diff options
| author | Jakub Kicinski <kuba@kernel.org> | 2026-03-24 03:59:58 +0300 |
|---|---|---|
| committer | Jakub Kicinski <kuba@kernel.org> | 2026-03-24 03:59:59 +0300 |
| commit | 1a8dd88469bf742fd5eda91cd8e0f720a983ec5a (patch) | |
| tree | 3ac5b2efb70cdde6c5ed9a197c40498939ed10e9 | |
| parent | 9027497a25e3c92b5053b2643e0c18f910865625 (diff) | |
| parent | 10329ce49285e8548da25bdb1cdba3badccfb00c (diff) | |
| download | linux-1a8dd88469bf742fd5eda91cd8e0f720a983ec5a.tar.xz | |
Merge branch 'ethtool-dynamic-rss-context-indirection-table-resizing'
Björn Töpel says:
====================
ethtool: Dynamic RSS context indirection table resizing
Some NICs (e.g. bnxt) change their RSS indirection table size based on
the queue count, because the hardware table is a shared resource. The
ethtool core locks ctx->indir_size at context creation, so drivers
have to reject channel changes when RSS contexts exist.
This series adds resize helpers and wires them up in bnxt. It also
adds tracking of the user provided indirection table size to the
ethtool core.
Patch 1 tracks the user-provided indirection table size (user_size)
in ctx->indir_user_size for non-default RSS contexts and in
dev->ethtool->rss_indir_user_size for context 0. It is set when the
indirection table is configured via netlink or ioctl, and cleared to
zero on reset-to-default.
IFF_RXFH_CONFIGURED is removed, and replaced with rss_indir_user_size.
The flag is redundant now that user_size captures the same
information.
Patch 2 adds core resize helpers:
ethtool_rxfh_indir_can_resize() - read-only validation for context 0
ethtool_rxfh_indir_resize() - fold/unfold context 0 table in place
ethtool_rxfh_ctxs_can_resize() - validate all non-default contexts
ethtool_rxfh_ctxs_resize() - resize all non-default contexts,
with locking and RSS_NTF notifications
Patch 3 uses the resize helpers in bnxt_set_channels().
Patch 4 adds HW tests in rss_drv.py (devices without dynamic table
sizing are skipped):
resize_periodic - fold/unfold with a non-default [3,2,1,0]
sub-table (user_size=4), verifying exact content preservation
(main + ctx)
resize_below_user_size_reject - periodic sub-table with user_size
between big and small device table sizes; verifies that shrinking
below user_size is rejected even when the table is periodic
(main + ctx)
resize_nonperiodic_reject - non-periodic table blocks channel
reduction, with an extra periodic context to exercise
multi-context validation (main + ctx)
resize_nonperiodic_no_corruption - failed resize leaves table
contents and channel count unchanged (main + ctx)
Running the tests:
# On real hardware
sudo NETIF=eth0 ./rss_drv.py
====================
Link: https://patch.msgid.link/20260320085826.1957255-1-bjorn@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
| -rw-r--r-- | drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 | ||||
| -rw-r--r-- | drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 35 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 21 | ||||
| -rw-r--r-- | include/linux/ethtool.h | 13 | ||||
| -rw-r--r-- | include/linux/netdevice.h | 7 | ||||
| -rw-r--r-- | net/ethtool/common.c | 183 | ||||
| -rw-r--r-- | net/ethtool/ioctl.c | 9 | ||||
| -rw-r--r-- | net/ethtool/rss.c | 24 | ||||
| -rwxr-xr-x | tools/testing/selftests/drivers/net/hw/rss_drv.py | 233 |
9 files changed, 488 insertions, 40 deletions
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 604966a398f5..84eb53b4172b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -8118,8 +8118,7 @@ static int __bnxt_reserve_rings(struct bnxt *bp) (bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings) != bnxt_get_nr_rss_ctxs(bp, rx_rings) || bnxt_get_max_rss_ring(bp) >= rx_rings)) { - netdev_warn(bp->dev, "RSS table entries reverting to default\n"); - bp->dev->priv_flags &= ~IFF_RXFH_CONFIGURED; + ethtool_rxfh_indir_lost(bp->dev); } } bp->rx_nr_rings = rx_rings; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 48e8e3be70d3..b87ac2bb43dd 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -942,6 +942,7 @@ static int bnxt_set_channels(struct net_device *dev, { struct bnxt *bp = netdev_priv(dev); int req_tx_rings, req_rx_rings, tcs; + u32 new_tbl_size = 0, old_tbl_size; bool sh = false; int tx_xdp = 0; int rc = 0; @@ -977,19 +978,33 @@ static int bnxt_set_channels(struct net_device *dev, tx_xdp = req_rx_rings; } - if (bnxt_get_nr_rss_ctxs(bp, req_rx_rings) != - bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings) && - (netif_is_rxfh_configured(dev) || bp->num_rss_ctx)) { - netdev_warn(dev, "RSS table size change required, RSS table entries must be default (with no additional RSS contexts present) to proceed\n"); - return -EINVAL; - } - rc = bnxt_check_rings(bp, req_tx_rings, req_rx_rings, sh, tcs, tx_xdp); if (rc) { netdev_warn(dev, "Unable to allocate the requested rings\n"); return rc; } + /* RSS table size only changes on P5 chips with older firmware; + * newer firmware always uses the largest table size. + */ + if (bnxt_get_nr_rss_ctxs(bp, req_rx_rings) != + bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings)) { + new_tbl_size = bnxt_get_nr_rss_ctxs(bp, req_rx_rings) * + BNXT_RSS_TABLE_ENTRIES_P5; + old_tbl_size = bnxt_get_rxfh_indir_size(dev); + + if (!ethtool_rxfh_indir_can_resize(dev, bp->rss_indir_tbl, + old_tbl_size, + new_tbl_size)) { + netdev_warn(dev, "RSS table resize not possible\n"); + return -EINVAL; + } + + rc = ethtool_rxfh_ctxs_can_resize(dev, new_tbl_size); + if (rc) + return rc; + } + if (netif_running(dev)) { if (BNXT_PF(bp)) { /* TODO CHIMP_FW: Send message to all VF's @@ -999,6 +1014,12 @@ static int bnxt_set_channels(struct net_device *dev, bnxt_close_nic(bp, true, false); } + if (new_tbl_size) { + ethtool_rxfh_indir_resize(dev, bp->rss_indir_tbl, + old_tbl_size, new_tbl_size); + ethtool_rxfh_ctxs_resize(dev, new_tbl_size); + } + if (sh) { bp->flags |= BNXT_FLAG_SHARED_RINGS; bp->rx_nr_rings = channel->combined_count; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 3eebdf402129..1238e5356012 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -6480,12 +6480,23 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv) /* max number of channels may have changed */ max_nch = mlx5e_calc_max_nch(priv->mdev, priv->netdev, profile); + + /* Locking is required by ethtool_rxfh_indir_lost() (sends + * ETHTOOL_MSG_RSS_NTF) and by netif_set_real_num_*_queues in case + * the netdev has been registered by this point (if this function + * was called in the reload or resume flow). + */ + if (need_lock) { + rtnl_lock(); + netdev_lock(priv->netdev); + } + if (priv->channels.params.num_channels > max_nch) { mlx5_core_warn(priv->mdev, "MLX5E: Reducing number of channels to %d\n", max_nch); /* Reducing the number of channels - RXFH has to be reset, and * mlx5e_num_channels_changed below will build the RQT. */ - priv->netdev->priv_flags &= ~IFF_RXFH_CONFIGURED; + ethtool_rxfh_indir_lost(priv->netdev); priv->channels.params.num_channels = max_nch; if (priv->channels.params.mqprio.mode == TC_MQPRIO_MODE_CHANNEL) { mlx5_core_warn(priv->mdev, "MLX5E: Disabling MQPRIO channel mode\n"); @@ -6502,15 +6513,7 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv) /* 1. Set the real number of queues in the kernel the first time. * 2. Set our default XPS cpumask. * 3. Build the RQT. - * - * Locking is required by netif_set_real_num_*_queues in case the - * netdev has been registered by this point (if this function was called - * in the reload or resume flow). */ - if (need_lock) { - rtnl_lock(); - netdev_lock(priv->netdev); - } err = mlx5e_num_channels_changed(priv); if (need_lock) { netdev_unlock(priv->netdev); diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 656d465bcd06..1cb0740ba331 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -176,6 +176,8 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) * struct ethtool_rxfh_context - a custom RSS context configuration * @indir_size: Number of u32 entries in indirection table * @key_size: Size of hash key, in bytes + * @indir_user_size: number of user provided entries for the + * indirection table * @priv_size: Size of driver private data, in bytes * @hfunc: RSS hash function identifier. One of the %ETH_RSS_HASH_* * @input_xfrm: Defines how the input data is transformed. Valid values are one @@ -186,6 +188,7 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) struct ethtool_rxfh_context { u32 indir_size; u32 key_size; + u32 indir_user_size; u16 priv_size; u8 hfunc; u8 input_xfrm; @@ -214,6 +217,13 @@ static inline u8 *ethtool_rxfh_context_key(struct ethtool_rxfh_context *ctx) } void ethtool_rxfh_context_lost(struct net_device *dev, u32 context_id); +void ethtool_rxfh_indir_lost(struct net_device *dev); +bool ethtool_rxfh_indir_can_resize(struct net_device *dev, const u32 *tbl, + u32 old_size, u32 new_size); +void ethtool_rxfh_indir_resize(struct net_device *dev, u32 *tbl, + u32 old_size, u32 new_size); +int ethtool_rxfh_ctxs_can_resize(struct net_device *dev, u32 new_indir_size); +void ethtool_rxfh_ctxs_resize(struct net_device *dev, u32 new_indir_size); struct link_mode_info { int speed; @@ -1337,12 +1347,15 @@ int ethtool_virtdev_set_link_ksettings(struct net_device *dev, * @rss_ctx: XArray of custom RSS contexts * @rss_lock: Protects entries in @rss_ctx. May be taken from * within RTNL. + * @rss_indir_user_size: Number of user provided entries for the default + * (context 0) indirection table. * @wol_enabled: Wake-on-LAN is enabled * @module_fw_flash_in_progress: Module firmware flashing is in progress. */ struct ethtool_netdev_state { struct xarray rss_ctx; struct mutex rss_lock; + u32 rss_indir_user_size; unsigned wol_enabled:1; unsigned module_fw_flash_in_progress:1; }; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6882b41bb3e8..e15367373f7c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1716,7 +1716,6 @@ struct net_device_ops { * @IFF_OPENVSWITCH: device is a Open vSwitch master * @IFF_L3MDEV_SLAVE: device is enslaved to an L3 master device * @IFF_TEAM: device is a team device - * @IFF_RXFH_CONFIGURED: device has had Rx Flow indirection table configured * @IFF_PHONY_HEADROOM: the headroom value is controlled by an external * entity (i.e. the master device for bridged veth) * @IFF_MACSEC: device is a MACsec device @@ -1752,7 +1751,6 @@ enum netdev_priv_flags { IFF_OPENVSWITCH = 1<<20, IFF_L3MDEV_SLAVE = 1<<21, IFF_TEAM = 1<<22, - IFF_RXFH_CONFIGURED = 1<<23, IFF_PHONY_HEADROOM = 1<<24, IFF_MACSEC = 1<<25, IFF_NO_RX_HANDLER = 1<<26, @@ -5580,10 +5578,7 @@ static inline bool netif_is_lag_port(const struct net_device *dev) return netif_is_bond_slave(dev) || netif_is_team_port(dev); } -static inline bool netif_is_rxfh_configured(const struct net_device *dev) -{ - return dev->priv_flags & IFF_RXFH_CONFIGURED; -} +bool netif_is_rxfh_configured(const struct net_device *dev); static inline bool netif_is_failover(const struct net_device *dev) { diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 6a4a3797a812..84ec88dee05c 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -1204,6 +1204,189 @@ void ethtool_rxfh_context_lost(struct net_device *dev, u32 context_id) } EXPORT_SYMBOL(ethtool_rxfh_context_lost); +bool netif_is_rxfh_configured(const struct net_device *dev) +{ + return dev->ethtool->rss_indir_user_size; +} +EXPORT_SYMBOL(netif_is_rxfh_configured); + +/** + * ethtool_rxfh_indir_lost - Notify core that the RSS indirection table was lost + * @dev: network device + * + * Drivers should call this when the device can no longer maintain the + * user-configured indirection table, typically after a HW fault recovery + * that reduced the maximum queue count. Marks the default RSS context + * indirection table as unconfigured and sends an %ETHTOOL_MSG_RSS_NTF + * notification. + */ +void ethtool_rxfh_indir_lost(struct net_device *dev) +{ + WARN_ONCE(!rtnl_is_locked() && + !lockdep_is_held_type(&dev->ethtool->rss_lock, -1), + "RSS context lock assertion failed\n"); + + netdev_err(dev, "device error, RSS indirection table lost\n"); + dev->ethtool->rss_indir_user_size = 0; + ethtool_rss_notify(dev, ETHTOOL_MSG_RSS_NTF, 0); +} +EXPORT_SYMBOL(ethtool_rxfh_indir_lost); + +static bool ethtool_rxfh_is_periodic(const u32 *tbl, u32 old_size, u32 new_size) +{ + u32 i; + + for (i = new_size; i < old_size; i++) + if (tbl[i] != tbl[i % new_size]) + return false; + return true; +} + +static bool ethtool_rxfh_can_resize(const u32 *tbl, u32 old_size, u32 new_size, + u32 user_size) +{ + if (new_size == old_size) + return true; + + if (!user_size) + return true; + + if (new_size < old_size) { + if (new_size < user_size) + return false; + if (old_size % new_size) + return false; + if (!ethtool_rxfh_is_periodic(tbl, old_size, new_size)) + return false; + return true; + } + + if (new_size % old_size) + return false; + return true; +} + +/* Resize without validation; caller must have called can_resize first */ +static void ethtool_rxfh_resize(u32 *tbl, u32 old_size, u32 new_size) +{ + u32 i; + + /* Grow: replicate existing pattern; shrink is a no-op on the data */ + for (i = old_size; i < new_size; i++) + tbl[i] = tbl[i % old_size]; +} + +/** + * ethtool_rxfh_indir_can_resize - Check if context 0 indir table can resize + * @dev: network device + * @tbl: indirection table + * @old_size: current number of entries in the table + * @new_size: desired number of entries + * + * Validate that @tbl can be resized from @old_size to @new_size without + * data loss. Uses the user_size floor from context 0. When user_size is + * zero the table is not user-configured and resize always succeeds. + * Read-only; does not modify the table. + * + * Return: true if resize is possible, false otherwise. + */ +bool ethtool_rxfh_indir_can_resize(struct net_device *dev, const u32 *tbl, + u32 old_size, u32 new_size) +{ + return ethtool_rxfh_can_resize(tbl, old_size, new_size, + dev->ethtool->rss_indir_user_size); +} +EXPORT_SYMBOL(ethtool_rxfh_indir_can_resize); + +/** + * ethtool_rxfh_indir_resize - Fold or unfold context 0 indirection table + * @dev: network device + * @tbl: indirection table (must have room for max(old_size, new_size) entries) + * @old_size: current number of entries in the table + * @new_size: desired number of entries + * + * Resize the default RSS context indirection table in place. Caller + * must have validated with ethtool_rxfh_indir_can_resize() first. + */ +void ethtool_rxfh_indir_resize(struct net_device *dev, u32 *tbl, + u32 old_size, u32 new_size) +{ + if (!dev->ethtool->rss_indir_user_size) + return; + + ethtool_rxfh_resize(tbl, old_size, new_size); +} +EXPORT_SYMBOL(ethtool_rxfh_indir_resize); + +/** + * ethtool_rxfh_ctxs_can_resize - Validate resize for all RSS contexts + * @dev: network device + * @new_indir_size: new indirection table size + * + * Validate that the indirection tables of all non-default RSS contexts + * can be resized to @new_indir_size. Read-only; does not modify any + * context. Intended to be paired with ethtool_rxfh_ctxs_resize(). + * + * Return: 0 if all contexts can be resized, negative errno on failure. + */ +int ethtool_rxfh_ctxs_can_resize(struct net_device *dev, u32 new_indir_size) +{ + struct ethtool_rxfh_context *ctx; + unsigned long context; + int ret = 0; + + if (!dev->ethtool_ops->rxfh_indir_space || + new_indir_size > dev->ethtool_ops->rxfh_indir_space) + return -EINVAL; + + mutex_lock(&dev->ethtool->rss_lock); + xa_for_each(&dev->ethtool->rss_ctx, context, ctx) { + u32 *indir = ethtool_rxfh_context_indir(ctx); + + if (!ethtool_rxfh_can_resize(indir, ctx->indir_size, + new_indir_size, + ctx->indir_user_size)) { + ret = -EINVAL; + goto unlock; + } + } +unlock: + mutex_unlock(&dev->ethtool->rss_lock); + return ret; +} +EXPORT_SYMBOL(ethtool_rxfh_ctxs_can_resize); + +/** + * ethtool_rxfh_ctxs_resize - Resize all RSS context indirection tables + * @dev: network device + * @new_indir_size: new indirection table size + * + * Resize the indirection table of every non-default RSS context to + * @new_indir_size. Caller must have validated with + * ethtool_rxfh_ctxs_can_resize() first. An %ETHTOOL_MSG_RSS_NTF is + * sent for each resized context. + * + * Notifications are sent outside the RSS lock to avoid holding the + * mutex during notification delivery. + */ +void ethtool_rxfh_ctxs_resize(struct net_device *dev, u32 new_indir_size) +{ + struct ethtool_rxfh_context *ctx; + unsigned long context; + + mutex_lock(&dev->ethtool->rss_lock); + xa_for_each(&dev->ethtool->rss_ctx, context, ctx) { + ethtool_rxfh_resize(ethtool_rxfh_context_indir(ctx), + ctx->indir_size, new_indir_size); + ctx->indir_size = new_indir_size; + } + mutex_unlock(&dev->ethtool->rss_lock); + + xa_for_each(&dev->ethtool->rss_ctx, context, ctx) + ethtool_rss_notify(dev, ETHTOOL_MSG_RSS_NTF, context); +} +EXPORT_SYMBOL(ethtool_rxfh_ctxs_resize); + enum ethtool_link_medium ethtool_str_to_medium(const char *str) { int i; diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 11dfbf076b6d..3c713a91ad0d 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1405,9 +1405,9 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev, /* indicate whether rxfh was set to default */ if (user_size == 0) - dev->priv_flags &= ~IFF_RXFH_CONFIGURED; + dev->ethtool->rss_indir_user_size = 0; else - dev->priv_flags |= IFF_RXFH_CONFIGURED; + dev->ethtool->rss_indir_user_size = rxfh_dev.indir_size; out_unlock: mutex_unlock(&dev->ethtool->rss_lock); @@ -1722,9 +1722,9 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, if (!rxfh_dev.rss_context) { /* indicate whether rxfh was set to default */ if (rxfh.indir_size == 0) - dev->priv_flags &= ~IFF_RXFH_CONFIGURED; + dev->ethtool->rss_indir_user_size = 0; else if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) - dev->priv_flags |= IFF_RXFH_CONFIGURED; + dev->ethtool->rss_indir_user_size = dev_indir_size; } /* Update rss_ctx tracking */ if (rxfh_dev.rss_delete) { @@ -1737,6 +1737,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, ctx->indir_configured = rxfh.indir_size && rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE; + ctx->indir_user_size = dev_indir_size; } if (rxfh_dev.key) { memcpy(ethtool_rxfh_context_key(ctx), rxfh_dev.key, diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index 0f4e5cd2ac71..5cf90d73e70b 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -686,7 +686,7 @@ rss_set_prep_indir(struct net_device *dev, struct genl_info *info, *mod |= memcmp(rxfh->indir, data->indir_table, data->indir_size); - return 0; + return user_size; err_free: kfree(rxfh->indir); @@ -833,6 +833,7 @@ ethnl_rss_set(struct ethnl_req_info *req_info, struct genl_info *info) struct nlattr **tb = info->attrs; struct rss_reply_data data = {}; const struct ethtool_ops *ops; + u32 indir_user_size; int ret; ops = dev->ethtool_ops; @@ -845,8 +846,9 @@ ethnl_rss_set(struct ethnl_req_info *req_info, struct genl_info *info) rxfh.rss_context = request->rss_context; ret = rss_set_prep_indir(dev, info, &data, &rxfh, &indir_reset, &mod); - if (ret) + if (ret < 0) goto exit_clean_data; + indir_user_size = ret; indir_mod = !!tb[ETHTOOL_A_RSS_INDIR]; rxfh.hfunc = data.hfunc; @@ -889,12 +891,15 @@ ethnl_rss_set(struct ethnl_req_info *req_info, struct genl_info *info) if (ret) goto exit_unlock; - if (ctx) + if (ctx) { rss_set_ctx_update(ctx, tb, &data, &rxfh); - else if (indir_reset) - dev->priv_flags &= ~IFF_RXFH_CONFIGURED; - else if (indir_mod) - dev->priv_flags |= IFF_RXFH_CONFIGURED; + if (indir_user_size) + ctx->indir_user_size = indir_user_size; + } else if (indir_reset) { + dev->ethtool->rss_indir_user_size = 0; + } else if (indir_mod) { + dev->ethtool->rss_indir_user_size = indir_user_size; + } exit_unlock: mutex_unlock(&dev->ethtool->rss_lock); @@ -999,6 +1004,7 @@ int ethnl_rss_create_doit(struct sk_buff *skb, struct genl_info *info) const struct ethtool_ops *ops; struct rss_req_info req = {}; struct net_device *dev; + u32 indir_user_size; struct sk_buff *rsp; void *hdr; u32 limit; @@ -1035,8 +1041,9 @@ int ethnl_rss_create_doit(struct sk_buff *skb, struct genl_info *info) goto exit_ops; ret = rss_set_prep_indir(dev, info, &data, &rxfh, &indir_dflt, &mod); - if (ret) + if (ret < 0) goto exit_clean_data; + indir_user_size = ret; ethnl_update_u8(&rxfh.hfunc, tb[ETHTOOL_A_RSS_HFUNC], &mod); @@ -1080,6 +1087,7 @@ int ethnl_rss_create_doit(struct sk_buff *skb, struct genl_info *info) /* Store the config from rxfh to Xarray.. */ rss_set_ctx_update(ctx, tb, &data, &rxfh); + ctx->indir_user_size = indir_user_size; /* .. copy from Xarray to data. */ __rss_prepare_ctx(dev, &data, ctx); diff --git a/tools/testing/selftests/drivers/net/hw/rss_drv.py b/tools/testing/selftests/drivers/net/hw/rss_drv.py index 2d1a33189076..bd59dace6e15 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_drv.py +++ b/tools/testing/selftests/drivers/net/hw/rss_drv.py @@ -5,9 +5,9 @@ Driver-related behavior tests for RSS. """ -from lib.py import ksft_run, ksft_exit, ksft_ge -from lib.py import ksft_variants, KsftNamedVariant, KsftSkipEx -from lib.py import defer, ethtool +from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_ge +from lib.py import ksft_variants, KsftNamedVariant, KsftSkipEx, ksft_raises +from lib.py import defer, ethtool, CmdExitFailure from lib.py import EthtoolFamily, NlError from lib.py import NetDrvEnv @@ -45,6 +45,18 @@ def _maybe_create_context(cfg, create_context): return ctx_id +def _require_dynamic_indir_size(cfg, ch_max): + """Skip if the device does not dynamically size its indirection table.""" + ethtool(f"-X {cfg.ifname} default") + ethtool(f"-L {cfg.ifname} combined 2") + small = len(_get_rss(cfg)['rss-indirection-table']) + ethtool(f"-L {cfg.ifname} combined {ch_max}") + large = len(_get_rss(cfg)['rss-indirection-table']) + + if small == large: + raise KsftSkipEx("Device does not dynamically size indirection table") + + @ksft_variants([ KsftNamedVariant("main", False), KsftNamedVariant("ctx", True), @@ -76,11 +88,224 @@ def indir_size_4x(cfg, create_context): _test_rss_indir_size(cfg, test_max, context=ctx_id) +@ksft_variants([ + KsftNamedVariant("main", False), + KsftNamedVariant("ctx", True), +]) +def resize_periodic(cfg, create_context): + """Test that a periodic indirection table survives channel changes. + + Set a non-default periodic table ([3, 2, 1, 0] x N) via netlink, + reduce channels to trigger a fold, then increase to trigger an + unfold. Using a reversed pattern (instead of [0, 1, 2, 3]) ensures + the test can distinguish a correct fold from a driver that silently + resets the table to defaults. Verify the exact pattern is preserved + and the size tracks the channel count. + """ + channels = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}}) + ch_max = channels.get('combined-max', 0) + qcnt = channels['combined-count'] + + if ch_max < 4: + raise KsftSkipEx(f"Not enough queues for the test: max={ch_max}") + + defer(ethtool, f"-L {cfg.ifname} combined {qcnt}") + + _require_dynamic_indir_size(cfg, ch_max) + + ctx_id = _maybe_create_context(cfg, create_context) + + # Set a non-default periodic pattern via netlink. + # Send only 4 entries (user_size=4) so the kernel replicates it + # to fill the device table. This allows folding down to 4 entries. + rss = _get_rss(cfg, context=ctx_id) + orig_size = len(rss['rss-indirection-table']) + pattern = [3, 2, 1, 0] + req = {'header': {'dev-index': cfg.ifindex}, 'indir': pattern} + if ctx_id: + req['context'] = ctx_id + else: + defer(ethtool, f"-X {cfg.ifname} default") + cfg.ethnl.rss_set(req) + + # Shrink — should fold + ethtool(f"-L {cfg.ifname} combined 4") + rss = _get_rss(cfg, context=ctx_id) + indir = rss['rss-indirection-table'] + + ksft_ge(orig_size, len(indir), "Table did not shrink") + ksft_eq(indir, [3, 2, 1, 0] * (len(indir) // 4), + "Folded table has wrong pattern") + + # Grow back — should unfold + ethtool(f"-L {cfg.ifname} combined {ch_max}") + rss = _get_rss(cfg, context=ctx_id) + indir = rss['rss-indirection-table'] + + ksft_eq(len(indir), orig_size, "Table size not restored") + ksft_eq(indir, [3, 2, 1, 0] * (len(indir) // 4), + "Unfolded table has wrong pattern") + + +@ksft_variants([ + KsftNamedVariant("main", False), + KsftNamedVariant("ctx", True), +]) +def resize_below_user_size_reject(cfg, create_context): + """Test that shrinking below user_size is rejected. + + Send a table via netlink whose size (user_size) sits between + the small and large device table sizes. The table is periodic, + so folding would normally succeed, but the user_size floor must + prevent it. + """ + channels = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}}) + ch_max = channels.get('combined-max', 0) + qcnt = channels['combined-count'] + + if ch_max < 4: + raise KsftSkipEx(f"Not enough queues for the test: max={ch_max}") + + defer(ethtool, f"-L {cfg.ifname} combined {qcnt}") + + _require_dynamic_indir_size(cfg, ch_max) + + ctx_id = _maybe_create_context(cfg, create_context) + + # Measure the table size at max channels + rss = _get_rss(cfg, context=ctx_id) + big_size = len(rss['rss-indirection-table']) + + # Measure the table size at reduced channels + ethtool(f"-L {cfg.ifname} combined 4") + rss = _get_rss(cfg, context=ctx_id) + small_size = len(rss['rss-indirection-table']) + ethtool(f"-L {cfg.ifname} combined {ch_max}") + + if small_size >= big_size: + raise KsftSkipEx("Table did not shrink at reduced channels") + + # Find a user_size + user_size = None + for div in [2, 4]: + candidate = big_size // div + if candidate > small_size and big_size % candidate == 0: + user_size = candidate + break + if user_size is None: + raise KsftSkipEx("No suitable user_size between small and big table") + + # Send a periodic sub-table of exactly user_size entries. + # Pattern safe for 4 channels. + pattern = [0, 1, 2, 3] * (user_size // 4) + if len(pattern) != user_size: + raise KsftSkipEx(f"user_size ({user_size}) not divisible by 4") + req = {'header': {'dev-index': cfg.ifindex}, 'indir': pattern} + if ctx_id: + req['context'] = ctx_id + else: + defer(ethtool, f"-X {cfg.ifname} default") + cfg.ethnl.rss_set(req) + + # Shrink channels — table would go to small_size < user_size. + # The table is periodic so folding would work, but user_size + # floor must reject it. + with ksft_raises(CmdExitFailure): + ethtool(f"-L {cfg.ifname} combined 4") + + +@ksft_variants([ + KsftNamedVariant("main", False), + KsftNamedVariant("ctx", True), +]) +def resize_nonperiodic_reject(cfg, create_context): + """Test that a non-periodic table blocks channel reduction. + + Set equal weight across all queues so the table is not periodic + at any smaller size, then verify channel reduction is rejected. + An additional context with a periodic table is created to verify + that validation catches the non-periodic one even when others + are fine. + """ + channels = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}}) + ch_max = channels.get('combined-max', 0) + qcnt = channels['combined-count'] + + if ch_max < 4: + raise KsftSkipEx(f"Not enough queues for the test: max={ch_max}") + + defer(ethtool, f"-L {cfg.ifname} combined {qcnt}") + + _require_dynamic_indir_size(cfg, ch_max) + + ctx_id = _maybe_create_context(cfg, create_context) + ctx_ref = f"context {ctx_id}" if ctx_id else "" + + # Create an extra context with a periodic (foldable) table so that + # the validation must iterate all contexts to find the bad one. + extra_ctx = _maybe_create_context(cfg, True) + ethtool(f"-X {cfg.ifname} context {extra_ctx} equal 2") + + ethtool(f"-X {cfg.ifname} {ctx_ref} equal {ch_max}") + if not create_context: + defer(ethtool, f"-X {cfg.ifname} default") + + with ksft_raises(CmdExitFailure): + ethtool(f"-L {cfg.ifname} combined 2") + + +@ksft_variants([ + KsftNamedVariant("main", False), + KsftNamedVariant("ctx", True), +]) +def resize_nonperiodic_no_corruption(cfg, create_context): + """Test that a failed resize does not corrupt table or channel count. + + Set a non-periodic table, attempt a channel reduction (which must + fail), then verify both the indirection table contents and the + channel count are unchanged. + """ + channels = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}}) + ch_max = channels.get('combined-max', 0) + qcnt = channels['combined-count'] + + if ch_max < 4: + raise KsftSkipEx(f"Not enough queues for the test: max={ch_max}") + + defer(ethtool, f"-L {cfg.ifname} combined {qcnt}") + + _require_dynamic_indir_size(cfg, ch_max) + + ctx_id = _maybe_create_context(cfg, create_context) + ctx_ref = f"context {ctx_id}" if ctx_id else "" + + ethtool(f"-X {cfg.ifname} {ctx_ref} equal {ch_max}") + if not create_context: + defer(ethtool, f"-X {cfg.ifname} default") + + rss_before = _get_rss(cfg, context=ctx_id) + + with ksft_raises(CmdExitFailure): + ethtool(f"-L {cfg.ifname} combined 2") + + rss_after = _get_rss(cfg, context=ctx_id) + ksft_eq(rss_after['rss-indirection-table'], + rss_before['rss-indirection-table'], + "Indirection table corrupted after failed resize") + + channels = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}}) + ksft_eq(channels['combined-count'], ch_max, + "Channel count changed after failed resize") + + def main() -> None: """ Ksft boiler plate main """ with NetDrvEnv(__file__) as cfg: cfg.ethnl = EthtoolFamily() - ksft_run([indir_size_4x], args=(cfg, )) + ksft_run([indir_size_4x, resize_periodic, + resize_below_user_size_reject, + resize_nonperiodic_reject, + resize_nonperiodic_no_corruption], args=(cfg, )) ksft_exit() |
