Hello Suresh,
> In driver init function after registering IRQ, I want to raise the thread
> priority to default + 1, but am unable to find the suitable API's.
> I am using 2.6.26 series with rt-patch.
I use the attached patches for this.
Did not found the time yet to push them upstream. (But they were
discussed about quite some time ago on lkml and the comments are
reworked.)
Apply these patches in this order:
1. add-map-functionality-to-kernel-cmdline.patch
2. changing_interrupt_prios_from_kernel_cmdline.patch
3. changing_softirq_prios_from_kernel_cmdline.patch
Kind regards,
Remy
Add generic routine for parsing map-like options on kernel cmd-line
This patch adds a generic routine to the kernel, so that a map of
settings can be entered on the kernel commandline.
Signed-off-by: Remy Bohmer <linux@xxxxxxxxxx>
---
---
include/linux/kernel.h | 1
lib/cmdline.c | 78 ++++++++++++++++++++++++++++++++++++++++++++++---
2 files changed, 75 insertions(+), 4 deletions(-)
Index: linux-2.6.26/include/linux/kernel.h
===================================================================
--- linux-2.6.26.orig/include/linux/kernel.h 2009-03-10 22:35:50.000000000 +0100
+++ linux-2.6.26/include/linux/kernel.h 2009-03-10 22:42:36.000000000 +0100
@@ -174,6 +174,7 @@ extern int vsscanf(const char *, const c
extern int get_option(char **str, int *pint);
extern char *get_options(const char *str, int nints, int *ints);
+extern int get_map_option(const char *str, const char *key, int *pint);
extern unsigned long long memparse(char *ptr, char **retptr);
extern int core_kernel_text(unsigned long addr);
Index: linux-2.6.26/lib/cmdline.c
===================================================================
--- linux-2.6.26.orig/lib/cmdline.c 2008-07-13 23:51:29.000000000 +0200
+++ linux-2.6.26/lib/cmdline.c 2009-03-10 22:42:36.000000000 +0100
@@ -15,6 +15,7 @@
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/string.h>
+#include <asm/setup.h>
/*
* If a hyphen was found in get_option, this will handle the
@@ -67,6 +68,7 @@ int get_option (char **str, int *pint)
return 1;
}
+EXPORT_SYMBOL(get_option);
/**
* get_options - Parse a string into a list of integers
@@ -112,6 +114,78 @@ char *get_options(const char *str, int n
ints[0] = i - 1;
return (char *)str;
}
+EXPORT_SYMBOL(get_options);
+
+static int
+parse_map_field(const char *key, const char *substr, int len, int *pint)
+{
+ int found = 0;
+
+ if (len != 0) {
+ if (key) {
+ /* check if the first part of the key matches */
+ if (!strncmp(substr, key, strlen(key))) {
+ const char *strval = substr + strlen(key);
+ /* Now the next char must be a ':',
+ if not, search for the next match */
+ if (*strval == ':') {
+ strval++;
+ if ((len - (strval - substr)) > 0) {
+ *pint = (int)
+ simple_strtol(strval,
+ NULL, 10);
+ found = 1;
+ }
+ }
+ }
+ } else {
+ /* Check for the absence of any ':' */
+ if (strnchr(substr, len, ':') == NULL) {
+ *pint = (int) simple_strtol(substr, NULL, 10);
+ found = 1;
+ }
+ }
+ }
+
+ return found;
+}
+
+/**
+ * get_map_option - Parse integer from an option map
+ * @str: option string
+ * @key: The key inside the map, can be NULL
+ * @pint: (output) integer value parsed from the map @str
+ *
+ * This function parses an integer from an option map like
+ * some_map=key1:99,key2:98,...,keyN:NN,NN
+ * Only the value of the first match is returned, or if no
+ * key option is given (key = NULL) the value of the first
+ * field without a ':' is returned.
+ *
+ * Return values:
+ * 0 - key (or default) not found or is invalid
+ * 1 - key found and is valid
+ */
+int get_map_option(const char *str, const char *key, int *pint)
+{
+ const char *start = str;
+ const char *end = str;
+ int found = 0;
+
+ do {
+ end++;
+ /* Search a for a field seperated by ',' */
+ if ((*end == ',') || (*end == '\0')) {
+ found = parse_map_field(key, start, end - start, pint);
+
+ /* set start to beginning of next field */
+ start = end + 1;
+ }
+ } while ((*end) && (!found));
+
+ return found;
+}
+EXPORT_SYMBOL(get_map_option);
/**
* memparse - parse a string with mem suffixes into a number
@@ -146,8 +220,4 @@ unsigned long long memparse (char *ptr,
}
return ret;
}
-
-
EXPORT_SYMBOL(memparse);
-EXPORT_SYMBOL(get_option);
-EXPORT_SYMBOL(get_options);
The RT-patch originally creates all its IRQ-threads at priority 50.
Of course, this is not a usable default for many realtime systems
and therefor these priorities has to be tuneable for each RT-system.
But, currently there is no way within the kernel to adjust this to
the needs of the user. Some scripts are floating around to do this
from userspace, but for several applications the priorities should
already be set properly by the kernel itself before userland is
started.
This patch changes this by adding a kernel cmd-line option that can
handle a map of priorities.
It is based on the name of the driver that requests an interrupt, it
does NOT use the IRQ-ID to prioritize a certain IRQ thread.
This is designed this way because across several hardware-boards the
IRQ-IDs can change, but not necessarily the drivers
(interrupt handlers) name.
Remarks:
* There is a check for conflicts added, for situations where
IRQ-sharing is detected with different priorities requested
on the kernel cmd-line.
* Priorities are only set at creation time of the IRQ-thread.
* If userland overrules, it is NOT restored by this code.
* if no new kernel cmdline options are given, the kernel works
as before, and all IRQ-threads start at 50.
* No wildcards are supported on the cmdline.
See kernel/Documentation/kernel-parameters.txt for usage info.
Signed-off-by: Remy Bohmer <linux@xxxxxxxxxx>
---
Documentation/kernel-parameters.txt | 6 ++
include/linux/irq.h | 1
kernel/Kconfig.preempt | 17 +++++
kernel/irq/manage.c | 105 ++++++++++++++++++++++++++++++++----
4 files changed, 118 insertions(+), 11 deletions(-)
Index: linux-2.6.26/Documentation/kernel-parameters.txt
===================================================================
--- linux-2.6.26.orig/Documentation/kernel-parameters.txt 2009-03-15 21:48:21.000000000 +0100
+++ linux-2.6.26/Documentation/kernel-parameters.txt 2009-03-15 22:05:05.000000000 +0100
@@ -881,6 +881,12 @@ and is between 256 and 4096 characters.
ips= [HW,SCSI] Adaptec / IBM ServeRAID controller
See header of drivers/scsi/ips.c.
+ pmap_hirq= [IRQ-threading] List of priorities each interrupt
+ thread must have. Used to overrule the list provided
+ by CONFIG_PREEMPT_HARDIRQS_PRIORITIES
+ Format: pmap_hirq=megasas:90,eth0:40,50
+ The first field without ':', is the default prio.
+
ports= [IP_VS_FTP] IPVS ftp helper module
Default is 21.
Up to 8 (IP_VS_APP_MAX_PORTS) ports
Index: linux-2.6.26/include/linux/irq.h
===================================================================
--- linux-2.6.26.orig/include/linux/irq.h 2009-03-15 21:43:08.000000000 +0100
+++ linux-2.6.26/include/linux/irq.h 2009-03-15 21:48:21.000000000 +0100
@@ -170,6 +170,7 @@ struct irq_desc {
unsigned int irqs_unhandled;
unsigned long last_unhandled; /* Aging timer for unhandled count */
struct task_struct *thread;
+ int rt_prio;
wait_queue_head_t wait_for_handler;
cycles_t timestamp;
raw_spinlock_t lock;
Index: linux-2.6.26/kernel/irq/manage.c
===================================================================
--- linux-2.6.26.orig/kernel/irq/manage.c 2009-03-15 21:43:08.000000000 +0100
+++ linux-2.6.26/kernel/irq/manage.c 2009-03-15 22:03:02.000000000 +0100
@@ -14,9 +14,14 @@
#include <linux/syscalls.h>
#include <linux/interrupt.h>
#include <linux/slab.h>
+#include <linux/list.h>
#include "internals.h"
+#ifdef CONFIG_PREEMPT_HARDIRQS
+static char *cmdline;
+#endif
+
#ifdef CONFIG_SMP
/**
@@ -266,7 +271,7 @@ void recalculate_desc_flags(struct irq_d
desc->status |= IRQ_NODELAY;
}
-static int start_irq_thread(int irq, struct irq_desc *desc);
+static int start_irq_thread(int irq, struct irq_desc *desc, int prio);
/*
* Internal function that tells the architecture code whether a
@@ -299,6 +304,8 @@ void compat_irq_chip_set_default_handler
desc->handle_irq = NULL;
}
+static int get_irq_prio(const char *name);
+
/*
* Internal function to register an irqaction - typically used to
* allocate special interrupts that are part of the architecture.
@@ -334,7 +341,7 @@ int setup_irq(unsigned int irq, struct i
}
if (!(new->flags & IRQF_NODELAY))
- if (start_irq_thread(irq, desc))
+ if (start_irq_thread(irq, desc, get_irq_prio(new->name)))
return -ENOMEM;
/*
* The following block of code has to be executed atomically
@@ -813,11 +820,7 @@ static int do_irqd(void * __desc)
#endif
current->flags |= PF_NOFREEZE | PF_HARDIRQ;
- /*
- * Set irq thread priority to SCHED_FIFO/50:
- */
- param.sched_priority = MAX_USER_RT_PRIO/2;
-
+ param.sched_priority = desc->rt_prio;
sys_sched_setscheduler(current->pid, SCHED_FIFO, ¶m);
while (!kthread_should_stop()) {
@@ -844,11 +847,20 @@ static int do_irqd(void * __desc)
static int ok_to_create_irq_threads;
-static int start_irq_thread(int irq, struct irq_desc *desc)
+static int start_irq_thread(int irq, struct irq_desc *desc, int prio)
{
- if (desc->thread || !ok_to_create_irq_threads)
+ if (!ok_to_create_irq_threads)
return 0;
+ if (desc->thread) {
+ if (desc->rt_prio != prio)
+ printk(KERN_NOTICE
+ "irqd: Interrupt sharing detected with "
+ "conflicting thread priorities, irq:%d!\n", irq);
+ return 0;
+ }
+
+ desc->rt_prio = prio;
desc->thread = kthread_create(do_irqd, desc, "IRQ-%d", irq);
if (!desc->thread) {
printk(KERN_ERR "irqd: could not create IRQ thread %d!\n", irq);
@@ -875,13 +887,13 @@ void __init init_hardirqs(void)
irq_desc_t *desc = irq_desc + i;
if (desc->action && !(desc->status & IRQ_NODELAY))
- start_irq_thread(i, desc);
+ start_irq_thread(i, desc, get_irq_prio(NULL));
}
}
#else
-static int start_irq_thread(int irq, struct irq_desc *desc)
+static int start_irq_thread(int irq, struct irq_desc *desc, int prio)
{
return 0;
}
@@ -895,3 +907,74 @@ void __init early_init_hardirqs(void)
for (i = 0; i < NR_IRQS; i++)
init_waitqueue_head(&irq_desc[i].wait_for_handler);
}
+
+#ifdef CONFIG_PREEMPT_HARDIRQS
+
+static int check_prio_range(int prio)
+{
+ if ((prio <= 0) || (prio >= MAX_USER_RT_PRIO))
+ prio = MAX_USER_RT_PRIO/2;
+
+ return prio;
+}
+
+static int get_default_irq_prio(const char *prio_map)
+{
+ int prio;
+
+ if (!get_map_option(prio_map, NULL, &prio))
+ prio = MAX_USER_RT_PRIO/2;
+
+ return prio;
+}
+
+/*
+ * Lookup the interrupt thread priority
+ * A map for the priorities can be given on the kernel commandline or Kconfig.
+ * if name is NULL, or no list is available, the default prio is used.
+ */
+static int get_irq_prio(const char *name)
+{
+ int prio;
+ char *prio_map = cmdline;
+
+ /* If no commandline options, use thread prio defaults from Kconfig.*/
+ if (!prio_map)
+ prio_map = CONFIG_PREEMPT_HARDIRQS_PRIORITIES;
+
+ if (!get_map_option(prio_map, name, &prio))
+ prio = get_default_irq_prio(prio_map);
+
+ prio = check_prio_range(prio);
+
+ return prio;
+}
+
+/*
+ * Store the pointer to the arguments in a global var, and store the
+ * default prio globally
+ */
+static int __init irq_prio_map_setup(char *str)
+{
+ if (!str) /* sanity check */
+ return 1;
+
+ cmdline = str; /* store it for later use */
+ return 1;
+}
+
+/*
+ * The commandline looks like this: pmap_hirq=megasas:90,eth0:40,50
+ * The first field without the ':' is used as the default for all irq-threads.
+ * There is a check for conflicts on irq-sharing.
+ * The priorities are only set on creation of the interrupt threads, thus at
+ * the time a driver uses a certain interrupt thread for the first time.
+ * Unknown or redundant fields are ignored.
+ */
+__setup("pmap_hirq=", irq_prio_map_setup);
+#else
+static int get_irq_prio(const char *name)
+{
+ return 50;
+}
+#endif
Index: linux-2.6.26/kernel/Kconfig.preempt
===================================================================
--- linux-2.6.26.orig/kernel/Kconfig.preempt 2009-03-15 21:43:08.000000000 +0100
+++ linux-2.6.26/kernel/Kconfig.preempt 2009-03-15 22:05:05.000000000 +0100
@@ -121,6 +121,23 @@ config PREEMPT_HARDIRQS
Say N if you are unsure.
+config PREEMPT_HARDIRQS_PRIORITIES
+ string "Thread Hardirqs priorities"
+ default "50"
+ depends on PREEMPT_HARDIRQS
+ help
+ This option specifies the priority of each interrupt thread.
+
+ Format: megasas:90,eth0:40,50
+ The first field without ':', is the default priority to be used.
+ The string to be used is the name of the interrupt handler, and
+ can be found in 'cat /proc/interrupts'.
+
+ This line can be overruled on the kernel command line through
+ the pmap_hirq option. See Documentation/kernel-parameters.txt
+
+ Leave default (50) if you are unsure.
+
config PREEMPT_RCU
bool "Preemptible RCU"
depends on PREEMPT
The RT-patch originally creates all its softirq-threads at
priority 50. Of course, this is not a usable default for many
realtime systems and therefor these priorities has to be tuneable
for each RT-system. But, currently there is no way within the
kernel to adjust this to the needs of the user. Some scripts
are floating around to do this from userspace, but for several
applications the priorities should already be set properly by
the kernel itself before userland is started.
This patch changes this by adding a kernel cmd-line option that
can handle a map of priorities.
Remarks:
* Priorities are only set at creation time of the softirq.
* Priorities has to be set per-cpu.
* If userland overrules, it is NOT restored by this code.
* if no new kernel cmdline options are given, the kernel works
as before, and all softirqs start at 50.
* No wildcards are supported on the cmdline.
See kernel/Documentation/kernel-parameters.txt for usage info.
Signed-off-by: Remy Bohmer <linux@xxxxxxxxxx>
---
Documentation/kernel-parameters.txt | 10 +++
kernel/Kconfig.preempt | 16 +++++
kernel/softirq.c | 109 ++++++++++++++++++++++++++++++------
3 files changed, 118 insertions(+), 17 deletions(-)
Index: linux-2.6.26/Documentation/kernel-parameters.txt
===================================================================
--- linux-2.6.26.orig/Documentation/kernel-parameters.txt 2009-03-15 21:48:21.000000000 +0100
+++ linux-2.6.26/Documentation/kernel-parameters.txt 2009-03-15 21:48:21.000000000 +0100
@@ -887,6 +887,16 @@ and is between 256 and 4096 characters.
Format: pmap_hirq=megasas:90,eth0:40,50
The first field without ':', is the default prio.
+ pmap_sirq= [IRQ-threading] List of priorities each softirq
+ thread must have. Used to overrule the list provided
+ by CONFIG_PREEMPT_SOFTIRQS_PRIORITIES
+ Format: pmap_sirq=block/0:90,sched/0:75,50
+ The priorities have to be specified per-cpu.
+ The first field without ':', is the default prio.
+ The names have to match the softirq_names[] table in
+ kernel/softirq.c, (thus without 'softirq-' prefix) to
+ keep the cmd-line short.
+
ports= [IP_VS_FTP] IPVS ftp helper module
Default is 21.
Up to 8 (IP_VS_APP_MAX_PORTS) ports
Index: linux-2.6.26/kernel/softirq.c
===================================================================
--- linux-2.6.26.orig/kernel/softirq.c 2009-03-15 21:43:08.000000000 +0100
+++ linux-2.6.26/kernel/softirq.c 2009-03-15 21:55:50.000000000 +0100
@@ -68,6 +68,9 @@ struct softirqdata {
static DEFINE_PER_CPU(struct softirqdata [MAX_SOFTIRQ], ksoftirqd);
+static char *cmdline;
+
+
#ifdef CONFIG_PREEMPT_SOFTIRQS
/*
* Preempting the softirq causes cases that would not be a
@@ -725,10 +728,28 @@ EXPORT_SYMBOL(tasklet_unlock_wait);
#endif
+static const char *softirq_names [] =
+{
+ [HI_SOFTIRQ] = "high",
+ [SCHED_SOFTIRQ] = "sched",
+ [TIMER_SOFTIRQ] = "timer",
+ [NET_TX_SOFTIRQ] = "net-tx",
+ [NET_RX_SOFTIRQ] = "net-rx",
+ [BLOCK_SOFTIRQ] = "block",
+ [TASKLET_SOFTIRQ] = "tasklet",
+#ifdef CONFIG_HIGH_RES_TIMERS
+ [HRTIMER_SOFTIRQ] = "hrtimer",
+#endif
+ [RCU_SOFTIRQ] = "rcu",
+};
+
+static int get_softirq_prio(const char *name);
+
static int ksoftirqd(void * __data)
{
- struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO/2 };
+ struct sched_param param = { 0, };
struct softirqdata *data = __data;
+ char buf[50];
u32 softirq_mask = (1 << data->nr);
struct softirq_action *h;
int cpu = data->cpu;
@@ -736,8 +757,12 @@ static int ksoftirqd(void * __data)
#ifdef CONFIG_PREEMPT_SOFTIRQS
init_waitqueue_head(&data->wait);
#endif
-
+ /* Lookup the priority of this softirq, and set the prio accordingly */
+ snprintf(buf, sizeof(buf), "%s/%lu",
+ softirq_names[data->nr], data->cpu);
+ param.sched_priority = get_softirq_prio(buf);
sys_sched_setscheduler(current->pid, SCHED_FIFO, ¶m);
+
current->flags |= PF_SOFTIRQ;
set_current_state(TASK_INTERRUPTIBLE);
@@ -873,21 +898,6 @@ void takeover_tasklets(unsigned int cpu)
}
#endif /* CONFIG_HOTPLUG_CPU */
-static const char *softirq_names [] =
-{
- [HI_SOFTIRQ] = "high",
- [SCHED_SOFTIRQ] = "sched",
- [TIMER_SOFTIRQ] = "timer",
- [NET_TX_SOFTIRQ] = "net-tx",
- [NET_RX_SOFTIRQ] = "net-rx",
- [BLOCK_SOFTIRQ] = "block",
- [TASKLET_SOFTIRQ] = "tasklet",
-#ifdef CONFIG_HIGH_RES_TIMERS
- [HRTIMER_SOFTIRQ] = "hrtimer",
-#endif
- [RCU_SOFTIRQ] = "rcu",
-};
-
static int __cpuinit cpu_callback(struct notifier_block *nfb,
unsigned long action,
void *hcpu)
@@ -1014,3 +1024,68 @@ int on_each_cpu(void (*func) (void *info
}
EXPORT_SYMBOL(on_each_cpu);
#endif
+
+static int check_prio_range(int prio)
+{
+ if ((prio <= 0) || (prio >= MAX_USER_RT_PRIO))
+ prio = MAX_USER_RT_PRIO/2;
+
+ return prio;
+}
+
+static int get_default_irq_prio(const char *prio_map)
+{
+ int prio;
+
+ if (!get_map_option(prio_map, NULL, &prio))
+ prio = MAX_USER_RT_PRIO/2;
+
+ return prio;
+}
+
+/*
+ * Lookup the softirq thread priority.
+ * A map for the priorities can be given on the kernel commandline or Kconfig.
+ * if name is NULL the default prio is used.
+ */
+static int get_softirq_prio(const char *name)
+{
+ int prio;
+ char *prio_map = cmdline;
+
+ /* If no commandline options, use thread prio defaults from Kconfig.*/
+#ifdef CONFIG_PREEMPT_SOFTIRQS_PRIORITIES
+ if (!prio_map)
+ prio_map = CONFIG_PREEMPT_SOFTIRQS_PRIORITIES;
+#endif
+ if (!get_map_option(prio_map, name, &prio))
+ prio = get_default_irq_prio(prio_map);
+
+ prio = check_prio_range(prio);
+
+ return prio;
+}
+
+/*
+ * Store the pointer to the arguments in a global var, and store the
+ * default prio globally
+ */
+static int __init softirq_prio_map_setup(char *str)
+{
+ if (!str) /* sanity check */
+ return 1;
+
+ cmdline = str; /* store it for later use */
+ return 1;
+}
+
+/*
+ * The commandline looks like this:
+ * pmap_sirq=block/0:90,sched/0:75,50
+ * The first field without the ':' is used as the default for all
+ * soft-irq-threads. The priorities are only set on creation of the
+ * softirq threads. Unknown or redundant fields are ignored.
+ * The names have to match the softirq_names[] table without 'softirq-' prefix
+ * to keep the cmd-line short.
+ */
+__setup("pmap_sirq=", softirq_prio_map_setup);
Index: linux-2.6.26/kernel/Kconfig.preempt
===================================================================
--- linux-2.6.26.orig/kernel/Kconfig.preempt 2009-03-15 21:48:21.000000000 +0100
+++ linux-2.6.26/kernel/Kconfig.preempt 2009-03-15 21:48:21.000000000 +0100
@@ -102,6 +102,22 @@ config PREEMPT_SOFTIRQS
Say N if you are unsure.
+config PREEMPT_SOFTIRQS_PRIORITIES
+ string "Thread Softirqs priorities"
+ default "50"
+ depends on PREEMPT_SOFTIRQS
+ help
+ This option specifies the priority of each soft-irq thread.
+
+ Format: "block/0:90,sched/0:75,50"
+ The priorities have to be specified per-cpu.
+ The first field without ':', is the default prio.
+ The names have to match the softirq_names[] table in
+ kernel/softirq.c, (thus without 'softirq-' prefix) to
+ keep the cmd-line short.
+
+ Leave default (50) if you are unsure.
+
config PREEMPT_HARDIRQS
bool "Thread Hardirqs"
default n
