From 784d5699eddc55878627da20d3fe0c8542e2f1a2 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 11 Jan 2016 11:04:34 -0500 Subject: x86: move exports to actual definitions Signed-off-by: Al Viro --- arch/x86/include/asm/export.h | 4 ++++ 1 file changed, 4 insertions(+) create mode 100644 arch/x86/include/asm/export.h (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/export.h b/arch/x86/include/asm/export.h new file mode 100644 index 000000000000..138de56b13eb --- /dev/null +++ b/arch/x86/include/asm/export.h @@ -0,0 +1,4 @@ +#ifdef CONFIG_64BIT +#define KSYM_ALIGN 16 +#endif +#include -- cgit v1.2.3 From 8a7e75d47b68193339f8727cf4503271d0a0b1d0 Mon Sep 17 00:00:00 2001 From: Suraj Jitindar Singh Date: Tue, 2 Aug 2016 14:03:22 +1000 Subject: KVM: Add provisioning for ulong vm stats and u64 vcpu stats vms and vcpus have statistics associated with them which can be viewed within the debugfs. Currently it is assumed within the vcpu_stat_get() and vm_stat_get() functions that all of these statistics are represented as u32s, however the next patch adds some u64 vcpu statistics. Change all vcpu statistics to u64 and modify vcpu_stat_get() accordingly. Since vcpu statistics are per vcpu, they will only be updated by a single vcpu at a time so this shouldn't present a problem on 32-bit machines which can't atomically increment 64-bit numbers. However vm statistics could potentially be updated by multiple vcpus from that vm at a time. To avoid the overhead of atomics make all vm statistics ulong such that they are 64-bit on 64-bit systems where they can be atomically incremented and are 32-bit on 32-bit systems which may not be able to atomically increment 64-bit numbers. Modify vm_stat_get() to expect ulongs. Signed-off-by: Suraj Jitindar Singh Reviewed-by: David Matlack Acked-by: Christian Borntraeger Signed-off-by: Paul Mackerras --- arch/arm/include/asm/kvm_host.h | 12 ++-- arch/arm64/include/asm/kvm_host.h | 12 ++-- arch/mips/include/asm/kvm_host.h | 46 ++++++------- arch/powerpc/include/asm/kvm_host.h | 60 ++++++++-------- arch/s390/include/asm/kvm_host.h | 134 ++++++++++++++++++------------------ arch/x86/include/asm/kvm_host.h | 72 +++++++++---------- virt/kvm/kvm_main.c | 4 +- 7 files changed, 170 insertions(+), 170 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index de338d93d11b..6ad21f04a922 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -183,15 +183,15 @@ struct kvm_vcpu_arch { }; struct kvm_vm_stat { - u32 remote_tlb_flush; + ulong remote_tlb_flush; }; struct kvm_vcpu_stat { - u32 halt_successful_poll; - u32 halt_attempted_poll; - u32 halt_poll_invalid; - u32 halt_wakeup; - u32 hvc_exit_stat; + u64 halt_successful_poll; + u64 halt_attempted_poll; + u64 halt_poll_invalid; + u64 halt_wakeup; + u64 hvc_exit_stat; u64 wfe_exit_stat; u64 wfi_exit_stat; u64 mmio_exit_user; diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 3eda975837d0..bd94e6766759 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -290,15 +290,15 @@ struct kvm_vcpu_arch { #endif struct kvm_vm_stat { - u32 remote_tlb_flush; + ulong remote_tlb_flush; }; struct kvm_vcpu_stat { - u32 halt_successful_poll; - u32 halt_attempted_poll; - u32 halt_poll_invalid; - u32 halt_wakeup; - u32 hvc_exit_stat; + u64 halt_successful_poll; + u64 halt_attempted_poll; + u64 halt_poll_invalid; + u64 halt_wakeup; + u64 hvc_exit_stat; u64 wfe_exit_stat; u64 wfi_exit_stat; u64 mmio_exit_user; diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index b54bcadd8aec..5f488dc8a7d5 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -110,32 +110,32 @@ extern atomic_t kvm_mips_instance; struct kvm_vm_stat { - u32 remote_tlb_flush; + ulong remote_tlb_flush; }; struct kvm_vcpu_stat { - u32 wait_exits; - u32 cache_exits; - u32 signal_exits; - u32 int_exits; - u32 cop_unusable_exits; - u32 tlbmod_exits; - u32 tlbmiss_ld_exits; - u32 tlbmiss_st_exits; - u32 addrerr_st_exits; - u32 addrerr_ld_exits; - u32 syscall_exits; - u32 resvd_inst_exits; - u32 break_inst_exits; - u32 trap_inst_exits; - u32 msa_fpe_exits; - u32 fpe_exits; - u32 msa_disabled_exits; - u32 flush_dcache_exits; - u32 halt_successful_poll; - u32 halt_attempted_poll; - u32 halt_poll_invalid; - u32 halt_wakeup; + u64 wait_exits; + u64 cache_exits; + u64 signal_exits; + u64 int_exits; + u64 cop_unusable_exits; + u64 tlbmod_exits; + u64 tlbmiss_ld_exits; + u64 tlbmiss_st_exits; + u64 addrerr_st_exits; + u64 addrerr_ld_exits; + u64 syscall_exits; + u64 resvd_inst_exits; + u64 break_inst_exits; + u64 trap_inst_exits; + u64 msa_fpe_exits; + u64 fpe_exits; + u64 msa_disabled_exits; + u64 flush_dcache_exits; + u64 halt_successful_poll; + u64 halt_attempted_poll; + u64 halt_poll_invalid; + u64 halt_wakeup; }; struct kvm_arch_memory_slot { diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 6ece4a854a59..5ec1dcf300f6 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -97,41 +97,41 @@ struct kvmppc_vcpu_book3s; struct kvmppc_book3s_shadow_vcpu; struct kvm_vm_stat { - u32 remote_tlb_flush; + ulong remote_tlb_flush; }; struct kvm_vcpu_stat { - u32 sum_exits; - u32 mmio_exits; - u32 signal_exits; - u32 light_exits; + u64 sum_exits; + u64 mmio_exits; + u64 signal_exits; + u64 light_exits; /* Account for special types of light exits: */ - u32 itlb_real_miss_exits; - u32 itlb_virt_miss_exits; - u32 dtlb_real_miss_exits; - u32 dtlb_virt_miss_exits; - u32 syscall_exits; - u32 isi_exits; - u32 dsi_exits; - u32 emulated_inst_exits; - u32 dec_exits; - u32 ext_intr_exits; - u32 halt_successful_poll; - u32 halt_attempted_poll; - u32 halt_poll_invalid; - u32 halt_wakeup; - u32 dbell_exits; - u32 gdbell_exits; - u32 ld; - u32 st; + u64 itlb_real_miss_exits; + u64 itlb_virt_miss_exits; + u64 dtlb_real_miss_exits; + u64 dtlb_virt_miss_exits; + u64 syscall_exits; + u64 isi_exits; + u64 dsi_exits; + u64 emulated_inst_exits; + u64 dec_exits; + u64 ext_intr_exits; + u64 halt_successful_poll; + u64 halt_attempted_poll; + u64 halt_poll_invalid; + u64 halt_wakeup; + u64 dbell_exits; + u64 gdbell_exits; + u64 ld; + u64 st; #ifdef CONFIG_PPC_BOOK3S - u32 pf_storage; - u32 pf_instruc; - u32 sp_storage; - u32 sp_instruc; - u32 queue_intr; - u32 ld_slow; - u32 st_slow; + u64 pf_storage; + u64 pf_instruc; + u64 sp_storage; + u64 sp_instruc; + u64 queue_intr; + u64 ld_slow; + u64 st_slow; #endif }; diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 8e5daf7a76ce..2bbe675c96b9 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -245,72 +245,72 @@ struct sie_page { } __packed; struct kvm_vcpu_stat { - u32 exit_userspace; - u32 exit_null; - u32 exit_external_request; - u32 exit_external_interrupt; - u32 exit_stop_request; - u32 exit_validity; - u32 exit_instruction; - u32 exit_pei; - u32 halt_successful_poll; - u32 halt_attempted_poll; - u32 halt_poll_invalid; - u32 halt_wakeup; - u32 instruction_lctl; - u32 instruction_lctlg; - u32 instruction_stctl; - u32 instruction_stctg; - u32 exit_program_interruption; - u32 exit_instr_and_program; - u32 exit_operation_exception; - u32 deliver_external_call; - u32 deliver_emergency_signal; - u32 deliver_service_signal; - u32 deliver_virtio_interrupt; - u32 deliver_stop_signal; - u32 deliver_prefix_signal; - u32 deliver_restart_signal; - u32 deliver_program_int; - u32 deliver_io_int; - u32 exit_wait_state; - u32 instruction_pfmf; - u32 instruction_stidp; - u32 instruction_spx; - u32 instruction_stpx; - u32 instruction_stap; - u32 instruction_storage_key; - u32 instruction_ipte_interlock; - u32 instruction_stsch; - u32 instruction_chsc; - u32 instruction_stsi; - u32 instruction_stfl; - u32 instruction_tprot; - u32 instruction_sie; - u32 instruction_essa; - u32 instruction_sthyi; - u32 instruction_sigp_sense; - u32 instruction_sigp_sense_running; - u32 instruction_sigp_external_call; - u32 instruction_sigp_emergency; - u32 instruction_sigp_cond_emergency; - u32 instruction_sigp_start; - u32 instruction_sigp_stop; - u32 instruction_sigp_stop_store_status; - u32 instruction_sigp_store_status; - u32 instruction_sigp_store_adtl_status; - u32 instruction_sigp_arch; - u32 instruction_sigp_prefix; - u32 instruction_sigp_restart; - u32 instruction_sigp_init_cpu_reset; - u32 instruction_sigp_cpu_reset; - u32 instruction_sigp_unknown; - u32 diagnose_10; - u32 diagnose_44; - u32 diagnose_9c; - u32 diagnose_258; - u32 diagnose_308; - u32 diagnose_500; + u64 exit_userspace; + u64 exit_null; + u64 exit_external_request; + u64 exit_external_interrupt; + u64 exit_stop_request; + u64 exit_validity; + u64 exit_instruction; + u64 exit_pei; + u64 halt_successful_poll; + u64 halt_attempted_poll; + u64 halt_poll_invalid; + u64 halt_wakeup; + u64 instruction_lctl; + u64 instruction_lctlg; + u64 instruction_stctl; + u64 instruction_stctg; + u64 exit_program_interruption; + u64 exit_instr_and_program; + u64 exit_operation_exception; + u64 deliver_external_call; + u64 deliver_emergency_signal; + u64 deliver_service_signal; + u64 deliver_virtio_interrupt; + u64 deliver_stop_signal; + u64 deliver_prefix_signal; + u64 deliver_restart_signal; + u64 deliver_program_int; + u64 deliver_io_int; + u64 exit_wait_state; + u64 instruction_pfmf; + u64 instruction_stidp; + u64 instruction_spx; + u64 instruction_stpx; + u64 instruction_stap; + u64 instruction_storage_key; + u64 instruction_ipte_interlock; + u64 instruction_stsch; + u64 instruction_chsc; + u64 instruction_stsi; + u64 instruction_stfl; + u64 instruction_tprot; + u64 instruction_sie; + u64 instruction_essa; + u64 instruction_sthyi; + u64 instruction_sigp_sense; + u64 instruction_sigp_sense_running; + u64 instruction_sigp_external_call; + u64 instruction_sigp_emergency; + u64 instruction_sigp_cond_emergency; + u64 instruction_sigp_start; + u64 instruction_sigp_stop; + u64 instruction_sigp_stop_store_status; + u64 instruction_sigp_store_status; + u64 instruction_sigp_store_adtl_status; + u64 instruction_sigp_arch; + u64 instruction_sigp_prefix; + u64 instruction_sigp_restart; + u64 instruction_sigp_init_cpu_reset; + u64 instruction_sigp_cpu_reset; + u64 instruction_sigp_unknown; + u64 diagnose_10; + u64 diagnose_44; + u64 diagnose_9c; + u64 diagnose_258; + u64 diagnose_308; + u64 diagnose_500; }; #define PGM_OPERATION 0x01 @@ -577,7 +577,7 @@ struct kvm_vcpu_arch { }; struct kvm_vm_stat { - u32 remote_tlb_flush; + ulong remote_tlb_flush; }; struct kvm_arch_memory_slot { diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 33ae3a4d0159..67c8f5268af5 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -790,45 +790,45 @@ struct kvm_arch { }; struct kvm_vm_stat { - u32 mmu_shadow_zapped; - u32 mmu_pte_write; - u32 mmu_pte_updated; - u32 mmu_pde_zapped; - u32 mmu_flooded; - u32 mmu_recycled; - u32 mmu_cache_miss; - u32 mmu_unsync; - u32 remote_tlb_flush; - u32 lpages; + ulong mmu_shadow_zapped; + ulong mmu_pte_write; + ulong mmu_pte_updated; + ulong mmu_pde_zapped; + ulong mmu_flooded; + ulong mmu_recycled; + ulong mmu_cache_miss; + ulong mmu_unsync; + ulong remote_tlb_flush; + ulong lpages; }; struct kvm_vcpu_stat { - u32 pf_fixed; - u32 pf_guest; - u32 tlb_flush; - u32 invlpg; - - u32 exits; - u32 io_exits; - u32 mmio_exits; - u32 signal_exits; - u32 irq_window_exits; - u32 nmi_window_exits; - u32 halt_exits; - u32 halt_successful_poll; - u32 halt_attempted_poll; - u32 halt_poll_invalid; - u32 halt_wakeup; - u32 request_irq_exits; - u32 irq_exits; - u32 host_state_reload; - u32 efer_reload; - u32 fpu_reload; - u32 insn_emulation; - u32 insn_emulation_fail; - u32 hypercalls; - u32 irq_injections; - u32 nmi_injections; + u64 pf_fixed; + u64 pf_guest; + u64 tlb_flush; + u64 invlpg; + + u64 exits; + u64 io_exits; + u64 mmio_exits; + u64 signal_exits; + u64 irq_window_exits; + u64 nmi_window_exits; + u64 halt_exits; + u64 halt_successful_poll; + u64 halt_attempted_poll; + u64 halt_poll_invalid; + u64 halt_wakeup; + u64 request_irq_exits; + u64 irq_exits; + u64 host_state_reload; + u64 efer_reload; + u64 fpu_reload; + u64 insn_emulation; + u64 insn_emulation_fail; + u64 hypercalls; + u64 irq_injections; + u64 nmi_injections; }; struct x86_instruction_info; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 195078225aa5..4171ef326543 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3619,7 +3619,7 @@ static int vm_stat_get_per_vm(void *data, u64 *val) { struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data; - *val = *(u32 *)((void *)stat_data->kvm + stat_data->offset); + *val = *(ulong *)((void *)stat_data->kvm + stat_data->offset); return 0; } @@ -3649,7 +3649,7 @@ static int vcpu_stat_get_per_vm(void *data, u64 *val) *val = 0; kvm_for_each_vcpu(i, vcpu, stat_data->kvm) - *val += *(u32 *)((void *)vcpu + stat_data->offset); + *val += *(u64 *)((void *)vcpu + stat_data->offset); return 0; } -- cgit v1.2.3 From 5ea11f2b31b83bd3c05357e6bec20f598e00705a Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Tue, 23 Aug 2016 13:52:41 -0500 Subject: svm: Introduces AVIC per-VM ID MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduces per-VM AVIC ID and helper functions to manage the IDs. Currently, the ID will be used to implement 32-bit AVIC IOMMU GA tag. The ID is 24-bit one-based indexing value, and is managed via helper functions to get the next ID, or to free an ID once a VM is destroyed. There should be no ID conflict for any active VMs. Reviewed-by: Radim Krčmář Signed-off-by: Suravee Suthikulpanit Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/svm.c | 51 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 52 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 33ae3a4d0159..d36176bb1b6d 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -781,6 +781,7 @@ struct kvm_arch { bool disabled_lapic_found; /* Struct members for AVIC */ + u32 avic_vm_id; u32 ldr_mode; struct page *avic_logical_id_table_page; struct page *avic_physical_id_table_page; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index af523d84d102..27e37d8044b3 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -96,6 +96,19 @@ MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id); #define AVIC_UNACCEL_ACCESS_OFFSET_MASK 0xFF0 #define AVIC_UNACCEL_ACCESS_VECTOR_MASK 0xFFFFFFFF +/* AVIC GATAG is encoded using VM and VCPU IDs */ +#define AVIC_VCPU_ID_BITS 8 +#define AVIC_VCPU_ID_MASK ((1 << AVIC_VCPU_ID_BITS) - 1) + +#define AVIC_VM_ID_BITS 24 +#define AVIC_VM_ID_NR (1 << AVIC_VM_ID_BITS) +#define AVIC_VM_ID_MASK ((1 << AVIC_VM_ID_BITS) - 1) + +#define AVIC_GATAG(x, y) (((x & AVIC_VM_ID_MASK) << AVIC_VCPU_ID_BITS) | \ + (y & AVIC_VCPU_ID_MASK)) +#define AVIC_GATAG_TO_VMID(x) ((x >> AVIC_VCPU_ID_BITS) & AVIC_VM_ID_MASK) +#define AVIC_GATAG_TO_VCPUID(x) (x & AVIC_VCPU_ID_MASK) + static bool erratum_383_found __read_mostly; static const u32 host_save_user_msrs[] = { @@ -242,6 +255,10 @@ static int avic; module_param(avic, int, S_IRUGO); #endif +/* AVIC VM ID bit masks and lock */ +static DECLARE_BITMAP(avic_vm_id_bitmap, AVIC_VM_ID_NR); +static DEFINE_SPINLOCK(avic_vm_id_lock); + static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); static void svm_flush_tlb(struct kvm_vcpu *vcpu); static void svm_complete_interrupts(struct vcpu_svm *svm); @@ -1280,10 +1297,40 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) return 0; } +static inline int avic_get_next_vm_id(void) +{ + int id; + + spin_lock(&avic_vm_id_lock); + + /* AVIC VM ID is one-based. */ + id = find_next_zero_bit(avic_vm_id_bitmap, AVIC_VM_ID_NR, 1); + if (id <= AVIC_VM_ID_MASK) + __set_bit(id, avic_vm_id_bitmap); + else + id = -EAGAIN; + + spin_unlock(&avic_vm_id_lock); + return id; +} + +static inline int avic_free_vm_id(int id) +{ + if (id <= 0 || id > AVIC_VM_ID_MASK) + return -EINVAL; + + spin_lock(&avic_vm_id_lock); + __clear_bit(id, avic_vm_id_bitmap); + spin_unlock(&avic_vm_id_lock); + return 0; +} + static void avic_vm_destroy(struct kvm *kvm) { struct kvm_arch *vm_data = &kvm->arch; + avic_free_vm_id(vm_data->avic_vm_id); + if (vm_data->avic_logical_id_table_page) __free_page(vm_data->avic_logical_id_table_page); if (vm_data->avic_physical_id_table_page) @@ -1300,6 +1347,10 @@ static int avic_vm_init(struct kvm *kvm) if (!avic) return 0; + vm_data->avic_vm_id = avic_get_next_vm_id(); + if (vm_data->avic_vm_id < 0) + return vm_data->avic_vm_id; + /* Allocating physical APIC ID table (4KB) */ p_page = alloc_page(GFP_KERNEL); if (!p_page) -- cgit v1.2.3 From 5881f73757cc3dbada878e67c119a801ed0f9a07 Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Tue, 23 Aug 2016 13:52:42 -0500 Subject: svm: Introduce AMD IOMMU avic_ga_log_notifier MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch introduces avic_ga_log_notifier, which will be called by IOMMU driver whenever it handles the Guest vAPIC (GA) log entry. Reviewed-by: Radim Krčmář Signed-off-by: Suravee Suthikulpanit Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/svm.c | 70 +++++++++++++++++++++++++++++++++++++++-- 2 files changed, 69 insertions(+), 2 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index d36176bb1b6d..4c738c206be3 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -785,6 +785,7 @@ struct kvm_arch { u32 ldr_mode; struct page *avic_logical_id_table_page; struct page *avic_physical_id_table_page; + struct hlist_node hnode; bool x2apic_format; bool x2apic_broadcast_quirk_disabled; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 27e37d8044b3..0a9e43b2bd26 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -34,6 +34,8 @@ #include #include #include +#include +#include #include #include @@ -945,6 +947,55 @@ static void svm_disable_lbrv(struct vcpu_svm *svm) set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0); } +/* Note: + * This hash table is used to map VM_ID to a struct kvm_arch, + * when handling AMD IOMMU GALOG notification to schedule in + * a particular vCPU. + */ +#define SVM_VM_DATA_HASH_BITS 8 +DECLARE_HASHTABLE(svm_vm_data_hash, SVM_VM_DATA_HASH_BITS); +static spinlock_t svm_vm_data_hash_lock; + +/* Note: + * This function is called from IOMMU driver to notify + * SVM to schedule in a particular vCPU of a particular VM. + */ +static int avic_ga_log_notifier(u32 ga_tag) +{ + unsigned long flags; + struct kvm_arch *ka = NULL; + struct kvm_vcpu *vcpu = NULL; + u32 vm_id = AVIC_GATAG_TO_VMID(ga_tag); + u32 vcpu_id = AVIC_GATAG_TO_VCPUID(ga_tag); + + pr_debug("SVM: %s: vm_id=%#x, vcpu_id=%#x\n", __func__, vm_id, vcpu_id); + + spin_lock_irqsave(&svm_vm_data_hash_lock, flags); + hash_for_each_possible(svm_vm_data_hash, ka, hnode, vm_id) { + struct kvm *kvm = container_of(ka, struct kvm, arch); + struct kvm_arch *vm_data = &kvm->arch; + + if (vm_data->avic_vm_id != vm_id) + continue; + vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id); + break; + } + spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags); + + if (!vcpu) + return 0; + + /* Note: + * At this point, the IOMMU should have already set the pending + * bit in the vAPIC backing page. So, we just need to schedule + * in the vcpu. + */ + if (vcpu->mode == OUTSIDE_GUEST_MODE) + kvm_vcpu_wake_up(vcpu); + + return 0; +} + static __init int svm_hardware_setup(void) { int cpu; @@ -1003,10 +1054,15 @@ static __init int svm_hardware_setup(void) if (avic) { if (!npt_enabled || !boot_cpu_has(X86_FEATURE_AVIC) || - !IS_ENABLED(CONFIG_X86_LOCAL_APIC)) + !IS_ENABLED(CONFIG_X86_LOCAL_APIC)) { avic = false; - else + } else { pr_info("AVIC enabled\n"); + + hash_init(svm_vm_data_hash); + spin_lock_init(&svm_vm_data_hash_lock); + amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier); + } } return 0; @@ -1327,6 +1383,7 @@ static inline int avic_free_vm_id(int id) static void avic_vm_destroy(struct kvm *kvm) { + unsigned long flags; struct kvm_arch *vm_data = &kvm->arch; avic_free_vm_id(vm_data->avic_vm_id); @@ -1335,10 +1392,15 @@ static void avic_vm_destroy(struct kvm *kvm) __free_page(vm_data->avic_logical_id_table_page); if (vm_data->avic_physical_id_table_page) __free_page(vm_data->avic_physical_id_table_page); + + spin_lock_irqsave(&svm_vm_data_hash_lock, flags); + hash_del(&vm_data->hnode); + spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags); } static int avic_vm_init(struct kvm *kvm) { + unsigned long flags; int err = -ENOMEM; struct kvm_arch *vm_data = &kvm->arch; struct page *p_page; @@ -1367,6 +1429,10 @@ static int avic_vm_init(struct kvm *kvm) vm_data->avic_logical_id_table_page = l_page; clear_page(page_address(l_page)); + spin_lock_irqsave(&svm_vm_data_hash_lock, flags); + hash_add(svm_vm_data_hash, &vm_data->hnode, vm_data->avic_vm_id); + spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags); + return 0; free_avic: -- cgit v1.2.3 From 7d06d9c9bd813fc956b9c7bffc1b9724009983eb Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Fri, 29 Jul 2016 09:30:12 -0700 Subject: mm: Implement new pkey_mprotect() system call pkey_mprotect() is just like mprotect, except it also takes a protection key as an argument. On systems that do not support protection keys, it still works, but requires that key=0. Otherwise it does exactly what mprotect does. I expect it to get used like this, if you want to guarantee that any mapping you create can *never* be accessed without the right protection keys set up. int real_prot = PROT_READ|PROT_WRITE; pkey = pkey_alloc(0, PKEY_DENY_ACCESS); ptr = mmap(NULL, PAGE_SIZE, PROT_NONE, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0); ret = pkey_mprotect(ptr, PAGE_SIZE, real_prot, pkey); This way, there is *no* window where the mapping is accessible since it was always either PROT_NONE or had a protection key set that denied all access. We settled on 'unsigned long' for the type of the key here. We only need 4 bits on x86 today, but I figured that other architectures might need some more space. Semantically, we have a bit of a problem if we combine this syscall with our previously-introduced execute-only support: What do we do when we mix execute-only pkey use with pkey_mprotect() use? For instance: pkey_mprotect(ptr, PAGE_SIZE, PROT_WRITE, 6); // set pkey=6 mprotect(ptr, PAGE_SIZE, PROT_EXEC); // set pkey=X_ONLY_PKEY? mprotect(ptr, PAGE_SIZE, PROT_WRITE); // is pkey=6 again? To solve that, we make the plain-mprotect()-initiated execute-only support only apply to VMAs that have the default protection key (0) set on them. Proposed semantics: 1. protection key 0 is special and represents the default, "unassigned" protection key. It is always allocated. 2. mprotect() never affects a mapping's pkey_mprotect()-assigned protection key. A protection key of 0 (even if set explicitly) represents an unassigned protection key. 2a. mprotect(PROT_EXEC) on a mapping with an assigned protection key may or may not result in a mapping with execute-only properties. pkey_mprotect() plus pkey_set() on all threads should be used to _guarantee_ execute-only semantics if this is not a strong enough semantic. 3. mprotect(PROT_EXEC) may result in an "execute-only" mapping. The kernel will internally attempt to allocate and dedicate a protection key for the purpose of execute-only mappings. This may not be possible in cases where there are no free protection keys available. It can also happen, of course, in situations where there is no hardware support for protection keys. Signed-off-by: Dave Hansen Acked-by: Mel Gorman Cc: linux-arch@vger.kernel.org Cc: Dave Hansen Cc: arnd@arndb.de Cc: linux-api@vger.kernel.org Cc: linux-mm@kvack.org Cc: luto@kernel.org Cc: akpm@linux-foundation.org Cc: torvalds@linux-foundation.org Link: http://lkml.kernel.org/r/20160729163012.3DDD36C4@viggo.jf.intel.com Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/mmu_context.h | 15 ++++++++++----- arch/x86/include/asm/pkeys.h | 11 +++++++++-- include/linux/pkeys.h | 12 ------------ mm/mprotect.c | 30 ++++++++++++++++++++++++++---- 4 files changed, 45 insertions(+), 23 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index d8abfcf524d1..af0251fc85ed 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -4,6 +4,7 @@ #include #include #include +#include #include @@ -195,16 +196,20 @@ static inline void arch_unmap(struct mm_struct *mm, struct vm_area_struct *vma, mpx_notify_unmap(mm, vma, start, end); } +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS static inline int vma_pkey(struct vm_area_struct *vma) { - u16 pkey = 0; -#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS unsigned long vma_pkey_mask = VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2 | VM_PKEY_BIT3; - pkey = (vma->vm_flags & vma_pkey_mask) >> VM_PKEY_SHIFT; -#endif - return pkey; + + return (vma->vm_flags & vma_pkey_mask) >> VM_PKEY_SHIFT; +} +#else +static inline int vma_pkey(struct vm_area_struct *vma) +{ + return 0; } +#endif static inline bool __pkru_allows_pkey(u16 pkey, bool write) { diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index 7b84565c916c..33777c291a85 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -1,7 +1,12 @@ #ifndef _ASM_X86_PKEYS_H #define _ASM_X86_PKEYS_H -#define arch_max_pkey() (boot_cpu_has(X86_FEATURE_OSPKE) ? 16 : 1) +#define PKEY_DEDICATED_EXECUTE_ONLY 15 +/* + * Consider the PKEY_DEDICATED_EXECUTE_ONLY key unavailable. + */ +#define arch_max_pkey() (boot_cpu_has(X86_FEATURE_OSPKE) ? \ + PKEY_DEDICATED_EXECUTE_ONLY : 1) extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val); @@ -10,7 +15,6 @@ extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, * Try to dedicate one of the protection keys to be used as an * execute-only protection key. */ -#define PKEY_DEDICATED_EXECUTE_ONLY 15 extern int __execute_only_pkey(struct mm_struct *mm); static inline int execute_only_pkey(struct mm_struct *mm) { @@ -31,4 +35,7 @@ static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma, return __arch_override_mprotect_pkey(vma, prot, pkey); } +extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey, + unsigned long init_val); + #endif /*_ASM_X86_PKEYS_H */ diff --git a/include/linux/pkeys.h b/include/linux/pkeys.h index 1d405a2b7272..0030b4024559 100644 --- a/include/linux/pkeys.h +++ b/include/linux/pkeys.h @@ -18,16 +18,4 @@ #define PKEY_DEDICATED_EXECUTE_ONLY 0 #endif /* ! CONFIG_ARCH_HAS_PKEYS */ -/* - * This is called from mprotect_pkey(). - * - * Returns true if the protection keys is valid. - */ -static inline bool validate_pkey(int pkey) -{ - if (pkey < 0) - return false; - return (pkey < arch_max_pkey()); -} - #endif /* _LINUX_PKEYS_H */ diff --git a/mm/mprotect.c b/mm/mprotect.c index a4830f0325fe..dd3f40a2935f 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -352,8 +352,11 @@ fail: return error; } -SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len, - unsigned long, prot) +/* + * pkey==-1 when doing a legacy mprotect() + */ +static int do_mprotect_pkey(unsigned long start, size_t len, + unsigned long prot, int pkey) { unsigned long nstart, end, tmp, reqprot; struct vm_area_struct *vma, *prev; @@ -361,6 +364,12 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len, const int grows = prot & (PROT_GROWSDOWN|PROT_GROWSUP); const bool rier = (current->personality & READ_IMPLIES_EXEC) && (prot & PROT_READ); + /* + * A temporary safety check since we are not validating + * the pkey before we introduce the allocation code. + */ + if (pkey != -1) + return -EINVAL; prot &= ~(PROT_GROWSDOWN|PROT_GROWSUP); if (grows == (PROT_GROWSDOWN|PROT_GROWSUP)) /* can't be both */ @@ -409,7 +418,7 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len, for (nstart = start ; ; ) { unsigned long newflags; - int pkey = arch_override_mprotect_pkey(vma, prot, -1); + int new_vma_pkey; /* Here we know that vma->vm_start <= nstart < vma->vm_end. */ @@ -417,7 +426,8 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len, if (rier && (vma->vm_flags & VM_MAYEXEC)) prot |= PROT_EXEC; - newflags = calc_vm_prot_bits(prot, pkey); + new_vma_pkey = arch_override_mprotect_pkey(vma, prot, pkey); + newflags = calc_vm_prot_bits(prot, new_vma_pkey); newflags |= (vma->vm_flags & ~(VM_READ | VM_WRITE | VM_EXEC)); /* newflags >> 4 shift VM_MAY% in place of VM_% */ @@ -454,3 +464,15 @@ out: up_write(¤t->mm->mmap_sem); return error; } + +SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len, + unsigned long, prot) +{ + return do_mprotect_pkey(start, len, prot, -1); +} + +SYSCALL_DEFINE4(pkey_mprotect, unsigned long, start, size_t, len, + unsigned long, prot, int, pkey) +{ + return do_mprotect_pkey(start, len, prot, pkey); +} -- cgit v1.2.3 From a8502b67d739c1d7a4542c1da0a5d98a6a58c177 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Fri, 29 Jul 2016 09:30:13 -0700 Subject: x86/pkeys: Make mprotect_key() mask off additional vm_flags Today, mprotect() takes 4 bits of data: PROT_READ/WRITE/EXEC/NONE. Three of those bits: READ/WRITE/EXEC get translated directly in to vma->vm_flags by calc_vm_prot_bits(). If a bit is unset in mprotect()'s 'prot' argument then it must be cleared in vma->vm_flags during the mprotect() call. We do this clearing today by first calculating the VMA flags we want set, then clearing the ones we do not want to inherit from the original VMA: vm_flags = calc_vm_prot_bits(prot, key); ... newflags = vm_flags; newflags |= (vma->vm_flags & ~(VM_READ | VM_WRITE | VM_EXEC)); However, we *also* want to mask off the original VMA's vm_flags in which we store the protection key. To do that, this patch adds a new macro: ARCH_VM_PKEY_FLAGS which allows the architecture to specify additional bits that it would like cleared. We use that to ensure that the VM_PKEY_BIT* bits get cleared. Signed-off-by: Dave Hansen Acked-by: Mel Gorman Reviewed-by: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: Dave Hansen Cc: arnd@arndb.de Cc: linux-api@vger.kernel.org Cc: linux-mm@kvack.org Cc: luto@kernel.org Cc: akpm@linux-foundation.org Cc: torvalds@linux-foundation.org Link: http://lkml.kernel.org/r/20160729163013.E48D6981@viggo.jf.intel.com Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/pkeys.h | 2 ++ include/linux/pkeys.h | 1 + mm/mprotect.c | 11 ++++++++++- 3 files changed, 13 insertions(+), 1 deletion(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index 33777c291a85..666ffc862ef7 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -38,4 +38,6 @@ static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma, extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val); +#define ARCH_VM_PKEY_FLAGS (VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2 | VM_PKEY_BIT3) + #endif /*_ASM_X86_PKEYS_H */ diff --git a/include/linux/pkeys.h b/include/linux/pkeys.h index 0030b4024559..6899b0bc7ce0 100644 --- a/include/linux/pkeys.h +++ b/include/linux/pkeys.h @@ -16,6 +16,7 @@ #define execute_only_pkey(mm) (0) #define arch_override_mprotect_pkey(vma, prot, pkey) (0) #define PKEY_DEDICATED_EXECUTE_ONLY 0 +#define ARCH_VM_PKEY_FLAGS 0 #endif /* ! CONFIG_ARCH_HAS_PKEYS */ #endif /* _LINUX_PKEYS_H */ diff --git a/mm/mprotect.c b/mm/mprotect.c index dd3f40a2935f..abd9c8257b2e 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -417,6 +417,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len, prev = vma; for (nstart = start ; ; ) { + unsigned long mask_off_old_flags; unsigned long newflags; int new_vma_pkey; @@ -426,9 +427,17 @@ static int do_mprotect_pkey(unsigned long start, size_t len, if (rier && (vma->vm_flags & VM_MAYEXEC)) prot |= PROT_EXEC; + /* + * Each mprotect() call explicitly passes r/w/x permissions. + * If a permission is not passed to mprotect(), it must be + * cleared from the VMA. + */ + mask_off_old_flags = VM_READ | VM_WRITE | VM_EXEC | + ARCH_VM_PKEY_FLAGS; + new_vma_pkey = arch_override_mprotect_pkey(vma, prot, pkey); newflags = calc_vm_prot_bits(prot, new_vma_pkey); - newflags |= (vma->vm_flags & ~(VM_READ | VM_WRITE | VM_EXEC)); + newflags |= (vma->vm_flags & ~mask_off_old_flags); /* newflags >> 4 shift VM_MAY% in place of VM_% */ if ((newflags & ~(newflags >> 4)) & (VM_READ | VM_WRITE | VM_EXEC)) { -- cgit v1.2.3 From e8c24d3a23a469f1f40d4de24d872ca7023ced0a Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Fri, 29 Jul 2016 09:30:15 -0700 Subject: x86/pkeys: Allocation/free syscalls This patch adds two new system calls: int pkey_alloc(unsigned long flags, unsigned long init_access_rights) int pkey_free(int pkey); These implement an "allocator" for the protection keys themselves, which can be thought of as analogous to the allocator that the kernel has for file descriptors. The kernel tracks which numbers are in use, and only allows operations on keys that are valid. A key which was not obtained by pkey_alloc() may not, for instance, be passed to pkey_mprotect(). These system calls are also very important given the kernel's use of pkeys to implement execute-only support. These help ensure that userspace can never assume that it has control of a key unless it first asks the kernel. The kernel does not promise to preserve PKRU (right register) contents except for allocated pkeys. The 'init_access_rights' argument to pkey_alloc() specifies the rights that will be established for the returned pkey. For instance: pkey = pkey_alloc(flags, PKEY_DENY_WRITE); will allocate 'pkey', but also sets the bits in PKRU[1] such that writing to 'pkey' is already denied. The kernel does not prevent pkey_free() from successfully freeing in-use pkeys (those still assigned to a memory range by pkey_mprotect()). It would be expensive to implement the checks for this, so we instead say, "Just don't do it" since sane software will never do it anyway. Any piece of userspace calling pkey_alloc() needs to be prepared for it to fail. Why? pkey_alloc() returns the same error code (ENOSPC) when there are no pkeys and when pkeys are unsupported. They can be unsupported for a whole host of reasons, so apps must be prepared for this. Also, libraries or LD_PRELOADs might steal keys before an application gets access to them. This allocation mechanism could be implemented in userspace. Even if we did it in userspace, we would still need additional user/kernel interfaces to tell userspace which keys are being used by the kernel internally (such as for execute-only mappings). Having the kernel provide this facility completely removes the need for these additional interfaces, or having an implementation of this in userspace at all. Note that we have to make changes to all of the architectures that do not use mman-common.h because we use the new PKEY_DENY_ACCESS/WRITE macros in arch-independent code. 1. PKRU is the Protection Key Rights User register. It is a usermode-accessible register that controls whether writes and/or access to each individual pkey is allowed or denied. Signed-off-by: Dave Hansen Acked-by: Mel Gorman Cc: linux-arch@vger.kernel.org Cc: Dave Hansen Cc: arnd@arndb.de Cc: linux-api@vger.kernel.org Cc: linux-mm@kvack.org Cc: luto@kernel.org Cc: akpm@linux-foundation.org Cc: torvalds@linux-foundation.org Link: http://lkml.kernel.org/r/20160729163015.444FE75F@viggo.jf.intel.com Signed-off-by: Thomas Gleixner --- arch/alpha/include/uapi/asm/mman.h | 5 +++ arch/mips/include/uapi/asm/mman.h | 5 +++ arch/parisc/include/uapi/asm/mman.h | 5 +++ arch/x86/include/asm/mmu.h | 8 ++++ arch/x86/include/asm/mmu_context.h | 10 ++++- arch/x86/include/asm/pkeys.h | 73 +++++++++++++++++++++++++++++++--- arch/x86/kernel/fpu/xstate.c | 5 ++- arch/x86/mm/pkeys.c | 38 ++++++++++++++---- arch/xtensa/include/uapi/asm/mman.h | 5 +++ include/linux/pkeys.h | 28 ++++++++++--- include/uapi/asm-generic/mman-common.h | 5 +++ mm/mprotect.c | 61 +++++++++++++++++++++++++--- 12 files changed, 221 insertions(+), 27 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h index fec1947b8dbc..02760f6e6ca4 100644 --- a/arch/alpha/include/uapi/asm/mman.h +++ b/arch/alpha/include/uapi/asm/mman.h @@ -78,4 +78,9 @@ #define MAP_HUGE_SHIFT 26 #define MAP_HUGE_MASK 0x3f +#define PKEY_DISABLE_ACCESS 0x1 +#define PKEY_DISABLE_WRITE 0x2 +#define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ + PKEY_DISABLE_WRITE) + #endif /* __ALPHA_MMAN_H__ */ diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h index ccdcfcbb24aa..655e2fb5395b 100644 --- a/arch/mips/include/uapi/asm/mman.h +++ b/arch/mips/include/uapi/asm/mman.h @@ -105,4 +105,9 @@ #define MAP_HUGE_SHIFT 26 #define MAP_HUGE_MASK 0x3f +#define PKEY_DISABLE_ACCESS 0x1 +#define PKEY_DISABLE_WRITE 0x2 +#define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ + PKEY_DISABLE_WRITE) + #endif /* _ASM_MMAN_H */ diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h index f3db7d8eb0c2..5979745815a5 100644 --- a/arch/parisc/include/uapi/asm/mman.h +++ b/arch/parisc/include/uapi/asm/mman.h @@ -75,4 +75,9 @@ #define MAP_HUGE_SHIFT 26 #define MAP_HUGE_MASK 0x3f +#define PKEY_DISABLE_ACCESS 0x1 +#define PKEY_DISABLE_WRITE 0x2 +#define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ + PKEY_DISABLE_WRITE) + #endif /* __PARISC_MMAN_H__ */ diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index 1ea0baef1175..72198c64e646 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -23,6 +23,14 @@ typedef struct { const struct vdso_image *vdso_image; /* vdso image in use */ atomic_t perf_rdpmc_allowed; /* nonzero if rdpmc is allowed */ +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS + /* + * One bit per protection key says whether userspace can + * use it or not. protected by mmap_sem. + */ + u16 pkey_allocation_map; + s16 execute_only_pkey; +#endif } mm_context_t; #ifdef CONFIG_SMP diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index af0251fc85ed..8e0a9fe86de4 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -108,7 +108,16 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { + #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS + if (cpu_feature_enabled(X86_FEATURE_OSPKE)) { + /* pkey 0 is the default and always allocated */ + mm->context.pkey_allocation_map = 0x1; + /* -1 means unallocated or invalid */ + mm->context.execute_only_pkey = -1; + } + #endif init_new_context_ldt(tsk, mm); + return 0; } static inline void destroy_context(struct mm_struct *mm) @@ -263,5 +272,4 @@ static inline bool arch_pte_access_permitted(pte_t pte, bool write) { return __pkru_allows_pkey(pte_flags_pkey(pte_flags(pte)), write); } - #endif /* _ASM_X86_MMU_CONTEXT_H */ diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index 666ffc862ef7..b406889de0db 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -1,12 +1,7 @@ #ifndef _ASM_X86_PKEYS_H #define _ASM_X86_PKEYS_H -#define PKEY_DEDICATED_EXECUTE_ONLY 15 -/* - * Consider the PKEY_DEDICATED_EXECUTE_ONLY key unavailable. - */ -#define arch_max_pkey() (boot_cpu_has(X86_FEATURE_OSPKE) ? \ - PKEY_DEDICATED_EXECUTE_ONLY : 1) +#define arch_max_pkey() (boot_cpu_has(X86_FEATURE_OSPKE) ? 16 : 1) extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val); @@ -40,4 +35,70 @@ extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey, #define ARCH_VM_PKEY_FLAGS (VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2 | VM_PKEY_BIT3) +#define mm_pkey_allocation_map(mm) (mm->context.pkey_allocation_map) +#define mm_set_pkey_allocated(mm, pkey) do { \ + mm_pkey_allocation_map(mm) |= (1U << pkey); \ +} while (0) +#define mm_set_pkey_free(mm, pkey) do { \ + mm_pkey_allocation_map(mm) &= ~(1U << pkey); \ +} while (0) + +static inline +bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey) +{ + return mm_pkey_allocation_map(mm) & (1U << pkey); +} + +/* + * Returns a positive, 4-bit key on success, or -1 on failure. + */ +static inline +int mm_pkey_alloc(struct mm_struct *mm) +{ + /* + * Note: this is the one and only place we make sure + * that the pkey is valid as far as the hardware is + * concerned. The rest of the kernel trusts that + * only good, valid pkeys come out of here. + */ + u16 all_pkeys_mask = ((1U << arch_max_pkey()) - 1); + int ret; + + /* + * Are we out of pkeys? We must handle this specially + * because ffz() behavior is undefined if there are no + * zeros. + */ + if (mm_pkey_allocation_map(mm) == all_pkeys_mask) + return -1; + + ret = ffz(mm_pkey_allocation_map(mm)); + + mm_set_pkey_allocated(mm, ret); + + return ret; +} + +static inline +int mm_pkey_free(struct mm_struct *mm, int pkey) +{ + /* + * pkey 0 is special, always allocated and can never + * be freed. + */ + if (!pkey) + return -EINVAL; + if (!mm_pkey_is_allocated(mm, pkey)) + return -EINVAL; + + mm_set_pkey_free(mm, pkey); + + return 0; +} + +extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, + unsigned long init_val); +extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey, + unsigned long init_val); + #endif /*_ASM_X86_PKEYS_H */ diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 01567aa87503..124aa5c593f8 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -5,6 +5,7 @@ */ #include #include +#include #include #include @@ -866,9 +867,10 @@ const void *get_xsave_field_ptr(int xsave_state) return get_xsave_addr(&fpu->state.xsave, xsave_state); } +#ifdef CONFIG_ARCH_HAS_PKEYS + #define NR_VALID_PKRU_BITS (CONFIG_NR_PROTECTION_KEYS * 2) #define PKRU_VALID_MASK (NR_VALID_PKRU_BITS - 1) - /* * This will go out and modify PKRU register to set the access * rights for @pkey to @init_val. @@ -914,6 +916,7 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, return 0; } +#endif /* ! CONFIG_ARCH_HAS_PKEYS */ /* * This is similar to user_regset_copyout(), but will not add offset to diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index e8c474451928..e6113bbb56e1 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -21,8 +21,19 @@ int __execute_only_pkey(struct mm_struct *mm) { + bool need_to_set_mm_pkey = false; + int execute_only_pkey = mm->context.execute_only_pkey; int ret; + /* Do we need to assign a pkey for mm's execute-only maps? */ + if (execute_only_pkey == -1) { + /* Go allocate one to use, which might fail */ + execute_only_pkey = mm_pkey_alloc(mm); + if (execute_only_pkey < 0) + return -1; + need_to_set_mm_pkey = true; + } + /* * We do not want to go through the relatively costly * dance to set PKRU if we do not need to. Check it @@ -32,22 +43,33 @@ int __execute_only_pkey(struct mm_struct *mm) * can make fpregs inactive. */ preempt_disable(); - if (fpregs_active() && - !__pkru_allows_read(read_pkru(), PKEY_DEDICATED_EXECUTE_ONLY)) { + if (!need_to_set_mm_pkey && + fpregs_active() && + !__pkru_allows_read(read_pkru(), execute_only_pkey)) { preempt_enable(); - return PKEY_DEDICATED_EXECUTE_ONLY; + return execute_only_pkey; } preempt_enable(); - ret = arch_set_user_pkey_access(current, PKEY_DEDICATED_EXECUTE_ONLY, + + /* + * Set up PKRU so that it denies access for everything + * other than execution. + */ + ret = arch_set_user_pkey_access(current, execute_only_pkey, PKEY_DISABLE_ACCESS); /* * If the PKRU-set operation failed somehow, just return * 0 and effectively disable execute-only support. */ - if (ret) - return 0; + if (ret) { + mm_set_pkey_free(mm, execute_only_pkey); + return -1; + } - return PKEY_DEDICATED_EXECUTE_ONLY; + /* We got one, store it and use it from here on out */ + if (need_to_set_mm_pkey) + mm->context.execute_only_pkey = execute_only_pkey; + return execute_only_pkey; } static inline bool vma_is_pkey_exec_only(struct vm_area_struct *vma) @@ -55,7 +77,7 @@ static inline bool vma_is_pkey_exec_only(struct vm_area_struct *vma) /* Do this check first since the vm_flags should be hot */ if ((vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)) != VM_EXEC) return false; - if (vma_pkey(vma) != PKEY_DEDICATED_EXECUTE_ONLY) + if (vma_pkey(vma) != vma->vm_mm->context.execute_only_pkey) return false; return true; diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h index 9e079d49e7f2..24365b30aae9 100644 --- a/arch/xtensa/include/uapi/asm/mman.h +++ b/arch/xtensa/include/uapi/asm/mman.h @@ -117,4 +117,9 @@ #define MAP_HUGE_SHIFT 26 #define MAP_HUGE_MASK 0x3f +#define PKEY_DISABLE_ACCESS 0x1 +#define PKEY_DISABLE_WRITE 0x2 +#define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ + PKEY_DISABLE_WRITE) + #endif /* _XTENSA_MMAN_H */ diff --git a/include/linux/pkeys.h b/include/linux/pkeys.h index 6899b0bc7ce0..8ff21125dc8a 100644 --- a/include/linux/pkeys.h +++ b/include/linux/pkeys.h @@ -4,11 +4,6 @@ #include #include -#define PKEY_DISABLE_ACCESS 0x1 -#define PKEY_DISABLE_WRITE 0x2 -#define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ - PKEY_DISABLE_WRITE) - #ifdef CONFIG_ARCH_HAS_PKEYS #include #else /* ! CONFIG_ARCH_HAS_PKEYS */ @@ -17,6 +12,29 @@ #define arch_override_mprotect_pkey(vma, prot, pkey) (0) #define PKEY_DEDICATED_EXECUTE_ONLY 0 #define ARCH_VM_PKEY_FLAGS 0 + +static inline bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey) +{ + return (pkey == 0); +} + +static inline int mm_pkey_alloc(struct mm_struct *mm) +{ + return -1; +} + +static inline int mm_pkey_free(struct mm_struct *mm, int pkey) +{ + WARN_ONCE(1, "free of protection key when disabled"); + return -EINVAL; +} + +static inline int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, + unsigned long init_val) +{ + return 0; +} + #endif /* ! CONFIG_ARCH_HAS_PKEYS */ #endif /* _LINUX_PKEYS_H */ diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h index 58274382a616..8c27db0c5c08 100644 --- a/include/uapi/asm-generic/mman-common.h +++ b/include/uapi/asm-generic/mman-common.h @@ -72,4 +72,9 @@ #define MAP_HUGE_SHIFT 26 #define MAP_HUGE_MASK 0x3f +#define PKEY_DISABLE_ACCESS 0x1 +#define PKEY_DISABLE_WRITE 0x2 +#define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ + PKEY_DISABLE_WRITE) + #endif /* __ASM_GENERIC_MMAN_COMMON_H */ diff --git a/mm/mprotect.c b/mm/mprotect.c index abd9c8257b2e..7b35ee3894ee 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -23,11 +23,13 @@ #include #include #include +#include #include #include #include #include #include +#include #include #include "internal.h" @@ -364,12 +366,6 @@ static int do_mprotect_pkey(unsigned long start, size_t len, const int grows = prot & (PROT_GROWSDOWN|PROT_GROWSUP); const bool rier = (current->personality & READ_IMPLIES_EXEC) && (prot & PROT_READ); - /* - * A temporary safety check since we are not validating - * the pkey before we introduce the allocation code. - */ - if (pkey != -1) - return -EINVAL; prot &= ~(PROT_GROWSDOWN|PROT_GROWSUP); if (grows == (PROT_GROWSDOWN|PROT_GROWSUP)) /* can't be both */ @@ -391,6 +387,14 @@ static int do_mprotect_pkey(unsigned long start, size_t len, if (down_write_killable(¤t->mm->mmap_sem)) return -EINTR; + /* + * If userspace did not allocate the pkey, do not let + * them use it here. + */ + error = -EINVAL; + if ((pkey != -1) && !mm_pkey_is_allocated(current->mm, pkey)) + goto out; + vma = find_vma(current->mm, start); error = -ENOMEM; if (!vma) @@ -485,3 +489,48 @@ SYSCALL_DEFINE4(pkey_mprotect, unsigned long, start, size_t, len, { return do_mprotect_pkey(start, len, prot, pkey); } + +SYSCALL_DEFINE2(pkey_alloc, unsigned long, flags, unsigned long, init_val) +{ + int pkey; + int ret; + + /* No flags supported yet. */ + if (flags) + return -EINVAL; + /* check for unsupported init values */ + if (init_val & ~PKEY_ACCESS_MASK) + return -EINVAL; + + down_write(¤t->mm->mmap_sem); + pkey = mm_pkey_alloc(current->mm); + + ret = -ENOSPC; + if (pkey == -1) + goto out; + + ret = arch_set_user_pkey_access(current, pkey, init_val); + if (ret) { + mm_pkey_free(current->mm, pkey); + goto out; + } + ret = pkey; +out: + up_write(¤t->mm->mmap_sem); + return ret; +} + +SYSCALL_DEFINE1(pkey_free, int, pkey) +{ + int ret; + + down_write(¤t->mm->mmap_sem); + ret = mm_pkey_free(current->mm, pkey); + up_write(¤t->mm->mmap_sem); + + /* + * We could provie warnings or errors if any VMA still + * has the pkey set here. + */ + return ret; +} -- cgit v1.2.3 From acd547b29880800d29222c4632d2c145e401988c Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Fri, 29 Jul 2016 09:30:21 -0700 Subject: x86/pkeys: Default to a restrictive init PKRU PKRU is the register that lets you disallow writes or all access to a given protection key. The XSAVE hardware defines an "init state" of 0 for PKRU: its most permissive state, allowing access/writes to everything. Since we start off all new processes with the init state, we start all processes off with the most permissive possible PKRU. This is unfortunate. If a thread is clone()'d [1] before a program has time to set PKRU to a restrictive value, that thread will be able to write to all data, no matter what pkey is set on it. This weakens any integrity guarantees that we want pkeys to provide. To fix this, we define a very restrictive PKRU to override the XSAVE-provided value when we create a new FPU context. We choose a value that only allows access to pkey 0, which is as restrictive as we can practically make it. This does not cause any practical problems with applications using protection keys because we require them to specify initial permissions for each key when it is allocated, which override the restrictive default. In the end, this ensures that threads which do not know how to manage their own pkey rights can not do damage to data which is pkey-protected. I would have thought this was a pretty contrived scenario, except that I heard a bug report from an MPX user who was creating threads in some very early code before main(). It may be crazy, but folks evidently _do_ it. Signed-off-by: Dave Hansen Cc: linux-arch@vger.kernel.org Cc: Dave Hansen Cc: mgorman@techsingularity.net Cc: arnd@arndb.de Cc: linux-api@vger.kernel.org Cc: linux-mm@kvack.org Cc: luto@kernel.org Cc: akpm@linux-foundation.org Cc: torvalds@linux-foundation.org Link: http://lkml.kernel.org/r/20160729163021.F3C25D4A@viggo.jf.intel.com Signed-off-by: Thomas Gleixner --- Documentation/kernel-parameters.txt | 5 +++++ arch/x86/include/asm/pkeys.h | 1 + arch/x86/kernel/fpu/core.c | 4 ++++ arch/x86/mm/pkeys.c | 38 +++++++++++++++++++++++++++++++++++++ include/linux/pkeys.h | 4 ++++ 5 files changed, 52 insertions(+) (limited to 'arch/x86/include') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index a4f4d693e2c1..3725976d0af5 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1643,6 +1643,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted. initrd= [BOOT] Specify the location of the initial ramdisk + init_pkru= [x86] Specify the default memory protection keys rights + register contents for all processes. 0x55555554 by + default (disallow access to all but pkey 0). Can + override in debugfs after boot. + inport.irq= [HW] Inport (ATI XL and Microsoft) busmouse driver Format: diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index b406889de0db..34684adb6899 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -100,5 +100,6 @@ extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val); extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val); +extern void copy_init_pkru_to_fpregs(void); #endif /*_ASM_X86_PKEYS_H */ diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 3fc03a09a93b..47004010ad5d 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -12,6 +12,7 @@ #include #include +#include #define CREATE_TRACE_POINTS #include @@ -505,6 +506,9 @@ static inline void copy_init_fpstate_to_fpregs(void) copy_kernel_to_fxregs(&init_fpstate.fxsave); else copy_kernel_to_fregs(&init_fpstate.fsave); + + if (boot_cpu_has(X86_FEATURE_OSPKE)) + copy_init_pkru_to_fpregs(); } /* diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index e6113bbb56e1..ddc54949078a 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -121,3 +121,41 @@ int __arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey */ return vma_pkey(vma); } + +#define PKRU_AD_KEY(pkey) (PKRU_AD_BIT << ((pkey) * PKRU_BITS_PER_PKEY)) + +/* + * Make the default PKRU value (at execve() time) as restrictive + * as possible. This ensures that any threads clone()'d early + * in the process's lifetime will not accidentally get access + * to data which is pkey-protected later on. + */ +u32 init_pkru_value = PKRU_AD_KEY( 1) | PKRU_AD_KEY( 2) | PKRU_AD_KEY( 3) | + PKRU_AD_KEY( 4) | PKRU_AD_KEY( 5) | PKRU_AD_KEY( 6) | + PKRU_AD_KEY( 7) | PKRU_AD_KEY( 8) | PKRU_AD_KEY( 9) | + PKRU_AD_KEY(10) | PKRU_AD_KEY(11) | PKRU_AD_KEY(12) | + PKRU_AD_KEY(13) | PKRU_AD_KEY(14) | PKRU_AD_KEY(15); + +/* + * Called from the FPU code when creating a fresh set of FPU + * registers. This is called from a very specific context where + * we know the FPU regstiers are safe for use and we can use PKRU + * directly. The fact that PKRU is only available when we are + * using eagerfpu mode makes this possible. + */ +void copy_init_pkru_to_fpregs(void) +{ + u32 init_pkru_value_snapshot = READ_ONCE(init_pkru_value); + /* + * Any write to PKRU takes it out of the XSAVE 'init + * state' which increases context switch cost. Avoid + * writing 0 when PKRU was already 0. + */ + if (!init_pkru_value_snapshot && !read_pkru()) + return; + /* + * Override the PKRU state that came from 'init_fpstate' + * with the baseline from the process. + */ + write_pkru(init_pkru_value_snapshot); +} diff --git a/include/linux/pkeys.h b/include/linux/pkeys.h index 8ff21125dc8a..e4c08c1ff0c5 100644 --- a/include/linux/pkeys.h +++ b/include/linux/pkeys.h @@ -35,6 +35,10 @@ static inline int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, return 0; } +static inline void copy_init_pkru_to_fpregs(void) +{ +} + #endif /* ! CONFIG_ARCH_HAS_PKEYS */ #endif /* _LINUX_PKEYS_H */ -- cgit v1.2.3 From a545ab6a0085e6df9c7b6e9734b40ba4d2aca8c9 Mon Sep 17 00:00:00 2001 From: Luiz Capitulino Date: Wed, 7 Sep 2016 14:47:19 -0400 Subject: kvm: x86: add tsc_offset field to struct kvm_vcpu_arch A future commit will want to easily read a vCPU's TSC offset, so we store it in struct kvm_arch_vcpu_arch for easy access. Signed-off-by: Luiz Capitulino Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/x86.c | 10 ++++++++-- 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index cd82bf74e7a5..ddffcfbe155c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -568,6 +568,7 @@ struct kvm_vcpu_arch { struct kvm_steal_time steal; } st; + u64 tsc_offset; u64 last_guest_tsc; u64 last_host_tsc; u64 tsc_offset_adjustment; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 57ffe7893104..9a2cc696702a 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1413,6 +1413,12 @@ u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) } EXPORT_SYMBOL_GPL(kvm_read_l1_tsc); +static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) +{ + kvm_x86_ops->write_tsc_offset(vcpu, offset); + vcpu->arch.tsc_offset = offset; +} + void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) { struct kvm *kvm = vcpu->kvm; @@ -1522,7 +1528,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) if (guest_cpuid_has_tsc_adjust(vcpu) && !msr->host_initiated) update_ia32_tsc_adjust_msr(vcpu, offset); - kvm_x86_ops->write_tsc_offset(vcpu, offset); + kvm_vcpu_write_tsc_offset(vcpu, offset); raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); spin_lock(&kvm->arch.pvclock_gtod_sync_lock); @@ -2750,7 +2756,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (check_tsc_unstable()) { u64 offset = kvm_compute_tsc_offset(vcpu, vcpu->arch.last_guest_tsc); - kvm_x86_ops->write_tsc_offset(vcpu, offset); + kvm_vcpu_write_tsc_offset(vcpu, offset); vcpu->arch.tsc_catchup = 1; } /* -- cgit v1.2.3 From 3e3f50262eb441d0fd1de4dce06739e9c0fe7c61 Mon Sep 17 00:00:00 2001 From: Luiz Capitulino Date: Wed, 7 Sep 2016 14:47:20 -0400 Subject: kvm: x86: drop read_tsc_offset() The TSC offset can now be read directly from struct kvm_arch_vcpu. Signed-off-by: Luiz Capitulino Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 1 - arch/x86/kvm/svm.c | 8 -------- arch/x86/kvm/vmx.c | 6 ------ arch/x86/kvm/x86.c | 2 +- 4 files changed, 1 insertion(+), 16 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index ddffcfbe155c..32a43a25d415 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -954,7 +954,6 @@ struct kvm_x86_ops { bool (*has_wbinvd_exit)(void); - u64 (*read_tsc_offset)(struct kvm_vcpu *vcpu); void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); u64 (*read_l1_tsc)(struct kvm_vcpu *vcpu, u64 host_tsc); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index db77c1ca9e76..8023d5342586 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1119,13 +1119,6 @@ static void init_sys_seg(struct vmcb_seg *seg, uint32_t type) seg->base = 0; } -static u64 svm_read_tsc_offset(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - return svm->vmcb->control.tsc_offset; -} - static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) { struct vcpu_svm *svm = to_svm(vcpu); @@ -5427,7 +5420,6 @@ static struct kvm_x86_ops svm_x86_ops = { .has_wbinvd_exit = svm_has_wbinvd_exit, - .read_tsc_offset = svm_read_tsc_offset, .write_tsc_offset = svm_write_tsc_offset, .adjust_tsc_offset_guest = svm_adjust_tsc_offset_guest, .read_l1_tsc = svm_read_l1_tsc, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index f9939d0722b4..fe2b14445879 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2609,11 +2609,6 @@ static u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) return host_tsc + tsc_offset; } -static u64 vmx_read_tsc_offset(struct kvm_vcpu *vcpu) -{ - return vmcs_read64(TSC_OFFSET); -} - /* * writes 'offset' into guest's timestamp counter offset register */ @@ -11286,7 +11281,6 @@ static struct kvm_x86_ops vmx_x86_ops = { .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, - .read_tsc_offset = vmx_read_tsc_offset, .write_tsc_offset = vmx_write_tsc_offset, .adjust_tsc_offset_guest = vmx_adjust_tsc_offset_guest, .read_l1_tsc = vmx_read_l1_tsc, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 9a2cc696702a..b4ae92599d34 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1367,7 +1367,7 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset) { - u64 curr_offset = kvm_x86_ops->read_tsc_offset(vcpu); + u64 curr_offset = vcpu->arch.tsc_offset; vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset; } -- cgit v1.2.3 From 108b249c453dd7132599ab6dc7e435a7036c193f Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 1 Sep 2016 14:21:03 +0200 Subject: KVM: x86: introduce get_kvmclock_ns Introduce a function that reads the exact nanoseconds value that is provided to the guest in kvmclock. This crystallizes the notion of kvmclock as a thin veneer over a stable TSC, that the guest will (hopefully) convert with NTP. In other words, kvmclock is *not* a paravirtualized host-to-guest NTP. Drop the get_kernel_ns() function, that was used both to get the base value of the master clock and to get the current value of kvmclock. The former use is replaced by ktime_get_boot_ns(), the latter is the purpose of get_kernel_ns(). This also allows KVM to provide a Hyper-V time reference counter that is synchronized with the time that is computed from the TSC page. Reviewed-by: Roman Kagan Signed-off-by: Paolo Bonzini --- arch/x86/entry/vdso/vclock_gettime.c | 2 +- arch/x86/include/asm/pvclock.h | 5 ++-- arch/x86/kernel/pvclock.c | 2 +- arch/x86/kvm/hyperv.c | 2 +- arch/x86/kvm/x86.c | 48 +++++++++++++++++++++++++++--------- arch/x86/kvm/x86.h | 6 +---- 6 files changed, 43 insertions(+), 22 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index 94d54d0defa7..02223cb4bcfd 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -129,7 +129,7 @@ static notrace cycle_t vread_pvclock(int *mode) return 0; } - ret = __pvclock_read_cycles(pvti); + ret = __pvclock_read_cycles(pvti, rdtsc_ordered()); } while (pvclock_read_retry(pvti, version)); /* refer to vread_tsc() comment for rationale */ diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index d019f0cc80ec..3ad741b84072 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -87,9 +87,10 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift) } static __always_inline -cycle_t __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src) +cycle_t __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, + u64 tsc) { - u64 delta = rdtsc_ordered() - src->tsc_timestamp; + u64 delta = tsc - src->tsc_timestamp; cycle_t offset = pvclock_scale_delta(delta, src->tsc_to_system_mul, src->tsc_shift); return src->system_time + offset; diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 3599404e3089..5b2cc889ce34 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -80,7 +80,7 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) do { version = pvclock_read_begin(src); - ret = __pvclock_read_cycles(src); + ret = __pvclock_read_cycles(src, rdtsc_ordered()); flags = src->flags; } while (pvclock_read_retry(src, version)); diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 01bd7b7a6866..ed5b77f39ffb 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -386,7 +386,7 @@ static void synic_init(struct kvm_vcpu_hv_synic *synic) static u64 get_time_ref_counter(struct kvm *kvm) { - return div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100); + return div_u64(get_kvmclock_ns(kvm), 100); } static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 00e569c3ca71..81e9945cdf28 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1431,7 +1431,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); offset = kvm_compute_tsc_offset(vcpu, data); - ns = get_kernel_ns(); + ns = ktime_get_boot_ns(); elapsed = ns - kvm->arch.last_tsc_nsec; if (vcpu->arch.virtual_tsc_khz) { @@ -1722,6 +1722,34 @@ static void kvm_gen_update_masterclock(struct kvm *kvm) #endif } +static u64 __get_kvmclock_ns(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu = kvm_get_vcpu(kvm, 0); + struct kvm_arch *ka = &kvm->arch; + s64 ns; + + if (vcpu->arch.hv_clock.flags & PVCLOCK_TSC_STABLE_BIT) { + u64 tsc = kvm_read_l1_tsc(vcpu, rdtsc()); + ns = __pvclock_read_cycles(&vcpu->arch.hv_clock, tsc); + } else { + ns = ktime_get_boot_ns() + ka->kvmclock_offset; + } + + return ns; +} + +u64 get_kvmclock_ns(struct kvm *kvm) +{ + unsigned long flags; + s64 ns; + + local_irq_save(flags); + ns = __get_kvmclock_ns(kvm); + local_irq_restore(flags); + + return ns; +} + static void kvm_setup_pvclock_page(struct kvm_vcpu *v) { struct kvm_vcpu_arch *vcpu = &v->arch; @@ -1811,7 +1839,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) } if (!use_master_clock) { host_tsc = rdtsc(); - kernel_ns = get_kernel_ns(); + kernel_ns = ktime_get_boot_ns(); } tsc_timestamp = kvm_read_l1_tsc(v, host_tsc); @@ -4054,7 +4082,6 @@ long kvm_arch_vm_ioctl(struct file *filp, case KVM_SET_CLOCK: { struct kvm_clock_data user_ns; u64 now_ns; - s64 delta; r = -EFAULT; if (copy_from_user(&user_ns, argp, sizeof(user_ns))) @@ -4066,10 +4093,9 @@ long kvm_arch_vm_ioctl(struct file *filp, r = 0; local_irq_disable(); - now_ns = get_kernel_ns(); - delta = user_ns.clock - now_ns; + now_ns = __get_kvmclock_ns(kvm); + kvm->arch.kvmclock_offset += user_ns.clock - now_ns; local_irq_enable(); - kvm->arch.kvmclock_offset = delta; kvm_gen_update_masterclock(kvm); break; } @@ -4077,10 +4103,8 @@ long kvm_arch_vm_ioctl(struct file *filp, struct kvm_clock_data user_ns; u64 now_ns; - local_irq_disable(); - now_ns = get_kernel_ns(); - user_ns.clock = kvm->arch.kvmclock_offset + now_ns; - local_irq_enable(); + now_ns = get_kvmclock_ns(kvm); + user_ns.clock = now_ns; user_ns.flags = 0; memset(&user_ns.pad, 0, sizeof(user_ns.pad)); @@ -7544,7 +7568,7 @@ int kvm_arch_hardware_enable(void) * before any KVM threads can be running. Unfortunately, we can't * bring the TSCs fully up to date with real time, as we aren't yet far * enough into CPU bringup that we know how much real time has actually - * elapsed; our helper function, get_kernel_ns() will be using boot + * elapsed; our helper function, ktime_get_boot_ns() will be using boot * variables that haven't been updated yet. * * So we simply find the maximum observed TSC above, then record the @@ -7779,7 +7803,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) mutex_init(&kvm->arch.apic_map_lock); spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock); - kvm->arch.kvmclock_offset = -get_kernel_ns(); + kvm->arch.kvmclock_offset = -ktime_get_boot_ns(); pvclock_update_vm_gtod_copy(kvm); INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index a82ca466b62e..e8ff3e4ce38a 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -148,11 +148,6 @@ static inline void kvm_register_writel(struct kvm_vcpu *vcpu, return kvm_register_write(vcpu, reg, val); } -static inline u64 get_kernel_ns(void) -{ - return ktime_get_boot_ns(); -} - static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk) { return !(kvm->arch.disabled_quirks & quirk); @@ -164,6 +159,7 @@ void kvm_set_pending_timer(struct kvm_vcpu *vcpu); int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip); void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr); +u64 get_kvmclock_ns(struct kvm *kvm); int kvm_read_guest_virt(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val, unsigned int bytes, -- cgit v1.2.3 From 095cf55df715d14d5dad75326faf5984e7fc0b3a Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 8 Feb 2016 12:54:12 +0100 Subject: KVM: x86: Hyper-V tsc page setup MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Lately tsc page was implemented but filled with empty values. This patch setup tsc page scale and offset based on vcpu tsc, tsc_khz and HV_X64_MSR_TIME_REF_COUNT value. The valid tsc page drops HV_X64_MSR_TIME_REF_COUNT msr reads count to zero which potentially improves performance. Signed-off-by: Andrey Smetanin Reviewed-by: Peter Hornyack Reviewed-by: Radim Krčmář CC: Paolo Bonzini CC: Roman Kagan CC: Denis V. Lunev [Computation of TSC page parameters rewritten to use the Linux timekeeper parameters. - Paolo] Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 2 + arch/x86/kvm/hyperv.c | 157 ++++++++++++++++++++++++++++++++++++---- arch/x86/kvm/hyperv.h | 3 + arch/x86/kvm/x86.c | 8 +- 4 files changed, 150 insertions(+), 20 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 32a43a25d415..4b20f7304b9c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -702,6 +702,8 @@ struct kvm_hv { /* Hyper-v based guest crash (NT kernel bugcheck) parameters */ u64 hv_crash_param[HV_X64_MSR_CRASH_PARAMS]; u64 hv_crash_ctl; + + HV_REFERENCE_TSC_PAGE tsc_ref; }; struct kvm_arch { diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index ed5b77f39ffb..42b1c83741c8 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -386,7 +386,21 @@ static void synic_init(struct kvm_vcpu_hv_synic *synic) static u64 get_time_ref_counter(struct kvm *kvm) { - return div_u64(get_kvmclock_ns(kvm), 100); + struct kvm_hv *hv = &kvm->arch.hyperv; + struct kvm_vcpu *vcpu; + u64 tsc; + + /* + * The guest has not set up the TSC page or the clock isn't + * stable, fall back to get_kvmclock_ns. + */ + if (!hv->tsc_ref.tsc_sequence) + return div_u64(get_kvmclock_ns(kvm), 100); + + vcpu = kvm_get_vcpu(kvm, 0); + tsc = kvm_read_l1_tsc(vcpu, rdtsc()); + return mul_u64_u64_shr(tsc, hv->tsc_ref.tsc_scale, 64) + + hv->tsc_ref.tsc_offset; } static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer, @@ -756,6 +770,129 @@ static int kvm_hv_msr_set_crash_data(struct kvm_vcpu *vcpu, return 0; } +/* + * The kvmclock and Hyper-V TSC page use similar formulas, and converting + * between them is possible: + * + * kvmclock formula: + * nsec = (ticks - tsc_timestamp) * tsc_to_system_mul * 2^(tsc_shift-32) + * + system_time + * + * Hyper-V formula: + * nsec/100 = ticks * scale / 2^64 + offset + * + * When tsc_timestamp = system_time = 0, offset is zero in the Hyper-V formula. + * By dividing the kvmclock formula by 100 and equating what's left we get: + * ticks * scale / 2^64 = ticks * tsc_to_system_mul * 2^(tsc_shift-32) / 100 + * scale / 2^64 = tsc_to_system_mul * 2^(tsc_shift-32) / 100 + * scale = tsc_to_system_mul * 2^(32+tsc_shift) / 100 + * + * Now expand the kvmclock formula and divide by 100: + * nsec = ticks * tsc_to_system_mul * 2^(tsc_shift-32) + * - tsc_timestamp * tsc_to_system_mul * 2^(tsc_shift-32) + * + system_time + * nsec/100 = ticks * tsc_to_system_mul * 2^(tsc_shift-32) / 100 + * - tsc_timestamp * tsc_to_system_mul * 2^(tsc_shift-32) / 100 + * + system_time / 100 + * + * Replace tsc_to_system_mul * 2^(tsc_shift-32) / 100 by scale / 2^64: + * nsec/100 = ticks * scale / 2^64 + * - tsc_timestamp * scale / 2^64 + * + system_time / 100 + * + * Equate with the Hyper-V formula so that ticks * scale / 2^64 cancels out: + * offset = system_time / 100 - tsc_timestamp * scale / 2^64 + * + * These two equivalencies are implemented in this function. + */ +static bool compute_tsc_page_parameters(struct pvclock_vcpu_time_info *hv_clock, + HV_REFERENCE_TSC_PAGE *tsc_ref) +{ + u64 max_mul; + + if (!(hv_clock->flags & PVCLOCK_TSC_STABLE_BIT)) + return false; + + /* + * check if scale would overflow, if so we use the time ref counter + * tsc_to_system_mul * 2^(tsc_shift+32) / 100 >= 2^64 + * tsc_to_system_mul / 100 >= 2^(32-tsc_shift) + * tsc_to_system_mul >= 100 * 2^(32-tsc_shift) + */ + max_mul = 100ull << (32 - hv_clock->tsc_shift); + if (hv_clock->tsc_to_system_mul >= max_mul) + return false; + + /* + * Otherwise compute the scale and offset according to the formulas + * derived above. + */ + tsc_ref->tsc_scale = + mul_u64_u32_div(1ULL << (32 + hv_clock->tsc_shift), + hv_clock->tsc_to_system_mul, + 100); + + tsc_ref->tsc_offset = hv_clock->system_time; + do_div(tsc_ref->tsc_offset, 100); + tsc_ref->tsc_offset -= + mul_u64_u64_shr(hv_clock->tsc_timestamp, tsc_ref->tsc_scale, 64); + return true; +} + +void kvm_hv_setup_tsc_page(struct kvm *kvm, + struct pvclock_vcpu_time_info *hv_clock) +{ + struct kvm_hv *hv = &kvm->arch.hyperv; + u32 tsc_seq; + u64 gfn; + + BUILD_BUG_ON(sizeof(tsc_seq) != sizeof(hv->tsc_ref.tsc_sequence)); + BUILD_BUG_ON(offsetof(HV_REFERENCE_TSC_PAGE, tsc_sequence) != 0); + + if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE)) + return; + + gfn = hv->hv_tsc_page >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT; + /* + * Because the TSC parameters only vary when there is a + * change in the master clock, do not bother with caching. + */ + if (unlikely(kvm_read_guest(kvm, gfn_to_gpa(gfn), + &tsc_seq, sizeof(tsc_seq)))) + return; + + /* + * While we're computing and writing the parameters, force the + * guest to use the time reference count MSR. + */ + hv->tsc_ref.tsc_sequence = 0; + if (kvm_write_guest(kvm, gfn_to_gpa(gfn), + &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence))) + return; + + if (!compute_tsc_page_parameters(hv_clock, &hv->tsc_ref)) + return; + + /* Ensure sequence is zero before writing the rest of the struct. */ + smp_wmb(); + if (kvm_write_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref))) + return; + + /* + * Now switch to the TSC page mechanism by writing the sequence. + */ + tsc_seq++; + if (tsc_seq == 0xFFFFFFFF || tsc_seq == 0) + tsc_seq = 1; + + /* Write the struct entirely before the non-zero sequence. */ + smp_wmb(); + + hv->tsc_ref.tsc_sequence = tsc_seq; + kvm_write_guest(kvm, gfn_to_gpa(gfn), + &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence)); +} + static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) { @@ -793,23 +930,11 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, mark_page_dirty(kvm, gfn); break; } - case HV_X64_MSR_REFERENCE_TSC: { - u64 gfn; - HV_REFERENCE_TSC_PAGE tsc_ref; - - memset(&tsc_ref, 0, sizeof(tsc_ref)); + case HV_X64_MSR_REFERENCE_TSC: hv->hv_tsc_page = data; - if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE)) - break; - gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT; - if (kvm_write_guest( - kvm, - gfn << HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT, - &tsc_ref, sizeof(tsc_ref))) - return 1; - mark_page_dirty(kvm, gfn); + if (hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE) + kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); break; - } case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: return kvm_hv_msr_set_crash_data(vcpu, msr - HV_X64_MSR_CRASH_P0, diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index 60eccd4bd1d3..cd1119538add 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -84,4 +84,7 @@ static inline bool kvm_hv_has_stimer_pending(struct kvm_vcpu *vcpu) void kvm_hv_process_stimers(struct kvm_vcpu *vcpu); +void kvm_hv_setup_tsc_page(struct kvm *kvm, + struct pvclock_vcpu_time_info *hv_clock); + #endif diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 81e9945cdf28..3ee8a91a78c3 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1887,10 +1887,10 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) vcpu->hv_clock.flags = pvclock_flags; - if (!vcpu->pv_time_enabled) - return 0; - - kvm_setup_pvclock_page(v); + if (vcpu->pv_time_enabled) + kvm_setup_pvclock_page(v); + if (v == kvm_get_vcpu(v->kvm, 0)) + kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); return 0; } -- cgit v1.2.3 From 799bc3c51b2b120ca6e59e702ede23fff2efaf43 Mon Sep 17 00:00:00 2001 From: Lance Richardson Date: Thu, 22 Sep 2016 10:03:57 -0400 Subject: percpu: eliminate two sparse warnings Fix two cases where a __percpu pointer cast drops __percpu. Signed-off-by: Lance Richardson Signed-off-by: Tejun Heo --- arch/x86/include/asm/percpu.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index e02e3f80d363..84f58de08c2b 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -521,7 +521,8 @@ do { \ static __always_inline bool x86_this_cpu_constant_test_bit(unsigned int nr, const unsigned long __percpu *addr) { - unsigned long __percpu *a = (unsigned long *)addr + nr / BITS_PER_LONG; + unsigned long __percpu *a = + (unsigned long __percpu *)addr + nr / BITS_PER_LONG; #ifdef CONFIG_X86_64 return ((1UL << (nr % BITS_PER_LONG)) & raw_cpu_read_8(*a)) != 0; @@ -538,7 +539,7 @@ static inline bool x86_this_cpu_variable_test_bit(int nr, asm volatile("bt "__percpu_arg(2)",%1\n\t" CC_SET(c) : CC_OUT(c) (oldbit) - : "m" (*(unsigned long *)addr), "Ir" (nr)); + : "m" (*(unsigned long __percpu *)addr), "Ir" (nr)); return oldbit; } -- cgit v1.2.3 From 3161832d58c7f3bf8b190a2887086be0932d8dd3 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 13 Sep 2016 09:05:40 -0600 Subject: x86/PCI: VMD: Request userspace control of PCIe hotplug indicators Add set_dev_domain_options() to set PCI domain-specific options as devices are added. The first usage is to request exclusive userspace control of PCIe hotplug indicators in VMD domains. Devices in a VMD domain use PCIe hotplug Attention and Power Indicators in a non-standard way; tell pciehp to ignore the indicators so userspace can control them via the sysfs "attention" file. To determine whether a bus is within a VMD domain, add a bool to the pci_sysdata structure that the VMD driver sets during initialization. [bhelgaas: changelog] Requested-by: Kapil Karkra Tested-by: Artur Paszkiewicz Signed-off-by: Keith Busch Signed-off-by: Bjorn Helgaas --- arch/x86/include/asm/pci.h | 14 ++++++++++++++ arch/x86/pci/common.c | 7 +++++++ arch/x86/pci/vmd.c | 1 + 3 files changed, 22 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 9ab7507ca1c2..1411dbed5e5e 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -23,6 +23,9 @@ struct pci_sysdata { #ifdef CONFIG_PCI_MSI_IRQ_DOMAIN void *fwnode; /* IRQ domain for MSI assignment */ #endif +#if IS_ENABLED(CONFIG_VMD) + bool vmd_domain; /* True if in Intel VMD domain */ +#endif }; extern int pci_routeirq; @@ -56,6 +59,17 @@ static inline void *_pci_root_bus_fwnode(struct pci_bus *bus) #define pci_root_bus_fwnode _pci_root_bus_fwnode #endif +static inline bool is_vmd(struct pci_bus *bus) +{ +#if IS_ENABLED(CONFIG_VMD) + struct pci_sysdata *sd = bus->sysdata; + + return sd->vmd_domain; +#else + return false; +#endif +} + /* Can be used to override the logic in pci_scan_bus for skipping already-configured bus numbers - to be used for buggy BIOSes or architectures with incomplete PCI setup by the loader */ diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 7b6a9d14c8c0..a4fdfa7dcc1b 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -677,6 +677,12 @@ static void set_dma_domain_ops(struct pci_dev *pdev) static void set_dma_domain_ops(struct pci_dev *pdev) {} #endif +static void set_dev_domain_options(struct pci_dev *pdev) +{ + if (is_vmd(pdev->bus)) + pdev->hotplug_user_indicators = 1; +} + int pcibios_add_device(struct pci_dev *dev) { struct setup_data *data; @@ -707,6 +713,7 @@ int pcibios_add_device(struct pci_dev *dev) iounmap(data); } set_dma_domain_ops(dev); + set_dev_domain_options(dev); return 0; } diff --git a/arch/x86/pci/vmd.c b/arch/x86/pci/vmd.c index b814ca675131..a021b7b0eb69 100644 --- a/arch/x86/pci/vmd.c +++ b/arch/x86/pci/vmd.c @@ -596,6 +596,7 @@ static int vmd_enable_domain(struct vmd_dev *vmd) .parent = res, }; + sd->vmd_domain = true; sd->domain = vmd_find_free_domain(); if (sd->domain < 0) return sd->domain; -- cgit v1.2.3 From b79d8d82bb994fe6154ea1a8e56d587ef9e356ae Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 5 Sep 2016 11:27:55 -0400 Subject: remove stray include of asm/uaccess.h from cacheflush.h It was introduced in "arch, x86: pmem api for ensuring durability of persistent memory updates" in July 2015, along with the code that really used that stuff. Three weeks later all that code got moved to asm/pmem.h by "pmem, x86: move x86 PMEM API to new pmem.h header"; include, however, was left behind. Signed-off-by: Al Viro --- arch/x86/include/asm/cacheflush.h | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h index 61518cf79437..872877d930de 100644 --- a/arch/x86/include/asm/cacheflush.h +++ b/arch/x86/include/asm/cacheflush.h @@ -4,7 +4,6 @@ /* Caches aren't brain-dead on the intel. */ #include #include -#include /* * The set_memory_* API can be used to change various attributes of a virtual -- cgit v1.2.3 From 45caf470077ae6b02da6d5eaee94003ee1543ca3 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 5 Sep 2016 11:32:44 -0400 Subject: x86: separate extable.h, switch sections.h to it drivers/platform/x86/dell-smo8800.c is touched due to the following obscenity: drivers/platform/x86/dell-smo8800.c -> linux/interrupt.h -> linux/hardirq.h -> asm/hardirq.h -> linux/irq.h -> asm/hw_irq.h -> asm/sections.h -> asm/uaccess.h is the only chain of includes pulling asm/uaccess.h there. Signed-off-by: Al Viro --- arch/x86/include/asm/extable.h | 35 +++++++++++++++++++++++++++++++++++ arch/x86/include/asm/sections.h | 2 +- arch/x86/include/asm/uaccess.h | 32 +------------------------------- drivers/platform/x86/dell-smo8800.c | 1 + 4 files changed, 38 insertions(+), 32 deletions(-) create mode 100644 arch/x86/include/asm/extable.h (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/extable.h b/arch/x86/include/asm/extable.h new file mode 100644 index 000000000000..b8ad261d11dc --- /dev/null +++ b/arch/x86/include/asm/extable.h @@ -0,0 +1,35 @@ +#ifndef _ASM_X86_EXTABLE_H +#define _ASM_X86_EXTABLE_H +/* + * The exception table consists of triples of addresses relative to the + * exception table entry itself. The first address is of an instruction + * that is allowed to fault, the second is the target at which the program + * should continue. The third is a handler function to deal with the fault + * caused by the instruction in the first field. + * + * All the routines below use bits of fixup code that are out of line + * with the main instruction path. This means when everything is well, + * we don't even have to jump over them. Further, they do not intrude + * on our cache or tlb entries. + */ + +struct exception_table_entry { + int insn, fixup, handler; +}; +struct pt_regs; + +#define ARCH_HAS_RELATIVE_EXTABLE + +#define swap_ex_entry_fixup(a, b, tmp, delta) \ + do { \ + (a)->fixup = (b)->fixup + (delta); \ + (b)->fixup = (tmp).fixup - (delta); \ + (a)->handler = (b)->handler + (delta); \ + (b)->handler = (tmp).handler - (delta); \ + } while (0) + +extern int fixup_exception(struct pt_regs *regs, int trapnr); +extern bool ex_has_fault_handler(unsigned long ip); +extern void early_fixup_exception(struct pt_regs *regs, int trapnr); + +#endif diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h index 13b6cdd0af57..2f75f30cb2f6 100644 --- a/arch/x86/include/asm/sections.h +++ b/arch/x86/include/asm/sections.h @@ -2,7 +2,7 @@ #define _ASM_X86_SECTIONS_H #include -#include +#include extern char __brk_base[], __brk_limit[]; extern struct exception_table_entry __stop___ex_table[]; diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 2131c4ce7d8a..faf3687f1035 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -11,6 +11,7 @@ #include #include #include +#include #define VERIFY_READ 0 #define VERIFY_WRITE 1 @@ -90,37 +91,6 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un #define access_ok(type, addr, size) \ likely(!__range_not_ok(addr, size, user_addr_max())) -/* - * The exception table consists of triples of addresses relative to the - * exception table entry itself. The first address is of an instruction - * that is allowed to fault, the second is the target at which the program - * should continue. The third is a handler function to deal with the fault - * caused by the instruction in the first field. - * - * All the routines below use bits of fixup code that are out of line - * with the main instruction path. This means when everything is well, - * we don't even have to jump over them. Further, they do not intrude - * on our cache or tlb entries. - */ - -struct exception_table_entry { - int insn, fixup, handler; -}; - -#define ARCH_HAS_RELATIVE_EXTABLE - -#define swap_ex_entry_fixup(a, b, tmp, delta) \ - do { \ - (a)->fixup = (b)->fixup + (delta); \ - (b)->fixup = (tmp).fixup - (delta); \ - (a)->handler = (b)->handler + (delta); \ - (b)->handler = (tmp).handler - (delta); \ - } while (0) - -extern int fixup_exception(struct pt_regs *regs, int trapnr); -extern bool ex_has_fault_handler(unsigned long ip); -extern void early_fixup_exception(struct pt_regs *regs, int trapnr); - /* * These are the main single-value transfer routines. They automatically * use the right size if we just have the right pointer type. diff --git a/drivers/platform/x86/dell-smo8800.c b/drivers/platform/x86/dell-smo8800.c index 0aec4fd4c48e..37e646034ef8 100644 --- a/drivers/platform/x86/dell-smo8800.c +++ b/drivers/platform/x86/dell-smo8800.c @@ -24,6 +24,7 @@ #include #include #include +#include struct smo8800_device { u32 irq; /* acpi device irq */ -- cgit v1.2.3 From 72a9b186292d98494f222226cfd24a1621796209 Mon Sep 17 00:00:00 2001 From: KarimAllah Ahmed Date: Fri, 26 Aug 2016 23:55:36 +0200 Subject: xen: Remove event channel notification through Xen PCI platform device Ever since commit 254d1a3f02eb ("xen/pv-on-hvm kexec: shutdown watches from old kernel") using the INTx interrupt from Xen PCI platform device for event channel notification would just lockup the guest during bootup. postcore_initcall now calls xs_reset_watches which will eventually try to read a value from XenStore and will get stuck on read_reply at XenBus forever since the platform driver is not probed yet and its INTx interrupt handler is not registered yet. That means that the guest can not be notified at this moment of any pending event channels and none of the per-event handlers will ever be invoked (including the XenStore one) and the reply will never be picked up by the kernel. The exact stack where things get stuck during xenbus_init: -xenbus_init -xs_init -xs_reset_watches -xenbus_scanf -xenbus_read -xs_single -xs_single -xs_talkv Vector callbacks have always been the favourite event notification mechanism since their introduction in commit 38e20b07efd5 ("x86/xen: event channels delivery on HVM.") and the vector callback feature has always been advertised for quite some time by Xen that's why INTx was broken for several years now without impacting anyone. Luckily this also means that event channel notification through INTx is basically dead-code which can be safely removed without impacting anybody since it has been effectively disabled for more than 4 years with nobody complaining about it (at least as far as I'm aware of). This commit removes event channel notification through Xen PCI platform device. Cc: Boris Ostrovsky Cc: David Vrabel Cc: Juergen Gross Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: x86@kernel.org Cc: Konrad Rzeszutek Wilk Cc: Bjorn Helgaas Cc: Stefano Stabellini Cc: Julien Grall Cc: Vitaly Kuznetsov Cc: Paul Gortmaker Cc: Ross Lagerwall Cc: xen-devel@lists.xenproject.org Cc: linux-kernel@vger.kernel.org Cc: linux-pci@vger.kernel.org Cc: Anthony Liguori Signed-off-by: KarimAllah Ahmed Reviewed-by: Boris Ostrovsky Signed-off-by: David Vrabel --- arch/x86/include/asm/xen/events.h | 11 ------- arch/x86/pci/xen.c | 2 +- arch/x86/xen/enlighten.c | 21 ++++--------- arch/x86/xen/smp.c | 2 -- arch/x86/xen/time.c | 5 --- drivers/xen/events/events_base.c | 26 ++++++---------- drivers/xen/platform-pci.c | 64 --------------------------------------- include/xen/xen.h | 3 +- 8 files changed, 17 insertions(+), 117 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h index e6911caf5bbf..608a79d5a466 100644 --- a/arch/x86/include/asm/xen/events.h +++ b/arch/x86/include/asm/xen/events.h @@ -20,15 +20,4 @@ static inline int xen_irqs_disabled(struct pt_regs *regs) /* No need for a barrier -- XCHG is a barrier on x86. */ #define xchg_xen_ulong(ptr, val) xchg((ptr), (val)) -extern int xen_have_vector_callback; - -/* - * Events delivered via platform PCI interrupts are always - * routed to vcpu 0 and hence cannot be rebound. - */ -static inline bool xen_support_evtchn_rebind(void) -{ - return (!xen_hvm_domain() || xen_have_vector_callback); -} - #endif /* _ASM_X86_XEN_EVENTS_H */ diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 3a483cb5ac81..bedfab98077a 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -456,7 +456,7 @@ void __init xen_msi_init(void) int __init pci_xen_hvm_init(void) { - if (!xen_have_vector_callback || !xen_feature(XENFEAT_hvm_pirqs)) + if (!xen_feature(XENFEAT_hvm_pirqs)) return 0; #ifdef CONFIG_ACPI diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index a9ba14ac3aea..366b6aed4a8e 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -137,8 +137,6 @@ struct shared_info xen_dummy_shared_info; void *xen_initial_gdt; RESERVE_BRK(shared_info_page_brk, PAGE_SIZE); -__read_mostly int xen_have_vector_callback; -EXPORT_SYMBOL_GPL(xen_have_vector_callback); static int xen_cpu_up_prepare(unsigned int cpu); static int xen_cpu_up_online(unsigned int cpu); @@ -1524,10 +1522,7 @@ static void __init xen_pvh_early_guest_init(void) if (!xen_feature(XENFEAT_auto_translated_physmap)) return; - if (!xen_feature(XENFEAT_hvm_callback_vector)) - return; - - xen_have_vector_callback = 1; + BUG_ON(!xen_feature(XENFEAT_hvm_callback_vector)); xen_pvh_early_cpu_init(0, false); xen_pvh_set_cr_flags(0); @@ -1864,9 +1859,7 @@ static int xen_cpu_up_prepare(unsigned int cpu) xen_vcpu_setup(cpu); } - if (xen_pv_domain() || - (xen_have_vector_callback && - xen_feature(XENFEAT_hvm_safe_pvclock))) + if (xen_pv_domain() || xen_feature(XENFEAT_hvm_safe_pvclock)) xen_setup_timer(cpu); rc = xen_smp_intr_init(cpu); @@ -1882,9 +1875,7 @@ static int xen_cpu_dead(unsigned int cpu) { xen_smp_intr_free(cpu); - if (xen_pv_domain() || - (xen_have_vector_callback && - xen_feature(XENFEAT_hvm_safe_pvclock))) + if (xen_pv_domain() || xen_feature(XENFEAT_hvm_safe_pvclock)) xen_teardown_timer(cpu); return 0; @@ -1922,8 +1913,8 @@ static void __init xen_hvm_guest_init(void) xen_panic_handler_init(); - if (xen_feature(XENFEAT_hvm_callback_vector)) - xen_have_vector_callback = 1; + BUG_ON(!xen_feature(XENFEAT_hvm_callback_vector)); + xen_hvm_smp_init(); WARN_ON(xen_cpuhp_setup()); xen_unplug_emulated_devices(); @@ -1961,7 +1952,7 @@ bool xen_hvm_need_lapic(void) return false; if (!xen_hvm_domain()) return false; - if (xen_feature(XENFEAT_hvm_pirqs) && xen_have_vector_callback) + if (xen_feature(XENFEAT_hvm_pirqs)) return false; return true; } diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 137afbbd0590..311acad7dad2 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -765,8 +765,6 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) void __init xen_hvm_smp_init(void) { - if (!xen_have_vector_callback) - return; smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus; smp_ops.smp_send_reschedule = xen_smp_send_reschedule; smp_ops.cpu_die = xen_cpu_die; diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 67356d29d74d..33d8f6a7829d 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -432,11 +432,6 @@ static void xen_hvm_setup_cpu_clockevents(void) void __init xen_hvm_init_time_ops(void) { - /* vector callback is needed otherwise we cannot receive interrupts - * on cpu > 0 and at this point we don't know how many cpus are - * available */ - if (!xen_have_vector_callback) - return; if (!xen_feature(XENFEAT_hvm_safe_pvclock)) { printk(KERN_INFO "Xen doesn't support pvclock on HVM," "disable pv timer\n"); diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index d5dbdb9d24d8..9ecfcdcdd6d6 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -1314,9 +1314,6 @@ static int rebind_irq_to_cpu(unsigned irq, unsigned tcpu) if (!VALID_EVTCHN(evtchn)) return -1; - if (!xen_support_evtchn_rebind()) - return -1; - /* Send future instances of this interrupt to other vcpu. */ bind_vcpu.port = evtchn; bind_vcpu.vcpu = xen_vcpu_nr(tcpu); @@ -1650,20 +1647,15 @@ void xen_callback_vector(void) { int rc; uint64_t callback_via; - if (xen_have_vector_callback) { - callback_via = HVM_CALLBACK_VECTOR(HYPERVISOR_CALLBACK_VECTOR); - rc = xen_set_callback_via(callback_via); - if (rc) { - pr_err("Request for Xen HVM callback vector failed\n"); - xen_have_vector_callback = 0; - return; - } - pr_info("Xen HVM callback vector for event delivery is enabled\n"); - /* in the restore case the vector has already been allocated */ - if (!test_bit(HYPERVISOR_CALLBACK_VECTOR, used_vectors)) - alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, - xen_hvm_callback_vector); - } + + callback_via = HVM_CALLBACK_VECTOR(HYPERVISOR_CALLBACK_VECTOR); + rc = xen_set_callback_via(callback_via); + BUG_ON(rc); + pr_info("Xen HVM callback vector for event delivery is enabled\n"); + /* in the restore case the vector has already been allocated */ + if (!test_bit(HYPERVISOR_CALLBACK_VECTOR, used_vectors)) + alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, + xen_hvm_callback_vector); } #else void xen_callback_vector(void) {} diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c index cf9666680c8c..b59c9455aae1 100644 --- a/drivers/xen/platform-pci.c +++ b/drivers/xen/platform-pci.c @@ -42,7 +42,6 @@ static unsigned long platform_mmio; static unsigned long platform_mmio_alloc; static unsigned long platform_mmiolen; -static uint64_t callback_via; static unsigned long alloc_xen_mmio(unsigned long len) { @@ -55,51 +54,6 @@ static unsigned long alloc_xen_mmio(unsigned long len) return addr; } -static uint64_t get_callback_via(struct pci_dev *pdev) -{ - u8 pin; - int irq; - - irq = pdev->irq; - if (irq < 16) - return irq; /* ISA IRQ */ - - pin = pdev->pin; - - /* We don't know the GSI. Specify the PCI INTx line instead. */ - return ((uint64_t)0x01 << 56) | /* PCI INTx identifier */ - ((uint64_t)pci_domain_nr(pdev->bus) << 32) | - ((uint64_t)pdev->bus->number << 16) | - ((uint64_t)(pdev->devfn & 0xff) << 8) | - ((uint64_t)(pin - 1) & 3); -} - -static irqreturn_t do_hvm_evtchn_intr(int irq, void *dev_id) -{ - xen_hvm_evtchn_do_upcall(); - return IRQ_HANDLED; -} - -static int xen_allocate_irq(struct pci_dev *pdev) -{ - return request_irq(pdev->irq, do_hvm_evtchn_intr, - IRQF_NOBALANCING | IRQF_TRIGGER_RISING, - "xen-platform-pci", pdev); -} - -static int platform_pci_resume(struct pci_dev *pdev) -{ - int err; - if (xen_have_vector_callback) - return 0; - err = xen_set_callback_via(callback_via); - if (err) { - dev_err(&pdev->dev, "platform_pci_resume failure!\n"); - return err; - } - return 0; -} - static int platform_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { @@ -138,21 +92,6 @@ static int platform_pci_probe(struct pci_dev *pdev, platform_mmio = mmio_addr; platform_mmiolen = mmio_len; - if (!xen_have_vector_callback) { - ret = xen_allocate_irq(pdev); - if (ret) { - dev_warn(&pdev->dev, "request_irq failed err=%d\n", ret); - goto out; - } - callback_via = get_callback_via(pdev); - ret = xen_set_callback_via(callback_via); - if (ret) { - dev_warn(&pdev->dev, "Unable to set the evtchn callback " - "err=%d\n", ret); - goto out; - } - } - max_nr_gframes = gnttab_max_grant_frames(); grant_frames = alloc_xen_mmio(PAGE_SIZE * max_nr_gframes); ret = gnttab_setup_auto_xlat_frames(grant_frames); @@ -184,9 +123,6 @@ static struct pci_driver platform_driver = { .name = DRV_NAME, .probe = platform_pci_probe, .id_table = platform_pci_tbl, -#ifdef CONFIG_PM - .resume_early = platform_pci_resume, -#endif }; static int __init platform_pci_init(void) diff --git a/include/xen/xen.h b/include/xen/xen.h index 0c0e3ef4c45d..f0f0252cff9a 100644 --- a/include/xen/xen.h +++ b/include/xen/xen.h @@ -38,8 +38,7 @@ extern enum xen_domain_type xen_domain_type; */ #include #define xen_pvh_domain() (xen_pv_domain() && \ - xen_feature(XENFEAT_auto_translated_physmap) && \ - xen_have_vector_callback) + xen_feature(XENFEAT_auto_translated_physmap)) #else #define xen_pvh_domain() (0) #endif -- cgit v1.2.3 From 08ea8c07fb56d6eb8194d8ad408b469544bf2c29 Mon Sep 17 00:00:00 2001 From: Baoyou Xie Date: Fri, 7 Oct 2016 17:00:55 -0700 Subject: mm: move phys_mem_access_prot_allowed() declaration to pgtable.h We get 1 warning when building kernel with W=1: drivers/char/mem.c:220:12: warning: no previous prototype for 'phys_mem_access_prot_allowed' [-Wmissing-prototypes] int __weak phys_mem_access_prot_allowed(struct file *file, In fact, its declaration is spreading to several header files in different architecture, but need to be declare in common header file. So this patch moves phys_mem_access_prot_allowed() to pgtable.h. Link: http://lkml.kernel.org/r/1473751597-12139-1-git-send-email-baoyou.xie@linaro.org Signed-off-by: Baoyou Xie Acked-by: Thomas Gleixner Acked-by: Ralf Baechle Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/mips/include/asm/pgtable.h | 2 -- arch/x86/include/asm/pgtable_types.h | 2 -- include/asm-generic/pgtable.h | 3 +++ 3 files changed, 3 insertions(+), 4 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 70128d3f770a..9e9e94415d08 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -673,8 +673,6 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, struct file; pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot); -int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, - unsigned long size, pgprot_t *vma_prot); #endif /* diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index f1218f512f62..8b4de22d6429 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -439,8 +439,6 @@ extern pgprot_t pgprot_writethrough(pgprot_t prot); struct file; pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot); -int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, - unsigned long size, pgprot_t *vma_prot); /* Install a pte for a particular vaddr in kernel space. */ void set_pte_vaddr(unsigned long vaddr, pte_t pte); diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index d4458b6dbfb4..c4f8fd2fd384 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -800,6 +800,9 @@ static inline int pmd_clear_huge(pmd_t *pmd) #endif #endif +struct file; +int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t *vma_prot); #endif /* !__ASSEMBLY__ */ #ifndef io_remap_pfn_range -- cgit v1.2.3 From 9a01c3ed5cdb35d9004eb92510ee6ea11b4a5f16 Mon Sep 17 00:00:00 2001 From: Chris Metcalf Date: Fri, 7 Oct 2016 17:02:45 -0700 Subject: nmi_backtrace: add more trigger_*_cpu_backtrace() methods Patch series "improvements to the nmi_backtrace code" v9. This patch series modifies the trigger_xxx_backtrace() NMI-based remote backtracing code to make it more flexible, and makes a few small improvements along the way. The motivation comes from the task isolation code, where there are scenarios where we want to be able to diagnose a case where some cpu is about to interrupt a task-isolated cpu. It can be helpful to see both where the interrupting cpu is, and also an approximation of where the cpu that is being interrupted is. The nmi_backtrace framework allows us to discover the stack of the interrupted cpu. I've tested that the change works as desired on tile, and build-tested x86, arm, mips, and sparc64. For x86 I confirmed that the generic cpuidle stuff as well as the architecture-specific routines are in the new cpuidle section. For arm, mips, and sparc I just build-tested it and made sure the generic cpuidle routines were in the new cpuidle section, but I didn't attempt to figure out which the platform-specific idle routines might be. That might be more usefully done by someone with platform experience in follow-up patches. This patch (of 4): Currently you can only request a backtrace of either all cpus, or all cpus but yourself. It can also be helpful to request a remote backtrace of a single cpu, and since we want that, the logical extension is to support a cpumask as the underlying primitive. This change modifies the existing lib/nmi_backtrace.c code to take a cpumask as its basic primitive, and modifies the linux/nmi.h code to use the new "cpumask" method instead. The existing clients of nmi_backtrace (arm and x86) are converted to using the new cpumask approach in this change. The other users of the backtracing API (sparc64 and mips) are converted to use the cpumask approach rather than the all/allbutself approach. The mips code ignored the "include_self" boolean but with this change it will now also dump a local backtrace if requested. Link: http://lkml.kernel.org/r/1472487169-14923-2-git-send-email-cmetcalf@mellanox.com Signed-off-by: Chris Metcalf Tested-by: Daniel Thompson [arm] Reviewed-by: Aaron Tomlin Reviewed-by: Petr Mladek Cc: "Rafael J. Wysocki" Cc: Russell King Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Ralf Baechle Cc: David Miller Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/include/asm/irq.h | 5 +++-- arch/arm/kernel/smp.c | 4 ++-- arch/mips/include/asm/irq.h | 5 +++-- arch/mips/kernel/process.c | 11 +++++++++-- arch/sparc/include/asm/irq_64.h | 5 +++-- arch/sparc/kernel/process_64.c | 10 +++++----- arch/x86/include/asm/irq.h | 5 +++-- arch/x86/kernel/apic/hw_nmi.c | 18 +++++++++--------- include/linux/nmi.h | 31 ++++++++++++++++++++++++++----- lib/nmi_backtrace.c | 17 +++++++++-------- 10 files changed, 72 insertions(+), 39 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h index 1bd9510de1b9..e53638c8ed8a 100644 --- a/arch/arm/include/asm/irq.h +++ b/arch/arm/include/asm/irq.h @@ -36,8 +36,9 @@ extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); #endif #ifdef CONFIG_SMP -extern void arch_trigger_all_cpu_backtrace(bool); -#define arch_trigger_all_cpu_backtrace(x) arch_trigger_all_cpu_backtrace(x) +extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask, + bool exclude_self); +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace #endif static inline int nr_legacy_irqs(void) diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 937c8920d741..5abc5697e4e5 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -760,7 +760,7 @@ static void raise_nmi(cpumask_t *mask) smp_cross_call(mask, IPI_CPU_BACKTRACE); } -void arch_trigger_all_cpu_backtrace(bool include_self) +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) { - nmi_trigger_all_cpu_backtrace(include_self, raise_nmi); + nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_nmi); } diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h index 15e0fecbc300..6bf10e796553 100644 --- a/arch/mips/include/asm/irq.h +++ b/arch/mips/include/asm/irq.h @@ -51,7 +51,8 @@ extern int cp0_fdc_irq; extern int get_c0_fdc_int(void); -void arch_trigger_all_cpu_backtrace(bool); -#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace +void arch_trigger_cpumask_backtrace(const struct cpumask *mask, + bool exclude_self); +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace #endif /* _ASM_IRQ_H */ diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index d2d061520a23..9514e5f2209f 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -569,9 +569,16 @@ static void arch_dump_stack(void *info) dump_stack(); } -void arch_trigger_all_cpu_backtrace(bool include_self) +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) { - smp_call_function(arch_dump_stack, NULL, 1); + long this_cpu = get_cpu(); + + if (cpumask_test_cpu(this_cpu, mask) && !exclude_self) + dump_stack(); + + smp_call_function_many(mask, arch_dump_stack, NULL, 1); + + put_cpu(); } int mips_get_process_fp_mode(struct task_struct *task) diff --git a/arch/sparc/include/asm/irq_64.h b/arch/sparc/include/asm/irq_64.h index 3f70f900e834..1d51a11fb261 100644 --- a/arch/sparc/include/asm/irq_64.h +++ b/arch/sparc/include/asm/irq_64.h @@ -86,8 +86,9 @@ static inline unsigned long get_softint(void) return retval; } -void arch_trigger_all_cpu_backtrace(bool); -#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace +void arch_trigger_cpumask_backtrace(const struct cpumask *mask, + bool exclude_self); +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace extern void *hardirq_stack[NR_CPUS]; extern void *softirq_stack[NR_CPUS]; diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index fa14402b33f9..47ff5588e521 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -239,7 +239,7 @@ static void __global_reg_poll(struct global_reg_snapshot *gp) } } -void arch_trigger_all_cpu_backtrace(bool include_self) +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) { struct thread_info *tp = current_thread_info(); struct pt_regs *regs = get_irq_regs(); @@ -255,15 +255,15 @@ void arch_trigger_all_cpu_backtrace(bool include_self) memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot)); - if (include_self) + if (cpumask_test_cpu(this_cpu, mask) && !exclude_self) __global_reg_self(tp, regs, this_cpu); smp_fetch_global_regs(); - for_each_online_cpu(cpu) { + for_each_cpu(cpu, mask) { struct global_reg_snapshot *gp; - if (!include_self && cpu == this_cpu) + if (exclude_self && cpu == this_cpu) continue; gp = &global_cpu_snapshot[cpu].reg; @@ -300,7 +300,7 @@ void arch_trigger_all_cpu_backtrace(bool include_self) static void sysrq_handle_globreg(int key) { - arch_trigger_all_cpu_backtrace(true); + trigger_all_cpu_backtrace(); } static struct sysrq_key_op sparc_globalreg_op = { diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index e7de5c9a4fbd..16d3fa211962 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -50,8 +50,9 @@ extern int vector_used_by_percpu_irq(unsigned int vector); extern void init_ISA_irqs(void); #ifdef CONFIG_X86_LOCAL_APIC -void arch_trigger_all_cpu_backtrace(bool); -#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace +void arch_trigger_cpumask_backtrace(const struct cpumask *mask, + bool exclude_self); +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace #endif #endif /* _ASM_X86_IRQ_H */ diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index f29501e1a5c1..c73c9fb281e1 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -26,32 +26,32 @@ u64 hw_nmi_get_sample_period(int watchdog_thresh) } #endif -#ifdef arch_trigger_all_cpu_backtrace +#ifdef arch_trigger_cpumask_backtrace static void nmi_raise_cpu_backtrace(cpumask_t *mask) { apic->send_IPI_mask(mask, NMI_VECTOR); } -void arch_trigger_all_cpu_backtrace(bool include_self) +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) { - nmi_trigger_all_cpu_backtrace(include_self, nmi_raise_cpu_backtrace); + nmi_trigger_cpumask_backtrace(mask, exclude_self, + nmi_raise_cpu_backtrace); } -static int -arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs) +static int nmi_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs) { if (nmi_cpu_backtrace(regs)) return NMI_HANDLED; return NMI_DONE; } -NOKPROBE_SYMBOL(arch_trigger_all_cpu_backtrace_handler); +NOKPROBE_SYMBOL(nmi_cpu_backtrace_handler); -static int __init register_trigger_all_cpu_backtrace(void) +static int __init register_nmi_cpu_backtrace_handler(void) { - register_nmi_handler(NMI_LOCAL, arch_trigger_all_cpu_backtrace_handler, + register_nmi_handler(NMI_LOCAL, nmi_cpu_backtrace_handler, 0, "arch_bt"); return 0; } -early_initcall(register_trigger_all_cpu_backtrace); +early_initcall(register_nmi_cpu_backtrace_handler); #endif diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 4630eeae18e0..a78c35cff1ae 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -35,21 +35,34 @@ static inline void hardlockup_detector_disable(void) {} * base function. Return whether such support was available, * to allow calling code to fall back to some other mechanism: */ -#ifdef arch_trigger_all_cpu_backtrace +#ifdef arch_trigger_cpumask_backtrace static inline bool trigger_all_cpu_backtrace(void) { - arch_trigger_all_cpu_backtrace(true); - + arch_trigger_cpumask_backtrace(cpu_online_mask, false); return true; } + static inline bool trigger_allbutself_cpu_backtrace(void) { - arch_trigger_all_cpu_backtrace(false); + arch_trigger_cpumask_backtrace(cpu_online_mask, true); + return true; +} + +static inline bool trigger_cpumask_backtrace(struct cpumask *mask) +{ + arch_trigger_cpumask_backtrace(mask, false); + return true; +} + +static inline bool trigger_single_cpu_backtrace(int cpu) +{ + arch_trigger_cpumask_backtrace(cpumask_of(cpu), false); return true; } /* generic implementation */ -void nmi_trigger_all_cpu_backtrace(bool include_self, +void nmi_trigger_cpumask_backtrace(const cpumask_t *mask, + bool exclude_self, void (*raise)(cpumask_t *mask)); bool nmi_cpu_backtrace(struct pt_regs *regs); @@ -62,6 +75,14 @@ static inline bool trigger_allbutself_cpu_backtrace(void) { return false; } +static inline bool trigger_cpumask_backtrace(struct cpumask *mask) +{ + return false; +} +static inline bool trigger_single_cpu_backtrace(int cpu) +{ + return false; +} #endif #ifdef CONFIG_LOCKUP_DETECTOR diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c index 26caf51cc238..df347e355267 100644 --- a/lib/nmi_backtrace.c +++ b/lib/nmi_backtrace.c @@ -17,20 +17,21 @@ #include #include -#ifdef arch_trigger_all_cpu_backtrace +#ifdef arch_trigger_cpumask_backtrace /* For reliability, we're prepared to waste bits here. */ static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; -/* "in progress" flag of arch_trigger_all_cpu_backtrace */ +/* "in progress" flag of arch_trigger_cpumask_backtrace */ static unsigned long backtrace_flag; /* - * When raise() is called it will be is passed a pointer to the + * When raise() is called it will be passed a pointer to the * backtrace_mask. Architectures that call nmi_cpu_backtrace() * directly from their raise() functions may rely on the mask * they are passed being updated as a side effect of this call. */ -void nmi_trigger_all_cpu_backtrace(bool include_self, +void nmi_trigger_cpumask_backtrace(const cpumask_t *mask, + bool exclude_self, void (*raise)(cpumask_t *mask)) { int i, this_cpu = get_cpu(); @@ -44,13 +45,13 @@ void nmi_trigger_all_cpu_backtrace(bool include_self, return; } - cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask); - if (!include_self) + cpumask_copy(to_cpumask(backtrace_mask), mask); + if (exclude_self) cpumask_clear_cpu(this_cpu, to_cpumask(backtrace_mask)); if (!cpumask_empty(to_cpumask(backtrace_mask))) { - pr_info("Sending NMI to %s CPUs:\n", - (include_self ? "all" : "other")); + pr_info("Sending NMI from CPU %d to CPUs %*pbl:\n", + this_cpu, nr_cpumask_bits, to_cpumask(backtrace_mask)); raise(to_cpumask(backtrace_mask)); } -- cgit v1.2.3 From 6727ad9e206cc08b80d8000a4d67f8417e53539d Mon Sep 17 00:00:00 2001 From: Chris Metcalf Date: Fri, 7 Oct 2016 17:02:55 -0700 Subject: nmi_backtrace: generate one-line reports for idle cpus When doing an nmi backtrace of many cores, most of which are idle, the output is a little overwhelming and very uninformative. Suppress messages for cpus that are idling when they are interrupted and just emit one line, "NMI backtrace for N skipped: idling at pc 0xNNN". We do this by grouping all the cpuidle code together into a new .cpuidle.text section, and then checking the address of the interrupted PC to see if it lies within that section. This commit suitably tags x86 and tile idle routines, and only adds in the minimal framework for other architectures. Link: http://lkml.kernel.org/r/1472487169-14923-5-git-send-email-cmetcalf@mellanox.com Signed-off-by: Chris Metcalf Acked-by: Peter Zijlstra (Intel) Tested-by: Peter Zijlstra (Intel) Tested-by: Daniel Thompson [arm] Tested-by: Petr Mladek Cc: Aaron Tomlin Cc: Peter Zijlstra (Intel) Cc: "Rafael J. Wysocki" Cc: Russell King Cc: Thomas Gleixner Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/kernel/vmlinux.lds.S | 1 + arch/arc/kernel/vmlinux.lds.S | 1 + arch/arm/kernel/vmlinux-xip.lds.S | 1 + arch/arm/kernel/vmlinux.lds.S | 1 + arch/arm64/kernel/vmlinux.lds.S | 1 + arch/avr32/kernel/vmlinux.lds.S | 1 + arch/blackfin/kernel/vmlinux.lds.S | 1 + arch/c6x/kernel/vmlinux.lds.S | 1 + arch/cris/kernel/vmlinux.lds.S | 1 + arch/frv/kernel/vmlinux.lds.S | 1 + arch/h8300/kernel/vmlinux.lds.S | 1 + arch/hexagon/kernel/vmlinux.lds.S | 1 + arch/ia64/kernel/vmlinux.lds.S | 1 + arch/m32r/kernel/vmlinux.lds.S | 1 + arch/m68k/kernel/vmlinux-nommu.lds | 1 + arch/m68k/kernel/vmlinux-std.lds | 1 + arch/m68k/kernel/vmlinux-sun3.lds | 1 + arch/metag/kernel/vmlinux.lds.S | 1 + arch/microblaze/kernel/vmlinux.lds.S | 1 + arch/mips/kernel/vmlinux.lds.S | 1 + arch/mn10300/kernel/vmlinux.lds.S | 1 + arch/nios2/kernel/vmlinux.lds.S | 1 + arch/openrisc/kernel/vmlinux.lds.S | 1 + arch/parisc/kernel/vmlinux.lds.S | 1 + arch/powerpc/kernel/vmlinux.lds.S | 1 + arch/s390/kernel/vmlinux.lds.S | 1 + arch/score/kernel/vmlinux.lds.S | 1 + arch/sh/kernel/vmlinux.lds.S | 1 + arch/sparc/kernel/vmlinux.lds.S | 1 + arch/tile/kernel/entry.S | 2 +- arch/tile/kernel/vmlinux.lds.S | 1 + arch/um/kernel/dyn.lds.S | 1 + arch/um/kernel/uml.lds.S | 1 + arch/unicore32/kernel/vmlinux.lds.S | 1 + arch/x86/include/asm/irqflags.h | 12 ++++++++---- arch/x86/kernel/acpi/cstate.c | 2 +- arch/x86/kernel/process.c | 4 ++-- arch/x86/kernel/vmlinux.lds.S | 1 + arch/xtensa/kernel/vmlinux.lds.S | 3 +++ drivers/acpi/processor_idle.c | 5 +++-- drivers/cpuidle/driver.c | 5 +++-- drivers/idle/intel_idle.c | 4 ++-- include/asm-generic/vmlinux.lds.h | 6 ++++++ include/linux/cpu.h | 5 +++++ kernel/sched/idle.c | 13 +++++++++++-- lib/nmi_backtrace.c | 16 +++++++++++----- scripts/mod/modpost.c | 2 +- scripts/recordmcount.c | 1 + scripts/recordmcount.pl | 1 + 49 files changed, 93 insertions(+), 22 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/alpha/kernel/vmlinux.lds.S b/arch/alpha/kernel/vmlinux.lds.S index 647b84c15382..cebecfb76fbf 100644 --- a/arch/alpha/kernel/vmlinux.lds.S +++ b/arch/alpha/kernel/vmlinux.lds.S @@ -22,6 +22,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.gnu.warning) diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S index 36611072305f..f35ed578e007 100644 --- a/arch/arc/kernel/vmlinux.lds.S +++ b/arch/arc/kernel/vmlinux.lds.S @@ -89,6 +89,7 @@ SECTIONS _text = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT *(.fixup) diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S index cba1ec899a69..7fa487ef7e2f 100644 --- a/arch/arm/kernel/vmlinux-xip.lds.S +++ b/arch/arm/kernel/vmlinux-xip.lds.S @@ -98,6 +98,7 @@ SECTIONS IRQENTRY_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT *(.gnu.warning) diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index d24e5dd2aa7a..f7f55df0bf7b 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -111,6 +111,7 @@ SECTIONS SOFTIRQENTRY_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT HYPERVISOR_TEXT KPROBES_TEXT diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 5ce9b2929e0d..1105aab1e6d6 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -122,6 +122,7 @@ SECTIONS ENTRY_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT HYPERVISOR_TEXT diff --git a/arch/avr32/kernel/vmlinux.lds.S b/arch/avr32/kernel/vmlinux.lds.S index a4589176bed5..17f2730eb497 100644 --- a/arch/avr32/kernel/vmlinux.lds.S +++ b/arch/avr32/kernel/vmlinux.lds.S @@ -52,6 +52,7 @@ SECTIONS KPROBES_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.gnu.warning) diff --git a/arch/blackfin/kernel/vmlinux.lds.S b/arch/blackfin/kernel/vmlinux.lds.S index d920b959ff3a..68069a120055 100644 --- a/arch/blackfin/kernel/vmlinux.lds.S +++ b/arch/blackfin/kernel/vmlinux.lds.S @@ -33,6 +33,7 @@ SECTIONS #ifndef CONFIG_SCHEDULE_L1 SCHED_TEXT #endif + CPUIDLE_TEXT LOCK_TEXT IRQENTRY_TEXT SOFTIRQENTRY_TEXT diff --git a/arch/c6x/kernel/vmlinux.lds.S b/arch/c6x/kernel/vmlinux.lds.S index 50bc10f97bcb..a1a5c166bc9b 100644 --- a/arch/c6x/kernel/vmlinux.lds.S +++ b/arch/c6x/kernel/vmlinux.lds.S @@ -70,6 +70,7 @@ SECTIONS _stext = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT IRQENTRY_TEXT SOFTIRQENTRY_TEXT diff --git a/arch/cris/kernel/vmlinux.lds.S b/arch/cris/kernel/vmlinux.lds.S index 7552c2557506..979586261520 100644 --- a/arch/cris/kernel/vmlinux.lds.S +++ b/arch/cris/kernel/vmlinux.lds.S @@ -43,6 +43,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.text.__*) diff --git a/arch/frv/kernel/vmlinux.lds.S b/arch/frv/kernel/vmlinux.lds.S index 7e958d829ec9..aa6e573d57da 100644 --- a/arch/frv/kernel/vmlinux.lds.S +++ b/arch/frv/kernel/vmlinux.lds.S @@ -63,6 +63,7 @@ SECTIONS *(.text..tlbmiss) TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT #ifdef CONFIG_DEBUG_INFO INIT_TEXT diff --git a/arch/h8300/kernel/vmlinux.lds.S b/arch/h8300/kernel/vmlinux.lds.S index cb5dfb02c88d..7f11da1b895e 100644 --- a/arch/h8300/kernel/vmlinux.lds.S +++ b/arch/h8300/kernel/vmlinux.lds.S @@ -29,6 +29,7 @@ SECTIONS _stext = . ; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT #if defined(CONFIG_ROMKERNEL) *(.int_redirect) diff --git a/arch/hexagon/kernel/vmlinux.lds.S b/arch/hexagon/kernel/vmlinux.lds.S index 5f268c1071b3..ec87e67feb19 100644 --- a/arch/hexagon/kernel/vmlinux.lds.S +++ b/arch/hexagon/kernel/vmlinux.lds.S @@ -50,6 +50,7 @@ SECTIONS _text = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT *(.fixup) diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S index dc506b05ffbd..f89d20c97412 100644 --- a/arch/ia64/kernel/vmlinux.lds.S +++ b/arch/ia64/kernel/vmlinux.lds.S @@ -46,6 +46,7 @@ SECTIONS { __end_ivt_text = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT *(.gnu.linkonce.t*) diff --git a/arch/m32r/kernel/vmlinux.lds.S b/arch/m32r/kernel/vmlinux.lds.S index 018e4a711d79..ad1fe56455aa 100644 --- a/arch/m32r/kernel/vmlinux.lds.S +++ b/arch/m32r/kernel/vmlinux.lds.S @@ -31,6 +31,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.gnu.warning) diff --git a/arch/m68k/kernel/vmlinux-nommu.lds b/arch/m68k/kernel/vmlinux-nommu.lds index 06a763f49fd3..d2c8abf1c8c4 100644 --- a/arch/m68k/kernel/vmlinux-nommu.lds +++ b/arch/m68k/kernel/vmlinux-nommu.lds @@ -45,6 +45,7 @@ SECTIONS { HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) . = ALIGN(16); diff --git a/arch/m68k/kernel/vmlinux-std.lds b/arch/m68k/kernel/vmlinux-std.lds index d0993594f558..5b5ce1e4d1ed 100644 --- a/arch/m68k/kernel/vmlinux-std.lds +++ b/arch/m68k/kernel/vmlinux-std.lds @@ -16,6 +16,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.gnu.warning) diff --git a/arch/m68k/kernel/vmlinux-sun3.lds b/arch/m68k/kernel/vmlinux-sun3.lds index 8080469ee6c1..fe5ea1974b16 100644 --- a/arch/m68k/kernel/vmlinux-sun3.lds +++ b/arch/m68k/kernel/vmlinux-sun3.lds @@ -16,6 +16,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.gnu.warning) diff --git a/arch/metag/kernel/vmlinux.lds.S b/arch/metag/kernel/vmlinux.lds.S index 150ace92c7ad..e6c700eaf207 100644 --- a/arch/metag/kernel/vmlinux.lds.S +++ b/arch/metag/kernel/vmlinux.lds.S @@ -21,6 +21,7 @@ SECTIONS .text : { TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/microblaze/kernel/vmlinux.lds.S b/arch/microblaze/kernel/vmlinux.lds.S index 0a47f0410554..289d0e7f3e3a 100644 --- a/arch/microblaze/kernel/vmlinux.lds.S +++ b/arch/microblaze/kernel/vmlinux.lds.S @@ -33,6 +33,7 @@ SECTIONS { EXIT_TEXT EXIT_CALL SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S index a82c178d0bb9..d5de67591735 100644 --- a/arch/mips/kernel/vmlinux.lds.S +++ b/arch/mips/kernel/vmlinux.lds.S @@ -55,6 +55,7 @@ SECTIONS .text : { TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/mn10300/kernel/vmlinux.lds.S b/arch/mn10300/kernel/vmlinux.lds.S index 13c4814c29f8..2d5f1c3f1afb 100644 --- a/arch/mn10300/kernel/vmlinux.lds.S +++ b/arch/mn10300/kernel/vmlinux.lds.S @@ -30,6 +30,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT *(.fixup) diff --git a/arch/nios2/kernel/vmlinux.lds.S b/arch/nios2/kernel/vmlinux.lds.S index e23e89539967..6a8045bb1a77 100644 --- a/arch/nios2/kernel/vmlinux.lds.S +++ b/arch/nios2/kernel/vmlinux.lds.S @@ -37,6 +37,7 @@ SECTIONS .text : { TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT IRQENTRY_TEXT SOFTIRQENTRY_TEXT diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S index d936de4c07ca..d68b9ede8423 100644 --- a/arch/openrisc/kernel/vmlinux.lds.S +++ b/arch/openrisc/kernel/vmlinux.lds.S @@ -47,6 +47,7 @@ SECTIONS _stext = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S index f3ead0b6ce46..9ec8ec075dae 100644 --- a/arch/parisc/kernel/vmlinux.lds.S +++ b/arch/parisc/kernel/vmlinux.lds.S @@ -69,6 +69,7 @@ SECTIONS .text ALIGN(PAGE_SIZE) : { TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index b5fba689fca6..7ed59f0d947f 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -52,6 +52,7 @@ SECTIONS /* careful! __ftr_alt_* sections need to be close to .text */ *(.text .fixup __ftr_alt_* .ref.text) SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 429bfd111961..000e6e91f6a0 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -35,6 +35,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/score/kernel/vmlinux.lds.S b/arch/score/kernel/vmlinux.lds.S index 7274b5c4287e..4117890b1db1 100644 --- a/arch/score/kernel/vmlinux.lds.S +++ b/arch/score/kernel/vmlinux.lds.S @@ -40,6 +40,7 @@ SECTIONS _text = .; /* Text and read-only data */ TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT *(.text.*) diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S index 235a4101999f..5b9a3cc90c58 100644 --- a/arch/sh/kernel/vmlinux.lds.S +++ b/arch/sh/kernel/vmlinux.lds.S @@ -36,6 +36,7 @@ SECTIONS TEXT_TEXT EXTRA_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index d79b3b734245..572db686f845 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -49,6 +49,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/tile/kernel/entry.S b/arch/tile/kernel/entry.S index 670a3569450f..101de132e363 100644 --- a/arch/tile/kernel/entry.S +++ b/arch/tile/kernel/entry.S @@ -50,7 +50,7 @@ STD_ENTRY(smp_nap) * When interrupted at _cpu_idle_nap, we bump the PC forward 8, and * as a result return to the function that called _cpu_idle(). */ -STD_ENTRY(_cpu_idle) +STD_ENTRY_SECTION(_cpu_idle, .cpuidle.text) movei r1, 1 IRQ_ENABLE_LOAD(r2, r3) mtspr INTERRUPT_CRITICAL_SECTION, r1 diff --git a/arch/tile/kernel/vmlinux.lds.S b/arch/tile/kernel/vmlinux.lds.S index 9d449caf8910..e1baf094fba4 100644 --- a/arch/tile/kernel/vmlinux.lds.S +++ b/arch/tile/kernel/vmlinux.lds.S @@ -42,6 +42,7 @@ SECTIONS .text : AT (ADDR(.text) - LOAD_OFFSET) { HEAD_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/um/kernel/dyn.lds.S b/arch/um/kernel/dyn.lds.S index adde088aeeff..4fdbcf958cd5 100644 --- a/arch/um/kernel/dyn.lds.S +++ b/arch/um/kernel/dyn.lds.S @@ -68,6 +68,7 @@ SECTIONS _stext = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.stub .text.* .gnu.linkonce.t.*) diff --git a/arch/um/kernel/uml.lds.S b/arch/um/kernel/uml.lds.S index 6899195602b7..1840f55ed042 100644 --- a/arch/um/kernel/uml.lds.S +++ b/arch/um/kernel/uml.lds.S @@ -28,6 +28,7 @@ SECTIONS _stext = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) /* .gnu.warning sections are handled specially by elf32.em. */ diff --git a/arch/unicore32/kernel/vmlinux.lds.S b/arch/unicore32/kernel/vmlinux.lds.S index 77e407e49a63..56e788e8ee83 100644 --- a/arch/unicore32/kernel/vmlinux.lds.S +++ b/arch/unicore32/kernel/vmlinux.lds.S @@ -37,6 +37,7 @@ SECTIONS .text : { /* Real text segment */ TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index b77f5edb03b0..ac7692dcfa2e 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -4,6 +4,10 @@ #include #ifndef __ASSEMBLY__ + +/* Provide __cpuidle; we can't safely include */ +#define __cpuidle __attribute__((__section__(".cpuidle.text"))) + /* * Interrupt control: */ @@ -44,12 +48,12 @@ static inline void native_irq_enable(void) asm volatile("sti": : :"memory"); } -static inline void native_safe_halt(void) +static inline __cpuidle void native_safe_halt(void) { asm volatile("sti; hlt": : :"memory"); } -static inline void native_halt(void) +static inline __cpuidle void native_halt(void) { asm volatile("hlt": : :"memory"); } @@ -86,7 +90,7 @@ static inline notrace void arch_local_irq_enable(void) * Used in the idle loop; sti takes one instruction cycle * to complete: */ -static inline void arch_safe_halt(void) +static inline __cpuidle void arch_safe_halt(void) { native_safe_halt(); } @@ -95,7 +99,7 @@ static inline void arch_safe_halt(void) * Used when interrupts are already enabled or to * shutdown the processor: */ -static inline void halt(void) +static inline __cpuidle void halt(void) { native_halt(); } diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index bdfad642123f..af15f4444330 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -152,7 +152,7 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu, } EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe); -void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cx) +void __cpuidle acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cx) { unsigned int cpu = smp_processor_id(); struct cstate_entry *percpu_entry; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 4002b475171c..28cea7802ecb 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -302,7 +302,7 @@ void arch_cpu_idle(void) /* * We use this if we don't have any better idle routine.. */ -void default_idle(void) +void __cpuidle default_idle(void) { trace_cpu_idle_rcuidle(1, smp_processor_id()); safe_halt(); @@ -417,7 +417,7 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) * with interrupts enabled and no flags, which is backwards compatible with the * original MWAIT implementation. */ -static void mwait_idle(void) +static __cpuidle void mwait_idle(void) { if (!current_set_polling_and_test()) { trace_cpu_idle_rcuidle(1, smp_processor_id()); diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 9297a002d8e5..dbf67f64d5ec 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -97,6 +97,7 @@ SECTIONS _stext = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT ENTRY_TEXT diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S index 72cfe3587dd8..31411fc82662 100644 --- a/arch/xtensa/kernel/vmlinux.lds.S +++ b/arch/xtensa/kernel/vmlinux.lds.S @@ -89,6 +89,9 @@ SECTIONS VMLINUX_SYMBOL(__sched_text_start) = .; *(.sched.literal .sched.text) VMLINUX_SYMBOL(__sched_text_end) = .; + VMLINUX_SYMBOL(__cpuidle_text_start) = .; + *(.cpuidle.literal .cpuidle.text) + VMLINUX_SYMBOL(__cpuidle_text_end) = .; VMLINUX_SYMBOL(__lock_text_start) = .; *(.spinlock.literal .spinlock.text) VMLINUX_SYMBOL(__lock_text_end) = .; diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index cea52528aa18..2237d3f24f0e 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -31,6 +31,7 @@ #include /* need_resched() */ #include #include +#include #include /* @@ -115,7 +116,7 @@ static const struct dmi_system_id processor_power_dmi_table[] = { * Callers should disable interrupts before the call and enable * interrupts after return. */ -static void acpi_safe_halt(void) +static void __cpuidle acpi_safe_halt(void) { if (!tif_need_resched()) { safe_halt(); @@ -645,7 +646,7 @@ static int acpi_idle_bm_check(void) * * Caller disables interrupt before call and enables interrupt after return. */ -static void acpi_idle_do_entry(struct acpi_processor_cx *cx) +static void __cpuidle acpi_idle_do_entry(struct acpi_processor_cx *cx) { if (cx->entry_method == ACPI_CSTATE_FFH) { /* Call into architectural FFH based C-state */ diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c index 389ade4572be..ab264d393233 100644 --- a/drivers/cpuidle/driver.c +++ b/drivers/cpuidle/driver.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "cpuidle.h" @@ -178,8 +179,8 @@ static void __cpuidle_driver_init(struct cpuidle_driver *drv) } #ifdef CONFIG_ARCH_HAS_CPU_RELAX -static int poll_idle(struct cpuidle_device *dev, - struct cpuidle_driver *drv, int index) +static int __cpuidle poll_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) { local_irq_enable(); if (!current_set_polling_and_test()) { diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 67ec58f9ef99..4466a2f969d7 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -863,8 +863,8 @@ static struct cpuidle_state dnv_cstates[] = { * * Must be called under local_irq_disable(). */ -static int intel_idle(struct cpuidle_device *dev, - struct cpuidle_driver *drv, int index) +static __cpuidle int intel_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) { unsigned long ecx = 1; /* break on interrupt flag */ struct cpuidle_state *state = &drv->states[index]; diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 24563970ff7b..3e42bcdd014b 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -454,6 +454,12 @@ *(.spinlock.text) \ VMLINUX_SYMBOL(__lock_text_end) = .; +#define CPUIDLE_TEXT \ + ALIGN_FUNCTION(); \ + VMLINUX_SYMBOL(__cpuidle_text_start) = .; \ + *(.cpuidle.text) \ + VMLINUX_SYMBOL(__cpuidle_text_end) = .; + #define KPROBES_TEXT \ ALIGN_FUNCTION(); \ VMLINUX_SYMBOL(__kprobes_text_start) = .; \ diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 7572d9e9dced..b886dc17f2f3 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -231,6 +231,11 @@ void cpu_startup_entry(enum cpuhp_state state); void cpu_idle_poll_ctrl(bool enable); +/* Attach to any functions which should be considered cpuidle. */ +#define __cpuidle __attribute__((__section__(".cpuidle.text"))) + +bool cpu_in_idle(unsigned long pc); + void arch_cpu_idle(void); void arch_cpu_idle_prepare(void); void arch_cpu_idle_enter(void); diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 9fb873cfc75c..1d8718d5300d 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -16,6 +16,9 @@ #include "sched.h" +/* Linker adds these: start and end of __cpuidle functions */ +extern char __cpuidle_text_start[], __cpuidle_text_end[]; + /** * sched_idle_set_state - Record idle state for the current CPU. * @idle_state: State to record. @@ -53,7 +56,7 @@ static int __init cpu_idle_nopoll_setup(char *__unused) __setup("hlt", cpu_idle_nopoll_setup); #endif -static inline int cpu_idle_poll(void) +static noinline int __cpuidle cpu_idle_poll(void) { rcu_idle_enter(); trace_cpu_idle_rcuidle(0, smp_processor_id()); @@ -84,7 +87,7 @@ void __weak arch_cpu_idle(void) * * To use when the cpuidle framework cannot be used. */ -void default_idle_call(void) +void __cpuidle default_idle_call(void) { if (current_clr_polling_and_test()) { local_irq_enable(); @@ -271,6 +274,12 @@ static void cpu_idle_loop(void) } } +bool cpu_in_idle(unsigned long pc) +{ + return pc >= (unsigned long)__cpuidle_text_start && + pc < (unsigned long)__cpuidle_text_end; +} + void cpu_startup_entry(enum cpuhp_state state) { /* diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c index 393a3cca1f47..75554754eadf 100644 --- a/lib/nmi_backtrace.c +++ b/lib/nmi_backtrace.c @@ -16,6 +16,7 @@ #include #include #include +#include #ifdef arch_trigger_cpumask_backtrace /* For reliability, we're prepared to waste bits here. */ @@ -87,11 +88,16 @@ bool nmi_cpu_backtrace(struct pt_regs *regs) int cpu = smp_processor_id(); if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) { - pr_warn("NMI backtrace for cpu %d\n", cpu); - if (regs) - show_regs(regs); - else - dump_stack(); + if (regs && cpu_in_idle(instruction_pointer(regs))) { + pr_warn("NMI backtrace for cpu %d skipped: idling at pc %#lx\n", + cpu, instruction_pointer(regs)); + } else { + pr_warn("NMI backtrace for cpu %d\n", cpu); + if (regs) + show_regs(regs); + else + dump_stack(); + } cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask)); return true; } diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 48958d3cec9e..bd8349759095 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -888,7 +888,7 @@ static void check_section(const char *modname, struct elf_info *elf, #define DATA_SECTIONS ".data", ".data.rel" #define TEXT_SECTIONS ".text", ".text.unlikely", ".sched.text", \ - ".kprobes.text" + ".kprobes.text", ".cpuidle.text" #define OTHER_TEXT_SECTIONS ".ref.text", ".head.text", ".spinlock.text", \ ".fixup", ".entry.text", ".exception.text", ".text.*", \ ".coldtext" diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c index a68f03133df9..5423a58d1b06 100644 --- a/scripts/recordmcount.c +++ b/scripts/recordmcount.c @@ -365,6 +365,7 @@ is_mcounted_section_name(char const *const txtname) strcmp(".irqentry.text", txtname) == 0 || strcmp(".softirqentry.text", txtname) == 0 || strcmp(".kprobes.text", txtname) == 0 || + strcmp(".cpuidle.text", txtname) == 0 || strcmp(".text.unlikely", txtname) == 0; } diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index 2d48011bc362..faac4b10d8ea 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -136,6 +136,7 @@ my %text_sections = ( ".irqentry.text" => 1, ".softirqentry.text" => 1, ".kprobes.text" => 1, + ".cpuidle.text" => 1, ".text.unlikely" => 1, ); -- cgit v1.2.3 From 0ee59413c967c35a6dd2dbdab605b4cd42025ee5 Mon Sep 17 00:00:00 2001 From: Hidehiro Kawai Date: Tue, 11 Oct 2016 13:54:23 -0700 Subject: x86/panic: replace smp_send_stop() with kdump friendly version in panic path Daniel Walker reported problems which happens when crash_kexec_post_notifiers kernel option is enabled (https://lkml.org/lkml/2015/6/24/44). In that case, smp_send_stop() is called before entering kdump routines which assume other CPUs are still online. As the result, for x86, kdump routines fail to save other CPUs' registers and disable virtualization extensions. To fix this problem, call a new kdump friendly function, crash_smp_send_stop(), instead of the smp_send_stop() when crash_kexec_post_notifiers is enabled. crash_smp_send_stop() is a weak function, and it just call smp_send_stop(). Architecture codes should override it so that kdump can work appropriately. This patch only provides x86-specific version. For Xen's PV kernel, just keep the current behavior. NOTES: - Right solution would be to place crash_smp_send_stop() before __crash_kexec() invocation in all cases and remove smp_send_stop(), but we can't do that until all architectures implement own crash_smp_send_stop() - crash_smp_send_stop()-like work is still needed by machine_crash_shutdown() because crash_kexec() can be called without entering panic() Fixes: f06e5153f4ae (kernel/panic.c: add "crash_kexec_post_notifiers" option) Link: http://lkml.kernel.org/r/20160810080948.11028.15344.stgit@sysi4-13.yrl.intra.hitachi.co.jp Signed-off-by: Hidehiro Kawai Reported-by: Daniel Walker Cc: Dave Young Cc: Baoquan He Cc: Vivek Goyal Cc: Eric Biederman Cc: Masami Hiramatsu Cc: Daniel Walker Cc: Xunlei Pang Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Borislav Petkov Cc: David Vrabel Cc: Toshi Kani Cc: Ralf Baechle Cc: David Daney Cc: Aaro Koskinen Cc: "Steven J. Hill" Cc: Corey Minyard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/kexec.h | 1 + arch/x86/include/asm/smp.h | 1 + arch/x86/kernel/crash.c | 22 ++++++++++++++++++--- arch/x86/kernel/smp.c | 5 +++++ kernel/panic.c | 47 +++++++++++++++++++++++++++++++++++++------- 5 files changed, 66 insertions(+), 10 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index d2434c1cad05..282630e4c6ea 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -210,6 +210,7 @@ struct kexec_entry64_regs { typedef void crash_vmclear_fn(void); extern crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss; +extern void kdump_nmi_shootdown_cpus(void); #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 19980b36f394..026ea82ecc60 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -47,6 +47,7 @@ struct smp_ops { void (*smp_cpus_done)(unsigned max_cpus); void (*stop_other_cpus)(int wait); + void (*crash_stop_other_cpus)(void); void (*smp_send_reschedule)(int cpu); int (*cpu_up)(unsigned cpu, struct task_struct *tidle); diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 9616cf76940c..650830e39e3a 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -133,15 +133,31 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs) disable_local_APIC(); } -static void kdump_nmi_shootdown_cpus(void) +void kdump_nmi_shootdown_cpus(void) { nmi_shootdown_cpus(kdump_nmi_callback); disable_local_APIC(); } +/* Override the weak function in kernel/panic.c */ +void crash_smp_send_stop(void) +{ + static int cpus_stopped; + + if (cpus_stopped) + return; + + if (smp_ops.crash_stop_other_cpus) + smp_ops.crash_stop_other_cpus(); + else + smp_send_stop(); + + cpus_stopped = 1; +} + #else -static void kdump_nmi_shootdown_cpus(void) +void crash_smp_send_stop(void) { /* There are no cpus to shootdown */ } @@ -160,7 +176,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs) /* The kernel is broken so disable interrupts */ local_irq_disable(); - kdump_nmi_shootdown_cpus(); + crash_smp_send_stop(); /* * VMCLEAR VMCSs loaded on this cpu if needed. diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 658777cf3851..68f8cc222f25 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -32,6 +32,8 @@ #include #include #include +#include + /* * Some notes on x86 processor bugs affecting SMP operation: * @@ -342,6 +344,9 @@ struct smp_ops smp_ops = { .smp_cpus_done = native_smp_cpus_done, .stop_other_cpus = native_stop_other_cpus, +#if defined(CONFIG_KEXEC_CORE) + .crash_stop_other_cpus = kdump_nmi_shootdown_cpus, +#endif .smp_send_reschedule = native_smp_send_reschedule, .cpu_up = native_cpu_up, diff --git a/kernel/panic.c b/kernel/panic.c index ca8cea1ef673..e6480e20379e 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -71,6 +71,32 @@ void __weak nmi_panic_self_stop(struct pt_regs *regs) panic_smp_self_stop(); } +/* + * Stop other CPUs in panic. Architecture dependent code may override this + * with more suitable version. For example, if the architecture supports + * crash dump, it should save registers of each stopped CPU and disable + * per-CPU features such as virtualization extensions. + */ +void __weak crash_smp_send_stop(void) +{ + static int cpus_stopped; + + /* + * This function can be called twice in panic path, but obviously + * we execute this only once. + */ + if (cpus_stopped) + return; + + /* + * Note smp_send_stop is the usual smp shutdown function, which + * unfortunately means it may not be hardened to work in a panic + * situation. + */ + smp_send_stop(); + cpus_stopped = 1; +} + atomic_t panic_cpu = ATOMIC_INIT(PANIC_CPU_INVALID); /* @@ -164,14 +190,21 @@ void panic(const char *fmt, ...) if (!_crash_kexec_post_notifiers) { printk_nmi_flush_on_panic(); __crash_kexec(NULL); - } - /* - * Note smp_send_stop is the usual smp shutdown function, which - * unfortunately means it may not be hardened to work in a panic - * situation. - */ - smp_send_stop(); + /* + * Note smp_send_stop is the usual smp shutdown function, which + * unfortunately means it may not be hardened to work in a + * panic situation. + */ + smp_send_stop(); + } else { + /* + * If we want to do crash dump after notifier calls and + * kmsg_dump, we will need architecture dependent extra + * works in addition to stopping other CPUs. + */ + crash_smp_send_stop(); + } /* * Run any panic handlers, including those that might need to -- cgit v1.2.3