aboutsummaryrefslogblamecommitdiffstats
path: root/crypto/cts.c
blob: ccf9c5de39584b32d34f26dc9a0e278f812825ac (plain) (tree)


























































































                                                                        


                                


















































































                                                                               


                                












































































































































































                                                                               
/*
 * CTS: Cipher Text Stealing mode
 *
 * COPYRIGHT (c) 2008
 * The Regents of the University of Michigan
 * ALL RIGHTS RESERVED
 *
 * Permission is granted to use, copy, create derivative works
 * and redistribute this software and such derivative works
 * for any purpose, so long as the name of The University of
 * Michigan is not used in any advertising or publicity
 * pertaining to the use of distribution of this software
 * without specific, written prior authorization.  If the
 * above copyright notice or any other identification of the
 * University of Michigan is included in any copy of any
 * portion of this software, then the disclaimer below must
 * also be included.
 *
 * THIS SOFTWARE IS PROVIDED AS IS, WITHOUT REPRESENTATION
 * FROM THE UNIVERSITY OF MICHIGAN AS TO ITS FITNESS FOR ANY
 * PURPOSE, AND WITHOUT WARRANTY BY THE UNIVERSITY OF
 * MICHIGAN OF ANY KIND, EITHER EXPRESS OR IMPLIED, INCLUDING
 * WITHOUT LIMITATION THE IMPLIED WARRANTIES OF
 * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE
 * REGENTS OF THE UNIVERSITY OF MICHIGAN SHALL NOT BE LIABLE
 * FOR ANY DAMAGES, INCLUDING SPECIAL, INDIRECT, INCIDENTAL, OR
 * CONSEQUENTIAL DAMAGES, WITH RESPECT TO ANY CLAIM ARISING
 * OUT OF OR IN CONNECTION WITH THE USE OF THE SOFTWARE, EVEN
 * IF IT HAS BEEN OR IS HEREAFTER ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGES.
 */

/* Derived from various:
 *	Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au>
 */

/*
 * This is the Cipher Text Stealing mode as described by
 * Section 8 of rfc2040 and referenced by rfc3962.
 * rfc3962 includes errata information in its Appendix A.
 */

#include <crypto/algapi.h>
#include <linux/err.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/log2.h>
#include <linux/module.h>
#include <linux/scatterlist.h>
#include <crypto/scatterwalk.h>
#include <linux/slab.h>

struct crypto_cts_ctx {
	struct crypto_blkcipher *child;
};

static int crypto_cts_setkey(struct crypto_tfm *parent, const u8 *key,
			     unsigned int keylen)
{
	struct crypto_cts_ctx *ctx = crypto_tfm_ctx(parent);
	struct crypto_blkcipher *child = ctx->child;
	int err;

	crypto_blkcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
	crypto_blkcipher_set_flags(child, crypto_tfm_get_flags(parent) &
				       CRYPTO_TFM_REQ_MASK);
	err = crypto_blkcipher_setkey(child, key, keylen);
	crypto_tfm_set_flags(parent, crypto_blkcipher_get_flags(child) &
				     CRYPTO_TFM_RES_MASK);
	return err;
}

static int cts_cbc_encrypt(struct crypto_cts_ctx *ctx,
			   struct blkcipher_desc *desc,
			   struct scatterlist *dst,
			   struct scatterlist *src,
			   unsigned int offset,
			   unsigned int nbytes)
{
	int bsize = crypto_blkcipher_blocksize(desc->tfm);
	u8 tmp[bsize], tmp2[bsize];
	struct blkcipher_desc lcldesc;
	struct scatterlist sgsrc[1], sgdst[1];
	int lastn = nbytes - bsize;
	u8 iv[bsize];
	u8 s[bsize * 2], d[bsize * 2];
	int err;

	if (lastn < 0)
		return -EINVAL;

	sg_init_table(sgsrc, 1);
	sg_init_table(sgdst, 1);

	memset(s, 0, sizeof(s));
	scatterwalk_map_and_copy(s, src, offset, nbytes, 0);

	memcpy(iv, desc->info, bsize);

	lcldesc.tfm = ctx->child;
	lcldesc.info = iv;
	lcldesc.flags = desc->flags;

	sg_set_buf(&sgsrc[0], s, bsize);
	sg_set_buf(&sgdst[0], tmp, bsize);
	err = crypto_blkcipher_encrypt_iv(&lcldesc, sgdst, sgsrc, bsize);

	memcpy(d + bsize, tmp, lastn);

	lcldesc.info = tmp;

	sg_set_buf(&sgsrc[0], s + bsize, bsize);
	sg_set_buf(&sgdst[0], tmp2, bsize);
	err = crypto_blkcipher_encrypt_iv(&lcldesc, sgdst, sgsrc, bsize);

	memcpy(d, tmp2, bsize);

	scatterwalk_map_and_copy(d, dst, offset, nbytes, 1);

	memcpy(desc->info, tmp2, bsize);

	return err;
}

static int crypto_cts_encrypt(struct blkcipher_desc *desc,
			      struct scatterlist *dst, struct scatterlist *src,
			      unsigned int nbytes)
{
	struct crypto_cts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
	int bsize = crypto_blkcipher_blocksize(desc->tfm);
	int tot_blocks = (nbytes + bsize - 1) / bsize;
	int cbc_blocks = tot_blocks > 2 ? tot_blocks - 2 : 0;
	struct blkcipher_desc lcldesc;
	int err;

	lcldesc.tfm = ctx->child;
	lcldesc.info = desc->info;
	lcldesc.flags = desc->flags;

	if (tot_blocks == 1) {
		err = crypto_blkcipher_encrypt_iv(&lcldesc, dst, src, bsize);
	} else if (nbytes <= bsize * 2) {
		err = cts_cbc_encrypt(ctx, desc, dst, src, 0, nbytes);
	} else {
		/* do normal function for tot_blocks - 2 */
		err = crypto_blkcipher_encrypt_iv(&lcldesc, dst, src,
							cbc_blocks * bsize);
		if (err == 0) {
			/* do cts for final two blocks */
			err = cts_cbc_encrypt(ctx, desc, dst, src,
						cbc_blocks * bsize,
						nbytes - (cbc_blocks * bsize));
		}
	}

	return err;
}

static int cts_cbc_decrypt(struct crypto_cts_ctx *ctx,
			   struct blkcipher_desc *desc,
			   struct scatterlist *dst,
			   struct scatterlist *src,
			   unsigned int offset,
			   unsigned int nbytes)
{
	int bsize = crypto_blkcipher_blocksize(desc->tfm);
	u8 tmp[bsize];
	struct blkcipher_desc lcldesc;
	struct scatterlist sgsrc[1], sgdst[1];
	int lastn = nbytes - bsize;
	u8 iv[bsize];
	u8 s[bsize * 2], d[bsize * 2];
	int err;

	if (lastn < 0)
		return -EINVAL;

	sg_init_table(sgsrc, 1);
	sg_init_table(sgdst, 1);

	scatterwalk_map_and_copy(s, src, offset, nbytes, 0);

	lcldesc.tfm = ctx->child;
	lcldesc.info = iv;
	lcldesc.flags = desc->flags;

	/* 1. Decrypt Cn-1 (s) to create Dn (tmp)*/
	memset(iv, 0, sizeof(iv));
	sg_set_buf(&sgsrc[0], s, bsize);
	sg_set_buf(&sgdst[0], tmp, bsize);
	err = crypto_blkcipher_decrypt_iv(&lcldesc, sgdst, sgsrc, bsize);
	if (err)
		return err;
	/* 2. Pad Cn with zeros at the end to create C of length BB */
	memset(iv, 0, sizeof(iv));
	memcpy(iv, s + bsize, lastn);
	/* 3. Exclusive-or Dn (tmp) with C (iv) to create Xn (tmp) */
	crypto_xor(tmp, iv, bsize);
	/* 4. Select the first Ln bytes of Xn (tmp) to create Pn */
	memcpy(d + bsize, tmp, lastn);

	/* 5. Append the tail (BB - Ln) bytes of Xn (tmp) to Cn to create En */
	memcpy(s + bsize + lastn, tmp + lastn, bsize - lastn);
	/* 6. Decrypt En to create Pn-1 */
	memset(iv, 0, sizeof(iv));
	sg_set_buf(&sgsrc[0], s + bsize, bsize);
	sg_set_buf(&sgdst[0], d, bsize);
	err = crypto_blkcipher_decrypt_iv(&lcldesc, sgdst, sgsrc, bsize);

	/* XOR with previous block */
	crypto_xor(d, desc->info, bsize);

	scatterwalk_map_and_copy(d, dst, offset, nbytes, 1);

	memcpy(desc->info, s, bsize);
	return err;
}

static int crypto_cts_decrypt(struct blkcipher_desc *desc,
			      struct scatterlist *dst, struct scatterlist *src,
			      unsigned int nbytes)
{
	struct crypto_cts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
	int bsize = crypto_blkcipher_blocksize(desc->tfm);
	int tot_blocks = (nbytes + bsize - 1) / bsize;
	int cbc_blocks = tot_blocks > 2 ? tot_blocks - 2 : 0;
	struct blkcipher_desc lcldesc;
	int err;

	lcldesc.tfm = ctx->child;
	lcldesc.info = desc->info;
	lcldesc.flags = desc->flags;

	if (tot_blocks == 1) {
		err = crypto_blkcipher_decrypt_iv(&lcldesc, dst, src, bsize);
	} else if (nbytes <= bsize * 2) {
		err = cts_cbc_decrypt(ctx, desc, dst, src, 0, nbytes);
	} else {
		/* do normal function for tot_blocks - 2 */
		err = crypto_blkcipher_decrypt_iv(&lcldesc, dst, src,
							cbc_blocks * bsize);
		if (err == 0) {
			/* do cts for final two blocks */
			err = cts_cbc_decrypt(ctx, desc, dst, src,
						cbc_blocks * bsize,
						nbytes - (cbc_blocks * bsize));
		}
	}
	return err;
}

static int crypto_cts_init_tfm(struct crypto_tfm *tfm)
{
	struct crypto_instance *inst = (void *)tfm->__crt_alg;
	struct crypto_spawn *spawn = crypto_instance_ctx(inst);
	struct crypto_cts_ctx *ctx = crypto_tfm_ctx(tfm);
	struct crypto_blkcipher *cipher;

	cipher = crypto_spawn_blkcipher(spawn);
	if (IS_ERR(cipher))
		return PTR_ERR(cipher);

	ctx->child = cipher;
	return 0;
}

static void crypto_cts_exit_tfm(struct crypto_tfm *tfm)
{
	struct crypto_cts_ctx *ctx = crypto_tfm_ctx(tfm);
	crypto_free_blkcipher(ctx->child);
}

static struct crypto_instance *crypto_cts_alloc(struct rtattr **tb)
{
	struct crypto_instance *inst;
	struct crypto_alg *alg;
	int err;

	err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_BLKCIPHER);
	if (err)
		return ERR_PTR(err);

	alg = crypto_attr_alg(tb[1], CRYPTO_ALG_TYPE_BLKCIPHER,
				  CRYPTO_ALG_TYPE_MASK);
	err = PTR_ERR(alg);
	if (IS_ERR(alg))
		return ERR_PTR(err);

	inst = ERR_PTR(-EINVAL);
	if (!is_power_of_2(alg->cra_blocksize))
		goto out_put_alg;

	inst = crypto_alloc_instance("cts", alg);
	if (IS_ERR(inst))
		goto out_put_alg;

	inst->alg.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER;
	inst->alg.cra_priority = alg->cra_priority;
	inst->alg.cra_blocksize = alg->cra_blocksize;
	inst->alg.cra_alignmask = alg->cra_alignmask;
	inst->alg.cra_type = &crypto_blkcipher_type;

	/* We access the data as u32s when xoring. */
	inst->alg.cra_alignmask |= __alignof__(u32) - 1;

	inst->alg.cra_blkcipher.ivsize = alg->cra_blocksize;
	inst->alg.cra_blkcipher.min_keysize = alg->cra_blkcipher.min_keysize;
	inst->alg.cra_blkcipher.max_keysize = alg->cra_blkcipher.max_keysize;

	inst->alg.cra_blkcipher.geniv = "seqiv";

	inst->alg.cra_ctxsize = sizeof(struct crypto_cts_ctx);

	inst->alg.cra_init = crypto_cts_init_tfm;
	inst->alg.cra_exit = crypto_cts_exit_tfm;

	inst->alg.cra_blkcipher.setkey = crypto_cts_setkey;
	inst->alg.cra_blkcipher.encrypt = crypto_cts_encrypt;
	inst->alg.cra_blkcipher.decrypt = crypto_cts_decrypt;

out_put_alg:
	crypto_mod_put(alg);
	return inst;
}

static void crypto_cts_free(struct crypto_instance *inst)
{
	crypto_drop_spawn(crypto_instance_ctx(inst));
	kfree(inst);
}

static struct crypto_template crypto_cts_tmpl = {
	.name = "cts",
	.alloc = crypto_cts_alloc,
	.free = crypto_cts_free,
	.module = THIS_MODULE,
};

static int __init crypto_cts_module_init(void)
{
	return crypto_register_template(&crypto_cts_tmpl);
}

static void __exit crypto_cts_module_exit(void)
{
	crypto_unregister_template(&crypto_cts_tmpl);
}

module_init(crypto_cts_module_init);
module_exit(crypto_cts_module_exit);

MODULE_LICENSE("Dual BSD/GPL");
MODULE_DESCRIPTION("CTS-CBC CipherText Stealing for CBC");
alloc(offsetof(struct vhost_memory, regions), GFP_KERNEL); if (!memory) return -ENOMEM; vhost_dev_cleanup(dev); memory->nregions = 0; dev->memory = memory; return 0; } /* Caller should have device mutex */ void vhost_dev_cleanup(struct vhost_dev *dev) { int i; for (i = 0; i < dev->nvqs; ++i) { if (dev->vqs[i].kick && dev->vqs[i].handle_kick) { vhost_poll_stop(&dev->vqs[i].poll); vhost_poll_flush(&dev->vqs[i].poll); } if (dev->vqs[i].error_ctx) eventfd_ctx_put(dev->vqs[i].error_ctx); if (dev->vqs[i].error) fput(dev->vqs[i].error); if (dev->vqs[i].kick) fput(dev->vqs[i].kick); if (dev->vqs[i].call_ctx) eventfd_ctx_put(dev->vqs[i].call_ctx); if (dev->vqs[i].call) fput(dev->vqs[i].call); vhost_vq_reset(dev, dev->vqs + i); } if (dev->log_ctx) eventfd_ctx_put(dev->log_ctx); dev->log_ctx = NULL; if (dev->log_file) fput(dev->log_file); dev->log_file = NULL; /* No one will access memory at this point */ kfree(dev->memory); dev->memory = NULL; if (dev->mm) mmput(dev->mm); dev->mm = NULL; } static int log_access_ok(void __user *log_base, u64 addr, unsigned long sz) { u64 a = addr / VHOST_PAGE_SIZE / 8; /* Make sure 64 bit math will not overflow. */ if (a > ULONG_MAX - (unsigned long)log_base || a + (unsigned long)log_base > ULONG_MAX) return -EFAULT; return access_ok(VERIFY_WRITE, log_base + a, (sz + VHOST_PAGE_SIZE * 8 - 1) / VHOST_PAGE_SIZE / 8); } /* Caller should have vq mutex and device mutex. */ static int vq_memory_access_ok(void __user *log_base, struct vhost_memory *mem, int log_all) { int i; if (!mem) return 0; for (i = 0; i < mem->nregions; ++i) { struct vhost_memory_region *m = mem->regions + i; unsigned long a = m->userspace_addr; if (m->memory_size > ULONG_MAX) return 0; else if (!access_ok(VERIFY_WRITE, (void __user *)a, m->memory_size)) return 0; else if (log_all && !log_access_ok(log_base, m->guest_phys_addr, m->memory_size)) return 0; } return 1; } /* Can we switch to this memory table? */ /* Caller should have device mutex but not vq mutex */ static int memory_access_ok(struct vhost_dev *d, struct vhost_memory *mem, int log_all) { int i; for (i = 0; i < d->nvqs; ++i) { int ok; mutex_lock(&d->vqs[i].mutex); /* If ring is inactive, will check when it's enabled. */ if (d->vqs[i].private_data) ok = vq_memory_access_ok(d->vqs[i].log_base, mem, log_all); else ok = 1; mutex_unlock(&d->vqs[i].mutex); if (!ok) return 0; } return 1; } static int vq_access_ok(unsigned int num, struct vring_desc __user *desc, struct vring_avail __user *avail, struct vring_used __user *used) { return access_ok(VERIFY_READ, desc, num * sizeof *desc) && access_ok(VERIFY_READ, avail, sizeof *avail + num * sizeof *avail->ring) && access_ok(VERIFY_WRITE, used, sizeof *used + num * sizeof *used->ring); } /* Can we log writes? */ /* Caller should have device mutex but not vq mutex */ int vhost_log_access_ok(struct vhost_dev *dev) { return memory_access_ok(dev, dev->memory, 1); } /* Verify access for write logging. */ /* Caller should have vq mutex and device mutex */ static int vq_log_access_ok(struct vhost_virtqueue *vq, void __user *log_base) { return vq_memory_access_ok(log_base, vq->dev->memory, vhost_has_feature(vq->dev, VHOST_F_LOG_ALL)) && (!vq->log_used || log_access_ok(log_base, vq->log_addr, sizeof *vq->used + vq->num * sizeof *vq->used->ring)); } /* Can we start vq? */ /* Caller should have vq mutex and device mutex */ int vhost_vq_access_ok(struct vhost_virtqueue *vq) { return vq_access_ok(vq->num, vq->desc, vq->avail, vq->used) && vq_log_access_ok(vq, vq->log_base); } static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m) { struct vhost_memory mem, *newmem, *oldmem; unsigned long size = offsetof(struct vhost_memory, regions); long r; r = copy_from_user(&mem, m, size); if (r) return r; if (mem.padding) return -EOPNOTSUPP; if (mem.nregions > VHOST_MEMORY_MAX_NREGIONS) return -E2BIG; newmem = kmalloc(size + mem.nregions * sizeof *m->regions, GFP_KERNEL); if (!newmem) return -ENOMEM; memcpy(newmem, &mem, size); r = copy_from_user(newmem->regions, m->regions, mem.nregions * sizeof *m->regions); if (r) { kfree(newmem); return r; } if (!memory_access_ok(d, newmem, vhost_has_feature(d, VHOST_F_LOG_ALL))) return -EFAULT; oldmem = d->memory; rcu_assign_pointer(d->memory, newmem); synchronize_rcu(); kfree(oldmem); return 0; } static int init_used(struct vhost_virtqueue *vq, struct vring_used __user *used) { int r = put_user(vq->used_flags, &used->flags); if (r) return r; return get_user(vq->last_used_idx, &used->idx); } static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp) { struct file *eventfp, *filep = NULL, *pollstart = NULL, *pollstop = NULL; struct eventfd_ctx *ctx = NULL; u32 __user *idxp = argp; struct vhost_virtqueue *vq; struct vhost_vring_state s; struct vhost_vring_file f; struct vhost_vring_addr a; u32 idx; long r; r = get_user(idx, idxp); if (r < 0) return r; if (idx > d->nvqs) return -ENOBUFS; vq = d->vqs + idx; mutex_lock(&vq->mutex); switch (ioctl) { case VHOST_SET_VRING_NUM: /* Resizing ring with an active backend? * You don't want to do that. */ if (vq->private_data) { r = -EBUSY; break; } r = copy_from_user(&s, argp, sizeof s); if (r < 0) break; if (!s.num || s.num > 0xffff || (s.num & (s.num - 1))) { r = -EINVAL; break; } vq->num = s.num; break; case VHOST_SET_VRING_BASE: /* Moving base with an active backend? * You don't want to do that. */ if (vq->private_data) { r = -EBUSY; break; } r = copy_from_user(&s, argp, sizeof s); if (r < 0) break; if (s.num > 0xffff) { r = -EINVAL; break; } vq->last_avail_idx = s.num; /* Forget the cached index value. */ vq->avail_idx = vq->last_avail_idx; break; case VHOST_GET_VRING_BASE: s.index = idx; s.num = vq->last_avail_idx; r = copy_to_user(argp, &s, sizeof s); break; case VHOST_SET_VRING_ADDR: r = copy_from_user(&a, argp, sizeof a); if (r < 0) break; if (a.flags & ~(0x1 << VHOST_VRING_F_LOG)) { r = -EOPNOTSUPP; break; } /* For 32bit, verify that the top 32bits of the user data are set to zero. */ if ((u64)(unsigned long)a.desc_user_addr != a.desc_user_addr || (u64)(unsigned long)a.used_user_addr != a.used_user_addr || (u64)(unsigned long)a.avail_user_addr != a.avail_user_addr) { r = -EFAULT; break; } if ((a.avail_user_addr & (sizeof *vq->avail->ring - 1)) || (a.used_user_addr & (sizeof *vq->used->ring - 1)) || (a.log_guest_addr & (sizeof *vq->used->ring - 1))) { r = -EINVAL; break; } /* We only verify access here if backend is configured. * If it is not, we don't as size might not have been setup. * We will verify when backend is configured. */ if (vq->private_data) { if (!vq_access_ok(vq->num, (void __user *)(unsigned long)a.desc_user_addr, (void __user *)(unsigned long)a.avail_user_addr, (void __user *)(unsigned long)a.used_user_addr)) { r = -EINVAL; break; } /* 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)) { r = -EINVAL; break; } } r = init_used(vq, (struct vring_used __user *)(unsigned long) a.used_user_addr); if (r) break; vq->log_used = !!(a.flags & (0x1 << VHOST_VRING_F_LOG)); vq->desc = (void __user *)(unsigned long)a.desc_user_addr; vq->avail = (void __user *)(unsigned long)a.avail_user_addr; vq->log_addr = a.log_guest_addr; vq->used = (void __user *)(unsigned long)a.used_user_addr; break; case VHOST_SET_VRING_KICK: r = copy_from_user(&f, argp, sizeof f); if (r < 0) break; eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd); if (IS_ERR(eventfp)) { r = PTR_ERR(eventfp); break; } if (eventfp != vq->kick) { pollstop = filep = vq->kick; pollstart = vq->kick = eventfp; } else filep = eventfp; break; case VHOST_SET_VRING_CALL: r = copy_from_user(&f, argp, sizeof f); if (r < 0) break; eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd); if (IS_ERR(eventfp)) { r = PTR_ERR(eventfp); break; } if (eventfp != vq->call) { filep = vq->call; ctx = vq->call_ctx; vq->call = eventfp; vq->call_ctx = eventfp ? eventfd_ctx_fileget(eventfp) : NULL; } else filep = eventfp; break; case VHOST_SET_VRING_ERR: r = copy_from_user(&f, argp, sizeof f); if (r < 0) break; eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd); if (IS_ERR(eventfp)) { r = PTR_ERR(eventfp); break; } if (eventfp != vq->error) { filep = vq->error; vq->error = eventfp; ctx = vq->error_ctx; vq->error_ctx = eventfp ? eventfd_ctx_fileget(eventfp) : NULL; } else filep = eventfp; break; default: r = -ENOIOCTLCMD; } if (pollstop && vq->handle_kick) vhost_poll_stop(&vq->poll); if (ctx) eventfd_ctx_put(ctx); if (filep) fput(filep); if (pollstart && vq->handle_kick) vhost_poll_start(&vq->poll, vq->kick); mutex_unlock(&vq->mutex); if (pollstop && vq->handle_kick) vhost_poll_flush(&vq->poll); return r; } /* Caller must have device mutex */ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, unsigned long arg) { void __user *argp = (void __user *)arg; struct file *eventfp, *filep = NULL; struct eventfd_ctx *ctx = NULL; u64 p; long r; int i, fd; /* If you are not the owner, you can become one */ if (ioctl == VHOST_SET_OWNER) { r = vhost_dev_set_owner(d); goto done; } /* You must be the owner to do anything else */ r = vhost_dev_check_owner(d); if (r) goto done; switch (ioctl) { case VHOST_SET_MEM_TABLE: r = vhost_set_memory(d, argp); break; case VHOST_SET_LOG_BASE: r = copy_from_user(&p, argp, sizeof p); if (r < 0) break; if ((u64)(unsigned long)p != p) { r = -EFAULT; break; } for (i = 0; i < d->nvqs; ++i) { struct vhost_virtqueue *vq; void __user *base = (void __user *)(unsigned long)p; vq = d->vqs + i; mutex_lock(&vq->mutex); /* If ring is inactive, will check when it's enabled. */ if (vq->private_data && !vq_log_access_ok(vq, base)) r = -EFAULT; else vq->log_base = base; mutex_unlock(&vq->mutex); } break; case VHOST_SET_LOG_FD: r = get_user(fd, (int __user *)argp); if (r < 0) break; eventfp = fd == -1 ? NULL : eventfd_fget(fd); if (IS_ERR(eventfp)) { r = PTR_ERR(eventfp); break; } if (eventfp != d->log_file) { filep = d->log_file; ctx = d->log_ctx; d->log_ctx = eventfp ? eventfd_ctx_fileget(eventfp) : NULL; } else filep = eventfp; for (i = 0; i < d->nvqs; ++i) { mutex_lock(&d->vqs[i].mutex); d->vqs[i].log_ctx = d->log_ctx; mutex_unlock(&d->vqs[i].mutex); } if (ctx) eventfd_ctx_put(ctx); if (filep) fput(filep); break; default: r = vhost_set_vring(d, ioctl, argp); break; } done: return r; } static const struct vhost_memory_region *find_region(struct vhost_memory *mem, __u64 addr, __u32 len) { struct vhost_memory_region *reg; int i; /* linear search is not brilliant, but we really have on the order of 6 * regions in practice */ for (i = 0; i < mem->nregions; ++i) { reg = mem->regions + i; if (reg->guest_phys_addr <= addr && reg->guest_phys_addr + reg->memory_size - 1 >= addr) return reg; } return NULL; } /* TODO: This is really inefficient. We need something like get_user() * (instruction directly accesses the data, with an exception table entry * returning -EFAULT). See Documentation/x86/exception-tables.txt. */ static int set_bit_to_user(int nr, void __user *addr) { unsigned long log = (unsigned long)addr; struct page *page; void *base; int bit = nr + (log % PAGE_SIZE) * 8; int r; r = get_user_pages_fast(log, 1, 1, &page); if (r < 0) return r; BUG_ON(r != 1); base = kmap_atomic(page, KM_USER0); set_bit(bit, base); kunmap_atomic(base, KM_USER0); set_page_dirty_lock(page); put_page(page); return 0; } static int log_write(void __user *log_base, u64 write_address, u64 write_length) { int r; if (!write_length) return 0; write_address /= VHOST_PAGE_SIZE; for (;;) { u64 base = (u64)(unsigned long)log_base; u64 log = base + write_address / 8; int bit = write_address % 8; if ((u64)(unsigned long)log != log) return -EFAULT; r = set_bit_to_user(bit, (void __user *)(unsigned long)log); if (r < 0) return r; if (write_length <= VHOST_PAGE_SIZE) break; write_length -= VHOST_PAGE_SIZE; write_address += VHOST_PAGE_SIZE; } return r; } int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log, unsigned int log_num, u64 len) { int i, r; /* Make sure data written is seen before log. */ smp_wmb(); for (i = 0; i < log_num; ++i) { u64 l = min(log[i].len, len); r = log_write(vq->log_base, log[i].addr, l); if (r < 0) return r; len -= l; if (!len) return 0; } if (vq->log_ctx) eventfd_signal(vq->log_ctx, 1); /* Length written exceeds what we have stored. This is a bug. */ BUG(); return 0; } static int translate_desc(struct vhost_dev *dev, u64 addr, u32 len, struct iovec iov[], int iov_size) { const struct vhost_memory_region *reg; struct vhost_memory *mem; struct iovec *_iov; u64 s = 0; int ret = 0; rcu_read_lock(); mem = rcu_dereference(dev->memory); while ((u64)len > s) { u64 size; if (ret >= iov_size) { ret = -ENOBUFS; break; } reg = find_region(mem, addr, len); if (!reg) { ret = -EFAULT; break; } _iov = iov + ret; size = reg->memory_size - addr + reg->guest_phys_addr; _iov->iov_len = min((u64)len, size); _iov->iov_base = (void __user *)(unsigned long) (reg->userspace_addr + addr - reg->guest_phys_addr); s += size; addr += size; ++ret; } rcu_read_unlock(); return ret; } /* Each buffer in the virtqueues is actually a chain of descriptors. This * function returns the next descriptor in the chain, * or -1U if we're at the end. */ static unsigned next_desc(struct vring_desc *desc) { unsigned int next; /* If this descriptor says it doesn't chain, we're done. */ if (!(desc->flags & VRING_DESC_F_NEXT)) return -1U; /* Check they're not leading us off end of descriptors. */ next = desc->next; /* Make sure compiler knows to grab that: we don't want it changing! */ /* We will use the result as an index in an array, so most * architectures only need a compiler barrier here. */ read_barrier_depends(); return next; } static unsigned get_indirect(struct vhost_dev *dev, struct vhost_virtqueue *vq, struct iovec iov[], unsigned int iov_size, unsigned int *out_num, unsigned int *in_num, struct vhost_log *log, unsigned int *log_num, struct vring_desc *indirect) { struct vring_desc desc; unsigned int i = 0, count, found = 0; int ret; /* Sanity check */ if (indirect->len % sizeof desc) { vq_err(vq, "Invalid length in indirect descriptor: " "len 0x%llx not multiple of 0x%zx\n", (unsigned long long)indirect->len, sizeof desc); return -EINVAL; } ret = translate_desc(dev, indirect->addr, indirect->len, vq->indirect, ARRAY_SIZE(vq->indirect)); if (ret < 0) { vq_err(vq, "Translation failure %d in indirect.\n", ret); return ret; } /* We will use the result as an address to read from, so most * architectures only need a compiler barrier here. */ read_barrier_depends(); count = indirect->len / sizeof desc; /* Buffers are chained via a 16 bit next field, so * we can have at most 2^16 of these. */ if (count > USHORT_MAX + 1) { vq_err(vq, "Indirect buffer length too big: %d\n", indirect->len); return -E2BIG; } do { unsigned iov_count = *in_num + *out_num; if (++found > count) { vq_err(vq, "Loop detected: last one at %u " "indirect size %u\n", i, count); return -EINVAL; } if (memcpy_fromiovec((unsigned char *)&desc, vq->indirect, sizeof desc)) { vq_err(vq, "Failed indirect descriptor: idx %d, %zx\n", i, (size_t)indirect->addr + i * sizeof desc); return -EINVAL; } if (desc.flags & VRING_DESC_F_INDIRECT) { vq_err(vq, "Nested indirect descriptor: idx %d, %zx\n", i, (size_t)indirect->addr + i * sizeof desc); return -EINVAL; } ret = translate_desc(dev, desc.addr, desc.len, iov + iov_count, iov_size - iov_count); if (ret < 0) { vq_err(vq, "Translation failure %d indirect idx %d\n", ret, i); return ret; } /* If this is an input descriptor, increment that count. */ if (desc.flags & VRING_DESC_F_WRITE) { *in_num += ret; if (unlikely(log)) { log[*log_num].addr = desc.addr; log[*log_num].len = desc.len; ++*log_num; } } else { /* If it's an output descriptor, they're all supposed * to come before any input descriptors. */ if (*in_num) { vq_err(vq, "Indirect descriptor " "has out after in: idx %d\n", i); return -EINVAL; } *out_num += ret; } } while ((i = next_desc(&desc)) != -1); return 0; } /* This looks in the virtqueue and for the first available buffer, and converts * it to an iovec for convenient access. Since descriptors consist of some * number of output then some number of input descriptors, it's actually two * iovecs, but we pack them into one and note how many of each there were. * * This function returns the descriptor number found, or vq->num (which * is never a valid descriptor number) if none was found. */ unsigned vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq, struct iovec iov[], unsigned int iov_size, unsigned int *out_num, unsigned int *in_num, struct vhost_log *log, unsigned int *log_num) { struct vring_desc desc; unsigned int i, head, found = 0; u16 last_avail_idx; int ret; /* Check it isn't doing very strange things with descriptor numbers. */ last_avail_idx = vq->last_avail_idx; if (get_user(vq->avail_idx, &vq->avail->idx)) { vq_err(vq, "Failed to access avail idx at %p\n", &vq->avail->idx); return vq->num; } if ((u16)(vq->avail_idx - last_avail_idx) > vq->num) { vq_err(vq, "Guest moved used index from %u to %u", last_avail_idx, vq->avail_idx); return vq->num; } /* If there's nothing new since last we looked, return invalid. */ if (vq->avail_idx == last_avail_idx) return vq->num; /* Only get avail ring entries after they have been exposed by guest. */ smp_rmb(); /* Grab the next descriptor number they're advertising, and increment * the index we've seen. */ if (get_user(head, &vq->avail->ring[last_avail_idx % vq->num])) { vq_err(vq, "Failed to read head: idx %d address %p\n", last_avail_idx, &vq->avail->ring[last_avail_idx % vq->num]); return vq->num; } /* If their number is silly, that's an error. */ if (head >= vq->num) { vq_err(vq, "Guest says index %u > %u is available", head, vq->num); return vq->num; } /* When we start there are none of either input nor output. */ *out_num = *in_num = 0; if (unlikely(log)) *log_num = 0; i = head; do { unsigned iov_count = *in_num + *out_num; if (i >= vq->num) { vq_err(vq, "Desc index is %u > %u, head = %u", i, vq->num, head); return vq->num; } if (++found > vq->num) { vq_err(vq, "Loop detected: last one at %u " "vq size %u head %u\n", i, vq->num, head); return vq->num; } ret = copy_from_user(&desc, vq->desc + i, sizeof desc); if (ret) { vq_err(vq, "Failed to get descriptor: idx %d addr %p\n", i, vq->desc + i); return vq->num; } if (desc.flags & VRING_DESC_F_INDIRECT) { ret = get_indirect(dev, vq, iov, iov_size, out_num, in_num, log, log_num, &desc); if (ret < 0) { vq_err(vq, "Failure detected " "in indirect descriptor at idx %d\n", i); return vq->num; } continue; } ret = translate_desc(dev, desc.addr, desc.len, iov + iov_count, iov_size - iov_count); if (ret < 0) { vq_err(vq, "Translation failure %d descriptor idx %d\n", ret, i); return vq->num; } if (desc.flags & VRING_DESC_F_WRITE) { /* If this is an input descriptor, * increment that count. */ *in_num += ret; if (unlikely(log)) { log[*log_num].addr = desc.addr; log[*log_num].len = desc.len; ++*log_num; } } else { /* If it's an output descriptor, they're all supposed * to come before any input descriptors. */ if (*in_num) { vq_err(vq, "Descriptor has out after in: " "idx %d\n", i); return vq->num; } *out_num += ret; } } while ((i = next_desc(&desc)) != -1); /* On success, increment avail index. */ vq->last_avail_idx++; return head; } /* Reverse the effect of vhost_get_vq_desc. Useful for error handling. */ void vhost_discard_vq_desc(struct vhost_virtqueue *vq) { vq->last_avail_idx--; } /* After we've used one of their buffers, we tell them about it. We'll then * want to notify the guest, using eventfd. */ int vhost_add_used(struct vhost_virtqueue *vq, unsigned int head, int len) { struct vring_used_elem __user *used; /* The virtqueue contains a ring of used buffers. Get a pointer to the * next entry in that used ring. */ used = &vq->used->ring[vq->last_used_idx % vq->num]; if (put_user(head, &used->id)) { vq_err(vq, "Failed to write used id"); return -EFAULT; } if (put_user(len, &used->len)) { vq_err(vq, "Failed to write used len"); return -EFAULT; } /* Make sure buffer is written before we update index. */ smp_wmb(); if (put_user(vq->last_used_idx + 1, &vq->used->idx)) { vq_err(vq, "Failed to increment used idx"); return -EFAULT; } if (unlikely(vq->log_used)) { /* Make sure data is seen before log. */ smp_wmb(); /* Log used ring entry write. */ log_write(vq->log_base, vq->log_addr + ((void __user *)used - (void __user *)vq->used), sizeof *used); /* Log used index update. */ log_write(vq->log_base, vq->log_addr + offsetof(struct vring_used, idx), sizeof vq->used->idx); if (vq->log_ctx) eventfd_signal(vq->log_ctx, 1); } vq->last_used_idx++; return 0; } /* This actually signals the guest, using eventfd. */ void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq) { __u16 flags = 0; if (get_user(flags, &vq->avail->flags)) { vq_err(vq, "Failed to get flags"); return; } /* If they don't want an interrupt, don't signal, unless empty. */ if ((flags & VRING_AVAIL_F_NO_INTERRUPT) && (vq->avail_idx != vq->last_avail_idx || !vhost_has_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY))) return; /* Signal the Guest tell them we used something up. */ if (vq->call_ctx) eventfd_signal(vq->call_ctx, 1); } /* And here's the combo meal deal. Supersize me! */ void vhost_add_used_and_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq, unsigned int head, int len) { vhost_add_used(vq, head, len); vhost_signal(dev, vq); } /* OK, now we need to know about added descriptors. */ bool vhost_enable_notify(struct vhost_virtqueue *vq) { u16 avail_idx; int r; if (!(vq->used_flags & VRING_USED_F_NO_NOTIFY)) return false; vq->used_flags &= ~VRING_USED_F_NO_NOTIFY; r = put_user(vq->used_flags, &vq->used->flags); if (r) { vq_err(vq, "Failed to enable notification at %p: %d\n", &vq->used->flags, r); return false; } /* They could have slipped one in as we were doing that: make * sure it's written, then check again. */ smp_mb(); r = get_user(avail_idx, &vq->avail->idx); if (r) { vq_err(vq, "Failed to check avail idx at %p: %d\n", &vq->avail->idx, r); return false; } return avail_idx != vq->last_avail_idx; } /* We don't need to be notified again. */ void vhost_disable_notify(struct vhost_virtqueue *vq) { int r; if (vq->used_flags & VRING_USED_F_NO_NOTIFY) return; vq->used_flags |= VRING_USED_F_NO_NOTIFY; r = put_user(vq->used_flags, &vq->used->flags); if (r) vq_err(vq, "Failed to enable notification at %p: %d\n", &vq->used->flags, r); } int vhost_init(void) { vhost_workqueue = create_singlethread_workqueue("vhost"); if (!vhost_workqueue) return -ENOMEM; return 0; } void vhost_cleanup(void) { destroy_workqueue(vhost_workqueue); }