Thread (6 messages) 6 messages, 1 author, 3d ago

[PATCH v5 3/5] powerpc/pseries/eeh: Implement RTAS-based EEH error injection

flat view
WARM3d SUPERSEDED

From: Narayana Murty N <hidden>
Date: 2026-10-19 10:19:20
Also in: kvm, lkml
Subsystem: linux for powerpc (32-bit and 64-bit), pci enhanced error handling (eeh) for powerpc, the rest · Maintainers: Madhavan Srinivasan, Mahesh J Salgaonkar, Linus Torvalds

Revision v5 of 2 in this series.

Revisions (2)
  1. v5 current
  2. v6 [diff vs current]
Replace the legacy MMIO stub in pseries_eeh_err_inject() with a full
PAPR-compliant RTAS error injection path.

Serialize each ibm,open-errinjct / ibm,errinjct / ibm,close-errinjct
session with errinjct_mutex because RTAS maintains state between these
calls.

Once ibm,open-errinjct succeeds, ibm,close-errinjct is attempted
after parameter preparation or ibm,errinjct failures.  The RTAS work
area is allocated after a successful open to avoid holding it while
waiting for the mutex or if open fails.

VFIO EEH error injection exposes a generic userspace ABI.  pSeries maps
the generic EEH error types to RTAS ibm,errinjct encodings via
pseries_eeh_type_to_rtas().  EEH_ERR_TYPE_32 and EEH_ERR_TYPE_64 are
unchanged; their values are defined in arch/powerpc/include/uapi/asm/eeh.h
and are not renumbered.

The RTAS work-area allocator guarantees that returned memory is within
the range accessible by RTAS (below min(ppc64_rma_size,
RTAS_INSTANTIATE_MAX), which is at most RTAS_INSTANTIATE_MAX = 1 GiB),
so the physical address fits in the 32-bit RTAS argument without
truncation.

Remove the now-unused eeh_pe_inject_mmio_error() helper and its
declaration; this patch removes its only caller.

Tested with corresponding QEMU patches:
https://lore.kernel.org/all/20251029150618.186803-1-nnmlinux@linux.ibm.com/ (local)

Signed-off-by: Narayana Murty N <redacted>
---
 arch/powerpc/include/asm/eeh.h               |   2 -
 arch/powerpc/kernel/eeh.c                    |   5 -
 arch/powerpc/platforms/pseries/eeh_pseries.c | 114 +++++++++++++++----
 3 files changed, 91 insertions(+), 30 deletions(-)
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index b7ebb4ac2c71..083ac58e7eb7 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -310,8 +310,6 @@ int eeh_pe_reset(struct eeh_pe *pe, int option, bool include_passed);
 int eeh_pe_configure(struct eeh_pe *pe);
 int eeh_pe_inject_err(struct eeh_pe *pe, int type, int func,
 		      unsigned long addr, unsigned long mask);
-int eeh_pe_inject_mmio_error(struct pci_dev *pdev);
-
 /**
  * EEH_POSSIBLE_ERROR() -- test for possible MMIO failure.
  *
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index bb836f02101c..369aad298f75 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -1664,11 +1664,6 @@ static int eeh_break_device(struct pci_dev *pdev)
 	return 0;
 }
 
-int eeh_pe_inject_mmio_error(struct pci_dev *pdev)
-{
-	return eeh_break_device(pdev);
-}
-
 #ifdef CONFIG_DEBUG_FS
 
 
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index 999b3065e09b..52d001042663 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -24,6 +24,7 @@
 #include <linux/proc_fs.h>
 #include <linux/rbtree.h>
 #include <linux/sched.h>
+#include <linux/mutex.h>
 #include <linux/seq_file.h>
 #include <linux/sizes.h>
 #include <linux/spinlock.h>
@@ -35,6 +36,7 @@
 #include <asm/machdep.h>
 #include <asm/ppc-pci.h>
 #include <asm/rtas.h>
+#include <asm/rtas-work-area.h>
 
 /* RTAS tokens */
 static int ibm_set_eeh_option;
@@ -1006,41 +1008,107 @@ static int prepare_errinjct_buffer(void *buf, struct eeh_pe *pe,
 	return 0;
 }
 
+/* Serializes the open/inject/close RTAS error injection session */
+static DEFINE_MUTEX(errinjct_mutex);
+
 /**
  * pseries_eeh_err_inject - Inject specified error to the indicated PE
  * @pe: the indicated PE
- * @type: error type
- * @func: specific error type
- * @addr: address
- * @mask: address mask
- * The routine is called to inject specified error, which is
- * determined by @type and @func, to the indicated PE
+ * @type: generic EEH error type (EEH_ERR_TYPE_32 or EEH_ERR_TYPE_64)
+ * @func: specific error function
+ * @addr: address argument (type-dependent, may be zero)
+ * @mask: address mask (type-dependent, may be zero)
+ *
+ * Implements PAPR-compliant error injection using:
+ *   ibm,open-errinjct -> ibm,errinjct -> ibm,close-errinjct
+ *
+ * errinjct_mutex serializes the open/inject/close session sequence
+ * because RTAS maintains state between these calls.  A short-lived
+ * RTAS work area is allocated after a successful open and freed before
+ * close.
+ *
+ * Return: 0 on success, negative errno on failure.
  */
 static int pseries_eeh_err_inject(struct eeh_pe *pe, int type, int func,
 				  unsigned long addr, unsigned long mask)
 {
-	struct	eeh_dev	*pdev;
+	struct rtas_work_area *area;
+	phys_addr_t area_phys;
+	void *buf;
+	int open_token, errinjct_token, close_token;
+	int session_token;
+	int rtas_err_type;
+	int close_rc;
+	int rc;
+
+	rc = validate_errinjct_args(pe, type, func, addr, mask);
+	if (rc)
+		return rc;
 
-	/* Check on PCI error type */
-	if (type != EEH_ERR_TYPE_32 && type != EEH_ERR_TYPE_64)
+	rtas_err_type = pseries_eeh_type_to_rtas(type);
+	if (rtas_err_type < 0)
 		return -EINVAL;
 
-	switch (func) {
-	case EEH_ERR_FUNC_LD_MEM_ADDR:
-	case EEH_ERR_FUNC_LD_MEM_DATA:
-	case EEH_ERR_FUNC_ST_MEM_ADDR:
-	case EEH_ERR_FUNC_ST_MEM_DATA:
-		/* injects a MMIO error for all pdev's belonging to PE */
-		pci_lock_rescan_remove();
-		list_for_each_entry(pdev, &pe->edevs, entry)
-			eeh_pe_inject_mmio_error(pdev->pdev);
-		pci_unlock_rescan_remove();
-		break;
-	default:
-		return -ERANGE;
+	open_token = rtas_function_token(RTAS_FN_IBM_OPEN_ERRINJCT);
+	errinjct_token = rtas_function_token(RTAS_FN_IBM_ERRINJCT);
+	close_token = rtas_function_token(RTAS_FN_IBM_CLOSE_ERRINJCT);
+
+	if (open_token == RTAS_UNKNOWN_SERVICE ||
+	    errinjct_token == RTAS_UNKNOWN_SERVICE ||
+	    close_token == RTAS_UNKNOWN_SERVICE)
+		return -ENODEV;
+
+	mutex_lock(&errinjct_mutex);
+
+	do {
+		rc = rtas_call(open_token, 0, 2, &session_token);
+	} while (rtas_busy_delay(rc));
+
+	if (rc) {
+		pr_err("ibm,open-errinjct failed: status=%d\n", rc);
+		rc = rtas_error_rc(rc);
+		goto out_unlock;
 	}
 
-	return 0;
+	area = rtas_work_area_alloc(RTAS_ERRINJCT_BUF_SIZE);
+	buf = rtas_work_area_raw_buf(area);
+	area_phys = rtas_work_area_phys(area);
+
+	rc = prepare_errinjct_buffer(buf, pe, rtas_err_type, func, addr, mask);
+	if (rc)
+		goto out_free_area;
+
+	/*
+	 * RTAS work areas are allocated below RTAS_INSTANTIATE_MAX, so
+	 * area_phys fits in the 32-bit RTAS argument.
+	 */
+	do {
+		rc = rtas_call(errinjct_token, 3, 1, NULL,
+			       rtas_err_type, session_token,
+			       (u32)area_phys);
+	} while (rtas_busy_delay(rc));
+
+	if (rc) {
+		pr_err("ibm,errinjct failed: status=%d\n", rc);
+		rc = rtas_error_rc(rc);
+	}
+
+out_free_area:
+	rtas_work_area_free(area);
+
+	do {
+		close_rc = rtas_call(close_token, 1, 1, NULL, session_token);
+	} while (rtas_busy_delay(close_rc));
+
+	if (close_rc) {
+		pr_warn("ibm,close-errinjct failed: status=%d\n", close_rc);
+		if (!rc)
+			rc = rtas_error_rc(close_rc);
+	}
+
+out_unlock:
+	mutex_unlock(&errinjct_mutex);
+	return rc;
 }
 
 static struct eeh_ops pseries_eeh_ops = {
-- 
2.54.0

Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help