diff mbox series

[net] octeontx2-af: Unlock contexts in the queue context cache in case of fault detection

Message ID 20230222065921.1852686-1-saikrishnag@marvell.com (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series [net] octeontx2-af: Unlock contexts in the queue context cache in case of fault detection | expand

Checks

Context Check Description
netdev/tree_selection success Clearly marked for net
netdev/apply fail Patch does not apply to net

Commit Message

Sai Krishna Gajula Feb. 22, 2023, 6:59 a.m. UTC
From: Suman Ghosh <sumang@marvell.com>

NDC caches contexts of frequently used queue's (Rx and Tx queues)
contexts. Due to a HW errata when NDC detects fault/poision while
accessing contexts it could go into an illegal state where a cache
line could get locked forever. To makesure all cache lines in NDC
are available for optimum performance upon fault/lockerror/posion
errors scan through all cache lines in NDC and clear the lock bit.

Fixes: 4a3581cd5995 ("octeontx2-af: NPA AQ instruction enqueue support")
Signed-off-by: Suman Ghosh <sumang@marvell.com>
Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Signed-off-by: Sai Krishna <saikrishnag@marvell.com>
---
 .../net/ethernet/marvell/octeontx2/af/rvu.h   |  8 +++
 .../marvell/octeontx2/af/rvu_debugfs.c        |  3 -
 .../ethernet/marvell/octeontx2/af/rvu_nix.c   | 16 +++++-
 .../ethernet/marvell/octeontx2/af/rvu_npa.c   | 55 ++++++++++++++++++-
 .../ethernet/marvell/octeontx2/af/rvu_reg.h   |  3 +
 5 files changed, 80 insertions(+), 5 deletions(-)

Comments

Paolo Abeni Feb. 23, 2023, 9:52 a.m. UTC | #1
On Wed, 2023-02-22 at 12:29 +0530, Sai Krishna wrote:
> From: Suman Ghosh <sumang@marvell.com>
> 
> NDC caches contexts of frequently used queue's (Rx and Tx queues)
> contexts. Due to a HW errata when NDC detects fault/poision while
> accessing contexts it could go into an illegal state where a cache
> line could get locked forever. To makesure all cache lines in NDC
> are available for optimum performance upon fault/lockerror/posion
> errors scan through all cache lines in NDC and clear the lock bit.
> 
> Fixes: 4a3581cd5995 ("octeontx2-af: NPA AQ instruction enqueue support")
> Signed-off-by: Suman Ghosh <sumang@marvell.com>
> Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
> Signed-off-by: Sai Krishna <saikrishnag@marvell.com>

After the net-next merge, this does not apply cleanly to net anymore.

Please rebase and re-post, thanks!

Paolo
diff mbox series

Patch

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 7f0a64731c67..7de817446fc3 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -866,6 +866,12 @@  int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int lf,
 			int slot);
 int rvu_cpt_ctx_flush(struct rvu *rvu, u16 pcifunc);
 
+/* NDC APIs */
+#define NDC_MAX_BANK(rvu, blk_addr) (rvu_read64(rvu, \
+					blk_addr, NDC_AF_CONST) & 0xFF)
+#define NDC_MAX_LINE_PER_BANK(rvu, blk_addr) ((rvu_read64(rvu, \
+					blk_addr, NDC_AF_CONST) & 0xFFFF0000) >> 16)
+
 /* CN10K RVU */
 int rvu_set_channels_base(struct rvu *rvu);
 void rvu_program_channels(struct rvu *rvu);
@@ -881,6 +887,8 @@  static inline void rvu_dbg_init(struct rvu *rvu) {}
 static inline void rvu_dbg_exit(struct rvu *rvu) {}
 #endif
 
+int rvu_ndc_fix_locked_cacheline(struct rvu *rvu, int blkaddr);
+
 /* RVU Switch */
 void rvu_switch_enable(struct rvu *rvu);
 void rvu_switch_disable(struct rvu *rvu);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index fa280ebd3052..fad83d1f84b0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -198,9 +198,6 @@  enum cpt_eng_type {
 	CPT_IE_TYPE = 3,
 };
 
-#define NDC_MAX_BANK(rvu, blk_addr) (rvu_read64(rvu, \
-						blk_addr, NDC_AF_CONST) & 0xFF)
-
 #define rvu_dbg_NULL NULL
 #define rvu_dbg_open_NULL NULL
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 6b8747ebc08c..bcce42cd1c24 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -790,6 +790,7 @@  static int nix_aq_enqueue_wait(struct rvu *rvu, struct rvu_block *block,
 	struct nix_aq_res_s *result;
 	int timeout = 1000;
 	u64 reg, head;
+	int ret;
 
 	result = (struct nix_aq_res_s *)aq->res->base;
 
@@ -813,9 +814,22 @@  static int nix_aq_enqueue_wait(struct rvu *rvu, struct rvu_block *block,
 			return -EBUSY;
 	}
 
-	if (result->compcode != NIX_AQ_COMP_GOOD)
+	if (result->compcode != NIX_AQ_COMP_GOOD) {
 		/* TODO: Replace this with some error code */
+		if (result->compcode == NIX_AQ_COMP_CTX_FAULT ||
+		    result->compcode == NIX_AQ_COMP_LOCKERR ||
+		    result->compcode == NIX_AQ_COMP_CTX_POISON) {
+			ret = rvu_ndc_fix_locked_cacheline(rvu, BLKADDR_NDC_NIX0_RX);
+			ret |= rvu_ndc_fix_locked_cacheline(rvu, BLKADDR_NDC_NIX0_TX);
+			ret |= rvu_ndc_fix_locked_cacheline(rvu, BLKADDR_NDC_NIX1_RX);
+			ret |= rvu_ndc_fix_locked_cacheline(rvu, BLKADDR_NDC_NIX1_TX);
+			if (ret)
+				dev_err(rvu->dev,
+					"%s: Not able to unlock cachelines\n", __func__);
+		}
+
 		return -EBUSY;
+	}
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
index 70bd036ed76e..6cd8cc8f3488 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
@@ -42,9 +42,18 @@  static int npa_aq_enqueue_wait(struct rvu *rvu, struct rvu_block *block,
 			return -EBUSY;
 	}
 
-	if (result->compcode != NPA_AQ_COMP_GOOD)
+	if (result->compcode != NPA_AQ_COMP_GOOD) {
 		/* TODO: Replace this with some error code */
+		if (result->compcode == NPA_AQ_COMP_CTX_FAULT ||
+		    result->compcode == NPA_AQ_COMP_LOCKERR ||
+		    result->compcode == NPA_AQ_COMP_CTX_POISON) {
+			if (rvu_ndc_fix_locked_cacheline(rvu, BLKADDR_NDC_NPA0))
+				dev_err(rvu->dev,
+					"%s: Not able to unlock cachelines\n", __func__);
+		}
+
 		return -EBUSY;
+	}
 
 	return 0;
 }
@@ -545,3 +554,47 @@  void rvu_npa_lf_teardown(struct rvu *rvu, u16 pcifunc, int npalf)
 
 	npa_ctx_free(rvu, pfvf);
 }
+
+/* Due to an Hardware errata, in some corner cases, AQ context lock
+ * operations can result in a NDC way getting into an illegal state
+ * of not valid but locked.
+ *
+ * This API solves the problem by clearing the lock bit of the NDC block.
+ * The operation needs to be done for each line of all the NDC banks.
+ */
+int rvu_ndc_fix_locked_cacheline(struct rvu *rvu, int blkaddr)
+{
+	int bank, max_bank, line, max_line, err;
+	u64 reg;
+
+	/* Set the ENABLE bit(63) to '0' */
+	reg = rvu_read64(rvu, blkaddr, NDC_AF_CAMS_RD_INTERVAL);
+	rvu_write64(rvu, blkaddr, NDC_AF_CAMS_RD_INTERVAL, reg & GENMASK_ULL(62, 0));
+
+	/* Poll until the BUSY bits(47:32) are set to '0' */
+	err = rvu_poll_reg(rvu, blkaddr, NDC_AF_CAMS_RD_INTERVAL, GENMASK_ULL(47, 32), true);
+	if (err) {
+		dev_err(rvu->dev, "Timed out while polling for NDC CAM busy bits.\n");
+		return err;
+	}
+
+	max_bank = NDC_MAX_BANK(rvu, blkaddr);
+	max_line = NDC_MAX_LINE_PER_BANK(rvu, blkaddr);
+	for (bank = 0; bank < max_bank; bank++) {
+		for (line = 0; line < max_line; line++) {
+			/* Check if 'cache line valid bit(63)' is not set
+			 * but 'cache line lock bit(60)' is set and on
+			 * success, reset the lock bit(60).
+			 */
+			reg = rvu_read64(rvu, blkaddr,
+					 NDC_AF_BANKX_LINEX_METADATA(bank, line));
+			if (!(reg & BIT_ULL(63)) && (reg & BIT_ULL(60))) {
+				rvu_write64(rvu, blkaddr,
+					    NDC_AF_BANKX_LINEX_METADATA(bank, line),
+					    reg & ~BIT_ULL(60));
+			}
+		}
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
index 0e0d536645ac..9bd4b6eeb7d5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
@@ -690,6 +690,7 @@ 
 #define NDC_AF_INTR_ENA_W1S		(0x00068)
 #define NDC_AF_INTR_ENA_W1C		(0x00070)
 #define NDC_AF_ACTIVE_PC		(0x00078)
+#define NDC_AF_CAMS_RD_INTERVAL		(0x00080)
 #define NDC_AF_BP_TEST_ENABLE		(0x001F8)
 #define NDC_AF_BP_TEST(a)		(0x00200 | (a) << 3)
 #define NDC_AF_BLK_RST			(0x002F0)
@@ -705,6 +706,8 @@ 
 		(0x00F00 | (a) << 5 | (b) << 4)
 #define NDC_AF_BANKX_HIT_PC(a)		(0x01000 | (a) << 3)
 #define NDC_AF_BANKX_MISS_PC(a)		(0x01100 | (a) << 3)
+#define NDC_AF_BANKX_LINEX_METADATA(a, b) \
+		(0x10000 | (a) << 3 | (b) << 3)
 
 /* LBK */
 #define LBK_CONST			(0x10ull)