KVM: PPC: Book3S HV: Provide a method for userspace to read and write…

… the HPT

A new ioctl, KVM_PPC_GET_HTAB_FD, returns a file descriptor.  Reads on
this fd return the contents of the HPT (hashed page table), writes
create and/or remove entries in the HPT.  There is a new capability,
KVM_CAP_PPC_HTAB_FD, to indicate the presence of the ioctl.  The ioctl
takes an argument structure with the index of the first HPT entry to
read out and a set of flags.  The flags indicate whether the user is
intending to read or write the HPT, and whether to return all entries
or only the "bolted" entries (those with the bolted bit, 0x10, set in
the first doubleword).

This is intended for use in implementing qemu's savevm/loadvm and for
live migration.  Therefore, on reads, the first pass returns information
about all HPTEs (or all bolted HPTEs).  When the first pass reaches the
end of the HPT, it returns from the read.  Subsequent reads only return
information about HPTEs that have changed since they were last read.
A read that finds no changed HPTEs in the HPT following where the last
read finished will return 0 bytes.

The format of the data provides a simple run-length compression of the
invalid entries.  Each block of data starts with a header that indicates
the index (position in the HPT, which is just an array), the number of
valid entries starting at that index (may be zero), and the number of
invalid entries following those valid entries.  The valid entries, 16
bytes each, follow the header.  The invalid entries are not explicitly
represented.

Signed-off-by: Paul Mackerras <[email protected]>
[agraf: fix documentation]
Signed-off-by: Alexander Graf <[email protected]>

Documentation/virtual/kvm/api.txt

@@ -2071,6 +2071,60 @@ KVM_S390_INT_EXTERNAL_CALL (vcpu) - sigp external call; source cpu in parm
 
 Note that the vcpu ioctl is asynchronous to vcpu execution.
 
+4.78 KVM_PPC_GET_HTAB_FD
+
+Capability: KVM_CAP_PPC_HTAB_FD
+Architectures: powerpc
+Type: vm ioctl
+Parameters: Pointer to struct kvm_get_htab_fd (in)
+Returns: file descriptor number (>= 0) on success, -1 on error
+
+This returns a file descriptor that can be used either to read out the
+entries in the guest's hashed page table (HPT), or to write entries to
+initialize the HPT.  The returned fd can only be written to if the
+KVM_GET_HTAB_WRITE bit is set in the flags field of the argument, and
+can only be read if that bit is clear.  The argument struct looks like
+this:
+
+/* For KVM_PPC_GET_HTAB_FD */
+struct kvm_get_htab_fd {
+	__u64	flags;
+	__u64	start_index;
+	__u64	reserved[2];
+};
+
+/* Values for kvm_get_htab_fd.flags */
+#define KVM_GET_HTAB_BOLTED_ONLY	((__u64)0x1)
+#define KVM_GET_HTAB_WRITE		((__u64)0x2)
+
+The `start_index' field gives the index in the HPT of the entry at
+which to start reading.  It is ignored when writing.
+
+Reads on the fd will initially supply information about all
+"interesting" HPT entries.  Interesting entries are those with the
+bolted bit set, if the KVM_GET_HTAB_BOLTED_ONLY bit is set, otherwise
+all entries.  When the end of the HPT is reached, the read() will
+return.  If read() is called again on the fd, it will start again from
+the beginning of the HPT, but will only return HPT entries that have
+changed since they were last read.
+
+Data read or written is structured as a header (8 bytes) followed by a
+series of valid HPT entries (16 bytes) each.  The header indicates how
+many valid HPT entries there are and how many invalid entries follow
+the valid entries.  The invalid entries are not represented explicitly
+in the stream.  The header format is:
+
+struct kvm_get_htab_header {
+	__u32	index;
+	__u16	n_valid;
+	__u16	n_invalid;
+};
+
+Writes to the fd create HPT entries starting at the index given in the
+header; first `n_valid' valid entries with contents from the data
+written, then `n_invalid' invalid entries, invalidating any previously
+valid entries found.
+
 
 5. The kvm_run structure
 ------------------------

arch/powerpc/include/asm/kvm_book3s_64.h

@@ -246,4 +246,26 @@ static inline bool slot_is_aligned(struct kvm_memory_slot *memslot,
 	return !(memslot->base_gfn & mask) && !(memslot->npages & mask);
 }
 
+/*
+ * This works for 4k, 64k and 16M pages on POWER7,
+ * and 4k and 16M pages on PPC970.
+ */
+static inline unsigned long slb_pgsize_encoding(unsigned long psize)
+{
+	unsigned long senc = 0;
+
+	if (psize > 0x1000) {
+		senc = SLB_VSID_L;
+		if (psize == 0x10000)
+			senc |= SLB_VSID_LP_01;
+	}
+	return senc;
+}
+
+static inline int is_vrma_hpte(unsigned long hpte_v)
+{
+	return (hpte_v & ~0xffffffUL) ==
+		(HPTE_V_1TB_SEG | (VRMA_VSID << (40 - 16)));
+}
+
 #endif /* __ASM_KVM_BOOK3S_64_H__ */

arch/powerpc/include/asm/kvm_ppc.h

@@ -164,6 +164,8 @@ extern void kvmppc_bookehv_exit(void);
 
 extern int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu);
 
+extern int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *);
+
 /*
  * Cuts out inst bits with ordering according to spec.
  * That means the leftmost bit is zero. All given bits are included.

arch/powerpc/include/uapi/asm/kvm.h

@@ -331,6 +331,31 @@ struct kvm_book3e_206_tlb_params {
 	__u32 reserved[8];
 };
 
+/* For KVM_PPC_GET_HTAB_FD */
+struct kvm_get_htab_fd {
+	__u64	flags;
+	__u64	start_index;
+	__u64	reserved[2];
+};
+
+/* Values for kvm_get_htab_fd.flags */
+#define KVM_GET_HTAB_BOLTED_ONLY	((__u64)0x1)
+#define KVM_GET_HTAB_WRITE		((__u64)0x2)
+
+/*
+ * Data read on the file descriptor is formatted as a series of
+ * records, each consisting of a header followed by a series of
+ * `n_valid' HPTEs (16 bytes each), which are all valid.  Following
+ * those valid HPTEs there are `n_invalid' invalid HPTEs, which
+ * are not represented explicitly in the stream.  The same format
+ * is used for writing.
+ */
+struct kvm_get_htab_header {
+	__u32	index;
+	__u16	n_valid;
+	__u16	n_invalid;
+};
+
 #define KVM_REG_PPC_HIOR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x1)
 #define KVM_REG_PPC_IAC1	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x2)
 #define KVM_REG_PPC_IAC2	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x3)