commit ea6fa4961aab8f90a8aa03575a98b4bda368d4b6 upstream.
Please apply to 5.15 and 5.16 trees.
To prevent an infinite loop in mc146818_get_time(),
commit 211e5db19d15 ("rtc: mc146818: Detect and handle broken RTCs")
added a check for RTC availability. Together with a later fix, it
checked if bit 6 in register 0x0d is cleared.
This, however, caused a false negative on a motherboard with an AMD
SB710 southbridge; according to the specification [1], bit 6 of register
0x0d of this chipset is a scratchbit. This caused a regression in Linux
5.11 - the RTC was determined broken by the kernel and not used by
rtc-cmos.c [3]. This problem was also reported in Fedora [4].
As a better alternative, check whether the UIP ("Update-in-progress")
bit is set for longer then 10ms. If that is the case, then apparently
the RTC is either absent (and all register reads return 0xff) or broken.
Also limit the number of loop iterations in mc146818_get_time() to 10 to
prevent an infinite loop there.
An equivalent patch has been in mainline since 5.17-rc1 and I have
received no complaints (the patch was refactored by following patches in
my mainline series, but the algorithm remained). Also, Google searches
for appropriate error messages are giving no problem reports.
Additionally, a more strigent test introduced by
commit 2aaa36e95ea5 ("selftests/rtc: continuously read RTC in a loop for 30s")
was added in merge window for kernel 5.18 and I have received no
reports it was failing.
Changes from the upstream commit:
- return values from mc146818_get_time() are different then in mainline,
so return a different value in case there is an error.
- print a warning in mc146818_get_time() if the RTC read fails.
In the mainline patch series this was done by callers of
mc146818_get_time(), for simplicity do this in mc146818_get_time() here.
[1] AMD SB700/710/750 Register Reference Guide, page 308,
https://developer.amd.com/wordpress/media/2012/10/43009_sb7xx_rrg_pub_1.00.pdf
[2] 7th Generation Intel ® Processor Family I/O for U/Y Platforms [...] Datasheet
Volume 1 of 2, page 209
Intel's Document Number: 334658-006,
https://www.intel.com/content/dam/www/public/us/en/documents/datasheets/7th-and-8th-gen-core-family-mobile-u-y-processor-lines-i-o-datasheet-vol-1.pdf
[3] Functions in arch/x86/kernel/rtc.c apparently were using it.
[4] https://bugzilla.redhat.com/show_bug.cgi?id=1936688
Fixes: 211e5db19d15 ("rtc: mc146818: Detect and handle broken RTCs")
Fixes: ebb22a059436 ("rtc: mc146818: Dont test for bit 0-5 in Register D")
Signed-off-by: Mateusz Jończyk <mat.jonczyk@xxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Alessandro Zummo <a.zummo@xxxxxxxxxxxx>
Cc: Alexandre Belloni <alexandre.belloni@xxxxxxxxxxx>
Link: https://lore.kernel.org/r/20211210200131.153887-5-mat.jonczyk@xxxxx
---
Tested on 3 computers and 2 different VMs (amd64 and i386), both on
kernel 5.15 and 5.16 stable releases. Then changed pr_err() to
pr_err_ratelimited(), but did not retest so carefully.
drivers/rtc/rtc-cmos.c | 10 ++++------
drivers/rtc/rtc-mc146818-lib.c | 35 ++++++++++++++++++++++++++++++----
include/linux/mc146818rtc.h | 1 +
3 files changed, 36 insertions(+), 10 deletions(-)
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index dc3f8b0dde98..9404f58ee01d 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -793,16 +793,14 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq)
rename_region(ports, dev_name(&cmos_rtc.rtc->dev));
- spin_lock_irq(&rtc_lock);
-
- /* Ensure that the RTC is accessible. Bit 6 must be 0! */
- if ((CMOS_READ(RTC_VALID) & 0x40) != 0) {
- spin_unlock_irq(&rtc_lock);
- dev_warn(dev, "not accessible\n");
+ if (!mc146818_does_rtc_work()) {
+ dev_warn(dev, "broken or not accessible\n");
retval = -ENXIO;
goto cleanup1;
}
+ spin_lock_irq(&rtc_lock);
+
if (!(flags & CMOS_RTC_FLAGS_NOFREQ)) {
/* force periodic irq to CMOS reset default of 1024Hz;
*
diff --git a/drivers/rtc/rtc-mc146818-lib.c b/drivers/rtc/rtc-mc146818-lib.c
index 04b05e3b68cb..f58b0d9dacca 100644
--- a/drivers/rtc/rtc-mc146818-lib.c
+++ b/drivers/rtc/rtc-mc146818-lib.c
@@ -8,10 +8,36 @@
#include <linux/acpi.h>
#endif
+/*
+ * If the UIP (Update-in-progress) bit of the RTC is set for more then
+ * 10ms, the RTC is apparently broken or not present.
+ */
+bool mc146818_does_rtc_work(void)
+{
+ int i;
+ unsigned char val;
+ unsigned long flags;
+
+ for (i = 0; i < 10; i++) {
+ spin_lock_irqsave(&rtc_lock, flags);
+ val = CMOS_READ(RTC_FREQ_SELECT);
+ spin_unlock_irqrestore(&rtc_lock, flags);
+
+ if ((val & RTC_UIP) == 0)
+ return true;
+
+ mdelay(1);
+ }
+
+ return false;
+}
+EXPORT_SYMBOL_GPL(mc146818_does_rtc_work);
+
unsigned int mc146818_get_time(struct rtc_time *time)
{
unsigned char ctrl;
unsigned long flags;
+ unsigned int iter_count = 0;
unsigned char century = 0;
bool retry;
@@ -20,13 +46,14 @@ unsigned int mc146818_get_time(struct rtc_time *time)
#endif
again:
- spin_lock_irqsave(&rtc_lock, flags);
- /* Ensure that the RTC is accessible. Bit 6 must be 0! */
- if (WARN_ON_ONCE((CMOS_READ(RTC_VALID) & 0x40) != 0)) {
- spin_unlock_irqrestore(&rtc_lock, flags);
+ if (iter_count > 10) {
+ pr_err_ratelimited("Unable to read current time from RTC\n");
memset(time, 0xff, sizeof(*time));
return 0;
}
+ iter_count++;
+
+ spin_lock_irqsave(&rtc_lock, flags);
/*
* Check whether there is an update in progress during which the
diff --git a/include/linux/mc146818rtc.h b/include/linux/mc146818rtc.h
index 0661af17a758..69c80c4325bf 100644
--- a/include/linux/mc146818rtc.h
+++ b/include/linux/mc146818rtc.h
@@ -123,6 +123,7 @@ struct cmos_rtc_board_info {
#define RTC_IO_EXTENT_USED RTC_IO_EXTENT
#endif /* ARCH_RTC_LOCATION */
+bool mc146818_does_rtc_work(void);
unsigned int mc146818_get_time(struct rtc_time *time);
int mc146818_set_time(struct rtc_time *time);
base-commit: 06f50ca83ace219cb72213369d2be05bb0dd337e
--
2.25.1
