diff options
Diffstat (limited to 'arch/arc/include')
24 files changed, 411 insertions, 258 deletions
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild index d8dd660898b9..5943f7f9d325 100644 --- a/arch/arc/include/asm/Kbuild +++ b/arch/arc/include/asm/Kbuild @@ -46,3 +46,4 @@ generic-y += ucontext.h generic-y += user.h generic-y += vga.h generic-y += xor.h +generic-y += preempt.h diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h index 5802849a6cae..2fd3162ec4df 100644 --- a/arch/arc/include/asm/cache.h +++ b/arch/arc/include/asm/cache.h @@ -17,13 +17,7 @@ #endif #define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT) - -/* 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)) +#define CACHE_LINE_MASK (~(L1_CACHE_BYTES - 1)) /* * ARC700 doesn't cache any access in top 256M. @@ -57,7 +51,7 @@ 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); +extern void read_decode_cache_bcr(void); #endif /* !__ASSEMBLY__ */ diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h index 442ce5d0f709..43de30256981 100644 --- a/arch/arc/include/asm/delay.h +++ b/arch/arc/include/asm/delay.h @@ -53,11 +53,10 @@ static inline void __udelay(unsigned long usecs) { unsigned long loops; - /* (long long) cast ensures 64 bit MPY - real or emulated + /* (u64) cast ensures 64 bit MPY - real or emulated * HZ * 4295 is pre-evaluated by gcc - hence only 2 mpy ops */ - loops = ((long long)(usecs * 4295 * HZ) * - (long long)(loops_per_jiffy)) >> 32; + loops = ((u64) usecs * 4295 * HZ * loops_per_jiffy) >> 32; __delay(loops); } diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h index df57611652e5..884081099f80 100644 --- a/arch/arc/include/asm/entry.h +++ b/arch/arc/include/asm/entry.h @@ -365,7 +365,7 @@ * it to memory (non-SMP case) or SCRATCH0 Aux Reg (SMP). * * Before saving the full regfile - this reg is restored back, only - * to be saved again on kernel mode stack, as part of ptregs. + * to be saved again on kernel mode stack, as part of pt_regs. *-------------------------------------------------------------*/ .macro EXCPN_PROLOG_FREEUP_REG reg #ifdef CONFIG_SMP @@ -384,6 +384,28 @@ .endm /*-------------------------------------------------------------- + * Exception Entry prologue + * -Switches stack to K mode (if not already) + * -Saves the register file + * + * After this it is safe to call the "C" handlers + *-------------------------------------------------------------*/ +.macro EXCEPTION_PROLOGUE + + /* Need at least 1 reg to code the early exception prologue */ + EXCPN_PROLOG_FREEUP_REG r9 + + /* U/K mode at time of exception (stack not switched if already K) */ + lr r9, [erstatus] + + /* ARC700 doesn't provide auto-stack switching */ + SWITCH_TO_KERNEL_STK + + /* save the regfile */ + SAVE_ALL_SYS +.endm + +/*-------------------------------------------------------------- * Save all registers used by Exceptions (TLB Miss, Prot-V, Mem err etc) * Requires SP to be already switched to kernel mode Stack * sp points to the next free element on the stack at exit of this macro. diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h index 473424d7528b..334ce7017a18 100644 --- a/arch/arc/include/asm/io.h +++ b/arch/arc/include/asm/io.h @@ -100,6 +100,10 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr) } +#define readb_relaxed readb +#define readw_relaxed readw +#define readl_relaxed readl + #include <asm-generic/io.h> #endif /* _ASM_ARC_IO_H */ diff --git a/arch/arc/include/asm/irq.h b/arch/arc/include/asm/irq.h index c0a72105ee0b..291a70db68b8 100644 --- a/arch/arc/include/asm/irq.h +++ b/arch/arc/include/asm/irq.h @@ -18,8 +18,8 @@ #include <asm-generic/irq.h> -extern void __init arc_init_IRQ(void); -extern int __init get_hw_config_num_irq(void); +extern void arc_init_IRQ(void); +extern int get_hw_config_num_irq(void); void arc_local_timer_setup(unsigned int cpu); diff --git a/arch/arc/include/asm/irqflags.h b/arch/arc/include/asm/irqflags.h index d99f79bcf865..cb7efc29f16f 100644 --- a/arch/arc/include/asm/irqflags.h +++ b/arch/arc/include/asm/irqflags.h @@ -151,23 +151,38 @@ static inline void arch_unmask_irq(unsigned int irq) #else -.macro IRQ_DISABLE scratch - lr \scratch, [status32] - bic \scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK) - flag \scratch +#ifdef CONFIG_TRACE_IRQFLAGS + +.macro TRACE_ASM_IRQ_DISABLE + bl trace_hardirqs_off +.endm + +.macro TRACE_ASM_IRQ_ENABLE + bl trace_hardirqs_on +.endm + +#else + +.macro TRACE_ASM_IRQ_DISABLE +.endm + +.macro TRACE_ASM_IRQ_ENABLE .endm -.macro IRQ_DISABLE_SAVE scratch, save +#endif + +.macro IRQ_DISABLE scratch lr \scratch, [status32] - mov \save, \scratch /* Make a copy */ bic \scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK) flag \scratch + TRACE_ASM_IRQ_DISABLE .endm .macro IRQ_ENABLE scratch lr \scratch, [status32] or \scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK) flag \scratch + TRACE_ASM_IRQ_ENABLE .endm #endif /* __ASSEMBLY__ */ diff --git a/arch/arc/include/asm/mach_desc.h b/arch/arc/include/asm/mach_desc.h index 9998dc846ebb..e8993a2be6c2 100644 --- a/arch/arc/include/asm/mach_desc.h +++ b/arch/arc/include/asm/mach_desc.h @@ -51,22 +51,12 @@ struct machine_desc { /* * Current machine - only accessible during boot. */ -extern struct machine_desc *machine_desc; +extern const struct machine_desc *machine_desc; /* * Machine type table - also only accessible during boot */ -extern struct machine_desc __arch_info_begin[], __arch_info_end[]; -#define for_each_machine_desc(p) \ - for (p = __arch_info_begin; p < __arch_info_end; p++) - -static inline struct machine_desc *default_machine_desc(void) -{ - /* the default machine is the last one linked in */ - if (__arch_info_end - 1 < __arch_info_begin) - return NULL; - return __arch_info_end - 1; -} +extern const struct machine_desc __arch_info_begin[], __arch_info_end[]; /* * Set of macros to define architecture features. @@ -81,7 +71,6 @@ __attribute__((__section__(".arch.info.init"))) = { \ #define MACHINE_END \ }; -extern struct machine_desc *setup_machine_fdt(void *dt); -extern void __init copy_devtree(void); +extern const struct machine_desc *setup_machine_fdt(void *dt); #endif diff --git a/arch/arc/include/asm/mmu.h b/arch/arc/include/asm/mmu.h index 7c03fe61759c..8c84ae98c337 100644 --- a/arch/arc/include/asm/mmu.h +++ b/arch/arc/include/asm/mmu.h @@ -32,6 +32,8 @@ /* Error code if probe fails */ #define TLB_LKUP_ERR 0x80000000 +#define TLB_DUP_ERR (TLB_LKUP_ERR | 0x00000001) + /* TLB Commands */ #define TLBWrite 0x1 #define TLBRead 0x2 @@ -46,21 +48,18 @@ #ifndef __ASSEMBLY__ typedef struct { - unsigned long asid; /* Pvt Addr-Space ID for mm */ -#ifdef CONFIG_ARC_TLB_DBG - struct task_struct *tsk; -#endif + unsigned long asid[NR_CPUS]; /* 8 bit MMU PID + Generation cycle */ } mm_context_t; #ifdef CONFIG_ARC_DBG_TLB_PARANOIA -void tlb_paranoid_check(unsigned int pid_sw, unsigned long address); +void tlb_paranoid_check(unsigned int mm_asid, 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); +void read_decode_mmu_bcr(void); #endif /* !__ASSEMBLY__ */ diff --git a/arch/arc/include/asm/mmu_context.h b/arch/arc/include/asm/mmu_context.h index 0d71fb11b57c..1fd467ef658f 100644 --- a/arch/arc/include/asm/mmu_context.h +++ b/arch/arc/include/asm/mmu_context.h @@ -30,99 +30,72 @@ * "Fast Context Switch" i.e. no TLB flush on ctxt-switch * * Linux assigns each task a unique ASID. A simple round-robin allocation - * of H/w ASID is done using software tracker @asid_cache. + * of H/w ASID is done using software tracker @asid_cpu. * When it reaches max 255, the allocation cycle starts afresh by flushing * the entire TLB and wrapping ASID back to zero. * - * For book-keeping, Linux uses a couple of data-structures: - * -mm_struct has an @asid field to keep a note of task's ASID (needed at the - * time of say switch_mm( ) - * -An array of mm structs @asid_mm_map[] for asid->mm the reverse mapping, - * given an ASID, finding the mm struct associated. - * - * The round-robin allocation algorithm allows for ASID stealing. - * If asid tracker is at "x-1", a new req will allocate "x", even if "x" was - * already assigned to another (switched-out) task. Obviously the prev owner - * is marked with an invalid ASID to make it request for a new ASID when it - * gets scheduled next time. However its TLB entries (with ASID "x") could - * exist, which must be cleared before the same ASID is used by the new owner. - * Flushing them would be plausible but costly solution. Instead we force a - * allocation policy quirk, which ensures that a stolen ASID won't have any - * TLB entries associates, alleviating the need to flush. - * The quirk essentially is not allowing ASID allocated in prev cycle - * to be used past a roll-over in the next cycle. - * When this happens (i.e. task ASID > asid tracker), task needs to refresh - * its ASID, aligning it to current value of tracker. If the task doesn't get - * scheduled past a roll-over, hence its ASID is not yet realigned with - * tracker, such ASID is anyways safely reusable because it is - * gauranteed that TLB entries with that ASID wont exist. + * A new allocation cycle, post rollover, could potentially reassign an ASID + * to a different task. Thus the rule is to refresh the ASID in a new cycle. + * The 32 bit @asid_cpu (and mm->asid) have 8 bits MMU PID and rest 24 bits + * serve as cycle/generation indicator and natural 32 bit unsigned math + * automagically increments the generation when lower 8 bits rollover. */ -#define FIRST_ASID 0 -#define MAX_ASID 255 /* 8 bit PID field in PID Aux reg */ -#define NO_ASID (MAX_ASID + 1) /* ASID Not alloc to mmu ctxt */ -#define NUM_ASID ((MAX_ASID - FIRST_ASID) + 1) +#define MM_CTXT_ASID_MASK 0x000000ff /* MMU PID reg :8 bit PID */ +#define MM_CTXT_CYCLE_MASK (~MM_CTXT_ASID_MASK) + +#define MM_CTXT_FIRST_CYCLE (MM_CTXT_ASID_MASK + 1) +#define MM_CTXT_NO_ASID 0UL -/* ASID to mm struct mapping */ -extern struct mm_struct *asid_mm_map[NUM_ASID + 1]; +#define asid_mm(mm, cpu) mm->context.asid[cpu] +#define hw_pid(mm, cpu) (asid_mm(mm, cpu) & MM_CTXT_ASID_MASK) -extern int asid_cache; +DECLARE_PER_CPU(unsigned int, asid_cache); +#define asid_cpu(cpu) per_cpu(asid_cache, cpu) /* - * Assign a new ASID to task. If the task already has an ASID, it is - * relinquished. + * Get a new ASID if task doesn't have a valid one (unalloc or from prev cycle) + * Also set the MMU PID register to existing/updated ASID */ static inline void get_new_mmu_context(struct mm_struct *mm) { - struct mm_struct *prev_owner; + const unsigned int cpu = smp_processor_id(); unsigned long flags; local_irq_save(flags); /* - * Relinquish the currently owned ASID (if any). - * Doing unconditionally saves a cmp-n-branch; for already unused - * ASID slot, the value was/remains NULL + * Move to new ASID if it was not from current alloc-cycle/generation. + * This is done by ensuring that the generation bits in both mm->ASID + * and cpu's ASID counter are exactly same. + * + * Note: Callers needing new ASID unconditionally, independent of + * generation, e.g. local_flush_tlb_mm() for forking parent, + * first need to destroy the context, setting it to invalid + * value. */ - asid_mm_map[mm->context.asid] = (struct mm_struct *)NULL; + if (!((asid_mm(mm, cpu) ^ asid_cpu(cpu)) & MM_CTXT_CYCLE_MASK)) + goto set_hw; - /* move to new ASID */ - if (++asid_cache > MAX_ASID) { /* ASID roll-over */ - asid_cache = FIRST_ASID; - flush_tlb_all(); - } + /* move to new ASID and handle rollover */ + if (unlikely(!(++asid_cpu(cpu) & MM_CTXT_ASID_MASK))) { - /* - * Is next ASID already owned by some-one else (we are stealing it). - * If so, let the orig owner be aware of this, so when it runs, it - * asks for a brand new ASID. This would only happen for a long-lived - * task with ASID from prev allocation cycle (before ASID roll-over). - * - * This might look wrong - if we are re-using some other task's ASID, - * won't we use it's stale TLB entries too. Actually switch_mm( ) takes - * care of such a case: it ensures that task with ASID from prev alloc - * cycle, when scheduled will refresh it's ASID: see switch_mm( ) below - * The stealing scenario described here will only happen if that task - * didn't get a chance to refresh it's ASID - implying stale entries - * won't exist. - */ - prev_owner = asid_mm_map[asid_cache]; - if (prev_owner) - prev_owner->context.asid = NO_ASID; + local_flush_tlb_all(); + + /* + * Above checke for rollover of 8 bit ASID in 32 bit container. + * If the container itself wrapped around, set it to a non zero + * "generation" to distinguish from no context + */ + if (!asid_cpu(cpu)) + asid_cpu(cpu) = MM_CTXT_FIRST_CYCLE; + } /* Assign new ASID to tsk */ - asid_mm_map[asid_cache] = mm; - mm->context.asid = asid_cache; - -#ifdef CONFIG_ARC_TLB_DBG - pr_info("ARC_TLB_DBG: NewMM=0x%x OldMM=0x%x task_struct=0x%x Task: %s," - " pid:%u, assigned asid:%lu\n", - (unsigned int)mm, (unsigned int)prev_owner, - (unsigned int)(mm->context.tsk), (mm->context.tsk)->comm, - (mm->context.tsk)->pid, mm->context.asid); -#endif + asid_mm(mm, cpu) = asid_cpu(cpu); - write_aux_reg(ARC_REG_PID, asid_cache | MMU_ENABLE); +set_hw: + write_aux_reg(ARC_REG_PID, hw_pid(mm, cpu) | MMU_ENABLE); local_irq_restore(flags); } @@ -134,59 +107,61 @@ static inline void get_new_mmu_context(struct mm_struct *mm) static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { - mm->context.asid = NO_ASID; -#ifdef CONFIG_ARC_TLB_DBG - mm->context.tsk = tsk; -#endif + int i; + + for_each_possible_cpu(i) + asid_mm(mm, i) = MM_CTXT_NO_ASID; + return 0; } +static inline void destroy_context(struct mm_struct *mm) +{ + unsigned long flags; + + /* Needed to elide CONFIG_DEBUG_PREEMPT warning */ + local_irq_save(flags); + asid_mm(mm, smp_processor_id()) = MM_CTXT_NO_ASID; + local_irq_restore(flags); +} + /* Prepare the MMU for task: setup PID reg with allocated ASID If task doesn't have an ASID (never alloc or stolen, get a new ASID) */ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { + const int cpu = smp_processor_id(); + + /* + * Note that the mm_cpumask is "aggregating" only, we don't clear it + * for the switched-out task, unlike some other arches. + * It is used to enlist cpus for sending TLB flush IPIs and not sending + * it to CPUs where a task once ran-on, could cause stale TLB entry + * re-use, specially for a multi-threaded task. + * e.g. T1 runs on C1, migrates to C3. T2 running on C2 munmaps. + * For a non-aggregating mm_cpumask, IPI not sent C1, and if T1 + * were to re-migrate to C1, it could access the unmapped region + * via any existing stale TLB entries. + */ + cpumask_set_cpu(cpu, mm_cpumask(next)); + #ifndef CONFIG_SMP /* PGD cached in MMU reg to avoid 3 mem lookups: task->mm->pgd */ write_aux_reg(ARC_REG_SCRATCH_DATA0, next->pgd); #endif - /* - * Get a new ASID if task doesn't have a valid one. Possible when - * -task never had an ASID (fresh after fork) - * -it's ASID was stolen - past an ASID roll-over. - * -There's a third obscure scenario (if this task is running for the - * first time afer an ASID rollover), where despite having a valid - * ASID, we force a get for new ASID - see comments at top. - * - * Both the non-alloc scenario and first-use-after-rollover can be - * detected using the single condition below: NO_ASID = 256 - * while asid_cache is always a valid ASID value (0-255). - */ - if (next->context.asid > asid_cache) { - get_new_mmu_context(next); - } else { - /* - * XXX: This will never happen given the chks above - * BUG_ON(next->context.asid > MAX_ASID); - */ - write_aux_reg(ARC_REG_PID, next->context.asid | MMU_ENABLE); - } - + get_new_mmu_context(next); } -static inline void destroy_context(struct mm_struct *mm) -{ - unsigned long flags; - - local_irq_save(flags); - - asid_mm_map[mm->context.asid] = NULL; - mm->context.asid = NO_ASID; - - local_irq_restore(flags); -} +/* + * Called at the time of execve() to get a new ASID + * Note the subtlety here: get_new_mmu_context() behaves differently here + * vs. in switch_mm(). Here it always returns a new ASID, because mm has + * an unallocated "initial" value, while in latter, it moves to a new ASID, + * only if it was unallocated + */ +#define activate_mm(prev, next) switch_mm(prev, next, NULL) /* it seemed that deactivate_mm( ) is a reasonable place to do book-keeping * for retiring-mm. However destroy_context( ) still needs to do that because @@ -197,17 +172,6 @@ static inline void destroy_context(struct mm_struct *mm) */ #define deactivate_mm(tsk, mm) do { } while (0) -static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next) -{ -#ifndef CONFIG_SMP - write_aux_reg(ARC_REG_SCRATCH_DATA0, next->pgd); -#endif - - /* Unconditionally get a new ASID */ - get_new_mmu_context(next); - -} - #define enter_lazy_tlb(mm, tsk) #endif /* __ASM_ARC_MMU_CONTEXT_H */ diff --git a/arch/arc/include/asm/perf_event.h b/arch/arc/include/asm/perf_event.h index 115ad96480e6..cbf755e32a03 100644 --- a/arch/arc/include/asm/perf_event.h +++ b/arch/arc/include/asm/perf_event.h @@ -1,5 +1,7 @@ /* - * Copyright (C) 2011-2012 Synopsys, Inc. (www.synopsys.com) + * Linux performance counter support for ARC + * + * Copyright (C) 2011-2013 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 @@ -10,4 +12,204 @@ #ifndef __ASM_PERF_EVENT_H #define __ASM_PERF_EVENT_H +/* real maximum varies per CPU, this is the maximum supported by the driver */ +#define ARC_PMU_MAX_HWEVENTS 64 + +#define ARC_REG_CC_BUILD 0xF6 +#define ARC_REG_CC_INDEX 0x240 +#define ARC_REG_CC_NAME0 0x241 +#define ARC_REG_CC_NAME1 0x242 + +#define ARC_REG_PCT_BUILD 0xF5 +#define ARC_REG_PCT_COUNTL 0x250 +#define ARC_REG_PCT_COUNTH 0x251 +#define ARC_REG_PCT_SNAPL 0x252 +#define ARC_REG_PCT_SNAPH 0x253 +#define ARC_REG_PCT_CONFIG 0x254 +#define ARC_REG_PCT_CONTROL 0x255 +#define ARC_REG_PCT_INDEX 0x256 + +#define ARC_REG_PCT_CONTROL_CC (1 << 16) /* clear counts */ +#define ARC_REG_PCT_CONTROL_SN (1 << 17) /* snapshot */ + +struct arc_reg_pct_build { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int m:8, c:8, r:6, s:2, v:8; +#else + unsigned int v:8, s:2, r:6, c:8, m:8; +#endif +}; + +struct arc_reg_cc_build { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int c:16, r:8, v:8; +#else + unsigned int v:8, r:8, c:16; +#endif +}; + +#define PERF_COUNT_ARC_DCLM (PERF_COUNT_HW_MAX + 0) +#define PERF_COUNT_ARC_DCSM (PERF_COUNT_HW_MAX + 1) +#define PERF_COUNT_ARC_ICM (PERF_COUNT_HW_MAX + 2) +#define PERF_COUNT_ARC_BPOK (PERF_COUNT_HW_MAX + 3) +#define PERF_COUNT_ARC_EDTLB (PERF_COUNT_HW_MAX + 4) +#define PERF_COUNT_ARC_EITLB (PERF_COUNT_HW_MAX + 5) +#define PERF_COUNT_ARC_HW_MAX (PERF_COUNT_HW_MAX + 6) + +/* + * The "generalized" performance events seem to really be a copy + * of the available events on x86 processors; the mapping to ARC + * events is not always possible 1-to-1. Fortunately, there doesn't + * seem to be an exact definition for these events, so we can cheat + * a bit where necessary. + * + * In particular, the following PERF events may behave a bit differently + * compared to other architectures: + * + * PERF_COUNT_HW_CPU_CYCLES + * Cycles not in halted state + * + * PERF_COUNT_HW_REF_CPU_CYCLES + * Reference cycles not in halted state, same as PERF_COUNT_HW_CPU_CYCLES + * for now as we don't do Dynamic Voltage/Frequency Scaling (yet) + * + * PERF_COUNT_HW_BUS_CYCLES + * Unclear what this means, Intel uses 0x013c, which according to + * their datasheet means "unhalted reference cycles". It sounds similar + * to PERF_COUNT_HW_REF_CPU_CYCLES, and we use the same counter for it. + * + * PERF_COUNT_HW_STALLED_CYCLES_BACKEND + * PERF_COUNT_HW_STALLED_CYCLES_FRONTEND + * The ARC 700 can either measure stalls per pipeline stage, or all stalls + * combined; for now we assign all stalls to STALLED_CYCLES_BACKEND + * and all pipeline flushes (e.g. caused by mispredicts, etc.) to + * STALLED_CYCLES_FRONTEND. + * + * We could start multiple performance counters and combine everything + * afterwards, but that makes it complicated. + * + * Note that I$ cache misses aren't counted by either of the two! + */ + +static const char * const arc_pmu_ev_hw_map[] = { + [PERF_COUNT_HW_CPU_CYCLES] = "crun", + [PERF_COUNT_HW_REF_CPU_CYCLES] = "crun", + [PERF_COUNT_HW_BUS_CYCLES] = "crun", + [PERF_COUNT_HW_INSTRUCTIONS] = "iall", + [PERF_COUNT_HW_BRANCH_MISSES] = "bpfail", + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmp", + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = "bflush", + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = "bstall", + [PERF_COUNT_ARC_DCLM] = "dclm", + [PERF_COUNT_ARC_DCSM] = "dcsm", + [PERF_COUNT_ARC_ICM] = "icm", + [PERF_COUNT_ARC_BPOK] = "bpok", + [PERF_COUNT_ARC_EDTLB] = "edtlb", + [PERF_COUNT_ARC_EITLB] = "eitlb", +}; + +#define C(_x) PERF_COUNT_HW_CACHE_##_x +#define CACHE_OP_UNSUPPORTED 0xffff + +static const unsigned arc_pmu_cache_map[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { + [C(L1D)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = PERF_COUNT_ARC_DCLM, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = PERF_COUNT_ARC_DCSM, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(L1I)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = PERF_COUNT_ARC_ICM, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(DTLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = PERF_COUNT_ARC_EDTLB, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(ITLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = PERF_COUNT_ARC_EITLB, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(BPU)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = PERF_COUNT_HW_BRANCH_INSTRUCTIONS, + [C(RESULT_MISS)] = PERF_COUNT_HW_BRANCH_MISSES, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(NODE)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, +}; + #endif /* __ASM_PERF_EVENT_H */ diff --git a/arch/arc/include/asm/pgalloc.h b/arch/arc/include/asm/pgalloc.h index 36a9f20c21a3..81208bfd9dcb 100644 --- a/arch/arc/include/asm/pgalloc.h +++ b/arch/arc/include/asm/pgalloc.h @@ -105,11 +105,16 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) { pgtable_t pte_pg; + struct page *page; pte_pg = __get_free_pages(GFP_KERNEL | __GFP_REPEAT, __get_order_pte()); - if (pte_pg) { - memzero((void *)pte_pg, PTRS_PER_PTE * 4); - pgtable_page_ctor(virt_to_page(pte_pg)); + if (!pte_pg) + return 0; + memzero((void *)pte_pg, PTRS_PER_PTE * 4); + page = virt_to_page(pte_pg); + if (!pgtable_page_ctor(page)) { + __free_page(page); + return 0; } return pte_pg; diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index 4749a0eee1cf..6b0b7f7ef783 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -57,43 +57,31 @@ #define _PAGE_ACCESSED (1<<1) /* Page is accessed (S) */ #define _PAGE_CACHEABLE (1<<2) /* Page is cached (H) */ -#define _PAGE_U_EXECUTE (1<<3) /* Page has user execute perm (H) */ -#define _PAGE_U_WRITE (1<<4) /* Page has user write perm (H) */ -#define _PAGE_U_READ (1<<5) /* Page has user read perm (H) */ -#define _PAGE_K_EXECUTE (1<<6) /* Page has kernel execute perm (H) */ -#define _PAGE_K_WRITE (1<<7) /* Page has kernel write perm (H) */ -#define _PAGE_K_READ (1<<8) /* Page has kernel perm (H) */ -#define _PAGE_GLOBAL (1<<9) /* Page is global (H) */ -#define _PAGE_MODIFIED (1<<10) /* Page modified (dirty) (S) */ -#define _PAGE_FILE (1<<10) /* page cache/ swap (S) */ -#define _PAGE_PRESENT (1<<11) /* TLB entry is valid (H) */ +#define _PAGE_EXECUTE (1<<3) /* Page has user execute perm (H) */ +#define _PAGE_WRITE (1<<4) /* Page has user write perm (H) */ +#define _PAGE_READ (1<<5) /* Page has user read perm (H) */ +#define _PAGE_MODIFIED (1<<6) /* Page modified (dirty) (S) */ +#define _PAGE_FILE (1<<7) /* page cache/ swap (S) */ +#define _PAGE_GLOBAL (1<<8) /* Page is global (H) */ +#define _PAGE_PRESENT (1<<10) /* TLB entry is valid (H) */ -#else +#else /* MMU v3 onwards */ -/* PD1 */ #define _PAGE_CACHEABLE (1<<0) /* Page is cached (H) */ -#define _PAGE_U_EXECUTE (1<<1) /* Page has user execute perm (H) */ -#define _PAGE_U_WRITE (1<<2) /* Page has user write perm (H) */ -#define _PAGE_U_READ (1<<3) /* Page has user read perm (H) */ -#define _PAGE_K_EXECUTE (1<<4) /* Page has kernel execute perm (H) */ -#define _PAGE_K_WRITE (1<<5) /* Page has kernel write perm (H) */ -#define _PAGE_K_READ (1<<6) /* Page has kernel perm (H) */ -#define _PAGE_ACCESSED (1<<7) /* Page is accessed (S) */ - -/* PD0 */ +#define _PAGE_EXECUTE (1<<1) /* Page has user execute perm (H) */ +#define _PAGE_WRITE (1<<2) /* Page has user write perm (H) */ +#define _PAGE_READ (1<<3) /* Page has user read perm (H) */ +#define _PAGE_ACCESSED (1<<4) /* Page is accessed (S) */ +#define _PAGE_MODIFIED (1<<5) /* Page modified (dirty) (S) */ +#define _PAGE_FILE (1<<6) /* page cache/ swap (S) */ #define _PAGE_GLOBAL (1<<8) /* Page is global (H) */ #define _PAGE_PRESENT (1<<9) /* TLB entry is valid (H) */ -#define _PAGE_SHARED_CODE (1<<10) /* Shared Code page with cmn vaddr +#define _PAGE_SHARED_CODE (1<<11) /* Shared Code page with cmn vaddr usable for shared TLB entries (H) */ - -#define _PAGE_MODIFIED (1<<11) /* Page modified (dirty) (S) */ -#define _PAGE_FILE (1<<12) /* page cache/ swap (S) */ - -#define _PAGE_SHARED_CODE_H (1<<31) /* Hardware counterpart of above */ #endif -/* Kernel allowed all permissions for all pages */ -#define _K_PAGE_PERMS (_PAGE_K_EXECUTE | _PAGE_K_WRITE | _PAGE_K_READ | \ +/* vmalloc permissions */ +#define _K_PAGE_PERMS (_PAGE_EXECUTE | _PAGE_WRITE | _PAGE_READ | \ _PAGE_GLOBAL | _PAGE_PRESENT) #ifdef CONFIG_ARC_CACHE_PAGES @@ -109,10 +97,6 @@ */ #define ___DEF (_PAGE_PRESENT | _PAGE_DEF_CACHEABLE) -#define _PAGE_READ (_PAGE_U_READ | _PAGE_K_READ) -#define _PAGE_WRITE (_PAGE_U_WRITE | _PAGE_K_WRITE) -#define _PAGE_EXECUTE (_PAGE_U_EXECUTE | _PAGE_K_EXECUTE) - /* Set of bits not changed in pte_modify */ #define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_ACCESSED | _PAGE_MODIFIED) @@ -126,8 +110,8 @@ #define PAGE_SHARED PAGE_U_W_R -/* While kernel runs out of unstrslated space, vmalloc/modules use a chunk of - * kernel vaddr space - visible in all addr spaces, but kernel mode only +/* While kernel runs out of unstranslated space, vmalloc/modules use a chunk of + * user vaddr space - visible in all addr spaces, but kernel mode only * Thus Global, all-kernel-access, no-user-access, cached */ #define PAGE_KERNEL __pgprot(_K_PAGE_PERMS | _PAGE_DEF_CACHEABLE) @@ -136,10 +120,9 @@ #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) +#define PTE_BITS_IN_PD0 (_PAGE_GLOBAL | _PAGE_PRESENT) +#define PTE_BITS_RWX (_PAGE_EXECUTE | _PAGE_WRITE | _PAGE_READ) +#define PTE_BITS_NON_RWX_IN_PD1 (PAGE_MASK | _PAGE_CACHEABLE) /************************************************************************** * Mapping of vm_flags (Generic VM) to PTE flags (arch specific) diff --git a/arch/arc/include/asm/prom.h b/arch/arc/include/asm/prom.h deleted file mode 100644 index 692d0d0789a7..000000000000 --- a/arch/arc/include/asm/prom.h +++ /dev/null @@ -1,14 +0,0 @@ -/* - * Copyright (C) 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 _ASM_ARC_PROM_H_ -#define _ASM_ARC_PROM_H_ - -#define HAVE_ARCH_DEVTREE_FIXUPS - -#endif diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h index c9938e7a7dbd..1bfeec2c0558 100644 --- a/arch/arc/include/asm/ptrace.h +++ b/arch/arc/include/asm/ptrace.h @@ -20,27 +20,17 @@ struct pt_regs { /* Real registers */ long bta; /* bta_l1, bta_l2, erbta */ - long lp_start; - long lp_end; - long lp_count; + + long lp_start, lp_end, lp_count; + long status32; /* status32_l1, status32_l2, erstatus */ long ret; /* ilink1, ilink2 or eret */ long blink; long fp; long r26; /* gp */ - long r12; - long r11; - long r10; - long r9; - long r8; - long r7; - long r6; - long r5; - long r4; - long r3; - long r2; - long r1; - long r0; + + long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0; + long sp; /* user/kernel sp depending on where we came from */ long orig_r0; @@ -70,19 +60,7 @@ struct pt_regs { /* Callee saved registers - need to be saved only when you are scheduled out */ struct callee_regs { - long r25; - long r24; - long r23; - long r22; - long r21; - long r20; - long r19; - long r18; - long r17; - long r16; - long r15; - long r14; - long r13; + long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13; }; #define instruction_pointer(regs) ((regs)->ret) diff --git a/arch/arc/include/asm/sections.h b/arch/arc/include/asm/sections.h index 6fc1159dfefe..764f1e3ba752 100644 --- a/arch/arc/include/asm/sections.h +++ b/arch/arc/include/asm/sections.h @@ -11,7 +11,6 @@ #include <asm-generic/sections.h> -extern char _int_vec_base_lds[]; extern char __arc_dccm_base[]; extern char __dtb_start[]; diff --git a/arch/arc/include/asm/setup.h b/arch/arc/include/asm/setup.h index 229e50681497..e10f8cef56a8 100644 --- a/arch/arc/include/asm/setup.h +++ b/arch/arc/include/asm/setup.h @@ -31,7 +31,7 @@ struct cpuinfo_data { extern int root_mountflags, end_mem; extern int running_on_hw; -void __init setup_processor(void); +void setup_processor(void); void __init setup_arch_memory(void); #endif /* __ASMARC_SETUP_H */ diff --git a/arch/arc/include/asm/smp.h b/arch/arc/include/asm/smp.h index c4fb211dcd25..eefc29f08cdb 100644 --- a/arch/arc/include/asm/smp.h +++ b/arch/arc/include/asm/smp.h @@ -30,7 +30,7 @@ extern void arch_send_call_function_ipi_mask(const struct cpumask *mask); * APIs provided by arch SMP code to rest of arch code */ extern void __init smp_init_cpus(void); -extern void __init first_lines_of_secondary(void); +extern void first_lines_of_secondary(void); extern const char *arc_platform_smp_cpuinfo(void); /* diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h index f158197ac5b0..b6a8c2dfbe6e 100644 --- a/arch/arc/include/asm/spinlock.h +++ b/arch/arc/include/asm/spinlock.h @@ -45,7 +45,14 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock) static inline void arch_spin_unlock(arch_spinlock_t *lock) { - lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__; + unsigned int tmp = __ARCH_SPIN_LOCK_UNLOCKED__; + + __asm__ __volatile__( + " ex %0, [%1] \n" + : "+r" (tmp) + : "r"(&(lock->slock)) + : "memory"); + smp_mb(); } diff --git a/arch/arc/include/asm/spinlock_types.h b/arch/arc/include/asm/spinlock_types.h index 8276bfd61704..662627ced4f2 100644 --- a/arch/arc/include/asm/spinlock_types.h +++ b/arch/arc/include/asm/spinlock_types.h @@ -20,9 +20,9 @@ typedef struct { #define __ARCH_SPIN_LOCK_LOCKED { __ARCH_SPIN_LOCK_LOCKED__ } /* - * Unlocked: 0x01_00_00_00 - * Read lock(s): 0x00_FF_00_00 to say 0x01 - * Write lock: 0x0, but only possible if prior value "unlocked" 0x0100_0000 + * Unlocked : 0x0100_0000 + * Read lock(s) : 0x00FF_FFFF to 0x01 (Multiple Readers decrement it) + * Write lock : 0x0, but only if prior value is "unlocked" 0x0100_0000 */ typedef struct { volatile unsigned int counter; diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h index 2d50a4cdd7f3..45be21672011 100644 --- a/arch/arc/include/asm/thread_info.h +++ b/arch/arc/include/asm/thread_info.h @@ -80,8 +80,6 @@ static inline __attribute_const__ struct thread_info *current_thread_info(void) #endif /* !__ASSEMBLY__ */ -#define PREEMPT_ACTIVE 0x10000000 - /* * thread information flags * - these are process state flags that various assembly files may need to diff --git a/arch/arc/include/asm/tlbflush.h b/arch/arc/include/asm/tlbflush.h index b2f9bc7f68c8..71c7b2e4b874 100644 --- a/arch/arc/include/asm/tlbflush.h +++ b/arch/arc/include/asm/tlbflush.h @@ -18,11 +18,18 @@ void local_flush_tlb_kernel_range(unsigned long start, unsigned long end); void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); -/* XXX: Revisit for SMP */ +#ifndef CONFIG_SMP #define flush_tlb_range(vma, s, e) local_flush_tlb_range(vma, s, e) #define flush_tlb_page(vma, page) local_flush_tlb_page(vma, page) #define flush_tlb_kernel_range(s, e) local_flush_tlb_kernel_range(s, e) #define flush_tlb_all() local_flush_tlb_all() #define flush_tlb_mm(mm) local_flush_tlb_mm(mm) - +#else +extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end); +extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long page); +extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); +extern void flush_tlb_all(void); +extern void flush_tlb_mm(struct mm_struct *mm); +#endif /* CONFIG_SMP */ #endif diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h index 32420824375b..30c9baffa96f 100644 --- a/arch/arc/include/asm/uaccess.h +++ b/arch/arc/include/asm/uaccess.h @@ -43,7 +43,7 @@ * Because it essentially checks if buffer end is within limit and @len is * non-ngeative, which implies that buffer start will be within limit too. * - * The reason for rewriting being, for majorit yof cases, @len is generally + * The reason for rewriting being, for majority of cases, @len is generally * compile time constant, causing first sub-expression to be compile time * subsumed. * @@ -53,7 +53,7 @@ * */ #define __user_ok(addr, sz) (((sz) <= TASK_SIZE) && \ - (((addr)+(sz)) <= get_fs())) + ((addr) <= (get_fs() - (sz)))) #define __access_ok(addr, sz) (unlikely(__kernel_ok) || \ likely(__user_ok((addr), (sz)))) diff --git a/arch/arc/include/asm/unaligned.h b/arch/arc/include/asm/unaligned.h index 60702f3751d2..3e5f071bc00c 100644 --- a/arch/arc/include/asm/unaligned.h +++ b/arch/arc/include/asm/unaligned.h @@ -22,7 +22,8 @@ static inline int misaligned_fixup(unsigned long address, struct pt_regs *regs, struct callee_regs *cregs) { - return 0; + /* Not fixed */ + return 1; } #endif |