#include <asm/cmpxchg.h>
#include <asm/war.h>
+ /*
+ * Using a branch-likely instruction to check the result of an sc instruction
+ * works around a bug present in R10000 CPUs prior to revision 3.0 that could
+ * cause ll-sc sequences to execute non-atomically.
+ */
+ #if R10000_LLSC_WAR
+ # define __scbeqz "beqzl"
+ #else
+ # define __scbeqz "beqz"
+ #endif
+
#define ATOMIC_INIT(i) { (i) }
/*
#define ATOMIC_OP(op, c_op, asm_op) \
static __inline__ void atomic_##op(int i, atomic_t * v) \
{ \
- if (kernel_uses_llsc && R10000_LLSC_WAR) { \
+ if (kernel_uses_llsc) { \
int temp; \
\
__asm__ __volatile__( \
- " .set arch=r4000 \n" \
+ " .set "MIPS_ISA_LEVEL" \n" \
"1: ll %0, %1 # atomic_" #op " \n" \
" " #asm_op " %0, %2 \n" \
" sc %0, %1 \n" \
- " beqzl %0, 1b \n" \
+ "\t" __scbeqz " %0, 1b \n" \
" .set mips0 \n" \
: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter) \
: "Ir" (i)); \
- } else if (kernel_uses_llsc) { \
- int temp; \
- \
- do { \
- __asm__ __volatile__( \
- " .set "MIPS_ISA_LEVEL" \n" \
- " ll %0, %1 # atomic_" #op "\n" \
- " " #asm_op " %0, %2 \n" \
- " sc %0, %1 \n" \
- " .set mips0 \n" \
- : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter) \
- : "Ir" (i)); \
- } while (unlikely(!temp)); \
} else { \
unsigned long flags; \
\
{ \
int result; \
\
- if (kernel_uses_llsc && R10000_LLSC_WAR) { \
+ if (kernel_uses_llsc) { \
int temp; \
\
__asm__ __volatile__( \
- " .set arch=r4000 \n" \
+ " .set "MIPS_ISA_LEVEL" \n" \
"1: ll %1, %2 # atomic_" #op "_return \n" \
" " #asm_op " %0, %1, %3 \n" \
" sc %0, %2 \n" \
- " beqzl %0, 1b \n" \
+ "\t" __scbeqz " %0, 1b \n" \
" " #asm_op " %0, %1, %3 \n" \
" .set mips0 \n" \
: "=&r" (result), "=&r" (temp), \
"+" GCC_OFF_SMALL_ASM() (v->counter) \
: "Ir" (i)); \
- } else if (kernel_uses_llsc) { \
- int temp; \
- \
- do { \
- __asm__ __volatile__( \
- " .set "MIPS_ISA_LEVEL" \n" \
- " ll %1, %2 # atomic_" #op "_return \n" \
- " " #asm_op " %0, %1, %3 \n" \
- " sc %0, %2 \n" \
- " .set mips0 \n" \
- : "=&r" (result), "=&r" (temp), \
- "+" GCC_OFF_SMALL_ASM() (v->counter) \
- : "Ir" (i)); \
- } while (unlikely(!result)); \
- \
- result = temp; result c_op i; \
} else { \
unsigned long flags; \
\
{ \
int result; \
\
- if (kernel_uses_llsc && R10000_LLSC_WAR) { \
+ if (kernel_uses_llsc) { \
int temp; \
\
__asm__ __volatile__( \
- " .set arch=r4000 \n" \
+ " .set "MIPS_ISA_LEVEL" \n" \
"1: ll %1, %2 # atomic_fetch_" #op " \n" \
" " #asm_op " %0, %1, %3 \n" \
" sc %0, %2 \n" \
- " beqzl %0, 1b \n" \
+ "\t" __scbeqz " %0, 1b \n" \
" move %0, %1 \n" \
" .set mips0 \n" \
: "=&r" (result), "=&r" (temp), \
"+" GCC_OFF_SMALL_ASM() (v->counter) \
: "Ir" (i)); \
- } else if (kernel_uses_llsc) { \
- int temp; \
- \
- do { \
- __asm__ __volatile__( \
- " .set "MIPS_ISA_LEVEL" \n" \
- " ll %1, %2 # atomic_fetch_" #op " \n" \
- " " #asm_op " %0, %1, %3 \n" \
- " sc %0, %2 \n" \
- " .set mips0 \n" \
- : "=&r" (result), "=&r" (temp), \
- "+" GCC_OFF_SMALL_ASM() (v->counter) \
- : "Ir" (i)); \
- } while (unlikely(!result)); \
- \
- result = temp; \
} else { \
unsigned long flags; \
\
smp_mb__before_llsc();
- if (kernel_uses_llsc && R10000_LLSC_WAR) {
- int temp;
-
- __asm__ __volatile__(
- " .set arch=r4000 \n"
- "1: ll %1, %2 # atomic_sub_if_positive\n"
- " subu %0, %1, %3 \n"
- " bltz %0, 1f \n"
- " sc %0, %2 \n"
- " .set noreorder \n"
- " beqzl %0, 1b \n"
- " subu %0, %1, %3 \n"
- " .set reorder \n"
- "1: \n"
- " .set mips0 \n"
- : "=&r" (result), "=&r" (temp),
- "+" GCC_OFF_SMALL_ASM() (v->counter)
- : "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter)
- : "memory");
- } else if (kernel_uses_llsc) {
+ if (kernel_uses_llsc) {
int temp;
__asm__ __volatile__(
" .set "MIPS_ISA_LEVEL" \n"
"1: ll %1, %2 # atomic_sub_if_positive\n"
" subu %0, %1, %3 \n"
+ " move %1, %0 \n"
" bltz %0, 1f \n"
- " sc %0, %2 \n"
- " .set noreorder \n"
- " beqz %0, 1b \n"
- " subu %0, %1, %3 \n"
- " .set reorder \n"
+ " sc %1, %2 \n"
+ "\t" __scbeqz " %1, 1b \n"
"1: \n"
" .set mips0 \n"
: "=&r" (result), "=&r" (temp),
#define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
#define atomic_xchg(v, new) (xchg(&((v)->counter), (new)))
-/**
- * __atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
-{
- int c, old;
- c = atomic_read(v);
- for (;;) {
- if (unlikely(c == (u)))
- break;
- old = atomic_cmpxchg((v), c, c + (a));
- if (likely(old == c))
- break;
- c = old;
- }
- return c;
-}
-
-#define atomic_dec_return(v) atomic_sub_return(1, (v))
-#define atomic_inc_return(v) atomic_add_return(1, (v))
-
-/*
- * atomic_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_sub_and_test(i, v) (atomic_sub_return((i), (v)) == 0)
-
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-
-/*
- * atomic_dec_and_test - decrement by 1 and test
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0)
-
/*
* atomic_dec_if_positive - decrement by 1 if old value positive
* @v: pointer of type atomic_t
*/
#define atomic_dec_if_positive(v) atomic_sub_if_positive(1, v)
-/*
- * atomic_inc - increment atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1.
- */
-#define atomic_inc(v) atomic_add(1, (v))
-
-/*
- * atomic_dec - decrement and test
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1.
- */
-#define atomic_dec(v) atomic_sub(1, (v))
-
-/*
- * atomic_add_negative - add and test if negative
- * @v: pointer of type atomic_t
- * @i: integer value to add
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-#define atomic_add_negative(i, v) (atomic_add_return(i, (v)) < 0)
-
#ifdef CONFIG_64BIT
#define ATOMIC64_INIT(i) { (i) }
#define ATOMIC64_OP(op, c_op, asm_op) \
static __inline__ void atomic64_##op(long i, atomic64_t * v) \
{ \
- if (kernel_uses_llsc && R10000_LLSC_WAR) { \
+ if (kernel_uses_llsc) { \
long temp; \
\
__asm__ __volatile__( \
- " .set arch=r4000 \n" \
+ " .set "MIPS_ISA_LEVEL" \n" \
"1: lld %0, %1 # atomic64_" #op " \n" \
" " #asm_op " %0, %2 \n" \
" scd %0, %1 \n" \
- " beqzl %0, 1b \n" \
+ "\t" __scbeqz " %0, 1b \n" \
" .set mips0 \n" \
: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter) \
: "Ir" (i)); \
- } else if (kernel_uses_llsc) { \
- long temp; \
- \
- do { \
- __asm__ __volatile__( \
- " .set "MIPS_ISA_LEVEL" \n" \
- " lld %0, %1 # atomic64_" #op "\n" \
- " " #asm_op " %0, %2 \n" \
- " scd %0, %1 \n" \
- " .set mips0 \n" \
- : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter) \
- : "Ir" (i)); \
- } while (unlikely(!temp)); \
} else { \
unsigned long flags; \
\
{ \
long result; \
\
- if (kernel_uses_llsc && R10000_LLSC_WAR) { \
+ if (kernel_uses_llsc) { \
long temp; \
\
__asm__ __volatile__( \
- " .set arch=r4000 \n" \
+ " .set "MIPS_ISA_LEVEL" \n" \
"1: lld %1, %2 # atomic64_" #op "_return\n" \
" " #asm_op " %0, %1, %3 \n" \
" scd %0, %2 \n" \
- " beqzl %0, 1b \n" \
+ "\t" __scbeqz " %0, 1b \n" \
" " #asm_op " %0, %1, %3 \n" \
" .set mips0 \n" \
: "=&r" (result), "=&r" (temp), \
"+" GCC_OFF_SMALL_ASM() (v->counter) \
: "Ir" (i)); \
- } else if (kernel_uses_llsc) { \
- long temp; \
- \
- do { \
- __asm__ __volatile__( \
- " .set "MIPS_ISA_LEVEL" \n" \
- " lld %1, %2 # atomic64_" #op "_return\n" \
- " " #asm_op " %0, %1, %3 \n" \
- " scd %0, %2 \n" \
- " .set mips0 \n" \
- : "=&r" (result), "=&r" (temp), \
- "=" GCC_OFF_SMALL_ASM() (v->counter) \
- : "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter) \
- : "memory"); \
- } while (unlikely(!result)); \
- \
- result = temp; result c_op i; \
} else { \
unsigned long flags; \
\
long temp; \
\
__asm__ __volatile__( \
- " .set arch=r4000 \n" \
+ " .set "MIPS_ISA_LEVEL" \n" \
"1: lld %1, %2 # atomic64_fetch_" #op "\n" \
" " #asm_op " %0, %1, %3 \n" \
" scd %0, %2 \n" \
- " beqzl %0, 1b \n" \
+ "\t" __scbeqz " %0, 1b \n" \
" move %0, %1 \n" \
" .set mips0 \n" \
: "=&r" (result), "=&r" (temp), \
"+" GCC_OFF_SMALL_ASM() (v->counter) \
: "Ir" (i)); \
- } else if (kernel_uses_llsc) { \
- long temp; \
- \
- do { \
- __asm__ __volatile__( \
- " .set "MIPS_ISA_LEVEL" \n" \
- " lld %1, %2 # atomic64_fetch_" #op "\n" \
- " " #asm_op " %0, %1, %3 \n" \
- " scd %0, %2 \n" \
- " .set mips0 \n" \
- : "=&r" (result), "=&r" (temp), \
- "=" GCC_OFF_SMALL_ASM() (v->counter) \
- : "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter) \
- : "memory"); \
- } while (unlikely(!result)); \
- \
- result = temp; \
} else { \
unsigned long flags; \
\
smp_mb__before_llsc();
- if (kernel_uses_llsc && R10000_LLSC_WAR) {
- long temp;
-
- __asm__ __volatile__(
- " .set arch=r4000 \n"
- "1: lld %1, %2 # atomic64_sub_if_positive\n"
- " dsubu %0, %1, %3 \n"
- " bltz %0, 1f \n"
- " scd %0, %2 \n"
- " .set noreorder \n"
- " beqzl %0, 1b \n"
- " dsubu %0, %1, %3 \n"
- " .set reorder \n"
- "1: \n"
- " .set mips0 \n"
- : "=&r" (result), "=&r" (temp),
- "=" GCC_OFF_SMALL_ASM() (v->counter)
- : "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter)
- : "memory");
- } else if (kernel_uses_llsc) {
+ if (kernel_uses_llsc) {
long temp;
__asm__ __volatile__(
" .set "MIPS_ISA_LEVEL" \n"
"1: lld %1, %2 # atomic64_sub_if_positive\n"
" dsubu %0, %1, %3 \n"
+ " move %1, %0 \n"
" bltz %0, 1f \n"
- " scd %0, %2 \n"
- " .set noreorder \n"
- " beqz %0, 1b \n"
- " dsubu %0, %1, %3 \n"
- " .set reorder \n"
+ " scd %1, %2 \n"
+ "\t" __scbeqz " %1, 1b \n"
"1: \n"
" .set mips0 \n"
: "=&r" (result), "=&r" (temp),
((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
#define atomic64_xchg(v, new) (xchg(&((v)->counter), (new)))
-/**
- * atomic64_add_unless - add unless the number is a given value
- * @v: pointer of type atomic64_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns true iff @v was not @u.
- */
-static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
-{
- long c, old;
- c = atomic64_read(v);
- for (;;) {
- if (unlikely(c == (u)))
- break;
- old = atomic64_cmpxchg((v), c, c + (a));
- if (likely(old == c))
- break;
- c = old;
- }
- return c != (u);
-}
-
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
-#define atomic64_dec_return(v) atomic64_sub_return(1, (v))
-#define atomic64_inc_return(v) atomic64_add_return(1, (v))
-
-/*
- * atomic64_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic64_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-#define atomic64_sub_and_test(i, v) (atomic64_sub_return((i), (v)) == 0)
-
-/*
- * atomic64_inc_and_test - increment and test
- * @v: pointer of type atomic64_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
-
-/*
- * atomic64_dec_and_test - decrement by 1 and test
- * @v: pointer of type atomic64_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0)
-
/*
* atomic64_dec_if_positive - decrement by 1 if old value positive
* @v: pointer of type atomic64_t
*/
#define atomic64_dec_if_positive(v) atomic64_sub_if_positive(1, v)
-/*
- * atomic64_inc - increment atomic variable
- * @v: pointer of type atomic64_t
- *
- * Atomically increments @v by 1.
- */
-#define atomic64_inc(v) atomic64_add(1, (v))
-
-/*
- * atomic64_dec - decrement and test
- * @v: pointer of type atomic64_t
- *
- * Atomically decrements @v by 1.
- */
-#define atomic64_dec(v) atomic64_sub(1, (v))
-
-/*
- * atomic64_add_negative - add and test if negative
- * @v: pointer of type atomic64_t
- * @i: integer value to add
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-#define atomic64_add_negative(i, v) (atomic64_add_return(i, (v)) < 0)
-
#endif /* CONFIG_64BIT */
#endif /* _ASM_ATOMIC_H */
#include <linux/kallsyms.h>
#include <linux/random.h>
#include <linux/prctl.h>
+#include <linux/nmi.h>
+ #include <linux/cpu.h>
#include <asm/asm.h>
#include <asm/bootinfo.h>
return sp & ALMASK;
}
-static void arch_dump_stack(void *info)
+static DEFINE_PER_CPU(call_single_data_t, backtrace_csd);
+static struct cpumask backtrace_csd_busy;
+
+static void handle_backtrace(void *info)
{
- struct pt_regs *regs;
+ nmi_cpu_backtrace(get_irq_regs());
+ cpumask_clear_cpu(smp_processor_id(), &backtrace_csd_busy);
+}
- regs = get_irq_regs();
+static void raise_backtrace(cpumask_t *mask)
+{
+ call_single_data_t *csd;
+ int cpu;
- if (regs)
- show_regs(regs);
+ for_each_cpu(cpu, mask) {
+ /*
+ * If we previously sent an IPI to the target CPU & it hasn't
+ * cleared its bit in the busy cpumask then it didn't handle
+ * our previous IPI & it's not safe for us to reuse the
+ * call_single_data_t.
+ */
+ if (cpumask_test_and_set_cpu(cpu, &backtrace_csd_busy)) {
+ pr_warn("Unable to send backtrace IPI to CPU%u - perhaps it hung?\n",
+ cpu);
+ continue;
+ }
- dump_stack();
+ csd = &per_cpu(backtrace_csd, cpu);
+ csd->func = handle_backtrace;
+ smp_call_function_single_async(cpu, csd);
+ }
}
void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self)
{
- long this_cpu = get_cpu();
-
- if (cpumask_test_cpu(this_cpu, mask) && !exclude_self)
- dump_stack();
-
- smp_call_function_many(mask, arch_dump_stack, NULL, 1);
-
- put_cpu();
+ nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace);
}
int mips_get_process_fp_mode(struct task_struct *task)
return value;
}
- static void prepare_for_fp_mode_switch(void *info)
+ static long prepare_for_fp_mode_switch(void *unused)
{
- struct mm_struct *mm = info;
-
- if (current->mm == mm)
- lose_fpu(1);
+ /*
+ * This is icky, but we use this to simply ensure that all CPUs have
+ * context switched, regardless of whether they were previously running
+ * kernel or user code. This ensures that no CPU currently has its FPU
+ * enabled, or is about to attempt to enable it through any path other
+ * than enable_restore_fp_context() which will wait appropriately for
+ * fp_mode_switching to be zero.
+ */
+ return 0;
}
int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
{
const unsigned int known_bits = PR_FP_MODE_FR | PR_FP_MODE_FRE;
struct task_struct *t;
- int max_users;
+ struct cpumask process_cpus;
+ int cpu;
/* If nothing to change, return right away, successfully. */
if (value == mips_get_process_fp_mode(task))
if (!(value & PR_FP_MODE_FR) && raw_cpu_has_fpu && cpu_has_mips_r6)
return -EOPNOTSUPP;
- /* Proceed with the mode switch */
- preempt_disable();
-
- /* Save FP & vector context, then disable FPU & MSA */
- if (task->signal == current->signal)
- lose_fpu(1);
-
- /* Prevent any threads from obtaining live FP context */
- atomic_set(&task->mm->context.fp_mode_switching, 1);
- smp_mb__after_atomic();
-
- /*
- * If there are multiple online CPUs then force any which are running
- * threads in this process to lose their FPU context, which they can't
- * regain until fp_mode_switching is cleared later.
- */
- if (num_online_cpus() > 1) {
- /* No need to send an IPI for the local CPU */
- max_users = (task->mm == current->mm) ? 1 : 0;
-
- if (atomic_read(¤t->mm->mm_users) > max_users)
- smp_call_function(prepare_for_fp_mode_switch,
- (void *)current->mm, 1);
- }
-
- /*
- * There are now no threads of the process with live FP context, so it
- * is safe to proceed with the FP mode switch.
- */
+ /* Indicate the new FP mode in each thread */
for_each_thread(task, t) {
/* Update desired FP register width */
if (value & PR_FP_MODE_FR) {
clear_tsk_thread_flag(t, TIF_HYBRID_FPREGS);
}
- /* Allow threads to use FP again */
- atomic_set(&task->mm->context.fp_mode_switching, 0);
- preempt_enable();
+ /*
+ * We need to ensure that all threads in the process have switched mode
+ * before returning, in order to allow userland to not worry about
+ * races. We can do this by forcing all CPUs that any thread in the
+ * process may be running on to schedule something else - in this case
+ * prepare_for_fp_mode_switch().
+ *
+ * We begin by generating a mask of all CPUs that any thread in the
+ * process may be running on.
+ */
+ cpumask_clear(&process_cpus);
+ for_each_thread(task, t)
+ cpumask_set_cpu(task_cpu(t), &process_cpus);
+
+ /*
+ * Now we schedule prepare_for_fp_mode_switch() on each of those CPUs.
+ *
+ * The CPUs may have rescheduled already since we switched mode or
+ * generated the cpumask, but that doesn't matter. If the task in this
+ * process is scheduled out then our scheduling
+ * prepare_for_fp_mode_switch() will simply be redundant. If it's
+ * scheduled in then it will already have picked up the new FP mode
+ * whilst doing so.
+ */
+ get_online_cpus();
+ for_each_cpu_and(cpu, &process_cpus, cpu_online_mask)
+ work_on_cpu(cpu, prepare_for_fp_mode_switch, NULL);
+ put_online_cpus();
wake_up_var(&task->mm->context.fp_mode_switching);