diff --git a/Documentation/ABI/testing/configfs-tsm b/Documentation/ABI/testing/configfs-tsm index dd24202b5ba5..534408bc1408 100644 --- a/Documentation/ABI/testing/configfs-tsm +++ b/Documentation/ABI/testing/configfs-tsm @@ -31,6 +31,18 @@ Description: Standardization v2.03 Section 4.1.8.1 MSG_REPORT_REQ. https://www.amd.com/content/dam/amd/en/documents/epyc-technical-docs/specifications/56421.pdf +What: /sys/kernel/config/tsm/report/$name/manifestblob +Date: January, 2024 +KernelVersion: v6.10 +Contact: linux-coco@lists.linux.dev +Description: + (RO) Optional supplemental data that a TSM may emit, visibility + of this attribute depends on TSM, and may be empty if no + manifest data is available. + + See 'service_provider' for information on the format of the + manifest blob. + What: /sys/kernel/config/tsm/report/$name/provider Date: September, 2023 KernelVersion: v6.7 @@ -80,3 +92,54 @@ Contact: linux-coco@lists.linux.dev Description: (RO) Indicates the minimum permissible value that can be written to @privlevel. + +What: /sys/kernel/config/tsm/report/$name/service_provider +Date: January, 2024 +KernelVersion: v6.10 +Contact: linux-coco@lists.linux.dev +Description: + (WO) Attribute is visible if a TSM implementation provider + supports the concept of attestation reports from a service + provider for TVMs, like SEV-SNP running under an SVSM. + Specifying the service provider via this attribute will create + an attestation report as specified by the service provider. + The only currently supported service provider is "svsm". + + For the "svsm" service provider, see the Secure VM Service Module + for SEV-SNP Guests v1.00 Section 7. For the doc, search for + "site:amd.com "Secure VM Service Module for SEV-SNP + Guests", docID: 58019" + +What: /sys/kernel/config/tsm/report/$name/service_guid +Date: January, 2024 +KernelVersion: v6.10 +Contact: linux-coco@lists.linux.dev +Description: + (WO) Attribute is visible if a TSM implementation provider + supports the concept of attestation reports from a service + provider for TVMs, like SEV-SNP running under an SVSM. + Specifying an empty/null GUID (00000000-0000-0000-0000-000000) + requests all active services within the service provider be + part of the attestation report. Specifying a GUID request + an attestation report of just the specified service using the + manifest form specified by the service_manifest_version + attribute. + + See 'service_provider' for information on the format of the + service guid. + +What: /sys/kernel/config/tsm/report/$name/service_manifest_version +Date: January, 2024 +KernelVersion: v6.10 +Contact: linux-coco@lists.linux.dev +Description: + (WO) Attribute is visible if a TSM implementation provider + supports the concept of attestation reports from a service + provider for TVMs, like SEV-SNP running under an SVSM. + Indicates the service manifest version requested for the + attestation report (default 0). If this field is not set by + the user, the default manifest version of the service (the + service's initial/first manifest version) is returned. + + See 'service_provider' for information on the format of the + service manifest version. diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index 53ed1a803422..325873385b71 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -605,6 +605,18 @@ Description: Umwait control Note that a value of zero means there is no limit. Low order two bits must be zero. +What: /sys/devices/system/cpu/sev + /sys/devices/system/cpu/sev/vmpl +Date: May 2024 +Contact: Linux kernel mailing list +Description: Secure Encrypted Virtualization (SEV) information + + This directory is only present when running as an SEV-SNP guest. + + vmpl: Reports the Virtual Machine Privilege Level (VMPL) at which + the SEV-SNP guest is running. + + What: /sys/devices/system/cpu/svm Date: August 2019 Contact: Linux kernel mailing list diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst index 25a04cda4c2c..132e0bc6007e 100644 --- a/Documentation/admin-guide/hw-vuln/spectre.rst +++ b/Documentation/admin-guide/hw-vuln/spectre.rst @@ -592,85 +592,19 @@ Spectre variant 2 Mitigation control on the kernel command line --------------------------------------------- -Spectre variant 2 mitigation can be disabled or force enabled at the -kernel command line. +In general the kernel selects reasonable default mitigations for the +current CPU. - nospectre_v1 +Spectre default mitigations can be disabled or changed at the kernel +command line with the following options: - [X86,PPC] Disable mitigations for Spectre Variant 1 - (bounds check bypass). With this option data leaks are - possible in the system. + - nospectre_v1 + - nospectre_v2 + - spectre_v2={option} + - spectre_v2_user={option} + - spectre_bhi={option} - nospectre_v2 - - [X86] Disable all mitigations for the Spectre variant 2 - (indirect branch prediction) vulnerability. System may - allow data leaks with this option, which is equivalent - to spectre_v2=off. - - - spectre_v2= - - [X86] Control mitigation of Spectre variant 2 - (indirect branch speculation) vulnerability. - The default operation protects the kernel from - user space attacks. - - on - unconditionally enable, implies - spectre_v2_user=on - off - unconditionally disable, implies - spectre_v2_user=off - auto - kernel detects whether your CPU model is - vulnerable - - Selecting 'on' will, and 'auto' may, choose a - mitigation method at run time according to the - CPU, the available microcode, the setting of the - CONFIG_MITIGATION_RETPOLINE configuration option, - and the compiler with which the kernel was built. - - Selecting 'on' will also enable the mitigation - against user space to user space task attacks. - - Selecting 'off' will disable both the kernel and - the user space protections. - - Specific mitigations can also be selected manually: - - retpoline auto pick between generic,lfence - retpoline,generic Retpolines - retpoline,lfence LFENCE; indirect branch - retpoline,amd alias for retpoline,lfence - eibrs Enhanced/Auto IBRS - eibrs,retpoline Enhanced/Auto IBRS + Retpolines - eibrs,lfence Enhanced/Auto IBRS + LFENCE - ibrs use IBRS to protect kernel - - Not specifying this option is equivalent to - spectre_v2=auto. - - In general the kernel by default selects - reasonable mitigations for the current CPU. To - disable Spectre variant 2 mitigations, boot with - spectre_v2=off. Spectre variant 1 mitigations - cannot be disabled. - - spectre_bhi= - - [X86] Control mitigation of Branch History Injection - (BHI) vulnerability. This setting affects the deployment - of the HW BHI control and the SW BHB clearing sequence. - - on - (default) Enable the HW or SW mitigation as - needed. - off - Disable the mitigation. - -For spectre_v2_user see Documentation/admin-guide/kernel-parameters.txt +For more details on the available options, refer to Documentation/admin-guide/kernel-parameters.txt Mitigation selection guide -------------------------- diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index b39dd7351509..f99728b6be4c 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3412,10 +3412,6 @@ deep - Suspend-To-RAM or equivalent (if supported) See Documentation/admin-guide/pm/sleep-states.rst. - mfgpt_irq= [IA-32] Specify the IRQ to use for the - Multi-Function General Purpose Timers on AMD Geode - platforms. - mfgptfix [X86-32] Fix MFGPT timers on AMD Geode platforms when the BIOS has incorrectly applied a workaround. TinyBIOS version 0.98 is known to be affected, 0.99 fixes the @@ -6148,9 +6144,15 @@ deployment of the HW BHI control and the SW BHB clearing sequence. - on - (default) Enable the HW or SW mitigation - as needed. - off - Disable the mitigation. + on - (default) Enable the HW or SW mitigation as + needed. This protects the kernel from + both syscalls and VMs. + vmexit - On systems which don't have the HW mitigation + available, enable the SW mitigation on vmexit + ONLY. On such systems, the host kernel is + protected from VM-originated BHI attacks, but + may still be vulnerable to syscall attacks. + off - Disable the mitigation. spectre_v2= [X86,EARLY] Control mitigation of Spectre variant 2 (indirect branch speculation) vulnerability. diff --git a/Documentation/arch/x86/amd-memory-encryption.rst b/Documentation/arch/x86/amd-memory-encryption.rst index 414bc7402ae7..6df3264f23b9 100644 --- a/Documentation/arch/x86/amd-memory-encryption.rst +++ b/Documentation/arch/x86/amd-memory-encryption.rst @@ -130,4 +130,31 @@ SNP feature support. More details in AMD64 APM[1] Vol 2: 15.34.10 SEV_STATUS MSR -[1] https://www.amd.com/content/dam/amd/en/documents/processor-tech-docs/programmer-references/24593.pdf +Secure VM Service Module (SVSM) +=============================== +SNP provides a feature called Virtual Machine Privilege Levels (VMPL) which +defines four privilege levels at which guest software can run. The most +privileged level is 0 and numerically higher numbers have lesser privileges. +More details in the AMD64 APM Vol 2, section "15.35.7 Virtual Machine +Privilege Levels", docID: 24593. + +When using that feature, different services can run at different protection +levels, apart from the guest OS but still within the secure SNP environment. +They can provide services to the guest, like a vTPM, for example. + +When a guest is not running at VMPL0, it needs to communicate with the software +running at VMPL0 to perform privileged operations or to interact with secure +services. An example fur such a privileged operation is PVALIDATE which is +*required* to be executed at VMPL0. + +In this scenario, the software running at VMPL0 is usually called a Secure VM +Service Module (SVSM). Discovery of an SVSM and the API used to communicate +with it is documented in "Secure VM Service Module for SEV-SNP Guests", docID: +58019. + +(Latest versions of the above-mentioned documents can be found by using +a search engine like duckduckgo.com and typing in: + + site:amd.com "Secure VM Service Module for SEV-SNP Guests", docID: 58019 + +for example.) diff --git a/Documentation/arch/x86/resctrl.rst b/Documentation/arch/x86/resctrl.rst index 627e23869bca..a824affd741d 100644 --- a/Documentation/arch/x86/resctrl.rst +++ b/Documentation/arch/x86/resctrl.rst @@ -375,6 +375,10 @@ When monitoring is enabled all MON groups will also contain: all tasks in the group. In CTRL_MON groups these files provide the sum for all tasks in the CTRL_MON group and all tasks in MON groups. Please see example section for more details on usage. + On systems with Sub-NUMA Cluster (SNC) enabled there are extra + directories for each node (located within the "mon_L3_XX" directory + for the L3 cache they occupy). These are named "mon_sub_L3_YY" + where "YY" is the node number. "mon_hw_id": Available only with debug option. The identifier used by hardware @@ -484,6 +488,29 @@ if non-contiguous 1s value is supported. On a system with a 20-bit mask each bit represents 5% of the capacity of the cache. You could partition the cache into four equal parts with masks: 0x1f, 0x3e0, 0x7c00, 0xf8000. +Notes on Sub-NUMA Cluster mode +============================== +When SNC mode is enabled, Linux may load balance tasks between Sub-NUMA +nodes much more readily than between regular NUMA nodes since the CPUs +on Sub-NUMA nodes share the same L3 cache and the system may report +the NUMA distance between Sub-NUMA nodes with a lower value than used +for regular NUMA nodes. + +The top-level monitoring files in each "mon_L3_XX" directory provide +the sum of data across all SNC nodes sharing an L3 cache instance. +Users who bind tasks to the CPUs of a specific Sub-NUMA node can read +the "llc_occupancy", "mbm_total_bytes", and "mbm_local_bytes" in the +"mon_sub_L3_YY" directories to get node local data. + +Memory bandwidth allocation is still performed at the L3 cache +level. I.e. throttling controls are applied to all SNC nodes. + +L3 cache allocation bitmaps also apply to all SNC nodes. But note that +the amount of L3 cache represented by each bit is divided by the number +of SNC nodes per L3 cache. E.g. with a 100MB cache on a system with 10-bit +allocation masks each bit normally represents 10MB. With SNC mode enabled +with two SNC nodes per L3 cache, each bit only represents 5MB. + Memory bandwidth Allocation and monitoring ========================================== diff --git a/Documentation/virt/coco/sev-guest.rst b/Documentation/virt/coco/sev-guest.rst index e1eaf6a830ce..9d00967a5b2b 100644 --- a/Documentation/virt/coco/sev-guest.rst +++ b/Documentation/virt/coco/sev-guest.rst @@ -204,6 +204,17 @@ has taken care to make use of the SEV-SNP CPUID throughout all stages of boot. Otherwise, guest owner attestation provides no assurance that the kernel wasn't fed incorrect values at some point during boot. +4. SEV Guest Driver Communication Key +===================================== + +Communication between an SEV guest and the SEV firmware in the AMD Secure +Processor (ASP, aka PSP) is protected by a VM Platform Communication Key +(VMPCK). By default, the sev-guest driver uses the VMPCK associated with the +VM Privilege Level (VMPL) at which the guest is running. Should this key be +wiped by the sev-guest driver (see the driver for reasons why a VMPCK can be +wiped), a different key can be used by reloading the sev-guest driver and +specifying the desired key using the vmpck_id module parameter. + Reference --------- diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index 2ed7d229c8f9..23c98203c40f 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note # # Linux system call numbers and entry vectors # diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 1d7122a1883e..125914536825 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1118,6 +1118,13 @@ config X86_LOCAL_APIC depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC || PCI_MSI select IRQ_DOMAIN_HIERARCHY +config ACPI_MADT_WAKEUP + def_bool y + depends on X86_64 + depends on ACPI + depends on SMP + depends on X86_LOCAL_APIC + config X86_IO_APIC def_bool y depends on X86_LOCAL_APIC || X86_UP_IOAPIC diff --git a/arch/x86/Kconfig.assembler b/arch/x86/Kconfig.assembler index 59aedf32c4ea..6d20a6ce0507 100644 --- a/arch/x86/Kconfig.assembler +++ b/arch/x86/Kconfig.assembler @@ -36,6 +36,6 @@ config AS_VPCLMULQDQ Supported by binutils >= 2.30 and LLVM integrated assembler config AS_WRUSS - def_bool $(as-instr,wrussq %rax$(comma)(%rbx)) + def_bool $(as-instr64,wrussq %rax$(comma)(%rbx)) help Supported by binutils >= 2.31 and LLVM integrated assembler diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index b70e4a21c15f..944454306ef4 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -531,8 +531,3 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output) return output + entry_offset; } - -void __fortify_panic(const u8 reason, size_t avail, size_t size) -{ - error("detected buffer overflow"); -} diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index 0457a9d7e515..cd44e120fe53 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -127,7 +127,35 @@ static bool fault_in_kernel_space(unsigned long address) #include "../../lib/insn.c" /* Include code for early handlers */ -#include "../../kernel/sev-shared.c" +#include "../../coco/sev/shared.c" + +static struct svsm_ca *svsm_get_caa(void) +{ + return boot_svsm_caa; +} + +static u64 svsm_get_caa_pa(void) +{ + return boot_svsm_caa_pa; +} + +static int svsm_perform_call_protocol(struct svsm_call *call) +{ + struct ghcb *ghcb; + int ret; + + if (boot_ghcb) + ghcb = boot_ghcb; + else + ghcb = NULL; + + do { + ret = ghcb ? svsm_perform_ghcb_protocol(ghcb, call) + : svsm_perform_msr_protocol(call); + } while (ret == -EAGAIN); + + return ret; +} bool sev_snp_enabled(void) { @@ -145,8 +173,8 @@ static void __page_state_change(unsigned long paddr, enum psc_op op) * If private -> shared then invalidate the page before requesting the * state change in the RMP table. */ - if (op == SNP_PAGE_STATE_SHARED && pvalidate(paddr, RMP_PG_SIZE_4K, 0)) - sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE); + if (op == SNP_PAGE_STATE_SHARED) + pvalidate_4k_page(paddr, paddr, false); /* Issue VMGEXIT to change the page state in RMP table. */ sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op)); @@ -161,8 +189,8 @@ static void __page_state_change(unsigned long paddr, enum psc_op op) * Now that page state is changed in the RMP table, validate it so that it is * consistent with the RMP entry. */ - if (op == SNP_PAGE_STATE_PRIVATE && pvalidate(paddr, RMP_PG_SIZE_4K, 1)) - sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE); + if (op == SNP_PAGE_STATE_PRIVATE) + pvalidate_4k_page(paddr, paddr, true); } void snp_set_page_private(unsigned long paddr) @@ -255,6 +283,16 @@ void sev_es_shutdown_ghcb(void) if (!sev_es_check_cpu_features()) error("SEV-ES CPU Features missing."); + /* + * This denotes whether to use the GHCB MSR protocol or the GHCB + * shared page to perform a GHCB request. Since the GHCB page is + * being changed to encrypted, it can't be used to perform GHCB + * requests. Clear the boot_ghcb variable so that the GHCB MSR + * protocol is used to change the GHCB page over to an encrypted + * page. + */ + boot_ghcb = NULL; + /* * GHCB Page must be flushed from the cache and mapped encrypted again. * Otherwise the running kernel will see strange cache effects when @@ -462,6 +500,13 @@ static bool early_snp_init(struct boot_params *bp) */ setup_cpuid_table(cc_info); + /* + * Record the SVSM Calling Area (CA) address if the guest is not + * running at VMPL0. The CA will be used to communicate with the + * SVSM and request its services. + */ + svsm_setup_ca(cc_info); + /* * Pass run-time kernel a pointer to CC info via boot_params so EFI * config table doesn't need to be searched again during early startup @@ -565,22 +610,31 @@ void sev_enable(struct boot_params *bp) * features. */ if (sev_status & MSR_AMD64_SEV_SNP_ENABLED) { - if (!(get_hv_features() & GHCB_HV_FT_SNP)) + u64 hv_features; + int ret; + + hv_features = get_hv_features(); + if (!(hv_features & GHCB_HV_FT_SNP)) sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); /* - * Enforce running at VMPL0. + * Enforce running at VMPL0 or with an SVSM. * - * RMPADJUST modifies RMP permissions of a lesser-privileged (numerically - * higher) privilege level. Here, clear the VMPL1 permission mask of the - * GHCB page. If the guest is not running at VMPL0, this will fail. - * - * If the guest is running at VMPL0, it will succeed. Even if that operation - * modifies permission bits, it is still ok to do so currently because Linux - * SNP guests running at VMPL0 only run at VMPL0, so VMPL1 or higher - * permission mask changes are a don't-care. + * Use RMPADJUST (see the rmpadjust() function for a description of + * what the instruction does) to update the VMPL1 permissions of a + * page. If the guest is running at VMPL0, this will succeed. If the + * guest is running at any other VMPL, this will fail. Linux SNP guests + * only ever run at a single VMPL level so permission mask changes of a + * lesser-privileged VMPL are a don't-care. */ - if (rmpadjust((unsigned long)&boot_ghcb_page, RMP_PG_SIZE_4K, 1)) + ret = rmpadjust((unsigned long)&boot_ghcb_page, RMP_PG_SIZE_4K, 1); + + /* + * Running at VMPL0 is not required if an SVSM is present and the hypervisor + * supports the required SVSM GHCB events. + */ + if (ret && + !(snp_vmpl && (hv_features & GHCB_HV_FT_SNP_MULTI_VMPL))) sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_NOT_VMPL0); } diff --git a/arch/x86/boot/cpucheck.c b/arch/x86/boot/cpucheck.c index fed8d13ce252..0aae4d4ed615 100644 --- a/arch/x86/boot/cpucheck.c +++ b/arch/x86/boot/cpucheck.c @@ -203,7 +203,7 @@ int check_knl_erratum(void) */ if (!is_intel() || cpu.family != 6 || - cpu.model != INTEL_FAM6_XEON_PHI_KNL) + cpu.model != 0x57 /*INTEL_XEON_PHI_KNL*/) return 0; /* diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c index 9049f390d834..9d0fea18d3c8 100644 --- a/arch/x86/boot/main.c +++ b/arch/x86/boot/main.c @@ -27,34 +27,32 @@ char *heap_end = _end; /* Default end of heap = no heap */ * screws up the old-style command line protocol, adjust by * filling in the new-style command line pointer instead. */ - static void copy_boot_params(void) { struct old_cmdline { u16 cl_magic; u16 cl_offset; }; - const struct old_cmdline * const oldcmd = - absolute_pointer(OLD_CL_ADDRESS); + const struct old_cmdline * const oldcmd = absolute_pointer(OLD_CL_ADDRESS); BUILD_BUG_ON(sizeof(boot_params) != 4096); memcpy(&boot_params.hdr, &hdr, sizeof(hdr)); - if (!boot_params.hdr.cmd_line_ptr && - oldcmd->cl_magic == OLD_CL_MAGIC) { - /* Old-style command line protocol. */ + if (!boot_params.hdr.cmd_line_ptr && oldcmd->cl_magic == OLD_CL_MAGIC) { + /* Old-style command line protocol */ u16 cmdline_seg; - /* Figure out if the command line falls in the region - of memory that an old kernel would have copied up - to 0x90000... */ + /* + * Figure out if the command line falls in the region + * of memory that an old kernel would have copied up + * to 0x90000... + */ if (oldcmd->cl_offset < boot_params.hdr.setup_move_size) cmdline_seg = ds(); else cmdline_seg = 0x9000; - boot_params.hdr.cmd_line_ptr = - (cmdline_seg << 4) + oldcmd->cl_offset; + boot_params.hdr.cmd_line_ptr = (cmdline_seg << 4) + oldcmd->cl_offset; } } @@ -66,6 +64,7 @@ static void copy_boot_params(void) static void keyboard_init(void) { struct biosregs ireg, oreg; + initregs(&ireg); ireg.ah = 0x02; /* Get keyboard status */ @@ -83,8 +82,10 @@ static void query_ist(void) { struct biosregs ireg, oreg; - /* Some older BIOSes apparently crash on this call, so filter - it from machines too old to have SpeedStep at all. */ + /* + * Some older BIOSes apparently crash on this call, so filter + * it from machines too old to have SpeedStep at all. + */ if (cpu.level < 6) return; @@ -119,17 +120,13 @@ static void init_heap(void) char *stack_end; if (boot_params.hdr.loadflags & CAN_USE_HEAP) { - asm("leal %n1(%%esp),%0" - : "=r" (stack_end) : "i" (STACK_SIZE)); - - heap_end = (char *) - ((size_t)boot_params.hdr.heap_end_ptr + 0x200); + stack_end = (char *) (current_stack_pointer - STACK_SIZE); + heap_end = (char *) ((size_t)boot_params.hdr.heap_end_ptr + 0x200); if (heap_end > stack_end) heap_end = stack_end; } else { /* Boot protocol 2.00 only, no heap available */ - puts("WARNING: Ancient bootloader, some functionality " - "may be limited!\n"); + puts("WARNING: Ancient bootloader, some functionality may be limited!\n"); } } @@ -150,12 +147,11 @@ void main(void) /* Make sure we have all the proper CPU support */ if (validate_cpu()) { - puts("Unable to boot - please use a kernel appropriate " - "for your CPU.\n"); + puts("Unable to boot - please use a kernel appropriate for your CPU.\n"); die(); } - /* Tell the BIOS what CPU mode we intend to run in. */ + /* Tell the BIOS what CPU mode we intend to run in */ set_bios_mode(); /* Detect memory layout */ diff --git a/arch/x86/coco/Makefile b/arch/x86/coco/Makefile index c816acf78b6a..eabdc7486538 100644 --- a/arch/x86/coco/Makefile +++ b/arch/x86/coco/Makefile @@ -6,3 +6,4 @@ CFLAGS_core.o += -fno-stack-protector obj-y += core.o obj-$(CONFIG_INTEL_TDX_GUEST) += tdx/ +obj-$(CONFIG_AMD_MEM_ENCRYPT) += sev/ diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c index b31ef2424d19..0f81f70aca82 100644 --- a/arch/x86/coco/core.c +++ b/arch/x86/coco/core.c @@ -29,7 +29,6 @@ static bool noinstr intel_cc_platform_has(enum cc_attr attr) { switch (attr) { case CC_ATTR_GUEST_UNROLL_STRING_IO: - case CC_ATTR_HOTPLUG_DISABLED: case CC_ATTR_GUEST_MEM_ENCRYPT: case CC_ATTR_MEM_ENCRYPT: return true; diff --git a/arch/x86/coco/sev/Makefile b/arch/x86/coco/sev/Makefile new file mode 100644 index 000000000000..4e375e7305ac --- /dev/null +++ b/arch/x86/coco/sev/Makefile @@ -0,0 +1,15 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-y += core.o + +ifdef CONFIG_FUNCTION_TRACER +CFLAGS_REMOVE_core.o = -pg +endif + +KASAN_SANITIZE_core.o := n +KMSAN_SANITIZE_core.o := n +KCOV_INSTRUMENT_core.o := n + +# With some compiler versions the generated code results in boot hangs, caused +# by several compilation units. To be safe, disable all instrumentation. +KCSAN_SANITIZE := n diff --git a/arch/x86/kernel/sev.c b/arch/x86/coco/sev/core.c similarity index 86% rename from arch/x86/kernel/sev.c rename to arch/x86/coco/sev/core.c index 3342ed58e168..082d61d85dfc 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/coco/sev/core.c @@ -133,16 +133,20 @@ struct ghcb_state { struct ghcb *ghcb; }; +/* For early boot SVSM communication */ +static struct svsm_ca boot_svsm_ca_page __aligned(PAGE_SIZE); + static DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data); static DEFINE_PER_CPU(struct sev_es_save_area *, sev_vmsa); +static DEFINE_PER_CPU(struct svsm_ca *, svsm_caa); +static DEFINE_PER_CPU(u64, svsm_caa_pa); struct sev_config { __u64 debug : 1, /* - * A flag used by __set_pages_state() that indicates when the - * per-CPU GHCB has been created and registered and thus can be - * used by the BSP instead of the early boot GHCB. + * Indicates when the per-CPU GHCB has been created and registered + * and thus can be used by the BSP instead of the early boot GHCB. * * For APs, the per-CPU GHCB is created before they are started * and registered upon startup, so this flag can be used globally @@ -150,6 +154,15 @@ struct sev_config { */ ghcbs_initialized : 1, + /* + * Indicates when the per-CPU SVSM CA is to be used instead of the + * boot SVSM CA. + * + * For APs, the per-CPU SVSM CA is created as part of the AP + * bringup, so this flag can be used globally for the BSP and APs. + */ + use_cas : 1, + __reserved : 62; }; @@ -572,8 +585,61 @@ fault: return ES_EXCEPTION; } +static __always_inline void vc_forward_exception(struct es_em_ctxt *ctxt) +{ + long error_code = ctxt->fi.error_code; + int trapnr = ctxt->fi.vector; + + ctxt->regs->orig_ax = ctxt->fi.error_code; + + switch (trapnr) { + case X86_TRAP_GP: + exc_general_protection(ctxt->regs, error_code); + break; + case X86_TRAP_UD: + exc_invalid_op(ctxt->regs); + break; + case X86_TRAP_PF: + write_cr2(ctxt->fi.cr2); + exc_page_fault(ctxt->regs, error_code); + break; + case X86_TRAP_AC: + exc_alignment_check(ctxt->regs, error_code); + break; + default: + pr_emerg("Unsupported exception in #VC instruction emulation - can't continue\n"); + BUG(); + } +} + /* Include code shared with pre-decompression boot stage */ -#include "sev-shared.c" +#include "shared.c" + +static inline struct svsm_ca *svsm_get_caa(void) +{ + /* + * Use rIP-relative references when called early in the boot. If + * ->use_cas is set, then it is late in the boot and no need + * to worry about rIP-relative references. + */ + if (RIP_REL_REF(sev_cfg).use_cas) + return this_cpu_read(svsm_caa); + else + return RIP_REL_REF(boot_svsm_caa); +} + +static u64 svsm_get_caa_pa(void) +{ + /* + * Use rIP-relative references when called early in the boot. If + * ->use_cas is set, then it is late in the boot and no need + * to worry about rIP-relative references. + */ + if (RIP_REL_REF(sev_cfg).use_cas) + return this_cpu_read(svsm_caa_pa); + else + return RIP_REL_REF(boot_svsm_caa_pa); +} static noinstr void __sev_put_ghcb(struct ghcb_state *state) { @@ -600,6 +666,44 @@ static noinstr void __sev_put_ghcb(struct ghcb_state *state) } } +static int svsm_perform_call_protocol(struct svsm_call *call) +{ + struct ghcb_state state; + unsigned long flags; + struct ghcb *ghcb; + int ret; + + /* + * This can be called very early in the boot, use native functions in + * order to avoid paravirt issues. + */ + flags = native_local_irq_save(); + + /* + * Use rip-relative references when called early in the boot. If + * ghcbs_initialized is set, then it is late in the boot and no need + * to worry about rip-relative references in called functions. + */ + if (RIP_REL_REF(sev_cfg).ghcbs_initialized) + ghcb = __sev_get_ghcb(&state); + else if (RIP_REL_REF(boot_ghcb)) + ghcb = RIP_REL_REF(boot_ghcb); + else + ghcb = NULL; + + do { + ret = ghcb ? svsm_perform_ghcb_protocol(ghcb, call) + : svsm_perform_msr_protocol(call); + } while (ret == -EAGAIN); + + if (RIP_REL_REF(sev_cfg).ghcbs_initialized) + __sev_put_ghcb(&state); + + native_local_irq_restore(flags); + + return ret; +} + void noinstr __sev_es_nmi_complete(void) { struct ghcb_state state; @@ -709,7 +813,6 @@ early_set_pages_state(unsigned long vaddr, unsigned long paddr, { unsigned long paddr_end; u64 val; - int ret; vaddr = vaddr & PAGE_MASK; @@ -717,12 +820,9 @@ early_set_pages_state(unsigned long vaddr, unsigned long paddr, paddr_end = paddr + (npages << PAGE_SHIFT); while (paddr < paddr_end) { - if (op == SNP_PAGE_STATE_SHARED) { - /* Page validation must be rescinded before changing to shared */ - ret = pvalidate(vaddr, RMP_PG_SIZE_4K, false); - if (WARN(ret, "Failed to validate address 0x%lx ret %d", paddr, ret)) - goto e_term; - } + /* Page validation must be rescinded before changing to shared */ + if (op == SNP_PAGE_STATE_SHARED) + pvalidate_4k_page(vaddr, paddr, false); /* * Use the MSR protocol because this function can be called before @@ -744,12 +844,9 @@ early_set_pages_state(unsigned long vaddr, unsigned long paddr, paddr, GHCB_MSR_PSC_RESP_VAL(val))) goto e_term; - if (op == SNP_PAGE_STATE_PRIVATE) { - /* Page validation must be performed after changing to private */ - ret = pvalidate(vaddr, RMP_PG_SIZE_4K, true); - if (WARN(ret, "Failed to validate address 0x%lx ret %d", paddr, ret)) - goto e_term; - } + /* Page validation must be performed after changing to private */ + if (op == SNP_PAGE_STATE_PRIVATE) + pvalidate_4k_page(vaddr, paddr, true); vaddr += PAGE_SIZE; paddr += PAGE_SIZE; @@ -913,22 +1010,49 @@ void snp_accept_memory(phys_addr_t start, phys_addr_t end) set_pages_state(vaddr, npages, SNP_PAGE_STATE_PRIVATE); } -static int snp_set_vmsa(void *va, bool vmsa) +static int snp_set_vmsa(void *va, void *caa, int apic_id, bool make_vmsa) { - u64 attrs; + int ret; - /* - * Running at VMPL0 allows the kernel to change the VMSA bit for a page - * using the RMPADJUST instruction. However, for the instruction to - * succeed it must target the permissions of a lesser privileged - * (higher numbered) VMPL level, so use VMPL1 (refer to the RMPADJUST - * instruction in the AMD64 APM Volume 3). - */ - attrs = 1; - if (vmsa) - attrs |= RMPADJUST_VMSA_PAGE_BIT; + if (snp_vmpl) { + struct svsm_call call = {}; + unsigned long flags; - return rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs); + local_irq_save(flags); + + call.caa = this_cpu_read(svsm_caa); + call.rcx = __pa(va); + + if (make_vmsa) { + /* Protocol 0, Call ID 2 */ + call.rax = SVSM_CORE_CALL(SVSM_CORE_CREATE_VCPU); + call.rdx = __pa(caa); + call.r8 = apic_id; + } else { + /* Protocol 0, Call ID 3 */ + call.rax = SVSM_CORE_CALL(SVSM_CORE_DELETE_VCPU); + } + + ret = svsm_perform_call_protocol(&call); + + local_irq_restore(flags); + } else { + /* + * If the kernel runs at VMPL0, it can change the VMSA + * bit for a page using the RMPADJUST instruction. + * However, for the instruction to succeed it must + * target the permissions of a lesser privileged (higher + * numbered) VMPL level, so use VMPL1. + */ + u64 attrs = 1; + + if (make_vmsa) + attrs |= RMPADJUST_VMSA_PAGE_BIT; + + ret = rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs); + } + + return ret; } #define __ATTR_BASE (SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK) @@ -962,11 +1086,11 @@ static void *snp_alloc_vmsa_page(int cpu) return page_address(p + 1); } -static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa) +static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa, int apic_id) { int err; - err = snp_set_vmsa(vmsa, false); + err = snp_set_vmsa(vmsa, NULL, apic_id, false); if (err) pr_err("clear VMSA page failed (%u), leaking page\n", err); else @@ -977,6 +1101,7 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip) { struct sev_es_save_area *cur_vmsa, *vmsa; struct ghcb_state state; + struct svsm_ca *caa; unsigned long flags; struct ghcb *ghcb; u8 sipi_vector; @@ -1023,6 +1148,9 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip) if (!vmsa) return -ENOMEM; + /* If an SVSM is present, the SVSM per-CPU CAA will be !NULL */ + caa = per_cpu(svsm_caa, cpu); + /* CR4 should maintain the MCE value */ cr4 = native_read_cr4() & X86_CR4_MCE; @@ -1070,11 +1198,11 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip) * VMPL level * SEV_FEATURES (matches the SEV STATUS MSR right shifted 2 bits) */ - vmsa->vmpl = 0; + vmsa->vmpl = snp_vmpl; vmsa->sev_features = sev_status >> 2; /* Switch the page over to a VMSA page now that it is initialized */ - ret = snp_set_vmsa(vmsa, true); + ret = snp_set_vmsa(vmsa, caa, apic_id, true); if (ret) { pr_err("set VMSA page failed (%u)\n", ret); free_page((unsigned long)vmsa); @@ -1090,7 +1218,10 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip) vc_ghcb_invalidate(ghcb); ghcb_set_rax(ghcb, vmsa->sev_features); ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_CREATION); - ghcb_set_sw_exit_info_1(ghcb, ((u64)apic_id << 32) | SVM_VMGEXIT_AP_CREATE); + ghcb_set_sw_exit_info_1(ghcb, + ((u64)apic_id << 32) | + ((u64)snp_vmpl << 16) | + SVM_VMGEXIT_AP_CREATE); ghcb_set_sw_exit_info_2(ghcb, __pa(vmsa)); sev_es_wr_ghcb_msr(__pa(ghcb)); @@ -1108,13 +1239,13 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip) /* Perform cleanup if there was an error */ if (ret) { - snp_cleanup_vmsa(vmsa); + snp_cleanup_vmsa(vmsa, apic_id); vmsa = NULL; } /* Free up any previous VMSA page */ if (cur_vmsa) - snp_cleanup_vmsa(cur_vmsa); + snp_cleanup_vmsa(cur_vmsa, apic_id); /* Record the current VMSA page */ per_cpu(sev_vmsa, cpu) = vmsa; @@ -1209,6 +1340,17 @@ static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt) /* Is it a WRMSR? */ exit_info_1 = (ctxt->insn.opcode.bytes[1] == 0x30) ? 1 : 0; + if (regs->cx == MSR_SVSM_CAA) { + /* Writes to the SVSM CAA msr are ignored */ + if (exit_info_1) + return ES_OK; + + regs->ax = lower_32_bits(this_cpu_read(svsm_caa_pa)); + regs->dx = upper_32_bits(this_cpu_read(svsm_caa_pa)); + + return ES_OK; + } + ghcb_set_rcx(ghcb, regs->cx); if (exit_info_1) { ghcb_set_rax(ghcb, regs->ax); @@ -1346,6 +1488,18 @@ static void __init alloc_runtime_data(int cpu) panic("Can't allocate SEV-ES runtime data"); per_cpu(runtime_data, cpu) = data; + + if (snp_vmpl) { + struct svsm_ca *caa; + + /* Allocate the SVSM CA page if an SVSM is present */ + caa = memblock_alloc(sizeof(*caa), PAGE_SIZE); + if (!caa) + panic("Can't allocate SVSM CA page\n"); + + per_cpu(svsm_caa, cpu) = caa; + per_cpu(svsm_caa_pa, cpu) = __pa(caa); + } } static void __init init_ghcb(int cpu) @@ -1395,6 +1549,32 @@ void __init sev_es_init_vc_handling(void) init_ghcb(cpu); } + /* If running under an SVSM, switch to the per-cpu CA */ + if (snp_vmpl) { + struct svsm_call call = {}; + unsigned long flags; + int ret; + + local_irq_save(flags); + + /* + * SVSM_CORE_REMAP_CA call: + * RAX = 0 (Protocol=0, CallID=0) + * RCX = New CA GPA + */ + call.caa = svsm_get_caa(); + call.rax = SVSM_CORE_CALL(SVSM_CORE_REMAP_CA); + call.rcx = this_cpu_read(svsm_caa_pa); + ret = svsm_perform_call_protocol(&call); + if (ret) + panic("Can't remap the SVSM CA, ret=%d, rax_out=0x%llx\n", + ret, call.rax_out); + + sev_cfg.use_cas = true; + + local_irq_restore(flags); + } + sev_es_setup_play_dead(); /* Secondary CPUs use the runtime #VC handler */ @@ -1819,33 +1999,6 @@ static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, return result; } -static __always_inline void vc_forward_exception(struct es_em_ctxt *ctxt) -{ - long error_code = ctxt->fi.error_code; - int trapnr = ctxt->fi.vector; - - ctxt->regs->orig_ax = ctxt->fi.error_code; - - switch (trapnr) { - case X86_TRAP_GP: - exc_general_protection(ctxt->regs, error_code); - break; - case X86_TRAP_UD: - exc_invalid_op(ctxt->regs); - break; - case X86_TRAP_PF: - write_cr2(ctxt->fi.cr2); - exc_page_fault(ctxt->regs, error_code); - break; - case X86_TRAP_AC: - exc_alignment_check(ctxt->regs, error_code); - break; - default: - pr_emerg("Unsupported exception in #VC instruction emulation - can't continue\n"); - BUG(); - } -} - static __always_inline bool is_vc2_stack(unsigned long sp) { return (sp >= __this_cpu_ist_bottom_va(VC2) && sp < __this_cpu_ist_top_va(VC2)); @@ -2095,6 +2248,47 @@ found_cc_info: return cc_info; } +static __head void svsm_setup(struct cc_blob_sev_info *cc_info) +{ + struct svsm_call call = {}; + int ret; + u64 pa; + + /* + * Record the SVSM Calling Area address (CAA) if the guest is not + * running at VMPL0. The CA will be used to communicate with the + * SVSM to perform the SVSM services. + */ + if (!svsm_setup_ca(cc_info)) + return; + + /* + * It is very early in the boot and the kernel is running identity + * mapped but without having adjusted the pagetables to where the + * kernel was loaded (physbase), so the get the CA address using + * RIP-relative addressing. + */ + pa = (u64)&RIP_REL_REF(boot_svsm_ca_page); + + /* + * Switch over to the boot SVSM CA while the current CA is still + * addressable. There is no GHCB at this point so use the MSR protocol. + * + * SVSM_CORE_REMAP_CA call: + * RAX = 0 (Protocol=0, CallID=0) + * RCX = New CA GPA + */ + call.caa = svsm_get_caa(); + call.rax = SVSM_CORE_CALL(SVSM_CORE_REMAP_CA); + call.rcx = pa; + ret = svsm_perform_call_protocol(&call); + if (ret) + panic("Can't remap the SVSM CA, ret=%d, rax_out=0x%llx\n", ret, call.rax_out); + + RIP_REL_REF(boot_svsm_caa) = (struct svsm_ca *)pa; + RIP_REL_REF(boot_svsm_caa_pa) = pa; +} + bool __head snp_init(struct boot_params *bp) { struct cc_blob_sev_info *cc_info; @@ -2108,6 +2302,8 @@ bool __head snp_init(struct boot_params *bp) setup_cpuid_table(cc_info); + svsm_setup(cc_info); + /* * The CC blob will be used later to access the secrets page. Cache * it here like the boot kernel does. @@ -2156,23 +2352,27 @@ static void dump_cpuid_table(void) * expected, but that initialization happens too early in boot to print any * sort of indicator, and there's not really any other good place to do it, * so do it here. + * + * If running as an SNP guest, report the current VM privilege level (VMPL). */ -static int __init report_cpuid_table(void) +static int __init report_snp_info(void) { const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); - if (!cpuid_table->count) - return 0; + if (cpuid_table->count) { + pr_info("Using SNP CPUID table, %d entries present.\n", + cpuid_table->count); - pr_info("Using SNP CPUID table, %d entries present.\n", - cpuid_table->count); + if (sev_cfg.debug) + dump_cpuid_table(); + } - if (sev_cfg.debug) - dump_cpuid_table(); + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + pr_info("SNP running at VMPL%u.\n", snp_vmpl); return 0; } -arch_initcall(report_cpuid_table); +arch_initcall(report_snp_info); static int __init init_sev_config(char *str) { @@ -2191,6 +2391,56 @@ static int __init init_sev_config(char *str) } __setup("sev=", init_sev_config); +static void update_attest_input(struct svsm_call *call, struct svsm_attest_call *input) +{ + /* If (new) lengths have been returned, propagate them up */ + if (call->rcx_out != call->rcx) + input->manifest_buf.len = call->rcx_out; + + if (call->rdx_out != call->rdx) + input->certificates_buf.len = call->rdx_out; + + if (call->r8_out != call->r8) + input->report_buf.len = call->r8_out; +} + +int snp_issue_svsm_attest_req(u64 call_id, struct svsm_call *call, + struct svsm_attest_call *input) +{ + struct svsm_attest_call *ac; + unsigned long flags; + u64 attest_call_pa; + int ret; + + if (!snp_vmpl) + return -EINVAL; + + local_irq_save(flags); + + call->caa = svsm_get_caa(); + + ac = (struct svsm_attest_call *)call->caa->svsm_buffer; + attest_call_pa = svsm_get_caa_pa() + offsetof(struct svsm_ca, svsm_buffer); + + *ac = *input; + + /* + * Set input registers for the request and set RDX and R8 to known + * values in order to detect length values being returned in them. + */ + call->rax = call_id; + call->rcx = attest_call_pa; + call->rdx = -1; + call->r8 = -1; + ret = svsm_perform_call_protocol(call); + update_attest_input(call, input); + + local_irq_restore(flags); + + return ret; +} +EXPORT_SYMBOL_GPL(snp_issue_svsm_attest_req); + int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio) { struct ghcb_state state; @@ -2299,3 +2549,58 @@ void sev_show_status(void) } pr_cont("\n"); } + +void __init snp_update_svsm_ca(void) +{ + if (!snp_vmpl) + return; + + /* Update the CAA to a proper kernel address */ + boot_svsm_caa = &boot_svsm_ca_page; +} + +#ifdef CONFIG_SYSFS +static ssize_t vmpl_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%d\n", snp_vmpl); +} + +static struct kobj_attribute vmpl_attr = __ATTR_RO(vmpl); + +static struct attribute *vmpl_attrs[] = { + &vmpl_attr.attr, + NULL +}; + +static struct attribute_group sev_attr_group = { + .attrs = vmpl_attrs, +}; + +static int __init sev_sysfs_init(void) +{ + struct kobject *sev_kobj; + struct device *dev_root; + int ret; + + if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + return -ENODEV; + + dev_root = bus_get_dev_root(&cpu_subsys); + if (!dev_root) + return -ENODEV; + + sev_kobj = kobject_create_and_add("sev", &dev_root->kobj); + put_device(dev_root); + + if (!sev_kobj) + return -ENOMEM; + + ret = sysfs_create_group(sev_kobj, &sev_attr_group); + if (ret) + kobject_put(sev_kobj); + + return ret; +} +arch_initcall(sev_sysfs_init); +#endif // CONFIG_SYSFS diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/coco/sev/shared.c similarity index 72% rename from arch/x86/kernel/sev-shared.c rename to arch/x86/coco/sev/shared.c index b4f8fa0f722c..71de53194089 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/coco/sev/shared.c @@ -21,8 +21,30 @@ #define WARN(condition, format...) (!!(condition)) #define sev_printk(fmt, ...) #define sev_printk_rtl(fmt, ...) +#undef vc_forward_exception +#define vc_forward_exception(c) panic("SNP: Hypervisor requested exception\n") #endif +/* + * SVSM related information: + * When running under an SVSM, the VMPL that Linux is executing at must be + * non-zero. The VMPL is therefore used to indicate the presence of an SVSM. + * + * During boot, the page tables are set up as identity mapped and later + * changed to use kernel virtual addresses. Maintain separate virtual and + * physical addresses for the CAA to allow SVSM functions to be used during + * early boot, both with identity mapped virtual addresses and proper kernel + * virtual addresses. + */ +u8 snp_vmpl __ro_after_init; +EXPORT_SYMBOL_GPL(snp_vmpl); +static struct svsm_ca *boot_svsm_caa __ro_after_init; +static u64 boot_svsm_caa_pa __ro_after_init; + +static struct svsm_ca *svsm_get_caa(void); +static u64 svsm_get_caa_pa(void); +static int svsm_perform_call_protocol(struct svsm_call *call); + /* I/O parameters for CPUID-related helpers */ struct cpuid_leaf { u32 fn; @@ -229,6 +251,126 @@ static enum es_result verify_exception_info(struct ghcb *ghcb, struct es_em_ctxt return ES_VMM_ERROR; } +static inline int svsm_process_result_codes(struct svsm_call *call) +{ + switch (call->rax_out) { + case SVSM_SUCCESS: + return 0; + case SVSM_ERR_INCOMPLETE: + case SVSM_ERR_BUSY: + return -EAGAIN; + default: + return -EINVAL; + } +} + +/* + * Issue a VMGEXIT to call the SVSM: + * - Load the SVSM register state (RAX, RCX, RDX, R8 and R9) + * - Set the CA call pending field to 1 + * - Issue VMGEXIT + * - Save the SVSM return register state (RAX, RCX, RDX, R8 and R9) + * - Perform atomic exchange of the CA call pending field + * + * - See the "Secure VM Service Module for SEV-SNP Guests" specification for + * details on the calling convention. + * - The calling convention loosely follows the Microsoft X64 calling + * convention by putting arguments in RCX, RDX, R8 and R9. + * - RAX specifies the SVSM protocol/callid as input and the return code + * as output. + */ +static __always_inline void svsm_issue_call(struct svsm_call *call, u8 *pending) +{ + register unsigned long rax asm("rax") = call->rax; + register unsigned long rcx asm("rcx") = call->rcx; + register unsigned long rdx asm("rdx") = call->rdx; + register unsigned long r8 asm("r8") = call->r8; + register unsigned long r9 asm("r9") = call->r9; + + call->caa->call_pending = 1; + + asm volatile("rep; vmmcall\n\t" + : "+r" (rax), "+r" (rcx), "+r" (rdx), "+r" (r8), "+r" (r9) + : : "memory"); + + *pending = xchg(&call->caa->call_pending, *pending); + + call->rax_out = rax; + call->rcx_out = rcx; + call->rdx_out = rdx; + call->r8_out = r8; + call->r9_out = r9; +} + +static int svsm_perform_msr_protocol(struct svsm_call *call) +{ + u8 pending = 0; + u64 val, resp; + + /* + * When using the MSR protocol, be sure to save and restore + * the current MSR value. + */ + val = sev_es_rd_ghcb_msr(); + + sev_es_wr_ghcb_msr(GHCB_MSR_VMPL_REQ_LEVEL(0)); + + svsm_issue_call(call, &pending); + + resp = sev_es_rd_ghcb_msr(); + + sev_es_wr_ghcb_msr(val); + + if (pending) + return -EINVAL; + + if (GHCB_RESP_CODE(resp) != GHCB_MSR_VMPL_RESP) + return -EINVAL; + + if (GHCB_MSR_VMPL_RESP_VAL(resp)) + return -EINVAL; + + return svsm_process_result_codes(call); +} + +static int svsm_perform_ghcb_protocol(struct ghcb *ghcb, struct svsm_call *call) +{ + struct es_em_ctxt ctxt; + u8 pending = 0; + + vc_ghcb_invalidate(ghcb); + + /* + * Fill in protocol and format specifiers. This can be called very early + * in the boot, so use rip-relative references as needed. + */ + ghcb->protocol_version = RIP_REL_REF(ghcb_version); + ghcb->ghcb_usage = GHCB_DEFAULT_USAGE; + + ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_SNP_RUN_VMPL); + ghcb_set_sw_exit_info_1(ghcb, 0); + ghcb_set_sw_exit_info_2(ghcb, 0); + + sev_es_wr_ghcb_msr(__pa(ghcb)); + + svsm_issue_call(call, &pending); + + if (pending) + return -EINVAL; + + switch (verify_exception_info(ghcb, &ctxt)) { + case ES_OK: + break; + case ES_EXCEPTION: + vc_forward_exception(&ctxt); + fallthrough; + default: + return -EINVAL; + } + + return svsm_process_result_codes(call); +} + static enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, struct es_em_ctxt *ctxt, u64 exit_code, u64 exit_info_1, @@ -1079,40 +1221,270 @@ static void __head setup_cpuid_table(const struct cc_blob_sev_info *cc_info) } } -static void pvalidate_pages(struct snp_psc_desc *desc) +static inline void __pval_terminate(u64 pfn, bool action, unsigned int page_size, + int ret, u64 svsm_ret) +{ + WARN(1, "PVALIDATE failure: pfn: 0x%llx, action: %u, size: %u, ret: %d, svsm_ret: 0x%llx\n", + pfn, action, page_size, ret, svsm_ret); + + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE); +} + +static void svsm_pval_terminate(struct svsm_pvalidate_call *pc, int ret, u64 svsm_ret) +{ + unsigned int page_size; + bool action; + u64 pfn; + + pfn = pc->entry[pc->cur_index].pfn; + action = pc->entry[pc->cur_index].action; + page_size = pc->entry[pc->cur_index].page_size; + + __pval_terminate(pfn, action, page_size, ret, svsm_ret); +} + +static void svsm_pval_4k_page(unsigned long paddr, bool validate) +{ + struct svsm_pvalidate_call *pc; + struct svsm_call call = {}; + unsigned long flags; + u64 pc_pa; + int ret; + + /* + * This can be called very early in the boot, use native functions in + * order to avoid paravirt issues. + */ + flags = native_local_irq_save(); + + call.caa = svsm_get_caa(); + + pc = (struct svsm_pvalidate_call *)call.caa->svsm_buffer; + pc_pa = svsm_get_caa_pa() + offsetof(struct svsm_ca, svsm_buffer); + + pc->num_entries = 1; + pc->cur_index = 0; + pc->entry[0].page_size = RMP_PG_SIZE_4K; + pc->entry[0].action = validate; + pc->entry[0].ignore_cf = 0; + pc->entry[0].pfn = paddr >> PAGE_SHIFT; + + /* Protocol 0, Call ID 1 */ + call.rax = SVSM_CORE_CALL(SVSM_CORE_PVALIDATE); + call.rcx = pc_pa; + + ret = svsm_perform_call_protocol(&call); + if (ret) + svsm_pval_terminate(pc, ret, call.rax_out); + + native_local_irq_restore(flags); +} + +static void pvalidate_4k_page(unsigned long vaddr, unsigned long paddr, bool validate) +{ + int ret; + + /* + * This can be called very early during boot, so use rIP-relative + * references as needed. + */ + if (RIP_REL_REF(snp_vmpl)) { + svsm_pval_4k_page(paddr, validate); + } else { + ret = pvalidate(vaddr, RMP_PG_SIZE_4K, validate); + if (ret) + __pval_terminate(PHYS_PFN(paddr), validate, RMP_PG_SIZE_4K, ret, 0); + } +} + +static void pval_pages(struct snp_psc_desc *desc) { struct psc_entry *e; unsigned long vaddr; unsigned int size; unsigned int i; bool validate; + u64 pfn; int rc; for (i = 0; i <= desc->hdr.end_entry; i++) { e = &desc->entries[i]; - vaddr = (unsigned long)pfn_to_kaddr(e->gfn); + pfn = e->gfn; + vaddr = (unsigned long)pfn_to_kaddr(pfn); size = e->pagesize ? RMP_PG_SIZE_2M : RMP_PG_SIZE_4K; validate = e->operation == SNP_PAGE_STATE_PRIVATE; rc = pvalidate(vaddr, size, validate); + if (!rc) + continue; + if (rc == PVALIDATE_FAIL_SIZEMISMATCH && size == RMP_PG_SIZE_2M) { unsigned long vaddr_end = vaddr + PMD_SIZE; - for (; vaddr < vaddr_end; vaddr += PAGE_SIZE) { + for (; vaddr < vaddr_end; vaddr += PAGE_SIZE, pfn++) { rc = pvalidate(vaddr, RMP_PG_SIZE_4K, validate); if (rc) - break; + __pval_terminate(pfn, validate, RMP_PG_SIZE_4K, rc, 0); } - } - - if (rc) { - WARN(1, "Failed to validate address 0x%lx ret %d", vaddr, rc); - sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE); + } else { + __pval_terminate(pfn, validate, size, rc, 0); } } } +static u64 svsm_build_ca_from_pfn_range(u64 pfn, u64 pfn_end, bool action, + struct svsm_pvalidate_call *pc) +{ + struct svsm_pvalidate_entry *pe; + + /* Nothing in the CA yet */ + pc->num_entries = 0; + pc->cur_index = 0; + + pe = &pc->entry[0]; + + while (pfn < pfn_end) { + pe->page_size = RMP_PG_SIZE_4K; + pe->action = action; + pe->ignore_cf = 0; + pe->pfn = pfn; + + pe++; + pfn++; + + pc->num_entries++; + if (pc->num_entries == SVSM_PVALIDATE_MAX_COUNT) + break; + } + + return pfn; +} + +static int svsm_build_ca_from_psc_desc(struct snp_psc_desc *desc, unsigned int desc_entry, + struct svsm_pvalidate_call *pc) +{ + struct svsm_pvalidate_entry *pe; + struct psc_entry *e; + + /* Nothing in the CA yet */ + pc->num_entries = 0; + pc->cur_index = 0; + + pe = &pc->entry[0]; + e = &desc->entries[desc_entry]; + + while (desc_entry <= desc->hdr.end_entry) { + pe->page_size = e->pagesize ? RMP_PG_SIZE_2M : RMP_PG_SIZE_4K; + pe->action = e->operation == SNP_PAGE_STATE_PRIVATE; + pe->ignore_cf = 0; + pe->pfn = e->gfn; + + pe++; + e++; + + desc_entry++; + pc->num_entries++; + if (pc->num_entries == SVSM_PVALIDATE_MAX_COUNT) + break; + } + + return desc_entry; +} + +static void svsm_pval_pages(struct snp_psc_desc *desc) +{ + struct svsm_pvalidate_entry pv_4k[VMGEXIT_PSC_MAX_ENTRY]; + unsigned int i, pv_4k_count = 0; + struct svsm_pvalidate_call *pc; + struct svsm_call call = {}; + unsigned long flags; + bool action; + u64 pc_pa; + int ret; + + /* + * This can be called very early in the boot, use native functions in + * order to avoid paravirt issues. + */ + flags = native_local_irq_save(); + + /* + * The SVSM calling area (CA) can support processing 510 entries at a + * time. Loop through the Page State Change descriptor until the CA is + * full or the last entry in the descriptor is reached, at which time + * the SVSM is invoked. This repeats until all entries in the descriptor + * are processed. + */ + call.caa = svsm_get_caa(); + + pc = (struct svsm_pvalidate_call *)call.caa->svsm_buffer; + pc_pa = svsm_get_caa_pa() + offsetof(struct svsm_ca, svsm_buffer); + + /* Protocol 0, Call ID 1 */ + call.rax = SVSM_CORE_CALL(SVSM_CORE_PVALIDATE); + call.rcx = pc_pa; + + for (i = 0; i <= desc->hdr.end_entry;) { + i = svsm_build_ca_from_psc_desc(desc, i, pc); + + do { + ret = svsm_perform_call_protocol(&call); + if (!ret) + continue; + + /* + * Check if the entry failed because of an RMP mismatch (a + * PVALIDATE at 2M was requested, but the page is mapped in + * the RMP as 4K). + */ + + if (call.rax_out == SVSM_PVALIDATE_FAIL_SIZEMISMATCH && + pc->entry[pc->cur_index].page_size == RMP_PG_SIZE_2M) { + /* Save this entry for post-processing at 4K */ + pv_4k[pv_4k_count++] = pc->entry[pc->cur_index]; + + /* Skip to the next one unless at the end of the list */ + pc->cur_index++; + if (pc->cur_index < pc->num_entries) + ret = -EAGAIN; + else + ret = 0; + } + } while (ret == -EAGAIN); + + if (ret) + svsm_pval_terminate(pc, ret, call.rax_out); + } + + /* Process any entries that failed to be validated at 2M and validate them at 4K */ + for (i = 0; i < pv_4k_count; i++) { + u64 pfn, pfn_end; + + action = pv_4k[i].action; + pfn = pv_4k[i].pfn; + pfn_end = pfn + 512; + + while (pfn < pfn_end) { + pfn = svsm_build_ca_from_pfn_range(pfn, pfn_end, action, pc); + + ret = svsm_perform_call_protocol(&call); + if (ret) + svsm_pval_terminate(pc, ret, call.rax_out); + } + } + + native_local_irq_restore(flags); +} + +static void pvalidate_pages(struct snp_psc_desc *desc) +{ + if (snp_vmpl) + svsm_pval_pages(desc); + else + pval_pages(desc); +} + static int vmgexit_psc(struct ghcb *ghcb, struct snp_psc_desc *desc) { int cur_entry, end_entry, ret = 0; @@ -1269,3 +1641,77 @@ static enum es_result vc_check_opcode_bytes(struct es_em_ctxt *ctxt, return ES_UNSUPPORTED; } + +/* + * Maintain the GPA of the SVSM Calling Area (CA) in order to utilize the SVSM + * services needed when not running in VMPL0. + */ +static bool __head svsm_setup_ca(const struct cc_blob_sev_info *cc_info) +{ + struct snp_secrets_page *secrets_page; + struct snp_cpuid_table *cpuid_table; + unsigned int i; + u64 caa; + + BUILD_BUG_ON(sizeof(*secrets_page) != PAGE_SIZE); + + /* + * Check if running at VMPL0. + * + * Use RMPADJUST (see the rmpadjust() function for a description of what + * the instruction does) to update the VMPL1 permissions of a page. If + * the guest is running at VMPL0, this will succeed and implies there is + * no SVSM. If the guest is running at any other VMPL, this will fail. + * Linux SNP guests only ever run at a single VMPL level so permission mask + * changes of a lesser-privileged VMPL are a don't-care. + * + * Use a rip-relative reference to obtain the proper address, since this + * routine is running identity mapped when called, both by the decompressor + * code and the early kernel code. + */ + if (!rmpadjust((unsigned long)&RIP_REL_REF(boot_ghcb_page), RMP_PG_SIZE_4K, 1)) + return false; + + /* + * Not running at VMPL0, ensure everything has been properly supplied + * for running under an SVSM. + */ + if (!cc_info || !cc_info->secrets_phys || cc_info->secrets_len != PAGE_SIZE) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SECRETS_PAGE); + + secrets_page = (struct snp_secrets_page *)cc_info->secrets_phys; + if (!secrets_page->svsm_size) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_NO_SVSM); + + if (!secrets_page->svsm_guest_vmpl) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SVSM_VMPL0); + + RIP_REL_REF(snp_vmpl) = secrets_page->svsm_guest_vmpl; + + caa = secrets_page->svsm_caa; + + /* + * An open-coded PAGE_ALIGNED() in order to avoid including + * kernel-proper headers into the decompressor. + */ + if (caa & (PAGE_SIZE - 1)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SVSM_CAA); + + /* + * The CA is identity mapped when this routine is called, both by the + * decompressor code and the early kernel code. + */ + RIP_REL_REF(boot_svsm_caa) = (struct svsm_ca *)caa; + RIP_REL_REF(boot_svsm_caa_pa) = caa; + + /* Advertise the SVSM presence via CPUID. */ + cpuid_table = (struct snp_cpuid_table *)snp_cpuid_get_table(); + for (i = 0; i < cpuid_table->count; i++) { + struct snp_cpuid_fn *fn = &cpuid_table->fn[i]; + + if (fn->eax_in == 0x8000001f) + fn->eax |= BIT(28); + } + + return true; +} diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index c1cb90369915..078e2bac2553 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -14,6 +15,7 @@ #include #include #include +#include /* MMIO direction */ #define EPT_READ 0 @@ -38,6 +40,8 @@ #define TDREPORT_SUBTYPE_0 0 +static atomic_long_t nr_shared; + /* Called from __tdx_hypercall() for unrecoverable failure */ noinstr void __noreturn __tdx_hypercall_failed(void) { @@ -798,28 +802,124 @@ static bool tdx_enc_status_changed(unsigned long vaddr, int numpages, bool enc) return true; } -static bool tdx_enc_status_change_prepare(unsigned long vaddr, int numpages, - bool enc) +static int tdx_enc_status_change_prepare(unsigned long vaddr, int numpages, + bool enc) { /* * Only handle shared->private conversion here. * See the comment in tdx_early_init(). */ - if (enc) - return tdx_enc_status_changed(vaddr, numpages, enc); - return true; + if (enc && !tdx_enc_status_changed(vaddr, numpages, enc)) + return -EIO; + + return 0; } -static bool tdx_enc_status_change_finish(unsigned long vaddr, int numpages, +static int tdx_enc_status_change_finish(unsigned long vaddr, int numpages, bool enc) { /* * Only handle private->shared conversion here. * See the comment in tdx_early_init(). */ - if (!enc) - return tdx_enc_status_changed(vaddr, numpages, enc); - return true; + if (!enc && !tdx_enc_status_changed(vaddr, numpages, enc)) + return -EIO; + + if (enc) + atomic_long_sub(numpages, &nr_shared); + else + atomic_long_add(numpages, &nr_shared); + + return 0; +} + +/* Stop new private<->shared conversions */ +static void tdx_kexec_begin(void) +{ + if (!IS_ENABLED(CONFIG_KEXEC_CORE)) + return; + + /* + * Crash kernel reaches here with interrupts disabled: can't wait for + * conversions to finish. + * + * If race happened, just report and proceed. + */ + if (!set_memory_enc_stop_conversion()) + pr_warn("Failed to stop shared<->private conversions\n"); +} + +/* Walk direct mapping and convert all shared memory back to private */ +static void tdx_kexec_finish(void) +{ + unsigned long addr, end; + long found = 0, shared; + + if (!IS_ENABLED(CONFIG_KEXEC_CORE)) + return; + + lockdep_assert_irqs_disabled(); + + addr = PAGE_OFFSET; + end = PAGE_OFFSET + get_max_mapped(); + + while (addr < end) { + unsigned long size; + unsigned int level; + pte_t *pte; + + pte = lookup_address(addr, &level); + size = page_level_size(level); + + if (pte && pte_decrypted(*pte)) { + int pages = size / PAGE_SIZE; + + /* + * Touching memory with shared bit set triggers implicit + * conversion to shared. + * + * Make sure nobody touches the shared range from + * now on. + */ + set_pte(pte, __pte(0)); + + /* + * Memory encryption state persists across kexec. + * If tdx_enc_status_changed() fails in the first + * kernel, it leaves memory in an unknown state. + * + * If that memory remains shared, accessing it in the + * *next* kernel through a private mapping will result + * in an unrecoverable guest shutdown. + * + * The kdump kernel boot is not impacted as it uses + * a pre-reserved memory range that is always private. + * However, gathering crash information could lead to + * a crash if it accesses unconverted memory through + * a private mapping which is possible when accessing + * that memory through /proc/vmcore, for example. + * + * In all cases, print error info in order to leave + * enough bread crumbs for debugging. + */ + if (!tdx_enc_status_changed(addr, pages, true)) { + pr_err("Failed to unshare range %#lx-%#lx\n", + addr, addr + size); + } + + found += pages; + } + + addr += size; + } + + __flush_tlb_all(); + + shared = atomic_long_read(&nr_shared); + if (shared != found) { + pr_err("shared page accounting is off\n"); + pr_err("nr_shared = %ld, nr_found = %ld\n", shared, found); + } } void __init tdx_early_init(void) @@ -881,6 +981,9 @@ void __init tdx_early_init(void) x86_platform.guest.enc_cache_flush_required = tdx_cache_flush_required; x86_platform.guest.enc_tlb_flush_required = tdx_tlb_flush_required; + x86_platform.guest.enc_kexec_begin = tdx_kexec_begin; + x86_platform.guest.enc_kexec_finish = tdx_kexec_finish; + /* * TDX intercepts the RDMSR to read the X2APIC ID in the parallel * bringup low level code. That raises #VE which cannot be handled diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c index c2235bae17ef..8cc9950d7104 100644 --- a/arch/x86/entry/syscall_32.c +++ b/arch/x86/entry/syscall_32.c @@ -14,9 +14,12 @@ #endif #define __SYSCALL(nr, sym) extern long __ia32_##sym(const struct pt_regs *); - +#define __SYSCALL_NORETURN(nr, sym) extern long __noreturn __ia32_##sym(const struct pt_regs *); #include -#undef __SYSCALL +#undef __SYSCALL + +#undef __SYSCALL_NORETURN +#define __SYSCALL_NORETURN __SYSCALL /* * The sys_call_table[] is no longer used for system calls, but @@ -28,11 +31,10 @@ const sys_call_ptr_t sys_call_table[] = { #include }; -#undef __SYSCALL +#undef __SYSCALL #endif #define __SYSCALL(nr, sym) case nr: return __ia32_##sym(regs); - long ia32_sys_call(const struct pt_regs *regs, unsigned int nr) { switch (nr) { diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index 33b3f09e6f15..ba8354424860 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -8,8 +8,12 @@ #include #define __SYSCALL(nr, sym) extern long __x64_##sym(const struct pt_regs *); +#define __SYSCALL_NORETURN(nr, sym) extern long __noreturn __x64_##sym(const struct pt_regs *); #include -#undef __SYSCALL +#undef __SYSCALL + +#undef __SYSCALL_NORETURN +#define __SYSCALL_NORETURN __SYSCALL /* * The sys_call_table[] is no longer used for system calls, but @@ -20,10 +24,9 @@ const sys_call_ptr_t sys_call_table[] = { #include }; -#undef __SYSCALL +#undef __SYSCALL #define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs); - long x64_sys_call(const struct pt_regs *regs, unsigned int nr) { switch (nr) { diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c index 03de4a932131..fb77908f44f3 100644 --- a/arch/x86/entry/syscall_x32.c +++ b/arch/x86/entry/syscall_x32.c @@ -8,11 +8,14 @@ #include #define __SYSCALL(nr, sym) extern long __x64_##sym(const struct pt_regs *); +#define __SYSCALL_NORETURN(nr, sym) extern long __noreturn __x64_##sym(const struct pt_regs *); #include -#undef __SYSCALL +#undef __SYSCALL + +#undef __SYSCALL_NORETURN +#define __SYSCALL_NORETURN __SYSCALL #define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs); - long x32_sys_call(const struct pt_regs *regs, unsigned int nr) { switch (nr) { diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index d6ebcab1d8b2..534c74b14fab 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -1,8 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note # # 32-bit system call numbers and entry vectors # # The format is: -# +# [ [noreturn]] # # The __ia32_sys and __ia32_compat_sys stubs are created on-the-fly for # sys_*() system calls and compat_sys_*() compat system calls if @@ -12,7 +13,7 @@ # The abi is always "i386" for this file. # 0 i386 restart_syscall sys_restart_syscall -1 i386 exit sys_exit +1 i386 exit sys_exit - noreturn 2 i386 fork sys_fork 3 i386 read sys_read 4 i386 write sys_write @@ -263,7 +264,7 @@ 249 i386 io_cancel sys_io_cancel 250 i386 fadvise64 sys_ia32_fadvise64 # 251 is available for reuse (was briefly sys_set_zone_reclaim) -252 i386 exit_group sys_exit_group +252 i386 exit_group sys_exit_group - noreturn 253 i386 lookup_dcookie 254 i386 epoll_create sys_epoll_create 255 i386 epoll_ctl sys_epoll_ctl diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index a396f6e6ab5b..097e5a18db52 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -1,8 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note # # 64-bit system call numbers and entry vectors # # The format is: -# +# [ [noreturn]] # # The __x64_sys_*() stubs are created on-the-fly for sys_*() system calls # @@ -68,7 +69,7 @@ 57 common fork sys_fork 58 common vfork sys_vfork 59 64 execve sys_execve -60 common exit sys_exit +60 common exit sys_exit - noreturn 61 common wait4 sys_wait4 62 common kill sys_kill 63 common uname sys_newuname @@ -239,7 +240,7 @@ 228 common clock_gettime sys_clock_gettime 229 common clock_getres sys_clock_getres 230 common clock_nanosleep sys_clock_nanosleep -231 common exit_group sys_exit_group +231 common exit_group sys_exit_group - noreturn 232 common epoll_wait sys_epoll_wait 233 common epoll_ctl sys_epoll_ctl 234 common tgkill sys_tgkill diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 38c1b1f1deaa..0e835dc134a5 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4698,8 +4698,8 @@ static void intel_pmu_check_extra_regs(struct extra_reg *extra_regs); static inline bool intel_pmu_broken_perf_cap(void) { /* The Perf Metric (Bit 15) is always cleared */ - if ((boot_cpu_data.x86_model == INTEL_FAM6_METEORLAKE) || - (boot_cpu_data.x86_model == INTEL_FAM6_METEORLAKE_L)) + if (boot_cpu_data.x86_vfm == INTEL_METEORLAKE || + boot_cpu_data.x86_vfm == INTEL_METEORLAKE_L) return true; return false; @@ -5187,35 +5187,35 @@ static __init void intel_clovertown_quirk(void) } static const struct x86_cpu_desc isolation_ucodes[] = { - INTEL_CPU_DESC(INTEL_FAM6_HASWELL, 3, 0x0000001f), - INTEL_CPU_DESC(INTEL_FAM6_HASWELL_L, 1, 0x0000001e), - INTEL_CPU_DESC(INTEL_FAM6_HASWELL_G, 1, 0x00000015), - INTEL_CPU_DESC(INTEL_FAM6_HASWELL_X, 2, 0x00000037), - INTEL_CPU_DESC(INTEL_FAM6_HASWELL_X, 4, 0x0000000a), - INTEL_CPU_DESC(INTEL_FAM6_BROADWELL, 4, 0x00000023), - INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_G, 1, 0x00000014), - INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 2, 0x00000010), - INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 3, 0x07000009), - INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 4, 0x0f000009), - INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 5, 0x0e000002), - INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_X, 1, 0x0b000014), - INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 3, 0x00000021), - INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 4, 0x00000000), - INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 5, 0x00000000), - INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 6, 0x00000000), - INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 7, 0x00000000), - INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 11, 0x00000000), - INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_L, 3, 0x0000007c), - INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE, 3, 0x0000007c), - INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 9, 0x0000004e), - INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_L, 9, 0x0000004e), - INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_L, 10, 0x0000004e), - INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_L, 11, 0x0000004e), - INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_L, 12, 0x0000004e), - INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 10, 0x0000004e), - INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 11, 0x0000004e), - INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 12, 0x0000004e), - INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 13, 0x0000004e), + INTEL_CPU_DESC(INTEL_HASWELL, 3, 0x0000001f), + INTEL_CPU_DESC(INTEL_HASWELL_L, 1, 0x0000001e), + INTEL_CPU_DESC(INTEL_HASWELL_G, 1, 0x00000015), + INTEL_CPU_DESC(INTEL_HASWELL_X, 2, 0x00000037), + INTEL_CPU_DESC(INTEL_HASWELL_X, 4, 0x0000000a), + INTEL_CPU_DESC(INTEL_BROADWELL, 4, 0x00000023), + INTEL_CPU_DESC(INTEL_BROADWELL_G, 1, 0x00000014), + INTEL_CPU_DESC(INTEL_BROADWELL_D, 2, 0x00000010), + INTEL_CPU_DESC(INTEL_BROADWELL_D, 3, 0x07000009), + INTEL_CPU_DESC(INTEL_BROADWELL_D, 4, 0x0f000009), + INTEL_CPU_DESC(INTEL_BROADWELL_D, 5, 0x0e000002), + INTEL_CPU_DESC(INTEL_BROADWELL_X, 1, 0x0b000014), + INTEL_CPU_DESC(INTEL_SKYLAKE_X, 3, 0x00000021), + INTEL_CPU_DESC(INTEL_SKYLAKE_X, 4, 0x00000000), + INTEL_CPU_DESC(INTEL_SKYLAKE_X, 5, 0x00000000), + INTEL_CPU_DESC(INTEL_SKYLAKE_X, 6, 0x00000000), + INTEL_CPU_DESC(INTEL_SKYLAKE_X, 7, 0x00000000), + INTEL_CPU_DESC(INTEL_SKYLAKE_X, 11, 0x00000000), + INTEL_CPU_DESC(INTEL_SKYLAKE_L, 3, 0x0000007c), + INTEL_CPU_DESC(INTEL_SKYLAKE, 3, 0x0000007c), + INTEL_CPU_DESC(INTEL_KABYLAKE, 9, 0x0000004e), + INTEL_CPU_DESC(INTEL_KABYLAKE_L, 9, 0x0000004e), + INTEL_CPU_DESC(INTEL_KABYLAKE_L, 10, 0x0000004e), + INTEL_CPU_DESC(INTEL_KABYLAKE_L, 11, 0x0000004e), + INTEL_CPU_DESC(INTEL_KABYLAKE_L, 12, 0x0000004e), + INTEL_CPU_DESC(INTEL_KABYLAKE, 10, 0x0000004e), + INTEL_CPU_DESC(INTEL_KABYLAKE, 11, 0x0000004e), + INTEL_CPU_DESC(INTEL_KABYLAKE, 12, 0x0000004e), + INTEL_CPU_DESC(INTEL_KABYLAKE, 13, 0x0000004e), {} }; @@ -5232,9 +5232,9 @@ static __init void intel_pebs_isolation_quirk(void) } static const struct x86_cpu_desc pebs_ucodes[] = { - INTEL_CPU_DESC(INTEL_FAM6_SANDYBRIDGE, 7, 0x00000028), - INTEL_CPU_DESC(INTEL_FAM6_SANDYBRIDGE_X, 6, 0x00000618), - INTEL_CPU_DESC(INTEL_FAM6_SANDYBRIDGE_X, 7, 0x0000070c), + INTEL_CPU_DESC(INTEL_SANDYBRIDGE, 7, 0x00000028), + INTEL_CPU_DESC(INTEL_SANDYBRIDGE_X, 6, 0x00000618), + INTEL_CPU_DESC(INTEL_SANDYBRIDGE_X, 7, 0x0000070c), {} }; @@ -6238,19 +6238,19 @@ __init int intel_pmu_init(void) /* * Install the hw-cache-events table: */ - switch (boot_cpu_data.x86_model) { - case INTEL_FAM6_CORE_YONAH: + switch (boot_cpu_data.x86_vfm) { + case INTEL_CORE_YONAH: pr_cont("Core events, "); name = "core"; break; - case INTEL_FAM6_CORE2_MEROM: + case INTEL_CORE2_MEROM: x86_add_quirk(intel_clovertown_quirk); fallthrough; - case INTEL_FAM6_CORE2_MEROM_L: - case INTEL_FAM6_CORE2_PENRYN: - case INTEL_FAM6_CORE2_DUNNINGTON: + case INTEL_CORE2_MEROM_L: + case INTEL_CORE2_PENRYN: + case INTEL_CORE2_DUNNINGTON: memcpy(hw_cache_event_ids, core2_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -6262,9 +6262,9 @@ __init int intel_pmu_init(void) name = "core2"; break; - case INTEL_FAM6_NEHALEM: - case INTEL_FAM6_NEHALEM_EP: - case INTEL_FAM6_NEHALEM_EX: + case INTEL_NEHALEM: + case INTEL_NEHALEM_EP: + case INTEL_NEHALEM_EX: memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs, @@ -6296,11 +6296,11 @@ __init int intel_pmu_init(void) name = "nehalem"; break; - case INTEL_FAM6_ATOM_BONNELL: - case INTEL_FAM6_ATOM_BONNELL_MID: - case INTEL_FAM6_ATOM_SALTWELL: - case INTEL_FAM6_ATOM_SALTWELL_MID: - case INTEL_FAM6_ATOM_SALTWELL_TABLET: + case INTEL_ATOM_BONNELL: + case INTEL_ATOM_BONNELL_MID: + case INTEL_ATOM_SALTWELL: + case INTEL_ATOM_SALTWELL_MID: + case INTEL_ATOM_SALTWELL_TABLET: memcpy(hw_cache_event_ids, atom_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -6313,11 +6313,11 @@ __init int intel_pmu_init(void) name = "bonnell"; break; - case INTEL_FAM6_ATOM_SILVERMONT: - case INTEL_FAM6_ATOM_SILVERMONT_D: - case INTEL_FAM6_ATOM_SILVERMONT_MID: - case INTEL_FAM6_ATOM_AIRMONT: - case INTEL_FAM6_ATOM_AIRMONT_MID: + case INTEL_ATOM_SILVERMONT: + case INTEL_ATOM_SILVERMONT_D: + case INTEL_ATOM_SILVERMONT_MID: + case INTEL_ATOM_AIRMONT: + case INTEL_ATOM_AIRMONT_MID: memcpy(hw_cache_event_ids, slm_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs, @@ -6335,8 +6335,8 @@ __init int intel_pmu_init(void) name = "silvermont"; break; - case INTEL_FAM6_ATOM_GOLDMONT: - case INTEL_FAM6_ATOM_GOLDMONT_D: + case INTEL_ATOM_GOLDMONT: + case INTEL_ATOM_GOLDMONT_D: memcpy(hw_cache_event_ids, glm_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, glm_hw_cache_extra_regs, @@ -6362,7 +6362,7 @@ __init int intel_pmu_init(void) name = "goldmont"; break; - case INTEL_FAM6_ATOM_GOLDMONT_PLUS: + case INTEL_ATOM_GOLDMONT_PLUS: memcpy(hw_cache_event_ids, glp_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, glp_hw_cache_extra_regs, @@ -6391,9 +6391,9 @@ __init int intel_pmu_init(void) name = "goldmont_plus"; break; - case INTEL_FAM6_ATOM_TREMONT_D: - case INTEL_FAM6_ATOM_TREMONT: - case INTEL_FAM6_ATOM_TREMONT_L: + case INTEL_ATOM_TREMONT_D: + case INTEL_ATOM_TREMONT: + case INTEL_ATOM_TREMONT_L: x86_pmu.late_ack = true; memcpy(hw_cache_event_ids, glp_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -6420,7 +6420,7 @@ __init int intel_pmu_init(void) name = "Tremont"; break; - case INTEL_FAM6_ATOM_GRACEMONT: + case INTEL_ATOM_GRACEMONT: intel_pmu_init_grt(NULL); intel_pmu_pebs_data_source_grt(); x86_pmu.pebs_latency_data = adl_latency_data_small; @@ -6432,8 +6432,8 @@ __init int intel_pmu_init(void) name = "gracemont"; break; - case INTEL_FAM6_ATOM_CRESTMONT: - case INTEL_FAM6_ATOM_CRESTMONT_X: + case INTEL_ATOM_CRESTMONT: + case INTEL_ATOM_CRESTMONT_X: intel_pmu_init_grt(NULL); x86_pmu.extra_regs = intel_cmt_extra_regs; intel_pmu_pebs_data_source_cmt(); @@ -6446,9 +6446,9 @@ __init int intel_pmu_init(void) name = "crestmont"; break; - case INTEL_FAM6_WESTMERE: - case INTEL_FAM6_WESTMERE_EP: - case INTEL_FAM6_WESTMERE_EX: + case INTEL_WESTMERE: + case INTEL_WESTMERE_EP: + case INTEL_WESTMERE_EX: memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs, @@ -6477,8 +6477,8 @@ __init int intel_pmu_init(void) name = "westmere"; break; - case INTEL_FAM6_SANDYBRIDGE: - case INTEL_FAM6_SANDYBRIDGE_X: + case INTEL_SANDYBRIDGE: + case INTEL_SANDYBRIDGE_X: x86_add_quirk(intel_sandybridge_quirk); x86_add_quirk(intel_ht_bug); memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, @@ -6491,7 +6491,7 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_snb_event_constraints; x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints; x86_pmu.pebs_aliases = intel_pebs_aliases_snb; - if (boot_cpu_data.x86_model == INTEL_FAM6_SANDYBRIDGE_X) + if (boot_cpu_data.x86_vfm == INTEL_SANDYBRIDGE_X) x86_pmu.extra_regs = intel_snbep_extra_regs; else x86_pmu.extra_regs = intel_snb_extra_regs; @@ -6517,8 +6517,8 @@ __init int intel_pmu_init(void) name = "sandybridge"; break; - case INTEL_FAM6_IVYBRIDGE: - case INTEL_FAM6_IVYBRIDGE_X: + case INTEL_IVYBRIDGE: + case INTEL_IVYBRIDGE_X: x86_add_quirk(intel_ht_bug); memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -6534,7 +6534,7 @@ __init int intel_pmu_init(void) x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints; x86_pmu.pebs_aliases = intel_pebs_aliases_ivb; x86_pmu.pebs_prec_dist = true; - if (boot_cpu_data.x86_model == INTEL_FAM6_IVYBRIDGE_X) + if (boot_cpu_data.x86_vfm == INTEL_IVYBRIDGE_X) x86_pmu.extra_regs = intel_snbep_extra_regs; else x86_pmu.extra_regs = intel_snb_extra_regs; @@ -6556,10 +6556,10 @@ __init int intel_pmu_init(void) break; - case INTEL_FAM6_HASWELL: - case INTEL_FAM6_HASWELL_X: - case INTEL_FAM6_HASWELL_L: - case INTEL_FAM6_HASWELL_G: + case INTEL_HASWELL: + case INTEL_HASWELL_X: + case INTEL_HASWELL_L: + case INTEL_HASWELL_G: x86_add_quirk(intel_ht_bug); x86_add_quirk(intel_pebs_isolation_quirk); x86_pmu.late_ack = true; @@ -6589,10 +6589,10 @@ __init int intel_pmu_init(void) name = "haswell"; break; - case INTEL_FAM6_BROADWELL: - case INTEL_FAM6_BROADWELL_D: - case INTEL_FAM6_BROADWELL_G: - case INTEL_FAM6_BROADWELL_X: + case INTEL_BROADWELL: + case INTEL_BROADWELL_D: + case INTEL_BROADWELL_G: + case INTEL_BROADWELL_X: x86_add_quirk(intel_pebs_isolation_quirk); x86_pmu.late_ack = true; memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -6631,8 +6631,8 @@ __init int intel_pmu_init(void) name = "broadwell"; break; - case INTEL_FAM6_XEON_PHI_KNL: - case INTEL_FAM6_XEON_PHI_KNM: + case INTEL_XEON_PHI_KNL: + case INTEL_XEON_PHI_KNM: memcpy(hw_cache_event_ids, slm_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, @@ -6651,15 +6651,15 @@ __init int intel_pmu_init(void) name = "knights-landing"; break; - case INTEL_FAM6_SKYLAKE_X: + case INTEL_SKYLAKE_X: pmem = true; fallthrough; - case INTEL_FAM6_SKYLAKE_L: - case INTEL_FAM6_SKYLAKE: - case INTEL_FAM6_KABYLAKE_L: - case INTEL_FAM6_KABYLAKE: - case INTEL_FAM6_COMETLAKE_L: - case INTEL_FAM6_COMETLAKE: + case INTEL_SKYLAKE_L: + case INTEL_SKYLAKE: + case INTEL_KABYLAKE_L: + case INTEL_KABYLAKE: + case INTEL_COMETLAKE_L: + case INTEL_COMETLAKE: x86_add_quirk(intel_pebs_isolation_quirk); x86_pmu.late_ack = true; memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -6708,16 +6708,16 @@ __init int intel_pmu_init(void) name = "skylake"; break; - case INTEL_FAM6_ICELAKE_X: - case INTEL_FAM6_ICELAKE_D: + case INTEL_ICELAKE_X: + case INTEL_ICELAKE_D: x86_pmu.pebs_ept = 1; pmem = true; fallthrough; - case INTEL_FAM6_ICELAKE_L: - case INTEL_FAM6_ICELAKE: - case INTEL_FAM6_TIGERLAKE_L: - case INTEL_FAM6_TIGERLAKE: - case INTEL_FAM6_ROCKETLAKE: + case INTEL_ICELAKE_L: + case INTEL_ICELAKE: + case INTEL_TIGERLAKE_L: + case INTEL_TIGERLAKE: + case INTEL_ROCKETLAKE: x86_pmu.late_ack = true; memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); @@ -6752,13 +6752,13 @@ __init int intel_pmu_init(void) name = "icelake"; break; - case INTEL_FAM6_SAPPHIRERAPIDS_X: - case INTEL_FAM6_EMERALDRAPIDS_X: + case INTEL_SAPPHIRERAPIDS_X: + case INTEL_EMERALDRAPIDS_X: x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX; x86_pmu.extra_regs = intel_glc_extra_regs; fallthrough; - case INTEL_FAM6_GRANITERAPIDS_X: - case INTEL_FAM6_GRANITERAPIDS_D: + case INTEL_GRANITERAPIDS_X: + case INTEL_GRANITERAPIDS_D: intel_pmu_init_glc(NULL); if (!x86_pmu.extra_regs) x86_pmu.extra_regs = intel_rwc_extra_regs; @@ -6776,11 +6776,11 @@ __init int intel_pmu_init(void) name = "sapphire_rapids"; break; - case INTEL_FAM6_ALDERLAKE: - case INTEL_FAM6_ALDERLAKE_L: - case INTEL_FAM6_RAPTORLAKE: - case INTEL_FAM6_RAPTORLAKE_P: - case INTEL_FAM6_RAPTORLAKE_S: + case INTEL_ALDERLAKE: + case INTEL_ALDERLAKE_L: + case INTEL_RAPTORLAKE: + case INTEL_RAPTORLAKE_P: + case INTEL_RAPTORLAKE_S: /* * Alder Lake has 2 types of CPU, core and atom. * @@ -6838,8 +6838,8 @@ __init int intel_pmu_init(void) name = "alderlake_hybrid"; break; - case INTEL_FAM6_METEORLAKE: - case INTEL_FAM6_METEORLAKE_L: + case INTEL_METEORLAKE: + case INTEL_METEORLAKE_L: intel_pmu_init_hybrid(hybrid_big_small); x86_pmu.pebs_latency_data = mtl_latency_data_small; diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index 0c5e7a7c43ac..b985ca79cf97 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -765,51 +765,51 @@ static struct rapl_model model_amd_hygon = { }; static const struct x86_cpu_id rapl_model_match[] __initconst = { - X86_MATCH_FEATURE(X86_FEATURE_RAPL, &model_amd_hygon), - X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE, &model_snb), - X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE_X, &model_snbep), - X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE, &model_snb), - X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X, &model_snbep), - X86_MATCH_INTEL_FAM6_MODEL(HASWELL, &model_hsw), - X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X, &model_hsx), - X86_MATCH_INTEL_FAM6_MODEL(HASWELL_L, &model_hsw), - X86_MATCH_INTEL_FAM6_MODEL(HASWELL_G, &model_hsw), - X86_MATCH_INTEL_FAM6_MODEL(BROADWELL, &model_hsw), - X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_G, &model_hsw), - X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X, &model_hsx), - X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D, &model_hsx), - X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL, &model_knl), - X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM, &model_knl), - X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L, &model_skl), - X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE, &model_skl), - X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, &model_hsx), - X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L, &model_skl), - X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE, &model_skl), - X86_MATCH_INTEL_FAM6_MODEL(CANNONLAKE_L, &model_skl), - X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, &model_hsw), - X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_D, &model_hsw), - X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS, &model_hsw), - X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, &model_skl), - X86_MATCH_INTEL_FAM6_MODEL(ICELAKE, &model_skl), - X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &model_hsx), - X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &model_hsx), - X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L, &model_skl), - X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, &model_skl), - X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &model_skl), - X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &model_skl), - X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &model_skl), - X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &model_skl), - X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT, &model_skl), - X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &model_spr), - X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &model_spr), - X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &model_skl), - X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &model_skl), - X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &model_skl), - X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, &model_skl), - X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, &model_skl), - X86_MATCH_INTEL_FAM6_MODEL(ARROWLAKE_H, &model_skl), - X86_MATCH_INTEL_FAM6_MODEL(ARROWLAKE, &model_skl), - X86_MATCH_INTEL_FAM6_MODEL(LUNARLAKE_M, &model_skl), + X86_MATCH_FEATURE(X86_FEATURE_RAPL, &model_amd_hygon), + X86_MATCH_VFM(INTEL_SANDYBRIDGE, &model_snb), + X86_MATCH_VFM(INTEL_SANDYBRIDGE_X, &model_snbep), + X86_MATCH_VFM(INTEL_IVYBRIDGE, &model_snb), + X86_MATCH_VFM(INTEL_IVYBRIDGE_X, &model_snbep), + X86_MATCH_VFM(INTEL_HASWELL, &model_hsw), + X86_MATCH_VFM(INTEL_HASWELL_X, &model_hsx), + X86_MATCH_VFM(INTEL_HASWELL_L, &model_hsw), + X86_MATCH_VFM(INTEL_HASWELL_G, &model_hsw), + X86_MATCH_VFM(INTEL_BROADWELL, &model_hsw), + X86_MATCH_VFM(INTEL_BROADWELL_G, &model_hsw), + X86_MATCH_VFM(INTEL_BROADWELL_X, &model_hsx), + X86_MATCH_VFM(INTEL_BROADWELL_D, &model_hsx), + X86_MATCH_VFM(INTEL_XEON_PHI_KNL, &model_knl), + X86_MATCH_VFM(INTEL_XEON_PHI_KNM, &model_knl), + X86_MATCH_VFM(INTEL_SKYLAKE_L, &model_skl), + X86_MATCH_VFM(INTEL_SKYLAKE, &model_skl), + X86_MATCH_VFM(INTEL_SKYLAKE_X, &model_hsx), + X86_MATCH_VFM(INTEL_KABYLAKE_L, &model_skl), + X86_MATCH_VFM(INTEL_KABYLAKE, &model_skl), + X86_MATCH_VFM(INTEL_CANNONLAKE_L, &model_skl), + X86_MATCH_VFM(INTEL_ATOM_GOLDMONT, &model_hsw), + X86_MATCH_VFM(INTEL_ATOM_GOLDMONT_D, &model_hsw), + X86_MATCH_VFM(INTEL_ATOM_GOLDMONT_PLUS, &model_hsw), + X86_MATCH_VFM(INTEL_ICELAKE_L, &model_skl), + X86_MATCH_VFM(INTEL_ICELAKE, &model_skl), + X86_MATCH_VFM(INTEL_ICELAKE_D, &model_hsx), + X86_MATCH_VFM(INTEL_ICELAKE_X, &model_hsx), + X86_MATCH_VFM(INTEL_COMETLAKE_L, &model_skl), + X86_MATCH_VFM(INTEL_COMETLAKE, &model_skl), + X86_MATCH_VFM(INTEL_TIGERLAKE_L, &model_skl), + X86_MATCH_VFM(INTEL_TIGERLAKE, &model_skl), + X86_MATCH_VFM(INTEL_ALDERLAKE, &model_skl), + X86_MATCH_VFM(INTEL_ALDERLAKE_L, &model_skl), + X86_MATCH_VFM(INTEL_ATOM_GRACEMONT, &model_skl), + X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, &model_spr), + X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, &model_spr), + X86_MATCH_VFM(INTEL_RAPTORLAKE, &model_skl), + X86_MATCH_VFM(INTEL_RAPTORLAKE_P, &model_skl), + X86_MATCH_VFM(INTEL_RAPTORLAKE_S, &model_skl), + X86_MATCH_VFM(INTEL_METEORLAKE, &model_skl), + X86_MATCH_VFM(INTEL_METEORLAKE_L, &model_skl), + X86_MATCH_VFM(INTEL_ARROWLAKE_H, &model_skl), + X86_MATCH_VFM(INTEL_ARROWLAKE, &model_skl), + X86_MATCH_VFM(INTEL_LUNARLAKE_M, &model_skl), {}, }; MODULE_DEVICE_TABLE(x86cpu, rapl_model_match); diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c index 768d73de0d09..b4a851d27c7c 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -523,9 +523,9 @@ static int hv_mark_gpa_visibility(u16 count, const u64 pfn[], * transition is complete, hv_vtom_set_host_visibility() marks the pages * as "present" again. */ -static bool hv_vtom_clear_present(unsigned long kbuffer, int pagecount, bool enc) +static int hv_vtom_clear_present(unsigned long kbuffer, int pagecount, bool enc) { - return !set_memory_np(kbuffer, pagecount); + return set_memory_np(kbuffer, pagecount); } /* @@ -536,20 +536,19 @@ static bool hv_vtom_clear_present(unsigned long kbuffer, int pagecount, bool enc * with host. This function works as wrap of hv_mark_gpa_visibility() * with memory base and size. */ -static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bool enc) +static int hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bool enc) { enum hv_mem_host_visibility visibility = enc ? VMBUS_PAGE_NOT_VISIBLE : VMBUS_PAGE_VISIBLE_READ_WRITE; u64 *pfn_array; phys_addr_t paddr; + int i, pfn, err; void *vaddr; int ret = 0; - bool result = true; - int i, pfn; pfn_array = kmalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL); if (!pfn_array) { - result = false; + ret = -ENOMEM; goto err_set_memory_p; } @@ -568,10 +567,8 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo if (pfn == HV_MAX_MODIFY_GPA_REP_COUNT || i == pagecount - 1) { ret = hv_mark_gpa_visibility(pfn, pfn_array, visibility); - if (ret) { - result = false; + if (ret) goto err_free_pfn_array; - } pfn = 0; } } @@ -586,10 +583,11 @@ err_set_memory_p: * order to avoid leaving the memory range in a "broken" state. Setting * the PRESENT bits shouldn't fail, but return an error if it does. */ - if (set_memory_p(kbuffer, pagecount)) - result = false; + err = set_memory_p(kbuffer, pagecount); + if (err && !ret) + ret = err; - return result; + return ret; } static bool hv_vtom_tlb_flush_required(bool private) diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 5af926c050f0..21bc53f5ed0c 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -78,6 +78,13 @@ static inline bool acpi_skip_set_wakeup_address(void) #define acpi_skip_set_wakeup_address acpi_skip_set_wakeup_address +union acpi_subtable_headers; + +int __init acpi_parse_mp_wake(union acpi_subtable_headers *header, + const unsigned long end); + +void asm_acpi_mp_play_dead(u64 reset_vector, u64 pgd_pa); + /* * Check if the CPU can handle C2 and deeper */ diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index ba99ef75f56c..ca9ae606aab9 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -156,102 +156,50 @@ static inline int alternatives_text_reserved(void *start, void *end) #define ALT_CALL_INSTR "call BUG_func" -#define b_replacement(num) "664"#num -#define e_replacement(num) "665"#num +#define alt_slen "772b-771b" +#define alt_total_slen "773b-771b" +#define alt_rlen "775f-774f" -#define alt_end_marker "663" -#define alt_slen "662b-661b" -#define alt_total_slen alt_end_marker"b-661b" -#define alt_rlen(num) e_replacement(num)"f-"b_replacement(num)"f" - -#define OLDINSTR(oldinstr, num) \ - "# ALT: oldnstr\n" \ - "661:\n\t" oldinstr "\n662:\n" \ +#define OLDINSTR(oldinstr) \ + "# ALT: oldinstr\n" \ + "771:\n\t" oldinstr "\n772:\n" \ "# ALT: padding\n" \ - ".skip -(((" alt_rlen(num) ")-(" alt_slen ")) > 0) * " \ - "((" alt_rlen(num) ")-(" alt_slen ")),0x90\n" \ - alt_end_marker ":\n" + ".skip -(((" alt_rlen ")-(" alt_slen ")) > 0) * " \ + "((" alt_rlen ")-(" alt_slen ")),0x90\n" \ + "773:\n" -/* - * gas compatible max based on the idea from: - * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax - * - * The additional "-" is needed because gas uses a "true" value of -1. - */ -#define alt_max_short(a, b) "((" a ") ^ (((" a ") ^ (" b ")) & -(-((" a ") < (" b ")))))" - -/* - * Pad the second replacement alternative with additional NOPs if it is - * additionally longer than the first replacement alternative. - */ -#define OLDINSTR_2(oldinstr, num1, num2) \ - "# ALT: oldinstr2\n" \ - "661:\n\t" oldinstr "\n662:\n" \ - "# ALT: padding2\n" \ - ".skip -((" alt_max_short(alt_rlen(num1), alt_rlen(num2)) " - (" alt_slen ")) > 0) * " \ - "(" alt_max_short(alt_rlen(num1), alt_rlen(num2)) " - (" alt_slen ")), 0x90\n" \ - alt_end_marker ":\n" - -#define OLDINSTR_3(oldinsn, n1, n2, n3) \ - "# ALT: oldinstr3\n" \ - "661:\n\t" oldinsn "\n662:\n" \ - "# ALT: padding3\n" \ - ".skip -((" alt_max_short(alt_max_short(alt_rlen(n1), alt_rlen(n2)), alt_rlen(n3)) \ - " - (" alt_slen ")) > 0) * " \ - "(" alt_max_short(alt_max_short(alt_rlen(n1), alt_rlen(n2)), alt_rlen(n3)) \ - " - (" alt_slen ")), 0x90\n" \ - alt_end_marker ":\n" - -#define ALTINSTR_ENTRY(ft_flags, num) \ - " .long 661b - .\n" /* label */ \ - " .long " b_replacement(num)"f - .\n" /* new instruction */ \ +#define ALTINSTR_ENTRY(ft_flags) \ + ".pushsection .altinstructions,\"a\"\n" \ + " .long 771b - .\n" /* label */ \ + " .long 774f - .\n" /* new instruction */ \ " .4byte " __stringify(ft_flags) "\n" /* feature + flags */ \ " .byte " alt_total_slen "\n" /* source len */ \ - " .byte " alt_rlen(num) "\n" /* replacement len */ + " .byte " alt_rlen "\n" /* replacement len */ \ + ".popsection\n" -#define ALTINSTR_REPLACEMENT(newinstr, num) /* replacement */ \ - "# ALT: replacement " #num "\n" \ - b_replacement(num)":\n\t" newinstr "\n" e_replacement(num) ":\n" +#define ALTINSTR_REPLACEMENT(newinstr) /* replacement */ \ + ".pushsection .altinstr_replacement, \"ax\"\n" \ + "# ALT: replacement\n" \ + "774:\n\t" newinstr "\n775:\n" \ + ".popsection\n" /* alternative assembly primitive: */ #define ALTERNATIVE(oldinstr, newinstr, ft_flags) \ - OLDINSTR(oldinstr, 1) \ - ".pushsection .altinstructions,\"a\"\n" \ - ALTINSTR_ENTRY(ft_flags, 1) \ - ".popsection\n" \ - ".pushsection .altinstr_replacement, \"ax\"\n" \ - ALTINSTR_REPLACEMENT(newinstr, 1) \ - ".popsection\n" + OLDINSTR(oldinstr) \ + ALTINSTR_ENTRY(ft_flags) \ + ALTINSTR_REPLACEMENT(newinstr) #define ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2) \ - OLDINSTR_2(oldinstr, 1, 2) \ - ".pushsection .altinstructions,\"a\"\n" \ - ALTINSTR_ENTRY(ft_flags1, 1) \ - ALTINSTR_ENTRY(ft_flags2, 2) \ - ".popsection\n" \ - ".pushsection .altinstr_replacement, \"ax\"\n" \ - ALTINSTR_REPLACEMENT(newinstr1, 1) \ - ALTINSTR_REPLACEMENT(newinstr2, 2) \ - ".popsection\n" + ALTERNATIVE(ALTERNATIVE(oldinstr, newinstr1, ft_flags1), newinstr2, ft_flags2) /* If @feature is set, patch in @newinstr_yes, otherwise @newinstr_no. */ #define ALTERNATIVE_TERNARY(oldinstr, ft_flags, newinstr_yes, newinstr_no) \ - ALTERNATIVE_2(oldinstr, newinstr_no, X86_FEATURE_ALWAYS, \ - newinstr_yes, ft_flags) + ALTERNATIVE_2(oldinstr, newinstr_no, X86_FEATURE_ALWAYS, newinstr_yes, ft_flags) -#define ALTERNATIVE_3(oldinsn, newinsn1, ft_flags1, newinsn2, ft_flags2, \ - newinsn3, ft_flags3) \ - OLDINSTR_3(oldinsn, 1, 2, 3) \ - ".pushsection .altinstructions,\"a\"\n" \ - ALTINSTR_ENTRY(ft_flags1, 1) \ - ALTINSTR_ENTRY(ft_flags2, 2) \ - ALTINSTR_ENTRY(ft_flags3, 3) \ - ".popsection\n" \ - ".pushsection .altinstr_replacement, \"ax\"\n" \ - ALTINSTR_REPLACEMENT(newinsn1, 1) \ - ALTINSTR_REPLACEMENT(newinsn2, 2) \ - ALTINSTR_REPLACEMENT(newinsn3, 3) \ - ".popsection\n" +#define ALTERNATIVE_3(oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2, \ + newinstr3, ft_flags3) \ + ALTERNATIVE(ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2), \ + newinstr3, ft_flags3) /* * Alternative instructions for different CPU types or capabilities. @@ -266,14 +214,11 @@ static inline int alternatives_text_reserved(void *start, void *end) * without volatile and memory clobber. */ #define alternative(oldinstr, newinstr, ft_flags) \ - asm_inline volatile (ALTERNATIVE(oldinstr, newinstr, ft_flags) : : : "memory") + asm_inline volatile(ALTERNATIVE(oldinstr, newinstr, ft_flags) : : : "memory") #define alternative_2(oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2) \ asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2) ::: "memory") -#define alternative_ternary(oldinstr, ft_flags, newinstr_yes, newinstr_no) \ - asm_inline volatile(ALTERNATIVE_TERNARY(oldinstr, ft_flags, newinstr_yes, newinstr_no) ::: "memory") - /* * Alternative inline assembly with input. * @@ -283,18 +228,28 @@ static inline int alternatives_text_reserved(void *start, void *end) * Leaving an unused argument 0 to keep API compatibility. */ #define alternative_input(oldinstr, newinstr, ft_flags, input...) \ - asm_inline volatile (ALTERNATIVE(oldinstr, newinstr, ft_flags) \ + asm_inline volatile(ALTERNATIVE(oldinstr, newinstr, ft_flags) \ : : "i" (0), ## input) /* Like alternative_input, but with a single output argument */ #define alternative_io(oldinstr, newinstr, ft_flags, output, input...) \ - asm_inline volatile (ALTERNATIVE(oldinstr, newinstr, ft_flags) \ + asm_inline volatile(ALTERNATIVE(oldinstr, newinstr, ft_flags) \ : output : "i" (0), ## input) -/* Like alternative_io, but for replacing a direct call with another one. */ -#define alternative_call(oldfunc, newfunc, ft_flags, output, input...) \ - asm_inline volatile (ALTERNATIVE("call %c[old]", "call %c[new]", ft_flags) \ - : output : [old] "i" (oldfunc), [new] "i" (newfunc), ## input) +/* + * Like alternative_io, but for replacing a direct call with another one. + * + * Use the %c operand modifier which is the generic way to print a bare + * constant expression with all syntax-specific punctuation omitted. %P + * is the x86-specific variant which can handle constants too, for + * historical reasons, but it should be used primarily for PIC + * references: i.e., if used for a function, it would add the PLT + * suffix. + */ +#define alternative_call(oldfunc, newfunc, ft_flags, output, input...) \ + asm_inline volatile(ALTERNATIVE("call %c[old]", "call %c[new]", ft_flags) \ + : ALT_OUTPUT_SP(output) \ + : [old] "i" (oldfunc), [new] "i" (newfunc), ## input) /* * Like alternative_call, but there are two features and respective functions. @@ -302,12 +257,12 @@ static inline int alternatives_text_reserved(void *start, void *end) * Otherwise, if CPU has feature1, function1 is used. * Otherwise, old function is used. */ -#define alternative_call_2(oldfunc, newfunc1, ft_flags1, newfunc2, ft_flags2, \ - output, input...) \ - asm_inline volatile (ALTERNATIVE_2("call %c[old]", "call %c[new1]", ft_flags1, \ - "call %c[new2]", ft_flags2) \ - : output, ASM_CALL_CONSTRAINT \ - : [old] "i" (oldfunc), [new1] "i" (newfunc1), \ +#define alternative_call_2(oldfunc, newfunc1, ft_flags1, newfunc2, ft_flags2, \ + output, input...) \ + asm_inline volatile(ALTERNATIVE_2("call %c[old]", "call %c[new1]", ft_flags1, \ + "call %c[new2]", ft_flags2) \ + : ALT_OUTPUT_SP(output) \ + : [old] "i" (oldfunc), [new1] "i" (newfunc1), \ [new2] "i" (newfunc2), ## input) /* @@ -322,6 +277,8 @@ static inline int alternatives_text_reserved(void *start, void *end) */ #define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr +#define ALT_OUTPUT_SP(...) ASM_CALL_CONSTRAINT, ## __VA_ARGS__ + /* Macro for creating assembler functions avoiding any C magic. */ #define DEFINE_ASM_FUNC(func, instr, sec) \ asm (".pushsection " #sec ", \"ax\"\n" \ @@ -388,22 +345,23 @@ void nop_func(void); * @newinstr. ".skip" directive takes care of proper instruction padding * in case @newinstr is longer than @oldinstr. */ +#define __ALTERNATIVE(oldinst, newinst, flag) \ +740: \ + oldinst ; \ +741: \ + .skip -(((744f-743f)-(741b-740b)) > 0) * ((744f-743f)-(741b-740b)),0x90 ;\ +742: \ + .pushsection .altinstructions,"a" ; \ + altinstr_entry 740b,743f,flag,742b-740b,744f-743f ; \ + .popsection ; \ + .pushsection .altinstr_replacement,"ax" ; \ +743: \ + newinst ; \ +744: \ + .popsection ; + .macro ALTERNATIVE oldinstr, newinstr, ft_flags -140: - \oldinstr -141: - .skip -(((144f-143f)-(141b-140b)) > 0) * ((144f-143f)-(141b-140b)),0x90 -142: - - .pushsection .altinstructions,"a" - altinstr_entry 140b,143f,\ft_flags,142b-140b,144f-143f - .popsection - - .pushsection .altinstr_replacement,"ax" -143: - \newinstr -144: - .popsection + __ALTERNATIVE(\oldinstr, \newinstr, \ft_flags) .endm #define old_len 141b-140b @@ -411,66 +369,19 @@ void nop_func(void); #define new_len2 145f-144f #define new_len3 146f-145f -/* - * gas compatible max based on the idea from: - * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax - * - * The additional "-" is needed because gas uses a "true" value of -1. - */ -#define alt_max_2(a, b) ((a) ^ (((a) ^ (b)) & -(-((a) < (b))))) -#define alt_max_3(a, b, c) (alt_max_2(alt_max_2(a, b), c)) - - /* * Same as ALTERNATIVE macro above but for two alternatives. If CPU * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has * @feature2, it replaces @oldinstr with @feature2. */ .macro ALTERNATIVE_2 oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2 -140: - \oldinstr -141: - .skip -((alt_max_2(new_len1, new_len2) - (old_len)) > 0) * \ - (alt_max_2(new_len1, new_len2) - (old_len)),0x90 -142: - - .pushsection .altinstructions,"a" - altinstr_entry 140b,143f,\ft_flags1,142b-140b,144f-143f - altinstr_entry 140b,144f,\ft_flags2,142b-140b,145f-144f - .popsection - - .pushsection .altinstr_replacement,"ax" -143: - \newinstr1 -144: - \newinstr2 -145: - .popsection + __ALTERNATIVE(__ALTERNATIVE(\oldinstr, \newinstr1, \ft_flags1), + \newinstr2, \ft_flags2) .endm .macro ALTERNATIVE_3 oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2, newinstr3, ft_flags3 -140: - \oldinstr -141: - .skip -((alt_max_3(new_len1, new_len2, new_len3) - (old_len)) > 0) * \ - (alt_max_3(new_len1, new_len2, new_len3) - (old_len)),0x90 -142: - - .pushsection .altinstructions,"a" - altinstr_entry 140b,143f,\ft_flags1,142b-140b,144f-143f - altinstr_entry 140b,144f,\ft_flags2,142b-140b,145f-144f - altinstr_entry 140b,145f,\ft_flags3,142b-140b,146f-145f - .popsection - - .pushsection .altinstr_replacement,"ax" -143: - \newinstr1 -144: - \newinstr2 -145: - \newinstr3 -146: - .popsection + __ALTERNATIVE(ALTERNATIVE_2(\oldinstr, \newinstr1, \ft_flags1, \newinstr2, \ft_flags2), + \newinstr3, \ft_flags3) .endm /* If @feature is set, patch in @newinstr_yes, otherwise @newinstr_no. */ diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index 5c37944c8a5e..6f3b6aef47ba 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -21,8 +21,8 @@ extern int amd_numa_init(void); extern int amd_get_subcaches(int); extern int amd_set_subcaches(int, unsigned long); -extern int amd_smn_read(u16 node, u32 address, u32 *value); -extern int amd_smn_write(u16 node, u32 address, u32 value); +int __must_check amd_smn_read(u16 node, u32 address, u32 *value); +int __must_check amd_smn_write(u16 node, u32 address, u32 value); struct amd_l3_cache { unsigned indices; diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h index b6325ee30871..3831f612e89c 100644 --- a/arch/x86/include/asm/cpu_device_id.h +++ b/arch/x86/include/asm/cpu_device_id.h @@ -280,10 +280,10 @@ struct x86_cpu_desc { u32 x86_microcode_rev; }; -#define INTEL_CPU_DESC(model, stepping, revision) { \ - .x86_family = 6, \ - .x86_vendor = X86_VENDOR_INTEL, \ - .x86_model = (model), \ +#define INTEL_CPU_DESC(vfm, stepping, revision) { \ + .x86_family = VFM_FAMILY(vfm), \ + .x86_vendor = VFM_VENDOR(vfm), \ + .x86_model = VFM_MODEL(vfm), \ .x86_stepping = (stepping), \ .x86_microcode_rev = (revision), \ } diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 3c7434329661..b51e88d01b21 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -18,170 +18,170 @@ /* * Note: If the comment begins with a quoted string, that string is used - * in /proc/cpuinfo instead of the macro name. If the string is "", - * this feature bit is not displayed in /proc/cpuinfo at all. + * in /proc/cpuinfo instead of the macro name. Otherwise, this feature + * bit is not displayed in /proc/cpuinfo at all. * * When adding new features here that depend on other features, * please update the table in kernel/cpu/cpuid-deps.c as well. */ /* Intel-defined CPU features, CPUID level 0x00000001 (EDX), word 0 */ -#define X86_FEATURE_FPU ( 0*32+ 0) /* Onboard FPU */ -#define X86_FEATURE_VME ( 0*32+ 1) /* Virtual Mode Extensions */ -#define X86_FEATURE_DE ( 0*32+ 2) /* Debugging Extensions */ -#define X86_FEATURE_PSE ( 0*32+ 3) /* Page Size Extensions */ -#define X86_FEATURE_TSC ( 0*32+ 4) /* Time Stamp Counter */ -#define X86_FEATURE_MSR ( 0*32+ 5) /* Model-Specific Registers */ -#define X86_FEATURE_PAE ( 0*32+ 6) /* Physical Address Extensions */ -#define X86_FEATURE_MCE ( 0*32+ 7) /* Machine Check Exception */ -#define X86_FEATURE_CX8 ( 0*32+ 8) /* CMPXCHG8 instruction */ -#define X86_FEATURE_APIC ( 0*32+ 9) /* Onboard APIC */ -#define X86_FEATURE_SEP ( 0*32+11) /* SYSENTER/SYSEXIT */ -#define X86_FEATURE_MTRR ( 0*32+12) /* Memory Type Range Registers */ -#define X86_FEATURE_PGE ( 0*32+13) /* Page Global Enable */ -#define X86_FEATURE_MCA ( 0*32+14) /* Machine Check Architecture */ -#define X86_FEATURE_CMOV ( 0*32+15) /* CMOV instructions (plus FCMOVcc, FCOMI with FPU) */ -#define X86_FEATURE_PAT ( 0*32+16) /* Page Attribute Table */ -#define X86_FEATURE_PSE36 ( 0*32+17) /* 36-bit PSEs */ -#define X86_FEATURE_PN ( 0*32+18) /* Processor serial number */ -#define X86_FEATURE_CLFLUSH ( 0*32+19) /* CLFLUSH instruction */ +#define X86_FEATURE_FPU ( 0*32+ 0) /* "fpu" Onboard FPU */ +#define X86_FEATURE_VME ( 0*32+ 1) /* "vme" Virtual Mode Extensions */ +#define X86_FEATURE_DE ( 0*32+ 2) /* "de" Debugging Extensions */ +#define X86_FEATURE_PSE ( 0*32+ 3) /* "pse" Page Size Extensions */ +#define X86_FEATURE_TSC ( 0*32+ 4) /* "tsc" Time Stamp Counter */ +#define X86_FEATURE_MSR ( 0*32+ 5) /* "msr" Model-Specific Registers */ +#define X86_FEATURE_PAE ( 0*32+ 6) /* "pae" Physical Address Extensions */ +#define X86_FEATURE_MCE ( 0*32+ 7) /* "mce" Machine Check Exception */ +#define X86_FEATURE_CX8 ( 0*32+ 8) /* "cx8" CMPXCHG8 instruction */ +#define X86_FEATURE_APIC ( 0*32+ 9) /* "apic" Onboard APIC */ +#define X86_FEATURE_SEP ( 0*32+11) /* "sep" SYSENTER/SYSEXIT */ +#define X86_FEATURE_MTRR ( 0*32+12) /* "mtrr" Memory Type Range Registers */ +#define X86_FEATURE_PGE ( 0*32+13) /* "pge" Page Global Enable */ +#define X86_FEATURE_MCA ( 0*32+14) /* "mca" Machine Check Architecture */ +#define X86_FEATURE_CMOV ( 0*32+15) /* "cmov" CMOV instructions (plus FCMOVcc, FCOMI with FPU) */ +#define X86_FEATURE_PAT ( 0*32+16) /* "pat" Page Attribute Table */ +#define X86_FEATURE_PSE36 ( 0*32+17) /* "pse36" 36-bit PSEs */ +#define X86_FEATURE_PN ( 0*32+18) /* "pn" Processor serial number */ +#define X86_FEATURE_CLFLUSH ( 0*32+19) /* "clflush" CLFLUSH instruction */ #define X86_FEATURE_DS ( 0*32+21) /* "dts" Debug Store */ -#define X86_FEATURE_ACPI ( 0*32+22) /* ACPI via MSR */ -#define X86_FEATURE_MMX ( 0*32+23) /* Multimedia Extensions */ -#define X86_FEATURE_FXSR ( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */ +#define X86_FEATURE_ACPI ( 0*32+22) /* "acpi" ACPI via MSR */ +#define X86_FEATURE_MMX ( 0*32+23) /* "mmx" Multimedia Extensions */ +#define X86_FEATURE_FXSR ( 0*32+24) /* "fxsr" FXSAVE/FXRSTOR, CR4.OSFXSR */ #define X86_FEATURE_XMM ( 0*32+25) /* "sse" */ #define X86_FEATURE_XMM2 ( 0*32+26) /* "sse2" */ #define X86_FEATURE_SELFSNOOP ( 0*32+27) /* "ss" CPU self snoop */ -#define X86_FEATURE_HT ( 0*32+28) /* Hyper-Threading */ +#define X86_FEATURE_HT ( 0*32+28) /* "ht" Hyper-Threading */ #define X86_FEATURE_ACC ( 0*32+29) /* "tm" Automatic clock control */ -#define X86_FEATURE_IA64 ( 0*32+30) /* IA-64 processor */ -#define X86_FEATURE_PBE ( 0*32+31) /* Pending Break Enable */ +#define X86_FEATURE_IA64 ( 0*32+30) /* "ia64" IA-64 processor */ +#define X86_FEATURE_PBE ( 0*32+31) /* "pbe" Pending Break Enable */ /* AMD-defined CPU features, CPUID level 0x80000001, word 1 */ /* Don't duplicate feature flags which are redundant with Intel! */ -#define X86_FEATURE_SYSCALL ( 1*32+11) /* SYSCALL/SYSRET */ -#define X86_FEATURE_MP ( 1*32+19) /* MP Capable */ -#define X86_FEATURE_NX ( 1*32+20) /* Execute Disable */ -#define X86_FEATURE_MMXEXT ( 1*32+22) /* AMD MMX extensions */ -#define X86_FEATURE_FXSR_OPT ( 1*32+25) /* FXSAVE/FXRSTOR optimizations */ +#define X86_FEATURE_SYSCALL ( 1*32+11) /* "syscall" SYSCALL/SYSRET */ +#define X86_FEATURE_MP ( 1*32+19) /* "mp" MP Capable */ +#define X86_FEATURE_NX ( 1*32+20) /* "nx" Execute Disable */ +#define X86_FEATURE_MMXEXT ( 1*32+22) /* "mmxext" AMD MMX extensions */ +#define X86_FEATURE_FXSR_OPT ( 1*32+25) /* "fxsr_opt" FXSAVE/FXRSTOR optimizations */ #define X86_FEATURE_GBPAGES ( 1*32+26) /* "pdpe1gb" GB pages */ -#define X86_FEATURE_RDTSCP ( 1*32+27) /* RDTSCP */ -#define X86_FEATURE_LM ( 1*32+29) /* Long Mode (x86-64, 64-bit support) */ -#define X86_FEATURE_3DNOWEXT ( 1*32+30) /* AMD 3DNow extensions */ -#define X86_FEATURE_3DNOW ( 1*32+31) /* 3DNow */ +#define X86_FEATURE_RDTSCP ( 1*32+27) /* "rdtscp" RDTSCP */ +#define X86_FEATURE_LM ( 1*32+29) /* "lm" Long Mode (x86-64, 64-bit support) */ +#define X86_FEATURE_3DNOWEXT ( 1*32+30) /* "3dnowext" AMD 3DNow extensions */ +#define X86_FEATURE_3DNOW ( 1*32+31) /* "3dnow" 3DNow */ /* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */ -#define X86_FEATURE_RECOVERY ( 2*32+ 0) /* CPU in recovery mode */ -#define X86_FEATURE_LONGRUN ( 2*32+ 1) /* Longrun power control */ -#define X86_FEATURE_LRTI ( 2*32+ 3) /* LongRun table interface */ +#define X86_FEATURE_RECOVERY ( 2*32+ 0) /* "recovery" CPU in recovery mode */ +#define X86_FEATURE_LONGRUN ( 2*32+ 1) /* "longrun" Longrun power control */ +#define X86_FEATURE_LRTI ( 2*32+ 3) /* "lrti" LongRun table interface */ /* Other features, Linux-defined mapping, word 3 */ /* This range is used for feature bits which conflict or are synthesized */ -#define X86_FEATURE_CXMMX ( 3*32+ 0) /* Cyrix MMX extensions */ -#define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* AMD K6 nonstandard MTRRs */ -#define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */ -#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* Centaur MCRs (= MTRRs) */ -#define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */ -#define X86_FEATURE_ZEN5 ( 3*32+ 5) /* "" CPU based on Zen5 microarchitecture */ -#define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */ -#define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */ -#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */ -#define X86_FEATURE_UP ( 3*32+ 9) /* SMP kernel running on UP */ -#define X86_FEATURE_ART ( 3*32+10) /* Always running timer (ART) */ -#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */ -#define X86_FEATURE_PEBS ( 3*32+12) /* Precise-Event Based Sampling */ -#define X86_FEATURE_BTS ( 3*32+13) /* Branch Trace Store */ -#define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in IA32 userspace */ -#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ -#define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ -#define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */ -#define X86_FEATURE_CLEAR_CPU_BUF ( 3*32+18) /* "" Clear CPU buffers using VERW */ -#define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ -#define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ -#define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ -#define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* CPU topology enum extensions */ -#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */ -#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* TSC does not stop in C states */ -#define X86_FEATURE_CPUID ( 3*32+25) /* CPU has CPUID instruction itself */ -#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* Extended APICID (8 bits) */ -#define X86_FEATURE_AMD_DCM ( 3*32+27) /* AMD multi-node processor */ -#define X86_FEATURE_APERFMPERF ( 3*32+28) /* P-State hardware coordination feedback capability (APERF/MPERF MSRs) */ -#define X86_FEATURE_RAPL ( 3*32+29) /* AMD/Hygon RAPL interface */ -#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */ -#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* TSC has known frequency */ +#define X86_FEATURE_CXMMX ( 3*32+ 0) /* "cxmmx" Cyrix MMX extensions */ +#define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* "k6_mtrr" AMD K6 nonstandard MTRRs */ +#define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* "cyrix_arr" Cyrix ARRs (= MTRRs) */ +#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* "centaur_mcr" Centaur MCRs (= MTRRs) */ +#define X86_FEATURE_K8 ( 3*32+ 4) /* Opteron, Athlon64 */ +#define X86_FEATURE_ZEN5 ( 3*32+ 5) /* CPU based on Zen5 microarchitecture */ +#define X86_FEATURE_P3 ( 3*32+ 6) /* P3 */ +#define X86_FEATURE_P4 ( 3*32+ 7) /* P4 */ +#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* "constant_tsc" TSC ticks at a constant rate */ +#define X86_FEATURE_UP ( 3*32+ 9) /* "up" SMP kernel running on UP */ +#define X86_FEATURE_ART ( 3*32+10) /* "art" Always running timer (ART) */ +#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* "arch_perfmon" Intel Architectural PerfMon */ +#define X86_FEATURE_PEBS ( 3*32+12) /* "pebs" Precise-Event Based Sampling */ +#define X86_FEATURE_BTS ( 3*32+13) /* "bts" Branch Trace Store */ +#define X86_FEATURE_SYSCALL32 ( 3*32+14) /* syscall in IA32 userspace */ +#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* sysenter in IA32 userspace */ +#define X86_FEATURE_REP_GOOD ( 3*32+16) /* "rep_good" REP microcode works well */ +#define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* "amd_lbr_v2" AMD Last Branch Record Extension Version 2 */ +#define X86_FEATURE_CLEAR_CPU_BUF ( 3*32+18) /* Clear CPU buffers using VERW */ +#define X86_FEATURE_ACC_POWER ( 3*32+19) /* "acc_power" AMD Accumulated Power Mechanism */ +#define X86_FEATURE_NOPL ( 3*32+20) /* "nopl" The NOPL (0F 1F) instructions */ +#define X86_FEATURE_ALWAYS ( 3*32+21) /* Always-present feature */ +#define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* "xtopology" CPU topology enum extensions */ +#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* "tsc_reliable" TSC is known to be reliable */ +#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* "nonstop_tsc" TSC does not stop in C states */ +#define X86_FEATURE_CPUID ( 3*32+25) /* "cpuid" CPU has CPUID instruction itself */ +#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* "extd_apicid" Extended APICID (8 bits) */ +#define X86_FEATURE_AMD_DCM ( 3*32+27) /* "amd_dcm" AMD multi-node processor */ +#define X86_FEATURE_APERFMPERF ( 3*32+28) /* "aperfmperf" P-State hardware coordination feedback capability (APERF/MPERF MSRs) */ +#define X86_FEATURE_RAPL ( 3*32+29) /* "rapl" AMD/Hygon RAPL interface */ +#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* "nonstop_tsc_s3" TSC doesn't stop in S3 state */ +#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* "tsc_known_freq" TSC has known frequency */ /* Intel-defined CPU features, CPUID level 0x00000001 (ECX), word 4 */ #define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */ -#define X86_FEATURE_PCLMULQDQ ( 4*32+ 1) /* PCLMULQDQ instruction */ -#define X86_FEATURE_DTES64 ( 4*32+ 2) /* 64-bit Debug Store */ +#define X86_FEATURE_PCLMULQDQ ( 4*32+ 1) /* "pclmulqdq" PCLMULQDQ instruction */ +#define X86_FEATURE_DTES64 ( 4*32+ 2) /* "dtes64" 64-bit Debug Store */ #define X86_FEATURE_MWAIT ( 4*32+ 3) /* "monitor" MONITOR/MWAIT support */ #define X86_FEATURE_DSCPL ( 4*32+ 4) /* "ds_cpl" CPL-qualified (filtered) Debug Store */ -#define X86_FEATURE_VMX ( 4*32+ 5) /* Hardware virtualization */ -#define X86_FEATURE_SMX ( 4*32+ 6) /* Safer Mode eXtensions */ -#define X86_FEATURE_EST ( 4*32+ 7) /* Enhanced SpeedStep */ -#define X86_FEATURE_TM2 ( 4*32+ 8) /* Thermal Monitor 2 */ -#define X86_FEATURE_SSSE3 ( 4*32+ 9) /* Supplemental SSE-3 */ -#define X86_FEATURE_CID ( 4*32+10) /* Context ID */ -#define X86_FEATURE_SDBG ( 4*32+11) /* Silicon Debug */ -#define X86_FEATURE_FMA ( 4*32+12) /* Fused multiply-add */ -#define X86_FEATURE_CX16 ( 4*32+13) /* CMPXCHG16B instruction */ -#define X86_FEATURE_XTPR ( 4*32+14) /* Send Task Priority Messages */ -#define X86_FEATURE_PDCM ( 4*32+15) /* Perf/Debug Capabilities MSR */ -#define X86_FEATURE_PCID ( 4*32+17) /* Process Context Identifiers */ -#define X86_FEATURE_DCA ( 4*32+18) /* Direct Cache Access */ +#define X86_FEATURE_VMX ( 4*32+ 5) /* "vmx" Hardware virtualization */ +#define X86_FEATURE_SMX ( 4*32+ 6) /* "smx" Safer Mode eXtensions */ +#define X86_FEATURE_EST ( 4*32+ 7) /* "est" Enhanced SpeedStep */ +#define X86_FEATURE_TM2 ( 4*32+ 8) /* "tm2" Thermal Monitor 2 */ +#define X86_FEATURE_SSSE3 ( 4*32+ 9) /* "ssse3" Supplemental SSE-3 */ +#define X86_FEATURE_CID ( 4*32+10) /* "cid" Context ID */ +#define X86_FEATURE_SDBG ( 4*32+11) /* "sdbg" Silicon Debug */ +#define X86_FEATURE_FMA ( 4*32+12) /* "fma" Fused multiply-add */ +#define X86_FEATURE_CX16 ( 4*32+13) /* "cx16" CMPXCHG16B instruction */ +#define X86_FEATURE_XTPR ( 4*32+14) /* "xtpr" Send Task Priority Messages */ +#define X86_FEATURE_PDCM ( 4*32+15) /* "pdcm" Perf/Debug Capabilities MSR */ +#define X86_FEATURE_PCID ( 4*32+17) /* "pcid" Process Context Identifiers */ +#define X86_FEATURE_DCA ( 4*32+18) /* "dca" Direct Cache Access */ #define X86_FEATURE_XMM4_1 ( 4*32+19) /* "sse4_1" SSE-4.1 */ #define X86_FEATURE_XMM4_2 ( 4*32+20) /* "sse4_2" SSE-4.2 */ -#define X86_FEATURE_X2APIC ( 4*32+21) /* X2APIC */ -#define X86_FEATURE_MOVBE ( 4*32+22) /* MOVBE instruction */ -#define X86_FEATURE_POPCNT ( 4*32+23) /* POPCNT instruction */ -#define X86_FEATURE_TSC_DEADLINE_TIMER ( 4*32+24) /* TSC deadline timer */ -#define X86_FEATURE_AES ( 4*32+25) /* AES instructions */ -#define X86_FEATURE_XSAVE ( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV instructions */ -#define X86_FEATURE_OSXSAVE ( 4*32+27) /* "" XSAVE instruction enabled in the OS */ -#define X86_FEATURE_AVX ( 4*32+28) /* Advanced Vector Extensions */ -#define X86_FEATURE_F16C ( 4*32+29) /* 16-bit FP conversions */ -#define X86_FEATURE_RDRAND ( 4*32+30) /* RDRAND instruction */ -#define X86_FEATURE_HYPERVISOR ( 4*32+31) /* Running on a hypervisor */ +#define X86_FEATURE_X2APIC ( 4*32+21) /* "x2apic" X2APIC */ +#define X86_FEATURE_MOVBE ( 4*32+22) /* "movbe" MOVBE instruction */ +#define X86_FEATURE_POPCNT ( 4*32+23) /* "popcnt" POPCNT instruction */ +#define X86_FEATURE_TSC_DEADLINE_TIMER ( 4*32+24) /* "tsc_deadline_timer" TSC deadline timer */ +#define X86_FEATURE_AES ( 4*32+25) /* "aes" AES instructions */ +#define X86_FEATURE_XSAVE ( 4*32+26) /* "xsave" XSAVE/XRSTOR/XSETBV/XGETBV instructions */ +#define X86_FEATURE_OSXSAVE ( 4*32+27) /* XSAVE instruction enabled in the OS */ +#define X86_FEATURE_AVX ( 4*32+28) /* "avx" Advanced Vector Extensions */ +#define X86_FEATURE_F16C ( 4*32+29) /* "f16c" 16-bit FP conversions */ +#define X86_FEATURE_RDRAND ( 4*32+30) /* "rdrand" RDRAND instruction */ +#define X86_FEATURE_HYPERVISOR ( 4*32+31) /* "hypervisor" Running on a hypervisor */ /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */ #define X86_FEATURE_XSTORE ( 5*32+ 2) /* "rng" RNG present (xstore) */ #define X86_FEATURE_XSTORE_EN ( 5*32+ 3) /* "rng_en" RNG enabled */ #define X86_FEATURE_XCRYPT ( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */ #define X86_FEATURE_XCRYPT_EN ( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */ -#define X86_FEATURE_ACE2 ( 5*32+ 8) /* Advanced Cryptography Engine v2 */ -#define X86_FEATURE_ACE2_EN ( 5*32+ 9) /* ACE v2 enabled */ -#define X86_FEATURE_PHE ( 5*32+10) /* PadLock Hash Engine */ -#define X86_FEATURE_PHE_EN ( 5*32+11) /* PHE enabled */ -#define X86_FEATURE_PMM ( 5*32+12) /* PadLock Montgomery Multiplier */ -#define X86_FEATURE_PMM_EN ( 5*32+13) /* PMM enabled */ +#define X86_FEATURE_ACE2 ( 5*32+ 8) /* "ace2" Advanced Cryptography Engine v2 */ +#define X86_FEATURE_ACE2_EN ( 5*32+ 9) /* "ace2_en" ACE v2 enabled */ +#define X86_FEATURE_PHE ( 5*32+10) /* "phe" PadLock Hash Engine */ +#define X86_FEATURE_PHE_EN ( 5*32+11) /* "phe_en" PHE enabled */ +#define X86_FEATURE_PMM ( 5*32+12) /* "pmm" PadLock Montgomery Multiplier */ +#define X86_FEATURE_PMM_EN ( 5*32+13) /* "pmm_en" PMM enabled */ /* More extended AMD flags: CPUID level 0x80000001, ECX, word 6 */ -#define X86_FEATURE_LAHF_LM ( 6*32+ 0) /* LAHF/SAHF in long mode */ -#define X86_FEATURE_CMP_LEGACY ( 6*32+ 1) /* If yes HyperThreading not valid */ -#define X86_FEATURE_SVM ( 6*32+ 2) /* Secure Virtual Machine */ -#define X86_FEATURE_EXTAPIC ( 6*32+ 3) /* Extended APIC space */ -#define X86_FEATURE_CR8_LEGACY ( 6*32+ 4) /* CR8 in 32-bit mode */ -#define X86_FEATURE_ABM ( 6*32+ 5) /* Advanced bit manipulation */ -#define X86_FEATURE_SSE4A ( 6*32+ 6) /* SSE-4A */ -#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */ -#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */ -#define X86_FEATURE_OSVW ( 6*32+ 9) /* OS Visible Workaround */ -#define X86_FEATURE_IBS ( 6*32+10) /* Instruction Based Sampling */ -#define X86_FEATURE_XOP ( 6*32+11) /* extended AVX instructions */ -#define X86_FEATURE_SKINIT ( 6*32+12) /* SKINIT/STGI instructions */ -#define X86_FEATURE_WDT ( 6*32+13) /* Watchdog timer */ -#define X86_FEATURE_LWP ( 6*32+15) /* Light Weight Profiling */ -#define X86_FEATURE_FMA4 ( 6*32+16) /* 4 operands MAC instructions */ -#define X86_FEATURE_TCE ( 6*32+17) /* Translation Cache Extension */ -#define X86_FEATURE_NODEID_MSR ( 6*32+19) /* NodeId MSR */ -#define X86_FEATURE_TBM ( 6*32+21) /* Trailing Bit Manipulations */ -#define X86_FEATURE_TOPOEXT ( 6*32+22) /* Topology extensions CPUID leafs */ -#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* Core performance counter extensions */ -#define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */ -#define X86_FEATURE_BPEXT ( 6*32+26) /* Data breakpoint extension */ -#define X86_FEATURE_PTSC ( 6*32+27) /* Performance time-stamp counter */ -#define X86_FEATURE_PERFCTR_LLC ( 6*32+28) /* Last Level Cache performance counter extensions */ -#define X86_FEATURE_MWAITX ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX instructions) */ +#define X86_FEATURE_LAHF_LM ( 6*32+ 0) /* "lahf_lm" LAHF/SAHF in long mode */ +#define X86_FEATURE_CMP_LEGACY ( 6*32+ 1) /* "cmp_legacy" If yes HyperThreading not valid */ +#define X86_FEATURE_SVM ( 6*32+ 2) /* "svm" Secure Virtual Machine */ +#define X86_FEATURE_EXTAPIC ( 6*32+ 3) /* "extapic" Extended APIC space */ +#define X86_FEATURE_CR8_LEGACY ( 6*32+ 4) /* "cr8_legacy" CR8 in 32-bit mode */ +#define X86_FEATURE_ABM ( 6*32+ 5) /* "abm" Advanced bit manipulation */ +#define X86_FEATURE_SSE4A ( 6*32+ 6) /* "sse4a" SSE-4A */ +#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* "misalignsse" Misaligned SSE mode */ +#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* "3dnowprefetch" 3DNow prefetch instructions */ +#define X86_FEATURE_OSVW ( 6*32+ 9) /* "osvw" OS Visible Workaround */ +#define X86_FEATURE_IBS ( 6*32+10) /* "ibs" Instruction Based Sampling */ +#define X86_FEATURE_XOP ( 6*32+11) /* "xop" Extended AVX instructions */ +#define X86_FEATURE_SKINIT ( 6*32+12) /* "skinit" SKINIT/STGI instructions */ +#define X86_FEATURE_WDT ( 6*32+13) /* "wdt" Watchdog timer */ +#define X86_FEATURE_LWP ( 6*32+15) /* "lwp" Light Weight Profiling */ +#define X86_FEATURE_FMA4 ( 6*32+16) /* "fma4" 4 operands MAC instructions */ +#define X86_FEATURE_TCE ( 6*32+17) /* "tce" Translation Cache Extension */ +#define X86_FEATURE_NODEID_MSR ( 6*32+19) /* "nodeid_msr" NodeId MSR */ +#define X86_FEATURE_TBM ( 6*32+21) /* "tbm" Trailing Bit Manipulations */ +#define X86_FEATURE_TOPOEXT ( 6*32+22) /* "topoext" Topology extensions CPUID leafs */ +#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* "perfctr_core" Core performance counter extensions */ +#define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* "perfctr_nb" NB performance counter extensions */ +#define X86_FEATURE_BPEXT ( 6*32+26) /* "bpext" Data breakpoint extension */ +#define X86_FEATURE_PTSC ( 6*32+27) /* "ptsc" Performance time-stamp counter */ +#define X86_FEATURE_PERFCTR_LLC ( 6*32+28) /* "perfctr_llc" Last Level Cache performance counter extensions */ +#define X86_FEATURE_MWAITX ( 6*32+29) /* "mwaitx" MWAIT extension (MONITORX/MWAITX instructions) */ /* * Auxiliary flags: Linux defined - For features scattered in various @@ -189,93 +189,93 @@ * * Reuse free bits when adding new feature flags! */ -#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* Ring 3 MONITOR/MWAIT instructions */ -#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* Intel CPUID faulting */ -#define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ -#define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ -#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */ -#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */ -#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */ -#define X86_FEATURE_TDX_HOST_PLATFORM ( 7*32+ 7) /* Platform supports being a TDX host */ -#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ -#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ -#define X86_FEATURE_XCOMPACTED ( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */ -#define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ -#define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* "" Set/clear IBRS on kernel entry/exit */ -#define X86_FEATURE_RSB_VMEXIT ( 7*32+13) /* "" Fill RSB on VM-Exit */ -#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ -#define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */ -#define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */ -#define X86_FEATURE_SSBD ( 7*32+17) /* Speculative Store Bypass Disable */ -#define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ -#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ -#define X86_FEATURE_PERFMON_V2 ( 7*32+20) /* AMD Performance Monitoring Version 2 */ -#define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ -#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ -#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* "" Disable Speculative Store Bypass. */ -#define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* "" AMD SSBD implementation via LS_CFG MSR */ -#define X86_FEATURE_IBRS ( 7*32+25) /* Indirect Branch Restricted Speculation */ -#define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */ -#define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */ -#define X86_FEATURE_ZEN ( 7*32+28) /* "" Generic flag for all Zen and newer */ -#define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* "" L1TF workaround PTE inversion */ -#define X86_FEATURE_IBRS_ENHANCED ( 7*32+30) /* Enhanced IBRS */ -#define X86_FEATURE_MSR_IA32_FEAT_CTL ( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */ +#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* "ring3mwait" Ring 3 MONITOR/MWAIT instructions */ +#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* "cpuid_fault" Intel CPUID faulting */ +#define X86_FEATURE_CPB ( 7*32+ 2) /* "cpb" AMD Core Performance Boost */ +#define X86_FEATURE_EPB ( 7*32+ 3) /* "epb" IA32_ENERGY_PERF_BIAS support */ +#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* "cat_l3" Cache Allocation Technology L3 */ +#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* "cat_l2" Cache Allocation Technology L2 */ +#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* "cdp_l3" Code and Data Prioritization L3 */ +#define X86_FEATURE_TDX_HOST_PLATFORM ( 7*32+ 7) /* "tdx_host_platform" Platform supports being a TDX host */ +#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* "hw_pstate" AMD HW-PState */ +#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* "proc_feedback" AMD ProcFeedbackInterface */ +#define X86_FEATURE_XCOMPACTED ( 7*32+10) /* Use compacted XSTATE (XSAVES or XSAVEC) */ +#define X86_FEATURE_PTI ( 7*32+11) /* "pti" Kernel Page Table Isolation enabled */ +#define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* Set/clear IBRS on kernel entry/exit */ +#define X86_FEATURE_RSB_VMEXIT ( 7*32+13) /* Fill RSB on VM-Exit */ +#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* "intel_ppin" Intel Processor Inventory Number */ +#define X86_FEATURE_CDP_L2 ( 7*32+15) /* "cdp_l2" Code and Data Prioritization L2 */ +#define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* MSR SPEC_CTRL is implemented */ +#define X86_FEATURE_SSBD ( 7*32+17) /* "ssbd" Speculative Store Bypass Disable */ +#define X86_FEATURE_MBA ( 7*32+18) /* "mba" Memory Bandwidth Allocation */ +#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* Fill RSB on context switches */ +#define X86_FEATURE_PERFMON_V2 ( 7*32+20) /* "perfmon_v2" AMD Performance Monitoring Version 2 */ +#define X86_FEATURE_USE_IBPB ( 7*32+21) /* Indirect Branch Prediction Barrier enabled */ +#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* Use IBRS during runtime firmware calls */ +#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* Disable Speculative Store Bypass. */ +#define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* AMD SSBD implementation via LS_CFG MSR */ +#define X86_FEATURE_IBRS ( 7*32+25) /* "ibrs" Indirect Branch Restricted Speculation */ +#define X86_FEATURE_IBPB ( 7*32+26) /* "ibpb" Indirect Branch Prediction Barrier */ +#define X86_FEATURE_STIBP ( 7*32+27) /* "stibp" Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_ZEN ( 7*32+28) /* Generic flag for all Zen and newer */ +#define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* L1TF workaround PTE inversion */ +#define X86_FEATURE_IBRS_ENHANCED ( 7*32+30) /* "ibrs_enhanced" Enhanced IBRS */ +#define X86_FEATURE_MSR_IA32_FEAT_CTL ( 7*32+31) /* MSR IA32_FEAT_CTL configured */ /* Virtualization flags: Linux defined, word 8 */ -#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ -#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* Intel FlexPriority */ -#define X86_FEATURE_EPT ( 8*32+ 2) /* Intel Extended Page Table */ -#define X86_FEATURE_VPID ( 8*32+ 3) /* Intel Virtual Processor ID */ +#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* "tpr_shadow" Intel TPR Shadow */ +#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* "flexpriority" Intel FlexPriority */ +#define X86_FEATURE_EPT ( 8*32+ 2) /* "ept" Intel Extended Page Table */ +#define X86_FEATURE_VPID ( 8*32+ 3) /* "vpid" Intel Virtual Processor ID */ -#define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer VMMCALL to VMCALL */ -#define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ -#define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */ -#define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */ -#define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */ -#define X86_FEATURE_PVUNLOCK ( 8*32+20) /* "" PV unlock function */ -#define X86_FEATURE_VCPUPREEMPT ( 8*32+21) /* "" PV vcpu_is_preempted function */ -#define X86_FEATURE_TDX_GUEST ( 8*32+22) /* Intel Trust Domain Extensions Guest */ +#define X86_FEATURE_VMMCALL ( 8*32+15) /* "vmmcall" Prefer VMMCALL to VMCALL */ +#define X86_FEATURE_XENPV ( 8*32+16) /* Xen paravirtual guest */ +#define X86_FEATURE_EPT_AD ( 8*32+17) /* "ept_ad" Intel Extended Page Table access-dirty bit */ +#define X86_FEATURE_VMCALL ( 8*32+18) /* Hypervisor supports the VMCALL instruction */ +#define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* VMware prefers VMMCALL hypercall instruction */ +#define X86_FEATURE_PVUNLOCK ( 8*32+20) /* PV unlock function */ +#define X86_FEATURE_VCPUPREEMPT ( 8*32+21) /* PV vcpu_is_preempted function */ +#define X86_FEATURE_TDX_GUEST ( 8*32+22) /* "tdx_guest" Intel Trust Domain Extensions Guest */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ -#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ -#define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* TSC adjustment MSR 0x3B */ -#define X86_FEATURE_SGX ( 9*32+ 2) /* Software Guard Extensions */ -#define X86_FEATURE_BMI1 ( 9*32+ 3) /* 1st group bit manipulation extensions */ -#define X86_FEATURE_HLE ( 9*32+ 4) /* Hardware Lock Elision */ -#define X86_FEATURE_AVX2 ( 9*32+ 5) /* AVX2 instructions */ -#define X86_FEATURE_FDP_EXCPTN_ONLY ( 9*32+ 6) /* "" FPU data pointer updated only on x87 exceptions */ -#define X86_FEATURE_SMEP ( 9*32+ 7) /* Supervisor Mode Execution Protection */ -#define X86_FEATURE_BMI2 ( 9*32+ 8) /* 2nd group bit manipulation extensions */ -#define X86_FEATURE_ERMS ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB instructions */ -#define X86_FEATURE_INVPCID ( 9*32+10) /* Invalidate Processor Context ID */ -#define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */ -#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */ -#define X86_FEATURE_ZERO_FCS_FDS ( 9*32+13) /* "" Zero out FPU CS and FPU DS */ -#define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */ -#define X86_FEATURE_RDT_A ( 9*32+15) /* Resource Director Technology Allocation */ -#define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */ -#define X86_FEATURE_AVX512DQ ( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */ -#define X86_FEATURE_RDSEED ( 9*32+18) /* RDSEED instruction */ -#define X86_FEATURE_ADX ( 9*32+19) /* ADCX and ADOX instructions */ -#define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */ -#define X86_FEATURE_AVX512IFMA ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */ -#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ -#define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */ -#define X86_FEATURE_INTEL_PT ( 9*32+25) /* Intel Processor Trace */ -#define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ -#define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */ -#define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */ -#define X86_FEATURE_SHA_NI ( 9*32+29) /* SHA1/SHA256 Instruction Extensions */ -#define X86_FEATURE_AVX512BW ( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */ -#define X86_FEATURE_AVX512VL ( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */ +#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* "fsgsbase" RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ +#define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* "tsc_adjust" TSC adjustment MSR 0x3B */ +#define X86_FEATURE_SGX ( 9*32+ 2) /* "sgx" Software Guard Extensions */ +#define X86_FEATURE_BMI1 ( 9*32+ 3) /* "bmi1" 1st group bit manipulation extensions */ +#define X86_FEATURE_HLE ( 9*32+ 4) /* "hle" Hardware Lock Elision */ +#define X86_FEATURE_AVX2 ( 9*32+ 5) /* "avx2" AVX2 instructions */ +#define X86_FEATURE_FDP_EXCPTN_ONLY ( 9*32+ 6) /* FPU data pointer updated only on x87 exceptions */ +#define X86_FEATURE_SMEP ( 9*32+ 7) /* "smep" Supervisor Mode Execution Protection */ +#define X86_FEATURE_BMI2 ( 9*32+ 8) /* "bmi2" 2nd group bit manipulation extensions */ +#define X86_FEATURE_ERMS ( 9*32+ 9) /* "erms" Enhanced REP MOVSB/STOSB instructions */ +#define X86_FEATURE_INVPCID ( 9*32+10) /* "invpcid" Invalidate Processor Context ID */ +#define X86_FEATURE_RTM ( 9*32+11) /* "rtm" Restricted Transactional Memory */ +#define X86_FEATURE_CQM ( 9*32+12) /* "cqm" Cache QoS Monitoring */ +#define X86_FEATURE_ZERO_FCS_FDS ( 9*32+13) /* Zero out FPU CS and FPU DS */ +#define X86_FEATURE_MPX ( 9*32+14) /* "mpx" Memory Protection Extension */ +#define X86_FEATURE_RDT_A ( 9*32+15) /* "rdt_a" Resource Director Technology Allocation */ +#define X86_FEATURE_AVX512F ( 9*32+16) /* "avx512f" AVX-512 Foundation */ +#define X86_FEATURE_AVX512DQ ( 9*32+17) /* "avx512dq" AVX-512 DQ (Double/Quad granular) Instructions */ +#define X86_FEATURE_RDSEED ( 9*32+18) /* "rdseed" RDSEED instruction */ +#define X86_FEATURE_ADX ( 9*32+19) /* "adx" ADCX and ADOX instructions */ +#define X86_FEATURE_SMAP ( 9*32+20) /* "smap" Supervisor Mode Access Prevention */ +#define X86_FEATURE_AVX512IFMA ( 9*32+21) /* "avx512ifma" AVX-512 Integer Fused Multiply-Add instructions */ +#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* "clflushopt" CLFLUSHOPT instruction */ +#define X86_FEATURE_CLWB ( 9*32+24) /* "clwb" CLWB instruction */ +#define X86_FEATURE_INTEL_PT ( 9*32+25) /* "intel_pt" Intel Processor Trace */ +#define X86_FEATURE_AVX512PF ( 9*32+26) /* "avx512pf" AVX-512 Prefetch */ +#define X86_FEATURE_AVX512ER ( 9*32+27) /* "avx512er" AVX-512 Exponential and Reciprocal */ +#define X86_FEATURE_AVX512CD ( 9*32+28) /* "avx512cd" AVX-512 Conflict Detection */ +#define X86_FEATURE_SHA_NI ( 9*32+29) /* "sha_ni" SHA1/SHA256 Instruction Extensions */ +#define X86_FEATURE_AVX512BW ( 9*32+30) /* "avx512bw" AVX-512 BW (Byte/Word granular) Instructions */ +#define X86_FEATURE_AVX512VL ( 9*32+31) /* "avx512vl" AVX-512 VL (128/256 Vector Length) Extensions */ /* Extended state features, CPUID level 0x0000000d:1 (EAX), word 10 */ -#define X86_FEATURE_XSAVEOPT (10*32+ 0) /* XSAVEOPT instruction */ -#define X86_FEATURE_XSAVEC (10*32+ 1) /* XSAVEC instruction */ -#define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 instruction */ -#define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS instructions */ -#define X86_FEATURE_XFD (10*32+ 4) /* "" eXtended Feature Disabling */ +#define X86_FEATURE_XSAVEOPT (10*32+ 0) /* "xsaveopt" XSAVEOPT instruction */ +#define X86_FEATURE_XSAVEC (10*32+ 1) /* "xsavec" XSAVEC instruction */ +#define X86_FEATURE_XGETBV1 (10*32+ 2) /* "xgetbv1" XGETBV with ECX = 1 instruction */ +#define X86_FEATURE_XSAVES (10*32+ 3) /* "xsaves" XSAVES/XRSTORS instructions */ +#define X86_FEATURE_XFD (10*32+ 4) /* eXtended Feature Disabling */ /* * Extended auxiliary flags: Linux defined - for features scattered in various @@ -283,181 +283,182 @@ * * Reuse free bits when adding new feature flags! */ -#define X86_FEATURE_CQM_LLC (11*32+ 0) /* LLC QoS if 1 */ -#define X86_FEATURE_CQM_OCCUP_LLC (11*32+ 1) /* LLC occupancy monitoring */ -#define X86_FEATURE_CQM_MBM_TOTAL (11*32+ 2) /* LLC Total MBM monitoring */ -#define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* LLC Local MBM monitoring */ -#define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* "" LFENCE in user entry SWAPGS path */ -#define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */ -#define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* #AC for split lock */ -#define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */ -#define X86_FEATURE_SGX1 (11*32+ 8) /* "" Basic SGX */ -#define X86_FEATURE_SGX2 (11*32+ 9) /* "" SGX Enclave Dynamic Memory Management (EDMM) */ -#define X86_FEATURE_ENTRY_IBPB (11*32+10) /* "" Issue an IBPB on kernel entry */ -#define X86_FEATURE_RRSBA_CTRL (11*32+11) /* "" RET prediction control */ -#define X86_FEATURE_RETPOLINE (11*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ -#define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* "" Use LFENCE for Spectre variant 2 */ -#define X86_FEATURE_RETHUNK (11*32+14) /* "" Use REturn THUNK */ -#define X86_FEATURE_UNRET (11*32+15) /* "" AMD BTB untrain return */ -#define X86_FEATURE_USE_IBPB_FW (11*32+16) /* "" Use IBPB during runtime firmware calls */ -#define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */ -#define X86_FEATURE_SGX_EDECCSSA (11*32+18) /* "" SGX EDECCSSA user leaf function */ -#define X86_FEATURE_CALL_DEPTH (11*32+19) /* "" Call depth tracking for RSB stuffing */ -#define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */ -#define X86_FEATURE_SMBA (11*32+21) /* "" Slow Memory Bandwidth Allocation */ -#define X86_FEATURE_BMEC (11*32+22) /* "" Bandwidth Monitoring Event Configuration */ -#define X86_FEATURE_USER_SHSTK (11*32+23) /* Shadow stack support for user mode applications */ -#define X86_FEATURE_SRSO (11*32+24) /* "" AMD BTB untrain RETs */ -#define X86_FEATURE_SRSO_ALIAS (11*32+25) /* "" AMD BTB untrain RETs through aliasing */ -#define X86_FEATURE_IBPB_ON_VMEXIT (11*32+26) /* "" Issue an IBPB only on VMEXIT */ -#define X86_FEATURE_APIC_MSRS_FENCE (11*32+27) /* "" IA32_TSC_DEADLINE and X2APIC MSRs need fencing */ -#define X86_FEATURE_ZEN2 (11*32+28) /* "" CPU based on Zen2 microarchitecture */ -#define X86_FEATURE_ZEN3 (11*32+29) /* "" CPU based on Zen3 microarchitecture */ -#define X86_FEATURE_ZEN4 (11*32+30) /* "" CPU based on Zen4 microarchitecture */ -#define X86_FEATURE_ZEN1 (11*32+31) /* "" CPU based on Zen1 microarchitecture */ +#define X86_FEATURE_CQM_LLC (11*32+ 0) /* "cqm_llc" LLC QoS if 1 */ +#define X86_FEATURE_CQM_OCCUP_LLC (11*32+ 1) /* "cqm_occup_llc" LLC occupancy monitoring */ +#define X86_FEATURE_CQM_MBM_TOTAL (11*32+ 2) /* "cqm_mbm_total" LLC Total MBM monitoring */ +#define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* "cqm_mbm_local" LLC Local MBM monitoring */ +#define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* LFENCE in user entry SWAPGS path */ +#define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* LFENCE in kernel entry SWAPGS path */ +#define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* "split_lock_detect" #AC for split lock */ +#define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* Per-thread Memory Bandwidth Allocation */ +#define X86_FEATURE_SGX1 (11*32+ 8) /* Basic SGX */ +#define X86_FEATURE_SGX2 (11*32+ 9) /* SGX Enclave Dynamic Memory Management (EDMM) */ +#define X86_FEATURE_ENTRY_IBPB (11*32+10) /* Issue an IBPB on kernel entry */ +#define X86_FEATURE_RRSBA_CTRL (11*32+11) /* RET prediction control */ +#define X86_FEATURE_RETPOLINE (11*32+12) /* Generic Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* Use LFENCE for Spectre variant 2 */ +#define X86_FEATURE_RETHUNK (11*32+14) /* Use REturn THUNK */ +#define X86_FEATURE_UNRET (11*32+15) /* AMD BTB untrain return */ +#define X86_FEATURE_USE_IBPB_FW (11*32+16) /* Use IBPB during runtime firmware calls */ +#define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* Fill RSB on VM exit when EIBRS is enabled */ +#define X86_FEATURE_SGX_EDECCSSA (11*32+18) /* SGX EDECCSSA user leaf function */ +#define X86_FEATURE_CALL_DEPTH (11*32+19) /* Call depth tracking for RSB stuffing */ +#define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* MSR IA32_TSX_CTRL (Intel) implemented */ +#define X86_FEATURE_SMBA (11*32+21) /* Slow Memory Bandwidth Allocation */ +#define X86_FEATURE_BMEC (11*32+22) /* Bandwidth Monitoring Event Configuration */ +#define X86_FEATURE_USER_SHSTK (11*32+23) /* "user_shstk" Shadow stack support for user mode applications */ +#define X86_FEATURE_SRSO (11*32+24) /* AMD BTB untrain RETs */ +#define X86_FEATURE_SRSO_ALIAS (11*32+25) /* AMD BTB untrain RETs through aliasing */ +#define X86_FEATURE_IBPB_ON_VMEXIT (11*32+26) /* Issue an IBPB only on VMEXIT */ +#define X86_FEATURE_APIC_MSRS_FENCE (11*32+27) /* IA32_TSC_DEADLINE and X2APIC MSRs need fencing */ +#define X86_FEATURE_ZEN2 (11*32+28) /* CPU based on Zen2 microarchitecture */ +#define X86_FEATURE_ZEN3 (11*32+29) /* CPU based on Zen3 microarchitecture */ +#define X86_FEATURE_ZEN4 (11*32+30) /* CPU based on Zen4 microarchitecture */ +#define X86_FEATURE_ZEN1 (11*32+31) /* CPU based on Zen1 microarchitecture */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ -#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ -#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ -#define X86_FEATURE_CMPCCXADD (12*32+ 7) /* "" CMPccXADD instructions */ -#define X86_FEATURE_ARCH_PERFMON_EXT (12*32+ 8) /* "" Intel Architectural PerfMon Extension */ -#define X86_FEATURE_FZRM (12*32+10) /* "" Fast zero-length REP MOVSB */ -#define X86_FEATURE_FSRS (12*32+11) /* "" Fast short REP STOSB */ -#define X86_FEATURE_FSRC (12*32+12) /* "" Fast short REP {CMPSB,SCASB} */ -#define X86_FEATURE_FRED (12*32+17) /* Flexible Return and Event Delivery */ -#define X86_FEATURE_LKGS (12*32+18) /* "" Load "kernel" (userspace) GS */ -#define X86_FEATURE_WRMSRNS (12*32+19) /* "" Non-serializing WRMSR */ -#define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */ -#define X86_FEATURE_AVX_IFMA (12*32+23) /* "" Support for VPMADD52[H,L]UQ */ -#define X86_FEATURE_LAM (12*32+26) /* Linear Address Masking */ +#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* "avx_vnni" AVX VNNI instructions */ +#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* "avx512_bf16" AVX512 BFLOAT16 instructions */ +#define X86_FEATURE_CMPCCXADD (12*32+ 7) /* CMPccXADD instructions */ +#define X86_FEATURE_ARCH_PERFMON_EXT (12*32+ 8) /* Intel Architectural PerfMon Extension */ +#define X86_FEATURE_FZRM (12*32+10) /* Fast zero-length REP MOVSB */ +#define X86_FEATURE_FSRS (12*32+11) /* Fast short REP STOSB */ +#define X86_FEATURE_FSRC (12*32+12) /* Fast short REP {CMPSB,SCASB} */ +#define X86_FEATURE_FRED (12*32+17) /* "fred" Flexible Return and Event Delivery */ +#define X86_FEATURE_LKGS (12*32+18) /* Load "kernel" (userspace) GS */ +#define X86_FEATURE_WRMSRNS (12*32+19) /* Non-serializing WRMSR */ +#define X86_FEATURE_AMX_FP16 (12*32+21) /* AMX fp16 Support */ +#define X86_FEATURE_AVX_IFMA (12*32+23) /* Support for VPMADD52[H,L]UQ */ +#define X86_FEATURE_LAM (12*32+26) /* "lam" Linear Address Masking */ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ -#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ -#define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */ -#define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */ -#define X86_FEATURE_RDPRU (13*32+ 4) /* Read processor register at user level */ -#define X86_FEATURE_WBNOINVD (13*32+ 9) /* WBNOINVD instruction */ -#define X86_FEATURE_AMD_IBPB (13*32+12) /* "" Indirect Branch Prediction Barrier */ -#define X86_FEATURE_AMD_IBRS (13*32+14) /* "" Indirect Branch Restricted Speculation */ -#define X86_FEATURE_AMD_STIBP (13*32+15) /* "" Single Thread Indirect Branch Predictors */ -#define X86_FEATURE_AMD_STIBP_ALWAYS_ON (13*32+17) /* "" Single Thread Indirect Branch Predictors always-on preferred */ -#define X86_FEATURE_AMD_PPIN (13*32+23) /* Protected Processor Inventory Number */ -#define X86_FEATURE_AMD_SSBD (13*32+24) /* "" Speculative Store Bypass Disable */ -#define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ -#define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ -#define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */ -#define X86_FEATURE_AMD_PSFD (13*32+28) /* "" Predictive Store Forwarding Disable */ -#define X86_FEATURE_BTC_NO (13*32+29) /* "" Not vulnerable to Branch Type Confusion */ -#define X86_FEATURE_BRS (13*32+31) /* Branch Sampling available */ +#define X86_FEATURE_CLZERO (13*32+ 0) /* "clzero" CLZERO instruction */ +#define X86_FEATURE_IRPERF (13*32+ 1) /* "irperf" Instructions Retired Count */ +#define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* "xsaveerptr" Always save/restore FP error pointers */ +#define X86_FEATURE_RDPRU (13*32+ 4) /* "rdpru" Read processor register at user level */ +#define X86_FEATURE_WBNOINVD (13*32+ 9) /* "wbnoinvd" WBNOINVD instruction */ +#define X86_FEATURE_AMD_IBPB (13*32+12) /* Indirect Branch Prediction Barrier */ +#define X86_FEATURE_AMD_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */ +#define X86_FEATURE_AMD_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_AMD_STIBP_ALWAYS_ON (13*32+17) /* Single Thread Indirect Branch Predictors always-on preferred */ +#define X86_FEATURE_AMD_PPIN (13*32+23) /* "amd_ppin" Protected Processor Inventory Number */ +#define X86_FEATURE_AMD_SSBD (13*32+24) /* Speculative Store Bypass Disable */ +#define X86_FEATURE_VIRT_SSBD (13*32+25) /* "virt_ssbd" Virtualized Speculative Store Bypass Disable */ +#define X86_FEATURE_AMD_SSB_NO (13*32+26) /* Speculative Store Bypass is fixed in hardware. */ +#define X86_FEATURE_CPPC (13*32+27) /* "cppc" Collaborative Processor Performance Control */ +#define X86_FEATURE_AMD_PSFD (13*32+28) /* Predictive Store Forwarding Disable */ +#define X86_FEATURE_BTC_NO (13*32+29) /* Not vulnerable to Branch Type Confusion */ +#define X86_FEATURE_BRS (13*32+31) /* "brs" Branch Sampling available */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ -#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ -#define X86_FEATURE_IDA (14*32+ 1) /* Intel Dynamic Acceleration */ -#define X86_FEATURE_ARAT (14*32+ 2) /* Always Running APIC Timer */ -#define X86_FEATURE_PLN (14*32+ 4) /* Intel Power Limit Notification */ -#define X86_FEATURE_PTS (14*32+ 6) /* Intel Package Thermal Status */ -#define X86_FEATURE_HWP (14*32+ 7) /* Intel Hardware P-states */ -#define X86_FEATURE_HWP_NOTIFY (14*32+ 8) /* HWP Notification */ -#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */ -#define X86_FEATURE_HWP_EPP (14*32+10) /* HWP Energy Perf. Preference */ -#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */ -#define X86_FEATURE_HFI (14*32+19) /* Hardware Feedback Interface */ +#define X86_FEATURE_DTHERM (14*32+ 0) /* "dtherm" Digital Thermal Sensor */ +#define X86_FEATURE_IDA (14*32+ 1) /* "ida" Intel Dynamic Acceleration */ +#define X86_FEATURE_ARAT (14*32+ 2) /* "arat" Always Running APIC Timer */ +#define X86_FEATURE_PLN (14*32+ 4) /* "pln" Intel Power Limit Notification */ +#define X86_FEATURE_PTS (14*32+ 6) /* "pts" Intel Package Thermal Status */ +#define X86_FEATURE_HWP (14*32+ 7) /* "hwp" Intel Hardware P-states */ +#define X86_FEATURE_HWP_NOTIFY (14*32+ 8) /* "hwp_notify" HWP Notification */ +#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* "hwp_act_window" HWP Activity Window */ +#define X86_FEATURE_HWP_EPP (14*32+10) /* "hwp_epp" HWP Energy Perf. Preference */ +#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* "hwp_pkg_req" HWP Package Level Request */ +#define X86_FEATURE_HFI (14*32+19) /* "hfi" Hardware Feedback Interface */ /* AMD SVM Feature Identification, CPUID level 0x8000000a (EDX), word 15 */ -#define X86_FEATURE_NPT (15*32+ 0) /* Nested Page Table support */ -#define X86_FEATURE_LBRV (15*32+ 1) /* LBR Virtualization support */ +#define X86_FEATURE_NPT (15*32+ 0) /* "npt" Nested Page Table support */ +#define X86_FEATURE_LBRV (15*32+ 1) /* "lbrv" LBR Virtualization support */ #define X86_FEATURE_SVML (15*32+ 2) /* "svm_lock" SVM locking MSR */ #define X86_FEATURE_NRIPS (15*32+ 3) /* "nrip_save" SVM next_rip save */ #define X86_FEATURE_TSCRATEMSR (15*32+ 4) /* "tsc_scale" TSC scaling support */ #define X86_FEATURE_VMCBCLEAN (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */ -#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */ -#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */ -#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */ -#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ -#define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ -#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */ -#define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ -#define X86_FEATURE_X2AVIC (15*32+18) /* Virtual x2apic */ -#define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* Virtual SPEC_CTRL */ -#define X86_FEATURE_VNMI (15*32+25) /* Virtual NMI */ -#define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* "" SVME addr check */ +#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* "flushbyasid" Flush-by-ASID support */ +#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* "decodeassists" Decode Assists support */ +#define X86_FEATURE_PAUSEFILTER (15*32+10) /* "pausefilter" Filtered pause intercept */ +#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* "pfthreshold" Pause filter threshold */ +#define X86_FEATURE_AVIC (15*32+13) /* "avic" Virtual Interrupt Controller */ +#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* "v_vmsave_vmload" Virtual VMSAVE VMLOAD */ +#define X86_FEATURE_VGIF (15*32+16) /* "vgif" Virtual GIF */ +#define X86_FEATURE_X2AVIC (15*32+18) /* "x2avic" Virtual x2apic */ +#define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* "v_spec_ctrl" Virtual SPEC_CTRL */ +#define X86_FEATURE_VNMI (15*32+25) /* "vnmi" Virtual NMI */ +#define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* SVME addr check */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */ -#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ -#define X86_FEATURE_UMIP (16*32+ 2) /* User Mode Instruction Protection */ -#define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */ -#define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */ -#define X86_FEATURE_WAITPKG (16*32+ 5) /* UMONITOR/UMWAIT/TPAUSE Instructions */ -#define X86_FEATURE_AVX512_VBMI2 (16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */ -#define X86_FEATURE_SHSTK (16*32+ 7) /* "" Shadow stack */ -#define X86_FEATURE_GFNI (16*32+ 8) /* Galois Field New Instructions */ -#define X86_FEATURE_VAES (16*32+ 9) /* Vector AES */ -#define X86_FEATURE_VPCLMULQDQ (16*32+10) /* Carry-Less Multiplication Double Quadword */ -#define X86_FEATURE_AVX512_VNNI (16*32+11) /* Vector Neural Network Instructions */ -#define X86_FEATURE_AVX512_BITALG (16*32+12) /* Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */ -#define X86_FEATURE_TME (16*32+13) /* Intel Total Memory Encryption */ -#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ -#define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */ -#define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */ -#define X86_FEATURE_BUS_LOCK_DETECT (16*32+24) /* Bus Lock detect */ -#define X86_FEATURE_CLDEMOTE (16*32+25) /* CLDEMOTE instruction */ -#define X86_FEATURE_MOVDIRI (16*32+27) /* MOVDIRI instruction */ -#define X86_FEATURE_MOVDIR64B (16*32+28) /* MOVDIR64B instruction */ -#define X86_FEATURE_ENQCMD (16*32+29) /* ENQCMD and ENQCMDS instructions */ -#define X86_FEATURE_SGX_LC (16*32+30) /* Software Guard Extensions Launch Control */ +#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* "avx512vbmi" AVX512 Vector Bit Manipulation instructions*/ +#define X86_FEATURE_UMIP (16*32+ 2) /* "umip" User Mode Instruction Protection */ +#define X86_FEATURE_PKU (16*32+ 3) /* "pku" Protection Keys for Userspace */ +#define X86_FEATURE_OSPKE (16*32+ 4) /* "ospke" OS Protection Keys Enable */ +#define X86_FEATURE_WAITPKG (16*32+ 5) /* "waitpkg" UMONITOR/UMWAIT/TPAUSE Instructions */ +#define X86_FEATURE_AVX512_VBMI2 (16*32+ 6) /* "avx512_vbmi2" Additional AVX512 Vector Bit Manipulation Instructions */ +#define X86_FEATURE_SHSTK (16*32+ 7) /* Shadow stack */ +#define X86_FEATURE_GFNI (16*32+ 8) /* "gfni" Galois Field New Instructions */ +#define X86_FEATURE_VAES (16*32+ 9) /* "vaes" Vector AES */ +#define X86_FEATURE_VPCLMULQDQ (16*32+10) /* "vpclmulqdq" Carry-Less Multiplication Double Quadword */ +#define X86_FEATURE_AVX512_VNNI (16*32+11) /* "avx512_vnni" Vector Neural Network Instructions */ +#define X86_FEATURE_AVX512_BITALG (16*32+12) /* "avx512_bitalg" Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */ +#define X86_FEATURE_TME (16*32+13) /* "tme" Intel Total Memory Encryption */ +#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* "avx512_vpopcntdq" POPCNT for vectors of DW/QW */ +#define X86_FEATURE_LA57 (16*32+16) /* "la57" 5-level page tables */ +#define X86_FEATURE_RDPID (16*32+22) /* "rdpid" RDPID instruction */ +#define X86_FEATURE_BUS_LOCK_DETECT (16*32+24) /* "bus_lock_detect" Bus Lock detect */ +#define X86_FEATURE_CLDEMOTE (16*32+25) /* "cldemote" CLDEMOTE instruction */ +#define X86_FEATURE_MOVDIRI (16*32+27) /* "movdiri" MOVDIRI instruction */ +#define X86_FEATURE_MOVDIR64B (16*32+28) /* "movdir64b" MOVDIR64B instruction */ +#define X86_FEATURE_ENQCMD (16*32+29) /* "enqcmd" ENQCMD and ENQCMDS instructions */ +#define X86_FEATURE_SGX_LC (16*32+30) /* "sgx_lc" Software Guard Extensions Launch Control */ /* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */ -#define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* MCA overflow recovery support */ -#define X86_FEATURE_SUCCOR (17*32+ 1) /* Uncorrectable error containment and recovery */ -#define X86_FEATURE_SMCA (17*32+ 3) /* Scalable MCA */ +#define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* "overflow_recov" MCA overflow recovery support */ +#define X86_FEATURE_SUCCOR (17*32+ 1) /* "succor" Uncorrectable error containment and recovery */ +#define X86_FEATURE_SMCA (17*32+ 3) /* "smca" Scalable MCA */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ -#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ -#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ -#define X86_FEATURE_FSRM (18*32+ 4) /* Fast Short Rep Mov */ -#define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */ -#define X86_FEATURE_SRBDS_CTRL (18*32+ 9) /* "" SRBDS mitigation MSR available */ -#define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */ -#define X86_FEATURE_RTM_ALWAYS_ABORT (18*32+11) /* "" RTM transaction always aborts */ -#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ -#define X86_FEATURE_SERIALIZE (18*32+14) /* SERIALIZE instruction */ -#define X86_FEATURE_HYBRID_CPU (18*32+15) /* "" This part has CPUs of more than one type */ -#define X86_FEATURE_TSXLDTRK (18*32+16) /* TSX Suspend Load Address Tracking */ -#define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ -#define X86_FEATURE_ARCH_LBR (18*32+19) /* Intel ARCH LBR */ -#define X86_FEATURE_IBT (18*32+20) /* Indirect Branch Tracking */ -#define X86_FEATURE_AMX_BF16 (18*32+22) /* AMX bf16 Support */ -#define X86_FEATURE_AVX512_FP16 (18*32+23) /* AVX512 FP16 */ -#define X86_FEATURE_AMX_TILE (18*32+24) /* AMX tile Support */ -#define X86_FEATURE_AMX_INT8 (18*32+25) /* AMX int8 Support */ -#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ -#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ -#define X86_FEATURE_FLUSH_L1D (18*32+28) /* Flush L1D cache */ -#define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */ -#define X86_FEATURE_CORE_CAPABILITIES (18*32+30) /* "" IA32_CORE_CAPABILITIES MSR */ -#define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* "" Speculative Store Bypass Disable */ +#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* "avx512_4vnniw" AVX-512 Neural Network Instructions */ +#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* "avx512_4fmaps" AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_FSRM (18*32+ 4) /* "fsrm" Fast Short Rep Mov */ +#define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* "avx512_vp2intersect" AVX-512 Intersect for D/Q */ +#define X86_FEATURE_SRBDS_CTRL (18*32+ 9) /* SRBDS mitigation MSR available */ +#define X86_FEATURE_MD_CLEAR (18*32+10) /* "md_clear" VERW clears CPU buffers */ +#define X86_FEATURE_RTM_ALWAYS_ABORT (18*32+11) /* RTM transaction always aborts */ +#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* TSX_FORCE_ABORT */ +#define X86_FEATURE_SERIALIZE (18*32+14) /* "serialize" SERIALIZE instruction */ +#define X86_FEATURE_HYBRID_CPU (18*32+15) /* This part has CPUs of more than one type */ +#define X86_FEATURE_TSXLDTRK (18*32+16) /* "tsxldtrk" TSX Suspend Load Address Tracking */ +#define X86_FEATURE_PCONFIG (18*32+18) /* "pconfig" Intel PCONFIG */ +#define X86_FEATURE_ARCH_LBR (18*32+19) /* "arch_lbr" Intel ARCH LBR */ +#define X86_FEATURE_IBT (18*32+20) /* "ibt" Indirect Branch Tracking */ +#define X86_FEATURE_AMX_BF16 (18*32+22) /* "amx_bf16" AMX bf16 Support */ +#define X86_FEATURE_AVX512_FP16 (18*32+23) /* "avx512_fp16" AVX512 FP16 */ +#define X86_FEATURE_AMX_TILE (18*32+24) /* "amx_tile" AMX tile Support */ +#define X86_FEATURE_AMX_INT8 (18*32+25) /* "amx_int8" AMX int8 Support */ +#define X86_FEATURE_SPEC_CTRL (18*32+26) /* Speculation Control (IBRS + IBPB) */ +#define X86_FEATURE_INTEL_STIBP (18*32+27) /* Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_FLUSH_L1D (18*32+28) /* "flush_l1d" Flush L1D cache */ +#define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* "arch_capabilities" IA32_ARCH_CAPABILITIES MSR (Intel) */ +#define X86_FEATURE_CORE_CAPABILITIES (18*32+30) /* IA32_CORE_CAPABILITIES MSR */ +#define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* Speculative Store Bypass Disable */ /* AMD-defined memory encryption features, CPUID level 0x8000001f (EAX), word 19 */ -#define X86_FEATURE_SME (19*32+ 0) /* AMD Secure Memory Encryption */ -#define X86_FEATURE_SEV (19*32+ 1) /* AMD Secure Encrypted Virtualization */ -#define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* "" VM Page Flush MSR is supported */ -#define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */ -#define X86_FEATURE_SEV_SNP (19*32+ 4) /* AMD Secure Encrypted Virtualization - Secure Nested Paging */ -#define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */ -#define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ -#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* AMD SEV-ES full debug state swap support */ +#define X86_FEATURE_SME (19*32+ 0) /* "sme" AMD Secure Memory Encryption */ +#define X86_FEATURE_SEV (19*32+ 1) /* "sev" AMD Secure Encrypted Virtualization */ +#define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* VM Page Flush MSR is supported */ +#define X86_FEATURE_SEV_ES (19*32+ 3) /* "sev_es" AMD Secure Encrypted Virtualization - Encrypted State */ +#define X86_FEATURE_SEV_SNP (19*32+ 4) /* "sev_snp" AMD Secure Encrypted Virtualization - Secure Nested Paging */ +#define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* Virtual TSC_AUX */ +#define X86_FEATURE_SME_COHERENT (19*32+10) /* AMD hardware-enforced cache coherency */ +#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" AMD SEV-ES full debug state swap support */ +#define X86_FEATURE_SVSM (19*32+28) /* "svsm" SVSM present */ /* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */ -#define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* "" No Nested Data Breakpoints */ -#define X86_FEATURE_WRMSR_XX_BASE_NS (20*32+ 1) /* "" WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */ -#define X86_FEATURE_LFENCE_RDTSC (20*32+ 2) /* "" LFENCE always serializing / synchronizes RDTSC */ -#define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* "" Null Selector Clears Base */ -#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* "" Automatic IBRS */ -#define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* "" SMM_CTL MSR is not present */ +#define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* No Nested Data Breakpoints */ +#define X86_FEATURE_WRMSR_XX_BASE_NS (20*32+ 1) /* WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */ +#define X86_FEATURE_LFENCE_RDTSC (20*32+ 2) /* LFENCE always serializing / synchronizes RDTSC */ +#define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* Null Selector Clears Base */ +#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* Automatic IBRS */ +#define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* SMM_CTL MSR is not present */ -#define X86_FEATURE_SBPB (20*32+27) /* "" Selective Branch Prediction Barrier */ -#define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */ -#define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */ +#define X86_FEATURE_SBPB (20*32+27) /* Selective Branch Prediction Barrier */ +#define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */ +#define X86_FEATURE_SRSO_NO (20*32+29) /* CPU is not affected by SRSO */ /* * Extended auxiliary flags: Linux defined - for features scattered in various @@ -465,59 +466,59 @@ * * Reuse free bits when adding new feature flags! */ -#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* AMD LBR and PMC Freeze */ -#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* "" Clear branch history at syscall entry using SW loop */ -#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* "" BHI_DIS_S HW control available */ -#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* "" BHI_DIS_S HW control enabled */ -#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* "" Clear branch history at vmexit using SW loop */ +#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* "amd_lbr_pmc_freeze" AMD LBR and PMC Freeze */ +#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* Clear branch history at syscall entry using SW loop */ +#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* BHI_DIS_S HW control available */ +#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* BHI_DIS_S HW control enabled */ +#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* Clear branch history at vmexit using SW loop */ /* * BUG word(s) */ #define X86_BUG(x) (NCAPINTS*32 + (x)) -#define X86_BUG_F00F X86_BUG(0) /* Intel F00F */ -#define X86_BUG_FDIV X86_BUG(1) /* FPU FDIV */ -#define X86_BUG_COMA X86_BUG(2) /* Cyrix 6x86 coma */ +#define X86_BUG_F00F X86_BUG(0) /* "f00f" Intel F00F */ +#define X86_BUG_FDIV X86_BUG(1) /* "fdiv" FPU FDIV */ +#define X86_BUG_COMA X86_BUG(2) /* "coma" Cyrix 6x86 coma */ #define X86_BUG_AMD_TLB_MMATCH X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */ #define X86_BUG_AMD_APIC_C1E X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */ -#define X86_BUG_11AP X86_BUG(5) /* Bad local APIC aka 11AP */ -#define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */ -#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */ -#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */ +#define X86_BUG_11AP X86_BUG(5) /* "11ap" Bad local APIC aka 11AP */ +#define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* "fxsave_leak" FXSAVE leaks FOP/FIP/FOP */ +#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* "clflush_monitor" AAI65, CLFLUSH required before MONITOR */ +#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* "sysret_ss_attrs" SYSRET doesn't fix up SS attrs */ #ifdef CONFIG_X86_32 /* * 64-bit kernels don't use X86_BUG_ESPFIX. Make the define conditional * to avoid confusion. */ -#define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */ +#define X86_BUG_ESPFIX X86_BUG(9) /* IRET to 16-bit SS corrupts ESP/RSP high bits */ #endif -#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */ -#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ -#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */ -#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */ -#define X86_BUG_CPU_MELTDOWN X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */ -#define X86_BUG_SPECTRE_V1 X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */ -#define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */ -#define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* CPU is affected by speculative store bypass attack */ -#define X86_BUG_L1TF X86_BUG(18) /* CPU is affected by L1 Terminal Fault */ -#define X86_BUG_MDS X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */ -#define X86_BUG_MSBDS_ONLY X86_BUG(20) /* CPU is only affected by the MSDBS variant of BUG_MDS */ -#define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */ -#define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */ -#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ -#define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */ -#define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */ -#define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */ -#define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */ -#define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ -#define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */ -#define X86_BUG_GDS X86_BUG(30) /* CPU is affected by Gather Data Sampling */ -#define X86_BUG_TDX_PW_MCE X86_BUG(31) /* CPU may incur #MC if non-TD software does partial write to TDX private memory */ +#define X86_BUG_NULL_SEG X86_BUG(10) /* "null_seg" Nulling a selector preserves the base */ +#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* "swapgs_fence" SWAPGS without input dep on GS */ +#define X86_BUG_MONITOR X86_BUG(12) /* "monitor" IPI required to wake up remote CPU */ +#define X86_BUG_AMD_E400 X86_BUG(13) /* "amd_e400" CPU is among the affected by Erratum 400 */ +#define X86_BUG_CPU_MELTDOWN X86_BUG(14) /* "cpu_meltdown" CPU is affected by meltdown attack and needs kernel page table isolation */ +#define X86_BUG_SPECTRE_V1 X86_BUG(15) /* "spectre_v1" CPU is affected by Spectre variant 1 attack with conditional branches */ +#define X86_BUG_SPECTRE_V2 X86_BUG(16) /* "spectre_v2" CPU is affected by Spectre variant 2 attack with indirect branches */ +#define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* "spec_store_bypass" CPU is affected by speculative store bypass attack */ +#define X86_BUG_L1TF X86_BUG(18) /* "l1tf" CPU is affected by L1 Terminal Fault */ +#define X86_BUG_MDS X86_BUG(19) /* "mds" CPU is affected by Microarchitectural data sampling */ +#define X86_BUG_MSBDS_ONLY X86_BUG(20) /* "msbds_only" CPU is only affected by the MSDBS variant of BUG_MDS */ +#define X86_BUG_SWAPGS X86_BUG(21) /* "swapgs" CPU is affected by speculation through SWAPGS */ +#define X86_BUG_TAA X86_BUG(22) /* "taa" CPU is affected by TSX Async Abort(TAA) */ +#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* "itlb_multihit" CPU may incur MCE during certain page attribute changes */ +#define X86_BUG_SRBDS X86_BUG(24) /* "srbds" CPU may leak RNG bits if not mitigated */ +#define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* "mmio_stale_data" CPU is affected by Processor MMIO Stale Data vulnerabilities */ +#define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* "mmio_unknown" CPU is too old and its MMIO Stale Data status is unknown */ +#define X86_BUG_RETBLEED X86_BUG(27) /* "retbleed" CPU is affected by RETBleed */ +#define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* "eibrs_pbrsb" EIBRS is vulnerable to Post Barrier RSB Predictions */ +#define X86_BUG_SMT_RSB X86_BUG(29) /* "smt_rsb" CPU is vulnerable to Cross-Thread Return Address Predictions */ +#define X86_BUG_GDS X86_BUG(30) /* "gds" CPU is affected by Gather Data Sampling */ +#define X86_BUG_TDX_PW_MCE X86_BUG(31) /* "tdx_pw_mce" CPU may incur #MC if non-TD software does partial write to TDX private memory */ /* BUG word 2 */ -#define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ -#define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */ -#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */ -#define X86_BUG_BHI X86_BUG(1*32 + 3) /* CPU is affected by Branch History Injection */ +#define X86_BUG_SRSO X86_BUG(1*32 + 0) /* "srso" AMD SRSO bug */ +#define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* "div0" AMD DIV0 speculation bug */ +#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* "rfds" CPU is vulnerable to Register File Data Sampling */ +#define X86_BUG_BHI X86_BUG(1*32 + 3) /* "bhi" CPU is affected by Branch History Injection */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h index cc9ccf61b6bd..14d72727d7ee 100644 --- a/arch/x86/include/asm/init.h +++ b/arch/x86/include/asm/init.h @@ -6,6 +6,7 @@ struct x86_mapping_info { void *(*alloc_pgt_page)(void *); /* allocate buf for page table */ + void (*free_pgt_page)(void *, void *); /* free buf for page table */ void *context; /* context for alloc_pgt_page */ unsigned long page_flag; /* page flag for PMD or PUD entry */ unsigned long offset; /* ident mapping offset */ @@ -16,4 +17,6 @@ struct x86_mapping_info { int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, unsigned long pstart, unsigned long pend); +void kernel_ident_mapping_free(struct x86_mapping_info *info, pgd_t *pgd); + #endif /* _ASM_X86_INIT_H */ diff --git a/arch/x86/include/asm/intel_pconfig.h b/arch/x86/include/asm/intel_pconfig.h deleted file mode 100644 index 994638ef171b..000000000000 --- a/arch/x86/include/asm/intel_pconfig.h +++ /dev/null @@ -1,65 +0,0 @@ -#ifndef _ASM_X86_INTEL_PCONFIG_H -#define _ASM_X86_INTEL_PCONFIG_H - -#include -#include - -enum pconfig_target { - INVALID_TARGET = 0, - MKTME_TARGET = 1, - PCONFIG_TARGET_NR -}; - -int pconfig_target_supported(enum pconfig_target target); - -enum pconfig_leaf { - MKTME_KEY_PROGRAM = 0, - PCONFIG_LEAF_INVALID, -}; - -#define PCONFIG ".byte 0x0f, 0x01, 0xc5" - -/* Defines and structure for MKTME_KEY_PROGRAM of PCONFIG instruction */ - -/* mktme_key_program::keyid_ctrl COMMAND, bits [7:0] */ -#define MKTME_KEYID_SET_KEY_DIRECT 0 -#define MKTME_KEYID_SET_KEY_RANDOM 1 -#define MKTME_KEYID_CLEAR_KEY 2 -#define MKTME_KEYID_NO_ENCRYPT 3 - -/* mktme_key_program::keyid_ctrl ENC_ALG, bits [23:8] */ -#define MKTME_AES_XTS_128 (1 << 8) - -/* Return codes from the PCONFIG MKTME_KEY_PROGRAM */ -#define MKTME_PROG_SUCCESS 0 -#define MKTME_INVALID_PROG_CMD 1 -#define MKTME_ENTROPY_ERROR 2 -#define MKTME_INVALID_KEYID 3 -#define MKTME_INVALID_ENC_ALG 4 -#define MKTME_DEVICE_BUSY 5 - -/* Hardware requires the structure to be 256 byte aligned. Otherwise #GP(0). */ -struct mktme_key_program { - u16 keyid; - u32 keyid_ctrl; - u8 __rsvd[58]; - u8 key_field_1[64]; - u8 key_field_2[64]; -} __packed __aligned(256); - -static inline int mktme_key_program(struct mktme_key_program *key_program) -{ - unsigned long rax = MKTME_KEY_PROGRAM; - - if (!pconfig_target_supported(MKTME_TARGET)) - return -ENXIO; - - asm volatile(PCONFIG - : "=a" (rax), "=b" (key_program) - : "0" (rax), "1" (key_program) - : "memory", "cc"); - - return rax; -} - -#endif /* _ASM_X86_INTEL_PCONFIG_H */ diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index 8c5ae649d2df..cf7fc2b8e3ce 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -54,6 +54,26 @@ static __always_inline void native_halt(void) asm volatile("hlt": : :"memory"); } +static __always_inline int native_irqs_disabled_flags(unsigned long flags) +{ + return !(flags & X86_EFLAGS_IF); +} + +static __always_inline unsigned long native_local_irq_save(void) +{ + unsigned long flags = native_save_fl(); + + native_irq_disable(); + + return flags; +} + +static __always_inline void native_local_irq_restore(unsigned long flags) +{ + if (!native_irqs_disabled_flags(flags)) + native_irq_enable(); +} + #endif #ifdef CONFIG_PARAVIRT_XXL diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index e022e6eb766c..01342963011e 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -660,6 +660,8 @@ #define MSR_AMD64_RMP_BASE 0xc0010132 #define MSR_AMD64_RMP_END 0xc0010133 +#define MSR_SVSM_CAA 0xc001f000 + /* AMD Collaborative Processor Performance Control MSRs */ #define MSR_AMD_CPPC_CAP1 0xc00102b0 #define MSR_AMD_CPPC_ENABLE 0xc00102b1 @@ -1164,6 +1166,7 @@ #define MSR_IA32_QM_CTR 0xc8e #define MSR_IA32_PQR_ASSOC 0xc8f #define MSR_IA32_L3_CBM_BASE 0xc90 +#define MSR_RMID_SNC_CONFIG 0xca0 #define MSR_IA32_L2_CBM_BASE 0xd10 #define MSR_IA32_MBA_THRTL_BASE 0xd50 diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index cc6b8e087192..af4302d79b59 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -54,7 +54,7 @@ static inline void clear_page(void *page) clear_page_rep, X86_FEATURE_REP_GOOD, clear_page_erms, X86_FEATURE_ERMS, "=D" (page), - "0" (page) + "D" (page) : "cc", "memory", "rax", "rcx"); } diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 65b8e5bb902c..e39311a89bf4 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -140,6 +140,11 @@ static inline int pte_young(pte_t pte) return pte_flags(pte) & _PAGE_ACCESSED; } +static inline bool pte_decrypted(pte_t pte) +{ + return cc_mkdec(pte_val(pte)) == pte_val(pte); +} + #define pmd_dirty pmd_dirty static inline bool pmd_dirty(pmd_t pmd) { diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index b78644962626..2f321137736c 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -549,6 +549,7 @@ enum pg_level { PG_LEVEL_2M, PG_LEVEL_1G, PG_LEVEL_512G, + PG_LEVEL_256T, PG_LEVEL_NUM }; diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index cb4f6c513c48..a75a07f4931f 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -692,7 +692,17 @@ static inline u32 per_cpu_l2c_id(unsigned int cpu) #ifdef CONFIG_CPU_SUP_AMD extern u32 amd_get_highest_perf(void); -extern void amd_clear_divider(void); + +/* + * Issue a DIV 0/1 insn to clear any division data from previous DIV + * operations. + */ +static __always_inline void amd_clear_divider(void) +{ + asm volatile(ALTERNATIVE("", "div %2\n\t", X86_BUG_DIV0) + :: "a" (0), "d" (0), "r" (1)); +} + extern void amd_check_microcode(void); #else static inline u32 amd_get_highest_perf(void) { return 0; } diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index 9aee31862b4a..4b2abce2e3e7 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -49,8 +49,11 @@ int set_memory_wb(unsigned long addr, int numpages); int set_memory_np(unsigned long addr, int numpages); int set_memory_p(unsigned long addr, int numpages); int set_memory_4k(unsigned long addr, int numpages); + +bool set_memory_enc_stop_conversion(void); int set_memory_encrypted(unsigned long addr, int numpages); int set_memory_decrypted(unsigned long addr, int numpages); + int set_memory_np_noalias(unsigned long addr, int numpages); int set_memory_nonglobal(unsigned long addr, int numpages); int set_memory_global(unsigned long addr, int numpages); diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index e61e68d71cba..0667b2a88614 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -28,6 +28,8 @@ #define NEW_CL_POINTER 0x228 /* Relative to real mode data */ #ifndef __ASSEMBLY__ +#include + #include #include @@ -133,6 +135,12 @@ asmlinkage void __init __noreturn x86_64_start_reservations(char *real_mode_data #endif /* __i386__ */ #endif /* _SETUP */ +#ifdef CONFIG_CMDLINE_BOOL +extern bool builtin_cmdline_added __ro_after_init; +#else +#define builtin_cmdline_added 0 +#endif + #else /* __ASSEMBLY */ .macro __RESERVE_BRK name, size diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h index 5a8246dd532f..e90d403f2068 100644 --- a/arch/x86/include/asm/sev-common.h +++ b/arch/x86/include/asm/sev-common.h @@ -98,6 +98,19 @@ enum psc_op { /* GHCBData[63:32] */ \ (((u64)(val) & GENMASK_ULL(63, 32)) >> 32) +/* GHCB Run at VMPL Request/Response */ +#define GHCB_MSR_VMPL_REQ 0x016 +#define GHCB_MSR_VMPL_REQ_LEVEL(v) \ + /* GHCBData[39:32] */ \ + (((u64)(v) & GENMASK_ULL(7, 0) << 32) | \ + /* GHCBDdata[11:0] */ \ + GHCB_MSR_VMPL_REQ) + +#define GHCB_MSR_VMPL_RESP 0x017 +#define GHCB_MSR_VMPL_RESP_VAL(v) \ + /* GHCBData[63:32] */ \ + (((u64)(v) & GENMASK_ULL(63, 32)) >> 32) + /* GHCB Hypervisor Feature Request/Response */ #define GHCB_MSR_HV_FT_REQ 0x080 #define GHCB_MSR_HV_FT_RESP 0x081 @@ -109,6 +122,7 @@ enum psc_op { #define GHCB_HV_FT_SNP BIT_ULL(0) #define GHCB_HV_FT_SNP_AP_CREATION BIT_ULL(1) +#define GHCB_HV_FT_SNP_MULTI_VMPL BIT_ULL(5) /* * SNP Page State Change NAE event @@ -163,6 +177,10 @@ struct snp_psc_desc { #define GHCB_TERM_NOT_VMPL0 3 /* SNP guest is not running at VMPL-0 */ #define GHCB_TERM_CPUID 4 /* CPUID-validation failure */ #define GHCB_TERM_CPUID_HV 5 /* CPUID failure during hypervisor fallback */ +#define GHCB_TERM_SECRETS_PAGE 6 /* Secrets page failure */ +#define GHCB_TERM_NO_SVSM 7 /* SVSM is not advertised in the secrets page */ +#define GHCB_TERM_SVSM_VMPL0 8 /* SVSM is present but has set VMPL to 0 */ +#define GHCB_TERM_SVSM_CAA 9 /* SVSM is present but CAA is not page aligned */ #define GHCB_RESP_CODE(v) ((v) & GHCB_MSR_INFO_MASK) diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index ca20cc4e5826..ac5886ce252e 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -152,10 +152,119 @@ struct snp_secrets_page { u8 vmpck2[VMPCK_KEY_LEN]; u8 vmpck3[VMPCK_KEY_LEN]; struct secrets_os_area os_area; - u8 rsvd3[3840]; + + u8 vmsa_tweak_bitmap[64]; + + /* SVSM fields */ + u64 svsm_base; + u64 svsm_size; + u64 svsm_caa; + u32 svsm_max_version; + u8 svsm_guest_vmpl; + u8 rsvd3[3]; + + /* Remainder of page */ + u8 rsvd4[3744]; } __packed; +/* + * The SVSM Calling Area (CA) related structures. + */ +struct svsm_ca { + u8 call_pending; + u8 mem_available; + u8 rsvd1[6]; + + u8 svsm_buffer[PAGE_SIZE - 8]; +}; + +#define SVSM_SUCCESS 0 +#define SVSM_ERR_INCOMPLETE 0x80000000 +#define SVSM_ERR_UNSUPPORTED_PROTOCOL 0x80000001 +#define SVSM_ERR_UNSUPPORTED_CALL 0x80000002 +#define SVSM_ERR_INVALID_ADDRESS 0x80000003 +#define SVSM_ERR_INVALID_FORMAT 0x80000004 +#define SVSM_ERR_INVALID_PARAMETER 0x80000005 +#define SVSM_ERR_INVALID_REQUEST 0x80000006 +#define SVSM_ERR_BUSY 0x80000007 +#define SVSM_PVALIDATE_FAIL_SIZEMISMATCH 0x80001006 + +/* + * The SVSM PVALIDATE related structures + */ +struct svsm_pvalidate_entry { + u64 page_size : 2, + action : 1, + ignore_cf : 1, + rsvd : 8, + pfn : 52; +}; + +struct svsm_pvalidate_call { + u16 num_entries; + u16 cur_index; + + u8 rsvd1[4]; + + struct svsm_pvalidate_entry entry[]; +}; + +#define SVSM_PVALIDATE_MAX_COUNT ((sizeof_field(struct svsm_ca, svsm_buffer) - \ + offsetof(struct svsm_pvalidate_call, entry)) / \ + sizeof(struct svsm_pvalidate_entry)) + +/* + * The SVSM Attestation related structures + */ +struct svsm_loc_entry { + u64 pa; + u32 len; + u8 rsvd[4]; +}; + +struct svsm_attest_call { + struct svsm_loc_entry report_buf; + struct svsm_loc_entry nonce; + struct svsm_loc_entry manifest_buf; + struct svsm_loc_entry certificates_buf; + + /* For attesting a single service */ + u8 service_guid[16]; + u32 service_manifest_ver; + u8 rsvd[4]; +}; + +/* + * SVSM protocol structure + */ +struct svsm_call { + struct svsm_ca *caa; + u64 rax; + u64 rcx; + u64 rdx; + u64 r8; + u64 r9; + u64 rax_out; + u64 rcx_out; + u64 rdx_out; + u64 r8_out; + u64 r9_out; +}; + +#define SVSM_CORE_CALL(x) ((0ULL << 32) | (x)) +#define SVSM_CORE_REMAP_CA 0 +#define SVSM_CORE_PVALIDATE 1 +#define SVSM_CORE_CREATE_VCPU 2 +#define SVSM_CORE_DELETE_VCPU 3 + +#define SVSM_ATTEST_CALL(x) ((1ULL << 32) | (x)) +#define SVSM_ATTEST_SERVICES 0 +#define SVSM_ATTEST_SINGLE_SERVICE 1 + #ifdef CONFIG_AMD_MEM_ENCRYPT + +extern u8 snp_vmpl; + extern void __sev_es_ist_enter(struct pt_regs *regs); extern void __sev_es_ist_exit(void); static __always_inline void sev_es_ist_enter(struct pt_regs *regs) @@ -181,6 +290,14 @@ static __always_inline void sev_es_nmi_complete(void) extern int __init sev_es_efi_map_ghcbs(pgd_t *pgd); extern void sev_enable(struct boot_params *bp); +/* + * RMPADJUST modifies the RMP permissions of a page of a lesser- + * privileged (numerically higher) VMPL. + * + * If the guest is running at a higher-privilege than the privilege + * level the instruction is targeting, the instruction will succeed, + * otherwise, it will fail. + */ static inline int rmpadjust(unsigned long vaddr, bool rmp_psize, unsigned long attrs) { int rc; @@ -225,11 +342,16 @@ bool snp_init(struct boot_params *bp); void __noreturn snp_abort(void); void snp_dmi_setup(void); int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio); +int snp_issue_svsm_attest_req(u64 call_id, struct svsm_call *call, struct svsm_attest_call *input); void snp_accept_memory(phys_addr_t start, phys_addr_t end); u64 snp_get_unsupported_features(u64 status); u64 sev_get_status(void); void sev_show_status(void); -#else +void snp_update_svsm_ca(void); + +#else /* !CONFIG_AMD_MEM_ENCRYPT */ + +#define snp_vmpl 0 static inline void sev_es_ist_enter(struct pt_regs *regs) { } static inline void sev_es_ist_exit(void) { } static inline int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) { return 0; } @@ -253,12 +375,17 @@ static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *in { return -ENOTTY; } - +static inline int snp_issue_svsm_attest_req(u64 call_id, struct svsm_call *call, struct svsm_attest_call *input) +{ + return -ENOTTY; +} static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { } static inline u64 snp_get_unsupported_features(u64 status) { return 0; } static inline u64 sev_get_status(void) { return 0; } static inline void sev_show_status(void) { } -#endif +static inline void snp_update_svsm_ca(void) { } + +#endif /* CONFIG_AMD_MEM_ENCRYPT */ #ifdef CONFIG_KVM_AMD_SEV bool snp_probe_rmptable_info(void); diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index a35936b512fe..ca073f40698f 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -35,6 +35,7 @@ struct smp_ops { int (*cpu_disable)(void); void (*cpu_die)(unsigned int cpu); void (*play_dead)(void); + void (*stop_this_cpu)(void); void (*send_call_func_ipi)(const struct cpumask *mask); void (*send_call_func_single_ipi)(int cpu); diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h index ac9fc51e2b18..c9cf43d5ef23 100644 --- a/arch/x86/include/asm/vmware.h +++ b/arch/x86/include/asm/vmware.h @@ -7,51 +7,321 @@ #include /* - * The hypercall definitions differ in the low word of the %edx argument - * in the following way: the old port base interface uses the port - * number to distinguish between high- and low bandwidth versions. + * VMware hypercall ABI. + * + * - Low bandwidth (LB) hypercalls (I/O port based, vmcall and vmmcall) + * have up to 6 input and 6 output arguments passed and returned using + * registers: %eax (arg0), %ebx (arg1), %ecx (arg2), %edx (arg3), + * %esi (arg4), %edi (arg5). + * The following input arguments must be initialized by the caller: + * arg0 - VMWARE_HYPERVISOR_MAGIC + * arg2 - Hypercall command + * arg3 bits [15:0] - Port number, LB and direction flags + * + * - Low bandwidth TDX hypercalls (x86_64 only) are similar to LB + * hypercalls. They also have up to 6 input and 6 output on registers + * arguments, with different argument to register mapping: + * %r12 (arg0), %rbx (arg1), %r13 (arg2), %rdx (arg3), + * %rsi (arg4), %rdi (arg5). + * + * - High bandwidth (HB) hypercalls are I/O port based only. They have + * up to 7 input and 7 output arguments passed and returned using + * registers: %eax (arg0), %ebx (arg1), %ecx (arg2), %edx (arg3), + * %esi (arg4), %edi (arg5), %ebp (arg6). + * The following input arguments must be initialized by the caller: + * arg0 - VMWARE_HYPERVISOR_MAGIC + * arg1 - Hypercall command + * arg3 bits [15:0] - Port number, HB and direction flags + * + * For compatibility purposes, x86_64 systems use only lower 32 bits + * for input and output arguments. + * + * The hypercall definitions differ in the low word of the %edx (arg3) + * in the following way: the old I/O port based interface uses the port + * number to distinguish between high- and low bandwidth versions, and + * uses IN/OUT instructions to define transfer direction. * * The new vmcall interface instead uses a set of flags to select * bandwidth mode and transfer direction. The flags should be loaded - * into %dx by any user and are automatically replaced by the port - * number if the VMWARE_HYPERVISOR_PORT method is used. - * - * In short, new driver code should strictly use the new definition of - * %dx content. + * into arg3 by any user and are automatically replaced by the port + * number if the I/O port method is used. */ -/* Old port-based version */ -#define VMWARE_HYPERVISOR_PORT 0x5658 -#define VMWARE_HYPERVISOR_PORT_HB 0x5659 +#define VMWARE_HYPERVISOR_HB BIT(0) +#define VMWARE_HYPERVISOR_OUT BIT(1) -/* Current vmcall / vmmcall version */ -#define VMWARE_HYPERVISOR_HB BIT(0) -#define VMWARE_HYPERVISOR_OUT BIT(1) +#define VMWARE_HYPERVISOR_PORT 0x5658 +#define VMWARE_HYPERVISOR_PORT_HB (VMWARE_HYPERVISOR_PORT | \ + VMWARE_HYPERVISOR_HB) -/* The low bandwidth call. The low word of edx is presumed clear. */ -#define VMWARE_HYPERCALL \ - ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT) ", %%dx; " \ - "inl (%%dx), %%eax", \ - "vmcall", X86_FEATURE_VMCALL, \ - "vmmcall", X86_FEATURE_VMW_VMMCALL) +#define VMWARE_HYPERVISOR_MAGIC 0x564d5868U + +#define VMWARE_CMD_GETVERSION 10 +#define VMWARE_CMD_GETHZ 45 +#define VMWARE_CMD_GETVCPU_INFO 68 +#define VMWARE_CMD_STEALCLOCK 91 +/* + * Hypercall command mask: + * bits [6:0] command, range [0, 127] + * bits [19:16] sub-command, range [0, 15] + */ +#define VMWARE_CMD_MASK 0xf007fU + +#define CPUID_VMWARE_FEATURES_ECX_VMMCALL BIT(0) +#define CPUID_VMWARE_FEATURES_ECX_VMCALL BIT(1) + +extern unsigned long vmware_hypercall_slow(unsigned long cmd, + unsigned long in1, unsigned long in3, + unsigned long in4, unsigned long in5, + u32 *out1, u32 *out2, u32 *out3, + u32 *out4, u32 *out5); + +#define VMWARE_TDX_VENDOR_LEAF 0x1af7e4909ULL +#define VMWARE_TDX_HCALL_FUNC 1 + +extern unsigned long vmware_tdx_hypercall(unsigned long cmd, + unsigned long in1, unsigned long in3, + unsigned long in4, unsigned long in5, + u32 *out1, u32 *out2, u32 *out3, + u32 *out4, u32 *out5); /* - * The high bandwidth out call. The low word of edx is presumed to have the - * HB and OUT bits set. + * The low bandwidth call. The low word of %edx is presumed to have OUT bit + * set. The high word of %edx may contain input data from the caller. */ -#define VMWARE_HYPERCALL_HB_OUT \ - ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT_HB) ", %%dx; " \ - "rep outsb", \ - "vmcall", X86_FEATURE_VMCALL, \ +#define VMWARE_HYPERCALL \ + ALTERNATIVE_2("movw %[port], %%dx\n\t" \ + "inl (%%dx), %%eax", \ + "vmcall", X86_FEATURE_VMCALL, \ "vmmcall", X86_FEATURE_VMW_VMMCALL) -/* - * The high bandwidth in call. The low word of edx is presumed to have the - * HB bit set. - */ -#define VMWARE_HYPERCALL_HB_IN \ - ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT_HB) ", %%dx; " \ - "rep insb", \ - "vmcall", X86_FEATURE_VMCALL, \ - "vmmcall", X86_FEATURE_VMW_VMMCALL) +static inline +unsigned long vmware_hypercall1(unsigned long cmd, unsigned long in1) +{ + unsigned long out0; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return vmware_tdx_hypercall(cmd, in1, 0, 0, 0, + NULL, NULL, NULL, NULL, NULL); + + if (unlikely(!alternatives_patched) && !__is_defined(MODULE)) + return vmware_hypercall_slow(cmd, in1, 0, 0, 0, + NULL, NULL, NULL, NULL, NULL); + + asm_inline volatile (VMWARE_HYPERCALL + : "=a" (out0) + : [port] "i" (VMWARE_HYPERVISOR_PORT), + "a" (VMWARE_HYPERVISOR_MAGIC), + "b" (in1), + "c" (cmd), + "d" (0) + : "cc", "memory"); + return out0; +} + +static inline +unsigned long vmware_hypercall3(unsigned long cmd, unsigned long in1, + u32 *out1, u32 *out2) +{ + unsigned long out0; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return vmware_tdx_hypercall(cmd, in1, 0, 0, 0, + out1, out2, NULL, NULL, NULL); + + if (unlikely(!alternatives_patched) && !__is_defined(MODULE)) + return vmware_hypercall_slow(cmd, in1, 0, 0, 0, + out1, out2, NULL, NULL, NULL); + + asm_inline volatile (VMWARE_HYPERCALL + : "=a" (out0), "=b" (*out1), "=c" (*out2) + : [port] "i" (VMWARE_HYPERVISOR_PORT), + "a" (VMWARE_HYPERVISOR_MAGIC), + "b" (in1), + "c" (cmd), + "d" (0) + : "cc", "memory"); + return out0; +} + +static inline +unsigned long vmware_hypercall4(unsigned long cmd, unsigned long in1, + u32 *out1, u32 *out2, u32 *out3) +{ + unsigned long out0; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return vmware_tdx_hypercall(cmd, in1, 0, 0, 0, + out1, out2, out3, NULL, NULL); + + if (unlikely(!alternatives_patched) && !__is_defined(MODULE)) + return vmware_hypercall_slow(cmd, in1, 0, 0, 0, + out1, out2, out3, NULL, NULL); + + asm_inline volatile (VMWARE_HYPERCALL + : "=a" (out0), "=b" (*out1), "=c" (*out2), "=d" (*out3) + : [port] "i" (VMWARE_HYPERVISOR_PORT), + "a" (VMWARE_HYPERVISOR_MAGIC), + "b" (in1), + "c" (cmd), + "d" (0) + : "cc", "memory"); + return out0; +} + +static inline +unsigned long vmware_hypercall5(unsigned long cmd, unsigned long in1, + unsigned long in3, unsigned long in4, + unsigned long in5, u32 *out2) +{ + unsigned long out0; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return vmware_tdx_hypercall(cmd, in1, in3, in4, in5, + NULL, out2, NULL, NULL, NULL); + + if (unlikely(!alternatives_patched) && !__is_defined(MODULE)) + return vmware_hypercall_slow(cmd, in1, in3, in4, in5, + NULL, out2, NULL, NULL, NULL); + + asm_inline volatile (VMWARE_HYPERCALL + : "=a" (out0), "=c" (*out2) + : [port] "i" (VMWARE_HYPERVISOR_PORT), + "a" (VMWARE_HYPERVISOR_MAGIC), + "b" (in1), + "c" (cmd), + "d" (in3), + "S" (in4), + "D" (in5) + : "cc", "memory"); + return out0; +} + +static inline +unsigned long vmware_hypercall6(unsigned long cmd, unsigned long in1, + unsigned long in3, u32 *out2, + u32 *out3, u32 *out4, u32 *out5) +{ + unsigned long out0; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return vmware_tdx_hypercall(cmd, in1, in3, 0, 0, + NULL, out2, out3, out4, out5); + + if (unlikely(!alternatives_patched) && !__is_defined(MODULE)) + return vmware_hypercall_slow(cmd, in1, in3, 0, 0, + NULL, out2, out3, out4, out5); + + asm_inline volatile (VMWARE_HYPERCALL + : "=a" (out0), "=c" (*out2), "=d" (*out3), "=S" (*out4), + "=D" (*out5) + : [port] "i" (VMWARE_HYPERVISOR_PORT), + "a" (VMWARE_HYPERVISOR_MAGIC), + "b" (in1), + "c" (cmd), + "d" (in3) + : "cc", "memory"); + return out0; +} + +static inline +unsigned long vmware_hypercall7(unsigned long cmd, unsigned long in1, + unsigned long in3, unsigned long in4, + unsigned long in5, u32 *out1, + u32 *out2, u32 *out3) +{ + unsigned long out0; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return vmware_tdx_hypercall(cmd, in1, in3, in4, in5, + out1, out2, out3, NULL, NULL); + + if (unlikely(!alternatives_patched) && !__is_defined(MODULE)) + return vmware_hypercall_slow(cmd, in1, in3, in4, in5, + out1, out2, out3, NULL, NULL); + + asm_inline volatile (VMWARE_HYPERCALL + : "=a" (out0), "=b" (*out1), "=c" (*out2), "=d" (*out3) + : [port] "i" (VMWARE_HYPERVISOR_PORT), + "a" (VMWARE_HYPERVISOR_MAGIC), + "b" (in1), + "c" (cmd), + "d" (in3), + "S" (in4), + "D" (in5) + : "cc", "memory"); + return out0; +} + +#ifdef CONFIG_X86_64 +#define VMW_BP_CONSTRAINT "r" +#else +#define VMW_BP_CONSTRAINT "m" +#endif + +/* + * High bandwidth calls are not supported on encrypted memory guests. + * The caller should check cc_platform_has(CC_ATTR_MEM_ENCRYPT) and use + * low bandwidth hypercall if memory encryption is set. + * This assumption simplifies HB hypercall implementation to just I/O port + * based approach without alternative patching. + */ +static inline +unsigned long vmware_hypercall_hb_out(unsigned long cmd, unsigned long in2, + unsigned long in3, unsigned long in4, + unsigned long in5, unsigned long in6, + u32 *out1) +{ + unsigned long out0; + + asm_inline volatile ( + UNWIND_HINT_SAVE + "push %%" _ASM_BP "\n\t" + UNWIND_HINT_UNDEFINED + "mov %[in6], %%" _ASM_BP "\n\t" + "rep outsb\n\t" + "pop %%" _ASM_BP "\n\t" + UNWIND_HINT_RESTORE + : "=a" (out0), "=b" (*out1) + : "a" (VMWARE_HYPERVISOR_MAGIC), + "b" (cmd), + "c" (in2), + "d" (in3 | VMWARE_HYPERVISOR_PORT_HB), + "S" (in4), + "D" (in5), + [in6] VMW_BP_CONSTRAINT (in6) + : "cc", "memory"); + return out0; +} + +static inline +unsigned long vmware_hypercall_hb_in(unsigned long cmd, unsigned long in2, + unsigned long in3, unsigned long in4, + unsigned long in5, unsigned long in6, + u32 *out1) +{ + unsigned long out0; + + asm_inline volatile ( + UNWIND_HINT_SAVE + "push %%" _ASM_BP "\n\t" + UNWIND_HINT_UNDEFINED + "mov %[in6], %%" _ASM_BP "\n\t" + "rep insb\n\t" + "pop %%" _ASM_BP "\n\t" + UNWIND_HINT_RESTORE + : "=a" (out0), "=b" (*out1) + : "a" (VMWARE_HYPERVISOR_MAGIC), + "b" (cmd), + "c" (in2), + "d" (in3 | VMWARE_HYPERVISOR_PORT_HB), + "S" (in4), + "D" (in5), + [in6] VMW_BP_CONSTRAINT (in6) + : "cc", "memory"); + return out0; +} +#undef VMW_BP_CONSTRAINT +#undef VMWARE_HYPERCALL + #endif diff --git a/arch/x86/include/asm/vmxfeatures.h b/arch/x86/include/asm/vmxfeatures.h index 695f36664889..09b1d7e607c1 100644 --- a/arch/x86/include/asm/vmxfeatures.h +++ b/arch/x86/include/asm/vmxfeatures.h @@ -9,85 +9,85 @@ /* * Note: If the comment begins with a quoted string, that string is used - * in /proc/cpuinfo instead of the macro name. If the string is "", - * this feature bit is not displayed in /proc/cpuinfo at all. + * in /proc/cpuinfo instead of the macro name. Otherwise, this feature bit + * is not displayed in /proc/cpuinfo at all. */ /* Pin-Based VM-Execution Controls, EPT/VPID, APIC and VM-Functions, word 0 */ -#define VMX_FEATURE_INTR_EXITING ( 0*32+ 0) /* "" VM-Exit on vectored interrupts */ -#define VMX_FEATURE_NMI_EXITING ( 0*32+ 3) /* "" VM-Exit on NMIs */ +#define VMX_FEATURE_INTR_EXITING ( 0*32+ 0) /* VM-Exit on vectored interrupts */ +#define VMX_FEATURE_NMI_EXITING ( 0*32+ 3) /* VM-Exit on NMIs */ #define VMX_FEATURE_VIRTUAL_NMIS ( 0*32+ 5) /* "vnmi" NMI virtualization */ -#define VMX_FEATURE_PREEMPTION_TIMER ( 0*32+ 6) /* VMX Preemption Timer */ -#define VMX_FEATURE_POSTED_INTR ( 0*32+ 7) /* Posted Interrupts */ +#define VMX_FEATURE_PREEMPTION_TIMER ( 0*32+ 6) /* "preemption_timer" VMX Preemption Timer */ +#define VMX_FEATURE_POSTED_INTR ( 0*32+ 7) /* "posted_intr" Posted Interrupts */ /* EPT/VPID features, scattered to bits 16-23 */ -#define VMX_FEATURE_INVVPID ( 0*32+ 16) /* INVVPID is supported */ +#define VMX_FEATURE_INVVPID ( 0*32+ 16) /* "invvpid" INVVPID is supported */ #define VMX_FEATURE_EPT_EXECUTE_ONLY ( 0*32+ 17) /* "ept_x_only" EPT entries can be execute only */ -#define VMX_FEATURE_EPT_AD ( 0*32+ 18) /* EPT Accessed/Dirty bits */ -#define VMX_FEATURE_EPT_1GB ( 0*32+ 19) /* 1GB EPT pages */ -#define VMX_FEATURE_EPT_5LEVEL ( 0*32+ 20) /* 5-level EPT paging */ +#define VMX_FEATURE_EPT_AD ( 0*32+ 18) /* "ept_ad" EPT Accessed/Dirty bits */ +#define VMX_FEATURE_EPT_1GB ( 0*32+ 19) /* "ept_1gb" 1GB EPT pages */ +#define VMX_FEATURE_EPT_5LEVEL ( 0*32+ 20) /* "ept_5level" 5-level EPT paging */ /* Aggregated APIC features 24-27 */ -#define VMX_FEATURE_FLEXPRIORITY ( 0*32+ 24) /* TPR shadow + virt APIC */ -#define VMX_FEATURE_APICV ( 0*32+ 25) /* TPR shadow + APIC reg virt + virt intr delivery + posted interrupts */ +#define VMX_FEATURE_FLEXPRIORITY ( 0*32+ 24) /* "flexpriority" TPR shadow + virt APIC */ +#define VMX_FEATURE_APICV ( 0*32+ 25) /* "apicv" TPR shadow + APIC reg virt + virt intr delivery + posted interrupts */ /* VM-Functions, shifted to bits 28-31 */ -#define VMX_FEATURE_EPTP_SWITCHING ( 0*32+ 28) /* EPTP switching (in guest) */ +#define VMX_FEATURE_EPTP_SWITCHING ( 0*32+ 28) /* "eptp_switching" EPTP switching (in guest) */ /* Primary Processor-Based VM-Execution Controls, word 1 */ -#define VMX_FEATURE_INTR_WINDOW_EXITING ( 1*32+ 2) /* "" VM-Exit if INTRs are unblocked in guest */ +#define VMX_FEATURE_INTR_WINDOW_EXITING ( 1*32+ 2) /* VM-Exit if INTRs are unblocked in guest */ #define VMX_FEATURE_USE_TSC_OFFSETTING ( 1*32+ 3) /* "tsc_offset" Offset hardware TSC when read in guest */ -#define VMX_FEATURE_HLT_EXITING ( 1*32+ 7) /* "" VM-Exit on HLT */ -#define VMX_FEATURE_INVLPG_EXITING ( 1*32+ 9) /* "" VM-Exit on INVLPG */ -#define VMX_FEATURE_MWAIT_EXITING ( 1*32+ 10) /* "" VM-Exit on MWAIT */ -#define VMX_FEATURE_RDPMC_EXITING ( 1*32+ 11) /* "" VM-Exit on RDPMC */ -#define VMX_FEATURE_RDTSC_EXITING ( 1*32+ 12) /* "" VM-Exit on RDTSC */ -#define VMX_FEATURE_CR3_LOAD_EXITING ( 1*32+ 15) /* "" VM-Exit on writes to CR3 */ -#define VMX_FEATURE_CR3_STORE_EXITING ( 1*32+ 16) /* "" VM-Exit on reads from CR3 */ -#define VMX_FEATURE_TERTIARY_CONTROLS ( 1*32+ 17) /* "" Enable Tertiary VM-Execution Controls */ -#define VMX_FEATURE_CR8_LOAD_EXITING ( 1*32+ 19) /* "" VM-Exit on writes to CR8 */ -#define VMX_FEATURE_CR8_STORE_EXITING ( 1*32+ 20) /* "" VM-Exit on reads from CR8 */ +#define VMX_FEATURE_HLT_EXITING ( 1*32+ 7) /* VM-Exit on HLT */ +#define VMX_FEATURE_INVLPG_EXITING ( 1*32+ 9) /* VM-Exit on INVLPG */ +#define VMX_FEATURE_MWAIT_EXITING ( 1*32+ 10) /* VM-Exit on MWAIT */ +#define VMX_FEATURE_RDPMC_EXITING ( 1*32+ 11) /* VM-Exit on RDPMC */ +#define VMX_FEATURE_RDTSC_EXITING ( 1*32+ 12) /* VM-Exit on RDTSC */ +#define VMX_FEATURE_CR3_LOAD_EXITING ( 1*32+ 15) /* VM-Exit on writes to CR3 */ +#define VMX_FEATURE_CR3_STORE_EXITING ( 1*32+ 16) /* VM-Exit on reads from CR3 */ +#define VMX_FEATURE_TERTIARY_CONTROLS ( 1*32+ 17) /* Enable Tertiary VM-Execution Controls */ +#define VMX_FEATURE_CR8_LOAD_EXITING ( 1*32+ 19) /* VM-Exit on writes to CR8 */ +#define VMX_FEATURE_CR8_STORE_EXITING ( 1*32+ 20) /* VM-Exit on reads from CR8 */ #define VMX_FEATURE_VIRTUAL_TPR ( 1*32+ 21) /* "vtpr" TPR virtualization, a.k.a. TPR shadow */ -#define VMX_FEATURE_NMI_WINDOW_EXITING ( 1*32+ 22) /* "" VM-Exit if NMIs are unblocked in guest */ -#define VMX_FEATURE_MOV_DR_EXITING ( 1*32+ 23) /* "" VM-Exit on accesses to debug registers */ -#define VMX_FEATURE_UNCOND_IO_EXITING ( 1*32+ 24) /* "" VM-Exit on *all* IN{S} and OUT{S}*/ -#define VMX_FEATURE_USE_IO_BITMAPS ( 1*32+ 25) /* "" VM-Exit based on I/O port */ +#define VMX_FEATURE_NMI_WINDOW_EXITING ( 1*32+ 22) /* VM-Exit if NMIs are unblocked in guest */ +#define VMX_FEATURE_MOV_DR_EXITING ( 1*32+ 23) /* VM-Exit on accesses to debug registers */ +#define VMX_FEATURE_UNCOND_IO_EXITING ( 1*32+ 24) /* VM-Exit on *all* IN{S} and OUT{S}*/ +#define VMX_FEATURE_USE_IO_BITMAPS ( 1*32+ 25) /* VM-Exit based on I/O port */ #define VMX_FEATURE_MONITOR_TRAP_FLAG ( 1*32+ 27) /* "mtf" VMX single-step VM-Exits */ -#define VMX_FEATURE_USE_MSR_BITMAPS ( 1*32+ 28) /* "" VM-Exit based on MSR index */ -#define VMX_FEATURE_MONITOR_EXITING ( 1*32+ 29) /* "" VM-Exit on MONITOR (MWAIT's accomplice) */ -#define VMX_FEATURE_PAUSE_EXITING ( 1*32+ 30) /* "" VM-Exit on PAUSE (unconditionally) */ -#define VMX_FEATURE_SEC_CONTROLS ( 1*32+ 31) /* "" Enable Secondary VM-Execution Controls */ +#define VMX_FEATURE_USE_MSR_BITMAPS ( 1*32+ 28) /* VM-Exit based on MSR index */ +#define VMX_FEATURE_MONITOR_EXITING ( 1*32+ 29) /* VM-Exit on MONITOR (MWAIT's accomplice) */ +#define VMX_FEATURE_PAUSE_EXITING ( 1*32+ 30) /* VM-Exit on PAUSE (unconditionally) */ +#define VMX_FEATURE_SEC_CONTROLS ( 1*32+ 31) /* Enable Secondary VM-Execution Controls */ /* Secondary Processor-Based VM-Execution Controls, word 2 */ #define VMX_FEATURE_VIRT_APIC_ACCESSES ( 2*32+ 0) /* "vapic" Virtualize memory mapped APIC accesses */ -#define VMX_FEATURE_EPT ( 2*32+ 1) /* Extended Page Tables, a.k.a. Two-Dimensional Paging */ -#define VMX_FEATURE_DESC_EXITING ( 2*32+ 2) /* "" VM-Exit on {S,L}*DT instructions */ -#define VMX_FEATURE_RDTSCP ( 2*32+ 3) /* "" Enable RDTSCP in guest */ -#define VMX_FEATURE_VIRTUAL_X2APIC ( 2*32+ 4) /* "" Virtualize X2APIC for the guest */ -#define VMX_FEATURE_VPID ( 2*32+ 5) /* Virtual Processor ID (TLB ASID modifier) */ -#define VMX_FEATURE_WBINVD_EXITING ( 2*32+ 6) /* "" VM-Exit on WBINVD */ -#define VMX_FEATURE_UNRESTRICTED_GUEST ( 2*32+ 7) /* Allow Big Real Mode and other "invalid" states */ +#define VMX_FEATURE_EPT ( 2*32+ 1) /* "ept" Extended Page Tables, a.k.a. Two-Dimensional Paging */ +#define VMX_FEATURE_DESC_EXITING ( 2*32+ 2) /* VM-Exit on {S,L}*DT instructions */ +#define VMX_FEATURE_RDTSCP ( 2*32+ 3) /* Enable RDTSCP in guest */ +#define VMX_FEATURE_VIRTUAL_X2APIC ( 2*32+ 4) /* Virtualize X2APIC for the guest */ +#define VMX_FEATURE_VPID ( 2*32+ 5) /* "vpid" Virtual Processor ID (TLB ASID modifier) */ +#define VMX_FEATURE_WBINVD_EXITING ( 2*32+ 6) /* VM-Exit on WBINVD */ +#define VMX_FEATURE_UNRESTRICTED_GUEST ( 2*32+ 7) /* "unrestricted_guest" Allow Big Real Mode and other "invalid" states */ #define VMX_FEATURE_APIC_REGISTER_VIRT ( 2*32+ 8) /* "vapic_reg" Hardware emulation of reads to the virtual-APIC */ #define VMX_FEATURE_VIRT_INTR_DELIVERY ( 2*32+ 9) /* "vid" Evaluation and delivery of pending virtual interrupts */ #define VMX_FEATURE_PAUSE_LOOP_EXITING ( 2*32+ 10) /* "ple" Conditionally VM-Exit on PAUSE at CPL0 */ -#define VMX_FEATURE_RDRAND_EXITING ( 2*32+ 11) /* "" VM-Exit on RDRAND*/ -#define VMX_FEATURE_INVPCID ( 2*32+ 12) /* "" Enable INVPCID in guest */ -#define VMX_FEATURE_VMFUNC ( 2*32+ 13) /* "" Enable VM-Functions (leaf dependent) */ -#define VMX_FEATURE_SHADOW_VMCS ( 2*32+ 14) /* VMREAD/VMWRITE in guest can access shadow VMCS */ -#define VMX_FEATURE_ENCLS_EXITING ( 2*32+ 15) /* "" VM-Exit on ENCLS (leaf dependent) */ -#define VMX_FEATURE_RDSEED_EXITING ( 2*32+ 16) /* "" VM-Exit on RDSEED */ +#define VMX_FEATURE_RDRAND_EXITING ( 2*32+ 11) /* VM-Exit on RDRAND*/ +#define VMX_FEATURE_INVPCID ( 2*32+ 12) /* Enable INVPCID in guest */ +#define VMX_FEATURE_VMFUNC ( 2*32+ 13) /* Enable VM-Functions (leaf dependent) */ +#define VMX_FEATURE_SHADOW_VMCS ( 2*32+ 14) /* "shadow_vmcs" VMREAD/VMWRITE in guest can access shadow VMCS */ +#define VMX_FEATURE_ENCLS_EXITING ( 2*32+ 15) /* VM-Exit on ENCLS (leaf dependent) */ +#define VMX_FEATURE_RDSEED_EXITING ( 2*32+ 16) /* VM-Exit on RDSEED */ #define VMX_FEATURE_PAGE_MOD_LOGGING ( 2*32+ 17) /* "pml" Log dirty pages into buffer */ -#define VMX_FEATURE_EPT_VIOLATION_VE ( 2*32+ 18) /* Conditionally reflect EPT violations as #VE exceptions */ -#define VMX_FEATURE_PT_CONCEAL_VMX ( 2*32+ 19) /* "" Suppress VMX indicators in Processor Trace */ -#define VMX_FEATURE_XSAVES ( 2*32+ 20) /* "" Enable XSAVES and XRSTORS in guest */ +#define VMX_FEATURE_EPT_VIOLATION_VE ( 2*32+ 18) /* "ept_violation_ve" Conditionally reflect EPT violations as #VE exceptions */ +#define VMX_FEATURE_PT_CONCEAL_VMX ( 2*32+ 19) /* Suppress VMX indicators in Processor Trace */ +#define VMX_FEATURE_XSAVES ( 2*32+ 20) /* Enable XSAVES and XRSTORS in guest */ #define VMX_FEATURE_MODE_BASED_EPT_EXEC ( 2*32+ 22) /* "ept_mode_based_exec" Enable separate EPT EXEC bits for supervisor vs. user */ -#define VMX_FEATURE_PT_USE_GPA ( 2*32+ 24) /* "" Processor Trace logs GPAs */ -#define VMX_FEATURE_TSC_SCALING ( 2*32+ 25) /* Scale hardware TSC when read in guest */ -#define VMX_FEATURE_USR_WAIT_PAUSE ( 2*32+ 26) /* Enable TPAUSE, UMONITOR, UMWAIT in guest */ -#define VMX_FEATURE_ENCLV_EXITING ( 2*32+ 28) /* "" VM-Exit on ENCLV (leaf dependent) */ -#define VMX_FEATURE_BUS_LOCK_DETECTION ( 2*32+ 30) /* "" VM-Exit when bus lock caused */ -#define VMX_FEATURE_NOTIFY_VM_EXITING ( 2*32+ 31) /* VM-Exit when no event windows after notify window */ +#define VMX_FEATURE_PT_USE_GPA ( 2*32+ 24) /* Processor Trace logs GPAs */ +#define VMX_FEATURE_TSC_SCALING ( 2*32+ 25) /* "tsc_scaling" Scale hardware TSC when read in guest */ +#define VMX_FEATURE_USR_WAIT_PAUSE ( 2*32+ 26) /* "usr_wait_pause" Enable TPAUSE, UMONITOR, UMWAIT in guest */ +#define VMX_FEATURE_ENCLV_EXITING ( 2*32+ 28) /* VM-Exit on ENCLV (leaf dependent) */ +#define VMX_FEATURE_BUS_LOCK_DETECTION ( 2*32+ 30) /* VM-Exit when bus lock caused */ +#define VMX_FEATURE_NOTIFY_VM_EXITING ( 2*32+ 31) /* "notify_vm_exiting" VM-Exit when no event windows after notify window */ /* Tertiary Processor-Based VM-Execution Controls, word 3 */ -#define VMX_FEATURE_IPI_VIRT ( 3*32+ 4) /* Enable IPI virtualization */ +#define VMX_FEATURE_IPI_VIRT ( 3*32+ 4) /* "ipi_virt" Enable IPI virtualization */ #endif /* _ASM_X86_VMXFEATURES_H */ diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 6149eabe200f..213cf5379a5a 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -149,12 +149,22 @@ struct x86_init_acpi { * @enc_status_change_finish Notify HV after the encryption status of a range is changed * @enc_tlb_flush_required Returns true if a TLB flush is needed before changing page encryption status * @enc_cache_flush_required Returns true if a cache flush is needed before changing page encryption status + * @enc_kexec_begin Begin the two-step process of converting shared memory back + * to private. It stops the new conversions from being started + * and waits in-flight conversions to finish, if possible. + * @enc_kexec_finish Finish the two-step process of converting shared memory to + * private. All memory is private after the call when + * the function returns. + * It is called on only one CPU while the others are shut down + * and with interrupts disabled. */ struct x86_guest { - bool (*enc_status_change_prepare)(unsigned long vaddr, int npages, bool enc); - bool (*enc_status_change_finish)(unsigned long vaddr, int npages, bool enc); + int (*enc_status_change_prepare)(unsigned long vaddr, int npages, bool enc); + int (*enc_status_change_finish)(unsigned long vaddr, int npages, bool enc); bool (*enc_tlb_flush_required)(bool enc); bool (*enc_cache_flush_required)(void); + void (*enc_kexec_begin)(void); + void (*enc_kexec_finish)(void); }; /** diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index 80e1df482337..1814b413fd57 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -115,6 +115,7 @@ #define SVM_VMGEXIT_AP_CREATE_ON_INIT 0 #define SVM_VMGEXIT_AP_CREATE 1 #define SVM_VMGEXIT_AP_DESTROY 2 +#define SVM_VMGEXIT_SNP_RUN_VMPL 0x80000018 #define SVM_VMGEXIT_HV_FEATURES 0x8000fffd #define SVM_VMGEXIT_TERM_REQUEST 0x8000fffe #define SVM_VMGEXIT_TERM_REASON(reason_set, reason_code) \ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 20a0dd51700a..a847180836e4 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -17,7 +17,6 @@ CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg CFLAGS_REMOVE_head64.o = -pg CFLAGS_REMOVE_head32.o = -pg -CFLAGS_REMOVE_sev.o = -pg CFLAGS_REMOVE_rethook.o = -pg endif @@ -26,19 +25,16 @@ KASAN_SANITIZE_dumpstack.o := n KASAN_SANITIZE_dumpstack_$(BITS).o := n KASAN_SANITIZE_stacktrace.o := n KASAN_SANITIZE_paravirt.o := n -KASAN_SANITIZE_sev.o := n # With some compiler versions the generated code results in boot hangs, caused # by several compilation units. To be safe, disable all instrumentation. KCSAN_SANITIZE := n KMSAN_SANITIZE_head$(BITS).o := n KMSAN_SANITIZE_nmi.o := n -KMSAN_SANITIZE_sev.o := n # If instrumentation of the following files is enabled, boot hangs during # first second. KCOV_INSTRUMENT_head$(BITS).o := n -KCOV_INSTRUMENT_sev.o := n CFLAGS_irq.o := -I $(src)/../include/asm/trace @@ -142,8 +138,6 @@ obj-$(CONFIG_UNWINDER_ORC) += unwind_orc.o obj-$(CONFIG_UNWINDER_FRAME_POINTER) += unwind_frame.o obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o -obj-$(CONFIG_AMD_MEM_ENCRYPT) += sev.o - obj-$(CONFIG_CFI_CLANG) += cfi.o obj-$(CONFIG_CALL_THUNKS) += callthunks.o diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile index fc17b3f136fe..842a5f449404 100644 --- a/arch/x86/kernel/acpi/Makefile +++ b/arch/x86/kernel/acpi/Makefile @@ -4,6 +4,7 @@ obj-$(CONFIG_ACPI) += boot.o obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup_$(BITS).o obj-$(CONFIG_ACPI_APEI) += apei.o obj-$(CONFIG_ACPI_CPPC_LIB) += cppc.o +obj-$(CONFIG_ACPI_MADT_WAKEUP) += madt_wakeup.o madt_playdead.o ifneq ($(CONFIG_ACPI_PROCESSOR),) obj-y += cstate.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 4bf82dbd2a6b..9f4618dcd704 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -67,13 +67,6 @@ static bool has_lapic_cpus __initdata; static bool acpi_support_online_capable; #endif -#ifdef CONFIG_X86_64 -/* Physical address of the Multiprocessor Wakeup Structure mailbox */ -static u64 acpi_mp_wake_mailbox_paddr; -/* Virtual address of the Multiprocessor Wakeup Structure mailbox */ -static struct acpi_madt_multiproc_wakeup_mailbox *acpi_mp_wake_mailbox; -#endif - #ifdef CONFIG_X86_IO_APIC /* * Locks related to IOAPIC hotplug @@ -341,60 +334,6 @@ acpi_parse_lapic_nmi(union acpi_subtable_headers * header, const unsigned long e return 0; } - -#ifdef CONFIG_X86_64 -static int acpi_wakeup_cpu(u32 apicid, unsigned long start_ip) -{ - /* - * Remap mailbox memory only for the first call to acpi_wakeup_cpu(). - * - * Wakeup of secondary CPUs is fully serialized in the core code. - * No need to protect acpi_mp_wake_mailbox from concurrent accesses. - */ - if (!acpi_mp_wake_mailbox) { - acpi_mp_wake_mailbox = memremap(acpi_mp_wake_mailbox_paddr, - sizeof(*acpi_mp_wake_mailbox), - MEMREMAP_WB); - } - - /* - * Mailbox memory is shared between the firmware and OS. Firmware will - * listen on mailbox command address, and once it receives the wakeup - * command, the CPU associated with the given apicid will be booted. - * - * The value of 'apic_id' and 'wakeup_vector' must be visible to the - * firmware before the wakeup command is visible. smp_store_release() - * ensures ordering and visibility. - */ - acpi_mp_wake_mailbox->apic_id = apicid; - acpi_mp_wake_mailbox->wakeup_vector = start_ip; - smp_store_release(&acpi_mp_wake_mailbox->command, - ACPI_MP_WAKE_COMMAND_WAKEUP); - - /* - * Wait for the CPU to wake up. - * - * The CPU being woken up is essentially in a spin loop waiting to be - * woken up. It should not take long for it wake up and acknowledge by - * zeroing out ->command. - * - * ACPI specification doesn't provide any guidance on how long kernel - * has to wait for a wake up acknowledgement. It also doesn't provide - * a way to cancel a wake up request if it takes too long. - * - * In TDX environment, the VMM has control over how long it takes to - * wake up secondary. It can postpone scheduling secondary vCPU - * indefinitely. Giving up on wake up request and reporting error opens - * possible attack vector for VMM: it can wake up a secondary CPU when - * kernel doesn't expect it. Wait until positive result of the wake up - * request. - */ - while (READ_ONCE(acpi_mp_wake_mailbox->command)) - cpu_relax(); - - return 0; -} -#endif /* CONFIG_X86_64 */ #endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_IO_APIC @@ -1124,29 +1063,6 @@ static int __init acpi_parse_madt_lapic_entries(void) } return 0; } - -#ifdef CONFIG_X86_64 -static int __init acpi_parse_mp_wake(union acpi_subtable_headers *header, - const unsigned long end) -{ - struct acpi_madt_multiproc_wakeup *mp_wake; - - if (!IS_ENABLED(CONFIG_SMP)) - return -ENODEV; - - mp_wake = (struct acpi_madt_multiproc_wakeup *)header; - if (BAD_MADT_ENTRY(mp_wake, end)) - return -EINVAL; - - acpi_table_print_madt_entry(&header->common); - - acpi_mp_wake_mailbox_paddr = mp_wake->base_address; - - apic_update_callback(wakeup_secondary_cpu_64, acpi_wakeup_cpu); - - return 0; -} -#endif /* CONFIG_X86_64 */ #endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_IO_APIC @@ -1343,7 +1259,7 @@ static void __init acpi_process_madt(void) smp_found_config = 1; } -#ifdef CONFIG_X86_64 +#ifdef CONFIG_ACPI_MADT_WAKEUP /* * Parse MADT MP Wake entry. */ diff --git a/arch/x86/kernel/acpi/madt_playdead.S b/arch/x86/kernel/acpi/madt_playdead.S new file mode 100644 index 000000000000..4e498d28cdc8 --- /dev/null +++ b/arch/x86/kernel/acpi/madt_playdead.S @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include +#include +#include +#include + + .text + .align PAGE_SIZE + +/* + * asm_acpi_mp_play_dead() - Hand over control of the CPU to the BIOS + * + * rdi: Address of the ACPI MADT MPWK ResetVector + * rsi: PGD of the identity mapping + */ +SYM_FUNC_START(asm_acpi_mp_play_dead) + /* Turn off global entries. Following CR3 write will flush them. */ + movq %cr4, %rdx + andq $~(X86_CR4_PGE), %rdx + movq %rdx, %cr4 + + /* Switch to identity mapping */ + movq %rsi, %cr3 + + /* Jump to reset vector */ + ANNOTATE_RETPOLINE_SAFE + jmp *%rdi +SYM_FUNC_END(asm_acpi_mp_play_dead) diff --git a/arch/x86/kernel/acpi/madt_wakeup.c b/arch/x86/kernel/acpi/madt_wakeup.c new file mode 100644 index 000000000000..6cfe762be28b --- /dev/null +++ b/arch/x86/kernel/acpi/madt_wakeup.c @@ -0,0 +1,292 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* Physical address of the Multiprocessor Wakeup Structure mailbox */ +static u64 acpi_mp_wake_mailbox_paddr __ro_after_init; + +/* Virtual address of the Multiprocessor Wakeup Structure mailbox */ +static struct acpi_madt_multiproc_wakeup_mailbox *acpi_mp_wake_mailbox __ro_after_init; + +static u64 acpi_mp_pgd __ro_after_init; +static u64 acpi_mp_reset_vector_paddr __ro_after_init; + +static void acpi_mp_stop_this_cpu(void) +{ + asm_acpi_mp_play_dead(acpi_mp_reset_vector_paddr, acpi_mp_pgd); +} + +static void acpi_mp_play_dead(void) +{ + play_dead_common(); + asm_acpi_mp_play_dead(acpi_mp_reset_vector_paddr, acpi_mp_pgd); +} + +static void acpi_mp_cpu_die(unsigned int cpu) +{ + u32 apicid = per_cpu(x86_cpu_to_apicid, cpu); + unsigned long timeout; + + /* + * Use TEST mailbox command to prove that BIOS got control over + * the CPU before declaring it dead. + * + * BIOS has to clear 'command' field of the mailbox. + */ + acpi_mp_wake_mailbox->apic_id = apicid; + smp_store_release(&acpi_mp_wake_mailbox->command, + ACPI_MP_WAKE_COMMAND_TEST); + + /* Don't wait longer than a second. */ + timeout = USEC_PER_SEC; + while (READ_ONCE(acpi_mp_wake_mailbox->command) && --timeout) + udelay(1); + + if (!timeout) + pr_err("Failed to hand over CPU %d to BIOS\n", cpu); +} + +/* The argument is required to match type of x86_mapping_info::alloc_pgt_page */ +static void __init *alloc_pgt_page(void *dummy) +{ + return memblock_alloc(PAGE_SIZE, PAGE_SIZE); +} + +static void __init free_pgt_page(void *pgt, void *dummy) +{ + return memblock_free(pgt, PAGE_SIZE); +} + +/* + * Make sure asm_acpi_mp_play_dead() is present in the identity mapping at + * the same place as in the kernel page tables. asm_acpi_mp_play_dead() switches + * to the identity mapping and the function has be present at the same spot in + * the virtual address space before and after switching page tables. + */ +static int __init init_transition_pgtable(pgd_t *pgd) +{ + pgprot_t prot = PAGE_KERNEL_EXEC_NOENC; + unsigned long vaddr, paddr; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + vaddr = (unsigned long)asm_acpi_mp_play_dead; + pgd += pgd_index(vaddr); + if (!pgd_present(*pgd)) { + p4d = (p4d_t *)alloc_pgt_page(NULL); + if (!p4d) + return -ENOMEM; + set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE)); + } + p4d = p4d_offset(pgd, vaddr); + if (!p4d_present(*p4d)) { + pud = (pud_t *)alloc_pgt_page(NULL); + if (!pud) + return -ENOMEM; + set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE)); + } + pud = pud_offset(p4d, vaddr); + if (!pud_present(*pud)) { + pmd = (pmd_t *)alloc_pgt_page(NULL); + if (!pmd) + return -ENOMEM; + set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE)); + } + pmd = pmd_offset(pud, vaddr); + if (!pmd_present(*pmd)) { + pte = (pte_t *)alloc_pgt_page(NULL); + if (!pte) + return -ENOMEM; + set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE)); + } + pte = pte_offset_kernel(pmd, vaddr); + + paddr = __pa(vaddr); + set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, prot)); + + return 0; +} + +static int __init acpi_mp_setup_reset(u64 reset_vector) +{ + struct x86_mapping_info info = { + .alloc_pgt_page = alloc_pgt_page, + .free_pgt_page = free_pgt_page, + .page_flag = __PAGE_KERNEL_LARGE_EXEC, + .kernpg_flag = _KERNPG_TABLE_NOENC, + }; + pgd_t *pgd; + + pgd = alloc_pgt_page(NULL); + if (!pgd) + return -ENOMEM; + + for (int i = 0; i < nr_pfn_mapped; i++) { + unsigned long mstart, mend; + + mstart = pfn_mapped[i].start << PAGE_SHIFT; + mend = pfn_mapped[i].end << PAGE_SHIFT; + if (kernel_ident_mapping_init(&info, pgd, mstart, mend)) { + kernel_ident_mapping_free(&info, pgd); + return -ENOMEM; + } + } + + if (kernel_ident_mapping_init(&info, pgd, + PAGE_ALIGN_DOWN(reset_vector), + PAGE_ALIGN(reset_vector + 1))) { + kernel_ident_mapping_free(&info, pgd); + return -ENOMEM; + } + + if (init_transition_pgtable(pgd)) { + kernel_ident_mapping_free(&info, pgd); + return -ENOMEM; + } + + smp_ops.play_dead = acpi_mp_play_dead; + smp_ops.stop_this_cpu = acpi_mp_stop_this_cpu; + smp_ops.cpu_die = acpi_mp_cpu_die; + + acpi_mp_reset_vector_paddr = reset_vector; + acpi_mp_pgd = __pa(pgd); + + return 0; +} + +static int acpi_wakeup_cpu(u32 apicid, unsigned long start_ip) +{ + if (!acpi_mp_wake_mailbox_paddr) { + pr_warn_once("No MADT mailbox: cannot bringup secondary CPUs. Booting with kexec?\n"); + return -EOPNOTSUPP; + } + + /* + * Remap mailbox memory only for the first call to acpi_wakeup_cpu(). + * + * Wakeup of secondary CPUs is fully serialized in the core code. + * No need to protect acpi_mp_wake_mailbox from concurrent accesses. + */ + if (!acpi_mp_wake_mailbox) { + acpi_mp_wake_mailbox = memremap(acpi_mp_wake_mailbox_paddr, + sizeof(*acpi_mp_wake_mailbox), + MEMREMAP_WB); + } + + /* + * Mailbox memory is shared between the firmware and OS. Firmware will + * listen on mailbox command address, and once it receives the wakeup + * command, the CPU associated with the given apicid will be booted. + * + * The value of 'apic_id' and 'wakeup_vector' must be visible to the + * firmware before the wakeup command is visible. smp_store_release() + * ensures ordering and visibility. + */ + acpi_mp_wake_mailbox->apic_id = apicid; + acpi_mp_wake_mailbox->wakeup_vector = start_ip; + smp_store_release(&acpi_mp_wake_mailbox->command, + ACPI_MP_WAKE_COMMAND_WAKEUP); + + /* + * Wait for the CPU to wake up. + * + * The CPU being woken up is essentially in a spin loop waiting to be + * woken up. It should not take long for it wake up and acknowledge by + * zeroing out ->command. + * + * ACPI specification doesn't provide any guidance on how long kernel + * has to wait for a wake up acknowledgment. It also doesn't provide + * a way to cancel a wake up request if it takes too long. + * + * In TDX environment, the VMM has control over how long it takes to + * wake up secondary. It can postpone scheduling secondary vCPU + * indefinitely. Giving up on wake up request and reporting error opens + * possible attack vector for VMM: it can wake up a secondary CPU when + * kernel doesn't expect it. Wait until positive result of the wake up + * request. + */ + while (READ_ONCE(acpi_mp_wake_mailbox->command)) + cpu_relax(); + + return 0; +} + +static void acpi_mp_disable_offlining(struct acpi_madt_multiproc_wakeup *mp_wake) +{ + cpu_hotplug_disable_offlining(); + + /* + * ACPI MADT doesn't allow to offline a CPU after it was onlined. This + * limits kexec: the second kernel won't be able to use more than one CPU. + * + * To prevent a kexec kernel from onlining secondary CPUs invalidate the + * mailbox address in the ACPI MADT wakeup structure which prevents a + * kexec kernel to use it. + * + * This is safe as the booting kernel has the mailbox address cached + * already and acpi_wakeup_cpu() uses the cached value to bring up the + * secondary CPUs. + * + * Note: This is a Linux specific convention and not covered by the + * ACPI specification. + */ + mp_wake->mailbox_address = 0; +} + +int __init acpi_parse_mp_wake(union acpi_subtable_headers *header, + const unsigned long end) +{ + struct acpi_madt_multiproc_wakeup *mp_wake; + + mp_wake = (struct acpi_madt_multiproc_wakeup *)header; + + /* + * Cannot use the standard BAD_MADT_ENTRY() to sanity check the @mp_wake + * entry. 'sizeof (struct acpi_madt_multiproc_wakeup)' can be larger + * than the actual size of the MP wakeup entry in ACPI table because the + * 'reset_vector' is only available in the V1 MP wakeup structure. + */ + if (!mp_wake) + return -EINVAL; + if (end - (unsigned long)mp_wake < ACPI_MADT_MP_WAKEUP_SIZE_V0) + return -EINVAL; + if (mp_wake->header.length < ACPI_MADT_MP_WAKEUP_SIZE_V0) + return -EINVAL; + + acpi_table_print_madt_entry(&header->common); + + acpi_mp_wake_mailbox_paddr = mp_wake->mailbox_address; + + if (mp_wake->version >= ACPI_MADT_MP_WAKEUP_VERSION_V1 && + mp_wake->header.length >= ACPI_MADT_MP_WAKEUP_SIZE_V1) { + if (acpi_mp_setup_reset(mp_wake->reset_vector)) { + pr_warn("Failed to setup MADT reset vector\n"); + acpi_mp_disable_offlining(mp_wake); + } + } else { + /* + * CPU offlining requires version 1 of the ACPI MADT wakeup + * structure. + */ + acpi_mp_disable_offlining(mp_wake); + } + + apic_update_callback(wakeup_secondary_cpu_64, acpi_wakeup_cpu); + + return 0; +} diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 89de61243272..333b16181357 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -432,6 +432,11 @@ static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a) return 5; } +static inline u8 * instr_va(struct alt_instr *i) +{ + return (u8 *)&i->instr_offset + i->instr_offset; +} + /* * Replace instructions with better alternatives for this CPU type. This runs * before SMP is initialized to avoid SMP problems with self modifying code. @@ -447,7 +452,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, { u8 insn_buff[MAX_PATCH_LEN]; u8 *instr, *replacement; - struct alt_instr *a; + struct alt_instr *a, *b; DPRINTK(ALT, "alt table %px, -> %px", start, end); @@ -473,7 +478,18 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, for (a = start; a < end; a++) { int insn_buff_sz = 0; - instr = (u8 *)&a->instr_offset + a->instr_offset; + /* + * In case of nested ALTERNATIVE()s the outer alternative might + * add more padding. To ensure consistent patching find the max + * padding for all alt_instr entries for this site (nested + * alternatives result in consecutive entries). + */ + for (b = a+1; b < end && instr_va(b) == instr_va(a); b++) { + u8 len = max(a->instrlen, b->instrlen); + a->instrlen = b->instrlen = len; + } + + instr = instr_va(a); replacement = (u8 *)&a->repl_offset + a->repl_offset; BUG_ON(a->instrlen > sizeof(insn_buff)); BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32); @@ -1641,7 +1657,7 @@ static noinline void __init alt_reloc_selftest(void) */ asm_inline volatile ( ALTERNATIVE("", "lea %[mem], %%" _ASM_ARG1 "; call __alt_reloc_selftest;", X86_FEATURE_ALWAYS) - : /* output */ + : ASM_CALL_CONSTRAINT : [mem] "m" (__alt_reloc_selftest_addr) : _ASM_ARG1 ); diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 027a8c7a2c9e..059e5c16af05 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -180,6 +180,43 @@ static struct pci_dev *next_northbridge(struct pci_dev *dev, return dev; } +/* + * SMN accesses may fail in ways that are difficult to detect here in the called + * functions amd_smn_read() and amd_smn_write(). Therefore, callers must do + * their own checking based on what behavior they expect. + * + * For SMN reads, the returned value may be zero if the register is Read-as-Zero. + * Or it may be a "PCI Error Response", e.g. all 0xFFs. The "PCI Error Response" + * can be checked here, and a proper error code can be returned. + * + * But the Read-as-Zero response cannot be verified here. A value of 0 may be + * correct in some cases, so callers must check that this correct is for the + * register/fields they need. + * + * For SMN writes, success can be determined through a "write and read back" + * However, this is not robust when done here. + * + * Possible issues: + * + * 1) Bits that are "Write-1-to-Clear". In this case, the read value should + * *not* match the write value. + * + * 2) Bits that are "Read-as-Zero"/"Writes-Ignored". This information cannot be + * known here. + * + * 3) Bits that are "Reserved / Set to 1". Ditto above. + * + * Callers of amd_smn_write() should do the "write and read back" check + * themselves, if needed. + * + * For #1, they can see if their target bits got cleared. + * + * For #2 and #3, they can check if their target bits got set as intended. + * + * This matches what is done for RDMSR/WRMSR. As long as there's no #GP, then + * the operation is considered a success, and the caller does their own + * checking. + */ static int __amd_smn_rw(u16 node, u32 address, u32 *value, bool write) { struct pci_dev *root; @@ -202,9 +239,6 @@ static int __amd_smn_rw(u16 node, u32 address, u32 *value, bool write) err = (write ? pci_write_config_dword(root, 0x64, *value) : pci_read_config_dword(root, 0x64, value)); - if (err) - pr_warn("Error %s SMN address 0x%x.\n", - (write ? "writing to" : "reading from"), address); out_unlock: mutex_unlock(&smn_mutex); @@ -213,7 +247,7 @@ out: return err; } -int amd_smn_read(u16 node, u32 address, u32 *value) +int __must_check amd_smn_read(u16 node, u32 address, u32 *value) { int err = __amd_smn_rw(node, address, value, false); @@ -226,7 +260,7 @@ int amd_smn_read(u16 node, u32 address, u32 *value) } EXPORT_SYMBOL_GPL(amd_smn_read); -int amd_smn_write(u16 node, u32 address, u32 value) +int __must_check amd_smn_write(u16 node, u32 address, u32 value) { return __amd_smn_rw(node, address, &value, true); } diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index a02bba0ed6b9..5857a0f5d514 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -34,7 +34,7 @@ obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_IA32_FEAT_CTL) += feat_ctl.o ifdef CONFIG_CPU_SUP_INTEL -obj-y += intel.o intel_pconfig.o tsx.o +obj-y += intel.o tsx.o obj-$(CONFIG_PM) += intel_epb.o endif obj-$(CONFIG_CPU_SUP_AMD) += amd.o diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 44df3f11e731..be5889bded49 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1220,14 +1220,3 @@ void amd_check_microcode(void) on_each_cpu(zenbleed_check_cpu, NULL, 1); } - -/* - * Issue a DIV 0/1 insn to clear any division data from previous DIV - * operations. - */ -void noinstr amd_clear_divider(void) -{ - asm volatile(ALTERNATIVE("", "div %2\n\t", X86_BUG_DIV0) - :: "a" (0), "d" (0), "r" (1)); -} -EXPORT_SYMBOL_GPL(amd_clear_divider); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index b6f927f6c567..45675da354f3 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1625,6 +1625,7 @@ static bool __init spec_ctrl_bhi_dis(void) enum bhi_mitigations { BHI_MITIGATION_OFF, BHI_MITIGATION_ON, + BHI_MITIGATION_VMEXIT_ONLY, }; static enum bhi_mitigations bhi_mitigation __ro_after_init = @@ -1639,6 +1640,8 @@ static int __init spectre_bhi_parse_cmdline(char *str) bhi_mitigation = BHI_MITIGATION_OFF; else if (!strcmp(str, "on")) bhi_mitigation = BHI_MITIGATION_ON; + else if (!strcmp(str, "vmexit")) + bhi_mitigation = BHI_MITIGATION_VMEXIT_ONLY; else pr_err("Ignoring unknown spectre_bhi option (%s)", str); @@ -1659,19 +1662,22 @@ static void __init bhi_select_mitigation(void) return; } + /* Mitigate in hardware if supported */ if (spec_ctrl_bhi_dis()) return; if (!IS_ENABLED(CONFIG_X86_64)) return; - /* Mitigate KVM by default */ - setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT); - pr_info("Spectre BHI mitigation: SW BHB clearing on vm exit\n"); + if (bhi_mitigation == BHI_MITIGATION_VMEXIT_ONLY) { + pr_info("Spectre BHI mitigation: SW BHB clearing on VM exit only\n"); + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT); + return; + } - /* Mitigate syscalls when the mitigation is forced =on */ + pr_info("Spectre BHI mitigation: SW BHB clearing on syscall and VM exit\n"); setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP); - pr_info("Spectre BHI mitigation: SW BHB clearing on syscall\n"); + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT); } static void __init spectre_v2_select_mitigation(void) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index fdf3489d92a4..08b95a35b5cb 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -72,19 +72,19 @@ static bool cpu_model_supports_sld __ro_after_init; */ static void check_memory_type_self_snoop_errata(struct cpuinfo_x86 *c) { - switch (c->x86_model) { - case INTEL_FAM6_CORE_YONAH: - case INTEL_FAM6_CORE2_MEROM: - case INTEL_FAM6_CORE2_MEROM_L: - case INTEL_FAM6_CORE2_PENRYN: - case INTEL_FAM6_CORE2_DUNNINGTON: - case INTEL_FAM6_NEHALEM: - case INTEL_FAM6_NEHALEM_G: - case INTEL_FAM6_NEHALEM_EP: - case INTEL_FAM6_NEHALEM_EX: - case INTEL_FAM6_WESTMERE: - case INTEL_FAM6_WESTMERE_EP: - case INTEL_FAM6_SANDYBRIDGE: + switch (c->x86_vfm) { + case INTEL_CORE_YONAH: + case INTEL_CORE2_MEROM: + case INTEL_CORE2_MEROM_L: + case INTEL_CORE2_PENRYN: + case INTEL_CORE2_DUNNINGTON: + case INTEL_NEHALEM: + case INTEL_NEHALEM_G: + case INTEL_NEHALEM_EP: + case INTEL_NEHALEM_EX: + case INTEL_WESTMERE: + case INTEL_WESTMERE_EP: + case INTEL_SANDYBRIDGE: setup_clear_cpu_cap(X86_FEATURE_SELFSNOOP); } } @@ -106,9 +106,9 @@ static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c) */ if (c->x86 != 6) return; - switch (c->x86_model) { - case INTEL_FAM6_XEON_PHI_KNL: - case INTEL_FAM6_XEON_PHI_KNM: + switch (c->x86_vfm) { + case INTEL_XEON_PHI_KNL: + case INTEL_XEON_PHI_KNM: break; default: return; @@ -134,32 +134,32 @@ static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c) * - Release note from 20180108 microcode release */ struct sku_microcode { - u8 model; + u32 vfm; u8 stepping; u32 microcode; }; static const struct sku_microcode spectre_bad_microcodes[] = { - { INTEL_FAM6_KABYLAKE, 0x0B, 0x80 }, - { INTEL_FAM6_KABYLAKE, 0x0A, 0x80 }, - { INTEL_FAM6_KABYLAKE, 0x09, 0x80 }, - { INTEL_FAM6_KABYLAKE_L, 0x0A, 0x80 }, - { INTEL_FAM6_KABYLAKE_L, 0x09, 0x80 }, - { INTEL_FAM6_SKYLAKE_X, 0x03, 0x0100013e }, - { INTEL_FAM6_SKYLAKE_X, 0x04, 0x0200003c }, - { INTEL_FAM6_BROADWELL, 0x04, 0x28 }, - { INTEL_FAM6_BROADWELL_G, 0x01, 0x1b }, - { INTEL_FAM6_BROADWELL_D, 0x02, 0x14 }, - { INTEL_FAM6_BROADWELL_D, 0x03, 0x07000011 }, - { INTEL_FAM6_BROADWELL_X, 0x01, 0x0b000025 }, - { INTEL_FAM6_HASWELL_L, 0x01, 0x21 }, - { INTEL_FAM6_HASWELL_G, 0x01, 0x18 }, - { INTEL_FAM6_HASWELL, 0x03, 0x23 }, - { INTEL_FAM6_HASWELL_X, 0x02, 0x3b }, - { INTEL_FAM6_HASWELL_X, 0x04, 0x10 }, - { INTEL_FAM6_IVYBRIDGE_X, 0x04, 0x42a }, + { INTEL_KABYLAKE, 0x0B, 0x80 }, + { INTEL_KABYLAKE, 0x0A, 0x80 }, + { INTEL_KABYLAKE, 0x09, 0x80 }, + { INTEL_KABYLAKE_L, 0x0A, 0x80 }, + { INTEL_KABYLAKE_L, 0x09, 0x80 }, + { INTEL_SKYLAKE_X, 0x03, 0x0100013e }, + { INTEL_SKYLAKE_X, 0x04, 0x0200003c }, + { INTEL_BROADWELL, 0x04, 0x28 }, + { INTEL_BROADWELL_G, 0x01, 0x1b }, + { INTEL_BROADWELL_D, 0x02, 0x14 }, + { INTEL_BROADWELL_D, 0x03, 0x07000011 }, + { INTEL_BROADWELL_X, 0x01, 0x0b000025 }, + { INTEL_HASWELL_L, 0x01, 0x21 }, + { INTEL_HASWELL_G, 0x01, 0x18 }, + { INTEL_HASWELL, 0x03, 0x23 }, + { INTEL_HASWELL_X, 0x02, 0x3b }, + { INTEL_HASWELL_X, 0x04, 0x10 }, + { INTEL_IVYBRIDGE_X, 0x04, 0x42a }, /* Observed in the wild */ - { INTEL_FAM6_SANDYBRIDGE_X, 0x06, 0x61b }, - { INTEL_FAM6_SANDYBRIDGE_X, 0x07, 0x712 }, + { INTEL_SANDYBRIDGE_X, 0x06, 0x61b }, + { INTEL_SANDYBRIDGE_X, 0x07, 0x712 }, }; static bool bad_spectre_microcode(struct cpuinfo_x86 *c) @@ -173,11 +173,8 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_HYPERVISOR)) return false; - if (c->x86 != 6) - return false; - for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) { - if (c->x86_model == spectre_bad_microcodes[i].model && + if (c->x86_vfm == spectre_bad_microcodes[i].vfm && c->x86_stepping == spectre_bad_microcodes[i].stepping) return (c->microcode <= spectre_bad_microcodes[i].microcode); } @@ -190,83 +187,35 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) #define TME_ACTIVATE_LOCKED(x) (x & 0x1) #define TME_ACTIVATE_ENABLED(x) (x & 0x2) -#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */ -#define TME_ACTIVATE_POLICY_AES_XTS_128 0 - #define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */ -#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */ -#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1 - -/* Values for mktme_status (SW only construct) */ -#define MKTME_ENABLED 0 -#define MKTME_DISABLED 1 -#define MKTME_UNINITIALIZED 2 -static int mktme_status = MKTME_UNINITIALIZED; - static void detect_tme_early(struct cpuinfo_x86 *c) { - u64 tme_activate, tme_policy, tme_crypto_algs; - int keyid_bits = 0, nr_keyids = 0; - static u64 tme_activate_cpu0 = 0; + u64 tme_activate; + int keyid_bits; rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate); - if (mktme_status != MKTME_UNINITIALIZED) { - if (tme_activate != tme_activate_cpu0) { - /* Broken BIOS? */ - pr_err_once("x86/tme: configuration is inconsistent between CPUs\n"); - pr_err_once("x86/tme: MKTME is not usable\n"); - mktme_status = MKTME_DISABLED; - - /* Proceed. We may need to exclude bits from x86_phys_bits. */ - } - } else { - tme_activate_cpu0 = tme_activate; - } - if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) { pr_info_once("x86/tme: not enabled by BIOS\n"); - mktme_status = MKTME_DISABLED; clear_cpu_cap(c, X86_FEATURE_TME); return; } - - if (mktme_status != MKTME_UNINITIALIZED) - goto detect_keyid_bits; - - pr_info("x86/tme: enabled by BIOS\n"); - - tme_policy = TME_ACTIVATE_POLICY(tme_activate); - if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128) - pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy); - - tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate); - if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) { - pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n", - tme_crypto_algs); - mktme_status = MKTME_DISABLED; - } -detect_keyid_bits: + pr_info_once("x86/tme: enabled by BIOS\n"); keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate); - nr_keyids = (1UL << keyid_bits) - 1; - if (nr_keyids) { - pr_info_once("x86/mktme: enabled by BIOS\n"); - pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids); - } else { - pr_info_once("x86/mktme: disabled by BIOS\n"); - } - - if (mktme_status == MKTME_UNINITIALIZED) { - /* MKTME is usable */ - mktme_status = MKTME_ENABLED; - } + if (!keyid_bits) + return; /* - * KeyID bits effectively lower the number of physical address - * bits. Update cpuinfo_x86::x86_phys_bits accordingly. + * KeyID bits are set by BIOS and can be present regardless + * of whether the kernel is using them. They effectively lower + * the number of physical address bits. + * + * Update cpuinfo_x86::x86_phys_bits accordingly. */ c->x86_phys_bits -= keyid_bits; + pr_info_once("x86/mktme: BIOS enabled: x86_phys_bits reduced by %d\n", + keyid_bits); } void intel_unlock_cpuid_leafs(struct cpuinfo_x86 *c) @@ -320,7 +269,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) * need the microcode to have already been loaded... so if it is * not, recommend a BIOS update and disable large pages. */ - if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_stepping <= 2 && + if (c->x86_vfm == INTEL_ATOM_BONNELL && c->x86_stepping <= 2 && c->microcode < 0x20e) { pr_warn("Atom PSE erratum detected, BIOS microcode update recommended\n"); clear_cpu_cap(c, X86_FEATURE_PSE); @@ -352,17 +301,13 @@ static void early_init_intel(struct cpuinfo_x86 *c) } /* Penwell and Cloverview have the TSC which doesn't sleep on S3 */ - if (c->x86 == 6) { - switch (c->x86_model) { - case INTEL_FAM6_ATOM_SALTWELL_MID: - case INTEL_FAM6_ATOM_SALTWELL_TABLET: - case INTEL_FAM6_ATOM_SILVERMONT_MID: - case INTEL_FAM6_ATOM_AIRMONT_NP: - set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC_S3); - break; - default: - break; - } + switch (c->x86_vfm) { + case INTEL_ATOM_SALTWELL_MID: + case INTEL_ATOM_SALTWELL_TABLET: + case INTEL_ATOM_SILVERMONT_MID: + case INTEL_ATOM_AIRMONT_NP: + set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC_S3); + break; } /* @@ -401,7 +346,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) * should be false so that __flush_tlb_all() causes CR3 instead of CR4.PGE * to be modified. */ - if (c->x86 == 5 && c->x86_model == 9) { + if (c->x86_vfm == INTEL_QUARK_X1000) { pr_info("Disabling PGE capability bit\n"); setup_clear_cpu_cap(X86_FEATURE_PGE); } @@ -633,12 +578,13 @@ static void init_intel(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_PEBS); } - if (c->x86 == 6 && boot_cpu_has(X86_FEATURE_CLFLUSH) && - (c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47)) + if (boot_cpu_has(X86_FEATURE_CLFLUSH) && + (c->x86_vfm == INTEL_CORE2_DUNNINGTON || + c->x86_vfm == INTEL_NEHALEM_EX || + c->x86_vfm == INTEL_WESTMERE_EX)) set_cpu_bug(c, X86_BUG_CLFLUSH_MONITOR); - if (c->x86 == 6 && boot_cpu_has(X86_FEATURE_MWAIT) && - ((c->x86_model == INTEL_FAM6_ATOM_GOLDMONT))) + if (boot_cpu_has(X86_FEATURE_MWAIT) && c->x86_vfm == INTEL_ATOM_GOLDMONT) set_cpu_bug(c, X86_BUG_MONITOR); #ifdef CONFIG_X86_64 @@ -1254,9 +1200,9 @@ void handle_bus_lock(struct pt_regs *regs) * feature even though they do not enumerate IA32_CORE_CAPABILITIES. */ static const struct x86_cpu_id split_lock_cpu_ids[] __initconst = { - X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, 0), - X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, 0), - X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, 0), + X86_MATCH_VFM(INTEL_ICELAKE_X, 0), + X86_MATCH_VFM(INTEL_ICELAKE_L, 0), + X86_MATCH_VFM(INTEL_ICELAKE_D, 0), {} }; diff --git a/arch/x86/kernel/cpu/intel_pconfig.c b/arch/x86/kernel/cpu/intel_pconfig.c deleted file mode 100644 index 5be2b1790282..000000000000 --- a/arch/x86/kernel/cpu/intel_pconfig.c +++ /dev/null @@ -1,84 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Intel PCONFIG instruction support. - * - * Copyright (C) 2017 Intel Corporation - * - * Author: - * Kirill A. Shutemov - */ -#include -#include - -#include -#include - -#define PCONFIG_CPUID 0x1b - -#define PCONFIG_CPUID_SUBLEAF_MASK ((1 << 12) - 1) - -/* Subleaf type (EAX) for PCONFIG CPUID leaf (0x1B) */ -enum { - PCONFIG_CPUID_SUBLEAF_INVALID = 0, - PCONFIG_CPUID_SUBLEAF_TARGETID = 1, -}; - -/* Bitmask of supported targets */ -static u64 targets_supported __read_mostly; - -int pconfig_target_supported(enum pconfig_target target) -{ - /* - * We would need to re-think the implementation once we get > 64 - * PCONFIG targets. Spec allows up to 2^32 targets. - */ - BUILD_BUG_ON(PCONFIG_TARGET_NR >= 64); - - if (WARN_ON_ONCE(target >= 64)) - return 0; - return targets_supported & (1ULL << target); -} - -static int __init intel_pconfig_init(void) -{ - int subleaf; - - if (!boot_cpu_has(X86_FEATURE_PCONFIG)) - return 0; - - /* - * Scan subleafs of PCONFIG CPUID leaf. - * - * Subleafs of the same type need not to be consecutive. - * - * Stop on the first invalid subleaf type. All subleafs after the first - * invalid are invalid too. - */ - for (subleaf = 0; subleaf < INT_MAX; subleaf++) { - struct cpuid_regs regs; - - cpuid_count(PCONFIG_CPUID, subleaf, - ®s.eax, ®s.ebx, ®s.ecx, ®s.edx); - - switch (regs.eax & PCONFIG_CPUID_SUBLEAF_MASK) { - case PCONFIG_CPUID_SUBLEAF_INVALID: - /* Stop on the first invalid subleaf */ - goto out; - case PCONFIG_CPUID_SUBLEAF_TARGETID: - /* Mark supported PCONFIG targets */ - if (regs.ebx < 64) - targets_supported |= (1ULL << regs.ebx); - if (regs.ecx < 64) - targets_supported |= (1ULL << regs.ecx); - if (regs.edx < 64) - targets_supported |= (1ULL << regs.edx); - break; - default: - /* Unknown CPUID.PCONFIG subleaf: ignore */ - break; - } - } -out: - return 0; -} -arch_initcall(intel_pconfig_init); diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 8d18074534ff..49ed3428785d 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -799,4 +799,5 @@ static void __exit inject_exit(void) module_init(inject_init); module_exit(inject_exit); +MODULE_DESCRIPTION("Machine check injection support"); MODULE_LICENSE("GPL"); diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh index 1db560ed2ca3..68f537347466 100644 --- a/arch/x86/kernel/cpu/mkcapflags.sh +++ b/arch/x86/kernel/cpu/mkcapflags.sh @@ -30,8 +30,7 @@ dump_array() # If the /* comment */ starts with a quote string, grab that. VALUE="$(echo "$i" | sed -n 's@.*/\* *\("[^"]*"\).*\*/@\1@p')" - [ -z "$VALUE" ] && VALUE="\"$NAME\"" - [ "$VALUE" = '""' ] && continue + [ ! "$VALUE" ] && continue # Name is uppercase, VALUE is all lowercase VALUE="$(echo "$VALUE" | tr A-Z a-z)" diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index a113d9aba553..1930fce9dfe9 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -19,7 +19,6 @@ #include #include #include -#include #include #include @@ -60,7 +59,8 @@ static void mba_wrmsr_intel(struct msr_param *m); static void cat_wrmsr(struct msr_param *m); static void mba_wrmsr_amd(struct msr_param *m); -#define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.domains) +#define ctrl_domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.ctrl_domains) +#define mon_domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.mon_domains) struct rdt_hw_resource rdt_resources_all[] = { [RDT_RESOURCE_L3] = @@ -68,8 +68,10 @@ struct rdt_hw_resource rdt_resources_all[] = { .r_resctrl = { .rid = RDT_RESOURCE_L3, .name = "L3", - .cache_level = 3, - .domains = domain_init(RDT_RESOURCE_L3), + .ctrl_scope = RESCTRL_L3_CACHE, + .mon_scope = RESCTRL_L3_CACHE, + .ctrl_domains = ctrl_domain_init(RDT_RESOURCE_L3), + .mon_domains = mon_domain_init(RDT_RESOURCE_L3), .parse_ctrlval = parse_cbm, .format_str = "%d=%0*x", .fflags = RFTYPE_RES_CACHE, @@ -82,8 +84,8 @@ struct rdt_hw_resource rdt_resources_all[] = { .r_resctrl = { .rid = RDT_RESOURCE_L2, .name = "L2", - .cache_level = 2, - .domains = domain_init(RDT_RESOURCE_L2), + .ctrl_scope = RESCTRL_L2_CACHE, + .ctrl_domains = ctrl_domain_init(RDT_RESOURCE_L2), .parse_ctrlval = parse_cbm, .format_str = "%d=%0*x", .fflags = RFTYPE_RES_CACHE, @@ -96,8 +98,8 @@ struct rdt_hw_resource rdt_resources_all[] = { .r_resctrl = { .rid = RDT_RESOURCE_MBA, .name = "MB", - .cache_level = 3, - .domains = domain_init(RDT_RESOURCE_MBA), + .ctrl_scope = RESCTRL_L3_CACHE, + .ctrl_domains = ctrl_domain_init(RDT_RESOURCE_MBA), .parse_ctrlval = parse_bw, .format_str = "%d=%*u", .fflags = RFTYPE_RES_MB, @@ -108,8 +110,8 @@ struct rdt_hw_resource rdt_resources_all[] = { .r_resctrl = { .rid = RDT_RESOURCE_SMBA, .name = "SMBA", - .cache_level = 3, - .domains = domain_init(RDT_RESOURCE_SMBA), + .ctrl_scope = RESCTRL_L3_CACHE, + .ctrl_domains = ctrl_domain_init(RDT_RESOURCE_SMBA), .parse_ctrlval = parse_bw, .format_str = "%d=%*u", .fflags = RFTYPE_RES_MB, @@ -306,8 +308,8 @@ static void rdt_get_cdp_l2_config(void) static void mba_wrmsr_amd(struct msr_param *m) { + struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(m->dom); struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res); - struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(m->dom); unsigned int i; for (i = m->low; i < m->high; i++) @@ -330,8 +332,8 @@ static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r) static void mba_wrmsr_intel(struct msr_param *m) { + struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(m->dom); struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res); - struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(m->dom); unsigned int i; /* Write the delay values for mba. */ @@ -341,23 +343,38 @@ static void mba_wrmsr_intel(struct msr_param *m) static void cat_wrmsr(struct msr_param *m) { + struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(m->dom); struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res); - struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(m->dom); unsigned int i; for (i = m->low; i < m->high; i++) wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]); } -struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r) +struct rdt_ctrl_domain *get_ctrl_domain_from_cpu(int cpu, struct rdt_resource *r) { - struct rdt_domain *d; + struct rdt_ctrl_domain *d; lockdep_assert_cpus_held(); - list_for_each_entry(d, &r->domains, list) { + list_for_each_entry(d, &r->ctrl_domains, hdr.list) { /* Find the domain that contains this CPU */ - if (cpumask_test_cpu(cpu, &d->cpu_mask)) + if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask)) + return d; + } + + return NULL; +} + +struct rdt_mon_domain *get_mon_domain_from_cpu(int cpu, struct rdt_resource *r) +{ + struct rdt_mon_domain *d; + + lockdep_assert_cpus_held(); + + list_for_each_entry(d, &r->mon_domains, hdr.list) { + /* Find the domain that contains this CPU */ + if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask)) return d; } @@ -379,24 +396,21 @@ void rdt_ctrl_update(void *arg) } /* - * rdt_find_domain - Find a domain in a resource that matches input resource id + * rdt_find_domain - Search for a domain id in a resource domain list. * - * Search resource r's domain list to find the resource id. If the resource - * id is found in a domain, return the domain. Otherwise, if requested by - * caller, return the first domain whose id is bigger than the input id. - * The domain list is sorted by id in ascending order. + * Search the domain list to find the domain id. If the domain id is + * found, return the domain. NULL otherwise. If the domain id is not + * found (and NULL returned) then the first domain with id bigger than + * the input id can be returned to the caller via @pos. */ -struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id, - struct list_head **pos) +struct rdt_domain_hdr *rdt_find_domain(struct list_head *h, int id, + struct list_head **pos) { - struct rdt_domain *d; + struct rdt_domain_hdr *d; struct list_head *l; - if (id < 0) - return ERR_PTR(-ENODEV); - - list_for_each(l, &r->domains) { - d = list_entry(l, struct rdt_domain, list); + list_for_each(l, h) { + d = list_entry(l, struct rdt_domain_hdr, list); /* When id is found, return its domain. */ if (id == d->id) return d; @@ -425,18 +439,23 @@ static void setup_default_ctrlval(struct rdt_resource *r, u32 *dc) *dc = r->default_ctrl; } -static void domain_free(struct rdt_hw_domain *hw_dom) +static void ctrl_domain_free(struct rdt_hw_ctrl_domain *hw_dom) { - kfree(hw_dom->arch_mbm_total); - kfree(hw_dom->arch_mbm_local); kfree(hw_dom->ctrl_val); kfree(hw_dom); } -static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d) +static void mon_domain_free(struct rdt_hw_mon_domain *hw_dom) { + kfree(hw_dom->arch_mbm_total); + kfree(hw_dom->arch_mbm_local); + kfree(hw_dom); +} + +static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_ctrl_domain *d) +{ + struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(d); struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); - struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); struct msr_param m; u32 *dc; @@ -461,7 +480,7 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d) * @num_rmid: The size of the MBM counter array * @hw_dom: The domain that owns the allocated arrays */ -static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_domain *hw_dom) +static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_mon_domain *hw_dom) { size_t tsize; @@ -484,37 +503,45 @@ static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_domain *hw_dom) return 0; } -/* - * domain_add_cpu - Add a cpu to a resource's domain list. - * - * If an existing domain in the resource r's domain list matches the cpu's - * resource id, add the cpu in the domain. - * - * Otherwise, a new domain is allocated and inserted into the right position - * in the domain list sorted by id in ascending order. - * - * The order in the domain list is visible to users when we print entries - * in the schemata file and schemata input is validated to have the same order - * as this list. - */ -static void domain_add_cpu(int cpu, struct rdt_resource *r) +static int get_domain_id_from_scope(int cpu, enum resctrl_scope scope) { - int id = get_cpu_cacheinfo_id(cpu, r->cache_level); + switch (scope) { + case RESCTRL_L2_CACHE: + case RESCTRL_L3_CACHE: + return get_cpu_cacheinfo_id(cpu, scope); + case RESCTRL_L3_NODE: + return cpu_to_node(cpu); + default: + break; + } + + return -EINVAL; +} + +static void domain_add_cpu_ctrl(int cpu, struct rdt_resource *r) +{ + int id = get_domain_id_from_scope(cpu, r->ctrl_scope); + struct rdt_hw_ctrl_domain *hw_dom; struct list_head *add_pos = NULL; - struct rdt_hw_domain *hw_dom; - struct rdt_domain *d; + struct rdt_domain_hdr *hdr; + struct rdt_ctrl_domain *d; int err; lockdep_assert_held(&domain_list_lock); - d = rdt_find_domain(r, id, &add_pos); - if (IS_ERR(d)) { - pr_warn("Couldn't find cache id for CPU %d\n", cpu); + if (id < 0) { + pr_warn_once("Can't find control domain id for CPU:%d scope:%d for resource %s\n", + cpu, r->ctrl_scope, r->name); return; } - if (d) { - cpumask_set_cpu(cpu, &d->cpu_mask); + hdr = rdt_find_domain(&r->ctrl_domains, id, &add_pos); + if (hdr) { + if (WARN_ON_ONCE(hdr->type != RESCTRL_CTRL_DOMAIN)) + return; + d = container_of(hdr, struct rdt_ctrl_domain, hdr); + + cpumask_set_cpu(cpu, &d->hdr.cpu_mask); if (r->cache.arch_has_per_cpu_cfg) rdt_domain_reconfigure_cdp(r); return; @@ -525,62 +552,185 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) return; d = &hw_dom->d_resctrl; - d->id = id; - cpumask_set_cpu(cpu, &d->cpu_mask); + d->hdr.id = id; + d->hdr.type = RESCTRL_CTRL_DOMAIN; + cpumask_set_cpu(cpu, &d->hdr.cpu_mask); rdt_domain_reconfigure_cdp(r); - if (r->alloc_capable && domain_setup_ctrlval(r, d)) { - domain_free(hw_dom); + if (domain_setup_ctrlval(r, d)) { + ctrl_domain_free(hw_dom); return; } - if (r->mon_capable && arch_domain_mbm_alloc(r->num_rmid, hw_dom)) { - domain_free(hw_dom); - return; - } + list_add_tail_rcu(&d->hdr.list, add_pos); - list_add_tail_rcu(&d->list, add_pos); - - err = resctrl_online_domain(r, d); + err = resctrl_online_ctrl_domain(r, d); if (err) { - list_del_rcu(&d->list); + list_del_rcu(&d->hdr.list); synchronize_rcu(); - domain_free(hw_dom); + ctrl_domain_free(hw_dom); + } +} + +static void domain_add_cpu_mon(int cpu, struct rdt_resource *r) +{ + int id = get_domain_id_from_scope(cpu, r->mon_scope); + struct list_head *add_pos = NULL; + struct rdt_hw_mon_domain *hw_dom; + struct rdt_domain_hdr *hdr; + struct rdt_mon_domain *d; + int err; + + lockdep_assert_held(&domain_list_lock); + + if (id < 0) { + pr_warn_once("Can't find monitor domain id for CPU:%d scope:%d for resource %s\n", + cpu, r->mon_scope, r->name); + return; + } + + hdr = rdt_find_domain(&r->mon_domains, id, &add_pos); + if (hdr) { + if (WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN)) + return; + d = container_of(hdr, struct rdt_mon_domain, hdr); + + cpumask_set_cpu(cpu, &d->hdr.cpu_mask); + return; + } + + hw_dom = kzalloc_node(sizeof(*hw_dom), GFP_KERNEL, cpu_to_node(cpu)); + if (!hw_dom) + return; + + d = &hw_dom->d_resctrl; + d->hdr.id = id; + d->hdr.type = RESCTRL_MON_DOMAIN; + d->ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE); + if (!d->ci) { + pr_warn_once("Can't find L3 cache for CPU:%d resource %s\n", cpu, r->name); + mon_domain_free(hw_dom); + return; + } + cpumask_set_cpu(cpu, &d->hdr.cpu_mask); + + arch_mon_domain_online(r, d); + + if (arch_domain_mbm_alloc(r->num_rmid, hw_dom)) { + mon_domain_free(hw_dom); + return; + } + + list_add_tail_rcu(&d->hdr.list, add_pos); + + err = resctrl_online_mon_domain(r, d); + if (err) { + list_del_rcu(&d->hdr.list); + synchronize_rcu(); + mon_domain_free(hw_dom); + } +} + +static void domain_add_cpu(int cpu, struct rdt_resource *r) +{ + if (r->alloc_capable) + domain_add_cpu_ctrl(cpu, r); + if (r->mon_capable) + domain_add_cpu_mon(cpu, r); +} + +static void domain_remove_cpu_ctrl(int cpu, struct rdt_resource *r) +{ + int id = get_domain_id_from_scope(cpu, r->ctrl_scope); + struct rdt_hw_ctrl_domain *hw_dom; + struct rdt_domain_hdr *hdr; + struct rdt_ctrl_domain *d; + + lockdep_assert_held(&domain_list_lock); + + if (id < 0) { + pr_warn_once("Can't find control domain id for CPU:%d scope:%d for resource %s\n", + cpu, r->ctrl_scope, r->name); + return; + } + + hdr = rdt_find_domain(&r->ctrl_domains, id, NULL); + if (!hdr) { + pr_warn("Can't find control domain for id=%d for CPU %d for resource %s\n", + id, cpu, r->name); + return; + } + + if (WARN_ON_ONCE(hdr->type != RESCTRL_CTRL_DOMAIN)) + return; + + d = container_of(hdr, struct rdt_ctrl_domain, hdr); + hw_dom = resctrl_to_arch_ctrl_dom(d); + + cpumask_clear_cpu(cpu, &d->hdr.cpu_mask); + if (cpumask_empty(&d->hdr.cpu_mask)) { + resctrl_offline_ctrl_domain(r, d); + list_del_rcu(&d->hdr.list); + synchronize_rcu(); + + /* + * rdt_ctrl_domain "d" is going to be freed below, so clear + * its pointer from pseudo_lock_region struct. + */ + if (d->plr) + d->plr->d = NULL; + ctrl_domain_free(hw_dom); + + return; + } +} + +static void domain_remove_cpu_mon(int cpu, struct rdt_resource *r) +{ + int id = get_domain_id_from_scope(cpu, r->mon_scope); + struct rdt_hw_mon_domain *hw_dom; + struct rdt_domain_hdr *hdr; + struct rdt_mon_domain *d; + + lockdep_assert_held(&domain_list_lock); + + if (id < 0) { + pr_warn_once("Can't find monitor domain id for CPU:%d scope:%d for resource %s\n", + cpu, r->mon_scope, r->name); + return; + } + + hdr = rdt_find_domain(&r->mon_domains, id, NULL); + if (!hdr) { + pr_warn("Can't find monitor domain for id=%d for CPU %d for resource %s\n", + id, cpu, r->name); + return; + } + + if (WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN)) + return; + + d = container_of(hdr, struct rdt_mon_domain, hdr); + hw_dom = resctrl_to_arch_mon_dom(d); + + cpumask_clear_cpu(cpu, &d->hdr.cpu_mask); + if (cpumask_empty(&d->hdr.cpu_mask)) { + resctrl_offline_mon_domain(r, d); + list_del_rcu(&d->hdr.list); + synchronize_rcu(); + mon_domain_free(hw_dom); + + return; } } static void domain_remove_cpu(int cpu, struct rdt_resource *r) { - int id = get_cpu_cacheinfo_id(cpu, r->cache_level); - struct rdt_hw_domain *hw_dom; - struct rdt_domain *d; - - lockdep_assert_held(&domain_list_lock); - - d = rdt_find_domain(r, id, NULL); - if (IS_ERR_OR_NULL(d)) { - pr_warn("Couldn't find cache id for CPU %d\n", cpu); - return; - } - hw_dom = resctrl_to_arch_dom(d); - - cpumask_clear_cpu(cpu, &d->cpu_mask); - if (cpumask_empty(&d->cpu_mask)) { - resctrl_offline_domain(r, d); - list_del_rcu(&d->list); - synchronize_rcu(); - - /* - * rdt_domain "d" is going to be freed below, so clear - * its pointer from pseudo_lock_region struct. - */ - if (d->plr) - d->plr->d = NULL; - domain_free(hw_dom); - - return; - } + if (r->alloc_capable) + domain_remove_cpu_ctrl(cpu, r); + if (r->mon_capable) + domain_remove_cpu_mon(cpu, r); } static void clear_closid_rmid(int cpu) diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index b7291f60399c..50fa1fe9a073 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -60,7 +60,7 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) } int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s, - struct rdt_domain *d) + struct rdt_ctrl_domain *d) { struct resctrl_staged_config *cfg; u32 closid = data->rdtgrp->closid; @@ -69,7 +69,7 @@ int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s, cfg = &d->staged_config[s->conf_type]; if (cfg->have_new_ctrl) { - rdt_last_cmd_printf("Duplicate domain %d\n", d->id); + rdt_last_cmd_printf("Duplicate domain %d\n", d->hdr.id); return -EINVAL; } @@ -139,7 +139,7 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) * resource type. */ int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s, - struct rdt_domain *d) + struct rdt_ctrl_domain *d) { struct rdtgroup *rdtgrp = data->rdtgrp; struct resctrl_staged_config *cfg; @@ -148,7 +148,7 @@ int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s, cfg = &d->staged_config[s->conf_type]; if (cfg->have_new_ctrl) { - rdt_last_cmd_printf("Duplicate domain %d\n", d->id); + rdt_last_cmd_printf("Duplicate domain %d\n", d->hdr.id); return -EINVAL; } @@ -208,8 +208,8 @@ static int parse_line(char *line, struct resctrl_schema *s, struct resctrl_staged_config *cfg; struct rdt_resource *r = s->res; struct rdt_parse_data data; + struct rdt_ctrl_domain *d; char *dom = NULL, *id; - struct rdt_domain *d; unsigned long dom_id; /* Walking r->domains, ensure it can't race with cpuhp */ @@ -231,8 +231,8 @@ next: return -EINVAL; } dom = strim(dom); - list_for_each_entry(d, &r->domains, list) { - if (d->id == dom_id) { + list_for_each_entry(d, &r->ctrl_domains, hdr.list) { + if (d->hdr.id == dom_id) { data.buf = dom; data.rdtgrp = rdtgrp; if (r->parse_ctrlval(&data, s, d)) @@ -272,15 +272,15 @@ static u32 get_config_index(u32 closid, enum resctrl_conf_type type) } } -int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d, +int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_ctrl_domain *d, u32 closid, enum resctrl_conf_type t, u32 cfg_val) { + struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(d); struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); - struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); u32 idx = get_config_index(closid, t); struct msr_param msr_param; - if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask)) + if (!cpumask_test_cpu(smp_processor_id(), &d->hdr.cpu_mask)) return -EINVAL; hw_dom->ctrl_val[idx] = cfg_val; @@ -297,17 +297,17 @@ int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d, int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid) { struct resctrl_staged_config *cfg; - struct rdt_hw_domain *hw_dom; + struct rdt_hw_ctrl_domain *hw_dom; struct msr_param msr_param; + struct rdt_ctrl_domain *d; enum resctrl_conf_type t; - struct rdt_domain *d; u32 idx; /* Walking r->domains, ensure it can't race with cpuhp */ lockdep_assert_cpus_held(); - list_for_each_entry(d, &r->domains, list) { - hw_dom = resctrl_to_arch_dom(d); + list_for_each_entry(d, &r->ctrl_domains, hdr.list) { + hw_dom = resctrl_to_arch_ctrl_dom(d); msr_param.res = NULL; for (t = 0; t < CDP_NUM_TYPES; t++) { cfg = &hw_dom->d_resctrl.staged_config[t]; @@ -330,7 +330,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid) } } if (msr_param.res) - smp_call_function_any(&d->cpu_mask, rdt_ctrl_update, &msr_param, 1); + smp_call_function_any(&d->hdr.cpu_mask, rdt_ctrl_update, &msr_param, 1); } return 0; @@ -430,10 +430,10 @@ out: return ret ?: nbytes; } -u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d, +u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_ctrl_domain *d, u32 closid, enum resctrl_conf_type type) { - struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); + struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(d); u32 idx = get_config_index(closid, type); return hw_dom->ctrl_val[idx]; @@ -442,7 +442,7 @@ u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d, static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int closid) { struct rdt_resource *r = schema->res; - struct rdt_domain *dom; + struct rdt_ctrl_domain *dom; bool sep = false; u32 ctrl_val; @@ -450,7 +450,7 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo lockdep_assert_cpus_held(); seq_printf(s, "%*s:", max_name_width, schema->name); - list_for_each_entry(dom, &r->domains, list) { + list_for_each_entry(dom, &r->ctrl_domains, hdr.list) { if (sep) seq_puts(s, ";"); @@ -460,7 +460,7 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo ctrl_val = resctrl_arch_get_config(r, dom, closid, schema->conf_type); - seq_printf(s, r->format_str, dom->id, max_data_width, + seq_printf(s, r->format_str, dom->hdr.id, max_data_width, ctrl_val); sep = true; } @@ -489,7 +489,7 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of, } else { seq_printf(s, "%s:%d=%x\n", rdtgrp->plr->s->res->name, - rdtgrp->plr->d->id, + rdtgrp->plr->d->hdr.id, rdtgrp->plr->cbm); } } else { @@ -514,8 +514,8 @@ static int smp_mon_event_count(void *arg) } void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, - struct rdt_domain *d, struct rdtgroup *rdtgrp, - int evtid, int first) + struct rdt_mon_domain *d, struct rdtgroup *rdtgrp, + cpumask_t *cpumask, int evtid, int first) { int cpu; @@ -529,7 +529,6 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, rr->evtid = evtid; rr->r = r; rr->d = d; - rr->val = 0; rr->first = first; rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evtid); if (IS_ERR(rr->arch_mon_ctx)) { @@ -537,7 +536,7 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, return; } - cpu = cpumask_any_housekeeping(&d->cpu_mask, RESCTRL_PICK_ANY_CPU); + cpu = cpumask_any_housekeeping(cpumask, RESCTRL_PICK_ANY_CPU); /* * cpumask_any_housekeeping() prefers housekeeping CPUs, but @@ -546,7 +545,7 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, * counters on some platforms if its called in IRQ context. */ if (tick_nohz_full_cpu(cpu)) - smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1); + smp_call_function_any(cpumask, mon_event_count, rr, 1); else smp_call_on_cpu(cpu, smp_mon_event_count, rr, false); @@ -556,12 +555,13 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, int rdtgroup_mondata_show(struct seq_file *m, void *arg) { struct kernfs_open_file *of = m->private; + struct rdt_domain_hdr *hdr; + struct rmid_read rr = {0}; + struct rdt_mon_domain *d; u32 resid, evtid, domid; struct rdtgroup *rdtgrp; struct rdt_resource *r; union mon_data_bits md; - struct rdt_domain *d; - struct rmid_read rr; int ret = 0; rdtgrp = rdtgroup_kn_lock_live(of->kn); @@ -574,15 +574,40 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) resid = md.u.rid; domid = md.u.domid; evtid = md.u.evtid; - r = &rdt_resources_all[resid].r_resctrl; - d = rdt_find_domain(r, domid, NULL); - if (IS_ERR_OR_NULL(d)) { + + if (md.u.sum) { + /* + * This file requires summing across all domains that share + * the L3 cache id that was provided in the "domid" field of the + * mon_data_bits union. Search all domains in the resource for + * one that matches this cache id. + */ + list_for_each_entry(d, &r->mon_domains, hdr.list) { + if (d->ci->id == domid) { + rr.ci = d->ci; + mon_event_read(&rr, r, NULL, rdtgrp, + &d->ci->shared_cpu_map, evtid, false); + goto checkresult; + } + } ret = -ENOENT; goto out; + } else { + /* + * This file provides data from a single domain. Search + * the resource to find the domain with "domid". + */ + hdr = rdt_find_domain(&r->mon_domains, domid, NULL); + if (!hdr || WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN)) { + ret = -ENOENT; + goto out; + } + d = container_of(hdr, struct rdt_mon_domain, hdr); + mon_event_read(&rr, r, d, rdtgrp, &d->hdr.cpu_mask, evtid, false); } - mon_event_read(&rr, r, d, rdtgrp, evtid, false); +checkresult: if (rr.err == -EIO) seq_puts(m, "Error\n"); diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index f1d926832ec8..955999aecfca 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -127,29 +127,54 @@ struct mon_evt { }; /** - * union mon_data_bits - Monitoring details for each event file + * union mon_data_bits - Monitoring details for each event file. * @priv: Used to store monitoring event data in @u - * as kernfs private data - * @rid: Resource id associated with the event file - * @evtid: Event id associated with the event file - * @domid: The domain to which the event file belongs - * @u: Name of the bit fields struct + * as kernfs private data. + * @u.rid: Resource id associated with the event file. + * @u.evtid: Event id associated with the event file. + * @u.sum: Set when event must be summed across multiple + * domains. + * @u.domid: When @u.sum is zero this is the domain to which + * the event file belongs. When @sum is one this + * is the id of the L3 cache that all domains to be + * summed share. + * @u: Name of the bit fields struct. */ union mon_data_bits { void *priv; struct { unsigned int rid : 10; - enum resctrl_event_id evtid : 8; + enum resctrl_event_id evtid : 7; + unsigned int sum : 1; unsigned int domid : 14; } u; }; +/** + * struct rmid_read - Data passed across smp_call*() to read event count. + * @rgrp: Resource group for which the counter is being read. If it is a parent + * resource group then its event count is summed with the count from all + * its child resource groups. + * @r: Resource describing the properties of the event being read. + * @d: Domain that the counter should be read from. If NULL then sum all + * domains in @r sharing L3 @ci.id + * @evtid: Which monitor event to read. + * @first: Initialize MBM counter when true. + * @ci: Cacheinfo for L3. Only set when @d is NULL. Used when summing domains. + * @err: Error encountered when reading counter. + * @val: Returned value of event counter. If @rgrp is a parent resource group, + * @val includes the sum of event counts from its child resource groups. + * If @d is NULL, @val includes the sum of all domains in @r sharing @ci.id, + * (summed across child resource groups if @rgrp is a parent resource group). + * @arch_mon_ctx: Hardware monitor allocated for this read request (MPAM only). + */ struct rmid_read { struct rdtgroup *rgrp; struct rdt_resource *r; - struct rdt_domain *d; + struct rdt_mon_domain *d; enum resctrl_event_id evtid; bool first; + struct cacheinfo *ci; int err; u64 val; void *arch_mon_ctx; @@ -232,7 +257,7 @@ struct mongroup { */ struct pseudo_lock_region { struct resctrl_schema *s; - struct rdt_domain *d; + struct rdt_ctrl_domain *d; u32 cbm; wait_queue_head_t lock_thread_wq; int thread_done; @@ -355,25 +380,41 @@ struct arch_mbm_state { }; /** - * struct rdt_hw_domain - Arch private attributes of a set of CPUs that share - * a resource + * struct rdt_hw_ctrl_domain - Arch private attributes of a set of CPUs that share + * a resource for a control function * @d_resctrl: Properties exposed to the resctrl file system * @ctrl_val: array of cache or mem ctrl values (indexed by CLOSID) + * + * Members of this structure are accessed via helpers that provide abstraction. + */ +struct rdt_hw_ctrl_domain { + struct rdt_ctrl_domain d_resctrl; + u32 *ctrl_val; +}; + +/** + * struct rdt_hw_mon_domain - Arch private attributes of a set of CPUs that share + * a resource for a monitor function + * @d_resctrl: Properties exposed to the resctrl file system * @arch_mbm_total: arch private state for MBM total bandwidth * @arch_mbm_local: arch private state for MBM local bandwidth * * Members of this structure are accessed via helpers that provide abstraction. */ -struct rdt_hw_domain { - struct rdt_domain d_resctrl; - u32 *ctrl_val; +struct rdt_hw_mon_domain { + struct rdt_mon_domain d_resctrl; struct arch_mbm_state *arch_mbm_total; struct arch_mbm_state *arch_mbm_local; }; -static inline struct rdt_hw_domain *resctrl_to_arch_dom(struct rdt_domain *r) +static inline struct rdt_hw_ctrl_domain *resctrl_to_arch_ctrl_dom(struct rdt_ctrl_domain *r) { - return container_of(r, struct rdt_hw_domain, d_resctrl); + return container_of(r, struct rdt_hw_ctrl_domain, d_resctrl); +} + +static inline struct rdt_hw_mon_domain *resctrl_to_arch_mon_dom(struct rdt_mon_domain *r) +{ + return container_of(r, struct rdt_hw_mon_domain, d_resctrl); } /** @@ -385,7 +426,7 @@ static inline struct rdt_hw_domain *resctrl_to_arch_dom(struct rdt_domain *r) */ struct msr_param { struct rdt_resource *res; - struct rdt_domain *dom; + struct rdt_ctrl_domain *dom; u32 low; u32 high; }; @@ -458,9 +499,9 @@ static inline struct rdt_hw_resource *resctrl_to_arch_res(struct rdt_resource *r } int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s, - struct rdt_domain *d); + struct rdt_ctrl_domain *d); int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s, - struct rdt_domain *d); + struct rdt_ctrl_domain *d); extern struct mutex rdtgroup_mutex; @@ -493,6 +534,8 @@ static inline bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l) int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable); +void arch_mon_domain_online(struct rdt_resource *r, struct rdt_mon_domain *d); + /* * To return the common struct rdt_resource, which is contained in struct * rdt_hw_resource, walk the resctrl member of struct rdt_hw_resource. @@ -558,27 +601,28 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn); int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name); int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name, umode_t mask); -struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id, - struct list_head **pos); +struct rdt_domain_hdr *rdt_find_domain(struct list_head *h, int id, + struct list_head **pos); ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off); int rdtgroup_schemata_show(struct kernfs_open_file *of, struct seq_file *s, void *v); -bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_domain *d, +bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_ctrl_domain *d, unsigned long cbm, int closid, bool exclusive); -unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_domain *d, +unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_ctrl_domain *d, unsigned long cbm); enum rdtgrp_mode rdtgroup_mode_by_closid(int closid); int rdtgroup_tasks_assigned(struct rdtgroup *r); int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp); int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp); -bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm); -bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d); +bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm); +bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d); int rdt_pseudo_lock_init(void); void rdt_pseudo_lock_release(void); int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp); void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp); -struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r); +struct rdt_ctrl_domain *get_ctrl_domain_from_cpu(int cpu, struct rdt_resource *r); +struct rdt_mon_domain *get_mon_domain_from_cpu(int cpu, struct rdt_resource *r); int closids_supported(void); void closid_free(int closid); int alloc_rmid(u32 closid); @@ -589,19 +633,19 @@ bool __init rdt_cpu_has(int flag); void mon_event_count(void *info); int rdtgroup_mondata_show(struct seq_file *m, void *arg); void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, - struct rdt_domain *d, struct rdtgroup *rdtgrp, - int evtid, int first); -void mbm_setup_overflow_handler(struct rdt_domain *dom, + struct rdt_mon_domain *d, struct rdtgroup *rdtgrp, + cpumask_t *cpumask, int evtid, int first); +void mbm_setup_overflow_handler(struct rdt_mon_domain *dom, unsigned long delay_ms, int exclude_cpu); void mbm_handle_overflow(struct work_struct *work); void __init intel_rdt_mbm_apply_quirk(void); bool is_mba_sc(struct rdt_resource *r); -void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms, +void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long delay_ms, int exclude_cpu); void cqm_handle_limbo(struct work_struct *work); -bool has_busy_rmid(struct rdt_domain *d); -void __check_limbo(struct rdt_domain *d, bool force_free); +bool has_busy_rmid(struct rdt_mon_domain *d); +void __check_limbo(struct rdt_mon_domain *d, bool force_free); void rdt_domain_reconfigure_cdp(struct rdt_resource *r); void __init thread_throttle_mode_init(void); void __init mbm_config_rftype_init(const char *config); diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 366f496ca3ce..851b561850e0 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -15,6 +15,8 @@ * Software Developer Manual June 2016, volume 3, section 17.17. */ +#define pr_fmt(fmt) "resctrl: " fmt + #include #include #include @@ -97,6 +99,8 @@ unsigned int resctrl_rmid_realloc_limit; #define CF(cf) ((unsigned long)(1048576 * (cf) + 0.5)) +static int snc_nodes_per_l3_cache = 1; + /* * The correction factor table is documented in Documentation/arch/x86/resctrl.rst. * If rmid > rmid threshold, MBM total and local values should be multiplied @@ -185,7 +189,43 @@ static inline struct rmid_entry *__rmid_entry(u32 idx) return entry; } -static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val) +/* + * When Sub-NUMA Cluster (SNC) mode is not enabled (as indicated by + * "snc_nodes_per_l3_cache == 1") no translation of the RMID value is + * needed. The physical RMID is the same as the logical RMID. + * + * On a platform with SNC mode enabled, Linux enables RMID sharing mode + * via MSR 0xCA0 (see the "RMID Sharing Mode" section in the "Intel + * Resource Director Technology Architecture Specification" for a full + * description of RMID sharing mode). + * + * In RMID sharing mode there are fewer "logical RMID" values available + * to accumulate data ("physical RMIDs" are divided evenly between SNC + * nodes that share an L3 cache). Linux creates an rdt_mon_domain for + * each SNC node. + * + * The value loaded into IA32_PQR_ASSOC is the "logical RMID". + * + * Data is collected independently on each SNC node and can be retrieved + * using the "physical RMID" value computed by this function and loaded + * into IA32_QM_EVTSEL. @cpu can be any CPU in the SNC node. + * + * The scope of the IA32_QM_EVTSEL and IA32_QM_CTR MSRs is at the L3 + * cache. So a "physical RMID" may be read from any CPU that shares + * the L3 cache with the desired SNC node, not just from a CPU in + * the specific SNC node. + */ +static int logical_rmid_to_physical_rmid(int cpu, int lrmid) +{ + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + + if (snc_nodes_per_l3_cache == 1) + return lrmid; + + return lrmid + (cpu_to_node(cpu) % snc_nodes_per_l3_cache) * r->num_rmid; +} + +static int __rmid_read_phys(u32 prmid, enum resctrl_event_id eventid, u64 *val) { u64 msr_val; @@ -197,7 +237,7 @@ static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val) * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62) * are error bits. */ - wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid); + wrmsr(MSR_IA32_QM_EVTSEL, eventid, prmid); rdmsrl(MSR_IA32_QM_CTR, msr_val); if (msr_val & RMID_VAL_ERROR) @@ -209,7 +249,7 @@ static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val) return 0; } -static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom, +static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_mon_domain *hw_dom, u32 rmid, enum resctrl_event_id eventid) { @@ -228,19 +268,22 @@ static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom, return NULL; } -void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d, +void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d, u32 unused, u32 rmid, enum resctrl_event_id eventid) { - struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); + struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d); + int cpu = cpumask_any(&d->hdr.cpu_mask); struct arch_mbm_state *am; + u32 prmid; am = get_arch_mbm_state(hw_dom, rmid, eventid); if (am) { memset(am, 0, sizeof(*am)); + prmid = logical_rmid_to_physical_rmid(cpu, rmid); /* Record any initial, non-zero count value. */ - __rmid_read(rmid, eventid, &am->prev_msr); + __rmid_read_phys(prmid, eventid, &am->prev_msr); } } @@ -248,9 +291,9 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d, * Assumes that hardware counters are also reset and thus that there is * no need to record initial non-zero counts. */ -void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_domain *d) +void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d) { - struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); + struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d); if (is_mbm_total_enabled()) memset(hw_dom->arch_mbm_total, 0, @@ -269,22 +312,22 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width) return chunks >> shift; } -int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, +int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d, u32 unused, u32 rmid, enum resctrl_event_id eventid, u64 *val, void *ignored) { + struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d); struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); - struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); + int cpu = cpumask_any(&d->hdr.cpu_mask); struct arch_mbm_state *am; u64 msr_val, chunks; + u32 prmid; int ret; resctrl_arch_rmid_read_context_check(); - if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask)) - return -EINVAL; - - ret = __rmid_read(rmid, eventid, &msr_val); + prmid = logical_rmid_to_physical_rmid(cpu, rmid); + ret = __rmid_read_phys(prmid, eventid, &msr_val); if (ret) return ret; @@ -320,7 +363,7 @@ static void limbo_release_entry(struct rmid_entry *entry) * decrement the count. If the busy count gets to zero on an RMID, we * free the RMID */ -void __check_limbo(struct rdt_domain *d, bool force_free) +void __check_limbo(struct rdt_mon_domain *d, bool force_free) { struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; u32 idx_limit = resctrl_arch_system_num_rmid_idx(); @@ -364,7 +407,7 @@ void __check_limbo(struct rdt_domain *d, bool force_free) * CLOSID and RMID because there may be dependencies between them * on some architectures. */ - trace_mon_llc_occupancy_limbo(entry->closid, entry->rmid, d->id, val); + trace_mon_llc_occupancy_limbo(entry->closid, entry->rmid, d->hdr.id, val); } if (force_free || !rmid_dirty) { @@ -378,7 +421,7 @@ void __check_limbo(struct rdt_domain *d, bool force_free) resctrl_arch_mon_ctx_free(r, QOS_L3_OCCUP_EVENT_ID, arch_mon_ctx); } -bool has_busy_rmid(struct rdt_domain *d) +bool has_busy_rmid(struct rdt_mon_domain *d) { u32 idx_limit = resctrl_arch_system_num_rmid_idx(); @@ -479,7 +522,7 @@ int alloc_rmid(u32 closid) static void add_rmid_to_limbo(struct rmid_entry *entry) { struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; - struct rdt_domain *d; + struct rdt_mon_domain *d; u32 idx; lockdep_assert_held(&rdtgroup_mutex); @@ -490,7 +533,7 @@ static void add_rmid_to_limbo(struct rmid_entry *entry) idx = resctrl_arch_rmid_idx_encode(entry->closid, entry->rmid); entry->busy = 0; - list_for_each_entry(d, &r->domains, list) { + list_for_each_entry(d, &r->mon_domains, hdr.list) { /* * For the first limbo RMID in the domain, * setup up the limbo worker. @@ -532,7 +575,7 @@ void free_rmid(u32 closid, u32 rmid) list_add_tail(&entry->list, &rmid_free_lru); } -static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 closid, +static struct mbm_state *get_mbm_state(struct rdt_mon_domain *d, u32 closid, u32 rmid, enum resctrl_event_id evtid) { u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid); @@ -549,7 +592,10 @@ static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 closid, static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr) { + int cpu = smp_processor_id(); + struct rdt_mon_domain *d; struct mbm_state *m; + int err, ret; u64 tval = 0; if (rr->first) { @@ -560,14 +606,47 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr) return 0; } - rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid, rr->evtid, - &tval, rr->arch_mon_ctx); - if (rr->err) - return rr->err; + if (rr->d) { + /* Reading a single domain, must be on a CPU in that domain. */ + if (!cpumask_test_cpu(cpu, &rr->d->hdr.cpu_mask)) + return -EINVAL; + rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid, + rr->evtid, &tval, rr->arch_mon_ctx); + if (rr->err) + return rr->err; - rr->val += tval; + rr->val += tval; - return 0; + return 0; + } + + /* Summing domains that share a cache, must be on a CPU for that cache. */ + if (!cpumask_test_cpu(cpu, &rr->ci->shared_cpu_map)) + return -EINVAL; + + /* + * Legacy files must report the sum of an event across all + * domains that share the same L3 cache instance. + * Report success if a read from any domain succeeds, -EINVAL + * (translated to "Unavailable" for user space) if reading from + * all domains fail for any reason. + */ + ret = -EINVAL; + list_for_each_entry(d, &rr->r->mon_domains, hdr.list) { + if (d->ci->id != rr->ci->id) + continue; + err = resctrl_arch_rmid_read(rr->r, d, closid, rmid, + rr->evtid, &tval, rr->arch_mon_ctx); + if (!err) { + rr->val += tval; + ret = 0; + } + } + + if (ret) + rr->err = ret; + + return ret; } /* @@ -668,12 +747,12 @@ void mon_event_count(void *info) * throttle MSRs already have low percentage values. To avoid * unnecessarily restricting such rdtgroups, we also increase the bandwidth. */ -static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) +static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm) { u32 closid, rmid, cur_msr_val, new_msr_val; struct mbm_state *pmbm_data, *cmbm_data; + struct rdt_ctrl_domain *dom_mba; struct rdt_resource *r_mba; - struct rdt_domain *dom_mba; u32 cur_bw, user_bw, idx; struct list_head *head; struct rdtgroup *entry; @@ -688,7 +767,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) idx = resctrl_arch_rmid_idx_encode(closid, rmid); pmbm_data = &dom_mbm->mbm_local[idx]; - dom_mba = get_domain_from_cpu(smp_processor_id(), r_mba); + dom_mba = get_ctrl_domain_from_cpu(smp_processor_id(), r_mba); if (!dom_mba) { pr_warn_once("Failure to get domain for MBA update\n"); return; @@ -734,12 +813,11 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val); } -static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, +static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d, u32 closid, u32 rmid) { - struct rmid_read rr; + struct rmid_read rr = {0}; - rr.first = false; rr.r = r; rr.d = d; @@ -792,17 +870,17 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, void cqm_handle_limbo(struct work_struct *work) { unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL); - struct rdt_domain *d; + struct rdt_mon_domain *d; cpus_read_lock(); mutex_lock(&rdtgroup_mutex); - d = container_of(work, struct rdt_domain, cqm_limbo.work); + d = container_of(work, struct rdt_mon_domain, cqm_limbo.work); __check_limbo(d, false); if (has_busy_rmid(d)) { - d->cqm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask, + d->cqm_work_cpu = cpumask_any_housekeeping(&d->hdr.cpu_mask, RESCTRL_PICK_ANY_CPU); schedule_delayed_work_on(d->cqm_work_cpu, &d->cqm_limbo, delay); @@ -820,13 +898,13 @@ void cqm_handle_limbo(struct work_struct *work) * @exclude_cpu: Which CPU the handler should not run on, * RESCTRL_PICK_ANY_CPU to pick any CPU. */ -void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms, +void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long delay_ms, int exclude_cpu) { unsigned long delay = msecs_to_jiffies(delay_ms); int cpu; - cpu = cpumask_any_housekeeping(&dom->cpu_mask, exclude_cpu); + cpu = cpumask_any_housekeeping(&dom->hdr.cpu_mask, exclude_cpu); dom->cqm_work_cpu = cpu; if (cpu < nr_cpu_ids) @@ -837,9 +915,9 @@ void mbm_handle_overflow(struct work_struct *work) { unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL); struct rdtgroup *prgrp, *crgrp; + struct rdt_mon_domain *d; struct list_head *head; struct rdt_resource *r; - struct rdt_domain *d; cpus_read_lock(); mutex_lock(&rdtgroup_mutex); @@ -852,7 +930,7 @@ void mbm_handle_overflow(struct work_struct *work) goto out_unlock; r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; - d = container_of(work, struct rdt_domain, mbm_over.work); + d = container_of(work, struct rdt_mon_domain, mbm_over.work); list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { mbm_update(r, d, prgrp->closid, prgrp->mon.rmid); @@ -869,7 +947,7 @@ void mbm_handle_overflow(struct work_struct *work) * Re-check for housekeeping CPUs. This allows the overflow handler to * move off a nohz_full CPU quickly. */ - d->mbm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask, + d->mbm_work_cpu = cpumask_any_housekeeping(&d->hdr.cpu_mask, RESCTRL_PICK_ANY_CPU); schedule_delayed_work_on(d->mbm_work_cpu, &d->mbm_over, delay); @@ -886,7 +964,7 @@ out_unlock: * @exclude_cpu: Which CPU the handler should not run on, * RESCTRL_PICK_ANY_CPU to pick any CPU. */ -void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms, +void mbm_setup_overflow_handler(struct rdt_mon_domain *dom, unsigned long delay_ms, int exclude_cpu) { unsigned long delay = msecs_to_jiffies(delay_ms); @@ -898,7 +976,7 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms, */ if (!resctrl_mounted || !resctrl_arch_mon_capable()) return; - cpu = cpumask_any_housekeeping(&dom->cpu_mask, exclude_cpu); + cpu = cpumask_any_housekeeping(&dom->hdr.cpu_mask, exclude_cpu); dom->mbm_work_cpu = cpu; if (cpu < nr_cpu_ids) @@ -1015,6 +1093,88 @@ static void l3_mon_evt_init(struct rdt_resource *r) list_add_tail(&mbm_local_event.list, &r->evt_list); } +/* + * The power-on reset value of MSR_RMID_SNC_CONFIG is 0x1 + * which indicates that RMIDs are configured in legacy mode. + * This mode is incompatible with Linux resctrl semantics + * as RMIDs are partitioned between SNC nodes, which requires + * a user to know which RMID is allocated to a task. + * Clearing bit 0 reconfigures the RMID counters for use + * in RMID sharing mode. This mode is better for Linux. + * The RMID space is divided between all SNC nodes with the + * RMIDs renumbered to start from zero in each node when + * counting operations from tasks. Code to read the counters + * must adjust RMID counter numbers based on SNC node. See + * logical_rmid_to_physical_rmid() for code that does this. + */ +void arch_mon_domain_online(struct rdt_resource *r, struct rdt_mon_domain *d) +{ + if (snc_nodes_per_l3_cache > 1) + msr_clear_bit(MSR_RMID_SNC_CONFIG, 0); +} + +/* CPU models that support MSR_RMID_SNC_CONFIG */ +static const struct x86_cpu_id snc_cpu_ids[] __initconst = { + X86_MATCH_VFM(INTEL_ICELAKE_X, 0), + X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, 0), + X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, 0), + X86_MATCH_VFM(INTEL_GRANITERAPIDS_X, 0), + X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X, 0), + {} +}; + +/* + * There isn't a simple hardware bit that indicates whether a CPU is running + * in Sub-NUMA Cluster (SNC) mode. Infer the state by comparing the + * number of CPUs sharing the L3 cache with CPU0 to the number of CPUs in + * the same NUMA node as CPU0. + * It is not possible to accurately determine SNC state if the system is + * booted with a maxcpus=N parameter. That distorts the ratio of SNC nodes + * to L3 caches. It will be OK if system is booted with hyperthreading + * disabled (since this doesn't affect the ratio). + */ +static __init int snc_get_config(void) +{ + struct cacheinfo *ci = get_cpu_cacheinfo_level(0, RESCTRL_L3_CACHE); + const cpumask_t *node0_cpumask; + int cpus_per_node, cpus_per_l3; + int ret; + + if (!x86_match_cpu(snc_cpu_ids) || !ci) + return 1; + + cpus_read_lock(); + if (num_online_cpus() != num_present_cpus()) + pr_warn("Some CPUs offline, SNC detection may be incorrect\n"); + cpus_read_unlock(); + + node0_cpumask = cpumask_of_node(cpu_to_node(0)); + + cpus_per_node = cpumask_weight(node0_cpumask); + cpus_per_l3 = cpumask_weight(&ci->shared_cpu_map); + + if (!cpus_per_node || !cpus_per_l3) + return 1; + + ret = cpus_per_l3 / cpus_per_node; + + /* sanity check: Only valid results are 1, 2, 3, 4 */ + switch (ret) { + case 1: + break; + case 2 ... 4: + pr_info("Sub-NUMA Cluster mode detected with %d nodes per L3 cache\n", ret); + rdt_resources_all[RDT_RESOURCE_L3].r_resctrl.mon_scope = RESCTRL_L3_NODE; + break; + default: + pr_warn("Ignore improbable SNC node count %d\n", ret); + ret = 1; + break; + } + + return ret; +} + int __init rdt_get_mon_l3_config(struct rdt_resource *r) { unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset; @@ -1022,9 +1182,11 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r) unsigned int threshold; int ret; + snc_nodes_per_l3_cache = snc_get_config(); + resctrl_rmid_realloc_limit = boot_cpu_data.x86_cache_size * 1024; - hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale; - r->num_rmid = boot_cpu_data.x86_cache_max_rmid + 1; + hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale / snc_nodes_per_l3_cache; + r->num_rmid = (boot_cpu_data.x86_cache_max_rmid + 1) / snc_nodes_per_l3_cache; hw_res->mbm_width = MBM_CNTR_WIDTH_BASE; if (mbm_offset > 0 && mbm_offset <= MBM_CNTR_WIDTH_OFFSET_MAX) diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index aacf236dfe3b..e69489d48625 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -11,7 +11,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include #include #include #include @@ -221,7 +220,7 @@ static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr) int cpu; int ret; - for_each_cpu(cpu, &plr->d->cpu_mask) { + for_each_cpu(cpu, &plr->d->hdr.cpu_mask) { pm_req = kzalloc(sizeof(*pm_req), GFP_KERNEL); if (!pm_req) { rdt_last_cmd_puts("Failure to allocate memory for PM QoS\n"); @@ -292,12 +291,15 @@ static void pseudo_lock_region_clear(struct pseudo_lock_region *plr) */ static int pseudo_lock_region_init(struct pseudo_lock_region *plr) { - struct cpu_cacheinfo *ci; + enum resctrl_scope scope = plr->s->res->ctrl_scope; + struct cacheinfo *ci; int ret; - int i; + + if (WARN_ON_ONCE(scope != RESCTRL_L2_CACHE && scope != RESCTRL_L3_CACHE)) + return -ENODEV; /* Pick the first cpu we find that is associated with the cache. */ - plr->cpu = cpumask_first(&plr->d->cpu_mask); + plr->cpu = cpumask_first(&plr->d->hdr.cpu_mask); if (!cpu_online(plr->cpu)) { rdt_last_cmd_printf("CPU %u associated with cache not online\n", @@ -306,15 +308,11 @@ static int pseudo_lock_region_init(struct pseudo_lock_region *plr) goto out_region; } - ci = get_cpu_cacheinfo(plr->cpu); - - plr->size = rdtgroup_cbm_to_size(plr->s->res, plr->d, plr->cbm); - - for (i = 0; i < ci->num_leaves; i++) { - if (ci->info_list[i].level == plr->s->res->cache_level) { - plr->line_size = ci->info_list[i].coherency_line_size; - return 0; - } + ci = get_cpu_cacheinfo_level(plr->cpu, scope); + if (ci) { + plr->line_size = ci->coherency_line_size; + plr->size = rdtgroup_cbm_to_size(plr->s->res, plr->d, plr->cbm); + return 0; } ret = -1; @@ -810,7 +808,7 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp) * Return: true if @cbm overlaps with pseudo-locked region on @d, false * otherwise. */ -bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm) +bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm) { unsigned int cbm_len; unsigned long cbm_b; @@ -837,11 +835,11 @@ bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm * if it is not possible to test due to memory allocation issue, * false otherwise. */ -bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d) +bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d) { + struct rdt_ctrl_domain *d_i; cpumask_var_t cpu_with_psl; struct rdt_resource *r; - struct rdt_domain *d_i; bool ret = false; /* Walking r->domains, ensure it can't race with cpuhp */ @@ -855,10 +853,10 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d) * associated with them. */ for_each_alloc_capable_rdt_resource(r) { - list_for_each_entry(d_i, &r->domains, list) { + list_for_each_entry(d_i, &r->ctrl_domains, hdr.list) { if (d_i->plr) cpumask_or(cpu_with_psl, cpu_with_psl, - &d_i->cpu_mask); + &d_i->hdr.cpu_mask); } } @@ -866,7 +864,7 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d) * Next test if new pseudo-locked region would intersect with * existing region. */ - if (cpumask_intersects(&d->cpu_mask, cpu_with_psl)) + if (cpumask_intersects(&d->hdr.cpu_mask, cpu_with_psl)) ret = true; free_cpumask_var(cpu_with_psl); @@ -1198,7 +1196,7 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel) } plr->thread_done = 0; - cpu = cpumask_first(&plr->d->cpu_mask); + cpu = cpumask_first(&plr->d->hdr.cpu_mask); if (!cpu_online(cpu)) { ret = -ENODEV; goto out; @@ -1528,7 +1526,7 @@ static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma) * may be scheduled elsewhere and invalidate entries in the * pseudo-locked region. */ - if (!cpumask_subset(current->cpus_ptr, &plr->d->cpu_mask)) { + if (!cpumask_subset(current->cpus_ptr, &plr->d->hdr.cpu_mask)) { mutex_unlock(&rdtgroup_mutex); return -EINVAL; } diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 02f213f1c51c..d7163b764c62 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -12,7 +12,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include #include #include #include @@ -92,13 +91,13 @@ void rdt_last_cmd_printf(const char *fmt, ...) void rdt_staged_configs_clear(void) { + struct rdt_ctrl_domain *dom; struct rdt_resource *r; - struct rdt_domain *dom; lockdep_assert_held(&rdtgroup_mutex); for_each_alloc_capable_rdt_resource(r) { - list_for_each_entry(dom, &r->domains, list) + list_for_each_entry(dom, &r->ctrl_domains, hdr.list) memset(dom->staged_config, 0, sizeof(dom->staged_config)); } } @@ -317,7 +316,7 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of, rdt_last_cmd_puts("Cache domain offline\n"); ret = -ENODEV; } else { - mask = &rdtgrp->plr->d->cpu_mask; + mask = &rdtgrp->plr->d->hdr.cpu_mask; seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n", cpumask_pr_args(mask)); @@ -1012,7 +1011,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, unsigned long sw_shareable = 0, hw_shareable = 0; unsigned long exclusive = 0, pseudo_locked = 0; struct rdt_resource *r = s->res; - struct rdt_domain *dom; + struct rdt_ctrl_domain *dom; int i, hwb, swb, excl, psl; enum rdtgrp_mode mode; bool sep = false; @@ -1021,12 +1020,12 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, cpus_read_lock(); mutex_lock(&rdtgroup_mutex); hw_shareable = r->cache.shareable_bits; - list_for_each_entry(dom, &r->domains, list) { + list_for_each_entry(dom, &r->ctrl_domains, hdr.list) { if (sep) seq_putc(seq, ';'); sw_shareable = 0; exclusive = 0; - seq_printf(seq, "%d=", dom->id); + seq_printf(seq, "%d=", dom->hdr.id); for (i = 0; i < closids_supported(); i++) { if (!closid_allocated(i)) continue; @@ -1243,7 +1242,7 @@ static int rdt_has_sparse_bitmasks_show(struct kernfs_open_file *of, * * Return: false if CBM does not overlap, true if it does. */ -static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, +static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_ctrl_domain *d, unsigned long cbm, int closid, enum resctrl_conf_type type, bool exclusive) { @@ -1298,7 +1297,7 @@ static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d * * Return: true if CBM overlap detected, false if there is no overlap */ -bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_domain *d, +bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_ctrl_domain *d, unsigned long cbm, int closid, bool exclusive) { enum resctrl_conf_type peer_type = resctrl_peer_type(s->conf_type); @@ -1329,10 +1328,10 @@ bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_domain *d, static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) { int closid = rdtgrp->closid; + struct rdt_ctrl_domain *d; struct resctrl_schema *s; struct rdt_resource *r; bool has_cache = false; - struct rdt_domain *d; u32 ctrl; /* Walking r->domains, ensure it can't race with cpuhp */ @@ -1343,7 +1342,7 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) if (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA) continue; has_cache = true; - list_for_each_entry(d, &r->domains, list) { + list_for_each_entry(d, &r->ctrl_domains, hdr.list) { ctrl = resctrl_arch_get_config(r, d, closid, s->conf_type); if (rdtgroup_cbm_overlaps(s, d, ctrl, closid, false)) { @@ -1448,20 +1447,19 @@ out: * bitmap functions work correctly. */ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, - struct rdt_domain *d, unsigned long cbm) + struct rdt_ctrl_domain *d, unsigned long cbm) { - struct cpu_cacheinfo *ci; unsigned int size = 0; - int num_b, i; + struct cacheinfo *ci; + int num_b; + + if (WARN_ON_ONCE(r->ctrl_scope != RESCTRL_L2_CACHE && r->ctrl_scope != RESCTRL_L3_CACHE)) + return size; num_b = bitmap_weight(&cbm, r->cache.cbm_len); - ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask)); - for (i = 0; i < ci->num_leaves; i++) { - if (ci->info_list[i].level == r->cache_level) { - size = ci->info_list[i].size / r->cache.cbm_len * num_b; - break; - } - } + ci = get_cpu_cacheinfo_level(cpumask_any(&d->hdr.cpu_mask), r->ctrl_scope); + if (ci) + size = ci->size / r->cache.cbm_len * num_b; return size; } @@ -1477,9 +1475,9 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, { struct resctrl_schema *schema; enum resctrl_conf_type type; + struct rdt_ctrl_domain *d; struct rdtgroup *rdtgrp; struct rdt_resource *r; - struct rdt_domain *d; unsigned int size; int ret = 0; u32 closid; @@ -1503,7 +1501,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, size = rdtgroup_cbm_to_size(rdtgrp->plr->s->res, rdtgrp->plr->d, rdtgrp->plr->cbm); - seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size); + seq_printf(s, "%d=%u\n", rdtgrp->plr->d->hdr.id, size); } goto out; } @@ -1515,7 +1513,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, type = schema->conf_type; sep = false; seq_printf(s, "%*s:", max_name_width, schema->name); - list_for_each_entry(d, &r->domains, list) { + list_for_each_entry(d, &r->ctrl_domains, hdr.list) { if (sep) seq_putc(s, ';'); if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { @@ -1533,7 +1531,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, else size = rdtgroup_cbm_to_size(r, d, ctrl); } - seq_printf(s, "%d=%u", d->id, size); + seq_printf(s, "%d=%u", d->hdr.id, size); sep = true; } seq_putc(s, '\n'); @@ -1591,21 +1589,21 @@ static void mon_event_config_read(void *info) mon_info->mon_config = msrval & MAX_EVT_CONFIG_BITS; } -static void mondata_config_read(struct rdt_domain *d, struct mon_config_info *mon_info) +static void mondata_config_read(struct rdt_mon_domain *d, struct mon_config_info *mon_info) { - smp_call_function_any(&d->cpu_mask, mon_event_config_read, mon_info, 1); + smp_call_function_any(&d->hdr.cpu_mask, mon_event_config_read, mon_info, 1); } static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid) { struct mon_config_info mon_info = {0}; - struct rdt_domain *dom; + struct rdt_mon_domain *dom; bool sep = false; cpus_read_lock(); mutex_lock(&rdtgroup_mutex); - list_for_each_entry(dom, &r->domains, list) { + list_for_each_entry(dom, &r->mon_domains, hdr.list) { if (sep) seq_puts(s, ";"); @@ -1613,7 +1611,7 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid mon_info.evtid = evtid; mondata_config_read(dom, &mon_info); - seq_printf(s, "%d=0x%02x", dom->id, mon_info.mon_config); + seq_printf(s, "%d=0x%02x", dom->hdr.id, mon_info.mon_config); sep = true; } seq_puts(s, "\n"); @@ -1658,7 +1656,7 @@ static void mon_event_config_write(void *info) } static void mbm_config_write_domain(struct rdt_resource *r, - struct rdt_domain *d, u32 evtid, u32 val) + struct rdt_mon_domain *d, u32 evtid, u32 val) { struct mon_config_info mon_info = {0}; @@ -1679,7 +1677,7 @@ static void mbm_config_write_domain(struct rdt_resource *r, * are scoped at the domain level. Writing any of these MSRs * on one CPU is observed by all the CPUs in the domain. */ - smp_call_function_any(&d->cpu_mask, mon_event_config_write, + smp_call_function_any(&d->hdr.cpu_mask, mon_event_config_write, &mon_info, 1); /* @@ -1699,7 +1697,7 @@ static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid) struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); char *dom_str = NULL, *id_str; unsigned long dom_id, val; - struct rdt_domain *d; + struct rdt_mon_domain *d; /* Walking r->domains, ensure it can't race with cpuhp */ lockdep_assert_cpus_held(); @@ -1729,8 +1727,8 @@ next: return -EINVAL; } - list_for_each_entry(d, &r->domains, list) { - if (d->id == dom_id) { + list_for_each_entry(d, &r->mon_domains, hdr.list) { + if (d->hdr.id == dom_id) { mbm_config_write_domain(r, d, evtid, val); goto next; } @@ -2258,9 +2256,9 @@ static inline bool is_mba_linear(void) static int set_cache_qos_cfg(int level, bool enable) { void (*update)(void *arg); + struct rdt_ctrl_domain *d; struct rdt_resource *r_l; cpumask_var_t cpu_mask; - struct rdt_domain *d; int cpu; /* Walking r->domains, ensure it can't race with cpuhp */ @@ -2277,14 +2275,14 @@ static int set_cache_qos_cfg(int level, bool enable) return -ENOMEM; r_l = &rdt_resources_all[level].r_resctrl; - list_for_each_entry(d, &r_l->domains, list) { + list_for_each_entry(d, &r_l->ctrl_domains, hdr.list) { if (r_l->cache.arch_has_per_cpu_cfg) /* Pick all the CPUs in the domain instance */ - for_each_cpu(cpu, &d->cpu_mask) + for_each_cpu(cpu, &d->hdr.cpu_mask) cpumask_set_cpu(cpu, cpu_mask); else /* Pick one CPU from each domain instance to update MSR */ - cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); + cpumask_set_cpu(cpumask_any(&d->hdr.cpu_mask), cpu_mask); } /* Update QOS_CFG MSR on all the CPUs in cpu_mask */ @@ -2310,10 +2308,10 @@ void rdt_domain_reconfigure_cdp(struct rdt_resource *r) l3_qos_cfg_update(&hw_res->cdp_enabled); } -static int mba_sc_domain_allocate(struct rdt_resource *r, struct rdt_domain *d) +static int mba_sc_domain_allocate(struct rdt_resource *r, struct rdt_ctrl_domain *d) { u32 num_closid = resctrl_arch_get_num_closid(r); - int cpu = cpumask_any(&d->cpu_mask); + int cpu = cpumask_any(&d->hdr.cpu_mask); int i; d->mbps_val = kcalloc_node(num_closid, sizeof(*d->mbps_val), @@ -2328,7 +2326,7 @@ static int mba_sc_domain_allocate(struct rdt_resource *r, struct rdt_domain *d) } static void mba_sc_domain_destroy(struct rdt_resource *r, - struct rdt_domain *d) + struct rdt_ctrl_domain *d) { kfree(d->mbps_val); d->mbps_val = NULL; @@ -2336,14 +2334,18 @@ static void mba_sc_domain_destroy(struct rdt_resource *r, /* * MBA software controller is supported only if - * MBM is supported and MBA is in linear scale. + * MBM is supported and MBA is in linear scale, + * and the MBM monitor scope is the same as MBA + * control scope. */ static bool supports_mba_mbps(void) { + struct rdt_resource *rmbm = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl; return (is_mbm_local_enabled() && - r->alloc_capable && is_mba_linear()); + r->alloc_capable && is_mba_linear() && + r->ctrl_scope == rmbm->mon_scope); } /* @@ -2354,7 +2356,7 @@ static int set_mba_sc(bool mba_sc) { struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl; u32 num_closid = resctrl_arch_get_num_closid(r); - struct rdt_domain *d; + struct rdt_ctrl_domain *d; int i; if (!supports_mba_mbps() || mba_sc == is_mba_sc(r)) @@ -2362,7 +2364,7 @@ static int set_mba_sc(bool mba_sc) r->membw.mba_sc = mba_sc; - list_for_each_entry(d, &r->domains, list) { + list_for_each_entry(d, &r->ctrl_domains, hdr.list) { for (i = 0; i < num_closid; i++) d->mbps_val[i] = MBA_MAX_MBPS; } @@ -2626,7 +2628,7 @@ static int rdt_get_tree(struct fs_context *fc) { struct rdt_fs_context *ctx = rdt_fc2context(fc); unsigned long flags = RFTYPE_CTRL_BASE; - struct rdt_domain *dom; + struct rdt_mon_domain *dom; struct rdt_resource *r; int ret; @@ -2701,7 +2703,7 @@ static int rdt_get_tree(struct fs_context *fc) if (is_mbm_enabled()) { r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; - list_for_each_entry(dom, &r->domains, list) + list_for_each_entry(dom, &r->mon_domains, hdr.list) mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL, RESCTRL_PICK_ANY_CPU); } @@ -2751,6 +2753,7 @@ static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct rdt_fs_context *ctx = rdt_fc2context(fc); struct fs_parse_result result; + const char *msg; int opt; opt = fs_parse(fc, rdt_fs_parameters, param, &result); @@ -2765,8 +2768,9 @@ static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param) ctx->enable_cdpl2 = true; return 0; case Opt_mba_mbps: + msg = "mba_MBps requires local MBM and linear scale MBA at L3 scope"; if (!supports_mba_mbps()) - return -EINVAL; + return invalfc(fc, msg); ctx->enable_mba_mbps = true; return 0; case Opt_debug: @@ -2811,9 +2815,9 @@ static int rdt_init_fs_context(struct fs_context *fc) static int reset_all_ctrls(struct rdt_resource *r) { struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); - struct rdt_hw_domain *hw_dom; + struct rdt_hw_ctrl_domain *hw_dom; struct msr_param msr_param; - struct rdt_domain *d; + struct rdt_ctrl_domain *d; int i; /* Walking r->domains, ensure it can't race with cpuhp */ @@ -2825,16 +2829,16 @@ static int reset_all_ctrls(struct rdt_resource *r) /* * Disable resource control for this resource by setting all - * CBMs in all domains to the maximum mask value. Pick one CPU + * CBMs in all ctrl_domains to the maximum mask value. Pick one CPU * from each domain to update the MSRs below. */ - list_for_each_entry(d, &r->domains, list) { - hw_dom = resctrl_to_arch_dom(d); + list_for_each_entry(d, &r->ctrl_domains, hdr.list) { + hw_dom = resctrl_to_arch_ctrl_dom(d); for (i = 0; i < hw_res->num_closid; i++) hw_dom->ctrl_val[i] = r->default_ctrl; msr_param.dom = d; - smp_call_function_any(&d->cpu_mask, rdt_ctrl_update, &msr_param, 1); + smp_call_function_any(&d->hdr.cpu_mask, rdt_ctrl_update, &msr_param, 1); } return 0; @@ -3002,62 +3006,126 @@ static int mon_addfile(struct kernfs_node *parent_kn, const char *name, return ret; } +static void mon_rmdir_one_subdir(struct kernfs_node *pkn, char *name, char *subname) +{ + struct kernfs_node *kn; + + kn = kernfs_find_and_get(pkn, name); + if (!kn) + return; + kernfs_put(kn); + + if (kn->dir.subdirs <= 1) + kernfs_remove(kn); + else + kernfs_remove_by_name(kn, subname); +} + /* * Remove all subdirectories of mon_data of ctrl_mon groups - * and monitor groups with given domain id. + * and monitor groups for the given domain. + * Remove files and directories containing "sum" of domain data + * when last domain being summed is removed. */ static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, - unsigned int dom_id) + struct rdt_mon_domain *d) { struct rdtgroup *prgrp, *crgrp; + char subname[32]; + bool snc_mode; char name[32]; + snc_mode = r->mon_scope == RESCTRL_L3_NODE; + sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id); + if (snc_mode) + sprintf(subname, "mon_sub_%s_%02d", r->name, d->hdr.id); + list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { - sprintf(name, "mon_%s_%02d", r->name, dom_id); - kernfs_remove_by_name(prgrp->mon.mon_data_kn, name); + mon_rmdir_one_subdir(prgrp->mon.mon_data_kn, name, subname); list_for_each_entry(crgrp, &prgrp->mon.crdtgrp_list, mon.crdtgrp_list) - kernfs_remove_by_name(crgrp->mon.mon_data_kn, name); + mon_rmdir_one_subdir(crgrp->mon.mon_data_kn, name, subname); } } -static int mkdir_mondata_subdir(struct kernfs_node *parent_kn, - struct rdt_domain *d, - struct rdt_resource *r, struct rdtgroup *prgrp) +static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain *d, + struct rdt_resource *r, struct rdtgroup *prgrp, + bool do_sum) { + struct rmid_read rr = {0}; union mon_data_bits priv; - struct kernfs_node *kn; struct mon_evt *mevt; - struct rmid_read rr; - char name[32]; int ret; - sprintf(name, "mon_%s_%02d", r->name, d->id); - /* create the directory */ - kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp); - if (IS_ERR(kn)) - return PTR_ERR(kn); - - ret = rdtgroup_kn_set_ugid(kn); - if (ret) - goto out_destroy; - - if (WARN_ON(list_empty(&r->evt_list))) { - ret = -EPERM; - goto out_destroy; - } + if (WARN_ON(list_empty(&r->evt_list))) + return -EPERM; priv.u.rid = r->rid; - priv.u.domid = d->id; + priv.u.domid = do_sum ? d->ci->id : d->hdr.id; + priv.u.sum = do_sum; list_for_each_entry(mevt, &r->evt_list, list) { priv.u.evtid = mevt->evtid; ret = mon_addfile(kn, mevt->name, priv.priv); + if (ret) + return ret; + + if (!do_sum && is_mbm_event(mevt->evtid)) + mon_event_read(&rr, r, d, prgrp, &d->hdr.cpu_mask, mevt->evtid, true); + } + + return 0; +} + +static int mkdir_mondata_subdir(struct kernfs_node *parent_kn, + struct rdt_mon_domain *d, + struct rdt_resource *r, struct rdtgroup *prgrp) +{ + struct kernfs_node *kn, *ckn; + char name[32]; + bool snc_mode; + int ret = 0; + + lockdep_assert_held(&rdtgroup_mutex); + + snc_mode = r->mon_scope == RESCTRL_L3_NODE; + sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id); + kn = kernfs_find_and_get(parent_kn, name); + if (kn) { + /* + * rdtgroup_mutex will prevent this directory from being + * removed. No need to keep this hold. + */ + kernfs_put(kn); + } else { + kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp); + if (IS_ERR(kn)) + return PTR_ERR(kn); + + ret = rdtgroup_kn_set_ugid(kn); + if (ret) + goto out_destroy; + ret = mon_add_all_files(kn, d, r, prgrp, snc_mode); + if (ret) + goto out_destroy; + } + + if (snc_mode) { + sprintf(name, "mon_sub_%s_%02d", r->name, d->hdr.id); + ckn = kernfs_create_dir(kn, name, parent_kn->mode, prgrp); + if (IS_ERR(ckn)) { + ret = -EINVAL; + goto out_destroy; + } + + ret = rdtgroup_kn_set_ugid(ckn); if (ret) goto out_destroy; - if (is_mbm_event(mevt->evtid)) - mon_event_read(&rr, r, d, prgrp, mevt->evtid, true); + ret = mon_add_all_files(ckn, d, r, prgrp, false); + if (ret) + goto out_destroy; } + kernfs_activate(kn); return 0; @@ -3071,7 +3139,7 @@ out_destroy: * and "monitor" groups with given domain id. */ static void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, - struct rdt_domain *d) + struct rdt_mon_domain *d) { struct kernfs_node *parent_kn; struct rdtgroup *prgrp, *crgrp; @@ -3093,13 +3161,13 @@ static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn, struct rdt_resource *r, struct rdtgroup *prgrp) { - struct rdt_domain *dom; + struct rdt_mon_domain *dom; int ret; /* Walking r->domains, ensure it can't race with cpuhp */ lockdep_assert_cpus_held(); - list_for_each_entry(dom, &r->domains, list) { + list_for_each_entry(dom, &r->mon_domains, hdr.list) { ret = mkdir_mondata_subdir(parent_kn, dom, r, prgrp); if (ret) return ret; @@ -3198,7 +3266,7 @@ static u32 cbm_ensure_valid(u32 _val, struct rdt_resource *r) * Set the RDT domain up to start off with all usable allocations. That is, * all shareable and unused bits. All-zero CBM is invalid. */ -static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s, +static int __init_one_rdt_domain(struct rdt_ctrl_domain *d, struct resctrl_schema *s, u32 closid) { enum resctrl_conf_type peer_type = resctrl_peer_type(s->conf_type); @@ -3258,7 +3326,7 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s, */ tmp_cbm = cfg->new_ctrl; if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) < r->cache.min_cbm_bits) { - rdt_last_cmd_printf("No space on %s:%d\n", s->name, d->id); + rdt_last_cmd_printf("No space on %s:%d\n", s->name, d->hdr.id); return -ENOSPC; } cfg->have_new_ctrl = true; @@ -3278,10 +3346,10 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s, */ static int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid) { - struct rdt_domain *d; + struct rdt_ctrl_domain *d; int ret; - list_for_each_entry(d, &s->res->domains, list) { + list_for_each_entry(d, &s->res->ctrl_domains, hdr.list) { ret = __init_one_rdt_domain(d, s, closid); if (ret < 0) return ret; @@ -3294,9 +3362,9 @@ static int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid) static void rdtgroup_init_mba(struct rdt_resource *r, u32 closid) { struct resctrl_staged_config *cfg; - struct rdt_domain *d; + struct rdt_ctrl_domain *d; - list_for_each_entry(d, &r->domains, list) { + list_for_each_entry(d, &r->ctrl_domains, hdr.list) { if (is_mba_sc(r)) { d->mbps_val[closid] = MBA_MAX_MBPS; continue; @@ -3920,29 +3988,33 @@ static void __init rdtgroup_setup_default(void) mutex_unlock(&rdtgroup_mutex); } -static void domain_destroy_mon_state(struct rdt_domain *d) +static void domain_destroy_mon_state(struct rdt_mon_domain *d) { bitmap_free(d->rmid_busy_llc); kfree(d->mbm_total); kfree(d->mbm_local); } -void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d) +void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d) { mutex_lock(&rdtgroup_mutex); if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) mba_sc_domain_destroy(r, d); - if (!r->mon_capable) - goto out_unlock; + mutex_unlock(&rdtgroup_mutex); +} + +void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d) +{ + mutex_lock(&rdtgroup_mutex); /* * If resctrl is mounted, remove all the * per domain monitor data directories. */ if (resctrl_mounted && resctrl_arch_mon_capable()) - rmdir_mondata_subdir_allrdtgrp(r, d->id); + rmdir_mondata_subdir_allrdtgrp(r, d); if (is_mbm_enabled()) cancel_delayed_work(&d->mbm_over); @@ -3961,11 +4033,10 @@ void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d) domain_destroy_mon_state(d); -out_unlock: mutex_unlock(&rdtgroup_mutex); } -static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) +static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_domain *d) { u32 idx_limit = resctrl_arch_system_num_rmid_idx(); size_t tsize; @@ -3996,7 +4067,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) return 0; } -int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d) +int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d) { int err = 0; @@ -4005,11 +4076,18 @@ int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d) if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) { /* RDT_RESOURCE_MBA is never mon_capable */ err = mba_sc_domain_allocate(r, d); - goto out_unlock; } - if (!r->mon_capable) - goto out_unlock; + mutex_unlock(&rdtgroup_mutex); + + return err; +} + +int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d) +{ + int err; + + mutex_lock(&rdtgroup_mutex); err = domain_setup_mon_state(r, d); if (err) @@ -4060,8 +4138,8 @@ static void clear_childcpus(struct rdtgroup *r, unsigned int cpu) void resctrl_offline_cpu(unsigned int cpu) { struct rdt_resource *l3 = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + struct rdt_mon_domain *d; struct rdtgroup *rdtgrp; - struct rdt_domain *d; mutex_lock(&rdtgroup_mutex); list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) { @@ -4074,7 +4152,7 @@ void resctrl_offline_cpu(unsigned int cpu) if (!l3->mon_capable) goto out_unlock; - d = get_domain_from_cpu(cpu, l3); + d = get_mon_domain_from_cpu(cpu, l3); if (d) { if (is_mbm_enabled() && cpu == d->mbm_work_cpu) { cancel_delayed_work(&d->mbm_over); diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 11f83d07925e..00189cdeb775 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -41,80 +41,97 @@ #define CPUID_VMWARE_INFO_LEAF 0x40000000 #define CPUID_VMWARE_FEATURES_LEAF 0x40000010 -#define CPUID_VMWARE_FEATURES_ECX_VMMCALL BIT(0) -#define CPUID_VMWARE_FEATURES_ECX_VMCALL BIT(1) -#define VMWARE_HYPERVISOR_MAGIC 0x564D5868 - -#define VMWARE_CMD_GETVERSION 10 -#define VMWARE_CMD_GETHZ 45 -#define VMWARE_CMD_GETVCPU_INFO 68 -#define VMWARE_CMD_LEGACY_X2APIC 3 -#define VMWARE_CMD_VCPU_RESERVED 31 -#define VMWARE_CMD_STEALCLOCK 91 +#define GETVCPU_INFO_LEGACY_X2APIC BIT(3) +#define GETVCPU_INFO_VCPU_RESERVED BIT(31) #define STEALCLOCK_NOT_AVAILABLE (-1) #define STEALCLOCK_DISABLED 0 #define STEALCLOCK_ENABLED 1 -#define VMWARE_PORT(cmd, eax, ebx, ecx, edx) \ - __asm__("inl (%%dx), %%eax" : \ - "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) : \ - "a"(VMWARE_HYPERVISOR_MAGIC), \ - "c"(VMWARE_CMD_##cmd), \ - "d"(VMWARE_HYPERVISOR_PORT), "b"(UINT_MAX) : \ - "memory") - -#define VMWARE_VMCALL(cmd, eax, ebx, ecx, edx) \ - __asm__("vmcall" : \ - "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) : \ - "a"(VMWARE_HYPERVISOR_MAGIC), \ - "c"(VMWARE_CMD_##cmd), \ - "d"(0), "b"(UINT_MAX) : \ - "memory") - -#define VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx) \ - __asm__("vmmcall" : \ - "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) : \ - "a"(VMWARE_HYPERVISOR_MAGIC), \ - "c"(VMWARE_CMD_##cmd), \ - "d"(0), "b"(UINT_MAX) : \ - "memory") - -#define VMWARE_CMD(cmd, eax, ebx, ecx, edx) do { \ - switch (vmware_hypercall_mode) { \ - case CPUID_VMWARE_FEATURES_ECX_VMCALL: \ - VMWARE_VMCALL(cmd, eax, ebx, ecx, edx); \ - break; \ - case CPUID_VMWARE_FEATURES_ECX_VMMCALL: \ - VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx); \ - break; \ - default: \ - VMWARE_PORT(cmd, eax, ebx, ecx, edx); \ - break; \ - } \ - } while (0) - struct vmware_steal_time { union { - uint64_t clock; /* stolen time counter in units of vtsc */ + u64 clock; /* stolen time counter in units of vtsc */ struct { /* only for little-endian */ - uint32_t clock_low; - uint32_t clock_high; + u32 clock_low; + u32 clock_high; }; }; - uint64_t reserved[7]; + u64 reserved[7]; }; static unsigned long vmware_tsc_khz __ro_after_init; static u8 vmware_hypercall_mode __ro_after_init; +unsigned long vmware_hypercall_slow(unsigned long cmd, + unsigned long in1, unsigned long in3, + unsigned long in4, unsigned long in5, + u32 *out1, u32 *out2, u32 *out3, + u32 *out4, u32 *out5) +{ + unsigned long out0, rbx, rcx, rdx, rsi, rdi; + + switch (vmware_hypercall_mode) { + case CPUID_VMWARE_FEATURES_ECX_VMCALL: + asm_inline volatile ("vmcall" + : "=a" (out0), "=b" (rbx), "=c" (rcx), + "=d" (rdx), "=S" (rsi), "=D" (rdi) + : "a" (VMWARE_HYPERVISOR_MAGIC), + "b" (in1), + "c" (cmd), + "d" (in3), + "S" (in4), + "D" (in5) + : "cc", "memory"); + break; + case CPUID_VMWARE_FEATURES_ECX_VMMCALL: + asm_inline volatile ("vmmcall" + : "=a" (out0), "=b" (rbx), "=c" (rcx), + "=d" (rdx), "=S" (rsi), "=D" (rdi) + : "a" (VMWARE_HYPERVISOR_MAGIC), + "b" (in1), + "c" (cmd), + "d" (in3), + "S" (in4), + "D" (in5) + : "cc", "memory"); + break; + default: + asm_inline volatile ("movw %[port], %%dx; inl (%%dx), %%eax" + : "=a" (out0), "=b" (rbx), "=c" (rcx), + "=d" (rdx), "=S" (rsi), "=D" (rdi) + : [port] "i" (VMWARE_HYPERVISOR_PORT), + "a" (VMWARE_HYPERVISOR_MAGIC), + "b" (in1), + "c" (cmd), + "d" (in3), + "S" (in4), + "D" (in5) + : "cc", "memory"); + break; + } + + if (out1) + *out1 = rbx; + if (out2) + *out2 = rcx; + if (out3) + *out3 = rdx; + if (out4) + *out4 = rsi; + if (out5) + *out5 = rdi; + + return out0; +} + static inline int __vmware_platform(void) { - uint32_t eax, ebx, ecx, edx; - VMWARE_CMD(GETVERSION, eax, ebx, ecx, edx); - return eax != (uint32_t)-1 && ebx == VMWARE_HYPERVISOR_MAGIC; + u32 eax, ebx, ecx; + + eax = vmware_hypercall3(VMWARE_CMD_GETVERSION, 0, &ebx, &ecx); + return eax != UINT_MAX && ebx == VMWARE_HYPERVISOR_MAGIC; } static unsigned long vmware_get_tsc_khz(void) @@ -166,21 +183,12 @@ static void __init vmware_cyc2ns_setup(void) pr_info("using clock offset of %llu ns\n", d->cyc2ns_offset); } -static int vmware_cmd_stealclock(uint32_t arg1, uint32_t arg2) +static int vmware_cmd_stealclock(u32 addr_hi, u32 addr_lo) { - uint32_t result, info; + u32 info; - asm volatile (VMWARE_HYPERCALL : - "=a"(result), - "=c"(info) : - "a"(VMWARE_HYPERVISOR_MAGIC), - "b"(0), - "c"(VMWARE_CMD_STEALCLOCK), - "d"(0), - "S"(arg1), - "D"(arg2) : - "memory"); - return result; + return vmware_hypercall5(VMWARE_CMD_STEALCLOCK, 0, 0, addr_hi, addr_lo, + &info); } static bool stealclock_enable(phys_addr_t pa) @@ -215,15 +223,15 @@ static bool vmware_is_stealclock_available(void) * Return: * The steal clock reading in ns. */ -static uint64_t vmware_steal_clock(int cpu) +static u64 vmware_steal_clock(int cpu) { struct vmware_steal_time *steal = &per_cpu(vmw_steal_time, cpu); - uint64_t clock; + u64 clock; if (IS_ENABLED(CONFIG_64BIT)) clock = READ_ONCE(steal->clock); else { - uint32_t initial_high, low, high; + u32 initial_high, low, high; do { initial_high = READ_ONCE(steal->clock_high); @@ -235,7 +243,7 @@ static uint64_t vmware_steal_clock(int cpu) high = READ_ONCE(steal->clock_high); } while (initial_high != high); - clock = ((uint64_t)high << 32) | low; + clock = ((u64)high << 32) | low; } return mul_u64_u32_shr(clock, vmware_cyc2ns.cyc2ns_mul, @@ -389,13 +397,13 @@ static void __init vmware_set_capabilities(void) static void __init vmware_platform_setup(void) { - uint32_t eax, ebx, ecx, edx; - uint64_t lpj, tsc_khz; + u32 eax, ebx, ecx; + u64 lpj, tsc_khz; - VMWARE_CMD(GETHZ, eax, ebx, ecx, edx); + eax = vmware_hypercall3(VMWARE_CMD_GETHZ, UINT_MAX, &ebx, &ecx); if (ebx != UINT_MAX) { - lpj = tsc_khz = eax | (((uint64_t)ebx) << 32); + lpj = tsc_khz = eax | (((u64)ebx) << 32); do_div(tsc_khz, 1000); WARN_ON(tsc_khz >> 32); pr_info("TSC freq read from hypervisor : %lu.%03lu MHz\n", @@ -446,7 +454,7 @@ static u8 __init vmware_select_hypercall(void) * If !boot_cpu_has(X86_FEATURE_HYPERVISOR), vmware_hypercall_mode * intentionally defaults to 0. */ -static uint32_t __init vmware_platform(void) +static u32 __init vmware_platform(void) { if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { unsigned int eax; @@ -474,12 +482,65 @@ static uint32_t __init vmware_platform(void) /* Checks if hypervisor supports x2apic without VT-D interrupt remapping. */ static bool __init vmware_legacy_x2apic_available(void) { - uint32_t eax, ebx, ecx, edx; - VMWARE_CMD(GETVCPU_INFO, eax, ebx, ecx, edx); - return !(eax & BIT(VMWARE_CMD_VCPU_RESERVED)) && - (eax & BIT(VMWARE_CMD_LEGACY_X2APIC)); + u32 eax; + + eax = vmware_hypercall1(VMWARE_CMD_GETVCPU_INFO, 0); + return !(eax & GETVCPU_INFO_VCPU_RESERVED) && + (eax & GETVCPU_INFO_LEGACY_X2APIC); } +#ifdef CONFIG_INTEL_TDX_GUEST +/* + * TDCALL[TDG.VP.VMCALL] uses %rax (arg0) and %rcx (arg2). Therefore, + * we remap those registers to %r12 and %r13, respectively. + */ +unsigned long vmware_tdx_hypercall(unsigned long cmd, + unsigned long in1, unsigned long in3, + unsigned long in4, unsigned long in5, + u32 *out1, u32 *out2, u32 *out3, + u32 *out4, u32 *out5) +{ + struct tdx_module_args args = {}; + + if (!hypervisor_is_type(X86_HYPER_VMWARE)) { + pr_warn_once("Incorrect usage\n"); + return ULONG_MAX; + } + + if (cmd & ~VMWARE_CMD_MASK) { + pr_warn_once("Out of range command %lx\n", cmd); + return ULONG_MAX; + } + + args.rbx = in1; + args.rdx = in3; + args.rsi = in4; + args.rdi = in5; + args.r10 = VMWARE_TDX_VENDOR_LEAF; + args.r11 = VMWARE_TDX_HCALL_FUNC; + args.r12 = VMWARE_HYPERVISOR_MAGIC; + args.r13 = cmd; + /* CPL */ + args.r15 = 0; + + __tdx_hypercall(&args); + + if (out1) + *out1 = args.rbx; + if (out2) + *out2 = args.r13; + if (out3) + *out3 = args.rdx; + if (out4) + *out4 = args.rsi; + if (out5) + *out5 = args.rdi; + + return args.r12; +} +EXPORT_SYMBOL_GPL(vmware_tdx_hypercall); +#endif + #ifdef CONFIG_AMD_MEM_ENCRYPT static void vmware_sev_es_hcall_prepare(struct ghcb *ghcb, struct pt_regs *regs) diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index f06501445cd9..340af8155658 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -128,6 +128,18 @@ void native_machine_crash_shutdown(struct pt_regs *regs) #ifdef CONFIG_HPET_TIMER hpet_disable(); #endif + + /* + * Non-crash kexec calls enc_kexec_begin() while scheduling is still + * active. This allows the callback to wait until all in-flight + * shared<->private conversions are complete. In a crash scenario, + * enc_kexec_begin() gets called after all but one CPU have been shut + * down and interrupts have been disabled. This allows the callback to + * detect a race with the conversion and report it. + */ + x86_platform.guest.enc_kexec_begin(); + x86_platform.guest.enc_kexec_finish(); + crash_save_cpu(regs, safe_smp_processor_id()); } diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 8e3c53b4d070..64280879c68c 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -83,7 +83,7 @@ static int x86_of_pci_irq_enable(struct pci_dev *dev) ret = pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin); if (ret) - return ret; + return pcibios_err_to_errno(ret); if (!pin) return 0; diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 68b09f718f10..4893d30ce438 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -828,7 +828,7 @@ u64 __init e820__memblock_alloc_reserved(u64 size, u64 align) /* * Find the highest page frame number we have available */ -static unsigned long __init e820_end_pfn(unsigned long limit_pfn, enum e820_type type) +static unsigned long __init e820__end_ram_pfn(unsigned long limit_pfn) { int i; unsigned long last_pfn = 0; @@ -839,7 +839,8 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn, enum e820_type unsigned long start_pfn; unsigned long end_pfn; - if (entry->type != type) + if (entry->type != E820_TYPE_RAM && + entry->type != E820_TYPE_ACPI) continue; start_pfn = entry->addr >> PAGE_SHIFT; @@ -865,12 +866,12 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn, enum e820_type unsigned long __init e820__end_of_ram_pfn(void) { - return e820_end_pfn(MAX_ARCH_PFN, E820_TYPE_RAM); + return e820__end_ram_pfn(MAX_ARCH_PFN); } unsigned long __init e820__end_of_low_ram_pfn(void) { - return e820_end_pfn(1UL << (32 - PAGE_SHIFT), E820_TYPE_RAM); + return e820__end_ram_pfn(1UL << (32 - PAGE_SHIFT)); } static void __init early_panic(char *msg) diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h index 05df04f39628..2ee0b9c53dcc 100644 --- a/arch/x86/kernel/fpu/xstate.h +++ b/arch/x86/kernel/fpu/xstate.h @@ -106,21 +106,17 @@ static inline u64 xfeatures_mask_independent(void) * Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT * supports modified optimization which is not supported by XSAVE. * - * We use XSAVE as a fallback. - * - * The 661 label is defined in the ALTERNATIVE* macros as the address of the - * original instruction which gets replaced. We need to use it here as the - * address of the instruction where we might get an exception at. + * Use XSAVE as a fallback. */ #define XSTATE_XSAVE(st, lmask, hmask, err) \ - asm volatile(ALTERNATIVE_3(XSAVE, \ + asm volatile("1: " ALTERNATIVE_3(XSAVE, \ XSAVEOPT, X86_FEATURE_XSAVEOPT, \ XSAVEC, X86_FEATURE_XSAVEC, \ XSAVES, X86_FEATURE_XSAVES) \ "\n" \ "xor %[err], %[err]\n" \ "3:\n" \ - _ASM_EXTABLE_TYPE_REG(661b, 3b, EX_TYPE_EFAULT_REG, %[err]) \ + _ASM_EXTABLE_TYPE_REG(1b, 3b, EX_TYPE_EFAULT_REG, %[err]) \ : [err] "=r" (err) \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") @@ -130,11 +126,11 @@ static inline u64 xfeatures_mask_independent(void) * XSAVE area format. */ #define XSTATE_XRESTORE(st, lmask, hmask) \ - asm volatile(ALTERNATIVE(XRSTOR, \ + asm volatile("1: " ALTERNATIVE(XRSTOR, \ XRSTORS, X86_FEATURE_XSAVES) \ "\n" \ "3:\n" \ - _ASM_EXTABLE_TYPE(661b, 3b, EX_TYPE_FPU_RESTORE) \ + _ASM_EXTABLE_TYPE(1b, 3b, EX_TYPE_FPU_RESTORE) \ : \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index b8441147eb5e..f63f8fd00a91 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -835,6 +835,13 @@ void __noreturn stop_this_cpu(void *dummy) */ cpumask_clear_cpu(cpu, &cpus_stop_mask); +#ifdef CONFIG_SMP + if (smp_ops.stop_this_cpu) { + smp_ops.stop_this_cpu(); + unreachable(); + } +#endif + for (;;) { /* * Use native_halt() so that memory contents don't change diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index f3130f762784..0e0a4cf6b5eb 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -716,6 +717,14 @@ static void native_machine_emergency_restart(void) void native_machine_shutdown(void) { + /* + * Call enc_kexec_begin() while all CPUs are still active and + * interrupts are enabled. This will allow all in-flight memory + * conversions to finish cleanly. + */ + if (kexec_in_progress) + x86_platform.guest.enc_kexec_begin(); + /* Stop the cpus and apics */ #ifdef CONFIG_X86_IO_APIC /* @@ -752,6 +761,9 @@ void native_machine_shutdown(void) #ifdef CONFIG_X86_64 x86_platform.iommu_shutdown(); #endif + + if (kexec_in_progress) + x86_platform.guest.enc_kexec_finish(); } static void __machine_emergency_restart(int emergency) @@ -868,6 +880,12 @@ static int crash_nmi_callback(unsigned int val, struct pt_regs *regs) cpu_emergency_disable_virtualization(); atomic_dec(&waiting_for_crash_ipi); + + if (smp_ops.stop_this_cpu) { + smp_ops.stop_this_cpu(); + unreachable(); + } + /* Assume hlt works */ halt(); for (;;) diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index 56cab1bb25f5..042c9a0334e9 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -5,6 +5,8 @@ */ #include +#include +#include #include #include #include @@ -145,16 +147,15 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) * Set cr4 to a known state: * - physical address extension enabled * - 5-level paging, if it was enabled before + * - Machine check exception on TDX guest, if it was enabled before. + * Clearing MCE might not be allowed in TDX guests, depending on setup. + * + * Use R13 that contains the original CR4 value, read in relocate_kernel(). + * PAE is always set in the original CR4. */ - movl $X86_CR4_PAE, %eax - testq $X86_CR4_LA57, %r13 - jz 1f - orl $X86_CR4_LA57, %eax -1: - movq %rax, %cr4 - - jmp 1f -1: + andl $(X86_CR4_PAE | X86_CR4_LA57), %r13d + ALTERNATIVE "", __stringify(orl $X86_CR4_MCE, %r13d), X86_FEATURE_TDX_GUEST + movq %r13, %cr4 /* Flush the TLB (needed?) */ movq %r9, %cr3 @@ -165,9 +166,9 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) * used by kexec. Flush the caches before copying the kernel. */ testq %r12, %r12 - jz 1f + jz .Lsme_off wbinvd -1: +.Lsme_off: movq %rcx, %r11 call swap_pages @@ -187,7 +188,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) */ testq %r11, %r11 - jnz 1f + jnz .Lrelocate xorl %eax, %eax xorl %ebx, %ebx xorl %ecx, %ecx @@ -208,7 +209,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) ret int3 -1: +.Lrelocate: popq %rdx leaq PAGE_SIZE(%r10), %rsp ANNOTATE_RETPOLINE_SAFE diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 05c5aa951da7..728927e4ba51 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -165,6 +165,7 @@ unsigned long saved_video_mode; static char __initdata command_line[COMMAND_LINE_SIZE]; #ifdef CONFIG_CMDLINE_BOOL static char __initdata builtin_cmdline[COMMAND_LINE_SIZE] = CONFIG_CMDLINE; +bool builtin_cmdline_added __ro_after_init; #endif #if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE) @@ -765,6 +766,7 @@ void __init setup_arch(char **cmdline_p) strscpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); } #endif + builtin_cmdline_added = true; #endif strscpy(command_line, boot_command_line, COMMAND_LINE_SIZE); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index d5dc5a92635a..82b128d3f309 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -134,10 +134,12 @@ struct x86_cpuinit_ops x86_cpuinit = { static void default_nmi_init(void) { }; -static bool enc_status_change_prepare_noop(unsigned long vaddr, int npages, bool enc) { return true; } -static bool enc_status_change_finish_noop(unsigned long vaddr, int npages, bool enc) { return true; } +static int enc_status_change_prepare_noop(unsigned long vaddr, int npages, bool enc) { return 0; } +static int enc_status_change_finish_noop(unsigned long vaddr, int npages, bool enc) { return 0; } static bool enc_tlb_flush_required_noop(bool enc) { return false; } static bool enc_cache_flush_required_noop(void) { return false; } +static void enc_kexec_begin_noop(void) {} +static void enc_kexec_finish_noop(void) {} static bool is_private_mmio_noop(u64 addr) {return false; } struct x86_platform_ops x86_platform __ro_after_init = { @@ -161,6 +163,8 @@ struct x86_platform_ops x86_platform __ro_after_init = { .enc_status_change_finish = enc_status_change_finish_noop, .enc_tlb_flush_required = enc_tlb_flush_required_noop, .enc_cache_flush_required = enc_cache_flush_required_noop, + .enc_kexec_begin = enc_kexec_begin_noop, + .enc_kexec_finish = enc_kexec_finish_noop, }, }; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 5d4c86133453..c8cc578646d0 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -1069,7 +1069,7 @@ static __always_inline u8 test_cc(unsigned int condition, unsigned long flags) flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF; asm("push %[flags]; popf; " CALL_NOSPEC - : "=a"(rc) : [thunk_target]"r"(fop), [flags]"r"(flags)); + : "=a"(rc), ASM_CALL_CONSTRAINT : [thunk_target]"r"(fop), [flags]"r"(flags)); return rc; } diff --git a/arch/x86/lib/cmdline.c b/arch/x86/lib/cmdline.c index 80570eb3c89b..384da1fdd5c6 100644 --- a/arch/x86/lib/cmdline.c +++ b/arch/x86/lib/cmdline.c @@ -6,8 +6,10 @@ #include #include #include + #include #include +#include static inline int myisspace(u8 c) { @@ -205,12 +207,18 @@ __cmdline_find_option(const char *cmdline, int max_cmdline_size, int cmdline_find_option_bool(const char *cmdline, const char *option) { + if (IS_ENABLED(CONFIG_CMDLINE_BOOL)) + WARN_ON_ONCE(!builtin_cmdline_added); + return __cmdline_find_option_bool(cmdline, COMMAND_LINE_SIZE, option); } int cmdline_find_option(const char *cmdline, const char *option, char *buffer, int bufsize) { + if (IS_ENABLED(CONFIG_CMDLINE_BOOL)) + WARN_ON_ONCE(!builtin_cmdline_added); + return __cmdline_find_option(cmdline, COMMAND_LINE_SIZE, option, buffer, bufsize); } diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index a1cb3a4e6742..a314622aa093 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -44,21 +44,23 @@ or %rdx, %rax .else cmp $TASK_SIZE_MAX-\size+1, %eax -.if \size != 8 jae .Lbad_get_user -.else - jae .Lbad_get_user_8 -.endif sbb %edx, %edx /* array_index_mask_nospec() */ and %edx, %eax .endif .endm +.macro UACCESS op src dst +1: \op \src,\dst + _ASM_EXTABLE_UA(1b, __get_user_handle_exception) +.endm + + .text SYM_FUNC_START(__get_user_1) check_range size=1 ASM_STAC -1: movzbl (%_ASM_AX),%edx + UACCESS movzbl (%_ASM_AX),%edx xor %eax,%eax ASM_CLAC RET @@ -68,7 +70,7 @@ EXPORT_SYMBOL(__get_user_1) SYM_FUNC_START(__get_user_2) check_range size=2 ASM_STAC -2: movzwl (%_ASM_AX),%edx + UACCESS movzwl (%_ASM_AX),%edx xor %eax,%eax ASM_CLAC RET @@ -78,7 +80,7 @@ EXPORT_SYMBOL(__get_user_2) SYM_FUNC_START(__get_user_4) check_range size=4 ASM_STAC -3: movl (%_ASM_AX),%edx + UACCESS movl (%_ASM_AX),%edx xor %eax,%eax ASM_CLAC RET @@ -89,10 +91,11 @@ SYM_FUNC_START(__get_user_8) check_range size=8 ASM_STAC #ifdef CONFIG_X86_64 -4: movq (%_ASM_AX),%rdx + UACCESS movq (%_ASM_AX),%rdx #else -4: movl (%_ASM_AX),%edx -5: movl 4(%_ASM_AX),%ecx + xor %ecx,%ecx + UACCESS movl (%_ASM_AX),%edx + UACCESS movl 4(%_ASM_AX),%ecx #endif xor %eax,%eax ASM_CLAC @@ -104,7 +107,7 @@ EXPORT_SYMBOL(__get_user_8) SYM_FUNC_START(__get_user_nocheck_1) ASM_STAC ASM_BARRIER_NOSPEC -6: movzbl (%_ASM_AX),%edx + UACCESS movzbl (%_ASM_AX),%edx xor %eax,%eax ASM_CLAC RET @@ -114,7 +117,7 @@ EXPORT_SYMBOL(__get_user_nocheck_1) SYM_FUNC_START(__get_user_nocheck_2) ASM_STAC ASM_BARRIER_NOSPEC -7: movzwl (%_ASM_AX),%edx + UACCESS movzwl (%_ASM_AX),%edx xor %eax,%eax ASM_CLAC RET @@ -124,7 +127,7 @@ EXPORT_SYMBOL(__get_user_nocheck_2) SYM_FUNC_START(__get_user_nocheck_4) ASM_STAC ASM_BARRIER_NOSPEC -8: movl (%_ASM_AX),%edx + UACCESS movl (%_ASM_AX),%edx xor %eax,%eax ASM_CLAC RET @@ -135,10 +138,11 @@ SYM_FUNC_START(__get_user_nocheck_8) ASM_STAC ASM_BARRIER_NOSPEC #ifdef CONFIG_X86_64 -9: movq (%_ASM_AX),%rdx + UACCESS movq (%_ASM_AX),%rdx #else -9: movl (%_ASM_AX),%edx -10: movl 4(%_ASM_AX),%ecx + xor %ecx,%ecx + UACCESS movl (%_ASM_AX),%edx + UACCESS movl 4(%_ASM_AX),%ecx #endif xor %eax,%eax ASM_CLAC @@ -154,36 +158,3 @@ SYM_CODE_START_LOCAL(__get_user_handle_exception) mov $(-EFAULT),%_ASM_AX RET SYM_CODE_END(__get_user_handle_exception) - -#ifdef CONFIG_X86_32 -SYM_CODE_START_LOCAL(__get_user_8_handle_exception) - ASM_CLAC -.Lbad_get_user_8: - xor %edx,%edx - xor %ecx,%ecx - mov $(-EFAULT),%_ASM_AX - RET -SYM_CODE_END(__get_user_8_handle_exception) -#endif - -/* get_user */ - _ASM_EXTABLE_UA(1b, __get_user_handle_exception) - _ASM_EXTABLE_UA(2b, __get_user_handle_exception) - _ASM_EXTABLE_UA(3b, __get_user_handle_exception) -#ifdef CONFIG_X86_64 - _ASM_EXTABLE_UA(4b, __get_user_handle_exception) -#else - _ASM_EXTABLE_UA(4b, __get_user_8_handle_exception) - _ASM_EXTABLE_UA(5b, __get_user_8_handle_exception) -#endif - -/* __get_user */ - _ASM_EXTABLE_UA(6b, __get_user_handle_exception) - _ASM_EXTABLE_UA(7b, __get_user_handle_exception) - _ASM_EXTABLE_UA(8b, __get_user_handle_exception) -#ifdef CONFIG_X86_64 - _ASM_EXTABLE_UA(9b, __get_user_handle_exception) -#else - _ASM_EXTABLE_UA(9b, __get_user_8_handle_exception) - _ASM_EXTABLE_UA(10b, __get_user_8_handle_exception) -#endif diff --git a/arch/x86/lib/iomem.c b/arch/x86/lib/iomem.c index e0411a3774d4..5eecb45d05d5 100644 --- a/arch/x86/lib/iomem.c +++ b/arch/x86/lib/iomem.c @@ -25,6 +25,9 @@ static __always_inline void rep_movs(void *to, const void *from, size_t n) static void string_memcpy_fromio(void *to, const volatile void __iomem *from, size_t n) { + const void *orig_to = to; + const size_t orig_n = n; + if (unlikely(!n)) return; @@ -39,7 +42,7 @@ static void string_memcpy_fromio(void *to, const volatile void __iomem *from, si } rep_movs(to, (const void *)from, n); /* KMSAN must treat values read from devices as initialized. */ - kmsan_unpoison_memory(to, n); + kmsan_unpoison_memory(orig_to, orig_n); } static void string_memcpy_toio(volatile void __iomem *to, const void *from, size_t n) diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c index 968d7005f4a7..c45127265f2f 100644 --- a/arch/x86/mm/ident_map.c +++ b/arch/x86/mm/ident_map.c @@ -4,6 +4,79 @@ * included by both the compressed kernel and the regular kernel. */ +static void free_pte(struct x86_mapping_info *info, pmd_t *pmd) +{ + pte_t *pte = pte_offset_kernel(pmd, 0); + + info->free_pgt_page(pte, info->context); +} + +static void free_pmd(struct x86_mapping_info *info, pud_t *pud) +{ + pmd_t *pmd = pmd_offset(pud, 0); + int i; + + for (i = 0; i < PTRS_PER_PMD; i++) { + if (!pmd_present(pmd[i])) + continue; + + if (pmd_leaf(pmd[i])) + continue; + + free_pte(info, &pmd[i]); + } + + info->free_pgt_page(pmd, info->context); +} + +static void free_pud(struct x86_mapping_info *info, p4d_t *p4d) +{ + pud_t *pud = pud_offset(p4d, 0); + int i; + + for (i = 0; i < PTRS_PER_PUD; i++) { + if (!pud_present(pud[i])) + continue; + + if (pud_leaf(pud[i])) + continue; + + free_pmd(info, &pud[i]); + } + + info->free_pgt_page(pud, info->context); +} + +static void free_p4d(struct x86_mapping_info *info, pgd_t *pgd) +{ + p4d_t *p4d = p4d_offset(pgd, 0); + int i; + + for (i = 0; i < PTRS_PER_P4D; i++) { + if (!p4d_present(p4d[i])) + continue; + + free_pud(info, &p4d[i]); + } + + if (pgtable_l5_enabled()) + info->free_pgt_page(p4d, info->context); +} + +void kernel_ident_mapping_free(struct x86_mapping_info *info, pgd_t *pgd) +{ + int i; + + for (i = 0; i < PTRS_PER_PGD; i++) { + if (!pgd_present(pgd[i])) + continue; + + free_p4d(info, &pgd[i]); + } + + info->free_pgt_page(pgd, info->context); +} + static void ident_pmd_init(struct x86_mapping_info *info, pmd_t *pmd_page, unsigned long addr, unsigned long end) { diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 7e177856ee4f..28002cc7a37d 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -469,7 +469,9 @@ phys_pte_init(pte_t *pte_page, unsigned long paddr, unsigned long paddr_end, !e820__mapped_any(paddr & PAGE_MASK, paddr_next, E820_TYPE_RAM) && !e820__mapped_any(paddr & PAGE_MASK, paddr_next, - E820_TYPE_RESERVED_KERN)) + E820_TYPE_RESERVED_KERN) && + !e820__mapped_any(paddr & PAGE_MASK, paddr_next, + E820_TYPE_ACPI)) set_pte_init(pte, __pte(0), init); continue; } @@ -524,7 +526,9 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long paddr, unsigned long paddr_end, !e820__mapped_any(paddr & PMD_MASK, paddr_next, E820_TYPE_RAM) && !e820__mapped_any(paddr & PMD_MASK, paddr_next, - E820_TYPE_RESERVED_KERN)) + E820_TYPE_RESERVED_KERN) && + !e820__mapped_any(paddr & PMD_MASK, paddr_next, + E820_TYPE_ACPI)) set_pmd_init(pmd, __pmd(0), init); continue; } @@ -611,7 +615,9 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end, !e820__mapped_any(paddr & PUD_MASK, paddr_next, E820_TYPE_RAM) && !e820__mapped_any(paddr & PUD_MASK, paddr_next, - E820_TYPE_RESERVED_KERN)) + E820_TYPE_RESERVED_KERN) && + !e820__mapped_any(paddr & PUD_MASK, paddr_next, + E820_TYPE_ACPI)) set_pud_init(pud, __pud(0), init); continue; } @@ -698,7 +704,9 @@ phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end, !e820__mapped_any(paddr & P4D_MASK, paddr_next, E820_TYPE_RAM) && !e820__mapped_any(paddr & P4D_MASK, paddr_next, - E820_TYPE_RESERVED_KERN)) + E820_TYPE_RESERVED_KERN) && + !e820__mapped_any(paddr & P4D_MASK, paddr_next, + E820_TYPE_ACPI)) set_p4d_init(p4d, __p4d(0), init); continue; } diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c index 422602f6039b..86a476a426c2 100644 --- a/arch/x86/mm/mem_encrypt_amd.c +++ b/arch/x86/mm/mem_encrypt_amd.c @@ -2,7 +2,7 @@ /* * AMD Memory Encryption Support * - * Copyright (C) 2016 Advanced Micro Devices, Inc. + * Copyright (C) 2016-2024 Advanced Micro Devices, Inc. * * Author: Tom Lendacky */ @@ -283,7 +283,7 @@ static void enc_dec_hypercall(unsigned long vaddr, unsigned long size, bool enc) #endif } -static bool amd_enc_status_change_prepare(unsigned long vaddr, int npages, bool enc) +static int amd_enc_status_change_prepare(unsigned long vaddr, int npages, bool enc) { /* * To maintain the security guarantees of SEV-SNP guests, make sure @@ -292,11 +292,11 @@ static bool amd_enc_status_change_prepare(unsigned long vaddr, int npages, bool if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP) && !enc) snp_set_memory_shared(vaddr, npages); - return true; + return 0; } /* Return true unconditionally: return value doesn't matter for the SEV side */ -static bool amd_enc_status_change_finish(unsigned long vaddr, int npages, bool enc) +static int amd_enc_status_change_finish(unsigned long vaddr, int npages, bool enc) { /* * After memory is mapped encrypted in the page table, validate it @@ -308,7 +308,7 @@ static bool amd_enc_status_change_finish(unsigned long vaddr, int npages, bool e if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) enc_dec_hypercall(vaddr, npages << PAGE_SHIFT, enc); - return true; + return 0; } static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc) @@ -510,6 +510,12 @@ void __init sme_early_init(void) */ x86_init.resources.dmi_setup = snp_dmi_setup; } + + /* + * Switch the SVSM CA mapping (if active) from identity mapped to + * kernel mapped. + */ + snp_update_svsm_ca(); } void __init mem_encrypt_free_decrypted_mem(void) diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 19fdfbb171ed..443a97e515c0 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -662,8 +662,9 @@ static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long star /* * Lookup the page table entry for a virtual address in a specific pgd. - * Return a pointer to the entry, the level of the mapping, and the effective - * NX and RW bits of all page table levels. + * Return a pointer to the entry (or NULL if the entry does not exist), + * the level of the entry, and the effective NX and RW bits of all + * page table levels. */ pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address, unsigned int *level, bool *nx, bool *rw) @@ -672,13 +673,14 @@ pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address, pud_t *pud; pmd_t *pmd; - *level = PG_LEVEL_NONE; + *level = PG_LEVEL_256T; *nx = false; *rw = true; if (pgd_none(*pgd)) return NULL; + *level = PG_LEVEL_512G; *nx |= pgd_flags(*pgd) & _PAGE_NX; *rw &= pgd_flags(*pgd) & _PAGE_RW; @@ -686,10 +688,10 @@ pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address, if (p4d_none(*p4d)) return NULL; - *level = PG_LEVEL_512G; if (p4d_leaf(*p4d) || !p4d_present(*p4d)) return (pte_t *)p4d; + *level = PG_LEVEL_1G; *nx |= p4d_flags(*p4d) & _PAGE_NX; *rw &= p4d_flags(*p4d) & _PAGE_RW; @@ -697,10 +699,10 @@ pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address, if (pud_none(*pud)) return NULL; - *level = PG_LEVEL_1G; if (pud_leaf(*pud) || !pud_present(*pud)) return (pte_t *)pud; + *level = PG_LEVEL_2M; *nx |= pud_flags(*pud) & _PAGE_NX; *rw &= pud_flags(*pud) & _PAGE_RW; @@ -708,15 +710,13 @@ pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address, if (pmd_none(*pmd)) return NULL; - *level = PG_LEVEL_2M; if (pmd_leaf(*pmd) || !pmd_present(*pmd)) return (pte_t *)pmd; + *level = PG_LEVEL_4K; *nx |= pmd_flags(*pmd) & _PAGE_NX; *rw &= pmd_flags(*pmd) & _PAGE_RW; - *level = PG_LEVEL_4K; - return pte_offset_kernel(pmd, address); } @@ -736,9 +736,8 @@ pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, * Lookup the page table entry for a virtual address. Return a pointer * to the entry and the level of the mapping. * - * Note: We return pud and pmd either when the entry is marked large - * or when the present bit is not set. Otherwise we would return a - * pointer to a nonexisting mapping. + * Note: the function returns p4d, pud or pmd either when the entry is marked + * large or when the present bit is not set. Otherwise it returns NULL. */ pte_t *lookup_address(unsigned long address, unsigned int *level) { @@ -2196,7 +2195,8 @@ static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc) cpa_flush(&cpa, x86_platform.guest.enc_cache_flush_required()); /* Notify hypervisor that we are about to set/clr encryption attribute. */ - if (!x86_platform.guest.enc_status_change_prepare(addr, numpages, enc)) + ret = x86_platform.guest.enc_status_change_prepare(addr, numpages, enc); + if (ret) goto vmm_fail; ret = __change_page_attr_set_clr(&cpa, 1); @@ -2214,24 +2214,61 @@ static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc) return ret; /* Notify hypervisor that we have successfully set/clr encryption attribute. */ - if (!x86_platform.guest.enc_status_change_finish(addr, numpages, enc)) + ret = x86_platform.guest.enc_status_change_finish(addr, numpages, enc); + if (ret) goto vmm_fail; return 0; vmm_fail: - WARN_ONCE(1, "CPA VMM failure to convert memory (addr=%p, numpages=%d) to %s.\n", - (void *)addr, numpages, enc ? "private" : "shared"); + WARN_ONCE(1, "CPA VMM failure to convert memory (addr=%p, numpages=%d) to %s: %d\n", + (void *)addr, numpages, enc ? "private" : "shared", ret); - return -EIO; + return ret; +} + +/* + * The lock serializes conversions between private and shared memory. + * + * It is taken for read on conversion. A write lock guarantees that no + * concurrent conversions are in progress. + */ +static DECLARE_RWSEM(mem_enc_lock); + +/* + * Stop new private<->shared conversions. + * + * Taking the exclusive mem_enc_lock waits for in-flight conversions to complete. + * The lock is not released to prevent new conversions from being started. + */ +bool set_memory_enc_stop_conversion(void) +{ + /* + * In a crash scenario, sleep is not allowed. Try to take the lock. + * Failure indicates that there is a race with the conversion. + */ + if (oops_in_progress) + return down_write_trylock(&mem_enc_lock); + + down_write(&mem_enc_lock); + + return true; } static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc) { - if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) - return __set_memory_enc_pgtable(addr, numpages, enc); + int ret = 0; - return 0; + if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) { + if (!down_read_trylock(&mem_enc_lock)) + return -EBUSY; + + ret = __set_memory_enc_pgtable(addr, numpages, enc); + + up_read(&mem_enc_lock); + } + + return ret; } int set_memory_encrypted(unsigned long addr, int numpages) diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 8edd62206604..b433b1753016 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -216,7 +216,7 @@ static int pci_write(struct pci_bus *bus, unsigned int devfn, int where, } static const struct x86_cpu_id intel_mid_cpu_ids[] = { - X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT_MID, NULL), + X86_MATCH_VFM(INTEL_ATOM_SILVERMONT_MID, NULL), {} }; @@ -233,9 +233,9 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) return 0; ret = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi); - if (ret < 0) { + if (ret) { dev_warn(&dev->dev, "Failed to read interrupt line: %d\n", ret); - return ret; + return pcibios_err_to_errno(ret); } id = x86_match_cpu(intel_mid_cpu_ids); @@ -243,7 +243,7 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) model = id->model; switch (model) { - case INTEL_FAM6_ATOM_SILVERMONT_MID: + case VFM_MODEL(INTEL_ATOM_SILVERMONT_MID): polarity_low = false; /* Special treatment for IRQ0 */ diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 652cd53e77f6..0f2fe524f60d 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -38,10 +38,10 @@ static int xen_pcifront_enable_irq(struct pci_dev *dev) u8 gsi; rc = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi); - if (rc < 0) { + if (rc) { dev_warn(&dev->dev, "Xen PCI: failed to read interrupt line: %d\n", rc); - return rc; + return pcibios_err_to_errno(rc); } /* In PV DomU the Xen PCI backend puts the PIRQ in the interrupt line.*/ pirq = gsi; diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c index 7be71c2cdc83..f83bbe0acd4a 100644 --- a/arch/x86/platform/intel-mid/intel-mid.c +++ b/arch/x86/platform/intel-mid/intel-mid.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -55,9 +56,8 @@ static void __init intel_mid_time_init(void) static void intel_mid_arch_setup(void) { - switch (boot_cpu_data.x86_model) { - case 0x3C: - case 0x4A: + switch (boot_cpu_data.x86_vfm) { + case INTEL_ATOM_SILVERMONT_MID: x86_platform.legacy.rtc = 1; break; default: diff --git a/arch/x86/platform/intel/iosf_mbi.c b/arch/x86/platform/intel/iosf_mbi.c index fdd49d70b437..c81cea208c2c 100644 --- a/arch/x86/platform/intel/iosf_mbi.c +++ b/arch/x86/platform/intel/iosf_mbi.c @@ -62,7 +62,7 @@ static int iosf_mbi_pci_read_mdr(u32 mcrx, u32 mcr, u32 *mdr) fail_read: dev_err(&mbi_pdev->dev, "PCI config access failed with %d\n", result); - return result; + return pcibios_err_to_errno(result); } static int iosf_mbi_pci_write_mdr(u32 mcrx, u32 mcr, u32 mdr) @@ -91,7 +91,7 @@ static int iosf_mbi_pci_write_mdr(u32 mcrx, u32 mcr, u32 mdr) fail_write: dev_err(&mbi_pdev->dev, "PCI config access failed with %d\n", result); - return result; + return pcibios_err_to_errno(result); } int iosf_mbi_read(u8 port, u8 opcode, u32 offset, u32 *mdr) diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c index 89df5d89d664..51655133eee3 100644 --- a/arch/x86/um/sys_call_table_32.c +++ b/arch/x86/um/sys_call_table_32.c @@ -9,6 +9,10 @@ #include #include +extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, + unsigned long, unsigned long, + unsigned long, unsigned long); + /* * Below you can see, in terms of #define's, the differences between the x86-64 * and the UML syscall table. @@ -22,15 +26,13 @@ #define sys_vm86 sys_ni_syscall #define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, native) +#define __SYSCALL_NORETURN __SYSCALL #define __SYSCALL(nr, sym) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); #include +#undef __SYSCALL -#undef __SYSCALL #define __SYSCALL(nr, sym) sym, - -extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); - const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = { #include }; diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c index b0b4cfd2308c..943d414f2109 100644 --- a/arch/x86/um/sys_call_table_64.c +++ b/arch/x86/um/sys_call_table_64.c @@ -9,6 +9,10 @@ #include #include +extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, + unsigned long, unsigned long, + unsigned long, unsigned long); + /* * Below you can see, in terms of #define's, the differences between the x86-64 * and the UML syscall table. @@ -18,14 +22,13 @@ #define sys_iopl sys_ni_syscall #define sys_ioperm sys_ni_syscall +#define __SYSCALL_NORETURN __SYSCALL + #define __SYSCALL(nr, sym) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); #include +#undef __SYSCALL -#undef __SYSCALL #define __SYSCALL(nr, sym) sym, - -extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); - const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = { #include }; diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c index 0ae10535c699..0ce17766c0e5 100644 --- a/arch/x86/virt/svm/sev.c +++ b/arch/x86/virt/svm/sev.c @@ -120,7 +120,7 @@ static __init void snp_enable(void *arg) bool snp_probe_rmptable_info(void) { - u64 max_rmp_pfn, calc_rmp_sz, rmp_sz, rmp_base, rmp_end; + u64 rmp_sz, rmp_base, rmp_end; rdmsrl(MSR_AMD64_RMP_BASE, rmp_base); rdmsrl(MSR_AMD64_RMP_END, rmp_end); @@ -137,28 +137,11 @@ bool snp_probe_rmptable_info(void) rmp_sz = rmp_end - rmp_base + 1; - /* - * Calculate the amount the memory that must be reserved by the BIOS to - * address the whole RAM, including the bookkeeping area. The RMP itself - * must also be covered. - */ - max_rmp_pfn = max_pfn; - if (PHYS_PFN(rmp_end) > max_pfn) - max_rmp_pfn = PHYS_PFN(rmp_end); - - calc_rmp_sz = (max_rmp_pfn << 4) + RMPTABLE_CPU_BOOKKEEPING_SZ; - - if (calc_rmp_sz > rmp_sz) { - pr_err("Memory reserved for the RMP table does not cover full system RAM (expected 0x%llx got 0x%llx)\n", - calc_rmp_sz, rmp_sz); - return false; - } - probed_rmp_base = rmp_base; probed_rmp_size = rmp_sz; pr_info("RMP table physical range [0x%016llx - 0x%016llx]\n", - probed_rmp_base, probed_rmp_base + probed_rmp_size - 1); + rmp_base, rmp_end); return true; } @@ -206,9 +189,8 @@ void __init snp_fixup_e820_tables(void) */ static int __init snp_rmptable_init(void) { + u64 max_rmp_pfn, calc_rmp_sz, rmptable_size, rmp_end, val; void *rmptable_start; - u64 rmptable_size; - u64 val; if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) return 0; @@ -219,10 +201,28 @@ static int __init snp_rmptable_init(void) if (!probed_rmp_size) goto nosnp; + rmp_end = probed_rmp_base + probed_rmp_size - 1; + + /* + * Calculate the amount the memory that must be reserved by the BIOS to + * address the whole RAM, including the bookkeeping area. The RMP itself + * must also be covered. + */ + max_rmp_pfn = max_pfn; + if (PFN_UP(rmp_end) > max_pfn) + max_rmp_pfn = PFN_UP(rmp_end); + + calc_rmp_sz = (max_rmp_pfn << 4) + RMPTABLE_CPU_BOOKKEEPING_SZ; + if (calc_rmp_sz > probed_rmp_size) { + pr_err("Memory reserved for the RMP table does not cover full system RAM (expected 0x%llx got 0x%llx)\n", + calc_rmp_sz, probed_rmp_size); + goto nosnp; + } + rmptable_start = memremap(probed_rmp_base, probed_rmp_size, MEMREMAP_WB); if (!rmptable_start) { pr_err("Failed to map RMP table\n"); - return 1; + goto nosnp; } /* diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c index 49a1c6890b55..4e2b2e2ac9f9 100644 --- a/arch/x86/virt/vmx/tdx/tdx.c +++ b/arch/x86/virt/vmx/tdx/tdx.c @@ -33,7 +33,7 @@ #include #include #include -#include +#include #include #include #include "tdx.h" @@ -1426,9 +1426,9 @@ static void __init check_tdx_erratum(void) * private memory poisons that memory, and a subsequent read of * that memory triggers #MC. */ - switch (boot_cpu_data.x86_model) { - case INTEL_FAM6_SAPPHIRERAPIDS_X: - case INTEL_FAM6_EMERALDRAPIDS_X: + switch (boot_cpu_data.x86_vfm) { + case INTEL_SAPPHIRERAPIDS_X: + case INTEL_EMERALDRAPIDS_X: setup_force_cpu_bug(X86_BUG_TDX_PW_MCE); } } diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c index b976e5fc3fbc..9e1b01c35070 100644 --- a/drivers/acpi/tables.c +++ b/drivers/acpi/tables.c @@ -198,6 +198,20 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header) } break; + case ACPI_MADT_TYPE_MULTIPROC_WAKEUP: + { + struct acpi_madt_multiproc_wakeup *p = + (struct acpi_madt_multiproc_wakeup *)header; + u64 reset_vector = 0; + + if (p->version >= ACPI_MADT_MP_WAKEUP_VERSION_V1) + reset_vector = p->reset_vector; + + pr_debug("MP Wakeup (version[%d], mailbox[%#llx], reset[%#llx])\n", + p->version, p->mailbox_address, reset_vector); + } + break; + case ACPI_MADT_TYPE_CORE_PIC: { struct acpi_madt_core_pic *p = (struct acpi_madt_core_pic *)header; diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index a17f3c0cdfa6..ddfbdb66b794 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -20,7 +20,6 @@ static inline u32 get_umc_reg(struct amd64_pvt *pvt, u32 reg) return reg; switch (reg) { - case UMCCH_ADDR_CFG: return UMCCH_ADDR_CFG_DDR5; case UMCCH_ADDR_MASK_SEC: return UMCCH_ADDR_MASK_SEC_DDR5; case UMCCH_DIMM_CFG: return UMCCH_DIMM_CFG_DDR5; } @@ -1341,22 +1340,15 @@ static void umc_debug_display_dimm_sizes(struct amd64_pvt *pvt, u8 ctrl) static void umc_dump_misc_regs(struct amd64_pvt *pvt) { struct amd64_umc *umc; - u32 i, tmp, umc_base; + u32 i; for_each_umc(i) { - umc_base = get_umc_base(i); umc = &pvt->umc[i]; edac_dbg(1, "UMC%d DIMM cfg: 0x%x\n", i, umc->dimm_cfg); edac_dbg(1, "UMC%d UMC cfg: 0x%x\n", i, umc->umc_cfg); edac_dbg(1, "UMC%d SDP ctrl: 0x%x\n", i, umc->sdp_ctrl); edac_dbg(1, "UMC%d ECC ctrl: 0x%x\n", i, umc->ecc_ctrl); - - amd_smn_read(pvt->mc_node_id, umc_base + UMCCH_ECC_BAD_SYMBOL, &tmp); - edac_dbg(1, "UMC%d ECC bad symbol: 0x%x\n", i, tmp); - - amd_smn_read(pvt->mc_node_id, umc_base + UMCCH_UMC_CAP, &tmp); - edac_dbg(1, "UMC%d UMC cap: 0x%x\n", i, tmp); edac_dbg(1, "UMC%d UMC cap high: 0x%x\n", i, umc->umc_cap_hi); edac_dbg(1, "UMC%d ECC capable: %s, ChipKill ECC capable: %s\n", @@ -1369,14 +1361,6 @@ static void umc_dump_misc_regs(struct amd64_pvt *pvt) edac_dbg(1, "UMC%d x16 DIMMs present: %s\n", i, (umc->dimm_cfg & BIT(7)) ? "yes" : "no"); - if (umc->dram_type == MEM_LRDDR4 || umc->dram_type == MEM_LRDDR5) { - amd_smn_read(pvt->mc_node_id, - umc_base + get_umc_reg(pvt, UMCCH_ADDR_CFG), - &tmp); - edac_dbg(1, "UMC%d LRDIMM %dx rank multiply\n", - i, 1 << ((tmp >> 4) & 0x3)); - } - umc_debug_display_dimm_sizes(pvt, i); } } @@ -1454,6 +1438,7 @@ static void umc_read_base_mask(struct amd64_pvt *pvt) u32 *base, *base_sec; u32 *mask, *mask_sec; int cs, umc; + u32 tmp; for_each_umc(umc) { umc_base_reg = get_umc_base(umc) + UMCCH_BASE_ADDR; @@ -1466,13 +1451,17 @@ static void umc_read_base_mask(struct amd64_pvt *pvt) base_reg = umc_base_reg + (cs * 4); base_reg_sec = umc_base_reg_sec + (cs * 4); - if (!amd_smn_read(pvt->mc_node_id, base_reg, base)) + if (!amd_smn_read(pvt->mc_node_id, base_reg, &tmp)) { + *base = tmp; edac_dbg(0, " DCSB%d[%d]=0x%08x reg: 0x%x\n", umc, cs, *base, base_reg); + } - if (!amd_smn_read(pvt->mc_node_id, base_reg_sec, base_sec)) + if (!amd_smn_read(pvt->mc_node_id, base_reg_sec, &tmp)) { + *base_sec = tmp; edac_dbg(0, " DCSB_SEC%d[%d]=0x%08x reg: 0x%x\n", umc, cs, *base_sec, base_reg_sec); + } } umc_mask_reg = get_umc_base(umc) + UMCCH_ADDR_MASK; @@ -1485,13 +1474,17 @@ static void umc_read_base_mask(struct amd64_pvt *pvt) mask_reg = umc_mask_reg + (cs * 4); mask_reg_sec = umc_mask_reg_sec + (cs * 4); - if (!amd_smn_read(pvt->mc_node_id, mask_reg, mask)) + if (!amd_smn_read(pvt->mc_node_id, mask_reg, &tmp)) { + *mask = tmp; edac_dbg(0, " DCSM%d[%d]=0x%08x reg: 0x%x\n", umc, cs, *mask, mask_reg); + } - if (!amd_smn_read(pvt->mc_node_id, mask_reg_sec, mask_sec)) + if (!amd_smn_read(pvt->mc_node_id, mask_reg_sec, &tmp)) { + *mask_sec = tmp; edac_dbg(0, " DCSM_SEC%d[%d]=0x%08x reg: 0x%x\n", umc, cs, *mask_sec, mask_reg_sec); + } } } } @@ -2910,7 +2903,7 @@ static void umc_read_mc_regs(struct amd64_pvt *pvt) { u8 nid = pvt->mc_node_id; struct amd64_umc *umc; - u32 i, umc_base; + u32 i, tmp, umc_base; /* Read registers from each UMC */ for_each_umc(i) { @@ -2918,11 +2911,20 @@ static void umc_read_mc_regs(struct amd64_pvt *pvt) umc_base = get_umc_base(i); umc = &pvt->umc[i]; - amd_smn_read(nid, umc_base + get_umc_reg(pvt, UMCCH_DIMM_CFG), &umc->dimm_cfg); - amd_smn_read(nid, umc_base + UMCCH_UMC_CFG, &umc->umc_cfg); - amd_smn_read(nid, umc_base + UMCCH_SDP_CTRL, &umc->sdp_ctrl); - amd_smn_read(nid, umc_base + UMCCH_ECC_CTRL, &umc->ecc_ctrl); - amd_smn_read(nid, umc_base + UMCCH_UMC_CAP_HI, &umc->umc_cap_hi); + if (!amd_smn_read(nid, umc_base + get_umc_reg(pvt, UMCCH_DIMM_CFG), &tmp)) + umc->dimm_cfg = tmp; + + if (!amd_smn_read(nid, umc_base + UMCCH_UMC_CFG, &tmp)) + umc->umc_cfg = tmp; + + if (!amd_smn_read(nid, umc_base + UMCCH_SDP_CTRL, &tmp)) + umc->sdp_ctrl = tmp; + + if (!amd_smn_read(nid, umc_base + UMCCH_ECC_CTRL, &tmp)) + umc->ecc_ctrl = tmp; + + if (!amd_smn_read(nid, umc_base + UMCCH_UMC_CAP_HI, &tmp)) + umc->umc_cap_hi = tmp; } } @@ -3651,16 +3653,21 @@ static void gpu_read_mc_regs(struct amd64_pvt *pvt) { u8 nid = pvt->mc_node_id; struct amd64_umc *umc; - u32 i, umc_base; + u32 i, tmp, umc_base; /* Read registers from each UMC */ for_each_umc(i) { umc_base = gpu_get_umc_base(pvt, i, 0); umc = &pvt->umc[i]; - amd_smn_read(nid, umc_base + UMCCH_UMC_CFG, &umc->umc_cfg); - amd_smn_read(nid, umc_base + UMCCH_SDP_CTRL, &umc->sdp_ctrl); - amd_smn_read(nid, umc_base + UMCCH_ECC_CTRL, &umc->ecc_ctrl); + if (!amd_smn_read(nid, umc_base + UMCCH_UMC_CFG, &tmp)) + umc->umc_cfg = tmp; + + if (!amd_smn_read(nid, umc_base + UMCCH_SDP_CTRL, &tmp)) + umc->sdp_ctrl = tmp; + + if (!amd_smn_read(nid, umc_base + UMCCH_ECC_CTRL, &tmp)) + umc->ecc_ctrl = tmp; } } diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h index b879b12971e7..17228d07de4c 100644 --- a/drivers/edac/amd64_edac.h +++ b/drivers/edac/amd64_edac.h @@ -256,15 +256,11 @@ #define UMCCH_ADDR_MASK 0x20 #define UMCCH_ADDR_MASK_SEC 0x28 #define UMCCH_ADDR_MASK_SEC_DDR5 0x30 -#define UMCCH_ADDR_CFG 0x30 -#define UMCCH_ADDR_CFG_DDR5 0x40 #define UMCCH_DIMM_CFG 0x80 #define UMCCH_DIMM_CFG_DDR5 0x90 #define UMCCH_UMC_CFG 0x100 #define UMCCH_SDP_CTRL 0x104 #define UMCCH_ECC_CTRL 0x14C -#define UMCCH_ECC_BAD_SYMBOL 0xD90 -#define UMCCH_UMC_CAP 0xDF0 #define UMCCH_UMC_CAP_HI 0xDF4 /* UMC CH bitfields */ diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c index 2651fe0ef518..1f15990d3934 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c @@ -48,8 +48,6 @@ #define RETRIES 3 -#define VMW_HYPERVISOR_MAGIC 0x564D5868 - #define VMW_PORT_CMD_MSG 30 #define VMW_PORT_CMD_HB_MSG 0 #define VMW_PORT_CMD_OPEN_CHANNEL (MSG_TYPE_OPEN << 16 | VMW_PORT_CMD_MSG) @@ -104,20 +102,18 @@ static const char* const mksstat_kern_name_desc[MKSSTAT_KERN_COUNT][2] = */ static int vmw_open_channel(struct rpc_channel *channel, unsigned int protocol) { - unsigned long eax, ebx, ecx, edx, si = 0, di = 0; + u32 ecx, edx, esi, edi; - VMW_PORT(VMW_PORT_CMD_OPEN_CHANNEL, - (protocol | GUESTMSG_FLAG_COOKIE), si, di, - 0, - VMW_HYPERVISOR_MAGIC, - eax, ebx, ecx, edx, si, di); + vmware_hypercall6(VMW_PORT_CMD_OPEN_CHANNEL, + (protocol | GUESTMSG_FLAG_COOKIE), 0, + &ecx, &edx, &esi, &edi); if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0) return -EINVAL; channel->channel_id = HIGH_WORD(edx); - channel->cookie_high = si; - channel->cookie_low = di; + channel->cookie_high = esi; + channel->cookie_low = edi; return 0; } @@ -133,17 +129,13 @@ static int vmw_open_channel(struct rpc_channel *channel, unsigned int protocol) */ static int vmw_close_channel(struct rpc_channel *channel) { - unsigned long eax, ebx, ecx, edx, si, di; + u32 ecx; - /* Set up additional parameters */ - si = channel->cookie_high; - di = channel->cookie_low; - - VMW_PORT(VMW_PORT_CMD_CLOSE_CHANNEL, - 0, si, di, - channel->channel_id << 16, - VMW_HYPERVISOR_MAGIC, - eax, ebx, ecx, edx, si, di); + vmware_hypercall5(VMW_PORT_CMD_CLOSE_CHANNEL, + 0, channel->channel_id << 16, + channel->cookie_high, + channel->cookie_low, + &ecx); if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0) return -EINVAL; @@ -163,24 +155,18 @@ static int vmw_close_channel(struct rpc_channel *channel) static unsigned long vmw_port_hb_out(struct rpc_channel *channel, const char *msg, bool hb) { - unsigned long si, di, eax, ebx, ecx, edx; + u32 ebx, ecx; unsigned long msg_len = strlen(msg); /* HB port can't access encrypted memory. */ if (hb && !cc_platform_has(CC_ATTR_MEM_ENCRYPT)) { - unsigned long bp = channel->cookie_high; - u32 channel_id = (channel->channel_id << 16); - - si = (uintptr_t) msg; - di = channel->cookie_low; - - VMW_PORT_HB_OUT( + vmware_hypercall_hb_out( (MESSAGE_STATUS_SUCCESS << 16) | VMW_PORT_CMD_HB_MSG, - msg_len, si, di, - VMWARE_HYPERVISOR_HB | channel_id | - VMWARE_HYPERVISOR_OUT, - VMW_HYPERVISOR_MAGIC, bp, - eax, ebx, ecx, edx, si, di); + msg_len, + channel->channel_id << 16, + (uintptr_t) msg, channel->cookie_low, + channel->cookie_high, + &ebx); return ebx; } @@ -194,14 +180,13 @@ static unsigned long vmw_port_hb_out(struct rpc_channel *channel, memcpy(&word, msg, bytes); msg_len -= bytes; msg += bytes; - si = channel->cookie_high; - di = channel->cookie_low; - VMW_PORT(VMW_PORT_CMD_MSG | (MSG_TYPE_SENDPAYLOAD << 16), - word, si, di, - channel->channel_id << 16, - VMW_HYPERVISOR_MAGIC, - eax, ebx, ecx, edx, si, di); + vmware_hypercall5(VMW_PORT_CMD_MSG | + (MSG_TYPE_SENDPAYLOAD << 16), + word, channel->channel_id << 16, + channel->cookie_high, + channel->cookie_low, + &ecx); } return ecx; @@ -220,22 +205,17 @@ static unsigned long vmw_port_hb_out(struct rpc_channel *channel, static unsigned long vmw_port_hb_in(struct rpc_channel *channel, char *reply, unsigned long reply_len, bool hb) { - unsigned long si, di, eax, ebx, ecx, edx; + u32 ebx, ecx, edx; /* HB port can't access encrypted memory */ if (hb && !cc_platform_has(CC_ATTR_MEM_ENCRYPT)) { - unsigned long bp = channel->cookie_low; - u32 channel_id = (channel->channel_id << 16); - - si = channel->cookie_high; - di = (uintptr_t) reply; - - VMW_PORT_HB_IN( + vmware_hypercall_hb_in( (MESSAGE_STATUS_SUCCESS << 16) | VMW_PORT_CMD_HB_MSG, - reply_len, si, di, - VMWARE_HYPERVISOR_HB | channel_id, - VMW_HYPERVISOR_MAGIC, bp, - eax, ebx, ecx, edx, si, di); + reply_len, + channel->channel_id << 16, + channel->cookie_high, + (uintptr_t) reply, channel->cookie_low, + &ebx); return ebx; } @@ -245,14 +225,13 @@ static unsigned long vmw_port_hb_in(struct rpc_channel *channel, char *reply, while (reply_len) { unsigned int bytes = min_t(unsigned long, reply_len, 4); - si = channel->cookie_high; - di = channel->cookie_low; - - VMW_PORT(VMW_PORT_CMD_MSG | (MSG_TYPE_RECVPAYLOAD << 16), - MESSAGE_STATUS_SUCCESS, si, di, - channel->channel_id << 16, - VMW_HYPERVISOR_MAGIC, - eax, ebx, ecx, edx, si, di); + vmware_hypercall7(VMW_PORT_CMD_MSG | + (MSG_TYPE_RECVPAYLOAD << 16), + MESSAGE_STATUS_SUCCESS, + channel->channel_id << 16, + channel->cookie_high, + channel->cookie_low, + &ebx, &ecx, &edx); if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0) break; @@ -276,22 +255,18 @@ static unsigned long vmw_port_hb_in(struct rpc_channel *channel, char *reply, */ static int vmw_send_msg(struct rpc_channel *channel, const char *msg) { - unsigned long eax, ebx, ecx, edx, si, di; + u32 ebx, ecx; size_t msg_len = strlen(msg); int retries = 0; while (retries < RETRIES) { retries++; - /* Set up additional parameters */ - si = channel->cookie_high; - di = channel->cookie_low; - - VMW_PORT(VMW_PORT_CMD_SENDSIZE, - msg_len, si, di, - channel->channel_id << 16, - VMW_HYPERVISOR_MAGIC, - eax, ebx, ecx, edx, si, di); + vmware_hypercall5(VMW_PORT_CMD_SENDSIZE, + msg_len, channel->channel_id << 16, + channel->cookie_high, + channel->cookie_low, + &ecx); if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0) { /* Expected success. Give up. */ @@ -329,7 +304,7 @@ STACK_FRAME_NON_STANDARD(vmw_send_msg); static int vmw_recv_msg(struct rpc_channel *channel, void **msg, size_t *msg_len) { - unsigned long eax, ebx, ecx, edx, si, di; + u32 ebx, ecx, edx; char *reply; size_t reply_len; int retries = 0; @@ -341,15 +316,11 @@ static int vmw_recv_msg(struct rpc_channel *channel, void **msg, while (retries < RETRIES) { retries++; - /* Set up additional parameters */ - si = channel->cookie_high; - di = channel->cookie_low; - - VMW_PORT(VMW_PORT_CMD_RECVSIZE, - 0, si, di, - channel->channel_id << 16, - VMW_HYPERVISOR_MAGIC, - eax, ebx, ecx, edx, si, di); + vmware_hypercall7(VMW_PORT_CMD_RECVSIZE, + 0, channel->channel_id << 16, + channel->cookie_high, + channel->cookie_low, + &ebx, &ecx, &edx); if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0) { DRM_ERROR("Failed to get reply size for host message.\n"); @@ -384,16 +355,12 @@ static int vmw_recv_msg(struct rpc_channel *channel, void **msg, reply[reply_len] = '\0'; - - /* Ack buffer */ - si = channel->cookie_high; - di = channel->cookie_low; - - VMW_PORT(VMW_PORT_CMD_RECVSTATUS, - MESSAGE_STATUS_SUCCESS, si, di, - channel->channel_id << 16, - VMW_HYPERVISOR_MAGIC, - eax, ebx, ecx, edx, si, di); + vmware_hypercall5(VMW_PORT_CMD_RECVSTATUS, + MESSAGE_STATUS_SUCCESS, + channel->channel_id << 16, + channel->cookie_high, + channel->cookie_low, + &ecx); if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0) { kfree(reply); @@ -652,13 +619,7 @@ static inline void reset_ppn_array(PPN64 *arr, size_t size) */ static inline void hypervisor_ppn_reset_all(void) { - unsigned long eax, ebx, ecx, edx, si = 0, di = 0; - - VMW_PORT(VMW_PORT_CMD_MKSGS_RESET, - 0, si, di, - 0, - VMW_HYPERVISOR_MAGIC, - eax, ebx, ecx, edx, si, di); + vmware_hypercall1(VMW_PORT_CMD_MKSGS_RESET, 0); } /** @@ -669,13 +630,7 @@ static inline void hypervisor_ppn_reset_all(void) */ static inline void hypervisor_ppn_add(PPN64 pfn) { - unsigned long eax, ebx, ecx, edx, si = 0, di = 0; - - VMW_PORT(VMW_PORT_CMD_MKSGS_ADD_PPN, - (unsigned long)pfn, si, di, - 0, - VMW_HYPERVISOR_MAGIC, - eax, ebx, ecx, edx, si, di); + vmware_hypercall1(VMW_PORT_CMD_MKSGS_ADD_PPN, (unsigned long)pfn); } /** @@ -686,13 +641,7 @@ static inline void hypervisor_ppn_add(PPN64 pfn) */ static inline void hypervisor_ppn_remove(PPN64 pfn) { - unsigned long eax, ebx, ecx, edx, si = 0, di = 0; - - VMW_PORT(VMW_PORT_CMD_MKSGS_REMOVE_PPN, - (unsigned long)pfn, si, di, - 0, - VMW_HYPERVISOR_MAGIC, - eax, ebx, ecx, edx, si, di); + vmware_hypercall1(VMW_PORT_CMD_MKSGS_REMOVE_PPN, (unsigned long)pfn); } #if IS_ENABLED(CONFIG_DRM_VMWGFX_MKSSTATS) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h b/drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h index 4f40167ad61f..3c78e9338b54 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h @@ -34,6 +34,8 @@ #define VMWARE_HYPERVISOR_HB BIT(0) #define VMWARE_HYPERVISOR_OUT BIT(1) +#define VMWARE_HYPERVISOR_MAGIC 0x564D5868 + #define X86_IO_MAGIC 0x86 #define X86_IO_W7_SIZE_SHIFT 0 @@ -45,86 +47,158 @@ #define X86_IO_W7_IMM_SHIFT 5 #define X86_IO_W7_IMM_MASK (0xff << X86_IO_W7_IMM_SHIFT) -static inline void vmw_port(unsigned long cmd, unsigned long in_ebx, - unsigned long in_si, unsigned long in_di, - unsigned long flags, unsigned long magic, - unsigned long *eax, unsigned long *ebx, - unsigned long *ecx, unsigned long *edx, - unsigned long *si, unsigned long *di) +static inline +unsigned long vmware_hypercall1(unsigned long cmd, unsigned long in1) { - register u64 x0 asm("x0") = magic; - register u64 x1 asm("x1") = in_ebx; + register u64 x0 asm("x0") = VMWARE_HYPERVISOR_MAGIC; + register u64 x1 asm("x1") = in1; register u64 x2 asm("x2") = cmd; - register u64 x3 asm("x3") = flags | VMWARE_HYPERVISOR_PORT; - register u64 x4 asm("x4") = in_si; - register u64 x5 asm("x5") = in_di; - + register u64 x3 asm("x3") = VMWARE_HYPERVISOR_PORT; register u64 x7 asm("x7") = ((u64)X86_IO_MAGIC << 32) | X86_IO_W7_WITH | X86_IO_W7_DIR | (2 << X86_IO_W7_SIZE_SHIFT); - asm volatile("mrs xzr, mdccsr_el0 \n\t" - : "+r"(x0), "+r"(x1), "+r"(x2), - "+r"(x3), "+r"(x4), "+r"(x5) - : "r"(x7) - :); - *eax = x0; - *ebx = x1; - *ecx = x2; - *edx = x3; - *si = x4; - *di = x5; + asm_inline volatile ( + "mrs xzr, mdccsr_el0; " + : "+r" (x0) + : "r" (x1), "r" (x2), "r" (x3), "r" (x7) + : "memory"); + + return x0; } -static inline void vmw_port_hb(unsigned long cmd, unsigned long in_ecx, - unsigned long in_si, unsigned long in_di, - unsigned long flags, unsigned long magic, - unsigned long bp, u32 w7dir, - unsigned long *eax, unsigned long *ebx, - unsigned long *ecx, unsigned long *edx, - unsigned long *si, unsigned long *di) +static inline +unsigned long vmware_hypercall5(unsigned long cmd, unsigned long in1, + unsigned long in3, unsigned long in4, + unsigned long in5, u32 *out2) { - register u64 x0 asm("x0") = magic; + register u64 x0 asm("x0") = VMWARE_HYPERVISOR_MAGIC; + register u64 x1 asm("x1") = in1; + register u64 x2 asm("x2") = cmd; + register u64 x3 asm("x3") = in3 | VMWARE_HYPERVISOR_PORT; + register u64 x4 asm("x4") = in4; + register u64 x5 asm("x5") = in5; + register u64 x7 asm("x7") = ((u64)X86_IO_MAGIC << 32) | + X86_IO_W7_WITH | + X86_IO_W7_DIR | + (2 << X86_IO_W7_SIZE_SHIFT); + + asm_inline volatile ( + "mrs xzr, mdccsr_el0; " + : "+r" (x0), "+r" (x2) + : "r" (x1), "r" (x3), "r" (x4), "r" (x5), "r" (x7) + : "memory"); + + *out2 = x2; + return x0; +} + +static inline +unsigned long vmware_hypercall6(unsigned long cmd, unsigned long in1, + unsigned long in3, u32 *out2, + u32 *out3, u32 *out4, u32 *out5) +{ + register u64 x0 asm("x0") = VMWARE_HYPERVISOR_MAGIC; + register u64 x1 asm("x1") = in1; + register u64 x2 asm("x2") = cmd; + register u64 x3 asm("x3") = in3 | VMWARE_HYPERVISOR_PORT; + register u64 x4 asm("x4"); + register u64 x5 asm("x5"); + register u64 x7 asm("x7") = ((u64)X86_IO_MAGIC << 32) | + X86_IO_W7_WITH | + X86_IO_W7_DIR | + (2 << X86_IO_W7_SIZE_SHIFT); + + asm_inline volatile ( + "mrs xzr, mdccsr_el0; " + : "+r" (x0), "+r" (x2), "+r" (x3), "=r" (x4), "=r" (x5) + : "r" (x1), "r" (x7) + : "memory"); + + *out2 = x2; + *out3 = x3; + *out4 = x4; + *out5 = x5; + return x0; +} + +static inline +unsigned long vmware_hypercall7(unsigned long cmd, unsigned long in1, + unsigned long in3, unsigned long in4, + unsigned long in5, u32 *out1, + u32 *out2, u32 *out3) +{ + register u64 x0 asm("x0") = VMWARE_HYPERVISOR_MAGIC; + register u64 x1 asm("x1") = in1; + register u64 x2 asm("x2") = cmd; + register u64 x3 asm("x3") = in3 | VMWARE_HYPERVISOR_PORT; + register u64 x4 asm("x4") = in4; + register u64 x5 asm("x5") = in5; + register u64 x7 asm("x7") = ((u64)X86_IO_MAGIC << 32) | + X86_IO_W7_WITH | + X86_IO_W7_DIR | + (2 << X86_IO_W7_SIZE_SHIFT); + + asm_inline volatile ( + "mrs xzr, mdccsr_el0; " + : "+r" (x0), "+r" (x1), "+r" (x2), "+r" (x3) + : "r" (x4), "r" (x5), "r" (x7) + : "memory"); + + *out1 = x1; + *out2 = x2; + *out3 = x3; + return x0; +} + +static inline +unsigned long vmware_hypercall_hb(unsigned long cmd, unsigned long in2, + unsigned long in3, unsigned long in4, + unsigned long in5, unsigned long in6, + u32 *out1, int dir) +{ + register u64 x0 asm("x0") = VMWARE_HYPERVISOR_MAGIC; register u64 x1 asm("x1") = cmd; - register u64 x2 asm("x2") = in_ecx; - register u64 x3 asm("x3") = flags | VMWARE_HYPERVISOR_PORT_HB; - register u64 x4 asm("x4") = in_si; - register u64 x5 asm("x5") = in_di; - register u64 x6 asm("x6") = bp; + register u64 x2 asm("x2") = in2; + register u64 x3 asm("x3") = in3 | VMWARE_HYPERVISOR_PORT_HB; + register u64 x4 asm("x4") = in4; + register u64 x5 asm("x5") = in5; + register u64 x6 asm("x6") = in6; register u64 x7 asm("x7") = ((u64)X86_IO_MAGIC << 32) | X86_IO_W7_STR | X86_IO_W7_WITH | - w7dir; + dir; - asm volatile("mrs xzr, mdccsr_el0 \n\t" - : "+r"(x0), "+r"(x1), "+r"(x2), - "+r"(x3), "+r"(x4), "+r"(x5) - : "r"(x6), "r"(x7) - :); - *eax = x0; - *ebx = x1; - *ecx = x2; - *edx = x3; - *si = x4; - *di = x5; + asm_inline volatile ( + "mrs xzr, mdccsr_el0; " + : "+r" (x0), "+r" (x1) + : "r" (x2), "r" (x3), "r" (x4), "r" (x5), + "r" (x6), "r" (x7) + : "memory"); + + *out1 = x1; + return x0; } -#define VMW_PORT(cmd, in_ebx, in_si, in_di, flags, magic, eax, ebx, ecx, edx, \ - si, di) \ - vmw_port(cmd, in_ebx, in_si, in_di, flags, magic, &eax, &ebx, &ecx, \ - &edx, &si, &di) - -#define VMW_PORT_HB_OUT(cmd, in_ecx, in_si, in_di, flags, magic, bp, eax, ebx, \ - ecx, edx, si, di) \ - vmw_port_hb(cmd, in_ecx, in_si, in_di, flags, magic, bp, \ - 0, &eax, &ebx, &ecx, &edx, &si, &di) - -#define VMW_PORT_HB_IN(cmd, in_ecx, in_si, in_di, flags, magic, bp, eax, ebx, \ - ecx, edx, si, di) \ - vmw_port_hb(cmd, in_ecx, in_si, in_di, flags, magic, bp, \ - X86_IO_W7_DIR, &eax, &ebx, &ecx, &edx, &si, &di) +static inline +unsigned long vmware_hypercall_hb_out(unsigned long cmd, unsigned long in2, + unsigned long in3, unsigned long in4, + unsigned long in5, unsigned long in6, + u32 *out1) +{ + return vmware_hypercall_hb(cmd, in2, in3, in4, in5, in6, out1, 0); +} +static inline +unsigned long vmware_hypercall_hb_in(unsigned long cmd, unsigned long in2, + unsigned long in3, unsigned long in4, + unsigned long in5, unsigned long in6, + u32 *out1) +{ + return vmware_hypercall_hb(cmd, in2, in3, in4, in5, in6, out1, + X86_IO_W7_DIR); +} #endif #endif /* _VMWGFX_MSG_ARM64_H */ diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h b/drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h index 23899d743a90..13304d34cc6e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h @@ -37,191 +37,6 @@ #include -/** - * Hypervisor-specific bi-directional communication channel. Should never - * execute on bare metal hardware. The caller must make sure to check for - * supported hypervisor before using these macros. - * - * The last two parameters are both input and output and must be initialized. - * - * @cmd: [IN] Message Cmd - * @in_ebx: [IN] Message Len, through EBX - * @in_si: [IN] Input argument through SI, set to 0 if not used - * @in_di: [IN] Input argument through DI, set ot 0 if not used - * @flags: [IN] hypercall flags + [channel id] - * @magic: [IN] hypervisor magic value - * @eax: [OUT] value of EAX register - * @ebx: [OUT] e.g. status from an HB message status command - * @ecx: [OUT] e.g. status from a non-HB message status command - * @edx: [OUT] e.g. channel id - * @si: [OUT] - * @di: [OUT] - */ -#define VMW_PORT(cmd, in_ebx, in_si, in_di, \ - flags, magic, \ - eax, ebx, ecx, edx, si, di) \ -({ \ - asm volatile (VMWARE_HYPERCALL : \ - "=a"(eax), \ - "=b"(ebx), \ - "=c"(ecx), \ - "=d"(edx), \ - "=S"(si), \ - "=D"(di) : \ - "a"(magic), \ - "b"(in_ebx), \ - "c"(cmd), \ - "d"(flags), \ - "S"(in_si), \ - "D"(in_di) : \ - "memory"); \ -}) - - -/** - * Hypervisor-specific bi-directional communication channel. Should never - * execute on bare metal hardware. The caller must make sure to check for - * supported hypervisor before using these macros. - * - * The last 3 parameters are both input and output and must be initialized. - * - * @cmd: [IN] Message Cmd - * @in_ecx: [IN] Message Len, through ECX - * @in_si: [IN] Input argument through SI, set to 0 if not used - * @in_di: [IN] Input argument through DI, set to 0 if not used - * @flags: [IN] hypercall flags + [channel id] - * @magic: [IN] hypervisor magic value - * @bp: [IN] - * @eax: [OUT] value of EAX register - * @ebx: [OUT] e.g. status from an HB message status command - * @ecx: [OUT] e.g. status from a non-HB message status command - * @edx: [OUT] e.g. channel id - * @si: [OUT] - * @di: [OUT] - */ -#ifdef __x86_64__ - -#define VMW_PORT_HB_OUT(cmd, in_ecx, in_si, in_di, \ - flags, magic, bp, \ - eax, ebx, ecx, edx, si, di) \ -({ \ - asm volatile ( \ - UNWIND_HINT_SAVE \ - "push %%rbp;" \ - UNWIND_HINT_UNDEFINED \ - "mov %12, %%rbp;" \ - VMWARE_HYPERCALL_HB_OUT \ - "pop %%rbp;" \ - UNWIND_HINT_RESTORE : \ - "=a"(eax), \ - "=b"(ebx), \ - "=c"(ecx), \ - "=d"(edx), \ - "=S"(si), \ - "=D"(di) : \ - "a"(magic), \ - "b"(cmd), \ - "c"(in_ecx), \ - "d"(flags), \ - "S"(in_si), \ - "D"(in_di), \ - "r"(bp) : \ - "memory", "cc"); \ -}) - - -#define VMW_PORT_HB_IN(cmd, in_ecx, in_si, in_di, \ - flags, magic, bp, \ - eax, ebx, ecx, edx, si, di) \ -({ \ - asm volatile ( \ - UNWIND_HINT_SAVE \ - "push %%rbp;" \ - UNWIND_HINT_UNDEFINED \ - "mov %12, %%rbp;" \ - VMWARE_HYPERCALL_HB_IN \ - "pop %%rbp;" \ - UNWIND_HINT_RESTORE : \ - "=a"(eax), \ - "=b"(ebx), \ - "=c"(ecx), \ - "=d"(edx), \ - "=S"(si), \ - "=D"(di) : \ - "a"(magic), \ - "b"(cmd), \ - "c"(in_ecx), \ - "d"(flags), \ - "S"(in_si), \ - "D"(in_di), \ - "r"(bp) : \ - "memory", "cc"); \ -}) - -#elif defined(__i386__) - -/* - * In the 32-bit version of this macro, we store bp in a memory location - * because we've ran out of registers. - * Now we can't reference that memory location while we've modified - * %esp or %ebp, so we first push it on the stack, just before we push - * %ebp, and then when we need it we read it from the stack where we - * just pushed it. - */ -#define VMW_PORT_HB_OUT(cmd, in_ecx, in_si, in_di, \ - flags, magic, bp, \ - eax, ebx, ecx, edx, si, di) \ -({ \ - asm volatile ("push %12;" \ - "push %%ebp;" \ - "mov 0x04(%%esp), %%ebp;" \ - VMWARE_HYPERCALL_HB_OUT \ - "pop %%ebp;" \ - "add $0x04, %%esp;" : \ - "=a"(eax), \ - "=b"(ebx), \ - "=c"(ecx), \ - "=d"(edx), \ - "=S"(si), \ - "=D"(di) : \ - "a"(magic), \ - "b"(cmd), \ - "c"(in_ecx), \ - "d"(flags), \ - "S"(in_si), \ - "D"(in_di), \ - "m"(bp) : \ - "memory", "cc"); \ -}) - - -#define VMW_PORT_HB_IN(cmd, in_ecx, in_si, in_di, \ - flags, magic, bp, \ - eax, ebx, ecx, edx, si, di) \ -({ \ - asm volatile ("push %12;" \ - "push %%ebp;" \ - "mov 0x04(%%esp), %%ebp;" \ - VMWARE_HYPERCALL_HB_IN \ - "pop %%ebp;" \ - "add $0x04, %%esp;" : \ - "=a"(eax), \ - "=b"(ebx), \ - "=c"(ecx), \ - "=d"(edx), \ - "=S"(si), \ - "=D"(di) : \ - "a"(magic), \ - "b"(cmd), \ - "c"(in_ecx), \ - "d"(flags), \ - "S"(in_si), \ - "D"(in_di), \ - "m"(bp) : \ - "memory", "cc"); \ -}) -#endif /* defined(__i386__) */ - #endif /* defined(__i386__) || defined(__x86_64__) */ #endif /* _VMWGFX_MSG_X86_H */ diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c index 8092312c0a87..543526bac042 100644 --- a/drivers/hwmon/k10temp.c +++ b/drivers/hwmon/k10temp.c @@ -101,7 +101,6 @@ struct k10temp_data { #define TCCD_BIT(x) ((x) + 2) #define HAVE_TEMP(d, channel) ((d)->show_temp & BIT(channel)) -#define HAVE_TDIE(d) HAVE_TEMP(d, TDIE_BIT) struct tctl_offset { u8 model; @@ -153,8 +152,16 @@ static void read_tempreg_nb_f15(struct pci_dev *pdev, u32 *regval) static void read_tempreg_nb_zen(struct pci_dev *pdev, u32 *regval) { - amd_smn_read(amd_pci_dev_to_node_id(pdev), - ZEN_REPORTED_TEMP_CTRL_BASE, regval); + if (amd_smn_read(amd_pci_dev_to_node_id(pdev), + ZEN_REPORTED_TEMP_CTRL_BASE, regval)) + *regval = 0; +} + +static int read_ccd_temp_reg(struct k10temp_data *data, int ccd, u32 *regval) +{ + u16 node_id = amd_pci_dev_to_node_id(data->pdev); + + return amd_smn_read(node_id, ZEN_CCD_TEMP(data->ccd_offset, ccd), regval); } static long get_raw_temp(struct k10temp_data *data) @@ -205,6 +212,7 @@ static int k10temp_read_temp(struct device *dev, u32 attr, int channel, long *val) { struct k10temp_data *data = dev_get_drvdata(dev); + int ret = -EOPNOTSUPP; u32 regval; switch (attr) { @@ -221,13 +229,15 @@ static int k10temp_read_temp(struct device *dev, u32 attr, int channel, *val = 0; break; case 2 ... 13: /* Tccd{1-12} */ - amd_smn_read(amd_pci_dev_to_node_id(data->pdev), - ZEN_CCD_TEMP(data->ccd_offset, channel - 2), - ®val); + ret = read_ccd_temp_reg(data, channel - 2, ®val); + + if (ret) + return ret; + *val = (regval & ZEN_CCD_TEMP_MASK) * 125 - 49000; break; default: - return -EOPNOTSUPP; + return ret; } break; case hwmon_temp_max: @@ -243,7 +253,7 @@ static int k10temp_read_temp(struct device *dev, u32 attr, int channel, - ((regval >> 24) & 0xf)) * 500 + 52000; break; default: - return -EOPNOTSUPP; + return ret; } return 0; } @@ -259,11 +269,11 @@ static int k10temp_read(struct device *dev, enum hwmon_sensor_types type, } } -static umode_t k10temp_is_visible(const void *_data, +static umode_t k10temp_is_visible(const void *drvdata, enum hwmon_sensor_types type, u32 attr, int channel) { - const struct k10temp_data *data = _data; + const struct k10temp_data *data = drvdata; struct pci_dev *pdev = data->pdev; u32 reg; @@ -374,15 +384,25 @@ static const struct hwmon_chip_info k10temp_chip_info = { .info = k10temp_info, }; -static void k10temp_get_ccd_support(struct pci_dev *pdev, - struct k10temp_data *data, int limit) +static void k10temp_get_ccd_support(struct k10temp_data *data, int limit) { u32 regval; int i; for (i = 0; i < limit; i++) { - amd_smn_read(amd_pci_dev_to_node_id(pdev), - ZEN_CCD_TEMP(data->ccd_offset, i), ®val); + /* + * Ignore inaccessible CCDs. + * + * Some systems will return a register value of 0, and the TEMP_VALID + * bit check below will naturally fail. + * + * Other systems will return a PCI_ERROR_RESPONSE (0xFFFFFFFF) for + * the register value. And this will incorrectly pass the TEMP_VALID + * bit check. + */ + if (read_ccd_temp_reg(data, i, ®val)) + continue; + if (regval & ZEN_CCD_TEMP_VALID) data->show_temp |= BIT(TCCD_BIT(i)); } @@ -434,18 +454,18 @@ static int k10temp_probe(struct pci_dev *pdev, const struct pci_device_id *id) case 0x11: /* Zen APU */ case 0x18: /* Zen+ APU */ data->ccd_offset = 0x154; - k10temp_get_ccd_support(pdev, data, 4); + k10temp_get_ccd_support(data, 4); break; case 0x31: /* Zen2 Threadripper */ case 0x60: /* Renoir */ case 0x68: /* Lucienne */ case 0x71: /* Zen2 */ data->ccd_offset = 0x154; - k10temp_get_ccd_support(pdev, data, 8); + k10temp_get_ccd_support(data, 8); break; case 0xa0 ... 0xaf: data->ccd_offset = 0x300; - k10temp_get_ccd_support(pdev, data, 8); + k10temp_get_ccd_support(data, 8); break; } } else if (boot_cpu_data.x86 == 0x19) { @@ -459,21 +479,21 @@ static int k10temp_probe(struct pci_dev *pdev, const struct pci_device_id *id) case 0x21: /* Zen3 Ryzen Desktop */ case 0x50 ... 0x5f: /* Green Sardine */ data->ccd_offset = 0x154; - k10temp_get_ccd_support(pdev, data, 8); + k10temp_get_ccd_support(data, 8); break; case 0x40 ... 0x4f: /* Yellow Carp */ data->ccd_offset = 0x300; - k10temp_get_ccd_support(pdev, data, 8); + k10temp_get_ccd_support(data, 8); break; case 0x60 ... 0x6f: case 0x70 ... 0x7f: data->ccd_offset = 0x308; - k10temp_get_ccd_support(pdev, data, 8); + k10temp_get_ccd_support(data, 8); break; case 0x10 ... 0x1f: case 0xa0 ... 0xaf: data->ccd_offset = 0x300; - k10temp_get_ccd_support(pdev, data, 12); + k10temp_get_ccd_support(data, 12); break; } } else if (boot_cpu_data.x86 == 0x1a) { diff --git a/drivers/input/mouse/vmmouse.c b/drivers/input/mouse/vmmouse.c index ea9eff7c8099..fb1d986a6895 100644 --- a/drivers/input/mouse/vmmouse.c +++ b/drivers/input/mouse/vmmouse.c @@ -21,19 +21,16 @@ #include "psmouse.h" #include "vmmouse.h" -#define VMMOUSE_PROTO_MAGIC 0x564D5868U - /* * Main commands supported by the vmmouse hypervisor port. */ -#define VMMOUSE_PROTO_CMD_GETVERSION 10 -#define VMMOUSE_PROTO_CMD_ABSPOINTER_DATA 39 -#define VMMOUSE_PROTO_CMD_ABSPOINTER_STATUS 40 -#define VMMOUSE_PROTO_CMD_ABSPOINTER_COMMAND 41 -#define VMMOUSE_PROTO_CMD_ABSPOINTER_RESTRICT 86 +#define VMWARE_CMD_ABSPOINTER_DATA 39 +#define VMWARE_CMD_ABSPOINTER_STATUS 40 +#define VMWARE_CMD_ABSPOINTER_COMMAND 41 +#define VMWARE_CMD_ABSPOINTER_RESTRICT 86 /* - * Subcommands for VMMOUSE_PROTO_CMD_ABSPOINTER_COMMAND + * Subcommands for VMWARE_CMD_ABSPOINTER_COMMAND */ #define VMMOUSE_CMD_ENABLE 0x45414552U #define VMMOUSE_CMD_DISABLE 0x000000f5U @@ -76,28 +73,6 @@ struct vmmouse_data { char dev_name[128]; }; -/* - * Hypervisor-specific bi-directional communication channel - * implementing the vmmouse protocol. Should never execute on - * bare metal hardware. - */ -#define VMMOUSE_CMD(cmd, in1, out1, out2, out3, out4) \ -({ \ - unsigned long __dummy1, __dummy2; \ - __asm__ __volatile__ (VMWARE_HYPERCALL : \ - "=a"(out1), \ - "=b"(out2), \ - "=c"(out3), \ - "=d"(out4), \ - "=S"(__dummy1), \ - "=D"(__dummy2) : \ - "a"(VMMOUSE_PROTO_MAGIC), \ - "b"(in1), \ - "c"(VMMOUSE_PROTO_CMD_##cmd), \ - "d"(0) : \ - "memory"); \ -}) - /** * vmmouse_report_button - report button state on the correct input device * @@ -145,14 +120,12 @@ static psmouse_ret_t vmmouse_report_events(struct psmouse *psmouse) struct input_dev *abs_dev = priv->abs_dev; struct input_dev *pref_dev; u32 status, x, y, z; - u32 dummy1, dummy2, dummy3; unsigned int queue_length; unsigned int count = 255; while (count--) { /* See if we have motion data. */ - VMMOUSE_CMD(ABSPOINTER_STATUS, 0, - status, dummy1, dummy2, dummy3); + status = vmware_hypercall1(VMWARE_CMD_ABSPOINTER_STATUS, 0); if ((status & VMMOUSE_ERROR) == VMMOUSE_ERROR) { psmouse_err(psmouse, "failed to fetch status data\n"); /* @@ -172,7 +145,8 @@ static psmouse_ret_t vmmouse_report_events(struct psmouse *psmouse) } /* Now get it */ - VMMOUSE_CMD(ABSPOINTER_DATA, 4, status, x, y, z); + status = vmware_hypercall4(VMWARE_CMD_ABSPOINTER_DATA, 4, + &x, &y, &z); /* * And report what we've got. Prefer to report button @@ -247,14 +221,10 @@ static psmouse_ret_t vmmouse_process_byte(struct psmouse *psmouse) static void vmmouse_disable(struct psmouse *psmouse) { u32 status; - u32 dummy1, dummy2, dummy3, dummy4; - VMMOUSE_CMD(ABSPOINTER_COMMAND, VMMOUSE_CMD_DISABLE, - dummy1, dummy2, dummy3, dummy4); - - VMMOUSE_CMD(ABSPOINTER_STATUS, 0, - status, dummy1, dummy2, dummy3); + vmware_hypercall1(VMWARE_CMD_ABSPOINTER_COMMAND, VMMOUSE_CMD_DISABLE); + status = vmware_hypercall1(VMWARE_CMD_ABSPOINTER_STATUS, 0); if ((status & VMMOUSE_ERROR) != VMMOUSE_ERROR) psmouse_warn(psmouse, "failed to disable vmmouse device\n"); } @@ -271,26 +241,24 @@ static void vmmouse_disable(struct psmouse *psmouse) static int vmmouse_enable(struct psmouse *psmouse) { u32 status, version; - u32 dummy1, dummy2, dummy3, dummy4; /* * Try enabling the device. If successful, we should be able to * read valid version ID back from it. */ - VMMOUSE_CMD(ABSPOINTER_COMMAND, VMMOUSE_CMD_ENABLE, - dummy1, dummy2, dummy3, dummy4); + vmware_hypercall1(VMWARE_CMD_ABSPOINTER_COMMAND, VMMOUSE_CMD_ENABLE); /* * See if version ID can be retrieved. */ - VMMOUSE_CMD(ABSPOINTER_STATUS, 0, status, dummy1, dummy2, dummy3); + status = vmware_hypercall1(VMWARE_CMD_ABSPOINTER_STATUS, 0); if ((status & 0x0000ffff) == 0) { psmouse_dbg(psmouse, "empty flags - assuming no device\n"); return -ENXIO; } - VMMOUSE_CMD(ABSPOINTER_DATA, 1 /* single item */, - version, dummy1, dummy2, dummy3); + version = vmware_hypercall1(VMWARE_CMD_ABSPOINTER_DATA, + 1 /* single item */); if (version != VMMOUSE_VERSION_ID) { psmouse_dbg(psmouse, "Unexpected version value: %u vs %u\n", (unsigned) version, VMMOUSE_VERSION_ID); @@ -301,11 +269,11 @@ static int vmmouse_enable(struct psmouse *psmouse) /* * Restrict ioport access, if possible. */ - VMMOUSE_CMD(ABSPOINTER_RESTRICT, VMMOUSE_RESTRICT_CPL0, - dummy1, dummy2, dummy3, dummy4); + vmware_hypercall1(VMWARE_CMD_ABSPOINTER_RESTRICT, + VMMOUSE_RESTRICT_CPL0); - VMMOUSE_CMD(ABSPOINTER_COMMAND, VMMOUSE_CMD_REQUEST_ABSOLUTE, - dummy1, dummy2, dummy3, dummy4); + vmware_hypercall1(VMWARE_CMD_ABSPOINTER_COMMAND, + VMMOUSE_CMD_REQUEST_ABSOLUTE); return 0; } @@ -342,7 +310,7 @@ static bool vmmouse_check_hypervisor(void) */ int vmmouse_detect(struct psmouse *psmouse, bool set_properties) { - u32 response, version, dummy1, dummy2; + u32 response, version, type; if (!vmmouse_check_hypervisor()) { psmouse_dbg(psmouse, @@ -351,9 +319,9 @@ int vmmouse_detect(struct psmouse *psmouse, bool set_properties) } /* Check if the device is present */ - response = ~VMMOUSE_PROTO_MAGIC; - VMMOUSE_CMD(GETVERSION, 0, version, response, dummy1, dummy2); - if (response != VMMOUSE_PROTO_MAGIC || version == 0xffffffffU) + response = ~VMWARE_HYPERVISOR_MAGIC; + version = vmware_hypercall3(VMWARE_CMD_GETVERSION, 0, &response, &type); + if (response != VMWARE_HYPERVISOR_MAGIC || version == 0xffffffffU) return -ENXIO; if (set_properties) { diff --git a/drivers/ptp/ptp_vmw.c b/drivers/ptp/ptp_vmw.c index 7ec90359428a..20ab05c4daa8 100644 --- a/drivers/ptp/ptp_vmw.c +++ b/drivers/ptp/ptp_vmw.c @@ -14,7 +14,6 @@ #include #include -#define VMWARE_MAGIC 0x564D5868 #define VMWARE_CMD_PCLK(nr) ((nr << 16) | 97) #define VMWARE_CMD_PCLK_GETTIME VMWARE_CMD_PCLK(0) @@ -24,15 +23,10 @@ static struct ptp_clock *ptp_vmw_clock; static int ptp_vmw_pclk_read(u64 *ns) { - u32 ret, nsec_hi, nsec_lo, unused1, unused2, unused3; - - asm volatile (VMWARE_HYPERCALL : - "=a"(ret), "=b"(nsec_hi), "=c"(nsec_lo), "=d"(unused1), - "=S"(unused2), "=D"(unused3) : - "a"(VMWARE_MAGIC), "b"(0), - "c"(VMWARE_CMD_PCLK_GETTIME), "d"(0) : - "memory"); + u32 ret, nsec_hi, nsec_lo; + ret = vmware_hypercall3(VMWARE_CMD_PCLK_GETTIME, 0, + &nsec_hi, &nsec_lo); if (ret == 0) *ns = ((u64)nsec_hi << 32) | nsec_lo; return ret; diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c index 654290a8e1ba..f714009b9ff7 100644 --- a/drivers/virt/coco/sev-guest/sev-guest.c +++ b/drivers/virt/coco/sev-guest/sev-guest.c @@ -2,7 +2,7 @@ /* * AMD Secure Encrypted Virtualization (SEV) guest driver interface * - * Copyright (C) 2021 Advanced Micro Devices, Inc. + * Copyright (C) 2021-2024 Advanced Micro Devices, Inc. * * Author: Brijesh Singh */ @@ -23,6 +23,7 @@ #include #include #include +#include #include #include @@ -38,6 +39,8 @@ #define SNP_REQ_MAX_RETRY_DURATION (60*HZ) #define SNP_REQ_RETRY_DELAY (2*HZ) +#define SVSM_MAX_RETRIES 3 + struct snp_guest_crypto { struct crypto_aead *tfm; u8 *iv, *authtag; @@ -70,8 +73,15 @@ struct snp_guest_dev { u8 *vmpck; }; -static u32 vmpck_id; -module_param(vmpck_id, uint, 0444); +/* + * The VMPCK ID represents the key used by the SNP guest to communicate with the + * SEV firmware in the AMD Secure Processor (ASP, aka PSP). By default, the key + * used will be the key associated with the VMPL at which the guest is running. + * Should the default key be wiped (see snp_disable_vmpck()), this parameter + * allows for using one of the remaining VMPCKs. + */ +static int vmpck_id = -1; +module_param(vmpck_id, int, 0444); MODULE_PARM_DESC(vmpck_id, "The VMPCK ID to use when communicating with the PSP."); /* Mutex to serialize the shared buffer access and command handling. */ @@ -783,6 +793,143 @@ struct snp_msg_cert_entry { u32 length; }; +static int sev_svsm_report_new(struct tsm_report *report, void *data) +{ + unsigned int rep_len, man_len, certs_len; + struct tsm_desc *desc = &report->desc; + struct svsm_attest_call ac = {}; + unsigned int retry_count; + void *rep, *man, *certs; + struct svsm_call call; + unsigned int size; + bool try_again; + void *buffer; + u64 call_id; + int ret; + + /* + * Allocate pages for the request: + * - Report blob (4K) + * - Manifest blob (4K) + * - Certificate blob (16K) + * + * Above addresses must be 4K aligned + */ + rep_len = SZ_4K; + man_len = SZ_4K; + certs_len = SEV_FW_BLOB_MAX_SIZE; + + guard(mutex)(&snp_cmd_mutex); + + if (guid_is_null(&desc->service_guid)) { + call_id = SVSM_ATTEST_CALL(SVSM_ATTEST_SERVICES); + } else { + export_guid(ac.service_guid, &desc->service_guid); + ac.service_manifest_ver = desc->service_manifest_version; + + call_id = SVSM_ATTEST_CALL(SVSM_ATTEST_SINGLE_SERVICE); + } + + retry_count = 0; + +retry: + memset(&call, 0, sizeof(call)); + + size = rep_len + man_len + certs_len; + buffer = alloc_pages_exact(size, __GFP_ZERO); + if (!buffer) + return -ENOMEM; + + rep = buffer; + ac.report_buf.pa = __pa(rep); + ac.report_buf.len = rep_len; + + man = rep + rep_len; + ac.manifest_buf.pa = __pa(man); + ac.manifest_buf.len = man_len; + + certs = man + man_len; + ac.certificates_buf.pa = __pa(certs); + ac.certificates_buf.len = certs_len; + + ac.nonce.pa = __pa(desc->inblob); + ac.nonce.len = desc->inblob_len; + + ret = snp_issue_svsm_attest_req(call_id, &call, &ac); + if (ret) { + free_pages_exact(buffer, size); + + switch (call.rax_out) { + case SVSM_ERR_INVALID_PARAMETER: + try_again = false; + + if (ac.report_buf.len > rep_len) { + rep_len = PAGE_ALIGN(ac.report_buf.len); + try_again = true; + } + + if (ac.manifest_buf.len > man_len) { + man_len = PAGE_ALIGN(ac.manifest_buf.len); + try_again = true; + } + + if (ac.certificates_buf.len > certs_len) { + certs_len = PAGE_ALIGN(ac.certificates_buf.len); + try_again = true; + } + + /* If one of the buffers wasn't large enough, retry the request */ + if (try_again && retry_count < SVSM_MAX_RETRIES) { + retry_count++; + goto retry; + } + + return -EINVAL; + default: + pr_err_ratelimited("SVSM attestation request failed (%d / 0x%llx)\n", + ret, call.rax_out); + return -EINVAL; + } + } + + /* + * Allocate all the blob memory buffers at once so that the cleanup is + * done for errors that occur after the first allocation (i.e. before + * using no_free_ptr()). + */ + rep_len = ac.report_buf.len; + void *rbuf __free(kvfree) = kvzalloc(rep_len, GFP_KERNEL); + + man_len = ac.manifest_buf.len; + void *mbuf __free(kvfree) = kvzalloc(man_len, GFP_KERNEL); + + certs_len = ac.certificates_buf.len; + void *cbuf __free(kvfree) = certs_len ? kvzalloc(certs_len, GFP_KERNEL) : NULL; + + if (!rbuf || !mbuf || (certs_len && !cbuf)) { + free_pages_exact(buffer, size); + return -ENOMEM; + } + + memcpy(rbuf, rep, rep_len); + report->outblob = no_free_ptr(rbuf); + report->outblob_len = rep_len; + + memcpy(mbuf, man, man_len); + report->manifestblob = no_free_ptr(mbuf); + report->manifestblob_len = man_len; + + if (certs_len) { + memcpy(cbuf, certs, certs_len); + report->auxblob = no_free_ptr(cbuf); + report->auxblob_len = certs_len; + } + + free_pages_exact(buffer, size); + + return 0; +} + static int sev_report_new(struct tsm_report *report, void *data) { struct snp_msg_cert_entry *cert_table; @@ -797,6 +944,13 @@ static int sev_report_new(struct tsm_report *report, void *data) if (desc->inblob_len != SNP_REPORT_USER_DATA_SIZE) return -EINVAL; + if (desc->service_provider) { + if (strcmp(desc->service_provider, "svsm")) + return -EINVAL; + + return sev_svsm_report_new(report, data); + } + void *buf __free(kvfree) = kvzalloc(size, GFP_KERNEL); if (!buf) return -ENOMEM; @@ -885,9 +1039,42 @@ static int sev_report_new(struct tsm_report *report, void *data) return 0; } -static const struct tsm_ops sev_tsm_ops = { +static bool sev_report_attr_visible(int n) +{ + switch (n) { + case TSM_REPORT_GENERATION: + case TSM_REPORT_PROVIDER: + case TSM_REPORT_PRIVLEVEL: + case TSM_REPORT_PRIVLEVEL_FLOOR: + return true; + case TSM_REPORT_SERVICE_PROVIDER: + case TSM_REPORT_SERVICE_GUID: + case TSM_REPORT_SERVICE_MANIFEST_VER: + return snp_vmpl; + } + + return false; +} + +static bool sev_report_bin_attr_visible(int n) +{ + switch (n) { + case TSM_REPORT_INBLOB: + case TSM_REPORT_OUTBLOB: + case TSM_REPORT_AUXBLOB: + return true; + case TSM_REPORT_MANIFESTBLOB: + return snp_vmpl; + } + + return false; +} + +static struct tsm_ops sev_tsm_ops = { .name = KBUILD_MODNAME, .report_new = sev_report_new, + .report_attr_visible = sev_report_attr_visible, + .report_bin_attr_visible = sev_report_bin_attr_visible, }; static void unregister_sev_tsm(void *data) @@ -923,6 +1110,10 @@ static int __init sev_guest_probe(struct platform_device *pdev) if (!snp_dev) goto e_unmap; + /* Adjust the default VMPCK key based on the executing VMPL level */ + if (vmpck_id == -1) + vmpck_id = snp_vmpl; + ret = -EINVAL; snp_dev->vmpck = get_vmpck(vmpck_id, secrets, &snp_dev->os_area_msg_seqno); if (!snp_dev->vmpck) { @@ -968,7 +1159,10 @@ static int __init sev_guest_probe(struct platform_device *pdev) snp_dev->input.resp_gpa = __pa(snp_dev->response); snp_dev->input.data_gpa = __pa(snp_dev->certs_data); - ret = tsm_register(&sev_tsm_ops, snp_dev, &tsm_report_extra_type); + /* Set the privlevel_floor attribute based on the vmpck_id */ + sev_tsm_ops.privlevel_floor = vmpck_id; + + ret = tsm_register(&sev_tsm_ops, snp_dev); if (ret) goto e_free_cert_data; @@ -1009,8 +1203,13 @@ static void __exit sev_guest_remove(struct platform_device *pdev) * This driver is meant to be a common SEV guest interface driver and to * support any SEV guest API. As such, even though it has been introduced * with the SEV-SNP support, it is named "sev-guest". + * + * sev_guest_remove() lives in .exit.text. For drivers registered via + * module_platform_driver_probe() this is ok because they cannot get unbound + * at runtime. So mark the driver struct with __refdata to prevent modpost + * triggering a section mismatch warning. */ -static struct platform_driver sev_guest_driver = { +static struct platform_driver sev_guest_driver __refdata = { .remove_new = __exit_p(sev_guest_remove), .driver = { .name = "sev-guest", diff --git a/drivers/virt/coco/tdx-guest/tdx-guest.c b/drivers/virt/coco/tdx-guest/tdx-guest.c index 1253bf76b570..2acba56ad42e 100644 --- a/drivers/virt/coco/tdx-guest/tdx-guest.c +++ b/drivers/virt/coco/tdx-guest/tdx-guest.c @@ -249,6 +249,28 @@ done: return ret; } +static bool tdx_report_attr_visible(int n) +{ + switch (n) { + case TSM_REPORT_GENERATION: + case TSM_REPORT_PROVIDER: + return true; + } + + return false; +} + +static bool tdx_report_bin_attr_visible(int n) +{ + switch (n) { + case TSM_REPORT_INBLOB: + case TSM_REPORT_OUTBLOB: + return true; + } + + return false; +} + static long tdx_guest_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -281,6 +303,8 @@ MODULE_DEVICE_TABLE(x86cpu, tdx_guest_ids); static const struct tsm_ops tdx_tsm_ops = { .name = KBUILD_MODNAME, .report_new = tdx_report_new, + .report_attr_visible = tdx_report_attr_visible, + .report_bin_attr_visible = tdx_report_bin_attr_visible, }; static int __init tdx_guest_init(void) @@ -301,7 +325,7 @@ static int __init tdx_guest_init(void) goto free_misc; } - ret = tsm_register(&tdx_tsm_ops, NULL, NULL); + ret = tsm_register(&tdx_tsm_ops, NULL); if (ret) goto free_quote; diff --git a/drivers/virt/coco/tsm.c b/drivers/virt/coco/tsm.c index d1c2db83a8ca..9432d4e303f1 100644 --- a/drivers/virt/coco/tsm.c +++ b/drivers/virt/coco/tsm.c @@ -14,7 +14,6 @@ static struct tsm_provider { const struct tsm_ops *ops; - const struct config_item_type *type; void *data; } provider; static DECLARE_RWSEM(tsm_rwsem); @@ -35,7 +34,7 @@ static DECLARE_RWSEM(tsm_rwsem); * The attestation report format is TSM provider specific, when / if a standard * materializes that can be published instead of the vendor layout. Until then * the 'provider' attribute indicates the format of 'outblob', and optionally - * 'auxblob'. + * 'auxblob' and 'manifestblob'. */ struct tsm_report_state { @@ -48,6 +47,7 @@ struct tsm_report_state { enum tsm_data_select { TSM_REPORT, TSM_CERTS, + TSM_MANIFEST, }; static struct tsm_report *to_tsm_report(struct config_item *cfg) @@ -119,6 +119,74 @@ static ssize_t tsm_report_privlevel_floor_show(struct config_item *cfg, } CONFIGFS_ATTR_RO(tsm_report_, privlevel_floor); +static ssize_t tsm_report_service_provider_store(struct config_item *cfg, + const char *buf, size_t len) +{ + struct tsm_report *report = to_tsm_report(cfg); + size_t sp_len; + char *sp; + int rc; + + guard(rwsem_write)(&tsm_rwsem); + rc = try_advance_write_generation(report); + if (rc) + return rc; + + sp_len = (buf[len - 1] != '\n') ? len : len - 1; + + sp = kstrndup(buf, sp_len, GFP_KERNEL); + if (!sp) + return -ENOMEM; + kfree(report->desc.service_provider); + + report->desc.service_provider = sp; + + return len; +} +CONFIGFS_ATTR_WO(tsm_report_, service_provider); + +static ssize_t tsm_report_service_guid_store(struct config_item *cfg, + const char *buf, size_t len) +{ + struct tsm_report *report = to_tsm_report(cfg); + int rc; + + guard(rwsem_write)(&tsm_rwsem); + rc = try_advance_write_generation(report); + if (rc) + return rc; + + report->desc.service_guid = guid_null; + + rc = guid_parse(buf, &report->desc.service_guid); + if (rc) + return rc; + + return len; +} +CONFIGFS_ATTR_WO(tsm_report_, service_guid); + +static ssize_t tsm_report_service_manifest_version_store(struct config_item *cfg, + const char *buf, size_t len) +{ + struct tsm_report *report = to_tsm_report(cfg); + unsigned int val; + int rc; + + rc = kstrtouint(buf, 0, &val); + if (rc) + return rc; + + guard(rwsem_write)(&tsm_rwsem); + rc = try_advance_write_generation(report); + if (rc) + return rc; + report->desc.service_manifest_version = val; + + return len; +} +CONFIGFS_ATTR_WO(tsm_report_, service_manifest_version); + static ssize_t tsm_report_inblob_write(struct config_item *cfg, const void *buf, size_t count) { @@ -163,6 +231,9 @@ static ssize_t __read_report(struct tsm_report *report, void *buf, size_t count, if (select == TSM_REPORT) { out = report->outblob; len = report->outblob_len; + } else if (select == TSM_MANIFEST) { + out = report->manifestblob; + len = report->manifestblob_len; } else { out = report->auxblob; len = report->auxblob_len; @@ -188,7 +259,7 @@ static ssize_t read_cached_report(struct tsm_report *report, void *buf, /* * A given TSM backend always fills in ->outblob regardless of - * whether the report includes an auxblob or not. + * whether the report includes an auxblob/manifestblob or not. */ if (!report->outblob || state->read_generation != state->write_generation) @@ -224,8 +295,10 @@ static ssize_t tsm_report_read(struct tsm_report *report, void *buf, kvfree(report->outblob); kvfree(report->auxblob); + kvfree(report->manifestblob); report->outblob = NULL; report->auxblob = NULL; + report->manifestblob = NULL; rc = ops->report_new(report, provider.data); if (rc < 0) return rc; @@ -252,34 +325,31 @@ static ssize_t tsm_report_auxblob_read(struct config_item *cfg, void *buf, } CONFIGFS_BIN_ATTR_RO(tsm_report_, auxblob, NULL, TSM_OUTBLOB_MAX); -#define TSM_DEFAULT_ATTRS() \ - &tsm_report_attr_generation, \ - &tsm_report_attr_provider +static ssize_t tsm_report_manifestblob_read(struct config_item *cfg, void *buf, + size_t count) +{ + struct tsm_report *report = to_tsm_report(cfg); + + return tsm_report_read(report, buf, count, TSM_MANIFEST); +} +CONFIGFS_BIN_ATTR_RO(tsm_report_, manifestblob, NULL, TSM_OUTBLOB_MAX); static struct configfs_attribute *tsm_report_attrs[] = { - TSM_DEFAULT_ATTRS(), + [TSM_REPORT_GENERATION] = &tsm_report_attr_generation, + [TSM_REPORT_PROVIDER] = &tsm_report_attr_provider, + [TSM_REPORT_PRIVLEVEL] = &tsm_report_attr_privlevel, + [TSM_REPORT_PRIVLEVEL_FLOOR] = &tsm_report_attr_privlevel_floor, + [TSM_REPORT_SERVICE_PROVIDER] = &tsm_report_attr_service_provider, + [TSM_REPORT_SERVICE_GUID] = &tsm_report_attr_service_guid, + [TSM_REPORT_SERVICE_MANIFEST_VER] = &tsm_report_attr_service_manifest_version, NULL, }; -static struct configfs_attribute *tsm_report_extra_attrs[] = { - TSM_DEFAULT_ATTRS(), - &tsm_report_attr_privlevel, - &tsm_report_attr_privlevel_floor, - NULL, -}; - -#define TSM_DEFAULT_BIN_ATTRS() \ - &tsm_report_attr_inblob, \ - &tsm_report_attr_outblob - static struct configfs_bin_attribute *tsm_report_bin_attrs[] = { - TSM_DEFAULT_BIN_ATTRS(), - NULL, -}; - -static struct configfs_bin_attribute *tsm_report_bin_extra_attrs[] = { - TSM_DEFAULT_BIN_ATTRS(), - &tsm_report_attr_auxblob, + [TSM_REPORT_INBLOB] = &tsm_report_attr_inblob, + [TSM_REPORT_OUTBLOB] = &tsm_report_attr_outblob, + [TSM_REPORT_AUXBLOB] = &tsm_report_attr_auxblob, + [TSM_REPORT_MANIFESTBLOB] = &tsm_report_attr_manifestblob, NULL, }; @@ -288,8 +358,10 @@ static void tsm_report_item_release(struct config_item *cfg) struct tsm_report *report = to_tsm_report(cfg); struct tsm_report_state *state = to_state(report); + kvfree(report->manifestblob); kvfree(report->auxblob); kvfree(report->outblob); + kfree(report->desc.service_provider); kfree(state); } @@ -297,21 +369,44 @@ static struct configfs_item_operations tsm_report_item_ops = { .release = tsm_report_item_release, }; -const struct config_item_type tsm_report_default_type = { +static bool tsm_report_is_visible(struct config_item *item, + struct configfs_attribute *attr, int n) +{ + guard(rwsem_read)(&tsm_rwsem); + if (!provider.ops) + return false; + + if (!provider.ops->report_attr_visible) + return true; + + return provider.ops->report_attr_visible(n); +} + +static bool tsm_report_is_bin_visible(struct config_item *item, + struct configfs_bin_attribute *attr, int n) +{ + guard(rwsem_read)(&tsm_rwsem); + if (!provider.ops) + return false; + + if (!provider.ops->report_bin_attr_visible) + return true; + + return provider.ops->report_bin_attr_visible(n); +} + +static struct configfs_group_operations tsm_report_attr_group_ops = { + .is_visible = tsm_report_is_visible, + .is_bin_visible = tsm_report_is_bin_visible, +}; + +static const struct config_item_type tsm_report_type = { .ct_owner = THIS_MODULE, .ct_bin_attrs = tsm_report_bin_attrs, .ct_attrs = tsm_report_attrs, .ct_item_ops = &tsm_report_item_ops, + .ct_group_ops = &tsm_report_attr_group_ops, }; -EXPORT_SYMBOL_GPL(tsm_report_default_type); - -const struct config_item_type tsm_report_extra_type = { - .ct_owner = THIS_MODULE, - .ct_bin_attrs = tsm_report_bin_extra_attrs, - .ct_attrs = tsm_report_extra_attrs, - .ct_item_ops = &tsm_report_item_ops, -}; -EXPORT_SYMBOL_GPL(tsm_report_extra_type); static struct config_item *tsm_report_make_item(struct config_group *group, const char *name) @@ -326,7 +421,7 @@ static struct config_item *tsm_report_make_item(struct config_group *group, if (!state) return ERR_PTR(-ENOMEM); - config_item_init_type_name(&state->cfg, name, provider.type); + config_item_init_type_name(&state->cfg, name, &tsm_report_type); return &state->cfg; } @@ -353,16 +448,10 @@ static struct configfs_subsystem tsm_configfs = { .su_mutex = __MUTEX_INITIALIZER(tsm_configfs.su_mutex), }; -int tsm_register(const struct tsm_ops *ops, void *priv, - const struct config_item_type *type) +int tsm_register(const struct tsm_ops *ops, void *priv) { const struct tsm_ops *conflict; - if (!type) - type = &tsm_report_default_type; - if (!(type == &tsm_report_default_type || type == &tsm_report_extra_type)) - return -EINVAL; - guard(rwsem_write)(&tsm_rwsem); conflict = provider.ops; if (conflict) { @@ -372,7 +461,6 @@ int tsm_register(const struct tsm_ops *ops, void *priv, provider.ops = ops; provider.data = priv; - provider.type = type; return 0; } EXPORT_SYMBOL_GPL(tsm_register); @@ -384,7 +472,6 @@ int tsm_unregister(const struct tsm_ops *ops) return -EBUSY; provider.ops = NULL; provider.data = NULL; - provider.type = NULL; return 0; } EXPORT_SYMBOL_GPL(tsm_unregister); diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index 18677cd4e62f..43d6bde1adcc 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -580,6 +580,7 @@ static void detach_attrs(struct config_item * item) static int populate_attrs(struct config_item *item) { const struct config_item_type *t = item->ci_type; + struct configfs_group_operations *ops; struct configfs_attribute *attr; struct configfs_bin_attribute *bin_attr; int error = 0; @@ -587,14 +588,23 @@ static int populate_attrs(struct config_item *item) if (!t) return -EINVAL; + + ops = t->ct_group_ops; + if (t->ct_attrs) { for (i = 0; (attr = t->ct_attrs[i]) != NULL; i++) { + if (ops && ops->is_visible && !ops->is_visible(item, attr, i)) + continue; + if ((error = configfs_create_file(item, attr))) break; } } if (t->ct_bin_attrs) { for (i = 0; (bin_attr = t->ct_bin_attrs[i]) != NULL; i++) { + if (ops && ops->is_bin_visible && !ops->is_bin_visible(item, bin_attr, i)) + continue; + error = configfs_create_bin_file(item, bin_attr); if (error) break; diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index ae747c89d92c..e27958ef8264 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -1194,11 +1194,23 @@ struct acpi_madt_generic_translator { struct acpi_madt_multiproc_wakeup { struct acpi_subtable_header header; - u16 mailbox_version; + u16 version; u32 reserved; /* reserved - must be zero */ - u64 base_address; + u64 mailbox_address; + u64 reset_vector; }; +/* Values for Version field above */ + +enum acpi_madt_multiproc_wakeup_version { + ACPI_MADT_MP_WAKEUP_VERSION_NONE = 0, + ACPI_MADT_MP_WAKEUP_VERSION_V1 = 1, + ACPI_MADT_MP_WAKEUP_VERSION_RESERVED = 2, /* 2 and greater are reserved */ +}; + +#define ACPI_MADT_MP_WAKEUP_SIZE_V0 16 +#define ACPI_MADT_MP_WAKEUP_SIZE_V1 24 + #define ACPI_MULTIPROC_WAKEUP_MB_OS_SIZE 2032 #define ACPI_MULTIPROC_WAKEUP_MB_FIRMWARE_SIZE 2048 @@ -1211,7 +1223,8 @@ struct acpi_madt_multiproc_wakeup_mailbox { u8 reserved_firmware[ACPI_MULTIPROC_WAKEUP_MB_FIRMWARE_SIZE]; /* reserved for firmware use */ }; -#define ACPI_MP_WAKE_COMMAND_WAKEUP 1 +#define ACPI_MP_WAKE_COMMAND_WAKEUP 1 +#define ACPI_MP_WAKE_COMMAND_TEST 2 /* 17: CPU Core Interrupt Controller (ACPI 6.5) */ diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 2cb15fe4fe12..3dde175f4108 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -3,6 +3,7 @@ #define _LINUX_CACHEINFO_H #include +#include #include #include @@ -112,24 +113,38 @@ int acpi_get_cache_info(unsigned int cpu, const struct attribute_group *cache_get_priv_group(struct cacheinfo *this_leaf); +/* + * Get the cacheinfo structure for the cache associated with @cpu at + * level @level. + * cpuhp lock must be held. + */ +static inline struct cacheinfo *get_cpu_cacheinfo_level(int cpu, int level) +{ + struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu); + int i; + + lockdep_assert_cpus_held(); + + for (i = 0; i < ci->num_leaves; i++) { + if (ci->info_list[i].level == level) { + if (ci->info_list[i].attributes & CACHE_ID) + return &ci->info_list[i]; + return NULL; + } + } + + return NULL; +} + /* * Get the id of the cache associated with @cpu at level @level. * cpuhp lock must be held. */ static inline int get_cpu_cacheinfo_id(int cpu, int level) { - struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu); - int i; + struct cacheinfo *ci = get_cpu_cacheinfo_level(cpu, level); - for (i = 0; i < ci->num_leaves; i++) { - if (ci->info_list[i].level == level) { - if (ci->info_list[i].attributes & CACHE_ID) - return ci->info_list[i].id; - return -1; - } - } - - return -1; + return ci ? ci->id : -1; } #ifdef CONFIG_ARM64 diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h index 60693a145894..caa4b4430634 100644 --- a/include/linux/cc_platform.h +++ b/include/linux/cc_platform.h @@ -81,16 +81,6 @@ enum cc_attr { */ CC_ATTR_GUEST_SEV_SNP, - /** - * @CC_ATTR_HOTPLUG_DISABLED: Hotplug is not supported or disabled. - * - * The platform/OS is running as a guest/virtual machine does not - * support CPU hotplug feature. - * - * Examples include TDX Guest. - */ - CC_ATTR_HOTPLUG_DISABLED, - /** * @CC_ATTR_HOST_SEV_SNP: AMD SNP enabled on the host. * diff --git a/include/linux/configfs.h b/include/linux/configfs.h index 2606711adb18..c771e9d0d0b9 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -216,6 +216,9 @@ struct configfs_group_operations { struct config_group *(*make_group)(struct config_group *group, const char *name); void (*disconnect_notify)(struct config_group *group, struct config_item *item); void (*drop_item)(struct config_group *group, struct config_item *item); + bool (*is_visible)(struct config_item *item, struct configfs_attribute *attr, int n); + bool (*is_bin_visible)(struct config_item *item, struct configfs_bin_attribute *attr, + int n); }; struct configfs_subsystem { diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 861c3bfc5f17..a8926d0a28cd 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -18,6 +18,7 @@ #include #include #include +#include #include struct device; @@ -132,38 +133,6 @@ static inline int add_cpu(unsigned int cpu) { return 0;} #endif /* CONFIG_SMP */ extern const struct bus_type cpu_subsys; -extern int lockdep_is_cpus_held(void); - -#ifdef CONFIG_HOTPLUG_CPU -extern void cpus_write_lock(void); -extern void cpus_write_unlock(void); -extern void cpus_read_lock(void); -extern void cpus_read_unlock(void); -extern int cpus_read_trylock(void); -extern void lockdep_assert_cpus_held(void); -extern void cpu_hotplug_disable(void); -extern void cpu_hotplug_enable(void); -void clear_tasks_mm_cpumask(int cpu); -int remove_cpu(unsigned int cpu); -int cpu_device_down(struct device *dev); -extern void smp_shutdown_nonboot_cpus(unsigned int primary_cpu); - -#else /* CONFIG_HOTPLUG_CPU */ - -static inline void cpus_write_lock(void) { } -static inline void cpus_write_unlock(void) { } -static inline void cpus_read_lock(void) { } -static inline void cpus_read_unlock(void) { } -static inline int cpus_read_trylock(void) { return true; } -static inline void lockdep_assert_cpus_held(void) { } -static inline void cpu_hotplug_disable(void) { } -static inline void cpu_hotplug_enable(void) { } -static inline int remove_cpu(unsigned int cpu) { return -EPERM; } -static inline void smp_shutdown_nonboot_cpus(unsigned int primary_cpu) { } -#endif /* !CONFIG_HOTPLUG_CPU */ - -DEFINE_LOCK_GUARD_0(cpus_read_lock, cpus_read_lock(), cpus_read_unlock()) - #ifdef CONFIG_PM_SLEEP_SMP extern int freeze_secondary_cpus(int primary); extern void thaw_secondary_cpus(void); diff --git a/include/linux/cpuhplock.h b/include/linux/cpuhplock.h new file mode 100644 index 000000000000..f7aa20f62b87 --- /dev/null +++ b/include/linux/cpuhplock.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * include/linux/cpuhplock.h - CPU hotplug locking + * + * Locking functions for CPU hotplug. + */ +#ifndef _LINUX_CPUHPLOCK_H_ +#define _LINUX_CPUHPLOCK_H_ + +#include +#include + +struct device; + +extern int lockdep_is_cpus_held(void); + +#ifdef CONFIG_HOTPLUG_CPU +void cpus_write_lock(void); +void cpus_write_unlock(void); +void cpus_read_lock(void); +void cpus_read_unlock(void); +int cpus_read_trylock(void); +void lockdep_assert_cpus_held(void); +void cpu_hotplug_disable_offlining(void); +void cpu_hotplug_disable(void); +void cpu_hotplug_enable(void); +void clear_tasks_mm_cpumask(int cpu); +int remove_cpu(unsigned int cpu); +int cpu_device_down(struct device *dev); +void smp_shutdown_nonboot_cpus(unsigned int primary_cpu); + +#else /* CONFIG_HOTPLUG_CPU */ + +static inline void cpus_write_lock(void) { } +static inline void cpus_write_unlock(void) { } +static inline void cpus_read_lock(void) { } +static inline void cpus_read_unlock(void) { } +static inline int cpus_read_trylock(void) { return true; } +static inline void lockdep_assert_cpus_held(void) { } +static inline void cpu_hotplug_disable_offlining(void) { } +static inline void cpu_hotplug_disable(void) { } +static inline void cpu_hotplug_enable(void) { } +static inline int remove_cpu(unsigned int cpu) { return -EPERM; } +static inline void smp_shutdown_nonboot_cpus(unsigned int primary_cpu) { } +#endif /* !CONFIG_HOTPLUG_CPU */ + +DEFINE_LOCK_GUARD_0(cpus_read_lock, cpus_read_lock(), cpus_read_unlock()) + +#endif /* _LINUX_CPUHPLOCK_H_ */ diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index a365f67131ec..b0875b99e811 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -2,6 +2,7 @@ #ifndef _RESCTRL_H #define _RESCTRL_H +#include #include #include #include @@ -58,11 +59,45 @@ struct resctrl_staged_config { bool have_new_ctrl; }; +enum resctrl_domain_type { + RESCTRL_CTRL_DOMAIN, + RESCTRL_MON_DOMAIN, +}; + /** - * struct rdt_domain - group of CPUs sharing a resctrl resource + * struct rdt_domain_hdr - common header for different domain types * @list: all instances of this resource * @id: unique id for this instance + * @type: type of this instance * @cpu_mask: which CPUs share this resource + */ +struct rdt_domain_hdr { + struct list_head list; + int id; + enum resctrl_domain_type type; + struct cpumask cpu_mask; +}; + +/** + * struct rdt_ctrl_domain - group of CPUs sharing a resctrl control resource + * @hdr: common header for different domain types + * @plr: pseudo-locked region (if any) associated with domain + * @staged_config: parsed configuration to be applied + * @mbps_val: When mba_sc is enabled, this holds the array of user + * specified control values for mba_sc in MBps, indexed + * by closid + */ +struct rdt_ctrl_domain { + struct rdt_domain_hdr hdr; + struct pseudo_lock_region *plr; + struct resctrl_staged_config staged_config[CDP_NUM_TYPES]; + u32 *mbps_val; +}; + +/** + * struct rdt_mon_domain - group of CPUs sharing a resctrl monitor resource + * @hdr: common header for different domain types + * @ci: cache info for this domain * @rmid_busy_llc: bitmap of which limbo RMIDs are above threshold * @mbm_total: saved state for MBM total bandwidth * @mbm_local: saved state for MBM local bandwidth @@ -70,16 +105,10 @@ struct resctrl_staged_config { * @cqm_limbo: worker to periodically read CQM h/w counters * @mbm_work_cpu: worker CPU for MBM h/w counters * @cqm_work_cpu: worker CPU for CQM h/w counters - * @plr: pseudo-locked region (if any) associated with domain - * @staged_config: parsed configuration to be applied - * @mbps_val: When mba_sc is enabled, this holds the array of user - * specified control values for mba_sc in MBps, indexed - * by closid */ -struct rdt_domain { - struct list_head list; - int id; - struct cpumask cpu_mask; +struct rdt_mon_domain { + struct rdt_domain_hdr hdr; + struct cacheinfo *ci; unsigned long *rmid_busy_llc; struct mbm_state *mbm_total; struct mbm_state *mbm_local; @@ -87,9 +116,6 @@ struct rdt_domain { struct delayed_work cqm_limbo; int mbm_work_cpu; int cqm_work_cpu; - struct pseudo_lock_region *plr; - struct resctrl_staged_config staged_config[CDP_NUM_TYPES]; - u32 *mbps_val; }; /** @@ -150,16 +176,24 @@ struct resctrl_membw { struct rdt_parse_data; struct resctrl_schema; +enum resctrl_scope { + RESCTRL_L2_CACHE = 2, + RESCTRL_L3_CACHE = 3, + RESCTRL_L3_NODE, +}; + /** * struct rdt_resource - attributes of a resctrl resource * @rid: The index of the resource * @alloc_capable: Is allocation available on this machine * @mon_capable: Is monitor feature available on this machine * @num_rmid: Number of RMIDs available - * @cache_level: Which cache level defines scope of this resource + * @ctrl_scope: Scope of this resource for control functions + * @mon_scope: Scope of this resource for monitor functions * @cache: Cache allocation related data * @membw: If the component has bandwidth controls, their properties. - * @domains: RCU list of all domains for this resource + * @ctrl_domains: RCU list of all control domains for this resource + * @mon_domains: RCU list of all monitor domains for this resource * @name: Name to use in "schemata" file. * @data_width: Character width of data when displaying * @default_ctrl: Specifies default cache cbm or memory B/W percent. @@ -174,17 +208,19 @@ struct rdt_resource { bool alloc_capable; bool mon_capable; int num_rmid; - int cache_level; + enum resctrl_scope ctrl_scope; + enum resctrl_scope mon_scope; struct resctrl_cache cache; struct resctrl_membw membw; - struct list_head domains; + struct list_head ctrl_domains; + struct list_head mon_domains; char *name; int data_width; u32 default_ctrl; const char *format_str; int (*parse_ctrlval)(struct rdt_parse_data *data, struct resctrl_schema *s, - struct rdt_domain *d); + struct rdt_ctrl_domain *d); struct list_head evt_list; unsigned long fflags; bool cdp_capable; @@ -218,13 +254,15 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid); * Update the ctrl_val and apply this config right now. * Must be called on one of the domain's CPUs. */ -int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d, +int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_ctrl_domain *d, u32 closid, enum resctrl_conf_type t, u32 cfg_val); -u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d, +u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_ctrl_domain *d, u32 closid, enum resctrl_conf_type type); -int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d); -void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d); +int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d); +int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d); +void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d); +void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d); void resctrl_online_cpu(unsigned int cpu); void resctrl_offline_cpu(unsigned int cpu); @@ -253,7 +291,7 @@ void resctrl_offline_cpu(unsigned int cpu); * Return: * 0 on success, or -EIO, -EINVAL etc on error. */ -int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, +int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d, u32 closid, u32 rmid, enum resctrl_event_id eventid, u64 *val, void *arch_mon_ctx); @@ -286,7 +324,7 @@ static inline void resctrl_arch_rmid_read_context_check(void) * * This can be called from any CPU. */ -void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d, +void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d, u32 closid, u32 rmid, enum resctrl_event_id eventid); @@ -299,7 +337,7 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d, * * This can be called from any CPU. */ -void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_domain *d); +void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d); extern unsigned int resctrl_rmid_realloc_threshold; extern unsigned int resctrl_rmid_realloc_limit; diff --git a/include/linux/tsm.h b/include/linux/tsm.h index de8324a2223c..11b0c525be30 100644 --- a/include/linux/tsm.h +++ b/include/linux/tsm.h @@ -4,6 +4,7 @@ #include #include +#include #define TSM_INBLOB_MAX 64 #define TSM_OUTBLOB_MAX SZ_32K @@ -19,11 +20,17 @@ * @privlevel: optional privilege level to associate with @outblob * @inblob_len: sizeof @inblob * @inblob: arbitrary input data + * @service_provider: optional name of where to obtain the tsm report blob + * @service_guid: optional service-provider service guid to attest + * @service_manifest_version: optional service-provider service manifest version requested */ struct tsm_desc { unsigned int privlevel; size_t inblob_len; u8 inblob[TSM_INBLOB_MAX]; + char *service_provider; + guid_t service_guid; + unsigned int service_manifest_version; }; /** @@ -33,6 +40,8 @@ struct tsm_desc { * @outblob: generated evidence to provider to the attestation agent * @auxblob_len: sizeof(@auxblob) * @auxblob: (optional) auxiliary data to the report (e.g. certificate data) + * @manifestblob_len: sizeof(@manifestblob) + * @manifestblob: (optional) manifest data associated with the report */ struct tsm_report { struct tsm_desc desc; @@ -40,6 +49,42 @@ struct tsm_report { u8 *outblob; size_t auxblob_len; u8 *auxblob; + size_t manifestblob_len; + u8 *manifestblob; +}; + +/** + * enum tsm_attr_index - index used to reference report attributes + * @TSM_REPORT_GENERATION: index of the report generation number attribute + * @TSM_REPORT_PROVIDER: index of the provider name attribute + * @TSM_REPORT_PRIVLEVEL: index of the desired privilege level attribute + * @TSM_REPORT_PRIVLEVEL_FLOOR: index of the minimum allowed privileg level attribute + * @TSM_REPORT_SERVICE_PROVIDER: index of the service provider identifier attribute + * @TSM_REPORT_SERVICE_GUID: index of the service GUID attribute + * @TSM_REPORT_SERVICE_MANIFEST_VER: index of the service manifest version attribute + */ +enum tsm_attr_index { + TSM_REPORT_GENERATION, + TSM_REPORT_PROVIDER, + TSM_REPORT_PRIVLEVEL, + TSM_REPORT_PRIVLEVEL_FLOOR, + TSM_REPORT_SERVICE_PROVIDER, + TSM_REPORT_SERVICE_GUID, + TSM_REPORT_SERVICE_MANIFEST_VER, +}; + +/** + * enum tsm_bin_attr_index - index used to reference binary report attributes + * @TSM_REPORT_INBLOB: index of the binary report input attribute + * @TSM_REPORT_OUTBLOB: index of the binary report output attribute + * @TSM_REPORT_AUXBLOB: index of the binary auxiliary data attribute + * @TSM_REPORT_MANIFESTBLOB: index of the binary manifest data attribute + */ +enum tsm_bin_attr_index { + TSM_REPORT_INBLOB, + TSM_REPORT_OUTBLOB, + TSM_REPORT_AUXBLOB, + TSM_REPORT_MANIFESTBLOB, }; /** @@ -48,22 +93,20 @@ struct tsm_report { * @privlevel_floor: convey base privlevel for nested scenarios * @report_new: Populate @report with the report blob and auxblob * (optional), return 0 on successful population, or -errno otherwise + * @report_attr_visible: show or hide a report attribute entry + * @report_bin_attr_visible: show or hide a report binary attribute entry * * Implementation specific ops, only one is expected to be registered at * a time i.e. only one of "sev-guest", "tdx-guest", etc. */ struct tsm_ops { const char *name; - const unsigned int privlevel_floor; + unsigned int privlevel_floor; int (*report_new)(struct tsm_report *report, void *data); + bool (*report_attr_visible)(int n); + bool (*report_bin_attr_visible)(int n); }; -extern const struct config_item_type tsm_report_default_type; - -/* publish @privlevel, @privlevel_floor, and @auxblob attributes */ -extern const struct config_item_type tsm_report_extra_type; - -int tsm_register(const struct tsm_ops *ops, void *priv, - const struct config_item_type *type); +int tsm_register(const struct tsm_ops *ops, void *priv); int tsm_unregister(const struct tsm_ops *ops); #endif /* __TSM_H */ diff --git a/kernel/cpu.c b/kernel/cpu.c index 5123121b1c48..1209ddaec026 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -483,6 +483,8 @@ static int cpu_hotplug_disabled; DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock); +static bool cpu_hotplug_offline_disabled __ro_after_init; + void cpus_read_lock(void) { percpu_down_read(&cpu_hotplug_lock); @@ -542,6 +544,14 @@ static void lockdep_release_cpus_lock(void) rwsem_release(&cpu_hotplug_lock.dep_map, _THIS_IP_); } +/* Declare CPU offlining not supported */ +void cpu_hotplug_disable_offlining(void) +{ + cpu_maps_update_begin(); + cpu_hotplug_offline_disabled = true; + cpu_maps_update_done(); +} + /* * Wait for currently running CPU hotplug operations to complete (if any) and * disable future CPU hotplug (from sysfs). The 'cpu_add_remove_lock' protects @@ -1471,7 +1481,7 @@ static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target) * If the platform does not support hotplug, report it explicitly to * differentiate it from a transient offlining failure. */ - if (cc_platform_has(CC_ATTR_HOTPLUG_DISABLED)) + if (cpu_hotplug_offline_disabled) return -EOPNOTSUPP; if (cpu_hotplug_disabled) return -EBUSY; diff --git a/scripts/Kconfig.include b/scripts/Kconfig.include index 3ee8ecfb8c04..3500a3d62f0d 100644 --- a/scripts/Kconfig.include +++ b/scripts/Kconfig.include @@ -33,7 +33,8 @@ ld-option = $(success,$(LD) -v $(1)) # $(as-instr,) # Return y if the assembler supports , n otherwise -as-instr = $(success,printf "%b\n" "$(1)" | $(CC) $(CLANG_FLAGS) -Wa$(comma)--fatal-warnings -c -x assembler-with-cpp -o /dev/null -) +as-instr = $(success,printf "%b\n" "$(1)" | $(CC) $(CLANG_FLAGS) $(2) -Wa$(comma)--fatal-warnings -c -x assembler-with-cpp -o /dev/null -) +as-instr64 = $(as-instr,$(1),$(m64-flag)) # check if $(CC) and $(LD) exist $(error-if,$(failure,command -v $(CC)),C compiler '$(CC)' not found) diff --git a/scripts/syscalltbl.sh b/scripts/syscalltbl.sh index 6abe143889ef..6a903b87a7c2 100755 --- a/scripts/syscalltbl.sh +++ b/scripts/syscalltbl.sh @@ -54,7 +54,7 @@ nxt=0 grep -E "^[0-9]+[[:space:]]+$abis" "$infile" | { - while read nr abi name native compat ; do + while read nr abi name native compat noreturn; do if [ $nxt -gt $nr ]; then echo "error: $infile: syscall table is not sorted or duplicates the same syscall number" >&2 @@ -66,7 +66,21 @@ grep -E "^[0-9]+[[:space:]]+$abis" "$infile" | { nxt=$((nxt + 1)) done - if [ -n "$compat" ]; then + if [ "$compat" = "-" ]; then + unset compat + fi + + if [ -n "$noreturn" ]; then + if [ "$noreturn" != "noreturn" ]; then + echo "error: $infile: invalid string \"$noreturn\" in 'noreturn' column" + exit 1 + fi + if [ -n "$compat" ]; then + echo "__SYSCALL_COMPAT_NORETURN($nr, $native, $compat)" + else + echo "__SYSCALL_NORETURN($nr, $native)" + fi + elif [ -n "$compat" ]; then echo "__SYSCALL_WITH_COMPAT($nr, $native, $compat)" elif [ -n "$native" ]; then echo "__SYSCALL($nr, $native)" diff --git a/tools/arch/x86/kcpuid/Makefile b/tools/arch/x86/kcpuid/Makefile index 87b554fab14b..d0b4b0ed10ff 100644 --- a/tools/arch/x86/kcpuid/Makefile +++ b/tools/arch/x86/kcpuid/Makefile @@ -19,6 +19,6 @@ clean : @rm -f kcpuid install : kcpuid - install -d $(DESTDIR)$(BINDIR) + install -d $(DESTDIR)$(BINDIR) $(DESTDIR)$(HWDATADIR) install -m 755 -p kcpuid $(DESTDIR)$(BINDIR)/kcpuid - install -m 444 -p cpuid.csv $(HWDATADIR)/cpuid.csv + install -m 444 -p cpuid.csv $(DESTDIR)$(HWDATADIR)/cpuid.csv diff --git a/tools/objtool/Documentation/objtool.txt b/tools/objtool/Documentation/objtool.txt index fe39c2a8ef0d..7c3ee959b63c 100644 --- a/tools/objtool/Documentation/objtool.txt +++ b/tools/objtool/Documentation/objtool.txt @@ -284,6 +284,25 @@ the objtool maintainers. Otherwise the stack frame may not get created before the call. + objtool can help with pinpointing the exact function where it happens: + + $ OBJTOOL_ARGS="--verbose" make arch/x86/kvm/ + + arch/x86/kvm/kvm.o: warning: objtool: .altinstr_replacement+0xc5: call without frame pointer save/setup + arch/x86/kvm/kvm.o: warning: objtool: em_loop.part.0+0x29: (alt) + arch/x86/kvm/kvm.o: warning: objtool: em_loop.part.0+0x0: <=== (sym) + LD [M] arch/x86/kvm/kvm-intel.o + 0000 0000000000028220 : + 0000 28220: 0f b6 47 61 movzbl 0x61(%rdi),%eax + 0004 28224: 3c e2 cmp $0xe2,%al + 0006 28226: 74 2c je 28254 + 0008 28228: 48 8b 57 10 mov 0x10(%rdi),%rdx + 000c 2822c: 83 f0 05 xor $0x5,%eax + 000f 2822f: 48 c1 e0 04 shl $0x4,%rax + 0013 28233: 25 f0 00 00 00 and $0xf0,%eax + 0018 28238: 81 e2 d5 08 00 00 and $0x8d5,%edx + 001e 2823e: 80 ce 02 or $0x2,%dh + ... 2. file.o: warning: objtool: .text+0x53: unreachable instruction diff --git a/tools/objtool/arch/x86/special.c b/tools/objtool/arch/x86/special.c index 4134d27c696b..4ea0f9815fda 100644 --- a/tools/objtool/arch/x86/special.c +++ b/tools/objtool/arch/x86/special.c @@ -9,6 +9,29 @@ void arch_handle_alternative(unsigned short feature, struct special_alt *alt) { + static struct special_alt *group, *prev; + + /* + * Recompute orig_len for nested ALTERNATIVE()s. + */ + if (group && group->orig_sec == alt->orig_sec && + group->orig_off == alt->orig_off) { + + struct special_alt *iter = group; + for (;;) { + unsigned int len = max(iter->orig_len, alt->orig_len); + iter->orig_len = alt->orig_len = len; + + if (iter == prev) + break; + + iter = list_next_entry(iter, list); + } + + } else group = alt; + + prev = alt; + switch (feature) { case X86_FEATURE_SMAP: /* diff --git a/tools/objtool/noreturns.h b/tools/objtool/noreturns.h index 7ebf29c91184..1e8141ef1b15 100644 --- a/tools/objtool/noreturns.h +++ b/tools/objtool/noreturns.h @@ -7,12 +7,16 @@ * Yes, this is unfortunate. A better solution is in the works. */ NORETURN(__fortify_panic) +NORETURN(__ia32_sys_exit) +NORETURN(__ia32_sys_exit_group) NORETURN(__kunit_abort) NORETURN(__module_put_and_kthread_exit) NORETURN(__reiserfs_panic) NORETURN(__stack_chk_fail) NORETURN(__tdx_hypercall_failed) NORETURN(__ubsan_handle_builtin_unreachable) +NORETURN(__x64_sys_exit) +NORETURN(__x64_sys_exit_group) NORETURN(arch_cpu_idle_dead) NORETURN(bch2_trans_in_restart_error) NORETURN(bch2_trans_restart_error) diff --git a/tools/objtool/special.c b/tools/objtool/special.c index 91b1950f5bd8..097a69db82a0 100644 --- a/tools/objtool/special.c +++ b/tools/objtool/special.c @@ -84,6 +84,14 @@ static int get_alt_entry(struct elf *elf, const struct special_entry *entry, entry->new_len); } + orig_reloc = find_reloc_by_dest(elf, sec, offset + entry->orig); + if (!orig_reloc) { + WARN_FUNC("can't find orig reloc", sec, offset + entry->orig); + return -1; + } + + reloc_to_sec_off(orig_reloc, &alt->orig_sec, &alt->orig_off); + if (entry->feature) { unsigned short feature; @@ -94,14 +102,6 @@ static int get_alt_entry(struct elf *elf, const struct special_entry *entry, arch_handle_alternative(feature, alt); } - orig_reloc = find_reloc_by_dest(elf, sec, offset + entry->orig); - if (!orig_reloc) { - WARN_FUNC("can't find orig reloc", sec, offset + entry->orig); - return -1; - } - - reloc_to_sec_off(orig_reloc, &alt->orig_sec, &alt->orig_off); - if (!entry->group || alt->new_len) { new_reloc = find_reloc_by_dest(elf, sec, offset + entry->new); if (!new_reloc) {