Merge tag 'nf-23-11-15' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf
Pablo Neira Ayuso says:
====================
Netfilter fixes for net
The following patchset contains Netfilter fixes for net:
1) Remove unused variable causing compilation warning in nft_set_rbtree,
from Yang Li. This unused variable is a left over from previous
merge window.
2) Possible return of uninitialized in nf_conntrack_bridge, from
Linkui Xiao. This is there since nf_conntrack_bridge is available.
3) Fix incorrect pointer math in nft_byteorder, from Dan Carpenter.
Problem has been there since 2016.
4) Fix bogus error in destroy set element command. Problem is there
since this new destroy command was added.
5) Fix race condition in ipset between swap and destroy commands and
add/del/test control plane. This problem is there since ipset was
merged.
6) Split async and sync catchall GC in two function to fix unsafe
iteration over RCU. This is a fix-for-fix that was included in
the previous pull request.
* tag 'nf-23-11-15' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf:
netfilter: nf_tables: split async and sync catchall in two functions
netfilter: ipset: fix race condition between swap/destroy and kernel side add/del/test
netfilter: nf_tables: bogus ENOENT when destroying element which does not exist
netfilter: nf_tables: fix pointer math issue in nft_byteorder_eval()
netfilter: nf_conntrack_bridge: initialize err to 0
netfilter: nft_set_rbtree: Remove unused variable nft_net
====================
Link: https://lore.kernel.org/r/20231115184514.8965-1-pablo@netfilter.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
index 9f6a5cc..d14d123 100644
--- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml
+++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
@@ -275,12 +275,12 @@
properties:
rx-internal-delay-ps:
description:
- RGMII Receive Clock Delay defined in pico seconds.This is used for
+ RGMII Receive Clock Delay defined in pico seconds. This is used for
controllers that have configurable RX internal delays. If this
property is present then the MAC applies the RX delay.
tx-internal-delay-ps:
description:
- RGMII Transmit Clock Delay defined in pico seconds.This is used for
+ RGMII Transmit Clock Delay defined in pico seconds. This is used for
controllers that have configurable TX internal delays. If this
property is present then the MAC applies the TX delay.
diff --git a/drivers/net/ethernet/amd/pds_core/adminq.c b/drivers/net/ethernet/amd/pds_core/adminq.c
index 045fe13..5beadab 100644
--- a/drivers/net/ethernet/amd/pds_core/adminq.c
+++ b/drivers/net/ethernet/amd/pds_core/adminq.c
@@ -146,7 +146,7 @@ irqreturn_t pdsc_adminq_isr(int irq, void *data)
}
queue_work(pdsc->wq, &qcq->work);
- pds_core_intr_mask(&pdsc->intr_ctrl[irq], PDS_CORE_INTR_MASK_CLEAR);
+ pds_core_intr_mask(&pdsc->intr_ctrl[qcq->intx], PDS_CORE_INTR_MASK_CLEAR);
return IRQ_HANDLED;
}
diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h
index f3a7ded..e35d3e7 100644
--- a/drivers/net/ethernet/amd/pds_core/core.h
+++ b/drivers/net/ethernet/amd/pds_core/core.h
@@ -15,7 +15,7 @@
#define PDSC_DRV_DESCRIPTION "AMD/Pensando Core Driver"
#define PDSC_WATCHDOG_SECS 5
-#define PDSC_QUEUE_NAME_MAX_SZ 32
+#define PDSC_QUEUE_NAME_MAX_SZ 16
#define PDSC_ADMINQ_MIN_LENGTH 16 /* must be a power of two */
#define PDSC_NOTIFYQ_LENGTH 64 /* must be a power of two */
#define PDSC_TEARDOWN_RECOVERY false
diff --git a/drivers/net/ethernet/amd/pds_core/dev.c b/drivers/net/ethernet/amd/pds_core/dev.c
index 7c1b965..31940b8 100644
--- a/drivers/net/ethernet/amd/pds_core/dev.c
+++ b/drivers/net/ethernet/amd/pds_core/dev.c
@@ -261,10 +261,14 @@ static int pdsc_identify(struct pdsc *pdsc)
struct pds_core_drv_identity drv = {};
size_t sz;
int err;
+ int n;
drv.drv_type = cpu_to_le32(PDS_DRIVER_LINUX);
- snprintf(drv.driver_ver_str, sizeof(drv.driver_ver_str),
- "%s %s", PDS_CORE_DRV_NAME, utsname()->release);
+ /* Catching the return quiets a Wformat-truncation complaint */
+ n = snprintf(drv.driver_ver_str, sizeof(drv.driver_ver_str),
+ "%s %s", PDS_CORE_DRV_NAME, utsname()->release);
+ if (n > sizeof(drv.driver_ver_str))
+ dev_dbg(pdsc->dev, "release name truncated, don't care\n");
/* Next let's get some info about the device
* We use the devcmd_lock at this level in order to
diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c
index 57f88c8..e9948ea 100644
--- a/drivers/net/ethernet/amd/pds_core/devlink.c
+++ b/drivers/net/ethernet/amd/pds_core/devlink.c
@@ -104,7 +104,7 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
struct pds_core_fw_list_info fw_list;
struct pdsc *pdsc = devlink_priv(dl);
union pds_core_dev_comp comp;
- char buf[16];
+ char buf[32];
int listlen;
int err;
int i;
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 1dee273..48b6191 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -6889,7 +6889,7 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget)
desc_idx, *post_ptr);
drop_it_no_recycle:
/* Other statistics kept track of by card. */
- tp->rx_dropped++;
+ tnapi->rx_dropped++;
goto next_pkt;
}
@@ -7918,8 +7918,10 @@ static int tg3_tso_bug(struct tg3 *tp, struct tg3_napi *tnapi,
segs = skb_gso_segment(skb, tp->dev->features &
~(NETIF_F_TSO | NETIF_F_TSO6));
- if (IS_ERR(segs) || !segs)
+ if (IS_ERR(segs) || !segs) {
+ tnapi->tx_dropped++;
goto tg3_tso_bug_end;
+ }
skb_list_walk_safe(segs, seg, next) {
skb_mark_not_on_list(seg);
@@ -8190,7 +8192,7 @@ static netdev_tx_t __tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
drop:
dev_kfree_skb_any(skb);
drop_nofree:
- tp->tx_dropped++;
+ tnapi->tx_dropped++;
return NETDEV_TX_OK;
}
@@ -9405,7 +9407,7 @@ static void __tg3_set_rx_mode(struct net_device *);
/* tp->lock is held. */
static int tg3_halt(struct tg3 *tp, int kind, bool silent)
{
- int err;
+ int err, i;
tg3_stop_fw(tp);
@@ -9426,6 +9428,13 @@ static int tg3_halt(struct tg3 *tp, int kind, bool silent)
/* And make sure the next sample is new data */
memset(tp->hw_stats, 0, sizeof(struct tg3_hw_stats));
+
+ for (i = 0; i < TG3_IRQ_MAX_VECS; ++i) {
+ struct tg3_napi *tnapi = &tp->napi[i];
+
+ tnapi->rx_dropped = 0;
+ tnapi->tx_dropped = 0;
+ }
}
return err;
@@ -11975,6 +11984,9 @@ static void tg3_get_nstats(struct tg3 *tp, struct rtnl_link_stats64 *stats)
{
struct rtnl_link_stats64 *old_stats = &tp->net_stats_prev;
struct tg3_hw_stats *hw_stats = tp->hw_stats;
+ unsigned long rx_dropped;
+ unsigned long tx_dropped;
+ int i;
stats->rx_packets = old_stats->rx_packets +
get_stat64(&hw_stats->rx_ucast_packets) +
@@ -12021,8 +12033,26 @@ static void tg3_get_nstats(struct tg3 *tp, struct rtnl_link_stats64 *stats)
stats->rx_missed_errors = old_stats->rx_missed_errors +
get_stat64(&hw_stats->rx_discards);
- stats->rx_dropped = tp->rx_dropped;
- stats->tx_dropped = tp->tx_dropped;
+ /* Aggregate per-queue counters. The per-queue counters are updated
+ * by a single writer, race-free. The result computed by this loop
+ * might not be 100% accurate (counters can be updated in the middle of
+ * the loop) but the next tg3_get_nstats() will recompute the current
+ * value so it is acceptable.
+ *
+ * Note that these counters wrap around at 4G on 32bit machines.
+ */
+ rx_dropped = (unsigned long)(old_stats->rx_dropped);
+ tx_dropped = (unsigned long)(old_stats->tx_dropped);
+
+ for (i = 0; i < tp->irq_cnt; i++) {
+ struct tg3_napi *tnapi = &tp->napi[i];
+
+ rx_dropped += tnapi->rx_dropped;
+ tx_dropped += tnapi->tx_dropped;
+ }
+
+ stats->rx_dropped = rx_dropped;
+ stats->tx_dropped = tx_dropped;
}
static int tg3_get_regs_len(struct net_device *dev)
diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
index ae5c01b..5016475 100644
--- a/drivers/net/ethernet/broadcom/tg3.h
+++ b/drivers/net/ethernet/broadcom/tg3.h
@@ -3018,6 +3018,7 @@ struct tg3_napi {
u16 *rx_rcb_prod_idx;
struct tg3_rx_prodring_set prodring;
struct tg3_rx_buffer_desc *rx_rcb;
+ unsigned long rx_dropped;
u32 tx_prod ____cacheline_aligned;
u32 tx_cons;
@@ -3026,6 +3027,7 @@ struct tg3_napi {
u32 prodmbox;
struct tg3_tx_buffer_desc *tx_ring;
struct tg3_tx_ring_info *tx_buffers;
+ unsigned long tx_dropped;
dma_addr_t status_mapping;
dma_addr_t rx_rcb_mapping;
@@ -3220,8 +3222,6 @@ struct tg3 {
/* begin "everything else" cacheline(s) section */
- unsigned long rx_dropped;
- unsigned long tx_dropped;
struct rtnl_link_stats64 net_stats_prev;
struct tg3_ethtool_stats estats_prev;
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 276f996..2d42e73 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -254,10 +254,13 @@ static int gve_napi_poll(struct napi_struct *napi, int budget)
if (block->tx) {
if (block->tx->q_num < priv->tx_cfg.num_queues)
reschedule |= gve_tx_poll(block, budget);
- else
+ else if (budget)
reschedule |= gve_xdp_poll(block, budget);
}
+ if (!budget)
+ return 0;
+
if (block->rx) {
work_done = gve_rx_poll(block, budget);
reschedule |= work_done == budget;
@@ -298,6 +301,9 @@ static int gve_napi_poll_dqo(struct napi_struct *napi, int budget)
if (block->tx)
reschedule |= gve_tx_poll_dqo(block, /*do_clean=*/true);
+ if (!budget)
+ return 0;
+
if (block->rx) {
work_done = gve_rx_poll_dqo(block, budget);
reschedule |= work_done == budget;
diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c
index e84a066..7365534 100644
--- a/drivers/net/ethernet/google/gve/gve_rx.c
+++ b/drivers/net/ethernet/google/gve/gve_rx.c
@@ -1007,10 +1007,6 @@ int gve_rx_poll(struct gve_notify_block *block, int budget)
feat = block->napi.dev->features;
- /* If budget is 0, do all the work */
- if (budget == 0)
- budget = INT_MAX;
-
if (budget > 0)
work_done = gve_clean_rx_done(rx, budget, feat);
diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c
index 6957a86..9f6ffc4 100644
--- a/drivers/net/ethernet/google/gve/gve_tx.c
+++ b/drivers/net/ethernet/google/gve/gve_tx.c
@@ -925,10 +925,6 @@ bool gve_xdp_poll(struct gve_notify_block *block, int budget)
bool repoll;
u32 to_do;
- /* If budget is 0, do all the work */
- if (budget == 0)
- budget = INT_MAX;
-
/* Find out how much work there is to be done */
nic_done = gve_tx_load_event_counter(priv, tx);
to_do = min_t(u32, (nic_done - tx->done), budget);
diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c
index cfb1580..8b7504a9 100644
--- a/drivers/net/ethernet/intel/ice/ice_ddp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ddp.c
@@ -1479,14 +1479,14 @@ ice_post_dwnld_pkg_actions(struct ice_hw *hw)
}
/**
- * ice_download_pkg
+ * ice_download_pkg_with_sig_seg
* @hw: pointer to the hardware structure
* @pkg_hdr: pointer to package header
*
* Handles the download of a complete package.
*/
static enum ice_ddp_state
-ice_download_pkg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr)
+ice_download_pkg_with_sig_seg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr)
{
enum ice_aq_err aq_err = hw->adminq.sq_last_status;
enum ice_ddp_state state = ICE_DDP_PKG_ERR;
@@ -1519,6 +1519,103 @@ ice_download_pkg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr)
state = ice_post_dwnld_pkg_actions(hw);
ice_release_global_cfg_lock(hw);
+
+ return state;
+}
+
+/**
+ * ice_dwnld_cfg_bufs
+ * @hw: pointer to the hardware structure
+ * @bufs: pointer to an array of buffers
+ * @count: the number of buffers in the array
+ *
+ * Obtains global config lock and downloads the package configuration buffers
+ * to the firmware.
+ */
+static enum ice_ddp_state
+ice_dwnld_cfg_bufs(struct ice_hw *hw, struct ice_buf *bufs, u32 count)
+{
+ enum ice_ddp_state state;
+ struct ice_buf_hdr *bh;
+ int status;
+
+ if (!bufs || !count)
+ return ICE_DDP_PKG_ERR;
+
+ /* If the first buffer's first section has its metadata bit set
+ * then there are no buffers to be downloaded, and the operation is
+ * considered a success.
+ */
+ bh = (struct ice_buf_hdr *)bufs;
+ if (le32_to_cpu(bh->section_entry[0].type) & ICE_METADATA_BUF)
+ return ICE_DDP_PKG_SUCCESS;
+
+ status = ice_acquire_global_cfg_lock(hw, ICE_RES_WRITE);
+ if (status) {
+ if (status == -EALREADY)
+ return ICE_DDP_PKG_ALREADY_LOADED;
+ return ice_map_aq_err_to_ddp_state(hw->adminq.sq_last_status);
+ }
+
+ state = ice_dwnld_cfg_bufs_no_lock(hw, bufs, 0, count, true);
+ if (!state)
+ state = ice_post_dwnld_pkg_actions(hw);
+
+ ice_release_global_cfg_lock(hw);
+
+ return state;
+}
+
+/**
+ * ice_download_pkg_without_sig_seg
+ * @hw: pointer to the hardware structure
+ * @ice_seg: pointer to the segment of the package to be downloaded
+ *
+ * Handles the download of a complete package without signature segment.
+ */
+static enum ice_ddp_state
+ice_download_pkg_without_sig_seg(struct ice_hw *hw, struct ice_seg *ice_seg)
+{
+ struct ice_buf_table *ice_buf_tbl;
+
+ ice_debug(hw, ICE_DBG_PKG, "Segment format version: %d.%d.%d.%d\n",
+ ice_seg->hdr.seg_format_ver.major,
+ ice_seg->hdr.seg_format_ver.minor,
+ ice_seg->hdr.seg_format_ver.update,
+ ice_seg->hdr.seg_format_ver.draft);
+
+ ice_debug(hw, ICE_DBG_PKG, "Seg: type 0x%X, size %d, name %s\n",
+ le32_to_cpu(ice_seg->hdr.seg_type),
+ le32_to_cpu(ice_seg->hdr.seg_size), ice_seg->hdr.seg_id);
+
+ ice_buf_tbl = ice_find_buf_table(ice_seg);
+
+ ice_debug(hw, ICE_DBG_PKG, "Seg buf count: %d\n",
+ le32_to_cpu(ice_buf_tbl->buf_count));
+
+ return ice_dwnld_cfg_bufs(hw, ice_buf_tbl->buf_array,
+ le32_to_cpu(ice_buf_tbl->buf_count));
+}
+
+/**
+ * ice_download_pkg
+ * @hw: pointer to the hardware structure
+ * @pkg_hdr: pointer to package header
+ * @ice_seg: pointer to the segment of the package to be downloaded
+ *
+ * Handles the download of a complete package.
+ */
+static enum ice_ddp_state
+ice_download_pkg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr,
+ struct ice_seg *ice_seg)
+{
+ enum ice_ddp_state state;
+
+ if (hw->pkg_has_signing_seg)
+ state = ice_download_pkg_with_sig_seg(hw, pkg_hdr);
+ else
+ state = ice_download_pkg_without_sig_seg(hw, ice_seg);
+
ice_post_pkg_dwnld_vlan_mode_cfg(hw);
return state;
@@ -2083,7 +2180,7 @@ enum ice_ddp_state ice_init_pkg(struct ice_hw *hw, u8 *buf, u32 len)
/* initialize package hints and then download package */
ice_init_pkg_hints(hw, seg);
- state = ice_download_pkg(hw, pkg);
+ state = ice_download_pkg(hw, pkg, seg);
if (state == ICE_DDP_PKG_ALREADY_LOADED) {
ice_debug(hw, ICE_DBG_INIT,
"package previously loaded - no work.\n");
diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c
index 835c419..86b180c 100644
--- a/drivers/net/ethernet/intel/ice/ice_dpll.c
+++ b/drivers/net/ethernet/intel/ice/ice_dpll.c
@@ -815,12 +815,6 @@ ice_dpll_input_prio_set(const struct dpll_pin *pin, void *pin_priv,
struct ice_pf *pf = d->pf;
int ret;
- if (prio > ICE_DPLL_PRIO_MAX) {
- NL_SET_ERR_MSG_FMT(extack, "prio out of supported range 0-%d",
- ICE_DPLL_PRIO_MAX);
- return -EINVAL;
- }
-
mutex_lock(&pf->dplls.lock);
ret = ice_dpll_hw_input_prio_set(pf, d, p, prio, extack);
mutex_unlock(&pf->dplls.lock);
@@ -1756,6 +1750,7 @@ ice_dpll_init_dpll(struct ice_pf *pf, struct ice_dpll *d, bool cgu,
}
d->pf = pf;
if (cgu) {
+ ice_dpll_update_state(pf, d, true);
ret = dpll_device_register(d->dpll, type, &ice_dpll_ops, d);
if (ret) {
dpll_device_put(d->dpll);
@@ -1796,8 +1791,6 @@ static int ice_dpll_init_worker(struct ice_pf *pf)
struct ice_dplls *d = &pf->dplls;
struct kthread_worker *kworker;
- ice_dpll_update_state(pf, &d->eec, true);
- ice_dpll_update_state(pf, &d->pps, true);
kthread_init_delayed_work(&d->work, ice_dpll_periodic_work);
kworker = kthread_create_worker(0, "ice-dplls-%s",
dev_name(ice_pf_to_dev(pf)));
@@ -1830,6 +1823,7 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf,
int num_pins, i, ret = -EINVAL;
struct ice_hw *hw = &pf->hw;
struct ice_dpll_pin *pins;
+ unsigned long caps;
u8 freq_supp_num;
bool input;
@@ -1849,6 +1843,7 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf,
}
for (i = 0; i < num_pins; i++) {
+ caps = 0;
pins[i].idx = i;
pins[i].prop.board_label = ice_cgu_get_pin_name(hw, i, input);
pins[i].prop.type = ice_cgu_get_pin_type(hw, i, input);
@@ -1861,8 +1856,8 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf,
&dp->input_prio[i]);
if (ret)
return ret;
- pins[i].prop.capabilities |=
- DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE;
+ caps |= (DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE |
+ DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE);
pins[i].prop.phase_range.min =
pf->dplls.input_phase_adj_max;
pins[i].prop.phase_range.max =
@@ -1872,9 +1867,11 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf,
pf->dplls.output_phase_adj_max;
pins[i].prop.phase_range.max =
-pf->dplls.output_phase_adj_max;
+ ret = ice_cgu_get_output_pin_state_caps(hw, i, &caps);
+ if (ret)
+ return ret;
}
- pins[i].prop.capabilities |=
- DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE;
+ pins[i].prop.capabilities = caps;
ret = ice_dpll_pin_state_update(pf, &pins[i], pin_type, NULL);
if (ret)
return ret;
diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.h b/drivers/net/ethernet/intel/ice/ice_dpll.h
index bb32b6d..93172e9 100644
--- a/drivers/net/ethernet/intel/ice/ice_dpll.h
+++ b/drivers/net/ethernet/intel/ice/ice_dpll.h
@@ -6,7 +6,6 @@
#include "ice.h"
-#define ICE_DPLL_PRIO_MAX 0xF
#define ICE_DPLL_RCLK_NUM_MAX 4
/** ice_dpll_pin - store info about pins
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index 6d57390..a00b55e 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -3961,3 +3961,57 @@ int ice_get_cgu_rclk_pin_info(struct ice_hw *hw, u8 *base_idx, u8 *pin_num)
return ret;
}
+
+/**
+ * ice_cgu_get_output_pin_state_caps - get output pin state capabilities
+ * @hw: pointer to the hw struct
+ * @pin_id: id of a pin
+ * @caps: capabilities to modify
+ *
+ * Return:
+ * * 0 - success, state capabilities were modified
+ * * negative - failure, capabilities were not modified
+ */
+int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id,
+ unsigned long *caps)
+{
+ bool can_change = true;
+
+ switch (hw->device_id) {
+ case ICE_DEV_ID_E810C_SFP:
+ if (pin_id == ZL_OUT2 || pin_id == ZL_OUT3)
+ can_change = false;
+ break;
+ case ICE_DEV_ID_E810C_QSFP:
+ if (pin_id == ZL_OUT2 || pin_id == ZL_OUT3 || pin_id == ZL_OUT4)
+ can_change = false;
+ break;
+ case ICE_DEV_ID_E823L_10G_BASE_T:
+ case ICE_DEV_ID_E823L_1GBE:
+ case ICE_DEV_ID_E823L_BACKPLANE:
+ case ICE_DEV_ID_E823L_QSFP:
+ case ICE_DEV_ID_E823L_SFP:
+ case ICE_DEV_ID_E823C_10G_BASE_T:
+ case ICE_DEV_ID_E823C_BACKPLANE:
+ case ICE_DEV_ID_E823C_QSFP:
+ case ICE_DEV_ID_E823C_SFP:
+ case ICE_DEV_ID_E823C_SGMII:
+ if (hw->cgu_part_number ==
+ ICE_AQC_GET_LINK_TOPO_NODE_NR_ZL30632_80032 &&
+ pin_id == ZL_OUT2)
+ can_change = false;
+ else if (hw->cgu_part_number ==
+ ICE_AQC_GET_LINK_TOPO_NODE_NR_SI5383_5384 &&
+ pin_id == SI_OUT1)
+ can_change = false;
+ break;
+ default:
+ return -EINVAL;
+ }
+ if (can_change)
+ *caps |= DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE;
+ else
+ *caps &= ~DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE;
+
+ return 0;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index 36aeeef..cf76701 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -282,6 +282,8 @@ int ice_get_cgu_state(struct ice_hw *hw, u8 dpll_idx,
int ice_get_cgu_rclk_pin_info(struct ice_hw *hw, u8 *base_idx, u8 *pin_num);
void ice_ptp_init_phy_model(struct ice_hw *hw);
+int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id,
+ unsigned long *caps);
#define PFTSYN_SEM_BYTES 4
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index bb11e64..af3928e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -177,6 +177,8 @@ static void mlx5e_ptpsq_mark_ts_cqes_undelivered(struct mlx5e_ptpsq *ptpsq,
static void mlx5e_ptp_handle_ts_cqe(struct mlx5e_ptpsq *ptpsq,
struct mlx5_cqe64 *cqe,
+ u8 *md_buff,
+ u8 *md_buff_sz,
int budget)
{
struct mlx5e_ptp_port_ts_cqe_list *pending_cqe_list = ptpsq->ts_cqe_pending_list;
@@ -211,19 +213,24 @@ static void mlx5e_ptp_handle_ts_cqe(struct mlx5e_ptpsq *ptpsq,
mlx5e_ptpsq_mark_ts_cqes_undelivered(ptpsq, hwtstamp);
out:
napi_consume_skb(skb, budget);
- mlx5e_ptp_metadata_fifo_push(&ptpsq->metadata_freelist, metadata_id);
+ md_buff[*md_buff_sz++] = metadata_id;
if (unlikely(mlx5e_ptp_metadata_map_unhealthy(&ptpsq->metadata_map)) &&
!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state))
queue_work(ptpsq->txqsq.priv->wq, &ptpsq->report_unhealthy_work);
}
-static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int budget)
+static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int napi_budget)
{
struct mlx5e_ptpsq *ptpsq = container_of(cq, struct mlx5e_ptpsq, ts_cq);
- struct mlx5_cqwq *cqwq = &cq->wq;
+ int budget = min(napi_budget, MLX5E_TX_CQ_POLL_BUDGET);
+ u8 metadata_buff[MLX5E_TX_CQ_POLL_BUDGET];
+ u8 metadata_buff_sz = 0;
+ struct mlx5_cqwq *cqwq;
struct mlx5_cqe64 *cqe;
int work_done = 0;
+ cqwq = &cq->wq;
+
if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &ptpsq->txqsq.state)))
return false;
@@ -234,7 +241,8 @@ static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int budget)
do {
mlx5_cqwq_pop(cqwq);
- mlx5e_ptp_handle_ts_cqe(ptpsq, cqe, budget);
+ mlx5e_ptp_handle_ts_cqe(ptpsq, cqe,
+ metadata_buff, &metadata_buff_sz, napi_budget);
} while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(cqwq)));
mlx5_cqwq_update_db_record(cqwq);
@@ -242,6 +250,10 @@ static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int budget)
/* ensure cq space is freed before enabling more cqes */
wmb();
+ while (metadata_buff_sz > 0)
+ mlx5e_ptp_metadata_fifo_push(&ptpsq->metadata_freelist,
+ metadata_buff[--metadata_buff_sz]);
+
mlx5e_txqsq_wake(&ptpsq->txqsq);
return work_done == budget;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
index fea8c0a..4358798 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
@@ -492,11 +492,11 @@ static int mlx5e_rx_reporter_dump(struct devlink_health_reporter *reporter,
void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq)
{
- char icosq_str[MLX5E_REPORTER_PER_Q_MAX_LEN] = {};
char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN];
struct mlx5e_icosq *icosq = rq->icosq;
struct mlx5e_priv *priv = rq->priv;
struct mlx5e_err_ctx err_ctx = {};
+ char icosq_str[32] = {};
err_ctx.ctx = rq;
err_ctx.recover = mlx5e_rx_reporter_timeout_recover;
@@ -505,7 +505,7 @@ void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq)
if (icosq)
snprintf(icosq_str, sizeof(icosq_str), "ICOSQ: 0x%x, ", icosq->sqn);
snprintf(err_str, sizeof(err_str),
- "RX timeout on channel: %d, %sRQ: 0x%x, CQ: 0x%x",
+ "RX timeout on channel: %d, %s RQ: 0x%x, CQ: 0x%x",
rq->ix, icosq_str, rq->rqn, rq->cq.mcq.cqn);
mlx5e_health_report(priv, priv->rx_reporter, err_str, &err_ctx);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index 00a04fd..668da5c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -300,9 +300,6 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
if (err)
goto destroy_neigh_entry;
- e->encap_size = ipv4_encap_size;
- e->encap_header = encap_header;
-
if (!(nud_state & NUD_VALID)) {
neigh_event_send(attr.n, NULL);
/* the encap entry will be made valid on neigh update event
@@ -322,6 +319,8 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
goto destroy_neigh_entry;
}
+ e->encap_size = ipv4_encap_size;
+ e->encap_header = encap_header;
e->flags |= MLX5_ENCAP_ENTRY_VALID;
mlx5e_rep_queue_neigh_stats_work(netdev_priv(attr.out_dev));
mlx5e_route_lookup_ipv4_put(&attr);
@@ -404,16 +403,12 @@ int mlx5e_tc_tun_update_header_ipv4(struct mlx5e_priv *priv,
if (err)
goto free_encap;
- e->encap_size = ipv4_encap_size;
- kfree(e->encap_header);
- e->encap_header = encap_header;
-
if (!(nud_state & NUD_VALID)) {
neigh_event_send(attr.n, NULL);
/* the encap entry will be made valid on neigh update event
* and not used before that.
*/
- goto release_neigh;
+ goto free_encap;
}
memset(&reformat_params, 0, sizeof(reformat_params));
@@ -427,6 +422,10 @@ int mlx5e_tc_tun_update_header_ipv4(struct mlx5e_priv *priv,
goto free_encap;
}
+ e->encap_size = ipv4_encap_size;
+ kfree(e->encap_header);
+ e->encap_header = encap_header;
+
e->flags |= MLX5_ENCAP_ENTRY_VALID;
mlx5e_rep_queue_neigh_stats_work(netdev_priv(attr.out_dev));
mlx5e_route_lookup_ipv4_put(&attr);
@@ -568,9 +567,6 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
if (err)
goto destroy_neigh_entry;
- e->encap_size = ipv6_encap_size;
- e->encap_header = encap_header;
-
if (!(nud_state & NUD_VALID)) {
neigh_event_send(attr.n, NULL);
/* the encap entry will be made valid on neigh update event
@@ -590,6 +586,8 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
goto destroy_neigh_entry;
}
+ e->encap_size = ipv6_encap_size;
+ e->encap_header = encap_header;
e->flags |= MLX5_ENCAP_ENTRY_VALID;
mlx5e_rep_queue_neigh_stats_work(netdev_priv(attr.out_dev));
mlx5e_route_lookup_ipv6_put(&attr);
@@ -671,16 +669,12 @@ int mlx5e_tc_tun_update_header_ipv6(struct mlx5e_priv *priv,
if (err)
goto free_encap;
- e->encap_size = ipv6_encap_size;
- kfree(e->encap_header);
- e->encap_header = encap_header;
-
if (!(nud_state & NUD_VALID)) {
neigh_event_send(attr.n, NULL);
/* the encap entry will be made valid on neigh update event
* and not used before that.
*/
- goto release_neigh;
+ goto free_encap;
}
memset(&reformat_params, 0, sizeof(reformat_params));
@@ -694,6 +688,10 @@ int mlx5e_tc_tun_update_header_ipv6(struct mlx5e_priv *priv,
goto free_encap;
}
+ e->encap_size = ipv6_encap_size;
+ kfree(e->encap_header);
+ e->encap_header = encap_header;
+
e->flags |= MLX5_ENCAP_ENTRY_VALID;
mlx5e_rep_queue_neigh_stats_work(netdev_priv(attr.out_dev));
mlx5e_route_lookup_ipv6_put(&attr);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 215261a..792a0ea 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -43,12 +43,17 @@ void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv,
struct ethtool_drvinfo *drvinfo)
{
struct mlx5_core_dev *mdev = priv->mdev;
+ int count;
strscpy(drvinfo->driver, KBUILD_MODNAME, sizeof(drvinfo->driver));
- snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
- "%d.%d.%04d (%.16s)",
- fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev),
- mdev->board_id);
+ count = snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+ "%d.%d.%04d (%.16s)", fw_rev_maj(mdev),
+ fw_rev_min(mdev), fw_rev_sub(mdev), mdev->board_id);
+ if (count == sizeof(drvinfo->fw_version))
+ snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+ "%d.%d.%04d", fw_rev_maj(mdev),
+ fw_rev_min(mdev), fw_rev_sub(mdev));
+
strscpy(drvinfo->bus_info, dev_name(mdev->device),
sizeof(drvinfo->bus_info));
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 693e55b..3ab682b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -71,13 +71,17 @@ static void mlx5e_rep_get_drvinfo(struct net_device *dev,
{
struct mlx5e_priv *priv = netdev_priv(dev);
struct mlx5_core_dev *mdev = priv->mdev;
+ int count;
strscpy(drvinfo->driver, mlx5e_rep_driver_name,
sizeof(drvinfo->driver));
- snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
- "%d.%d.%04d (%.16s)",
- fw_rev_maj(mdev), fw_rev_min(mdev),
- fw_rev_sub(mdev), mdev->board_id);
+ count = snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+ "%d.%d.%04d (%.16s)", fw_rev_maj(mdev),
+ fw_rev_min(mdev), fw_rev_sub(mdev), mdev->board_id);
+ if (count == sizeof(drvinfo->fw_version))
+ snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+ "%d.%d.%04d", fw_rev_maj(mdev),
+ fw_rev_min(mdev), fw_rev_sub(mdev));
}
static const struct counter_desc sw_rep_stats_desc[] = {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 9a5a5c2..7ca9e5b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -3147,7 +3147,7 @@ static struct mlx5_fields fields[] = {
OFFLOAD(DIPV6_31_0, 32, U32_MAX, ip6.daddr.s6_addr32[3], 0,
dst_ipv4_dst_ipv6.ipv6_layout.ipv6[12]),
OFFLOAD(IPV6_HOPLIMIT, 8, U8_MAX, ip6.hop_limit, 0, ttl_hoplimit),
- OFFLOAD(IP_DSCP, 16, 0xc00f, ip6, 0, ip_dscp),
+ OFFLOAD(IP_DSCP, 16, 0x0fc0, ip6, 0, ip_dscp),
OFFLOAD(TCP_SPORT, 16, U16_MAX, tcp.source, 0, tcp_sport),
OFFLOAD(TCP_DPORT, 16, U16_MAX, tcp.dest, 0, tcp_dport),
@@ -3158,21 +3158,31 @@ static struct mlx5_fields fields[] = {
OFFLOAD(UDP_DPORT, 16, U16_MAX, udp.dest, 0, udp_dport),
};
-static unsigned long mask_to_le(unsigned long mask, int size)
+static u32 mask_field_get(void *mask, struct mlx5_fields *f)
{
- __be32 mask_be32;
- __be16 mask_be16;
-
- if (size == 32) {
- mask_be32 = (__force __be32)(mask);
- mask = (__force unsigned long)cpu_to_le32(be32_to_cpu(mask_be32));
- } else if (size == 16) {
- mask_be32 = (__force __be32)(mask);
- mask_be16 = *(__be16 *)&mask_be32;
- mask = (__force unsigned long)cpu_to_le16(be16_to_cpu(mask_be16));
+ switch (f->field_bsize) {
+ case 32:
+ return be32_to_cpu(*(__be32 *)mask) & f->field_mask;
+ case 16:
+ return be16_to_cpu(*(__be16 *)mask) & (u16)f->field_mask;
+ default:
+ return *(u8 *)mask & (u8)f->field_mask;
}
+}
- return mask;
+static void mask_field_clear(void *mask, struct mlx5_fields *f)
+{
+ switch (f->field_bsize) {
+ case 32:
+ *(__be32 *)mask &= ~cpu_to_be32(f->field_mask);
+ break;
+ case 16:
+ *(__be16 *)mask &= ~cpu_to_be16((u16)f->field_mask);
+ break;
+ default:
+ *(u8 *)mask &= ~(u8)f->field_mask;
+ break;
+ }
}
static int offload_pedit_fields(struct mlx5e_priv *priv,
@@ -3184,11 +3194,12 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
struct pedit_headers *set_masks, *add_masks, *set_vals, *add_vals;
struct pedit_headers_action *hdrs = parse_attr->hdrs;
void *headers_c, *headers_v, *action, *vals_p;
- u32 *s_masks_p, *a_masks_p, s_mask, a_mask;
struct mlx5e_tc_mod_hdr_acts *mod_acts;
- unsigned long mask, field_mask;
+ void *s_masks_p, *a_masks_p;
int i, first, last, next_z;
struct mlx5_fields *f;
+ unsigned long mask;
+ u32 s_mask, a_mask;
u8 cmd;
mod_acts = &parse_attr->mod_hdr_acts;
@@ -3204,15 +3215,11 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
bool skip;
f = &fields[i];
- /* avoid seeing bits set from previous iterations */
- s_mask = 0;
- a_mask = 0;
-
s_masks_p = (void *)set_masks + f->offset;
a_masks_p = (void *)add_masks + f->offset;
- s_mask = *s_masks_p & f->field_mask;
- a_mask = *a_masks_p & f->field_mask;
+ s_mask = mask_field_get(s_masks_p, f);
+ a_mask = mask_field_get(a_masks_p, f);
if (!s_mask && !a_mask) /* nothing to offload here */
continue;
@@ -3239,22 +3246,20 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
match_mask, f->field_bsize))
skip = true;
/* clear to denote we consumed this field */
- *s_masks_p &= ~f->field_mask;
+ mask_field_clear(s_masks_p, f);
} else {
cmd = MLX5_ACTION_TYPE_ADD;
mask = a_mask;
vals_p = (void *)add_vals + f->offset;
/* add 0 is no change */
- if ((*(u32 *)vals_p & f->field_mask) == 0)
+ if (!mask_field_get(vals_p, f))
skip = true;
/* clear to denote we consumed this field */
- *a_masks_p &= ~f->field_mask;
+ mask_field_clear(a_masks_p, f);
}
if (skip)
continue;
- mask = mask_to_le(mask, f->field_bsize);
-
first = find_first_bit(&mask, f->field_bsize);
next_z = find_next_zero_bit(&mask, f->field_bsize, first);
last = find_last_bit(&mask, f->field_bsize);
@@ -3281,10 +3286,9 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
MLX5_SET(set_action_in, action, field, f->field);
if (cmd == MLX5_ACTION_TYPE_SET) {
+ unsigned long field_mask = f->field_mask;
int start;
- field_mask = mask_to_le(f->field_mask, f->field_bsize);
-
/* if field is bit sized it can start not from first bit */
start = find_first_bit(&field_mask, f->field_bsize);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index d41435c..f0b506e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -399,9 +399,9 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb,
u8 metadata_index = be32_to_cpu(eseg->flow_table_metadata);
mlx5e_skb_cb_hwtstamp_init(skb);
- mlx5e_ptpsq_track_metadata(sq->ptpsq, metadata_index);
mlx5e_ptp_metadata_map_put(&sq->ptpsq->metadata_map, skb,
metadata_index);
+ mlx5e_ptpsq_track_metadata(sq->ptpsq, metadata_index);
if (!netif_tx_queue_stopped(sq->txq) &&
mlx5e_ptpsq_metadata_freelist_empty(sq->ptpsq)) {
netif_tx_stop_queue(sq->txq);
@@ -494,10 +494,10 @@ mlx5e_sq_xmit_wqe(struct mlx5e_txqsq *sq, struct sk_buff *skb,
err_drop:
stats->dropped++;
- dev_kfree_skb_any(skb);
if (unlikely(sq->ptpsq && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)))
mlx5e_ptp_metadata_fifo_push(&sq->ptpsq->metadata_freelist,
be32_to_cpu(eseg->flow_table_metadata));
+ dev_kfree_skb_any(skb);
mlx5e_tx_flush(sq);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index ea0405e..40a6cb0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -885,11 +885,14 @@ static void comp_irq_release_sf(struct mlx5_core_dev *dev, u16 vecidx)
{
struct mlx5_eq_table *table = dev->priv.eq_table;
struct mlx5_irq *irq;
+ int cpu;
irq = xa_load(&table->comp_irqs, vecidx);
if (!irq)
return;
+ cpu = cpumask_first(mlx5_irq_get_affinity_mask(irq));
+ cpumask_clear_cpu(cpu, &table->used_cpus);
xa_erase(&table->comp_irqs, vecidx);
mlx5_irq_affinity_irq_release(dev, irq);
}
@@ -897,16 +900,26 @@ static void comp_irq_release_sf(struct mlx5_core_dev *dev, u16 vecidx)
static int comp_irq_request_sf(struct mlx5_core_dev *dev, u16 vecidx)
{
struct mlx5_eq_table *table = dev->priv.eq_table;
+ struct mlx5_irq_pool *pool = mlx5_irq_pool_get(dev);
+ struct irq_affinity_desc af_desc = {};
struct mlx5_irq *irq;
- irq = mlx5_irq_affinity_irq_request_auto(dev, &table->used_cpus, vecidx);
- if (IS_ERR(irq)) {
- /* In case SF irq pool does not exist, fallback to the PF irqs*/
- if (PTR_ERR(irq) == -ENOENT)
- return comp_irq_request_pci(dev, vecidx);
+ /* In case SF irq pool does not exist, fallback to the PF irqs*/
+ if (!mlx5_irq_pool_is_sf_pool(pool))
+ return comp_irq_request_pci(dev, vecidx);
+ af_desc.is_managed = 1;
+ cpumask_copy(&af_desc.mask, cpu_online_mask);
+ cpumask_andnot(&af_desc.mask, &af_desc.mask, &table->used_cpus);
+ irq = mlx5_irq_affinity_request(pool, &af_desc);
+ if (IS_ERR(irq))
return PTR_ERR(irq);
- }
+
+ cpumask_or(&table->used_cpus, &table->used_cpus, mlx5_irq_get_affinity_mask(irq));
+ mlx5_core_dbg(pool->dev, "IRQ %u mapped to cpu %*pbl, %u EQs on this irq\n",
+ pci_irq_vector(dev->pdev, mlx5_irq_get_index(irq)),
+ cpumask_pr_args(mlx5_irq_get_affinity_mask(irq)),
+ mlx5_irq_read_locked(irq) / MLX5_EQ_REFS_PER_IRQ);
return xa_err(xa_store(&table->comp_irqs, vecidx, irq, GFP_KERNEL));
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index b296ac5..88236e7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -984,7 +984,8 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw,
dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
- if (rep->vport == MLX5_VPORT_UPLINK && on_esw->offloads.ft_ipsec_tx_pol) {
+ if (rep->vport == MLX5_VPORT_UPLINK &&
+ on_esw == from_esw && on_esw->offloads.ft_ipsec_tx_pol) {
dest.ft = on_esw->offloads.ft_ipsec_tx_pol;
flow_act.flags = FLOW_ACT_IGNORE_FLOW_LEVEL;
dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
index 047d5fe..612e666 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
@@ -168,45 +168,3 @@ void mlx5_irq_affinity_irq_release(struct mlx5_core_dev *dev, struct mlx5_irq *i
if (pool->irqs_per_cpu)
cpu_put(pool, cpu);
}
-
-/**
- * mlx5_irq_affinity_irq_request_auto - request one IRQ for mlx5 device.
- * @dev: mlx5 device that is requesting the IRQ.
- * @used_cpus: cpumask of bounded cpus by the device
- * @vecidx: vector index to request an IRQ for.
- *
- * Each IRQ is bounded to at most 1 CPU.
- * This function is requesting an IRQ according to the default assignment.
- * The default assignment policy is:
- * - request the least loaded IRQ which is not bound to any
- * CPU of the previous IRQs requested.
- *
- * On success, this function updates used_cpus mask and returns an irq pointer.
- * In case of an error, an appropriate error pointer is returned.
- */
-struct mlx5_irq *mlx5_irq_affinity_irq_request_auto(struct mlx5_core_dev *dev,
- struct cpumask *used_cpus, u16 vecidx)
-{
- struct mlx5_irq_pool *pool = mlx5_irq_pool_get(dev);
- struct irq_affinity_desc af_desc = {};
- struct mlx5_irq *irq;
-
- if (!mlx5_irq_pool_is_sf_pool(pool))
- return ERR_PTR(-ENOENT);
-
- af_desc.is_managed = 1;
- cpumask_copy(&af_desc.mask, cpu_online_mask);
- cpumask_andnot(&af_desc.mask, &af_desc.mask, used_cpus);
- irq = mlx5_irq_affinity_request(pool, &af_desc);
-
- if (IS_ERR(irq))
- return irq;
-
- cpumask_or(used_cpus, used_cpus, mlx5_irq_get_affinity_mask(irq));
- mlx5_core_dbg(pool->dev, "IRQ %u mapped to cpu %*pbl, %u EQs on this irq\n",
- pci_irq_vector(dev->pdev, mlx5_irq_get_index(irq)),
- cpumask_pr_args(mlx5_irq_get_affinity_mask(irq)),
- mlx5_irq_read_locked(irq) / MLX5_EQ_REFS_PER_IRQ);
-
- return irq;
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index aa29f09..0c83ef1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -384,7 +384,12 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
static int mlx5_ptp_adjphase(struct ptp_clock_info *ptp, s32 delta)
{
- return mlx5_ptp_adjtime(ptp, delta);
+ struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
+ struct mlx5_core_dev *mdev;
+
+ mdev = container_of(clock, struct mlx5_core_dev, clock);
+
+ return mlx5_ptp_adjtime_real_time(mdev, delta);
}
static int mlx5_ptp_freq_adj_real_time(struct mlx5_core_dev *mdev, long scaled_ppm)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index 6536482..4dcf995 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -28,7 +28,7 @@
struct mlx5_irq {
struct atomic_notifier_head nh;
cpumask_var_t mask;
- char name[MLX5_MAX_IRQ_NAME];
+ char name[MLX5_MAX_IRQ_FORMATTED_NAME];
struct mlx5_irq_pool *pool;
int refcount;
struct msi_map map;
@@ -292,8 +292,8 @@ struct mlx5_irq *mlx5_irq_alloc(struct mlx5_irq_pool *pool, int i,
else
irq_sf_set_name(pool, name, i);
ATOMIC_INIT_NOTIFIER_HEAD(&irq->nh);
- snprintf(irq->name, MLX5_MAX_IRQ_NAME,
- "%s@pci:%s", name, pci_name(dev->pdev));
+ snprintf(irq->name, MLX5_MAX_IRQ_FORMATTED_NAME,
+ MLX5_IRQ_NAME_FORMAT_STR, name, pci_name(dev->pdev));
err = request_irq(irq->map.virq, irq_int_handler, 0, irq->name,
&irq->nh);
if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h
index d3a77a0..c4d377f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h
@@ -7,6 +7,9 @@
#include <linux/mlx5/driver.h>
#define MLX5_MAX_IRQ_NAME (32)
+#define MLX5_IRQ_NAME_FORMAT_STR ("%s@pci:%s")
+#define MLX5_MAX_IRQ_FORMATTED_NAME \
+ (MLX5_MAX_IRQ_NAME + sizeof(MLX5_IRQ_NAME_FORMAT_STR))
/* max irq_index is 2047, so four chars */
#define MLX5_MAX_IRQ_IDX_CHARS (4)
#define MLX5_EQ_REFS_PER_IRQ (2)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
index 6ea88a5..e3ec559 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
@@ -57,7 +57,8 @@ static const char *dr_action_id_to_str(enum mlx5dr_action_type action_id)
static bool mlx5dr_action_supp_fwd_fdb_multi_ft(struct mlx5_core_dev *dev)
{
- return (MLX5_CAP_ESW_FLOWTABLE(dev, fdb_multi_path_any_table_limit_regc) ||
+ return (MLX5_CAP_GEN(dev, steering_format_version) < MLX5_STEERING_FORMAT_CONNECTX_6DX ||
+ MLX5_CAP_ESW_FLOWTABLE(dev, fdb_multi_path_any_table_limit_regc) ||
MLX5_CAP_ESW_FLOWTABLE(dev, fdb_multi_path_any_table));
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index 4e8527a..6fa06ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -52,7 +52,6 @@ struct dr_qp_init_attr {
u32 cqn;
u32 pdn;
u32 max_send_wr;
- u32 max_send_sge;
struct mlx5_uars_page *uar;
u8 isolate_vl_tc:1;
};
@@ -247,37 +246,6 @@ static int dr_poll_cq(struct mlx5dr_cq *dr_cq, int ne)
return err == CQ_POLL_ERR ? err : npolled;
}
-static int dr_qp_get_args_update_send_wqe_size(struct dr_qp_init_attr *attr)
-{
- return roundup_pow_of_two(sizeof(struct mlx5_wqe_ctrl_seg) +
- sizeof(struct mlx5_wqe_flow_update_ctrl_seg) +
- sizeof(struct mlx5_wqe_header_modify_argument_update_seg));
-}
-
-/* We calculate for specific RC QP with the required functionality */
-static int dr_qp_calc_rc_send_wqe(struct dr_qp_init_attr *attr)
-{
- int update_arg_size;
- int inl_size = 0;
- int tot_size;
- int size;
-
- update_arg_size = dr_qp_get_args_update_send_wqe_size(attr);
-
- size = sizeof(struct mlx5_wqe_ctrl_seg) +
- sizeof(struct mlx5_wqe_raddr_seg);
- inl_size = size + ALIGN(sizeof(struct mlx5_wqe_inline_seg) +
- DR_STE_SIZE, 16);
-
- size += attr->max_send_sge * sizeof(struct mlx5_wqe_data_seg);
-
- size = max(size, update_arg_size);
-
- tot_size = max(size, inl_size);
-
- return ALIGN(tot_size, MLX5_SEND_WQE_BB);
-}
-
static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev,
struct dr_qp_init_attr *attr)
{
@@ -285,7 +253,6 @@ static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev,
u32 temp_qpc[MLX5_ST_SZ_DW(qpc)] = {};
struct mlx5_wq_param wqp;
struct mlx5dr_qp *dr_qp;
- int wqe_size;
int inlen;
void *qpc;
void *in;
@@ -365,15 +332,6 @@ static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev,
if (err)
goto err_in;
dr_qp->uar = attr->uar;
- wqe_size = dr_qp_calc_rc_send_wqe(attr);
- dr_qp->max_inline_data = min(wqe_size -
- (sizeof(struct mlx5_wqe_ctrl_seg) +
- sizeof(struct mlx5_wqe_raddr_seg) +
- sizeof(struct mlx5_wqe_inline_seg)),
- (2 * MLX5_SEND_WQE_BB -
- (sizeof(struct mlx5_wqe_ctrl_seg) +
- sizeof(struct mlx5_wqe_raddr_seg) +
- sizeof(struct mlx5_wqe_inline_seg))));
return dr_qp;
@@ -437,48 +395,8 @@ dr_rdma_handle_flow_access_arg_segments(struct mlx5_wqe_ctrl_seg *wq_ctrl,
MLX5_SEND_WQE_DS;
}
-static int dr_set_data_inl_seg(struct mlx5dr_qp *dr_qp,
- struct dr_data_seg *data_seg, void *wqe)
-{
- int inline_header_size = sizeof(struct mlx5_wqe_ctrl_seg) +
- sizeof(struct mlx5_wqe_raddr_seg) +
- sizeof(struct mlx5_wqe_inline_seg);
- struct mlx5_wqe_inline_seg *seg;
- int left_space;
- int inl = 0;
- void *addr;
- int len;
- int idx;
-
- seg = wqe;
- wqe += sizeof(*seg);
- addr = (void *)(unsigned long)(data_seg->addr);
- len = data_seg->length;
- inl += len;
- left_space = MLX5_SEND_WQE_BB - inline_header_size;
-
- if (likely(len > left_space)) {
- memcpy(wqe, addr, left_space);
- len -= left_space;
- addr += left_space;
- idx = (dr_qp->sq.pc + 1) & (dr_qp->sq.wqe_cnt - 1);
- wqe = mlx5_wq_cyc_get_wqe(&dr_qp->wq.sq, idx);
- }
-
- memcpy(wqe, addr, len);
-
- if (likely(inl)) {
- seg->byte_count = cpu_to_be32(inl | MLX5_INLINE_SEG);
- return DIV_ROUND_UP(inl + sizeof(seg->byte_count),
- MLX5_SEND_WQE_DS);
- } else {
- return 0;
- }
-}
-
static void
-dr_rdma_handle_icm_write_segments(struct mlx5dr_qp *dr_qp,
- struct mlx5_wqe_ctrl_seg *wq_ctrl,
+dr_rdma_handle_icm_write_segments(struct mlx5_wqe_ctrl_seg *wq_ctrl,
u64 remote_addr,
u32 rkey,
struct dr_data_seg *data_seg,
@@ -494,17 +412,15 @@ dr_rdma_handle_icm_write_segments(struct mlx5dr_qp *dr_qp,
wq_raddr->reserved = 0;
wq_dseg = (void *)(wq_raddr + 1);
- /* WQE ctrl segment + WQE remote addr segment */
- *size = (sizeof(*wq_ctrl) + sizeof(*wq_raddr)) / MLX5_SEND_WQE_DS;
- if (data_seg->send_flags & IB_SEND_INLINE) {
- *size += dr_set_data_inl_seg(dr_qp, data_seg, wq_dseg);
- } else {
- wq_dseg->byte_count = cpu_to_be32(data_seg->length);
- wq_dseg->lkey = cpu_to_be32(data_seg->lkey);
- wq_dseg->addr = cpu_to_be64(data_seg->addr);
- *size += sizeof(*wq_dseg) / MLX5_SEND_WQE_DS; /* WQE data segment */
- }
+ wq_dseg->byte_count = cpu_to_be32(data_seg->length);
+ wq_dseg->lkey = cpu_to_be32(data_seg->lkey);
+ wq_dseg->addr = cpu_to_be64(data_seg->addr);
+
+ *size = (sizeof(*wq_ctrl) + /* WQE ctrl segment */
+ sizeof(*wq_dseg) + /* WQE data segment */
+ sizeof(*wq_raddr)) / /* WQE remote addr segment */
+ MLX5_SEND_WQE_DS;
}
static void dr_set_ctrl_seg(struct mlx5_wqe_ctrl_seg *wq_ctrl,
@@ -535,7 +451,7 @@ static void dr_rdma_segments(struct mlx5dr_qp *dr_qp, u64 remote_addr,
switch (opcode) {
case MLX5_OPCODE_RDMA_READ:
case MLX5_OPCODE_RDMA_WRITE:
- dr_rdma_handle_icm_write_segments(dr_qp, wq_ctrl, remote_addr,
+ dr_rdma_handle_icm_write_segments(wq_ctrl, remote_addr,
rkey, data_seg, &size);
break;
case MLX5_OPCODE_FLOW_TBL_ACCESS:
@@ -656,7 +572,7 @@ static void dr_fill_write_args_segs(struct mlx5dr_send_ring *send_ring,
if (send_ring->pending_wqe % send_ring->signal_th == 0)
send_info->write.send_flags |= IB_SEND_SIGNALED;
else
- send_info->write.send_flags &= ~IB_SEND_SIGNALED;
+ send_info->write.send_flags = 0;
}
static void dr_fill_write_icm_segs(struct mlx5dr_domain *dmn,
@@ -680,13 +596,9 @@ static void dr_fill_write_icm_segs(struct mlx5dr_domain *dmn,
}
send_ring->pending_wqe++;
- if (!send_info->write.lkey)
- send_info->write.send_flags |= IB_SEND_INLINE;
if (send_ring->pending_wqe % send_ring->signal_th == 0)
send_info->write.send_flags |= IB_SEND_SIGNALED;
- else
- send_info->write.send_flags &= ~IB_SEND_SIGNALED;
send_ring->pending_wqe++;
send_info->read.length = send_info->write.length;
@@ -696,9 +608,9 @@ static void dr_fill_write_icm_segs(struct mlx5dr_domain *dmn,
send_info->read.lkey = send_ring->sync_mr->mkey;
if (send_ring->pending_wqe % send_ring->signal_th == 0)
- send_info->read.send_flags |= IB_SEND_SIGNALED;
+ send_info->read.send_flags = IB_SEND_SIGNALED;
else
- send_info->read.send_flags &= ~IB_SEND_SIGNALED;
+ send_info->read.send_flags = 0;
}
static void dr_fill_data_segs(struct mlx5dr_domain *dmn,
@@ -1345,7 +1257,6 @@ int mlx5dr_send_ring_alloc(struct mlx5dr_domain *dmn)
dmn->send_ring->cq->qp = dmn->send_ring->qp;
dmn->info.max_send_wr = QUEUE_SIZE;
- init_attr.max_send_sge = 1;
dmn->info.max_inline_size = min(dmn->send_ring->qp->max_inline_data,
DR_STE_SIZE);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 3e50fd5..2afb2bd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -5293,6 +5293,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
dma_dir = page_pool_get_dma_dir(rx_q->page_pool);
buf_sz = DIV_ROUND_UP(priv->dma_conf.dma_buf_sz, PAGE_SIZE) * PAGE_SIZE;
+ limit = min(priv->dma_conf.dma_rx_size - 1, (unsigned int)limit);
if (netif_msg_rx_status(priv)) {
void *rx_head;
@@ -5328,10 +5329,10 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
len = 0;
}
+read_again:
if (count >= limit)
break;
-read_again:
buf1_len = 0;
buf2_len = 0;
entry = next_entry;
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 02bd201..c8da94a 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -780,7 +780,7 @@ static void macvlan_change_rx_flags(struct net_device *dev, int change)
if (dev->flags & IFF_UP) {
if (change & IFF_ALLMULTI)
dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1);
- if (change & IFF_PROMISC)
+ if (!macvlan_passthru(vlan->port) && change & IFF_PROMISC)
dev_set_promiscuity(lowerdev,
dev->flags & IFF_PROMISC ? 1 : -1);
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b4825d3..6762dac 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -56,7 +56,7 @@ extern struct idr btf_idr;
extern spinlock_t btf_idr_lock;
extern struct kobject *btf_kobj;
extern struct bpf_mem_alloc bpf_global_ma, bpf_global_percpu_ma;
-extern bool bpf_global_ma_set, bpf_global_percpu_ma_set;
+extern bool bpf_global_ma_set;
typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64);
typedef int (*bpf_iter_init_seq_priv_t)(void *private_data,
@@ -909,10 +909,14 @@ bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size)
aux->ctx_field_size = size;
}
+static bool bpf_is_ldimm64(const struct bpf_insn *insn)
+{
+ return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
+}
+
static inline bool bpf_pseudo_func(const struct bpf_insn *insn)
{
- return insn->code == (BPF_LD | BPF_IMM | BPF_DW) &&
- insn->src_reg == BPF_PSEUDO_FUNC;
+ return bpf_is_ldimm64(insn) && insn->src_reg == BPF_PSEUDO_FUNC;
}
struct bpf_prog_ops {
diff --git a/include/net/tc_act/tc_ct.h b/include/net/tc_act/tc_ct.h
index 8a6dbfb..77f87c6 100644
--- a/include/net/tc_act/tc_ct.h
+++ b/include/net/tc_act/tc_ct.h
@@ -58,6 +58,11 @@ static inline struct nf_flowtable *tcf_ct_ft(const struct tc_action *a)
return to_ct_params(a)->nf_ft;
}
+static inline struct nf_conntrack_helper *tcf_ct_helper(const struct tc_action *a)
+{
+ return to_ct_params(a)->helper;
+}
+
#else
static inline uint16_t tcf_ct_zone(const struct tc_action *a) { return 0; }
static inline int tcf_ct_action(const struct tc_action *a) { return 0; }
@@ -65,6 +70,10 @@ static inline struct nf_flowtable *tcf_ct_ft(const struct tc_action *a)
{
return NULL;
}
+static inline struct nf_conntrack_helper *tcf_ct_helper(const struct tc_action *a)
+{
+ return NULL;
+}
#endif /* CONFIG_NF_CONNTRACK */
#if IS_ENABLED(CONFIG_NET_ACT_CT)
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 08626b5..cd3afe5 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -64,8 +64,8 @@
#define OFF insn->off
#define IMM insn->imm
-struct bpf_mem_alloc bpf_global_ma, bpf_global_percpu_ma;
-bool bpf_global_ma_set, bpf_global_percpu_ma_set;
+struct bpf_mem_alloc bpf_global_ma;
+bool bpf_global_ma_set;
/* No hurry in this branch
*
@@ -2934,9 +2934,7 @@ static int __init bpf_global_ma_init(void)
ret = bpf_mem_alloc_init(&bpf_global_ma, 0, false);
bpf_global_ma_set = !ret;
- ret = bpf_mem_alloc_init(&bpf_global_percpu_ma, 0, true);
- bpf_global_percpu_ma_set = !ret;
- return !bpf_global_ma_set || !bpf_global_percpu_ma_set;
+ return ret;
}
late_initcall(bpf_global_ma_init);
#endif
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index bd1c42eb..6da370a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -26,6 +26,7 @@
#include <linux/poison.h>
#include <linux/module.h>
#include <linux/cpumask.h>
+#include <linux/bpf_mem_alloc.h>
#include <net/xdp.h>
#include "disasm.h"
@@ -41,6 +42,9 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
#undef BPF_LINK_TYPE
};
+struct bpf_mem_alloc bpf_global_percpu_ma;
+static bool bpf_global_percpu_ma_set;
+
/* bpf_check() is a static code analyzer that walks eBPF program
* instruction by instruction and updates register/stack state.
* All paths of conditional branches are analyzed until 'bpf_exit' insn.
@@ -336,6 +340,7 @@ struct bpf_kfunc_call_arg_meta {
struct btf *btf_vmlinux;
static DEFINE_MUTEX(bpf_verifier_lock);
+static DEFINE_MUTEX(bpf_percpu_ma_lock);
static const struct bpf_line_info *
find_linfo(const struct bpf_verifier_env *env, u32 insn_off)
@@ -3516,12 +3521,29 @@ static int push_jmp_history(struct bpf_verifier_env *env,
/* Backtrack one insn at a time. If idx is not at the top of recorded
* history then previous instruction came from straight line execution.
+ * Return -ENOENT if we exhausted all instructions within given state.
+ *
+ * It's legal to have a bit of a looping with the same starting and ending
+ * insn index within the same state, e.g.: 3->4->5->3, so just because current
+ * instruction index is the same as state's first_idx doesn't mean we are
+ * done. If there is still some jump history left, we should keep going. We
+ * need to take into account that we might have a jump history between given
+ * state's parent and itself, due to checkpointing. In this case, we'll have
+ * history entry recording a jump from last instruction of parent state and
+ * first instruction of given state.
*/
static int get_prev_insn_idx(struct bpf_verifier_state *st, int i,
u32 *history)
{
u32 cnt = *history;
+ if (i == st->first_insn_idx) {
+ if (cnt == 0)
+ return -ENOENT;
+ if (cnt == 1 && st->jmp_history[0].idx == i)
+ return -ENOENT;
+ }
+
if (cnt && st->jmp_history[cnt - 1].idx == i) {
i = st->jmp_history[cnt - 1].prev_idx;
(*history)--;
@@ -4401,10 +4423,10 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
* Nothing to be tracked further in the parent state.
*/
return 0;
- if (i == first_idx)
- break;
subseq_idx = i;
i = get_prev_insn_idx(st, i, &history);
+ if (i == -ENOENT)
+ break;
if (i >= env->prog->len) {
/* This can happen if backtracking reached insn 0
* and there are still reg_mask or stack_mask
@@ -12074,8 +12096,19 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl] && !bpf_global_ma_set)
return -ENOMEM;
- if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl] && !bpf_global_percpu_ma_set)
- return -ENOMEM;
+ if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
+ if (!bpf_global_percpu_ma_set) {
+ mutex_lock(&bpf_percpu_ma_lock);
+ if (!bpf_global_percpu_ma_set) {
+ err = bpf_mem_alloc_init(&bpf_global_percpu_ma, 0, true);
+ if (!err)
+ bpf_global_percpu_ma_set = true;
+ }
+ mutex_unlock(&bpf_percpu_ma_lock);
+ if (err)
+ return err;
+ }
+ }
if (((u64)(u32)meta.arg_constant.value) != meta.arg_constant.value) {
verbose(env, "local type ID argument must be in range [0, U32_MAX]\n");
@@ -15386,8 +15419,7 @@ enum {
* w - next instruction
* e - edge
*/
-static int push_insn(int t, int w, int e, struct bpf_verifier_env *env,
- bool loop_ok)
+static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
{
int *insn_stack = env->cfg.insn_stack;
int *insn_state = env->cfg.insn_state;
@@ -15419,7 +15451,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env,
insn_stack[env->cfg.cur_stack++] = w;
return KEEP_EXPLORING;
} else if ((insn_state[w] & 0xF0) == DISCOVERED) {
- if (loop_ok && env->bpf_capable)
+ if (env->bpf_capable)
return DONE_EXPLORING;
verbose_linfo(env, t, "%d: ", t);
verbose_linfo(env, w, "%d: ", w);
@@ -15439,24 +15471,20 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns,
struct bpf_verifier_env *env,
bool visit_callee)
{
- int ret;
+ int ret, insn_sz;
- ret = push_insn(t, t + 1, FALLTHROUGH, env, false);
+ insn_sz = bpf_is_ldimm64(&insns[t]) ? 2 : 1;
+ ret = push_insn(t, t + insn_sz, FALLTHROUGH, env);
if (ret)
return ret;
- mark_prune_point(env, t + 1);
+ mark_prune_point(env, t + insn_sz);
/* when we exit from subprog, we need to record non-linear history */
- mark_jmp_point(env, t + 1);
+ mark_jmp_point(env, t + insn_sz);
if (visit_callee) {
mark_prune_point(env, t);
- ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env,
- /* It's ok to allow recursion from CFG point of
- * view. __check_func_call() will do the actual
- * check.
- */
- bpf_pseudo_func(insns + t));
+ ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env);
}
return ret;
}
@@ -15469,15 +15497,17 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns,
static int visit_insn(int t, struct bpf_verifier_env *env)
{
struct bpf_insn *insns = env->prog->insnsi, *insn = &insns[t];
- int ret, off;
+ int ret, off, insn_sz;
if (bpf_pseudo_func(insn))
return visit_func_call_insn(t, insns, env, true);
/* All non-branch instructions have a single fall-through edge. */
if (BPF_CLASS(insn->code) != BPF_JMP &&
- BPF_CLASS(insn->code) != BPF_JMP32)
- return push_insn(t, t + 1, FALLTHROUGH, env, false);
+ BPF_CLASS(insn->code) != BPF_JMP32) {
+ insn_sz = bpf_is_ldimm64(insn) ? 2 : 1;
+ return push_insn(t, t + insn_sz, FALLTHROUGH, env);
+ }
switch (BPF_OP(insn->code)) {
case BPF_EXIT:
@@ -15523,8 +15553,7 @@ static int visit_insn(int t, struct bpf_verifier_env *env)
off = insn->imm;
/* unconditional jump with single edge */
- ret = push_insn(t, t + off + 1, FALLTHROUGH, env,
- true);
+ ret = push_insn(t, t + off + 1, FALLTHROUGH, env);
if (ret)
return ret;
@@ -15537,11 +15566,11 @@ static int visit_insn(int t, struct bpf_verifier_env *env)
/* conditional jump with two edges */
mark_prune_point(env, t);
- ret = push_insn(t, t + 1, FALLTHROUGH, env, true);
+ ret = push_insn(t, t + 1, FALLTHROUGH, env);
if (ret)
return ret;
- return push_insn(t, t + insn->off + 1, BRANCH, env, true);
+ return push_insn(t, t + insn->off + 1, BRANCH, env);
}
}
@@ -15607,11 +15636,21 @@ static int check_cfg(struct bpf_verifier_env *env)
}
for (i = 0; i < insn_cnt; i++) {
+ struct bpf_insn *insn = &env->prog->insnsi[i];
+
if (insn_state[i] != EXPLORED) {
verbose(env, "unreachable insn %d\n", i);
ret = -EINVAL;
goto err_free;
}
+ if (bpf_is_ldimm64(insn)) {
+ if (insn_state[i + 1] != 0) {
+ verbose(env, "jump into the middle of ldimm64 insn %d\n", i);
+ ret = -EINVAL;
+ goto err_free;
+ }
+ i++; /* skip second half of ldimm64 */
+ }
}
ret = 0; /* cfg looks good */
diff --git a/net/core/dev.c b/net/core/dev.c
index 0d54843..af53f6d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1119,7 +1119,9 @@ static int __dev_alloc_name(struct net *net, const char *name, char *res)
if (i == max_netdevices)
return -ENFILE;
- snprintf(res, IFNAMSIZ, name, i);
+ /* 'res' and 'name' could overlap, use 'buf' as an intermediate buffer */
+ strscpy(buf, name, IFNAMSIZ);
+ snprintf(res, IFNAMSIZ, buf, i);
return i;
}
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 1529ec3..bf4d96f 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1515,8 +1515,9 @@ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list)
struct mptcp_pm_addr_entry *entry;
list_for_each_entry(entry, rm_list, list) {
- remove_anno_list_by_saddr(msk, &entry->addr);
- if (alist.nr < MPTCP_RM_IDS_MAX)
+ if ((remove_anno_list_by_saddr(msk, &entry->addr) ||
+ lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) &&
+ alist.nr < MPTCP_RM_IDS_MAX)
alist.ids[alist.nr++] = entry->addr.id;
}
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index a0b8356..bc81ea5 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1230,6 +1230,8 @@ static void mptcp_update_infinite_map(struct mptcp_sock *msk,
mptcp_do_fallback(ssk);
}
+#define MPTCP_MAX_GSO_SIZE (GSO_LEGACY_MAX_SIZE - (MAX_TCP_HEADER + 1))
+
static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
struct mptcp_data_frag *dfrag,
struct mptcp_sendmsg_info *info)
@@ -1256,6 +1258,8 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
return -EAGAIN;
/* compute send limit */
+ if (unlikely(ssk->sk_gso_max_size > MPTCP_MAX_GSO_SIZE))
+ ssk->sk_gso_max_size = MPTCP_MAX_GSO_SIZE;
info->mss_now = tcp_send_mss(ssk, &info->size_goal, info->flags);
copy = info->size_goal;
@@ -3398,10 +3402,11 @@ static void mptcp_release_cb(struct sock *sk)
if (__test_and_clear_bit(MPTCP_CLEAN_UNA, &msk->cb_flags))
__mptcp_clean_una_wakeup(sk);
if (unlikely(msk->cb_flags)) {
- /* be sure to set the current sk state before tacking actions
- * depending on sk_state, that is processing MPTCP_ERROR_REPORT
+ /* be sure to set the current sk state before taking actions
+ * depending on sk_state (MPTCP_ERROR_REPORT)
+ * On sk release avoid actions depending on the first subflow
*/
- if (__test_and_clear_bit(MPTCP_CONNECTED, &msk->cb_flags))
+ if (__test_and_clear_bit(MPTCP_CONNECTED, &msk->cb_flags) && msk->first)
__mptcp_set_connected(sk);
if (__test_and_clear_bit(MPTCP_ERROR_REPORT, &msk->cb_flags))
__mptcp_error_report(sk);
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 77f5e89..3536807 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -738,8 +738,11 @@ static int mptcp_setsockopt_v4_set_tos(struct mptcp_sock *msk, int optname,
val = READ_ONCE(inet_sk(sk)->tos);
mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+ bool slow;
+ slow = lock_sock_fast(ssk);
__ip_sock_set_tos(ssk, val);
+ unlock_sock_fast(ssk, slow);
}
release_sock(sk);
diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c
index f8854bf..62fb103 100644
--- a/net/ncsi/ncsi-aen.c
+++ b/net/ncsi/ncsi-aen.c
@@ -89,11 +89,6 @@ static int ncsi_aen_handler_lsc(struct ncsi_dev_priv *ndp,
if ((had_link == has_link) || chained)
return 0;
- if (had_link)
- netif_carrier_off(ndp->ndev.dev);
- else
- netif_carrier_on(ndp->ndev.dev);
-
if (!ndp->multi_package && !nc->package->multi_channel) {
if (had_link) {
ndp->flags |= NCSI_DEV_RESHUFFLE;
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 0db0ecf..b3f4a50 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -1549,6 +1549,9 @@ static int tcf_ct_offload_act_setup(struct tc_action *act, void *entry_data,
if (bind) {
struct flow_action_entry *entry = entry_data;
+ if (tcf_ct_helper(act))
+ return -EOPNOTSUPP;
+
entry->id = FLOW_ACTION_CT;
entry->ct.action = tcf_ct_action(act);
entry->ct.zone = tcf_ct_zone(act);
diff --git a/tools/testing/selftests/bpf/progs/verifier_cfg.c b/tools/testing/selftests/bpf/progs/verifier_cfg.c
index df7697b..c1f55e1 100644
--- a/tools/testing/selftests/bpf/progs/verifier_cfg.c
+++ b/tools/testing/selftests/bpf/progs/verifier_cfg.c
@@ -97,4 +97,66 @@ l0_%=: r2 = r0; \
" ::: __clobber_all);
}
+SEC("socket")
+__description("conditional loop (2)")
+__success
+__failure_unpriv __msg_unpriv("back-edge from insn 10 to 11")
+__naked void conditional_loop2(void)
+{
+ asm volatile (" \
+ r9 = 2 ll; \
+ r3 = 0x20 ll; \
+ r4 = 0x35 ll; \
+ r8 = r4; \
+ goto l1_%=; \
+l0_%=: r9 -= r3; \
+ r9 -= r4; \
+ r9 -= r8; \
+l1_%=: r8 += r4; \
+ if r8 < 0x64 goto l0_%=; \
+ r0 = r9; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("unconditional loop after conditional jump")
+__failure __msg("infinite loop detected")
+__failure_unpriv __msg_unpriv("back-edge from insn 3 to 2")
+__naked void uncond_loop_after_cond_jmp(void)
+{
+ asm volatile (" \
+ r0 = 0; \
+ if r0 > 0 goto l1_%=; \
+l0_%=: r0 = 1; \
+ goto l0_%=; \
+l1_%=: exit; \
+" ::: __clobber_all);
+}
+
+
+__naked __noinline __used
+static unsigned long never_ending_subprog()
+{
+ asm volatile (" \
+ r0 = r1; \
+ goto -1; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("unconditional loop after conditional jump")
+/* infinite loop is detected *after* check_cfg() */
+__failure __msg("infinite loop detected")
+__naked void uncond_loop_in_subprog_after_cond_jmp(void)
+{
+ asm volatile (" \
+ r0 = 0; \
+ if r0 > 0 goto l1_%=; \
+l0_%=: r0 += 1; \
+ call never_ending_subprog; \
+l1_%=: exit; \
+" ::: __clobber_all);
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_loops1.c b/tools/testing/selftests/bpf/progs/verifier_loops1.c
index 5bc86af..71735db 100644
--- a/tools/testing/selftests/bpf/progs/verifier_loops1.c
+++ b/tools/testing/selftests/bpf/progs/verifier_loops1.c
@@ -75,9 +75,10 @@ l0_%=: r0 += 1; \
" ::: __clobber_all);
}
-SEC("tracepoint")
+SEC("socket")
__description("bounded loop, start in the middle")
-__failure __msg("back-edge")
+__success
+__failure_unpriv __msg_unpriv("back-edge")
__naked void loop_start_in_the_middle(void)
{
asm volatile (" \
@@ -136,7 +137,9 @@ l0_%=: exit; \
SEC("tracepoint")
__description("bounded recursion")
-__failure __msg("back-edge")
+__failure
+/* verifier limitation in detecting max stack depth */
+__msg("the call stack of 8 frames is too deep !")
__naked void bounded_recursion(void)
{
asm volatile (" \
diff --git a/tools/testing/selftests/bpf/progs/verifier_precision.c b/tools/testing/selftests/bpf/progs/verifier_precision.c
index 193c0f8..6b564d4 100644
--- a/tools/testing/selftests/bpf/progs/verifier_precision.c
+++ b/tools/testing/selftests/bpf/progs/verifier_precision.c
@@ -91,3 +91,43 @@ __naked int bpf_end_bswap(void)
}
#endif /* v4 instruction */
+
+SEC("?raw_tp")
+__success __log_level(2)
+/*
+ * Without the bug fix there will be no history between "last_idx 3 first_idx 3"
+ * and "parent state regs=" lines. "R0_w=6" parts are here to help anchor
+ * expected log messages to the one specific mark_chain_precision operation.
+ *
+ * This is quite fragile: if verifier checkpointing heuristic changes, this
+ * might need adjusting.
+ */
+__msg("2: (07) r0 += 1 ; R0_w=6")
+__msg("3: (35) if r0 >= 0xa goto pc+1")
+__msg("mark_precise: frame0: last_idx 3 first_idx 3 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r0 stack= before 2: (07) r0 += 1")
+__msg("mark_precise: frame0: regs=r0 stack= before 1: (07) r0 += 1")
+__msg("mark_precise: frame0: regs=r0 stack= before 4: (05) goto pc-4")
+__msg("mark_precise: frame0: regs=r0 stack= before 3: (35) if r0 >= 0xa goto pc+1")
+__msg("mark_precise: frame0: parent state regs= stack=: R0_rw=P4")
+__msg("3: R0_w=6")
+__naked int state_loop_first_last_equal(void)
+{
+ asm volatile (
+ "r0 = 0;"
+ "l0_%=:"
+ "r0 += 1;"
+ "r0 += 1;"
+ /* every few iterations we'll have a checkpoint here with
+ * first_idx == last_idx, potentially confusing precision
+ * backtracking logic
+ */
+ "if r0 >= 10 goto l1_%=;" /* checkpoint + mark_precise */
+ "goto l0_%=;"
+ "l1_%=:"
+ "exit;"
+ ::: __clobber_common
+ );
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c
index 1bdf2b4..3d5cd51 100644
--- a/tools/testing/selftests/bpf/verifier/calls.c
+++ b/tools/testing/selftests/bpf/verifier/calls.c
@@ -442,7 +442,7 @@
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
- .errstr = "back-edge from insn 0 to 0",
+ .errstr = "the call stack of 9 frames is too deep",
.result = REJECT,
},
{
@@ -799,7 +799,7 @@
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
- .errstr = "back-edge",
+ .errstr = "the call stack of 9 frames is too deep",
.result = REJECT,
},
{
@@ -811,7 +811,7 @@
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
- .errstr = "back-edge",
+ .errstr = "the call stack of 9 frames is too deep",
.result = REJECT,
},
{
diff --git a/tools/testing/selftests/bpf/verifier/ld_imm64.c b/tools/testing/selftests/bpf/verifier/ld_imm64.c
index f929790..78f19c2 100644
--- a/tools/testing/selftests/bpf/verifier/ld_imm64.c
+++ b/tools/testing/selftests/bpf/verifier/ld_imm64.c
@@ -9,8 +9,8 @@
BPF_MOV64_IMM(BPF_REG_0, 2),
BPF_EXIT_INSN(),
},
- .errstr = "invalid BPF_LD_IMM insn",
- .errstr_unpriv = "R1 pointer comparison",
+ .errstr = "jump into the middle of ldimm64 insn 1",
+ .errstr_unpriv = "jump into the middle of ldimm64 insn 1",
.result = REJECT,
},
{
@@ -23,8 +23,8 @@
BPF_LD_IMM64(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
- .errstr = "invalid BPF_LD_IMM insn",
- .errstr_unpriv = "R1 pointer comparison",
+ .errstr = "jump into the middle of ldimm64 insn 1",
+ .errstr_unpriv = "jump into the middle of ldimm64 insn 1",
.result = REJECT,
},
{
diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 591ca96..b604c57 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -908,8 +908,9 @@ static bool is_metadata_correct(struct pkt *pkt, void *buffer, u64 addr)
struct xdp_info *meta = data - sizeof(struct xdp_info);
if (meta->count != pkt->pkt_nb) {
- ksft_print_msg("[%s] expected meta_count [%d], got meta_count [%d]\n",
- __func__, pkt->pkt_nb, meta->count);
+ ksft_print_msg("[%s] expected meta_count [%d], got meta_count [%llu]\n",
+ __func__, pkt->pkt_nb,
+ (unsigned long long)meta->count);
return false;
}
@@ -926,11 +927,13 @@ static bool is_frag_valid(struct xsk_umem_info *umem, u64 addr, u32 len, u32 exp
if (addr >= umem->num_frames * umem->frame_size ||
addr + len > umem->num_frames * umem->frame_size) {
- ksft_print_msg("Frag invalid addr: %llx len: %u\n", addr, len);
+ ksft_print_msg("Frag invalid addr: %llx len: %u\n",
+ (unsigned long long)addr, len);
return false;
}
if (!umem->unaligned_mode && addr % umem->frame_size + len > umem->frame_size) {
- ksft_print_msg("Frag crosses frame boundary addr: %llx len: %u\n", addr, len);
+ ksft_print_msg("Frag crosses frame boundary addr: %llx len: %u\n",
+ (unsigned long long)addr, len);
return false;
}
@@ -1029,7 +1032,8 @@ static int complete_pkts(struct xsk_socket_info *xsk, int batch_size)
u64 addr = *xsk_ring_cons__comp_addr(&xsk->umem->cq, idx + rcvd - 1);
ksft_print_msg("[%s] Too many packets completed\n", __func__);
- ksft_print_msg("Last completion address: %llx\n", addr);
+ ksft_print_msg("Last completion address: %llx\n",
+ (unsigned long long)addr);
return TEST_FAILURE;
}
@@ -1513,8 +1517,9 @@ static int validate_tx_invalid_descs(struct ifobject *ifobject)
}
if (stats.tx_invalid_descs != ifobject->xsk->pkt_stream->nb_pkts / 2) {
- ksft_print_msg("[%s] tx_invalid_descs incorrect. Got [%u] expected [%u]\n",
- __func__, stats.tx_invalid_descs,
+ ksft_print_msg("[%s] tx_invalid_descs incorrect. Got [%llu] expected [%u]\n",
+ __func__,
+ (unsigned long long)stats.tx_invalid_descs,
ifobject->xsk->pkt_stream->nb_pkts);
return TEST_FAILURE;
}
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 75a2438..3c94f2f 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -3240,7 +3240,7 @@
if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then
test_linkfail=1024 fastclose=server \
run_tests $ns1 $ns2 10.0.1.1
- chk_join_nr 0 0 0
+ chk_join_nr 0 0 0 0 0 0 1
chk_fclose_nr 1 1 invert
chk_rst_nr 1 1
fi
