From 9bad5658ea710f45e4ee68b88a01cfe1839d8b00 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 28 Aug 2018 09:40:23 +0200 Subject: x86/paravirt: Move the Xen-only pv_cpu_ops under the PARAVIRT_XXL umbrella Most of the paravirt ops defined in pv_cpu_ops are for Xen PV guests only. Define them only if CONFIG_PARAVIRT_XXL is set. Signed-off-by: Juergen Gross Signed-off-by: Thomas Gleixner Cc: xen-devel@lists.xenproject.org Cc: virtualization@lists.linux-foundation.org Cc: akataria@vmware.com Cc: rusty@rustcorp.com.au Cc: boris.ostrovsky@oracle.com Cc: hpa@zytor.com Link: https://lkml.kernel.org/r/20180828074026.820-13-jgross@suse.com --- arch/x86/include/asm/processor.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/include/asm/processor.h') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index d53c54b842da..a47d3c84631d 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -578,7 +578,7 @@ static inline bool on_thread_stack(void) current_stack_pointer) < THREAD_SIZE; } -#ifdef CONFIG_PARAVIRT +#ifdef CONFIG_PARAVIRT_XXL #include #else #define __cpuid native_cpuid @@ -589,7 +589,7 @@ static inline void load_sp0(unsigned long sp0) } #define set_iopl_mask native_set_iopl_mask -#endif /* CONFIG_PARAVIRT */ +#endif /* CONFIG_PARAVIRT_XXL */ /* Free all resources held by a thread. */ extern void release_thread(struct task_struct *); -- cgit v1.2.3 From 98f05b5138f0a9b56022295cc1387e635b25635d Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Mon, 3 Sep 2018 15:59:43 -0700 Subject: x86/entry/64: Use the TSS sp2 slot for SYSCALL/SYSRET scratch space In the non-trampoline SYSCALL64 path, a percpu variable is used to temporarily store the user RSP value. Instead of a separate variable, use the otherwise unused sp2 slot in the TSS. This will improve cache locality, as the sp1 slot is already used in the same code to find the kernel stack. It will also simplify a future change to make the non-trampoline path work in PTI mode. Signed-off-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Reviewed-by: Borislav Petkov Cc: Borislav Petkov Cc: Dave Hansen Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Linus Torvalds Cc: Josh Poimboeuf Cc: Joerg Roedel Cc: Jiri Olsa Cc: Andi Kleen Cc: Peter Zijlstra Link: https://lkml.kernel.org/r/08e769a0023dbad4bac6f34f3631dbaf8ad59f4f.1536015544.git.luto@kernel.org --- arch/x86/entry/entry_64.S | 16 +++++++++------- arch/x86/include/asm/processor.h | 6 ++++++ arch/x86/kernel/asm-offsets.c | 3 ++- arch/x86/kernel/process_64.c | 2 -- arch/x86/xen/xen-asm_64.S | 8 +++++--- 5 files changed, 22 insertions(+), 13 deletions(-) (limited to 'arch/x86/include/asm/processor.h') diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index ce6af4460e9c..7e82e553183a 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -215,18 +215,20 @@ ENTRY(entry_SYSCALL_64) /* * This path is only taken when PAGE_TABLE_ISOLATION is disabled so it * is not required to switch CR3. + * + * tss.sp2 is scratch space. */ - movq %rsp, PER_CPU_VAR(rsp_scratch) + movq %rsp, PER_CPU_VAR(cpu_tss_rw + TSS_sp2) movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp /* Construct struct pt_regs on stack */ - pushq $__USER_DS /* pt_regs->ss */ - pushq PER_CPU_VAR(rsp_scratch) /* pt_regs->sp */ - pushq %r11 /* pt_regs->flags */ - pushq $__USER_CS /* pt_regs->cs */ - pushq %rcx /* pt_regs->ip */ + pushq $__USER_DS /* pt_regs->ss */ + pushq PER_CPU_VAR(cpu_tss_rw + TSS_sp2) /* pt_regs->sp */ + pushq %r11 /* pt_regs->flags */ + pushq $__USER_CS /* pt_regs->cs */ + pushq %rcx /* pt_regs->ip */ GLOBAL(entry_SYSCALL_64_after_hwframe) - pushq %rax /* pt_regs->orig_ax */ + pushq %rax /* pt_regs->orig_ax */ PUSH_AND_CLEAR_REGS rax=$-ENOSYS diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index d53c54b842da..b2bb1d691efc 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -315,7 +315,13 @@ struct x86_hw_tss { */ u64 sp1; + /* + * Since Linux does not use ring 2, the 'sp2' slot is unused by + * hardware. entry_SYSCALL_64 uses it as scratch space to stash + * the user RSP value. + */ u64 sp2; + u64 reserved2; u64 ist[7]; u32 reserved3; diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 01de31db300d..fc2e90d3429a 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -105,7 +105,8 @@ void common(void) { DEFINE(SIZEOF_entry_stack, sizeof(struct entry_stack)); DEFINE(MASK_entry_stack, (~(sizeof(struct entry_stack) - 1))); - /* Offset for sp0 and sp1 into the tss_struct */ + /* Offset for fields in tss_struct */ OFFSET(TSS_sp0, tss_struct, x86_tss.sp0); OFFSET(TSS_sp1, tss_struct, x86_tss.sp1); + OFFSET(TSS_sp2, tss_struct, x86_tss.sp2); } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index a451bc374b9b..0fa7aa19f09e 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -59,8 +59,6 @@ #include #endif -__visible DEFINE_PER_CPU(unsigned long, rsp_scratch); - /* Prints also some state that isn't saved in the pt_regs */ void __show_regs(struct pt_regs *regs, int all) { diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S index 417b339e5c8e..bb1c2da0381d 100644 --- a/arch/x86/xen/xen-asm_64.S +++ b/arch/x86/xen/xen-asm_64.S @@ -91,13 +91,15 @@ ENTRY(xen_iret) ENTRY(xen_sysret64) /* * We're already on the usermode stack at this point, but - * still with the kernel gs, so we can easily switch back + * still with the kernel gs, so we can easily switch back. + * + * tss.sp2 is scratch space. */ - movq %rsp, PER_CPU_VAR(rsp_scratch) + movq %rsp, PER_CPU_VAR(cpu_tss_rw + TSS_sp2) movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp pushq $__USER_DS - pushq PER_CPU_VAR(rsp_scratch) + pushq PER_CPU_VAR(cpu_tss_rw + TSS_sp2) pushq %r11 pushq $__USER_CS pushq %rcx -- cgit v1.2.3 From c9661c1e80b609cd038db7c908e061f0535804ef Mon Sep 17 00:00:00 2001 From: Pu Wen Date: Sun, 23 Sep 2018 17:33:12 +0800 Subject: x86/cpu: Create Hygon Dhyana architecture support file Add x86 architecture support for a new processor: Hygon Dhyana Family 18h. Carve out initialization code needed by Dhyana into a separate compilation unit. To identify Hygon Dhyana CPU, add a new vendor type X86_VENDOR_HYGON. Since Dhyana uses AMD functionality to a large degree, select CPU_SUP_AMD which provides that functionality. [ bp: drop explicit license statement as it has an SPDX tag already. ] Signed-off-by: Pu Wen Reviewed-by: Borislav Petkov Signed-off-by: Borislav Petkov Cc: tglx@linutronix.de Cc: mingo@redhat.com Cc: hpa@zytor.com Cc: x86@kernel.org Cc: thomas.lendacky@amd.com Link: https://lkml.kernel.org/r/1a882065223bacbde5726f3beaa70cebd8dcd814.1537533369.git.puwen@hygon.cn --- MAINTAINERS | 6 + arch/x86/Kconfig.cpu | 14 ++ arch/x86/include/asm/processor.h | 3 +- arch/x86/kernel/cpu/Makefile | 1 + arch/x86/kernel/cpu/hygon.c | 405 +++++++++++++++++++++++++++++++++++++++ 5 files changed, 428 insertions(+), 1 deletion(-) create mode 100644 arch/x86/kernel/cpu/hygon.c (limited to 'arch/x86/include/asm/processor.h') diff --git a/MAINTAINERS b/MAINTAINERS index 4ece30f15777..c028e1d45c90 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6762,6 +6762,12 @@ S: Maintained F: mm/memory-failure.c F: mm/hwpoison-inject.c +HYGON PROCESSOR SUPPORT +M: Pu Wen +L: linux-kernel@vger.kernel.org +S: Maintained +F: arch/x86/kernel/cpu/hygon.c + Hyper-V CORE AND DRIVERS M: "K. Y. Srinivasan" M: Haiyang Zhang diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 638411f22267..6adce15268bd 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -426,6 +426,20 @@ config CPU_SUP_AMD If unsure, say N. +config CPU_SUP_HYGON + default y + bool "Support Hygon processors" if PROCESSOR_SELECT + select CPU_SUP_AMD + help + This enables detection, tunings and quirks for Hygon processors + + You need this enabled if you want your kernel to run on an + Hygon CPU. Disabling this option on other types of CPUs + makes the kernel a tiny bit smaller. Disabling it on an Hygon + CPU might render the kernel unbootable. + + If unsure, say N. + config CPU_SUP_CENTAUR default y bool "Support Centaur processors" if PROCESSOR_SELECT diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index d53c54b842da..d4dfd02b740e 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -155,7 +155,8 @@ enum cpuid_regs_idx { #define X86_VENDOR_CENTAUR 5 #define X86_VENDOR_TRANSMETA 7 #define X86_VENDOR_NSC 8 -#define X86_VENDOR_NUM 9 +#define X86_VENDOR_HYGON 9 +#define X86_VENDOR_NUM 10 #define X86_VENDOR_UNKNOWN 0xff diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 347137e80bf5..1f5d2291c31e 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -30,6 +30,7 @@ obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o obj-$(CONFIG_CPU_SUP_INTEL) += intel.o intel_pconfig.o obj-$(CONFIG_CPU_SUP_AMD) += amd.o +obj-$(CONFIG_CPU_SUP_HYGON) += hygon.o obj-$(CONFIG_CPU_SUP_CYRIX_32) += cyrix.o obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o obj-$(CONFIG_CPU_SUP_TRANSMETA_32) += transmeta.o diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c new file mode 100644 index 000000000000..a43d5f1f8b41 --- /dev/null +++ b/arch/x86/kernel/cpu/hygon.c @@ -0,0 +1,405 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Hygon Processor Support for Linux + * + * Copyright (C) 2018 Chengdu Haiguang IC Design Co., Ltd. + * + * Author: Pu Wen + */ +#include + +#include +#include +#include +#include +#include +#ifdef CONFIG_X86_64 +# include +#endif + +#include "cpu.h" + +/* + * nodes_per_socket: Stores the number of nodes per socket. + * Refer to CPUID Fn8000_001E_ECX Node Identifiers[10:8] + */ +static u32 nodes_per_socket = 1; + +#ifdef CONFIG_NUMA +/* + * To workaround broken NUMA config. Read the comment in + * srat_detect_node(). + */ +static int nearby_node(int apicid) +{ + int i, node; + + for (i = apicid - 1; i >= 0; i--) { + node = __apicid_to_node[i]; + if (node != NUMA_NO_NODE && node_online(node)) + return node; + } + for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) { + node = __apicid_to_node[i]; + if (node != NUMA_NO_NODE && node_online(node)) + return node; + } + return first_node(node_online_map); /* Shouldn't happen */ +} +#endif + +static void hygon_get_topology_early(struct cpuinfo_x86 *c) +{ + if (cpu_has(c, X86_FEATURE_TOPOEXT)) + smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1; +} + +/* + * Fixup core topology information for + * (1) Hygon multi-node processors + * Assumption: Number of cores in each internal node is the same. + * (2) Hygon processors supporting compute units + */ +static void hygon_get_topology(struct cpuinfo_x86 *c) +{ + u8 node_id; + int cpu = smp_processor_id(); + + /* get information required for multi-node processors */ + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { + int err; + u32 eax, ebx, ecx, edx; + + cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); + + node_id = ecx & 0xff; + + c->cpu_core_id = ebx & 0xff; + + if (smp_num_siblings > 1) + c->x86_max_cores /= smp_num_siblings; + + /* + * In case leaf B is available, use it to derive + * topology information. + */ + err = detect_extended_topology(c); + if (!err) + c->x86_coreid_bits = get_count_order(c->x86_max_cores); + + } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) { + u64 value; + + rdmsrl(MSR_FAM10H_NODE_ID, value); + node_id = value & 7; + + per_cpu(cpu_llc_id, cpu) = node_id; + } else + return; + + if (nodes_per_socket > 1) + set_cpu_cap(c, X86_FEATURE_AMD_DCM); +} + +/* + * On Hygon setup the lower bits of the APIC id distinguish the cores. + * Assumes number of cores is a power of two. + */ +static void hygon_detect_cmp(struct cpuinfo_x86 *c) +{ + unsigned int bits; + int cpu = smp_processor_id(); + + bits = c->x86_coreid_bits; + /* Low order bits define the core id (index of core in socket) */ + c->cpu_core_id = c->initial_apicid & ((1 << bits)-1); + /* Convert the initial APIC ID into the socket ID */ + c->phys_proc_id = c->initial_apicid >> bits; + /* use socket ID also for last level cache */ + per_cpu(cpu_llc_id, cpu) = c->phys_proc_id; +} + +static void srat_detect_node(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_NUMA + int cpu = smp_processor_id(); + int node; + unsigned int apicid = c->apicid; + + node = numa_cpu_node(cpu); + if (node == NUMA_NO_NODE) + node = per_cpu(cpu_llc_id, cpu); + + /* + * On multi-fabric platform (e.g. Numascale NumaChip) a + * platform-specific handler needs to be called to fixup some + * IDs of the CPU. + */ + if (x86_cpuinit.fixup_cpu_id) + x86_cpuinit.fixup_cpu_id(c, node); + + if (!node_online(node)) { + /* + * Two possibilities here: + * + * - The CPU is missing memory and no node was created. In + * that case try picking one from a nearby CPU. + * + * - The APIC IDs differ from the HyperTransport node IDs. + * Assume they are all increased by a constant offset, but + * in the same order as the HT nodeids. If that doesn't + * result in a usable node fall back to the path for the + * previous case. + * + * This workaround operates directly on the mapping between + * APIC ID and NUMA node, assuming certain relationship + * between APIC ID, HT node ID and NUMA topology. As going + * through CPU mapping may alter the outcome, directly + * access __apicid_to_node[]. + */ + int ht_nodeid = c->initial_apicid; + + if (__apicid_to_node[ht_nodeid] != NUMA_NO_NODE) + node = __apicid_to_node[ht_nodeid]; + /* Pick a nearby node */ + if (!node_online(node)) + node = nearby_node(apicid); + } + numa_set_node(cpu, node); +#endif +} + +static void early_init_hygon_mc(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_SMP + unsigned int bits, ecx; + + /* Multi core CPU? */ + if (c->extended_cpuid_level < 0x80000008) + return; + + ecx = cpuid_ecx(0x80000008); + + c->x86_max_cores = (ecx & 0xff) + 1; + + /* CPU telling us the core id bits shift? */ + bits = (ecx >> 12) & 0xF; + + /* Otherwise recompute */ + if (bits == 0) { + while ((1 << bits) < c->x86_max_cores) + bits++; + } + + c->x86_coreid_bits = bits; +#endif +} + +static void bsp_init_hygon(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_X86_64 + unsigned long long tseg; + + /* + * Split up direct mapping around the TSEG SMM area. + * Don't do it for gbpages because there seems very little + * benefit in doing so. + */ + if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) { + unsigned long pfn = tseg >> PAGE_SHIFT; + + pr_debug("tseg: %010llx\n", tseg); + if (pfn_range_is_mapped(pfn, pfn + 1)) + set_memory_4k((unsigned long)__va(tseg), 1); + } +#endif + + if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { + u64 val; + + rdmsrl(MSR_K7_HWCR, val); + if (!(val & BIT(24))) + pr_warn(FW_BUG "TSC doesn't count with P0 frequency!\n"); + } + + if (cpu_has(c, X86_FEATURE_MWAITX)) + use_mwaitx_delay(); + + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { + u32 ecx; + + ecx = cpuid_ecx(0x8000001e); + nodes_per_socket = ((ecx >> 8) & 7) + 1; + } else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) { + u64 value; + + rdmsrl(MSR_FAM10H_NODE_ID, value); + nodes_per_socket = ((value >> 3) & 7) + 1; + } + + if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) && + !boot_cpu_has(X86_FEATURE_VIRT_SSBD)) { + /* + * Try to cache the base value so further operations can + * avoid RMW. If that faults, do not enable SSBD. + */ + if (!rdmsrl_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) { + setup_force_cpu_cap(X86_FEATURE_LS_CFG_SSBD); + setup_force_cpu_cap(X86_FEATURE_SSBD); + x86_amd_ls_cfg_ssbd_mask = 1ULL << 10; + } + } +} + +static void early_init_hygon(struct cpuinfo_x86 *c) +{ + u32 dummy; + + early_init_hygon_mc(c); + + set_cpu_cap(c, X86_FEATURE_K8); + + rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy); + + /* + * c->x86_power is 8000_0007 edx. Bit 8 is TSC runs at constant rate + * with P/T states and does not stop in deep C-states + */ + if (c->x86_power & (1 << 8)) { + set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); + set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); + } + + /* Bit 12 of 8000_0007 edx is accumulated power mechanism. */ + if (c->x86_power & BIT(12)) + set_cpu_cap(c, X86_FEATURE_ACC_POWER); + +#ifdef CONFIG_X86_64 + set_cpu_cap(c, X86_FEATURE_SYSCALL32); +#endif + +#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI) + /* + * ApicID can always be treated as an 8-bit value for Hygon APIC So, we + * can safely set X86_FEATURE_EXTD_APICID unconditionally. + */ + if (boot_cpu_has(X86_FEATURE_APIC)) + set_cpu_cap(c, X86_FEATURE_EXTD_APICID); +#endif + + /* + * This is only needed to tell the kernel whether to use VMCALL + * and VMMCALL. VMMCALL is never executed except under virt, so + * we can set it unconditionally. + */ + set_cpu_cap(c, X86_FEATURE_VMMCALL); + + hygon_get_topology_early(c); +} + +static void init_hygon(struct cpuinfo_x86 *c) +{ + early_init_hygon(c); + + /* + * Bit 31 in normal CPUID used for nonstandard 3DNow ID; + * 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway + */ + clear_cpu_cap(c, 0*32+31); + + set_cpu_cap(c, X86_FEATURE_REP_GOOD); + + /* get apicid instead of initial apic id from cpuid */ + c->apicid = hard_smp_processor_id(); + + set_cpu_cap(c, X86_FEATURE_ZEN); + set_cpu_cap(c, X86_FEATURE_CPB); + + cpu_detect_cache_sizes(c); + + hygon_detect_cmp(c); + hygon_get_topology(c); + srat_detect_node(c); + + if (cpu_has(c, X86_FEATURE_XMM2)) { + unsigned long long val; + int ret; + + /* + * A serializing LFENCE has less overhead than MFENCE, so + * use it for execution serialization. On families which + * don't have that MSR, LFENCE is already serializing. + * msr_set_bit() uses the safe accessors, too, even if the MSR + * is not present. + */ + msr_set_bit(MSR_F10H_DECFG, + MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT); + + /* + * Verify that the MSR write was successful (could be running + * under a hypervisor) and only then assume that LFENCE is + * serializing. + */ + ret = rdmsrl_safe(MSR_F10H_DECFG, &val); + if (!ret && (val & MSR_F10H_DECFG_LFENCE_SERIALIZE)) { + /* A serializing LFENCE stops RDTSC speculation */ + set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); + } else { + /* MFENCE stops RDTSC speculation */ + set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); + } + } + + /* + * Hygon processors have APIC timer running in deep C states. + */ + set_cpu_cap(c, X86_FEATURE_ARAT); + + /* Hygon CPUs don't reset SS attributes on SYSRET, Xen does. */ + if (!cpu_has(c, X86_FEATURE_XENPV)) + set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); +} + +static void cpu_detect_tlb_hygon(struct cpuinfo_x86 *c) +{ + u32 ebx, eax, ecx, edx; + u16 mask = 0xfff; + + if (c->extended_cpuid_level < 0x80000006) + return; + + cpuid(0x80000006, &eax, &ebx, &ecx, &edx); + + tlb_lld_4k[ENTRIES] = (ebx >> 16) & mask; + tlb_lli_4k[ENTRIES] = ebx & mask; + + /* Handle DTLB 2M and 4M sizes, fall back to L1 if L2 is disabled */ + if (!((eax >> 16) & mask)) + tlb_lld_2m[ENTRIES] = (cpuid_eax(0x80000005) >> 16) & 0xff; + else + tlb_lld_2m[ENTRIES] = (eax >> 16) & mask; + + /* a 4M entry uses two 2M entries */ + tlb_lld_4m[ENTRIES] = tlb_lld_2m[ENTRIES] >> 1; + + /* Handle ITLB 2M and 4M sizes, fall back to L1 if L2 is disabled */ + if (!(eax & mask)) { + cpuid(0x80000005, &eax, &ebx, &ecx, &edx); + tlb_lli_2m[ENTRIES] = eax & 0xff; + } else + tlb_lli_2m[ENTRIES] = eax & mask; + + tlb_lli_4m[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1; +} + +static const struct cpu_dev hygon_cpu_dev = { + .c_vendor = "Hygon", + .c_ident = { "HygonGenuine" }, + .c_early_init = early_init_hygon, + .c_detect_tlb = cpu_detect_tlb_hygon, + .c_bsp_init = bsp_init_hygon, + .c_init = init_hygon, + .c_x86_vendor = X86_VENDOR_HYGON, +}; + +cpu_dev_register(hygon_cpu_dev); -- cgit v1.2.3 From de0d22e50cd3d57277f073ccf65d57aa519d6888 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Tue, 30 Oct 2018 15:04:47 -0700 Subject: treewide: remove current_text_addr Prefer _THIS_IP_ defined in linux/kernel.h. Most definitions of current_text_addr were the same as _THIS_IP_, but a few archs had inline assembly instead. This patch removes the final call site of current_text_addr, making all of the definitions dead code. [akpm@linux-foundation.org: fix arch/csky/include/asm/processor.h] Link: http://lkml.kernel.org/r/20180911182413.180715-1-ndesaulniers@google.com Signed-off-by: Nick Desaulniers Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/include/asm/processor.h | 6 ------ arch/arc/include/asm/processor.h | 8 -------- arch/arm/include/asm/processor.h | 6 ------ arch/arm64/include/asm/processor.h | 7 ------- arch/c6x/include/asm/processor.h | 11 ----------- arch/csky/include/asm/processor.h | 6 ------ arch/h8300/include/asm/processor.h | 6 ------ arch/hexagon/include/asm/processor.h | 3 --- arch/ia64/include/asm/processor.h | 6 ------ arch/m68k/include/asm/processor.h | 6 ------ arch/microblaze/include/asm/processor.h | 12 ------------ arch/mips/include/asm/processor.h | 5 ----- arch/nds32/include/asm/processor.h | 6 ------ arch/nios2/include/asm/processor.h | 6 ------ arch/openrisc/include/asm/processor.h | 5 ----- arch/parisc/include/asm/processor.h | 11 ----------- arch/powerpc/include/asm/processor.h | 6 ------ arch/riscv/include/asm/processor.h | 6 ------ arch/s390/include/asm/processor.h | 6 ------ arch/sh/include/asm/processor_32.h | 6 ------ arch/sh/include/asm/processor_64.h | 15 --------------- arch/sparc/include/asm/processor_32.h | 6 ------ arch/sparc/include/asm/processor_64.h | 6 ------ arch/unicore32/include/asm/processor.h | 6 ------ arch/x86/include/asm/kexec.h | 3 ++- arch/x86/include/asm/processor.h | 12 ------------ arch/x86/um/asm/processor_32.h | 8 -------- arch/x86/um/asm/processor_64.h | 3 --- arch/xtensa/include/asm/processor.h | 8 -------- 29 files changed, 2 insertions(+), 199 deletions(-) (limited to 'arch/x86/include/asm/processor.h') diff --git a/arch/alpha/include/asm/processor.h b/arch/alpha/include/asm/processor.h index cb05d045efe3..6100431da07a 100644 --- a/arch/alpha/include/asm/processor.h +++ b/arch/alpha/include/asm/processor.h @@ -10,12 +10,6 @@ #include /* for ADDR_LIMIT_32BIT */ -/* - * Returns current instruction pointer ("program counter"). - */ -#define current_text_addr() \ - ({ void *__pc; __asm__ ("br %0,.+4" : "=r"(__pc)); __pc; }) - /* * We have a 42-bit user address space: 4TB user VM... */ diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h index 8ee41e988169..10346d6cf926 100644 --- a/arch/arc/include/asm/processor.h +++ b/arch/arc/include/asm/processor.h @@ -98,14 +98,6 @@ extern void start_thread(struct pt_regs * regs, unsigned long pc, extern unsigned int get_wchan(struct task_struct *p); -/* - * Default implementation of macro that returns current - * instruction pointer ("program counter"). - * Should the PC register be read instead ? This macro does not seem to - * be used in many places so this wont be all that bad. - */ -#define current_text_addr() ({ __label__ _l; _l: &&_l; }) - #endif /* !__ASSEMBLY__ */ /* diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h index 1bf65b47808a..120f4c9bbfde 100644 --- a/arch/arm/include/asm/processor.h +++ b/arch/arm/include/asm/processor.h @@ -11,12 +11,6 @@ #ifndef __ASM_ARM_PROCESSOR_H #define __ASM_ARM_PROCESSOR_H -/* - * Default implementation of macro that returns current - * instruction pointer ("program counter"). - */ -#define current_text_addr() ({ __label__ _l; _l: &&_l;}) - #ifdef __KERNEL__ #include diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 2bf6691371c2..3e2091708b8e 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -25,13 +25,6 @@ #define USER_DS (TASK_SIZE_64 - 1) #ifndef __ASSEMBLY__ - -/* - * Default implementation of macro that returns current - * instruction pointer ("program counter"). - */ -#define current_text_addr() ({ __label__ _l; _l: &&_l;}) - #ifdef __KERNEL__ #include diff --git a/arch/c6x/include/asm/processor.h b/arch/c6x/include/asm/processor.h index 8f7cce829f8e..a8581f5b27f6 100644 --- a/arch/c6x/include/asm/processor.h +++ b/arch/c6x/include/asm/processor.h @@ -17,17 +17,6 @@ #include #include -/* - * Default implementation of macro that returns current - * instruction pointer ("program counter"). - */ -#define current_text_addr() \ -({ \ - void *__pc; \ - asm("mvc .S2 pce1,%0\n" : "=b"(__pc)); \ - __pc; \ -}) - /* * User space process size. This is mostly meaningless for NOMMU * but some C6X processors may have RAM addresses up to 0xFFFFFFFF. diff --git a/arch/csky/include/asm/processor.h b/arch/csky/include/asm/processor.h index 5ad4f0b83092..b1748659b2e9 100644 --- a/arch/csky/include/asm/processor.h +++ b/arch/csky/include/asm/processor.h @@ -4,12 +4,6 @@ #ifndef __ASM_CSKY_PROCESSOR_H #define __ASM_CSKY_PROCESSOR_H -/* - * Default implementation of macro that returns current - * instruction pointer ("program counter"). - */ -#define current_text_addr() ({ __label__ _l; _l: &&_l; }) - #include #include #include diff --git a/arch/h8300/include/asm/processor.h b/arch/h8300/include/asm/processor.h index 985346393e4a..a060b41b2d31 100644 --- a/arch/h8300/include/asm/processor.h +++ b/arch/h8300/include/asm/processor.h @@ -12,12 +12,6 @@ #ifndef __ASM_H8300_PROCESSOR_H #define __ASM_H8300_PROCESSOR_H -/* - * Default implementation of macro that returns current - * instruction pointer ("program counter"). - */ -#define current_text_addr() ({ __label__ _l; _l: &&_l; }) - #include #include #include diff --git a/arch/hexagon/include/asm/processor.h b/arch/hexagon/include/asm/processor.h index ce67940860a5..227bcb9cfdac 100644 --- a/arch/hexagon/include/asm/processor.h +++ b/arch/hexagon/include/asm/processor.h @@ -27,9 +27,6 @@ #include #include -/* must be a macro */ -#define current_text_addr() ({ __label__ _l; _l: &&_l; }) - /* task_struct, defined elsewhere, is the "process descriptor" */ struct task_struct; diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h index 10061ccf0440..c91ef98ed6bf 100644 --- a/arch/ia64/include/asm/processor.h +++ b/arch/ia64/include/asm/processor.h @@ -602,12 +602,6 @@ ia64_set_unat (__u64 *unat, void *spill_addr, unsigned long nat) *unat = (*unat & ~mask) | (nat << bit); } -/* - * Get the current instruction/program counter value. - */ -#define current_text_addr() \ - ({ void *_pc; _pc = (void *)ia64_getreg(_IA64_REG_IP); _pc; }) - static inline __u64 ia64_get_ivr (void) { diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h index 464e9f5f50ee..3750819ac5a1 100644 --- a/arch/m68k/include/asm/processor.h +++ b/arch/m68k/include/asm/processor.h @@ -8,12 +8,6 @@ #ifndef __ASM_M68K_PROCESSOR_H #define __ASM_M68K_PROCESSOR_H -/* - * Default implementation of macro that returns current - * instruction pointer ("program counter"). - */ -#define current_text_addr() ({ __label__ _l; _l: &&_l;}) - #include #include #include diff --git a/arch/microblaze/include/asm/processor.h b/arch/microblaze/include/asm/processor.h index 330d556860ba..66b537b8d138 100644 --- a/arch/microblaze/include/asm/processor.h +++ b/arch/microblaze/include/asm/processor.h @@ -45,12 +45,6 @@ extern void ret_from_kernel_thread(void); */ # define TASK_SIZE (0x81000000 - 0x80000000) -/* - * Default implementation of macro that returns current - * instruction pointer ("program counter"). - */ -# define current_text_addr() ({ __label__ _l; _l: &&_l; }) - /* * This decides where the kernel will search for a free chunk of vm * space during mmap's. We won't be using it @@ -92,12 +86,6 @@ extern unsigned long get_wchan(struct task_struct *p); # ifndef __ASSEMBLY__ -/* - * Default implementation of macro that returns current - * instruction pointer ("program counter"). - */ -# define current_text_addr() ({ __label__ _l; _l: &&_l; }) - /* If you change this, you must change the associated assembly-languages * constants defined below, THREAD_*. */ diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h index c373eb605040..ce3ed4d17813 100644 --- a/arch/mips/include/asm/processor.h +++ b/arch/mips/include/asm/processor.h @@ -23,11 +23,6 @@ #include #include -/* - * Return current * instruction pointer ("program counter"). - */ -#define current_text_addr() ({ __label__ _l; _l: &&_l;}) - /* * System setup and hardware flags.. */ diff --git a/arch/nds32/include/asm/processor.h b/arch/nds32/include/asm/processor.h index 9c83caf4269f..c2660f566bac 100644 --- a/arch/nds32/include/asm/processor.h +++ b/arch/nds32/include/asm/processor.h @@ -4,12 +4,6 @@ #ifndef __ASM_NDS32_PROCESSOR_H #define __ASM_NDS32_PROCESSOR_H -/* - * Default implementation of macro that returns current - * instruction pointer ("program counter"). - */ -#define current_text_addr() ({ __label__ _l; _l: &&_l;}) - #ifdef __KERNEL__ #include diff --git a/arch/nios2/include/asm/processor.h b/arch/nios2/include/asm/processor.h index 4944e2e1d8b0..94bcb86f679f 100644 --- a/arch/nios2/include/asm/processor.h +++ b/arch/nios2/include/asm/processor.h @@ -38,12 +38,6 @@ #define KUSER_SIZE (PAGE_SIZE) #ifndef __ASSEMBLY__ -/* - * Default implementation of macro that returns current - * instruction pointer ("program counter"). - */ -#define current_text_addr() ({ __label__ _l; _l: &&_l; }) - # define TASK_SIZE 0x7FFF0000UL # define TASK_UNMAPPED_BASE (PAGE_ALIGN(TASK_SIZE / 3)) diff --git a/arch/openrisc/include/asm/processor.h b/arch/openrisc/include/asm/processor.h index af31a9fe736a..351d3aed7a06 100644 --- a/arch/openrisc/include/asm/processor.h +++ b/arch/openrisc/include/asm/processor.h @@ -30,11 +30,6 @@ | SPR_SR_DCE | SPR_SR_SM) #define USER_SR (SPR_SR_DME | SPR_SR_IME | SPR_SR_ICE \ | SPR_SR_DCE | SPR_SR_IEE | SPR_SR_TEE) -/* - * Default implementation of macro that returns current - * instruction pointer ("program counter"). - */ -#define current_text_addr() ({ __label__ _l; _l: &&_l; }) /* * User space process size. This is hardcoded into a few places, diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h index 2bd5e695bdad..6e2a8176b0dd 100644 --- a/arch/parisc/include/asm/processor.h +++ b/arch/parisc/include/asm/processor.h @@ -20,17 +20,6 @@ #include #endif /* __ASSEMBLY__ */ -/* - * Default implementation of macro that returns current - * instruction pointer ("program counter"). - */ -#ifdef CONFIG_PA20 -#define current_ia(x) __asm__("mfia %0" : "=r"(x)) -#else /* mfia added in pa2.0 */ -#define current_ia(x) __asm__("blr 0,%0\n\tnop" : "=r"(x)) -#endif -#define current_text_addr() ({ void *pc; current_ia(pc); pc; }) - #define HAVE_ARCH_PICK_MMAP_LAYOUT #define TASK_SIZE_OF(tsk) ((tsk)->thread.task_size) diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 7d04d60a39c9..ee58526cb6c2 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -67,12 +67,6 @@ extern int _chrp_type; #endif /* defined(__KERNEL__) && defined(CONFIG_PPC32) */ -/* - * Default implementation of macro that returns current - * instruction pointer ("program counter"). - */ -#define current_text_addr() ({ __label__ _l; _l: &&_l;}) - /* Macros for adjusting thread priority (hardware multi-threading) */ #define HMT_very_low() asm volatile("or 31,31,31 # very low priority") #define HMT_low() asm volatile("or 1,1,1 # low priority") diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h index 50de774d827a..0531f49af5c3 100644 --- a/arch/riscv/include/asm/processor.h +++ b/arch/riscv/include/asm/processor.h @@ -33,12 +33,6 @@ struct task_struct; struct pt_regs; -/* - * Default implementation of macro that returns current - * instruction pointer ("program counter"). - */ -#define current_text_addr() ({ __label__ _l; _l: &&_l; }) - /* CPU-specific state of a task */ struct thread_struct { /* Callee-saved registers */ diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 34768e6ef4fb..302795c47c06 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -73,12 +73,6 @@ static inline int test_cpu_flag_of(int flag, int cpu) #define arch_needs_cpu() test_cpu_flag(CIF_NOHZ_DELAY) -/* - * Default implementation of macro that returns current - * instruction pointer ("program counter"). - */ -#define current_text_addr() ({ void *pc; asm("basr %0,0" : "=a" (pc)); pc; }) - static inline void get_cpu_id(struct cpuid *ptr) { asm volatile("stidp %0" : "=Q" (*ptr)); diff --git a/arch/sh/include/asm/processor_32.h b/arch/sh/include/asm/processor_32.h index 95100d8a0b7b..0e0ecc0132e3 100644 --- a/arch/sh/include/asm/processor_32.h +++ b/arch/sh/include/asm/processor_32.h @@ -16,12 +16,6 @@ #include #include -/* - * Default implementation of macro that returns current - * instruction pointer ("program counter"). - */ -#define current_text_addr() ({ void *pc; __asm__("mova 1f, %0\n.align 2\n1:":"=z" (pc)); pc; }) - /* Core Processor Version Register */ #define CCN_PVR 0xff000030 #define CCN_CVR 0xff000040 diff --git a/arch/sh/include/asm/processor_64.h b/arch/sh/include/asm/processor_64.h index 777a16318aff..f3d7075648d0 100644 --- a/arch/sh/include/asm/processor_64.h +++ b/arch/sh/include/asm/processor_64.h @@ -19,21 +19,6 @@ #include #include -/* - * Default implementation of macro that returns current - * instruction pointer ("program counter"). - */ -#define current_text_addr() ({ \ -void *pc; \ -unsigned long long __dummy = 0; \ -__asm__("gettr tr0, %1\n\t" \ - "pta 4, tr0\n\t" \ - "gettr tr0, %0\n\t" \ - "ptabs %1, tr0\n\t" \ - :"=r" (pc), "=r" (__dummy) \ - : "1" (__dummy)); \ -pc; }) - #endif /* diff --git a/arch/sparc/include/asm/processor_32.h b/arch/sparc/include/asm/processor_32.h index 192493c257fa..3c4bc2189092 100644 --- a/arch/sparc/include/asm/processor_32.h +++ b/arch/sparc/include/asm/processor_32.h @@ -7,12 +7,6 @@ #ifndef __ASM_SPARC_PROCESSOR_H #define __ASM_SPARC_PROCESSOR_H -/* - * Sparc32 implementation of macro that returns current - * instruction pointer ("program counter"). - */ -#define current_text_addr() ({ void *pc; __asm__("sethi %%hi(1f), %0; or %0, %%lo(1f), %0;\n1:" : "=r" (pc)); pc; }) - #include #include #include diff --git a/arch/sparc/include/asm/processor_64.h b/arch/sparc/include/asm/processor_64.h index aac23d4a4ddd..5cf145f18f36 100644 --- a/arch/sparc/include/asm/processor_64.h +++ b/arch/sparc/include/asm/processor_64.h @@ -8,12 +8,6 @@ #ifndef __ASM_SPARC64_PROCESSOR_H #define __ASM_SPARC64_PROCESSOR_H -/* - * Sparc64 implementation of macro that returns current - * instruction pointer ("program counter"). - */ -#define current_text_addr() ({ void *pc; __asm__("rd %%pc, %0" : "=r" (pc)); pc; }) - #include #include #include diff --git a/arch/unicore32/include/asm/processor.h b/arch/unicore32/include/asm/processor.h index 4eaa42167667..b772ed1c0f25 100644 --- a/arch/unicore32/include/asm/processor.h +++ b/arch/unicore32/include/asm/processor.h @@ -13,12 +13,6 @@ #ifndef __UNICORE_PROCESSOR_H__ #define __UNICORE_PROCESSOR_H__ -/* - * Default implementation of macro that returns current - * instruction pointer ("program counter"). - */ -#define current_text_addr() ({ __label__ _l; _l: &&_l; }) - #ifdef __KERNEL__ #include diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index 5125fca472bb..003f2daa3b0f 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -21,6 +21,7 @@ #ifndef __ASSEMBLY__ #include +#include #include #include @@ -132,7 +133,7 @@ static inline void crash_setup_regs(struct pt_regs *newregs, asm volatile("movl %%cs, %%eax;" :"=a"(newregs->cs)); asm volatile("pushfq; popq %0" :"=m"(newregs->flags)); #endif - newregs->ip = (unsigned long)current_text_addr(); + newregs->ip = _THIS_IP_; } } diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 617805981cce..071b2a6fff85 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -42,18 +42,6 @@ struct vm86; #define NET_IP_ALIGN 0 #define HBP_NUM 4 -/* - * Default implementation of macro that returns current - * instruction pointer ("program counter"). - */ -static inline void *current_text_addr(void) -{ - void *pc; - - asm volatile("mov $1f, %0; 1:":"=r" (pc)); - - return pc; -} /* * These alignment constraints are for performance in the vSMP case, diff --git a/arch/x86/um/asm/processor_32.h b/arch/x86/um/asm/processor_32.h index c112de81c9e1..5fb1b8449adf 100644 --- a/arch/x86/um/asm/processor_32.h +++ b/arch/x86/um/asm/processor_32.h @@ -47,14 +47,6 @@ static inline void arch_copy_thread(struct arch_thread *from, memcpy(&to->tls_array, &from->tls_array, sizeof(from->tls_array)); } -/* - * Default implementation of macro that returns current - * instruction pointer ("program counter"). Stolen - * from asm-i386/processor.h - */ -#define current_text_addr() \ - ({ void *pc; __asm__("movl $1f,%0\n1:":"=g" (pc)); pc; }) - #define current_sp() ({ void *sp; __asm__("movl %%esp, %0" : "=r" (sp) : ); sp; }) #define current_bp() ({ unsigned long bp; __asm__("movl %%ebp, %0" : "=r" (bp) : ); bp; }) diff --git a/arch/x86/um/asm/processor_64.h b/arch/x86/um/asm/processor_64.h index c3be85205a65..1ef9c21877bc 100644 --- a/arch/x86/um/asm/processor_64.h +++ b/arch/x86/um/asm/processor_64.h @@ -31,9 +31,6 @@ static inline void arch_copy_thread(struct arch_thread *from, to->fs = from->fs; } -#define current_text_addr() \ - ({ void *pc; __asm__("movq $1f,%0\n1:":"=g" (pc)); pc; }) - #define current_sp() ({ void *sp; __asm__("movq %%rsp, %0" : "=r" (sp) : ); sp; }) #define current_bp() ({ unsigned long bp; __asm__("movq %%rbp, %0" : "=r" (bp) : ); bp; }) diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h index e4ccb88b7996..be9bfd9aa865 100644 --- a/arch/xtensa/include/asm/processor.h +++ b/arch/xtensa/include/asm/processor.h @@ -152,14 +152,6 @@ struct thread_struct { int align[0] __attribute__ ((aligned(16))); }; - -/* - * Default implementation of macro that returns current - * instruction pointer ("program counter"). - */ -#define current_text_addr() ({ __label__ _l; _l: &&_l;}) - - /* This decides where the kernel will search for a free chunk of vm * space during mmap's. */ -- cgit v1.2.3