linux/net/ethtool/ioctl.c

3379 lines
86 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* net/core/ethtool.c - Ethtool ioctl handler
* Copyright (c) 2003 Matthew Wilcox <matthew@wil.cx>
*
* This file is where we call all the ethtool_ops commands to get
* the information ethtool needs.
*/
#include <linux/compat.h>
#include <linux/etherdevice.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/ethtool.h>
#include <linux/netdevice.h>
#include <linux/net_tstamp.h>
#include <linux/phy.h>
ethtool: Add direct access to ops->get_sset_count On 03/04/2010 09:26 AM, Ben Hutchings wrote: > On Thu, 2010-03-04 at 00:51 -0800, Jeff Kirsher wrote: >> From: Jeff Garzik<jgarzik@redhat.com> >> >> This patch is an alternative approach for accessing string >> counts, vs. the drvinfo indirect approach. This way the drvinfo >> space doesn't run out, and we don't break ABI later. > [...] >> --- a/net/core/ethtool.c >> +++ b/net/core/ethtool.c >> @@ -214,6 +214,10 @@ static noinline int ethtool_get_drvinfo(struct net_device *dev, void __user *use >> info.cmd = ETHTOOL_GDRVINFO; >> ops->get_drvinfo(dev,&info); >> >> + /* >> + * this method of obtaining string set info is deprecated; >> + * consider using ETHTOOL_GSSET_INFO instead >> + */ > > This comment belongs on the interface (ethtool.h) not the > implementation. Debatable -- the current comment is located at the callsite of ops->get_sset_count(), which is where an implementor might think to add a new call. Not all the numeric fields in ethtool_drvinfo are obtained from ->get_sset_count(). Hence the "some" in the attached patch to include/linux/ethtool.h, addressing your comment. > [...] >> +static noinline int ethtool_get_sset_info(struct net_device *dev, >> + void __user *useraddr) >> +{ > [...] >> + /* calculate size of return buffer */ >> + for (i = 0; i< 64; i++) >> + if (sset_mask& (1ULL<< i)) >> + n_bits++; > [...] > > We have a function for this: > > n_bits = hweight64(sset_mask); Agreed. I've attached a follow-up patch, which should enable my/Jeff's kernel patch to be applied, followed by this one. Signed-off-by: Jeff Garzik <jgarzik@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-03-04 16:21:53 +08:00
#include <linux/bitops.h>
#include <linux/uaccess.h>
#include <linux/vmalloc.h>
#include <linux/sfp.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/rtnetlink.h>
#include <linux/sched/signal.h>
#include <linux/net.h>
#include <linux/pm_runtime.h>
#include <net/devlink.h>
#include <net/xdp_sock_drv.h>
#include <net/flow_offload.h>
#include <linux/ethtool_netlink.h>
#include <generated/utsrelease.h>
#include "common.h"
/* State held across locks and calls for commands which have devlink fallback */
struct ethtool_devlink_compat {
struct devlink *devlink;
union {
struct ethtool_flash efl;
struct ethtool_drvinfo info;
};
};
static struct devlink *netdev_to_devlink_get(struct net_device *dev)
{
if (!dev->devlink_port)
return NULL;
return devlink_try_get(dev->devlink_port->devlink);
}
/*
* Some useful ethtool_ops methods that're device independent.
* If we find that all drivers want to do the same thing here,
* we can turn these into dev_() function calls.
*/
u32 ethtool_op_get_link(struct net_device *dev)
{
return netif_carrier_ok(dev) ? 1 : 0;
}
EXPORT_SYMBOL(ethtool_op_get_link);
int ethtool_op_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info)
{
info->so_timestamping =
SOF_TIMESTAMPING_TX_SOFTWARE |
SOF_TIMESTAMPING_RX_SOFTWARE |
SOF_TIMESTAMPING_SOFTWARE;
info->phc_index = -1;
return 0;
}
EXPORT_SYMBOL(ethtool_op_get_ts_info);
/* Handlers for each ethtool command */
static int ethtool_get_features(struct net_device *dev, void __user *useraddr)
{
struct ethtool_gfeatures cmd = {
.cmd = ETHTOOL_GFEATURES,
.size = ETHTOOL_DEV_FEATURE_WORDS,
};
struct ethtool_get_features_block features[ETHTOOL_DEV_FEATURE_WORDS];
u32 __user *sizeaddr;
u32 copy_size;
int i;
/* in case feature bits run out again */
BUILD_BUG_ON(ETHTOOL_DEV_FEATURE_WORDS * sizeof(u32) > sizeof(netdev_features_t));
for (i = 0; i < ETHTOOL_DEV_FEATURE_WORDS; ++i) {
features[i].available = (u32)(dev->hw_features >> (32 * i));
features[i].requested = (u32)(dev->wanted_features >> (32 * i));
features[i].active = (u32)(dev->features >> (32 * i));
features[i].never_changed =
(u32)(NETIF_F_NEVER_CHANGE >> (32 * i));
}
sizeaddr = useraddr + offsetof(struct ethtool_gfeatures, size);
if (get_user(copy_size, sizeaddr))
return -EFAULT;
if (copy_size > ETHTOOL_DEV_FEATURE_WORDS)
copy_size = ETHTOOL_DEV_FEATURE_WORDS;
if (copy_to_user(useraddr, &cmd, sizeof(cmd)))
return -EFAULT;
useraddr += sizeof(cmd);
if (copy_to_user(useraddr, features,
array_size(copy_size, sizeof(*features))))
return -EFAULT;
return 0;
}
static int ethtool_set_features(struct net_device *dev, void __user *useraddr)
{
struct ethtool_sfeatures cmd;
struct ethtool_set_features_block features[ETHTOOL_DEV_FEATURE_WORDS];
netdev_features_t wanted = 0, valid = 0;
int i, ret = 0;
if (copy_from_user(&cmd, useraddr, sizeof(cmd)))
return -EFAULT;
useraddr += sizeof(cmd);
if (cmd.size != ETHTOOL_DEV_FEATURE_WORDS)
return -EINVAL;
if (copy_from_user(features, useraddr, sizeof(features)))
return -EFAULT;
for (i = 0; i < ETHTOOL_DEV_FEATURE_WORDS; ++i) {
valid |= (netdev_features_t)features[i].valid << (32 * i);
wanted |= (netdev_features_t)features[i].requested << (32 * i);
}
if (valid & ~NETIF_F_ETHTOOL_BITS)
return -EINVAL;
if (valid & ~dev->hw_features) {
valid &= dev->hw_features;
ret |= ETHTOOL_F_UNSUPPORTED;
}
dev->wanted_features &= ~valid;
dev->wanted_features |= wanted & valid;
__netdev_update_features(dev);
if ((dev->wanted_features ^ dev->features) & valid)
ret |= ETHTOOL_F_WISH;
return ret;
}
static int __ethtool_get_sset_count(struct net_device *dev, int sset)
{
const struct ethtool_phy_ops *phy_ops = ethtool_phy_ops;
const struct ethtool_ops *ops = dev->ethtool_ops;
if (sset == ETH_SS_FEATURES)
return ARRAY_SIZE(netdev_features_strings);
ethtool: Support for configurable RSS hash function This patch extends the set/get_rxfh ethtool-options for getting or setting the RSS hash function. It modifies drivers implementation of set/get_rxfh accordingly. This change also delegates the responsibility of checking whether a modification to a certain RX flow hash parameter is supported to the driver implementation of set_rxfh. User-kernel API is done through the new hfunc bitmask field in the ethtool_rxfh struct. A bit set in the hfunc field is corresponding to an index in the new string-set ETH_SS_RSS_HASH_FUNCS. Got approval from most of the relevant driver maintainers that their driver is using Toeplitz, and for the few that didn't answered, also assumed it is Toeplitz. Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Ariel Elior <ariel.elior@qlogic.com> Cc: Prashant Sreedharan <prashant@broadcom.com> Cc: Michael Chan <mchan@broadcom.com> Cc: Hariprasad S <hariprasad@chelsio.com> Cc: Sathya Perla <sathya.perla@emulex.com> Cc: Subbu Seetharaman <subbu.seetharaman@emulex.com> Cc: Ajit Khaparde <ajit.khaparde@emulex.com> Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Cc: Jesse Brandeburg <jesse.brandeburg@intel.com> Cc: Bruce Allan <bruce.w.allan@intel.com> Cc: Carolyn Wyborny <carolyn.wyborny@intel.com> Cc: Don Skidmore <donald.c.skidmore@intel.com> Cc: Greg Rose <gregory.v.rose@intel.com> Cc: Matthew Vick <matthew.vick@intel.com> Cc: John Ronciak <john.ronciak@intel.com> Cc: Mitch Williams <mitch.a.williams@intel.com> Cc: Amir Vadai <amirv@mellanox.com> Cc: Solarflare linux maintainers <linux-net-drivers@solarflare.com> Cc: Shradha Shah <sshah@solarflare.com> Cc: Shreyas Bhatewara <sbhatewara@vmware.com> Cc: "VMware, Inc." <pv-drivers@vmware.com> Cc: Ben Hutchings <ben@decadent.org.uk> Signed-off-by: Eyal Perry <eyalpe@mellanox.com> Signed-off-by: Amir Vadai <amirv@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-03 00:12:10 +08:00
if (sset == ETH_SS_RSS_HASH_FUNCS)
return ARRAY_SIZE(rss_hash_func_strings);
if (sset == ETH_SS_TUNABLES)
return ARRAY_SIZE(tunable_strings);
if (sset == ETH_SS_PHY_TUNABLES)
return ARRAY_SIZE(phy_tunable_strings);
if (sset == ETH_SS_PHY_STATS && dev->phydev &&
!ops->get_ethtool_phy_stats &&
phy_ops && phy_ops->get_sset_count)
return phy_ops->get_sset_count(dev->phydev);
if (sset == ETH_SS_LINK_MODES)
return __ETHTOOL_LINK_MODE_MASK_NBITS;
if (ops->get_sset_count && ops->get_strings)
return ops->get_sset_count(dev, sset);
else
return -EOPNOTSUPP;
}
static void __ethtool_get_strings(struct net_device *dev,
u32 stringset, u8 *data)
{
const struct ethtool_phy_ops *phy_ops = ethtool_phy_ops;
const struct ethtool_ops *ops = dev->ethtool_ops;
if (stringset == ETH_SS_FEATURES)
memcpy(data, netdev_features_strings,
sizeof(netdev_features_strings));
ethtool: Support for configurable RSS hash function This patch extends the set/get_rxfh ethtool-options for getting or setting the RSS hash function. It modifies drivers implementation of set/get_rxfh accordingly. This change also delegates the responsibility of checking whether a modification to a certain RX flow hash parameter is supported to the driver implementation of set_rxfh. User-kernel API is done through the new hfunc bitmask field in the ethtool_rxfh struct. A bit set in the hfunc field is corresponding to an index in the new string-set ETH_SS_RSS_HASH_FUNCS. Got approval from most of the relevant driver maintainers that their driver is using Toeplitz, and for the few that didn't answered, also assumed it is Toeplitz. Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Ariel Elior <ariel.elior@qlogic.com> Cc: Prashant Sreedharan <prashant@broadcom.com> Cc: Michael Chan <mchan@broadcom.com> Cc: Hariprasad S <hariprasad@chelsio.com> Cc: Sathya Perla <sathya.perla@emulex.com> Cc: Subbu Seetharaman <subbu.seetharaman@emulex.com> Cc: Ajit Khaparde <ajit.khaparde@emulex.com> Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Cc: Jesse Brandeburg <jesse.brandeburg@intel.com> Cc: Bruce Allan <bruce.w.allan@intel.com> Cc: Carolyn Wyborny <carolyn.wyborny@intel.com> Cc: Don Skidmore <donald.c.skidmore@intel.com> Cc: Greg Rose <gregory.v.rose@intel.com> Cc: Matthew Vick <matthew.vick@intel.com> Cc: John Ronciak <john.ronciak@intel.com> Cc: Mitch Williams <mitch.a.williams@intel.com> Cc: Amir Vadai <amirv@mellanox.com> Cc: Solarflare linux maintainers <linux-net-drivers@solarflare.com> Cc: Shradha Shah <sshah@solarflare.com> Cc: Shreyas Bhatewara <sbhatewara@vmware.com> Cc: "VMware, Inc." <pv-drivers@vmware.com> Cc: Ben Hutchings <ben@decadent.org.uk> Signed-off-by: Eyal Perry <eyalpe@mellanox.com> Signed-off-by: Amir Vadai <amirv@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-03 00:12:10 +08:00
else if (stringset == ETH_SS_RSS_HASH_FUNCS)
memcpy(data, rss_hash_func_strings,
sizeof(rss_hash_func_strings));
else if (stringset == ETH_SS_TUNABLES)
memcpy(data, tunable_strings, sizeof(tunable_strings));
else if (stringset == ETH_SS_PHY_TUNABLES)
memcpy(data, phy_tunable_strings, sizeof(phy_tunable_strings));
else if (stringset == ETH_SS_PHY_STATS && dev->phydev &&
!ops->get_ethtool_phy_stats && phy_ops &&
phy_ops->get_strings)
phy_ops->get_strings(dev->phydev, data);
else if (stringset == ETH_SS_LINK_MODES)
memcpy(data, link_mode_names,
__ETHTOOL_LINK_MODE_MASK_NBITS * ETH_GSTRING_LEN);
else
/* ops->get_strings is valid because checked earlier */
ops->get_strings(dev, stringset, data);
}
static netdev_features_t ethtool_get_feature_mask(u32 eth_cmd)
{
/* feature masks of legacy discrete ethtool ops */
switch (eth_cmd) {
case ETHTOOL_GTXCSUM:
case ETHTOOL_STXCSUM:
return NETIF_F_CSUM_MASK | NETIF_F_FCOE_CRC |
NETIF_F_SCTP_CRC;
case ETHTOOL_GRXCSUM:
case ETHTOOL_SRXCSUM:
return NETIF_F_RXCSUM;
case ETHTOOL_GSG:
case ETHTOOL_SSG:
return NETIF_F_SG | NETIF_F_FRAGLIST;
case ETHTOOL_GTSO:
case ETHTOOL_STSO:
return NETIF_F_ALL_TSO;
case ETHTOOL_GGSO:
case ETHTOOL_SGSO:
return NETIF_F_GSO;
case ETHTOOL_GGRO:
case ETHTOOL_SGRO:
return NETIF_F_GRO;
default:
BUG();
}
}
static int ethtool_get_one_feature(struct net_device *dev,
char __user *useraddr, u32 ethcmd)
{
netdev_features_t mask = ethtool_get_feature_mask(ethcmd);
struct ethtool_value edata = {
.cmd = ethcmd,
.data = !!(dev->features & mask),
};
if (copy_to_user(useraddr, &edata, sizeof(edata)))
return -EFAULT;
return 0;
}
static int ethtool_set_one_feature(struct net_device *dev,
void __user *useraddr, u32 ethcmd)
{
struct ethtool_value edata;
netdev_features_t mask;
if (copy_from_user(&edata, useraddr, sizeof(edata)))
return -EFAULT;
mask = ethtool_get_feature_mask(ethcmd);
mask &= dev->hw_features;
if (!mask)
return -EOPNOTSUPP;
if (edata.data)
dev->wanted_features |= mask;
else
dev->wanted_features &= ~mask;
__netdev_update_features(dev);
return 0;
}
#define ETH_ALL_FLAGS (ETH_FLAG_LRO | ETH_FLAG_RXVLAN | ETH_FLAG_TXVLAN | \
ETH_FLAG_NTUPLE | ETH_FLAG_RXHASH)
#define ETH_ALL_FEATURES (NETIF_F_LRO | NETIF_F_HW_VLAN_CTAG_RX | \
NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_NTUPLE | \
NETIF_F_RXHASH)
static u32 __ethtool_get_flags(struct net_device *dev)
{
u32 flags = 0;
if (dev->features & NETIF_F_LRO)
flags |= ETH_FLAG_LRO;
if (dev->features & NETIF_F_HW_VLAN_CTAG_RX)
flags |= ETH_FLAG_RXVLAN;
if (dev->features & NETIF_F_HW_VLAN_CTAG_TX)
flags |= ETH_FLAG_TXVLAN;
if (dev->features & NETIF_F_NTUPLE)
flags |= ETH_FLAG_NTUPLE;
if (dev->features & NETIF_F_RXHASH)
flags |= ETH_FLAG_RXHASH;
return flags;
}
static int __ethtool_set_flags(struct net_device *dev, u32 data)
{
netdev_features_t features = 0, changed;
if (data & ~ETH_ALL_FLAGS)
return -EINVAL;
if (data & ETH_FLAG_LRO)
features |= NETIF_F_LRO;
if (data & ETH_FLAG_RXVLAN)
features |= NETIF_F_HW_VLAN_CTAG_RX;
if (data & ETH_FLAG_TXVLAN)
features |= NETIF_F_HW_VLAN_CTAG_TX;
if (data & ETH_FLAG_NTUPLE)
features |= NETIF_F_NTUPLE;
if (data & ETH_FLAG_RXHASH)
features |= NETIF_F_RXHASH;
/* allow changing only bits set in hw_features */
changed = (features ^ dev->features) & ETH_ALL_FEATURES;
if (changed & ~dev->hw_features)
return (changed & dev->hw_features) ? -EINVAL : -EOPNOTSUPP;
dev->wanted_features =
(dev->wanted_features & ~changed) | (features & changed);
__netdev_update_features(dev);
return 0;
}
/* Given two link masks, AND them together and save the result in dst. */
void ethtool_intersect_link_masks(struct ethtool_link_ksettings *dst,
struct ethtool_link_ksettings *src)
{
unsigned int size = BITS_TO_LONGS(__ETHTOOL_LINK_MODE_MASK_NBITS);
unsigned int idx = 0;
for (; idx < size; idx++) {
dst->link_modes.supported[idx] &=
src->link_modes.supported[idx];
dst->link_modes.advertising[idx] &=
src->link_modes.advertising[idx];
}
}
EXPORT_SYMBOL(ethtool_intersect_link_masks);
void ethtool_convert_legacy_u32_to_link_mode(unsigned long *dst,
u32 legacy_u32)
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
{
net: convert users of bitmap_foo() to linkmode_foo() This converts instances of bitmap_foo(args..., __ETHTOOL_LINK_MODE_MASK_NBITS) to linkmode_foo(args...) I manually fixed up some lines to prevent them from being excessively long. Otherwise, this change was generated with the following semantic patch: // Generated with // echo linux/linkmode.h > includes // git grep -Flf includes include/ | cut -f 2- -d / | cat includes - \ // | sort | uniq | tee new_includes | wc -l && mv new_includes includes // and repeating until the number stopped going up @i@ @@ ( #include <linux/acpi_mdio.h> | #include <linux/brcmphy.h> | #include <linux/dsa/loop.h> | #include <linux/dsa/sja1105.h> | #include <linux/ethtool.h> | #include <linux/ethtool_netlink.h> | #include <linux/fec.h> | #include <linux/fs_enet_pd.h> | #include <linux/fsl/enetc_mdio.h> | #include <linux/fwnode_mdio.h> | #include <linux/linkmode.h> | #include <linux/lsm_audit.h> | #include <linux/mdio-bitbang.h> | #include <linux/mdio.h> | #include <linux/mdio-mux.h> | #include <linux/mii.h> | #include <linux/mii_timestamper.h> | #include <linux/mlx5/accel.h> | #include <linux/mlx5/cq.h> | #include <linux/mlx5/device.h> | #include <linux/mlx5/driver.h> | #include <linux/mlx5/eswitch.h> | #include <linux/mlx5/fs.h> | #include <linux/mlx5/port.h> | #include <linux/mlx5/qp.h> | #include <linux/mlx5/rsc_dump.h> | #include <linux/mlx5/transobj.h> | #include <linux/mlx5/vport.h> | #include <linux/of_mdio.h> | #include <linux/of_net.h> | #include <linux/pcs-lynx.h> | #include <linux/pcs/pcs-xpcs.h> | #include <linux/phy.h> | #include <linux/phy_led_triggers.h> | #include <linux/phylink.h> | #include <linux/platform_data/bcmgenet.h> | #include <linux/platform_data/xilinx-ll-temac.h> | #include <linux/pxa168_eth.h> | #include <linux/qed/qed_eth_if.h> | #include <linux/qed/qed_fcoe_if.h> | #include <linux/qed/qed_if.h> | #include <linux/qed/qed_iov_if.h> | #include <linux/qed/qed_iscsi_if.h> | #include <linux/qed/qed_ll2_if.h> | #include <linux/qed/qed_nvmetcp_if.h> | #include <linux/qed/qed_rdma_if.h> | #include <linux/sfp.h> | #include <linux/sh_eth.h> | #include <linux/smsc911x.h> | #include <linux/soc/nxp/lpc32xx-misc.h> | #include <linux/stmmac.h> | #include <linux/sunrpc/svc_rdma.h> | #include <linux/sxgbe_platform.h> | #include <net/cfg80211.h> | #include <net/dsa.h> | #include <net/mac80211.h> | #include <net/selftests.h> | #include <rdma/ib_addr.h> | #include <rdma/ib_cache.h> | #include <rdma/ib_cm.h> | #include <rdma/ib_hdrs.h> | #include <rdma/ib_mad.h> | #include <rdma/ib_marshall.h> | #include <rdma/ib_pack.h> | #include <rdma/ib_pma.h> | #include <rdma/ib_sa.h> | #include <rdma/ib_smi.h> | #include <rdma/ib_umem.h> | #include <rdma/ib_umem_odp.h> | #include <rdma/ib_verbs.h> | #include <rdma/iw_cm.h> | #include <rdma/mr_pool.h> | #include <rdma/opa_addr.h> | #include <rdma/opa_port_info.h> | #include <rdma/opa_smi.h> | #include <rdma/opa_vnic.h> | #include <rdma/rdma_cm.h> | #include <rdma/rdma_cm_ib.h> | #include <rdma/rdmavt_cq.h> | #include <rdma/rdma_vt.h> | #include <rdma/rdmavt_qp.h> | #include <rdma/rw.h> | #include <rdma/tid_rdma_defs.h> | #include <rdma/uverbs_ioctl.h> | #include <rdma/uverbs_named_ioctl.h> | #include <rdma/uverbs_std_types.h> | #include <rdma/uverbs_types.h> | #include <soc/mscc/ocelot.h> | #include <soc/mscc/ocelot_ptp.h> | #include <soc/mscc/ocelot_vcap.h> | #include <trace/events/ib_mad.h> | #include <trace/events/rdma_core.h> | #include <trace/events/rdma.h> | #include <trace/events/rpcrdma.h> | #include <uapi/linux/ethtool.h> | #include <uapi/linux/ethtool_netlink.h> | #include <uapi/linux/mdio.h> | #include <uapi/linux/mii.h> ) @depends on i@ expression list args; @@ ( - bitmap_zero(args, __ETHTOOL_LINK_MODE_MASK_NBITS) + linkmode_zero(args) | - bitmap_copy(args, __ETHTOOL_LINK_MODE_MASK_NBITS) + linkmode_copy(args) | - bitmap_and(args, __ETHTOOL_LINK_MODE_MASK_NBITS) + linkmode_and(args) | - bitmap_or(args, __ETHTOOL_LINK_MODE_MASK_NBITS) + linkmode_or(args) | - bitmap_empty(args, ETHTOOL_LINK_MODE_MASK_NBITS) + linkmode_empty(args) | - bitmap_andnot(args, __ETHTOOL_LINK_MODE_MASK_NBITS) + linkmode_andnot(args) | - bitmap_equal(args, __ETHTOOL_LINK_MODE_MASK_NBITS) + linkmode_equal(args) | - bitmap_intersects(args, __ETHTOOL_LINK_MODE_MASK_NBITS) + linkmode_intersects(args) | - bitmap_subset(args, __ETHTOOL_LINK_MODE_MASK_NBITS) + linkmode_subset(args) ) Add missing linux/mii.h include to mellanox. -DaveM Signed-off-by: Sean Anderson <sean.anderson@seco.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-10-23 06:41:04 +08:00
linkmode_zero(dst);
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
dst[0] = legacy_u32;
}
EXPORT_SYMBOL(ethtool_convert_legacy_u32_to_link_mode);
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
/* return false if src had higher bits set. lower bits always updated. */
bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32,
const unsigned long *src)
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
{
*legacy_u32 = src[0];
return find_next_bit(src, __ETHTOOL_LINK_MODE_MASK_NBITS, 32) ==
__ETHTOOL_LINK_MODE_MASK_NBITS;
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
}
EXPORT_SYMBOL(ethtool_convert_link_mode_to_legacy_u32);
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
/* return false if ksettings link modes had higher bits
* set. legacy_settings always updated (best effort)
*/
static bool
convert_link_ksettings_to_legacy_settings(
struct ethtool_cmd *legacy_settings,
const struct ethtool_link_ksettings *link_ksettings)
{
bool retval = true;
memset(legacy_settings, 0, sizeof(*legacy_settings));
/* this also clears the deprecated fields in legacy structure:
* __u8 transceiver;
* __u32 maxtxpkt;
* __u32 maxrxpkt;
*/
retval &= ethtool_convert_link_mode_to_legacy_u32(
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
&legacy_settings->supported,
link_ksettings->link_modes.supported);
retval &= ethtool_convert_link_mode_to_legacy_u32(
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
&legacy_settings->advertising,
link_ksettings->link_modes.advertising);
retval &= ethtool_convert_link_mode_to_legacy_u32(
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
&legacy_settings->lp_advertising,
link_ksettings->link_modes.lp_advertising);
ethtool_cmd_speed_set(legacy_settings, link_ksettings->base.speed);
legacy_settings->duplex
= link_ksettings->base.duplex;
legacy_settings->port
= link_ksettings->base.port;
legacy_settings->phy_address
= link_ksettings->base.phy_address;
legacy_settings->autoneg
= link_ksettings->base.autoneg;
legacy_settings->mdio_support
= link_ksettings->base.mdio_support;
legacy_settings->eth_tp_mdix
= link_ksettings->base.eth_tp_mdix;
legacy_settings->eth_tp_mdix_ctrl
= link_ksettings->base.eth_tp_mdix_ctrl;
legacy_settings->transceiver
= link_ksettings->base.transceiver;
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
return retval;
}
/* number of 32-bit words to store the user's link mode bitmaps */
#define __ETHTOOL_LINK_MODE_MASK_NU32 \
DIV_ROUND_UP(__ETHTOOL_LINK_MODE_MASK_NBITS, 32)
/* layout of the struct passed from/to userland */
struct ethtool_link_usettings {
struct ethtool_link_settings base;
struct {
__u32 supported[__ETHTOOL_LINK_MODE_MASK_NU32];
__u32 advertising[__ETHTOOL_LINK_MODE_MASK_NU32];
__u32 lp_advertising[__ETHTOOL_LINK_MODE_MASK_NU32];
} link_modes;
};
/* Internal kernel helper to query a device ethtool_link_settings. */
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
int __ethtool_get_link_ksettings(struct net_device *dev,
struct ethtool_link_ksettings *link_ksettings)
{
ASSERT_RTNL();
if (!dev->ethtool_ops->get_link_ksettings)
return -EOPNOTSUPP;
memset(link_ksettings, 0, sizeof(*link_ksettings));
ethtool: Remove link_mode param and derive link params from driver Some drivers clear the 'ethtool_link_ksettings' struct in their get_link_ksettings() callback, before populating it with actual values. Such drivers will set the new 'link_mode' field to zero, resulting in user space receiving wrong link mode information given that zero is a valid value for the field. Another problem is that some drivers (notably tun) can report random values in the 'link_mode' field. This can result in a general protection fault when the field is used as an index to the 'link_mode_params' array [1]. This happens because such drivers implement their set_link_ksettings() callback by simply overwriting their private copy of 'ethtool_link_ksettings' struct with the one they get from the stack, which is not always properly initialized. Fix these problems by removing 'link_mode' from 'ethtool_link_ksettings' and instead have drivers call ethtool_params_from_link_mode() with the current link mode. The function will derive the link parameters (e.g., speed) from the link mode and fill them in the 'ethtool_link_ksettings' struct. v3: * Remove link_mode parameter and derive the link parameters in the driver instead of passing link_mode parameter to ethtool and derive it there. v2: * Introduce 'cap_link_mode_supported' instead of adding a validity field to 'ethtool_link_ksettings' struct. [1] general protection fault, probably for non-canonical address 0xdffffc00f14cc32c: 0000 [#1] PREEMPT SMP KASAN KASAN: probably user-memory-access in range [0x000000078a661960-0x000000078a661967] CPU: 0 PID: 8452 Comm: syz-executor360 Not tainted 5.11.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__ethtool_get_link_ksettings+0x1a3/0x3a0 net/ethtool/ioctl.c:446 Code: b7 3e fa 83 fd ff 0f 84 30 01 00 00 e8 16 b0 3e fa 48 8d 3c ed 60 d5 69 8a 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <0f> b6 14 02 48 89 f8 83 e0 07 83 c0 03 +38 d0 7c 08 84 d2 0f 85 b9 RSP: 0018:ffffc900019df7a0 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: ffff888026136008 RCX: 0000000000000000 RDX: 00000000f14cc32c RSI: ffffffff873439ca RDI: 000000078a661960 RBP: 00000000ffff8880 R08: 00000000ffffffff R09: ffff88802613606f R10: ffffffff873439bc R11: 0000000000000000 R12: 0000000000000000 R13: ffff88802613606c R14: ffff888011d0c210 R15: ffff888011d0c210 FS: 0000000000749300(0000) GS:ffff8880b9c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000004b60f0 CR3: 00000000185c2000 CR4: 00000000001506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: linkinfo_prepare_data+0xfd/0x280 net/ethtool/linkinfo.c:37 ethnl_default_notify+0x1dc/0x630 net/ethtool/netlink.c:586 ethtool_notify+0xbd/0x1f0 net/ethtool/netlink.c:656 ethtool_set_link_ksettings+0x277/0x330 net/ethtool/ioctl.c:620 dev_ethtool+0x2b35/0x45d0 net/ethtool/ioctl.c:2842 dev_ioctl+0x463/0xb70 net/core/dev_ioctl.c:440 sock_do_ioctl+0x148/0x2d0 net/socket.c:1060 sock_ioctl+0x477/0x6a0 net/socket.c:1177 vfs_ioctl fs/ioctl.c:48 [inline] __do_sys_ioctl fs/ioctl.c:753 [inline] __se_sys_ioctl fs/ioctl.c:739 [inline] __x64_sys_ioctl+0x193/0x200 fs/ioctl.c:739 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fixes: c8907043c6ac9 ("ethtool: Get link mode in use instead of speed and duplex parameters") Signed-off-by: Danielle Ratson <danieller@nvidia.com> Reported-by: Eric Dumazet <eric.dumazet@gmail.com> Reviewed-by: Ido Schimmel <idosch@nvidia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-04-07 18:06:51 +08:00
return dev->ethtool_ops->get_link_ksettings(dev, link_ksettings);
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
}
EXPORT_SYMBOL(__ethtool_get_link_ksettings);
/* convert ethtool_link_usettings in user space to a kernel internal
* ethtool_link_ksettings. return 0 on success, errno on error.
*/
static int load_link_ksettings_from_user(struct ethtool_link_ksettings *to,
const void __user *from)
{
struct ethtool_link_usettings link_usettings;
if (copy_from_user(&link_usettings, from, sizeof(link_usettings)))
return -EFAULT;
memcpy(&to->base, &link_usettings.base, sizeof(to->base));
bitmap_from_arr32(to->link_modes.supported,
link_usettings.link_modes.supported,
__ETHTOOL_LINK_MODE_MASK_NBITS);
bitmap_from_arr32(to->link_modes.advertising,
link_usettings.link_modes.advertising,
__ETHTOOL_LINK_MODE_MASK_NBITS);
bitmap_from_arr32(to->link_modes.lp_advertising,
link_usettings.link_modes.lp_advertising,
__ETHTOOL_LINK_MODE_MASK_NBITS);
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
return 0;
}
/* Check if the user is trying to change anything besides speed/duplex */
bool ethtool_virtdev_validate_cmd(const struct ethtool_link_ksettings *cmd)
{
struct ethtool_link_settings base2 = {};
base2.speed = cmd->base.speed;
base2.port = PORT_OTHER;
base2.duplex = cmd->base.duplex;
base2.cmd = cmd->base.cmd;
base2.link_mode_masks_nwords = cmd->base.link_mode_masks_nwords;
return !memcmp(&base2, &cmd->base, sizeof(base2)) &&
bitmap_empty(cmd->link_modes.supported,
__ETHTOOL_LINK_MODE_MASK_NBITS) &&
bitmap_empty(cmd->link_modes.lp_advertising,
__ETHTOOL_LINK_MODE_MASK_NBITS);
}
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
/* convert a kernel internal ethtool_link_ksettings to
* ethtool_link_usettings in user space. return 0 on success, errno on
* error.
*/
static int
store_link_ksettings_for_user(void __user *to,
const struct ethtool_link_ksettings *from)
{
struct ethtool_link_usettings link_usettings;
memcpy(&link_usettings, from, sizeof(link_usettings));
bitmap_to_arr32(link_usettings.link_modes.supported,
from->link_modes.supported,
__ETHTOOL_LINK_MODE_MASK_NBITS);
bitmap_to_arr32(link_usettings.link_modes.advertising,
from->link_modes.advertising,
__ETHTOOL_LINK_MODE_MASK_NBITS);
bitmap_to_arr32(link_usettings.link_modes.lp_advertising,
from->link_modes.lp_advertising,
__ETHTOOL_LINK_MODE_MASK_NBITS);
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
if (copy_to_user(to, &link_usettings, sizeof(link_usettings)))
return -EFAULT;
return 0;
}
/* Query device for its ethtool_link_settings. */
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
static int ethtool_get_link_ksettings(struct net_device *dev,
void __user *useraddr)
{
int err = 0;
struct ethtool_link_ksettings link_ksettings;
ASSERT_RTNL();
if (!dev->ethtool_ops->get_link_ksettings)
return -EOPNOTSUPP;
/* handle bitmap nbits handshake */
if (copy_from_user(&link_ksettings.base, useraddr,
sizeof(link_ksettings.base)))
return -EFAULT;
if (__ETHTOOL_LINK_MODE_MASK_NU32
!= link_ksettings.base.link_mode_masks_nwords) {
/* wrong link mode nbits requested */
memset(&link_ksettings, 0, sizeof(link_ksettings));
link_ksettings.base.cmd = ETHTOOL_GLINKSETTINGS;
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
/* send back number of words required as negative val */
compiletime_assert(__ETHTOOL_LINK_MODE_MASK_NU32 <= S8_MAX,
"need too many bits for link modes!");
link_ksettings.base.link_mode_masks_nwords
= -((s8)__ETHTOOL_LINK_MODE_MASK_NU32);
/* copy the base fields back to user, not the link
* mode bitmaps
*/
if (copy_to_user(useraddr, &link_ksettings.base,
sizeof(link_ksettings.base)))
return -EFAULT;
return 0;
}
/* handshake successful: user/kernel agree on
* link_mode_masks_nwords
*/
memset(&link_ksettings, 0, sizeof(link_ksettings));
err = dev->ethtool_ops->get_link_ksettings(dev, &link_ksettings);
if (err < 0)
return err;
/* make sure we tell the right values to user */
link_ksettings.base.cmd = ETHTOOL_GLINKSETTINGS;
link_ksettings.base.link_mode_masks_nwords
= __ETHTOOL_LINK_MODE_MASK_NU32;
ethtool: provide UAPI for PHY master/slave configuration. This UAPI is needed for BroadR-Reach 100BASE-T1 devices. Due to lack of auto-negotiation support, we needed to be able to configure the MASTER-SLAVE role of the port manually or from an application in user space. The same UAPI can be used for 1000BASE-T or MultiGBASE-T devices to force MASTER or SLAVE role. See IEEE 802.3-2018: 22.2.4.3.7 MASTER-SLAVE control register (Register 9) 22.2.4.3.8 MASTER-SLAVE status register (Register 10) 40.5.2 MASTER-SLAVE configuration resolution 45.2.1.185.1 MASTER-SLAVE config value (1.2100.14) 45.2.7.10 MultiGBASE-T AN control 1 register (Register 7.32) The MASTER-SLAVE role affects the clock configuration: ------------------------------------------------------------------------------- When the PHY is configured as MASTER, the PMA Transmit function shall source TX_TCLK from a local clock source. When configured as SLAVE, the PMA Transmit function shall source TX_TCLK from the clock recovered from data stream provided by MASTER. iMX6Q KSZ9031 XXX ------\ /-----------\ /------------\ | | | | | MAC |<----RGMII----->| PHY Slave |<------>| PHY Master | |<--- 125 MHz ---+-<------/ | | \ | ------/ \-----------/ \------------/ ^ \-TX_TCLK ------------------------------------------------------------------------------- Since some clock or link related issues are only reproducible in a specific MASTER-SLAVE-role, MAC and PHY configuration, it is beneficial to provide generic (not 100BASE-T1 specific) interface to the user space for configuration flexibility and trouble shooting. Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-05 14:35:05 +08:00
link_ksettings.base.master_slave_cfg = MASTER_SLAVE_CFG_UNSUPPORTED;
link_ksettings.base.master_slave_state = MASTER_SLAVE_STATE_UNSUPPORTED;
net: phy: Add support for rate matching This adds support for rate matching (also known as rate adaptation) to the phy subsystem. The general idea is that the phy interface runs at one speed, and the MAC throttles the rate at which it sends packets to the link speed. There's a good overview of several techniques for achieving this at [1]. This patch adds support for three: pause-frame based (such as in Aquantia phys), CRS-based (such as in 10PASS-TS and 2BASE-TL), and open-loop-based (such as in 10GBASE-W). This patch makes a few assumptions and a few non assumptions about the types of rate matching available. First, it assumes that different phys may use different forms of rate matching. Second, it assumes that phys can use rate matching for any of their supported link speeds (e.g. if a phy supports 10BASE-T and XGMII, then it can adapt XGMII to 10BASE-T). Third, it does not assume that all interface modes will use the same form of rate matching. Fourth, it does not assume that all phy devices will support rate matching (even if some do). Relaxing or strengthening these (non-)assumptions could result in a different API. For example, if all interface modes were assumed to use the same form of rate matching, then a bitmask of interface modes supportting rate matching would suffice. For some better visibility into the process, the current rate matching mode is exposed as part of the ethtool ksettings. For the moment, only read access is supported. I'm not sure what userspace might want to configure yet (disable it altogether, disable just one mode, specify the mode to use, etc.). For the moment, since only pause-based rate adaptation support is added in the next few commits, rate matching can be disabled altogether by adjusting the advertisement. 802.3 calls this feature "rate adaptation" in clause 49 (10GBASE-R) and "rate matching" in clause 61 (10PASS-TL and 2BASE-TS). Aquantia also calls this feature "rate adaptation". I chose "rate matching" because it is shorter, and because Russell doesn't think "adaptation" is correct in this context. Signed-off-by: Sean Anderson <sean.anderson@seco.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-09-21 06:12:31 +08:00
link_ksettings.base.rate_matching = RATE_MATCH_NONE;
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
return store_link_ksettings_for_user(useraddr, &link_ksettings);
}
/* Update device ethtool_link_settings. */
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
static int ethtool_set_link_ksettings(struct net_device *dev,
void __user *useraddr)
{
int err;
struct ethtool_link_ksettings link_ksettings;
ASSERT_RTNL();
if (!dev->ethtool_ops->set_link_ksettings)
return -EOPNOTSUPP;
/* make sure nbits field has expected value */
if (copy_from_user(&link_ksettings.base, useraddr,
sizeof(link_ksettings.base)))
return -EFAULT;
if (__ETHTOOL_LINK_MODE_MASK_NU32
!= link_ksettings.base.link_mode_masks_nwords)
return -EINVAL;
/* copy the whole structure, now that we know it has expected
* format
*/
err = load_link_ksettings_from_user(&link_ksettings, useraddr);
if (err)
return err;
/* re-check nwords field, just in case */
if (__ETHTOOL_LINK_MODE_MASK_NU32
!= link_ksettings.base.link_mode_masks_nwords)
return -EINVAL;
ethtool: provide UAPI for PHY master/slave configuration. This UAPI is needed for BroadR-Reach 100BASE-T1 devices. Due to lack of auto-negotiation support, we needed to be able to configure the MASTER-SLAVE role of the port manually or from an application in user space. The same UAPI can be used for 1000BASE-T or MultiGBASE-T devices to force MASTER or SLAVE role. See IEEE 802.3-2018: 22.2.4.3.7 MASTER-SLAVE control register (Register 9) 22.2.4.3.8 MASTER-SLAVE status register (Register 10) 40.5.2 MASTER-SLAVE configuration resolution 45.2.1.185.1 MASTER-SLAVE config value (1.2100.14) 45.2.7.10 MultiGBASE-T AN control 1 register (Register 7.32) The MASTER-SLAVE role affects the clock configuration: ------------------------------------------------------------------------------- When the PHY is configured as MASTER, the PMA Transmit function shall source TX_TCLK from a local clock source. When configured as SLAVE, the PMA Transmit function shall source TX_TCLK from the clock recovered from data stream provided by MASTER. iMX6Q KSZ9031 XXX ------\ /-----------\ /------------\ | | | | | MAC |<----RGMII----->| PHY Slave |<------>| PHY Master | |<--- 125 MHz ---+-<------/ | | \ | ------/ \-----------/ \------------/ ^ \-TX_TCLK ------------------------------------------------------------------------------- Since some clock or link related issues are only reproducible in a specific MASTER-SLAVE-role, MAC and PHY configuration, it is beneficial to provide generic (not 100BASE-T1 specific) interface to the user space for configuration flexibility and trouble shooting. Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-05 14:35:05 +08:00
if (link_ksettings.base.master_slave_cfg ||
link_ksettings.base.master_slave_state)
return -EINVAL;
err = dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings);
if (err >= 0) {
ethtool_notify(dev, ETHTOOL_MSG_LINKINFO_NTF, NULL);
ethtool_notify(dev, ETHTOOL_MSG_LINKMODES_NTF, NULL);
}
return err;
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
}
int ethtool_virtdev_set_link_ksettings(struct net_device *dev,
const struct ethtool_link_ksettings *cmd,
u32 *dev_speed, u8 *dev_duplex)
{
u32 speed;
u8 duplex;
speed = cmd->base.speed;
duplex = cmd->base.duplex;
/* don't allow custom speed and duplex */
if (!ethtool_validate_speed(speed) ||
!ethtool_validate_duplex(duplex) ||
!ethtool_virtdev_validate_cmd(cmd))
return -EINVAL;
*dev_speed = speed;
*dev_duplex = duplex;
return 0;
}
EXPORT_SYMBOL(ethtool_virtdev_set_link_ksettings);
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
/* Query device for its ethtool_cmd settings.
*
* Backward compatibility note: for compatibility with legacy ethtool, this is
* now implemented via get_link_ksettings. When driver reports higher link mode
* bits, a kernel warning is logged once (with name of 1st driver/device) to
* recommend user to upgrade ethtool, but the command is successful (only the
* lower link mode bits reported back to user). Deprecated fields from
* ethtool_cmd (transceiver/maxrxpkt/maxtxpkt) are always set to zero.
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
*/
static int ethtool_get_settings(struct net_device *dev, void __user *useraddr)
{
struct ethtool_link_ksettings link_ksettings;
struct ethtool_cmd cmd;
int err;
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
ASSERT_RTNL();
if (!dev->ethtool_ops->get_link_ksettings)
return -EOPNOTSUPP;
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
memset(&link_ksettings, 0, sizeof(link_ksettings));
err = dev->ethtool_ops->get_link_ksettings(dev, &link_ksettings);
if (err < 0)
return err;
convert_link_ksettings_to_legacy_settings(&cmd, &link_ksettings);
/* send a sensible cmd tag back to user */
cmd.cmd = ETHTOOL_GSET;
if (copy_to_user(useraddr, &cmd, sizeof(cmd)))
return -EFAULT;
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
return 0;
}
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
/* Update device link settings with given ethtool_cmd.
*
* Backward compatibility note: for compatibility with legacy ethtool, this is
* now always implemented via set_link_settings. When user's request updates
* deprecated ethtool_cmd fields (transceiver/maxrxpkt/maxtxpkt), a kernel
* warning is logged once (with name of 1st driver/device) to recommend user to
* upgrade ethtool, and the request is rejected.
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
*/
static int ethtool_set_settings(struct net_device *dev, void __user *useraddr)
{
struct ethtool_link_ksettings link_ksettings;
struct ethtool_cmd cmd;
int ret;
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
ASSERT_RTNL();
if (copy_from_user(&cmd, useraddr, sizeof(cmd)))
return -EFAULT;
if (!dev->ethtool_ops->set_link_ksettings)
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
return -EOPNOTSUPP;
if (!convert_legacy_settings_to_link_ksettings(&link_ksettings, &cmd))
return -EINVAL;
link_ksettings.base.link_mode_masks_nwords =
__ETHTOOL_LINK_MODE_MASK_NU32;
ret = dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings);
if (ret >= 0) {
ethtool_notify(dev, ETHTOOL_MSG_LINKINFO_NTF, NULL);
ethtool_notify(dev, ETHTOOL_MSG_LINKMODES_NTF, NULL);
}
return ret;
}
static int
ethtool_get_drvinfo(struct net_device *dev, struct ethtool_devlink_compat *rsp)
{
const struct ethtool_ops *ops = dev->ethtool_ops;
struct device *parent = dev->dev.parent;
rsp->info.cmd = ETHTOOL_GDRVINFO;
strscpy(rsp->info.version, UTS_RELEASE, sizeof(rsp->info.version));
if (ops->get_drvinfo) {
ops->get_drvinfo(dev, &rsp->info);
if (!rsp->info.bus_info[0] && parent)
strscpy(rsp->info.bus_info, dev_name(parent),
sizeof(rsp->info.bus_info));
if (!rsp->info.driver[0] && parent && parent->driver)
strscpy(rsp->info.driver, parent->driver->name,
sizeof(rsp->info.driver));
} else if (parent && parent->driver) {
strscpy(rsp->info.bus_info, dev_name(parent),
sizeof(rsp->info.bus_info));
strscpy(rsp->info.driver, parent->driver->name,
sizeof(rsp->info.driver));
} else if (dev->rtnl_link_ops) {
strscpy(rsp->info.driver, dev->rtnl_link_ops->kind,
sizeof(rsp->info.driver));
} else {
return -EOPNOTSUPP;
}
/*
* this method of obtaining string set info is deprecated;
ethtool: Add direct access to ops->get_sset_count On 03/04/2010 09:26 AM, Ben Hutchings wrote: > On Thu, 2010-03-04 at 00:51 -0800, Jeff Kirsher wrote: >> From: Jeff Garzik<jgarzik@redhat.com> >> >> This patch is an alternative approach for accessing string >> counts, vs. the drvinfo indirect approach. This way the drvinfo >> space doesn't run out, and we don't break ABI later. > [...] >> --- a/net/core/ethtool.c >> +++ b/net/core/ethtool.c >> @@ -214,6 +214,10 @@ static noinline int ethtool_get_drvinfo(struct net_device *dev, void __user *use >> info.cmd = ETHTOOL_GDRVINFO; >> ops->get_drvinfo(dev,&info); >> >> + /* >> + * this method of obtaining string set info is deprecated; >> + * consider using ETHTOOL_GSSET_INFO instead >> + */ > > This comment belongs on the interface (ethtool.h) not the > implementation. Debatable -- the current comment is located at the callsite of ops->get_sset_count(), which is where an implementor might think to add a new call. Not all the numeric fields in ethtool_drvinfo are obtained from ->get_sset_count(). Hence the "some" in the attached patch to include/linux/ethtool.h, addressing your comment. > [...] >> +static noinline int ethtool_get_sset_info(struct net_device *dev, >> + void __user *useraddr) >> +{ > [...] >> + /* calculate size of return buffer */ >> + for (i = 0; i< 64; i++) >> + if (sset_mask& (1ULL<< i)) >> + n_bits++; > [...] > > We have a function for this: > > n_bits = hweight64(sset_mask); Agreed. I've attached a follow-up patch, which should enable my/Jeff's kernel patch to be applied, followed by this one. Signed-off-by: Jeff Garzik <jgarzik@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-03-04 16:21:53 +08:00
* Use ETHTOOL_GSSET_INFO instead.
*/
if (ops->get_sset_count) {
int rc;
rc = ops->get_sset_count(dev, ETH_SS_TEST);
if (rc >= 0)
rsp->info.testinfo_len = rc;
rc = ops->get_sset_count(dev, ETH_SS_STATS);
if (rc >= 0)
rsp->info.n_stats = rc;
rc = ops->get_sset_count(dev, ETH_SS_PRIV_FLAGS);
if (rc >= 0)
rsp->info.n_priv_flags = rc;
}
if (ops->get_regs_len) {
int ret = ops->get_regs_len(dev);
if (ret > 0)
rsp->info.regdump_len = ret;
}
if (ops->get_eeprom_len)
rsp->info.eedump_len = ops->get_eeprom_len(dev);
if (!rsp->info.fw_version[0])
rsp->devlink = netdev_to_devlink_get(dev);
return 0;
}
static noinline_for_stack int ethtool_get_sset_info(struct net_device *dev,
void __user *useraddr)
{
struct ethtool_sset_info info;
u64 sset_mask;
int i, idx = 0, n_bits = 0, ret, rc;
u32 *info_buf = NULL;
if (copy_from_user(&info, useraddr, sizeof(info)))
return -EFAULT;
/* store copy of mask, because we zero struct later on */
sset_mask = info.sset_mask;
if (!sset_mask)
return 0;
/* calculate size of return buffer */
ethtool: Add direct access to ops->get_sset_count On 03/04/2010 09:26 AM, Ben Hutchings wrote: > On Thu, 2010-03-04 at 00:51 -0800, Jeff Kirsher wrote: >> From: Jeff Garzik<jgarzik@redhat.com> >> >> This patch is an alternative approach for accessing string >> counts, vs. the drvinfo indirect approach. This way the drvinfo >> space doesn't run out, and we don't break ABI later. > [...] >> --- a/net/core/ethtool.c >> +++ b/net/core/ethtool.c >> @@ -214,6 +214,10 @@ static noinline int ethtool_get_drvinfo(struct net_device *dev, void __user *use >> info.cmd = ETHTOOL_GDRVINFO; >> ops->get_drvinfo(dev,&info); >> >> + /* >> + * this method of obtaining string set info is deprecated; >> + * consider using ETHTOOL_GSSET_INFO instead >> + */ > > This comment belongs on the interface (ethtool.h) not the > implementation. Debatable -- the current comment is located at the callsite of ops->get_sset_count(), which is where an implementor might think to add a new call. Not all the numeric fields in ethtool_drvinfo are obtained from ->get_sset_count(). Hence the "some" in the attached patch to include/linux/ethtool.h, addressing your comment. > [...] >> +static noinline int ethtool_get_sset_info(struct net_device *dev, >> + void __user *useraddr) >> +{ > [...] >> + /* calculate size of return buffer */ >> + for (i = 0; i< 64; i++) >> + if (sset_mask& (1ULL<< i)) >> + n_bits++; > [...] > > We have a function for this: > > n_bits = hweight64(sset_mask); Agreed. I've attached a follow-up patch, which should enable my/Jeff's kernel patch to be applied, followed by this one. Signed-off-by: Jeff Garzik <jgarzik@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-03-04 16:21:53 +08:00
n_bits = hweight64(sset_mask);
memset(&info, 0, sizeof(info));
info.cmd = ETHTOOL_GSSET_INFO;
treewide: kzalloc() -> kcalloc() The kzalloc() function has a 2-factor argument form, kcalloc(). This patch replaces cases of: kzalloc(a * b, gfp) with: kcalloc(a * b, gfp) as well as handling cases of: kzalloc(a * b * c, gfp) with: kzalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kzalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kzalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kzalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kzalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kzalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(char) * COUNT + COUNT , ...) | kzalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kzalloc + kcalloc ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kzalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kzalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kzalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kzalloc(C1 * C2 * C3, ...) | kzalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kzalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kzalloc(sizeof(THING) * C2, ...) | kzalloc(sizeof(TYPE) * C2, ...) | kzalloc(C1 * C2 * C3, ...) | kzalloc(C1 * C2, ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - (E1) * E2 + E1, E2 , ...) | - kzalloc + kcalloc ( - (E1) * (E2) + E1, E2 , ...) | - kzalloc + kcalloc ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 05:03:40 +08:00
info_buf = kcalloc(n_bits, sizeof(u32), GFP_USER);
if (!info_buf)
return -ENOMEM;
/*
* fill return buffer based on input bitmask and successful
* get_sset_count return
*/
for (i = 0; i < 64; i++) {
if (!(sset_mask & (1ULL << i)))
continue;
rc = __ethtool_get_sset_count(dev, i);
if (rc >= 0) {
info.sset_mask |= (1ULL << i);
info_buf[idx++] = rc;
}
}
ret = -EFAULT;
if (copy_to_user(useraddr, &info, sizeof(info)))
goto out;
useraddr += offsetof(struct ethtool_sset_info, data);
if (copy_to_user(useraddr, info_buf, array_size(idx, sizeof(u32))))
goto out;
ret = 0;
out:
kfree(info_buf);
return ret;
}
static noinline_for_stack int
ethtool_rxnfc_copy_from_compat(struct ethtool_rxnfc *rxnfc,
const struct compat_ethtool_rxnfc __user *useraddr,
size_t size)
{
struct compat_ethtool_rxnfc crxnfc = {};
/* We expect there to be holes between fs.m_ext and
* fs.ring_cookie and at the end of fs, but nowhere else.
* On non-x86, no conversion should be needed.
*/
BUILD_BUG_ON(!IS_ENABLED(CONFIG_X86_64) &&
sizeof(struct compat_ethtool_rxnfc) !=
sizeof(struct ethtool_rxnfc));
BUILD_BUG_ON(offsetof(struct compat_ethtool_rxnfc, fs.m_ext) +
sizeof(useraddr->fs.m_ext) !=
offsetof(struct ethtool_rxnfc, fs.m_ext) +
sizeof(rxnfc->fs.m_ext));
BUILD_BUG_ON(offsetof(struct compat_ethtool_rxnfc, fs.location) -
offsetof(struct compat_ethtool_rxnfc, fs.ring_cookie) !=
offsetof(struct ethtool_rxnfc, fs.location) -
offsetof(struct ethtool_rxnfc, fs.ring_cookie));
if (copy_from_user(&crxnfc, useraddr, min(size, sizeof(crxnfc))))
return -EFAULT;
*rxnfc = (struct ethtool_rxnfc) {
.cmd = crxnfc.cmd,
.flow_type = crxnfc.flow_type,
.data = crxnfc.data,
.fs = {
.flow_type = crxnfc.fs.flow_type,
.h_u = crxnfc.fs.h_u,
.h_ext = crxnfc.fs.h_ext,
.m_u = crxnfc.fs.m_u,
.m_ext = crxnfc.fs.m_ext,
.ring_cookie = crxnfc.fs.ring_cookie,
.location = crxnfc.fs.location,
},
.rule_cnt = crxnfc.rule_cnt,
};
return 0;
}
static int ethtool_rxnfc_copy_from_user(struct ethtool_rxnfc *rxnfc,
const void __user *useraddr,
size_t size)
{
if (compat_need_64bit_alignment_fixup())
return ethtool_rxnfc_copy_from_compat(rxnfc, useraddr, size);
if (copy_from_user(rxnfc, useraddr, size))
return -EFAULT;
return 0;
}
static int ethtool_rxnfc_copy_to_compat(void __user *useraddr,
const struct ethtool_rxnfc *rxnfc,
size_t size, const u32 *rule_buf)
{
struct compat_ethtool_rxnfc crxnfc;
memset(&crxnfc, 0, sizeof(crxnfc));
crxnfc = (struct compat_ethtool_rxnfc) {
.cmd = rxnfc->cmd,
.flow_type = rxnfc->flow_type,
.data = rxnfc->data,
.fs = {
.flow_type = rxnfc->fs.flow_type,
.h_u = rxnfc->fs.h_u,
.h_ext = rxnfc->fs.h_ext,
.m_u = rxnfc->fs.m_u,
.m_ext = rxnfc->fs.m_ext,
.ring_cookie = rxnfc->fs.ring_cookie,
.location = rxnfc->fs.location,
},
.rule_cnt = rxnfc->rule_cnt,
};
if (copy_to_user(useraddr, &crxnfc, min(size, sizeof(crxnfc))))
return -EFAULT;
return 0;
}
static int ethtool_rxnfc_copy_to_user(void __user *useraddr,
const struct ethtool_rxnfc *rxnfc,
size_t size, const u32 *rule_buf)
{
int ret;
if (compat_need_64bit_alignment_fixup()) {
ret = ethtool_rxnfc_copy_to_compat(useraddr, rxnfc, size,
rule_buf);
useraddr += offsetof(struct compat_ethtool_rxnfc, rule_locs);
} else {
ethtool: Fix rxnfc copy to user buffer overflow In the cited commit, copy_to_user() got called with the wrong pointer, instead of passing the actual buffer ptr to copy from, a pointer to the pointer got passed, which causes a buffer overflow calltrace to pop up when executing "ethtool -x ethX". Fix ethtool_rxnfc_copy_to_user() to use the rxnfc pointer as passed to the function, instead of a pointer to it. This fixes below call trace: [ 15.533533] ------------[ cut here ]------------ [ 15.539007] Buffer overflow detected (8 < 192)! [ 15.544110] WARNING: CPU: 3 PID: 1801 at include/linux/thread_info.h:200 copy_overflow+0x15/0x20 [ 15.549308] Modules linked in: [ 15.551449] CPU: 3 PID: 1801 Comm: ethtool Not tainted 5.14.0-rc2+ #1058 [ 15.553919] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 [ 15.558378] RIP: 0010:copy_overflow+0x15/0x20 [ 15.560648] Code: e9 7c ff ff ff b8 a1 ff ff ff eb c4 66 0f 1f 84 00 00 00 00 00 55 48 89 f2 89 fe 48 c7 c7 88 55 78 8a 48 89 e5 e8 06 5c 1e 00 <0f> 0b 5d c3 0f 1f 80 00 00 00 00 0f 1f 44 00 00 55 48 89 e5 41 55 [ 15.565114] RSP: 0018:ffffad49c0523bd0 EFLAGS: 00010286 [ 15.566231] RAX: 0000000000000000 RBX: 00000000000000c0 RCX: 0000000000000000 [ 15.567616] RDX: 0000000000000001 RSI: ffffffff8a7912e7 RDI: 00000000ffffffff [ 15.569050] RBP: ffffad49c0523bd0 R08: ffffffff8ab2ae28 R09: 00000000ffffdfff [ 15.570534] R10: ffffffff8aa4ae40 R11: ffffffff8aa4ae40 R12: 0000000000000000 [ 15.571899] R13: 00007ffd4cc2a230 R14: ffffad49c0523c00 R15: 0000000000000000 [ 15.573584] FS: 00007f538112f740(0000) GS:ffff96d5bdd80000(0000) knlGS:0000000000000000 [ 15.575639] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 15.577092] CR2: 00007f5381226d40 CR3: 0000000013542000 CR4: 00000000001506e0 [ 15.578929] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 15.580695] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 15.582441] Call Trace: [ 15.582970] ethtool_rxnfc_copy_to_user+0x30/0x46 [ 15.583815] ethtool_get_rxnfc.cold+0x23/0x2b [ 15.584584] dev_ethtool+0x29c/0x25f0 [ 15.585286] ? security_netlbl_sid_to_secattr+0x77/0xd0 [ 15.586728] ? do_set_pte+0xc4/0x110 [ 15.587349] ? _raw_spin_unlock+0x18/0x30 [ 15.588118] ? __might_sleep+0x49/0x80 [ 15.588956] dev_ioctl+0x2c1/0x490 [ 15.589616] sock_ioctl+0x18e/0x330 [ 15.591143] __x64_sys_ioctl+0x41c/0x990 [ 15.591823] ? irqentry_exit_to_user_mode+0x9/0x20 [ 15.592657] ? irqentry_exit+0x33/0x40 [ 15.593308] ? exc_page_fault+0x32f/0x770 [ 15.593877] ? exit_to_user_mode_prepare+0x3c/0x130 [ 15.594775] do_syscall_64+0x35/0x80 [ 15.595397] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 15.596037] RIP: 0033:0x7f5381226d4b [ 15.596492] Code: 0f 1e fa 48 8b 05 3d b1 0c 00 64 c7 00 26 00 00 00 48 c7 c0 ff ff ff ff c3 66 0f 1f 44 00 00 f3 0f 1e fa b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 0d b1 0c 00 f7 d8 64 89 01 48 [ 15.598743] RSP: 002b:00007ffd4cc2a1f8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 [ 15.599804] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f5381226d4b [ 15.600795] RDX: 00007ffd4cc2a350 RSI: 0000000000008946 RDI: 0000000000000003 [ 15.601712] RBP: 00007ffd4cc2a340 R08: 00007ffd4cc2a350 R09: 0000000000000001 [ 15.602751] R10: 00007f538128a990 R11: 0000000000000246 R12: 0000000000000000 [ 15.603882] R13: 00007ffd4cc2a350 R14: 00007ffd4cc2a4b0 R15: 0000000000000000 [ 15.605042] ---[ end trace 325cf185e2795048 ]--- Fixes: dd98d2895de6 ("ethtool: improve compat ioctl handling") Reported-by: Shannon Nelson <snelson@pensando.io> CC: Arnd Bergmann <arnd@arndb.de> CC: Christoph Hellwig <hch@lst.de> Signed-off-by: Saeed Mahameed <saeedm@nvidia.com> Tested-by: Shannon Nelson <snelson@pensando.io> Acked-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-07-27 06:15:39 +08:00
ret = copy_to_user(useraddr, rxnfc, size);
useraddr += offsetof(struct ethtool_rxnfc, rule_locs);
}
if (ret)
return -EFAULT;
if (rule_buf) {
if (copy_to_user(useraddr, rule_buf,
rxnfc->rule_cnt * sizeof(u32)))
return -EFAULT;
}
return 0;
}
static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev,
u32 cmd, void __user *useraddr)
{
struct ethtool_rxnfc info;
size_t info_size = sizeof(info);
int rc;
if (!dev->ethtool_ops->set_rxnfc)
return -EOPNOTSUPP;
/* struct ethtool_rxnfc was originally defined for
* ETHTOOL_{G,S}RXFH with only the cmd, flow_type and data
* members. User-space might still be using that
* definition. */
if (cmd == ETHTOOL_SRXFH)
info_size = (offsetof(struct ethtool_rxnfc, data) +
sizeof(info.data));
if (ethtool_rxnfc_copy_from_user(&info, useraddr, info_size))
return -EFAULT;
rc = dev->ethtool_ops->set_rxnfc(dev, &info);
if (rc)
return rc;
if (cmd == ETHTOOL_SRXCLSRLINS &&
ethtool_rxnfc_copy_to_user(useraddr, &info, info_size, NULL))
return -EFAULT;
return 0;
}
static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev,
u32 cmd, void __user *useraddr)
{
struct ethtool_rxnfc info;
size_t info_size = sizeof(info);
const struct ethtool_ops *ops = dev->ethtool_ops;
int ret;
void *rule_buf = NULL;
if (!ops->get_rxnfc)
return -EOPNOTSUPP;
/* struct ethtool_rxnfc was originally defined for
* ETHTOOL_{G,S}RXFH with only the cmd, flow_type and data
* members. User-space might still be using that
* definition. */
if (cmd == ETHTOOL_GRXFH)
info_size = (offsetof(struct ethtool_rxnfc, data) +
sizeof(info.data));
if (ethtool_rxnfc_copy_from_user(&info, useraddr, info_size))
return -EFAULT;
/* If FLOW_RSS was requested then user-space must be using the
* new definition, as FLOW_RSS is newer.
*/
if (cmd == ETHTOOL_GRXFH && info.flow_type & FLOW_RSS) {
info_size = sizeof(info);
if (ethtool_rxnfc_copy_from_user(&info, useraddr, info_size))
return -EFAULT;
/* Since malicious users may modify the original data,
* we need to check whether FLOW_RSS is still requested.
*/
if (!(info.flow_type & FLOW_RSS))
return -EINVAL;
}
if (info.cmd != cmd)
return -EINVAL;
if (info.cmd == ETHTOOL_GRXCLSRLALL) {
if (info.rule_cnt > 0) {
if (info.rule_cnt <= KMALLOC_MAX_SIZE / sizeof(u32))
treewide: kzalloc() -> kcalloc() The kzalloc() function has a 2-factor argument form, kcalloc(). This patch replaces cases of: kzalloc(a * b, gfp) with: kcalloc(a * b, gfp) as well as handling cases of: kzalloc(a * b * c, gfp) with: kzalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kzalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kzalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kzalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kzalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kzalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(char) * COUNT + COUNT , ...) | kzalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kzalloc + kcalloc ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kzalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kzalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kzalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kzalloc(C1 * C2 * C3, ...) | kzalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kzalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kzalloc(sizeof(THING) * C2, ...) | kzalloc(sizeof(TYPE) * C2, ...) | kzalloc(C1 * C2 * C3, ...) | kzalloc(C1 * C2, ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - (E1) * E2 + E1, E2 , ...) | - kzalloc + kcalloc ( - (E1) * (E2) + E1, E2 , ...) | - kzalloc + kcalloc ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 05:03:40 +08:00
rule_buf = kcalloc(info.rule_cnt, sizeof(u32),
GFP_USER);
if (!rule_buf)
return -ENOMEM;
}
}
ret = ops->get_rxnfc(dev, &info, rule_buf);
if (ret < 0)
goto err_out;
ret = ethtool_rxnfc_copy_to_user(useraddr, &info, info_size, rule_buf);
err_out:
kfree(rule_buf);
return ret;
}
static int ethtool_copy_validate_indir(u32 *indir, void __user *useraddr,
struct ethtool_rxnfc *rx_rings,
u32 size)
{
int i;
if (copy_from_user(indir, useraddr, array_size(size, sizeof(indir[0]))))
return -EFAULT;
/* Validate ring indices */
for (i = 0; i < size; i++)
if (indir[i] >= rx_rings->data)
return -EINVAL;
return 0;
}
u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly;
void netdev_rss_key_fill(void *buffer, size_t len)
{
BUG_ON(len > sizeof(netdev_rss_key));
net_get_random_once(netdev_rss_key, sizeof(netdev_rss_key));
memcpy(buffer, netdev_rss_key, len);
}
EXPORT_SYMBOL(netdev_rss_key_fill);
static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev,
void __user *useraddr)
{
u32 user_size, dev_size;
u32 *indir;
int ret;
if (!dev->ethtool_ops->get_rxfh_indir_size ||
!dev->ethtool_ops->get_rxfh)
return -EOPNOTSUPP;
dev_size = dev->ethtool_ops->get_rxfh_indir_size(dev);
if (dev_size == 0)
return -EOPNOTSUPP;
if (copy_from_user(&user_size,
useraddr + offsetof(struct ethtool_rxfh_indir, size),
sizeof(user_size)))
return -EFAULT;
if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh_indir, size),
&dev_size, sizeof(dev_size)))
return -EFAULT;
/* If the user buffer size is 0, this is just a query for the
* device table size. Otherwise, if it's smaller than the
* device table size it's an error.
*/
if (user_size < dev_size)
return user_size == 0 ? 0 : -EINVAL;
indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER);
if (!indir)
return -ENOMEM;
ethtool: Support for configurable RSS hash function This patch extends the set/get_rxfh ethtool-options for getting or setting the RSS hash function. It modifies drivers implementation of set/get_rxfh accordingly. This change also delegates the responsibility of checking whether a modification to a certain RX flow hash parameter is supported to the driver implementation of set_rxfh. User-kernel API is done through the new hfunc bitmask field in the ethtool_rxfh struct. A bit set in the hfunc field is corresponding to an index in the new string-set ETH_SS_RSS_HASH_FUNCS. Got approval from most of the relevant driver maintainers that their driver is using Toeplitz, and for the few that didn't answered, also assumed it is Toeplitz. Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Ariel Elior <ariel.elior@qlogic.com> Cc: Prashant Sreedharan <prashant@broadcom.com> Cc: Michael Chan <mchan@broadcom.com> Cc: Hariprasad S <hariprasad@chelsio.com> Cc: Sathya Perla <sathya.perla@emulex.com> Cc: Subbu Seetharaman <subbu.seetharaman@emulex.com> Cc: Ajit Khaparde <ajit.khaparde@emulex.com> Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Cc: Jesse Brandeburg <jesse.brandeburg@intel.com> Cc: Bruce Allan <bruce.w.allan@intel.com> Cc: Carolyn Wyborny <carolyn.wyborny@intel.com> Cc: Don Skidmore <donald.c.skidmore@intel.com> Cc: Greg Rose <gregory.v.rose@intel.com> Cc: Matthew Vick <matthew.vick@intel.com> Cc: John Ronciak <john.ronciak@intel.com> Cc: Mitch Williams <mitch.a.williams@intel.com> Cc: Amir Vadai <amirv@mellanox.com> Cc: Solarflare linux maintainers <linux-net-drivers@solarflare.com> Cc: Shradha Shah <sshah@solarflare.com> Cc: Shreyas Bhatewara <sbhatewara@vmware.com> Cc: "VMware, Inc." <pv-drivers@vmware.com> Cc: Ben Hutchings <ben@decadent.org.uk> Signed-off-by: Eyal Perry <eyalpe@mellanox.com> Signed-off-by: Amir Vadai <amirv@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-03 00:12:10 +08:00
ret = dev->ethtool_ops->get_rxfh(dev, indir, NULL, NULL);
if (ret)
goto out;
if (copy_to_user(useraddr +
offsetof(struct ethtool_rxfh_indir, ring_index[0]),
indir, dev_size * sizeof(indir[0])))
ret = -EFAULT;
out:
kfree(indir);
return ret;
}
static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
void __user *useraddr)
{
struct ethtool_rxnfc rx_rings;
u32 user_size, dev_size, i;
u32 *indir;
const struct ethtool_ops *ops = dev->ethtool_ops;
int ret;
u32 ringidx_offset = offsetof(struct ethtool_rxfh_indir, ring_index[0]);
if (!ops->get_rxfh_indir_size || !ops->set_rxfh ||
!ops->get_rxnfc)
return -EOPNOTSUPP;
dev_size = ops->get_rxfh_indir_size(dev);
if (dev_size == 0)
return -EOPNOTSUPP;
if (copy_from_user(&user_size,
useraddr + offsetof(struct ethtool_rxfh_indir, size),
sizeof(user_size)))
return -EFAULT;
if (user_size != 0 && user_size != dev_size)
return -EINVAL;
indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER);
if (!indir)
return -ENOMEM;
rx_rings.cmd = ETHTOOL_GRXRINGS;
ret = ops->get_rxnfc(dev, &rx_rings, NULL);
if (ret)
goto out;
if (user_size == 0) {
for (i = 0; i < dev_size; i++)
indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data);
} else {
ret = ethtool_copy_validate_indir(indir,
useraddr + ringidx_offset,
&rx_rings,
dev_size);
if (ret)
goto out;
}
ethtool: Support for configurable RSS hash function This patch extends the set/get_rxfh ethtool-options for getting or setting the RSS hash function. It modifies drivers implementation of set/get_rxfh accordingly. This change also delegates the responsibility of checking whether a modification to a certain RX flow hash parameter is supported to the driver implementation of set_rxfh. User-kernel API is done through the new hfunc bitmask field in the ethtool_rxfh struct. A bit set in the hfunc field is corresponding to an index in the new string-set ETH_SS_RSS_HASH_FUNCS. Got approval from most of the relevant driver maintainers that their driver is using Toeplitz, and for the few that didn't answered, also assumed it is Toeplitz. Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Ariel Elior <ariel.elior@qlogic.com> Cc: Prashant Sreedharan <prashant@broadcom.com> Cc: Michael Chan <mchan@broadcom.com> Cc: Hariprasad S <hariprasad@chelsio.com> Cc: Sathya Perla <sathya.perla@emulex.com> Cc: Subbu Seetharaman <subbu.seetharaman@emulex.com> Cc: Ajit Khaparde <ajit.khaparde@emulex.com> Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Cc: Jesse Brandeburg <jesse.brandeburg@intel.com> Cc: Bruce Allan <bruce.w.allan@intel.com> Cc: Carolyn Wyborny <carolyn.wyborny@intel.com> Cc: Don Skidmore <donald.c.skidmore@intel.com> Cc: Greg Rose <gregory.v.rose@intel.com> Cc: Matthew Vick <matthew.vick@intel.com> Cc: John Ronciak <john.ronciak@intel.com> Cc: Mitch Williams <mitch.a.williams@intel.com> Cc: Amir Vadai <amirv@mellanox.com> Cc: Solarflare linux maintainers <linux-net-drivers@solarflare.com> Cc: Shradha Shah <sshah@solarflare.com> Cc: Shreyas Bhatewara <sbhatewara@vmware.com> Cc: "VMware, Inc." <pv-drivers@vmware.com> Cc: Ben Hutchings <ben@decadent.org.uk> Signed-off-by: Eyal Perry <eyalpe@mellanox.com> Signed-off-by: Amir Vadai <amirv@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-03 00:12:10 +08:00
ret = ops->set_rxfh(dev, indir, NULL, ETH_RSS_HASH_NO_CHANGE);
ethtool: correctly ensure {GS}CHANNELS doesn't conflict with GS{RXFH} Ethernet drivers implementing both {GS}RXFH and {GS}CHANNELS ethtool ops incorrectly allow SCHANNELS when it would conflict with the settings from SRXFH. This occurs because it is not possible for drivers to understand whether their Rx flow indirection table has been configured or is in the default state. In addition, drivers currently behave in various ways when increasing the number of Rx channels. Some drivers will always destroy the Rx flow indirection table when this occurs, whether it has been set by the user or not. Other drivers will attempt to preserve the table even if the user has never modified it from the default driver settings. Neither of these situation is desirable because it leads to unexpected behavior or loss of user configuration. The correct behavior is to simply return -EINVAL when SCHANNELS would conflict with the current Rx flow table settings. However, it should only do so if the current settings were modified by the user. If we required that the new settings never conflict with the current (default) Rx flow settings, we would force users to first reduce their Rx flow settings and then reduce the number of Rx channels. This patch proposes a solution implemented in net/core/ethtool.c which ensures that all drivers behave correctly. It checks whether the RXFH table has been configured to non-default settings, and stores this information in a private netdev flag. When the number of channels is requested to change, it first ensures that the current Rx flow table is not going to assign flows to now disabled channels. Signed-off-by: Jacob Keller <jacob.e.keller@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-09 08:05:03 +08:00
if (ret)
goto out;
/* indicate whether rxfh was set to default */
if (user_size == 0)
dev->priv_flags &= ~IFF_RXFH_CONFIGURED;
else
dev->priv_flags |= IFF_RXFH_CONFIGURED;
out:
kfree(indir);
return ret;
}
static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
void __user *useraddr)
{
int ret;
const struct ethtool_ops *ops = dev->ethtool_ops;
u32 user_indir_size, user_key_size;
u32 dev_indir_size = 0, dev_key_size = 0;
struct ethtool_rxfh rxfh;
u32 total_size;
u32 indir_bytes;
u32 *indir = NULL;
ethtool: Support for configurable RSS hash function This patch extends the set/get_rxfh ethtool-options for getting or setting the RSS hash function. It modifies drivers implementation of set/get_rxfh accordingly. This change also delegates the responsibility of checking whether a modification to a certain RX flow hash parameter is supported to the driver implementation of set_rxfh. User-kernel API is done through the new hfunc bitmask field in the ethtool_rxfh struct. A bit set in the hfunc field is corresponding to an index in the new string-set ETH_SS_RSS_HASH_FUNCS. Got approval from most of the relevant driver maintainers that their driver is using Toeplitz, and for the few that didn't answered, also assumed it is Toeplitz. Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Ariel Elior <ariel.elior@qlogic.com> Cc: Prashant Sreedharan <prashant@broadcom.com> Cc: Michael Chan <mchan@broadcom.com> Cc: Hariprasad S <hariprasad@chelsio.com> Cc: Sathya Perla <sathya.perla@emulex.com> Cc: Subbu Seetharaman <subbu.seetharaman@emulex.com> Cc: Ajit Khaparde <ajit.khaparde@emulex.com> Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Cc: Jesse Brandeburg <jesse.brandeburg@intel.com> Cc: Bruce Allan <bruce.w.allan@intel.com> Cc: Carolyn Wyborny <carolyn.wyborny@intel.com> Cc: Don Skidmore <donald.c.skidmore@intel.com> Cc: Greg Rose <gregory.v.rose@intel.com> Cc: Matthew Vick <matthew.vick@intel.com> Cc: John Ronciak <john.ronciak@intel.com> Cc: Mitch Williams <mitch.a.williams@intel.com> Cc: Amir Vadai <amirv@mellanox.com> Cc: Solarflare linux maintainers <linux-net-drivers@solarflare.com> Cc: Shradha Shah <sshah@solarflare.com> Cc: Shreyas Bhatewara <sbhatewara@vmware.com> Cc: "VMware, Inc." <pv-drivers@vmware.com> Cc: Ben Hutchings <ben@decadent.org.uk> Signed-off-by: Eyal Perry <eyalpe@mellanox.com> Signed-off-by: Amir Vadai <amirv@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-03 00:12:10 +08:00
u8 dev_hfunc = 0;
u8 *hkey = NULL;
u8 *rss_config;
ethtool: Support for configurable RSS hash function This patch extends the set/get_rxfh ethtool-options for getting or setting the RSS hash function. It modifies drivers implementation of set/get_rxfh accordingly. This change also delegates the responsibility of checking whether a modification to a certain RX flow hash parameter is supported to the driver implementation of set_rxfh. User-kernel API is done through the new hfunc bitmask field in the ethtool_rxfh struct. A bit set in the hfunc field is corresponding to an index in the new string-set ETH_SS_RSS_HASH_FUNCS. Got approval from most of the relevant driver maintainers that their driver is using Toeplitz, and for the few that didn't answered, also assumed it is Toeplitz. Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Ariel Elior <ariel.elior@qlogic.com> Cc: Prashant Sreedharan <prashant@broadcom.com> Cc: Michael Chan <mchan@broadcom.com> Cc: Hariprasad S <hariprasad@chelsio.com> Cc: Sathya Perla <sathya.perla@emulex.com> Cc: Subbu Seetharaman <subbu.seetharaman@emulex.com> Cc: Ajit Khaparde <ajit.khaparde@emulex.com> Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Cc: Jesse Brandeburg <jesse.brandeburg@intel.com> Cc: Bruce Allan <bruce.w.allan@intel.com> Cc: Carolyn Wyborny <carolyn.wyborny@intel.com> Cc: Don Skidmore <donald.c.skidmore@intel.com> Cc: Greg Rose <gregory.v.rose@intel.com> Cc: Matthew Vick <matthew.vick@intel.com> Cc: John Ronciak <john.ronciak@intel.com> Cc: Mitch Williams <mitch.a.williams@intel.com> Cc: Amir Vadai <amirv@mellanox.com> Cc: Solarflare linux maintainers <linux-net-drivers@solarflare.com> Cc: Shradha Shah <sshah@solarflare.com> Cc: Shreyas Bhatewara <sbhatewara@vmware.com> Cc: "VMware, Inc." <pv-drivers@vmware.com> Cc: Ben Hutchings <ben@decadent.org.uk> Signed-off-by: Eyal Perry <eyalpe@mellanox.com> Signed-off-by: Amir Vadai <amirv@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-03 00:12:10 +08:00
if (!ops->get_rxfh)
return -EOPNOTSUPP;
if (ops->get_rxfh_indir_size)
dev_indir_size = ops->get_rxfh_indir_size(dev);
if (ops->get_rxfh_key_size)
dev_key_size = ops->get_rxfh_key_size(dev);
if (copy_from_user(&rxfh, useraddr, sizeof(rxfh)))
return -EFAULT;
user_indir_size = rxfh.indir_size;
user_key_size = rxfh.key_size;
/* Check that reserved fields are 0 for now */
if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd8[2] || rxfh.rsvd32)
return -EINVAL;
/* Most drivers don't handle rss_context, check it's 0 as well */
if (rxfh.rss_context && !ops->get_rxfh_context)
return -EOPNOTSUPP;
rxfh.indir_size = dev_indir_size;
rxfh.key_size = dev_key_size;
if (copy_to_user(useraddr, &rxfh, sizeof(rxfh)))
return -EFAULT;
if ((user_indir_size && (user_indir_size != dev_indir_size)) ||
(user_key_size && (user_key_size != dev_key_size)))
return -EINVAL;
indir_bytes = user_indir_size * sizeof(indir[0]);
total_size = indir_bytes + user_key_size;
rss_config = kzalloc(total_size, GFP_USER);
if (!rss_config)
return -ENOMEM;
if (user_indir_size)
indir = (u32 *)rss_config;
if (user_key_size)
hkey = rss_config + indir_bytes;
if (rxfh.rss_context)
ret = dev->ethtool_ops->get_rxfh_context(dev, indir, hkey,
&dev_hfunc,
rxfh.rss_context);
else
ret = dev->ethtool_ops->get_rxfh(dev, indir, hkey, &dev_hfunc);
ethtool: Support for configurable RSS hash function This patch extends the set/get_rxfh ethtool-options for getting or setting the RSS hash function. It modifies drivers implementation of set/get_rxfh accordingly. This change also delegates the responsibility of checking whether a modification to a certain RX flow hash parameter is supported to the driver implementation of set_rxfh. User-kernel API is done through the new hfunc bitmask field in the ethtool_rxfh struct. A bit set in the hfunc field is corresponding to an index in the new string-set ETH_SS_RSS_HASH_FUNCS. Got approval from most of the relevant driver maintainers that their driver is using Toeplitz, and for the few that didn't answered, also assumed it is Toeplitz. Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Ariel Elior <ariel.elior@qlogic.com> Cc: Prashant Sreedharan <prashant@broadcom.com> Cc: Michael Chan <mchan@broadcom.com> Cc: Hariprasad S <hariprasad@chelsio.com> Cc: Sathya Perla <sathya.perla@emulex.com> Cc: Subbu Seetharaman <subbu.seetharaman@emulex.com> Cc: Ajit Khaparde <ajit.khaparde@emulex.com> Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Cc: Jesse Brandeburg <jesse.brandeburg@intel.com> Cc: Bruce Allan <bruce.w.allan@intel.com> Cc: Carolyn Wyborny <carolyn.wyborny@intel.com> Cc: Don Skidmore <donald.c.skidmore@intel.com> Cc: Greg Rose <gregory.v.rose@intel.com> Cc: Matthew Vick <matthew.vick@intel.com> Cc: John Ronciak <john.ronciak@intel.com> Cc: Mitch Williams <mitch.a.williams@intel.com> Cc: Amir Vadai <amirv@mellanox.com> Cc: Solarflare linux maintainers <linux-net-drivers@solarflare.com> Cc: Shradha Shah <sshah@solarflare.com> Cc: Shreyas Bhatewara <sbhatewara@vmware.com> Cc: "VMware, Inc." <pv-drivers@vmware.com> Cc: Ben Hutchings <ben@decadent.org.uk> Signed-off-by: Eyal Perry <eyalpe@mellanox.com> Signed-off-by: Amir Vadai <amirv@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-03 00:12:10 +08:00
if (ret)
goto out;
ethtool: Support for configurable RSS hash function This patch extends the set/get_rxfh ethtool-options for getting or setting the RSS hash function. It modifies drivers implementation of set/get_rxfh accordingly. This change also delegates the responsibility of checking whether a modification to a certain RX flow hash parameter is supported to the driver implementation of set_rxfh. User-kernel API is done through the new hfunc bitmask field in the ethtool_rxfh struct. A bit set in the hfunc field is corresponding to an index in the new string-set ETH_SS_RSS_HASH_FUNCS. Got approval from most of the relevant driver maintainers that their driver is using Toeplitz, and for the few that didn't answered, also assumed it is Toeplitz. Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Ariel Elior <ariel.elior@qlogic.com> Cc: Prashant Sreedharan <prashant@broadcom.com> Cc: Michael Chan <mchan@broadcom.com> Cc: Hariprasad S <hariprasad@chelsio.com> Cc: Sathya Perla <sathya.perla@emulex.com> Cc: Subbu Seetharaman <subbu.seetharaman@emulex.com> Cc: Ajit Khaparde <ajit.khaparde@emulex.com> Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Cc: Jesse Brandeburg <jesse.brandeburg@intel.com> Cc: Bruce Allan <bruce.w.allan@intel.com> Cc: Carolyn Wyborny <carolyn.wyborny@intel.com> Cc: Don Skidmore <donald.c.skidmore@intel.com> Cc: Greg Rose <gregory.v.rose@intel.com> Cc: Matthew Vick <matthew.vick@intel.com> Cc: John Ronciak <john.ronciak@intel.com> Cc: Mitch Williams <mitch.a.williams@intel.com> Cc: Amir Vadai <amirv@mellanox.com> Cc: Solarflare linux maintainers <linux-net-drivers@solarflare.com> Cc: Shradha Shah <sshah@solarflare.com> Cc: Shreyas Bhatewara <sbhatewara@vmware.com> Cc: "VMware, Inc." <pv-drivers@vmware.com> Cc: Ben Hutchings <ben@decadent.org.uk> Signed-off-by: Eyal Perry <eyalpe@mellanox.com> Signed-off-by: Amir Vadai <amirv@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-03 00:12:10 +08:00
if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh, hfunc),
&dev_hfunc, sizeof(rxfh.hfunc))) {
ret = -EFAULT;
} else if (copy_to_user(useraddr +
offsetof(struct ethtool_rxfh, rss_config[0]),
rss_config, total_size)) {
ret = -EFAULT;
}
out:
kfree(rss_config);
return ret;
}
static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
void __user *useraddr)
{
int ret;
const struct ethtool_ops *ops = dev->ethtool_ops;
struct ethtool_rxnfc rx_rings;
struct ethtool_rxfh rxfh;
u32 dev_indir_size = 0, dev_key_size = 0, i;
u32 *indir = NULL, indir_bytes = 0;
u8 *hkey = NULL;
u8 *rss_config;
u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]);
bool delete = false;
ethtool: Support for configurable RSS hash function This patch extends the set/get_rxfh ethtool-options for getting or setting the RSS hash function. It modifies drivers implementation of set/get_rxfh accordingly. This change also delegates the responsibility of checking whether a modification to a certain RX flow hash parameter is supported to the driver implementation of set_rxfh. User-kernel API is done through the new hfunc bitmask field in the ethtool_rxfh struct. A bit set in the hfunc field is corresponding to an index in the new string-set ETH_SS_RSS_HASH_FUNCS. Got approval from most of the relevant driver maintainers that their driver is using Toeplitz, and for the few that didn't answered, also assumed it is Toeplitz. Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Ariel Elior <ariel.elior@qlogic.com> Cc: Prashant Sreedharan <prashant@broadcom.com> Cc: Michael Chan <mchan@broadcom.com> Cc: Hariprasad S <hariprasad@chelsio.com> Cc: Sathya Perla <sathya.perla@emulex.com> Cc: Subbu Seetharaman <subbu.seetharaman@emulex.com> Cc: Ajit Khaparde <ajit.khaparde@emulex.com> Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Cc: Jesse Brandeburg <jesse.brandeburg@intel.com> Cc: Bruce Allan <bruce.w.allan@intel.com> Cc: Carolyn Wyborny <carolyn.wyborny@intel.com> Cc: Don Skidmore <donald.c.skidmore@intel.com> Cc: Greg Rose <gregory.v.rose@intel.com> Cc: Matthew Vick <matthew.vick@intel.com> Cc: John Ronciak <john.ronciak@intel.com> Cc: Mitch Williams <mitch.a.williams@intel.com> Cc: Amir Vadai <amirv@mellanox.com> Cc: Solarflare linux maintainers <linux-net-drivers@solarflare.com> Cc: Shradha Shah <sshah@solarflare.com> Cc: Shreyas Bhatewara <sbhatewara@vmware.com> Cc: "VMware, Inc." <pv-drivers@vmware.com> Cc: Ben Hutchings <ben@decadent.org.uk> Signed-off-by: Eyal Perry <eyalpe@mellanox.com> Signed-off-by: Amir Vadai <amirv@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-03 00:12:10 +08:00
if (!ops->get_rxnfc || !ops->set_rxfh)
return -EOPNOTSUPP;
if (ops->get_rxfh_indir_size)
dev_indir_size = ops->get_rxfh_indir_size(dev);
if (ops->get_rxfh_key_size)
dev_key_size = ops->get_rxfh_key_size(dev);
if (copy_from_user(&rxfh, useraddr, sizeof(rxfh)))
return -EFAULT;
/* Check that reserved fields are 0 for now */
if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd8[2] || rxfh.rsvd32)
return -EINVAL;
/* Most drivers don't handle rss_context, check it's 0 as well */
if (rxfh.rss_context && !ops->set_rxfh_context)
return -EOPNOTSUPP;
ethtool: Support for configurable RSS hash function This patch extends the set/get_rxfh ethtool-options for getting or setting the RSS hash function. It modifies drivers implementation of set/get_rxfh accordingly. This change also delegates the responsibility of checking whether a modification to a certain RX flow hash parameter is supported to the driver implementation of set_rxfh. User-kernel API is done through the new hfunc bitmask field in the ethtool_rxfh struct. A bit set in the hfunc field is corresponding to an index in the new string-set ETH_SS_RSS_HASH_FUNCS. Got approval from most of the relevant driver maintainers that their driver is using Toeplitz, and for the few that didn't answered, also assumed it is Toeplitz. Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Ariel Elior <ariel.elior@qlogic.com> Cc: Prashant Sreedharan <prashant@broadcom.com> Cc: Michael Chan <mchan@broadcom.com> Cc: Hariprasad S <hariprasad@chelsio.com> Cc: Sathya Perla <sathya.perla@emulex.com> Cc: Subbu Seetharaman <subbu.seetharaman@emulex.com> Cc: Ajit Khaparde <ajit.khaparde@emulex.com> Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Cc: Jesse Brandeburg <jesse.brandeburg@intel.com> Cc: Bruce Allan <bruce.w.allan@intel.com> Cc: Carolyn Wyborny <carolyn.wyborny@intel.com> Cc: Don Skidmore <donald.c.skidmore@intel.com> Cc: Greg Rose <gregory.v.rose@intel.com> Cc: Matthew Vick <matthew.vick@intel.com> Cc: John Ronciak <john.ronciak@intel.com> Cc: Mitch Williams <mitch.a.williams@intel.com> Cc: Amir Vadai <amirv@mellanox.com> Cc: Solarflare linux maintainers <linux-net-drivers@solarflare.com> Cc: Shradha Shah <sshah@solarflare.com> Cc: Shreyas Bhatewara <sbhatewara@vmware.com> Cc: "VMware, Inc." <pv-drivers@vmware.com> Cc: Ben Hutchings <ben@decadent.org.uk> Signed-off-by: Eyal Perry <eyalpe@mellanox.com> Signed-off-by: Amir Vadai <amirv@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-03 00:12:10 +08:00
/* If either indir, hash key or function is valid, proceed further.
* Must request at least one change: indir size, hash key or function.
*/
if ((rxfh.indir_size &&
rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE &&
rxfh.indir_size != dev_indir_size) ||
(rxfh.key_size && (rxfh.key_size != dev_key_size)) ||
(rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE &&
ethtool: Support for configurable RSS hash function This patch extends the set/get_rxfh ethtool-options for getting or setting the RSS hash function. It modifies drivers implementation of set/get_rxfh accordingly. This change also delegates the responsibility of checking whether a modification to a certain RX flow hash parameter is supported to the driver implementation of set_rxfh. User-kernel API is done through the new hfunc bitmask field in the ethtool_rxfh struct. A bit set in the hfunc field is corresponding to an index in the new string-set ETH_SS_RSS_HASH_FUNCS. Got approval from most of the relevant driver maintainers that their driver is using Toeplitz, and for the few that didn't answered, also assumed it is Toeplitz. Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Ariel Elior <ariel.elior@qlogic.com> Cc: Prashant Sreedharan <prashant@broadcom.com> Cc: Michael Chan <mchan@broadcom.com> Cc: Hariprasad S <hariprasad@chelsio.com> Cc: Sathya Perla <sathya.perla@emulex.com> Cc: Subbu Seetharaman <subbu.seetharaman@emulex.com> Cc: Ajit Khaparde <ajit.khaparde@emulex.com> Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Cc: Jesse Brandeburg <jesse.brandeburg@intel.com> Cc: Bruce Allan <bruce.w.allan@intel.com> Cc: Carolyn Wyborny <carolyn.wyborny@intel.com> Cc: Don Skidmore <donald.c.skidmore@intel.com> Cc: Greg Rose <gregory.v.rose@intel.com> Cc: Matthew Vick <matthew.vick@intel.com> Cc: John Ronciak <john.ronciak@intel.com> Cc: Mitch Williams <mitch.a.williams@intel.com> Cc: Amir Vadai <amirv@mellanox.com> Cc: Solarflare linux maintainers <linux-net-drivers@solarflare.com> Cc: Shradha Shah <sshah@solarflare.com> Cc: Shreyas Bhatewara <sbhatewara@vmware.com> Cc: "VMware, Inc." <pv-drivers@vmware.com> Cc: Ben Hutchings <ben@decadent.org.uk> Signed-off-by: Eyal Perry <eyalpe@mellanox.com> Signed-off-by: Amir Vadai <amirv@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-03 00:12:10 +08:00
rxfh.key_size == 0 && rxfh.hfunc == ETH_RSS_HASH_NO_CHANGE))
return -EINVAL;
if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE)
indir_bytes = dev_indir_size * sizeof(indir[0]);
rss_config = kzalloc(indir_bytes + rxfh.key_size, GFP_USER);
if (!rss_config)
return -ENOMEM;
rx_rings.cmd = ETHTOOL_GRXRINGS;
ret = ops->get_rxnfc(dev, &rx_rings, NULL);
if (ret)
goto out;
/* rxfh.indir_size == 0 means reset the indir table to default (master
* context) or delete the context (other RSS contexts).
* rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE means leave it unchanged.
*/
if (rxfh.indir_size &&
rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) {
indir = (u32 *)rss_config;
ret = ethtool_copy_validate_indir(indir,
useraddr + rss_cfg_offset,
&rx_rings,
rxfh.indir_size);
if (ret)
goto out;
} else if (rxfh.indir_size == 0) {
if (rxfh.rss_context == 0) {
indir = (u32 *)rss_config;
for (i = 0; i < dev_indir_size; i++)
indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data);
} else {
delete = true;
}
}
if (rxfh.key_size) {
hkey = rss_config + indir_bytes;
if (copy_from_user(hkey,
useraddr + rss_cfg_offset + indir_bytes,
rxfh.key_size)) {
ret = -EFAULT;
goto out;
}
}
if (rxfh.rss_context)
ret = ops->set_rxfh_context(dev, indir, hkey, rxfh.hfunc,
&rxfh.rss_context, delete);
else
ret = ops->set_rxfh(dev, indir, hkey, rxfh.hfunc);
ethtool: correctly ensure {GS}CHANNELS doesn't conflict with GS{RXFH} Ethernet drivers implementing both {GS}RXFH and {GS}CHANNELS ethtool ops incorrectly allow SCHANNELS when it would conflict with the settings from SRXFH. This occurs because it is not possible for drivers to understand whether their Rx flow indirection table has been configured or is in the default state. In addition, drivers currently behave in various ways when increasing the number of Rx channels. Some drivers will always destroy the Rx flow indirection table when this occurs, whether it has been set by the user or not. Other drivers will attempt to preserve the table even if the user has never modified it from the default driver settings. Neither of these situation is desirable because it leads to unexpected behavior or loss of user configuration. The correct behavior is to simply return -EINVAL when SCHANNELS would conflict with the current Rx flow table settings. However, it should only do so if the current settings were modified by the user. If we required that the new settings never conflict with the current (default) Rx flow settings, we would force users to first reduce their Rx flow settings and then reduce the number of Rx channels. This patch proposes a solution implemented in net/core/ethtool.c which ensures that all drivers behave correctly. It checks whether the RXFH table has been configured to non-default settings, and stores this information in a private netdev flag. When the number of channels is requested to change, it first ensures that the current Rx flow table is not going to assign flows to now disabled channels. Signed-off-by: Jacob Keller <jacob.e.keller@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-09 08:05:03 +08:00
if (ret)
goto out;
if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh, rss_context),
&rxfh.rss_context, sizeof(rxfh.rss_context)))
ret = -EFAULT;
if (!rxfh.rss_context) {
/* indicate whether rxfh was set to default */
if (rxfh.indir_size == 0)
dev->priv_flags &= ~IFF_RXFH_CONFIGURED;
else if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE)
dev->priv_flags |= IFF_RXFH_CONFIGURED;
}
out:
kfree(rss_config);
return ret;
}
static int ethtool_get_regs(struct net_device *dev, char __user *useraddr)
{
struct ethtool_regs regs;
const struct ethtool_ops *ops = dev->ethtool_ops;
void *regbuf;
int reglen, ret;
if (!ops->get_regs || !ops->get_regs_len)
return -EOPNOTSUPP;
if (copy_from_user(&regs, useraddr, sizeof(regs)))
return -EFAULT;
reglen = ops->get_regs_len(dev);
if (reglen <= 0)
return reglen;
if (regs.len > reglen)
regs.len = reglen;
regbuf = vzalloc(reglen);
if (!regbuf)
return -ENOMEM;
if (regs.len < reglen)
reglen = regs.len;
ops->get_regs(dev, &regs, regbuf);
ret = -EFAULT;
if (copy_to_user(useraddr, &regs, sizeof(regs)))
goto out;
useraddr += offsetof(struct ethtool_regs, data);
if (copy_to_user(useraddr, regbuf, reglen))
goto out;
ret = 0;
out:
vfree(regbuf);
return ret;
}
static int ethtool_reset(struct net_device *dev, char __user *useraddr)
{
struct ethtool_value reset;
int ret;
if (!dev->ethtool_ops->reset)
return -EOPNOTSUPP;
if (copy_from_user(&reset, useraddr, sizeof(reset)))
return -EFAULT;
ret = dev->ethtool_ops->reset(dev, &reset.data);
if (ret)
return ret;
if (copy_to_user(useraddr, &reset, sizeof(reset)))
return -EFAULT;
return 0;
}
static int ethtool_get_wol(struct net_device *dev, char __user *useraddr)
{
struct ethtool_wolinfo wol;
if (!dev->ethtool_ops->get_wol)
return -EOPNOTSUPP;
memset(&wol, 0, sizeof(struct ethtool_wolinfo));
wol.cmd = ETHTOOL_GWOL;
dev->ethtool_ops->get_wol(dev, &wol);
if (copy_to_user(useraddr, &wol, sizeof(wol)))
return -EFAULT;
return 0;
}
static int ethtool_set_wol(struct net_device *dev, char __user *useraddr)
{
struct ethtool_wolinfo wol;
int ret;
if (!dev->ethtool_ops->set_wol)
return -EOPNOTSUPP;
if (copy_from_user(&wol, useraddr, sizeof(wol)))
return -EFAULT;
ret = dev->ethtool_ops->set_wol(dev, &wol);
if (ret)
return ret;
dev->wol_enabled = !!wol.wolopts;
ethtool_notify(dev, ETHTOOL_MSG_WOL_NTF, NULL);
return 0;
}
static int ethtool_get_eee(struct net_device *dev, char __user *useraddr)
{
struct ethtool_eee edata;
int rc;
if (!dev->ethtool_ops->get_eee)
return -EOPNOTSUPP;
memset(&edata, 0, sizeof(struct ethtool_eee));
edata.cmd = ETHTOOL_GEEE;
rc = dev->ethtool_ops->get_eee(dev, &edata);
if (rc)
return rc;
if (copy_to_user(useraddr, &edata, sizeof(edata)))
return -EFAULT;
return 0;
}
static int ethtool_set_eee(struct net_device *dev, char __user *useraddr)
{
struct ethtool_eee edata;
int ret;
if (!dev->ethtool_ops->set_eee)
return -EOPNOTSUPP;
if (copy_from_user(&edata, useraddr, sizeof(edata)))
return -EFAULT;
ret = dev->ethtool_ops->set_eee(dev, &edata);
if (!ret)
ethtool_notify(dev, ETHTOOL_MSG_EEE_NTF, NULL);
return ret;
}
static int ethtool_nway_reset(struct net_device *dev)
{
if (!dev->ethtool_ops->nway_reset)
return -EOPNOTSUPP;
return dev->ethtool_ops->nway_reset(dev);
}
static int ethtool_get_link(struct net_device *dev, char __user *useraddr)
{
struct ethtool_value edata = { .cmd = ETHTOOL_GLINK };
int link = __ethtool_get_link(dev);
if (link < 0)
return link;
edata.data = link;
if (copy_to_user(useraddr, &edata, sizeof(edata)))
return -EFAULT;
return 0;
}
static int ethtool_get_any_eeprom(struct net_device *dev, void __user *useraddr,
int (*getter)(struct net_device *,
struct ethtool_eeprom *, u8 *),
u32 total_len)
{
struct ethtool_eeprom eeprom;
void __user *userbuf = useraddr + sizeof(eeprom);
u32 bytes_remaining;
u8 *data;
int ret = 0;
if (copy_from_user(&eeprom, useraddr, sizeof(eeprom)))
return -EFAULT;
/* Check for wrap and zero */
if (eeprom.offset + eeprom.len <= eeprom.offset)
return -EINVAL;
/* Check for exceeding total eeprom len */
if (eeprom.offset + eeprom.len > total_len)
return -EINVAL;
data = kzalloc(PAGE_SIZE, GFP_USER);
if (!data)
return -ENOMEM;
bytes_remaining = eeprom.len;
while (bytes_remaining > 0) {
eeprom.len = min(bytes_remaining, (u32)PAGE_SIZE);
ret = getter(dev, &eeprom, data);
if (ret)
break;
if (!eeprom.len) {
ret = -EIO;
break;
}
if (copy_to_user(userbuf, data, eeprom.len)) {
ret = -EFAULT;
break;
}
userbuf += eeprom.len;
eeprom.offset += eeprom.len;
bytes_remaining -= eeprom.len;
}
eeprom.len = userbuf - (useraddr + sizeof(eeprom));
eeprom.offset -= eeprom.len;
if (copy_to_user(useraddr, &eeprom, sizeof(eeprom)))
ret = -EFAULT;
kfree(data);
return ret;
}
static int ethtool_get_eeprom(struct net_device *dev, void __user *useraddr)
{
const struct ethtool_ops *ops = dev->ethtool_ops;
if (!ops->get_eeprom || !ops->get_eeprom_len ||
!ops->get_eeprom_len(dev))
return -EOPNOTSUPP;
return ethtool_get_any_eeprom(dev, useraddr, ops->get_eeprom,
ops->get_eeprom_len(dev));
}
static int ethtool_set_eeprom(struct net_device *dev, void __user *useraddr)
{
struct ethtool_eeprom eeprom;
const struct ethtool_ops *ops = dev->ethtool_ops;
void __user *userbuf = useraddr + sizeof(eeprom);
u32 bytes_remaining;
u8 *data;
int ret = 0;
if (!ops->set_eeprom || !ops->get_eeprom_len ||
!ops->get_eeprom_len(dev))
return -EOPNOTSUPP;
if (copy_from_user(&eeprom, useraddr, sizeof(eeprom)))
return -EFAULT;
/* Check for wrap and zero */
if (eeprom.offset + eeprom.len <= eeprom.offset)
return -EINVAL;
/* Check for exceeding total eeprom len */
if (eeprom.offset + eeprom.len > ops->get_eeprom_len(dev))
return -EINVAL;
data = kzalloc(PAGE_SIZE, GFP_USER);
if (!data)
return -ENOMEM;
bytes_remaining = eeprom.len;
while (bytes_remaining > 0) {
eeprom.len = min(bytes_remaining, (u32)PAGE_SIZE);
if (copy_from_user(data, userbuf, eeprom.len)) {
ret = -EFAULT;
break;
}
ret = ops->set_eeprom(dev, &eeprom, data);
if (ret)
break;
userbuf += eeprom.len;
eeprom.offset += eeprom.len;
bytes_remaining -= eeprom.len;
}
kfree(data);
return ret;
}
static noinline_for_stack int ethtool_get_coalesce(struct net_device *dev,
void __user *useraddr)
{
struct ethtool_coalesce coalesce = { .cmd = ETHTOOL_GCOALESCE };
struct kernel_ethtool_coalesce kernel_coalesce = {};
int ret;
if (!dev->ethtool_ops->get_coalesce)
return -EOPNOTSUPP;
ret = dev->ethtool_ops->get_coalesce(dev, &coalesce, &kernel_coalesce,
NULL);
if (ret)
return ret;
if (copy_to_user(useraddr, &coalesce, sizeof(coalesce)))
return -EFAULT;
return 0;
}
static bool
ethtool_set_coalesce_supported(struct net_device *dev,
struct ethtool_coalesce *coalesce)
{
u32 supported_params = dev->ethtool_ops->supported_coalesce_params;
u32 nonzero_params = 0;
if (coalesce->rx_coalesce_usecs)
nonzero_params |= ETHTOOL_COALESCE_RX_USECS;
if (coalesce->rx_max_coalesced_frames)
nonzero_params |= ETHTOOL_COALESCE_RX_MAX_FRAMES;
if (coalesce->rx_coalesce_usecs_irq)
nonzero_params |= ETHTOOL_COALESCE_RX_USECS_IRQ;
if (coalesce->rx_max_coalesced_frames_irq)
nonzero_params |= ETHTOOL_COALESCE_RX_MAX_FRAMES_IRQ;
if (coalesce->tx_coalesce_usecs)
nonzero_params |= ETHTOOL_COALESCE_TX_USECS;
if (coalesce->tx_max_coalesced_frames)
nonzero_params |= ETHTOOL_COALESCE_TX_MAX_FRAMES;
if (coalesce->tx_coalesce_usecs_irq)
nonzero_params |= ETHTOOL_COALESCE_TX_USECS_IRQ;
if (coalesce->tx_max_coalesced_frames_irq)
nonzero_params |= ETHTOOL_COALESCE_TX_MAX_FRAMES_IRQ;
if (coalesce->stats_block_coalesce_usecs)
nonzero_params |= ETHTOOL_COALESCE_STATS_BLOCK_USECS;
if (coalesce->use_adaptive_rx_coalesce)
nonzero_params |= ETHTOOL_COALESCE_USE_ADAPTIVE_RX;
if (coalesce->use_adaptive_tx_coalesce)
nonzero_params |= ETHTOOL_COALESCE_USE_ADAPTIVE_TX;
if (coalesce->pkt_rate_low)
nonzero_params |= ETHTOOL_COALESCE_PKT_RATE_LOW;
if (coalesce->rx_coalesce_usecs_low)
nonzero_params |= ETHTOOL_COALESCE_RX_USECS_LOW;
if (coalesce->rx_max_coalesced_frames_low)
nonzero_params |= ETHTOOL_COALESCE_RX_MAX_FRAMES_LOW;
if (coalesce->tx_coalesce_usecs_low)
nonzero_params |= ETHTOOL_COALESCE_TX_USECS_LOW;
if (coalesce->tx_max_coalesced_frames_low)
nonzero_params |= ETHTOOL_COALESCE_TX_MAX_FRAMES_LOW;
if (coalesce->pkt_rate_high)
nonzero_params |= ETHTOOL_COALESCE_PKT_RATE_HIGH;
if (coalesce->rx_coalesce_usecs_high)
nonzero_params |= ETHTOOL_COALESCE_RX_USECS_HIGH;
if (coalesce->rx_max_coalesced_frames_high)
nonzero_params |= ETHTOOL_COALESCE_RX_MAX_FRAMES_HIGH;
if (coalesce->tx_coalesce_usecs_high)
nonzero_params |= ETHTOOL_COALESCE_TX_USECS_HIGH;
if (coalesce->tx_max_coalesced_frames_high)
nonzero_params |= ETHTOOL_COALESCE_TX_MAX_FRAMES_HIGH;
if (coalesce->rate_sample_interval)
nonzero_params |= ETHTOOL_COALESCE_RATE_SAMPLE_INTERVAL;
return (supported_params & nonzero_params) == nonzero_params;
}
static noinline_for_stack int ethtool_set_coalesce(struct net_device *dev,
void __user *useraddr)
{
struct kernel_ethtool_coalesce kernel_coalesce = {};
struct ethtool_coalesce coalesce;
int ret;
if (!dev->ethtool_ops->set_coalesce || !dev->ethtool_ops->get_coalesce)
return -EOPNOTSUPP;
ret = dev->ethtool_ops->get_coalesce(dev, &coalesce, &kernel_coalesce,
NULL);
if (ret)
return ret;
if (copy_from_user(&coalesce, useraddr, sizeof(coalesce)))
return -EFAULT;
if (!ethtool_set_coalesce_supported(dev, &coalesce))
return -EOPNOTSUPP;
ret = dev->ethtool_ops->set_coalesce(dev, &coalesce, &kernel_coalesce,
NULL);
if (!ret)
ethtool_notify(dev, ETHTOOL_MSG_COALESCE_NTF, NULL);
return ret;
}
static int ethtool_get_ringparam(struct net_device *dev, void __user *useraddr)
{
struct ethtool_ringparam ringparam = { .cmd = ETHTOOL_GRINGPARAM };
struct kernel_ethtool_ringparam kernel_ringparam = {};
if (!dev->ethtool_ops->get_ringparam)
return -EOPNOTSUPP;
dev->ethtool_ops->get_ringparam(dev, &ringparam,
&kernel_ringparam, NULL);
if (copy_to_user(useraddr, &ringparam, sizeof(ringparam)))
return -EFAULT;
return 0;
}
static int ethtool_set_ringparam(struct net_device *dev, void __user *useraddr)
{
struct ethtool_ringparam ringparam, max = { .cmd = ETHTOOL_GRINGPARAM };
struct kernel_ethtool_ringparam kernel_ringparam;
int ret;
if (!dev->ethtool_ops->set_ringparam || !dev->ethtool_ops->get_ringparam)
return -EOPNOTSUPP;
if (copy_from_user(&ringparam, useraddr, sizeof(ringparam)))
return -EFAULT;
dev->ethtool_ops->get_ringparam(dev, &max, &kernel_ringparam, NULL);
/* ensure new ring parameters are within the maximums */
if (ringparam.rx_pending > max.rx_max_pending ||
ringparam.rx_mini_pending > max.rx_mini_max_pending ||
ringparam.rx_jumbo_pending > max.rx_jumbo_max_pending ||
ringparam.tx_pending > max.tx_max_pending)
return -EINVAL;
ret = dev->ethtool_ops->set_ringparam(dev, &ringparam,
&kernel_ringparam, NULL);
if (!ret)
ethtool_notify(dev, ETHTOOL_MSG_RINGS_NTF, NULL);
return ret;
}
static noinline_for_stack int ethtool_get_channels(struct net_device *dev,
void __user *useraddr)
{
struct ethtool_channels channels = { .cmd = ETHTOOL_GCHANNELS };
if (!dev->ethtool_ops->get_channels)
return -EOPNOTSUPP;
dev->ethtool_ops->get_channels(dev, &channels);
if (copy_to_user(useraddr, &channels, sizeof(channels)))
return -EFAULT;
return 0;
}
static noinline_for_stack int ethtool_set_channels(struct net_device *dev,
void __user *useraddr)
{
struct ethtool_channels channels, curr = { .cmd = ETHTOOL_GCHANNELS };
u16 from_channel, to_channel;
u64 max_rxnfc_in_use;
u32 max_rxfh_in_use;
unsigned int i;
int ret;
if (!dev->ethtool_ops->set_channels || !dev->ethtool_ops->get_channels)
return -EOPNOTSUPP;
if (copy_from_user(&channels, useraddr, sizeof(channels)))
return -EFAULT;
dev->ethtool_ops->get_channels(dev, &curr);
if (channels.rx_count == curr.rx_count &&
channels.tx_count == curr.tx_count &&
channels.combined_count == curr.combined_count &&
channels.other_count == curr.other_count)
return 0;
/* ensure new counts are within the maximums */
if (channels.rx_count > curr.max_rx ||
channels.tx_count > curr.max_tx ||
channels.combined_count > curr.max_combined ||
channels.other_count > curr.max_other)
return -EINVAL;
/* ensure there is at least one RX and one TX channel */
if (!channels.combined_count &&
(!channels.rx_count || !channels.tx_count))
return -EINVAL;
ethtool: correctly ensure {GS}CHANNELS doesn't conflict with GS{RXFH} Ethernet drivers implementing both {GS}RXFH and {GS}CHANNELS ethtool ops incorrectly allow SCHANNELS when it would conflict with the settings from SRXFH. This occurs because it is not possible for drivers to understand whether their Rx flow indirection table has been configured or is in the default state. In addition, drivers currently behave in various ways when increasing the number of Rx channels. Some drivers will always destroy the Rx flow indirection table when this occurs, whether it has been set by the user or not. Other drivers will attempt to preserve the table even if the user has never modified it from the default driver settings. Neither of these situation is desirable because it leads to unexpected behavior or loss of user configuration. The correct behavior is to simply return -EINVAL when SCHANNELS would conflict with the current Rx flow table settings. However, it should only do so if the current settings were modified by the user. If we required that the new settings never conflict with the current (default) Rx flow settings, we would force users to first reduce their Rx flow settings and then reduce the number of Rx channels. This patch proposes a solution implemented in net/core/ethtool.c which ensures that all drivers behave correctly. It checks whether the RXFH table has been configured to non-default settings, and stores this information in a private netdev flag. When the number of channels is requested to change, it first ensures that the current Rx flow table is not going to assign flows to now disabled channels. Signed-off-by: Jacob Keller <jacob.e.keller@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-09 08:05:03 +08:00
/* ensure the new Rx count fits within the configured Rx flow
* indirection table/rxnfc settings */
if (ethtool_get_max_rxnfc_channel(dev, &max_rxnfc_in_use))
max_rxnfc_in_use = 0;
if (!netif_is_rxfh_configured(dev) ||
ethtool_get_max_rxfh_channel(dev, &max_rxfh_in_use))
max_rxfh_in_use = 0;
if (channels.combined_count + channels.rx_count <=
max_t(u64, max_rxnfc_in_use, max_rxfh_in_use))
return -EINVAL;
ethtool: correctly ensure {GS}CHANNELS doesn't conflict with GS{RXFH} Ethernet drivers implementing both {GS}RXFH and {GS}CHANNELS ethtool ops incorrectly allow SCHANNELS when it would conflict with the settings from SRXFH. This occurs because it is not possible for drivers to understand whether their Rx flow indirection table has been configured or is in the default state. In addition, drivers currently behave in various ways when increasing the number of Rx channels. Some drivers will always destroy the Rx flow indirection table when this occurs, whether it has been set by the user or not. Other drivers will attempt to preserve the table even if the user has never modified it from the default driver settings. Neither of these situation is desirable because it leads to unexpected behavior or loss of user configuration. The correct behavior is to simply return -EINVAL when SCHANNELS would conflict with the current Rx flow table settings. However, it should only do so if the current settings were modified by the user. If we required that the new settings never conflict with the current (default) Rx flow settings, we would force users to first reduce their Rx flow settings and then reduce the number of Rx channels. This patch proposes a solution implemented in net/core/ethtool.c which ensures that all drivers behave correctly. It checks whether the RXFH table has been configured to non-default settings, and stores this information in a private netdev flag. When the number of channels is requested to change, it first ensures that the current Rx flow table is not going to assign flows to now disabled channels. Signed-off-by: Jacob Keller <jacob.e.keller@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-09 08:05:03 +08:00
/* Disabling channels, query zero-copy AF_XDP sockets */
from_channel = channels.combined_count +
min(channels.rx_count, channels.tx_count);
to_channel = curr.combined_count + max(curr.rx_count, curr.tx_count);
for (i = from_channel; i < to_channel; i++)
if (xsk_get_pool_from_qid(dev, i))
return -EINVAL;
ret = dev->ethtool_ops->set_channels(dev, &channels);
if (!ret)
ethtool_notify(dev, ETHTOOL_MSG_CHANNELS_NTF, NULL);
return ret;
}
static int ethtool_get_pauseparam(struct net_device *dev, void __user *useraddr)
{
struct ethtool_pauseparam pauseparam = { .cmd = ETHTOOL_GPAUSEPARAM };
if (!dev->ethtool_ops->get_pauseparam)
return -EOPNOTSUPP;
dev->ethtool_ops->get_pauseparam(dev, &pauseparam);
if (copy_to_user(useraddr, &pauseparam, sizeof(pauseparam)))
return -EFAULT;
return 0;
}
static int ethtool_set_pauseparam(struct net_device *dev, void __user *useraddr)
{
struct ethtool_pauseparam pauseparam;
int ret;
if (!dev->ethtool_ops->set_pauseparam)
return -EOPNOTSUPP;
if (copy_from_user(&pauseparam, useraddr, sizeof(pauseparam)))
return -EFAULT;
ret = dev->ethtool_ops->set_pauseparam(dev, &pauseparam);
if (!ret)
ethtool_notify(dev, ETHTOOL_MSG_PAUSE_NTF, NULL);
return ret;
}
static int ethtool_self_test(struct net_device *dev, char __user *useraddr)
{
struct ethtool_test test;
const struct ethtool_ops *ops = dev->ethtool_ops;
u64 *data;
int ret, test_len;
if (!ops->self_test || !ops->get_sset_count)
return -EOPNOTSUPP;
test_len = ops->get_sset_count(dev, ETH_SS_TEST);
if (test_len < 0)
return test_len;
WARN_ON(test_len == 0);
if (copy_from_user(&test, useraddr, sizeof(test)))
return -EFAULT;
test.len = test_len;
data = kcalloc(test_len, sizeof(u64), GFP_USER);
if (!data)
return -ENOMEM;
netif_testing_on(dev);
ops->self_test(dev, &test, data);
netif_testing_off(dev);
ret = -EFAULT;
if (copy_to_user(useraddr, &test, sizeof(test)))
goto out;
useraddr += sizeof(test);
if (copy_to_user(useraddr, data, array_size(test.len, sizeof(u64))))
goto out;
ret = 0;
out:
kfree(data);
return ret;
}
static int ethtool_get_strings(struct net_device *dev, void __user *useraddr)
{
struct ethtool_gstrings gstrings;
u8 *data;
int ret;
if (copy_from_user(&gstrings, useraddr, sizeof(gstrings)))
return -EFAULT;
ret = __ethtool_get_sset_count(dev, gstrings.string_set);
if (ret < 0)
return ret;
net: ethtool: convert large order kmalloc allocations to vzalloc under memory pressure 'ethtool -S' command may warn: [ 2374.385195] ethtool: page allocation failure: order:4, mode:0x242c0c0 [ 2374.405573] CPU: 12 PID: 40211 Comm: ethtool Not tainted [ 2374.423071] Call Trace: [ 2374.423076] [<ffffffff8148cb29>] dump_stack+0x4d/0x64 [ 2374.423080] [<ffffffff811667cb>] warn_alloc_failed+0xeb/0x150 [ 2374.423082] [<ffffffff81169cd3>] ? __alloc_pages_direct_compact+0x43/0xf0 [ 2374.423084] [<ffffffff8116a25c>] __alloc_pages_nodemask+0x4dc/0xbf0 [ 2374.423091] [<ffffffffa0023dc2>] ? cmd_exec+0x722/0xcd0 [mlx5_core] [ 2374.423095] [<ffffffff811b3dcc>] alloc_pages_current+0x8c/0x110 [ 2374.423097] [<ffffffff81168859>] alloc_kmem_pages+0x19/0x90 [ 2374.423099] [<ffffffff81186e5e>] kmalloc_order_trace+0x2e/0xe0 [ 2374.423101] [<ffffffff811c0084>] __kmalloc+0x204/0x220 [ 2374.423105] [<ffffffff816c269e>] dev_ethtool+0xe4e/0x1f80 [ 2374.423106] [<ffffffff816b967e>] ? dev_get_by_name_rcu+0x5e/0x80 [ 2374.423108] [<ffffffff816d6926>] dev_ioctl+0x156/0x560 [ 2374.423111] [<ffffffff811d4c68>] ? mem_cgroup_commit_charge+0x78/0x3c0 [ 2374.423117] [<ffffffff8169d542>] sock_do_ioctl+0x42/0x50 [ 2374.423119] [<ffffffff8169d9c3>] sock_ioctl+0x1b3/0x250 [ 2374.423121] [<ffffffff811f0f42>] do_vfs_ioctl+0x92/0x580 [ 2374.423123] [<ffffffff8100222b>] ? do_audit_syscall_entry+0x4b/0x70 [ 2374.423124] [<ffffffff8100287c>] ? syscall_trace_enter_phase1+0xfc/0x120 [ 2374.423126] [<ffffffff811f14a9>] SyS_ioctl+0x79/0x90 [ 2374.423127] [<ffffffff81002bb0>] do_syscall_64+0x50/0xa0 [ 2374.423129] [<ffffffff817e19bc>] entry_SYSCALL64_slow_path+0x25/0x25 ~1160 mlx5 counters ~= order 4 allocation which is unlikely to succeed under memory pressure. Convert them to vzalloc() as ethtool_get_regs() does. Also take care of drivers without counters similar to commit 67ae7cf1eeda ("ethtool: Allow zero-length register dumps again") and reduce warn_on to warn_on_once. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-31 10:25:18 +08:00
if (ret > S32_MAX / ETH_GSTRING_LEN)
return -ENOMEM;
WARN_ON_ONCE(!ret);
gstrings.len = ret;
if (gstrings.len) {
data = vzalloc(array_size(gstrings.len, ETH_GSTRING_LEN));
if (!data)
return -ENOMEM;
__ethtool_get_strings(dev, gstrings.string_set, data);
} else {
data = NULL;
}
ret = -EFAULT;
if (copy_to_user(useraddr, &gstrings, sizeof(gstrings)))
goto out;
useraddr += sizeof(gstrings);
net: ethtool: convert large order kmalloc allocations to vzalloc under memory pressure 'ethtool -S' command may warn: [ 2374.385195] ethtool: page allocation failure: order:4, mode:0x242c0c0 [ 2374.405573] CPU: 12 PID: 40211 Comm: ethtool Not tainted [ 2374.423071] Call Trace: [ 2374.423076] [<ffffffff8148cb29>] dump_stack+0x4d/0x64 [ 2374.423080] [<ffffffff811667cb>] warn_alloc_failed+0xeb/0x150 [ 2374.423082] [<ffffffff81169cd3>] ? __alloc_pages_direct_compact+0x43/0xf0 [ 2374.423084] [<ffffffff8116a25c>] __alloc_pages_nodemask+0x4dc/0xbf0 [ 2374.423091] [<ffffffffa0023dc2>] ? cmd_exec+0x722/0xcd0 [mlx5_core] [ 2374.423095] [<ffffffff811b3dcc>] alloc_pages_current+0x8c/0x110 [ 2374.423097] [<ffffffff81168859>] alloc_kmem_pages+0x19/0x90 [ 2374.423099] [<ffffffff81186e5e>] kmalloc_order_trace+0x2e/0xe0 [ 2374.423101] [<ffffffff811c0084>] __kmalloc+0x204/0x220 [ 2374.423105] [<ffffffff816c269e>] dev_ethtool+0xe4e/0x1f80 [ 2374.423106] [<ffffffff816b967e>] ? dev_get_by_name_rcu+0x5e/0x80 [ 2374.423108] [<ffffffff816d6926>] dev_ioctl+0x156/0x560 [ 2374.423111] [<ffffffff811d4c68>] ? mem_cgroup_commit_charge+0x78/0x3c0 [ 2374.423117] [<ffffffff8169d542>] sock_do_ioctl+0x42/0x50 [ 2374.423119] [<ffffffff8169d9c3>] sock_ioctl+0x1b3/0x250 [ 2374.423121] [<ffffffff811f0f42>] do_vfs_ioctl+0x92/0x580 [ 2374.423123] [<ffffffff8100222b>] ? do_audit_syscall_entry+0x4b/0x70 [ 2374.423124] [<ffffffff8100287c>] ? syscall_trace_enter_phase1+0xfc/0x120 [ 2374.423126] [<ffffffff811f14a9>] SyS_ioctl+0x79/0x90 [ 2374.423127] [<ffffffff81002bb0>] do_syscall_64+0x50/0xa0 [ 2374.423129] [<ffffffff817e19bc>] entry_SYSCALL64_slow_path+0x25/0x25 ~1160 mlx5 counters ~= order 4 allocation which is unlikely to succeed under memory pressure. Convert them to vzalloc() as ethtool_get_regs() does. Also take care of drivers without counters similar to commit 67ae7cf1eeda ("ethtool: Allow zero-length register dumps again") and reduce warn_on to warn_on_once. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-31 10:25:18 +08:00
if (gstrings.len &&
copy_to_user(useraddr, data,
array_size(gstrings.len, ETH_GSTRING_LEN)))
goto out;
ret = 0;
out:
net: ethtool: convert large order kmalloc allocations to vzalloc under memory pressure 'ethtool -S' command may warn: [ 2374.385195] ethtool: page allocation failure: order:4, mode:0x242c0c0 [ 2374.405573] CPU: 12 PID: 40211 Comm: ethtool Not tainted [ 2374.423071] Call Trace: [ 2374.423076] [<ffffffff8148cb29>] dump_stack+0x4d/0x64 [ 2374.423080] [<ffffffff811667cb>] warn_alloc_failed+0xeb/0x150 [ 2374.423082] [<ffffffff81169cd3>] ? __alloc_pages_direct_compact+0x43/0xf0 [ 2374.423084] [<ffffffff8116a25c>] __alloc_pages_nodemask+0x4dc/0xbf0 [ 2374.423091] [<ffffffffa0023dc2>] ? cmd_exec+0x722/0xcd0 [mlx5_core] [ 2374.423095] [<ffffffff811b3dcc>] alloc_pages_current+0x8c/0x110 [ 2374.423097] [<ffffffff81168859>] alloc_kmem_pages+0x19/0x90 [ 2374.423099] [<ffffffff81186e5e>] kmalloc_order_trace+0x2e/0xe0 [ 2374.423101] [<ffffffff811c0084>] __kmalloc+0x204/0x220 [ 2374.423105] [<ffffffff816c269e>] dev_ethtool+0xe4e/0x1f80 [ 2374.423106] [<ffffffff816b967e>] ? dev_get_by_name_rcu+0x5e/0x80 [ 2374.423108] [<ffffffff816d6926>] dev_ioctl+0x156/0x560 [ 2374.423111] [<ffffffff811d4c68>] ? mem_cgroup_commit_charge+0x78/0x3c0 [ 2374.423117] [<ffffffff8169d542>] sock_do_ioctl+0x42/0x50 [ 2374.423119] [<ffffffff8169d9c3>] sock_ioctl+0x1b3/0x250 [ 2374.423121] [<ffffffff811f0f42>] do_vfs_ioctl+0x92/0x580 [ 2374.423123] [<ffffffff8100222b>] ? do_audit_syscall_entry+0x4b/0x70 [ 2374.423124] [<ffffffff8100287c>] ? syscall_trace_enter_phase1+0xfc/0x120 [ 2374.423126] [<ffffffff811f14a9>] SyS_ioctl+0x79/0x90 [ 2374.423127] [<ffffffff81002bb0>] do_syscall_64+0x50/0xa0 [ 2374.423129] [<ffffffff817e19bc>] entry_SYSCALL64_slow_path+0x25/0x25 ~1160 mlx5 counters ~= order 4 allocation which is unlikely to succeed under memory pressure. Convert them to vzalloc() as ethtool_get_regs() does. Also take care of drivers without counters similar to commit 67ae7cf1eeda ("ethtool: Allow zero-length register dumps again") and reduce warn_on to warn_on_once. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-31 10:25:18 +08:00
vfree(data);
return ret;
}
__printf(2, 3) void ethtool_sprintf(u8 **data, const char *fmt, ...)
{
va_list args;
va_start(args, fmt);
vsnprintf(*data, ETH_GSTRING_LEN, fmt, args);
va_end(args);
*data += ETH_GSTRING_LEN;
}
EXPORT_SYMBOL(ethtool_sprintf);
static int ethtool_phys_id(struct net_device *dev, void __user *useraddr)
{
struct ethtool_value id;
static bool busy;
const struct ethtool_ops *ops = dev->ethtool_ops;
netdevice_tracker dev_tracker;
int rc;
if (!ops->set_phys_id)
return -EOPNOTSUPP;
if (busy)
return -EBUSY;
if (copy_from_user(&id, useraddr, sizeof(id)))
return -EFAULT;
rc = ops->set_phys_id(dev, ETHTOOL_ID_ACTIVE);
ethtool: allow custom interval for physical identification When physical identification of an adapter is done by toggling the mechanism on and off through software utilizing the set_phys_id operation, it is done with a fixed duration for both on and off states. Some drivers may want to set a custom duration for the on/off intervals. This patch changes the API so the return code from the driver's entry point when it is called with ETHTOOL_ID_ACTIVE can specify the frequency at which to cycle the on/off states, and updates the drivers that have already been converted to use the new set_phys_id and use the synchronous method for identifying an adapter. The physical identification frequency set in the updated drivers is based on how it was done prior to the introduction of set_phys_id. Compile tested only. Also fixes a compiler warning in sfc. v2: drivers do not return -EINVAL for ETHOOL_ID_ACTIVE v3: fold patchset into single patch and cleanup per Ben's feedback Signed-off-by: Bruce Allan <bruce.w.allan@intel.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Sathya Perla <sathya.perla@emulex.com> Cc: Subbu Seetharaman <subbu.seetharaman@emulex.com> Cc: Ajit Khaparde <ajit.khaparde@emulex.com> Cc: Michael Chan <mchan@broadcom.com> Cc: Eilon Greenstein <eilong@broadcom.com> Cc: Divy Le Ray <divy@chelsio.com> Cc: Don Fry <pcnet32@frontier.com> Cc: Jon Mason <jdmason@kudzu.us> Cc: Solarflare linux maintainers <linux-net-drivers@solarflare.com> Cc: Steve Hodgson <shodgson@solarflare.com> Cc: Stephen Hemminger <shemminger@linux-foundation.org> Cc: Matt Carlson <mcarlson@broadcom.com> Acked-by: Jon Mason <jdmason@kudzu.us> Acked-by: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-04-13 21:09:10 +08:00
if (rc < 0)
return rc;
/* Drop the RTNL lock while waiting, but prevent reentry or
* removal of the device.
*/
busy = true;
netdev_hold(dev, &dev_tracker, GFP_KERNEL);
rtnl_unlock();
if (rc == 0) {
/* Driver will handle this itself */
schedule_timeout_interruptible(
id.data ? (id.data * HZ) : MAX_SCHEDULE_TIMEOUT);
} else {
ethtool: allow custom interval for physical identification When physical identification of an adapter is done by toggling the mechanism on and off through software utilizing the set_phys_id operation, it is done with a fixed duration for both on and off states. Some drivers may want to set a custom duration for the on/off intervals. This patch changes the API so the return code from the driver's entry point when it is called with ETHTOOL_ID_ACTIVE can specify the frequency at which to cycle the on/off states, and updates the drivers that have already been converted to use the new set_phys_id and use the synchronous method for identifying an adapter. The physical identification frequency set in the updated drivers is based on how it was done prior to the introduction of set_phys_id. Compile tested only. Also fixes a compiler warning in sfc. v2: drivers do not return -EINVAL for ETHOOL_ID_ACTIVE v3: fold patchset into single patch and cleanup per Ben's feedback Signed-off-by: Bruce Allan <bruce.w.allan@intel.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Sathya Perla <sathya.perla@emulex.com> Cc: Subbu Seetharaman <subbu.seetharaman@emulex.com> Cc: Ajit Khaparde <ajit.khaparde@emulex.com> Cc: Michael Chan <mchan@broadcom.com> Cc: Eilon Greenstein <eilong@broadcom.com> Cc: Divy Le Ray <divy@chelsio.com> Cc: Don Fry <pcnet32@frontier.com> Cc: Jon Mason <jdmason@kudzu.us> Cc: Solarflare linux maintainers <linux-net-drivers@solarflare.com> Cc: Steve Hodgson <shodgson@solarflare.com> Cc: Stephen Hemminger <shemminger@linux-foundation.org> Cc: Matt Carlson <mcarlson@broadcom.com> Acked-by: Jon Mason <jdmason@kudzu.us> Acked-by: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-04-13 21:09:10 +08:00
/* Driver expects to be called at twice the frequency in rc */
int n = rc * 2, interval = HZ / n;
u64 count = mul_u32_u32(n, id.data);
u64 i = 0;
ethtool: allow custom interval for physical identification When physical identification of an adapter is done by toggling the mechanism on and off through software utilizing the set_phys_id operation, it is done with a fixed duration for both on and off states. Some drivers may want to set a custom duration for the on/off intervals. This patch changes the API so the return code from the driver's entry point when it is called with ETHTOOL_ID_ACTIVE can specify the frequency at which to cycle the on/off states, and updates the drivers that have already been converted to use the new set_phys_id and use the synchronous method for identifying an adapter. The physical identification frequency set in the updated drivers is based on how it was done prior to the introduction of set_phys_id. Compile tested only. Also fixes a compiler warning in sfc. v2: drivers do not return -EINVAL for ETHOOL_ID_ACTIVE v3: fold patchset into single patch and cleanup per Ben's feedback Signed-off-by: Bruce Allan <bruce.w.allan@intel.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Sathya Perla <sathya.perla@emulex.com> Cc: Subbu Seetharaman <subbu.seetharaman@emulex.com> Cc: Ajit Khaparde <ajit.khaparde@emulex.com> Cc: Michael Chan <mchan@broadcom.com> Cc: Eilon Greenstein <eilong@broadcom.com> Cc: Divy Le Ray <divy@chelsio.com> Cc: Don Fry <pcnet32@frontier.com> Cc: Jon Mason <jdmason@kudzu.us> Cc: Solarflare linux maintainers <linux-net-drivers@solarflare.com> Cc: Steve Hodgson <shodgson@solarflare.com> Cc: Stephen Hemminger <shemminger@linux-foundation.org> Cc: Matt Carlson <mcarlson@broadcom.com> Acked-by: Jon Mason <jdmason@kudzu.us> Acked-by: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-04-13 21:09:10 +08:00
do {
rtnl_lock();
rc = ops->set_phys_id(dev,
(i++ & 1) ? ETHTOOL_ID_OFF : ETHTOOL_ID_ON);
rtnl_unlock();
if (rc)
break;
schedule_timeout_interruptible(interval);
} while (!signal_pending(current) && (!id.data || i < count));
}
rtnl_lock();
netdev_put(dev, &dev_tracker);
busy = false;
(void) ops->set_phys_id(dev, ETHTOOL_ID_INACTIVE);
return rc;
}
static int ethtool_get_stats(struct net_device *dev, void __user *useraddr)
{
struct ethtool_stats stats;
const struct ethtool_ops *ops = dev->ethtool_ops;
u64 *data;
int ret, n_stats;
if (!ops->get_ethtool_stats || !ops->get_sset_count)
return -EOPNOTSUPP;
n_stats = ops->get_sset_count(dev, ETH_SS_STATS);
if (n_stats < 0)
return n_stats;
net: ethtool: convert large order kmalloc allocations to vzalloc under memory pressure 'ethtool -S' command may warn: [ 2374.385195] ethtool: page allocation failure: order:4, mode:0x242c0c0 [ 2374.405573] CPU: 12 PID: 40211 Comm: ethtool Not tainted [ 2374.423071] Call Trace: [ 2374.423076] [<ffffffff8148cb29>] dump_stack+0x4d/0x64 [ 2374.423080] [<ffffffff811667cb>] warn_alloc_failed+0xeb/0x150 [ 2374.423082] [<ffffffff81169cd3>] ? __alloc_pages_direct_compact+0x43/0xf0 [ 2374.423084] [<ffffffff8116a25c>] __alloc_pages_nodemask+0x4dc/0xbf0 [ 2374.423091] [<ffffffffa0023dc2>] ? cmd_exec+0x722/0xcd0 [mlx5_core] [ 2374.423095] [<ffffffff811b3dcc>] alloc_pages_current+0x8c/0x110 [ 2374.423097] [<ffffffff81168859>] alloc_kmem_pages+0x19/0x90 [ 2374.423099] [<ffffffff81186e5e>] kmalloc_order_trace+0x2e/0xe0 [ 2374.423101] [<ffffffff811c0084>] __kmalloc+0x204/0x220 [ 2374.423105] [<ffffffff816c269e>] dev_ethtool+0xe4e/0x1f80 [ 2374.423106] [<ffffffff816b967e>] ? dev_get_by_name_rcu+0x5e/0x80 [ 2374.423108] [<ffffffff816d6926>] dev_ioctl+0x156/0x560 [ 2374.423111] [<ffffffff811d4c68>] ? mem_cgroup_commit_charge+0x78/0x3c0 [ 2374.423117] [<ffffffff8169d542>] sock_do_ioctl+0x42/0x50 [ 2374.423119] [<ffffffff8169d9c3>] sock_ioctl+0x1b3/0x250 [ 2374.423121] [<ffffffff811f0f42>] do_vfs_ioctl+0x92/0x580 [ 2374.423123] [<ffffffff8100222b>] ? do_audit_syscall_entry+0x4b/0x70 [ 2374.423124] [<ffffffff8100287c>] ? syscall_trace_enter_phase1+0xfc/0x120 [ 2374.423126] [<ffffffff811f14a9>] SyS_ioctl+0x79/0x90 [ 2374.423127] [<ffffffff81002bb0>] do_syscall_64+0x50/0xa0 [ 2374.423129] [<ffffffff817e19bc>] entry_SYSCALL64_slow_path+0x25/0x25 ~1160 mlx5 counters ~= order 4 allocation which is unlikely to succeed under memory pressure. Convert them to vzalloc() as ethtool_get_regs() does. Also take care of drivers without counters similar to commit 67ae7cf1eeda ("ethtool: Allow zero-length register dumps again") and reduce warn_on to warn_on_once. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-31 10:25:18 +08:00
if (n_stats > S32_MAX / sizeof(u64))
return -ENOMEM;
WARN_ON_ONCE(!n_stats);
if (copy_from_user(&stats, useraddr, sizeof(stats)))
return -EFAULT;
stats.n_stats = n_stats;
if (n_stats) {
data = vzalloc(array_size(n_stats, sizeof(u64)));
if (!data)
return -ENOMEM;
ops->get_ethtool_stats(dev, &stats, data);
} else {
data = NULL;
}
ret = -EFAULT;
if (copy_to_user(useraddr, &stats, sizeof(stats)))
goto out;
useraddr += sizeof(stats);
if (n_stats && copy_to_user(useraddr, data, array_size(n_stats, sizeof(u64))))
goto out;
ret = 0;
out:
net: ethtool: convert large order kmalloc allocations to vzalloc under memory pressure 'ethtool -S' command may warn: [ 2374.385195] ethtool: page allocation failure: order:4, mode:0x242c0c0 [ 2374.405573] CPU: 12 PID: 40211 Comm: ethtool Not tainted [ 2374.423071] Call Trace: [ 2374.423076] [<ffffffff8148cb29>] dump_stack+0x4d/0x64 [ 2374.423080] [<ffffffff811667cb>] warn_alloc_failed+0xeb/0x150 [ 2374.423082] [<ffffffff81169cd3>] ? __alloc_pages_direct_compact+0x43/0xf0 [ 2374.423084] [<ffffffff8116a25c>] __alloc_pages_nodemask+0x4dc/0xbf0 [ 2374.423091] [<ffffffffa0023dc2>] ? cmd_exec+0x722/0xcd0 [mlx5_core] [ 2374.423095] [<ffffffff811b3dcc>] alloc_pages_current+0x8c/0x110 [ 2374.423097] [<ffffffff81168859>] alloc_kmem_pages+0x19/0x90 [ 2374.423099] [<ffffffff81186e5e>] kmalloc_order_trace+0x2e/0xe0 [ 2374.423101] [<ffffffff811c0084>] __kmalloc+0x204/0x220 [ 2374.423105] [<ffffffff816c269e>] dev_ethtool+0xe4e/0x1f80 [ 2374.423106] [<ffffffff816b967e>] ? dev_get_by_name_rcu+0x5e/0x80 [ 2374.423108] [<ffffffff816d6926>] dev_ioctl+0x156/0x560 [ 2374.423111] [<ffffffff811d4c68>] ? mem_cgroup_commit_charge+0x78/0x3c0 [ 2374.423117] [<ffffffff8169d542>] sock_do_ioctl+0x42/0x50 [ 2374.423119] [<ffffffff8169d9c3>] sock_ioctl+0x1b3/0x250 [ 2374.423121] [<ffffffff811f0f42>] do_vfs_ioctl+0x92/0x580 [ 2374.423123] [<ffffffff8100222b>] ? do_audit_syscall_entry+0x4b/0x70 [ 2374.423124] [<ffffffff8100287c>] ? syscall_trace_enter_phase1+0xfc/0x120 [ 2374.423126] [<ffffffff811f14a9>] SyS_ioctl+0x79/0x90 [ 2374.423127] [<ffffffff81002bb0>] do_syscall_64+0x50/0xa0 [ 2374.423129] [<ffffffff817e19bc>] entry_SYSCALL64_slow_path+0x25/0x25 ~1160 mlx5 counters ~= order 4 allocation which is unlikely to succeed under memory pressure. Convert them to vzalloc() as ethtool_get_regs() does. Also take care of drivers without counters similar to commit 67ae7cf1eeda ("ethtool: Allow zero-length register dumps again") and reduce warn_on to warn_on_once. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-31 10:25:18 +08:00
vfree(data);
return ret;
}
static int ethtool_vzalloc_stats_array(int n_stats, u64 **data)
{
if (n_stats < 0)
return n_stats;
net: ethtool: convert large order kmalloc allocations to vzalloc under memory pressure 'ethtool -S' command may warn: [ 2374.385195] ethtool: page allocation failure: order:4, mode:0x242c0c0 [ 2374.405573] CPU: 12 PID: 40211 Comm: ethtool Not tainted [ 2374.423071] Call Trace: [ 2374.423076] [<ffffffff8148cb29>] dump_stack+0x4d/0x64 [ 2374.423080] [<ffffffff811667cb>] warn_alloc_failed+0xeb/0x150 [ 2374.423082] [<ffffffff81169cd3>] ? __alloc_pages_direct_compact+0x43/0xf0 [ 2374.423084] [<ffffffff8116a25c>] __alloc_pages_nodemask+0x4dc/0xbf0 [ 2374.423091] [<ffffffffa0023dc2>] ? cmd_exec+0x722/0xcd0 [mlx5_core] [ 2374.423095] [<ffffffff811b3dcc>] alloc_pages_current+0x8c/0x110 [ 2374.423097] [<ffffffff81168859>] alloc_kmem_pages+0x19/0x90 [ 2374.423099] [<ffffffff81186e5e>] kmalloc_order_trace+0x2e/0xe0 [ 2374.423101] [<ffffffff811c0084>] __kmalloc+0x204/0x220 [ 2374.423105] [<ffffffff816c269e>] dev_ethtool+0xe4e/0x1f80 [ 2374.423106] [<ffffffff816b967e>] ? dev_get_by_name_rcu+0x5e/0x80 [ 2374.423108] [<ffffffff816d6926>] dev_ioctl+0x156/0x560 [ 2374.423111] [<ffffffff811d4c68>] ? mem_cgroup_commit_charge+0x78/0x3c0 [ 2374.423117] [<ffffffff8169d542>] sock_do_ioctl+0x42/0x50 [ 2374.423119] [<ffffffff8169d9c3>] sock_ioctl+0x1b3/0x250 [ 2374.423121] [<ffffffff811f0f42>] do_vfs_ioctl+0x92/0x580 [ 2374.423123] [<ffffffff8100222b>] ? do_audit_syscall_entry+0x4b/0x70 [ 2374.423124] [<ffffffff8100287c>] ? syscall_trace_enter_phase1+0xfc/0x120 [ 2374.423126] [<ffffffff811f14a9>] SyS_ioctl+0x79/0x90 [ 2374.423127] [<ffffffff81002bb0>] do_syscall_64+0x50/0xa0 [ 2374.423129] [<ffffffff817e19bc>] entry_SYSCALL64_slow_path+0x25/0x25 ~1160 mlx5 counters ~= order 4 allocation which is unlikely to succeed under memory pressure. Convert them to vzalloc() as ethtool_get_regs() does. Also take care of drivers without counters similar to commit 67ae7cf1eeda ("ethtool: Allow zero-length register dumps again") and reduce warn_on to warn_on_once. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-31 10:25:18 +08:00
if (n_stats > S32_MAX / sizeof(u64))
return -ENOMEM;
if (WARN_ON_ONCE(!n_stats))
return -EOPNOTSUPP;
*data = vzalloc(array_size(n_stats, sizeof(u64)));
if (!*data)
return -ENOMEM;
return 0;
}
static int ethtool_get_phy_stats_phydev(struct phy_device *phydev,
struct ethtool_stats *stats,
u64 **data)
{
const struct ethtool_phy_ops *phy_ops = ethtool_phy_ops;
int n_stats, ret;
if (!phy_ops || !phy_ops->get_sset_count || !phy_ops->get_stats)
return -EOPNOTSUPP;
n_stats = phy_ops->get_sset_count(phydev);
ret = ethtool_vzalloc_stats_array(n_stats, data);
if (ret)
return ret;
stats->n_stats = n_stats;
return phy_ops->get_stats(phydev, stats, *data);
}
static int ethtool_get_phy_stats_ethtool(struct net_device *dev,
struct ethtool_stats *stats,
u64 **data)
{
const struct ethtool_ops *ops = dev->ethtool_ops;
int n_stats, ret;
if (!ops || !ops->get_sset_count || ops->get_ethtool_phy_stats)
return -EOPNOTSUPP;
n_stats = ops->get_sset_count(dev, ETH_SS_PHY_STATS);
ret = ethtool_vzalloc_stats_array(n_stats, data);
if (ret)
return ret;
stats->n_stats = n_stats;
ops->get_ethtool_phy_stats(dev, stats, *data);
return 0;
}
static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
{
struct phy_device *phydev = dev->phydev;
struct ethtool_stats stats;
u64 *data = NULL;
int ret = -EOPNOTSUPP;
if (copy_from_user(&stats, useraddr, sizeof(stats)))
return -EFAULT;
if (phydev)
ret = ethtool_get_phy_stats_phydev(phydev, &stats, &data);
if (ret == -EOPNOTSUPP)
ret = ethtool_get_phy_stats_ethtool(dev, &stats, &data);
if (ret)
goto out;
if (copy_to_user(useraddr, &stats, sizeof(stats))) {
ret = -EFAULT;
goto out;
}
useraddr += sizeof(stats);
if (copy_to_user(useraddr, data, array_size(stats.n_stats, sizeof(u64))))
ret = -EFAULT;
out:
net: ethtool: convert large order kmalloc allocations to vzalloc under memory pressure 'ethtool -S' command may warn: [ 2374.385195] ethtool: page allocation failure: order:4, mode:0x242c0c0 [ 2374.405573] CPU: 12 PID: 40211 Comm: ethtool Not tainted [ 2374.423071] Call Trace: [ 2374.423076] [<ffffffff8148cb29>] dump_stack+0x4d/0x64 [ 2374.423080] [<ffffffff811667cb>] warn_alloc_failed+0xeb/0x150 [ 2374.423082] [<ffffffff81169cd3>] ? __alloc_pages_direct_compact+0x43/0xf0 [ 2374.423084] [<ffffffff8116a25c>] __alloc_pages_nodemask+0x4dc/0xbf0 [ 2374.423091] [<ffffffffa0023dc2>] ? cmd_exec+0x722/0xcd0 [mlx5_core] [ 2374.423095] [<ffffffff811b3dcc>] alloc_pages_current+0x8c/0x110 [ 2374.423097] [<ffffffff81168859>] alloc_kmem_pages+0x19/0x90 [ 2374.423099] [<ffffffff81186e5e>] kmalloc_order_trace+0x2e/0xe0 [ 2374.423101] [<ffffffff811c0084>] __kmalloc+0x204/0x220 [ 2374.423105] [<ffffffff816c269e>] dev_ethtool+0xe4e/0x1f80 [ 2374.423106] [<ffffffff816b967e>] ? dev_get_by_name_rcu+0x5e/0x80 [ 2374.423108] [<ffffffff816d6926>] dev_ioctl+0x156/0x560 [ 2374.423111] [<ffffffff811d4c68>] ? mem_cgroup_commit_charge+0x78/0x3c0 [ 2374.423117] [<ffffffff8169d542>] sock_do_ioctl+0x42/0x50 [ 2374.423119] [<ffffffff8169d9c3>] sock_ioctl+0x1b3/0x250 [ 2374.423121] [<ffffffff811f0f42>] do_vfs_ioctl+0x92/0x580 [ 2374.423123] [<ffffffff8100222b>] ? do_audit_syscall_entry+0x4b/0x70 [ 2374.423124] [<ffffffff8100287c>] ? syscall_trace_enter_phase1+0xfc/0x120 [ 2374.423126] [<ffffffff811f14a9>] SyS_ioctl+0x79/0x90 [ 2374.423127] [<ffffffff81002bb0>] do_syscall_64+0x50/0xa0 [ 2374.423129] [<ffffffff817e19bc>] entry_SYSCALL64_slow_path+0x25/0x25 ~1160 mlx5 counters ~= order 4 allocation which is unlikely to succeed under memory pressure. Convert them to vzalloc() as ethtool_get_regs() does. Also take care of drivers without counters similar to commit 67ae7cf1eeda ("ethtool: Allow zero-length register dumps again") and reduce warn_on to warn_on_once. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-31 10:25:18 +08:00
vfree(data);
return ret;
}
static int ethtool_get_perm_addr(struct net_device *dev, void __user *useraddr)
{
struct ethtool_perm_addr epaddr;
if (copy_from_user(&epaddr, useraddr, sizeof(epaddr)))
return -EFAULT;
if (epaddr.size < dev->addr_len)
return -ETOOSMALL;
epaddr.size = dev->addr_len;
if (copy_to_user(useraddr, &epaddr, sizeof(epaddr)))
return -EFAULT;
useraddr += sizeof(epaddr);
if (copy_to_user(useraddr, dev->perm_addr, epaddr.size))
return -EFAULT;
return 0;
}
static int ethtool_get_value(struct net_device *dev, char __user *useraddr,
u32 cmd, u32 (*actor)(struct net_device *))
{
struct ethtool_value edata = { .cmd = cmd };
if (!actor)
return -EOPNOTSUPP;
edata.data = actor(dev);
if (copy_to_user(useraddr, &edata, sizeof(edata)))
return -EFAULT;
return 0;
}
static int ethtool_set_value_void(struct net_device *dev, char __user *useraddr,
void (*actor)(struct net_device *, u32))
{
struct ethtool_value edata;
if (!actor)
return -EOPNOTSUPP;
if (copy_from_user(&edata, useraddr, sizeof(edata)))
return -EFAULT;
actor(dev, edata.data);
return 0;
}
static int ethtool_set_value(struct net_device *dev, char __user *useraddr,
int (*actor)(struct net_device *, u32))
{
struct ethtool_value edata;
if (!actor)
return -EOPNOTSUPP;
if (copy_from_user(&edata, useraddr, sizeof(edata)))
return -EFAULT;
return actor(dev, edata.data);
}
static int
ethtool_flash_device(struct net_device *dev, struct ethtool_devlink_compat *req)
{
if (!dev->ethtool_ops->flash_device) {
req->devlink = netdev_to_devlink_get(dev);
return 0;
}
return dev->ethtool_ops->flash_device(dev, &req->efl);
}
static int ethtool_set_dump(struct net_device *dev,
void __user *useraddr)
{
struct ethtool_dump dump;
if (!dev->ethtool_ops->set_dump)
return -EOPNOTSUPP;
if (copy_from_user(&dump, useraddr, sizeof(dump)))
return -EFAULT;
return dev->ethtool_ops->set_dump(dev, &dump);
}
static int ethtool_get_dump_flag(struct net_device *dev,
void __user *useraddr)
{
int ret;
struct ethtool_dump dump;
const struct ethtool_ops *ops = dev->ethtool_ops;
if (!ops->get_dump_flag)
return -EOPNOTSUPP;
if (copy_from_user(&dump, useraddr, sizeof(dump)))
return -EFAULT;
ret = ops->get_dump_flag(dev, &dump);
if (ret)
return ret;
if (copy_to_user(useraddr, &dump, sizeof(dump)))
return -EFAULT;
return 0;
}
static int ethtool_get_dump_data(struct net_device *dev,
void __user *useraddr)
{
int ret;
__u32 len;
struct ethtool_dump dump, tmp;
const struct ethtool_ops *ops = dev->ethtool_ops;
void *data = NULL;
if (!ops->get_dump_data || !ops->get_dump_flag)
return -EOPNOTSUPP;
if (copy_from_user(&dump, useraddr, sizeof(dump)))
return -EFAULT;
memset(&tmp, 0, sizeof(tmp));
tmp.cmd = ETHTOOL_GET_DUMP_FLAG;
ret = ops->get_dump_flag(dev, &tmp);
if (ret)
return ret;
len = min(tmp.len, dump.len);
if (!len)
return -EFAULT;
/* Don't ever let the driver think there's more space available
* than it requested with .get_dump_flag().
*/
dump.len = len;
/* Always allocate enough space to hold the whole thing so that the
* driver does not need to check the length and bother with partial
* dumping.
*/
data = vzalloc(tmp.len);
if (!data)
return -ENOMEM;
ret = ops->get_dump_data(dev, &dump, data);
if (ret)
goto out;
/* There are two sane possibilities:
* 1. The driver's .get_dump_data() does not touch dump.len.
* 2. Or it may set dump.len to how much it really writes, which
* should be tmp.len (or len if it can do a partial dump).
* In any case respond to userspace with the actual length of data
* it's receiving.
*/
WARN_ON(dump.len != len && dump.len != tmp.len);
dump.len = len;
if (copy_to_user(useraddr, &dump, sizeof(dump))) {
ret = -EFAULT;
goto out;
}
useraddr += offsetof(struct ethtool_dump, data);
if (copy_to_user(useraddr, data, len))
ret = -EFAULT;
out:
vfree(data);
return ret;
}
static int ethtool_get_ts_info(struct net_device *dev, void __user *useraddr)
{
struct ethtool_ts_info info;
int err;
err = __ethtool_get_ts_info(dev, &info);
if (err)
return err;
if (copy_to_user(useraddr, &info, sizeof(info)))
return -EFAULT;
return 0;
}
int ethtool_get_module_info_call(struct net_device *dev,
struct ethtool_modinfo *modinfo)
{
const struct ethtool_ops *ops = dev->ethtool_ops;
struct phy_device *phydev = dev->phydev;
if (dev->sfp_bus)
return sfp_get_module_info(dev->sfp_bus, modinfo);
if (phydev && phydev->drv && phydev->drv->module_info)
return phydev->drv->module_info(phydev, modinfo);
if (ops->get_module_info)
return ops->get_module_info(dev, modinfo);
return -EOPNOTSUPP;
}
static int ethtool_get_module_info(struct net_device *dev,
void __user *useraddr)
{
int ret;
struct ethtool_modinfo modinfo;
if (copy_from_user(&modinfo, useraddr, sizeof(modinfo)))
return -EFAULT;
ret = ethtool_get_module_info_call(dev, &modinfo);
if (ret)
return ret;
if (copy_to_user(useraddr, &modinfo, sizeof(modinfo)))
return -EFAULT;
return 0;
}
int ethtool_get_module_eeprom_call(struct net_device *dev,
struct ethtool_eeprom *ee, u8 *data)
{
const struct ethtool_ops *ops = dev->ethtool_ops;
struct phy_device *phydev = dev->phydev;
if (dev->sfp_bus)
return sfp_get_module_eeprom(dev->sfp_bus, ee, data);
if (phydev && phydev->drv && phydev->drv->module_eeprom)
return phydev->drv->module_eeprom(phydev, ee, data);
if (ops->get_module_eeprom)
return ops->get_module_eeprom(dev, ee, data);
return -EOPNOTSUPP;
}
static int ethtool_get_module_eeprom(struct net_device *dev,
void __user *useraddr)
{
int ret;
struct ethtool_modinfo modinfo;
ret = ethtool_get_module_info_call(dev, &modinfo);
if (ret)
return ret;
return ethtool_get_any_eeprom(dev, useraddr,
ethtool_get_module_eeprom_call,
modinfo.eeprom_len);
}
static int ethtool_tunable_valid(const struct ethtool_tunable *tuna)
{
switch (tuna->id) {
case ETHTOOL_RX_COPYBREAK:
case ETHTOOL_TX_COPYBREAK:
case ETHTOOL_TX_COPYBREAK_BUF_SIZE:
if (tuna->len != sizeof(u32) ||
tuna->type_id != ETHTOOL_TUNABLE_U32)
return -EINVAL;
break;
case ETHTOOL_PFC_PREVENTION_TOUT:
if (tuna->len != sizeof(u16) ||
tuna->type_id != ETHTOOL_TUNABLE_U16)
return -EINVAL;
break;
default:
return -EINVAL;
}
return 0;
}
static int ethtool_get_tunable(struct net_device *dev, void __user *useraddr)
{
int ret;
struct ethtool_tunable tuna;
const struct ethtool_ops *ops = dev->ethtool_ops;
void *data;
if (!ops->get_tunable)
return -EOPNOTSUPP;
if (copy_from_user(&tuna, useraddr, sizeof(tuna)))
return -EFAULT;
ret = ethtool_tunable_valid(&tuna);
if (ret)
return ret;
data = kzalloc(tuna.len, GFP_USER);
if (!data)
return -ENOMEM;
ret = ops->get_tunable(dev, &tuna, data);
if (ret)
goto out;
useraddr += sizeof(tuna);
ret = -EFAULT;
if (copy_to_user(useraddr, data, tuna.len))
goto out;
ret = 0;
out:
kfree(data);
return ret;
}
static int ethtool_set_tunable(struct net_device *dev, void __user *useraddr)
{
int ret;
struct ethtool_tunable tuna;
const struct ethtool_ops *ops = dev->ethtool_ops;
void *data;
if (!ops->set_tunable)
return -EOPNOTSUPP;
if (copy_from_user(&tuna, useraddr, sizeof(tuna)))
return -EFAULT;
ret = ethtool_tunable_valid(&tuna);
if (ret)
return ret;
useraddr += sizeof(tuna);
data = memdup_user(useraddr, tuna.len);
if (IS_ERR(data))
return PTR_ERR(data);
ret = ops->set_tunable(dev, &tuna, data);
kfree(data);
return ret;
}
static noinline_for_stack int
ethtool_get_per_queue_coalesce(struct net_device *dev,
void __user *useraddr,
struct ethtool_per_queue_op *per_queue_opt)
{
u32 bit;
int ret;
DECLARE_BITMAP(queue_mask, MAX_NUM_QUEUE);
if (!dev->ethtool_ops->get_per_queue_coalesce)
return -EOPNOTSUPP;
useraddr += sizeof(*per_queue_opt);
bitmap_from_arr32(queue_mask, per_queue_opt->queue_mask,
MAX_NUM_QUEUE);
for_each_set_bit(bit, queue_mask, MAX_NUM_QUEUE) {
struct ethtool_coalesce coalesce = { .cmd = ETHTOOL_GCOALESCE };
ret = dev->ethtool_ops->get_per_queue_coalesce(dev, bit, &coalesce);
if (ret != 0)
return ret;
if (copy_to_user(useraddr, &coalesce, sizeof(coalesce)))
return -EFAULT;
useraddr += sizeof(coalesce);
}
return 0;
}
static noinline_for_stack int
ethtool_set_per_queue_coalesce(struct net_device *dev,
void __user *useraddr,
struct ethtool_per_queue_op *per_queue_opt)
{
u32 bit;
int i, ret = 0;
int n_queue;
struct ethtool_coalesce *backup = NULL, *tmp = NULL;
DECLARE_BITMAP(queue_mask, MAX_NUM_QUEUE);
if ((!dev->ethtool_ops->set_per_queue_coalesce) ||
(!dev->ethtool_ops->get_per_queue_coalesce))
return -EOPNOTSUPP;
useraddr += sizeof(*per_queue_opt);
bitmap_from_arr32(queue_mask, per_queue_opt->queue_mask, MAX_NUM_QUEUE);
n_queue = bitmap_weight(queue_mask, MAX_NUM_QUEUE);
tmp = backup = kmalloc_array(n_queue, sizeof(*backup), GFP_KERNEL);
if (!backup)
return -ENOMEM;
for_each_set_bit(bit, queue_mask, MAX_NUM_QUEUE) {
struct ethtool_coalesce coalesce;
ret = dev->ethtool_ops->get_per_queue_coalesce(dev, bit, tmp);
if (ret != 0)
goto roll_back;
tmp++;
if (copy_from_user(&coalesce, useraddr, sizeof(coalesce))) {
ret = -EFAULT;
goto roll_back;
}
if (!ethtool_set_coalesce_supported(dev, &coalesce)) {
ret = -EOPNOTSUPP;
goto roll_back;
}
ret = dev->ethtool_ops->set_per_queue_coalesce(dev, bit, &coalesce);
if (ret != 0)
goto roll_back;
useraddr += sizeof(coalesce);
}
roll_back:
if (ret != 0) {
tmp = backup;
for_each_set_bit(i, queue_mask, bit) {
dev->ethtool_ops->set_per_queue_coalesce(dev, i, tmp);
tmp++;
}
}
kfree(backup);
return ret;
}
static int noinline_for_stack ethtool_set_per_queue(struct net_device *dev,
ethtool: fix a privilege escalation bug In dev_ethtool(), the eth command 'ethcmd' is firstly copied from the use-space buffer 'useraddr' and checked to see whether it is ETHTOOL_PERQUEUE. If yes, the sub-command 'sub_cmd' is further copied from the user space. Otherwise, 'sub_cmd' is the same as 'ethcmd'. Next, according to 'sub_cmd', a permission check is enforced through the function ns_capable(). For example, the permission check is required if 'sub_cmd' is ETHTOOL_SCOALESCE, but it is not necessary if 'sub_cmd' is ETHTOOL_GCOALESCE, as suggested in the comment "Allow some commands to be done by anyone". The following execution invokes different handlers according to 'ethcmd'. Specifically, if 'ethcmd' is ETHTOOL_PERQUEUE, ethtool_set_per_queue() is called. In ethtool_set_per_queue(), the kernel object 'per_queue_opt' is copied again from the user-space buffer 'useraddr' and 'per_queue_opt.sub_command' is used to determine which operation should be performed. Given that the buffer 'useraddr' is in the user space, a malicious user can race to change the sub-command between the two copies. In particular, the attacker can supply ETHTOOL_PERQUEUE and ETHTOOL_GCOALESCE to bypass the permission check in dev_ethtool(). Then before ethtool_set_per_queue() is called, the attacker changes ETHTOOL_GCOALESCE to ETHTOOL_SCOALESCE. In this way, the attacker can bypass the permission check and execute ETHTOOL_SCOALESCE. This patch enforces a check in ethtool_set_per_queue() after the second copy from 'useraddr'. If the sub-command is different from the one obtained in the first copy in dev_ethtool(), an error code EINVAL will be returned. Fixes: f38d138a7da6 ("net/ethtool: support set coalesce per queue") Signed-off-by: Wenwen Wang <wang6495@umn.edu> Reviewed-by: Michal Kubecek <mkubecek@suse.cz> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-08 23:49:35 +08:00
void __user *useraddr, u32 sub_cmd)
{
struct ethtool_per_queue_op per_queue_opt;
if (copy_from_user(&per_queue_opt, useraddr, sizeof(per_queue_opt)))
return -EFAULT;
ethtool: fix a privilege escalation bug In dev_ethtool(), the eth command 'ethcmd' is firstly copied from the use-space buffer 'useraddr' and checked to see whether it is ETHTOOL_PERQUEUE. If yes, the sub-command 'sub_cmd' is further copied from the user space. Otherwise, 'sub_cmd' is the same as 'ethcmd'. Next, according to 'sub_cmd', a permission check is enforced through the function ns_capable(). For example, the permission check is required if 'sub_cmd' is ETHTOOL_SCOALESCE, but it is not necessary if 'sub_cmd' is ETHTOOL_GCOALESCE, as suggested in the comment "Allow some commands to be done by anyone". The following execution invokes different handlers according to 'ethcmd'. Specifically, if 'ethcmd' is ETHTOOL_PERQUEUE, ethtool_set_per_queue() is called. In ethtool_set_per_queue(), the kernel object 'per_queue_opt' is copied again from the user-space buffer 'useraddr' and 'per_queue_opt.sub_command' is used to determine which operation should be performed. Given that the buffer 'useraddr' is in the user space, a malicious user can race to change the sub-command between the two copies. In particular, the attacker can supply ETHTOOL_PERQUEUE and ETHTOOL_GCOALESCE to bypass the permission check in dev_ethtool(). Then before ethtool_set_per_queue() is called, the attacker changes ETHTOOL_GCOALESCE to ETHTOOL_SCOALESCE. In this way, the attacker can bypass the permission check and execute ETHTOOL_SCOALESCE. This patch enforces a check in ethtool_set_per_queue() after the second copy from 'useraddr'. If the sub-command is different from the one obtained in the first copy in dev_ethtool(), an error code EINVAL will be returned. Fixes: f38d138a7da6 ("net/ethtool: support set coalesce per queue") Signed-off-by: Wenwen Wang <wang6495@umn.edu> Reviewed-by: Michal Kubecek <mkubecek@suse.cz> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-08 23:49:35 +08:00
if (per_queue_opt.sub_command != sub_cmd)
return -EINVAL;
switch (per_queue_opt.sub_command) {
case ETHTOOL_GCOALESCE:
return ethtool_get_per_queue_coalesce(dev, useraddr, &per_queue_opt);
case ETHTOOL_SCOALESCE:
return ethtool_set_per_queue_coalesce(dev, useraddr, &per_queue_opt);
default:
return -EOPNOTSUPP;
}
}
static int ethtool_phy_tunable_valid(const struct ethtool_tunable *tuna)
{
switch (tuna->id) {
case ETHTOOL_PHY_DOWNSHIFT:
case ETHTOOL_PHY_FAST_LINK_DOWN:
if (tuna->len != sizeof(u8) ||
tuna->type_id != ETHTOOL_TUNABLE_U8)
return -EINVAL;
break;
ethtool: implement Energy Detect Powerdown support via phy-tunable The `phy_tunable_id` has been named `ETHTOOL_PHY_EDPD` since it looks like this feature is common across other PHYs (like EEE), and defining `ETHTOOL_PHY_ENERGY_DETECT_POWER_DOWN` seems too long. The way EDPD works, is that the RX block is put to a lower power mode, except for link-pulse detection circuits. The TX block is also put to low power mode, but the PHY wakes-up periodically to send link pulses, to avoid lock-ups in case the other side is also in EDPD mode. Currently, there are 2 PHY drivers that look like they could use this new PHY tunable feature: the `adin` && `micrel` PHYs. The ADIN's datasheet mentions that TX pulses are at intervals of 1 second default each, and they can be disabled. For the Micrel KSZ9031 PHY, the datasheet does not mention whether they can be disabled, but mentions that they can modified. The way this change is structured, is similar to the PHY tunable downshift control: * a `ETHTOOL_PHY_EDPD_DFLT_TX_MSECS` value is exposed to cover a default TX interval; some PHYs could specify a certain value that makes sense * `ETHTOOL_PHY_EDPD_NO_TX` would disable TX when EDPD is enabled * `ETHTOOL_PHY_EDPD_DISABLE` will disable EDPD As noted by the `ETHTOOL_PHY_EDPD_DFLT_TX_MSECS` the interval unit is 1 millisecond, which should cover a reasonable range of intervals: - from 1 millisecond, which does not sound like much of a power-saver - to ~65 seconds which is quite a lot to wait for a link to come up when plugging a cable Reviewed-by: Andrew Lunn <andrew@lunn.ch> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-09-16 15:35:25 +08:00
case ETHTOOL_PHY_EDPD:
if (tuna->len != sizeof(u16) ||
tuna->type_id != ETHTOOL_TUNABLE_U16)
return -EINVAL;
break;
default:
return -EINVAL;
}
return 0;
}
static int get_phy_tunable(struct net_device *dev, void __user *useraddr)
{
struct phy_device *phydev = dev->phydev;
struct ethtool_tunable tuna;
bool phy_drv_tunable;
void *data;
int ret;
phy_drv_tunable = phydev && phydev->drv && phydev->drv->get_tunable;
if (!phy_drv_tunable && !dev->ethtool_ops->get_phy_tunable)
return -EOPNOTSUPP;
if (copy_from_user(&tuna, useraddr, sizeof(tuna)))
return -EFAULT;
ret = ethtool_phy_tunable_valid(&tuna);
if (ret)
return ret;
data = kzalloc(tuna.len, GFP_USER);
if (!data)
return -ENOMEM;
if (phy_drv_tunable) {
mutex_lock(&phydev->lock);
ret = phydev->drv->get_tunable(phydev, &tuna, data);
mutex_unlock(&phydev->lock);
} else {
ret = dev->ethtool_ops->get_phy_tunable(dev, &tuna, data);
}
if (ret)
goto out;
useraddr += sizeof(tuna);
ret = -EFAULT;
if (copy_to_user(useraddr, data, tuna.len))
goto out;
ret = 0;
out:
kfree(data);
return ret;
}
static int set_phy_tunable(struct net_device *dev, void __user *useraddr)
{
struct phy_device *phydev = dev->phydev;
struct ethtool_tunable tuna;
bool phy_drv_tunable;
void *data;
int ret;
phy_drv_tunable = phydev && phydev->drv && phydev->drv->get_tunable;
if (!phy_drv_tunable && !dev->ethtool_ops->set_phy_tunable)
return -EOPNOTSUPP;
if (copy_from_user(&tuna, useraddr, sizeof(tuna)))
return -EFAULT;
ret = ethtool_phy_tunable_valid(&tuna);
if (ret)
return ret;
useraddr += sizeof(tuna);
data = memdup_user(useraddr, tuna.len);
if (IS_ERR(data))
return PTR_ERR(data);
if (phy_drv_tunable) {
mutex_lock(&phydev->lock);
ret = phydev->drv->set_tunable(phydev, &tuna, data);
mutex_unlock(&phydev->lock);
} else {
ret = dev->ethtool_ops->set_phy_tunable(dev, &tuna, data);
}
kfree(data);
return ret;
}
net: ethtool: add support for forward error correction modes Forward Error Correction (FEC) modes i.e Base-R and Reed-Solomon modes are introduced in 25G/40G/100G standards for providing good BER at high speeds. Various networking devices which support 25G/40G/100G provides ability to manage supported FEC modes and the lack of FEC encoding control and reporting today is a source for interoperability issues for many vendors. FEC capability as well as specific FEC mode i.e. Base-R or RS modes can be requested or advertised through bits D44:47 of base link codeword. This patch set intends to provide option under ethtool to manage and report FEC encoding settings for networking devices as per IEEE 802.3 bj, bm and by specs. set-fec/show-fec option(s) are designed to provide control and report the FEC encoding on the link. SET FEC option: root@tor: ethtool --set-fec swp1 encoding [off | RS | BaseR | auto] Encoding: Types of encoding Off : Turning off any encoding RS : enforcing RS-FEC encoding on supported speeds BaseR : enforcing Base R encoding on supported speeds Auto : IEEE defaults for the speed/medium combination Here are a few examples of what we would expect if encoding=auto: - if autoneg is on, we are expecting FEC to be negotiated as on or off as long as protocol supports it - if the hardware is capable of detecting the FEC encoding on it's receiver it will reconfigure its encoder to match - in absence of the above, the configuration would be set to IEEE defaults. >From our understanding , this is essentially what most hardware/driver combinations are doing today in the absence of a way for users to control the behavior. SHOW FEC option: root@tor: ethtool --show-fec swp1 FEC parameters for swp1: Active FEC encodings: RS Configured FEC encodings: RS | BaseR ETHTOOL DEVNAME output modification: ethtool devname output: root@tor:~# ethtool swp1 Settings for swp1: root@hpe-7712-03:~# ethtool swp18 Settings for swp18: Supported ports: [ FIBRE ] Supported link modes: 40000baseCR4/Full 40000baseSR4/Full 40000baseLR4/Full 100000baseSR4/Full 100000baseCR4/Full 100000baseLR4_ER4/Full Supported pause frame use: No Supports auto-negotiation: Yes Supported FEC modes: [RS | BaseR | None | Not reported] Advertised link modes: Not reported Advertised pause frame use: No Advertised auto-negotiation: No Advertised FEC modes: [RS | BaseR | None | Not reported] <<<< One or more FEC modes Speed: 100000Mb/s Duplex: Full Port: FIBRE PHYAD: 106 Transceiver: internal Auto-negotiation: off Link detected: yes This patch includes following changes a) New ETHTOOL_SFECPARAM/SFECPARAM API, handled by the new get_fecparam/set_fecparam callbacks, provides support for configuration of forward error correction modes. b) Link mode bits for FEC modes i.e. None (No FEC mode), RS, BaseR/FC are defined so that users can configure these fec modes for supported and advertising fields as part of link autonegotiation. Signed-off-by: Vidya Sagar Ravipati <vidya.chowdary@gmail.com> Signed-off-by: Dustin Byford <dustin@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-28 07:47:26 +08:00
static int ethtool_get_fecparam(struct net_device *dev, void __user *useraddr)
{
struct ethtool_fecparam fecparam = { .cmd = ETHTOOL_GFECPARAM };
int rc;
net: ethtool: add support for forward error correction modes Forward Error Correction (FEC) modes i.e Base-R and Reed-Solomon modes are introduced in 25G/40G/100G standards for providing good BER at high speeds. Various networking devices which support 25G/40G/100G provides ability to manage supported FEC modes and the lack of FEC encoding control and reporting today is a source for interoperability issues for many vendors. FEC capability as well as specific FEC mode i.e. Base-R or RS modes can be requested or advertised through bits D44:47 of base link codeword. This patch set intends to provide option under ethtool to manage and report FEC encoding settings for networking devices as per IEEE 802.3 bj, bm and by specs. set-fec/show-fec option(s) are designed to provide control and report the FEC encoding on the link. SET FEC option: root@tor: ethtool --set-fec swp1 encoding [off | RS | BaseR | auto] Encoding: Types of encoding Off : Turning off any encoding RS : enforcing RS-FEC encoding on supported speeds BaseR : enforcing Base R encoding on supported speeds Auto : IEEE defaults for the speed/medium combination Here are a few examples of what we would expect if encoding=auto: - if autoneg is on, we are expecting FEC to be negotiated as on or off as long as protocol supports it - if the hardware is capable of detecting the FEC encoding on it's receiver it will reconfigure its encoder to match - in absence of the above, the configuration would be set to IEEE defaults. >From our understanding , this is essentially what most hardware/driver combinations are doing today in the absence of a way for users to control the behavior. SHOW FEC option: root@tor: ethtool --show-fec swp1 FEC parameters for swp1: Active FEC encodings: RS Configured FEC encodings: RS | BaseR ETHTOOL DEVNAME output modification: ethtool devname output: root@tor:~# ethtool swp1 Settings for swp1: root@hpe-7712-03:~# ethtool swp18 Settings for swp18: Supported ports: [ FIBRE ] Supported link modes: 40000baseCR4/Full 40000baseSR4/Full 40000baseLR4/Full 100000baseSR4/Full 100000baseCR4/Full 100000baseLR4_ER4/Full Supported pause frame use: No Supports auto-negotiation: Yes Supported FEC modes: [RS | BaseR | None | Not reported] Advertised link modes: Not reported Advertised pause frame use: No Advertised auto-negotiation: No Advertised FEC modes: [RS | BaseR | None | Not reported] <<<< One or more FEC modes Speed: 100000Mb/s Duplex: Full Port: FIBRE PHYAD: 106 Transceiver: internal Auto-negotiation: off Link detected: yes This patch includes following changes a) New ETHTOOL_SFECPARAM/SFECPARAM API, handled by the new get_fecparam/set_fecparam callbacks, provides support for configuration of forward error correction modes. b) Link mode bits for FEC modes i.e. None (No FEC mode), RS, BaseR/FC are defined so that users can configure these fec modes for supported and advertising fields as part of link autonegotiation. Signed-off-by: Vidya Sagar Ravipati <vidya.chowdary@gmail.com> Signed-off-by: Dustin Byford <dustin@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-28 07:47:26 +08:00
if (!dev->ethtool_ops->get_fecparam)
return -EOPNOTSUPP;
rc = dev->ethtool_ops->get_fecparam(dev, &fecparam);
if (rc)
return rc;
net: ethtool: add support for forward error correction modes Forward Error Correction (FEC) modes i.e Base-R and Reed-Solomon modes are introduced in 25G/40G/100G standards for providing good BER at high speeds. Various networking devices which support 25G/40G/100G provides ability to manage supported FEC modes and the lack of FEC encoding control and reporting today is a source for interoperability issues for many vendors. FEC capability as well as specific FEC mode i.e. Base-R or RS modes can be requested or advertised through bits D44:47 of base link codeword. This patch set intends to provide option under ethtool to manage and report FEC encoding settings for networking devices as per IEEE 802.3 bj, bm and by specs. set-fec/show-fec option(s) are designed to provide control and report the FEC encoding on the link. SET FEC option: root@tor: ethtool --set-fec swp1 encoding [off | RS | BaseR | auto] Encoding: Types of encoding Off : Turning off any encoding RS : enforcing RS-FEC encoding on supported speeds BaseR : enforcing Base R encoding on supported speeds Auto : IEEE defaults for the speed/medium combination Here are a few examples of what we would expect if encoding=auto: - if autoneg is on, we are expecting FEC to be negotiated as on or off as long as protocol supports it - if the hardware is capable of detecting the FEC encoding on it's receiver it will reconfigure its encoder to match - in absence of the above, the configuration would be set to IEEE defaults. >From our understanding , this is essentially what most hardware/driver combinations are doing today in the absence of a way for users to control the behavior. SHOW FEC option: root@tor: ethtool --show-fec swp1 FEC parameters for swp1: Active FEC encodings: RS Configured FEC encodings: RS | BaseR ETHTOOL DEVNAME output modification: ethtool devname output: root@tor:~# ethtool swp1 Settings for swp1: root@hpe-7712-03:~# ethtool swp18 Settings for swp18: Supported ports: [ FIBRE ] Supported link modes: 40000baseCR4/Full 40000baseSR4/Full 40000baseLR4/Full 100000baseSR4/Full 100000baseCR4/Full 100000baseLR4_ER4/Full Supported pause frame use: No Supports auto-negotiation: Yes Supported FEC modes: [RS | BaseR | None | Not reported] Advertised link modes: Not reported Advertised pause frame use: No Advertised auto-negotiation: No Advertised FEC modes: [RS | BaseR | None | Not reported] <<<< One or more FEC modes Speed: 100000Mb/s Duplex: Full Port: FIBRE PHYAD: 106 Transceiver: internal Auto-negotiation: off Link detected: yes This patch includes following changes a) New ETHTOOL_SFECPARAM/SFECPARAM API, handled by the new get_fecparam/set_fecparam callbacks, provides support for configuration of forward error correction modes. b) Link mode bits for FEC modes i.e. None (No FEC mode), RS, BaseR/FC are defined so that users can configure these fec modes for supported and advertising fields as part of link autonegotiation. Signed-off-by: Vidya Sagar Ravipati <vidya.chowdary@gmail.com> Signed-off-by: Dustin Byford <dustin@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-28 07:47:26 +08:00
if (WARN_ON_ONCE(fecparam.reserved))
fecparam.reserved = 0;
net: ethtool: add support for forward error correction modes Forward Error Correction (FEC) modes i.e Base-R and Reed-Solomon modes are introduced in 25G/40G/100G standards for providing good BER at high speeds. Various networking devices which support 25G/40G/100G provides ability to manage supported FEC modes and the lack of FEC encoding control and reporting today is a source for interoperability issues for many vendors. FEC capability as well as specific FEC mode i.e. Base-R or RS modes can be requested or advertised through bits D44:47 of base link codeword. This patch set intends to provide option under ethtool to manage and report FEC encoding settings for networking devices as per IEEE 802.3 bj, bm and by specs. set-fec/show-fec option(s) are designed to provide control and report the FEC encoding on the link. SET FEC option: root@tor: ethtool --set-fec swp1 encoding [off | RS | BaseR | auto] Encoding: Types of encoding Off : Turning off any encoding RS : enforcing RS-FEC encoding on supported speeds BaseR : enforcing Base R encoding on supported speeds Auto : IEEE defaults for the speed/medium combination Here are a few examples of what we would expect if encoding=auto: - if autoneg is on, we are expecting FEC to be negotiated as on or off as long as protocol supports it - if the hardware is capable of detecting the FEC encoding on it's receiver it will reconfigure its encoder to match - in absence of the above, the configuration would be set to IEEE defaults. >From our understanding , this is essentially what most hardware/driver combinations are doing today in the absence of a way for users to control the behavior. SHOW FEC option: root@tor: ethtool --show-fec swp1 FEC parameters for swp1: Active FEC encodings: RS Configured FEC encodings: RS | BaseR ETHTOOL DEVNAME output modification: ethtool devname output: root@tor:~# ethtool swp1 Settings for swp1: root@hpe-7712-03:~# ethtool swp18 Settings for swp18: Supported ports: [ FIBRE ] Supported link modes: 40000baseCR4/Full 40000baseSR4/Full 40000baseLR4/Full 100000baseSR4/Full 100000baseCR4/Full 100000baseLR4_ER4/Full Supported pause frame use: No Supports auto-negotiation: Yes Supported FEC modes: [RS | BaseR | None | Not reported] Advertised link modes: Not reported Advertised pause frame use: No Advertised auto-negotiation: No Advertised FEC modes: [RS | BaseR | None | Not reported] <<<< One or more FEC modes Speed: 100000Mb/s Duplex: Full Port: FIBRE PHYAD: 106 Transceiver: internal Auto-negotiation: off Link detected: yes This patch includes following changes a) New ETHTOOL_SFECPARAM/SFECPARAM API, handled by the new get_fecparam/set_fecparam callbacks, provides support for configuration of forward error correction modes. b) Link mode bits for FEC modes i.e. None (No FEC mode), RS, BaseR/FC are defined so that users can configure these fec modes for supported and advertising fields as part of link autonegotiation. Signed-off-by: Vidya Sagar Ravipati <vidya.chowdary@gmail.com> Signed-off-by: Dustin Byford <dustin@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-28 07:47:26 +08:00
if (copy_to_user(useraddr, &fecparam, sizeof(fecparam)))
return -EFAULT;
return 0;
}
static int ethtool_set_fecparam(struct net_device *dev, void __user *useraddr)
{
struct ethtool_fecparam fecparam;
if (!dev->ethtool_ops->set_fecparam)
return -EOPNOTSUPP;
if (copy_from_user(&fecparam, useraddr, sizeof(fecparam)))
return -EFAULT;
if (!fecparam.fec || fecparam.fec & ETHTOOL_FEC_NONE)
return -EINVAL;
fecparam.active_fec = 0;
fecparam.reserved = 0;
net: ethtool: add support for forward error correction modes Forward Error Correction (FEC) modes i.e Base-R and Reed-Solomon modes are introduced in 25G/40G/100G standards for providing good BER at high speeds. Various networking devices which support 25G/40G/100G provides ability to manage supported FEC modes and the lack of FEC encoding control and reporting today is a source for interoperability issues for many vendors. FEC capability as well as specific FEC mode i.e. Base-R or RS modes can be requested or advertised through bits D44:47 of base link codeword. This patch set intends to provide option under ethtool to manage and report FEC encoding settings for networking devices as per IEEE 802.3 bj, bm and by specs. set-fec/show-fec option(s) are designed to provide control and report the FEC encoding on the link. SET FEC option: root@tor: ethtool --set-fec swp1 encoding [off | RS | BaseR | auto] Encoding: Types of encoding Off : Turning off any encoding RS : enforcing RS-FEC encoding on supported speeds BaseR : enforcing Base R encoding on supported speeds Auto : IEEE defaults for the speed/medium combination Here are a few examples of what we would expect if encoding=auto: - if autoneg is on, we are expecting FEC to be negotiated as on or off as long as protocol supports it - if the hardware is capable of detecting the FEC encoding on it's receiver it will reconfigure its encoder to match - in absence of the above, the configuration would be set to IEEE defaults. >From our understanding , this is essentially what most hardware/driver combinations are doing today in the absence of a way for users to control the behavior. SHOW FEC option: root@tor: ethtool --show-fec swp1 FEC parameters for swp1: Active FEC encodings: RS Configured FEC encodings: RS | BaseR ETHTOOL DEVNAME output modification: ethtool devname output: root@tor:~# ethtool swp1 Settings for swp1: root@hpe-7712-03:~# ethtool swp18 Settings for swp18: Supported ports: [ FIBRE ] Supported link modes: 40000baseCR4/Full 40000baseSR4/Full 40000baseLR4/Full 100000baseSR4/Full 100000baseCR4/Full 100000baseLR4_ER4/Full Supported pause frame use: No Supports auto-negotiation: Yes Supported FEC modes: [RS | BaseR | None | Not reported] Advertised link modes: Not reported Advertised pause frame use: No Advertised auto-negotiation: No Advertised FEC modes: [RS | BaseR | None | Not reported] <<<< One or more FEC modes Speed: 100000Mb/s Duplex: Full Port: FIBRE PHYAD: 106 Transceiver: internal Auto-negotiation: off Link detected: yes This patch includes following changes a) New ETHTOOL_SFECPARAM/SFECPARAM API, handled by the new get_fecparam/set_fecparam callbacks, provides support for configuration of forward error correction modes. b) Link mode bits for FEC modes i.e. None (No FEC mode), RS, BaseR/FC are defined so that users can configure these fec modes for supported and advertising fields as part of link autonegotiation. Signed-off-by: Vidya Sagar Ravipati <vidya.chowdary@gmail.com> Signed-off-by: Dustin Byford <dustin@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-28 07:47:26 +08:00
return dev->ethtool_ops->set_fecparam(dev, &fecparam);
}
/* The main entry point in this file. Called from net/core/dev_ioctl.c */
static int
__dev_ethtool(struct net *net, struct ifreq *ifr, void __user *useraddr,
u32 ethcmd, struct ethtool_devlink_compat *devlink_state)
{
struct net_device *dev;
u32 sub_cmd;
int rc;
netdev_features_t old_features;
dev = __dev_get_by_name(net, ifr->ifr_name);
if (!dev)
return -ENODEV;
if (ethcmd == ETHTOOL_PERQUEUE) {
if (copy_from_user(&sub_cmd, useraddr + sizeof(ethcmd), sizeof(sub_cmd)))
return -EFAULT;
} else {
sub_cmd = ethcmd;
}
/* Allow some commands to be done by anyone */
switch (sub_cmd) {
case ETHTOOL_GSET:
case ETHTOOL_GDRVINFO:
case ETHTOOL_GMSGLVL:
case ETHTOOL_GLINK:
case ETHTOOL_GCOALESCE:
case ETHTOOL_GRINGPARAM:
case ETHTOOL_GPAUSEPARAM:
case ETHTOOL_GRXCSUM:
case ETHTOOL_GTXCSUM:
case ETHTOOL_GSG:
case ETHTOOL_GSSET_INFO:
case ETHTOOL_GSTRINGS:
case ETHTOOL_GSTATS:
case ETHTOOL_GPHYSTATS:
case ETHTOOL_GTSO:
case ETHTOOL_GPERMADDR:
case ETHTOOL_GUFO:
case ETHTOOL_GGSO:
case ETHTOOL_GGRO:
case ETHTOOL_GFLAGS:
case ETHTOOL_GPFLAGS:
case ETHTOOL_GRXFH:
case ETHTOOL_GRXRINGS:
case ETHTOOL_GRXCLSRLCNT:
case ETHTOOL_GRXCLSRULE:
case ETHTOOL_GRXCLSRLALL:
case ETHTOOL_GRXFHINDIR:
case ETHTOOL_GRSSH:
case ETHTOOL_GFEATURES:
case ETHTOOL_GCHANNELS:
case ETHTOOL_GET_TS_INFO:
case ETHTOOL_GEEE:
case ETHTOOL_GTUNABLE:
case ETHTOOL_PHY_GTUNABLE:
case ETHTOOL_GLINKSETTINGS:
net: ethtool: add support for forward error correction modes Forward Error Correction (FEC) modes i.e Base-R and Reed-Solomon modes are introduced in 25G/40G/100G standards for providing good BER at high speeds. Various networking devices which support 25G/40G/100G provides ability to manage supported FEC modes and the lack of FEC encoding control and reporting today is a source for interoperability issues for many vendors. FEC capability as well as specific FEC mode i.e. Base-R or RS modes can be requested or advertised through bits D44:47 of base link codeword. This patch set intends to provide option under ethtool to manage and report FEC encoding settings for networking devices as per IEEE 802.3 bj, bm and by specs. set-fec/show-fec option(s) are designed to provide control and report the FEC encoding on the link. SET FEC option: root@tor: ethtool --set-fec swp1 encoding [off | RS | BaseR | auto] Encoding: Types of encoding Off : Turning off any encoding RS : enforcing RS-FEC encoding on supported speeds BaseR : enforcing Base R encoding on supported speeds Auto : IEEE defaults for the speed/medium combination Here are a few examples of what we would expect if encoding=auto: - if autoneg is on, we are expecting FEC to be negotiated as on or off as long as protocol supports it - if the hardware is capable of detecting the FEC encoding on it's receiver it will reconfigure its encoder to match - in absence of the above, the configuration would be set to IEEE defaults. >From our understanding , this is essentially what most hardware/driver combinations are doing today in the absence of a way for users to control the behavior. SHOW FEC option: root@tor: ethtool --show-fec swp1 FEC parameters for swp1: Active FEC encodings: RS Configured FEC encodings: RS | BaseR ETHTOOL DEVNAME output modification: ethtool devname output: root@tor:~# ethtool swp1 Settings for swp1: root@hpe-7712-03:~# ethtool swp18 Settings for swp18: Supported ports: [ FIBRE ] Supported link modes: 40000baseCR4/Full 40000baseSR4/Full 40000baseLR4/Full 100000baseSR4/Full 100000baseCR4/Full 100000baseLR4_ER4/Full Supported pause frame use: No Supports auto-negotiation: Yes Supported FEC modes: [RS | BaseR | None | Not reported] Advertised link modes: Not reported Advertised pause frame use: No Advertised auto-negotiation: No Advertised FEC modes: [RS | BaseR | None | Not reported] <<<< One or more FEC modes Speed: 100000Mb/s Duplex: Full Port: FIBRE PHYAD: 106 Transceiver: internal Auto-negotiation: off Link detected: yes This patch includes following changes a) New ETHTOOL_SFECPARAM/SFECPARAM API, handled by the new get_fecparam/set_fecparam callbacks, provides support for configuration of forward error correction modes. b) Link mode bits for FEC modes i.e. None (No FEC mode), RS, BaseR/FC are defined so that users can configure these fec modes for supported and advertising fields as part of link autonegotiation. Signed-off-by: Vidya Sagar Ravipati <vidya.chowdary@gmail.com> Signed-off-by: Dustin Byford <dustin@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-28 07:47:26 +08:00
case ETHTOOL_GFECPARAM:
break;
default:
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
}
if (dev->dev.parent)
pm_runtime_get_sync(dev->dev.parent);
if (!netif_device_present(dev)) {
rc = -ENODEV;
goto out;
}
if (dev->ethtool_ops->begin) {
rc = dev->ethtool_ops->begin(dev);
if (rc < 0)
goto out;
}
old_features = dev->features;
switch (ethcmd) {
case ETHTOOL_GSET:
rc = ethtool_get_settings(dev, useraddr);
break;
case ETHTOOL_SSET:
rc = ethtool_set_settings(dev, useraddr);
break;
case ETHTOOL_GDRVINFO:
rc = ethtool_get_drvinfo(dev, devlink_state);
break;
case ETHTOOL_GREGS:
rc = ethtool_get_regs(dev, useraddr);
break;
case ETHTOOL_GWOL:
rc = ethtool_get_wol(dev, useraddr);
break;
case ETHTOOL_SWOL:
rc = ethtool_set_wol(dev, useraddr);
break;
case ETHTOOL_GMSGLVL:
rc = ethtool_get_value(dev, useraddr, ethcmd,
dev->ethtool_ops->get_msglevel);
break;
case ETHTOOL_SMSGLVL:
rc = ethtool_set_value_void(dev, useraddr,
dev->ethtool_ops->set_msglevel);
if (!rc)
ethtool_notify(dev, ETHTOOL_MSG_DEBUG_NTF, NULL);
break;
case ETHTOOL_GEEE:
rc = ethtool_get_eee(dev, useraddr);
break;
case ETHTOOL_SEEE:
rc = ethtool_set_eee(dev, useraddr);
break;
case ETHTOOL_NWAY_RST:
rc = ethtool_nway_reset(dev);
break;
case ETHTOOL_GLINK:
rc = ethtool_get_link(dev, useraddr);
break;
case ETHTOOL_GEEPROM:
rc = ethtool_get_eeprom(dev, useraddr);
break;
case ETHTOOL_SEEPROM:
rc = ethtool_set_eeprom(dev, useraddr);
break;
case ETHTOOL_GCOALESCE:
rc = ethtool_get_coalesce(dev, useraddr);
break;
case ETHTOOL_SCOALESCE:
rc = ethtool_set_coalesce(dev, useraddr);
break;
case ETHTOOL_GRINGPARAM:
rc = ethtool_get_ringparam(dev, useraddr);
break;
case ETHTOOL_SRINGPARAM:
rc = ethtool_set_ringparam(dev, useraddr);
break;
case ETHTOOL_GPAUSEPARAM:
rc = ethtool_get_pauseparam(dev, useraddr);
break;
case ETHTOOL_SPAUSEPARAM:
rc = ethtool_set_pauseparam(dev, useraddr);
break;
case ETHTOOL_TEST:
rc = ethtool_self_test(dev, useraddr);
break;
case ETHTOOL_GSTRINGS:
rc = ethtool_get_strings(dev, useraddr);
break;
case ETHTOOL_PHYS_ID:
rc = ethtool_phys_id(dev, useraddr);
break;
case ETHTOOL_GSTATS:
rc = ethtool_get_stats(dev, useraddr);
break;
case ETHTOOL_GPERMADDR:
rc = ethtool_get_perm_addr(dev, useraddr);
break;
case ETHTOOL_GFLAGS:
rc = ethtool_get_value(dev, useraddr, ethcmd,
__ethtool_get_flags);
break;
case ETHTOOL_SFLAGS:
rc = ethtool_set_value(dev, useraddr, __ethtool_set_flags);
break;
case ETHTOOL_GPFLAGS:
rc = ethtool_get_value(dev, useraddr, ethcmd,
dev->ethtool_ops->get_priv_flags);
if (!rc)
ethtool_notify(dev, ETHTOOL_MSG_PRIVFLAGS_NTF, NULL);
break;
case ETHTOOL_SPFLAGS:
rc = ethtool_set_value(dev, useraddr,
dev->ethtool_ops->set_priv_flags);
break;
case ETHTOOL_GRXFH:
case ETHTOOL_GRXRINGS:
case ETHTOOL_GRXCLSRLCNT:
case ETHTOOL_GRXCLSRULE:
case ETHTOOL_GRXCLSRLALL:
rc = ethtool_get_rxnfc(dev, ethcmd, useraddr);
break;
case ETHTOOL_SRXFH:
case ETHTOOL_SRXCLSRLDEL:
case ETHTOOL_SRXCLSRLINS:
rc = ethtool_set_rxnfc(dev, ethcmd, useraddr);
break;
case ETHTOOL_FLASHDEV:
rc = ethtool_flash_device(dev, devlink_state);
break;
case ETHTOOL_RESET:
rc = ethtool_reset(dev, useraddr);
break;
case ETHTOOL_GSSET_INFO:
rc = ethtool_get_sset_info(dev, useraddr);
break;
case ETHTOOL_GRXFHINDIR:
rc = ethtool_get_rxfh_indir(dev, useraddr);
break;
case ETHTOOL_SRXFHINDIR:
rc = ethtool_set_rxfh_indir(dev, useraddr);
break;
case ETHTOOL_GRSSH:
rc = ethtool_get_rxfh(dev, useraddr);
break;
case ETHTOOL_SRSSH:
rc = ethtool_set_rxfh(dev, useraddr);
break;
case ETHTOOL_GFEATURES:
rc = ethtool_get_features(dev, useraddr);
break;
case ETHTOOL_SFEATURES:
rc = ethtool_set_features(dev, useraddr);
break;
case ETHTOOL_GTXCSUM:
case ETHTOOL_GRXCSUM:
case ETHTOOL_GSG:
case ETHTOOL_GTSO:
case ETHTOOL_GGSO:
case ETHTOOL_GGRO:
rc = ethtool_get_one_feature(dev, useraddr, ethcmd);
break;
case ETHTOOL_STXCSUM:
case ETHTOOL_SRXCSUM:
case ETHTOOL_SSG:
case ETHTOOL_STSO:
case ETHTOOL_SGSO:
case ETHTOOL_SGRO:
rc = ethtool_set_one_feature(dev, useraddr, ethcmd);
break;
case ETHTOOL_GCHANNELS:
rc = ethtool_get_channels(dev, useraddr);
break;
case ETHTOOL_SCHANNELS:
rc = ethtool_set_channels(dev, useraddr);
break;
case ETHTOOL_SET_DUMP:
rc = ethtool_set_dump(dev, useraddr);
break;
case ETHTOOL_GET_DUMP_FLAG:
rc = ethtool_get_dump_flag(dev, useraddr);
break;
case ETHTOOL_GET_DUMP_DATA:
rc = ethtool_get_dump_data(dev, useraddr);
break;
case ETHTOOL_GET_TS_INFO:
rc = ethtool_get_ts_info(dev, useraddr);
break;
case ETHTOOL_GMODULEINFO:
rc = ethtool_get_module_info(dev, useraddr);
break;
case ETHTOOL_GMODULEEEPROM:
rc = ethtool_get_module_eeprom(dev, useraddr);
break;
case ETHTOOL_GTUNABLE:
rc = ethtool_get_tunable(dev, useraddr);
break;
case ETHTOOL_STUNABLE:
rc = ethtool_set_tunable(dev, useraddr);
break;
case ETHTOOL_GPHYSTATS:
rc = ethtool_get_phy_stats(dev, useraddr);
break;
case ETHTOOL_PERQUEUE:
ethtool: fix a privilege escalation bug In dev_ethtool(), the eth command 'ethcmd' is firstly copied from the use-space buffer 'useraddr' and checked to see whether it is ETHTOOL_PERQUEUE. If yes, the sub-command 'sub_cmd' is further copied from the user space. Otherwise, 'sub_cmd' is the same as 'ethcmd'. Next, according to 'sub_cmd', a permission check is enforced through the function ns_capable(). For example, the permission check is required if 'sub_cmd' is ETHTOOL_SCOALESCE, but it is not necessary if 'sub_cmd' is ETHTOOL_GCOALESCE, as suggested in the comment "Allow some commands to be done by anyone". The following execution invokes different handlers according to 'ethcmd'. Specifically, if 'ethcmd' is ETHTOOL_PERQUEUE, ethtool_set_per_queue() is called. In ethtool_set_per_queue(), the kernel object 'per_queue_opt' is copied again from the user-space buffer 'useraddr' and 'per_queue_opt.sub_command' is used to determine which operation should be performed. Given that the buffer 'useraddr' is in the user space, a malicious user can race to change the sub-command between the two copies. In particular, the attacker can supply ETHTOOL_PERQUEUE and ETHTOOL_GCOALESCE to bypass the permission check in dev_ethtool(). Then before ethtool_set_per_queue() is called, the attacker changes ETHTOOL_GCOALESCE to ETHTOOL_SCOALESCE. In this way, the attacker can bypass the permission check and execute ETHTOOL_SCOALESCE. This patch enforces a check in ethtool_set_per_queue() after the second copy from 'useraddr'. If the sub-command is different from the one obtained in the first copy in dev_ethtool(), an error code EINVAL will be returned. Fixes: f38d138a7da6 ("net/ethtool: support set coalesce per queue") Signed-off-by: Wenwen Wang <wang6495@umn.edu> Reviewed-by: Michal Kubecek <mkubecek@suse.cz> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-08 23:49:35 +08:00
rc = ethtool_set_per_queue(dev, useraddr, sub_cmd);
break;
net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny <decot@googlers.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-25 02:57:59 +08:00
case ETHTOOL_GLINKSETTINGS:
rc = ethtool_get_link_ksettings(dev, useraddr);
break;
case ETHTOOL_SLINKSETTINGS:
rc = ethtool_set_link_ksettings(dev, useraddr);
break;
case ETHTOOL_PHY_GTUNABLE:
rc = get_phy_tunable(dev, useraddr);
break;
case ETHTOOL_PHY_STUNABLE:
rc = set_phy_tunable(dev, useraddr);
break;
net: ethtool: add support for forward error correction modes Forward Error Correction (FEC) modes i.e Base-R and Reed-Solomon modes are introduced in 25G/40G/100G standards for providing good BER at high speeds. Various networking devices which support 25G/40G/100G provides ability to manage supported FEC modes and the lack of FEC encoding control and reporting today is a source for interoperability issues for many vendors. FEC capability as well as specific FEC mode i.e. Base-R or RS modes can be requested or advertised through bits D44:47 of base link codeword. This patch set intends to provide option under ethtool to manage and report FEC encoding settings for networking devices as per IEEE 802.3 bj, bm and by specs. set-fec/show-fec option(s) are designed to provide control and report the FEC encoding on the link. SET FEC option: root@tor: ethtool --set-fec swp1 encoding [off | RS | BaseR | auto] Encoding: Types of encoding Off : Turning off any encoding RS : enforcing RS-FEC encoding on supported speeds BaseR : enforcing Base R encoding on supported speeds Auto : IEEE defaults for the speed/medium combination Here are a few examples of what we would expect if encoding=auto: - if autoneg is on, we are expecting FEC to be negotiated as on or off as long as protocol supports it - if the hardware is capable of detecting the FEC encoding on it's receiver it will reconfigure its encoder to match - in absence of the above, the configuration would be set to IEEE defaults. >From our understanding , this is essentially what most hardware/driver combinations are doing today in the absence of a way for users to control the behavior. SHOW FEC option: root@tor: ethtool --show-fec swp1 FEC parameters for swp1: Active FEC encodings: RS Configured FEC encodings: RS | BaseR ETHTOOL DEVNAME output modification: ethtool devname output: root@tor:~# ethtool swp1 Settings for swp1: root@hpe-7712-03:~# ethtool swp18 Settings for swp18: Supported ports: [ FIBRE ] Supported link modes: 40000baseCR4/Full 40000baseSR4/Full 40000baseLR4/Full 100000baseSR4/Full 100000baseCR4/Full 100000baseLR4_ER4/Full Supported pause frame use: No Supports auto-negotiation: Yes Supported FEC modes: [RS | BaseR | None | Not reported] Advertised link modes: Not reported Advertised pause frame use: No Advertised auto-negotiation: No Advertised FEC modes: [RS | BaseR | None | Not reported] <<<< One or more FEC modes Speed: 100000Mb/s Duplex: Full Port: FIBRE PHYAD: 106 Transceiver: internal Auto-negotiation: off Link detected: yes This patch includes following changes a) New ETHTOOL_SFECPARAM/SFECPARAM API, handled by the new get_fecparam/set_fecparam callbacks, provides support for configuration of forward error correction modes. b) Link mode bits for FEC modes i.e. None (No FEC mode), RS, BaseR/FC are defined so that users can configure these fec modes for supported and advertising fields as part of link autonegotiation. Signed-off-by: Vidya Sagar Ravipati <vidya.chowdary@gmail.com> Signed-off-by: Dustin Byford <dustin@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-28 07:47:26 +08:00
case ETHTOOL_GFECPARAM:
rc = ethtool_get_fecparam(dev, useraddr);
break;
case ETHTOOL_SFECPARAM:
rc = ethtool_set_fecparam(dev, useraddr);
break;
default:
rc = -EOPNOTSUPP;
}
if (dev->ethtool_ops->complete)
dev->ethtool_ops->complete(dev);
if (old_features != dev->features)
netdev_features_change(dev);
out:
if (dev->dev.parent)
pm_runtime_put(dev->dev.parent);
return rc;
}
int dev_ethtool(struct net *net, struct ifreq *ifr, void __user *useraddr)
{
struct ethtool_devlink_compat *state;
u32 ethcmd;
int rc;
if (copy_from_user(&ethcmd, useraddr, sizeof(ethcmd)))
return -EFAULT;
state = kzalloc(sizeof(*state), GFP_KERNEL);
if (!state)
return -ENOMEM;
switch (ethcmd) {
case ETHTOOL_FLASHDEV:
if (copy_from_user(&state->efl, useraddr, sizeof(state->efl))) {
rc = -EFAULT;
goto exit_free;
}
state->efl.data[ETHTOOL_FLASH_MAX_FILENAME - 1] = 0;
break;
}
rtnl_lock();
rc = __dev_ethtool(net, ifr, useraddr, ethcmd, state);
rtnl_unlock();
if (rc)
goto exit_free;
switch (ethcmd) {
case ETHTOOL_FLASHDEV:
if (state->devlink)
rc = devlink_compat_flash_update(state->devlink,
state->efl.data);
break;
case ETHTOOL_GDRVINFO:
if (state->devlink)
devlink_compat_running_version(state->devlink,
state->info.fw_version,
sizeof(state->info.fw_version));
if (copy_to_user(useraddr, &state->info, sizeof(state->info))) {
rc = -EFAULT;
goto exit_free;
}
break;
}
exit_free:
if (state->devlink)
devlink_put(state->devlink);
kfree(state);
return rc;
}
struct ethtool_rx_flow_key {
struct flow_dissector_key_basic basic;
union {
struct flow_dissector_key_ipv4_addrs ipv4;
struct flow_dissector_key_ipv6_addrs ipv6;
};
struct flow_dissector_key_ports tp;
struct flow_dissector_key_ip ip;
struct flow_dissector_key_vlan vlan;
struct flow_dissector_key_eth_addrs eth_addrs;
} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
struct ethtool_rx_flow_match {
struct flow_dissector dissector;
struct ethtool_rx_flow_key key;
struct ethtool_rx_flow_key mask;
};
struct ethtool_rx_flow_rule *
ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input)
{
const struct ethtool_rx_flow_spec *fs = input->fs;
static struct in6_addr zero_addr = {};
struct ethtool_rx_flow_match *match;
struct ethtool_rx_flow_rule *flow;
struct flow_action_entry *act;
flow = kzalloc(sizeof(struct ethtool_rx_flow_rule) +
sizeof(struct ethtool_rx_flow_match), GFP_KERNEL);
if (!flow)
return ERR_PTR(-ENOMEM);
/* ethtool_rx supports only one single action per rule. */
flow->rule = flow_rule_alloc(1);
if (!flow->rule) {
kfree(flow);
return ERR_PTR(-ENOMEM);
}
match = (struct ethtool_rx_flow_match *)flow->priv;
flow->rule->match.dissector = &match->dissector;
flow->rule->match.mask = &match->mask;
flow->rule->match.key = &match->key;
match->mask.basic.n_proto = htons(0xffff);
switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS)) {
case ETHER_FLOW: {
const struct ethhdr *ether_spec, *ether_m_spec;
ether_spec = &fs->h_u.ether_spec;
ether_m_spec = &fs->m_u.ether_spec;
if (!is_zero_ether_addr(ether_m_spec->h_source)) {
ether_addr_copy(match->key.eth_addrs.src,
ether_spec->h_source);
ether_addr_copy(match->mask.eth_addrs.src,
ether_m_spec->h_source);
}
if (!is_zero_ether_addr(ether_m_spec->h_dest)) {
ether_addr_copy(match->key.eth_addrs.dst,
ether_spec->h_dest);
ether_addr_copy(match->mask.eth_addrs.dst,
ether_m_spec->h_dest);
}
if (ether_m_spec->h_proto) {
match->key.basic.n_proto = ether_spec->h_proto;
match->mask.basic.n_proto = ether_m_spec->h_proto;
}
}
break;
case TCP_V4_FLOW:
case UDP_V4_FLOW: {
const struct ethtool_tcpip4_spec *v4_spec, *v4_m_spec;
match->key.basic.n_proto = htons(ETH_P_IP);
v4_spec = &fs->h_u.tcp_ip4_spec;
v4_m_spec = &fs->m_u.tcp_ip4_spec;
if (v4_m_spec->ip4src) {
match->key.ipv4.src = v4_spec->ip4src;
match->mask.ipv4.src = v4_m_spec->ip4src;
}
if (v4_m_spec->ip4dst) {
match->key.ipv4.dst = v4_spec->ip4dst;
match->mask.ipv4.dst = v4_m_spec->ip4dst;
}
if (v4_m_spec->ip4src ||
v4_m_spec->ip4dst) {
match->dissector.used_keys |=
BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS);
match->dissector.offset[FLOW_DISSECTOR_KEY_IPV4_ADDRS] =
offsetof(struct ethtool_rx_flow_key, ipv4);
}
if (v4_m_spec->psrc) {
match->key.tp.src = v4_spec->psrc;
match->mask.tp.src = v4_m_spec->psrc;
}
if (v4_m_spec->pdst) {
match->key.tp.dst = v4_spec->pdst;
match->mask.tp.dst = v4_m_spec->pdst;
}
if (v4_m_spec->psrc ||
v4_m_spec->pdst) {
match->dissector.used_keys |=
BIT(FLOW_DISSECTOR_KEY_PORTS);
match->dissector.offset[FLOW_DISSECTOR_KEY_PORTS] =
offsetof(struct ethtool_rx_flow_key, tp);
}
if (v4_m_spec->tos) {
match->key.ip.tos = v4_spec->tos;
match->mask.ip.tos = v4_m_spec->tos;
match->dissector.used_keys |=
BIT(FLOW_DISSECTOR_KEY_IP);
match->dissector.offset[FLOW_DISSECTOR_KEY_IP] =
offsetof(struct ethtool_rx_flow_key, ip);
}
}
break;
case TCP_V6_FLOW:
case UDP_V6_FLOW: {
const struct ethtool_tcpip6_spec *v6_spec, *v6_m_spec;
match->key.basic.n_proto = htons(ETH_P_IPV6);
v6_spec = &fs->h_u.tcp_ip6_spec;
v6_m_spec = &fs->m_u.tcp_ip6_spec;
if (memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr))) {
memcpy(&match->key.ipv6.src, v6_spec->ip6src,
sizeof(match->key.ipv6.src));
memcpy(&match->mask.ipv6.src, v6_m_spec->ip6src,
sizeof(match->mask.ipv6.src));
}
if (memcmp(v6_m_spec->ip6dst, &zero_addr, sizeof(zero_addr))) {
memcpy(&match->key.ipv6.dst, v6_spec->ip6dst,
sizeof(match->key.ipv6.dst));
memcpy(&match->mask.ipv6.dst, v6_m_spec->ip6dst,
sizeof(match->mask.ipv6.dst));
}
if (memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr)) ||
memcmp(v6_m_spec->ip6dst, &zero_addr, sizeof(zero_addr))) {
match->dissector.used_keys |=
BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS);
match->dissector.offset[FLOW_DISSECTOR_KEY_IPV6_ADDRS] =
offsetof(struct ethtool_rx_flow_key, ipv6);
}
if (v6_m_spec->psrc) {
match->key.tp.src = v6_spec->psrc;
match->mask.tp.src = v6_m_spec->psrc;
}
if (v6_m_spec->pdst) {
match->key.tp.dst = v6_spec->pdst;
match->mask.tp.dst = v6_m_spec->pdst;
}
if (v6_m_spec->psrc ||
v6_m_spec->pdst) {
match->dissector.used_keys |=
BIT(FLOW_DISSECTOR_KEY_PORTS);
match->dissector.offset[FLOW_DISSECTOR_KEY_PORTS] =
offsetof(struct ethtool_rx_flow_key, tp);
}
if (v6_m_spec->tclass) {
match->key.ip.tos = v6_spec->tclass;
match->mask.ip.tos = v6_m_spec->tclass;
match->dissector.used_keys |=
BIT(FLOW_DISSECTOR_KEY_IP);
match->dissector.offset[FLOW_DISSECTOR_KEY_IP] =
offsetof(struct ethtool_rx_flow_key, ip);
}
}
break;
default:
ethtool_rx_flow_rule_destroy(flow);
return ERR_PTR(-EINVAL);
}
switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS)) {
case TCP_V4_FLOW:
case TCP_V6_FLOW:
match->key.basic.ip_proto = IPPROTO_TCP;
match->mask.basic.ip_proto = 0xff;
break;
case UDP_V4_FLOW:
case UDP_V6_FLOW:
match->key.basic.ip_proto = IPPROTO_UDP;
match->mask.basic.ip_proto = 0xff;
break;
}
match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_BASIC);
match->dissector.offset[FLOW_DISSECTOR_KEY_BASIC] =
offsetof(struct ethtool_rx_flow_key, basic);
if (fs->flow_type & FLOW_EXT) {
const struct ethtool_flow_ext *ext_h_spec = &fs->h_ext;
const struct ethtool_flow_ext *ext_m_spec = &fs->m_ext;
if (ext_m_spec->vlan_etype) {
match->key.vlan.vlan_tpid = ext_h_spec->vlan_etype;
match->mask.vlan.vlan_tpid = ext_m_spec->vlan_etype;
}
if (ext_m_spec->vlan_tci) {
match->key.vlan.vlan_id =
ntohs(ext_h_spec->vlan_tci) & 0x0fff;
match->mask.vlan.vlan_id =
ntohs(ext_m_spec->vlan_tci) & 0x0fff;
match->key.vlan.vlan_dei =
!!(ext_h_spec->vlan_tci & htons(0x1000));
match->mask.vlan.vlan_dei =
!!(ext_m_spec->vlan_tci & htons(0x1000));
match->key.vlan.vlan_priority =
(ntohs(ext_h_spec->vlan_tci) & 0xe000) >> 13;
match->mask.vlan.vlan_priority =
(ntohs(ext_m_spec->vlan_tci) & 0xe000) >> 13;
}
if (ext_m_spec->vlan_etype ||
ext_m_spec->vlan_tci) {
match->dissector.used_keys |=
BIT(FLOW_DISSECTOR_KEY_VLAN);
match->dissector.offset[FLOW_DISSECTOR_KEY_VLAN] =
offsetof(struct ethtool_rx_flow_key, vlan);
}
}
if (fs->flow_type & FLOW_MAC_EXT) {
const struct ethtool_flow_ext *ext_h_spec = &fs->h_ext;
const struct ethtool_flow_ext *ext_m_spec = &fs->m_ext;
memcpy(match->key.eth_addrs.dst, ext_h_spec->h_dest,
ETH_ALEN);
memcpy(match->mask.eth_addrs.dst, ext_m_spec->h_dest,
ETH_ALEN);
match->dissector.used_keys |=
BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS);
match->dissector.offset[FLOW_DISSECTOR_KEY_ETH_ADDRS] =
offsetof(struct ethtool_rx_flow_key, eth_addrs);
}
act = &flow->rule->action.entries[0];
switch (fs->ring_cookie) {
case RX_CLS_FLOW_DISC:
act->id = FLOW_ACTION_DROP;
break;
case RX_CLS_FLOW_WAKE:
act->id = FLOW_ACTION_WAKE;
break;
default:
act->id = FLOW_ACTION_QUEUE;
if (fs->flow_type & FLOW_RSS)
act->queue.ctx = input->rss_ctx;
act->queue.vf = ethtool_get_flow_spec_ring_vf(fs->ring_cookie);
act->queue.index = ethtool_get_flow_spec_ring(fs->ring_cookie);
break;
}
return flow;
}
EXPORT_SYMBOL(ethtool_rx_flow_rule_create);
void ethtool_rx_flow_rule_destroy(struct ethtool_rx_flow_rule *flow)
{
kfree(flow->rule);
kfree(flow);
}
EXPORT_SYMBOL(ethtool_rx_flow_rule_destroy);