From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ... --- drivers/mmc/host/cqhci-crypto.c | 243 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 243 insertions(+) create mode 100644 drivers/mmc/host/cqhci-crypto.c (limited to 'drivers/mmc/host/cqhci-crypto.c') diff --git a/drivers/mmc/host/cqhci-crypto.c b/drivers/mmc/host/cqhci-crypto.c new file mode 100644 index 000000000..d5f4b6972 --- /dev/null +++ b/drivers/mmc/host/cqhci-crypto.c @@ -0,0 +1,243 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * CQHCI crypto engine (inline encryption) support + * + * Copyright 2020 Google LLC + */ + +#include +#include +#include + +#include "cqhci-crypto.h" + +/* Map from blk-crypto modes to CQHCI crypto algorithm IDs and key sizes */ +static const struct cqhci_crypto_alg_entry { + enum cqhci_crypto_alg alg; + enum cqhci_crypto_key_size key_size; +} cqhci_crypto_algs[BLK_ENCRYPTION_MODE_MAX] = { + [BLK_ENCRYPTION_MODE_AES_256_XTS] = { + .alg = CQHCI_CRYPTO_ALG_AES_XTS, + .key_size = CQHCI_CRYPTO_KEY_SIZE_256, + }, +}; + +static inline struct cqhci_host * +cqhci_host_from_crypto_profile(struct blk_crypto_profile *profile) +{ + struct mmc_host *mmc = + container_of(profile, struct mmc_host, crypto_profile); + + return mmc->cqe_private; +} + +static int cqhci_crypto_program_key(struct cqhci_host *cq_host, + const union cqhci_crypto_cfg_entry *cfg, + int slot) +{ + u32 slot_offset = cq_host->crypto_cfg_register + slot * sizeof(*cfg); + int i; + + if (cq_host->ops->program_key) + return cq_host->ops->program_key(cq_host, cfg, slot); + + /* Clear CFGE */ + cqhci_writel(cq_host, 0, slot_offset + 16 * sizeof(cfg->reg_val[0])); + + /* Write the key */ + for (i = 0; i < 16; i++) { + cqhci_writel(cq_host, le32_to_cpu(cfg->reg_val[i]), + slot_offset + i * sizeof(cfg->reg_val[0])); + } + /* Write dword 17 */ + cqhci_writel(cq_host, le32_to_cpu(cfg->reg_val[17]), + slot_offset + 17 * sizeof(cfg->reg_val[0])); + /* Write dword 16, which includes the new value of CFGE */ + cqhci_writel(cq_host, le32_to_cpu(cfg->reg_val[16]), + slot_offset + 16 * sizeof(cfg->reg_val[0])); + return 0; +} + +static int cqhci_crypto_keyslot_program(struct blk_crypto_profile *profile, + const struct blk_crypto_key *key, + unsigned int slot) + +{ + struct cqhci_host *cq_host = cqhci_host_from_crypto_profile(profile); + const union cqhci_crypto_cap_entry *ccap_array = + cq_host->crypto_cap_array; + const struct cqhci_crypto_alg_entry *alg = + &cqhci_crypto_algs[key->crypto_cfg.crypto_mode]; + u8 data_unit_mask = key->crypto_cfg.data_unit_size / 512; + int i; + int cap_idx = -1; + union cqhci_crypto_cfg_entry cfg = {}; + int err; + + BUILD_BUG_ON(CQHCI_CRYPTO_KEY_SIZE_INVALID != 0); + for (i = 0; i < cq_host->crypto_capabilities.num_crypto_cap; i++) { + if (ccap_array[i].algorithm_id == alg->alg && + ccap_array[i].key_size == alg->key_size && + (ccap_array[i].sdus_mask & data_unit_mask)) { + cap_idx = i; + break; + } + } + if (WARN_ON(cap_idx < 0)) + return -EOPNOTSUPP; + + cfg.data_unit_size = data_unit_mask; + cfg.crypto_cap_idx = cap_idx; + cfg.config_enable = CQHCI_CRYPTO_CONFIGURATION_ENABLE; + + if (ccap_array[cap_idx].algorithm_id == CQHCI_CRYPTO_ALG_AES_XTS) { + /* In XTS mode, the blk_crypto_key's size is already doubled */ + memcpy(cfg.crypto_key, key->raw, key->size/2); + memcpy(cfg.crypto_key + CQHCI_CRYPTO_KEY_MAX_SIZE/2, + key->raw + key->size/2, key->size/2); + } else { + memcpy(cfg.crypto_key, key->raw, key->size); + } + + err = cqhci_crypto_program_key(cq_host, &cfg, slot); + + memzero_explicit(&cfg, sizeof(cfg)); + return err; +} + +static int cqhci_crypto_clear_keyslot(struct cqhci_host *cq_host, int slot) +{ + /* + * Clear the crypto cfg on the device. Clearing CFGE + * might not be sufficient, so just clear the entire cfg. + */ + union cqhci_crypto_cfg_entry cfg = {}; + + return cqhci_crypto_program_key(cq_host, &cfg, slot); +} + +static int cqhci_crypto_keyslot_evict(struct blk_crypto_profile *profile, + const struct blk_crypto_key *key, + unsigned int slot) +{ + struct cqhci_host *cq_host = cqhci_host_from_crypto_profile(profile); + + return cqhci_crypto_clear_keyslot(cq_host, slot); +} + +/* + * The keyslot management operations for CQHCI crypto. + * + * Note that the block layer ensures that these are never called while the host + * controller is runtime-suspended. However, the CQE won't necessarily be + * "enabled" when these are called, i.e. CQHCI_ENABLE might not be set in the + * CQHCI_CFG register. But the hardware allows that. + */ +static const struct blk_crypto_ll_ops cqhci_crypto_ops = { + .keyslot_program = cqhci_crypto_keyslot_program, + .keyslot_evict = cqhci_crypto_keyslot_evict, +}; + +static enum blk_crypto_mode_num +cqhci_find_blk_crypto_mode(union cqhci_crypto_cap_entry cap) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(cqhci_crypto_algs); i++) { + BUILD_BUG_ON(CQHCI_CRYPTO_KEY_SIZE_INVALID != 0); + if (cqhci_crypto_algs[i].alg == cap.algorithm_id && + cqhci_crypto_algs[i].key_size == cap.key_size) + return i; + } + return BLK_ENCRYPTION_MODE_INVALID; +} + +/** + * cqhci_crypto_init - initialize CQHCI crypto support + * @cq_host: a cqhci host + * + * If the driver previously set MMC_CAP2_CRYPTO and the CQE declares + * CQHCI_CAP_CS, initialize the crypto support. This involves reading the + * crypto capability registers, initializing the blk_crypto_profile, clearing + * all keyslots, and enabling 128-bit task descriptors. + * + * Return: 0 if crypto was initialized or isn't supported; whether + * MMC_CAP2_CRYPTO remains set indicates which one of those cases it is. + * Also can return a negative errno value on unexpected error. + */ +int cqhci_crypto_init(struct cqhci_host *cq_host) +{ + struct mmc_host *mmc = cq_host->mmc; + struct device *dev = mmc_dev(mmc); + struct blk_crypto_profile *profile = &mmc->crypto_profile; + unsigned int num_keyslots; + unsigned int cap_idx; + enum blk_crypto_mode_num blk_mode_num; + unsigned int slot; + int err = 0; + + if (!(mmc->caps2 & MMC_CAP2_CRYPTO) || + !(cqhci_readl(cq_host, CQHCI_CAP) & CQHCI_CAP_CS)) + goto out; + + cq_host->crypto_capabilities.reg_val = + cpu_to_le32(cqhci_readl(cq_host, CQHCI_CCAP)); + + cq_host->crypto_cfg_register = + (u32)cq_host->crypto_capabilities.config_array_ptr * 0x100; + + cq_host->crypto_cap_array = + devm_kcalloc(dev, cq_host->crypto_capabilities.num_crypto_cap, + sizeof(cq_host->crypto_cap_array[0]), GFP_KERNEL); + if (!cq_host->crypto_cap_array) { + err = -ENOMEM; + goto out; + } + + /* + * CCAP.CFGC is off by one, so the actual number of crypto + * configurations (a.k.a. keyslots) is CCAP.CFGC + 1. + */ + num_keyslots = cq_host->crypto_capabilities.config_count + 1; + + err = devm_blk_crypto_profile_init(dev, profile, num_keyslots); + if (err) + goto out; + + profile->ll_ops = cqhci_crypto_ops; + profile->dev = dev; + + /* Unfortunately, CQHCI crypto only supports 32 DUN bits. */ + profile->max_dun_bytes_supported = 4; + + /* + * Cache all the crypto capabilities and advertise the supported crypto + * modes and data unit sizes to the block layer. + */ + for (cap_idx = 0; cap_idx < cq_host->crypto_capabilities.num_crypto_cap; + cap_idx++) { + cq_host->crypto_cap_array[cap_idx].reg_val = + cpu_to_le32(cqhci_readl(cq_host, + CQHCI_CRYPTOCAP + + cap_idx * sizeof(__le32))); + blk_mode_num = cqhci_find_blk_crypto_mode( + cq_host->crypto_cap_array[cap_idx]); + if (blk_mode_num == BLK_ENCRYPTION_MODE_INVALID) + continue; + profile->modes_supported[blk_mode_num] |= + cq_host->crypto_cap_array[cap_idx].sdus_mask * 512; + } + + /* Clear all the keyslots so that we start in a known state. */ + for (slot = 0; slot < num_keyslots; slot++) + cqhci_crypto_clear_keyslot(cq_host, slot); + + /* CQHCI crypto requires the use of 128-bit task descriptors. */ + cq_host->caps |= CQHCI_TASK_DESC_SZ_128; + + return 0; + +out: + mmc->caps2 &= ~MMC_CAP2_CRYPTO; + return err; +} -- cgit v1.2.3