summaryrefslogtreecommitdiff
path: root/include/linux/spi
diff options
context:
space:
mode:
authorMartin Sperl <kernel@martin.sperl.org>2019-01-08 15:13:45 +0300
committerMark Brown <broonie@kernel.org>2019-01-09 22:16:18 +0300
commit412e60373245fd1dfae8d4d44c5d1406b3d90971 (patch)
treecd716d2e49b96ff645de95863b7fa760ed7a6adc /include/linux/spi
parent9400c41e77b8f1f9c711b08a6c79bdbc5681fb00 (diff)
downloadlinux-412e60373245fd1dfae8d4d44c5d1406b3d90971.tar.xz
spi: core: avoid waking pump thread from spi_sync instead run teardown delayed
When spi_sync is running alone with no other spi devices connected to the bus the worker thread is woken during spi_finalize_current_message to run the teardown code every time. This is totally unnecessary in the case that there is no message queued. On a multi-core system this results in one wakeup of the thread for each spi_message processed via spi_sync where in most cases the teardown does not happen as the hw is already in use. This patch now delays the teardown by 1 second by using a separate kthread_delayed_work for the teardown. This avoids waking the kthread too often. For spi_sync transfers in a tight loop (say 40k messages/s) this avoids the penalty of waking the worker thread 40k times/s. On a rasperry pi 3 with 4 cores the results in 32% of a single core only to find out that there is nothing in the queue and it can go back to sleep. With this patch applied the spi-worker is woken exactly once: after the load finishes and the spi bus is idle for 1 second. I believe I have also seen situations where during a spi_sync loop the worker thread (triggered by the last message finished) is slightly faster and _wins_ the race to process the message, so we are actually running the kthread and letting it do some work... This is also no longer observed with this patch applied as. Tested with a new CAN controller driver for the mcp2517fd which uses spi_sync for interrupt handling and spi_async for scheduling of can frames for transmission (in a different thread) Some statistics when receiving 100000 CAN frames with the mcp25xxfd driver on a Raspberry pi 3: without the patch: ------------------ root@raspcm3:~# for x in $(pgrep spi0) $(pgrep irq/94-mcp25xxf) ; do awk '{printf "%-20s %6i\n", $2,$15}' /proc/$x/stat; done (spi0) 5 (irq/94-mcp25xxf) 0 root@raspcm3:~# vmstat 1 procs -----------memory---------- ---swap-- -----io---- -system-- ------cpu----- r b swpd free buff cache si so bi bo in cs us sy id wa st 1 0 0 821960 13592 50848 0 0 80 2 1986 105 1 2 97 0 0 0 0 0 821968 13592 50876 0 0 0 0 8046 30 0 0 100 0 0 0 0 0 821936 13592 50876 0 0 0 0 8032 24 0 0 100 0 0 0 0 0 821936 13592 50876 0 0 0 0 8035 30 0 0 100 0 0 0 0 0 821936 13592 50876 0 0 0 0 8033 22 0 0 100 0 0 2 0 0 821936 13592 50876 0 0 0 0 11598 7129 0 3 97 0 0 1 0 0 821872 13592 50876 0 0 0 0 37741 59003 0 31 69 0 0 2 0 0 821840 13592 50876 0 0 0 0 37762 59078 0 29 71 0 0 2 0 0 821776 13592 50876 0 0 0 0 37593 58792 0 28 72 0 0 1 0 0 821744 13592 50876 0 0 0 0 37642 58881 0 30 70 0 0 2 0 0 821680 13592 50876 0 0 0 0 37490 58602 0 27 73 0 0 1 0 0 821648 13592 50876 0 0 0 0 37412 58418 0 29 71 0 0 1 0 0 821584 13592 50876 0 0 0 0 37337 58288 0 27 73 0 0 1 0 0 821552 13592 50876 0 0 0 0 37584 58774 0 27 73 0 0 0 0 0 821520 13592 50876 0 0 0 0 18363 20566 0 9 91 0 0 0 0 0 821520 13592 50876 0 0 0 0 8037 32 0 0 100 0 0 0 0 0 821520 13592 50876 0 0 0 0 8031 23 0 0 100 0 0 0 0 0 821520 13592 50876 0 0 0 0 8034 26 0 0 100 0 0 0 0 0 821520 13592 50876 0 0 0 0 8033 24 0 0 100 0 0 ^C root@raspcm3:~# for x in $(pgrep spi0) $(pgrep irq/94-mcp25xxf) ; do awk '{printf "%-20s %6i\n", $2,$15}' /proc/$x/stat; done (spi0) 228 (irq/94-mcp25xxf) 794 root@raspcm3:~# cat /proc/interrupts CPU0 CPU1 CPU2 CPU3 17: 34 0 0 0 ARMCTRL-level 1 Edge 3f00b880.mailbox 27: 1 0 0 0 ARMCTRL-level 35 Edge timer 33: 1416870 0 0 0 ARMCTRL-level 41 Edge 3f980000.usb, dwc2_hsotg:usb1 34: 1 0 0 0 ARMCTRL-level 42 Edge vc4 35: 0 0 0 0 ARMCTRL-level 43 Edge 3f004000.txp 40: 1753 0 0 0 ARMCTRL-level 48 Edge DMA IRQ 42: 11 0 0 0 ARMCTRL-level 50 Edge DMA IRQ 44: 11 0 0 0 ARMCTRL-level 52 Edge DMA IRQ 45: 0 0 0 0 ARMCTRL-level 53 Edge DMA IRQ 66: 0 0 0 0 ARMCTRL-level 74 Edge vc4 crtc 69: 0 0 0 0 ARMCTRL-level 77 Edge vc4 crtc 70: 0 0 0 0 ARMCTRL-level 78 Edge vc4 crtc 77: 20 0 0 0 ARMCTRL-level 85 Edge 3f205000.i2c, 3f804000.i2c, 3f805000.i2c 78: 6346 0 0 0 ARMCTRL-level 86 Edge 3f204000.spi 80: 205 0 0 0 ARMCTRL-level 88 Edge mmc0 81: 493 0 0 0 ARMCTRL-level 89 Edge uart-pl011 89: 0 0 0 0 bcm2836-timer 0 Edge arch_timer 90: 4291 3821 2180 1649 bcm2836-timer 1 Edge arch_timer 94: 14289 0 0 0 pinctrl-bcm2835 16 Level mcp25xxfd IPI0: 0 0 0 0 CPU wakeup interrupts IPI1: 0 0 0 0 Timer broadcast interrupts IPI2: 3645 242371 7919 1328 Rescheduling interrupts IPI3: 112 543 273 194 Function call interrupts IPI4: 0 0 0 0 CPU stop interrupts IPI5: 1 0 0 0 IRQ work interrupts IPI6: 0 0 0 0 completion interrupts Err: 0 top shows 93% for the mcp25xxfd interrupt handler, 31% for spi0. with the patch: --------------- root@raspcm3:~# for x in $(pgrep spi0) $(pgrep irq/94-mcp25xxf) ; do awk '{printf "%-20s %6i\n", $2,$15}' /proc/$x/stat; done (spi0) 0 (irq/94-mcp25xxf) 0 root@raspcm3:~# vmstat 1 procs -----------memory---------- ---swap-- -----io---- -system-- ------cpu----- 0 0 0 804768 13584 62628 0 0 0 0 8038 24 0 0 100 0 0 0 0 0 804768 13584 62628 0 0 0 0 8042 25 0 0 100 0 0 1 0 0 804704 13584 62628 0 0 0 0 9603 2967 0 20 80 0 0 1 0 0 804672 13584 62628 0 0 0 0 9828 3380 0 24 76 0 0 1 0 0 804608 13584 62628 0 0 0 0 9823 3375 0 23 77 0 0 1 0 0 804608 13584 62628 0 0 0 12 9829 3394 0 23 77 0 0 1 0 0 804544 13584 62628 0 0 0 0 9816 3362 0 22 78 0 0 1 0 0 804512 13584 62628 0 0 0 0 9817 3367 0 23 77 0 0 1 0 0 804448 13584 62628 0 0 0 0 9822 3370 0 22 78 0 0 1 0 0 804416 13584 62628 0 0 0 0 9815 3367 0 23 77 0 0 0 0 0 804352 13584 62628 0 0 0 84 9222 2250 0 14 86 0 0 0 0 0 804352 13592 62620 0 0 0 24 8131 209 0 0 93 7 0 0 0 0 804320 13592 62628 0 0 0 0 8041 27 0 0 100 0 0 0 0 0 804352 13592 62628 0 0 0 0 8040 26 0 0 100 0 0 root@raspcm3:~# for x in $(pgrep spi0) $(pgrep irq/94-mcp25xxf) ; do awk '{printf "%-20s %6i\n", $2,$15}' /proc/$x/stat; done (spi0) 0 (irq/94-mcp25xxf) 767 root@raspcm3:~# cat /proc/interrupts CPU0 CPU1 CPU2 CPU3 17: 29 0 0 0 ARMCTRL-level 1 Edge 3f00b880.mailbox 27: 1 0 0 0 ARMCTRL-level 35 Edge timer 33: 1024412 0 0 0 ARMCTRL-level 41 Edge 3f980000.usb, dwc2_hsotg:usb1 34: 1 0 0 0 ARMCTRL-level 42 Edge vc4 35: 0 0 0 0 ARMCTRL-level 43 Edge 3f004000.txp 40: 1773 0 0 0 ARMCTRL-level 48 Edge DMA IRQ 42: 11 0 0 0 ARMCTRL-level 50 Edge DMA IRQ 44: 11 0 0 0 ARMCTRL-level 52 Edge DMA IRQ 45: 0 0 0 0 ARMCTRL-level 53 Edge DMA IRQ 66: 0 0 0 0 ARMCTRL-level 74 Edge vc4 crtc 69: 0 0 0 0 ARMCTRL-level 77 Edge vc4 crtc 70: 0 0 0 0 ARMCTRL-level 78 Edge vc4 crtc 77: 20 0 0 0 ARMCTRL-level 85 Edge 3f205000.i2c, 3f804000.i2c, 3f805000.i2c 78: 6417 0 0 0 ARMCTRL-level 86 Edge 3f204000.spi 80: 237 0 0 0 ARMCTRL-level 88 Edge mmc0 81: 489 0 0 0 ARMCTRL-level 89 Edge uart-pl011 89: 0 0 0 0 bcm2836-timer 0 Edge arch_timer 90: 4048 3704 2383 1892 bcm2836-timer 1 Edge arch_timer 94: 14287 0 0 0 pinctrl-bcm2835 16 Level mcp25xxfd IPI0: 0 0 0 0 CPU wakeup interrupts IPI1: 0 0 0 0 Timer broadcast interrupts IPI2: 2361 2948 7890 1616 Rescheduling interrupts IPI3: 65 617 301 166 Function call interrupts IPI4: 0 0 0 0 CPU stop interrupts IPI5: 1 0 0 0 IRQ work interrupts IPI6: 0 0 0 0 completion interrupts Err: 0 top shows 91% for the mcp25xxfd interrupt handler, 0% for spi0 So we see that spi0 is no longer getting scheduled wasting CPU cycles There are a lot less context switches and corresponding Rescheduling interrupts All of these show that this improves efficiency of the system and reduces CPU utilization. Signed-off-by: Martin Sperl <kernel@martin.sperl.org> Signed-off-by: Mark Brown <broonie@kernel.org>
Diffstat (limited to 'include/linux/spi')
-rw-r--r--include/linux/spi/spi.h2
1 files changed, 2 insertions, 0 deletions
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 916bba47d156..79ad62e2487c 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -334,6 +334,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
* @kworker: thread struct for message pump
* @kworker_task: pointer to task for message pump kworker thread
* @pump_messages: work struct for scheduling work to the message pump
+ * @pump_idle_teardown: work structure for scheduling a teardown delayed
* @queue_lock: spinlock to syncronise access to message queue
* @queue: message queue
* @idling: the device is entering idle state
@@ -532,6 +533,7 @@ struct spi_controller {
struct kthread_worker kworker;
struct task_struct *kworker_task;
struct kthread_work pump_messages;
+ struct kthread_delayed_work pump_idle_teardown;
spinlock_t queue_lock;
struct list_head queue;
struct spi_message *cur_msg;