summaryrefslogtreecommitdiff
path: root/arch/arc/include
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arc/include')
-rw-r--r--arch/arc/include/asm/arcregs.h8
-rw-r--r--arch/arc/include/asm/atomic.h86
-rw-r--r--arch/arc/include/asm/cache.h8
-rw-r--r--arch/arc/include/asm/cmpxchg.h22
-rw-r--r--arch/arc/include/asm/futex.h72
-rw-r--r--arch/arc/include/asm/perf_event.h23
-rw-r--r--arch/arc/include/asm/ptrace.h54
-rw-r--r--arch/arc/include/asm/spinlock.h538
-rw-r--r--arch/arc/include/asm/spinlock_types.h2
-rw-r--r--arch/arc/include/uapi/asm/ptrace.h20
10 files changed, 706 insertions, 127 deletions
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index 070f58827a5c..d8023bc8d1ad 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -35,6 +35,7 @@
#define ARC_REG_RTT_BCR 0xF2
#define ARC_REG_IRQ_BCR 0xF3
#define ARC_REG_SMART_BCR 0xFF
+#define ARC_REG_CLUSTER_BCR 0xcf
/* status32 Bits Positions */
#define STATUS_AE_BIT 5 /* Exception active */
@@ -89,11 +90,10 @@
#define ECR_C_BIT_DTLB_LD_MISS 8
#define ECR_C_BIT_DTLB_ST_MISS 9
-
/* Auxiliary registers */
#define AUX_IDENTITY 4
#define AUX_INTR_VEC_BASE 0x25
-
+#define AUX_NON_VOL 0x5e
/*
* Floating Pt Registers
@@ -240,9 +240,9 @@ struct bcr_extn_xymem {
struct bcr_perip {
#ifdef CONFIG_CPU_BIG_ENDIAN
- unsigned int start:8, pad2:8, sz:8, pad:8;
+ unsigned int start:8, pad2:8, sz:8, ver:8;
#else
- unsigned int pad:8, sz:8, pad2:8, start:8;
+ unsigned int ver:8, sz:8, pad2:8, start:8;
#endif
};
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 03484cb4d16d..c3ecda023e3a 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -23,33 +23,60 @@
#define atomic_set(v, i) (((v)->counter) = (i))
-#ifdef CONFIG_ISA_ARCV2
-#define PREFETCHW " prefetchw [%1] \n"
-#else
-#define PREFETCHW
+#ifdef CONFIG_ARC_STAR_9000923308
+
+#define SCOND_FAIL_RETRY_VAR_DEF \
+ unsigned int delay = 1, tmp; \
+
+#define SCOND_FAIL_RETRY_ASM \
+ " bz 4f \n" \
+ " ; --- scond fail delay --- \n" \
+ " mov %[tmp], %[delay] \n" /* tmp = delay */ \
+ "2: brne.d %[tmp], 0, 2b \n" /* while (tmp != 0) */ \
+ " sub %[tmp], %[tmp], 1 \n" /* tmp-- */ \
+ " rol %[delay], %[delay] \n" /* delay *= 2 */ \
+ " b 1b \n" /* start over */ \
+ "4: ; --- success --- \n" \
+
+#define SCOND_FAIL_RETRY_VARS \
+ ,[delay] "+&r" (delay),[tmp] "=&r" (tmp) \
+
+#else /* !CONFIG_ARC_STAR_9000923308 */
+
+#define SCOND_FAIL_RETRY_VAR_DEF
+
+#define SCOND_FAIL_RETRY_ASM \
+ " bnz 1b \n" \
+
+#define SCOND_FAIL_RETRY_VARS
+
#endif
#define ATOMIC_OP(op, c_op, asm_op) \
static inline void atomic_##op(int i, atomic_t *v) \
{ \
- unsigned int temp; \
+ unsigned int val; \
+ SCOND_FAIL_RETRY_VAR_DEF \
\
__asm__ __volatile__( \
- "1: \n" \
- PREFETCHW \
- " llock %0, [%1] \n" \
- " " #asm_op " %0, %0, %2 \n" \
- " scond %0, [%1] \n" \
- " bnz 1b \n" \
- : "=&r"(temp) /* Early clobber, to prevent reg reuse */ \
- : "r"(&v->counter), "ir"(i) \
+ "1: llock %[val], [%[ctr]] \n" \
+ " " #asm_op " %[val], %[val], %[i] \n" \
+ " scond %[val], [%[ctr]] \n" \
+ " \n" \
+ SCOND_FAIL_RETRY_ASM \
+ \
+ : [val] "=&r" (val) /* Early clobber to prevent reg reuse */ \
+ SCOND_FAIL_RETRY_VARS \
+ : [ctr] "r" (&v->counter), /* Not "m": llock only supports reg direct addr mode */ \
+ [i] "ir" (i) \
: "cc"); \
} \
#define ATOMIC_OP_RETURN(op, c_op, asm_op) \
static inline int atomic_##op##_return(int i, atomic_t *v) \
{ \
- unsigned int temp; \
+ unsigned int val; \
+ SCOND_FAIL_RETRY_VAR_DEF \
\
/* \
* Explicit full memory barrier needed before/after as \
@@ -58,19 +85,21 @@ static inline int atomic_##op##_return(int i, atomic_t *v) \
smp_mb(); \
\
__asm__ __volatile__( \
- "1: \n" \
- PREFETCHW \
- " llock %0, [%1] \n" \
- " " #asm_op " %0, %0, %2 \n" \
- " scond %0, [%1] \n" \
- " bnz 1b \n" \
- : "=&r"(temp) \
- : "r"(&v->counter), "ir"(i) \
+ "1: llock %[val], [%[ctr]] \n" \
+ " " #asm_op " %[val], %[val], %[i] \n" \
+ " scond %[val], [%[ctr]] \n" \
+ " \n" \
+ SCOND_FAIL_RETRY_ASM \
+ \
+ : [val] "=&r" (val) \
+ SCOND_FAIL_RETRY_VARS \
+ : [ctr] "r" (&v->counter), \
+ [i] "ir" (i) \
: "cc"); \
\
smp_mb(); \
\
- return temp; \
+ return val; \
}
#else /* !CONFIG_ARC_HAS_LLSC */
@@ -143,13 +172,20 @@ static inline int atomic_##op##_return(int i, atomic_t *v) \
ATOMIC_OPS(add, +=, add)
ATOMIC_OPS(sub, -=, sub)
-ATOMIC_OP(and, &=, and)
-#define atomic_clear_mask(mask, v) atomic_and(~(mask), (v))
+#define atomic_andnot atomic_andnot
+
+ATOMIC_OP(and, &=, and)
+ATOMIC_OP(andnot, &= ~, bic)
+ATOMIC_OP(or, |=, or)
+ATOMIC_OP(xor, ^=, xor)
#undef ATOMIC_OPS
#undef ATOMIC_OP_RETURN
#undef ATOMIC_OP
+#undef SCOND_FAIL_RETRY_VAR_DEF
+#undef SCOND_FAIL_RETRY_ASM
+#undef SCOND_FAIL_RETRY_VARS
/**
* __atomic_add_unless - add unless the number is a given value
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index d67345d3e2d4..e23ea6e7633a 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -53,6 +53,8 @@ extern void arc_cache_init(void);
extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len);
extern void read_decode_cache_bcr(void);
+extern int ioc_exists;
+
#endif /* !__ASSEMBLY__ */
/* Instruction cache related Auxiliary registers */
@@ -94,4 +96,10 @@ extern void read_decode_cache_bcr(void);
#define SLC_CTRL_BUSY 0x100
#define SLC_CTRL_RGN_OP_INV 0x200
+/* IO coherency related Auxiliary registers */
+#define ARC_REG_IO_COH_ENABLE 0x500
+#define ARC_REG_IO_COH_PARTIAL 0x501
+#define ARC_REG_IO_COH_AP0_BASE 0x508
+#define ARC_REG_IO_COH_AP0_SIZE 0x509
+
#endif /* _ASM_CACHE_H */
diff --git a/arch/arc/include/asm/cmpxchg.h b/arch/arc/include/asm/cmpxchg.h
index 44fd531f4d7b..af7a2db139c9 100644
--- a/arch/arc/include/asm/cmpxchg.h
+++ b/arch/arc/include/asm/cmpxchg.h
@@ -110,18 +110,18 @@ static inline unsigned long __xchg(unsigned long val, volatile void *ptr,
sizeof(*(ptr))))
/*
- * On ARC700, EX insn is inherently atomic, so by default "vanilla" xchg() need
- * not require any locking. However there's a quirk.
- * ARC lacks native CMPXCHG, thus emulated (see above), using external locking -
- * incidently it "reuses" the same atomic_ops_lock used by atomic APIs.
- * Now, llist code uses cmpxchg() and xchg() on same data, so xchg() needs to
- * abide by same serializing rules, thus ends up using atomic_ops_lock as well.
+ * xchg() maps directly to ARC EX instruction which guarantees atomicity.
+ * However in !LLSC config, it also needs to be use @atomic_ops_lock spinlock
+ * due to a subtle reason:
+ * - For !LLSC, cmpxchg() needs to use that lock (see above) and there is lot
+ * of kernel code which calls xchg()/cmpxchg() on same data (see llist.h)
+ * Hence xchg() needs to follow same locking rules.
*
- * This however is only relevant if SMP and/or ARC lacks LLSC
- * if (UP or LLSC)
- * xchg doesn't need serialization
- * else <==> !(UP or LLSC) <==> (!UP and !LLSC) <==> (SMP and !LLSC)
- * xchg needs serialization
+ * Technically the lock is also needed for UP (boils down to irq save/restore)
+ * but we can cheat a bit since cmpxchg() atomic_ops_lock() would cause irqs to
+ * be disabled thus can't possibly be interrpted/preempted/clobbered by xchg()
+ * Other way around, xchg is one instruction anyways, so can't be interrupted
+ * as such
*/
#if !defined(CONFIG_ARC_HAS_LLSC) && defined(CONFIG_SMP)
diff --git a/arch/arc/include/asm/futex.h b/arch/arc/include/asm/futex.h
index 70cfe16b742d..11e1b1f3acda 100644
--- a/arch/arc/include/asm/futex.h
+++ b/arch/arc/include/asm/futex.h
@@ -20,6 +20,7 @@
#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)\
\
+ smp_mb(); \
__asm__ __volatile__( \
"1: llock %1, [%2] \n" \
insn "\n" \
@@ -30,7 +31,7 @@
" .section .fixup,\"ax\" \n" \
" .align 4 \n" \
"4: mov %0, %4 \n" \
- " b 3b \n" \
+ " j 3b \n" \
" .previous \n" \
" .section __ex_table,\"a\" \n" \
" .align 4 \n" \
@@ -40,12 +41,14 @@
\
: "=&r" (ret), "=&r" (oldval) \
: "r" (uaddr), "r" (oparg), "ir" (-EFAULT) \
- : "cc", "memory")
+ : "cc", "memory"); \
+ smp_mb() \
#else /* !CONFIG_ARC_HAS_LLSC */
#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)\
\
+ smp_mb(); \
__asm__ __volatile__( \
"1: ld %1, [%2] \n" \
insn "\n" \
@@ -55,7 +58,7 @@
" .section .fixup,\"ax\" \n" \
" .align 4 \n" \
"4: mov %0, %4 \n" \
- " b 3b \n" \
+ " j 3b \n" \
" .previous \n" \
" .section __ex_table,\"a\" \n" \
" .align 4 \n" \
@@ -65,7 +68,8 @@
\
: "=&r" (ret), "=&r" (oldval) \
: "r" (uaddr), "r" (oparg), "ir" (-EFAULT) \
- : "cc", "memory")
+ : "cc", "memory"); \
+ smp_mb() \
#endif
@@ -83,6 +87,9 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
return -EFAULT;
+#ifndef CONFIG_ARC_HAS_LLSC
+ preempt_disable(); /* to guarantee atomic r-m-w of futex op */
+#endif
pagefault_disable();
switch (op) {
@@ -90,6 +97,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
__futex_atomic_op("mov %0, %3", ret, oldval, uaddr, oparg);
break;
case FUTEX_OP_ADD:
+ /* oldval = *uaddr; *uaddr += oparg ; ret = *uaddr */
__futex_atomic_op("add %0, %1, %3", ret, oldval, uaddr, oparg);
break;
case FUTEX_OP_OR:
@@ -106,6 +114,9 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
}
pagefault_enable();
+#ifndef CONFIG_ARC_HAS_LLSC
+ preempt_enable();
+#endif
if (!ret) {
switch (cmp) {
@@ -134,54 +145,57 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
return ret;
}
-/* Compare-xchg with pagefaults disabled.
- * Notes:
- * -Best-Effort: Exchg happens only if compare succeeds.
- * If compare fails, returns; leaving retry/looping to upper layers
- * -successful cmp-xchg: return orig value in @addr (same as cmp val)
- * -Compare fails: return orig value in @addr
- * -user access r/w fails: return -EFAULT
+/*
+ * cmpxchg of futex (pagefaults disabled by caller)
+ * Return 0 for success, -EFAULT otherwise
*/
static inline int
-futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval,
- u32 newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 expval,
+ u32 newval)
{
- u32 val;
+ int ret = 0;
+ u32 existval;
- if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+ if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
- pagefault_disable();
+#ifndef CONFIG_ARC_HAS_LLSC
+ preempt_disable(); /* to guarantee atomic r-m-w of futex op */
+#endif
+ smp_mb();
__asm__ __volatile__(
#ifdef CONFIG_ARC_HAS_LLSC
- "1: llock %0, [%3] \n"
- " brne %0, %1, 3f \n"
- "2: scond %2, [%3] \n"
+ "1: llock %1, [%4] \n"
+ " brne %1, %2, 3f \n"
+ "2: scond %3, [%4] \n"
" bnz 1b \n"
#else
- "1: ld %0, [%3] \n"
- " brne %0, %1, 3f \n"
- "2: st %2, [%3] \n"
+ "1: ld %1, [%4] \n"
+ " brne %1, %2, 3f \n"
+ "2: st %3, [%4] \n"
#endif
"3: \n"
" .section .fixup,\"ax\" \n"
- "4: mov %0, %4 \n"
- " b 3b \n"
+ "4: mov %0, %5 \n"
+ " j 3b \n"
" .previous \n"
" .section __ex_table,\"a\" \n"
" .align 4 \n"
" .word 1b, 4b \n"
" .word 2b, 4b \n"
" .previous\n"
- : "=&r"(val)
- : "r"(oldval), "r"(newval), "r"(uaddr), "ir"(-EFAULT)
+ : "+&r"(ret), "=&r"(existval)
+ : "r"(expval), "r"(newval), "r"(uaddr), "ir"(-EFAULT)
: "cc", "memory");
- pagefault_enable();
+ smp_mb();
- *uval = val;
- return val;
+#ifndef CONFIG_ARC_HAS_LLSC
+ preempt_enable();
+#endif
+ *uval = existval;
+ return ret;
}
#endif
diff --git a/arch/arc/include/asm/perf_event.h b/arch/arc/include/asm/perf_event.h
index 2b8880e953a2..5f071762fb1c 100644
--- a/arch/arc/include/asm/perf_event.h
+++ b/arch/arc/include/asm/perf_event.h
@@ -1,6 +1,7 @@
/*
* Linux performance counter support for ARC
*
+ * Copyright (C) 2014-2015 Synopsys, Inc. (www.synopsys.com)
* Copyright (C) 2011-2013 Synopsys, Inc. (www.synopsys.com)
*
* This program is free software; you can redistribute it and/or modify
@@ -12,8 +13,8 @@
#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
+/* Max number of counters that PCT block may ever have */
+#define ARC_PERF_MAX_COUNTERS 32
#define ARC_REG_CC_BUILD 0xF6
#define ARC_REG_CC_INDEX 0x240
@@ -28,15 +29,22 @@
#define ARC_REG_PCT_CONFIG 0x254
#define ARC_REG_PCT_CONTROL 0x255
#define ARC_REG_PCT_INDEX 0x256
+#define ARC_REG_PCT_INT_CNTL 0x25C
+#define ARC_REG_PCT_INT_CNTH 0x25D
+#define ARC_REG_PCT_INT_CTRL 0x25E
+#define ARC_REG_PCT_INT_ACT 0x25F
+
+#define ARC_REG_PCT_CONFIG_USER (1 << 18) /* count in user mode */
+#define ARC_REG_PCT_CONFIG_KERN (1 << 19) /* count in kernel mode */
#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;
+ unsigned int m:8, c:8, r:5, i:1, s:2, v:8;
#else
- unsigned int v:8, s:2, r:6, c:8, m:8;
+ unsigned int v:8, s:2, i:1, r:5, c:8, m:8;
#endif
};
@@ -95,10 +103,13 @@ static const char * const arc_pmu_ev_hw_map[] = {
/* counts condition */
[PERF_COUNT_HW_INSTRUCTIONS] = "iall",
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmp",
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmp", /* Excludes ZOL jumps */
[PERF_COUNT_ARC_BPOK] = "bpok", /* NP-NT, PT-T, PNT-NT */
+#ifdef CONFIG_ISA_ARCV2
+ [PERF_COUNT_HW_BRANCH_MISSES] = "bpmp",
+#else
[PERF_COUNT_HW_BRANCH_MISSES] = "bpfail", /* NP-T, PT-NT, PNT-T */
-
+#endif
[PERF_COUNT_ARC_LDC] = "imemrdc", /* Instr: mem read cached */
[PERF_COUNT_ARC_STC] = "imemwrc", /* Instr: mem write cached */
diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h
index 91694ec1ce95..69095da1fcfd 100644
--- a/arch/arc/include/asm/ptrace.h
+++ b/arch/arc/include/asm/ptrace.h
@@ -20,20 +20,20 @@
struct pt_regs {
/* Real registers */
- long bta; /* bta_l1, bta_l2, erbta */
+ unsigned long bta; /* bta_l1, bta_l2, erbta */
- long lp_start, lp_end, lp_count;
+ unsigned 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 */
+ unsigned long status32; /* status32_l1, status32_l2, erstatus */
+ unsigned long ret; /* ilink1, ilink2 or eret */
+ unsigned long blink;
+ unsigned long fp;
+ unsigned long r26; /* gp */
- long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
+ unsigned 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;
+ unsigned long sp; /* User/Kernel depending on where we came from */
+ unsigned long orig_r0;
/*
* To distinguish bet excp, syscall, irq
@@ -55,13 +55,13 @@ struct pt_regs {
unsigned long event;
};
- long user_r25;
+ unsigned long user_r25;
};
#else
struct pt_regs {
- long orig_r0;
+ unsigned long orig_r0;
union {
struct {
@@ -76,26 +76,26 @@ struct pt_regs {
unsigned long event;
};
- long bta; /* bta_l1, bta_l2, erbta */
+ unsigned long bta; /* bta_l1, bta_l2, erbta */
- long user_r25;
+ unsigned long user_r25;
- long r26; /* gp */
- long fp;
- long sp; /* user/kernel sp depending on where we came from */
+ unsigned long r26; /* gp */
+ unsigned long fp;
+ unsigned long sp; /* user/kernel sp depending on where we came from */
- long r12;
+ unsigned long r12;
/*------- Below list auto saved by h/w -----------*/
- long r0, r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11;
+ unsigned long r0, r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11;
- long blink;
- long lp_end, lp_start, lp_count;
+ unsigned long blink;
+ unsigned long lp_end, lp_start, lp_count;
- long ei, ldi, jli;
+ unsigned long ei, ldi, jli;
- long ret;
- long status32;
+ unsigned long ret;
+ unsigned long status32;
};
#endif
@@ -103,10 +103,10 @@ struct pt_regs {
/* Callee saved registers - need to be saved only when you are scheduled out */
struct callee_regs {
- long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13;
+ unsigned long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13;
};
-#define instruction_pointer(regs) (unsigned long)((regs)->ret)
+#define instruction_pointer(regs) ((regs)->ret)
#define profile_pc(regs) instruction_pointer(regs)
/* return 1 if user mode or 0 if kernel mode */
@@ -142,7 +142,7 @@ struct callee_regs {
static inline long regs_return_value(struct pt_regs *regs)
{
- return regs->r0;
+ return (long)regs->r0;
}
#endif /* !__ASSEMBLY__ */
diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h
index e1651df6a93d..db8c59d1eaeb 100644
--- a/arch/arc/include/asm/spinlock.h
+++ b/arch/arc/include/asm/spinlock.h
@@ -18,9 +18,518 @@
#define arch_spin_unlock_wait(x) \
do { while (arch_spin_is_locked(x)) cpu_relax(); } while (0)
+#ifdef CONFIG_ARC_HAS_LLSC
+
+/*
+ * A normal LLOCK/SCOND based system, w/o need for livelock workaround
+ */
+#ifndef CONFIG_ARC_STAR_9000923308
+
static inline void arch_spin_lock(arch_spinlock_t *lock)
{
- unsigned int tmp = __ARCH_SPIN_LOCK_LOCKED__;
+ unsigned int val;
+
+ smp_mb();
+
+ __asm__ __volatile__(
+ "1: llock %[val], [%[slock]] \n"
+ " breq %[val], %[LOCKED], 1b \n" /* spin while LOCKED */
+ " scond %[LOCKED], [%[slock]] \n" /* acquire */
+ " bnz 1b \n"
+ " \n"
+ : [val] "=&r" (val)
+ : [slock] "r" (&(lock->slock)),
+ [LOCKED] "r" (__ARCH_SPIN_LOCK_LOCKED__)
+ : "memory", "cc");
+
+ smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_spin_trylock(arch_spinlock_t *lock)
+{
+ unsigned int val, got_it = 0;
+
+ smp_mb();
+
+ __asm__ __volatile__(
+ "1: llock %[val], [%[slock]] \n"
+ " breq %[val], %[LOCKED], 4f \n" /* already LOCKED, just bail */
+ " scond %[LOCKED], [%[slock]] \n" /* acquire */
+ " bnz 1b \n"
+ " mov %[got_it], 1 \n"
+ "4: \n"
+ " \n"
+ : [val] "=&r" (val),
+ [got_it] "+&r" (got_it)
+ : [slock] "r" (&(lock->slock)),
+ [LOCKED] "r" (__ARCH_SPIN_LOCK_LOCKED__)
+ : "memory", "cc");
+
+ smp_mb();
+
+ return got_it;
+}
+
+static inline void arch_spin_unlock(arch_spinlock_t *lock)
+{
+ smp_mb();
+
+ lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__;
+
+ smp_mb();
+}
+
+/*
+ * Read-write spinlocks, allowing multiple readers but only one writer.
+ * Unfair locking as Writers could be starved indefinitely by Reader(s)
+ */
+
+static inline void arch_read_lock(arch_rwlock_t *rw)
+{
+ unsigned int val;
+
+ smp_mb();
+
+ /*
+ * zero means writer holds the lock exclusively, deny Reader.
+ * Otherwise grant lock to first/subseq reader
+ *
+ * if (rw->counter > 0) {
+ * rw->counter--;
+ * ret = 1;
+ * }
+ */
+
+ __asm__ __volatile__(
+ "1: llock %[val], [%[rwlock]] \n"
+ " brls %[val], %[WR_LOCKED], 1b\n" /* <= 0: spin while write locked */
+ " sub %[val], %[val], 1 \n" /* reader lock */
+ " scond %[val], [%[rwlock]] \n"
+ " bnz 1b \n"
+ " \n"
+ : [val] "=&r" (val)
+ : [rwlock] "r" (&(rw->counter)),
+ [WR_LOCKED] "ir" (0)
+ : "memory", "cc");
+
+ smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_read_trylock(arch_rwlock_t *rw)
+{
+ unsigned int val, got_it = 0;
+
+ smp_mb();
+
+ __asm__ __volatile__(
+ "1: llock %[val], [%[rwlock]] \n"
+ " brls %[val], %[WR_LOCKED], 4f\n" /* <= 0: already write locked, bail */
+ " sub %[val], %[val], 1 \n" /* counter-- */
+ " scond %[val], [%[rwlock]] \n"
+ " bnz 1b \n" /* retry if collided with someone */
+ " mov %[got_it], 1 \n"
+ " \n"
+ "4: ; --- done --- \n"
+
+ : [val] "=&r" (val),
+ [got_it] "+&r" (got_it)
+ : [rwlock] "r" (&(rw->counter)),
+ [WR_LOCKED] "ir" (0)
+ : "memory", "cc");
+
+ smp_mb();
+
+ return got_it;
+}
+
+static inline void arch_write_lock(arch_rwlock_t *rw)
+{
+ unsigned int val;
+
+ smp_mb();
+
+ /*
+ * If reader(s) hold lock (lock < __ARCH_RW_LOCK_UNLOCKED__),
+ * deny writer. Otherwise if unlocked grant to writer
+ * Hence the claim that Linux rwlocks are unfair to writers.
+ * (can be starved for an indefinite time by readers).
+ *
+ * if (rw->counter == __ARCH_RW_LOCK_UNLOCKED__) {
+ * rw->counter = 0;
+ * ret = 1;
+ * }
+ */
+
+ __asm__ __volatile__(
+ "1: llock %[val], [%[rwlock]] \n"
+ " brne %[val], %[UNLOCKED], 1b \n" /* while !UNLOCKED spin */
+ " mov %[val], %[WR_LOCKED] \n"
+ " scond %[val], [%[rwlock]] \n"
+ " bnz 1b \n"
+ " \n"
+ : [val] "=&r" (val)
+ : [rwlock] "r" (&(rw->counter)),
+ [UNLOCKED] "ir" (__ARCH_RW_LOCK_UNLOCKED__),
+ [WR_LOCKED] "ir" (0)
+ : "memory", "cc");
+
+ smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_write_trylock(arch_rwlock_t *rw)
+{
+ unsigned int val, got_it = 0;
+
+ smp_mb();
+
+ __asm__ __volatile__(
+ "1: llock %[val], [%[rwlock]] \n"
+ " brne %[val], %[UNLOCKED], 4f \n" /* !UNLOCKED, bail */
+ " mov %[val], %[WR_LOCKED] \n"
+ " scond %[val], [%[rwlock]] \n"
+ " bnz 1b \n" /* retry if collided with someone */
+ " mov %[got_it], 1 \n"
+ " \n"
+ "4: ; --- done --- \n"
+
+ : [val] "=&r" (val),
+ [got_it] "+&r" (got_it)
+ : [rwlock] "r" (&(rw->counter)),
+ [UNLOCKED] "ir" (__ARCH_RW_LOCK_UNLOCKED__),
+ [WR_LOCKED] "ir" (0)
+ : "memory", "cc");
+
+ smp_mb();
+
+ return got_it;
+}
+
+static inline void arch_read_unlock(arch_rwlock_t *rw)
+{
+ unsigned int val;
+
+ smp_mb();
+
+ /*
+ * rw->counter++;
+ */
+ __asm__ __volatile__(
+ "1: llock %[val], [%[rwlock]] \n"
+ " add %[val], %[val], 1 \n"
+ " scond %[val], [%[rwlock]] \n"
+ " bnz 1b \n"
+ " \n"
+ : [val] "=&r" (val)
+ : [rwlock] "r" (&(rw->counter))
+ : "memory", "cc");
+
+ smp_mb();
+}
+
+static inline void arch_write_unlock(arch_rwlock_t *rw)
+{
+ smp_mb();
+
+ rw->counter = __ARCH_RW_LOCK_UNLOCKED__;
+
+ smp_mb();
+}
+
+#else /* CONFIG_ARC_STAR_9000923308 */
+
+/*
+ * HS38x4 could get into a LLOCK/SCOND livelock in case of multiple overlapping
+ * coherency transactions in the SCU. The exclusive line state keeps rotating
+ * among contenting cores leading to a never ending cycle. So break the cycle
+ * by deferring the retry of failed exclusive access (SCOND). The actual delay
+ * needed is function of number of contending cores as well as the unrelated
+ * coherency traffic from other cores. To keep the code simple, start off with
+ * small delay of 1 which would suffice most cases and in case of contention
+ * double the delay. Eventually the delay is sufficient such that the coherency
+ * pipeline is drained, thus a subsequent exclusive access would succeed.
+ */
+
+#define SCOND_FAIL_RETRY_VAR_DEF \
+ unsigned int delay, tmp; \
+
+#define SCOND_FAIL_RETRY_ASM \
+ " ; --- scond fail delay --- \n" \
+ " mov %[tmp], %[delay] \n" /* tmp = delay */ \
+ "2: brne.d %[tmp], 0, 2b \n" /* while (tmp != 0) */ \
+ " sub %[tmp], %[tmp], 1 \n" /* tmp-- */ \
+ " rol %[delay], %[delay] \n" /* delay *= 2 */ \
+ " b 1b \n" /* start over */ \
+ " \n" \
+ "4: ; --- done --- \n" \
+
+#define SCOND_FAIL_RETRY_VARS \
+ ,[delay] "=&r" (delay), [tmp] "=&r" (tmp) \
+
+static inline void arch_spin_lock(arch_spinlock_t *lock)
+{
+ unsigned int val;
+ SCOND_FAIL_RETRY_VAR_DEF;
+
+ smp_mb();
+
+ __asm__ __volatile__(
+ "0: mov %[delay], 1 \n"
+ "1: llock %[val], [%[slock]] \n"
+ " breq %[val], %[LOCKED], 0b \n" /* spin while LOCKED */
+ " scond %[LOCKED], [%[slock]] \n" /* acquire */
+ " bz 4f \n" /* done */
+ " \n"
+ SCOND_FAIL_RETRY_ASM
+
+ : [val] "=&r" (val)
+ SCOND_FAIL_RETRY_VARS
+ : [slock] "r" (&(lock->slock)),
+ [LOCKED] "r" (__ARCH_SPIN_LOCK_LOCKED__)
+ : "memory", "cc");
+
+ smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_spin_trylock(arch_spinlock_t *lock)
+{
+ unsigned int val, got_it = 0;
+ SCOND_FAIL_RETRY_VAR_DEF;
+
+ smp_mb();
+
+ __asm__ __volatile__(
+ "0: mov %[delay], 1 \n"
+ "1: llock %[val], [%[slock]] \n"
+ " breq %[val], %[LOCKED], 4f \n" /* already LOCKED, just bail */
+ " scond %[LOCKED], [%[slock]] \n" /* acquire */
+ " bz.d 4f \n"
+ " mov.z %[got_it], 1 \n" /* got it */
+ " \n"
+ SCOND_FAIL_RETRY_ASM
+
+ : [val] "=&r" (val),
+ [got_it] "+&r" (got_it)
+ SCOND_FAIL_RETRY_VARS
+ : [slock] "r" (&(lock->slock)),
+ [LOCKED] "r" (__ARCH_SPIN_LOCK_LOCKED__)
+ : "memory", "cc");
+
+ smp_mb();
+
+ return got_it;
+}
+
+static inline void arch_spin_unlock(arch_spinlock_t *lock)
+{
+ smp_mb();
+
+ lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__;
+
+ smp_mb();
+}
+
+/*
+ * Read-write spinlocks, allowing multiple readers but only one writer.
+ * Unfair locking as Writers could be starved indefinitely by Reader(s)
+ */
+
+static inline void arch_read_lock(arch_rwlock_t *rw)
+{
+ unsigned int val;
+ SCOND_FAIL_RETRY_VAR_DEF;
+
+ smp_mb();
+
+ /*
+ * zero means writer holds the lock exclusively, deny Reader.
+ * Otherwise grant lock to first/subseq reader
+ *
+ * if (rw->counter > 0) {
+ * rw->counter--;
+ * ret = 1;
+ * }
+ */
+
+ __asm__ __volatile__(
+ "0: mov %[delay], 1 \n"
+ "1: llock %[val], [%[rwlock]] \n"
+ " brls %[val], %[WR_LOCKED], 0b\n" /* <= 0: spin while write locked */
+ " sub %[val], %[val], 1 \n" /* reader lock */
+ " scond %[val], [%[rwlock]] \n"
+ " bz 4f \n" /* done */
+ " \n"
+ SCOND_FAIL_RETRY_ASM
+
+ : [val] "=&r" (val)
+ SCOND_FAIL_RETRY_VARS
+ : [rwlock] "r" (&(rw->counter)),
+ [WR_LOCKED] "ir" (0)
+ : "memory", "cc");
+
+ smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_read_trylock(arch_rwlock_t *rw)
+{
+ unsigned int val, got_it = 0;
+ SCOND_FAIL_RETRY_VAR_DEF;
+
+ smp_mb();
+
+ __asm__ __volatile__(
+ "0: mov %[delay], 1 \n"
+ "1: llock %[val], [%[rwlock]] \n"
+ " brls %[val], %[WR_LOCKED], 4f\n" /* <= 0: already write locked, bail */
+ " sub %[val], %[val], 1 \n" /* counter-- */
+ " scond %[val], [%[rwlock]] \n"
+ " bz.d 4f \n"
+ " mov.z %[got_it], 1 \n" /* got it */
+ " \n"
+ SCOND_FAIL_RETRY_ASM
+
+ : [val] "=&r" (val),
+ [got_it] "+&r" (got_it)
+ SCOND_FAIL_RETRY_VARS
+ : [rwlock] "r" (&(rw->counter)),
+ [WR_LOCKED] "ir" (0)
+ : "memory", "cc");
+
+ smp_mb();
+
+ return got_it;
+}
+
+static inline void arch_write_lock(arch_rwlock_t *rw)
+{
+ unsigned int val;
+ SCOND_FAIL_RETRY_VAR_DEF;
+
+ smp_mb();
+
+ /*
+ * If reader(s) hold lock (lock < __ARCH_RW_LOCK_UNLOCKED__),
+ * deny writer. Otherwise if unlocked grant to writer
+ * Hence the claim that Linux rwlocks are unfair to writers.
+ * (can be starved for an indefinite time by readers).
+ *
+ * if (rw->counter == __ARCH_RW_LOCK_UNLOCKED__) {
+ * rw->counter = 0;
+ * ret = 1;
+ * }
+ */
+
+ __asm__ __volatile__(
+ "0: mov %[delay], 1 \n"
+ "1: llock %[val], [%[rwlock]] \n"
+ " brne %[val], %[UNLOCKED], 0b \n" /* while !UNLOCKED spin */
+ " mov %[val], %[WR_LOCKED] \n"
+ " scond %[val], [%[rwlock]] \n"
+ " bz 4f \n"
+ " \n"
+ SCOND_FAIL_RETRY_ASM
+
+ : [val] "=&r" (val)
+ SCOND_FAIL_RETRY_VARS
+ : [rwlock] "r" (&(rw->counter)),
+ [UNLOCKED] "ir" (__ARCH_RW_LOCK_UNLOCKED__),
+ [WR_LOCKED] "ir" (0)
+ : "memory", "cc");
+
+ smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_write_trylock(arch_rwlock_t *rw)
+{
+ unsigned int val, got_it = 0;
+ SCOND_FAIL_RETRY_VAR_DEF;
+
+ smp_mb();
+
+ __asm__ __volatile__(
+ "0: mov %[delay], 1 \n"
+ "1: llock %[val], [%[rwlock]] \n"
+ " brne %[val], %[UNLOCKED], 4f \n" /* !UNLOCKED, bail */
+ " mov %[val], %[WR_LOCKED] \n"
+ " scond %[val], [%[rwlock]] \n"
+ " bz.d 4f \n"
+ " mov.z %[got_it], 1 \n" /* got it */
+ " \n"
+ SCOND_FAIL_RETRY_ASM
+
+ : [val] "=&r" (val),
+ [got_it] "+&r" (got_it)
+ SCOND_FAIL_RETRY_VARS
+ : [rwlock] "r" (&(rw->counter)),
+ [UNLOCKED] "ir" (__ARCH_RW_LOCK_UNLOCKED__),
+ [WR_LOCKED] "ir" (0)
+ : "memory", "cc");
+
+ smp_mb();
+
+ return got_it;
+}
+
+static inline void arch_read_unlock(arch_rwlock_t *rw)
+{
+ unsigned int val;
+
+ smp_mb();
+
+ /*
+ * rw->counter++;
+ */
+ __asm__ __volatile__(
+ "1: llock %[val], [%[rwlock]] \n"
+ " add %[val], %[val], 1 \n"
+ " scond %[val], [%[rwlock]] \n"
+ " bnz 1b \n"
+ " \n"
+ : [val] "=&r" (val)
+ : [rwlock] "r" (&(rw->counter))
+ : "memory", "cc");
+
+ smp_mb();
+}
+
+static inline void arch_write_unlock(arch_rwlock_t *rw)
+{
+ unsigned int val;
+
+ smp_mb();
+
+ /*
+ * rw->counter = __ARCH_RW_LOCK_UNLOCKED__;
+ */
+ __asm__ __volatile__(
+ "1: llock %[val], [%[rwlock]] \n"
+ " scond %[UNLOCKED], [%[rwlock]]\n"
+ " bnz 1b \n"
+ " \n"
+ : [val] "=&r" (val)
+ : [rwlock] "r" (&(rw->counter)),
+ [UNLOCKED] "r" (__ARCH_RW_LOCK_UNLOCKED__)
+ : "memory", "cc");
+
+ smp_mb();
+}
+
+#undef SCOND_FAIL_RETRY_VAR_DEF
+#undef SCOND_FAIL_RETRY_ASM
+#undef SCOND_FAIL_RETRY_VARS
+
+#endif /* CONFIG_ARC_STAR_9000923308 */
+
+#else /* !CONFIG_ARC_HAS_LLSC */
+
+static inline void arch_spin_lock(arch_spinlock_t *lock)
+{
+ unsigned int val = __ARCH_SPIN_LOCK_LOCKED__;
/*
* This smp_mb() is technically superfluous, we only need the one
@@ -33,7 +542,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
__asm__ __volatile__(
"1: ex %0, [%1] \n"
" breq %0, %2, 1b \n"
- : "+&r" (tmp)
+ : "+&r" (val)
: "r"(&(lock->slock)), "ir"(__ARCH_SPIN_LOCK_LOCKED__)
: "memory");
@@ -48,26 +557,27 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
smp_mb();
}
+/* 1 - lock taken successfully */
static inline int arch_spin_trylock(arch_spinlock_t *lock)
{
- unsigned int tmp = __ARCH_SPIN_LOCK_LOCKED__;
+ unsigned int val = __ARCH_SPIN_LOCK_LOCKED__;
smp_mb();
__asm__ __volatile__(
"1: ex %0, [%1] \n"
- : "+r" (tmp)
+ : "+r" (val)
: "r"(&(lock->slock))
: "memory");
smp_mb();
- return (tmp == __ARCH_SPIN_LOCK_UNLOCKED__);
+ return (val == __ARCH_SPIN_LOCK_UNLOCKED__);
}
static inline void arch_spin_unlock(arch_spinlock_t *lock)
{
- unsigned int tmp = __ARCH_SPIN_LOCK_UNLOCKED__;
+ unsigned int val = __ARCH_SPIN_LOCK_UNLOCKED__;
/*
* RELEASE barrier: given the instructions avail on ARCv2, full barrier
@@ -77,7 +587,7 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
__asm__ __volatile__(
" ex %0, [%1] \n"
- : "+r" (tmp)
+ : "+r" (val)
: "r"(&(lock->slock))
: "memory");
@@ -90,19 +600,12 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
/*
* Read-write spinlocks, allowing multiple readers but only one writer.
+ * Unfair locking as Writers could be starved indefinitely by Reader(s)
*
* The spinlock itself is contained in @counter and access to it is
* serialized with @lock_mutex.
- *
- * Unfair locking as Writers could be starved indefinitely by Reader(s)
*/
-/* Would read_trylock() succeed? */
-#define arch_read_can_lock(x) ((x)->counter > 0)
-
-/* Would write_trylock() succeed? */
-#define arch_write_can_lock(x) ((x)->counter == __ARCH_RW_LOCK_UNLOCKED__)
-
/* 1 - lock taken successfully */
static inline int arch_read_trylock(arch_rwlock_t *rw)
{
@@ -173,6 +676,11 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
arch_spin_unlock(&(rw->lock_mutex));
}
+#endif
+
+#define arch_read_can_lock(x) ((x)->counter > 0)
+#define arch_write_can_lock(x) ((x)->counter == __ARCH_RW_LOCK_UNLOCKED__)
+
#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
diff --git a/arch/arc/include/asm/spinlock_types.h b/arch/arc/include/asm/spinlock_types.h
index 662627ced4f2..4e1ef5f650c6 100644
--- a/arch/arc/include/asm/spinlock_types.h
+++ b/arch/arc/include/asm/spinlock_types.h
@@ -26,7 +26,9 @@ typedef struct {
*/
typedef struct {
volatile unsigned int counter;
+#ifndef CONFIG_ARC_HAS_LLSC
arch_spinlock_t lock_mutex;
+#endif
} arch_rwlock_t;
#define __ARCH_RW_LOCK_UNLOCKED__ 0x01000000
diff --git a/arch/arc/include/uapi/asm/ptrace.h b/arch/arc/include/uapi/asm/ptrace.h
index 76a7739aab1c..0b3ef63d4a03 100644
--- a/arch/arc/include/uapi/asm/ptrace.h
+++ b/arch/arc/include/uapi/asm/ptrace.h
@@ -32,20 +32,20 @@
*/
struct user_regs_struct {
- long pad;
+ unsigned long pad;
struct {
- 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;
+ unsigned long bta, lp_start, lp_end, lp_count;
+ unsigned long status32, ret, blink, fp, gp;
+ unsigned long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
+ unsigned long sp;
} scratch;
- long pad2;
+ unsigned long pad2;
struct {
- long r25, r24, r23, r22, r21, r20;
- long r19, r18, r17, r16, r15, r14, r13;
+ unsigned long r25, r24, r23, r22, r21, r20;
+ unsigned 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 after ensuring brkpt trap */
+ unsigned long efa; /* break pt addr, for break points in delay slots */
+ unsigned long stop_pc; /* give dbg stop_pc after ensuring brkpt trap */
};
#endif /* !__ASSEMBLY__ */
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-04 16:26:59 +0000