linux/arch/powerpc/platforms/pseries/dtl.c

395 lines
8.4 KiB
C
Raw Normal View History

/*
* Virtual Processor Dispatch Trace Log
*
* (C) Copyright IBM Corporation 2009
*
* Author: Jeremy Kerr <jk@ozlabs.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2, or (at your option)
* any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include <linux/init.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/debugfs.h>
#include <linux/spinlock.h>
#include <asm/smp.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/firmware.h>
powerpc: Account time using timebase rather than PURR Currently, when CONFIG_VIRT_CPU_ACCOUNTING is enabled, we use the PURR register for measuring the user and system time used by processes, as well as other related times such as hardirq and softirq times. This turns out to be quite confusing for users because it means that a program will often be measured as taking less time when run on a multi-threaded processor (SMT2 or SMT4 mode) than it does when run on a single-threaded processor (ST mode), even though the program takes longer to finish. The discrepancy is accounted for as stolen time, which is also confusing, particularly when there are no other partitions running. This changes the accounting to use the timebase instead, meaning that the reported user and system times are the actual number of real-time seconds that the program was executing on the processor thread, regardless of which SMT mode the processor is in. Thus a program will generally show greater user and system times when run on a multi-threaded processor than on a single-threaded processor. On pSeries systems on POWER5 or later processors, we measure the stolen time (time when this partition wasn't running) using the hypervisor dispatch trace log. We check for new entries in the log on every entry from user mode and on every transition from kernel process context to soft or hard IRQ context (i.e. when account_system_vtime() gets called). So that we can correctly distinguish time stolen from user time and time stolen from system time, without having to check the log on every exit to user mode, we store separate timestamps for exit to user mode and entry from user mode. On systems that have a SPURR (POWER6 and POWER7), we read the SPURR in account_system_vtime() (as before), and then apportion the SPURR ticks since the last time we read it between scaled user time and scaled system time according to the relative proportions of user time and system time over the same interval. This avoids having to read the SPURR on every kernel entry and exit. On systems that have PURR but not SPURR (i.e., POWER5), we do the same using the PURR rather than the SPURR. This disables the DTL user interface in /sys/debug/kernel/powerpc/dtl for now since it conflicts with the use of the dispatch trace log by the time accounting code. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2010-08-27 03:56:43 +08:00
#include <asm/lppaca.h>
#include "plpar_wrappers.h"
struct dtl {
struct dtl_entry *buf;
struct dentry *file;
int cpu;
int buf_entries;
u64 last_idx;
spinlock_t lock;
};
static DEFINE_PER_CPU(struct dtl, cpu_dtl);
/*
* Dispatch trace log event mask:
* 0x7: 0x1: voluntary virtual processor waits
* 0x2: time-slice preempts
* 0x4: virtual partition memory page faults
*/
static u8 dtl_event_mask = 0x7;
/*
* Size of per-cpu log buffers. Default is just under 16 pages worth.
*/
static int dtl_buf_entries = (16 * 85);
#ifdef CONFIG_VIRT_CPU_ACCOUNTING
struct dtl_ring {
u64 write_index;
struct dtl_entry *write_ptr;
struct dtl_entry *buf;
struct dtl_entry *buf_end;
u8 saved_dtl_mask;
};
static DEFINE_PER_CPU(struct dtl_ring, dtl_rings);
static atomic_t dtl_count;
/*
* The cpu accounting code controls the DTL ring buffer, and we get
* given entries as they are processed.
*/
static void consume_dtle(struct dtl_entry *dtle, u64 index)
{
struct dtl_ring *dtlr = &__get_cpu_var(dtl_rings);
struct dtl_entry *wp = dtlr->write_ptr;
struct lppaca *vpa = local_paca->lppaca_ptr;
if (!wp)
return;
*wp = *dtle;
barrier();
/* check for hypervisor ring buffer overflow, ignore this entry if so */
if (index + N_DISPATCH_LOG < vpa->dtl_idx)
return;
++wp;
if (wp == dtlr->buf_end)
wp = dtlr->buf;
dtlr->write_ptr = wp;
/* incrementing write_index makes the new entry visible */
smp_wmb();
++dtlr->write_index;
}
static int dtl_start(struct dtl *dtl)
{
struct dtl_ring *dtlr = &per_cpu(dtl_rings, dtl->cpu);
dtlr->buf = dtl->buf;
dtlr->buf_end = dtl->buf + dtl->buf_entries;
dtlr->write_index = 0;
/* setting write_ptr enables logging into our buffer */
smp_wmb();
dtlr->write_ptr = dtl->buf;
/* enable event logging */
dtlr->saved_dtl_mask = lppaca_of(dtl->cpu).dtl_enable_mask;
lppaca_of(dtl->cpu).dtl_enable_mask |= dtl_event_mask;
dtl_consumer = consume_dtle;
atomic_inc(&dtl_count);
return 0;
}
static void dtl_stop(struct dtl *dtl)
{
struct dtl_ring *dtlr = &per_cpu(dtl_rings, dtl->cpu);
dtlr->write_ptr = NULL;
smp_wmb();
dtlr->buf = NULL;
/* restore dtl_enable_mask */
lppaca_of(dtl->cpu).dtl_enable_mask = dtlr->saved_dtl_mask;
if (atomic_dec_and_test(&dtl_count))
dtl_consumer = NULL;
}
static u64 dtl_current_index(struct dtl *dtl)
{
return per_cpu(dtl_rings, dtl->cpu).write_index;
}
#else /* CONFIG_VIRT_CPU_ACCOUNTING */
static int dtl_start(struct dtl *dtl)
{
unsigned long addr;
int ret, hwcpu;
/* Register our dtl buffer with the hypervisor. The HV expects the
* buffer size to be passed in the second word of the buffer */
((u32 *)dtl->buf)[1] = dtl->buf_entries * sizeof(struct dtl_entry);
hwcpu = get_hard_smp_processor_id(dtl->cpu);
addr = __pa(dtl->buf);
ret = register_dtl(hwcpu, addr);
if (ret) {
printk(KERN_WARNING "%s: DTL registration for cpu %d (hw %d) "
"failed with %d\n", __func__, dtl->cpu, hwcpu, ret);
return -EIO;
}
/* set our initial buffer indices */
lppaca_of(dtl->cpu).dtl_idx = 0;
/* ensure that our updates to the lppaca fields have occurred before
* we actually enable the logging */
smp_wmb();
/* enable event logging */
lppaca_of(dtl->cpu).dtl_enable_mask = dtl_event_mask;
return 0;
}
static void dtl_stop(struct dtl *dtl)
{
int hwcpu = get_hard_smp_processor_id(dtl->cpu);
lppaca_of(dtl->cpu).dtl_enable_mask = 0x0;
unregister_dtl(hwcpu, __pa(dtl->buf));
}
static u64 dtl_current_index(struct dtl *dtl)
{
return lppaca_of(dtl->cpu).dtl_idx;
}
#endif /* CONFIG_VIRT_CPU_ACCOUNTING */
static int dtl_enable(struct dtl *dtl)
{
long int n_entries;
long int rc;
struct dtl_entry *buf = NULL;
/* only allow one reader */
if (dtl->buf)
return -EBUSY;
n_entries = dtl_buf_entries;
buf = kmalloc_node(n_entries * sizeof(struct dtl_entry),
GFP_KERNEL, cpu_to_node(dtl->cpu));
if (!buf) {
printk(KERN_WARNING "%s: buffer alloc failed for cpu %d\n",
__func__, dtl->cpu);
return -ENOMEM;
}
spin_lock(&dtl->lock);
rc = -EBUSY;
if (!dtl->buf) {
/* store the original allocation size for use during read */
dtl->buf_entries = n_entries;
dtl->buf = buf;
dtl->last_idx = 0;
rc = dtl_start(dtl);
if (rc)
dtl->buf = NULL;
}
spin_unlock(&dtl->lock);
if (rc)
kfree(buf);
return rc;
}
static void dtl_disable(struct dtl *dtl)
{
spin_lock(&dtl->lock);
dtl_stop(dtl);
kfree(dtl->buf);
dtl->buf = NULL;
dtl->buf_entries = 0;
spin_unlock(&dtl->lock);
}
/* file interface */
static int dtl_file_open(struct inode *inode, struct file *filp)
{
struct dtl *dtl = inode->i_private;
int rc;
rc = dtl_enable(dtl);
if (rc)
return rc;
filp->private_data = dtl;
return 0;
}
static int dtl_file_release(struct inode *inode, struct file *filp)
{
struct dtl *dtl = inode->i_private;
dtl_disable(dtl);
return 0;
}
static ssize_t dtl_file_read(struct file *filp, char __user *buf, size_t len,
loff_t *pos)
{
long int rc, n_read, n_req, read_size;
struct dtl *dtl;
u64 cur_idx, last_idx, i;
if ((len % sizeof(struct dtl_entry)) != 0)
return -EINVAL;
dtl = filp->private_data;
/* requested number of entries to read */
n_req = len / sizeof(struct dtl_entry);
/* actual number of entries read */
n_read = 0;
spin_lock(&dtl->lock);
cur_idx = dtl_current_index(dtl);
last_idx = dtl->last_idx;
if (last_idx + dtl->buf_entries <= cur_idx)
last_idx = cur_idx - dtl->buf_entries + 1;
if (last_idx + n_req > cur_idx)
n_req = cur_idx - last_idx;
if (n_req > 0)
dtl->last_idx = last_idx + n_req;
spin_unlock(&dtl->lock);
if (n_req <= 0)
return 0;
i = last_idx % dtl->buf_entries;
/* read the tail of the buffer if we've wrapped */
if (i + n_req > dtl->buf_entries) {
read_size = dtl->buf_entries - i;
rc = copy_to_user(buf, &dtl->buf[i],
read_size * sizeof(struct dtl_entry));
if (rc)
return -EFAULT;
i = 0;
n_req -= read_size;
n_read += read_size;
buf += read_size * sizeof(struct dtl_entry);
}
/* .. and now the head */
rc = copy_to_user(buf, &dtl->buf[i], n_req * sizeof(struct dtl_entry));
if (rc)
return -EFAULT;
n_read += n_req;
return n_read * sizeof(struct dtl_entry);
}
static const struct file_operations dtl_fops = {
.open = dtl_file_open,
.release = dtl_file_release,
.read = dtl_file_read,
.llseek = no_llseek,
};
static struct dentry *dtl_dir;
static int dtl_setup_file(struct dtl *dtl)
{
char name[10];
sprintf(name, "cpu-%d", dtl->cpu);
dtl->file = debugfs_create_file(name, 0400, dtl_dir, dtl, &dtl_fops);
if (!dtl->file)
return -ENOMEM;
return 0;
}
static int dtl_init(void)
{
struct dentry *event_mask_file, *buf_entries_file;
int rc, i;
if (!firmware_has_feature(FW_FEATURE_SPLPAR))
return -ENODEV;
/* set up common debugfs structure */
rc = -ENOMEM;
dtl_dir = debugfs_create_dir("dtl", powerpc_debugfs_root);
if (!dtl_dir) {
printk(KERN_WARNING "%s: can't create dtl root dir\n",
__func__);
goto err;
}
event_mask_file = debugfs_create_x8("dtl_event_mask", 0600,
dtl_dir, &dtl_event_mask);
buf_entries_file = debugfs_create_u32("dtl_buf_entries", 0600,
dtl_dir, &dtl_buf_entries);
if (!event_mask_file || !buf_entries_file) {
printk(KERN_WARNING "%s: can't create dtl files\n", __func__);
goto err_remove_dir;
}
/* set up the per-cpu log structures */
for_each_possible_cpu(i) {
struct dtl *dtl = &per_cpu(cpu_dtl, i);
spin_lock_init(&dtl->lock);
dtl->cpu = i;
rc = dtl_setup_file(dtl);
if (rc)
goto err_remove_dir;
}
return 0;
err_remove_dir:
debugfs_remove_recursive(dtl_dir);
err:
return rc;
}
arch_initcall(dtl_init);