[PATCH v2 1/3] KVM: PPC: Book3S HV: Add a mechanism for recording modified HPTEs

[PATCH v2 1/3] KVM: PPC: Book3S HV: Add a mechanism for recording modified HPTEs

[Paul Mackerras]

This uses a bit in our record of the guest view of the HPTE to record
when the HPTE gets modified.  We use a reserved bit for this, and ensure
that this bit is always cleared in HPTE values returned to the guest.

The recording of modified HPTEs is only done if other code indicates
its interest by setting kvm->arch.hpte_mod_interest to a non-zero value.
The reason for this is that when later commits add facilities for
userspace to read the HPT, the first pass of reading the HPT will be
quicker if there are no (or very few) HPTEs marked as modified,
rather than having most HPTEs marked as modified.

Signed-off-by: Paul Mackerras <paulus@samba.org>
---
v2: added HPTE_GR_RESERVED, clear those bits in H_ENTER

 arch/powerpc/include/asm/kvm_book3s_64.h |    9 +++++++++
 arch/powerpc/include/asm/kvm_host.h      |    1 +
 arch/powerpc/kvm/book3s_hv_rm_mmu.c      |   28 ++++++++++++++++++++++++----
 3 files changed, 34 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 1472a5b..b322e5b 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -50,6 +50,15 @@ extern int kvm_hpt_order;		/* order of preallocated HPTs */
 #define HPTE_V_HVLOCK	0x40UL
 #define HPTE_V_ABSENT	0x20UL
 
+/*
+ * We use this bit in the guest_rpte field of the revmap entry
+ * to indicate a modified HPTE.
+ */
+#define HPTE_GR_MODIFIED	(1ul << 62)
+
+/* These bits are reserved in the guest view of the HPTE */
+#define HPTE_GR_RESERVED	HPTE_GR_MODIFIED
+
 static inline long try_lock_hpte(unsigned long *hpte, unsigned long bits)
 {
 	unsigned long tmp, old;
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 3093896..58c7264 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -248,6 +248,7 @@ struct kvm_arch {
 	atomic_t vcpus_running;
 	unsigned long hpt_npte;
 	unsigned long hpt_mask;
+	atomic_t hpte_mod_interest;
 	spinlock_t slot_phys_lock;
 	unsigned short last_vcpu[NR_CPUS];
 	struct kvmppc_vcore *vcores[KVM_MAX_VCORES];
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 362dffe..a96f90a 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -66,6 +66,17 @@ void kvmppc_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev,
 }
 EXPORT_SYMBOL_GPL(kvmppc_add_revmap_chain);
 
+/*
+ * Note modification of an HPTE; set the HPTE modified bit
+ * if anyone is interested.
+ */
+static inline void note_hpte_modification(struct kvm *kvm,
+					  struct revmap_entry *rev)
+{
+	if (atomic_read(&kvm->arch.hpte_mod_interest))
+		rev->guest_rpte |= HPTE_GR_MODIFIED;
+}
+
 /* Remove this HPTE from the chain for a real page */
 static void remove_revmap_chain(struct kvm *kvm, long pte_index,
 				struct revmap_entry *rev,
@@ -138,7 +149,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 	unsigned long slot_fn, hva;
 	unsigned long *hpte;
 	struct revmap_entry *rev;
-	unsigned long g_ptel = ptel;
+	unsigned long g_ptel;
 	struct kvm_memory_slot *memslot;
 	unsigned long *physp, pte_size;
 	unsigned long is_io;
@@ -153,6 +164,8 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 		return H_PARAMETER;
 	writing = hpte_is_writable(ptel);
 	pteh &= ~(HPTE_V_HVLOCK | HPTE_V_ABSENT | HPTE_V_VALID);
+	ptel &= ~HPTE_GR_RESERVED;
+	g_ptel = ptel;
 
 	/* used later to detect if we might have been invalidated */
 	mmu_seq = kvm->mmu_notifier_seq;
@@ -287,8 +300,10 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 	rev = &kvm->arch.revmap[pte_index];
 	if (realmode)
 		rev = real_vmalloc_addr(rev);
-	if (rev)
+	if (rev) {
 		rev->guest_rpte = g_ptel;
+		note_hpte_modification(kvm, rev);
+	}
 
 	/* Link HPTE into reverse-map chain */
 	if (pteh & HPTE_V_VALID) {
@@ -392,7 +407,8 @@ long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags,
 		/* Read PTE low word after tlbie to get final R/C values */
 		remove_revmap_chain(kvm, pte_index, rev, v, hpte[1]);
 	}
-	r = rev->guest_rpte;
+	r = rev->guest_rpte & ~HPTE_GR_RESERVED;
+	note_hpte_modification(kvm, rev);
 	unlock_hpte(hpte, 0);
 
 	vcpu->arch.gpr[4] = v;
@@ -466,6 +482,7 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
 
 			args[j] = ((0x80 | flags) << 56) + pte_index;
 			rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]);
+			note_hpte_modification(kvm, rev);
 
 			if (!(hp[0] & HPTE_V_VALID)) {
 				/* insert R and C bits from PTE */
@@ -555,6 +572,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 	if (rev) {
 		r = (rev->guest_rpte & ~mask) | bits;
 		rev->guest_rpte = r;
+		note_hpte_modification(kvm, rev);
 	}
 	r = (hpte[1] & ~mask) | bits;
 
@@ -606,8 +624,10 @@ long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
 			v &= ~HPTE_V_ABSENT;
 			v |= HPTE_V_VALID;
 		}
-		if (v & HPTE_V_VALID)
+		if (v & HPTE_V_VALID) {
 			r = rev[i].guest_rpte | (r & (HPTE_R_R | HPTE_R_C));
+			r &= ~HPTE_GR_RESERVED;
+		}
 		vcpu->arch.gpr[4 + i * 2] = v;
 		vcpu->arch.gpr[5 + i * 2] = r;
 	}
-- 
1.7.10.4

[PATCH v2 2/3] KVM: PPC: Book3S HV: Make a HPTE removal function available

[Paul Mackerras]

This makes a HPTE removal function, kvmppc_do_h_remove(), available
outside book3s_hv_rm_mmu.c.  This will be used by the HPT writing
code.

Signed-off-by: Paul Mackerras <paulus@samba.org>
---
v2: basically unchanged from v1, just rediffed

 arch/powerpc/include/asm/kvm_book3s.h |    3 +++
 arch/powerpc/kvm/book3s_hv_rm_mmu.c   |   19 +++++++++++++------
 2 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index fea768f..46763d10 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -160,6 +160,9 @@ extern long kvmppc_virtmode_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 extern long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 			long pte_index, unsigned long pteh, unsigned long ptel,
 			pgd_t *pgdir, bool realmode, unsigned long *idx_ret);
+extern long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
+			unsigned long pte_index, unsigned long avpn,
+			unsigned long *hpret);
 extern long kvmppc_hv_get_dirty_log(struct kvm *kvm,
 			struct kvm_memory_slot *memslot, unsigned long *map);
 
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index a96f90a..2334000 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -365,11 +365,10 @@ static inline int try_lock_tlbie(unsigned int *lock)
 	return old == 0;
 }
 
-long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags,
-		     unsigned long pte_index, unsigned long avpn,
-		     unsigned long va)
+long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
+			unsigned long pte_index, unsigned long avpn,
+			unsigned long *hpret)
 {
-	struct kvm *kvm = vcpu->kvm;
 	unsigned long *hpte;
 	unsigned long v, r, rb;
 	struct revmap_entry *rev;
@@ -411,10 +410,18 @@ long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags,
 	note_hpte_modification(kvm, rev);
 	unlock_hpte(hpte, 0);
 
-	vcpu->arch.gpr[4] = v;
-	vcpu->arch.gpr[5] = r;
+	hpret[0] = v;
+	hpret[1] = r;
 	return H_SUCCESS;
 }
+EXPORT_SYMBOL_GPL(kvmppc_do_h_remove);
+
+long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags,
+		     unsigned long pte_index, unsigned long avpn)
+{
+	return kvmppc_do_h_remove(vcpu->kvm, flags, pte_index, avpn,
+				  &vcpu->arch.gpr[4]);
+}
 
 long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
 {
-- 
1.7.10.4

[PATCH v2 3/3] KVM: PPC: Book3S HV: Provide a method for userspace to read and write the HPT

[Paul Mackerras]

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 <paulus@samba.org>
---
v2: added comments, added reserved field in struct kvm_get_htab_fd

 Documentation/virtual/kvm/api.txt        |   53 +++++
 arch/powerpc/include/asm/kvm_book3s_64.h |   22 ++
 arch/powerpc/include/asm/kvm_ppc.h       |    2 +
 arch/powerpc/include/uapi/asm/kvm.h      |   25 +++
 arch/powerpc/kvm/book3s_64_mmu_hv.c      |  344 ++++++++++++++++++++++++++++++
 arch/powerpc/kvm/book3s_hv.c             |   12 --
 arch/powerpc/kvm/powerpc.c               |   17 ++
 include/uapi/linux/kvm.h                 |    3 +
 8 files changed, 466 insertions(+), 12 deletions(-)

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 6671fdc..33080ea 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -2071,6 +2071,59 @@ 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;
+};
+
+/* 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
 ------------------------
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index b322e5b..38bec1d 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/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__ */
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 609cca3..1ca31e9 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/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.
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index b89ae4d..373de3e 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/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)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 6ee6516..42a1088 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -25,6 +25,8 @@
 #include <linux/hugetlb.h>
 #include <linux/vmalloc.h>
 #include <linux/srcu.h>
+#include <linux/anon_inodes.h>
+#include <linux/file.h>
 
 #include <asm/tlbflush.h>
 #include <asm/kvm_ppc.h>
@@ -1145,6 +1147,348 @@ void kvmppc_unpin_guest_page(struct kvm *kvm, void *va)
 	put_page(page);
 }
 
+/*
+ * Functions for reading and writing the hash table via reads and
+ * writes on a file descriptor.
+ *
+ * Reads return the guest view of the hash table, which has to be
+ * pieced together from the real hash table and the guest_rpte
+ * values in the revmap array.
+ *
+ * On writes, each HPTE written is considered in turn, and if it
+ * is valid, it is written to the HPT as if an H_ENTER with the
+ * exact flag set was done.  When the invalid count is non-zero
+ * in the header written to the stream, the kernel will make
+ * sure that that many HPTEs are invalid, and invalidate them
+ * if not.
+ */
+
+struct kvm_htab_ctx {
+	unsigned long	index;
+	unsigned long	flags;
+	struct kvm	*kvm;
+	int		first_pass;
+};
+
+#define HPTE_SIZE	(2 * sizeof(unsigned long))
+
+static long record_hpte(unsigned long flags, unsigned long *hptp,
+			unsigned long *hpte, struct revmap_entry *revp,
+			int want_valid, int first_pass)
+{
+	unsigned long v, r;
+	int ok = 1;
+	int valid, dirty;
+
+	/* Unmodified entries are uninteresting except on the first pass */
+	dirty = !!(revp->guest_rpte & HPTE_GR_MODIFIED);
+	if (!first_pass && !dirty)
+		return 0;
+
+	valid = 0;
+	if (hptp[0] & (HPTE_V_VALID | HPTE_V_ABSENT)) {
+		valid = 1;
+		if ((flags & KVM_GET_HTAB_BOLTED_ONLY) &&
+		    !(hptp[0] & HPTE_V_BOLTED))
+			valid = 0;
+	}
+	if (valid != want_valid)
+		return 0;
+
+	v = r = 0;
+	if (valid || dirty) {
+		/* lock the HPTE so it's stable and read it */
+		preempt_disable();
+		while (!try_lock_hpte(hptp, HPTE_V_HVLOCK))
+			cpu_relax();
+		v = hptp[0];
+		if (v & HPTE_V_ABSENT) {
+			v &= ~HPTE_V_ABSENT;
+			v |= HPTE_V_VALID;
+		}
+		/* re-evaluate valid and dirty from synchronized HPTE value */
+		valid = !!(v & HPTE_V_VALID);
+		if ((flags & KVM_GET_HTAB_BOLTED_ONLY) && !(v & HPTE_V_BOLTED))
+			valid = 0;
+		r = revp->guest_rpte | (hptp[1] & (HPTE_R_R | HPTE_R_C));
+		dirty = !!(revp->guest_rpte & HPTE_GR_MODIFIED);
+		/* only clear modified if this is the right sort of entry */
+		if (valid == want_valid && dirty) {
+			r &= ~HPTE_GR_MODIFIED;
+			revp->guest_rpte = r;
+		}
+		asm volatile(PPC_RELEASE_BARRIER "" : : : "memory");
+		hptp[0] &= ~HPTE_V_HVLOCK;
+		preempt_enable();
+		if (!(valid == want_valid && (first_pass || dirty)))
+			ok = 0;
+	}
+	hpte[0] = v;
+	hpte[1] = r;
+	return ok;
+}
+
+static ssize_t kvm_htab_read(struct file *file, char __user *buf,
+			     size_t count, loff_t *ppos)
+{
+	struct kvm_htab_ctx *ctx = file->private_data;
+	struct kvm *kvm = ctx->kvm;
+	struct kvm_get_htab_header hdr;
+	unsigned long *hptp;
+	struct revmap_entry *revp;
+	unsigned long i, nb, nw;
+	unsigned long __user *lbuf;
+	struct kvm_get_htab_header __user *hptr;
+	unsigned long flags;
+	int first_pass;
+	unsigned long hpte[2];
+
+	if (!access_ok(VERIFY_WRITE, buf, count))
+		return -EFAULT;
+
+	first_pass = ctx->first_pass;
+	flags = ctx->flags;
+
+	i = ctx->index;
+	hptp = (unsigned long *)(kvm->arch.hpt_virt + (i * HPTE_SIZE));
+	revp = kvm->arch.revmap + i;
+	lbuf = (unsigned long __user *)buf;
+
+	nb = 0;
+	while (nb + sizeof(hdr) + HPTE_SIZE < count) {
+		/* Initialize header */
+		hptr = (struct kvm_get_htab_header __user *)buf;
+		hdr.index = i;
+		hdr.n_valid = 0;
+		hdr.n_invalid = 0;
+		nw = nb;
+		nb += sizeof(hdr);
+		lbuf = (unsigned long __user *)(buf + sizeof(hdr));
+
+		/* Skip uninteresting entries, i.e. clean on not-first pass */
+		if (!first_pass) {
+			while (i < kvm->arch.hpt_npte &&
+			       !(revp->guest_rpte & HPTE_GR_MODIFIED)) {
+				++i;
+				hptp += 2;
+				++revp;
+			}
+		}
+
+		/* Grab a series of valid entries */
+		while (i < kvm->arch.hpt_npte &&
+		       hdr.n_valid < 0xffff &&
+		       nb + HPTE_SIZE < count &&
+		       record_hpte(flags, hptp, hpte, revp, 1, first_pass)) {
+			/* valid entry, write it out */
+			++hdr.n_valid;
+			if (__put_user(hpte[0], lbuf) ||
+			    __put_user(hpte[1], lbuf + 1))
+				return -EFAULT;
+			nb += HPTE_SIZE;
+			lbuf += 2;
+			++i;
+			hptp += 2;
+			++revp;
+		}
+		/* Now skip invalid entries while we can */
+		while (i < kvm->arch.hpt_npte &&
+		       hdr.n_invalid < 0xffff &&
+		       record_hpte(flags, hptp, hpte, revp, 0, first_pass)) {
+			/* found an invalid entry */
+			++hdr.n_invalid;
+			++i;
+			hptp += 2;
+			++revp;
+		}
+ 
+		if (hdr.n_valid || hdr.n_invalid) {
+			/* write back the header */
+			if (__copy_to_user(hptr, &hdr, sizeof(hdr)))
+				return -EFAULT;
+			nw = nb;
+			buf = (char __user *)lbuf;
+		} else {
+			nb = nw;
+		}
+
+		/* Check if we've wrapped around the hash table */
+		if (i >= kvm->arch.hpt_npte) {
+			i = 0;
+			ctx->first_pass = 0;
+			break;
+		}
+	}
+
+	ctx->index = i;
+
+	return nb;
+}
+
+static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
+			      size_t count, loff_t *ppos)
+{
+	struct kvm_htab_ctx *ctx = file->private_data;
+	struct kvm *kvm = ctx->kvm;
+	struct kvm_get_htab_header hdr;
+	unsigned long i, j;
+	unsigned long v, r;
+	unsigned long __user *lbuf;
+	unsigned long *hptp;
+	unsigned long tmp[2];
+	ssize_t nb;
+	long int err, ret;
+	int rma_setup;
+
+	if (!access_ok(VERIFY_READ, buf, count))
+		return -EFAULT;
+
+	/* lock out vcpus from running while we're doing this */
+	mutex_lock(&kvm->lock);
+	rma_setup = kvm->arch.rma_setup_done;
+	if (rma_setup) {
+		kvm->arch.rma_setup_done = 0;	/* temporarily */
+		/* order rma_setup_done vs. vcpus_running */
+		smp_mb();
+		if (atomic_read(&kvm->arch.vcpus_running)) {
+			kvm->arch.rma_setup_done = 1;
+			mutex_unlock(&kvm->lock);
+			return -EBUSY;
+		}
+	}
+
+	err = 0;
+	for (nb = 0; nb + sizeof(hdr) <= count; ) {
+		err = -EFAULT;
+		if (__copy_from_user(&hdr, buf, sizeof(hdr)))
+			break;
+
+		err = 0;
+		if (nb + hdr.n_valid * HPTE_SIZE > count)
+			break;
+
+		nb += sizeof(hdr);
+		buf += sizeof(hdr);
+
+		err = -EINVAL;
+		i = hdr.index;
+		if (i >= kvm->arch.hpt_npte ||
+		    i + hdr.n_valid + hdr.n_invalid > kvm->arch.hpt_npte)
+			break;
+
+		hptp = (unsigned long *)(kvm->arch.hpt_virt + (i * HPTE_SIZE));
+		lbuf = (unsigned long __user *)buf;
+		for (j = 0; j < hdr.n_valid; ++j) {
+			err = -EFAULT;
+			if (__get_user(v, lbuf) || __get_user(r, lbuf + 1))
+				goto out;
+			err = -EINVAL;
+			if (!(v & HPTE_V_VALID))
+				goto out;
+			lbuf += 2;
+			nb += HPTE_SIZE;
+
+			if (hptp[0] & (HPTE_V_VALID | HPTE_V_ABSENT))
+				kvmppc_do_h_remove(kvm, 0, i, 0, tmp);
+			err = -EIO;
+			ret = kvmppc_virtmode_do_h_enter(kvm, H_EXACT, i, v, r,
+							 tmp);
+			if (ret != H_SUCCESS) {
+				pr_err("kvm_htab_write ret %ld i=%ld v=%lx "
+				       "r=%lx\n", ret, i, v, r);
+				goto out;
+			}
+			if (!rma_setup && is_vrma_hpte(v)) {
+				unsigned long psize = hpte_page_size(v, r);
+				unsigned long senc = slb_pgsize_encoding(psize);
+				unsigned long lpcr;
+
+				kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
+					(VRMA_VSID << SLB_VSID_SHIFT_1T);
+				lpcr = kvm->arch.lpcr & ~LPCR_VRMASD;
+				lpcr |= senc << (LPCR_VRMASD_SH - 4);
+				kvm->arch.lpcr = lpcr;
+				rma_setup = 1;
+			}
+			++i;
+			hptp += 2;
+		}
+
+		for (j = 0; j < hdr.n_invalid; ++j) {
+			if (hptp[0] & (HPTE_V_VALID | HPTE_V_ABSENT))
+				kvmppc_do_h_remove(kvm, 0, i, 0, tmp);
+			++i;
+			hptp += 2;
+		}
+		err = 0;
+	}
+
+ out:
+	/* Order HPTE updates vs. rma_setup_done */
+	smp_wmb();
+	kvm->arch.rma_setup_done = rma_setup;
+	mutex_unlock(&kvm->lock);
+
+	if (err)
+		return err;
+	return nb;
+}
+
+static int kvm_htab_release(struct inode *inode, struct file *filp)
+{
+	struct kvm_htab_ctx *ctx = filp->private_data;
+
+	filp->private_data = NULL;
+	if (!(ctx->flags & KVM_GET_HTAB_WRITE))
+		atomic_dec(&ctx->kvm->arch.hpte_mod_interest);
+	kvm_put_kvm(ctx->kvm);
+	kfree(ctx);
+	return 0;
+}
+
+static struct file_operations kvm_htab_fops = {
+	.read		= kvm_htab_read,
+	.write		= kvm_htab_write,
+	.llseek		= default_llseek,
+	.release	= kvm_htab_release,
+};
+
+int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *ghf)
+{
+	int ret;
+	struct kvm_htab_ctx *ctx;
+	int rwflag;
+
+	/* reject flags we don't recognize */
+	if (ghf->flags & ~(KVM_GET_HTAB_BOLTED_ONLY | KVM_GET_HTAB_WRITE))
+		return -EINVAL;
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+	kvm_get_kvm(kvm);
+	ctx->kvm = kvm;
+	ctx->index = ghf->start_index;
+	ctx->flags = ghf->flags;
+	ctx->first_pass = 1;
+
+	rwflag = (ghf->flags & KVM_GET_HTAB_WRITE) ? O_WRONLY : O_RDONLY;
+	ret = anon_inode_getfd("kvm-htab", &kvm_htab_fops, ctx, rwflag);
+	if (ret < 0) {
+		kvm_put_kvm(kvm);
+		return ret;
+	}
+
+	if (rwflag == O_RDONLY) {
+		mutex_lock(&kvm->slots_lock);
+		atomic_inc(&kvm->arch.hpte_mod_interest);
+		/* make sure kvmppc_do_h_enter etc. see the increment */
+		synchronize_srcu_expedited(&kvm->srcu);
+		mutex_unlock(&kvm->slots_lock);
+	}
+
+	return ret;
+}
+
 void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_mmu *mmu = &vcpu->arch.mmu;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 843eb75..a4f59db 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1563,18 +1563,6 @@ out:
 	return r;
 }
 
-static 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 void unpin_slot(struct kvm_memory_slot *memslot)
 {
 	unsigned long *physp;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 900d8fc..d16be2a 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -354,6 +354,12 @@ int kvm_dev_ioctl_check_extension(long ext)
 		r = 1;
 #else
 		r = 0;
+		break;
+#endif
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+	case KVM_CAP_PPC_HTAB_FD:
+		r = 1;
+		break;
 #endif
 		break;
 	case KVM_CAP_NR_VCPUS:
@@ -949,6 +955,17 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = 0;
 		break;
 	}
+
+	case KVM_PPC_GET_HTAB_FD: {
+		struct kvm *kvm = filp->private_data;
+		struct kvm_get_htab_fd ghf;
+
+		r = -EFAULT;
+		if (copy_from_user(&ghf, argp, sizeof(ghf)))
+			break;
+		r = kvm_vm_ioctl_get_htab_fd(kvm, &ghf);
+		break;
+	}
 #endif /* CONFIG_KVM_BOOK3S_64_HV */
 
 #ifdef CONFIG_PPC_BOOK3S_64
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 494a84c..e6e5d4b 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -634,6 +634,7 @@ struct kvm_ppc_smmu_info {
 #endif
 #define KVM_CAP_IRQFD_RESAMPLE 82
 #define KVM_CAP_PPC_BOOKE_WATCHDOG 83
+#define KVM_CAP_PPC_HTAB_FD 84
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -859,6 +860,8 @@ struct kvm_s390_ucas_mapping {
 #define KVM_CREATE_SPAPR_TCE	  _IOW(KVMIO,  0xa8, struct kvm_create_spapr_tce)
 /* Available with KVM_CAP_RMA */
 #define KVM_ALLOCATE_RMA	  _IOR(KVMIO,  0xa9, struct kvm_allocate_rma)
+/* Available with KVM_CAP_PPC_HTAB_FD */
+#define KVM_PPC_GET_HTAB_FD	  _IOW(KVMIO,  0xaa, struct kvm_get_htab_fd)
 
 /*
  * ioctls for vcpu fds
-- 
1.7.10.4

Re: [PATCH v2 3/3] KVM: PPC: Book3S HV: Provide a method for userspace to read and write the HPT

[Alexander Graf]

On 20.11.2012, at 09:57, Paul Mackerras wrote:

> 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 <paulus@samba.org>
> ---
> v2: added comments, added reserved field in struct kvm_get_htab_fd
> 
> Documentation/virtual/kvm/api.txt        |   53 +++++
> arch/powerpc/include/asm/kvm_book3s_64.h |   22 ++
> arch/powerpc/include/asm/kvm_ppc.h       |    2 +
> arch/powerpc/include/uapi/asm/kvm.h      |   25 +++
> arch/powerpc/kvm/book3s_64_mmu_hv.c      |  344 ++++++++++++++++++++++++++++++
> arch/powerpc/kvm/book3s_hv.c             |   12 --
> arch/powerpc/kvm/powerpc.c               |   17 ++
> include/uapi/linux/kvm.h                 |    3 +
> 8 files changed, 466 insertions(+), 12 deletions(-)
> 
> diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
> index 6671fdc..33080ea 100644
> --- a/Documentation/virtual/kvm/api.txt
> +++ b/Documentation/virtual/kvm/api.txt
> @@ -2071,6 +2071,59 @@ 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;

Documentation is out of sync :).

Applied all 3 with fixed documentation.


Alex

Re: [PATCH v2 3/3] KVM: PPC: Book3S HV: Provide a method for userspace to read and write the HPT

[Paul Mackerras]

On Tue, Nov 20, 2012 at 10:16:24AM +0100, Alexander Graf wrote:

> Documentation is out of sync :).

Oops, sorry... :)

> Applied all 3 with fixed documentation.

Great, thanks.

Regards,
Paul.