Merge remote-tracking branch 'remotes/agraf/tags/signed-ppc-for-upstream' into staging

Patch queue for ppc - 2014-09-08

Alexander Graf (11):
      PPC: KVM: Fix g3beige and mac99 when HV is loaded
      PPC: mac99: Move NVRAM to page boundary when necessary
      KVM: Add helper to run KVM_CHECK_EXTENSION on vm fd
      PPC: KVM: Use vm check_extension for pv hcall
      PPC: mac99: Fix core99 timer frequency
      PPC: mac_nvram: Remove unused functions
      PPC: mac_nvram: Allow 2 and 4 byte accesses
      PPC: mac_nvram: Split NVRAM into OF and OSX parts
      PPC: Mac: Move tbfreq into local variable
      PPC: Cuda: Use cuda timer to expose tbfreq to guest
      PPC: Fix default config ordering and add eTSEC for ppc64

Alexey Kardashevskiy (7):
      spapr: Move DT memory node rendering to a helper
      spapr: Use DT memory node rendering helper for other nodes
      spapr: Refactor spapr_populate_memory() to allow memoryless nodes
      spapr: Split memory nodes to power-of-two blocks
      spapr: Add a helper for node0_size calculation
      spapr: Fix ibm, associativity for memory nodes
      spapr_pci: Fix config space corruption

Anton Blanchard (2):
      spapr-vlan: Don't touch last entry in buffer list
      hypervisor property clashes with hypervisor node

Benjamin Herrenschmidt (2):
      loader: Add load_image_size() to replace load_image()
      spapr: Locate RTAS and device-tree based on real RMA

Bharat Bhushan (4):
      ppc: debug stub: Get trap instruction opcode from KVM
      ppc: synchronize excp_vectors for injecting exception
      ppc: Add software breakpoint support
      ppc: Add hw breakpoint watchpoint support

Gonglei (1):
      spapr: fix possible memory leak

Greg Kurz (1):
      spapr_pci: map the MSI window in each PHB

Nikunj A Dadhania (3):
      ppc: spapr-rtas - implement os-term rtas call
      spapr: add uuid/host details to device tree
      ppc/spapr: Fix MAX_CPUS to 255

Peter Maydell (1):
      hw/ppc/spapr_hcall.c: Fix typo in function names

Tom Musta (20):
      linux-user: Fix Stack Pointer Bug in PPC setup_rt_frame
      linux-user: Split PPC Trampoline Encoding from Register Save
      linux-user: Enable Signal Handlers on PPC64
      linux-user: Properly Dereference PPC64 ELFv1 Signal Handler Pointer
      linux-user: Implement do_setcontext for PPC64
      linux-user: Handle PPC64 ELFv2 Function Pointers
      target-ppc: Bug Fix: rlwinm
      target-ppc: Bug Fix: rlwnm
      target-ppc: Bug Fix: rlwimi
      target-ppc: Bug Fix: mullwo
      target-ppc: Bug Fix: mullw
      target-ppc: Bug Fix: mulldo OV Detection
      target-ppc: Bug Fix: srawi
      target-ppc: Bug Fix: srad
      target-ppc: Special Case of rlwimi Should Use Deposit
      target-ppc: Optimize rlwinm MB=0 ME=31
      target-ppc: Optimize rlwnm MB=0 ME=31
      target-ppc: Clean Up mullw
      target-ppc: Clean up mullwo
      target-ppc: Implement mulldo with TCG

# gpg: Signature made Mon 08 Sep 2014 11:51:15 BST using RSA key ID 03FEDC60
# gpg: Can't check signature: public key not found

* remotes/agraf/tags/signed-ppc-for-upstream: (52 commits)
  hypervisor property clashes with hypervisor node
  PPC: Fix default config ordering and add eTSEC for ppc64
  spapr_pci: map the MSI window in each PHB
  target-ppc: Implement mulldo with TCG
  target-ppc: Clean up mullwo
  target-ppc: Clean Up mullw
  target-ppc: Optimize rlwnm MB=0 ME=31
  target-ppc: Optimize rlwinm MB=0 ME=31
  target-ppc: Special Case of rlwimi Should Use Deposit
  spapr-vlan: Don't touch last entry in buffer list
  spapr_pci: Fix config space corruption
  PPC: Cuda: Use cuda timer to expose tbfreq to guest
  PPC: Mac: Move tbfreq into local variable
  PPC: mac_nvram: Split NVRAM into OF and OSX parts
  PPC: mac_nvram: Allow 2 and 4 byte accesses
  PPC: mac_nvram: Remove unused functions
  PPC: mac99: Fix core99 timer frequency
  PPC: KVM: Use vm check_extension for pv hcall
  KVM: Add helper to run KVM_CHECK_EXTENSION on vm fd
  target-ppc: Bug Fix: srad
  ...

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

1 files changed, 123 insertions, 65 deletions

diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index 5cb452f234..2ab4460f04 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -71,6 +71,7 @@
  */
 #define FDT_MAX_SIZE            0x40000
 #define RTAS_MAX_SIZE           0x10000
+#define RTAS_MAX_ADDR           0x80000000 /* RTAS must stay below that */
 #define FW_MAX_SIZE             0x400000
 #define FW_FILE_NAME            "slof.bin"
 #define FW_OVERHEAD             0x2800000
@@ -80,7 +81,7 @@
 
 #define TIMEBASE_FREQ           512000000ULL
 
-#define MAX_CPUS                256
+#define MAX_CPUS                255
 
 #define PHANDLE_XICP            0x00001111
 
@@ -283,6 +284,19 @@ static size_t create_page_sizes_prop(CPUPPCState *env, uint32_t *prop,
     return (p - prop) * sizeof(uint32_t);
 }
 
+static hwaddr spapr_node0_size(void)
+{
+    if (nb_numa_nodes) {
+        int i;
+        for (i = 0; i < nb_numa_nodes; ++i) {
+            if (numa_info[i].node_mem) {
+                return MIN(pow2floor(numa_info[i].node_mem), ram_size);
+            }
+        }
+    }
+    return ram_size;
+}
+
 #define _FDT(exp) \
     do { \
         int ret = (exp);                                           \
@@ -319,6 +333,7 @@ static void *spapr_create_fdt_skel(hwaddr initrd_base,
     QemuOpts *opts = qemu_opts_find(qemu_find_opts("smp-opts"), NULL);
     unsigned sockets = opts ? qemu_opt_get_number(opts, "sockets", 0) : 0;
     uint32_t cpus_per_socket = sockets ? (smp_cpus / sockets) : 1;
+    char *buf;
 
     add_str(hypertas, "hcall-pft");
     add_str(hypertas, "hcall-term");
@@ -348,6 +363,29 @@ static void *spapr_create_fdt_skel(hwaddr initrd_base,
     _FDT((fdt_property_string(fdt, "model", "IBM pSeries (emulated by qemu)")));
     _FDT((fdt_property_string(fdt, "compatible", "qemu,pseries")));
 
+    /*
+     * Add info to guest to indentify which host is it being run on
+     * and what is the uuid of the guest
+     */
+    if (kvmppc_get_host_model(&buf)) {
+        _FDT((fdt_property_string(fdt, "host-model", buf)));
+        g_free(buf);
+    }
+    if (kvmppc_get_host_serial(&buf)) {
+        _FDT((fdt_property_string(fdt, "host-serial", buf)));
+        g_free(buf);
+    }
+
+    buf = g_strdup_printf(UUID_FMT, qemu_uuid[0], qemu_uuid[1],
+                          qemu_uuid[2], qemu_uuid[3], qemu_uuid[4],
+                          qemu_uuid[5], qemu_uuid[6], qemu_uuid[7],
+                          qemu_uuid[8], qemu_uuid[9], qemu_uuid[10],
+                          qemu_uuid[11], qemu_uuid[12], qemu_uuid[13],
+                          qemu_uuid[14], qemu_uuid[15]);
+
+    _FDT((fdt_property_string(fdt, "vm,uuid", buf)));
+    g_free(buf);
+
     _FDT((fdt_property_cell(fdt, "#address-cells", 0x2)));
     _FDT((fdt_property_cell(fdt, "#size-cells", 0x2)));
 
@@ -502,6 +540,15 @@ static void *spapr_create_fdt_skel(hwaddr initrd_base,
 
     _FDT((fdt_property_cell(fdt, "rtas-error-log-max", RTAS_ERROR_LOG_MAX)));
 
+    /*
+     * According to PAPR, rtas ibm,os-term, does not gaurantee a return
+     * back to the guest cpu.
+     *
+     * While an additional ibm,extended-os-term property indicates that
+     * rtas call return will always occur. Set this property.
+     */
+    _FDT((fdt_property(fdt, "ibm,extended-os-term", NULL, 0)));
+
     _FDT((fdt_end_node(fdt)));
 
     /* interrupt controller */
@@ -597,72 +644,75 @@ int spapr_h_cas_compose_response(target_ulong addr, target_ulong size)
     return 0;
 }
 
-static int spapr_populate_memory(sPAPREnvironment *spapr, void *fdt)
+static void spapr_populate_memory_node(void *fdt, int nodeid, hwaddr start,
+                                       hwaddr size)
 {
-    uint32_t associativity[] = {cpu_to_be32(0x4), cpu_to_be32(0x0),
-                                cpu_to_be32(0x0), cpu_to_be32(0x0),
-                                cpu_to_be32(0x0)};
+    uint32_t associativity[] = {
+        cpu_to_be32(0x4), /* length */
+        cpu_to_be32(0x0), cpu_to_be32(0x0),
+        cpu_to_be32(0x0), cpu_to_be32(nodeid)
+    };
     char mem_name[32];
-    hwaddr node0_size, mem_start, node_size;
     uint64_t mem_reg_property[2];
-    int i, off;
+    int off;
 
-    /* memory node(s) */
-    if (nb_numa_nodes > 1 && numa_info[0].node_mem < ram_size) {
-        node0_size = numa_info[0].node_mem;
-    } else {
-        node0_size = ram_size;
-    }
+    mem_reg_property[0] = cpu_to_be64(start);
+    mem_reg_property[1] = cpu_to_be64(size);
 
-    /* RMA */
-    mem_reg_property[0] = 0;
-    mem_reg_property[1] = cpu_to_be64(spapr->rma_size);
-    off = fdt_add_subnode(fdt, 0, "memory@0");
+    sprintf(mem_name, "memory@" TARGET_FMT_lx, start);
+    off = fdt_add_subnode(fdt, 0, mem_name);
     _FDT(off);
     _FDT((fdt_setprop_string(fdt, off, "device_type", "memory")));
     _FDT((fdt_setprop(fdt, off, "reg", mem_reg_property,
                       sizeof(mem_reg_property))));
     _FDT((fdt_setprop(fdt, off, "ibm,associativity", associativity,
                       sizeof(associativity))));
+}
+
+static int spapr_populate_memory(sPAPREnvironment *spapr, void *fdt)
+{
+    hwaddr mem_start, node_size;
+    int i, nb_nodes = nb_numa_nodes;
+    NodeInfo *nodes = numa_info;
+    NodeInfo ramnode;
+
+    /* No NUMA nodes, assume there is just one node with whole RAM */
+    if (!nb_numa_nodes) {
+        nb_nodes = 1;
+        ramnode.node_mem = ram_size;
+        nodes = &ramnode;
+    }
 
-    /* RAM: Node 0 */
-    if (node0_size > spapr->rma_size) {
-        mem_reg_property[0] = cpu_to_be64(spapr->rma_size);
-        mem_reg_property[1] = cpu_to_be64(node0_size - spapr->rma_size);
-
-        sprintf(mem_name, "memory@" TARGET_FMT_lx, spapr->rma_size);
-        off = fdt_add_subnode(fdt, 0, mem_name);
-        _FDT(off);
-        _FDT((fdt_setprop_string(fdt, off, "device_type", "memory")));
-        _FDT((fdt_setprop(fdt, off, "reg", mem_reg_property,
-                          sizeof(mem_reg_property))));
-        _FDT((fdt_setprop(fdt, off, "ibm,associativity", associativity,
-                          sizeof(associativity))));
-    }
-
-    /* RAM: Node 1 and beyond */
-    mem_start = node0_size;
-    for (i = 1; i < nb_numa_nodes; i++) {
-        mem_reg_property[0] = cpu_to_be64(mem_start);
+    for (i = 0, mem_start = 0; i < nb_nodes; ++i) {
+        if (!nodes[i].node_mem) {
+            continue;
+        }
         if (mem_start >= ram_size) {
             node_size = 0;
         } else {
-            node_size = numa_info[i].node_mem;
+            node_size = nodes[i].node_mem;
             if (node_size > ram_size - mem_start) {
                 node_size = ram_size - mem_start;
             }
         }
-        mem_reg_property[1] = cpu_to_be64(node_size);
-        associativity[3] = associativity[4] = cpu_to_be32(i);
-        sprintf(mem_name, "memory@" TARGET_FMT_lx, mem_start);
-        off = fdt_add_subnode(fdt, 0, mem_name);
-        _FDT(off);
-        _FDT((fdt_setprop_string(fdt, off, "device_type", "memory")));
-        _FDT((fdt_setprop(fdt, off, "reg", mem_reg_property,
-                          sizeof(mem_reg_property))));
-        _FDT((fdt_setprop(fdt, off, "ibm,associativity", associativity,
-                          sizeof(associativity))));
-        mem_start += node_size;
+        if (!mem_start) {
+            /* ppc_spapr_init() checks for rma_size <= node0_size already */
+            spapr_populate_memory_node(fdt, i, 0, spapr->rma_size);
+            mem_start += spapr->rma_size;
+            node_size -= spapr->rma_size;
+        }
+        for ( ; node_size; ) {
+            hwaddr sizetmp = pow2floor(node_size);
+
+            /* mem_start != 0 here */
+            if (ctzl(mem_start) < ctzl(sizetmp)) {
+                sizetmp = 1ULL << ctzl(mem_start);
+            }
+
+            spapr_populate_memory_node(fdt, i, mem_start, sizetmp);
+            node_size -= sizetmp;
+            mem_start += sizetmp;
+        }
     }
 
     return 0;
@@ -746,6 +796,7 @@ static void spapr_finalize_fdt(sPAPREnvironment *spapr,
 
     cpu_physical_memory_write(fdt_addr, fdt, fdt_totalsize(fdt));
 
+    g_free(bootlist);
     g_free(fdt);
 }
 
@@ -792,25 +843,38 @@ static void spapr_reset_htab(sPAPREnvironment *spapr)
 
     /* Update the RMA size if necessary */
     if (spapr->vrma_adjust) {
-        hwaddr node0_size = (nb_numa_nodes > 1) ?
-            numa_info[0].node_mem : ram_size;
-        spapr->rma_size = kvmppc_rma_size(node0_size, spapr->htab_shift);
+        spapr->rma_size = kvmppc_rma_size(spapr_node0_size(),
+                                          spapr->htab_shift);
     }
 }
 
 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, RTAS_MAX_ADDR);
+    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;
@@ -1227,10 +1291,10 @@ static void ppc_spapr_init(MachineState *machine)
     MemoryRegion *rma_region;
     void *rma = NULL;
     hwaddr rma_alloc_size;
-    hwaddr node0_size = (nb_numa_nodes > 1) ? numa_info[0].node_mem : ram_size;
+    hwaddr node0_size = spapr_node0_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;
 
@@ -1275,13 +1339,8 @@ 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, RTAS_MAX_ADDR) - 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
@@ -1349,14 +1408,14 @@ 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);
     }
     if (spapr->rtas_size > RTAS_MAX_SIZE) {
-        hw_error("RTAS too big ! 0x%lx bytes (max is 0x%x)\n",
+        hw_error("RTAS too big ! 0x%zx bytes (max is 0x%x)\n",
                  spapr->rtas_size, RTAS_MAX_SIZE);
         exit(1);
     }
@@ -1378,7 +1437,6 @@ static void ppc_spapr_init(MachineState *machine)
     spapr_create_nvram(spapr);
 
     /* Set up PCI */
-    spapr_pci_msi_init(spapr, SPAPR_PCI_MSI_WINDOW);
     spapr_pci_rtas_init();
 
     phb = spapr_create_phb(spapr, 0);