[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [PATCH v5 3/3] sclp-s390: Add memory hotplug SCLPs
|
From: |
Christian Borntraeger |
|
Subject: |
Re: [Qemu-devel] [PATCH v5 3/3] sclp-s390: Add memory hotplug SCLPs |
|
Date: |
Thu, 26 Jun 2014 15:14:47 +0200 |
|
User-agent: |
Mozilla/5.0 (X11; Linux i686; rv:24.0) Gecko/20100101 Thunderbird/24.6.0 |
On 25/06/14 16:27, Matthew Rosato wrote:
> Add memory information to read SCP info and add handlers for
> Read Storage Element Information, Attach Storage Element,
> Assign Storage and Unassign Storage.
>
> Signed-off-by: Matthew Rosato <address@hidden>
In general this looks fine. I gave it some testing and most of it seems to work.
With lots of standy chunks (-m 10240,maxmem=204800M,slots=16) I get an abort,
though:
#0 0x000003fffb9cffd8 in raise () from /lib64/libc.so.6
#1 0x000003fffb9d1b30 in abort () from /lib64/libc.so.6
#2 0x000003fffb9c7376 in __assert_fail_base () from /lib64/libc.so.6
#3 0x000003fffb9c7418 in __assert_fail () from /lib64/libc.so.6
#4 0x000000008001db28 in find_ram_offset (size=<optimized out>) at
/home/cborntra/REPOS/qemu/exec.c:1109
#5 ram_block_add (new_block=0x3fd70001ab0) at
/home/cborntra/REPOS/qemu/exec.c:1236
#6 0x000000008005ced0 in memory_region_init_ram (address@hidden,
address@hidden, address@hidden "standby.ram1", size=0) at
/home/cborntra/REPOS/qemu/memory.c:1033
Why do we pass size==0?
#7 0x0000000080080cdc in assign_storage (sccb=0x3fd759fca98) at
/home/cborntra/REPOS/qemu/hw/s390x/sclp.c:242
#8 sclp_execute (code=<optimized out>, sccb=0x3fd759fca98) at
/home/cborntra/REPOS/qemu/hw/s390x/sclp.c:348
#9 sclp_service_call (address@hidden, sccb=2144296960, code=<optimized out>)
at /home/cborntra/REPOS/qemu/hw/s390x/sclp.c:395
#10 0x00000000800b127c in kvm_sclp_service_call (run=<optimized out>, ipbh0=35,
cpu=0x808d4d00) at /home/cborntra/REPOS/qemu/target-s390x/kvm.c:705
#11 handle_b2 (run=<optimized out>, ipa1=<optimized out>, cpu=0x808d4d00) at
/home/cborntra/REPOS/qemu/target-s390x/kvm.c:777
#12 handle_instruction (run=<optimized out>, cpu=0x808d4d00) at
/home/cborntra/REPOS/qemu/target-s390x/kvm.c:1001
#13 handle_intercept (cpu=0x808d4d00) at
/home/cborntra/REPOS/qemu/target-s390x/kvm.c:1060
#14 kvm_arch_handle_exit (address@hidden, address@hidden) at
/home/cborntra/REPOS/qemu/target-s390x/kvm.c:1177
#15 0x000000008005a696 in kvm_cpu_exec (address@hidden) at
/home/cborntra/REPOS/qemu/kvm-all.c:1784
#16 0x000000008004668a in qemu_kvm_cpu_thread_fn (arg=0x808d4d00) at
/home/cborntra/REPOS/qemu/cpus.c:874
#17 0x000003fffce18412 in start_thread () from /lib64/libpthread.so.0
#18 0x000003fffba9e0ae in thread_start () from /lib64/libc.so.6
> ---
> hw/s390x/sclp.c | 259
> ++++++++++++++++++++++++++++++++++++++++++++++++++--
> target-s390x/cpu.h | 15 +++
> target-s390x/kvm.c | 5 +
> 3 files changed, 273 insertions(+), 6 deletions(-)
>
> diff --git a/hw/s390x/sclp.c b/hw/s390x/sclp.c
> index 769d7c3..b3bf924 100644
> --- a/hw/s390x/sclp.c
> +++ b/hw/s390x/sclp.c
> @@ -16,7 +16,8 @@
> #include "sysemu/kvm.h"
> #include "exec/memory.h"
> #include "sysemu/sysemu.h"
> -
> +#include "exec/address-spaces.h"
> +#include "qemu/config-file.h"
> #include "hw/s390x/sclp.h"
> #include "hw/s390x/event-facility.h"
>
> @@ -33,10 +34,19 @@ static inline SCLPEventFacility *get_event_facility(void)
> static void read_SCP_info(SCCB *sccb)
> {
> ReadInfo *read_info = (ReadInfo *) sccb;
> + sclpMemoryHotplugDev *mhd = get_sclp_memory_hotplug_dev();
> CPUState *cpu;
> - int shift = 0;
> int cpu_count = 0;
> int i = 0;
> + int increment_size = 20;
> + int rnsize, rnmax;
> + QemuOpts *opts = qemu_opts_find(qemu_find_opts("memory"), NULL);
> + int slots = qemu_opt_get_number(opts, "slots", 0);
> + int max_avail_slots = s390_get_memslot_count(kvm_state);
> +
> + if (slots > max_avail_slots) {
> + slots = max_avail_slots;
> + }
>
> CPU_FOREACH(cpu) {
> cpu_count++;
> @@ -54,14 +64,235 @@ static void read_SCP_info(SCCB *sccb)
>
> read_info->facilities = cpu_to_be64(SCLP_HAS_CPU_INFO);
>
> - while ((ram_size >> (20 + shift)) > 65535) {
> - shift++;
> + /*
> + * The storage increment size is a multiple of 1M and is a power of 2.
> + * The number of storage increments must be MAX_STORAGE_INCREMENTS or
> fewer.
> + */
> + while ((ram_size >> increment_size) > MAX_STORAGE_INCREMENTS) {
> + increment_size++;
> + }
> + rnmax = ram_size >> increment_size;
> +
> + /* Memory Hotplug is only supported for the ccw machine type */
> + if (mhd) {
> + while ((mhd->standby_mem_size >> increment_size) >
> + MAX_STORAGE_INCREMENTS) {
> + increment_size++;
> + }
> + assert(increment_size == mhd->increment_size);
> +
> + mhd->standby_subregion_size = MEM_SECTION_SIZE;
> + /* Deduct the memory slot already used for core */
> + if (slots > 0) {
> + while ((mhd->standby_subregion_size * (slots - 1)
> + < mhd->standby_mem_size)) {
> + mhd->standby_subregion_size = mhd->standby_subregion_size <<
> 1;
> + }
> + }
> + /*
> + * Initialize mapping of guest standby memory sections indicating
> which
> + * are and are not online. Assume all standby memory begins offline.
> + */
> + if (mhd->standby_state_map == 0) {
> + if (mhd->standby_mem_size % mhd->standby_subregion_size) {
> + mhd->standby_state_map = g_malloc0((mhd->standby_mem_size /
> + mhd->standby_subregion_size +
> 1) *
> + (mhd->standby_subregion_size /
> + MEM_SECTION_SIZE));
> + } else {
> + mhd->standby_state_map = g_malloc0(mhd->standby_mem_size /
> + MEM_SECTION_SIZE);
> + }
> + }
> + mhd->padded_ram_size = ram_size + mhd->pad_size;
> + mhd->rzm = 1 << mhd->increment_size;
> + rnmax = ((ram_size + mhd->standby_mem_size + mhd->pad_size)
> + >> mhd->increment_size);
> +
> + read_info->facilities |=
> cpu_to_be64(SCLP_FC_ASSIGN_ATTACH_READ_STOR);
> + }
> +
> + rnsize = 1 << (increment_size - 20);
> + if (rnsize <= 128) {
> + read_info->rnsize = rnsize;
> + } else {
> + read_info->rnsize = 0;
> + read_info->rnsize2 = cpu_to_be32(rnsize);
> }
> - read_info->rnmax = cpu_to_be16(ram_size >> (20 + shift));
> - read_info->rnsize = 1 << shift;
> +
> + if (rnmax < 0x10000) {
> + read_info->rnmax = cpu_to_be16(rnmax);
> + } else {
> + read_info->rnmax = cpu_to_be16(0);
> + read_info->rnmax2 = cpu_to_be64(rnmax);
> + }
> +
> sccb->h.response_code = cpu_to_be16(SCLP_RC_NORMAL_READ_COMPLETION);
> }
>
> +static void read_storage_element0_info(SCCB *sccb)
> +{
> + int i, assigned;
> + int subincrement_id = SCLP_STARTING_SUBINCREMENT_ID;
> + ReadStorageElementInfo *storage_info = (ReadStorageElementInfo *) sccb;
> + sclpMemoryHotplugDev *mhd = get_sclp_memory_hotplug_dev();
> +
> + assert(mhd);
> +
> + if ((ram_size >> mhd->increment_size) >= 0x10000) {
> + sccb->h.response_code = cpu_to_be16(SCLP_RC_SCCB_BOUNDARY_VIOLATION);
> + return;
> + }
> +
> + /* Return information regarding core memory */
> + storage_info->max_id = cpu_to_be16(mhd->standby_mem_size ? 1 : 0);
> + assigned = ram_size >> mhd->increment_size;
> + storage_info->assigned = cpu_to_be16(assigned);
> +
> + for (i = 0; i < assigned; i++) {
> + storage_info->entries[i] = cpu_to_be32(subincrement_id);
> + subincrement_id += SCLP_INCREMENT_UNIT;
> + }
> + sccb->h.response_code = cpu_to_be16(SCLP_RC_NORMAL_READ_COMPLETION);
> +}
> +
> +static void read_storage_element1_info(SCCB *sccb)
> +{
> + ReadStorageElementInfo *storage_info = (ReadStorageElementInfo *) sccb;
> + sclpMemoryHotplugDev *mhd = get_sclp_memory_hotplug_dev();
> +
> + assert(mhd);
> +
> + if ((mhd->standby_mem_size >> mhd->increment_size) >= 0x10000) {
> + sccb->h.response_code = cpu_to_be16(SCLP_RC_SCCB_BOUNDARY_VIOLATION);
> + return;
> + }
> +
> + /* Return information regarding standby memory */
> + storage_info->max_id = cpu_to_be16(mhd->standby_mem_size ? 1 : 0);
> + storage_info->assigned = cpu_to_be16(mhd->standby_mem_size >>
> + mhd->increment_size);
> + storage_info->standby = cpu_to_be16(mhd->standby_mem_size >>
> + mhd->increment_size);
> + sccb->h.response_code = cpu_to_be16(SCLP_RC_STANDBY_READ_COMPLETION);
> +}
> +
> +static void attach_storage_element(SCCB *sccb, uint16_t element)
> +{
> + int i, assigned, subincrement_id;
> + AttachStorageElement *attach_info = (AttachStorageElement *) sccb;
> + sclpMemoryHotplugDev *mhd = get_sclp_memory_hotplug_dev();
> +
> + assert(mhd);
> +
> + if (element != 1) {
> + sccb->h.response_code = cpu_to_be16(SCLP_RC_INVALID_SCLP_COMMAND);
> + return;
> + }
> +
> + assigned = mhd->standby_mem_size >> mhd->increment_size;
> + attach_info->assigned = cpu_to_be16(assigned);
> + subincrement_id = ((ram_size >> mhd->increment_size) << 16)
> + + SCLP_STARTING_SUBINCREMENT_ID;
> + for (i = 0; i < assigned; i++) {
> + attach_info->entries[i] = cpu_to_be32(subincrement_id);
> + subincrement_id += SCLP_INCREMENT_UNIT;
> + }
> + sccb->h.response_code = cpu_to_be16(SCLP_RC_NORMAL_COMPLETION);
> +}
> +
> +static void assign_storage(SCCB *sccb)
> +{
> + MemoryRegion *mr = NULL;
> + int this_subregion_size;
> + AssignStorage *assign_info = (AssignStorage *) sccb;
> + sclpMemoryHotplugDev *mhd = get_sclp_memory_hotplug_dev();
> + assert(mhd);
> + ram_addr_t assign_addr = (assign_info->rn - 1) * mhd->rzm;
> + MemoryRegion *sysmem = get_system_memory();
> +
> + if ((assign_addr % MEM_SECTION_SIZE == 0) &&
> + (assign_addr >= mhd->padded_ram_size)) {
> + /* Re-use existing memory region if found */
> + mr = memory_region_find(sysmem, assign_addr, 1).mr;
> + if (!mr) {
> +
> + MemoryRegion *standby_ram = g_new(MemoryRegion, 1);
> +
> + /* offset to align to standby_subregion_size for allocation */
> + ram_addr_t offset = assign_addr -
> + (assign_addr - mhd->padded_ram_size)
> + % mhd->standby_subregion_size;
> +
> + /* strlen("standby.ram") + 4 (Max of KVM_MEMORY_SLOTS) + NULL */
> + char id[16];
> + snprintf(id, 16, "standby.ram%d",
> + (int)((offset - mhd->padded_ram_size) /
> + mhd->standby_subregion_size) + 1);
> +
> + /* Allocate a subregion of the calculated standby_subregion_size
> */
> + if (offset + mhd->standby_subregion_size >
> + mhd->padded_ram_size + mhd->standby_mem_size) {
> + this_subregion_size = mhd->padded_ram_size +
> + mhd->standby_mem_size - offset;
> + } else {
> + this_subregion_size = mhd->standby_subregion_size;
> + }
> +
> + memory_region_init_ram(standby_ram, NULL, id,
> this_subregion_size);
> + vmstate_register_ram_global(standby_ram);
> + memory_region_add_subregion(sysmem, offset, standby_ram);
> + }
> + /* The specified subregion is no longer in standby */
> + mhd->standby_state_map[(assign_addr - mhd->padded_ram_size)
> + / MEM_SECTION_SIZE] = 1;
> + }
> + sccb->h.response_code = cpu_to_be16(SCLP_RC_NORMAL_COMPLETION);
> +}
> +
> +static void unassign_storage(SCCB *sccb)
> +{
> + MemoryRegion *mr = NULL;
> + AssignStorage *assign_info = (AssignStorage *) sccb;
> + sclpMemoryHotplugDev *mhd = get_sclp_memory_hotplug_dev();
> + assert(mhd);
> + ram_addr_t unassign_addr = (assign_info->rn - 1) * mhd->rzm;
> + MemoryRegion *sysmem = get_system_memory();
> +
> + /* if the addr is a multiple of 256 MB */
> + if ((unassign_addr % MEM_SECTION_SIZE == 0) &&
> + (unassign_addr >= mhd->padded_ram_size)) {
> + mhd->standby_state_map[(unassign_addr -
> + mhd->padded_ram_size) / MEM_SECTION_SIZE] = 0;
> +
> + /* find the specified memory region and destroy it */
> + mr = memory_region_find(sysmem, unassign_addr, 1).mr;
> + if (mr) {
> + int i;
> + int is_removable = 1;
> + ram_addr_t map_offset = (unassign_addr - mhd->padded_ram_size -
> + (unassign_addr - mhd->padded_ram_size)
> + % mhd->standby_subregion_size);
> + /* Mark all affected subregions as 'standby' once again */
> + for (i = 0;
> + i < (mhd->standby_subregion_size / MEM_SECTION_SIZE);
> + i++) {
> +
> + if (mhd->standby_state_map[i + map_offset /
> MEM_SECTION_SIZE]) {
> + is_removable = 0;
> + break;
> + }
> + }
> + if (is_removable) {
> + memory_region_del_subregion(sysmem, mr);
> + memory_region_destroy(mr);
> + g_free(mr);
> + }
> + }
> + }
> + sccb->h.response_code = cpu_to_be16(SCLP_RC_NORMAL_COMPLETION);
> +}
> +
> /* Provide information about the CPU */
> static void sclp_read_cpu_info(SCCB *sccb)
> {
> @@ -103,6 +334,22 @@ static void sclp_execute(SCCB *sccb, uint32_t code)
> case SCLP_CMDW_READ_CPU_INFO:
> sclp_read_cpu_info(sccb);
> break;
> + case SCLP_READ_STORAGE_ELEMENT_INFO:
> + if (code & 0xff00) {
> + read_storage_element1_info(sccb);
> + } else {
> + read_storage_element0_info(sccb);
> + }
> + break;
> + case SCLP_ATTACH_STORAGE_ELEMENT:
> + attach_storage_element(sccb, (code & 0xff00) >> 8);
> + break;
> + case SCLP_ASSIGN_STORAGE:
> + assign_storage(sccb);
> + break;
> + case SCLP_UNASSIGN_STORAGE:
> + unassign_storage(sccb);
> + break;
> default:
> efc->command_handler(ef, sccb, code);
> break;
> diff --git a/target-s390x/cpu.h b/target-s390x/cpu.h
> index ba0e4b4..1c1681c 100644
> --- a/target-s390x/cpu.h
> +++ b/target-s390x/cpu.h
> @@ -1047,6 +1047,7 @@ static inline void cpu_inject_crw_mchk(S390CPU *cpu)
>
> /* from s390-virtio-ccw */
> #define MEM_SECTION_SIZE 0x10000000UL
> +#define MAX_AVAIL_SLOTS 32
>
> /* fpu_helper.c */
> uint32_t set_cc_nz_f32(float32 v);
> @@ -1070,6 +1071,7 @@ void kvm_s390_enable_css_support(S390CPU *cpu);
> int kvm_s390_assign_subch_ioeventfd(EventNotifier *notifier, uint32_t sch,
> int vq, bool assign);
> int kvm_s390_cpu_restart(S390CPU *cpu);
> +int kvm_s390_get_memslot_count(KVMState *s);
> void kvm_s390_clear_cmma_callback(void *opaque);
> #else
> static inline void kvm_s390_io_interrupt(uint16_t subchannel_id,
> @@ -1097,6 +1099,10 @@ static inline int kvm_s390_cpu_restart(S390CPU *cpu)
> static inline void kvm_s390_clear_cmma_callback(void *opaque)
> {
> }
> +static inline int kvm_s390_get_memslot_count(KVMState *s)
> +{
> + return MAX_AVAIL_SLOTS;
> +}
> #endif
>
> static inline void cmma_reset(S390CPU *cpu)
> @@ -1115,6 +1121,15 @@ static inline int s390_cpu_restart(S390CPU *cpu)
> return -ENOSYS;
> }
>
> +static inline int s390_get_memslot_count(KVMState *s)
> +{
> + if (kvm_enabled()) {
> + return kvm_s390_get_memslot_count(s);
> + } else {
> + return MAX_AVAIL_SLOTS;
> + }
> +}
> +
> void s390_io_interrupt(uint16_t subchannel_id, uint16_t subchannel_nr,
> uint32_t io_int_parm, uint32_t io_int_word);
> void s390_crw_mchk(void);
> diff --git a/target-s390x/kvm.c b/target-s390x/kvm.c
> index a6e587b..4b05d48 100644
> --- a/target-s390x/kvm.c
> +++ b/target-s390x/kvm.c
> @@ -1283,3 +1283,8 @@ int kvm_s390_assign_subch_ioeventfd(EventNotifier
> *notifier, uint32_t sch,
> }
> return kvm_vm_ioctl(kvm_state, KVM_IOEVENTFD, &kick);
> }
> +
> +int kvm_s390_get_memslot_count(KVMState *s)
> +{
> + return kvm_check_extension(s, KVM_CAP_NR_MEMSLOTS);
> +}
>