINE(__SIE_PROG0C, offsetof(struct kvm_s390_sie_block, prog0c)); + DEFINE(__SIE_PROG20, offsetof(struct kvm_s390_sie_block, prog20)); #endif /* CONFIG_32BIT */ return 0; } diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 4d5e6f8a7978..be7a408be7a1 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -429,11 +429,19 @@ io_skip: stm %r0,%r7,__PT_R0(%r11) mvc __PT_R8(32,%r11),__LC_SAVE_AREA_ASYNC stm %r8,%r9,__PT_PSW(%r11) + mvc __PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID TRACE_IRQS_OFF xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) +io_loop: l %r1,BASED(.Ldo_IRQ) lr %r2,%r11 # pass pointer to pt_regs basr %r14,%r1 # call do_IRQ + tm __LC_MACHINE_FLAGS+2,0x10 # MACHINE_FLAG_LPAR + jz io_return + tpi 0 + jz io_return + mvc __PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID + j io_loop io_return: LOCKDEP_SYS_EXIT TRACE_IRQS_ON @@ -573,10 +581,10 @@ ext_skip: stm %r0,%r7,__PT_R0(%r11) mvc __PT_R8(32,%r11),__LC_SAVE_AREA_ASYNC stm %r8,%r9,__PT_PSW(%r11) + mvc __PT_INT_CODE(4,%r11),__LC_EXT_CPU_ADDR + mvc __PT_INT_PARM(4,%r11),__LC_EXT_PARAMS TRACE_IRQS_OFF lr %r2,%r11 # pass pointer to pt_regs - l %r3,__LC_EXT_CPU_ADDR # get cpu address + interruption code - l %r4,__LC_EXT_PARAMS # get external parameters l %r1,BASED(.Ldo_extint) basr %r14,%r1 # call do_extint j io_return diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index aa0ab02e9595..3ddbc26d246e 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -54,7 +54,7 @@ void handle_signal32(unsigned long sig, struct k_sigaction *ka, void do_notify_resume(struct pt_regs *regs); struct ext_code; -void do_extint(struct pt_regs *regs, struct ext_code, unsigned int, unsigned long); +void do_extint(struct pt_regs *regs); void do_restart(void); void __init startup_init(void); void die(struct pt_regs *regs, const char *str); diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S index 4c17eece707e..1c039d0c24c7 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -47,7 +47,6 @@ _TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ _TIF_MCCK_PENDING) _TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \ _TIF_SYSCALL_TRACEPOINT) -_TIF_EXIT_SIE = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING) #define BASED(name) name-system_call(%r13) @@ -81,23 +80,27 @@ _TIF_EXIT_SIE = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING) #endif .endm - .macro HANDLE_SIE_INTERCEPT scratch,pgmcheck + .macro HANDLE_SIE_INTERCEPT scratch,reason #if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE) tmhh %r8,0x0001 # interrupting from user ? - jnz .+42 + jnz .+62 lgr \scratch,%r9 - slg \scratch,BASED(.Lsie_loop) - clg \scratch,BASED(.Lsie_length) - .if \pgmcheck + slg \scratch,BASED(.Lsie_critical) + clg \scratch,BASED(.Lsie_critical_length) + .if \reason==1 # Some program interrupts are suppressing (e.g. protection). # We must also check the instruction after SIE in that case. # do_protection_exception will rewind to rewind_pad - jh .+22 + jh .+42 .else - jhe .+22 + jhe .+42 .endif - lg %r9,BASED(.Lsie_loop) - LPP BASED(.Lhost_id) # set host id + lg %r14,__SF_EMPTY(%r15) # get control block pointer + LPP __SF_EMPTY+16(%r15) # set host id + ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE + lctlg %c1,%c1,__LC_USER_ASCE # load primary asce + larl %r9,sie_exit # skip forward to sie_exit + mvi __SF_EMPTY+31(%r15),\reason # set exit reason #endif .endm @@ -450,7 +453,7 @@ ENTRY(io_int_handler) lg %r12,__LC_THREAD_INFO larl %r13,system_call lmg %r8,%r9,__LC_IO_OLD_PSW - HANDLE_SIE_INTERCEPT %r14,0 + HANDLE_SIE_INTERCEPT %r14,2 SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT tmhh %r8,0x0001 # interrupting from user? jz io_skip @@ -460,10 +463,18 @@ io_skip: stmg %r0,%r7,__PT_R0(%r11) mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC stmg %r8,%r9,__PT_PSW(%r11) + mvc __PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID TRACE_IRQS_OFF xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) +io_loop: lgr %r2,%r11 # pass pointer to pt_regs brasl %r14,do_IRQ + tm __LC_MACHINE_FLAGS+6,0x10 # MACHINE_FLAG_LPAR + jz io_return + tpi 0 + jz io_return + mvc __PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID + j io_loop io_return: LOCKDEP_SYS_EXIT TRACE_IRQS_ON @@ -595,7 +606,7 @@ ENTRY(ext_int_handler) lg %r12,__LC_THREAD_INFO larl %r13,system_call lmg %r8,%r9,__LC_EXT_OLD_PSW - HANDLE_SIE_INTERCEPT %r14,0 + HANDLE_SIE_INTERCEPT %r14,3 SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT tmhh %r8,0x0001 # interrupting from user ? jz ext_skip @@ -605,13 +616,13 @@ ext_skip: stmg %r0,%r7,__PT_R0(%r11) mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC stmg %r8,%r9,__PT_PSW(%r11) + lghi %r1,__LC_EXT_PARAMS2 + mvc __PT_INT_CODE(4,%r11),__LC_EXT_CPU_ADDR + mvc __PT_INT_PARM(4,%r11),__LC_EXT_PARAMS + mvc __PT_INT_PARM_LONG(8,%r11),0(%r1) TRACE_IRQS_OFF xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) - lghi %r1,4096 lgr %r2,%r11 # pass pointer to pt_regs - llgf %r3,__LC_EXT_CPU_ADDR # get cpu address + interruption code - llgf %r4,__LC_EXT_PARAMS # get external parameter - lg %r5,__LC_EXT_PARAMS2-4096(%r1) # get 64 bit external parameter brasl %r14,do_extint j io_return @@ -643,7 +654,7 @@ ENTRY(mcck_int_handler) lg %r12,__LC_THREAD_INFO larl %r13,system_call lmg %r8,%r9,__LC_MCK_OLD_PSW - HANDLE_SIE_INTERCEPT %r14,0 + HANDLE_SIE_INTERCEPT %r14,4 tm __LC_MCCK_CODE,0x80 # system damage? jo mcck_panic # yes -> rest of mcck code invalid lghi %r14,__LC_CPU_TIMER_SAVE_AREA @@ -937,56 +948,50 @@ ENTRY(sie64a) stmg %r6,%r14,__SF_GPRS(%r15) # save kernel registers stg %r2,__SF_EMPTY(%r15) # save control block pointer stg %r3,__SF_EMPTY+8(%r15) # save guest register save area - xc __SF_EMPTY+16(8,%r15),__SF_EMPTY+16(%r15) # host id == 0 + xc __SF_EMPTY+16(16,%r15),__SF_EMPTY+16(%r15) # host id & reason lmg %r0,%r13,0(%r3) # load guest gprs 0-13 -# some program checks are suppressing. C code (e.g. do_protection_exception) -# will rewind the PSW by the ILC, which is 4 bytes in case of SIE. Other -# instructions in the sie_loop should not cause program interrupts. So -# lets use a nop (47 00 00 00) as a landing pad. -# See also HANDLE_SIE_INTERCEPT -rewind_pad: - nop 0 -sie_loop: - lg %r14,__LC_THREAD_INFO # pointer thread_info struct - tm __TI_flags+7(%r14),_TIF_EXIT_SIE - jnz sie_exit lg %r14,__LC_GMAP # get gmap pointer ltgr %r14,%r14 jz sie_gmap lctlg %c1,%c1,__GMAP_ASCE(%r14) # load primary asce sie_gmap: lg %r14,__SF_EMPTY(%r15) # get control block pointer + oi __SIE_PROG0C+3(%r14),1 # we are going into SIE now + tm __SIE_PROG20+3(%r14),1 # last exit... + jnz sie_done LPP __SF_EMPTY(%r15) # set guest id sie 0(%r14) sie_done: LPP __SF_EMPTY+16(%r15) # set host id - lg %r14,__LC_THREAD_INFO # pointer thread_info struct -sie_exit: + ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE lctlg %c1,%c1,__LC_USER_ASCE # load primary asce +# some program checks are suppressing. C code (e.g. do_protection_exception) +# will rewind the PSW by the ILC, which is 4 bytes in case of SIE. Other +# instructions beween sie64a and sie_done should not cause program +# interrupts. So lets use a nop (47 00 00 00) as a landing pad. +# See also HANDLE_SIE_INTERCEPT +rewind_pad: + nop 0 + .globl sie_exit +sie_exit: lg %r14,__SF_EMPTY+8(%r15) # load guest register save area stmg %r0,%r13,0(%r14) # save guest gprs 0-13 lmg %r6,%r14,__SF_GPRS(%r15) # restore kernel registers - lghi %r2,0 + lg %r2,__SF_EMPTY+24(%r15) # return exit reason code br %r14 sie_fault: - lctlg %c1,%c1,__LC_USER_ASCE # load primary asce - lg %r14,__LC_THREAD_INFO # pointer thread_info struct - lg %r14,__SF_EMPTY+8(%r15) # load guest register save area - stmg %r0,%r13,0(%r14) # save guest gprs 0-13 - lmg %r6,%r14,__SF_GPRS(%r15) # restore kernel registers - lghi %r2,-EFAULT - br %r14 + lghi %r14,-EFAULT + stg %r14,__SF_EMPTY+24(%r15) # set exit reason code + j sie_exit .align 8 -.Lsie_loop: - .quad sie_loop -.Lsie_length: - .quad sie_done - sie_loop -.Lhost_id: - .quad 0 +.Lsie_critical: + .quad sie_gmap +.Lsie_critical_length: + .quad sie_done - sie_gmap EX_TABLE(rewind_pad,sie_fault) - EX_TABLE(sie_loop,sie_fault) + EX_TABLE(sie_exit,sie_fault) #endif .section .rodata, "a" diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index dd3c1994b8bd..54b0995514e8 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -234,9 +234,9 @@ int unregister_external_interrupt(u16 code, ext_int_handler_t handler) } EXPORT_SYMBOL(unregister_external_interrupt); -void __irq_entry do_extint(struct pt_regs *regs, struct ext_code ext_code, - unsigned int param32, unsigned long param64) +void __irq_entry do_extint(struct pt_regs *regs) { + struct ext_code ext_code; struct pt_regs *old_regs; struct ext_int_info *p; int index; @@ -248,6 +248,7 @@ void __irq_entry do_extint(struct pt_regs *regs, struct ext_code ext_code, clock_comparator_work(); } kstat_incr_irqs_this_cpu(EXTERNAL_INTERRUPT, NULL); + ext_code = *(struct ext_code *) ®s->int_code; if (ext_code.code != 0x1004) __get_cpu_var(s390_idle).nohz_delay = 1; @@ -255,7 +256,8 @@ void __irq_entry do_extint(struct pt_regs *regs, struct ext_code ext_code, rcu_read_lock(); list_for_each_entry_rcu(p, &ext_int_hash[index], entry) if (likely(p->code == ext_code.code)) - p->handler(ext_code, param32, param64); + p->handler(ext_code, regs->int_parm, + regs->int_parm_long); rcu_read_unlock(); irq_exit(); set_irq_regs(old_regs); diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c index f58f37f66824..a6fc037671b1 100644 --- a/arch/s390/kernel/perf_event.c +++ b/arch/s390/kernel/perf_event.c @@ -13,6 +13,7 @@ #include <linux/kernel.h> #include <linux/perf_event.h> +#include <linux/kvm_host.h> #include <linux/percpu.h> #include <linux/export.h> #include <asm/irq.h> @@ -39,6 +40,57 @@ int perf_num_counters(void) } EXPORT_SYMBOL(perf_num_counters); +static struct kvm_s390_sie_block *sie_block(struct pt_regs *regs) +{ + struct stack_frame *stack = (struct stack_frame *) regs->gprs[15]; + + if (!stack) + return NULL; + + return (struct kvm_s390_sie_block *) stack->empty1[0]; +} + +static bool is_in_guest(struct pt_regs *regs) +{ + unsigned long ip = instruction_pointer(regs); + + if (user_mode(regs)) + return false; + + return ip == (unsigned long) &sie_exit; +} + +static unsigned long guest_is_user_mode(struct pt_regs *regs) +{ + return sie_block(regs)->gpsw.mask & PSW_MASK_PSTATE; +} + +static unsigned long instruction_pointer_guest(struct pt_regs *regs) +{ + return sie_block(regs)->gpsw.addr & PSW_ADDR_INSN; +} + +unsigned long perf_instruction_pointer(struct pt_regs *regs) +{ + return is_in_guest(regs) ? instruction_pointer_guest(regs) + : instruction_pointer(regs); +} + +static unsigned long perf_misc_guest_flags(struct pt_regs *regs) +{ + return guest_is_user_mode(regs) ? PERF_RECORD_MISC_GUEST_USER + : PERF_RECORD_MISC_GUEST_KERNEL; +} + +unsigned long perf_misc_flags(struct pt_regs *regs) +{ + if (is_in_guest(regs)) + return perf_misc_guest_flags(regs); + + return user_mode(regs) ? PERF_RECORD_MISC_USER + : PERF_RECORD_MISC_KERNEL; +} + void perf_event_print_debug(void) { struct cpumf_ctr_info cf_info; diff --git a/arch/s390/kernel/s390_ksyms.c b/arch/s390/kernel/s390_ksyms.c index 9bdbcef1da9e..3bac589844a7 100644 --- a/arch/s390/kernel/s390_ksyms.c +++ b/arch/s390/kernel/s390_ksyms.c @@ -7,6 +7,7 @@ EXPORT_SYMBOL(_mcount); #endif #if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE) EXPORT_SYMBOL(sie64a); +EXPORT_SYMBOL(sie_exit); #endif EXPORT_SYMBOL(memcpy); EXPORT_SYMBOL(memset); diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 4f977d0d25c2..15a016c10563 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -49,7 +49,6 @@ enum { ec_schedule = 0, - ec_call_function, ec_call_function_single, ec_stop_cpu, }; @@ -438,8 +437,6 @@ static void smp_handle_ext_call(void) smp_stop_cpu(); if (test_bit(ec_schedule, &bits)) scheduler_ipi(); - if (test_bit(ec_call_function, &bits)) - generic_smp_call_function_interrupt(); if (test_bit(ec_call_function_single, &bits)) generic_smp_call_function_single_interrupt(); } @@ -456,7 +453,7 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask) int cpu; for_each_cpu(cpu, mask) - pcpu_ec_call(pcpu_devices + cpu, ec_call_function); + pcpu_ec_call(pcpu_devices + cpu, ec_call_function_single); } void arch_send_call_function_single_ipi(int cpu) diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile index 8fe9d65a4585..40b4c6470f88 100644 --- a/arch/s390/kvm/Makefile +++ b/arch/s390/kvm/Makefile @@ -6,7 +6,8 @@ # it under the terms of the GNU General Public License (version 2 only) # as published by the Free Software Foundation. -common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o eventfd.o) +KVM := ../../../virt/kvm +common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o ccflags-y := -Ivirt/kvm -Iarch/s390/kvm diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 1c01a9912989..3074475c8ae0 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -132,6 +132,9 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu) { int code = (vcpu->arch.sie_block->ipb & 0xfff0000) >> 16; + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + trace_kvm_s390_handle_diag(vcpu, code); switch (code) { case 0x10: diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index b7d1b2edeeb3..5ee56e5acc23 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -22,87 +22,6 @@ #include "trace.h" #include "trace-s390.h" -static int handle_lctlg(struct kvm_vcpu *vcpu) -{ - int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; - int reg3 = vcpu->arch.sie_block->ipa & 0x000f; - u64 useraddr; - int reg, rc; - - vcpu->stat.instruction_lctlg++; - - useraddr = kvm_s390_get_base_disp_rsy(vcpu); - - if (useraddr & 7) - return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - - reg = reg1; - - VCPU_EVENT(vcpu, 5, "lctlg r1:%x, r3:%x, addr:%llx", reg1, reg3, - useraddr); - trace_kvm_s390_handle_lctl(vcpu, 1, reg1, reg3, useraddr); - - do { - rc = get_guest(vcpu, vcpu->arch.sie_block->gcr[reg], - (u64 __user *) useraddr); - if (rc) - return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - useraddr += 8; - if (reg == reg3) - break; - reg = (reg + 1) % 16; - } while (1); - return 0; -} - -static int handle_lctl(struct kvm_vcpu *vcpu) -{ - int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; - int reg3 = vcpu->arch.sie_block->ipa & 0x000f; - u64 useraddr; - u32 val = 0; - int reg, rc; - - vcpu->stat.instruction_lctl++; - - useraddr = kvm_s390_get_base_disp_rs(vcpu); - - if (useraddr & 3) - return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - - VCPU_EVENT(vcpu, 5, "lctl r1:%x, r3:%x, addr:%llx", reg1, reg3, - useraddr); - trace_kvm_s390_handle_lctl(vcpu, 0, reg1, reg3, useraddr); - - reg = reg1; - do { - rc = get_guest(vcpu, val, (u32 __user *) useraddr); - if (rc) - return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - vcpu->arch.sie_block->gcr[reg] &= 0xffffffff00000000ul; - vcpu->arch.sie_block->gcr[reg] |= val; - useraddr += 4; - if (reg == reg3) - break; - reg = (reg + 1) % 16; - } while (1); - return 0; -} - -static const intercept_handler_t eb_handlers[256] = { - [0x2f] = handle_lctlg, - [0x8a] = kvm_s390_handle_priv_eb, -}; - -static int handle_eb(struct kvm_vcpu *vcpu) -{ - intercept_handler_t handler; - - handler = eb_handlers[vcpu->arch.sie_block->ipb & 0xff]; - if (handler) - return handler(vcpu); - return -EOPNOTSUPP; -} static const intercept_handler_t instruction_handlers[256] = { [0x01] = kvm_s390_handle_01, @@ -110,10 +29,10 @@ static const intercept_handler_t instruction_handlers[256] = { [0x83] = kvm_s390_handle_diag, [0xae] = kvm_s390_handle_sigp, [0xb2] = kvm_s390_handle_b2, - [0xb7] = handle_lctl, + [0xb7] = kvm_s390_handle_lctl, [0xb9] = kvm_s390_handle_b9, [0xe5] = kvm_s390_handle_e5, - [0xeb] = handle_eb, + [0xeb] = kvm_s390_handle_eb, }; static int handle_noop(struct kvm_vcpu *vcpu) @@ -174,47 +93,12 @@ static int handle_stop(struct kvm_vcpu *vcpu) static int handle_validity(struct kvm_vcpu *vcpu) { - unsigned long vmaddr; int viwhy = vcpu->arch.sie_block->ipb >> 16; - int rc; vcpu->stat.exit_validity++; trace_kvm_s390_intercept_validity(vcpu, viwhy); - if (viwhy == 0x37) { - vmaddr = gmap_fault(vcpu->arch.sie_block->prefix, - vcpu->arch.gmap); - if (IS_ERR_VALUE(vmaddr)) { - rc = -EOPNOTSUPP; - goto out; - } - rc = fault_in_pages_writeable((char __user *) vmaddr, - PAGE_SIZE); - if (rc) { - /* user will receive sigsegv, exit to user */ - rc = -EOPNOTSUPP; - goto out; - } - vmaddr = gmap_fault(vcpu->arch.sie_block->prefix + PAGE_SIZE, - vcpu->arch.gmap); - if (IS_ERR_VALUE(vmaddr)) { - rc = -EOPNOTSUPP; - goto out; - } - rc = fault_in_pages_writeable((char __user *) vmaddr, - PAGE_SIZE); - if (rc) { - /* user will receive sigsegv, exit to user */ - rc = -EOPNOTSUPP; - goto out; - } - } else - rc = -EOPNOTSUPP; - -out: - if (rc) - VCPU_EVENT(vcpu, 2, "unhandled validity intercept code %d", - viwhy); - return rc; + WARN_ONCE(true, "kvm: unhandled validity intercept 0x%x\n", viwhy); + return -EOPNOTSUPP; } static int handle_instruction(struct kvm_vcpu *vcpu) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 5c948177529e..7f35cb33e510 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -438,7 +438,7 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) no_timer: spin_lock(&vcpu->arch.local_int.float_int->lock); spin_lock_bh(&vcpu->arch.local_int.lock); - add_wait_queue(&vcpu->arch.local_int.wq, &wait); + add_wait_queue(&vcpu->wq, &wait); while (list_empty(&vcpu->arch.local_int.list) && list_empty(&vcpu->arch.local_int.float_int->list) && (!vcpu->arch.local_int.timer_due) && @@ -452,7 +452,7 @@ no_timer: } __unset_cpu_idle(vcpu); __set_current_state(TASK_RUNNING); - remove_wait_queue(&vcpu->arch.local_int.wq, &wait); + remove_wait_queue(&vcpu->wq, &wait); spin_unlock_bh(&vcpu->arch.local_int.lock); spin_unlock(&vcpu->arch.local_int.float_int->lock); hrtimer_try_to_cancel(&vcpu->arch.ckc_timer); @@ -465,8 +465,8 @@ void kvm_s390_tasklet(unsigned long parm) spin_lock(&vcpu->arch.local_int.lock); vcpu->arch.local_int.timer_due = 1; - if (waitqueue_active(&vcpu->arch.local_int.wq)) - wake_up_interruptible(&vcpu->arch.local_int.wq); + if (waitqueue_active(&vcpu->wq)) + wake_up_interruptible(&vcpu->wq); spin_unlock(&vcpu->arch.local_int.lock); } @@ -613,7 +613,7 @@ int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code) spin_lock_bh(&li->lock); list_add(&inti->list, &li->list); atomic_set(&li->active, 1); - BUG_ON(waitqueue_active(&li->wq)); + BUG_ON(waitqueue_active(li->wq)); spin_unlock_bh(&li->lock); return 0; } @@ -746,8 +746,8 @@ int kvm_s390_inject_vm(struct kvm *kvm, li = fi->local_int[sigcpu]; spin_lock_bh(&li->lock); atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); - if (waitqueue_active(&li->wq)) - wake_up_interruptible(&li->wq); + if (waitqueue_active(li->wq)) + wake_up_interruptible(li->wq); spin_unlock_bh(&li->lock); spin_unlock(&fi->lock); mutex_unlock(&kvm->lock); @@ -832,8 +832,8 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, if (inti->type == KVM_S390_SIGP_STOP) li->action_bits |= ACTION_STOP_ON_STOP; atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); - if (waitqueue_active(&li->wq)) - wake_up_interruptible(&vcpu->arch.local_int.wq); + if (waitqueue_active(&vcpu->wq)) + wake_up_interruptible(&vcpu->wq); spin_unlock_bh(&li->lock); mutex_unlock(&vcpu->kvm->lock); return 0; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index c1c7c683fa26..ba694d2ba51e 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -59,6 +59,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "deliver_restart_signal", VCPU_STAT(deliver_restart_signal) }, { "deliver_program_interruption", VCPU_STAT(deliver_program_int) }, { "exit_wait_state", VCPU_STAT(exit_wait_state) }, + { "instruction_pfmf", VCPU_STAT(instruction_pfmf) }, { "instruction_stidp", VCPU_STAT(instruction_stidp) }, { "instruction_spx", VCPU_STAT(instruction_spx) }, { "instruction_stpx", VCPU_STAT(instruction_stpx) }, @@ -84,6 +85,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { }; static unsigned long long *facilities; +static struct gmap_notifier gmap_notifier; /* Section: not file related */ int kvm_arch_hardware_enable(void *garbage) @@ -96,13 +98,18 @@ void kvm_arch_hardware_disable(void *garbage) { } +static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address); + int kvm_arch_hardware_setup(void) { + gmap_notifier.notifier_call = kvm_gmap_notifier; + gmap_register_ipte_notifier(&gmap_notifier); return 0; } void kvm_arch_hardware_unsetup(void) { + gmap_unregister_ipte_notifier(&gmap_notifier); } void kvm_arch_check_processor_compat(void *rtn) @@ -239,6 +246,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.gmap = gmap_alloc(current->mm); if (!kvm->arch.gmap) goto out_nogmap; + kvm->arch.gmap->private = kvm; } kvm->arch.css_support = 0; @@ -270,7 +278,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) free_page((unsigned long)(vcpu->arch.sie_block)); kvm_vcpu_uninit(vcpu); - kfree(vcpu); + kmem_cache_free(kvm_vcpu_cache, vcpu); } static void kvm_free_vcpus(struct kvm *kvm) @@ -309,6 +317,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) vcpu->arch.gmap = gmap_alloc(current->mm); if (!vcpu->arch.gmap) return -ENOMEM; + vcpu->arch.gmap->private = vcpu->kvm; return 0; } @@ -373,8 +382,10 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH | CPUSTAT_SM | - CPUSTAT_STOPPED); + CPUSTAT_STOPPED | + CPUSTAT_GED); vcpu->arch.sie_block->ecb = 6; + vcpu->arch.sie_block->ecb2 = 8; vcpu->arch.sie_block->eca = 0xC1002001U; vcpu->arch.sie_block->fac = (int) (long) facilities; hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS); @@ -397,7 +408,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, rc = -ENOMEM; - vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL); + vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); if (!vcpu) goto out; @@ -427,7 +438,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, vcpu->arch.local_int.float_int = &kvm->arch.float_int; spin_lock(&kvm->arch.float_int.lock); kvm->arch.float_int.local_int[id] = &vcpu->arch.local_int; - init_waitqueue_head(&vcpu->arch.local_int.wq); + vcpu->arch.local_int.wq = &vcpu->wq; vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags; spin_unlock(&kvm->arch.float_int.lock); @@ -442,7 +453,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, out_free_sie_block: free_page((unsigned long)(vcpu->arch.sie_block)); out_free_cpu: - kfree(vcpu); + kmem_cache_free(kvm_vcpu_cache, vcpu); out: return ERR_PTR(rc); } @@ -454,6 +465,50 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) return 0; } +void s390_vcpu_block(struct kvm_vcpu *vcpu) +{ + atomic_set_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20); +} + +void s390_vcpu_unblock(struct kvm_vcpu *vcpu) +{ + atomic_clear_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20); +} + +/* + * Kick a guest cpu out of SIE and wait until SIE is not running. + * If the CPU is not running (e.g. waiting as idle) the function will + * return immediately. */ +void exit_sie(struct kvm_vcpu *vcpu) +{ + atomic_set_mask(CPUSTAT_STOP_INT, &vcpu->arch.sie_block->cpuflags); + while (vcpu->arch.sie_block->prog0c & PROG_IN_SIE) + cpu_relax(); +} + +/* Kick a guest cpu out of SIE and prevent SIE-reentry */ +void exit_sie_sync(struct kvm_vcpu *vcpu) +{ + s390_vcpu_block(vcpu); + exit_sie(vcpu); +} + +static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address) +{ + int i; + struct kvm *kvm = gmap->private; + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(i, vcpu, kvm) { + /* match against both prefix pages */ + if (vcpu->arch.sie_block->prefix == (address & ~0x1000UL)) { + VCPU_EVENT(vcpu, 2, "gmap notifier for %lx", address); + kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu); + exit_sie_sync(vcpu); + } + } +} + int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) { /* kvm common code refers to this, but never calls it */ @@ -606,6 +661,27 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, return -EINVAL; /* not implemented yet */ } +static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu) +{ + /* + * We use MMU_RELOAD just to re-arm the ipte notifier for the + * guest prefix page. gmap_ipte_notify will wait on the ptl lock. + * This ensures that the ipte instruction for this request has + * already finished. We might race against a second unmapper that + * wants to set the blocking bit. Lets just retry the request loop. + */ + while (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) { + int rc; + rc = gmap_ipte_notify(vcpu->arch.gmap, + vcpu->arch.sie_block->prefix, + PAGE_SIZE * 2); + if (rc) + return rc; + s390_vcpu_unblock(vcpu); + } + return 0; +} + static int __vcpu_run(struct kvm_vcpu *vcpu) { int rc; @@ -621,6 +697,10 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) if (!kvm_is_ucontrol(vcpu->kvm)) kvm_s390_deliver_pending_interrupts(vcpu); + rc = kvm_s390_handle_requests(vcpu); + if (rc) + return rc; + vcpu->arch.sie_block->icptcode = 0; preempt_disable(); kvm_guest_enter(); @@ -630,7 +710,9 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) trace_kvm_s390_sie_enter(vcpu, atomic_read(&vcpu->arch.sie_block->cpuflags)); rc = sie64a(vcpu->arch.sie_block, vcpu->run->s.regs.gprs); - if (rc) { + if (rc > 0) + rc = 0; + if (rc < 0) { if (kvm_is_ucontrol(vcpu->kvm)) { rc = SIE_INTERCEPT_UCONTROL; } else { @@ -1046,7 +1128,7 @@ static int __init kvm_s390_init(void) return -ENOMEM; } memcpy(facilities, S390_lowcore.stfle_fac_list, 16); - facilities[0] &= 0xff00fff3f47c0000ULL; + facilities[0] &= 0xff82fff3f47c0000ULL; facilities[1] &= 0x001c000000000000ULL; return 0; } @@ -1059,3 +1141,12 @@ static void __exit kvm_s390_exit(void) module_init(kvm_s390_init); module_exit(kvm_s390_exit); + +/* + * Enable autoloading of the kvm module. + * Note that we add the module alias here instead of virt/kvm/kvm_main.c + * since x86 takes a different approach. + */ +#include <linux/miscdevice.h> +MODULE_ALIAS_MISCDEV(KVM_MINOR); +MODULE_ALIAS("devname:kvm"); diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index efc14f687265..028ca9fd2158 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -63,6 +63,7 @@ static inline void kvm_s390_set_prefix(struct kvm_vcpu *vcpu, u32 prefix) { vcpu->arch.sie_block->prefix = prefix & 0x7fffe000u; vcpu->arch.sie_block->ihcpu = 0xffff; + kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu); } static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu) @@ -85,6 +86,12 @@ static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu, *address2 = (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2; } +static inline void kvm_s390_get_regs_rre(struct kvm_vcpu *vcpu, int *r1, int *r2) +{ + *r1 = (vcpu->arch.sie_block->ipb & 0x00f00000) >> 20; + *r2 = (vcpu->arch.sie_block->ipb & 0x000f0000) >> 16; +} + static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu) { u32 base2 = vcpu->arch.sie_block->ipb >> 28; @@ -125,7 +132,8 @@ int kvm_s390_handle_e5(struct kvm_vcpu *vcpu); int kvm_s390_handle_01(struct kvm_vcpu *vcpu); int kvm_s390_handle_b9(struct kvm_vcpu *vcpu); int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu); -int kvm_s390_handle_priv_eb(struct kvm_vcpu *vcpu); +int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu); +int kvm_s390_handle_eb(struct kvm_vcpu *vcpu); /* implemented in sigp.c */ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu); @@ -133,6 +141,10 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu); /* implemented in kvm-s390.c */ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr); +void s390_vcpu_block(struct kvm_vcpu *vcpu); +void s390_vcpu_unblock(struct kvm_vcpu *vcpu); +void exit_sie(struct kvm_vcpu *vcpu); +void exit_sie_sync(struct kvm_vcpu *vcpu); /* implemented in diag.c */ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 6bbd7b5a0bbe..0da3e6eb6be6 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -1,7 +1,7 @@ /* * handling privileged instructions * - * Copyright IBM Corp. 2008 + * Copyright IBM Corp. 2008, 2013 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) @@ -20,6 +20,9 @@ #include <asm/debug.h> #include <asm/ebcdic.h> #include <asm/sysinfo.h> +#include <asm/pgtable.h> +#include <asm/pgalloc.h> +#include <asm/io.h> #include <asm/ptrace.h> #include <asm/compat.h> #include "gaccess.h" @@ -34,6 +37,9 @@ static int handle_set_prefix(struct kvm_vcpu *vcpu) vcpu->stat.instruction_spx++; + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + operand2 = kvm_s390_get_base_disp_s(vcpu); /* must be word boundary */ @@ -65,6 +71,9 @@ static int handle_store_prefix(struct kvm_vcpu *vcpu) vcpu->stat.instruction_stpx++; + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + operand2 = kvm_s390_get_base_disp_s(vcpu); /* must be word boundary */ @@ -89,6 +98,9 @@ static int handle_store_cpu_address(struct kvm_vcpu *vcpu) vcpu->stat.instruction_stap++; + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + useraddr = kvm_s390_get_base_disp_s(vcpu); if (useraddr & 1) @@ -105,7 +117,12 @@ static int handle_store_cpu_address(struct kvm_vcpu *vcpu) static int handle_skey(struct kvm_vcpu *vcpu) { vcpu->stat.instruction_storage_key++; - vcpu->arch.sie_block->gpsw.addr -= 4; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + vcpu->arch.sie_block->gpsw.addr = + __rewind_psw(vcpu->arch.sie_block->gpsw, 4); VCPU_EVENT(vcpu, 4, "%s", "retrying storage key operation"); return 0; } @@ -129,9 +146,10 @@ static int handle_tpi(struct kvm_vcpu *vcpu) * Store the two-word I/O interruption code into the * provided area. */ - put_guest(vcpu, inti->io.subchannel_id, (u16 __user *) addr); - put_guest(vcpu, inti->io.subchannel_nr, (u16 __user *) (addr + 2)); - put_guest(vcpu, inti->io.io_int_parm, (u32 __user *) (addr + 4)); + if (put_guest(vcpu, inti->io.subchannel_id, (u16 __user *)addr) + || put_guest(vcpu, inti->io.subchannel_nr, (u16 __user *)(addr + 2)) + || put_guest(vcpu, inti->io.io_int_parm, (u32 __user *)(addr + 4))) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); } else { /* * Store the three-word I/O interruption code into @@ -182,6 +200,9 @@ static int handle_io_inst(struct kvm_vcpu *vcpu) { VCPU_EVENT(vcpu, 4, "%s", "I/O instruction"); + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + if (vcpu->kvm->arch.css_support) { /* * Most I/O instructions will be handled by userspace. @@ -210,8 +231,12 @@ static int handle_stfl(struct kvm_vcpu *vcpu) int rc; vcpu->stat.instruction_stfl++; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + /* only pass the facility bits, which we can handle */ - facility_list = S390_lowcore.stfl_fac_list & 0xff00fff3; + facility_list = S390_lowcore.stfl_fac_list & 0xff82fff3; rc = copy_to_guest(vcpu, offsetof(struct _lowcore, stfl_fac_list), &facility_list, sizeof(facility_list)); @@ -255,8 +280,8 @@ int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu) u64 addr; if (gpsw->mask & PSW_MASK_PSTATE) - return kvm_s390_inject_program_int(vcpu, - PGM_PRIVILEGED_OPERATION); + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + addr = kvm_s390_get_base_disp_s(vcpu); if (addr & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); @@ -278,6 +303,9 @@ static int handle_lpswe(struct kvm_vcpu *vcpu) psw_t new_psw; u64 addr; + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + addr = kvm_s390_get_base_disp_s(vcpu); if (addr & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); @@ -296,6 +324,9 @@ static int handle_stidp(struct kvm_vcpu *vcpu) vcpu->stat.instruction_stidp++; + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + operand2 = kvm_s390_get_base_disp_s(vcpu); if (operand2 & 7) @@ -351,16 +382,30 @@ static int handle_stsi(struct kvm_vcpu *vcpu) vcpu->stat.instruction_stsi++; VCPU_EVENT(vcpu, 4, "stsi: fc: %x sel1: %x sel2: %x", fc, sel1, sel2); - operand2 = kvm_s390_get_base_disp_s(vcpu); + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + if (fc > 3) { + vcpu->arch.sie_block->gpsw.mask |= 3ul << 44; /* cc 3 */ + return 0; + } - if (operand2 & 0xfff && fc > 0) + if (vcpu->run->s.regs.gprs[0] & 0x0fffff00 + || vcpu->run->s.regs.gprs[1] & 0xffff0000) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - switch (fc) { - case 0: + if (fc == 0) { vcpu->run->s.regs.gprs[0] = 3 << 28; - vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); + vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); /* cc 0 */ return 0; + } + + operand2 = kvm_s390_get_base_disp_s(vcpu); + + if (operand2 & 0xfff) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + switch (fc) { case 1: /* same handling for 1 and 2 */ case 2: mem = get_zeroed_page(GFP_KERNEL); @@ -377,8 +422,6 @@ static int handle_stsi(struct kvm_vcpu *vcpu) goto out_no_data; handle_stsi_3_2_2(vcpu, (void *) mem); break; - default: - goto out_no_data; } if (copy_to_guest_absolute(vcpu, operand2, (void *) mem, PAGE_SIZE)) { @@ -432,20 +475,14 @@ int kvm_s390_handle_b2(struct kvm_vcpu *vcpu) intercept_handler_t handler; /* - * a lot of B2 instructions are priviledged. We first check for - * the privileged ones, that we can handle in the kernel. If the - * kernel can handle this instruction, we check for the problem - * state bit and (a) handle the instruction or (b) send a code 2 - * program check. - * Anything else goes to userspace.*/ + * A lot of B2 instructions are priviledged. Here we check for + * the privileged ones, that we can handle in the kernel. + * Anything else goes to userspace. + */ handler = b2_handlers[vcpu->arch.sie_block->ipa & 0x00ff]; - if (handler) { - if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) - return kvm_s390_inject_program_int(vcpu, - PGM_PRIVILEGED_OPERATION); - else - return handler(vcpu); - } + if (handler) + return handler(vcpu); + return -EOPNOTSUPP; } @@ -453,8 +490,7 @@ static int handle_epsw(struct kvm_vcpu *vcpu) { int reg1, reg2; - reg1 = (vcpu->arch.sie_block->ipb & 0x00f00000) >> 24; - reg2 = (vcpu->arch.sie_block->ipb & 0x000f0000) >> 16; + kvm_s390_get_regs_rre(vcpu, ®1, ®2); /* This basically extracts the mask half of the psw. */ vcpu->run->s.regs.gprs[reg1] &= 0xffffffff00000000; @@ -467,9 +503,88 @@ static int handle_epsw(struct kvm_vcpu *vcpu) return 0; } +#define PFMF_RESERVED 0xfffc0101UL +#define PFMF_SK 0x00020000UL +#define PFMF_CF 0x00010000UL +#define PFMF_UI 0x00008000UL +#define PFMF_FSC 0x00007000UL +#define PFMF_NQ 0x00000800UL +#define PFMF_MR 0x00000400UL +#define PFMF_MC 0x00000200UL +#define PFMF_KEY 0x000000feUL + +static int handle_pfmf(struct kvm_vcpu *vcpu) +{ + int reg1, reg2; + unsigned long start, end; + + vcpu->stat.instruction_pfmf++; + + kvm_s390_get_regs_rre(vcpu, ®1, ®2); + + if (!MACHINE_HAS_PFMF) + return kvm_s390_inject_program_int(vcpu, PGM_OPERATION); + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + if (vcpu->run->s.regs.gprs[reg1] & PFMF_RESERVED) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + /* Only provide non-quiescing support if the host supports it */ + if (vcpu->run->s.regs.gprs[reg1] & PFMF_NQ && + S390_lowcore.stfl_fac_list & 0x00020000) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + /* No support for conditional-SSKE */ + if (vcpu->run->s.regs.gprs[reg1] & (PFMF_MR | PFMF_MC)) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + start = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK; + switch (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) { + case 0x00000000: + end = (start + (1UL << 12)) & ~((1UL << 12) - 1); + break; + case 0x00001000: + end = (start + (1UL << 20)) & ~((1UL << 20) - 1); + break; + /* We dont support EDAT2 + case 0x00002000: + end = (start + (1UL << 31)) & ~((1UL << 31) - 1); + break;*/ + default: + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + } + while (start < end) { + unsigned long useraddr; + + useraddr = gmap_translate(start, vcpu->arch.gmap); + if (IS_ERR((void *)useraddr)) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + + if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) { + if (clear_user((void __user *)useraddr, PAGE_SIZE)) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + } + + if (vcpu->run->s.regs.gprs[reg1] & PFMF_SK) { + if (set_guest_storage_key(current->mm, useraddr, + vcpu->run->s.regs.gprs[reg1] & PFMF_KEY, + vcpu->run->s.regs.gprs[reg1] & PFMF_NQ)) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + } + + start += PAGE_SIZE; + } + if (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) + vcpu->run->s.regs.gprs[reg2] = end; + return 0; +} + static const intercept_handler_t b9_handlers[256] = { [0x8d] = handle_epsw, [0x9c] = handle_io_inst, + [0xaf] = handle_pfmf, }; int kvm_s390_handle_b9(struct kvm_vcpu *vcpu) @@ -478,29 +593,96 @@ int kvm_s390_handle_b9(struct kvm_vcpu *vcpu) /* This is handled just as for the B2 instructions. */ handler = b9_handlers[vcpu->arch.sie_block->ipa & 0x00ff]; - if (handler) { - if ((handler != handle_epsw) && - (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)) - return kvm_s390_inject_program_int(vcpu, - PGM_PRIVILEGED_OPERATION); - else - return handler(vcpu); - } + if (handler) + return handler(vcpu); + return -EOPNOTSUPP; } +int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu) +{ + int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; + int reg3 = vcpu->arch.sie_block->ipa & 0x000f; + u64 useraddr; + u32 val = 0; + int reg, rc; + + vcpu->stat.instruction_lctl++; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + useraddr = kvm_s390_get_base_disp_rs(vcpu); + + if (useraddr & 3) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + VCPU_EVENT(vcpu, 5, "lctl r1:%x, r3:%x, addr:%llx", reg1, reg3, + useraddr); + trace_kvm_s390_handle_lctl(vcpu, 0, reg1, reg3, useraddr); + + reg = reg1; + do { + rc = get_guest(vcpu, val, (u32 __user *) useraddr); + if (rc) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + vcpu->arch.sie_block->gcr[reg] &= 0xffffffff00000000ul; + vcpu->arch.sie_block->gcr[reg] |= val; + useraddr += 4; + if (reg == reg3) + break; + reg = (reg + 1) % 16; + } while (1); + + return 0; +} + +static int handle_lctlg(struct kvm_vcpu *vcpu) +{ + int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; + int reg3 = vcpu->arch.sie_block->ipa & 0x000f; + u64 useraddr; + int reg, rc; + + vcpu->stat.instruction_lctlg++; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + useraddr = kvm_s390_get_base_disp_rsy(vcpu); + + if (useraddr & 7) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + reg = reg1; + + VCPU_EVENT(vcpu, 5, "lctlg r1:%x, r3:%x, addr:%llx", reg1, reg3, + useraddr); + trace_kvm_s390_handle_lctl(vcpu, 1, reg1, reg3, useraddr); + + do { + rc = get_guest(vcpu, vcpu->arch.sie_block->gcr[reg], + (u64 __user *) useraddr); + if (rc) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + useraddr += 8; + if (reg == reg3) + break; + reg = (reg + 1) % 16; + } while (1); + + return 0; +} + static const intercept_handler_t eb_handlers[256] = { + [0x2f] = handle_lctlg, [0x8a] = handle_io_inst, }; -int kvm_s390_handle_priv_eb(struct kvm_vcpu *vcpu) +int kvm_s390_handle_eb(struct kvm_vcpu *vcpu) { intercept_handler_t handler; - /* All eb instructions that end up here are privileged. */ - if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) - return kvm_s390_inject_program_int(vcpu, - PGM_PRIVILEGED_OPERATION); handler = eb_handlers[vcpu->arch.sie_block->ipb & 0xff]; if (handler) return handler(vcpu); @@ -515,6 +697,9 @@ static int handle_tprot(struct kvm_vcpu *vcpu) vcpu->stat.instruction_tprot++; + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + kvm_s390_get_base_disp_sse(vcpu, &address1, &address2); /* we only handle the Linux memory detection case: @@ -560,8 +745,7 @@ static int handle_sckpf(struct kvm_vcpu *vcpu) u32 value; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) - return kvm_s390_inject_program_int(vcpu, - PGM_PRIVILEGED_OPERATION); + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); if (vcpu->run->s.regs.gprs[0] & 0x00000000ffff0000) return kvm_s390_inject_program_int(vcpu, diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index 1c48ab2845e0..bec398c57acf 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -79,8 +79,8 @@ static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr) list_add_tail(&inti->list, &li->list); atomic_set(&li->active, 1); atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); - if (waitqueue_active(&li->wq)) - wake_up_interruptible(&li->wq); + if (waitqueue_active(li->wq)) + wake_up_interruptible(li->wq); spin_unlock_bh(&li->lock); rc = SIGP_CC_ORDER_CODE_ACCEPTED; VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x", cpu_addr); @@ -117,8 +117,8 @@ static int __sigp_external_call(struct kvm_vcpu *vcpu, u16 cpu_addr) list_add_tail(&inti->list, &li->list); atomic_set(&li->active, 1); atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); - if (waitqueue_active(&li->wq)) - wake_up_interruptible(&li->wq); + if (waitqueue_active(li->wq)) + wake_up_interruptible(li->wq); spin_unlock_bh(&li->lock); rc = SIGP_CC_ORDER_CODE_ACCEPTED; VCPU_EVENT(vcpu, 4, "sent sigp ext call to cpu %x", cpu_addr); @@ -145,8 +145,8 @@ static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action) atomic_set(&li->active, 1); atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags); li->action_bits |= action; - if (waitqueue_active(&li->wq)) - wake_up_interruptible(&li->wq); + if (waitqueue_active(li->wq)) + wake_up_interruptible(li->wq); out: spin_unlock_bh(&li->lock); @@ -250,8 +250,8 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address, list_add_tail(&inti->list, &li->list); atomic_set(&li->active, 1); - if (waitqueue_active(&li->wq)) - wake_up_interruptible(&li->wq); + if (waitqueue_active(li->wq)) + wake_up_interruptible(li->wq); rc = SIGP_CC_ORDER_CODE_ACCEPTED; VCPU_EVENT(vcpu, 4, "set prefix of cpu %02x to %x", cpu_addr, address); @@ -333,8 +333,7 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu) /* sigp in userspace can exit */ if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) - return kvm_s390_inject_program_int(vcpu, - PGM_PRIVILEGED_OPERATION); + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); order_code = kvm_s390_get_base_disp_rs(vcpu); diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index a938b548f07e..17bf4d3d303a 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -689,7 +689,7 @@ int gmap_ipte_notify(struct gmap *gmap, unsigned long start, unsigned long len) entry = *ptep; if ((pte_val(entry) & (_PAGE_INVALID | _PAGE_RO)) == 0) { pgste = pgste_get_lock(ptep); - pgste_val(pgste) |= RCP_IN_BIT; + pgste_val(pgste) |= PGSTE_IN_BIT; pgste_set_unlock(ptep, pgste); start += PAGE_SIZE; len -= PAGE_SIZE; @@ -771,6 +771,54 @@ static inline void page_table_free_pgste(unsigned long *table) __free_page(page); } +int set_guest_storage_key(struct mm_struct *mm, unsigned long addr, + unsigned long key, bool nq) +{ + spinlock_t *ptl; + pgste_t old, new; + pte_t *ptep; + + down_read(&mm->mmap_sem); + ptep = get_locked_pte(current->mm, addr, &ptl); + if (unlikely(!ptep)) { + up_read(&mm->mmap_sem); + return -EFAULT; + } + + new = old = pgste_get_lock(ptep); + pgste_val(new) &= ~(PGSTE_GR_BIT | PGSTE_GC_BIT | + PGSTE_ACC_BITS | PGSTE_FP_BIT); + pgste_val(new) |= (key & (_PAGE_CHANGED | _PAGE_REFERENCED)) << 48; + pgste_val(new) |= (key & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56; + if (!(pte_val(*ptep) & _PAGE_INVALID)) { + unsigned long address, bits; + unsigned char skey; + + address = pte_val(*ptep) & PAGE_MASK; + skey = page_get_storage_key(address); + bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED); + /* Set storage key ACC and FP */ + page_set_storage_key(address, + (key & (_PAGE_ACC_BITS | _PAGE_FP_BIT)), + !nq); + + /* Merge host changed & referenced into pgste */ + pgste_val(new) |= bits << 52; + /* Transfer skey changed & referenced bit to kvm user bits */ + pgste_val(new) |= bits << 45; /* PGSTE_UR_BIT & PGSTE_UC_BIT */ + } + /* changing the guest storage key is considered a change of the page */ + if ((pgste_val(new) ^ pgste_val(old)) & + (PGSTE_ACC_BITS | PGSTE_FP_BIT | PGSTE_GR_BIT | PGSTE_GC_BIT)) + pgste_val(new) |= PGSTE_UC_BIT; + + pgste_set_unlock(ptep, new); + pte_unmap_unlock(*ptep, ptl); + up_read(&mm->mmap_sem); + return 0; +} +EXPORT_SYMBOL(set_guest_storage_key); + #else /* CONFIG_PGSTE */ static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm, diff --git a/arch/s390/oprofile/hwsampler.h b/arch/s390/oprofile/hwsampler.h index 1912f3bb190c..0022e1ebfbde 100644 --- a/arch/s390/oprofile/hwsampler.h +++ b/arch/s390/oprofile/hwsampler.h @@ -81,8 +81,8 @@ struct hws_data_entry { unsigned int:16; unsigned int prim_asn:16; /* primary ASN */ unsigned long long ia; /* Instruction Address */ - unsigned long long lpp; /* Logical-Partition Program Param. */ - unsigned long long vpp; /* Virtual-Machine Program Param. */ + unsigned long long gpp; /* Guest Program Parameter */ + unsigned long long hpp; /* Host Program Parameter */ }; struct hws_trailer_entry { diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index f1e5be85d592..e2956ad39a4f 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -82,10 +82,13 @@ struct intr_bucket { static struct intr_bucket *bucket; -/* Adapter local summary indicator */ -static u8 *zpci_irq_si; +/* Adapter interrupt definitions */ +static void zpci_irq_handler(struct airq_struct *airq); -static atomic_t irq_retries = ATOMIC_INIT(0); +static struct airq_struct zpci_airq = { + .handler = zpci_irq_handler, + .isc = PCI_ISC, +}; /* I/O Map */ static DEFINE_SPINLOCK(zpci_iomap_lock); @@ -404,7 +407,7 @@ static struct pci_ops pci_root_ops = { /* store the last handled bit to implement fair scheduling of devices */ static DEFINE_PER_CPU(unsigned long, next_sbit); -static void zpci_irq_handler(void *dont, void *need) +static void zpci_irq_handler(struct airq_struct *airq) { unsigned long sbit, mbit, last = 0, start = __get_cpu_var(next_sbit); int rescan = 0, max = aisb_max; @@ -452,7 +455,6 @@ scan: max = aisb_max; sbit = find_first_bit_left(bucket->aisb, max); if (sbit != max) { - atomic_inc(&irq_retries); rescan++; goto scan; } @@ -565,7 +567,21 @@ static void zpci_map_resources(struct zpci_dev *zdev) pr_debug("BAR%i: -> start: %Lx end: %Lx\n", i, pdev->resource[i].start, pdev->resource[i].end); } -}; +} + +static void zpci_unmap_resources(struct zpci_dev *zdev) +{ + struct pci_dev *pdev = zdev->pdev; + resource_size_t len; + int i; + + for (i = 0; i < PCI_BAR_COUNT; i++) { + len = pci_resource_len(pdev, i); + if (!len) + continue; + pci_iounmap(pdev, (void *) pdev->resource[i].start); + } +} struct zpci_dev *zpci_alloc_device(void) { @@ -701,25 +717,20 @@ static int __init zpci_irq_init(void) goto out_alloc; } - isc_register(PCI_ISC); - zpci_irq_si = s390_register_adapter_interrupt(&zpci_irq_handler, NULL, PCI_ISC); - if (IS_ERR(zpci_irq_si)) { - rc = PTR_ERR(zpci_irq_si); - zpci_irq_si = NULL; + rc = register_adapter_interrupt(&zpci_airq); + if (rc) goto out_ai; - } + /* Set summary to 1 to be called every time for the ISC. */ + *zpci_airq.lsi_ptr = 1; for_each_online_cpu(cpu) per_cpu(next_sbit, cpu) = 0; spin_lock_init(&bucket->lock); - /* set summary to 1 to be called every time for the ISC */ - *zpci_irq_si = 1; set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC); return 0; out_ai: - isc_unregister(PCI_ISC); free_page((unsigned long) bucket->alloc); out_alloc: free_page((unsigned long) bucket->aisb); @@ -732,21 +743,10 @@ static void zpci_irq_exit(void) { free_page((unsigned long) bucket->alloc); free_page((unsigned long) bucket->aisb); - s390_unregister_adapter_interrupt(zpci_irq_si, PCI_ISC); - isc_unregister(PCI_ISC); + unregister_adapter_interrupt(&zpci_airq); kfree(bucket); } -void zpci_debug_info(struct zpci_dev *zdev, struct seq_file *m) -{ - if (!zdev) - return; - - seq_printf(m, "global irq retries: %u\n", atomic_read(&irq_retries)); - seq_printf(m, "aibv[0]:%016lx aibv[1]:%016lx aisb:%016lx\n", - get_imap(0)->aibv, get_imap(1)->aibv, *bucket->aisb); -} - static struct resource *zpci_alloc_bus_resource(unsigned long start, unsigned long size, unsigned long flags, int domain) { @@ -810,6 +810,16 @@ int pcibios_add_device(struct pci_dev *pdev) return 0; } +void pcibios_release_device(struct pci_dev *pdev) +{ + struct zpci_dev *zdev = get_zdev(pdev); + + zpci_unmap_resources(zdev); + zpci_fmb_disable_device(zdev); + zpci_debug_exit_device(zdev); + zdev->pdev = NULL; +} + static int zpci_scan_bus(struct zpci_dev *zdev) { struct resource *res; @@ -950,25 +960,6 @@ void zpci_stop_device(struct zpci_dev *zdev) } EXPORT_SYMBOL_GPL(zpci_stop_device); -int zpci_scan_device(struct zpci_dev *zdev) -{ - zdev->pdev = pci_scan_single_device(zdev->bus, ZPCI_DEVFN); - if (!zdev->pdev) { - pr_err("pci_scan_single_device failed for fid: 0x%x\n", - zdev->fid); - goto out; - } - - pci_bus_add_devices(zdev->bus); - - return 0; -out: - zpci_dma_exit_device(zdev); - clp_disable_fh(zdev); - return -EIO; -} -EXPORT_SYMBOL_GPL(zpci_scan_device); - static inline int barsize(u8 size) { return (size) ? (1 << size) >> 10 : 0; diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index bd34359d1546..2e9539625d93 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -236,7 +236,6 @@ int clp_disable_fh(struct zpci_dev *zdev) if (!zdev_enabled(zdev)) return 0; - dev_info(&zdev->pdev->dev, "disabling fn handle: 0x%x\n", fh); rc = clp_set_pci_fn(&fh, 0, CLP_SET_DISABLE_PCI_FN); if (!rc) /* Success -> store disabled handle in zdev */ diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c index 771b82359af4..75c69b402e05 100644 --- a/arch/s390/pci/pci_debug.c +++ b/arch/s390/pci/pci_debug.c @@ -115,27 +115,6 @@ static const struct file_operations debugfs_pci_perf_fops = { .release = single_release, }; -static int pci_debug_show(struct seq_file *m, void *v) -{ - struct zpci_dev *zdev = m->private; - - zpci_debug_info(zdev, m); - return 0; -} - -static int pci_debug_seq_open(struct inode *inode, struct file *filp) -{ - return single_open(filp, pci_debug_show, - file_inode(filp)->i_private); -} - -static const struct file_operations debugfs_pci_debug_fops = { - .open = pci_debug_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - void zpci_debug_init_device(struct zpci_dev *zdev) { zdev->debugfs_dev = debugfs_create_dir(dev_name(&zdev->pdev->dev), @@ -149,19 +128,11 @@ void zpci_debug_init_device(struct zpci_dev *zdev) &debugfs_pci_perf_fops); if (IS_ERR(zdev->debugfs_perf)) zdev->debugfs_perf = NULL; - - zdev->debugfs_debug = debugfs_create_file("debug", - S_IFREG | S_IRUGO | S_IWUSR, - zdev->debugfs_dev, zdev, - &debugfs_pci_debug_fops); - if (IS_ERR(zdev->debugfs_debug)) - zdev->debugfs_debug = NULL; } void zpci_debug_exit_device(struct zpci_dev *zdev) { debugfs_remove(zdev->debugfs_perf); - debugfs_remove(zdev->debugfs_debug); debugfs_remove(zdev->debugfs_dev); } diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index f8e69d5bc0a9..a2343c1f6e04 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -263,7 +263,7 @@ static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page, enum dma_data_direction direction, struct dma_attrs *attrs) { - struct zpci_dev *zdev = get_zdev(container_of(dev, struct pci_dev, dev)); + struct zpci_dev *zdev = get_zdev(to_pci_dev(dev)); unsigned long nr_pages, iommu_page_index; unsigned long pa = page_to_phys(page) + offset; int flags = ZPCI_PTE_VALID; @@ -304,7 +304,7 @@ static void s390_dma_unmap_pages(struct device *dev, dma_addr_t dma_addr, size_t size, enum dma_data_direction direction, struct dma_attrs *attrs) { - struct zpci_dev *zdev = get_zdev(container_of(dev, struct pci_dev, dev)); + struct zpci_dev *zdev = get_zdev(to_pci_dev(dev)); unsigned long iommu_page_index; int npages; @@ -323,7 +323,7 @@ static void *s390_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, struct dma_attrs *attrs) { - struct zpci_dev *zdev = get_zdev(container_of(dev, struct pci_dev, dev)); + struct zpci_dev *zdev = get_zdev(to_pci_dev(dev)); struct page *page; unsigned long pa; dma_addr_t map; diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c index a42cce69d0a0..e99a2557f186 100644 --- a/arch/s390/pci/pci_sysfs.c +++ b/arch/s390/pci/pci_sysfs.c @@ -15,40 +15,36 @@ static ssize_t show_fid(struct device *dev, struct device_attribute *attr, char *buf) { - struct zpci_dev *zdev = get_zdev(container_of(dev, struct pci_dev, dev)); + struct zpci_dev *zdev = get_zdev(to_pci_dev(dev)); - sprintf(buf, "0x%08x\n", zdev->fid); - return strlen(buf); + return sprintf(buf, "0x%08x\n", zdev->fid); } static DEVICE_ATTR(function_id, S_IRUGO, show_fid, NULL); static ssize_t show_fh(struct device *dev, struct device_attribute *attr, char *buf) { - struct zpci_dev *zdev = get_zdev(container_of(dev, struct pci_dev, dev)); + struct zpci_dev *zdev = get_zdev(to_pci_dev(dev)); - sprintf(buf, "0x%08x\n", zdev->fh); - return strlen(buf); + return sprintf(buf, "0x%08x\n", zdev->fh); } static DEVICE_ATTR(function_handle, S_IRUGO, show_fh, NULL); static ssize_t show_pchid(struct device *dev, struct device_attribute *attr, char *buf) { - struct zpci_dev *zdev = get_zdev(container_of(dev, struct pci_dev, dev)); + struct zpci_dev *zdev = get_zdev(to_pci_dev(dev)); - sprintf(buf, "0x%04x\n", zdev->pchid); - return strlen(buf); + return sprintf(buf, "0x%04x\n", zdev->pchid); } static DEVICE_ATTR(pchid, S_IRUGO, show_pchid, NULL); static ssize_t show_pfgid(struct device *dev, struct device_attribute *attr, char *buf) { - struct zpci_dev *zdev = get_zdev(container_of(dev, struct pci_dev, dev)); + struct zpci_dev *zdev = get_zdev(to_pci_dev(dev)); - sprintf(buf, "0x%02x\n", zdev->pfgid); - return strlen(buf); + return sprintf(buf, "0x%02x\n", zdev->pfgid); } static DEVICE_ATTR(pfgid, S_IRUGO, show_pfgid, NULL); diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild index cebaff8069a1..e1c7bb999b06 100644 --- a/arch/score/include/asm/Kbuild +++ b/arch/score/include/asm/Kbuild @@ -3,3 +3,4 @@ header-y += generic-y += clkdev.h generic-y += trace_clock.h +generic-y += xor.h diff --git a/arch/score/include/asm/dma-mapping.h b/arch/score/include/asm/dma-mapping.h deleted file mode 100644 index f9c0193c7a53..000000000000 --- a/arch/score/include/asm/dma-mapping.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _ASM_SCORE_DMA_MAPPING_H -#define _ASM_SCORE_DMA_MAPPING_H - -#include <asm-generic/dma-mapping-broken.h> - -#endif /* _ASM_SCORE_DMA_MAPPING_H */ diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index 2031c65fd4ea..bc4d3f5d2e5d 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -254,7 +254,7 @@ static struct pci_dev *of_create_pci_dev(struct pci_pbm_info *pbm, const char *type; u32 class; - dev = alloc_pci_dev(); + dev = pci_alloc_dev(bus); if (!dev) return NULL; @@ -281,7 +281,6 @@ static struct pci_dev *of_create_pci_dev(struct pci_pbm_info *pbm, printk(" create device, devfn: %x, type: %s\n", devfn, type); - dev->bus = bus; dev->sysdata = node; dev->dev.parent = bus->bridge; dev->dev.bus = &pci_bus_type; @@ -327,7 +326,7 @@ static struct pci_dev *of_create_pci_dev(struct pci_pbm_info *pbm, if ((dev->class >> 8) == PCI_CLASS_STORAGE_IDE) pci_set_master(dev); - dev->current_state = 4; /* unknown power state */ + dev->current_state = PCI_UNKNOWN; /* unknown power state */ dev->error_state = pci_channel_io_normal; dev->dma_mask = 0xffffffff; diff --git a/arch/unicore32/boot/compressed/Makefile b/arch/unicore32/boot/compressed/Makefile index 950a9afa38f8..96494fb646f7 100644 --- a/arch/unicore32/boot/compressed/Makefile +++ b/arch/unicore32/boot/compressed/Makefile @@ -17,7 +17,7 @@ OBJS := misc.o # font.c and font.o CFLAGS_font.o := -Dstatic= -$(obj)/font.c: $(srctree)/drivers/video/console/font_8x8.c +$(obj)/font.c: $(srctree)/lib/fonts/font_8x8.c $(call cmd,shipped) # piggy.S and piggy.o diff --git a/arch/unicore32/kernel/pci.c b/arch/unicore32/kernel/pci.c index ef69c0c82825..374a055a8e6b 100644 --- a/arch/unicore32/kernel/pci.c +++ b/arch/unicore32/kernel/pci.c @@ -277,11 +277,6 @@ static int __init pci_common_init(void) pci_bus_assign_resources(puv3_bus); } - /* - * Tell drivers about devices found. - */ - pci_bus_add_devices(puv3_bus); - return 0; } subsys_initcall(pci_common_init); diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index b31bf97775fc..2dfac58f3b11 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -111,7 +111,7 @@ static inline void acpi_disable_pci(void) } /* Low-level suspend routine. */ -extern int acpi_suspend_lowlevel(void); +extern int (*acpi_suspend_lowlevel)(void); /* Physical address to resume after wakeup */ #define acpi_wakeup_address ((unsigned long)(real_mode_header->wakeup_start)) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index af9c5525434d..f87f7fcefa0a 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -222,14 +222,22 @@ struct kvm_mmu_page { int root_count; /* Currently serving as active root */ unsigned int unsync_children; unsigned long parent_ptes; /* Reverse mapping for parent_pte */ + + /* The page is obsolete if mmu_valid_gen != kvm->arch.mmu_valid_gen. */ + unsigned long mmu_valid_gen; + DECLARE_BITMAP(unsync_child_bitmap, 512); #ifdef CONFIG_X86_32 + /* + * Used out of the mmu-lock to avoid reading spte values while an + * update is in progress; see the comments in __get_spte_lockless(). + */ int clear_spte_count; #endif + /* Number of writes since the last time traversal visited this page. */ int write_flooding_count; - bool mmio_cached; }; struct kvm_pio_request { @@ -529,11 +537,14 @@ struct kvm_arch { unsigned int n_requested_mmu_pages; unsigned int n_max_mmu_pages; unsigned int indirect_shadow_pages; + unsigned long mmu_valid_gen; struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES]; /* * Hash table of struct kvm_mmu_page. */ struct list_head active_mmu_pages; + struct list_head zapped_obsolete_pages; + struct list_head assigned_dev_head; struct iommu_domain *iommu_domain; int iommu_flags; @@ -769,7 +780,7 @@ void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask); void kvm_mmu_zap_all(struct kvm *kvm); -void kvm_mmu_zap_mmio_sptes(struct kvm *kvm); +void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm); unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm); void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages); diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 230c8ea878e5..d81a972dd506 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -44,6 +44,7 @@ #include <asm/mpspec.h> #include <asm/smp.h> +#include "sleep.h" /* To include x86_acpi_suspend_lowlevel */ static int __initdata acpi_force = 0; u32 acpi_rsdt_forced; int acpi_disabled; @@ -559,6 +560,12 @@ static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi, int (*__acpi_register_gsi)(struct device *dev, u32 gsi, int trigger, int polarity) = acpi_register_gsi_pic; +#ifdef CONFIG_ACPI_SLEEP +int (*acpi_suspend_lowlevel)(void) = x86_acpi_suspend_lowlevel; +#else +int (*acpi_suspend_lowlevel)(void); +#endif + /* * success: return IRQ number (>=0) * failure: return < 0 diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index b44577bc9744..2a34aaf3c8f1 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -26,12 +26,12 @@ static char temp_stack[4096]; #endif /** - * acpi_suspend_lowlevel - save kernel state + * x86_acpi_suspend_lowlevel - save kernel state * * Create an identity mapped page table and copy the wakeup routine to * low memory. */ -int acpi_suspend_lowlevel(void) +int x86_acpi_suspend_lowlevel(void) { struct wakeup_header *header = (struct wakeup_header *) __va(real_mode_header->wakeup_header); diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h index 67f59f8c6956..c9c2c982d5e4 100644 --- a/arch/x86/kernel/acpi/sleep.h +++ b/arch/x86/kernel/acpi/sleep.h @@ -15,3 +15,5 @@ extern unsigned long acpi_copy_wakeup_routine(unsigned long); extern void wakeup_long64(void); extern void do_suspend_lowlevel(void); + +extern int x86_acpi_suspend_lowlevel(void); diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 2f3a7995e56a..98f2083832eb 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -182,11 +182,6 @@ static int therm_throt_process(bool new_event, int event, int level) this_cpu, level == CORE_LEVEL ? "Core" : "Package", state->count); - else - printk(KERN_CRIT "CPU%d: %s power limit notification (total events = %lu)\n", - this_cpu, - level == CORE_LEVEL ? "Core" : "Package", - state->count); return 1; } if (old_event) { @@ -194,10 +189,6 @@ static int therm_throt_process(bool new_event, int event, int level) printk(KERN_INFO "CPU%d: %s temperature/speed normal\n", this_cpu, level == CORE_LEVEL ? "Core" : "Package"); - else - printk(KERN_INFO "CPU%d: %s power limit normal\n", - this_cpu, - level == CORE_LEVEL ? "Core" : "Package"); return 1; } @@ -220,6 +211,15 @@ static int thresh_event_valid(int event) return 1; } +static bool int_pln_enable; +static int __init int_pln_enable_setup(char *s) +{ + int_pln_enable = true; + + return 1; +} +__setup("int_pln_enable", int_pln_enable_setup); + #ifdef CONFIG_SYSFS /* Add/Remove thermal_throttle interface for CPU device: */ static __cpuinit int thermal_throttle_add_dev(struct device *dev, @@ -232,7 +232,7 @@ static __cpuinit int thermal_throttle_add_dev(struct device *dev, if (err) return err; - if (cpu_has(c, X86_FEATURE_PLN)) + if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) err = sysfs_add_file_to_group(&dev->kobj, &dev_attr_core_power_limit_count.attr, thermal_attr_group.name); @@ -240,7 +240,7 @@ static __cpuinit int thermal_throttle_add_dev(struct device *dev, err = sysfs_add_file_to_group(&dev->kobj, &dev_attr_package_throttle_count.attr, thermal_attr_group.name); - if (cpu_has(c, X86_FEATURE_PLN)) + if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) err = sysfs_add_file_to_group(&dev->kobj, &dev_attr_package_power_limit_count.attr, thermal_attr_group.name); @@ -353,7 +353,7 @@ static void intel_thermal_interrupt(void) CORE_LEVEL) != 0) mce_log_therm_throt_event(msr_val); - if (this_cpu_has(X86_FEATURE_PLN)) + if (this_cpu_has(X86_FEATURE_PLN) && int_pln_enable) therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT, POWER_LIMIT_EVENT, CORE_LEVEL); @@ -363,7 +363,7 @@ static void intel_thermal_interrupt(void) therm_throt_process(msr_val & PACKAGE_THERM_STATUS_PROCHOT, THERMAL_THROTTLING_EVENT, PACKAGE_LEVEL); - if (this_cpu_has(X86_FEATURE_PLN)) + if (this_cpu_has(X86_FEATURE_PLN) && int_pln_enable) therm_throt_process(msr_val & PACKAGE_THERM_STATUS_POWER_LIMIT, POWER_LIMIT_EVENT, @@ -482,9 +482,13 @@ void intel_init_thermal(struct cpuinfo_x86 *c) apic_write(APIC_LVTTHMR, h); rdmsr(MSR_IA32_THERM_INTERRUPT, l, h); - if (cpu_has(c, X86_FEATURE_PLN)) + if (cpu_has(c, X86_FEATURE_PLN) && !int_pln_enable) wrmsr(MSR_IA32_THERM_INTERRUPT, - l | (THERM_INT_LOW_ENABLE + (l | (THERM_INT_LOW_ENABLE + | THERM_INT_HIGH_ENABLE)) & ~THERM_INT_PLN_ENABLE, h); + else if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) + wrmsr(MSR_IA32_THERM_INTERRUPT, + l | (THERM_INT_LOW_ENABLE | THERM_INT_HIGH_ENABLE | THERM_INT_PLN_ENABLE), h); else wrmsr(MSR_IA32_THERM_INTERRUPT, @@ -492,9 +496,14 @@ void intel_init_thermal(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_PTS)) { rdmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h); - if (cpu_has(c, X86_FEATURE_PLN)) + if (cpu_has(c, X86_FEATURE_PLN) && !int_pln_enable) wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, - l | (PACKAGE_THERM_INT_LOW_ENABLE + (l | (PACKAGE_THERM_INT_LOW_ENABLE + | PACKAGE_THERM_INT_HIGH_ENABLE)) + & ~PACKAGE_THERM_INT_PLN_ENABLE, h); + else if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) + wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, + l | (PACKAGE_THERM_INT_LOW_ENABLE | PACKAGE_THERM_INT_HIGH_ENABLE | PACKAGE_THERM_INT_PLN_ENABLE), h); else diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index d609e1d84048..bf4fb04d0112 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -5,12 +5,13 @@ CFLAGS_x86.o := -I. CFLAGS_svm.o := -I. CFLAGS_vmx.o := -I. -kvm-y += $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \ - coalesced_mmio.o irq_comm.o eventfd.o \ - irqchip.o) -kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += $(addprefix ../../../virt/kvm/, \ - assigned-dev.o iommu.o) -kvm-$(CONFIG_KVM_ASYNC_PF) += $(addprefix ../../../virt/kvm/, async_pf.o) +KVM := ../../../virt/kvm + +kvm-y += $(KVM)/kvm_main.o $(KVM)/ioapic.o \ + $(KVM)/coalesced_mmio.o $(KVM)/irq_comm.o \ + $(KVM)/eventfd.o $(KVM)/irqchip.o +kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += $(KVM)/assigned-dev.o $(KVM)/iommu.o +kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ i8254.o cpuid.o pmu.o diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 5953dcea752d..2bc1e81045b0 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -61,6 +61,8 @@ #define OpMem8 26ull /* 8-bit zero extended memory operand */ #define OpImm64 27ull /* Sign extended 16/32/64-bit immediate */ #define OpXLat 28ull /* memory at BX/EBX/RBX + zero-extended AL */ +#define OpAccLo 29ull /* Low part of extended acc (AX/AX/EAX/RAX) */ +#define OpAccHi 30ull /* High part of extended acc (-/DX/EDX/RDX) */ #define OpBits 5 /* Width of operand field */ #define OpMask ((1ull << OpBits) - 1) @@ -86,6 +88,7 @@ #define DstMem64 (OpMem64 << DstShift) #define DstImmUByte (OpImmUByte << DstShift) #define DstDX (OpDX << DstShift) +#define DstAccLo (OpAccLo << DstShift) #define DstMask (OpMask << DstShift) /* Source operand type. */ #define SrcShift 6 @@ -108,6 +111,7 @@ #define SrcImm64 (OpImm64 << SrcShift) #define SrcDX (OpDX << SrcShift) #define SrcMem8 (OpMem8 << SrcShift) +#define SrcAccHi (OpAccHi << SrcShift) #define SrcMask (OpMask << SrcShift) #define BitOp (1<<11) #define MemAbs (1<<12) /* Memory operand is absolute displacement */ @@ -138,6 +142,7 @@ /* Source 2 operand type */ #define Src2Shift (31) #define Src2None (OpNone << Src2Shift) +#define Src2Mem (OpMem << Src2Shift) #define Src2CL (OpCL << Src2Shift) #define Src2ImmByte (OpImmByte << Src2Shift) #define Src2One (OpOne << Src2Shift) @@ -155,6 +160,9 @@ #define Avx ((u64)1 << 43) /* Advanced Vector Extensions */ #define Fastop ((u64)1 << 44) /* Use opcode::u.fastop */ #define NoWrite ((u64)1 << 45) /* No writeback */ +#define SrcWrite ((u64)1 << 46) /* Write back src operand */ + +#define DstXacc (DstAccLo | SrcAccHi | SrcWrite) #define X2(x...) x, x #define X3(x...) X2(x), x @@ -171,10 +179,11 @@ /* * fastop functions have a special calling convention: * - * dst: [rdx]:rax (in/out) - * src: rbx (in/out) + * dst: rax (in/out) + * src: rdx (in/out) * src2: rcx (in) * flags: rflags (in/out) + * ex: rsi (in:fastop pointer, out:zero if exception) * * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for * different operand sizes can be reached by calculation, rather than a jump @@ -276,174 +285,17 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt) } /* - * Instruction emulation: - * Most instructions are emulated directly via a fragment of inline assembly - * code. This allows us to save/restore EFLAGS and thus very easily pick up - * any modified flags. - */ - -#if defined(CONFIG_X86_64) -#define _LO32 "k" /* force 32-bit operand */ -#define _STK "%%rsp" /* stack pointer */ -#elif defined(__i386__) -#define _LO32 "" /* force 32-bit operand */ -#define _STK "%%esp" /* stack pointer */ -#endif - -/* * These EFLAGS bits are restored from saved value during emulation, and * any changes are written back to the saved value after emulation. */ #define EFLAGS_MASK (EFLG_OF|EFLG_SF|EFLG_ZF|EFLG_AF|EFLG_PF|EFLG_CF) -/* Before executing instruction: restore necessary bits in EFLAGS. */ -#define _PRE_EFLAGS(_sav, _msk, _tmp) \ - /* EFLAGS = (_sav & _msk) | (EFLAGS & ~_msk); _sav &= ~_msk; */ \ - "movl %"_sav",%"_LO32 _tmp"; " \ - "push %"_tmp"; " \ - "push %"_tmp"; " \ - "movl %"_msk",%"_LO32 _tmp"; " \ - "andl %"_LO32 _tmp",("_STK"); " \ - "pushf; " \ - "notl %"_LO32 _tmp"; " \ - "andl %"_LO32 _tmp",("_STK"); " \ - "andl %"_LO32 _tmp","__stringify(BITS_PER_LONG/4)"("_STK"); " \ - "pop %"_tmp"; " \ - "orl %"_LO32 _tmp",("_STK"); " \ - "popf; " \ - "pop %"_sav"; " - -/* After executing instruction: write-back necessary bits in EFLAGS. */ -#define _POST_EFLAGS(_sav, _msk, _tmp) \ - /* _sav |= EFLAGS & _msk; */ \ - "pushf; " \ - "pop %"_tmp"; " \ - "andl %"_msk",%"_LO32 _tmp"; " \ - "orl %"_LO32 _tmp",%"_sav"; " - #ifdef CONFIG_X86_64 #define ON64(x) x #else #define ON64(x) #endif -#define ____emulate_2op(ctxt, _op, _x, _y, _suffix, _dsttype) \ - do { \ - __asm__ __volatile__ ( \ - _PRE_EFLAGS("0", "4", "2") \ - _op _suffix " %"_x"3,%1; " \ - _POST_EFLAGS("0", "4", "2") \ - : "=m" ((ctxt)->eflags), \ - "+q" (*(_dsttype*)&(ctxt)->dst.val), \ - "=&r" (_tmp) \ - : _y ((ctxt)->src.val), "i" (EFLAGS_MASK)); \ - } while (0) - - -/* Raw emulation: instruction has two explicit operands. */ -#define __emulate_2op_nobyte(ctxt,_op,_wx,_wy,_lx,_ly,_qx,_qy) \ - do { \ - unsigned long _tmp; \ - \ - switch ((ctxt)->dst.bytes) { \ - case 2: \ - ____emulate_2op(ctxt,_op,_wx,_wy,"w",u16); \ - break; \ - case 4: \ - ____emulate_2op(ctxt,_op,_lx,_ly,"l",u32); \ - break; \ - case 8: \ - ON64(____emulate_2op(ctxt,_op,_qx,_qy,"q",u64)); \ - break; \ - } \ - } while (0) - -#define __emulate_2op(ctxt,_op,_bx,_by,_wx,_wy,_lx,_ly,_qx,_qy) \ - do { \ - unsigned long _tmp; \ - switch ((ctxt)->dst.bytes) { \ - case 1: \ - ____emulate_2op(ctxt,_op,_bx,_by,"b",u8); \ - break; \ - default: \ - __emulate_2op_nobyte(ctxt, _op, \ - _wx, _wy, _lx, _ly, _qx, _qy); \ - break; \ - } \ - } while (0) - -/* Source operand is byte-sized and may be restricted to just %cl. */ -#define emulate_2op_SrcB(ctxt, _op) \ - __emulate_2op(ctxt, _op, "b", "c", "b", "c", "b", "c", "b", "c") - -/* Source operand is byte, word, long or quad sized. */ -#define emulate_2op_SrcV(ctxt, _op) \ - __emulate_2op(ctxt, _op, "b", "q", "w", "r", _LO32, "r", "", "r") - -/* Source operand is word, long or quad sized. */ -#define emulate_2op_SrcV_nobyte(ctxt, _op) \ - __emulate_2op_nobyte(ctxt, _op, "w", "r", _LO32, "r", "", "r") - -/* Instruction has three operands and one operand is stored in ECX register */ -#define __emulate_2op_cl(ctxt, _op, _suffix, _type) \ - do { \ - unsigned long _tmp; \ - _type _clv = (ctxt)->src2.val; \ - _type _srcv = (ctxt)->src.val; \ - _type _dstv = (ctxt)->dst.val; \ - \ - __asm__ __volatile__ ( \ - _PRE_EFLAGS("0", "5", "2") \ - _op _suffix " %4,%1 \n" \ - _POST_EFLAGS("0", "5", "2") \ - : "=m" ((ctxt)->eflags), "+r" (_dstv), "=&r" (_tmp) \ - : "c" (_clv) , "r" (_srcv), "i" (EFLAGS_MASK) \ - ); \ - \ - (ctxt)->src2.val = (unsigned long) _clv; \ - (ctxt)->src2.val = (unsigned long) _srcv; \ - (ctxt)->dst.val = (unsigned long) _dstv; \ - } while (0) - -#define emulate_2op_cl(ctxt, _op) \ - do { \ - switch ((ctxt)->dst.bytes) { \ - case 2: \ - __emulate_2op_cl(ctxt, _op, "w", u16); \ - break; \ - case 4: \ - __emulate_2op_cl(ctxt, _op, "l", u32); \ - break; \ - case 8: \ - ON64(__emulate_2op_cl(ctxt, _op, "q", ulong)); \ - break; \ - } \ - } while (0) - -#define __emulate_1op(ctxt, _op, _suffix) \ - do { \ - unsigned long _tmp; \ - \ - __asm__ __volatile__ ( \ - _PRE_EFLAGS("0", "3", "2") \ - _op _suffix " %1; " \ - _POST_EFLAGS("0", "3", "2") \ - : "=m" ((ctxt)->eflags), "+m" ((ctxt)->dst.val), \ - "=&r" (_tmp) \ - : "i" (EFLAGS_MASK)); \ - } while (0) - -/* Instruction has only one explicit operand (no source operand). */ -#define emulate_1op(ctxt, _op) \ - do { \ - switch ((ctxt)->dst.bytes) { \ - case 1: __emulate_1op(ctxt, _op, "b"); break; \ - case 2: __emulate_1op(ctxt, _op, "w"); break; \ - case 4: __emulate_1op(ctxt, _op, "l"); break; \ - case 8: ON64(__emulate_1op(ctxt, _op, "q")); break; \ - } \ - } while (0) - static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)); #define FOP_ALIGN ".align " __stringify(FASTOP_SIZE) " \n\t" @@ -462,7 +314,10 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)); #define FOPNOP() FOP_ALIGN FOP_RET #define FOP1E(op, dst) \ - FOP_ALIGN #op " %" #dst " \n\t" FOP_RET + FOP_ALIGN "10: " #op " %" #dst " \n\t" FOP_RET + +#define FOP1EEX(op, dst) \ + FOP1E(op, dst) _ASM_EXTABLE(10b, kvm_fastop_exception) #define FASTOP1(op) \ FOP_START(op) \ @@ -472,24 +327,42 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)); ON64(FOP1E(op##q, rax)) \ FOP_END +/* 1-operand, using src2 (for MUL/DIV r/m) */ +#define FASTOP1SRC2(op, name) \ + FOP_START(name) \ + FOP1E(op, cl) \ + FOP1E(op, cx) \ + FOP1E(op, ecx) \ + ON64(FOP1E(op, rcx)) \ + FOP_END + +/* 1-operand, using src2 (for MUL/DIV r/m), with exceptions */ +#define FASTOP1SRC2EX(op, name) \ + FOP_START(name) \ + FOP1EEX(op, cl) \ + FOP1EEX(op, cx) \ + FOP1EEX(op, ecx) \ + ON64(FOP1EEX(op, rcx)) \ + FOP_END + #define FOP2E(op, dst, src) \ FOP_ALIGN #op " %" #src ", %" #dst " \n\t" FOP_RET #define FASTOP2(op) \ FOP_START(op) \ - FOP2E(op##b, al, bl) \ - FOP2E(op##w, ax, bx) \ - FOP2E(op##l, eax, ebx) \ - ON64(FOP2E(op##q, rax, rbx)) \ + FOP2E(op##b, al, dl) \ + FOP2E(op##w, ax, dx) \ + FOP2E(op##l, eax, edx) \ + ON64(FOP2E(op##q, rax, rdx)) \ FOP_END /* 2 operand, word only */ #define FASTOP2W(op) \ FOP_START(op) \ FOPNOP() \ - FOP2E(op##w, ax, bx) \ - FOP2E(op##l, eax, ebx) \ - ON64(FOP2E(op##q, rax, rbx)) \ + FOP2E(op##w, ax, dx) \ + FOP2E(op##l, eax, edx) \ + ON64(FOP2E(op##q, rax, rdx)) \ FOP_END /* 2 operand, src is CL */ @@ -508,14 +381,17 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)); #define FASTOP3WCL(op) \ FOP_START(op) \ FOPNOP() \ - FOP3E(op##w, ax, bx, cl) \ - FOP3E(op##l, eax, ebx, cl) \ - ON64(FOP3E(op##q, rax, rbx, cl)) \ + FOP3E(op##w, ax, dx, cl) \ + FOP3E(op##l, eax, edx, cl) \ + ON64(FOP3E(op##q, rax, rdx, cl)) \ FOP_END /* Special case for SETcc - 1 instruction per cc */ #define FOP_SETCC(op) ".align 4; " #op " %al; ret \n\t" +asm(".global kvm_fastop_exception \n" + "kvm_fastop_exception: xor %esi, %esi; ret"); + FOP_START(setcc) FOP_SETCC(seto) FOP_SETCC(setno) @@ -538,47 +414,6 @@ FOP_END; FOP_START(salc) "pushf; sbb %al, %al; popf \n\t" FOP_RET FOP_END; -#define __emulate_1op_rax_rdx(ctxt, _op, _suffix, _ex) \ - do { \ - unsigned long _tmp; \ - ulong *rax = reg_rmw((ctxt), VCPU_REGS_RAX); \ - ulong *rdx = reg_rmw((ctxt), VCPU_REGS_RDX); \ - \ - __asm__ __volatile__ ( \ - _PRE_EFLAGS("0", "5", "1") \ - "1: \n\t" \ - _op _suffix " %6; " \ - "2: \n\t" \ - _POST_EFLAGS("0", "5", "1") \ - ".pushsection .fixup,\"ax\" \n\t" \ - "3: movb $1, %4 \n\t" \ - "jmp 2b \n\t" \ - ".popsection \n\t" \ - _ASM_EXTABLE(1b, 3b) \ - : "=m" ((ctxt)->eflags), "=&r" (_tmp), \ - "+a" (*rax), "+d" (*rdx), "+qm"(_ex) \ - : "i" (EFLAGS_MASK), "m" ((ctxt)->src.val)); \ - } while (0) - -/* instruction has only one source operand, destination is implicit (e.g. mul, div, imul, idiv) */ -#define emulate_1op_rax_rdx(ctxt, _op, _ex) \ - do { \ - switch((ctxt)->src.bytes) { \ - case 1: \ - __emulate_1op_rax_rdx(ctxt, _op, "b", _ex); \ - break; \ - case 2: \ - __emulate_1op_rax_rdx(ctxt, _op, "w", _ex); \ - break; \ - case 4: \ - __emulate_1op_rax_rdx(ctxt, _op, "l", _ex); \ - break; \ - case 8: ON64( \ - __emulate_1op_rax_rdx(ctxt, _op, "q", _ex)); \ - break; \ - } \ - } while (0) - static int emulator_check_intercept(struct x86_emulate_ctxt *ctxt, enum x86_intercept intercept, enum x86_intercept_stage stage) @@ -988,6 +823,11 @@ FASTOP2(xor); FASTOP2(cmp); FASTOP2(test); +FASTOP1SRC2(mul, mul_ex); +FASTOP1SRC2(imul, imul_ex); +FASTOP1SRC2EX(div, div_ex); +FASTOP1SRC2EX(idiv, idiv_ex); + FASTOP3WCL(shld); FASTOP3WCL(shrd); @@ -1013,6 +853,8 @@ FASTOP2W(bts); FASTOP2W(btr); FASTOP2W(btc); +FASTOP2(xadd); + static u8 test_cc(unsigned int condition, unsigned long flags) { u8 rc; @@ -1726,45 +1568,42 @@ static void write_register_operand(struct operand *op) } } -static int writeback(struct x86_emulate_ctxt *ctxt) +static int writeback(struct x86_emulate_ctxt *ctxt, struct operand *op) { int rc; - if (ctxt->d & NoWrite) - return X86EMUL_CONTINUE; - - switch (ctxt->dst.type) { + switch (op->type) { case OP_REG: - write_register_operand(&ctxt->dst); + write_register_operand(op); break; case OP_MEM: if (ctxt->lock_prefix) rc = segmented_cmpxchg(ctxt, - ctxt->dst.addr.mem, - &ctxt->dst.orig_val, - &ctxt->dst.val, - ctxt->dst.bytes); + op->addr.mem, + &op->orig_val, + &op->val, + op->bytes); else rc = segmented_write(ctxt, - ctxt->dst.addr.mem, - &ctxt->dst.val, - ctxt->dst.bytes); + op->addr.mem, + &op->val, + op->bytes); if (rc != X86EMUL_CONTINUE) return rc; break; case OP_MEM_STR: rc = segmented_write(ctxt, - ctxt->dst.addr.mem, - ctxt->dst.data, - ctxt->dst.bytes * ctxt->dst.count); + op->addr.mem, + op->data, + op->bytes * op->count); if (rc != X86EMUL_CONTINUE) return rc; break; case OP_XMM: - write_sse_reg(ctxt, &ctxt->dst.vec_val, ctxt->dst.addr.xmm); + write_sse_reg(ctxt, &op->vec_val, op->addr.xmm); break; case OP_MM: - write_mmx_reg(ctxt, &ctxt->dst.mm_val, ctxt->dst.addr.mm); + write_mmx_reg(ctxt, &op->mm_val, op->addr.mm); break; case OP_NONE: /* no writeback */ @@ -2117,42 +1956,6 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -static int em_mul_ex(struct x86_emulate_ctxt *ctxt) -{ - u8 ex = 0; - - emulate_1op_rax_rdx(ctxt, "mul", ex); - return X86EMUL_CONTINUE; -} - -static int em_imul_ex(struct x86_emulate_ctxt *ctxt) -{ - u8 ex = 0; - - emulate_1op_rax_rdx(ctxt, "imul", ex); - return X86EMUL_CONTINUE; -} - -static int em_div_ex(struct x86_emulate_ctxt *ctxt) -{ - u8 de = 0; - - emulate_1op_rax_rdx(ctxt, "div", de); - if (de) - return emulate_de(ctxt); - return X86EMUL_CONTINUE; -} - -static int em_idiv_ex(struct x86_emulate_ctxt *ctxt) -{ - u8 de = 0; - - emulate_1op_rax_rdx(ctxt, "idiv", de); - if (de) - return emulate_de(ctxt); - return X86EMUL_CONTINUE; -} - static int em_grp45(struct x86_emulate_ctxt *ctxt) { int rc = X86EMUL_CONTINUE; @@ -3734,10 +3537,10 @@ static const struct opcode group3[] = { F(DstMem | SrcImm | NoWrite, em_test), F(DstMem | SrcNone | Lock, em_not), F(DstMem | SrcNone | Lock, em_neg), - I(SrcMem, em_mul_ex), - I(SrcMem, em_imul_ex), - I(SrcMem, em_div_ex), - I(SrcMem, em_idiv_ex), + F(DstXacc | Src2Mem, em_mul_ex), + F(DstXacc | Src2Mem, em_imul_ex), + F(DstXacc | Src2Mem, em_div_ex), + F(DstXacc | Src2Mem, em_idiv_ex), }; static const struct opcode group4[] = { @@ -4064,7 +3867,7 @@ static const struct opcode twobyte_table[256] = { F(DstReg | SrcMem | ModRM, em_bsf), F(DstReg | SrcMem | ModRM, em_bsr), D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), /* 0xC0 - 0xC7 */ - D2bv(DstMem | SrcReg | ModRM | Lock), + F2bv(DstMem | SrcReg | ModRM | SrcWrite | Lock, em_xadd), N, D(DstMem | SrcReg | ModRM | Mov), N, N, N, GD(0, &group9), /* 0xC8 - 0xCF */ @@ -4172,6 +3975,24 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op, fetch_register_operand(op); op->orig_val = op->val; break; + case OpAccLo: + op->type = OP_REG; + op->bytes = (ctxt->d & ByteOp) ? 2 : ctxt->op_bytes; + op->addr.reg = reg_rmw(ctxt, VCPU_REGS_RAX); + fetch_register_operand(op); + op->orig_val = op->val; + break; + case OpAccHi: + if (ctxt->d & ByteOp) { + op->type = OP_NONE; + break; + } + op->type = OP_REG; + op->bytes = ctxt->op_bytes; + op->addr.reg = reg_rmw(ctxt, VCPU_REGS_RDX); + fetch_register_operand(op); + op->orig_val = op->val; + break; case OpDI: op->type = OP_MEM; op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; @@ -4553,11 +4374,15 @@ static void fetch_possible_mmx_operand(struct x86_emulate_ctxt *ctxt, static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)) { ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF; - fop += __ffs(ctxt->dst.bytes) * FASTOP_SIZE; + if (!(ctxt->d & ByteOp)) + fop += __ffs(ctxt->dst.bytes) * FASTOP_SIZE; asm("push %[flags]; popf; call *%[fastop]; pushf; pop %[flags]\n" - : "+a"(ctxt->dst.val), "+b"(ctxt->src.val), [flags]"+D"(flags) - : "c"(ctxt->src2.val), [fastop]"S"(fop)); + : "+a"(ctxt->dst.val), "+d"(ctxt->src.val), [flags]"+D"(flags), + [fastop]"+S"(fop) + : "c"(ctxt->src2.val)); ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK); + if (!fop) /* exception is returned in fop variable */ + return emulate_de(ctxt); return X86EMUL_CONTINUE; } @@ -4773,9 +4598,17 @@ special_insn: goto done; writeback: - rc = writeback(ctxt); - if (rc != X86EMUL_CONTINUE) - goto done; + if (!(ctxt->d & NoWrite)) { + rc = writeback(ctxt, &ctxt->dst); + if (rc != X86EMUL_CONTINUE) + goto done; + } + if (ctxt->d & SrcWrite) { + BUG_ON(ctxt->src.type == OP_MEM || ctxt->src.type == OP_MEM_STR); + rc = writeback(ctxt, &ctxt->src); + if (rc != X86EMUL_CONTINUE) + goto done; + } /* * restore dst type in case the decoding will be reused @@ -4872,12 +4705,6 @@ twobyte_insn: ctxt->dst.val = (ctxt->src.bytes == 1) ? (s8) ctxt->src.val : (s16) ctxt->src.val; break; - case 0xc0 ... 0xc1: /* xadd */ - fastop(ctxt, em_add); - /* Write back the register source. */ - ctxt->src.val = ctxt->dst.orig_val; - write_register_operand(&ctxt->src); - break; case 0xc3: /* movnti */ ctxt->dst.bytes = ctxt->op_bytes; ctxt->dst.val = (ctxt->op_bytes == 4) ? (u32) ctxt->src.val : diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 0eee2c8b64d1..afc11245827c 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1608,8 +1608,8 @@ void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu) return; if (atomic_read(&apic->lapic_timer.pending) > 0) { - if (kvm_apic_local_deliver(apic, APIC_LVTT)) - atomic_dec(&apic->lapic_timer.pending); + kvm_apic_local_deliver(apic, APIC_LVTT); + atomic_set(&apic->lapic_timer.pending, 0); } } diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 004cc87b781c..0d094da49541 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -197,15 +197,63 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask) } EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask); -static void mark_mmio_spte(u64 *sptep, u64 gfn, unsigned access) +/* + * spte bits of bit 3 ~ bit 11 are used as low 9 bits of generation number, + * the bits of bits 52 ~ bit 61 are used as high 10 bits of generation + * number. + */ +#define MMIO_SPTE_GEN_LOW_SHIFT 3 +#define MMIO_SPTE_GEN_HIGH_SHIFT 52 + +#define MMIO_GEN_SHIFT 19 +#define MMIO_GEN_LOW_SHIFT 9 +#define MMIO_GEN_LOW_MASK ((1 << MMIO_GEN_LOW_SHIFT) - 1) +#define MMIO_GEN_MASK ((1 << MMIO_GEN_SHIFT) - 1) +#define MMIO_MAX_GEN ((1 << MMIO_GEN_SHIFT) - 1) + +static u64 generation_mmio_spte_mask(unsigned int gen) { - struct kvm_mmu_page *sp = page_header(__pa(sptep)); + u64 mask; + + WARN_ON(gen > MMIO_MAX_GEN); + + mask = (gen & MMIO_GEN_LOW_MASK) << MMIO_SPTE_GEN_LOW_SHIFT; + mask |= ((u64)gen >> MMIO_GEN_LOW_SHIFT) << MMIO_SPTE_GEN_HIGH_SHIFT; + return mask; +} + +static unsigned int get_mmio_spte_generation(u64 spte) +{ + unsigned int gen; + + spte &= ~shadow_mmio_mask; + + gen = (spte >> MMIO_SPTE_GEN_LOW_SHIFT) & MMIO_GEN_LOW_MASK; + gen |= (spte >> MMIO_SPTE_GEN_HIGH_SHIFT) << MMIO_GEN_LOW_SHIFT; + return gen; +} + +static unsigned int kvm_current_mmio_generation(struct kvm *kvm) +{ + /* + * Init kvm generation close to MMIO_MAX_GEN to easily test the + * code of handling generation number wrap-around. + */ + return (kvm_memslots(kvm)->generation + + MMIO_MAX_GEN - 150) & MMIO_GEN_MASK; +} + +static void mark_mmio_spte(struct kvm *kvm, u64 *sptep, u64 gfn, + unsigned access) +{ + unsigned int gen = kvm_current_mmio_generation(kvm); + u64 mask = generation_mmio_spte_mask(gen); access &= ACC_WRITE_MASK | ACC_USER_MASK; + mask |= shadow_mmio_mask | access | gfn << PAGE_SHIFT; - sp->mmio_cached = true; - trace_mark_mmio_spte(sptep, gfn, access); - mmu_spte_set(sptep, shadow_mmio_mask | access | gfn << PAGE_SHIFT); + trace_mark_mmio_spte(sptep, gfn, access, gen); + mmu_spte_set(sptep, mask); } static bool is_mmio_spte(u64 spte) @@ -215,24 +263,38 @@ static bool is_mmio_spte(u64 spte) static gfn_t get_mmio_spte_gfn(u64 spte) { - return (spte & ~shadow_mmio_mask) >> PAGE_SHIFT; + u64 mask = generation_mmio_spte_mask(MMIO_MAX_GEN) | shadow_mmio_mask; + return (spte & ~mask) >> PAGE_SHIFT; } static unsigned get_mmio_spte_access(u64 spte) { - return (spte & ~shadow_mmio_mask) & ~PAGE_MASK; + u64 mask = generation_mmio_spte_mask(MMIO_MAX_GEN) | shadow_mmio_mask; + return (spte & ~mask) & ~PAGE_MASK; } -static bool set_mmio_spte(u64 *sptep, gfn_t gfn, pfn_t pfn, unsigned access) +static bool set_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn, + pfn_t pfn, unsigned access) { if (unlikely(is_noslot_pfn(pfn))) { - mark_mmio_spte(sptep, gfn, access); + mark_mmio_spte(kvm, sptep, gfn, access); return true; } return false; } +static bool check_mmio_spte(struct kvm *kvm, u64 spte) +{ + unsigned int kvm_gen, spte_gen; + + kvm_gen = kvm_current_mmio_generation(kvm); + spte_gen = get_mmio_spte_generation(spte); + + trace_check_mmio_spte(spte, kvm_gen, spte_gen); + return likely(kvm_gen == spte_gen); +} + static inline u64 rsvd_bits(int s, int e) { return ((1ULL << (e - s + 1)) - 1) << s; @@ -404,9 +466,20 @@ static u64 __update_clear_spte_slow(u64 *sptep, u64 spte) /* * The idea using the light way get the spte on x86_32 guest is from * gup_get_pte(arch/x86/mm/gup.c). - * The difference is we can not catch the spte tlb flush if we leave - * guest mode, so we emulate it by increase clear_spte_count when spte - * is cleared. + * + * An spte tlb flush may be pending, because kvm_set_pte_rmapp + * coalesces them and we are running out of the MMU lock. Therefore + * we need to protect against in-progress updates of the spte. + * + * Reading the spte while an update is in progress may get the old value + * for the high part of the spte. The race is fine for a present->non-present + * change (because the high part of the spte is ignored for non-present spte), + * but for a present->present change we must reread the spte. + * + * All such changes are done in two steps (present->non-present and + * non-present->present), hence it is enough to count the number of + * present->non-present updates: if it changed while reading the spte, + * we might have hit the race. This is done using clear_spte_count. */ static u64 __get_spte_lockless(u64 *sptep) { @@ -1511,6 +1584,12 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, if (!direct) sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache); set_page_private(virt_to_page(sp->spt), (unsigned long)sp); + + /* + * The active_mmu_pages list is the FIFO list, do not move the + * page until it is zapped. kvm_zap_obsolete_pages depends on + * this feature. See the comments in kvm_zap_obsolete_pages(). + */ list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages); sp->parent_ptes = 0; mmu_page_add_parent_pte(vcpu, sp, parent_pte); @@ -1648,6 +1727,16 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, static void kvm_mmu_commit_zap_page(struct kvm *kvm, struct list_head *invalid_list); +/* + * NOTE: we should pay more attention on the zapped-obsolete page + * (is_obsolete_sp(sp) && sp->role.invalid) when you do hash list walk + * since it has been deleted from active_mmu_pages but still can be found + * at hast list. + * + * for_each_gfn_indirect_valid_sp has skipped that kind of page and + * kvm_mmu_get_page(), the only user of for_each_gfn_sp(), has skipped + * all the obsolete pages. + */ #define for_each_gfn_sp(_kvm, _sp, _gfn) \ hlist_for_each_entry(_sp, \ &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)], hash_link) \ @@ -1838,6 +1927,11 @@ static void clear_sp_write_flooding_count(u64 *spte) __clear_sp_write_flooding_count(sp); } +static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + return unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen); +} + static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, gfn_t gfn, gva_t gaddr, @@ -1864,6 +1958,9 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, role.quadrant = quadrant; } for_each_gfn_sp(vcpu->kvm, sp, gfn) { + if (is_obsolete_sp(vcpu->kvm, sp)) + continue; + if (!need_sync && sp->unsync) need_sync = true; @@ -1900,6 +1997,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, account_shadowed(vcpu->kvm, gfn); } + sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen; init_shadow_page_table(sp); trace_kvm_mmu_get_page(sp, true); return sp; @@ -2070,8 +2168,10 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, ret = mmu_zap_unsync_children(kvm, sp, invalid_list); kvm_mmu_page_unlink_children(kvm, sp); kvm_mmu_unlink_parents(kvm, sp); + if (!sp->role.invalid && !sp->role.direct) unaccount_shadowed(kvm, sp->gfn); + if (sp->unsync) kvm_unlink_unsync_page(kvm, sp); if (!sp->root_count) { @@ -2081,7 +2181,13 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, kvm_mod_used_mmu_pages(kvm, -1); } else { list_move(&sp->link, &kvm->arch.active_mmu_pages); - kvm_reload_remote_mmus(kvm); + + /* + * The obsolete pages can not be used on any vcpus. + * See the comments in kvm_mmu_invalidate_zap_all_pages(). + */ + if (!sp->role.invalid && !is_obsolete_sp(kvm, sp)) + kvm_reload_remote_mmus(kvm); } sp->role.invalid = 1; @@ -2331,7 +2437,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 spte; int ret = 0; - if (set_mmio_spte(sptep, gfn, pfn, pte_access)) + if (set_mmio_spte(vcpu->kvm, sptep, gfn, pfn, pte_access)) return 0; spte = PT_PRESENT_MASK; @@ -2869,22 +2975,25 @@ static void mmu_free_roots(struct kvm_vcpu *vcpu) if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) return; - spin_lock(&vcpu->kvm->mmu_lock); + if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL && (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL || vcpu->arch.mmu.direct_map)) { hpa_t root = vcpu->arch.mmu.root_hpa; + spin_lock(&vcpu->kvm->mmu_lock); sp = page_header(root); --sp->root_count; if (!sp->root_count && sp->role.invalid) { kvm_mmu_prepare_zap_page(vcpu->kvm, sp, &invalid_list); kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); } - vcpu->arch.mmu.root_hpa = INVALID_PAGE; spin_unlock(&vcpu->kvm->mmu_lock); + vcpu->arch.mmu.root_hpa = INVALID_PAGE; return; } + + spin_lock(&vcpu->kvm->mmu_lock); for (i = 0; i < 4; ++i) { hpa_t root = vcpu->arch.mmu.pae_root[i]; @@ -3148,17 +3257,12 @@ static u64 walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr) return spte; } -/* - * If it is a real mmio page fault, return 1 and emulat the instruction - * directly, return 0 to let CPU fault again on the address, -1 is - * returned if bug is detected. - */ int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct) { u64 spte; if (quickly_check_mmio_pf(vcpu, addr, direct)) - return 1; + return RET_MMIO_PF_EMULATE; spte = walk_shadow_page_get_mmio_spte(vcpu, addr); @@ -3166,12 +3270,15 @@ int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct) gfn_t gfn = get_mmio_spte_gfn(spte); unsigned access = get_mmio_spte_access(spte); + if (!check_mmio_spte(vcpu->kvm, spte)) + return RET_MMIO_PF_INVALID; + if (direct) addr = 0; trace_handle_mmio_page_fault(addr, gfn, access); vcpu_cache_mmio_info(vcpu, addr, gfn, access); - return 1; + return RET_MMIO_PF_EMULATE; } /* @@ -3179,13 +3286,13 @@ int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct) * it's a BUG if the gfn is not a mmio page. */ if (direct && !check_direct_spte_mmio_pf(spte)) - return -1; + return RET_MMIO_PF_BUG; /* * If the page table is zapped by other cpus, let CPU fault again on * the address. */ - return 0; + return RET_MMIO_PF_RETRY; } EXPORT_SYMBOL_GPL(handle_mmio_page_fault_common); @@ -3195,7 +3302,7 @@ static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, int ret; ret = handle_mmio_page_fault_common(vcpu, addr, direct); - WARN_ON(ret < 0); + WARN_ON(ret == RET_MMIO_PF_BUG); return ret; } @@ -3207,8 +3314,12 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code); - if (unlikely(error_code & PFERR_RSVD_MASK)) - return handle_mmio_page_fault(vcpu, gva, error_code, true); + if (unlikely(error_code & PFERR_RSVD_MASK)) { + r = handle_mmio_page_fault(vcpu, gva, error_code, true); + + if (likely(r != RET_MMIO_PF_INVALID)) + return r; + } r = mmu_topup_memory_caches(vcpu); if (r) @@ -3284,8 +3395,12 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, ASSERT(vcpu); ASSERT(VALID_PAGE(vcpu->arch.mmu.root_hpa)); - if (unlikely(error_code & PFERR_RSVD_MASK)) - return handle_mmio_page_fault(vcpu, gpa, error_code, true); + if (unlikely(error_code & PFERR_RSVD_MASK)) { + r = handle_mmio_page_fault(vcpu, gpa, error_code, true); + + if (likely(r != RET_MMIO_PF_INVALID)) + return r; + } r = mmu_topup_memory_caches(vcpu); if (r) @@ -3391,8 +3506,8 @@ static inline void protect_clean_gpte(unsigned *access, unsigned gpte) *access &= mask; } -static bool sync_mmio_spte(u64 *sptep, gfn_t gfn, unsigned access, - int *nr_present) +static bool sync_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn, + unsigned access, int *nr_present) { if (unlikely(is_mmio_spte(*sptep))) { if (gfn != get_mmio_spte_gfn(*sptep)) { @@ -3401,7 +3516,7 @@ static bool sync_mmio_spte(u64 *sptep, gfn_t gfn, unsigned access, } (*nr_present)++; - mark_mmio_spte(sptep, gfn, access); + mark_mmio_spte(kvm, sptep, gfn, access); return true; } @@ -3764,9 +3879,7 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu) if (r) goto out; r = mmu_alloc_roots(vcpu); - spin_lock(&vcpu->kvm->mmu_lock); - mmu_sync_roots(vcpu); - spin_unlock(&vcpu->kvm->mmu_lock); + kvm_mmu_sync_roots(vcpu); if (r) goto out; /* set_cr3() should ensure TLB has been flushed */ @@ -4179,39 +4292,107 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot) spin_unlock(&kvm->mmu_lock); } -void kvm_mmu_zap_all(struct kvm *kvm) +#define BATCH_ZAP_PAGES 10 +static void kvm_zap_obsolete_pages(struct kvm *kvm) { struct kvm_mmu_page *sp, *node; - LIST_HEAD(invalid_list); + int batch = 0; - spin_lock(&kvm->mmu_lock); restart: - list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link) - if (kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list)) + list_for_each_entry_safe_reverse(sp, node, + &kvm->arch.active_mmu_pages, link) { + int ret; + + /* + * No obsolete page exists before new created page since + * active_mmu_pages is the FIFO list. + */ + if (!is_obsolete_sp(kvm, sp)) + break; + + /* + * Since we are reversely walking the list and the invalid + * list will be moved to the head, skip the invalid page + * can help us to avoid the infinity list walking. + */ + if (sp->role.invalid) + continue; + + /* + * Need not flush tlb since we only zap the sp with invalid + * generation number. + */ + if (batch >= BATCH_ZAP_PAGES && + cond_resched_lock(&kvm->mmu_lock)) { + batch = 0; + goto restart; + } + + ret = kvm_mmu_prepare_zap_page(kvm, sp, + &kvm->arch.zapped_obsolete_pages); + batch += ret; + + if (ret) goto restart; + } - kvm_mmu_commit_zap_page(kvm, &invalid_list); - spin_unlock(&kvm->mmu_lock); + /* + * Should flush tlb before free page tables since lockless-walking + * may use the pages. + */ + kvm_mmu_commit_zap_page(kvm, &kvm->arch.zapped_obsolete_pages); } -void kvm_mmu_zap_mmio_sptes(struct kvm *kvm) +/* + * Fast invalidate all shadow pages and use lock-break technique + * to zap obsolete pages. + * + * It's required when memslot is being deleted or VM is being + * destroyed, in these cases, we should ensure that KVM MMU does + * not use any resource of the being-deleted slot or all slots + * after calling the function. + */ +void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm) { - struct kvm_mmu_page *sp, *node; - LIST_HEAD(invalid_list); - spin_lock(&kvm->mmu_lock); -restart: - list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link) { - if (!sp->mmio_cached) - continue; - if (kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list)) - goto restart; - } + trace_kvm_mmu_invalidate_zap_all_pages(kvm); + kvm->arch.mmu_valid_gen++; - kvm_mmu_commit_zap_page(kvm, &invalid_list); + /* + * Notify all vcpus to reload its shadow page table + * and flush TLB. Then all vcpus will switch to new + * shadow page table with the new mmu_valid_gen. + * + * Note: we should do this under the protection of + * mmu-lock, otherwise, vcpu would purge shadow page + * but miss tlb flush. + */ + kvm_reload_remote_mmus(kvm); + + kvm_zap_obsolete_pages(kvm); spin_unlock(&kvm->mmu_lock); } +static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm) +{ + return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages)); +} + +void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm) +{ + /* + * The very rare case: if the generation-number is round, + * zap all shadow pages. + * + * The max value is MMIO_MAX_GEN - 1 since it is not called + * when mark memslot invalid. + */ + if (unlikely(kvm_current_mmio_generation(kvm) >= (MMIO_MAX_GEN - 1))) { + printk_ratelimited(KERN_INFO "kvm: zapping shadow pages for mmio generation wraparound\n"); + kvm_mmu_invalidate_zap_all_pages(kvm); + } +} + static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc) { struct kvm *kvm; @@ -4240,15 +4421,23 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc) * want to shrink a VM that only started to populate its MMU * anyway. */ - if (!kvm->arch.n_used_mmu_pages) + if (!kvm->arch.n_used_mmu_pages && + !kvm_has_zapped_obsolete_pages(kvm)) continue; idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); + if (kvm_has_zapped_obsolete_pages(kvm)) { + kvm_mmu_commit_zap_page(kvm, + &kvm->arch.zapped_obsolete_pages); + goto unlock; + } + prepare_zap_oldest_mmu_page(kvm, &invalid_list); kvm_mmu_commit_zap_page(kvm, &invalid_list); +unlock: spin_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, idx); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 2adcbc2cac6d..5b59c573aba7 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -52,6 +52,23 @@ int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]); void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask); + +/* + * Return values of handle_mmio_page_fault_common: + * RET_MMIO_PF_EMULATE: it is a real mmio page fault, emulate the instruction + * directly. + * RET_MMIO_PF_INVALID: invalid spte is detected then let the real page + * fault path update the mmio spte. + * RET_MMIO_PF_RETRY: let CPU fault again on the address. + * RET_MMIO_PF_BUG: bug is detected. + */ +enum { + RET_MMIO_PF_EMULATE = 1, + RET_MMIO_PF_INVALID = 2, + RET_MMIO_PF_RETRY = 0, + RET_MMIO_PF_BUG = -1 +}; + int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct); int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context); @@ -97,4 +114,5 @@ static inline bool permission_fault(struct kvm_mmu *mmu, unsigned pte_access, return (mmu->permissions[pfec >> 1] >> pte_access) & 1; } +void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm); #endif diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index b8f6172f4174..9d2e0ffcb190 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -7,16 +7,18 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM kvmmmu -#define KVM_MMU_PAGE_FIELDS \ - __field(__u64, gfn) \ - __field(__u32, role) \ - __field(__u32, root_count) \ +#define KVM_MMU_PAGE_FIELDS \ + __field(unsigned long, mmu_valid_gen) \ + __field(__u64, gfn) \ + __field(__u32, role) \ + __field(__u32, root_count) \ __field(bool, unsync) -#define KVM_MMU_PAGE_ASSIGN(sp) \ - __entry->gfn = sp->gfn; \ - __entry->role = sp->role.word; \ - __entry->root_count = sp->root_count; \ +#define KVM_MMU_PAGE_ASSIGN(sp) \ + __entry->mmu_valid_gen = sp->mmu_valid_gen; \ + __entry->gfn = sp->gfn; \ + __entry->role = sp->role.word; \ + __entry->root_count = sp->root_count; \ __entry->unsync = sp->unsync; #define KVM_MMU_PAGE_PRINTK() ({ \ @@ -28,8 +30,8 @@ \ role.word = __entry->role; \ \ - trace_seq_printf(p, "sp gfn %llx %u%s q%u%s %s%s" \ - " %snxe root %u %s%c", \ + trace_seq_printf(p, "sp gen %lx gfn %llx %u%s q%u%s %s%s" \ + " %snxe root %u %s%c", __entry->mmu_valid_gen, \ __entry->gfn, role.level, \ role.cr4_pae ? " pae" : "", \ role.quadrant, \ @@ -197,23 +199,25 @@ DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_prepare_zap_page, TRACE_EVENT( mark_mmio_spte, - TP_PROTO(u64 *sptep, gfn_t gfn, unsigned access), - TP_ARGS(sptep, gfn, access), + TP_PROTO(u64 *sptep, gfn_t gfn, unsigned access, unsigned int gen), + TP_ARGS(sptep, gfn, access, gen), TP_STRUCT__entry( __field(void *, sptep) __field(gfn_t, gfn) __field(unsigned, access) + __field(unsigned int, gen) ), TP_fast_assign( __entry->sptep = sptep; __entry->gfn = gfn; __entry->access = access; + __entry->gen = gen; ), - TP_printk("sptep:%p gfn %llx access %x", __entry->sptep, __entry->gfn, - __entry->access) + TP_printk("sptep:%p gfn %llx access %x gen %x", __entry->sptep, + __entry->gfn, __entry->access, __entry->gen) ); TRACE_EVENT( @@ -274,6 +278,50 @@ TRACE_EVENT( __spte_satisfied(old_spte), __spte_satisfied(new_spte) ) ); + +TRACE_EVENT( + kvm_mmu_invalidate_zap_all_pages, + TP_PROTO(struct kvm *kvm), + TP_ARGS(kvm), + + TP_STRUCT__entry( + __field(unsigned long, mmu_valid_gen) + __field(unsigned int, mmu_used_pages) + ), + + TP_fast_assign( + __entry->mmu_valid_gen = kvm->arch.mmu_valid_gen; + __entry->mmu_used_pages = kvm->arch.n_used_mmu_pages; + ), + + TP_printk("kvm-mmu-valid-gen %lx used_pages %x", + __entry->mmu_valid_gen, __entry->mmu_used_pages + ) +); + + +TRACE_EVENT( + check_mmio_spte, + TP_PROTO(u64 spte, unsigned int kvm_gen, unsigned int spte_gen), + TP_ARGS(spte, kvm_gen, spte_gen), + + TP_STRUCT__entry( + __field(unsigned int, kvm_gen) + __field(unsigned int, spte_gen) + __field(u64, spte) + ), + + TP_fast_assign( + __entry->kvm_gen = kvm_gen; + __entry->spte_gen = spte_gen; + __entry->spte = spte; + ), + + TP_printk("spte %llx kvm_gen %x spte-gen %x valid %d", __entry->spte, + __entry->kvm_gen, __entry->spte_gen, + __entry->kvm_gen == __entry->spte_gen + ) +); #endif /* _TRACE_KVMMMU_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index da20860b457a..7769699d48a8 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -552,9 +552,12 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code); - if (unlikely(error_code & PFERR_RSVD_MASK)) - return handle_mmio_page_fault(vcpu, addr, error_code, + if (unlikely(error_code & PFERR_RSVD_MASK)) { + r = handle_mmio_page_fault(vcpu, addr, error_code, mmu_is_nested(vcpu)); + if (likely(r != RET_MMIO_PF_INVALID)) + return r; + }; r = mmu_topup_memory_caches(vcpu); if (r) @@ -792,7 +795,8 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) pte_access &= gpte_access(vcpu, gpte); protect_clean_gpte(&pte_access, gpte); - if (sync_mmio_spte(&sp->spt[i], gfn, pte_access, &nr_present)) + if (sync_mmio_spte(vcpu->kvm, &sp->spt[i], gfn, pte_access, + &nr_present)) continue; if (gfn != sp->gfns[i]) { diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index a14a6eaf871d..c0bc80391e40 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1026,7 +1026,10 @@ static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) g_tsc_offset = svm->vmcb->control.tsc_offset - svm->nested.hsave->control.tsc_offset; svm->nested.hsave->control.tsc_offset = offset; - } + } else + trace_kvm_write_tsc_offset(vcpu->vcpu_id, + svm->vmcb->control.tsc_offset, + offset); svm->vmcb->control.tsc_offset = offset + g_tsc_offset; @@ -1044,6 +1047,11 @@ static void svm_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool ho svm->vmcb->control.tsc_offset += adjustment; if (is_guest_mode(vcpu)) svm->nested.hsave->control.tsc_offset += adjustment; + else + trace_kvm_write_tsc_offset(vcpu->vcpu_id, + svm->vmcb->control.tsc_offset - adjustment, + svm->vmcb->control.tsc_offset); + mark_dirty(svm->vmcb, VMCB_INTERCEPTS); } diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index fe5e00ed7036..545245d7cc63 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -756,6 +756,27 @@ TRACE_EVENT( __entry->gpa_match ? "GPA" : "GVA") ); +TRACE_EVENT(kvm_write_tsc_offset, + TP_PROTO(unsigned int vcpu_id, __u64 previous_tsc_offset, + __u64 next_tsc_offset), + TP_ARGS(vcpu_id, previous_tsc_offset, next_tsc_offset), + + TP_STRUCT__entry( + __field( unsigned int, vcpu_id ) + __field( __u64, previous_tsc_offset ) + __field( __u64, next_tsc_offset ) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->previous_tsc_offset = previous_tsc_offset; + __entry->next_tsc_offset = next_tsc_offset; + ), + + TP_printk("vcpu=%u prev=%llu next=%llu", __entry->vcpu_id, + __entry->previous_tsc_offset, __entry->next_tsc_offset) +); + #ifdef CONFIG_X86_64 #define host_clocks \ diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index b30f5a54a2ab..a7e18551c968 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2096,6 +2096,8 @@ static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) (nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETING) ? vmcs12->tsc_offset : 0)); } else { + trace_kvm_write_tsc_offset(vcpu->vcpu_id, + vmcs_read64(TSC_OFFSET), offset); vmcs_write64(TSC_OFFSET, offset); } } @@ -2103,11 +2105,14 @@ static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool host) { u64 offset = vmcs_read64(TSC_OFFSET); + vmcs_write64(TSC_OFFSET, offset + adjustment); if (is_guest_mode(vcpu)) { /* Even when running L2, the adjustment needs to apply to L1 */ to_vmx(vcpu)->nested.vmcs01_tsc_offset += adjustment; - } + } else + trace_kvm_write_tsc_offset(vcpu->vcpu_id, offset, + offset + adjustment); } static u64 vmx_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) @@ -4176,10 +4181,10 @@ static void ept_set_mmio_spte_mask(void) /* * EPT Misconfigurations can be generated if the value of bits 2:0 * of an EPT paging-structure entry is 110b (write/execute). - * Also, magic bits (0xffull << 49) is set to quickly identify mmio + * Also, magic bits (0x3ull << 62) is set to quickly identify mmio * spte. */ - kvm_mmu_set_mmio_spte_mask(0xffull << 49 | 0x6ull); + kvm_mmu_set_mmio_spte_mask((0x3ull << 62) | 0x6ull); } /* @@ -5366,10 +5371,14 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); ret = handle_mmio_page_fault_common(vcpu, gpa, true); - if (likely(ret == 1)) + if (likely(ret == RET_MMIO_PF_EMULATE)) return x86_emulate_instruction(vcpu, gpa, 0, NULL, 0) == EMULATE_DONE; - if (unlikely(!ret)) + + if (unlikely(ret == RET_MMIO_PF_INVALID)) + return kvm_mmu_page_fault(vcpu, gpa, 0, NULL, 0); + + if (unlikely(ret == RET_MMIO_PF_RETRY)) return 1; /* It is the real ept misconfig */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 292e6ca89f42..d21bce505315 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1193,20 +1193,37 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) elapsed = ns - kvm->arch.last_tsc_nsec; if (vcpu->arch.virtual_tsc_khz) { + int faulted = 0; + /* n.b - signed multiplication and division required */ usdiff = data - kvm->arch.last_tsc_write; #ifdef CONFIG_X86_64 usdiff = (usdiff * 1000) / vcpu->arch.virtual_tsc_khz; #else /* do_div() only does unsigned */ - asm("idivl %2; xor %%edx, %%edx" - : "=A"(usdiff) - : "A"(usdiff * 1000), "rm"(vcpu->arch.virtual_tsc_khz)); + asm("1: idivl %[divisor]\n" + "2: xor %%edx, %%edx\n" + " movl $0, %[faulted]\n" + "3:\n" + ".section .fixup,\"ax\"\n" + "4: movl $1, %[faulted]\n" + " jmp 3b\n" + ".previous\n" + + _ASM_EXTABLE(1b, 4b) + + : "=A"(usdiff), [faulted] "=r" (faulted) + : "A"(usdiff * 1000), [divisor] "rm"(vcpu->arch.virtual_tsc_khz)); + #endif do_div(elapsed, 1000); usdiff -= elapsed; if (usdiff < 0) usdiff = -usdiff; + + /* idivl overflow => difference is larger than USEC_PER_SEC */ + if (faulted) + usdiff = USEC_PER_SEC; } else usdiff = USEC_PER_SEC; /* disable TSC match window below */ @@ -1587,6 +1604,30 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) return 0; } +/* + * kvmclock updates which are isolated to a given vcpu, such as + * vcpu->cpu migration, should not allow system_timestamp from + * the rest of the vcpus to remain static. Otherwise ntp frequency + * correction applies to one vcpu's system_timestamp but not + * the others. + * + * So in those cases, request a kvmclock update for all vcpus. + * The worst case for a remote vcpu to update its kvmclock + * is then bounded by maximum nohz sleep latency. + */ + +static void kvm_gen_kvmclock_update(struct kvm_vcpu *v) +{ + int i; + struct kvm *kvm = v->kvm; + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(i, vcpu, kvm) { + set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests); + kvm_vcpu_kick(vcpu); + } +} + static bool msr_mtrr_valid(unsigned msr) { switch (msr) { @@ -1984,7 +2025,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) kvmclock_reset(vcpu); vcpu->arch.time = data; - kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); + kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu); /* we verify if the enable bit is set... */ if (!(data & 1)) @@ -2701,7 +2742,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) * kvmclock on vcpu->cpu migration */ if (!vcpu->kvm->arch.use_master_clock || vcpu->cpu == -1) - kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); + kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu); if (vcpu->cpu != cpu) kvm_migrate_timers(vcpu); vcpu->cpu = cpu; @@ -5238,7 +5279,13 @@ static void kvm_set_mmio_spte_mask(void) * Set the reserved bits and the present bit of an paging-structure * entry to generate page fault with PFER.RSV = 1. */ - mask = ((1ull << (62 - maxphyaddr + 1)) - 1) << maxphyaddr; + /* Mask the reserved physical address bits. */ + mask = ((1ull << (51 - maxphyaddr + 1)) - 1) << maxphyaddr; + + /* Bit 62 is always reserved for 32bit host. */ + mask |= 0x3ull << 62; + + /* Set the present bit. */ mask |= 1ull; #ifdef CONFIG_X86_64 @@ -5498,13 +5545,6 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) char instruction[3]; unsigned long rip = kvm_rip_read(vcpu); - /* - * Blow out the MMU to ensure that no other VCPU has an active mapping - * to ensure that the updated hypercall appears atomically across all - * VCPUs. - */ - kvm_mmu_zap_all(vcpu->kvm); - kvm_x86_ops->patch_hypercall(vcpu, instruction); return emulator_write_emulated(ctxt, rip, instruction, 3, NULL); @@ -5702,6 +5742,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) __kvm_migrate_timers(vcpu); if (kvm_check_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu)) kvm_gen_update_masterclock(vcpu->kvm); + if (kvm_check_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu)) + kvm_gen_kvmclock_update(vcpu); if (kvm_check_request(KVM_REQ_CLOCK_UPDATE, vcpu)) { r = kvm_guest_time_update(vcpu); if (unlikely(r)) @@ -6812,6 +6854,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) return -EINVAL; INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); + INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); /* Reserve bit 0 of irq_sources_bitmap for userspace irq source */ @@ -7040,22 +7083,18 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, * If memory slot is created, or moved, we need to clear all * mmio sptes. */ - if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) { - kvm_mmu_zap_mmio_sptes(kvm); - kvm_reload_remote_mmus(kvm); - } + kvm_mmu_invalidate_mmio_sptes(kvm); } void kvm_arch_flush_shadow_all(struct kvm *kvm) { - kvm_mmu_zap_all(kvm); - kvm_reload_remote_mmus(kvm); + kvm_mmu_invalidate_zap_all_pages(kvm); } void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { - kvm_arch_flush_shadow_all(kvm); + kvm_mmu_invalidate_zap_all_pages(kvm); } int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) @@ -7263,3 +7302,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_write_tsc_offset); diff --git a/arch/x86/lguest/Makefile b/arch/x86/lguest/Makefile index 94e0e54056a9..8f38d577a2fa 100644 --- a/arch/x86/lguest/Makefile +++ b/arch/x86/lguest/Makefile @@ -1,2 +1,2 @@ -obj-y := i386_head.o boot.o +obj-y := head_32.o boot.o CFLAGS_boot.o := $(call cc-option, -fno-stack-protector) diff --git a/arch/x86/lguest/i386_head.S b/arch/x86/lguest/head_32.S index 6ddfe4fc23c3..6ddfe4fc23c3 100644 --- a/arch/x86/lguest/i386_head.S +++ b/arch/x86/lguest/head_32.S diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 3e724256dbee..d641897a1f4e 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -324,14 +324,11 @@ setup_resource(struct acpi_resource *acpi_res, void *data) res->start = start; res->end = end; info->res_offset[info->res_num] = addr.translation_offset; + info->res_num++; - if (!pci_use_crs) { + if (!pci_use_crs) dev_printk(KERN_DEBUG, &info->bridge->dev, "host bridge window %pR (ignored)\n", res); - return AE_OK; - } - - info->res_num++; return AE_OK; } diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index d99cae8147d1..c1367b29c3b1 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -40,11 +40,15 @@ cpumask_var_t xen_cpu_initialized_map; -static DEFINE_PER_CPU(int, xen_resched_irq); -static DEFINE_PER_CPU(int, xen_callfunc_irq); -static DEFINE_PER_CPU(int, xen_callfuncsingle_irq); -static DEFINE_PER_CPU(int, xen_irq_work); -static DEFINE_PER_CPU(int, xen_debug_irq) = -1; +struct xen_common_irq { + int irq; + char *name; +}; +static DEFINE_PER_CPU(struct xen_common_irq, xen_resched_irq) = { .irq = -1 }; +static DEFINE_PER_CPU(struct xen_common_irq, xen_callfunc_irq) = { .irq = -1 }; +static DEFINE_PER_CPU(struct xen_common_irq, xen_callfuncsingle_irq) = { .irq = -1 }; +static DEFINE_PER_CPU(struct xen_common_irq, xen_irq_work) = { .irq = -1 }; +static DEFINE_PER_CPU(struct xen_common_irq, xen_debug_irq) = { .irq = -1 }; static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id); static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id); @@ -99,10 +103,47 @@ static void __cpuinit cpu_bringup_and_idle(void) cpu_startup_entry(CPUHP_ONLINE); } +static void xen_smp_intr_free(unsigned int cpu) +{ + if (per_cpu(xen_resched_irq, cpu).irq >= 0) { + unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu).irq, NULL); + per_cpu(xen_resched_irq, cpu).irq = -1; + kfree(per_cpu(xen_resched_irq, cpu).name); + per_cpu(xen_resched_irq, cpu).name = NULL; + } + if (per_cpu(xen_callfunc_irq, cpu).irq >= 0) { + unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu).irq, NULL); + per_cpu(xen_callfunc_irq, cpu).irq = -1; + kfree(per_cpu(xen_callfunc_irq, cpu).name); + per_cpu(xen_callfunc_irq, cpu).name = NULL; + } + if (per_cpu(xen_debug_irq, cpu).irq >= 0) { + unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu).irq, NULL); + per_cpu(xen_debug_irq, cpu).irq = -1; + kfree(per_cpu(xen_debug_irq, cpu).name); + per_cpu(xen_debug_irq, cpu).name = NULL; + } + if (per_cpu(xen_callfuncsingle_irq, cpu).irq >= 0) { + unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu).irq, + NULL); + per_cpu(xen_callfuncsingle_irq, cpu).irq = -1; + kfree(per_cpu(xen_callfuncsingle_irq, cpu).name); + per_cpu(xen_callfuncsingle_irq, cpu).name = NULL; + } + if (xen_hvm_domain()) + return; + + if (per_cpu(xen_irq_work, cpu).irq >= 0) { + unbind_from_irqhandler(per_cpu(xen_irq_work, cpu).irq, NULL); + per_cpu(xen_irq_work, cpu).irq = -1; + kfree(per_cpu(xen_irq_work, cpu).name); + per_cpu(xen_irq_work, cpu).name = NULL; + } +}; static int xen_smp_intr_init(unsigned int cpu) { int rc; - const char *resched_name, *callfunc_name, *debug_name; + char *resched_name, *callfunc_name, *debug_name; resched_name = kasprintf(GFP_KERNEL, "resched%d", cpu); rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR, @@ -113,7 +154,8 @@ static int xen_smp_intr_init(unsigned int cpu) NULL); if (rc < 0) goto fail; - per_cpu(xen_resched_irq, cpu) = rc; + per_cpu(xen_resched_irq, cpu).irq = rc; + per_cpu(xen_resched_irq, cpu).name = resched_name; callfunc_name = kasprintf(GFP_KERNEL, "callfunc%d", cpu); rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_VECTOR, @@ -124,7 +166,8 @@ static int xen_smp_intr_init(unsigned int cpu) NULL); if (rc < 0) goto fail; - per_cpu(xen_callfunc_irq, cpu) = rc; + per_cpu(xen_callfunc_irq, cpu).irq = rc; + per_cpu(xen_callfunc_irq, cpu).name = callfunc_name; debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu); rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu, xen_debug_interrupt, @@ -132,7 +175,8 @@ static int xen_smp_intr_init(unsigned int cpu) debug_name, NULL); if (rc < 0) goto fail; - per_cpu(xen_debug_irq, cpu) = rc; + per_cpu(xen_debug_irq, cpu).irq = rc; + per_cpu(xen_debug_irq, cpu).name = debug_name; callfunc_name = kasprintf(GFP_KERNEL, "callfuncsingle%d", cpu); rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR, @@ -143,7 +187,8 @@ static int xen_smp_intr_init(unsigned int cpu) NULL); if (rc < 0) goto fail; - per_cpu(xen_callfuncsingle_irq, cpu) = rc; + per_cpu(xen_callfuncsingle_irq, cpu).irq = rc; + per_cpu(xen_callfuncsingle_irq, cpu).name = callfunc_name; /* * The IRQ worker on PVHVM goes through the native path and uses the @@ -161,26 +206,13 @@ static int xen_smp_intr_init(unsigned int cpu) NULL); if (rc < 0) goto fail; - per_cpu(xen_irq_work, cpu) = rc; + per_cpu(xen_irq_work, cpu).irq = rc; + per_cpu(xen_irq_work, cpu).name = callfunc_name; return 0; fail: - if (per_cpu(xen_resched_irq, cpu) >= 0) - unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu), NULL); - if (per_cpu(xen_callfunc_irq, cpu) >= 0) - unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL); - if (per_cpu(xen_debug_irq, cpu) >= 0) - unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL); - if (per_cpu(xen_callfuncsingle_irq, cpu) >= 0) - unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), - NULL); - if (xen_hvm_domain()) - return rc; - - if (per_cpu(xen_irq_work, cpu) >= 0) - unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL); - + xen_smp_intr_free(cpu); return rc; } @@ -433,12 +465,7 @@ static void xen_cpu_die(unsigned int cpu) current->state = TASK_UNINTERRUPTIBLE; schedule_timeout(HZ/10); } - unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu), NULL); - unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL); - unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL); - unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL); - if (!xen_hvm_domain()) - unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL); + xen_smp_intr_free(cpu); xen_uninit_lock_cpu(cpu); xen_teardown_timer(cpu); } diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 3002ec1bb71a..a40f8508e760 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -7,6 +7,7 @@ #include <linux/debugfs.h> #include <linux/log2.h> #include <linux/gfp.h> +#include <linux/slab.h> #include <asm/paravirt.h> @@ -165,6 +166,7 @@ static int xen_spin_trylock(struct arch_spinlock *lock) return old == 0; } +static DEFINE_PER_CPU(char *, irq_name); static DEFINE_PER_CPU(int, lock_kicker_irq) = -1; static DEFINE_PER_CPU(struct xen_spinlock *, lock_spinners); @@ -362,7 +364,7 @@ static irqreturn_t dummy_handler(int irq, void *dev_id) void __cpuinit xen_init_lock_cpu(int cpu) { int irq; - const char *name; + char *name; WARN(per_cpu(lock_kicker_irq, cpu) >= 0, "spinlock on CPU%d exists on IRQ%d!\n", cpu, per_cpu(lock_kicker_irq, cpu)); @@ -385,6 +387,7 @@ void __cpuinit xen_init_lock_cpu(int cpu) if (irq >= 0) { disable_irq(irq); /* make sure it's never delivered */ per_cpu(lock_kicker_irq, cpu) = irq; + per_cpu(irq_name, cpu) = name; } printk("cpu %d spinlock event irq %d\n", cpu, irq); @@ -401,6 +404,8 @@ void xen_uninit_lock_cpu(int cpu) unbind_from_irqhandler(per_cpu(lock_kicker_irq, cpu), NULL); per_cpu(lock_kicker_irq, cpu) = -1; + kfree(per_cpu(irq_name, cpu)); + per_cpu(irq_name, cpu) = NULL; } void __init xen_init_spinlocks(void) diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 3d88bfdf9e1c..a690868be837 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -14,6 +14,7 @@ #include <linux/kernel_stat.h> #include <linux/math64.h> #include <linux/gfp.h> +#include <linux/slab.h> #include <asm/pvclock.h> #include <asm/xen/hypervisor.h> @@ -36,9 +37,8 @@ static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate); /* snapshots of runstate info */ static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate_snapshot); -/* unused ns of stolen and blocked time */ +/* unused ns of stolen time */ static DEFINE_PER_CPU(u64, xen_residual_stolen); -static DEFINE_PER_CPU(u64, xen_residual_blocked); /* return an consistent snapshot of 64-bit time/counter value */ static u64 get64(const u64 *p) @@ -115,7 +115,7 @@ static void do_stolen_accounting(void) { struct vcpu_runstate_info state; struct vcpu_runstate_info *snap; - s64 blocked, runnable, offline, stolen; + s64 runnable, offline, stolen; cputime_t ticks; get_runstate_snapshot(&state); @@ -125,7 +125,6 @@ static void do_stolen_accounting(void) snap = &__get_cpu_var(xen_runstate_snapshot); /* work out how much time the VCPU has not been runn*ing* */ - blocked = state.time[RUNSTATE_blocked] - snap->time[RUNSTATE_blocked]; runnable = state.time[RUNSTATE_runnable] - snap->time[RUNSTATE_runnable]; offline = state.time[RUNSTATE_offline] - snap->time[RUNSTATE_offline]; @@ -141,17 +140,6 @@ static void do_stolen_accounting(void) ticks = iter_div_u64_rem(stolen, NS_PER_TICK, &stolen); __this_cpu_write(xen_residual_stolen, stolen); account_steal_ticks(ticks); - - /* Add the appropriate number of ticks of blocked time, - including any left-overs from last time. */ - blocked += __this_cpu_read(xen_residual_blocked); - - if (blocked < 0) - blocked = 0; - - ticks = iter_div_u64_rem(blocked, NS_PER_TICK, &blocked); - __this_cpu_write(xen_residual_blocked, blocked); - account_idle_ticks(ticks); } /* Get the TSC speed from Xen */ @@ -377,11 +365,16 @@ static const struct clock_event_device xen_vcpuop_clockevent = { static const struct clock_event_device *xen_clockevent = &xen_timerop_clockevent; -static DEFINE_PER_CPU(struct clock_event_device, xen_clock_events) = { .irq = -1 }; + +struct xen_clock_event_device { + struct clock_event_device evt; + char *name; +}; +static DEFINE_PER_CPU(struct xen_clock_event_device, xen_clock_events) = { .evt.irq = -1 }; static irqreturn_t xen_timer_interrupt(int irq, void *dev_id) { - struct clock_event_device *evt = &__get_cpu_var(xen_clock_events); + struct clock_event_device *evt = &__get_cpu_var(xen_clock_events).evt; irqreturn_t ret; ret = IRQ_NONE; @@ -395,14 +388,30 @@ static irqreturn_t xen_timer_interrupt(int irq, void *dev_id) return ret; } +void xen_teardown_timer(int cpu) +{ + struct clock_event_device *evt; + BUG_ON(cpu == 0); + evt = &per_cpu(xen_clock_events, cpu).evt; + + if (evt->irq >= 0) { + unbind_from_irqhandler(evt->irq, NULL); + evt->irq = -1; + kfree(per_cpu(xen_clock_events, cpu).name); + per_cpu(xen_clock_events, cpu).name = NULL; + } +} + void xen_setup_timer(int cpu) { - const char *name; + char *name; struct clock_event_device *evt; int irq; - evt = &per_cpu(xen_clock_events, cpu); + evt = &per_cpu(xen_clock_events, cpu).evt; WARN(evt->irq >= 0, "IRQ%d for CPU%d is already allocated\n", evt->irq, cpu); + if (evt->irq >= 0) + xen_teardown_timer(cpu); printk(KERN_INFO "installing Xen timer for CPU %d\n", cpu); @@ -420,22 +429,15 @@ void xen_setup_timer(int cpu) evt->cpumask = cpumask_of(cpu); evt->irq = irq; + per_cpu(xen_clock_events, cpu).name = name; } -void xen_teardown_timer(int cpu) -{ - struct clock_event_device *evt; - BUG_ON(cpu == 0); - evt = &per_cpu(xen_clock_events, cpu); - unbind_from_irqhandler(evt->irq, NULL); - evt->irq = -1; -} void xen_setup_cpu_clockevents(void) { BUG_ON(preemptible()); - clockevents_register_device(&__get_cpu_var(xen_clock_events)); + clockevents_register_device(&__get_cpu_var(xen_clock_events).evt); } void xen_timer_resume(void) |