target-ppc: Support dump for little endian ppc64

Fix ppc64 arch specific dump code to support all combinations of little/big
endian hosts/guests. FWIW the current code is broken for altivec registers
when guest and host have a different endianness: these 128-bit registers
are written to guest memory as a two 64-bit entities and we should also swap
them.

Unit testing was done with the following program provided by Tom Musta:

#include <stdio.h>
#include <stdint.h>
#include <stdlib.h>

int main(int argc, char** argv)
{

__uint128_t v = ((__uint128_t)0x0001020304050607ull << 64) |
0x08090a0b0c0d0e0full;

register void * vptr asm ("r11");
vptr = &v;

for(;;)
asm volatile ("lvx 30,0,11" );
}

When sending SIGABRT to this program and examining the core file, we get:

- ppc64  : 00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f
- ppc64le: 0f 0e 0d 0c 0b 0a 09 08 07 06 05 04 03 02 01 00

We expect to find the very same layout in the QEMU dump since they are
real core files. This is what we get:

- ppc64 host, ppc64 guest   : 00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f
- ppc64 host, ppc64le guest : 0f 0e 0d 0c 0b 0a 09 08 07 06 05 04 03 02 01 00
- x86_64 host, ppc64 guest  : 00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f
- x86_64 host, ppc64le guest: 0f 0e 0d 0c 0b 0a 09 08 07 06 05 04 03 02 01 00

We introduce a NoteFuncArg type to avoid adding extra arguments to all note
functions.

Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com>
[ rebased on top of current master branch,
  introduced NoteFuncArg,
  use new cpu_to_dump{16,32,64} endian helpers,
  fix altivec support,
  Greg Kurz <gkurz@linux.vnet.ibm.com> ]
Reviewed-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>

1 files changed, 62 insertions, 33 deletions

diff --git a/target-ppc/arch_dump.c b/target-ppc/arch_dump.c
index 9dccf1ae1f..5a3b40df10 100644
--- a/target-ppc/arch_dump.c
+++ b/target-ppc/arch_dump.c
@@ -79,94 +79,122 @@ typedef struct noteStruct {
     } contents;
 } QEMU_PACKED Note;
 
+typedef struct NoteFuncArg {
+    Note note;
+    DumpState *state;
+} NoteFuncArg;
 
-static void ppc64_write_elf64_prstatus(Note *note, PowerPCCPU *cpu)
+static void ppc64_write_elf64_prstatus(NoteFuncArg *arg, PowerPCCPU *cpu)
 {
     int i;
     uint64_t cr;
     struct PPC64ElfPrstatus *prstatus;
     struct PPC64UserRegStruct *reg;
+    Note *note = &arg->note;
+    DumpState *s = arg->state;
 
-    note->hdr.n_type = cpu_to_be32(NT_PRSTATUS);
+    note->hdr.n_type = cpu_to_dump32(s, NT_PRSTATUS);
 
     prstatus = &note->contents.prstatus;
     memset(prstatus, 0, sizeof(*prstatus));
     reg = &prstatus->pr_reg;
 
     for (i = 0; i < 32; i++) {
-        reg->gpr[i] = cpu_to_be64(cpu->env.gpr[i]);
+        reg->gpr[i] = cpu_to_dump64(s, cpu->env.gpr[i]);
     }
-    reg->nip = cpu_to_be64(cpu->env.nip);
-    reg->msr = cpu_to_be64(cpu->env.msr);
-    reg->ctr = cpu_to_be64(cpu->env.ctr);
-    reg->link = cpu_to_be64(cpu->env.lr);
-    reg->xer = cpu_to_be64(cpu_read_xer(&cpu->env));
+    reg->nip = cpu_to_dump64(s, cpu->env.nip);
+    reg->msr = cpu_to_dump64(s, cpu->env.msr);
+    reg->ctr = cpu_to_dump64(s, cpu->env.ctr);
+    reg->link = cpu_to_dump64(s, cpu->env.lr);
+    reg->xer = cpu_to_dump64(s, cpu_read_xer(&cpu->env));
 
     cr = 0;
     for (i = 0; i < 8; i++) {
         cr |= (cpu->env.crf[i] & 15) << (4 * (7 - i));
     }
-    reg->ccr = cpu_to_be64(cr);
+    reg->ccr = cpu_to_dump64(s, cr);
 }
 
-static void ppc64_write_elf64_fpregset(Note *note, PowerPCCPU *cpu)
+static void ppc64_write_elf64_fpregset(NoteFuncArg *arg, PowerPCCPU *cpu)
 {
     int i;
     struct PPC64ElfFpregset  *fpregset;
+    Note *note = &arg->note;
+    DumpState *s = arg->state;
 
-    note->hdr.n_type = cpu_to_be32(NT_PRFPREG);
+    note->hdr.n_type = cpu_to_dump32(s, NT_PRFPREG);
 
     fpregset = &note->contents.fpregset;
     memset(fpregset, 0, sizeof(*fpregset));
 
     for (i = 0; i < 32; i++) {
-        fpregset->fpr[i] = cpu_to_be64(cpu->env.fpr[i]);
+        fpregset->fpr[i] = cpu_to_dump64(s, cpu->env.fpr[i]);
     }
-    fpregset->fpscr = cpu_to_be64(cpu->env.fpscr);
+    fpregset->fpscr = cpu_to_dump64(s, cpu->env.fpscr);
 }
 
-static void ppc64_write_elf64_vmxregset(Note *note, PowerPCCPU *cpu)
+static void ppc64_write_elf64_vmxregset(NoteFuncArg *arg, PowerPCCPU *cpu)
 {
     int i;
     struct PPC64ElfVmxregset *vmxregset;
+    Note *note = &arg->note;
+    DumpState *s = arg->state;
 
-    note->hdr.n_type = cpu_to_be32(NT_PPC_VMX);
+    note->hdr.n_type = cpu_to_dump32(s, NT_PPC_VMX);
     vmxregset = &note->contents.vmxregset;
     memset(vmxregset, 0, sizeof(*vmxregset));
 
     for (i = 0; i < 32; i++) {
-        vmxregset->avr[i].u64[0] = cpu_to_be64(cpu->env.avr[i].u64[0]);
-        vmxregset->avr[i].u64[1] = cpu_to_be64(cpu->env.avr[i].u64[1]);
+        bool needs_byteswap;
+
+#ifdef HOST_WORDS_BIGENDIAN
+        needs_byteswap = s->dump_info.d_endian == ELFDATA2LSB;
+#else
+        needs_byteswap = s->dump_info.d_endian == ELFDATA2MSB;
+#endif
+
+        if (needs_byteswap) {
+            vmxregset->avr[i].u64[0] = bswap64(cpu->env.avr[i].u64[1]);
+            vmxregset->avr[i].u64[1] = bswap64(cpu->env.avr[i].u64[0]);
+        } else {
+            vmxregset->avr[i].u64[0] = cpu->env.avr[i].u64[0];
+            vmxregset->avr[i].u64[1] = cpu->env.avr[i].u64[1];
+        }
     }
-    vmxregset->vscr.u32[3] = cpu_to_be32(cpu->env.vscr);
+    vmxregset->vscr.u32[3] = cpu_to_dump32(s, cpu->env.vscr);
 }
-static void ppc64_write_elf64_vsxregset(Note *note, PowerPCCPU *cpu)
+static void ppc64_write_elf64_vsxregset(NoteFuncArg *arg, PowerPCCPU *cpu)
 {
     int i;
     struct PPC64ElfVsxregset *vsxregset;
+    Note *note = &arg->note;
+    DumpState *s = arg->state;
 
-    note->hdr.n_type = cpu_to_be32(NT_PPC_VSX);
+    note->hdr.n_type = cpu_to_dump32(s, NT_PPC_VSX);
     vsxregset = &note->contents.vsxregset;
     memset(vsxregset, 0, sizeof(*vsxregset));
 
     for (i = 0; i < 32; i++) {
-        vsxregset->vsr[i] = cpu_to_be64(cpu->env.vsr[i]);
+        vsxregset->vsr[i] = cpu_to_dump64(s, cpu->env.vsr[i]);
     }
 }
-static void ppc64_write_elf64_speregset(Note *note, PowerPCCPU *cpu)
+static void ppc64_write_elf64_speregset(NoteFuncArg *arg, PowerPCCPU *cpu)
 {
     struct PPC64ElfSperegset *speregset;
-    note->hdr.n_type = cpu_to_be32(NT_PPC_SPE);
+    Note *note = &arg->note;
+    DumpState *s = arg->state;
+
+    note->hdr.n_type = cpu_to_dump32(s, NT_PPC_SPE);
     speregset = &note->contents.speregset;
     memset(speregset, 0, sizeof(*speregset));
 
-    speregset->spe_acc = cpu_to_be64(cpu->env.spe_acc);
-    speregset->spe_fscr = cpu_to_be32(cpu->env.spe_fscr);
+    speregset->spe_acc = cpu_to_dump64(s, cpu->env.spe_acc);
+    speregset->spe_fscr = cpu_to_dump32(s, cpu->env.spe_fscr);
 }
 
 static const struct NoteFuncDescStruct {
     int contents_size;
-    void (*note_contents_func)(Note *note, PowerPCCPU *cpu);
+    void (*note_contents_func)(NoteFuncArg *arg, PowerPCCPU *cpu);
 } note_func[] = {
     {sizeof(((Note *)0)->contents.prstatus),  ppc64_write_elf64_prstatus},
     {sizeof(((Note *)0)->contents.fpregset),  ppc64_write_elf64_fpregset},
@@ -218,20 +246,21 @@ static int ppc64_write_all_elf64_notes(const char *note_name,
                                        PowerPCCPU *cpu, int id,
                                        void *opaque)
 {
-    Note note;
+    NoteFuncArg arg = { .state = opaque };
     int ret = -1;
     int note_size;
     const NoteFuncDesc *nf;
 
     for (nf = note_func; nf->note_contents_func; nf++) {
-        note.hdr.n_namesz = cpu_to_be32(sizeof(note.name));
-        note.hdr.n_descsz = cpu_to_be32(nf->contents_size);
-        strncpy(note.name, note_name, sizeof(note.name));
+        arg.note.hdr.n_namesz = cpu_to_dump32(opaque, sizeof(arg.note.name));
+        arg.note.hdr.n_descsz = cpu_to_dump32(opaque, nf->contents_size);
+        strncpy(arg.note.name, note_name, sizeof(arg.note.name));
 
-        (*nf->note_contents_func)(&note, cpu);
+        (*nf->note_contents_func)(&arg, cpu);
 
-        note_size = sizeof(note) - sizeof(note.contents) + nf->contents_size;
-        ret = f(&note, note_size, opaque);
+        note_size =
+            sizeof(arg.note) - sizeof(arg.note.contents) + nf->contents_size;
+        ret = f(&arg.note, note_size, opaque);
         if (ret < 0) {
             return -1;
         }