Merge tag 's390-5.17-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 updates from Heiko Carstens:
 "Besides all the small improvements and cleanups the most notable part
  is the fast vector/SIMD implementation of the ChaCha20 stream cipher,
  which is an adaptation of Andy Polyakov's code for the kernel.

  Summary:

   - add fast vector/SIMD implementation of the ChaCha20 stream cipher,
     which mainly adapts Andy Polyakov's code for the kernel

   - add status attribute to AP queue device so users can easily figure
     out its status

   - fix race in page table release code, and and lots of documentation

   - remove uevent suppress from cio device driver, since it turned out
     that it generated more problems than it solved problems

   - quite a lot of virtual vs physical address confusion fixes

   - various other small improvements and cleanups all over the place"

* tag 's390-5.17-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (39 commits)
  s390/dasd: use default_groups in kobj_type
  s390/sclp_sd: use default_groups in kobj_type
  s390/pci: simplify __pciwb_mio() inline asm
  s390: remove unused TASK_SIZE_OF
  s390/crash_dump: fix virtual vs physical address handling
  s390/crypto: fix compile error for ChaCha20 module
  s390/mm: check 2KB-fragment page on release
  s390/mm: better annotate 2KB pagetable fragments handling
  s390/mm: fix 2KB pgtable release race
  s390/sclp: release SCLP early buffer after kernel initialization
  s390/nmi: disable interrupts on extended save area update
  s390/zcrypt: CCA control CPRB sending
  s390/disassembler: update opcode table
  s390/uv: fix memblock virtual vs physical address confusion
  s390/smp: fix memblock_phys_free() vs memblock_free() confusion
  s390/sclp: fix memblock_phys_free() vs memblock_free() confusion
  s390/exit: remove dead reference to do_exit from copy_thread
  s390/ap: add missing virt_to_phys address conversion
  s390/pgalloc: use pointers instead of unsigned long values
  s390/pgalloc: add virt/phys address handling to base asce functions
  ...

Author: torvalds

arch/s390/configs/debug_defconfig

@@ -770,6 +770,7 @@ CONFIG_CRYPTO_SHA3_256_S390=m
 CONFIG_CRYPTO_SHA3_512_S390=m
 CONFIG_CRYPTO_DES_S390=m
 CONFIG_CRYPTO_AES_S390=m
+CONFIG_CRYPTO_CHACHA_S390=m
 CONFIG_CRYPTO_GHASH_S390=m
 CONFIG_CRYPTO_CRC32_S390=y
 CONFIG_CRYPTO_DEV_VIRTIO=m

arch/s390/configs/defconfig

@@ -757,6 +757,7 @@ CONFIG_CRYPTO_SHA3_256_S390=m
 CONFIG_CRYPTO_SHA3_512_S390=m
 CONFIG_CRYPTO_DES_S390=m
 CONFIG_CRYPTO_AES_S390=m
+CONFIG_CRYPTO_CHACHA_S390=m
 CONFIG_CRYPTO_GHASH_S390=m
 CONFIG_CRYPTO_CRC32_S390=y
 CONFIG_CRYPTO_DEV_VIRTIO=m

arch/s390/crypto/Makefile

@@ -11,9 +11,11 @@ obj-$(CONFIG_CRYPTO_SHA3_512_S390) += sha3_512_s390.o sha_common.o
 obj-$(CONFIG_CRYPTO_DES_S390) += des_s390.o
 obj-$(CONFIG_CRYPTO_AES_S390) += aes_s390.o
 obj-$(CONFIG_CRYPTO_PAES_S390) += paes_s390.o
+obj-$(CONFIG_CRYPTO_CHACHA_S390) += chacha_s390.o
 obj-$(CONFIG_S390_PRNG) += prng.o
 obj-$(CONFIG_CRYPTO_GHASH_S390) += ghash_s390.o
 obj-$(CONFIG_CRYPTO_CRC32_S390) += crc32-vx_s390.o
 obj-$(CONFIG_ARCH_RANDOM) += arch_random.o
 
 crc32-vx_s390-y := crc32-vx.o crc32le-vx.o crc32be-vx.o
+chacha_s390-y := chacha-glue.o chacha-s390.o

arch/s390/crypto/chacha-glue.c

@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * s390 ChaCha stream cipher.
+ *
+ * Copyright IBM Corp. 2021
+ */
+
+#define KMSG_COMPONENT "chacha_s390"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <crypto/internal/chacha.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/algapi.h>
+#include <linux/cpufeature.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sizes.h>
+#include <asm/fpu/api.h>
+#include "chacha-s390.h"
+
+static void chacha20_crypt_s390(u32 *state, u8 *dst, const u8 *src,
+				unsigned int nbytes, const u32 *key,
+				u32 *counter)
+{
+	struct kernel_fpu vxstate;
+
+	kernel_fpu_begin(&vxstate, KERNEL_VXR);
+	chacha20_vx(dst, src, nbytes, key, counter);
+	kernel_fpu_end(&vxstate, KERNEL_VXR);
+
+	*counter += round_up(nbytes, CHACHA_BLOCK_SIZE) / CHACHA_BLOCK_SIZE;
+}
+
+static int chacha20_s390(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
+	u32 state[CHACHA_STATE_WORDS] __aligned(16);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
+	int rc;
+
+	rc = skcipher_walk_virt(&walk, req, false);
+	chacha_init_generic(state, ctx->key, req->iv);
+
+	while (walk.nbytes > 0) {
+		nbytes = walk.nbytes;
+		if (nbytes < walk.total)
+			nbytes = round_down(nbytes, walk.stride);
+
+		if (nbytes <= CHACHA_BLOCK_SIZE) {
+			chacha_crypt_generic(state, walk.dst.virt.addr,
+					     walk.src.virt.addr, nbytes,
+					     ctx->nrounds);
+		} else {
+			chacha20_crypt_s390(state, walk.dst.virt.addr,
+					    walk.src.virt.addr, nbytes,
+					    &state[4], &state[12]);
+		}
+		rc = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+	}
+	return rc;
+}
+
+static struct skcipher_alg chacha_algs[] = {
+	{
+		.base.cra_name		= "chacha20",
+		.base.cra_driver_name	= "chacha20-s390",
+		.base.cra_priority	= 900,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
+		.base.cra_module	= THIS_MODULE,
+
+		.min_keysize		= CHACHA_KEY_SIZE,
+		.max_keysize		= CHACHA_KEY_SIZE,
+		.ivsize			= CHACHA_IV_SIZE,
+		.chunksize		= CHACHA_BLOCK_SIZE,
+		.setkey			= chacha20_setkey,
+		.encrypt		= chacha20_s390,
+		.decrypt		= chacha20_s390,
+	}
+};
+
+static int __init chacha_mod_init(void)
+{
+	return crypto_register_skciphers(chacha_algs, ARRAY_SIZE(chacha_algs));
+}
+
+static void __exit chacha_mod_fini(void)
+{
+	crypto_unregister_skciphers(chacha_algs, ARRAY_SIZE(chacha_algs));
+}
+
+module_cpu_feature_match(VXRS, chacha_mod_init);
+module_exit(chacha_mod_fini);
+
+MODULE_DESCRIPTION("ChaCha20 stream cipher");
+MODULE_LICENSE("GPL v2");
+
+MODULE_ALIAS_CRYPTO("chacha20");