aboutsummaryrefslogtreecommitdiff
path: root/arch/powerpc/oprofile/cell
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/oprofile/cell')
-rw-r--r--arch/powerpc/oprofile/cell/pr_util.h26
-rw-r--r--arch/powerpc/oprofile/cell/spu_profiler.c65
-rw-r--r--arch/powerpc/oprofile/cell/spu_task_sync.c264
-rw-r--r--arch/powerpc/oprofile/cell/vma_map.c15
4 files changed, 299 insertions, 71 deletions
diff --git a/arch/powerpc/oprofile/cell/pr_util.h b/arch/powerpc/oprofile/cell/pr_util.h
index 22e4e8d4eb2..964b93974d8 100644
--- a/arch/powerpc/oprofile/cell/pr_util.h
+++ b/arch/powerpc/oprofile/cell/pr_util.h
@@ -24,6 +24,15 @@
#define SKIP_GENERIC_SYNC 0
#define SYNC_START_ERROR -1
#define DO_GENERIC_SYNC 1
+#define SPUS_PER_NODE 8
+#define DEFAULT_TIMER_EXPIRE (HZ / 10)
+
+extern struct delayed_work spu_work;
+extern int spu_prof_running;
+
+#define TRACE_ARRAY_SIZE 1024
+
+extern spinlock_t oprof_spu_smpl_arry_lck;
struct spu_overlay_info { /* map of sections within an SPU overlay */
unsigned int vma; /* SPU virtual memory address from elf */
@@ -62,11 +71,19 @@ struct vma_to_fileoffset_map { /* map of sections within an SPU program */
};
+struct spu_buffer {
+ int last_guard_val;
+ int ctx_sw_seen;
+ unsigned long *buff;
+ unsigned int head, tail;
+};
+
+
/* The three functions below are for maintaining and accessing
* the vma-to-fileoffset map.
*/
struct vma_to_fileoffset_map *create_vma_map(const struct spu *spu,
- u64 objectid);
+ unsigned long objectid);
unsigned int vma_map_lookup(struct vma_to_fileoffset_map *map,
unsigned int vma, const struct spu *aSpu,
int *grd_val);
@@ -76,10 +93,11 @@ void vma_map_free(struct vma_to_fileoffset_map *map);
* Entry point for SPU profiling.
* cycles_reset is the SPU_CYCLES count value specified by the user.
*/
-int start_spu_profiling(unsigned int cycles_reset);
-
-void stop_spu_profiling(void);
+int start_spu_profiling_cycles(unsigned int cycles_reset);
+void start_spu_profiling_events(void);
+void stop_spu_profiling_cycles(void);
+void stop_spu_profiling_events(void);
/* add the necessary profiling hooks */
int spu_sync_start(void);
diff --git a/arch/powerpc/oprofile/cell/spu_profiler.c b/arch/powerpc/oprofile/cell/spu_profiler.c
index 380d7e21753..b129d007e7f 100644
--- a/arch/powerpc/oprofile/cell/spu_profiler.c
+++ b/arch/powerpc/oprofile/cell/spu_profiler.c
@@ -16,24 +16,34 @@
#include <linux/smp.h>
#include <linux/slab.h>
#include <asm/cell-pmu.h>
+#include <asm/time.h>
#include "pr_util.h"
-#define TRACE_ARRAY_SIZE 1024
#define SCALE_SHIFT 14
static u32 *samples;
-static int spu_prof_running;
+/* spu_prof_running is a flag used to indicate if spu profiling is enabled
+ * or not. It is set by the routines start_spu_profiling_cycles() and
+ * start_spu_profiling_events(). The flag is cleared by the routines
+ * stop_spu_profiling_cycles() and stop_spu_profiling_events(). These
+ * routines are called via global_start() and global_stop() which are called in
+ * op_powerpc_start() and op_powerpc_stop(). These routines are called once
+ * per system as a result of the user starting/stopping oprofile. Hence, only
+ * one CPU per user at a time will be changing the value of spu_prof_running.
+ * In general, OProfile does not protect against multiple users trying to run
+ * OProfile at a time.
+ */
+int spu_prof_running;
static unsigned int profiling_interval;
#define NUM_SPU_BITS_TRBUF 16
#define SPUS_PER_TB_ENTRY 4
-#define SPUS_PER_NODE 8
#define SPU_PC_MASK 0xFFFF
-static DEFINE_SPINLOCK(sample_array_lock);
-unsigned long sample_array_lock_flags;
+DEFINE_SPINLOCK(oprof_spu_smpl_arry_lck);
+unsigned long oprof_spu_smpl_arry_lck_flags;
void set_spu_profiling_frequency(unsigned int freq_khz, unsigned int cycles_reset)
{
@@ -50,7 +60,7 @@ void set_spu_profiling_frequency(unsigned int freq_khz, unsigned int cycles_rese
* of precision. This is close enough for the purpose at hand.
*
* The value of the timeout should be small enough that the hw
- * trace buffer will not get more then about 1/3 full for the
+ * trace buffer will not get more than about 1/3 full for the
* maximum user specified (the LFSR value) hw sampling frequency.
* This is to ensure the trace buffer will never fill even if the
* kernel thread scheduling varies under a heavy system load.
@@ -146,13 +156,13 @@ static enum hrtimer_restart profile_spus(struct hrtimer *timer)
* sample array must be loaded and then processed for a given
* cpu. The sample array is not per cpu.
*/
- spin_lock_irqsave(&sample_array_lock,
- sample_array_lock_flags);
+ spin_lock_irqsave(&oprof_spu_smpl_arry_lck,
+ oprof_spu_smpl_arry_lck_flags);
num_samples = cell_spu_pc_collection(cpu);
if (num_samples == 0) {
- spin_unlock_irqrestore(&sample_array_lock,
- sample_array_lock_flags);
+ spin_unlock_irqrestore(&oprof_spu_smpl_arry_lck,
+ oprof_spu_smpl_arry_lck_flags);
continue;
}
@@ -163,8 +173,8 @@ static enum hrtimer_restart profile_spus(struct hrtimer *timer)
num_samples);
}
- spin_unlock_irqrestore(&sample_array_lock,
- sample_array_lock_flags);
+ spin_unlock_irqrestore(&oprof_spu_smpl_arry_lck,
+ oprof_spu_smpl_arry_lck_flags);
}
smp_wmb(); /* insure spu event buffer updates are written */
@@ -183,20 +193,20 @@ static enum hrtimer_restart profile_spus(struct hrtimer *timer)
static struct hrtimer timer;
/*
- * Entry point for SPU profiling.
+ * Entry point for SPU cycle profiling.
* NOTE: SPU profiling is done system-wide, not per-CPU.
*
* cycles_reset is the count value specified by the user when
* setting up OProfile to count SPU_CYCLES.
*/
-int start_spu_profiling(unsigned int cycles_reset)
+int start_spu_profiling_cycles(unsigned int cycles_reset)
{
ktime_t kt;
pr_debug("timer resolution: %lu\n", TICK_NSEC);
kt = ktime_set(0, profiling_interval);
hrtimer_init(&timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
- timer.expires = kt;
+ hrtimer_set_expires(&timer, kt);
timer.function = profile_spus;
/* Allocate arrays for collecting SPU PC samples */
@@ -208,14 +218,35 @@ int start_spu_profiling(unsigned int cycles_reset)
spu_prof_running = 1;
hrtimer_start(&timer, kt, HRTIMER_MODE_REL);
+ schedule_delayed_work(&spu_work, DEFAULT_TIMER_EXPIRE);
return 0;
}
-void stop_spu_profiling(void)
+/*
+ * Entry point for SPU event profiling.
+ * NOTE: SPU profiling is done system-wide, not per-CPU.
+ *
+ * cycles_reset is the count value specified by the user when
+ * setting up OProfile to count SPU_CYCLES.
+ */
+void start_spu_profiling_events(void)
+{
+ spu_prof_running = 1;
+ schedule_delayed_work(&spu_work, DEFAULT_TIMER_EXPIRE);
+
+ return;
+}
+
+void stop_spu_profiling_cycles(void)
{
spu_prof_running = 0;
hrtimer_cancel(&timer);
kfree(samples);
- pr_debug("SPU_PROF: stop_spu_profiling issued\n");
+ pr_debug("SPU_PROF: stop_spu_profiling_cycles issued\n");
+}
+
+void stop_spu_profiling_events(void)
+{
+ spu_prof_running = 0;
}
diff --git a/arch/powerpc/oprofile/cell/spu_task_sync.c b/arch/powerpc/oprofile/cell/spu_task_sync.c
index 257b13cb18a..28f1af2db1f 100644
--- a/arch/powerpc/oprofile/cell/spu_task_sync.c
+++ b/arch/powerpc/oprofile/cell/spu_task_sync.c
@@ -26,6 +26,7 @@
#include <linux/notifier.h>
#include <linux/numa.h>
#include <linux/oprofile.h>
+#include <linux/slab.h>
#include <linux/spinlock.h>
#include "pr_util.h"
@@ -35,7 +36,102 @@ static DEFINE_SPINLOCK(buffer_lock);
static DEFINE_SPINLOCK(cache_lock);
static int num_spu_nodes;
int spu_prof_num_nodes;
-int last_guard_val[MAX_NUMNODES * 8];
+
+struct spu_buffer spu_buff[MAX_NUMNODES * SPUS_PER_NODE];
+struct delayed_work spu_work;
+static unsigned max_spu_buff;
+
+static void spu_buff_add(unsigned long int value, int spu)
+{
+ /* spu buff is a circular buffer. Add entries to the
+ * head. Head is the index to store the next value.
+ * The buffer is full when there is one available entry
+ * in the queue, i.e. head and tail can't be equal.
+ * That way we can tell the difference between the
+ * buffer being full versus empty.
+ *
+ * ASSUPTION: the buffer_lock is held when this function
+ * is called to lock the buffer, head and tail.
+ */
+ int full = 1;
+
+ if (spu_buff[spu].head >= spu_buff[spu].tail) {
+ if ((spu_buff[spu].head - spu_buff[spu].tail)
+ < (max_spu_buff - 1))
+ full = 0;
+
+ } else if (spu_buff[spu].tail > spu_buff[spu].head) {
+ if ((spu_buff[spu].tail - spu_buff[spu].head)
+ > 1)
+ full = 0;
+ }
+
+ if (!full) {
+ spu_buff[spu].buff[spu_buff[spu].head] = value;
+ spu_buff[spu].head++;
+
+ if (spu_buff[spu].head >= max_spu_buff)
+ spu_buff[spu].head = 0;
+ } else {
+ /* From the user's perspective make the SPU buffer
+ * size management/overflow look like we are using
+ * per cpu buffers. The user uses the same
+ * per cpu parameter to adjust the SPU buffer size.
+ * Increment the sample_lost_overflow to inform
+ * the user the buffer size needs to be increased.
+ */
+ oprofile_cpu_buffer_inc_smpl_lost();
+ }
+}
+
+/* This function copies the per SPU buffers to the
+ * OProfile kernel buffer.
+ */
+void sync_spu_buff(void)
+{
+ int spu;
+ unsigned long flags;
+ int curr_head;
+
+ for (spu = 0; spu < num_spu_nodes; spu++) {
+ /* In case there was an issue and the buffer didn't
+ * get created skip it.
+ */
+ if (spu_buff[spu].buff == NULL)
+ continue;
+
+ /* Hold the lock to make sure the head/tail
+ * doesn't change while spu_buff_add() is
+ * deciding if the buffer is full or not.
+ * Being a little paranoid.
+ */
+ spin_lock_irqsave(&buffer_lock, flags);
+ curr_head = spu_buff[spu].head;
+ spin_unlock_irqrestore(&buffer_lock, flags);
+
+ /* Transfer the current contents to the kernel buffer.
+ * data can still be added to the head of the buffer.
+ */
+ oprofile_put_buff(spu_buff[spu].buff,
+ spu_buff[spu].tail,
+ curr_head, max_spu_buff);
+
+ spin_lock_irqsave(&buffer_lock, flags);
+ spu_buff[spu].tail = curr_head;
+ spin_unlock_irqrestore(&buffer_lock, flags);
+ }
+
+}
+
+static void wq_sync_spu_buff(struct work_struct *work)
+{
+ /* move data from spu buffers to kernel buffer */
+ sync_spu_buff();
+
+ /* only reschedule if profiling is not done */
+ if (spu_prof_running)
+ schedule_delayed_work(&spu_work, DEFAULT_TIMER_EXPIRE);
+}
/* Container for caching information about an active SPU task. */
struct cached_info {
@@ -68,7 +164,7 @@ static struct cached_info *get_cached_info(struct spu *the_spu, int spu_num)
if (spu_num >= num_spu_nodes) {
printk(KERN_ERR "SPU_PROF: "
"%s, line %d: Invalid index %d into spu info cache\n",
- __FUNCTION__, __LINE__, spu_num);
+ __func__, __LINE__, spu_num);
ret_info = NULL;
goto out;
}
@@ -115,7 +211,7 @@ prepare_cached_spu_info(struct spu *spu, unsigned long objectId)
if (!info) {
printk(KERN_ERR "SPU_PROF: "
"%s, line %d: create vma_map failed\n",
- __FUNCTION__, __LINE__);
+ __func__, __LINE__);
retval = -ENOMEM;
goto err_alloc;
}
@@ -123,7 +219,7 @@ prepare_cached_spu_info(struct spu *spu, unsigned long objectId)
if (!new_map) {
printk(KERN_ERR "SPU_PROF: "
"%s, line %d: create vma_map failed\n",
- __FUNCTION__, __LINE__);
+ __func__, __LINE__);
retval = -ENOMEM;
goto err_alloc;
}
@@ -171,7 +267,7 @@ static int release_cached_info(int spu_index)
printk(KERN_ERR "SPU_PROF: "
"%s, line %d: "
"Invalid index %d into spu info cache\n",
- __FUNCTION__, __LINE__, spu_index);
+ __func__, __LINE__, spu_index);
goto out;
}
end = spu_index + 1;
@@ -202,13 +298,13 @@ static inline unsigned long fast_get_dcookie(struct path *path)
{
unsigned long cookie;
- if (path->dentry->d_cookie)
+ if (path->dentry->d_flags & DCACHE_COOKIE)
return (unsigned long)path->dentry;
get_dcookie(path, &cookie);
return cookie;
}
-/* Look up the dcookie for the task's first VM_EXECUTABLE mapping,
+/* Look up the dcookie for the task's mm->exe_file,
* which corresponds loosely to "application name". Also, determine
* the offset for the SPU ELF object. If computed offset is
* non-zero, it implies an embedded SPU object; otherwise, it's a
@@ -225,7 +321,6 @@ get_exec_dcookie_and_offset(struct spu *spu, unsigned int *offsetp,
{
unsigned long app_cookie = 0;
unsigned int my_offset = 0;
- struct file *app = NULL;
struct vm_area_struct *vma;
struct mm_struct *mm = spu->mm;
@@ -234,16 +329,10 @@ get_exec_dcookie_and_offset(struct spu *spu, unsigned int *offsetp,
down_read(&mm->mmap_sem);
- for (vma = mm->mmap; vma; vma = vma->vm_next) {
- if (!vma->vm_file)
- continue;
- if (!(vma->vm_flags & VM_EXECUTABLE))
- continue;
- app_cookie = fast_get_dcookie(&vma->vm_file->f_path);
+ if (mm->exe_file) {
+ app_cookie = fast_get_dcookie(&mm->exe_file->f_path);
pr_debug("got dcookie for %s\n",
- vma->vm_file->f_dentry->d_name.name);
- app = vma->vm_file;
- break;
+ mm->exe_file->f_dentry->d_name.name);
}
for (vma = mm->mmap; vma; vma = vma->vm_next) {
@@ -273,7 +362,7 @@ fail_no_image_cookie:
printk(KERN_ERR "SPU_PROF: "
"%s, line %d: Cannot find dcookie for SPU binary\n",
- __FUNCTION__, __LINE__);
+ __func__, __LINE__);
goto out;
}
@@ -305,14 +394,21 @@ static int process_context_switch(struct spu *spu, unsigned long objectId)
/* Record context info in event buffer */
spin_lock_irqsave(&buffer_lock, flags);
- add_event_entry(ESCAPE_CODE);
- add_event_entry(SPU_CTX_SWITCH_CODE);
- add_event_entry(spu->number);
- add_event_entry(spu->pid);
- add_event_entry(spu->tgid);
- add_event_entry(app_dcookie);
- add_event_entry(spu_cookie);
- add_event_entry(offset);
+ spu_buff_add(ESCAPE_CODE, spu->number);
+ spu_buff_add(SPU_CTX_SWITCH_CODE, spu->number);
+ spu_buff_add(spu->number, spu->number);
+ spu_buff_add(spu->pid, spu->number);
+ spu_buff_add(spu->tgid, spu->number);
+ spu_buff_add(app_dcookie, spu->number);
+ spu_buff_add(spu_cookie, spu->number);
+ spu_buff_add(offset, spu->number);
+
+ /* Set flag to indicate SPU PC data can now be written out. If
+ * the SPU program counter data is seen before an SPU context
+ * record is seen, the postprocessing will fail.
+ */
+ spu_buff[spu->number].ctx_sw_seen = 1;
+
spin_unlock_irqrestore(&buffer_lock, flags);
smp_wmb(); /* insure spu event buffer updates are written */
/* don't want entries intermingled... */
@@ -360,6 +456,47 @@ static int number_of_online_nodes(void)
return nodes;
}
+static int oprofile_spu_buff_create(void)
+{
+ int spu;
+
+ max_spu_buff = oprofile_get_cpu_buffer_size();
+
+ for (spu = 0; spu < num_spu_nodes; spu++) {
+ /* create circular buffers to store the data in.
+ * use locks to manage accessing the buffers
+ */
+ spu_buff[spu].head = 0;
+ spu_buff[spu].tail = 0;
+
+ /*
+ * Create a buffer for each SPU. Can't reliably
+ * create a single buffer for all spus due to not
+ * enough contiguous kernel memory.
+ */
+
+ spu_buff[spu].buff = kzalloc((max_spu_buff
+ * sizeof(unsigned long)),
+ GFP_KERNEL);
+
+ if (!spu_buff[spu].buff) {
+ printk(KERN_ERR "SPU_PROF: "
+ "%s, line %d: oprofile_spu_buff_create "
+ "failed to allocate spu buffer %d.\n",
+ __func__, __LINE__, spu);
+
+ /* release the spu buffers that have been allocated */
+ while (spu >= 0) {
+ kfree(spu_buff[spu].buff);
+ spu_buff[spu].buff = 0;
+ spu--;
+ }
+ return -ENOMEM;
+ }
+ }
+ return 0;
+}
+
/* The main purpose of this function is to synchronize
* OProfile with SPUFS by registering to be notified of
* SPU task switches.
@@ -372,20 +509,35 @@ static int number_of_online_nodes(void)
*/
int spu_sync_start(void)
{
- int k;
+ int spu;
int ret = SKIP_GENERIC_SYNC;
int register_ret;
unsigned long flags = 0;
spu_prof_num_nodes = number_of_online_nodes();
num_spu_nodes = spu_prof_num_nodes * 8;
+ INIT_DELAYED_WORK(&spu_work, wq_sync_spu_buff);
+
+ /* create buffer for storing the SPU data to put in
+ * the kernel buffer.
+ */
+ ret = oprofile_spu_buff_create();
+ if (ret)
+ goto out;
spin_lock_irqsave(&buffer_lock, flags);
- add_event_entry(ESCAPE_CODE);
- add_event_entry(SPU_PROFILING_CODE);
- add_event_entry(num_spu_nodes);
+ for (spu = 0; spu < num_spu_nodes; spu++) {
+ spu_buff_add(ESCAPE_CODE, spu);
+ spu_buff_add(SPU_PROFILING_CODE, spu);
+ spu_buff_add(num_spu_nodes, spu);
+ }
spin_unlock_irqrestore(&buffer_lock, flags);
+ for (spu = 0; spu < num_spu_nodes; spu++) {
+ spu_buff[spu].ctx_sw_seen = 0;
+ spu_buff[spu].last_guard_val = 0;
+ }
+
/* Register for SPU events */
register_ret = spu_switch_event_register(&spu_active);
if (register_ret) {
@@ -393,8 +545,6 @@ int spu_sync_start(void)
goto out;
}
- for (k = 0; k < (MAX_NUMNODES * 8); k++)
- last_guard_val[k] = 0;
pr_debug("spu_sync_start -- running.\n");
out:
return ret;
@@ -446,13 +596,20 @@ void spu_sync_buffer(int spu_num, unsigned int *samples,
* use. We need to discard samples taken during the time
* period which an overlay occurs (i.e., guard value changes).
*/
- if (grd_val && grd_val != last_guard_val[spu_num]) {
- last_guard_val[spu_num] = grd_val;
+ if (grd_val && grd_val != spu_buff[spu_num].last_guard_val) {
+ spu_buff[spu_num].last_guard_val = grd_val;
/* Drop the rest of the samples. */
break;
}
- add_event_entry(file_offset | spu_num_shifted);
+ /* We must ensure that the SPU context switch has been written
+ * out before samples for the SPU. Otherwise, the SPU context
+ * information is not available and the postprocessing of the
+ * SPU PC will fail with no available anonymous map information.
+ */
+ if (spu_buff[spu_num].ctx_sw_seen)
+ spu_buff_add((file_offset | spu_num_shifted),
+ spu_num);
}
spin_unlock(&buffer_lock);
out:
@@ -463,20 +620,41 @@ out:
int spu_sync_stop(void)
{
unsigned long flags = 0;
- int ret = spu_switch_event_unregister(&spu_active);
- if (ret) {
+ int ret;
+ int k;
+
+ ret = spu_switch_event_unregister(&spu_active);
+
+ if (ret)
printk(KERN_ERR "SPU_PROF: "
- "%s, line %d: spu_switch_event_unregister returned %d\n",
- __FUNCTION__, __LINE__, ret);
- goto out;
- }
+ "%s, line %d: spu_switch_event_unregister " \
+ "returned %d\n",
+ __func__, __LINE__, ret);
+
+ /* flush any remaining data in the per SPU buffers */
+ sync_spu_buff();
spin_lock_irqsave(&cache_lock, flags);
ret = release_cached_info(RELEASE_ALL);
spin_unlock_irqrestore(&cache_lock, flags);
-out:
+
+ /* remove scheduled work queue item rather then waiting
+ * for every queued entry to execute. Then flush pending
+ * system wide buffer to event buffer.
+ */
+ cancel_delayed_work(&spu_work);
+
+ for (k = 0; k < num_spu_nodes; k++) {
+ spu_buff[k].ctx_sw_seen = 0;
+
+ /*
+ * spu_sys_buff will be null if there was a problem
+ * allocating the buffer. Only delete if it exists.
+ */
+ kfree(spu_buff[k].buff);
+ spu_buff[k].buff = 0;
+ }
pr_debug("spu_sync_stop -- done.\n");
return ret;
}
-
diff --git a/arch/powerpc/oprofile/cell/vma_map.c b/arch/powerpc/oprofile/cell/vma_map.c
index 9a932177e70..c579b16845d 100644
--- a/arch/powerpc/oprofile/cell/vma_map.c
+++ b/arch/powerpc/oprofile/cell/vma_map.c
@@ -20,6 +20,7 @@
#include <linux/string.h>
#include <linux/uaccess.h>
#include <linux/elf.h>
+#include <linux/slab.h>
#include "pr_util.h"
@@ -72,7 +73,7 @@ vma_map_add(struct vma_to_fileoffset_map *map, unsigned int vma,
kzalloc(sizeof(struct vma_to_fileoffset_map), GFP_KERNEL);
if (!new) {
printk(KERN_ERR "SPU_PROF: %s, line %d: malloc failed\n",
- __FUNCTION__, __LINE__);
+ __func__, __LINE__);
vma_map_free(map);
return NULL;
}
@@ -134,19 +135,19 @@ struct vma_to_fileoffset_map *create_vma_map(const struct spu *aSpu,
if (memcmp(ehdr.e_ident, expected, EI_PAD) != 0) {
printk(KERN_ERR "SPU_PROF: "
"%s, line %d: Unexpected e_ident parsing SPU ELF\n",
- __FUNCTION__, __LINE__);
+ __func__, __LINE__);
goto fail;
}
if (ehdr.e_machine != EM_SPU) {
printk(KERN_ERR "SPU_PROF: "
"%s, line %d: Unexpected e_machine parsing SPU ELF\n",
- __FUNCTION__, __LINE__);
+ __func__, __LINE__);
goto fail;
}
if (ehdr.e_type != ET_EXEC) {
printk(KERN_ERR "SPU_PROF: "
"%s, line %d: Unexpected e_type parsing SPU ELF\n",
- __FUNCTION__, __LINE__);
+ __func__, __LINE__);
goto fail;
}
phdr_start = spu_elf_start + ehdr.e_phoff;
@@ -185,7 +186,7 @@ struct vma_to_fileoffset_map *create_vma_map(const struct spu *aSpu,
goto fail;
if (shdr_str.sh_type != SHT_STRTAB)
- goto fail;;
+ goto fail;
for (j = 0; j < shdr.sh_size / sizeof (sym); j++) {
if (copy_from_user(&sym, spu_elf_start +
@@ -229,10 +230,10 @@ struct vma_to_fileoffset_map *create_vma_map(const struct spu *aSpu,
*/
overlay_tbl_offset = vma_map_lookup(map, ovly_table_sym,
aSpu, &grd_val);
- if (overlay_tbl_offset < 0) {
+ if (overlay_tbl_offset > 0x10000000) {
printk(KERN_ERR "SPU_PROF: "
"%s, line %d: Error finding SPU overlay table\n",
- __FUNCTION__, __LINE__);
+ __func__, __LINE__);
goto fail;
}
ovly_table = spu_elf_start + overlay_tbl_offset;
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-10 18:03:22 +0000