Build ACPI Heterogeneous Memory Attribute Table (HMAT)
Subsystems (5)
v6 cover Build ACPI Heterogeneous Memory Attribute Table (HMAT)
This series of patches will build Heterogeneous Memory Attribute Table (HMAT) according to the command line. The ACPI HMAT describes the memory attributes, such as memory side cache attributes and bandwidth and latency details, related to the Memory Proximity Domain.
The software is expected to use HMAT information as hint for optimization.
The V5 patches link:
https://lists.gnu.org/archive/html/qemu-devel/2019-06/msg03138.html
Changelog:
v6:
- Rebase to upstream, move numa globals in arm/sbsa-ref
- When used once or twice in the function, use ms->numa_state->num_nodes(numa_info) directly (Igor)
- Correct some mistakes
- Use once monitor_printf in hmp_info_numa (Igor)
- Add new patch to extend CLI of "-numa node" option to indicate the initiator numa node-id (Dan)
- Update to ACPI 6.3 (Jonathan)
- Add QMP interface to update HMAT at runtime (Igor)
- Add test cases for ACPI HMAT
v5:
- spilt the 1-6/11 and 8/11 from patch v4 to build Memory Subsystem Address Range Structure(s) and System Locality Latency and Bandwidth Information Structure(s) firstly.
- add 1/8 of patch v5 to simplify arm_load_dtb() (Igor)
- drop the helper machine_num_numa_nodes() and use machine->numa_state->num_nodes (and numa_state->nodes) directly (Igor)
- Add more descriptions from ACPI spec (Igor)
- Add the reason of using stub (Igor)
- Use GArray for NUMA memory ranges data (Igor)
- Separate hmat_build_lb() (Igor)
- Drop all global variables and use local variables instead (Igor)
- Add error message when base unit < 10
- Update the hmat-lb option example by using '-numa cpu' and '-numa memdev' (Igor)
v4:
- send the patch of "move numa global variables into MachineState" together with HMAT patches.
https://lists.gnu.org/archive/html/qemu-devel/2019-04/msg03662.html
- spilt the 1/8 of v3 patch into two patches, 4/11 introduces build_mem_ranges() and 5/11 builds HMAT (Igor)
- use build_append_int_noprefix() to build parts of ACPI table in all patches (Igor)
- Split 8/8 of patch v3 into two parts, 10/11 introduces NFIT generalizations (build_acpi_aml_common), and use it in 11/11 to simplify hmat_build_aml (Igor)
- use MachineState instead of PCMachineState to build HMAT more generalic (Igor)
- move the 7/8 v3 patch into the former patches
- update the version tag from 4.0 to 4.1
v3:
- rebase the fixing patch into the jingqi's patches (Eric)
- update the version tag from 3.10 to 4.0 (Eric)
v2:
Per Igor and Eric's comments, fix some coding style and small issues:
- update the version number in qapi/misc.json
- including the expansion of the acronym HMAT in qapi/misc.json
- correct spell mistakes in qapi/misc.json and qemu-options.hx
- fix the comment syle in hw/i386/acpi-build.c
and hw/acpi/hmat.h
- remove some unnecessary head files in hw/acpi/hmat.c
- use hardcoded numbers from spec to generate
Memory Subsystem Address Range Structure in hw/acpi/hmat.c
- drop the struct AcpiHmat and AcpiHmatSpaRange
in hw/acpi/hmat.h
- rewrite NFIT code to build _HMA method
Liu Jingqi (6):
hmat acpi: Build Memory Proximity Domain Attributes Structure(s) hmat acpi: Build System Locality Latency and Bandwidth Information
Structure(s)
hmat acpi: Build Memory Side Cache Information Structure(s)
numa: Extend the CLI to provide memory latency and bandwidth
information
numa: Extend the CLI to provide memory side cache information hmat acpi: Implement _HMA method to update HMAT at runtime
Tao Xu (8):
hw/arm: simplify arm_load_dtb
numa: move numa global variable nb_numa_nodes into MachineState
numa: move numa global variable have_numa_distance into MachineState
numa: move numa global variable numa_info into MachineState
numa: Extend CLI to provide initiator information for numa nodes
acpi: introduce aml_build_runtime_buf for NFIT generalizations
QMP: Add QMP interface to update HMAT at runtime tests/bios-tables-test: add test cases for ACPI HMAT
exec.c | 5 +- hw/acpi/Kconfig | 5 + hw/acpi/Makefile.objs | 1 + hw/acpi/acpi-stub.c | 7 + hw/acpi/aml-build.c | 9 +- hw/acpi/hmat.c | 552 ++++++++++++++++++++++++++++ hw/acpi/hmat.h | 172 +++++++++ hw/acpi/nvdimm.c | 49 ++- hw/arm/aspeed.c | 5 +- hw/arm/boot.c | 20 +- hw/arm/collie.c | 8 +- hw/arm/cubieboard.c | 5 +- hw/arm/exynos4_boards.c | 7 +- hw/arm/highbank.c | 8 +- hw/arm/imx25_pdk.c | 5 +- hw/arm/integratorcp.c | 8 +- hw/arm/kzm.c | 5 +- hw/arm/mainstone.c | 5 +- hw/arm/mcimx6ul-evk.c | 5 +- hw/arm/mcimx7d-sabre.c | 5 +- hw/arm/musicpal.c | 8 +- hw/arm/nseries.c | 5 +- hw/arm/omap_sx1.c | 5 +- hw/arm/palm.c | 10 +- hw/arm/raspi.c | 6 +- hw/arm/realview.c | 5 +- hw/arm/sabrelite.c | 5 +- hw/arm/sbsa-ref.c | 12 +- hw/arm/spitz.c | 5 +- hw/arm/tosa.c | 8 +- hw/arm/versatilepb.c | 5 +- hw/arm/vexpress.c | 5 +- hw/arm/virt-acpi-build.c | 19 +- hw/arm/virt.c | 18 +- hw/arm/xilinx_zynq.c | 8 +- hw/arm/xlnx-versal-virt.c | 7 +- hw/arm/xlnx-zcu102.c | 5 +- hw/arm/z2.c | 8 +- hw/core/machine.c | 42 ++- hw/i386/acpi-build.c | 11 +- hw/i386/pc.c | 14 +- hw/i386/pc_piix.c | 6 + hw/i386/pc_q35.c | 6 + hw/mem/pc-dimm.c | 2 + hw/pci-bridge/pci_expander_bridge.c | 3 +- hw/ppc/spapr.c | 36 +- hw/ppc/spapr_pci.c | 4 +- include/hw/acpi/aml-build.h | 2 +- include/hw/arm/boot.h | 4 +- include/hw/boards.h | 2 + include/hw/mem/nvdimm.h | 6 + include/qemu/typedefs.h | 2 + include/sysemu/numa.h | 32 +- include/sysemu/sysemu.h | 24 ++ monitor/misc.c | 12 +- numa.c | 341 +++++++++++++++-- qapi/misc.json | 235 +++++++++++- qemu-options.hx | 84 ++++- tests/bios-tables-test.c | 43 +++ 59 files changed, 1677 insertions(+), 264 deletions(-) create mode 100644 hw/acpi/hmat.c create mode 100644 hw/acpi/hmat.h
Signature · 1 line
2.20.1
PATCH v6 1/14 hw/arm: simplify arm_load_dtb
In struct arm_boot_info, kernel_filename, initrd_filename and kernel_cmdline are copied from from MachineState. This patch add MachineState as a parameter into arm_load_dtb() and move the copy chunk of kernel_filename, initrd_filename and kernel_cmdline into arm_load_kernel().
---
Changes in v6:
- rebase to upstream, move the copy chunk of kernel_filename arm_load_kernel() in arm/sbsa-ref
--- hw/arm/aspeed.c | 5 +---- hw/arm/boot.c | 14 ++++++++------ hw/arm/collie.c | 8 +------- hw/arm/cubieboard.c | 5 +---- hw/arm/exynos4_boards.c | 7 ++----- hw/arm/highbank.c | 8 +------- hw/arm/imx25_pdk.c | 5 +---- hw/arm/integratorcp.c | 8 +------- hw/arm/kzm.c | 5 +---- hw/arm/mainstone.c | 5 +---- hw/arm/mcimx6ul-evk.c | 5 +---- hw/arm/mcimx7d-sabre.c | 5 +---- hw/arm/musicpal.c | 8 +------- hw/arm/nseries.c | 5 +---- hw/arm/omap_sx1.c | 5 +---- hw/arm/palm.c | 10 ++-------- hw/arm/raspi.c | 6 +----- hw/arm/realview.c | 5 +---- hw/arm/sabrelite.c | 5 +---- hw/arm/sbsa-ref.c | 3 +-- hw/arm/spitz.c | 5 +---- hw/arm/tosa.c | 8 +------- hw/arm/versatilepb.c | 5 +---- hw/arm/vexpress.c | 5 +---- hw/arm/virt.c | 8 +++----- hw/arm/xilinx_zynq.c | 8 +------- hw/arm/xlnx-versal-virt.c | 7 ++----- hw/arm/xlnx-zcu102.c | 5 +---- hw/arm/z2.c | 8 +------- include/hw/arm/boot.h | 4 ++-- 30 files changed, 43 insertions(+), 147 deletions(-)
hw/arm/aspeed.c +1 -4
@@ -241,9 +241,6 @@ static void aspeed_board_init(MachineState *machine,write_boot_rom (drive0,FIRMWARE_ADDR , fl->size, &error_abort); } - aspeed_board_binfo.kernel_filename = machine->kernel_filename; - aspeed_board_binfo.initrd_filename = machine->initrd_filename; - aspeed_board_binfo.kernel_cmdline = machine->kernel_cmdline; aspeed_board_binfo.ram_size = ram_size; aspeed_board_binfo.loader_start = sc->info->memmap[ASPEED_SDRAM ]; aspeed_board_binfo.nb_cpus = bmc->soc.num_cpus;
@@ -252,7 +249,7 @@ static void aspeed_board_init(MachineState *machine, cfg->i2c_init (bmc); } -arm_load_kernel (ARM_CPU (first_cpu), &aspeed_board_binfo); +arm_load_kernel (ARM_CPU (first_cpu), machine, &aspeed_board_binfo); }static void palmetto_bmc_i2c_init (AspeedBoardState *bmc)
hw/arm/boot.c +8 -6
@@ -524,7 +524,7 @@ static void fdt_add_psci_node(void *fdt) }int arm_load_dtb (hwaddr addr,const struct arm_boot_info *binfo, -hwaddr addr_limit,AddressSpace *as) +hwaddr addr_limit,AddressSpace *as,MachineState *ms) {void *fdt =NULL ;int size, rc, n =0 ;
@@ -627,9 +627,9 @@ int arm_load_dtb(hwaddr addr, const struct arm_boot_info *binfo,qemu_fdt_add_subnode (fdt,"/chosen" ); } -if (binfo->kernel_cmdline && *binfo->kernel_cmdline) { +if (ms->kernel_cmdline && *ms->kernel_cmdline) { rc =qemu_fdt_setprop_string (fdt,"/chosen" ,"bootargs" , - binfo->kernel_cmdline); + ms->kernel_cmdline);if (rc <0 ) {fprintf (stderr,"couldn't set /chosen/bootargs\n" ); goto fail;
@@ -1244,7 +1244,7 @@ static void arm_setup_firmware_boot(ARMCPU *cpu, struct arm_boot_info *info)*/ } -void arm_load_kernel (ARMCPU *cpu,struct arm_boot_info *info) +void arm_load_kernel (ARMCPU *cpu,MachineState *ms,struct arm_boot_info *info) {CPUState *cs;AddressSpace *as =arm_boot_address_space (cpu, info);
@@ -1265,7 +1265,9 @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info)* doesn't support secure. */ assert (!(info->secure_board_setup &&kvm_enabled ())); - + info->kernel_filename = ms->kernel_filename; + info->kernel_cmdline = ms->kernel_cmdline; + info->initrd_filename = ms->initrd_filename; info->dtb_filename =qemu_opt_get (qemu_get_machine_opts (),"dtb" ); info->dtb_limit =0 ;
@@ -1277,7 +1279,7 @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info) }if (!info->skip_dtb_autoload &&have_dtb (info)) { -if (arm_load_dtb (info->dtb_start, info, info->dtb_limit, as) <0 ) { +if (arm_load_dtb (info->dtb_start, info, info->dtb_limit, as, ms) <0 ) {exit (1 ); } }
hw/arm/collie.c +1 -7
@@ -26,9 +26,6 @@ static struct arm_boot_info collie_binfo = {static void collie_init (MachineState *machine) { -const char *kernel_filename = machine->kernel_filename; -const char *kernel_cmdline = machine->kernel_cmdline; -const char *initrd_filename = machine->initrd_filename;StrongARMState *s;DriveInfo *dinfo;MemoryRegion *sysmem =get_system_memory ();
@@ -47,11 +44,8 @@ static void collie_init(MachineState *machine)sysbus_create_simple ("scoop" ,0x40800000 ,NULL ); - collie_binfo.kernel_filename = kernel_filename; - collie_binfo.kernel_cmdline = kernel_cmdline; - collie_binfo.initrd_filename = initrd_filename; collie_binfo.board_id =0x208 ; -arm_load_kernel (s->cpu, &collie_binfo); +arm_load_kernel (s->cpu, machine, &collie_binfo); }static void collie_machine_init (MachineClass *mc)
hw/arm/cubieboard.c +1 -4
@@ -72,10 +72,7 @@ static void cubieboard_init(MachineState *machine)/* TODO create and connect IDE devices for ide_drive_get() */ cubieboard_binfo.ram_size = machine->ram_size; - cubieboard_binfo.kernel_filename = machine->kernel_filename; - cubieboard_binfo.kernel_cmdline = machine->kernel_cmdline; - cubieboard_binfo.initrd_filename = machine->initrd_filename; -arm_load_kernel (&s->a10->cpu, &cubieboard_binfo); +arm_load_kernel (&s->a10->cpu, machine, &cubieboard_binfo); }static void cubieboard_machine_init (MachineClass *mc)
hw/arm/exynos4_boards.c +2 -5
@@ -120,9 +120,6 @@ exynos4_boards_init_common(MachineState *machine, exynos4_board_binfo.board_id = exynos4_board_id[board_type]; exynos4_board_binfo.smp_bootreg_addr = exynos4_board_smp_bootreg_addr[board_type]; - exynos4_board_binfo.kernel_filename = machine->kernel_filename; - exynos4_board_binfo.initrd_filename = machine->initrd_filename; - exynos4_board_binfo.kernel_cmdline = machine->kernel_cmdline; exynos4_board_binfo.gic_cpu_if_addr =EXYNOS4210_SMP_PRIVATE_BASE_ADDR +0x100 ;
@@ -141,7 +138,7 @@ static void nuri_init(MachineState *machine) {exynos4_boards_init_common (machine,EXYNOS4_BOARD_NURI ); -arm_load_kernel (ARM_CPU (first_cpu), &exynos4_board_binfo); +arm_load_kernel (ARM_CPU (first_cpu), machine, &exynos4_board_binfo); }static void smdkc210_init (MachineState *machine)
@@ -151,7 +148,7 @@ static void smdkc210_init(MachineState *machine)lan9215_init (SMDK_LAN9118_BASE_ADDR ,qemu_irq_invert (s->soc.irq_table[exynos4210_get_irq (37 ,1 )])); -arm_load_kernel (ARM_CPU (first_cpu), &exynos4_board_binfo); +arm_load_kernel (ARM_CPU (first_cpu), machine, &exynos4_board_binfo); }static void nuri_class_init (ObjectClass *oc,void *data)
hw/arm/highbank.c +1 -7
@@ -234,9 +234,6 @@ enum cxmachines {static void calxeda_init (MachineState *machine,enum cxmachines machine_id) {ram_addr_t ram_size = machine->ram_size; -const char *kernel_filename = machine->kernel_filename; -const char *kernel_cmdline = machine->kernel_cmdline; -const char *initrd_filename = machine->initrd_filename;DeviceState *dev =NULL ;SysBusDevice *busdev;qemu_irq pic[128 ];
@@ -387,9 +384,6 @@ static void calxeda_init(MachineState *machine, enum cxmachines machine_id)/* TODO create and connect IDE devices for ide_drive_get() */ highbank_binfo.ram_size = ram_size; - highbank_binfo.kernel_filename = kernel_filename; - highbank_binfo.kernel_cmdline = kernel_cmdline; - highbank_binfo.initrd_filename = initrd_filename;/* highbank requires a dtb in order to boot, and the dtb will override * the board ID. The following value is ignored, so set it to -1 to be * clear that the value is meaningless.
@@ -409,7 +403,7 @@ static void calxeda_init(MachineState *machine, enum cxmachines machine_id) "may not boot."); } -arm_load_kernel (ARM_CPU (first_cpu), &highbank_binfo); +arm_load_kernel (ARM_CPU (first_cpu), machine, &highbank_binfo); }static void highbank_init (MachineState *machine)
hw/arm/imx25_pdk.c +1 -4
@@ -116,9 +116,6 @@ static void imx25_pdk_init(MachineState *machine) } imx25_pdk_binfo.ram_size = machine->ram_size; - imx25_pdk_binfo.kernel_filename = machine->kernel_filename; - imx25_pdk_binfo.kernel_cmdline = machine->kernel_cmdline; - imx25_pdk_binfo.initrd_filename = machine->initrd_filename; imx25_pdk_binfo.loader_start =FSL_IMX25_SDRAM0_ADDR ; imx25_pdk_binfo.board_id =1771 , imx25_pdk_binfo.nb_cpus =1 ;
@@ -129,7 +126,7 @@ static void imx25_pdk_init(MachineState *machine)* fail. */ if (!qtest_enabled ()) { -arm_load_kernel (&s->soc.cpu, &imx25_pdk_binfo); +arm_load_kernel (&s->soc.cpu, machine, &imx25_pdk_binfo); } }
hw/arm/integratorcp.c +1 -7
@@ -578,9 +578,6 @@ static struct arm_boot_info integrator_binfo = {static void integratorcp_init (MachineState *machine) {ram_addr_t ram_size = machine->ram_size; -const char *kernel_filename = machine->kernel_filename; -const char *kernel_cmdline = machine->kernel_cmdline; -const char *initrd_filename = machine->initrd_filename;Object *cpuobj;ARMCPU *cpu;MemoryRegion *address_space_mem =get_system_memory ();
@@ -650,10 +647,7 @@ static void integratorcp_init(MachineState *machine)sysbus_create_simple ("pl110" ,0xc0000000 , pic[22 ]); integrator_binfo.ram_size = ram_size; - integrator_binfo.kernel_filename = kernel_filename; - integrator_binfo.kernel_cmdline = kernel_cmdline; - integrator_binfo.initrd_filename = initrd_filename; -arm_load_kernel (cpu, &integrator_binfo); +arm_load_kernel (cpu, machine, &integrator_binfo); }static void integratorcp_machine_init (MachineClass *mc)
hw/arm/kzm.c +1 -4
@@ -126,13 +126,10 @@ static void kzm_init(MachineState *machine) } kzm_binfo.ram_size = machine->ram_size; - kzm_binfo.kernel_filename = machine->kernel_filename; - kzm_binfo.kernel_cmdline = machine->kernel_cmdline; - kzm_binfo.initrd_filename = machine->initrd_filename; kzm_binfo.nb_cpus =1 ;if (!qtest_enabled ()) { -arm_load_kernel (&s->soc.cpu, &kzm_binfo); +arm_load_kernel (&s->soc.cpu, machine, &kzm_binfo); } }
hw/arm/mainstone.c +1 -4
@@ -177,11 +177,8 @@ static void mainstone_common_init(MemoryRegion *address_space_mem,smc91c111_init (&nd_table[0 ],MST_ETH_PHYS ,qdev_get_gpio_in (mst_irq,ETHERNET_IRQ )); - mainstone_binfo.kernel_filename = machine->kernel_filename; - mainstone_binfo.kernel_cmdline = machine->kernel_cmdline; - mainstone_binfo.initrd_filename = machine->initrd_filename; mainstone_binfo.board_id = arm_id; -arm_load_kernel (mpu->cpu, &mainstone_binfo); +arm_load_kernel (mpu->cpu, machine, &mainstone_binfo); }static void mainstone_init (MachineState *machine)
hw/arm/mcimx6ul-evk.c +1 -4
@@ -39,9 +39,6 @@ static void mcimx6ul_evk_init(MachineState *machine) .loader_start = FSL_IMX6UL_MMDC_ADDR, .board_id = -1, .ram_size = machine->ram_size, - .kernel_filename = machine->kernel_filename, - .kernel_cmdline = machine->kernel_cmdline, - .initrd_filename = machine->initrd_filename, .nb_cpus = smp_cpus, };
@@ -71,7 +68,7 @@ static void mcimx6ul_evk_init(MachineState *machine) }if (!qtest_enabled ()) { -arm_load_kernel (&s->soc.cpu[0 ], &boot_info); +arm_load_kernel (&s->soc.cpu[0 ], machine, &boot_info); } }
hw/arm/mcimx7d-sabre.c +1 -4
@@ -42,9 +42,6 @@ static void mcimx7d_sabre_init(MachineState *machine) .loader_start = FSL_IMX7_MMDC_ADDR, .board_id = -1, .ram_size = machine->ram_size, - .kernel_filename = machine->kernel_filename, - .kernel_cmdline = machine->kernel_cmdline, - .initrd_filename = machine->initrd_filename, .nb_cpus = smp_cpus, };
@@ -74,7 +71,7 @@ static void mcimx7d_sabre_init(MachineState *machine) }if (!qtest_enabled ()) { -arm_load_kernel (&s->soc.cpu[0 ], &boot_info); +arm_load_kernel (&s->soc.cpu[0 ], machine, &boot_info); } }
hw/arm/musicpal.c +1 -7
@@ -1568,9 +1568,6 @@ static struct arm_boot_info musicpal_binfo = {static void musicpal_init (MachineState *machine) { -const char *kernel_filename = machine->kernel_filename; -const char *kernel_cmdline = machine->kernel_cmdline; -const char *initrd_filename = machine->initrd_filename;ARMCPU *cpu;qemu_irq pic[32 ];DeviceState *dev;
@@ -1699,10 +1696,7 @@ static void musicpal_init(MachineState *machine)sysbus_connect_irq (s,0 , pic[MP_AUDIO_IRQ ]); musicpal_binfo.ram_size =MP_RAM_DEFAULT_SIZE ; - musicpal_binfo.kernel_filename = kernel_filename; - musicpal_binfo.kernel_cmdline = kernel_cmdline; - musicpal_binfo.initrd_filename = initrd_filename; -arm_load_kernel (cpu, &musicpal_binfo); +arm_load_kernel (cpu, machine, &musicpal_binfo); }static void musicpal_machine_init (MachineClass *mc)
hw/arm/nseries.c +1 -4
@@ -1358,10 +1358,7 @@ static void n8x0_init(MachineState *machine,if (machine->kernel_filename) {/* Or at the linux loader. */ - binfo->kernel_filename = machine->kernel_filename; - binfo->kernel_cmdline = machine->kernel_cmdline; - binfo->initrd_filename = machine->initrd_filename; -arm_load_kernel (s->mpu->cpu, binfo); +arm_load_kernel (s->mpu->cpu, machine, binfo);qemu_register_reset (n8x0_boot_init, s); }
hw/arm/omap_sx1.c +1 -4
@@ -196,10 +196,7 @@ static void sx1_init(MachineState *machine, const int version) }/* Load the kernel. */ - sx1_binfo.kernel_filename = machine->kernel_filename; - sx1_binfo.kernel_cmdline = machine->kernel_cmdline; - sx1_binfo.initrd_filename = machine->initrd_filename; -arm_load_kernel (mpu->cpu, &sx1_binfo); +arm_load_kernel (mpu->cpu, machine, &sx1_binfo);/* TODO: fix next line */ //~ qemu_console_resize(ds, 640, 480);
hw/arm/palm.c +2 -8
@@ -186,9 +186,6 @@ static struct arm_boot_info palmte_binfo = {static void palmte_init (MachineState *machine) { -const char *kernel_filename = machine->kernel_filename; -const char *kernel_cmdline = machine->kernel_cmdline; -const char *initrd_filename = machine->initrd_filename;MemoryRegion *address_space_mem =get_system_memory ();struct omap_mpu_state_s *mpu;int flash_size =0x00800000 ;
@@ -248,16 +245,13 @@ static void palmte_init(MachineState *machine) } } -if (!rom_loaded && !kernel_filename && !qtest_enabled ()) { +if (!rom_loaded && !machine->kernel_filename && !qtest_enabled ()) {fprintf (stderr,"Kernel or ROM image must be specified\n" );exit (1 ); }/* Load the kernel. */ - palmte_binfo.kernel_filename = kernel_filename; - palmte_binfo.kernel_cmdline = kernel_cmdline; - palmte_binfo.initrd_filename = initrd_filename; -arm_load_kernel (mpu->cpu, &palmte_binfo); +arm_load_kernel (mpu->cpu, machine, &palmte_binfo); }static void palmte_machine_init (MachineClass *mc)
hw/arm/raspi.c +1 -5
@@ -157,13 +157,9 @@ static void setup_boot(MachineState *machine, int version, size_t ram_size) binfo.entry = firmware_addr; binfo.firmware_loaded = true; - }else { - binfo.kernel_filename = machine->kernel_filename; - binfo.kernel_cmdline = machine->kernel_cmdline; - binfo.initrd_filename = machine->initrd_filename; } -arm_load_kernel (ARM_CPU (first_cpu), &binfo); +arm_load_kernel (ARM_CPU (first_cpu), machine, &binfo); }static void raspi_init (MachineState *machine,int version)
hw/arm/realview.c +1 -4
@@ -349,13 +349,10 @@ static void realview_init(MachineState *machine,memory_region_add_subregion (sysmem,SMP_BOOT_ADDR , ram_hack); realview_binfo.ram_size = ram_size; - realview_binfo.kernel_filename = machine->kernel_filename; - realview_binfo.kernel_cmdline = machine->kernel_cmdline; - realview_binfo.initrd_filename = machine->initrd_filename; realview_binfo.nb_cpus = smp_cpus; realview_binfo.board_id = realview_board_id[board_type]; realview_binfo.loader_start = (board_type ==BOARD_PB_A8 ?0x70000000 :0 ); -arm_load_kernel (ARM_CPU (first_cpu), &realview_binfo); +arm_load_kernel (ARM_CPU (first_cpu), machine, &realview_binfo); }static void realview_eb_init (MachineState *machine)
hw/arm/sabrelite.c +1 -4
@@ -102,16 +102,13 @@ static void sabrelite_init(MachineState *machine) } sabrelite_binfo.ram_size = machine->ram_size; - sabrelite_binfo.kernel_filename = machine->kernel_filename; - sabrelite_binfo.kernel_cmdline = machine->kernel_cmdline; - sabrelite_binfo.initrd_filename = machine->initrd_filename; sabrelite_binfo.nb_cpus = smp_cpus; sabrelite_binfo.secure_boot = true; sabrelite_binfo.write_secondary_boot = sabrelite_write_secondary; sabrelite_binfo.secondary_cpu_reset_hook = sabrelite_reset_secondary;if (!qtest_enabled ()) { -arm_load_kernel (&s->soc.cpu[0 ], &sabrelite_binfo); +arm_load_kernel (&s->soc.cpu[0 ], machine, &sabrelite_binfo); } }
hw/arm/sbsa-ref.c +1 -2
@@ -710,13 +710,12 @@ static void sbsa_ref_init(MachineState *machine)create_pcie (sms, pic); sms->bootinfo.ram_size = machine->ram_size; - sms->bootinfo.kernel_filename = machine->kernel_filename; sms->bootinfo.nb_cpus = smp_cpus; sms->bootinfo.board_id =-1 ; sms->bootinfo.loader_start = sbsa_ref_memmap[SBSA_MEM ].base; sms->bootinfo.get_dtb = sbsa_ref_dtb; sms->bootinfo.firmware_loaded = firmware_loaded; -arm_load_kernel (ARM_CPU (first_cpu), &sms->bootinfo); +arm_load_kernel (ARM_CPU (first_cpu), machine, &sms->bootinfo); }static uint64_t sbsa_ref_cpu_mp_affinity (SBSAMachineState *sms,int idx)
hw/arm/spitz.c +1 -4
@@ -951,11 +951,8 @@ static void spitz_common_init(MachineState *machine,/* A 4.0 GB microdrive is permanently sitting in CF slot 0. */ spitz_microdrive_attach (mpu,0 ); - spitz_binfo.kernel_filename = machine->kernel_filename; - spitz_binfo.kernel_cmdline = machine->kernel_cmdline; - spitz_binfo.initrd_filename = machine->initrd_filename; spitz_binfo.board_id = arm_id; -arm_load_kernel (mpu->cpu, &spitz_binfo); +arm_load_kernel (mpu->cpu, machine, &spitz_binfo);sl_bootparam_write (SL_PXA_PARAM_BASE ); }
hw/arm/tosa.c +1 -7
@@ -218,9 +218,6 @@ static struct arm_boot_info tosa_binfo = {static void tosa_init (MachineState *machine) { -const char *kernel_filename = machine->kernel_filename; -const char *kernel_cmdline = machine->kernel_cmdline; -const char *initrd_filename = machine->initrd_filename;MemoryRegion *address_space_mem =get_system_memory ();MemoryRegion *rom =g_new (MemoryRegion,1 );PXA2xxState *mpu;
@@ -245,11 +242,8 @@ static void tosa_init(MachineState *machine)tosa_tg_init (mpu); - tosa_binfo.kernel_filename = kernel_filename; - tosa_binfo.kernel_cmdline = kernel_cmdline; - tosa_binfo.initrd_filename = initrd_filename; tosa_binfo.board_id =0x208 ; -arm_load_kernel (mpu->cpu, &tosa_binfo); +arm_load_kernel (mpu->cpu, machine, &tosa_binfo);sl_bootparam_write (SL_PXA_PARAM_BASE ); }
hw/arm/versatilepb.c +1 -4
@@ -373,11 +373,8 @@ static void versatile_init(MachineState *machine, int board_id) } versatile_binfo.ram_size = machine->ram_size; - versatile_binfo.kernel_filename = machine->kernel_filename; - versatile_binfo.kernel_cmdline = machine->kernel_cmdline; - versatile_binfo.initrd_filename = machine->initrd_filename; versatile_binfo.board_id = board_id; -arm_load_kernel (cpu, &versatile_binfo); +arm_load_kernel (cpu, machine, &versatile_binfo); }static void vpb_init (MachineState *machine)
hw/arm/vexpress.c +1 -4
@@ -703,9 +703,6 @@ static void vexpress_common_init(MachineState *machine) } daughterboard->bootinfo.ram_size = machine->ram_size; - daughterboard->bootinfo.kernel_filename = machine->kernel_filename; - daughterboard->bootinfo.kernel_cmdline = machine->kernel_cmdline; - daughterboard->bootinfo.initrd_filename = machine->initrd_filename; daughterboard->bootinfo.nb_cpus = smp_cpus; daughterboard->bootinfo.board_id =VEXPRESS_BOARD_ID ; daughterboard->bootinfo.loader_start = daughterboard->loader_start;
@@ -715,7 +712,7 @@ static void vexpress_common_init(MachineState *machine) daughterboard->bootinfo.modify_dtb = vexpress_modify_dtb;/* When booting Linux we should be in secure state if the CPU has one. */ daughterboard->bootinfo.secure_boot = vms->secure; -arm_load_kernel (ARM_CPU (first_cpu), &daughterboard->bootinfo); +arm_load_kernel (ARM_CPU (first_cpu), machine, &daughterboard->bootinfo); }static bool vexpress_get_secure (Object *obj,Error **errp)
hw/arm/virt.c +3 -5
@@ -1361,6 +1361,7 @@ void virt_machine_done(Notifier *notifier, void *data) {VirtMachineState *vms =container_of (notifier, VirtMachineState, machine_done); +MachineState *ms =MACHINE (vms);ARMCPU *cpu =ARM_CPU (first_cpu);struct arm_boot_info *info = &vms->bootinfo;AddressSpace *as =arm_boot_address_space (cpu, info);
@@ -1378,7 +1379,7 @@ void virt_machine_done(Notifier *notifier, void *data) vms->memmap[VIRT_PLATFORM_BUS ].size, vms->irqmap[VIRT_PLATFORM_BUS]); } -if (arm_load_dtb (info->dtb_start, info, info->dtb_limit, as) <0 ) { +if (arm_load_dtb (info->dtb_start, info, info->dtb_limit, as, ms) <0 ) {exit (1 ); }
@@ -1702,16 +1703,13 @@ static void machvirt_init(MachineState *machine)create_platform_bus (vms, pic); vms->bootinfo.ram_size = machine->ram_size; - vms->bootinfo.kernel_filename = machine->kernel_filename; - vms->bootinfo.kernel_cmdline = machine->kernel_cmdline; - vms->bootinfo.initrd_filename = machine->initrd_filename; vms->bootinfo.nb_cpus = smp_cpus; vms->bootinfo.board_id =-1 ; vms->bootinfo.loader_start = vms->memmap[VIRT_MEM ].base; vms->bootinfo.get_dtb = machvirt_dtb; vms->bootinfo.skip_dtb_autoload = true; vms->bootinfo.firmware_loaded = firmware_loaded; -arm_load_kernel (ARM_CPU (first_cpu), &vms->bootinfo); +arm_load_kernel (ARM_CPU (first_cpu), machine, &vms->bootinfo); vms->machine_done.notify = virt_machine_done;qemu_add_machine_init_done_notifier (&vms->machine_done);
hw/arm/xilinx_zynq.c +1 -7
@@ -158,9 +158,6 @@ static inline void zynq_init_spi_flashes(uint32_t base_addr, qemu_irq irq,static void zynq_init (MachineState *machine) {ram_addr_t ram_size = machine->ram_size; -const char *kernel_filename = machine->kernel_filename; -const char *kernel_cmdline = machine->kernel_cmdline; -const char *initrd_filename = machine->initrd_filename;ARMCPU *cpu;MemoryRegion *address_space_mem =get_system_memory ();MemoryRegion *ext_ram =g_new (MemoryRegion,1 );
@@ -303,16 +300,13 @@ static void zynq_init(MachineState *machine)sysbus_mmio_map (busdev,0 ,0xF8007000 ); zynq_binfo.ram_size = ram_size; - zynq_binfo.kernel_filename = kernel_filename; - zynq_binfo.kernel_cmdline = kernel_cmdline; - zynq_binfo.initrd_filename = initrd_filename; zynq_binfo.nb_cpus =1 ; zynq_binfo.board_id =0xd32 ; zynq_binfo.loader_start =0 ; zynq_binfo.board_setup_addr =BOARD_SETUP_ADDR ; zynq_binfo.write_board_setup = zynq_write_board_setup; -arm_load_kernel (ARM_CPU (first_cpu), &zynq_binfo); +arm_load_kernel (ARM_CPU (first_cpu), machine, &zynq_binfo); }static void zynq_machine_init (MachineClass *mc)
hw/arm/xlnx-versal-virt.c +2 -5
@@ -441,14 +441,11 @@ static void versal_virt_init(MachineState *machine) 0, &s->soc.fpd.apu.mr, 0); s->binfo.ram_size = machine->ram_size; - s->binfo.kernel_filename = machine->kernel_filename; - s->binfo.kernel_cmdline = machine->kernel_cmdline; - s->binfo.initrd_filename = machine->initrd_filename; s->binfo.loader_start =0x0 ; s->binfo.get_dtb = versal_virt_get_dtb; s->binfo.modify_dtb = versal_virt_modify_dtb;if (machine->kernel_filename) { -arm_load_kernel (s->soc.fpd.apu.cpu[0 ], &s->binfo); +arm_load_kernel (s->soc.fpd.apu.cpu[0 ], machine, &s->binfo); }else {AddressSpace *as =arm_boot_address_space (s->soc.fpd.apu.cpu[0 ], &s->binfo);
@@ -457,7 +454,7 @@ static void versal_virt_init(MachineState *machine) s->binfo.loader_start =0x1000 ; s->binfo.dtb_limit =0x1000000 ;if (arm_load_dtb (s->binfo.loader_start, - &s->binfo, s->binfo.dtb_limit, as) <0 ) { + &s->binfo, s->binfo.dtb_limit, as, machine) <0 ) {exit (EXIT_FAILURE ); } }
hw/arm/xlnx-zcu102.c +1 -4
@@ -171,11 +171,8 @@ static void xlnx_zcu102_init(MachineState *machine)/* TODO create and connect IDE devices for ide_drive_get() */ xlnx_zcu102_binfo.ram_size = ram_size; - xlnx_zcu102_binfo.kernel_filename = machine->kernel_filename; - xlnx_zcu102_binfo.kernel_cmdline = machine->kernel_cmdline; - xlnx_zcu102_binfo.initrd_filename = machine->initrd_filename; xlnx_zcu102_binfo.loader_start =0 ; -arm_load_kernel (s->soc.boot_cpu_ptr, &xlnx_zcu102_binfo); +arm_load_kernel (s->soc.boot_cpu_ptr, machine, &xlnx_zcu102_binfo); }static void xlnx_zcu102_machine_instance_init (Object *obj)
hw/arm/z2.c +1 -7
@@ -296,9 +296,6 @@ static const TypeInfo aer915_info = {static void z2_init (MachineState *machine) { -const char *kernel_filename = machine->kernel_filename; -const char *kernel_cmdline = machine->kernel_cmdline; -const char *initrd_filename = machine->initrd_filename;MemoryRegion *address_space_mem =get_system_memory ();uint32_t sector_len =0x10000 ;PXA2xxState *mpu;
@@ -352,11 +349,8 @@ static void z2_init(MachineState *machine)qdev_connect_gpio_out (mpu->gpio,Z2_GPIO_LCD_CS ,qemu_allocate_irq (z2_lcd_cs, z2_lcd,0 )); - z2_binfo.kernel_filename = kernel_filename; - z2_binfo.kernel_cmdline = kernel_cmdline; - z2_binfo.initrd_filename = initrd_filename; z2_binfo.board_id =0x6dd ; -arm_load_kernel (mpu->cpu, &z2_binfo); +arm_load_kernel (mpu->cpu, machine, &z2_binfo); }static void z2_machine_init (MachineClass *mc)
include/hw/arm/boot.h +2 -2
@@ -133,7 +133,7 @@ struct arm_boot_info {* before sysbus-fdt arm_register_platform_bus_fdt_creator. Indeed the * machine init done notifiers are called in registration reverse order. */ -void arm_load_kernel (ARMCPU *cpu,struct arm_boot_info *info); +void arm_load_kernel (ARMCPU *cpu,MachineState *ms,struct arm_boot_info *info);AddressSpace *arm_boot_address_space (ARMCPU *cpu,const struct arm_boot_info *info);
@@ -160,7 +160,7 @@ AddressSpace *arm_boot_address_space(ARMCPU *cpu,* Note: Must not be called unless have_dtb(binfo) is true. */ int arm_load_dtb (hwaddr addr,const struct arm_boot_info *binfo, -hwaddr addr_limit,AddressSpace *as); +hwaddr addr_limit,AddressSpace *as,MachineState *ms);/* Write a secure board setup routine with a dummy handler for SMCs */ void arm_write_secure_board_setup_dummy_smc(ARMCPU *cpu,
Signature · 1 line
2.20.1
PATCH v6 2/14 numa: move numa global variable nb_numa_nodes into MachineState
In reply to Tao XuAdd struct NumaState in MachineState and move existing numa global nb_numa_nodes(renamed as "num_nodes") into NumaState. And add variable numa_support into MachineClass to decide which submachines support NUMA.
---
Changes in v6:
- Rebase to upstream, move globals in arm/sbsa-ref
- When used once or twice in the function, use ms->numa_state->num_nodes directly
- Correct some mistakes
- Use once monitor_printf in hmp_info_numa
--- exec.c | 5 ++- hw/acpi/aml-build.c | 3 +- hw/arm/boot.c | 4 +- hw/arm/sbsa-ref.c | 4 +- hw/arm/virt-acpi-build.c | 10 +++-- hw/arm/virt.c | 5 ++- hw/core/machine.c | 14 +++++-- hw/i386/acpi-build.c | 2 +- hw/i386/pc.c | 10 +++-- hw/mem/pc-dimm.c | 2 + hw/pci-bridge/pci_expander_bridge.c | 3 +- hw/ppc/spapr.c | 26 +++++++----- include/hw/acpi/aml-build.h | 2 +- include/hw/boards.h | 2 + include/sysemu/numa.h | 11 ++++- monitor/misc.c | 12 ++++-- numa.c | 62 +++++++++++++++++------------ 17 files changed, 116 insertions(+), 61 deletions(-)
exec.c +4 -1
@@ -1736,6 +1736,7 @@ long qemu_minrampagesize(void)long hpsize =LONG_MAX ;long mainrampagesize;Object *memdev_root; +MachineState *ms =MACHINE (qdev_get_machine ()); mainrampagesize =qemu_mempath_getpagesize (mem_path);
@@ -1763,7 +1764,9 @@ long qemu_minrampagesize(void)* so if its page size is smaller we have got to report that size instead. */ if (hpsize > mainrampagesize && - (nb_numa_nodes ==0 || numa_info[0 ].node_memdev ==NULL )) { + (ms->numa_state ==NULL || + ms->numa_state->num_nodes ==0 || + numa_info[0 ].node_memdev ==NULL )) {static bool warned;if (!warned) {error_report ("Huge page support disabled (n/a for main memory)." );
hw/acpi/aml-build.c +2 -1
@@ -1726,10 +1726,11 @@ void build_srat_memory(AcpiSratMemoryAffinity *numamem, uint64_t base,* ACPI spec 5.2.17 System Locality Distance Information Table * (Revision 2.0 or later) */ -void build_slit (GArray *table_data,BIOSLinker *linker) +void build_slit (GArray *table_data,BIOSLinker *linker,MachineState *ms) {int slit_start, i, j; slit_start = table_data->len; +int nb_numa_nodes = ms->numa_state->num_nodes;acpi_data_push (table_data,sizeof (AcpiTableHeader));
hw/arm/boot.c +2 -2
@@ -598,9 +598,9 @@ int arm_load_dtb(hwaddr addr, const struct arm_boot_info *binfo, }g_strfreev (node_path); -if (nb_numa_nodes >0 ) { +if (ms->numa_state !=NULL && ms->numa_state->num_nodes >0 ) { mem_base = binfo->loader_start; -for (i =0 ; i < nb_numa_nodes; i++) { +for (i =0 ; i < ms->numa_state->num_nodes; i++) { mem_len = numa_info[i].node_mem; rc =fdt_add_memory_node (fdt, acells, mem_base, scells, mem_len, i);
hw/arm/sbsa-ref.c +3 -1
@@ -144,6 +144,7 @@ static void create_fdt(SBSAMachineState *sms) {void *fdt =create_device_tree (&sms->fdt_size);const MachineState *ms =MACHINE (sms); +int nb_numa_nodes = ms->numa_state->num_nodes;int cpu;if (!fdt) {
@@ -760,7 +761,7 @@ sbsa_ref_cpu_index_to_props(MachineState *ms, unsigned cpu_index)static int64_t sbsa_ref_get_default_cpu_node_id (const MachineState *ms,int idx) { -return idx % nb_numa_nodes; +return idx % ms->numa_state->num_nodes; }static void sbsa_ref_instance_init (Object *obj)
@@ -787,6 +788,7 @@ static void sbsa_ref_class_init(ObjectClass *oc, void *data) mc->possible_cpu_arch_ids = sbsa_ref_possible_cpu_arch_ids; mc->cpu_index_to_instance_props = sbsa_ref_cpu_index_to_props; mc->get_default_cpu_node_id = sbsa_ref_get_default_cpu_node_id; + mc->numa_supported = true; }static const TypeInfo sbsa_ref_info = {
hw/arm/virt-acpi-build.c +6 -4
@@ -516,7 +516,8 @@ build_srat(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)int i, srat_start;uint64_t mem_base;MachineClass *mc =MACHINE_GET_CLASS (vms); -const CPUArchIdList *cpu_list = mc->possible_cpu_arch_ids (MACHINE (vms)); +MachineState *ms =MACHINE (vms); +const CPUArchIdList *cpu_list = mc->possible_cpu_arch_ids (ms); srat_start = table_data->len; srat =acpi_data_push (table_data,sizeof (*srat));
@@ -532,7 +533,7 @@ build_srat(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) } mem_base = vms->memmap[VIRT_MEM ].base; -for (i =0 ; i < nb_numa_nodes; ++i) { +for (i =0 ; i < ms->numa_state->num_nodes; ++i) {if (numa_info[i].node_mem >0 ) { numamem =acpi_data_push (table_data,sizeof (*numamem)); build_srat_memory(numamem, mem_base, numa_info[i].node_mem, i,
@@ -758,6 +759,7 @@ void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables)GArray *table_offsets;unsigned dsdt, xsdt;GArray *tables_blob = tables->table_data; +MachineState *ms =MACHINE (vms); table_offsets =g_array_new (false, true/* clear */ ,sizeof (uint32_t ));
@@ -792,12 +794,12 @@ void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables)acpi_add_table (table_offsets, tables_blob);build_spcr (tables_blob, tables->linker, vms); -if (nb_numa_nodes >0 ) { +if (ms->numa_state->num_nodes >0 ) {acpi_add_table (table_offsets, tables_blob);build_srat (tables_blob, tables->linker, vms);if (have_numa_distance) {acpi_add_table (table_offsets, tables_blob); -build_slit (tables_blob, tables->linker); +build_slit (tables_blob, tables->linker, ms); } }
hw/arm/virt.c +4 -1
@@ -199,6 +199,8 @@ static bool cpu_type_valid(const char *cpu)static void create_fdt (VirtMachineState *vms) { +MachineState *ms =MACHINE (vms); +int nb_numa_nodes = ms->numa_state->num_nodes;void *fdt =create_device_tree (&vms->fdt_size);if (!fdt) {
@@ -1837,7 +1839,7 @@ virt_cpu_index_to_props(MachineState *ms, unsigned cpu_index)static int64_t virt_get_default_cpu_node_id (const MachineState *ms,int idx) { -return idx % nb_numa_nodes; +return idx % ms->numa_state->num_nodes; }static const CPUArchIdList *virt_possible_cpu_arch_ids (MachineState *ms)
@@ -1943,6 +1945,7 @@ static void virt_machine_class_init(ObjectClass *oc, void *data) mc->kvm_type = virt_kvm_type;assert (!mc->get_hotplug_handler); mc->get_hotplug_handler = virt_machine_get_hotplug_handler; + mc->numa_supported = true; hc->plug = virt_machine_device_plug_cb; }
hw/core/machine.c +10 -4
@@ -880,6 +880,9 @@ static void machine_initfn(Object *obj) NULL); } +if (mc->numa_supported) { + ms->numa_state =g_new0 (NumaState,1 ); + }/* Register notifier when init is done for sysbus sanity checks */ ms->sysbus_notifier.notify = machine_init_notify;
@@ -900,6 +903,7 @@ static void machine_finalize(Object *obj)g_free (ms->firmware);g_free (ms->device_memory);g_free (ms->nvdimms_state); +g_free (ms->numa_state); }bool machine_usb (MachineState *machine)
@@ -971,7 +975,7 @@ static void machine_numa_finish_cpu_init(MachineState *machine)MachineClass *mc =MACHINE_GET_CLASS (machine);const CPUArchIdList *possible_cpus = mc->possible_cpu_arch_ids (machine); -assert (nb_numa_nodes); +assert (machine->numa_state->num_nodes);for (i =0 ; i < possible_cpus->len; i++) {if (possible_cpus->cpus[i].props.has_node_id) {break ;
@@ -1017,9 +1021,11 @@ void machine_run_board_init(MachineState *machine) {MachineClass *machine_class =MACHINE_GET_CLASS (machine); -numa_complete_configuration (machine); -if (nb_numa_nodes) { -machine_numa_finish_cpu_init (machine); +if (machine_class->numa_supported) { +numa_complete_configuration (machine); +if (machine->numa_state->num_nodes) { +machine_numa_finish_cpu_init (machine); + } }/* If the machine supports the valid_cpu_types check and the user
hw/i386/acpi-build.c +1 -1
@@ -2682,7 +2682,7 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine)build_srat (tables_blob, tables->linker, machine);if (have_numa_distance) {acpi_add_table (table_offsets, tables_blob); -build_slit (tables_blob, tables->linker); +build_slit (tables_blob, tables->linker, machine); } }if (acpi_get_mcfg (&mcfg)) {
hw/i386/pc.c +7 -3
@@ -995,6 +995,8 @@ static FWCfgState *bochs_bios_init(AddressSpace *as, PCMachineState *pcms)int i;const CPUArchIdList *cpus;MachineClass *mc =MACHINE_GET_CLASS (pcms); +MachineState *ms =MACHINE (pcms); +int nb_numa_nodes = ms->numa_state->num_nodes; fw_cfg =fw_cfg_init_io_dma (FW_CFG_IO_BASE ,FW_CFG_IO_BASE +4 , as);fw_cfg_add_i16 (fw_cfg,FW_CFG_NB_CPUS , pcms->boot_cpus);
@@ -1671,12 +1673,13 @@ void pc_machine_done(Notifier *notifier, void *data)void pc_guest_info_init (PCMachineState *pcms) {int i; +MachineState *ms =MACHINE (pcms); pcms->apic_xrupt_override =kvm_allows_irq0_override (); - pcms->numa_nodes = nb_numa_nodes; + pcms->numa_nodes = ms->numa_state->num_nodes; pcms->node_mem =g_malloc0 (pcms->numa_nodes *sizeof *pcms->node_mem); -for (i =0 ; i < nb_numa_nodes; i++) { +for (i =0 ; i < ms->numa_state->num_nodes; i++) { pcms->node_mem[i] = numa_info[i].node_mem; }
@@ -2655,7 +2658,7 @@ static int64_t pc_get_default_cpu_node_id(const MachineState *ms, int idx)assert (idx < ms->possible_cpus->len);x86_topo_ids_from_apicid (ms->possible_cpus->cpus[idx].arch_id, smp_cores, smp_threads, &topo); -return topo.pkg_id % nb_numa_nodes; +return topo.pkg_id % ms->numa_state->num_nodes; }static const CPUArchIdList *pc_possible_cpu_arch_ids (MachineState *ms)
@@ -2749,6 +2752,7 @@ static void pc_machine_class_init(ObjectClass *oc, void *data) nc->nmi_monitor_handler = x86_nmi; mc->default_cpu_type =TARGET_DEFAULT_CPU_TYPE ; mc->nvdimm_supported = true; + mc->numa_supported = true; object_class_property_add(oc, PC_MACHINE_DEVMEM_REGION_SIZE, "int", pc_machine_get_device_memory_region_size, NULL,
hw/mem/pc-dimm.c +2 -0
@@ -161,6 +161,8 @@ static void pc_dimm_realize(DeviceState *dev, Error **errp) {PCDIMMDevice *dimm =PC_DIMM (dev);PCDIMMDeviceClass *ddc =PC_DIMM_GET_CLASS (dimm); +MachineState *ms =MACHINE (qdev_get_machine ()); +int nb_numa_nodes = ms->numa_state->num_nodes;if (!dimm->hostmem) {error_setg (errp,"'" PC_DIMM_MEMDEV_PROP "' property is not set" );
hw/pci-bridge/pci_expander_bridge.c +2 -1
@@ -212,9 +212,10 @@ static void pxb_dev_realize_common(PCIDevice *dev, bool pcie, Error **errp)PCIBus *bus;const char *dev_name =NULL ;Error *local_err =NULL ; +MachineState *ms =MACHINE (qdev_get_machine ());if (pxb->numa_node !=NUMA_NODE_UNASSIGNED && - pxb->numa_node >= nb_numa_nodes) { + pxb->numa_node >= ms->numa_state->num_nodes) {error_setg (errp,"Illegal numa node %d" , pxb->numa_node);return ; }
hw/ppc/spapr.c +15 -11
@@ -291,6 +291,7 @@ static int spapr_fixup_cpu_dt(void *fdt, SpaprMachineState *spapr)CPUState *cs;char cpu_model[32 ];uint32_t pft_size_prop[] = {0 ,cpu_to_be32 (spapr->htab_shift)}; +MachineState *ms =MACHINE (spapr);CPU_FOREACH (cs) {PowerPCCPU *cpu =POWERPC_CPU (cs);
@@ -325,7 +326,7 @@ static int spapr_fixup_cpu_dt(void *fdt, SpaprMachineState *spapr)return ret; } -if (nb_numa_nodes >1 ) { +if (ms->numa_state->num_nodes >1 ) { ret =spapr_fixup_cpu_numa_dt (fdt, offset, cpu);if (ret <0 ) {return ret;
@@ -345,9 +346,9 @@ static int spapr_fixup_cpu_dt(void *fdt, SpaprMachineState *spapr)static hwaddr spapr_node0_size (MachineState *machine) { -if (nb_numa_nodes) { +if (machine->numa_state->num_nodes) {int i; -for (i =0 ; i < nb_numa_nodes; ++i) { +for (i =0 ; i < machine->numa_state->num_nodes; ++i) {if (numa_info[i].node_mem) {return MIN (pow2floor (numa_info[i].node_mem), machine->ram_size);
@@ -392,18 +393,18 @@ static int spapr_populate_memory(SpaprMachineState *spapr, void *fdt) {MachineState *machine =MACHINE (spapr);hwaddr mem_start, node_size; -int i, nb_nodes = nb_numa_nodes; +int i;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 ; +if (!machine->numa_state->num_nodes) { + machine->numa_state->num_nodes =1 ; ramnode.node_mem = machine->ram_size; nodes = &ramnode; } -for (i =0 , mem_start =0 ; i < nb_nodes; ++i) { +for (i =0 , mem_start =0 ; i < machine->numa_state->num_nodes; ++i) {if (!nodes[i].node_mem) {continue ; }
@@ -445,6 +446,7 @@ static void spapr_populate_cpu_dt(CPUState *cs, void *fdt, int offset,PowerPCCPU *cpu =POWERPC_CPU (cs);CPUPPCState *env = &cpu->env;PowerPCCPUClass *pcc =POWERPC_CPU_GET_CLASS (cs); +MachineState *ms =MACHINE (spapr);int index =spapr_get_vcpu_id (cpu);uint32_t segs[] = {cpu_to_be32 (28 ),cpu_to_be32 (40 ),0xffffffff ,0xffffffff };
@@ -546,7 +548,7 @@ static void spapr_populate_cpu_dt(CPUState *cs, void *fdt, int offset,_FDT ((fdt_setprop (fdt, offset,"ibm,pft-size" , pft_size_prop,sizeof (pft_size_prop)))); -if (nb_numa_nodes >1 ) { +if (ms->numa_state->num_nodes >1 ) {_FDT (spapr_fixup_cpu_numa_dt (fdt, offset, cpu)); }
@@ -853,6 +855,7 @@ static int spapr_populate_drmem_v1(SpaprMachineState *spapr, void *fdt,static int spapr_populate_drconf_memory (SpaprMachineState *spapr,void *fdt) {MachineState *machine =MACHINE (spapr); +int nb_numa_nodes = machine->numa_state->num_nodes;int ret, i, offset;uint64_t lmb_size =SPAPR_MEMORY_BLOCK_SIZE ;uint32_t prop_lmb_size[] = {0 ,cpu_to_be32 (lmb_size)};
@@ -1742,7 +1745,7 @@ static void spapr_machine_reset(void)* The final value of spapr->gpu_numa_id is going to be written to * max-associativity-domains in spapr_build_fdt(). */ - spapr->gpu_numa_id =MAX (1 , nb_numa_nodes); + spapr->gpu_numa_id =MAX (1 , machine->numa_state->num_nodes);qemu_devices_reset ();/*
@@ -2529,7 +2532,7 @@ static void spapr_validate_node_memory(MachineState *machine, Error **errp)return ; } -for (i =0 ; i < nb_numa_nodes; i++) { +for (i =0 ; i < machine->numa_state->num_nodes; i++) {if (numa_info[i].node_mem %SPAPR_MEMORY_BLOCK_SIZE ) {error_setg (errp, "Node %d memory size 0x%" PRIx64
@@ -4125,7 +4128,7 @@ spapr_cpu_index_to_props(MachineState *machine, unsigned cpu_index)static int64_t spapr_get_default_cpu_node_id (const MachineState *ms,int idx) { -return idx / smp_cores % nb_numa_nodes; +return idx / smp_cores % ms->numa_state->num_nodes; }static const CPUArchIdList *spapr_possible_cpu_arch_ids (MachineState *machine)
@@ -4329,6 +4332,7 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data) smc->update_dt_enabled = true; mc->default_cpu_type =POWERPC_CPU_TYPE_NAME ("power9_v2.0" ); mc->has_hotpluggable_cpus = true; + mc->numa_supported = true; smc->resize_hpt_default =SPAPR_RESIZE_HPT_ENABLED ; fwc->get_dev_path = spapr_get_fw_dev_path; nc->nmi_monitor_handler = spapr_nmi;
include/hw/acpi/aml-build.h +1 -1
@@ -414,7 +414,7 @@ build_append_gas_from_struct(GArray *table, const struct AcpiGenericAddress *s)void build_srat_memory (AcpiSratMemoryAffinity *numamem,uint64_t base,uint64_t len,int node,MemoryAffinityFlags flags); -void build_slit (GArray *table_data,BIOSLinker *linker); +void build_slit (GArray *table_data,BIOSLinker *linker,MachineState *ms);void build_fadt (GArray *tbl,BIOSLinker *linker,const AcpiFadtData *f,const char *oem_id,const char *oem_table_id);
include/hw/boards.h +2 -0
@@ -211,6 +211,7 @@ struct MachineClass {bool ignore_boot_device_suffixes;bool smbus_no_migration_support;bool nvdimm_supported; +bool numa_supported; HotplugHandler *(*get_hotplug_handler)(MachineState *machine, DeviceState *dev);
@@ -274,6 +275,7 @@ struct MachineState {AccelState *accelerator;CPUArchIdList *possible_cpus;struct NVDIMMState *nvdimms_state; +struct NumaState *numa_state; };#define DEFINE_MACHINE (namestr, machine_initfn) \
include/sysemu/numa.h +9 -2
@@ -6,7 +6,6 @@#include "sysemu/hostmem.h" #include "hw/boards.h" -extern int nb_numa_nodes;/* Number of NUMA nodes */ extern bool have_numa_distance;struct NodeInfo {
@@ -22,9 +21,17 @@ struct NumaNodeMem { };extern NodeInfo numa_info[MAX_NODES ]; + +struct NumaState { +/* Number of NUMA nodes */ +int num_nodes; + +}; +typedef struct NumaState NumaState ; +void parse_numa_opts (MachineState *ms);void numa_complete_configuration (MachineState *ms); -void query_numa_node_mem (NumaNodeMem node_mem[]); +void query_numa_node_mem (NumaNodeMem node_mem[],MachineState *ms);extern QemuOptsList qemu_numa_opts;void numa_legacy_auto_assign_ram (MachineClass *mc,NodeInfo *nodes,int nb_nodes,ram_addr_t size);
monitor/misc.c +9 -3
@@ -1083,15 +1083,21 @@ static void hmp_info_mtree(Monitor *mon, const QDict *qdict)static void hmp_info_numa (Monitor *mon,const QDict *qdict) { -int i; +int i, nb_numa_nodes;NumaNodeMem *node_mem;CpuInfoList *cpu_list, *cpu; +MachineState *ms =MACHINE (qdev_get_machine ()); + + nb_numa_nodes = ms->numa_state ? ms->numa_state->num_nodes :0 ; +monitor_printf (mon,"%d nodes\n" , nb_numa_nodes); +if (!nb_numa_nodes) { +return ; + } cpu_list =qmp_query_cpus (&error_abort); node_mem =g_new0 (NumaNodeMem, nb_numa_nodes); -query_numa_node_mem (node_mem); -monitor_printf (mon,"%d nodes\n" , nb_numa_nodes); +query_numa_node_mem (node_mem, ms);for (i =0 ; i < nb_numa_nodes; i++) {monitor_printf (mon,"node %d cpus:" , i);for (cpu = cpu_list; cpu; cpu = cpu->next) {
numa.c +37 -25
176 lines not on this page · raw message
Signature · 1 line
2.20.1
PATCH v6 3/14 numa: move numa global variable have_numa_distance into MachineState
In reply to Tao XuMove existing numa global have_numa_distance into NumaState.
---
Changes in v6:
- rebase to upstream, move globals in arm/sbsa-ref
--- hw/arm/sbsa-ref.c | 2 +- hw/arm/virt-acpi-build.c | 2 +- hw/arm/virt.c | 2 +- hw/i386/acpi-build.c | 2 +- include/sysemu/numa.h | 4 ++-- numa.c | 5 ++--- 6 files changed, 8 insertions(+), 9 deletions(-)
hw/arm/sbsa-ref.c +1 -1
@@ -158,7 +158,7 @@ static void create_fdt(SBSAMachineState *sms)qemu_fdt_setprop_cell (fdt,"/" ,"#address-cells" ,0x2 );qemu_fdt_setprop_cell (fdt,"/" ,"#size-cells" ,0x2 ); -if (have_numa_distance) { +if (ms->numa_state->have_numa_distance) {int size = nb_numa_nodes * nb_numa_nodes *3 *sizeof (uint32_t );uint32_t *matrix =g_malloc0 (size);int idx, i, j;
hw/arm/virt-acpi-build.c +1 -1
@@ -797,7 +797,7 @@ void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables)if (ms->numa_state->num_nodes >0 ) {acpi_add_table (table_offsets, tables_blob);build_srat (tables_blob, tables->linker, vms); -if (have_numa_distance) { +if (ms->numa_state->have_numa_distance) {acpi_add_table (table_offsets, tables_blob);build_slit (tables_blob, tables->linker, ms); }
hw/arm/virt.c +1 -1
@@ -232,7 +232,7 @@ static void create_fdt(VirtMachineState *vms) "clk24mhz");qemu_fdt_setprop_cell (fdt,"/apb-pclk" ,"phandle" , vms->clock_phandle); -if (have_numa_distance) { +if (nb_numa_nodes >0 && ms->numa_state->have_numa_distance) {int size = nb_numa_nodes * nb_numa_nodes *3 *sizeof (uint32_t );uint32_t *matrix =g_malloc0 (size);int idx, i, j;
hw/i386/acpi-build.c +1 -1
@@ -2680,7 +2680,7 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine)if (pcms->numa_nodes) {acpi_add_table (table_offsets, tables_blob);build_srat (tables_blob, tables->linker, machine); -if (have_numa_distance) { +if (machine->numa_state->have_numa_distance) {acpi_add_table (table_offsets, tables_blob);build_slit (tables_blob, tables->linker, machine); }
include/sysemu/numa.h +2 -2
@@ -6,8 +6,6 @@#include "sysemu/hostmem.h" #include "hw/boards.h" -extern bool have_numa_distance; -struct NodeInfo {uint64_t node_mem;struct HostMemoryBackend *node_memdev;
@@ -26,6 +24,8 @@ struct NumaState {/* Number of NUMA nodes */ int num_nodes; +/* Allow setting NUMA distance for different NUMA nodes */ +bool have_numa_distance; };typedef struct NumaState NumaState ;
numa.c +2 -3
@@ -52,7 +52,6 @@ static int have_memdevs = -1;static int max_numa_nodeid;/* Highest specified NUMA node ID, plus one. * For all nodes, nodeid < max_numa_nodeid */ -bool have_numa_distance;NodeInfo numa_info[MAX_NODES ];
@@ -171,7 +170,7 @@ void parse_numa_distance(MachineState *ms, NumaDistOptions *dist, Error **errp) } numa_info[src].distance[dst] = val; - have_numa_distance = true; + ms->numa_state->have_numa_distance = true; } static
@@ -442,7 +441,7 @@ void numa_complete_configuration(MachineState *ms)* asymmetric. In this case, the distances for both directions * of all node pairs are required. */ -if (have_numa_distance) { +if (ms->numa_state->have_numa_distance) {/* Validate enough NUMA distance information was provided. */ validate_numa_distance (ms);
Signature · 1 line
2.20.1
PATCH v6 4/14 numa: move numa global variable numa_info into MachineState
In reply to Tao XuMove existing numa global numa_info (renamed as "nodes") into NumaState.
---
Changes in v6:
- Rebase to upstream, move globals in arm/sbsa-ref
- Correct some mistake(Igor)
- Use ms->numa_state->nodes directly, when use it once or twice(Igor)
--- exec.c | 2 +- hw/acpi/aml-build.c | 6 ++++-- hw/arm/boot.c | 2 +- hw/arm/sbsa-ref.c | 3 ++- hw/arm/virt-acpi-build.c | 7 ++++--- hw/arm/virt.c | 3 ++- hw/i386/pc.c | 4 ++-- hw/ppc/spapr.c | 10 +++++----- hw/ppc/spapr_pci.c | 4 +++- include/sysemu/numa.h | 3 +++ numa.c | 15 +++++++++------ 11 files changed, 36 insertions(+), 23 deletions(-)
exec.c +1 -1
@@ -1766,7 +1766,7 @@ long qemu_minrampagesize(void)if (hpsize > mainrampagesize && (ms->numa_state ==NULL || ms->numa_state->num_nodes ==0 || - numa_info[0 ].node_memdev ==NULL )) { + ms->numa_state->nodes[0 ].node_memdev ==NULL )) {static bool warned;if (!warned) {error_report ("Huge page support disabled (n/a for main memory)." );
hw/acpi/aml-build.c +4 -2
@@ -1737,8 +1737,10 @@ void build_slit(GArray *table_data, BIOSLinker *linker, MachineState *ms)build_append_int_noprefix (table_data, nb_numa_nodes,8 );for (i =0 ; i < nb_numa_nodes; i++) {for (j =0 ; j < nb_numa_nodes; j++) { -assert (numa_info[i].distance[j]); -build_append_int_noprefix (table_data, numa_info[i].distance[j],1 ); +assert (ms->numa_state->nodes[i].distance[j]); +build_append_int_noprefix (table_data, + ms->numa_state->nodes[i].distance[j], +1 ); } }
hw/arm/boot.c +1 -1
@@ -601,7 +601,7 @@ int arm_load_dtb(hwaddr addr, const struct arm_boot_info *binfo,if (ms->numa_state !=NULL && ms->numa_state->num_nodes >0 ) { mem_base = binfo->loader_start;for (i =0 ; i < ms->numa_state->num_nodes; i++) { - mem_len = numa_info[i].node_mem; + mem_len = ms->numa_state->nodes[i].node_mem; rc =fdt_add_memory_node (fdt, acells, mem_base, scells, mem_len, i);if (rc <0 ) {
hw/arm/sbsa-ref.c +2 -1
@@ -168,7 +168,8 @@ static void create_fdt(SBSAMachineState *sms) idx = (i * nb_numa_nodes + j) *3 ; matrix[idx +0 ] =cpu_to_be32 (i); matrix[idx +1 ] =cpu_to_be32 (j); - matrix[idx +2 ] =cpu_to_be32 (numa_info[i].distance[j]); + matrix[idx +2 ] = +cpu_to_be32 (ms->numa_state->nodes[i].distance[j]); } }
hw/arm/virt-acpi-build.c +4 -3
@@ -534,11 +534,12 @@ build_srat(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) mem_base = vms->memmap[VIRT_MEM ].base;for (i =0 ; i < ms->numa_state->num_nodes; ++i) { -if (numa_info[i].node_mem >0 ) { +if (ms->numa_state->nodes[i].node_mem >0 ) { numamem =acpi_data_push (table_data,sizeof (*numamem)); -build_srat_memory (numamem, mem_base, numa_info[i].node_mem, i, +build_srat_memory (numamem, mem_base, + ms->numa_state->nodes[i].node_mem, i,MEM_AFFINITY_ENABLED ); - mem_base += numa_info[i].node_mem; + mem_base += ms->numa_state->nodes[i].node_mem; } }
hw/arm/virt.c +2 -1
@@ -242,7 +242,8 @@ static void create_fdt(VirtMachineState *vms) idx = (i * nb_numa_nodes + j) *3 ; matrix[idx +0 ] =cpu_to_be32 (i); matrix[idx +1 ] =cpu_to_be32 (j); - matrix[idx +2 ] =cpu_to_be32 (numa_info[i].distance[j]); + matrix[idx +2 ] = +cpu_to_be32 (ms->numa_state->nodes[i].distance[j]); } }
hw/i386/pc.c +2 -2
@@ -1039,7 +1039,7 @@ static FWCfgState *bochs_bios_init(AddressSpace *as, PCMachineState *pcms) }for (i =0 ; i < nb_numa_nodes; i++) { numa_fw_cfg[pcms->apic_id_limit +1 + i] = -cpu_to_le64 (numa_info[i].node_mem); +cpu_to_le64 (ms->numa_state->nodes[i].node_mem); } fw_cfg_add_bytes(fw_cfg, FW_CFG_NUMA, numa_fw_cfg, (1 + pcms->apic_id_limit + nb_numa_nodes) *
@@ -1680,7 +1680,7 @@ void pc_guest_info_init(PCMachineState *pcms) pcms->node_mem =g_malloc0 (pcms->numa_nodes *sizeof *pcms->node_mem);for (i =0 ; i < ms->numa_state->num_nodes; i++) { - pcms->node_mem[i] = numa_info[i].node_mem; + pcms->node_mem[i] = ms->numa_state->nodes[i].node_mem; } pcms->machine_done.notify = pc_machine_done;
hw/ppc/spapr.c +5 -5
@@ -349,8 +349,8 @@ static hwaddr spapr_node0_size(MachineState *machine)if (machine->numa_state->num_nodes) {int i;for (i =0 ; i < machine->numa_state->num_nodes; ++i) { -if (numa_info[i].node_mem) { -return MIN (pow2floor (numa_info[i].node_mem), +if (machine->numa_state->nodes[i].node_mem) { +return MIN (pow2floor (machine->numa_state->nodes[i].node_mem), machine->ram_size); } }
@@ -394,7 +394,7 @@ static int spapr_populate_memory(SpaprMachineState *spapr, void *fdt)MachineState *machine =MACHINE (spapr);hwaddr mem_start, node_size;int i; -NodeInfo *nodes = numa_info; +NodeInfo *nodes = machine->numa_state->nodes;NodeInfo ramnode;/* No NUMA nodes, assume there is just one node with whole RAM */
@@ -2533,11 +2533,11 @@ static void spapr_validate_node_memory(MachineState *machine, Error **errp) }for (i =0 ; i < machine->numa_state->num_nodes; i++) { -if (numa_info[i].node_mem %SPAPR_MEMORY_BLOCK_SIZE ) { +if (machine->numa_state->nodes[i].node_mem %SPAPR_MEMORY_BLOCK_SIZE ) {error_setg (errp,"Node %d memory size 0x%" PRIx64" is not aligned to %" PRIu64" MiB" , - i, numa_info[i].node_mem, + i, machine->numa_state->nodes[i].node_mem,SPAPR_MEMORY_BLOCK_SIZE / MiB);return ; }
hw/ppc/spapr_pci.c +3 -1
@@ -1818,6 +1818,7 @@ static void spapr_phb_realize(DeviceState *dev, Error **errp)SysBusDevice *s =SYS_BUS_DEVICE (dev);SpaprPhbState *sphb =SPAPR_PCI_HOST_BRIDGE (s);PCIHostState *phb =PCI_HOST_BRIDGE (s); +MachineState *ms =MACHINE (spapr);char *namebuf;int i;PCIBus *bus;
@@ -1870,7 +1871,8 @@ static void spapr_phb_realize(DeviceState *dev, Error **errp) }if (sphb->numa_node !=-1 && - (sphb->numa_node >=MAX_NODES || !numa_info[sphb->numa_node].present)) { + (sphb->numa_node >=MAX_NODES || + !ms->numa_state->nodes[sphb->numa_node].present)) {error_setg (errp,"Invalid NUMA node ID for PCI host bridge" );return ; }
include/sysemu/numa.h +3 -0
@@ -26,6 +26,9 @@ struct NumaState {/* Allow setting NUMA distance for different NUMA nodes */ bool have_numa_distance; + +/* NUMA nodes information */ +NodeInfo nodes[MAX_NODES ]; };typedef struct NumaState NumaState ;
numa.c +9 -6
@@ -52,8 +52,6 @@ static int have_memdevs = -1;static int max_numa_nodeid;/* Highest specified NUMA node ID, plus one. * For all nodes, nodeid < max_numa_nodeid */ -NodeInfo numa_info[MAX_NODES ]; -static void parse_numa_node (MachineState *ms,NumaNodeOptions *node,Error **errp)
@@ -62,6 +60,7 @@ static void parse_numa_node(MachineState *ms, NumaNodeOptions *node,uint16_t nodenr;uint16List *cpus =NULL ;MachineClass *mc =MACHINE_GET_CLASS (ms); +NodeInfo *numa_info = ms->numa_state->nodes;if (node->has_nodeid) { nodenr = node->nodeid;
@@ -143,6 +142,7 @@ void parse_numa_distance(MachineState *ms, NumaDistOptions *dist, Error **errp)uint16_t src = dist->src;uint16_t dst = dist->dst;uint8_t val = dist->val; +NodeInfo *numa_info = ms->numa_state->nodes;if (src >=MAX_NODES || dst >=MAX_NODES ) { error_setg(errp, "Parameter '%s' expects an integer between 0 and %d",
@@ -202,7 +202,7 @@ void set_numa_options(MachineState *ms, NumaOptions *object, Error **errp)error_setg (&err,"Missing mandatory node-id property" ); goto end; } -if (!numa_info[object->u.cpu.node_id].present) { +if (!ms->numa_state->nodes[object->u.cpu.node_id].present) {error_setg (&err,"Invalid node-id=%" PRId64", NUMA node must be " "defined with -numa node,nodeid=ID before it's used with " "-numa cpu,node-id=ID" , object->u.cpu.node_id);
@@ -262,6 +262,7 @@ static void validate_numa_distance(MachineState *ms)int src, dst;bool is_asymmetrical = false;int nb_numa_nodes = ms->numa_state->num_nodes; +NodeInfo *numa_info = ms->numa_state->nodes;for (src =0 ; src < nb_numa_nodes; src++) {for (dst = src; dst < nb_numa_nodes; dst++) {
@@ -302,6 +303,7 @@ static void validate_numa_distance(MachineState *ms)static void complete_init_numa_distance (MachineState *ms) {int src, dst; +NodeInfo *numa_info = ms->numa_state->nodes;/* Fixup NUMA distance by symmetric policy because if it is an * asymmetric distance table, it should be a complete table and
@@ -361,6 +363,7 @@ void numa_complete_configuration(MachineState *ms) {int i;MachineClass *mc =MACHINE_GET_CLASS (ms); +NodeInfo *numa_info = ms->numa_state->nodes;/* * If memory hotplug is enabled (slots > 0) but without '-numa'
@@ -532,8 +535,8 @@ void memory_region_allocate_system_memory(MemoryRegion *mr, Object *owner,memory_region_init (mr, owner, name, ram_size);for (i =0 ; i < ms->numa_state->num_nodes; i++) { -uint64_t size = numa_info[i].node_mem; -HostMemoryBackend *backend = numa_info[i].node_memdev; +uint64_t size = ms->numa_state->nodes[i].node_mem; +HostMemoryBackend *backend = ms->numa_state->nodes[i].node_memdev;if (!backend) {continue ; }
@@ -599,7 +602,7 @@ void query_numa_node_mem(NumaNodeMem node_mem[], MachineState *ms)numa_stat_memory_devices (node_mem);for (i =0 ; i < ms->numa_state->num_nodes; i++) { - node_mem[i].node_mem += numa_info[i].node_mem; + node_mem[i].node_mem += ms->numa_state->nodes[i].node_mem; } }
Signature · 1 line
2.20.1
PATCH v6 5/14 numa: Extend CLI to provide initiator information for numa nodes
In reply to Tao XuIn ACPI 6.3 chapter 5.2.27 Heterogeneous Memory Attribute Table (HMAT), The initiator represents processor which access to memory. And in 5.2.27.3 Memory Proximity Domain Attributes Structure, the attached initiator is defined as where the memory controller responsible for a memory proximity domain. With attached initiator information, the topology of heterogeneous memory can be described.
Extend CLI of "-numa node" option to indicate the initiator numa node-id.
--- hw/core/machine.c | 24 ++++++++++++++++++++++++ include/sysemu/numa.h | 3 +++ numa.c | 13 +++++++++++++ qapi/misc.json | 6 +++++- qemu-options.hx | 27 +++++++++++++++++++++++---- 5 files changed, 68 insertions(+), 5 deletions(-)
hw/core/machine.c +24 -0
@@ -649,6 +649,7 @@ void machine_set_cpu_numa_node(MachineState *machine, const CpuInstanceProperties *props, Error **errp) { MachineClass *mc = MACHINE_GET_CLASS(machine); +NodeInfo *numa_info = machine->numa_state->nodes;bool match = false;int i;
@@ -709,6 +710,16 @@ void machine_set_cpu_numa_node(MachineState *machine, match = true; slot->props.node_id = props->node_id; slot->props.has_node_id = props->has_node_id; + +if (numa_info[props->node_id].initiator_valid && + (props->node_id != numa_info[props->node_id].initiator)) { +error_setg (errp,"The initiator of CPU NUMA node %" PRId64 +" should be itself." , props->node_id); +return ; + } + numa_info[props->node_id].initiator_valid = true; + numa_info[props->node_id].has_cpu = true; + numa_info[props->node_id].initiator = props->node_id; }if (!match) {
@@ -974,6 +985,7 @@ static void machine_numa_finish_cpu_init(MachineState *machine)GString *s =g_string_new (NULL );MachineClass *mc =MACHINE_GET_CLASS (machine);const CPUArchIdList *possible_cpus = mc->possible_cpu_arch_ids (machine); +NodeInfo *numa_info = machine->numa_state->nodes;assert (machine->numa_state->num_nodes);for (i =0 ; i < possible_cpus->len; i++) {
@@ -1007,6 +1019,18 @@ static void machine_numa_finish_cpu_init(MachineState *machine)machine_set_cpu_numa_node (machine, &props, &error_fatal); } } + +for (i =0 ; i < machine->numa_state->num_nodes; i++) { +if (numa_info[i].initiator_valid && + !numa_info[numa_info[i].initiator].has_cpu) { +error_report ("The initiator-id %" PRIu16" of NUMA node %d" +" does not exist." , numa_info[i].initiator, i); +error_printf ("\n" ); + +exit (1 ); + } + } +if (s->len && !qtest_enabled ()) {warn_report ("CPU(s) not present in any NUMA nodes: %s" , s->str);
include/sysemu/numa.h +3 -0
@@ -10,6 +10,9 @@ struct NodeInfo {uint64_t node_mem;struct HostMemoryBackend *node_memdev;bool present; +bool has_cpu; +bool initiator_valid; +uint16_t initiator;uint8_t distance[MAX_NODES ]; };
numa.c +13 -0
@@ -131,6 +131,19 @@ static void parse_numa_node(MachineState *ms, NumaNodeOptions *node, numa_info[nodenr].node_mem =object_property_get_uint (o,"size" ,NULL ); numa_info[nodenr].node_memdev =MEMORY_BACKEND (o); } + +if (node->has_initiator) { +if (numa_info[nodenr].initiator_valid && + (node->initiator != numa_info[nodenr].initiator)) { +error_setg (errp,"The initiator of NUMA node %" PRIu16" has been " +"set to node %" PRIu16, nodenr, + numa_info[nodenr].initiator); +return ; + } + + numa_info[nodenr].initiator_valid = true; + numa_info[nodenr].initiator = node->initiator; + } numa_info[nodenr].present = true; max_numa_nodeid =MAX (max_numa_nodeid, nodenr +1 ); ms->numa_state->num_nodes++;
qapi/misc.json +5 -1
@@ -2572,6 +2572,9 @@ # @memdev: memory backend object. If specified for one node, # it must be specified for all nodes. # +# @initiator: the initiator numa nodeid that is closest (as in directly +# attached) to this numa node. +# # Since: 2.1 ## { 'struct': 'NumaNodeOptions',
@@ -2579,7 +2582,8 @@ '*nodeid': 'uint16', '*cpus': ['uint16'], '*mem': 'size', - '*memdev': 'str' }} + '*memdev': 'str', + '*initiator': 'uint16' }} ## # @NumaDistOptions:
qemu-options.hx +23 -4
@@ -160,14 +160,14 @@ specifies the maximum number of hotpluggable CPUs. ETEXI DEF("numa", HAS_ARG, QEMU_OPTION_numa, - "-numa node[,mem=size][,cpus=firstcpu[-lastcpu]][,nodeid=node]\n" - "-numa node[,memdev=id][,cpus=firstcpu[-lastcpu]][,nodeid=node]\n" + "-numa node[,mem=size][,cpus=firstcpu[-lastcpu]][,nodeid=node][,initiator=node]\n" + "-numa node[,memdev=id][,cpus=firstcpu[-lastcpu]][,nodeid=node][,initiator=node]\n" "-numa dist,src=source,dst=destination,val=distance\n" "-numa cpu,node-id=node[,socket-id=x][,core-id=y][,thread-id=z]\n", QEMU_ARCH_ALL) STEXI -@item -numa node[,mem=@var{size}][,cpus=@var{firstcpu}[-@var{lastcpu}]][,nodeid=@var{node}] -@itemx -numa node[,memdev=@var{id}][,cpus=@var{firstcpu}[-@var{lastcpu}]][,nodeid=@var{node}] +@item -numa node[,mem=@var{size}][,cpus=@var{firstcpu}[-@var{lastcpu}]][,nodeid=@var{node}][,initiator=@var{initiator}] +@itemx -numa node[,memdev=@var{id}][,cpus=@var{firstcpu}[-@var{lastcpu}]][,nodeid=@var{node}][,initiator=@var{initiator}] @itemx -numa dist,src=@var{source},dst=@var{destination},val=@var{distance} @itemx -numa cpu,node-id=@var{node}[,socket-id=@var{x}][,core-id=@var{y}][,thread-id=@var{z}] @findex -numa
@@ -214,6 +214,25 @@ split equally between them. @samp{mem} and @samp{memdev} are mutually exclusive. Furthermore, if one node uses @samp{memdev}, all of them have to use it. +@samp{initiator} indicate the initiator NUMA @var{initiator} that is +closest (as in directly attached) to this NUMA @var{node}. + +For example, the following option assigns 2 NUMA nodes, node 0 has CPU. +node 1 has only memory, and its' initiator is node 0. Note that because +node 0 has CPU, by default the initiator of node 0 is itself and must be +itself. +@example +-M pc \ +-m 2G,slots=2,maxmem=4G \ +-object memory-backend-ram,size=1G,id=m0 \ +-object memory-backend-ram,size=1G,id=m1 \ +-numa node,nodeid=0,memdev=m0 \ +-numa node,nodeid=1,memdev=m1,initiator=0 \ +-smp 2,sockets=2,maxcpus=2 \ +-numa cpu,node-id=0,socket-id=0 \ +-numa cpu,node-id=0,socket-id=1 \ +@end example + @var{source} and @var{destination} are NUMA node IDs. @var{distance} is the NUMA distance from @var{source} to @var{destination}. The distance from a node to itself is always 10. If any pair of nodes is
Signature · 1 line
2.20.1
Re: [Qemu-devel] [PATCH v6 05/14] numa: Extend CLI to provide initiator information for numa nodes
Quoted 16 lines · Tao Xu
In ACPI 6.3 chapter 5.2.27 Heterogeneous Memory Attribute Table (HMAT), The initiator represents processor which access to memory. And in 5.2.27.3 Memory Proximity Domain Attributes Structure, the attached initiator is defined as where the memory controller responsible for a memory proximity domain. With attached initiator information, the topology of heterogeneous memory can be described.
Extend CLI of "-numa node" option to indicate the initiator numa node-id.
Suggested-by Dan Williams <[email protected]>Signed-off-by Tao Xu <[email protected]>---
+++
b/qapi/misc.json
qapi/misc.json line 2576
Quoted 5 lines
qapi/misc.json +2
-0@@ -2572,6 +2572,9 @@ # @memdev: memory backend object. If specified for one node, # it must be specified for all nodes. # +# @initiator: the initiator numa nodeid that is closest (as in directly +# attached) to this numa node.
Missing a '(since 4.2)' designator. We've already missed softfreeze for 4.1, and this is a new feature, so probably does have to slip into 4.2.
Signature · 3 lines
Eric Blake, Principal Software Engineer Red Hat, Inc. +1-919-301-3226 Virtualization: qemu.org | libvirt.org
Re: [Qemu-devel] [PATCH v6 05/14] numa: Extend CLI to provide initiator information for numa nodes
Quoted 15 lines · Eric Blake
Quoted 13 lines · Tao Xu
In ACPI 6.3 chapter 5.2.27 Heterogeneous Memory Attribute Table (HMAT), The initiator represents processor which access to memory. And in 5.2.27.3 Memory Proximity Domain Attributes Structure, the attached initiator is defined as where the memory controller responsible for a memory proximity domain. With attached initiator information, the topology of heterogeneous memory can be described.
Extend CLI of "-numa node" option to indicate the initiator numa node-id.
Suggested-by Dan Williams <[email protected]>Signed-off-by Tao Xu <[email protected]>---
Quoted 11 lines
qapi/misc.json line 2576
Quoted 7 lines
+++
b/qapi/misc.jsonqapi/misc.json +2
-0@@ -2572,6 +2572,9 @@ # @memdev: memory backend object. If specified for one node, # it must be specified for all nodes. # +# @initiator: the initiator numa nodeid that is closest (as in directly +# attached) to this numa node.Missing a '(since 4.2)' designator. We've already missed softfreeze for 4.1, and this is a new feature, so probably does have to slip into 4.2.
thanks, and I see the numa.c has been moved, i will rebase my patch and change the version flag
PATCH v6 6/14 hmat acpi: Build Memory Proximity Domain Attributes Structure(s)
In reply to Tao XuFrom: Liu Jingqi <[email protected]>
HMAT is defined in ACPI 6.3: 5.2.27 Heterogeneous Memory Attribute Table (HMAT). The specification references below link:
http://www.uefi.org/sites/default/files/resources/ACPI_6_3_final_Jan30.pdf
It describes the memory attributes, such as memory side cache attributes and bandwidth and latency details, related to the Memory Proximity Domain. The software is
expected to use this information as hint for optimization.
This structure describes Memory Proximity Domain Attributes by memory subsystem and its associativity with processor proximity domain as well as hint for memory usage.
---
Changes in v6:
Update to ACPI 6.3, main changes are:
- Renamed as Memory Proximity Domain Attributes, use numa nodes to replace memory ranges
- Use "-numa initiator" to describe "the Attached Initiator", more clear for memory topology
- Because HMAT does not use memory ranges, remove the codes to build mem_renges for dimm device
--- hw/acpi/Kconfig | 5 +++ hw/acpi/Makefile.objs | 1 + hw/acpi/hmat.c | 101 ++++++++++++++++++++++++++++++++++++++++++ hw/acpi/hmat.h | 45 +++++++++++++++++++ hw/i386/acpi-build.c | 3 ++ 5 files changed, 155 insertions(+) create mode 100644 hw/acpi/hmat.c create mode 100644 hw/acpi/hmat.h
hw/acpi/Kconfig +5 -0
@@ -7,6 +7,7 @@ config ACPI_X86 select ACPI_NVDIMM select ACPI_CPU_HOTPLUG select ACPI_MEMORY_HOTPLUG + select ACPI_HMAT config ACPI_X86_ICH bool
@@ -31,3 +32,7 @@ config ACPI_VMGENID bool default y depends on PC + +config ACPI_HMAT + bool + depends on ACPI
hw/acpi/Makefile.objs +1 -0
@@ -6,6 +6,7 @@ common-obj-$(CONFIG_ACPI_MEMORY_HOTPLUG) += memory_hotplug.o common-obj-$(CONFIG_ACPI_CPU_HOTPLUG) += cpu.o common-obj-$(CONFIG_ACPI_NVDIMM) += nvdimm.o common-obj-$(CONFIG_ACPI_VMGENID) += vmgenid.o +common-obj-$(CONFIG_ACPI_HMAT) += hmat.o common-obj-$(call lnot,$(CONFIG_ACPI_X86)) += acpi-stub.o common-obj-y += acpi_interface.o
hw/acpi/hmat.c new file +101 -0
101 lines not on this page · raw message
hw/acpi/hmat.h new file +45 -0
45 lines not on this page · raw message
hw/i386/acpi-build.c +3 -0
@@ -65,6 +65,7 @@#include "hw/i386/intel_iommu.h" #include "hw/acpi/ipmi.h" +#include "hw/acpi/hmat.h" /* These are used to size the ACPI tables for -M pc-i440fx-1.7 and * -M pc-i440fx-2.0. Even if the actual amount of AML generated grows
@@ -2684,6 +2685,8 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine)acpi_add_table (table_offsets, tables_blob);build_slit (tables_blob, tables->linker, machine); } +acpi_add_table (table_offsets, tables_blob); +build_hmat (tables_blob, tables->linker, machine->numa_state); }if (acpi_get_mcfg (&mcfg)) {acpi_add_table (table_offsets, tables_blob);
Signature · 1 line
2.20.1
Re: [Qemu-devel] [PATCH v6 06/14] hmat acpi: Build Memory Proximity Domain Attributes Structure(s)
Quoted 11 lines · On Sun, 7 Jul 2019 22:29:50 +0800 Tao Xu <[email protected]> wrote:
From: Liu Jingqi <[email protected]>
HMAT is defined in ACPI 6.3: 5.2.27 Heterogeneous Memory Attribute Table (HMAT). The specification references below link:
http://www.uefi.org/sites/default/files/resources/ACPI_6_3_final_Jan30.pdfIt describes the memory attributes, such as memory side cache attributes and bandwidth and latency details, related to the Memory Proximity Domain. The software is
expected to use this information as hint for optimization.
Quoted 6 lines
This structure describes Memory Proximity Domain Attributes by memory subsystem and its associativity with processor proximity domain as well as hint for memory usage.
Signed-off-by Liu Jingqi <[email protected]>Signed-off-by Tao Xu <[email protected]>
Looks good to me. Thanks for changing to 6.3.
Quoted 231 lines
---
Changes in v6:
Update to ACPI 6.3, main changes are:
- Renamed as Memory Proximity Domain Attributes, use numa nodes to replace memory ranges
- Use "-numa initiator" to describe "the Attached Initiator", more clear for memory topology
- Because HMAT does not use memory ranges, remove the codes to buildmem_rengesfor dimm device--- hw/acpi/Kconfig | 5 +++ hw/acpi/Makefile.objs | 1 + hw/acpi/hmat.c | 101 ++++++++++++++++++++++++++++++++++++++++++ hw/acpi/hmat.h | 45 +++++++++++++++++++ hw/i386/acpi-build.c | 3 ++ 5 files changed, 155 insertions(+) create mode 100644 hw/acpi/hmat.c create mode 100644 hw/acpi/hmat.hhw/acpi/Kconfig +5
-0@@ -7,6 +7,7 @@ config ACPI_X86 select ACPI_NVDIMM select ACPI_CPU_HOTPLUG select ACPI_MEMORY_HOTPLUG + select ACPI_HMAT config ACPI_X86_ICH bool@@ -31,3 +32,7 @@ config ACPI_VMGENID bool default y depends on PC + +config ACPI_HMAT + bool + depends on ACPIhw/acpi/Makefile.objs +1
-0@@ -6,6 +6,7 @@ common-obj-$(CONFIG_ACPI_MEMORY_HOTPLUG) += memory_hotplug.o common-obj-$(CONFIG_ACPI_CPU_HOTPLUG) += cpu.o common-obj-$(CONFIG_ACPI_NVDIMM) += nvdimm.o common-obj-$(CONFIG_ACPI_VMGENID) += vmgenid.o +common-obj-$(CONFIG_ACPI_HMAT) += hmat.o common-obj-$(call lnot,$(CONFIG_ACPI_X86)) += acpi-stub.o common-obj-y += acpi_interface.ohw/acpi/hmat.c new file +101
-0@@ -0,0 +1,101 @@ +/* +* HMAT ACPI Implementation +* +* Copyright(C) 2019 Intel Corporation. +* +* Author: +* Liu jingqi <[email protected]> +* Tao Xu <[email protected]> +* +* HMAT is defined in ACPI 6.3: 5.2.27 Heterogeneous Memory Attribute Table +* (HMAT) +* +* This library is free software; you can redistribute it and/or +* modify it under the terms of the GNU Lesser General Public +* License as published by the Free Software Foundation; either +* version 2 of the License, or (at your option) any later version. +* +* This library is distributed in the hope that it will be useful, +* but WITHOUT ANY WARRANTY; without even the implied warranty of +* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +* Lesser General Public License for more details. +* +* You should have received a copy of the GNU Lesser General Public +* License along with this library; if not, see <http://www.gnu.org/licenses/> +*/ + +#include "qemu/osdep.h" +#include "sysemu/numa.h" +#include "hw/acpi/hmat.h" + +/* +* ACPI 6.3: +* 5.2.27.3 Memory Proximity Domain Attributes Structure: Table 5-141 +*/ +static void build_hmat_mpda (GArray *table_data,uint16_t flags,int initiator, +int mem_node) +{ + +/* Memory Proximity Domain Attributes Structure */ +/* Type */ +build_append_int_noprefix (table_data,0 ,2 ); +/* Reserved */ +build_append_int_noprefix (table_data,0 ,2 ); +/* Length */ +build_append_int_noprefix (table_data,40 ,4 ); +/* Flags */ +build_append_int_noprefix (table_data, flags,2 ); +/* Reserved */ +build_append_int_noprefix (table_data,0 ,2 ); +/* Proximity Domain for the Attached Initiator */ +build_append_int_noprefix (table_data, initiator,4 ); +/* Proximity Domain for the Memory */ +build_append_int_noprefix (table_data, mem_node,4 ); +/* Reserved */ +build_append_int_noprefix (table_data,0 ,4 ); +/* +* Reserved: +* Previously defined as the Start Address of the System Physical +* Address Range. Deprecated since ACPI Spec 6.3. +*/ +build_append_int_noprefix (table_data,0 ,8 ); +/* +* Reserved: +* Previously defined as the Range Length of the region in bytes. +* Deprecated since ACPI Spec 6.3. +*/ +build_append_int_noprefix (table_data,0 ,8 ); +} + +/* Build HMAT sub table structures */ +static void hmat_build_table_structs (GArray *table_data,NumaState *nstat) +{ +uint16_t flags; +int i; + +for (i =0 ; i < nstat->num_nodes; i++) { + flags =0 ; + +if (nstat->nodes[i].initiator_valid) { + flags |=HMAT_PROX_INIT_VALID ; + } + +build_hmat_mpda (table_data, flags, nstat->nodes[i].initiator, i); + } +} + +void build_hmat (GArray *table_data,BIOSLinker *linker,NumaState *nstat) +{ +uint64_t hmat_start; + + hmat_start = table_data->len; + +/* reserve space for HMAT header */ +acpi_data_push (table_data,40 ); + +hmat_build_table_structs (table_data, nstat); + +build_header (linker, table_data, + (void *)(table_data->data + hmat_start), +"HMAT" , table_data->len - hmat_start,2 ,NULL ,NULL ); +}hw/acpi/hmat.h new file +45
-0@@ -0,0 +1,45 @@ +/* +* HMAT ACPI Implementation Header +* +* Copyright(C) 2019 Intel Corporation. +* +* Author: +* Liu jingqi <[email protected]> +* Tao Xu <[email protected]> +* +* HMAT is defined in ACPI 6.3: 5.2.27 Heterogeneous Memory Attribute Table +* (HMAT) +* +* This library is free software; you can redistribute it and/or +* modify it under the terms of the GNU Lesser General Public +* License as published by the Free Software Foundation; either +* version 2 of the License, or (at your option) any later version. +* +* This library is distributed in the hope that it will be useful, +* but WITHOUT ANY WARRANTY; without even the implied warranty of +* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +* Lesser General Public License for more details. +* +* You should have received a copy of the GNU Lesser General Public +* License along with this library; if not, see <http://www.gnu.org/licenses/> +*/ + +#ifndef HMAT_H +#define HMAT_H + +#include "hw/acpi/acpi-defs.h" +#include "hw/acpi/acpi.h" +#include "hw/acpi/bios-linker-loader.h" +#include "hw/acpi/aml-build.h" + +/* +* ACPI 6.3: 5.2.27.3 Memory Proximity Domain Attributes Structure, +* Table 5-141, Field "flag", Bit [0]: set to 1 to indicate that data in +* the Proximity Domain for the Attached Initiator field is valid. +* Other bits reserved. +*/ +#define HMAT_PROX_INIT_VALID 0x1 + +void build_hmat (GArray *table_data,BIOSLinker *linker,NumaState *nstat); + +#endif hw/i386/acpi-build.c +3
-0@@ -65,6 +65,7 @@#include "hw/i386/intel_iommu.h" #include "hw/acpi/ipmi.h" +#include "hw/acpi/hmat.h" /* These are used to size the ACPI tables for -M pc-i440fx-1.7 and * -M pc-i440fx-2.0. Even if the actual amount of AML generated grows @@ -2684,6 +2685,8 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine)acpi_add_table (table_offsets, tables_blob);build_slit (tables_blob, tables->linker, machine); } +acpi_add_table (table_offsets, tables_blob); +build_hmat (tables_blob, tables->linker, machine->numa_state); }if (acpi_get_mcfg (&mcfg)) {acpi_add_table (table_offsets, tables_blob);
PATCH v6 7/14 hmat acpi: Build System Locality Latency and Bandwidth Information Structure(s)
In reply to Tao XuFrom: Liu Jingqi <[email protected]>
This structure describes the memory access latency and bandwidth information from various memory access initiator proximity domains. The latency and bandwidth numbers represented in this structure correspond to rated latency and bandwidth for the platform. The software could use this information as hint for optimization.
---
Changes in v6:
- Update the describes in ACPI 6.3
- remove num target and target_pxm, because all numa node can be target(no matter it can be reached or not, The Entry Base Unit for latency 0xFFFF means the initiator and target domains are unreachable from each other)
--- hw/acpi/hmat.c | 94 ++++++++++++++++++++++++++++++++++++++++- hw/acpi/hmat.h | 39 +++++++++++++++++ include/qemu/typedefs.h | 1 + include/sysemu/numa.h | 3 ++ include/sysemu/sysemu.h | 22 ++++++++++ 5 files changed, 158 insertions(+), 1 deletion(-)
hw/acpi/hmat.c +93 -1
@@ -67,11 +67,80 @@ static void build_hmat_mpda(GArray *table_data, uint16_t flags, int initiator,build_append_int_noprefix (table_data,0 ,8 ); } +/* +* ACPI 6.3: 5.2.27.4 System Locality Latency and Bandwidth Information +* Structure: Table 5-142 +*/ +static void build_hmat_lb (GArray *table_data,HMAT_LB_Info *numa_hmat_lb, +uint32_t num_initiator,uint32_t num_target, +uint32_t *initiator_pxm,int type) +{ +uint32_t s = num_initiator; +uint32_t t = num_target; +uint8_t m, n; +int i; + +/* Type */ +build_append_int_noprefix (table_data,1 ,2 ); +/* Reserved */ +build_append_int_noprefix (table_data,0 ,2 ); +/* Length */ +build_append_int_noprefix (table_data,32 +4 * s +4 * t +2 * s * t,4 ); +/* Flags */ +build_append_int_noprefix (table_data, numa_hmat_lb->hierarchy,1 ); +/* Data Type */ +build_append_int_noprefix (table_data, numa_hmat_lb->data_type,1 ); +/* Reserved */ +build_append_int_noprefix (table_data,0 ,2 ); +/* Number of Initiator Proximity Domains (s) */ +build_append_int_noprefix (table_data, s,4 ); +/* Number of Target Proximity Domains (t) */ +build_append_int_noprefix (table_data, t,4 ); +/* Reserved */ +build_append_int_noprefix (table_data,0 ,4 ); + +/* Entry Base Unit */ +if (type <=HMAT_LB_DATA_WRITE_LATENCY ) { +build_append_int_noprefix (table_data, numa_hmat_lb->base_lat,8 ); + }else { +build_append_int_noprefix (table_data, numa_hmat_lb->base_bw,8 ); + } + +/* Initiator Proximity Domain List */ +for (i =0 ; i < s; i++) { +build_append_int_noprefix (table_data, initiator_pxm[i],4 ); + } + +/* Target Proximity Domain List */ +for (i =0 ; i < t; i++) { +build_append_int_noprefix (table_data, i,4 ); + } + +/* Latency or Bandwidth Entries */ +for (i =0 ; i < s; i++) { + m = initiator_pxm[i]; +for (n =0 ; n < t; n++) { +uint16_t entry; + +if (type <=HMAT_LB_DATA_WRITE_LATENCY ) { + entry = numa_hmat_lb->latency[m][n]; + }else { + entry = numa_hmat_lb->bandwidth[m][n]; + } + +build_append_int_noprefix (table_data, entry,2 ); + } + } +} +/* Build HMAT sub table structures */ static void hmat_build_table_structs (GArray *table_data,NumaState *nstat) {uint16_t flags; -int i; +uint32_t num_initiator =0 ; +uint32_t initiator_pxm[MAX_NODES ]; +int i, hrchy, type; +HMAT_LB_Info *numa_hmat_lb;for (i =0 ; i < nstat->num_nodes; i++) { flags =0 ;
@@ -82,6 +151,29 @@ static void hmat_build_table_structs(GArray *table_data, NumaState *nstat)build_hmat_mpda (table_data, flags, nstat->nodes[i].initiator, i); } + +for (i =0 ; i < nstat->num_nodes; i++) { +if (nstat->nodes[i].has_cpu) { + initiator_pxm[num_initiator++] = i; + } + } + +/* +* ACPI 6.3: 5.2.27.4 System Locality Latency and Bandwidth Information +* Structure: Table 5-142 +*/ +for (hrchy =HMAT_LB_MEM_MEMORY ; + hrchy <=HMAT_LB_MEM_CACHE_3RD_LEVEL ; hrchy++) { +for (type =HMAT_LB_DATA_ACCESS_LATENCY ; + type <=HMAT_LB_DATA_WRITE_BANDWIDTH ; type++) { + numa_hmat_lb = nstat->hmat_lb[hrchy][type]; + +if (numa_hmat_lb) { +build_hmat_lb (table_data, numa_hmat_lb, num_initiator, + nstat->num_nodes, initiator_pxm, type); + } + } + } }void build_hmat (GArray *table_data,BIOSLinker *linker,NumaState *nstat)
hw/acpi/hmat.h +39 -0
@@ -40,6 +40,45 @@*/ #define HMAT_PROX_INIT_VALID 0x1 +struct HMAT_LB_Info { +/* +* Indicates total number of Proximity Domains +* that can initiate memory access requests. +*/ +uint32_t num_initiator; +/* +* Indicates total number of Proximity Domains +* that can act as target. +*/ +uint32_t num_target; +/* +* Indicates it's memory or +* the specified level memory side cache. +*/ +uint8_t hierarchy; +/* +* Present the type of data, +* access/read/write latency or bandwidth. +*/ +uint8_t data_type; +/* The base unit for latency in nanoseconds. */ +uint64_t base_lat; +/* The base unit for bandwidth in megabytes per second(MB/s). */ +uint64_t base_bw; +/* +* latency[i][j]: +* Indicates the latency based on base_lat +* from Initiator Proximity Domain i to Target Proximity Domain j. +*/ +uint16_t latency[MAX_NODES ][MAX_NODES ]; +/* +* bandwidth[i][j]: +* Indicates the bandwidth based on base_bw +* from Initiator Proximity Domain i to Target Proximity Domain j. +*/ +uint16_t bandwidth[MAX_NODES ][MAX_NODES ]; +}; +void build_hmat (GArray *table_data,BIOSLinker *linker,NumaState *nstat);#endif
include/qemu/typedefs.h +1 -0
@@ -33,6 +33,7 @@ typedef struct FWCfgEntry FWCfgEntry;typedef struct FWCfgIoState FWCfgIoState ;typedef struct FWCfgMemState FWCfgMemState ;typedef struct FWCfgState FWCfgState ; +typedef struct HMAT_LB_Info HMAT_LB_Info ;typedef struct HVFX86EmulatorState HVFX86EmulatorState ;typedef struct I2CBus I2CBus ;typedef struct I2SCodec I2SCodec ;
include/sysemu/numa.h +3 -0
@@ -32,6 +32,9 @@ struct NumaState {/* NUMA nodes information */ NodeInfo nodes[MAX_NODES ]; + +/* NUMA modes HMAT Locality Latency and Bandwidth Information */ +HMAT_LB_Info *hmat_lb[HMAT_LB_LEVELS ][HMAT_LB_TYPES ]; };typedef struct NumaState NumaState ;
include/sysemu/sysemu.h +22 -0
@@ -124,6 +124,28 @@ extern int mem_prealloc;#define NUMA_DISTANCE_MAX 254#define NUMA_DISTANCE_UNREACHABLE 255 +/* the value of AcpiHmatLBInfo flags */ +enum { +HMAT_LB_MEM_MEMORY =0 , +HMAT_LB_MEM_CACHE_LAST_LEVEL =1 , +HMAT_LB_MEM_CACHE_1ST_LEVEL =2 , +HMAT_LB_MEM_CACHE_2ND_LEVEL =3 , +HMAT_LB_MEM_CACHE_3RD_LEVEL =4 , +}; + +/* the value of AcpiHmatLBInfo data type */ +enum { +HMAT_LB_DATA_ACCESS_LATENCY =0 , +HMAT_LB_DATA_READ_LATENCY =1 , +HMAT_LB_DATA_WRITE_LATENCY =2 , +HMAT_LB_DATA_ACCESS_BANDWIDTH =3 , +HMAT_LB_DATA_READ_BANDWIDTH =4 , +HMAT_LB_DATA_WRITE_BANDWIDTH =5 , +}; + +#define HMAT_LB_LEVELS (HMAT_LB_MEM_CACHE_3RD_LEVEL + 1) +#define HMAT_LB_TYPES (HMAT_LB_DATA_WRITE_BANDWIDTH + 1) +#define MAX_OPTION_ROMS 16 typedef struct QEMUOptionRom { const char *name;
Signature · 1 line
2.20.1
Re: [Qemu-devel] [PATCH v6 07/14] hmat acpi: Build System Locality Latency and Bandwidth Information Structure(s)
Quoted 10 lines · On Sun, 7 Jul 2019 22:29:51 +0800 Tao Xu <[email protected]> wrote:
From: Liu Jingqi <[email protected]>
This structure describes the memory access latency and bandwidth information from various memory access initiator proximity domains. The latency and bandwidth numbers represented in this structure correspond to rated latency and bandwidth for the platform. The software could use this information as hint for optimization.
Signed-off-by Liu Jingqi <[email protected]>Signed-off-by Tao Xu <[email protected]>
I think you've missed one of the 6.3 changes. Otherwise a few nitpicks but looks good to me.
I've focused on the patches actually dealing with the ACPI tables because I'm far less familiar with the opt parsing etc in qemu so don't feel confident expressing a view on those.
Thanks,
Jonathan
Quoted 35 lines
---
Changes in v6:
- Update the describes in ACPI 6.3
- remove num target andtarget_pxm, because all numa node can be target(no matter it can be reached or not, The Entry Base Unit for latency0xFFFFmeans the initiator and target domains are unreachable from each other)--- hw/acpi/hmat.c | 94 ++++++++++++++++++++++++++++++++++++++++- hw/acpi/hmat.h | 39 +++++++++++++++++ include/qemu/typedefs.h | 1 + include/sysemu/numa.h | 3 ++ include/sysemu/sysemu.h | 22 ++++++++++ 5 files changed, 158 insertions(+), 1 deletion(-)hw/acpi/hmat.c +11
-0@@ -67,11 +67,80 @@ static void build_hmat_mpda(GArray *table_data, uint16_t flags, int initiator,build_append_int_noprefix (table_data,0 ,8 ); } +/* +* ACPI 6.3: 5.2.27.4 System Locality Latency and Bandwidth Information +* Structure: Table 5-142 +*/ +static void build_hmat_lb (GArray *table_data,HMAT_LB_Info *numa_hmat_lb, +uint32_t num_initiator,uint32_t num_target, +uint32_t *initiator_pxm,int type) +{ +uint32_t s = num_initiator; +uint32_t t = num_target; +uint8_t m, n;
hw/acpi/hmat.c static void build_hmat_mpda(GArray *table_data, uint16_t flags, int initiator, · line 90
Quoted 10 lines
hw/acpi/hmat.c +10
-0+int i; + +/* Type */ +build_append_int_noprefix (table_data,1 ,2 ); +/* Reserved */ +build_append_int_noprefix (table_data,0 ,2 ); +/* Length */ +build_append_int_noprefix (table_data,32 +4 * s +4 * t +2 * s * t,4 ); +/* Flags */ +build_append_int_noprefix (table_data, numa_hmat_lb->hierarchy,1 );
There might be a small argument in favour of masking this as half the bits are reserved.
hw/acpi/hmat.c static void build_hmat_mpda(GArray *table_data, uint16_t flags, int initiator, · line 103
Quoted 13 lines
hw/acpi/hmat.c +13
-0+/* Data Type */ +build_append_int_noprefix (table_data, numa_hmat_lb->data_type,1 ); +/* Reserved */ +build_append_int_noprefix (table_data,0 ,2 ); +/* Number of Initiator Proximity Domains (s) */ +build_append_int_noprefix (table_data, s,4 ); +/* Number of Target Proximity Domains (t) */ +build_append_int_noprefix (table_data, t,4 ); +/* Reserved */ +build_append_int_noprefix (table_data,0 ,4 ); + +/* Entry Base Unit */ +if (type <=HMAT_LB_DATA_WRITE_LATENCY ) {
I'd slightly prefer this as an explicit switch with all the elements laid out. That would make it 'obvious' that this is all the Latency cases and the next path is all the Bandwidth ones.
(up to you though!)
Quoted 12 lines
hw/acpi/hmat.c +12
-0+build_append_int_noprefix (table_data, numa_hmat_lb->base_lat,8 ); + }else { +build_append_int_noprefix (table_data, numa_hmat_lb->base_bw,8 ); + } + +/* Initiator Proximity Domain List */ +for (i =0 ; i < s; i++) { +build_append_int_noprefix (table_data, initiator_pxm[i],4 ); + } + +/* Target Proximity Domain List */ +for (i =0 ; i < t; i++) {
hw/acpi/hmat.c static void build_hmat_mpda(GArray *table_data, uint16_t flags, int initiator, · line 125
Quoted 10 lines
hw/acpi/hmat.c +10
-0+build_append_int_noprefix (table_data, i,4 ); + } + +/* Latency or Bandwidth Entries */ +for (i =0 ; i < s; i++) { + m = initiator_pxm[i]; +for (n =0 ; n < t; n++) { +uint16_t entry; + +if (type <=HMAT_LB_DATA_WRITE_LATENCY ) {
As above, a switch is more code, but it's clearer. Alternative would be a macro HMAT_IS_LATENCY()
Quoted 133 lines
hw/acpi/hmat.c +37
-1+ entry = numa_hmat_lb->latency[m][n]; + }else { + entry = numa_hmat_lb->bandwidth[m][n]; + } + +build_append_int_noprefix (table_data, entry,2 ); + } + } +} +/* Build HMAT sub table structures */ static void hmat_build_table_structs (GArray *table_data,NumaState *nstat) {uint16_t flags; -int i; +uint32_t num_initiator =0 ; +uint32_t initiator_pxm[MAX_NODES ]; +int i, hrchy, type; +HMAT_LB_Info *numa_hmat_lb;for (i =0 ; i < nstat->num_nodes; i++) { flags =0 ;@@ -82,6 +151,29 @@ static void hmat_build_table_structs(GArray *table_data, NumaState *nstat)build_hmat_mpda (table_data, flags, nstat->nodes[i].initiator, i); } + +for (i =0 ; i < nstat->num_nodes; i++) { +if (nstat->nodes[i].has_cpu) { + initiator_pxm[num_initiator++] = i; + } + } + +/* +* ACPI 6.3: 5.2.27.4 System Locality Latency and Bandwidth Information +* Structure: Table 5-142 +*/ +for (hrchy =HMAT_LB_MEM_MEMORY ; + hrchy <=HMAT_LB_MEM_CACHE_3RD_LEVEL ; hrchy++) { +for (type =HMAT_LB_DATA_ACCESS_LATENCY ; + type <=HMAT_LB_DATA_WRITE_BANDWIDTH ; type++) { + numa_hmat_lb = nstat->hmat_lb[hrchy][type]; + +if (numa_hmat_lb) { +build_hmat_lb (table_data, numa_hmat_lb, num_initiator, + nstat->num_nodes, initiator_pxm, type); + } + } + } }void build_hmat (GArray *table_data,BIOSLinker *linker,NumaState *nstat)hw/acpi/hmat.h +39
-0@@ -40,6 +40,45 @@*/ #define HMAT_PROX_INIT_VALID 0x1 +struct HMAT_LB_Info { +/* +* Indicates total number of Proximity Domains +* that can initiate memory access requests. +*/ +uint32_t num_initiator; +/* +* Indicates total number of Proximity Domains +* that can act as target. +*/ +uint32_t num_target; +/* +* Indicates it's memory or +* the specified level memory side cache. +*/ +uint8_t hierarchy; +/* +* Present the type of data, +* access/read/write latency or bandwidth. +*/ +uint8_t data_type; +/* The base unit for latency in nanoseconds. */ +uint64_t base_lat; +/* The base unit for bandwidth in megabytes per second(MB/s). */ +uint64_t base_bw; +/* +* latency[i][j]: +* Indicates the latency based on base_lat +* from Initiator Proximity Domain i to Target Proximity Domain j. +*/ +uint16_t latency[MAX_NODES ][MAX_NODES ]; +/* +* bandwidth[i][j]: +* Indicates the bandwidth based on base_bw +* from Initiator Proximity Domain i to Target Proximity Domain j. +*/ +uint16_t bandwidth[MAX_NODES ][MAX_NODES ]; +}; +void build_hmat (GArray *table_data,BIOSLinker *linker,NumaState *nstat);#endif include/qemu/typedefs.h +1
-0@@ -33,6 +33,7 @@ typedef struct FWCfgEntry FWCfgEntry;typedef struct FWCfgIoState FWCfgIoState ;typedef struct FWCfgMemState FWCfgMemState ;typedef struct FWCfgState FWCfgState ; +typedef struct HMAT_LB_Info HMAT_LB_Info ;typedef struct HVFX86EmulatorState HVFX86EmulatorState ;typedef struct I2CBus I2CBus ;typedef struct I2SCodec I2SCodec ;include/sysemu/numa.h +3
-0@@ -32,6 +32,9 @@ struct NumaState {/* NUMA nodes information */ NodeInfo nodes[MAX_NODES ]; + +/* NUMA modes HMAT Locality Latency and Bandwidth Information */ +HMAT_LB_Info *hmat_lb[HMAT_LB_LEVELS ][HMAT_LB_TYPES ]; };typedef struct NumaState NumaState ;include/sysemu/sysemu.h +0
-0
include/sysemu/sysemu.h extern int mem_prealloc; · line 130
Quoted 7 lines
include/sysemu/sysemu.h +4
-0@@ -124,6 +124,28 @@ extern int mem_prealloc;#define NUMA_DISTANCE_MAX 254#define NUMA_DISTANCE_UNREACHABLE 255 +/* the value of AcpiHmatLBInfo flags */ +enum { +HMAT_LB_MEM_MEMORY =0 , +HMAT_LB_MEM_CACHE_LAST_LEVEL =1 ,
This changed in 6.3. There isn't a last level one now.
Quoted 21 lines
include/sysemu/sysemu.h +18
-0+HMAT_LB_MEM_CACHE_1ST_LEVEL =2 , +HMAT_LB_MEM_CACHE_2ND_LEVEL =3 , + HMAT_LB_MEM_CACHE_3RD_LEVEL = 4, +}; + +/* the value of AcpiHmatLBInfo data type */ +enum { +HMAT_LB_DATA_ACCESS_LATENCY =0 , +HMAT_LB_DATA_READ_LATENCY =1 , +HMAT_LB_DATA_WRITE_LATENCY =2 , +HMAT_LB_DATA_ACCESS_BANDWIDTH =3 , +HMAT_LB_DATA_READ_BANDWIDTH =4 , +HMAT_LB_DATA_WRITE_BANDWIDTH =5 , +}; + +#define HMAT_LB_LEVELS (HMAT_LB_MEM_CACHE_3RD_LEVEL + 1) +#define HMAT_LB_TYPES (HMAT_LB_DATA_WRITE_BANDWIDTH + 1) +#define MAX_OPTION_ROMS 16 typedef struct QEMUOptionRom { const char *name;
Re: [Qemu-devel] [PATCH v6 07/14] hmat acpi: Build System Locality Latency and Bandwidth Information Structure(s)
Quoted 19 lines · Jonathan Cameron
Quoted 10 lines · On Sun, 7 Jul 2019 22:29:51 +0800 Tao Xu <[email protected]> wrote:
From: Liu Jingqi <[email protected]>
This structure describes the memory access latency and bandwidth information from various memory access initiator proximity domains. The latency and bandwidth numbers represented in this structure correspond to rated latency and bandwidth for the platform. The software could use this information as hint for optimization.
Signed-off-by Liu Jingqi <[email protected]>Signed-off-by Tao Xu <[email protected]>I think you've missed one of the 6.3 changes. Otherwise a few nitpicks but looks good to me.
Reviewed-by Jonathan Cameron <[email protected]>
Quoted 8 lines
I've focused on the patches actually dealing with the ACPI tables because I'm far less familiar with the opt parsing etc in qemu so don't feel confident expressing a view on those.
Thanks,
Jonathan
Thank you for your review and suggestions :) I will improve the issues in my next version.
Tao
Quoted 40 lines
Quoted 40 lines
---
Changes in v6:
- Update the describes in ACPI 6.3
- remove num target andtarget_pxm, because all numa node can be target(no matter it can be reached or not, The Entry Base Unit for latency0xFFFFmeans the initiator and target domains are unreachable from each other)--- hw/acpi/hmat.c | 94 ++++++++++++++++++++++++++++++++++++++++- hw/acpi/hmat.h | 39 +++++++++++++++++ include/qemu/typedefs.h | 1 + include/sysemu/numa.h | 3 ++ include/sysemu/sysemu.h | 22 ++++++++++ 5 files changed, 158 insertions(+), 1 deletion(-)hw/acpi/hmat.c +16
-0@@ -67,11 +67,80 @@ static void build_hmat_mpda(GArray *table_data, uint16_t flags, int initiator,build_append_int_noprefix (table_data,0 ,8 ); } +/* +* ACPI 6.3: 5.2.27.4 System Locality Latency and Bandwidth Information +* Structure: Table 5-142 +*/ +static void build_hmat_lb (GArray *table_data,HMAT_LB_Info *numa_hmat_lb, +uint32_t num_initiator,uint32_t num_target, +uint32_t *initiator_pxm,int type) +{ +uint32_t s = num_initiator; +uint32_t t = num_target; +uint8_t m, n; +int i; + +/* Type */ +build_append_int_noprefix (table_data,1 ,2 ); +/* Reserved */
Quoted 8 lines
hw/acpi/hmat.c static void build_hmat_mpda(GArray *table_data, uint16_t flags, int initiator, · line 90
Quoted 5 lines
hw/acpi/hmat.c +5
-0+build_append_int_noprefix (table_data,0 ,2 ); +/* Length */ +build_append_int_noprefix (table_data,32 +4 * s +4 * t +2 * s * t,4 ); +/* Flags */ +build_append_int_noprefix (table_data, numa_hmat_lb->hierarchy,1 );There might be a small argument in favour of masking this as half the bits are reserved.
Thanks, I will add a reserved bit mask.
Quoted 35 lines
hw/acpi/hmat.c static void build_hmat_mpda(GArray *table_data, uint16_t flags, int initiator, · line 103
Quoted 13 lines
hw/acpi/hmat.c +13
-0+/* Data Type */ +build_append_int_noprefix (table_data, numa_hmat_lb->data_type,1 ); +/* Reserved */ +build_append_int_noprefix (table_data,0 ,2 ); +/* Number of Initiator Proximity Domains (s) */ +build_append_int_noprefix (table_data, s,4 ); +/* Number of Target Proximity Domains (t) */ +build_append_int_noprefix (table_data, t,4 ); +/* Reserved */ +build_append_int_noprefix (table_data,0 ,4 ); + +/* Entry Base Unit */ +if (type <=HMAT_LB_DATA_WRITE_LATENCY ) {I'd slightly prefer this as an explicit switch with all the elements laid out. That would make it 'obvious' that this is all the Latency cases and the next path is all the Bandwidth ones.
(up to you though!)Quoted 16 lines
hw/acpi/hmat.c +16
-0+build_append_int_noprefix (table_data, numa_hmat_lb->base_lat,8 ); + }else { +build_append_int_noprefix (table_data, numa_hmat_lb->base_bw,8 ); + } + +/* Initiator Proximity Domain List */ +for (i =0 ; i < s; i++) { +build_append_int_noprefix (table_data, initiator_pxm[i],4 ); + } + +/* Target Proximity Domain List */ +for (i =0 ; i < t; i++) { +build_append_int_noprefix (table_data, i,4 ); + } + +/* Latency or Bandwidth Entries */
Quoted 9 lines
hw/acpi/hmat.c static void build_hmat_mpda(GArray *table_data, uint16_t flags, int initiator, · line 125
Quoted 6 lines
hw/acpi/hmat.c +6
-0+for (i =0 ; i < s; i++) { + m = initiator_pxm[i]; +for (n =0 ; n < t; n++) { +uint16_t entry; + +if (type <=HMAT_LB_DATA_WRITE_LATENCY ) {As above, a switch is more code, but it's clearer. Alternative would be a macro
HMAT_IS_LATENCY()
Thank you, indeed a macro is clearer.
Quoted 166 lines
Quoted 133 lines
hw/acpi/hmat.c +37
-1+ entry = numa_hmat_lb->latency[m][n]; + }else { + entry = numa_hmat_lb->bandwidth[m][n]; + } + +build_append_int_noprefix (table_data, entry,2 ); + } + } +} +/* Build HMAT sub table structures */ static void hmat_build_table_structs (GArray *table_data,NumaState *nstat) {uint16_t flags; -int i; +uint32_t num_initiator =0 ; +uint32_t initiator_pxm[MAX_NODES ]; +int i, hrchy, type; +HMAT_LB_Info *numa_hmat_lb;for (i =0 ; i < nstat->num_nodes; i++) { flags =0 ;@@ -82,6 +151,29 @@ static void hmat_build_table_structs(GArray *table_data, NumaState *nstat)build_hmat_mpda (table_data, flags, nstat->nodes[i].initiator, i); } + +for (i =0 ; i < nstat->num_nodes; i++) { +if (nstat->nodes[i].has_cpu) { + initiator_pxm[num_initiator++] = i; + } + } + +/* +* ACPI 6.3: 5.2.27.4 System Locality Latency and Bandwidth Information +* Structure: Table 5-142 +*/ +for (hrchy =HMAT_LB_MEM_MEMORY ; + hrchy <=HMAT_LB_MEM_CACHE_3RD_LEVEL ; hrchy++) { +for (type =HMAT_LB_DATA_ACCESS_LATENCY ; + type <=HMAT_LB_DATA_WRITE_BANDWIDTH ; type++) { + numa_hmat_lb = nstat->hmat_lb[hrchy][type]; + +if (numa_hmat_lb) { +build_hmat_lb (table_data, numa_hmat_lb, num_initiator, + nstat->num_nodes, initiator_pxm, type); + } + } + } }void build_hmat (GArray *table_data,BIOSLinker *linker,NumaState *nstat)hw/acpi/hmat.h +39
-0@@ -40,6 +40,45 @@*/ #define HMAT_PROX_INIT_VALID 0x1 +struct HMAT_LB_Info { +/* +* Indicates total number of Proximity Domains +* that can initiate memory access requests. +*/ +uint32_t num_initiator; +/* +* Indicates total number of Proximity Domains +* that can act as target. +*/ +uint32_t num_target; +/* +* Indicates it's memory or +* the specified level memory side cache. +*/ +uint8_t hierarchy; +/* +* Present the type of data, +* access/read/write latency or bandwidth. +*/ +uint8_t data_type; +/* The base unit for latency in nanoseconds. */ +uint64_t base_lat; +/* The base unit for bandwidth in megabytes per second(MB/s). */ +uint64_t base_bw; +/* +* latency[i][j]: +* Indicates the latency based on base_lat +* from Initiator Proximity Domain i to Target Proximity Domain j. +*/ +uint16_t latency[MAX_NODES ][MAX_NODES ]; +/* +* bandwidth[i][j]: +* Indicates the bandwidth based on base_bw +* from Initiator Proximity Domain i to Target Proximity Domain j. +*/ +uint16_t bandwidth[MAX_NODES ][MAX_NODES ]; +}; +void build_hmat (GArray *table_data,BIOSLinker *linker,NumaState *nstat);#endif include/qemu/typedefs.h +1
-0@@ -33,6 +33,7 @@ typedef struct FWCfgEntry FWCfgEntry;typedef struct FWCfgIoState FWCfgIoState ;typedef struct FWCfgMemState FWCfgMemState ;typedef struct FWCfgState FWCfgState ; +typedef struct HMAT_LB_Info HMAT_LB_Info ;typedef struct HVFX86EmulatorState HVFX86EmulatorState ;typedef struct I2CBus I2CBus ;typedef struct I2SCodec I2SCodec ;include/sysemu/numa.h +3
-0@@ -32,6 +32,9 @@ struct NumaState {/* NUMA nodes information */ NodeInfo nodes[MAX_NODES ]; + +/* NUMA modes HMAT Locality Latency and Bandwidth Information */ +HMAT_LB_Info *hmat_lb[HMAT_LB_LEVELS ][HMAT_LB_TYPES ]; };typedef struct NumaState NumaState ;include/sysemu/sysemu.h +0
-0include/sysemu/sysemu.h extern int mem_prealloc; · line 130
Quoted 7 lines
include/sysemu/sysemu.h +4
-0@@ -124,6 +124,28 @@ extern int mem_prealloc;#define NUMA_DISTANCE_MAX 254#define NUMA_DISTANCE_UNREACHABLE 255 +/* the value of AcpiHmatLBInfo flags */ +enum { +HMAT_LB_MEM_MEMORY =0 , +HMAT_LB_MEM_CACHE_LAST_LEVEL =1 ,This changed in 6.3. There isn't a last level one now.
Quoted 21 lines
include/sysemu/sysemu.h +18
-0+HMAT_LB_MEM_CACHE_1ST_LEVEL =2 , +HMAT_LB_MEM_CACHE_2ND_LEVEL =3 , + HMAT_LB_MEM_CACHE_3RD_LEVEL = 4, +}; + +/* the value of AcpiHmatLBInfo data type */ +enum { +HMAT_LB_DATA_ACCESS_LATENCY =0 , +HMAT_LB_DATA_READ_LATENCY =1 , +HMAT_LB_DATA_WRITE_LATENCY =2 , +HMAT_LB_DATA_ACCESS_BANDWIDTH =3 , +HMAT_LB_DATA_READ_BANDWIDTH =4 , +HMAT_LB_DATA_WRITE_BANDWIDTH =5 , +}; + +#define HMAT_LB_LEVELS (HMAT_LB_MEM_CACHE_3RD_LEVEL + 1) +#define HMAT_LB_TYPES (HMAT_LB_DATA_WRITE_BANDWIDTH + 1) +#define MAX_OPTION_ROMS 16 typedef struct QEMUOptionRom { const char *name;
PATCH v6 8/14 hmat acpi: Build Memory Side Cache Information Structure(s)
In reply to Tao XuFrom: Liu Jingqi <[email protected]>
This structure describes memory side cache information for memory proximity domains if the memory side cache is present and the physical device forms the memory side cache.
The software could use this information to effectively place the data in memory to maximize the performance of the system memory that use the memory side cache.
---
Changes in v6:
- Add descriptions from ACPI 6.3 spec
--- hw/acpi/hmat.c | 64 ++++++++++++++++++++++++++++++++++++++++- hw/acpi/hmat.h | 20 +++++++++++++ include/qemu/typedefs.h | 1 + include/sysemu/numa.h | 3 ++ include/sysemu/sysemu.h | 2 ++ 5 files changed, 89 insertions(+), 1 deletion(-)
hw/acpi/hmat.c +63 -1
@@ -133,14 +133,63 @@ static void build_hmat_lb(GArray *table_data, HMAT_LB_Info *numa_hmat_lb, } } +/* ACPI 6.3: 5.2.27.5 Memory Side Cache Information Structure: Table 5-143 */ +static void build_hmat_cache (GArray *table_data,HMAT_Cache_Info *hmat_cache) +{ +/* +* Cache Attributes: Bits [3:0] – Total Cache Levels +* for this Memory Proximity Domain +*/ +uint32_t cache_attr = hmat_cache->total_levels &0xF ; + +/* Bits [7:4] : Cache Level described in this structure */ + cache_attr |= (hmat_cache->level &0xF ) <<4 ; + +/* Bits [11:8] - Cache Associativity */ + cache_attr |= (hmat_cache->associativity &0xF ) <<8 ; + +/* Bits [15:12] - Write Policy */ + cache_attr |= (hmat_cache->write_policy &0xF ) <<12 ; + +/* Bits [31:16] - Cache Line size in bytes */ + cache_attr |= (hmat_cache->line_size &0xFFFF ) <<16 ; + + cache_attr =cpu_to_le32 (cache_attr); + +/* Type */ +build_append_int_noprefix (table_data,2 ,2 ); +/* Reserved */ +build_append_int_noprefix (table_data,0 ,2 ); +/* Length */ +build_append_int_noprefix (table_data,32 ,4 ); +/* Proximity Domain for the Memory */ +build_append_int_noprefix (table_data, hmat_cache->mem_proximity,4 ); +/* Reserved */ +build_append_int_noprefix (table_data,0 ,4 ); +/* Memory Side Cache Size */ +build_append_int_noprefix (table_data, hmat_cache->size,8 ); +/* Cache Attributes */ +build_append_int_noprefix (table_data, cache_attr,4 ); +/* Reserved */ +build_append_int_noprefix (table_data,0 ,2 ); +/* +* Number of SMBIOS handles (n) +* Linux kernel uses Memory Side Cache Information Structure +* without SMBIOS entries for now, so set Number of SMBIOS handles +* as 0. +*/ +build_append_int_noprefix (table_data,0 ,2 ); +} +/* Build HMAT sub table structures */ static void hmat_build_table_structs (GArray *table_data,NumaState *nstat) {uint16_t flags;uint32_t num_initiator =0 ;uint32_t initiator_pxm[MAX_NODES ]; -int i, hrchy, type; +int i, hrchy, type, level;HMAT_LB_Info *numa_hmat_lb; +HMAT_Cache_Info *numa_hmat_cache;for (i =0 ; i < nstat->num_nodes; i++) { flags =0 ;
@@ -174,6 +223,19 @@ static void hmat_build_table_structs(GArray *table_data, NumaState *nstat) } } } + +/* +* ACPI 6.3: 5.2.27.5 Memory Side Cache Information Structure: +* Table 5-143 +*/ +for (i =0 ; i < nstat->num_nodes; i++) { +for (level =0 ; level <=MAX_HMAT_CACHE_LEVEL ; level++) { + numa_hmat_cache = nstat->hmat_cache[i][level]; +if (numa_hmat_cache) { +build_hmat_cache (table_data, numa_hmat_cache); + } + } + } }void build_hmat (GArray *table_data,BIOSLinker *linker,NumaState *nstat)
hw/acpi/hmat.h +20 -0
@@ -79,6 +79,26 @@ struct HMAT_LB_Info { uint16_t bandwidth[MAX_NODES][MAX_NODES]; }; +struct HMAT_Cache_Info { +/* The memory proximity domain to which the memory belongs. */ +uint32_t mem_proximity; +/* Size of memory side cache in bytes. */ +uint64_t size; +/* +* Total cache levels for this memory +* pr#include "hw/acpi/aml-build.h"oximity domain. +*/ +uint8_t total_levels; +/* Cache level described in this structure. */ +uint8_t level; +/* Cache Associativity: None/Direct Mapped/Comple Cache Indexing */ +uint8_t associativity; +/* Write Policy: None/Write Back(WB)/Write Through(WT) */ +uint8_t write_policy; +/* Cache Line size in bytes. */ +uint16_t line_size; +}; +void build_hmat (GArray *table_data,BIOSLinker *linker,NumaState *nstat);#endif
include/qemu/typedefs.h +1 -0
@@ -33,6 +33,7 @@ typedef struct FWCfgEntry FWCfgEntry;typedef struct FWCfgIoState FWCfgIoState ;typedef struct FWCfgMemState FWCfgMemState ;typedef struct FWCfgState FWCfgState ; +typedef struct HMAT_Cache_Info HMAT_Cache_Info ;typedef struct HMAT_LB_Info HMAT_LB_Info ;typedef struct HVFX86EmulatorState HVFX86EmulatorState ;typedef struct I2CBus I2CBus ;
include/sysemu/numa.h +3 -0
@@ -35,6 +35,9 @@ struct NumaState {/* NUMA modes HMAT Locality Latency and Bandwidth Information */ HMAT_LB_Info *hmat_lb[HMAT_LB_LEVELS ][HMAT_LB_TYPES ]; + +/* Memory Side Cache Information Structure */ +HMAT_Cache_Info *hmat_cache[MAX_NODES ][MAX_HMAT_CACHE_LEVEL +1 ]; };typedef struct NumaState NumaState ;
include/sysemu/sysemu.h +2 -0
@@ -143,6 +143,8 @@ enum { HMAT_LB_DATA_WRITE_BANDWIDTH = 5, }; +#define MAX_HMAT_CACHE_LEVEL 3 +#define HMAT_LB_LEVELS (HMAT_LB_MEM_CACHE_3RD_LEVEL + 1)#define HMAT_LB_TYPES (HMAT_LB_DATA_WRITE_BANDWIDTH + 1)
Signature · 1 line
2.20.1
Re: [Qemu-devel] [PATCH v6 08/14] hmat acpi: Build Memory Side Cache Information Structure(s)
Quoted 11 lines · On Sun, 7 Jul 2019 22:29:52 +0800 Tao Xu <[email protected]> wrote:
From: Liu Jingqi <[email protected]>
This structure describes memory side cache information for memory proximity domains if the memory side cache is present and the physical device forms the memory side cache.
The software could use this information to effectively place the data in memory to maximize the performance of the system memory that use the memory side cache.Signed-off-by Liu Jingqi <[email protected]>Signed-off-by Tao Xu <[email protected]>
There is what I'll call a paste 'splurge' inline.
Otherwise looks good.
Quoted 107 lines
---
Changes in v6:
- Add descriptions from ACPI 6.3 spec--- hw/acpi/hmat.c | 64 ++++++++++++++++++++++++++++++++++++++++- hw/acpi/hmat.h | 20 +++++++++++++ include/qemu/typedefs.h | 1 + include/sysemu/numa.h | 3 ++ include/sysemu/sysemu.h | 2 ++ 5 files changed, 89 insertions(+), 1 deletion(-)hw/acpi/hmat.c +63
-1@@ -133,14 +133,63 @@ static void build_hmat_lb(GArray *table_data, HMAT_LB_Info *numa_hmat_lb, } } +/* ACPI 6.3: 5.2.27.5 Memory Side Cache Information Structure: Table 5-143 */ +static void build_hmat_cache (GArray *table_data,HMAT_Cache_Info *hmat_cache) +{ +/* +* Cache Attributes: Bits [3:0] – Total Cache Levels +* for this Memory Proximity Domain +*/ +uint32_t cache_attr = hmat_cache->total_levels &0xF ; + +/* Bits [7:4] : Cache Level described in this structure */ + cache_attr |= (hmat_cache->level &0xF ) <<4 ; + +/* Bits [11:8] - Cache Associativity */ + cache_attr |= (hmat_cache->associativity &0xF ) <<8 ; + +/* Bits [15:12] - Write Policy */ + cache_attr |= (hmat_cache->write_policy &0xF ) <<12 ; + +/* Bits [31:16] - Cache Line size in bytes */ + cache_attr |= (hmat_cache->line_size &0xFFFF ) <<16 ; + + cache_attr =cpu_to_le32 (cache_attr); + +/* Type */ +build_append_int_noprefix (table_data,2 ,2 ); +/* Reserved */ +build_append_int_noprefix (table_data,0 ,2 ); +/* Length */ +build_append_int_noprefix (table_data,32 ,4 ); +/* Proximity Domain for the Memory */ +build_append_int_noprefix (table_data, hmat_cache->mem_proximity,4 ); +/* Reserved */ +build_append_int_noprefix (table_data,0 ,4 ); +/* Memory Side Cache Size */ +build_append_int_noprefix (table_data, hmat_cache->size,8 ); +/* Cache Attributes */ +build_append_int_noprefix (table_data, cache_attr,4 ); +/* Reserved */ +build_append_int_noprefix (table_data,0 ,2 ); +/* +* Number of SMBIOS handles (n) +* Linux kernel uses Memory Side Cache Information Structure +* without SMBIOS entries for now, so set Number of SMBIOS handles +* as 0. +*/ +build_append_int_noprefix (table_data,0 ,2 ); +} +/* Build HMAT sub table structures */ static void hmat_build_table_structs (GArray *table_data,NumaState *nstat) {uint16_t flags;uint32_t num_initiator =0 ;uint32_t initiator_pxm[MAX_NODES ]; -int i, hrchy, type; +int i, hrchy, type, level;HMAT_LB_Info *numa_hmat_lb; +HMAT_Cache_Info *numa_hmat_cache;for (i =0 ; i < nstat->num_nodes; i++) { flags =0 ;@@ -174,6 +223,19 @@ static void hmat_build_table_structs(GArray *table_data, NumaState *nstat) } } } + +/* +* ACPI 6.3: 5.2.27.5 Memory Side Cache Information Structure: +* Table 5-143 +*/ +for (i =0 ; i < nstat->num_nodes; i++) { +for (level =0 ; level <=MAX_HMAT_CACHE_LEVEL ; level++) { + numa_hmat_cache = nstat->hmat_cache[i][level]; +if (numa_hmat_cache) { +build_hmat_cache (table_data, numa_hmat_cache); + } + } + } }void build_hmat (GArray *table_data,BIOSLinker *linker,NumaState *nstat)hw/acpi/hmat.h +0
-0@@ -79,6 +79,26 @@ struct HMAT_LB_Info {uint16_t bandwidth[MAX_NODES ][MAX_NODES ];
hw/acpi/hmat.h struct HMAT_LB_Info { · line 89
Quoted 10 lines
hw/acpi/hmat.h +8
-0}; +struct HMAT_Cache_Info { +/* The memory proximity domain to which the memory belongs. */ +uint32_t mem_proximity; +/* Size of memory side cache in bytes. */ +uint64_t size; +/* +* Total cache levels for this memory +* pr#include "hw/acpi/aml-build.h"oximity domain.
:) Happens to us all. (I went back and checked original email in case I'd just inserted that.
Quoted 54 lines
hw/acpi/hmat.h +12
-0+*/ +uint8_t total_levels; +/* Cache level described in this structure. */ +uint8_t level; +/* Cache Associativity: None/Direct Mapped/Comple Cache Indexing */ +uint8_t associativity; +/* Write Policy: None/Write Back(WB)/Write Through(WT) */ +uint8_t write_policy; +/* Cache Line size in bytes. */ + uint16_t line_size; +}; +void build_hmat (GArray *table_data,BIOSLinker *linker,NumaState *nstat);#endif include/qemu/typedefs.h +1
-0@@ -33,6 +33,7 @@ typedef struct FWCfgEntry FWCfgEntry;typedef struct FWCfgIoState FWCfgIoState ;typedef struct FWCfgMemState FWCfgMemState ;typedef struct FWCfgState FWCfgState ; +typedef struct HMAT_Cache_Info HMAT_Cache_Info ;typedef struct HMAT_LB_Info HMAT_LB_Info ;typedef struct HVFX86EmulatorState HVFX86EmulatorState ;typedef struct I2CBus I2CBus ;include/sysemu/numa.h +3
-0@@ -35,6 +35,9 @@ struct NumaState {/* NUMA modes HMAT Locality Latency and Bandwidth Information */ HMAT_LB_Info *hmat_lb[HMAT_LB_LEVELS ][HMAT_LB_TYPES ]; + +/* Memory Side Cache Information Structure */ +HMAT_Cache_Info *hmat_cache[MAX_NODES ][MAX_HMAT_CACHE_LEVEL +1 ]; };typedef struct NumaState NumaState ;include/sysemu/sysemu.h +2
-0@@ -143,6 +143,8 @@ enum { HMAT_LB_DATA_WRITE_BANDWIDTH = 5, }; +#define MAX_HMAT_CACHE_LEVEL 3 +#define HMAT_LB_LEVELS (HMAT_LB_MEM_CACHE_3RD_LEVEL + 1)#define HMAT_LB_TYPES (HMAT_LB_DATA_WRITE_BANDWIDTH + 1)
Re: [Qemu-devel] [PATCH v6 08/14] hmat acpi: Build Memory Side Cache Information Structure(s)
Quoted 130 lines · Jonathan Cameron
Quoted 11 lines · On Sun, 7 Jul 2019 22:29:52 +0800 Tao Xu <[email protected]> wrote:
From: Liu Jingqi <[email protected]>
This structure describes memory side cache information for memory proximity domains if the memory side cache is present and the physical device forms the memory side cache.
The software could use this information to effectively place the data in memory to maximize the performance of the system memory that use the memory side cache.Signed-off-by Liu Jingqi <[email protected]>Signed-off-by Tao Xu <[email protected]>There is what I'll call a paste 'splurge' inline.
Otherwise looks good.
Reviewed-by Jonathan Cameron <[email protected]>Quoted 109 lines
---
Changes in v6:
- Add descriptions from ACPI 6.3 spec--- hw/acpi/hmat.c | 64 ++++++++++++++++++++++++++++++++++++++++- hw/acpi/hmat.h | 20 +++++++++++++ include/qemu/typedefs.h | 1 + include/sysemu/numa.h | 3 ++ include/sysemu/sysemu.h | 2 ++ 5 files changed, 89 insertions(+), 1 deletion(-)hw/acpi/hmat.c +63
-1@@ -133,14 +133,63 @@ static void build_hmat_lb(GArray *table_data, HMAT_LB_Info *numa_hmat_lb, } } +/* ACPI 6.3: 5.2.27.5 Memory Side Cache Information Structure: Table 5-143 */ +static void build_hmat_cache (GArray *table_data,HMAT_Cache_Info *hmat_cache) +{ +/* +* Cache Attributes: Bits [3:0] – Total Cache Levels +* for this Memory Proximity Domain +*/ +uint32_t cache_attr = hmat_cache->total_levels &0xF ; + +/* Bits [7:4] : Cache Level described in this structure */ + cache_attr |= (hmat_cache->level &0xF ) <<4 ; + +/* Bits [11:8] - Cache Associativity */ + cache_attr |= (hmat_cache->associativity &0xF ) <<8 ; + +/* Bits [15:12] - Write Policy */ + cache_attr |= (hmat_cache->write_policy &0xF ) <<12 ; + +/* Bits [31:16] - Cache Line size in bytes */ + cache_attr |= (hmat_cache->line_size &0xFFFF ) <<16 ; + + cache_attr =cpu_to_le32 (cache_attr); + +/* Type */ +build_append_int_noprefix (table_data,2 ,2 ); +/* Reserved */ +build_append_int_noprefix (table_data,0 ,2 ); +/* Length */ +build_append_int_noprefix (table_data,32 ,4 ); +/* Proximity Domain for the Memory */ +build_append_int_noprefix (table_data, hmat_cache->mem_proximity,4 ); +/* Reserved */ +build_append_int_noprefix (table_data,0 ,4 ); +/* Memory Side Cache Size */ +build_append_int_noprefix (table_data, hmat_cache->size,8 ); +/* Cache Attributes */ +build_append_int_noprefix (table_data, cache_attr,4 ); +/* Reserved */ +build_append_int_noprefix (table_data,0 ,2 ); +/* +* Number of SMBIOS handles (n) +* Linux kernel uses Memory Side Cache Information Structure +* without SMBIOS entries for now, so set Number of SMBIOS handles +* as 0. +*/ +build_append_int_noprefix (table_data,0 ,2 ); +} +/* Build HMAT sub table structures */ static void hmat_build_table_structs (GArray *table_data,NumaState *nstat) {uint16_t flags;uint32_t num_initiator =0 ;uint32_t initiator_pxm[MAX_NODES ]; -int i, hrchy, type; +int i, hrchy, type, level;HMAT_LB_Info *numa_hmat_lb; +HMAT_Cache_Info *numa_hmat_cache;for (i =0 ; i < nstat->num_nodes; i++) { flags =0 ;@@ -174,6 +223,19 @@ static void hmat_build_table_structs(GArray *table_data, NumaState *nstat) } } } + +/* +* ACPI 6.3: 5.2.27.5 Memory Side Cache Information Structure: +* Table 5-143 +*/ +for (i =0 ; i < nstat->num_nodes; i++) { +for (level =0 ; level <=MAX_HMAT_CACHE_LEVEL ; level++) { + numa_hmat_cache = nstat->hmat_cache[i][level]; +if (numa_hmat_cache) { +build_hmat_cache (table_data, numa_hmat_cache); + } + } + } }void build_hmat (GArray *table_data,BIOSLinker *linker,NumaState *nstat)hw/acpi/hmat.h +0
-0@@ -79,6 +79,26 @@ struct HMAT_LB_Info {uint16_t bandwidth[MAX_NODES ][MAX_NODES ]; };
Quoted 12 lines
hw/acpi/hmat.h struct HMAT_LB_Info { · line 89
Quoted 8 lines
hw/acpi/hmat.h +8
-0+struct HMAT_Cache_Info { +/* The memory proximity domain to which the memory belongs. */ +uint32_t mem_proximity; +/* Size of memory side cache in bytes. */ +uint64_t size; +/* +* Total cache levels for this memory +* pr#include "hw/acpi/aml-build.h"oximity domain. :) Happens to us all. (I went back and checked original email in case I'd just inserted that.
Thank you for pointing it. Maybe I make a mistake here when I rebase it. I will correct it.
Quoted 56 lines
Quoted 54 lines
hw/acpi/hmat.h +12
-0+*/ +uint8_t total_levels; +/* Cache level described in this structure. */ +uint8_t level; +/* Cache Associativity: None/Direct Mapped/Comple Cache Indexing */ +uint8_t associativity; +/* Write Policy: None/Write Back(WB)/Write Through(WT) */ +uint8_t write_policy; +/* Cache Line size in bytes. */ + uint16_t line_size; +}; +void build_hmat (GArray *table_data,BIOSLinker *linker,NumaState *nstat);#endif include/qemu/typedefs.h +1
-0@@ -33,6 +33,7 @@ typedef struct FWCfgEntry FWCfgEntry;typedef struct FWCfgIoState FWCfgIoState ;typedef struct FWCfgMemState FWCfgMemState ;typedef struct FWCfgState FWCfgState ; +typedef struct HMAT_Cache_Info HMAT_Cache_Info ;typedef struct HMAT_LB_Info HMAT_LB_Info ;typedef struct HVFX86EmulatorState HVFX86EmulatorState ;typedef struct I2CBus I2CBus ;include/sysemu/numa.h +3
-0@@ -35,6 +35,9 @@ struct NumaState {/* NUMA modes HMAT Locality Latency and Bandwidth Information */ HMAT_LB_Info *hmat_lb[HMAT_LB_LEVELS ][HMAT_LB_TYPES ]; + +/* Memory Side Cache Information Structure */ +HMAT_Cache_Info *hmat_cache[MAX_NODES ][MAX_HMAT_CACHE_LEVEL +1 ]; };typedef struct NumaState NumaState ;include/sysemu/sysemu.h +2
-0@@ -143,6 +143,8 @@ enum { HMAT_LB_DATA_WRITE_BANDWIDTH = 5, }; +#define MAX_HMAT_CACHE_LEVEL 3 +#define HMAT_LB_LEVELS (HMAT_LB_MEM_CACHE_3RD_LEVEL + 1)#define HMAT_LB_TYPES (HMAT_LB_DATA_WRITE_BANDWIDTH + 1)
PATCH v6 9/14 numa: Extend the CLI to provide memory latency and bandwidth information
In reply to Tao XuFrom: Liu Jingqi <[email protected]>
Add -numa hmat-lb option to provide System Locality Latency and Bandwidth Information. These memory attributes help to build System Locality Latency and Bandwidth Information Structure(s) in ACPI Heterogeneous Memory Attribute Table (HMAT).
---
Changes in v6:
- Update the describes in ACPI 6.3(The entry base unit for latency is in picoseconds)
--- numa.c | 127 ++++++++++++++++++++++++++++++++++++++++++++++++ qapi/misc.json | 103 ++++++++++++++++++++++++++++++++++++++- qemu-options.hx | 45 ++++++++++++++++- 3 files changed, 272 insertions(+), 3 deletions(-)
numa.c +127 -0
@@ -40,6 +40,7 @@#include "qemu/option.h" #include "qemu/config-file.h" #include "qemu/cutils.h" +#include "hw/acpi/hmat.h" QemuOptsList qemu_numa_opts = { .name ="numa" ,
@@ -186,6 +187,126 @@ void parse_numa_distance(MachineState *ms, NumaDistOptions *dist, Error **errp) ms->numa_state->have_numa_distance = true; } +static void parse_numa_hmat_lb (MachineState *ms,NumaHmatLBOptions *node, +Error **errp) +{ +int nb_numa_nodes = ms->numa_state->num_nodes; +NodeInfo *numa_info = ms->numa_state->nodes; +HMAT_LB_Info *hmat_lb =NULL ; + +if (node->data_type <=HMATLB_DATA_TYPE_WRITE_LATENCY ) { +if (!node->has_latency) { +error_setg (errp,"Missing 'latency' option." ); +return ; + } +if (node->has_bandwidth) { +error_setg (errp,"Invalid option 'bandwidth' since " +"the data type is latency." ); +return ; + } +if (node->has_base_bw) { +error_setg (errp,"Invalid option 'base_bw' since " +"the data type is latency." ); +return ; + } + } + +if (node->data_type >=HMATLB_DATA_TYPE_ACCESS_BANDWIDTH ) { +if (!node->has_bandwidth) { +error_setg (errp,"Missing 'bandwidth' option." ); +return ; + } +if (node->has_latency) { +error_setg (errp,"Invalid option 'latency' since " +"the data type is bandwidth." ); +return ; + } +if (node->has_base_lat) { +error_setg (errp,"Invalid option 'base_lat' since " +"the data type is bandwidth." ); +return ; + } + } + +if (node->initiator >= nb_numa_nodes) { +error_setg (errp,"Invalid initiator=%" + PRIu16", it should be less than %d." , + node->initiator, nb_numa_nodes); +return ; + } +if (!numa_info[node->initiator].has_cpu) { +error_setg (errp,"Invalid initiator=%" + PRIu16", it isn't an initiator proximity domain." , + node->initiator); +return ; + } + +if (node->target >= nb_numa_nodes) { +error_setg (errp,"Invalid target=%" + PRIu16", it should be less than %d." , + node->target, nb_numa_nodes); +return ; + } +if (!numa_info[node->target].initiator_valid) { +error_setg (errp,"Invalid target=%" + PRIu16", it hasn't a valid initiator proximity domain." , + node->target); +return ; + } + +if (node->has_latency) { + hmat_lb = ms->numa_state->hmat_lb[node->hierarchy][node->data_type]; + +if (!hmat_lb) { + hmat_lb =g_malloc0 (sizeof (*hmat_lb)); + ms->numa_state->hmat_lb[node->hierarchy][node->data_type] = hmat_lb; + }else if (hmat_lb->latency[node->initiator][node->target]) { +error_setg (errp,"Duplicate configuration of the latency for " +"initiator=%" PRIu16" and target=%" PRIu16"." , + node->initiator, node->target); +return ; + } + +/* Only the first time of setting the base unit is valid. */ +if ((hmat_lb->base_lat ==0 ) && (node->has_base_lat)) { + hmat_lb->base_lat = node->base_lat; + } + + hmat_lb->latency[node->initiator][node->target] = node->latency; + } + +if (node->has_bandwidth) { + hmat_lb = ms->numa_state->hmat_lb[node->hierarchy][node->data_type]; + +if (!hmat_lb) { + hmat_lb =g_malloc0 (sizeof (*hmat_lb)); + ms->numa_state->hmat_lb[node->hierarchy][node->data_type] = hmat_lb; + }else if (hmat_lb->bandwidth[node->initiator][node->target]) { +error_setg (errp,"Duplicate configuration of the bandwidth for " +"initiator=%" PRIu16" and target=%" PRIu16"." , + node->initiator, node->target); +return ; + } + +/* Only the first time of setting the base unit is valid. */ +if (hmat_lb->base_bw ==0 ) { +if (!node->has_base_bw) { +error_setg (errp,"Missing 'base-bw' option" ); +return ; + }else { + hmat_lb->base_bw = node->base_bw; + } + } + + hmat_lb->bandwidth[node->initiator][node->target] = node->bandwidth; + } + +if (hmat_lb) { + hmat_lb->hierarchy = node->hierarchy; + hmat_lb->data_type = node->data_type; + } +} +static void set_numa_options (MachineState *ms,NumaOptions *object,Error **errp) {
@@ -225,6 +346,12 @@ void set_numa_options(MachineState *ms, NumaOptions *object, Error **errp)machine_set_cpu_numa_node (ms,qapi_NumaCpuOptions_base (&object->u.cpu), &err);break ; +case NUMA_OPTIONS_TYPE_HMAT_LB : +parse_numa_hmat_lb (ms, &object->u.hmat_lb, &err); +if (err) { + goto end; + } +break ;default :abort (); }
qapi/misc.json +101 -2
124 lines not on this page · raw message
qemu-options.hx +44 -1
66 lines not on this page · raw message
Signature · 1 line
2.20.1
PATCH v6 10/14 numa: Extend the CLI to provide memory side cache information
In reply to Tao XuFrom: Liu Jingqi <[email protected]>
Add -numa hmat-cache option to provide Memory Side Cache Information. These memory attributes help to build Memory Side Cache Information Structure(s) in ACPI Heterogeneous Memory Attribute Table (HMAT).
---
Changes in v6:
- Add add reference to ACPI 6.3 spec (Igor)
--- numa.c | 68 +++++++++++++++++++++++++++++++++++++++++ qapi/misc.json | 81 +++++++++++++++++++++++++++++++++++++++++++++++-- qemu-options.hx | 16 ++++++++-- 3 files changed, 161 insertions(+), 4 deletions(-)
numa.c +68 -0
@@ -307,6 +307,68 @@ static void parse_numa_hmat_lb(MachineState *ms, NumaHmatLBOptions *node, } } +static +void parse_numa_hmat_cache (MachineState *ms,NumaHmatCacheOptions *node, +Error **errp) +{ +int nb_numa_nodes = ms->numa_state->num_nodes; +HMAT_Cache_Info *hmat_cache =NULL ; + +if (node->node_id >= nb_numa_nodes) { +error_setg (errp,"Invalid node-id=%" PRIu32 +", it should be less than %d." , + node->node_id, nb_numa_nodes); +return ; + } + +if (node->total >MAX_HMAT_CACHE_LEVEL ) { +error_setg (errp,"Invalid total=%" PRIu8 +", it should be less than or equal to %d." , + node->total,MAX_HMAT_CACHE_LEVEL ); +return ; + } +if (node->level > node->total) { +error_setg (errp,"Invalid level=%" PRIu8 +", it should be less than or equal to" +" total=%" PRIu8"." , + node->level, node->total); +return ; + } +if (ms->numa_state->hmat_cache[node->node_id][node->level]) { +error_setg (errp,"Duplicate configuration of the side cache for " +"node-id=%" PRIu32" and level=%" PRIu8"." , + node->node_id, node->level); +return ; + } + +if ((node->level >1 ) && + ms->numa_state->hmat_cache[node->node_id][node->level -1 ] && + (node->size >= + ms->numa_state->hmat_cache[node->node_id][node->level -1 ]->size)) { +error_setg (errp,"Invalid size=0x%" PRIx64 +", the size of level=%" PRIu8 +" should be less than the size(0x%" PRIx64 +") of level=%" PRIu8"." , + node->size, node->level, + ms->numa_state->hmat_cache[node->node_id] + [node->level -1 ]->size, + node->level -1 ); +return ; + } + + hmat_cache =g_malloc0 (sizeof (*hmat_cache)); + + hmat_cache->mem_proximity = node->node_id; + hmat_cache->size = node->size; + hmat_cache->total_levels = node->total; + hmat_cache->level = node->level; + hmat_cache->associativity = node->assoc; + hmat_cache->write_policy = node->policy; + hmat_cache->line_size = node->line; + + ms->numa_state->hmat_cache[node->node_id][node->level] = hmat_cache; +} +static void set_numa_options (MachineState *ms,NumaOptions *object,Error **errp) {
@@ -352,6 +414,12 @@ void set_numa_options(MachineState *ms, NumaOptions *object, Error **errp) goto end; }break ; +case NUMA_OPTIONS_TYPE_HMAT_CACHE : +parse_numa_hmat_cache (ms, &object->u.hmat_cache, &err); +if (err) { + goto end; + } +break ;default :abort (); }
qapi/misc.json +79 -2
102 lines not on this page · raw message
qemu-options.hx +14 -2
@@ -164,7 +164,8 @@ DEF("numa", HAS_ARG, QEMU_OPTION_numa, "-numa node[,memdev=id][,cpus=firstcpu[-lastcpu]][,nodeid=node][,initiator=node]\n" "-numa dist,src=source,dst=destination,val=distance\n" "-numa cpu,node-id=node[,socket-id=x][,core-id=y][,thread-id=z]\n" - "-numa hmat-lb,initiator=node,target=node,hierarchy=memory|last-level|first-level|second-level|third-level,data-type=access-latency|read-latency|write-latency[,base-lat=blat][,base-bw=bbw][,latency=lat][,bandwidth=bw]\n", + "-numa hmat-lb,initiator=node,target=node,hierarchy=memory|last-level|first-level|second-level|third-level,data-type=access-latency|read-latency|write-latency[,base-lat=blat][,base-bw=bbw][,latency=lat][,bandwidth=bw]\n" + "-numa hmat-cache,node-id=node,size=size,total=total,level=level[,assoc=none|direct|complex][,policy=none|write-back|write-through][,line=size]\n", QEMU_ARCH_ALL) STEXI @item -numa node[,mem=@var{size}][,cpus=@var{firstcpu}[-@var{lastcpu}]][,nodeid=@var{node}][,initiator=@var{initiator}]
@@ -172,6 +173,7 @@ STEXI @itemx -numa dist,src=@var{source},dst=@var{destination},val=@var{distance} @itemx -numa cpu,node-id=@var{node}[,socket-id=@var{x}][,core-id=@var{y}][,thread-id=@var{z}] @itemx -numa hmat-lb,initiator=@var{node},target=@var{node},hierarchy=@var{str},data-type=@var{str}[,base-lat=@var{blat}][,base-bw=@var{bbw}][,latency=@var{lat}][,bandwidth=@var{bw}] +@itemx -numa hmat-cache,node-id=@var{node},size=@var{size},total=@var{total},level=@var{level}[,assoc=@var{str}][,policy=@var{str}][,line=@var{size}] @findex -numa Define a NUMA node and assign RAM and VCPUs to it. Set the NUMA distance from a source node to a destination node.
@@ -274,11 +276,19 @@ Note: Due to the minimum matrix value entry value being 10, the base unit corres to a value of 10. And @var{blat} or @var{bbw} should be an integer. @var{lat} or @var{bw} is the latency/bandwidth value. +In @samp{hmat-cache} option, @var{node-id} is the NUMA-id of the memory belongs. +@var{size} is the size of memory side cache in bytes. @var{total} is the total cache levels. +@var{level} is the cache level described in this structure. @var{assoc} is the cache associativity. +"none/direct-mapped/complex(complex cache indexing). @var{policy} is the write policy. +@var{line} is the cache Line size in bytes. + For example, the following option assigns NUMA node 0 and 1. Node 0 has 2 cpus and a ram, node 1 has only a ram. The processors in node 0 access memory in node 0 with access-latency 5 picoseconds(base latency is 10), access-bandwidth 5 MB/s(base latency is 20); The processors in NUMA node 0 access memory in NUMA node 1 with access-latency 10 -picoseconds(base latency is 10), access-bandwidth 10 MB/s(base latency is 20): +picoseconds(base latency is 10), access-bandwidth 10 MB/s(base latency is 20). +And for memory side cache information, NUMA node 0 and 1 both have 1 level memory +cache, size is 0x20000 bytes, policy is write-back, the cache Line size is 8 bytes: @example -m 2G \ -object memory-backend-ram,size=1024M,policy=bind,host-nodes=0,id=ram-node0 -numa node,nodeid=0,memdev=ram-node0 \
@@ -290,6 +300,8 @@ picoseconds(base latency is 10), access-bandwidth 10 MB/s(base latency is 20): -numa hmat-lb,initiator=0,target=0,hierarchy=memory,data-type=access-bandwidth,base-bw=20,bandwidth=5 \ -numa hmat-lb,initiator=0,target=1,hierarchy=memory,data-type=access-latency,base-lat=10,latency=10 \ -numa hmat-lb,initiator=0,target=1,hierarchy=memory,data-type=access-bandwidth,base-bw=20,bandwidth=10 \ +-numa hmat-cache,node-id=0,size=0x20000,total=1,level=1,assoc=direct,policy=write-back,line=8 \ +-numa hmat-cache,node-id=1,size=0x20000,total=1,level=1,assoc=direct,policy=write-back,line=8 \ @end example ETEXI
Signature · 1 line
2.20.1
PATCH v6 11/14 acpi: introduce aml_build_runtime_buf for NFIT generalizations
In reply to Tao XuMove the _FIT method buff Aml-build codes into aml_build_runtime_buf(), and then NFIT and HMAT can both use it.
---
Changes in v6:
- Add more commit message and change the function name
--- hw/acpi/nvdimm.c | 49 +++++++++++++++++++++++++++-------------- include/hw/mem/nvdimm.h | 6 +++++ 2 files changed, 38 insertions(+), 17 deletions(-)
hw/acpi/nvdimm.c +32 -17
@@ -1140,12 +1140,11 @@ static void nvdimm_build_device_dsm(Aml *dev, uint32_t handle)static void nvdimm_build_fit (Aml *dev) { -Aml *method, *pkg, *buf, *buf_size, *offset, *call_result; -Aml *whilectx, *ifcond, *ifctx, *elsectx, *fit; +Aml *method, *pkg, *buf, *buf_name, *buf_size, *call_result; buf =aml_local (0 ); buf_size =aml_local (1 ); - fit =aml_local (2 ); + buf_name =aml_local (2 );aml_append (dev,aml_name_decl (NVDIMM_DSM_RFIT_STATUS ,aml_int (0 )));
@@ -1164,6 +1163,22 @@ static void nvdimm_build_fit(Aml *dev)aml_int (1 )/* Revision 1 */ ,aml_int (0x1 )/* Read FIT */ , pkg, aml_int(NVDIMM_QEMU_RSVD_HANDLE_ROOT)); + +aml_build_runtime_buf (method, buf, buf_size, + call_result, buf_name, dev, +"RFIT" ,"_FIT" , +NVDIMM_DSM_RET_STATUS_SUCCESS , +NVDIMM_DSM_RET_STATUS_FIT_CHANGED ); +} + +void aml_build_runtime_buf (Aml *method,Aml *buf,Aml *buf_size, +Aml *call_result,Aml *buf_name,Aml *dev, +const char *help_function,const char *method_name, +int ret_status_success, +int ret_status_changed) +{ +Aml *offset, *whilectx, *ifcond, *ifctx, *elsectx; +aml_append (method,aml_store (call_result, buf));/* handle _DSM result. */
@@ -1174,7 +1189,7 @@ static void nvdimm_build_fit(Aml *dev) aml_name(NVDIMM_DSM_RFIT_STATUS)));/* if something is wrong during _DSM. */ - ifcond =aml_equal (aml_int (NVDIMM_DSM_RET_STATUS_SUCCESS ), + ifcond =aml_equal (aml_int (ret_status_success),aml_name ("STAU" )); ifctx =aml_if (aml_lnot (ifcond));aml_append (ifctx,aml_return (aml_buffer (0 ,NULL )));
@@ -1185,7 +1200,7 @@ static void nvdimm_build_fit(Aml *dev)aml_int (4 )/* the size of "STAU" */ , buf_size)); -/* if we read the end of fit. */ +/* if we read the end of buff method. */ ifctx =aml_if (aml_equal (buf_size,aml_int (0 )));aml_append (ifctx,aml_return (aml_buffer (0 ,NULL )));aml_append (method, ifctx);
@@ -1196,38 +1211,38 @@ static void nvdimm_build_fit(Aml *dev)aml_append (method,aml_return (aml_name ("BUFF" )));aml_append (dev, method); -/* build _FIT. */ - method =aml_method ("_FIT" ,0 ,AML_SERIALIZED ); +/* build buff method. */ + method =aml_method (method_name,0 ,AML_SERIALIZED ); offset =aml_local (3 ); -aml_append (method,aml_store (aml_buffer (0 ,NULL ), fit)); +aml_append (method,aml_store (aml_buffer (0 ,NULL ), buf_name));aml_append (method,aml_store (aml_int (0 ), offset)); whilectx =aml_while (aml_int (1 )); -aml_append (whilectx,aml_store (aml_call1 ("RFIT" , offset), buf)); +aml_append (whilectx,aml_store (aml_call1 (help_function, offset), buf));aml_append (whilectx,aml_store (aml_sizeof (buf), buf_size));/* -* if fit buffer was changed during RFIT, read from the beginning -* again. +* if buffer was changed during runtime, +* read from the beginning again. */ ifctx =aml_if (aml_equal (aml_name (NVDIMM_DSM_RFIT_STATUS ), -aml_int (NVDIMM_DSM_RET_STATUS_FIT_CHANGED ))); -aml_append (ifctx,aml_store (aml_buffer (0 ,NULL ), fit)); +aml_int (ret_status_changed))); +aml_append (ifctx,aml_store (aml_buffer (0 ,NULL ), buf_name));aml_append (ifctx,aml_store (aml_int (0 ), offset));aml_append (whilectx, ifctx); elsectx =aml_else (); -/* finish fit read if no data is read out. */ +/* finish buff read if no data is read out. */ ifctx =aml_if (aml_equal (buf_size,aml_int (0 ))); -aml_append (ifctx,aml_return (fit)); +aml_append (ifctx,aml_return (buf_name));aml_append (elsectx, ifctx);/* update the offset. */ aml_append (elsectx,aml_add (offset, buf_size, offset)); -/* append the data we read out to the fit buffer. */ -aml_append (elsectx,aml_concatenate (fit, buf, fit)); +/* append the data we read out to the buffer. */ +aml_append (elsectx,aml_concatenate (buf_name, buf, buf_name));aml_append (whilectx, elsectx);aml_append (method, whilectx);
include/hw/mem/nvdimm.h +6 -0
@@ -25,6 +25,7 @@#include "hw/mem/pc-dimm.h" #include "hw/acpi/bios-linker-loader.h" +#include "hw/acpi/aml-build.h" #define NVDIMM_DEBUG 0#define nvdimm_debug (fmt, ...) \
@@ -150,4 +151,9 @@ void nvdimm_build_acpi(GArray *table_offsets, GArray *table_data, uint32_t ram_slots);void nvdimm_plug (NVDIMMState *state);void nvdimm_acpi_plug_cb (HotplugHandler *hotplug_dev,DeviceState *dev); +void aml_build_runtime_buf (Aml *method,Aml *buf,Aml *buf_size, +Aml *call_result,Aml *buf_name,Aml *dev, +const char *help_function,const char *method_name, +int ret_status_success, +int ret_status_changed);#endif
Signature · 1 line
2.20.1
PATCH v6 12/14 hmat acpi: Implement _HMA method to update HMAT at runtime
In reply to Tao XuFrom: Liu Jingqi <[email protected]>
OSPM evaluates HMAT only during system initialization. Any changes to the HMAT state at runtime or information regarding HMAT for hot plug are communicated using _HMA method.
_HMA is an optional object that enables the platform to provide the OS with updated Heterogeneous Memory Attributes information at runtime. _HMA provides OSPM with the latest HMAT in entirety overriding existing HMAT.
---
Changes in v6:
- move AcpiHmaState from PCMachineState to MachineState to make HMAT more generalic (Igor)
- use build_acpi_aml_common() introduced in patch 10/11 to simplify hmat_build_aml (Igor)
- Add _HMA only qemu use hmat-lb or hmat-cache
--- hw/acpi/hmat.c | 297 ++++++++++++++++++++++++++++++++++++++++++ hw/acpi/hmat.h | 68 ++++++++++ hw/core/machine.c | 4 + hw/i386/acpi-build.c | 4 + hw/i386/pc_piix.c | 6 + hw/i386/pc_q35.c | 6 + include/sysemu/numa.h | 5 + numa.c | 10 ++ 8 files changed, 400 insertions(+)
hw/acpi/hmat.c +297 -0
@@ -27,6 +27,8 @@#include "qemu/osdep.h" #include "sysemu/numa.h" #include "hw/acpi/hmat.h" +#include "hw/mem/nvdimm.h" +#include "hw/nvram/fw_cfg.h" /* * ACPI 6.3:
@@ -238,6 +240,270 @@ static void hmat_build_table_structs(GArray *table_data, NumaState *nstat) } } +static uint64_t +hmat_hma_method_read (void *opaque,hwaddr addr,unsigned size) +{ +printf ("BUG: we never read _HMA IO Port.\n" ); +return 0 ; +} + +/* _HMA Method: read HMA data. */ +static void hmat_handle_hma_method (AcpiHmaState *state, +HmatHmamIn *in,hwaddr hmam_mem_addr) +{ +HmatHmaBuffer *hma_buf = &state->hma_buf; +HmatHmamOut *read_hma_out; +GArray *hma; +uint32_t read_len =0 , ret_status; +int size; + +if (in !=NULL ) { +le32_to_cpus (&in->offset); + } + + hma = hma_buf->hma; +if (in->offset > hma->len) { + ret_status =HMAM_RET_STATUS_INVALID ; + goto exit; + } + +/* It is the first time to read HMA. */ +if (!in->offset) { + hma_buf->dirty = false; + }else if (hma_buf->dirty) { +/* HMA has been changed during Reading HMA. */ + ret_status =HMAM_RET_STATUS_HMA_CHANGED ; + goto exit; + } + + ret_status =HMAM_RET_STATUS_SUCCESS ; + read_len =MIN (hma->len - in->offset, +HMAM_MEMORY_SIZE -2 *sizeof (uint32_t )); +exit: + size =sizeof (HmatHmamOut) + read_len; + read_hma_out =g_malloc (size); + + read_hma_out->len =cpu_to_le32 (size); + read_hma_out->ret_status =cpu_to_le32 (ret_status); +memcpy (read_hma_out->data, hma->data + in->offset, read_len); + +cpu_physical_memory_write (hmam_mem_addr, read_hma_out, size); + +g_free (read_hma_out); +} + +static void +hmat_hma_method_write (void *opaque,hwaddr addr,uint64_t val,unsigned size) +{ +AcpiHmaState *state = opaque; +hwaddr hmam_mem_addr = val; +HmatHmamIn *in; + + in =g_new (HmatHmamIn,1 ); +cpu_physical_memory_read (hmam_mem_addr, in,sizeof (*in)); + +hmat_handle_hma_method (state, in, hmam_mem_addr); +} + +static const MemoryRegionOps hmat_hma_method_ops = { + .read = hmat_hma_method_read, + .write = hmat_hma_method_write, + .endianness =DEVICE_LITTLE_ENDIAN , + .valid = { + .min_access_size =4 , + .max_access_size =4 , + }, +}; + +static void hmat_init_hma_buffer (HmatHmaBuffer *hma_buf) +{ + hma_buf->hma =g_array_new (false, true/* clear */ ,1 ); +} + +static uint8_t hmat_acpi_table_checksum (uint8_t *buffer,uint32_t length) +{ +uint8_t sum =0 ; +uint8_t *end = buffer + length; + +while (buffer < end) { + sum = (uint8_t ) (sum + *(buffer++)); + } +return (uint8_t )(0 - sum); +} + +static void hmat_build_header (AcpiTableHeader *h, +const char *sig,int len,uint8_t rev, +const char *oem_id,const char *oem_table_id) +{ +memcpy (&h->signature, sig,4 ); + h->length =cpu_to_le32 (len); + h->revision = rev; + +if (oem_id) { +strncpy ((char *)h->oem_id, oem_id,sizeof h->oem_id); + }else { +memcpy (h->oem_id,ACPI_BUILD_APPNAME6 ,6 ); + } + +if (oem_table_id) { +strncpy ((char *)h->oem_table_id, oem_table_id,sizeof (h->oem_table_id)); + }else { +memcpy (h->oem_table_id,ACPI_BUILD_APPNAME4 ,4 ); +memcpy (h->oem_table_id +4 , sig,4 ); + } + + h->oem_revision =cpu_to_le32 (1 ); +memcpy (h->asl_compiler_id,ACPI_BUILD_APPNAME4 ,4 ); + h->asl_compiler_revision =cpu_to_le32 (1 ); + +/* Caculate the checksum of acpi table. */ + h->checksum =0 ; + h->checksum =hmat_acpi_table_checksum ((uint8_t *)h, len); +} + +static void hmat_build_hma_buffer (NumaState *nstat) +{ +HmatHmaBuffer *hma_buf = &(nstat->acpi_hma_state->hma_buf); + +/* Free the old hma buffer before new allocation. */ +g_array_free (hma_buf->hma, true); + + hma_buf->hma =g_array_new (false, true/* clear */ ,1 ); +acpi_data_push (hma_buf->hma,40 ); + +/* build HMAT in a given buffer. */ +hmat_build_table_structs (hma_buf->hma, nstat); +hmat_build_header ((void *)hma_buf->hma->data, +"HMAT" , hma_buf->hma->len,2 ,NULL ,NULL ); + hma_buf->dirty = true; +} + +static void hmat_build_common_aml (Aml *dev) +{ +Aml *method, *ifctx, *hmam_mem; +Aml *unsupport; +Aml *pckg, *pckg_index, *pckg_buf, *field; +Aml *hmam_out_buf, *hmam_out_buf_size; +uint8_t byte_list[1 ]; + + method =aml_method (HMA_COMMON_METHOD ,1 ,AML_SERIALIZED ); + hmam_mem =aml_local (6 ); + hmam_out_buf =aml_local (7 ); + +aml_append (method,aml_store (aml_name (HMAM_ACPI_MEM_ADDR ), hmam_mem)); + +/* map _HMA memory and IO into ACPI namespace. */ +aml_append (method,aml_operation_region (HMAM_IOPORT ,AML_SYSTEM_IO , +aml_int (HMAM_ACPI_IO_BASE ),HMAM_ACPI_IO_LEN )); +aml_append (method,aml_operation_region (HMAM_MEMORY , +AML_SYSTEM_MEMORY , hmam_mem,HMAM_MEMORY_SIZE )); + +/* +* _HMAC notifier: +* HMAM_NOTIFY: write the address of DSM memory and notify QEMU to +* emulate the access. +* +* It is the IO port so that accessing them will cause VM-exit, the +* control will be transferred to QEMU. +*/ + field =aml_field (HMAM_IOPORT ,AML_DWORD_ACC ,AML_NOLOCK , +AML_PRESERVE ); +aml_append (field,aml_named_field (HMAM_NOTIFY , +sizeof (uint32_t ) *BITS_PER_BYTE )); +aml_append (method, field); + +/* +* _HMAC input: +* HMAM_OFFSET: store the current offset of _HMA buffer. +* +* They are RAM mapping on host so that these accesses never cause VMExit. +*/ + field =aml_field (HMAM_MEMORY ,AML_DWORD_ACC ,AML_NOLOCK , +AML_PRESERVE ); +aml_append (field,aml_named_field (HMAM_OFFSET , +sizeof (typeof_field (HmatHmamIn, offset)) *BITS_PER_BYTE )); +aml_append (method, field); + +/* +* _HMAC output: +* HMAM_OUT_BUF_SIZE: the size of the buffer filled by QEMU. +* HMAM_OUT_BUF: the buffer QEMU uses to store the result. +* +* Since the page is reused by both input and out, the input data +* will be lost after storing new result into ODAT so we should fetch +* all the input data before writing the result. +*/ + field =aml_field (HMAM_MEMORY ,AML_DWORD_ACC ,AML_NOLOCK , +AML_PRESERVE ); +aml_append (field,aml_named_field (HMAM_OUT_BUF_SIZE , +sizeof (typeof_field (HmatHmamOut, len)) *BITS_PER_BYTE )); +aml_append (field,aml_named_field (HMAM_OUT_BUF , + (sizeof (HmatHmamOut) -sizeof (uint32_t )) *BITS_PER_BYTE )); +aml_append (method, field); + +/* +* do not support any method if HMA memory address has not been +* patched. +*/ + unsupport =aml_if (aml_equal (hmam_mem,aml_int (0x0 ))); + byte_list[0 ] =HMAM_RET_STATUS_UNSUPPORT ; +aml_append (unsupport,aml_return (aml_buffer (1 , byte_list))); +aml_append (method, unsupport); + +/* The parameter (Arg0) of _HMAC is a package which contains a buffer. */ + pckg =aml_arg (0 ); + ifctx =aml_if (aml_and (aml_equal (aml_object_type (pckg), +aml_int (4 /* Package */ ))/* It is a Package? */ , +aml_equal (aml_sizeof (pckg),aml_int (1 ))/* 1 element */ , +NULL )); + + pckg_index =aml_local (2 ); + pckg_buf =aml_local (3 ); +aml_append (ifctx,aml_store (aml_index (pckg,aml_int (0 )), pckg_index)); +aml_append (ifctx,aml_store (aml_derefof (pckg_index), pckg_buf)); +aml_append (ifctx,aml_store (pckg_buf,aml_name (HMAM_OFFSET ))); +aml_append (method, ifctx); + +/* +* tell QEMU about the real address of HMA memory, then QEMU +* gets the control and fills the result in _HMAC memory. +*/ +aml_append (method,aml_store (hmam_mem,aml_name (HMAM_NOTIFY ))); + + hmam_out_buf_size =aml_local (1 ); +/* RLEN is not included in the payload returned to guest. */ +aml_append (method,aml_subtract (aml_name (HMAM_OUT_BUF_SIZE ), +aml_int (4 ), hmam_out_buf_size)); +aml_append (method,aml_store (aml_shiftleft (hmam_out_buf_size,aml_int (3 )), + hmam_out_buf_size)); +aml_append (method,aml_create_field (aml_name (HMAM_OUT_BUF ), +aml_int (0 ), hmam_out_buf_size,"OBUF" )); +aml_append (method,aml_concatenate (aml_buffer (0 ,NULL ),aml_name ("OBUF" ), + hmam_out_buf)); +aml_append (method,aml_return (hmam_out_buf)); +aml_append (dev, method); +} + +void hmat_init_acpi_state (AcpiHmaState *state,MemoryRegion *io, +FWCfgState *fw_cfg,Object *owner) +{ +memory_region_init_io (&state->io_mr, owner, &hmat_hma_method_ops, state, +"hma-acpi-io" ,HMAM_ACPI_IO_LEN ); +memory_region_add_subregion (io,HMAM_ACPI_IO_BASE , &state->io_mr); + + state->hmam_mem =g_array_new (false, true/* clear */ ,1 ); +fw_cfg_add_file (fw_cfg,HMAM_MEM_FILE , state->hmam_mem->data, + state->hmam_mem->len); + +hmat_init_hma_buffer (&state->hma_buf); +} + +void hmat_update (NumaState *nstat) +{ +/* build HMAT in a given buffer. */ +hmat_build_hma_buffer (nstat); +} +void build_hmat (GArray *table_data,BIOSLinker *linker,NumaState *nstat) {uint64_t hmat_start;
@@ -253,3 +519,34 @@ void build_hmat(GArray *table_data, BIOSLinker *linker, NumaState *nstat) (void *)(table_data->data + hmat_start), "HMAT", table_data->len - hmat_start, 2, NULL, NULL); } + +void hmat_build_aml (Aml *dev) +{ +Aml *method, *pkg, *buf, *buf_name, *buf_size, *call_result; + +hmat_build_common_aml (dev); + + buf =aml_local (0 ); + buf_size =aml_local (1 ); + buf_name =aml_local (2 ); + +aml_append (dev,aml_name_decl (HMAM_RHMA_STATUS ,aml_int (0 ))); + +/* build helper function, RHMA. */ + method =aml_method ("RHMA" ,1 ,AML_SERIALIZED ); +aml_append (method,aml_name_decl ("OFST" ,aml_int (0 ))); + +/* prepare input package. */ + pkg =aml_package (1 ); +aml_append (method,aml_store (aml_arg (0 ),aml_name ("OFST" ))); +aml_append (pkg,aml_name ("OFST" )); + +/* call Read HMA function. */ + call_result =aml_call1 (HMA_COMMON_METHOD , pkg); + +aml_build_runtime_buf (method, buf, buf_size, + call_result, buf_name, dev, +"RHMA" ,"_HMA" , +HMAM_RET_STATUS_SUCCESS , +HMAM_RET_STATUS_HMA_CHANGED ); +}
hw/acpi/hmat.h +68 -0
74 lines not on this page · raw message
hw/core/machine.c +4 -0
@@ -23,6 +23,7 @@#include "sysemu/qtest.h" #include "hw/pci/pci.h" #include "hw/mem/nvdimm.h" +#include "hw/acpi/hmat.h" GlobalProperty hw_compat_4_0[] = { {"VGA" ,"edid" ,"false" },
@@ -914,6 +915,9 @@ static void machine_finalize(Object *obj)g_free (ms->firmware);g_free (ms->device_memory);g_free (ms->nvdimms_state); +if (ms->numa_state->hma_enabled) { +g_free (ms->numa_state->acpi_hma_state); + }g_free (ms->numa_state); }
hw/i386/acpi-build.c +4 -0
@@ -1854,6 +1854,10 @@ build_dsdt(GArray *table_data, BIOSLinker *linker,build_q35_pci0_int (dsdt); } +if (machine->numa_state->hma_enabled) { +hmat_build_aml (dsdt); + } +if (pcmc->legacy_cpu_hotplug) {build_legacy_cpu_hotplug_aml (dsdt, machine, pm->cpu_hp_io_base); }else {
hw/i386/pc_piix.c +6 -0
@@ -58,6 +58,7 @@#include "migration/misc.h" #include "kvm_i386.h" #include "sysemu/numa.h" +#include "hw/acpi/hmat.h" #define MAX_IDE_BUS 2
@@ -301,6 +302,11 @@ static void pc_init1(MachineState *machine,nvdimm_init_acpi_state (machine->nvdimms_state, system_io, pcms->fw_cfg,OBJECT (pcms)); } + +if (machine->numa_state->hma_enabled) { +hmat_init_acpi_state (machine->numa_state->acpi_hma_state, system_io, + pcms->fw_cfg,OBJECT (pcms)); + } }/* Looking for a pc_compat_2_4() function? It doesn't exist.
hw/i386/pc_q35.c +6 -0
@@ -54,6 +54,7 @@#include "qapi/error.h" #include "qemu/error-report.h" #include "sysemu/numa.h" +#include "hw/acpi/hmat.h" /* ICH9 AHCI has 6 ports */ #define MAX_SATA_PORTS 6
@@ -333,6 +334,11 @@ static void pc_q35_init(MachineState *machine)nvdimm_init_acpi_state (machine->nvdimms_state, system_io, pcms->fw_cfg,OBJECT (pcms)); } + +if (machine->numa_state->hma_enabled) { +hmat_init_acpi_state (machine->numa_state->acpi_hma_state, system_io, + pcms->fw_cfg,OBJECT (pcms)); + } }#define DEFINE_Q35_MACHINE (suffix, name, compatfn, optionfn) \
include/sysemu/numa.h +5 -0
@@ -38,6 +38,11 @@ struct NumaState {/* Memory Side Cache Information Structure */ HMAT_Cache_Info *hmat_cache[MAX_NODES ][MAX_HMAT_CACHE_LEVEL +1 ]; + +/* Detect if HMA support is enabled. */ +bool hma_enabled; + +struct AcpiHmaState *acpi_hma_state; };typedef struct NumaState NumaState ;
numa.c +10 -0
@@ -254,6 +254,11 @@ static void parse_numa_hmat_lb(MachineState *ms, NumaHmatLBOptions *node,return ; } +if (!ms->numa_state->hma_enabled && !ms->numa_state->acpi_hma_state) { + ms->numa_state->hma_enabled = true; + ms->numa_state->acpi_hma_state =g_new0 (AcpiHmaState,1 ); + } +if (node->has_latency) { hmat_lb = ms->numa_state->hmat_lb[node->hierarchy][node->data_type];
@@ -356,6 +361,11 @@ void parse_numa_hmat_cache(MachineState *ms, NumaHmatCacheOptions *node,return ; } +if (!ms->numa_state->hma_enabled && !ms->numa_state->acpi_hma_state) { + ms->numa_state->hma_enabled = true; + ms->numa_state->acpi_hma_state =g_new0 (AcpiHmaState,1 ); + } + hmat_cache =g_malloc0 (sizeof (*hmat_cache)); hmat_cache->mem_proximity = node->node_id;
Signature · 1 line
2.20.1
PATCH v6 13/14 QMP: Add QMP interface to update HMAT at runtime
In reply to Tao XuAdd QMP interface to introduce new HMAT data (including System Locality Latency and Bandwidth Information Structure, Memory Side Cache Information Structure) at runtime. The interface can
also replace existing HMAT data.
--- hw/acpi/acpi-stub.c | 7 ++++++ numa.c | 55 +++++++++++++++++++++++++++++++++++++++------ qapi/misc.json | 49 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 104 insertions(+), 7 deletions(-)
hw/acpi/acpi-stub.c +7 -0
@@ -22,8 +22,15 @@#include "qapi/error.h" #include "qapi/qmp/qerror.h" #include "hw/acpi/acpi.h" +#include "sysemu/numa.h" +#include "hw/acpi/hmat.h" void acpi_table_add (const QemuOpts *opts,Error **errp) {error_setg (errp,QERR_UNSUPPORTED ); } + +void hmat_update (NumaState *nstat) +{ +/* For qmp_set_hmat_lb and qmp_set_hmat_cache in numa.c can compile */ +}
numa.c +48 -7
102 lines not on this page · raw message
qapi/misc.json +49 -0
61 lines not on this page · raw message
Signature · 1 line
2.20.1
PATCH v6 14/14 tests/bios-tables-test: add test cases for ACPI HMAT
In reply to Tao XuACPI table HMAT has been introduced, QEMU now builds HMAT tables for Heterogeneous Memory with boot option '-numa node'.
Add test cases on PC and Q35 machines with 2 numa nodes. Because HMAT is generated when system enable numa, the following tables need to be added for this test:
tests/acpi-test-data/pc/*.acpihmat tests/acpi-test-data/pc/HMAT.* tests/acpi-test-data/q35/*.acpihmat tests/acpi-test-data/q35/HMAT.*
--- tests/bios-tables-test.c | 43 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+)
tests/bios-tables-test.c +43 -0
@@ -844,6 +844,47 @@ static void test_acpi_piix4_tcg_dimm_pxm(void)test_acpi_tcg_dimm_pxm (MACHINE_PC ); } +static void test_acpi_tcg_acpi_hmat (const char *machine) +{ +test_data data; + +memset (&data,0 ,sizeof (data)); + data.machine = machine; + data.variant =".acpihmat" ; +test_acpi_one (" -smp 2,sockets=2" +" -m 128M,slots=2,maxmem=1G" +" -object memory-backend-ram,size=64M,id=m0" +" -object memory-backend-ram,size=64M,id=m1" +" -numa node,nodeid=0,memdev=m0" +" -numa node,nodeid=1,memdev=m1,initiator=0" +" -numa cpu,node-id=0,socket-id=0" +" -numa cpu,node-id=0,socket-id=1" +" -numa hmat-lb,initiator=0,target=0,hierarchy=memory," +"data-type=access-latency,base-lat=10,latency=5" +" -numa hmat-lb,initiator=0,target=0,hierarchy=memory," +"data-type=access-bandwidth,base-bw=20,bandwidth=5" +" -numa hmat-lb,initiator=0,target=1,hierarchy=memory," +"data-type=access-latency,base-lat=10,latency=10" +" -numa hmat-lb,initiator=0,target=1,hierarchy=memory," +"data-type=access-bandwidth,base-bw=20,bandwidth=10" +" -numa hmat-cache,node-id=0,size=0x20000,total=1,level=1" +",assoc=direct,policy=write-back,line=8" +" -numa hmat-cache,node-id=1,size=0x20000,total=1,level=1" +",assoc=direct,policy=write-back,line=8" , + &data); +free_test_data (&data); +} + +static void test_acpi_q35_tcg_acpi_hmat (void ) +{ +test_acpi_tcg_acpi_hmat (MACHINE_Q35 ); +} + +static void test_acpi_piix4_tcg_acpi_hmat (void ) +{ +test_acpi_tcg_acpi_hmat (MACHINE_PC ); +} +static void test_acpi_virt_tcg (void ) {test_data data = {
@@ -888,6 +929,8 @@ int main(int argc, char *argv[])qtest_add_func ("acpi/q35/numamem" , test_acpi_q35_tcg_numamem);qtest_add_func ("acpi/piix4/dimmpxm" , test_acpi_piix4_tcg_dimm_pxm);qtest_add_func ("acpi/q35/dimmpxm" , test_acpi_q35_tcg_dimm_pxm); +qtest_add_func ("acpi/piix4/acpihmat" , test_acpi_piix4_tcg_acpi_hmat); +qtest_add_func ("acpi/q35/acpihmat" , test_acpi_q35_tcg_acpi_hmat); }else if (strcmp (arch,"aarch64" ) ==0 ) {qtest_add_func ("acpi/virt" , test_acpi_virt_tcg); }
Signature · 1 line
2.20.1