[Qemu-ppc] [PATCH 2/2] ppc/spapr: Locate RTAS and device-tree based on real RMA

[Benjamin Herrenschmidt]

We currently calculate the final RTAS and FDT location based on
the early estimate of the RMA size, cropped to 256M on KVM since
we only know the real RMA size at reset time which happens much
later in the boot process.

This means the FDT and RTAS end up right below 256M while they
could be much higher, using precious RMA space and limiting
what the OS bootloader can put there which has proved to be
a problem with some OSes (such as when using very large initrd's)

Fortunately, we do the actual copy of the device-tree into guest
memory much later, during reset, late enough to be able to do it
using the final RMA value, we just need to move the calculation
to the right place.

However, RTAS is still loaded too early, so we change the code to
load the tiny blob into qemu memory early on, and then copy it into
guest memory at reset time. It's small enough that the memory usage
doesn't matter.

Signed-off-by: Benjamin Herrenschmidt <address@hidden>
---
 hw/ppc/spapr.c         | 30 +++++++++++++++++++-----------
 include/hw/ppc/spapr.h |  3 ++-
 2 files changed, 21 insertions(+), 12 deletions(-)

diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index 82f183f..949d5ba 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -866,16 +866,29 @@ static void spapr_reset_htab(sPAPREnvironment *spapr)
 static void ppc_spapr_reset(void)
 {
     PowerPCCPU *first_ppc_cpu;
+    uint32_t rtas_limit;
 
     /* Reset the hash table & recalc the RMA */
     spapr_reset_htab(spapr);
 
     qemu_devices_reset();
 
+    /* We place the device tree and RTAS just below either the top of the RMA,
+     * or just below 2GB, whichever is lowere, so that it can be
+     * processed with 32-bit real mode code if necessary
+     */
+    rtas_limit = MIN(spapr->rma_size, 0x80000000);
+    spapr->rtas_addr = rtas_limit - RTAS_MAX_SIZE;
+    spapr->fdt_addr = spapr->rtas_addr - FDT_MAX_SIZE;
+
     /* Load the fdt */
     spapr_finalize_fdt(spapr, spapr->fdt_addr, spapr->rtas_addr,
                        spapr->rtas_size);
 
+    /* Copy RTAS over */
+    cpu_physical_memory_write(spapr->rtas_addr, spapr->rtas_blob,
+                             spapr->rtas_size);
+
     /* Set up the entry state */
     first_ppc_cpu = POWERPC_CPU(first_cpu);
     first_ppc_cpu->env.gpr[3] = spapr->fdt_addr;
@@ -1293,7 +1306,7 @@ static void ppc_spapr_init(MachineState *machine)
     hwaddr node0_size = (nb_numa_nodes > 1) ? numa_info[0].node_mem : ram_size;
     uint32_t initrd_base = 0;
     long kernel_size = 0, initrd_size = 0;
-    long load_limit, rtas_limit, fw_size;
+    long load_limit, fw_size;
     bool kernel_le = false;
     char *filename;
 
@@ -1338,13 +1351,8 @@ static void ppc_spapr_init(MachineState *machine)
         exit(1);
     }
 
-    /* We place the device tree and RTAS just below either the top of the RMA,
-     * or just below 2GB, whichever is lowere, so that it can be
-     * processed with 32-bit real mode code if necessary */
-    rtas_limit = MIN(spapr->rma_size, 0x80000000);
-    spapr->rtas_addr = rtas_limit - RTAS_MAX_SIZE;
-    spapr->fdt_addr = spapr->rtas_addr - FDT_MAX_SIZE;
-    load_limit = spapr->fdt_addr - FW_OVERHEAD;
+    /* Setup a load limit for the ramdisk leaving room for SLOF and FDT */
+    load_limit = MIN(spapr->rma_size, 0x80000000) - FW_OVERHEAD;
 
     /* We aim for a hash table of size 1/128 the size of RAM.  The
      * normal rule of thumb is 1/64 the size of RAM, but that's much
@@ -1410,9 +1418,9 @@ static void ppc_spapr_init(MachineState *machine)
     }
 
     filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, "spapr-rtas.bin");
-    spapr->rtas_size = load_image_targphys(filename, spapr->rtas_addr,
-                                           rtas_limit - spapr->rtas_addr);
-    if (spapr->rtas_size < 0) {
+    spapr->rtas_size = get_image_size(filename);
+    spapr->rtas_blob = g_malloc(spapr->rtas_size);
+    if (load_image_size(filename, spapr->rtas_blob, spapr->rtas_size) < 0) {
         hw_error("qemu: could not load LPAR rtas '%s'\n", filename);
         exit(1);
     }
diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
index e3e7aff..5b399b8 100644
--- a/include/hw/ppc/spapr.h
+++ b/include/hw/ppc/spapr.h
@@ -24,7 +24,8 @@ typedef struct sPAPREnvironment {
     hwaddr rma_size;
     int vrma_adjust;
     hwaddr fdt_addr, rtas_addr;
-    long rtas_size;
+    ssize_t rtas_size;
+    void *rtas_blob;
     void *fdt_skel;
     target_ulong entry_point;
     uint32_t next_irq;