cxl: Mask slice error interrupts after first occurrence

In some situations, a faulty AFU slice may create an interrupt storm of
slice errors, rendering the machine unusable. Since these interrupts are
informational only, present the interrupt once, then mask it off to
prevent it from being retriggered until the AFU is reset.

Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
Reviewed-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Reviewed-by: Vaibhav Jain <vaibhav@linux.vnet.ibm.com>
Acked-by: Frederic Barrat <fbarrat@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

2 files changed, 35 insertions, 2 deletions

diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index 452e209c5e675..c8568ea7c5186 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -228,6 +228,24 @@ static const cxl_p2n_reg_t CXL_PSL_WED_An     = {0x0A0};
 #define CXL_PSL_SERR_An_llcmdto	(1ull << (63-6))
 #define CXL_PSL_SERR_An_afupar	(1ull << (63-7))
 #define CXL_PSL_SERR_An_afudup	(1ull << (63-8))
+#define CXL_PSL_SERR_An_IRQS	( \
+	CXL_PSL_SERR_An_afuto | CXL_PSL_SERR_An_afudis | CXL_PSL_SERR_An_afuov | \
+	CXL_PSL_SERR_An_badsrc | CXL_PSL_SERR_An_badctx | CXL_PSL_SERR_An_llcmdis | \
+	CXL_PSL_SERR_An_llcmdto | CXL_PSL_SERR_An_afupar | CXL_PSL_SERR_An_afudup)
+#define CXL_PSL_SERR_An_afuto_mask	(1ull << (63-32))
+#define CXL_PSL_SERR_An_afudis_mask	(1ull << (63-33))
+#define CXL_PSL_SERR_An_afuov_mask	(1ull << (63-34))
+#define CXL_PSL_SERR_An_badsrc_mask	(1ull << (63-35))
+#define CXL_PSL_SERR_An_badctx_mask	(1ull << (63-36))
+#define CXL_PSL_SERR_An_llcmdis_mask	(1ull << (63-37))
+#define CXL_PSL_SERR_An_llcmdto_mask	(1ull << (63-38))
+#define CXL_PSL_SERR_An_afupar_mask	(1ull << (63-39))
+#define CXL_PSL_SERR_An_afudup_mask	(1ull << (63-40))
+#define CXL_PSL_SERR_An_IRQ_MASKS	( \
+	CXL_PSL_SERR_An_afuto_mask | CXL_PSL_SERR_An_afudis_mask | CXL_PSL_SERR_An_afuov_mask | \
+	CXL_PSL_SERR_An_badsrc_mask | CXL_PSL_SERR_An_badctx_mask | CXL_PSL_SERR_An_llcmdis_mask | \
+	CXL_PSL_SERR_An_llcmdto_mask | CXL_PSL_SERR_An_afupar_mask | CXL_PSL_SERR_An_afudup_mask)
+
 #define CXL_PSL_SERR_An_AE	(1ull << (63-30))
 
 /****** CXL_PSL_SCNTL_An ****************************************************/
diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c
index 194c58ec83b82..871a2f09c7184 100644
--- a/drivers/misc/cxl/native.c
+++ b/drivers/misc/cxl/native.c
@@ -95,12 +95,23 @@ int cxl_afu_disable(struct cxl_afu *afu)
 /* This will disable as well as reset */
 static int native_afu_reset(struct cxl_afu *afu)
 {
+	int rc;
+	u64 serr;
+
 	pr_devel("AFU reset request\n");
 
-	return afu_control(afu, CXL_AFU_Cntl_An_RA, 0,
+	rc = afu_control(afu, CXL_AFU_Cntl_An_RA, 0,
 			   CXL_AFU_Cntl_An_RS_Complete | CXL_AFU_Cntl_An_ES_Disabled,
 			   CXL_AFU_Cntl_An_RS_MASK | CXL_AFU_Cntl_An_ES_MASK,
 			   false);
+
+	/* Re-enable any masked interrupts */
+	serr = cxl_p1n_read(afu, CXL_PSL_SERR_An);
+	serr &= ~CXL_PSL_SERR_An_IRQ_MASKS;
+	cxl_p1n_write(afu, CXL_PSL_SERR_An, serr);
+
+
+	return rc;
 }
 
 static int native_afu_check_and_enable(struct cxl_afu *afu)
@@ -1205,7 +1216,7 @@ static irqreturn_t native_slice_irq_err(int irq, void *data)
 {
 	struct cxl_afu *afu = data;
 	u64 errstat, serr, afu_error, dsisr;
-	u64 fir_slice, afu_debug;
+	u64 fir_slice, afu_debug, irq_mask;
 
 	/*
 	 * slice err interrupt is only used with full PSL (no XSL)
@@ -1226,7 +1237,11 @@ static irqreturn_t native_slice_irq_err(int irq, void *data)
 	dev_crit(&afu->dev, "AFU_ERR_An: 0x%.16llx\n", afu_error);
 	dev_crit(&afu->dev, "PSL_DSISR_An: 0x%.16llx\n", dsisr);
 
+	/* mask off the IRQ so it won't retrigger until the AFU is reset */
+	irq_mask = (serr & CXL_PSL_SERR_An_IRQS) >> 32;
+	serr |= irq_mask;
 	cxl_p1n_write(afu, CXL_PSL_SERR_An, serr);
+	dev_info(&afu->dev, "Further such interrupts will be masked until the AFU is reset\n");
 
 	return IRQ_HANDLED;
 }