aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/crypto/des3_ede_glue.c
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
committerLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /arch/x86/crypto/des3_ede_glue.c
downloadlinux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz
linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip
Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted
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(). ...
Diffstat (limited to 'arch/x86/crypto/des3_ede_glue.c')
-rw-r--r--arch/x86/crypto/des3_ede_glue.c392
1 files changed, 392 insertions, 0 deletions
diff --git a/arch/x86/crypto/des3_ede_glue.c b/arch/x86/crypto/des3_ede_glue.c
new file mode 100644
index 000000000..abb8b1fe1
--- /dev/null
+++ b/arch/x86/crypto/des3_ede_glue.c
@@ -0,0 +1,392 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Glue Code for assembler optimized version of 3DES
+ *
+ * Copyright © 2014 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
+ *
+ * CBC & ECB parts based on code (crypto/cbc.c,ecb.c) by:
+ * Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au>
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/des.h>
+#include <crypto/internal/skcipher.h>
+#include <linux/crypto.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/types.h>
+
+struct des3_ede_x86_ctx {
+ struct des3_ede_ctx enc;
+ struct des3_ede_ctx dec;
+};
+
+/* regular block cipher functions */
+asmlinkage void des3_ede_x86_64_crypt_blk(const u32 *expkey, u8 *dst,
+ const u8 *src);
+
+/* 3-way parallel cipher functions */
+asmlinkage void des3_ede_x86_64_crypt_blk_3way(const u32 *expkey, u8 *dst,
+ const u8 *src);
+
+static inline void des3_ede_enc_blk(struct des3_ede_x86_ctx *ctx, u8 *dst,
+ const u8 *src)
+{
+ u32 *enc_ctx = ctx->enc.expkey;
+
+ des3_ede_x86_64_crypt_blk(enc_ctx, dst, src);
+}
+
+static inline void des3_ede_dec_blk(struct des3_ede_x86_ctx *ctx, u8 *dst,
+ const u8 *src)
+{
+ u32 *dec_ctx = ctx->dec.expkey;
+
+ des3_ede_x86_64_crypt_blk(dec_ctx, dst, src);
+}
+
+static inline void des3_ede_dec_blk_3way(struct des3_ede_x86_ctx *ctx, u8 *dst,
+ const u8 *src)
+{
+ u32 *dec_ctx = ctx->dec.expkey;
+
+ des3_ede_x86_64_crypt_blk_3way(dec_ctx, dst, src);
+}
+
+static void des3_ede_x86_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
+{
+ des3_ede_enc_blk(crypto_tfm_ctx(tfm), dst, src);
+}
+
+static void des3_ede_x86_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
+{
+ des3_ede_dec_blk(crypto_tfm_ctx(tfm), dst, src);
+}
+
+static int ecb_crypt(struct skcipher_request *req, const u32 *expkey)
+{
+ const unsigned int bsize = DES3_EDE_BLOCK_SIZE;
+ struct skcipher_walk walk;
+ unsigned int nbytes;
+ int err;
+
+ err = skcipher_walk_virt(&walk, req, false);
+
+ while ((nbytes = walk.nbytes)) {
+ u8 *wsrc = walk.src.virt.addr;
+ u8 *wdst = walk.dst.virt.addr;
+
+ /* Process four block batch */
+ if (nbytes >= bsize * 3) {
+ do {
+ des3_ede_x86_64_crypt_blk_3way(expkey, wdst,
+ wsrc);
+
+ wsrc += bsize * 3;
+ wdst += bsize * 3;
+ nbytes -= bsize * 3;
+ } while (nbytes >= bsize * 3);
+
+ if (nbytes < bsize)
+ goto done;
+ }
+
+ /* Handle leftovers */
+ do {
+ des3_ede_x86_64_crypt_blk(expkey, wdst, wsrc);
+
+ wsrc += bsize;
+ wdst += bsize;
+ nbytes -= bsize;
+ } while (nbytes >= bsize);
+
+done:
+ err = skcipher_walk_done(&walk, nbytes);
+ }
+
+ return err;
+}
+
+static int ecb_encrypt(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct des3_ede_x86_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+ return ecb_crypt(req, ctx->enc.expkey);
+}
+
+static int ecb_decrypt(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct des3_ede_x86_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+ return ecb_crypt(req, ctx->dec.expkey);
+}
+
+static unsigned int __cbc_encrypt(struct des3_ede_x86_ctx *ctx,
+ struct skcipher_walk *walk)
+{
+ unsigned int bsize = DES3_EDE_BLOCK_SIZE;
+ unsigned int nbytes = walk->nbytes;
+ u64 *src = (u64 *)walk->src.virt.addr;
+ u64 *dst = (u64 *)walk->dst.virt.addr;
+ u64 *iv = (u64 *)walk->iv;
+
+ do {
+ *dst = *src ^ *iv;
+ des3_ede_enc_blk(ctx, (u8 *)dst, (u8 *)dst);
+ iv = dst;
+
+ src += 1;
+ dst += 1;
+ nbytes -= bsize;
+ } while (nbytes >= bsize);
+
+ *(u64 *)walk->iv = *iv;
+ return nbytes;
+}
+
+static int cbc_encrypt(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct des3_ede_x86_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct skcipher_walk walk;
+ unsigned int nbytes;
+ int err;
+
+ err = skcipher_walk_virt(&walk, req, false);
+
+ while (walk.nbytes) {
+ nbytes = __cbc_encrypt(ctx, &walk);
+ err = skcipher_walk_done(&walk, nbytes);
+ }
+
+ return err;
+}
+
+static unsigned int __cbc_decrypt(struct des3_ede_x86_ctx *ctx,
+ struct skcipher_walk *walk)
+{
+ unsigned int bsize = DES3_EDE_BLOCK_SIZE;
+ unsigned int nbytes = walk->nbytes;
+ u64 *src = (u64 *)walk->src.virt.addr;
+ u64 *dst = (u64 *)walk->dst.virt.addr;
+ u64 ivs[3 - 1];
+ u64 last_iv;
+
+ /* Start of the last block. */
+ src += nbytes / bsize - 1;
+ dst += nbytes / bsize - 1;
+
+ last_iv = *src;
+
+ /* Process four block batch */
+ if (nbytes >= bsize * 3) {
+ do {
+ nbytes -= bsize * 3 - bsize;
+ src -= 3 - 1;
+ dst -= 3 - 1;
+
+ ivs[0] = src[0];
+ ivs[1] = src[1];
+
+ des3_ede_dec_blk_3way(ctx, (u8 *)dst, (u8 *)src);
+
+ dst[1] ^= ivs[0];
+ dst[2] ^= ivs[1];
+
+ nbytes -= bsize;
+ if (nbytes < bsize)
+ goto done;
+
+ *dst ^= *(src - 1);
+ src -= 1;
+ dst -= 1;
+ } while (nbytes >= bsize * 3);
+ }
+
+ /* Handle leftovers */
+ for (;;) {
+ des3_ede_dec_blk(ctx, (u8 *)dst, (u8 *)src);
+
+ nbytes -= bsize;
+ if (nbytes < bsize)
+ break;
+
+ *dst ^= *(src - 1);
+ src -= 1;
+ dst -= 1;
+ }
+
+done:
+ *dst ^= *(u64 *)walk->iv;
+ *(u64 *)walk->iv = last_iv;
+
+ return nbytes;
+}
+
+static int cbc_decrypt(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct des3_ede_x86_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct skcipher_walk walk;
+ unsigned int nbytes;
+ int err;
+
+ err = skcipher_walk_virt(&walk, req, false);
+
+ while (walk.nbytes) {
+ nbytes = __cbc_decrypt(ctx, &walk);
+ err = skcipher_walk_done(&walk, nbytes);
+ }
+
+ return err;
+}
+
+static int des3_ede_x86_setkey(struct crypto_tfm *tfm, const u8 *key,
+ unsigned int keylen)
+{
+ struct des3_ede_x86_ctx *ctx = crypto_tfm_ctx(tfm);
+ u32 i, j, tmp;
+ int err;
+
+ err = des3_ede_expand_key(&ctx->enc, key, keylen);
+ if (err == -ENOKEY) {
+ if (crypto_tfm_get_flags(tfm) & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)
+ err = -EINVAL;
+ else
+ err = 0;
+ }
+
+ if (err) {
+ memset(ctx, 0, sizeof(*ctx));
+ return err;
+ }
+
+ /* Fix encryption context for this implementation and form decryption
+ * context. */
+ j = DES3_EDE_EXPKEY_WORDS - 2;
+ for (i = 0; i < DES3_EDE_EXPKEY_WORDS; i += 2, j -= 2) {
+ tmp = ror32(ctx->enc.expkey[i + 1], 4);
+ ctx->enc.expkey[i + 1] = tmp;
+
+ ctx->dec.expkey[j + 0] = ctx->enc.expkey[i + 0];
+ ctx->dec.expkey[j + 1] = tmp;
+ }
+
+ return 0;
+}
+
+static int des3_ede_x86_setkey_skcipher(struct crypto_skcipher *tfm,
+ const u8 *key,
+ unsigned int keylen)
+{
+ return des3_ede_x86_setkey(&tfm->base, key, keylen);
+}
+
+static struct crypto_alg des3_ede_cipher = {
+ .cra_name = "des3_ede",
+ .cra_driver_name = "des3_ede-asm",
+ .cra_priority = 200,
+ .cra_flags = CRYPTO_ALG_TYPE_CIPHER,
+ .cra_blocksize = DES3_EDE_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct des3_ede_x86_ctx),
+ .cra_alignmask = 0,
+ .cra_module = THIS_MODULE,
+ .cra_u = {
+ .cipher = {
+ .cia_min_keysize = DES3_EDE_KEY_SIZE,
+ .cia_max_keysize = DES3_EDE_KEY_SIZE,
+ .cia_setkey = des3_ede_x86_setkey,
+ .cia_encrypt = des3_ede_x86_encrypt,
+ .cia_decrypt = des3_ede_x86_decrypt,
+ }
+ }
+};
+
+static struct skcipher_alg des3_ede_skciphers[] = {
+ {
+ .base.cra_name = "ecb(des3_ede)",
+ .base.cra_driver_name = "ecb-des3_ede-asm",
+ .base.cra_priority = 300,
+ .base.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+ .base.cra_ctxsize = sizeof(struct des3_ede_x86_ctx),
+ .base.cra_module = THIS_MODULE,
+ .min_keysize = DES3_EDE_KEY_SIZE,
+ .max_keysize = DES3_EDE_KEY_SIZE,
+ .setkey = des3_ede_x86_setkey_skcipher,
+ .encrypt = ecb_encrypt,
+ .decrypt = ecb_decrypt,
+ }, {
+ .base.cra_name = "cbc(des3_ede)",
+ .base.cra_driver_name = "cbc-des3_ede-asm",
+ .base.cra_priority = 300,
+ .base.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+ .base.cra_ctxsize = sizeof(struct des3_ede_x86_ctx),
+ .base.cra_module = THIS_MODULE,
+ .min_keysize = DES3_EDE_KEY_SIZE,
+ .max_keysize = DES3_EDE_KEY_SIZE,
+ .ivsize = DES3_EDE_BLOCK_SIZE,
+ .setkey = des3_ede_x86_setkey_skcipher,
+ .encrypt = cbc_encrypt,
+ .decrypt = cbc_decrypt,
+ }
+};
+
+static bool is_blacklisted_cpu(void)
+{
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+ return false;
+
+ if (boot_cpu_data.x86 == 0x0f) {
+ /*
+ * On Pentium 4, des3_ede-x86_64 is slower than generic C
+ * implementation because use of 64bit rotates (which are really
+ * slow on P4). Therefore blacklist P4s.
+ */
+ return true;
+ }
+
+ return false;
+}
+
+static int force;
+module_param(force, int, 0);
+MODULE_PARM_DESC(force, "Force module load, ignore CPU blacklist");
+
+static int __init des3_ede_x86_init(void)
+{
+ int err;
+
+ if (!force && is_blacklisted_cpu()) {
+ pr_info("des3_ede-x86_64: performance on this CPU would be suboptimal: disabling des3_ede-x86_64.\n");
+ return -ENODEV;
+ }
+
+ err = crypto_register_alg(&des3_ede_cipher);
+ if (err)
+ return err;
+
+ err = crypto_register_skciphers(des3_ede_skciphers,
+ ARRAY_SIZE(des3_ede_skciphers));
+ if (err)
+ crypto_unregister_alg(&des3_ede_cipher);
+
+ return err;
+}
+
+static void __exit des3_ede_x86_fini(void)
+{
+ crypto_unregister_alg(&des3_ede_cipher);
+ crypto_unregister_skciphers(des3_ede_skciphers,
+ ARRAY_SIZE(des3_ede_skciphers));
+}
+
+module_init(des3_ede_x86_init);
+module_exit(des3_ede_x86_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Triple DES EDE Cipher Algorithm, asm optimized");
+MODULE_ALIAS_CRYPTO("des3_ede");
+MODULE_ALIAS_CRYPTO("des3_ede-asm");
+MODULE_AUTHOR("Jussi Kivilinna <jussi.kivilinna@iki.fi>");