Detect and mitigate uncontrolled ACPI GPE interrupt storms on OpenBSD (7.3, 7.3-current)

acpi.diff

diff --git sys/dev/acpi/acpi.c sys/dev/acpi/acpi.c
index 853bad1ab..26a5c1702 100644
--- sys/dev/acpi/acpi.c
+++ sys/dev/acpi/acpi.c
@@ -52,6 +52,9 @@
 #define APMDEV_NORMAL	0
 #define APMDEV_CTL	8
 
+#define GPE_RATE_MIN_CYCLE	5		/* seconds    */
+#define GPE_RATE_MAX		1000	/* per second */
+
 #include "wd.h"
 
 #ifdef ACPI_DEBUG
@@ -98,6 +101,8 @@ void	acpi_disable_allgpes(struct acpi_softc *);
 struct gpe_block *acpi_find_gpe(struct acpi_softc *, int);
 void	acpi_enable_onegpe(struct acpi_softc *, int);
 int	acpi_gpe(struct acpi_softc *, int, void *);
+void	acpi_init_gpe_rate(struct acpi_softc *, int);
+int	acpi_gpe_rate(struct acpi_softc *, int);
 
 void	acpi_enable_rungpes(struct acpi_softc *);
 
@@ -2229,6 +2234,7 @@ acpi_enable_onegpe(struct acpi_softc *sc, int gpe)
 	dnprintf(50, "enabling GPE %.2x (current: %sabled) %.2x\n",
 	    gpe, (en & mask) ? "en" : "dis", en);
 	acpi_write_pmreg(sc, ACPIREG_GPE_EN, gpe>>3, en | mask);
+	acpi_init_gpe_rate(sc, gpe);
 }
 
 /* Clear all GPEs */
@@ -2307,7 +2313,40 @@ acpi_gpe(struct acpi_softc *sc, int gpe, void *arg)
 	if (sc->gpe_table[gpe].flags & GPE_LEVEL)
 		acpi_write_pmreg(sc, ACPIREG_GPE_STS, gpe>>3, mask);
 	en = acpi_read_pmreg(sc, ACPIREG_GPE_EN,  gpe>>3);
-	acpi_write_pmreg(sc, ACPIREG_GPE_EN,  gpe>>3, en | mask);
+	/* Re-enable if GPE rate passes, otherwise leave disabled */
+	if (!acpi_gpe_rate(sc, gpe))
+		acpi_write_pmreg(sc, ACPIREG_GPE_EN,  gpe>>3, en | mask);
+	return (0);
+}
+
+void
+acpi_init_gpe_rate(struct acpi_softc *sc, int gpe)
+{
+	sc->gpe_table[gpe].rate_start = getuptime();
+	sc->gpe_table[gpe].rate_count = 0;
+}
+
+int
+acpi_gpe_rate(struct acpi_softc *sc, int gpe)
+{
+	struct gpe_block *pgpe = &sc->gpe_table[gpe];
+	time_t cycle;
+
+	pgpe->rate_count++;
+	dnprintf(10, "rate GPE %.2x start %lld elapsed %lld count %zu\n", gpe,
+	    pgpe->rate_start, getuptime() - pgpe->rate_start, pgpe->rate_count);
+
+	cycle = getuptime() - pgpe->rate_start;
+	if (cycle >= GPE_RATE_MIN_CYCLE) {
+		if (pgpe->rate_count > (GPE_RATE_MAX * cycle)) {
+			printf("uncontrolled GPE storm %lld/s, disabling GPE %.2x\n",
+			    pgpe->rate_count / cycle, gpe);
+			return (1);
+		}
+
+		/* Reset and start a new cycle */
+		acpi_init_gpe_rate(sc, gpe);
+	}
 	return (0);
 }
 
diff --git sys/dev/acpi/acpivar.h sys/dev/acpi/acpivar.h
index a9b4a2ae9..4e2f47053 100644
--- sys/dev/acpi/acpivar.h
+++ sys/dev/acpi/acpivar.h
@@ -185,6 +185,9 @@ struct gpe_block {
 	void *arg;
 	int   active;
 	int   flags;
+
+	time_t rate_start;
+	size_t rate_count;
 };
 
 struct acpi_devlist {

An uncontrolled GPE storm will be logged as such:

Feb 21 02:06:03 acpitest2 /bsd: uncontrolled GPE storm 7106/s, disabling GPE 6f

@bconway I tried this out on 7.2-stable branch and it is working well. thank you

Verified on OpenBSD 7.3.

Applied and tested on 7.4 -stable, it work great thanks.

Thanks! I'm no longer using this diff, as the one system I had afflicted was a cured with an (unofficial) BIOS update, but I will come back to it in the future if the occasion arises.

Works on 7.5-stable. On my (similar?) fanless system, idle CPU temp dropped by 6C by about 15 minutes after rebooting into the modified kernel.

looks like this is still working on obsd 7.6

This is confirmed still working, and useful on 7.7-snapshot.

bios0: vendor Techvision, LLC. version "5.19" date 11/08/2022
bios0: Techvision TVI7309X
efi0 at bios0: UEFI 2.7
efi0: American Megatrends rev 0x50013
acpi0 at bios0: ACPI 6.2
[...]
cpu0: Intel(R) Celeron(R) N5100 @ 1.10GHz, 2793.96 MHz, 06-9c-00, patch 24000026

The acpi0 interrupt rate was ~7kps before patching (with a bit of fuzz).
Thanks.