On 07/09/2014 05:46 PM, Paolo Bonzini wrote:> Il 09/07/2014 07:57, Alexey
Kardashevskiy ha scritto:
>> 0b183fc87 "memory: move mem_path handling to
>> memory_region_allocate_system_memory" disabled -mempath use for all
>> machines that do not use memory_region_allocate_system_memory() to
>> register RAM. Since SPAPR uses memory_region_init_ram(), the huge pages
>> support was disabled for it.
>>
>> This replaces memory_region_init_ram()+vmstate_register_ram_global() with
>> memory_region_allocate_system_memory() to get huge pages back.
>>
>> Cc: Paolo Bonzini <pbonz...@redhat.com>
>> Cc: Hu Tao <hu...@cn.fujitsu.com>
>> Signed-off-by: Alexey Kardashevskiy <a...@ozlabs.ru>
>> ---
>> hw/ppc/spapr.c | 4 ++--
>> 1 file changed, 2 insertions(+), 2 deletions(-)
>>
>> diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
>> index a23c0f0..8fa9f7e 100644
>> --- a/hw/ppc/spapr.c
>> +++ b/hw/ppc/spapr.c
>> @@ -1337,8 +1337,8 @@ static void ppc_spapr_init(MachineState *machine)
>> ram_addr_t nonrma_base = rma_alloc_size;
>> ram_addr_t nonrma_size = spapr->ram_limit - rma_alloc_size;
>>
>> - memory_region_init_ram(ram, NULL, "ppc_spapr.ram", nonrma_size);
>> - vmstate_register_ram_global(ram);
>> + memory_region_allocate_system_memory(ram, NULL, "ppc_spapr.ram",
>> + nonrma_size);
>
> The reason why I didn't do this in the simple way is that depending on the
> value of nonrma_base you may get smaller hugepages than you wanted.
>
> For example, if the hugepage size is 1G but nonrma_base is 32M, you will
> not be able to get a page size larger than 32M.
>
> Depending on the value of nonrma_base, it may be better to allocate the
> whole spapr->ram_limit to ppc_spapr.ram, and just ignore the first part of it.
>
> I see in target-ppc/kvm.c that rma_alloc_size is capped to 256M, and in
> practice it is 128M (arch/powerpc/kvm/book3s_hv_builtin.c. Considering
> that Linux overcommits so the memory isn't lost in the non-hugepage case, I
> think it's better to just waste the 128M of address space.
>
> Paolo
>
>> memory_region_add_subregion(sysmem, nonrma_base, ram);
>> }
Did you mean something like below? If so, I have to change MR tree and
place RMA under RAM, I guess.
I'll try to give it a try tomorrow on bare PPC970.
---
hw/ppc/spapr.c | 19 ++++++++++++-------
target-ppc/kvm.c | 9 +--------
target-ppc/kvm_ppc.h | 2 +-
3 files changed, 14 insertions(+), 16 deletions(-)
diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index a23c0f0..47ae6c1 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -1223,6 +1223,7 @@ static void ppc_spapr_init(MachineState *machine)
int i;
MemoryRegion *sysmem = get_system_memory();
MemoryRegion *ram = g_new(MemoryRegion, 1);
+ MemoryRegion *rma_region;
hwaddr rma_alloc_size;
hwaddr node0_size = (nb_numa_nodes > 1) ? numa_info[0].node_mem : ram_size;
uint32_t initrd_base = 0;
@@ -1230,6 +1231,7 @@ static void ppc_spapr_init(MachineState *machine)
long load_limit, rtas_limit, fw_size;
bool kernel_le = false;
char *filename;
+ void *rma = NULL;
msi_supported = true;
@@ -1239,7 +1241,7 @@ static void ppc_spapr_init(MachineState *machine)
cpu_ppc_hypercall = emulate_spapr_hypercall;
/* Allocate RMA if necessary */
- rma_alloc_size = kvmppc_alloc_rma("ppc_spapr.rma", sysmem);
+ rma_alloc_size = kvmppc_alloc_rma(&rma);
if (rma_alloc_size == -1) {
hw_error("qemu: Unable to create RMA\n");
@@ -1333,13 +1335,16 @@ static void ppc_spapr_init(MachineState *machine)
/* allocate RAM */
spapr->ram_limit = ram_size;
- if (spapr->ram_limit > rma_alloc_size) {
- ram_addr_t nonrma_base = rma_alloc_size;
- ram_addr_t nonrma_size = spapr->ram_limit - rma_alloc_size;
+ memory_region_allocate_system_memory(ram, NULL, "ppc_spapr.ram",
+ spapr->ram_limit);
+ memory_region_add_subregion(sysmem, 0, ram);
- memory_region_init_ram(ram, NULL, "ppc_spapr.ram", nonrma_size);
- vmstate_register_ram_global(ram);
- memory_region_add_subregion(sysmem, nonrma_base, ram);
+ if (rma_alloc_size && rma) {
+ rma_region = g_new(MemoryRegion, 1);
+ memory_region_init_ram_ptr(rma_region, NULL, "ppc_spapr.rma",
+ rma_alloc_size, rma);
+ vmstate_register_ram_global(rma_region);
+ memory_region_add_subregion(sysmem, 0, rma_region);
}
filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, "spapr-rtas.bin");
diff --git a/target-ppc/kvm.c b/target-ppc/kvm.c
index 995706a..9ca14d2 100644
--- a/target-ppc/kvm.c
+++ b/target-ppc/kvm.c
@@ -1582,13 +1582,11 @@ int kvmppc_smt_threads(void)
}
#ifdef TARGET_PPC64
-off_t kvmppc_alloc_rma(const char *name, MemoryRegion *sysmem)
+off_t kvmppc_alloc_rma(void **rma)
{
- void *rma;
off_t size;
int fd;
struct kvm_allocate_rma ret;
- MemoryRegion *rma_region;
/* If cap_ppc_rma == 0, contiguous RMA allocation is not supported
* if cap_ppc_rma == 1, contiguous RMA allocation is supported, but
@@ -1617,11 +1615,6 @@ off_t kvmppc_alloc_rma(const char *name, MemoryRegion
*sysmem)
return -1;
};
- rma_region = g_new(MemoryRegion, 1);
- memory_region_init_ram_ptr(rma_region, NULL, name, size, rma);
- vmstate_register_ram_global(rma_region);
- memory_region_add_subregion(sysmem, 0, rma_region);
-
return size;
}
diff --git a/target-ppc/kvm_ppc.h b/target-ppc/kvm_ppc.h
index 33c2171..bc5d2e8 100644
--- a/target-ppc/kvm_ppc.h
+++ b/target-ppc/kvm_ppc.h
@@ -31,7 +31,7 @@ int kvmppc_or_tsr_bits(PowerPCCPU *cpu, uint32_t tsr_bits);
int kvmppc_set_tcr(PowerPCCPU *cpu);
int kvmppc_booke_watchdog_enable(PowerPCCPU *cpu);
#ifndef CONFIG_USER_ONLY
-off_t kvmppc_alloc_rma(const char *name, MemoryRegion *sysmem);
+off_t kvmppc_alloc_rma(void **rma);
bool kvmppc_spapr_use_multitce(void);
void *kvmppc_create_spapr_tce(uint32_t liobn, uint32_t window_size,
uint64_t bus_offset, uint32_t page_shift,
--
2.0.0
