* Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs.
* Copyright (C) 2008-2009, Red Hat Inc., Ingo Molnar
*/
-#include <linux/interrupt.h>
-#include <linux/mmiotrace.h>
-#include <linux/bootmem.h>
-#include <linux/compiler.h>
-#include <linux/highmem.h>
-#include <linux/kprobes.h>
-#include <linux/uaccess.h>
-#include <linux/vmalloc.h>
-#include <linux/vt_kern.h>
-#include <linux/signal.h>
-#include <linux/kernel.h>
-#include <linux/ptrace.h>
-#include <linux/string.h>
-#include <linux/module.h>
-#include <linux/kdebug.h>
-#include <linux/errno.h>
-#include <linux/magic.h>
-#include <linux/sched.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/mman.h>
-#include <linux/tty.h>
-#include <linux/smp.h>
-#include <linux/mm.h>
-
-#include <asm-generic/sections.h>
-
-#include <asm/kmemcheck.h>
-#include <asm/tlbflush.h>
-#include <asm/pgalloc.h>
-#include <asm/segment.h>
-#include <asm/system.h>
-#include <asm/proto.h>
-#include <asm/traps.h>
-#include <asm/desc.h>
+#include <linux/magic.h> /* STACK_END_MAGIC */
+#include <linux/sched.h> /* test_thread_flag(), ... */
+#include <linux/kdebug.h> /* oops_begin/end, ... */
+#include <linux/module.h> /* search_exception_table */
+#include <linux/bootmem.h> /* max_low_pfn */
+#include <linux/kprobes.h> /* __kprobes, ... */
+#include <linux/mmiotrace.h> /* kmmio_handler, ... */
+
+#include <asm/traps.h> /* dotraplinkage, ... */
+#include <asm/pgalloc.h> /* pgd_*(), ... */
++#include <asm/kmemcheck.h> /* kmemcheck_*(), ... */
/*
* Page fault error code bits:
#include <asm/page.h> /* kmalloc_sizes.h needs PAGE_SIZE */
#include <asm/cache.h> /* kmalloc_sizes.h needs L1_CACHE_BYTES */
#include <linux/compiler.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
+ /*
+ * struct kmem_cache
+ *
+ * manages a cache.
+ */
+
+ struct kmem_cache {
+ /* 1) per-cpu data, touched during every alloc/free */
+ struct array_cache *array[NR_CPUS];
+ /* 2) Cache tunables. Protected by cache_chain_mutex */
+ unsigned int batchcount;
+ unsigned int limit;
+ unsigned int shared;
+
+ unsigned int buffer_size;
+ u32 reciprocal_buffer_size;
+ /* 3) touched by every alloc & free from the backend */
+
+ unsigned int flags; /* constant flags */
+ unsigned int num; /* # of objs per slab */
+
+ /* 4) cache_grow/shrink */
+ /* order of pgs per slab (2^n) */
+ unsigned int gfporder;
+
+ /* force GFP flags, e.g. GFP_DMA */
+ gfp_t gfpflags;
+
+ size_t colour; /* cache colouring range */
+ unsigned int colour_off; /* colour offset */
+ struct kmem_cache *slabp_cache;
+ unsigned int slab_size;
+ unsigned int dflags; /* dynamic flags */
+
+ /* constructor func */
+ void (*ctor)(void *obj);
+
+ /* 5) cache creation/removal */
+ const char *name;
+ struct list_head next;
+
+ /* 6) statistics */
+ #ifdef CONFIG_DEBUG_SLAB
+ unsigned long num_active;
+ unsigned long num_allocations;
+ unsigned long high_mark;
+ unsigned long grown;
+ unsigned long reaped;
+ unsigned long errors;
+ unsigned long max_freeable;
+ unsigned long node_allocs;
+ unsigned long node_frees;
+ unsigned long node_overflow;
+ atomic_t allochit;
+ atomic_t allocmiss;
+ atomic_t freehit;
+ atomic_t freemiss;
+
+ /*
+ * If debugging is enabled, then the allocator can add additional
+ * fields and/or padding to every object. buffer_size contains the total
+ * object size including these internal fields, the following two
+ * variables contain the offset to the user object and its size.
+ */
+ int obj_offset;
+ int obj_size;
+ #endif /* CONFIG_DEBUG_SLAB */
+
+ /*
+ * We put nodelists[] at the end of kmem_cache, because we want to size
+ * this array to nr_node_ids slots instead of MAX_NUMNODES
+ * (see kmem_cache_init())
+ * We still use [MAX_NUMNODES] and not [1] or [0] because cache_cache
+ * is statically defined, so we reserve the max number of nodes.
+ */
+ struct kmem_list3 *nodelists[MAX_NUMNODES];
+ /*
+ * Do not add fields after nodelists[]
+ */
+ };
+
/* Size description struct for general caches. */
struct cache_sizes {
size_t cs_size;
return length;
}
+
static struct ring_buffer_event *
-__rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
- unsigned type, unsigned long length, u64 *ts)
+rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
+ unsigned long length, unsigned long tail,
+ struct buffer_page *commit_page,
+ struct buffer_page *tail_page, u64 *ts)
{
- struct buffer_page *tail_page, *head_page, *reader_page, *commit_page;
- unsigned long tail, write;
+ struct buffer_page *next_page, *head_page, *reader_page;
struct ring_buffer *buffer = cpu_buffer->buffer;
struct ring_buffer_event *event;
- unsigned long flags;
bool lock_taken = false;
+ unsigned long flags;
- commit_page = cpu_buffer->commit_page;
- /* we just need to protect against interrupts */
- barrier();
- tail_page = cpu_buffer->tail_page;
- write = local_add_return(length, &tail_page->write);
- tail = write - length;
+ next_page = tail_page;
- /* See if we shot pass the end of this buffer page */
- if (write > BUF_PAGE_SIZE) {
- struct buffer_page *next_page = tail_page;
+ local_irq_save(flags);
+ /*
+ * Since the write to the buffer is still not
+ * fully lockless, we must be careful with NMIs.
+ * The locks in the writers are taken when a write
+ * crosses to a new page. The locks protect against
+ * races with the readers (this will soon be fixed
+ * with a lockless solution).
+ *
+ * Because we can not protect against NMIs, and we
+ * want to keep traces reentrant, we need to manage
+ * what happens when we are in an NMI.
+ *
+ * NMIs can happen after we take the lock.
+ * If we are in an NMI, only take the lock
+ * if it is not already taken. Otherwise
+ * simply fail.
+ */
+ if (unlikely(in_nmi())) {
+ if (!__raw_spin_trylock(&cpu_buffer->lock)) {
+ cpu_buffer->nmi_dropped++;
+ goto out_reset;
+ }
+ } else
+ __raw_spin_lock(&cpu_buffer->lock);
- local_irq_save(flags);
- /*
- * Since the write to the buffer is still not
- * fully lockless, we must be careful with NMIs.
- * The locks in the writers are taken when a write
- * crosses to a new page. The locks protect against
- * races with the readers (this will soon be fixed
- * with a lockless solution).
- *
- * Because we can not protect against NMIs, and we
- * want to keep traces reentrant, we need to manage
- * what happens when we are in an NMI.
- *
- * NMIs can happen after we take the lock.
- * If we are in an NMI, only take the lock
- * if it is not already taken. Otherwise
- * simply fail.
- */
- if (unlikely(in_nmi())) {
- if (!__raw_spin_trylock(&cpu_buffer->lock))
- goto out_reset;
- } else
- __raw_spin_lock(&cpu_buffer->lock);
+ lock_taken = true;
- lock_taken = true;
+ rb_inc_page(cpu_buffer, &next_page);
- rb_inc_page(cpu_buffer, &next_page);
+ head_page = cpu_buffer->head_page;
+ reader_page = cpu_buffer->reader_page;
- head_page = cpu_buffer->head_page;
- reader_page = cpu_buffer->reader_page;
+ /* we grabbed the lock before incrementing */
+ if (RB_WARN_ON(cpu_buffer, next_page == reader_page))
+ goto out_reset;
- /* we grabbed the lock before incrementing */
- if (RB_WARN_ON(cpu_buffer, next_page == reader_page))
- goto out_reset;
+ /*
+ * If for some reason, we had an interrupt storm that made
+ * it all the way around the buffer, bail, and warn
+ * about it.
+ */
+ if (unlikely(next_page == commit_page)) {
+ cpu_buffer->commit_overrun++;
+ goto out_reset;
+ }
- /*
- * If for some reason, we had an interrupt storm that made
- * it all the way around the buffer, bail, and warn
- * about it.
- */
- if (unlikely(next_page == commit_page)) {
- WARN_ON_ONCE(1);
+ if (next_page == head_page) {
+ if (!(buffer->flags & RB_FL_OVERWRITE))
goto out_reset;
- }
-
- if (next_page == head_page) {
- if (!(buffer->flags & RB_FL_OVERWRITE))
- goto out_reset;
- /* tail_page has not moved yet? */
- if (tail_page == cpu_buffer->tail_page) {
- /* count overflows */
- rb_update_overflow(cpu_buffer);
+ /* tail_page has not moved yet? */
+ if (tail_page == cpu_buffer->tail_page) {
+ /* count overflows */
+ cpu_buffer->overrun +=
+ local_read(&head_page->entries);
- rb_inc_page(cpu_buffer, &head_page);
- cpu_buffer->head_page = head_page;
- cpu_buffer->head_page->read = 0;
- }
+ rb_inc_page(cpu_buffer, &head_page);
+ cpu_buffer->head_page = head_page;
+ cpu_buffer->head_page->read = 0;
}
+ }
- /*
- * If the tail page is still the same as what we think
- * it is, then it is up to us to update the tail
- * pointer.
- */
- if (tail_page == cpu_buffer->tail_page) {
- local_set(&next_page->write, 0);
- local_set(&next_page->page->commit, 0);
- cpu_buffer->tail_page = next_page;
+ /*
+ * If the tail page is still the same as what we think
+ * it is, then it is up to us to update the tail
+ * pointer.
+ */
+ if (tail_page == cpu_buffer->tail_page) {
+ local_set(&next_page->write, 0);
+ local_set(&next_page->entries, 0);
+ local_set(&next_page->page->commit, 0);
+ cpu_buffer->tail_page = next_page;
+
+ /* reread the time stamp */
+ *ts = ring_buffer_time_stamp(buffer, cpu_buffer->cpu);
+ cpu_buffer->tail_page->page->time_stamp = *ts;
+ }
- /* reread the time stamp */
- *ts = ring_buffer_time_stamp(buffer, cpu_buffer->cpu);
- cpu_buffer->tail_page->page->time_stamp = *ts;
- }
+ /*
+ * The actual tail page has moved forward.
+ */
+ if (tail < BUF_PAGE_SIZE) {
+ /* Mark the rest of the page with padding */
+ event = __rb_page_index(tail_page, tail);
++ kmemcheck_annotate_bitfield(event->bitfield);
+ rb_event_set_padding(event);
+ }
- /*
- * The actual tail page has moved forward.
- */
- if (tail < BUF_PAGE_SIZE) {
- /* Mark the rest of the page with padding */
- event = __rb_page_index(tail_page, tail);
- kmemcheck_annotate_bitfield(event->bitfield);
- rb_event_set_padding(event);
- }
+ /* Set the write back to the previous setting */
+ local_sub(length, &tail_page->write);
- if (tail <= BUF_PAGE_SIZE)
- /* Set the write back to the previous setting */
- local_set(&tail_page->write, tail);
+ /*
+ * If this was a commit entry that failed,
+ * increment that too
+ */
+ if (tail_page == cpu_buffer->commit_page &&
+ tail == rb_commit_index(cpu_buffer)) {
+ rb_set_commit_to_write(cpu_buffer);
+ }
- /*
- * If this was a commit entry that failed,
- * increment that too
- */
- if (tail_page == cpu_buffer->commit_page &&
- tail == rb_commit_index(cpu_buffer)) {
- rb_set_commit_to_write(cpu_buffer);
- }
+ __raw_spin_unlock(&cpu_buffer->lock);
+ local_irq_restore(flags);
+
+ /* fail and let the caller try again */
+ return ERR_PTR(-EAGAIN);
+
+ out_reset:
+ /* reset write */
+ local_sub(length, &tail_page->write);
+ if (likely(lock_taken))
__raw_spin_unlock(&cpu_buffer->lock);
- local_irq_restore(flags);
+ local_irq_restore(flags);
+ return NULL;
+}
- /* fail and let the caller try again */
- return ERR_PTR(-EAGAIN);
- }
+static struct ring_buffer_event *
+__rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
+ unsigned type, unsigned long length, u64 *ts)
+{
+ struct buffer_page *tail_page, *commit_page;
+ struct ring_buffer_event *event;
+ unsigned long tail, write;
+
+ commit_page = cpu_buffer->commit_page;
+ /* we just need to protect against interrupts */
+ barrier();
+ tail_page = cpu_buffer->tail_page;
+ write = local_add_return(length, &tail_page->write);
+ tail = write - length;
+
+ /* See if we shot pass the end of this buffer page */
+ if (write > BUF_PAGE_SIZE)
+ return rb_move_tail(cpu_buffer, length, tail,
+ commit_page, tail_page, ts);
/* We reserved something on the buffer */
return NULL;
event = __rb_page_index(tail_page, tail);
+ kmemcheck_annotate_bitfield(event->bitfield);
rb_update_event(event, type, length);
+ /* The passed in type is zero for DATA */
+ if (likely(!type))
+ local_inc(&tail_page->entries);
+
/*
* If this is a commit and the tail is zero, then update
* this page's time stamp.