KVM: s390: ioctls to get and set guest storage attributes

* Add the struct used in the ioctls to get and set CMMA attributes.
* Add the two functions needed to get and set the CMMA attributes for
  guest pages.
* Add the two ioctls that use the aforementioned functions.

Signed-off-by: Claudio Imbrenda <imbrenda@linux.vnet.ibm.com>
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>

Documentation/virtual/kvm/api.txt

@@ -3255,6 +3255,141 @@ Otherwise, if the MCE is a corrected error, KVM will just
 store it in the corresponding bank (provided this bank is
 not holding a previously reported uncorrected error).
 
+4.107 KVM_S390_GET_CMMA_BITS
+
+Capability: KVM_CAP_S390_CMMA_MIGRATION
+Architectures: s390
+Type: vm ioctl
+Parameters: struct kvm_s390_cmma_log (in, out)
+Returns: 0 on success, a negative value on error
+
+This ioctl is used to get the values of the CMMA bits on the s390
+architecture. It is meant to be used in two scenarios:
+- During live migration to save the CMMA values. Live migration needs
+  to be enabled via the KVM_REQ_START_MIGRATION VM property.
+- To non-destructively peek at the CMMA values, with the flag
+  KVM_S390_CMMA_PEEK set.
+
+The ioctl takes parameters via the kvm_s390_cmma_log struct. The desired
+values are written to a buffer whose location is indicated via the "values"
+member in the kvm_s390_cmma_log struct.  The values in the input struct are
+also updated as needed.
+Each CMMA value takes up one byte.
+
+struct kvm_s390_cmma_log {
+	__u64 start_gfn;
+	__u32 count;
+	__u32 flags;
+	union {
+		__u64 remaining;
+		__u64 mask;
+	};
+	__u64 values;
+};
+
+start_gfn is the number of the first guest frame whose CMMA values are
+to be retrieved,
+
+count is the length of the buffer in bytes,
+
+values points to the buffer where the result will be written to.
+
+If count is greater than KVM_S390_SKEYS_MAX, then it is considered to be
+KVM_S390_SKEYS_MAX. KVM_S390_SKEYS_MAX is re-used for consistency with
+other ioctls.
+
+The result is written in the buffer pointed to by the field values, and
+the values of the input parameter are updated as follows.
+
+Depending on the flags, different actions are performed. The only
+supported flag so far is KVM_S390_CMMA_PEEK.
+
+The default behaviour if KVM_S390_CMMA_PEEK is not set is:
+start_gfn will indicate the first page frame whose CMMA bits were dirty.
+It is not necessarily the same as the one passed as input, as clean pages
+are skipped.
+
+count will indicate the number of bytes actually written in the buffer.
+It can (and very often will) be smaller than the input value, since the
+buffer is only filled until 16 bytes of clean values are found (which
+are then not copied in the buffer). Since a CMMA migration block needs
+the base address and the length, for a total of 16 bytes, we will send
+back some clean data if there is some dirty data afterwards, as long as
+the size of the clean data does not exceed the size of the header. This
+allows to minimize the amount of data to be saved or transferred over
+the network at the expense of more roundtrips to userspace. The next
+invocation of the ioctl will skip over all the clean values, saving
+potentially more than just the 16 bytes we found.
+
+If KVM_S390_CMMA_PEEK is set:
+the existing storage attributes are read even when not in migration
+mode, and no other action is performed;
+
+the output start_gfn will be equal to the input start_gfn,
+
+the output count will be equal to the input count, except if the end of
+memory has been reached.
+
+In both cases:
+the field "remaining" will indicate the total number of dirty CMMA values
+still remaining, or 0 if KVM_S390_CMMA_PEEK is set and migration mode is
+not enabled.
+
+mask is unused.
+
+values points to the userspace buffer where the result will be stored.
+
+This ioctl can fail with -ENOMEM if not enough memory can be allocated to
+complete the task, with -ENXIO if CMMA is not enabled, with -EINVAL if
+KVM_S390_CMMA_PEEK is not set but migration mode was not enabled, with
+-EFAULT if the userspace address is invalid or if no page table is
+present for the addresses (e.g. when using hugepages).
+
+4.108 KVM_S390_SET_CMMA_BITS
+
+Capability: KVM_CAP_S390_CMMA_MIGRATION
+Architectures: s390
+Type: vm ioctl
+Parameters: struct kvm_s390_cmma_log (in)
+Returns: 0 on success, a negative value on error
+
+This ioctl is used to set the values of the CMMA bits on the s390
+architecture. It is meant to be used during live migration to restore
+the CMMA values, but there are no restrictions on its use.
+The ioctl takes parameters via the kvm_s390_cmma_values struct.
+Each CMMA value takes up one byte.
+
+struct kvm_s390_cmma_log {
+	__u64 start_gfn;
+	__u32 count;
+	__u32 flags;
+	union {
+		__u64 remaining;
+		__u64 mask;
+	};
+	__u64 values;
+};
+
+start_gfn indicates the starting guest frame number,
+
+count indicates how many values are to be considered in the buffer,
+
+flags is not used and must be 0.
+
+mask indicates which PGSTE bits are to be considered.
+
+remaining is not used.
+
+values points to the buffer in userspace where to store the values.
+
+This ioctl can fail with -ENOMEM if not enough memory can be allocated to
+complete the task, with -ENXIO if CMMA is not enabled, with -EINVAL if
+the count field is too large (e.g. more than KVM_S390_CMMA_SIZE_MAX) or
+if the flags field was not 0, with -EFAULT if the userspace address is
+invalid, if invalid pages are written to (e.g. after the end of memory)
+or if no page table is present for the addresses (e.g. when using
+hugepages).
+
 5. The kvm_run structure
 ------------------------
 

arch/s390/kvm/kvm-s390.c

@@ -30,8 +30,8 @@
 #include <linux/vmalloc.h>
 #include <linux/bitmap.h>
 #include <linux/sched/signal.h>
-
 #include <linux/string.h>
+
 #include <asm/asm-offsets.h>
 #include <asm/lowcore.h>
 #include <asm/stp.h>
@@ -387,6 +387,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_SKEYS:
 	case KVM_CAP_S390_IRQ_STATE:
 	case KVM_CAP_S390_USER_INSTR0:
+	case KVM_CAP_S390_CMMA_MIGRATION:
 	case KVM_CAP_S390_AIS:
 		r = 1;
 		break;
@@ -1419,6 +1420,182 @@ out:
 	return r;
 }
 
+/*
+ * Base address and length must be sent at the start of each block, therefore
+ * it's cheaper to send some clean data, as long as it's less than the size of
+ * two longs.
+ */
+#define KVM_S390_MAX_BIT_DISTANCE (2 * sizeof(void *))
+/* for consistency */
+#define KVM_S390_CMMA_SIZE_MAX ((u32)KVM_S390_SKEYS_MAX)
+
+/*
+ * This function searches for the next page with dirty CMMA attributes, and
+ * saves the attributes in the buffer up to either the end of the buffer or
+ * until a block of at least KVM_S390_MAX_BIT_DISTANCE clean bits is found;
+ * no trailing clean bytes are saved.
+ * In case no dirty bits were found, or if CMMA was not enabled or used, the
+ * output buffer will indicate 0 as length.
+ */
+static int kvm_s390_get_cmma_bits(struct kvm *kvm,
+				  struct kvm_s390_cmma_log *args)
+{
+	struct kvm_s390_migration_state *s = kvm->arch.migration_state;
+	unsigned long bufsize, hva, pgstev, i, next, cur;
+	int srcu_idx, peek, r = 0, rr;
+	u8 *res;
+
+	cur = args->start_gfn;
+	i = next = pgstev = 0;
+
+	if (unlikely(!kvm->arch.use_cmma))
+		return -ENXIO;
+	/* Invalid/unsupported flags were specified */
+	if (args->flags & ~KVM_S390_CMMA_PEEK)
+		return -EINVAL;
+	/* Migration mode query, and we are not doing a migration */
+	peek = !!(args->flags & KVM_S390_CMMA_PEEK);
+	if (!peek && !s)
+		return -EINVAL;
+	/* CMMA is disabled or was not used, or the buffer has length zero */
+	bufsize = min(args->count, KVM_S390_CMMA_SIZE_MAX);
+	if (!bufsize || !kvm->mm->context.use_cmma) {
+		memset(args, 0, sizeof(*args));
+		return 0;
+	}
+
+	if (!peek) {
+		/* We are not peeking, and there are no dirty pages */
+		if (!atomic64_read(&s->dirty_pages)) {
+			memset(args, 0, sizeof(*args));
+			return 0;
+		}
+		cur = find_next_bit(s->pgste_bitmap, s->bitmap_size,
+				    args->start_gfn);
+		if (cur >= s->bitmap_size)	/* nothing found, loop back */
+			cur = find_next_bit(s->pgste_bitmap, s->bitmap_size, 0);
+		if (cur >= s->bitmap_size) {	/* again! (very unlikely) */
+			memset(args, 0, sizeof(*args));
+			return 0;
+		}
+		next = find_next_bit(s->pgste_bitmap, s->bitmap_size, cur + 1);
+	}
+
+	res = vmalloc(bufsize);
+	if (!res)
+		return -ENOMEM;
+
+	args->start_gfn = cur;
+
+	down_read(&kvm->mm->mmap_sem);
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+	while (i < bufsize) {
+		hva = gfn_to_hva(kvm, cur);
+		if (kvm_is_error_hva(hva)) {
+			r = -EFAULT;
+			break;
+		}
+		/* decrement only if we actually flipped the bit to 0 */
+		if (!peek && test_and_clear_bit(cur, s->pgste_bitmap))
+			atomic64_dec(&s->dirty_pages);
+		r = get_pgste(kvm->mm, hva, &pgstev);
+		if (r < 0)
+			pgstev = 0;
+		/* save the value */
+		res[i++] = (pgstev >> 24) & 0x3;
+		/*
+		 * if the next bit is too far away, stop.
+		 * if we reached the previous "next", find the next one
+		 */
+		if (!peek) {
+			if (next > cur + KVM_S390_MAX_BIT_DISTANCE)
+				break;
+			if (cur == next)
+				next = find_next_bit(s->pgste_bitmap,
+						     s->bitmap_size, cur + 1);
+		/* reached the end of the bitmap or of the buffer, stop */
+			if ((next >= s->bitmap_size) ||
+			    (next >= args->start_gfn + bufsize))
+				break;
+		}
+		cur++;
+	}
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+	up_read(&kvm->mm->mmap_sem);
+	args->count = i;
+	args->remaining = s ? atomic64_read(&s->dirty_pages) : 0;
+
+	rr = copy_to_user((void __user *)args->values, res, args->count);
+	if (rr)
+		r = -EFAULT;
+
+	vfree(res);
+	return r;
+}
+
+/*
+ * This function sets the CMMA attributes for the given pages. If the input
+ * buffer has zero length, no action is taken, otherwise the attributes are
+ * set and the mm->context.use_cmma flag is set.
+ */
+static int kvm_s390_set_cmma_bits(struct kvm *kvm,
+				  const struct kvm_s390_cmma_log *args)
+{
+	unsigned long hva, mask, pgstev, i;
+	uint8_t *bits;
+	int srcu_idx, r = 0;
+
+	mask = args->mask;
+
+	if (!kvm->arch.use_cmma)
+		return -ENXIO;
+	/* invalid/unsupported flags */
+	if (args->flags != 0)
+		return -EINVAL;
+	/* Enforce sane limit on memory allocation */
+	if (args->count > KVM_S390_CMMA_SIZE_MAX)
+		return -EINVAL;
+	/* Nothing to do */
+	if (args->count == 0)
+		return 0;
+
+	bits = vmalloc(sizeof(*bits) * args->count);
+	if (!bits)
+		return -ENOMEM;
+
+	r = copy_from_user(bits, (void __user *)args->values, args->count);
+	if (r) {
+		r = -EFAULT;
+		goto out;
+	}
+
+	down_read(&kvm->mm->mmap_sem);
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+	for (i = 0; i < args->count; i++) {
+		hva = gfn_to_hva(kvm, args->start_gfn + i);
+		if (kvm_is_error_hva(hva)) {
+			r = -EFAULT;
+			break;
+		}
+
+		pgstev = bits[i];
+		pgstev = pgstev << 24;
+		mask &= _PGSTE_GPS_USAGE_MASK;
+		set_pgste_bits(kvm->mm, hva, mask, pgstev);
+	}
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+	up_read(&kvm->mm->mmap_sem);
+
+	if (!kvm->mm->context.use_cmma) {
+		down_write(&kvm->mm->mmap_sem);
+		kvm->mm->context.use_cmma = 1;
+		up_write(&kvm->mm->mmap_sem);
+	}
+out:
+	vfree(bits);
+	return r;
+}
+
 long kvm_arch_vm_ioctl(struct file *filp,
 		       unsigned int ioctl, unsigned long arg)
 {
@@ -1497,6 +1674,29 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = kvm_s390_set_skeys(kvm, &args);
 		break;
 	}
+	case KVM_S390_GET_CMMA_BITS: {
+		struct kvm_s390_cmma_log args;
+
+		r = -EFAULT;
+		if (copy_from_user(&args, argp, sizeof(args)))
+			break;
+		r = kvm_s390_get_cmma_bits(kvm, &args);
+		if (!r) {
+			r = copy_to_user(argp, &args, sizeof(args));
+			if (r)
+				r = -EFAULT;
+		}
+		break;
+	}
+	case KVM_S390_SET_CMMA_BITS: {
+		struct kvm_s390_cmma_log args;
+
+		r = -EFAULT;
+		if (copy_from_user(&args, argp, sizeof(args)))
+			break;
+		r = kvm_s390_set_cmma_bits(kvm, &args);
+		break;
+	}
 	default:
 		r = -ENOTTY;
 	}

include/uapi/linux/kvm.h

@@ -155,6 +155,35 @@ struct kvm_s390_skeys {
 	__u32 reserved[9];
 };
 
+#define KVM_S390_CMMA_PEEK (1 << 0)
+
+/**
+ * kvm_s390_cmma_log - Used for CMMA migration.
+ *
+ * Used both for input and output.
+ *
+ * @start_gfn: Guest page number to start from.
+ * @count: Size of the result buffer.
+ * @flags: Control operation mode via KVM_S390_CMMA_* flags
+ * @remaining: Used with KVM_S390_GET_CMMA_BITS. Indicates how many dirty
+ *             pages are still remaining.
+ * @mask: Used with KVM_S390_SET_CMMA_BITS. Bitmap of bits to actually set
+ *        in the PGSTE.
+ * @values: Pointer to the values buffer.
+ *
+ * Used in KVM_S390_{G,S}ET_CMMA_BITS ioctls.
+ */
+struct kvm_s390_cmma_log {
+	__u64 start_gfn;
+	__u32 count;
+	__u32 flags;
+	union {
+		__u64 remaining;
+		__u64 mask;
+	};
+	__u64 values;
+};
+
 struct kvm_hyperv_exit {
 #define KVM_EXIT_HYPERV_SYNIC          1
 #define KVM_EXIT_HYPERV_HCALL          2
@@ -895,6 +924,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_SPAPR_TCE_VFIO 142
 #define KVM_CAP_X86_GUEST_MWAIT 143
 #define KVM_CAP_ARM_USER_IRQ 144
+#define KVM_CAP_S390_CMMA_MIGRATION 145
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1318,6 +1348,9 @@ struct kvm_s390_ucas_mapping {
 #define KVM_S390_GET_IRQ_STATE	  _IOW(KVMIO, 0xb6, struct kvm_s390_irq_state)
 /* Available with KVM_CAP_X86_SMM */
 #define KVM_SMI                   _IO(KVMIO,   0xb7)
+/* Available with KVM_CAP_S390_CMMA_MIGRATION */
+#define KVM_S390_GET_CMMA_BITS      _IOW(KVMIO, 0xb8, struct kvm_s390_cmma_log)
+#define KVM_S390_SET_CMMA_BITS      _IOW(KVMIO, 0xb9, struct kvm_s390_cmma_log)
 
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
 #define KVM_DEV_ASSIGN_PCI_2_3		(1 << 1)