bte_error.c:

bte.c:
  After working with the chip designer some more, we have determined one
  more hardware register we were supposed to write to ensure the SHUB
  chip was ready for future transfers.  This patch fixes that.  This also
  allowed us to eliminate a udelay which was working around the problem.

  During retesting, we uncovered a race condition where transfer status
  was changed by a different cpu after we were expecting one value which
  cascaded to additional problems.  This patch uses a local variable to
  also eliminate that race.
Signed-off-by: Robin Holt <holt@sgi.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>

arch/ia64/sn/io/sn2/bte_error.c

@@ -90,6 +90,7 @@ bte_error_handler(unsigned long _nodepda)
 	ii_icrb0_d_u_t icrbd;	/* II CRB Register D */
 	ii_ibcr_u_t ibcr;
 	ii_icmr_u_t icmr;
+	ii_ieclr_u_t ieclr;
 
 
 	BTE_PRINTK(("bte_error_handler(%p) - %d\n", err_nodepda,
@@ -177,6 +178,14 @@ bte_error_handler(unsigned long _nodepda)
 	imem.ii_imem_fld_s.i_b0_esd = imem.ii_imem_fld_s.i_b1_esd = 1;
 	REMOTE_HUB_S(nasid, IIO_IMEM, imem.ii_imem_regval);
 
+	/* Clear IBLS0/1 error bits */
+	ieclr.ii_ieclr_regval = 0;
+	if (err_nodepda->bte_if[0].bh_error != BTE_SUCCESS)
+		ieclr.ii_ieclr_fld_s.i_e_bte_0 = 1;
+	if (err_nodepda->bte_if[1].bh_error != BTE_SUCCESS)
+                ieclr.ii_ieclr_fld_s.i_e_bte_1 = 1;
+	REMOTE_HUB_S(nasid, IIO_IECLR, ieclr.ii_ieclr_regval);
+
 	/* Reinitialize both BTE state machines. */
 	ibcr.ii_ibcr_regval = REMOTE_HUB_L(nasid, IIO_IBCR);
 	ibcr.ii_ibcr_fld_s.i_soft_reset = 1;

arch/ia64/sn/kernel/bte.c

@@ -16,7 +16,6 @@
 #include <asm/sn/pda.h>
 #include <asm/sn/sn2/shubio.h>
 #include <asm/nodedata.h>
-#include <asm/delay.h>
 
 #include <linux/bootmem.h>
 #include <linux/string.h>
@@ -71,6 +70,7 @@ bte_result_t
 bte_copy(u64 src, u64 dest, u64 len, u64 mode, void *notification)
 {
 	u64 transfer_size;
+	u64 transfer_stat;
 	struct bteinfo_s *bte;
 	bte_result_t bte_status;
 	unsigned long irq_flags;
@@ -148,9 +148,6 @@ bte_copy(u64 src, u64 dest, u64 len, u64 mode, void *notification)
 		if (!(mode & BTE_WACQUIRE)) {
 			return BTEFAIL_NOTAVAIL;
 		}
-
-		/* Wait until a bte is available. */
-		udelay(1);
 	} while (1);
 
 
@@ -194,15 +191,15 @@ bte_copy(u64 src, u64 dest, u64 len, u64 mode, void *notification)
 		return BTE_SUCCESS;
 	}
 
-	while (*bte->most_rcnt_na == -1UL) {
+	while ((transfer_stat = *bte->most_rcnt_na) == -1UL) {
 	}
 
 
 	BTE_PRINTKV((" Delay Done.  IBLS = 0x%lx, most_rcnt_na = 0x%lx\n",
 				BTE_LNSTAT_LOAD(bte), *bte->most_rcnt_na));
 
-	if (*bte->most_rcnt_na & IBLS_ERROR) {
-		bte_status = *bte->most_rcnt_na & ~IBLS_ERROR;
+	if (transfer_stat & IBLS_ERROR) {
+		bte_status = transfer_stat & ~IBLS_ERROR;
 		*bte->most_rcnt_na = 0L;
 	} else {
 		bte_status = BTE_SUCCESS;