* [PATCH v4 net-next 1/5] octeontx2-af: npc: cn20k: debugfs enhancements
2026-03-12 2:27 [PATCH v4 net-next 0/5] octeontx2-af: npc: Enhancements Ratheesh Kannoth
@ 2026-03-12 2:27 ` Ratheesh Kannoth
2026-03-12 2:27 ` [PATCH v4 net-next 2/5] devlink: Implement devlink param multi attribute nested data values Ratheesh Kannoth
` (3 subsequent siblings)
4 siblings, 0 replies; 11+ messages in thread
From: Ratheesh Kannoth @ 2026-03-12 2:27 UTC (permalink / raw)
To: netdev, linux-kernel
Cc: sgoutham, davem, edumazet, kuba, pabeni, horms, donald.hunter,
jiri, chuck.lever, matttbe, cjubran, shshitrit, Ratheesh Kannoth
Improve MCAM visibility and field debugging for CN20K NPC.
- Extend "mcam_layout" to show enabled (+) or disabled state per entry
so status can be verified without parsing the full "mcam_entry" dump.
- Add "dstats" debugfs entry: reports recently hit MCAM indices with
packet counts; stats are cleared on read so each read shows deltas.
- Add "mismatch" debugfs entry: lists MCAM entries that are enabled
but not explicitly allocated, helping diagnose allocation/field issues.
Signed-off-by: Ratheesh Kannoth <rkannoth@marvell.com>
---
.../marvell/octeontx2/af/cn20k/debugfs.c | 126 +++++++++++++++++-
.../ethernet/marvell/octeontx2/af/cn20k/npc.c | 16 ++-
.../ethernet/marvell/octeontx2/af/cn20k/npc.h | 7 +
3 files changed, 135 insertions(+), 14 deletions(-)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/debugfs.c
index 3debf2fae1a4..e8f85ed5ead7 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/debugfs.c
@@ -13,6 +13,7 @@
#include "struct.h"
#include "rvu.h"
#include "debugfs.h"
+#include "cn20k/reg.h"
#include "cn20k/npc.h"
static int npc_mcam_layout_show(struct seq_file *s, void *unused)
@@ -58,7 +59,8 @@ static int npc_mcam_layout_show(struct seq_file *s, void *unused)
"v:%u", vidx0);
}
- seq_printf(s, "\t%u(%#x) %s\n", idx0, pf1,
+ seq_printf(s, "\t%u(%#x)%c %s\n", idx0, pf1,
+ test_bit(idx0, npc_priv->en_map) ? '+' : ' ',
map ? buf0 : " ");
}
goto next;
@@ -101,9 +103,13 @@ static int npc_mcam_layout_show(struct seq_file *s, void *unused)
vidx1);
}
- seq_printf(s, "%05u(%#x) %s\t\t%05u(%#x) %s\n",
- idx1, pf2, v1 ? buf1 : " ",
- idx0, pf1, v0 ? buf0 : " ");
+ seq_printf(s, "%05u(%#x)%c %s\t\t%05u(%#x)%c %s\n",
+ idx1, pf2,
+ test_bit(idx1, npc_priv->en_map) ? '+' : ' ',
+ v1 ? buf1 : " ",
+ idx0, pf1,
+ test_bit(idx0, npc_priv->en_map) ? '+' : ' ',
+ v0 ? buf0 : " ");
continue;
}
@@ -120,8 +126,9 @@ static int npc_mcam_layout_show(struct seq_file *s, void *unused)
vidx0);
}
- seq_printf(s, "\t\t \t\t%05u(%#x) %s\n", idx0,
- pf1, map ? buf0 : " ");
+ seq_printf(s, "\t\t \t\t%05u(%#x)%c %s\n", idx0, pf1,
+ test_bit(idx0, npc_priv->en_map) ? '+' : ' ',
+ map ? buf0 : " ");
continue;
}
@@ -134,7 +141,8 @@ static int npc_mcam_layout_show(struct seq_file *s, void *unused)
snprintf(buf1, sizeof(buf1), "v:%05u", vidx1);
}
- seq_printf(s, "%05u(%#x) %s\n", idx1, pf1,
+ seq_printf(s, "%05u(%#x)%c %s\n", idx1, pf1,
+ test_bit(idx1, npc_priv->en_map) ? '+' : ' ',
map ? buf1 : " ");
}
next:
@@ -145,6 +153,100 @@ static int npc_mcam_layout_show(struct seq_file *s, void *unused)
DEFINE_SHOW_ATTRIBUTE(npc_mcam_layout);
+static u64 dstats[MAX_NUM_BANKS][MAX_SUBBANK_DEPTH * MAX_NUM_SUB_BANKS] = {};
+static int npc_mcam_dstats_show(struct seq_file *s, void *unused)
+{
+ struct npc_priv_t *npc_priv;
+ int blkaddr, pf, mcam_idx;
+ u64 stats, delta;
+ struct rvu *rvu;
+ u8 key_type;
+ void *map;
+
+ npc_priv = npc_priv_get();
+ rvu = s->private;
+ blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+ if (blkaddr < 0)
+ return 0;
+
+ seq_puts(s, "idx\tpfunc\tstats\n");
+ for (int bank = npc_priv->num_banks - 1; bank >= 0; bank--) {
+ for (int idx = npc_priv->bank_depth - 1; idx >= 0; idx--) {
+ mcam_idx = bank * npc_priv->bank_depth + idx;
+
+ npc_mcam_idx_2_key_type(rvu, mcam_idx, &key_type);
+ if (key_type == NPC_MCAM_KEY_X4 && bank != 0)
+ continue;
+
+ if (!test_bit(mcam_idx, npc_priv->en_map))
+ continue;
+
+ stats = rvu_read64(rvu, blkaddr,
+ NPC_AF_CN20K_MCAMEX_BANKX_STAT_EXT(idx, bank));
+ if (!stats)
+ continue;
+ if (stats == dstats[bank][idx])
+ continue;
+
+ if (stats < dstats[bank][idx])
+ dstats[bank][idx] = 0;
+
+ pf = 0xFFFF;
+ map = xa_load(&npc_priv->xa_idx2pf_map, mcam_idx);
+ if (map)
+ pf = xa_to_value(map);
+
+ if (stats > dstats[bank][idx])
+ delta = stats - dstats[bank][idx];
+ else
+ delta = stats;
+
+ seq_printf(s, "%u\t%#04x\t%llu\n",
+ mcam_idx, pf, delta);
+ dstats[bank][idx] = stats;
+ }
+ }
+ return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(npc_mcam_dstats);
+
+static int npc_mcam_mismatch_show(struct seq_file *s, void *unused)
+{
+ struct npc_priv_t *npc_priv;
+ struct npc_subbank *sb;
+ int mcam_idx, sb_off;
+ struct rvu *rvu;
+ void *map;
+ int rc;
+
+ npc_priv = npc_priv_get();
+ rvu = s->private;
+
+ seq_puts(s, "index\tsb idx\tkw type\n");
+ for (int bank = npc_priv->num_banks - 1; bank >= 0; bank--) {
+ for (int idx = npc_priv->bank_depth - 1; idx >= 0; idx--) {
+ mcam_idx = bank * npc_priv->bank_depth + idx;
+
+ if (!test_bit(mcam_idx, npc_priv->en_map))
+ continue;
+
+ map = xa_load(&npc_priv->xa_idx2pf_map, mcam_idx);
+ if (map)
+ continue;
+
+ rc = npc_mcam_idx_2_subbank_idx(rvu, mcam_idx,
+ &sb, &sb_off);
+ if (rc)
+ continue;
+
+ seq_printf(s, "%u\t%d\t%u\n", mcam_idx, sb->idx,
+ sb->key_type);
+ }
+ }
+ return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(npc_mcam_mismatch);
+
static int npc_mcam_default_show(struct seq_file *s, void *unused)
{
struct npc_priv_t *npc_priv;
@@ -257,6 +359,16 @@ int npc_cn20k_debugfs_init(struct rvu *rvu)
if (!npc_dentry)
return -EFAULT;
+ npc_dentry = debugfs_create_file("dstats", 0444, rvu->rvu_dbg.npc, rvu,
+ &npc_mcam_dstats_fops);
+ if (!npc_dentry)
+ return -EFAULT;
+
+ npc_dentry = debugfs_create_file("mismatch", 0444, rvu->rvu_dbg.npc, rvu,
+ &npc_mcam_mismatch_fops);
+ if (!npc_dentry)
+ return -EFAULT;
+
npc_dentry = debugfs_create_file("mcam_default", 0444, rvu->rvu_dbg.npc,
rvu, &npc_mcam_default_fops);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c
index 7291fdb89b03..e854b85ced9e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c
@@ -808,6 +808,9 @@ npc_cn20k_enable_mcam_entry(struct rvu *rvu, int blkaddr,
u64 cfg, hw_prio;
u8 kw_type;
+ enable ? set_bit(index, npc_priv.en_map) :
+ clear_bit(index, npc_priv.en_map);
+
npc_mcam_idx_2_key_type(rvu, index, &kw_type);
if (kw_type == NPC_MCAM_KEY_X2) {
cfg = rvu_read64(rvu, blkaddr,
@@ -1016,14 +1019,12 @@ static void npc_cn20k_config_kw_x4(struct rvu *rvu, struct npc_mcam *mcam,
static void
npc_cn20k_set_mcam_bank_cfg(struct rvu *rvu, int blkaddr, int mcam_idx,
- int bank, u8 kw_type, bool enable, u8 hw_prio)
+ int bank, u8 kw_type, u8 hw_prio)
{
struct npc_mcam *mcam = &rvu->hw->mcam;
u64 bank_cfg;
bank_cfg = (u64)hw_prio << 24;
- if (enable)
- bank_cfg |= 0x1;
if (kw_type == NPC_MCAM_KEY_X2) {
rvu_write64(rvu, blkaddr,
@@ -1119,7 +1120,8 @@ void npc_cn20k_config_mcam_entry(struct rvu *rvu, int blkaddr, int index,
/* TODO: */
/* PF installing VF rule */
npc_cn20k_set_mcam_bank_cfg(rvu, blkaddr, mcam_idx, bank,
- kw_type, enable, hw_prio);
+ kw_type, hw_prio);
+ npc_cn20k_enable_mcam_entry(rvu, blkaddr, index, enable);
}
void npc_cn20k_copy_mcam_entry(struct rvu *rvu, int blkaddr, u16 src, u16 dest)
@@ -1735,9 +1737,9 @@ static int npc_subbank_idx_2_mcam_idx(struct rvu *rvu, struct npc_subbank *sb,
return 0;
}
-static int npc_mcam_idx_2_subbank_idx(struct rvu *rvu, u16 mcam_idx,
- struct npc_subbank **sb,
- int *sb_off)
+int npc_mcam_idx_2_subbank_idx(struct rvu *rvu, u16 mcam_idx,
+ struct npc_subbank **sb,
+ int *sb_off)
{
int bank_off, sb_id;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.h
index 815d0b257a7e..004a556c7b90 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.h
@@ -170,6 +170,7 @@ struct npc_defrag_show_node {
* @num_banks: Number of banks.
* @num_subbanks: Number of subbanks.
* @subbank_depth: Depth of subbank.
+ * @en_map: Enable/disable status.
* @kw: Kex configured key type.
* @sb: Subbank array.
* @xa_sb_used: Array of used subbanks.
@@ -193,6 +194,9 @@ struct npc_priv_t {
const int num_banks;
int num_subbanks;
int subbank_depth;
+ DECLARE_BITMAP(en_map, MAX_NUM_BANKS *
+ MAX_NUM_SUB_BANKS *
+ MAX_SUBBANK_DEPTH);
u8 kw;
struct npc_subbank *sb;
struct xarray xa_sb_used;
@@ -336,5 +340,8 @@ int npc_mcam_idx_2_key_type(struct rvu *rvu, u16 mcam_idx, u8 *key_type);
u16 npc_cn20k_vidx2idx(u16 index);
u16 npc_cn20k_idx2vidx(u16 idx);
int npc_cn20k_defrag(struct rvu *rvu);
+int npc_mcam_idx_2_subbank_idx(struct rvu *rvu, u16 mcam_idx,
+ struct npc_subbank **sb,
+ int *sb_off);
#endif /* NPC_CN20K_H */
--
2.43.0
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH v4 net-next 2/5] devlink: Implement devlink param multi attribute nested data values
2026-03-12 2:27 [PATCH v4 net-next 0/5] octeontx2-af: npc: Enhancements Ratheesh Kannoth
2026-03-12 2:27 ` [PATCH v4 net-next 1/5] octeontx2-af: npc: cn20k: debugfs enhancements Ratheesh Kannoth
@ 2026-03-12 2:27 ` Ratheesh Kannoth
2026-03-17 3:36 ` Jakub Kicinski
2026-03-17 13:22 ` Jiri Pirko
2026-03-12 2:27 ` [PATCH v4 net-next 3/5] octeontx2-af: npc: cn20k: add subbank search order control Ratheesh Kannoth
` (2 subsequent siblings)
4 siblings, 2 replies; 11+ messages in thread
From: Ratheesh Kannoth @ 2026-03-12 2:27 UTC (permalink / raw)
To: netdev, linux-kernel
Cc: sgoutham, davem, edumazet, kuba, pabeni, horms, donald.hunter,
jiri, chuck.lever, matttbe, cjubran, shshitrit, Saeed Mahameed,
Ratheesh Kannoth
From: Saeed Mahameed <saeedm@nvidia.com>
Devlink param value attribute is not defined since devlink is handling
the value validating and parsing internally, this allows us to implement
multi attribute values without breaking any policies.
Devlink param multi-attribute values are considered to be dynamically
sized arrays of u32 values, by introducing a new devlink param type
DEVLINK_PARAM_TYPE_U32_ARRAY, driver and user space can set a variable
count of u32 values into the DEVLINK_ATTR_PARAM_VALUE_DATA attribute.
Implement get/set parsing and add to the internal value structure passed
to drivers.
This is useful for devices that need to configure a list of values for
a specific configuration.
example:
$ devlink dev param show pci/... name multi-value-param
name multi-value-param type driver-specific
values:
cmode permanent value: 0,1,2,3,4,5,6,7
$ devlink dev param set pci/... name multi-value-param \
value 4,5,6,7,0,1,2,3 cmode permanent
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Ratheesh Kannoth <rkannoth@marvell.com>
---
Documentation/netlink/specs/devlink.yaml | 4 ++
include/net/devlink.h | 8 +++
include/uapi/linux/devlink.h | 1 +
net/devlink/netlink_gen.c | 2 +
net/devlink/param.c | 81 ++++++++++++++++++------
5 files changed, 78 insertions(+), 18 deletions(-)
diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml
index 837112da6738..e8a8287c4f19 100644
--- a/Documentation/netlink/specs/devlink.yaml
+++ b/Documentation/netlink/specs/devlink.yaml
@@ -226,6 +226,10 @@ definitions:
value: 10
-
name: binary
+ -
+ name: u32-array
+ value: 129
+
-
name: rate-tc-index-max
type: const
diff --git a/include/net/devlink.h b/include/net/devlink.h
index cb839e0435a1..0a496715da99 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -432,6 +432,13 @@ enum devlink_param_type {
DEVLINK_PARAM_TYPE_U64 = DEVLINK_VAR_ATTR_TYPE_U64,
DEVLINK_PARAM_TYPE_STRING = DEVLINK_VAR_ATTR_TYPE_STRING,
DEVLINK_PARAM_TYPE_BOOL = DEVLINK_VAR_ATTR_TYPE_FLAG,
+ DEVLINK_PARAM_TYPE_U32_ARRAY = DEVLINK_VAR_ATTR_TYPE_U32_ARRAY,
+};
+
+#define __DEVLINK_PARAM_MAX_ARRAY_SIZE 32
+struct devlink_param_u32_array {
+ u32 size;
+ u32 val[__DEVLINK_PARAM_MAX_ARRAY_SIZE];
};
union devlink_param_value {
@@ -441,6 +448,7 @@ union devlink_param_value {
u64 vu64;
char vstr[__DEVLINK_PARAM_MAX_STRING_VALUE];
bool vbool;
+ struct devlink_param_u32_array u32arr;
};
struct devlink_param_gset_ctx {
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index e7d6b6d13470..768d0d88710f 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -404,6 +404,7 @@ enum devlink_var_attr_type {
DEVLINK_VAR_ATTR_TYPE_BINARY,
__DEVLINK_VAR_ATTR_TYPE_CUSTOM_BASE = 0x80,
/* Any possible custom types, unrelated to NLA_* values go below */
+ DEVLINK_VAR_ATTR_TYPE_U32_ARRAY,
};
enum devlink_attr {
diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c
index f4c61c2b4f22..e5a80eb467b8 100644
--- a/net/devlink/netlink_gen.c
+++ b/net/devlink/netlink_gen.c
@@ -32,6 +32,8 @@ devlink_attr_param_type_validate(const struct nlattr *attr,
case DEVLINK_VAR_ATTR_TYPE_NUL_STRING:
fallthrough;
case DEVLINK_VAR_ATTR_TYPE_BINARY:
+ fallthrough;
+ case DEVLINK_VAR_ATTR_TYPE_U32_ARRAY:
return 0;
}
NL_SET_ERR_MSG_ATTR(extack, attr, "invalid enum value");
diff --git a/net/devlink/param.c b/net/devlink/param.c
index cf95268da5b0..519cfa1ce459 100644
--- a/net/devlink/param.c
+++ b/net/devlink/param.c
@@ -252,6 +252,14 @@ devlink_nl_param_value_put(struct sk_buff *msg, enum devlink_param_type type,
return -EMSGSIZE;
}
break;
+ case DEVLINK_PARAM_TYPE_U32_ARRAY:
+ if (val.u32arr.size > __DEVLINK_PARAM_MAX_ARRAY_SIZE)
+ return -EMSGSIZE;
+
+ for (int i = 0; i < val.u32arr.size; i++)
+ if (nla_put_u32(msg, nla_type, val.u32arr.val[i]))
+ return -EMSGSIZE;
+ break;
}
return 0;
}
@@ -304,8 +312,8 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink,
u32 portid, u32 seq, int flags,
struct netlink_ext_ack *extack)
{
- union devlink_param_value default_value[DEVLINK_PARAM_CMODE_MAX + 1];
- union devlink_param_value param_value[DEVLINK_PARAM_CMODE_MAX + 1];
+ union devlink_param_value (*default_value)[DEVLINK_PARAM_CMODE_MAX + 1];
+ union devlink_param_value (*param_value)[DEVLINK_PARAM_CMODE_MAX + 1];
bool default_value_set[DEVLINK_PARAM_CMODE_MAX + 1] = {};
bool param_value_set[DEVLINK_PARAM_CMODE_MAX + 1] = {};
const struct devlink_param *param = param_item->param;
@@ -316,44 +324,57 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink,
int err;
int i;
+ default_value = kmalloc_obj(*default_value);
+ if (!default_value)
+ return -ENOMEM;
+
+ param_value = kmalloc_obj(*param_value);
+ if (!param_value) {
+ kfree(default_value);
+ return -ENOMEM;
+ }
+
/* Get value from driver part to driverinit configuration mode */
for (i = 0; i <= DEVLINK_PARAM_CMODE_MAX; i++) {
if (!devlink_param_cmode_is_supported(param, i))
continue;
if (i == DEVLINK_PARAM_CMODE_DRIVERINIT) {
- if (param_item->driverinit_value_new_valid)
- param_value[i] = param_item->driverinit_value_new;
- else if (param_item->driverinit_value_valid)
- param_value[i] = param_item->driverinit_value;
- else
- return -EOPNOTSUPP;
+ if (param_item->driverinit_value_new_valid) {
+ (*param_value)[i] = param_item->driverinit_value_new;
+ } else if (param_item->driverinit_value_valid) {
+ (*param_value)[i] = param_item->driverinit_value;
+ } else {
+ err = -EOPNOTSUPP;
+ goto get_put_fail;
+ }
if (param_item->driverinit_value_valid) {
- default_value[i] = param_item->driverinit_default;
+ (*default_value)[i] = param_item->driverinit_default;
default_value_set[i] = true;
}
} else {
ctx.cmode = i;
err = devlink_param_get(devlink, param, &ctx, extack);
if (err)
- return err;
- param_value[i] = ctx.val;
+ goto get_put_fail;
+ (*param_value)[i] = ctx.val;
err = devlink_param_get_default(devlink, param, &ctx,
extack);
if (!err) {
- default_value[i] = ctx.val;
+ (*default_value)[i] = ctx.val;
default_value_set[i] = true;
} else if (err != -EOPNOTSUPP) {
- return err;
+ goto get_put_fail;
}
}
param_value_set[i] = true;
}
+ err = -EMSGSIZE;
hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
if (!hdr)
- return -EMSGSIZE;
+ goto get_put_fail;
if (devlink_nl_put_handle(msg, devlink))
goto genlmsg_cancel;
@@ -383,8 +404,8 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink,
if (!param_value_set[i])
continue;
err = devlink_nl_param_value_fill_one(msg, param->type,
- i, param_value[i],
- default_value[i],
+ i, (*param_value)[i],
+ (*default_value)[i],
default_value_set[i]);
if (err)
goto values_list_nest_cancel;
@@ -393,6 +414,8 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink,
nla_nest_end(msg, param_values_list);
nla_nest_end(msg, param_attr);
genlmsg_end(msg, hdr);
+ kfree(default_value);
+ kfree(param_value);
return 0;
values_list_nest_cancel:
@@ -401,7 +424,10 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink,
nla_nest_cancel(msg, param_attr);
genlmsg_cancel:
genlmsg_cancel(msg, hdr);
- return -EMSGSIZE;
+get_put_fail:
+ kfree(default_value);
+ kfree(param_value);
+ return err;
}
static void devlink_param_notify(struct devlink *devlink,
@@ -507,7 +533,7 @@ devlink_param_value_get_from_info(const struct devlink_param *param,
union devlink_param_value *value)
{
struct nlattr *param_data;
- int len;
+ int len, cnt, rem;
param_data = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA];
@@ -547,6 +573,25 @@ devlink_param_value_get_from_info(const struct devlink_param *param,
return -EINVAL;
value->vbool = nla_get_flag(param_data);
break;
+
+ case DEVLINK_PARAM_TYPE_U32_ARRAY:
+ cnt = 0;
+ nla_for_each_attr_type(param_data,
+ DEVLINK_ATTR_PARAM_VALUE_DATA,
+ genlmsg_data(info->genlhdr),
+ genlmsg_len(info->genlhdr), rem) {
+ if (cnt >= __DEVLINK_PARAM_MAX_ARRAY_SIZE)
+ return -EMSGSIZE;
+
+ if (nla_len(param_data) != sizeof(u32))
+ return -EINVAL;
+
+ value->u32arr.val[cnt] = nla_get_u32(param_data);
+ cnt++;
+ }
+
+ value->u32arr.size = cnt;
+ break;
}
return 0;
}
--
2.43.0
^ permalink raw reply related [flat|nested] 11+ messages in thread* Re: [PATCH v4 net-next 2/5] devlink: Implement devlink param multi attribute nested data values
2026-03-12 2:27 ` [PATCH v4 net-next 2/5] devlink: Implement devlink param multi attribute nested data values Ratheesh Kannoth
@ 2026-03-17 3:36 ` Jakub Kicinski
2026-03-17 13:22 ` Jiri Pirko
1 sibling, 0 replies; 11+ messages in thread
From: Jakub Kicinski @ 2026-03-17 3:36 UTC (permalink / raw)
To: Ratheesh Kannoth
Cc: netdev, linux-kernel, sgoutham, davem, edumazet, pabeni, horms,
donald.hunter, jiri, chuck.lever, matttbe, cjubran, shshitrit,
Saeed Mahameed
On Thu, 12 Mar 2026 07:57:51 +0530 Ratheesh Kannoth wrote:
> - union devlink_param_value default_value[DEVLINK_PARAM_CMODE_MAX + 1];
> - union devlink_param_value param_value[DEVLINK_PARAM_CMODE_MAX + 1];
> + union devlink_param_value (*default_value)[DEVLINK_PARAM_CMODE_MAX + 1];
> + union devlink_param_value (*param_value)[DEVLINK_PARAM_CMODE_MAX + 1];
let's declare this as a pointer rather than pointer to an array,
the (*arr)[i] indexing changes won't be necessary.
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [PATCH v4 net-next 2/5] devlink: Implement devlink param multi attribute nested data values
2026-03-12 2:27 ` [PATCH v4 net-next 2/5] devlink: Implement devlink param multi attribute nested data values Ratheesh Kannoth
2026-03-17 3:36 ` Jakub Kicinski
@ 2026-03-17 13:22 ` Jiri Pirko
2026-03-18 2:31 ` Ratheesh Kannoth
1 sibling, 1 reply; 11+ messages in thread
From: Jiri Pirko @ 2026-03-17 13:22 UTC (permalink / raw)
To: Ratheesh Kannoth
Cc: netdev, linux-kernel, sgoutham, davem, edumazet, kuba, pabeni,
horms, donald.hunter, chuck.lever, matttbe, cjubran, shshitrit,
Saeed Mahameed
Thu, Mar 12, 2026 at 03:27:51AM +0100, rkannoth@marvell.com wrote:
>From: Saeed Mahameed <saeedm@nvidia.com>
[..]
>+
>+ case DEVLINK_PARAM_TYPE_U32_ARRAY:
>+ cnt = 0;
>+ nla_for_each_attr_type(param_data,
>+ DEVLINK_ATTR_PARAM_VALUE_DATA,
>+ genlmsg_data(info->genlhdr),
>+ genlmsg_len(info->genlhdr), rem) {
>+ if (cnt >= __DEVLINK_PARAM_MAX_ARRAY_SIZE)
>+ return -EMSGSIZE;
>+
>+ if (nla_len(param_data) != sizeof(u32))
>+ return -EINVAL;
>+
>+ value->u32arr.val[cnt] = nla_get_u32(param_data);
Now that we have UINT to be used everywhere for new netlink attributes,
wouldn't it make sense to have rather UINT array?
>+ cnt++;
>+ }
>+
>+ value->u32arr.size = cnt;
>+ break;
[..]
^ permalink raw reply [flat|nested] 11+ messages in thread* Re: [PATCH v4 net-next 2/5] devlink: Implement devlink param multi attribute nested data values
2026-03-17 13:22 ` Jiri Pirko
@ 2026-03-18 2:31 ` Ratheesh Kannoth
0 siblings, 0 replies; 11+ messages in thread
From: Ratheesh Kannoth @ 2026-03-18 2:31 UTC (permalink / raw)
To: Jiri Pirko
Cc: netdev, linux-kernel, sgoutham, davem, edumazet, kuba, pabeni,
horms, donald.hunter, chuck.lever, matttbe, cjubran, shshitrit,
Saeed Mahameed
On 2026-03-17 at 18:52:32, Jiri Pirko (jiri@resnulli.us) wrote:
> >+ case DEVLINK_PARAM_TYPE_U32_ARRAY:
> >+ cnt = 0;
> >+ nla_for_each_attr_type(param_data,
> >+ DEVLINK_ATTR_PARAM_VALUE_DATA,
> >+ genlmsg_data(info->genlhdr),
> >+ genlmsg_len(info->genlhdr), rem) {
> >+ if (cnt >= __DEVLINK_PARAM_MAX_ARRAY_SIZE)
> >+ return -EMSGSIZE;
> >+
> >+ if (nla_len(param_data) != sizeof(u32))
> >+ return -EINVAL;
> >+
> >+ value->u32arr.val[cnt] = nla_get_u32(param_data);
>
> Now that we have UINT to be used everywhere for new netlink attributes,
> wouldn't it make sense to have rather UINT array?
We have U8, U16, U32, U64 param types in devlink. So declared as u32 array.
Let me know if you feel strongly about your opinion, will respin
enum devlink_param_type {
DEVLINK_PARAM_TYPE_U8 = DEVLINK_VAR_ATTR_TYPE_U8,
DEVLINK_PARAM_TYPE_U16 = DEVLINK_VAR_ATTR_TYPE_U16,
DEVLINK_PARAM_TYPE_U32 = DEVLINK_VAR_ATTR_TYPE_U32,
DEVLINK_PARAM_TYPE_U64 = DEVLINK_VAR_ATTR_TYPE_U64,
DEVLINK_PARAM_TYPE_STRING = DEVLINK_VAR_ATTR_TYPE_STRING,
DEVLINK_PARAM_TYPE_BOOL = DEVLINK_VAR_ATTR_TYPE_FLAG,
DEVLINK_PARAM_TYPE_U32_ARRAY = DEVLINK_VAR_ATTR_TYPE_U32_ARRAY,
};
^ permalink raw reply [flat|nested] 11+ messages in thread
* [PATCH v4 net-next 3/5] octeontx2-af: npc: cn20k: add subbank search order control
2026-03-12 2:27 [PATCH v4 net-next 0/5] octeontx2-af: npc: Enhancements Ratheesh Kannoth
2026-03-12 2:27 ` [PATCH v4 net-next 1/5] octeontx2-af: npc: cn20k: debugfs enhancements Ratheesh Kannoth
2026-03-12 2:27 ` [PATCH v4 net-next 2/5] devlink: Implement devlink param multi attribute nested data values Ratheesh Kannoth
@ 2026-03-12 2:27 ` Ratheesh Kannoth
2026-03-17 3:32 ` [v4,net-next,3/5] " Jakub Kicinski
2026-03-12 2:27 ` [PATCH v4 net-next 4/5] octeontx2-af: npc: cn20k: dynamically allocate and free default MCAM entries Ratheesh Kannoth
2026-03-12 2:27 ` [PATCH v4 net-next 5/5] octeontx2-af: npc: Support for custom KPU profile from filesystem Ratheesh Kannoth
4 siblings, 1 reply; 11+ messages in thread
From: Ratheesh Kannoth @ 2026-03-12 2:27 UTC (permalink / raw)
To: netdev, linux-kernel
Cc: sgoutham, davem, edumazet, kuba, pabeni, horms, donald.hunter,
jiri, chuck.lever, matttbe, cjubran, shshitrit, Ratheesh Kannoth
CN20K NPC MCAM is split into 32 subbanks that are searched in a
predefined order during allocation. Lower-numbered subbanks have
higher priority than higher-numbered ones.
Add a runtime devlink parameter "srch_order" (
DEVLINK_PARAM_TYPE_U32_ARRAY) to control the order in which
subbanks are searched during MCAM allocation.
Signed-off-by: Ratheesh Kannoth <rkannoth@marvell.com>
---
.../ethernet/marvell/octeontx2/af/cn20k/npc.c | 87 ++++++++++++++++++
.../ethernet/marvell/octeontx2/af/cn20k/npc.h | 2 +
.../marvell/octeontx2/af/rvu_devlink.c | 92 +++++++++++++++++--
3 files changed, 171 insertions(+), 10 deletions(-)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c
index e854b85ced9e..348a72c4ee43 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c
@@ -3809,6 +3809,93 @@ static void npc_unlock_all_subbank(void)
mutex_unlock(&npc_priv.sb[i].lock);
}
+int npc_cn20k_search_order_set(struct rvu *rvu,
+ u32 arr[MAX_NUM_SUB_BANKS], int cnt)
+{
+ struct npc_mcam *mcam = &rvu->hw->mcam;
+ u32 fslots[MAX_NUM_SUB_BANKS][2];
+ u32 uslots[MAX_NUM_SUB_BANKS][2];
+ int fcnt = 0, ucnt = 0;
+ struct npc_subbank *sb;
+ int idx, val, rc = 0;
+
+ unsigned long index;
+ void *v;
+
+ if (cnt != npc_priv.num_subbanks) {
+ dev_err(rvu->dev, "Number of entries(%u) != %u\n",
+ cnt, npc_priv.num_subbanks);
+ return -EINVAL;
+ }
+
+ mutex_lock(&mcam->lock);
+ npc_lock_all_subbank();
+ restrict_valid = false;
+
+ for (int i = 0; i < cnt; i++)
+ subbank_srch_order[i] = arr[i];
+
+ xa_for_each(&npc_priv.xa_sb_used, index, v) {
+ val = xa_to_value(v);
+ uslots[ucnt][0] = index;
+ uslots[ucnt][1] = val;
+ xa_erase(&npc_priv.xa_sb_used, index);
+ ucnt++;
+ }
+
+ xa_for_each(&npc_priv.xa_sb_free, index, v) {
+ val = xa_to_value(v);
+ fslots[fcnt][0] = index;
+ fslots[fcnt][1] = val;
+ xa_erase(&npc_priv.xa_sb_free, index);
+ fcnt++;
+ }
+
+ /* xa_store() is done under lock. If xa_store fails
+ * ,no rollback is planned as it might also fail.
+ */
+ for (int i = 0; i < ucnt; i++) {
+ idx = uslots[i][1];
+ sb = &npc_priv.sb[idx];
+ sb->arr_idx = subbank_srch_order[sb->idx];
+ rc = xa_err(xa_store(&npc_priv.xa_sb_used, sb->arr_idx,
+ xa_mk_value(sb->idx), GFP_KERNEL));
+ if (rc) {
+ dev_err(rvu->dev,
+ "Error to insert index to used list %u\n",
+ sb->idx);
+ goto fail_used;
+ }
+ }
+
+ for (int i = 0; i < fcnt; i++) {
+ idx = fslots[i][1];
+ sb = &npc_priv.sb[idx];
+ sb->arr_idx = subbank_srch_order[sb->idx];
+ rc = xa_err(xa_store(&npc_priv.xa_sb_free, sb->arr_idx,
+ xa_mk_value(sb->idx), GFP_KERNEL));
+ if (rc) {
+ dev_err(rvu->dev,
+ "Error to insert index to free list %u\n",
+ sb->idx);
+ goto fail_used;
+ }
+ }
+
+fail_used:
+ npc_unlock_all_subbank();
+ mutex_unlock(&mcam->lock);
+
+ return rc;
+}
+
+const u32 *npc_cn20k_search_order_get(bool *restricted_order, u32 *sz)
+{
+ *restricted_order = restrict_valid;
+ *sz = npc_priv.num_subbanks;
+ return subbank_srch_order;
+}
+
/* Only non-ref non-contigous mcam indexes
* are picked for defrag process
*/
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.h
index 004a556c7b90..b168ecfbc5c8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.h
@@ -343,5 +343,7 @@ int npc_cn20k_defrag(struct rvu *rvu);
int npc_mcam_idx_2_subbank_idx(struct rvu *rvu, u16 mcam_idx,
struct npc_subbank **sb,
int *sb_off);
+const u32 *npc_cn20k_search_order_get(bool *restricted_order, u32 *sz);
+int npc_cn20k_search_order_set(struct rvu *rvu, u32 arr[32], int cnt);
#endif /* NPC_CN20K_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
index 287ff0eda152..420cda6d5d5f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
@@ -1258,6 +1258,7 @@ enum rvu_af_dl_param_id {
RVU_AF_DEVLINK_PARAM_ID_NPC_EXACT_FEATURE_DISABLE,
RVU_AF_DEVLINK_PARAM_ID_NPC_DEF_RULE_CNTR_ENABLE,
RVU_AF_DEVLINK_PARAM_ID_NPC_DEFRAG,
+ RVU_AF_DEVLINK_PARAM_ID_NPC_SRCH_ORDER,
RVU_AF_DEVLINK_PARAM_ID_NIX_MAXLF,
};
@@ -1619,12 +1620,83 @@ static int rvu_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
return 0;
}
+static int rvu_af_dl_npc_srch_order_set(struct devlink *devlink, u32 id,
+ struct devlink_param_gset_ctx *ctx,
+ struct netlink_ext_ack *extack)
+{
+ struct rvu_devlink *rvu_dl = devlink_priv(devlink);
+ struct rvu *rvu = rvu_dl->rvu;
+
+ return npc_cn20k_search_order_set(rvu,
+ ctx->val.u32arr.val,
+ ctx->val.u32arr.size);
+}
+
+static int rvu_af_dl_npc_srch_order_get(struct devlink *devlink, u32 id,
+ struct devlink_param_gset_ctx *ctx,
+ struct netlink_ext_ack *extack)
+{
+ bool restricted_order;
+ const u32 *order;
+ u32 sz;
+
+ order = npc_cn20k_search_order_get(&restricted_order, &sz);
+ ctx->val.u32arr.size = sz;
+ for (int i = 0; i < sz; i++)
+ ctx->val.u32arr.val[i] = order[i];
+
+ return 0;
+}
+
+static int rvu_af_dl_npc_srch_order_validate(struct devlink *devlink, u32 id,
+ union devlink_param_value val,
+ struct netlink_ext_ack *extack)
+{
+ struct rvu_devlink *rvu_dl = devlink_priv(devlink);
+ struct rvu *rvu = rvu_dl->rvu;
+ bool restricted_order;
+ unsigned long w = 0;
+ u32 *arr;
+ u32 sz;
+
+ npc_cn20k_search_order_get(&restricted_order, &sz);
+ if (sz != val.u32arr.size) {
+ dev_err(rvu->dev,
+ "Wrong size %u, should be %u\n",
+ val.u32arr.size, sz);
+ return -EINVAL;
+ }
+
+ arr = val.u32arr.val;
+ for (int i = 0; i < sz; i++) {
+ if (arr[i] >= sz)
+ return -EINVAL;
+
+ w |= BIT_ULL(arr[i]);
+ }
+
+ if (bitmap_weight(&w, sz) != sz) {
+ dev_err(rvu->dev,
+ "Duplicate or out-of-range subbank index. %lu\n",
+ find_first_zero_bit(&w, sz));
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static const struct devlink_ops rvu_devlink_ops = {
.eswitch_mode_get = rvu_devlink_eswitch_mode_get,
.eswitch_mode_set = rvu_devlink_eswitch_mode_set,
};
-static const struct devlink_param rvu_af_dl_param_defrag[] = {
+static const struct devlink_param rvu_af_dl_cn20k_params[] = {
+ DEVLINK_PARAM_DRIVER(RVU_AF_DEVLINK_PARAM_ID_NPC_SRCH_ORDER,
+ "npc_srch_order", DEVLINK_PARAM_TYPE_U32_ARRAY,
+ BIT(DEVLINK_PARAM_CMODE_RUNTIME),
+ rvu_af_dl_npc_srch_order_get,
+ rvu_af_dl_npc_srch_order_set,
+ rvu_af_dl_npc_srch_order_validate),
DEVLINK_PARAM_DRIVER(RVU_AF_DEVLINK_PARAM_ID_NPC_DEFRAG,
"npc_defrag", DEVLINK_PARAM_TYPE_STRING,
BIT(DEVLINK_PARAM_CMODE_RUNTIME),
@@ -1666,13 +1738,13 @@ int rvu_register_dl(struct rvu *rvu)
}
if (is_cn20k(rvu->pdev)) {
- err = devlink_params_register(dl, rvu_af_dl_param_defrag,
- ARRAY_SIZE(rvu_af_dl_param_defrag));
+ err = devlink_params_register(dl, rvu_af_dl_cn20k_params,
+ ARRAY_SIZE(rvu_af_dl_cn20k_params));
if (err) {
dev_err(rvu->dev,
- "devlink defrag params register failed with error %d",
+ "devlink cn20k params register failed with error %d",
err);
- goto err_dl_defrag;
+ goto err_dl_cn20k_params;
}
}
@@ -1695,10 +1767,10 @@ int rvu_register_dl(struct rvu *rvu)
err_dl_exact_match:
if (is_cn20k(rvu->pdev))
- devlink_params_unregister(dl, rvu_af_dl_param_defrag,
- ARRAY_SIZE(rvu_af_dl_param_defrag));
+ devlink_params_unregister(dl, rvu_af_dl_cn20k_params,
+ ARRAY_SIZE(rvu_af_dl_cn20k_params));
-err_dl_defrag:
+err_dl_cn20k_params:
devlink_params_unregister(dl, rvu_af_dl_params, ARRAY_SIZE(rvu_af_dl_params));
err_dl_health:
@@ -1717,8 +1789,8 @@ void rvu_unregister_dl(struct rvu *rvu)
devlink_params_unregister(dl, rvu_af_dl_params, ARRAY_SIZE(rvu_af_dl_params));
if (is_cn20k(rvu->pdev))
- devlink_params_unregister(dl, rvu_af_dl_param_defrag,
- ARRAY_SIZE(rvu_af_dl_param_defrag));
+ devlink_params_unregister(dl, rvu_af_dl_cn20k_params,
+ ARRAY_SIZE(rvu_af_dl_cn20k_params));
/* Unregister exact match devlink only for CN10K-B */
if (rvu_npc_exact_has_match_table(rvu))
--
2.43.0
^ permalink raw reply related [flat|nested] 11+ messages in thread* Re: [v4,net-next,3/5] octeontx2-af: npc: cn20k: add subbank search order control
2026-03-12 2:27 ` [PATCH v4 net-next 3/5] octeontx2-af: npc: cn20k: add subbank search order control Ratheesh Kannoth
@ 2026-03-17 3:32 ` Jakub Kicinski
0 siblings, 0 replies; 11+ messages in thread
From: Jakub Kicinski @ 2026-03-17 3:32 UTC (permalink / raw)
To: rkannoth
Cc: Jakub Kicinski, linux-kernel, chuck.lever, jiri, netdev,
donald.hunter, saeedm, sgoutham, edumazet, davem, matttbe, horms,
cjubran, pabeni, shshitrit
This is an AI-generated review of your patch. The human sending this
email has considered the AI review valid, or at least plausible.
For local reproduction steps see https://netdev-ai.bots.linux.dev/ai-local.html
---
octeontx2-af: npc: cn20k: add subbank search order control
CN20K NPC MCAM is split into 32 subbanks that are searched in a
predefined order during allocation. Lower-numbered subbanks have
higher priority than higher-numbered ones. Add a runtime devlink
parameter "srch_order" (DEVLINK_PARAM_TYPE_U32_ARRAY) to control the
order in which subbanks are searched during MCAM allocation.
> diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c
> index e854b85ced9e..348a72c4ee43 100644
> --- a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c
> +++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c
> @@ -3809,6 +3809,93 @@ static void npc_unlock_all_subbank(void)
> mutex_unlock(&npc_priv.sb[i].lock);
> }
>
> +int npc_cn20k_search_order_set(struct rvu *rvu,
> + u32 arr[MAX_NUM_SUB_BANKS], int cnt)
> +{
[ ... ]
> +fail_used:
> + npc_unlock_all_subbank();
> + mutex_unlock(&mcam->lock);
> +
> + return rc;
> +}
> +
> +const u32 *npc_cn20k_search_order_get(bool *restricted_order, u32 *sz)
> +{
> + *restricted_order = restrict_valid;
> + *sz = npc_priv.num_subbanks;
> + return subbank_srch_order;
> +}
^^^^^^^^^^^^^^^^^^^
Is there a type mismatch here? The function signature declares the return
type as 'const u32 *' but returns 'subbank_srch_order', which appears to be
declared as 'static int *' elsewhere in the code. While the values stored
(0-31 for subbank indices) fit within both int and u32, and sizeof(int) ==
sizeof(u32) on all kernel-supported architectures, this conversion between
signed and unsigned pointer types is technically incompatible.
The callers rvu_af_dl_npc_srch_order_get() and
rvu_af_dl_npc_srch_order_validate() treat the returned pointer as a u32
array:
drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c:rvu_af_dl_npc_srch_order_get()
{
const u32 *order;
...
order = npc_cn20k_search_order_get(&restricted_order, &sz);
...
for (int i = 0; i < sz; i++)
ctx->val.u32arr.val[i] = order[i];
}
Should subbank_srch_order be declared as 'static u32 *' instead of 'static
int *', or should the function return type be changed to 'const int *' to
match the actual type?
> diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.h
> index 004a556c7b90..b168ecfbc5c8 100644
> --- a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.h
> +++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.h
> @@ -343,5 +343,7 @@ int npc_cn20k_defrag(struct rvu *rvu);
[ ... ]
--
pw-bot: cr
^ permalink raw reply [flat|nested] 11+ messages in thread
* [PATCH v4 net-next 4/5] octeontx2-af: npc: cn20k: dynamically allocate and free default MCAM entries
2026-03-12 2:27 [PATCH v4 net-next 0/5] octeontx2-af: npc: Enhancements Ratheesh Kannoth
` (2 preceding siblings ...)
2026-03-12 2:27 ` [PATCH v4 net-next 3/5] octeontx2-af: npc: cn20k: add subbank search order control Ratheesh Kannoth
@ 2026-03-12 2:27 ` Ratheesh Kannoth
2026-03-12 2:27 ` [PATCH v4 net-next 5/5] octeontx2-af: npc: Support for custom KPU profile from filesystem Ratheesh Kannoth
4 siblings, 0 replies; 11+ messages in thread
From: Ratheesh Kannoth @ 2026-03-12 2:27 UTC (permalink / raw)
To: netdev, linux-kernel
Cc: sgoutham, davem, edumazet, kuba, pabeni, horms, donald.hunter,
jiri, chuck.lever, matttbe, cjubran, shshitrit, Ratheesh Kannoth
Improve MCAM utilization by tying default (broadcast, multicast,
promisc, ucast) entry lifetime to NIX LF usage.
- On NIX LF alloc (e.g. kernel or DPDK), allocate default MCAM entries
if missing; on NIX LF free, release them so they return to the pool.
- Add NIX_LF_DONT_FREE_DFT_IDXS so the kernel PF driver can free the
NIX LF without releasing default entries (e.g. across suspend/resume).
- When NIX LF is used by DPDK, default entries are allocated on first
use and freed when the LF is released if NIX_LF_DONT_FREE_DFT_IDXS is
not set
Signed-off-by: Ratheesh Kannoth <rkannoth@marvell.com>
---
.../ethernet/marvell/octeontx2/af/cn20k/npc.c | 108 +++++++++++----
.../ethernet/marvell/octeontx2/af/cn20k/npc.h | 1 +
.../net/ethernet/marvell/octeontx2/af/mbox.h | 1 +
.../ethernet/marvell/octeontx2/af/rvu_nix.c | 16 ++-
.../ethernet/marvell/octeontx2/af/rvu_npc.c | 128 +++++++++++++-----
.../ethernet/marvell/octeontx2/nic/otx2_pf.c | 6 +-
6 files changed, 191 insertions(+), 69 deletions(-)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c
index 348a72c4ee43..8dad272fd069 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c
@@ -808,6 +808,11 @@ npc_cn20k_enable_mcam_entry(struct rvu *rvu, int blkaddr,
u64 cfg, hw_prio;
u8 kw_type;
+ if (index < 0 || index >= mcam->total_entries) {
+ WARN(1, "Wrong mcam index %d\n", index);
+ return;
+ }
+
enable ? set_bit(index, npc_priv.en_map) :
clear_bit(index, npc_priv.en_map);
@@ -1053,6 +1058,11 @@ void npc_cn20k_config_mcam_entry(struct rvu *rvu, int blkaddr, int index,
int kw = 0;
u8 kw_type;
+ if (index < 0 || index >= mcam->total_entries) {
+ WARN(1, "Wrong mcam index %d\n", index);
+ return;
+ }
+
/* Disable before mcam entry update */
npc_cn20k_enable_mcam_entry(rvu, blkaddr, index, false);
@@ -1132,6 +1142,11 @@ void npc_cn20k_copy_mcam_entry(struct rvu *rvu, int blkaddr, u16 src, u16 dest)
int bank, i, sb, db;
int dbank, sbank;
+ if (src >= mcam->total_entries || dest >= mcam->total_entries) {
+ WARN(1, "Wrong mcam index src=%u dest=%u\n", src, dest);
+ return;
+ }
+
dbank = npc_get_bank(mcam, dest);
sbank = npc_get_bank(mcam, src);
npc_mcam_idx_2_key_type(rvu, src, &src_kwtype);
@@ -1190,11 +1205,24 @@ void npc_cn20k_read_mcam_entry(struct rvu *rvu, int blkaddr, u16 index,
int kw = 0, bank;
u8 kw_type;
+ if (index >= mcam->total_entries) {
+ WARN(1, "Wrong mcam index %u\n", index);
+ return;
+ }
+
npc_mcam_idx_2_key_type(rvu, index, &kw_type);
bank = npc_get_bank(mcam, index);
index &= (mcam->banksize - 1);
+ cfg = rvu_read64(rvu, blkaddr,
+ NPC_AF_CN20K_MCAMEX_BANKX_ACTIONX_EXT(index, bank, 0));
+ entry->action = cfg;
+
+ cfg = rvu_read64(rvu, blkaddr,
+ NPC_AF_CN20K_MCAMEX_BANKX_ACTIONX_EXT(index, bank, 1));
+ entry->vtag_action = cfg;
+
cfg = rvu_read64(rvu, blkaddr,
NPC_AF_CN20K_MCAMEX_BANKX_CAMX_INTF_EXT(index,
bank, 1)) & 3;
@@ -1244,7 +1272,7 @@ void npc_cn20k_read_mcam_entry(struct rvu *rvu, int blkaddr, u16 index,
bank,
0));
npc_cn20k_fill_entryword(entry, kw + 3, cam0, cam1);
- goto read_action;
+ return;
}
for (bank = 0; bank < mcam->banks_per_entry; bank++, kw = kw + 4) {
@@ -1289,17 +1317,6 @@ void npc_cn20k_read_mcam_entry(struct rvu *rvu, int blkaddr, u16 index,
npc_cn20k_fill_entryword(entry, kw + 3, cam0, cam1);
}
-read_action:
- /* 'action' is set to same value for both bank '0' and '1'.
- * Hence, reading bank '0' should be enough.
- */
- cfg = rvu_read64(rvu, blkaddr,
- NPC_AF_CN20K_MCAMEX_BANKX_ACTIONX_EXT(index, 0, 0));
- entry->action = cfg;
-
- cfg = rvu_read64(rvu, blkaddr,
- NPC_AF_CN20K_MCAMEX_BANKX_ACTIONX_EXT(index, 0, 1));
- entry->vtag_action = cfg;
}
int rvu_mbox_handler_npc_cn20k_mcam_write_entry(struct rvu *rvu,
@@ -1671,8 +1688,8 @@ int npc_mcam_idx_2_key_type(struct rvu *rvu, u16 mcam_idx, u8 *key_type)
/* mcam_idx should be less than (2 * bank depth) */
if (mcam_idx >= npc_priv.bank_depth * 2) {
- dev_err(rvu->dev, "%s: bad params\n",
- __func__);
+ dev_err(rvu->dev, "%s: bad params mcam_idx=%u\n",
+ __func__, mcam_idx);
return -EINVAL;
}
@@ -4024,6 +4041,13 @@ int npc_cn20k_dft_rules_idx_get(struct rvu *rvu, u16 pcifunc, u16 *bcast,
void *val;
int i, j;
+ for (int i = 0; i < ARRAY_SIZE(ptr); i++) {
+ if (!ptr[i])
+ continue;
+
+ *ptr[i] = USHRT_MAX;
+ }
+
if (!npc_priv.init_done)
return 0;
@@ -4039,7 +4063,6 @@ int npc_cn20k_dft_rules_idx_get(struct rvu *rvu, u16 pcifunc, u16 *bcast,
npc_dft_rule_name[NPC_DFT_RULE_PROMISC_ID],
pcifunc);
- *ptr[0] = USHRT_MAX;
return -ESRCH;
}
@@ -4059,7 +4082,6 @@ int npc_cn20k_dft_rules_idx_get(struct rvu *rvu, u16 pcifunc, u16 *bcast,
npc_dft_rule_name[NPC_DFT_RULE_UCAST_ID],
pcifunc);
- *ptr[3] = USHRT_MAX;
return -ESRCH;
}
@@ -4079,7 +4101,6 @@ int npc_cn20k_dft_rules_idx_get(struct rvu *rvu, u16 pcifunc, u16 *bcast,
__func__,
npc_dft_rule_name[i], pcifunc);
- *ptr[j] = USHRT_MAX;
continue;
}
@@ -4174,7 +4195,7 @@ int rvu_mbox_handler_npc_get_dft_rl_idxs(struct rvu *rvu, struct msg_req *req,
return 0;
}
-static bool npc_is_cgx_or_lbk(struct rvu *rvu, u16 pcifunc)
+bool npc_is_cgx_or_lbk(struct rvu *rvu, u16 pcifunc)
{
return is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, pcifunc)) ||
is_lbk_vf(rvu, pcifunc);
@@ -4182,9 +4203,10 @@ static bool npc_is_cgx_or_lbk(struct rvu *rvu, u16 pcifunc)
void npc_cn20k_dft_rules_free(struct rvu *rvu, u16 pcifunc)
{
- struct npc_mcam_free_entry_req free_req = { 0 };
+ struct npc_mcam *mcam = &rvu->hw->mcam;
+ struct rvu_npc_mcam_rule *rule, *tmp;
unsigned long index;
- struct msg_rsp rsp;
+ int blkaddr;
u16 ptr[4];
int rc, i;
void *map;
@@ -4209,7 +4231,7 @@ void npc_cn20k_dft_rules_free(struct rvu *rvu, u16 pcifunc)
index = NPC_DFT_RULE_ID_MK(pcifunc, NPC_DFT_RULE_PROMISC_ID);
map = xa_erase(&npc_priv.xa_pf2dfl_rmap, index);
if (!map)
- dev_dbg(rvu->dev,
+ dev_err(rvu->dev,
"%s: Err from delete %s mcam idx from xarray (pcifunc=%#x\n",
__func__,
npc_dft_rule_name[NPC_DFT_RULE_PROMISC_ID],
@@ -4223,7 +4245,7 @@ void npc_cn20k_dft_rules_free(struct rvu *rvu, u16 pcifunc)
index = NPC_DFT_RULE_ID_MK(pcifunc, NPC_DFT_RULE_UCAST_ID);
map = xa_erase(&npc_priv.xa_pf2dfl_rmap, index);
if (!map)
- dev_dbg(rvu->dev,
+ dev_err(rvu->dev,
"%s: Err from delete %s mcam idx from xarray (pcifunc=%#x\n",
__func__,
npc_dft_rule_name[NPC_DFT_RULE_UCAST_ID],
@@ -4237,21 +4259,47 @@ void npc_cn20k_dft_rules_free(struct rvu *rvu, u16 pcifunc)
index = NPC_DFT_RULE_ID_MK(pcifunc, i);
map = xa_erase(&npc_priv.xa_pf2dfl_rmap, index);
if (!map)
- dev_dbg(rvu->dev,
+ dev_err(rvu->dev,
"%s: Err from delete %s mcam idx from xarray (pcifunc=%#x\n",
__func__, npc_dft_rule_name[i],
pcifunc);
}
free_rules:
+ blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+ if (blkaddr < 0)
+ return;
- free_req.hdr.pcifunc = pcifunc;
- free_req.all = 1;
- rc = rvu_mbox_handler_npc_mcam_free_entry(rvu, &free_req, &rsp);
- if (rc)
- dev_err(rvu->dev,
- "%s: Error deleting default entries (pcifunc=%#x\n",
- __func__, pcifunc);
+ for (int i = 0; i < 4; i++) {
+ if (ptr[i] == USHRT_MAX)
+ continue;
+
+ mutex_lock(&mcam->lock);
+ npc_mcam_clear_bit(mcam, ptr[i]);
+ mcam->entry2pfvf_map[ptr[i]] = NPC_MCAM_INVALID_MAP;
+ npc_cn20k_enable_mcam_entry(rvu, blkaddr, ptr[i], false);
+ mcam->entry2target_pffunc[ptr[i]] = 0x0;
+ mutex_unlock(&mcam->lock);
+
+ rc = npc_cn20k_idx_free(rvu, &ptr[i], 1);
+ if (rc)
+ dev_err(rvu->dev,
+ "%s:%d Error deleting default entries (pcifunc=%#x) mcam_idx=%u\n",
+ __func__, __LINE__, pcifunc, ptr[i]);
+ }
+
+ mutex_lock(&mcam->lock);
+ list_for_each_entry_safe(rule, tmp, &mcam->mcam_rules, list) {
+ for (int i = 0; i < 4; i++) {
+ if (ptr[i] != rule->entry)
+ continue;
+
+ list_del(&rule->list);
+ kfree(rule);
+ break;
+ }
+ }
+ mutex_unlock(&mcam->lock);
}
int npc_cn20k_dft_rules_alloc(struct rvu *rvu, u16 pcifunc)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.h
index b168ecfbc5c8..0fa56f5382b4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.h
@@ -345,5 +345,6 @@ int npc_mcam_idx_2_subbank_idx(struct rvu *rvu, u16 mcam_idx,
int *sb_off);
const u32 *npc_cn20k_search_order_get(bool *restricted_order, u32 *sz);
int npc_cn20k_search_order_set(struct rvu *rvu, u32 arr[32], int cnt);
+bool npc_is_cgx_or_lbk(struct rvu *rvu, u16 pcifunc);
#endif /* NPC_CN20K_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index dc42c81c0942..e07fbf842b94 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -1009,6 +1009,7 @@ struct nix_lf_free_req {
struct mbox_msghdr hdr;
#define NIX_LF_DISABLE_FLOWS BIT_ULL(0)
#define NIX_LF_DONT_FREE_TX_VTAG BIT_ULL(1)
+#define NIX_LF_DONT_FREE_DFT_IDXS BIT_ULL(2)
u64 flags;
};
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index ef5b081162eb..bd671b553df5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -16,6 +16,7 @@
#include "cgx.h"
#include "lmac_common.h"
#include "rvu_npc_hash.h"
+#include "cn20k/npc.h"
static void nix_free_tx_vtag_entries(struct rvu *rvu, u16 pcifunc);
static int rvu_nix_get_bpid(struct rvu *rvu, struct nix_bp_cfg_req *req,
@@ -1684,10 +1685,16 @@ int rvu_mbox_handler_nix_lf_alloc(struct rvu *rvu,
if (is_sdp_pfvf(rvu, pcifunc))
intf = NIX_INTF_TYPE_SDP;
+ if (is_cn20k(rvu->pdev)) {
+ rc = npc_cn20k_dft_rules_alloc(rvu, pcifunc);
+ if (rc)
+ goto free_mem;
+ }
+
err = nix_interface_init(rvu, pcifunc, intf, nixlf, rsp,
!!(req->flags & NIX_LF_LBK_BLK_SEL));
if (err)
- goto free_mem;
+ goto free_dft;
/* Disable NPC entries as NIXLF's contexts are not initialized yet */
rvu_npc_disable_default_entries(rvu, pcifunc, nixlf);
@@ -1699,6 +1706,10 @@ int rvu_mbox_handler_nix_lf_alloc(struct rvu *rvu,
goto exit;
+free_dft:
+ if (is_cn20k(rvu->pdev))
+ npc_cn20k_dft_rules_free(rvu, pcifunc);
+
free_mem:
nix_ctx_free(rvu, pfvf);
rc = -ENOMEM;
@@ -1775,6 +1786,9 @@ int rvu_mbox_handler_nix_lf_free(struct rvu *rvu, struct nix_lf_free_req *req,
nix_ctx_free(rvu, pfvf);
+ if (is_cn20k(rvu->pdev) && !(req->flags & NIX_LF_DONT_FREE_DFT_IDXS))
+ npc_cn20k_dft_rules_free(rvu, pcifunc);
+
return 0;
}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index c2ca5ed1d028..352dc5f1d5b9 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -165,12 +165,20 @@ int npc_get_nixlf_mcam_index(struct npc_mcam *mcam,
switch (type) {
case NIXLF_BCAST_ENTRY:
+ if (bcast == USHRT_MAX)
+ return -EINVAL;
return bcast;
case NIXLF_ALLMULTI_ENTRY:
+ if (mcast == USHRT_MAX)
+ return -EINVAL;
return mcast;
case NIXLF_PROMISC_ENTRY:
+ if (promisc == USHRT_MAX)
+ return -EINVAL;
return promisc;
case NIXLF_UCAST_ENTRY:
+ if (ucast == USHRT_MAX)
+ return -EINVAL;
return ucast;
default:
return -EINVAL;
@@ -237,12 +245,8 @@ void npc_enable_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
int bank = npc_get_bank(mcam, index);
int actbank = bank;
- if (is_cn20k(rvu->pdev)) {
- if (index < 0 || index >= mcam->banksize * mcam->banks)
- return;
-
+ if (is_cn20k(rvu->pdev))
return npc_cn20k_enable_mcam_entry(rvu, blkaddr, index, enable);
- }
index &= (mcam->banksize - 1);
for (; bank < (actbank + mcam->banks_per_entry); bank++) {
@@ -1113,7 +1117,7 @@ void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf,
index = mcam_index;
}
- if (index >= mcam->total_entries)
+ if (index < 0 || index >= mcam->total_entries)
return;
bank = npc_get_bank(mcam, index);
@@ -1158,16 +1162,18 @@ void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf,
/* If PF's promiscuous entry is enabled,
* Set RSS action for that entry as well
*/
- npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index,
- blkaddr, alg_idx);
+ if (index >= 0)
+ npc_update_rx_action_with_alg_idx(rvu, action, pfvf,
+ index, blkaddr, alg_idx);
index = npc_get_nixlf_mcam_index(mcam, pcifunc,
nixlf, NIXLF_ALLMULTI_ENTRY);
/* If PF's allmulti entry is enabled,
* Set RSS action for that entry as well
*/
- npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index,
- blkaddr, alg_idx);
+ if (index >= 0)
+ npc_update_rx_action_with_alg_idx(rvu, action, pfvf,
+ index, blkaddr, alg_idx);
}
}
@@ -1212,8 +1218,13 @@ static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc,
{
struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
struct npc_mcam *mcam = &rvu->hw->mcam;
+ int type = NIXLF_UCAST_ENTRY;
int index, blkaddr;
+ /* only CGX or LBK interfaces have default entries */
+ if (is_cn20k(rvu->pdev) && !npc_is_cgx_or_lbk(rvu, pcifunc))
+ return;
+
blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
if (blkaddr < 0)
return;
@@ -1221,8 +1232,11 @@ static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc,
/* Ucast MCAM match entry of this PF/VF */
if (npc_is_feature_supported(rvu, BIT_ULL(NPC_DMAC),
pfvf->nix_rx_intf)) {
+ if (is_cn20k(rvu->pdev) && is_lbk_vf(rvu, pcifunc))
+ type = NIXLF_PROMISC_ENTRY;
+
index = npc_get_nixlf_mcam_index(mcam, pcifunc,
- nixlf, NIXLF_UCAST_ENTRY);
+ nixlf, type);
npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable);
}
@@ -1232,9 +1246,13 @@ static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc,
if ((pcifunc & RVU_PFVF_FUNC_MASK) && !rvu->hw->cap.nix_rx_multicast)
return;
+ type = NIXLF_BCAST_ENTRY;
+ if (is_cn20k(rvu->pdev) && is_lbk_vf(rvu, pcifunc))
+ type = NIXLF_PROMISC_ENTRY;
+
/* add/delete pf_func to broadcast MCE list */
npc_enadis_default_mce_entry(rvu, pcifunc, nixlf,
- NIXLF_BCAST_ENTRY, enable);
+ type, enable);
}
void rvu_npc_disable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
@@ -1244,6 +1262,9 @@ void rvu_npc_disable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
npc_enadis_default_entries(rvu, pcifunc, nixlf, false);
+ if (is_cn20k(rvu->pdev) && is_vf(pcifunc))
+ return;
+
/* Delete multicast and promisc MCAM entries */
npc_enadis_default_mce_entry(rvu, pcifunc, nixlf,
NIXLF_ALLMULTI_ENTRY, false);
@@ -1301,6 +1322,10 @@ void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
if (blkaddr < 0)
return;
+ /* only CGX or LBK interfaces have default entries */
+ if (is_cn20k(rvu->pdev) && !npc_is_cgx_or_lbk(rvu, pcifunc))
+ return;
+
mutex_lock(&mcam->lock);
/* Disable MCAM entries directing traffic to this 'pcifunc' */
@@ -1345,6 +1370,8 @@ void rvu_npc_free_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
/* Free all MCAM counters owned by this 'pcifunc' */
npc_mcam_free_all_counters(rvu, mcam, pcifunc);
+ rvu_npc_disable_default_entries(rvu, pcifunc, nixlf);
+
/* Delete MCAM entries owned by this 'pcifunc' */
list_for_each_entry_safe(rule, tmp, &mcam->mcam_rules, list) {
if (rule->owner == pcifunc && !rule->default_rule) {
@@ -1355,7 +1382,6 @@ void rvu_npc_free_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
mutex_unlock(&mcam->lock);
- rvu_npc_disable_default_entries(rvu, pcifunc, nixlf);
}
static void npc_program_mkex_rx(struct rvu *rvu, int blkaddr,
@@ -2504,33 +2530,58 @@ void npc_mcam_clear_bit(struct npc_mcam *mcam, u16 index)
static void npc_mcam_free_all_entries(struct rvu *rvu, struct npc_mcam *mcam,
int blkaddr, u16 pcifunc)
{
+ u16 dft_idxs[NPC_DFT_RULE_MAX_ID] = {[0 ... NPC_DFT_RULE_MAX_ID - 1] = USHRT_MAX};
u16 index, cntr;
+ bool dft_rl;
int rc;
+ npc_cn20k_dft_rules_idx_get(rvu, pcifunc,
+ &dft_idxs[NPC_DFT_RULE_BCAST_ID],
+ &dft_idxs[NPC_DFT_RULE_MCAST_ID],
+ &dft_idxs[NPC_DFT_RULE_PROMISC_ID],
+ &dft_idxs[NPC_DFT_RULE_UCAST_ID]);
+
/* Scan all MCAM entries and free the ones mapped to 'pcifunc' */
for (index = 0; index < mcam->bmap_entries; index++) {
- if (mcam->entry2pfvf_map[index] == pcifunc) {
- mcam->entry2pfvf_map[index] = NPC_MCAM_INVALID_MAP;
- /* Free the entry in bitmap */
- npc_mcam_clear_bit(mcam, index);
- /* Disable the entry */
- npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false);
-
- /* Update entry2counter mapping */
- cntr = mcam->entry2cntr_map[index];
- if (cntr != NPC_MCAM_INVALID_MAP)
- npc_unmap_mcam_entry_and_cntr(rvu, mcam,
- blkaddr, index,
- cntr);
- mcam->entry2target_pffunc[index] = 0x0;
- if (is_cn20k(rvu->pdev)) {
- rc = npc_cn20k_idx_free(rvu, &index, 1);
- if (rc)
- dev_err(rvu->dev,
- "Failed to free mcam idx=%u pcifunc=%#x\n",
- index, pcifunc);
+ if (mcam->entry2pfvf_map[index] != pcifunc)
+ continue;
+
+ mcam->entry2pfvf_map[index] = NPC_MCAM_INVALID_MAP;
+
+ dft_rl = false;
+ if (is_cn20k(rvu->pdev)) {
+ if (dft_idxs[NPC_DFT_RULE_BCAST_ID] == index ||
+ dft_idxs[NPC_DFT_RULE_MCAST_ID] == index ||
+ dft_idxs[NPC_DFT_RULE_PROMISC_ID] == index ||
+ dft_idxs[NPC_DFT_RULE_UCAST_ID] == index) {
+ dft_rl = true;
}
}
+
+ /* Free the entry in bitmap.*/
+ if (!dft_rl)
+ npc_mcam_clear_bit(mcam, index);
+
+ /* Disable the entry */
+ npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false);
+
+ /* Update entry2counter mapping */
+ cntr = mcam->entry2cntr_map[index];
+ if (cntr != NPC_MCAM_INVALID_MAP)
+ npc_unmap_mcam_entry_and_cntr(rvu, mcam,
+ blkaddr, index,
+ cntr);
+ mcam->entry2target_pffunc[index] = 0x0;
+ if (is_cn20k(rvu->pdev)) {
+ if (dft_rl)
+ continue;
+
+ rc = npc_cn20k_idx_free(rvu, &index, 1);
+ if (rc)
+ dev_err(rvu->dev,
+ "Failed to free mcam idx=%u pcifunc=%#x\n",
+ index, pcifunc);
+ }
}
}
@@ -3917,13 +3968,22 @@ void rvu_npc_clear_ucast_entry(struct rvu *rvu, int pcifunc, int nixlf)
struct npc_mcam *mcam = &rvu->hw->mcam;
struct rvu_npc_mcam_rule *rule;
int ucast_idx, blkaddr;
+ u8 type;
blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
if (blkaddr < 0)
return;
+ type = NIXLF_UCAST_ENTRY;
+ if (is_cn20k(rvu->pdev) && is_lbk_vf(rvu, pcifunc))
+ type = NIXLF_PROMISC_ENTRY;
+
ucast_idx = npc_get_nixlf_mcam_index(mcam, pcifunc,
- nixlf, NIXLF_UCAST_ENTRY);
+ nixlf, type);
+
+ /* In cn20k, default rules are freed before detach rsrc */
+ if (ucast_idx < 0)
+ return;
npc_enable_mcam_entry(rvu, mcam, blkaddr, ucast_idx, false);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index ee623476e5ff..81b088f5a016 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -1053,7 +1053,6 @@ irqreturn_t otx2_pfaf_mbox_intr_handler(int irq, void *pf_irq)
/* Clear the IRQ */
otx2_write64(pf, RVU_PF_INT, BIT_ULL(0));
-
mbox_data = otx2_read64(pf, RVU_PF_PFAF_MBOX0);
if (mbox_data & MBOX_UP_MSG) {
@@ -1729,7 +1728,7 @@ int otx2_init_hw_resources(struct otx2_nic *pf)
mutex_lock(&mbox->lock);
free_req = otx2_mbox_alloc_msg_nix_lf_free(mbox);
if (free_req) {
- free_req->flags = NIX_LF_DISABLE_FLOWS;
+ free_req->flags = NIX_LF_DISABLE_FLOWS | NIX_LF_DONT_FREE_DFT_IDXS;
if (otx2_sync_mbox_msg(mbox))
dev_err(pf->dev, "%s failed to free nixlf\n", __func__);
}
@@ -1803,7 +1802,7 @@ void otx2_free_hw_resources(struct otx2_nic *pf)
/* Reset NIX LF */
free_req = otx2_mbox_alloc_msg_nix_lf_free(mbox);
if (free_req) {
- free_req->flags = NIX_LF_DISABLE_FLOWS;
+ free_req->flags = NIX_LF_DISABLE_FLOWS | NIX_LF_DONT_FREE_DFT_IDXS;
if (!(pf->flags & OTX2_FLAG_PF_SHUTDOWN))
free_req->flags |= NIX_LF_DONT_FREE_TX_VTAG;
if (otx2_sync_mbox_msg(mbox))
@@ -1926,7 +1925,6 @@ int otx2_alloc_queue_mem(struct otx2_nic *pf)
struct otx2_qset *qset = &pf->qset;
struct otx2_cq_poll *cq_poll;
-
/* RQ and SQs are mapped to different CQs,
* so find out max CQ IRQs (i.e CINTs) needed.
*/
--
2.43.0
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH v4 net-next 5/5] octeontx2-af: npc: Support for custom KPU profile from filesystem
2026-03-12 2:27 [PATCH v4 net-next 0/5] octeontx2-af: npc: Enhancements Ratheesh Kannoth
` (3 preceding siblings ...)
2026-03-12 2:27 ` [PATCH v4 net-next 4/5] octeontx2-af: npc: cn20k: dynamically allocate and free default MCAM entries Ratheesh Kannoth
@ 2026-03-12 2:27 ` Ratheesh Kannoth
2026-03-17 3:32 ` [v4,net-next,5/5] " Jakub Kicinski
4 siblings, 1 reply; 11+ messages in thread
From: Ratheesh Kannoth @ 2026-03-12 2:27 UTC (permalink / raw)
To: netdev, linux-kernel
Cc: sgoutham, davem, edumazet, kuba, pabeni, horms, donald.hunter,
jiri, chuck.lever, matttbe, cjubran, shshitrit, Ratheesh Kannoth
Flashing updated firmware on deployed devices is cumbersome. Provide a
mechanism to load a custom KPU (Key Parse Unit) profile directly from
the filesystem at module load time.
When the rvu_af module is loaded with the kpu_profile parameter, the
specified profile is read from /lib/firmware/kpu and programmed into
the KPU registers. Add npc_kpu_profile_cam2 for the extended cam format
used by filesystem-loaded profiles and support ptype/ptype_mask in
npc_config_kpucam when profile->from_fs is set.
Usage:
1. Copy the KPU profile file to /lib/firmware/kpu.
2. Build OCTEONTX2_AF as a module.
3. Load: insmod rvu_af.ko kpu_profile=<profile_name>
Signed-off-by: Ratheesh Kannoth <rkannoth@marvell.com>
---
.../ethernet/marvell/octeontx2/af/cn20k/npc.c | 21 +-
.../net/ethernet/marvell/octeontx2/af/npc.h | 17 ++
.../net/ethernet/marvell/octeontx2/af/rvu.h | 6 +-
.../ethernet/marvell/octeontx2/af/rvu_npc.c | 269 +++++++++++++++---
.../ethernet/marvell/octeontx2/af/rvu_npc.h | 17 ++
.../ethernet/marvell/octeontx2/af/rvu_reg.h | 1 +
6 files changed, 285 insertions(+), 46 deletions(-)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c
index 8dad272fd069..c8c09a91b13f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c
@@ -521,13 +521,17 @@ npc_program_single_kpm_profile(struct rvu *rvu, int blkaddr,
int kpm, int start_entry,
const struct npc_kpu_profile *profile)
{
+ int num_cam_entries, num_action_entries;
int entry, num_entries, max_entries;
u64 idx;
- if (profile->cam_entries != profile->action_entries) {
+ num_cam_entries = npc_get_num_kpu_cam_entries(rvu, profile);
+ num_action_entries = npc_get_num_kpu_action_entries(rvu, profile);
+
+ if (num_cam_entries != num_action_entries) {
dev_err(rvu->dev,
"kpm%d: CAM and action entries [%d != %d] not equal\n",
- kpm, profile->cam_entries, profile->action_entries);
+ kpm, num_cam_entries, num_action_entries);
WARN(1, "Fatal error\n");
return;
@@ -536,16 +540,18 @@ npc_program_single_kpm_profile(struct rvu *rvu, int blkaddr,
max_entries = rvu->hw->npc_kpu_entries / 2;
entry = start_entry;
/* Program CAM match entries for previous kpm extracted data */
- num_entries = min_t(int, profile->cam_entries, max_entries);
+ num_entries = min_t(int, num_cam_entries, max_entries);
for (idx = 0; entry < num_entries + start_entry; entry++, idx++)
- npc_config_kpmcam(rvu, blkaddr, &profile->cam[idx],
+ npc_config_kpmcam(rvu, blkaddr,
+ npc_get_kpu_cam_nth_entry(rvu, profile, idx),
kpm, entry);
entry = start_entry;
/* Program this kpm's actions */
- num_entries = min_t(int, profile->action_entries, max_entries);
+ num_entries = min_t(int, num_action_entries, max_entries);
for (idx = 0; entry < num_entries + start_entry; entry++, idx++)
- npc_config_kpmaction(rvu, blkaddr, &profile->action[idx],
+ npc_config_kpmaction(rvu, blkaddr,
+ npc_get_kpu_action_nth_entry(rvu, profile, idx),
kpm, entry, false);
}
@@ -666,7 +672,8 @@ void npc_cn20k_parser_profile_init(struct rvu *rvu, int blkaddr)
num_pkinds = min_t(int, hw->npc_pkinds, num_pkinds);
for (idx = 0; idx < num_pkinds; idx++)
- npc_config_kpmaction(rvu, blkaddr, &rvu->kpu.ikpu[idx],
+ npc_config_kpmaction(rvu, blkaddr,
+ npc_get_ikpu_nth_entry(rvu, idx),
0, idx, true);
/* Program KPM CAM and Action profiles */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
index cefc5d70f3e4..c8c0cb68535c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
@@ -265,6 +265,19 @@ struct npc_kpu_profile_cam {
u16 dp2_mask;
} __packed;
+struct npc_kpu_profile_cam2 {
+ u8 state;
+ u8 state_mask;
+ u16 dp0;
+ u16 dp0_mask;
+ u16 dp1;
+ u16 dp1_mask;
+ u16 dp2;
+ u16 dp2_mask;
+ u8 ptype;
+ u8 ptype_mask;
+} __packed;
+
struct npc_kpu_profile_action {
u8 errlev;
u8 errcode;
@@ -290,6 +303,10 @@ struct npc_kpu_profile {
int action_entries;
struct npc_kpu_profile_cam *cam;
struct npc_kpu_profile_action *action;
+ int cam_entries2;
+ int action_entries2;
+ struct npc_kpu_profile_action *action2;
+ struct npc_kpu_profile_cam2 *cam2;
};
/* NPC KPU register formats */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index a466181cf908..eb2e4ccf070d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -553,8 +553,9 @@ struct npc_kpu_profile_adapter {
const char *name;
u64 version;
const struct npc_lt_def_cfg *lt_def;
- const struct npc_kpu_profile_action *ikpu; /* array[pkinds] */
- const struct npc_kpu_profile *kpu; /* array[kpus] */
+ struct npc_kpu_profile_action *ikpu; /* array[pkinds] */
+ struct npc_kpu_profile_action *ikpu2; /* array[pkinds] */
+ struct npc_kpu_profile *kpu; /* array[kpus] */
union npc_mcam_key_prfl {
struct npc_mcam_kex *mkex;
/* used for cn9k and cn10k */
@@ -564,6 +565,7 @@ struct npc_kpu_profile_adapter {
bool custom;
size_t pkinds;
size_t kpus;
+ bool from_fs;
};
#define RVU_SWITCH_LBK_CHAN 63
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 352dc5f1d5b9..e348cdd375eb 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -1583,8 +1583,12 @@ static void npc_config_kpucam(struct rvu *rvu, int blkaddr,
const struct npc_kpu_profile_cam *kpucam,
int kpu, int entry)
{
+ const struct npc_kpu_profile_cam2 *kpucam2 = (void *)kpucam;
+ struct npc_kpu_profile_adapter *profile = &rvu->kpu;
struct npc_kpu_cam cam0 = {0};
struct npc_kpu_cam cam1 = {0};
+ u64 *val = (u64 *)&cam1;
+ u64 *mask = (u64 *)&cam0;
cam1.state = kpucam->state & kpucam->state_mask;
cam1.dp0_data = kpucam->dp0 & kpucam->dp0_mask;
@@ -1596,6 +1600,14 @@ static void npc_config_kpucam(struct rvu *rvu, int blkaddr,
cam0.dp1_data = ~kpucam->dp1 & kpucam->dp1_mask;
cam0.dp2_data = ~kpucam->dp2 & kpucam->dp2_mask;
+ if (profile->from_fs) {
+ u8 ptype = kpucam2->ptype;
+ u8 pmask = kpucam2->ptype_mask;
+
+ *val |= FIELD_PREP(GENMASK_ULL(57, 56), ptype & pmask);
+ *mask |= FIELD_PREP(GENMASK_ULL(57, 56), ~ptype & pmask);
+ }
+
rvu_write64(rvu, blkaddr,
NPC_AF_KPUX_ENTRYX_CAMX(kpu, entry, 0), *(u64 *)&cam0);
rvu_write64(rvu, blkaddr,
@@ -1607,34 +1619,104 @@ u64 npc_enable_mask(int count)
return (((count) < 64) ? ~(BIT_ULL(count) - 1) : (0x00ULL));
}
+struct npc_kpu_profile_action *
+npc_get_ikpu_nth_entry(struct rvu *rvu, int n)
+{
+ struct npc_kpu_profile_adapter *profile = &rvu->kpu;
+
+ if (profile->from_fs)
+ return &profile->ikpu2[n];
+
+ return &profile->ikpu[n];
+}
+
+int
+npc_get_num_kpu_cam_entries(struct rvu *rvu,
+ const struct npc_kpu_profile *kpu_pfl)
+{
+ struct npc_kpu_profile_adapter *profile = &rvu->kpu;
+
+ if (profile->from_fs)
+ return kpu_pfl->cam_entries2;
+
+ return kpu_pfl->cam_entries;
+}
+
+struct npc_kpu_profile_cam *
+npc_get_kpu_cam_nth_entry(struct rvu *rvu,
+ const struct npc_kpu_profile *kpu_pfl, int n)
+{
+ struct npc_kpu_profile_adapter *profile = &rvu->kpu;
+
+ if (profile->from_fs)
+ return (void *)&kpu_pfl->cam2[n];
+
+ return (void *)&kpu_pfl->cam[n];
+}
+
+int
+npc_get_num_kpu_action_entries(struct rvu *rvu,
+ const struct npc_kpu_profile *kpu_pfl)
+{
+ struct npc_kpu_profile_adapter *profile = &rvu->kpu;
+
+ if (profile->from_fs)
+ return kpu_pfl->action_entries2;
+
+ return kpu_pfl->action_entries;
+}
+
+struct npc_kpu_profile_action *
+npc_get_kpu_action_nth_entry(struct rvu *rvu,
+ const struct npc_kpu_profile *kpu_pfl,
+ int n)
+{
+ struct npc_kpu_profile_adapter *profile = &rvu->kpu;
+
+ if (profile->from_fs)
+ return (void *)&kpu_pfl->action2[n];
+
+ return (void *)&kpu_pfl->action[n];
+}
+
static void npc_program_kpu_profile(struct rvu *rvu, int blkaddr, int kpu,
const struct npc_kpu_profile *profile)
{
+ int num_cam_entries, num_action_entries;
int entry, num_entries, max_entries;
u64 entry_mask;
- if (profile->cam_entries != profile->action_entries) {
+ num_cam_entries = npc_get_num_kpu_cam_entries(rvu, profile);
+ num_action_entries = npc_get_num_kpu_action_entries(rvu, profile);
+
+ if (num_cam_entries != num_action_entries) {
dev_err(rvu->dev,
"KPU%d: CAM and action entries [%d != %d] not equal\n",
- kpu, profile->cam_entries, profile->action_entries);
+ kpu, num_cam_entries, num_action_entries);
}
max_entries = rvu->hw->npc_kpu_entries;
+ WARN(num_cam_entries > max_entries,
+ "KPU%u: err: hw max entries=%u, input entries=%u\n",
+ kpu, rvu->hw->npc_kpu_entries, num_cam_entries);
+
/* Program CAM match entries for previous KPU extracted data */
- num_entries = min_t(int, profile->cam_entries, max_entries);
+ num_entries = min_t(int, num_cam_entries, max_entries);
for (entry = 0; entry < num_entries; entry++)
npc_config_kpucam(rvu, blkaddr,
- &profile->cam[entry], kpu, entry);
+ (void *)npc_get_kpu_cam_nth_entry(rvu, profile, entry),
+ kpu, entry);
/* Program this KPU's actions */
- num_entries = min_t(int, profile->action_entries, max_entries);
+ num_entries = min_t(int, num_action_entries, max_entries);
for (entry = 0; entry < num_entries; entry++)
- npc_config_kpuaction(rvu, blkaddr, &profile->action[entry],
+ npc_config_kpuaction(rvu, blkaddr,
+ (void *)npc_get_kpu_action_nth_entry(rvu, profile, entry),
kpu, entry, false);
/* Enable all programmed entries */
- num_entries = min_t(int, profile->action_entries, profile->cam_entries);
+ num_entries = min_t(int, num_action_entries, num_cam_entries);
entry_mask = npc_enable_mask(num_entries);
/* Disable first KPU_MAX_CST_ENT entries for built-in profile */
if (!rvu->kpu.custom)
@@ -1678,26 +1760,50 @@ static void npc_prepare_default_kpu(struct rvu *rvu,
npc_cn20k_update_action_entries_n_flags(rvu, profile);
}
+static int npc_alloc_kpu_cam2_n_action2(struct rvu *rvu, int kpu_num,
+ int num_entries)
+{
+ struct npc_kpu_profile_adapter *adapter = &rvu->kpu;
+ struct npc_kpu_profile *kpu;
+
+ kpu = &adapter->kpu[kpu_num];
+
+ kpu->cam2 = devm_kcalloc(rvu->dev, num_entries,
+ sizeof(*kpu->cam2), GFP_KERNEL);
+ if (!kpu->cam2)
+ return -ENOMEM;
+
+ kpu->action2 = devm_kcalloc(rvu->dev, num_entries,
+ sizeof(*kpu->action2), GFP_KERNEL);
+ if (!kpu->action2)
+ return -ENOMEM;
+
+ return 0;
+}
+
static int npc_apply_custom_kpu(struct rvu *rvu,
- struct npc_kpu_profile_adapter *profile)
+ struct npc_kpu_profile_adapter *profile,
+ bool from_fs, int *fw_kpus)
{
size_t hdr_sz = sizeof(struct npc_kpu_profile_fwdata), offset = 0;
struct npc_kpu_profile_action *action;
+ struct npc_kpu_profile_fwdata *sfw;
struct npc_kpu_profile_fwdata *fw;
+ struct npc_kpu_profile_cam2 *cam2;
struct npc_kpu_profile_cam *cam;
struct npc_kpu_fwdata *fw_kpu;
- int entries;
+ int entries, ret;
u16 kpu, entry;
if (is_cn20k(rvu->pdev))
return npc_cn20k_apply_custom_kpu(rvu, profile);
- fw = rvu->kpu_fwdata;
-
if (rvu->kpu_fwdata_sz < hdr_sz) {
dev_warn(rvu->dev, "Invalid KPU profile size\n");
return -EINVAL;
}
+
+ fw = rvu->kpu_fwdata;
if (le64_to_cpu(fw->signature) != KPU_SIGN) {
dev_warn(rvu->dev, "Invalid KPU profile signature %llx\n",
fw->signature);
@@ -1731,32 +1837,89 @@ static int npc_apply_custom_kpu(struct rvu *rvu,
return -EINVAL;
}
+ *fw_kpus = fw->kpus;
+
+ sfw = devm_kcalloc(rvu->dev, 1, sizeof(*sfw), GFP_KERNEL);
+ if (!sfw)
+ return -ENOMEM;
+
+ memcpy(sfw, fw, sizeof(*sfw));
+
profile->custom = 1;
- profile->name = fw->name;
+ profile->name = sfw->name;
profile->version = le64_to_cpu(fw->version);
- profile->mcam_kex_prfl.mkex = &fw->mkex;
- profile->lt_def = &fw->lt_def;
+ profile->mcam_kex_prfl.mkex = &sfw->mkex;
+ profile->lt_def = &sfw->lt_def;
+
+ /* Binary blob contains ikpu actions entries at start of data[0] */
+ if (from_fs) {
+ profile->ikpu2 = devm_kcalloc(rvu->dev, 1,
+ sizeof(ikpu_action_entries),
+ GFP_KERNEL);
+ if (!profile->ikpu2)
+ return -ENOMEM;
+
+ action = (struct npc_kpu_profile_action *)(fw->data + offset);
+
+ if (rvu->kpu_fwdata_sz < hdr_sz + sizeof(ikpu_action_entries))
+ return -ENOMEM;
+
+ memcpy((void *)profile->ikpu2, action, sizeof(ikpu_action_entries));
+ offset += sizeof(ikpu_action_entries);
+ }
for (kpu = 0; kpu < fw->kpus; kpu++) {
fw_kpu = (struct npc_kpu_fwdata *)(fw->data + offset);
- if (fw_kpu->entries > KPU_MAX_CST_ENT)
- dev_warn(rvu->dev,
- "Too many custom entries on KPU%d: %d > %d\n",
- kpu, fw_kpu->entries, KPU_MAX_CST_ENT);
- entries = min(fw_kpu->entries, KPU_MAX_CST_ENT);
- cam = (struct npc_kpu_profile_cam *)fw_kpu->data;
- offset += sizeof(*fw_kpu) + fw_kpu->entries * sizeof(*cam);
+ if (!from_fs) {
+ if (fw_kpu->entries > KPU_MAX_CST_ENT)
+ dev_warn(rvu->dev,
+ "Too many custom entries on KPU%d: %d > %d\n",
+ kpu, fw_kpu->entries, KPU_MAX_CST_ENT);
+ entries = min(fw_kpu->entries, KPU_MAX_CST_ENT);
+ cam = (struct npc_kpu_profile_cam *)fw_kpu->data;
+ offset += sizeof(*fw_kpu) + fw_kpu->entries * sizeof(*cam);
+ action = (struct npc_kpu_profile_action *)(fw->data + offset);
+ offset += fw_kpu->entries * sizeof(*action);
+ if (rvu->kpu_fwdata_sz < hdr_sz + offset) {
+ dev_warn(rvu->dev,
+ "Profile size mismatch on KPU%i parsing.\n",
+ kpu + 1);
+ return -EINVAL;
+ }
+ for (entry = 0; entry < entries; entry++) {
+ profile->kpu[kpu].cam[entry] = cam[entry];
+ profile->kpu[kpu].action[entry] = action[entry];
+ }
+ continue;
+ }
+ entries = fw_kpu->entries;
+ dev_info(rvu->dev,
+ "Loading %u entries on KPU%d\n", entries, kpu);
+
+ cam2 = (struct npc_kpu_profile_cam2 *)fw_kpu->data;
+ offset += sizeof(*fw_kpu) + fw_kpu->entries * sizeof(*cam2);
action = (struct npc_kpu_profile_action *)(fw->data + offset);
offset += fw_kpu->entries * sizeof(*action);
if (rvu->kpu_fwdata_sz < hdr_sz + offset) {
dev_warn(rvu->dev,
- "Profile size mismatch on KPU%i parsing.\n",
+ "profile size mismatch on kpu%i parsing.\n",
kpu + 1);
return -EINVAL;
}
+
+ profile->kpu[kpu].cam_entries2 = entries;
+ profile->kpu[kpu].action_entries2 = entries;
+ ret = npc_alloc_kpu_cam2_n_action2(rvu, kpu, entries);
+ if (ret) {
+ dev_warn(rvu->dev,
+ "profile entry allocation failed for kpu=%d for %d entries\n",
+ kpu, entries);
+ return -EINVAL;
+ }
+
for (entry = 0; entry < entries; entry++) {
- profile->kpu[kpu].cam[entry] = cam[entry];
- profile->kpu[kpu].action[entry] = action[entry];
+ profile->kpu[kpu].cam2[entry] = cam2[entry];
+ profile->kpu[kpu].action2[entry] = action[entry];
}
}
@@ -1853,7 +2016,10 @@ void npc_load_kpu_profile(struct rvu *rvu)
struct npc_kpu_profile_adapter *profile = &rvu->kpu;
const char *kpu_profile = rvu->kpu_pfl_name;
const struct firmware *fw = NULL;
- bool retry_fwdb = false;
+ int len, ret, fw_kpus = 0;
+ char *path;
+
+ profile->from_fs = false;
/* If user not specified profile customization */
if (!strncmp(kpu_profile, def_pfl_name, KPU_NAME_LEN))
@@ -1866,27 +2032,52 @@ void npc_load_kpu_profile(struct rvu *rvu)
* Firmware database method.
* Default KPU profile.
*/
- if (!request_firmware_direct(&fw, kpu_profile, rvu->dev)) {
- dev_info(rvu->dev, "Loading KPU profile from firmware: %s\n",
- kpu_profile);
+
+#define PDIR "kpu/"
+ len = strlen(kpu_profile) + sizeof(PDIR);
+ path = kmalloc(len, GFP_KERNEL);
+ if (!path)
+ return;
+
+ strscpy(path, PDIR, len);
+ strcat(path, kpu_profile);
+ if (!request_firmware_direct(&fw, path, rvu->dev)) {
+ dev_info(rvu->dev, "Loading KPU profile from filesystem: %s\n",
+ path);
rvu->kpu_fwdata = kzalloc(fw->size, GFP_KERNEL);
if (rvu->kpu_fwdata) {
memcpy(rvu->kpu_fwdata, fw->data, fw->size);
rvu->kpu_fwdata_sz = fw->size;
}
release_firmware(fw);
- retry_fwdb = true;
- goto program_kpu;
+ kfree(path);
+
+ ret = npc_apply_custom_kpu(rvu, profile, true, &fw_kpus);
+ kfree(rvu->kpu_fwdata);
+ rvu->kpu_fwdata = NULL;
+
+ if (ret) {
+ rvu->kpu_fwdata_sz = 0;
+ npc_prepare_default_kpu(rvu, profile);
+ dev_err(rvu->dev,
+ "Loading KPU profile from filesystem failed\n");
+ goto load_image_fwdb;
+ }
+
+ rvu->kpu.kpus = fw_kpus;
+ profile->from_fs = true;
+ return;
}
+ kfree(path);
load_image_fwdb:
/* Loading the KPU profile using firmware database */
if (npc_load_kpu_profile_fwdb(rvu, kpu_profile))
goto revert_to_default;
-program_kpu:
/* Apply profile customization if firmware was loaded. */
- if (!rvu->kpu_fwdata_sz || npc_apply_custom_kpu(rvu, profile)) {
+ if (!rvu->kpu_fwdata_sz ||
+ npc_apply_custom_kpu(rvu, profile, false, &fw_kpus)) {
/* If image from firmware filesystem fails to load or invalid
* retry with firmware database method.
*/
@@ -1900,10 +2091,6 @@ void npc_load_kpu_profile(struct rvu *rvu)
}
rvu->kpu_fwdata = NULL;
rvu->kpu_fwdata_sz = 0;
- if (retry_fwdb) {
- retry_fwdb = false;
- goto load_image_fwdb;
- }
}
dev_warn(rvu->dev,
@@ -1927,6 +2114,7 @@ void npc_load_kpu_profile(struct rvu *rvu)
static void npc_parser_profile_init(struct rvu *rvu, int blkaddr)
{
+ struct npc_kpu_profile_adapter *profile = &rvu->kpu;
struct rvu_hwinfo *hw = rvu->hw;
int num_pkinds, num_kpus, idx;
@@ -1950,7 +2138,9 @@ static void npc_parser_profile_init(struct rvu *rvu, int blkaddr)
num_pkinds = min_t(int, hw->npc_pkinds, num_pkinds);
for (idx = 0; idx < num_pkinds; idx++)
- npc_config_kpuaction(rvu, blkaddr, &rvu->kpu.ikpu[idx], 0, idx, true);
+ npc_config_kpuaction(rvu, blkaddr,
+ npc_get_ikpu_nth_entry(rvu, idx),
+ 0, idx, true);
/* Program KPU CAM and Action profiles */
num_kpus = rvu->kpu.kpus;
@@ -1958,6 +2148,11 @@ static void npc_parser_profile_init(struct rvu *rvu, int blkaddr)
for (idx = 0; idx < num_kpus; idx++)
npc_program_kpu_profile(rvu, blkaddr, idx, &rvu->kpu.kpu[idx]);
+
+ if (profile->from_fs) {
+ rvu_write64(rvu, blkaddr, NPC_AF_PKINDX_TYPE(54), 0x03);
+ rvu_write64(rvu, blkaddr, NPC_AF_PKINDX_TYPE(58), 0x03);
+ }
}
void npc_mcam_rsrcs_deinit(struct rvu *rvu)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.h
index 83c5e32e2afc..662f6693cfe9 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.h
@@ -18,4 +18,21 @@ int npc_fwdb_prfl_img_map(struct rvu *rvu, void __iomem **prfl_img_addr,
void npc_mcam_clear_bit(struct npc_mcam *mcam, u16 index);
void npc_mcam_set_bit(struct npc_mcam *mcam, u16 index);
+
+struct npc_kpu_profile_action *
+npc_get_ikpu_nth_entry(struct rvu *rvu, int n);
+
+int
+npc_get_num_kpu_cam_entries(struct rvu *rvu,
+ const struct npc_kpu_profile *kpu_pfl);
+struct npc_kpu_profile_cam *
+npc_get_kpu_cam_nth_entry(struct rvu *rvu,
+ const struct npc_kpu_profile *kpu_pfl, int n);
+
+int
+npc_get_num_kpu_action_entries(struct rvu *rvu,
+ const struct npc_kpu_profile *kpu_pfl);
+struct npc_kpu_profile_action *
+npc_get_kpu_action_nth_entry(struct rvu *rvu,
+ const struct npc_kpu_profile *kpu_pfl, int n);
#endif /* RVU_NPC_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
index 62cdc714ba57..ab89b8c6e490 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
@@ -596,6 +596,7 @@
#define NPC_AF_INTFX_KEX_CFG(a) (0x01010 | (a) << 8)
#define NPC_AF_PKINDX_ACTION0(a) (0x80000ull | (a) << 6)
#define NPC_AF_PKINDX_ACTION1(a) (0x80008ull | (a) << 6)
+#define NPC_AF_PKINDX_TYPE(a) (0x80010ull | (a) << 6)
#define NPC_AF_PKINDX_CPI_DEFX(a, b) (0x80020ull | (a) << 6 | (b) << 3)
#define NPC_AF_KPUX_ENTRYX_CAMX(a, b, c) \
(0x100000 | (a) << 14 | (b) << 6 | (c) << 3)
--
2.43.0
^ permalink raw reply related [flat|nested] 11+ messages in thread* Re: [v4,net-next,5/5] octeontx2-af: npc: Support for custom KPU profile from filesystem
2026-03-12 2:27 ` [PATCH v4 net-next 5/5] octeontx2-af: npc: Support for custom KPU profile from filesystem Ratheesh Kannoth
@ 2026-03-17 3:32 ` Jakub Kicinski
0 siblings, 0 replies; 11+ messages in thread
From: Jakub Kicinski @ 2026-03-17 3:32 UTC (permalink / raw)
To: rkannoth
Cc: Jakub Kicinski, linux-kernel, chuck.lever, jiri, netdev,
donald.hunter, saeedm, sgoutham, edumazet, davem, matttbe, horms,
cjubran, pabeni, shshitrit
This is an AI-generated review of your patch. The human sending this
email says "review on patch 3 looks legit, so sending this along
even tho not so sure about this one".
For local reproduction steps see https://netdev-ai.bots.linux.dev/ai-local.html
---
octeontx2-af: npc: Support for custom KPU profile from filesystem
This commit provides a mechanism to load custom KPU (Key Parse Unit)
profiles from the filesystem at module load time, avoiding the need to
flash updated firmware on deployed devices.
> diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c
> index 8dad272fd069..c8c09a91b13f 100644
> --- a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c
> +++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c
[ ... ]
> @@ -666,7 +672,8 @@ void npc_cn20k_parser_profile_init(struct rvu *rvu, int blkaddr)
> num_pkinds = min_t(int, hw->npc_pkinds, num_pkinds);
>
> for (idx = 0; idx < num_pkinds; idx++)
> - npc_config_kpmaction(rvu, blkaddr, &rvu->kpu.ikpu[idx],
> + npc_config_kpmaction(rvu, blkaddr,
> + npc_get_ikpu_nth_entry(rvu, idx),
> 0, idx, true);
When a filesystem-loaded profile is used on cn20k (from_fs=true),
npc_get_ikpu_nth_entry() returns &profile->ikpu2[idx]. However, ikpu2
is never allocated for the cn20k path.
The allocation of ikpu2 happens inside npc_apply_custom_kpu() in the
from_fs block, but that block is never reached for cn20k because
npc_apply_custom_kpu() returns early via npc_cn20k_apply_custom_kpu()
before reaching the ikpu2 allocation:
static int npc_apply_custom_kpu(struct rvu *rvu,
struct npc_kpu_profile_adapter *profile,
bool from_fs, int *fw_kpus)
{
...
if (is_cn20k(rvu->pdev))
return npc_cn20k_apply_custom_kpu(rvu, profile);
if (from_fs) {
profile->ikpu2 = devm_kcalloc(rvu->dev, 1,
sizeof(ikpu_action_entries),
GFP_KERNEL);
...
}
...
}
However, npc_load_kpu_profile() unconditionally sets profile->from_fs =
true after npc_apply_custom_kpu() returns success.
Does this code dereference a NULL-offset pointer? The resulting
&NULL[idx] is passed to npc_config_kpmaction() which dereferences it
(kpuaction->errlev), which would cause a kernel crash.
This same issue affects cam2 and action2 via npc_get_kpu_cam_nth_entry()
and npc_get_kpu_action_nth_entry().
>
> /* Program KPM CAM and Action profiles */
[ ... ]
> diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
> index 352dc5f1d5b9..e348cdd375eb 100644
> --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
> +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
[ ... ]
> @@ -1731,32 +1837,89 @@ static int npc_apply_custom_kpu(struct rvu *rvu,
> return -EINVAL;
> }
>
> + *fw_kpus = fw->kpus;
> +
> + sfw = devm_kcalloc(rvu->dev, 1, sizeof(*sfw), GFP_KERNEL);
> + if (!sfw)
> + return -ENOMEM;
> +
> + memcpy(sfw, fw, sizeof(*sfw));
> +
> profile->custom = 1;
> - profile->name = fw->name;
> + profile->name = sfw->name;
> profile->version = le64_to_cpu(fw->version);
> - profile->mcam_kex_prfl.mkex = &fw->mkex;
> - profile->lt_def = &fw->lt_def;
> + profile->mcam_kex_prfl.mkex = &sfw->mkex;
> + profile->lt_def = &sfw->lt_def;
> +
> + /* Binary blob contains ikpu actions entries at start of data[0] */
> + if (from_fs) {
> + profile->ikpu2 = devm_kcalloc(rvu->dev, 1,
> + sizeof(ikpu_action_entries),
> + GFP_KERNEL);
> + if (!profile->ikpu2)
> + return -ENOMEM;
> +
> + action = (struct npc_kpu_profile_action *)(fw->data + offset);
> +
> + if (rvu->kpu_fwdata_sz < hdr_sz + sizeof(ikpu_action_entries))
> + return -ENOMEM;
> +
> + memcpy((void *)profile->ikpu2, action, sizeof(ikpu_action_entries));
> + offset += sizeof(ikpu_action_entries);
> + }
> +
> for (kpu = 0; kpu < fw->kpus; kpu++) {
> fw_kpu = (struct npc_kpu_fwdata *)(fw->data + offset);
> - if (fw_kpu->entries > KPU_MAX_CST_ENT)
> - dev_warn(rvu->dev,
> - "Too many custom entries on KPU%d: %d > %d\n",
> - kpu, fw_kpu->entries, KPU_MAX_CST_ENT);
> - entries = min(fw_kpu->entries, KPU_MAX_CST_ENT);
> - cam = (struct npc_kpu_profile_cam *)fw_kpu->data;
> - offset += sizeof(*fw_kpu) + fw_kpu->entries * sizeof(*cam);
> + if (!from_fs) {
> + if (fw_kpu->entries > KPU_MAX_CST_ENT)
> + dev_warn(rvu->dev,
> + "Too many custom entries on KPU%d: %d > %d\n",
> + kpu, fw_kpu->entries, KPU_MAX_CST_ENT);
> + entries = min(fw_kpu->entries, KPU_MAX_CST_ENT);
> + cam = (struct npc_kpu_profile_cam *)fw_kpu->data;
> + offset += sizeof(*fw_kpu) + fw_kpu->entries * sizeof(*cam);
> + action = (struct npc_kpu_profile_action *)(fw->data + offset);
> + offset += fw_kpu->entries * sizeof(*action);
> + if (rvu->kpu_fwdata_sz < hdr_sz + offset) {
> + dev_warn(rvu->dev,
> + "Profile size mismatch on KPU%i parsing.\n",
> + kpu + 1);
> + return -EINVAL;
> + }
> + for (entry = 0; entry < entries; entry++) {
> + profile->kpu[kpu].cam[entry] = cam[entry];
> + profile->kpu[kpu].action[entry] = action[entry];
> + }
> + continue;
> + }
> + entries = fw_kpu->entries;
> + dev_info(rvu->dev,
> + "Loading %u entries on KPU%d\n", entries, kpu);
> +
> + cam2 = (struct npc_kpu_profile_cam2 *)fw_kpu->data;
> + offset += sizeof(*fw_kpu) + fw_kpu->entries * sizeof(*cam2);
> action = (struct npc_kpu_profile_action *)(fw->data + offset);
> offset += fw_kpu->entries * sizeof(*action);
> if (rvu->kpu_fwdata_sz < hdr_sz + offset) {
> dev_warn(rvu->dev,
> - "Profile size mismatch on KPU%i parsing.\n",
> + "profile size mismatch on kpu%i parsing.\n",
> kpu + 1);
> return -EINVAL;
> }
> +
> + profile->kpu[kpu].cam_entries2 = entries;
> + profile->kpu[kpu].action_entries2 = entries;
> + ret = npc_alloc_kpu_cam2_n_action2(rvu, kpu, entries);
> + if (ret) {
> + dev_warn(rvu->dev,
> + "profile entry allocation failed for kpu=%d for %d entries\n",
> + kpu, entries);
> + return -EINVAL;
> + }
> +
> for (entry = 0; entry < entries; entry++) {
> - profile->kpu[kpu].cam[entry] = cam[entry];
> - profile->kpu[kpu].action[entry] = action[entry];
> + profile->kpu[kpu].cam2[entry] = cam2[entry];
> + profile->kpu[kpu].action2[entry] = action[entry];
> }
> }
This is a concern raised by Simon Horman during review that was
acknowledged but not addressed in v4.
The loop variable 'entry' is declared as u16 in npc_apply_custom_kpu():
u16 kpu, entry;
while 'entries' is an int:
entries = fw_kpu->entries;
In the from_fs path, 'entries' is read directly from the firmware blob
without bounds checking. If a corrupt or malicious firmware file
specifies fw_kpu->entries > 65535, the u16 variable wraps around at
65536:
for (entry = 0; entry < entries; entry++)
When entry reaches 65535, incrementing it produces 0, which is still
less than entries, creating an infinite loop that hangs the kernel.
Should the code cap entries in the from_fs path or use an int-sized loop
variable? The author acknowledged this concern with 'ACK' in v3 review
discussion, and Simon emphasized that "the kernel should not rely on
filesystem data being well-formed."
>
> return 0;
[ ... ]
> diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c
> @@ -521,13 +521,17 @@ npc_program_single_kpm_profile(struct rvu *rvu, int blkaddr,
[ ... ]
> @@ -536,16 +540,18 @@ npc_program_single_kpm_profile(struct rvu *rvu, int blkaddr,
> max_entries = rvu->hw->npc_kpu_entries / 2;
> entry = start_entry;
> /* Program CAM match entries for previous kpm extracted data */
> - num_entries = min_t(int, profile->cam_entries, max_entries);
> + num_entries = min_t(int, num_cam_entries, max_entries);
> for (idx = 0; entry < num_entries + start_entry; entry++, idx++)
> - npc_config_kpmcam(rvu, blkaddr, &profile->cam[idx],
> + npc_config_kpmcam(rvu, blkaddr,
> + npc_get_kpu_cam_nth_entry(rvu, profile, idx),
> kpm, entry);
>
> entry = start_entry;
> /* Program this kpm's actions */
> - num_entries = min_t(int, profile->action_entries, max_entries);
> + num_entries = min_t(int, num_action_entries, max_entries);
> for (idx = 0; entry < num_entries + start_entry; entry++, idx++)
> - npc_config_kpmaction(rvu, blkaddr, &profile->action[idx],
> + npc_config_kpmaction(rvu, blkaddr,
> + npc_get_kpu_action_nth_entry(rvu, profile, idx),
> kpm, entry, false);
> }
>
> @@ -615,6 +621,12 @@ npc_program_kpm_profile(struct rvu *rvu, int blkaddr,
> const struct npc_kpu_profile *profile1,
> const struct npc_kpu_profile *profile2)
> {
[ ... ]
> + /* Program the first KPM profile */
> + npc_program_single_kpm_profile(rvu, blkaddr, idx,
> + 0, profile1);
> +
> + /* Program the second KPM profile */
> + start_entry = profile->cam_entries;
> + npc_program_single_kpm_profile(rvu, blkaddr, idx,
> + start_entry, profile2);
> +
> + total_cam_entries = profile->cam_entries + profile2->cam_entries;
> + total_action_entries = profile->action_entries + profile2->action_entries;
> + npc_enable_kpm_entry(rvu, blkaddr, idx, 0,
> + total_cam_entries, total_action_entries);
> +
> + val = profile->cam_entries;
> + rvu_write64(rvu, blkaddr, NPC_AF_KPMX_PASS2_OFFSET(idx), val);
> }
Looking at npc_program_kpm_profile(), it uses profile->cam_entries
directly in four places instead of calling npc_get_num_kpu_cam_entries().
When profile->from_fs is true (filesystem-loaded KPU profile), the
accessor returns cam_entries2, while the raw field cam_entries retains
its default value from npc_prepare_default_kpu().
Does this cause the start_entry for the second profile to be based on
the wrong count, leading profile2 entries to overlap or be offset
incorrectly? Would total_cam_entries and total_action_entries passed to
npc_enable_kpm_entry() be wrong, enabling the wrong set of entries? And
would NPC_AF_KPMX_PASS2_OFFSET be set incorrectly?
The callee npc_program_single_kpm_profile() was correctly updated to use
accessors, but npc_program_kpm_profile() was not.
^ permalink raw reply [flat|nested] 11+ messages in thread