[Qemu-devel] [PATCH 2/2] pseries: Correctly create ibm, segment-page-sizes property

[Qemu-devel] [PATCH 2/2] pseries: Correctly create ibm, segment-page-sizes property

[Benjamin Herrenschmidt]

The core tcg/kvm code for ppc64 now has at least the outline
capability to support pagesizes beyond the standard 4k and 16MB.  The
CPUState is initialized with information advertising the available
pagesizes and their correct encodings, and under the right KVM setup
this will be populated with page sizes beyond the standard.

Obviously guests can't use the extra page sizes unless they know
they're present.  For the pseries machine, at least, there is a
defined method for conveying exactly this information, the
"ibm-segment-page-sizes" property in the guest device tree.

This patch generates this property using the supported page size
information that's already in the CPUState.

Signed-off-by: Nishanth Aravamudan <nacc@us.ibm.com>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 hw/spapr.c |   43 +++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 43 insertions(+), 0 deletions(-)

diff --git a/hw/spapr.c b/hw/spapr.c
index b20f70d..a22a6b6 100644
--- a/hw/spapr.c
+++ b/hw/spapr.c
@@ -149,6 +149,40 @@ static int spapr_set_associativity(void *fdt, sPAPREnvironment *spapr)
     return ret;
 }
 
+
+static size_t create_page_sizes_prop(CPUPPCState *env, uint32_t *prop,
+                                     size_t maxsize)
+{
+    size_t maxcells = maxsize / sizeof(uint32_t);
+    int i, j, count;
+    uint32_t *p = prop;
+
+    for (i = 0; i < PPC_PAGE_SIZES_MAX_SZ; i++) {
+        struct ppc_one_seg_page_size *sps = &env->sps.sps[i];
+
+        if (!sps->page_shift) {
+            break;
+        }
+        for (count = 0; count < PPC_PAGE_SIZES_MAX_SZ; count++) {
+            if (sps->enc[count].page_shift == 0) {
+                break;
+            }
+        }
+        if ((p - prop) >= (maxcells - 3 - count * 2)) {
+            break;
+        }
+        *(p++) = cpu_to_be32(sps->page_shift);
+        *(p++) = cpu_to_be32(sps->slb_enc);
+        *(p++) = cpu_to_be32(count);
+        for (j = 0; j < count; j++) {
+            *(p++) = cpu_to_be32(sps->enc[j].page_shift);
+            *(p++) = cpu_to_be32(sps->enc[j].pte_enc);
+        }
+    }
+
+    return (p - prop) * sizeof(uint32_t);
+}
+
 static void *spapr_create_fdt_skel(const char *cpu_model,
                                    target_phys_addr_t rma_size,
                                    target_phys_addr_t initrd_base,
@@ -304,6 +338,8 @@ static void *spapr_create_fdt_skel(const char *cpu_model,
                            0xffffffff, 0xffffffff};
         uint32_t tbfreq = kvm_enabled() ? kvmppc_get_tbfreq() : TIMEBASE_FREQ;
         uint32_t cpufreq = kvm_enabled() ? kvmppc_get_clockfreq() : 1000000000;
+        uint32_t page_sizes_prop[64];
+        size_t page_sizes_prop_size;
 
         if ((index % smt) != 0) {
             continue;
@@ -368,6 +404,13 @@ static void *spapr_create_fdt_skel(const char *cpu_model,
             _FDT((fdt_property_cell(fdt, "ibm,dfp", 1)));
         }
 
+        page_sizes_prop_size = create_page_sizes_prop(env, page_sizes_prop,
+                                                      sizeof(page_sizes_prop));
+        if (page_sizes_prop_size) {
+            _FDT((fdt_property(fdt, "ibm,segment-page-sizes",
+                               page_sizes_prop, page_sizes_prop_size)));
+        }
+
         _FDT((fdt_end_node(fdt)));
     }