2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-22 12:14:01 +08:00
linux-next/include/linux/hardirq.h
Steven Rostedt 5a5fb7dbe8 preempt-count: force hardirq-count to max of 10
To add a bit in the preempt_count to be set when in NMI context, we
found that some archs did not have enough bits to spare. This is
due to the hardirq_count being a mask that can hold NR_IRQS.

Some archs allow for over 16000 IRQs, and that would require a mask
of 14 bits. The sofitrq mask is 8 bits and the preempt disable mask
is also 8 bits.  The PREEMP_ACTIVE bit is bit 30, and bit 31 would
make the preempt_count (which is type int) a negative number.
A negative preempt_count is a sign of failure.

Add them up 14+8+8+1+1 you get 32 bits. No room for the NMI bit.

But the hardirq_count is to track the number of nested IRQs, not
the number of total IRQs.  This originally took the paranoid approach
of setting the max nesting to NR_IRQS. But when we have archs with
over 1000 IRQs, it is not practical to think they will ever all
nest on a single CPU. Not to mention that this would most definitely
cause a stack overflow.

This patch sets a max of 10 bits to be used for IRQ nesting.
I did a 'git grep HARDIRQ' to examine all users of HARDIRQ_BITS and
HARDIRQ_MASK, and found that making it a max of 10 would not hurt
anyone. I did find that the m68k expected it to be 8 bits, so
I allow for the archs to set the number to be less than 10.

I removed the setting of HARDIRQ_BITS from the archs that set it
to more than 10. This includes ALPHA, ia64 and avr32.

This will always allow room for the NMI bit, and if we need to allow
for NMI nesting, we have 4 bits to play with.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-12 11:19:05 -05:00

199 lines
5.3 KiB
C

#ifndef LINUX_HARDIRQ_H
#define LINUX_HARDIRQ_H
#include <linux/preempt.h>
#include <linux/smp_lock.h>
#include <linux/lockdep.h>
#include <linux/ftrace_irq.h>
#include <asm/hardirq.h>
#include <asm/system.h>
/*
* We put the hardirq and softirq counter into the preemption
* counter. The bitmask has the following meaning:
*
* - bits 0-7 are the preemption count (max preemption depth: 256)
* - bits 8-15 are the softirq count (max # of softirqs: 256)
*
* The hardirq count can in theory reach the same as NR_IRQS.
* In reality, the number of nested IRQS is limited to the stack
* size as well. For archs with over 1000 IRQS it is not practical
* to expect that they will all nest. We give a max of 10 bits for
* hardirq nesting. An arch may choose to give less than 10 bits.
* m68k expects it to be 8.
*
* - bits 16-25 are the hardirq count (max # of nested hardirqs: 1024)
* - bit 26 is the NMI_MASK
* - bit 28 is the PREEMPT_ACTIVE flag
*
* PREEMPT_MASK: 0x000000ff
* SOFTIRQ_MASK: 0x0000ff00
* HARDIRQ_MASK: 0x03ff0000
* NMI_MASK: 0x04000000
*/
#define PREEMPT_BITS 8
#define SOFTIRQ_BITS 8
#define NMI_BITS 1
#define MAX_HARDIRQ_BITS 10
#ifndef HARDIRQ_BITS
# define HARDIRQ_BITS MAX_HARDIRQ_BITS
#endif
#if HARDIRQ_BITS > MAX_HARDIRQ_BITS
#error HARDIRQ_BITS too high!
#endif
#define PREEMPT_SHIFT 0
#define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS)
#define HARDIRQ_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS)
#define NMI_SHIFT (HARDIRQ_SHIFT + HARDIRQ_BITS)
#define __IRQ_MASK(x) ((1UL << (x))-1)
#define PREEMPT_MASK (__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT)
#define SOFTIRQ_MASK (__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT)
#define HARDIRQ_MASK (__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT)
#define NMI_MASK (__IRQ_MASK(NMI_BITS) << NMI_SHIFT)
#define PREEMPT_OFFSET (1UL << PREEMPT_SHIFT)
#define SOFTIRQ_OFFSET (1UL << SOFTIRQ_SHIFT)
#define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT)
#define NMI_OFFSET (1UL << NMI_SHIFT)
#if PREEMPT_ACTIVE < (1 << (NMI_SHIFT + NMI_BITS))
#error PREEMPT_ACTIVE is too low!
#endif
#define hardirq_count() (preempt_count() & HARDIRQ_MASK)
#define softirq_count() (preempt_count() & SOFTIRQ_MASK)
#define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \
| NMI_MASK))
/*
* Are we doing bottom half or hardware interrupt processing?
* Are we in a softirq context? Interrupt context?
*/
#define in_irq() (hardirq_count())
#define in_softirq() (softirq_count())
#define in_interrupt() (irq_count())
/*
* Are we in NMI context?
*/
#define in_nmi() (preempt_count() & NMI_MASK)
#if defined(CONFIG_PREEMPT)
# define PREEMPT_INATOMIC_BASE kernel_locked()
# define PREEMPT_CHECK_OFFSET 1
#else
# define PREEMPT_INATOMIC_BASE 0
# define PREEMPT_CHECK_OFFSET 0
#endif
/*
* Are we running in atomic context? WARNING: this macro cannot
* always detect atomic context; in particular, it cannot know about
* held spinlocks in non-preemptible kernels. Thus it should not be
* used in the general case to determine whether sleeping is possible.
* Do not use in_atomic() in driver code.
*/
#define in_atomic() ((preempt_count() & ~PREEMPT_ACTIVE) != PREEMPT_INATOMIC_BASE)
/*
* Check whether we were atomic before we did preempt_disable():
* (used by the scheduler, *after* releasing the kernel lock)
*/
#define in_atomic_preempt_off() \
((preempt_count() & ~PREEMPT_ACTIVE) != PREEMPT_CHECK_OFFSET)
#ifdef CONFIG_PREEMPT
# define preemptible() (preempt_count() == 0 && !irqs_disabled())
# define IRQ_EXIT_OFFSET (HARDIRQ_OFFSET-1)
#else
# define preemptible() 0
# define IRQ_EXIT_OFFSET HARDIRQ_OFFSET
#endif
#ifdef CONFIG_SMP
extern void synchronize_irq(unsigned int irq);
#else
# define synchronize_irq(irq) barrier()
#endif
struct task_struct;
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
static inline void account_system_vtime(struct task_struct *tsk)
{
}
#endif
#if defined(CONFIG_NO_HZ) && !defined(CONFIG_CLASSIC_RCU)
extern void rcu_irq_enter(void);
extern void rcu_irq_exit(void);
extern void rcu_nmi_enter(void);
extern void rcu_nmi_exit(void);
#else
# define rcu_irq_enter() do { } while (0)
# define rcu_irq_exit() do { } while (0)
# define rcu_nmi_enter() do { } while (0)
# define rcu_nmi_exit() do { } while (0)
#endif /* #if defined(CONFIG_NO_HZ) && !defined(CONFIG_CLASSIC_RCU) */
/*
* It is safe to do non-atomic ops on ->hardirq_context,
* because NMI handlers may not preempt and the ops are
* always balanced, so the interrupted value of ->hardirq_context
* will always be restored.
*/
#define __irq_enter() \
do { \
account_system_vtime(current); \
add_preempt_count(HARDIRQ_OFFSET); \
trace_hardirq_enter(); \
} while (0)
/*
* Enter irq context (on NO_HZ, update jiffies):
*/
extern void irq_enter(void);
/*
* Exit irq context without processing softirqs:
*/
#define __irq_exit() \
do { \
trace_hardirq_exit(); \
account_system_vtime(current); \
sub_preempt_count(HARDIRQ_OFFSET); \
} while (0)
/*
* Exit irq context and process softirqs if needed:
*/
extern void irq_exit(void);
#define nmi_enter() \
do { \
ftrace_nmi_enter(); \
BUG_ON(in_nmi()); \
add_preempt_count(NMI_OFFSET); \
lockdep_off(); \
rcu_nmi_enter(); \
__irq_enter(); \
} while (0)
#define nmi_exit() \
do { \
__irq_exit(); \
rcu_nmi_exit(); \
lockdep_on(); \
BUG_ON(!in_nmi()); \
sub_preempt_count(NMI_OFFSET); \
ftrace_nmi_exit(); \
} while (0)
#endif /* LINUX_HARDIRQ_H */