Re: [PATCHv4] tty: hvc: dcc: Bind driver to CPU core0 for reads and writes
From: Sai Prakash Ranjan
Date: Fri Feb 11 2022 - 07:49:14 EST
On 2/10/2022 7:26 PM, Sai Prakash Ranjan wrote:
From: Shanker Donthineni <shankerd@xxxxxxxxxxxxxx>
Some debuggers, such as Trace32 from Lauterbach GmbH, do not handle
reads/writes from/to DCC on secondary cores. Each core has its
own DCC device registers, so when a core reads or writes from/to DCC,
it only accesses its own DCC device. Since kernel code can run on
any core, every time the kernel wants to write to the console, it
might write to a different DCC.
In SMP mode, Trace32 creates multiple windows, and each window shows
the DCC output only from that core's DCC. The result is that console
output is either lost or scattered across windows.
Selecting this option will enable code that serializes all console
input and output to core 0. The DCC driver will create input and
output FIFOs that all cores will use. Reads and writes from/to DCC
are handled by a workqueue that runs only core 0.
Signed-off-by: Shanker Donthineni <shankerd@xxxxxxxxxxxxxx>
Acked-by: Adam Wallis <awallis@xxxxxxxxxxxxxx>
Signed-off-by: Timur Tabi <timur@xxxxxxxxxxxxxx>
Signed-off-by: Elliot Berman <eberman@xxxxxxxxxxxxxx>
Signed-off-by: Sai Prakash Ranjan <quic_saipraka@xxxxxxxxxxx>
---
Changes in v4:
* Use module parameter for runtime choice of enabling this feature.
* Use hotplug locks to avoid race between cpu online check and work schedule.
* Remove ifdefs and move to common ops.
* Remove unnecessary check for this configuration.
* Use macros for buf size instead of magic numbers.
* v3 - https://lore.kernel.org/lkml/20211213141013.21464-1-quic_saipraka@xxxxxxxxxxx/
Changes in v3:
* Handle case where core0 is not online.
Changes in v2:
* Checkpatch warning fixes.
* Use of IS_ENABLED macros instead of ifdefs.
---
drivers/tty/hvc/hvc_dcc.c | 177 +++++++++++++++++++++++++++++++++++++-
1 file changed, 174 insertions(+), 3 deletions(-)
diff --git a/drivers/tty/hvc/hvc_dcc.c b/drivers/tty/hvc/hvc_dcc.c
index 8e0edb7d93fd..535b09441e55 100644
--- a/drivers/tty/hvc/hvc_dcc.c
+++ b/drivers/tty/hvc/hvc_dcc.c
@@ -2,19 +2,35 @@
/* Copyright (c) 2010, 2014 The Linux Foundation. All rights reserved. */
#include <linux/console.h>
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
#include <linux/init.h>
+#include <linux/kfifo.h>
+#include <linux/moduleparam.h>
#include <linux/serial.h>
#include <linux/serial_core.h>
+#include <linux/spinlock.h>
#include <asm/dcc.h>
#include <asm/processor.h>
#include "hvc_console.h"
+static bool serialize_smp;
+module_param(serialize_smp, bool, 0444);
+MODULE_PARM_DESC(serialize_smp, "Serialize all DCC console input and output to CPU core 0");
+
/* DCC Status Bits */
#define DCC_STATUS_RX (1 << 30)
#define DCC_STATUS_TX (1 << 29)
+#define DCC_INBUF_SIZE 128
+#define DCC_OUTBUF_SIZE 1024
+
+static DEFINE_SPINLOCK(dcc_lock);
+static DEFINE_KFIFO(inbuf, unsigned char, DCC_INBUF_SIZE);
+static DEFINE_KFIFO(outbuf, unsigned char, DCC_OUTBUF_SIZE);
+
static void dcc_uart_console_putchar(struct uart_port *port, int ch)
{
while (__dcc_getstatus() & DCC_STATUS_TX)
@@ -67,24 +83,179 @@ static int hvc_dcc_get_chars(uint32_t vt, char *buf, int count)
return i;
}
+/*
+ * Check if the DCC is enabled. If serialize_smp module param is enabled,
+ * then we assume then this function will be called first on core0. That way,
+ * dcc_core0_available will be true only if it's available on core0.
+ */
static bool hvc_dcc_check(void)
{
unsigned long time = jiffies + (HZ / 10);
+ static bool dcc_core0_available;
+
+ /*
+ * If we're not on core 0, but we previously confirmed that DCC is
+ * active, then just return true.
+ */
+ if (serialize_smp && smp_processor_id() && dcc_core0_available)
+ return true;
/* Write a test character to check if it is handled */
__dcc_putchar('\n');
while (time_is_after_jiffies(time)) {
- if (!(__dcc_getstatus() & DCC_STATUS_TX))
+ if (!(__dcc_getstatus() & DCC_STATUS_TX)) {
+ dcc_core0_available = true;
return true;
+ }
}
return false;
}
+/*
+ * Workqueue function that writes the output FIFO to the DCC on core 0.
+ */
+static void dcc_put_work(struct work_struct *work)
+{
+ unsigned char ch;
+ unsigned long irqflags;
+
+ spin_lock_irqsave(&dcc_lock, irqflags);
+
+ /* While there's data in the output FIFO, write it to the DCC */
+ while (kfifo_get(&outbuf, &ch))
+ hvc_dcc_put_chars(0, &ch, 1);
+
+ /* While we're at it, check for any input characters */
+ while (!kfifo_is_full(&inbuf)) {
+ if (!hvc_dcc_get_chars(0, &ch, 1))
+ break;
+ kfifo_put(&inbuf, ch);
+ }
+
+ spin_unlock_irqrestore(&dcc_lock, irqflags);
+}
+
+static DECLARE_WORK(dcc_pwork, dcc_put_work);
+
+/*
+ * Workqueue function that reads characters from DCC and puts them into the
+ * input FIFO.
+ */
+static void dcc_get_work(struct work_struct *work)
+{
+ unsigned char ch;
+ unsigned long irqflags;
+
+ /*
+ * Read characters from DCC and put them into the input FIFO, as
+ * long as there is room and we have characters to read.
+ */
+ spin_lock_irqsave(&dcc_lock, irqflags);
+
+ while (!kfifo_is_full(&inbuf)) {
+ if (!hvc_dcc_get_chars(0, &ch, 1))
+ break;
+ kfifo_put(&inbuf, ch);
+ }
+ spin_unlock_irqrestore(&dcc_lock, irqflags);
+}
+
+static DECLARE_WORK(dcc_gwork, dcc_get_work);
+
+/*
+ * Write characters directly to the DCC if we're on core 0 and the FIFO
+ * is empty, or write them to the FIFO if we're not.
+ */
+static int hvc_dcc0_put_chars(u32 vt, const char *buf, int count)
+{
+ int len;
+ unsigned long irqflags;
+
+ if (!serialize_smp)
+ return hvc_dcc_put_chars(vt, buf, count);
+
+ spin_lock_irqsave(&dcc_lock, irqflags);
+ if (smp_processor_id() || (!kfifo_is_empty(&outbuf))) {
+ len = kfifo_in(&outbuf, buf, count);
+ spin_unlock_irqrestore(&dcc_lock, irqflags);
+
+ /*
+ * We just push data to the output FIFO, so schedule the
+ * workqueue that will actually write that data to DCC.
+ * Also take a CPU hotplug lock to avoid CPU going down
+ * between the check and scheduling work on CPU0.
+ */
+ cpus_read_lock();
+
+ if (cpu_online(0))
+ schedule_work_on(0, &dcc_pwork);
+
+ cpus_read_unlock();
+
This is a bug, I ran with lock debug configs enabled and apparently this
runs in atomic context and
cpus_read_lock/unlock() can sleep. Will remove these locks in next version.
+ return len;
+ }
+
+ /*
+ * If we're already on core 0, and the FIFO is empty, then just
+ * write the data to DCC.
+ */
+ len = hvc_dcc_put_chars(vt, buf, count);
+ spin_unlock_irqrestore(&dcc_lock, irqflags);
+
+ return len;
+}
+
+/*
+ * Read characters directly from the DCC if we're on core 0 and the FIFO
+ * is empty, or read them from the FIFO if we're not.
+ */
+static int hvc_dcc0_get_chars(u32 vt, char *buf, int count)
+{
+ int len;
+ unsigned long irqflags;
+
+ if (!serialize_smp)
+ return hvc_dcc_get_chars(vt, buf, count);
+
+ spin_lock_irqsave(&dcc_lock, irqflags);
+
+ if (smp_processor_id() || (!kfifo_is_empty(&inbuf))) {
+ len = kfifo_out(&inbuf, buf, count);
+ spin_unlock_irqrestore(&dcc_lock, irqflags);
+
+ /*
+ * If the FIFO was empty, there may be characters in the DCC
+ * that we haven't read yet. Schedule a workqueue to fill
+ * the input FIFO, so that the next time this function is
+ * called, we'll have data. Take a CPU hotplug lock as well
+ * to avoid CPU going down between the cpu online check and
+ * scheduling work on CPU0.
+ */
+ cpus_read_lock();
+
+ if (!len && cpu_online(0))
+ schedule_work_on(0, &dcc_gwork);
+
+ cpus_read_unlock();
+
Same as above.
Thanks,
Sai
+ return len;
+ }
+
+ /*
+ * If we're already on core 0, and the FIFO is empty, then just
+ * read the data from DCC.
+ */
+ len = hvc_dcc_get_chars(vt, buf, count);
+ spin_unlock_irqrestore(&dcc_lock, irqflags);
+
+ return len;
+}
+
static const struct hv_ops hvc_dcc_get_put_ops = {
- .get_chars = hvc_dcc_get_chars,
- .put_chars = hvc_dcc_put_chars,
+ .get_chars = hvc_dcc0_get_chars,
+ .put_chars = hvc_dcc0_put_chars,
};
static int __init hvc_dcc_console_init(void)
base-commit: 395a61741f7ea29e1f4a0d6e160197fe8e377572