- "renesas,etheravb-r8a774a1" for the R8A774A1 SoC.
- "renesas,etheravb-r8a774b1" for the R8A774B1 SoC.
- "renesas,etheravb-r8a774c0" for the R8A774C0 SoC.
+ - "renesas,etheravb-r8a774e1" for the R8A774E1 SoC.
- "renesas,etheravb-r8a7795" for the R8A7795 SoC.
- "renesas,etheravb-r8a7796" for the R8A77960 SoC.
- "renesas,etheravb-r8a77961" for the R8A77961 SoC.
F: include/uapi/drm/i915_drm.h
INTEL ETHERNET DRIVERS
-M: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
+M: Jesse Brandeburg <jesse.brandeburg@intel.com>
+M: Tony Nguyen <anthony.l.nguyen@intel.com>
L: intel-wired-lan@lists.osuosl.org (moderated for non-subscribers)
S: Supported
W: http://www.intel.com/support/feedback.htm
M: Andrew Lunn <andrew@lunn.ch>
M: Vivien Didelot <vivien.didelot@gmail.com>
M: Florian Fainelli <f.fainelli@gmail.com>
+M: Vladimir Oltean <olteanv@gmail.com>
S: Maintained
F: Documentation/devicetree/bindings/net/dsa/
F: drivers/net/dsa/
F: include/linux/vga_switcheroo.h
VIA RHINE NETWORK DRIVER
-S: Orphan
+S: Maintained
+M: Kevin Brace <kevinbrace@bracecomputerlab.com>
F: drivers/net/ethernet/via/via-rhine.c
VIA SD/MMC CARD CONTROLLER DRIVER
F: arch/x86/mm/
X86 PLATFORM DRIVERS
-M: Darren Hart <dvhart@infradead.org>
-M: Andy Shevchenko <andy@infradead.org>
+M: Hans de Goede <hdegoede@redhat.com>
+M: Mark Gross <mgross@linux.intel.com>
L: platform-driver-x86@vger.kernel.org
-S: Odd Fixes
+S: Maintained
T: git git://git.infradead.org/linux-platform-drivers-x86.git
F: drivers/platform/olpc/
F: drivers/platform/x86/
pr_info("Xen: initializing cpu%d\n", cpu);
vcpup = per_cpu_ptr(xen_vcpu_info, cpu);
- info.mfn = virt_to_gfn(vcpup);
+ info.mfn = percpu_to_gfn(vcpup);
info.offset = xen_offset_in_page(vcpup);
err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, xen_vcpu_nr(cpu),
0: mov bskey, x21
mov rounds, x22
- br x7
+ br x16
SYM_FUNC_END(__xts_crypt8)
.macro __xts_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7
uzp1 v30.4s, v30.4s, v25.4s
ld1 {v25.16b}, [x24]
-99: adr x7, \do8
+99: adr x16, \do8
bl __xts_crypt8
ldp q16, q17, [sp, #.Lframe_local_offset]
case BPF_JMP | BPF_JSET | BPF_K:
case BPF_JMP | BPF_JSET | BPF_X:
true_cond = COND_NE;
- fallthrough;
cond_branch:
/* same targets, can avoid doing the test :) */
if (filter[i].jt == filter[i].jf) {
if (!disk->fops->getgeo)
goto out_exit;
fn = symbol_get(dasd_biodasdinfo);
- if (!fn)
- goto out_exit;
blocksize = bdev_logical_block_size(bdev);
if (blocksize <= 0)
goto out_symbol;
geo->start = get_start_sect(bdev);
if (disk->fops->getgeo(bdev, geo))
goto out_freeall;
- if (fn(disk, info)) {
+ if (!fn || fn(disk, info)) {
kfree(info);
info = NULL;
}
out_nogeo:
kfree(info);
out_symbol:
- symbol_put(dasd_biodasdinfo);
+ if (fn)
+ symbol_put(dasd_biodasdinfo);
out_exit:
return res;
}
compat_int_t stat;
compat_caddr_t sense;
unsigned char data_direction;
+ unsigned char pad[3];
compat_int_t quiet;
compat_int_t timeout;
compat_caddr_t reserved[1];
* put_page(); and would cause either a VM_BUG directly, or
* __page_cache_release a page that would actually still be referenced
* by someone, leading to some obscure delayed Oops somewhere else. */
- if (drbd_disable_sendpage || (page_count(page) < 1) || PageSlab(page))
+ if (drbd_disable_sendpage || !sendpage_ok(page))
return _drbd_no_send_page(peer_device, page, offset, size, msg_flags);
msg_flags |= MSG_NOSIGNAL;
}
EXPORT_SYMBOL(rdma_read_gid_attr_ndev_rcu);
-static int get_lower_dev_vlan(struct net_device *lower_dev, void *data)
+static int get_lower_dev_vlan(struct net_device *lower_dev,
+ struct netdev_nested_priv *priv)
{
- u16 *vlan_id = data;
+ u16 *vlan_id = (u16 *)priv->data;
if (is_vlan_dev(lower_dev))
*vlan_id = vlan_dev_vlan_id(lower_dev);
int rdma_read_gid_l2_fields(const struct ib_gid_attr *attr,
u16 *vlan_id, u8 *smac)
{
+ struct netdev_nested_priv priv = {
+ .data = (void *)vlan_id,
+ };
struct net_device *ndev;
rcu_read_lock();
* the lower vlan device for this gid entry.
*/
netdev_walk_all_lower_dev_rcu(attr->ndev,
- get_lower_dev_vlan, vlan_id);
+ get_lower_dev_vlan, &priv);
}
}
rcu_read_unlock();
bool found;
};
-static int get_lower_vlan_dev_tc(struct net_device *dev, void *data)
+static int get_lower_vlan_dev_tc(struct net_device *dev,
+ struct netdev_nested_priv *priv)
{
- struct iboe_prio_tc_map *map = data;
+ struct iboe_prio_tc_map *map = (struct iboe_prio_tc_map *)priv->data;
if (is_vlan_dev(dev))
map->output_tc = get_vlan_ndev_tc(dev, map->input_prio);
{
struct iboe_prio_tc_map prio_tc_map = {};
int prio = rt_tos2priority(tos);
+ struct netdev_nested_priv priv;
/* If VLAN device, get it directly from the VLAN netdev */
if (is_vlan_dev(ndev))
return get_vlan_ndev_tc(ndev, prio);
prio_tc_map.input_prio = prio;
+ priv.data = (void *)&prio_tc_map;
rcu_read_lock();
netdev_walk_all_lower_dev_rcu(ndev,
get_lower_vlan_dev_tc,
- &prio_tc_map);
+ &priv);
rcu_read_unlock();
/* If map is found from lower device, use it; Otherwise
* continue with the current netdevice to get priority to tc map.
struct net_device *upper;
};
-static int netdev_upper_walk(struct net_device *upper, void *data)
+static int netdev_upper_walk(struct net_device *upper,
+ struct netdev_nested_priv *priv)
{
struct upper_list *entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
- struct list_head *upper_list = data;
+ struct list_head *upper_list = (struct list_head *)priv->data;
if (!entry)
return 0;
struct net_device *ndev))
{
struct net_device *ndev = cookie;
+ struct netdev_nested_priv priv;
struct upper_list *upper_iter;
struct upper_list *upper_temp;
LIST_HEAD(upper_list);
+ priv.data = &upper_list;
rcu_read_lock();
- netdev_walk_all_upper_dev_rcu(ndev, netdev_upper_walk, &upper_list);
+ netdev_walk_all_upper_dev_rcu(ndev, netdev_upper_walk, &priv);
rcu_read_unlock();
handle_netdev(ib_dev, port, ndev);
struct net_device *result;
};
-static int ipoib_upper_walk(struct net_device *upper, void *_data)
+static int ipoib_upper_walk(struct net_device *upper,
+ struct netdev_nested_priv *priv)
{
- struct ipoib_walk_data *data = _data;
+ struct ipoib_walk_data *data = (struct ipoib_walk_data *)priv->data;
int ret = 0;
if (ipoib_is_dev_match_addr_rcu(data->addr, upper)) {
static struct net_device *ipoib_get_net_dev_match_addr(
const struct sockaddr *addr, struct net_device *dev)
{
+ struct netdev_nested_priv priv;
struct ipoib_walk_data data = {
.addr = addr,
};
+ priv.data = (void *)&data;
rcu_read_lock();
if (ipoib_is_dev_match_addr_rcu(addr, dev)) {
dev_hold(dev);
goto out;
}
- netdev_walk_all_upper_dev_rcu(dev, ipoib_upper_walk, &data);
+ netdev_walk_all_upper_dev_rcu(dev, ipoib_upper_walk, &priv);
out:
rcu_read_unlock();
return data.result;
bool strict_match;
};
-static int alb_upper_dev_walk(struct net_device *upper, void *_data)
+static int alb_upper_dev_walk(struct net_device *upper,
+ struct netdev_nested_priv *priv)
{
- struct alb_walk_data *data = _data;
+ struct alb_walk_data *data = (struct alb_walk_data *)priv->data;
bool strict_match = data->strict_match;
struct bonding *bond = data->bond;
struct slave *slave = data->slave;
bool strict_match)
{
struct bonding *bond = bond_get_bond_by_slave(slave);
+ struct netdev_nested_priv priv;
struct alb_walk_data data = {
.strict_match = strict_match,
.mac_addr = mac_addr,
.bond = bond,
};
+ priv.data = (void *)&data;
/* send untagged */
alb_send_lp_vid(slave, mac_addr, 0, 0);
* for that device.
*/
rcu_read_lock();
- netdev_walk_all_upper_dev_rcu(bond->dev, alb_upper_dev_walk, &data);
+ netdev_walk_all_upper_dev_rcu(bond->dev, alb_upper_dev_walk, &priv);
rcu_read_unlock();
}
bond_dev->type = slave_dev->type;
bond_dev->hard_header_len = slave_dev->hard_header_len;
+ bond_dev->needed_headroom = slave_dev->needed_headroom;
bond_dev->addr_len = slave_dev->addr_len;
memcpy(bond_dev->broadcast, slave_dev->broadcast,
}
}
-static int bond_upper_dev_walk(struct net_device *upper, void *data)
+static int bond_upper_dev_walk(struct net_device *upper,
+ struct netdev_nested_priv *priv)
{
- __be32 ip = *((__be32 *)data);
+ __be32 ip = *(__be32 *)priv->data;
return ip == bond_confirm_addr(upper, 0, ip);
}
static bool bond_has_this_ip(struct bonding *bond, __be32 ip)
{
+ struct netdev_nested_priv priv = {
+ .data = (void *)&ip,
+ };
bool ret = false;
if (ip == bond_confirm_addr(bond->dev, 0, ip))
return true;
rcu_read_lock();
- if (netdev_walk_all_upper_dev_rcu(bond->dev, bond_upper_dev_walk, &ip))
+ if (netdev_walk_all_upper_dev_rcu(bond->dev, bond_upper_dev_walk, &priv))
ret = true;
rcu_read_unlock();
int ksz_switch_register(struct ksz_device *dev,
const struct ksz_dev_ops *ops)
{
+ struct device_node *port, *ports;
phy_interface_t interface;
- struct device_node *port;
unsigned int port_num;
int ret;
ret = of_get_phy_mode(dev->dev->of_node, &interface);
if (ret == 0)
dev->compat_interface = interface;
- for_each_available_child_of_node(dev->dev->of_node, port) {
- if (of_property_read_u32(port, "reg", &port_num))
- continue;
- if (port_num >= dev->port_cnt)
- return -EINVAL;
- of_get_phy_mode(port, &dev->ports[port_num].interface);
- }
+ ports = of_get_child_by_name(dev->dev->of_node, "ports");
+ if (ports)
+ for_each_available_child_of_node(ports, port) {
+ if (of_property_read_u32(port, "reg",
+ &port_num))
+ continue;
+ if (port_num >= dev->port_cnt)
+ return -EINVAL;
+ of_get_phy_mode(port,
+ &dev->ports[port_num].interface);
+ }
dev->synclko_125 = of_property_read_bool(dev->dev->of_node,
"microchip,synclko-125");
}
[VCAP_IS2_ACT_POLICE_ENA] = { 9, 1},
[VCAP_IS2_ACT_POLICE_IDX] = { 10, 9},
[VCAP_IS2_ACT_POLICE_VCAP_ONLY] = { 19, 1},
- [VCAP_IS2_ACT_PORT_MASK] = { 20, 11},
- [VCAP_IS2_ACT_REW_OP] = { 31, 9},
- [VCAP_IS2_ACT_SMAC_REPLACE_ENA] = { 40, 1},
- [VCAP_IS2_ACT_RSV] = { 41, 2},
- [VCAP_IS2_ACT_ACL_ID] = { 43, 6},
- [VCAP_IS2_ACT_HIT_CNT] = { 49, 32},
+ [VCAP_IS2_ACT_PORT_MASK] = { 20, 6},
+ [VCAP_IS2_ACT_REW_OP] = { 26, 9},
+ [VCAP_IS2_ACT_SMAC_REPLACE_ENA] = { 35, 1},
+ [VCAP_IS2_ACT_RSV] = { 36, 2},
+ [VCAP_IS2_ACT_ACL_ID] = { 38, 6},
+ [VCAP_IS2_ACT_HIT_CNT] = { 44, 32},
};
static const struct vcap_props vsc9959_vcap_props[] = {
*/
static u16 vsc9959_wm_enc(u16 value)
{
+ WARN_ON(value >= 16 * BIT(8));
+
if (value >= BIT(8))
return BIT(8) | (value / 16);
static void vsc9959_sched_speed_set(struct ocelot *ocelot, int port,
u32 speed)
{
+ u8 tas_speed;
+
+ switch (speed) {
+ case SPEED_10:
+ tas_speed = OCELOT_SPEED_10;
+ break;
+ case SPEED_100:
+ tas_speed = OCELOT_SPEED_100;
+ break;
+ case SPEED_1000:
+ tas_speed = OCELOT_SPEED_1000;
+ break;
+ case SPEED_2500:
+ tas_speed = OCELOT_SPEED_2500;
+ break;
+ default:
+ tas_speed = OCELOT_SPEED_1000;
+ break;
+ }
+
ocelot_rmw_rix(ocelot,
- QSYS_TAG_CONFIG_LINK_SPEED(speed),
+ QSYS_TAG_CONFIG_LINK_SPEED(tas_speed),
QSYS_TAG_CONFIG_LINK_SPEED_M,
QSYS_TAG_CONFIG, port);
}
.action_type_width = 1,
.action_table = {
[IS2_ACTION_TYPE_NORMAL] = {
- .width = 44,
+ .width = 50, /* HIT_CNT not included */
.count = 2
},
[IS2_ACTION_TYPE_SMAC_SIP] = {
*/
static u16 vsc9953_wm_enc(u16 value)
{
+ WARN_ON(value >= 16 * BIT(9));
+
if (value >= BIT(9))
return BIT(9) | (value / 16);
u32 lastWrite;
};
-/* The Typoon transmit ring -- same as a basic ring, plus:
+/* The Typhoon transmit ring -- same as a basic ring, plus:
* lastRead: where we're at in regard to cleaning up the ring
* writeRegister: register to use for writing (different for Hi & Lo rings)
*/
obj-$(CONFIG_AQTION) += atlantic.o
-ccflags-y += -I$(src)
+ccflags-y += -I$(srctree)/$(src)
atlantic-objs := aq_main.o \
aq_nic.o \
atlantic-$(CONFIG_MACSEC) += aq_macsec.o
-atlantic-$(CONFIG_PTP_1588_CLOCK) += aq_ptp.o
\ No newline at end of file
+atlantic-$(CONFIG_PTP_1588_CLOCK) += aq_ptp.o
#define CCM_REG_GR_ARB_TYPE 0xd015c
/* [RW 2] Load (FIC0) channel group priority. The lowest priority is 0; the
highest priority is 3. It is supposed; that the Store channel priority is
- the compliment to 4 of the rest priorities - Aggregation channel; Load
+ the complement to 4 of the rest priorities - Aggregation channel; Load
(FIC0) channel and Load (FIC1). */
#define CCM_REG_GR_LD0_PR 0xd0164
/* [RW 2] Load (FIC1) channel group priority. The lowest priority is 0; the
highest priority is 3. It is supposed; that the Store channel priority is
- the compliment to 4 of the rest priorities - Aggregation channel; Load
+ the complement to 4 of the rest priorities - Aggregation channel; Load
(FIC0) channel and Load (FIC1). */
#define CCM_REG_GR_LD1_PR 0xd0168
/* [RW 2] General flags index. */
#define TCM_REG_GR_ARB_TYPE 0x50114
/* [RW 2] Load (FIC0) channel group priority. The lowest priority is 0; the
highest priority is 3. It is supposed that the Store channel is the
- compliment of the other 3 groups. */
+ complement of the other 3 groups. */
#define TCM_REG_GR_LD0_PR 0x5011c
/* [RW 2] Load (FIC1) channel group priority. The lowest priority is 0; the
highest priority is 3. It is supposed that the Store channel is the
- compliment of the other 3 groups. */
+ complement of the other 3 groups. */
#define TCM_REG_GR_LD1_PR 0x50120
/* [RW 4] The number of double REG-pairs; loaded from the STORM context and
sent to STORM; for a specific connection type. The double REG-pairs are
#define UCM_REG_GR_ARB_TYPE 0xe0144
/* [RW 2] Load (FIC0) channel group priority. The lowest priority is 0; the
highest priority is 3. It is supposed that the Store channel group is
- compliment to the others. */
+ complement to the others. */
#define UCM_REG_GR_LD0_PR 0xe014c
/* [RW 2] Load (FIC1) channel group priority. The lowest priority is 0; the
highest priority is 3. It is supposed that the Store channel group is
- compliment to the others. */
+ complement to the others. */
#define UCM_REG_GR_LD1_PR 0xe0150
/* [RW 2] The queue index for invalidate counter flag decision. */
#define UCM_REG_INV_CFLG_Q 0xe00e4
#define XCM_REG_GR_ARB_TYPE 0x2020c
/* [RW 2] Load (FIC0) channel group priority. The lowest priority is 0; the
highest priority is 3. It is supposed that the Channel group is the
- compliment of the other 3 groups. */
+ complement of the other 3 groups. */
#define XCM_REG_GR_LD0_PR 0x20214
/* [RW 2] Load (FIC1) channel group priority. The lowest priority is 0; the
highest priority is 3. It is supposed that the Channel group is the
- compliment of the other 3 groups. */
+ complement of the other 3 groups. */
#define XCM_REG_GR_LD1_PR 0x20218
/* [RW 1] Input nig0 Interface enable. If 0 - the valid input is
disregarded; acknowledge output is deasserted; all other signals are
*/
if (netdev->phydev) {
netif_carrier_off(netdev);
- phy_start_aneg(netdev->phydev);
+ phy_start(netdev->phydev);
}
netif_wake_queue(netdev);
napi_disable(&p->napi);
netif_stop_queue(netdev);
- if (netdev->phydev)
+ if (netdev->phydev) {
+ phy_stop(netdev->phydev);
phy_disconnect(netdev->phydev);
+ }
netif_carrier_off(netdev);
#define DPNI_VER_MAJOR 7
#define DPNI_VER_MINOR 0
#define DPNI_CMD_BASE_VERSION 1
+#define DPNI_CMD_2ND_VERSION 2
#define DPNI_CMD_ID_OFFSET 4
#define DPNI_CMD(id) (((id) << DPNI_CMD_ID_OFFSET) | DPNI_CMD_BASE_VERSION)
+#define DPNI_CMD_V2(id) (((id) << DPNI_CMD_ID_OFFSET) | DPNI_CMD_2ND_VERSION)
#define DPNI_CMDID_OPEN DPNI_CMD(0x801)
#define DPNI_CMDID_CLOSE DPNI_CMD(0x800)
#define DPNI_CMDID_SET_MAX_FRAME_LENGTH DPNI_CMD(0x216)
#define DPNI_CMDID_GET_MAX_FRAME_LENGTH DPNI_CMD(0x217)
#define DPNI_CMDID_SET_LINK_CFG DPNI_CMD(0x21A)
-#define DPNI_CMDID_SET_TX_SHAPING DPNI_CMD(0x21B)
+#define DPNI_CMDID_SET_TX_SHAPING DPNI_CMD_V2(0x21B)
#define DPNI_CMDID_SET_MCAST_PROMISC DPNI_CMD(0x220)
#define DPNI_CMDID_GET_MCAST_PROMISC DPNI_CMD(0x221)
/* Return all Fs if nothing was there */
if ((xgmac_read32(®s->mdio_stat, endian) & MDIO_STAT_RD_ER) &&
!priv->has_a011043) {
- dev_err(&bus->dev,
+ dev_dbg(&bus->dev,
"Error while reading PHY%d reg at %d.%hhu\n",
phy_id, dev_addr, regnum);
return 0xffff;
config HINIC
tristate "Huawei Intelligent PCIE Network Interface Card"
depends on (PCI_MSI && (X86 || ARM64))
+ select NET_DEVLINK
help
This driver supports HiNIC PCIE Ethernet cards.
To compile this driver as part of the kernel, choose Y here.
sizeof(port_mac_cmd),
&port_mac_cmd, &out_size);
if (err || out_size != sizeof(port_mac_cmd) ||
- (port_mac_cmd.status &&
- port_mac_cmd.status != HINIC_PF_SET_VF_ALREADY &&
- port_mac_cmd.status != HINIC_MGMT_STATUS_EXIST)) {
+ (port_mac_cmd.status &&
+ (port_mac_cmd.status != HINIC_PF_SET_VF_ALREADY || !HINIC_IS_VF(hwif)) &&
+ port_mac_cmd.status != HINIC_MGMT_STATUS_EXIST)) {
dev_err(&pdev->dev, "Failed to change MAC, err: %d, status: 0x%x, out size: 0x%x\n",
err, port_mac_cmd.status, out_size);
return -EFAULT;
err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_MAC, &mac_info,
sizeof(mac_info), &mac_info, &out_size);
if (err || out_size != sizeof(mac_info) ||
- (mac_info.status && mac_info.status != HINIC_PF_SET_VF_ALREADY &&
- mac_info.status != HINIC_MGMT_STATUS_EXIST)) {
+ (mac_info.status && mac_info.status != HINIC_MGMT_STATUS_EXIST)) {
dev_err(&hwdev->func_to_io.hwif->pdev->dev, "Failed to set MAC, err: %d, status: 0x%x, out size: 0x%x\n",
err, mac_info.status, out_size);
return -EIO;
static int hinic_check_mac_info(u8 status, u16 vlan_id)
{
- if ((status && status != HINIC_MGMT_STATUS_EXIST &&
- status != HINIC_PF_SET_VF_ALREADY) ||
+ if ((status && status != HINIC_MGMT_STATUS_EXIST) ||
(vlan_id & CHECK_IPSU_15BIT &&
status == HINIC_MGMT_STATUS_EXIST))
return -EINVAL;
return -EINVAL;
}
- if (mac_info.status == HINIC_PF_SET_VF_ALREADY) {
- dev_warn(&hwdev->hwif->pdev->dev,
- "PF has already set VF MAC. Ignore update operation\n");
- return HINIC_PF_SET_VF_ALREADY;
- }
-
if (mac_info.status == HINIC_MGMT_STATUS_EXIST)
dev_warn(&hwdev->hwif->pdev->dev, "MAC is repeated. Ignore update operation\n");
static int __maybe_unused iavf_resume(struct device *dev_d)
{
struct pci_dev *pdev = to_pci_dev(dev_d);
- struct iavf_adapter *adapter = pci_get_drvdata(pdev);
- struct net_device *netdev = adapter->netdev;
+ struct net_device *netdev = pci_get_drvdata(pdev);
+ struct iavf_adapter *adapter = netdev_priv(netdev);
u32 err;
pci_set_master(pdev);
{
struct ice_hw_func_caps *func_caps = &hw->func_caps;
struct ice_hw_dev_caps *dev_caps = &hw->dev_caps;
- u32 valid_func, rxq_first_id, txq_first_id;
- u32 msix_vector_first_id, max_mtu;
+ struct ice_hw_common_caps cached_caps;
u32 num_funcs;
/* cache some func_caps values that should be restored after memset */
- valid_func = func_caps->common_cap.valid_functions;
- txq_first_id = func_caps->common_cap.txq_first_id;
- rxq_first_id = func_caps->common_cap.rxq_first_id;
- msix_vector_first_id = func_caps->common_cap.msix_vector_first_id;
- max_mtu = func_caps->common_cap.max_mtu;
+ cached_caps = func_caps->common_cap;
/* unset func capabilities */
memset(func_caps, 0, sizeof(*func_caps));
+#define ICE_RESTORE_FUNC_CAP(name) \
+ func_caps->common_cap.name = cached_caps.name
+
/* restore cached values */
- func_caps->common_cap.valid_functions = valid_func;
- func_caps->common_cap.txq_first_id = txq_first_id;
- func_caps->common_cap.rxq_first_id = rxq_first_id;
- func_caps->common_cap.msix_vector_first_id = msix_vector_first_id;
- func_caps->common_cap.max_mtu = max_mtu;
+ ICE_RESTORE_FUNC_CAP(valid_functions);
+ ICE_RESTORE_FUNC_CAP(txq_first_id);
+ ICE_RESTORE_FUNC_CAP(rxq_first_id);
+ ICE_RESTORE_FUNC_CAP(msix_vector_first_id);
+ ICE_RESTORE_FUNC_CAP(max_mtu);
+ ICE_RESTORE_FUNC_CAP(nvm_unified_update);
+ ICE_RESTORE_FUNC_CAP(nvm_update_pending_nvm);
+ ICE_RESTORE_FUNC_CAP(nvm_update_pending_orom);
+ ICE_RESTORE_FUNC_CAP(nvm_update_pending_netlist);
/* one Tx and one Rx queue in safe mode */
func_caps->common_cap.num_rxq = 1;
func_caps->guar_num_vsi = 1;
/* cache some dev_caps values that should be restored after memset */
- valid_func = dev_caps->common_cap.valid_functions;
- txq_first_id = dev_caps->common_cap.txq_first_id;
- rxq_first_id = dev_caps->common_cap.rxq_first_id;
- msix_vector_first_id = dev_caps->common_cap.msix_vector_first_id;
- max_mtu = dev_caps->common_cap.max_mtu;
+ cached_caps = dev_caps->common_cap;
num_funcs = dev_caps->num_funcs;
/* unset dev capabilities */
memset(dev_caps, 0, sizeof(*dev_caps));
+#define ICE_RESTORE_DEV_CAP(name) \
+ dev_caps->common_cap.name = cached_caps.name
+
/* restore cached values */
- dev_caps->common_cap.valid_functions = valid_func;
- dev_caps->common_cap.txq_first_id = txq_first_id;
- dev_caps->common_cap.rxq_first_id = rxq_first_id;
- dev_caps->common_cap.msix_vector_first_id = msix_vector_first_id;
- dev_caps->common_cap.max_mtu = max_mtu;
+ ICE_RESTORE_DEV_CAP(valid_functions);
+ ICE_RESTORE_DEV_CAP(txq_first_id);
+ ICE_RESTORE_DEV_CAP(rxq_first_id);
+ ICE_RESTORE_DEV_CAP(msix_vector_first_id);
+ ICE_RESTORE_DEV_CAP(max_mtu);
+ ICE_RESTORE_DEV_CAP(nvm_unified_update);
+ ICE_RESTORE_DEV_CAP(nvm_update_pending_nvm);
+ ICE_RESTORE_DEV_CAP(nvm_update_pending_orom);
+ ICE_RESTORE_DEV_CAP(nvm_update_pending_netlist);
dev_caps->num_funcs = num_funcs;
/* one Tx and one Rx queue per function in safe mode */
return -EIO;
}
- err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_write, HZ, &event);
+ /* In most cases, firmware reports a write completion within a few
+ * milliseconds. However, it has been observed that a completion might
+ * take more than a second to complete in some cases. The timeout here
+ * is conservative and is intended to prevent failure to update when
+ * firmware is slow to respond.
+ */
+ err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_write, 15 * HZ, &event);
if (err) {
dev_err(dev, "Timed out waiting for firmware write completion for module 0x%02x, err %d\n",
module, err);
return -EIO;
}
- err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_write_activate, HZ,
+ err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_write_activate, 30 * HZ,
&event);
if (err) {
dev_err(dev, "Timed out waiting for firmware to switch active flash banks, err %d\n",
* ice_vsi_delete - delete a VSI from the switch
* @vsi: pointer to VSI being removed
*/
-void ice_vsi_delete(struct ice_vsi *vsi)
+static void ice_vsi_delete(struct ice_vsi *vsi)
{
struct ice_pf *pf = vsi->back;
struct ice_vsi_ctx *ctxt;
*
* Returns 0 on success, negative on failure
*/
-int ice_vsi_clear(struct ice_vsi *vsi)
+static int ice_vsi_clear(struct ice_vsi *vsi)
{
struct ice_pf *pf = NULL;
struct device *dev;
* ice_vsi_put_qs - Release queues from VSI to PF
* @vsi: the VSI that is going to release queues
*/
-void ice_vsi_put_qs(struct ice_vsi *vsi)
+static void ice_vsi_put_qs(struct ice_vsi *vsi)
{
struct ice_pf *pf = vsi->back;
int i;
{
int i;
+ /* Avoid stale references by clearing map from vector to ring */
+ if (vsi->q_vectors) {
+ ice_for_each_q_vector(vsi, i) {
+ struct ice_q_vector *q_vector = vsi->q_vectors[i];
+
+ if (q_vector) {
+ q_vector->tx.ring = NULL;
+ q_vector->rx.ring = NULL;
+ }
+ }
+ }
+
if (vsi->tx_rings) {
for (i = 0; i < vsi->alloc_txq; i++) {
if (vsi->tx_rings[i]) {
if (status) {
dev_err(dev, "VSI %d failed lan queue config, error %s\n",
vsi->vsi_num, ice_stat_str(status));
- goto unroll_vector_base;
+ goto unroll_clear_rings;
}
/* Add switch rule to drop all Tx Flow Control Frames, of look up
void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create);
-void ice_vsi_delete(struct ice_vsi *vsi);
-
-int ice_vsi_clear(struct ice_vsi *vsi);
-
#ifdef CONFIG_DCB
int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc);
#endif /* CONFIG_DCB */
void
ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio);
-void ice_vsi_put_qs(struct ice_vsi *vsi);
-
void ice_vsi_dis_irq(struct ice_vsi *vsi);
void ice_vsi_free_irq(struct ice_vsi *vsi);
return -EBUSY;
vsi = ice_pf_vsi_setup(pf, pf->hw.port_info);
- if (!vsi) {
- status = -ENOMEM;
- goto unroll_vsi_setup;
- }
+ if (!vsi)
+ return -ENOMEM;
status = ice_cfg_netdev(vsi);
if (status) {
}
unroll_vsi_setup:
- if (vsi) {
- ice_vsi_free_q_vectors(vsi);
- ice_vsi_delete(vsi);
- ice_vsi_put_qs(vsi);
- ice_vsi_clear(vsi);
- }
+ ice_vsi_release(vsi);
return status;
}
}
ice_clear_interrupt_scheme(pf);
+ pci_save_state(pdev);
pci_wake_from_d3(pdev, pf->wol_ena);
pci_set_power_state(pdev, PCI_D3hot);
return 0;
return err;
}
-static int ixgbe_macvlan_up(struct net_device *vdev, void *data)
+static int ixgbe_macvlan_up(struct net_device *vdev,
+ struct netdev_nested_priv *priv)
{
- struct ixgbe_adapter *adapter = data;
+ struct ixgbe_adapter *adapter = (struct ixgbe_adapter *)priv->data;
struct ixgbe_fwd_adapter *accel;
if (!netif_is_macvlan(vdev))
static void ixgbe_configure_dfwd(struct ixgbe_adapter *adapter)
{
+ struct netdev_nested_priv priv = {
+ .data = (void *)adapter,
+ };
+
netdev_walk_all_upper_dev_rcu(adapter->netdev,
- ixgbe_macvlan_up, adapter);
+ ixgbe_macvlan_up, &priv);
}
static void ixgbe_configure(struct ixgbe_adapter *adapter)
}
#endif /* CONFIG_IXGBE_DCB */
-static int ixgbe_reassign_macvlan_pool(struct net_device *vdev, void *data)
+static int ixgbe_reassign_macvlan_pool(struct net_device *vdev,
+ struct netdev_nested_priv *priv)
{
- struct ixgbe_adapter *adapter = data;
+ struct ixgbe_adapter *adapter = (struct ixgbe_adapter *)priv->data;
struct ixgbe_fwd_adapter *accel;
int pool;
static void ixgbe_defrag_macvlan_pools(struct net_device *dev)
{
struct ixgbe_adapter *adapter = netdev_priv(dev);
+ struct netdev_nested_priv priv = {
+ .data = (void *)adapter,
+ };
/* flush any stale bits out of the fwd bitmask */
bitmap_clear(adapter->fwd_bitmask, 1, 63);
/* walk through upper devices reassigning pools */
netdev_walk_all_upper_dev_rcu(dev, ixgbe_reassign_macvlan_pool,
- adapter);
+ &priv);
}
/**
u8 queue;
};
-static int get_macvlan_queue(struct net_device *upper, void *_data)
+static int get_macvlan_queue(struct net_device *upper,
+ struct netdev_nested_priv *priv)
{
if (netif_is_macvlan(upper)) {
struct ixgbe_fwd_adapter *vadapter = macvlan_accel_priv(upper);
- struct upper_walk_data *data = _data;
- struct ixgbe_adapter *adapter = data->adapter;
- int ifindex = data->ifindex;
+ struct ixgbe_adapter *adapter;
+ struct upper_walk_data *data;
+ int ifindex;
+ data = (struct upper_walk_data *)priv->data;
+ ifindex = data->ifindex;
+ adapter = data->adapter;
if (vadapter && upper->ifindex == ifindex) {
data->queue = adapter->rx_ring[vadapter->rx_base_queue]->reg_idx;
data->action = data->queue;
{
struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ];
unsigned int num_vfs = adapter->num_vfs, vf;
+ struct netdev_nested_priv priv;
struct upper_walk_data data;
struct net_device *upper;
data.ifindex = ifindex;
data.action = 0;
data.queue = 0;
+ priv.data = (void *)&data;
if (netdev_walk_all_upper_dev_rcu(adapter->netdev,
- get_macvlan_queue, &data)) {
+ get_macvlan_queue, &priv)) {
*action = data.action;
*queue = data.queue;
int pkts = 0;
int bytes = 0;
+ netif_tx_lock(net_dev);
while (pkts < budget) {
struct ltq_dma_desc *desc = &ch->dma.desc_base[ch->tx_free];
net_dev->stats.tx_bytes += bytes;
netdev_completed_queue(ch->priv->net_dev, pkts, bytes);
+ netif_tx_unlock(net_dev);
if (netif_queue_stopped(net_dev))
netif_wake_queue(net_dev);
txq->last_desc = txq->size - 1;
txq->buf = kmalloc_array(txq->size, sizeof(*txq->buf), GFP_KERNEL);
- if (!txq->buf) {
- dma_free_coherent(pp->dev->dev.parent,
- txq->size * MVNETA_DESC_ALIGNED_SIZE,
- txq->descs, txq->descs_phys);
+ if (!txq->buf)
return -ENOMEM;
- }
/* Allocate DMA buffers for TSO MAC/IP/TCP headers */
txq->tso_hdrs = dma_alloc_coherent(pp->dev->dev.parent,
txq->size * TSO_HEADER_SIZE,
&txq->tso_hdrs_phys, GFP_KERNEL);
- if (!txq->tso_hdrs) {
- kfree(txq->buf);
- dma_free_coherent(pp->dev->dev.parent,
- txq->size * MVNETA_DESC_ALIGNED_SIZE,
- txq->descs, txq->descs_phys);
+ if (!txq->tso_hdrs)
return -ENOMEM;
- }
/* Setup XPS mapping */
if (txq_number > 1)
static const u16 msgs_offset = ALIGN(sizeof(struct mbox_hdr), MBOX_MSG_ALIGN);
-void otx2_mbox_reset(struct otx2_mbox *mbox, int devid)
+void __otx2_mbox_reset(struct otx2_mbox *mbox, int devid)
{
void *hw_mbase = mbox->hwbase + (devid * MBOX_SIZE);
struct otx2_mbox_dev *mdev = &mbox->dev[devid];
tx_hdr = hw_mbase + mbox->tx_start;
rx_hdr = hw_mbase + mbox->rx_start;
- spin_lock(&mdev->mbox_lock);
mdev->msg_size = 0;
mdev->rsp_size = 0;
tx_hdr->num_msgs = 0;
tx_hdr->msg_size = 0;
rx_hdr->num_msgs = 0;
rx_hdr->msg_size = 0;
+}
+EXPORT_SYMBOL(__otx2_mbox_reset);
+
+void otx2_mbox_reset(struct otx2_mbox *mbox, int devid)
+{
+ struct otx2_mbox_dev *mdev = &mbox->dev[devid];
+
+ spin_lock(&mdev->mbox_lock);
+ __otx2_mbox_reset(mbox, devid);
spin_unlock(&mdev->mbox_lock);
}
EXPORT_SYMBOL(otx2_mbox_reset);
};
void otx2_mbox_reset(struct otx2_mbox *mbox, int devid);
+void __otx2_mbox_reset(struct otx2_mbox *mbox, int devid);
void otx2_mbox_destroy(struct otx2_mbox *mbox);
int otx2_mbox_init(struct otx2_mbox *mbox, void __force *hwbase,
struct pci_dev *pdev, void __force *reg_base,
int rvu_get_nixlf_count(struct rvu *rvu);
void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int npalf);
int nix_get_nixlf(struct rvu *rvu, u16 pcifunc, int *nixlf, int *nix_blkaddr);
+int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add);
/* NPC APIs */
int rvu_npc_init(struct rvu *rvu);
void rvu_npc_enable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf);
void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
int nixlf, u64 chan);
-void rvu_npc_disable_bcast_entry(struct rvu *rvu, u16 pcifunc);
+void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, bool enable);
int rvu_npc_update_rxvlan(struct rvu *rvu, u16 pcifunc, int nixlf);
void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf);
void rvu_npc_disable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf);
#include "npc.h"
#include "cgx.h"
-static int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add);
static int rvu_nix_get_bpid(struct rvu *rvu, struct nix_bp_cfg_req *req,
int type, int chan_id);
return 0;
}
-static int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add)
+int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add)
{
int err = 0, idx, next_idx, last_idx;
struct nix_mce_list *mce_list;
/* Disable MCAM entry in NPC */
if (!mce_list->count) {
- rvu_npc_disable_bcast_entry(rvu, pcifunc);
+ rvu_npc_enable_bcast_entry(rvu, pcifunc, false);
goto end;
}
NIX_INTF_RX, &entry, true);
}
-void rvu_npc_disable_bcast_entry(struct rvu *rvu, u16 pcifunc)
+void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, bool enable)
{
struct npc_mcam *mcam = &rvu->hw->mcam;
int blkaddr, index;
pcifunc = pcifunc & ~RVU_PFVF_FUNC_MASK;
index = npc_get_nixlf_mcam_index(mcam, pcifunc, 0, NIXLF_BCAST_ENTRY);
- npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false);
+ npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable);
}
void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf,
nixlf, NIXLF_UCAST_ENTRY);
npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable);
- /* For PF, ena/dis promisc and bcast MCAM match entries */
- if (pcifunc & RVU_PFVF_FUNC_MASK)
+ /* For PF, ena/dis promisc and bcast MCAM match entries.
+ * For VFs add/delete from bcast list when RX multicast
+ * feature is present.
+ */
+ if (pcifunc & RVU_PFVF_FUNC_MASK && !rvu->hw->cap.nix_rx_multicast)
return;
/* For bcast, enable/disable only if it's action is not
* packet replication, incase if action is replication
- * then this PF's nixlf is removed from bcast replication
+ * then this PF/VF's nixlf is removed from bcast replication
* list.
*/
- index = npc_get_nixlf_mcam_index(mcam, pcifunc,
+ index = npc_get_nixlf_mcam_index(mcam, pcifunc & ~RVU_PFVF_FUNC_MASK,
nixlf, NIXLF_BCAST_ENTRY);
bank = npc_get_bank(mcam, index);
*(u64 *)&action = rvu_read64(rvu, blkaddr,
NPC_AF_MCAMEX_BANKX_ACTION(index & (mcam->banksize - 1), bank));
- if (action.op != NIX_RX_ACTIONOP_MCAST)
+
+ /* VFs will not have BCAST entry */
+ if (action.op != NIX_RX_ACTIONOP_MCAST &&
+ !(pcifunc & RVU_PFVF_FUNC_MASK)) {
npc_enable_mcam_entry(rvu, mcam,
blkaddr, index, enable);
+ } else {
+ nix_update_bcast_mce_list(rvu, pcifunc, enable);
+ /* Enable PF's BCAST entry for packet replication */
+ rvu_npc_enable_bcast_entry(rvu, pcifunc, enable);
+ }
+
if (enable)
rvu_npc_enable_promisc_entry(rvu, pcifunc, nixlf);
else
dst_mbox = &pf->mbox;
dst_size = dst_mbox->mbox.tx_size -
ALIGN(sizeof(*mbox_hdr), MBOX_MSG_ALIGN);
- /* Check if msgs fit into destination area */
- if (mbox_hdr->msg_size > dst_size)
+ /* Check if msgs fit into destination area and has valid size */
+ if (mbox_hdr->msg_size > dst_size || !mbox_hdr->msg_size)
return -EINVAL;
dst_mdev = &dst_mbox->mbox.dev[0];
end:
offset = mbox->rx_start + msg->next_msgoff;
+ if (mdev->msgs_acked == (vf_mbox->up_num_msgs - 1))
+ __otx2_mbox_reset(mbox, 0);
mdev->msgs_acked++;
}
-
- otx2_mbox_reset(mbox, vf_idx);
}
static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq)
msg = (struct mbox_msghdr *)(mdev->mbase + offset);
otx2_process_pfaf_mbox_msg(pf, msg);
offset = mbox->rx_start + msg->next_msgoff;
+ if (mdev->msgs_acked == (af_mbox->num_msgs - 1))
+ __otx2_mbox_reset(mbox, 0);
mdev->msgs_acked++;
}
- otx2_mbox_reset(mbox, 0);
}
static void otx2_handle_link_event(struct otx2_nic *pf)
err = otx2_rxtx_enable(pf, true);
if (err)
- goto err_free_cints;
+ goto err_tx_stop_queues;
return 0;
+err_tx_stop_queues:
+ netif_tx_stop_all_queues(netdev);
+ netif_carrier_off(netdev);
err_free_cints:
otx2_free_cints(pf, qidx);
vec = pci_irq_vector(pf->pdev,
sqe_hdr->ol3type = NIX_SENDL3TYPE_IP4_CKSUM;
} else if (skb->protocol == htons(ETH_P_IPV6)) {
proto = ipv6_hdr(skb)->nexthdr;
+ sqe_hdr->ol3type = NIX_SENDL3TYPE_IP6;
}
if (proto == IPPROTO_TCP)
msg = (struct mbox_msghdr *)(mdev->mbase + offset);
otx2vf_process_vfaf_mbox_msg(af_mbox->pfvf, msg);
offset = mbox->rx_start + msg->next_msgoff;
+ if (mdev->msgs_acked == (af_mbox->num_msgs - 1))
+ __otx2_mbox_reset(mbox, 0);
mdev->msgs_acked++;
}
-
- otx2_mbox_reset(mbox, 0);
}
static int otx2vf_process_mbox_msg_up(struct otx2_nic *vf,
MLX5_CMD_DELIVERY_STAT_CMD_DESCR_ERR = 0x10,
};
-static struct mlx5_cmd_work_ent *alloc_cmd(struct mlx5_cmd *cmd,
- struct mlx5_cmd_msg *in,
- struct mlx5_cmd_msg *out,
- void *uout, int uout_size,
- mlx5_cmd_cbk_t cbk,
- void *context, int page_queue)
+static struct mlx5_cmd_work_ent *
+cmd_alloc_ent(struct mlx5_cmd *cmd, struct mlx5_cmd_msg *in,
+ struct mlx5_cmd_msg *out, void *uout, int uout_size,
+ mlx5_cmd_cbk_t cbk, void *context, int page_queue)
{
gfp_t alloc_flags = cbk ? GFP_ATOMIC : GFP_KERNEL;
struct mlx5_cmd_work_ent *ent;
if (!ent)
return ERR_PTR(-ENOMEM);
+ ent->idx = -EINVAL;
ent->in = in;
ent->out = out;
ent->uout = uout;
ent->context = context;
ent->cmd = cmd;
ent->page_queue = page_queue;
+ refcount_set(&ent->refcnt, 1);
return ent;
}
+static void cmd_free_ent(struct mlx5_cmd_work_ent *ent)
+{
+ kfree(ent);
+}
+
static u8 alloc_token(struct mlx5_cmd *cmd)
{
u8 token;
return token;
}
-static int alloc_ent(struct mlx5_cmd *cmd)
+static int cmd_alloc_index(struct mlx5_cmd *cmd)
{
unsigned long flags;
int ret;
return ret < cmd->max_reg_cmds ? ret : -ENOMEM;
}
-static void free_ent(struct mlx5_cmd *cmd, int idx)
+static void cmd_free_index(struct mlx5_cmd *cmd, int idx)
{
unsigned long flags;
spin_unlock_irqrestore(&cmd->alloc_lock, flags);
}
+static void cmd_ent_get(struct mlx5_cmd_work_ent *ent)
+{
+ refcount_inc(&ent->refcnt);
+}
+
+static void cmd_ent_put(struct mlx5_cmd_work_ent *ent)
+{
+ if (!refcount_dec_and_test(&ent->refcnt))
+ return;
+
+ if (ent->idx >= 0)
+ cmd_free_index(ent->cmd, ent->idx);
+
+ cmd_free_ent(ent);
+}
+
static struct mlx5_cmd_layout *get_inst(struct mlx5_cmd *cmd, int idx)
{
return cmd->cmd_buf + (idx << cmd->log_stride);
ent->ret = -ETIMEDOUT;
}
-static void free_cmd(struct mlx5_cmd_work_ent *ent)
-{
- kfree(ent);
-}
-
static int verify_signature(struct mlx5_cmd_work_ent *ent)
{
struct mlx5_cmd_mailbox *next = ent->out->next;
struct mlx5_core_dev *dev = container_of(ent->cmd, struct mlx5_core_dev,
cmd);
+ mlx5_cmd_eq_recover(dev);
+
+ /* Maybe got handled by eq recover ? */
+ if (!test_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state)) {
+ mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) Async, recovered after timeout\n", ent->idx,
+ mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in));
+ goto out; /* phew, already handled */
+ }
+
ent->ret = -ETIMEDOUT;
- mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n",
- mlx5_command_str(msg_to_opcode(ent->in)),
- msg_to_opcode(ent->in));
+ mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) Async, timeout. Will cause a leak of a command resource\n",
+ ent->idx, mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in));
mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
+
+out:
+ cmd_ent_put(ent); /* for the cmd_ent_get() took on schedule delayed work */
}
static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg);
return cmd->allowed_opcode == opcode;
}
+static int cmd_alloc_index_retry(struct mlx5_cmd *cmd)
+{
+ unsigned long alloc_end = jiffies + msecs_to_jiffies(1000);
+ int idx;
+
+retry:
+ idx = cmd_alloc_index(cmd);
+ if (idx < 0 && time_before(jiffies, alloc_end)) {
+ /* Index allocation can fail on heavy load of commands. This is a temporary
+ * situation as the current command already holds the semaphore, meaning that
+ * another command completion is being handled and it is expected to release
+ * the entry index soon.
+ */
+ cpu_relax();
+ goto retry;
+ }
+ return idx;
+}
+
+bool mlx5_cmd_is_down(struct mlx5_core_dev *dev)
+{
+ return pci_channel_offline(dev->pdev) ||
+ dev->cmd.state != MLX5_CMDIF_STATE_UP ||
+ dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR;
+}
+
static void cmd_work_handler(struct work_struct *work)
{
struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work);
sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem;
down(sem);
if (!ent->page_queue) {
- alloc_ret = alloc_ent(cmd);
+ alloc_ret = cmd_alloc_index_retry(cmd);
if (alloc_ret < 0) {
mlx5_core_err_rl(dev, "failed to allocate command entry\n");
if (ent->callback) {
ent->callback(-EAGAIN, ent->context);
mlx5_free_cmd_msg(dev, ent->out);
free_msg(dev, ent->in);
- free_cmd(ent);
+ cmd_ent_put(ent);
} else {
ent->ret = -EAGAIN;
complete(&ent->done);
ent->ts1 = ktime_get_ns();
cmd_mode = cmd->mode;
- if (ent->callback)
- schedule_delayed_work(&ent->cb_timeout_work, cb_timeout);
+ if (ent->callback && schedule_delayed_work(&ent->cb_timeout_work, cb_timeout))
+ cmd_ent_get(ent);
set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state);
/* Skip sending command to fw if internal error */
- if (pci_channel_offline(dev->pdev) ||
- dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR ||
- cmd->state != MLX5_CMDIF_STATE_UP ||
- !opcode_allowed(&dev->cmd, ent->op)) {
+ if (mlx5_cmd_is_down(dev) || !opcode_allowed(&dev->cmd, ent->op)) {
u8 status = 0;
u32 drv_synd;
MLX5_SET(mbox_out, ent->out, syndrome, drv_synd);
mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
- /* no doorbell, no need to keep the entry */
- free_ent(cmd, ent->idx);
- if (ent->callback)
- free_cmd(ent);
return;
}
+ cmd_ent_get(ent); /* for the _real_ FW event on completion */
/* ring doorbell after the descriptor is valid */
mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx);
wmb();
}
}
+enum {
+ MLX5_CMD_TIMEOUT_RECOVER_MSEC = 5 * 1000,
+};
+
+static void wait_func_handle_exec_timeout(struct mlx5_core_dev *dev,
+ struct mlx5_cmd_work_ent *ent)
+{
+ unsigned long timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_RECOVER_MSEC);
+
+ mlx5_cmd_eq_recover(dev);
+
+ /* Re-wait on the ent->done after executing the recovery flow. If the
+ * recovery flow (or any other recovery flow running simultaneously)
+ * has recovered an EQE, it should cause the entry to be completed by
+ * the command interface.
+ */
+ if (wait_for_completion_timeout(&ent->done, timeout)) {
+ mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) recovered after timeout\n", ent->idx,
+ mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in));
+ return;
+ }
+
+ mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) No done completion\n", ent->idx,
+ mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in));
+
+ ent->ret = -ETIMEDOUT;
+ mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
+}
+
static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
{
unsigned long timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC);
ent->ret = -ECANCELED;
goto out_err;
}
- if (cmd->mode == CMD_MODE_POLLING || ent->polling) {
+ if (cmd->mode == CMD_MODE_POLLING || ent->polling)
wait_for_completion(&ent->done);
- } else if (!wait_for_completion_timeout(&ent->done, timeout)) {
- ent->ret = -ETIMEDOUT;
- mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
- }
+ else if (!wait_for_completion_timeout(&ent->done, timeout))
+ wait_func_handle_exec_timeout(dev, ent);
out_err:
err = ent->ret;
if (callback && page_queue)
return -EINVAL;
- ent = alloc_cmd(cmd, in, out, uout, uout_size, callback, context,
- page_queue);
+ ent = cmd_alloc_ent(cmd, in, out, uout, uout_size,
+ callback, context, page_queue);
if (IS_ERR(ent))
return PTR_ERR(ent);
+ /* put for this ent is when consumed, depending on the use case
+ * 1) (!callback) blocking flow: by caller after wait_func completes
+ * 2) (callback) flow: by mlx5_cmd_comp_handler() when ent is handled
+ */
+
ent->token = token;
ent->polling = force_polling;
}
if (callback)
- goto out;
+ goto out; /* mlx5_cmd_comp_handler() will put(ent) */
err = wait_func(dev, ent);
- if (err == -ETIMEDOUT)
- goto out;
- if (err == -ECANCELED)
+ if (err == -ETIMEDOUT || err == -ECANCELED)
goto out_free;
ds = ent->ts2 - ent->ts1;
*status = ent->status;
out_free:
- free_cmd(ent);
+ cmd_ent_put(ent);
out:
return err;
}
if (!forced) {
mlx5_core_err(dev, "Command completion arrived after timeout (entry idx = %d).\n",
ent->idx);
- free_ent(cmd, ent->idx);
- free_cmd(ent);
+ cmd_ent_put(ent);
}
continue;
}
- if (ent->callback)
- cancel_delayed_work(&ent->cb_timeout_work);
+ if (ent->callback && cancel_delayed_work(&ent->cb_timeout_work))
+ cmd_ent_put(ent); /* timeout work was canceled */
+
+ if (!forced || /* Real FW completion */
+ pci_channel_offline(dev->pdev) || /* FW is inaccessible */
+ dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
+ cmd_ent_put(ent);
+
if (ent->page_queue)
sem = &cmd->pages_sem;
else
ent->ret, deliv_status_to_str(ent->status), ent->status);
}
- /* only real completion will free the entry slot */
- if (!forced)
- free_ent(cmd, ent->idx);
-
if (ent->callback) {
ds = ent->ts2 - ent->ts1;
if (ent->op < MLX5_CMD_OP_MAX) {
free_msg(dev, ent->in);
err = err ? err : ent->status;
- if (!forced)
- free_cmd(ent);
+ /* final consumer is done, release ent */
+ cmd_ent_put(ent);
callback(err, context);
} else {
+ /* release wait_func() so mlx5_cmd_invoke()
+ * can make the final ent_put()
+ */
complete(&ent->done);
}
up(sem);
void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev)
{
+ struct mlx5_cmd *cmd = &dev->cmd;
+ unsigned long bitmask;
unsigned long flags;
u64 vector;
+ int i;
/* wait for pending handlers to complete */
mlx5_eq_synchronize_cmd_irq(dev);
if (!vector)
goto no_trig;
+ bitmask = vector;
+ /* we must increment the allocated entries refcount before triggering the completions
+ * to guarantee pending commands will not get freed in the meanwhile.
+ * For that reason, it also has to be done inside the alloc_lock.
+ */
+ for_each_set_bit(i, &bitmask, (1 << cmd->log_sz))
+ cmd_ent_get(cmd->ent_arr[i]);
vector |= MLX5_TRIGGERED_CMD_COMP;
spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags);
mlx5_core_dbg(dev, "vector 0x%llx\n", vector);
mlx5_cmd_comp_handler(dev, vector, true);
+ for_each_set_bit(i, &bitmask, (1 << cmd->log_sz))
+ cmd_ent_put(cmd->ent_arr[i]);
return;
no_trig:
u8 token;
opcode = MLX5_GET(mbox_in, in, opcode);
- if (pci_channel_offline(dev->pdev) ||
- dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR ||
- dev->cmd.state != MLX5_CMDIF_STATE_UP ||
- !opcode_allowed(&dev->cmd, opcode)) {
+ if (mlx5_cmd_is_down(dev) || !opcode_allowed(&dev->cmd, opcode)) {
err = mlx5_internal_err_ret_value(dev, opcode, &drv_synd, &status);
MLX5_SET(mbox_out, out, status, status);
MLX5_SET(mbox_out, out, syndrome, drv_synd);
#define MLX5_MPWRQ_PAGES_PER_WQE BIT(MLX5_MPWRQ_WQE_PAGE_ORDER)
#define MLX5_MTT_OCTW(npages) (ALIGN(npages, 8) / 2)
-#define MLX5E_REQUIRED_WQE_MTTS (ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8))
+/* Add another page to MLX5E_REQUIRED_WQE_MTTS as a buffer between
+ * WQEs, This page will absorb write overflow by the hardware, when
+ * receiving packets larger than MTU. These oversize packets are
+ * dropped by the driver at a later stage.
+ */
+#define MLX5E_REQUIRED_WQE_MTTS (ALIGN(MLX5_MPWRQ_PAGES_PER_WQE + 1, 8))
#define MLX5E_LOG_ALIGNED_MPWQE_PPW (ilog2(MLX5E_REQUIRED_WQE_MTTS))
#define MLX5E_REQUIRED_MTTS(wqes) (wqes * MLX5E_REQUIRED_WQE_MTTS)
#define MLX5E_MAX_RQ_NUM_MTTS \
u32 rqn;
struct mlx5_core_dev *mdev;
struct mlx5_core_mkey umr_mkey;
+ struct mlx5e_dma_info wqe_overflow;
/* XDP read-mostly */
struct xdp_rxq_info xdp_rxq;
if (fec_policy >= (1 << MLX5E_FEC_LLRS_272_257_1) && !fec_50g_per_lane)
return -EOPNOTSUPP;
+ if (fec_policy && !mlx5e_fec_in_caps(dev, fec_policy))
+ return -EOPNOTSUPP;
+
MLX5_SET(pplm_reg, in, local_port, 1);
err = mlx5_core_access_reg(dev, in, sz, out, sz, MLX5_REG_PPLM, 0, 0);
if (err)
rtnl_unlock();
}
+struct neigh_update_work {
+ struct work_struct work;
+ struct neighbour *n;
+ struct mlx5e_neigh_hash_entry *nhe;
+};
+
+static void mlx5e_release_neigh_update_work(struct neigh_update_work *update_work)
+{
+ neigh_release(update_work->n);
+ mlx5e_rep_neigh_entry_release(update_work->nhe);
+ kfree(update_work);
+}
+
static void mlx5e_rep_neigh_update(struct work_struct *work)
{
- struct mlx5e_neigh_hash_entry *nhe =
- container_of(work, struct mlx5e_neigh_hash_entry, neigh_update_work);
- struct neighbour *n = nhe->n;
+ struct neigh_update_work *update_work = container_of(work, struct neigh_update_work,
+ work);
+ struct mlx5e_neigh_hash_entry *nhe = update_work->nhe;
+ struct neighbour *n = update_work->n;
struct mlx5e_encap_entry *e;
unsigned char ha[ETH_ALEN];
struct mlx5e_priv *priv;
mlx5e_rep_update_flows(priv, e, neigh_connected, ha);
mlx5e_encap_put(priv, e);
}
- mlx5e_rep_neigh_entry_release(nhe);
rtnl_unlock();
- neigh_release(n);
+ mlx5e_release_neigh_update_work(update_work);
}
-static void mlx5e_rep_queue_neigh_update_work(struct mlx5e_priv *priv,
- struct mlx5e_neigh_hash_entry *nhe,
- struct neighbour *n)
+static struct neigh_update_work *mlx5e_alloc_neigh_update_work(struct mlx5e_priv *priv,
+ struct neighbour *n)
{
- /* Take a reference to ensure the neighbour and mlx5 encap
- * entry won't be destructed until we drop the reference in
- * delayed work.
- */
- neigh_hold(n);
+ struct neigh_update_work *update_work;
+ struct mlx5e_neigh_hash_entry *nhe;
+ struct mlx5e_neigh m_neigh = {};
- /* This assignment is valid as long as the the neigh reference
- * is taken
- */
- nhe->n = n;
+ update_work = kzalloc(sizeof(*update_work), GFP_ATOMIC);
+ if (WARN_ON(!update_work))
+ return NULL;
- if (!queue_work(priv->wq, &nhe->neigh_update_work)) {
- mlx5e_rep_neigh_entry_release(nhe);
- neigh_release(n);
+ m_neigh.dev = n->dev;
+ m_neigh.family = n->ops->family;
+ memcpy(&m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
+
+ /* Obtain reference to nhe as last step in order not to release it in
+ * atomic context.
+ */
+ rcu_read_lock();
+ nhe = mlx5e_rep_neigh_entry_lookup(priv, &m_neigh);
+ rcu_read_unlock();
+ if (!nhe) {
+ kfree(update_work);
+ return NULL;
}
+
+ INIT_WORK(&update_work->work, mlx5e_rep_neigh_update);
+ neigh_hold(n);
+ update_work->n = n;
+ update_work->nhe = nhe;
+
+ return update_work;
}
static int mlx5e_rep_netevent_event(struct notifier_block *nb,
struct net_device *netdev = rpriv->netdev;
struct mlx5e_priv *priv = netdev_priv(netdev);
struct mlx5e_neigh_hash_entry *nhe = NULL;
- struct mlx5e_neigh m_neigh = {};
+ struct neigh_update_work *update_work;
struct neigh_parms *p;
struct neighbour *n;
bool found = false;
#endif
return NOTIFY_DONE;
- m_neigh.dev = n->dev;
- m_neigh.family = n->ops->family;
- memcpy(&m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
-
- rcu_read_lock();
- nhe = mlx5e_rep_neigh_entry_lookup(priv, &m_neigh);
- rcu_read_unlock();
- if (!nhe)
+ update_work = mlx5e_alloc_neigh_update_work(priv, n);
+ if (!update_work)
return NOTIFY_DONE;
- mlx5e_rep_queue_neigh_update_work(priv, nhe, n);
+ queue_work(priv->wq, &update_work->work);
break;
case NETEVENT_DELAY_PROBE_TIME_UPDATE:
(*nhe)->priv = priv;
memcpy(&(*nhe)->m_neigh, &e->m_neigh, sizeof(e->m_neigh));
- INIT_WORK(&(*nhe)->neigh_update_work, mlx5e_rep_neigh_update);
spin_lock_init(&(*nhe)->encap_list_lock);
INIT_LIST_HEAD(&(*nhe)->encap_list);
refcount_set(&(*nhe)->refcnt, 1);
case FLOW_ACT_MANGLE_HDR_TYPE_IP6:
ip6_offset = (offset - offsetof(struct ipv6hdr, saddr));
ip6_offset /= 4;
- if (ip6_offset < 8)
+ if (ip6_offset < 4)
tuple->ip.src_v6.s6_addr32[ip6_offset] = cpu_to_be32(val);
+ else if (ip6_offset < 8)
+ tuple->ip.dst_v6.s6_addr32[ip6_offset - 4] = cpu_to_be32(val);
else
return -EOPNOTSUPP;
break;
break;
}
+ if (WARN_ONCE(*rule_p, "VLAN rule already exists type %d", rule_type))
+ return 0;
+
*rule_p = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
if (IS_ERR(*rule_p)) {
for_each_set_bit(i, priv->fs.vlan.active_svlans, VLAN_N_VID)
mlx5e_add_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_MATCH_STAG_VID, i);
- if (priv->fs.vlan.cvlan_filter_disabled &&
- !(priv->netdev->flags & IFF_PROMISC))
+ if (priv->fs.vlan.cvlan_filter_disabled)
mlx5e_add_any_vid_rules(priv);
}
for_each_set_bit(i, priv->fs.vlan.active_svlans, VLAN_N_VID)
mlx5e_del_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_MATCH_STAG_VID, i);
- if (priv->fs.vlan.cvlan_filter_disabled &&
- !(priv->netdev->flags & IFF_PROMISC))
+ WARN_ON_ONCE(!(test_bit(MLX5E_STATE_DESTROYING, &priv->state)));
+
+ /* must be called after DESTROY bit is set and
+ * set_rx_mode is called and flushed
+ */
+ if (priv->fs.vlan.cvlan_filter_disabled)
mlx5e_del_any_vid_rules(priv);
}
static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev,
u64 npages, u8 page_shift,
- struct mlx5_core_mkey *umr_mkey)
+ struct mlx5_core_mkey *umr_mkey,
+ dma_addr_t filler_addr)
{
- int inlen = MLX5_ST_SZ_BYTES(create_mkey_in);
+ struct mlx5_mtt *mtt;
+ int inlen;
void *mkc;
u32 *in;
int err;
+ int i;
+
+ inlen = MLX5_ST_SZ_BYTES(create_mkey_in) + sizeof(*mtt) * npages;
in = kvzalloc(inlen, GFP_KERNEL);
if (!in)
MLX5_SET(mkc, mkc, translations_octword_size,
MLX5_MTT_OCTW(npages));
MLX5_SET(mkc, mkc, log_page_size, page_shift);
+ MLX5_SET(create_mkey_in, in, translations_octword_actual_size,
+ MLX5_MTT_OCTW(npages));
+
+ /* Initialize the mkey with all MTTs pointing to a default
+ * page (filler_addr). When the channels are activated, UMR
+ * WQEs will redirect the RX WQEs to the actual memory from
+ * the RQ's pool, while the gaps (wqe_overflow) remain mapped
+ * to the default page.
+ */
+ mtt = MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt);
+ for (i = 0 ; i < npages ; i++)
+ mtt[i].ptag = cpu_to_be64(filler_addr);
err = mlx5_core_create_mkey(mdev, umr_mkey, in, inlen);
{
u64 num_mtts = MLX5E_REQUIRED_MTTS(mlx5_wq_ll_get_size(&rq->mpwqe.wq));
- return mlx5e_create_umr_mkey(mdev, num_mtts, PAGE_SHIFT, &rq->umr_mkey);
+ return mlx5e_create_umr_mkey(mdev, num_mtts, PAGE_SHIFT, &rq->umr_mkey,
+ rq->wqe_overflow.addr);
}
static inline u64 mlx5e_get_mpwqe_offset(struct mlx5e_rq *rq, u16 wqe_ix)
mlx5e_reporter_rq_cqe_err(rq);
}
+static int mlx5e_alloc_mpwqe_rq_drop_page(struct mlx5e_rq *rq)
+{
+ rq->wqe_overflow.page = alloc_page(GFP_KERNEL);
+ if (!rq->wqe_overflow.page)
+ return -ENOMEM;
+
+ rq->wqe_overflow.addr = dma_map_page(rq->pdev, rq->wqe_overflow.page, 0,
+ PAGE_SIZE, rq->buff.map_dir);
+ if (dma_mapping_error(rq->pdev, rq->wqe_overflow.addr)) {
+ __free_page(rq->wqe_overflow.page);
+ return -ENOMEM;
+ }
+ return 0;
+}
+
+static void mlx5e_free_mpwqe_rq_drop_page(struct mlx5e_rq *rq)
+{
+ dma_unmap_page(rq->pdev, rq->wqe_overflow.addr, PAGE_SIZE,
+ rq->buff.map_dir);
+ __free_page(rq->wqe_overflow.page);
+}
+
static int mlx5e_alloc_rq(struct mlx5e_channel *c,
struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk,
rq_xdp_ix += params->num_channels * MLX5E_RQ_GROUP_XSK;
err = xdp_rxq_info_reg(&rq->xdp_rxq, rq->netdev, rq_xdp_ix);
if (err < 0)
- goto err_rq_wq_destroy;
+ goto err_rq_xdp_prog;
rq->buff.map_dir = params->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
rq->buff.headroom = mlx5e_get_rq_headroom(mdev, params, xsk);
err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->mpwqe.wq,
&rq->wq_ctrl);
if (err)
+ goto err_rq_xdp;
+
+ err = mlx5e_alloc_mpwqe_rq_drop_page(rq);
+ if (err)
goto err_rq_wq_destroy;
rq->mpwqe.wq.db = &rq->mpwqe.wq.db[MLX5_RCV_DBR];
err = mlx5e_create_rq_umr_mkey(mdev, rq);
if (err)
- goto err_rq_wq_destroy;
+ goto err_rq_drop_page;
rq->mkey_be = cpu_to_be32(rq->umr_mkey.key);
err = mlx5e_rq_alloc_mpwqe_info(rq, c);
if (err)
- goto err_free;
+ goto err_rq_mkey;
break;
default: /* MLX5_WQ_TYPE_CYCLIC */
err = mlx5_wq_cyc_create(mdev, &rqp->wq, rqc_wq, &rq->wqe.wq,
&rq->wq_ctrl);
if (err)
- goto err_rq_wq_destroy;
+ goto err_rq_xdp;
rq->wqe.wq.db = &rq->wqe.wq.db[MLX5_RCV_DBR];
GFP_KERNEL, cpu_to_node(c->cpu));
if (!rq->wqe.frags) {
err = -ENOMEM;
- goto err_free;
+ goto err_rq_wq_destroy;
}
err = mlx5e_init_di_list(rq, wq_sz, c->cpu);
if (err)
- goto err_free;
+ goto err_rq_frags;
rq->mkey_be = c->mkey_be;
}
err = mlx5e_rq_set_handlers(rq, params, xsk);
if (err)
- goto err_free;
+ goto err_free_by_rq_type;
if (xsk) {
err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
if (IS_ERR(rq->page_pool)) {
err = PTR_ERR(rq->page_pool);
rq->page_pool = NULL;
- goto err_free;
+ goto err_free_by_rq_type;
}
err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
MEM_TYPE_PAGE_POOL, rq->page_pool);
}
if (err)
- goto err_free;
+ goto err_free_by_rq_type;
for (i = 0; i < wq_sz; i++) {
if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
return 0;
-err_free:
+err_free_by_rq_type:
switch (rq->wq_type) {
case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
kvfree(rq->mpwqe.info);
+err_rq_mkey:
mlx5_core_destroy_mkey(mdev, &rq->umr_mkey);
+err_rq_drop_page:
+ mlx5e_free_mpwqe_rq_drop_page(rq);
break;
default: /* MLX5_WQ_TYPE_CYCLIC */
- kvfree(rq->wqe.frags);
mlx5e_free_di_list(rq);
+err_rq_frags:
+ kvfree(rq->wqe.frags);
}
-
err_rq_wq_destroy:
+ mlx5_wq_destroy(&rq->wq_ctrl);
+err_rq_xdp:
+ xdp_rxq_info_unreg(&rq->xdp_rxq);
+err_rq_xdp_prog:
if (params->xdp_prog)
bpf_prog_put(params->xdp_prog);
- xdp_rxq_info_unreg(&rq->xdp_rxq);
- page_pool_destroy(rq->page_pool);
- mlx5_wq_destroy(&rq->wq_ctrl);
return err;
}
case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
kvfree(rq->mpwqe.info);
mlx5_core_destroy_mkey(rq->mdev, &rq->umr_mkey);
+ mlx5e_free_mpwqe_rq_drop_page(rq);
break;
default: /* MLX5_WQ_TYPE_CYCLIC */
kvfree(rq->wqe.frags);
}
#endif
+static bool mlx5e_gre_tunnel_inner_proto_offload_supported(struct mlx5_core_dev *mdev,
+ struct sk_buff *skb)
+{
+ switch (skb->inner_protocol) {
+ case htons(ETH_P_IP):
+ case htons(ETH_P_IPV6):
+ case htons(ETH_P_TEB):
+ return true;
+ case htons(ETH_P_MPLS_UC):
+ case htons(ETH_P_MPLS_MC):
+ return MLX5_CAP_ETH(mdev, tunnel_stateless_mpls_over_gre);
+ }
+ return false;
+}
+
static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
struct sk_buff *skb,
netdev_features_t features)
switch (proto) {
case IPPROTO_GRE:
- return features;
+ if (mlx5e_gre_tunnel_inner_proto_offload_supported(priv->mdev, skb))
+ return features;
+ break;
case IPPROTO_IPIP:
case IPPROTO_IPV6:
if (mlx5e_tunnel_proto_supported(priv->mdev, IPPROTO_IPIP))
/* encap list sharing the same neigh */
struct list_head encap_list;
- /* valid only when the neigh reference is taken during
- * neigh_update_work workqueue callback.
- */
- struct neighbour *n;
- struct work_struct neigh_update_work;
-
/* neigh hash entry can be deleted only when the refcount is zero.
* refcount is needed to avoid neigh hash entry removal by TC, while
* it's used by the neigh notification call.
return count_eqe;
}
+static void mlx5_eq_async_int_lock(struct mlx5_eq_async *eq, unsigned long *flags)
+ __acquires(&eq->lock)
+{
+ if (in_irq())
+ spin_lock(&eq->lock);
+ else
+ spin_lock_irqsave(&eq->lock, *flags);
+}
+
+static void mlx5_eq_async_int_unlock(struct mlx5_eq_async *eq, unsigned long *flags)
+ __releases(&eq->lock)
+{
+ if (in_irq())
+ spin_unlock(&eq->lock);
+ else
+ spin_unlock_irqrestore(&eq->lock, *flags);
+}
+
+enum async_eq_nb_action {
+ ASYNC_EQ_IRQ_HANDLER = 0,
+ ASYNC_EQ_RECOVER = 1,
+};
+
static int mlx5_eq_async_int(struct notifier_block *nb,
unsigned long action, void *data)
{
struct mlx5_eq_table *eqt;
struct mlx5_core_dev *dev;
struct mlx5_eqe *eqe;
+ unsigned long flags;
int num_eqes = 0;
dev = eq->dev;
eqt = dev->priv.eq_table;
+ mlx5_eq_async_int_lock(eq_async, &flags);
+
eqe = next_eqe_sw(eq);
if (!eqe)
goto out;
out:
eq_update_ci(eq, 1);
+ mlx5_eq_async_int_unlock(eq_async, &flags);
- return 0;
+ return unlikely(action == ASYNC_EQ_RECOVER) ? num_eqes : 0;
+}
+
+void mlx5_cmd_eq_recover(struct mlx5_core_dev *dev)
+{
+ struct mlx5_eq_async *eq = &dev->priv.eq_table->cmd_eq;
+ int eqes;
+
+ eqes = mlx5_eq_async_int(&eq->irq_nb, ASYNC_EQ_RECOVER, NULL);
+ if (eqes)
+ mlx5_core_warn(dev, "Recovered %d EQEs on cmd_eq\n", eqes);
}
static void init_eq_buf(struct mlx5_eq *eq)
int err;
eq->irq_nb.notifier_call = mlx5_eq_async_int;
+ spin_lock_init(&eq->lock);
err = create_async_eq(dev, &eq->core, param);
if (err) {
cleanup_async_eq(dev, &table->pages_eq, "pages");
cleanup_async_eq(dev, &table->async_eq, "async");
+ mlx5_cmd_allowed_opcode(dev, MLX5_CMD_OP_DESTROY_EQ);
mlx5_cmd_use_polling(dev);
cleanup_async_eq(dev, &table->cmd_eq, "cmd");
+ mlx5_cmd_allowed_opcode(dev, CMD_ALLOWED_OPCODE_ALL);
mlx5_eq_notifier_unregister(dev, &table->cq_err_nb);
}
struct mlx5_eq_async {
struct mlx5_eq core;
struct notifier_block irq_nb;
+ spinlock_t lock; /* To avoid irq EQ handle races with resiliency flows */
};
struct mlx5_eq_comp {
struct cpumask *mlx5_eq_comp_cpumask(struct mlx5_core_dev *dev, int ix);
u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq_comp *eq);
+void mlx5_cmd_eq_recover(struct mlx5_core_dev *dev);
void mlx5_eq_synchronize_async_irq(struct mlx5_core_dev *dev);
void mlx5_eq_synchronize_cmd_irq(struct mlx5_core_dev *dev);
u32 npages;
u32 i = 0;
- if (dev->state != MLX5_DEVICE_STATE_INTERNAL_ERROR)
+ if (!mlx5_cmd_is_down(dev))
return mlx5_cmd_exec(dev, in, in_size, out, out_size);
/* No hard feelings, we want our pages back! */
return 0;
err_request_irq:
- for (; i >= 0; i--) {
+ while (i--) {
struct mlx5_irq *irq = mlx5_irq_get(dev, i);
int irqn = pci_irq_vector(dev->pdev, i);
return dev->netdev_ops == &mlxsw_sp_port_netdev_ops;
}
-static int mlxsw_sp_lower_dev_walk(struct net_device *lower_dev, void *data)
+static int mlxsw_sp_lower_dev_walk(struct net_device *lower_dev,
+ struct netdev_nested_priv *priv)
{
- struct mlxsw_sp_port **p_mlxsw_sp_port = data;
int ret = 0;
if (mlxsw_sp_port_dev_check(lower_dev)) {
- *p_mlxsw_sp_port = netdev_priv(lower_dev);
+ priv->data = (void *)netdev_priv(lower_dev);
ret = 1;
}
struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev)
{
- struct mlxsw_sp_port *mlxsw_sp_port;
+ struct netdev_nested_priv priv = {
+ .data = NULL,
+ };
if (mlxsw_sp_port_dev_check(dev))
return netdev_priv(dev);
- mlxsw_sp_port = NULL;
- netdev_walk_all_lower_dev(dev, mlxsw_sp_lower_dev_walk, &mlxsw_sp_port);
+ netdev_walk_all_lower_dev(dev, mlxsw_sp_lower_dev_walk, &priv);
- return mlxsw_sp_port;
+ return (struct mlxsw_sp_port *)priv.data;
}
struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev)
struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find_rcu(struct net_device *dev)
{
- struct mlxsw_sp_port *mlxsw_sp_port;
+ struct netdev_nested_priv priv = {
+ .data = NULL,
+ };
if (mlxsw_sp_port_dev_check(dev))
return netdev_priv(dev);
- mlxsw_sp_port = NULL;
netdev_walk_all_lower_dev_rcu(dev, mlxsw_sp_lower_dev_walk,
- &mlxsw_sp_port);
+ &priv);
- return mlxsw_sp_port;
+ return (struct mlxsw_sp_port *)priv.data;
}
struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev)
int err;
group->tcam = tcam;
- mutex_init(&group->lock);
INIT_LIST_HEAD(&group->region_list);
err = mlxsw_sp_acl_tcam_group_id_get(tcam, &group->id);
if (err)
return err;
+ mutex_init(&group->lock);
+
return 0;
}
return err;
}
-static int __mlxsw_sp_rif_macvlan_flush(struct net_device *dev, void *data)
+static int __mlxsw_sp_rif_macvlan_flush(struct net_device *dev,
+ struct netdev_nested_priv *priv)
{
- struct mlxsw_sp_rif *rif = data;
+ struct mlxsw_sp_rif *rif = (struct mlxsw_sp_rif *)priv->data;
if (!netif_is_macvlan(dev))
return 0;
static int mlxsw_sp_rif_macvlan_flush(struct mlxsw_sp_rif *rif)
{
+ struct netdev_nested_priv priv = {
+ .data = (void *)rif,
+ };
+
if (!netif_is_macvlan_port(rif->dev))
return 0;
netdev_warn(rif->dev, "Router interface is deleted. Upper macvlans will not work\n");
return netdev_walk_all_upper_dev_rcu(rif->dev,
- __mlxsw_sp_rif_macvlan_flush, rif);
+ __mlxsw_sp_rif_macvlan_flush, &priv);
}
static void mlxsw_sp_rif_subport_setup(struct mlxsw_sp_rif *rif,
}
static int mlxsw_sp_bridge_device_upper_rif_destroy(struct net_device *dev,
- void *data)
+ struct netdev_nested_priv *priv)
{
- struct mlxsw_sp *mlxsw_sp = data;
+ struct mlxsw_sp *mlxsw_sp = priv->data;
mlxsw_sp_rif_destroy_by_dev(mlxsw_sp, dev);
return 0;
static void mlxsw_sp_bridge_device_rifs_destroy(struct mlxsw_sp *mlxsw_sp,
struct net_device *dev)
{
+ struct netdev_nested_priv priv = {
+ .data = (void *)mlxsw_sp,
+ };
+
mlxsw_sp_rif_destroy_by_dev(mlxsw_sp, dev);
netdev_walk_all_upper_dev_rcu(dev,
mlxsw_sp_bridge_device_upper_rif_destroy,
- mlxsw_sp);
+ &priv);
}
static int mlxsw_sp_bridge_device_vxlan_init(struct mlxsw_sp_bridge *bridge,
struct ocelot_port *ocelot_port = ocelot->ports[port];
int maxlen = sdu + ETH_HLEN + ETH_FCS_LEN;
int pause_start, pause_stop;
- int atop_wm;
+ int atop, atop_tot;
if (port == ocelot->npi) {
maxlen += OCELOT_TAG_LEN;
ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_STOP,
pause_stop);
- /* Tail dropping watermark */
- atop_wm = (ocelot->shared_queue_sz - 9 * maxlen) /
+ /* Tail dropping watermarks */
+ atop_tot = (ocelot->shared_queue_sz - 9 * maxlen) /
OCELOT_BUFFER_CELL_SZ;
- ocelot_write_rix(ocelot, ocelot->ops->wm_enc(9 * maxlen),
- SYS_ATOP, port);
- ocelot_write(ocelot, ocelot->ops->wm_enc(atop_wm), SYS_ATOP_TOT_CFG);
+ atop = (9 * maxlen) / OCELOT_BUFFER_CELL_SZ;
+ ocelot_write_rix(ocelot, ocelot->ops->wm_enc(atop), SYS_ATOP, port);
+ ocelot_write(ocelot, ocelot->ops->wm_enc(atop_tot), SYS_ATOP_TOT_CFG);
}
EXPORT_SYMBOL(ocelot_port_set_maxlen);
*/
static u16 ocelot_wm_enc(u16 value)
{
+ WARN_ON(value >= 16 * BIT(8));
+
if (value >= BIT(8))
return BIT(8) | (value / 16);
void r8169_apply_firmware(struct rtl8169_private *tp)
{
+ int val;
+
/* TODO: release firmware if rtl_fw_write_firmware signals failure. */
if (tp->rtl_fw) {
rtl_fw_write_firmware(tp, tp->rtl_fw);
/* At least one firmware doesn't reset tp->ocp_base. */
tp->ocp_base = OCP_STD_PHY_BASE;
+
+ /* PHY soft reset may still be in progress */
+ phy_read_poll_timeout(tp->phydev, MII_BMCR, val,
+ !(val & BMCR_RESET),
+ 50000, 600000, true);
}
}
default:
break;
}
-
- clk_disable_unprepare(tp->clk);
}
static void rtl_pll_power_up(struct rtl8169_private *tp)
{
- clk_prepare_enable(tp->clk);
-
switch (tp->mac_version) {
case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_33:
case RTL_GIGA_MAC_VER_37:
{ 0x08, 0x0001, 0x0002 },
{ 0x09, 0x0000, 0x0080 },
{ 0x19, 0x0000, 0x0224 },
- { 0x00, 0x0000, 0x0004 },
+ { 0x00, 0x0000, 0x0008 },
{ 0x0c, 0x3df0, 0x0200 },
};
{ 0x06, 0x00c0, 0x0020 },
{ 0x0f, 0xffff, 0x5200 },
{ 0x19, 0x0000, 0x0224 },
- { 0x00, 0x0000, 0x0004 },
+ { 0x00, 0x0000, 0x0008 },
{ 0x0c, 0x3df0, 0x0200 },
};
#ifdef CONFIG_PM
+static int rtl8169_net_resume(struct rtl8169_private *tp)
+{
+ rtl_rar_set(tp, tp->dev->dev_addr);
+
+ if (tp->TxDescArray)
+ rtl8169_up(tp);
+
+ netif_device_attach(tp->dev);
+
+ return 0;
+}
+
static int __maybe_unused rtl8169_suspend(struct device *device)
{
struct rtl8169_private *tp = dev_get_drvdata(device);
rtnl_lock();
rtl8169_net_suspend(tp);
+ if (!device_may_wakeup(tp_to_dev(tp)))
+ clk_disable_unprepare(tp->clk);
rtnl_unlock();
return 0;
}
-static int rtl8169_resume(struct device *device)
+static int __maybe_unused rtl8169_resume(struct device *device)
{
struct rtl8169_private *tp = dev_get_drvdata(device);
- rtl_rar_set(tp, tp->dev->dev_addr);
+ if (!device_may_wakeup(tp_to_dev(tp)))
+ clk_prepare_enable(tp->clk);
- if (tp->TxDescArray)
- rtl8169_up(tp);
+ /* Reportedly at least Asus X453MA truncates packets otherwise */
+ if (tp->mac_version == RTL_GIGA_MAC_VER_37)
+ rtl_init_rxcfg(tp);
- netif_device_attach(tp->dev);
-
- return 0;
+ return rtl8169_net_resume(tp);
}
static int rtl8169_runtime_suspend(struct device *device)
__rtl8169_set_wol(tp, tp->saved_wolopts);
- return rtl8169_resume(device);
+ return rtl8169_net_resume(tp);
}
static int rtl8169_runtime_idle(struct device *device)
return error;
}
-/* MDIO bus init function */
-static int ravb_mdio_init(struct ravb_private *priv)
-{
- struct platform_device *pdev = priv->pdev;
- struct device *dev = &pdev->dev;
- int error;
-
- /* Bitbang init */
- priv->mdiobb.ops = &bb_ops;
-
- /* MII controller setting */
- priv->mii_bus = alloc_mdio_bitbang(&priv->mdiobb);
- if (!priv->mii_bus)
- return -ENOMEM;
-
- /* Hook up MII support for ethtool */
- priv->mii_bus->name = "ravb_mii";
- priv->mii_bus->parent = dev;
- snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x",
- pdev->name, pdev->id);
-
- /* Register MDIO bus */
- error = of_mdiobus_register(priv->mii_bus, dev->of_node);
- if (error)
- goto out_free_bus;
-
- return 0;
-
-out_free_bus:
- free_mdio_bitbang(priv->mii_bus);
- return error;
-}
-
-/* MDIO bus release function */
-static int ravb_mdio_release(struct ravb_private *priv)
-{
- /* Unregister mdio bus */
- mdiobus_unregister(priv->mii_bus);
-
- /* Free bitbang info */
- free_mdio_bitbang(priv->mii_bus);
-
- return 0;
-}
-
/* Network device open function for Ethernet AVB */
static int ravb_open(struct net_device *ndev)
{
struct device *dev = &pdev->dev;
int error;
- /* MDIO bus init */
- error = ravb_mdio_init(priv);
- if (error) {
- netdev_err(ndev, "failed to initialize MDIO\n");
- return error;
- }
-
napi_enable(&priv->napi[RAVB_BE]);
napi_enable(&priv->napi[RAVB_NC]);
out_napi_off:
napi_disable(&priv->napi[RAVB_NC]);
napi_disable(&priv->napi[RAVB_BE]);
- ravb_mdio_release(priv);
return error;
}
ravb_ring_free(ndev, RAVB_BE);
ravb_ring_free(ndev, RAVB_NC);
- ravb_mdio_release(priv);
-
return 0;
}
.ndo_set_features = ravb_set_features,
};
+/* MDIO bus init function */
+static int ravb_mdio_init(struct ravb_private *priv)
+{
+ struct platform_device *pdev = priv->pdev;
+ struct device *dev = &pdev->dev;
+ int error;
+
+ /* Bitbang init */
+ priv->mdiobb.ops = &bb_ops;
+
+ /* MII controller setting */
+ priv->mii_bus = alloc_mdio_bitbang(&priv->mdiobb);
+ if (!priv->mii_bus)
+ return -ENOMEM;
+
+ /* Hook up MII support for ethtool */
+ priv->mii_bus->name = "ravb_mii";
+ priv->mii_bus->parent = dev;
+ snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x",
+ pdev->name, pdev->id);
+
+ /* Register MDIO bus */
+ error = of_mdiobus_register(priv->mii_bus, dev->of_node);
+ if (error)
+ goto out_free_bus;
+
+ return 0;
+
+out_free_bus:
+ free_mdio_bitbang(priv->mii_bus);
+ return error;
+}
+
+/* MDIO bus release function */
+static int ravb_mdio_release(struct ravb_private *priv)
+{
+ /* Unregister mdio bus */
+ mdiobus_unregister(priv->mii_bus);
+
+ /* Free bitbang info */
+ free_mdio_bitbang(priv->mii_bus);
+
+ return 0;
+}
+
static const struct of_device_id ravb_match_table[] = {
{ .compatible = "renesas,etheravb-r8a7790", .data = (void *)RCAR_GEN2 },
{ .compatible = "renesas,etheravb-r8a7794", .data = (void *)RCAR_GEN2 },
eth_hw_addr_random(ndev);
}
+ /* MDIO bus init */
+ error = ravb_mdio_init(priv);
+ if (error) {
+ dev_err(&pdev->dev, "failed to initialize MDIO\n");
+ goto out_dma_free;
+ }
+
netif_napi_add(ndev, &priv->napi[RAVB_BE], ravb_poll, 64);
netif_napi_add(ndev, &priv->napi[RAVB_NC], ravb_poll, 64);
out_napi_del:
netif_napi_del(&priv->napi[RAVB_NC]);
netif_napi_del(&priv->napi[RAVB_BE]);
+ ravb_mdio_release(priv);
+out_dma_free:
dma_free_coherent(ndev->dev.parent, priv->desc_bat_size, priv->desc_bat,
priv->desc_bat_dma);
unregister_netdev(ndev);
netif_napi_del(&priv->napi[RAVB_NC]);
netif_napi_del(&priv->napi[RAVB_BE]);
+ ravb_mdio_release(priv);
pm_runtime_disable(&pdev->dev);
free_netdev(ndev);
platform_set_drvdata(pdev, NULL);
struct rocker_port *port;
};
-static int rocker_lower_dev_walk(struct net_device *lower_dev, void *_data)
+static int rocker_lower_dev_walk(struct net_device *lower_dev,
+ struct netdev_nested_priv *priv)
{
- struct rocker_walk_data *data = _data;
+ struct rocker_walk_data *data = (struct rocker_walk_data *)priv->data;
int ret = 0;
if (rocker_port_dev_check_under(lower_dev, data->rocker)) {
struct rocker_port *rocker_port_dev_lower_find(struct net_device *dev,
struct rocker *rocker)
{
+ struct netdev_nested_priv priv;
struct rocker_walk_data data;
if (rocker_port_dev_check_under(dev, rocker))
data.rocker = rocker;
data.port = NULL;
- netdev_walk_all_lower_dev(dev, rocker_lower_dev_walk, &data);
+ priv.data = (void *)&data;
+ netdev_walk_all_lower_dev(dev, rocker_lower_dev_walk, &priv);
return data.port;
}
pci_free_irq_vectors(pdev);
- clk_disable_unprepare(priv->plat->stmmac_clk);
clk_unregister_fixed_rate(priv->plat->stmmac_clk);
pcim_iounmap_regions(pdev, BIT(0));
int eee_enabled;
int eee_active;
int tx_lpi_timer;
+ int tx_lpi_enabled;
+ int eee_tw_timer;
unsigned int mode;
unsigned int chain_mode;
int extend_desc;
edata->eee_enabled = priv->eee_enabled;
edata->eee_active = priv->eee_active;
edata->tx_lpi_timer = priv->tx_lpi_timer;
+ edata->tx_lpi_enabled = priv->tx_lpi_enabled;
return phylink_ethtool_get_eee(priv->phylink, edata);
}
struct stmmac_priv *priv = netdev_priv(dev);
int ret;
- if (!edata->eee_enabled) {
+ if (!priv->dma_cap.eee)
+ return -EOPNOTSUPP;
+
+ if (priv->tx_lpi_enabled != edata->tx_lpi_enabled)
+ netdev_warn(priv->dev,
+ "Setting EEE tx-lpi is not supported\n");
+
+ if (!edata->eee_enabled)
stmmac_disable_eee_mode(priv);
- } else {
- /* We are asking for enabling the EEE but it is safe
- * to verify all by invoking the eee_init function.
- * In case of failure it will return an error.
- */
- edata->eee_enabled = stmmac_eee_init(priv);
- if (!edata->eee_enabled)
- return -EOPNOTSUPP;
- }
ret = phylink_ethtool_set_eee(priv->phylink, edata);
if (ret)
return ret;
- priv->eee_enabled = edata->eee_enabled;
- priv->tx_lpi_timer = edata->tx_lpi_timer;
+ if (edata->eee_enabled &&
+ priv->tx_lpi_timer != edata->tx_lpi_timer) {
+ priv->tx_lpi_timer = edata->tx_lpi_timer;
+ stmmac_eee_init(priv);
+ }
+
return 0;
}
static int eee_timer = STMMAC_DEFAULT_LPI_TIMER;
module_param(eee_timer, int, 0644);
MODULE_PARM_DESC(eee_timer, "LPI tx expiration time in msec");
-#define STMMAC_LPI_T(x) (jiffies + msecs_to_jiffies(x))
+#define STMMAC_LPI_T(x) (jiffies + usecs_to_jiffies(x))
/* By default the driver will use the ring mode to manage tx and rx descriptors,
* but allow user to force to use the chain instead of the ring
struct stmmac_priv *priv = from_timer(priv, t, eee_ctrl_timer);
stmmac_enable_eee_mode(priv);
- mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(eee_timer));
+ mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer));
}
/**
*/
bool stmmac_eee_init(struct stmmac_priv *priv)
{
- int tx_lpi_timer = priv->tx_lpi_timer;
+ int eee_tw_timer = priv->eee_tw_timer;
/* Using PCS we cannot dial with the phy registers at this stage
* so we do not support extra feature like EEE.
if (priv->eee_enabled) {
netdev_dbg(priv->dev, "disable EEE\n");
del_timer_sync(&priv->eee_ctrl_timer);
- stmmac_set_eee_timer(priv, priv->hw, 0, tx_lpi_timer);
+ stmmac_set_eee_timer(priv, priv->hw, 0, eee_tw_timer);
}
mutex_unlock(&priv->lock);
return false;
if (priv->eee_active && !priv->eee_enabled) {
timer_setup(&priv->eee_ctrl_timer, stmmac_eee_ctrl_timer, 0);
- mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(eee_timer));
stmmac_set_eee_timer(priv, priv->hw, STMMAC_DEFAULT_LIT_LS,
- tx_lpi_timer);
+ eee_tw_timer);
}
+ mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer));
+
mutex_unlock(&priv->lock);
netdev_dbg(priv->dev, "Energy-Efficient Ethernet initialized\n");
return true;
stmmac_mac_set(priv, priv->ioaddr, false);
priv->eee_active = false;
+ priv->tx_lpi_enabled = false;
stmmac_eee_init(priv);
stmmac_set_eee_pls(priv, priv->hw, false);
}
if (phy && priv->dma_cap.eee) {
priv->eee_active = phy_init_eee(phy, 1) >= 0;
priv->eee_enabled = stmmac_eee_init(priv);
+ priv->tx_lpi_enabled = priv->eee_enabled;
stmmac_set_eee_pls(priv, priv->hw, true);
}
}
if ((priv->eee_enabled) && (!priv->tx_path_in_lpi_mode)) {
stmmac_enable_eee_mode(priv);
- mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(eee_timer));
+ mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer));
}
/* We still have pending packets, let's call for a new scheduling */
netdev_warn(priv->dev, "PTP init failed\n");
}
- priv->tx_lpi_timer = STMMAC_DEFAULT_TWT_LS;
+ priv->eee_tw_timer = STMMAC_DEFAULT_TWT_LS;
+
+ /* Convert the timer from msec to usec */
+ if (!priv->tx_lpi_timer)
+ priv->tx_lpi_timer = eee_timer * 1000;
if (priv->use_riwt) {
if (!priv->rx_riwt)
/*
Written 1998-2001 by Donald Becker.
- Current Maintainer: Roger Luethi <rl@hellgate.ch>
+ Current Maintainer: Kevin Brace <kevinbrace@bracecomputerlab.com>
This software may be used and distributed according to the terms of
the GNU General Public License (GPL), incorporated herein by reference.
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#define DRV_NAME "via-rhine"
-#define DRV_VERSION "1.5.1"
-#define DRV_RELDATE "2010-10-09"
#include <linux/types.h>
#include <linux/uaccess.h>
#include <linux/dmi.h>
-/* These identify the driver base version and may not be removed. */
-static const char version[] =
- "v1.10-LK" DRV_VERSION " " DRV_RELDATE " Written by Donald Becker";
-
MODULE_AUTHOR("Donald Becker <becker@scyld.com>");
MODULE_DESCRIPTION("VIA Rhine PCI Fast Ethernet driver");
MODULE_LICENSE("GPL");
VT8233 = 0x60, /* Integrated MAC */
VT8235 = 0x74, /* Integrated MAC */
VT8237 = 0x78, /* Integrated MAC */
- VTunknown1 = 0x7C,
+ VT8251 = 0x7C, /* Integrated MAC */
VT6105 = 0x80,
VT6105_B0 = 0x83,
VT6105L = 0x8A,
u32 quirks = 0;
#endif
-/* when built into the kernel, we only print version if device is found */
-#ifndef MODULE
- pr_info_once("%s\n", version);
-#endif
-
rc = pci_enable_device(pdev);
if (rc)
goto err_out;
goto out_free_ring;
alloc_tbufs(dev);
+ enable_mmio(rp->pioaddr, rp->quirks);
+ rhine_power_init(dev);
rhine_chip_reset(dev);
rhine_task_enable(rp);
init_registers(dev);
struct device *hwdev = dev->dev.parent;
strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
- strlcpy(info->version, DRV_VERSION, sizeof(info->version));
strlcpy(info->bus_info, dev_name(hwdev), sizeof(info->bus_info));
}
int ret_pci, ret_platform;
/* when a module, this is printed whether or not devices are found in probe */
-#ifdef MODULE
- pr_info("%s\n", version);
-#endif
if (dmi_check_system(rhine_dmi_table)) {
/* these BIOSes fail at PXE boot if chip is in D3 */
avoid_D3 = true;
struct macsec_rx_sa *rx_sa;
struct macsec_rxh_data *rxd;
struct macsec_dev *macsec;
+ unsigned int len;
sci_t sci;
u32 hdr_pn;
bool cbit;
macsec_rxsc_put(rx_sc);
skb_orphan(skb);
+ len = skb->len;
ret = gro_cells_receive(&macsec->gro_cells, skb);
if (ret == NET_RX_SUCCESS)
- count_rx(dev, skb->len);
+ count_rx(dev, len);
else
macsec->secy.netdev->stats.rx_dropped++;
depends on 64BIT
depends on PCI
select MDIO_CAVIUM
+ select MDIO_DEVRES
help
This driver supports the MDIO interfaces found on Cavium
ThunderX SoCs when the MDIO bus device appears as a PCI
// SPDX-License-Identifier: GPL-2.0+
-/*
- * drivers/net/phy/realtek.c
+/* drivers/net/phy/realtek.c
*
* Driver for Realtek PHYs
*
#define RTL8211F_TX_DELAY BIT(8)
#define RTL8211F_RX_DELAY BIT(3)
-#define RTL8211E_TX_DELAY BIT(1)
-#define RTL8211E_RX_DELAY BIT(2)
-#define RTL8211E_MODE_MII_GMII BIT(3)
+#define RTL8211E_CTRL_DELAY BIT(13)
+#define RTL8211E_TX_DELAY BIT(12)
+#define RTL8211E_RX_DELAY BIT(11)
#define RTL8201F_ISR 0x1e
#define RTL8201F_IER 0x13
/* enable TX/RX delay for rgmii-* modes, and disable them for rgmii. */
switch (phydev->interface) {
case PHY_INTERFACE_MODE_RGMII:
- val = 0;
+ val = RTL8211E_CTRL_DELAY | 0;
break;
case PHY_INTERFACE_MODE_RGMII_ID:
- val = RTL8211E_TX_DELAY | RTL8211E_RX_DELAY;
+ val = RTL8211E_CTRL_DELAY | RTL8211E_TX_DELAY | RTL8211E_RX_DELAY;
break;
case PHY_INTERFACE_MODE_RGMII_RXID:
- val = RTL8211E_RX_DELAY;
+ val = RTL8211E_CTRL_DELAY | RTL8211E_RX_DELAY;
break;
case PHY_INTERFACE_MODE_RGMII_TXID:
- val = RTL8211E_TX_DELAY;
+ val = RTL8211E_CTRL_DELAY | RTL8211E_TX_DELAY;
break;
default: /* the rest of the modes imply leaving delays as is. */
return 0;
/* According to a sample driver there is a 0x1c config register on the
* 0xa4 extension page (0x7) layout. It can be used to disable/enable
- * the RX/TX delays otherwise controlled by RXDLY/TXDLY pins. It can
- * also be used to customize the whole configuration register:
- * 8:6 = PHY Address, 5:4 = Auto-Negotiation, 3 = Interface Mode Select,
- * 2 = RX Delay, 1 = TX Delay, 0 = SELRGV (see original PHY datasheet
- * for details).
+ * the RX/TX delays otherwise controlled by RXDLY/TXDLY pins.
+ * The configuration register definition:
+ * 14 = reserved
+ * 13 = Force Tx RX Delay controlled by bit12 bit11,
+ * 12 = RX Delay, 11 = TX Delay
+ * 10:0 = Test && debug settings reserved by realtek
*/
oldpage = phy_select_page(phydev, 0x7);
if (oldpage < 0)
if (ret)
goto err_restore_page;
- ret = __phy_modify(phydev, 0x1c, RTL8211E_TX_DELAY | RTL8211E_RX_DELAY,
+ ret = __phy_modify(phydev, 0x1c, RTL8211E_CTRL_DELAY
+ | RTL8211E_TX_DELAY | RTL8211E_RX_DELAY,
val);
err_restore_page:
for (i--; i >= 0; i--)
__team_option_inst_del_option(team, dst_opts[i]);
- i = option_count - 1;
+ i = option_count;
alloc_rollback:
for (i--; i >= 0; i--)
kfree(dst_opts[i]);
dev->header_ops = port_dev->header_ops;
dev->type = port_dev->type;
dev->hard_header_len = port_dev->hard_header_len;
+ dev->needed_headroom = port_dev->needed_headroom;
dev->addr_len = port_dev->addr_len;
dev->mtu = port_dev->mtu;
memcpy(dev->broadcast, port_dev->broadcast, port_dev->addr_len);
.status = ax88179_status,
.link_reset = ax88179_link_reset,
.reset = ax88179_reset,
+ .stop = ax88179_stop,
+ .flags = FLAG_ETHER | FLAG_FRAMING_AX,
+ .rx_fixup = ax88179_rx_fixup,
+ .tx_fixup = ax88179_tx_fixup,
+};
+
+static const struct driver_info toshiba_info = {
+ .description = "Toshiba USB Ethernet Adapter",
+ .bind = ax88179_bind,
+ .unbind = ax88179_unbind,
+ .status = ax88179_status,
+ .link_reset = ax88179_link_reset,
+ .reset = ax88179_reset,
+ .stop = ax88179_stop,
+ .flags = FLAG_ETHER | FLAG_FRAMING_AX,
+ .rx_fixup = ax88179_rx_fixup,
+ .tx_fixup = ax88179_tx_fixup,
+};
+
+static const struct driver_info mct_info = {
+ .description = "MCT USB 3.0 Gigabit Ethernet Adapter",
+ .bind = ax88179_bind,
+ .unbind = ax88179_unbind,
+ .status = ax88179_status,
+ .link_reset = ax88179_link_reset,
+ .reset = ax88179_reset,
+ .stop = ax88179_stop,
.flags = FLAG_ETHER | FLAG_FRAMING_AX,
.rx_fixup = ax88179_rx_fixup,
.tx_fixup = ax88179_tx_fixup,
/* Belkin B2B128 USB 3.0 Hub + Gigabit Ethernet Adapter */
USB_DEVICE(0x050d, 0x0128),
.driver_info = (unsigned long)&belkin_info,
+}, {
+ /* Toshiba USB 3.0 GBit Ethernet Adapter */
+ USB_DEVICE(0x0930, 0x0a13),
+ .driver_info = (unsigned long)&toshiba_info,
+}, {
+ /* Magic Control Technology U3-A9003 USB 3.0 Gigabit Ethernet Adapter */
+ USB_DEVICE(0x0711, 0x0179),
+ .driver_info = (unsigned long)&mct_info,
},
{ },
};
}
#endif /* PEGASUS_WRITE_EEPROM */
-static inline void get_node_id(pegasus_t *pegasus, __u8 *id)
+static inline int get_node_id(pegasus_t *pegasus, u8 *id)
{
- int i;
- __u16 w16;
+ int i, ret;
+ u16 w16;
for (i = 0; i < 3; i++) {
- read_eprom_word(pegasus, i, &w16);
+ ret = read_eprom_word(pegasus, i, &w16);
+ if (ret < 0)
+ return ret;
((__le16 *) id)[i] = cpu_to_le16(w16);
}
+
+ return 0;
}
static void set_ethernet_addr(pegasus_t *pegasus)
{
- __u8 node_id[6];
+ int ret;
+ u8 node_id[6];
if (pegasus->features & PEGASUS_II) {
- get_registers(pegasus, 0x10, sizeof(node_id), node_id);
+ ret = get_registers(pegasus, 0x10, sizeof(node_id), node_id);
+ if (ret < 0)
+ goto err;
} else {
- get_node_id(pegasus, node_id);
- set_registers(pegasus, EthID, sizeof(node_id), node_id);
+ ret = get_node_id(pegasus, node_id);
+ if (ret < 0)
+ goto err;
+ ret = set_registers(pegasus, EthID, sizeof(node_id), node_id);
+ if (ret < 0)
+ goto err;
}
+
memcpy(pegasus->net->dev_addr, node_id, sizeof(node_id));
+
+ return;
+err:
+ eth_hw_addr_random(pegasus->net);
+ dev_info(&pegasus->intf->dev, "software assigned MAC address.\n");
+
+ return;
}
static inline int reset_mac(pegasus_t *pegasus)
{QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)}, /* Fibocom NL678 series */
{QMI_FIXED_INTF(0x0489, 0xe0b4, 0)}, /* Foxconn T77W968 LTE */
{QMI_FIXED_INTF(0x0489, 0xe0b5, 0)}, /* Foxconn T77W968 LTE with eSIM support*/
+ {QMI_FIXED_INTF(0x2692, 0x9025, 4)}, /* Cellient MPL200 (rebranded Qualcomm 05c6:9025) */
/* 4. Gobi 1000 devices */
{QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */
return 1;
}
-static inline void set_ethernet_addr(rtl8150_t * dev)
+static void set_ethernet_addr(rtl8150_t *dev)
{
- u8 node_id[6];
+ u8 node_id[ETH_ALEN];
+ int ret;
+
+ ret = get_registers(dev, IDR, sizeof(node_id), node_id);
- get_registers(dev, IDR, sizeof(node_id), node_id);
- memcpy(dev->netdev->dev_addr, node_id, sizeof(node_id));
+ if (ret == sizeof(node_id)) {
+ ether_addr_copy(dev->netdev->dev_addr, node_id);
+ } else {
+ eth_hw_addr_random(dev->netdev);
+ netdev_notice(dev->netdev, "Assigned a random MAC address: %pM\n",
+ dev->netdev->dev_addr);
+ }
}
static int rtl8150_set_mac_address(struct net_device *netdev, void *p)
VIRTIO_NET_F_GUEST_CSUM
};
+#define GUEST_OFFLOAD_LRO_MASK ((1ULL << VIRTIO_NET_F_GUEST_TSO4) | \
+ (1ULL << VIRTIO_NET_F_GUEST_TSO6) | \
+ (1ULL << VIRTIO_NET_F_GUEST_ECN) | \
+ (1ULL << VIRTIO_NET_F_GUEST_UFO))
+
struct virtnet_stat_desc {
char desc[ETH_GSTRING_LEN];
size_t offset;
if (features & NETIF_F_LRO)
offloads = vi->guest_offloads_capable;
else
- offloads = 0;
+ offloads = vi->guest_offloads_capable &
+ ~GUEST_OFFLOAD_LRO_MASK;
err = virtnet_set_guest_offloads(vi, offloads);
if (err)
/* Use temporary descriptor to avoid touching bits multiple times */
union Vmxnet3_GenericDesc tempTxDesc;
#endif
- struct udphdr *udph;
count = txd_estimate(skb);
gdesc->txd.om = VMXNET3_OM_ENCAP;
gdesc->txd.msscof = ctx.mss;
- udph = udp_hdr(skb);
- if (udph->check)
+ if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM)
gdesc->txd.oco = 1;
} else {
gdesc->txd.hlen = ctx.l4_offset + ctx.l4_hdr_size;
.ndo_change_mtu = vmxnet3_change_mtu,
.ndo_fix_features = vmxnet3_fix_features,
.ndo_set_features = vmxnet3_set_features,
+ .ndo_features_check = vmxnet3_features_check,
.ndo_get_stats64 = vmxnet3_get_stats64,
.ndo_tx_timeout = vmxnet3_tx_timeout,
.ndo_set_rx_mode = vmxnet3_set_mc,
return features;
}
+netdev_features_t vmxnet3_features_check(struct sk_buff *skb,
+ struct net_device *netdev,
+ netdev_features_t features)
+{
+ struct vmxnet3_adapter *adapter = netdev_priv(netdev);
+
+ /* Validate if the tunneled packet is being offloaded by the device */
+ if (VMXNET3_VERSION_GE_4(adapter) &&
+ skb->encapsulation && skb->ip_summed == CHECKSUM_PARTIAL) {
+ u8 l4_proto = 0;
+
+ switch (vlan_get_protocol(skb)) {
+ case htons(ETH_P_IP):
+ l4_proto = ip_hdr(skb)->protocol;
+ break;
+ case htons(ETH_P_IPV6):
+ l4_proto = ipv6_hdr(skb)->nexthdr;
+ break;
+ default:
+ return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
+ }
+
+ if (l4_proto != IPPROTO_UDP)
+ return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
+ }
+ return features;
+}
+
static void vmxnet3_enable_encap_offloads(struct net_device *netdev)
{
struct vmxnet3_adapter *adapter = netdev_priv(netdev);
netdev_features_t
vmxnet3_fix_features(struct net_device *netdev, netdev_features_t features);
+netdev_features_t
+vmxnet3_features_check(struct sk_buff *skb,
+ struct net_device *netdev, netdev_features_t features);
+
int
vmxnet3_set_features(struct net_device *netdev, netdev_features_t features);
{
struct x25_asy *sl = netdev_priv(dev);
unsigned long len;
- int err;
if (sl->tty == NULL)
return -ENODEV;
sl->xleft = 0;
sl->flags &= (1 << SLF_INUSE); /* Clear ESCAPE & ERROR flags */
- netif_start_queue(dev);
-
- /*
- * Now attach LAPB
- */
- err = lapb_register(dev, &x25_asy_callbacks);
- if (err == LAPB_OK)
- return 0;
+ return 0;
/* Cleanup */
kfree(sl->xbuff);
if (sl->tty)
clear_bit(TTY_DO_WRITE_WAKEUP, &sl->tty->flags);
- netif_stop_queue(dev);
sl->rcount = 0;
sl->xleft = 0;
spin_unlock(&sl->lock);
static void x25_asy_close_tty(struct tty_struct *tty)
{
struct x25_asy *sl = tty->disc_data;
- int err;
/* First make sure we're connected. */
if (!sl || sl->magic != X25_ASY_MAGIC)
dev_close(sl->dev);
rtnl_unlock();
- err = lapb_unregister(sl->dev);
- if (err != LAPB_OK)
- pr_err("%s: lapb_unregister error: %d\n",
- __func__, err);
-
tty->disc_data = NULL;
sl->tty = NULL;
x25_asy_free(sl);
static int x25_asy_open_dev(struct net_device *dev)
{
+ int err;
struct x25_asy *sl = netdev_priv(dev);
if (sl->tty == NULL)
return -ENODEV;
+
+ err = lapb_register(dev, &x25_asy_callbacks);
+ if (err != LAPB_OK)
+ return -ENOMEM;
+
+ netif_start_queue(dev);
+
+ return 0;
+}
+
+static int x25_asy_close_dev(struct net_device *dev)
+{
+ int err;
+
+ netif_stop_queue(dev);
+
+ err = lapb_unregister(dev);
+ if (err != LAPB_OK)
+ pr_err("%s: lapb_unregister error: %d\n",
+ __func__, err);
+
+ x25_asy_close(dev);
+
return 0;
}
static const struct net_device_ops x25_asy_netdev_ops = {
.ndo_open = x25_asy_open_dev,
- .ndo_stop = x25_asy_close,
+ .ndo_stop = x25_asy_close_dev,
.ndo_start_xmit = x25_asy_xmit,
.ndo_tx_timeout = x25_asy_timeout,
.ndo_change_mtu = x25_asy_change_mtu,
dev->mphy.sband_2g.sband.ht_cap.cap |= IEEE80211_HT_CAP_LDPC_CODING;
dev->mphy.sband_5g.sband.ht_cap.cap |= IEEE80211_HT_CAP_LDPC_CODING;
dev->mphy.sband_5g.sband.vht_cap.cap |=
- IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 |
+ IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 |
IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK;
mt7615_cap_dbdc_disable(dev);
dev->phy.dfs_state = -1;
return ndev->netdev_ops == &qtnf_netdev_ops;
}
-static int qtnf_check_br_ports(struct net_device *dev, void *data)
+static int qtnf_check_br_ports(struct net_device *dev,
+ struct netdev_nested_priv *priv)
{
- struct net_device *ndev = data;
+ struct net_device *ndev = (struct net_device *)priv->data;
if (dev != ndev && netdev_port_same_parent_id(dev, ndev))
return -ENOTSUPP;
{
struct net_device *ndev = netdev_notifier_info_to_dev(ptr);
const struct netdev_notifier_changeupper_info *info;
+ struct netdev_nested_priv priv = {
+ .data = (void *)ndev,
+ };
struct net_device *brdev;
struct qtnf_vif *vif;
struct qtnf_bus *bus;
} else {
ret = netdev_walk_all_lower_dev(brdev,
qtnf_check_br_ports,
- ndev);
+ &priv);
}
break;
}
nvme_get_ctrl(ctrl);
- if (!try_module_get(ctrl->ops->module))
+ if (!try_module_get(ctrl->ops->module)) {
+ nvme_put_ctrl(ctrl);
return -EINVAL;
+ }
file->private_data = ctrl;
return 0;
else
flags |= MSG_MORE | MSG_SENDPAGE_NOTLAST;
- /* can't zcopy slab pages */
- if (unlikely(PageSlab(page))) {
- ret = sock_no_sendpage(queue->sock, page, offset, len,
+ if (sendpage_ok(page)) {
+ ret = kernel_sendpage(queue->sock, page, offset, len,
flags);
} else {
- ret = kernel_sendpage(queue->sock, page, offset, len,
+ ret = sock_no_sendpage(queue->sock, page, offset, len,
flags);
}
if (ret <= 0)
&config);
if (IS_ERR(ec->dcon_rdev)) {
dev_err(&pdev->dev, "failed to register DCON regulator\n");
- return PTR_ERR(ec->dcon_rdev);
+ err = PTR_ERR(ec->dcon_rdev);
+ kfree(ec);
+ return err;
}
ec->dbgfs_dir = olpc_ec_setup_debugfs();
depends on BACKLIGHT_CLASS_DEVICE
depends on ACPI_VIDEO || ACPI_VIDEO = n
select INPUT_SPARSEKMAP
+ select NEW_LEDS
select LEDS_CLASS
help
This is a driver for laptops built by Fujitsu:
depends on ACPI_WMI
depends on INPUT
select INPUT_SPARSEKMAP
+ select NEW_LEDS
select LEDS_CLASS
help
This driver adds support for hotkeys as well as control of keyboard
.wmi_backlight_set_devstate = true,
};
+static struct quirk_entry quirk_asus_use_kbd_dock_devid = {
+ .use_kbd_dock_devid = true,
+};
+
static int dmi_matched(const struct dmi_system_id *dmi)
{
pr_info("Identified laptop model '%s'\n", dmi->ident);
},
.driver_data = &quirk_asus_vendor_backlight,
},
+ {
+ .callback = dmi_matched,
+ .ident = "Asus Transformer T100TA / T100HA / T100CHI",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ /* Match *T100* */
+ DMI_MATCH(DMI_PRODUCT_NAME, "T100"),
+ },
+ .driver_data = &quirk_asus_use_kbd_dock_devid,
+ },
+ {
+ .callback = dmi_matched,
+ .ident = "Asus Transformer T101HA",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "T101HA"),
+ },
+ .driver_data = &quirk_asus_use_kbd_dock_devid,
+ },
+ {
+ .callback = dmi_matched,
+ .ident = "Asus Transformer T200TA",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "T200TA"),
+ },
+ .driver_data = &quirk_asus_use_kbd_dock_devid,
+ },
{},
};
.detect_quirks = asus_nb_wmi_quirks,
};
-static const struct dmi_system_id asus_nb_wmi_blacklist[] __initconst = {
- {
- /*
- * asus-nb-wm adds no functionality. The T100TA has a detachable
- * USB kbd, so no hotkeys and it has no WMI rfkill; and loading
- * asus-nb-wm causes the camera LED to turn and _stay_ on.
- */
- .matches = {
- DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
- DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100TA"),
- },
- },
- {
- /* The Asus T200TA has the same issue as the T100TA */
- .matches = {
- DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
- DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T200TA"),
- },
- },
- {} /* Terminating entry */
-};
static int __init asus_nb_wmi_init(void)
{
- if (dmi_check_system(asus_nb_wmi_blacklist))
- return -ENODEV;
-
return asus_wmi_register_driver(&asus_nb_wmi_driver);
}
if (err)
goto err_free_dev;
- result = asus_wmi_get_devstate_simple(asus, ASUS_WMI_DEVID_KBD_DOCK);
- if (result >= 0) {
- input_set_capability(asus->inputdev, EV_SW, SW_TABLET_MODE);
- input_report_switch(asus->inputdev, SW_TABLET_MODE, !result);
- } else if (result != -ENODEV) {
- pr_err("Error checking for keyboard-dock: %d\n", result);
+ if (asus->driver->quirks->use_kbd_dock_devid) {
+ result = asus_wmi_get_devstate_simple(asus, ASUS_WMI_DEVID_KBD_DOCK);
+ if (result >= 0) {
+ input_set_capability(asus->inputdev, EV_SW, SW_TABLET_MODE);
+ input_report_switch(asus->inputdev, SW_TABLET_MODE, !result);
+ } else if (result != -ENODEV) {
+ pr_err("Error checking for keyboard-dock: %d\n", result);
+ }
}
err = input_register_device(asus->inputdev);
*/
if (strcmp(battery->desc->name, "BAT0") != 0 &&
strcmp(battery->desc->name, "BAT1") != 0 &&
+ strcmp(battery->desc->name, "BATC") != 0 &&
strcmp(battery->desc->name, "BATT") != 0)
return -ENODEV;
return;
}
- if (code == NOTIFY_KBD_DOCK_CHANGE) {
+ if (asus->driver->quirks->use_kbd_dock_devid && code == NOTIFY_KBD_DOCK_CHANGE) {
result = asus_wmi_get_devstate_simple(asus,
ASUS_WMI_DEVID_KBD_DOCK);
if (result >= 0) {
bool wmi_backlight_native;
bool wmi_backlight_set_devstate;
bool wmi_force_als_set;
+ bool use_kbd_dock_devid;
int wapf;
/*
* For machines with AMD graphic chips, it will send out WMI event
return ACPI_SUCCESS(status);
}
+/*
+ * There are several laptops (non 2-in-1) models out there which support VGBS,
+ * but simply always return 0, which we translate to SW_TABLET_MODE=1. This in
+ * turn causes userspace (libinput) to suppress events from the builtin
+ * keyboard and touchpad, making the laptop essentially unusable.
+ *
+ * Since the problem of wrongly reporting SW_TABLET_MODE=1 in combination
+ * with libinput, leads to a non-usable system. Where as OTOH many people will
+ * not even notice when SW_TABLET_MODE is not being reported, a DMI based allow
+ * list is used here. This list mainly matches on the chassis-type of 2-in-1s.
+ *
+ * There are also some 2-in-1s which use the intel-vbtn ACPI interface to report
+ * SW_TABLET_MODE with a chassis-type of 8 ("Portable") or 10 ("Notebook"),
+ * these are matched on a per model basis, since many normal laptops with a
+ * possible broken VGBS ACPI-method also use these chassis-types.
+ */
+static const struct dmi_system_id dmi_switches_allow_list[] = {
+ {
+ .matches = {
+ DMI_EXACT_MATCH(DMI_CHASSIS_TYPE, "31" /* Convertible */),
+ },
+ },
+ {
+ .matches = {
+ DMI_EXACT_MATCH(DMI_CHASSIS_TYPE, "32" /* Detachable */),
+ },
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Venue 11 Pro 7130"),
+ },
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP Stream x360 Convertible PC 11"),
+ },
+ },
+ {} /* Array terminator */
+};
+
static bool intel_vbtn_has_switches(acpi_handle handle)
{
- const char *chassis_type = dmi_get_system_info(DMI_CHASSIS_TYPE);
unsigned long long vgbs;
acpi_status status;
- /*
- * Some normal laptops have a VGBS method despite being non-convertible
- * and their VGBS method always returns 0, causing detect_tablet_mode()
- * to report SW_TABLET_MODE=1 to userspace, which causes issues.
- * These laptops have a DMI chassis_type of 9 ("Laptop"), do not report
- * switches on any devices with a DMI chassis_type of 9.
- */
- if (chassis_type && strcmp(chassis_type, "9") == 0)
+ if (!dmi_check_system(dmi_switches_allow_list))
return false;
status = acpi_evaluate_integer(handle, "VGBS", NULL, &vgbs);
static void intel_pmc_core_release(struct device *dev)
{
- /* Nothing to do. */
+ kfree(dev);
}
-static struct platform_device pmc_core_device = {
- .name = "intel_pmc_core",
- .dev = {
- .release = intel_pmc_core_release,
- },
-};
+static struct platform_device *pmc_core_device;
/*
* intel_pmc_core_platform_ids is the list of platforms where we want to
static int __init pmc_core_platform_init(void)
{
+ int retval;
+
/* Skip creating the platform device if ACPI already has a device */
if (acpi_dev_present("INT33A1", NULL, -1))
return -ENODEV;
if (!x86_match_cpu(intel_pmc_core_platform_ids))
return -ENODEV;
- return platform_device_register(&pmc_core_device);
+ pmc_core_device = kzalloc(sizeof(*pmc_core_device), GFP_KERNEL);
+ if (!pmc_core_device)
+ return -ENOMEM;
+
+ pmc_core_device->name = "intel_pmc_core";
+ pmc_core_device->dev.release = intel_pmc_core_release;
+
+ retval = platform_device_register(pmc_core_device);
+ if (retval)
+ kfree(pmc_core_device);
+
+ return retval;
}
static void __exit pmc_core_platform_exit(void)
{
- platform_device_unregister(&pmc_core_device);
+ platform_device_unregister(pmc_core_device);
}
module_init(pmc_core_platform_init);
#define MLXPLAT_CPLD_NR_NONE -1
#define MLXPLAT_CPLD_PSU_DEFAULT_NR 10
#define MLXPLAT_CPLD_PSU_MSNXXXX_NR 4
-#define MLXPLAT_CPLD_PSU_MSNXXXX_NR2 3
#define MLXPLAT_CPLD_FAN1_DEFAULT_NR 11
#define MLXPLAT_CPLD_FAN2_DEFAULT_NR 12
#define MLXPLAT_CPLD_FAN3_DEFAULT_NR 13
},
};
+static struct i2c_board_info mlxplat_mlxcpld_ext_pwr[] = {
+ {
+ I2C_BOARD_INFO("dps460", 0x5b),
+ },
+ {
+ I2C_BOARD_INFO("dps460", 0x5a),
+ },
+};
+
static struct i2c_board_info mlxplat_mlxcpld_fan[] = {
{
I2C_BOARD_INFO("24c32", 0x50),
.label = "pwr3",
.reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET,
.mask = BIT(2),
- .hpdev.brdinfo = &mlxplat_mlxcpld_pwr[0],
- .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR2,
+ .hpdev.brdinfo = &mlxplat_mlxcpld_ext_pwr[0],
+ .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR,
},
{
.label = "pwr4",
.reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET,
.mask = BIT(3),
- .hpdev.brdinfo = &mlxplat_mlxcpld_pwr[1],
- .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR2,
+ .hpdev.brdinfo = &mlxplat_mlxcpld_ext_pwr[1],
+ .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR,
},
};
#define APU2_GPIO_REG_LED3 AMD_FCH_GPIO_REG_GPIO59_DEVSLP1
#define APU2_GPIO_REG_MODESW AMD_FCH_GPIO_REG_GPIO32_GE1
#define APU2_GPIO_REG_SIMSWAP AMD_FCH_GPIO_REG_GPIO33_GE2
-#define APU2_GPIO_REG_MPCIE2 AMD_FCH_GPIO_REG_GPIO59_DEVSLP0
+#define APU2_GPIO_REG_MPCIE2 AMD_FCH_GPIO_REG_GPIO55_DEVSLP0
#define APU2_GPIO_REG_MPCIE3 AMD_FCH_GPIO_REG_GPIO51
/* Order in which the GPIO lines are defined in the register list */
*/
static int hotkey_kthread(void *data)
{
- struct tp_nvram_state s[2];
+ struct tp_nvram_state s[2] = { 0 };
u32 poll_mask, event_mask;
unsigned int si, so;
unsigned long t;
list_for_each_entry(child, &device->children, node) {
acpi_status status = acpi_evaluate_object(child->handle, "_BCL",
NULL, &buffer);
- if (ACPI_FAILURE(status))
+ if (ACPI_FAILURE(status)) {
+ buffer.length = ACPI_ALLOCATE_BUFFER;
continue;
+ }
obj = (union acpi_object *)buffer.pointer;
if (!obj || (obj->type != ACPI_TYPE_PACKAGE)) {
.properties = jumper_ezpad_mini3_props,
};
+static const struct property_entry mpman_converter9_props[] = {
+ PROPERTY_ENTRY_U32("touchscreen-min-x", 8),
+ PROPERTY_ENTRY_U32("touchscreen-min-y", 8),
+ PROPERTY_ENTRY_U32("touchscreen-size-x", 1664),
+ PROPERTY_ENTRY_U32("touchscreen-size-y", 880),
+ PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"),
+ PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"),
+ PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-mpman-converter9.fw"),
+ PROPERTY_ENTRY_U32("silead,max-fingers", 10),
+ { }
+};
+
+static const struct ts_dmi_data mpman_converter9_data = {
+ .acpi_name = "MSSL1680:00",
+ .properties = mpman_converter9_props,
+};
+
static const struct property_entry mpman_mpwin895cl_props[] = {
PROPERTY_ENTRY_U32("touchscreen-min-x", 3),
PROPERTY_ENTRY_U32("touchscreen-min-y", 9),
},
},
{
+ /* MP Man Converter 9 */
+ .driver_data = (void *)&mpman_converter9_data,
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "MPMAN"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Converter9"),
+ },
+ },
+ {
/* MP Man MPWIN895CL */
.driver_data = (void *)&mpman_mpwin895cl_data,
.matches = {
* coalescing neighboring slab objects into a single frag which
* triggers one of hardened usercopy checks.
*/
- if (!recv && page_count(sg_page(sg)) >= 1 && !PageSlab(sg_page(sg)))
+ if (!recv && sendpage_ok(sg_page(sg)))
return;
if (recv) {
be called ifcvf.
config MLX5_VDPA
- bool "MLX5 VDPA support library for ConnectX devices"
- depends on MLX5_CORE
- default n
+ bool
help
Support library for Mellanox VDPA drivers. Provides code that is
common for all types of VDPA drivers. The following drivers are planned:
config MLX5_VDPA_NET
tristate "vDPA driver for ConnectX devices"
- depends on MLX5_VDPA
+ select MLX5_VDPA
+ depends on MLX5_CORE
default n
help
VDPA network driver for ConnectX6 and newer. Provides offloading
if (!mvq->initialized)
return;
- if (query_virtqueue(ndev, mvq, &attr)) {
- mlx5_vdpa_warn(&ndev->mvdev, "failed to query virtqueue\n");
- return;
- }
if (mvq->fw_state != MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY)
return;
if (modify_virtqueue(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND))
mlx5_vdpa_warn(&ndev->mvdev, "modify to suspend failed\n");
+
+ if (query_virtqueue(ndev, mvq, &attr)) {
+ mlx5_vdpa_warn(&ndev->mvdev, "failed to query virtqueue\n");
+ return;
+ }
+ mvq->avail_idx = attr.available_index;
}
static void suspend_vqs(struct mlx5_vdpa_net *ndev)
struct mlx5_virtq_attr attr;
int err;
- if (!mvq->initialized)
- return -EAGAIN;
+ /* If the virtq object was destroyed, use the value saved at
+ * the last minute of suspend_vq. This caters for userspace
+ * that cares about emulating the index after vq is stopped.
+ */
+ if (!mvq->initialized) {
+ state->avail_index = mvq->avail_idx;
+ return 0;
+ }
err = query_virtqueue(ndev, mvq, &attr);
if (err) {
perm_to_iommu_flags(perm));
}
+ if (r)
+ vhost_iotlb_del_range(dev->iotlb, iova, iova + size - 1);
+
return r;
}
struct vhost_dev *dev = &v->vdev;
struct vhost_iotlb *iotlb = dev->iotlb;
struct page **page_list;
- unsigned long list_size = PAGE_SIZE / sizeof(struct page *);
+ struct vm_area_struct **vmas;
unsigned int gup_flags = FOLL_LONGTERM;
- unsigned long npages, cur_base, map_pfn, last_pfn = 0;
- unsigned long locked, lock_limit, pinned, i;
+ unsigned long map_pfn, last_pfn = 0;
+ unsigned long npages, lock_limit;
+ unsigned long i, nmap = 0;
u64 iova = msg->iova;
+ long pinned;
int ret = 0;
if (vhost_iotlb_itree_first(iotlb, msg->iova,
msg->iova + msg->size - 1))
return -EEXIST;
- page_list = (struct page **) __get_free_page(GFP_KERNEL);
- if (!page_list)
- return -ENOMEM;
-
if (msg->perm & VHOST_ACCESS_WO)
gup_flags |= FOLL_WRITE;
if (!npages)
return -EINVAL;
+ page_list = kvmalloc_array(npages, sizeof(struct page *), GFP_KERNEL);
+ vmas = kvmalloc_array(npages, sizeof(struct vm_area_struct *),
+ GFP_KERNEL);
+ if (!page_list || !vmas) {
+ ret = -ENOMEM;
+ goto free;
+ }
+
mmap_read_lock(dev->mm);
- locked = atomic64_add_return(npages, &dev->mm->pinned_vm);
lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-
- if (locked > lock_limit) {
+ if (npages + atomic64_read(&dev->mm->pinned_vm) > lock_limit) {
ret = -ENOMEM;
- goto out;
+ goto unlock;
}
- cur_base = msg->uaddr & PAGE_MASK;
- iova &= PAGE_MASK;
+ pinned = pin_user_pages(msg->uaddr & PAGE_MASK, npages, gup_flags,
+ page_list, vmas);
+ if (npages != pinned) {
+ if (pinned < 0) {
+ ret = pinned;
+ } else {
+ unpin_user_pages(page_list, pinned);
+ ret = -ENOMEM;
+ }
+ goto unlock;
+ }
- while (npages) {
- pinned = min_t(unsigned long, npages, list_size);
- ret = pin_user_pages(cur_base, pinned,
- gup_flags, page_list, NULL);
- if (ret != pinned)
- goto out;
-
- if (!last_pfn)
- map_pfn = page_to_pfn(page_list[0]);
-
- for (i = 0; i < ret; i++) {
- unsigned long this_pfn = page_to_pfn(page_list[i]);
- u64 csize;
-
- if (last_pfn && (this_pfn != last_pfn + 1)) {
- /* Pin a contiguous chunk of memory */
- csize = (last_pfn - map_pfn + 1) << PAGE_SHIFT;
- if (vhost_vdpa_map(v, iova, csize,
- map_pfn << PAGE_SHIFT,
- msg->perm))
- goto out;
- map_pfn = this_pfn;
- iova += csize;
+ iova &= PAGE_MASK;
+ map_pfn = page_to_pfn(page_list[0]);
+
+ /* One more iteration to avoid extra vdpa_map() call out of loop. */
+ for (i = 0; i <= npages; i++) {
+ unsigned long this_pfn;
+ u64 csize;
+
+ /* The last chunk may have no valid PFN next to it */
+ this_pfn = i < npages ? page_to_pfn(page_list[i]) : -1UL;
+
+ if (last_pfn && (this_pfn == -1UL ||
+ this_pfn != last_pfn + 1)) {
+ /* Pin a contiguous chunk of memory */
+ csize = last_pfn - map_pfn + 1;
+ ret = vhost_vdpa_map(v, iova, csize << PAGE_SHIFT,
+ map_pfn << PAGE_SHIFT,
+ msg->perm);
+ if (ret) {
+ /*
+ * Unpin the rest chunks of memory on the
+ * flight with no corresponding vdpa_map()
+ * calls having been made yet. On the other
+ * hand, vdpa_unmap() in the failure path
+ * is in charge of accounting the number of
+ * pinned pages for its own.
+ * This asymmetrical pattern of accounting
+ * is for efficiency to pin all pages at
+ * once, while there is no other callsite
+ * of vdpa_map() than here above.
+ */
+ unpin_user_pages(&page_list[nmap],
+ npages - nmap);
+ goto out;
}
-
- last_pfn = this_pfn;
+ atomic64_add(csize, &dev->mm->pinned_vm);
+ nmap += csize;
+ iova += csize << PAGE_SHIFT;
+ map_pfn = this_pfn;
}
-
- cur_base += ret << PAGE_SHIFT;
- npages -= ret;
+ last_pfn = this_pfn;
}
- /* Pin the rest chunk */
- ret = vhost_vdpa_map(v, iova, (last_pfn - map_pfn + 1) << PAGE_SHIFT,
- map_pfn << PAGE_SHIFT, msg->perm);
+ WARN_ON(nmap != npages);
out:
- if (ret) {
+ if (ret)
vhost_vdpa_unmap(v, msg->iova, msg->size);
- atomic64_sub(npages, &dev->mm->pinned_vm);
- }
+unlock:
mmap_read_unlock(dev->mm);
- free_page((unsigned long)page_list);
+free:
+ kvfree(vmas);
+ kvfree(page_list);
return ret;
}
err_init_iotlb:
vhost_dev_cleanup(&v->vdev);
+ kfree(vqs);
err:
atomic_dec(&v->opened);
return r;
vring_used_t __user *used)
{
+ /* If an IOTLB device is present, the vring addresses are
+ * GIOVAs. Access validation occurs at prefetch time. */
+ if (vq->iotlb)
+ return true;
+
return access_ok(desc, vhost_get_desc_size(vq, num)) &&
access_ok(avail, vhost_get_avail_size(vq, num)) &&
access_ok(used, vhost_get_used_size(vq, num));
}
EXPORT_SYMBOL_GPL(vhost_log_access_ok);
+static bool vq_log_used_access_ok(struct vhost_virtqueue *vq,
+ void __user *log_base,
+ bool log_used,
+ u64 log_addr)
+{
+ /* If an IOTLB device is present, log_addr is a GIOVA that
+ * will never be logged by log_used(). */
+ if (vq->iotlb)
+ return true;
+
+ return !log_used || log_access_ok(log_base, log_addr,
+ vhost_get_used_size(vq, vq->num));
+}
+
/* Verify access for write logging. */
/* Caller should have vq mutex and device mutex */
static bool vq_log_access_ok(struct vhost_virtqueue *vq,
{
return vq_memory_access_ok(log_base, vq->umem,
vhost_has_feature(vq, VHOST_F_LOG_ALL)) &&
- (!vq->log_used || log_access_ok(log_base, vq->log_addr,
- vhost_get_used_size(vq, vq->num)));
+ vq_log_used_access_ok(vq, log_base, vq->log_used, vq->log_addr);
}
/* Can we start vq? */
if (!vq_log_access_ok(vq, vq->log_base))
return false;
- /* Access validation occurs at prefetch time with IOTLB */
- if (vq->iotlb)
- return true;
-
return vq_access_ok(vq, vq->num, vq->desc, vq->avail, vq->used);
}
EXPORT_SYMBOL_GPL(vhost_vq_access_ok);
return -EINVAL;
/* Also validate log access for used ring if enabled. */
- if ((a.flags & (0x1 << VHOST_VRING_F_LOG)) &&
- !log_access_ok(vq->log_base, a.log_guest_addr,
- sizeof *vq->used +
- vq->num * sizeof *vq->used->ring))
+ if (!vq_log_used_access_ok(vq, vq->log_base,
+ a.flags & (0x1 << VHOST_VRING_F_LOG),
+ a.log_guest_addr))
return -EINVAL;
}
static void afs_setattr_success(struct afs_operation *op)
{
- struct inode *inode = &op->file[0].vnode->vfs_inode;
+ struct afs_vnode_param *vp = &op->file[0];
+ struct inode *inode = &vp->vnode->vfs_inode;
+ loff_t old_i_size = i_size_read(inode);
+
+ op->setattr.old_i_size = old_i_size;
+ afs_vnode_commit_status(op, vp);
+ /* inode->i_size has now been changed. */
+
+ if (op->setattr.attr->ia_valid & ATTR_SIZE) {
+ loff_t size = op->setattr.attr->ia_size;
+ if (size > old_i_size)
+ pagecache_isize_extended(inode, old_i_size, size);
+ }
+}
+
+static void afs_setattr_edit_file(struct afs_operation *op)
+{
+ struct afs_vnode_param *vp = &op->file[0];
+ struct inode *inode = &vp->vnode->vfs_inode;
- afs_vnode_commit_status(op, &op->file[0]);
if (op->setattr.attr->ia_valid & ATTR_SIZE) {
- loff_t i_size = inode->i_size, size = op->setattr.attr->ia_size;
- if (size > i_size)
- pagecache_isize_extended(inode, i_size, size);
- truncate_pagecache(inode, size);
+ loff_t size = op->setattr.attr->ia_size;
+ loff_t i_size = op->setattr.old_i_size;
+
+ if (size < i_size)
+ truncate_pagecache(inode, size);
}
}
.issue_afs_rpc = afs_fs_setattr,
.issue_yfs_rpc = yfs_fs_setattr,
.success = afs_setattr_success,
+ .edit_dir = afs_setattr_edit_file,
};
/*
if (S_ISREG(vnode->vfs_inode.i_mode))
filemap_write_and_wait(vnode->vfs_inode.i_mapping);
+ /* Prevent any new writebacks from starting whilst we do this. */
+ down_write(&vnode->validate_lock);
+
op = afs_alloc_operation(((attr->ia_valid & ATTR_FILE) ?
afs_file_key(attr->ia_file) : NULL),
vnode->volume);
- if (IS_ERR(op))
- return PTR_ERR(op);
+ if (IS_ERR(op)) {
+ ret = PTR_ERR(op);
+ goto out_unlock;
+ }
afs_op_set_vnode(op, 0, vnode);
op->setattr.attr = attr;
op->file[0].update_ctime = 1;
op->ops = &afs_setattr_operation;
- return afs_do_sync_operation(op);
+ ret = afs_do_sync_operation(op);
+
+out_unlock:
+ up_write(&vnode->validate_lock);
+ _leave(" = %d", ret);
+ return ret;
}
} store;
struct {
struct iattr *attr;
+ loff_t old_i_size;
} setattr;
struct afs_acl *acl;
struct yfs_acl *yacl;
int afs_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
+ struct afs_vnode *vnode = AFS_FS_I(mapping->host);
pgoff_t start, end, next;
int ret;
_enter("");
+ /* We have to be careful as we can end up racing with setattr()
+ * truncating the pagecache since the caller doesn't take a lock here
+ * to prevent it.
+ */
+ if (wbc->sync_mode == WB_SYNC_ALL)
+ down_read(&vnode->validate_lock);
+ else if (!down_read_trylock(&vnode->validate_lock))
+ return 0;
+
if (wbc->range_cyclic) {
start = mapping->writeback_index;
end = -1;
ret = afs_writepages_region(mapping, wbc, start, end, &next);
}
+ up_read(&vnode->validate_lock);
_leave(" = %d", ret);
return ret;
}
#include "exfat_raw.h"
#include "exfat_fs.h"
-#define EXFAT_CACHE_VALID 0
#define EXFAT_MAX_CACHE 16
struct exfat_cache {
kmem_cache_destroy(exfat_cachep);
}
-void exfat_cache_init_inode(struct inode *inode)
-{
- struct exfat_inode_info *ei = EXFAT_I(inode);
-
- spin_lock_init(&ei->cache_lru_lock);
- ei->nr_caches = 0;
- ei->cache_valid_id = EXFAT_CACHE_VALID + 1;
- INIT_LIST_HEAD(&ei->cache_lru);
-}
-
static inline struct exfat_cache *exfat_cache_alloc(void)
{
return kmem_cache_alloc(exfat_cachep, GFP_NOFS);
struct rcu_head rcu;
};
+#define EXFAT_CACHE_VALID 0
+
/*
* EXFAT file system inode in-memory data
*/
/* cache.c */
int exfat_cache_init(void);
void exfat_cache_shutdown(void);
-void exfat_cache_init_inode(struct inode *inode);
void exfat_cache_inval_inode(struct inode *inode);
int exfat_get_cluster(struct inode *inode, unsigned int cluster,
unsigned int *fclus, unsigned int *dclus,
ei->i_crtime = info->crtime;
inode->i_atime = info->atime;
- exfat_cache_init_inode(inode);
-
return 0;
}
i_pos = exfat_make_i_pos(&info);
inode = exfat_build_inode(sb, &info, i_pos);
- if (IS_ERR(inode))
+ err = PTR_ERR_OR_ZERO(inode);
+ if (err)
goto unlock;
inode_inc_iversion(inode);
i_pos = exfat_make_i_pos(&info);
inode = exfat_build_inode(sb, &info, i_pos);
- if (IS_ERR(inode)) {
- err = PTR_ERR(inode);
+ err = PTR_ERR_OR_ZERO(inode);
+ if (err)
goto unlock;
- }
i_mode = inode->i_mode;
alias = d_find_alias(inode);
i_pos = exfat_make_i_pos(&info);
inode = exfat_build_inode(sb, &info, i_pos);
- if (IS_ERR(inode)) {
- err = PTR_ERR(inode);
+ err = PTR_ERR_OR_ZERO(inode);
+ if (err)
goto unlock;
- }
inode_inc_iversion(inode);
inode->i_mtime = inode->i_atime = inode->i_ctime =
inode->i_mtime = inode->i_atime = inode->i_ctime = ei->i_crtime =
current_time(inode);
exfat_truncate_atime(&inode->i_atime);
- exfat_cache_init_inode(inode);
return 0;
}
{
struct exfat_inode_info *ei = (struct exfat_inode_info *)foo;
+ spin_lock_init(&ei->cache_lru_lock);
+ ei->nr_caches = 0;
+ ei->cache_valid_id = EXFAT_CACHE_VALID + 1;
+ INIT_LIST_HEAD(&ei->cache_lru);
INIT_HLIST_NODE(&ei->i_hash_fat);
inode_init_once(&ei->vfs_inode);
}
return 1;
}
+/* We know we have a pipe buffer, but maybe it's empty? */
+static inline bool eat_empty_buffer(struct pipe_inode_info *pipe)
+{
+ unsigned int tail = pipe->tail;
+ unsigned int mask = pipe->ring_size - 1;
+ struct pipe_buffer *buf = &pipe->bufs[tail & mask];
+
+ if (unlikely(!buf->len)) {
+ pipe_buf_release(pipe, buf);
+ pipe->tail = tail+1;
+ return true;
+ }
+
+ return false;
+}
+
/**
* splice_from_pipe_next - wait for some data to splice from
* @pipe: pipe to splice from
if (signal_pending(current))
return -ERESTARTSYS;
+repeat:
while (pipe_empty(pipe->head, pipe->tail)) {
if (!pipe->writers)
return 0;
pipe_wait_readable(pipe);
}
+ if (eat_empty_buffer(pipe))
+ goto repeat;
+
return 1;
}
#define BTF \
.BTF : AT(ADDR(.BTF) - LOAD_OFFSET) { \
__start_BTF = .; \
- *(.BTF) \
+ KEEP(*(.BTF)) \
__stop_BTF = .; \
} \
. = ALIGN(4); \
u64 ts2;
u16 op;
bool polling;
+ /* Track the max comp handlers */
+ refcount_t refcnt;
};
struct mlx5_pas {
int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size,
void *out, int out_size);
void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome);
+bool mlx5_cmd_is_down(struct mlx5_core_dev *dev);
int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type);
int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn);
#include <linux/rcupdate.h>
#include <linux/once.h>
#include <linux/fs.h>
+#include <linux/mm.h>
#include <linux/sockptr.h>
#include <uapi/linux/net.h>
#define net_get_random_once_wait(buf, nbytes) \
get_random_once_wait((buf), (nbytes))
+/*
+ * E.g. XFS meta- & log-data is in slab pages, or bcache meta
+ * data pages, or other high order pages allocated by
+ * __get_free_pages() without __GFP_COMP, which have a page_count
+ * of 0 and/or have PageSlab() set. We cannot use send_page for
+ * those, as that does get_page(); put_page(); and would cause
+ * either a VM_BUG directly, or __page_cache_release a page that
+ * would actually still be referenced by someone, leading to some
+ * obscure delayed Oops somewhere else.
+ */
+static inline bool sendpage_ok(struct page *page)
+{
+ return !PageSlab(page) && page_count(page) >= 1;
+}
+
int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec,
size_t num, size_t len);
int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg,
* @udp_tunnel_nic: UDP tunnel offload state
* @xdp_state: stores info on attached XDP BPF programs
*
+ * @nested_level: Used as as a parameter of spin_lock_nested() of
+ * dev->addr_list_lock.
+ * @unlink_list: As netif_addr_lock() can be called recursively,
+ * keep a list of interfaces to be deleted.
+ *
* FIXME: cleanup struct net_device such that network protocol info
* moves out.
*/
unsigned short type;
unsigned short hard_header_len;
unsigned char min_header_len;
+ unsigned char name_assign_type;
unsigned short needed_headroom;
unsigned short needed_tailroom;
unsigned char addr_len;
unsigned char upper_level;
unsigned char lower_level;
+
unsigned short neigh_priv_len;
unsigned short dev_id;
unsigned short dev_port;
spinlock_t addr_list_lock;
- unsigned char name_assign_type;
- bool uc_promisc;
+
struct netdev_hw_addr_list uc;
struct netdev_hw_addr_list mc;
struct netdev_hw_addr_list dev_addrs;
#ifdef CONFIG_SYSFS
struct kset *queues_kset;
#endif
+#ifdef CONFIG_LOCKDEP
+ struct list_head unlink_list;
+#endif
unsigned int promiscuity;
unsigned int allmulti;
+ bool uc_promisc;
+#ifdef CONFIG_LOCKDEP
+ unsigned char nested_level;
+#endif
/* Protocol-specific pointers */
static inline void netif_addr_lock(struct net_device *dev)
{
- spin_lock(&dev->addr_list_lock);
-}
+ unsigned char nest_level = 0;
-static inline void netif_addr_lock_nested(struct net_device *dev)
-{
- spin_lock_nested(&dev->addr_list_lock, dev->lower_level);
+#ifdef CONFIG_LOCKDEP
+ nest_level = dev->nested_level;
+#endif
+ spin_lock_nested(&dev->addr_list_lock, nest_level);
}
static inline void netif_addr_lock_bh(struct net_device *dev)
{
- spin_lock_bh(&dev->addr_list_lock);
+ unsigned char nest_level = 0;
+
+#ifdef CONFIG_LOCKDEP
+ nest_level = dev->nested_level;
+#endif
+ local_bh_disable();
+ spin_lock_nested(&dev->addr_list_lock, nest_level);
}
static inline void netif_addr_unlock(struct net_device *dev)
extern int dev_tx_weight;
extern int gro_normal_batch;
+enum {
+ NESTED_SYNC_IMM_BIT,
+ NESTED_SYNC_TODO_BIT,
+};
+
+#define __NESTED_SYNC_BIT(bit) ((u32)1 << (bit))
+#define __NESTED_SYNC(name) __NESTED_SYNC_BIT(NESTED_SYNC_ ## name ## _BIT)
+
+#define NESTED_SYNC_IMM __NESTED_SYNC(IMM)
+#define NESTED_SYNC_TODO __NESTED_SYNC(TODO)
+
+struct netdev_nested_priv {
+ unsigned char flags;
+ void *data;
+};
+
bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev);
struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
struct list_head **iter);
struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
struct list_head **iter);
+#ifdef CONFIG_LOCKDEP
+static LIST_HEAD(net_unlink_list);
+
+static inline void net_unlink_todo(struct net_device *dev)
+{
+ if (list_empty(&dev->unlink_list))
+ list_add_tail(&dev->unlink_list, &net_unlink_list);
+}
+#endif
+
/* iterate through upper list, must be called under RCU read lock */
#define netdev_for_each_upper_dev_rcu(dev, updev, iter) \
for (iter = &(dev)->adj_list.upper, \
int netdev_walk_all_upper_dev_rcu(struct net_device *dev,
int (*fn)(struct net_device *upper_dev,
- void *data),
- void *data);
+ struct netdev_nested_priv *priv),
+ struct netdev_nested_priv *priv);
bool netdev_has_upper_dev_all_rcu(struct net_device *dev,
struct net_device *upper_dev);
struct list_head **iter);
int netdev_walk_all_lower_dev(struct net_device *dev,
int (*fn)(struct net_device *lower_dev,
- void *data),
- void *data);
+ struct netdev_nested_priv *priv),
+ struct netdev_nested_priv *priv);
int netdev_walk_all_lower_dev_rcu(struct net_device *dev,
int (*fn)(struct net_device *lower_dev,
- void *data),
- void *data);
+ struct netdev_nested_priv *priv),
+ struct netdev_nested_priv *priv);
void *netdev_adjacent_get_private(struct list_head *adj_list);
void *netdev_lower_get_first_private_rcu(struct net_device *dev);
#define AMD_FCH_GPIO_REG_GPIO49 0x40
#define AMD_FCH_GPIO_REG_GPIO50 0x41
#define AMD_FCH_GPIO_REG_GPIO51 0x42
-#define AMD_FCH_GPIO_REG_GPIO59_DEVSLP0 0x43
+#define AMD_FCH_GPIO_REG_GPIO55_DEVSLP0 0x43
#define AMD_FCH_GPIO_REG_GPIO57 0x44
#define AMD_FCH_GPIO_REG_GPIO58 0x45
#define AMD_FCH_GPIO_REG_GPIO59_DEVSLP1 0x46
struct nlattr *est, struct tc_action **a,
const struct tc_action_ops *ops, int bind,
u32 flags);
-void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a);
-
void tcf_idr_cleanup(struct tc_action_net *tn, u32 index);
int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index,
struct tc_action **a, int bind);
* @cmd: command identifier
* @internal_flags: flags used by the family
* @flags: flags
+ * @validate: validation flags from enum genl_validate_flags
* @doit: standard command callback
* @start: start callback for dumps
* @dumpit: callback for dumpers
bool forwarding)
{
struct net *net = dev_net(dst->dev);
+ unsigned int mtu;
if (net->ipv4.sysctl_ip_fwd_use_pmtu ||
ip_mtu_locked(dst) ||
!forwarding)
return dst_mtu(dst);
+ /* 'forwarding = true' case should always honour route mtu */
+ mtu = dst_metric_raw(dst, RTAX_MTU);
+ if (mtu)
+ return mtu;
+
return min(READ_ONCE(dst->dev->mtu), IP_MAX_MTU);
}
int netlink_policy_dump_start(const struct nla_policy *policy,
unsigned int maxtype,
unsigned long *state);
-bool netlink_policy_dump_loop(unsigned long *state);
+bool netlink_policy_dump_loop(unsigned long state);
int netlink_policy_dump_write(struct sk_buff *skb, unsigned long state);
+void netlink_policy_dump_free(unsigned long state);
#endif
static inline int xfrm_replay_clone(struct xfrm_state *x,
struct xfrm_state *orig)
{
- x->replay_esn = kzalloc(xfrm_replay_state_esn_len(orig->replay_esn),
+
+ x->replay_esn = kmemdup(orig->replay_esn,
+ xfrm_replay_state_esn_len(orig->replay_esn),
GFP_KERNEL);
if (!x->replay_esn)
return -ENOMEM;
-
- x->replay_esn->bmp_len = orig->replay_esn->bmp_len;
- x->replay_esn->replay_window = orig->replay_esn->replay_window;
-
- x->preplay_esn = kmemdup(x->replay_esn,
- xfrm_replay_state_esn_len(x->replay_esn),
+ x->preplay_esn = kmemdup(orig->preplay_esn,
+ xfrm_replay_state_esn_len(orig->preplay_esn),
GFP_KERNEL);
- if (!x->preplay_esn) {
- kfree(x->replay_esn);
+ if (!x->preplay_esn)
return -ENOMEM;
- }
return 0;
}
#define ANA_SG_CONFIG_REG_3_LIST_LENGTH_M GENMASK(18, 16)
#define ANA_SG_CONFIG_REG_3_LIST_LENGTH_X(x) (((x) & GENMASK(18, 16)) >> 16)
#define ANA_SG_CONFIG_REG_3_GATE_ENABLE BIT(20)
-#define ANA_SG_CONFIG_REG_3_INIT_IPS(x) (((x) << 24) & GENMASK(27, 24))
-#define ANA_SG_CONFIG_REG_3_INIT_IPS_M GENMASK(27, 24)
-#define ANA_SG_CONFIG_REG_3_INIT_IPS_X(x) (((x) & GENMASK(27, 24)) >> 24)
-#define ANA_SG_CONFIG_REG_3_INIT_GATE_STATE BIT(28)
+#define ANA_SG_CONFIG_REG_3_INIT_IPS(x) (((x) << 21) & GENMASK(24, 21))
+#define ANA_SG_CONFIG_REG_3_INIT_IPS_M GENMASK(24, 21)
+#define ANA_SG_CONFIG_REG_3_INIT_IPS_X(x) (((x) & GENMASK(24, 21)) >> 21)
+#define ANA_SG_CONFIG_REG_3_INIT_GATE_STATE BIT(25)
#define ANA_SG_GCL_GS_CONFIG_RSZ 0x4
RXRPC_BUSY = 6, /* -r: server busy received [terminal] */
RXRPC_LOCAL_ERROR = 7, /* -r: local error generated [terminal] */
RXRPC_NEW_CALL = 8, /* -r: [Service] new incoming call notification */
- RXRPC_ACCEPT = 9, /* s-: [Service] accept request */
RXRPC_EXCLUSIVE_CALL = 10, /* s-: Call should be on exclusive connection */
RXRPC_UPGRADE_SERVICE = 11, /* s-: Request service upgrade for client call */
RXRPC_TX_LENGTH = 12, /* s-: Total length of Tx data */
RXRPC_SET_CALL_TIMEOUT = 13, /* s-: Set one or more call timeouts */
+ RXRPC_CHARGE_ACCEPT = 14, /* s-: Charge the accept pool with a user call ID */
RXRPC__SUPPORTED
};
LINUX_MIB_TCPTIMEOUTREHASH, /* TCPTimeoutRehash */
LINUX_MIB_TCPDUPLICATEDATAREHASH, /* TCPDuplicateDataRehash */
LINUX_MIB_TCPDSACKRECVSEGS, /* TCPDSACKRecvSegs */
+ LINUX_MIB_TCPDSACKIGNOREDDUBIOUS, /* TCPDSACKIgnoredDubious */
__LINUX_MIB_MAX
};
})
#define gfn_to_virt(m) (__va(gfn_to_pfn(m) << XEN_PAGE_SHIFT))
+#define percpu_to_gfn(v) \
+ (pfn_to_gfn(per_cpu_ptr_to_phys(v) >> XEN_PAGE_SHIFT))
+
/* Only used in PV code. But ARM guests are always HVM. */
static inline xmaddr_t arbitrary_virt_to_machine(void *vaddr)
{
static int __init btf_vmlinux_init(void)
{
- if (!__start_BTF)
+ bin_attr_btf_vmlinux.size = __stop_BTF - __start_BTF;
+
+ if (!__start_BTF || bin_attr_btf_vmlinux.size == 0)
return 0;
btf_kobj = kobject_create_and_add("btf", kernel_kobj);
if (!btf_kobj)
return -ENOMEM;
- bin_attr_btf_vmlinux.size = __stop_BTF - __start_BTF;
-
return sysfs_create_bin_file(btf_kobj, &bin_attr_btf_vmlinux);
}
bool src_known = tnum_subreg_is_const(src_reg->var_off);
bool dst_known = tnum_subreg_is_const(dst_reg->var_off);
struct tnum var32_off = tnum_subreg(dst_reg->var_off);
- s32 smin_val = src_reg->smin_value;
- u32 umin_val = src_reg->umin_value;
+ s32 smin_val = src_reg->s32_min_value;
+ u32 umin_val = src_reg->u32_min_value;
/* Assuming scalar64_min_max_or will be called so it is safe
* to skip updating register for known case.
/* ORing two positives gives a positive, so safe to
* cast result into s64.
*/
- dst_reg->s32_min_value = dst_reg->umin_value;
- dst_reg->s32_max_value = dst_reg->umax_value;
+ dst_reg->s32_min_value = dst_reg->u32_min_value;
+ dst_reg->s32_max_value = dst_reg->u32_max_value;
}
}
#include <linux/cred.h>
#include <linux/file.h>
#include <linux/fdtable.h>
+#include <linux/fs_struct.h>
#include <linux/workqueue.h>
#include <linux/security.h>
#include <linux/mount.h>
spin_unlock_irq(¤t->sighand->siglock);
/*
+ * Initial kernel threads share ther FS with init, in order to
+ * get the init root directory. But we've now created a new
+ * thread that is going to execve a user process and has its own
+ * 'struct fs_struct'. Reset umask to the default.
+ */
+ current->fs->umask = 0022;
+
+ /*
* Our parent (unbound workqueue) runs with elevated scheduling
* priority. Avoid propagating that into the userspace child.
*/
return 1;
/*
- * The trick starts.
- *
* What we want to do is to check whether this page may
* have been pinned by the parent process. If so,
* instead of wrprotect the pte on both sides, we copy
* the pinned page won't be randomly replaced in the
* future.
*
- * To achieve this, we do the following:
- *
- * 1. Write-protect the pte if it's writable. This is
- * to protect concurrent write fast-gup with
- * FOLL_PIN, so that we'll fail the fast-gup with
- * the write bit removed.
- *
- * 2. Check page_maybe_dma_pinned() to see whether this
- * page may have been pinned.
- *
- * The order of these steps is important to serialize
- * against the fast-gup code (gup_pte_range()) on the
- * pte check and try_grab_compound_head(), so that
- * we'll make sure either we'll capture that fast-gup
- * so we'll copy the pinned page here, or we'll fail
- * that fast-gup.
- *
- * NOTE! Even if we don't end up copying the page,
- * we won't undo this wrprotect(), because the normal
- * reference copy will need it anyway.
- */
- if (pte_write(pte))
- ptep_set_wrprotect(src_mm, addr, src_pte);
-
- /*
- * These are the "normally we can just copy by reference"
- * checks.
+ * The page pinning checks are just "has this mm ever
+ * seen pinning", along with the (inexact) check of
+ * the page count. That might give false positives for
+ * for pinning, but it will work correctly.
*/
if (likely(!atomic_read(&src_mm->has_pinned)))
return 1;
if (likely(!page_maybe_dma_pinned(page)))
return 1;
- /*
- * Uhhuh. It looks like the page might be a pinned page,
- * and we actually need to copy it. Now we can set the
- * source pte back to being writable.
- */
- if (pte_write(pte))
- set_pte_at(src_mm, addr, src_pte, pte);
-
new_page = *prealloc;
if (!new_page)
return -EAGAIN;
}
}
-static int br_chk_addr_ip(struct net_device *dev, void *data)
+static int br_chk_addr_ip(struct net_device *dev,
+ struct netdev_nested_priv *priv)
{
- __be32 ip = *(__be32 *)data;
+ __be32 ip = *(__be32 *)priv->data;
struct in_device *in_dev;
__be32 addr = 0;
static bool br_is_local_ip(struct net_device *dev, __be32 ip)
{
- if (br_chk_addr_ip(dev, &ip))
+ struct netdev_nested_priv priv = {
+ .data = (void *)&ip,
+ };
+
+ if (br_chk_addr_ip(dev, &priv))
return true;
/* check if ip is configured on upper dev */
- if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip, &ip))
+ if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip, &priv))
return true;
return false;
}
}
-static int br_chk_addr_ip6(struct net_device *dev, void *data)
+static int br_chk_addr_ip6(struct net_device *dev,
+ struct netdev_nested_priv *priv)
{
- struct in6_addr *addr = (struct in6_addr *)data;
+ struct in6_addr *addr = (struct in6_addr *)priv->data;
if (ipv6_chk_addr(dev_net(dev), addr, dev, 0))
return 1;
static bool br_is_local_ip6(struct net_device *dev, struct in6_addr *addr)
{
- if (br_chk_addr_ip6(dev, addr))
+ struct netdev_nested_priv priv = {
+ .data = (void *)addr,
+ };
+
+ if (br_chk_addr_ip6(dev, &priv))
return true;
/* check if ip is configured on upper dev */
- if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip6, addr))
+ if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip6, &priv))
return true;
return false;
if (!do_all)
if (test_bit(BR_FDB_STATIC, &f->flags) ||
+ (test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &f->flags) &&
+ !test_bit(BR_FDB_OFFLOADED, &f->flags)) ||
(vid && f->key.vlan_id != vid))
continue;
u32 filter_mask, const struct net_device *dev)
{
u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN;
+ struct nlattr *af = NULL;
struct net_bridge *br;
struct ifinfomsg *hdr;
struct nlmsghdr *nlh;
nla_nest_end(skb, nest);
}
+ if (filter_mask & (RTEXT_FILTER_BRVLAN |
+ RTEXT_FILTER_BRVLAN_COMPRESSED |
+ RTEXT_FILTER_MRP)) {
+ af = nla_nest_start_noflag(skb, IFLA_AF_SPEC);
+ if (!af)
+ goto nla_put_failure;
+ }
+
/* Check if the VID information is requested */
if ((filter_mask & RTEXT_FILTER_BRVLAN) ||
(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) {
struct net_bridge_vlan_group *vg;
- struct nlattr *af;
int err;
/* RCU needed because of the VLAN locking rules (rcu || rtnl) */
rcu_read_unlock();
goto done;
}
- af = nla_nest_start_noflag(skb, IFLA_AF_SPEC);
- if (!af) {
- rcu_read_unlock();
- goto nla_put_failure;
- }
if (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)
err = br_fill_ifvlaninfo_compressed(skb, vg);
else
rcu_read_unlock();
if (err)
goto nla_put_failure;
-
- nla_nest_end(skb, af);
}
if (filter_mask & RTEXT_FILTER_MRP) {
- struct nlattr *af;
int err;
if (!br_mrp_enabled(br) || port)
goto done;
- af = nla_nest_start_noflag(skb, IFLA_AF_SPEC);
- if (!af)
- goto nla_put_failure;
-
rcu_read_lock();
err = br_mrp_fill_info(skb, br);
rcu_read_unlock();
if (err)
goto nla_put_failure;
-
- nla_nest_end(skb, af);
}
done:
+ if (af)
+ nla_nest_end(skb, af);
nlmsg_end(skb, nlh);
return 0;
}
static int br_vlan_is_bind_vlan_dev_fn(struct net_device *dev,
- __always_unused void *data)
+ __always_unused struct netdev_nested_priv *priv)
{
return br_vlan_is_bind_vlan_dev(dev);
}
};
static int br_vlan_match_bind_vlan_dev_fn(struct net_device *dev,
- void *data_in)
+ struct netdev_nested_priv *priv)
{
- struct br_vlan_bind_walk_data *data = data_in;
+ struct br_vlan_bind_walk_data *data = priv->data;
int found = 0;
if (br_vlan_is_bind_vlan_dev(dev) &&
struct br_vlan_bind_walk_data data = {
.vid = vid,
};
+ struct netdev_nested_priv priv = {
+ .data = (void *)&data,
+ };
rcu_read_lock();
netdev_walk_all_upper_dev_rcu(dev, br_vlan_match_bind_vlan_dev_fn,
- &data);
+ &priv);
rcu_read_unlock();
return data.result;
};
static int br_vlan_link_state_change_fn(struct net_device *vlan_dev,
- void *data_in)
+ struct netdev_nested_priv *priv)
{
- struct br_vlan_link_state_walk_data *data = data_in;
+ struct br_vlan_link_state_walk_data *data = priv->data;
if (br_vlan_is_bind_vlan_dev(vlan_dev))
br_vlan_set_vlan_dev_state(data->br, vlan_dev);
struct br_vlan_link_state_walk_data data = {
.br = br
};
+ struct netdev_nested_priv priv = {
+ .data = (void *)&data,
+ };
rcu_read_lock();
netdev_walk_all_upper_dev_rcu(dev, br_vlan_link_state_change_fn,
- &data);
+ &priv);
rcu_read_unlock();
}
* coalescing neighboring slab objects into a single frag which
* triggers one of hardened usercopy checks.
*/
- if (page_count(page) >= 1 && !PageSlab(page))
+ if (sendpage_ok(page))
sendpage = sock->ops->sendpage;
else
sendpage = sock_no_sendpage;
return NULL;
}
-static int ____netdev_has_upper_dev(struct net_device *upper_dev, void *data)
+static int ____netdev_has_upper_dev(struct net_device *upper_dev,
+ struct netdev_nested_priv *priv)
{
- struct net_device *dev = data;
+ struct net_device *dev = (struct net_device *)priv->data;
return upper_dev == dev;
}
bool netdev_has_upper_dev(struct net_device *dev,
struct net_device *upper_dev)
{
+ struct netdev_nested_priv priv = {
+ .data = (void *)upper_dev,
+ };
+
ASSERT_RTNL();
return netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev,
- upper_dev);
+ &priv);
}
EXPORT_SYMBOL(netdev_has_upper_dev);
bool netdev_has_upper_dev_all_rcu(struct net_device *dev,
struct net_device *upper_dev)
{
+ struct netdev_nested_priv priv = {
+ .data = (void *)upper_dev,
+ };
+
return !!netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev,
- upper_dev);
+ &priv);
}
EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu);
static int __netdev_walk_all_upper_dev(struct net_device *dev,
int (*fn)(struct net_device *dev,
- void *data),
- void *data)
+ struct netdev_nested_priv *priv),
+ struct netdev_nested_priv *priv)
{
struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
while (1) {
if (now != dev) {
- ret = fn(now, data);
+ ret = fn(now, priv);
if (ret)
return ret;
}
int netdev_walk_all_upper_dev_rcu(struct net_device *dev,
int (*fn)(struct net_device *dev,
- void *data),
- void *data)
+ struct netdev_nested_priv *priv),
+ struct netdev_nested_priv *priv)
{
struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
while (1) {
if (now != dev) {
- ret = fn(now, data);
+ ret = fn(now, priv);
if (ret)
return ret;
}
static bool __netdev_has_upper_dev(struct net_device *dev,
struct net_device *upper_dev)
{
+ struct netdev_nested_priv priv = {
+ .flags = 0,
+ .data = (void *)upper_dev,
+ };
+
ASSERT_RTNL();
return __netdev_walk_all_upper_dev(dev, ____netdev_has_upper_dev,
- upper_dev);
+ &priv);
}
/**
int netdev_walk_all_lower_dev(struct net_device *dev,
int (*fn)(struct net_device *dev,
- void *data),
- void *data)
+ struct netdev_nested_priv *priv),
+ struct netdev_nested_priv *priv)
{
struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
while (1) {
if (now != dev) {
- ret = fn(now, data);
+ ret = fn(now, priv);
if (ret)
return ret;
}
static int __netdev_walk_all_lower_dev(struct net_device *dev,
int (*fn)(struct net_device *dev,
- void *data),
- void *data)
+ struct netdev_nested_priv *priv),
+ struct netdev_nested_priv *priv)
{
struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
while (1) {
if (now != dev) {
- ret = fn(now, data);
+ ret = fn(now, priv);
if (ret)
return ret;
}
return max_depth;
}
-static int __netdev_update_upper_level(struct net_device *dev, void *data)
+static int __netdev_update_upper_level(struct net_device *dev,
+ struct netdev_nested_priv *__unused)
{
dev->upper_level = __netdev_upper_depth(dev) + 1;
return 0;
}
-static int __netdev_update_lower_level(struct net_device *dev, void *data)
+static int __netdev_update_lower_level(struct net_device *dev,
+ struct netdev_nested_priv *priv)
{
dev->lower_level = __netdev_lower_depth(dev) + 1;
+
+#ifdef CONFIG_LOCKDEP
+ if (!priv)
+ return 0;
+
+ if (priv->flags & NESTED_SYNC_IMM)
+ dev->nested_level = dev->lower_level - 1;
+ if (priv->flags & NESTED_SYNC_TODO)
+ net_unlink_todo(dev);
+#endif
return 0;
}
int netdev_walk_all_lower_dev_rcu(struct net_device *dev,
int (*fn)(struct net_device *dev,
- void *data),
- void *data)
+ struct netdev_nested_priv *priv),
+ struct netdev_nested_priv *priv)
{
struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
while (1) {
if (now != dev) {
- ret = fn(now, data);
+ ret = fn(now, priv);
if (ret)
return ret;
}
static int __netdev_upper_dev_link(struct net_device *dev,
struct net_device *upper_dev, bool master,
void *upper_priv, void *upper_info,
+ struct netdev_nested_priv *priv,
struct netlink_ext_ack *extack)
{
struct netdev_notifier_changeupper_info changeupper_info = {
__netdev_update_upper_level(dev, NULL);
__netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL);
- __netdev_update_lower_level(upper_dev, NULL);
+ __netdev_update_lower_level(upper_dev, priv);
__netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level,
- NULL);
+ priv);
return 0;
struct net_device *upper_dev,
struct netlink_ext_ack *extack)
{
+ struct netdev_nested_priv priv = {
+ .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO,
+ .data = NULL,
+ };
+
return __netdev_upper_dev_link(dev, upper_dev, false,
- NULL, NULL, extack);
+ NULL, NULL, &priv, extack);
}
EXPORT_SYMBOL(netdev_upper_dev_link);
void *upper_priv, void *upper_info,
struct netlink_ext_ack *extack)
{
+ struct netdev_nested_priv priv = {
+ .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO,
+ .data = NULL,
+ };
+
return __netdev_upper_dev_link(dev, upper_dev, true,
- upper_priv, upper_info, extack);
+ upper_priv, upper_info, &priv, extack);
}
EXPORT_SYMBOL(netdev_master_upper_dev_link);
-/**
- * netdev_upper_dev_unlink - Removes a link to upper device
- * @dev: device
- * @upper_dev: new upper device
- *
- * Removes a link to device which is upper to this one. The caller must hold
- * the RTNL lock.
- */
-void netdev_upper_dev_unlink(struct net_device *dev,
- struct net_device *upper_dev)
+static void __netdev_upper_dev_unlink(struct net_device *dev,
+ struct net_device *upper_dev,
+ struct netdev_nested_priv *priv)
{
struct netdev_notifier_changeupper_info changeupper_info = {
.info = {
__netdev_update_upper_level(dev, NULL);
__netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL);
- __netdev_update_lower_level(upper_dev, NULL);
+ __netdev_update_lower_level(upper_dev, priv);
__netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level,
- NULL);
+ priv);
+}
+
+/**
+ * netdev_upper_dev_unlink - Removes a link to upper device
+ * @dev: device
+ * @upper_dev: new upper device
+ *
+ * Removes a link to device which is upper to this one. The caller must hold
+ * the RTNL lock.
+ */
+void netdev_upper_dev_unlink(struct net_device *dev,
+ struct net_device *upper_dev)
+{
+ struct netdev_nested_priv priv = {
+ .flags = NESTED_SYNC_TODO,
+ .data = NULL,
+ };
+
+ __netdev_upper_dev_unlink(dev, upper_dev, &priv);
}
EXPORT_SYMBOL(netdev_upper_dev_unlink);
struct net_device *dev,
struct netlink_ext_ack *extack)
{
+ struct netdev_nested_priv priv = {
+ .flags = 0,
+ .data = NULL,
+ };
int err;
if (!new_dev)
if (old_dev && new_dev != old_dev)
netdev_adjacent_dev_disable(dev, old_dev);
-
- err = netdev_upper_dev_link(new_dev, dev, extack);
+ err = __netdev_upper_dev_link(new_dev, dev, false, NULL, NULL, &priv,
+ extack);
if (err) {
if (old_dev && new_dev != old_dev)
netdev_adjacent_dev_enable(dev, old_dev);
struct net_device *new_dev,
struct net_device *dev)
{
+ struct netdev_nested_priv priv = {
+ .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO,
+ .data = NULL,
+ };
+
if (!new_dev || !old_dev)
return;
return;
netdev_adjacent_dev_enable(dev, old_dev);
- netdev_upper_dev_unlink(old_dev, dev);
+ __netdev_upper_dev_unlink(old_dev, dev, &priv);
}
EXPORT_SYMBOL(netdev_adjacent_change_commit);
struct net_device *new_dev,
struct net_device *dev)
{
+ struct netdev_nested_priv priv = {
+ .flags = 0,
+ .data = NULL,
+ };
+
if (!new_dev)
return;
if (old_dev && new_dev != old_dev)
netdev_adjacent_dev_enable(dev, old_dev);
- netdev_upper_dev_unlink(new_dev, dev);
+ __netdev_upper_dev_unlink(new_dev, dev, &priv);
}
EXPORT_SYMBOL(netdev_adjacent_change_abort);
void netdev_run_todo(void)
{
struct list_head list;
+#ifdef CONFIG_LOCKDEP
+ struct list_head unlink_list;
+
+ list_replace_init(&net_unlink_list, &unlink_list);
+
+ while (!list_empty(&unlink_list)) {
+ struct net_device *dev = list_first_entry(&unlink_list,
+ struct net_device,
+ unlink_list);
+ list_del(&dev->unlink_list);
+ dev->nested_level = dev->lower_level - 1;
+ }
+#endif
/* Snapshot list, allow later requests */
list_replace_init(&net_todo_list, &list);
dev->gso_max_segs = GSO_MAX_SEGS;
dev->upper_level = 1;
dev->lower_level = 1;
+#ifdef CONFIG_LOCKDEP
+ dev->nested_level = 0;
+ INIT_LIST_HEAD(&dev->unlink_list);
+#endif
INIT_LIST_HEAD(&dev->napi_list);
INIT_LIST_HEAD(&dev->unreg_list);
if (to->addr_len != from->addr_len)
return -EINVAL;
- netif_addr_lock_nested(to);
+ netif_addr_lock(to);
err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len);
if (!err)
__dev_set_rx_mode(to);
if (to->addr_len != from->addr_len)
return -EINVAL;
- netif_addr_lock_nested(to);
+ netif_addr_lock(to);
err = __hw_addr_sync_multiple(&to->uc, &from->uc, to->addr_len);
if (!err)
__dev_set_rx_mode(to);
* larger.
*/
netif_addr_lock_bh(from);
- netif_addr_lock_nested(to);
+ netif_addr_lock(to);
__hw_addr_unsync(&to->uc, &from->uc, to->addr_len);
__dev_set_rx_mode(to);
netif_addr_unlock(to);
if (to->addr_len != from->addr_len)
return -EINVAL;
- netif_addr_lock_nested(to);
+ netif_addr_lock(to);
err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len);
if (!err)
__dev_set_rx_mode(to);
if (to->addr_len != from->addr_len)
return -EINVAL;
- netif_addr_lock_nested(to);
+ netif_addr_lock(to);
err = __hw_addr_sync_multiple(&to->mc, &from->mc, to->addr_len);
if (!err)
__dev_set_rx_mode(to);
/* See the above comments inside dev_uc_unsync(). */
netif_addr_lock_bh(from);
- netif_addr_lock_nested(to);
+ netif_addr_lock(to);
__hw_addr_unsync(&to->mc, &from->mc, to->addr_len);
__dev_set_rx_mode(to);
netif_addr_unlock(to);
BPF_CALL_1(bpf_skc_to_tcp_timewait_sock, struct sock *, sk)
{
+ /* BTF types for tcp_timewait_sock and inet_timewait_sock are not
+ * generated if CONFIG_INET=n. Trigger an explicit generation here.
+ */
+ BTF_TYPE_EMIT(struct inet_timewait_sock);
+ BTF_TYPE_EMIT(struct tcp_timewait_sock);
+
#ifdef CONFIG_INET
if (sk && sk->sk_prot == &tcp_prot && sk->sk_state == TCP_TIME_WAIT)
return (unsigned long)sk;
lse->label_stack_entry = mpls_lse;
skb_postpush_rcsum(skb, lse, MPLS_HLEN);
- if (ethernet)
+ if (ethernet && mac_len >= ETH_HLEN)
skb_mod_eth_type(skb, eth_hdr(skb), mpls_proto);
skb->protocol = mpls_proto;
skb_reset_mac_header(skb);
skb_set_network_header(skb, mac_len);
- if (ethernet) {
+ if (ethernet && mac_len >= ETH_HLEN) {
struct ethhdr *hdr;
/* use mpls_hdr() to get ethertype to account for VLANs. */
[ETHNL_MCGRP_MONITOR] = { .name = ETHTOOL_MCGRP_MONITOR_NAME },
};
-static struct genl_family ethtool_genl_family = {
+static struct genl_family ethtool_genl_family __ro_after_init = {
.name = ETHTOOL_GENL_NAME,
.version = ETHTOOL_GENL_VERSION,
.netnsok = true,
.priority = 0,
};
+#if IS_ENABLED(CONFIG_IPV6)
static struct xfrm_tunnel vti_ipip6_handler __read_mostly = {
.handler = vti_rcv_tunnel,
.cb_handler = vti_rcv_cb,
.priority = 0,
};
#endif
+#endif
static int __net_init vti_init_net(struct net *net)
{
SNMP_MIB_ITEM("TcpTimeoutRehash", LINUX_MIB_TCPTIMEOUTREHASH),
SNMP_MIB_ITEM("TcpDuplicateDataRehash", LINUX_MIB_TCPDUPLICATEDATAREHASH),
SNMP_MIB_ITEM("TCPDSACKRecvSegs", LINUX_MIB_TCPDSACKRECVSEGS),
+ SNMP_MIB_ITEM("TCPDSACKIgnoredDubious", LINUX_MIB_TCPDSACKIGNOREDDUBIOUS),
SNMP_MIB_SENTINEL
};
sock_rps_save_rxhash(child, skb);
if (rsk_drop_req(req)) {
- refcount_set(&req->rsk_refcnt, 2);
+ reqsk_put(req);
return child;
}
long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
if (IS_ENABLED(CONFIG_DEBUG_VM) &&
- WARN_ONCE(PageSlab(page), "page must not be a Slab one"))
+ WARN_ONCE(!sendpage_ok(page),
+ "page must not be a Slab one and have page_count > 0"))
return -EINVAL;
/* Wait for a connection to finish. One exception is TCP Fast Open
struct rate_sample *rate;
};
-/* Take a notice that peer is sending D-SACKs */
+/* Take a notice that peer is sending D-SACKs. Skip update of data delivery
+ * and spurious retransmission information if this DSACK is unlikely caused by
+ * sender's action:
+ * - DSACKed sequence range is larger than maximum receiver's window.
+ * - Total no. of DSACKed segments exceed the total no. of retransmitted segs.
+ */
static u32 tcp_dsack_seen(struct tcp_sock *tp, u32 start_seq,
u32 end_seq, struct tcp_sacktag_state *state)
{
u32 seq_len, dup_segs = 1;
- if (before(start_seq, end_seq)) {
- seq_len = end_seq - start_seq;
- if (seq_len > tp->mss_cache)
- dup_segs = DIV_ROUND_UP(seq_len, tp->mss_cache);
- }
+ if (!before(start_seq, end_seq))
+ return 0;
+
+ seq_len = end_seq - start_seq;
+ /* Dubious DSACK: DSACKed range greater than maximum advertised rwnd */
+ if (seq_len > tp->max_window)
+ return 0;
+ if (seq_len > tp->mss_cache)
+ dup_segs = DIV_ROUND_UP(seq_len, tp->mss_cache);
+
+ tp->dsack_dups += dup_segs;
+ /* Skip the DSACK if dup segs weren't retransmitted by sender */
+ if (tp->dsack_dups > tp->total_retrans)
+ return 0;
tp->rx_opt.sack_ok |= TCP_DSACK_SEEN;
tp->rack.dsack_seen = 1;
- tp->dsack_dups += dup_segs;
state->flag |= FLAG_DSACKING_ACK;
/* A spurious retransmission is delivered */
}
dup_segs = tcp_dsack_seen(tp, start_seq_0, end_seq_0, state);
+ if (!dup_segs) { /* Skip dubious DSACK */
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDSACKIGNOREDDUBIOUS);
+ return false;
+ }
+
NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPDSACKRECVSEGS, dup_segs);
/* D-SACK for already forgotten data... Do dumb counting. */
__skb_pull(skb, hdrlen);
if (skb_try_coalesce(tail, skb, &fragstolen, &delta)) {
- thtail->window = th->window;
-
TCP_SKB_CB(tail)->end_seq = TCP_SKB_CB(skb)->end_seq;
- if (after(TCP_SKB_CB(skb)->ack_seq, TCP_SKB_CB(tail)->ack_seq))
+ if (likely(!before(TCP_SKB_CB(skb)->ack_seq, TCP_SKB_CB(tail)->ack_seq))) {
TCP_SKB_CB(tail)->ack_seq = TCP_SKB_CB(skb)->ack_seq;
+ thtail->window = th->window;
+ }
/* We have to update both TCP_SKB_CB(tail)->tcp_flags and
* thtail->fin, so that the fast path in tcp_rcv_established()
static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow,
struct sk_buff *skb, struct mptcp_ext *ext)
{
- u64 data_fin_tx_seq = READ_ONCE(mptcp_sk(subflow->conn)->write_seq);
+ /* The write_seq value has already been incremented, so the actual
+ * sequence number for the DATA_FIN is one less.
+ */
+ u64 data_fin_tx_seq = READ_ONCE(mptcp_sk(subflow->conn)->write_seq) - 1;
if (!ext->use_map || !skb->len) {
/* RFC6824 requires a DSS mapping with specific values
ext->data_fin = 1;
ext->use_map = 1;
ext->dsn64 = 1;
- /* The write_seq value has already been incremented, so
- * the actual sequence number for the DATA_FIN is one less.
- */
- ext->data_seq = data_fin_tx_seq - 1;
+ ext->data_seq = data_fin_tx_seq;
ext->subflow_seq = 0;
ext->data_len = 1;
} else if (ext->data_seq + ext->data_len == data_fin_tx_seq) {
if (subflow->use_64bit_ack) {
ack_size = TCPOLEN_MPTCP_DSS_ACK64;
- opts->ext_copy.data_ack = msk->ack_seq;
+ opts->ext_copy.data_ack = READ_ONCE(msk->ack_seq);
opts->ext_copy.ack64 = 1;
} else {
ack_size = TCPOLEN_MPTCP_DSS_ACK32;
- opts->ext_copy.data_ack32 = (uint32_t)(msk->ack_seq);
+ opts->ext_copy.data_ack32 = (uint32_t)READ_ONCE(msk->ack_seq);
opts->ext_copy.ack64 = 0;
}
opts->ext_copy.use_ack = 1;
}
}
-bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq)
+bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit)
{
/* Skip if DATA_FIN was already received.
* If updating simultaneously with the recvmsg loop, values
if (READ_ONCE(msk->rcv_data_fin) || !READ_ONCE(msk->first))
return false;
- WRITE_ONCE(msk->rcv_data_fin_seq, data_fin_seq);
+ WRITE_ONCE(msk->rcv_data_fin_seq,
+ expand_ack(READ_ONCE(msk->ack_seq), data_fin_seq, use_64bit));
WRITE_ONCE(msk->rcv_data_fin, 1);
return true;
*/
if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) {
if (mp_opt.data_fin && mp_opt.data_len == 1 &&
- mptcp_update_rcv_data_fin(msk, mp_opt.data_seq) &&
+ mptcp_update_rcv_data_fin(msk, mp_opt.data_seq, mp_opt.dsn64) &&
schedule_work(&msk->work))
sock_hold(subflow->conn);
skb_ext_reset(skb);
skb_orphan(skb);
- msk->ack_seq += copy_len;
+ WRITE_ONCE(msk->ack_seq, msk->ack_seq + copy_len);
tail = skb_peek_tail(&sk->sk_receive_queue);
if (offset == 0 && tail) {
if (mptcp_pending_data_fin(sk, &rcv_data_fin_seq)) {
struct mptcp_subflow_context *subflow;
- msk->ack_seq++;
+ WRITE_ONCE(msk->ack_seq, msk->ack_seq + 1);
WRITE_ONCE(msk->rcv_data_fin, 0);
sk->sk_shutdown |= RCV_SHUTDOWN;
msk->remote_key = mp_opt->sndr_key;
mptcp_crypto_key_sha(msk->remote_key, NULL, &ack_seq);
ack_seq++;
- msk->ack_seq = ack_seq;
+ WRITE_ONCE(msk->ack_seq, ack_seq);
}
sock_reset_flag(nsk, SOCK_RCU_FREE);
parent_sock = READ_ONCE(parent->sk_socket);
if (parent_sock && !sk->sk_socket)
mptcp_sock_graft(sk, parent_sock);
- subflow->map_seq = msk->ack_seq;
+ subflow->map_seq = READ_ONCE(msk->ack_seq);
return true;
}
bool mptcp_finish_join(struct sock *sk);
void mptcp_data_acked(struct sock *sk);
void mptcp_subflow_eof(struct sock *sk);
-bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq);
+bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit);
void __init mptcp_token_init(void);
static inline void mptcp_token_init_request(struct request_sock *req)
if (mpext->data_fin == 1) {
if (data_len == 1) {
- mptcp_update_rcv_data_fin(msk, mpext->data_seq);
+ bool updated = mptcp_update_rcv_data_fin(msk, mpext->data_seq,
+ mpext->dsn64);
pr_debug("DATA_FIN with no payload seq=%llu", mpext->data_seq);
if (subflow->map_valid) {
/* A DATA_FIN might arrive in a DSS
skb_ext_del(skb, SKB_EXT_MPTCP);
return MAPPING_OK;
} else {
+ if (updated && schedule_work(&msk->work))
+ sock_hold((struct sock *)msk);
+
return MAPPING_DATA_FIN;
}
} else {
- mptcp_update_rcv_data_fin(msk, mpext->data_seq + data_len);
- pr_debug("DATA_FIN with mapping seq=%llu", mpext->data_seq + data_len);
+ u64 data_fin_seq = mpext->data_seq + data_len - 1;
+
+ /* If mpext->data_seq is a 32-bit value, data_fin_seq
+ * must also be limited to 32 bits.
+ */
+ if (!mpext->dsn64)
+ data_fin_seq &= GENMASK_ULL(31, 0);
+
+ mptcp_update_rcv_data_fin(msk, data_fin_seq, mpext->dsn64);
+ pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d",
+ data_fin_seq, mpext->dsn64);
}
/* Adjust for DATA_FIN using 1 byte of sequence space */
if (err)
return err;
- while (netlink_policy_dump_loop(&cb->args[1])) {
+ while (netlink_policy_dump_loop(cb->args[1])) {
void *hdr;
struct nlattr *nest;
return skb->len;
}
+static int ctrl_dumppolicy_done(struct netlink_callback *cb)
+{
+ netlink_policy_dump_free(cb->args[1]);
+ return 0;
+}
+
static const struct genl_ops genl_ctrl_ops[] = {
{
.cmd = CTRL_CMD_GETFAMILY,
{
.cmd = CTRL_CMD_GETPOLICY,
.dumpit = ctrl_dumppolicy,
+ .done = ctrl_dumppolicy_done,
},
};
unsigned int policy_idx;
int err;
- /* also returns 0 if "*_state" is our ERR_PTR() end marker */
if (*_state)
return 0;
!state->policies[state->policy_idx].policy;
}
-bool netlink_policy_dump_loop(unsigned long *_state)
+bool netlink_policy_dump_loop(unsigned long _state)
{
- struct nl_policy_dump *state = (void *)*_state;
-
- if (IS_ERR(state))
- return false;
-
- if (netlink_policy_dump_finished(state)) {
- kfree(state);
- /* store end marker instead of freed state */
- *_state = (unsigned long)ERR_PTR(-ENOENT);
- return false;
- }
+ struct nl_policy_dump *state = (void *)_state;
- return true;
+ return !netlink_policy_dump_finished(state);
}
int netlink_policy_dump_write(struct sk_buff *skb, unsigned long _state)
nla_nest_cancel(skb, policy);
return -ENOBUFS;
}
+
+void netlink_policy_dump_free(unsigned long _state)
+{
+ struct nl_policy_dump *state = (void *)_state;
+
+ kfree(state);
+}
}
err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype);
- if (err == NF_ACCEPT &&
- ct->status & IPS_SRC_NAT && ct->status & IPS_DST_NAT) {
- if (maniptype == NF_NAT_MANIP_SRC)
- maniptype = NF_NAT_MANIP_DST;
- else
- maniptype = NF_NAT_MANIP_SRC;
-
- err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range,
- maniptype);
+ if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) {
+ if (ct->status & IPS_SRC_NAT) {
+ if (maniptype == NF_NAT_MANIP_SRC)
+ maniptype = NF_NAT_MANIP_DST;
+ else
+ maniptype = NF_NAT_MANIP_SRC;
+
+ err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range,
+ maniptype);
+ } else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {
+ err = ovs_ct_nat_execute(skb, ct, ctinfo, NULL,
+ NF_NAT_MANIP_SRC);
+ }
}
/* Mark NAT done if successful and update the flow key. */
if (!node)
return 0;
+ rcu_read_lock();
/* Announce the list of servers registered in this node */
radix_tree_for_each_slot(slot, &node->servers, &iter, 0) {
srv = radix_tree_deref_slot(slot);
+ if (!srv)
+ continue;
+ if (radix_tree_deref_retry(srv)) {
+ slot = radix_tree_iter_retry(&iter);
+ continue;
+ }
+ slot = radix_tree_iter_resume(slot, &iter);
+ rcu_read_unlock();
ret = service_announce_new(sq, srv);
if (ret < 0) {
pr_err("failed to announce new service\n");
return ret;
}
+
+ rcu_read_lock();
}
+ rcu_read_unlock();
+
return 0;
}
if (!node)
return 0;
+ rcu_read_lock();
/* Advertise removal of this client to all servers of remote node */
radix_tree_for_each_slot(slot, &node->servers, &iter, 0) {
srv = radix_tree_deref_slot(slot);
+ if (!srv)
+ continue;
+ if (radix_tree_deref_retry(srv)) {
+ slot = radix_tree_iter_retry(&iter);
+ continue;
+ }
+ slot = radix_tree_iter_resume(slot, &iter);
+ rcu_read_unlock();
server_del(node, srv->port);
+ rcu_read_lock();
}
+ rcu_read_unlock();
/* Advertise the removal of this client to all local servers */
local_node = node_get(qrtr_ns.local_node);
pkt.cmd = cpu_to_le32(QRTR_TYPE_BYE);
pkt.client.node = cpu_to_le32(from->sq_node);
+ rcu_read_lock();
radix_tree_for_each_slot(slot, &local_node->servers, &iter, 0) {
srv = radix_tree_deref_slot(slot);
+ if (!srv)
+ continue;
+ if (radix_tree_deref_retry(srv)) {
+ slot = radix_tree_iter_retry(&iter);
+ continue;
+ }
+ slot = radix_tree_iter_resume(slot, &iter);
+ rcu_read_unlock();
sq.sq_family = AF_QIPCRTR;
sq.sq_node = srv->node;
pr_err("failed to send bye cmd\n");
return ret;
}
+ rcu_read_lock();
}
+ rcu_read_unlock();
+
return 0;
}
pkt.client.node = cpu_to_le32(node_id);
pkt.client.port = cpu_to_le32(port);
+ rcu_read_lock();
radix_tree_for_each_slot(slot, &local_node->servers, &iter, 0) {
srv = radix_tree_deref_slot(slot);
+ if (!srv)
+ continue;
+ if (radix_tree_deref_retry(srv)) {
+ slot = radix_tree_iter_retry(&iter);
+ continue;
+ }
+ slot = radix_tree_iter_resume(slot, &iter);
+ rcu_read_unlock();
sq.sq_family = AF_QIPCRTR;
sq.sq_node = srv->node;
pr_err("failed to send del client cmd\n");
return ret;
}
+ rcu_read_lock();
}
+ rcu_read_unlock();
+
return 0;
}
filter.service = service;
filter.instance = instance;
+ rcu_read_lock();
radix_tree_for_each_slot(node_slot, &nodes, &node_iter, 0) {
node = radix_tree_deref_slot(node_slot);
+ if (!node)
+ continue;
+ if (radix_tree_deref_retry(node)) {
+ node_slot = radix_tree_iter_retry(&node_iter);
+ continue;
+ }
+ node_slot = radix_tree_iter_resume(node_slot, &node_iter);
radix_tree_for_each_slot(srv_slot, &node->servers,
&srv_iter, 0) {
struct qrtr_server *srv;
srv = radix_tree_deref_slot(srv_slot);
+ if (!srv)
+ continue;
+ if (radix_tree_deref_retry(srv)) {
+ srv_slot = radix_tree_iter_retry(&srv_iter);
+ continue;
+ }
+
if (!server_match(srv, &filter))
continue;
+ srv_slot = radix_tree_iter_resume(srv_slot, &srv_iter);
+
+ rcu_read_unlock();
lookup_notify(from, srv, true);
+ rcu_read_lock();
}
}
+ rcu_read_unlock();
/* Empty notification, to indicate end of listing */
lookup_notify(from, NULL, true);
RXRPC_CALL_CLIENT_RECV_REPLY, /* - client receiving reply phase */
RXRPC_CALL_SERVER_PREALLOC, /* - service preallocation */
RXRPC_CALL_SERVER_SECURING, /* - server securing request connection */
- RXRPC_CALL_SERVER_ACCEPTING, /* - server accepting request */
RXRPC_CALL_SERVER_RECV_REQUEST, /* - server receiving request */
RXRPC_CALL_SERVER_ACK_REQUEST, /* - server pending ACK of request */
RXRPC_CALL_SERVER_SEND_REPLY, /* - server sending reply */
enum rxrpc_command {
RXRPC_CMD_SEND_DATA, /* send data message */
RXRPC_CMD_SEND_ABORT, /* request abort generation */
- RXRPC_CMD_ACCEPT, /* [server] accept incoming call */
RXRPC_CMD_REJECT_BUSY, /* [server] reject a call as busy */
+ RXRPC_CMD_CHARGE_ACCEPT, /* [server] charge accept preallocation */
};
struct rxrpc_call_params {
struct rxrpc_sock *,
struct sk_buff *);
void rxrpc_accept_incoming_calls(struct rxrpc_local *);
-struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *, unsigned long,
- rxrpc_notify_rx_t);
-int rxrpc_reject_call(struct rxrpc_sock *);
+int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long);
/*
* call_event.c
unsigned int debug_id)
{
const void *here = __builtin_return_address(0);
- struct rxrpc_call *call;
+ struct rxrpc_call *call, *xcall;
struct rxrpc_net *rxnet = rxrpc_net(sock_net(&rx->sk));
+ struct rb_node *parent, **pp;
int max, tmp;
unsigned int size = RXRPC_BACKLOG_MAX;
unsigned int head, tail, call_head, call_tail;
}
/* Now it gets complicated, because calls get registered with the
- * socket here, particularly if a user ID is preassigned by the user.
+ * socket here, with a user ID preassigned by the user.
*/
call = rxrpc_alloc_call(rx, gfp, debug_id);
if (!call)
here, (const void *)user_call_ID);
write_lock(&rx->call_lock);
- if (user_attach_call) {
- struct rxrpc_call *xcall;
- struct rb_node *parent, **pp;
-
- /* Check the user ID isn't already in use */
- pp = &rx->calls.rb_node;
- parent = NULL;
- while (*pp) {
- parent = *pp;
- xcall = rb_entry(parent, struct rxrpc_call, sock_node);
- if (user_call_ID < xcall->user_call_ID)
- pp = &(*pp)->rb_left;
- else if (user_call_ID > xcall->user_call_ID)
- pp = &(*pp)->rb_right;
- else
- goto id_in_use;
- }
- call->user_call_ID = user_call_ID;
- call->notify_rx = notify_rx;
+ /* Check the user ID isn't already in use */
+ pp = &rx->calls.rb_node;
+ parent = NULL;
+ while (*pp) {
+ parent = *pp;
+ xcall = rb_entry(parent, struct rxrpc_call, sock_node);
+ if (user_call_ID < xcall->user_call_ID)
+ pp = &(*pp)->rb_left;
+ else if (user_call_ID > xcall->user_call_ID)
+ pp = &(*pp)->rb_right;
+ else
+ goto id_in_use;
+ }
+
+ call->user_call_ID = user_call_ID;
+ call->notify_rx = notify_rx;
+ if (user_attach_call) {
rxrpc_get_call(call, rxrpc_call_got_kernel);
user_attach_call(call, user_call_ID);
- rxrpc_get_call(call, rxrpc_call_got_userid);
- rb_link_node(&call->sock_node, parent, pp);
- rb_insert_color(&call->sock_node, &rx->calls);
- set_bit(RXRPC_CALL_HAS_USERID, &call->flags);
}
+ rxrpc_get_call(call, rxrpc_call_got_userid);
+ rb_link_node(&call->sock_node, parent, pp);
+ rb_insert_color(&call->sock_node, &rx->calls);
+ set_bit(RXRPC_CALL_HAS_USERID, &call->flags);
+
list_add(&call->sock_link, &rx->sock_calls);
write_unlock(&rx->call_lock);
}
/*
- * Preallocate sufficient service connections, calls and peers to cover the
- * entire backlog of a socket. When a new call comes in, if we don't have
- * sufficient of each available, the call gets rejected as busy or ignored.
- *
- * The backlog is replenished when a connection is accepted or rejected.
+ * Allocate the preallocation buffers for incoming service calls. These must
+ * be charged manually.
*/
int rxrpc_service_prealloc(struct rxrpc_sock *rx, gfp_t gfp)
{
rx->backlog = b;
}
- if (rx->discard_new_call)
- return 0;
-
- while (rxrpc_service_prealloc_one(rx, b, NULL, NULL, 0, gfp,
- atomic_inc_return(&rxrpc_debug_id)) == 0)
- ;
-
return 0;
}
rxrpc_see_call(call);
call->conn = conn;
call->security = conn->security;
+ call->security_ix = conn->security_ix;
call->peer = rxrpc_get_peer(conn->params.peer);
call->cong_cwnd = call->peer->cong_cwnd;
return call;
if (rx->notify_new_call)
rx->notify_new_call(&rx->sk, call, call->user_call_ID);
- else
- sk_acceptq_added(&rx->sk);
spin_lock(&conn->state_lock);
switch (conn->state) {
case RXRPC_CONN_SERVICE:
write_lock(&call->state_lock);
- if (call->state < RXRPC_CALL_COMPLETE) {
- if (rx->discard_new_call)
- call->state = RXRPC_CALL_SERVER_RECV_REQUEST;
- else
- call->state = RXRPC_CALL_SERVER_ACCEPTING;
- }
+ if (call->state < RXRPC_CALL_COMPLETE)
+ call->state = RXRPC_CALL_SERVER_RECV_REQUEST;
write_unlock(&call->state_lock);
break;
rxrpc_send_ping(call, skb);
- if (call->state == RXRPC_CALL_SERVER_ACCEPTING)
- rxrpc_notify_socket(call);
-
/* We have to discard the prealloc queue's ref here and rely on a
* combination of the RCU read lock and refs held either by the socket
* (recvmsg queue, to-be-accepted queue or user ID tree) or the kernel
}
/*
- * handle acceptance of a call by userspace
- * - assign the user call ID to the call at the front of the queue
- * - called with the socket locked.
+ * Charge up socket with preallocated calls, attaching user call IDs.
*/
-struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *rx,
- unsigned long user_call_ID,
- rxrpc_notify_rx_t notify_rx)
- __releases(&rx->sk.sk_lock.slock)
- __acquires(call->user_mutex)
+int rxrpc_user_charge_accept(struct rxrpc_sock *rx, unsigned long user_call_ID)
{
- struct rxrpc_call *call;
- struct rb_node *parent, **pp;
- int ret;
-
- _enter(",%lx", user_call_ID);
-
- ASSERT(!irqs_disabled());
-
- write_lock(&rx->call_lock);
-
- if (list_empty(&rx->to_be_accepted)) {
- write_unlock(&rx->call_lock);
- release_sock(&rx->sk);
- kleave(" = -ENODATA [empty]");
- return ERR_PTR(-ENODATA);
- }
-
- /* check the user ID isn't already in use */
- pp = &rx->calls.rb_node;
- parent = NULL;
- while (*pp) {
- parent = *pp;
- call = rb_entry(parent, struct rxrpc_call, sock_node);
-
- if (user_call_ID < call->user_call_ID)
- pp = &(*pp)->rb_left;
- else if (user_call_ID > call->user_call_ID)
- pp = &(*pp)->rb_right;
- else
- goto id_in_use;
- }
-
- /* Dequeue the first call and check it's still valid. We gain
- * responsibility for the queue's reference.
- */
- call = list_entry(rx->to_be_accepted.next,
- struct rxrpc_call, accept_link);
- write_unlock(&rx->call_lock);
-
- /* We need to gain the mutex from the interrupt handler without
- * upsetting lockdep, so we have to release it there and take it here.
- * We are, however, still holding the socket lock, so other accepts
- * must wait for us and no one can add the user ID behind our backs.
- */
- if (mutex_lock_interruptible(&call->user_mutex) < 0) {
- release_sock(&rx->sk);
- kleave(" = -ERESTARTSYS");
- return ERR_PTR(-ERESTARTSYS);
- }
-
- write_lock(&rx->call_lock);
- list_del_init(&call->accept_link);
- sk_acceptq_removed(&rx->sk);
- rxrpc_see_call(call);
-
- /* Find the user ID insertion point. */
- pp = &rx->calls.rb_node;
- parent = NULL;
- while (*pp) {
- parent = *pp;
- call = rb_entry(parent, struct rxrpc_call, sock_node);
-
- if (user_call_ID < call->user_call_ID)
- pp = &(*pp)->rb_left;
- else if (user_call_ID > call->user_call_ID)
- pp = &(*pp)->rb_right;
- else
- BUG();
- }
-
- write_lock_bh(&call->state_lock);
- switch (call->state) {
- case RXRPC_CALL_SERVER_ACCEPTING:
- call->state = RXRPC_CALL_SERVER_RECV_REQUEST;
- break;
- case RXRPC_CALL_COMPLETE:
- ret = call->error;
- goto out_release;
- default:
- BUG();
- }
-
- /* formalise the acceptance */
- call->notify_rx = notify_rx;
- call->user_call_ID = user_call_ID;
- rxrpc_get_call(call, rxrpc_call_got_userid);
- rb_link_node(&call->sock_node, parent, pp);
- rb_insert_color(&call->sock_node, &rx->calls);
- if (test_and_set_bit(RXRPC_CALL_HAS_USERID, &call->flags))
- BUG();
-
- write_unlock_bh(&call->state_lock);
- write_unlock(&rx->call_lock);
- rxrpc_notify_socket(call);
- rxrpc_service_prealloc(rx, GFP_KERNEL);
- release_sock(&rx->sk);
- _leave(" = %p{%d}", call, call->debug_id);
- return call;
-
-out_release:
- _debug("release %p", call);
- write_unlock_bh(&call->state_lock);
- write_unlock(&rx->call_lock);
- rxrpc_release_call(rx, call);
- rxrpc_put_call(call, rxrpc_call_put);
- goto out;
-
-id_in_use:
- ret = -EBADSLT;
- write_unlock(&rx->call_lock);
-out:
- rxrpc_service_prealloc(rx, GFP_KERNEL);
- release_sock(&rx->sk);
- _leave(" = %d", ret);
- return ERR_PTR(ret);
-}
-
-/*
- * Handle rejection of a call by userspace
- * - reject the call at the front of the queue
- */
-int rxrpc_reject_call(struct rxrpc_sock *rx)
-{
- struct rxrpc_call *call;
- bool abort = false;
- int ret;
-
- _enter("");
-
- ASSERT(!irqs_disabled());
-
- write_lock(&rx->call_lock);
-
- if (list_empty(&rx->to_be_accepted)) {
- write_unlock(&rx->call_lock);
- return -ENODATA;
- }
-
- /* Dequeue the first call and check it's still valid. We gain
- * responsibility for the queue's reference.
- */
- call = list_entry(rx->to_be_accepted.next,
- struct rxrpc_call, accept_link);
- list_del_init(&call->accept_link);
- sk_acceptq_removed(&rx->sk);
- rxrpc_see_call(call);
+ struct rxrpc_backlog *b = rx->backlog;
- write_lock_bh(&call->state_lock);
- switch (call->state) {
- case RXRPC_CALL_SERVER_ACCEPTING:
- __rxrpc_abort_call("REJ", call, 1, RX_USER_ABORT, -ECONNABORTED);
- abort = true;
- fallthrough;
- case RXRPC_CALL_COMPLETE:
- ret = call->error;
- goto out_discard;
- default:
- BUG();
- }
+ if (rx->sk.sk_state == RXRPC_CLOSE)
+ return -ESHUTDOWN;
-out_discard:
- write_unlock_bh(&call->state_lock);
- write_unlock(&rx->call_lock);
- if (abort) {
- rxrpc_send_abort_packet(call);
- rxrpc_release_call(rx, call);
- rxrpc_put_call(call, rxrpc_call_put);
- }
- rxrpc_service_prealloc(rx, GFP_KERNEL);
- _leave(" = %d", ret);
- return ret;
+ return rxrpc_service_prealloc_one(rx, b, NULL, NULL, user_call_ID,
+ GFP_KERNEL,
+ atomic_inc_return(&rxrpc_debug_id));
}
/*
[RXRPC_CALL_CLIENT_RECV_REPLY] = "ClRcvRpl",
[RXRPC_CALL_SERVER_PREALLOC] = "SvPrealc",
[RXRPC_CALL_SERVER_SECURING] = "SvSecure",
- [RXRPC_CALL_SERVER_ACCEPTING] = "SvAccept",
[RXRPC_CALL_SERVER_RECV_REQUEST] = "SvRcvReq",
[RXRPC_CALL_SERVER_ACK_REQUEST] = "SvAckReq",
[RXRPC_CALL_SERVER_SEND_REPLY] = "SvSndRpl",
call->call_id = sp->hdr.callNumber;
call->service_id = sp->hdr.serviceId;
call->cid = sp->hdr.cid;
- call->state = RXRPC_CALL_SERVER_ACCEPTING;
- if (sp->hdr.securityIndex > 0)
- call->state = RXRPC_CALL_SERVER_SECURING;
+ call->state = RXRPC_CALL_SERVER_SECURING;
call->cong_tstamp = skb->tstamp;
/* Set the channel for this call. We don't get channel_lock as we're
if (call) {
write_lock_bh(&call->state_lock);
if (call->state == RXRPC_CALL_SERVER_SECURING) {
- call->state = RXRPC_CALL_SERVER_ACCEPTING;
+ call->state = RXRPC_CALL_SERVER_RECV_REQUEST;
rxrpc_notify_socket(call);
}
write_unlock_bh(&call->state_lock);
return ret;
spin_lock(&conn->channel_lock);
- spin_lock(&conn->state_lock);
+ spin_lock_bh(&conn->state_lock);
if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) {
conn->state = RXRPC_CONN_SERVICE;
- spin_unlock(&conn->state_lock);
+ spin_unlock_bh(&conn->state_lock);
for (loop = 0; loop < RXRPC_MAXCALLS; loop++)
rxrpc_call_is_secure(
rcu_dereference_protected(
conn->channels[loop].call,
lockdep_is_held(&conn->channel_lock)));
} else {
- spin_unlock(&conn->state_lock);
+ spin_unlock_bh(&conn->state_lock);
}
spin_unlock(&conn->channel_lock);
_enter("");
- if (optlen <= 0 || optlen > PAGE_SIZE - 1)
+ if (optlen <= 0 || optlen > PAGE_SIZE - 1 || rx->securities)
return -EINVAL;
description = memdup_sockptr_nul(optval, optlen);
if (IS_ERR(description))
return PTR_ERR(description);
- key = request_key_net(&key_type_keyring, description, sock_net(&rx->sk), NULL);
+ key = request_key(&key_type_keyring, description, NULL);
if (IS_ERR(key)) {
kfree(description);
_leave(" = %ld", PTR_ERR(key));
switch (token->security_index) {
case RXRPC_SECURITY_RXKAD:
- toksize += 9 * 4; /* viceid, kvno, key*2 + len, begin,
+ toksize += 8 * 4; /* viceid, kvno, key*2, begin,
* end, primary, tktlen */
toksize += RND(token->kad->ticket_len);
break;
break;
default: /* we have a ticket we can't encode */
- BUG();
+ pr_err("Unsupported key token type (%u)\n",
+ token->security_index);
continue;
}
memcpy((u8 *)xdr + _l, &zero, 4 - (_l & 3)); \
xdr += (_l + 3) >> 2; \
} while(0)
+#define ENCODE_BYTES(l, s) \
+ do { \
+ u32 _l = (l); \
+ memcpy(xdr, (s), _l); \
+ if (_l & 3) \
+ memcpy((u8 *)xdr + _l, &zero, 4 - (_l & 3)); \
+ xdr += (_l + 3) >> 2; \
+ } while(0)
#define ENCODE64(x) \
do { \
__be64 y = cpu_to_be64(x); \
case RXRPC_SECURITY_RXKAD:
ENCODE(token->kad->vice_id);
ENCODE(token->kad->kvno);
- ENCODE_DATA(8, token->kad->session_key);
+ ENCODE_BYTES(8, token->kad->session_key);
ENCODE(token->kad->start);
ENCODE(token->kad->expiry);
ENCODE(token->kad->primary_flag);
break;
default:
- BUG();
break;
}
}
/*
- * Pass back notification of a new call. The call is added to the
- * to-be-accepted list. This means that the next call to be accepted might not
- * be the last call seen awaiting acceptance, but unless we leave this on the
- * front of the queue and block all other messages until someone gives us a
- * user_ID for it, there's not a lot we can do.
- */
-static int rxrpc_recvmsg_new_call(struct rxrpc_sock *rx,
- struct rxrpc_call *call,
- struct msghdr *msg, int flags)
-{
- int tmp = 0, ret;
-
- ret = put_cmsg(msg, SOL_RXRPC, RXRPC_NEW_CALL, 0, &tmp);
-
- if (ret == 0 && !(flags & MSG_PEEK)) {
- _debug("to be accepted");
- write_lock_bh(&rx->recvmsg_lock);
- list_del_init(&call->recvmsg_link);
- write_unlock_bh(&rx->recvmsg_lock);
-
- rxrpc_get_call(call, rxrpc_call_got);
- write_lock(&rx->call_lock);
- list_add_tail(&call->accept_link, &rx->to_be_accepted);
- write_unlock(&rx->call_lock);
- }
-
- trace_rxrpc_recvmsg(call, rxrpc_recvmsg_to_be_accepted, 1, 0, 0, ret);
- return ret;
-}
-
-/*
* End the packet reception phase.
*/
static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial)
}
switch (READ_ONCE(call->state)) {
- case RXRPC_CALL_SERVER_ACCEPTING:
- ret = rxrpc_recvmsg_new_call(rx, call, msg, flags);
- break;
case RXRPC_CALL_CLIENT_RECV_REPLY:
case RXRPC_CALL_SERVER_RECV_REQUEST:
case RXRPC_CALL_SERVER_ACK_REQUEST:
call->debug_id, rxrpc_call_states[call->state],
iov_iter_count(iter), want_more);
- ASSERTCMP(call->state, !=, RXRPC_CALL_SERVER_ACCEPTING);
+ ASSERTCMP(call->state, !=, RXRPC_CALL_SERVER_SECURING);
mutex_lock(&call->user_mutex);
return -EINVAL;
break;
- case RXRPC_ACCEPT:
+ case RXRPC_CHARGE_ACCEPT:
if (p->command != RXRPC_CMD_SEND_DATA)
return -EINVAL;
- p->command = RXRPC_CMD_ACCEPT;
+ p->command = RXRPC_CMD_CHARGE_ACCEPT;
if (len != 0)
return -EINVAL;
break;
if (ret < 0)
goto error_release_sock;
- if (p.command == RXRPC_CMD_ACCEPT) {
+ if (p.command == RXRPC_CMD_CHARGE_ACCEPT) {
ret = -EINVAL;
if (rx->sk.sk_state != RXRPC_SERVER_LISTENING)
goto error_release_sock;
- call = rxrpc_accept_call(rx, p.call.user_call_ID, NULL);
- /* The socket is now unlocked. */
- if (IS_ERR(call))
- return PTR_ERR(call);
- ret = 0;
- goto out_put_unlock;
+ ret = rxrpc_user_charge_accept(rx, p.call.user_call_ID);
+ goto error_release_sock;
}
call = rxrpc_find_call_by_user_ID(rx, p.call.user_call_ID);
case RXRPC_CALL_CLIENT_AWAIT_CONN:
case RXRPC_CALL_SERVER_PREALLOC:
case RXRPC_CALL_SERVER_SECURING:
- case RXRPC_CALL_SERVER_ACCEPTING:
rxrpc_put_call(call, rxrpc_call_put);
ret = -EBUSY;
goto error_release_sock;
index++;
if (index < s_i)
continue;
+ if (IS_ERR(p))
+ continue;
if (jiffy_since &&
time_after(jiffy_since,
mutex_lock(&idrinfo->lock);
idr_for_each_entry_ul(idr, p, tmp, id) {
+ if (IS_ERR(p))
+ continue;
ret = tcf_idr_release_unsafe(p);
if (ret == ACT_P_DELETED) {
module_put(ops->owner);
}
EXPORT_SYMBOL(tcf_idr_create_from_flags);
-void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a)
-{
- struct tcf_idrinfo *idrinfo = tn->idrinfo;
-
- mutex_lock(&idrinfo->lock);
- /* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */
- WARN_ON(!IS_ERR(idr_replace(&idrinfo->action_idr, a, a->tcfa_index)));
- mutex_unlock(&idrinfo->lock);
-}
-EXPORT_SYMBOL(tcf_idr_insert);
-
/* Cleanup idr index that was allocated but not initialized. */
void tcf_idr_cleanup(struct tc_action_net *tn, u32 index)
return ret;
}
-static int tcf_action_destroy_1(struct tc_action *a, int bind)
-{
- struct tc_action *actions[] = { a, NULL };
-
- return tcf_action_destroy(actions, bind);
-}
-
static int tcf_action_put(struct tc_action *p)
{
return __tcf_action_put(p, false);
[TCA_ACT_HW_STATS] = NLA_POLICY_BITFIELD32(TCA_ACT_HW_STATS_ANY),
};
+static void tcf_idr_insert_many(struct tc_action *actions[])
+{
+ int i;
+
+ for (i = 0; i < TCA_ACT_MAX_PRIO; i++) {
+ struct tc_action *a = actions[i];
+ struct tcf_idrinfo *idrinfo;
+
+ if (!a)
+ continue;
+ idrinfo = a->idrinfo;
+ mutex_lock(&idrinfo->lock);
+ /* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc if
+ * it is just created, otherwise this is just a nop.
+ */
+ idr_replace(&idrinfo->action_idr, a, a->tcfa_index);
+ mutex_unlock(&idrinfo->lock);
+ }
+}
+
struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
struct nlattr *nla, struct nlattr *est,
char *name, int ovr, int bind,
if (err != ACT_P_CREATED)
module_put(a_o->owner);
- if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN) &&
- !rcu_access_pointer(a->goto_chain)) {
- tcf_action_destroy_1(a, bind);
- NL_SET_ERR_MSG(extack, "can't use goto chain with NULL chain");
- return ERR_PTR(-EINVAL);
- }
-
return a;
err_mod:
actions[i - 1] = act;
}
+ /* We have to commit them all together, because if any error happened in
+ * between, we could not handle the failure gracefully.
+ */
+ tcf_idr_insert_many(actions);
+
*attr_size = tcf_action_full_attrs_size(sz);
return i - 1;
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
- if (res == ACT_P_CREATED) {
- tcf_idr_insert(tn, *act);
- } else {
+ if (res != ACT_P_CREATED) {
/* make sure the program being replaced is no longer executing */
synchronize_rcu();
tcf_bpf_cfg_cleanup(&old);
ci->net = net;
ci->zone = parm->zone;
- tcf_idr_insert(tn, *a);
ret = ACT_P_CREATED;
} else if (ret > 0) {
ci = to_connmark(*a);
if (params_new)
kfree_rcu(params_new, rcu);
- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
-
return ret;
put_chain:
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
if (params)
call_rcu(¶ms->rcu, tcf_ct_params_free);
- if (res == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
return res;
if (cp_new)
kfree_rcu(cp_new, rcu);
- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
-
return ret;
put_chain:
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
return ret;
release_idr:
tcf_idr_release(*a, bind);
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
-
return ret;
chain_put:
if (p)
kfree_rcu(p, rcu);
- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
-
return ret;
metadata_parse_err:
if (goto_ch)
ipt->tcfi_t = t;
ipt->tcfi_hook = hook;
spin_unlock_bh(&ipt->tcf_lock);
- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
return ret;
err3:
spin_lock(&mirred_list_lock);
list_add(&m->tcfm_list, &mirred_list);
spin_unlock(&mirred_list_lock);
-
- tcf_idr_insert(tn, *a);
}
return ret;
if (p)
kfree_rcu(p, rcu);
- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
return ret;
put_chain:
if (goto_ch)
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
-
return ret;
release_idr:
tcf_idr_release(*a, bind);
spin_unlock_bh(&p->tcf_lock);
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
return ret;
put_chain:
if (new)
kfree_rcu(new, rcu);
- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
return ret;
failure:
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
return ret;
put_chain:
if (goto_ch)
goto release_idr;
}
- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
return ret;
put_chain:
if (goto_ch)
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
return ret;
put_chain:
if (goto_ch)
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
return ret;
put_chain:
if (goto_ch)
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
-
return ret;
put_chain:
if (p)
kfree_rcu(p, rcu);
- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
return ret;
put_chain:
if (goto_ch)
out_err:
/* Clean up any successful allocations */
sctp_auth_destroy_hmacs(ep->auth_hmacs);
+ ep->auth_hmacs = NULL;
return -ENOMEM;
}
int kernel_sendpage(struct socket *sock, struct page *page, int offset,
size_t size, int flags)
{
- if (sock->ops->sendpage)
+ if (sock->ops->sendpage) {
+ /* Warn in case the improper page to zero-copy send */
+ WARN_ONCE(!sendpage_ok(page), "improper page for zero-copy send");
return sock->ops->sendpage(sock, page, offset, size, flags);
-
+ }
return sock_no_sendpage(sock, page, offset, size, flags);
}
EXPORT_SYMBOL(kernel_sendpage);
* @val: value passed unmodified to notifier function
* @dev: port device
* @info: notifier information data
- *
+ * @extack: netlink extended ack
* Call all network notifier blocks.
*/
int call_switchdev_notifiers(unsigned long val, struct net_device *dev,
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
struct tls_rec *rec, *tmp;
+ int pending;
/* Wait for any pending async encryptions to complete */
- smp_store_mb(ctx->async_notify, true);
- if (atomic_read(&ctx->encrypt_pending))
+ spin_lock_bh(&ctx->encrypt_compl_lock);
+ ctx->async_notify = true;
+ pending = atomic_read(&ctx->encrypt_pending);
+ spin_unlock_bh(&ctx->encrypt_compl_lock);
+
+ if (pending)
crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
tls_tx_records(sk, -1);
if (err)
return err;
+ if (key.idx < 0)
+ return -EINVAL;
+
if (info->attrs[NL80211_ATTR_MAC])
mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]);
skb_shinfo(skb)->destructor_arg = (void *)(long)desc.addr;
skb->destructor = xsk_destruct_skb;
+ /* Hinder dev_direct_xmit from freeing the packet and
+ * therefore completing it in the destructor
+ */
+ refcount_inc(&skb->users);
err = dev_direct_xmit(skb, xs->queue_id);
+ if (err == NETDEV_TX_BUSY) {
+ /* Tell user-space to retry the send */
+ skb->destructor = sock_wfree;
+ /* Free skb without triggering the perf drop trace */
+ consume_skb(skb);
+ err = -EAGAIN;
+ goto out;
+ }
+
xskq_cons_release(xs->tx);
/* Ignore NET_XMIT_CN as packet might have been sent */
- if (err == NET_XMIT_DROP || err == NETDEV_TX_BUSY) {
+ if (err == NET_XMIT_DROP) {
/* SKB completed but not sent */
+ kfree_skb(skb);
err = -EBUSY;
goto out;
}
+ consume_skb(skb);
sent_frame = true;
}
static void handle_esp(struct sk_buff *skb, struct sock *sk)
{
+ struct tcp_skb_cb *tcp_cb = (struct tcp_skb_cb *)skb->cb;
+
skb_reset_transport_header(skb);
- memset(skb->cb, 0, sizeof(skb->cb));
+
+ /* restore IP CB, we need at least IP6CB->nhoff */
+ memmove(skb->cb, &tcp_cb->header, sizeof(tcp_cb->header));
rcu_read_lock();
skb->dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif);
}
mtu = dst_mtu(dst);
- if (!skb->ignore_df && skb->len > mtu) {
+ if (skb->len > mtu) {
skb_dst_update_pmtu_no_confirm(skb, mtu);
if (skb->protocol == htons(ETH_P_IPV6)) {
*/
if (x->km.state == XFRM_STATE_VALID) {
if ((x->sel.family &&
- !xfrm_selector_match(&x->sel, fl, x->sel.family)) ||
+ (x->sel.family != family ||
+ !xfrm_selector_match(&x->sel, fl, family))) ||
!security_xfrm_state_pol_flow_match(x, pol, fl))
return;
*acq_in_progress = 1;
} else if (x->km.state == XFRM_STATE_ERROR ||
x->km.state == XFRM_STATE_EXPIRED) {
- if (xfrm_selector_match(&x->sel, fl, x->sel.family) &&
+ if ((!x->sel.family ||
+ (x->sel.family == family &&
+ xfrm_selector_match(&x->sel, fl, family))) &&
security_xfrm_state_pol_flow_match(x, pol, fl))
*error = -ESRCH;
}
tmpl->mode == x->props.mode &&
tmpl->id.proto == x->id.proto &&
(tmpl->id.spi == x->id.spi || !tmpl->id.spi))
- xfrm_state_look_at(pol, x, fl, encap_family,
+ xfrm_state_look_at(pol, x, fl, family,
&best, &acquire_in_progress, &error);
}
if (best || acquire_in_progress)
tmpl->mode == x->props.mode &&
tmpl->id.proto == x->id.proto &&
(tmpl->id.spi == x->id.spi || !tmpl->id.spi))
- xfrm_state_look_at(pol, x, fl, encap_family,
+ xfrm_state_look_at(pol, x, fl, family,
&best, &acquire_in_progress, &error);
}
EXPORT_SYMBOL(xfrm_state_add);
#ifdef CONFIG_XFRM_MIGRATE
+static inline int clone_security(struct xfrm_state *x, struct xfrm_sec_ctx *security)
+{
+ struct xfrm_user_sec_ctx *uctx;
+ int size = sizeof(*uctx) + security->ctx_len;
+ int err;
+
+ uctx = kmalloc(size, GFP_KERNEL);
+ if (!uctx)
+ return -ENOMEM;
+
+ uctx->exttype = XFRMA_SEC_CTX;
+ uctx->len = size;
+ uctx->ctx_doi = security->ctx_doi;
+ uctx->ctx_alg = security->ctx_alg;
+ uctx->ctx_len = security->ctx_len;
+ memcpy(uctx + 1, security->ctx_str, security->ctx_len);
+ err = security_xfrm_state_alloc(x, uctx);
+ kfree(uctx);
+ if (err)
+ return err;
+
+ return 0;
+}
+
static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
struct xfrm_encap_tmpl *encap)
{
goto error;
}
+ if (orig->security)
+ if (clone_security(x, orig->security))
+ goto error;
+
if (orig->coaddr) {
x->coaddr = kmemdup(orig->coaddr, sizeof(*x->coaddr),
GFP_KERNEL);
}
memcpy(&x->mark, &orig->mark, sizeof(x->mark));
+ memcpy(&x->props.smark, &orig->props.smark, sizeof(x->props.smark));
if (xfrm_init_state(x) < 0)
goto error;
x->tfcpad = orig->tfcpad;
x->replay_maxdiff = orig->replay_maxdiff;
x->replay_maxage = orig->replay_maxage;
- x->curlft.add_time = orig->curlft.add_time;
+ memcpy(&x->curlft, &orig->curlft, sizeof(x->curlft));
x->km.state = orig->km.state;
x->km.seq = orig->km.seq;
x->replay = orig->replay;
LIBBPF = $(LIBBPF_PATH)libbpf.a
-BPFTOOL_VERSION := $(shell make -rR --no-print-directory -sC ../../.. kernelversion)
+BPFTOOL_VERSION ?= $(shell make -rR --no-print-directory -sC ../../.. kernelversion)
$(LIBBPF): FORCE
$(if $(LIBBPF_OUTPUT),@mkdir -p $(LIBBPF_OUTPUT))
err = -EIO;
goto err_out;
}
+ if (magic == __bswap_16(BTF_MAGIC)) {
+ /* non-native endian raw BTF */
+ pr_warn("non-native BTF endianness is not supported\n");
+ err = -LIBBPF_ERRNO__ENDIAN;
+ goto err_out;
+ }
if (magic != BTF_MAGIC) {
/* definitely not a raw BTF */
err = -EPROTO;
BPF_XDP_DEVMAP),
BPF_EAPROG_SEC("xdp_cpumap/", BPF_PROG_TYPE_XDP,
BPF_XDP_CPUMAP),
- BPF_EAPROG_SEC("xdp", BPF_PROG_TYPE_XDP,
+ BPF_APROG_SEC("xdp", BPF_PROG_TYPE_XDP,
BPF_XDP),
BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT),
BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN),
projects / platform / kernel / linux-starfive.git / commitdiff