42a0bb3f71
printk() takes some locks and could not be used a safe way in NMI
context.
The chance of a deadlock is real especially when printing stacks from
all CPUs. This particular problem has been addressed on x86 by the
commit a9edc88093 ("x86/nmi: Perform a safe NMI stack trace on all
CPUs").
The patchset brings two big advantages. First, it makes the NMI
backtraces safe on all architectures for free. Second, it makes all NMI
messages almost safe on all architectures (the temporary buffer is
limited. We still should keep the number of messages in NMI context at
minimum).
Note that there already are several messages printed in NMI context:
WARN_ON(in_nmi()), BUG_ON(in_nmi()), anything being printed out from MCE
handlers. These are not easy to avoid.
This patch reuses most of the code and makes it generic. It is useful
for all messages and architectures that support NMI.
The alternative printk_func is set when entering and is reseted when
leaving NMI context. It queues IRQ work to copy the messages into the
main ring buffer in a safe context.
__printk_nmi_flush() copies all available messages and reset the buffer.
Then we could use a simple cmpxchg operations to get synchronized with
writers. There is also used a spinlock to get synchronized with other
flushers.
We do not longer use seq_buf because it depends on external lock. It
would be hard to make all supported operations safe for a lockless use.
It would be confusing and error prone to make only some operations safe.
The code is put into separate printk/nmi.c as suggested by Steven
Rostedt. It needs a per-CPU buffer and is compiled only on
architectures that call nmi_enter(). This is achieved by the new
HAVE_NMI Kconfig flag.
The are MN10300 and Xtensa architectures. We need to clean up NMI
handling there first. Let's do it separately.
The patch is heavily based on the draft from Peter Zijlstra, see
https://lkml.org/lkml/2015/6/10/327
[arnd@arndb.de: printk-nmi: use %zu format string for size_t]
[akpm@linux-foundation.org: min_t->min - all types are size_t here]
Signed-off-by: Petr Mladek <pmladek@suse.com>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Jan Kara <jack@suse.cz>
Acked-by: Russell King <rmk+kernel@arm.linux.org.uk> [arm part]
Cc: Daniel Thompson <daniel.thompson@linaro.org>
Cc: Jiri Kosina <jkosina@suse.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: David Miller <davem@davemloft.net>
Cc: Daniel Thompson <daniel.thompson@linaro.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
133 lines
4.1 KiB
C
133 lines
4.1 KiB
C
#ifndef __LINUX_PERCPU_H
|
|
#define __LINUX_PERCPU_H
|
|
|
|
#include <linux/mmdebug.h>
|
|
#include <linux/preempt.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/cpumask.h>
|
|
#include <linux/printk.h>
|
|
#include <linux/pfn.h>
|
|
#include <linux/init.h>
|
|
|
|
#include <asm/percpu.h>
|
|
|
|
/* enough to cover all DEFINE_PER_CPUs in modules */
|
|
#ifdef CONFIG_MODULES
|
|
#define PERCPU_MODULE_RESERVE (8 << 10)
|
|
#else
|
|
#define PERCPU_MODULE_RESERVE 0
|
|
#endif
|
|
|
|
/* minimum unit size, also is the maximum supported allocation size */
|
|
#define PCPU_MIN_UNIT_SIZE PFN_ALIGN(32 << 10)
|
|
|
|
/*
|
|
* Percpu allocator can serve percpu allocations before slab is
|
|
* initialized which allows slab to depend on the percpu allocator.
|
|
* The following two parameters decide how much resource to
|
|
* preallocate for this. Keep PERCPU_DYNAMIC_RESERVE equal to or
|
|
* larger than PERCPU_DYNAMIC_EARLY_SIZE.
|
|
*/
|
|
#define PERCPU_DYNAMIC_EARLY_SLOTS 128
|
|
#define PERCPU_DYNAMIC_EARLY_SIZE (12 << 10)
|
|
|
|
/*
|
|
* PERCPU_DYNAMIC_RESERVE indicates the amount of free area to piggy
|
|
* back on the first chunk for dynamic percpu allocation if arch is
|
|
* manually allocating and mapping it for faster access (as a part of
|
|
* large page mapping for example).
|
|
*
|
|
* The following values give between one and two pages of free space
|
|
* after typical minimal boot (2-way SMP, single disk and NIC) with
|
|
* both defconfig and a distro config on x86_64 and 32. More
|
|
* intelligent way to determine this would be nice.
|
|
*/
|
|
#if BITS_PER_LONG > 32
|
|
#define PERCPU_DYNAMIC_RESERVE (28 << 10)
|
|
#else
|
|
#define PERCPU_DYNAMIC_RESERVE (20 << 10)
|
|
#endif
|
|
|
|
extern void *pcpu_base_addr;
|
|
extern const unsigned long *pcpu_unit_offsets;
|
|
|
|
struct pcpu_group_info {
|
|
int nr_units; /* aligned # of units */
|
|
unsigned long base_offset; /* base address offset */
|
|
unsigned int *cpu_map; /* unit->cpu map, empty
|
|
* entries contain NR_CPUS */
|
|
};
|
|
|
|
struct pcpu_alloc_info {
|
|
size_t static_size;
|
|
size_t reserved_size;
|
|
size_t dyn_size;
|
|
size_t unit_size;
|
|
size_t atom_size;
|
|
size_t alloc_size;
|
|
size_t __ai_size; /* internal, don't use */
|
|
int nr_groups; /* 0 if grouping unnecessary */
|
|
struct pcpu_group_info groups[];
|
|
};
|
|
|
|
enum pcpu_fc {
|
|
PCPU_FC_AUTO,
|
|
PCPU_FC_EMBED,
|
|
PCPU_FC_PAGE,
|
|
|
|
PCPU_FC_NR,
|
|
};
|
|
extern const char * const pcpu_fc_names[PCPU_FC_NR];
|
|
|
|
extern enum pcpu_fc pcpu_chosen_fc;
|
|
|
|
typedef void * (*pcpu_fc_alloc_fn_t)(unsigned int cpu, size_t size,
|
|
size_t align);
|
|
typedef void (*pcpu_fc_free_fn_t)(void *ptr, size_t size);
|
|
typedef void (*pcpu_fc_populate_pte_fn_t)(unsigned long addr);
|
|
typedef int (pcpu_fc_cpu_distance_fn_t)(unsigned int from, unsigned int to);
|
|
|
|
extern struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups,
|
|
int nr_units);
|
|
extern void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai);
|
|
|
|
extern int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
|
|
void *base_addr);
|
|
|
|
#ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK
|
|
extern int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
|
|
size_t atom_size,
|
|
pcpu_fc_cpu_distance_fn_t cpu_distance_fn,
|
|
pcpu_fc_alloc_fn_t alloc_fn,
|
|
pcpu_fc_free_fn_t free_fn);
|
|
#endif
|
|
|
|
#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
|
|
extern int __init pcpu_page_first_chunk(size_t reserved_size,
|
|
pcpu_fc_alloc_fn_t alloc_fn,
|
|
pcpu_fc_free_fn_t free_fn,
|
|
pcpu_fc_populate_pte_fn_t populate_pte_fn);
|
|
#endif
|
|
|
|
extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align);
|
|
extern bool is_kernel_percpu_address(unsigned long addr);
|
|
|
|
#if !defined(CONFIG_SMP) || !defined(CONFIG_HAVE_SETUP_PER_CPU_AREA)
|
|
extern void __init setup_per_cpu_areas(void);
|
|
#endif
|
|
extern void __init percpu_init_late(void);
|
|
|
|
extern void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp);
|
|
extern void __percpu *__alloc_percpu(size_t size, size_t align);
|
|
extern void free_percpu(void __percpu *__pdata);
|
|
extern phys_addr_t per_cpu_ptr_to_phys(void *addr);
|
|
|
|
#define alloc_percpu_gfp(type, gfp) \
|
|
(typeof(type) __percpu *)__alloc_percpu_gfp(sizeof(type), \
|
|
__alignof__(type), gfp)
|
|
#define alloc_percpu(type) \
|
|
(typeof(type) __percpu *)__alloc_percpu(sizeof(type), \
|
|
__alignof__(type))
|
|
|
|
#endif /* __LINUX_PERCPU_H */
|