Merge remote-tracking branch 'remotes/dgibson/tags/ppc-for-2.9-20170303' into staging

ppc patch queuye for 2017-03-03

This will probably be my last pull request before the hard freeze.  It
has some new work, but that has all been posted in draft before the
soft freeze, so I think it's reasonable to include in qemu-2.9.

This batch has:
    * A substantial amount of POWER9 work
        * Implements the legacy (hash) MMU for POWER9
	* Some more preliminaries for implementing the POWER9 radix
          MMU
	* POWER9 has_work
	* Basic POWER9 compatibility mode handling
	* Removal of some premature tests
    * Some cleanups and fixes to the existing MMU code to make the
      POWER9 work simpler
    * A bugfix for TCG multiply adds on power
    * Allow pseries guests to access PCIe extended config space

This also includes a code-motion not strictly in ppc code - moving
getrampagesize() from ppc code to exec.c.  This will make some future
VFIO improvements easier, Paolo said it was ok to merge via my tree.

# gpg: Signature made Fri 03 Mar 2017 03:20:36 GMT
# gpg:                using RSA key 0x6C38CACA20D9B392
# gpg: Good signature from "David Gibson <david@gibson.dropbear.id.au>"
# gpg:                 aka "David Gibson (Red Hat) <dgibson@redhat.com>"
# gpg:                 aka "David Gibson (ozlabs.org) <dgibson@ozlabs.org>"
# gpg:                 aka "David Gibson (kernel.org) <dwg@kernel.org>"
# Primary key fingerprint: 75F4 6586 AE61 A66C C44E  87DC 6C38 CACA 20D9 B392

* remotes/dgibson/tags/ppc-for-2.9-20170303:
  target/ppc: rewrite f[n]m[add,sub] using float64_muladd
  spapr: Small cleanup of PPC MMU enums
  spapr_pci: Advertise access to PCIe extended config space
  target/ppc: Rework hash mmu page fault code and add defines for clarity
  target/ppc: Move no-execute and guarded page checking into new function
  target/ppc: Add execute permission checking to access authority check
  target/ppc: Add Instruction Authority Mask Register Check
  hw/ppc/spapr: Add POWER9 to pseries cpu models
  target/ppc/POWER9: Add cpu_has_work function for POWER9
  target/ppc/POWER9: Add POWER9 pa-features definition
  target/ppc/POWER9: Add POWER9 mmu fault handler
  target/ppc: Don't gen an SDR1 on POWER9 and rework register creation
  target/ppc: Add patb_entry to sPAPRMachineState
  target/ppc/POWER9: Add POWERPC_MMU_V3 bit
  powernv: Don't test POWER9 CPU yet
  exec, kvm, target-ppc: Move getrampagesize() to common code
  target/ppc: Add POWER9/ISAv3.00 to compat_table

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 82 insertions, 0 deletions

diff --git a/exec.c b/exec.c
index 785d20f648..aabb035e92 100644
--- a/exec.c
+++ b/exec.c
@@ -42,6 +42,7 @@
 #include "exec/memory.h"
 #include "exec/ioport.h"
 #include "sysemu/dma.h"
+#include "sysemu/numa.h"
 #include "exec/address-spaces.h"
 #include "sysemu/xen-mapcache.h"
 #include "trace-root.h"
@@ -1257,6 +1258,87 @@ void qemu_mutex_unlock_ramlist(void)
 }
 
 #ifdef __linux__
+/*
+ * FIXME TOCTTOU: this iterates over memory backends' mem-path, which
+ * may or may not name the same files / on the same filesystem now as
+ * when we actually open and map them.  Iterate over the file
+ * descriptors instead, and use qemu_fd_getpagesize().
+ */
+static int find_max_supported_pagesize(Object *obj, void *opaque)
+{
+    char *mem_path;
+    long *hpsize_min = opaque;
+
+    if (object_dynamic_cast(obj, TYPE_MEMORY_BACKEND)) {
+        mem_path = object_property_get_str(obj, "mem-path", NULL);
+        if (mem_path) {
+            long hpsize = qemu_mempath_getpagesize(mem_path);
+            if (hpsize < *hpsize_min) {
+                *hpsize_min = hpsize;
+            }
+        } else {
+            *hpsize_min = getpagesize();
+        }
+    }
+
+    return 0;
+}
+
+long qemu_getrampagesize(void)
+{
+    long hpsize = LONG_MAX;
+    long mainrampagesize;
+    Object *memdev_root;
+
+    if (mem_path) {
+        mainrampagesize = qemu_mempath_getpagesize(mem_path);
+    } else {
+        mainrampagesize = getpagesize();
+    }
+
+    /* it's possible we have memory-backend objects with
+     * hugepage-backed RAM. these may get mapped into system
+     * address space via -numa parameters or memory hotplug
+     * hooks. we want to take these into account, but we
+     * also want to make sure these supported hugepage
+     * sizes are applicable across the entire range of memory
+     * we may boot from, so we take the min across all
+     * backends, and assume normal pages in cases where a
+     * backend isn't backed by hugepages.
+     */
+    memdev_root = object_resolve_path("/objects", NULL);
+    if (memdev_root) {
+        object_child_foreach(memdev_root, find_max_supported_pagesize, &hpsize);
+    }
+    if (hpsize == LONG_MAX) {
+        /* No additional memory regions found ==> Report main RAM page size */
+        return mainrampagesize;
+    }
+
+    /* If NUMA is disabled or the NUMA nodes are not backed with a
+     * memory-backend, then there is at least one node using "normal" RAM,
+     * so if its page size is smaller we have got to report that size instead.
+     */
+    if (hpsize > mainrampagesize &&
+        (nb_numa_nodes == 0 || numa_info[0].node_memdev == NULL)) {
+        static bool warned;
+        if (!warned) {
+            error_report("Huge page support disabled (n/a for main memory).");
+            warned = true;
+        }
+        return mainrampagesize;
+    }
+
+    return hpsize;
+}
+#else
+long qemu_getrampagesize(void)
+{
+    return getpagesize();
+}
+#endif
+
+#ifdef __linux__
 static int64_t get_file_size(int fd)
 {
     int64_t size = lseek(fd, 0, SEEK_END);