Files
linux/drivers/crypto/chelsio/chcr_core.c
Linus Torvalds 9ff9b0d392 Merge tag 'net-next-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski:

 - Add redirect_neigh() BPF packet redirect helper, allowing to limit
   stack traversal in common container configs and improving TCP
   back-pressure.

   Daniel reports ~10Gbps => ~15Gbps single stream TCP performance gain.

 - Expand netlink policy support and improve policy export to user
   space. (Ge)netlink core performs request validation according to
   declared policies. Expand the expressiveness of those policies
   (min/max length and bitmasks). Allow dumping policies for particular
   commands. This is used for feature discovery by user space (instead
   of kernel version parsing or trial and error).

 - Support IGMPv3/MLDv2 multicast listener discovery protocols in
   bridge.

 - Allow more than 255 IPv4 multicast interfaces.

 - Add support for Type of Service (ToS) reflection in SYN/SYN-ACK
   packets of TCPv6.

 - In Multi-patch TCP (MPTCP) support concurrent transmission of data on
   multiple subflows in a load balancing scenario. Enhance advertising
   addresses via the RM_ADDR/ADD_ADDR options.

 - Support SMC-Dv2 version of SMC, which enables multi-subnet
   deployments.

 - Allow more calls to same peer in RxRPC.

 - Support two new Controller Area Network (CAN) protocols - CAN-FD and
   ISO 15765-2:2016.

 - Add xfrm/IPsec compat layer, solving the 32bit user space on 64bit
   kernel problem.

 - Add TC actions for implementing MPLS L2 VPNs.

 - Improve nexthop code - e.g. handle various corner cases when nexthop
   objects are removed from groups better, skip unnecessary
   notifications and make it easier to offload nexthops into HW by
   converting to a blocking notifier.

 - Support adding and consuming TCP header options by BPF programs,
   opening the doors for easy experimental and deployment-specific TCP
   option use.

 - Reorganize TCP congestion control (CC) initialization to simplify
   life of TCP CC implemented in BPF.

 - Add support for shipping BPF programs with the kernel and loading
   them early on boot via the User Mode Driver mechanism, hence reusing
   all the user space infra we have.

 - Support sleepable BPF programs, initially targeting LSM and tracing.

 - Add bpf_d_path() helper for returning full path for given 'struct
   path'.

 - Make bpf_tail_call compatible with bpf-to-bpf calls.

 - Allow BPF programs to call map_update_elem on sockmaps.

 - Add BPF Type Format (BTF) support for type and enum discovery, as
   well as support for using BTF within the kernel itself (current use
   is for pretty printing structures).

 - Support listing and getting information about bpf_links via the bpf
   syscall.

 - Enhance kernel interfaces around NIC firmware update. Allow
   specifying overwrite mask to control if settings etc. are reset
   during update; report expected max time operation may take to users;
   support firmware activation without machine reboot incl. limits of
   how much impact reset may have (e.g. dropping link or not).

 - Extend ethtool configuration interface to report IEEE-standard
   counters, to limit the need for per-vendor logic in user space.

 - Adopt or extend devlink use for debug, monitoring, fw update in many
   drivers (dsa loop, ice, ionic, sja1105, qed, mlxsw, mv88e6xxx,
   dpaa2-eth).

 - In mlxsw expose critical and emergency SFP module temperature alarms.
   Refactor port buffer handling to make the defaults more suitable and
   support setting these values explicitly via the DCBNL interface.

 - Add XDP support for Intel's igb driver.

 - Support offloading TC flower classification and filtering rules to
   mscc_ocelot switches.

 - Add PTP support for Marvell Octeontx2 and PP2.2 hardware, as well as
   fixed interval period pulse generator and one-step timestamping in
   dpaa-eth.

 - Add support for various auth offloads in WiFi APs, e.g. SAE (WPA3)
   offload.

 - Add Lynx PHY/PCS MDIO module, and convert various drivers which have
   this HW to use it. Convert mvpp2 to split PCS.

 - Support Marvell Prestera 98DX3255 24-port switch ASICs, as well as
   7-port Mediatek MT7531 IP.

 - Add initial support for QCA6390 and IPQ6018 in ath11k WiFi driver,
   and wcn3680 support in wcn36xx.

 - Improve performance for packets which don't require much offloads on
   recent Mellanox NICs by 20% by making multiple packets share a
   descriptor entry.

 - Move chelsio inline crypto drivers (for TLS and IPsec) from the
   crypto subtree to drivers/net. Move MDIO drivers out of the phy
   directory.

 - Clean up a lot of W=1 warnings, reportedly the actively developed
   subsections of networking drivers should now build W=1 warning free.

 - Make sure drivers don't use in_interrupt() to dynamically adapt their
   code. Convert tasklets to use new tasklet_setup API (sadly this
   conversion is not yet complete).

* tag 'net-next-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2583 commits)
  Revert "bpfilter: Fix build error with CONFIG_BPFILTER_UMH"
  net, sockmap: Don't call bpf_prog_put() on NULL pointer
  bpf, selftest: Fix flaky tcp_hdr_options test when adding addr to lo
  bpf, sockmap: Add locking annotations to iterator
  netfilter: nftables: allow re-computing sctp CRC-32C in 'payload' statements
  net: fix pos incrementment in ipv6_route_seq_next
  net/smc: fix invalid return code in smcd_new_buf_create()
  net/smc: fix valid DMBE buffer sizes
  net/smc: fix use-after-free of delayed events
  bpfilter: Fix build error with CONFIG_BPFILTER_UMH
  cxgb4/ch_ipsec: Replace the module name to ch_ipsec from chcr
  net: sched: Fix suspicious RCU usage while accessing tcf_tunnel_info
  bpf: Fix register equivalence tracking.
  rxrpc: Fix loss of final ack on shutdown
  rxrpc: Fix bundle counting for exclusive connections
  netfilter: restore NF_INET_NUMHOOKS
  ibmveth: Identify ingress large send packets.
  ibmveth: Switch order of ibmveth_helper calls.
  cxgb4: handle 4-tuple PEDIT to NAT mode translation
  selftests: Add VRF route leaking tests
  ...
2020-10-15 18:42:13 -07:00

313 lines
7.9 KiB
C

/**
* This file is part of the Chelsio T4/T5/T6 Ethernet driver for Linux.
*
* Copyright (C) 2011-2016 Chelsio Communications. All rights reserved.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation.
*
* Written and Maintained by:
* Manoj Malviya (manojmalviya@chelsio.com)
* Atul Gupta (atul.gupta@chelsio.com)
* Jitendra Lulla (jlulla@chelsio.com)
* Yeshaswi M R Gowda (yeshaswi@chelsio.com)
* Harsh Jain (harsh@chelsio.com)
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <crypto/aes.h>
#include <crypto/hash.h>
#include "t4_msg.h"
#include "chcr_core.h"
#include "cxgb4_uld.h"
static struct chcr_driver_data drv_data;
typedef int (*chcr_handler_func)(struct adapter *adap, unsigned char *input);
static int cpl_fw6_pld_handler(struct adapter *adap, unsigned char *input);
static void *chcr_uld_add(const struct cxgb4_lld_info *lld);
static int chcr_uld_state_change(void *handle, enum cxgb4_state state);
static chcr_handler_func work_handlers[NUM_CPL_CMDS] = {
[CPL_FW6_PLD] = cpl_fw6_pld_handler,
};
static struct cxgb4_uld_info chcr_uld_info = {
.name = DRV_MODULE_NAME,
.nrxq = MAX_ULD_QSETS,
/* Max ntxq will be derived from fw config file*/
.rxq_size = 1024,
.add = chcr_uld_add,
.state_change = chcr_uld_state_change,
.rx_handler = chcr_uld_rx_handler,
};
static void detach_work_fn(struct work_struct *work)
{
struct chcr_dev *dev;
dev = container_of(work, struct chcr_dev, detach_work.work);
if (atomic_read(&dev->inflight)) {
dev->wqretry--;
if (dev->wqretry) {
pr_debug("Request Inflight Count %d\n",
atomic_read(&dev->inflight));
schedule_delayed_work(&dev->detach_work, WQ_DETACH_TM);
} else {
WARN(1, "CHCR:%d request Still Pending\n",
atomic_read(&dev->inflight));
complete(&dev->detach_comp);
}
} else {
complete(&dev->detach_comp);
}
}
struct uld_ctx *assign_chcr_device(void)
{
struct uld_ctx *u_ctx = NULL;
/*
* When multiple devices are present in system select
* device in round-robin fashion for crypto operations
* Although One session must use the same device to
* maintain request-response ordering.
*/
mutex_lock(&drv_data.drv_mutex);
if (!list_empty(&drv_data.act_dev)) {
u_ctx = drv_data.last_dev;
if (list_is_last(&drv_data.last_dev->entry, &drv_data.act_dev))
drv_data.last_dev = list_first_entry(&drv_data.act_dev,
struct uld_ctx, entry);
else
drv_data.last_dev =
list_next_entry(drv_data.last_dev, entry);
}
mutex_unlock(&drv_data.drv_mutex);
return u_ctx;
}
static void chcr_dev_add(struct uld_ctx *u_ctx)
{
struct chcr_dev *dev;
dev = &u_ctx->dev;
dev->state = CHCR_ATTACH;
atomic_set(&dev->inflight, 0);
mutex_lock(&drv_data.drv_mutex);
list_move(&u_ctx->entry, &drv_data.act_dev);
if (!drv_data.last_dev)
drv_data.last_dev = u_ctx;
mutex_unlock(&drv_data.drv_mutex);
}
static void chcr_dev_init(struct uld_ctx *u_ctx)
{
struct chcr_dev *dev;
dev = &u_ctx->dev;
spin_lock_init(&dev->lock_chcr_dev);
INIT_DELAYED_WORK(&dev->detach_work, detach_work_fn);
init_completion(&dev->detach_comp);
dev->state = CHCR_INIT;
dev->wqretry = WQ_RETRY;
atomic_inc(&drv_data.dev_count);
atomic_set(&dev->inflight, 0);
mutex_lock(&drv_data.drv_mutex);
list_add_tail(&u_ctx->entry, &drv_data.inact_dev);
mutex_unlock(&drv_data.drv_mutex);
}
static int chcr_dev_move(struct uld_ctx *u_ctx)
{
mutex_lock(&drv_data.drv_mutex);
if (drv_data.last_dev == u_ctx) {
if (list_is_last(&drv_data.last_dev->entry, &drv_data.act_dev))
drv_data.last_dev = list_first_entry(&drv_data.act_dev,
struct uld_ctx, entry);
else
drv_data.last_dev =
list_next_entry(drv_data.last_dev, entry);
}
list_move(&u_ctx->entry, &drv_data.inact_dev);
if (list_empty(&drv_data.act_dev))
drv_data.last_dev = NULL;
atomic_dec(&drv_data.dev_count);
mutex_unlock(&drv_data.drv_mutex);
return 0;
}
static int cpl_fw6_pld_handler(struct adapter *adap,
unsigned char *input)
{
struct crypto_async_request *req;
struct cpl_fw6_pld *fw6_pld;
u32 ack_err_status = 0;
int error_status = 0;
fw6_pld = (struct cpl_fw6_pld *)input;
req = (struct crypto_async_request *)(uintptr_t)be64_to_cpu(
fw6_pld->data[1]);
ack_err_status =
ntohl(*(__be32 *)((unsigned char *)&fw6_pld->data[0] + 4));
if (CHK_MAC_ERR_BIT(ack_err_status) || CHK_PAD_ERR_BIT(ack_err_status))
error_status = -EBADMSG;
/* call completion callback with failure status */
if (req) {
error_status = chcr_handle_resp(req, input, error_status);
} else {
pr_err("Incorrect request address from the firmware\n");
return -EFAULT;
}
if (error_status)
atomic_inc(&adap->chcr_stats.error);
return 0;
}
int chcr_send_wr(struct sk_buff *skb)
{
return cxgb4_crypto_send(skb->dev, skb);
}
static void *chcr_uld_add(const struct cxgb4_lld_info *lld)
{
struct uld_ctx *u_ctx;
/* Create the device and add it in the device list */
pr_info_once("%s - version %s\n", DRV_DESC, DRV_VERSION);
if (!(lld->ulp_crypto & ULP_CRYPTO_LOOKASIDE))
return ERR_PTR(-EOPNOTSUPP);
/* Create the device and add it in the device list */
u_ctx = kzalloc(sizeof(*u_ctx), GFP_KERNEL);
if (!u_ctx) {
u_ctx = ERR_PTR(-ENOMEM);
goto out;
}
u_ctx->lldi = *lld;
chcr_dev_init(u_ctx);
out:
return u_ctx;
}
int chcr_uld_rx_handler(void *handle, const __be64 *rsp,
const struct pkt_gl *pgl)
{
struct uld_ctx *u_ctx = (struct uld_ctx *)handle;
struct chcr_dev *dev = &u_ctx->dev;
struct adapter *adap = padap(dev);
const struct cpl_fw6_pld *rpl = (struct cpl_fw6_pld *)rsp;
if (!work_handlers[rpl->opcode]) {
pr_err("Unsupported opcode %d received\n", rpl->opcode);
return 0;
}
if (!pgl)
work_handlers[rpl->opcode](adap, (unsigned char *)&rsp[1]);
else
work_handlers[rpl->opcode](adap, pgl->va);
return 0;
}
static void chcr_detach_device(struct uld_ctx *u_ctx)
{
struct chcr_dev *dev = &u_ctx->dev;
if (dev->state == CHCR_DETACH) {
pr_debug("Detached Event received for already detach device\n");
return;
}
dev->state = CHCR_DETACH;
if (atomic_read(&dev->inflight) != 0) {
schedule_delayed_work(&dev->detach_work, WQ_DETACH_TM);
wait_for_completion(&dev->detach_comp);
}
// Move u_ctx to inactive_dev list
chcr_dev_move(u_ctx);
}
static int chcr_uld_state_change(void *handle, enum cxgb4_state state)
{
struct uld_ctx *u_ctx = handle;
int ret = 0;
switch (state) {
case CXGB4_STATE_UP:
if (u_ctx->dev.state != CHCR_INIT) {
// ALready Initialised.
return 0;
}
chcr_dev_add(u_ctx);
ret = start_crypto();
break;
case CXGB4_STATE_DETACH:
chcr_detach_device(u_ctx);
if (!atomic_read(&drv_data.dev_count))
stop_crypto();
break;
case CXGB4_STATE_START_RECOVERY:
case CXGB4_STATE_DOWN:
default:
break;
}
return ret;
}
static int __init chcr_crypto_init(void)
{
INIT_LIST_HEAD(&drv_data.act_dev);
INIT_LIST_HEAD(&drv_data.inact_dev);
atomic_set(&drv_data.dev_count, 0);
mutex_init(&drv_data.drv_mutex);
drv_data.last_dev = NULL;
cxgb4_register_uld(CXGB4_ULD_CRYPTO, &chcr_uld_info);
return 0;
}
static void __exit chcr_crypto_exit(void)
{
struct uld_ctx *u_ctx, *tmp;
struct adapter *adap;
stop_crypto();
cxgb4_unregister_uld(CXGB4_ULD_CRYPTO);
/* Remove all devices from list */
mutex_lock(&drv_data.drv_mutex);
list_for_each_entry_safe(u_ctx, tmp, &drv_data.act_dev, entry) {
adap = padap(&u_ctx->dev);
memset(&adap->chcr_stats, 0, sizeof(adap->chcr_stats));
list_del(&u_ctx->entry);
kfree(u_ctx);
}
list_for_each_entry_safe(u_ctx, tmp, &drv_data.inact_dev, entry) {
adap = padap(&u_ctx->dev);
memset(&adap->chcr_stats, 0, sizeof(adap->chcr_stats));
list_del(&u_ctx->entry);
kfree(u_ctx);
}
mutex_unlock(&drv_data.drv_mutex);
}
module_init(chcr_crypto_init);
module_exit(chcr_crypto_exit);
MODULE_DESCRIPTION("Crypto Co-processor for Chelsio Terminator cards.");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Chelsio Communications");
MODULE_VERSION(DRV_VERSION);