linux-sg2042/drivers/char/mmtimer.c

859 lines
21 KiB
C
Raw Normal View History

/*
* Timer device implementation for SGI SN platforms.
*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*
* Copyright (c) 2001-2006 Silicon Graphics, Inc. All rights reserved.
*
* This driver exports an API that should be supportable by any HPET or IA-PC
* multimedia timer. The code below is currently specific to the SGI Altix
* SHub RTC, however.
*
* 11/01/01 - jbarnes - initial revision
* 9/10/04 - Christoph Lameter - remove interrupt support for kernel inclusion
* 10/1/04 - Christoph Lameter - provide posix clock CLOCK_SGI_CYCLE
* 10/13/04 - Christoph Lameter, Dimitri Sivanich - provide timer interrupt
* support via the posix timer interface
*/
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/ioctl.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/mm.h>
Remove fs.h from mm.h Remove fs.h from mm.h. For this, 1) Uninline vma_wants_writenotify(). It's pretty huge anyway. 2) Add back fs.h or less bloated headers (err.h) to files that need it. As result, on x86_64 allyesconfig, fs.h dependencies cut down from 3929 files rebuilt down to 3444 (-12.3%). Cross-compile tested without regressions on my two usual configs and (sigh): alpha arm-mx1ads mips-bigsur powerpc-ebony alpha-allnoconfig arm-neponset mips-capcella powerpc-g5 alpha-defconfig arm-netwinder mips-cobalt powerpc-holly alpha-up arm-netx mips-db1000 powerpc-iseries arm arm-ns9xxx mips-db1100 powerpc-linkstation arm-assabet arm-omap_h2_1610 mips-db1200 powerpc-lite5200 arm-at91rm9200dk arm-onearm mips-db1500 powerpc-maple arm-at91rm9200ek arm-picotux200 mips-db1550 powerpc-mpc7448_hpc2 arm-at91sam9260ek arm-pleb mips-ddb5477 powerpc-mpc8272_ads arm-at91sam9261ek arm-pnx4008 mips-decstation powerpc-mpc8313_rdb arm-at91sam9263ek arm-pxa255-idp mips-e55 powerpc-mpc832x_mds arm-at91sam9rlek arm-realview mips-emma2rh powerpc-mpc832x_rdb arm-ateb9200 arm-realview-smp mips-excite powerpc-mpc834x_itx arm-badge4 arm-rpc mips-fulong powerpc-mpc834x_itxgp arm-carmeva arm-s3c2410 mips-ip22 powerpc-mpc834x_mds arm-cerfcube arm-shannon mips-ip27 powerpc-mpc836x_mds arm-clps7500 arm-shark mips-ip32 powerpc-mpc8540_ads arm-collie arm-simpad mips-jazz powerpc-mpc8544_ds arm-corgi arm-spitz mips-jmr3927 powerpc-mpc8560_ads arm-csb337 arm-trizeps4 mips-malta powerpc-mpc8568mds arm-csb637 arm-versatile mips-mipssim powerpc-mpc85xx_cds arm-ebsa110 i386 mips-mpc30x powerpc-mpc8641_hpcn arm-edb7211 i386-allnoconfig mips-msp71xx powerpc-mpc866_ads arm-em_x270 i386-defconfig mips-ocelot powerpc-mpc885_ads arm-ep93xx i386-up mips-pb1100 powerpc-pasemi arm-footbridge ia64 mips-pb1500 powerpc-pmac32 arm-fortunet ia64-allnoconfig mips-pb1550 powerpc-ppc64 arm-h3600 ia64-bigsur mips-pnx8550-jbs powerpc-prpmc2800 arm-h7201 ia64-defconfig mips-pnx8550-stb810 powerpc-ps3 arm-h7202 ia64-gensparse mips-qemu powerpc-pseries arm-hackkit ia64-sim mips-rbhma4200 powerpc-up arm-integrator ia64-sn2 mips-rbhma4500 s390 arm-iop13xx ia64-tiger mips-rm200 s390-allnoconfig arm-iop32x ia64-up mips-sb1250-swarm s390-defconfig arm-iop33x ia64-zx1 mips-sead s390-up arm-ixp2000 m68k mips-tb0219 sparc arm-ixp23xx m68k-amiga mips-tb0226 sparc-allnoconfig arm-ixp4xx m68k-apollo mips-tb0287 sparc-defconfig arm-jornada720 m68k-atari mips-workpad sparc-up arm-kafa m68k-bvme6000 mips-wrppmc sparc64 arm-kb9202 m68k-hp300 mips-yosemite sparc64-allnoconfig arm-ks8695 m68k-mac parisc sparc64-defconfig arm-lart m68k-mvme147 parisc-allnoconfig sparc64-up arm-lpd270 m68k-mvme16x parisc-defconfig um-x86_64 arm-lpd7a400 m68k-q40 parisc-up x86_64 arm-lpd7a404 m68k-sun3 powerpc x86_64-allnoconfig arm-lubbock m68k-sun3x powerpc-cell x86_64-defconfig arm-lusl7200 mips powerpc-celleb x86_64-up arm-mainstone mips-atlas powerpc-chrp32 Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-30 06:36:13 +08:00
#include <linux/fs.h>
#include <linux/mmtimer.h>
#include <linux/miscdevice.h>
#include <linux/posix-timers.h>
#include <linux/interrupt.h>
#include <linux/time.h>
#include <linux/math64.h>
#include <linux/mutex.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 <asm/uaccess.h>
#include <asm/sn/addrs.h>
#include <asm/sn/intr.h>
#include <asm/sn/shub_mmr.h>
#include <asm/sn/nodepda.h>
#include <asm/sn/shubio.h>
MODULE_AUTHOR("Jesse Barnes <jbarnes@sgi.com>");
MODULE_DESCRIPTION("SGI Altix RTC Timer");
MODULE_LICENSE("GPL");
/* name of the device, usually in /dev */
#define MMTIMER_NAME "mmtimer"
#define MMTIMER_DESC "SGI Altix RTC Timer"
#define MMTIMER_VERSION "2.1"
#define RTC_BITS 55 /* 55 bits for this implementation */
static struct k_clock sgi_clock;
extern unsigned long sn_rtc_cycles_per_second;
#define RTC_COUNTER_ADDR ((long *)LOCAL_MMR_ADDR(SH_RTC))
#define rtc_time() (*RTC_COUNTER_ADDR)
static DEFINE_MUTEX(mmtimer_mutex);
static long mmtimer_ioctl(struct file *file, unsigned int cmd,
unsigned long arg);
static int mmtimer_mmap(struct file *file, struct vm_area_struct *vma);
/*
* Period in femtoseconds (10^-15 s)
*/
static unsigned long mmtimer_femtoperiod = 0;
static const struct file_operations mmtimer_fops = {
.owner = THIS_MODULE,
.mmap = mmtimer_mmap,
.unlocked_ioctl = mmtimer_ioctl,
llseek: automatically add .llseek fop All file_operations should get a .llseek operation so we can make nonseekable_open the default for future file operations without a .llseek pointer. The three cases that we can automatically detect are no_llseek, seq_lseek and default_llseek. For cases where we can we can automatically prove that the file offset is always ignored, we use noop_llseek, which maintains the current behavior of not returning an error from a seek. New drivers should normally not use noop_llseek but instead use no_llseek and call nonseekable_open at open time. Existing drivers can be converted to do the same when the maintainer knows for certain that no user code relies on calling seek on the device file. The generated code is often incorrectly indented and right now contains comments that clarify for each added line why a specific variant was chosen. In the version that gets submitted upstream, the comments will be gone and I will manually fix the indentation, because there does not seem to be a way to do that using coccinelle. Some amount of new code is currently sitting in linux-next that should get the same modifications, which I will do at the end of the merge window. Many thanks to Julia Lawall for helping me learn to write a semantic patch that does all this. ===== begin semantic patch ===== // This adds an llseek= method to all file operations, // as a preparation for making no_llseek the default. // // The rules are // - use no_llseek explicitly if we do nonseekable_open // - use seq_lseek for sequential files // - use default_llseek if we know we access f_pos // - use noop_llseek if we know we don't access f_pos, // but we still want to allow users to call lseek // @ open1 exists @ identifier nested_open; @@ nested_open(...) { <+... nonseekable_open(...) ...+> } @ open exists@ identifier open_f; identifier i, f; identifier open1.nested_open; @@ int open_f(struct inode *i, struct file *f) { <+... ( nonseekable_open(...) | nested_open(...) ) ...+> } @ read disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ read_no_fpos disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { ... when != off } @ write @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ write_no_fpos @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { ... when != off } @ fops0 @ identifier fops; @@ struct file_operations fops = { ... }; @ has_llseek depends on fops0 @ identifier fops0.fops; identifier llseek_f; @@ struct file_operations fops = { ... .llseek = llseek_f, ... }; @ has_read depends on fops0 @ identifier fops0.fops; identifier read_f; @@ struct file_operations fops = { ... .read = read_f, ... }; @ has_write depends on fops0 @ identifier fops0.fops; identifier write_f; @@ struct file_operations fops = { ... .write = write_f, ... }; @ has_open depends on fops0 @ identifier fops0.fops; identifier open_f; @@ struct file_operations fops = { ... .open = open_f, ... }; // use no_llseek if we call nonseekable_open //////////////////////////////////////////// @ nonseekable1 depends on !has_llseek && has_open @ identifier fops0.fops; identifier nso ~= "nonseekable_open"; @@ struct file_operations fops = { ... .open = nso, ... +.llseek = no_llseek, /* nonseekable */ }; @ nonseekable2 depends on !has_llseek @ identifier fops0.fops; identifier open.open_f; @@ struct file_operations fops = { ... .open = open_f, ... +.llseek = no_llseek, /* open uses nonseekable */ }; // use seq_lseek for sequential files ///////////////////////////////////// @ seq depends on !has_llseek @ identifier fops0.fops; identifier sr ~= "seq_read"; @@ struct file_operations fops = { ... .read = sr, ... +.llseek = seq_lseek, /* we have seq_read */ }; // use default_llseek if there is a readdir /////////////////////////////////////////// @ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier readdir_e; @@ // any other fop is used that changes pos struct file_operations fops = { ... .readdir = readdir_e, ... +.llseek = default_llseek, /* readdir is present */ }; // use default_llseek if at least one of read/write touches f_pos ///////////////////////////////////////////////////////////////// @ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read.read_f; @@ // read fops use offset struct file_operations fops = { ... .read = read_f, ... +.llseek = default_llseek, /* read accesses f_pos */ }; @ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, ... + .llseek = default_llseek, /* write accesses f_pos */ }; // Use noop_llseek if neither read nor write accesses f_pos /////////////////////////////////////////////////////////// @ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; identifier write_no_fpos.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, .read = read_f, ... +.llseek = noop_llseek, /* read and write both use no f_pos */ }; @ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write_no_fpos.write_f; @@ struct file_operations fops = { ... .write = write_f, ... +.llseek = noop_llseek, /* write uses no f_pos */ }; @ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; @@ struct file_operations fops = { ... .read = read_f, ... +.llseek = noop_llseek, /* read uses no f_pos */ }; @ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; @@ struct file_operations fops = { ... +.llseek = noop_llseek, /* no read or write fn */ }; ===== End semantic patch ===== Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Julia Lawall <julia@diku.dk> Cc: Christoph Hellwig <hch@infradead.org>
2010-08-16 00:52:59 +08:00
.llseek = noop_llseek,
};
/*
* We only have comparison registers RTC1-4 currently available per
* node. RTC0 is used by SAL.
*/
/* Check for an RTC interrupt pending */
static int mmtimer_int_pending(int comparator)
{
if (HUB_L((unsigned long *)LOCAL_MMR_ADDR(SH_EVENT_OCCURRED)) &
SH_EVENT_OCCURRED_RTC1_INT_MASK << comparator)
return 1;
else
return 0;
}
/* Clear the RTC interrupt pending bit */
static void mmtimer_clr_int_pending(int comparator)
{
HUB_S((u64 *)LOCAL_MMR_ADDR(SH_EVENT_OCCURRED_ALIAS),
SH_EVENT_OCCURRED_RTC1_INT_MASK << comparator);
}
/* Setup timer on comparator RTC1 */
static void mmtimer_setup_int_0(int cpu, u64 expires)
{
u64 val;
/* Disable interrupt */
HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC1_INT_ENABLE), 0UL);
/* Initialize comparator value */
HUB_S((u64 *)LOCAL_MMR_ADDR(SH_INT_CMPB), -1L);
/* Clear pending bit */
mmtimer_clr_int_pending(0);
val = ((u64)SGI_MMTIMER_VECTOR << SH_RTC1_INT_CONFIG_IDX_SHFT) |
((u64)cpu_physical_id(cpu) <<
SH_RTC1_INT_CONFIG_PID_SHFT);
/* Set configuration */
HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC1_INT_CONFIG), val);
/* Enable RTC interrupts */
HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC1_INT_ENABLE), 1UL);
/* Initialize comparator value */
HUB_S((u64 *)LOCAL_MMR_ADDR(SH_INT_CMPB), expires);
}
/* Setup timer on comparator RTC2 */
static void mmtimer_setup_int_1(int cpu, u64 expires)
{
u64 val;
HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC2_INT_ENABLE), 0UL);
HUB_S((u64 *)LOCAL_MMR_ADDR(SH_INT_CMPC), -1L);
mmtimer_clr_int_pending(1);
val = ((u64)SGI_MMTIMER_VECTOR << SH_RTC2_INT_CONFIG_IDX_SHFT) |
((u64)cpu_physical_id(cpu) <<
SH_RTC2_INT_CONFIG_PID_SHFT);
HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC2_INT_CONFIG), val);
HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC2_INT_ENABLE), 1UL);
HUB_S((u64 *)LOCAL_MMR_ADDR(SH_INT_CMPC), expires);
}
/* Setup timer on comparator RTC3 */
static void mmtimer_setup_int_2(int cpu, u64 expires)
{
u64 val;
HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC3_INT_ENABLE), 0UL);
HUB_S((u64 *)LOCAL_MMR_ADDR(SH_INT_CMPD), -1L);
mmtimer_clr_int_pending(2);
val = ((u64)SGI_MMTIMER_VECTOR << SH_RTC3_INT_CONFIG_IDX_SHFT) |
((u64)cpu_physical_id(cpu) <<
SH_RTC3_INT_CONFIG_PID_SHFT);
HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC3_INT_CONFIG), val);
HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC3_INT_ENABLE), 1UL);
HUB_S((u64 *)LOCAL_MMR_ADDR(SH_INT_CMPD), expires);
}
/*
* This function must be called with interrupts disabled and preemption off
* in order to insure that the setup succeeds in a deterministic time frame.
* It will check if the interrupt setup succeeded.
*/
static int mmtimer_setup(int cpu, int comparator, unsigned long expires,
u64 *set_completion_time)
{
switch (comparator) {
case 0:
mmtimer_setup_int_0(cpu, expires);
break;
case 1:
mmtimer_setup_int_1(cpu, expires);
break;
case 2:
mmtimer_setup_int_2(cpu, expires);
break;
}
/* We might've missed our expiration time */
*set_completion_time = rtc_time();
if (*set_completion_time <= expires)
return 1;
/*
* If an interrupt is already pending then its okay
* if not then we failed
*/
return mmtimer_int_pending(comparator);
}
static int mmtimer_disable_int(long nasid, int comparator)
{
switch (comparator) {
case 0:
nasid == -1 ? HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC1_INT_ENABLE),
0UL) : REMOTE_HUB_S(nasid, SH_RTC1_INT_ENABLE, 0UL);
break;
case 1:
nasid == -1 ? HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC2_INT_ENABLE),
0UL) : REMOTE_HUB_S(nasid, SH_RTC2_INT_ENABLE, 0UL);
break;
case 2:
nasid == -1 ? HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC3_INT_ENABLE),
0UL) : REMOTE_HUB_S(nasid, SH_RTC3_INT_ENABLE, 0UL);
break;
default:
return -EFAULT;
}
return 0;
}
#define COMPARATOR 1 /* The comparator to use */
#define TIMER_OFF 0xbadcabLL /* Timer is not setup */
#define TIMER_SET 0 /* Comparator is set for this timer */
#define MMTIMER_INTERVAL_RETRY_INCREMENT_DEFAULT 40
/* There is one of these for each timer */
struct mmtimer {
struct rb_node list;
struct k_itimer *timer;
int cpu;
};
struct mmtimer_node {
spinlock_t lock ____cacheline_aligned;
struct rb_root timer_head;
struct rb_node *next;
struct tasklet_struct tasklet;
};
static struct mmtimer_node *timers;
static unsigned mmtimer_interval_retry_increment =
MMTIMER_INTERVAL_RETRY_INCREMENT_DEFAULT;
module_param(mmtimer_interval_retry_increment, uint, 0644);
MODULE_PARM_DESC(mmtimer_interval_retry_increment,
"RTC ticks to add to expiration on interval retry (default 40)");
/*
* Add a new mmtimer struct to the node's mmtimer list.
* This function assumes the struct mmtimer_node is locked.
*/
static void mmtimer_add_list(struct mmtimer *n)
{
int nodeid = n->timer->it.mmtimer.node;
unsigned long expires = n->timer->it.mmtimer.expires;
struct rb_node **link = &timers[nodeid].timer_head.rb_node;
struct rb_node *parent = NULL;
struct mmtimer *x;
/*
* Find the right place in the rbtree:
*/
while (*link) {
parent = *link;
x = rb_entry(parent, struct mmtimer, list);
if (expires < x->timer->it.mmtimer.expires)
link = &(*link)->rb_left;
else
link = &(*link)->rb_right;
}
/*
* Insert the timer to the rbtree and check whether it
* replaces the first pending timer
*/
rb_link_node(&n->list, parent, link);
rb_insert_color(&n->list, &timers[nodeid].timer_head);
if (!timers[nodeid].next || expires < rb_entry(timers[nodeid].next,
struct mmtimer, list)->timer->it.mmtimer.expires)
timers[nodeid].next = &n->list;
}
/*
* Set the comparator for the next timer.
* This function assumes the struct mmtimer_node is locked.
*/
static void mmtimer_set_next_timer(int nodeid)
{
struct mmtimer_node *n = &timers[nodeid];
struct mmtimer *x;
struct k_itimer *t;
u64 expires, exp, set_completion_time;
int i;
restart:
if (n->next == NULL)
return;
x = rb_entry(n->next, struct mmtimer, list);
t = x->timer;
if (!t->it.mmtimer.incr) {
/* Not an interval timer */
if (!mmtimer_setup(x->cpu, COMPARATOR,
t->it.mmtimer.expires,
&set_completion_time)) {
/* Late setup, fire now */
tasklet_schedule(&n->tasklet);
}
return;
}
/* Interval timer */
i = 0;
expires = exp = t->it.mmtimer.expires;
while (!mmtimer_setup(x->cpu, COMPARATOR, expires,
&set_completion_time)) {
int to;
i++;
expires = set_completion_time +
mmtimer_interval_retry_increment + (1 << i);
/* Calculate overruns as we go. */
to = ((u64)(expires - exp) / t->it.mmtimer.incr);
if (to) {
t->it_overrun += to;
t->it.mmtimer.expires += t->it.mmtimer.incr * to;
exp = t->it.mmtimer.expires;
}
if (i > 20) {
printk(KERN_ALERT "mmtimer: cannot reschedule timer\n");
t->it.mmtimer.clock = TIMER_OFF;
n->next = rb_next(&x->list);
rb_erase(&x->list, &n->timer_head);
kfree(x);
goto restart;
}
}
}
/**
* mmtimer_ioctl - ioctl interface for /dev/mmtimer
* @file: file structure for the device
* @cmd: command to execute
* @arg: optional argument to command
*
* Executes the command specified by @cmd. Returns 0 for success, < 0 for
* failure.
*
* Valid commands:
*
* %MMTIMER_GETOFFSET - Should return the offset (relative to the start
* of the page where the registers are mapped) for the counter in question.
*
* %MMTIMER_GETRES - Returns the resolution of the clock in femto (10^-15)
* seconds
*
* %MMTIMER_GETFREQ - Copies the frequency of the clock in Hz to the address
* specified by @arg
*
* %MMTIMER_GETBITS - Returns the number of bits in the clock's counter
*
* %MMTIMER_MMAPAVAIL - Returns 1 if the registers can be mmap'd into userspace
*
* %MMTIMER_GETCOUNTER - Gets the current value in the counter and places it
* in the address specified by @arg.
*/
static long mmtimer_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
int ret = 0;
mutex_lock(&mmtimer_mutex);
switch (cmd) {
case MMTIMER_GETOFFSET: /* offset of the counter */
/*
* SN RTC registers are on their own 64k page
*/
if(PAGE_SIZE <= (1 << 16))
ret = (((long)RTC_COUNTER_ADDR) & (PAGE_SIZE-1)) / 8;
else
ret = -ENOSYS;
break;
case MMTIMER_GETRES: /* resolution of the clock in 10^-15 s */
if(copy_to_user((unsigned long __user *)arg,
&mmtimer_femtoperiod, sizeof(unsigned long)))
ret = -EFAULT;
break;
case MMTIMER_GETFREQ: /* frequency in Hz */
if(copy_to_user((unsigned long __user *)arg,
&sn_rtc_cycles_per_second,
sizeof(unsigned long)))
ret = -EFAULT;
break;
case MMTIMER_GETBITS: /* number of bits in the clock */
ret = RTC_BITS;
break;
case MMTIMER_MMAPAVAIL: /* can we mmap the clock into userspace? */
ret = (PAGE_SIZE <= (1 << 16)) ? 1 : 0;
break;
case MMTIMER_GETCOUNTER:
if(copy_to_user((unsigned long __user *)arg,
RTC_COUNTER_ADDR, sizeof(unsigned long)))
ret = -EFAULT;
break;
default:
ret = -ENOTTY;
break;
}
mutex_unlock(&mmtimer_mutex);
return ret;
}
/**
* mmtimer_mmap - maps the clock's registers into userspace
* @file: file structure for the device
* @vma: VMA to map the registers into
*
* Calls remap_pfn_range() to map the clock's registers into
* the calling process' address space.
*/
static int mmtimer_mmap(struct file *file, struct vm_area_struct *vma)
{
unsigned long mmtimer_addr;
if (vma->vm_end - vma->vm_start != PAGE_SIZE)
return -EINVAL;
if (vma->vm_flags & VM_WRITE)
return -EPERM;
if (PAGE_SIZE > (1 << 16))
return -ENOSYS;
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
mmtimer_addr = __pa(RTC_COUNTER_ADDR);
mmtimer_addr &= ~(PAGE_SIZE - 1);
mmtimer_addr &= 0xfffffffffffffffUL;
if (remap_pfn_range(vma, vma->vm_start, mmtimer_addr >> PAGE_SHIFT,
PAGE_SIZE, vma->vm_page_prot)) {
printk(KERN_ERR "remap_pfn_range failed in mmtimer.c\n");
return -EAGAIN;
}
return 0;
}
static struct miscdevice mmtimer_miscdev = {
SGI_MMTIMER,
MMTIMER_NAME,
&mmtimer_fops
};
static struct timespec sgi_clock_offset;
static int sgi_clock_period;
/*
* Posix Timer Interface
*/
static struct timespec sgi_clock_offset;
static int sgi_clock_period;
static int sgi_clock_get(clockid_t clockid, struct timespec *tp)
{
u64 nsec;
nsec = rtc_time() * sgi_clock_period
+ sgi_clock_offset.tv_nsec;
*tp = ns_to_timespec(nsec);
tp->tv_sec += sgi_clock_offset.tv_sec;
return 0;
};
static int sgi_clock_set(const clockid_t clockid, const struct timespec *tp)
{
u64 nsec;
u32 rem;
nsec = rtc_time() * sgi_clock_period;
sgi_clock_offset.tv_sec = tp->tv_sec - div_u64_rem(nsec, NSEC_PER_SEC, &rem);
if (rem <= tp->tv_nsec)
sgi_clock_offset.tv_nsec = tp->tv_sec - rem;
else {
sgi_clock_offset.tv_nsec = tp->tv_sec + NSEC_PER_SEC - rem;
sgi_clock_offset.tv_sec--;
}
return 0;
}
/**
* mmtimer_interrupt - timer interrupt handler
* @irq: irq received
* @dev_id: device the irq came from
*
* Called when one of the comarators matches the counter, This
* routine will send signals to processes that have requested
* them.
*
* This interrupt is run in an interrupt context
* by the SHUB. It is therefore safe to locally access SHub
* registers.
*/
static irqreturn_t
IRQ: Maintain regs pointer globally rather than passing to IRQ handlers Maintain a per-CPU global "struct pt_regs *" variable which can be used instead of passing regs around manually through all ~1800 interrupt handlers in the Linux kernel. The regs pointer is used in few places, but it potentially costs both stack space and code to pass it around. On the FRV arch, removing the regs parameter from all the genirq function results in a 20% speed up of the IRQ exit path (ie: from leaving timer_interrupt() to leaving do_IRQ()). Where appropriate, an arch may override the generic storage facility and do something different with the variable. On FRV, for instance, the address is maintained in GR28 at all times inside the kernel as part of general exception handling. Having looked over the code, it appears that the parameter may be handed down through up to twenty or so layers of functions. Consider a USB character device attached to a USB hub, attached to a USB controller that posts its interrupts through a cascaded auxiliary interrupt controller. A character device driver may want to pass regs to the sysrq handler through the input layer which adds another few layers of parameter passing. I've build this code with allyesconfig for x86_64 and i386. I've runtested the main part of the code on FRV and i386, though I can't test most of the drivers. I've also done partial conversion for powerpc and MIPS - these at least compile with minimal configurations. This will affect all archs. Mostly the changes should be relatively easy. Take do_IRQ(), store the regs pointer at the beginning, saving the old one: struct pt_regs *old_regs = set_irq_regs(regs); And put the old one back at the end: set_irq_regs(old_regs); Don't pass regs through to generic_handle_irq() or __do_IRQ(). In timer_interrupt(), this sort of change will be necessary: - update_process_times(user_mode(regs)); - profile_tick(CPU_PROFILING, regs); + update_process_times(user_mode(get_irq_regs())); + profile_tick(CPU_PROFILING); I'd like to move update_process_times()'s use of get_irq_regs() into itself, except that i386, alone of the archs, uses something other than user_mode(). Some notes on the interrupt handling in the drivers: (*) input_dev() is now gone entirely. The regs pointer is no longer stored in the input_dev struct. (*) finish_unlinks() in drivers/usb/host/ohci-q.c needs checking. It does something different depending on whether it's been supplied with a regs pointer or not. (*) Various IRQ handler function pointers have been moved to type irq_handler_t. Signed-Off-By: David Howells <dhowells@redhat.com> (cherry picked from 1b16e7ac850969f38b375e511e3fa2f474a33867 commit)
2006-10-05 21:55:46 +08:00
mmtimer_interrupt(int irq, void *dev_id)
{
unsigned long expires = 0;
int result = IRQ_NONE;
unsigned indx = cpu_to_node(smp_processor_id());
struct mmtimer *base;
spin_lock(&timers[indx].lock);
base = rb_entry(timers[indx].next, struct mmtimer, list);
if (base == NULL) {
spin_unlock(&timers[indx].lock);
return result;
}
if (base->cpu == smp_processor_id()) {
if (base->timer)
expires = base->timer->it.mmtimer.expires;
/* expires test won't work with shared irqs */
if ((mmtimer_int_pending(COMPARATOR) > 0) ||
(expires && (expires <= rtc_time()))) {
mmtimer_clr_int_pending(COMPARATOR);
tasklet_schedule(&timers[indx].tasklet);
result = IRQ_HANDLED;
}
}
spin_unlock(&timers[indx].lock);
return result;
}
static void mmtimer_tasklet(unsigned long data)
{
int nodeid = data;
struct mmtimer_node *mn = &timers[nodeid];
struct mmtimer *x;
struct k_itimer *t;
unsigned long flags;
/* Send signal and deal with periodic signals */
spin_lock_irqsave(&mn->lock, flags);
if (!mn->next)
goto out;
x = rb_entry(mn->next, struct mmtimer, list);
t = x->timer;
if (t->it.mmtimer.clock == TIMER_OFF)
goto out;
t->it_overrun = 0;
mn->next = rb_next(&x->list);
rb_erase(&x->list, &mn->timer_head);
if (posix_timer_event(t, 0) != 0)
t->it_overrun++;
if(t->it.mmtimer.incr) {
t->it.mmtimer.expires += t->it.mmtimer.incr;
mmtimer_add_list(x);
} else {
/* Ensure we don't false trigger in mmtimer_interrupt */
t->it.mmtimer.clock = TIMER_OFF;
t->it.mmtimer.expires = 0;
kfree(x);
}
/* Set comparator for next timer, if there is one */
mmtimer_set_next_timer(nodeid);
t->it_overrun_last = t->it_overrun;
out:
spin_unlock_irqrestore(&mn->lock, flags);
}
static int sgi_timer_create(struct k_itimer *timer)
{
/* Insure that a newly created timer is off */
timer->it.mmtimer.clock = TIMER_OFF;
return 0;
}
/* This does not really delete a timer. It just insures
* that the timer is not active
*
* Assumption: it_lock is already held with irq's disabled
*/
static int sgi_timer_del(struct k_itimer *timr)
{
cnodeid_t nodeid = timr->it.mmtimer.node;
unsigned long irqflags;
spin_lock_irqsave(&timers[nodeid].lock, irqflags);
if (timr->it.mmtimer.clock != TIMER_OFF) {
unsigned long expires = timr->it.mmtimer.expires;
struct rb_node *n = timers[nodeid].timer_head.rb_node;
struct mmtimer *uninitialized_var(t);
int r = 0;
timr->it.mmtimer.clock = TIMER_OFF;
timr->it.mmtimer.expires = 0;
while (n) {
t = rb_entry(n, struct mmtimer, list);
if (t->timer == timr)
break;
if (expires < t->timer->it.mmtimer.expires)
n = n->rb_left;
else
n = n->rb_right;
}
if (!n) {
spin_unlock_irqrestore(&timers[nodeid].lock, irqflags);
return 0;
}
if (timers[nodeid].next == n) {
timers[nodeid].next = rb_next(n);
r = 1;
}
rb_erase(n, &timers[nodeid].timer_head);
kfree(t);
if (r) {
mmtimer_disable_int(cnodeid_to_nasid(nodeid),
COMPARATOR);
mmtimer_set_next_timer(nodeid);
}
}
spin_unlock_irqrestore(&timers[nodeid].lock, irqflags);
return 0;
}
/* Assumption: it_lock is already held with irq's disabled */
static void sgi_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
{
if (timr->it.mmtimer.clock == TIMER_OFF) {
cur_setting->it_interval.tv_nsec = 0;
cur_setting->it_interval.tv_sec = 0;
cur_setting->it_value.tv_nsec = 0;
cur_setting->it_value.tv_sec =0;
return;
}
cur_setting->it_interval = ns_to_timespec(timr->it.mmtimer.incr * sgi_clock_period);
cur_setting->it_value = ns_to_timespec((timr->it.mmtimer.expires - rtc_time()) * sgi_clock_period);
}
static int sgi_timer_set(struct k_itimer *timr, int flags,
struct itimerspec * new_setting,
struct itimerspec * old_setting)
{
unsigned long when, period, irqflags;
int err = 0;
cnodeid_t nodeid;
struct mmtimer *base;
struct rb_node *n;
if (old_setting)
sgi_timer_get(timr, old_setting);
sgi_timer_del(timr);
when = timespec_to_ns(&new_setting->it_value);
period = timespec_to_ns(&new_setting->it_interval);
if (when == 0)
/* Clear timer */
return 0;
base = kmalloc(sizeof(struct mmtimer), GFP_KERNEL);
if (base == NULL)
return -ENOMEM;
if (flags & TIMER_ABSTIME) {
struct timespec n;
unsigned long now;
getnstimeofday(&n);
now = timespec_to_ns(&n);
if (when > now)
when -= now;
else
/* Fire the timer immediately */
when = 0;
}
/*
* Convert to sgi clock period. Need to keep rtc_time() as near as possible
* to getnstimeofday() in order to be as faithful as possible to the time
* specified.
*/
when = (when + sgi_clock_period - 1) / sgi_clock_period + rtc_time();
period = (period + sgi_clock_period - 1) / sgi_clock_period;
/*
* We are allocating a local SHub comparator. If we would be moved to another
* cpu then another SHub may be local to us. Prohibit that by switching off
* preemption.
*/
preempt_disable();
nodeid = cpu_to_node(smp_processor_id());
/* Lock the node timer structure */
spin_lock_irqsave(&timers[nodeid].lock, irqflags);
base->timer = timr;
base->cpu = smp_processor_id();
timr->it.mmtimer.clock = TIMER_SET;
timr->it.mmtimer.node = nodeid;
timr->it.mmtimer.incr = period;
timr->it.mmtimer.expires = when;
n = timers[nodeid].next;
/* Add the new struct mmtimer to node's timer list */
mmtimer_add_list(base);
if (timers[nodeid].next == n) {
/* No need to reprogram comparator for now */
spin_unlock_irqrestore(&timers[nodeid].lock, irqflags);
preempt_enable();
return err;
}
/* We need to reprogram the comparator */
if (n)
mmtimer_disable_int(cnodeid_to_nasid(nodeid), COMPARATOR);
mmtimer_set_next_timer(nodeid);
/* Unlock the node timer structure */
spin_unlock_irqrestore(&timers[nodeid].lock, irqflags);
preempt_enable();
return err;
}
static int sgi_clock_getres(const clockid_t which_clock, struct timespec *tp)
{
tp->tv_sec = 0;
tp->tv_nsec = sgi_clock_period;
return 0;
}
static struct k_clock sgi_clock = {
.clock_set = sgi_clock_set,
.clock_get = sgi_clock_get,
.clock_getres = sgi_clock_getres,
.timer_create = sgi_timer_create,
.timer_set = sgi_timer_set,
.timer_del = sgi_timer_del,
.timer_get = sgi_timer_get
};
/**
* mmtimer_init - device initialization routine
*
* Does initial setup for the mmtimer device.
*/
static int __init mmtimer_init(void)
{
cnodeid_t node, maxn = -1;
if (!ia64_platform_is("sn2"))
return 0;
/*
* Sanity check the cycles/sec variable
*/
if (sn_rtc_cycles_per_second < 100000) {
printk(KERN_ERR "%s: unable to determine clock frequency\n",
MMTIMER_NAME);
goto out1;
}
mmtimer_femtoperiod = ((unsigned long)1E15 + sn_rtc_cycles_per_second /
2) / sn_rtc_cycles_per_second;
if (request_irq(SGI_MMTIMER_VECTOR, mmtimer_interrupt, IRQF_PERCPU, MMTIMER_NAME, NULL)) {
printk(KERN_WARNING "%s: unable to allocate interrupt.",
MMTIMER_NAME);
goto out1;
}
if (misc_register(&mmtimer_miscdev)) {
printk(KERN_ERR "%s: failed to register device\n",
MMTIMER_NAME);
goto out2;
}
/* Get max numbered node, calculate slots needed */
for_each_online_node(node) {
maxn = node;
}
maxn++;
/* Allocate list of node ptrs to mmtimer_t's */
timers = kzalloc(sizeof(struct mmtimer_node)*maxn, GFP_KERNEL);
if (!timers) {
printk(KERN_ERR "%s: failed to allocate memory for device\n",
MMTIMER_NAME);
goto out3;
}
/* Initialize struct mmtimer's for each online node */
for_each_online_node(node) {
spin_lock_init(&timers[node].lock);
tasklet_init(&timers[node].tasklet, mmtimer_tasklet,
(unsigned long) node);
}
sgi_clock_period = NSEC_PER_SEC / sn_rtc_cycles_per_second;
posix_timers_register_clock(CLOCK_SGI_CYCLE, &sgi_clock);
printk(KERN_INFO "%s: v%s, %ld MHz\n", MMTIMER_DESC, MMTIMER_VERSION,
sn_rtc_cycles_per_second/(unsigned long)1E6);
return 0;
out3:
misc_deregister(&mmtimer_miscdev);
out2:
free_irq(SGI_MMTIMER_VECTOR, NULL);
out1:
return -1;
}
module_init(mmtimer_init);