diff --git a/.mailmap b/.mailmap index 191778125ef1..3e63fb0b1088 100644 --- a/.mailmap +++ b/.mailmap @@ -336,6 +336,7 @@ Oleksij Rempel Oleksij Rempel Oleksij Rempel Oleksij Rempel +Oliver Upton Pali Rohár Paolo 'Blaisorblade' Giarrusso Patrick Mochel diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index be4a77baf784..7ce8130a8924 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1355,6 +1355,11 @@ PAGE_SIZE multiple when read back. pagetables Amount of memory allocated for page tables. + sec_pagetables + Amount of memory allocated for secondary page tables, + this currently includes KVM mmu allocations on x86 + and arm64. + percpu (npn) Amount of memory used for storing per-cpu kernel data structures. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 5258043cafed..1373e62b305d 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3637,7 +3637,7 @@ (bounds check bypass). With this option data leaks are possible in the system. - nospectre_v2 [X86,PPC_FSL_BOOK3E,ARM64] Disable all mitigations for + nospectre_v2 [X86,PPC_E500,ARM64] Disable all mitigations for the Spectre variant 2 (indirect branch prediction) vulnerability. System may allow data leaks with this option. @@ -3756,9 +3756,9 @@ [X86,PV_OPS] Disable paravirtualized VMware scheduler clock and use the default one. - no-steal-acc [X86,PV_OPS,ARM64] Disable paravirtualized steal time - accounting. steal time is computed, but won't - influence scheduler behaviour + no-steal-acc [X86,PV_OPS,ARM64,PPC/PSERIES] Disable paravirtualized + steal time accounting. steal time is computed, but + won't influence scheduler behaviour nolapic [X86-32,APIC] Do not enable or use the local APIC. diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index e7aafc82be99..898c99eae8e4 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -982,6 +982,7 @@ Example output. You may not have all of these fields. SUnreclaim: 142336 kB KernelStack: 11168 kB PageTables: 20540 kB + SecPageTables: 0 kB NFS_Unstable: 0 kB Bounce: 0 kB WritebackTmp: 0 kB @@ -1090,6 +1091,9 @@ KernelStack Memory consumed by the kernel stacks of all tasks PageTables Memory consumed by userspace page tables +SecPageTables + Memory consumed by secondary page tables, this currently + currently includes KVM mmu allocations on x86 and arm64. NFS_Unstable Always zero. Previous counted pages which had been written to the server, but has not been committed to stable storage. diff --git a/Documentation/powerpc/isa-versions.rst b/Documentation/powerpc/isa-versions.rst index dfcb1097dce4..a8d6b6028b3e 100644 --- a/Documentation/powerpc/isa-versions.rst +++ b/Documentation/powerpc/isa-versions.rst @@ -4,12 +4,16 @@ CPU to ISA Version Mapping Mapping of some CPU versions to relevant ISA versions. +Note Power4 and Power4+ are not supported. + ========= ==================================================================== CPU Architecture version ========= ==================================================================== Power10 Power ISA v3.1 Power9 Power ISA v3.0B Power8 Power ISA v2.07 +e6500 Power ISA v2.06 with some exceptions +e5500 Power ISA v2.06 with some exceptions, no Altivec Power7 Power ISA v2.06 Power6 Power ISA v2.05 PA6T Power ISA v2.04 @@ -24,6 +28,12 @@ PPC970 - PowerPC User Instruction Set Architecture Book I v2.01 - PowerPC Virtual Environment Architecture Book II v2.01 - PowerPC Operating Environment Architecture Book III v2.01 - Plus Altivec/VMX ~= 2.03 +Power4+ - PowerPC User Instruction Set Architecture Book I v2.01 + - PowerPC Virtual Environment Architecture Book II v2.01 + - PowerPC Operating Environment Architecture Book III v2.01 +Power4 - PowerPC User Instruction Set Architecture Book I v2.00 + - PowerPC Virtual Environment Architecture Book II v2.00 + - PowerPC Operating Environment Architecture Book III v2.00 ========= ==================================================================== @@ -36,6 +46,8 @@ CPU VMX (aka. Altivec) Power10 Yes Power9 Yes Power8 Yes +e6500 Yes +e5500 No Power7 Yes Power6 Yes PA6T Yes @@ -44,6 +56,8 @@ Power5++ No Power5+ No Power5 No PPC970 Yes +Power4+ No +Power4 No ========== ================== ========== ==== @@ -52,6 +66,8 @@ CPU VSX Power10 Yes Power9 Yes Power8 Yes +e6500 No +e5500 No Power7 Yes Power6 No PA6T No @@ -60,6 +76,8 @@ Power5++ No Power5+ No Power5 No PPC970 No +Power4+ No +Power4 No ========== ==== ========== ==================================== @@ -68,6 +86,8 @@ CPU Transactional Memory Power10 No (* see Power ISA v3.1, "Appendix A. Notes on the Removal of Transactional Memory from the Architecture") Power9 Yes (* see transactional_memory.txt) Power8 Yes +e6500 No +e5500 No Power7 No Power6 No PA6T No @@ -76,4 +96,6 @@ Power5++ No Power5+ No Power5 No PPC970 No +Power4+ No +Power4 No ========== ==================================== diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index abd7c32126ce..236a797be71c 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -4074,7 +4074,7 @@ Queues an SMI on the thread's vcpu. 4.97 KVM_X86_SET_MSR_FILTER ---------------------------- -:Capability: KVM_X86_SET_MSR_FILTER +:Capability: KVM_CAP_X86_MSR_FILTER :Architectures: x86 :Type: vm ioctl :Parameters: struct kvm_msr_filter @@ -4173,8 +4173,10 @@ If an MSR access is not permitted through the filtering, it generates a allows user space to deflect and potentially handle various MSR accesses into user space. -If a vCPU is in running state while this ioctl is invoked, the vCPU may -experience inconsistent filtering behavior on MSR accesses. +Note, invoking this ioctl while a vCPU is running is inherently racy. However, +KVM does guarantee that vCPUs will see either the previous filter or the new +filter, e.g. MSRs with identical settings in both the old and new filter will +have deterministic behavior. 4.98 KVM_CREATE_SPAPR_TCE_64 ---------------------------- @@ -5287,110 +5289,7 @@ KVM_PV_DUMP authentication tag all of which are needed to decrypt the dump at a later time. - -4.126 KVM_X86_SET_MSR_FILTER ----------------------------- - -:Capability: KVM_CAP_X86_MSR_FILTER -:Architectures: x86 -:Type: vm ioctl -:Parameters: struct kvm_msr_filter -:Returns: 0 on success, < 0 on error - -:: - - struct kvm_msr_filter_range { - #define KVM_MSR_FILTER_READ (1 << 0) - #define KVM_MSR_FILTER_WRITE (1 << 1) - __u32 flags; - __u32 nmsrs; /* number of msrs in bitmap */ - __u32 base; /* MSR index the bitmap starts at */ - __u8 *bitmap; /* a 1 bit allows the operations in flags, 0 denies */ - }; - - #define KVM_MSR_FILTER_MAX_RANGES 16 - struct kvm_msr_filter { - #define KVM_MSR_FILTER_DEFAULT_ALLOW (0 << 0) - #define KVM_MSR_FILTER_DEFAULT_DENY (1 << 0) - __u32 flags; - struct kvm_msr_filter_range ranges[KVM_MSR_FILTER_MAX_RANGES]; - }; - -flags values for ``struct kvm_msr_filter_range``: - -``KVM_MSR_FILTER_READ`` - - Filter read accesses to MSRs using the given bitmap. A 0 in the bitmap - indicates that a read should immediately fail, while a 1 indicates that - a read for a particular MSR should be handled regardless of the default - filter action. - -``KVM_MSR_FILTER_WRITE`` - - Filter write accesses to MSRs using the given bitmap. A 0 in the bitmap - indicates that a write should immediately fail, while a 1 indicates that - a write for a particular MSR should be handled regardless of the default - filter action. - -``KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE`` - - Filter both read and write accesses to MSRs using the given bitmap. A 0 - in the bitmap indicates that both reads and writes should immediately fail, - while a 1 indicates that reads and writes for a particular MSR are not - filtered by this range. - -flags values for ``struct kvm_msr_filter``: - -``KVM_MSR_FILTER_DEFAULT_ALLOW`` - - If no filter range matches an MSR index that is getting accessed, KVM will - fall back to allowing access to the MSR. - -``KVM_MSR_FILTER_DEFAULT_DENY`` - - If no filter range matches an MSR index that is getting accessed, KVM will - fall back to rejecting access to the MSR. In this mode, all MSRs that should - be processed by KVM need to explicitly be marked as allowed in the bitmaps. - -This ioctl allows user space to define up to 16 bitmaps of MSR ranges to -specify whether a certain MSR access should be explicitly filtered for or not. - -If this ioctl has never been invoked, MSR accesses are not guarded and the -default KVM in-kernel emulation behavior is fully preserved. - -Calling this ioctl with an empty set of ranges (all nmsrs == 0) disables MSR -filtering. In that mode, ``KVM_MSR_FILTER_DEFAULT_DENY`` is invalid and causes -an error. - -As soon as the filtering is in place, every MSR access is processed through -the filtering except for accesses to the x2APIC MSRs (from 0x800 to 0x8ff); -x2APIC MSRs are always allowed, independent of the ``default_allow`` setting, -and their behavior depends on the ``X2APIC_ENABLE`` bit of the APIC base -register. - -If a bit is within one of the defined ranges, read and write accesses are -guarded by the bitmap's value for the MSR index if the kind of access -is included in the ``struct kvm_msr_filter_range`` flags. If no range -cover this particular access, the behavior is determined by the flags -field in the kvm_msr_filter struct: ``KVM_MSR_FILTER_DEFAULT_ALLOW`` -and ``KVM_MSR_FILTER_DEFAULT_DENY``. - -Each bitmap range specifies a range of MSRs to potentially allow access on. -The range goes from MSR index [base .. base+nmsrs]. The flags field -indicates whether reads, writes or both reads and writes are filtered -by setting a 1 bit in the bitmap for the corresponding MSR index. - -If an MSR access is not permitted through the filtering, it generates a -#GP inside the guest. When combined with KVM_CAP_X86_USER_SPACE_MSR, that -allows user space to deflect and potentially handle various MSR accesses -into user space. - -Note, invoking this ioctl with a vCPU is running is inherently racy. However, -KVM does guarantee that vCPUs will see either the previous filter or the new -filter, e.g. MSRs with identical settings in both the old and new filter will -have deterministic behavior. - -4.127 KVM_XEN_HVM_SET_ATTR +4.126 KVM_XEN_HVM_SET_ATTR -------------------------- :Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO diff --git a/Documentation/virt/kvm/vcpu-requests.rst b/Documentation/virt/kvm/vcpu-requests.rst index 31f62b64e07b..87f04c1fa53d 100644 --- a/Documentation/virt/kvm/vcpu-requests.rst +++ b/Documentation/virt/kvm/vcpu-requests.rst @@ -97,7 +97,7 @@ VCPU requests are simply bit indices of the ``vcpu->requests`` bitmap. This means general bitops, like those documented in [atomic-ops]_ could also be used, e.g. :: - clear_bit(KVM_REQ_UNHALT & KVM_REQUEST_MASK, &vcpu->requests); + clear_bit(KVM_REQ_UNBLOCK & KVM_REQUEST_MASK, &vcpu->requests); However, VCPU request users should refrain from doing so, as it would break the abstraction. The first 8 bits are reserved for architecture @@ -126,17 +126,6 @@ KVM_REQ_UNBLOCK or in order to update the interrupt routing and ensure that assigned devices will wake up the vCPU. -KVM_REQ_UNHALT - - This request may be made from the KVM common function kvm_vcpu_block(), - which is used to emulate an instruction that causes a CPU to halt until - one of an architectural specific set of events and/or interrupts is - received (determined by checking kvm_arch_vcpu_runnable()). When that - event or interrupt arrives kvm_vcpu_block() makes the request. This is - in contrast to when kvm_vcpu_block() returns due to any other reason, - such as a pending signal, which does not indicate the VCPU's halt - emulation should stop, and therefore does not make the request. - KVM_REQ_OUTSIDE_GUEST_MODE This "request" ensures the target vCPU has exited guest mode prior to the @@ -297,21 +286,6 @@ architecture dependent. kvm_vcpu_block() calls kvm_arch_vcpu_runnable() to check if it should awaken. One reason to do so is to provide architectures a function where requests may be checked if necessary. -Clearing Requests ------------------ - -Generally it only makes sense for the receiving VCPU thread to clear a -request. However, in some circumstances, such as when the requesting -thread and the receiving VCPU thread are executed serially, such as when -they are the same thread, or when they are using some form of concurrency -control to temporarily execute synchronously, then it's possible to know -that the request may be cleared immediately, rather than waiting for the -receiving VCPU thread to handle the request in VCPU RUN. The only current -examples of this are kvm_vcpu_block() calls made by VCPUs to block -themselves. A possible side-effect of that call is to make the -KVM_REQ_UNHALT request, which may then be cleared immediately when the -VCPU returns from the call. - References ========== diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 44ebf5b2fc4b..817d788cd866 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -22,46 +22,6 @@ #include #include -void store_cpu_topology(unsigned int cpuid) -{ - struct cpu_topology *cpuid_topo = &cpu_topology[cpuid]; - u64 mpidr; - - if (cpuid_topo->package_id != -1) - goto topology_populated; - - mpidr = read_cpuid_mpidr(); - - /* Uniprocessor systems can rely on default topology values */ - if (mpidr & MPIDR_UP_BITMASK) - return; - - /* - * This would be the place to create cpu topology based on MPIDR. - * - * However, it cannot be trusted to depict the actual topology; some - * pieces of the architecture enforce an artificial cap on Aff0 values - * (e.g. GICv3's ICC_SGI1R_EL1 limits it to 15), leading to an - * artificial cycling of Aff1, Aff2 and Aff3 values. IOW, these end up - * having absolutely no relationship to the actual underlying system - * topology, and cannot be reasonably used as core / package ID. - * - * If the MT bit is set, Aff0 *could* be used to define a thread ID, but - * we still wouldn't be able to obtain a sane core ID. This means we - * need to entirely ignore MPIDR for any topology deduction. - */ - cpuid_topo->thread_id = -1; - cpuid_topo->core_id = cpuid; - cpuid_topo->package_id = cpu_to_node(cpuid); - - pr_debug("CPU%u: cluster %d core %d thread %d mpidr %#016llx\n", - cpuid, cpuid_topo->package_id, cpuid_topo->core_id, - cpuid_topo->thread_id, mpidr); - -topology_populated: - update_siblings_masks(cpuid); -} - #ifdef CONFIG_ACPI static bool __init acpi_cpu_is_threaded(int cpu) { diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 917086be5c6b..446f628a9de1 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -666,7 +666,6 @@ void kvm_vcpu_wfi(struct kvm_vcpu *vcpu) kvm_vcpu_halt(vcpu); vcpu_clear_flag(vcpu, IN_WFIT); - kvm_clear_request(KVM_REQ_UNHALT, vcpu); preempt_disable(); vgic_v4_load(vcpu); diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index c9a13e487187..34c5feed9dc1 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -92,9 +92,13 @@ static bool kvm_is_device_pfn(unsigned long pfn) static void *stage2_memcache_zalloc_page(void *arg) { struct kvm_mmu_memory_cache *mc = arg; + void *virt; /* Allocated with __GFP_ZERO, so no need to zero */ - return kvm_mmu_memory_cache_alloc(mc); + virt = kvm_mmu_memory_cache_alloc(mc); + if (virt) + kvm_account_pgtable_pages(virt, 1); + return virt; } static void *kvm_host_zalloc_pages_exact(size_t size) @@ -102,6 +106,21 @@ static void *kvm_host_zalloc_pages_exact(size_t size) return alloc_pages_exact(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO); } +static void *kvm_s2_zalloc_pages_exact(size_t size) +{ + void *virt = kvm_host_zalloc_pages_exact(size); + + if (virt) + kvm_account_pgtable_pages(virt, (size >> PAGE_SHIFT)); + return virt; +} + +static void kvm_s2_free_pages_exact(void *virt, size_t size) +{ + kvm_account_pgtable_pages(virt, -(size >> PAGE_SHIFT)); + free_pages_exact(virt, size); +} + static void kvm_host_get_page(void *addr) { get_page(virt_to_page(addr)); @@ -112,6 +131,15 @@ static void kvm_host_put_page(void *addr) put_page(virt_to_page(addr)); } +static void kvm_s2_put_page(void *addr) +{ + struct page *p = virt_to_page(addr); + /* Dropping last refcount, the page will be freed */ + if (page_count(p) == 1) + kvm_account_pgtable_pages(addr, -1); + put_page(p); +} + static int kvm_host_page_count(void *addr) { return page_count(virt_to_page(addr)); @@ -625,10 +653,10 @@ static int get_user_mapping_size(struct kvm *kvm, u64 addr) static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = { .zalloc_page = stage2_memcache_zalloc_page, - .zalloc_pages_exact = kvm_host_zalloc_pages_exact, - .free_pages_exact = free_pages_exact, + .zalloc_pages_exact = kvm_s2_zalloc_pages_exact, + .free_pages_exact = kvm_s2_free_pages_exact, .get_page = kvm_host_get_page, - .put_page = kvm_host_put_page, + .put_page = kvm_s2_put_page, .page_count = kvm_host_page_count, .phys_to_virt = kvm_host_va, .virt_to_phys = kvm_host_pa, diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index 996132a5ef35..4ebb56d6d959 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -204,6 +204,16 @@ config TASK_SIZE hex "Size of user task space" if TASK_SIZE_BOOL default "0x80000000" +config MB_MANAGER + bool "Support for Microblaze Manager" + depends on ADVANCED_OPTIONS + help + This option enables API for configuring the MicroBlaze manager + control register, which is consumed by the break handler to + block the break. + + Say N here unless you know what you are doing. + endmenu menu "Bus Options" diff --git a/arch/microblaze/include/asm/xilinx_mb_manager.h b/arch/microblaze/include/asm/xilinx_mb_manager.h new file mode 100644 index 000000000000..7b6995722b0c --- /dev/null +++ b/arch/microblaze/include/asm/xilinx_mb_manager.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022 Xilinx, Inc. + */ +#ifndef _XILINX_MB_MANAGER_H +#define _XILINX_MB_MANAGER_H + +# ifndef __ASSEMBLY__ + +#include + +/* + * When the break vector gets asserted because of error injection, the break + * signal must be blocked before exiting from the break handler, Below api + * updates the manager address and control register and error counter callback + * arguments, which will be used by the break handler to block the break and + * call the callback function. + */ +void xmb_manager_register(uintptr_t phys_baseaddr, u32 cr_val, + void (*callback)(void *data), + void *priv, void (*reset_callback)(void *data)); +asmlinkage void xmb_inject_err(void); + +# endif /* __ASSEMBLY__ */ + +/* Error injection offset */ +#define XMB_INJECT_ERR_OFFSET 0x200 + +#endif /* _XILINX_MB_MANAGER_H */ diff --git a/arch/microblaze/kernel/asm-offsets.c b/arch/microblaze/kernel/asm-offsets.c index 47ee409508b1..104c3ac5f30c 100644 --- a/arch/microblaze/kernel/asm-offsets.c +++ b/arch/microblaze/kernel/asm-offsets.c @@ -120,5 +120,12 @@ int main(int argc, char *argv[]) DEFINE(CC_FSR, offsetof(struct cpu_context, fsr)); BLANK(); + /* struct cpuinfo */ + DEFINE(CI_DCS, offsetof(struct cpuinfo, dcache_size)); + DEFINE(CI_DCL, offsetof(struct cpuinfo, dcache_line_length)); + DEFINE(CI_ICS, offsetof(struct cpuinfo, icache_size)); + DEFINE(CI_ICL, offsetof(struct cpuinfo, icache_line_length)); + BLANK(); + return 0; } diff --git a/arch/microblaze/kernel/entry.S b/arch/microblaze/kernel/entry.S index d875a0c01032..582d7256d815 100644 --- a/arch/microblaze/kernel/entry.S +++ b/arch/microblaze/kernel/entry.S @@ -27,9 +27,11 @@ #include #include +#include #include #include +#include #undef DEBUG @@ -287,6 +289,44 @@ syscall_debug_table: .text +.extern cpuinfo + +C_ENTRY(mb_flush_dcache): + addik r1, r1, -PT_SIZE + SAVE_REGS + + addik r3, r0, cpuinfo + lwi r7, r3, CI_DCS + lwi r8, r3, CI_DCL + sub r9, r7, r8 +1: + wdc.flush r9, r0 + bgtid r9, 1b + addk r9, r9, r8 + + RESTORE_REGS + addik r1, r1, PT_SIZE + rtsd r15, 8 + nop + +C_ENTRY(mb_invalidate_icache): + addik r1, r1, -PT_SIZE + SAVE_REGS + + addik r3, r0, cpuinfo + lwi r7, r3, CI_ICS + lwi r8, r3, CI_ICL + sub r9, r7, r8 +1: + wic r9, r0 + bgtid r9, 1b + addk r9, r9, r8 + + RESTORE_REGS + addik r1, r1, PT_SIZE + rtsd r15, 8 + nop + /* * User trap. * @@ -753,6 +793,160 @@ IRQ_return: /* MS: Make global symbol for debugging */ rtid r14, 0 nop +#ifdef CONFIG_MB_MANAGER + +#define PT_PID PT_SIZE +#define PT_TLBI PT_SIZE + 4 +#define PT_ZPR PT_SIZE + 8 +#define PT_TLBL0 PT_SIZE + 12 +#define PT_TLBH0 PT_SIZE + 16 + +C_ENTRY(_xtmr_manager_reset): + lwi r1, r0, xmb_manager_stackpointer + + /* Restore MSR */ + lwi r2, r1, PT_MSR + mts rmsr, r2 + bri 4 + + /* restore Special purpose registers */ + lwi r2, r1, PT_PID + mts rpid, r2 + + lwi r2, r1, PT_TLBI + mts rtlbx, r2 + + lwi r2, r1, PT_ZPR + mts rzpr, r2 + +#if CONFIG_XILINX_MICROBLAZE0_USE_FPU + lwi r2, r1, PT_FSR + mts rfsr, r2 +#endif + + /* restore all the tlb's */ + addik r3, r0, TOPHYS(tlb_skip) + addik r6, r0, PT_TLBL0 + addik r7, r0, PT_TLBH0 +restore_tlb: + add r6, r6, r1 + add r7, r7, r1 + lwi r2, r6, 0 + mts rtlblo, r2 + lwi r2, r7, 0 + mts rtlbhi, r2 + addik r6, r6, 4 + addik r7, r7, 4 + bgtid r3, restore_tlb + addik r3, r3, -1 + + lwi r5, r0, TOPHYS(xmb_manager_dev) + lwi r8, r0, TOPHYS(xmb_manager_reset_callback) + set_vms + /* return from reset need -8 to adjust for rtsd r15, 8 */ + addik r15, r0, ret_from_reset - 8 + rtbd r8, 0 + nop + +ret_from_reset: + set_bip /* Ints masked for state restore */ + VM_OFF + /* MS: Restore all regs */ + RESTORE_REGS + lwi r14, r1, PT_R14 + lwi r16, r1, PT_PC + addik r1, r1, PT_SIZE + 36 + rtbd r16, 0 + nop + +/* + * Break handler for MB Manager. Enter to _xmb_manager_break by + * injecting fault in one of the TMR Microblaze core. + * FIXME: This break handler supports getting + * called from kernel space only. + */ +C_ENTRY(_xmb_manager_break): + /* + * Reserve memory in the stack for context store/restore + * (which includes memory for storing tlbs (max two tlbs)) + */ + addik r1, r1, -PT_SIZE - 36 + swi r1, r0, xmb_manager_stackpointer + SAVE_REGS + swi r14, r1, PT_R14 /* rewrite saved R14 value */ + swi r16, r1, PT_PC; /* PC and r16 are the same */ + + lwi r6, r0, TOPHYS(xmb_manager_baseaddr) + lwi r7, r0, TOPHYS(xmb_manager_crval) + /* + * When the break vector gets asserted because of error injection, + * the break signal must be blocked before exiting from the + * break handler, below code configures the tmr manager + * control register to block break signal. + */ + swi r7, r6, 0 + + /* Save the special purpose registers */ + mfs r2, rpid + swi r2, r1, PT_PID + + mfs r2, rtlbx + swi r2, r1, PT_TLBI + + mfs r2, rzpr + swi r2, r1, PT_ZPR + +#if CONFIG_XILINX_MICROBLAZE0_USE_FPU + mfs r2, rfsr + swi r2, r1, PT_FSR +#endif + mfs r2, rmsr + swi r2, r1, PT_MSR + + /* Save all the tlb's */ + addik r3, r0, TOPHYS(tlb_skip) + addik r6, r0, PT_TLBL0 + addik r7, r0, PT_TLBH0 +save_tlb: + add r6, r6, r1 + add r7, r7, r1 + mfs r2, rtlblo + swi r2, r6, 0 + mfs r2, rtlbhi + swi r2, r7, 0 + addik r6, r6, 4 + addik r7, r7, 4 + bgtid r3, save_tlb + addik r3, r3, -1 + + lwi r5, r0, TOPHYS(xmb_manager_dev) + lwi r8, r0, TOPHYS(xmb_manager_callback) + /* return from break need -8 to adjust for rtsd r15, 8 */ + addik r15, r0, ret_from_break - 8 + rtbd r8, 0 + nop + +ret_from_break: + /* flush the d-cache */ + bralid r15, mb_flush_dcache + nop + + /* + * To make sure microblaze i-cache is in a proper state + * invalidate the i-cache. + */ + bralid r15, mb_invalidate_icache + nop + + set_bip; /* Ints masked for state restore */ + VM_OFF; + mbar 1 + mbar 2 + bri 4 + suspend + nop +#endif + /* * Debug trap for KGDB. Enter to _debug_exception by brki r16, 0x18 * and call handling function with saved pt_regs @@ -957,6 +1151,88 @@ ENTRY(_switch_to) rtsd r15, 8 nop +#ifdef CONFIG_MB_MANAGER +.global xmb_inject_err +.section .text +.align 2 +.ent xmb_inject_err +.type xmb_inject_err, @function +xmb_inject_err: + addik r1, r1, -PT_SIZE + SAVE_REGS + + /* Switch to real mode */ + VM_OFF; + set_bip; + mbar 1 + mbar 2 + bralid r15, XMB_INJECT_ERR_OFFSET + nop; + + /* enable virtual mode */ + set_vms; + /* barrier for instructions and data accesses */ + mbar 1 + mbar 2 + /* + * Enable Interrupts, Virtual Protected Mode, equalize + * initial state for all possible entries. + */ + rtbd r0, 1f + nop; +1: + RESTORE_REGS + addik r1, r1, PT_SIZE + rtsd r15, 8; + nop; +.end xmb_inject_err + +.section .data +.global xmb_manager_dev +.global xmb_manager_baseaddr +.global xmb_manager_crval +.global xmb_manager_callback +.global xmb_manager_reset_callback +.global xmb_manager_stackpointer +.align 4 +xmb_manager_dev: + .long 0 +xmb_manager_baseaddr: + .long 0 +xmb_manager_crval: + .long 0 +xmb_manager_callback: + .long 0 +xmb_manager_reset_callback: + .long 0 +xmb_manager_stackpointer: + .long 0 + +/* + * When the break vector gets asserted because of error injection, + * the break signal must be blocked before exiting from the + * break handler, Below api updates the manager address and + * control register and error count callback arguments, + * which will be used by the break handler to block the + * break and call the callback function. + */ +.global xmb_manager_register +.section .text +.align 2 +.ent xmb_manager_register +.type xmb_manager_register, @function +xmb_manager_register: + swi r5, r0, xmb_manager_baseaddr + swi r6, r0, xmb_manager_crval + swi r7, r0, xmb_manager_callback + swi r8, r0, xmb_manager_dev + swi r9, r0, xmb_manager_reset_callback + + rtsd r15, 8; + nop; +.end xmb_manager_register +#endif + ENTRY(_reset) VM_OFF brai 0; /* Jump to reset vector */ @@ -964,19 +1240,43 @@ ENTRY(_reset) /* These are compiled and loaded into high memory, then * copied into place in mach_early_setup */ .section .init.ivt, "ax" -#if CONFIG_MANUAL_RESET_VECTOR +#if CONFIG_MANUAL_RESET_VECTOR && !defined(CONFIG_MB_MANAGER) .org 0x0 brai CONFIG_MANUAL_RESET_VECTOR +#elif defined(CONFIG_MB_MANAGER) + .org 0x0 + brai TOPHYS(_xtmr_manager_reset); #endif .org 0x8 brai TOPHYS(_user_exception); /* syscall handler */ .org 0x10 brai TOPHYS(_interrupt); /* Interrupt handler */ +#ifdef CONFIG_MB_MANAGER + .org 0x18 + brai TOPHYS(_xmb_manager_break); /* microblaze manager break handler */ +#else .org 0x18 brai TOPHYS(_debug_exception); /* debug trap handler */ +#endif .org 0x20 brai TOPHYS(_hw_exception_handler); /* HW exception handler */ +#ifdef CONFIG_MB_MANAGER + /* + * For TMR Inject API which injects the error should + * be executed from LMB. + * TMR Inject is programmed with address of 0x200 so that + * when program counter matches with this address error will + * be injected. 0x200 is expected to be next available bram + * offset, hence used for this api. + */ + .org XMB_INJECT_ERR_OFFSET +xmb_inject_error: + nop + rtsd r15, 8 + nop +#endif + .section .rodata,"a" #include "syscall_table.S" diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index b494d8d39290..edaec93a1a1f 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -955,13 +955,11 @@ enum emulation_result kvm_mips_emul_wait(struct kvm_vcpu *vcpu) kvm_vcpu_halt(vcpu); /* - * We we are runnable, then definitely go off to user space to + * We are runnable, then definitely go off to user space to * check if any I/O interrupts are pending. */ - if (kvm_check_request(KVM_REQ_UNHALT, vcpu)) { - kvm_clear_request(KVM_REQ_UNHALT, vcpu); + if (kvm_arch_vcpu_runnable(vcpu)) vcpu->run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; - } } return EMULATE_DONE; diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 4c466acdc70d..81c9f895d690 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -135,8 +135,9 @@ config PPC select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE && PPC_BOOK3S_64 select ARCH_HAS_SET_MEMORY select ARCH_HAS_STRICT_KERNEL_RWX if (PPC_BOOK3S || PPC_8xx || 40x) && !HIBERNATION - select ARCH_HAS_STRICT_KERNEL_RWX if FSL_BOOKE && !HIBERNATION && !RANDOMIZE_BASE + select ARCH_HAS_STRICT_KERNEL_RWX if PPC_85xx && !HIBERNATION && !RANDOMIZE_BASE select ARCH_HAS_STRICT_MODULE_RWX if ARCH_HAS_STRICT_KERNEL_RWX + select ARCH_HAS_SYSCALL_WRAPPER if !SPU_BASE && !COMPAT select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAS_UACCESS_FLUSHCACHE select ARCH_HAS_UBSAN_SANITIZE_ALL @@ -194,7 +195,7 @@ config PPC select HAVE_ARCH_KASAN if PPC_RADIX_MMU select HAVE_ARCH_KASAN if PPC_BOOK3E_64 select HAVE_ARCH_KASAN_VMALLOC if HAVE_ARCH_KASAN - select HAVE_ARCH_KFENCE if PPC_BOOK3S_32 || PPC_8xx || 40x + select HAVE_ARCH_KFENCE if ARCH_SUPPORTS_DEBUG_PAGEALLOC select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET select HAVE_ARCH_KGDB select HAVE_ARCH_MMAP_RND_BITS @@ -211,7 +212,7 @@ config PPC select HAVE_DYNAMIC_FTRACE_WITH_ARGS if MPROFILE_KERNEL || PPC32 select HAVE_DYNAMIC_FTRACE_WITH_REGS if MPROFILE_KERNEL || PPC32 select HAVE_EBPF_JIT - select HAVE_EFFICIENT_UNALIGNED_ACCESS if !(CPU_LITTLE_ENDIAN && POWER7_CPU) + select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_FAST_GUP select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_DESCRIPTORS if PPC64_ELF_ABI_V1 @@ -290,7 +291,7 @@ config PPC_LONG_DOUBLE_128 config PPC_BARRIER_NOSPEC bool default y - depends on PPC_BOOK3S_64 || PPC_FSL_BOOK3E + depends on PPC_BOOK3S_64 || PPC_E500 config EARLY_PRINTK bool @@ -548,7 +549,7 @@ config PPC64_SUPPORTS_MEMORY_FAILURE config KEXEC bool "kexec system call" - depends on (PPC_BOOK3S || FSL_BOOKE || (44x && !SMP)) || PPC_BOOK3E + depends on PPC_BOOK3S || PPC_E500 || (44x && !SMP) select KEXEC_CORE help kexec is a system call that implements the ability to shutdown your @@ -583,7 +584,7 @@ config ARCH_HAS_KEXEC_PURGATORY config RELOCATABLE bool "Build a relocatable kernel" - depends on PPC64 || (FLATMEM && (44x || FSL_BOOKE)) + depends on PPC64 || (FLATMEM && (44x || PPC_85xx)) select NONSTATIC_KERNEL help This builds a kernel image that is capable of running at the @@ -606,7 +607,7 @@ config RELOCATABLE config RANDOMIZE_BASE bool "Randomize the address of the kernel image" - depends on (FSL_BOOKE && FLATMEM && PPC32) + depends on PPC_85xx && FLATMEM depends on RELOCATABLE help Randomizes the virtual address at which the kernel image is @@ -625,8 +626,8 @@ config RELOCATABLE_TEST config CRASH_DUMP bool "Build a dump capture kernel" - depends on PPC64 || PPC_BOOK3S_32 || FSL_BOOKE || (44x && !SMP) - select RELOCATABLE if PPC64 || 44x || FSL_BOOKE + depends on PPC64 || PPC_BOOK3S_32 || PPC_85xx || (44x && !SMP) + select RELOCATABLE if PPC64 || 44x || PPC_85xx help Build a kernel suitable for use as a dump capture kernel. The same kernel binary can be used as production kernel and dump @@ -815,7 +816,7 @@ config DATA_SHIFT_BOOL depends on ADVANCED_OPTIONS depends on STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE depends on PPC_BOOK3S_32 || (PPC_8xx && !PIN_TLB_DATA && !STRICT_KERNEL_RWX) || \ - FSL_BOOKE + PPC_85xx help This option allows you to set the kernel data alignment. When RAM is mapped by blocks, the alignment needs to fit the size and @@ -828,13 +829,13 @@ config DATA_SHIFT default 24 if STRICT_KERNEL_RWX && PPC64 range 17 28 if (STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE) && PPC_BOOK3S_32 range 19 23 if (STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE) && PPC_8xx - range 20 24 if (STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE) && PPC_FSL_BOOKE + range 20 24 if (STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE) && PPC_85xx default 22 if STRICT_KERNEL_RWX && PPC_BOOK3S_32 default 18 if (DEBUG_PAGEALLOC || KFENCE) && PPC_BOOK3S_32 default 23 if STRICT_KERNEL_RWX && PPC_8xx default 23 if (DEBUG_PAGEALLOC || KFENCE) && PPC_8xx && PIN_TLB_DATA default 19 if (DEBUG_PAGEALLOC || KFENCE) && PPC_8xx - default 24 if STRICT_KERNEL_RWX && FSL_BOOKE + default 24 if STRICT_KERNEL_RWX && PPC_85xx default PPC_PAGE_SHIFT help On Book3S 32 (603+), DBATs are used to map kernel text and rodata RO. @@ -1150,7 +1151,7 @@ config LOWMEM_SIZE config LOWMEM_CAM_NUM_BOOL bool "Set number of CAMs to use to map low memory" - depends on ADVANCED_OPTIONS && FSL_BOOKE + depends on ADVANCED_OPTIONS && PPC_85xx help This option allows you to set the maximum number of CAM slots that will be used to map low memory. There are a limited number of slots @@ -1161,7 +1162,7 @@ config LOWMEM_CAM_NUM_BOOL Say N here unless you know what you are doing. config LOWMEM_CAM_NUM - depends on FSL_BOOKE + depends on PPC_85xx int "Number of CAMs to use to map low memory" if LOWMEM_CAM_NUM_BOOL default 3 if !STRICT_KERNEL_RWX default 9 if DATA_SHIFT >= 24 @@ -1170,7 +1171,7 @@ config LOWMEM_CAM_NUM config DYNAMIC_MEMSTART bool "Enable page aligned dynamic load address for kernel" - depends on ADVANCED_OPTIONS && FLATMEM && (FSL_BOOKE || 44x) + depends on ADVANCED_OPTIONS && FLATMEM && (PPC_85xx || 44x) select NONSTATIC_KERNEL help This option enables the kernel to be loaded at any page aligned @@ -1219,7 +1220,7 @@ config KERNEL_START config PHYSICAL_START_BOOL bool "Set physical address where the kernel is loaded" - depends on ADVANCED_OPTIONS && FLATMEM && FSL_BOOKE + depends on ADVANCED_OPTIONS && FLATMEM && PPC_85xx help This gives the physical address where the kernel is loaded. @@ -1232,7 +1233,7 @@ config PHYSICAL_START config PHYSICAL_ALIGN hex - default "0x04000000" if FSL_BOOKE + default "0x04000000" if PPC_85xx help This value puts the alignment restrictions on physical address where kernel is loaded and run from. Kernel is compiled for an diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug index ae727d4218b9..6aaf8dc60610 100644 --- a/arch/powerpc/Kconfig.debug +++ b/arch/powerpc/Kconfig.debug @@ -283,6 +283,12 @@ config PPC_EARLY_DEBUG_MEMCONS This console provides input and output buffers stored within the kernel BSS and should be safe to select on any system. A debugger can then be used to read kernel output or send input to the console. + +config PPC_EARLY_DEBUG_16550 + bool "Serial 16550" + depends on PPC_UDBG_16550 + help + Select this to enable early debugging via Serial 16550 console endchoice config PPC_MEMCONS_OUTPUT_SIZE @@ -354,6 +360,15 @@ config PPC_EARLY_DEBUG_CPM_ADDR platform probing is done, all platforms selected must share the same address. +config PPC_EARLY_DEBUG_16550_PHYSADDR + hex "Early debug Serial 16550 physical address" + depends on PPC_EARLY_DEBUG_16550 + +config PPC_EARLY_DEBUG_16550_STRIDE + int "Early debug Serial 16550 stride" + depends on PPC_EARLY_DEBUG_16550 + default 1 + config FAIL_IOMMU bool "Fault-injection capability for IOMMU" depends on FAULT_INJECTION diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 02742facf895..19470d29de16 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -149,11 +149,12 @@ CFLAGS-$(CONFIG_PPC32) += $(call cc-option,-mno-readonly-in-sdata) ifdef CONFIG_PPC_BOOK3S_64 ifdef CONFIG_CPU_LITTLE_ENDIAN CFLAGS-$(CONFIG_GENERIC_CPU) += -mcpu=power8 -CFLAGS-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=power9,-mtune=power8) else -CFLAGS-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=power7,$(call cc-option,-mtune=power5)) -CFLAGS-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mcpu=power5,-mcpu=power4) +CFLAGS-$(CONFIG_GENERIC_CPU) += -mcpu=power4 endif +CFLAGS-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=power10, \ + $(call cc-option,-mtune=power9, \ + $(call cc-option,-mtune=power8))) else ifdef CONFIG_PPC_BOOK3E_64 CFLAGS-$(CONFIG_GENERIC_CPU) += -mcpu=powerpc64 endif @@ -191,9 +192,14 @@ ifdef CONFIG_476FPE_ERR46 -T $(srctree)/arch/powerpc/platforms/44x/ppc476_modules.lds endif -# No AltiVec or VSX instructions when building kernel +# No prefix or pcrel +KBUILD_CFLAGS += $(call cc-option,-mno-prefixed) +KBUILD_CFLAGS += $(call cc-option,-mno-pcrel) + +# No AltiVec or VSX or MMA instructions when building kernel KBUILD_CFLAGS += $(call cc-option,-mno-altivec) KBUILD_CFLAGS += $(call cc-option,-mno-vsx) +KBUILD_CFLAGS += $(call cc-option,-mno-mma) # No SPE instruction when building kernel # (We use all available options to help semi-broken compilers) @@ -210,7 +216,7 @@ KBUILD_CFLAGS += $(call cc-option,-mno-string) cpu-as-$(CONFIG_40x) += -Wa,-m405 cpu-as-$(CONFIG_44x) += -Wa,-m440 cpu-as-$(CONFIG_ALTIVEC) += $(call as-option,-Wa$(comma)-maltivec) -cpu-as-$(CONFIG_E500) += -Wa,-me500 +cpu-as-$(CONFIG_PPC_E500) += -Wa,-me500 # When using '-many -mpower4' gas will first try and find a matching power4 # mnemonic and failing that it will allow any valid mnemonic that GAS knows @@ -231,7 +237,7 @@ head-$(CONFIG_PPC_BOOK3S_32) := arch/powerpc/kernel/head_book3s_32.o head-$(CONFIG_PPC_8xx) := arch/powerpc/kernel/head_8xx.o head-$(CONFIG_40x) := arch/powerpc/kernel/head_40x.o head-$(CONFIG_44x) := arch/powerpc/kernel/head_44x.o -head-$(CONFIG_FSL_BOOKE) := arch/powerpc/kernel/head_fsl_booke.o +head-$(CONFIG_PPC_85xx) := arch/powerpc/kernel/head_85xx.o head-$(CONFIG_PPC64) += arch/powerpc/kernel/entry_64.o head-$(CONFIG_PPC_FPU) += arch/powerpc/kernel/fpu.o diff --git a/arch/powerpc/boot/44x.h b/arch/powerpc/boot/44x.h index 02563443788a..9b15e59522d6 100644 --- a/arch/powerpc/boot/44x.h +++ b/arch/powerpc/boot/44x.h @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * PowerPC 44x related functions * * Copyright 2007 David Gibson, IBM Corporation. - * - * This file is licensed under the terms of the GNU General Public - * License version 2. This program is licensed "as is" without any - * warranty of any kind, whether express or implied. */ #ifndef _PPC_BOOT_44X_H_ #define _PPC_BOOT_44X_H_ diff --git a/arch/powerpc/boot/4xx.h b/arch/powerpc/boot/4xx.h index 7dc5d45361bc..77f15d124c81 100644 --- a/arch/powerpc/boot/4xx.h +++ b/arch/powerpc/boot/4xx.h @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * PowerPC 4xx related functions * * Copyright 2007 IBM Corporation. * Josh Boyer - * - * This file is licensed under the terms of the GNU General Public - * License version 2. This program is licensed "as is" without any - * warranty of any kind, whether express or implied. */ #ifndef _POWERPC_BOOT_4XX_H_ #define _POWERPC_BOOT_4XX_H_ diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index a9cd2ea4a861..d32d95aea5d6 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -34,6 +34,7 @@ endif BOOTCFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -O2 -msoft-float -mno-altivec -mno-vsx \ + $(call cc-option,-mno-spe) $(call cc-option,-mspe=no) \ -pipe -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \ $(LINUXINCLUDE) diff --git a/arch/powerpc/boot/dts/fsl/e500v1_power_isa.dtsi b/arch/powerpc/boot/dts/fsl/e500v1_power_isa.dtsi new file mode 100644 index 000000000000..7e2a90cde72e --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/e500v1_power_isa.dtsi @@ -0,0 +1,51 @@ +/* + * e500v1 Power ISA Device Tree Source (include) + * + * Copyright 2012 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +/ { + cpus { + power-isa-version = "2.03"; + power-isa-b; // Base + power-isa-e; // Embedded + power-isa-atb; // Alternate Time Base + power-isa-cs; // Cache Specification + power-isa-e.le; // Embedded.Little-Endian + power-isa-e.pm; // Embedded.Performance Monitor + power-isa-ecl; // Embedded Cache Locking + power-isa-mmc; // Memory Coherence + power-isa-sp; // Signal Processing Engine + power-isa-sp.fs; // SPE.Embedded Float Scalar Single + power-isa-sp.fv; // SPE.Embedded Float Vector + mmu-type = "power-embedded"; + }; +}; diff --git a/arch/powerpc/boot/dts/fsl/mpc8540ads.dts b/arch/powerpc/boot/dts/fsl/mpc8540ads.dts index 18a885130538..e03ae130162b 100644 --- a/arch/powerpc/boot/dts/fsl/mpc8540ads.dts +++ b/arch/powerpc/boot/dts/fsl/mpc8540ads.dts @@ -7,7 +7,7 @@ /dts-v1/; -/include/ "e500v2_power_isa.dtsi" +/include/ "e500v1_power_isa.dtsi" / { model = "MPC8540ADS"; diff --git a/arch/powerpc/boot/dts/fsl/mpc8541cds.dts b/arch/powerpc/boot/dts/fsl/mpc8541cds.dts index ac381e7b1c60..a2a6c5cf852e 100644 --- a/arch/powerpc/boot/dts/fsl/mpc8541cds.dts +++ b/arch/powerpc/boot/dts/fsl/mpc8541cds.dts @@ -7,7 +7,7 @@ /dts-v1/; -/include/ "e500v2_power_isa.dtsi" +/include/ "e500v1_power_isa.dtsi" / { model = "MPC8541CDS"; diff --git a/arch/powerpc/boot/dts/fsl/mpc8555cds.dts b/arch/powerpc/boot/dts/fsl/mpc8555cds.dts index 9f58db2a7e66..901b6ff06dfb 100644 --- a/arch/powerpc/boot/dts/fsl/mpc8555cds.dts +++ b/arch/powerpc/boot/dts/fsl/mpc8555cds.dts @@ -7,7 +7,7 @@ /dts-v1/; -/include/ "e500v2_power_isa.dtsi" +/include/ "e500v1_power_isa.dtsi" / { model = "MPC8555CDS"; diff --git a/arch/powerpc/boot/dts/fsl/mpc8560ads.dts b/arch/powerpc/boot/dts/fsl/mpc8560ads.dts index a24722ccaebf..c2f9aea78b29 100644 --- a/arch/powerpc/boot/dts/fsl/mpc8560ads.dts +++ b/arch/powerpc/boot/dts/fsl/mpc8560ads.dts @@ -7,7 +7,7 @@ /dts-v1/; -/include/ "e500v2_power_isa.dtsi" +/include/ "e500v1_power_isa.dtsi" / { model = "MPC8560ADS"; diff --git a/arch/powerpc/boot/dts/ksi8560.dts b/arch/powerpc/boot/dts/ksi8560.dts index fe6c17c8812a..37a7eb576d02 100644 --- a/arch/powerpc/boot/dts/ksi8560.dts +++ b/arch/powerpc/boot/dts/ksi8560.dts @@ -14,6 +14,8 @@ /dts-v1/; +/include/ "fsl/e500v1_power_isa.dtsi" + / { model = "KSI8560"; compatible = "emerson,KSI8560"; diff --git a/arch/powerpc/boot/dts/mgcoge.dts b/arch/powerpc/boot/dts/mgcoge.dts index 7de068991bde..9cefed207234 100644 --- a/arch/powerpc/boot/dts/mgcoge.dts +++ b/arch/powerpc/boot/dts/mgcoge.dts @@ -225,13 +225,6 @@ interrupts = <2 8>; interrupt-parent = <&PIC>; cs-gpios = < &cpm2_pio_d 19 0>; - #address-cells = <1>; - #size-cells = <0>; - ds3106@1 { - compatible = "gen,spidev"; - reg = <0>; - spi-max-frequency = <8000000>; - }; }; }; diff --git a/arch/powerpc/boot/dts/stx_gp3_8560.dts b/arch/powerpc/boot/dts/stx_gp3_8560.dts index d1ab698eef36..e73f7e75b0b4 100644 --- a/arch/powerpc/boot/dts/stx_gp3_8560.dts +++ b/arch/powerpc/boot/dts/stx_gp3_8560.dts @@ -7,6 +7,8 @@ /dts-v1/; +/include/ "fsl/e500v1_power_isa.dtsi" + / { model = "stx,gp3"; compatible = "stx,gp3-8560", "stx,gp3"; diff --git a/arch/powerpc/boot/dts/stxssa8555.dts b/arch/powerpc/boot/dts/stxssa8555.dts index 5dca2a91c41f..96add25c904b 100644 --- a/arch/powerpc/boot/dts/stxssa8555.dts +++ b/arch/powerpc/boot/dts/stxssa8555.dts @@ -9,6 +9,8 @@ /dts-v1/; +/include/ "fsl/e500v1_power_isa.dtsi" + / { model = "stx,gp3"; compatible = "stx,gp3-8560", "stx,gp3"; diff --git a/arch/powerpc/boot/dts/tqm8540.dts b/arch/powerpc/boot/dts/tqm8540.dts index 9c1eb9779108..eb4d8fd3f7aa 100644 --- a/arch/powerpc/boot/dts/tqm8540.dts +++ b/arch/powerpc/boot/dts/tqm8540.dts @@ -7,6 +7,8 @@ /dts-v1/; +/include/ "fsl/e500v1_power_isa.dtsi" + / { model = "tqc,tqm8540"; compatible = "tqc,tqm8540"; diff --git a/arch/powerpc/boot/dts/tqm8541.dts b/arch/powerpc/boot/dts/tqm8541.dts index 44595cf675d0..fe5d3d873ec9 100644 --- a/arch/powerpc/boot/dts/tqm8541.dts +++ b/arch/powerpc/boot/dts/tqm8541.dts @@ -7,6 +7,8 @@ /dts-v1/; +/include/ "fsl/e500v1_power_isa.dtsi" + / { model = "tqc,tqm8541"; compatible = "tqc,tqm8541"; diff --git a/arch/powerpc/boot/dts/tqm8555.dts b/arch/powerpc/boot/dts/tqm8555.dts index 54f3e82907d6..4be05b7d225d 100644 --- a/arch/powerpc/boot/dts/tqm8555.dts +++ b/arch/powerpc/boot/dts/tqm8555.dts @@ -7,6 +7,8 @@ /dts-v1/; +/include/ "fsl/e500v1_power_isa.dtsi" + / { model = "tqc,tqm8555"; compatible = "tqc,tqm8555"; diff --git a/arch/powerpc/boot/dts/tqm8560.dts b/arch/powerpc/boot/dts/tqm8560.dts index 7415cb69f60d..8ea48502420b 100644 --- a/arch/powerpc/boot/dts/tqm8560.dts +++ b/arch/powerpc/boot/dts/tqm8560.dts @@ -8,6 +8,8 @@ /dts-v1/; +/include/ "fsl/e500v1_power_isa.dtsi" + / { model = "tqc,tqm8560"; compatible = "tqc,tqm8560"; diff --git a/arch/powerpc/boot/dts/turris1x.dts b/arch/powerpc/boot/dts/turris1x.dts index 12e08271e61f..045af668e928 100644 --- a/arch/powerpc/boot/dts/turris1x.dts +++ b/arch/powerpc/boot/dts/turris1x.dts @@ -147,7 +147,7 @@ port@0 { reg = <0>; - label = "cpu1"; + label = "cpu"; ethernet = <&enet1>; phy-mode = "rgmii-id"; @@ -184,7 +184,7 @@ port@6 { reg = <6>; - label = "cpu0"; + label = "cpu"; ethernet = <&enet0>; phy-mode = "rgmii-id"; @@ -263,21 +263,21 @@ }; partition@20000 { - /* 1.7 MB for Rescue Linux Kernel Image */ + /* 1.7 MB for Linux Kernel Image */ reg = <0x00020000 0x001a0000>; - label = "rescue-kernel"; + label = "kernel"; }; partition@1c0000 { /* 1.5 MB for Rescue JFFS2 Root File System */ reg = <0x001c0000 0x00180000>; - label = "rescue-rootfs"; + label = "rescue"; }; partition@340000 { - /* 11 MB for TAR.XZ Backup with content of NAND Root File System */ + /* 11 MB for TAR.XZ Archive with Factory content of NAND Root File System */ reg = <0x00340000 0x00b00000>; - label = "backup-rootfs"; + label = "factory"; }; partition@e40000 { diff --git a/arch/powerpc/boot/dummy.c b/arch/powerpc/boot/dummy.c deleted file mode 100644 index 31dbf45bf99c..000000000000 --- a/arch/powerpc/boot/dummy.c +++ /dev/null @@ -1,4 +0,0 @@ -int main(void) -{ - return 0; -} diff --git a/arch/powerpc/boot/opal-calls.S b/arch/powerpc/boot/opal-calls.S index ad0e15d930c4..1f2f330a459e 100644 --- a/arch/powerpc/boot/opal-calls.S +++ b/arch/powerpc/boot/opal-calls.S @@ -16,7 +16,7 @@ opal_kentry: li r5, 0 li r6, 0 li r7, 0 - ld r11,opal@got(r2) + LOAD_REG_ADDR(r11, opal) ld r8,0(r11) ld r9,8(r11) bctr @@ -35,7 +35,7 @@ opal_call: mr r13,r2 /* Set opal return address */ - ld r11,opal_return@got(r2) + LOAD_REG_ADDR(r11, opal_return) mtlr r11 mfmsr r12 @@ -45,7 +45,7 @@ opal_call: mtspr SPRN_HSRR1,r12 /* load the opal call entry point and base */ - ld r11,opal@got(r2) + LOAD_REG_ADDR(r11, opal) ld r12,8(r11) ld r2,0(r11) mtspr SPRN_HSRR0,r12 diff --git a/arch/powerpc/boot/ops.h b/arch/powerpc/boot/ops.h index 8334bc3cbe49..a40c2162a4e9 100644 --- a/arch/powerpc/boot/ops.h +++ b/arch/powerpc/boot/ops.h @@ -1,12 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Global definition of all the bootwrapper operations. * * Author: Mark A. Greer * - * 2006 (c) MontaVista Software, Inc. This file is licensed under - * the terms of the GNU General Public License version 2. This program - * is licensed "as is" without any warranty of any kind, whether express - * or implied. + * 2006 (c) MontaVista Software, Inc. */ #ifndef _PPC_BOOT_OPS_H_ #define _PPC_BOOT_OPS_H_ diff --git a/arch/powerpc/boot/ppc_asm.h b/arch/powerpc/boot/ppc_asm.h index 192b97523b05..a66cfd76fa4d 100644 --- a/arch/powerpc/boot/ppc_asm.h +++ b/arch/powerpc/boot/ppc_asm.h @@ -84,4 +84,14 @@ #define MFTBU(dest) mfspr dest, SPRN_TBRU #endif +#ifdef CONFIG_PPC64_BOOT_WRAPPER +#define LOAD_REG_ADDR(reg,name) \ + addis reg,r2,name@toc@ha; \ + addi reg,reg,name@toc@l +#else +#define LOAD_REG_ADDR(reg,name) \ + lis reg,name@ha; \ + addi reg,reg,name@l +#endif + #endif /* _PPC64_PPC_ASM_H */ diff --git a/arch/powerpc/boot/serial.c b/arch/powerpc/boot/serial.c index 54d2522be485..c6d32a8c3612 100644 --- a/arch/powerpc/boot/serial.c +++ b/arch/powerpc/boot/serial.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Generic serial console support * @@ -6,10 +7,7 @@ * Code in serial_edit_cmdline() copied from * and was written by Matt Porter . * - * 2001,2006 (c) MontaVista Software, Inc. This file is licensed under - * the terms of the GNU General Public License version 2. This program - * is licensed "as is" without any warranty of any kind, whether express - * or implied. + * 2001,2006 (c) MontaVista Software, Inc. */ #include #include diff --git a/arch/powerpc/boot/simple_alloc.c b/arch/powerpc/boot/simple_alloc.c index 65ec135d0157..267d6524caac 100644 --- a/arch/powerpc/boot/simple_alloc.c +++ b/arch/powerpc/boot/simple_alloc.c @@ -1,12 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Implement primitive realloc(3) functionality. * * Author: Mark A. Greer * - * 2006 (c) MontaVista, Software, Inc. This file is licensed under - * the terms of the GNU General Public License version 2. This program - * is licensed "as is" without any warranty of any kind, whether express - * or implied. + * 2006 (c) MontaVista, Software, Inc. */ #include diff --git a/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig b/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig index cbcae2a927e9..4e3373381ab6 100644 --- a/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig +++ b/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig @@ -77,6 +77,5 @@ CONFIG_NFS_FS=y CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y CONFIG_CRC_T10DIF=y -# CONFIG_ENABLE_MUST_CHECK is not set CONFIG_CRYPTO_ECB=m CONFIG_CRYPTO_PCBC=m diff --git a/arch/powerpc/configs/85xx/ge_imp3a_defconfig b/arch/powerpc/configs/85xx/ge_imp3a_defconfig index f29c166998af..e6d878a44d33 100644 --- a/arch/powerpc/configs/85xx/ge_imp3a_defconfig +++ b/arch/powerpc/configs/85xx/ge_imp3a_defconfig @@ -74,7 +74,6 @@ CONFIG_MTD_PHYSMAP_OF=y CONFIG_MTD_RAW_NAND=y CONFIG_MTD_NAND_FSL_ELBC=y CONFIG_BLK_DEV_LOOP=m -CONFIG_BLK_DEV_CRYPTOLOOP=m CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=131072 diff --git a/arch/powerpc/configs/85xx/ppa8548_defconfig b/arch/powerpc/configs/85xx/ppa8548_defconfig index 190978a5b7d5..4bd5f993d26a 100644 --- a/arch/powerpc/configs/85xx/ppa8548_defconfig +++ b/arch/powerpc/configs/85xx/ppa8548_defconfig @@ -7,9 +7,7 @@ CONFIG_RAPIDIO=y CONFIG_FSL_RIO=y CONFIG_RAPIDIO_DMA_ENGINE=y CONFIG_RAPIDIO_ENUM_BASIC=y -CONFIG_RAPIDIO_TSI57X=y CONFIG_RAPIDIO_CPS_XX=y -CONFIG_RAPIDIO_TSI568=y CONFIG_RAPIDIO_CPS_GEN2=y CONFIG_ADVANCED_OPTIONS=y CONFIG_LOWMEM_SIZE_BOOL=y diff --git a/arch/powerpc/configs/cell_defconfig b/arch/powerpc/configs/cell_defconfig index 7fd9e596ea33..06391cc2af3a 100644 --- a/arch/powerpc/configs/cell_defconfig +++ b/arch/powerpc/configs/cell_defconfig @@ -195,7 +195,6 @@ CONFIG_NLS_ISO8859_9=m CONFIG_NLS_ISO8859_13=m CONFIG_NLS_ISO8859_14=m CONFIG_NLS_ISO8859_15=m -# CONFIG_ENABLE_MUST_CHECK is not set CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_MUTEXES=y diff --git a/arch/powerpc/configs/g5_defconfig b/arch/powerpc/configs/g5_defconfig index 9d6212a8b195..71d9d112c0b6 100644 --- a/arch/powerpc/configs/g5_defconfig +++ b/arch/powerpc/configs/g5_defconfig @@ -119,7 +119,6 @@ CONFIG_INPUT_EVDEV=y # CONFIG_SERIO_I8042 is not set # CONFIG_SERIO_SERPORT is not set # CONFIG_HW_RANDOM is not set -CONFIG_RAW_DRIVER=y CONFIG_I2C_CHARDEV=y CONFIG_AGP=m CONFIG_AGP_UNINORTH=m diff --git a/arch/powerpc/configs/microwatt_defconfig b/arch/powerpc/configs/microwatt_defconfig index eff933ebbb9e..ea2dbd778aad 100644 --- a/arch/powerpc/configs/microwatt_defconfig +++ b/arch/powerpc/configs/microwatt_defconfig @@ -75,7 +75,12 @@ CONFIG_SPI_BITBANG=y CONFIG_SPI_SPIDEV=y # CONFIG_HWMON is not set # CONFIG_USB_SUPPORT is not set +CONFIG_MMC=y +# CONFIG_PWRSEQ_EMMC is not set +# CONFIG_PWRSEQ_SIMPLE is not set +CONFIG_MMC_LITEX=y # CONFIG_VIRTIO_MENU is not set +CONFIG_COMMON_CLK=y # CONFIG_IOMMU_SUPPORT is not set # CONFIG_NVMEM is not set CONFIG_EXT4_FS=y diff --git a/arch/powerpc/configs/mpc512x_defconfig b/arch/powerpc/configs/mpc512x_defconfig index e75d3f3060c9..10fe061c5e6d 100644 --- a/arch/powerpc/configs/mpc512x_defconfig +++ b/arch/powerpc/configs/mpc512x_defconfig @@ -114,5 +114,4 @@ CONFIG_NFS_FS=y CONFIG_ROOT_NFS=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y -# CONFIG_ENABLE_MUST_CHECK is not set # CONFIG_CRYPTO_HW is not set diff --git a/arch/powerpc/configs/mpc885_ads_defconfig b/arch/powerpc/configs/mpc885_ads_defconfig index 700115d85d6f..56b876e418e9 100644 --- a/arch/powerpc/configs/mpc885_ads_defconfig +++ b/arch/powerpc/configs/mpc885_ads_defconfig @@ -78,4 +78,4 @@ CONFIG_DEBUG_VM_PGTABLE=y CONFIG_DETECT_HUNG_TASK=y CONFIG_BDI_SWITCH=y CONFIG_PPC_EARLY_DEBUG=y -CONFIG_PPC_PTDUMP=y +CONFIG_GENERIC_PTDUMP=y diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig index e00a703581c3..96aa5355911f 100644 --- a/arch/powerpc/configs/pasemi_defconfig +++ b/arch/powerpc/configs/pasemi_defconfig @@ -92,7 +92,6 @@ CONFIG_LEGACY_PTY_COUNT=4 CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_HW_RANDOM=y -CONFIG_RAW_DRIVER=y CONFIG_I2C_CHARDEV=y CONFIG_I2C_PASEMI=y CONFIG_SENSORS_LM85=y diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig index 13885ec563d1..019163c2571e 100644 --- a/arch/powerpc/configs/pmac32_defconfig +++ b/arch/powerpc/configs/pmac32_defconfig @@ -284,7 +284,6 @@ CONFIG_BOOTX_TEXT=y CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_SHA512=m -CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_ANUBIS=m CONFIG_CRYPTO_BLOWFISH=m diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig index 49f49c263935..43e38f0fa5a7 100644 --- a/arch/powerpc/configs/powernv_defconfig +++ b/arch/powerpc/configs/powernv_defconfig @@ -50,6 +50,7 @@ CONFIG_CPU_IDLE=y CONFIG_HZ_100=y CONFIG_BINFMT_MISC=m CONFIG_PPC_TRANSACTIONAL_MEM=y +CONFIG_PPC_UV=y CONFIG_HOTPLUG_CPU=y CONFIG_KEXEC=y CONFIG_KEXEC_FILE=y @@ -65,6 +66,8 @@ CONFIG_DEFERRED_STRUCT_PAGE_INIT=y CONFIG_SCHED_SMT=y CONFIG_PM=y CONFIG_HOTPLUG_PCI=y +CONFIG_ZONE_DEVICE=y +CONFIG_DEVICE_PRIVATE=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -252,7 +255,6 @@ CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_GENERIC=y # CONFIG_VIRTIO_MENU is not set CONFIG_LIBNVDIMM=y -# CONFIG_ND_BLK is not set CONFIG_EXT2_FS=y CONFIG_EXT2_FS_XATTR=y CONFIG_EXT2_FS_POSIX_ACL=y @@ -325,13 +327,11 @@ CONFIG_CRYPTO_MD5_PPC=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_SHA1_PPC=m CONFIG_CRYPTO_SHA256=y -CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_ANUBIS=m CONFIG_CRYPTO_BLOWFISH=m CONFIG_CRYPTO_CAST6=m CONFIG_CRYPTO_KHAZAD=m -CONFIG_CRYPTO_SALSA20=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index c8b0e80d613b..d6949a6c5b2b 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -1,7 +1,9 @@ CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y +# CONFIG_CONTEXT_TRACKING_USER_FORCE is not set CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y +CONFIG_VIRT_CPU_ACCOUNTING_GEN=y CONFIG_TASKSTATS=y CONFIG_TASK_DELAY_ACCT=y CONFIG_IKCONFIG=y @@ -213,7 +215,6 @@ CONFIG_HVC_RTAS=y CONFIG_HVCS=m CONFIG_VIRTIO_CONSOLE=m CONFIG_IBM_BSR=m -CONFIG_RAW_DRIVER=y CONFIG_I2C_CHARDEV=y CONFIG_I2C_AMD8111=y CONFIG_I2C_PASEMI=y @@ -342,13 +343,11 @@ CONFIG_CRYPTO_MD5_PPC=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_SHA1_PPC=m CONFIG_CRYPTO_SHA256=y -CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_ANUBIS=m CONFIG_CRYPTO_BLOWFISH=m CONFIG_CRYPTO_CAST6=m CONFIG_CRYPTO_KHAZAD=m -CONFIG_CRYPTO_SALSA20=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig index 5cf49a515f8e..f97a2d31bbf7 100644 --- a/arch/powerpc/configs/ppc64e_defconfig +++ b/arch/powerpc/configs/ppc64e_defconfig @@ -118,7 +118,6 @@ CONFIG_INPUT_MISC=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y # CONFIG_HW_RANDOM is not set -CONFIG_RAW_DRIVER=y CONFIG_I2C_CHARDEV=y CONFIG_I2C_AMD8111=y CONFIG_FB=y @@ -234,13 +233,11 @@ CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_HMAC=y CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_SHA512=m -CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_ANUBIS=m CONFIG_CRYPTO_BLOWFISH=m CONFIG_CRYPTO_CAST6=m CONFIG_CRYPTO_KHAZAD=m -CONFIG_CRYPTO_SALSA20=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index a24f484bfbd2..d23deb94b36e 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -321,7 +321,6 @@ CONFIG_PNP=y CONFIG_ISAPNP=y CONFIG_MAC_FLOPPY=m CONFIG_BLK_DEV_LOOP=m -CONFIG_BLK_DEV_CRYPTOLOOP=m CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=16384 @@ -590,7 +589,6 @@ CONFIG_GAMEPORT_EMU10K1=m CONFIG_GAMEPORT_FM801=m # CONFIG_LEGACY_PTYS is not set CONFIG_SERIAL_NONSTANDARD=y -CONFIG_ROCKETPORT=m CONFIG_SYNCLINK_GT=m CONFIG_NOZOMI=m CONFIG_N_HDLC=m @@ -1107,13 +1105,9 @@ CONFIG_CRYPTO_XTS=m CONFIG_CRYPTO_HMAC=y CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_MICHAEL_MIC=m -CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m -CONFIG_CRYPTO_RMD256=m -CONFIG_CRYPTO_RMD320=m CONFIG_CRYPTO_SHA1=y CONFIG_CRYPTO_SHA512=m -CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_ANUBIS=m CONFIG_CRYPTO_BLOWFISH=m @@ -1121,7 +1115,6 @@ CONFIG_CRYPTO_CAMELLIA=m CONFIG_CRYPTO_CAST6=m CONFIG_CRYPTO_FCRYPT=m CONFIG_CRYPTO_KHAZAD=m -CONFIG_CRYPTO_SALSA20=m CONFIG_CRYPTO_SEED=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig index 2d9ac233da68..0a1b42c4f26a 100644 --- a/arch/powerpc/configs/ps3_defconfig +++ b/arch/powerpc/configs/ps3_defconfig @@ -165,6 +165,5 @@ CONFIG_RCU_CPU_STALL_TIMEOUT=60 # CONFIG_FTRACE is not set CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_MICHAEL_MIC=m -CONFIG_CRYPTO_SALSA20=m CONFIG_CRYPTO_LZO=m CONFIG_PRINTK_TIME=y diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index b571d084c148..a25cf2ca5c7a 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -3,8 +3,10 @@ CONFIG_NR_CPUS=2048 CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_AUDIT=y +# CONFIG_CONTEXT_TRACKING_USER_FORCE is not set CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y +CONFIG_VIRT_CPU_ACCOUNTING_GEN=y CONFIG_TASKSTATS=y CONFIG_TASK_DELAY_ACCT=y CONFIG_TASK_XACCT=y @@ -40,6 +42,7 @@ CONFIG_PPC_SPLPAR=y CONFIG_DTL=y CONFIG_PPC_SMLPAR=y CONFIG_IBMEBUS=y +CONFIG_LIBNVDIMM=m CONFIG_PAPR_SCM=m CONFIG_PPC_SVM=y # CONFIG_PPC_PMAC is not set @@ -187,7 +190,6 @@ CONFIG_HVC_RTAS=y CONFIG_HVCS=m CONFIG_VIRTIO_CONSOLE=m CONFIG_IBM_BSR=m -CONFIG_RAW_DRIVER=y CONFIG_I2C_CHARDEV=y CONFIG_FB=y CONFIG_FIRMWARE_EDID=y @@ -302,13 +304,11 @@ CONFIG_CRYPTO_MD5_PPC=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_SHA1_PPC=m CONFIG_CRYPTO_SHA256=y -CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_ANUBIS=m CONFIG_CRYPTO_BLOWFISH=m CONFIG_CRYPTO_CAST6=m CONFIG_CRYPTO_KHAZAD=m -CONFIG_CRYPTO_SALSA20=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig index f491875700e8..e0964210f259 100644 --- a/arch/powerpc/configs/skiroot_defconfig +++ b/arch/powerpc/configs/skiroot_defconfig @@ -133,7 +133,6 @@ CONFIG_ACENIC_OMIT_TIGON_I=y # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set # CONFIG_NET_VENDOR_ATHEROS is not set -# CONFIG_NET_VENDOR_AURORA is not set CONFIG_TIGON3=m CONFIG_BNX2X=m # CONFIG_NET_VENDOR_BROCADE is not set @@ -274,7 +273,6 @@ CONFIG_NLS_UTF8=y CONFIG_ENCRYPTED_KEYS=y CONFIG_SECURITY=y CONFIG_HARDENED_USERCOPY=y -CONFIG_HARDENED_USERCOPY_PAGESPAN=y CONFIG_FORTIFY_SOURCE=y CONFIG_SECURITY_LOCKDOWN_LSM=y CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y diff --git a/arch/powerpc/configs/storcenter_defconfig b/arch/powerpc/configs/storcenter_defconfig index 47dcfaddc1ac..7a978d396991 100644 --- a/arch/powerpc/configs/storcenter_defconfig +++ b/arch/powerpc/configs/storcenter_defconfig @@ -76,4 +76,3 @@ CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y CONFIG_NLS_UTF8=y CONFIG_CRC_T10DIF=y -# CONFIG_ENABLE_MUST_CHECK is not set diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index 81631e64dbeb..274bce76f5da 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -36,6 +36,7 @@ int64_t __opal_call(int64_t a0, int64_t a1, int64_t a2, int64_t a3, int64_t opcode, uint64_t msr); /* misc runtime */ +void enable_machine_check(void); extern u64 __bswapdi2(u64); extern s64 __lshrdi3(s64, int); extern s64 __ashldi3(s64, int); @@ -55,19 +56,6 @@ struct kvm_vcpu; void _kvmppc_restore_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr); void _kvmppc_save_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr); -/* Patch sites */ -extern s32 patch__call_flush_branch_caches1; -extern s32 patch__call_flush_branch_caches2; -extern s32 patch__call_flush_branch_caches3; -extern s32 patch__flush_count_cache_return; -extern s32 patch__flush_link_stack_return; -extern s32 patch__call_kvm_flush_link_stack; -extern s32 patch__call_kvm_flush_link_stack_p9; -extern s32 patch__memset_nocache, patch__memcpy_nocache; - -extern long flush_branch_caches; -extern long kvm_flush_link_stack; - #ifdef CONFIG_PPC_TRANSACTIONAL_MEM void kvmppc_save_tm_hv(struct kvm_vcpu *vcpu, u64 msr, bool preserve_nv); void kvmppc_restore_tm_hv(struct kvm_vcpu *vcpu, u64 msr, bool preserve_nv); diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h index ef2d8b15eaab..e80b2c0e9315 100644 --- a/arch/powerpc/include/asm/barrier.h +++ b/arch/powerpc/include/asm/barrier.h @@ -86,7 +86,7 @@ do { \ #ifdef CONFIG_PPC_BOOK3S_64 #define NOSPEC_BARRIER_SLOT nop -#elif defined(CONFIG_PPC_FSL_BOOK3E) +#elif defined(CONFIG_PPC_E500) #define NOSPEC_BARRIER_SLOT nop; nop #endif diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 40041ac713d9..75823f39e042 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -112,31 +112,11 @@ static inline bool pte_user(pte_t pte) /* Permission masks used for kernel mappings */ #define PAGE_KERNEL __pgprot(_PAGE_BASE | _PAGE_KERNEL_RW) #define PAGE_KERNEL_NC __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | _PAGE_NO_CACHE) -#define PAGE_KERNEL_NCG __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \ - _PAGE_NO_CACHE | _PAGE_GUARDED) +#define PAGE_KERNEL_NCG __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | _PAGE_NO_CACHE | _PAGE_GUARDED) #define PAGE_KERNEL_X __pgprot(_PAGE_BASE | _PAGE_KERNEL_RWX) #define PAGE_KERNEL_RO __pgprot(_PAGE_BASE | _PAGE_KERNEL_RO) #define PAGE_KERNEL_ROX __pgprot(_PAGE_BASE | _PAGE_KERNEL_ROX) -/* - * Protection used for kernel text. We want the debuggers to be able to - * set breakpoints anywhere, so don't write protect the kernel text - * on platforms where such control is possible. - */ -#if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH) ||\ - defined(CONFIG_KPROBES) || defined(CONFIG_DYNAMIC_FTRACE) -#define PAGE_KERNEL_TEXT PAGE_KERNEL_X -#else -#define PAGE_KERNEL_TEXT PAGE_KERNEL_ROX -#endif - -/* Make modules code happy. We don't set RO yet */ -#define PAGE_KERNEL_EXEC PAGE_KERNEL_X - -/* Advertise special mapping type for AGP */ -#define PAGE_AGP (PAGE_KERNEL_NC) -#define HAVE_PAGE_AGP - #define PTE_INDEX_SIZE PTE_SHIFT #define PMD_INDEX_SIZE 0 #define PUD_INDEX_SIZE 0 diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h index e1af0b394ceb..dd2cff53a111 100644 --- a/arch/powerpc/include/asm/book3s/64/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h @@ -113,9 +113,11 @@ static inline void __pud_free(pud_t *pud) /* * Early pud pages allocated via memblock allocator - * can't be directly freed to slab + * can't be directly freed to slab. KFENCE pages have + * both reserved and slab flags set so need to be freed + * kmem_cache_free. */ - if (PageReserved(page)) + if (PageReserved(page) && !PageSlab(page)) free_reserved_page(page); else kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), pud); diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h index 4e697bc2f4cd..48f21820afe2 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h @@ -26,16 +26,6 @@ static inline int pud_huge(pud_t pud) return 0; } -static inline int pgd_huge(pgd_t pgd) -{ - /* - * leaf pte for huge page - */ - if (radix_enabled()) - return !!(pgd_raw(pgd) & cpu_to_be64(_PAGE_PTE)); - return 0; -} -#define pgd_huge pgd_huge /* * With radix , we have hugepage ptes in the pud and pmd entries. We don't * need to setup hugepage directory for them. Our pte and page directory format diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h index 34d1018896b3..2fce3498b000 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h @@ -30,15 +30,6 @@ static inline int pud_huge(pud_t pud) return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE)); } -static inline int pgd_huge(pgd_t pgd) -{ - /* - * leaf pte for huge page - */ - return !!(pgd_raw(pgd) & cpu_to_be64(_PAGE_PTE)); -} -#define pgd_huge pgd_huge - /* * With 64k page size, we have hugepage ptes in the pgd and pmd entries. We don't * need to setup hugepage directory for them. Our pte and page directory format diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 392ff48f77df..c436d8422654 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -117,8 +117,7 @@ #define _PAGE_KERNEL_RW (_PAGE_PRIVILEGED | _PAGE_RW | _PAGE_DIRTY) #define _PAGE_KERNEL_RO (_PAGE_PRIVILEGED | _PAGE_READ) #define _PAGE_KERNEL_ROX (_PAGE_PRIVILEGED | _PAGE_READ | _PAGE_EXEC) -#define _PAGE_KERNEL_RWX (_PAGE_PRIVILEGED | _PAGE_DIRTY | \ - _PAGE_RW | _PAGE_EXEC) +#define _PAGE_KERNEL_RWX (_PAGE_PRIVILEGED | _PAGE_DIRTY | _PAGE_RW | _PAGE_EXEC) /* * _PAGE_CHG_MASK masks of bits that are to be preserved across * pgprot changes @@ -151,33 +150,17 @@ #define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC) #define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_READ) #define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC) +/* Radix only, Hash uses PAGE_READONLY_X + execute-only pkey instead */ +#define PAGE_EXECONLY __pgprot(_PAGE_BASE | _PAGE_EXEC) /* Permission masks used for kernel mappings */ #define PAGE_KERNEL __pgprot(_PAGE_BASE | _PAGE_KERNEL_RW) -#define PAGE_KERNEL_NC __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \ - _PAGE_TOLERANT) -#define PAGE_KERNEL_NCG __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \ - _PAGE_NON_IDEMPOTENT) +#define PAGE_KERNEL_NC __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | _PAGE_TOLERANT) +#define PAGE_KERNEL_NCG __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | _PAGE_NON_IDEMPOTENT) #define PAGE_KERNEL_X __pgprot(_PAGE_BASE | _PAGE_KERNEL_RWX) #define PAGE_KERNEL_RO __pgprot(_PAGE_BASE | _PAGE_KERNEL_RO) #define PAGE_KERNEL_ROX __pgprot(_PAGE_BASE | _PAGE_KERNEL_ROX) -/* - * Protection used for kernel text. We want the debuggers to be able to - * set breakpoints anywhere, so don't write protect the kernel text - * on platforms where such control is possible. - */ -#if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH) || \ - defined(CONFIG_KPROBES) || defined(CONFIG_DYNAMIC_FTRACE) -#define PAGE_KERNEL_TEXT PAGE_KERNEL_X -#else -#define PAGE_KERNEL_TEXT PAGE_KERNEL_ROX -#endif - -/* Make modules code happy. We don't set RO yet */ -#define PAGE_KERNEL_EXEC PAGE_KERNEL_X -#define PAGE_AGP (PAGE_KERNEL_NC) - #ifndef __ASSEMBLY__ /* * page table defines @@ -333,9 +316,6 @@ extern unsigned long pci_io_base; #define IOREMAP_END (KERN_IO_END - FIXADDR_SIZE) #define FIXADDR_SIZE SZ_32M -/* Advertise special mapping type for AGP */ -#define HAVE_PAGE_AGP - #ifndef __ASSEMBLY__ /* @@ -411,6 +391,9 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm, * event of it not getting flushed for a long time the delay * shouldn't really matter because there's no real memory * pressure for swapout to react to. ] + * + * Note: this optimisation also exists in pte_needs_flush() and + * huge_pmd_needs_flush(). */ #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH #define ptep_clear_flush_young ptep_test_and_clear_young @@ -1123,7 +1106,7 @@ static inline void vmemmap_remove_mapping(unsigned long start, } #endif -#ifdef CONFIG_DEBUG_PAGEALLOC +#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE) static inline void __kernel_map_pages(struct page *page, int numpages, int enable) { if (radix_enabled()) @@ -1457,12 +1440,5 @@ static inline bool pud_is_leaf(pud_t pud) return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE)); } -#define p4d_is_leaf p4d_is_leaf -#define p4d_leaf p4d_is_leaf -static inline bool p4d_is_leaf(p4d_t p4d) -{ - return !!(p4d_raw(p4d) & cpu_to_be64(_PAGE_PTE)); -} - #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ */ diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h index 8b762f282190..fab8332fe1ad 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h @@ -112,13 +112,11 @@ static inline void hash__flush_tlb_kernel_range(unsigned long start, struct mmu_gather; extern void hash__tlb_flush(struct mmu_gather *tlb); -void flush_tlb_pmd_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr); #ifdef CONFIG_PPC_64S_HASH_MMU /* Private function for use by PCI IO mapping code */ extern void __flush_hash_table_range(unsigned long start, unsigned long end); -extern void flush_tlb_pmd_range(struct mm_struct *mm, pmd_t *pmd, - unsigned long addr); +void flush_hash_table_pmd_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr); #else static inline void __flush_hash_table_range(unsigned long start, unsigned long end) { } #endif diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h index 206f920fe5b9..67655cd60545 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h @@ -163,6 +163,62 @@ static inline void flush_tlb_fix_spurious_fault(struct vm_area_struct *vma, */ } +static inline bool __pte_flags_need_flush(unsigned long oldval, + unsigned long newval) +{ + unsigned long delta = oldval ^ newval; + + /* + * The return value of this function doesn't matter for hash, + * ptep_modify_prot_start() does a pte_update() which does or schedules + * any necessary hash table update and flush. + */ + if (!radix_enabled()) + return true; + + /* + * We do not expect kernel mappings or non-PTEs or not-present PTEs. + */ + VM_WARN_ON_ONCE(oldval & _PAGE_PRIVILEGED); + VM_WARN_ON_ONCE(newval & _PAGE_PRIVILEGED); + VM_WARN_ON_ONCE(!(oldval & _PAGE_PTE)); + VM_WARN_ON_ONCE(!(newval & _PAGE_PTE)); + VM_WARN_ON_ONCE(!(oldval & _PAGE_PRESENT)); + VM_WARN_ON_ONCE(!(newval & _PAGE_PRESENT)); + + /* + * Must flush on any change except READ, WRITE, EXEC, DIRTY, ACCESSED. + * + * In theory, some changed software bits could be tolerated, in + * practice those should rarely if ever matter. + */ + + if (delta & ~(_PAGE_RWX | _PAGE_DIRTY | _PAGE_ACCESSED)) + return true; + + /* + * If any of the above was present in old but cleared in new, flush. + * With the exception of _PAGE_ACCESSED, don't worry about flushing + * if that was cleared (see the comment in ptep_clear_flush_young()). + */ + if ((delta & ~_PAGE_ACCESSED) & oldval) + return true; + + return false; +} + +static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte) +{ + return __pte_flags_need_flush(pte_val(oldpte), pte_val(newpte)); +} +#define pte_needs_flush pte_needs_flush + +static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd) +{ + return __pte_flags_need_flush(pmd_val(oldpmd), pmd_val(newpmd)); +} +#define huge_pmd_needs_flush huge_pmd_needs_flush + extern bool tlbie_capable; extern bool tlbie_enabled; diff --git a/arch/powerpc/include/asm/book3s/pgtable.h b/arch/powerpc/include/asm/book3s/pgtable.h index e8269434ecbe..d18b748ea3ae 100644 --- a/arch/powerpc/include/asm/book3s/pgtable.h +++ b/arch/powerpc/include/asm/book3s/pgtable.h @@ -25,7 +25,8 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot); #define __HAVE_PHYS_MEM_ACCESS_PROT -#if defined(CONFIG_PPC32) || defined(CONFIG_PPC_64S_HASH_MMU) +void __update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); + /* * This gets called at the end of handling a page fault, when * the kernel has put a new PTE into the page table for the process. @@ -35,10 +36,14 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, * corresponding HPTE into the hash table ahead of time, instead of * waiting for the inevitable extra hash-table miss exception. */ -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); -#else -static inline void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) {} -#endif +static inline void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) +{ + if (IS_ENABLED(CONFIG_PPC32) && !mmu_has_feature(MMU_FTR_HPTE_TABLE)) + return; + if (radix_enabled()) + return; + __update_mmu_cache(vma, address, ptep); +} #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/powerpc/include/asm/cpu_setup.h b/arch/powerpc/include/asm/cpu_setup.h new file mode 100644 index 000000000000..30e2fe389502 --- /dev/null +++ b/arch/powerpc/include/asm/cpu_setup.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2020 IBM Corporation + */ + +#ifndef _ASM_POWERPC_CPU_SETUP_H +#define _ASM_POWERPC_CPU_SETUP_H +void __setup_cpu_power7(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_power8(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_power9(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_power10(unsigned long offset, struct cpu_spec *spec); +void __restore_cpu_power7(void); +void __restore_cpu_power8(void); +void __restore_cpu_power9(void); +void __restore_cpu_power10(void); + +void __setup_cpu_e500v1(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_e500v2(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_e500mc(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_440ep(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_440epx(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_440gx(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_440grx(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_440spe(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_440x5(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_460ex(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_460gt(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_460sx(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_apm821xx(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_603(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_604(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_750(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_750cx(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_750fx(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_7400(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_7410(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_745x(unsigned long offset, struct cpu_spec *spec); + +void __setup_cpu_ppc970(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_ppc970MP(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_pa6t(unsigned long offset, struct cpu_spec *spec); +void __restore_cpu_pa6t(void); +void __restore_cpu_ppc970(void); + +void __setup_cpu_e5500(unsigned long offset, struct cpu_spec *spec); +void __setup_cpu_e6500(unsigned long offset, struct cpu_spec *spec); +void __restore_cpu_e5500(void); +void __restore_cpu_e6500(void); +#endif /* _ASM_POWERPC_CPU_SETUP_H */ diff --git a/arch/powerpc/include/asm/cpu_setup_power.h b/arch/powerpc/include/asm/cpu_setup_power.h deleted file mode 100644 index 24be9131f803..000000000000 --- a/arch/powerpc/include/asm/cpu_setup_power.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (C) 2020 IBM Corporation - */ -void __setup_cpu_power7(unsigned long offset, struct cpu_spec *spec); -void __restore_cpu_power7(void); -void __setup_cpu_power8(unsigned long offset, struct cpu_spec *spec); -void __restore_cpu_power8(void); -void __setup_cpu_power9(unsigned long offset, struct cpu_spec *spec); -void __restore_cpu_power9(void); -void __setup_cpu_power10(unsigned long offset, struct cpu_spec *spec); -void __restore_cpu_power10(void); diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index ae8c3e13cfce..757dbded11dc 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -463,7 +463,7 @@ static inline void cpu_feature_keys_init(void) { } #define CPU_FTRS_COMPATIBLE (CPU_FTR_PPCAS_ARCH_V2) #ifdef CONFIG_PPC64 -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 #define CPU_FTRS_POSSIBLE (CPU_FTRS_E6500 | CPU_FTRS_E5500) #else #ifdef CONFIG_CPU_LITTLE_ENDIAN @@ -510,7 +510,7 @@ enum { #elif defined(CONFIG_44x) CPU_FTRS_44X | CPU_FTRS_440x6 | #endif -#ifdef CONFIG_E500 +#ifdef CONFIG_PPC_E500 CPU_FTRS_E500 | CPU_FTRS_E500_2 | #endif #ifdef CONFIG_PPC_E500MC @@ -521,7 +521,7 @@ enum { #endif /* __powerpc64__ */ #ifdef CONFIG_PPC64 -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 #define CPU_FTRS_ALWAYS (CPU_FTRS_E6500 & CPU_FTRS_E5500) #else @@ -584,7 +584,7 @@ enum { #elif defined(CONFIG_44x) CPU_FTRS_44X & CPU_FTRS_440x6 & #endif -#ifdef CONFIG_E500 +#ifdef CONFIG_PPC_E500 CPU_FTRS_E500 & CPU_FTRS_E500_2 & #endif #ifdef CONFIG_PPC_E500MC diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h index 6d2b27997492..431ae2343022 100644 --- a/arch/powerpc/include/asm/cputime.h +++ b/arch/powerpc/include/asm/cputime.h @@ -95,7 +95,7 @@ static notrace inline void account_stolen_time(void) struct lppaca *lp = local_paca->lppaca_ptr; if (unlikely(local_paca->dtl_ridx != be64_to_cpu(lp->dtl_idx))) - accumulate_stolen_time(); + pseries_accumulate_stolen_time(); } #endif } diff --git a/arch/powerpc/include/asm/dtl.h b/arch/powerpc/include/asm/dtl.h index 1625888f27ef..4bcb9f9ac764 100644 --- a/arch/powerpc/include/asm/dtl.h +++ b/arch/powerpc/include/asm/dtl.h @@ -37,14 +37,6 @@ struct dtl_entry { extern struct kmem_cache *dtl_cache; extern rwlock_t dtl_access_lock; -/* - * When CONFIG_VIRT_CPU_ACCOUNTING_NATIVE = y, the cpu accounting code controls - * reading from the dispatch trace log. If other code wants to consume - * DTL entries, it can set this pointer to a function that will get - * called once for each DTL entry that gets processed. - */ -extern void (*dtl_consumer)(struct dtl_entry *entry, u64 index); - extern void register_dtl_buffer(int cpu); extern void alloc_dtl_buffers(unsigned long *time_limit); extern long hcall_vphn(unsigned long cpu, u64 flags, __be32 *associativity); diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index 32ce0fb7548f..ea71f7245a63 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -7,8 +7,8 @@ #ifdef CONFIG_PPC_BOOK3S_64 #include -#elif defined(CONFIG_PPC_FSL_BOOK3E) -#include +#elif defined(CONFIG_PPC_E500) +#include #elif defined(CONFIG_PPC_8xx) #include #endif /* CONFIG_PPC_BOOK3S_64 */ diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 983551859891..77fa88c2aed0 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -157,36 +157,18 @@ static inline notrace void irq_soft_mask_set(unsigned long mask) static inline notrace unsigned long irq_soft_mask_set_return(unsigned long mask) { - unsigned long flags; + unsigned long flags = irq_soft_mask_return(); -#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG - WARN_ON(mask && !(mask & IRQS_DISABLED)); -#endif - - asm volatile( - "lbz %0,%1(13); stb %2,%1(13)" - : "=&r" (flags) - : "i" (offsetof(struct paca_struct, irq_soft_mask)), - "r" (mask) - : "memory"); + irq_soft_mask_set(mask); return flags; } static inline notrace unsigned long irq_soft_mask_or_return(unsigned long mask) { - unsigned long flags, tmp; + unsigned long flags = irq_soft_mask_return(); - asm volatile( - "lbz %0,%2(13); or %1,%0,%3; stb %1,%2(13)" - : "=&r" (flags), "=r" (tmp) - : "i" (offsetof(struct paca_struct, irq_soft_mask)), - "r" (mask) - : "memory"); - -#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG - WARN_ON((mask | flags) && !((mask | flags) & IRQS_DISABLED)); -#endif + irq_soft_mask_set(flags | mask); return flags; } @@ -489,6 +471,30 @@ static inline void irq_soft_mask_regs_set_state(struct pt_regs *regs, unsigned l } #endif /* CONFIG_PPC64 */ +static inline unsigned long mtmsr_isync_irqsafe(unsigned long msr) +{ +#ifdef CONFIG_PPC64 + if (arch_irqs_disabled()) { + /* + * With soft-masking, MSR[EE] can change from 1 to 0 + * asynchronously when irqs are disabled, and we don't want to + * set MSR[EE] back to 1 here if that has happened. A race-free + * way to do this is ensure EE is already 0. Another way it + * could be done is with a RESTART_TABLE handler, but that's + * probably overkill here. + */ + msr &= ~MSR_EE; + mtmsr_isync(msr); + irq_soft_mask_set(IRQS_ALL_DISABLED); + local_paca->irq_happened |= PACA_IRQ_HARD_DIS; + } else +#endif + mtmsr_isync(msr); + + return msr; +} + + #define ARCH_IRQ_INIT_FLAGS IRQ_NOREQUEST #endif /* __ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h index 8069dbc4b8d1..4745bb9998bd 100644 --- a/arch/powerpc/include/asm/interrupt.h +++ b/arch/powerpc/include/asm/interrupt.h @@ -74,6 +74,19 @@ #include #include +#ifdef CONFIG_PPC64 +/* + * WARN/BUG is handled with a program interrupt so minimise checks here to + * avoid recursion and maximise the chance of getting the first oops handled. + */ +#define INT_SOFT_MASK_BUG_ON(regs, cond) \ +do { \ + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG) && \ + (user_mode(regs) || (TRAP(regs) != INTERRUPT_PROGRAM))) \ + BUG_ON(cond); \ +} while (0) +#endif + #ifdef CONFIG_PPC_BOOK3S_64 extern char __end_soft_masked[]; bool search_kernel_soft_mask_table(unsigned long addr); @@ -170,8 +183,7 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs) * context. */ if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) { - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - BUG_ON(!(regs->msr & MSR_EE)); + INT_SOFT_MASK_BUG_ON(regs, !(regs->msr & MSR_EE)); __hard_irq_enable(); } else { __hard_RI_enable(); @@ -194,19 +206,15 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs) * CT_WARN_ON comes here via program_check_exception, * so avoid recursion. */ - if (TRAP(regs) != INTERRUPT_PROGRAM) { - CT_WARN_ON(ct_state() != CONTEXT_KERNEL); - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - BUG_ON(is_implicit_soft_masked(regs)); - } - - /* Move this under a debugging check */ - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG) && - arch_irq_disabled_regs(regs)) - BUG_ON(search_kernel_restart_table(regs->nip)); + if (TRAP(regs) != INTERRUPT_PROGRAM) + CT_WARN_ON(ct_state() != CONTEXT_KERNEL && + ct_state() != CONTEXT_IDLE); + INT_SOFT_MASK_BUG_ON(regs, is_implicit_soft_masked(regs)); + INT_SOFT_MASK_BUG_ON(regs, arch_irq_disabled_regs(regs) && + search_kernel_restart_table(regs->nip)); } - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - BUG_ON(!arch_irq_disabled_regs(regs) && !(regs->msr & MSR_EE)); + INT_SOFT_MASK_BUG_ON(regs, !arch_irq_disabled_regs(regs) && + !(regs->msr & MSR_EE)); #endif booke_restore_dbcr0(); @@ -281,7 +289,7 @@ static inline bool nmi_disables_ftrace(struct pt_regs *regs) if (TRAP(regs) == INTERRUPT_PERFMON) return false; } - if (IS_ENABLED(CONFIG_PPC_BOOK3E)) { + if (IS_ENABLED(CONFIG_PPC_BOOK3E_64)) { if (TRAP(regs) == INTERRUPT_PERFMON) return false; } @@ -665,8 +673,7 @@ static inline void interrupt_cond_local_irq_enable(struct pt_regs *regs) local_irq_enable(); } -long system_call_exception(long r3, long r4, long r5, long r6, long r7, long r8, - unsigned long r0, struct pt_regs *regs); +long system_call_exception(struct pt_regs *regs, unsigned long r0); notrace unsigned long syscall_exit_prepare(unsigned long r3, struct pt_regs *regs, long scv); notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs); notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs); diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index f8d122d16af4..a1ddba01e7d1 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -3,7 +3,7 @@ #define _ASM_POWERPC_KEXEC_H #ifdef __KERNEL__ -#if defined(CONFIG_FSL_BOOKE) || defined(CONFIG_44x) +#if defined(CONFIG_PPC_85xx) || defined(CONFIG_44x) /* * On FSL-BookE we setup a 1:1 mapping which covers the first 2GiB of memory diff --git a/arch/powerpc/include/asm/kfence.h b/arch/powerpc/include/asm/kfence.h index a9846b68c6b9..6fd2b4d486c5 100644 --- a/arch/powerpc/include/asm/kfence.h +++ b/arch/powerpc/include/asm/kfence.h @@ -11,11 +11,25 @@ #include #include +#ifdef CONFIG_PPC64_ELF_ABI_V1 +#define ARCH_FUNC_PREFIX "." +#endif + static inline bool arch_kfence_init_pool(void) { return true; } +#ifdef CONFIG_PPC64 +static inline bool kfence_protect_page(unsigned long addr, bool protect) +{ + struct page *page = virt_to_page(addr); + + __kernel_map_pages(page, 1, !protect); + + return true; +} +#else static inline bool kfence_protect_page(unsigned long addr, bool protect) { pte_t *kpte = virt_to_kpte(addr); @@ -29,5 +43,6 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect) return true; } +#endif #endif /* __ASM_POWERPC_KFENCE_H */ diff --git a/arch/powerpc/include/asm/kgdb.h b/arch/powerpc/include/asm/kgdb.h index a9e098a3b881..715c18b75334 100644 --- a/arch/powerpc/include/asm/kgdb.h +++ b/arch/powerpc/include/asm/kgdb.h @@ -52,7 +52,7 @@ static inline void arch_kgdb_breakpoint(void) /* On non-E500 family PPC32 we determine the size by picking the last * register we need, but on E500 we skip sections so we list what we * need to store, and add it up. */ -#ifndef CONFIG_E500 +#ifndef CONFIG_PPC_E500 #define MAXREG (PT_FPSCR+1) #else /* 32 GPRs (8 bytes), nip, msr, ccr, link, ctr, xer, acc (8 bytes), spefscr*/ diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index c2b003550dc9..caea15dcb91d 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -443,7 +443,7 @@ struct kvmppc_passthru_irqmap { }; #endif -# ifdef CONFIG_PPC_FSL_BOOK3E +# ifdef CONFIG_PPC_E500 #define KVMPPC_BOOKE_IAC_NUM 2 #define KVMPPC_BOOKE_DAC_NUM 2 # else diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 9f625af3b65b..bfacf12784dd 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -104,7 +104,6 @@ extern void kvmppc_subarch_vcpu_uninit(struct kvm_vcpu *vcpu); extern void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr, unsigned int gtlb_idx); -extern void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode); extern void kvmppc_mmu_switch_pid(struct kvm_vcpu *vcpu, u32 pid); extern int kvmppc_mmu_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr); extern int kvmppc_mmu_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr); @@ -153,7 +152,6 @@ extern int kvmppc_core_check_requests(struct kvm_vcpu *vcpu); extern int kvmppc_booke_init(void); extern void kvmppc_booke_exit(void); -extern void kvmppc_core_destroy_mmu(struct kvm_vcpu *vcpu); extern int kvmppc_kvm_pv(struct kvm_vcpu *vcpu); extern void kvmppc_map_magic(struct kvm_vcpu *vcpu); @@ -162,8 +160,6 @@ extern void kvmppc_set_hpt(struct kvm *kvm, struct kvm_hpt_info *info); extern long kvmppc_alloc_reset_hpt(struct kvm *kvm, int order); extern void kvmppc_free_hpt(struct kvm_hpt_info *info); extern void kvmppc_rmap_reset(struct kvm *kvm); -extern long kvmppc_prepare_vrma(struct kvm *kvm, - struct kvm_userspace_memory_region *mem); extern void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, unsigned long porder); extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu); diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h index c390ec377bae..34d44cb17c87 100644 --- a/arch/powerpc/include/asm/lppaca.h +++ b/arch/powerpc/include/asm/lppaca.h @@ -104,14 +104,18 @@ struct lppaca { volatile __be32 dispersion_count; /* dispatch changed physical cpu */ volatile __be64 cmo_faults; /* CMO page fault count */ volatile __be64 cmo_fault_time; /* CMO page fault time */ - u8 reserved10[104]; + u8 reserved10[64]; /* [S]PURR expropriated/donated */ + volatile __be64 enqueue_dispatch_tb; /* Total TB enqueue->dispatch */ + volatile __be64 ready_enqueue_tb; /* Total TB ready->enqueue */ + volatile __be64 wait_ready_tb; /* Total TB wait->ready */ + u8 reserved11[16]; /* cacheline 4-5 */ __be32 page_ins; /* CMO Hint - # page ins by OS */ - u8 reserved11[148]; + u8 reserved12[148]; volatile __be64 dtl_idx; /* Dispatch Trace Log head index */ - u8 reserved12[96]; + u8 reserved13[96]; } ____cacheline_aligned; #define lppaca_of(cpu) (*paca_ptrs[cpu]->lppaca_ptr) diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 8cb83600c434..378b8d5836a7 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -204,7 +204,6 @@ struct machdep_calls { extern void e500_idle(void); extern void power4_idle(void); extern void ppc6xx_idle(void); -extern void book3e_idle(void); /* * ppc_md contains a copy of the machine description structure for the diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index 860d0290ca4d..94b981152667 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -120,6 +120,9 @@ */ #define MMU_FTR_1T_SEGMENT ASM_CONST(0x40000000) +// NX paste RMA reject in DSI +#define MMU_FTR_NX_DSI ASM_CONST(0x80000000) + /* MMU feature bit sets for various CPUs */ #define MMU_FTRS_DEFAULT_HPTE_ARCH_V2 (MMU_FTR_HPTE_TABLE | MMU_FTR_TLBIEL | MMU_FTR_16M_PAGE) #define MMU_FTRS_POWER MMU_FTRS_DEFAULT_HPTE_ARCH_V2 @@ -141,7 +144,7 @@ typedef pte_t *pgtable_t; -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 #include DECLARE_PER_CPU(int, next_tlbcam_idx); #endif @@ -162,7 +165,7 @@ enum { #elif defined(CONFIG_44x) MMU_FTR_TYPE_44x | #endif -#ifdef CONFIG_E500 +#ifdef CONFIG_PPC_E500 MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | MMU_FTR_USE_TLBILX | #endif #ifdef CONFIG_PPC_BOOK3S_32 @@ -181,7 +184,7 @@ enum { #endif #ifdef CONFIG_PPC_RADIX_MMU MMU_FTR_TYPE_RADIX | - MMU_FTR_GTSE | + MMU_FTR_GTSE | MMU_FTR_NX_DSI | #endif /* CONFIG_PPC_RADIX_MMU */ #endif #ifdef CONFIG_PPC_KUAP @@ -211,7 +214,7 @@ enum { #elif defined(CONFIG_44x) #define MMU_FTRS_ALWAYS MMU_FTR_TYPE_44x #endif -#ifdef CONFIG_E500 +#ifdef CONFIG_PPC_E500 #define MMU_FTRS_ALWAYS MMU_FTR_TYPE_FSL_E #endif diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index 3f25bd3e14eb..c1ea270bb848 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -31,7 +31,6 @@ extern long mm_iommu_newdev(struct mm_struct *mm, unsigned long ua, extern long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem); extern void mm_iommu_init(struct mm_struct *mm); -extern void mm_iommu_cleanup(struct mm_struct *mm); extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup(struct mm_struct *mm, unsigned long ua, unsigned long size); extern struct mm_iommu_table_group_mem_t *mm_iommu_get(struct mm_struct *mm, @@ -117,7 +116,6 @@ static inline bool need_extra_context(struct mm_struct *mm, unsigned long ea) } #endif -extern void switch_cop(struct mm_struct *next); extern int use_cop(unsigned long acop, struct mm_struct *mm); extern void drop_cop(unsigned long acop, struct mm_struct *mm); diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index 9091e4904a6b..0d40b33184eb 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -130,10 +130,10 @@ void unmap_kernel_page(unsigned long va); #include #elif defined(CONFIG_44x) #include -#elif defined(CONFIG_FSL_BOOKE) && defined(CONFIG_PTE_64BIT) -#include -#elif defined(CONFIG_FSL_BOOKE) -#include +#elif defined(CONFIG_PPC_85xx) && defined(CONFIG_PTE_64BIT) +#include +#elif defined(CONFIG_PPC_85xx) +#include #elif defined(CONFIG_PPC_8xx) #include #endif diff --git a/arch/powerpc/include/asm/nohash/32/pte-fsl-booke.h b/arch/powerpc/include/asm/nohash/32/pte-85xx.h similarity index 94% rename from arch/powerpc/include/asm/nohash/32/pte-fsl-booke.h rename to arch/powerpc/include/asm/nohash/32/pte-85xx.h index 0fc1bd42bb3e..93fb8e11a3f1 100644 --- a/arch/powerpc/include/asm/nohash/32/pte-fsl-booke.h +++ b/arch/powerpc/include/asm/nohash/32/pte-85xx.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_POWERPC_NOHASH_32_PTE_FSL_BOOKE_H -#define _ASM_POWERPC_NOHASH_32_PTE_FSL_BOOKE_H +#ifndef _ASM_POWERPC_NOHASH_32_PTE_85xx_H +#define _ASM_POWERPC_NOHASH_32_PTE_85xx_H #ifdef __KERNEL__ /* PTE bit definitions for Freescale BookE SW loaded TLB MMU based @@ -71,4 +71,4 @@ #define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) #endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_NOHASH_32_PTE_FSL_BOOKE_H */ +#endif /* _ASM_POWERPC_NOHASH_32_PTE_FSL_85xx_H */ diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index 599921cc257e..879e9a6e5a87 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -70,7 +70,7 @@ /* * Include the PTE bits definitions */ -#include +#include #define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1)) diff --git a/arch/powerpc/include/asm/nohash/hugetlb-book3e.h b/arch/powerpc/include/asm/nohash/hugetlb-e500.h similarity index 84% rename from arch/powerpc/include/asm/nohash/hugetlb-book3e.h rename to arch/powerpc/include/asm/nohash/hugetlb-e500.h index ecd8694cb229..8f04ad20e040 100644 --- a/arch/powerpc/include/asm/nohash/hugetlb-book3e.h +++ b/arch/powerpc/include/asm/nohash/hugetlb-e500.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_POWERPC_NOHASH_HUGETLB_BOOK3E_H -#define _ASM_POWERPC_NOHASH_HUGETLB_BOOK3E_H +#ifndef _ASM_POWERPC_NOHASH_HUGETLB_E500_H +#define _ASM_POWERPC_NOHASH_HUGETLB_E500_H static inline pte_t *hugepd_page(hugepd_t hpd) { @@ -30,7 +30,7 @@ void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr); static inline void hugepd_populate(hugepd_t *hpdp, pte_t *new, unsigned int pshift) { - /* We use the old format for PPC_FSL_BOOK3E */ + /* We use the old format for PPC_E500 */ *hpdp = __hugepd(((unsigned long)new & ~PD_HUGE) | pshift); } @@ -42,4 +42,4 @@ static inline int check_and_get_huge_psize(int shift) return shift_to_mmu_psize(shift); } -#endif /* _ASM_POWERPC_NOHASH_HUGETLB_BOOK3E_H */ +#endif /* _ASM_POWERPC_NOHASH_HUGETLB_E500_H */ diff --git a/arch/powerpc/include/asm/nohash/mmu-book3e.h b/arch/powerpc/include/asm/nohash/mmu-e500.h similarity index 100% rename from arch/powerpc/include/asm/nohash/mmu-book3e.h rename to arch/powerpc/include/asm/nohash/mmu-e500.h diff --git a/arch/powerpc/include/asm/nohash/mmu.h b/arch/powerpc/include/asm/nohash/mmu.h index edc793e5f08f..e264be219fdb 100644 --- a/arch/powerpc/include/asm/nohash/mmu.h +++ b/arch/powerpc/include/asm/nohash/mmu.h @@ -8,9 +8,9 @@ #elif defined(CONFIG_44x) /* 44x-style software loaded TLB */ #include -#elif defined(CONFIG_PPC_BOOK3E_MMU) +#elif defined(CONFIG_PPC_E500) /* Freescale Book-E software loaded TLB or Book-3e (ISA 2.06+) MMU */ -#include +#include #elif defined (CONFIG_PPC_8xx) /* Motorola/Freescale 8xx software loaded TLB */ #include diff --git a/arch/powerpc/include/asm/nohash/pgalloc.h b/arch/powerpc/include/asm/nohash/pgalloc.h index 29c43665a753..4b62376318e1 100644 --- a/arch/powerpc/include/asm/nohash/pgalloc.h +++ b/arch/powerpc/include/asm/nohash/pgalloc.h @@ -15,7 +15,7 @@ static inline void tlb_flush_pgtable(struct mmu_gather *tlb, { } -#endif /* !CONFIG_PPC_BOOK3E */ +#endif /* !CONFIG_PPC_BOOK3E_64 */ static inline pgd_t *pgd_alloc(struct mm_struct *mm) { diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h index b499da6c1a99..d9067dfc531c 100644 --- a/arch/powerpc/include/asm/nohash/pgtable.h +++ b/arch/powerpc/include/asm/nohash/pgtable.h @@ -11,31 +11,11 @@ /* Permission masks used for kernel mappings */ #define PAGE_KERNEL __pgprot(_PAGE_BASE | _PAGE_KERNEL_RW) #define PAGE_KERNEL_NC __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | _PAGE_NO_CACHE) -#define PAGE_KERNEL_NCG __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \ - _PAGE_NO_CACHE | _PAGE_GUARDED) +#define PAGE_KERNEL_NCG __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | _PAGE_NO_CACHE | _PAGE_GUARDED) #define PAGE_KERNEL_X __pgprot(_PAGE_BASE | _PAGE_KERNEL_RWX) #define PAGE_KERNEL_RO __pgprot(_PAGE_BASE | _PAGE_KERNEL_RO) #define PAGE_KERNEL_ROX __pgprot(_PAGE_BASE | _PAGE_KERNEL_ROX) -/* - * Protection used for kernel text. We want the debuggers to be able to - * set breakpoints anywhere, so don't write protect the kernel text - * on platforms where such control is possible. - */ -#if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH) ||\ - defined(CONFIG_KPROBES) || defined(CONFIG_DYNAMIC_FTRACE) -#define PAGE_KERNEL_TEXT PAGE_KERNEL_X -#else -#define PAGE_KERNEL_TEXT PAGE_KERNEL_ROX -#endif - -/* Make modules code happy. We don't set RO yet */ -#define PAGE_KERNEL_EXEC PAGE_KERNEL_X - -/* Advertise special mapping type for AGP */ -#define PAGE_AGP (PAGE_KERNEL_NC) -#define HAVE_PAGE_AGP - #ifndef __ASSEMBLY__ /* Generic accessors to PTE bits */ @@ -277,12 +257,6 @@ static inline int pud_huge(pud_t pud) return 0; } -static inline int pgd_huge(pgd_t pgd) -{ - return 0; -} -#define pgd_huge pgd_huge - #define is_hugepd(hpd) (hugepd_ok(hpd)) #endif @@ -292,7 +266,7 @@ static inline int pgd_huge(pgd_t pgd) * We use it to ensure coherency between the i-cache and d-cache * for the page which has just been mapped in. */ -#if defined(CONFIG_PPC_FSL_BOOK3E) && defined(CONFIG_HUGETLB_PAGE) +#if defined(CONFIG_PPC_E500) && defined(CONFIG_HUGETLB_PAGE) void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); #else static inline diff --git a/arch/powerpc/include/asm/nohash/pte-book3e.h b/arch/powerpc/include/asm/nohash/pte-e500.h similarity index 96% rename from arch/powerpc/include/asm/nohash/pte-book3e.h rename to arch/powerpc/include/asm/nohash/pte-e500.h index f798640422c2..0934e8965e4e 100644 --- a/arch/powerpc/include/asm/nohash/pte-book3e.h +++ b/arch/powerpc/include/asm/nohash/pte-e500.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_POWERPC_NOHASH_PTE_BOOK3E_H -#define _ASM_POWERPC_NOHASH_PTE_BOOK3E_H +#ifndef _ASM_POWERPC_NOHASH_PTE_E500_H +#define _ASM_POWERPC_NOHASH_PTE_E500_H #ifdef __KERNEL__ /* PTE bit definitions for processors compliant to the Book3E @@ -126,4 +126,4 @@ static inline pte_t pte_mkexec(pte_t pte) #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_NOHASH_PTE_BOOK3E_H */ +#endif /* _ASM_POWERPC_NOHASH_PTE_E500_H */ diff --git a/arch/powerpc/include/asm/nohash/tlbflush.h b/arch/powerpc/include/asm/nohash/tlbflush.h index 698935d4f72d..bdaf34ad41ea 100644 --- a/arch/powerpc/include/asm/nohash/tlbflush.h +++ b/arch/powerpc/include/asm/nohash/tlbflush.h @@ -18,7 +18,7 @@ /* * TLB flushing for software loaded TLB chips * - * TODO: (CONFIG_FSL_BOOKE) determine if flush_tlb_range & + * TODO: (CONFIG_PPC_85xx) determine if flush_tlb_range & * flush_tlb_kernel_range are best implemented as tlbia vs * specific tlbie's */ diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index bfd3142cd0ba..726125a534de 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -324,16 +324,10 @@ extern int opal_flush_console(uint32_t vtermno); extern void hvc_opal_init_early(void); -extern int opal_notifier_register(struct notifier_block *nb); -extern int opal_notifier_unregister(struct notifier_block *nb); - extern int opal_message_notifier_register(enum opal_msg_type msg_type, struct notifier_block *nb); extern int opal_message_notifier_unregister(enum opal_msg_type msg_type, struct notifier_block *nb); -extern void opal_notifier_enable(void); -extern void opal_notifier_disable(void); -extern void opal_notifier_update_evt(uint64_t evt_mask, uint64_t evt_val); extern int opal_async_get_token_interruptible(void); extern int opal_async_release_token(int token); diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 4d7aaab82702..09f1790d0ae1 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -18,7 +18,7 @@ #include #include #include -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 #include #else #include @@ -127,7 +127,7 @@ struct paca_struct { #endif #endif /* CONFIG_PPC_BOOK3S_64 */ -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 u64 exgen[8] __aligned(0x40); /* Keep pgd in the same cacheline as the start of extlb */ pgd_t *pgd __aligned(0x40); /* Current PGD */ @@ -151,7 +151,7 @@ struct paca_struct { void *dbg_kstack; struct tlb_core_data tcd; -#endif /* CONFIG_PPC_BOOK3E */ +#endif /* CONFIG_PPC_BOOK3E_64 */ #ifdef CONFIG_PPC_64S_HASH_MMU unsigned char mm_ctx_low_slices_psize[BITS_PER_LONG / BITS_PER_BYTE]; @@ -168,7 +168,7 @@ struct paca_struct { #ifdef CONFIG_PPC64 u64 exit_save_r1; /* Syscall/interrupt R1 save */ #endif -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 u16 trap_save; /* Used when bad stack is encountered */ #endif #ifdef CONFIG_PPC_BOOK3S_64 @@ -263,7 +263,6 @@ struct paca_struct { u64 l1d_flush_size; #endif #ifdef CONFIG_PPC_PSERIES - struct rtas_args *rtas_args_reentrant; u8 *mce_data_buf; /* buffer to hold per cpu rtas errlog */ #endif /* CONFIG_PPC_PSERIES */ diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index e5f75c70eda8..edf1dd1b0ca9 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -31,7 +31,7 @@ extern unsigned int hpage_shift; #define HPAGE_SHIFT hpage_shift #elif defined(CONFIG_PPC_8xx) #define HPAGE_SHIFT 19 /* 512k pages */ -#elif defined(CONFIG_PPC_FSL_BOOK3E) +#elif defined(CONFIG_PPC_E500) #define HPAGE_SHIFT 22 /* 4M pages */ #endif #define HPAGE_SIZE ((1UL) << HPAGE_SHIFT) @@ -308,12 +308,6 @@ static inline bool pfn_valid(unsigned long pfn) #include #endif - -#ifndef CONFIG_HUGETLB_PAGE -#define is_hugepd(pdep) (0) -#define pgd_huge(pgd) (0) -#endif /* CONFIG_HUGETLB_PAGE */ - struct page; extern void clear_user_page(void *page, unsigned long vaddr, struct page *pg); extern void copy_user_page(void *to, void *from, unsigned long vaddr, diff --git a/arch/powerpc/include/asm/paravirt.h b/arch/powerpc/include/asm/paravirt.h index eb7df559ae74..f5ba1a3c41f8 100644 --- a/arch/powerpc/include/asm/paravirt.h +++ b/arch/powerpc/include/asm/paravirt.h @@ -21,6 +21,18 @@ static inline bool is_shared_processor(void) return static_branch_unlikely(&shared_processor); } +#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING +extern struct static_key paravirt_steal_enabled; +extern struct static_key paravirt_steal_rq_enabled; + +u64 pseries_paravirt_steal_clock(int cpu); + +static inline u64 paravirt_steal_clock(int cpu) +{ + return pseries_paravirt_steal_clock(cpu); +} +#endif + /* If bit 0 is set, the cpu has been ceded, conferred, or preempted */ static inline u32 yield_count_of(int cpu) { diff --git a/arch/powerpc/include/asm/paravirt_api_clock.h b/arch/powerpc/include/asm/paravirt_api_clock.h new file mode 100644 index 000000000000..d25ca7ac57c7 --- /dev/null +++ b/arch/powerpc/include/asm/paravirt_api_clock.h @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include diff --git a/arch/powerpc/include/asm/pgtable-be-types.h b/arch/powerpc/include/asm/pgtable-be-types.h index b169bbf95fcb..82633200b500 100644 --- a/arch/powerpc/include/asm/pgtable-be-types.h +++ b/arch/powerpc/include/asm/pgtable-be-types.h @@ -101,6 +101,7 @@ static inline bool pmd_xchg(pmd_t *pmdp, pmd_t old, pmd_t new) return pmd_raw(old) == prev; } +#ifdef CONFIG_ARCH_HAS_HUGEPD typedef struct { __be64 pdbe; } hugepd_t; #define __hugepd(x) ((hugepd_t) { cpu_to_be64(x) }) @@ -108,5 +109,6 @@ static inline unsigned long hpd_val(hugepd_t x) { return be64_to_cpu(x.pdbe); } +#endif #endif /* _ASM_POWERPC_PGTABLE_BE_TYPES_H */ diff --git a/arch/powerpc/include/asm/pgtable-types.h b/arch/powerpc/include/asm/pgtable-types.h index efed0db7b1db..082c85cc09b1 100644 --- a/arch/powerpc/include/asm/pgtable-types.h +++ b/arch/powerpc/include/asm/pgtable-types.h @@ -83,11 +83,13 @@ static inline bool pte_xchg(pte_t *ptep, pte_t old, pte_t new) } #endif +#ifdef CONFIG_ARCH_HAS_HUGEPD typedef struct { unsigned long pd; } hugepd_t; #define __hugepd(x) ((hugepd_t) { (x) }) static inline unsigned long hpd_val(hugepd_t x) { return x.pd; } +#endif #endif /* _ASM_POWERPC_PGTABLE_TYPES_H */ diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index 33f4bf8d22b0..283f40d05a4d 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -20,6 +20,25 @@ struct mm_struct; #include #endif /* !CONFIG_PPC_BOOK3S */ +/* + * Protection used for kernel text. We want the debuggers to be able to + * set breakpoints anywhere, so don't write protect the kernel text + * on platforms where such control is possible. + */ +#if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH) || \ + defined(CONFIG_KPROBES) || defined(CONFIG_DYNAMIC_FTRACE) +#define PAGE_KERNEL_TEXT PAGE_KERNEL_X +#else +#define PAGE_KERNEL_TEXT PAGE_KERNEL_ROX +#endif + +/* Make modules code happy. We don't set RO yet */ +#define PAGE_KERNEL_EXEC PAGE_KERNEL_X + +/* Advertise special mapping type for AGP */ +#define PAGE_AGP (PAGE_KERNEL_NC) +#define HAVE_PAGE_AGP + #ifndef __ASSEMBLY__ #ifndef MAX_PTRS_PER_PGD diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index c6d724104ed1..21e33e46f4b8 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -330,6 +330,7 @@ #define __PPC_XSP(s) ((((s) & 0x1e) | (((s) >> 5) & 0x1)) << 21) #define __PPC_XTP(s) __PPC_XSP(s) #define __PPC_T_TLB(t) (((t) & 0x3) << 21) +#define __PPC_PL(p) (((p) & 0x3) << 16) #define __PPC_WC(w) (((w) & 0x3) << 21) #define __PPC_WS(w) (((w) & 0x1f) << 11) #define __PPC_SH(s) __PPC_WS(s) @@ -388,7 +389,8 @@ #define PPC_RAW_RFDI (0x4c00004e) #define PPC_RAW_RFMCI (0x4c00004c) #define PPC_RAW_TLBILX(t, a, b) (0x7c000024 | __PPC_T_TLB(t) | __PPC_RA0(a) | __PPC_RB(b)) -#define PPC_RAW_WAIT(w) (0x7c00007c | __PPC_WC(w)) +#define PPC_RAW_WAIT_v203 (0x7c00007c) +#define PPC_RAW_WAIT(w, p) (0x7c00003c | __PPC_WC(w) | __PPC_PL(p)) #define PPC_RAW_TLBIE(lp, a) (0x7c000264 | ___PPC_RB(a) | ___PPC_RS(lp)) #define PPC_RAW_TLBIE_5(rb, rs, ric, prs, r) \ (0x7c000264 | ___PPC_RB(rb) | ___PPC_RS(rs) | ___PPC_RIC(ric) | ___PPC_PRS(prs) | ___PPC_R(r)) @@ -606,7 +608,8 @@ #define PPC_TLBILX_ALL(a, b) PPC_TLBILX(0, a, b) #define PPC_TLBILX_PID(a, b) PPC_TLBILX(1, a, b) #define PPC_TLBILX_VA(a, b) PPC_TLBILX(3, a, b) -#define PPC_WAIT(w) stringify_in_c(.long PPC_RAW_WAIT(w)) +#define PPC_WAIT_v203 stringify_in_c(.long PPC_RAW_WAIT_v203) +#define PPC_WAIT(w, p) stringify_in_c(.long PPC_RAW_WAIT(w, p)) #define PPC_TLBIE(lp, a) stringify_in_c(.long PPC_RAW_TLBIE(lp, a)) #define PPC_TLBIE_5(rb, rs, ric, prs, r) \ stringify_in_c(.long PPC_RAW_TLBIE_5(rb, rs, ric, prs, r)) diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 83c02f5a7f2a..753a2757bcd4 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -33,6 +33,20 @@ .endr .endm +/* + * This expands to a sequence of register clears for regs start to end + * inclusive, of the form: + * + * li rN, 0 + */ +.macro ZEROIZE_REGS start, end + .Lreg=\start + .rept (\end - \start + 1) + li .Lreg, 0 + .Lreg=.Lreg+1 + .endr +.endm + /* * Macros for storing registers into and loading registers from * exception frames. @@ -49,6 +63,14 @@ #define REST_NVGPRS(base) REST_GPRS(13, 31, base) #endif +#define ZEROIZE_GPRS(start, end) ZEROIZE_REGS start, end +#ifdef __powerpc64__ +#define ZEROIZE_NVGPRS() ZEROIZE_GPRS(14, 31) +#else +#define ZEROIZE_NVGPRS() ZEROIZE_GPRS(13, 31) +#endif +#define ZEROIZE_GPR(n) ZEROIZE_GPRS(n, n) + #define SAVE_GPR(n, base) SAVE_GPRS(n, n, base) #define REST_GPR(n, base) REST_GPRS(n, n, base) @@ -305,6 +327,12 @@ n: #ifdef __powerpc64__ +#define __LOAD_PACA_TOC(reg) \ + ld reg,PACATOC(r13) + +#define LOAD_PACA_TOC() \ + __LOAD_PACA_TOC(r2) + #define LOAD_REG_IMMEDIATE(reg, expr) __LOAD_REG_IMMEDIATE reg, expr #define LOAD_REG_IMMEDIATE_SYM(reg, tmp, expr) \ @@ -315,7 +343,19 @@ n: rldimi reg, tmp, 32, 0 #define LOAD_REG_ADDR(reg,name) \ - ld reg,name@got(r2) + addis reg,r2,name@toc@ha; \ + addi reg,reg,name@toc@l + +#ifdef CONFIG_PPC_BOOK3E_64 +/* + * This is used in register-constrained interrupt handlers. Not to be used + * by BOOK3S. ld complains with "got/toc optimization is not supported" if r2 + * is not used for the TOC offset, so use @got(tocreg). If the interrupt + * handlers saved r2 instead, LOAD_REG_ADDR could be used. + */ +#define LOAD_REG_ADDR_ALTTOC(reg,tocreg,name) \ + ld reg,name@got(tocreg) +#endif #define LOAD_REG_ADDRBASE(reg,name) LOAD_REG_ADDR(reg,name) #define ADDROFF(name) 0 @@ -342,7 +382,7 @@ n: #endif /* various errata or part fixups */ -#if defined(CONFIG_PPC_CELL) || defined(CONFIG_PPC_FSL_BOOK3E) +#if defined(CONFIG_PPC_CELL) || defined(CONFIG_PPC_E500) #define MFTB(dest) \ 90: mfspr dest, SPRN_TBRL; \ BEGIN_FTR_SECTION_NESTED(96); \ @@ -709,7 +749,7 @@ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96) * kernel is built for. */ -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 #define FIXUP_ENDIAN #else /* @@ -749,7 +789,7 @@ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96) .long 0x2402004c; /* hrfid */ \ 191: -#endif /* !CONFIG_PPC_BOOK3E */ +#endif /* !CONFIG_PPC_BOOK3E_64 */ #endif /* __ASSEMBLY__ */ @@ -768,7 +808,7 @@ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96) stringify_in_c(.llong (_target);) \ stringify_in_c(.previous) -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 #define BTB_FLUSH(reg) \ lis reg,BUCSR_INIT@h; \ ori reg,reg,BUCSR_INIT@l; \ @@ -776,6 +816,6 @@ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96) isync; #else #define BTB_FLUSH(reg) -#endif /* CONFIG_PPC_FSL_BOOK3E */ +#endif /* CONFIG_PPC_E500 */ #endif /* _ASM_POWERPC_PPC_ASM_H */ diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index fdfaae194ddd..9bff4ab8242d 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -355,11 +355,23 @@ static inline unsigned long __pack_fe01(unsigned int fpmode) #ifdef CONFIG_PPC64 -#define spin_begin() HMT_low() +#define spin_begin() \ + asm volatile(ASM_FTR_IFCLR( \ + "or 1,1,1", /* HMT_LOW */ \ + "nop", /* v3.1 uses pause_short in cpu_relax instead */ \ + %0) :: "i" (CPU_FTR_ARCH_31) : "memory") -#define spin_cpu_relax() barrier() +#define spin_cpu_relax() \ + asm volatile(ASM_FTR_IFCLR( \ + "nop", /* Before v3.1 use priority nops in spin_begin/end */ \ + PPC_WAIT(2, 0), /* aka pause_short */ \ + %0) :: "i" (CPU_FTR_ARCH_31) : "memory") -#define spin_end() HMT_medium() +#define spin_end() \ + asm volatile(ASM_FTR_IFCLR( \ + "or 2,2,2", /* HMT_MEDIUM */ \ + "nop", \ + %0) :: "i" (CPU_FTR_ARCH_31) : "memory") #endif @@ -426,6 +438,8 @@ extern int fix_alignment(struct pt_regs *); #endif int do_mathemu(struct pt_regs *regs); +int do_spe_mathemu(struct pt_regs *regs); +int speround_handler(struct pt_regs *regs); /* VMX copying */ int enter_vmx_usercopy(void); diff --git a/arch/powerpc/include/asm/ps3av.h b/arch/powerpc/include/asm/ps3av.h index 82db78fc169d..c8b0f2ffcd35 100644 --- a/arch/powerpc/include/asm/ps3av.h +++ b/arch/powerpc/include/asm/ps3av.h @@ -726,6 +726,4 @@ extern int ps3av_video_mode2res(u32, u32 *, u32 *); extern int ps3av_video_mute(int); extern int ps3av_audio_mute(int); extern int ps3av_audio_mute_analog(int); -extern int ps3av_dev_open(void); -extern int ps3av_dev_close(void); #endif /* _ASM_POWERPC_PS3AV_H_ */ diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index a03403695cd4..2efec6d87049 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -99,6 +99,13 @@ struct pt_regs #define STACK_FRAME_WITH_PT_REGS (STACK_FRAME_OVERHEAD + sizeof(struct pt_regs)) +// Always displays as "REGS" in memory dumps +#ifdef CONFIG_CPU_BIG_ENDIAN +#define STACK_FRAME_REGS_MARKER ASM_CONST(0x52454753) +#else +#define STACK_FRAME_REGS_MARKER ASM_CONST(0x53474552) +#endif + #ifdef __powerpc64__ /* @@ -115,7 +122,6 @@ struct pt_regs #define STACK_FRAME_OVERHEAD 112 /* size of minimum stack frame */ #define STACK_FRAME_LR_SAVE 2 /* Location of LR in stack frame */ -#define STACK_FRAME_REGS_MARKER ASM_CONST(0x7265677368657265) #define STACK_INT_FRAME_SIZE (sizeof(struct pt_regs) + \ STACK_FRAME_OVERHEAD + KERNEL_REDZONE_SIZE) #define STACK_FRAME_MARKER 12 @@ -136,7 +142,6 @@ struct pt_regs #define KERNEL_REDZONE_SIZE 0 #define STACK_FRAME_OVERHEAD 16 /* size of minimum stack frame */ #define STACK_FRAME_LR_SAVE 1 /* Location of LR in stack frame */ -#define STACK_FRAME_REGS_MARKER ASM_CONST(0x72656773) #define STACK_INT_FRAME_SIZE (sizeof(struct pt_regs) + STACK_FRAME_OVERHEAD) #define STACK_FRAME_MARKER 2 #define STACK_FRAME_MIN_SIZE STACK_FRAME_OVERHEAD diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h index 17b8dcd9a40d..af56980b6cdb 100644 --- a/arch/powerpc/include/asm/reg_booke.h +++ b/arch/powerpc/include/asm/reg_booke.h @@ -246,7 +246,7 @@ #define PPC47x_MCSR_FPR 0x00800000 /* FPR parity error */ #define PPC47x_MCSR_IPR 0x00400000 /* Imprecise Machine Check Exception */ -#ifdef CONFIG_E500 +#ifdef CONFIG_PPC_E500 /* All e500 */ #define MCSR_MCP 0x80000000UL /* Machine Check Input Pin */ #define MCSR_ICPERR 0x40000000UL /* I-Cache Parity Error */ @@ -282,7 +282,7 @@ #endif /* Bit definitions for the HID1 */ -#ifdef CONFIG_E500 +#ifdef CONFIG_PPC_E500 /* e500v1/v2 */ #define HID1_PLL_CFG_MASK 0xfc000000 /* PLL_CFG input pins */ #define HID1_RFXE 0x00020000 /* Read fault exception enable */ @@ -545,7 +545,7 @@ #define TCR_FIE 0x00800000 /* FIT Interrupt Enable */ #define TCR_ARE 0x00400000 /* Auto Reload Enable */ -#ifdef CONFIG_E500 +#ifdef CONFIG_PPC_E500 #define TCR_GET_WP(tcr) ((((tcr) & 0xC0000000) >> 30) | \ (((tcr) & 0x1E0000) >> 15)) #else diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h index 00531af17ce0..56319aea646e 100644 --- a/arch/powerpc/include/asm/rtas.h +++ b/arch/powerpc/include/asm/rtas.h @@ -240,7 +240,6 @@ extern struct rtas_t rtas; extern int rtas_token(const char *service); extern int rtas_service_present(const char *service); extern int rtas_call(int token, int, int, int *, ...); -int rtas_call_reentrant(int token, int nargs, int nret, int *outputs, ...); void rtas_call_unlocked(struct rtas_args *args, int token, int nargs, int nret, ...); extern void __noreturn rtas_restart(char *cmd); diff --git a/arch/powerpc/include/asm/runlatch.h b/arch/powerpc/include/asm/runlatch.h index cfb390edf7d0..ceb66d761fe1 100644 --- a/arch/powerpc/include/asm/runlatch.h +++ b/arch/powerpc/include/asm/runlatch.h @@ -19,10 +19,9 @@ extern void __ppc64_runlatch_off(void); do { \ if (cpu_has_feature(CPU_FTR_CTRL) && \ test_thread_local_flags(_TLF_RUNLATCH)) { \ - unsigned long msr = mfmsr(); \ __hard_irq_disable(); \ __ppc64_runlatch_off(); \ - if (msr & MSR_EE) \ + if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) \ __hard_irq_enable(); \ } \ } while (0) @@ -31,10 +30,9 @@ extern void __ppc64_runlatch_off(void); do { \ if (cpu_has_feature(CPU_FTR_CTRL) && \ !test_thread_local_flags(_TLF_RUNLATCH)) { \ - unsigned long msr = mfmsr(); \ __hard_irq_disable(); \ __ppc64_runlatch_on(); \ - if (msr & MSR_EE) \ + if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) \ __hard_irq_enable(); \ } \ } while (0) diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h index 8be2c491c733..9c00c9c0ca8f 100644 --- a/arch/powerpc/include/asm/sections.h +++ b/arch/powerpc/include/asm/sections.h @@ -13,15 +13,26 @@ typedef struct func_desc func_desc_t; #include extern char __head_end[]; +extern char __srwx_boundary[]; + +/* Patch sites */ +extern s32 patch__call_flush_branch_caches1; +extern s32 patch__call_flush_branch_caches2; +extern s32 patch__call_flush_branch_caches3; +extern s32 patch__flush_count_cache_return; +extern s32 patch__flush_link_stack_return; +extern s32 patch__call_kvm_flush_link_stack; +extern s32 patch__call_kvm_flush_link_stack_p9; +extern s32 patch__memset_nocache, patch__memcpy_nocache; + +extern long flush_branch_caches; +extern long kvm_flush_link_stack; #ifdef __powerpc64__ extern char __start_interrupts[]; extern char __end_interrupts[]; -extern char __prom_init_toc_start[]; -extern char __prom_init_toc_end[]; - #ifdef CONFIG_PPC_POWERNV extern char start_real_trampolines[]; extern char end_real_trampolines[]; diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index d8c28902cf59..e29e83f8a89c 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -7,7 +7,6 @@ #ifndef __ASSEMBLY__ extern void ppc_printk_progress(char *s, unsigned short hex); -extern unsigned int rtas_data; extern unsigned long long memory_limit; extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask); @@ -70,7 +69,7 @@ void do_barrier_nospec_fixups_range(bool enable, void *start, void *end); static inline void do_barrier_nospec_fixups_range(bool enable, void *start, void *end) { } #endif -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 void __init setup_spectre_v2(void); #else static inline void setup_spectre_v2(void) {} @@ -89,6 +88,8 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, unsigned long pp, unsigned long r6, unsigned long r7, unsigned long kbase); +extern struct seq_buf ppc_hw_desc; + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_POWERPC_SETUP_H */ diff --git a/arch/powerpc/include/asm/synch.h b/arch/powerpc/include/asm/synch.h index 7130176d8cb8..b0b4c64870d7 100644 --- a/arch/powerpc/include/asm/synch.h +++ b/arch/powerpc/include/asm/synch.h @@ -44,7 +44,7 @@ static inline void ppc_after_tlbiel_barrier(void) #if defined(__powerpc64__) # define LWSYNC lwsync -#elif defined(CONFIG_E500) +#elif defined(CONFIG_PPC_E500) # define LWSYNC \ START_LWSYNC_SECTION(96); \ sync; \ diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h index 25fc8ad9a27a..3dd36c5e334a 100644 --- a/arch/powerpc/include/asm/syscall.h +++ b/arch/powerpc/include/asm/syscall.h @@ -14,9 +14,16 @@ #include #include +#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER +typedef long (*syscall_fn)(const struct pt_regs *); +#else +typedef long (*syscall_fn)(unsigned long, unsigned long, unsigned long, + unsigned long, unsigned long, unsigned long); +#endif + /* ftrace syscalls requires exporting the sys_call_table */ -extern const unsigned long sys_call_table[]; -extern const unsigned long compat_sys_call_table[]; +extern const syscall_fn sys_call_table[]; +extern const syscall_fn compat_sys_call_table[]; static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs) { diff --git a/arch/powerpc/include/asm/syscall_wrapper.h b/arch/powerpc/include/asm/syscall_wrapper.h new file mode 100644 index 000000000000..67486c67e8a2 --- /dev/null +++ b/arch/powerpc/include/asm/syscall_wrapper.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * syscall_wrapper.h - powerpc specific wrappers to syscall definitions + * + * Based on arch/{x86,arm64}/include/asm/syscall_wrapper.h + */ + +#ifndef __ASM_POWERPC_SYSCALL_WRAPPER_H +#define __ASM_POWERPC_SYSCALL_WRAPPER_H + +struct pt_regs; + +#define SC_POWERPC_REGS_TO_ARGS(x, ...) \ + __MAP(x,__SC_ARGS \ + ,,regs->gpr[3],,regs->gpr[4],,regs->gpr[5] \ + ,,regs->gpr[6],,regs->gpr[7],,regs->gpr[8]) + +#define __SYSCALL_DEFINEx(x, name, ...) \ + long sys##name(const struct pt_regs *regs); \ + ALLOW_ERROR_INJECTION(sys##name, ERRNO); \ + static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ + static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ + long sys##name(const struct pt_regs *regs) \ + { \ + return __se_sys##name(SC_POWERPC_REGS_TO_ARGS(x,__VA_ARGS__)); \ + } \ + static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ + { \ + long ret = __do_sys##name(__MAP(x,__SC_CAST,__VA_ARGS__)); \ + __MAP(x,__SC_TEST,__VA_ARGS__); \ + __PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__)); \ + return ret; \ + } \ + static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) + +#define SYSCALL_DEFINE0(sname) \ + SYSCALL_METADATA(_##sname, 0); \ + long sys_##sname(const struct pt_regs *__unused); \ + ALLOW_ERROR_INJECTION(sys_##sname, ERRNO); \ + long sys_##sname(const struct pt_regs *__unused) + +#define COND_SYSCALL(name) \ + long sys_##name(const struct pt_regs *regs); \ + long __weak sys_##name(const struct pt_regs *regs) \ + { \ + return sys_ni_syscall(); \ + } + +#endif // __ASM_POWERPC_SYSCALL_WRAPPER_H diff --git a/arch/powerpc/include/asm/syscalls.h b/arch/powerpc/include/asm/syscalls.h index a2b13e55254f..9840d572da55 100644 --- a/arch/powerpc/include/asm/syscalls.h +++ b/arch/powerpc/include/asm/syscalls.h @@ -8,49 +8,131 @@ #include #include +#include +#ifdef CONFIG_PPC64 +#include +#endif +#include +#include + +#ifndef CONFIG_ARCH_HAS_SYSCALL_WRAPPER +long sys_ni_syscall(void); +#else +long sys_ni_syscall(const struct pt_regs *regs); +#endif + struct rtas_args; -asmlinkage long sys_mmap(unsigned long addr, size_t len, - unsigned long prot, unsigned long flags, - unsigned long fd, off_t offset); -asmlinkage long sys_mmap2(unsigned long addr, size_t len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long pgoff); -asmlinkage long ppc64_personality(unsigned long personality); -asmlinkage long sys_rtas(struct rtas_args __user *uargs); -int ppc_select(int n, fd_set __user *inp, fd_set __user *outp, - fd_set __user *exp, struct __kernel_old_timeval __user *tvp); -long ppc_fadvise64_64(int fd, int advice, u32 offset_high, u32 offset_low, - u32 len_high, u32 len_low); +/* + * long long munging: + * The 32 bit ABI passes long longs in an odd even register pair. + * High and low parts are swapped depending on endian mode, + * so define a macro (similar to mips linux32) to handle that. + */ +#ifdef __LITTLE_ENDIAN__ +#define merge_64(low, high) (((u64)high << 32) | low) +#else +#define merge_64(high, low) (((u64)high << 32) | low) +#endif + +/* + * PowerPC architecture-specific syscalls + */ + +#ifndef CONFIG_ARCH_HAS_SYSCALL_WRAPPER + +long sys_rtas(struct rtas_args __user *uargs); + +#ifdef CONFIG_PPC64 +long sys_ppc64_personality(unsigned long personality); +#ifdef CONFIG_COMPAT +long compat_sys_ppc64_personality(unsigned long personality); +#endif /* CONFIG_COMPAT */ +#endif /* CONFIG_PPC64 */ + +long sys_swapcontext(struct ucontext __user *old_ctx, + struct ucontext __user *new_ctx, long ctx_size); +long sys_mmap(unsigned long addr, size_t len, + unsigned long prot, unsigned long flags, + unsigned long fd, off_t offset); +long sys_mmap2(unsigned long addr, size_t len, + unsigned long prot, unsigned long flags, + unsigned long fd, unsigned long pgoff); +long sys_switch_endian(void); + +#ifdef CONFIG_PPC32 +long sys_sigreturn(void); +long sys_debug_setcontext(struct ucontext __user *ctx, int ndbg, + struct sig_dbg_op __user *dbg); +#endif + +long sys_rt_sigreturn(void); + +long sys_subpage_prot(unsigned long addr, + unsigned long len, u32 __user *map); #ifdef CONFIG_COMPAT -unsigned long compat_sys_mmap2(unsigned long addr, size_t len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long pgoff); +long compat_sys_swapcontext(struct ucontext32 __user *old_ctx, + struct ucontext32 __user *new_ctx, + int ctx_size); +long compat_sys_old_getrlimit(unsigned int resource, + struct compat_rlimit __user *rlim); +long compat_sys_sigreturn(void); +long compat_sys_rt_sigreturn(void); +#endif /* CONFIG_COMPAT */ -compat_ssize_t compat_sys_pread64(unsigned int fd, char __user *ubuf, compat_size_t count, - u32 reg6, u32 pos1, u32 pos2); +/* + * Architecture specific signatures required by long long munging: + * The 32 bit ABI passes long longs in an odd even register pair. + * The following signatures provide a machine long parameter for + * each register that will be supplied. The implementation is + * responsible for combining parameter pairs. + */ -compat_ssize_t compat_sys_pwrite64(unsigned int fd, const char __user *ubuf, compat_size_t count, - u32 reg6, u32 pos1, u32 pos2); +#ifdef CONFIG_COMPAT +long compat_sys_mmap2(unsigned long addr, size_t len, + unsigned long prot, unsigned long flags, + unsigned long fd, unsigned long pgoff); +long compat_sys_ppc_pread64(unsigned int fd, + char __user *ubuf, compat_size_t count, + u32 reg6, u32 pos1, u32 pos2); +long compat_sys_ppc_pwrite64(unsigned int fd, + const char __user *ubuf, compat_size_t count, + u32 reg6, u32 pos1, u32 pos2); +long compat_sys_ppc_readahead(int fd, u32 r4, + u32 offset1, u32 offset2, u32 count); +long compat_sys_ppc_truncate64(const char __user *path, u32 reg4, + unsigned long len1, unsigned long len2); +long compat_sys_ppc_ftruncate64(unsigned int fd, u32 reg4, + unsigned long len1, unsigned long len2); +long compat_sys_ppc32_fadvise64(int fd, u32 unused, u32 offset1, u32 offset2, + size_t len, int advice); +long compat_sys_ppc_sync_file_range2(int fd, unsigned int flags, + unsigned int offset1, + unsigned int offset2, + unsigned int nbytes1, + unsigned int nbytes2); +#endif /* CONFIG_COMPAT */ -compat_ssize_t compat_sys_readahead(int fd, u32 r4, u32 offset1, u32 offset2, u32 count); - -int compat_sys_truncate64(const char __user *path, u32 reg4, - unsigned long len1, unsigned long len2); - -long compat_sys_fallocate(int fd, int mode, u32 offset1, u32 offset2, u32 len1, u32 len2); - -int compat_sys_ftruncate64(unsigned int fd, u32 reg4, unsigned long len1, - unsigned long len2); - -long ppc32_fadvise64(int fd, u32 unused, u32 offset1, u32 offset2, - size_t len, int advice); - -long compat_sys_sync_file_range2(int fd, unsigned int flags, - unsigned int offset1, unsigned int offset2, - unsigned int nbytes1, unsigned int nbytes2); +#if defined(CONFIG_PPC32) || defined(CONFIG_COMPAT) +long sys_ppc_fadvise64_64(int fd, int advice, + u32 offset_high, u32 offset_low, + u32 len_high, u32 len_low); #endif +#else + +#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, native) +#define __SYSCALL(nr, entry) \ + long entry(const struct pt_regs *regs); + +#ifdef CONFIG_PPC64 +#include +#else +#include +#endif /* CONFIG_PPC64 */ + +#endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */ + #endif /* __KERNEL__ */ #endif /* __ASM_POWERPC_SYSCALLS_H */ diff --git a/arch/powerpc/kernel/ppc32.h b/arch/powerpc/include/asm/syscalls_32.h similarity index 93% rename from arch/powerpc/kernel/ppc32.h rename to arch/powerpc/include/asm/syscalls_32.h index 2346f8c7ff2e..749255568be9 100644 --- a/arch/powerpc/kernel/ppc32.h +++ b/arch/powerpc/include/asm/syscalls_32.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ -#ifndef _PPC64_PPC32_H -#define _PPC64_PPC32_H +#ifndef _ASM_POWERPC_SYSCALLS_32_H +#define _ASM_POWERPC_SYSCALLS_32_H #include #include @@ -57,4 +57,4 @@ struct ucontext32 { struct mcontext32 uc_mcontext; }; -#endif /* _PPC64_PPC32_H */ +#endif // _ASM_POWERPC_SYSCALLS_32_H diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index 1e5643a9b1f2..9f50766c4623 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -116,8 +116,9 @@ unsigned long long tb_to_ns(unsigned long long tb_ticks); void timer_broadcast_interrupt(void); -/* SPLPAR */ -void accumulate_stolen_time(void); +/* SPLPAR and VIRT_CPU_ACCOUNTING_NATIVE */ +void pseries_accumulate_stolen_time(void); +u64 pseries_calculate_stolen_time(u64 stop_tb); #endif /* __KERNEL__ */ #endif /* __POWERPC_TIME_H */ diff --git a/arch/powerpc/include/asm/udbg.h b/arch/powerpc/include/asm/udbg.h index b4aa0d88ce2c..b1f094728b35 100644 --- a/arch/powerpc/include/asm/udbg.h +++ b/arch/powerpc/include/asm/udbg.h @@ -15,13 +15,13 @@ extern void (*udbg_flush)(void); extern int (*udbg_getc)(void); extern int (*udbg_getc_poll)(void); -extern void udbg_puts(const char *s); -extern int udbg_write(const char *s, int n); +void udbg_puts(const char *s); +int udbg_write(const char *s, int n); -extern void register_early_udbg_console(void); -extern void udbg_printf(const char *fmt, ...) +void register_early_udbg_console(void); +void udbg_printf(const char *fmt, ...) __attribute__ ((format (printf, 1, 2))); -extern void udbg_progress(char *s, unsigned short hex); +void udbg_progress(char *s, unsigned short hex); void __init udbg_uart_init_mmio(void __iomem *addr, unsigned int stride); void __init udbg_uart_init_pio(unsigned long port, unsigned int stride); @@ -31,28 +31,28 @@ unsigned int __init udbg_probe_uart_speed(unsigned int clock); struct device_node; void __init udbg_scc_init(int force_scc); -extern int udbg_adb_init(int force_btext); -extern void udbg_adb_init_early(void); +int udbg_adb_init(int force_btext); +void udbg_adb_init_early(void); -extern void __init udbg_early_init(void); -extern void __init udbg_init_debug_lpar(void); -extern void __init udbg_init_debug_lpar_hvsi(void); -extern void __init udbg_init_pmac_realmode(void); -extern void __init udbg_init_maple_realmode(void); -extern void __init udbg_init_pas_realmode(void); -extern void __init udbg_init_rtas_panel(void); -extern void __init udbg_init_rtas_console(void); -extern void __init udbg_init_debug_beat(void); -extern void __init udbg_init_btext(void); -extern void __init udbg_init_44x_as1(void); -extern void __init udbg_init_40x_realmode(void); -extern void __init udbg_init_cpm(void); -extern void __init udbg_init_usbgecko(void); -extern void __init udbg_init_memcons(void); -extern void __init udbg_init_ehv_bc(void); -extern void __init udbg_init_ps3gelic(void); -extern void __init udbg_init_debug_opal_raw(void); -extern void __init udbg_init_debug_opal_hvsi(void); +void __init udbg_early_init(void); +void __init udbg_init_debug_lpar(void); +void __init udbg_init_debug_lpar_hvsi(void); +void __init udbg_init_pmac_realmode(void); +void __init udbg_init_maple_realmode(void); +void __init udbg_init_pas_realmode(void); +void __init udbg_init_rtas_panel(void); +void __init udbg_init_rtas_console(void); +void __init udbg_init_btext(void); +void __init udbg_init_44x_as1(void); +void __init udbg_init_40x_realmode(void); +void __init udbg_init_cpm(void); +void __init udbg_init_usbgecko(void); +void __init udbg_init_memcons(void); +void __init udbg_init_ehv_bc(void); +void __init udbg_init_ps3gelic(void); +void __init udbg_init_debug_opal_raw(void); +void __init udbg_init_debug_opal_hvsi(void); +void __init udbg_init_debug_16550(void); #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_UDBG_H */ diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index b1129b4ef57d..659a996c75aa 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -45,6 +45,7 @@ #define __ARCH_WANT_SYS_UTIME #define __ARCH_WANT_SYS_NEWFSTATAT #define __ARCH_WANT_COMPAT_STAT +#define __ARCH_WANT_COMPAT_FALLOCATE #define __ARCH_WANT_COMPAT_SYS_SENDFILE #endif #define __ARCH_WANT_SYS_FORK diff --git a/arch/powerpc/include/asm/vdso.h b/arch/powerpc/include/asm/vdso.h index 8542e9bbeead..7650b6ce14c8 100644 --- a/arch/powerpc/include/asm/vdso.h +++ b/arch/powerpc/include/asm/vdso.h @@ -2,9 +2,6 @@ #ifndef _ASM_POWERPC_VDSO_H #define _ASM_POWERPC_VDSO_H -/* Default map addresses for 32bit vDSO */ -#define VDSO32_MBASE 0x100000 - #define VDSO_VERSION_STRING LINUX_2.6.15 #ifndef __ASSEMBLY__ diff --git a/arch/powerpc/include/asm/vdso/processor.h b/arch/powerpc/include/asm/vdso/processor.h index 8d79f994b4aa..80d13207c568 100644 --- a/arch/powerpc/include/asm/vdso/processor.h +++ b/arch/powerpc/include/asm/vdso/processor.h @@ -22,7 +22,13 @@ #endif #ifdef CONFIG_PPC64 -#define cpu_relax() do { HMT_low(); HMT_medium(); barrier(); } while (0) +#define cpu_relax() \ + asm volatile(ASM_FTR_IFCLR( \ + /* Pre-POWER10 uses low ; medium priority nops */ \ + "or 1,1,1 ; or 2,2,2", \ + /* POWER10 onward uses pause_short (wait 2,0) */ \ + PPC_WAIT(2, 0), \ + %0) :: "i" (CPU_FTR_ARCH_31) : "memory") #else #define cpu_relax() barrier() #endif diff --git a/arch/powerpc/include/asm/vdso/timebase.h b/arch/powerpc/include/asm/vdso/timebase.h index 891c9d5eaabe..e9245f86a46c 100644 --- a/arch/powerpc/include/asm/vdso/timebase.h +++ b/arch/powerpc/include/asm/vdso/timebase.h @@ -12,7 +12,7 @@ * We use __powerpc64__ here because we want the compat VDSO to use the 32-bit * version below in the else case of the ifdef. */ -#if defined(__powerpc64__) && (defined(CONFIG_PPC_CELL) || defined(CONFIG_E500)) +#if defined(__powerpc64__) && (defined(CONFIG_PPC_CELL) || defined(CONFIG_PPC_E500)) #define mftb() ({unsigned long rval; \ asm volatile( \ "90: mfspr %0, %2;\n" \ diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h index e2e704eca5f6..89090485bec1 100644 --- a/arch/powerpc/include/asm/xics.h +++ b/arch/powerpc/include/asm/xics.h @@ -159,7 +159,6 @@ extern void xics_setup_cpu(void); extern void xics_update_irq_servers(void); extern void xics_set_cpu_giq(unsigned int gserver, unsigned int join); extern void xics_mask_unknown_vec(unsigned int vec); -extern irqreturn_t xics_ipi_dispatch(int cpu); extern void xics_smp_probe(void); extern void xics_register_ics(struct ics *ics); extern void xics_teardown_cpu(void); diff --git a/arch/powerpc/kernel/fsl_booke_entry_mapping.S b/arch/powerpc/kernel/85xx_entry_mapping.S similarity index 100% rename from arch/powerpc/kernel/fsl_booke_entry_mapping.S rename to arch/powerpc/kernel/85xx_entry_mapping.S diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 06d2d1f78f71..1f121c188805 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -81,7 +81,7 @@ obj-$(CONFIG_PPC_DAWR) += dawr.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o -obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o +obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_64e.o obj-$(CONFIG_PPC_BARRIER_NOSPEC) += security.o obj-$(CONFIG_PPC64) += vdso64_wrapper.o obj-$(CONFIG_ALTIVEC) += vecemu.o @@ -100,21 +100,19 @@ obj-$(CONFIG_GENERIC_TBSYNC) += smp-tbsync.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_FA_DUMP) += fadump.o obj-$(CONFIG_PRESERVE_FA_DUMP) += fadump.o -ifdef CONFIG_PPC32 -obj-$(CONFIG_E500) += idle_e500.o -endif +obj-$(CONFIG_PPC_85xx) += idle_85xx.o obj-$(CONFIG_PPC_BOOK3S_32) += idle_6xx.o l2cr_6xx.o cpu_setup_6xx.o obj-$(CONFIG_TAU) += tau_6xx.o obj-$(CONFIG_HIBERNATION) += swsusp.o suspend.o -ifdef CONFIG_FSL_BOOKE -obj-$(CONFIG_HIBERNATION) += swsusp_booke.o +ifdef CONFIG_PPC_85xx +obj-$(CONFIG_HIBERNATION) += swsusp_85xx.o else obj-$(CONFIG_HIBERNATION) += swsusp_$(BITS).o endif obj64-$(CONFIG_HIBERNATION) += swsusp_asm64.o obj-$(CONFIG_MODULES) += module.o module_$(BITS).o obj-$(CONFIG_44x) += cpu_setup_44x.o -obj-$(CONFIG_PPC_FSL_BOOK3E) += cpu_setup_fsl_booke.o +obj-$(CONFIG_PPC_E500) += cpu_setup_e500.o obj-$(CONFIG_PPC_DOORBELL) += dbell.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o @@ -122,7 +120,7 @@ extra-$(CONFIG_PPC64) := head_64.o extra-$(CONFIG_PPC_BOOK3S_32) := head_book3s_32.o extra-$(CONFIG_40x) := head_40x.o extra-$(CONFIG_44x) := head_44x.o -extra-$(CONFIG_FSL_BOOKE) := head_fsl_booke.o +extra-$(CONFIG_PPC_85xx) := head_85xx.o extra-$(CONFIG_PPC_8xx) := head_8xx.o extra-y += vmlinux.lds diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 8c10f536e478..4ce2a4aa3985 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -59,7 +59,7 @@ #endif #endif -#if defined(CONFIG_PPC_FSL_BOOK3E) +#if defined(CONFIG_PPC_E500) #include "../mm/mmu_decl.h" #endif @@ -197,7 +197,7 @@ int main(void) OFFSET(PACAIRQHAPPENED, paca_struct, irq_happened); OFFSET(PACA_FTRACE_ENABLED, paca_struct, ftrace_enabled); -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 OFFSET(PACAPGD, paca_struct, pgd); OFFSET(PACA_KERNELPGD, paca_struct, kernel_pgd); OFFSET(PACA_EXGEN, paca_struct, exgen); @@ -213,7 +213,7 @@ int main(void) OFFSET(TCD_ESEL_NEXT, tlb_core_data, esel_next); OFFSET(TCD_ESEL_MAX, tlb_core_data, esel_max); OFFSET(TCD_ESEL_FIRST, tlb_core_data, esel_first); -#endif /* CONFIG_PPC_BOOK3E */ +#endif /* CONFIG_PPC_BOOK3E_64 */ #ifdef CONFIG_PPC_BOOK3S_64 OFFSET(PACA_EXGEN, paca_struct, exgen); @@ -248,7 +248,7 @@ int main(void) #ifdef CONFIG_PPC64 OFFSET(PACA_EXIT_SAVE_R1, paca_struct, exit_save_r1); #endif -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 OFFSET(PACA_TRAP_SAVE, paca_struct, trap_save); #endif OFFSET(PACA_SPRG_VDSO, paca_struct, sprg_vdso); @@ -651,7 +651,7 @@ int main(void) DEFINE(PGD_T_LOG2, PGD_T_LOG2); DEFINE(PTE_T_LOG2, PTE_T_LOG2); #endif -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 DEFINE(TLBCAM_SIZE, sizeof(struct tlbcam)); OFFSET(TLBCAM_MAS0, tlbcam, MAS0); OFFSET(TLBCAM_MAS1, tlbcam, MAS1); diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_e500.S similarity index 98% rename from arch/powerpc/kernel/cpu_setup_fsl_booke.S rename to arch/powerpc/kernel/cpu_setup_e500.S index 4bf33f1b4193..2ab25161b0ad 100644 --- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S +++ b/arch/powerpc/kernel/cpu_setup_e500.S @@ -12,7 +12,7 @@ #include #include #include -#include +#include #include #include @@ -108,7 +108,7 @@ _GLOBAL(__setup_cpu_e6500) #endif /* CONFIG_PPC_E500MC */ #ifdef CONFIG_PPC32 -#ifdef CONFIG_E500 +#ifdef CONFIG_PPC_E500 #ifndef CONFIG_PPC_E500MC _GLOBAL(__setup_cpu_e500v1) _GLOBAL(__setup_cpu_e500v2) @@ -156,7 +156,7 @@ _GLOBAL(__setup_cpu_e5500) mtlr r5 blr #endif /* CONFIG_PPC_E500MC */ -#endif /* CONFIG_E500 */ +#endif /* CONFIG_PPC_E500 */ #endif /* CONFIG_PPC32 */ #ifdef CONFIG_PPC_BOOK3E_64 diff --git a/arch/powerpc/kernel/cpu_setup_power.c b/arch/powerpc/kernel/cpu_setup_power.c index 3dc61e203f37..097c033668f0 100644 --- a/arch/powerpc/kernel/cpu_setup_power.c +++ b/arch/powerpc/kernel/cpu_setup_power.c @@ -11,7 +11,7 @@ #include #include #include -#include +#include /* Disable CPU_FTR_HVMODE and return false if MSR:HV is not set */ static bool init_hvmode_206(struct cpu_spec *t) diff --git a/arch/powerpc/kernel/cpu_specs.h b/arch/powerpc/kernel/cpu_specs.h new file mode 100644 index 000000000000..85ded3f77204 --- /dev/null +++ b/arch/powerpc/kernel/cpu_specs.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifdef CONFIG_40x +#include "cpu_specs_40x.h" +#endif + +#ifdef CONFIG_PPC_47x +#include "cpu_specs_47x.h" +#elif defined(CONFIG_44x) +#include "cpu_specs_44x.h" +#endif + +#ifdef CONFIG_PPC_8xx +#include "cpu_specs_8xx.h" +#endif + +#ifdef CONFIG_PPC_E500MC +#include "cpu_specs_e500mc.h" +#elif defined(CONFIG_PPC_85xx) +#include "cpu_specs_85xx.h" +#endif + +#ifdef CONFIG_PPC_BOOK3S_32 +#include "cpu_specs_book3s_32.h" +#endif + +#ifdef CONFIG_PPC_BOOK3S_64 +#include "cpu_specs_book3s_64.h" +#endif diff --git a/arch/powerpc/kernel/cpu_specs_40x.h b/arch/powerpc/kernel/cpu_specs_40x.h new file mode 100644 index 000000000000..a1362a75b8c8 --- /dev/null +++ b/arch/powerpc/kernel/cpu_specs_40x.h @@ -0,0 +1,280 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org) + */ + +static struct cpu_spec cpu_specs[] __initdata = { + { /* STB 04xxx */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x41810000, + .cpu_name = "STB04xxx", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | + PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc405", + }, + { /* NP405L */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x41610000, + .cpu_name = "NP405L", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | + PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc405", + }, + { /* NP4GS3 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x40B10000, + .cpu_name = "NP4GS3", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | + PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc405", + }, + { /* NP405H */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x41410000, + .cpu_name = "NP405H", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | + PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc405", + }, + { /* 405GPr */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x50910000, + .cpu_name = "405GPr", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | + PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc405", + }, + { /* STBx25xx */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x51510000, + .cpu_name = "STBx25xx", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | + PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc405", + }, + { /* 405LP */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x41F10000, + .cpu_name = "405LP", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .mmu_features = MMU_FTR_TYPE_40x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc405", + }, + { /* 405EP */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x51210000, + .cpu_name = "405EP", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | + PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc405", + }, + { /* 405EX Rev. A/B with Security */ + .pvr_mask = 0xffff000f, + .pvr_value = 0x12910007, + .cpu_name = "405EX Rev. A/B", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | + PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc405", + }, + { /* 405EX Rev. C without Security */ + .pvr_mask = 0xffff000f, + .pvr_value = 0x1291000d, + .cpu_name = "405EX Rev. C", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | + PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc405", + }, + { /* 405EX Rev. C with Security */ + .pvr_mask = 0xffff000f, + .pvr_value = 0x1291000f, + .cpu_name = "405EX Rev. C", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | + PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc405", + }, + { /* 405EX Rev. D without Security */ + .pvr_mask = 0xffff000f, + .pvr_value = 0x12910003, + .cpu_name = "405EX Rev. D", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | + PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc405", + }, + { /* 405EX Rev. D with Security */ + .pvr_mask = 0xffff000f, + .pvr_value = 0x12910005, + .cpu_name = "405EX Rev. D", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | + PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc405", + }, + { /* 405EXr Rev. A/B without Security */ + .pvr_mask = 0xffff000f, + .pvr_value = 0x12910001, + .cpu_name = "405EXr Rev. A/B", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | + PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc405", + }, + { /* 405EXr Rev. C without Security */ + .pvr_mask = 0xffff000f, + .pvr_value = 0x12910009, + .cpu_name = "405EXr Rev. C", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | + PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc405", + }, + { /* 405EXr Rev. C with Security */ + .pvr_mask = 0xffff000f, + .pvr_value = 0x1291000b, + .cpu_name = "405EXr Rev. C", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | + PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc405", + }, + { /* 405EXr Rev. D without Security */ + .pvr_mask = 0xffff000f, + .pvr_value = 0x12910000, + .cpu_name = "405EXr Rev. D", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | + PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc405", + }, + { /* 405EXr Rev. D with Security */ + .pvr_mask = 0xffff000f, + .pvr_value = 0x12910002, + .cpu_name = "405EXr Rev. D", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | + PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc405", + }, + { + /* 405EZ */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x41510000, + .cpu_name = "405EZ", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | + PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc405", + }, + { /* APM8018X */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x7ff11432, + .cpu_name = "APM8018X", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | + PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc405", + }, + { /* default match */ + .pvr_mask = 0x00000000, + .pvr_value = 0x00000000, + .cpu_name = "(generic 40x PPC)", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | + PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc405", + } +}; diff --git a/arch/powerpc/kernel/cpu_specs_44x.h b/arch/powerpc/kernel/cpu_specs_44x.h new file mode 100644 index 000000000000..69c4cdc0cdee --- /dev/null +++ b/arch/powerpc/kernel/cpu_specs_44x.h @@ -0,0 +1,304 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org) + */ + +#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ + PPC_FEATURE_BOOKE) + +static struct cpu_spec cpu_specs[] __initdata = { + { + .pvr_mask = 0xf0000fff, + .pvr_value = 0x40000850, + .cpu_name = "440GR Rev. A", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc440", + }, + { /* Use logical PVR for 440EP (logical pvr = pvr | 0x8) */ + .pvr_mask = 0xf0000fff, + .pvr_value = 0x40000858, + .cpu_name = "440EP Rev. A", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_44x, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_440ep, + .machine_check = machine_check_4xx, + .platform = "ppc440", + }, + { + .pvr_mask = 0xf0000fff, + .pvr_value = 0x400008d3, + .cpu_name = "440GR Rev. B", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_44x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc440", + }, + { /* Matches both physical and logical PVR for 440EP (logical pvr = pvr | 0x8) */ + .pvr_mask = 0xf0000ff7, + .pvr_value = 0x400008d4, + .cpu_name = "440EP Rev. C", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_44x, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_440ep, + .machine_check = machine_check_4xx, + .platform = "ppc440", + }, + { /* Use logical PVR for 440EP (logical pvr = pvr | 0x8) */ + .pvr_mask = 0xf0000fff, + .pvr_value = 0x400008db, + .cpu_name = "440EP Rev. B", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_44x, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_440ep, + .machine_check = machine_check_4xx, + .platform = "ppc440", + }, + { /* 440GRX */ + .pvr_mask = 0xf0000ffb, + .pvr_value = 0x200008D0, + .cpu_name = "440GRX", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_440grx, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* Use logical PVR for 440EPx (logical pvr = pvr | 0x8) */ + .pvr_mask = 0xf0000ffb, + .pvr_value = 0x200008D8, + .cpu_name = "440EPX", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_44x, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_440epx, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* 440GP Rev. B */ + .pvr_mask = 0xf0000fff, + .pvr_value = 0x40000440, + .cpu_name = "440GP Rev. B", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc440gp", + }, + { /* 440GP Rev. C */ + .pvr_mask = 0xf0000fff, + .pvr_value = 0x40000481, + .cpu_name = "440GP Rev. C", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc440gp", + }, + { /* 440GX Rev. A */ + .pvr_mask = 0xf0000fff, + .pvr_value = 0x50000850, + .cpu_name = "440GX Rev. A", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_440gx, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* 440GX Rev. B */ + .pvr_mask = 0xf0000fff, + .pvr_value = 0x50000851, + .cpu_name = "440GX Rev. B", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_440gx, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* 440GX Rev. C */ + .pvr_mask = 0xf0000fff, + .pvr_value = 0x50000892, + .cpu_name = "440GX Rev. C", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_440gx, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* 440GX Rev. F */ + .pvr_mask = 0xf0000fff, + .pvr_value = 0x50000894, + .cpu_name = "440GX Rev. F", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_440gx, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* 440SP Rev. A */ + .pvr_mask = 0xfff00fff, + .pvr_value = 0x53200891, + .cpu_name = "440SP Rev. A", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc440", + }, + { /* 440SPe Rev. A */ + .pvr_mask = 0xfff00fff, + .pvr_value = 0x53400890, + .cpu_name = "440SPe Rev. A", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_440spe, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* 440SPe Rev. B */ + .pvr_mask = 0xfff00fff, + .pvr_value = 0x53400891, + .cpu_name = "440SPe Rev. B", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_440spe, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* 460EX */ + .pvr_mask = 0xffff0006, + .pvr_value = 0x13020002, + .cpu_name = "460EX", + .cpu_features = CPU_FTRS_440x6, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_44x, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_460ex, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* 460EX Rev B */ + .pvr_mask = 0xffff0007, + .pvr_value = 0x13020004, + .cpu_name = "460EX Rev. B", + .cpu_features = CPU_FTRS_440x6, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_44x, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_460ex, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* 460GT */ + .pvr_mask = 0xffff0006, + .pvr_value = 0x13020000, + .cpu_name = "460GT", + .cpu_features = CPU_FTRS_440x6, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_44x, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_460gt, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* 460GT Rev B */ + .pvr_mask = 0xffff0007, + .pvr_value = 0x13020005, + .cpu_name = "460GT Rev. B", + .cpu_features = CPU_FTRS_440x6, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_44x, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_460gt, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* 460SX */ + .pvr_mask = 0xffffff00, + .pvr_value = 0x13541800, + .cpu_name = "460SX", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_460sx, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* 464 in APM821xx */ + .pvr_mask = 0xfffffff0, + .pvr_value = 0x12C41C80, + .cpu_name = "APM821XX", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = COMMON_USER_BOOKE | + PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_44x, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_apm821xx, + .machine_check = machine_check_440A, + .platform = "ppc440", + }, + { /* default match */ + .pvr_mask = 0x00000000, + .pvr_value = 0x00000000, + .cpu_name = "(generic 44x PPC)", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_4xx, + .platform = "ppc440", + } +}; diff --git a/arch/powerpc/kernel/cpu_specs_47x.h b/arch/powerpc/kernel/cpu_specs_47x.h new file mode 100644 index 000000000000..3143cd504a51 --- /dev/null +++ b/arch/powerpc/kernel/cpu_specs_47x.h @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org) + */ + +#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ + PPC_FEATURE_BOOKE) + +static struct cpu_spec cpu_specs[] __initdata = { + { /* 476 DD2 core */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x11a52080, + .cpu_name = "476", + .cpu_features = CPU_FTRS_47X | CPU_FTR_476_DD2, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_47x | MMU_FTR_USE_TLBIVAX_BCAST | + MMU_FTR_LOCK_BCAST_INVAL, + .icache_bsize = 32, + .dcache_bsize = 128, + .machine_check = machine_check_47x, + .platform = "ppc470", + }, + { /* 476fpe */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x7ff50000, + .cpu_name = "476fpe", + .cpu_features = CPU_FTRS_47X | CPU_FTR_476_DD2, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_47x | MMU_FTR_USE_TLBIVAX_BCAST | + MMU_FTR_LOCK_BCAST_INVAL, + .icache_bsize = 32, + .dcache_bsize = 128, + .machine_check = machine_check_47x, + .platform = "ppc470", + }, + { /* 476 iss */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00050000, + .cpu_name = "476", + .cpu_features = CPU_FTRS_47X, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_47x | MMU_FTR_USE_TLBIVAX_BCAST | + MMU_FTR_LOCK_BCAST_INVAL, + .icache_bsize = 32, + .dcache_bsize = 128, + .machine_check = machine_check_47x, + .platform = "ppc470", + }, + { /* 476 others */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x11a50000, + .cpu_name = "476", + .cpu_features = CPU_FTRS_47X, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_47x | MMU_FTR_USE_TLBIVAX_BCAST | + MMU_FTR_LOCK_BCAST_INVAL, + .icache_bsize = 32, + .dcache_bsize = 128, + .machine_check = machine_check_47x, + .platform = "ppc470", + }, + { /* default match */ + .pvr_mask = 0x00000000, + .pvr_value = 0x00000000, + .cpu_name = "(generic 47x PPC)", + .cpu_features = CPU_FTRS_47X, + .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_47x, + .icache_bsize = 32, + .dcache_bsize = 128, + .machine_check = machine_check_47x, + .platform = "ppc470", + } +}; diff --git a/arch/powerpc/kernel/cpu_specs_85xx.h b/arch/powerpc/kernel/cpu_specs_85xx.h new file mode 100644 index 000000000000..aaae202c1a89 --- /dev/null +++ b/arch/powerpc/kernel/cpu_specs_85xx.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org) + */ + +#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ + PPC_FEATURE_BOOKE) + +static struct cpu_spec cpu_specs[] __initdata = { + { /* e500 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80200000, + .cpu_name = "e500", + .cpu_features = CPU_FTRS_E500, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_SPE_COMP | + PPC_FEATURE_HAS_EFP_SINGLE_COMP, + .cpu_user_features2 = PPC_FEATURE2_ISEL, + .mmu_features = MMU_FTR_TYPE_FSL_E, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_e500v1, + .machine_check = machine_check_e500, + .platform = "ppc8540", + }, + { /* e500v2 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80210000, + .cpu_name = "e500v2", + .cpu_features = CPU_FTRS_E500_2, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_SPE_COMP | + PPC_FEATURE_HAS_EFP_SINGLE_COMP | + PPC_FEATURE_HAS_EFP_DOUBLE_COMP, + .cpu_user_features2 = PPC_FEATURE2_ISEL, + .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_e500v2, + .machine_check = machine_check_e500, + .platform = "ppc8548", + .cpu_down_flush = cpu_down_flush_e500v2, + }, + { /* default match */ + .pvr_mask = 0x00000000, + .pvr_value = 0x00000000, + .cpu_name = "(generic E500 PPC)", + .cpu_features = CPU_FTRS_E500, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_SPE_COMP | + PPC_FEATURE_HAS_EFP_SINGLE_COMP, + .mmu_features = MMU_FTR_TYPE_FSL_E, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_e500, + .platform = "powerpc", + } +}; diff --git a/arch/powerpc/kernel/cpu_specs_8xx.h b/arch/powerpc/kernel/cpu_specs_8xx.h new file mode 100644 index 000000000000..93ddbc202ba3 --- /dev/null +++ b/arch/powerpc/kernel/cpu_specs_8xx.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org) + */ + +static struct cpu_spec cpu_specs[] __initdata = { + { /* 8xx */ + .pvr_mask = 0xffff0000, + .pvr_value = PVR_8xx, + .cpu_name = "8xx", + /* + * CPU_FTR_MAYBE_CAN_DOZE is possible, + * if the 8xx code is there.... + */ + .cpu_features = CPU_FTRS_8XX, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .mmu_features = MMU_FTR_TYPE_8xx, + .icache_bsize = 16, + .dcache_bsize = 16, + .machine_check = machine_check_8xx, + .platform = "ppc823", + }, +}; diff --git a/arch/powerpc/kernel/cpu_specs_book3s_32.h b/arch/powerpc/kernel/cpu_specs_book3s_32.h new file mode 100644 index 000000000000..3714634d194a --- /dev/null +++ b/arch/powerpc/kernel/cpu_specs_book3s_32.h @@ -0,0 +1,605 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org) + */ + +#define COMMON_USER (PPC_FEATURE_32 | PPC_FEATURE_HAS_FPU | \ + PPC_FEATURE_HAS_MMU) + +static struct cpu_spec cpu_specs[] __initdata = { +#ifdef CONFIG_PPC_BOOK3S_603 + { /* 603 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00030000, + .cpu_name = "603", + .cpu_features = CPU_FTRS_603, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = 0, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_603, + .machine_check = machine_check_generic, + .platform = "ppc603", + }, + { /* 603e */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00060000, + .cpu_name = "603e", + .cpu_features = CPU_FTRS_603, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = 0, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_603, + .machine_check = machine_check_generic, + .platform = "ppc603", + }, + { /* 603ev */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00070000, + .cpu_name = "603ev", + .cpu_features = CPU_FTRS_603, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = 0, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_603, + .machine_check = machine_check_generic, + .platform = "ppc603", + }, + { /* 82xx (8240, 8245, 8260 are all 603e cores) */ + .pvr_mask = 0x7fff0000, + .pvr_value = 0x00810000, + .cpu_name = "82xx", + .cpu_features = CPU_FTRS_82XX, + .cpu_user_features = COMMON_USER, + .mmu_features = 0, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_603, + .machine_check = machine_check_generic, + .platform = "ppc603", + }, + { /* All G2_LE (603e core, plus some) have the same pvr */ + .pvr_mask = 0x7fff0000, + .pvr_value = 0x00820000, + .cpu_name = "G2_LE", + .cpu_features = CPU_FTRS_G2_LE, + .cpu_user_features = COMMON_USER, + .mmu_features = MMU_FTR_USE_HIGH_BATS, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_603, + .machine_check = machine_check_generic, + .platform = "ppc603", + }, +#ifdef CONFIG_PPC_83xx + { /* e300c1 (a 603e core, plus some) on 83xx */ + .pvr_mask = 0x7fff0000, + .pvr_value = 0x00830000, + .cpu_name = "e300c1", + .cpu_features = CPU_FTRS_E300, + .cpu_user_features = COMMON_USER, + .mmu_features = MMU_FTR_USE_HIGH_BATS, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_603, + .machine_check = machine_check_83xx, + .platform = "ppc603", + }, + { /* e300c2 (an e300c1 core, plus some, minus FPU) on 83xx */ + .pvr_mask = 0x7fff0000, + .pvr_value = 0x00840000, + .cpu_name = "e300c2", + .cpu_features = CPU_FTRS_E300C2, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .mmu_features = MMU_FTR_USE_HIGH_BATS | MMU_FTR_NEED_DTLB_SW_LRU, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_603, + .machine_check = machine_check_83xx, + .platform = "ppc603", + }, + { /* e300c3 (e300c1, plus one IU, half cache size) on 83xx */ + .pvr_mask = 0x7fff0000, + .pvr_value = 0x00850000, + .cpu_name = "e300c3", + .cpu_features = CPU_FTRS_E300, + .cpu_user_features = COMMON_USER, + .mmu_features = MMU_FTR_USE_HIGH_BATS | MMU_FTR_NEED_DTLB_SW_LRU, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_603, + .machine_check = machine_check_83xx, + .num_pmcs = 4, + .platform = "ppc603", + }, + { /* e300c4 (e300c1, plus one IU) */ + .pvr_mask = 0x7fff0000, + .pvr_value = 0x00860000, + .cpu_name = "e300c4", + .cpu_features = CPU_FTRS_E300, + .cpu_user_features = COMMON_USER, + .mmu_features = MMU_FTR_USE_HIGH_BATS | MMU_FTR_NEED_DTLB_SW_LRU, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_603, + .machine_check = machine_check_83xx, + .num_pmcs = 4, + .platform = "ppc603", + }, +#endif +#endif /* CONFIG_PPC_BOOK3S_603 */ +#ifdef CONFIG_PPC_BOOK3S_604 + { /* 604 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00040000, + .cpu_name = "604", + .cpu_features = CPU_FTRS_604, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 2, + .cpu_setup = __setup_cpu_604, + .machine_check = machine_check_generic, + .platform = "ppc604", + }, + { /* 604e */ + .pvr_mask = 0xfffff000, + .pvr_value = 0x00090000, + .cpu_name = "604e", + .cpu_features = CPU_FTRS_604, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_604, + .machine_check = machine_check_generic, + .platform = "ppc604", + }, + { /* 604r */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00090000, + .cpu_name = "604r", + .cpu_features = CPU_FTRS_604, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_604, + .machine_check = machine_check_generic, + .platform = "ppc604", + }, + { /* 604ev */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x000a0000, + .cpu_name = "604ev", + .cpu_features = CPU_FTRS_604, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_604, + .machine_check = machine_check_generic, + .platform = "ppc604", + }, + { /* 740/750 (0x4202, don't support TAU ?) */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x00084202, + .cpu_name = "740/750", + .cpu_features = CPU_FTRS_740_NOTAU, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_750, + .machine_check = machine_check_generic, + .platform = "ppc750", + }, + { /* 750CX (80100 and 8010x?) */ + .pvr_mask = 0xfffffff0, + .pvr_value = 0x00080100, + .cpu_name = "750CX", + .cpu_features = CPU_FTRS_750, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_750cx, + .machine_check = machine_check_generic, + .platform = "ppc750", + }, + { /* 750CX (82201 and 82202) */ + .pvr_mask = 0xfffffff0, + .pvr_value = 0x00082200, + .cpu_name = "750CX", + .cpu_features = CPU_FTRS_750, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_750cx, + .machine_check = machine_check_generic, + .platform = "ppc750", + }, + { /* 750CXe (82214) */ + .pvr_mask = 0xfffffff0, + .pvr_value = 0x00082210, + .cpu_name = "750CXe", + .cpu_features = CPU_FTRS_750, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_750cx, + .machine_check = machine_check_generic, + .platform = "ppc750", + }, + { /* 750CXe "Gekko" (83214) */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x00083214, + .cpu_name = "750CXe", + .cpu_features = CPU_FTRS_750, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_750cx, + .machine_check = machine_check_generic, + .platform = "ppc750", + }, + { /* 750CL (and "Broadway") */ + .pvr_mask = 0xfffff0e0, + .pvr_value = 0x00087000, + .cpu_name = "750CL", + .cpu_features = CPU_FTRS_750CL, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_750, + .machine_check = machine_check_generic, + .platform = "ppc750", + }, + { /* 745/755 */ + .pvr_mask = 0xfffff000, + .pvr_value = 0x00083000, + .cpu_name = "745/755", + .cpu_features = CPU_FTRS_750, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_750, + .machine_check = machine_check_generic, + .platform = "ppc750", + }, + { /* 750FX rev 1.x */ + .pvr_mask = 0xffffff00, + .pvr_value = 0x70000100, + .cpu_name = "750FX", + .cpu_features = CPU_FTRS_750FX1, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_750, + .machine_check = machine_check_generic, + .platform = "ppc750", + }, + { /* 750FX rev 2.0 must disable HID0[DPM] */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x70000200, + .cpu_name = "750FX", + .cpu_features = CPU_FTRS_750FX2, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_750, + .machine_check = machine_check_generic, + .platform = "ppc750", + }, + { /* 750FX (All revs except 2.0) */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x70000000, + .cpu_name = "750FX", + .cpu_features = CPU_FTRS_750FX, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_750fx, + .machine_check = machine_check_generic, + .platform = "ppc750", + }, + { /* 750GX */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x70020000, + .cpu_name = "750GX", + .cpu_features = CPU_FTRS_750GX, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_750fx, + .machine_check = machine_check_generic, + .platform = "ppc750", + }, + { /* 740/750 (L2CR bit need fixup for 740) */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00080000, + .cpu_name = "740/750", + .cpu_features = CPU_FTRS_740, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_750, + .machine_check = machine_check_generic, + .platform = "ppc750", + }, + { /* 7400 rev 1.1 ? (no TAU) */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x000c1101, + .cpu_name = "7400 (1.1)", + .cpu_features = CPU_FTRS_7400_NOTAU, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | + PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .pmc_type = PPC_PMC_G4, + .cpu_setup = __setup_cpu_7400, + .machine_check = machine_check_generic, + .platform = "ppc7400", + }, + { /* 7400 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x000c0000, + .cpu_name = "7400", + .cpu_features = CPU_FTRS_7400, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | + PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .pmc_type = PPC_PMC_G4, + .cpu_setup = __setup_cpu_7400, + .machine_check = machine_check_generic, + .platform = "ppc7400", + }, + { /* 7410 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x800c0000, + .cpu_name = "7410", + .cpu_features = CPU_FTRS_7400, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | + PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .pmc_type = PPC_PMC_G4, + .cpu_setup = __setup_cpu_7410, + .machine_check = machine_check_generic, + .platform = "ppc7400", + }, + { /* 7450 2.0 - no doze/nap */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x80000200, + .cpu_name = "7450", + .cpu_features = CPU_FTRS_7450_20, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | + PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 6, + .pmc_type = PPC_PMC_G4, + .cpu_setup = __setup_cpu_745x, + .machine_check = machine_check_generic, + .platform = "ppc7450", + }, + { /* 7450 2.1 */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x80000201, + .cpu_name = "7450", + .cpu_features = CPU_FTRS_7450_21, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | + PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 6, + .pmc_type = PPC_PMC_G4, + .cpu_setup = __setup_cpu_745x, + .machine_check = machine_check_generic, + .platform = "ppc7450", + }, + { /* 7450 2.3 and newer */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80000000, + .cpu_name = "7450", + .cpu_features = CPU_FTRS_7450_23, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | + PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 6, + .pmc_type = PPC_PMC_G4, + .cpu_setup = __setup_cpu_745x, + .machine_check = machine_check_generic, + .platform = "ppc7450", + }, + { /* 7455 rev 1.x */ + .pvr_mask = 0xffffff00, + .pvr_value = 0x80010100, + .cpu_name = "7455", + .cpu_features = CPU_FTRS_7455_1, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | + PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 6, + .pmc_type = PPC_PMC_G4, + .cpu_setup = __setup_cpu_745x, + .machine_check = machine_check_generic, + .platform = "ppc7450", + }, + { /* 7455 rev 2.0 */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x80010200, + .cpu_name = "7455", + .cpu_features = CPU_FTRS_7455_20, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | + PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 6, + .pmc_type = PPC_PMC_G4, + .cpu_setup = __setup_cpu_745x, + .machine_check = machine_check_generic, + .platform = "ppc7450", + }, + { /* 7455 others */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80010000, + .cpu_name = "7455", + .cpu_features = CPU_FTRS_7455, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | + PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 6, + .pmc_type = PPC_PMC_G4, + .cpu_setup = __setup_cpu_745x, + .machine_check = machine_check_generic, + .platform = "ppc7450", + }, + { /* 7447/7457 Rev 1.0 */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x80020100, + .cpu_name = "7447/7457", + .cpu_features = CPU_FTRS_7447_10, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | + PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 6, + .pmc_type = PPC_PMC_G4, + .cpu_setup = __setup_cpu_745x, + .machine_check = machine_check_generic, + .platform = "ppc7450", + }, + { /* 7447/7457 Rev 1.1 */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x80020101, + .cpu_name = "7447/7457", + .cpu_features = CPU_FTRS_7447_10, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | + PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 6, + .pmc_type = PPC_PMC_G4, + .cpu_setup = __setup_cpu_745x, + .machine_check = machine_check_generic, + .platform = "ppc7450", + }, + { /* 7447/7457 Rev 1.2 and later */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80020000, + .cpu_name = "7447/7457", + .cpu_features = CPU_FTRS_7447, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | + PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 6, + .pmc_type = PPC_PMC_G4, + .cpu_setup = __setup_cpu_745x, + .machine_check = machine_check_generic, + .platform = "ppc7450", + }, + { /* 7447A */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80030000, + .cpu_name = "7447A", + .cpu_features = CPU_FTRS_7447A, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | + PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 6, + .pmc_type = PPC_PMC_G4, + .cpu_setup = __setup_cpu_745x, + .machine_check = machine_check_generic, + .platform = "ppc7450", + }, + { /* 7448 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80040000, + .cpu_name = "7448", + .cpu_features = CPU_FTRS_7448, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | + PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 6, + .pmc_type = PPC_PMC_G4, + .cpu_setup = __setup_cpu_745x, + .machine_check = machine_check_generic, + .platform = "ppc7450", + }, + { /* default match, we assume split I/D cache & TB (non-601)... */ + .pvr_mask = 0x00000000, + .pvr_value = 0x00000000, + .cpu_name = "(generic PPC)", + .cpu_features = CPU_FTRS_CLASSIC32, + .cpu_user_features = COMMON_USER, + .mmu_features = MMU_FTR_HPTE_TABLE, + .icache_bsize = 32, + .dcache_bsize = 32, + .machine_check = machine_check_generic, + .platform = "ppc603", + }, +#endif /* CONFIG_PPC_BOOK3S_604 */ +}; diff --git a/arch/powerpc/kernel/cpu_specs_book3s_64.h b/arch/powerpc/kernel/cpu_specs_book3s_64.h new file mode 100644 index 000000000000..c370c1b804a9 --- /dev/null +++ b/arch/powerpc/kernel/cpu_specs_book3s_64.h @@ -0,0 +1,481 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org) + * + * Modifications for ppc64: + * Copyright (C) 2003 Dave Engebretsen + */ + +/* NOTE: + * Unlike ppc32, ppc64 will only call cpu_setup() for the boot CPU, it's + * the responsibility of the appropriate CPU save/restore functions to + * eventually copy these settings over. Those save/restore aren't yet + * part of the cputable though. That has to be fixed for both ppc32 + * and ppc64 + */ +#define COMMON_USER_PPC64 (PPC_FEATURE_32 | PPC_FEATURE_HAS_FPU | \ + PPC_FEATURE_HAS_MMU | PPC_FEATURE_64) +#define COMMON_USER_POWER4 (COMMON_USER_PPC64 | PPC_FEATURE_POWER4) +#define COMMON_USER_POWER5 (COMMON_USER_PPC64 | PPC_FEATURE_POWER5 |\ + PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP) +#define COMMON_USER_POWER5_PLUS (COMMON_USER_PPC64 | PPC_FEATURE_POWER5_PLUS|\ + PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP) +#define COMMON_USER_POWER6 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_05 |\ + PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \ + PPC_FEATURE_TRUE_LE | \ + PPC_FEATURE_PSERIES_PERFMON_COMPAT) +#define COMMON_USER_POWER7 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_06 |\ + PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \ + PPC_FEATURE_TRUE_LE | \ + PPC_FEATURE_PSERIES_PERFMON_COMPAT) +#define COMMON_USER2_POWER7 (PPC_FEATURE2_DSCR) +#define COMMON_USER_POWER8 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_06 |\ + PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \ + PPC_FEATURE_TRUE_LE | \ + PPC_FEATURE_PSERIES_PERFMON_COMPAT) +#define COMMON_USER2_POWER8 (PPC_FEATURE2_ARCH_2_07 | \ + PPC_FEATURE2_HTM_COMP | \ + PPC_FEATURE2_HTM_NOSC_COMP | \ + PPC_FEATURE2_DSCR | \ + PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \ + PPC_FEATURE2_VEC_CRYPTO) +#define COMMON_USER_PA6T (COMMON_USER_PPC64 | PPC_FEATURE_PA6T |\ + PPC_FEATURE_TRUE_LE | \ + PPC_FEATURE_HAS_ALTIVEC_COMP) +#define COMMON_USER_POWER9 COMMON_USER_POWER8 +#define COMMON_USER2_POWER9 (COMMON_USER2_POWER8 | \ + PPC_FEATURE2_ARCH_3_00 | \ + PPC_FEATURE2_HAS_IEEE128 | \ + PPC_FEATURE2_DARN | \ + PPC_FEATURE2_SCV) +#define COMMON_USER_POWER10 COMMON_USER_POWER9 +#define COMMON_USER2_POWER10 (PPC_FEATURE2_ARCH_3_1 | \ + PPC_FEATURE2_MMA | \ + PPC_FEATURE2_ARCH_3_00 | \ + PPC_FEATURE2_HAS_IEEE128 | \ + PPC_FEATURE2_DARN | \ + PPC_FEATURE2_SCV | \ + PPC_FEATURE2_ARCH_2_07 | \ + PPC_FEATURE2_DSCR | \ + PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \ + PPC_FEATURE2_VEC_CRYPTO) + +static struct cpu_spec cpu_specs[] __initdata = { + { /* PPC970 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00390000, + .cpu_name = "PPC970", + .cpu_features = CPU_FTRS_PPC970, + .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, + .mmu_features = MMU_FTRS_PPC970, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 8, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_ppc970, + .cpu_restore = __restore_cpu_ppc970, + .platform = "ppc970", + }, + { /* PPC970FX */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x003c0000, + .cpu_name = "PPC970FX", + .cpu_features = CPU_FTRS_PPC970, + .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, + .mmu_features = MMU_FTRS_PPC970, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 8, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_ppc970, + .cpu_restore = __restore_cpu_ppc970, + .platform = "ppc970", + }, + { /* PPC970MP DD1.0 - no DEEPNAP, use regular 970 init */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x00440100, + .cpu_name = "PPC970MP", + .cpu_features = CPU_FTRS_PPC970, + .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, + .mmu_features = MMU_FTRS_PPC970, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 8, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_ppc970, + .cpu_restore = __restore_cpu_ppc970, + .platform = "ppc970", + }, + { /* PPC970MP */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00440000, + .cpu_name = "PPC970MP", + .cpu_features = CPU_FTRS_PPC970, + .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, + .mmu_features = MMU_FTRS_PPC970, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 8, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_ppc970MP, + .cpu_restore = __restore_cpu_ppc970, + .platform = "ppc970", + }, + { /* PPC970GX */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00450000, + .cpu_name = "PPC970GX", + .cpu_features = CPU_FTRS_PPC970, + .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, + .mmu_features = MMU_FTRS_PPC970, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 8, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_ppc970, + .platform = "ppc970", + }, + { /* Power5 GR */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x003a0000, + .cpu_name = "POWER5 (gr)", + .cpu_features = CPU_FTRS_POWER5, + .cpu_user_features = COMMON_USER_POWER5, + .mmu_features = MMU_FTRS_POWER5, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .platform = "power5", + }, + { /* Power5++ */ + .pvr_mask = 0xffffff00, + .pvr_value = 0x003b0300, + .cpu_name = "POWER5+ (gs)", + .cpu_features = CPU_FTRS_POWER5, + .cpu_user_features = COMMON_USER_POWER5_PLUS, + .mmu_features = MMU_FTRS_POWER5, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .platform = "power5+", + }, + { /* Power5 GS */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x003b0000, + .cpu_name = "POWER5+ (gs)", + .cpu_features = CPU_FTRS_POWER5, + .cpu_user_features = COMMON_USER_POWER5_PLUS, + .mmu_features = MMU_FTRS_POWER5, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .platform = "power5+", + }, + { /* POWER6 in P5+ mode; 2.04-compliant processor */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x0f000001, + .cpu_name = "POWER5+", + .cpu_features = CPU_FTRS_POWER5, + .cpu_user_features = COMMON_USER_POWER5_PLUS, + .mmu_features = MMU_FTRS_POWER5, + .icache_bsize = 128, + .dcache_bsize = 128, + .platform = "power5+", + }, + { /* Power6 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x003e0000, + .cpu_name = "POWER6 (raw)", + .cpu_features = CPU_FTRS_POWER6, + .cpu_user_features = COMMON_USER_POWER6 | PPC_FEATURE_POWER6_EXT, + .mmu_features = MMU_FTRS_POWER6, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .platform = "power6x", + }, + { /* 2.05-compliant processor, i.e. Power6 "architected" mode */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x0f000002, + .cpu_name = "POWER6 (architected)", + .cpu_features = CPU_FTRS_POWER6, + .cpu_user_features = COMMON_USER_POWER6, + .mmu_features = MMU_FTRS_POWER6, + .icache_bsize = 128, + .dcache_bsize = 128, + .platform = "power6", + }, + { /* 2.06-compliant processor, i.e. Power7 "architected" mode */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x0f000003, + .cpu_name = "POWER7 (architected)", + .cpu_features = CPU_FTRS_POWER7, + .cpu_user_features = COMMON_USER_POWER7, + .cpu_user_features2 = COMMON_USER2_POWER7, + .mmu_features = MMU_FTRS_POWER7, + .icache_bsize = 128, + .dcache_bsize = 128, + .cpu_setup = __setup_cpu_power7, + .cpu_restore = __restore_cpu_power7, + .machine_check_early = __machine_check_early_realmode_p7, + .platform = "power7", + }, + { /* 2.07-compliant processor, i.e. Power8 "architected" mode */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x0f000004, + .cpu_name = "POWER8 (architected)", + .cpu_features = CPU_FTRS_POWER8, + .cpu_user_features = COMMON_USER_POWER8, + .cpu_user_features2 = COMMON_USER2_POWER8, + .mmu_features = MMU_FTRS_POWER8, + .icache_bsize = 128, + .dcache_bsize = 128, + .cpu_setup = __setup_cpu_power8, + .cpu_restore = __restore_cpu_power8, + .machine_check_early = __machine_check_early_realmode_p8, + .platform = "power8", + }, + { /* 3.00-compliant processor, i.e. Power9 "architected" mode */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x0f000005, + .cpu_name = "POWER9 (architected)", + .cpu_features = CPU_FTRS_POWER9, + .cpu_user_features = COMMON_USER_POWER9, + .cpu_user_features2 = COMMON_USER2_POWER9, + .mmu_features = MMU_FTRS_POWER9, + .icache_bsize = 128, + .dcache_bsize = 128, + .cpu_setup = __setup_cpu_power9, + .cpu_restore = __restore_cpu_power9, + .platform = "power9", + }, + { /* 3.1-compliant processor, i.e. Power10 "architected" mode */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x0f000006, + .cpu_name = "POWER10 (architected)", + .cpu_features = CPU_FTRS_POWER10, + .cpu_user_features = COMMON_USER_POWER10, + .cpu_user_features2 = COMMON_USER2_POWER10, + .mmu_features = MMU_FTRS_POWER10, + .icache_bsize = 128, + .dcache_bsize = 128, + .cpu_setup = __setup_cpu_power10, + .cpu_restore = __restore_cpu_power10, + .platform = "power10", + }, + { /* Power7 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x003f0000, + .cpu_name = "POWER7 (raw)", + .cpu_features = CPU_FTRS_POWER7, + .cpu_user_features = COMMON_USER_POWER7, + .cpu_user_features2 = COMMON_USER2_POWER7, + .mmu_features = MMU_FTRS_POWER7, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_power7, + .cpu_restore = __restore_cpu_power7, + .machine_check_early = __machine_check_early_realmode_p7, + .platform = "power7", + }, + { /* Power7+ */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x004A0000, + .cpu_name = "POWER7+ (raw)", + .cpu_features = CPU_FTRS_POWER7, + .cpu_user_features = COMMON_USER_POWER7, + .cpu_user_features2 = COMMON_USER2_POWER7, + .mmu_features = MMU_FTRS_POWER7, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_power7, + .cpu_restore = __restore_cpu_power7, + .machine_check_early = __machine_check_early_realmode_p7, + .platform = "power7+", + }, + { /* Power8E */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x004b0000, + .cpu_name = "POWER8E (raw)", + .cpu_features = CPU_FTRS_POWER8E, + .cpu_user_features = COMMON_USER_POWER8, + .cpu_user_features2 = COMMON_USER2_POWER8, + .mmu_features = MMU_FTRS_POWER8, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_power8, + .cpu_restore = __restore_cpu_power8, + .machine_check_early = __machine_check_early_realmode_p8, + .platform = "power8", + }, + { /* Power8NVL */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x004c0000, + .cpu_name = "POWER8NVL (raw)", + .cpu_features = CPU_FTRS_POWER8, + .cpu_user_features = COMMON_USER_POWER8, + .cpu_user_features2 = COMMON_USER2_POWER8, + .mmu_features = MMU_FTRS_POWER8, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_power8, + .cpu_restore = __restore_cpu_power8, + .machine_check_early = __machine_check_early_realmode_p8, + .platform = "power8", + }, + { /* Power8 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x004d0000, + .cpu_name = "POWER8 (raw)", + .cpu_features = CPU_FTRS_POWER8, + .cpu_user_features = COMMON_USER_POWER8, + .cpu_user_features2 = COMMON_USER2_POWER8, + .mmu_features = MMU_FTRS_POWER8, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_power8, + .cpu_restore = __restore_cpu_power8, + .machine_check_early = __machine_check_early_realmode_p8, + .platform = "power8", + }, + { /* Power9 DD2.0 */ + .pvr_mask = 0xffffefff, + .pvr_value = 0x004e0200, + .cpu_name = "POWER9 (raw)", + .cpu_features = CPU_FTRS_POWER9_DD2_0, + .cpu_user_features = COMMON_USER_POWER9, + .cpu_user_features2 = COMMON_USER2_POWER9, + .mmu_features = MMU_FTRS_POWER9, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_power9, + .cpu_restore = __restore_cpu_power9, + .machine_check_early = __machine_check_early_realmode_p9, + .platform = "power9", + }, + { /* Power9 DD 2.1 */ + .pvr_mask = 0xffffefff, + .pvr_value = 0x004e0201, + .cpu_name = "POWER9 (raw)", + .cpu_features = CPU_FTRS_POWER9_DD2_1, + .cpu_user_features = COMMON_USER_POWER9, + .cpu_user_features2 = COMMON_USER2_POWER9, + .mmu_features = MMU_FTRS_POWER9, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_power9, + .cpu_restore = __restore_cpu_power9, + .machine_check_early = __machine_check_early_realmode_p9, + .platform = "power9", + }, + { /* Power9 DD2.2 */ + .pvr_mask = 0xffffefff, + .pvr_value = 0x004e0202, + .cpu_name = "POWER9 (raw)", + .cpu_features = CPU_FTRS_POWER9_DD2_2, + .cpu_user_features = COMMON_USER_POWER9, + .cpu_user_features2 = COMMON_USER2_POWER9, + .mmu_features = MMU_FTRS_POWER9, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_power9, + .cpu_restore = __restore_cpu_power9, + .machine_check_early = __machine_check_early_realmode_p9, + .platform = "power9", + }, + { /* Power9 DD2.3 or later */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x004e0000, + .cpu_name = "POWER9 (raw)", + .cpu_features = CPU_FTRS_POWER9_DD2_3, + .cpu_user_features = COMMON_USER_POWER9, + .cpu_user_features2 = COMMON_USER2_POWER9, + .mmu_features = MMU_FTRS_POWER9, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_power9, + .cpu_restore = __restore_cpu_power9, + .machine_check_early = __machine_check_early_realmode_p9, + .platform = "power9", + }, + { /* Power10 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00800000, + .cpu_name = "POWER10 (raw)", + .cpu_features = CPU_FTRS_POWER10, + .cpu_user_features = COMMON_USER_POWER10, + .cpu_user_features2 = COMMON_USER2_POWER10, + .mmu_features = MMU_FTRS_POWER10, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .cpu_setup = __setup_cpu_power10, + .cpu_restore = __restore_cpu_power10, + .machine_check_early = __machine_check_early_realmode_p10, + .platform = "power10", + }, + { /* Cell Broadband Engine */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00700000, + .cpu_name = "Cell Broadband Engine", + .cpu_features = CPU_FTRS_CELL, + .cpu_user_features = COMMON_USER_PPC64 | PPC_FEATURE_CELL | + PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_SMT, + .mmu_features = MMU_FTRS_CELL, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 4, + .pmc_type = PPC_PMC_IBM, + .platform = "ppc-cell-be", + }, + { /* PA Semi PA6T */ + .pvr_mask = 0x7fff0000, + .pvr_value = 0x00900000, + .cpu_name = "PA6T", + .cpu_features = CPU_FTRS_PA6T, + .cpu_user_features = COMMON_USER_PA6T, + .mmu_features = MMU_FTRS_PA6T, + .icache_bsize = 64, + .dcache_bsize = 64, + .num_pmcs = 6, + .pmc_type = PPC_PMC_PA6T, + .cpu_setup = __setup_cpu_pa6t, + .cpu_restore = __restore_cpu_pa6t, + .platform = "pa6t", + }, + { /* default match */ + .pvr_mask = 0x00000000, + .pvr_value = 0x00000000, + .cpu_name = "POWER5 (compatible)", + .cpu_features = CPU_FTRS_COMPATIBLE, + .cpu_user_features = COMMON_USER_PPC64, + .mmu_features = MMU_FTRS_POWER, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .platform = "power5", + } +}; diff --git a/arch/powerpc/kernel/cpu_specs_e500mc.h b/arch/powerpc/kernel/cpu_specs_e500mc.h new file mode 100644 index 000000000000..ceb06b109f83 --- /dev/null +++ b/arch/powerpc/kernel/cpu_specs_e500mc.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org) + * + * Modifications for ppc64: + * Copyright (C) 2003 Dave Engebretsen + */ + +#ifdef CONFIG_PPC64 +#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ + PPC_FEATURE_HAS_FPU | PPC_FEATURE_64) +#else +#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ + PPC_FEATURE_BOOKE) +#endif + +static struct cpu_spec cpu_specs[] __initdata = { +#ifdef CONFIG_PPC32 + { /* e500mc */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80230000, + .cpu_name = "e500mc", + .cpu_features = CPU_FTRS_E500MC, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .cpu_user_features2 = PPC_FEATURE2_ISEL, + .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | MMU_FTR_USE_TLBILX, + .icache_bsize = 64, + .dcache_bsize = 64, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_e500mc, + .machine_check = machine_check_e500mc, + .platform = "ppce500mc", + .cpu_down_flush = cpu_down_flush_e500mc, + }, +#endif /* CONFIG_PPC32 */ + { /* e5500 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80240000, + .cpu_name = "e5500", + .cpu_features = CPU_FTRS_E5500, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .cpu_user_features2 = PPC_FEATURE2_ISEL, + .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | MMU_FTR_USE_TLBILX, + .icache_bsize = 64, + .dcache_bsize = 64, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_e5500, +#ifndef CONFIG_PPC32 + .cpu_restore = __restore_cpu_e5500, +#endif + .machine_check = machine_check_e500mc, + .platform = "ppce5500", + .cpu_down_flush = cpu_down_flush_e5500, + }, + { /* e6500 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80400000, + .cpu_name = "e6500", + .cpu_features = CPU_FTRS_E6500, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU | + PPC_FEATURE_HAS_ALTIVEC_COMP, + .cpu_user_features2 = PPC_FEATURE2_ISEL, + .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | MMU_FTR_USE_TLBILX, + .icache_bsize = 64, + .dcache_bsize = 64, + .num_pmcs = 6, + .cpu_setup = __setup_cpu_e6500, +#ifndef CONFIG_PPC32 + .cpu_restore = __restore_cpu_e6500, +#endif + .machine_check = machine_check_e500mc, + .platform = "ppce6500", + .cpu_down_flush = cpu_down_flush_e6500, + }, +}; diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index d8e42ef750f1..8a32bffefa5b 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -18,6 +18,7 @@ #include #include #include +#include static struct cpu_spec the_cpu_spec __read_mostly; @@ -27,1922 +28,7 @@ EXPORT_SYMBOL(cur_cpu_spec); /* The platform string corresponding to the real PVR */ const char *powerpc_base_platform; -/* NOTE: - * Unlike ppc32, ppc64 will only call this once for the boot CPU, it's - * the responsibility of the appropriate CPU save/restore functions to - * eventually copy these settings over. Those save/restore aren't yet - * part of the cputable though. That has to be fixed for both ppc32 - * and ppc64 - */ -#ifdef CONFIG_PPC32 -extern void __setup_cpu_e500v1(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_e500v2(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_e500mc(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_440ep(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_440epx(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_440gx(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_440grx(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_440spe(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_440x5(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_460ex(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_460gt(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_460sx(unsigned long offset, struct cpu_spec *spec); -extern void __setup_cpu_apm821xx(unsigned long offset, struct cpu_spec *spec); -extern void __setup_cpu_603(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_604(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_750(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_750cx(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_750fx(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_7400(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_7410(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_745x(unsigned long offset, struct cpu_spec* spec); -#endif /* CONFIG_PPC32 */ -#ifdef CONFIG_PPC64 -#include -extern void __setup_cpu_ppc970(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_ppc970MP(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_pa6t(unsigned long offset, struct cpu_spec* spec); -extern void __restore_cpu_pa6t(void); -extern void __restore_cpu_ppc970(void); -extern long __machine_check_early_realmode_p7(struct pt_regs *regs); -extern long __machine_check_early_realmode_p8(struct pt_regs *regs); -extern long __machine_check_early_realmode_p9(struct pt_regs *regs); -#endif /* CONFIG_PPC64 */ -#if defined(CONFIG_E500) -extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_e6500(unsigned long offset, struct cpu_spec* spec); -extern void __restore_cpu_e5500(void); -extern void __restore_cpu_e6500(void); -#endif /* CONFIG_E500 */ - -/* This table only contains "desktop" CPUs, it need to be filled with embedded - * ones as well... - */ -#define COMMON_USER (PPC_FEATURE_32 | PPC_FEATURE_HAS_FPU | \ - PPC_FEATURE_HAS_MMU) -#define COMMON_USER_PPC64 (COMMON_USER | PPC_FEATURE_64) -#define COMMON_USER_POWER4 (COMMON_USER_PPC64 | PPC_FEATURE_POWER4) -#define COMMON_USER_POWER5 (COMMON_USER_PPC64 | PPC_FEATURE_POWER5 |\ - PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP) -#define COMMON_USER_POWER5_PLUS (COMMON_USER_PPC64 | PPC_FEATURE_POWER5_PLUS|\ - PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP) -#define COMMON_USER_POWER6 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_05 |\ - PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \ - PPC_FEATURE_TRUE_LE | \ - PPC_FEATURE_PSERIES_PERFMON_COMPAT) -#define COMMON_USER_POWER7 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_06 |\ - PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \ - PPC_FEATURE_TRUE_LE | \ - PPC_FEATURE_PSERIES_PERFMON_COMPAT) -#define COMMON_USER2_POWER7 (PPC_FEATURE2_DSCR) -#define COMMON_USER_POWER8 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_06 |\ - PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \ - PPC_FEATURE_TRUE_LE | \ - PPC_FEATURE_PSERIES_PERFMON_COMPAT) -#define COMMON_USER2_POWER8 (PPC_FEATURE2_ARCH_2_07 | \ - PPC_FEATURE2_HTM_COMP | \ - PPC_FEATURE2_HTM_NOSC_COMP | \ - PPC_FEATURE2_DSCR | \ - PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \ - PPC_FEATURE2_VEC_CRYPTO) -#define COMMON_USER_PA6T (COMMON_USER_PPC64 | PPC_FEATURE_PA6T |\ - PPC_FEATURE_TRUE_LE | \ - PPC_FEATURE_HAS_ALTIVEC_COMP) -#define COMMON_USER_POWER9 COMMON_USER_POWER8 -#define COMMON_USER2_POWER9 (COMMON_USER2_POWER8 | \ - PPC_FEATURE2_ARCH_3_00 | \ - PPC_FEATURE2_HAS_IEEE128 | \ - PPC_FEATURE2_DARN | \ - PPC_FEATURE2_SCV) -#define COMMON_USER_POWER10 COMMON_USER_POWER9 -#define COMMON_USER2_POWER10 (PPC_FEATURE2_ARCH_3_1 | \ - PPC_FEATURE2_MMA | \ - PPC_FEATURE2_ARCH_3_00 | \ - PPC_FEATURE2_HAS_IEEE128 | \ - PPC_FEATURE2_DARN | \ - PPC_FEATURE2_SCV | \ - PPC_FEATURE2_ARCH_2_07 | \ - PPC_FEATURE2_DSCR | \ - PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \ - PPC_FEATURE2_VEC_CRYPTO) - -#ifdef CONFIG_PPC_BOOK3E_64 -#define COMMON_USER_BOOKE (COMMON_USER_PPC64 | PPC_FEATURE_BOOKE) -#else -#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ - PPC_FEATURE_BOOKE) -#endif - -static struct cpu_spec __initdata cpu_specs[] = { -#ifdef CONFIG_PPC_BOOK3S_64 - { /* PPC970 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00390000, - .cpu_name = "PPC970", - .cpu_features = CPU_FTRS_PPC970, - .cpu_user_features = COMMON_USER_POWER4 | - PPC_FEATURE_HAS_ALTIVEC_COMP, - .mmu_features = MMU_FTRS_PPC970, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 8, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_ppc970, - .cpu_restore = __restore_cpu_ppc970, - .platform = "ppc970", - }, - { /* PPC970FX */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x003c0000, - .cpu_name = "PPC970FX", - .cpu_features = CPU_FTRS_PPC970, - .cpu_user_features = COMMON_USER_POWER4 | - PPC_FEATURE_HAS_ALTIVEC_COMP, - .mmu_features = MMU_FTRS_PPC970, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 8, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_ppc970, - .cpu_restore = __restore_cpu_ppc970, - .platform = "ppc970", - }, - { /* PPC970MP DD1.0 - no DEEPNAP, use regular 970 init */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x00440100, - .cpu_name = "PPC970MP", - .cpu_features = CPU_FTRS_PPC970, - .cpu_user_features = COMMON_USER_POWER4 | - PPC_FEATURE_HAS_ALTIVEC_COMP, - .mmu_features = MMU_FTRS_PPC970, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 8, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_ppc970, - .cpu_restore = __restore_cpu_ppc970, - .platform = "ppc970", - }, - { /* PPC970MP */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00440000, - .cpu_name = "PPC970MP", - .cpu_features = CPU_FTRS_PPC970, - .cpu_user_features = COMMON_USER_POWER4 | - PPC_FEATURE_HAS_ALTIVEC_COMP, - .mmu_features = MMU_FTRS_PPC970, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 8, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_ppc970MP, - .cpu_restore = __restore_cpu_ppc970, - .platform = "ppc970", - }, - { /* PPC970GX */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00450000, - .cpu_name = "PPC970GX", - .cpu_features = CPU_FTRS_PPC970, - .cpu_user_features = COMMON_USER_POWER4 | - PPC_FEATURE_HAS_ALTIVEC_COMP, - .mmu_features = MMU_FTRS_PPC970, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 8, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_ppc970, - .platform = "ppc970", - }, - { /* Power5 GR */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x003a0000, - .cpu_name = "POWER5 (gr)", - .cpu_features = CPU_FTRS_POWER5, - .cpu_user_features = COMMON_USER_POWER5, - .mmu_features = MMU_FTRS_POWER5, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .platform = "power5", - }, - { /* Power5++ */ - .pvr_mask = 0xffffff00, - .pvr_value = 0x003b0300, - .cpu_name = "POWER5+ (gs)", - .cpu_features = CPU_FTRS_POWER5, - .cpu_user_features = COMMON_USER_POWER5_PLUS, - .mmu_features = MMU_FTRS_POWER5, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .platform = "power5+", - }, - { /* Power5 GS */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x003b0000, - .cpu_name = "POWER5+ (gs)", - .cpu_features = CPU_FTRS_POWER5, - .cpu_user_features = COMMON_USER_POWER5_PLUS, - .mmu_features = MMU_FTRS_POWER5, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .platform = "power5+", - }, - { /* POWER6 in P5+ mode; 2.04-compliant processor */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x0f000001, - .cpu_name = "POWER5+", - .cpu_features = CPU_FTRS_POWER5, - .cpu_user_features = COMMON_USER_POWER5_PLUS, - .mmu_features = MMU_FTRS_POWER5, - .icache_bsize = 128, - .dcache_bsize = 128, - .platform = "power5+", - }, - { /* Power6 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x003e0000, - .cpu_name = "POWER6 (raw)", - .cpu_features = CPU_FTRS_POWER6, - .cpu_user_features = COMMON_USER_POWER6 | - PPC_FEATURE_POWER6_EXT, - .mmu_features = MMU_FTRS_POWER6, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .platform = "power6x", - }, - { /* 2.05-compliant processor, i.e. Power6 "architected" mode */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x0f000002, - .cpu_name = "POWER6 (architected)", - .cpu_features = CPU_FTRS_POWER6, - .cpu_user_features = COMMON_USER_POWER6, - .mmu_features = MMU_FTRS_POWER6, - .icache_bsize = 128, - .dcache_bsize = 128, - .platform = "power6", - }, - { /* 2.06-compliant processor, i.e. Power7 "architected" mode */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x0f000003, - .cpu_name = "POWER7 (architected)", - .cpu_features = CPU_FTRS_POWER7, - .cpu_user_features = COMMON_USER_POWER7, - .cpu_user_features2 = COMMON_USER2_POWER7, - .mmu_features = MMU_FTRS_POWER7, - .icache_bsize = 128, - .dcache_bsize = 128, - .cpu_setup = __setup_cpu_power7, - .cpu_restore = __restore_cpu_power7, - .machine_check_early = __machine_check_early_realmode_p7, - .platform = "power7", - }, - { /* 2.07-compliant processor, i.e. Power8 "architected" mode */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x0f000004, - .cpu_name = "POWER8 (architected)", - .cpu_features = CPU_FTRS_POWER8, - .cpu_user_features = COMMON_USER_POWER8, - .cpu_user_features2 = COMMON_USER2_POWER8, - .mmu_features = MMU_FTRS_POWER8, - .icache_bsize = 128, - .dcache_bsize = 128, - .cpu_setup = __setup_cpu_power8, - .cpu_restore = __restore_cpu_power8, - .machine_check_early = __machine_check_early_realmode_p8, - .platform = "power8", - }, - { /* 3.00-compliant processor, i.e. Power9 "architected" mode */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x0f000005, - .cpu_name = "POWER9 (architected)", - .cpu_features = CPU_FTRS_POWER9, - .cpu_user_features = COMMON_USER_POWER9, - .cpu_user_features2 = COMMON_USER2_POWER9, - .mmu_features = MMU_FTRS_POWER9, - .icache_bsize = 128, - .dcache_bsize = 128, - .cpu_setup = __setup_cpu_power9, - .cpu_restore = __restore_cpu_power9, - .platform = "power9", - }, - { /* 3.1-compliant processor, i.e. Power10 "architected" mode */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x0f000006, - .cpu_name = "POWER10 (architected)", - .cpu_features = CPU_FTRS_POWER10, - .cpu_user_features = COMMON_USER_POWER10, - .cpu_user_features2 = COMMON_USER2_POWER10, - .mmu_features = MMU_FTRS_POWER10, - .icache_bsize = 128, - .dcache_bsize = 128, - .cpu_setup = __setup_cpu_power10, - .cpu_restore = __restore_cpu_power10, - .platform = "power10", - }, - { /* Power7 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x003f0000, - .cpu_name = "POWER7 (raw)", - .cpu_features = CPU_FTRS_POWER7, - .cpu_user_features = COMMON_USER_POWER7, - .cpu_user_features2 = COMMON_USER2_POWER7, - .mmu_features = MMU_FTRS_POWER7, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_power7, - .cpu_restore = __restore_cpu_power7, - .machine_check_early = __machine_check_early_realmode_p7, - .platform = "power7", - }, - { /* Power7+ */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x004A0000, - .cpu_name = "POWER7+ (raw)", - .cpu_features = CPU_FTRS_POWER7, - .cpu_user_features = COMMON_USER_POWER7, - .cpu_user_features2 = COMMON_USER2_POWER7, - .mmu_features = MMU_FTRS_POWER7, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_power7, - .cpu_restore = __restore_cpu_power7, - .machine_check_early = __machine_check_early_realmode_p7, - .platform = "power7+", - }, - { /* Power8E */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x004b0000, - .cpu_name = "POWER8E (raw)", - .cpu_features = CPU_FTRS_POWER8E, - .cpu_user_features = COMMON_USER_POWER8, - .cpu_user_features2 = COMMON_USER2_POWER8, - .mmu_features = MMU_FTRS_POWER8, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_power8, - .cpu_restore = __restore_cpu_power8, - .machine_check_early = __machine_check_early_realmode_p8, - .platform = "power8", - }, - { /* Power8NVL */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x004c0000, - .cpu_name = "POWER8NVL (raw)", - .cpu_features = CPU_FTRS_POWER8, - .cpu_user_features = COMMON_USER_POWER8, - .cpu_user_features2 = COMMON_USER2_POWER8, - .mmu_features = MMU_FTRS_POWER8, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_power8, - .cpu_restore = __restore_cpu_power8, - .machine_check_early = __machine_check_early_realmode_p8, - .platform = "power8", - }, - { /* Power8 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x004d0000, - .cpu_name = "POWER8 (raw)", - .cpu_features = CPU_FTRS_POWER8, - .cpu_user_features = COMMON_USER_POWER8, - .cpu_user_features2 = COMMON_USER2_POWER8, - .mmu_features = MMU_FTRS_POWER8, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_power8, - .cpu_restore = __restore_cpu_power8, - .machine_check_early = __machine_check_early_realmode_p8, - .platform = "power8", - }, - { /* Power9 DD2.0 */ - .pvr_mask = 0xffffefff, - .pvr_value = 0x004e0200, - .cpu_name = "POWER9 (raw)", - .cpu_features = CPU_FTRS_POWER9_DD2_0, - .cpu_user_features = COMMON_USER_POWER9, - .cpu_user_features2 = COMMON_USER2_POWER9, - .mmu_features = MMU_FTRS_POWER9, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_power9, - .cpu_restore = __restore_cpu_power9, - .machine_check_early = __machine_check_early_realmode_p9, - .platform = "power9", - }, - { /* Power9 DD 2.1 */ - .pvr_mask = 0xffffefff, - .pvr_value = 0x004e0201, - .cpu_name = "POWER9 (raw)", - .cpu_features = CPU_FTRS_POWER9_DD2_1, - .cpu_user_features = COMMON_USER_POWER9, - .cpu_user_features2 = COMMON_USER2_POWER9, - .mmu_features = MMU_FTRS_POWER9, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_power9, - .cpu_restore = __restore_cpu_power9, - .machine_check_early = __machine_check_early_realmode_p9, - .platform = "power9", - }, - { /* Power9 DD2.2 */ - .pvr_mask = 0xffffefff, - .pvr_value = 0x004e0202, - .cpu_name = "POWER9 (raw)", - .cpu_features = CPU_FTRS_POWER9_DD2_2, - .cpu_user_features = COMMON_USER_POWER9, - .cpu_user_features2 = COMMON_USER2_POWER9, - .mmu_features = MMU_FTRS_POWER9, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_power9, - .cpu_restore = __restore_cpu_power9, - .machine_check_early = __machine_check_early_realmode_p9, - .platform = "power9", - }, - { /* Power9 DD2.3 or later */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x004e0000, - .cpu_name = "POWER9 (raw)", - .cpu_features = CPU_FTRS_POWER9_DD2_3, - .cpu_user_features = COMMON_USER_POWER9, - .cpu_user_features2 = COMMON_USER2_POWER9, - .mmu_features = MMU_FTRS_POWER9, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_power9, - .cpu_restore = __restore_cpu_power9, - .machine_check_early = __machine_check_early_realmode_p9, - .platform = "power9", - }, - { /* Power10 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00800000, - .cpu_name = "POWER10 (raw)", - .cpu_features = CPU_FTRS_POWER10, - .cpu_user_features = COMMON_USER_POWER10, - .cpu_user_features2 = COMMON_USER2_POWER10, - .mmu_features = MMU_FTRS_POWER10, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_power10, - .cpu_restore = __restore_cpu_power10, - .machine_check_early = __machine_check_early_realmode_p10, - .platform = "power10", - }, - { /* Cell Broadband Engine */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00700000, - .cpu_name = "Cell Broadband Engine", - .cpu_features = CPU_FTRS_CELL, - .cpu_user_features = COMMON_USER_PPC64 | - PPC_FEATURE_CELL | PPC_FEATURE_HAS_ALTIVEC_COMP | - PPC_FEATURE_SMT, - .mmu_features = MMU_FTRS_CELL, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 4, - .pmc_type = PPC_PMC_IBM, - .platform = "ppc-cell-be", - }, - { /* PA Semi PA6T */ - .pvr_mask = 0x7fff0000, - .pvr_value = 0x00900000, - .cpu_name = "PA6T", - .cpu_features = CPU_FTRS_PA6T, - .cpu_user_features = COMMON_USER_PA6T, - .mmu_features = MMU_FTRS_PA6T, - .icache_bsize = 64, - .dcache_bsize = 64, - .num_pmcs = 6, - .pmc_type = PPC_PMC_PA6T, - .cpu_setup = __setup_cpu_pa6t, - .cpu_restore = __restore_cpu_pa6t, - .platform = "pa6t", - }, - { /* default match */ - .pvr_mask = 0x00000000, - .pvr_value = 0x00000000, - .cpu_name = "POWER5 (compatible)", - .cpu_features = CPU_FTRS_COMPATIBLE, - .cpu_user_features = COMMON_USER_PPC64, - .mmu_features = MMU_FTRS_POWER, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .platform = "power5", - } -#endif /* CONFIG_PPC_BOOK3S_64 */ - -#ifdef CONFIG_PPC32 -#ifdef CONFIG_PPC_BOOK3S_32 -#ifdef CONFIG_PPC_BOOK3S_604 - { /* 604 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00040000, - .cpu_name = "604", - .cpu_features = CPU_FTRS_604, - .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 2, - .cpu_setup = __setup_cpu_604, - .machine_check = machine_check_generic, - .platform = "ppc604", - }, - { /* 604e */ - .pvr_mask = 0xfffff000, - .pvr_value = 0x00090000, - .cpu_name = "604e", - .cpu_features = CPU_FTRS_604, - .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 4, - .cpu_setup = __setup_cpu_604, - .machine_check = machine_check_generic, - .platform = "ppc604", - }, - { /* 604r */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00090000, - .cpu_name = "604r", - .cpu_features = CPU_FTRS_604, - .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 4, - .cpu_setup = __setup_cpu_604, - .machine_check = machine_check_generic, - .platform = "ppc604", - }, - { /* 604ev */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x000a0000, - .cpu_name = "604ev", - .cpu_features = CPU_FTRS_604, - .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 4, - .cpu_setup = __setup_cpu_604, - .machine_check = machine_check_generic, - .platform = "ppc604", - }, - { /* 740/750 (0x4202, don't support TAU ?) */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x00084202, - .cpu_name = "740/750", - .cpu_features = CPU_FTRS_740_NOTAU, - .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 4, - .cpu_setup = __setup_cpu_750, - .machine_check = machine_check_generic, - .platform = "ppc750", - }, - { /* 750CX (80100 and 8010x?) */ - .pvr_mask = 0xfffffff0, - .pvr_value = 0x00080100, - .cpu_name = "750CX", - .cpu_features = CPU_FTRS_750, - .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 4, - .cpu_setup = __setup_cpu_750cx, - .machine_check = machine_check_generic, - .platform = "ppc750", - }, - { /* 750CX (82201 and 82202) */ - .pvr_mask = 0xfffffff0, - .pvr_value = 0x00082200, - .cpu_name = "750CX", - .cpu_features = CPU_FTRS_750, - .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 4, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_750cx, - .machine_check = machine_check_generic, - .platform = "ppc750", - }, - { /* 750CXe (82214) */ - .pvr_mask = 0xfffffff0, - .pvr_value = 0x00082210, - .cpu_name = "750CXe", - .cpu_features = CPU_FTRS_750, - .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 4, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_750cx, - .machine_check = machine_check_generic, - .platform = "ppc750", - }, - { /* 750CXe "Gekko" (83214) */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x00083214, - .cpu_name = "750CXe", - .cpu_features = CPU_FTRS_750, - .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 4, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_750cx, - .machine_check = machine_check_generic, - .platform = "ppc750", - }, - { /* 750CL (and "Broadway") */ - .pvr_mask = 0xfffff0e0, - .pvr_value = 0x00087000, - .cpu_name = "750CL", - .cpu_features = CPU_FTRS_750CL, - .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 4, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_750, - .machine_check = machine_check_generic, - .platform = "ppc750", - }, - { /* 745/755 */ - .pvr_mask = 0xfffff000, - .pvr_value = 0x00083000, - .cpu_name = "745/755", - .cpu_features = CPU_FTRS_750, - .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 4, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_750, - .machine_check = machine_check_generic, - .platform = "ppc750", - }, - { /* 750FX rev 1.x */ - .pvr_mask = 0xffffff00, - .pvr_value = 0x70000100, - .cpu_name = "750FX", - .cpu_features = CPU_FTRS_750FX1, - .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 4, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_750, - .machine_check = machine_check_generic, - .platform = "ppc750", - }, - { /* 750FX rev 2.0 must disable HID0[DPM] */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x70000200, - .cpu_name = "750FX", - .cpu_features = CPU_FTRS_750FX2, - .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 4, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_750, - .machine_check = machine_check_generic, - .platform = "ppc750", - }, - { /* 750FX (All revs except 2.0) */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x70000000, - .cpu_name = "750FX", - .cpu_features = CPU_FTRS_750FX, - .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 4, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_750fx, - .machine_check = machine_check_generic, - .platform = "ppc750", - }, - { /* 750GX */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x70020000, - .cpu_name = "750GX", - .cpu_features = CPU_FTRS_750GX, - .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 4, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_750fx, - .machine_check = machine_check_generic, - .platform = "ppc750", - }, - { /* 740/750 (L2CR bit need fixup for 740) */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00080000, - .cpu_name = "740/750", - .cpu_features = CPU_FTRS_740, - .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 4, - .pmc_type = PPC_PMC_IBM, - .cpu_setup = __setup_cpu_750, - .machine_check = machine_check_generic, - .platform = "ppc750", - }, - { /* 7400 rev 1.1 ? (no TAU) */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x000c1101, - .cpu_name = "7400 (1.1)", - .cpu_features = CPU_FTRS_7400_NOTAU, - .cpu_user_features = COMMON_USER | - PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 4, - .pmc_type = PPC_PMC_G4, - .cpu_setup = __setup_cpu_7400, - .machine_check = machine_check_generic, - .platform = "ppc7400", - }, - { /* 7400 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x000c0000, - .cpu_name = "7400", - .cpu_features = CPU_FTRS_7400, - .cpu_user_features = COMMON_USER | - PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 4, - .pmc_type = PPC_PMC_G4, - .cpu_setup = __setup_cpu_7400, - .machine_check = machine_check_generic, - .platform = "ppc7400", - }, - { /* 7410 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x800c0000, - .cpu_name = "7410", - .cpu_features = CPU_FTRS_7400, - .cpu_user_features = COMMON_USER | - PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 4, - .pmc_type = PPC_PMC_G4, - .cpu_setup = __setup_cpu_7410, - .machine_check = machine_check_generic, - .platform = "ppc7400", - }, - { /* 7450 2.0 - no doze/nap */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x80000200, - .cpu_name = "7450", - .cpu_features = CPU_FTRS_7450_20, - .cpu_user_features = COMMON_USER | - PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 6, - .pmc_type = PPC_PMC_G4, - .cpu_setup = __setup_cpu_745x, - .machine_check = machine_check_generic, - .platform = "ppc7450", - }, - { /* 7450 2.1 */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x80000201, - .cpu_name = "7450", - .cpu_features = CPU_FTRS_7450_21, - .cpu_user_features = COMMON_USER | - PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 6, - .pmc_type = PPC_PMC_G4, - .cpu_setup = __setup_cpu_745x, - .machine_check = machine_check_generic, - .platform = "ppc7450", - }, - { /* 7450 2.3 and newer */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x80000000, - .cpu_name = "7450", - .cpu_features = CPU_FTRS_7450_23, - .cpu_user_features = COMMON_USER | - PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 6, - .pmc_type = PPC_PMC_G4, - .cpu_setup = __setup_cpu_745x, - .machine_check = machine_check_generic, - .platform = "ppc7450", - }, - { /* 7455 rev 1.x */ - .pvr_mask = 0xffffff00, - .pvr_value = 0x80010100, - .cpu_name = "7455", - .cpu_features = CPU_FTRS_7455_1, - .cpu_user_features = COMMON_USER | - PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 6, - .pmc_type = PPC_PMC_G4, - .cpu_setup = __setup_cpu_745x, - .machine_check = machine_check_generic, - .platform = "ppc7450", - }, - { /* 7455 rev 2.0 */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x80010200, - .cpu_name = "7455", - .cpu_features = CPU_FTRS_7455_20, - .cpu_user_features = COMMON_USER | - PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 6, - .pmc_type = PPC_PMC_G4, - .cpu_setup = __setup_cpu_745x, - .machine_check = machine_check_generic, - .platform = "ppc7450", - }, - { /* 7455 others */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x80010000, - .cpu_name = "7455", - .cpu_features = CPU_FTRS_7455, - .cpu_user_features = COMMON_USER | - PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 6, - .pmc_type = PPC_PMC_G4, - .cpu_setup = __setup_cpu_745x, - .machine_check = machine_check_generic, - .platform = "ppc7450", - }, - { /* 7447/7457 Rev 1.0 */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x80020100, - .cpu_name = "7447/7457", - .cpu_features = CPU_FTRS_7447_10, - .cpu_user_features = COMMON_USER | - PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 6, - .pmc_type = PPC_PMC_G4, - .cpu_setup = __setup_cpu_745x, - .machine_check = machine_check_generic, - .platform = "ppc7450", - }, - { /* 7447/7457 Rev 1.1 */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x80020101, - .cpu_name = "7447/7457", - .cpu_features = CPU_FTRS_7447_10, - .cpu_user_features = COMMON_USER | - PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 6, - .pmc_type = PPC_PMC_G4, - .cpu_setup = __setup_cpu_745x, - .machine_check = machine_check_generic, - .platform = "ppc7450", - }, - { /* 7447/7457 Rev 1.2 and later */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x80020000, - .cpu_name = "7447/7457", - .cpu_features = CPU_FTRS_7447, - .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 6, - .pmc_type = PPC_PMC_G4, - .cpu_setup = __setup_cpu_745x, - .machine_check = machine_check_generic, - .platform = "ppc7450", - }, - { /* 7447A */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x80030000, - .cpu_name = "7447A", - .cpu_features = CPU_FTRS_7447A, - .cpu_user_features = COMMON_USER | - PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 6, - .pmc_type = PPC_PMC_G4, - .cpu_setup = __setup_cpu_745x, - .machine_check = machine_check_generic, - .platform = "ppc7450", - }, - { /* 7448 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x80040000, - .cpu_name = "7448", - .cpu_features = CPU_FTRS_7448, - .cpu_user_features = COMMON_USER | - PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 6, - .pmc_type = PPC_PMC_G4, - .cpu_setup = __setup_cpu_745x, - .machine_check = machine_check_generic, - .platform = "ppc7450", - }, -#endif /* CONFIG_PPC_BOOK3S_604 */ -#ifdef CONFIG_PPC_BOOK3S_603 - { /* 603 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00030000, - .cpu_name = "603", - .cpu_features = CPU_FTRS_603, - .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, - .mmu_features = 0, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_603, - .machine_check = machine_check_generic, - .platform = "ppc603", - }, - { /* 603e */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00060000, - .cpu_name = "603e", - .cpu_features = CPU_FTRS_603, - .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, - .mmu_features = 0, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_603, - .machine_check = machine_check_generic, - .platform = "ppc603", - }, - { /* 603ev */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00070000, - .cpu_name = "603ev", - .cpu_features = CPU_FTRS_603, - .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, - .mmu_features = 0, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_603, - .machine_check = machine_check_generic, - .platform = "ppc603", - }, - { /* 82xx (8240, 8245, 8260 are all 603e cores) */ - .pvr_mask = 0x7fff0000, - .pvr_value = 0x00810000, - .cpu_name = "82xx", - .cpu_features = CPU_FTRS_82XX, - .cpu_user_features = COMMON_USER, - .mmu_features = 0, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_603, - .machine_check = machine_check_generic, - .platform = "ppc603", - }, - { /* All G2_LE (603e core, plus some) have the same pvr */ - .pvr_mask = 0x7fff0000, - .pvr_value = 0x00820000, - .cpu_name = "G2_LE", - .cpu_features = CPU_FTRS_G2_LE, - .cpu_user_features = COMMON_USER, - .mmu_features = MMU_FTR_USE_HIGH_BATS, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_603, - .machine_check = machine_check_generic, - .platform = "ppc603", - }, -#ifdef CONFIG_PPC_83xx - { /* e300c1 (a 603e core, plus some) on 83xx */ - .pvr_mask = 0x7fff0000, - .pvr_value = 0x00830000, - .cpu_name = "e300c1", - .cpu_features = CPU_FTRS_E300, - .cpu_user_features = COMMON_USER, - .mmu_features = MMU_FTR_USE_HIGH_BATS, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_603, - .machine_check = machine_check_83xx, - .platform = "ppc603", - }, - { /* e300c2 (an e300c1 core, plus some, minus FPU) on 83xx */ - .pvr_mask = 0x7fff0000, - .pvr_value = 0x00840000, - .cpu_name = "e300c2", - .cpu_features = CPU_FTRS_E300C2, - .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, - .mmu_features = MMU_FTR_USE_HIGH_BATS | - MMU_FTR_NEED_DTLB_SW_LRU, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_603, - .machine_check = machine_check_83xx, - .platform = "ppc603", - }, - { /* e300c3 (e300c1, plus one IU, half cache size) on 83xx */ - .pvr_mask = 0x7fff0000, - .pvr_value = 0x00850000, - .cpu_name = "e300c3", - .cpu_features = CPU_FTRS_E300, - .cpu_user_features = COMMON_USER, - .mmu_features = MMU_FTR_USE_HIGH_BATS | - MMU_FTR_NEED_DTLB_SW_LRU, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_603, - .machine_check = machine_check_83xx, - .num_pmcs = 4, - .platform = "ppc603", - }, - { /* e300c4 (e300c1, plus one IU) */ - .pvr_mask = 0x7fff0000, - .pvr_value = 0x00860000, - .cpu_name = "e300c4", - .cpu_features = CPU_FTRS_E300, - .cpu_user_features = COMMON_USER, - .mmu_features = MMU_FTR_USE_HIGH_BATS | - MMU_FTR_NEED_DTLB_SW_LRU, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_603, - .machine_check = machine_check_83xx, - .num_pmcs = 4, - .platform = "ppc603", - }, -#endif -#endif /* CONFIG_PPC_BOOK3S_603 */ -#ifdef CONFIG_PPC_BOOK3S_604 - { /* default match, we assume split I/D cache & TB (non-601)... */ - .pvr_mask = 0x00000000, - .pvr_value = 0x00000000, - .cpu_name = "(generic PPC)", - .cpu_features = CPU_FTRS_CLASSIC32, - .cpu_user_features = COMMON_USER, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_generic, - .platform = "ppc603", - }, -#endif /* CONFIG_PPC_BOOK3S_604 */ -#endif /* CONFIG_PPC_BOOK3S_32 */ -#ifdef CONFIG_PPC_8xx - { /* 8xx */ - .pvr_mask = 0xffff0000, - .pvr_value = PVR_8xx, - .cpu_name = "8xx", - /* CPU_FTR_MAYBE_CAN_DOZE is possible, - * if the 8xx code is there.... */ - .cpu_features = CPU_FTRS_8XX, - .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, - .mmu_features = MMU_FTR_TYPE_8xx, - .icache_bsize = 16, - .dcache_bsize = 16, - .machine_check = machine_check_8xx, - .platform = "ppc823", - }, -#endif /* CONFIG_PPC_8xx */ -#ifdef CONFIG_40x - { /* STB 04xxx */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x41810000, - .cpu_name = "STB04xxx", - .cpu_features = CPU_FTRS_40X, - .cpu_user_features = PPC_FEATURE_32 | - PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, - .mmu_features = MMU_FTR_TYPE_40x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc405", - }, - { /* NP405L */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x41610000, - .cpu_name = "NP405L", - .cpu_features = CPU_FTRS_40X, - .cpu_user_features = PPC_FEATURE_32 | - PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, - .mmu_features = MMU_FTR_TYPE_40x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc405", - }, - { /* NP4GS3 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x40B10000, - .cpu_name = "NP4GS3", - .cpu_features = CPU_FTRS_40X, - .cpu_user_features = PPC_FEATURE_32 | - PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, - .mmu_features = MMU_FTR_TYPE_40x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc405", - }, - { /* NP405H */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x41410000, - .cpu_name = "NP405H", - .cpu_features = CPU_FTRS_40X, - .cpu_user_features = PPC_FEATURE_32 | - PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, - .mmu_features = MMU_FTR_TYPE_40x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc405", - }, - { /* 405GPr */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x50910000, - .cpu_name = "405GPr", - .cpu_features = CPU_FTRS_40X, - .cpu_user_features = PPC_FEATURE_32 | - PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, - .mmu_features = MMU_FTR_TYPE_40x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc405", - }, - { /* STBx25xx */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x51510000, - .cpu_name = "STBx25xx", - .cpu_features = CPU_FTRS_40X, - .cpu_user_features = PPC_FEATURE_32 | - PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, - .mmu_features = MMU_FTR_TYPE_40x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc405", - }, - { /* 405LP */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x41F10000, - .cpu_name = "405LP", - .cpu_features = CPU_FTRS_40X, - .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, - .mmu_features = MMU_FTR_TYPE_40x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc405", - }, - { /* 405EP */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x51210000, - .cpu_name = "405EP", - .cpu_features = CPU_FTRS_40X, - .cpu_user_features = PPC_FEATURE_32 | - PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, - .mmu_features = MMU_FTR_TYPE_40x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc405", - }, - { /* 405EX Rev. A/B with Security */ - .pvr_mask = 0xffff000f, - .pvr_value = 0x12910007, - .cpu_name = "405EX Rev. A/B", - .cpu_features = CPU_FTRS_40X, - .cpu_user_features = PPC_FEATURE_32 | - PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, - .mmu_features = MMU_FTR_TYPE_40x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc405", - }, - { /* 405EX Rev. C without Security */ - .pvr_mask = 0xffff000f, - .pvr_value = 0x1291000d, - .cpu_name = "405EX Rev. C", - .cpu_features = CPU_FTRS_40X, - .cpu_user_features = PPC_FEATURE_32 | - PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, - .mmu_features = MMU_FTR_TYPE_40x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc405", - }, - { /* 405EX Rev. C with Security */ - .pvr_mask = 0xffff000f, - .pvr_value = 0x1291000f, - .cpu_name = "405EX Rev. C", - .cpu_features = CPU_FTRS_40X, - .cpu_user_features = PPC_FEATURE_32 | - PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, - .mmu_features = MMU_FTR_TYPE_40x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc405", - }, - { /* 405EX Rev. D without Security */ - .pvr_mask = 0xffff000f, - .pvr_value = 0x12910003, - .cpu_name = "405EX Rev. D", - .cpu_features = CPU_FTRS_40X, - .cpu_user_features = PPC_FEATURE_32 | - PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, - .mmu_features = MMU_FTR_TYPE_40x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc405", - }, - { /* 405EX Rev. D with Security */ - .pvr_mask = 0xffff000f, - .pvr_value = 0x12910005, - .cpu_name = "405EX Rev. D", - .cpu_features = CPU_FTRS_40X, - .cpu_user_features = PPC_FEATURE_32 | - PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, - .mmu_features = MMU_FTR_TYPE_40x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc405", - }, - { /* 405EXr Rev. A/B without Security */ - .pvr_mask = 0xffff000f, - .pvr_value = 0x12910001, - .cpu_name = "405EXr Rev. A/B", - .cpu_features = CPU_FTRS_40X, - .cpu_user_features = PPC_FEATURE_32 | - PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, - .mmu_features = MMU_FTR_TYPE_40x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc405", - }, - { /* 405EXr Rev. C without Security */ - .pvr_mask = 0xffff000f, - .pvr_value = 0x12910009, - .cpu_name = "405EXr Rev. C", - .cpu_features = CPU_FTRS_40X, - .cpu_user_features = PPC_FEATURE_32 | - PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, - .mmu_features = MMU_FTR_TYPE_40x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc405", - }, - { /* 405EXr Rev. C with Security */ - .pvr_mask = 0xffff000f, - .pvr_value = 0x1291000b, - .cpu_name = "405EXr Rev. C", - .cpu_features = CPU_FTRS_40X, - .cpu_user_features = PPC_FEATURE_32 | - PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, - .mmu_features = MMU_FTR_TYPE_40x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc405", - }, - { /* 405EXr Rev. D without Security */ - .pvr_mask = 0xffff000f, - .pvr_value = 0x12910000, - .cpu_name = "405EXr Rev. D", - .cpu_features = CPU_FTRS_40X, - .cpu_user_features = PPC_FEATURE_32 | - PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, - .mmu_features = MMU_FTR_TYPE_40x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc405", - }, - { /* 405EXr Rev. D with Security */ - .pvr_mask = 0xffff000f, - .pvr_value = 0x12910002, - .cpu_name = "405EXr Rev. D", - .cpu_features = CPU_FTRS_40X, - .cpu_user_features = PPC_FEATURE_32 | - PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, - .mmu_features = MMU_FTR_TYPE_40x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc405", - }, - { - /* 405EZ */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x41510000, - .cpu_name = "405EZ", - .cpu_features = CPU_FTRS_40X, - .cpu_user_features = PPC_FEATURE_32 | - PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, - .mmu_features = MMU_FTR_TYPE_40x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc405", - }, - { /* APM8018X */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x7ff11432, - .cpu_name = "APM8018X", - .cpu_features = CPU_FTRS_40X, - .cpu_user_features = PPC_FEATURE_32 | - PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, - .mmu_features = MMU_FTR_TYPE_40x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc405", - }, - { /* default match */ - .pvr_mask = 0x00000000, - .pvr_value = 0x00000000, - .cpu_name = "(generic 40x PPC)", - .cpu_features = CPU_FTRS_40X, - .cpu_user_features = PPC_FEATURE_32 | - PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, - .mmu_features = MMU_FTR_TYPE_40x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc405", - } - -#endif /* CONFIG_40x */ -#ifdef CONFIG_44x -#ifndef CONFIG_PPC_47x - { - .pvr_mask = 0xf0000fff, - .pvr_value = 0x40000850, - .cpu_name = "440GR Rev. A", - .cpu_features = CPU_FTRS_44X, - .cpu_user_features = COMMON_USER_BOOKE, - .mmu_features = MMU_FTR_TYPE_44x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc440", - }, - { /* Use logical PVR for 440EP (logical pvr = pvr | 0x8) */ - .pvr_mask = 0xf0000fff, - .pvr_value = 0x40000858, - .cpu_name = "440EP Rev. A", - .cpu_features = CPU_FTRS_44X, - .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, - .mmu_features = MMU_FTR_TYPE_44x, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_440ep, - .machine_check = machine_check_4xx, - .platform = "ppc440", - }, - { - .pvr_mask = 0xf0000fff, - .pvr_value = 0x400008d3, - .cpu_name = "440GR Rev. B", - .cpu_features = CPU_FTRS_44X, - .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, - .mmu_features = MMU_FTR_TYPE_44x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc440", - }, - { /* Matches both physical and logical PVR for 440EP (logical pvr = pvr | 0x8) */ - .pvr_mask = 0xf0000ff7, - .pvr_value = 0x400008d4, - .cpu_name = "440EP Rev. C", - .cpu_features = CPU_FTRS_44X, - .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, - .mmu_features = MMU_FTR_TYPE_44x, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_440ep, - .machine_check = machine_check_4xx, - .platform = "ppc440", - }, - { /* Use logical PVR for 440EP (logical pvr = pvr | 0x8) */ - .pvr_mask = 0xf0000fff, - .pvr_value = 0x400008db, - .cpu_name = "440EP Rev. B", - .cpu_features = CPU_FTRS_44X, - .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, - .mmu_features = MMU_FTR_TYPE_44x, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_440ep, - .machine_check = machine_check_4xx, - .platform = "ppc440", - }, - { /* 440GRX */ - .pvr_mask = 0xf0000ffb, - .pvr_value = 0x200008D0, - .cpu_name = "440GRX", - .cpu_features = CPU_FTRS_44X, - .cpu_user_features = COMMON_USER_BOOKE, - .mmu_features = MMU_FTR_TYPE_44x, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_440grx, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* Use logical PVR for 440EPx (logical pvr = pvr | 0x8) */ - .pvr_mask = 0xf0000ffb, - .pvr_value = 0x200008D8, - .cpu_name = "440EPX", - .cpu_features = CPU_FTRS_44X, - .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, - .mmu_features = MMU_FTR_TYPE_44x, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_440epx, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* 440GP Rev. B */ - .pvr_mask = 0xf0000fff, - .pvr_value = 0x40000440, - .cpu_name = "440GP Rev. B", - .cpu_features = CPU_FTRS_44X, - .cpu_user_features = COMMON_USER_BOOKE, - .mmu_features = MMU_FTR_TYPE_44x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc440gp", - }, - { /* 440GP Rev. C */ - .pvr_mask = 0xf0000fff, - .pvr_value = 0x40000481, - .cpu_name = "440GP Rev. C", - .cpu_features = CPU_FTRS_44X, - .cpu_user_features = COMMON_USER_BOOKE, - .mmu_features = MMU_FTR_TYPE_44x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc440gp", - }, - { /* 440GX Rev. A */ - .pvr_mask = 0xf0000fff, - .pvr_value = 0x50000850, - .cpu_name = "440GX Rev. A", - .cpu_features = CPU_FTRS_44X, - .cpu_user_features = COMMON_USER_BOOKE, - .mmu_features = MMU_FTR_TYPE_44x, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_440gx, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* 440GX Rev. B */ - .pvr_mask = 0xf0000fff, - .pvr_value = 0x50000851, - .cpu_name = "440GX Rev. B", - .cpu_features = CPU_FTRS_44X, - .cpu_user_features = COMMON_USER_BOOKE, - .mmu_features = MMU_FTR_TYPE_44x, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_440gx, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* 440GX Rev. C */ - .pvr_mask = 0xf0000fff, - .pvr_value = 0x50000892, - .cpu_name = "440GX Rev. C", - .cpu_features = CPU_FTRS_44X, - .cpu_user_features = COMMON_USER_BOOKE, - .mmu_features = MMU_FTR_TYPE_44x, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_440gx, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* 440GX Rev. F */ - .pvr_mask = 0xf0000fff, - .pvr_value = 0x50000894, - .cpu_name = "440GX Rev. F", - .cpu_features = CPU_FTRS_44X, - .cpu_user_features = COMMON_USER_BOOKE, - .mmu_features = MMU_FTR_TYPE_44x, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_440gx, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* 440SP Rev. A */ - .pvr_mask = 0xfff00fff, - .pvr_value = 0x53200891, - .cpu_name = "440SP Rev. A", - .cpu_features = CPU_FTRS_44X, - .cpu_user_features = COMMON_USER_BOOKE, - .mmu_features = MMU_FTR_TYPE_44x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc440", - }, - { /* 440SPe Rev. A */ - .pvr_mask = 0xfff00fff, - .pvr_value = 0x53400890, - .cpu_name = "440SPe Rev. A", - .cpu_features = CPU_FTRS_44X, - .cpu_user_features = COMMON_USER_BOOKE, - .mmu_features = MMU_FTR_TYPE_44x, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_440spe, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* 440SPe Rev. B */ - .pvr_mask = 0xfff00fff, - .pvr_value = 0x53400891, - .cpu_name = "440SPe Rev. B", - .cpu_features = CPU_FTRS_44X, - .cpu_user_features = COMMON_USER_BOOKE, - .mmu_features = MMU_FTR_TYPE_44x, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_440spe, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* 460EX */ - .pvr_mask = 0xffff0006, - .pvr_value = 0x13020002, - .cpu_name = "460EX", - .cpu_features = CPU_FTRS_440x6, - .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, - .mmu_features = MMU_FTR_TYPE_44x, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_460ex, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* 460EX Rev B */ - .pvr_mask = 0xffff0007, - .pvr_value = 0x13020004, - .cpu_name = "460EX Rev. B", - .cpu_features = CPU_FTRS_440x6, - .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, - .mmu_features = MMU_FTR_TYPE_44x, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_460ex, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* 460GT */ - .pvr_mask = 0xffff0006, - .pvr_value = 0x13020000, - .cpu_name = "460GT", - .cpu_features = CPU_FTRS_440x6, - .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, - .mmu_features = MMU_FTR_TYPE_44x, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_460gt, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* 460GT Rev B */ - .pvr_mask = 0xffff0007, - .pvr_value = 0x13020005, - .cpu_name = "460GT Rev. B", - .cpu_features = CPU_FTRS_440x6, - .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, - .mmu_features = MMU_FTR_TYPE_44x, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_460gt, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* 460SX */ - .pvr_mask = 0xffffff00, - .pvr_value = 0x13541800, - .cpu_name = "460SX", - .cpu_features = CPU_FTRS_44X, - .cpu_user_features = COMMON_USER_BOOKE, - .mmu_features = MMU_FTR_TYPE_44x, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_460sx, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* 464 in APM821xx */ - .pvr_mask = 0xfffffff0, - .pvr_value = 0x12C41C80, - .cpu_name = "APM821XX", - .cpu_features = CPU_FTRS_44X, - .cpu_user_features = COMMON_USER_BOOKE | - PPC_FEATURE_HAS_FPU, - .mmu_features = MMU_FTR_TYPE_44x, - .icache_bsize = 32, - .dcache_bsize = 32, - .cpu_setup = __setup_cpu_apm821xx, - .machine_check = machine_check_440A, - .platform = "ppc440", - }, - { /* default match */ - .pvr_mask = 0x00000000, - .pvr_value = 0x00000000, - .cpu_name = "(generic 44x PPC)", - .cpu_features = CPU_FTRS_44X, - .cpu_user_features = COMMON_USER_BOOKE, - .mmu_features = MMU_FTR_TYPE_44x, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_4xx, - .platform = "ppc440", - } -#else /* CONFIG_PPC_47x */ - { /* 476 DD2 core */ - .pvr_mask = 0xffffffff, - .pvr_value = 0x11a52080, - .cpu_name = "476", - .cpu_features = CPU_FTRS_47X | CPU_FTR_476_DD2, - .cpu_user_features = COMMON_USER_BOOKE | - PPC_FEATURE_HAS_FPU, - .mmu_features = MMU_FTR_TYPE_47x | - MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_LOCK_BCAST_INVAL, - .icache_bsize = 32, - .dcache_bsize = 128, - .machine_check = machine_check_47x, - .platform = "ppc470", - }, - { /* 476fpe */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x7ff50000, - .cpu_name = "476fpe", - .cpu_features = CPU_FTRS_47X | CPU_FTR_476_DD2, - .cpu_user_features = COMMON_USER_BOOKE | - PPC_FEATURE_HAS_FPU, - .mmu_features = MMU_FTR_TYPE_47x | - MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_LOCK_BCAST_INVAL, - .icache_bsize = 32, - .dcache_bsize = 128, - .machine_check = machine_check_47x, - .platform = "ppc470", - }, - { /* 476 iss */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00050000, - .cpu_name = "476", - .cpu_features = CPU_FTRS_47X, - .cpu_user_features = COMMON_USER_BOOKE | - PPC_FEATURE_HAS_FPU, - .mmu_features = MMU_FTR_TYPE_47x | - MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_LOCK_BCAST_INVAL, - .icache_bsize = 32, - .dcache_bsize = 128, - .machine_check = machine_check_47x, - .platform = "ppc470", - }, - { /* 476 others */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x11a50000, - .cpu_name = "476", - .cpu_features = CPU_FTRS_47X, - .cpu_user_features = COMMON_USER_BOOKE | - PPC_FEATURE_HAS_FPU, - .mmu_features = MMU_FTR_TYPE_47x | - MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_LOCK_BCAST_INVAL, - .icache_bsize = 32, - .dcache_bsize = 128, - .machine_check = machine_check_47x, - .platform = "ppc470", - }, - { /* default match */ - .pvr_mask = 0x00000000, - .pvr_value = 0x00000000, - .cpu_name = "(generic 47x PPC)", - .cpu_features = CPU_FTRS_47X, - .cpu_user_features = COMMON_USER_BOOKE, - .mmu_features = MMU_FTR_TYPE_47x, - .icache_bsize = 32, - .dcache_bsize = 128, - .machine_check = machine_check_47x, - .platform = "ppc470", - } -#endif /* CONFIG_PPC_47x */ -#endif /* CONFIG_44x */ -#endif /* CONFIG_PPC32 */ -#ifdef CONFIG_E500 -#ifdef CONFIG_PPC32 -#ifndef CONFIG_PPC_E500MC - { /* e500 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x80200000, - .cpu_name = "e500", - .cpu_features = CPU_FTRS_E500, - .cpu_user_features = COMMON_USER_BOOKE | - PPC_FEATURE_HAS_SPE_COMP | - PPC_FEATURE_HAS_EFP_SINGLE_COMP, - .cpu_user_features2 = PPC_FEATURE2_ISEL, - .mmu_features = MMU_FTR_TYPE_FSL_E, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 4, - .cpu_setup = __setup_cpu_e500v1, - .machine_check = machine_check_e500, - .platform = "ppc8540", - }, - { /* e500v2 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x80210000, - .cpu_name = "e500v2", - .cpu_features = CPU_FTRS_E500_2, - .cpu_user_features = COMMON_USER_BOOKE | - PPC_FEATURE_HAS_SPE_COMP | - PPC_FEATURE_HAS_EFP_SINGLE_COMP | - PPC_FEATURE_HAS_EFP_DOUBLE_COMP, - .cpu_user_features2 = PPC_FEATURE2_ISEL, - .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS, - .icache_bsize = 32, - .dcache_bsize = 32, - .num_pmcs = 4, - .cpu_setup = __setup_cpu_e500v2, - .machine_check = machine_check_e500, - .platform = "ppc8548", - .cpu_down_flush = cpu_down_flush_e500v2, - }, -#else - { /* e500mc */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x80230000, - .cpu_name = "e500mc", - .cpu_features = CPU_FTRS_E500MC, - .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, - .cpu_user_features2 = PPC_FEATURE2_ISEL, - .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | - MMU_FTR_USE_TLBILX, - .icache_bsize = 64, - .dcache_bsize = 64, - .num_pmcs = 4, - .cpu_setup = __setup_cpu_e500mc, - .machine_check = machine_check_e500mc, - .platform = "ppce500mc", - .cpu_down_flush = cpu_down_flush_e500mc, - }, -#endif /* CONFIG_PPC_E500MC */ -#endif /* CONFIG_PPC32 */ -#ifdef CONFIG_PPC_E500MC - { /* e5500 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x80240000, - .cpu_name = "e5500", - .cpu_features = CPU_FTRS_E5500, - .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, - .cpu_user_features2 = PPC_FEATURE2_ISEL, - .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | - MMU_FTR_USE_TLBILX, - .icache_bsize = 64, - .dcache_bsize = 64, - .num_pmcs = 4, - .cpu_setup = __setup_cpu_e5500, -#ifndef CONFIG_PPC32 - .cpu_restore = __restore_cpu_e5500, -#endif - .machine_check = machine_check_e500mc, - .platform = "ppce5500", - .cpu_down_flush = cpu_down_flush_e5500, - }, - { /* e6500 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x80400000, - .cpu_name = "e6500", - .cpu_features = CPU_FTRS_E6500, - .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU | - PPC_FEATURE_HAS_ALTIVEC_COMP, - .cpu_user_features2 = PPC_FEATURE2_ISEL, - .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | - MMU_FTR_USE_TLBILX, - .icache_bsize = 64, - .dcache_bsize = 64, - .num_pmcs = 6, - .cpu_setup = __setup_cpu_e6500, -#ifndef CONFIG_PPC32 - .cpu_restore = __restore_cpu_e6500, -#endif - .machine_check = machine_check_e500mc, - .platform = "ppce6500", - .cpu_down_flush = cpu_down_flush_e6500, - }, -#endif /* CONFIG_PPC_E500MC */ -#ifdef CONFIG_PPC32 - { /* default match */ - .pvr_mask = 0x00000000, - .pvr_value = 0x00000000, - .cpu_name = "(generic E500 PPC)", - .cpu_features = CPU_FTRS_E500, - .cpu_user_features = COMMON_USER_BOOKE | - PPC_FEATURE_HAS_SPE_COMP | - PPC_FEATURE_HAS_EFP_SINGLE_COMP, - .mmu_features = MMU_FTR_TYPE_FSL_E, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_e500, - .platform = "powerpc", - } -#endif /* CONFIG_PPC32 */ -#endif /* CONFIG_E500 */ -}; +#include "cpu_specs.h" void __init set_cur_cpu_spec(struct cpu_spec *s) { @@ -2018,6 +104,8 @@ struct cpu_spec * __init identify_cpu(unsigned long offset, unsigned int pvr) struct cpu_spec *s = cpu_specs; int i; + BUILD_BUG_ON(!ARRAY_SIZE(cpu_specs)); + s = PTRRELOC(s); for (i = 0; i < ARRAY_SIZE(cpu_specs); i++,s++) { diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index fc800a9fb2c4..c3fb9fdf5bd7 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -1099,7 +1099,7 @@ static int __init dt_cpu_ftrs_scan_callback(unsigned long node, const char prop = of_get_flat_dt_prop(node, "display-name", NULL); if (prop && strlen((char *)prop) != 0) { - strlcpy(dt_cpu_name, (char *)prop, sizeof(dt_cpu_name)); + strscpy(dt_cpu_name, (char *)prop, sizeof(dt_cpu_name)); cur_cpu_spec->cpu_name = dt_cpu_name; } diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 1d599df6f169..3fc7c9886bb7 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -49,7 +49,7 @@ */ .align 12 -#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_E500) +#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_PPC_E500) .globl prepare_transfer_to_handler prepare_transfer_to_handler: /* if from kernel, check interrupted DOZE/NAP mode */ @@ -68,10 +68,10 @@ prepare_transfer_to_handler: lwz r9,_MSR(r11) /* if sleeping, clear MSR.EE */ rlwinm r9,r9,0,~MSR_EE lwz r12,_LINK(r11) /* and return to address in LR */ - lwz r2, GPR2(r11) + REST_GPR(2, r11) b fast_exception_return _ASM_NOKPROBE_SYMBOL(prepare_transfer_to_handler) -#endif /* CONFIG_PPC_BOOK3S_32 || CONFIG_E500 */ +#endif /* CONFIG_PPC_BOOK3S_32 || CONFIG_PPC_E500 */ #if defined(CONFIG_PPC_KUEP) && defined(CONFIG_PPC_BOOK3S_32) .globl __kuep_lock @@ -101,6 +101,7 @@ __kuep_unlock: .globl transfer_to_syscall transfer_to_syscall: + stw r3, ORIG_GPR3(r1) stw r11, GPR1(r1) stw r11, 0(r1) mflr r12 @@ -121,9 +122,9 @@ transfer_to_syscall: SAVE_NVGPRS(r1) kuep_lock - /* Calling convention has r9 = orig r0, r10 = regs */ - addi r10,r1,STACK_FRAME_OVERHEAD - mr r9,r0 + /* Calling convention has r3 = regs, r4 = orig r0 */ + addi r3,r1,STACK_FRAME_OVERHEAD + mr r4,r0 bl system_call_exception ret_from_syscall: @@ -143,7 +144,7 @@ ret_from_syscall: lwz r7,_NIP(r1) lwz r8,_MSR(r1) cmpwi r3,0 - lwz r3,GPR3(r1) + REST_GPR(3, r1) syscall_exit_finish: mtspr SPRN_SRR0,r7 mtspr SPRN_SRR1,r8 @@ -151,8 +152,8 @@ syscall_exit_finish: bne 3f mtcr r5 -1: lwz r2,GPR2(r1) - lwz r1,GPR1(r1) +1: REST_GPR(2, r1) + REST_GPR(1, r1) rfi #ifdef CONFIG_40x b . /* Prevent prefetch past rfi */ @@ -164,10 +165,8 @@ syscall_exit_finish: REST_NVGPRS(r1) mtctr r4 mtxer r5 - lwz r0,GPR0(r1) - lwz r3,GPR3(r1) - REST_GPRS(4, 11, r1) - lwz r12,GPR12(r1) + REST_GPR(0, r1) + REST_GPRS(3, 12, r1) b 1b #ifdef CONFIG_44x @@ -259,13 +258,12 @@ fast_exception_return: beq 3f /* if not, we've got problems */ #endif -2: REST_GPRS(3, 6, r11) - lwz r10,_CCR(r11) - REST_GPRS(1, 2, r11) +2: lwz r10,_CCR(r11) + REST_GPRS(1, 6, r11) mtcr r10 lwz r10,_LINK(r11) mtlr r10 - /* Clear the exception_marker on the stack to avoid confusing stacktrace */ + /* Clear the exception marker on the stack to avoid confusing stacktrace */ li r10, 0 stw r10, 8(r11) REST_GPR(10, r11) @@ -276,7 +274,7 @@ fast_exception_return: mtspr SPRN_SRR0,r12 REST_GPR(9, r11) REST_GPR(12, r11) - lwz r11,GPR11(r11) + REST_GPR(11, r11) rfi #ifdef CONFIG_40x b . /* Prevent prefetch past rfi */ @@ -322,7 +320,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS) li r0,0 /* - * Leaving a stale exception_marker on the stack can confuse + * Leaving a stale exception marker on the stack can confuse * the reliable stack unwinder later on. Clear it. */ stw r0,8(r1) @@ -374,7 +372,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS) mtspr SPRN_XER,r5 /* - * Leaving a stale exception_marker on the stack can confuse + * Leaving a stale exception marker on the stack can confuse * the reliable stack unwinder later on. Clear it. */ stw r0,8(r1) @@ -453,9 +451,8 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return) lwz r3,_MSR(r1); \ andi. r3,r3,MSR_PR; \ bne interrupt_return; \ - lwz r0,GPR0(r1); \ - lwz r2,GPR2(r1); \ - REST_GPRS(3, 8, r1); \ + REST_GPR(0, r1); \ + REST_GPRS(2, 8, r1); \ lwz r10,_XER(r1); \ lwz r11,_CTR(r1); \ mtspr SPRN_XER,r10; \ @@ -474,11 +471,8 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return) lwz r12,_MSR(r1); \ mtspr exc_lvl_srr0,r11; \ mtspr exc_lvl_srr1,r12; \ - lwz r9,GPR9(r1); \ - lwz r12,GPR12(r1); \ - lwz r10,GPR10(r1); \ - lwz r11,GPR11(r1); \ - lwz r1,GPR1(r1); \ + REST_GPRS(9, 12, r1); \ + REST_GPR(1, r1); \ exc_lvl_rfi; \ b .; /* prevent prefetch past exc_lvl_rfi */ @@ -488,7 +482,7 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return) mtspr SPRN_##exc_lvl_srr0,r9; \ mtspr SPRN_##exc_lvl_srr1,r10; -#if defined(CONFIG_PPC_BOOK3E_MMU) +#if defined(CONFIG_PPC_E500) #ifdef CONFIG_PHYS_64BIT #define RESTORE_MAS7 \ lwz r11,MAS7(r1); \ diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 01ace4c56104..3e2e37e6ecab 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -292,16 +292,16 @@ _GLOBAL(enter_prom) /* Prepare a 32-bit mode big endian MSR */ -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 rlwinm r11,r11,0,1,31 mtsrr1 r11 rfi -#else /* CONFIG_PPC_BOOK3E */ +#else /* CONFIG_PPC_BOOK3E_64 */ LOAD_REG_IMMEDIATE(r12, MSR_SF | MSR_LE) andc r11,r11,r12 mtsrr1 r11 RFI_TO_KERNEL -#endif /* CONFIG_PPC_BOOK3E */ +#endif /* CONFIG_PPC_BOOK3E_64 */ 1: /* Return from OF */ FIXUP_ENDIAN diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 67dc4e3179a0..930e36099015 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -216,17 +216,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) mtlr r10 mtcr r11 - ld r10,GPR10(r1) - ld r11,GPR11(r1) - ld r12,GPR12(r1) + REST_GPRS(10, 12, r1) mtspr \scratch,r0 std r10,\paca_ex+EX_R10(r13); std r11,\paca_ex+EX_R11(r13); ld r10,_NIP(r1) ld r11,_MSR(r1) - ld r0,GPR0(r1) - ld r1,GPR1(r1) + REST_GPR(0, r1) + REST_GPR(1, r1) mtspr \srr0,r10 mtspr \srr1,r11 ld r10,\paca_ex+EX_R10(r13) @@ -291,7 +289,6 @@ ret_from_mc_except: #define SPRN_MC_SRR0 SPRN_MCSRR0 #define SPRN_MC_SRR1 SPRN_MCSRR1 -#ifdef CONFIG_PPC_FSL_BOOK3E #define GEN_BTB_FLUSH \ START_BTB_FLUSH_SECTION \ beq 1f; \ @@ -307,13 +304,6 @@ ret_from_mc_except: #define DBG_BTB_FLUSH CRIT_BTB_FLUSH #define MC_BTB_FLUSH CRIT_BTB_FLUSH #define GDBELL_BTB_FLUSH GEN_BTB_FLUSH -#else -#define GEN_BTB_FLUSH -#define CRIT_BTB_FLUSH -#define DBG_BTB_FLUSH -#define MC_BTB_FLUSH -#define GDBELL_BTB_FLUSH -#endif #define NORMAL_EXCEPTION_PROLOG(n, intnum, addition) \ EXCEPTION_PROLOG(n, intnum, GEN, addition##_GEN(n)) @@ -372,25 +362,24 @@ ret_from_mc_except: /* Core exception code for all exceptions except TLB misses. */ #define EXCEPTION_COMMON_LVL(n, scratch, excf) \ exc_##n##_common: \ - std r0,GPR0(r1); /* save r0 in stackframe */ \ - std r2,GPR2(r1); /* save r2 in stackframe */ \ - SAVE_GPRS(3, 9, r1); /* save r3 - r9 in stackframe */ \ + SAVE_GPR(0, r1); /* save r0 in stackframe */ \ + SAVE_GPRS(2, 9, r1); /* save r2 - r9 in stackframe */ \ std r10,_NIP(r1); /* save SRR0 to stackframe */ \ std r11,_MSR(r1); /* save SRR1 to stackframe */ \ beq 2f; /* if from kernel mode */ \ 2: ld r3,excf+EX_R10(r13); /* get back r10 */ \ ld r4,excf+EX_R11(r13); /* get back r11 */ \ mfspr r5,scratch; /* get back r13 */ \ - std r12,GPR12(r1); /* save r12 in stackframe */ \ - ld r2,PACATOC(r13); /* get kernel TOC into r2 */ \ + SAVE_GPR(12, r1); /* save r12 in stackframe */ \ + LOAD_PACA_TOC(); /* get kernel TOC into r2 */ \ mflr r6; /* save LR in stackframe */ \ mfctr r7; /* save CTR in stackframe */ \ mfspr r8,SPRN_XER; /* save XER in stackframe */ \ ld r9,excf+EX_R1(r13); /* load orig r1 back from PACA */ \ lwz r10,excf+EX_CR(r13); /* load orig CR back from PACA */ \ lbz r11,PACAIRQSOFTMASK(r13); /* get current IRQ softe */ \ - ld r12,exception_marker@toc(r2); \ - li r0,0; \ + LOAD_REG_IMMEDIATE(r12, STACK_FRAME_REGS_MARKER); \ + ZEROIZE_GPR(0); \ std r3,GPR10(r1); /* save r10 to stackframe */ \ std r4,GPR11(r1); /* save r11 to stackframe */ \ std r5,GPR13(r1); /* save it to stackframe */ \ @@ -470,12 +459,6 @@ exc_##n##_bad_stack: \ bl hdlr; \ b interrupt_return -/* This value is used to mark exception frames on the stack. */ - .section ".toc","aw" -exception_marker: - .tc ID_EXC_MARKER[TC],STACK_FRAME_REGS_MARKER - - /* * And here we have the exception vectors ! */ @@ -704,9 +687,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) beq+ 1f #ifdef CONFIG_RELOCATABLE - ld r15,PACATOC(r13) - ld r14,interrupt_base_book3e@got(r15) - ld r15,__end_interrupts@got(r15) + __LOAD_PACA_TOC(r15) + LOAD_REG_ADDR_ALTTOC(r14, r15, interrupt_base_book3e) + LOAD_REG_ADDR_ALTTOC(r15, r15, __end_interrupts) cmpld cr0,r10,r14 cmpld cr1,r10,r15 #else @@ -775,9 +758,9 @@ kernel_dbg_exc: beq+ 1f #ifdef CONFIG_RELOCATABLE - ld r15,PACATOC(r13) - ld r14,interrupt_base_book3e@got(r15) - ld r15,__end_interrupts@got(r15) + __LOAD_PACA_TOC(r15) + LOAD_REG_ADDR_ALTTOC(r14, r15, interrupt_base_book3e) + LOAD_REG_ADDR_ALTTOC(r15, r15, __end_interrupts) cmpld cr0,r10,r14 cmpld cr1,r10,r15 #else @@ -900,9 +883,9 @@ kernel_dbg_exc: .macro SEARCH_RESTART_TABLE #ifdef CONFIG_RELOCATABLE - ld r11,PACATOC(r13) - ld r14,__start___restart_table@got(r11) - ld r15,__stop___restart_table@got(r11) + __LOAD_PACA_TOC(r11) + LOAD_REG_ADDR_ALTTOC(r14, r11, __start___restart_table) + LOAD_REG_ADDR_ALTTOC(r15, r11, __stop___restart_table) #else LOAD_REG_IMMEDIATE_SYM(r14, r11, __start___restart_table) LOAD_REG_IMMEDIATE_SYM(r15, r11, __stop___restart_table) @@ -1056,15 +1039,14 @@ bad_stack_book3e: mfspr r11,SPRN_ESR std r10,_DEAR(r1) std r11,_ESR(r1) - std r0,GPR0(r1); /* save r0 in stackframe */ \ - std r2,GPR2(r1); /* save r2 in stackframe */ \ - SAVE_GPRS(3, 9, r1); /* save r3 - r9 in stackframe */ \ + SAVE_GPR(0, r1); /* save r0 in stackframe */ \ + SAVE_GPRS(2, 9, r1); /* save r2 - r9 in stackframe */ \ ld r3,PACA_EXGEN+EX_R10(r13);/* get back r10 */ \ ld r4,PACA_EXGEN+EX_R11(r13);/* get back r11 */ \ mfspr r5,SPRN_SPRG_GEN_SCRATCH;/* get back r13 XXX can be wrong */ \ std r3,GPR10(r1); /* save r10 to stackframe */ \ std r4,GPR11(r1); /* save r11 to stackframe */ \ - std r12,GPR12(r1); /* save r12 in stackframe */ \ + SAVE_GPR(12, r1); /* save r12 in stackframe */ \ std r5,GPR13(r1); /* save it to stackframe */ \ mflr r10 mfctr r11 @@ -1072,14 +1054,14 @@ bad_stack_book3e: std r10,_LINK(r1) std r11,_CTR(r1) std r12,_XER(r1) - SAVE_GPRS(14, 31, r1) + SAVE_NVGPRS(r1) lhz r12,PACA_TRAP_SAVE(r13) std r12,_TRAP(r1) addi r11,r1,INT_FRAME_SIZE std r11,0(r1) - li r12,0 + ZEROIZE_GPR(12) std r12,0(r11) - ld r2,PACATOC(r13) + LOAD_PACA_TOC() 1: addi r3,r1,STACK_FRAME_OVERHEAD bl kernel_bad_stack b 1b @@ -1320,8 +1302,8 @@ a2_tlbinit_after_linear_map: /* Now we branch the new virtual address mapped by this entry */ #ifdef CONFIG_RELOCATABLE - ld r5,PACATOC(r13) - ld r3,1f@got(r5) + __LOAD_PACA_TOC(r5) + LOAD_REG_ADDR_ALTTOC(r3, r5, 1f) #else LOAD_REG_IMMEDIATE_SYM(r3, r5, 1f) #endif diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 3d0dc133a9ae..5381a43e50fe 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -281,7 +281,7 @@ BEGIN_FTR_SECTION mfspr r9,SPRN_PPR END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) HMT_MEDIUM - std r10,IAREA+EX_R10(r13) /* save r10 - r12 */ + std r10,IAREA+EX_R10(r13) /* save r10 */ .if ICFAR BEGIN_FTR_SECTION mfspr r10,SPRN_CFAR @@ -321,7 +321,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) mfctr r10 std r10,IAREA+EX_CTR(r13) mfcr r9 - std r11,IAREA+EX_R11(r13) + std r11,IAREA+EX_R11(r13) /* save r11 - r12 */ std r12,IAREA+EX_R12(r13) /* @@ -580,7 +580,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) std r2,GPR2(r1) /* save r2 in stackframe */ SAVE_GPRS(3, 8, r1) /* save r3 - r8 in stackframe */ mflr r9 /* Get LR, later save to stack */ - ld r2,PACATOC(r13) /* get kernel TOC into r2 */ + LOAD_PACA_TOC() /* get kernel TOC into r2 */ std r9,_LINK(r1) lbz r10,PACAIRQSOFTMASK(r13) mfspr r11,SPRN_XER /* save XER in stackframe */ @@ -589,7 +589,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) li r9,IVEC std r9,_TRAP(r1) /* set trap number */ li r10,0 - ld r11,exception_marker@toc(r2) + LOAD_REG_IMMEDIATE(r11, STACK_FRAME_REGS_MARKER) std r10,RESULT(r1) /* clear regs->result */ std r11,STACK_FRAME_OVERHEAD-16(r1) /* mark the frame */ .endm @@ -610,7 +610,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) .macro SEARCH_RESTART_TABLE #ifdef CONFIG_RELOCATABLE mr r12,r2 - ld r2,PACATOC(r13) + LOAD_PACA_TOC() LOAD_REG_ADDR(r9, __start___restart_table) LOAD_REG_ADDR(r10, __stop___restart_table) mr r2,r12 @@ -640,7 +640,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) .macro SEARCH_SOFT_MASK_TABLE #ifdef CONFIG_RELOCATABLE mr r12,r2 - ld r2,PACATOC(r13) + LOAD_PACA_TOC() LOAD_REG_ADDR(r9, __start___soft_mask_table) LOAD_REG_ADDR(r10, __stop___soft_mask_table) mr r2,r12 @@ -702,6 +702,71 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) ld r1,GPR1(r1) .endm +/* + * EARLY_BOOT_FIXUP - Fix real-mode interrupt with wrong endian in early boot. + * + * There's a short window during boot where although the kernel is running + * little endian, any exceptions will cause the CPU to switch back to big + * endian. For example a WARN() boils down to a trap instruction, which will + * cause a program check, and we end up here but with the CPU in big endian + * mode. The first instruction of the program check handler (in GEN_INT_ENTRY + * below) is an mtsprg, which when executed in the wrong endian is an lhzu with + * a ~3GB displacement from r3. The content of r3 is random, so that is a load + * from some random location, and depending on the system can easily lead to a + * checkstop, or an infinitely recursive page fault. + * + * So to handle that case we have a trampoline here that can detect we are in + * the wrong endian and flip us back to the correct endian. We can't flip + * MSR[LE] using mtmsr, so we have to use rfid. That requires backing up SRR0/1 + * as well as a GPR. To do that we use SPRG0/2/3, as SPRG1 is already used for + * the paca. SPRG3 is user readable, but this trampoline is only active very + * early in boot, and SPRG3 will be reinitialised in vdso_getcpu_init() before + * userspace starts. + */ +.macro EARLY_BOOT_FIXUP +BEGIN_FTR_SECTION +#ifdef CONFIG_CPU_LITTLE_ENDIAN + tdi 0,0,0x48 // Trap never, or in reverse endian: b . + 8 + b 2f // Skip trampoline if endian is correct + .long 0xa643707d // mtsprg 0, r11 Backup r11 + .long 0xa6027a7d // mfsrr0 r11 + .long 0xa643727d // mtsprg 2, r11 Backup SRR0 in SPRG2 + .long 0xa6027b7d // mfsrr1 r11 + .long 0xa643737d // mtsprg 3, r11 Backup SRR1 in SPRG3 + .long 0xa600607d // mfmsr r11 + .long 0x01006b69 // xori r11, r11, 1 Invert MSR[LE] + .long 0xa6037b7d // mtsrr1 r11 + /* + * This is 'li r11,1f' where 1f is the absolute address of that + * label, byteswapped into the SI field of the instruction. + */ + .long 0x00006039 | \ + ((ABS_ADDR(1f, real_vectors) & 0x00ff) << 24) | \ + ((ABS_ADDR(1f, real_vectors) & 0xff00) << 8) + .long 0xa6037a7d // mtsrr0 r11 + .long 0x2400004c // rfid +1: + mfsprg r11, 3 + mtsrr1 r11 // Restore SRR1 + mfsprg r11, 2 + mtsrr0 r11 // Restore SRR0 + mfsprg r11, 0 // Restore r11 +2: +#endif + /* + * program check could hit at any time, and pseries can not block + * MSR[ME] in early boot. So check if there is anything useful in r13 + * yet, and spin forever if not. + */ + mtsprg 0, r11 + mfcr r11 + cmpdi r13, 0 + beq . + mtcr r11 + mfsprg r11, 0 +END_FTR_SECTION(0, 1) // nop out after boot +.endm + /* * There are a few constraints to be concerned with. * - Real mode exceptions code/data must be located at their physical location. @@ -1079,6 +1144,7 @@ INT_DEFINE_BEGIN(machine_check) INT_DEFINE_END(machine_check) EXC_REAL_BEGIN(machine_check, 0x200, 0x100) + EARLY_BOOT_FIXUP GEN_INT_ENTRY machine_check_early, virt=0 EXC_REAL_END(machine_check, 0x200, 0x100) EXC_VIRT_NONE(0x4200, 0x100) @@ -1143,6 +1209,9 @@ BEGIN_FTR_SECTION bl enable_machine_check END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) addi r3,r1,STACK_FRAME_OVERHEAD +BEGIN_FTR_SECTION + bl machine_check_early_boot +END_FTR_SECTION(0, 1) // nop out after boot bl machine_check_early std r3,RESULT(r1) /* Save result */ ld r12,_MSR(r1) @@ -1619,51 +1688,7 @@ INT_DEFINE_BEGIN(program_check) INT_DEFINE_END(program_check) EXC_REAL_BEGIN(program_check, 0x700, 0x100) - -#ifdef CONFIG_CPU_LITTLE_ENDIAN - /* - * There's a short window during boot where although the kernel is - * running little endian, any exceptions will cause the CPU to switch - * back to big endian. For example a WARN() boils down to a trap - * instruction, which will cause a program check, and we end up here but - * with the CPU in big endian mode. The first instruction of the program - * check handler (in GEN_INT_ENTRY below) is an mtsprg, which when - * executed in the wrong endian is an lhzu with a ~3GB displacement from - * r3. The content of r3 is random, so that is a load from some random - * location, and depending on the system can easily lead to a checkstop, - * or an infinitely recursive page fault. - * - * So to handle that case we have a trampoline here that can detect we - * are in the wrong endian and flip us back to the correct endian. We - * can't flip MSR[LE] using mtmsr, so we have to use rfid. That requires - * backing up SRR0/1 as well as a GPR. To do that we use SPRG0/2/3, as - * SPRG1 is already used for the paca. SPRG3 is user readable, but this - * trampoline is only active very early in boot, and SPRG3 will be - * reinitialised in vdso_getcpu_init() before userspace starts. - */ -BEGIN_FTR_SECTION - tdi 0,0,0x48 // Trap never, or in reverse endian: b . + 8 - b 1f // Skip trampoline if endian is correct - .long 0xa643707d // mtsprg 0, r11 Backup r11 - .long 0xa6027a7d // mfsrr0 r11 - .long 0xa643727d // mtsprg 2, r11 Backup SRR0 in SPRG2 - .long 0xa6027b7d // mfsrr1 r11 - .long 0xa643737d // mtsprg 3, r11 Backup SRR1 in SPRG3 - .long 0xa600607d // mfmsr r11 - .long 0x01006b69 // xori r11, r11, 1 Invert MSR[LE] - .long 0xa6037b7d // mtsrr1 r11 - .long 0x34076039 // li r11, 0x734 - .long 0xa6037a7d // mtsrr0 r11 - .long 0x2400004c // rfid - mfsprg r11, 3 - mtsrr1 r11 // Restore SRR1 - mfsprg r11, 2 - mtsrr0 r11 // Restore SRR0 - mfsprg r11, 0 // Restore r11 -1: -END_FTR_SECTION(0, 1) // nop out after boot -#endif /* CONFIG_CPU_LITTLE_ENDIAN */ - + EARLY_BOOT_FIXUP GEN_INT_ENTRY program_check, virt=0 EXC_REAL_END(program_check, 0x700, 0x100) EXC_VIRT_BEGIN(program_check, 0x4700, 0x100) @@ -2794,6 +2819,20 @@ masked_Hinterrupt: masked_interrupt: .endif stw r9,PACA_EXGEN+EX_CCR(r13) +#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG + /* + * Ensure there was no previous MUST_HARD_MASK interrupt or + * HARD_DIS setting. If this does fire, the interrupt is still + * masked and MSR[EE] will be cleared on return, so no need to + * panic, but somebody probably enabled MSR[EE] under + * PACA_IRQ_HARD_DIS, mtmsr(mfmsr() | MSR_x) being a common + * cause. + */ + lbz r9,PACAIRQHAPPENED(r13) + andi. r9,r9,(PACA_IRQ_MUST_HARD_MASK|PACA_IRQ_HARD_DIS) +0: tdnei r9,0 + EMIT_WARN_ENTRY 0b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE) +#endif lbz r9,PACAIRQHAPPENED(r13) or r9,r9,r10 stb r9,PACAIRQHAPPENED(r13) @@ -3034,22 +3073,6 @@ EXPORT_SYMBOL(do_uaccess_flush) MASKED_INTERRUPT MASKED_INTERRUPT hsrr=1 - /* - * Relocation-on interrupts: A subset of the interrupts can be delivered - * with IR=1/DR=1, if AIL==2 and MSR.HV won't be changed by delivering - * it. Addresses are the same as the original interrupt addresses, but - * offset by 0xc000000000004000. - * It's impossible to receive interrupts below 0x300 via this mechanism. - * KVM: None of these traps are from the guest ; anything that escalated - * to HV=1 from HV=0 is delivered via real mode handlers. - */ - - /* - * This uses the standard macro, since the original 0x300 vector - * only has extra guff for STAB-based processors -- which never - * come here. - */ - USE_FIXED_SECTION(virt_trampolines) /* * All code below __end_soft_masked is treated as soft-masked. If @@ -3075,7 +3098,7 @@ CLOSE_FIXED_SECTION(virt_trampolines); USE_TEXT_SECTION() /* MSR[RI] should be clear because this uses SRR[01] */ -enable_machine_check: +_GLOBAL(enable_machine_check) mflr r0 bcl 20,31,$+4 0: mflr r3 diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index cf2c08902c05..cfc09a96a420 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -143,7 +143,7 @@ DEFINE_FIXED_SYMBOL(__run_at_load, first_256B) .globl __secondary_hold __secondary_hold: FIXUP_ENDIAN -#ifndef CONFIG_PPC_BOOK3E +#ifndef CONFIG_PPC_BOOK3E_64 mfmsr r24 ori r24,r24,MSR_RI mtmsrd r24 /* RI on */ @@ -160,7 +160,7 @@ __secondary_hold: sync li r26,0 -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 tovirt(r26,r26) #endif /* All secondary cpus wait here until told to start. */ @@ -169,7 +169,7 @@ __secondary_hold: beq 100b #if defined(CONFIG_SMP) || defined(CONFIG_KEXEC_CORE) -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 tovirt(r12,r12) #endif mtctr r12 @@ -178,7 +178,7 @@ __secondary_hold: * it may be the case that other platforms have r4 right to * begin with, this gives us some safety in case it is not */ -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 mr r4,r25 #else li r4,0 @@ -192,13 +192,6 @@ __secondary_hold: #endif CLOSE_FIXED_SECTION(first_256B) -/* This value is used to mark exception frames on the stack. */ - .section ".toc","aw" -/* This value is used to mark exception frames on the stack. */ -exception_marker: - .tc ID_EXC_MARKER[TC],STACK_FRAME_REGS_MARKER - .previous - /* * On server, we include the exception vectors code here as it * relies on absolute addressing which is only possible within @@ -214,7 +207,7 @@ USE_TEXT_SECTION() #include "interrupt_64.S" -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 /* * The booting_thread_hwid holds the thread id we want to boot in cpu * hotplug case. It is set by cpu hotplug code, and is invalid by default. @@ -322,7 +315,7 @@ _GLOBAL(fsl_secondary_thread_init) bl book3e_secondary_thread_init b generic_secondary_common_init -#endif /* CONFIG_PPC_BOOK3E */ +#endif /* CONFIG_PPC_BOOK3E_64 */ /* * On pSeries and most other platforms, secondary processors spin @@ -345,7 +338,7 @@ _GLOBAL(generic_secondary_smp_init) bl relative_toc tovirt(r2,r2) -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 /* Book3E initialization */ mr r3,r24 mr r4,r25 @@ -417,7 +410,7 @@ generic_secondary_common_init: b kexec_wait /* next kernel might do better */ 2: SET_PACA(r13) -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 addi r12,r13,PACA_EXTLB /* and TLB exc frame in another */ mtspr SPRN_SPRG_TLB_EXFRAME,r12 #endif @@ -494,6 +487,9 @@ __start_initialization_multiplatform: /* Make sure we are running in 64 bits mode */ bl enable_64b_mode + /* Zero r13 (paca) so early program check / mce don't use it */ + li r13,0 + /* Get TOC pointer (current runtime address) */ bl relative_toc @@ -519,7 +515,7 @@ __start_initialization_multiplatform: mr r29,r9 #endif -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 bl start_initialization_book3e b __after_prom_start #else @@ -540,7 +536,7 @@ __start_initialization_multiplatform: /* Switch off MMU if not already off */ bl __mmu_off b __after_prom_start -#endif /* CONFIG_PPC_BOOK3E */ +#endif /* CONFIG_PPC_BOOK3E_64 */ __REF __boot_from_prom: @@ -587,11 +583,11 @@ __after_prom_start: /* process relocations for the final address of the kernel */ lis r25,PAGE_OFFSET@highest /* compute virtual base of kernel */ sldi r25,r25,32 -#if defined(CONFIG_PPC_BOOK3E) +#if defined(CONFIG_PPC_BOOK3E_64) tovirt(r26,r26) /* on booke, we already run at PAGE_OFFSET */ #endif lwz r7,(FIXED_SYMBOL_ABS_ADDR(__run_at_load))(r26) -#if defined(CONFIG_PPC_BOOK3E) +#if defined(CONFIG_PPC_BOOK3E_64) tophys(r26,r26) #endif cmplwi cr0,r7,1 /* flagged to stay where we are ? */ @@ -599,7 +595,7 @@ __after_prom_start: add r25,r25,r26 1: mr r3,r25 bl relocate -#if defined(CONFIG_PPC_BOOK3E) +#if defined(CONFIG_PPC_BOOK3E_64) /* IVPR needs to be set after relocation. */ bl init_core_book3e #endif @@ -613,11 +609,11 @@ __after_prom_start: * Note: This process overwrites the OF exception vectors. */ li r3,0 /* target addr */ -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 tovirt(r3,r3) /* on booke, we already run at PAGE_OFFSET */ #endif mr. r4,r26 /* In some cases the loader may */ -#if defined(CONFIG_PPC_BOOK3E) +#if defined(CONFIG_PPC_BOOK3E_64) tovirt(r4,r4) #endif beq 9f /* have already put us at zero */ @@ -630,14 +626,14 @@ __after_prom_start: * variable __run_at_load, if it is set the kernel is treated as relocatable * kernel, otherwise it will be moved to PHYSICAL_START */ -#if defined(CONFIG_PPC_BOOK3E) +#if defined(CONFIG_PPC_BOOK3E_64) tovirt(r26,r26) /* on booke, we already run at PAGE_OFFSET */ #endif lwz r7,(FIXED_SYMBOL_ABS_ADDR(__run_at_load))(r26) cmplwi cr0,r7,1 bne 3f -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 LOAD_REG_ADDR(r5, __end_interrupts) LOAD_REG_ADDR(r11, _stext) sub r5,r5,r11 @@ -848,7 +844,7 @@ __secondary_start: * before going into C code. */ start_secondary_prolog: - ld r2,PACATOC(r13) + LOAD_PACA_TOC() li r3,0 std r3,0(r1) /* Zero the stack frame pointer */ bl start_secondary @@ -871,10 +867,10 @@ _GLOBAL(start_secondary_resume) */ enable_64b_mode: mfmsr r11 /* grab the current MSR */ -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 oris r11,r11,0x8000 /* CM bit set, we'll set ICM later */ mtmsr r11 -#else /* CONFIG_PPC_BOOK3E */ +#else /* CONFIG_PPC_BOOK3E_64 */ LOAD_REG_IMMEDIATE(r12, MSR_64BIT) or r11,r11,r12 mtmsrd r11 @@ -940,7 +936,7 @@ start_here_multiplatform: std r29,8(r11); #endif -#ifndef CONFIG_PPC_BOOK3E +#ifndef CONFIG_PPC_BOOK3E_64 mfmsr r6 ori r6,r6,MSR_RI mtmsrd r6 /* RI on */ @@ -988,7 +984,7 @@ start_here_common: std r1,PACAKSAVE(r13) /* Load the TOC (virtual address) */ - ld r2,PACATOC(r13) + LOAD_PACA_TOC() /* Mark interrupts soft and hard disabled (they might be enabled * in the PACA when doing hotplug) diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_85xx.S similarity index 99% rename from arch/powerpc/kernel/head_fsl_booke.S rename to arch/powerpc/kernel/head_85xx.S index f0db4f52bc00..52c0ab416326 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_85xx.S @@ -129,7 +129,7 @@ _GLOBAL(_start); /* * For the second relocation, we already set the right tlb entries - * for the kernel space, so skip the code in fsl_booke_entry_mapping.S + * for the kernel space, so skip the code in 85xx_entry_mapping.S */ cmpwi r19,1 beq set_ivor @@ -159,7 +159,7 @@ _GLOBAL(__early_start) lwz r20,0(r20) #define ENTRY_MAPPING_BOOT_SETUP -#include "fsl_booke_entry_mapping.S" +#include "85xx_entry_mapping.S" #undef ENTRY_MAPPING_BOOT_SETUP set_ivor: @@ -912,7 +912,7 @@ get_phys_addr: * Global functions */ -#ifdef CONFIG_E500 +#ifdef CONFIG_PPC_E500 #ifndef CONFIG_PPC_E500MC /* Adjust or setup IVORs for e500v1/v2 */ _GLOBAL(__setup_e500_ivors) @@ -955,7 +955,7 @@ _GLOBAL(__setup_ehv_ivors) sync blr #endif /* CONFIG_PPC_E500MC */ -#endif /* CONFIG_E500 */ +#endif /* CONFIG_PPC_E500 */ #ifdef CONFIG_SPE /* diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h index bb6d5d0fc4ac..1cb9d0f7cbf2 100644 --- a/arch/powerpc/kernel/head_booke.h +++ b/arch/powerpc/kernel/head_booke.h @@ -34,7 +34,7 @@ */ #define THREAD_NORMSAVE(offset) (THREAD_NORMSAVES + (offset * 4)) -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 #define BOOKE_CLEAR_BTB(reg) \ START_BTB_FLUSH_SECTION \ BTB_FLUSH(reg) \ @@ -103,7 +103,7 @@ END_BTB_FLUSH_SECTION .endm .macro prepare_transfer_to_handler -#ifdef CONFIG_E500 +#ifdef CONFIG_PPC_E500 andi. r12,r9,MSR_PR bne 777f bl prepare_transfer_to_handler @@ -242,7 +242,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV) .macro SAVE_MMU_REGS -#ifdef CONFIG_PPC_BOOK3E_MMU +#ifdef CONFIG_PPC_E500 mfspr r0,SPRN_MAS0 stw r0,MAS0(r1) mfspr r0,SPRN_MAS1 @@ -257,7 +257,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV) mfspr r0,SPRN_MAS7 stw r0,MAS7(r1) #endif /* CONFIG_PHYS_64BIT */ -#endif /* CONFIG_PPC_BOOK3E_MMU */ +#endif /* CONFIG_PPC_E500 */ #ifdef CONFIG_44x mfspr r0,SPRN_MMUCR stw r0,MMUCR(r1) diff --git a/arch/powerpc/kernel/idle_book3e.S b/arch/powerpc/kernel/idle_64e.S similarity index 93% rename from arch/powerpc/kernel/idle_book3e.S rename to arch/powerpc/kernel/idle_64e.S index cc008de58b05..0fc680e03dee 100644 --- a/arch/powerpc/kernel/idle_book3e.S +++ b/arch/powerpc/kernel/idle_64e.S @@ -2,7 +2,7 @@ /* * Copyright 2010 IBM Corp, Benjamin Herrenschmidt * - * Generic idle routine for Book3E processors + * Generic idle routine for 64 bits e500 processors */ #include @@ -16,8 +16,6 @@ #include /* 64-bit version only for now */ -#ifdef CONFIG_PPC64 - .macro BOOK3E_IDLE name loop _GLOBAL(\name) /* Save LR for later */ @@ -77,7 +75,7 @@ _GLOBAL(\name) .macro BOOK3E_IDLE_LOOP 1: - PPC_WAIT(0) + PPC_WAIT_v203 b 1b .endm @@ -98,6 +96,4 @@ epapr_ev_idle_start: BOOK3E_IDLE epapr_ev_idle EPAPR_EV_IDLE_LOOP -BOOK3E_IDLE book3e_idle BOOK3E_IDLE_LOOP - -#endif /* CONFIG_PPC64 */ +BOOK3E_IDLE e500_idle BOOK3E_IDLE_LOOP diff --git a/arch/powerpc/kernel/idle_e500.S b/arch/powerpc/kernel/idle_85xx.S similarity index 100% rename from arch/powerpc/kernel/idle_e500.S rename to arch/powerpc/kernel/idle_85xx.S diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c index 0e75cb03244a..f9db0a172401 100644 --- a/arch/powerpc/kernel/interrupt.c +++ b/arch/powerpc/kernel/interrupt.c @@ -431,16 +431,6 @@ again: if (unlikely(stack_store)) __hard_EE_RI_disable(); - /* - * Returning to a kernel context with local irqs disabled. - * Here, if EE was enabled in the interrupted context, enable - * it on return as well. A problem exists here where a soft - * masked interrupt may have cleared MSR[EE] and set HARD_DIS - * here, and it will still exist on return to the caller. This - * will be resolved by the masked interrupt firing again. - */ - if (regs->msr & MSR_EE) - local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS; #endif /* CONFIG_PPC64 */ } diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S index ce25b28cf418..904a5608cbe3 100644 --- a/arch/powerpc/kernel/interrupt_64.S +++ b/arch/powerpc/kernel/interrupt_64.S @@ -13,16 +13,6 @@ #include #include - .section ".toc","aw" -SYS_CALL_TABLE: - .tc sys_call_table[TC],sys_call_table - -#ifdef CONFIG_COMPAT -COMPAT_SYS_CALL_TABLE: - .tc compat_sys_call_table[TC],compat_sys_call_table -#endif - .previous - .align 7 .macro DEBUG_SRR_VALID srr @@ -67,16 +57,11 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name) std r0,GPR0(r1) std r10,GPR1(r1) std r2,GPR2(r1) - ld r2,PACATOC(r13) + LOAD_PACA_TOC() mfcr r12 li r11,0 - /* Can we avoid saving r3-r8 in common case? */ - std r3,GPR3(r1) - std r4,GPR4(r1) - std r5,GPR5(r1) - std r6,GPR6(r1) - std r7,GPR7(r1) - std r8,GPR8(r1) + /* Save syscall parameters in r3-r8 */ + SAVE_GPRS(3, 8, r1) /* Zero r9-r12, this should only be required when restoring all GPRs */ std r11,GPR9(r1) std r11,GPR10(r1) @@ -91,9 +76,12 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name) li r11,\trapnr std r11,_TRAP(r1) std r12,_CCR(r1) - addi r10,r1,STACK_FRAME_OVERHEAD - ld r11,exception_marker@toc(r2) - std r11,-16(r10) /* "regshere" marker */ + std r3,ORIG_GPR3(r1) + /* Calling convention has r3 = regs, r4 = orig r0 */ + addi r3,r1,STACK_FRAME_OVERHEAD + mr r4,r0 + LOAD_REG_IMMEDIATE(r11, STACK_FRAME_REGS_MARKER) + std r11,-16(r3) /* "regshere" marker */ BEGIN_FTR_SECTION HMT_MEDIUM @@ -108,8 +96,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) * but this is the best we can do. */ - /* Calling convention has r9 = orig r0, r10 = regs */ - mr r9,r0 bl system_call_exception .Lsyscall_vectored_\name\()_exit: @@ -148,17 +134,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) /* Could zero these as per ABI, but we may consider a stricter ABI * which preserves these if libc implementations can benefit, so * restore them for now until further measurement is done. */ - ld r0,GPR0(r1) - ld r4,GPR4(r1) - ld r5,GPR5(r1) - ld r6,GPR6(r1) - ld r7,GPR7(r1) - ld r8,GPR8(r1) + REST_GPR(0, r1) + REST_GPRS(4, 8, r1) /* Zero volatile regs that may contain sensitive kernel data */ - li r9,0 - li r10,0 - li r11,0 - li r12,0 + ZEROIZE_GPRS(9, 12) mtspr SPRN_XER,r0 /* @@ -181,7 +160,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) ld r5,_XER(r1) REST_NVGPRS(r1) - ld r0,GPR0(r1) + REST_GPR(0, r1) mtcr r2 mtctr r3 mtlr r4 @@ -195,7 +174,7 @@ syscall_vectored_\name\()_restart: _ASM_NOKPROBE_SYMBOL(syscall_vectored_\name\()_restart) GET_PACA(r13) ld r1,PACA_EXIT_SAVE_R1(r13) - ld r2,PACATOC(r13) + LOAD_PACA_TOC() ld r3,RESULT(r1) addi r4,r1,STACK_FRAME_OVERHEAD li r11,IRQS_ALL_DISABLED @@ -240,21 +219,16 @@ _ASM_NOKPROBE_SYMBOL(system_call_common) std r0,GPR0(r1) std r10,GPR1(r1) std r2,GPR2(r1) -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 START_BTB_FLUSH_SECTION BTB_FLUSH(r10) END_BTB_FLUSH_SECTION #endif - ld r2,PACATOC(r13) + LOAD_PACA_TOC() mfcr r12 li r11,0 - /* Can we avoid saving r3-r8 in common case? */ - std r3,GPR3(r1) - std r4,GPR4(r1) - std r5,GPR5(r1) - std r6,GPR6(r1) - std r7,GPR7(r1) - std r8,GPR8(r1) + /* Save syscall parameters in r3-r8 */ + SAVE_GPRS(3, 8, r1) /* Zero r9-r12, this should only be required when restoring all GPRs */ std r11,GPR9(r1) std r11,GPR10(r1) @@ -275,9 +249,12 @@ END_BTB_FLUSH_SECTION std r10,_LINK(r1) std r11,_TRAP(r1) std r12,_CCR(r1) - addi r10,r1,STACK_FRAME_OVERHEAD - ld r11,exception_marker@toc(r2) - std r11,-16(r10) /* "regshere" marker */ + std r3,ORIG_GPR3(r1) + /* Calling convention has r3 = regs, r4 = orig r0 */ + addi r3,r1,STACK_FRAME_OVERHEAD + mr r4,r0 + LOAD_REG_IMMEDIATE(r11, STACK_FRAME_REGS_MARKER) + std r11,-16(r3) /* "regshere" marker */ #ifdef CONFIG_PPC_BOOK3S li r11,1 @@ -298,8 +275,6 @@ END_BTB_FLUSH_SECTION wrteei 1 #endif - /* Calling convention has r9 = orig r0, r10 = regs */ - mr r9,r0 bl system_call_exception .Lsyscall_exit: @@ -343,16 +318,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS) cmpdi r3,0 bne .Lsyscall_restore_regs /* Zero volatile regs that may contain sensitive kernel data */ - li r0,0 - li r4,0 - li r5,0 - li r6,0 - li r7,0 - li r8,0 - li r9,0 - li r10,0 - li r11,0 - li r12,0 + ZEROIZE_GPR(0) + ZEROIZE_GPRS(4, 12) mtctr r0 mtspr SPRN_XER,r0 .Lsyscall_restore_regs_cont: @@ -378,7 +345,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) REST_NVGPRS(r1) mtctr r3 mtspr SPRN_XER,r4 - ld r0,GPR0(r1) + REST_GPR(0, r1) REST_GPRS(4, 12, r1) b .Lsyscall_restore_regs_cont .Lsyscall_rst_end: @@ -388,7 +355,7 @@ syscall_restart: _ASM_NOKPROBE_SYMBOL(syscall_restart) GET_PACA(r13) ld r1,PACA_EXIT_SAVE_R1(r13) - ld r2,PACATOC(r13) + LOAD_PACA_TOC() ld r3,RESULT(r1) addi r4,r1,STACK_FRAME_OVERHEAD li r11,IRQS_ALL_DISABLED @@ -535,7 +502,7 @@ interrupt_return_\srr\()_user_restart: _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_user_restart) GET_PACA(r13) ld r1,PACA_EXIT_SAVE_R1(r13) - ld r2,PACATOC(r13) + LOAD_PACA_TOC() addi r3,r1,STACK_FRAME_OVERHEAD li r11,IRQS_ALL_DISABLED stb r11,PACAIRQSOFTMASK(r13) @@ -559,15 +526,43 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_kernel) ld r11,SOFTE(r1) cmpwi r11,IRQS_ENABLED stb r11,PACAIRQSOFTMASK(r13) - bne 1f + beq .Linterrupt_return_\srr\()_soft_enabled + + /* + * Returning to soft-disabled context. + * Check if a MUST_HARD_MASK interrupt has become pending, in which + * case we need to disable MSR[EE] in the return context. + */ + ld r12,_MSR(r1) + andi. r10,r12,MSR_EE + beq .Lfast_kernel_interrupt_return_\srr\() // EE already disabled + lbz r11,PACAIRQHAPPENED(r13) + andi. r10,r11,PACA_IRQ_MUST_HARD_MASK + beq 1f // No HARD_MASK pending + + /* Must clear MSR_EE from _MSR */ +#ifdef CONFIG_PPC_BOOK3S + li r10,0 + /* Clear valid before changing _MSR */ + .ifc \srr,srr + stb r10,PACASRR_VALID(r13) + .else + stb r10,PACAHSRR_VALID(r13) + .endif +#endif + xori r12,r12,MSR_EE + std r12,_MSR(r1) + b .Lfast_kernel_interrupt_return_\srr\() + +.Linterrupt_return_\srr\()_soft_enabled: #ifdef CONFIG_PPC_BOOK3S lbz r11,PACAIRQHAPPENED(r13) andi. r11,r11,(~PACA_IRQ_HARD_DIS)@l bne- interrupt_return_\srr\()_kernel_restart #endif - li r11,0 - stb r11,PACAIRQHAPPENED(r13) # clear out possible HARD_DIS 1: + li r11,0 + stb r11,PACAIRQHAPPENED(r13) // clear the possible HARD_DIS .Lfast_kernel_interrupt_return_\srr\(): cmpdi cr1,r3,0 @@ -619,7 +614,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS) mtspr SPRN_XER,r5 /* - * Leaving a stale exception_marker on the stack can confuse + * Leaving a stale STACK_FRAME_REGS_MARKER on the stack can confuse * the reliable stack unwinder later on. Clear it. */ std r0,STACK_FRAME_OVERHEAD-16(r1) @@ -668,7 +663,7 @@ interrupt_return_\srr\()_kernel_restart: _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_kernel_restart) GET_PACA(r13) ld r1,PACA_EXIT_SAVE_R1(r13) - ld r2,PACATOC(r13) + LOAD_PACA_TOC() addi r3,r1,STACK_FRAME_OVERHEAD li r11,IRQS_ALL_DISABLED stb r11,PACAIRQSOFTMASK(r13) diff --git a/arch/powerpc/kernel/irq_64.c b/arch/powerpc/kernel/irq_64.c index 01645e03e9f0..eb2b380e52a0 100644 --- a/arch/powerpc/kernel/irq_64.c +++ b/arch/powerpc/kernel/irq_64.c @@ -68,6 +68,35 @@ int distribute_irqs = 1; +static inline void next_interrupt(struct pt_regs *regs) +{ + /* + * Softirq processing can enable/disable irqs, which will leave + * MSR[EE] enabled and the soft mask set to IRQS_DISABLED. Fix + * this up. + */ + if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) + hard_irq_disable(); + else + irq_soft_mask_set(IRQS_ALL_DISABLED); + + /* + * We are responding to the next interrupt, so interrupt-off + * latencies should be reset here. + */ + trace_hardirqs_on(); + trace_hardirqs_off(); +} + +static inline bool irq_happened_test_and_clear(u8 irq) +{ + if (local_paca->irq_happened & irq) { + local_paca->irq_happened &= ~irq; + return true; + } + return false; +} + void replay_soft_interrupts(void) { struct pt_regs regs; @@ -79,18 +108,25 @@ void replay_soft_interrupts(void) * recurse into this function. Don't keep any state across * interrupt handler calls which may change underneath us. * + * Softirqs can not be disabled over replay to stop this recursion + * because interrupts taken in idle code may require RCU softirq + * to run in the irq RCU tracking context. This is a hard problem + * to fix without changes to the softirq or idle layer. + * * We use local_paca rather than get_paca() to avoid all the * debug_smp_processor_id() business in this low level function. */ + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { + WARN_ON_ONCE(mfmsr() & MSR_EE); + WARN_ON(!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)); + } + ppc_save_regs(®s); regs.softe = IRQS_ENABLED; regs.msr |= MSR_EE; again: - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - WARN_ON_ONCE(mfmsr() & MSR_EE); - /* * Force the delivery of pending soft-disabled interrupts on PS3. * Any HV call will have this side effect. @@ -105,56 +141,47 @@ again: * This is a higher priority interrupt than the others, so * replay it first. */ - if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_HMI)) { - local_paca->irq_happened &= ~PACA_IRQ_HMI; + if (IS_ENABLED(CONFIG_PPC_BOOK3S) && + irq_happened_test_and_clear(PACA_IRQ_HMI)) { regs.trap = INTERRUPT_HMI; handle_hmi_exception(®s); - if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) - hard_irq_disable(); + next_interrupt(®s); } - if (local_paca->irq_happened & PACA_IRQ_DEC) { - local_paca->irq_happened &= ~PACA_IRQ_DEC; + if (irq_happened_test_and_clear(PACA_IRQ_DEC)) { regs.trap = INTERRUPT_DECREMENTER; timer_interrupt(®s); - if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) - hard_irq_disable(); + next_interrupt(®s); } - if (local_paca->irq_happened & PACA_IRQ_EE) { - local_paca->irq_happened &= ~PACA_IRQ_EE; + if (irq_happened_test_and_clear(PACA_IRQ_EE)) { regs.trap = INTERRUPT_EXTERNAL; do_IRQ(®s); - if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) - hard_irq_disable(); + next_interrupt(®s); } - if (IS_ENABLED(CONFIG_PPC_DOORBELL) && (local_paca->irq_happened & PACA_IRQ_DBELL)) { - local_paca->irq_happened &= ~PACA_IRQ_DBELL; + if (IS_ENABLED(CONFIG_PPC_DOORBELL) && + irq_happened_test_and_clear(PACA_IRQ_DBELL)) { regs.trap = INTERRUPT_DOORBELL; doorbell_exception(®s); - if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) - hard_irq_disable(); + next_interrupt(®s); } /* Book3E does not support soft-masking PMI interrupts */ - if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_PMI)) { - local_paca->irq_happened &= ~PACA_IRQ_PMI; + if (IS_ENABLED(CONFIG_PPC_BOOK3S) && + irq_happened_test_and_clear(PACA_IRQ_PMI)) { regs.trap = INTERRUPT_PERFMON; performance_monitor_exception(®s); - if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) - hard_irq_disable(); + next_interrupt(®s); } - if (local_paca->irq_happened & ~PACA_IRQ_HARD_DIS) { - /* - * We are responding to the next interrupt, so interrupt-off - * latencies should be reset here. - */ - trace_hardirqs_on(); - trace_hardirqs_off(); + /* + * Softirq processing can enable and disable interrupts, which can + * result in new irqs becoming pending. Must keep looping until we + * have cleared out all pending interrupts. + */ + if (local_paca->irq_happened & ~PACA_IRQ_HARD_DIS) goto again; - } } #if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_KUAP) @@ -270,10 +297,12 @@ happened: trace_hardirqs_off(); replay_soft_interrupts_irqrestore(); - local_paca->irq_happened = 0; trace_hardirqs_on(); irq_soft_mask_set(IRQS_ENABLED); + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + WARN_ON(local_paca->irq_happened != PACA_IRQ_HARD_DIS); + local_paca->irq_happened = 0; __hard_irq_enable(); preempt_enable(); } diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index a20deebf233f..1a1e9995dae3 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -47,7 +47,7 @@ static struct hard_trap_info { 0x0c00, 0x14 /* SIGCHLD */ }, /* system call */ #ifdef CONFIG_BOOKE_OR_40x { 0x2002, 0x05 /* SIGTRAP */ }, /* debug */ -#if defined(CONFIG_FSL_BOOKE) +#if defined(CONFIG_PPC_85xx) { 0x2010, 0x08 /* SIGFPE */ }, /* spe unavailable */ { 0x2020, 0x08 /* SIGFPE */ }, /* spe unavailable */ { 0x2030, 0x08 /* SIGFPE */ }, /* spe fp data */ @@ -57,7 +57,7 @@ static struct hard_trap_info { 0x2900, 0x08 /* SIGFPE */ }, /* apu unavailable */ { 0x3100, 0x0e /* SIGALRM */ }, /* fixed interval timer */ { 0x3200, 0x02 /* SIGINT */ }, /* watchdog */ -#else /* ! CONFIG_FSL_BOOKE */ +#else /* ! CONFIG_PPC_85xx */ { 0x1000, 0x0e /* SIGALRM */ }, /* prog interval timer */ { 0x1010, 0x0e /* SIGALRM */ }, /* fixed interval timer */ { 0x1020, 0x02 /* SIGINT */ }, /* watchdog */ @@ -208,7 +208,7 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p) for (reg = 14; reg < 32; reg++) PACK64(ptr, regs->gpr[reg]); -#ifdef CONFIG_FSL_BOOKE +#ifdef CONFIG_PPC_85xx #ifdef CONFIG_SPE for (reg = 0; reg < 32; reg++) PACK64(ptr, p->thread.evr[reg]); @@ -234,7 +234,7 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p) #define GDB_SIZEOF_REG sizeof(unsigned long) #define GDB_SIZEOF_REG_U32 sizeof(u32) -#ifdef CONFIG_FSL_BOOKE +#ifdef CONFIG_PPC_85xx #define GDB_SIZEOF_FLOAT_REG sizeof(unsigned long) #else #define GDB_SIZEOF_FLOAT_REG sizeof(u64) @@ -329,7 +329,7 @@ char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs) if (regno >= 32 && regno < 64) { /* FP registers 32 -> 63 */ -#if defined(CONFIG_FSL_BOOKE) && defined(CONFIG_SPE) +#if defined(CONFIG_PPC_85xx) && defined(CONFIG_SPE) if (current) memcpy(mem, ¤t->thread.evr[regno-32], dbg_reg_def[regno].size); @@ -355,7 +355,7 @@ int dbg_set_reg(int regno, void *mem, struct pt_regs *regs) if (regno >= 32 && regno < 64) { /* FP registers 32 -> 63 */ -#if defined(CONFIG_FSL_BOOKE) && defined(CONFIG_SPE) +#if defined(CONFIG_PPC_85xx) && defined(CONFIG_SPE) memcpy(¤t->thread.evr[regno-32], mem, dbg_reg_def[regno].size); #else diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 912d4f8a13be..bd7b1a035459 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -161,7 +161,13 @@ int arch_prepare_kprobe(struct kprobe *p) preempt_disable(); prev = get_kprobe(p->addr - 1); preempt_enable_no_resched(); - if (prev && ppc_inst_prefixed(ppc_inst_read(prev->ainsn.insn))) { + + /* + * When prev is a ftrace-based kprobe, we don't have an insn, and it + * doesn't probe for prefixed instruction. + */ + if (prev && !kprobe_ftrace(prev) && + ppc_inst_prefixed(ppc_inst_read(prev->ainsn.insn))) { printk("Cannot register a kprobe on the second word of prefixed instruction\n"); ret = -EINVAL; } diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index 6568823cf306..5b3c093611ba 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -455,7 +455,7 @@ static void __init kvm_check_ins(u32 *inst, u32 features) kvm_patch_ins_lwz(inst, magic_var(dsisr), inst_rt); break; -#ifdef CONFIG_PPC_BOOK3E_MMU +#ifdef CONFIG_PPC_E500 case KVM_INST_MFSPR(SPRN_MAS0): if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7) kvm_patch_ins_lwz(inst, magic_var(mas0), inst_rt); @@ -484,7 +484,7 @@ static void __init kvm_check_ins(u32 *inst, u32 features) if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7) kvm_patch_ins_lwz(inst, magic_var(mas7_3), inst_rt); break; -#endif /* CONFIG_PPC_BOOK3E_MMU */ +#endif /* CONFIG_PPC_E500 */ case KVM_INST_MFSPR(SPRN_SPRG4): #ifdef CONFIG_BOOKE @@ -557,7 +557,7 @@ static void __init kvm_check_ins(u32 *inst, u32 features) case KVM_INST_MTSPR(SPRN_DSISR): kvm_patch_ins_stw(inst, magic_var(dsisr), inst_rt); break; -#ifdef CONFIG_PPC_BOOK3E_MMU +#ifdef CONFIG_PPC_E500 case KVM_INST_MTSPR(SPRN_MAS0): if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7) kvm_patch_ins_stw(inst, magic_var(mas0), inst_rt); @@ -586,7 +586,7 @@ static void __init kvm_check_ins(u32 *inst, u32 features) if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7) kvm_patch_ins_stw(inst, magic_var(mas7_3), inst_rt); break; -#endif /* CONFIG_PPC_BOOK3E_MMU */ +#endif /* CONFIG_PPC_E500 */ case KVM_INST_MTSPR(SPRN_SPRG4): if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7) diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 5c58460b269a..f048c424c525 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -471,6 +471,8 @@ void __init find_legacy_serial_ports(void) } #endif + of_node_put(stdout); + DBG("legacy_serial_console = %d\n", legacy_serial_console); if (legacy_serial_console >= 0) setup_legacy_serial_console(legacy_serial_console); diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index fd6d8d3a548e..36184cada00b 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -286,7 +286,7 @@ kexec_flag: #ifdef CONFIG_KEXEC_CORE -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 /* * BOOK3E has no real MMU mode, so we have to setup the initial TLB * for a core to identity map v:0 to p:0. This current implementation @@ -354,7 +354,7 @@ _GLOBAL(kexec_smp_wait) * don't overwrite r3 here, it is live for kexec_wait above. */ real_mode: /* assume normal blr return */ -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 /* Create an identity mapping. */ b kexec_create_tlb #else @@ -413,7 +413,7 @@ _GLOBAL(kexec_sequence) lhz r25,PACAHWCPUID(r13) /* get our phys cpu from paca */ /* disable interrupts, we are overwriting kernel data next */ -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 wrteei 0 #else mfmsr r3 diff --git a/arch/powerpc/kernel/optprobes_head.S b/arch/powerpc/kernel/optprobes_head.S index 5c7f0b4b784b..cd4e7bc32609 100644 --- a/arch/powerpc/kernel/optprobes_head.S +++ b/arch/powerpc/kernel/optprobes_head.S @@ -73,7 +73,7 @@ optprobe_template_entry: * further below. */ #ifdef CONFIG_PPC64 - ld r2,PACATOC(r13) + LOAD_PACA_TOC() #endif .global optprobe_template_op_address diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index ba593fd60124..be8db402e963 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -16,7 +16,6 @@ #include #include #include -#include #include "setup.h" @@ -170,30 +169,6 @@ static struct slb_shadow * __init new_slb_shadow(int cpu, unsigned long limit) } #endif /* CONFIG_PPC_64S_HASH_MMU */ -#ifdef CONFIG_PPC_PSERIES -/** - * new_rtas_args() - Allocates rtas args - * @cpu: CPU number - * @limit: Memory limit for this allocation - * - * Allocates a struct rtas_args and return it's pointer, - * if not in Hypervisor mode - * - * Return: Pointer to allocated rtas_args - * NULL if CPU in Hypervisor Mode - */ -static struct rtas_args * __init new_rtas_args(int cpu, unsigned long limit) -{ - limit = min_t(unsigned long, limit, RTAS_INSTANTIATE_MAX); - - if (early_cpu_has_feature(CPU_FTR_HVMODE)) - return NULL; - - return alloc_paca_data(sizeof(struct rtas_args), L1_CACHE_BYTES, - limit, cpu); -} -#endif /* CONFIG_PPC_PSERIES */ - /* The Paca is an array with one entry per processor. Each contains an * lppaca, which contains the information shared between the * hypervisor and Linux. @@ -211,7 +186,7 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu) #ifdef CONFIG_PPC_PSERIES new_paca->lppaca_ptr = NULL; #endif -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 new_paca->kernel_pgd = swapper_pg_dir; #endif new_paca->lock_token = 0x8000; @@ -228,14 +203,10 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu) new_paca->slb_shadow_ptr = NULL; #endif -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 /* For now -- if we have threads this will be adjusted later */ new_paca->tcd_ptr = &new_paca->tcd; #endif - -#ifdef CONFIG_PPC_PSERIES - new_paca->rtas_args_reentrant = NULL; -#endif } /* Put the paca pointer into r13 and SPRG_PACA */ @@ -244,7 +215,7 @@ void setup_paca(struct paca_struct *new_paca) /* Setup r13 */ local_paca = new_paca; -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 /* On Book3E, initialize the TLB miss exception frames */ mtspr(SPRN_SPRG_TLB_EXFRAME, local_paca->extlb); #else @@ -307,9 +278,6 @@ void __init allocate_paca(int cpu) #endif #ifdef CONFIG_PPC_64S_HASH_MMU paca->slb_shadow_ptr = new_slb_shadow(cpu, limit); -#endif -#ifdef CONFIG_PPC_PSERIES - paca->rtas_args_reentrant = new_rtas_args(cpu, limit); #endif paca_struct_size += sizeof(struct paca_struct); } diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 31de91c8359c..d67cf79bf5d0 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -135,7 +135,7 @@ struct pci_controller *pcibios_alloc_controller(struct device_node *dev) list_add_tail(&phb->list_node, &hose_list); spin_unlock(&hose_spinlock); - phb->dn = dev; + phb->dn = of_node_get(dev); phb->is_dynamic = slab_is_available(); #ifdef CONFIG_PPC64 if (dev) { @@ -158,7 +158,7 @@ void pcibios_free_controller(struct pci_controller *phb) /* Clear bit of phb_bitmap to allow reuse of this PHB number. */ if (phb->global_number < MAX_PHBS) clear_bit(phb->global_number, phb_bitmap); - + of_node_put(phb->dn); list_del(&phb->list_node); spin_unlock(&hose_spinlock); diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index 7a35fc25a304..38561d6a2079 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -330,6 +330,7 @@ struct pci_dn *pci_add_device_node_info(struct pci_controller *hose, INIT_LIST_HEAD(&pdn->list); parent = of_get_parent(dn); pdn->parent = parent ? PCI_DN(parent) : NULL; + of_node_put(parent); if (pdn->parent) list_add_tail(&pdn->list, &pdn->parent->child_list); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 0fbda89cd1bb..37df0428e4fb 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -127,7 +127,7 @@ unsigned long notrace msr_check_and_set(unsigned long bits) newmsr |= MSR_VSX; if (oldmsr != newmsr) - mtmsr_isync(newmsr); + newmsr = mtmsr_isync_irqsafe(newmsr); return newmsr; } @@ -145,7 +145,7 @@ void notrace __msr_check_and_clear(unsigned long bits) newmsr &= ~MSR_VSX; if (oldmsr != newmsr) - mtmsr_isync(newmsr); + mtmsr_isync_irqsafe(newmsr); } EXPORT_SYMBOL(__msr_check_and_clear); diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index a730b951b64b..1eed87d954ba 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include @@ -137,7 +138,7 @@ static void __init move_device_tree(void) } /* - * ibm,pa-features is a per-cpu property that contains a string of + * ibm,pa/pi-features is a per-cpu property that contains a string of * attribute descriptors, each of which has a 2 byte header plus up * to 254 bytes worth of processor attribute bits. First header * byte specifies the number of bytes following the header. @@ -149,15 +150,17 @@ static void __init move_device_tree(void) * is supported/not supported. Note that the bit numbers are * big-endian to match the definition in PAPR. */ -static struct ibm_pa_feature { +struct ibm_feature { unsigned long cpu_features; /* CPU_FTR_xxx bit */ unsigned long mmu_features; /* MMU_FTR_xxx bit */ unsigned int cpu_user_ftrs; /* PPC_FEATURE_xxx bit */ unsigned int cpu_user_ftrs2; /* PPC_FEATURE2_xxx bit */ - unsigned char pabyte; /* byte number in ibm,pa-features */ + unsigned char pabyte; /* byte number in ibm,pa/pi-features */ unsigned char pabit; /* bit number (big-endian) */ unsigned char invert; /* if 1, pa bit set => clear feature */ -} ibm_pa_features[] __initdata = { +}; + +static struct ibm_feature ibm_pa_features[] __initdata = { { .pabyte = 0, .pabit = 0, .cpu_user_ftrs = PPC_FEATURE_HAS_MMU }, { .pabyte = 0, .pabit = 1, .cpu_user_ftrs = PPC_FEATURE_HAS_FPU }, { .pabyte = 0, .pabit = 3, .cpu_features = CPU_FTR_CTRL }, @@ -179,9 +182,19 @@ static struct ibm_pa_feature { { .pabyte = 64, .pabit = 0, .cpu_features = CPU_FTR_DAWR1 }, }; +/* + * ibm,pi-features property provides the support of processor specific + * options not described in ibm,pa-features. Right now use byte 0, bit 3 + * which indicates the occurrence of DSI interrupt when the paste operation + * on the suspended NX window. + */ +static struct ibm_feature ibm_pi_features[] __initdata = { + { .pabyte = 0, .pabit = 3, .mmu_features = MMU_FTR_NX_DSI }, +}; + static void __init scan_features(unsigned long node, const unsigned char *ftrs, unsigned long tablelen, - struct ibm_pa_feature *fp, + struct ibm_feature *fp, unsigned long ft_size) { unsigned long i, len, bit; @@ -218,17 +231,18 @@ static void __init scan_features(unsigned long node, const unsigned char *ftrs, } } -static void __init check_cpu_pa_features(unsigned long node) +static void __init check_cpu_features(unsigned long node, char *name, + struct ibm_feature *fp, + unsigned long size) { const unsigned char *pa_ftrs; int tablelen; - pa_ftrs = of_get_flat_dt_prop(node, "ibm,pa-features", &tablelen); + pa_ftrs = of_get_flat_dt_prop(node, name, &tablelen); if (pa_ftrs == NULL) return; - scan_features(node, pa_ftrs, tablelen, - ibm_pa_features, ARRAY_SIZE(ibm_pa_features)); + scan_features(node, pa_ftrs, tablelen, fp, size); } #ifdef CONFIG_PPC_64S_HASH_MMU @@ -376,11 +390,16 @@ static int __init early_init_dt_scan_cpus(unsigned long node, */ if (!dt_cpu_ftrs_in_use()) { prop = of_get_flat_dt_prop(node, "cpu-version", NULL); - if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000) + if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000) { identify_cpu(0, be32_to_cpup(prop)); + seq_buf_printf(&ppc_hw_desc, "0x%04x ", be32_to_cpup(prop)); + } check_cpu_feature_properties(node); - check_cpu_pa_features(node); + check_cpu_features(node, "ibm,pa-features", ibm_pa_features, + ARRAY_SIZE(ibm_pa_features)); + check_cpu_features(node, "ibm,pi-features", ibm_pi_features, + ARRAY_SIZE(ibm_pi_features)); } identical_pvr_fixup(node); @@ -696,6 +715,23 @@ static void __init tm_init(void) static void tm_init(void) { } #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ +static int __init +early_init_dt_scan_model(unsigned long node, const char *uname, + int depth, void *data) +{ + const char *prop; + + if (depth != 0) + return 0; + + prop = of_get_flat_dt_prop(node, "model", NULL); + if (prop) + seq_buf_printf(&ppc_hw_desc, "%s ", prop); + + /* break now */ + return 1; +} + #ifdef CONFIG_PPC64 static void __init save_fscr_to_task(void) { @@ -724,6 +760,8 @@ void __init early_init_devtree(void *params) if (!early_init_dt_verify(params)) panic("BUG: Failed verifying flat device tree, bad version?"); + of_scan_flat_dt(early_init_dt_scan_model, NULL); + #ifdef CONFIG_PPC_RTAS /* Some machines might need RTAS info for debugging, grab it now. */ of_scan_flat_dt(early_init_dt_scan_rtas, NULL); @@ -803,6 +841,9 @@ void __init early_init_devtree(void *params) dt_cpu_ftrs_scan(); + // We can now add the CPU name & PVR to the hardware description + seq_buf_printf(&ppc_hw_desc, "%s 0x%04lx ", cur_cpu_spec->cpu_name, mfspr(SPRN_PVR)); + /* Retrieve CPU related informations from the flat tree * (altivec support, boot CPU ID, ...) */ diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index a6669c40c1db..d464ba412084 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -96,12 +96,6 @@ static int of_workarounds __prombss; #define OF_WA_CLAIM 1 /* do phys/virt claim separately, then map */ #define OF_WA_LONGTRAIL 2 /* work around longtrail bugs */ -#define PROM_BUG() do { \ - prom_printf("kernel BUG at %s line 0x%x!\n", \ - __FILE__, __LINE__); \ - __builtin_trap(); \ -} while (0) - #ifdef DEBUG_PROM #define prom_debug(x...) prom_printf(x) #else diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh index dfa5f729f774..311890d71c4c 100644 --- a/arch/powerpc/kernel/prom_init_check.sh +++ b/arch/powerpc/kernel/prom_init_check.sh @@ -26,8 +26,7 @@ _end enter_prom $MEM_FUNCS reloc_offset __secondary_hold __secondary_hold_acknowledge __secondary_hold_spinloop __start logo_linux_clut224 btext_prepare_BAT reloc_got2 kernstart_addr memstart_addr linux_banner _stext -__prom_init_toc_start __prom_init_toc_end btext_setup_display TOC. -relocate" +btext_setup_display TOC. relocate" NM="$1" OBJ="$2" diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S index 232e4549defe..efd52f2e7033 100644 --- a/arch/powerpc/kernel/reloc_64.S +++ b/arch/powerpc/kernel/reloc_64.S @@ -27,8 +27,8 @@ _GLOBAL(relocate) add r9,r9,r12 /* r9 has runtime addr of .rela.dyn section */ ld r10,(p_st - 0b)(r12) add r10,r10,r12 /* r10 has runtime addr of _stext */ - ld r13,(p_sym - 0b)(r12) - add r13,r13,r12 /* r13 has runtime addr of .dynsym */ + ld r4,(p_sym - 0b)(r12) + add r4,r4,r12 /* r4 has runtime addr of .dynsym */ /* * Scan the dynamic section for the RELA, RELASZ and RELAENT entries. @@ -84,16 +84,16 @@ _GLOBAL(relocate) ld r0,16(r9) /* reloc->r_addend */ b .Lstore .Luaddr64: - srdi r14,r0,32 /* ELF64_R_SYM(reloc->r_info) */ + srdi r5,r0,32 /* ELF64_R_SYM(reloc->r_info) */ clrldi r0,r0,32 cmpdi r0,R_PPC64_UADDR64 bne .Lnext ld r6,0(r9) ld r0,16(r9) - mulli r14,r14,24 /* 24 == sizeof(elf64_sym) */ - add r14,r14,r13 /* elf64_sym[ELF64_R_SYM] */ - ld r14,8(r14) - add r0,r0,r14 + mulli r5,r5,24 /* 24 == sizeof(elf64_sym) */ + add r5,r5,r4 /* elf64_sym[ELF64_R_SYM] */ + ld r5,8(r5) + add r0,r0,r5 .Lstore: add r0,r0,r3 stdx r0,r7,r6 diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 693133972294..e847f9b1c5b9 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include @@ -43,7 +44,6 @@ #include #include #include -#include /* This is here deliberately so it's only used in this file */ void enter_rtas(unsigned long); @@ -464,6 +464,9 @@ void rtas_call_unlocked(struct rtas_args *args, int token, int nargs, int nret, va_end(list); } +static int ibm_open_errinjct_token; +static int ibm_errinjct_token; + int rtas_call(int token, int nargs, int nret, int *outputs, ...) { va_list list; @@ -476,6 +479,16 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...) if (!rtas.entry || token == RTAS_UNKNOWN_SERVICE) return -1; + if (token == ibm_open_errinjct_token || token == ibm_errinjct_token) { + /* + * It would be nicer to not discard the error value + * from security_locked_down(), but callers expect an + * RTAS status, not an errno. + */ + if (security_locked_down(LOCKDOWN_RTAS_ERROR_INJECTION)) + return -1; + } + if ((mfmsr() & (MSR_IR|MSR_DR)) != (MSR_IR|MSR_DR)) { WARN_ON_ONCE(1); return -1; @@ -932,59 +945,6 @@ void rtas_activate_firmware(void) pr_err("ibm,activate-firmware failed (%i)\n", fwrc); } -#ifdef CONFIG_PPC_PSERIES -/** - * rtas_call_reentrant() - Used for reentrant rtas calls - * @token: Token for desired reentrant RTAS call - * @nargs: Number of Input Parameters - * @nret: Number of Output Parameters - * @outputs: Array of outputs - * @...: Inputs for desired RTAS call - * - * According to LoPAR documentation, only "ibm,int-on", "ibm,int-off", - * "ibm,get-xive" and "ibm,set-xive" are currently reentrant. - * Reentrant calls need their own rtas_args buffer, so not using rtas.args, but - * PACA one instead. - * - * Return: -1 on error, - * First output value of RTAS call if (nret > 0), - * 0 otherwise, - */ -int rtas_call_reentrant(int token, int nargs, int nret, int *outputs, ...) -{ - va_list list; - struct rtas_args *args; - unsigned long flags; - int i, ret = 0; - - if (!rtas.entry || token == RTAS_UNKNOWN_SERVICE) - return -1; - - local_irq_save(flags); - preempt_disable(); - - /* We use the per-cpu (PACA) rtas args buffer */ - args = local_paca->rtas_args_reentrant; - - va_start(list, outputs); - va_rtas_call_unlocked(args, token, nargs, nret, list); - va_end(list); - - if (nret > 1 && outputs) - for (i = 0; i < nret - 1; ++i) - outputs[i] = be32_to_cpu(args->rets[i + 1]); - - if (nret > 0) - ret = be32_to_cpu(args->rets[0]); - - local_irq_restore(flags); - preempt_enable(); - - return ret; -} - -#endif /* CONFIG_PPC_PSERIES */ - /** * get_pseries_errorlog() - Find a specific pseries error log in an RTAS * extended event log. @@ -1227,6 +1187,14 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs) if (block_rtas_call(token, nargs, &args)) return -EINVAL; + if (token == ibm_open_errinjct_token || token == ibm_errinjct_token) { + int err; + + err = security_locked_down(LOCKDOWN_RTAS_ERROR_INJECTION); + if (err) + return err; + } + /* Need to handle ibm,suspend_me call specially */ if (token == rtas_token("ibm,suspend-me")) { @@ -1325,7 +1293,8 @@ void __init rtas_initialize(void) #ifdef CONFIG_RTAS_ERROR_LOGGING rtas_last_error_token = rtas_token("rtas-last-error"); #endif - + ibm_open_errinjct_token = rtas_token("ibm,open-errinjct"); + ibm_errinjct_token = rtas_token("ibm,errinjct"); rtas_syscall_filter_init(); } diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index d96fd14bd7c9..206475e3e0b4 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include @@ -34,7 +35,7 @@ static enum branch_cache_flush_type link_stack_flush_type = BRANCH_CACHE_FLUSH_N bool barrier_nospec_enabled; static bool no_nospec; static bool btb_flush_enabled; -#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_BOOK3S_64) +#if defined(CONFIG_PPC_E500) || defined(CONFIG_PPC_BOOK3S_64) static bool no_spectrev2; #endif @@ -121,7 +122,7 @@ static __init int security_feature_debugfs_init(void) device_initcall(security_feature_debugfs_init); #endif /* CONFIG_DEBUG_FS */ -#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_BOOK3S_64) +#if defined(CONFIG_PPC_E500) || defined(CONFIG_PPC_BOOK3S_64) static int __init handle_nospectre_v2(char *p) { no_spectrev2 = true; @@ -129,9 +130,9 @@ static int __init handle_nospectre_v2(char *p) return 0; } early_param("nospectre_v2", handle_nospectre_v2); -#endif /* CONFIG_PPC_FSL_BOOK3E || CONFIG_PPC_BOOK3S_64 */ +#endif /* CONFIG_PPC_E500 || CONFIG_PPC_BOOK3S_64 */ -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 void __init setup_spectre_v2(void) { if (no_spectrev2 || cpu_mitigations_off()) @@ -139,7 +140,7 @@ void __init setup_spectre_v2(void) else btb_flush_enabled = true; } -#endif /* CONFIG_PPC_FSL_BOOK3E */ +#endif /* CONFIG_PPC_E500 */ #ifdef CONFIG_PPC_BOOK3S_64 ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index dd98f43bd685..6d041993a45d 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -25,6 +26,7 @@ #include #include #include +#include #include #include #include @@ -588,6 +590,15 @@ static __init int add_pcspkr(void) device_initcall(add_pcspkr); #endif /* CONFIG_PCSPKR_PLATFORM */ +static char ppc_hw_desc_buf[128] __initdata; + +struct seq_buf ppc_hw_desc __initdata = { + .buffer = ppc_hw_desc_buf, + .size = sizeof(ppc_hw_desc_buf), + .len = 0, + .readpos = 0, +}; + static __init void probe_machine(void) { extern struct machdep_calls __machine_desc_start; @@ -628,7 +639,13 @@ static __init void probe_machine(void) for (;;); } - printk(KERN_INFO "Using %s machine description\n", ppc_md.name); + // Append the machine name to other info we've gathered + seq_buf_puts(&ppc_hw_desc, ppc_md.name); + + // Set the generic hardware description shown in oopses + dump_stack_set_arch_desc(ppc_hw_desc.buffer); + + pr_info("Hardware name: %s\n", ppc_hw_desc.buffer); } /* Match a class of boards, not a specific device configuration. */ diff --git a/arch/powerpc/kernel/setup.h b/arch/powerpc/kernel/setup.h index 93f22da12abe..7912bb50a7cb 100644 --- a/arch/powerpc/kernel/setup.h +++ b/arch/powerpc/kernel/setup.h @@ -23,7 +23,7 @@ void check_smt_enabled(void); static inline void check_smt_enabled(void) { } #endif -#if defined(CONFIG_PPC_BOOK3E) && defined(CONFIG_SMP) +#if defined(CONFIG_PPC_BOOK3E_64) && defined(CONFIG_SMP) void setup_tlb_core_data(void); #else static inline void setup_tlb_core_data(void) { } diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 813261789303..b761cc1a403c 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -207,7 +207,7 @@ void __init setup_power_save(void) ppc_md.power_save = ppc6xx_idle; #endif -#ifdef CONFIG_E500 +#ifdef CONFIG_PPC_E500 if (cpu_has_feature(CPU_FTR_CAN_DOZE) || cpu_has_feature(CPU_FTR_CAN_NAP)) ppc_md.power_save = e500_idle; diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 2b2d0b0fbb30..a0dee7354fe6 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -34,6 +34,7 @@ #include #include +#include #include #include #include @@ -86,7 +87,7 @@ struct ppc64_caches ppc64_caches = { }; EXPORT_SYMBOL_GPL(ppc64_caches); -#if defined(CONFIG_PPC_BOOK3E) && defined(CONFIG_SMP) +#if defined(CONFIG_PPC_BOOK3E_64) && defined(CONFIG_SMP) void __init setup_tlb_core_data(void) { int cpu; @@ -176,14 +177,26 @@ early_param("smt-enabled", early_smt_enabled); #endif /* CONFIG_SMP */ /** Fix up paca fields required for the boot cpu */ -static void __init fixup_boot_paca(void) +static void __init fixup_boot_paca(struct paca_struct *boot_paca) { /* The boot cpu is started */ - get_paca()->cpu_start = 1; + boot_paca->cpu_start = 1; +#ifdef CONFIG_PPC_BOOK3S_64 + /* + * Give the early boot machine check stack somewhere to use, use + * half of the init stack. This is a bit hacky but there should not be + * deep stack usage in early init so shouldn't overflow it or overwrite + * things. + */ + boot_paca->mc_emergency_sp = (void *)&init_thread_union + + (THREAD_SIZE/2); +#endif /* Allow percpu accesses to work until we setup percpu data */ - get_paca()->data_offset = 0; - /* Mark interrupts disabled in PACA */ - irq_soft_mask_set(IRQS_DISABLED); + boot_paca->data_offset = 0; + /* Mark interrupts soft and hard disabled in PACA */ + boot_paca->irq_soft_mask = IRQS_DISABLED; + boot_paca->irq_happened = PACA_IRQ_HARD_DIS; + WARN_ON(mfmsr() & MSR_EE); } static void __init configure_exceptions(void) @@ -350,11 +363,15 @@ void __init early_setup(unsigned long dt_ptr) * what CPU we are on. */ initialise_paca(&boot_paca, 0); - setup_paca(&boot_paca); - fixup_boot_paca(); + fixup_boot_paca(&boot_paca); + WARN_ON(local_paca != 0); + setup_paca(&boot_paca); /* install the paca into registers */ /* -------- printk is now safe to use ------- */ + if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && (mfmsr() & MSR_HV)) + enable_machine_check(); + /* Try new device tree based feature discovery ... */ if (!dt_cpu_ftrs_init(__va(dt_ptr))) /* Otherwise use the old style CPU table */ @@ -377,8 +394,8 @@ void __init early_setup(unsigned long dt_ptr) /* Poison paca_ptrs[0] again if it's not the boot cpu */ memset(&paca_ptrs[0], 0x88, sizeof(paca_ptrs[0])); } - setup_paca(paca_ptrs[boot_cpuid]); - fixup_boot_paca(); + fixup_boot_paca(paca_ptrs[boot_cpuid]); + setup_paca(paca_ptrs[boot_cpuid]); /* install the paca into registers */ /* * Configure exception handlers. This include setting up trampolines @@ -673,7 +690,7 @@ void __init initialize_cache_info(void) */ __init u64 ppc64_bolted_size(void) { -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 /* Freescale BookE bolts the entire linear mapping */ /* XXX: BookE ppc64_rma_limit setup seems to disagree? */ if (early_mmu_has_feature(MMU_FTR_TYPE_FSL_E)) @@ -723,7 +740,7 @@ void __init irqstack_early_init(void) } } -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 void __init exc_lvl_early_init(void) { unsigned int i; @@ -825,7 +842,7 @@ void __init setup_per_cpu_areas(void) /* * BookE and BookS radix are historical values and should be revisited. */ - if (IS_ENABLED(CONFIG_PPC_BOOK3E)) { + if (IS_ENABLED(CONFIG_PPC_BOOK3E_64)) { atom_size = SZ_1M; } else if (radix_enabled()) { atom_size = PAGE_SIZE; diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h index 618aeccdf691..a429c57ed433 100644 --- a/arch/powerpc/kernel/signal.h +++ b/arch/powerpc/kernel/signal.h @@ -196,9 +196,6 @@ extern int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, #else /* CONFIG_PPC64 */ -extern long sys_rt_sigreturn(void); -extern long sys_sigreturn(void); - static inline int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, struct task_struct *tsk) { diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 157a7403e3eb..c114c7f25645 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -43,7 +43,7 @@ #include #include #ifdef CONFIG_PPC64 -#include "ppc32.h" +#include #include #else #include diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 169703fead57..0da6e59161cd 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -708,7 +708,7 @@ static struct task_struct *current_set[NR_CPUS]; static void smp_store_cpu_info(int id) { per_cpu(cpu_pvr, id) = mfspr(SPRN_PVR); -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 per_cpu(next_tlbcam_idx, id) = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) - 1; #endif @@ -1257,7 +1257,12 @@ static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle) int __cpu_up(unsigned int cpu, struct task_struct *tidle) { - int rc, c; + const unsigned long boot_spin_ms = 5 * MSEC_PER_SEC; + const bool booting = system_state < SYSTEM_RUNNING; + const unsigned long hp_spin_ms = 1; + unsigned long deadline; + int rc; + const unsigned long spin_wait_ms = booting ? boot_spin_ms : hp_spin_ms; /* * Don't allow secondary threads to come online if inhibited @@ -1302,22 +1307,23 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle) } /* - * wait to see if the cpu made a callin (is actually up). - * use this value that I found through experimentation. - * -- Cort + * At boot time, simply spin on the callin word until the + * deadline passes. + * + * At run time, spin for an optimistic amount of time to avoid + * sleeping in the common case. */ - if (system_state < SYSTEM_RUNNING) - for (c = 50000; c && !cpu_callin_map[cpu]; c--) - udelay(100); -#ifdef CONFIG_HOTPLUG_CPU - else - /* - * CPUs can take much longer to come up in the - * hotplug case. Wait five seconds. - */ - for (c = 5000; c && !cpu_callin_map[cpu]; c--) - msleep(1); -#endif + deadline = jiffies + msecs_to_jiffies(spin_wait_ms); + spin_until_cond(cpu_callin_map[cpu] || time_is_before_jiffies(deadline)); + + if (!cpu_callin_map[cpu] && system_state >= SYSTEM_RUNNING) { + const unsigned long sleep_interval_us = 10 * USEC_PER_MSEC; + const unsigned long sleep_wait_ms = 100 * MSEC_PER_SEC; + + deadline = jiffies + msecs_to_jiffies(sleep_wait_ms); + while (!cpu_callin_map[cpu] && time_is_after_jiffies(deadline)) + fsleep(sleep_interval_us); + } if (!cpu_callin_map[cpu]) { printk(KERN_ERR "Processor %u is stuck.\n", cpu); diff --git a/arch/powerpc/kernel/swsusp_booke.S b/arch/powerpc/kernel/swsusp_85xx.S similarity index 100% rename from arch/powerpc/kernel/swsusp_booke.S rename to arch/powerpc/kernel/swsusp_85xx.S diff --git a/arch/powerpc/kernel/swsusp_asm64.S b/arch/powerpc/kernel/swsusp_asm64.S index 9f1903c7f540..f645652c2654 100644 --- a/arch/powerpc/kernel/swsusp_asm64.S +++ b/arch/powerpc/kernel/swsusp_asm64.S @@ -76,16 +76,10 @@ swsusp_save_area: .space SL_SIZE - .section ".toc","aw" -swsusp_save_area_ptr: - .tc swsusp_save_area[TC],swsusp_save_area -restore_pblist_ptr: - .tc restore_pblist[TC],restore_pblist - .section .text .align 5 _GLOBAL(swsusp_arch_suspend) - ld r11,swsusp_save_area_ptr@toc(r2) + LOAD_REG_ADDR(r11, swsusp_save_area) SAVE_SPECIAL(LR) SAVE_REGISTER(r1) SAVE_SPECIAL(CR) @@ -131,7 +125,7 @@ END_FW_FTR_SECTION_IFCLR(FW_FEATURE_LPAR) bl swsusp_save /* restore LR */ - ld r11,swsusp_save_area_ptr@toc(r2) + LOAD_REG_ADDR(r11, swsusp_save_area) RESTORE_SPECIAL(LR) addi r1,r1,128 @@ -145,7 +139,7 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) sync - ld r12,restore_pblist_ptr@toc(r2) + LOAD_REG_ADDR(r11, restore_pblist) ld r12,0(r12) cmpdi r12,0 @@ -187,7 +181,7 @@ nothing_to_copy: tlbia #endif - ld r11,swsusp_save_area_ptr@toc(r2) + LOAD_REG_ADDR(r11, swsusp_save_area) RESTORE_SPECIAL(CR) @@ -265,7 +259,7 @@ END_FW_FTR_SECTION_IFCLR(FW_FEATURE_LPAR) bl do_after_copyback addi r1,r1,128 - ld r11,swsusp_save_area_ptr@toc(r2) + LOAD_REG_ADDR(r11, swsusp_save_area) RESTORE_SPECIAL(LR) li r3, 0 diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index 16ff0399a257..dcc3c9fd4cfd 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -25,7 +25,6 @@ #include #include #include -#include #include #include #include @@ -48,72 +47,55 @@ #include #include -unsigned long compat_sys_mmap2(unsigned long addr, size_t len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long pgoff) -{ - /* This should remain 12 even if PAGE_SIZE changes */ - return sys_mmap(addr, len, prot, flags, fd, pgoff << 12); -} - -/* - * long long munging: - * The 32 bit ABI passes long longs in an odd even register pair. - * High and low parts are swapped depending on endian mode, - * so define a macro (similar to mips linux32) to handle that. - */ -#ifdef __LITTLE_ENDIAN__ -#define merge_64(low, high) ((u64)high << 32) | low -#else -#define merge_64(high, low) ((u64)high << 32) | low -#endif - -compat_ssize_t compat_sys_pread64(unsigned int fd, char __user *ubuf, compat_size_t count, - u32 reg6, u32 pos1, u32 pos2) +COMPAT_SYSCALL_DEFINE6(ppc_pread64, + unsigned int, fd, + char __user *, ubuf, compat_size_t, count, + u32, reg6, u32, pos1, u32, pos2) { return ksys_pread64(fd, ubuf, count, merge_64(pos1, pos2)); } -compat_ssize_t compat_sys_pwrite64(unsigned int fd, const char __user *ubuf, compat_size_t count, - u32 reg6, u32 pos1, u32 pos2) +COMPAT_SYSCALL_DEFINE6(ppc_pwrite64, + unsigned int, fd, + const char __user *, ubuf, compat_size_t, count, + u32, reg6, u32, pos1, u32, pos2) { return ksys_pwrite64(fd, ubuf, count, merge_64(pos1, pos2)); } -compat_ssize_t compat_sys_readahead(int fd, u32 r4, u32 offset1, u32 offset2, u32 count) +COMPAT_SYSCALL_DEFINE5(ppc_readahead, + int, fd, u32, r4, + u32, offset1, u32, offset2, u32, count) { return ksys_readahead(fd, merge_64(offset1, offset2), count); } -asmlinkage int compat_sys_truncate64(const char __user * path, u32 reg4, - unsigned long len1, unsigned long len2) +COMPAT_SYSCALL_DEFINE4(ppc_truncate64, + const char __user *, path, u32, reg4, + unsigned long, len1, unsigned long, len2) { return ksys_truncate(path, merge_64(len1, len2)); } -asmlinkage long compat_sys_fallocate(int fd, int mode, u32 offset1, u32 offset2, - u32 len1, u32 len2) -{ - return ksys_fallocate(fd, mode, ((loff_t)offset1 << 32) | offset2, - merge_64(len1, len2)); -} - -asmlinkage int compat_sys_ftruncate64(unsigned int fd, u32 reg4, unsigned long len1, - unsigned long len2) +COMPAT_SYSCALL_DEFINE4(ppc_ftruncate64, + unsigned int, fd, u32, reg4, + unsigned long, len1, unsigned long, len2) { return ksys_ftruncate(fd, merge_64(len1, len2)); } -long ppc32_fadvise64(int fd, u32 unused, u32 offset1, u32 offset2, - size_t len, int advice) +COMPAT_SYSCALL_DEFINE6(ppc32_fadvise64, + int, fd, u32, unused, u32, offset1, u32, offset2, + size_t, len, int, advice) { return ksys_fadvise64_64(fd, merge_64(offset1, offset2), len, advice); } -asmlinkage long compat_sys_sync_file_range2(int fd, unsigned int flags, - unsigned offset1, unsigned offset2, - unsigned nbytes1, unsigned nbytes2) +COMPAT_SYSCALL_DEFINE6(ppc_sync_file_range2, + int, fd, unsigned int, flags, + unsigned int, offset1, unsigned int, offset2, + unsigned int, nbytes1, unsigned int, nbytes2) { loff_t offset = merge_64(offset1, offset2); loff_t nbytes = merge_64(nbytes1, nbytes2); diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c index 81ace9e8b72b..18b9d325395f 100644 --- a/arch/powerpc/kernel/syscall.c +++ b/arch/powerpc/kernel/syscall.c @@ -12,12 +12,8 @@ #include -typedef long (*syscall_fn)(long, long, long, long, long, long); - /* Has to run notrace because it is entered not completely "reconciled" */ -notrace long system_call_exception(long r3, long r4, long r5, - long r6, long r7, long r8, - unsigned long r0, struct pt_regs *regs) +notrace long system_call_exception(struct pt_regs *regs, unsigned long r0) { long ret; syscall_fn f; @@ -25,7 +21,6 @@ notrace long system_call_exception(long r3, long r4, long r5, kuap_lock(); add_random_kstack_offset(); - regs->orig_gpr3 = r3; if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) BUG_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED); @@ -139,12 +134,6 @@ notrace long system_call_exception(long r3, long r4, long r5, r0 = do_syscall_trace_enter(regs); if (unlikely(r0 >= NR_syscalls)) return regs->gpr[3]; - r3 = regs->gpr[3]; - r4 = regs->gpr[4]; - r5 = regs->gpr[5]; - r6 = regs->gpr[6]; - r7 = regs->gpr[7]; - r8 = regs->gpr[8]; } else if (unlikely(r0 >= NR_syscalls)) { if (unlikely(trap_is_unsupported_scv(regs))) { @@ -158,21 +147,31 @@ notrace long system_call_exception(long r3, long r4, long r5, /* May be faster to do array_index_nospec? */ barrier_nospec(); +#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER + // No COMPAT if we have SYSCALL_WRAPPER, see Kconfig + f = (void *)sys_call_table[r0]; + ret = f(regs); +#else if (unlikely(is_compat_task())) { + unsigned long r3, r4, r5, r6, r7, r8; + f = (void *)compat_sys_call_table[r0]; - r3 &= 0x00000000ffffffffULL; - r4 &= 0x00000000ffffffffULL; - r5 &= 0x00000000ffffffffULL; - r6 &= 0x00000000ffffffffULL; - r7 &= 0x00000000ffffffffULL; - r8 &= 0x00000000ffffffffULL; + r3 = regs->gpr[3] & 0x00000000ffffffffULL; + r4 = regs->gpr[4] & 0x00000000ffffffffULL; + r5 = regs->gpr[5] & 0x00000000ffffffffULL; + r6 = regs->gpr[6] & 0x00000000ffffffffULL; + r7 = regs->gpr[7] & 0x00000000ffffffffULL; + r8 = regs->gpr[8] & 0x00000000ffffffffULL; + ret = f(r3, r4, r5, r6, r7, r8); } else { f = (void *)sys_call_table[r0]; - } - ret = f(r3, r4, r5, r6, r7, r8); + ret = f(regs->gpr[3], regs->gpr[4], regs->gpr[5], + regs->gpr[6], regs->gpr[7], regs->gpr[8]); + } +#endif /* * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(), diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c index fc999140bc27..68ebb23a5af4 100644 --- a/arch/powerpc/kernel/syscalls.c +++ b/arch/powerpc/kernel/syscalls.c @@ -36,9 +36,9 @@ #include #include -static inline long do_mmap2(unsigned long addr, size_t len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long off, int shift) +static long do_mmap2(unsigned long addr, size_t len, + unsigned long prot, unsigned long flags, + unsigned long fd, unsigned long off, int shift) { if (!arch_validate_prot(prot, addr)) return -EINVAL; @@ -56,6 +56,16 @@ SYSCALL_DEFINE6(mmap2, unsigned long, addr, size_t, len, return do_mmap2(addr, len, prot, flags, fd, pgoff, PAGE_SHIFT-12); } +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE6(mmap2, + unsigned long, addr, size_t, len, + unsigned long, prot, unsigned long, flags, + unsigned long, fd, unsigned long, off_4k) +{ + return do_mmap2(addr, len, prot, flags, fd, off_4k, PAGE_SHIFT-12); +} +#endif + SYSCALL_DEFINE6(mmap, unsigned long, addr, size_t, len, unsigned long, prot, unsigned long, flags, unsigned long, fd, off_t, offset) @@ -63,43 +73,39 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, size_t, len, return do_mmap2(addr, len, prot, flags, fd, offset, PAGE_SHIFT); } -#ifdef CONFIG_PPC32 -/* - * Due to some executables calling the wrong select we sometimes - * get wrong args. This determines how the args are being passed - * (a single ptr to them all args passed) then calls - * sys_select() with the appropriate args. -- Cort - */ -int -ppc_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct __kernel_old_timeval __user *tvp) -{ - if ((unsigned long)n >= 4096) - return sys_old_select((void __user *)n); - - return sys_select(n, inp, outp, exp, tvp); -} -#endif - #ifdef CONFIG_PPC64 -long ppc64_personality(unsigned long personality) +static long do_ppc64_personality(unsigned long personality) { long ret; if (personality(current->personality) == PER_LINUX32 && personality(personality) == PER_LINUX) personality = (personality & ~PER_MASK) | PER_LINUX32; - ret = sys_personality(personality); + ret = ksys_personality(personality); if (personality(ret) == PER_LINUX32) ret = (ret & ~PER_MASK) | PER_LINUX; return ret; } -#endif -long ppc_fadvise64_64(int fd, int advice, u32 offset_high, u32 offset_low, - u32 len_high, u32 len_low) +SYSCALL_DEFINE1(ppc64_personality, unsigned long, personality) { - return ksys_fadvise64_64(fd, (u64)offset_high << 32 | offset_low, - (u64)len_high << 32 | len_low, advice); + return do_ppc64_personality(personality); +} + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE1(ppc64_personality, unsigned long, personality) +{ + return do_ppc64_personality(personality); +} +#endif /* CONFIG_COMPAT */ +#endif /* CONFIG_PPC64 */ + +SYSCALL_DEFINE6(ppc_fadvise64_64, + int, fd, int, advice, u32, offset_high, u32, offset_low, + u32, len_high, u32, len_low) +{ + return ksys_fadvise64_64(fd, merge_64(offset_high, offset_low), + merge_64(len_high, len_low), advice); } SYSCALL_DEFINE0(switch_endian) diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 2600b4237292..2bca64f96164 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -110,7 +110,7 @@ 79 common settimeofday sys_settimeofday compat_sys_settimeofday 80 common getgroups sys_getgroups 81 common setgroups sys_setgroups -82 32 select ppc_select sys_ni_syscall +82 32 select sys_old_select compat_sys_old_select 82 64 select sys_ni_syscall 82 spu select sys_ni_syscall 83 common symlink sys_symlink @@ -178,9 +178,9 @@ 133 common fchdir sys_fchdir 134 common bdflush sys_ni_syscall 135 common sysfs sys_sysfs -136 32 personality sys_personality ppc64_personality -136 64 personality ppc64_personality -136 spu personality ppc64_personality +136 32 personality sys_personality compat_sys_ppc64_personality +136 64 personality sys_ppc64_personality +136 spu personality sys_ppc64_personality 137 common afs_syscall sys_ni_syscall 138 common setfsuid sys_setfsuid 139 common setfsgid sys_setfsgid @@ -228,8 +228,8 @@ 176 64 rt_sigtimedwait sys_rt_sigtimedwait 177 nospu rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo 178 nospu rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend -179 common pread64 sys_pread64 compat_sys_pread64 -180 common pwrite64 sys_pwrite64 compat_sys_pwrite64 +179 common pread64 sys_pread64 compat_sys_ppc_pread64 +180 common pwrite64 sys_pwrite64 compat_sys_ppc_pwrite64 181 common chown sys_chown 182 common getcwd sys_getcwd 183 common capget sys_capget @@ -242,10 +242,10 @@ 188 common putpmsg sys_ni_syscall 189 nospu vfork sys_vfork 190 common ugetrlimit sys_getrlimit compat_sys_getrlimit -191 common readahead sys_readahead compat_sys_readahead +191 common readahead sys_readahead compat_sys_ppc_readahead 192 32 mmap2 sys_mmap2 compat_sys_mmap2 -193 32 truncate64 sys_truncate64 compat_sys_truncate64 -194 32 ftruncate64 sys_ftruncate64 compat_sys_ftruncate64 +193 32 truncate64 sys_truncate64 compat_sys_ppc_truncate64 +194 32 ftruncate64 sys_ftruncate64 compat_sys_ppc_ftruncate64 195 32 stat64 sys_stat64 196 32 lstat64 sys_lstat64 197 32 fstat64 sys_fstat64 @@ -288,7 +288,7 @@ 230 common io_submit sys_io_submit compat_sys_io_submit 231 common io_cancel sys_io_cancel 232 nospu set_tid_address sys_set_tid_address -233 common fadvise64 sys_fadvise64 ppc32_fadvise64 +233 common fadvise64 sys_fadvise64 compat_sys_ppc32_fadvise64 234 nospu exit_group sys_exit_group 235 nospu lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie 236 common epoll_create sys_epoll_create @@ -323,7 +323,7 @@ 251 spu utimes sys_utimes 252 common statfs64 sys_statfs64 compat_sys_statfs64 253 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 -254 32 fadvise64_64 ppc_fadvise64_64 +254 32 fadvise64_64 sys_ppc_fadvise64_64 254 spu fadvise64_64 sys_ni_syscall 255 common rtas sys_rtas 256 32 sys_debug_setcontext sys_debug_setcontext sys_ni_syscall @@ -390,7 +390,7 @@ 305 common signalfd sys_signalfd compat_sys_signalfd 306 common timerfd_create sys_timerfd_create 307 common eventfd sys_eventfd -308 common sync_file_range2 sys_sync_file_range2 compat_sys_sync_file_range2 +308 common sync_file_range2 sys_sync_file_range2 compat_sys_ppc_sync_file_range2 309 nospu fallocate sys_fallocate compat_sys_fallocate 310 nospu subpage_prot sys_subpage_prot 311 32 timerfd_settime sys_timerfd_settime32 diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 3a10cda9c05e..ef9a61718940 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -228,7 +228,7 @@ static void __init sysfs_create_dscr_default(void) } #endif /* CONFIG_PPC64 */ -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 #define MAX_BIT 63 static u64 pw20_wt; @@ -907,7 +907,7 @@ static int register_cpu_online(unsigned int cpu) device_create_file(s, &dev_attr_tscr); #endif /* CONFIG_PPC64 */ -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 if (PVR_VER(cur_cpu_spec->pvr_value) == PVR_VER_E6500) { device_create_file(s, &dev_attr_pw20_state); device_create_file(s, &dev_attr_pw20_wait_time); @@ -1003,7 +1003,7 @@ static int unregister_cpu_online(unsigned int cpu) device_remove_file(s, &dev_attr_tscr); #endif /* CONFIG_PPC64 */ -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 if (PVR_VER(cur_cpu_spec->pvr_value) == PVR_VER_E6500) { device_remove_file(s, &dev_attr_pw20_state); device_remove_file(s, &dev_attr_pw20_wait_time); diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.c similarity index 52% rename from arch/powerpc/kernel/systbl.S rename to arch/powerpc/kernel/systbl.c index 6c1db3b6de2d..4305f2a2162f 100644 --- a/arch/powerpc/kernel/systbl.S +++ b/arch/powerpc/kernel/systbl.c @@ -10,32 +10,37 @@ * PPC64 updates by Dave Engebretsen (engebret@us.ibm.com) */ -#include +#include +#include +#include +#include -.section .rodata,"a" +#undef __SYSCALL_WITH_COMPAT +#define __SYSCALL_WITH_COMPAT(nr, entry, compat) __SYSCALL(nr, entry) -#ifdef CONFIG_PPC64 - .p2align 3 -#define __SYSCALL(nr, entry) .8byte entry +#undef __SYSCALL +#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER +#define __SYSCALL(nr, entry) [nr] = entry, #else - .p2align 2 -#define __SYSCALL(nr, entry) .long entry +/* + * Coerce syscall handlers with arbitrary parameters to common type + * requires cast to void* to avoid -Wcast-function-type. + */ +#define __SYSCALL(nr, entry) [nr] = (void *) entry, #endif -#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, native) -.globl sys_call_table -sys_call_table: +const syscall_fn sys_call_table[] = { #ifdef CONFIG_PPC64 #include #else #include #endif +}; #ifdef CONFIG_COMPAT #undef __SYSCALL_WITH_COMPAT #define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, compat) -.globl compat_sys_call_table -compat_sys_call_table: -#define compat_sys_sigsuspend sys_sigsuspend +const syscall_fn compat_sys_call_table[] = { #include -#endif +}; +#endif /* CONFIG_COMPAT */ diff --git a/arch/powerpc/kernel/systbl_chk.sh b/arch/powerpc/kernel/systbl_chk.sh deleted file mode 100644 index c7ac3ed657c4..000000000000 --- a/arch/powerpc/kernel/systbl_chk.sh +++ /dev/null @@ -1,30 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0-or-later -# -# Just process the CPP output from systbl_chk.c and complain -# if anything is out of order. -# -# Copyright © 2008 IBM Corporation -# - -awk 'BEGIN { num = -1; } # Ignore the beginning of the file - /^#/ { next; } - /^[ \t]*$/ { next; } - /^START_TABLE/ { num = 0; next; } - /^END_TABLE/ { - if (num != $2) { - printf "Error: NR_syscalls (%s) is not one more than the last syscall (%s)\n", - $2, num - 1; - exit(1); - } - num = -1; # Ignore the rest of the file - } - { - if (num == -1) next; - if (($1 != -1) && ($1 != num)) { - printf "Error: Syscall %s out of order (expected %s)\n", - $1, num; - exit(1); - }; - num++; - }' "$1" diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 587adcc12860..a2ab397065c6 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -178,92 +178,6 @@ static inline unsigned long read_spurr(unsigned long tb) return tb; } -#ifdef CONFIG_PPC_SPLPAR - -#include - -void (*dtl_consumer)(struct dtl_entry *, u64); - -/* - * Scan the dispatch trace log and count up the stolen time. - * Should be called with interrupts disabled. - */ -static u64 scan_dispatch_log(u64 stop_tb) -{ - u64 i = local_paca->dtl_ridx; - struct dtl_entry *dtl = local_paca->dtl_curr; - struct dtl_entry *dtl_end = local_paca->dispatch_log_end; - struct lppaca *vpa = local_paca->lppaca_ptr; - u64 tb_delta; - u64 stolen = 0; - u64 dtb; - - if (!dtl) - return 0; - - if (i == be64_to_cpu(vpa->dtl_idx)) - return 0; - while (i < be64_to_cpu(vpa->dtl_idx)) { - dtb = be64_to_cpu(dtl->timebase); - tb_delta = be32_to_cpu(dtl->enqueue_to_dispatch_time) + - be32_to_cpu(dtl->ready_to_enqueue_time); - barrier(); - if (i + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx)) { - /* buffer has overflowed */ - i = be64_to_cpu(vpa->dtl_idx) - N_DISPATCH_LOG; - dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG); - continue; - } - if (dtb > stop_tb) - break; - if (dtl_consumer) - dtl_consumer(dtl, i); - stolen += tb_delta; - ++i; - ++dtl; - if (dtl == dtl_end) - dtl = local_paca->dispatch_log; - } - local_paca->dtl_ridx = i; - local_paca->dtl_curr = dtl; - return stolen; -} - -/* - * Accumulate stolen time by scanning the dispatch trace log. - * Called on entry from user mode. - */ -void notrace accumulate_stolen_time(void) -{ - u64 sst, ust; - struct cpu_accounting_data *acct = &local_paca->accounting; - - sst = scan_dispatch_log(acct->starttime_user); - ust = scan_dispatch_log(acct->starttime); - acct->stime -= sst; - acct->utime -= ust; - acct->steal_time += ust + sst; -} - -static inline u64 calculate_stolen_time(u64 stop_tb) -{ - if (!firmware_has_feature(FW_FEATURE_SPLPAR)) - return 0; - - if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) - return scan_dispatch_log(stop_tb); - - return 0; -} - -#else /* CONFIG_PPC_SPLPAR */ -static inline u64 calculate_stolen_time(u64 stop_tb) -{ - return 0; -} - -#endif /* CONFIG_PPC_SPLPAR */ - /* * Account time for a transition between system, hard irq * or soft irq state. @@ -322,7 +236,11 @@ static unsigned long vtime_delta(struct cpu_accounting_data *acct, *stime_scaled = vtime_delta_scaled(acct, now, stime); - *steal_time = calculate_stolen_time(now); + if (IS_ENABLED(CONFIG_PPC_SPLPAR) && + firmware_has_feature(FW_FEATURE_SPLPAR)) + *steal_time = pseries_calculate_stolen_time(now); + else + *steal_time = 0; return stime; } @@ -614,22 +532,23 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt) return; } - /* - * Ensure a positive value is written to the decrementer, or - * else some CPUs will continue to take decrementer exceptions. - * When the PPC_WATCHDOG (decrementer based) is configured, - * keep this at most 31 bits, which is about 4 seconds on most - * systems, which gives the watchdog a chance of catching timer - * interrupt hard lockups. - */ - if (IS_ENABLED(CONFIG_PPC_WATCHDOG)) - set_dec(0x7fffffff); - else - set_dec(decrementer_max); - /* Conditionally hard-enable interrupts. */ - if (should_hard_irq_enable()) + if (should_hard_irq_enable()) { + /* + * Ensure a positive value is written to the decrementer, or + * else some CPUs will continue to take decrementer exceptions. + * When the PPC_WATCHDOG (decrementer based) is configured, + * keep this at most 31 bits, which is about 4 seconds on most + * systems, which gives the watchdog a chance of catching timer + * interrupt hard lockups. + */ + if (IS_ENABLED(CONFIG_PPC_WATCHDOG)) + set_dec(0x7fffffff); + else + set_dec(decrementer_max); + do_hard_irq_enable(); + } #if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC) if (atomic_read(&ppc_n_lost_interrupts) != 0) diff --git a/arch/powerpc/kernel/trace/ftrace_low.S b/arch/powerpc/kernel/trace/ftrace_low.S index 0bddf1fa6636..294d1e05958a 100644 --- a/arch/powerpc/kernel/trace/ftrace_low.S +++ b/arch/powerpc/kernel/trace/ftrace_low.S @@ -48,7 +48,7 @@ _GLOBAL(return_to_handler) * We might be called from a module. * Switch to our TOC to run inside the core kernel. */ - ld r2, PACATOC(r13) + LOAD_PACA_TOC() #else stwu r1, -16(r1) stw r3, 8(r1) diff --git a/arch/powerpc/kernel/trace/ftrace_mprofile.S b/arch/powerpc/kernel/trace/ftrace_mprofile.S index 4fa23e260cab..d031093bc436 100644 --- a/arch/powerpc/kernel/trace/ftrace_mprofile.S +++ b/arch/powerpc/kernel/trace/ftrace_mprofile.S @@ -83,10 +83,8 @@ #ifdef CONFIG_PPC64 /* Save callee's TOC in the ABI compliant location */ std r2, STK_GOT(r1) - ld r2,PACATOC(r13) /* get kernel TOC in r2 */ - - addis r3,r2,function_trace_op@toc@ha - addi r3,r3,function_trace_op@toc@l + LOAD_PACA_TOC() /* get kernel TOC in r2 */ + LOAD_REG_ADDR(r3, function_trace_op) ld r5,0(r3) #else lis r3,function_trace_op@ha diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index dadfcef5d6db..9bdd79aa51cf 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -68,6 +68,7 @@ #include #include #include +#include #if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC_CORE) int (*__debugger)(struct pt_regs *regs) __read_mostly; @@ -600,7 +601,7 @@ static inline int check_io_access(struct pt_regs *regs) #define inst_length(reason) (((reason) & REASON_PREFIXED) ? 8 : 4) -#if defined(CONFIG_E500) +#if defined(CONFIG_PPC_E500) int machine_check_e500mc(struct pt_regs *regs) { unsigned long mcsr = mfspr(SPRN_MCSR); @@ -850,6 +851,19 @@ bail: } #ifdef CONFIG_PPC_BOOK3S_64 +DEFINE_INTERRUPT_HANDLER_RAW(machine_check_early_boot) +{ + udbg_printf("Machine check (early boot)\n"); + udbg_printf("SRR0=0x%016lx SRR1=0x%016lx\n", regs->nip, regs->msr); + udbg_printf(" DAR=0x%016lx DSISR=0x%08lx\n", regs->dar, regs->dsisr); + udbg_printf(" LR=0x%016lx R1=0x%08lx\n", regs->link, regs->gpr[1]); + udbg_printf("------\n"); + die("Machine check (early boot)", regs, SIGBUS); + for (;;) + ; + return 0; +} + DEFINE_INTERRUPT_HANDLER_ASYNC(machine_check_exception_async) { __machine_check_exception(regs); @@ -2085,7 +2099,7 @@ DEFINE_INTERRUPT_HANDLER(altivec_assist_exception) } #endif /* CONFIG_ALTIVEC */ -#ifdef CONFIG_FSL_BOOKE +#ifdef CONFIG_PPC_85xx DEFINE_INTERRUPT_HANDLER(CacheLockingException) { unsigned long error_code = regs->dsisr; @@ -2098,12 +2112,11 @@ DEFINE_INTERRUPT_HANDLER(CacheLockingException) _exception(SIGILL, regs, ILL_PRVOPC, regs->nip); return; } -#endif /* CONFIG_FSL_BOOKE */ +#endif /* CONFIG_PPC_85xx */ #ifdef CONFIG_SPE DEFINE_INTERRUPT_HANDLER(SPEFloatingPointException) { - extern int do_spe_mathemu(struct pt_regs *regs); unsigned long spefscr; int fpexc_mode; int code = FPE_FLTUNK; @@ -2153,7 +2166,6 @@ DEFINE_INTERRUPT_HANDLER(SPEFloatingPointException) DEFINE_INTERRUPT_HANDLER(SPEFloatingPointRoundException) { - extern int speround_handler(struct pt_regs *regs); int err; interrupt_cond_local_irq_enable(regs); diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c index b1544b2f6321..92b3fc258d11 100644 --- a/arch/powerpc/kernel/udbg.c +++ b/arch/powerpc/kernel/udbg.c @@ -67,6 +67,8 @@ void __init udbg_early_init(void) udbg_init_debug_opal_raw(); #elif defined(CONFIG_PPC_EARLY_DEBUG_OPAL_HVSI) udbg_init_debug_opal_hvsi(); +#elif defined(CONFIG_PPC_EARLY_DEBUG_16550) + udbg_init_debug_16550(); #endif #ifdef CONFIG_PPC_EARLY_DEBUG diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c index d3942de254c6..74ddf836f7a2 100644 --- a/arch/powerpc/kernel/udbg_16550.c +++ b/arch/powerpc/kernel/udbg_16550.c @@ -8,6 +8,7 @@ #include #include #include +#include extern u8 real_readb(volatile u8 __iomem *addr); extern void real_writeb(u8 data, volatile u8 __iomem *addr); @@ -297,41 +298,34 @@ void __init udbg_init_40x_realmode(void) #endif /* CONFIG_PPC_EARLY_DEBUG_40x */ -#ifdef CONFIG_PPC_EARLY_DEBUG_MICROWATT +#ifdef CONFIG_PPC_EARLY_DEBUG_16550 -#define UDBG_UART_MW_ADDR ((void __iomem *)0xc0002000) +static void __iomem *udbg_uart_early_addr; -static u8 udbg_uart_in_isa300_rm(unsigned int reg) +void __init udbg_init_debug_16550(void) { - uint64_t msr = mfmsr(); - uint8_t c; - - mtmsr(msr & ~(MSR_EE|MSR_DR)); - isync(); - eieio(); - c = __raw_rm_readb(UDBG_UART_MW_ADDR + (reg << 2)); - mtmsr(msr); - isync(); - return c; + udbg_uart_early_addr = early_ioremap(CONFIG_PPC_EARLY_DEBUG_16550_PHYSADDR, 0x1000); + udbg_uart_init_mmio(udbg_uart_early_addr, CONFIG_PPC_EARLY_DEBUG_16550_STRIDE); } -static void udbg_uart_out_isa300_rm(unsigned int reg, u8 val) +static int __init udbg_init_debug_16550_ioremap(void) { - uint64_t msr = mfmsr(); + void __iomem *addr; - mtmsr(msr & ~(MSR_EE|MSR_DR)); - isync(); - eieio(); - __raw_rm_writeb(val, UDBG_UART_MW_ADDR + (reg << 2)); - mtmsr(msr); - isync(); + if (!udbg_uart_early_addr) + return 0; + + addr = ioremap(CONFIG_PPC_EARLY_DEBUG_16550_PHYSADDR, 0x1000); + if (WARN_ON(!addr)) + return -ENOMEM; + + udbg_uart_init_mmio(addr, CONFIG_PPC_EARLY_DEBUG_16550_STRIDE); + early_iounmap(udbg_uart_early_addr, 0x1000); + udbg_uart_early_addr = NULL; + + return 0; } -void __init udbg_init_debug_microwatt(void) -{ - udbg_uart_in = udbg_uart_in_isa300_rm; - udbg_uart_out = udbg_uart_out_isa300_rm; - udbg_use_uart(); -} +early_initcall(udbg_init_debug_16550_ioremap); -#endif /* CONFIG_PPC_EARLY_DEBUG_MICROWATT */ +#endif /* CONFIG_PPC_EARLY_DEBUG_16550 */ diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 0da287544054..e1f36fd61db3 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -39,6 +39,8 @@ extern char vdso32_start, vdso32_end; extern char vdso64_start, vdso64_end; +long sys_ni_syscall(void); + /* * The vdso data page (aka. systemcfg for old ppc64 fans) is here. * Once the early boot kernel code no longer needs to muck around @@ -200,28 +202,19 @@ static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_int if (is_32bit_task()) { vdso_spec = &vdso32_spec; vdso_size = &vdso32_end - &vdso32_start; - vdso_base = VDSO32_MBASE; } else { vdso_spec = &vdso64_spec; vdso_size = &vdso64_end - &vdso64_start; - /* - * On 64bit we don't have a preferred map address. This - * allows get_unmapped_area to find an area near other mmaps - * and most likely share a SLB entry. - */ - vdso_base = 0; } mappings_size = vdso_size + vvar_size; mappings_size += (VDSO_ALIGNMENT - 1) & PAGE_MASK; /* - * pick a base address for the vDSO in process space. We try to put it - * at vdso_base which is the "natural" base for it, but we might fail - * and end up putting it elsewhere. + * Pick a base address for the vDSO in process space. * Add enough to the size so that the result can be aligned. */ - vdso_base = get_unmapped_area(NULL, vdso_base, mappings_size, 0, 0); + vdso_base = get_unmapped_area(NULL, 0, mappings_size, 0, 0); if (IS_ERR_VALUE(vdso_base)) return vdso_base; @@ -313,10 +306,10 @@ static void __init vdso_setup_syscall_map(void) unsigned int i; for (i = 0; i < NR_syscalls; i++) { - if (sys_call_table[i] != (unsigned long)&sys_ni_syscall) + if (sys_call_table[i] != (void *)&sys_ni_syscall) vdso_data->syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f); if (IS_ENABLED(CONFIG_COMPAT) && - compat_sys_call_table[i] != (unsigned long)&sys_ni_syscall) + compat_sys_call_table[i] != (void *)&sys_ni_syscall) vdso_data->compat_syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f); } } diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile index 096b0bf1335f..a2e7b0ce5b19 100644 --- a/arch/powerpc/kernel/vdso/Makefile +++ b/arch/powerpc/kernel/vdso/Makefile @@ -92,13 +92,13 @@ include/generated/vdso64-offsets.h: $(obj)/vdso64.so.dbg FORCE # actual build commands quiet_cmd_vdso32ld_and_check = VDSO32L $@ - cmd_vdso32ld_and_check = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) ; $(cmd_vdso_check) + cmd_vdso32ld_and_check = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) -z noexecstack ; $(cmd_vdso_check) quiet_cmd_vdso32as = VDSO32A $@ cmd_vdso32as = $(VDSOCC) $(a_flags) $(CC32FLAGS) $(AS32FLAGS) -c -o $@ $< quiet_cmd_vdso32cc = VDSO32C $@ cmd_vdso32cc = $(VDSOCC) $(c_flags) $(CC32FLAGS) -c -o $@ $< quiet_cmd_vdso64ld_and_check = VDSO64L $@ - cmd_vdso64ld_and_check = $(VDSOCC) $(c_flags) $(CC64FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) ; $(cmd_vdso_check) + cmd_vdso64ld_and_check = $(VDSOCC) $(c_flags) $(CC64FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) -z noexecstack ; $(cmd_vdso_check) quiet_cmd_vdso64as = VDSO64A $@ cmd_vdso64as = $(VDSOCC) $(a_flags) $(CC64FLAGS) $(AS64FLAGS) -c -o $@ $< diff --git a/arch/powerpc/kernel/vdso/vdso32.lds.S b/arch/powerpc/kernel/vdso/vdso32.lds.S index e0d19d74455f..bc0be274a9ac 100644 --- a/arch/powerpc/kernel/vdso/vdso32.lds.S +++ b/arch/powerpc/kernel/vdso/vdso32.lds.S @@ -78,7 +78,6 @@ SECTIONS __end = .; PROVIDE(end = .); - STABS_DEBUG DWARF_DEBUG ELF_DETAILS diff --git a/arch/powerpc/kernel/vdso/vdso64.lds.S b/arch/powerpc/kernel/vdso/vdso64.lds.S index 1a4a7bc4c815..744ae5363e6c 100644 --- a/arch/powerpc/kernel/vdso/vdso64.lds.S +++ b/arch/powerpc/kernel/vdso/vdso64.lds.S @@ -76,7 +76,6 @@ SECTIONS _end = .; PROVIDE(end = .); - STABS_DEBUG DWARF_DEBUG ELF_DETAILS diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S index 5cc24d8cce94..5cf64740edb8 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -155,8 +155,8 @@ _GLOBAL(load_up_vsx) * usage of floating-point registers. These routines must be called * with preempt disabled. */ -#ifdef CONFIG_PPC32 .data +#ifdef CONFIG_PPC32 fpzero: .long 0 fpone: @@ -169,18 +169,17 @@ fphalf: lfs fr,name@l(r11) #else - .section ".toc","aw" fpzero: - .tc FD_0_0[TC],0 + .quad 0 fpone: - .tc FD_3ff00000_0[TC],0x3ff0000000000000 /* 1.0 */ + .quad 0x3ff0000000000000 /* 1.0 */ fphalf: - .tc FD_3fe00000_0[TC],0x3fe0000000000000 /* 0.5 */ + .quad 0x3fe0000000000000 /* 0.5 */ -#define LDCONST(fr, name) \ - lfd fr,name@toc(r2) +#define LDCONST(fr, name) \ + addis r11,r2,name@toc@ha; \ + lfd fr,name@toc@l(r11) #endif - .text /* * Internal routine to enable floating point and set FPSCR to 0. diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index fe22d940412f..7786e3ac7611 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -32,6 +32,10 @@ #define STRICT_ALIGN_SIZE (1 << CONFIG_DATA_SHIFT) +#if STRICT_ALIGN_SIZE < PAGE_SIZE +#error "CONFIG_DATA_SHIFT must be >= PAGE_SHIFT" +#endif + ENTRY(_stext) PHDRS { @@ -67,7 +71,7 @@ SECTIONS .head.text : AT(ADDR(.head.text) - LOAD_OFFSET) { #ifdef CONFIG_PPC64 KEEP(*(.head.text.first_256B)); -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 #else KEEP(*(.head.text.real_vectors)); *(.head.text.real_trampolines); @@ -122,14 +126,6 @@ SECTIONS *(.sfpr); MEM_KEEP(init.text) MEM_KEEP(exit.text) - -#ifdef CONFIG_PPC32 - *(.got1) - __got2_start = .; - *(.got2) - __got2_end = .; -#endif /* CONFIG_PPC32 */ - } :text . = ALIGN(PAGE_SIZE); @@ -139,15 +135,57 @@ SECTIONS /* Read-only data */ RO_DATA(PAGE_SIZE) -#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC32 + .sdata2 : AT(ADDR(.sdata2) - LOAD_OFFSET) { + *(.sdata2) + } +#endif + + .data.rel.ro : AT(ADDR(.data.rel.ro) - LOAD_OFFSET) { + *(.data.rel.ro*) + } + + .branch_lt : AT(ADDR(.branch_lt) - LOAD_OFFSET) { + *(.branch_lt) + } + +#ifdef CONFIG_PPC32 + .got1 : AT(ADDR(.got1) - LOAD_OFFSET) { + *(.got1) + } + .got2 : AT(ADDR(.got2) - LOAD_OFFSET) { + __got2_start = .; + *(.got2) + __got2_end = .; + } + .got : AT(ADDR(.got) - LOAD_OFFSET) { + *(.got) + *(.got.plt) + } + .plt : AT(ADDR(.plt) - LOAD_OFFSET) { + /* XXX: is .plt (and .got.plt) required? */ + *(.plt) + } + +#else /* CONFIG_PPC32 */ + .toc1 : AT(ADDR(.toc1) - LOAD_OFFSET) { + *(.toc1) + } + + .got : AT(ADDR(.got) - LOAD_OFFSET) ALIGN(256) { + *(.got .toc) + } + SOFT_MASK_TABLE(8) RESTART_TABLE(8) +#ifdef CONFIG_PPC64_ELF_ABI_V1 .opd : AT(ADDR(.opd) - LOAD_OFFSET) { __start_opd = .; KEEP(*(.opd)) __end_opd = .; } +#endif . = ALIGN(8); __stf_entry_barrier_fixup : AT(ADDR(__stf_entry_barrier_fixup) - LOAD_OFFSET) { @@ -190,7 +228,7 @@ SECTIONS *(__rfi_flush_fixup) __stop___rfi_flush_fixup = .; } -#endif /* CONFIG_PPC64 */ +#endif /* CONFIG_PPC32 */ #ifdef CONFIG_PPC_BARRIER_NOSPEC . = ALIGN(8); @@ -201,7 +239,7 @@ SECTIONS } #endif /* CONFIG_PPC_BARRIER_NOSPEC */ -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 . = ALIGN(8); __spec_btb_flush_fixup : AT(ADDR(__spec_btb_flush_fixup) - LOAD_OFFSET) { __start__btb_flush_fixup = .; @@ -210,12 +248,17 @@ SECTIONS } #endif + /* + * Various code relies on __init_begin being at the strict RWX boundary. + */ + . = ALIGN(STRICT_ALIGN_SIZE); + __srwx_boundary = .; + __end_rodata = .; + __init_begin = .; + /* * Init sections discarded at runtime */ - . = ALIGN(STRICT_ALIGN_SIZE); - __init_begin = .; - . = ALIGN(PAGE_SIZE); .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) { _sinittext = .; INIT_TEXT @@ -317,34 +360,13 @@ SECTIONS . = ALIGN(PAGE_SIZE); _sdata = .; + .data : AT(ADDR(.data) - LOAD_OFFSET) { + DATA_DATA + *(.data.rel*) #ifdef CONFIG_PPC32 - .data : AT(ADDR(.data) - LOAD_OFFSET) { - DATA_DATA - *(.data.rel*) *(SDATA_MAIN) - *(.sdata2) - *(.got.plt) *(.got) - *(.plt) - *(.branch_lt) - } -#else - .data : AT(ADDR(.data) - LOAD_OFFSET) { - DATA_DATA - *(.data.rel*) - *(.toc1) - *(.branch_lt) - } - - .got : AT(ADDR(.got) - LOAD_OFFSET) ALIGN(256) { - *(.got) -#ifndef CONFIG_RELOCATABLE - __prom_init_toc_start = .; - arch/powerpc/kernel/prom_init.o*(.toc) - __prom_init_toc_end = .; #endif - *(.toc) } -#endif /* The initial task and kernel stack */ INIT_TASK_DATA_SECTION(THREAD_ALIGN) @@ -382,7 +404,6 @@ SECTIONS _end = . ; PROVIDE32 (end = .); - STABS_DEBUG DWARF_DEBUG ELF_DETAILS diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c index cf84bfe9e27e..de64c7962991 100644 --- a/arch/powerpc/kexec/core.c +++ b/arch/powerpc/kexec/core.c @@ -136,7 +136,7 @@ void __init reserve_crashkernel(void) #ifdef CONFIG_PPC64 /* * On the LPAR platform place the crash kernel to mid of - * RMA size (512MB or more) to ensure the crash kernel + * RMA size (max. of 512MB) to ensure the crash kernel * gets enough space to place itself and some stack to be * in the first segment. At the same time normal kernel * also get enough space to allocate memory for essential @@ -144,9 +144,9 @@ void __init reserve_crashkernel(void) * kernel starts at 128MB offset on other platforms. */ if (firmware_has_feature(FW_FEATURE_LPAR)) - crashk_res.start = ppc64_rma_size / 2; + crashk_res.start = min_t(u64, ppc64_rma_size / 2, SZ_512M); else - crashk_res.start = min(0x8000000ULL, (ppc64_rma_size / 2)); + crashk_res.start = min_t(u64, ppc64_rma_size / 2, SZ_128M); #else crashk_res.start = KDUMP_KERNELBASE; #endif diff --git a/arch/powerpc/kexec/core_32.c b/arch/powerpc/kexec/core_32.c index b50aed48d09d..c95f96850c9e 100644 --- a/arch/powerpc/kexec/core_32.c +++ b/arch/powerpc/kexec/core_32.c @@ -55,7 +55,7 @@ void default_machine_kexec(struct kimage *image) reboot_code_buffer + KEXEC_CONTROL_PAGE_SIZE); printk(KERN_INFO "Bye!\n"); - if (!IS_ENABLED(CONFIG_FSL_BOOKE) && !IS_ENABLED(CONFIG_44x)) + if (!IS_ENABLED(CONFIG_PPC_85xx) && !IS_ENABLED(CONFIG_44x)) relocate_new_kernel(page_list, reboot_code_buffer_phys, image->start); /* now call it */ diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c index c2bea9db1c1e..a79e28c91e2b 100644 --- a/arch/powerpc/kexec/core_64.c +++ b/arch/powerpc/kexec/core_64.c @@ -360,7 +360,7 @@ void default_machine_kexec(struct kimage *image) * the RMA. On BookE there is no real MMU off mode, so we have to * keep it enabled as well (but then we have bolted TLB entries). */ -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 copy_with_mmu_off = false; #else copy_with_mmu_off = radix_enabled() || diff --git a/arch/powerpc/kexec/relocate_32.S b/arch/powerpc/kexec/relocate_32.S index cf6e52bdf8d8..d9f0dd9b34ff 100644 --- a/arch/powerpc/kexec/relocate_32.S +++ b/arch/powerpc/kexec/relocate_32.S @@ -25,14 +25,14 @@ relocate_new_kernel: /* r4 = reboot_code_buffer */ /* r5 = start_address */ -#ifdef CONFIG_FSL_BOOKE +#ifdef CONFIG_PPC_85xx mr r29, r3 mr r30, r4 mr r31, r5 #define ENTRY_MAPPING_KEXEC_SETUP -#include +#include #undef ENTRY_MAPPING_KEXEC_SETUP mr r3, r29 diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index dcb398d5e009..61cdd782d3c5 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -189,7 +189,7 @@ config KVM_EXIT_TIMING config KVM_E500V2 bool "KVM support for PowerPC E500v2 processors" - depends on E500 && !PPC_E500MC + depends on PPC_E500 && !PPC_E500MC select KVM select KVM_MMIO select MMU_NOTIFIER @@ -220,7 +220,7 @@ config KVM_E500MC config KVM_MPIC bool "KVM in-kernel MPIC emulation" - depends on KVM && E500 + depends on KVM && PPC_E500 select HAVE_KVM_IRQCHIP select HAVE_KVM_IRQFD select HAVE_KVM_IRQ_ROUTING diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S index e43704547a1e..6c2b1d17cb63 100644 --- a/arch/powerpc/kvm/book3s_64_entry.S +++ b/arch/powerpc/kvm/book3s_64_entry.S @@ -315,7 +315,7 @@ kvmppc_p9_exit_interrupt: reg = reg + 1 .endr - ld r2,PACATOC(r13) + LOAD_PACA_TOC() mflr r4 std r4,VCPU_LR(r3) diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 57d0835e56fd..6ba68dd6190b 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -249,6 +249,7 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) /* * We use the vcpu_load/put functions to measure stolen time. + * * Stolen time is counted as time when either the vcpu is able to * run as part of a virtual core, but the task running the vcore * is preempted or sleeping, or when the vcpu needs something done @@ -278,6 +279,12 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) * lock. The stolen times are measured in units of timebase ticks. * (Note that the != TB_NIL checks below are purely defensive; * they should never fail.) + * + * The POWER9 path is simpler, one vcpu per virtual core so the + * former case does not exist. If a vcpu is preempted when it is + * BUSY_IN_HOST and not ceded or otherwise blocked, then accumulate + * the stolen cycles in busy_stolen. RUNNING is not a preemptible + * state in the P9 path. */ static void kvmppc_core_start_stolen(struct kvmppc_vcore *vc, u64 tb) @@ -311,8 +318,14 @@ static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu) unsigned long flags; u64 now; - if (cpu_has_feature(CPU_FTR_ARCH_300)) + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + if (vcpu->arch.busy_preempt != TB_NIL) { + WARN_ON_ONCE(vcpu->arch.state != KVMPPC_VCPU_BUSY_IN_HOST); + vc->stolen_tb += mftb() - vcpu->arch.busy_preempt; + vcpu->arch.busy_preempt = TB_NIL; + } return; + } now = mftb(); @@ -340,8 +353,21 @@ static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu) unsigned long flags; u64 now; - if (cpu_has_feature(CPU_FTR_ARCH_300)) + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + /* + * In the P9 path, RUNNABLE is not preemptible + * (nor takes host interrupts) + */ + WARN_ON_ONCE(vcpu->arch.state == KVMPPC_VCPU_RUNNABLE); + /* + * Account stolen time when preempted while the vcpu task is + * running in the kernel (but not in qemu, which is INACTIVE). + */ + if (task_is_running(current) && + vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST) + vcpu->arch.busy_preempt = mftb(); return; + } now = mftb(); @@ -707,16 +733,15 @@ static u64 vcore_stolen_time(struct kvmppc_vcore *vc, u64 now) } static void __kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, + struct lppaca *vpa, unsigned int pcpu, u64 now, unsigned long stolen) { struct dtl_entry *dt; - struct lppaca *vpa; dt = vcpu->arch.dtl_ptr; - vpa = vcpu->arch.vpa.pinned_addr; - if (!dt || !vpa) + if (!dt) return; dt->dispatch_reason = 7; @@ -737,17 +762,23 @@ static void __kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, /* order writing *dt vs. writing vpa->dtl_idx */ smp_wmb(); vpa->dtl_idx = cpu_to_be64(++vcpu->arch.dtl_index); - vcpu->arch.dtl.dirty = true; + + /* vcpu->arch.dtl.dirty is set by the caller */ } -static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, - struct kvmppc_vcore *vc) +static void kvmppc_update_vpa_dispatch(struct kvm_vcpu *vcpu, + struct kvmppc_vcore *vc) { + struct lppaca *vpa; unsigned long stolen; unsigned long core_stolen; u64 now; unsigned long flags; + vpa = vcpu->arch.vpa.pinned_addr; + if (!vpa) + return; + now = mftb(); core_stolen = vcore_stolen_time(vc, now); @@ -758,7 +789,34 @@ static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, vcpu->arch.busy_stolen = 0; spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags); - __kvmppc_create_dtl_entry(vcpu, vc->pcpu, now + vc->tb_offset, stolen); + vpa->enqueue_dispatch_tb = cpu_to_be64(be64_to_cpu(vpa->enqueue_dispatch_tb) + stolen); + + __kvmppc_create_dtl_entry(vcpu, vpa, vc->pcpu, now + vc->tb_offset, stolen); + + vcpu->arch.vpa.dirty = true; +} + +static void kvmppc_update_vpa_dispatch_p9(struct kvm_vcpu *vcpu, + struct kvmppc_vcore *vc, + u64 now) +{ + struct lppaca *vpa; + unsigned long stolen; + unsigned long stolen_delta; + + vpa = vcpu->arch.vpa.pinned_addr; + if (!vpa) + return; + + stolen = vc->stolen_tb; + stolen_delta = stolen - vcpu->arch.stolen_logged; + vcpu->arch.stolen_logged = stolen; + + vpa->enqueue_dispatch_tb = cpu_to_be64(stolen); + + __kvmppc_create_dtl_entry(vcpu, vpa, vc->pcpu, now, stolen_delta); + + vcpu->arch.vpa.dirty = true; } /* See if there is a doorbell interrupt pending for a vcpu */ @@ -2517,10 +2575,24 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, r = set_vpa(vcpu, &vcpu->arch.dtl, addr, len); break; case KVM_REG_PPC_TB_OFFSET: + { /* round up to multiple of 2^24 */ - vcpu->arch.vcore->tb_offset = - ALIGN(set_reg_val(id, *val), 1UL << 24); + u64 tb_offset = ALIGN(set_reg_val(id, *val), 1UL << 24); + + /* + * Now that we know the timebase offset, update the + * decrementer expiry with a guest timebase value. If + * the userspace does not set DEC_EXPIRY, this ensures + * a migrated vcpu at least starts with an expired + * decrementer, which is better than a large one that + * causes a hang. + */ + if (!vcpu->arch.dec_expires && tb_offset) + vcpu->arch.dec_expires = get_tb() + tb_offset; + + vcpu->arch.vcore->tb_offset = tb_offset; break; + } case KVM_REG_PPC_LPCR: kvmppc_set_lpcr(vcpu, set_reg_val(id, *val), true); break; @@ -3800,7 +3872,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) * kvmppc_core_prepare_to_enter. */ kvmppc_start_thread(vcpu, pvc); - kvmppc_create_dtl_entry(vcpu, pvc); + kvmppc_update_vpa_dispatch(vcpu, pvc); trace_kvm_guest_enter(vcpu); if (!vcpu->arch.ptid) thr0_done = true; @@ -3840,23 +3912,17 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) for (sub = 0; sub < core_info.n_subcores; ++sub) spin_unlock(&core_info.vc[sub]->lock); - guest_enter_irqoff(); + guest_timing_enter_irqoff(); srcu_idx = srcu_read_lock(&vc->kvm->srcu); + guest_state_enter_irqoff(); this_cpu_disable_ftrace(); - /* - * Interrupts will be enabled once we get into the guest, - * so tell lockdep that we're about to enable interrupts. - */ - trace_hardirqs_on(); - trap = __kvmppc_vcore_entry(); - trace_hardirqs_off(); - this_cpu_enable_ftrace(); + guest_state_exit_irqoff(); srcu_read_unlock(&vc->kvm->srcu, srcu_idx); @@ -3891,11 +3957,10 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) kvmppc_set_host_core(pcpu); - context_tracking_guest_exit(); if (!vtime_accounting_enabled_this_cpu()) { local_irq_enable(); /* - * Service IRQs here before vtime_account_guest_exit() so any + * Service IRQs here before guest_timing_exit_irqoff() so any * ticks that occurred while running the guest are accounted to * the guest. If vtime accounting is enabled, accounting uses * TB rather than ticks, so it can be done without enabling @@ -3904,7 +3969,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) */ local_irq_disable(); } - vtime_account_guest_exit(); + guest_timing_exit_irqoff(); local_irq_enable(); @@ -4404,7 +4469,7 @@ static int kvmppc_run_vcpu(struct kvm_vcpu *vcpu) if ((vc->vcore_state == VCORE_PIGGYBACK || vc->vcore_state == VCORE_RUNNING) && !VCORE_IS_EXITING(vc)) { - kvmppc_create_dtl_entry(vcpu, vc); + kvmppc_update_vpa_dispatch(vcpu, vc); kvmppc_start_thread(vcpu, vc); trace_kvm_guest_enter(vcpu); } else if (vc->vcore_state == VCORE_SLEEPING) { @@ -4520,7 +4585,6 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, vc = vcpu->arch.vcore; vcpu->arch.ceded = 0; vcpu->arch.run_task = current; - vcpu->arch.state = KVMPPC_VCPU_RUNNABLE; vcpu->arch.last_inst = KVM_INST_FETCH_FAILED; /* See if the MMU is ready to go */ @@ -4547,6 +4611,8 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, /* flags save not required, but irq_pmu has no disable/enable API */ powerpc_local_irq_pmu_save(flags); + vcpu->arch.state = KVMPPC_VCPU_RUNNABLE; + if (signal_pending(current)) goto sigpend; if (need_resched() || !kvm->arch.mmu_ready) @@ -4591,47 +4657,44 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, tb = mftb(); - __kvmppc_create_dtl_entry(vcpu, pcpu, tb + vc->tb_offset, 0); + kvmppc_update_vpa_dispatch_p9(vcpu, vc, tb + vc->tb_offset); trace_kvm_guest_enter(vcpu); - guest_enter_irqoff(); + guest_timing_enter_irqoff(); srcu_idx = srcu_read_lock(&kvm->srcu); + guest_state_enter_irqoff(); this_cpu_disable_ftrace(); - /* Tell lockdep that we're about to enable interrupts */ - trace_hardirqs_on(); - trap = kvmhv_p9_guest_entry(vcpu, time_limit, lpcr, &tb); vcpu->arch.trap = trap; - trace_hardirqs_off(); - this_cpu_enable_ftrace(); + guest_state_exit_irqoff(); srcu_read_unlock(&kvm->srcu, srcu_idx); set_irq_happened(trap); - context_tracking_guest_exit(); + vcpu->cpu = -1; + vcpu->arch.thread_cpu = -1; + vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST; + if (!vtime_accounting_enabled_this_cpu()) { - local_irq_enable(); + powerpc_local_irq_pmu_restore(flags); /* - * Service IRQs here before vtime_account_guest_exit() so any + * Service IRQs here before guest_timing_exit_irqoff() so any * ticks that occurred while running the guest are accounted to * the guest. If vtime accounting is enabled, accounting uses * TB rather than ticks, so it can be done without enabling * interrupts here, which has the problem that it accounts * interrupt processing overhead to the host. */ - local_irq_disable(); + powerpc_local_irq_pmu_save(flags); } - vtime_account_guest_exit(); - - vcpu->cpu = -1; - vcpu->arch.thread_cpu = -1; + guest_timing_exit_irqoff(); powerpc_local_irq_pmu_restore(flags); @@ -4694,6 +4757,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, out: vcpu->cpu = -1; vcpu->arch.thread_cpu = -1; + vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST; powerpc_local_irq_pmu_restore(flags); preempt_enable(); goto done; diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 7ded202bf995..37f50861dd98 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1024,7 +1024,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) /* Restore R1/R2 so we can handle faults */ ld r1, HSTATE_HOST_R1(r13) - ld r2, PACATOC(r13) + LOAD_PACA_TOC() mfspr r10, SPRN_SRR0 mfspr r11, SPRN_SRR1 @@ -2727,8 +2727,8 @@ kvmppc_bad_host_intr: std r4, _CTR(r1) std r5, _XER(r1) std r6, SOFTE(r1) - ld r2, PACATOC(r13) - LOAD_REG_IMMEDIATE(3, 0x7265677368657265) + LOAD_PACA_TOC() + LOAD_REG_IMMEDIATE(3, STACK_FRAME_REGS_MARKER) std r3, STACK_FRAME_OVERHEAD-16(r1) /* diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index d6abed6e51e6..9fc4dd8f66eb 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -499,7 +499,6 @@ static void kvmppc_set_msr_pr(struct kvm_vcpu *vcpu, u64 msr) if (msr & MSR_POW) { if (!vcpu->arch.pending_exceptions) { kvm_vcpu_halt(vcpu); - kvm_clear_request(KVM_REQ_UNHALT, vcpu); vcpu->stat.generic.halt_wakeup++; /* Unset POW bit after we woke up */ diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c index a1f2978b2a86..b2c89e850d7a 100644 --- a/arch/powerpc/kvm/book3s_pr_papr.c +++ b/arch/powerpc/kvm/book3s_pr_papr.c @@ -393,7 +393,6 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd) case H_CEDE: kvmppc_set_msr_fast(vcpu, kvmppc_get_msr(vcpu) | MSR_EE); kvm_vcpu_halt(vcpu); - kvm_clear_request(KVM_REQ_UNHALT, vcpu); vcpu->stat.generic.halt_wakeup++; return EMULATE_DONE; case H_LOGICAL_CI_LOAD: diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 06c5830a93f9..7b4920e9fd26 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -719,7 +719,6 @@ int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu) if (vcpu->arch.shared->msr & MSR_WE) { local_irq_enable(); kvm_vcpu_halt(vcpu); - kvm_clear_request(KVM_REQ_UNHALT, vcpu); hard_irq_disable(); kvmppc_set_exit_type(vcpu, EMULATED_MTMSRWE_EXITS); diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S index 6fa82efe833b..205545d820a1 100644 --- a/arch/powerpc/kvm/booke_interrupts.S +++ b/arch/powerpc/kvm/booke_interrupts.S @@ -223,7 +223,7 @@ _GLOBAL(kvmppc_resume_host) lwz r3, VCPU_HOST_PID(r4) mtspr SPRN_PID, r3 -#ifdef CONFIG_FSL_BOOKE +#ifdef CONFIG_PPC_85xx /* we cheat and know that Linux doesn't use PID1 which is always 0 */ lis r3, 0 mtspr SPRN_PID1, r3 @@ -406,7 +406,7 @@ lightweight_exit: lwz r3, VCPU_SHADOW_PID(r4) mtspr SPRN_PID, r3 -#ifdef CONFIG_FSL_BOOKE +#ifdef CONFIG_PPC_85xx lwz r3, VCPU_SHADOW_PID1(r4) mtspr SPRN_PID1, r3 #endif diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h index c3ef751465fb..6d0d329cbb35 100644 --- a/arch/powerpc/kvm/e500.h +++ b/arch/powerpc/kvm/e500.h @@ -17,7 +17,7 @@ #define KVM_E500_H #include -#include +#include #include #include diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index fb1490761c87..b850b0efa201 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -239,7 +239,6 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu) case EV_HCALL_TOKEN(EV_IDLE): r = EV_SUCCESS; kvm_vcpu_halt(vcpu); - kvm_clear_request(KVM_REQ_UNHALT, vcpu); break; default: r = EV_UNIMPLEMENTED; @@ -786,7 +785,6 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) hrtimer_init(&vcpu->arch.dec_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS); vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup; - vcpu->arch.dec_expires = get_tb(); #ifdef CONFIG_KVM_EXIT_TIMING mutex_init(&vcpu->arch.exit_timing_lock); diff --git a/arch/powerpc/kvm/tm.S b/arch/powerpc/kvm/tm.S index 3bf17c854be4..2158f61e317f 100644 --- a/arch/powerpc/kvm/tm.S +++ b/arch/powerpc/kvm/tm.S @@ -110,7 +110,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_HV_ASSIST) mtmsrd r2, 1 /* Reload TOC pointer. */ - ld r2, PACATOC(r13) + LOAD_PACA_TOC() /* Save all but r0-r2, r9 & r13 */ reg = 3 diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index 6edf0697a526..ad0cf3108dd0 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -94,17 +94,20 @@ void __init poking_init(void) static_branch_enable(&poking_init_done); } +static unsigned long get_patch_pfn(void *addr) +{ + if (IS_ENABLED(CONFIG_MODULES) && is_vmalloc_or_module_addr(addr)) + return vmalloc_to_pfn(addr); + else + return __pa_symbol(addr) >> PAGE_SHIFT; +} + /* * This can be called for kernel text or a module. */ static int map_patch_area(void *addr, unsigned long text_poke_addr) { - unsigned long pfn; - - if (IS_ENABLED(CONFIG_MODULES) && is_vmalloc_or_module_addr(addr)) - pfn = vmalloc_to_pfn(addr); - else - pfn = __pa_symbol(addr) >> PAGE_SHIFT; + unsigned long pfn = get_patch_pfn(addr); return map_kernel_page(text_poke_addr, (pfn << PAGE_SHIFT), PAGE_KERNEL); } @@ -149,17 +152,22 @@ static int __do_patch_instruction(u32 *addr, ppc_inst_t instr) int err; u32 *patch_addr; unsigned long text_poke_addr; + pte_t *pte; + unsigned long pfn = get_patch_pfn(addr); - text_poke_addr = (unsigned long)__this_cpu_read(text_poke_area)->addr; + text_poke_addr = (unsigned long)__this_cpu_read(text_poke_area)->addr & PAGE_MASK; patch_addr = (u32 *)(text_poke_addr + offset_in_page(addr)); - err = map_patch_area(addr, text_poke_addr); - if (err) - return err; + pte = virt_to_kpte(text_poke_addr); + __set_pte_at(&init_mm, text_poke_addr, pte, pfn_pte(pfn, PAGE_KERNEL), 0); + /* See ptesync comment in radix__set_pte_at() */ + if (radix_enabled()) + asm volatile("ptesync": : :"memory"); err = __patch_instruction(addr, instr, patch_addr); - unmap_patch_area(text_poke_addr); + pte_clear(&init_mm, text_poke_addr, pte); + flush_tlb_kernel_range(text_poke_addr, text_poke_addr + PAGE_SIZE); return err; } diff --git a/arch/powerpc/lib/copypage_64.S b/arch/powerpc/lib/copypage_64.S index d1091b5ee5da..6812cb19d04a 100644 --- a/arch/powerpc/lib/copypage_64.S +++ b/arch/powerpc/lib/copypage_64.S @@ -9,11 +9,6 @@ #include #include - .section ".toc","aw" -PPC64_CACHES: - .tc ppc64_caches[TC],ppc64_caches - .section ".text" - _GLOBAL_TOC(copy_page) BEGIN_FTR_SECTION lis r5,PAGE_SIZE@h @@ -24,7 +19,7 @@ FTR_SECTION_ELSE ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY) ori r5,r5,PAGE_SIZE@l BEGIN_FTR_SECTION - ld r10,PPC64_CACHES@toc(r2) + LOAD_REG_ADDR(r10, ppc64_caches) lwz r11,DCACHEL1LOGBLOCKSIZE(r10) /* log2 of cache block size */ lwz r12,DCACHEL1BLOCKSIZE(r10) /* get cache block size */ li r9,0 diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 993d3f31832a..31f40f544de5 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -550,7 +550,7 @@ void do_barrier_nospec_fixups(bool enable) } #endif /* CONFIG_PPC_BARRIER_NOSPEC */ -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 void do_barrier_nospec_fixups_range(bool enable, void *fixup_start, void *fixup_end) { unsigned int instr[2], *dest; @@ -602,7 +602,7 @@ void __init do_btb_flush_fixups(void) for (; start < end; start += 2) patch_btb_flush_section(start); } -#endif /* CONFIG_PPC_FSL_BOOK3E */ +#endif /* CONFIG_PPC_E500 */ void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end) { diff --git a/arch/powerpc/lib/string_64.S b/arch/powerpc/lib/string_64.S index 169872bc0892..df41ce06f86b 100644 --- a/arch/powerpc/lib/string_64.S +++ b/arch/powerpc/lib/string_64.S @@ -11,11 +11,6 @@ #include #include - .section ".toc","aw" -PPC64_CACHES: - .tc ppc64_caches[TC],ppc64_caches - .section ".text" - /** * __arch_clear_user: - Zero a block of memory in user space, with less checking. * @to: Destination address, in user space. @@ -133,7 +128,7 @@ err1; stb r0,0(r3) blr .Llong_clear: - ld r5,PPC64_CACHES@toc(r2) + LOAD_REG_ADDR(r5, ppc64_caches) bf cr7*4+0,11f err2; std r0,0(r3) diff --git a/arch/powerpc/math-emu/Makefile b/arch/powerpc/math-emu/Makefile index a8794032f15f..603e59c3db10 100644 --- a/arch/powerpc/math-emu/Makefile +++ b/arch/powerpc/math-emu/Makefile @@ -17,4 +17,9 @@ obj-$(CONFIG_SPE) += math_efp.o CFLAGS_fabs.o = -fno-builtin-fabs CFLAGS_math.o = -fno-builtin-fabs -ccflags-y = -w +ccflags-remove-y = -Wmissing-prototypes -Wmissing-declarations -Wunused-but-set-variable + +ifdef KBUILD_EXTRA_WARN +CFLAGS_math.o += -Wmissing-prototypes -Wmissing-declarations -Wunused-but-set-variable +CFLAGS_math_efp.o += -Wmissing-prototypes -Wmissing-declarations -Wunused-but-set-variable +endif diff --git a/arch/powerpc/math-emu/math.c b/arch/powerpc/math-emu/math.c index 36761bd00f38..936a9a149037 100644 --- a/arch/powerpc/math-emu/math.c +++ b/arch/powerpc/math-emu/math.c @@ -24,9 +24,9 @@ FLOATFUNC(mtfsf); FLOATFUNC(mtfsfi); #ifdef CONFIG_MATH_EMULATION_HW_UNIMPLEMENTED -#undef FLOATFUNC(x) +#undef FLOATFUNC #define FLOATFUNC(x) static inline int x(void *op1, void *op2, void *op3, \ - void *op4) { } + void *op4) { return 0; } #endif FLOATFUNC(fadd); @@ -396,28 +396,28 @@ do_mathemu(struct pt_regs *regs) case XCR: op0 = (void *)®s->ccr; - op1 = (void *)((insn >> 23) & 0x7); + op1 = (void *)(long)((insn >> 23) & 0x7); op2 = (void *)¤t->thread.TS_FPR((insn >> 16) & 0x1f); op3 = (void *)¤t->thread.TS_FPR((insn >> 11) & 0x1f); break; case XCRL: op0 = (void *)®s->ccr; - op1 = (void *)((insn >> 23) & 0x7); - op2 = (void *)((insn >> 18) & 0x7); + op1 = (void *)(long)((insn >> 23) & 0x7); + op2 = (void *)(long)((insn >> 18) & 0x7); break; case XCRB: - op0 = (void *)((insn >> 21) & 0x1f); + op0 = (void *)(long)((insn >> 21) & 0x1f); break; case XCRI: - op0 = (void *)((insn >> 23) & 0x7); - op1 = (void *)((insn >> 12) & 0xf); + op0 = (void *)(long)((insn >> 23) & 0x7); + op1 = (void *)(long)((insn >> 12) & 0xf); break; case XFLB: - op0 = (void *)((insn >> 17) & 0xff); + op0 = (void *)(long)((insn >> 17) & 0xff); op1 = (void *)¤t->thread.TS_FPR((insn >> 11) & 0x1f); break; diff --git a/arch/powerpc/math-emu/math_efp.c b/arch/powerpc/math-emu/math_efp.c index 39b84e7452e1..34f62aafe706 100644 --- a/arch/powerpc/math-emu/math_efp.c +++ b/arch/powerpc/math-emu/math_efp.c @@ -17,6 +17,7 @@ #include #include +#include #include #include @@ -218,6 +219,7 @@ int do_spe_mathemu(struct pt_regs *regs) case AB: case XCR: FP_UNPACK_SP(SA, va.wp + 1); + fallthrough; case XB: FP_UNPACK_SP(SB, vb.wp + 1); break; @@ -226,8 +228,8 @@ int do_spe_mathemu(struct pt_regs *regs) break; } - pr_debug("SA: %ld %08lx %ld (%ld)\n", SA_s, SA_f, SA_e, SA_c); - pr_debug("SB: %ld %08lx %ld (%ld)\n", SB_s, SB_f, SB_e, SB_c); + pr_debug("SA: %d %08x %d (%d)\n", SA_s, SA_f, SA_e, SA_c); + pr_debug("SB: %d %08x %d (%d)\n", SB_s, SB_f, SB_e, SB_c); switch (func) { case EFSABS: @@ -278,7 +280,7 @@ int do_spe_mathemu(struct pt_regs *regs) } else { SB_e += (func == EFSCTSF ? 31 : 32); FP_TO_INT_ROUND_S(vc.wp[1], SB, 32, - (func == EFSCTSF)); + (func == EFSCTSF) ? 1 : 0); } goto update_regs; @@ -287,7 +289,7 @@ int do_spe_mathemu(struct pt_regs *regs) FP_CLEAR_EXCEPTIONS; FP_UNPACK_DP(DB, vb.dp); - pr_debug("DB: %ld %08lx %08lx %ld (%ld)\n", + pr_debug("DB: %d %08x %08x %d (%d)\n", DB_s, DB_f1, DB_f0, DB_e, DB_c); FP_CONV(S, D, 1, 2, SR, DB); @@ -301,7 +303,7 @@ int do_spe_mathemu(struct pt_regs *regs) FP_SET_EXCEPTION(FP_EX_INVALID); } else { FP_TO_INT_ROUND_S(vc.wp[1], SB, 32, - ((func & 0x3) != 0)); + ((func & 0x3) != 0) ? 1 : 0); } goto update_regs; @@ -312,7 +314,7 @@ int do_spe_mathemu(struct pt_regs *regs) FP_SET_EXCEPTION(FP_EX_INVALID); } else { FP_TO_INT_S(vc.wp[1], SB, 32, - ((func & 0x3) != 0)); + ((func & 0x3) != 0) ? 1 : 0); } goto update_regs; @@ -322,7 +324,7 @@ int do_spe_mathemu(struct pt_regs *regs) break; pack_s: - pr_debug("SR: %ld %08lx %ld (%ld)\n", SR_s, SR_f, SR_e, SR_c); + pr_debug("SR: %d %08x %d (%d)\n", SR_s, SR_f, SR_e, SR_c); FP_PACK_SP(vc.wp + 1, SR); goto update_regs; @@ -346,6 +348,7 @@ cmp_s: case AB: case XCR: FP_UNPACK_DP(DA, va.dp); + fallthrough; case XB: FP_UNPACK_DP(DB, vb.dp); break; @@ -354,9 +357,9 @@ cmp_s: break; } - pr_debug("DA: %ld %08lx %08lx %ld (%ld)\n", + pr_debug("DA: %d %08x %08x %d (%d)\n", DA_s, DA_f1, DA_f0, DA_e, DA_c); - pr_debug("DB: %ld %08lx %08lx %ld (%ld)\n", + pr_debug("DB: %d %08x %08x %d (%d)\n", DB_s, DB_f1, DB_f0, DB_e, DB_c); switch (func) { @@ -408,7 +411,7 @@ cmp_s: } else { DB_e += (func == EFDCTSF ? 31 : 32); FP_TO_INT_ROUND_D(vc.wp[1], DB, 32, - (func == EFDCTSF)); + (func == EFDCTSF) ? 1 : 0); } goto update_regs; @@ -417,7 +420,7 @@ cmp_s: FP_CLEAR_EXCEPTIONS; FP_UNPACK_SP(SB, vb.wp + 1); - pr_debug("SB: %ld %08lx %ld (%ld)\n", + pr_debug("SB: %d %08x %d (%d)\n", SB_s, SB_f, SB_e, SB_c); FP_CONV(D, S, 2, 1, DR, SB); @@ -431,7 +434,7 @@ cmp_s: FP_SET_EXCEPTION(FP_EX_INVALID); } else { FP_TO_INT_D(vc.dp[0], DB, 64, - ((func & 0x1) == 0)); + ((func & 0x1) == 0) ? 1 : 0); } goto update_regs; @@ -442,7 +445,7 @@ cmp_s: FP_SET_EXCEPTION(FP_EX_INVALID); } else { FP_TO_INT_ROUND_D(vc.wp[1], DB, 32, - ((func & 0x3) != 0)); + ((func & 0x3) != 0) ? 1 : 0); } goto update_regs; @@ -453,7 +456,7 @@ cmp_s: FP_SET_EXCEPTION(FP_EX_INVALID); } else { FP_TO_INT_D(vc.wp[1], DB, 32, - ((func & 0x3) != 0)); + ((func & 0x3) != 0) ? 1 : 0); } goto update_regs; @@ -463,7 +466,7 @@ cmp_s: break; pack_d: - pr_debug("DR: %ld %08lx %08lx %ld (%ld)\n", + pr_debug("DR: %d %08x %08x %d (%d)\n", DR_s, DR_f1, DR_f0, DR_e, DR_c); FP_PACK_DP(vc.dp, DR); @@ -492,6 +495,7 @@ cmp_d: case XCR: FP_UNPACK_SP(SA0, va.wp); FP_UNPACK_SP(SA1, va.wp + 1); + fallthrough; case XB: FP_UNPACK_SP(SB0, vb.wp); FP_UNPACK_SP(SB1, vb.wp + 1); @@ -502,13 +506,13 @@ cmp_d: break; } - pr_debug("SA0: %ld %08lx %ld (%ld)\n", + pr_debug("SA0: %d %08x %d (%d)\n", SA0_s, SA0_f, SA0_e, SA0_c); - pr_debug("SA1: %ld %08lx %ld (%ld)\n", + pr_debug("SA1: %d %08x %d (%d)\n", SA1_s, SA1_f, SA1_e, SA1_c); - pr_debug("SB0: %ld %08lx %ld (%ld)\n", + pr_debug("SB0: %d %08x %d (%d)\n", SB0_s, SB0_f, SB0_e, SB0_c); - pr_debug("SB1: %ld %08lx %ld (%ld)\n", + pr_debug("SB1: %d %08x %d (%d)\n", SB1_s, SB1_f, SB1_e, SB1_c); switch (func) { @@ -567,7 +571,7 @@ cmp_d: } else { SB0_e += (func == EVFSCTSF ? 31 : 32); FP_TO_INT_ROUND_S(vc.wp[0], SB0, 32, - (func == EVFSCTSF)); + (func == EVFSCTSF) ? 1 : 0); } if (SB1_c == FP_CLS_NAN) { vc.wp[1] = 0; @@ -575,7 +579,7 @@ cmp_d: } else { SB1_e += (func == EVFSCTSF ? 31 : 32); FP_TO_INT_ROUND_S(vc.wp[1], SB1, 32, - (func == EVFSCTSF)); + (func == EVFSCTSF) ? 1 : 0); } goto update_regs; @@ -586,14 +590,14 @@ cmp_d: FP_SET_EXCEPTION(FP_EX_INVALID); } else { FP_TO_INT_ROUND_S(vc.wp[0], SB0, 32, - ((func & 0x3) != 0)); + ((func & 0x3) != 0) ? 1 : 0); } if (SB1_c == FP_CLS_NAN) { vc.wp[1] = 0; FP_SET_EXCEPTION(FP_EX_INVALID); } else { FP_TO_INT_ROUND_S(vc.wp[1], SB1, 32, - ((func & 0x3) != 0)); + ((func & 0x3) != 0) ? 1 : 0); } goto update_regs; @@ -604,14 +608,14 @@ cmp_d: FP_SET_EXCEPTION(FP_EX_INVALID); } else { FP_TO_INT_S(vc.wp[0], SB0, 32, - ((func & 0x3) != 0)); + ((func & 0x3) != 0) ? 1 : 0); } if (SB1_c == FP_CLS_NAN) { vc.wp[1] = 0; FP_SET_EXCEPTION(FP_EX_INVALID); } else { FP_TO_INT_S(vc.wp[1], SB1, 32, - ((func & 0x3) != 0)); + ((func & 0x3) != 0) ? 1 : 0); } goto update_regs; @@ -621,9 +625,9 @@ cmp_d: break; pack_vs: - pr_debug("SR0: %ld %08lx %ld (%ld)\n", + pr_debug("SR0: %d %08x %d (%d)\n", SR0_s, SR0_f, SR0_e, SR0_c); - pr_debug("SR1: %ld %08lx %ld (%ld)\n", + pr_debug("SR1: %d %08x %d (%d)\n", SR1_s, SR1_f, SR1_e, SR1_c); FP_PACK_SP(vc.wp, SR0); @@ -886,7 +890,7 @@ int speround_handler(struct pt_regs *regs) return 0; } -int __init spe_mathemu_init(void) +static int __init spe_mathemu_init(void) { u32 pvr, maj, min; diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index a96b73006dfb..850783cfa9c7 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -158,7 +158,7 @@ static unsigned long __init __mmu_mapin_ram(unsigned long base, unsigned long to unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top) { unsigned long done; - unsigned long border = (unsigned long)__init_begin - PAGE_OFFSET; + unsigned long border = (unsigned long)__srwx_boundary - PAGE_OFFSET; unsigned long size; size = roundup_pow_of_two((unsigned long)_einittext - PAGE_OFFSET); @@ -240,7 +240,7 @@ void mmu_mark_rodata_ro(void) for (i = 0; i < nb; i++) { struct ppc_bat *bat = BATS[i]; - if (bat_addrs[i].start < (unsigned long)__init_begin) + if (bat_addrs[i].start < (unsigned long)__end_rodata) bat[1].batl = (bat[1].batl & ~BPP_RW) | BPP_RX; } @@ -314,11 +314,9 @@ static void hash_preload(struct mm_struct *mm, unsigned long ea) * * This must always be called with the pte lock held. */ -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, +void __update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { - if (!mmu_has_feature(MMU_FTR_HPTE_TABLE)) - return; /* * We don't need to worry about _PAGE_PRESENT here because we are * called with either mm->page_table_lock held or ptl lock held diff --git a/arch/powerpc/mm/book3s64/hash_pgtable.c b/arch/powerpc/mm/book3s64/hash_pgtable.c index ae008b9df0e6..747492edb75a 100644 --- a/arch/powerpc/mm/book3s64/hash_pgtable.c +++ b/arch/powerpc/mm/book3s64/hash_pgtable.c @@ -256,7 +256,7 @@ pmd_t hash__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long addres * the __collapse_huge_page_copy can result in copying * the old content. */ - flush_tlb_pmd_range(vma->vm_mm, &pmd, address); + flush_hash_table_pmd_range(vma->vm_mm, &pmd, address); return pmd; } @@ -541,7 +541,7 @@ void hash__mark_rodata_ro(void) unsigned long start, end, pp; start = (unsigned long)_stext; - end = (unsigned long)__init_begin; + end = (unsigned long)__end_rodata; pp = htab_convert_pte_flags(pgprot_val(PAGE_KERNEL_ROX), HPTE_USE_KERNEL_KEY); diff --git a/arch/powerpc/mm/book3s64/hash_tlb.c b/arch/powerpc/mm/book3s64/hash_tlb.c index eb0bccaf221e..a64ea0a7ef96 100644 --- a/arch/powerpc/mm/book3s64/hash_tlb.c +++ b/arch/powerpc/mm/book3s64/hash_tlb.c @@ -221,7 +221,7 @@ void __flush_hash_table_range(unsigned long start, unsigned long end) local_irq_restore(flags); } -void flush_tlb_pmd_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr) +void flush_hash_table_pmd_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr) { pte_t *pte; pte_t *start_pte; diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index 363a9447d63d..df008edf7be0 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -123,11 +123,8 @@ EXPORT_SYMBOL_GPL(mmu_slb_size); #ifdef CONFIG_PPC_64K_PAGES int mmu_ci_restrictions; #endif -#ifdef CONFIG_DEBUG_PAGEALLOC static u8 *linear_map_hash_slots; static unsigned long linear_map_hash_count; -static DEFINE_SPINLOCK(linear_map_hash_lock); -#endif /* CONFIG_DEBUG_PAGEALLOC */ struct mmu_hash_ops mmu_hash_ops; EXPORT_SYMBOL(mmu_hash_ops); @@ -427,11 +424,9 @@ repeat: break; cond_resched(); -#ifdef CONFIG_DEBUG_PAGEALLOC - if (debug_pagealloc_enabled() && + if (debug_pagealloc_enabled_or_kfence() && (paddr >> PAGE_SHIFT) < linear_map_hash_count) linear_map_hash_slots[paddr >> PAGE_SHIFT] = ret | 0x80; -#endif /* CONFIG_DEBUG_PAGEALLOC */ } return ret < 0 ? ret : 0; } @@ -778,7 +773,7 @@ static void __init htab_init_page_sizes(void) bool aligned = true; init_hpte_page_sizes(); - if (!debug_pagealloc_enabled()) { + if (!debug_pagealloc_enabled_or_kfence()) { /* * Pick a size for the linear mapping. Currently, we only * support 16M, 1M and 4K which is the default @@ -1066,8 +1061,7 @@ static void __init htab_initialize(void) prot = pgprot_val(PAGE_KERNEL); -#ifdef CONFIG_DEBUG_PAGEALLOC - if (debug_pagealloc_enabled()) { + if (debug_pagealloc_enabled_or_kfence()) { linear_map_hash_count = memblock_end_of_DRAM() >> PAGE_SHIFT; linear_map_hash_slots = memblock_alloc_try_nid( linear_map_hash_count, 1, MEMBLOCK_LOW_LIMIT, @@ -1076,7 +1070,6 @@ static void __init htab_initialize(void) panic("%s: Failed to allocate %lu bytes max_addr=%pa\n", __func__, linear_map_hash_count, &ppc64_rma_size); } -#endif /* CONFIG_DEBUG_PAGEALLOC */ /* create bolted the linear mapping in the hash table */ for_each_mem_range(i, &base, &end) { @@ -1781,7 +1774,7 @@ static void hash_preload(struct mm_struct *mm, pte_t *ptep, unsigned long ea, * * This must always be called with the pte lock held. */ -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, +void __update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { /* @@ -1791,9 +1784,6 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, unsigned long trap; bool is_exec; - if (radix_enabled()) - return; - /* We only want HPTEs for linux PTEs that have _PAGE_ACCESSED set */ if (!pte_young(*ptep) || address >= TASK_SIZE) return; @@ -1990,7 +1980,9 @@ repeat: return slot; } -#ifdef CONFIG_DEBUG_PAGEALLOC +#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE) +static DEFINE_SPINLOCK(linear_map_hash_lock); + static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi) { unsigned long hash; @@ -2005,6 +1997,9 @@ static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi) if (!vsid) return; + if (linear_map_hash_slots[lmi] & 0x80) + return; + ret = hpte_insert_repeating(hash, vpn, __pa(vaddr), mode, HPTE_V_BOLTED, mmu_linear_psize, mmu_kernel_ssize); @@ -2024,7 +2019,10 @@ static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi) hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize); spin_lock(&linear_map_hash_lock); - BUG_ON(!(linear_map_hash_slots[lmi] & 0x80)); + if (!(linear_map_hash_slots[lmi] & 0x80)) { + spin_unlock(&linear_map_hash_lock); + return; + } hidx = linear_map_hash_slots[lmi] & 0x7f; linear_map_hash_slots[lmi] = 0; spin_unlock(&linear_map_hash_lock); @@ -2055,7 +2053,7 @@ void hash__kernel_map_pages(struct page *page, int numpages, int enable) } local_irq_restore(flags); } -#endif /* CONFIG_DEBUG_PAGEALLOC */ +#endif /* CONFIG_DEBUG_PAGEALLOC || CONFIG_KFENCE */ void hash__setup_initial_memory_limit(phys_addr_t first_memblock_base, phys_addr_t first_memblock_size) diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index 7b9966402b25..f6151a589298 100644 --- a/arch/powerpc/mm/book3s64/pgtable.c +++ b/arch/powerpc/mm/book3s64/pgtable.c @@ -553,8 +553,15 @@ EXPORT_SYMBOL_GPL(memremap_compat_align); pgprot_t vm_get_page_prot(unsigned long vm_flags) { - unsigned long prot = pgprot_val(protection_map[vm_flags & - (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]); + unsigned long prot; + + /* Radix supports execute-only, but protection_map maps X -> RX */ + if (radix_enabled() && ((vm_flags & VM_ACCESS_FLAGS) == VM_EXEC)) { + prot = pgprot_val(PAGE_EXECONLY); + } else { + prot = pgprot_val(protection_map[vm_flags & + (VM_ACCESS_FLAGS | VM_SHARED)]); + } if (vm_flags & VM_SAO) prot |= _PAGE_SAO; diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index e712f80fe189..cac727b01799 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -30,9 +30,12 @@ #include #include #include +#include #include +#include + unsigned int mmu_base_pid; unsigned long radix_mem_block_size __ro_after_init; @@ -228,7 +231,7 @@ void radix__mark_rodata_ro(void) unsigned long start, end; start = (unsigned long)_stext; - end = (unsigned long)__init_begin; + end = (unsigned long)__end_rodata; radix__change_memory_range(start, end, _PAGE_WRITE); } @@ -259,21 +262,24 @@ print_mapping(unsigned long start, unsigned long end, unsigned long size, bool e static unsigned long next_boundary(unsigned long addr, unsigned long end) { #ifdef CONFIG_STRICT_KERNEL_RWX - if (addr < __pa_symbol(__init_begin)) - return __pa_symbol(__init_begin); + if (addr < __pa_symbol(__srwx_boundary)) + return __pa_symbol(__srwx_boundary); #endif return end; } static int __meminit create_physical_mapping(unsigned long start, unsigned long end, - unsigned long max_mapping_size, int nid, pgprot_t _prot) { unsigned long vaddr, addr, mapping_size = 0; bool prev_exec, exec = false; pgprot_t prot; int psize; + unsigned long max_mapping_size = radix_mem_block_size; + + if (debug_pagealloc_enabled_or_kfence()) + max_mapping_size = PAGE_SIZE; start = ALIGN(start, PAGE_SIZE); end = ALIGN_DOWN(end, PAGE_SIZE); @@ -352,7 +358,6 @@ static void __init radix_init_pgtable(void) } WARN_ON(create_physical_mapping(start, end, - radix_mem_block_size, -1, PAGE_KERNEL)); } @@ -850,7 +855,7 @@ int __meminit radix__create_section_mapping(unsigned long start, } return create_physical_mapping(__pa(start), __pa(end), - radix_mem_block_size, nid, prot); + nid, prot); } int __meminit radix__remove_section_mapping(unsigned long start, unsigned long end) @@ -896,10 +901,17 @@ void __meminit radix__vmemmap_remove_mapping(unsigned long start, unsigned long #endif #endif -#ifdef CONFIG_DEBUG_PAGEALLOC +#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE) void radix__kernel_map_pages(struct page *page, int numpages, int enable) { - pr_warn_once("DEBUG_PAGEALLOC not supported in radix mode\n"); + unsigned long addr; + + addr = (unsigned long)page_address(page); + + if (enable) + set_memory_p(addr, numpages); + else + set_memory_np(addr, numpages); } #endif diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 014005428687..2bef19cc1b98 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -270,7 +270,11 @@ static bool access_error(bool is_write, bool is_exec, struct vm_area_struct *vma return false; } - if (unlikely(!vma_is_accessible(vma))) + /* + * Check for a read fault. This could be caused by a read on an + * inaccessible page (i.e. PROT_NONE), or a Radix MMU execute-only page. + */ + if (unlikely(!(vma->vm_flags & VM_READ))) return true; /* * We should ideally do the vma pkey access check here. But in the @@ -367,7 +371,22 @@ static void sanity_check_fault(bool is_write, bool is_user, #elif defined(CONFIG_PPC_8xx) #define page_fault_is_bad(__err) ((__err) & DSISR_NOEXEC_OR_G) #elif defined(CONFIG_PPC64) -#define page_fault_is_bad(__err) ((__err) & DSISR_BAD_FAULT_64S) +static int page_fault_is_bad(unsigned long err) +{ + unsigned long flag = DSISR_BAD_FAULT_64S; + + /* + * PAPR+ v2.11 § 14.15.3.4.1 (unreleased) + * If byte 0, bit 3 of pi-attribute-specifier-type in + * ibm,pi-features property is defined, ignore the DSI error + * which is caused by the paste instruction on the + * suspended NX window. + */ + if (mmu_has_feature(MMU_FTR_NX_DSI)) + flag &= ~DSISR_BAD_COPYPASTE; + + return err & flag; +} #else #define page_fault_is_bad(__err) ((__err) & DSISR_BAD_FAULT_32S) #endif diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index bc84a594ca62..5852a86d990d 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -392,7 +392,7 @@ static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud, * single hugepage, but all of them point to * the same kmem cache that holds the hugepte. */ - more = addr + (1 << hugepd_shift(*(hugepd_t *)pmd)); + more = addr + (1UL << hugepd_shift(*(hugepd_t *)pmd)); if (more > next) next = more; @@ -434,7 +434,7 @@ static void hugetlb_free_pud_range(struct mmu_gather *tlb, p4d_t *p4d, * single hugepage, but all of them point to * the same kmem cache that holds the hugepte. */ - more = addr + (1 << hugepd_shift(*(hugepd_t *)pud)); + more = addr + (1UL << hugepd_shift(*(hugepd_t *)pud)); if (more > next) next = more; @@ -496,7 +496,7 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb, * for a single hugepage, but all of them point to the * same kmem cache that holds the hugepte. */ - more = addr + (1 << hugepd_shift(*(hugepd_t *)pgd)); + more = addr + (1UL << hugepd_shift(*(hugepd_t *)pgd)); if (more > next) next = more; @@ -623,7 +623,7 @@ static int __init hugetlbpage_init(void) if (pdshift > shift) { if (!IS_ENABLED(CONFIG_PPC_8xx)) pgtable_cache_add(pdshift - shift); - } else if (IS_ENABLED(CONFIG_PPC_FSL_BOOK3E) || + } else if (IS_ENABLED(CONFIG_PPC_E500) || IS_ENABLED(CONFIG_PPC_8xx)) { pgtable_cache_add(PTE_T_ORDER); } diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index 62d9af6606cd..d4cc3749e621 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -82,28 +82,15 @@ void __init MMU_init(void) if (ppc_md.progress) ppc_md.progress("MMU:enter", 0x111); - /* - * Reserve gigantic pages for hugetlb. This MUST occur before - * lowmem_end_addr is initialized below. - */ - if (memblock.memory.cnt > 1) { -#ifndef CONFIG_WII - memblock_enforce_memory_limit(memblock.memory.regions[0].size); - pr_warn("Only using first contiguous memory region\n"); -#else - wii_memory_fixups(); -#endif - } - total_lowmem = total_memory = memblock_end_of_DRAM() - memstart_addr; lowmem_end_addr = memstart_addr + total_lowmem; -#ifdef CONFIG_FSL_BOOKE +#ifdef CONFIG_PPC_85xx /* Freescale Book-E parts expect lowmem to be mapped by fixed TLB * entries, so we need to adjust lowmem to match the amount we can map * in the fixed entries */ adjust_total_lowmem(); -#endif /* CONFIG_FSL_BOOKE */ +#endif /* CONFIG_PPC_85xx */ if (total_lowmem > __max_low_memory) { total_lowmem = __max_low_memory; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 01772e79fd93..84d171953ba4 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -302,13 +302,13 @@ void __init mem_init(void) for (pfn = highmem_mapnr; pfn < max_mapnr; ++pfn) { phys_addr_t paddr = (phys_addr_t)pfn << PAGE_SHIFT; struct page *page = pfn_to_page(pfn); - if (!memblock_is_reserved(paddr)) + if (memblock_is_memory(paddr) && !memblock_is_reserved(paddr)) free_highmem_page(page); } } #endif /* CONFIG_HIGHMEM */ -#if defined(CONFIG_PPC_FSL_BOOK3E) && !defined(CONFIG_SMP) +#if defined(CONFIG_PPC_E500) && !defined(CONFIG_SMP) /* * If smp is enabled, next_tlbcam_idx is initialized in the cpu up * functions.... do it here for the non-smp case. diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h index 229c72e49198..bd9784f77f2e 100644 --- a/arch/powerpc/mm/mmu_decl.h +++ b/arch/powerpc/mm/mmu_decl.h @@ -38,7 +38,7 @@ static inline void _tlbil_pid(unsigned int pid) #else /* CONFIG_40x || CONFIG_PPC_8xx */ extern void _tlbil_all(void); extern void _tlbil_pid(unsigned int pid); -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 extern void _tlbil_pid_noind(unsigned int pid); #else #define _tlbil_pid_noind(pid) _tlbil_pid(pid) @@ -55,7 +55,7 @@ static inline void _tlbil_va(unsigned long address, unsigned int pid, asm volatile ("tlbie %0; sync" : : "r" (address) : "memory"); trace_tlbie(0, 0, address, pid, 0, 0, 0); } -#elif defined(CONFIG_PPC_BOOK3E) +#elif defined(CONFIG_PPC_BOOK3E_64) extern void _tlbil_va(unsigned long address, unsigned int pid, unsigned int tsize, unsigned int ind); #else @@ -67,7 +67,7 @@ static inline void _tlbil_va(unsigned long address, unsigned int pid, } #endif /* CONFIG_PPC_8xx */ -#if defined(CONFIG_PPC_BOOK3E) || defined(CONFIG_PPC_47x) +#if defined(CONFIG_PPC_BOOK3E_64) || defined(CONFIG_PPC_47x) extern void _tlbivax_bcast(unsigned long address, unsigned int pid, unsigned int tsize, unsigned int ind); #else @@ -92,28 +92,16 @@ extern void mapin_ram(void); extern void setbat(int index, unsigned long virt, phys_addr_t phys, unsigned int size, pgprot_t prot); -extern unsigned int rtas_data, rtas_size; - -struct hash_pte; extern u8 early_hash[]; #endif /* CONFIG_PPC32 */ extern unsigned long __max_low_memory; -extern phys_addr_t __initial_memory_limit_addr; extern phys_addr_t total_memory; extern phys_addr_t total_lowmem; extern phys_addr_t memstart_addr; extern phys_addr_t lowmem_end_addr; -#ifdef CONFIG_WII -extern unsigned long wii_hole_start; -extern unsigned long wii_hole_size; - -extern unsigned long wii_mmu_mapin_mem2(unsigned long top); -extern void wii_memory_fixups(void); -#endif - /* ...and now those things that may be slightly different between processor * architectures. -- Dan */ @@ -123,11 +111,9 @@ void MMU_init_hw_patch(void); unsigned long mmu_mapin_ram(unsigned long base, unsigned long top); #endif -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 extern unsigned long map_mem_in_cams(unsigned long ram, int max_cam_idx, bool dryrun, bool init); -extern unsigned long calc_cam_sz(unsigned long ram, unsigned long virt, - phys_addr_t phys); #ifdef CONFIG_PPC32 extern void adjust_total_lowmem(void); extern int switch_to_as1(void); @@ -160,9 +146,9 @@ struct tlbcam { extern struct tlbcam TLBCAM[NUM_TLBCAMS]; #endif -#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_FSL_BOOKE) || defined(CONFIG_PPC_8xx) +#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_PPC_85xx) || defined(CONFIG_PPC_8xx) /* 6xx have BATS */ -/* FSL_BOOKE have TLBCAM */ +/* PPC_85xx have TLBCAM */ /* 8xx have LTLB */ phys_addr_t v_block_mapped(unsigned long va); unsigned long p_block_mapped(phys_addr_t pa); @@ -171,7 +157,7 @@ static inline phys_addr_t v_block_mapped(unsigned long va) { return 0; } static inline unsigned long p_block_mapped(phys_addr_t pa) { return 0; } #endif -#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_PPC_8xx) || defined(CONFIG_PPC_FSL_BOOK3E) +#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_PPC_8xx) || defined(CONFIG_PPC_E500) void mmu_mark_initmem_nx(void); void mmu_mark_rodata_ro(void); #else diff --git a/arch/powerpc/mm/nohash/Makefile b/arch/powerpc/mm/nohash/Makefile index b467a25ee155..f3894e79d5f7 100644 --- a/arch/powerpc/mm/nohash/Makefile +++ b/arch/powerpc/mm/nohash/Makefile @@ -7,13 +7,13 @@ obj-$(CONFIG_PPC_BOOK3E_64) += tlb_low_64e.o book3e_pgtable.o obj-$(CONFIG_40x) += 40x.o obj-$(CONFIG_44x) += 44x.o obj-$(CONFIG_PPC_8xx) += 8xx.o -obj-$(CONFIG_PPC_FSL_BOOK3E) += fsl_book3e.o +obj-$(CONFIG_PPC_E500) += e500.o obj-$(CONFIG_RANDOMIZE_BASE) += kaslr_booke.o ifdef CONFIG_HUGETLB_PAGE -obj-$(CONFIG_PPC_FSL_BOOK3E) += book3e_hugetlbpage.o +obj-$(CONFIG_PPC_E500) += e500_hugetlbpage.o endif # Disable kcov instrumentation on sensitive code # This is necessary for booting with kcov enabled on book3e machines KCOV_INSTRUMENT_tlb.o := n -KCOV_INSTRUMENT_fsl_book3e.o := n +KCOV_INSTRUMENT_e500.o := n diff --git a/arch/powerpc/mm/nohash/fsl_book3e.c b/arch/powerpc/mm/nohash/e500.c similarity index 98% rename from arch/powerpc/mm/nohash/fsl_book3e.c rename to arch/powerpc/mm/nohash/e500.c index b8ae6c08c06f..40a4e69ae1a9 100644 --- a/arch/powerpc/mm/nohash/fsl_book3e.c +++ b/arch/powerpc/mm/nohash/e500.c @@ -59,7 +59,7 @@ static struct { phys_addr_t phys; } tlbcam_addrs[NUM_TLBCAMS]; -#ifdef CONFIG_FSL_BOOKE +#ifdef CONFIG_PPC_85xx /* * Return PA for this VA if it is mapped by a CAM, or 0 */ @@ -135,8 +135,8 @@ static void settlbcam(int index, unsigned long virt, phys_addr_t phys, tlbcam_addrs[index].phys = phys; } -unsigned long calc_cam_sz(unsigned long ram, unsigned long virt, - phys_addr_t phys) +static unsigned long calc_cam_sz(unsigned long ram, unsigned long virt, + phys_addr_t phys) { unsigned int camsize = __ilog2(ram); unsigned int align = __ffs(virt | phys); diff --git a/arch/powerpc/mm/nohash/book3e_hugetlbpage.c b/arch/powerpc/mm/nohash/e500_hugetlbpage.c similarity index 100% rename from arch/powerpc/mm/nohash/book3e_hugetlbpage.c rename to arch/powerpc/mm/nohash/e500_hugetlbpage.c diff --git a/arch/powerpc/mm/nohash/tlb.c b/arch/powerpc/mm/nohash/tlb.c index 5e7ccb48b79c..2c15c86c7015 100644 --- a/arch/powerpc/mm/nohash/tlb.c +++ b/arch/powerpc/mm/nohash/tlb.c @@ -49,8 +49,7 @@ * other sizes not listed here. The .ind field is only used on MMUs that have * indirect page table entries. */ -#if defined(CONFIG_PPC_BOOK3E_MMU) || defined(CONFIG_PPC_8xx) -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = { [MMU_PAGE_4K] = { .shift = 12, @@ -81,7 +80,20 @@ struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = { .enc = BOOK3E_PAGESZ_1GB, }, }; -#elif defined(CONFIG_PPC_8xx) + +static inline int mmu_get_tsize(int psize) +{ + return mmu_psize_defs[psize].enc; +} +#else +static inline int mmu_get_tsize(int psize) +{ + /* This isn't used on !Book3E for now */ + return 0; +} +#endif + +#ifdef CONFIG_PPC_8xx struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = { [MMU_PAGE_4K] = { .shift = 12, @@ -96,53 +108,7 @@ struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = { .shift = 23, }, }; -#else -struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = { - [MMU_PAGE_4K] = { - .shift = 12, - .ind = 20, - .enc = BOOK3E_PAGESZ_4K, - }, - [MMU_PAGE_16K] = { - .shift = 14, - .enc = BOOK3E_PAGESZ_16K, - }, - [MMU_PAGE_64K] = { - .shift = 16, - .ind = 28, - .enc = BOOK3E_PAGESZ_64K, - }, - [MMU_PAGE_1M] = { - .shift = 20, - .enc = BOOK3E_PAGESZ_1M, - }, - [MMU_PAGE_16M] = { - .shift = 24, - .ind = 36, - .enc = BOOK3E_PAGESZ_16M, - }, - [MMU_PAGE_256M] = { - .shift = 28, - .enc = BOOK3E_PAGESZ_256M, - }, - [MMU_PAGE_1G] = { - .shift = 30, - .enc = BOOK3E_PAGESZ_1GB, - }, -}; -#endif /* CONFIG_FSL_BOOKE */ - -static inline int mmu_get_tsize(int psize) -{ - return mmu_psize_defs[psize].enc; -} -#else -static inline int mmu_get_tsize(int psize) -{ - /* This isn't used on !Book3E for now */ - return 0; -} -#endif /* CONFIG_PPC_BOOK3E_MMU */ +#endif /* The variables below are currently only used on 64-bit Book3E * though this will probably be made common with other nohash @@ -166,7 +132,7 @@ int extlb_level_exc; #endif /* CONFIG_PPC64 */ -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 /* next_tlbcam_idx is used to round-robin tlbcam entry assignment */ DEFINE_PER_CPU(int, next_tlbcam_idx); EXPORT_PER_CPU_SYMBOL(next_tlbcam_idx); @@ -441,7 +407,7 @@ static void __init setup_page_sizes(void) unsigned int eptcfg; int i, psize; -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 unsigned int mmucfg = mfspr(SPRN_MMUCFG); int fsl_mmu = mmu_has_feature(MMU_FTR_TYPE_FSL_E); @@ -584,7 +550,7 @@ static void __init setup_mmu_htw(void) patch_exception(0x1c0, exc_data_tlb_miss_htw_book3e); patch_exception(0x1e0, exc_instruction_tlb_miss_htw_book3e); break; -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 case PPC_HTW_E6500: extlb_level_exc = EX_TLB_SIZE; patch_exception(0x1c0, exc_data_tlb_miss_e6500_book3e); @@ -627,7 +593,7 @@ static void early_init_this_mmu(void) } mtspr(SPRN_MAS4, mas4); -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) { unsigned int num_cams; bool map = true; @@ -680,7 +646,7 @@ static void __init early_init_mmu_global(void) /* Look for HW tablewalk support */ setup_mmu_htw(); -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) { if (book3e_htw_mode == PPC_HTW_NONE) { extlb_level_exc = EX_TLB_SIZE; @@ -701,7 +667,7 @@ static void __init early_init_mmu_global(void) static void __init early_mmu_set_memory_limit(void) { -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) { /* * Limit memory so we dont have linear faults. @@ -750,7 +716,7 @@ void setup_initial_memory_limit(phys_addr_t first_memblock_base, * We crop it to the size of the first MEMBLOCK to * avoid going over total available memory just in case... */ -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 if (early_mmu_has_feature(MMU_FTR_TYPE_FSL_E)) { unsigned long linear_sz; unsigned int num_cams; diff --git a/arch/powerpc/mm/nohash/tlb_low.S b/arch/powerpc/mm/nohash/tlb_low.S index d62b613a0d5d..e1199608ff4d 100644 --- a/arch/powerpc/mm/nohash/tlb_low.S +++ b/arch/powerpc/mm/nohash/tlb_low.S @@ -221,7 +221,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_476_DD2) blr #endif /* CONFIG_PPC_47x */ -#elif defined(CONFIG_FSL_BOOKE) +#elif defined(CONFIG_PPC_85xx) /* * FSL BookE implementations. * @@ -294,7 +294,7 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_USE_TLBILX) isync 1: wrtee r10 blr -#elif defined(CONFIG_PPC_BOOK3E) +#elif defined(CONFIG_PPC_BOOK3E_64) /* * New Book3E (>= 2.06) implementation * @@ -364,7 +364,7 @@ _GLOBAL(_tlbivax_bcast) #error Unsupported processor type ! #endif -#if defined(CONFIG_PPC_FSL_BOOK3E) +#if defined(CONFIG_PPC_E500) /* * extern void loadcam_entry(unsigned int index) * diff --git a/arch/powerpc/mm/nohash/tlb_low_64e.S b/arch/powerpc/mm/nohash/tlb_low_64e.S index 68ffbfdba894..76cf456d7976 100644 --- a/arch/powerpc/mm/nohash/tlb_low_64e.S +++ b/arch/powerpc/mm/nohash/tlb_low_64e.S @@ -61,7 +61,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) ld r14,PACAPGD(r13) std r15,EX_TLB_R15(r12) std r10,EX_TLB_CR(r12) -#ifdef CONFIG_PPC_FSL_BOOK3E START_BTB_FLUSH_SECTION mfspr r11, SPRN_SRR1 andi. r10,r11,MSR_PR @@ -70,14 +69,11 @@ START_BTB_FLUSH_SECTION 1: END_BTB_FLUSH_SECTION std r7,EX_TLB_R7(r12) -#endif .endm .macro tlb_epilog_bolted ld r14,EX_TLB_CR(r12) -#ifdef CONFIG_PPC_FSL_BOOK3E ld r7,EX_TLB_R7(r12) -#endif ld r10,EX_TLB_R10(r12) ld r11,EX_TLB_R11(r12) ld r13,EX_TLB_R13(r12) @@ -248,7 +244,6 @@ itlb_miss_fault_bolted: beq tlb_miss_user_bolted b itlb_miss_kernel_bolted -#ifdef CONFIG_PPC_FSL_BOOK3E /* * TLB miss handling for e6500 and derivatives, using hardware tablewalk. * @@ -515,7 +510,6 @@ dtlb_miss_fault_e6500: itlb_miss_fault_e6500: tlb_epilog_bolted b exc_instruction_storage_book3e -#endif /* CONFIG_PPC_FSL_BOOK3E */ /********************************************************************** * * @@ -1124,8 +1118,8 @@ tlb_load_linear: * we only use 1G pages for now. That might have to be changed in a * final implementation, especially when dealing with hypervisors */ - ld r11,PACATOC(r13) - ld r11,linear_map_top@got(r11) + __LOAD_PACA_TOC(r11) + LOAD_REG_ADDR_ALTTOC(r11, r11, linear_map_top) ld r10,0(r11) tovirt(10,10) cmpld cr0,r16,r10 diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 0801b2ce9b7d..b44ce71917d7 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1160,6 +1160,9 @@ void __init mem_topology_setup(void) { int cpu; + max_low_pfn = max_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT; + min_low_pfn = MEMORY_START >> PAGE_SHIFT; + /* * Linux/mm assumes node 0 to be online at boot. However this is not * true on PowerPC, where node 0 is similar to any other node, it @@ -1204,9 +1207,6 @@ void __init initmem_init(void) { int nid; - max_low_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT; - max_pfn = max_low_pfn; - memblock_dump_all(); for_each_online_node(nid) { diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index 3ac73f9fb5d5..5c02fd08d61e 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -158,10 +158,11 @@ void mark_rodata_ro(void) } /* - * mark .text and .rodata as read only. Use __init_begin rather than - * __end_rodata to cover NOTES and EXCEPTION_TABLE. + * mark text and rodata as read only. __end_rodata is set by + * powerpc's linker script and includes tables and data + * requiring relocation which are not put in RO_DATA. */ - numpages = PFN_UP((unsigned long)__init_begin) - + numpages = PFN_UP((unsigned long)__end_rodata) - PFN_DOWN((unsigned long)_stext); set_memory_ro((unsigned long)_stext, numpages); diff --git a/arch/powerpc/mm/ptdump/Makefile b/arch/powerpc/mm/ptdump/Makefile index b533caaf0910..dc896d2874f3 100644 --- a/arch/powerpc/mm/ptdump/Makefile +++ b/arch/powerpc/mm/ptdump/Makefile @@ -4,7 +4,7 @@ obj-y += ptdump.o obj-$(CONFIG_4xx) += shared.o obj-$(CONFIG_PPC_8xx) += 8xx.o -obj-$(CONFIG_PPC_BOOK3E_MMU) += shared.o +obj-$(CONFIG_PPC_E500) += shared.o obj-$(CONFIG_PPC_BOOK3S_32) += shared.o obj-$(CONFIG_PPC_BOOK3S_64) += book3s64.o diff --git a/arch/powerpc/perf/bhrb.S b/arch/powerpc/perf/bhrb.S index 1aa3259716b8..47ba05d5ae76 100644 --- a/arch/powerpc/perf/bhrb.S +++ b/arch/powerpc/perf/bhrb.S @@ -21,7 +21,7 @@ _GLOBAL(read_bhrb) cmpldi r3,31 bgt 1f - ld r4,bhrb_table@got(r2) + LOAD_REG_ADDR(r4, bhrb_table) sldi r3,r3,3 add r3,r4,r3 mtctr r3 diff --git a/arch/powerpc/perf/callchain_32.c b/arch/powerpc/perf/callchain_32.c index b83c47b7947f..ea8cfe3806dc 100644 --- a/arch/powerpc/perf/callchain_32.c +++ b/arch/powerpc/perf/callchain_32.c @@ -19,7 +19,7 @@ #include "callchain.h" #ifdef CONFIG_PPC64 -#include "../kernel/ppc32.h" +#include #else /* CONFIG_PPC64 */ #define __SIGNAL_FRAMESIZE32 __SIGNAL_FRAMESIZE diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 13919eb96931..03e31ae97741 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -2131,6 +2131,23 @@ static int power_pmu_event_init(struct perf_event *event) if (has_branch_stack(event)) { u64 bhrb_filter = -1; + /* + * Currently no PMU supports having multiple branch filters + * at the same time. Branch filters are set via MMCRA IFM[32:33] + * bits for Power8 and above. Return EOPNOTSUPP when multiple + * branch filters are requested in the event attr. + * + * When opening event via perf_event_open(), branch_sample_type + * gets adjusted in perf_copy_attr(). Kernel will automatically + * adjust the branch_sample_type based on the event modifier + * settings to include PERF_SAMPLE_BRANCH_PLM_ALL. Hence drop + * the check for PERF_SAMPLE_BRANCH_PLM_ALL. + */ + if (hweight64(event->attr.branch_sample_type & ~PERF_SAMPLE_BRANCH_PLM_ALL) > 1) { + local_irq_restore(irq_flags); + return -EOPNOTSUPP; + } + if (ppmu->bhrb_filter_map) bhrb_filter = ppmu->bhrb_filter_map( event->attr.branch_sample_type); diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index d7976ab40d38..d517aba94d1b 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -240,8 +240,10 @@ static int update_events_in_group(struct device_node *node, struct imc_pmu *pmu) ct = of_get_child_count(pmu_events); /* Get the event prefix */ - if (of_property_read_string(node, "events-prefix", &prefix)) + if (of_property_read_string(node, "events-prefix", &prefix)) { + of_node_put(pmu_events); return 0; + } /* Get a global unit and scale data if available */ if (of_property_read_string(node, "scale", &g_scale)) @@ -255,8 +257,10 @@ static int update_events_in_group(struct device_node *node, struct imc_pmu *pmu) /* Allocate memory for the events */ pmu->events = kcalloc(ct, sizeof(struct imc_events), GFP_KERNEL); - if (!pmu->events) + if (!pmu->events) { + of_node_put(pmu_events); return -ENOMEM; + } ct = 0; /* Parse the events and update the struct */ @@ -266,6 +270,8 @@ static int update_events_in_group(struct device_node *node, struct imc_pmu *pmu) ct++; } + of_node_put(pmu_events); + /* Allocate memory for attribute group */ attr_group = kzalloc(sizeof(*attr_group), GFP_KERNEL); if (!attr_group) { diff --git a/arch/powerpc/platforms/44x/ppc476.c b/arch/powerpc/platforms/44x/ppc476.c index 20cc8f80b086..7c91ac5a5241 100644 --- a/arch/powerpc/platforms/44x/ppc476.c +++ b/arch/powerpc/platforms/44x/ppc476.c @@ -140,6 +140,8 @@ static void __init ppc47x_init_irq(void) ppc_md.get_irq = mpic_get_irq; } else panic("Unrecognized top level interrupt controller"); + + of_node_put(np); } #ifdef CONFIG_SMP diff --git a/arch/powerpc/platforms/512x/clock-commonclk.c b/arch/powerpc/platforms/512x/clock-commonclk.c index 0652c7e69225..42abeba4f698 100644 --- a/arch/powerpc/platforms/512x/clock-commonclk.c +++ b/arch/powerpc/platforms/512x/clock-commonclk.c @@ -950,7 +950,7 @@ static void __init mpc5121_clk_register_of_provider(struct device_node *np) */ static void __init mpc5121_clk_provide_migration_support(void) { - + struct device_node *np; /* * pre-enable those clock items which are not yet appropriately * acquired by their peripheral driver @@ -970,7 +970,9 @@ static void __init mpc5121_clk_provide_migration_support(void) * unused and so it gets disabled */ clk_prepare_enable(clks[MPC512x_CLK_PSC3_MCLK]);/* serial console */ - if (of_find_compatible_node(NULL, "pci", "fsl,mpc5121-pci")) + np = of_find_compatible_node(NULL, "pci", "fsl,mpc5121-pci"); + of_node_put(np); + if (np) clk_prepare_enable(clks[MPC512x_CLK_PCI]); } @@ -1208,6 +1210,8 @@ int __init mpc5121_clk_init(void) /* register as an OF clock provider */ mpc5121_clk_register_of_provider(clk_np); + of_node_put(clk_np); + /* * unbreak not yet adjusted peripheral drivers during migration * towards fully operational common clock support, and allow diff --git a/arch/powerpc/platforms/52xx/media5200.c b/arch/powerpc/platforms/52xx/media5200.c index ee367ff3ec8a..33a35fff11b5 100644 --- a/arch/powerpc/platforms/52xx/media5200.c +++ b/arch/powerpc/platforms/52xx/media5200.c @@ -174,6 +174,8 @@ static void __init media5200_init_irq(void) goto out; pr_debug("%s: allocated irqhost\n", __func__); + of_node_put(fpga_np); + irq_set_handler_data(cascade_virq, &media5200_irq); irq_set_chained_handler(cascade_virq, media5200_irq_cascade); @@ -181,6 +183,7 @@ static void __init media5200_init_irq(void) out: pr_err("Could not find Media5200 FPGA; PCI interrupts will not work\n"); + of_node_put(fpga_np); } /* diff --git a/arch/powerpc/platforms/83xx/mpc832x_rdb.c b/arch/powerpc/platforms/83xx/mpc832x_rdb.c index bb8caa5071f8..e12cb44e717f 100644 --- a/arch/powerpc/platforms/83xx/mpc832x_rdb.c +++ b/arch/powerpc/platforms/83xx/mpc832x_rdb.c @@ -162,6 +162,8 @@ static struct spi_board_info mpc832x_spi_boardinfo = { static int __init mpc832x_spi_init(void) { + struct device_node *np; + par_io_config_pin(3, 0, 3, 0, 1, 0); /* SPI1 MOSI, I/O */ par_io_config_pin(3, 1, 3, 0, 1, 0); /* SPI1 MISO, I/O */ par_io_config_pin(3, 2, 3, 0, 1, 0); /* SPI1 CLK, I/O */ @@ -175,7 +177,9 @@ static int __init mpc832x_spi_init(void) * Don't bother with legacy stuff when device tree contains * mmc-spi-slot node. */ - if (of_find_compatible_node(NULL, NULL, "mmc-spi-slot")) + np = of_find_compatible_node(NULL, NULL, "mmc-spi-slot"); + of_node_put(np); + if (np) return 0; return fsl_spi_init(&mpc832x_spi_boardinfo, 1, mpc83xx_spi_cs_control); } diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig index be16eba0f704..b92cb2b4d54d 100644 --- a/arch/powerpc/platforms/85xx/Kconfig +++ b/arch/powerpc/platforms/85xx/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 menuconfig FSL_SOC_BOOKE bool "Freescale Book-E Machine Type" - depends on PPC_85xx || PPC_BOOK3E + depends on PPC_E500 select FSL_SOC select PPC_UDBG_16550 select MPIC @@ -241,8 +241,6 @@ endif # PPC32 config PPC_QEMU_E500 bool "QEMU generic e500 platform" select DEFAULT_UIMAGE - select E500 - select PPC_E500MC if PPC64 help This option enables support for running as a QEMU guest using QEMU's generic e500 machine. This is not required if you're @@ -258,7 +256,6 @@ config PPC_QEMU_E500 config CORENET_GENERIC bool "Freescale CoreNet Generic" select DEFAULT_UIMAGE - select E500 select PPC_E500MC select PHYS_64BIT select SWIOTLB diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c index 28d6b36f1ccd..2c539de2d629 100644 --- a/arch/powerpc/platforms/85xx/corenet_generic.c +++ b/arch/powerpc/platforms/85xx/corenet_generic.c @@ -200,9 +200,5 @@ define_machine(corenet_generic) { #endif .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, -#ifdef CONFIG_PPC64 - .power_save = book3e_idle, -#else .power_save = e500_idle, -#endif }; diff --git a/arch/powerpc/platforms/85xx/ge_imp3a.c b/arch/powerpc/platforms/85xx/ge_imp3a.c index 8e827376d97b..e3e8f18825a1 100644 --- a/arch/powerpc/platforms/85xx/ge_imp3a.c +++ b/arch/powerpc/platforms/85xx/ge_imp3a.c @@ -89,8 +89,10 @@ static void __init ge_imp3a_pci_assign_primary(void) of_device_is_compatible(np, "fsl,mpc8548-pcie") || of_device_is_compatible(np, "fsl,p2020-pcie")) { of_address_to_resource(np, 0, &rsrc); - if ((rsrc.start & 0xfffff) == 0x9000) - fsl_pci_primary = np; + if ((rsrc.start & 0xfffff) == 0x9000) { + of_node_put(fsl_pci_primary); + fsl_pci_primary = of_node_get(np); + } } } #endif diff --git a/arch/powerpc/platforms/85xx/ksi8560.c b/arch/powerpc/platforms/85xx/ksi8560.c index bdf9d42f8521..a22f02b0fc77 100644 --- a/arch/powerpc/platforms/85xx/ksi8560.c +++ b/arch/powerpc/platforms/85xx/ksi8560.c @@ -133,6 +133,8 @@ static void __init ksi8560_setup_arch(void) else printk(KERN_ERR "Can't find CPLD in device tree\n"); + of_node_put(cpld); + if (ppc_md.progress) ppc_md.progress("ksi8560_setup_arch()", 0); diff --git a/arch/powerpc/platforms/85xx/mpc85xx_cds.c b/arch/powerpc/platforms/85xx/mpc85xx_cds.c index 48f3acfece0b..0b8f2101c5fb 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_cds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_cds.c @@ -159,6 +159,7 @@ static void __init mpc85xx_cds_pci_irq_fixup(struct pci_dev *dev) else dev->irq = 10; pci_write_config_byte(dev, PCI_INTERRUPT_LINE, dev->irq); + break; default: break; } diff --git a/arch/powerpc/platforms/85xx/qemu_e500.c b/arch/powerpc/platforms/85xx/qemu_e500.c index 64109ad6736c..1639e222cc33 100644 --- a/arch/powerpc/platforms/85xx/qemu_e500.c +++ b/arch/powerpc/platforms/85xx/qemu_e500.c @@ -68,9 +68,5 @@ define_machine(qemu_e500) { .get_irq = mpic_get_coreint_irq, .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, -#ifdef CONFIG_PPC64 - .power_save = book3e_idle, -#else .power_save = e500_idle, -#endif }; diff --git a/arch/powerpc/platforms/85xx/sgy_cts1000.c b/arch/powerpc/platforms/85xx/sgy_cts1000.c index 98ae64075193..e14d1b74d4e4 100644 --- a/arch/powerpc/platforms/85xx/sgy_cts1000.c +++ b/arch/powerpc/platforms/85xx/sgy_cts1000.c @@ -71,6 +71,7 @@ static int gpio_halt_probe(struct platform_device *pdev) { enum of_gpio_flags flags; struct device_node *node = pdev->dev.of_node; + struct device_node *child_node; int gpio, err, irq; int trigger; @@ -78,26 +79,29 @@ static int gpio_halt_probe(struct platform_device *pdev) return -ENODEV; /* If there's no matching child, this isn't really an error */ - halt_node = of_find_matching_node(node, child_match); - if (!halt_node) + child_node = of_find_matching_node(node, child_match); + if (!child_node) return 0; /* Technically we could just read the first one, but punish * DT writers for invalid form. */ - if (of_gpio_count(halt_node) != 1) - return -EINVAL; + if (of_gpio_count(child_node) != 1) { + err = -EINVAL; + goto err_put; + } /* Get the gpio number relative to the dynamic base. */ - gpio = of_get_gpio_flags(halt_node, 0, &flags); - if (!gpio_is_valid(gpio)) - return -EINVAL; + gpio = of_get_gpio_flags(child_node, 0, &flags); + if (!gpio_is_valid(gpio)) { + err = -EINVAL; + goto err_put; + } err = gpio_request(gpio, "gpio-halt"); if (err) { printk(KERN_ERR "gpio-halt: error requesting GPIO %d.\n", gpio); - halt_node = NULL; - return err; + goto err_put; } trigger = (flags == OF_GPIO_ACTIVE_LOW); @@ -105,15 +109,14 @@ static int gpio_halt_probe(struct platform_device *pdev) gpio_direction_output(gpio, !trigger); /* Now get the IRQ which tells us when the power button is hit */ - irq = irq_of_parse_and_map(halt_node, 0); + irq = irq_of_parse_and_map(child_node, 0); err = request_irq(irq, gpio_halt_irq, IRQF_TRIGGER_RISING | - IRQF_TRIGGER_FALLING, "gpio-halt", halt_node); + IRQF_TRIGGER_FALLING, "gpio-halt", child_node); if (err) { printk(KERN_ERR "gpio-halt: error requesting IRQ %d for " "GPIO %d.\n", irq, gpio); gpio_free(gpio); - halt_node = NULL; - return err; + goto err_put; } /* Register our halt function */ @@ -123,7 +126,12 @@ static int gpio_halt_probe(struct platform_device *pdev) printk(KERN_INFO "gpio-halt: registered GPIO %d (%d trigger, %d" " irq).\n", gpio, trigger, irq); + halt_node = child_node; return 0; + +err_put: + of_node_put(child_node); + return err; } static int gpio_halt_remove(struct platform_device *pdev) @@ -139,6 +147,7 @@ static int gpio_halt_remove(struct platform_device *pdev) gpio_free(gpio); + of_node_put(halt_node); halt_node = NULL; } diff --git a/arch/powerpc/platforms/8xx/tqm8xx_setup.c b/arch/powerpc/platforms/8xx/tqm8xx_setup.c index 3725d51248df..ffcfd17a5fa3 100644 --- a/arch/powerpc/platforms/8xx/tqm8xx_setup.c +++ b/arch/powerpc/platforms/8xx/tqm8xx_setup.c @@ -105,6 +105,9 @@ static void __init init_ioports(void) if (dnode == NULL) return; prop = of_find_property(dnode, "ethernet1", &len); + + of_node_put(dnode); + if (prop == NULL) return; diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 5185d942b455..0c4eed9aea80 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -33,7 +33,7 @@ config PPC_BOOK3S_32 config PPC_85xx bool "Freescale 85xx" - select E500 + select PPC_E500 config PPC_8xx bool "Freescale 8xx" @@ -107,7 +107,8 @@ config PPC_BOOK3S_64 config PPC_BOOK3E_64 bool "Embedded processors" - select PPC_FSL_BOOK3E + select PPC_E500 + select PPC_E500MC select PPC_FPU # Make it a choice ? select PPC_SMP_MUXED_IPI select PPC_DOORBELL @@ -125,7 +126,7 @@ choice If unsure, select Generic. config GENERIC_CPU - bool "Generic (POWER4 and above)" + bool "Generic (POWER5 and PowerPC 970 and above)" depends on PPC_BOOK3S_64 && !CPU_LITTLE_ENDIAN select PPC_64S_HASH_MMU @@ -144,8 +145,8 @@ config CELL_CPU depends on PPC_BOOK3S_64 && !CPU_LITTLE_ENDIAN select PPC_64S_HASH_MMU -config POWER5_CPU - bool "POWER5" +config PPC_970_CPU + bool "PowerPC 970 (including PowerPC G5)" depends on PPC_BOOK3S_64 && !CPU_LITTLE_ENDIAN select PPC_64S_HASH_MMU @@ -171,13 +172,18 @@ config POWER9_CPU depends on PPC_BOOK3S_64 select ARCH_HAS_FAST_MULTIPLIER +config POWER10_CPU + bool "POWER10" + depends on PPC_BOOK3S_64 + select ARCH_HAS_FAST_MULTIPLIER + config E5500_CPU bool "Freescale e5500" - depends on PPC64 && E500 + depends on PPC64 && PPC_E500 config E6500_CPU bool "Freescale e6500" - depends on PPC64 && E500 + depends on PPC64 && PPC_E500 config 405_CPU bool "40x family" @@ -234,11 +240,12 @@ config TARGET_CPU string depends on TARGET_CPU_BOOL default "cell" if CELL_CPU - default "power5" if POWER5_CPU + default "970" if PPC_970_CPU default "power6" if POWER6_CPU default "power7" if POWER7_CPU default "power8" if POWER8_CPU default "power9" if POWER9_CPU + default "power10" if POWER10_CPU default "405" if 405_CPU default "440" if 440_CPU default "464" if 464_CPU @@ -255,20 +262,19 @@ config PPC_BOOK3S def_bool y depends on PPC_BOOK3S_32 || PPC_BOOK3S_64 -config PPC_BOOK3E - def_bool y - depends on PPC_BOOK3E_64 - -config E500 +config PPC_E500 select FSL_EMB_PERFMON - select PPC_FSL_BOOK3E bool + select ARCH_SUPPORTS_HUGETLBFS if PHYS_64BIT || PPC64 + select PPC_SMP_MUXED_IPI + select PPC_DOORBELL + select PPC_KUEP config PPC_E500MC bool "e500mc Support" select PPC_FPU select COMMON_CLK - depends on E500 + depends on PPC_E500 help This must be enabled for running on e500mc (and derivatives such as e5500/e6500), and must be disabled for running on @@ -291,7 +297,7 @@ config PPC_FPU config FSL_EMB_PERFMON bool "Freescale Embedded Perfmon" - depends on E500 || PPC_83xx + depends on PPC_E500 || PPC_83xx help This is the Performance Monitor support found on the e500 core and some e300 cores (c3 and c4). Select this only if your @@ -304,7 +310,7 @@ config FSL_EMB_PERF_EVENT config FSL_EMB_PERF_EVENT_E500 bool - depends on FSL_EMB_PERF_EVENT && E500 + depends on FSL_EMB_PERF_EVENT && PPC_E500 default y config 4xx @@ -314,7 +320,7 @@ config 4xx config BOOKE bool - depends on E500 || 44x || PPC_BOOK3E + depends on PPC_E500 || 44x default y config BOOKE_OR_40x @@ -322,29 +328,14 @@ config BOOKE_OR_40x depends on BOOKE || 40x default y -config FSL_BOOKE - bool - depends on E500 && PPC32 - default y - -# this is for common code between PPC32 & PPC64 FSL BOOKE -config PPC_FSL_BOOK3E - bool - select ARCH_SUPPORTS_HUGETLBFS if PHYS_64BIT || PPC64 - imply FSL_EMB_PERFMON - select PPC_SMP_MUXED_IPI - select PPC_DOORBELL - select PPC_KUEP - default y if FSL_BOOKE - config PTE_64BIT bool - depends on 44x || E500 || PPC_86xx + depends on 44x || PPC_E500 || PPC_86xx default y if PHYS_64BIT config PHYS_64BIT - bool 'Large physical address support' if E500 || PPC_86xx - depends on (44x || E500 || PPC_86xx) && !PPC_83xx && !PPC_82xx + bool 'Large physical address support' if PPC_E500 || PPC_86xx + depends on (44x || PPC_E500 || PPC_86xx) && !PPC_83xx && !PPC_82xx select PHYS_ADDR_T_64BIT help This option enables kernel support for larger than 32-bit physical @@ -391,7 +382,7 @@ config VSX config SPE_POSSIBLE def_bool y - depends on E500 && !PPC_E500MC + depends on PPC_E500 && !PPC_E500MC config SPE bool "SPE Support" @@ -481,10 +472,6 @@ config PPC_MMU_NOHASH def_bool y depends on !PPC_BOOK3S -config PPC_BOOK3E_MMU - def_bool y - depends on FSL_BOOKE || PPC_BOOK3E - config PPC_HAVE_PMU_SUPPORT bool @@ -506,7 +493,7 @@ config FORCE_SMP select SMP config SMP - depends on PPC_BOOK3S || PPC_BOOK3E || FSL_BOOKE || PPC_47x + depends on PPC_BOOK3S || PPC_E500 || PPC_47x select GENERIC_IRQ_MIGRATION bool "Symmetric multi-processing support" if !FORCE_SMP help diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c index c0799fb26b6d..40f5ae5e1238 100644 --- a/arch/powerpc/platforms/book3s/vas-api.c +++ b/arch/powerpc/platforms/book3s/vas-api.c @@ -431,7 +431,7 @@ static vm_fault_t vas_mmap_fault(struct vm_fault *vmf) * The window may be inactive due to lost credit (Ex: core * removal with DLPAR). If the window is active again when * the credit is available, map the new paste address at the - * the window virtual address. + * window virtual address. */ if (txwin->status == VAS_WIN_ACTIVE) { paste_addr = cp_inst->coproc->vops->paste_addr(txwin); diff --git a/arch/powerpc/platforms/cell/cbe_regs.c b/arch/powerpc/platforms/cell/cbe_regs.c index 316e533afc00..fb4023f9ea6b 100644 --- a/arch/powerpc/platforms/cell/cbe_regs.c +++ b/arch/powerpc/platforms/cell/cbe_regs.c @@ -182,9 +182,16 @@ static struct device_node *__init cbe_get_be_node(int cpu_id) if (WARN_ON_ONCE(!cpu_handle)) return np; - for (i=0; ibe_node) { - struct device_node *be, *np; + struct device_node *be, *np, *parent_np; be = map->be_node; - for_each_node_by_type(np, "pervasive") - if (of_get_parent(np) == be) + for_each_node_by_type(np, "pervasive") { + parent_np = of_get_parent(np); + if (parent_np == be) map->pmd_regs = of_iomap(np, 0); + of_node_put(parent_np); + } - for_each_node_by_type(np, "CBEA-Internal-Interrupt-Controller") - if (of_get_parent(np) == be) + for_each_node_by_type(np, "CBEA-Internal-Interrupt-Controller") { + parent_np = of_get_parent(np); + if (parent_np == be) map->iic_regs = of_iomap(np, 2); + of_node_put(parent_np); + } - for_each_node_by_type(np, "mic-tm") - if (of_get_parent(np) == be) + for_each_node_by_type(np, "mic-tm") { + parent_np = of_get_parent(np); + if (parent_np == be) map->mic_tm_regs = of_iomap(np, 0); + of_node_put(parent_np); + } } else { struct device_node *cpu; /* That hack must die die die ! */ @@ -261,7 +277,8 @@ void __init cbe_regs_init(void) of_node_put(cpu); return; } - map->cpu_node = cpu; + of_node_put(map->cpu_node); + map->cpu_node = of_node_get(cpu); for_each_possible_cpu(i) { struct cbe_thread_map *thread = &cbe_thread_map[i]; diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index 0ca3efeef293..8c7133039566 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -720,8 +720,10 @@ static int __init cell_iommu_init_disabled(void) cell_disable_iommus(); /* If we have no Axon, we set up the spider DMA magic offset */ - if (of_find_node_by_name(NULL, "axon") == NULL) + np = of_find_node_by_name(NULL, "axon"); + if (!np) cell_dma_nommu_offset = SPIDER_DMA_OFFSET; + of_node_put(np); /* Now we need to check to see where the memory is mapped * in PCI space. We assume that all busses use the same dma diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c index 52de014983c9..47eaf75349f2 100644 --- a/arch/powerpc/platforms/cell/setup.c +++ b/arch/powerpc/platforms/cell/setup.c @@ -167,6 +167,8 @@ static int __init cell_publish_devices(void) of_platform_device_create(np, NULL, NULL); } + of_node_put(root); + /* There is no device for the MIC memory controller, thus we create * a platform device for it to attach the EDAC driver to. */ diff --git a/arch/powerpc/platforms/cell/spu_callbacks.c b/arch/powerpc/platforms/cell/spu_callbacks.c index fe0d8797a00a..e780c14c5733 100644 --- a/arch/powerpc/platforms/cell/spu_callbacks.c +++ b/arch/powerpc/platforms/cell/spu_callbacks.c @@ -34,15 +34,15 @@ * mbind, mq_open, ipc, ... */ -static void *spu_syscall_table[] = { +static const syscall_fn spu_syscall_table[] = { #define __SYSCALL_WITH_COMPAT(nr, entry, compat) __SYSCALL(nr, entry) -#define __SYSCALL(nr, entry) [nr] = entry, +#define __SYSCALL(nr, entry) [nr] = (void *) entry, #include }; long spu_sys_callback(struct spu_syscall_block *s) { - long (*syscall)(u64 a1, u64 a2, u64 a3, u64 a4, u64 a5, u64 a6); + syscall_fn syscall; if (s->nr_ret >= ARRAY_SIZE(spu_syscall_table)) { pr_debug("%s: invalid syscall #%lld", __func__, s->nr_ret); diff --git a/arch/powerpc/platforms/cell/spu_manage.c b/arch/powerpc/platforms/cell/spu_manage.c index ae09c5a91b40..f1ac4c742069 100644 --- a/arch/powerpc/platforms/cell/spu_manage.c +++ b/arch/powerpc/platforms/cell/spu_manage.c @@ -488,6 +488,8 @@ static void __init init_affinity_node(int cbe) avoid_ph = vic_dn->phandle; } + of_node_put(vic_dn); + list_add_tail(&spu->aff_list, &last_spu->aff_list); last_spu = spu; break; diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h index af048b6dd30a..84958487f696 100644 --- a/arch/powerpc/platforms/cell/spufs/spufs.h +++ b/arch/powerpc/platforms/cell/spufs/spufs.h @@ -333,7 +333,6 @@ void spufs_stop_callback(struct spu *spu, int irq); void spufs_mfc_callback(struct spu *spu); void spufs_dma_callback(struct spu *spu, int type); -extern struct spu_coredump_calls spufs_coredump_calls; struct spufs_coredump_reader { char *name; ssize_t (*dump)(struct spu_context *ctx, struct coredump_params *cprm); @@ -341,7 +340,6 @@ struct spufs_coredump_reader { size_t size; }; extern const struct spufs_coredump_reader spufs_coredump_read[]; -extern int spufs_coredump_num_notes; extern int spu_init_csa(struct spu_state *csa); extern void spu_fini_csa(struct spu_state *csa); diff --git a/arch/powerpc/platforms/chrp/chrp.h b/arch/powerpc/platforms/chrp/chrp.h index a5a7c338caf9..6ff4631d9db4 100644 --- a/arch/powerpc/platforms/chrp/chrp.h +++ b/arch/powerpc/platforms/chrp/chrp.h @@ -9,4 +9,3 @@ extern int chrp_set_rtc_time(struct rtc_time *); extern long chrp_time_init(void); extern void chrp_find_bridges(void); -extern void chrp_event_scan(unsigned long); diff --git a/arch/powerpc/platforms/embedded6xx/holly.c b/arch/powerpc/platforms/embedded6xx/holly.c index 78f2378d9223..bebc5a972694 100644 --- a/arch/powerpc/platforms/embedded6xx/holly.c +++ b/arch/powerpc/platforms/embedded6xx/holly.c @@ -123,6 +123,8 @@ static void __init holly_init_pci(void) if (np) tsi108_setup_pci(np, HOLLY_PCI_CFG_PHYS, 1); + of_node_put(np); + ppc_md.pci_exclude_device = holly_exclude_device; if (ppc_md.progress) ppc_md.progress("tsi108: resources set", 0x100); @@ -184,6 +186,9 @@ static void __init holly_init_IRQ(void) tsi108_pci_int_init(cascade_node); irq_set_handler_data(cascade_pci_irq, mpic); irq_set_chained_handler(cascade_pci_irq, tsi108_irq_cascade); + + of_node_put(tsi_pci); + of_node_put(cascade_node); #endif /* Configure MPIC outputs to CPU0 */ tsi108_write_reg(TSI108_MPIC_OFFSET + 0x30c, 0); @@ -210,6 +215,7 @@ static void __noreturn holly_restart(char *cmd) if (bridge) { prop = of_get_property(bridge, "reg", &size); addr = of_translate_address(bridge, prop); + of_node_put(bridge); } addr += (TSI108_PB_OFFSET + 0x414); diff --git a/arch/powerpc/platforms/embedded6xx/ls_uart.c b/arch/powerpc/platforms/embedded6xx/ls_uart.c index 0133e175a0fc..4ecbc55b37c0 100644 --- a/arch/powerpc/platforms/embedded6xx/ls_uart.c +++ b/arch/powerpc/platforms/embedded6xx/ls_uart.c @@ -124,6 +124,8 @@ static int __init ls_uarts_init(void) avr_clock = *(u32*)of_get_property(avr, "clock-frequency", &len); phys_addr = ((u32*)of_get_property(avr, "reg", &len))[0]; + of_node_put(avr); + if (!avr_clock || !phys_addr) return -EINVAL; diff --git a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c index 8b2b42210356..ddf0c652af80 100644 --- a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c +++ b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c @@ -135,6 +135,9 @@ static void __init mpc7448_hpc2_init_IRQ(void) tsi108_pci_int_init(cascade_node); irq_set_handler_data(cascade_pci_irq, mpic); irq_set_chained_handler(cascade_pci_irq, tsi108_irq_cascade); + + of_node_put(tsi_pci); + of_node_put(cascade_node); #endif /* Configure MPIC outputs to CPU0 */ tsi108_write_reg(TSI108_MPIC_OFFSET + 0x30c, 0); diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c index 9e03ff8f631c..f4e654a9d4ff 100644 --- a/arch/powerpc/platforms/embedded6xx/wii.c +++ b/arch/powerpc/platforms/embedded6xx/wii.c @@ -15,8 +15,6 @@ #include #include #include -#include -#include #include #include @@ -49,19 +47,6 @@ static void __iomem *hw_ctrl; static void __iomem *hw_gpio; -static int __init page_aligned(unsigned long x) -{ - return !(x & (PAGE_SIZE-1)); -} - -void __init wii_memory_fixups(void) -{ - struct memblock_region *p = memblock.memory.regions; - - BUG_ON(memblock.memory.cnt != 2); - BUG_ON(!page_aligned(p[0].base) || !page_aligned(p[1].base)); -} - static void __noreturn wii_spin(void) { local_irq_disable(); diff --git a/arch/powerpc/platforms/maple/time.c b/arch/powerpc/platforms/maple/time.c index 823e219ef8ee..91606411d2e0 100644 --- a/arch/powerpc/platforms/maple/time.c +++ b/arch/powerpc/platforms/maple/time.c @@ -153,6 +153,7 @@ time64_t __init maple_get_boot_time(void) maple_rtc_addr); } bail: + of_node_put(rtcs); if (maple_rtc_addr == 0) { maple_rtc_addr = RTC_PORT(0); /* legacy address */ printk(KERN_INFO "Maple: No device node for RTC, assuming " diff --git a/arch/powerpc/platforms/pasemi/misc.c b/arch/powerpc/platforms/pasemi/misc.c index f859ada29074..9e9a7e46288a 100644 --- a/arch/powerpc/platforms/pasemi/misc.c +++ b/arch/powerpc/platforms/pasemi/misc.c @@ -36,8 +36,7 @@ static int __init find_i2c_driver(struct device_node *node, for (i = 0; i < ARRAY_SIZE(i2c_devices); i++) { if (!of_device_is_compatible(node, i2c_devices[i].of_device)) continue; - if (strlcpy(info->type, i2c_devices[i].i2c_type, - I2C_NAME_SIZE) >= I2C_NAME_SIZE) + if (strscpy(info->type, i2c_devices[i].i2c_type, I2C_NAME_SIZE) < 0) return -ENOMEM; return 0; } diff --git a/arch/powerpc/platforms/pasemi/pci.c b/arch/powerpc/platforms/pasemi/pci.c index 55f0160910bf..f27d31414737 100644 --- a/arch/powerpc/platforms/pasemi/pci.c +++ b/arch/powerpc/platforms/pasemi/pci.c @@ -270,18 +270,12 @@ static int __init pas_add_bridge(struct device_node *dev) void __init pas_pci_init(void) { - struct device_node *np, *root; + struct device_node *np; int res; - root = of_find_node_by_path("/"); - if (!root) { - pr_crit("pas_pci_init: can't find root of device tree\n"); - return; - } - pci_set_flags(PCI_SCAN_ALL_PCIE_DEVS); - np = of_find_compatible_node(root, NULL, "pasemi,rootbus"); + np = of_find_compatible_node(of_root, NULL, "pasemi,rootbus"); if (np) { res = pas_add_bridge(np); of_node_put(np); diff --git a/arch/powerpc/platforms/powermac/feature.c b/arch/powerpc/platforms/powermac/feature.c index 5cc958adba13..0382d20b5619 100644 --- a/arch/powerpc/platforms/powermac/feature.c +++ b/arch/powerpc/platforms/powermac/feature.c @@ -2632,31 +2632,31 @@ static void __init probe_one_macio(const char *name, const char *compat, int typ if (!macio_chips[i].of_node) break; if (macio_chips[i].of_node == node) - return; + goto out_put; } if (i >= MAX_MACIO_CHIPS) { printk(KERN_ERR "pmac_feature: Please increase MAX_MACIO_CHIPS !\n"); printk(KERN_ERR "pmac_feature: %pOF skipped\n", node); - return; + goto out_put; } addrp = of_get_pci_address(node, 0, &size, NULL); if (addrp == NULL) { printk(KERN_ERR "pmac_feature: %pOF: can't find base !\n", node); - return; + goto out_put; } addr = of_translate_address(node, addrp); if (addr == 0) { printk(KERN_ERR "pmac_feature: %pOF, can't translate base !\n", node); - return; + goto out_put; } base = ioremap(addr, (unsigned long)size); if (!base) { printk(KERN_ERR "pmac_feature: %pOF, can't map mac-io chip !\n", node); - return; + goto out_put; } if (type == macio_keylargo || type == macio_keylargo2) { const u32 *did = of_get_property(node, "device-id", NULL); @@ -2677,6 +2677,11 @@ static void __init probe_one_macio(const char *name, const char *compat, int typ macio_chips[i].rev = *revp; printk(KERN_INFO "Found a %s mac-io controller, rev: %d, mapped at 0x%p\n", macio_names[type], macio_chips[i].rev, macio_chips[i].base); + + return; + +out_put: + of_node_put(node); } static int __init diff --git a/arch/powerpc/platforms/powermac/low_i2c.c b/arch/powerpc/platforms/powermac/low_i2c.c index c1c430c66dc9..40f3aa432fba 100644 --- a/arch/powerpc/platforms/powermac/low_i2c.c +++ b/arch/powerpc/platforms/powermac/low_i2c.c @@ -627,6 +627,7 @@ static void __init kw_i2c_probe(void) if (parent == NULL) continue; chans = parent->name[0] == 'u' ? 2 : 1; + of_node_put(parent); for (i = 0; i < chans; i++) kw_i2c_add(host, np, np, i); } else { diff --git a/arch/powerpc/platforms/powermac/pfunc_base.c b/arch/powerpc/platforms/powermac/pfunc_base.c index 9c2947a3edd5..085e0ad20eba 100644 --- a/arch/powerpc/platforms/powermac/pfunc_base.c +++ b/arch/powerpc/platforms/powermac/pfunc_base.c @@ -136,6 +136,8 @@ static void __init macio_gpio_init_one(struct macio_chip *macio) for_each_child_of_node(gparent, gp) pmf_do_functions(gp, NULL, 0, PMF_FLAGS_ON_INIT, NULL); + of_node_put(gparent); + /* Note: We do not at this point implement the "at sleep" or "at wake" * functions. I yet to find any for GPIOs anyway */ diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index d9df45741ece..5b26a9012d2e 100644 --- a/arch/powerpc/platforms/powermac/smp.c +++ b/arch/powerpc/platforms/powermac/smp.c @@ -711,6 +711,7 @@ static void __init smp_core99_setup(int ncpus) printk(KERN_INFO "Processor timebase sync using" " platform function\n"); } + of_node_put(cpus); } #else /* CONFIG_PPC64 */ diff --git a/arch/powerpc/platforms/powermac/udbg_scc.c b/arch/powerpc/platforms/powermac/udbg_scc.c index 734df5a32f99..1b7c39e841ee 100644 --- a/arch/powerpc/platforms/powermac/udbg_scc.c +++ b/arch/powerpc/platforms/powermac/udbg_scc.c @@ -81,10 +81,14 @@ void __init udbg_scc_init(int force_scc) if (path != NULL) stdout = of_find_node_by_path(path); for_each_child_of_node(escc, ch) { - if (ch == stdout) + if (ch == stdout) { + of_node_put(ch_def); ch_def = of_node_get(ch); - if (of_node_name_eq(ch, "ch-a")) + } + if (of_node_name_eq(ch, "ch-a")) { + of_node_put(ch_a); ch_a = of_node_get(ch); + } } if (ch_def == NULL && !force_scc) goto bail; diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index 6f94b808dd39..841cb7f31f4f 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -1411,7 +1411,7 @@ static int __init pnv_parse_cpuidle_dt(void) goto out; } for (i = 0; i < nr_idle_states; i++) - strlcpy(pnv_idle_states[i].name, temp_string[i], + strscpy(pnv_idle_states[i].name, temp_string[i], PNV_IDLE_NAME_LEN); nr_pnv_idle_states = nr_idle_states; rc = 0; @@ -1419,6 +1419,7 @@ out: kfree(temp_u32); kfree(temp_u64); kfree(temp_string); + of_node_put(np); return rc; } diff --git a/arch/powerpc/platforms/powernv/ocxl.c b/arch/powerpc/platforms/powernv/ocxl.c index 27c936075031..629067781cec 100644 --- a/arch/powerpc/platforms/powernv/ocxl.c +++ b/arch/powerpc/platforms/powernv/ocxl.c @@ -478,10 +478,8 @@ EXPORT_SYMBOL_GPL(pnv_ocxl_spa_release); int pnv_ocxl_spa_remove_pe_from_cache(void *platform_data, int pe_handle) { struct spa_data *data = (struct spa_data *) platform_data; - int rc; - rc = opal_npu_spa_clear_cache(data->phb_opal_id, data->bdfn, pe_handle); - return rc; + return opal_npu_spa_clear_cache(data->phb_opal_id, data->bdfn, pe_handle); } EXPORT_SYMBOL_GPL(pnv_ocxl_spa_remove_pe_from_cache); diff --git a/arch/powerpc/platforms/powernv/opal-core.c b/arch/powerpc/platforms/powernv/opal-core.c index adcb1a1a2bfe..bb7657115f1d 100644 --- a/arch/powerpc/platforms/powernv/opal-core.c +++ b/arch/powerpc/platforms/powernv/opal-core.c @@ -348,6 +348,8 @@ static int __init create_opalcore(void) if (!dn || ret) pr_warn("WARNING: Failed to read OPAL base & entry values\n"); + of_node_put(dn); + /* Use count to keep track of the program headers */ count = 0; diff --git a/arch/powerpc/platforms/powernv/opal-powercap.c b/arch/powerpc/platforms/powernv/opal-powercap.c index 64506b46e77b..7bfe4cbeb35a 100644 --- a/arch/powerpc/platforms/powernv/opal-powercap.c +++ b/arch/powerpc/platforms/powernv/opal-powercap.c @@ -153,7 +153,7 @@ void __init opal_powercap_init(void) pcaps = kcalloc(of_get_child_count(powercap), sizeof(*pcaps), GFP_KERNEL); if (!pcaps) - return; + goto out_put_powercap; powercap_kobj = kobject_create_and_add("powercap", opal_kobj); if (!powercap_kobj) { @@ -226,6 +226,7 @@ void __init opal_powercap_init(void) } i++; } + of_node_put(powercap); return; @@ -236,6 +237,9 @@ out_pcaps_pattrs: kfree(pcaps[i].pg.name); } kobject_put(powercap_kobj); + of_node_put(node); out_pcaps: kfree(pcaps); +out_put_powercap: + of_node_put(powercap); } diff --git a/arch/powerpc/platforms/powernv/opal-psr.c b/arch/powerpc/platforms/powernv/opal-psr.c index 69d7e75950d1..6441e17b6996 100644 --- a/arch/powerpc/platforms/powernv/opal-psr.c +++ b/arch/powerpc/platforms/powernv/opal-psr.c @@ -135,7 +135,7 @@ void __init opal_psr_init(void) psr_attrs = kcalloc(of_get_child_count(psr), sizeof(*psr_attrs), GFP_KERNEL); if (!psr_attrs) - return; + goto out_put_psr; psr_kobj = kobject_create_and_add("psr", opal_kobj); if (!psr_kobj) { @@ -162,10 +162,14 @@ void __init opal_psr_init(void) } i++; } + of_node_put(psr); return; out_kobj: + of_node_put(node); kobject_put(psr_kobj); out: kfree(psr_attrs); +out_put_psr: + of_node_put(psr); } diff --git a/arch/powerpc/platforms/powernv/opal-sensor-groups.c b/arch/powerpc/platforms/powernv/opal-sensor-groups.c index 8fba7d25ae56..9944376b115c 100644 --- a/arch/powerpc/platforms/powernv/opal-sensor-groups.c +++ b/arch/powerpc/platforms/powernv/opal-sensor-groups.c @@ -170,7 +170,7 @@ void __init opal_sensor_groups_init(void) sgs = kcalloc(of_get_child_count(sg), sizeof(*sgs), GFP_KERNEL); if (!sgs) - return; + goto out_sg_put; sg_kobj = kobject_create_and_add("sensor_groups", opal_kobj); if (!sg_kobj) { @@ -222,6 +222,7 @@ void __init opal_sensor_groups_init(void) } i++; } + of_node_put(sg); return; @@ -231,6 +232,9 @@ out_sgs_sgattrs: kfree(sgs[i].sg.attrs); } kobject_put(sg_kobj); + of_node_put(node); out_sgs: kfree(sgs); +out_sg_put: + of_node_put(sg); } diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index e5acc33b3b20..0ed95f753416 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -57,7 +57,7 @@ opal_return: .long 0xa64b7b7d /* mthsrr1 r11 */ .long 0x2402004c /* hrfid */ #endif - ld r2,PACATOC(r13) + LOAD_PACA_TOC() ld r0,PPC_LR_STKOFF(r1) mtlr r0 blr diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 55a8fbfdb5b2..cdf3838f08d3 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -892,6 +892,7 @@ static void opal_export_attrs(void) kobj = kobject_create_and_add("exports", opal_kobj); if (!kobj) { pr_warn("kobject_create_and_add() of exports failed\n"); + of_node_put(np); return; } @@ -952,6 +953,8 @@ static void __init opal_imc_init_dev(void) np = of_find_compatible_node(NULL, NULL, IMC_DTB_COMPAT); if (np) of_platform_device_create(np, NULL, NULL); + + of_node_put(np); } static int kopald(void *unused) diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 9de9b2fb163d..5c144c05cbfd 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -67,7 +67,7 @@ void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level, vaf.va = &args; if (pe->flags & PNV_IODA_PE_DEV) - strlcpy(pfix, dev_name(&pe->pdev->dev), sizeof(pfix)); + strscpy(pfix, dev_name(&pe->pdev->dev), sizeof(pfix)); else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) sprintf(pfix, "%04x:%02x ", pci_domain_nr(pe->pbus), pe->pbus->number); diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index dac545aa0308..61ab2d38ff4b 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -207,8 +208,29 @@ static void __init pnv_setup_arch(void) pnv_rng_init(); } +static void __init pnv_add_hw_description(void) +{ + struct device_node *dn; + const char *s; + + dn = of_find_node_by_path("/ibm,opal/firmware"); + if (!dn) + return; + + if (of_property_read_string(dn, "version", &s) == 0 || + of_property_read_string(dn, "git-id", &s) == 0) + seq_buf_printf(&ppc_hw_desc, "opal:%s ", s); + + if (of_property_read_string(dn, "mi-version", &s) == 0) + seq_buf_printf(&ppc_hw_desc, "mi:%s ", s); + + of_node_put(dn); +} + static void __init pnv_init(void) { + pnv_add_hw_description(); + /* * Initialize the LPC bus now so that legacy serial * ports can be found on it diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index fb6499977f99..a3b4d99567cb 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -23,13 +23,21 @@ config PPC_PSERIES select SWIOTLB default y +config PARAVIRT + bool + config PARAVIRT_SPINLOCKS bool +config PARAVIRT_TIME_ACCOUNTING + select PARAVIRT + bool + config PPC_SPLPAR bool "Support for shared-processor logical partitions" depends on PPC_PSERIES select PARAVIRT_SPINLOCKS if PPC_QUEUED_SPINLOCKS + select PARAVIRT_TIME_ACCOUNTING if VIRT_CPU_ACCOUNTING_GEN default y help Enabling this option will make the kernel run more efficiently diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c index 352af5b14a0f..1b1977bc78e7 100644 --- a/arch/powerpc/platforms/pseries/dtl.c +++ b/arch/powerpc/platforms/pseries/dtl.c @@ -37,6 +37,15 @@ static u8 dtl_event_mask = DTL_LOG_ALL; static int dtl_buf_entries = N_DISPATCH_LOG; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE + +/* + * When CONFIG_VIRT_CPU_ACCOUNTING_NATIVE = y, the cpu accounting code controls + * reading from the dispatch trace log. If other code wants to consume + * DTL entries, it can set this pointer to a function that will get + * called once for each DTL entry that gets processed. + */ +static void (*dtl_consumer)(struct dtl_entry *entry, u64 index); + struct dtl_ring { u64 write_index; struct dtl_entry *write_ptr; @@ -48,6 +57,78 @@ static DEFINE_PER_CPU(struct dtl_ring, dtl_rings); static atomic_t dtl_count; +/* + * Scan the dispatch trace log and count up the stolen time. + * Should be called with interrupts disabled. + */ +static notrace u64 scan_dispatch_log(u64 stop_tb) +{ + u64 i = local_paca->dtl_ridx; + struct dtl_entry *dtl = local_paca->dtl_curr; + struct dtl_entry *dtl_end = local_paca->dispatch_log_end; + struct lppaca *vpa = local_paca->lppaca_ptr; + u64 tb_delta; + u64 stolen = 0; + u64 dtb; + + if (!dtl) + return 0; + + if (i == be64_to_cpu(vpa->dtl_idx)) + return 0; + while (i < be64_to_cpu(vpa->dtl_idx)) { + dtb = be64_to_cpu(dtl->timebase); + tb_delta = be32_to_cpu(dtl->enqueue_to_dispatch_time) + + be32_to_cpu(dtl->ready_to_enqueue_time); + barrier(); + if (i + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx)) { + /* buffer has overflowed */ + i = be64_to_cpu(vpa->dtl_idx) - N_DISPATCH_LOG; + dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG); + continue; + } + if (dtb > stop_tb) + break; + if (dtl_consumer) + dtl_consumer(dtl, i); + stolen += tb_delta; + ++i; + ++dtl; + if (dtl == dtl_end) + dtl = local_paca->dispatch_log; + } + local_paca->dtl_ridx = i; + local_paca->dtl_curr = dtl; + return stolen; +} + +/* + * Accumulate stolen time by scanning the dispatch trace log. + * Called on entry from user mode. + */ +void notrace pseries_accumulate_stolen_time(void) +{ + u64 sst, ust; + struct cpu_accounting_data *acct = &local_paca->accounting; + + sst = scan_dispatch_log(acct->starttime_user); + ust = scan_dispatch_log(acct->starttime); + acct->stime -= sst; + acct->utime -= ust; + acct->steal_time += ust + sst; +} + +u64 pseries_calculate_stolen_time(u64 stop_tb) +{ + if (!firmware_has_feature(FW_FEATURE_SPLPAR)) + return 0; + + if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) + return scan_dispatch_log(stop_tb); + + return 0; +} + /* * The cpu accounting code controls the DTL ring buffer, and we get * given entries as they are processed. diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 0f8cd8b06432..e0a7ac5db15d 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -619,17 +619,21 @@ static ssize_t dlpar_cpu_add(u32 drc_index) static unsigned int pseries_cpuhp_cache_use_count(const struct device_node *cachedn) { unsigned int use_count = 0; - struct device_node *dn; + struct device_node *dn, *tn; WARN_ON(!of_node_is_type(cachedn, "cache")); for_each_of_cpu_node(dn) { - if (of_find_next_cache_node(dn) == cachedn) + tn = of_find_next_cache_node(dn); + of_node_put(tn); + if (tn == cachedn) use_count++; } for_each_node_by_type(dn, "cache") { - if (of_find_next_cache_node(dn) == cachedn) + tn = of_find_next_cache_node(dn); + of_node_put(tn); + if (tn == cachedn) use_count++; } @@ -649,10 +653,13 @@ static int pseries_cpuhp_detach_nodes(struct device_node *cpudn) dn = cpudn; while ((dn = of_find_next_cache_node(dn))) { - if (pseries_cpuhp_cache_use_count(dn) > 1) + if (pseries_cpuhp_cache_use_count(dn) > 1) { + of_node_put(dn); break; + } ret = of_changeset_detach_node(&cs, dn); + of_node_put(dn); if (ret) goto out; } diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index ab9fc6506861..762eb15d3bd4 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -16,7 +16,7 @@ #ifdef CONFIG_TRACEPOINTS #ifndef CONFIG_JUMP_LABEL - .section ".toc","aw" + .data .globl hcall_tracepoint_refcount hcall_tracepoint_refcount: @@ -88,7 +88,7 @@ hcall_tracepoint_refcount: BEGIN_FTR_SECTION; \ b 1f; \ END_FTR_SECTION(0, 1); \ - ld r12,hcall_tracepoint_refcount@toc(r2); \ + LOAD_REG_ADDR(r12, hcall_tracepoint_refcount) ; \ std r12,32(r1); \ cmpdi r12,0; \ bne- LABEL; \ diff --git a/arch/powerpc/platforms/pseries/hvcserver.c b/arch/powerpc/platforms/pseries/hvcserver.c index 96e18d3b2fcf..d48c9c7ce10f 100644 --- a/arch/powerpc/platforms/pseries/hvcserver.c +++ b/arch/powerpc/platforms/pseries/hvcserver.c @@ -176,7 +176,7 @@ int hvcs_get_partner_info(uint32_t unit_address, struct list_head *head, = (unsigned int)last_p_partition_ID; /* copy the Null-term char too */ - strlcpy(&next_partner_info->location_code[0], + strscpy(&next_partner_info->location_code[0], (char *)&pi_buff[2], sizeof(next_partner_info->location_code)); diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c index 7ee3ed7d6cc2..a870cada7acd 100644 --- a/arch/powerpc/platforms/pseries/ibmebus.c +++ b/arch/powerpc/platforms/pseries/ibmebus.c @@ -152,7 +152,11 @@ static const struct dma_map_ops ibmebus_dma_ops = { static int ibmebus_match_path(struct device *dev, const void *data) { struct device_node *dn = to_platform_device(dev)->dev.of_node; - return (of_find_node_by_path(data) == dn); + struct device_node *tn = of_find_node_by_path(data); + + of_node_put(tn); + + return (tn == dn); } static int ibmebus_match_node(struct device *dev, const void *data) diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index e6c117fb6491..97ef6499e501 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -660,6 +660,17 @@ static int __init vcpudispatch_stats_procfs_init(void) } machine_device_initcall(pseries, vcpudispatch_stats_procfs_init); + +#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING +u64 pseries_paravirt_steal_clock(int cpu) +{ + struct lppaca *lppaca = &lppaca_of(cpu); + + return be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb)) + + be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb)); +} +#endif + #endif /* CONFIG_PPC_SPLPAR */ void vpa_init(int cpu) diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 3d36a8955eaf..634fac5db3f9 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -216,7 +216,7 @@ static int update_dt_node(struct device_node *dn, s32 scope) nprops = be32_to_cpu(upwa->nprops); /* On the first call to ibm,update-properties for a node the - * the first property value descriptor contains an empty + * first property value descriptor contains an empty * property name, the property value length encoded as u32, * and the property value is the node path being updated. */ @@ -740,11 +740,19 @@ static int pseries_migrate_partition(u64 handle) #ifdef CONFIG_PPC_WATCHDOG factor = nmi_wd_lpm_factor; #endif + /* + * When the migration is initiated, the hypervisor changes VAS + * mappings to prepare before OS gets the notification and + * closes all VAS windows. NX generates continuous faults during + * this time and the user space can not differentiate these + * faults from the migration event. So reduce this time window + * by closing VAS windows at the beginning of this function. + */ + vas_migration_handler(VAS_SUSPEND); + ret = wait_for_vasi_session_suspending(handle); if (ret) - return ret; - - vas_migration_handler(VAS_SUSPEND); + goto out; if (factor) watchdog_nmi_set_timeout_pct(factor); @@ -765,6 +773,7 @@ static int pseries_migrate_partition(u64 handle) if (factor) watchdog_nmi_set_timeout_pct(0); +out: vas_migration_handler(VAS_RESUME); return ret; diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c index cad7a0c93117..599bd2c78514 100644 --- a/arch/powerpc/platforms/pseries/reconfig.c +++ b/arch/powerpc/platforms/pseries/reconfig.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include @@ -361,6 +362,10 @@ static ssize_t ofdt_write(struct file *file, const char __user *buf, size_t coun char *kbuf; char *tmp; + rv = security_locked_down(LOCKDOWN_DEVICE_TREE); + if (rv) + return rv; + kbuf = memdup_user_nul(buf, count); if (IS_ERR(kbuf)) return PTR_ERR(kbuf); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 489f4c4df468..8ef3270515a9 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -41,6 +41,7 @@ #include #include #include +#include #include #include @@ -80,6 +81,20 @@ DEFINE_STATIC_KEY_FALSE(shared_processor); EXPORT_SYMBOL(shared_processor); +#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING +struct static_key paravirt_steal_enabled; +struct static_key paravirt_steal_rq_enabled; + +static bool steal_acc = true; +static int __init parse_no_stealacc(char *arg) +{ + steal_acc = false; + return 0; +} + +early_param("no-steal-acc", parse_no_stealacc); +#endif + int CMO_PrPSP = -1; int CMO_SecPSP = -1; unsigned long CMO_PageSize = (ASM_CONST(1) << IOMMU_PAGE_SHIFT_4K); @@ -834,6 +849,11 @@ static void __init pSeries_setup_arch(void) if (lppaca_shared_proc(get_lppaca())) { static_branch_enable(&shared_processor); pv_spinlocks_init(); +#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING + static_key_slow_inc(¶virt_steal_enabled); + if (steal_acc) + static_key_slow_inc(¶virt_steal_rq_enabled); +#endif } ppc_md.power_save = pseries_lpar_idle; @@ -992,6 +1012,33 @@ static void __init pSeries_cmo_feature_init(void) pr_debug(" <- fw_cmo_feature_init()\n"); } +static void __init pseries_add_hw_description(void) +{ + struct device_node *dn; + const char *s; + + dn = of_find_node_by_path("/openprom"); + if (dn) { + if (of_property_read_string(dn, "model", &s) == 0) + seq_buf_printf(&ppc_hw_desc, "of:%s ", s); + + of_node_put(dn); + } + + dn = of_find_node_by_path("/hypervisor"); + if (dn) { + if (of_property_read_string(dn, "compatible", &s) == 0) + seq_buf_printf(&ppc_hw_desc, "hv:%s ", s); + + of_node_put(dn); + return; + } + + if (of_property_read_bool(of_root, "ibm,powervm-partition") || + of_property_read_bool(of_root, "ibm,fw-net-version")) + seq_buf_printf(&ppc_hw_desc, "hv:phyp "); +} + /* * Early initialization. Relocation is on but do not reference unbolted pages */ @@ -999,6 +1046,8 @@ static void __init pseries_init(void) { pr_debug(" -> pseries_init()\n"); + pseries_add_hw_description(); + #ifdef CONFIG_HVC_CONSOLE if (firmware_has_feature(FW_FEATURE_LPAR)) hvc_vio_init_early(); diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c index 7e6e6dd2e33e..0e0524cbe20c 100644 --- a/arch/powerpc/platforms/pseries/vas.c +++ b/arch/powerpc/platforms/pseries/vas.c @@ -333,7 +333,7 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, * So no unpacking needs to be done. */ rc = plpar_hcall9(H_HOME_NODE_ASSOCIATIVITY, domain, - VPHN_FLAG_VCPU, smp_processor_id()); + VPHN_FLAG_VCPU, hard_smp_processor_id()); if (rc != H_SUCCESS) { pr_err("H_HOME_NODE_ASSOCIATIVITY error: %d\n", rc); goto out; @@ -501,14 +501,10 @@ static const struct vas_user_win_ops vops_pseries = { int vas_register_api_pseries(struct module *mod, enum vas_cop_type cop_type, const char *name) { - int rc; - if (!copypaste_feat) return -ENOTSUPP; - rc = vas_register_coproc_api(mod, cop_type, name, &vops_pseries); - - return rc; + return vas_register_coproc_api(mod, cop_type, name, &vops_pseries); } EXPORT_SYMBOL_GPL(vas_register_api_pseries); diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c index ef9a5999fa93..73c2d70706c0 100644 --- a/arch/powerpc/sysdev/fsl_msi.c +++ b/arch/powerpc/sysdev/fsl_msi.c @@ -209,8 +209,10 @@ static int fsl_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) dev_err(&pdev->dev, "node %pOF has an invalid fsl,msi phandle %u\n", hose->dn, np->phandle); + of_node_put(np); return -EINVAL; } + of_node_put(np); } msi_for_each_desc(entry, &pdev->dev, MSI_DESC_NOTASSOCIATED) { diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index af6c8ca824d3..974d3db6faab 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -181,6 +181,7 @@ static int setup_one_atmu(struct ccsr_pci __iomem *pci, static bool is_kdump(void) { struct device_node *node; + bool ret; node = of_find_node_by_type(NULL, "memory"); if (!node) { @@ -188,7 +189,10 @@ static bool is_kdump(void) return false; } - return of_property_read_bool(node, "linux,usable-memory"); + ret = of_property_read_bool(node, "linux,usable-memory"); + of_node_put(node); + + return ret; } /* atmu setup for fsl pci/pcie controller */ @@ -939,7 +943,7 @@ u64 fsl_pci_immrbar_base(struct pci_controller *hose) return 0; } -#ifdef CONFIG_E500 +#ifdef CONFIG_PPC_E500 static int mcheck_handle_load(struct pt_regs *regs, u32 inst) { unsigned int rd, ra, rb, d; @@ -1142,7 +1146,6 @@ void __init fsl_pci_assign_primary(void) for_each_matching_node(np, pci_ids) { if (of_device_is_available(np)) { fsl_pci_primary = np; - of_node_put(np); return; } } diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c index 4647c6074f3b..c8f044d62fe2 100644 --- a/arch/powerpc/sysdev/fsl_rio.c +++ b/arch/powerpc/sysdev/fsl_rio.c @@ -98,7 +98,7 @@ resource_size_t rio_law_start; struct fsl_rio_dbell *dbell; struct fsl_rio_pw *pw; -#ifdef CONFIG_E500 +#ifdef CONFIG_PPC_E500 int fsl_rio_mcheck_exception(struct pt_regs *regs) { const struct exception_table_entry *entry; diff --git a/arch/powerpc/sysdev/mpic_msgr.c b/arch/powerpc/sysdev/mpic_msgr.c index 698fefaaa6dd..a439e33eae06 100644 --- a/arch/powerpc/sysdev/mpic_msgr.c +++ b/arch/powerpc/sysdev/mpic_msgr.c @@ -121,6 +121,7 @@ static unsigned int mpic_msgr_number_of_blocks(void) count += 1; } + of_node_put(aliases); } return count; @@ -144,12 +145,18 @@ static int mpic_msgr_block_number(struct device_node *node) for (index = 0; index < number_of_blocks; ++index) { struct property *prop; + struct device_node *tn; snprintf(buf, sizeof(buf), "mpic-msgr-block%d", index); prop = of_find_property(aliases, buf, NULL); - if (node == of_find_node_by_path(prop->value)) + tn = of_find_node_by_path(prop->value); + if (node == tn) { + of_node_put(tn); break; + } + of_node_put(tn); } + of_node_put(aliases); return index == number_of_blocks ? -1 : index; } diff --git a/arch/powerpc/sysdev/xics/ics-rtas.c b/arch/powerpc/sysdev/xics/ics-rtas.c index 9e7007f9aca5..f8320f8e5bc7 100644 --- a/arch/powerpc/sysdev/xics/ics-rtas.c +++ b/arch/powerpc/sysdev/xics/ics-rtas.c @@ -36,8 +36,8 @@ static void ics_rtas_unmask_irq(struct irq_data *d) server = xics_get_irq_server(d->irq, irq_data_get_affinity_mask(d), 0); - call_status = rtas_call_reentrant(ibm_set_xive, 3, 1, NULL, hw_irq, - server, DEFAULT_PRIORITY); + call_status = rtas_call(ibm_set_xive, 3, 1, NULL, hw_irq, server, + DEFAULT_PRIORITY); if (call_status != 0) { printk(KERN_ERR "%s: ibm_set_xive irq %u server %x returned %d\n", @@ -46,7 +46,7 @@ static void ics_rtas_unmask_irq(struct irq_data *d) } /* Now unmask the interrupt (often a no-op) */ - call_status = rtas_call_reentrant(ibm_int_on, 1, 1, NULL, hw_irq); + call_status = rtas_call(ibm_int_on, 1, 1, NULL, hw_irq); if (call_status != 0) { printk(KERN_ERR "%s: ibm_int_on irq=%u returned %d\n", __func__, hw_irq, call_status); @@ -68,7 +68,7 @@ static void ics_rtas_mask_real_irq(unsigned int hw_irq) if (hw_irq == XICS_IPI) return; - call_status = rtas_call_reentrant(ibm_int_off, 1, 1, NULL, hw_irq); + call_status = rtas_call(ibm_int_off, 1, 1, NULL, hw_irq); if (call_status != 0) { printk(KERN_ERR "%s: ibm_int_off irq=%u returned %d\n", __func__, hw_irq, call_status); @@ -76,8 +76,8 @@ static void ics_rtas_mask_real_irq(unsigned int hw_irq) } /* Have to set XIVE to 0xff to be able to remove a slot */ - call_status = rtas_call_reentrant(ibm_set_xive, 3, 1, NULL, hw_irq, - xics_default_server, 0xff); + call_status = rtas_call(ibm_set_xive, 3, 1, NULL, hw_irq, + xics_default_server, 0xff); if (call_status != 0) { printk(KERN_ERR "%s: ibm_set_xive(0xff) irq=%u returned %d\n", __func__, hw_irq, call_status); @@ -108,7 +108,7 @@ static int ics_rtas_set_affinity(struct irq_data *d, if (hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS) return -1; - status = rtas_call_reentrant(ibm_get_xive, 1, 3, xics_status, hw_irq); + status = rtas_call(ibm_get_xive, 1, 3, xics_status, hw_irq); if (status) { printk(KERN_ERR "%s: ibm,get-xive irq=%u returns %d\n", @@ -126,8 +126,8 @@ static int ics_rtas_set_affinity(struct irq_data *d, pr_debug("%s: irq %d [hw 0x%x] server: 0x%x\n", __func__, d->irq, hw_irq, irq_server); - status = rtas_call_reentrant(ibm_set_xive, 3, 1, NULL, - hw_irq, irq_server, xics_status[1]); + status = rtas_call(ibm_set_xive, 3, 1, NULL, + hw_irq, irq_server, xics_status[1]); if (status) { printk(KERN_ERR "%s: ibm,set-xive irq=%u returns %d\n", @@ -158,7 +158,7 @@ static int ics_rtas_check(struct ics *ics, unsigned int hw_irq) return -EINVAL; /* Check if RTAS knows about this interrupt */ - rc = rtas_call_reentrant(ibm_get_xive, 1, 3, status, hw_irq); + rc = rtas_call(ibm_get_xive, 1, 3, status, hw_irq); if (rc) return -ENXIO; @@ -174,7 +174,7 @@ static long ics_rtas_get_server(struct ics *ics, unsigned long vec) { int rc, status[2]; - rc = rtas_call_reentrant(ibm_get_xive, 1, 3, status, vec); + rc = rtas_call(ibm_get_xive, 1, 3, status, vec); if (rc) return -1; return status[0]; diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index 61b9f98dfd4a..a289cb97c1d7 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -783,7 +783,7 @@ static int xive_irq_set_type(struct irq_data *d, unsigned int flow_type) * the corresponding descriptor bits mind you but those will in turn * affect the resend function when re-enabling an edge interrupt. * - * Set set the default to edge as explained in map(). + * Set the default to edge as explained in map(). */ if (flow_type == IRQ_TYPE_DEFAULT || flow_type == IRQ_TYPE_NONE) flow_type = IRQ_TYPE_EDGE_RISING; diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c index d25d8c692909..3925825954bc 100644 --- a/arch/powerpc/sysdev/xive/native.c +++ b/arch/powerpc/sysdev/xive/native.c @@ -579,12 +579,12 @@ bool __init xive_native_init(void) /* Resource 1 is HV window */ if (of_address_to_resource(np, 1, &r)) { pr_err("Failed to get thread mgmnt area resource\n"); - return false; + goto err_put; } tima = ioremap(r.start, resource_size(&r)); if (!tima) { pr_err("Failed to map thread mgmnt area\n"); - return false; + goto err_put; } /* Read number of priorities */ @@ -612,7 +612,7 @@ bool __init xive_native_init(void) /* Resource 2 is OS window */ if (of_address_to_resource(np, 2, &r)) { pr_err("Failed to get thread mgmnt area resource\n"); - return false; + goto err_put; } xive_tima_os = r.start; @@ -624,7 +624,7 @@ bool __init xive_native_init(void) rc = opal_xive_reset(OPAL_XIVE_MODE_EXPL); if (rc) { pr_err("Switch to exploitation mode failed with error %lld\n", rc); - return false; + goto err_put; } /* Setup some dummy HV pool VPs */ @@ -634,10 +634,15 @@ bool __init xive_native_init(void) if (!xive_core_init(np, &xive_native_ops, tima, TM_QW3_HV_PHYS, max_prio)) { opal_xive_reset(OPAL_XIVE_MODE_EMU); - return false; + goto err_put; } + of_node_put(np); pr_info("Using %dkB queues\n", 1 << (xive_queue_shift - 10)); return true; + +err_put: + of_node_put(np); + return false; } static bool xive_native_provision_pages(void) diff --git a/arch/powerpc/xmon/ppc.h b/arch/powerpc/xmon/ppc.h index d00f33dcf192..1d98b8dd134e 100644 --- a/arch/powerpc/xmon/ppc.h +++ b/arch/powerpc/xmon/ppc.h @@ -435,8 +435,6 @@ struct powerpc_macro extern const struct powerpc_macro powerpc_macros[]; extern const int powerpc_num_macros; -extern ppc_cpu_t ppc_parse_cpu (ppc_cpu_t, ppc_cpu_t *, const char *); - static inline long ppc_optional_operand_value (const struct powerpc_operand *operand) { diff --git a/arch/powerpc/xmon/spr_access.S b/arch/powerpc/xmon/spr_access.S index 720a52afdd58..c308ddf268fb 100644 --- a/arch/powerpc/xmon/spr_access.S +++ b/arch/powerpc/xmon/spr_access.S @@ -4,12 +4,12 @@ /* unsigned long xmon_mfspr(sprn, default_value) */ _GLOBAL(xmon_mfspr) - PPC_LL r5, .Lmfspr_table@got(r2) + LOAD_REG_ADDR(r5, .Lmfspr_table) b xmon_mxspr /* void xmon_mtspr(sprn, new_value) */ _GLOBAL(xmon_mtspr) - PPC_LL r5, .Lmtspr_table@got(r2) + LOAD_REG_ADDR(r5, .Lmtspr_table) b xmon_mxspr /* diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 26ef3388c24c..f51c882bf902 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -195,7 +195,7 @@ static int do_spu_cmd(void); #ifdef CONFIG_44x static void dump_tlb_44x(void); #endif -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 static void dump_tlb_book3e(void); #endif @@ -288,11 +288,11 @@ Commands:\n\ t print backtrace\n\ x exit monitor and recover\n\ X exit monitor and don't recover\n" -#if defined(CONFIG_PPC64) && !defined(CONFIG_PPC_BOOK3E) +#if defined(CONFIG_PPC_BOOK3S_64) " u dump segment table or SLB\n" #elif defined(CONFIG_PPC_BOOK3S_32) " u dump segment registers\n" -#elif defined(CONFIG_44x) || defined(CONFIG_PPC_BOOK3E) +#elif defined(CONFIG_44x) || defined(CONFIG_PPC_BOOK3E_64) " u dump TLB\n" #endif " U show uptime information\n" @@ -1166,7 +1166,7 @@ cmds(struct pt_regs *excp) case 'u': dump_tlb_44x(); break; -#elif defined(CONFIG_PPC_BOOK3E) +#elif defined(CONFIG_PPC_BOOK3E_64) case 'u': dump_tlb_book3e(); break; @@ -2686,7 +2686,7 @@ static void dump_one_paca(int cpu) DUMP(p, rfi_flush_fallback_area, "%-*px"); #endif DUMP(p, dscr_default, "%#-*llx"); -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 DUMP(p, pgd, "%-*px"); DUMP(p, kernel_pgd, "%-*px"); DUMP(p, tcd_ptr, "%-*px"); @@ -2701,7 +2701,7 @@ static void dump_one_paca(int cpu) DUMP(p, canary, "%#-*lx"); #endif DUMP(p, saved_r1, "%#-*llx"); -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 DUMP(p, trap_save, "%#-*x"); #endif DUMP(p, irq_soft_mask, "%#-*x"); @@ -3823,7 +3823,7 @@ static void dump_tlb_44x(void) } #endif /* CONFIG_44x */ -#ifdef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_BOOK3E_64 static void dump_tlb_book3e(void) { u32 mmucfg, pidmask, lpidmask; @@ -3965,7 +3965,7 @@ static void dump_tlb_book3e(void) } } } -#endif /* CONFIG_PPC_BOOK3E */ +#endif /* CONFIG_PPC_BOOK3E_64 */ static void xmon_init(int enable) { diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 59d18881f35b..e84f2742b6bb 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -45,6 +45,7 @@ config RISCV select ARCH_WANT_FRAME_POINTERS select ARCH_WANT_GENERAL_HUGETLB select ARCH_WANT_HUGE_PMD_SHARE if 64BIT + select ARCH_WANTS_THP_SWAP if HAVE_ARCH_TRANSPARENT_HUGEPAGE select BINFMT_FLAT_NO_DATA_START_OFFSET if !MMU select BUILDTIME_TABLE_SORT if MMU select CLONE_BACKWARDS @@ -52,7 +53,7 @@ config RISCV select COMMON_CLK select CPU_PM if CPU_IDLE select EDAC_SUPPORT - select GENERIC_ARCH_TOPOLOGY if SMP + select GENERIC_ARCH_TOPOLOGY select GENERIC_ATOMIC64 if !64BIT select GENERIC_CLOCKEVENTS_BROADCAST if SMP select GENERIC_EARLY_IOREMAP @@ -309,10 +310,13 @@ config SMP If you don't know what to do here, say N. config NR_CPUS - int "Maximum number of CPUs (2-32)" - range 2 32 + int "Maximum number of CPUs (2-512)" depends on SMP - default "8" + range 2 512 if !SBI_V01 + range 2 32 if SBI_V01 && 32BIT + range 2 64 if SBI_V01 && 64BIT + default "32" if 32BIT + default "64" if 64BIT config HOTPLUG_CPU bool "Support for hot-pluggable CPUs" diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index aed332a9d4ea..05fd5fcf24f9 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -166,6 +166,9 @@ CONFIG_BTRFS_FS=m CONFIG_BTRFS_FS_POSIX_ACL=y CONFIG_AUTOFS4_FS=y CONFIG_OVERLAY_FS=m +CONFIG_ISO9660_FS=y +CONFIG_JOLIET=y +CONFIG_ZISOFS=y CONFIG_MSDOS_FS=y CONFIG_VFAT_FS=y CONFIG_TMPFS=y diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c index 0be8a2403212..87455d12970f 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -92,10 +92,10 @@ int riscv_of_parent_hartid(struct device_node *node, unsigned long *hartid) */ static struct riscv_isa_ext_data isa_ext_arr[] = { __RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF), + __RISCV_ISA_EXT_DATA(sstc, RISCV_ISA_EXT_SSTC), __RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT), __RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM), __RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE), - __RISCV_ISA_EXT_DATA(sstc, RISCV_ISA_EXT_SSTC), __RISCV_ISA_EXT_DATA("", RISCV_ISA_EXT_MAX), }; diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index ceb9ebab6558..b0c63e8e867e 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -105,7 +105,7 @@ static int __init compat_mode_detect(void) csr_write(CSR_STATUS, tmp); pr_info("riscv: ELF compat mode %s", - compat_mode_supported ? "supported" : "failed"); + compat_mode_supported ? "supported" : "unsupported"); return 0; } diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index a752c7b41683..3373df413c88 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -49,6 +49,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) unsigned int curr_cpuid; curr_cpuid = smp_processor_id(); + store_cpu_topology(curr_cpuid); numa_store_cpu_info(curr_cpuid); numa_add_cpu(curr_cpuid); @@ -162,9 +163,9 @@ asmlinkage __visible void smp_callin(void) mmgrab(mm); current->active_mm = mm; + store_cpu_topology(curr_cpuid); notify_cpu_starting(curr_cpuid); numa_add_cpu(curr_cpuid); - update_siblings_masks(curr_cpuid); set_cpu_online(curr_cpuid, 1); /* diff --git a/arch/riscv/kvm/vcpu_insn.c b/arch/riscv/kvm/vcpu_insn.c index 7eb90a47b571..0bb52761a3f7 100644 --- a/arch/riscv/kvm/vcpu_insn.c +++ b/arch/riscv/kvm/vcpu_insn.c @@ -191,7 +191,6 @@ void kvm_riscv_vcpu_wfi(struct kvm_vcpu *vcpu) kvm_vcpu_srcu_read_unlock(vcpu); kvm_vcpu_halt(vcpu); kvm_vcpu_srcu_read_lock(vcpu); - kvm_clear_request(KVM_REQ_UNHALT, vcpu); } } diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index bc48fe82d949..6e7f01ca53e6 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -10,11 +10,14 @@ #include #include #include +#include #include "decompressor.h" #include "boot.h" #include "uv.h" unsigned long __bootdata_preserved(__kaslr_offset); +unsigned long __bootdata_preserved(__abs_lowcore); +unsigned long __bootdata_preserved(__memcpy_real_area); unsigned long __bootdata(__amode31_base); unsigned long __bootdata_preserved(VMALLOC_START); unsigned long __bootdata_preserved(VMALLOC_END); @@ -180,7 +183,10 @@ static void setup_kernel_memory_layout(void) /* force vmalloc and modules below kasan shadow */ vmax = min(vmax, KASAN_SHADOW_START); #endif - MODULES_END = vmax; + __memcpy_real_area = round_down(vmax - PAGE_SIZE, PAGE_SIZE); + __abs_lowcore = round_down(__memcpy_real_area - ABS_LOWCORE_MAP_SIZE, + sizeof(struct lowcore)); + MODULES_END = round_down(__abs_lowcore, _SEGMENT_SIZE); MODULES_VADDR = MODULES_END - MODULES_LEN; VMALLOC_END = MODULES_VADDR; diff --git a/arch/s390/include/asm/abs_lowcore.h b/arch/s390/include/asm/abs_lowcore.h new file mode 100644 index 000000000000..4c61b14ee928 --- /dev/null +++ b/arch/s390/include/asm/abs_lowcore.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_S390_ABS_LOWCORE_H +#define _ASM_S390_ABS_LOWCORE_H + +#include + +#define ABS_LOWCORE_MAP_SIZE (NR_CPUS * sizeof(struct lowcore)) + +extern unsigned long __abs_lowcore; +extern bool abs_lowcore_mapped; + +struct lowcore *get_abs_lowcore(unsigned long *flags); +void put_abs_lowcore(struct lowcore *lc, unsigned long flags); +int abs_lowcore_map(int cpu, struct lowcore *lc, bool alloc); +void abs_lowcore_unmap(int cpu); + +#endif /* _ASM_S390_ABS_LOWCORE_H */ diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h index d4e90f2ba77e..bd1596810cc1 100644 --- a/arch/s390/include/asm/ccwdev.h +++ b/arch/s390/include/asm/ccwdev.h @@ -214,7 +214,6 @@ extern struct ccw_device *ccw_device_create_console(struct ccw_driver *); extern void ccw_device_destroy_console(struct ccw_device *); extern int ccw_device_enable_console(struct ccw_device *); extern void ccw_device_wait_idle(struct ccw_device *); -extern int ccw_device_force_console(struct ccw_device *); extern void *ccw_device_dma_zalloc(struct ccw_device *cdev, size_t size); extern void ccw_device_dma_free(struct ccw_device *cdev, diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h index 267a8f88e143..adf7d8cdac7e 100644 --- a/arch/s390/include/asm/ctl_reg.h +++ b/arch/s390/include/asm/ctl_reg.h @@ -95,7 +95,8 @@ union ctlreg0 { Interruption-Filtering Override */ unsigned long : 3; unsigned long ccc : 1; /* Cryptography counter control */ - unsigned long : 18; + unsigned long pec : 1; /* PAI extension control */ + unsigned long : 17; unsigned long : 3; unsigned long lap : 1; /* Low-address-protection control */ unsigned long : 4; diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h index 26fe5e535728..8aa1f6530a3e 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -203,7 +203,9 @@ struct lowcore { __u8 pad_0x1400[0x1500-0x1400]; /* 0x1400 */ /* Cryptography-counter designation */ __u64 ccd; /* 0x1500 */ - __u8 pad_0x1508[0x1800-0x1508]; /* 0x1508 */ + /* AI-extension counter designation */ + __u64 aicd; /* 0x1508 */ + __u8 pad_0x1510[0x1800-0x1510]; /* 0x1510 */ /* Transaction abort diagnostic block */ struct pgm_tdb pgm_tdb; /* 0x1800 */ diff --git a/arch/s390/include/asm/maccess.h b/arch/s390/include/asm/maccess.h new file mode 100644 index 000000000000..c7fa838cf6b9 --- /dev/null +++ b/arch/s390/include/asm/maccess.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_S390_MACCESS_H +#define __ASM_S390_MACCESS_H + +#include + +struct iov_iter; + +extern unsigned long __memcpy_real_area; +void memcpy_real_init(void); +size_t memcpy_real_iter(struct iov_iter *iter, unsigned long src, size_t count); +int memcpy_real(void *dest, unsigned long src, size_t count); +#ifdef CONFIG_CRASH_DUMP +int copy_oldmem_kernel(void *dst, unsigned long src, size_t count); +#endif + +#endif /* __ASM_S390_MACCESS_H */ diff --git a/arch/s390/include/asm/os_info.h b/arch/s390/include/asm/os_info.h index 85248d8fee0c..0d1c74a7a650 100644 --- a/arch/s390/include/asm/os_info.h +++ b/arch/s390/include/asm/os_info.h @@ -41,20 +41,6 @@ u32 os_info_csum(struct os_info *os_info); #ifdef CONFIG_CRASH_DUMP void *os_info_old_entry(int nr, unsigned long *size); -size_t copy_oldmem_iter(struct iov_iter *iter, unsigned long src, size_t count); - -static inline int copy_oldmem_kernel(void *dst, unsigned long src, size_t count) -{ - struct iov_iter iter; - struct kvec kvec; - - kvec.iov_base = dst; - kvec.iov_len = count; - iov_iter_kvec(&iter, WRITE, &kvec, 1, count); - if (copy_oldmem_iter(&iter, src, count) < count) - return -EFAULT; - return 0; -} #else static inline void *os_info_old_entry(int nr, unsigned long *size) { diff --git a/arch/s390/include/asm/pai.h b/arch/s390/include/asm/pai.h index 5b7e33ac6f0b..1a8a6b15d121 100644 --- a/arch/s390/include/asm/pai.h +++ b/arch/s390/include/asm/pai.h @@ -17,7 +17,9 @@ struct qpaci_info_block { struct { u64 : 8; u64 num_cc : 8; /* # of supported crypto counters */ - u64 : 48; + u64 : 9; + u64 num_nnpa : 7; /* # of supported NNPA counters */ + u64 : 32; }; }; @@ -42,6 +44,8 @@ static inline int qpaci(struct qpaci_info_block *info) #define PAI_CRYPTO_BASE 0x1000 /* First event number */ #define PAI_CRYPTO_MAXCTR 256 /* Max # of event counters */ #define PAI_CRYPTO_KERNEL_OFFSET 2048 +#define PAI_NNPA_BASE 0x1800 /* First event number */ +#define PAI_NNPA_MAXCTR 128 /* Max # of event counters */ DECLARE_STATIC_KEY_FALSE(pai_key); diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index 7b4cdadbc023..108e732d7b14 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -117,7 +117,6 @@ struct zpci_bus { struct zpci_dev { struct zpci_bus *zbus; struct list_head entry; /* list of all zpci_devices, needed for hotplug, etc. */ - struct list_head bus_next; struct kref kref; struct hotplug_slot hotplug_slot; diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index f019df19884d..f1cb9391190d 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1777,6 +1777,10 @@ static inline swp_entry_t __swp_entry(unsigned long type, unsigned long offset) extern int vmem_add_mapping(unsigned long start, unsigned long size); extern void vmem_remove_mapping(unsigned long start, unsigned long size); +extern int __vmem_map_4k_page(unsigned long addr, unsigned long phys, pgprot_t prot, bool alloc); +extern int vmem_map_4k_page(unsigned long addr, unsigned long phys, pgprot_t prot); +extern void vmem_unmap_4k_page(unsigned long addr); +extern pte_t *vmem_get_alloc_pte(unsigned long addr, bool alloc); extern int s390_enable_sie(void); extern int s390_enable_skey(void); extern void s390_reset_cmma(struct mm_struct *mm); diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index bd66f8e34949..4eb9b7875e13 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -306,23 +306,6 @@ static __always_inline void __noreturn disabled_wait(void) #define ARCH_LOW_ADDRESS_LIMIT 0x7fffffffUL -extern int memcpy_real(void *, unsigned long, size_t); -extern void memcpy_absolute(void *, void *, size_t); - -#define put_abs_lowcore(member, x) do { \ - unsigned long __abs_address = offsetof(struct lowcore, member); \ - __typeof__(((struct lowcore *)0)->member) __tmp = (x); \ - \ - memcpy_absolute(__va(__abs_address), &__tmp, sizeof(__tmp)); \ -} while (0) - -#define get_abs_lowcore(x, member) do { \ - unsigned long __abs_address = offsetof(struct lowcore, member); \ - __typeof__(((struct lowcore *)0)->member) *__ptr = &(x); \ - \ - memcpy_absolute(__ptr, __va(__abs_address), sizeof(*__ptr)); \ -} while (0) - extern int s390_isolate_bp(void); extern int s390_isolate_bp_guest(void); diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h index 7f5d4763357b..73ed2781073b 100644 --- a/arch/s390/include/asm/smp.h +++ b/arch/s390/include/asm/smp.h @@ -30,7 +30,8 @@ extern void smp_emergency_stop(void); extern int smp_find_processor_id(u16 address); extern int smp_store_status(int cpu); -extern void smp_save_dump_cpus(void); +extern void smp_save_dump_ipl_cpu(void); +extern void smp_save_dump_secondary_cpus(void); extern void smp_yield_cpu(int cpu); extern void smp_cpu_set_polarization(int cpu, int val); extern int smp_cpu_get_polarization(int cpu); @@ -58,6 +59,7 @@ static inline void smp_cpus_done(unsigned int max_cpus) { } +extern int smp_reinit_ipl_cpu(void); extern int smp_rescan_cpus(void); extern void __noreturn cpu_die(void); extern void __cpu_die(unsigned int cpu); diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 3cbfa9fddd9a..70b776863f84 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -40,7 +40,7 @@ obj-y += sysinfo.o lgr.o os_info.o machine_kexec.o obj-y += runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o obj-y += entry.o reipl.o relocate_kernel.o kdebugfs.o alternative.o obj-y += nospec-branch.o ipl_vmparm.o machine_kexec_reloc.o unwind_bc.o -obj-y += smp.o text_amode31.o stacktrace.o +obj-y += smp.o text_amode31.o stacktrace.o abs_lowcore.o extra-y += head64.o vmlinux.lds @@ -72,7 +72,7 @@ obj-$(CONFIG_IMA_SECURE_AND_OR_TRUSTED_BOOT) += ima_arch.o obj-$(CONFIG_PERF_EVENTS) += perf_event.o perf_cpum_cf_common.o obj-$(CONFIG_PERF_EVENTS) += perf_cpum_cf.o perf_cpum_sf.o obj-$(CONFIG_PERF_EVENTS) += perf_cpum_cf_events.o perf_regs.o -obj-$(CONFIG_PERF_EVENTS) += perf_pai_crypto.o +obj-$(CONFIG_PERF_EVENTS) += perf_pai_crypto.o perf_pai_ext.o obj-$(CONFIG_TRACEPOINTS) += trace.o obj-$(findstring y, $(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) $(CONFIG_PGSTE)) += uv.o diff --git a/arch/s390/kernel/abs_lowcore.c b/arch/s390/kernel/abs_lowcore.c new file mode 100644 index 000000000000..fb92e8ed0525 --- /dev/null +++ b/arch/s390/kernel/abs_lowcore.c @@ -0,0 +1,95 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +#define ABS_LOWCORE_UNMAPPED 1 +#define ABS_LOWCORE_LAP_ON 2 +#define ABS_LOWCORE_IRQS_ON 4 + +unsigned long __bootdata_preserved(__abs_lowcore); +bool __ro_after_init abs_lowcore_mapped; + +int abs_lowcore_map(int cpu, struct lowcore *lc, bool alloc) +{ + unsigned long addr = __abs_lowcore + (cpu * sizeof(struct lowcore)); + unsigned long phys = __pa(lc); + int rc, i; + + for (i = 0; i < LC_PAGES; i++) { + rc = __vmem_map_4k_page(addr, phys, PAGE_KERNEL, alloc); + if (rc) { + /* + * Do not unmap allocated page tables in case the + * allocation was not requested. In such a case the + * request is expected coming from an atomic context, + * while the unmap attempt might sleep. + */ + if (alloc) { + for (--i; i >= 0; i--) { + addr -= PAGE_SIZE; + vmem_unmap_4k_page(addr); + } + } + return rc; + } + addr += PAGE_SIZE; + phys += PAGE_SIZE; + } + return 0; +} + +void abs_lowcore_unmap(int cpu) +{ + unsigned long addr = __abs_lowcore + (cpu * sizeof(struct lowcore)); + int i; + + for (i = 0; i < LC_PAGES; i++) { + vmem_unmap_4k_page(addr); + addr += PAGE_SIZE; + } +} + +struct lowcore *get_abs_lowcore(unsigned long *flags) +{ + unsigned long irq_flags; + union ctlreg0 cr0; + int cpu; + + *flags = 0; + cpu = get_cpu(); + if (abs_lowcore_mapped) { + return ((struct lowcore *)__abs_lowcore) + cpu; + } else { + if (cpu != 0) + panic("Invalid unmapped absolute lowcore access\n"); + local_irq_save(irq_flags); + if (!irqs_disabled_flags(irq_flags)) + *flags |= ABS_LOWCORE_IRQS_ON; + __ctl_store(cr0.val, 0, 0); + if (cr0.lap) { + *flags |= ABS_LOWCORE_LAP_ON; + __ctl_clear_bit(0, 28); + } + *flags |= ABS_LOWCORE_UNMAPPED; + return lowcore_ptr[0]; + } +} + +void put_abs_lowcore(struct lowcore *lc, unsigned long flags) +{ + if (abs_lowcore_mapped) { + if (flags) + panic("Invalid mapped absolute lowcore release\n"); + } else { + if (smp_processor_id() != 0) + panic("Invalid mapped absolute lowcore access\n"); + if (!(flags & ABS_LOWCORE_UNMAPPED)) + panic("Invalid unmapped absolute lowcore release\n"); + if (flags & ABS_LOWCORE_LAP_ON) + __ctl_set_bit(0, 28); + if (flags & ABS_LOWCORE_IRQS_ON) + local_irq_enable(); + } + put_cpu(); +} diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index bad8f47fc5d6..dd74fe664ed1 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -21,6 +21,7 @@ #include #include #include +#include #define PTR_ADD(x, y) (((char *) (x)) + ((unsigned long) (y))) #define PTR_SUB(x, y) (((char *) (x)) - ((unsigned long) (y))) @@ -53,8 +54,6 @@ struct save_area { }; static LIST_HEAD(dump_save_areas); -static DEFINE_MUTEX(memcpy_real_mutex); -static char memcpy_real_buf[PAGE_SIZE]; /* * Allocate a save area @@ -116,27 +115,7 @@ void __init save_area_add_vxrs(struct save_area *sa, __vector128 *vxrs) memcpy(sa->vxrs_high, vxrs + 16, 16 * sizeof(__vector128)); } -static size_t copy_to_iter_real(struct iov_iter *iter, unsigned long src, size_t count) -{ - size_t len, copied, res = 0; - - mutex_lock(&memcpy_real_mutex); - while (count) { - len = min(PAGE_SIZE, count); - if (memcpy_real(memcpy_real_buf, src, len)) - break; - copied = copy_to_iter(memcpy_real_buf, len, iter); - count -= copied; - src += copied; - res += copied; - if (copied < len) - break; - } - mutex_unlock(&memcpy_real_mutex); - return res; -} - -size_t copy_oldmem_iter(struct iov_iter *iter, unsigned long src, size_t count) +static size_t copy_oldmem_iter(struct iov_iter *iter, unsigned long src, size_t count) { size_t len, copied, res = 0; @@ -156,7 +135,7 @@ size_t copy_oldmem_iter(struct iov_iter *iter, unsigned long src, size_t count) } else { len = count; } - copied = copy_to_iter_real(iter, src, len); + copied = memcpy_real_iter(iter, src, len); } count -= copied; src += copied; @@ -167,6 +146,19 @@ size_t copy_oldmem_iter(struct iov_iter *iter, unsigned long src, size_t count) return res; } +int copy_oldmem_kernel(void *dst, unsigned long src, size_t count) +{ + struct iov_iter iter; + struct kvec kvec; + + kvec.iov_base = dst; + kvec.iov_len = count; + iov_iter_kvec(&iter, WRITE, &kvec, 1, count); + if (copy_oldmem_iter(&iter, src, count) < count) + return -EFAULT; + return 0; +} + /* * Copy one page from "oldmem" */ diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index 4331c7e6e1c0..d7a82066a638 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -250,7 +250,7 @@ static debug_info_t *debug_info_alloc(const char *name, int pages_per_area, rc->level = level; rc->buf_size = buf_size; rc->entry_size = sizeof(debug_entry_t) + buf_size; - strlcpy(rc->name, name, sizeof(rc->name)); + strscpy(rc->name, name, sizeof(rc->name)); memset(rc->views, 0, DEBUG_MAX_VIEWS * sizeof(struct debug_view *)); memset(rc->debugfs_entries, 0, DEBUG_MAX_VIEWS * sizeof(struct dentry *)); refcount_set(&(rc->ref_count), 0); diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 432c8c987256..6030fdd6997b 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -267,7 +267,7 @@ char __bootdata(early_command_line)[COMMAND_LINE_SIZE]; static void __init setup_boot_command_line(void) { /* copy arch command line */ - strlcpy(boot_command_line, early_command_line, COMMAND_LINE_SIZE); + strscpy(boot_command_line, early_command_line, COMMAND_LINE_SIZE); } static void __init check_image_bootable(void) diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 1cc85b8ff42e..325cbf69ebbd 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include #include @@ -1642,12 +1643,16 @@ static struct shutdown_action __refdata dump_action = { static void dump_reipl_run(struct shutdown_trigger *trigger) { unsigned long ipib = (unsigned long) reipl_block_actual; + struct lowcore *abs_lc; + unsigned long flags; unsigned int csum; csum = (__force unsigned int) csum_partial(reipl_block_actual, reipl_block_actual->hdr.len, 0); - put_abs_lowcore(ipib, ipib); - put_abs_lowcore(ipib_checksum, csum); + abs_lc = get_abs_lowcore(&flags); + abs_lc->ipib = ipib; + abs_lc->ipib_checksum = csum; + put_abs_lowcore(abs_lc, flags); dump_run(trigger); } diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index ab761c008f98..4579b42286d5 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -222,13 +223,18 @@ void machine_kexec_cleanup(struct kimage *image) void arch_crash_save_vmcoreinfo(void) { + struct lowcore *abs_lc; + unsigned long flags; + VMCOREINFO_SYMBOL(lowcore_ptr); VMCOREINFO_SYMBOL(high_memory); VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS); vmcoreinfo_append_str("SAMODE31=%lx\n", __samode31); vmcoreinfo_append_str("EAMODE31=%lx\n", __eamode31); vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); - put_abs_lowcore(vmcore_info, paddr_vmcoreinfo_note()); + abs_lc = get_abs_lowcore(&flags); + abs_lc->vmcore_info = paddr_vmcoreinfo_note(); + put_abs_lowcore(abs_lc, flags); } void machine_shutdown(void) diff --git a/arch/s390/kernel/os_info.c b/arch/s390/kernel/os_info.c index 1acc2e05d70f..ec0bd9457e90 100644 --- a/arch/s390/kernel/os_info.c +++ b/arch/s390/kernel/os_info.c @@ -13,8 +13,9 @@ #include #include #include -#include +#include #include +#include #include /* @@ -57,13 +58,16 @@ void os_info_entry_add(int nr, void *ptr, u64 size) */ void __init os_info_init(void) { - void *ptr = &os_info; + struct lowcore *abs_lc; + unsigned long flags; os_info.version_major = OS_INFO_VERSION_MAJOR; os_info.version_minor = OS_INFO_VERSION_MINOR; os_info.magic = OS_INFO_MAGIC; os_info.csum = os_info_csum(&os_info); - put_abs_lowcore(os_info, __pa(ptr)); + abs_lc = get_abs_lowcore(&flags); + abs_lc->os_info = __pa(&os_info); + put_abs_lowcore(abs_lc, flags); } #ifdef CONFIG_CRASH_DUMP diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c new file mode 100644 index 000000000000..d5c7c1e30c17 --- /dev/null +++ b/arch/s390/kernel/perf_pai_ext.c @@ -0,0 +1,671 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Performance event support - Processor Activity Instrumentation Extension + * Facility + * + * Copyright IBM Corp. 2022 + * Author(s): Thomas Richter + */ +#define KMSG_COMPONENT "pai_ext" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +#define PAIE1_CB_SZ 0x200 /* Size of PAIE1 control block */ +#define PAIE1_CTRBLOCK_SZ 0x400 /* Size of PAIE1 counter blocks */ + +static debug_info_t *paiext_dbg; +static unsigned int paiext_cnt; /* Extracted with QPACI instruction */ + +enum paiext_mode { + PAI_MODE_NONE, + PAI_MODE_SAMPLING, + PAI_MODE_COUNTER, +}; + +struct pai_userdata { + u16 num; + u64 value; +} __packed; + +/* Create the PAI extension 1 control block area. + * The PAI extension control block 1 is pointed to by lowcore + * address 0x1508 for each CPU. This control block is 512 bytes in size + * and requires a 512 byte boundary alignment. + */ +struct paiext_cb { /* PAI extension 1 control block */ + u64 header; /* Not used */ + u64 reserved1; + u64 acc; /* Addr to analytics counter control block */ + u8 reserved2[488]; +} __packed; + +struct paiext_map { + unsigned long *area; /* Area for CPU to store counters */ + struct pai_userdata *save; /* Area to store non-zero counters */ + enum paiext_mode mode; /* Type of event */ + unsigned int active_events; /* # of PAI Extension users */ + unsigned int refcnt; + struct perf_event *event; /* Perf event for sampling */ + struct paiext_cb *paiext_cb; /* PAI extension control block area */ +}; + +struct paiext_mapptr { + struct paiext_map *mapptr; +}; + +static struct paiext_root { /* Anchor to per CPU data */ + int refcnt; /* Overall active events */ + struct paiext_mapptr __percpu *mapptr; +} paiext_root; + +/* Free per CPU data when the last event is removed. */ +static void paiext_root_free(void) +{ + if (!--paiext_root.refcnt) { + free_percpu(paiext_root.mapptr); + paiext_root.mapptr = NULL; + } +} + +/* On initialization of first event also allocate per CPU data dynamically. + * Start with an array of pointers, the array size is the maximum number of + * CPUs possible, which might be larger than the number of CPUs currently + * online. + */ +static int paiext_root_alloc(void) +{ + if (++paiext_root.refcnt == 1) { + /* The memory is already zeroed. */ + paiext_root.mapptr = alloc_percpu(struct paiext_mapptr); + if (!paiext_root.mapptr) { + /* Returing without refcnt adjustment is ok. The + * error code is handled by paiext_alloc() which + * decrements refcnt when an event can not be + * created. + */ + return -ENOMEM; + } + } + return 0; +} + +/* Protects against concurrent increment of sampler and counter member + * increments at the same time and prohibits concurrent execution of + * counting and sampling events. + * Ensures that analytics counter block is deallocated only when the + * sampling and counting on that cpu is zero. + * For details see paiext_alloc(). + */ +static DEFINE_MUTEX(paiext_reserve_mutex); + +/* Free all memory allocated for event counting/sampling setup */ +static void paiext_free(struct paiext_mapptr *mp) +{ + kfree(mp->mapptr->area); + kfree(mp->mapptr->paiext_cb); + kvfree(mp->mapptr->save); + kfree(mp->mapptr); + mp->mapptr = NULL; +} + +/* Release the PMU if event is the last perf event */ +static void paiext_event_destroy(struct perf_event *event) +{ + struct paiext_mapptr *mp = per_cpu_ptr(paiext_root.mapptr, event->cpu); + struct paiext_map *cpump = mp->mapptr; + + mutex_lock(&paiext_reserve_mutex); + cpump->event = NULL; + if (!--cpump->refcnt) /* Last reference gone */ + paiext_free(mp); + paiext_root_free(); + mutex_unlock(&paiext_reserve_mutex); + debug_sprintf_event(paiext_dbg, 4, "%s cpu %d mapptr %p\n", __func__, + event->cpu, mp->mapptr); + +} + +/* Used to avoid races in checking concurrent access of counting and + * sampling for pai_extension events. + * + * Only one instance of event pai_ext/NNPA_ALL/ for sampling is + * allowed and when this event is running, no counting event is allowed. + * Several counting events are allowed in parallel, but no sampling event + * is allowed while one (or more) counting events are running. + * + * This function is called in process context and it is safe to block. + * When the event initialization functions fails, no other call back will + * be invoked. + * + * Allocate the memory for the event. + */ +static int paiext_alloc(struct perf_event_attr *a, struct perf_event *event) +{ + struct paiext_mapptr *mp; + struct paiext_map *cpump; + int rc; + + mutex_lock(&paiext_reserve_mutex); + + rc = paiext_root_alloc(); + if (rc) + goto unlock; + + mp = per_cpu_ptr(paiext_root.mapptr, event->cpu); + cpump = mp->mapptr; + if (!cpump) { /* Paiext_map allocated? */ + rc = -ENOMEM; + cpump = kzalloc(sizeof(*cpump), GFP_KERNEL); + if (!cpump) + goto unlock; + + /* Allocate memory for counter area and counter extraction. + * These are + * - a 512 byte block and requires 512 byte boundary alignment. + * - a 1KB byte block and requires 1KB boundary alignment. + * Only the first counting event has to allocate the area. + * + * Note: This works with commit 59bb47985c1d by default. + * Backporting this to kernels without this commit might + * need adjustment. + */ + mp->mapptr = cpump; + cpump->area = kzalloc(PAIE1_CTRBLOCK_SZ, GFP_KERNEL); + cpump->paiext_cb = kzalloc(PAIE1_CB_SZ, GFP_KERNEL); + cpump->save = kvmalloc_array(paiext_cnt + 1, + sizeof(struct pai_userdata), + GFP_KERNEL); + if (!cpump->save || !cpump->area || !cpump->paiext_cb) { + paiext_free(mp); + goto unlock; + } + cpump->mode = a->sample_period ? PAI_MODE_SAMPLING + : PAI_MODE_COUNTER; + } else { + /* Multiple invocation, check whats active. + * Supported are multiple counter events or only one sampling + * event concurrently at any one time. + */ + if (cpump->mode == PAI_MODE_SAMPLING || + (cpump->mode == PAI_MODE_COUNTER && a->sample_period)) { + rc = -EBUSY; + goto unlock; + } + } + + rc = 0; + cpump->event = event; + ++cpump->refcnt; + +unlock: + if (rc) { + /* Error in allocation of event, decrement anchor. Since + * the event in not created, its destroy() function is never + * invoked. Adjust the reference counter for the anchor. + */ + paiext_root_free(); + } + mutex_unlock(&paiext_reserve_mutex); + /* If rc is non-zero, no increment of counter/sampler was done. */ + return rc; +} + +/* The PAI extension 1 control block supports up to 128 entries. Return + * the index within PAIE1_CB given the event number. Also validate event + * number. + */ +static int paiext_event_valid(struct perf_event *event) +{ + u64 cfg = event->attr.config; + + if (cfg >= PAI_NNPA_BASE && cfg <= PAI_NNPA_BASE + paiext_cnt) { + /* Offset NNPA in paiext_cb */ + event->hw.config_base = offsetof(struct paiext_cb, acc); + return 0; + } + return -EINVAL; +} + +/* Might be called on different CPU than the one the event is intended for. */ +static int paiext_event_init(struct perf_event *event) +{ + struct perf_event_attr *a = &event->attr; + int rc; + + /* PMU pai_ext registered as PERF_TYPE_RAW, check event type */ + if (a->type != PERF_TYPE_RAW && event->pmu->type != a->type) + return -ENOENT; + /* PAI extension event must be valid and in supported range */ + rc = paiext_event_valid(event); + if (rc) + return rc; + /* Allow only CPU wide operation, no process context for now. */ + if (event->hw.target || event->cpu == -1) + return -ENOENT; + /* Allow only event NNPA_ALL for sampling. */ + if (a->sample_period && a->config != PAI_NNPA_BASE) + return -EINVAL; + /* Prohibit exclude_user event selection */ + if (a->exclude_user) + return -EINVAL; + + rc = paiext_alloc(a, event); + if (rc) + return rc; + event->hw.last_tag = 0; + event->destroy = paiext_event_destroy; + + if (a->sample_period) { + a->sample_period = 1; + a->freq = 0; + /* Register for paicrypt_sched_task() to be called */ + event->attach_state |= PERF_ATTACH_SCHED_CB; + /* Add raw data which are the memory mapped counters */ + a->sample_type |= PERF_SAMPLE_RAW; + /* Turn off inheritance */ + a->inherit = 0; + } + + return 0; +} + +static u64 paiext_getctr(struct paiext_map *cpump, int nr) +{ + return cpump->area[nr]; +} + +/* Read the counter values. Return value from location in buffer. For event + * NNPA_ALL sum up all events. + */ +static u64 paiext_getdata(struct perf_event *event) +{ + struct paiext_mapptr *mp = this_cpu_ptr(paiext_root.mapptr); + struct paiext_map *cpump = mp->mapptr; + u64 sum = 0; + int i; + + if (event->attr.config != PAI_NNPA_BASE) + return paiext_getctr(cpump, event->attr.config - PAI_NNPA_BASE); + + for (i = 1; i <= paiext_cnt; i++) + sum += paiext_getctr(cpump, i); + + return sum; +} + +static u64 paiext_getall(struct perf_event *event) +{ + return paiext_getdata(event); +} + +static void paiext_read(struct perf_event *event) +{ + u64 prev, new, delta; + + prev = local64_read(&event->hw.prev_count); + new = paiext_getall(event); + local64_set(&event->hw.prev_count, new); + delta = new - prev; + local64_add(delta, &event->count); +} + +static void paiext_start(struct perf_event *event, int flags) +{ + u64 sum; + + if (event->hw.last_tag) + return; + event->hw.last_tag = 1; + sum = paiext_getall(event); /* Get current value */ + local64_set(&event->hw.prev_count, sum); + local64_set(&event->count, 0); +} + +static int paiext_add(struct perf_event *event, int flags) +{ + struct paiext_mapptr *mp = this_cpu_ptr(paiext_root.mapptr); + struct paiext_map *cpump = mp->mapptr; + struct paiext_cb *pcb = cpump->paiext_cb; + + if (++cpump->active_events == 1) { + S390_lowcore.aicd = virt_to_phys(cpump->paiext_cb); + pcb->acc = virt_to_phys(cpump->area) | 0x1; + /* Enable CPU instruction lookup for PAIE1 control block */ + __ctl_set_bit(0, 49); + debug_sprintf_event(paiext_dbg, 4, "%s 1508 %llx acc %llx\n", + __func__, S390_lowcore.aicd, pcb->acc); + } + if (flags & PERF_EF_START && !event->attr.sample_period) { + /* Only counting needs initial counter value */ + paiext_start(event, PERF_EF_RELOAD); + } + event->hw.state = 0; + if (event->attr.sample_period) { + cpump->event = event; + perf_sched_cb_inc(event->pmu); + } + return 0; +} + +static void paiext_stop(struct perf_event *event, int flags) +{ + paiext_read(event); + event->hw.state = PERF_HES_STOPPED; +} + +static void paiext_del(struct perf_event *event, int flags) +{ + struct paiext_mapptr *mp = this_cpu_ptr(paiext_root.mapptr); + struct paiext_map *cpump = mp->mapptr; + struct paiext_cb *pcb = cpump->paiext_cb; + + if (event->attr.sample_period) + perf_sched_cb_dec(event->pmu); + if (!event->attr.sample_period) { + /* Only counting needs to read counter */ + paiext_stop(event, PERF_EF_UPDATE); + } + if (--cpump->active_events == 0) { + /* Disable CPU instruction lookup for PAIE1 control block */ + __ctl_clear_bit(0, 49); + pcb->acc = 0; + S390_lowcore.aicd = 0; + debug_sprintf_event(paiext_dbg, 4, "%s 1508 %llx acc %llx\n", + __func__, S390_lowcore.aicd, pcb->acc); + } +} + +/* Create raw data and save it in buffer. Returns number of bytes copied. + * Saves only positive counter entries of the form + * 2 bytes: Number of counter + * 8 bytes: Value of counter + */ +static size_t paiext_copy(struct paiext_map *cpump) +{ + struct pai_userdata *userdata = cpump->save; + int i, outidx = 0; + + for (i = 1; i <= paiext_cnt; i++) { + u64 val = paiext_getctr(cpump, i); + + if (val) { + userdata[outidx].num = i; + userdata[outidx].value = val; + outidx++; + } + } + return outidx * sizeof(*userdata); +} + +/* Write sample when one or more counters values are nonzero. + * + * Note: The function paiext_sched_task() and paiext_push_sample() are not + * invoked after function paiext_del() has been called because of function + * perf_sched_cb_dec(). + * The function paiext_sched_task() and paiext_push_sample() are only + * called when sampling is active. Function perf_sched_cb_inc() + * has been invoked to install function paiext_sched_task() as call back + * to run at context switch time (see paiext_add()). + * + * This causes function perf_event_context_sched_out() and + * perf_event_context_sched_in() to check whether the PMU has installed an + * sched_task() callback. That callback is not active after paiext_del() + * returns and has deleted the event on that CPU. + */ +static int paiext_push_sample(void) +{ + struct paiext_mapptr *mp = this_cpu_ptr(paiext_root.mapptr); + struct paiext_map *cpump = mp->mapptr; + struct perf_event *event = cpump->event; + struct perf_sample_data data; + struct perf_raw_record raw; + struct pt_regs regs; + size_t rawsize; + int overflow; + + rawsize = paiext_copy(cpump); + if (!rawsize) /* No incremented counters */ + return 0; + + /* Setup perf sample */ + memset(®s, 0, sizeof(regs)); + memset(&raw, 0, sizeof(raw)); + memset(&data, 0, sizeof(data)); + perf_sample_data_init(&data, 0, event->hw.last_period); + if (event->attr.sample_type & PERF_SAMPLE_TID) { + data.tid_entry.pid = task_tgid_nr(current); + data.tid_entry.tid = task_pid_nr(current); + } + if (event->attr.sample_type & PERF_SAMPLE_TIME) + data.time = event->clock(); + if (event->attr.sample_type & (PERF_SAMPLE_ID | PERF_SAMPLE_IDENTIFIER)) + data.id = event->id; + if (event->attr.sample_type & PERF_SAMPLE_CPU) + data.cpu_entry.cpu = smp_processor_id(); + if (event->attr.sample_type & PERF_SAMPLE_RAW) { + raw.frag.size = rawsize; + raw.frag.data = cpump->save; + raw.size = raw.frag.size; + data.raw = &raw; + } + + overflow = perf_event_overflow(event, &data, ®s); + perf_event_update_userpage(event); + /* Clear lowcore area after read */ + memset(cpump->area, 0, PAIE1_CTRBLOCK_SZ); + return overflow; +} + +/* Called on schedule-in and schedule-out. No access to event structure, + * but for sampling only event NNPA_ALL is allowed. + */ +static void paiext_sched_task(struct perf_event_context *ctx, bool sched_in) +{ + /* We started with a clean page on event installation. So read out + * results on schedule_out and if page was dirty, clear values. + */ + if (!sched_in) + paiext_push_sample(); +} + +/* Attribute definitions for pai extension1 interface. As with other CPU + * Measurement Facilities, there is one attribute per mapped counter. + * The number of mapped counters may vary per machine generation. Use + * the QUERY PROCESSOR ACTIVITY COUNTER INFORMATION (QPACI) instruction + * to determine the number of mapped counters. The instructions returns + * a positive number, which is the highest number of supported counters. + * All counters less than this number are also supported, there are no + * holes. A returned number of zero means no support for mapped counters. + * + * The identification of the counter is a unique number. The chosen range + * is 0x1800 + offset in mapped kernel page. + * All CPU Measurement Facility counters identifiers must be unique and + * the numbers from 0 to 496 are already used for the CPU Measurement + * Counter facility. Number 0x1000 to 0x103e are used for PAI cryptography + * counters. + * Numbers 0xb0000, 0xbc000 and 0xbd000 are already + * used for the CPU Measurement Sampling facility. + */ +PMU_FORMAT_ATTR(event, "config:0-63"); + +static struct attribute *paiext_format_attr[] = { + &format_attr_event.attr, + NULL, +}; + +static struct attribute_group paiext_events_group = { + .name = "events", + .attrs = NULL, /* Filled in attr_event_init() */ +}; + +static struct attribute_group paiext_format_group = { + .name = "format", + .attrs = paiext_format_attr, +}; + +static const struct attribute_group *paiext_attr_groups[] = { + &paiext_events_group, + &paiext_format_group, + NULL, +}; + +/* Performance monitoring unit for mapped counters */ +static struct pmu paiext = { + .task_ctx_nr = perf_invalid_context, + .event_init = paiext_event_init, + .add = paiext_add, + .del = paiext_del, + .start = paiext_start, + .stop = paiext_stop, + .read = paiext_read, + .sched_task = paiext_sched_task, + .attr_groups = paiext_attr_groups, +}; + +/* List of symbolic PAI extension 1 NNPA counter names. */ +static const char * const paiext_ctrnames[] = { + [0] = "NNPA_ALL", + [1] = "NNPA_ADD", + [2] = "NNPA_SUB", + [3] = "NNPA_MUL", + [4] = "NNPA_DIV", + [5] = "NNPA_MIN", + [6] = "NNPA_MAX", + [7] = "NNPA_LOG", + [8] = "NNPA_EXP", + [9] = "NNPA_IBM_RESERVED_9", + [10] = "NNPA_RELU", + [11] = "NNPA_TANH", + [12] = "NNPA_SIGMOID", + [13] = "NNPA_SOFTMAX", + [14] = "NNPA_BATCHNORM", + [15] = "NNPA_MAXPOOL2D", + [16] = "NNPA_AVGPOOL2D", + [17] = "NNPA_LSTMACT", + [18] = "NNPA_GRUACT", + [19] = "NNPA_CONVOLUTION", + [20] = "NNPA_MATMUL_OP", + [21] = "NNPA_MATMUL_OP_BCAST23", + [22] = "NNPA_SMALLBATCH", + [23] = "NNPA_LARGEDIM", + [24] = "NNPA_SMALLTENSOR", + [25] = "NNPA_1MFRAME", + [26] = "NNPA_2GFRAME", + [27] = "NNPA_ACCESSEXCEPT", +}; + +static void __init attr_event_free(struct attribute **attrs, int num) +{ + struct perf_pmu_events_attr *pa; + struct device_attribute *dap; + int i; + + for (i = 0; i < num; i++) { + dap = container_of(attrs[i], struct device_attribute, attr); + pa = container_of(dap, struct perf_pmu_events_attr, attr); + kfree(pa); + } + kfree(attrs); +} + +static int __init attr_event_init_one(struct attribute **attrs, int num) +{ + struct perf_pmu_events_attr *pa; + + pa = kzalloc(sizeof(*pa), GFP_KERNEL); + if (!pa) + return -ENOMEM; + + sysfs_attr_init(&pa->attr.attr); + pa->id = PAI_NNPA_BASE + num; + pa->attr.attr.name = paiext_ctrnames[num]; + pa->attr.attr.mode = 0444; + pa->attr.show = cpumf_events_sysfs_show; + pa->attr.store = NULL; + attrs[num] = &pa->attr.attr; + return 0; +} + +/* Create PMU sysfs event attributes on the fly. */ +static int __init attr_event_init(void) +{ + struct attribute **attrs; + int ret, i; + + attrs = kmalloc_array(ARRAY_SIZE(paiext_ctrnames) + 1, sizeof(*attrs), + GFP_KERNEL); + if (!attrs) + return -ENOMEM; + for (i = 0; i < ARRAY_SIZE(paiext_ctrnames); i++) { + ret = attr_event_init_one(attrs, i); + if (ret) { + attr_event_free(attrs, i - 1); + return ret; + } + } + attrs[i] = NULL; + paiext_events_group.attrs = attrs; + return 0; +} + +static int __init paiext_init(void) +{ + struct qpaci_info_block ib; + int rc = -ENOMEM; + + if (!test_facility(197)) + return 0; + + qpaci(&ib); + paiext_cnt = ib.num_nnpa; + if (paiext_cnt >= PAI_NNPA_MAXCTR) + paiext_cnt = PAI_NNPA_MAXCTR; + if (!paiext_cnt) + return 0; + + rc = attr_event_init(); + if (rc) { + pr_err("Creation of PMU " KMSG_COMPONENT " /sysfs failed\n"); + return rc; + } + + /* Setup s390dbf facility */ + paiext_dbg = debug_register(KMSG_COMPONENT, 2, 256, 128); + if (!paiext_dbg) { + pr_err("Registration of s390dbf " KMSG_COMPONENT " failed\n"); + rc = -ENOMEM; + goto out_init; + } + debug_register_view(paiext_dbg, &debug_sprintf_view); + + rc = perf_pmu_register(&paiext, KMSG_COMPONENT, -1); + if (rc) { + pr_err("Registration of " KMSG_COMPONENT " PMU failed with " + "rc=%i\n", rc); + goto out_pmu; + } + + return 0; + +out_pmu: + debug_unregister_view(paiext_dbg, &debug_sprintf_view); + debug_unregister(paiext_dbg); +out_init: + attr_event_free(paiext_events_group.attrs, + ARRAY_SIZE(paiext_ctrnames) + 1); + return rc; +} + +device_initcall(paiext_init); diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index bbd4bde4f65d..ab19ddb09d65 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -58,7 +58,7 @@ #include #include #include -#include +#include #include #include #include @@ -74,6 +74,7 @@ #include #include #include +#include #include #include #include "entry.h" @@ -395,6 +396,7 @@ void __init arch_call_rest_init(void) { unsigned long stack; + smp_reinit_ipl_cpu(); stack = stack_alloc(); if (!stack) panic("Couldn't allocate kernel stack"); @@ -411,8 +413,9 @@ void __init arch_call_rest_init(void) static void __init setup_lowcore_dat_off(void) { unsigned long int_psw_mask = PSW_KERNEL_BITS; + struct lowcore *abs_lc, *lc; unsigned long mcck_stack; - struct lowcore *lc; + unsigned long flags; if (IS_ENABLED(CONFIG_KASAN)) int_psw_mask |= PSW_MASK_DAT; @@ -474,12 +477,14 @@ static void __init setup_lowcore_dat_off(void) lc->restart_data = 0; lc->restart_source = -1U; - put_abs_lowcore(restart_stack, lc->restart_stack); - put_abs_lowcore(restart_fn, lc->restart_fn); - put_abs_lowcore(restart_data, lc->restart_data); - put_abs_lowcore(restart_source, lc->restart_source); - put_abs_lowcore(restart_psw, lc->restart_psw); - put_abs_lowcore(mcesad, lc->mcesad); + abs_lc = get_abs_lowcore(&flags); + abs_lc->restart_stack = lc->restart_stack; + abs_lc->restart_fn = lc->restart_fn; + abs_lc->restart_data = lc->restart_data; + abs_lc->restart_source = lc->restart_source; + abs_lc->restart_psw = lc->restart_psw; + abs_lc->mcesad = lc->mcesad; + put_abs_lowcore(abs_lc, flags); mcck_stack = (unsigned long)memblock_alloc(THREAD_SIZE, THREAD_SIZE); if (!mcck_stack) @@ -500,8 +505,8 @@ static void __init setup_lowcore_dat_off(void) static void __init setup_lowcore_dat_on(void) { - struct lowcore *lc = lowcore_ptr[0]; - int cr; + struct lowcore *abs_lc; + unsigned long flags; __ctl_clear_bit(0, 28); S390_lowcore.external_new_psw.mask |= PSW_MASK_DAT; @@ -510,10 +515,15 @@ static void __init setup_lowcore_dat_on(void) S390_lowcore.io_new_psw.mask |= PSW_MASK_DAT; __ctl_set_bit(0, 28); __ctl_store(S390_lowcore.cregs_save_area, 0, 15); - put_abs_lowcore(restart_flags, RESTART_FLAG_CTLREGS); - put_abs_lowcore(program_new_psw, lc->program_new_psw); - for (cr = 0; cr < ARRAY_SIZE(lc->cregs_save_area); cr++) - put_abs_lowcore(cregs_save_area[cr], lc->cregs_save_area[cr]); + if (abs_lowcore_map(0, lowcore_ptr[0], true)) + panic("Couldn't setup absolute lowcore"); + abs_lowcore_mapped = true; + abs_lc = get_abs_lowcore(&flags); + abs_lc->restart_flags = RESTART_FLAG_CTLREGS; + abs_lc->program_new_psw = S390_lowcore.program_new_psw; + memcpy(abs_lc->cregs_save_area, S390_lowcore.cregs_save_area, + sizeof(abs_lc->cregs_save_area)); + put_abs_lowcore(abs_lc, flags); } static struct resource code_resource = { @@ -1019,10 +1029,10 @@ void __init setup_arch(char **cmdline_p) reserve_crashkernel(); #ifdef CONFIG_CRASH_DUMP /* - * Be aware that smp_save_dump_cpus() triggers a system reset. + * Be aware that smp_save_dump_secondary_cpus() triggers a system reset. * Therefore CPU and device initialization should be done afterwards. */ - smp_save_dump_cpus(); + smp_save_dump_secondary_cpus(); #endif setup_resources(); @@ -1041,12 +1051,15 @@ void __init setup_arch(char **cmdline_p) * Create kernel page tables and switch to virtual addressing. */ paging_init(); - + memcpy_real_init(); /* * After paging_init created the kernel page table, the new PSWs * in lowcore can now run with DAT enabled. */ setup_lowcore_dat_on(); +#ifdef CONFIG_CRASH_DUMP + smp_save_dump_ipl_cpu(); +#endif /* Setup default console */ conmode_default(); diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 30c91d565933..0031325ce4bc 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -45,7 +45,7 @@ #include #include #include -#include +#include #include #include #include @@ -55,6 +55,7 @@ #include #include #include +#include #include "entry.h" enum { @@ -212,10 +213,14 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu) lc->preempt_count = PREEMPT_DISABLED; if (nmi_alloc_mcesa(&lc->mcesad)) goto out; + if (abs_lowcore_map(cpu, lc, true)) + goto out_mcesa; lowcore_ptr[cpu] = lc; pcpu_sigp_retry(pcpu, SIGP_SET_PREFIX, __pa(lc)); return 0; +out_mcesa: + nmi_free_mcesa(&lc->mcesad); out: stack_free(mcck_stack); stack_free(async_stack); @@ -237,6 +242,7 @@ static void pcpu_free_lowcore(struct pcpu *pcpu) mcck_stack = lc->mcck_stack - STACK_INIT_OFFSET; pcpu_sigp_retry(pcpu, SIGP_SET_PREFIX, 0); lowcore_ptr[cpu] = NULL; + abs_lowcore_unmap(cpu); nmi_free_mcesa(&lc->mcesad); stack_free(async_stack); stack_free(mcck_stack); @@ -315,9 +321,12 @@ static void pcpu_delegate(struct pcpu *pcpu, pcpu_delegate_fn *func, void *data, unsigned long stack) { - struct lowcore *lc = lowcore_ptr[pcpu - pcpu_devices]; - unsigned int source_cpu = stap(); + struct lowcore *lc, *abs_lc; + unsigned int source_cpu; + unsigned long flags; + lc = lowcore_ptr[pcpu - pcpu_devices]; + source_cpu = stap(); __load_psw_mask(PSW_KERNEL_BITS | PSW_MASK_DAT); if (pcpu->address == source_cpu) { call_on_stack(2, stack, void, __pcpu_delegate, @@ -332,10 +341,12 @@ static void pcpu_delegate(struct pcpu *pcpu, lc->restart_data = (unsigned long)data; lc->restart_source = source_cpu; } else { - put_abs_lowcore(restart_stack, stack); - put_abs_lowcore(restart_fn, (unsigned long)func); - put_abs_lowcore(restart_data, (unsigned long)data); - put_abs_lowcore(restart_source, source_cpu); + abs_lc = get_abs_lowcore(&flags); + abs_lc->restart_stack = stack; + abs_lc->restart_fn = (unsigned long)func; + abs_lc->restart_data = (unsigned long)data; + abs_lc->restart_source = source_cpu; + put_abs_lowcore(abs_lc, flags); } __bpon(); asm volatile( @@ -581,6 +592,8 @@ static DEFINE_SPINLOCK(ctl_lock); void smp_ctl_set_clear_bit(int cr, int bit, bool set) { struct ec_creg_mask_parms parms = { .cr = cr, }; + struct lowcore *abs_lc; + unsigned long flags; u64 ctlreg; if (set) { @@ -591,9 +604,11 @@ void smp_ctl_set_clear_bit(int cr, int bit, bool set) parms.andval = ~(1UL << bit); } spin_lock(&ctl_lock); - get_abs_lowcore(ctlreg, cregs_save_area[cr]); + abs_lc = get_abs_lowcore(&flags); + ctlreg = abs_lc->cregs_save_area[cr]; ctlreg = (ctlreg & parms.andval) | parms.orval; - put_abs_lowcore(cregs_save_area[cr], ctlreg); + abs_lc->cregs_save_area[cr] = ctlreg; + put_abs_lowcore(abs_lc, flags); spin_unlock(&ctl_lock); on_each_cpu(smp_ctl_bit_callback, &parms, 1); } @@ -650,35 +665,36 @@ int smp_store_status(int cpu) * This case does not exist for s390 anymore, setup_arch explicitly * deactivates the elfcorehdr= kernel parameter */ -static __init void smp_save_cpu_vxrs(struct save_area *sa, u16 addr, - bool is_boot_cpu, __vector128 *vxrs) +static bool dump_available(void) { - if (is_boot_cpu) - vxrs = boot_cpu_vector_save_area; - else - __pcpu_sigp_relax(addr, SIGP_STORE_ADDITIONAL_STATUS, __pa(vxrs)); - save_area_add_vxrs(sa, vxrs); + return oldmem_data.start || is_ipl_type_dump(); } -static __init void smp_save_cpu_regs(struct save_area *sa, u16 addr, - bool is_boot_cpu, void *regs) +void __init smp_save_dump_ipl_cpu(void) { - if (is_boot_cpu) - copy_oldmem_kernel(regs, __LC_FPREGS_SAVE_AREA, 512); - else - __pcpu_sigp_relax(addr, SIGP_STORE_STATUS_AT_ADDRESS, __pa(regs)); + struct save_area *sa; + void *regs; + + if (!dump_available()) + return; + sa = save_area_alloc(true); + regs = memblock_alloc(512, 8); + if (!sa || !regs) + panic("could not allocate memory for boot CPU save area\n"); + copy_oldmem_kernel(regs, __LC_FPREGS_SAVE_AREA, 512); save_area_add_regs(sa, regs); + memblock_free(regs, 512); + if (MACHINE_HAS_VX) + save_area_add_vxrs(sa, boot_cpu_vector_save_area); } -void __init smp_save_dump_cpus(void) +void __init smp_save_dump_secondary_cpus(void) { int addr, boot_cpu_addr, max_cpu_addr; struct save_area *sa; - bool is_boot_cpu; void *page; - if (!(oldmem_data.start || is_ipl_type_dump())) - /* No previous system present, normal boot. */ + if (!dump_available()) return; /* Allocate a page as dumping area for the store status sigps */ page = memblock_alloc_low(PAGE_SIZE, PAGE_SIZE); @@ -691,26 +707,20 @@ void __init smp_save_dump_cpus(void) boot_cpu_addr = stap(); max_cpu_addr = SCLP_MAX_CORES << sclp.mtid_prev; for (addr = 0; addr <= max_cpu_addr; addr++) { + if (addr == boot_cpu_addr) + continue; if (__pcpu_sigp_relax(addr, SIGP_SENSE, 0) == SIGP_CC_NOT_OPERATIONAL) continue; - is_boot_cpu = (addr == boot_cpu_addr); - /* Allocate save area */ - sa = save_area_alloc(is_boot_cpu); + sa = save_area_alloc(false); if (!sa) panic("could not allocate memory for save area\n"); - if (MACHINE_HAS_VX) - /* Get the vector registers */ - smp_save_cpu_vxrs(sa, addr, is_boot_cpu, page); - /* - * For a zfcp/nvme dump OLDMEM_BASE == NULL and the registers - * of the boot CPU are stored in the HSA. To retrieve - * these registers an SCLP request is required which is - * done by drivers/s390/char/zcore.c:init_cpu_info() - */ - if (!is_boot_cpu || oldmem_data.start) - /* Get the CPU registers */ - smp_save_cpu_regs(sa, addr, is_boot_cpu, page); + __pcpu_sigp_relax(addr, SIGP_STORE_STATUS_AT_ADDRESS, __pa(page)); + save_area_add_regs(sa, page); + if (MACHINE_HAS_VX) { + __pcpu_sigp_relax(addr, SIGP_STORE_ADDITIONAL_STATUS, __pa(page)); + save_area_add_vxrs(sa, page); + } } memblock_free(page, PAGE_SIZE); diag_amode31_ops.diag308_reset(); @@ -1256,7 +1266,7 @@ static __always_inline void set_new_lowcore(struct lowcore *lc) : "memory", "cc"); } -static int __init smp_reinit_ipl_cpu(void) +int __init smp_reinit_ipl_cpu(void) { unsigned long async_stack, nodat_stack, mcck_stack; struct lowcore *lc, *lc_ipl; @@ -1281,6 +1291,8 @@ static int __init smp_reinit_ipl_cpu(void) __ctl_clear_bit(0, 28); /* disable lowcore protection */ S390_lowcore.mcesad = mcesad; __ctl_load(cr0, 0, 0); + if (abs_lowcore_map(0, lc, false)) + panic("Couldn't remap absolute lowcore"); lowcore_ptr[0] = lc; local_mcck_enable(); local_irq_restore(flags); @@ -1291,4 +1303,3 @@ static int __init smp_reinit_ipl_cpu(void) return 0; } -early_initcall(smp_reinit_ipl_cpu); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index b7ef0b71014d..45d4b8182b07 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -4343,8 +4343,6 @@ retry: goto retry; } - /* nothing to do, just clear the request */ - kvm_clear_request(KVM_REQ_UNHALT, vcpu); /* we left the vsie handler, nothing to do, just clear the request */ kvm_clear_request(KVM_REQ_VSIE_RESTART, vcpu); diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c index f7f5adea8940..be14c58cb989 100644 --- a/arch/s390/lib/delay.c +++ b/arch/s390/lib/delay.c @@ -13,13 +13,10 @@ void __delay(unsigned long loops) { - /* - * To end the bloody studid and useless discussion about the - * BogoMips number I took the liberty to define the __delay - * function in a way that that resulting BogoMips number will - * yield the megahertz number of the cpu. The important function - * is udelay and that is done using the tod clock. -- martin. - */ + /* + * Loop 'loops' times. Callers must not assume a specific + * amount of time passes before this function returns. + */ asm volatile("0: brct %0,0b" : : "d" ((loops/2) + 1)); } EXPORT_SYMBOL(__delay); diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c index 9f9af5298dd6..9953819d7959 100644 --- a/arch/s390/mm/dump_pagetables.c +++ b/arch/s390/mm/dump_pagetables.c @@ -8,8 +8,10 @@ #include #include #include +#include #include #include +#include static unsigned long max_addr; @@ -21,6 +23,8 @@ struct addr_marker { enum address_markers_idx { IDENTITY_BEFORE_NR = 0, IDENTITY_BEFORE_END_NR, + AMODE31_START_NR, + AMODE31_END_NR, KERNEL_START_NR, KERNEL_END_NR, #ifdef CONFIG_KFENCE @@ -39,11 +43,17 @@ enum address_markers_idx { VMALLOC_END_NR, MODULES_NR, MODULES_END_NR, + ABS_LOWCORE_NR, + ABS_LOWCORE_END_NR, + MEMCPY_REAL_NR, + MEMCPY_REAL_END_NR, }; static struct addr_marker address_markers[] = { [IDENTITY_BEFORE_NR] = {0, "Identity Mapping Start"}, [IDENTITY_BEFORE_END_NR] = {(unsigned long)_stext, "Identity Mapping End"}, + [AMODE31_START_NR] = {0, "Amode31 Area Start"}, + [AMODE31_END_NR] = {0, "Amode31 Area End"}, [KERNEL_START_NR] = {(unsigned long)_stext, "Kernel Image Start"}, [KERNEL_END_NR] = {(unsigned long)_end, "Kernel Image End"}, #ifdef CONFIG_KFENCE @@ -62,6 +72,10 @@ static struct addr_marker address_markers[] = { [VMALLOC_END_NR] = {0, "vmalloc Area End"}, [MODULES_NR] = {0, "Modules Area Start"}, [MODULES_END_NR] = {0, "Modules Area End"}, + [ABS_LOWCORE_NR] = {0, "Lowcore Area Start"}, + [ABS_LOWCORE_END_NR] = {0, "Lowcore Area End"}, + [MEMCPY_REAL_NR] = {0, "Real Memory Copy Area Start"}, + [MEMCPY_REAL_END_NR] = {0, "Real Memory Copy Area End"}, { -1, NULL } }; @@ -276,8 +290,14 @@ static int pt_dump_init(void) max_addr = (S390_lowcore.kernel_asce & _REGION_ENTRY_TYPE_MASK) >> 2; max_addr = 1UL << (max_addr * 11 + 31); address_markers[IDENTITY_AFTER_END_NR].start_address = ident_map_size; + address_markers[AMODE31_START_NR].start_address = __samode31; + address_markers[AMODE31_END_NR].start_address = __eamode31; address_markers[MODULES_NR].start_address = MODULES_VADDR; address_markers[MODULES_END_NR].start_address = MODULES_END; + address_markers[ABS_LOWCORE_NR].start_address = __abs_lowcore; + address_markers[ABS_LOWCORE_END_NR].start_address = __abs_lowcore + ABS_LOWCORE_MAP_SIZE; + address_markers[MEMCPY_REAL_NR].start_address = __memcpy_real_area; + address_markers[MEMCPY_REAL_END_NR].start_address = __memcpy_real_area + PAGE_SIZE; address_markers[VMEMMAP_NR].start_address = (unsigned long) vmemmap; address_markers[VMEMMAP_END_NR].start_address = (unsigned long)vmemmap + vmemmap_size; address_markers[VMALLOC_NR].start_address = VMALLOC_START; diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 9ab6ca6f7f59..9649d9382e0a 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -268,8 +268,7 @@ static noinline void do_sigbus(struct pt_regs *regs) (void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK)); } -static noinline void do_fault_error(struct pt_regs *regs, int access, - vm_fault_t fault) +static noinline void do_fault_error(struct pt_regs *regs, vm_fault_t fault) { int si_code; @@ -516,7 +515,7 @@ void do_protection_exception(struct pt_regs *regs) fault = do_exception(regs, access); } if (unlikely(fault)) - do_fault_error(regs, access, fault); + do_fault_error(regs, fault); } NOKPROBE_SYMBOL(do_protection_exception); @@ -528,7 +527,7 @@ void do_dat_exception(struct pt_regs *regs) access = VM_ACCESS_FLAGS; fault = do_exception(regs, access); if (unlikely(fault)) - do_fault_error(regs, access, fault); + do_fault_error(regs, fault); } NOKPROBE_SYMBOL(do_dat_exception); @@ -803,7 +802,7 @@ void do_secure_storage_access(struct pt_regs *regs) addr = __gmap_translate(gmap, addr); mmap_read_unlock(mm); if (IS_ERR_VALUE(addr)) { - do_fault_error(regs, VM_ACCESS_FLAGS, VM_FAULT_BADMAP); + do_fault_error(regs, VM_FAULT_BADMAP); break; } fallthrough; @@ -813,7 +812,7 @@ void do_secure_storage_access(struct pt_regs *regs) vma = find_vma(mm, addr); if (!vma) { mmap_read_unlock(mm); - do_fault_error(regs, VM_READ | VM_WRITE, VM_FAULT_BADMAP); + do_fault_error(regs, VM_FAULT_BADMAP); break; } page = follow_page(vma, addr, FOLL_WRITE | FOLL_GET); @@ -836,7 +835,7 @@ void do_secure_storage_access(struct pt_regs *regs) BUG(); break; default: - do_fault_error(regs, VM_READ | VM_WRITE, VM_FAULT_BADMAP); + do_fault_error(regs, VM_FAULT_BADMAP); WARN_ON_ONCE(1); } } @@ -848,7 +847,7 @@ void do_non_secure_storage_access(struct pt_regs *regs) struct gmap *gmap = (struct gmap *)S390_lowcore.gmap; if (get_fault_type(regs) != GMAP_FAULT) { - do_fault_error(regs, VM_READ | VM_WRITE, VM_FAULT_BADMAP); + do_fault_error(regs, VM_FAULT_BADMAP); WARN_ON_ONCE(1); return; } diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 4a154a084966..97d66a3e60fb 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -37,7 +37,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c index d6d84e02f35a..1571cdcb0c50 100644 --- a/arch/s390/mm/maccess.c +++ b/arch/s390/mm/maccess.c @@ -12,10 +12,17 @@ #include #include #include +#include #include #include #include +#include #include +#include + +unsigned long __bootdata_preserved(__memcpy_real_area); +static __ro_after_init pte_t *memcpy_real_ptep; +static DEFINE_MUTEX(memcpy_real_mutex); static notrace long s390_kernel_write_odd(void *dst, const void *src, size_t size) { @@ -76,118 +83,72 @@ notrace void *s390_kernel_write(void *dst, const void *src, size_t size) return dst; } -static int __no_sanitize_address __memcpy_real(void *dest, void *src, size_t count) +void __init memcpy_real_init(void) { - union register_pair _dst, _src; - int rc = -EFAULT; - - _dst.even = (unsigned long) dest; - _dst.odd = (unsigned long) count; - _src.even = (unsigned long) src; - _src.odd = (unsigned long) count; - asm volatile ( - "0: mvcle %[dst],%[src],0\n" - "1: jo 0b\n" - " lhi %[rc],0\n" - "2:\n" - EX_TABLE(1b,2b) - : [rc] "+&d" (rc), [dst] "+&d" (_dst.pair), [src] "+&d" (_src.pair) - : : "cc", "memory"); - return rc; + memcpy_real_ptep = vmem_get_alloc_pte(__memcpy_real_area, true); + if (!memcpy_real_ptep) + panic("Couldn't setup memcpy real area"); } -static unsigned long __no_sanitize_address _memcpy_real(unsigned long dest, - unsigned long src, - unsigned long count) +size_t memcpy_real_iter(struct iov_iter *iter, unsigned long src, size_t count) { - int irqs_disabled, rc; - unsigned long flags; + size_t len, copied, res = 0; + unsigned long phys, offset; + void *chunk; + pte_t pte; - if (!count) - return 0; - flags = arch_local_irq_save(); - irqs_disabled = arch_irqs_disabled_flags(flags); - if (!irqs_disabled) - trace_hardirqs_off(); - __arch_local_irq_stnsm(0xf8); // disable DAT - rc = __memcpy_real((void *) dest, (void *) src, (size_t) count); - if (flags & PSW_MASK_DAT) - __arch_local_irq_stosm(0x04); // enable DAT - if (!irqs_disabled) - trace_hardirqs_on(); - __arch_local_irq_ssm(flags); - return rc; + while (count) { + phys = src & PAGE_MASK; + offset = src & ~PAGE_MASK; + chunk = (void *)(__memcpy_real_area + offset); + len = min(count, PAGE_SIZE - offset); + pte = mk_pte_phys(phys, PAGE_KERNEL_RO); + + mutex_lock(&memcpy_real_mutex); + if (pte_val(pte) != pte_val(*memcpy_real_ptep)) { + __ptep_ipte(__memcpy_real_area, memcpy_real_ptep, 0, 0, IPTE_GLOBAL); + set_pte(memcpy_real_ptep, pte); + } + copied = copy_to_iter(chunk, len, iter); + mutex_unlock(&memcpy_real_mutex); + + count -= copied; + src += copied; + res += copied; + if (copied < len) + break; + } + return res; } -/* - * Copy memory in real mode (kernel to kernel) - */ int memcpy_real(void *dest, unsigned long src, size_t count) { - unsigned long _dest = (unsigned long)dest; - unsigned long _src = (unsigned long)src; - unsigned long _count = (unsigned long)count; - int rc; + struct iov_iter iter; + struct kvec kvec; - if (S390_lowcore.nodat_stack != 0) { - preempt_disable(); - rc = call_on_stack(3, S390_lowcore.nodat_stack, - unsigned long, _memcpy_real, - unsigned long, _dest, - unsigned long, _src, - unsigned long, _count); - preempt_enable(); - return rc; - } - /* - * This is a really early memcpy_real call, the stacks are - * not set up yet. Just call _memcpy_real on the early boot - * stack - */ - return _memcpy_real(_dest, _src, _count); + kvec.iov_base = dest; + kvec.iov_len = count; + iov_iter_kvec(&iter, WRITE, &kvec, 1, count); + if (memcpy_real_iter(&iter, src, count) < count) + return -EFAULT; + return 0; } /* - * Copy memory in absolute mode (kernel to kernel) + * Find CPU that owns swapped prefix page */ -void memcpy_absolute(void *dest, void *src, size_t count) -{ - unsigned long cr0, flags, prefix; - - flags = arch_local_irq_save(); - __ctl_store(cr0, 0, 0); - __ctl_clear_bit(0, 28); /* disable lowcore protection */ - prefix = store_prefix(); - if (prefix) { - local_mcck_disable(); - set_prefix(0); - memcpy(dest, src, count); - set_prefix(prefix); - local_mcck_enable(); - } else { - memcpy(dest, src, count); - } - __ctl_load(cr0, 0, 0); - arch_local_irq_restore(flags); -} - -/* - * Check if physical address is within prefix or zero page - */ -static int is_swapped(phys_addr_t addr) +static int get_swapped_owner(phys_addr_t addr) { phys_addr_t lc; int cpu; - if (addr < sizeof(struct lowcore)) - return 1; for_each_online_cpu(cpu) { lc = virt_to_phys(lowcore_ptr[cpu]); if (addr > lc + sizeof(struct lowcore) - 1 || addr < lc) continue; - return 1; + return cpu; } - return 0; + return -1; } /* @@ -200,17 +161,35 @@ void *xlate_dev_mem_ptr(phys_addr_t addr) { void *ptr = phys_to_virt(addr); void *bounce = ptr; + struct lowcore *abs_lc; + unsigned long flags; unsigned long size; + int this_cpu, cpu; cpus_read_lock(); - preempt_disable(); - if (is_swapped(addr)) { - size = PAGE_SIZE - (addr & ~PAGE_MASK); - bounce = (void *) __get_free_page(GFP_ATOMIC); - if (bounce) - memcpy_absolute(bounce, ptr, size); + this_cpu = get_cpu(); + if (addr >= sizeof(struct lowcore)) { + cpu = get_swapped_owner(addr); + if (cpu < 0) + goto out; } - preempt_enable(); + bounce = (void *)__get_free_page(GFP_ATOMIC); + if (!bounce) + goto out; + size = PAGE_SIZE - (addr & ~PAGE_MASK); + if (addr < sizeof(struct lowcore)) { + abs_lc = get_abs_lowcore(&flags); + ptr = (void *)abs_lc + addr; + memcpy(bounce, ptr, size); + put_abs_lowcore(abs_lc, flags); + } else if (cpu == this_cpu) { + ptr = (void *)(addr - virt_to_phys(lowcore_ptr[cpu])); + memcpy(bounce, ptr, size); + } else { + memcpy(bounce, ptr, size); + } +out: + put_cpu(); cpus_read_unlock(); return bounce; } diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index c2583f921ca8..ee1a97078527 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -240,7 +240,7 @@ static int __ref modify_pmd_table(pud_t *pud, unsigned long addr, } else if (pmd_none(*pmd)) { if (IS_ALIGNED(addr, PMD_SIZE) && IS_ALIGNED(next, PMD_SIZE) && - MACHINE_HAS_EDAT1 && addr && direct && + MACHINE_HAS_EDAT1 && direct && !debug_pagealloc_enabled()) { set_pmd(pmd, __pmd(__pa(addr) | prot)); pages++; @@ -336,7 +336,7 @@ static int modify_pud_table(p4d_t *p4d, unsigned long addr, unsigned long end, } else if (pud_none(*pud)) { if (IS_ALIGNED(addr, PUD_SIZE) && IS_ALIGNED(next, PUD_SIZE) && - MACHINE_HAS_EDAT2 && addr && direct && + MACHINE_HAS_EDAT2 && direct && !debug_pagealloc_enabled()) { set_pud(pud, __pud(__pa(addr) | prot)); pages++; @@ -560,6 +560,103 @@ int vmem_add_mapping(unsigned long start, unsigned long size) return ret; } +/* + * Allocate new or return existing page-table entry, but do not map it + * to any physical address. If missing, allocate segment- and region- + * table entries along. Meeting a large segment- or region-table entry + * while traversing is an error, since the function is expected to be + * called against virtual regions reserverd for 4KB mappings only. + */ +pte_t *vmem_get_alloc_pte(unsigned long addr, bool alloc) +{ + pte_t *ptep = NULL; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + pgd = pgd_offset_k(addr); + if (pgd_none(*pgd)) { + if (!alloc) + goto out; + p4d = vmem_crst_alloc(_REGION2_ENTRY_EMPTY); + if (!p4d) + goto out; + pgd_populate(&init_mm, pgd, p4d); + } + p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) { + if (!alloc) + goto out; + pud = vmem_crst_alloc(_REGION3_ENTRY_EMPTY); + if (!pud) + goto out; + p4d_populate(&init_mm, p4d, pud); + } + pud = pud_offset(p4d, addr); + if (pud_none(*pud)) { + if (!alloc) + goto out; + pmd = vmem_crst_alloc(_SEGMENT_ENTRY_EMPTY); + if (!pmd) + goto out; + pud_populate(&init_mm, pud, pmd); + } else if (WARN_ON_ONCE(pud_large(*pud))) { + goto out; + } + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) { + if (!alloc) + goto out; + pte = vmem_pte_alloc(); + if (!pte) + goto out; + pmd_populate(&init_mm, pmd, pte); + } else if (WARN_ON_ONCE(pmd_large(*pmd))) { + goto out; + } + ptep = pte_offset_kernel(pmd, addr); +out: + return ptep; +} + +int __vmem_map_4k_page(unsigned long addr, unsigned long phys, pgprot_t prot, bool alloc) +{ + pte_t *ptep, pte; + + if (!IS_ALIGNED(addr, PAGE_SIZE)) + return -EINVAL; + ptep = vmem_get_alloc_pte(addr, alloc); + if (!ptep) + return -ENOMEM; + __ptep_ipte(addr, ptep, 0, 0, IPTE_GLOBAL); + pte = mk_pte_phys(phys, prot); + set_pte(ptep, pte); + return 0; +} + +int vmem_map_4k_page(unsigned long addr, unsigned long phys, pgprot_t prot) +{ + int rc; + + mutex_lock(&vmem_mutex); + rc = __vmem_map_4k_page(addr, phys, prot, true); + mutex_unlock(&vmem_mutex); + return rc; +} + +void vmem_unmap_4k_page(unsigned long addr) +{ + pte_t *ptep; + + mutex_lock(&vmem_mutex); + ptep = virt_to_kpte(addr); + __ptep_ipte(addr, ptep, 0, 0, IPTE_GLOBAL); + pte_clear(&init_mm, addr, ptep); + mutex_unlock(&vmem_mutex); +} + /* * map whole physical memory to virtual memory (identity mapping) * we reserve enough space in the vmalloc area for vmemmap to hotplug @@ -584,6 +681,9 @@ void __init vmem_map_init(void) __set_memory(__stext_amode31, (__etext_amode31 - __stext_amode31) >> PAGE_SHIFT, SET_MEMORY_RO | SET_MEMORY_X); + /* lowcore requires 4k mapping for real addresses / prefixing */ + set_memory_4k(0, LC_PAGES); + /* lowcore must be executable for LPSWE */ if (!static_key_enabled(&cpu_has_bear)) set_memory_x(0, 1); diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index f46833a25526..227cf0a62800 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -666,7 +666,7 @@ static int __init dma_alloc_cpu_table_caches(void) int __init zpci_dma_init(void) { - s390_iommu_aperture = (u64)high_memory; + s390_iommu_aperture = (u64)virt_to_phys(high_memory); if (!s390_iommu_aperture_factor) s390_iommu_aperture = ULONG_MAX; else diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index 0a9407dc0859..3089ec352743 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -138,6 +138,9 @@ #define HV_X64_NESTED_GUEST_MAPPING_FLUSH BIT(18) #define HV_X64_NESTED_MSR_BITMAP BIT(19) +/* Nested features #2. These are HYPERV_CPUID_NESTED_FEATURES.EBX bits. */ +#define HV_X64_NESTED_EVMCS1_PERF_GLOBAL_CTRL BIT(0) + /* * This is specific to AMD and specifies that enlightened TLB flush is * supported. If guest opts in to this feature, ASID invalidations only @@ -546,7 +549,7 @@ struct hv_enlightened_vmcs { u64 guest_rip; u32 hv_clean_fields; - u32 hv_padding_32; + u32 padding32_1; u32 hv_synthetic_controls; struct { u32 nested_flush_hypercall:1; @@ -554,14 +557,25 @@ struct hv_enlightened_vmcs { u32 reserved:30; } __packed hv_enlightenments_control; u32 hv_vp_id; - + u32 padding32_2; u64 hv_vm_id; u64 partition_assist_page; u64 padding64_4[4]; u64 guest_bndcfgs; - u64 padding64_5[7]; + u64 guest_ia32_perf_global_ctrl; + u64 guest_ia32_s_cet; + u64 guest_ssp; + u64 guest_ia32_int_ssp_table_addr; + u64 guest_ia32_lbr_ctl; + u64 padding64_5[2]; u64 xss_exit_bitmap; - u64 padding64_6[7]; + u64 encls_exiting_bitmap; + u64 host_ia32_perf_global_ctrl; + u64 tsc_multiplier; + u64 host_ia32_s_cet; + u64 host_ssp; + u64 host_ia32_int_ssp_table_addr; + u64 padding64_6; } __packed; #define HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE 0 diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 51f777071584..82ba4a564e58 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -67,7 +67,7 @@ KVM_X86_OP(get_interrupt_shadow) KVM_X86_OP(patch_hypercall) KVM_X86_OP(inject_irq) KVM_X86_OP(inject_nmi) -KVM_X86_OP(queue_exception) +KVM_X86_OP(inject_exception) KVM_X86_OP(cancel_injection) KVM_X86_OP(interrupt_allowed) KVM_X86_OP(nmi_allowed) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index aa381ab69a19..61b9dd34d333 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -615,6 +615,8 @@ struct kvm_vcpu_hv { u32 enlightenments_eax; /* HYPERV_CPUID_ENLIGHTMENT_INFO.EAX */ u32 enlightenments_ebx; /* HYPERV_CPUID_ENLIGHTMENT_INFO.EBX */ u32 syndbg_cap_eax; /* HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES.EAX */ + u32 nested_eax; /* HYPERV_CPUID_NESTED_FEATURES.EAX */ + u32 nested_ebx; /* HYPERV_CPUID_NESTED_FEATURES.EBX */ } cpuid_cache; }; @@ -639,6 +641,16 @@ struct kvm_vcpu_xen { struct timer_list poll_timer; }; +struct kvm_queued_exception { + bool pending; + bool injected; + bool has_error_code; + u8 vector; + u32 error_code; + unsigned long payload; + bool has_payload; +}; + struct kvm_vcpu_arch { /* * rip and regs accesses must go through @@ -738,16 +750,12 @@ struct kvm_vcpu_arch { u8 event_exit_inst_len; - struct kvm_queued_exception { - bool pending; - bool injected; - bool has_error_code; - u8 nr; - u32 error_code; - unsigned long payload; - bool has_payload; - u8 nested_apf; - } exception; + bool exception_from_userspace; + + /* Exceptions to be injected to the guest. */ + struct kvm_queued_exception exception; + /* Exception VM-Exits to be synthesized to L1. */ + struct kvm_queued_exception exception_vmexit; struct kvm_queued_interrupt { bool injected; @@ -858,7 +866,6 @@ struct kvm_vcpu_arch { u32 id; bool send_user_only; u32 host_apf_flags; - unsigned long nested_apf_token; bool delivery_as_pf_vmexit; bool pageready_pending; } apf; @@ -1524,7 +1531,7 @@ struct kvm_x86_ops { unsigned char *hypercall_addr); void (*inject_irq)(struct kvm_vcpu *vcpu, bool reinjected); void (*inject_nmi)(struct kvm_vcpu *vcpu); - void (*queue_exception)(struct kvm_vcpu *vcpu); + void (*inject_exception)(struct kvm_vcpu *vcpu); void (*cancel_injection)(struct kvm_vcpu *vcpu); int (*interrupt_allowed)(struct kvm_vcpu *vcpu, bool for_injection); int (*nmi_allowed)(struct kvm_vcpu *vcpu, bool for_injection); @@ -1634,10 +1641,10 @@ struct kvm_x86_ops { struct kvm_x86_nested_ops { void (*leave_nested)(struct kvm_vcpu *vcpu); + bool (*is_exception_vmexit)(struct kvm_vcpu *vcpu, u8 vector, + u32 error_code); int (*check_events)(struct kvm_vcpu *vcpu); - bool (*handle_page_fault_workaround)(struct kvm_vcpu *vcpu, - struct x86_exception *fault); - bool (*hv_timer_pending)(struct kvm_vcpu *vcpu); + bool (*has_events)(struct kvm_vcpu *vcpu); void (*triple_fault)(struct kvm_vcpu *vcpu); int (*get_state)(struct kvm_vcpu *vcpu, struct kvm_nested_state __user *user_kvm_nested_state, @@ -1863,7 +1870,7 @@ void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, unsigned long pay void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr); void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code); void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault); -bool kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, +void kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault); bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl); bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 2796dde06302..7065462378e2 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -311,6 +311,15 @@ void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_update_cpuid_runtime); +static bool kvm_cpuid_has_hyperv(struct kvm_cpuid_entry2 *entries, int nent) +{ + struct kvm_cpuid_entry2 *entry; + + entry = cpuid_entry2_find(entries, nent, HYPERV_CPUID_INTERFACE, + KVM_CPUID_INDEX_NOT_SIGNIFICANT); + return entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX; +} + static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; @@ -346,7 +355,8 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vcpu->arch.cr4_guest_rsvd_bits = __cr4_reserved_bits(guest_cpuid_has, vcpu); - kvm_hv_set_cpuid(vcpu); + kvm_hv_set_cpuid(vcpu, kvm_cpuid_has_hyperv(vcpu->arch.cpuid_entries, + vcpu->arch.cpuid_nent)); /* Invoke the vendor callback only after the above state is updated. */ static_call(kvm_x86_vcpu_after_set_cpuid)(vcpu); @@ -409,6 +419,12 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, return 0; } + if (kvm_cpuid_has_hyperv(e2, nent)) { + r = kvm_hv_vcpu_init(vcpu); + if (r) + return r; + } + r = kvm_check_cpuid(vcpu, e2, nent); if (r) return r; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index aacb28c83e43..3b27622d4642 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -1137,9 +1137,11 @@ static int em_fnstsw(struct x86_emulate_ctxt *ctxt) static void decode_register_operand(struct x86_emulate_ctxt *ctxt, struct operand *op) { - unsigned reg = ctxt->modrm_reg; + unsigned int reg; - if (!(ctxt->d & ModRM)) + if (ctxt->d & ModRM) + reg = ctxt->modrm_reg; + else reg = (ctxt->b & 7) | ((ctxt->rex_prefix & 1) << 3); if (ctxt->d & Sse) { @@ -1953,7 +1955,7 @@ static int em_pop_sreg(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - if (ctxt->modrm_reg == VCPU_SREG_SS) + if (seg == VCPU_SREG_SS) ctxt->interruptibility = KVM_X86_SHADOW_INT_MOV_SS; if (ctxt->op_bytes > 2) rsp_increment(ctxt, ctxt->op_bytes - 2); @@ -3645,13 +3647,10 @@ static int em_wrmsr(struct x86_emulate_ctxt *ctxt) | ((u64)reg_read(ctxt, VCPU_REGS_RDX) << 32); r = ctxt->ops->set_msr_with_filter(ctxt, msr_index, msr_data); - if (r == X86EMUL_IO_NEEDED) - return r; - - if (r > 0) + if (r == X86EMUL_PROPAGATE_FAULT) return emulate_gp(ctxt, 0); - return r < 0 ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE; + return r; } static int em_rdmsr(struct x86_emulate_ctxt *ctxt) @@ -3662,15 +3661,14 @@ static int em_rdmsr(struct x86_emulate_ctxt *ctxt) r = ctxt->ops->get_msr_with_filter(ctxt, msr_index, &msr_data); - if (r == X86EMUL_IO_NEEDED) - return r; - - if (r) + if (r == X86EMUL_PROPAGATE_FAULT) return emulate_gp(ctxt, 0); - *reg_write(ctxt, VCPU_REGS_RAX) = (u32)msr_data; - *reg_write(ctxt, VCPU_REGS_RDX) = msr_data >> 32; - return X86EMUL_CONTINUE; + if (r == X86EMUL_CONTINUE) { + *reg_write(ctxt, VCPU_REGS_RAX) = (u32)msr_data; + *reg_write(ctxt, VCPU_REGS_RDX) = msr_data >> 32; + } + return r; } static int em_store_sreg(struct x86_emulate_ctxt *ctxt, int segment) @@ -4171,8 +4169,7 @@ static int check_dr7_gd(struct x86_emulate_ctxt *ctxt) ctxt->ops->get_dr(ctxt, 7, &dr7); - /* Check if DR7.Global_Enable is set */ - return dr7 & (1 << 13); + return dr7 & DR7_GD; } static int check_dr_read(struct x86_emulate_ctxt *ctxt) diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index ed804447589c..0adf4a437e85 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -38,9 +38,6 @@ #include "irq.h" #include "fpu.h" -/* "Hv#1" signature */ -#define HYPERV_CPUID_SIGNATURE_EAX 0x31237648 - #define KVM_HV_MAX_SPARSE_VCPU_SET_BITS DIV_ROUND_UP(KVM_MAX_VCPUS, 64) static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer, @@ -934,11 +931,14 @@ static void stimer_init(struct kvm_vcpu_hv_stimer *stimer, int timer_index) stimer_prepare_msg(stimer); } -static int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu) +int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu) { - struct kvm_vcpu_hv *hv_vcpu; + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); int i; + if (hv_vcpu) + return 0; + hv_vcpu = kzalloc(sizeof(struct kvm_vcpu_hv), GFP_KERNEL_ACCOUNT); if (!hv_vcpu) return -ENOMEM; @@ -962,11 +962,9 @@ int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages) struct kvm_vcpu_hv_synic *synic; int r; - if (!to_hv_vcpu(vcpu)) { - r = kvm_hv_vcpu_init(vcpu); - if (r) - return r; - } + r = kvm_hv_vcpu_init(vcpu); + if (r) + return r; synic = to_hv_synic(vcpu); @@ -1660,10 +1658,8 @@ int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) if (!host && !vcpu->arch.hyperv_enabled) return 1; - if (!to_hv_vcpu(vcpu)) { - if (kvm_hv_vcpu_init(vcpu)) - return 1; - } + if (kvm_hv_vcpu_init(vcpu)) + return 1; if (kvm_hv_msr_partition_wide(msr)) { int r; @@ -1683,10 +1679,8 @@ int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) if (!host && !vcpu->arch.hyperv_enabled) return 1; - if (!to_hv_vcpu(vcpu)) { - if (kvm_hv_vcpu_init(vcpu)) - return 1; - } + if (kvm_hv_vcpu_init(vcpu)) + return 1; if (kvm_hv_msr_partition_wide(msr)) { int r; @@ -1987,49 +1981,49 @@ ret_success: return HV_STATUS_SUCCESS; } -void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu) +void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu, bool hyperv_enabled) { + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct kvm_cpuid_entry2 *entry; - struct kvm_vcpu_hv *hv_vcpu; - entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_INTERFACE); - if (entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX) { - vcpu->arch.hyperv_enabled = true; - } else { - vcpu->arch.hyperv_enabled = false; + vcpu->arch.hyperv_enabled = hyperv_enabled; + + if (!hv_vcpu) { + /* + * KVM should have already allocated kvm_vcpu_hv if Hyper-V is + * enabled in CPUID. + */ + WARN_ON_ONCE(vcpu->arch.hyperv_enabled); return; } - if (!to_hv_vcpu(vcpu) && kvm_hv_vcpu_init(vcpu)) - return; + memset(&hv_vcpu->cpuid_cache, 0, sizeof(hv_vcpu->cpuid_cache)); - hv_vcpu = to_hv_vcpu(vcpu); + if (!vcpu->arch.hyperv_enabled) + return; entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_FEATURES); if (entry) { hv_vcpu->cpuid_cache.features_eax = entry->eax; hv_vcpu->cpuid_cache.features_ebx = entry->ebx; hv_vcpu->cpuid_cache.features_edx = entry->edx; - } else { - hv_vcpu->cpuid_cache.features_eax = 0; - hv_vcpu->cpuid_cache.features_ebx = 0; - hv_vcpu->cpuid_cache.features_edx = 0; } entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_ENLIGHTMENT_INFO); if (entry) { hv_vcpu->cpuid_cache.enlightenments_eax = entry->eax; hv_vcpu->cpuid_cache.enlightenments_ebx = entry->ebx; - } else { - hv_vcpu->cpuid_cache.enlightenments_eax = 0; - hv_vcpu->cpuid_cache.enlightenments_ebx = 0; } entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES); if (entry) hv_vcpu->cpuid_cache.syndbg_cap_eax = entry->eax; - else - hv_vcpu->cpuid_cache.syndbg_cap_eax = 0; + + entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_NESTED_FEATURES); + if (entry) { + hv_vcpu->cpuid_cache.nested_eax = entry->eax; + hv_vcpu->cpuid_cache.nested_ebx = entry->ebx; + } } int kvm_hv_set_enforce_cpuid(struct kvm_vcpu *vcpu, bool enforce) @@ -2552,7 +2546,7 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, case HYPERV_CPUID_NESTED_FEATURES: ent->eax = evmcs_ver; ent->eax |= HV_X64_NESTED_MSR_BITMAP; - + ent->ebx |= HV_X64_NESTED_EVMCS1_PERF_GLOBAL_CTRL; break; case HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS: diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index da2737f2a956..1030b1b50552 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -23,6 +23,9 @@ #include +/* "Hv#1" signature */ +#define HYPERV_CPUID_SIGNATURE_EAX 0x31237648 + /* * The #defines related to the synthetic debugger are required by KDNet, but * they are not documented in the Hyper-V TLFS because the synthetic debugger @@ -141,7 +144,8 @@ void kvm_hv_request_tsc_page_update(struct kvm *kvm); void kvm_hv_init_vm(struct kvm *kvm); void kvm_hv_destroy_vm(struct kvm *kvm); -void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu); +int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu); +void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu, bool hyperv_enabled); int kvm_hv_set_enforce_cpuid(struct kvm_vcpu *vcpu, bool enforce); int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args); int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 9dda989a1cf0..d7639d126e6c 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -3025,17 +3025,8 @@ int kvm_apic_accept_events(struct kvm_vcpu *vcpu) struct kvm_lapic *apic = vcpu->arch.apic; u8 sipi_vector; int r; - unsigned long pe; - if (!lapic_in_kernel(vcpu)) - return 0; - - /* - * Read pending events before calling the check_events - * callback. - */ - pe = smp_load_acquire(&apic->pending_events); - if (!pe) + if (!kvm_apic_has_pending_init_or_sipi(vcpu)) return 0; if (is_guest_mode(vcpu)) { @@ -3043,38 +3034,31 @@ int kvm_apic_accept_events(struct kvm_vcpu *vcpu) if (r < 0) return r == -EBUSY ? 0 : r; /* - * If an event has happened and caused a vmexit, - * we know INITs are latched and therefore - * we will not incorrectly deliver an APIC - * event instead of a vmexit. + * Continue processing INIT/SIPI even if a nested VM-Exit + * occurred, e.g. pending SIPIs should be dropped if INIT+SIPI + * are blocked as a result of transitioning to VMX root mode. */ } /* - * INITs are latched while CPU is in specific states - * (SMM, VMX root mode, SVM with GIF=0). - * Because a CPU cannot be in these states immediately - * after it has processed an INIT signal (and thus in - * KVM_MP_STATE_INIT_RECEIVED state), just eat SIPIs - * and leave the INIT pending. + * INITs are blocked while CPU is in specific states (SMM, VMX root + * mode, SVM with GIF=0), while SIPIs are dropped if the CPU isn't in + * wait-for-SIPI (WFS). */ - if (kvm_vcpu_latch_init(vcpu)) { + if (!kvm_apic_init_sipi_allowed(vcpu)) { WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED); - if (test_bit(KVM_APIC_SIPI, &pe)) - clear_bit(KVM_APIC_SIPI, &apic->pending_events); + clear_bit(KVM_APIC_SIPI, &apic->pending_events); return 0; } - if (test_bit(KVM_APIC_INIT, &pe)) { - clear_bit(KVM_APIC_INIT, &apic->pending_events); + if (test_and_clear_bit(KVM_APIC_INIT, &apic->pending_events)) { kvm_vcpu_reset(vcpu, true); if (kvm_vcpu_is_bsp(apic->vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED; } - if (test_bit(KVM_APIC_SIPI, &pe)) { - clear_bit(KVM_APIC_SIPI, &apic->pending_events); + if (test_and_clear_bit(KVM_APIC_SIPI, &apic->pending_events)) { if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { /* evaluate pending_events before reading the vector */ smp_rmb(); diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 117a46df5cc1..a5ac4a5a5179 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -7,6 +7,7 @@ #include #include "hyperv.h" +#include "kvm_cache_regs.h" #define KVM_APIC_INIT 0 #define KVM_APIC_SIPI 1 @@ -223,11 +224,17 @@ static inline bool kvm_vcpu_apicv_active(struct kvm_vcpu *vcpu) return lapic_in_kernel(vcpu) && vcpu->arch.apic->apicv_active; } -static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu) +static inline bool kvm_apic_has_pending_init_or_sipi(struct kvm_vcpu *vcpu) { return lapic_in_kernel(vcpu) && vcpu->arch.apic->pending_events; } +static inline bool kvm_apic_init_sipi_allowed(struct kvm_vcpu *vcpu) +{ + return !is_smm(vcpu) && + !static_call(kvm_x86_apic_init_signal_blocked)(vcpu); +} + static inline bool kvm_lowest_prio_delivery(struct kvm_lapic_irq *irq) { return (irq->delivery_mode == APIC_DM_LOWEST || diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 3552e6af3684..6f81539061d6 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1667,6 +1667,18 @@ static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, long nr) percpu_counter_add(&kvm_total_used_mmu_pages, nr); } +static void kvm_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + kvm_mod_used_mmu_pages(kvm, +1); + kvm_account_pgtable_pages((void *)sp->spt, +1); +} + +static void kvm_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + kvm_mod_used_mmu_pages(kvm, -1); + kvm_account_pgtable_pages((void *)sp->spt, -1); +} + static void kvm_mmu_free_shadow_page(struct kvm_mmu_page *sp) { MMU_WARN_ON(!is_empty_shadow_page(sp->spt)); @@ -2124,7 +2136,7 @@ static struct kvm_mmu_page *kvm_mmu_alloc_shadow_page(struct kvm *kvm, */ sp->mmu_valid_gen = kvm->arch.mmu_valid_gen; list_add(&sp->link, &kvm->arch.active_mmu_pages); - kvm_mod_used_mmu_pages(kvm, +1); + kvm_account_mmu_page(kvm, sp); sp->gfn = gfn; sp->role = role; @@ -2458,7 +2470,7 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm, list_add(&sp->link, invalid_list); else list_move(&sp->link, invalid_list); - kvm_mod_used_mmu_pages(kvm, -1); + kvm_unaccount_mmu_page(kvm, sp); } else { /* * Remove the active root from the active page list, the root @@ -4292,7 +4304,7 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, vcpu->arch.l1tf_flush_l1d = true; if (!flags) { - trace_kvm_page_fault(fault_address, error_code); + trace_kvm_page_fault(vcpu, fault_address, error_code); if (kvm_event_needs_reinjection(vcpu)) kvm_mmu_unprotect_page_virt(vcpu, fault_address); @@ -6704,10 +6716,12 @@ int kvm_mmu_vendor_module_init(void) ret = register_shrinker(&mmu_shrinker, "x86-mmu"); if (ret) - goto out; + goto out_shrinker; return 0; +out_shrinker: + percpu_counter_destroy(&kvm_total_used_mmu_pages); out: mmu_destroy_caches(); return ret; diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 39e0205e7300..5ab5f94dcb6f 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -472,7 +472,7 @@ error: #if PTTYPE == PTTYPE_EPT /* - * Use PFERR_RSVD_MASK in error_code to to tell if EPT + * Use PFERR_RSVD_MASK in error_code to tell if EPT * misconfiguration requires to be injected. The detection is * done by is_rsvd_bits_set() above. * diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index bf2ccf9debca..672f0432d777 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -372,6 +372,16 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn, } } +static void tdp_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + kvm_account_pgtable_pages((void *)sp->spt, +1); +} + +static void tdp_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + kvm_account_pgtable_pages((void *)sp->spt, -1); +} + /** * tdp_mmu_unlink_sp() - Remove a shadow page from the list of used pages * @@ -384,6 +394,7 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn, static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp, bool shared) { + tdp_unaccount_mmu_page(kvm, sp); if (shared) spin_lock(&kvm->arch.tdp_mmu_pages_lock); else @@ -1132,6 +1143,7 @@ static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter, if (account_nx) account_huge_nx_page(kvm, sp); spin_unlock(&kvm->arch.tdp_mmu_pages_lock); + tdp_account_mmu_page(kvm, sp); return 0; } diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 76dcc8a3e849..4c620999d230 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -55,28 +55,6 @@ static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu, nested_svm_vmexit(svm); } -static bool nested_svm_handle_page_fault_workaround(struct kvm_vcpu *vcpu, - struct x86_exception *fault) -{ - struct vcpu_svm *svm = to_svm(vcpu); - struct vmcb *vmcb = svm->vmcb; - - WARN_ON(!is_guest_mode(vcpu)); - - if (vmcb12_is_intercept(&svm->nested.ctl, - INTERCEPT_EXCEPTION_OFFSET + PF_VECTOR) && - !WARN_ON_ONCE(svm->nested.nested_run_pending)) { - vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + PF_VECTOR; - vmcb->control.exit_code_hi = 0; - vmcb->control.exit_info_1 = fault->error_code; - vmcb->control.exit_info_2 = fault->address; - nested_svm_vmexit(svm); - return true; - } - - return false; -} - static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index) { struct vcpu_svm *svm = to_svm(vcpu); @@ -468,7 +446,7 @@ static void nested_save_pending_event_to_vmcb12(struct vcpu_svm *svm, unsigned int nr; if (vcpu->arch.exception.injected) { - nr = vcpu->arch.exception.nr; + nr = vcpu->arch.exception.vector; exit_int_info = nr | SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_EXEPT; if (vcpu->arch.exception.has_error_code) { @@ -781,11 +759,15 @@ int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa, struct vcpu_svm *svm = to_svm(vcpu); int ret; - trace_kvm_nested_vmrun(svm->vmcb->save.rip, vmcb12_gpa, - vmcb12->save.rip, - vmcb12->control.int_ctl, - vmcb12->control.event_inj, - vmcb12->control.nested_ctl); + trace_kvm_nested_vmenter(svm->vmcb->save.rip, + vmcb12_gpa, + vmcb12->save.rip, + vmcb12->control.int_ctl, + vmcb12->control.event_inj, + vmcb12->control.nested_ctl, + vmcb12->control.nested_cr3, + vmcb12->save.cr3, + KVM_ISA_SVM); trace_kvm_nested_intercepts(vmcb12->control.intercepts[INTERCEPT_CR] & 0xffff, vmcb12->control.intercepts[INTERCEPT_CR] >> 16, @@ -1304,44 +1286,46 @@ int nested_svm_check_permissions(struct kvm_vcpu *vcpu) return 0; } -static bool nested_exit_on_exception(struct vcpu_svm *svm) +static bool nested_svm_is_exception_vmexit(struct kvm_vcpu *vcpu, u8 vector, + u32 error_code) { - unsigned int nr = svm->vcpu.arch.exception.nr; + struct vcpu_svm *svm = to_svm(vcpu); - return (svm->nested.ctl.intercepts[INTERCEPT_EXCEPTION] & BIT(nr)); + return (svm->nested.ctl.intercepts[INTERCEPT_EXCEPTION] & BIT(vector)); } -static void nested_svm_inject_exception_vmexit(struct vcpu_svm *svm) +static void nested_svm_inject_exception_vmexit(struct kvm_vcpu *vcpu) { - unsigned int nr = svm->vcpu.arch.exception.nr; + struct kvm_queued_exception *ex = &vcpu->arch.exception_vmexit; + struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *vmcb = svm->vmcb; - vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr; + vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + ex->vector; vmcb->control.exit_code_hi = 0; - if (svm->vcpu.arch.exception.has_error_code) - vmcb->control.exit_info_1 = svm->vcpu.arch.exception.error_code; + if (ex->has_error_code) + vmcb->control.exit_info_1 = ex->error_code; /* * EXITINFO2 is undefined for all exception intercepts other * than #PF. */ - if (nr == PF_VECTOR) { - if (svm->vcpu.arch.exception.nested_apf) - vmcb->control.exit_info_2 = svm->vcpu.arch.apf.nested_apf_token; - else if (svm->vcpu.arch.exception.has_payload) - vmcb->control.exit_info_2 = svm->vcpu.arch.exception.payload; + if (ex->vector == PF_VECTOR) { + if (ex->has_payload) + vmcb->control.exit_info_2 = ex->payload; else - vmcb->control.exit_info_2 = svm->vcpu.arch.cr2; - } else if (nr == DB_VECTOR) { - /* See inject_pending_event. */ - kvm_deliver_exception_payload(&svm->vcpu); - if (svm->vcpu.arch.dr7 & DR7_GD) { - svm->vcpu.arch.dr7 &= ~DR7_GD; - kvm_update_dr7(&svm->vcpu); + vmcb->control.exit_info_2 = vcpu->arch.cr2; + } else if (ex->vector == DB_VECTOR) { + /* See kvm_check_and_inject_events(). */ + kvm_deliver_exception_payload(vcpu, ex); + + if (vcpu->arch.dr7 & DR7_GD) { + vcpu->arch.dr7 &= ~DR7_GD; + kvm_update_dr7(vcpu); } - } else - WARN_ON(svm->vcpu.arch.exception.has_payload); + } else { + WARN_ON(ex->has_payload); + } nested_svm_vmexit(svm); } @@ -1353,10 +1337,22 @@ static inline bool nested_exit_on_init(struct vcpu_svm *svm) static int svm_check_nested_events(struct kvm_vcpu *vcpu) { - struct vcpu_svm *svm = to_svm(vcpu); - bool block_nested_events = - kvm_event_needs_reinjection(vcpu) || svm->nested.nested_run_pending; struct kvm_lapic *apic = vcpu->arch.apic; + struct vcpu_svm *svm = to_svm(vcpu); + /* + * Only a pending nested run blocks a pending exception. If there is a + * previously injected event, the pending exception occurred while said + * event was being delivered and thus needs to be handled. + */ + bool block_nested_exceptions = svm->nested.nested_run_pending; + /* + * New events (not exceptions) are only recognized at instruction + * boundaries. If an event needs reinjection, then KVM is handling a + * VM-Exit that occurred _during_ instruction execution; new events are + * blocked until the instruction completes. + */ + bool block_nested_events = block_nested_exceptions || + kvm_event_needs_reinjection(vcpu); if (lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &apic->pending_events)) { @@ -1368,18 +1364,16 @@ static int svm_check_nested_events(struct kvm_vcpu *vcpu) return 0; } - if (vcpu->arch.exception.pending) { - /* - * Only a pending nested run can block a pending exception. - * Otherwise an injected NMI/interrupt should either be - * lost or delivered to the nested hypervisor in the EXITINTINFO - * vmcb field, while delivering the pending exception. - */ - if (svm->nested.nested_run_pending) + if (vcpu->arch.exception_vmexit.pending) { + if (block_nested_exceptions) return -EBUSY; - if (!nested_exit_on_exception(svm)) - return 0; - nested_svm_inject_exception_vmexit(svm); + nested_svm_inject_exception_vmexit(vcpu); + return 0; + } + + if (vcpu->arch.exception.pending) { + if (block_nested_exceptions) + return -EBUSY; return 0; } @@ -1720,8 +1714,8 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu) struct kvm_x86_nested_ops svm_nested_ops = { .leave_nested = svm_leave_nested, + .is_exception_vmexit = nested_svm_is_exception_vmexit, .check_events = svm_check_nested_events, - .handle_page_fault_workaround = nested_svm_handle_page_fault_workaround, .triple_fault = nested_svm_triple_fault, .get_nested_state_pages = svm_get_nested_state_pages, .get_state = svm_get_nested_state, diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index f3813dbacb9f..58f0077d9357 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -461,24 +461,22 @@ static int svm_update_soft_interrupt_rip(struct kvm_vcpu *vcpu) return 0; } -static void svm_queue_exception(struct kvm_vcpu *vcpu) +static void svm_inject_exception(struct kvm_vcpu *vcpu) { + struct kvm_queued_exception *ex = &vcpu->arch.exception; struct vcpu_svm *svm = to_svm(vcpu); - unsigned nr = vcpu->arch.exception.nr; - bool has_error_code = vcpu->arch.exception.has_error_code; - u32 error_code = vcpu->arch.exception.error_code; - kvm_deliver_exception_payload(vcpu); + kvm_deliver_exception_payload(vcpu, ex); - if (kvm_exception_is_soft(nr) && + if (kvm_exception_is_soft(ex->vector) && svm_update_soft_interrupt_rip(vcpu)) return; - svm->vmcb->control.event_inj = nr + svm->vmcb->control.event_inj = ex->vector | SVM_EVTINJ_VALID - | (has_error_code ? SVM_EVTINJ_VALID_ERR : 0) + | (ex->has_error_code ? SVM_EVTINJ_VALID_ERR : 0) | SVM_EVTINJ_TYPE_EXEPT; - svm->vmcb->control.event_inj_err = error_code; + svm->vmcb->control.event_inj_err = ex->error_code; } static void svm_init_erratum_383(void) @@ -1975,7 +1973,7 @@ static int npf_interception(struct kvm_vcpu *vcpu) u64 fault_address = svm->vmcb->control.exit_info_2; u64 error_code = svm->vmcb->control.exit_info_1; - trace_kvm_page_fault(fault_address, error_code); + trace_kvm_page_fault(vcpu, fault_address, error_code); return kvm_mmu_page_fault(vcpu, fault_address, error_code, static_cpu_has(X86_FEATURE_DECODEASSISTS) ? svm->vmcb->control.insn_bytes : NULL, @@ -2341,7 +2339,8 @@ void svm_set_gif(struct vcpu_svm *svm, bool value) enable_gif(svm); if (svm->vcpu.arch.smi_pending || svm->vcpu.arch.nmi_pending || - kvm_cpu_has_injectable_intr(&svm->vcpu)) + kvm_cpu_has_injectable_intr(&svm->vcpu) || + kvm_apic_has_pending_init_or_sipi(&svm->vcpu)) kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); } else { disable_gif(svm); @@ -3522,7 +3521,7 @@ void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode, /* Note, this is called iff the local APIC is in-kernel. */ if (!READ_ONCE(vcpu->arch.apic->apicv_active)) { - /* Process the interrupt via inject_pending_event */ + /* Process the interrupt via kvm_check_and_inject_events(). */ kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); return; @@ -4697,15 +4696,7 @@ static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - /* - * TODO: Last condition latch INIT signals on vCPU when - * vCPU is in guest-mode and vmcb12 defines intercept on INIT. - * To properly emulate the INIT intercept, - * svm_check_nested_events() should call nested_svm_vmexit() - * if an INIT signal is pending. - */ - return !gif_set(svm) || - (vmcb_is_intercept(&svm->vmcb->control, INTERCEPT_INIT)); + return !gif_set(svm); } static void svm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) @@ -4798,7 +4789,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .patch_hypercall = svm_patch_hypercall, .inject_irq = svm_inject_irq, .inject_nmi = svm_inject_nmi, - .queue_exception = svm_queue_exception, + .inject_exception = svm_inject_exception, .cancel_injection = svm_cancel_injection, .interrupt_allowed = svm_interrupt_allowed, .nmi_allowed = svm_nmi_allowed, diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 2120d7c060a9..bc25589ad588 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -394,20 +394,25 @@ TRACE_EVENT(kvm_inj_exception, * Tracepoint for page fault. */ TRACE_EVENT(kvm_page_fault, - TP_PROTO(unsigned long fault_address, unsigned int error_code), - TP_ARGS(fault_address, error_code), + TP_PROTO(struct kvm_vcpu *vcpu, u64 fault_address, u64 error_code), + TP_ARGS(vcpu, fault_address, error_code), TP_STRUCT__entry( - __field( unsigned long, fault_address ) - __field( unsigned int, error_code ) + __field( unsigned int, vcpu_id ) + __field( unsigned long, guest_rip ) + __field( u64, fault_address ) + __field( u64, error_code ) ), TP_fast_assign( + __entry->vcpu_id = vcpu->vcpu_id; + __entry->guest_rip = kvm_rip_read(vcpu); __entry->fault_address = fault_address; __entry->error_code = error_code; ), - TP_printk("address %lx error_code %x", + TP_printk("vcpu %u rip 0x%lx address 0x%016llx error_code 0x%llx", + __entry->vcpu_id, __entry->guest_rip, __entry->fault_address, __entry->error_code) ); @@ -589,10 +594,12 @@ TRACE_EVENT(kvm_pv_eoi, /* * Tracepoint for nested VMRUN */ -TRACE_EVENT(kvm_nested_vmrun, +TRACE_EVENT(kvm_nested_vmenter, TP_PROTO(__u64 rip, __u64 vmcb, __u64 nested_rip, __u32 int_ctl, - __u32 event_inj, bool npt), - TP_ARGS(rip, vmcb, nested_rip, int_ctl, event_inj, npt), + __u32 event_inj, bool tdp_enabled, __u64 guest_tdp_pgd, + __u64 guest_cr3, __u32 isa), + TP_ARGS(rip, vmcb, nested_rip, int_ctl, event_inj, tdp_enabled, + guest_tdp_pgd, guest_cr3, isa), TP_STRUCT__entry( __field( __u64, rip ) @@ -600,7 +607,9 @@ TRACE_EVENT(kvm_nested_vmrun, __field( __u64, nested_rip ) __field( __u32, int_ctl ) __field( __u32, event_inj ) - __field( bool, npt ) + __field( bool, tdp_enabled ) + __field( __u64, guest_pgd ) + __field( __u32, isa ) ), TP_fast_assign( @@ -609,14 +618,24 @@ TRACE_EVENT(kvm_nested_vmrun, __entry->nested_rip = nested_rip; __entry->int_ctl = int_ctl; __entry->event_inj = event_inj; - __entry->npt = npt; + __entry->tdp_enabled = tdp_enabled; + __entry->guest_pgd = tdp_enabled ? guest_tdp_pgd : guest_cr3; + __entry->isa = isa; ), - TP_printk("rip: 0x%016llx vmcb: 0x%016llx nrip: 0x%016llx int_ctl: 0x%08x " - "event_inj: 0x%08x npt: %s", - __entry->rip, __entry->vmcb, __entry->nested_rip, - __entry->int_ctl, __entry->event_inj, - __entry->npt ? "on" : "off") + TP_printk("rip: 0x%016llx %s: 0x%016llx nested_rip: 0x%016llx " + "int_ctl: 0x%08x event_inj: 0x%08x nested_%s=%s %s: 0x%016llx", + __entry->rip, + __entry->isa == KVM_ISA_VMX ? "vmcs" : "vmcb", + __entry->vmcb, + __entry->nested_rip, + __entry->int_ctl, + __entry->event_inj, + __entry->isa == KVM_ISA_VMX ? "ept" : "npt", + __entry->tdp_enabled ? "y" : "n", + !__entry->tdp_enabled ? "guest_cr3" : + __entry->isa == KVM_ISA_VMX ? "nested_eptp" : "nested_cr3", + __entry->guest_pgd) ); TRACE_EVENT(kvm_nested_intercepts, diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index c5e5dfef69c7..87c4e46daf37 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -65,6 +65,7 @@ struct vmcs_config { u64 cpu_based_3rd_exec_ctrl; u32 vmexit_ctrl; u32 vmentry_ctrl; + u64 misc; struct nested_vmx_msrs nested; }; extern struct vmcs_config vmcs_config; @@ -82,7 +83,8 @@ static inline bool cpu_has_vmx_basic_inout(void) static inline bool cpu_has_virtual_nmis(void) { - return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS; + return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS && + vmcs_config.cpu_based_exec_ctrl & CPU_BASED_NMI_WINDOW_EXITING; } static inline bool cpu_has_vmx_preemption_timer(void) @@ -224,11 +226,8 @@ static inline bool cpu_has_vmx_vmfunc(void) static inline bool cpu_has_vmx_shadow_vmcs(void) { - u64 vmx_msr; - /* check if the cpu supports writing r/o exit information fields */ - rdmsrl(MSR_IA32_VMX_MISC, vmx_msr); - if (!(vmx_msr & MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS)) + if (!(vmcs_config.misc & MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS)) return false; return vmcs_config.cpu_based_2nd_exec_ctrl & @@ -370,10 +369,7 @@ static inline bool cpu_has_vmx_invvpid_global(void) static inline bool cpu_has_vmx_intel_pt(void) { - u64 vmx_msr; - - rdmsrl(MSR_IA32_VMX_MISC, vmx_msr); - return (vmx_msr & MSR_IA32_VMX_MISC_INTEL_PT) && + return (vmcs_config.misc & MSR_IA32_VMX_MISC_INTEL_PT) && (vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_PT_USE_GPA) && (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_RTIT_CTL); } diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c index 6a61b1ae7942..d8b23c96d627 100644 --- a/arch/x86/kvm/vmx/evmcs.c +++ b/arch/x86/kvm/vmx/evmcs.c @@ -10,6 +10,8 @@ #include "vmx.h" #include "trace.h" +#define CC KVM_NESTED_VMENTER_CONSISTENCY_CHECK + DEFINE_STATIC_KEY_FALSE(enable_evmcs); #define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x) @@ -28,6 +30,8 @@ const struct evmcs_field vmcs_field_to_evmcs_1[] = { HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), EVMCS1_FIELD(HOST_IA32_EFER, host_ia32_efer, HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_IA32_PERF_GLOBAL_CTRL, host_ia32_perf_global_ctrl, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), EVMCS1_FIELD(HOST_CR0, host_cr0, HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), EVMCS1_FIELD(HOST_CR3, host_cr3, @@ -78,6 +82,8 @@ const struct evmcs_field vmcs_field_to_evmcs_1[] = { HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), EVMCS1_FIELD(GUEST_IA32_EFER, guest_ia32_efer, HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_IA32_PERF_GLOBAL_CTRL, guest_ia32_perf_global_ctrl, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), EVMCS1_FIELD(GUEST_PDPTR0, guest_pdptr0, HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), EVMCS1_FIELD(GUEST_PDPTR1, guest_pdptr1, @@ -126,6 +132,28 @@ const struct evmcs_field vmcs_field_to_evmcs_1[] = { HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), EVMCS1_FIELD(XSS_EXIT_BITMAP, xss_exit_bitmap, HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + EVMCS1_FIELD(ENCLS_EXITING_BITMAP, encls_exiting_bitmap, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + EVMCS1_FIELD(TSC_MULTIPLIER, tsc_multiplier, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + /* + * Not used by KVM: + * + * EVMCS1_FIELD(0x00006828, guest_ia32_s_cet, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + * EVMCS1_FIELD(0x0000682A, guest_ssp, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), + * EVMCS1_FIELD(0x0000682C, guest_ia32_int_ssp_table_addr, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + * EVMCS1_FIELD(0x00002816, guest_ia32_lbr_ctl, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + * EVMCS1_FIELD(0x00006C18, host_ia32_s_cet, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + * EVMCS1_FIELD(0x00006C1A, host_ssp, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + * EVMCS1_FIELD(0x00006C1C, host_ia32_int_ssp_table_addr, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + */ /* 64 bit read only */ EVMCS1_FIELD(GUEST_PHYSICAL_ADDRESS, guest_physical_address, @@ -294,19 +322,6 @@ const struct evmcs_field vmcs_field_to_evmcs_1[] = { }; const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1); -#if IS_ENABLED(CONFIG_HYPERV) -__init void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) -{ - vmcs_conf->cpu_based_exec_ctrl &= ~EVMCS1_UNSUPPORTED_EXEC_CTRL; - vmcs_conf->pin_based_exec_ctrl &= ~EVMCS1_UNSUPPORTED_PINCTRL; - vmcs_conf->cpu_based_2nd_exec_ctrl &= ~EVMCS1_UNSUPPORTED_2NDEXEC; - vmcs_conf->cpu_based_3rd_exec_ctrl = 0; - - vmcs_conf->vmexit_ctrl &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL; - vmcs_conf->vmentry_ctrl &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL; -} -#endif - bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa) { struct hv_vp_assist_page assist_page; @@ -334,6 +349,9 @@ uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu) * versions: lower 8 bits is the minimal version, higher 8 bits is the * maximum supported version. KVM supports versions from 1 to * KVM_EVMCS_VERSION. + * + * Note, do not check the Hyper-V is fully enabled in guest CPUID, this + * helper is used to _get_ the vCPU's supported CPUID. */ if (kvm_cpu_cap_get(X86_FEATURE_VMX) && (!vcpu || to_vmx(vcpu)->nested.enlightened_vmcs_enabled)) @@ -342,10 +360,67 @@ uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu) return 0; } -void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata) +enum evmcs_revision { + EVMCSv1_LEGACY, + NR_EVMCS_REVISIONS, +}; + +enum evmcs_ctrl_type { + EVMCS_EXIT_CTRLS, + EVMCS_ENTRY_CTRLS, + EVMCS_2NDEXEC, + EVMCS_PINCTRL, + EVMCS_VMFUNC, + NR_EVMCS_CTRLS, +}; + +static const u32 evmcs_unsupported_ctrls[NR_EVMCS_CTRLS][NR_EVMCS_REVISIONS] = { + [EVMCS_EXIT_CTRLS] = { + [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_VMEXIT_CTRL, + }, + [EVMCS_ENTRY_CTRLS] = { + [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_VMENTRY_CTRL, + }, + [EVMCS_2NDEXEC] = { + [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_2NDEXEC, + }, + [EVMCS_PINCTRL] = { + [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_PINCTRL, + }, + [EVMCS_VMFUNC] = { + [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_VMFUNC, + }, +}; + +static u32 evmcs_get_unsupported_ctls(enum evmcs_ctrl_type ctrl_type) +{ + enum evmcs_revision evmcs_rev = EVMCSv1_LEGACY; + + return evmcs_unsupported_ctrls[ctrl_type][evmcs_rev]; +} + +static bool evmcs_has_perf_global_ctrl(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + + /* + * PERF_GLOBAL_CTRL has a quirk where some Windows guests may fail to + * boot if a PV CPUID feature flag is not also set. Treat the fields + * as unsupported if the flag is not set in guest CPUID. This should + * be called only for guest accesses, and all guest accesses should be + * gated on Hyper-V being enabled and initialized. + */ + if (WARN_ON_ONCE(!hv_vcpu)) + return false; + + return hv_vcpu->cpuid_cache.nested_ebx & HV_X64_NESTED_EVMCS1_PERF_GLOBAL_CTRL; +} + +void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) { u32 ctl_low = (u32)*pdata; u32 ctl_high = (u32)(*pdata >> 32); + u32 unsupported_ctrls; /* * Hyper-V 2016 and 2019 try using these features even when eVMCS @@ -354,77 +429,70 @@ void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata) switch (msr_index) { case MSR_IA32_VMX_EXIT_CTLS: case MSR_IA32_VMX_TRUE_EXIT_CTLS: - ctl_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL; + unsupported_ctrls = evmcs_get_unsupported_ctls(EVMCS_EXIT_CTRLS); + if (!evmcs_has_perf_global_ctrl(vcpu)) + unsupported_ctrls |= VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; + ctl_high &= ~unsupported_ctrls; break; case MSR_IA32_VMX_ENTRY_CTLS: case MSR_IA32_VMX_TRUE_ENTRY_CTLS: - ctl_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL; + unsupported_ctrls = evmcs_get_unsupported_ctls(EVMCS_ENTRY_CTRLS); + if (!evmcs_has_perf_global_ctrl(vcpu)) + unsupported_ctrls |= VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + ctl_high &= ~unsupported_ctrls; break; case MSR_IA32_VMX_PROCBASED_CTLS2: - ctl_high &= ~EVMCS1_UNSUPPORTED_2NDEXEC; + ctl_high &= ~evmcs_get_unsupported_ctls(EVMCS_2NDEXEC); break; case MSR_IA32_VMX_TRUE_PINBASED_CTLS: case MSR_IA32_VMX_PINBASED_CTLS: - ctl_high &= ~EVMCS1_UNSUPPORTED_PINCTRL; + ctl_high &= ~evmcs_get_unsupported_ctls(EVMCS_PINCTRL); break; case MSR_IA32_VMX_VMFUNC: - ctl_low &= ~EVMCS1_UNSUPPORTED_VMFUNC; + ctl_low &= ~evmcs_get_unsupported_ctls(EVMCS_VMFUNC); break; } *pdata = ctl_low | ((u64)ctl_high << 32); } +static bool nested_evmcs_is_valid_controls(enum evmcs_ctrl_type ctrl_type, + u32 val) +{ + return !(val & evmcs_get_unsupported_ctls(ctrl_type)); +} + int nested_evmcs_check_controls(struct vmcs12 *vmcs12) { - int ret = 0; - u32 unsupp_ctl; + if (CC(!nested_evmcs_is_valid_controls(EVMCS_PINCTRL, + vmcs12->pin_based_vm_exec_control))) + return -EINVAL; - unsupp_ctl = vmcs12->pin_based_vm_exec_control & - EVMCS1_UNSUPPORTED_PINCTRL; - if (unsupp_ctl) { - trace_kvm_nested_vmenter_failed( - "eVMCS: unsupported pin-based VM-execution controls", - unsupp_ctl); - ret = -EINVAL; - } + if (CC(!nested_evmcs_is_valid_controls(EVMCS_2NDEXEC, + vmcs12->secondary_vm_exec_control))) + return -EINVAL; - unsupp_ctl = vmcs12->secondary_vm_exec_control & - EVMCS1_UNSUPPORTED_2NDEXEC; - if (unsupp_ctl) { - trace_kvm_nested_vmenter_failed( - "eVMCS: unsupported secondary VM-execution controls", - unsupp_ctl); - ret = -EINVAL; - } + if (CC(!nested_evmcs_is_valid_controls(EVMCS_EXIT_CTRLS, + vmcs12->vm_exit_controls))) + return -EINVAL; - unsupp_ctl = vmcs12->vm_exit_controls & - EVMCS1_UNSUPPORTED_VMEXIT_CTRL; - if (unsupp_ctl) { - trace_kvm_nested_vmenter_failed( - "eVMCS: unsupported VM-exit controls", - unsupp_ctl); - ret = -EINVAL; - } + if (CC(!nested_evmcs_is_valid_controls(EVMCS_ENTRY_CTRLS, + vmcs12->vm_entry_controls))) + return -EINVAL; - unsupp_ctl = vmcs12->vm_entry_controls & - EVMCS1_UNSUPPORTED_VMENTRY_CTRL; - if (unsupp_ctl) { - trace_kvm_nested_vmenter_failed( - "eVMCS: unsupported VM-entry controls", - unsupp_ctl); - ret = -EINVAL; - } + /* + * VM-Func controls are 64-bit, but KVM currently doesn't support any + * controls in bits 63:32, i.e. dropping those bits on the consistency + * check is intentional. + */ + if (WARN_ON_ONCE(vmcs12->vm_function_control >> 32)) + return -EINVAL; - unsupp_ctl = vmcs12->vm_function_control & EVMCS1_UNSUPPORTED_VMFUNC; - if (unsupp_ctl) { - trace_kvm_nested_vmenter_failed( - "eVMCS: unsupported VM-function controls", - unsupp_ctl); - ret = -EINVAL; - } + if (CC(!nested_evmcs_is_valid_controls(EVMCS_VMFUNC, + vmcs12->vm_function_control))) + return -EINVAL; - return ret; + return 0; } int nested_enable_evmcs(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/evmcs.h index f886a8ff0342..6f746ef3c038 100644 --- a/arch/x86/kvm/vmx/evmcs.h +++ b/arch/x86/kvm/vmx/evmcs.h @@ -42,8 +42,6 @@ DECLARE_STATIC_KEY_FALSE(enable_evmcs); * PLE_GAP = 0x00004020, * PLE_WINDOW = 0x00004022, * VMX_PREEMPTION_TIMER_VALUE = 0x0000482E, - * GUEST_IA32_PERF_GLOBAL_CTRL = 0x00002808, - * HOST_IA32_PERF_GLOBAL_CTRL = 0x00002c04, * * Currently unsupported in KVM: * GUEST_IA32_RTIT_CTL = 0x00002814, @@ -61,9 +59,8 @@ DECLARE_STATIC_KEY_FALSE(enable_evmcs); SECONDARY_EXEC_TSC_SCALING | \ SECONDARY_EXEC_PAUSE_LOOP_EXITING) #define EVMCS1_UNSUPPORTED_VMEXIT_CTRL \ - (VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ - VM_EXIT_SAVE_VMX_PREEMPTION_TIMER) -#define EVMCS1_UNSUPPORTED_VMENTRY_CTRL (VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) + (VM_EXIT_SAVE_VMX_PREEMPTION_TIMER) +#define EVMCS1_UNSUPPORTED_VMENTRY_CTRL (0) #define EVMCS1_UNSUPPORTED_VMFUNC (VMX_VMFUNC_EPTP_SWITCHING) struct evmcs_field { @@ -212,7 +209,6 @@ static inline void evmcs_load(u64 phys_addr) vp_ap->enlighten_vmentry = 1; } -__init void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf); #else /* !IS_ENABLED(CONFIG_HYPERV) */ static __always_inline void evmcs_write64(unsigned long field, u64 value) {} static inline void evmcs_write32(unsigned long field, u32 value) {} @@ -243,7 +239,7 @@ bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa); uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu); int nested_enable_evmcs(struct kvm_vcpu *vcpu, uint16_t *vmcs_version); -void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata); +void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata); int nested_evmcs_check_controls(struct vmcs12 *vmcs12); #endif /* __KVM_X86_VMX_EVMCS_H */ diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 7eaf96064cb0..0c62352dda6a 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -439,61 +439,22 @@ static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12, return inequality ^ bit; } - -/* - * KVM wants to inject page-faults which it got to the guest. This function - * checks whether in a nested guest, we need to inject them to L1 or L2. - */ -static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned long *exit_qual) -{ - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - unsigned int nr = vcpu->arch.exception.nr; - bool has_payload = vcpu->arch.exception.has_payload; - unsigned long payload = vcpu->arch.exception.payload; - - if (nr == PF_VECTOR) { - if (vcpu->arch.exception.nested_apf) { - *exit_qual = vcpu->arch.apf.nested_apf_token; - return 1; - } - if (nested_vmx_is_page_fault_vmexit(vmcs12, - vcpu->arch.exception.error_code)) { - *exit_qual = has_payload ? payload : vcpu->arch.cr2; - return 1; - } - } else if (vmcs12->exception_bitmap & (1u << nr)) { - if (nr == DB_VECTOR) { - if (!has_payload) { - payload = vcpu->arch.dr6; - payload &= ~DR6_BT; - payload ^= DR6_ACTIVE_LOW; - } - *exit_qual = payload; - } else - *exit_qual = 0; - return 1; - } - - return 0; -} - -static bool nested_vmx_handle_page_fault_workaround(struct kvm_vcpu *vcpu, - struct x86_exception *fault) +static bool nested_vmx_is_exception_vmexit(struct kvm_vcpu *vcpu, u8 vector, + u32 error_code) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - WARN_ON(!is_guest_mode(vcpu)); + /* + * Drop bits 31:16 of the error code when performing the #PF mask+match + * check. All VMCS fields involved are 32 bits, but Intel CPUs never + * set bits 31:16 and VMX disallows setting bits 31:16 in the injected + * error code. Including the to-be-dropped bits in the check might + * result in an "impossible" or missed exit from L1's perspective. + */ + if (vector == PF_VECTOR) + return nested_vmx_is_page_fault_vmexit(vmcs12, (u16)error_code); - if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code) && - !WARN_ON_ONCE(to_vmx(vcpu)->nested.nested_run_pending)) { - vmcs12->vm_exit_intr_error_code = fault->error_code; - nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, - PF_VECTOR | INTR_TYPE_HARD_EXCEPTION | - INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK, - fault->address); - return true; - } - return false; + return (vmcs12->exception_bitmap & (1u << vector)); } static int nested_vmx_check_io_bitmap_controls(struct kvm_vcpu *vcpu, @@ -1607,6 +1568,10 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields vmcs12->guest_rflags = evmcs->guest_rflags; vmcs12->guest_interruptibility_info = evmcs->guest_interruptibility_info; + /* + * Not present in struct vmcs12: + * vmcs12->guest_ssp = evmcs->guest_ssp; + */ } if (unlikely(!(hv_clean_fields & @@ -1653,6 +1618,13 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields vmcs12->host_fs_selector = evmcs->host_fs_selector; vmcs12->host_gs_selector = evmcs->host_gs_selector; vmcs12->host_tr_selector = evmcs->host_tr_selector; + vmcs12->host_ia32_perf_global_ctrl = evmcs->host_ia32_perf_global_ctrl; + /* + * Not present in struct vmcs12: + * vmcs12->host_ia32_s_cet = evmcs->host_ia32_s_cet; + * vmcs12->host_ssp = evmcs->host_ssp; + * vmcs12->host_ia32_int_ssp_table_addr = evmcs->host_ia32_int_ssp_table_addr; + */ } if (unlikely(!(hv_clean_fields & @@ -1720,6 +1692,8 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields vmcs12->tsc_offset = evmcs->tsc_offset; vmcs12->virtual_apic_page_addr = evmcs->virtual_apic_page_addr; vmcs12->xss_exit_bitmap = evmcs->xss_exit_bitmap; + vmcs12->encls_exiting_bitmap = evmcs->encls_exiting_bitmap; + vmcs12->tsc_multiplier = evmcs->tsc_multiplier; } if (unlikely(!(hv_clean_fields & @@ -1767,6 +1741,13 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields vmcs12->guest_bndcfgs = evmcs->guest_bndcfgs; vmcs12->guest_activity_state = evmcs->guest_activity_state; vmcs12->guest_sysenter_cs = evmcs->guest_sysenter_cs; + vmcs12->guest_ia32_perf_global_ctrl = evmcs->guest_ia32_perf_global_ctrl; + /* + * Not present in struct vmcs12: + * vmcs12->guest_ia32_s_cet = evmcs->guest_ia32_s_cet; + * vmcs12->guest_ia32_lbr_ctl = evmcs->guest_ia32_lbr_ctl; + * vmcs12->guest_ia32_int_ssp_table_addr = evmcs->guest_ia32_int_ssp_table_addr; + */ } /* @@ -1869,12 +1850,23 @@ static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) * evmcs->vm_exit_msr_store_count = vmcs12->vm_exit_msr_store_count; * evmcs->vm_exit_msr_load_count = vmcs12->vm_exit_msr_load_count; * evmcs->vm_entry_msr_load_count = vmcs12->vm_entry_msr_load_count; + * evmcs->guest_ia32_perf_global_ctrl = vmcs12->guest_ia32_perf_global_ctrl; + * evmcs->host_ia32_perf_global_ctrl = vmcs12->host_ia32_perf_global_ctrl; + * evmcs->encls_exiting_bitmap = vmcs12->encls_exiting_bitmap; + * evmcs->tsc_multiplier = vmcs12->tsc_multiplier; * * Not present in struct vmcs12: * evmcs->exit_io_instruction_ecx = vmcs12->exit_io_instruction_ecx; * evmcs->exit_io_instruction_esi = vmcs12->exit_io_instruction_esi; * evmcs->exit_io_instruction_edi = vmcs12->exit_io_instruction_edi; * evmcs->exit_io_instruction_eip = vmcs12->exit_io_instruction_eip; + * evmcs->host_ia32_s_cet = vmcs12->host_ia32_s_cet; + * evmcs->host_ssp = vmcs12->host_ssp; + * evmcs->host_ia32_int_ssp_table_addr = vmcs12->host_ia32_int_ssp_table_addr; + * evmcs->guest_ia32_s_cet = vmcs12->guest_ia32_s_cet; + * evmcs->guest_ia32_lbr_ctl = vmcs12->guest_ia32_lbr_ctl; + * evmcs->guest_ia32_int_ssp_table_addr = vmcs12->guest_ia32_int_ssp_table_addr; + * evmcs->guest_ssp = vmcs12->guest_ssp; */ evmcs->guest_es_selector = vmcs12->guest_es_selector; @@ -1982,7 +1974,7 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( bool evmcs_gpa_changed = false; u64 evmcs_gpa; - if (likely(!vmx->nested.enlightened_vmcs_enabled)) + if (likely(!guest_cpuid_has_evmcs(vcpu))) return EVMPTRLD_DISABLED; if (!nested_enlightened_vmentry(vcpu, &evmcs_gpa)) { @@ -2328,9 +2320,14 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0 * are emulated by vmx_set_efer() in prepare_vmcs02(), but speculate * on the related bits (if supported by the CPU) in the hope that * we can avoid VMWrites during vmx_set_efer(). + * + * Similarly, take vmcs01's PERF_GLOBAL_CTRL in the hope that if KVM is + * loading PERF_GLOBAL_CTRL via the VMCS for L1, then KVM will want to + * do the same for L2. */ exec_control = __vm_entry_controls_get(vmcs01); - exec_control |= vmcs12->vm_entry_controls; + exec_control |= (vmcs12->vm_entry_controls & + ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL); exec_control &= ~(VM_ENTRY_IA32E_MODE | VM_ENTRY_LOAD_IA32_EFER); if (cpu_has_load_ia32_efer()) { if (guest_efer & EFER_LMA) @@ -2863,7 +2860,7 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu, nested_check_vm_entry_controls(vcpu, vmcs12)) return -EINVAL; - if (to_vmx(vcpu)->nested.enlightened_vmcs_enabled) + if (guest_cpuid_has_evmcs(vcpu)) return nested_evmcs_check_controls(vmcs12); return 0; @@ -3145,7 +3142,7 @@ static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) * L2 was running), map it here to make sure vmcs12 changes are * properly reflected. */ - if (vmx->nested.enlightened_vmcs_enabled && + if (guest_cpuid_has_evmcs(vcpu) && vmx->nested.hv_evmcs_vmptr == EVMPTR_MAP_PENDING) { enum nested_evmptrld_status evmptrld_status = nested_vmx_handle_enlightened_vmptrld(vcpu, false); @@ -3364,12 +3361,24 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, }; u32 failed_index; + trace_kvm_nested_vmenter(kvm_rip_read(vcpu), + vmx->nested.current_vmptr, + vmcs12->guest_rip, + vmcs12->guest_intr_status, + vmcs12->vm_entry_intr_info_field, + vmcs12->secondary_vm_exec_control & SECONDARY_EXEC_ENABLE_EPT, + vmcs12->ept_pointer, + vmcs12->guest_cr3, + KVM_ISA_VMX); + kvm_service_local_tlb_flush_requests(vcpu); evaluate_pending_interrupts = exec_controls_get(vmx) & (CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING); if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu)) evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu); + if (!evaluate_pending_interrupts) + evaluate_pending_interrupts |= kvm_apic_has_pending_init_or_sipi(vcpu); if (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) @@ -3450,18 +3459,10 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, } /* - * If L1 had a pending IRQ/NMI until it executed - * VMLAUNCH/VMRESUME which wasn't delivered because it was - * disallowed (e.g. interrupts disabled), L0 needs to - * evaluate if this pending event should cause an exit from L2 - * to L1 or delivered directly to L2 (e.g. In case L1 don't - * intercept EXTERNAL_INTERRUPT). - * - * Usually this would be handled by the processor noticing an - * IRQ/NMI window request, or checking RVI during evaluation of - * pending virtual interrupts. However, this setting was done - * on VMCS01 and now VMCS02 is active instead. Thus, we force L0 - * to perform pending event evaluation by requesting a KVM_REQ_EVENT. + * Re-evaluate pending events if L1 had a pending IRQ/NMI/INIT/SIPI + * when it executed VMLAUNCH/VMRESUME, as entering non-root mode can + * effectively unblock various events, e.g. INIT/SIPI cause VM-Exit + * unconditionally. */ if (unlikely(evaluate_pending_interrupts)) kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -3718,7 +3719,7 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu, is_double_fault(exit_intr_info))) { vmcs12->idt_vectoring_info_field = 0; } else if (vcpu->arch.exception.injected) { - nr = vcpu->arch.exception.nr; + nr = vcpu->arch.exception.vector; idt_vectoring = nr | VECTORING_INFO_VALID_MASK; if (kvm_exception_is_soft(nr)) { @@ -3819,19 +3820,40 @@ mmio_needed: return -ENXIO; } -static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu, - unsigned long exit_qual) +static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu) { + struct kvm_queued_exception *ex = &vcpu->arch.exception_vmexit; + u32 intr_info = ex->vector | INTR_INFO_VALID_MASK; struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - unsigned int nr = vcpu->arch.exception.nr; - u32 intr_info = nr | INTR_INFO_VALID_MASK; + unsigned long exit_qual; - if (vcpu->arch.exception.has_error_code) { - vmcs12->vm_exit_intr_error_code = vcpu->arch.exception.error_code; + if (ex->has_payload) { + exit_qual = ex->payload; + } else if (ex->vector == PF_VECTOR) { + exit_qual = vcpu->arch.cr2; + } else if (ex->vector == DB_VECTOR) { + exit_qual = vcpu->arch.dr6; + exit_qual &= ~DR6_BT; + exit_qual ^= DR6_ACTIVE_LOW; + } else { + exit_qual = 0; + } + + if (ex->has_error_code) { + /* + * Intel CPUs do not generate error codes with bits 31:16 set, + * and more importantly VMX disallows setting bits 31:16 in the + * injected error code for VM-Entry. Drop the bits to mimic + * hardware and avoid inducing failure on nested VM-Entry if L1 + * chooses to inject the exception back to L2. AMD CPUs _do_ + * generate "full" 32-bit error codes, so KVM allows userspace + * to inject exception error codes with bits 31:16 set. + */ + vmcs12->vm_exit_intr_error_code = (u16)ex->error_code; intr_info |= INTR_INFO_DELIVER_CODE_MASK; } - if (kvm_exception_is_soft(nr)) + if (kvm_exception_is_soft(ex->vector)) intr_info |= INTR_TYPE_SOFT_EXCEPTION; else intr_info |= INTR_TYPE_HARD_EXCEPTION; @@ -3844,16 +3866,39 @@ static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu, } /* - * Returns true if a debug trap is pending delivery. + * Returns true if a debug trap is (likely) pending delivery. Infer the class + * of a #DB (trap-like vs. fault-like) from the exception payload (to-be-DR6). + * Using the payload is flawed because code breakpoints (fault-like) and data + * breakpoints (trap-like) set the same bits in DR6 (breakpoint detected), i.e. + * this will return false positives if a to-be-injected code breakpoint #DB is + * pending (from KVM's perspective, but not "pending" across an instruction + * boundary). ICEBP, a.k.a. INT1, is also not reflected here even though it + * too is trap-like. * - * In KVM, debug traps bear an exception payload. As such, the class of a #DB - * exception may be inferred from the presence of an exception payload. + * KVM "works" despite these flaws as ICEBP isn't currently supported by the + * emulator, Monitor Trap Flag is not marked pending on intercepted #DBs (the + * #DB has already happened), and MTF isn't marked pending on code breakpoints + * from the emulator (because such #DBs are fault-like and thus don't trigger + * actions that fire on instruction retire). */ -static inline bool vmx_pending_dbg_trap(struct kvm_vcpu *vcpu) +static unsigned long vmx_get_pending_dbg_trap(struct kvm_queued_exception *ex) { - return vcpu->arch.exception.pending && - vcpu->arch.exception.nr == DB_VECTOR && - vcpu->arch.exception.payload; + if (!ex->pending || ex->vector != DB_VECTOR) + return 0; + + /* General Detect #DBs are always fault-like. */ + return ex->payload & ~DR6_BD; +} + +/* + * Returns true if there's a pending #DB exception that is lower priority than + * a pending Monitor Trap Flag VM-Exit. TSS T-flag #DBs are not emulated by + * KVM, but could theoretically be injected by userspace. Note, this code is + * imperfect, see above. + */ +static bool vmx_is_low_priority_db_trap(struct kvm_queued_exception *ex) +{ + return vmx_get_pending_dbg_trap(ex) & ~DR6_BT; } /* @@ -3865,9 +3910,11 @@ static inline bool vmx_pending_dbg_trap(struct kvm_vcpu *vcpu) */ static void nested_vmx_update_pending_dbg(struct kvm_vcpu *vcpu) { - if (vmx_pending_dbg_trap(vcpu)) - vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, - vcpu->arch.exception.payload); + unsigned long pending_dbg; + + pending_dbg = vmx_get_pending_dbg_trap(&vcpu->arch.exception); + if (pending_dbg) + vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, pending_dbg); } static bool nested_vmx_preemption_timer_pending(struct kvm_vcpu *vcpu) @@ -3876,21 +3923,113 @@ static bool nested_vmx_preemption_timer_pending(struct kvm_vcpu *vcpu) to_vmx(vcpu)->nested.preemption_timer_expired; } +static bool vmx_has_nested_events(struct kvm_vcpu *vcpu) +{ + return nested_vmx_preemption_timer_pending(vcpu) || + to_vmx(vcpu)->nested.mtf_pending; +} + +/* + * Per the Intel SDM's table "Priority Among Concurrent Events", with minor + * edits to fill in missing examples, e.g. #DB due to split-lock accesses, + * and less minor edits to splice in the priority of VMX Non-Root specific + * events, e.g. MTF and NMI/INTR-window exiting. + * + * 1 Hardware Reset and Machine Checks + * - RESET + * - Machine Check + * + * 2 Trap on Task Switch + * - T flag in TSS is set (on task switch) + * + * 3 External Hardware Interventions + * - FLUSH + * - STOPCLK + * - SMI + * - INIT + * + * 3.5 Monitor Trap Flag (MTF) VM-exit[1] + * + * 4 Traps on Previous Instruction + * - Breakpoints + * - Trap-class Debug Exceptions (#DB due to TF flag set, data/I-O + * breakpoint, or #DB due to a split-lock access) + * + * 4.3 VMX-preemption timer expired VM-exit + * + * 4.6 NMI-window exiting VM-exit[2] + * + * 5 Nonmaskable Interrupts (NMI) + * + * 5.5 Interrupt-window exiting VM-exit and Virtual-interrupt delivery + * + * 6 Maskable Hardware Interrupts + * + * 7 Code Breakpoint Fault + * + * 8 Faults from Fetching Next Instruction + * - Code-Segment Limit Violation + * - Code Page Fault + * - Control protection exception (missing ENDBRANCH at target of indirect + * call or jump) + * + * 9 Faults from Decoding Next Instruction + * - Instruction length > 15 bytes + * - Invalid Opcode + * - Coprocessor Not Available + * + *10 Faults on Executing Instruction + * - Overflow + * - Bound error + * - Invalid TSS + * - Segment Not Present + * - Stack fault + * - General Protection + * - Data Page Fault + * - Alignment Check + * - x86 FPU Floating-point exception + * - SIMD floating-point exception + * - Virtualization exception + * - Control protection exception + * + * [1] Per the "Monitor Trap Flag" section: System-management interrupts (SMIs), + * INIT signals, and higher priority events take priority over MTF VM exits. + * MTF VM exits take priority over debug-trap exceptions and lower priority + * events. + * + * [2] Debug-trap exceptions and higher priority events take priority over VM exits + * caused by the VMX-preemption timer. VM exits caused by the VMX-preemption + * timer take priority over VM exits caused by the "NMI-window exiting" + * VM-execution control and lower priority events. + * + * [3] Debug-trap exceptions and higher priority events take priority over VM exits + * caused by "NMI-window exiting". VM exits caused by this control take + * priority over non-maskable interrupts (NMIs) and lower priority events. + * + * [4] Virtual-interrupt delivery has the same priority as that of VM exits due to + * the 1-setting of the "interrupt-window exiting" VM-execution control. Thus, + * non-maskable interrupts (NMIs) and higher priority events take priority over + * delivery of a virtual interrupt; delivery of a virtual interrupt takes + * priority over external interrupts and lower priority events. + */ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) { - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long exit_qual; - bool block_nested_events = - vmx->nested.nested_run_pending || kvm_event_needs_reinjection(vcpu); - bool mtf_pending = vmx->nested.mtf_pending; struct kvm_lapic *apic = vcpu->arch.apic; - + struct vcpu_vmx *vmx = to_vmx(vcpu); /* - * Clear the MTF state. If a higher priority VM-exit is delivered first, - * this state is discarded. + * Only a pending nested run blocks a pending exception. If there is a + * previously injected event, the pending exception occurred while said + * event was being delivered and thus needs to be handled. */ - if (!block_nested_events) - vmx->nested.mtf_pending = false; + bool block_nested_exceptions = vmx->nested.nested_run_pending; + /* + * New events (not exceptions) are only recognized at instruction + * boundaries. If an event needs reinjection, then KVM is handling a + * VM-Exit that occurred _during_ instruction execution; new events are + * blocked until the instruction completes. + */ + bool block_nested_events = block_nested_exceptions || + kvm_event_needs_reinjection(vcpu); if (lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &apic->pending_events)) { @@ -3900,6 +4039,9 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) clear_bit(KVM_APIC_INIT, &apic->pending_events); if (vcpu->arch.mp_state != KVM_MP_STATE_INIT_RECEIVED) nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0); + + /* MTF is discarded if the vCPU is in WFS. */ + vmx->nested.mtf_pending = false; return 0; } @@ -3909,31 +4051,41 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) return -EBUSY; clear_bit(KVM_APIC_SIPI, &apic->pending_events); - if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) + if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { nested_vmx_vmexit(vcpu, EXIT_REASON_SIPI_SIGNAL, 0, apic->sipi_vector & 0xFFUL); - return 0; + return 0; + } + /* Fallthrough, the SIPI is completely ignored. */ } /* - * Process any exceptions that are not debug traps before MTF. + * Process exceptions that are higher priority than Monitor Trap Flag: + * fault-like exceptions, TSS T flag #DB (not emulated by KVM, but + * could theoretically come in from userspace), and ICEBP (INT1). * - * Note that only a pending nested run can block a pending exception. - * Otherwise an injected NMI/interrupt should either be - * lost or delivered to the nested hypervisor in the IDT_VECTORING_INFO, - * while delivering the pending exception. + * TODO: SMIs have higher priority than MTF and trap-like #DBs (except + * for TSS T flag #DBs). KVM also doesn't save/restore pending MTF + * across SMI/RSM as it should; that needs to be addressed in order to + * prioritize SMI over MTF and trap-like #DBs. */ - - if (vcpu->arch.exception.pending && !vmx_pending_dbg_trap(vcpu)) { - if (vmx->nested.nested_run_pending) + if (vcpu->arch.exception_vmexit.pending && + !vmx_is_low_priority_db_trap(&vcpu->arch.exception_vmexit)) { + if (block_nested_exceptions) return -EBUSY; - if (!nested_vmx_check_exception(vcpu, &exit_qual)) - goto no_vmexit; - nested_vmx_inject_exception_vmexit(vcpu, exit_qual); + + nested_vmx_inject_exception_vmexit(vcpu); return 0; } - if (mtf_pending) { + if (vcpu->arch.exception.pending && + !vmx_is_low_priority_db_trap(&vcpu->arch.exception)) { + if (block_nested_exceptions) + return -EBUSY; + goto no_vmexit; + } + + if (vmx->nested.mtf_pending) { if (block_nested_events) return -EBUSY; nested_vmx_update_pending_dbg(vcpu); @@ -3941,15 +4093,20 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) return 0; } - if (vcpu->arch.exception.pending) { - if (vmx->nested.nested_run_pending) + if (vcpu->arch.exception_vmexit.pending) { + if (block_nested_exceptions) return -EBUSY; - if (!nested_vmx_check_exception(vcpu, &exit_qual)) - goto no_vmexit; - nested_vmx_inject_exception_vmexit(vcpu, exit_qual); + + nested_vmx_inject_exception_vmexit(vcpu); return 0; } + if (vcpu->arch.exception.pending) { + if (block_nested_exceptions) + return -EBUSY; + goto no_vmexit; + } + if (nested_vmx_preemption_timer_pending(vcpu)) { if (block_nested_events) return -EBUSY; @@ -4255,14 +4412,6 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, nested_vmx_abort(vcpu, VMX_ABORT_SAVE_GUEST_MSR_FAIL); } - - /* - * Drop what we picked up for L2 via vmx_complete_interrupts. It is - * preserved above and would only end up incorrectly in L1. - */ - vcpu->arch.nmi_injected = false; - kvm_clear_exception_queue(vcpu); - kvm_clear_interrupt_queue(vcpu); } /* @@ -4538,6 +4687,9 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + /* Pending MTF traps are discarded on VM-Exit. */ + vmx->nested.mtf_pending = false; + /* trying to cancel vmlaunch/vmresume is a bug */ WARN_ON_ONCE(vmx->nested.nested_run_pending); @@ -4602,6 +4754,17 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, WARN_ON_ONCE(nested_early_check); } + /* + * Drop events/exceptions that were queued for re-injection to L2 + * (picked up via vmx_complete_interrupts()), as well as exceptions + * that were pending for L2. Note, this must NOT be hoisted above + * prepare_vmcs12(), events/exceptions queued for re-injection need to + * be captured in vmcs12 (see vmcs12_save_pending_event()). + */ + vcpu->arch.nmi_injected = false; + kvm_clear_exception_queue(vcpu); + kvm_clear_interrupt_queue(vcpu); + vmx_switch_vmcs(vcpu, &vmx->vmcs01); /* Update any VMCS fields that might have changed while L2 ran */ @@ -5030,8 +5193,8 @@ static int handle_vmxoff(struct kvm_vcpu *vcpu) free_nested(vcpu); - /* Process a latched INIT during time CPU was in VMX operation */ - kvm_make_request(KVM_REQ_EVENT, vcpu); + if (kvm_apic_has_pending_init_or_sipi(vcpu)) + kvm_make_request(KVM_REQ_EVENT, vcpu); return nested_vmx_succeed(vcpu); } @@ -5067,7 +5230,7 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) * state. It is possible that the area will stay mapped as * vmx->nested.hv_evmcs but this shouldn't be a problem. */ - if (likely(!vmx->nested.enlightened_vmcs_enabled || + if (likely(!guest_cpuid_has_evmcs(vcpu) || !nested_enlightened_vmentry(vcpu, &evmcs_gpa))) { if (vmptr == vmx->nested.current_vmptr) nested_release_vmcs12(vcpu); @@ -6463,6 +6626,9 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, if (ret) goto error_guest_mode; + if (vmx->nested.mtf_pending) + kvm_make_request(KVM_REQ_EVENT, vcpu); + return 0; error_guest_mode: @@ -6522,8 +6688,10 @@ static u64 nested_vmx_calc_vmcs_enum_msr(void) * bit in the high half is on if the corresponding bit in the control field * may be on. See also vmx_control_verify(). */ -void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) +void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) { + struct nested_vmx_msrs *msrs = &vmcs_conf->nested; + /* * Note that as a general rule, the high half of the MSRs (bits in * the control fields which may be 1) should be initialized by the @@ -6540,11 +6708,10 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) */ /* pin-based controls */ - rdmsr(MSR_IA32_VMX_PINBASED_CTLS, - msrs->pinbased_ctls_low, - msrs->pinbased_ctls_high); - msrs->pinbased_ctls_low |= + msrs->pinbased_ctls_low = PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR; + + msrs->pinbased_ctls_high = vmcs_conf->pin_based_exec_ctrl; msrs->pinbased_ctls_high &= PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING | @@ -6555,50 +6722,47 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) PIN_BASED_VMX_PREEMPTION_TIMER; /* exit controls */ - rdmsr(MSR_IA32_VMX_EXIT_CTLS, - msrs->exit_ctls_low, - msrs->exit_ctls_high); msrs->exit_ctls_low = VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR; + msrs->exit_ctls_high = vmcs_conf->vmexit_ctrl; msrs->exit_ctls_high &= #ifdef CONFIG_X86_64 VM_EXIT_HOST_ADDR_SPACE_SIZE | #endif VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT | - VM_EXIT_CLEAR_BNDCFGS | VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; + VM_EXIT_CLEAR_BNDCFGS; msrs->exit_ctls_high |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER | - VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT; + VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT | + VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; /* We support free control of debug control saving. */ msrs->exit_ctls_low &= ~VM_EXIT_SAVE_DEBUG_CONTROLS; /* entry controls */ - rdmsr(MSR_IA32_VMX_ENTRY_CTLS, - msrs->entry_ctls_low, - msrs->entry_ctls_high); msrs->entry_ctls_low = VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR; + + msrs->entry_ctls_high = vmcs_conf->vmentry_ctrl; msrs->entry_ctls_high &= #ifdef CONFIG_X86_64 VM_ENTRY_IA32E_MODE | #endif - VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_BNDCFGS | - VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_BNDCFGS; msrs->entry_ctls_high |= - (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER); + (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER | + VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL); /* We support free control of debug control loading. */ msrs->entry_ctls_low &= ~VM_ENTRY_LOAD_DEBUG_CONTROLS; /* cpu-based controls */ - rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, - msrs->procbased_ctls_low, - msrs->procbased_ctls_high); msrs->procbased_ctls_low = CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR; + + msrs->procbased_ctls_high = vmcs_conf->cpu_based_exec_ctrl; msrs->procbased_ctls_high &= CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING | CPU_BASED_USE_TSC_OFFSETTING | @@ -6632,12 +6796,9 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) * depend on CPUID bits, they are added later by * vmx_vcpu_after_set_cpuid. */ - if (msrs->procbased_ctls_high & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) - rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2, - msrs->secondary_ctls_low, - msrs->secondary_ctls_high); - msrs->secondary_ctls_low = 0; + + msrs->secondary_ctls_high = vmcs_conf->cpu_based_2nd_exec_ctrl; msrs->secondary_ctls_high &= SECONDARY_EXEC_DESC | SECONDARY_EXEC_ENABLE_RDTSCP | @@ -6717,10 +6878,7 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) msrs->secondary_ctls_high |= SECONDARY_EXEC_ENCLS_EXITING; /* miscellaneous data */ - rdmsr(MSR_IA32_VMX_MISC, - msrs->misc_low, - msrs->misc_high); - msrs->misc_low &= VMX_MISC_SAVE_EFER_LMA; + msrs->misc_low = (u32)vmcs_conf->misc & VMX_MISC_SAVE_EFER_LMA; msrs->misc_low |= MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS | VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE | @@ -6814,9 +6972,9 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)) struct kvm_x86_nested_ops vmx_nested_ops = { .leave_nested = vmx_leave_nested, + .is_exception_vmexit = nested_vmx_is_exception_vmexit, .check_events = vmx_check_nested_events, - .handle_page_fault_workaround = nested_vmx_handle_page_fault_workaround, - .hv_timer_pending = nested_vmx_preemption_timer_pending, + .has_events = vmx_has_nested_events, .triple_fault = nested_vmx_triple_fault, .get_state = vmx_get_nested_state, .set_state = vmx_set_nested_state, diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index 88b00a7359e4..6312c9541c3c 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -17,7 +17,7 @@ enum nvmx_vmentry_status { }; void vmx_leave_nested(struct kvm_vcpu *vcpu); -void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps); +void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps); void nested_vmx_hardware_unsetup(void); __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)); void nested_vmx_set_vmcs_shadowing_bitmap(void); diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c index aba8cebdc587..8f95c7c01433 100644 --- a/arch/x86/kvm/vmx/sgx.c +++ b/arch/x86/kvm/vmx/sgx.c @@ -129,7 +129,7 @@ static int sgx_inject_fault(struct kvm_vcpu *vcpu, gva_t gva, int trapnr) ex.address = gva; ex.error_code_valid = true; ex.nested_page_fault = false; - kvm_inject_page_fault(vcpu, &ex); + kvm_inject_emulated_page_fault(vcpu, &ex); } else { kvm_inject_gp(vcpu, 0); } diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 6de96b943804..8477d8bdd69c 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -189,13 +189,16 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL) xor %ebx, %ebx .Lclear_regs: + /* Discard @regs. The register is irrelevant, it just can't be RBX. */ + pop %_ASM_AX + /* * Clear all general purpose registers except RSP and RBX to prevent * speculative use of the guest's values, even those that are reloaded * via the stack. In theory, an L1 cache miss when restoring registers * could lead to speculative execution with the guest's values. * Zeroing XORs are dirt cheap, i.e. the extra paranoia is essentially - * free. RSP and RAX are exempt as RSP is restored by hardware during + * free. RSP and RBX are exempt as RSP is restored by hardware during * VM-Exit and RBX is explicitly loaded with 0 or 1 to hold the return * value. */ @@ -216,9 +219,6 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL) xor %r15d, %r15d #endif - /* "POP" @regs. */ - add $WORD_SIZE, %_ASM_SP - /* * IMPORTANT: RSB filling and SPEC_CTRL handling must be done before * the first unbalanced RET after vmexit! @@ -234,7 +234,6 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL) FILL_RETURN_BUFFER %_ASM_CX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT,\ X86_FEATURE_RSB_VMEXIT_LITE - pop %_ASM_ARG2 /* @flags */ pop %_ASM_ARG1 /* @vmx */ @@ -293,22 +292,13 @@ SYM_FUNC_START(vmread_error_trampoline) push %r10 push %r11 #endif -#ifdef CONFIG_X86_64 + /* Load @field and @fault to arg1 and arg2 respectively. */ - mov 3*WORD_SIZE(%rbp), %_ASM_ARG2 - mov 2*WORD_SIZE(%rbp), %_ASM_ARG1 -#else - /* Parameters are passed on the stack for 32-bit (see asmlinkage). */ - push 3*WORD_SIZE(%ebp) - push 2*WORD_SIZE(%ebp) -#endif + mov 3*WORD_SIZE(%_ASM_BP), %_ASM_ARG2 + mov 2*WORD_SIZE(%_ASM_BP), %_ASM_ARG1 call vmread_error -#ifndef CONFIG_X86_64 - add $8, %esp -#endif - /* Zero out @fault, which will be popped into the result register. */ _ASM_MOV $0, 3*WORD_SIZE(%_ASM_BP) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index c9b49a09e6b5..9dba04b6b019 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -439,7 +439,7 @@ do { \ pr_warn_ratelimited(fmt); \ } while (0) -asmlinkage void vmread_error(unsigned long field, bool fault) +void vmread_error(unsigned long field, bool fault) { if (fault) kvm_spurious_fault(); @@ -864,7 +864,7 @@ unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx) return flags; } -static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, +static __always_inline void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, unsigned long entry, unsigned long exit) { vm_entry_controls_clearbit(vmx, entry); @@ -922,7 +922,7 @@ skip_guest: vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr); } -static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx, +static __always_inline void add_atomic_switch_msr_special(struct vcpu_vmx *vmx, unsigned long entry, unsigned long exit, unsigned long guest_val_vmcs, unsigned long host_val_vmcs, u64 guest_val, u64 host_val) @@ -1652,17 +1652,25 @@ static void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu) /* * Per the SDM, MTF takes priority over debug-trap exceptions besides - * T-bit traps. As instruction emulation is completed (i.e. at the - * instruction boundary), any #DB exception pending delivery must be a - * debug-trap. Record the pending MTF state to be delivered in + * TSS T-bit traps and ICEBP (INT1). KVM doesn't emulate T-bit traps + * or ICEBP (in the emulator proper), and skipping of ICEBP after an + * intercepted #DB deliberately avoids single-step #DB and MTF updates + * as ICEBP is higher priority than both. As instruction emulation is + * completed at this point (i.e. KVM is at the instruction boundary), + * any #DB exception pending delivery must be a debug-trap of lower + * priority than MTF. Record the pending MTF state to be delivered in * vmx_check_nested_events(). */ if (nested_cpu_has_mtf(vmcs12) && (!vcpu->arch.exception.pending || - vcpu->arch.exception.nr == DB_VECTOR)) + vcpu->arch.exception.vector == DB_VECTOR) && + (!vcpu->arch.exception_vmexit.pending || + vcpu->arch.exception_vmexit.vector == DB_VECTOR)) { vmx->nested.mtf_pending = true; - else + kvm_make_request(KVM_REQ_EVENT, vcpu); + } else { vmx->nested.mtf_pending = false; + } } static int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu) @@ -1684,32 +1692,40 @@ static void vmx_clear_hlt(struct kvm_vcpu *vcpu) vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE); } -static void vmx_queue_exception(struct kvm_vcpu *vcpu) +static void vmx_inject_exception(struct kvm_vcpu *vcpu) { + struct kvm_queued_exception *ex = &vcpu->arch.exception; + u32 intr_info = ex->vector | INTR_INFO_VALID_MASK; struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned nr = vcpu->arch.exception.nr; - bool has_error_code = vcpu->arch.exception.has_error_code; - u32 error_code = vcpu->arch.exception.error_code; - u32 intr_info = nr | INTR_INFO_VALID_MASK; - kvm_deliver_exception_payload(vcpu); + kvm_deliver_exception_payload(vcpu, ex); - if (has_error_code) { - vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code); + if (ex->has_error_code) { + /* + * Despite the error code being architecturally defined as 32 + * bits, and the VMCS field being 32 bits, Intel CPUs and thus + * VMX don't actually supporting setting bits 31:16. Hardware + * will (should) never provide a bogus error code, but AMD CPUs + * do generate error codes with bits 31:16 set, and so KVM's + * ABI lets userspace shove in arbitrary 32-bit values. Drop + * the upper bits to avoid VM-Fail, losing information that + * does't really exist is preferable to killing the VM. + */ + vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, (u16)ex->error_code); intr_info |= INTR_INFO_DELIVER_CODE_MASK; } if (vmx->rmode.vm86_active) { int inc_eip = 0; - if (kvm_exception_is_soft(nr)) + if (kvm_exception_is_soft(ex->vector)) inc_eip = vcpu->arch.event_exit_inst_len; - kvm_inject_realmode_interrupt(vcpu, nr, inc_eip); + kvm_inject_realmode_interrupt(vcpu, ex->vector, inc_eip); return; } WARN_ON_ONCE(vmx->emulation_required); - if (kvm_exception_is_soft(nr)) { + if (kvm_exception_is_soft(ex->vector)) { vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, vmx->vcpu.arch.event_exit_inst_len); intr_info |= INTR_TYPE_SOFT_EXCEPTION; @@ -1930,9 +1946,8 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * sanity checking and refuse to boot. Filter all unsupported * features out. */ - if (!msr_info->host_initiated && - vmx->nested.enlightened_vmcs_enabled) - nested_evmcs_filter_control_msr(msr_info->index, + if (!msr_info->host_initiated && guest_cpuid_has_evmcs(vcpu)) + nested_evmcs_filter_control_msr(vcpu, msr_info->index, &msr_info->data); break; case MSR_IA32_RTIT_CTL: @@ -2494,6 +2509,30 @@ static bool cpu_has_sgx(void) return cpuid_eax(0) >= 0x12 && (cpuid_eax(0x12) & BIT(0)); } +/* + * Some cpus support VM_{ENTRY,EXIT}_IA32_PERF_GLOBAL_CTRL but they + * can't be used due to errata where VM Exit may incorrectly clear + * IA32_PERF_GLOBAL_CTRL[34:32]. Work around the errata by using the + * MSR load mechanism to switch IA32_PERF_GLOBAL_CTRL. + */ +static bool cpu_has_perf_global_ctrl_bug(void) +{ + if (boot_cpu_data.x86 == 0x6) { + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_NEHALEM_EP: /* AAK155 */ + case INTEL_FAM6_NEHALEM: /* AAP115 */ + case INTEL_FAM6_WESTMERE: /* AAT100 */ + case INTEL_FAM6_WESTMERE_EP: /* BC86,AAY89,BD102 */ + case INTEL_FAM6_NEHALEM_EX: /* BA97 */ + return true; + default: + break; + } + } + + return false; +} + static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, u32 msr, u32 *result) { @@ -2526,13 +2565,13 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, struct vmx_capability *vmx_cap) { u32 vmx_msr_low, vmx_msr_high; - u32 min, opt, min2, opt2; u32 _pin_based_exec_control = 0; u32 _cpu_based_exec_control = 0; u32 _cpu_based_2nd_exec_control = 0; u64 _cpu_based_3rd_exec_control = 0; u32 _vmexit_control = 0; u32 _vmentry_control = 0; + u64 misc_msr; int i; /* @@ -2552,64 +2591,17 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, }; memset(vmcs_conf, 0, sizeof(*vmcs_conf)); - min = CPU_BASED_HLT_EXITING | -#ifdef CONFIG_X86_64 - CPU_BASED_CR8_LOAD_EXITING | - CPU_BASED_CR8_STORE_EXITING | -#endif - CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_CR3_STORE_EXITING | - CPU_BASED_UNCOND_IO_EXITING | - CPU_BASED_MOV_DR_EXITING | - CPU_BASED_USE_TSC_OFFSETTING | - CPU_BASED_MWAIT_EXITING | - CPU_BASED_MONITOR_EXITING | - CPU_BASED_INVLPG_EXITING | - CPU_BASED_RDPMC_EXITING; - opt = CPU_BASED_TPR_SHADOW | - CPU_BASED_USE_MSR_BITMAPS | - CPU_BASED_ACTIVATE_SECONDARY_CONTROLS | - CPU_BASED_ACTIVATE_TERTIARY_CONTROLS; - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS, - &_cpu_based_exec_control) < 0) + if (adjust_vmx_controls(KVM_REQUIRED_VMX_CPU_BASED_VM_EXEC_CONTROL, + KVM_OPTIONAL_VMX_CPU_BASED_VM_EXEC_CONTROL, + MSR_IA32_VMX_PROCBASED_CTLS, + &_cpu_based_exec_control)) return -EIO; -#ifdef CONFIG_X86_64 - if (_cpu_based_exec_control & CPU_BASED_TPR_SHADOW) - _cpu_based_exec_control &= ~CPU_BASED_CR8_LOAD_EXITING & - ~CPU_BASED_CR8_STORE_EXITING; -#endif if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) { - min2 = 0; - opt2 = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | - SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | - SECONDARY_EXEC_WBINVD_EXITING | - SECONDARY_EXEC_ENABLE_VPID | - SECONDARY_EXEC_ENABLE_EPT | - SECONDARY_EXEC_UNRESTRICTED_GUEST | - SECONDARY_EXEC_PAUSE_LOOP_EXITING | - SECONDARY_EXEC_DESC | - SECONDARY_EXEC_ENABLE_RDTSCP | - SECONDARY_EXEC_ENABLE_INVPCID | - SECONDARY_EXEC_APIC_REGISTER_VIRT | - SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | - SECONDARY_EXEC_SHADOW_VMCS | - SECONDARY_EXEC_XSAVES | - SECONDARY_EXEC_RDSEED_EXITING | - SECONDARY_EXEC_RDRAND_EXITING | - SECONDARY_EXEC_ENABLE_PML | - SECONDARY_EXEC_TSC_SCALING | - SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | - SECONDARY_EXEC_PT_USE_GPA | - SECONDARY_EXEC_PT_CONCEAL_VMX | - SECONDARY_EXEC_ENABLE_VMFUNC | - SECONDARY_EXEC_BUS_LOCK_DETECTION | - SECONDARY_EXEC_NOTIFY_VM_EXITING; - if (cpu_has_sgx()) - opt2 |= SECONDARY_EXEC_ENCLS_EXITING; - if (adjust_vmx_controls(min2, opt2, + if (adjust_vmx_controls(KVM_REQUIRED_VMX_SECONDARY_VM_EXEC_CONTROL, + KVM_OPTIONAL_VMX_SECONDARY_VM_EXEC_CONTROL, MSR_IA32_VMX_PROCBASED_CTLS2, - &_cpu_based_2nd_exec_control) < 0) + &_cpu_based_2nd_exec_control)) return -EIO; } #ifndef CONFIG_X86_64 @@ -2627,13 +2619,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, rdmsr_safe(MSR_IA32_VMX_EPT_VPID_CAP, &vmx_cap->ept, &vmx_cap->vpid); - if (_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) { - /* CR3 accesses and invlpg don't need to cause VM Exits when EPT - enabled */ - _cpu_based_exec_control &= ~(CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_CR3_STORE_EXITING | - CPU_BASED_INVLPG_EXITING); - } else if (vmx_cap->ept) { + if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) && + vmx_cap->ept) { pr_warn_once("EPT CAP should not exist if not support " "1-setting enable EPT VM-execution control\n"); @@ -2653,32 +2640,24 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, vmx_cap->vpid = 0; } - if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_TERTIARY_CONTROLS) { - u64 opt3 = TERTIARY_EXEC_IPI_VIRT; + if (!cpu_has_sgx()) + _cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_ENCLS_EXITING; - _cpu_based_3rd_exec_control = adjust_vmx_controls64(opt3, + if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_TERTIARY_CONTROLS) + _cpu_based_3rd_exec_control = + adjust_vmx_controls64(KVM_OPTIONAL_VMX_TERTIARY_VM_EXEC_CONTROL, MSR_IA32_VMX_PROCBASED_CTLS3); - } - min = VM_EXIT_SAVE_DEBUG_CONTROLS | VM_EXIT_ACK_INTR_ON_EXIT; -#ifdef CONFIG_X86_64 - min |= VM_EXIT_HOST_ADDR_SPACE_SIZE; -#endif - opt = VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | - VM_EXIT_LOAD_IA32_PAT | - VM_EXIT_LOAD_IA32_EFER | - VM_EXIT_CLEAR_BNDCFGS | - VM_EXIT_PT_CONCEAL_PIP | - VM_EXIT_CLEAR_IA32_RTIT_CTL; - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS, - &_vmexit_control) < 0) + if (adjust_vmx_controls(KVM_REQUIRED_VMX_VM_EXIT_CONTROLS, + KVM_OPTIONAL_VMX_VM_EXIT_CONTROLS, + MSR_IA32_VMX_EXIT_CTLS, + &_vmexit_control)) return -EIO; - min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING; - opt = PIN_BASED_VIRTUAL_NMIS | PIN_BASED_POSTED_INTR | - PIN_BASED_VMX_PREEMPTION_TIMER; - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PINBASED_CTLS, - &_pin_based_exec_control) < 0) + if (adjust_vmx_controls(KVM_REQUIRED_VMX_PIN_BASED_VM_EXEC_CONTROL, + KVM_OPTIONAL_VMX_PIN_BASED_VM_EXEC_CONTROL, + MSR_IA32_VMX_PINBASED_CTLS, + &_pin_based_exec_control)) return -EIO; if (cpu_has_broken_vmx_preemption_timer()) @@ -2687,15 +2666,10 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY)) _pin_based_exec_control &= ~PIN_BASED_POSTED_INTR; - min = VM_ENTRY_LOAD_DEBUG_CONTROLS; - opt = VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | - VM_ENTRY_LOAD_IA32_PAT | - VM_ENTRY_LOAD_IA32_EFER | - VM_ENTRY_LOAD_BNDCFGS | - VM_ENTRY_PT_CONCEAL_PIP | - VM_ENTRY_LOAD_IA32_RTIT_CTL; - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_ENTRY_CTLS, - &_vmentry_control) < 0) + if (adjust_vmx_controls(KVM_REQUIRED_VMX_VM_ENTRY_CONTROLS, + KVM_OPTIONAL_VMX_VM_ENTRY_CONTROLS, + MSR_IA32_VMX_ENTRY_CTLS, + &_vmentry_control)) return -EIO; for (i = 0; i < ARRAY_SIZE(vmcs_entry_exit_pairs); i++) { @@ -2715,30 +2689,6 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, _vmexit_control &= ~x_ctrl; } - /* - * Some cpus support VM_{ENTRY,EXIT}_IA32_PERF_GLOBAL_CTRL but they - * can't be used due to an errata where VM Exit may incorrectly clear - * IA32_PERF_GLOBAL_CTRL[34:32]. Workaround the errata by using the - * MSR load mechanism to switch IA32_PERF_GLOBAL_CTRL. - */ - if (boot_cpu_data.x86 == 0x6) { - switch (boot_cpu_data.x86_model) { - case 26: /* AAK155 */ - case 30: /* AAP115 */ - case 37: /* AAT100 */ - case 44: /* BC86,AAY89,BD102 */ - case 46: /* BA97 */ - _vmentry_control &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; - _vmexit_control &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; - pr_warn_once("kvm: VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL " - "does not work properly. Using workaround\n"); - break; - default: - break; - } - } - - rdmsr(MSR_IA32_VMX_BASIC, vmx_msr_low, vmx_msr_high); /* IA-32 SDM Vol 3B: VMCS size is never greater than 4kB. */ @@ -2755,6 +2705,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, if (((vmx_msr_high >> 18) & 15) != 6) return -EIO; + rdmsrl(MSR_IA32_VMX_MISC, misc_msr); + vmcs_conf->size = vmx_msr_high & 0x1fff; vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff; @@ -2766,11 +2718,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, vmcs_conf->cpu_based_3rd_exec_ctrl = _cpu_based_3rd_exec_control; vmcs_conf->vmexit_ctrl = _vmexit_control; vmcs_conf->vmentry_ctrl = _vmentry_control; - -#if IS_ENABLED(CONFIG_HYPERV) - if (enlightened_vmcs) - evmcs_sanitize_exec_ctrls(vmcs_conf); -#endif + vmcs_conf->misc = misc_msr; return 0; } @@ -3037,10 +2985,15 @@ int vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) return 0; vcpu->arch.efer = efer; +#ifdef CONFIG_X86_64 if (efer & EFER_LMA) vm_entry_controls_setbit(vmx, VM_ENTRY_IA32E_MODE); else vm_entry_controls_clearbit(vmx, VM_ENTRY_IA32E_MODE); +#else + if (KVM_BUG_ON(efer & EFER_LMA, vcpu->kvm)) + return 1; +#endif vmx_setup_uret_msrs(vmx); return 0; @@ -4327,18 +4280,37 @@ static u32 vmx_vmentry_ctrl(void) if (vmx_pt_mode_is_system()) vmentry_ctrl &= ~(VM_ENTRY_PT_CONCEAL_PIP | VM_ENTRY_LOAD_IA32_RTIT_CTL); - /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ - return vmentry_ctrl & - ~(VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | VM_ENTRY_LOAD_IA32_EFER); + /* + * IA32e mode, and loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically. + */ + vmentry_ctrl &= ~(VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | + VM_ENTRY_LOAD_IA32_EFER | + VM_ENTRY_IA32E_MODE); + + if (cpu_has_perf_global_ctrl_bug()) + vmentry_ctrl &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + + return vmentry_ctrl; } static u32 vmx_vmexit_ctrl(void) { u32 vmexit_ctrl = vmcs_config.vmexit_ctrl; + /* + * Not used by KVM and never set in vmcs01 or vmcs02, but emulated for + * nested virtualization and thus allowed to be set in vmcs12. + */ + vmexit_ctrl &= ~(VM_EXIT_SAVE_IA32_PAT | VM_EXIT_SAVE_IA32_EFER | + VM_EXIT_SAVE_VMX_PREEMPTION_TIMER); + if (vmx_pt_mode_is_system()) vmexit_ctrl &= ~(VM_EXIT_PT_CONCEAL_PIP | VM_EXIT_CLEAR_IA32_RTIT_CTL); + + if (cpu_has_perf_global_ctrl_bug()) + vmexit_ctrl &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; + /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ return vmexit_ctrl & ~(VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | VM_EXIT_LOAD_IA32_EFER); @@ -4376,20 +4348,38 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx) { u32 exec_control = vmcs_config.cpu_based_exec_ctrl; + /* + * Not used by KVM, but fully supported for nesting, i.e. are allowed in + * vmcs12 and propagated to vmcs02 when set in vmcs12. + */ + exec_control &= ~(CPU_BASED_RDTSC_EXITING | + CPU_BASED_USE_IO_BITMAPS | + CPU_BASED_MONITOR_TRAP_FLAG | + CPU_BASED_PAUSE_EXITING); + + /* INTR_WINDOW_EXITING and NMI_WINDOW_EXITING are toggled dynamically */ + exec_control &= ~(CPU_BASED_INTR_WINDOW_EXITING | + CPU_BASED_NMI_WINDOW_EXITING); + if (vmx->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT) exec_control &= ~CPU_BASED_MOV_DR_EXITING; - if (!cpu_need_tpr_shadow(&vmx->vcpu)) { + if (!cpu_need_tpr_shadow(&vmx->vcpu)) exec_control &= ~CPU_BASED_TPR_SHADOW; + #ifdef CONFIG_X86_64 + if (exec_control & CPU_BASED_TPR_SHADOW) + exec_control &= ~(CPU_BASED_CR8_LOAD_EXITING | + CPU_BASED_CR8_STORE_EXITING); + else exec_control |= CPU_BASED_CR8_STORE_EXITING | CPU_BASED_CR8_LOAD_EXITING; #endif - } - if (!enable_ept) - exec_control |= CPU_BASED_CR3_STORE_EXITING | - CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_INVLPG_EXITING; + /* No need to intercept CR3 access or INVPLG when using EPT. */ + if (enable_ept) + exec_control &= ~(CPU_BASED_CR3_LOAD_EXITING | + CPU_BASED_CR3_STORE_EXITING | + CPU_BASED_INVLPG_EXITING); if (kvm_mwait_in_guest(vmx->vcpu.kvm)) exec_control &= ~(CPU_BASED_MWAIT_EXITING | CPU_BASED_MONITOR_EXITING); @@ -5155,8 +5145,10 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) * instruction. ICEBP generates a trap-like #DB, but * despite its interception control being tied to #DB, * is an instruction intercept, i.e. the VM-Exit occurs - * on the ICEBP itself. Note, skipping ICEBP also - * clears STI and MOVSS blocking. + * on the ICEBP itself. Use the inner "skip" helper to + * avoid single-step #DB and MTF updates, as ICEBP is + * higher priority. Note, skipping ICEBP still clears + * STI and MOVSS blocking. * * For all other #DBs, set vmcs.PENDING_DBG_EXCEPTIONS.BS * if single-step is enabled in RFLAGS and STI or MOVSS @@ -5638,7 +5630,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); - trace_kvm_page_fault(gpa, exit_qualification); + trace_kvm_page_fault(vcpu, gpa, exit_qualification); /* Is it a read fault? */ error_code = (exit_qualification & EPT_VIOLATION_ACC_READ) @@ -5710,7 +5702,7 @@ static bool vmx_emulation_required_with_pending_exception(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); return vmx->emulation_required && !vmx->rmode.vm86_active && - (vcpu->arch.exception.pending || vcpu->arch.exception.injected); + (kvm_is_exception_pending(vcpu) || vcpu->arch.exception.injected); } static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) @@ -7430,7 +7422,7 @@ static int __init vmx_check_processor_compat(void) if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) return -EIO; if (nested) - nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept); + nested_vmx_setup_ctls_msrs(&vmcs_conf, vmx_cap.ept); if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) { printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n", smp_processor_id()); @@ -8070,7 +8062,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .patch_hypercall = vmx_patch_hypercall, .inject_irq = vmx_inject_irq, .inject_nmi = vmx_inject_nmi, - .queue_exception = vmx_queue_exception, + .inject_exception = vmx_inject_exception, .cancel_injection = vmx_cancel_injection, .interrupt_allowed = vmx_interrupt_allowed, .nmi_allowed = vmx_nmi_allowed, @@ -8227,6 +8219,10 @@ static __init int hardware_setup(void) if (setup_vmcs_config(&vmcs_config, &vmx_capability) < 0) return -EIO; + if (cpu_has_perf_global_ctrl_bug()) + pr_warn_once("kvm: VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL " + "does not work properly. Using workaround\n"); + if (boot_cpu_has(X86_FEATURE_NX)) kvm_enable_efer_bits(EFER_NX); @@ -8341,11 +8337,9 @@ static __init int hardware_setup(void) if (enable_preemption_timer) { u64 use_timer_freq = 5000ULL * 1000 * 1000; - u64 vmx_msr; - rdmsrl(MSR_IA32_VMX_MISC, vmx_msr); cpu_preemption_timer_multi = - vmx_msr & VMX_MISC_PREEMPTION_TIMER_RATE_MASK; + vmcs_config.misc & VMX_MISC_PREEMPTION_TIMER_RATE_MASK; if (tsc_khz) use_timer_freq = (u64)tsc_khz * 1000; @@ -8381,8 +8375,7 @@ static __init int hardware_setup(void) setup_default_sgx_lepubkeyhash(); if (nested) { - nested_vmx_setup_ctls_msrs(&vmcs_config.nested, - vmx_capability.ept); + nested_vmx_setup_ctls_msrs(&vmcs_config, vmx_capability.ept); r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers); if (r) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 24d58c2ffaa3..a3da84f4ea45 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -477,29 +477,145 @@ static inline u8 vmx_get_rvi(void) return vmcs_read16(GUEST_INTR_STATUS) & 0xff; } -#define BUILD_CONTROLS_SHADOW(lname, uname, bits) \ -static inline void lname##_controls_set(struct vcpu_vmx *vmx, u##bits val) \ -{ \ - if (vmx->loaded_vmcs->controls_shadow.lname != val) { \ - vmcs_write##bits(uname, val); \ - vmx->loaded_vmcs->controls_shadow.lname = val; \ - } \ -} \ -static inline u##bits __##lname##_controls_get(struct loaded_vmcs *vmcs) \ -{ \ - return vmcs->controls_shadow.lname; \ -} \ -static inline u##bits lname##_controls_get(struct vcpu_vmx *vmx) \ -{ \ - return __##lname##_controls_get(vmx->loaded_vmcs); \ -} \ -static inline void lname##_controls_setbit(struct vcpu_vmx *vmx, u##bits val) \ -{ \ - lname##_controls_set(vmx, lname##_controls_get(vmx) | val); \ -} \ -static inline void lname##_controls_clearbit(struct vcpu_vmx *vmx, u##bits val) \ -{ \ - lname##_controls_set(vmx, lname##_controls_get(vmx) & ~val); \ +#define __KVM_REQUIRED_VMX_VM_ENTRY_CONTROLS \ + (VM_ENTRY_LOAD_DEBUG_CONTROLS) +#ifdef CONFIG_X86_64 + #define KVM_REQUIRED_VMX_VM_ENTRY_CONTROLS \ + (__KVM_REQUIRED_VMX_VM_ENTRY_CONTROLS | \ + VM_ENTRY_IA32E_MODE) +#else + #define KVM_REQUIRED_VMX_VM_ENTRY_CONTROLS \ + __KVM_REQUIRED_VMX_VM_ENTRY_CONTROLS +#endif +#define KVM_OPTIONAL_VMX_VM_ENTRY_CONTROLS \ + (VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_ENTRY_LOAD_IA32_PAT | \ + VM_ENTRY_LOAD_IA32_EFER | \ + VM_ENTRY_LOAD_BNDCFGS | \ + VM_ENTRY_PT_CONCEAL_PIP | \ + VM_ENTRY_LOAD_IA32_RTIT_CTL) + +#define __KVM_REQUIRED_VMX_VM_EXIT_CONTROLS \ + (VM_EXIT_SAVE_DEBUG_CONTROLS | \ + VM_EXIT_ACK_INTR_ON_EXIT) +#ifdef CONFIG_X86_64 + #define KVM_REQUIRED_VMX_VM_EXIT_CONTROLS \ + (__KVM_REQUIRED_VMX_VM_EXIT_CONTROLS | \ + VM_EXIT_HOST_ADDR_SPACE_SIZE) +#else + #define KVM_REQUIRED_VMX_VM_EXIT_CONTROLS \ + __KVM_REQUIRED_VMX_VM_EXIT_CONTROLS +#endif +#define KVM_OPTIONAL_VMX_VM_EXIT_CONTROLS \ + (VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_EXIT_SAVE_IA32_PAT | \ + VM_EXIT_LOAD_IA32_PAT | \ + VM_EXIT_SAVE_IA32_EFER | \ + VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | \ + VM_EXIT_LOAD_IA32_EFER | \ + VM_EXIT_CLEAR_BNDCFGS | \ + VM_EXIT_PT_CONCEAL_PIP | \ + VM_EXIT_CLEAR_IA32_RTIT_CTL) + +#define KVM_REQUIRED_VMX_PIN_BASED_VM_EXEC_CONTROL \ + (PIN_BASED_EXT_INTR_MASK | \ + PIN_BASED_NMI_EXITING) +#define KVM_OPTIONAL_VMX_PIN_BASED_VM_EXEC_CONTROL \ + (PIN_BASED_VIRTUAL_NMIS | \ + PIN_BASED_POSTED_INTR | \ + PIN_BASED_VMX_PREEMPTION_TIMER) + +#define __KVM_REQUIRED_VMX_CPU_BASED_VM_EXEC_CONTROL \ + (CPU_BASED_HLT_EXITING | \ + CPU_BASED_CR3_LOAD_EXITING | \ + CPU_BASED_CR3_STORE_EXITING | \ + CPU_BASED_UNCOND_IO_EXITING | \ + CPU_BASED_MOV_DR_EXITING | \ + CPU_BASED_USE_TSC_OFFSETTING | \ + CPU_BASED_MWAIT_EXITING | \ + CPU_BASED_MONITOR_EXITING | \ + CPU_BASED_INVLPG_EXITING | \ + CPU_BASED_RDPMC_EXITING | \ + CPU_BASED_INTR_WINDOW_EXITING) + +#ifdef CONFIG_X86_64 + #define KVM_REQUIRED_VMX_CPU_BASED_VM_EXEC_CONTROL \ + (__KVM_REQUIRED_VMX_CPU_BASED_VM_EXEC_CONTROL | \ + CPU_BASED_CR8_LOAD_EXITING | \ + CPU_BASED_CR8_STORE_EXITING) +#else + #define KVM_REQUIRED_VMX_CPU_BASED_VM_EXEC_CONTROL \ + __KVM_REQUIRED_VMX_CPU_BASED_VM_EXEC_CONTROL +#endif + +#define KVM_OPTIONAL_VMX_CPU_BASED_VM_EXEC_CONTROL \ + (CPU_BASED_RDTSC_EXITING | \ + CPU_BASED_TPR_SHADOW | \ + CPU_BASED_USE_IO_BITMAPS | \ + CPU_BASED_MONITOR_TRAP_FLAG | \ + CPU_BASED_USE_MSR_BITMAPS | \ + CPU_BASED_NMI_WINDOW_EXITING | \ + CPU_BASED_PAUSE_EXITING | \ + CPU_BASED_ACTIVATE_SECONDARY_CONTROLS | \ + CPU_BASED_ACTIVATE_TERTIARY_CONTROLS) + +#define KVM_REQUIRED_VMX_SECONDARY_VM_EXEC_CONTROL 0 +#define KVM_OPTIONAL_VMX_SECONDARY_VM_EXEC_CONTROL \ + (SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | \ + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | \ + SECONDARY_EXEC_WBINVD_EXITING | \ + SECONDARY_EXEC_ENABLE_VPID | \ + SECONDARY_EXEC_ENABLE_EPT | \ + SECONDARY_EXEC_UNRESTRICTED_GUEST | \ + SECONDARY_EXEC_PAUSE_LOOP_EXITING | \ + SECONDARY_EXEC_DESC | \ + SECONDARY_EXEC_ENABLE_RDTSCP | \ + SECONDARY_EXEC_ENABLE_INVPCID | \ + SECONDARY_EXEC_APIC_REGISTER_VIRT | \ + SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | \ + SECONDARY_EXEC_SHADOW_VMCS | \ + SECONDARY_EXEC_XSAVES | \ + SECONDARY_EXEC_RDSEED_EXITING | \ + SECONDARY_EXEC_RDRAND_EXITING | \ + SECONDARY_EXEC_ENABLE_PML | \ + SECONDARY_EXEC_TSC_SCALING | \ + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | \ + SECONDARY_EXEC_PT_USE_GPA | \ + SECONDARY_EXEC_PT_CONCEAL_VMX | \ + SECONDARY_EXEC_ENABLE_VMFUNC | \ + SECONDARY_EXEC_BUS_LOCK_DETECTION | \ + SECONDARY_EXEC_NOTIFY_VM_EXITING | \ + SECONDARY_EXEC_ENCLS_EXITING) + +#define KVM_REQUIRED_VMX_TERTIARY_VM_EXEC_CONTROL 0 +#define KVM_OPTIONAL_VMX_TERTIARY_VM_EXEC_CONTROL \ + (TERTIARY_EXEC_IPI_VIRT) + +#define BUILD_CONTROLS_SHADOW(lname, uname, bits) \ +static inline void lname##_controls_set(struct vcpu_vmx *vmx, u##bits val) \ +{ \ + if (vmx->loaded_vmcs->controls_shadow.lname != val) { \ + vmcs_write##bits(uname, val); \ + vmx->loaded_vmcs->controls_shadow.lname = val; \ + } \ +} \ +static inline u##bits __##lname##_controls_get(struct loaded_vmcs *vmcs) \ +{ \ + return vmcs->controls_shadow.lname; \ +} \ +static inline u##bits lname##_controls_get(struct vcpu_vmx *vmx) \ +{ \ + return __##lname##_controls_get(vmx->loaded_vmcs); \ +} \ +static __always_inline void lname##_controls_setbit(struct vcpu_vmx *vmx, u##bits val) \ +{ \ + BUILD_BUG_ON(!(val & (KVM_REQUIRED_VMX_##uname | KVM_OPTIONAL_VMX_##uname))); \ + lname##_controls_set(vmx, lname##_controls_get(vmx) | val); \ +} \ +static __always_inline void lname##_controls_clearbit(struct vcpu_vmx *vmx, u##bits val) \ +{ \ + BUILD_BUG_ON(!(val & (KVM_REQUIRED_VMX_##uname | KVM_OPTIONAL_VMX_##uname))); \ + lname##_controls_set(vmx, lname##_controls_get(vmx) & ~val); \ } BUILD_CONTROLS_SHADOW(vm_entry, VM_ENTRY_CONTROLS, 32) BUILD_CONTROLS_SHADOW(vm_exit, VM_EXIT_CONTROLS, 32) @@ -626,4 +742,14 @@ static inline bool vmx_can_use_ipiv(struct kvm_vcpu *vcpu) return lapic_in_kernel(vcpu) && enable_ipiv; } +static inline bool guest_cpuid_has_evmcs(struct kvm_vcpu *vcpu) +{ + /* + * eVMCS is exposed to the guest if Hyper-V is enabled in CPUID and + * eVMCS has been explicitly enabled by userspace. + */ + return vcpu->arch.hyperv_enabled && + to_vmx(vcpu)->nested.enlightened_vmcs_enabled; +} + #endif /* __KVM_X86_VMX_H */ diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index 5cfc49ddb1b4..ec268df83ed6 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -10,7 +10,7 @@ #include "vmcs.h" #include "../x86.h" -asmlinkage void vmread_error(unsigned long field, bool fault); +void vmread_error(unsigned long field, bool fault); __attribute__((regparm(0))) void vmread_error_trampoline(unsigned long field, bool fault); void vmwrite_error(unsigned long field, unsigned long value); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index b0c47b41c264..4bd5f8a751de 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -173,8 +173,13 @@ bool __read_mostly enable_vmware_backdoor = false; module_param(enable_vmware_backdoor, bool, S_IRUGO); EXPORT_SYMBOL_GPL(enable_vmware_backdoor); -static bool __read_mostly force_emulation_prefix = false; -module_param(force_emulation_prefix, bool, S_IRUGO); +/* + * Flags to manipulate forced emulation behavior (any non-zero value will + * enable forced emulation). + */ +#define KVM_FEP_CLEAR_RFLAGS_RF BIT(1) +static int __read_mostly force_emulation_prefix; +module_param(force_emulation_prefix, int, 0644); int __read_mostly pi_inject_timer = -1; module_param(pi_inject_timer, bint, S_IRUGO | S_IWUSR); @@ -528,6 +533,7 @@ static int exception_class(int vector) #define EXCPT_TRAP 1 #define EXCPT_ABORT 2 #define EXCPT_INTERRUPT 3 +#define EXCPT_DB 4 static int exception_type(int vector) { @@ -538,8 +544,14 @@ static int exception_type(int vector) mask = 1 << vector; - /* #DB is trap, as instruction watchpoints are handled elsewhere */ - if (mask & ((1 << DB_VECTOR) | (1 << BP_VECTOR) | (1 << OF_VECTOR))) + /* + * #DBs can be trap-like or fault-like, the caller must check other CPU + * state, e.g. DR6, to determine whether a #DB is a trap or fault. + */ + if (mask & (1 << DB_VECTOR)) + return EXCPT_DB; + + if (mask & ((1 << BP_VECTOR) | (1 << OF_VECTOR))) return EXCPT_TRAP; if (mask & ((1 << DF_VECTOR) | (1 << MC_VECTOR))) @@ -549,16 +561,13 @@ static int exception_type(int vector) return EXCPT_FAULT; } -void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu) +void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu, + struct kvm_queued_exception *ex) { - unsigned nr = vcpu->arch.exception.nr; - bool has_payload = vcpu->arch.exception.has_payload; - unsigned long payload = vcpu->arch.exception.payload; - - if (!has_payload) + if (!ex->has_payload) return; - switch (nr) { + switch (ex->vector) { case DB_VECTOR: /* * "Certain debug exceptions may clear bit 0-3. The @@ -583,8 +592,8 @@ void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu) * So they need to be flipped for DR6. */ vcpu->arch.dr6 |= DR6_ACTIVE_LOW; - vcpu->arch.dr6 |= payload; - vcpu->arch.dr6 ^= payload & DR6_ACTIVE_LOW; + vcpu->arch.dr6 |= ex->payload; + vcpu->arch.dr6 ^= ex->payload & DR6_ACTIVE_LOW; /* * The #DB payload is defined as compatible with the 'pending @@ -595,15 +604,30 @@ void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu) vcpu->arch.dr6 &= ~BIT(12); break; case PF_VECTOR: - vcpu->arch.cr2 = payload; + vcpu->arch.cr2 = ex->payload; break; } - vcpu->arch.exception.has_payload = false; - vcpu->arch.exception.payload = 0; + ex->has_payload = false; + ex->payload = 0; } EXPORT_SYMBOL_GPL(kvm_deliver_exception_payload); +static void kvm_queue_exception_vmexit(struct kvm_vcpu *vcpu, unsigned int vector, + bool has_error_code, u32 error_code, + bool has_payload, unsigned long payload) +{ + struct kvm_queued_exception *ex = &vcpu->arch.exception_vmexit; + + ex->vector = vector; + ex->injected = false; + ex->pending = true; + ex->has_error_code = has_error_code; + ex->error_code = error_code; + ex->has_payload = has_payload; + ex->payload = payload; +} + static void kvm_multiple_exception(struct kvm_vcpu *vcpu, unsigned nr, bool has_error, u32 error_code, bool has_payload, unsigned long payload, bool reinject) @@ -613,18 +637,31 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu, kvm_make_request(KVM_REQ_EVENT, vcpu); + /* + * If the exception is destined for L2 and isn't being reinjected, + * morph it to a VM-Exit if L1 wants to intercept the exception. A + * previously injected exception is not checked because it was checked + * when it was original queued, and re-checking is incorrect if _L1_ + * injected the exception, in which case it's exempt from interception. + */ + if (!reinject && is_guest_mode(vcpu) && + kvm_x86_ops.nested_ops->is_exception_vmexit(vcpu, nr, error_code)) { + kvm_queue_exception_vmexit(vcpu, nr, has_error, error_code, + has_payload, payload); + return; + } + if (!vcpu->arch.exception.pending && !vcpu->arch.exception.injected) { queue: if (reinject) { /* - * On vmentry, vcpu->arch.exception.pending is only - * true if an event injection was blocked by - * nested_run_pending. In that case, however, - * vcpu_enter_guest requests an immediate exit, - * and the guest shouldn't proceed far enough to - * need reinjection. + * On VM-Entry, an exception can be pending if and only + * if event injection was blocked by nested_run_pending. + * In that case, however, vcpu_enter_guest() requests an + * immediate exit, and the guest shouldn't proceed far + * enough to need reinjection. */ - WARN_ON_ONCE(vcpu->arch.exception.pending); + WARN_ON_ONCE(kvm_is_exception_pending(vcpu)); vcpu->arch.exception.injected = true; if (WARN_ON_ONCE(has_payload)) { /* @@ -639,17 +676,18 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu, vcpu->arch.exception.injected = false; } vcpu->arch.exception.has_error_code = has_error; - vcpu->arch.exception.nr = nr; + vcpu->arch.exception.vector = nr; vcpu->arch.exception.error_code = error_code; vcpu->arch.exception.has_payload = has_payload; vcpu->arch.exception.payload = payload; if (!is_guest_mode(vcpu)) - kvm_deliver_exception_payload(vcpu); + kvm_deliver_exception_payload(vcpu, + &vcpu->arch.exception); return; } /* to check exception */ - prev_nr = vcpu->arch.exception.nr; + prev_nr = vcpu->arch.exception.vector; if (prev_nr == DF_VECTOR) { /* triple fault -> shutdown */ kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); @@ -657,25 +695,22 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu, } class1 = exception_class(prev_nr); class2 = exception_class(nr); - if ((class1 == EXCPT_CONTRIBUTORY && class2 == EXCPT_CONTRIBUTORY) - || (class1 == EXCPT_PF && class2 != EXCPT_BENIGN)) { + if ((class1 == EXCPT_CONTRIBUTORY && class2 == EXCPT_CONTRIBUTORY) || + (class1 == EXCPT_PF && class2 != EXCPT_BENIGN)) { /* - * Generate double fault per SDM Table 5-5. Set - * exception.pending = true so that the double fault - * can trigger a nested vmexit. + * Synthesize #DF. Clear the previously injected or pending + * exception so as not to incorrectly trigger shutdown. */ - vcpu->arch.exception.pending = true; vcpu->arch.exception.injected = false; - vcpu->arch.exception.has_error_code = true; - vcpu->arch.exception.nr = DF_VECTOR; - vcpu->arch.exception.error_code = 0; - vcpu->arch.exception.has_payload = false; - vcpu->arch.exception.payload = 0; - } else + vcpu->arch.exception.pending = false; + + kvm_queue_exception_e(vcpu, DF_VECTOR, 0); + } else { /* replace previous exception with a new one in a hope that instruction re-execution will regenerate lost exception */ goto queue; + } } void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr) @@ -729,20 +764,22 @@ static int complete_emulated_insn_gp(struct kvm_vcpu *vcpu, int err) void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) { ++vcpu->stat.pf_guest; - vcpu->arch.exception.nested_apf = - is_guest_mode(vcpu) && fault->async_page_fault; - if (vcpu->arch.exception.nested_apf) { - vcpu->arch.apf.nested_apf_token = fault->address; - kvm_queue_exception_e(vcpu, PF_VECTOR, fault->error_code); - } else { + + /* + * Async #PF in L2 is always forwarded to L1 as a VM-Exit regardless of + * whether or not L1 wants to intercept "regular" #PF. + */ + if (is_guest_mode(vcpu) && fault->async_page_fault) + kvm_queue_exception_vmexit(vcpu, PF_VECTOR, + true, fault->error_code, + true, fault->address); + else kvm_queue_exception_e_p(vcpu, PF_VECTOR, fault->error_code, fault->address); - } } EXPORT_SYMBOL_GPL(kvm_inject_page_fault); -/* Returns true if the page fault was immediately morphed into a VM-Exit. */ -bool kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, +void kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) { struct kvm_mmu *fault_mmu; @@ -760,26 +797,7 @@ bool kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, kvm_mmu_invalidate_gva(vcpu, fault_mmu, fault->address, fault_mmu->root.hpa); - /* - * A workaround for KVM's bad exception handling. If KVM injected an - * exception into L2, and L2 encountered a #PF while vectoring the - * injected exception, manually check to see if L1 wants to intercept - * #PF, otherwise queuing the #PF will lead to #DF or a lost exception. - * In all other cases, defer the check to nested_ops->check_events(), - * which will correctly handle priority (this does not). Note, other - * exceptions, e.g. #GP, are theoretically affected, #PF is simply the - * most problematic, e.g. when L0 and L1 are both intercepting #PF for - * shadow paging. - * - * TODO: Rewrite exception handling to track injected and pending - * (VM-Exit) exceptions separately. - */ - if (unlikely(vcpu->arch.exception.injected && is_guest_mode(vcpu)) && - kvm_x86_ops.nested_ops->handle_page_fault_workaround(vcpu, fault)) - return true; - fault_mmu->inject_page_fault(vcpu, fault); - return false; } EXPORT_SYMBOL_GPL(kvm_inject_emulated_page_fault); @@ -4841,7 +4859,7 @@ static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu) return (kvm_arch_interrupt_allowed(vcpu) && kvm_cpu_accept_dm_intr(vcpu) && !kvm_event_needs_reinjection(vcpu) && - !vcpu->arch.exception.pending); + !kvm_is_exception_pending(vcpu)); } static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, @@ -5016,25 +5034,38 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { + struct kvm_queued_exception *ex; + process_nmi(vcpu); if (kvm_check_request(KVM_REQ_SMI, vcpu)) process_smi(vcpu); /* - * In guest mode, payload delivery should be deferred, - * so that the L1 hypervisor can intercept #PF before - * CR2 is modified (or intercept #DB before DR6 is - * modified under nVMX). Unless the per-VM capability, - * KVM_CAP_EXCEPTION_PAYLOAD, is set, we may not defer the delivery of - * an exception payload and handle after a KVM_GET_VCPU_EVENTS. Since we - * opportunistically defer the exception payload, deliver it if the - * capability hasn't been requested before processing a - * KVM_GET_VCPU_EVENTS. + * KVM's ABI only allows for one exception to be migrated. Luckily, + * the only time there can be two queued exceptions is if there's a + * non-exiting _injected_ exception, and a pending exiting exception. + * In that case, ignore the VM-Exiting exception as it's an extension + * of the injected exception. + */ + if (vcpu->arch.exception_vmexit.pending && + !vcpu->arch.exception.pending && + !vcpu->arch.exception.injected) + ex = &vcpu->arch.exception_vmexit; + else + ex = &vcpu->arch.exception; + + /* + * In guest mode, payload delivery should be deferred if the exception + * will be intercepted by L1, e.g. KVM should not modifying CR2 if L1 + * intercepts #PF, ditto for DR6 and #DBs. If the per-VM capability, + * KVM_CAP_EXCEPTION_PAYLOAD, is not set, userspace may or may not + * propagate the payload and so it cannot be safely deferred. Deliver + * the payload if the capability hasn't been requested. */ if (!vcpu->kvm->arch.exception_payload_enabled && - vcpu->arch.exception.pending && vcpu->arch.exception.has_payload) - kvm_deliver_exception_payload(vcpu); + ex->pending && ex->has_payload) + kvm_deliver_exception_payload(vcpu, ex); /* * The API doesn't provide the instruction length for software @@ -5042,26 +5073,25 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, * isn't advanced, we should expect to encounter the exception * again. */ - if (kvm_exception_is_soft(vcpu->arch.exception.nr)) { + if (kvm_exception_is_soft(ex->vector)) { events->exception.injected = 0; events->exception.pending = 0; } else { - events->exception.injected = vcpu->arch.exception.injected; - events->exception.pending = vcpu->arch.exception.pending; + events->exception.injected = ex->injected; + events->exception.pending = ex->pending; /* * For ABI compatibility, deliberately conflate * pending and injected exceptions when * KVM_CAP_EXCEPTION_PAYLOAD isn't enabled. */ if (!vcpu->kvm->arch.exception_payload_enabled) - events->exception.injected |= - vcpu->arch.exception.pending; + events->exception.injected |= ex->pending; } - events->exception.nr = vcpu->arch.exception.nr; - events->exception.has_error_code = vcpu->arch.exception.has_error_code; - events->exception.error_code = vcpu->arch.exception.error_code; - events->exception_has_payload = vcpu->arch.exception.has_payload; - events->exception_payload = vcpu->arch.exception.payload; + events->exception.nr = ex->vector; + events->exception.has_error_code = ex->has_error_code; + events->exception.error_code = ex->error_code; + events->exception_has_payload = ex->has_payload; + events->exception_payload = ex->payload; events->interrupt.injected = vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft; @@ -5131,9 +5161,22 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, return -EINVAL; process_nmi(vcpu); + + /* + * Flag that userspace is stuffing an exception, the next KVM_RUN will + * morph the exception to a VM-Exit if appropriate. Do this only for + * pending exceptions, already-injected exceptions are not subject to + * intercpetion. Note, userspace that conflates pending and injected + * is hosed, and will incorrectly convert an injected exception into a + * pending exception, which in turn may cause a spurious VM-Exit. + */ + vcpu->arch.exception_from_userspace = events->exception.pending; + + vcpu->arch.exception_vmexit.pending = false; + vcpu->arch.exception.injected = events->exception.injected; vcpu->arch.exception.pending = events->exception.pending; - vcpu->arch.exception.nr = events->exception.nr; + vcpu->arch.exception.vector = events->exception.nr; vcpu->arch.exception.has_error_code = events->exception.has_error_code; vcpu->arch.exception.error_code = events->exception.error_code; vcpu->arch.exception.has_payload = events->exception_has_payload; @@ -7257,6 +7300,7 @@ static int kvm_can_emulate_insn(struct kvm_vcpu *vcpu, int emul_type, int handle_ud(struct kvm_vcpu *vcpu) { static const char kvm_emulate_prefix[] = { __KVM_EMULATE_PREFIX }; + int fep_flags = READ_ONCE(force_emulation_prefix); int emul_type = EMULTYPE_TRAP_UD; char sig[5]; /* ud2; .ascii "kvm" */ struct x86_exception e; @@ -7264,10 +7308,12 @@ int handle_ud(struct kvm_vcpu *vcpu) if (unlikely(!kvm_can_emulate_insn(vcpu, emul_type, NULL, 0))) return 1; - if (force_emulation_prefix && + if (fep_flags && kvm_read_guest_virt(vcpu, kvm_get_linear_rip(vcpu), sig, sizeof(sig), &e) == 0 && memcmp(sig, kvm_emulate_prefix, sizeof(sig)) == 0) { + if (fep_flags & KVM_FEP_CLEAR_RFLAGS_RF) + kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) & ~X86_EFLAGS_RF); kvm_rip_write(vcpu, kvm_rip_read(vcpu) + sizeof(sig)); emul_type = EMULTYPE_TRAP_UD_FORCED; } @@ -7933,14 +7979,20 @@ static int emulator_get_msr_with_filter(struct x86_emulate_ctxt *ctxt, int r; r = kvm_get_msr_with_filter(vcpu, msr_index, pdata); + if (r < 0) + return X86EMUL_UNHANDLEABLE; - if (r && kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_RDMSR, 0, - complete_emulated_rdmsr, r)) { - /* Bounce to user space */ - return X86EMUL_IO_NEEDED; + if (r) { + if (kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_RDMSR, 0, + complete_emulated_rdmsr, r)) + return X86EMUL_IO_NEEDED; + + trace_kvm_msr_read_ex(msr_index); + return X86EMUL_PROPAGATE_FAULT; } - return r; + trace_kvm_msr_read(msr_index, *pdata); + return X86EMUL_CONTINUE; } static int emulator_set_msr_with_filter(struct x86_emulate_ctxt *ctxt, @@ -7950,14 +8002,20 @@ static int emulator_set_msr_with_filter(struct x86_emulate_ctxt *ctxt, int r; r = kvm_set_msr_with_filter(vcpu, msr_index, data); + if (r < 0) + return X86EMUL_UNHANDLEABLE; - if (r && kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_WRMSR, data, - complete_emulated_msr_access, r)) { - /* Bounce to user space */ - return X86EMUL_IO_NEEDED; + if (r) { + if (kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_WRMSR, data, + complete_emulated_msr_access, r)) + return X86EMUL_IO_NEEDED; + + trace_kvm_msr_write_ex(msr_index, data); + return X86EMUL_PROPAGATE_FAULT; } - return r; + trace_kvm_msr_write(msr_index, data); + return X86EMUL_CONTINUE; } static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, @@ -8161,18 +8219,17 @@ static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) } } -static bool inject_emulated_exception(struct kvm_vcpu *vcpu) +static void inject_emulated_exception(struct kvm_vcpu *vcpu) { struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; - if (ctxt->exception.vector == PF_VECTOR) - return kvm_inject_emulated_page_fault(vcpu, &ctxt->exception); - if (ctxt->exception.error_code_valid) + if (ctxt->exception.vector == PF_VECTOR) + kvm_inject_emulated_page_fault(vcpu, &ctxt->exception); + else if (ctxt->exception.error_code_valid) kvm_queue_exception_e(vcpu, ctxt->exception.vector, ctxt->exception.error_code); else kvm_queue_exception(vcpu, ctxt->exception.vector); - return false; } static struct x86_emulate_ctxt *alloc_emulate_ctxt(struct kvm_vcpu *vcpu) @@ -8548,8 +8605,46 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_skip_emulated_instruction); -static bool kvm_vcpu_check_code_breakpoint(struct kvm_vcpu *vcpu, int *r) +static bool kvm_is_code_breakpoint_inhibited(struct kvm_vcpu *vcpu) { + u32 shadow; + + if (kvm_get_rflags(vcpu) & X86_EFLAGS_RF) + return true; + + /* + * Intel CPUs inhibit code #DBs when MOV/POP SS blocking is active, + * but AMD CPUs do not. MOV/POP SS blocking is rare, check that first + * to avoid the relatively expensive CPUID lookup. + */ + shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu); + return (shadow & KVM_X86_SHADOW_INT_MOV_SS) && + guest_cpuid_is_intel(vcpu); +} + +static bool kvm_vcpu_check_code_breakpoint(struct kvm_vcpu *vcpu, + int emulation_type, int *r) +{ + WARN_ON_ONCE(emulation_type & EMULTYPE_NO_DECODE); + + /* + * Do not check for code breakpoints if hardware has already done the + * checks, as inferred from the emulation type. On NO_DECODE and SKIP, + * the instruction has passed all exception checks, and all intercepted + * exceptions that trigger emulation have lower priority than code + * breakpoints, i.e. the fact that the intercepted exception occurred + * means any code breakpoints have already been serviced. + * + * Note, KVM needs to check for code #DBs on EMULTYPE_TRAP_UD_FORCED as + * hardware has checked the RIP of the magic prefix, but not the RIP of + * the instruction being emulated. The intent of forced emulation is + * to behave as if KVM intercepted the instruction without an exception + * and without a prefix. + */ + if (emulation_type & (EMULTYPE_NO_DECODE | EMULTYPE_SKIP | + EMULTYPE_TRAP_UD | EMULTYPE_VMWARE_GP | EMULTYPE_PF)) + return false; + if (unlikely(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) && (vcpu->arch.guest_debug_dr7 & DR7_BP_EN_MASK)) { struct kvm_run *kvm_run = vcpu->run; @@ -8569,7 +8664,7 @@ static bool kvm_vcpu_check_code_breakpoint(struct kvm_vcpu *vcpu, int *r) } if (unlikely(vcpu->arch.dr7 & DR7_BP_EN_MASK) && - !(kvm_get_rflags(vcpu) & X86_EFLAGS_RF)) { + !kvm_is_code_breakpoint_inhibited(vcpu)) { unsigned long eip = kvm_get_linear_rip(vcpu); u32 dr6 = kvm_vcpu_check_hw_bp(eip, 0, vcpu->arch.dr7, @@ -8671,8 +8766,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, * are fault-like and are higher priority than any faults on * the code fetch itself. */ - if (!(emulation_type & EMULTYPE_SKIP) && - kvm_vcpu_check_code_breakpoint(vcpu, &r)) + if (kvm_vcpu_check_code_breakpoint(vcpu, emulation_type, &r)) return r; r = x86_decode_emulated_instruction(vcpu, emulation_type, @@ -8770,8 +8864,7 @@ restart: if (ctxt->have_exception) { r = 1; - if (inject_emulated_exception(vcpu)) - return r; + inject_emulated_exception(vcpu); } else if (vcpu->arch.pio.count) { if (!vcpu->arch.pio.in) { /* FIXME: return into emulator if single-stepping. */ @@ -8801,6 +8894,12 @@ writeback: unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu); toggle_interruptibility(vcpu, ctxt->interruptibility); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; + + /* + * Note, EXCPT_DB is assumed to be fault-like as the emulator + * only supports code breakpoints and general detect #DB, both + * of which are fault-like. + */ if (!ctxt->have_exception || exception_type(ctxt->exception.vector) == EXCPT_TRAP) { kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_INSTRUCTIONS); @@ -9662,74 +9761,155 @@ int kvm_check_nested_events(struct kvm_vcpu *vcpu) static void kvm_inject_exception(struct kvm_vcpu *vcpu) { - trace_kvm_inj_exception(vcpu->arch.exception.nr, + trace_kvm_inj_exception(vcpu->arch.exception.vector, vcpu->arch.exception.has_error_code, vcpu->arch.exception.error_code, vcpu->arch.exception.injected); if (vcpu->arch.exception.error_code && !is_protmode(vcpu)) vcpu->arch.exception.error_code = false; - static_call(kvm_x86_queue_exception)(vcpu); + static_call(kvm_x86_inject_exception)(vcpu); } -static int inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit) +/* + * Check for any event (interrupt or exception) that is ready to be injected, + * and if there is at least one event, inject the event with the highest + * priority. This handles both "pending" events, i.e. events that have never + * been injected into the guest, and "injected" events, i.e. events that were + * injected as part of a previous VM-Enter, but weren't successfully delivered + * and need to be re-injected. + * + * Note, this is not guaranteed to be invoked on a guest instruction boundary, + * i.e. doesn't guarantee that there's an event window in the guest. KVM must + * be able to inject exceptions in the "middle" of an instruction, and so must + * also be able to re-inject NMIs and IRQs in the middle of an instruction. + * I.e. for exceptions and re-injected events, NOT invoking this on instruction + * boundaries is necessary and correct. + * + * For simplicity, KVM uses a single path to inject all events (except events + * that are injected directly from L1 to L2) and doesn't explicitly track + * instruction boundaries for asynchronous events. However, because VM-Exits + * that can occur during instruction execution typically result in KVM skipping + * the instruction or injecting an exception, e.g. instruction and exception + * intercepts, and because pending exceptions have higher priority than pending + * interrupts, KVM still honors instruction boundaries in most scenarios. + * + * But, if a VM-Exit occurs during instruction execution, and KVM does NOT skip + * the instruction or inject an exception, then KVM can incorrecty inject a new + * asynchrounous event if the event became pending after the CPU fetched the + * instruction (in the guest). E.g. if a page fault (#PF, #NPF, EPT violation) + * occurs and is resolved by KVM, a coincident NMI, SMI, IRQ, etc... can be + * injected on the restarted instruction instead of being deferred until the + * instruction completes. + * + * In practice, this virtualization hole is unlikely to be observed by the + * guest, and even less likely to cause functional problems. To detect the + * hole, the guest would have to trigger an event on a side effect of an early + * phase of instruction execution, e.g. on the instruction fetch from memory. + * And for it to be a functional problem, the guest would need to depend on the + * ordering between that side effect, the instruction completing, _and_ the + * delivery of the asynchronous event. + */ +static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu, + bool *req_immediate_exit) { + bool can_inject; int r; - bool can_inject = true; - /* try to reinject previous events if any */ - - if (vcpu->arch.exception.injected) { - kvm_inject_exception(vcpu); - can_inject = false; - } /* - * Do not inject an NMI or interrupt if there is a pending - * exception. Exceptions and interrupts are recognized at - * instruction boundaries, i.e. the start of an instruction. - * Trap-like exceptions, e.g. #DB, have higher priority than - * NMIs and interrupts, i.e. traps are recognized before an - * NMI/interrupt that's pending on the same instruction. - * Fault-like exceptions, e.g. #GP and #PF, are the lowest - * priority, but are only generated (pended) during instruction - * execution, i.e. a pending fault-like exception means the - * fault occurred on the *previous* instruction and must be - * serviced prior to recognizing any new events in order to - * fully complete the previous instruction. + * Process nested events first, as nested VM-Exit supercedes event + * re-injection. If there's an event queued for re-injection, it will + * be saved into the appropriate vmc{b,s}12 fields on nested VM-Exit. */ - else if (!vcpu->arch.exception.pending) { - if (vcpu->arch.nmi_injected) { - static_call(kvm_x86_inject_nmi)(vcpu); - can_inject = false; - } else if (vcpu->arch.interrupt.injected) { - static_call(kvm_x86_inject_irq)(vcpu, true); - can_inject = false; - } - } + if (is_guest_mode(vcpu)) + r = kvm_check_nested_events(vcpu); + else + r = 0; + /* + * Re-inject exceptions and events *especially* if immediate entry+exit + * to/from L2 is needed, as any event that has already been injected + * into L2 needs to complete its lifecycle before injecting a new event. + * + * Don't re-inject an NMI or interrupt if there is a pending exception. + * This collision arises if an exception occurred while vectoring the + * injected event, KVM intercepted said exception, and KVM ultimately + * determined the fault belongs to the guest and queues the exception + * for injection back into the guest. + * + * "Injected" interrupts can also collide with pending exceptions if + * userspace ignores the "ready for injection" flag and blindly queues + * an interrupt. In that case, prioritizing the exception is correct, + * as the exception "occurred" before the exit to userspace. Trap-like + * exceptions, e.g. most #DBs, have higher priority than interrupts. + * And while fault-like exceptions, e.g. #GP and #PF, are the lowest + * priority, they're only generated (pended) during instruction + * execution, and interrupts are recognized at instruction boundaries. + * Thus a pending fault-like exception means the fault occurred on the + * *previous* instruction and must be serviced prior to recognizing any + * new events in order to fully complete the previous instruction. + */ + if (vcpu->arch.exception.injected) + kvm_inject_exception(vcpu); + else if (kvm_is_exception_pending(vcpu)) + ; /* see above */ + else if (vcpu->arch.nmi_injected) + static_call(kvm_x86_inject_nmi)(vcpu); + else if (vcpu->arch.interrupt.injected) + static_call(kvm_x86_inject_irq)(vcpu, true); + + /* + * Exceptions that morph to VM-Exits are handled above, and pending + * exceptions on top of injected exceptions that do not VM-Exit should + * either morph to #DF or, sadly, override the injected exception. + */ WARN_ON_ONCE(vcpu->arch.exception.injected && vcpu->arch.exception.pending); /* - * Call check_nested_events() even if we reinjected a previous event - * in order for caller to determine if it should require immediate-exit - * from L2 to L1 due to pending L1 events which require exit - * from L2 to L1. + * Bail if immediate entry+exit to/from the guest is needed to complete + * nested VM-Enter or event re-injection so that a different pending + * event can be serviced (or if KVM needs to exit to userspace). + * + * Otherwise, continue processing events even if VM-Exit occurred. The + * VM-Exit will have cleared exceptions that were meant for L2, but + * there may now be events that can be injected into L1. */ - if (is_guest_mode(vcpu)) { - r = kvm_check_nested_events(vcpu); - if (r < 0) - goto out; - } + if (r < 0) + goto out; + + /* + * A pending exception VM-Exit should either result in nested VM-Exit + * or force an immediate re-entry and exit to/from L2, and exception + * VM-Exits cannot be injected (flag should _never_ be set). + */ + WARN_ON_ONCE(vcpu->arch.exception_vmexit.injected || + vcpu->arch.exception_vmexit.pending); + + /* + * New events, other than exceptions, cannot be injected if KVM needs + * to re-inject a previous event. See above comments on re-injecting + * for why pending exceptions get priority. + */ + can_inject = !kvm_event_needs_reinjection(vcpu); - /* try to inject new event if pending */ if (vcpu->arch.exception.pending) { - if (exception_type(vcpu->arch.exception.nr) == EXCPT_FAULT) + /* + * Fault-class exceptions, except #DBs, set RF=1 in the RFLAGS + * value pushed on the stack. Trap-like exception and all #DBs + * leave RF as-is (KVM follows Intel's behavior in this regard; + * AMD states that code breakpoint #DBs excplitly clear RF=0). + * + * Note, most versions of Intel's SDM and AMD's APM incorrectly + * describe the behavior of General Detect #DBs, which are + * fault-like. They do _not_ set RF, a la code breakpoints. + */ + if (exception_type(vcpu->arch.exception.vector) == EXCPT_FAULT) __kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) | X86_EFLAGS_RF); - if (vcpu->arch.exception.nr == DB_VECTOR) { - kvm_deliver_exception_payload(vcpu); + if (vcpu->arch.exception.vector == DB_VECTOR) { + kvm_deliver_exception_payload(vcpu, &vcpu->arch.exception); if (vcpu->arch.dr7 & DR7_GD) { vcpu->arch.dr7 &= ~DR7_GD; kvm_update_dr7(vcpu); @@ -9801,11 +9981,11 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit) } if (is_guest_mode(vcpu) && - kvm_x86_ops.nested_ops->hv_timer_pending && - kvm_x86_ops.nested_ops->hv_timer_pending(vcpu)) + kvm_x86_ops.nested_ops->has_events && + kvm_x86_ops.nested_ops->has_events(vcpu)) *req_immediate_exit = true; - WARN_ON(vcpu->arch.exception.pending); + WARN_ON(kvm_is_exception_pending(vcpu)); return 0; out: @@ -10110,7 +10290,7 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) * When APICv gets disabled, we may still have injected interrupts * pending. At the same time, KVM_REQ_EVENT may not be set as APICv was * still active when the interrupt got accepted. Make sure - * inject_pending_event() is called to check for that. + * kvm_check_and_inject_events() is called to check for that. */ if (!apic->apicv_active) kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -10407,7 +10587,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto out; } - r = inject_pending_event(vcpu, &req_immediate_exit); + r = kvm_check_and_inject_events(vcpu, &req_immediate_exit); if (r < 0) { r = 0; goto out; @@ -10646,10 +10826,26 @@ static inline int vcpu_block(struct kvm_vcpu *vcpu) if (hv_timer) kvm_lapic_switch_to_hv_timer(vcpu); - if (!kvm_check_request(KVM_REQ_UNHALT, vcpu)) + /* + * If the vCPU is not runnable, a signal or another host event + * of some kind is pending; service it without changing the + * vCPU's activity state. + */ + if (!kvm_arch_vcpu_runnable(vcpu)) return 1; } + /* + * Evaluate nested events before exiting the halted state. This allows + * the halt state to be recorded properly in the VMCS12's activity + * state field (AMD does not have a similar field and a VM-Exit always + * causes a spurious wakeup from HLT). + */ + if (is_guest_mode(vcpu)) { + if (kvm_check_nested_events(vcpu) < 0) + return 0; + } + if (kvm_apic_accept_events(vcpu) < 0) return 0; switch(vcpu->arch.mp_state) { @@ -10673,9 +10869,6 @@ static inline int vcpu_block(struct kvm_vcpu *vcpu) static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) { - if (is_guest_mode(vcpu)) - kvm_check_nested_events(vcpu); - return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && !vcpu->arch.apf.halted); } @@ -10824,6 +11017,7 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { + struct kvm_queued_exception *ex = &vcpu->arch.exception; struct kvm_run *kvm_run = vcpu->run; int r; @@ -10852,7 +11046,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) r = 0; goto out; } - kvm_clear_request(KVM_REQ_UNHALT, vcpu); r = -EAGAIN; if (signal_pending(current)) { r = -EINTR; @@ -10882,6 +11075,21 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) } } + /* + * If userspace set a pending exception and L2 is active, convert it to + * a pending VM-Exit if L1 wants to intercept the exception. + */ + if (vcpu->arch.exception_from_userspace && is_guest_mode(vcpu) && + kvm_x86_ops.nested_ops->is_exception_vmexit(vcpu, ex->vector, + ex->error_code)) { + kvm_queue_exception_vmexit(vcpu, ex->vector, + ex->has_error_code, ex->error_code, + ex->has_payload, ex->payload); + ex->injected = false; + ex->pending = false; + } + vcpu->arch.exception_from_userspace = false; + if (unlikely(vcpu->arch.complete_userspace_io)) { int (*cui)(struct kvm_vcpu *) = vcpu->arch.complete_userspace_io; vcpu->arch.complete_userspace_io = NULL; @@ -10988,6 +11196,7 @@ static void __set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) kvm_set_rflags(vcpu, regs->rflags | X86_EFLAGS_FIXED); vcpu->arch.exception.pending = false; + vcpu->arch.exception_vmexit.pending = false; kvm_make_request(KVM_REQ_EVENT, vcpu); } @@ -11125,11 +11334,12 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, } /* - * KVM_MP_STATE_INIT_RECEIVED means the processor is in - * INIT state; latched init should be reported using - * KVM_SET_VCPU_EVENTS, so reject it here. + * Pending INITs are reported using KVM_SET_VCPU_EVENTS, disallow + * forcing the guest into INIT/SIPI if those events are supposed to be + * blocked. KVM prioritizes SMI over INIT, so reject INIT/SIPI state + * if an SMI is pending as well. */ - if ((kvm_vcpu_latch_init(vcpu) || vcpu->arch.smi_pending) && + if ((!kvm_apic_init_sipi_allowed(vcpu) || vcpu->arch.smi_pending) && (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED || mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED)) goto out; @@ -11368,7 +11578,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, if (dbg->control & (KVM_GUESTDBG_INJECT_DB | KVM_GUESTDBG_INJECT_BP)) { r = -EBUSY; - if (vcpu->arch.exception.pending) + if (kvm_is_exception_pending(vcpu)) goto out; if (dbg->control & KVM_GUESTDBG_INJECT_DB) kvm_queue_exception(vcpu, DB_VECTOR); @@ -11750,8 +11960,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) struct fpstate *fpstate = vcpu->arch.guest_fpu.fpstate; /* - * To avoid have the INIT path from kvm_apic_has_events() that be - * called with loaded FPU and does not let userspace fix the state. + * All paths that lead to INIT are required to load the guest's + * FPU state (because most paths are buried in KVM_RUN). */ if (init_event) kvm_put_guest_fpu(vcpu); @@ -12080,6 +12290,10 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) if (ret) goto out_page_track; + ret = static_call(kvm_x86_vm_init)(kvm); + if (ret) + goto out_uninit_mmu; + INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list); INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); atomic_set(&kvm->arch.noncoherent_dma_count, 0); @@ -12115,8 +12329,10 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_hv_init_vm(kvm); kvm_xen_init_vm(kvm); - return static_call(kvm_x86_vm_init)(kvm); + return 0; +out_uninit_mmu: + kvm_mmu_uninit_vm(kvm); out_page_track: kvm_page_track_cleanup(kvm); out: @@ -12589,13 +12805,14 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) if (!list_empty_careful(&vcpu->async_pf.done)) return true; - if (kvm_apic_has_events(vcpu)) + if (kvm_apic_has_pending_init_or_sipi(vcpu) && + kvm_apic_init_sipi_allowed(vcpu)) return true; if (vcpu->arch.pv.pv_unhalted) return true; - if (vcpu->arch.exception.pending) + if (kvm_is_exception_pending(vcpu)) return true; if (kvm_test_request(KVM_REQ_NMI, vcpu) || @@ -12617,16 +12834,13 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) return true; if (is_guest_mode(vcpu) && - kvm_x86_ops.nested_ops->hv_timer_pending && - kvm_x86_ops.nested_ops->hv_timer_pending(vcpu)) + kvm_x86_ops.nested_ops->has_events && + kvm_x86_ops.nested_ops->has_events(vcpu)) return true; if (kvm_xen_has_pending_events(vcpu)) return true; - if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) - return true; - return false; } @@ -12850,7 +13064,7 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu) { if (unlikely(!lapic_in_kernel(vcpu) || kvm_event_needs_reinjection(vcpu) || - vcpu->arch.exception.pending)) + kvm_is_exception_pending(vcpu))) return false; if (kvm_hlt_in_guest(vcpu->kvm) && !kvm_can_deliver_async_pf(vcpu)) @@ -13401,7 +13615,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_msr); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_cr); -EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmrun); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmenter); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 1926d2cb8e79..829d3134c1eb 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -82,10 +82,18 @@ static inline unsigned int __shrink_ple_window(unsigned int val, void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu); int kvm_check_nested_events(struct kvm_vcpu *vcpu); +static inline bool kvm_is_exception_pending(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.exception.pending || + vcpu->arch.exception_vmexit.pending || + kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu); +} + static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu) { vcpu->arch.exception.pending = false; vcpu->arch.exception.injected = false; + vcpu->arch.exception_vmexit.pending = false; } static inline void kvm_queue_interrupt(struct kvm_vcpu *vcpu, u8 vector, @@ -267,11 +275,6 @@ static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk) return !(kvm->arch.disabled_quirks & quirk); } -static inline bool kvm_vcpu_latch_init(struct kvm_vcpu *vcpu) -{ - return is_smm(vcpu) || static_call(kvm_x86_apic_init_signal_blocked)(vcpu); -} - void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip); u64 get_kvmclock_ns(struct kvm *kvm); @@ -286,7 +289,8 @@ int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, int handle_ud(struct kvm_vcpu *vcpu); -void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu); +void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu, + struct kvm_queued_exception *ex); void kvm_vcpu_mtrr_init(struct kvm_vcpu *vcpu); u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn); diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 280cb5dc7341..93c628d3e3a9 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -1065,7 +1065,6 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode, del_timer(&vcpu->arch.xen.poll_timer); vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; - kvm_clear_request(KVM_REQ_UNHALT, vcpu); } vcpu->arch.xen.poll_evtchn = 0; diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 133105574181..5071a45a600a 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -849,4 +849,23 @@ void __init init_cpu_topology(void) return; } } + +void store_cpu_topology(unsigned int cpuid) +{ + struct cpu_topology *cpuid_topo = &cpu_topology[cpuid]; + + if (cpuid_topo->package_id != -1) + goto topology_populated; + + cpuid_topo->thread_id = -1; + cpuid_topo->core_id = cpuid; + cpuid_topo->package_id = cpu_to_node(cpuid); + + pr_debug("CPU%u: package %d core %d thread %d\n", + cpuid, cpuid_topo->package_id, cpuid_topo->core_id, + cpuid_topo->thread_id); + +topology_populated: + update_siblings_masks(cpuid); +} #endif diff --git a/drivers/base/node.c b/drivers/base/node.c index eb0f43784c2b..432d40a5f910 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -433,6 +433,7 @@ static ssize_t node_read_meminfo(struct device *dev, "Node %d ShadowCallStack:%8lu kB\n" #endif "Node %d PageTables: %8lu kB\n" + "Node %d SecPageTables: %8lu kB\n" "Node %d NFS_Unstable: %8lu kB\n" "Node %d Bounce: %8lu kB\n" "Node %d WritebackTmp: %8lu kB\n" @@ -459,6 +460,7 @@ static ssize_t node_read_meminfo(struct device *dev, nid, node_page_state(pgdat, NR_KERNEL_SCS_KB), #endif nid, K(node_page_state(pgdat, NR_PAGETABLE)), + nid, K(node_page_state(pgdat, NR_SECONDARY_PAGETABLE)), nid, 0UL, nid, K(sum_zone_node_page_state(nid, NR_BOUNCE)), nid, K(node_page_state(pgdat, NR_WRITEBACK_TEMP)), diff --git a/drivers/cpuidle/cpuidle-riscv-sbi.c b/drivers/cpuidle/cpuidle-riscv-sbi.c index 862a2876f1c9..05fe2902df9a 100644 --- a/drivers/cpuidle/cpuidle-riscv-sbi.c +++ b/drivers/cpuidle/cpuidle-riscv-sbi.c @@ -97,8 +97,13 @@ static int sbi_cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, int idx) { u32 *states = __this_cpu_read(sbi_cpuidle_data.states); + u32 state = states[idx]; - return CPU_PM_CPU_IDLE_ENTER_PARAM(sbi_suspend, idx, states[idx]); + if (state & SBI_HSM_SUSP_NON_RET_BIT) + return CPU_PM_CPU_IDLE_ENTER_PARAM(sbi_suspend, idx, state); + else + return CPU_PM_CPU_IDLE_ENTER_RETENTION_PARAM(sbi_suspend, + idx, state); } static int __sbi_enter_domain_idle_state(struct cpuidle_device *dev, diff --git a/drivers/macintosh/therm_windtunnel.c b/drivers/macintosh/therm_windtunnel.c index 61fe2ab910b8..b8228ca40454 100644 --- a/drivers/macintosh/therm_windtunnel.c +++ b/drivers/macintosh/therm_windtunnel.c @@ -317,19 +317,21 @@ static void do_attach(struct i2c_adapter *adapter) if (x.running || strncmp(adapter->name, "uni-n", 5)) return; + of_node_get(adapter->dev.of_node); np = of_find_compatible_node(adapter->dev.of_node, NULL, "MAC,ds1775"); if (np) { of_node_put(np); } else { - strlcpy(info.type, "MAC,ds1775", I2C_NAME_SIZE); + strscpy(info.type, "MAC,ds1775", I2C_NAME_SIZE); i2c_new_scanned_device(adapter, &info, scan_ds1775, NULL); } + of_node_get(adapter->dev.of_node); np = of_find_compatible_node(adapter->dev.of_node, NULL, "MAC,adm1030"); if (np) { of_node_put(np); } else { - strlcpy(info.type, "MAC,adm1030", I2C_NAME_SIZE); + strscpy(info.type, "MAC,adm1030", I2C_NAME_SIZE); i2c_new_scanned_device(adapter, &info, scan_adm1030, NULL); } } diff --git a/drivers/perf/riscv_pmu_legacy.c b/drivers/perf/riscv_pmu_legacy.c index 2c20b0de8cb0..ca9e20bfc7ac 100644 --- a/drivers/perf/riscv_pmu_legacy.c +++ b/drivers/perf/riscv_pmu_legacy.c @@ -14,7 +14,6 @@ #define RISCV_PMU_LEGACY_CYCLE 0 #define RISCV_PMU_LEGACY_INSTRET 1 -#define RISCV_PMU_LEGACY_NUM_CTR 2 static bool pmu_init_done; @@ -83,7 +82,8 @@ static void pmu_legacy_init(struct riscv_pmu *pmu) { pr_info("Legacy PMU implementation is available\n"); - pmu->num_counters = RISCV_PMU_LEGACY_NUM_CTR; + pmu->cmask = BIT(RISCV_PMU_LEGACY_CYCLE) | + BIT(RISCV_PMU_LEGACY_INSTRET); pmu->ctr_start = pmu_legacy_ctr_start; pmu->ctr_stop = NULL; pmu->event_map = pmu_legacy_event_map; diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 8de4ca2fef21..15e5a47be7d5 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -271,7 +272,6 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event) struct sbiret ret; int idx; uint64_t cbase = 0; - uint64_t cmask = GENMASK_ULL(rvpmu->num_counters - 1, 0); unsigned long cflags = 0; if (event->attr.exclude_kernel) @@ -281,11 +281,12 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event) /* retrieve the available counter index */ #if defined(CONFIG_32BIT) - ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, cmask, - cflags, hwc->event_base, hwc->config, hwc->config >> 32); + ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, + rvpmu->cmask, cflags, hwc->event_base, hwc->config, + hwc->config >> 32); #else - ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, cmask, - cflags, hwc->event_base, hwc->config, 0); + ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, + rvpmu->cmask, cflags, hwc->event_base, hwc->config, 0); #endif if (ret.error) { pr_debug("Not able to find a counter for event %lx config %llx\n", @@ -294,7 +295,7 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event) } idx = ret.value; - if (idx >= rvpmu->num_counters || !pmu_ctr_list[idx].value) + if (!test_bit(idx, &rvpmu->cmask) || !pmu_ctr_list[idx].value) return -ENOENT; /* Additional sanity check for the counter id */ @@ -463,7 +464,7 @@ static int pmu_sbi_find_num_ctrs(void) return sbi_err_map_linux_errno(ret.error); } -static int pmu_sbi_get_ctrinfo(int nctr) +static int pmu_sbi_get_ctrinfo(int nctr, unsigned long *mask) { struct sbiret ret; int i, num_hw_ctr = 0, num_fw_ctr = 0; @@ -478,6 +479,9 @@ static int pmu_sbi_get_ctrinfo(int nctr) if (ret.error) /* The logical counter ids are not expected to be contiguous */ continue; + + *mask |= BIT(i); + cinfo.value = ret.value; if (cinfo.type == SBI_PMU_CTR_TYPE_FW) num_fw_ctr++; @@ -498,7 +502,7 @@ static inline void pmu_sbi_stop_all(struct riscv_pmu *pmu) * which may include counters that are not enabled yet. */ sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, - 0, GENMASK_ULL(pmu->num_counters - 1, 0), 0, 0, 0, 0); + 0, pmu->cmask, 0, 0, 0, 0); } static inline void pmu_sbi_stop_hw_ctrs(struct riscv_pmu *pmu) @@ -567,6 +571,7 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev) unsigned long overflow; unsigned long overflowed_ctrs = 0; struct cpu_hw_events *cpu_hw_evt = dev; + u64 start_clock = sched_clock(); if (WARN_ON_ONCE(!cpu_hw_evt)) return IRQ_NONE; @@ -635,7 +640,9 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev) perf_event_overflow(event, &data, regs); } } + pmu_sbi_start_overflow_mask(pmu, overflowed_ctrs); + perf_sample_event_took(sched_clock() - start_clock); return IRQ_HANDLED; } @@ -788,8 +795,9 @@ static void riscv_pmu_destroy(struct riscv_pmu *pmu) static int pmu_sbi_device_probe(struct platform_device *pdev) { struct riscv_pmu *pmu = NULL; - int num_counters; + unsigned long cmask = 0; int ret = -ENODEV; + int num_counters; pr_info("SBI PMU extension is available\n"); pmu = riscv_pmu_alloc(); @@ -803,7 +811,7 @@ static int pmu_sbi_device_probe(struct platform_device *pdev) } /* cache all the information about counters now */ - if (pmu_sbi_get_ctrinfo(num_counters)) + if (pmu_sbi_get_ctrinfo(num_counters, &cmask)) goto out_free; ret = pmu_sbi_setup_irqs(pmu, pdev); @@ -812,8 +820,9 @@ static int pmu_sbi_device_probe(struct platform_device *pdev) pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; pmu->pmu.capabilities |= PERF_PMU_CAP_NO_EXCLUDE; } + pmu->pmu.attr_groups = riscv_pmu_attr_groups; - pmu->num_counters = num_counters; + pmu->cmask = cmask; pmu->ctr_start = pmu_sbi_ctr_start; pmu->ctr_stop = pmu_sbi_ctr_stop; pmu->event_map = pmu_sbi_event_map; diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c index 1beb596d1434..cb83f81da416 100644 --- a/drivers/s390/block/dasd_devmap.c +++ b/drivers/s390/block/dasd_devmap.c @@ -426,7 +426,7 @@ dasd_add_busid(const char *bus_id, int features) if (!devmap) { /* This bus_id is new. */ new->devindex = dasd_max_devindex++; - strlcpy(new->bus_id, bus_id, DASD_BUS_ID_SIZE); + strscpy(new->bus_id, bus_id, DASD_BUS_ID_SIZE); new->features = features; new->device = NULL; list_add(&new->list, &dasd_hashlists[hash]); diff --git a/drivers/s390/block/dasd_eer.c b/drivers/s390/block/dasd_eer.c index 5ae64af9ccea..d4d31cd11d26 100644 --- a/drivers/s390/block/dasd_eer.c +++ b/drivers/s390/block/dasd_eer.c @@ -313,7 +313,7 @@ static void dasd_eer_write_standard_trigger(struct dasd_device *device, ktime_get_real_ts64(&ts); header.tv_sec = ts.tv_sec; header.tv_usec = ts.tv_nsec / NSEC_PER_USEC; - strlcpy(header.busid, dev_name(&device->cdev->dev), + strscpy(header.busid, dev_name(&device->cdev->dev), DASD_EER_BUSID_SIZE); spin_lock_irqsave(&bufferlock, flags); @@ -356,7 +356,7 @@ static void dasd_eer_write_snss_trigger(struct dasd_device *device, ktime_get_real_ts64(&ts); header.tv_sec = ts.tv_sec; header.tv_usec = ts.tv_nsec / NSEC_PER_USEC; - strlcpy(header.busid, dev_name(&device->cdev->dev), + strscpy(header.busid, dev_name(&device->cdev->dev), DASD_EER_BUSID_SIZE); spin_lock_irqsave(&bufferlock, flags); diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index 5187705bd0f3..93b80da60277 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -614,7 +614,7 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char rc = -ENAMETOOLONG; goto seg_list_del; } - strlcpy(local_buf, buf, i + 1); + strscpy(local_buf, buf, i + 1); dev_info->num_of_segments = num_of_segments; rc = dcssblk_is_continuous(dev_info); if (rc < 0) diff --git a/drivers/s390/char/hmcdrv_cache.c b/drivers/s390/char/hmcdrv_cache.c index 1f5bdb237862..43df27ceec11 100644 --- a/drivers/s390/char/hmcdrv_cache.c +++ b/drivers/s390/char/hmcdrv_cache.c @@ -154,7 +154,7 @@ static ssize_t hmcdrv_cache_do(const struct hmcdrv_ftp_cmdspec *ftp, /* cache some file info (FTP command, file name and file * size) unconditionally */ - strlcpy(hmcdrv_cache_file.fname, ftp->fname, + strscpy(hmcdrv_cache_file.fname, ftp->fname, HMCDRV_FTP_FIDENT_MAX); hmcdrv_cache_file.id = ftp->id; pr_debug("caching cmd %d, file size %zu for '%s'\n", diff --git a/drivers/s390/char/tape_class.c b/drivers/s390/char/tape_class.c index b58df0dd0039..c21dc68e05a0 100644 --- a/drivers/s390/char/tape_class.c +++ b/drivers/s390/char/tape_class.c @@ -54,10 +54,10 @@ struct tape_class_device *register_tape_dev( if (!tcd) return ERR_PTR(-ENOMEM); - strlcpy(tcd->device_name, device_name, TAPECLASS_NAME_LEN); + strscpy(tcd->device_name, device_name, TAPECLASS_NAME_LEN); for (s = strchr(tcd->device_name, '/'); s; s = strchr(s, '/')) *s = '!'; - strlcpy(tcd->mode_name, mode_name, TAPECLASS_NAME_LEN); + strscpy(tcd->mode_name, mode_name, TAPECLASS_NAME_LEN); for (s = strchr(tcd->mode_name, '/'); s; s = strchr(s, '/')) *s = '!'; diff --git a/drivers/s390/char/zcore.c b/drivers/s390/char/zcore.c index f6da215ccf9f..6165e6aae762 100644 --- a/drivers/s390/char/zcore.c +++ b/drivers/s390/char/zcore.c @@ -30,6 +30,7 @@ #include #include #include +#include #include "sclp.h" #define TRACE(x...) debug_sprintf_event(zcore_dbf, 1, x) diff --git a/drivers/s390/cio/qdio_debug.c b/drivers/s390/cio/qdio_debug.c index 4bb7965daa0f..1a9714af51e4 100644 --- a/drivers/s390/cio/qdio_debug.c +++ b/drivers/s390/cio/qdio_debug.c @@ -87,7 +87,7 @@ int qdio_allocate_dbf(struct qdio_irq *irq_ptr) debug_unregister(irq_ptr->debug_area); return -ENOMEM; } - strlcpy(new_entry->dbf_name, text, QDIO_DBF_NAME_LEN); + strscpy(new_entry->dbf_name, text, QDIO_DBF_NAME_LEN); new_entry->dbf_info = irq_ptr->debug_area; mutex_lock(&qdio_dbf_list_mutex); list_add(&new_entry->dbf_list, &qdio_dbf_list); diff --git a/drivers/s390/net/ctcm_main.c b/drivers/s390/net/ctcm_main.c index e0fdd54bfeb7..37b551bd43bf 100644 --- a/drivers/s390/net/ctcm_main.c +++ b/drivers/s390/net/ctcm_main.c @@ -1566,7 +1566,7 @@ static int ctcm_new_device(struct ccwgroup_device *cgdev) goto out_dev; } - strlcpy(priv->fsm->name, dev->name, sizeof(priv->fsm->name)); + strscpy(priv->fsm->name, dev->name, sizeof(priv->fsm->name)); dev_info(&dev->dev, "setup OK : r/w = %s/%s, protocol : %d\n", diff --git a/drivers/s390/net/fsm.c b/drivers/s390/net/fsm.c index 98c4864932d2..0ff61d00feb1 100644 --- a/drivers/s390/net/fsm.c +++ b/drivers/s390/net/fsm.c @@ -28,7 +28,7 @@ init_fsm(char *name, const char **state_names, const char **event_names, int nr_ "fsm(%s): init_fsm: Couldn't alloc instance\n", name); return NULL; } - strlcpy(this->name, name, sizeof(this->name)); + strscpy(this->name, name, sizeof(this->name)); init_waitqueue_head(&this->wait_q); f = kzalloc(sizeof(fsm), order); diff --git a/drivers/s390/net/qeth_ethtool.c b/drivers/s390/net/qeth_ethtool.c index 9eba0a32e9f9..e250f49535fa 100644 --- a/drivers/s390/net/qeth_ethtool.c +++ b/drivers/s390/net/qeth_ethtool.c @@ -188,9 +188,9 @@ static void qeth_get_drvinfo(struct net_device *dev, { struct qeth_card *card = dev->ml_priv; - strlcpy(info->driver, IS_LAYER2(card) ? "qeth_l2" : "qeth_l3", + strscpy(info->driver, IS_LAYER2(card) ? "qeth_l2" : "qeth_l3", sizeof(info->driver)); - strlcpy(info->fw_version, card->info.mcl_level, + strscpy(info->fw_version, card->info.mcl_level, sizeof(info->fw_version)); snprintf(info->bus_info, sizeof(info->bus_info), "%s/%s/%s", CARD_RDEV_ID(card), CARD_WDEV_ID(card), CARD_DDEV_ID(card)); diff --git a/drivers/s390/scsi/zfcp_aux.c b/drivers/s390/scsi/zfcp_aux.c index fd2f1c31bd21..df782646e856 100644 --- a/drivers/s390/scsi/zfcp_aux.c +++ b/drivers/s390/scsi/zfcp_aux.c @@ -103,7 +103,7 @@ static void __init zfcp_init_device_setup(char *devstr) token = strsep(&str, ","); if (!token || strlen(token) >= ZFCP_BUS_ID_SIZE) goto err_out; - strlcpy(busid, token, ZFCP_BUS_ID_SIZE); + strscpy(busid, token, ZFCP_BUS_ID_SIZE); token = strsep(&str, ","); if (!token || kstrtoull(token, 0, (unsigned long long *) &wwpn)) diff --git a/drivers/s390/scsi/zfcp_fc.c b/drivers/s390/scsi/zfcp_fc.c index b61acbb09be3..77917b339870 100644 --- a/drivers/s390/scsi/zfcp_fc.c +++ b/drivers/s390/scsi/zfcp_fc.c @@ -885,7 +885,7 @@ static int zfcp_fc_gspn(struct zfcp_adapter *adapter, dev_name(&adapter->ccw_device->dev), init_utsname()->nodename); else - strlcpy(fc_host_symbolic_name(adapter->scsi_host), + strscpy(fc_host_symbolic_name(adapter->scsi_host), gspn_rsp->gspn.fp_name, FC_SYMBOLIC_NAME_SIZE); return 0; diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index 688922fc4edb..76c3500b21c7 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -1935,10 +1935,10 @@ config BOOKE_WDT config BOOKE_WDT_DEFAULT_TIMEOUT int "PowerPC Book-E Watchdog Timer Default Timeout" depends on BOOKE_WDT - default 38 if PPC_FSL_BOOK3E - range 0 63 if PPC_FSL_BOOK3E - default 3 if !PPC_FSL_BOOK3E - range 0 3 if !PPC_FSL_BOOK3E + default 38 if PPC_E500 + range 0 63 if PPC_E500 + default 3 if !PPC_E500 + range 0 3 if !PPC_E500 help Select the default watchdog timer period to be used by the PowerPC Book-E watchdog driver. A watchdog "event" occurs when the bit diff --git a/drivers/watchdog/booke_wdt.c b/drivers/watchdog/booke_wdt.c index 75da5cd02615..932a03f4436a 100644 --- a/drivers/watchdog/booke_wdt.c +++ b/drivers/watchdog/booke_wdt.c @@ -27,7 +27,7 @@ */ -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 #define WDTP(x) ((((x)&0x3)<<30)|(((x)&0x3c)<<15)) #define WDTP_MASK (WDTP(0x3f)) #else @@ -45,7 +45,7 @@ MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); -#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_E500 /* For the specified period, determine the number of seconds * corresponding to the reset time. There will be a watchdog @@ -88,7 +88,7 @@ static unsigned int sec_to_period(unsigned int secs) #define MAX_WDT_TIMEOUT period_to_sec(1) -#else /* CONFIG_PPC_FSL_BOOK3E */ +#else /* CONFIG_PPC_E500 */ static unsigned long long period_to_sec(unsigned int period) { @@ -102,7 +102,7 @@ static unsigned int sec_to_period(unsigned int secs) #define MAX_WDT_TIMEOUT 3 /* from Kconfig */ -#endif /* !CONFIG_PPC_FSL_BOOK3E */ +#endif /* !CONFIG_PPC_E500 */ static void __booke_wdt_set(void *data) { diff --git a/fs/coredump.c b/fs/coredump.c index 3538f3a63965..7c6bb4e9db20 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -354,7 +354,7 @@ static int zap_process(struct task_struct *start, int exit_code) struct task_struct *t; int nr = 0; - /* ignore all signals except SIGKILL, see prepare_signal() */ + /* Allow SIGKILL, see prepare_signal() */ start->signal->flags = SIGNAL_GROUP_EXIT; start->signal->group_exit_code = exit_code; start->signal->group_stop_count = 0; diff --git a/fs/exec.c b/fs/exec.c index 768843477a49..de084e485462 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1879,7 +1879,7 @@ static int do_execveat_common(int fd, struct filename *filename, * whether NPROC limit is still exceeded. */ if ((current->flags & PF_NPROC_EXCEEDED) && - is_ucounts_overlimit(current_ucounts(), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) { + is_rlimit_overlimit(current_ucounts(), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) { retval = -EAGAIN; goto out_ret; } diff --git a/fs/proc/array.c b/fs/proc/array.c index 99fcbfda8e25..49283b8103c7 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -279,7 +279,7 @@ static inline void task_sig(struct seq_file *m, struct task_struct *p) collect_sigign_sigcatch(p, &ignored, &caught); num_threads = get_nr_threads(p); rcu_read_lock(); /* FIXME: is this correct? */ - qsize = get_ucounts_value(task_ucounts(p), UCOUNT_RLIMIT_SIGPENDING); + qsize = get_rlimit_value(task_ucounts(p), UCOUNT_RLIMIT_SIGPENDING); rcu_read_unlock(); qlim = task_rlimit(p, RLIMIT_SIGPENDING); unlock_task_sighand(p, &flags); diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 6e89f0e2fd20..208efd4fa52c 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -115,6 +115,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v) #endif show_val_kb(m, "PageTables: ", global_node_page_state(NR_PAGETABLE)); + show_val_kb(m, "SecPageTables: ", + global_node_page_state(NR_SECONDARY_PAGETABLE)); show_val_kb(m, "NFS_Unstable: ", 0); show_val_kb(m, "Bounce: ", diff --git a/include/asm-generic/compat.h b/include/asm-generic/compat.h index d06308a2a7a8..aeb257ad3d1a 100644 --- a/include/asm-generic/compat.h +++ b/include/asm-generic/compat.h @@ -14,12 +14,17 @@ #define COMPAT_OFF_T_MAX 0x7fffffff #endif -#if !defined(compat_arg_u64) && !defined(CONFIG_CPU_BIG_ENDIAN) +#ifndef compat_arg_u64 +#ifdef CONFIG_CPU_BIG_ENDIAN #define compat_arg_u64(name) u32 name##_lo, u32 name##_hi #define compat_arg_u64_dual(name) u32, name##_lo, u32, name##_hi +#else +#define compat_arg_u64(name) u32 name##_hi, u32 name##_lo +#define compat_arg_u64_dual(name) u32, name##_hi, u32, name##_lo +#endif #define compat_arg_u64_glue(name) (((u64)name##_lo & 0xffffffffUL) | \ ((u64)name##_hi << 32)) -#endif +#endif /* compat_arg_u64 */ /* These types are common across all compat ABIs */ typedef u32 compat_size_t; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 3ec981a0d8b3..1ec1535be04f 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -17,7 +17,7 @@ struct ctl_table; struct user_struct; struct mmu_gather; -#ifndef is_hugepd +#ifndef CONFIG_ARCH_HAS_HUGEPD typedef struct { unsigned long pd; } hugepd_t; #define is_hugepd(hugepd) (0) #define __hugepd(x) ((hugepd_t) { (x) }) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f4519d3689e1..32f259fa5801 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -151,12 +151,11 @@ static inline bool is_error_page(struct page *page) #define KVM_REQUEST_NO_ACTION BIT(10) /* * Architecture-independent vcpu->requests bit members - * Bits 4-7 are reserved for more arch-independent bits. + * Bits 3-7 are reserved for more arch-independent bits. */ #define KVM_REQ_TLB_FLUSH (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_VM_DEAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_UNBLOCK 2 -#define KVM_REQ_UNHALT 3 #define KVM_REQUEST_ARCH_BASE 8 /* @@ -2247,6 +2246,19 @@ static inline void kvm_handle_signal_exit(struct kvm_vcpu *vcpu) } #endif /* CONFIG_KVM_XFER_TO_GUEST_WORK */ +/* + * If more than one page is being (un)accounted, @virt must be the address of + * the first page of a block of pages what were allocated together (i.e + * accounted together). + * + * kvm_account_pgtable_pages() is thread-safe because mod_lruvec_page_state() + * is thread-safe. + */ +static inline void kvm_account_pgtable_pages(void *virt, int nr) +{ + mod_lruvec_page_state(virt_to_page(virt), NR_SECONDARY_PAGETABLE, nr); +} + /* * This defines how many reserved entries we want to keep before we * kick the vcpu to the userspace to avoid dirty ring full. This diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index b196eab316c2..5a18c518dca1 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -214,6 +214,7 @@ enum node_stat_item { NR_KERNEL_SCS_KB, /* measured in KiB */ #endif NR_PAGETABLE, /* used for pagetables */ + NR_SECONDARY_PAGETABLE, /* secondary pagetables, e.g. KVM pagetables */ #ifdef CONFIG_SWAP NR_SWAPCACHE, #endif diff --git a/include/linux/perf/riscv_pmu.h b/include/linux/perf/riscv_pmu.h index bf66fe011fa8..e17e86ad6f3a 100644 --- a/include/linux/perf/riscv_pmu.h +++ b/include/linux/perf/riscv_pmu.h @@ -45,7 +45,7 @@ struct riscv_pmu { irqreturn_t (*handle_irq)(int irq_num, void *dev); - int num_counters; + unsigned long cmask; u64 (*ctr_read)(struct perf_event *event); int (*ctr_get_idx)(struct perf_event *event); int (*ctr_get_width)(int idx); diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index cafbe03eed01..20099268fa25 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -94,6 +94,7 @@ struct signal_struct { refcount_t sigcnt; atomic_t live; int nr_threads; + int quick_threads; struct list_head thread_head; wait_queue_head_t wait_chldexit; /* for wait4() */ diff --git a/include/linux/security.h b/include/linux/security.h index 87fac3af6dad..ca1b7109c0db 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -114,6 +114,7 @@ enum lockdown_reason { LOCKDOWN_IOPORT, LOCKDOWN_MSR, LOCKDOWN_ACPI_TABLES, + LOCKDOWN_DEVICE_TREE, LOCKDOWN_PCMCIA_CIS, LOCKDOWN_TIOCSSERIAL, LOCKDOWN_MODULE_PARAMETERS, @@ -122,6 +123,7 @@ enum lockdown_reason { LOCKDOWN_XMON_WR, LOCKDOWN_BPF_WRITE_USER, LOCKDOWN_DBG_WRITE_KERNEL, + LOCKDOWN_RTAS_ERROR_INJECTION, LOCKDOWN_INTEGRITY_MAX, LOCKDOWN_KCORE, LOCKDOWN_KPROBES, diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 33a4240e6a6f..45f09bec02c4 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -54,15 +54,17 @@ enum ucount_type { UCOUNT_FANOTIFY_GROUPS, UCOUNT_FANOTIFY_MARKS, #endif + UCOUNT_COUNTS, +}; + +enum rlimit_type { UCOUNT_RLIMIT_NPROC, UCOUNT_RLIMIT_MSGQUEUE, UCOUNT_RLIMIT_SIGPENDING, UCOUNT_RLIMIT_MEMLOCK, - UCOUNT_COUNTS, + UCOUNT_RLIMIT_COUNTS, }; -#define MAX_PER_NAMESPACE_UCOUNTS UCOUNT_RLIMIT_NPROC - struct user_namespace { struct uid_gid_map uid_map; struct uid_gid_map gid_map; @@ -99,6 +101,7 @@ struct user_namespace { #endif struct ucounts *ucounts; long ucount_max[UCOUNT_COUNTS]; + long rlimit_max[UCOUNT_RLIMIT_COUNTS]; } __randomize_layout; struct ucounts { @@ -107,6 +110,7 @@ struct ucounts { kuid_t uid; atomic_t count; atomic_long_t ucount[UCOUNT_COUNTS]; + atomic_long_t rlimit[UCOUNT_RLIMIT_COUNTS]; }; extern struct user_namespace init_user_ns; @@ -120,21 +124,26 @@ struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid); struct ucounts * __must_check get_ucounts(struct ucounts *ucounts); void put_ucounts(struct ucounts *ucounts); -static inline long get_ucounts_value(struct ucounts *ucounts, enum ucount_type type) +static inline long get_rlimit_value(struct ucounts *ucounts, enum rlimit_type type) { - return atomic_long_read(&ucounts->ucount[type]); + return atomic_long_read(&ucounts->rlimit[type]); } -long inc_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v); -bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v); -long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type); -void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum ucount_type type); -bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long max); +long inc_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v); +bool dec_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v); +long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type); +void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type); +bool is_rlimit_overlimit(struct ucounts *ucounts, enum rlimit_type type, unsigned long max); -static inline void set_rlimit_ucount_max(struct user_namespace *ns, - enum ucount_type type, unsigned long max) +static inline long get_userns_rlimit_max(struct user_namespace *ns, enum rlimit_type type) { - ns->ucount_max[type] = max <= LONG_MAX ? max : LONG_MAX; + return READ_ONCE(ns->rlimit_max[type]); +} + +static inline void set_userns_rlimit_max(struct user_namespace *ns, + enum rlimit_type type, unsigned long max) +{ + ns->rlimit_max[type] = max <= LONG_MAX ? max : LONG_MAX; } #ifdef CONFIG_USER_NS diff --git a/include/math-emu/op-common.h b/include/math-emu/op-common.h index 4b57bbba588a..8ce066c035cf 100644 --- a/include/math-emu/op-common.h +++ b/include/math-emu/op-common.h @@ -662,12 +662,14 @@ do { \ if (X##_e < 0) \ { \ FP_SET_EXCEPTION(FP_EX_INEXACT); \ + fallthrough; \ case FP_CLS_ZERO: \ r = 0; \ } \ else if (X##_e >= rsize - (rsigned > 0 || X##_s) \ || (!rsigned && X##_s)) \ { /* overflow */ \ + fallthrough; \ case FP_CLS_NAN: \ case FP_CLS_INF: \ if (rsigned == 2) \ @@ -767,6 +769,7 @@ do { \ if (X##_e >= rsize - (rsigned > 0 || X##_s) \ || (!rsigned && X##_s)) \ { /* overflow */ \ + fallthrough; \ case FP_CLS_NAN: \ case FP_CLS_INF: \ if (!rsigned) \ diff --git a/init/Kconfig b/init/Kconfig index 3aeaafcf4d57..b666993b7961 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -473,8 +473,7 @@ config VIRT_CPU_ACCOUNTING choice prompt "Cputime accounting" - default TICK_CPU_ACCOUNTING if !PPC64 - default VIRT_CPU_ACCOUNTING_NATIVE if PPC64 + default TICK_CPU_ACCOUNTING # Kind of a stub config for the pure tick based cputime accounting config TICK_CPU_ACCOUNTING diff --git a/ipc/mqueue.c b/ipc/mqueue.c index f98de32aeea1..9cf314b3f079 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -1746,6 +1746,7 @@ out_filesystem: unregister_filesystem(&mqueue_fs_type); out_sysctl: kmem_cache_destroy(mqueue_inode_cachep); + retire_mq_sysctls(&init_ipc_ns); return error; } diff --git a/kernel/exit.c b/kernel/exit.c index 84021b24f79e..4f7424523bac 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -733,11 +733,29 @@ static void check_stack_usage(void) static inline void check_stack_usage(void) {} #endif +static void synchronize_group_exit(struct task_struct *tsk, long code) +{ + struct sighand_struct *sighand = tsk->sighand; + struct signal_struct *signal = tsk->signal; + + spin_lock_irq(&sighand->siglock); + signal->quick_threads--; + if ((signal->quick_threads == 0) && + !(signal->flags & SIGNAL_GROUP_EXIT)) { + signal->flags = SIGNAL_GROUP_EXIT; + signal->group_exit_code = code; + signal->group_stop_count = 0; + } + spin_unlock_irq(&sighand->siglock); +} + void __noreturn do_exit(long code) { struct task_struct *tsk = current; int group_dead; + synchronize_group_exit(tsk, code); + WARN_ON(tsk->plug); kcov_task_exit(tsk); @@ -905,7 +923,7 @@ do_group_exit(int exit_code) exit_code = sig->group_exit_code; else if (sig->group_exec_task) exit_code = 0; - else if (!thread_group_empty(current)) { + else { struct sighand_struct *const sighand = current->sighand; spin_lock_irq(&sighand->siglock); diff --git a/kernel/fork.c b/kernel/fork.c index 898ea2d04184..c5f99a9129cd 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -933,13 +933,13 @@ void __init fork_init(void) init_task.signal->rlim[RLIMIT_SIGPENDING] = init_task.signal->rlim[RLIMIT_NPROC]; - for (i = 0; i < MAX_PER_NAMESPACE_UCOUNTS; i++) + for (i = 0; i < UCOUNT_COUNTS; i++) init_user_ns.ucount_max[i] = max_threads/2; - set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_NPROC, RLIM_INFINITY); - set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE, RLIM_INFINITY); - set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, RLIM_INFINITY); - set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK, RLIM_INFINITY); + set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_NPROC, RLIM_INFINITY); + set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE, RLIM_INFINITY); + set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, RLIM_INFINITY); + set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK, RLIM_INFINITY); #ifdef CONFIG_VMAP_STACK cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache", @@ -1704,6 +1704,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) return -ENOMEM; sig->nr_threads = 1; + sig->quick_threads = 1; atomic_set(&sig->live, 1); refcount_set(&sig->sigcnt, 1); @@ -2129,7 +2130,7 @@ static __latent_entropy struct task_struct *copy_process( goto bad_fork_free; retval = -EAGAIN; - if (is_ucounts_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) { + if (is_rlimit_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) { if (p->real_cred->user != INIT_USER && !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) goto bad_fork_cleanup_count; @@ -2473,6 +2474,7 @@ static __latent_entropy struct task_struct *copy_process( __this_cpu_inc(process_counts); } else { current->signal->nr_threads++; + current->signal->quick_threads++; atomic_inc(¤t->signal->live); refcount_inc(¤t->signal->sigcnt); task_join_group_stop(p); diff --git a/kernel/kthread.c b/kernel/kthread.c index de7238e5fe8c..261021050f6c 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -705,6 +705,7 @@ int kthread_stop(struct task_struct *k) kthread = to_kthread(k); set_bit(KTHREAD_SHOULD_STOP, &kthread->flags); kthread_unpark(k); + set_tsk_thread_flag(k, TIF_NOTIFY_SIGNAL); wake_up_process(k); wait_for_completion(&kthread->exited); ret = kthread->result; diff --git a/kernel/signal.c b/kernel/signal.c index 6f86fda5e432..8a0f114d00e0 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -913,8 +913,9 @@ static bool prepare_signal(int sig, struct task_struct *p, bool force) if (signal->core_state) return sig == SIGKILL; /* - * The process is in the middle of dying, nothing to do. + * The process is in the middle of dying, drop the signal. */ + return false; } else if (sig_kernel_stop(sig)) { /* * This is a stop signal. Remove SIGCONT from all queues. diff --git a/kernel/sys.c b/kernel/sys.c index 3dd04b0b46e5..7982bbab8033 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -498,7 +498,7 @@ static void flag_nproc_exceeded(struct cred *new) * for programs doing set*uid()+execve() by harmlessly deferring the * failure to the execve() stage. */ - if (is_ucounts_overlimit(new->ucounts, UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC)) && + if (is_rlimit_overlimit(new->ucounts, UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC)) && new->user != INIT_USER) current->flags |= PF_NPROC_EXCEEDED; else diff --git a/kernel/ucount.c b/kernel/ucount.c index 06ea04d44685..ee8e57fd6f90 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -87,10 +87,6 @@ static struct ctl_table user_table[] = { UCOUNT_ENTRY("max_fanotify_groups"), UCOUNT_ENTRY("max_fanotify_marks"), #endif - { }, - { }, - { }, - { }, { } }; #endif /* CONFIG_SYSCTL */ @@ -263,29 +259,29 @@ void dec_ucount(struct ucounts *ucounts, enum ucount_type type) put_ucounts(ucounts); } -long inc_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v) +long inc_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v) { struct ucounts *iter; long max = LONG_MAX; long ret = 0; for (iter = ucounts; iter; iter = iter->ns->ucounts) { - long new = atomic_long_add_return(v, &iter->ucount[type]); + long new = atomic_long_add_return(v, &iter->rlimit[type]); if (new < 0 || new > max) ret = LONG_MAX; else if (iter == ucounts) ret = new; - max = READ_ONCE(iter->ns->ucount_max[type]); + max = get_userns_rlimit_max(iter->ns, type); } return ret; } -bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v) +bool dec_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v) { struct ucounts *iter; long new = -1; /* Silence compiler warning */ for (iter = ucounts; iter; iter = iter->ns->ucounts) { - long dec = atomic_long_sub_return(v, &iter->ucount[type]); + long dec = atomic_long_sub_return(v, &iter->rlimit[type]); WARN_ON_ONCE(dec < 0); if (iter == ucounts) new = dec; @@ -294,11 +290,11 @@ bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v) } static void do_dec_rlimit_put_ucounts(struct ucounts *ucounts, - struct ucounts *last, enum ucount_type type) + struct ucounts *last, enum rlimit_type type) { struct ucounts *iter, *next; for (iter = ucounts; iter != last; iter = next) { - long dec = atomic_long_sub_return(1, &iter->ucount[type]); + long dec = atomic_long_sub_return(1, &iter->rlimit[type]); WARN_ON_ONCE(dec < 0); next = iter->ns->ucounts; if (dec == 0) @@ -306,12 +302,12 @@ static void do_dec_rlimit_put_ucounts(struct ucounts *ucounts, } } -void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum ucount_type type) +void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type) { do_dec_rlimit_put_ucounts(ucounts, NULL, type); } -long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type) +long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type) { /* Caller must hold a reference to ucounts */ struct ucounts *iter; @@ -319,12 +315,12 @@ long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type) long dec, ret = 0; for (iter = ucounts; iter; iter = iter->ns->ucounts) { - long new = atomic_long_add_return(1, &iter->ucount[type]); + long new = atomic_long_add_return(1, &iter->rlimit[type]); if (new < 0 || new > max) goto unwind; if (iter == ucounts) ret = new; - max = READ_ONCE(iter->ns->ucount_max[type]); + max = get_userns_rlimit_max(iter->ns, type); /* * Grab an extra ucount reference for the caller when * the rlimit count was previously 0. @@ -336,24 +332,24 @@ long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type) } return ret; dec_unwind: - dec = atomic_long_sub_return(1, &iter->ucount[type]); + dec = atomic_long_sub_return(1, &iter->rlimit[type]); WARN_ON_ONCE(dec < 0); unwind: do_dec_rlimit_put_ucounts(ucounts, iter, type); return 0; } -bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long rlimit) +bool is_rlimit_overlimit(struct ucounts *ucounts, enum rlimit_type type, unsigned long rlimit) { struct ucounts *iter; long max = rlimit; if (rlimit > LONG_MAX) max = LONG_MAX; for (iter = ucounts; iter; iter = iter->ns->ucounts) { - long val = get_ucounts_value(iter, type); + long val = get_rlimit_value(iter, type); if (val < 0 || val > max) return true; - max = READ_ONCE(iter->ns->ucount_max[type]); + max = get_userns_rlimit_max(iter->ns, type); } return false; } diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 3f464bbda0e9..54211dbd516c 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -136,13 +136,13 @@ int create_user_ns(struct cred *new) ns->owner = owner; ns->group = group; INIT_WORK(&ns->work, free_user_ns); - for (i = 0; i < MAX_PER_NAMESPACE_UCOUNTS; i++) { + for (i = 0; i < UCOUNT_COUNTS; i++) { ns->ucount_max[i] = INT_MAX; } - set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_NPROC, enforced_nproc_rlimit()); - set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_MSGQUEUE, rlimit(RLIMIT_MSGQUEUE)); - set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_SIGPENDING, rlimit(RLIMIT_SIGPENDING)); - set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_MEMLOCK, rlimit(RLIMIT_MEMLOCK)); + set_userns_rlimit_max(ns, UCOUNT_RLIMIT_NPROC, enforced_nproc_rlimit()); + set_userns_rlimit_max(ns, UCOUNT_RLIMIT_MSGQUEUE, rlimit(RLIMIT_MSGQUEUE)); + set_userns_rlimit_max(ns, UCOUNT_RLIMIT_SIGPENDING, rlimit(RLIMIT_SIGPENDING)); + set_userns_rlimit_max(ns, UCOUNT_RLIMIT_MEMLOCK, rlimit(RLIMIT_MEMLOCK)); ns->ucounts = ucounts; /* Inherit USERNS_SETGROUPS_ALLOWED from our parent */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b69979c9ced5..9d054e3767ce 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1401,6 +1401,7 @@ static const struct memory_stat memory_stats[] = { { "kernel", MEMCG_KMEM }, { "kernel_stack", NR_KERNEL_STACK_KB }, { "pagetables", NR_PAGETABLE }, + { "sec_pagetables", NR_SECONDARY_PAGETABLE }, { "percpu", MEMCG_PERCPU_B }, { "sock", MEMCG_SOCK }, { "vmalloc", MEMCG_VMALLOC }, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d04211f0ef0b..08522a831c7a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6085,7 +6085,8 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) " active_file:%lu inactive_file:%lu isolated_file:%lu\n" " unevictable:%lu dirty:%lu writeback:%lu\n" " slab_reclaimable:%lu slab_unreclaimable:%lu\n" - " mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n" + " mapped:%lu shmem:%lu pagetables:%lu\n" + " sec_pagetables:%lu bounce:%lu\n" " kernel_misc_reclaimable:%lu\n" " free:%lu free_pcp:%lu free_cma:%lu\n", global_node_page_state(NR_ACTIVE_ANON), @@ -6102,6 +6103,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) global_node_page_state(NR_FILE_MAPPED), global_node_page_state(NR_SHMEM), global_node_page_state(NR_PAGETABLE), + global_node_page_state(NR_SECONDARY_PAGETABLE), global_zone_page_state(NR_BOUNCE), global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE), global_zone_page_state(NR_FREE_PAGES), @@ -6135,6 +6137,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) " shadow_call_stack:%lukB" #endif " pagetables:%lukB" + " sec_pagetables:%lukB" " all_unreclaimable? %s" "\n", pgdat->node_id, @@ -6160,6 +6163,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) node_page_state(pgdat, NR_KERNEL_SCS_KB), #endif K(node_page_state(pgdat, NR_PAGETABLE)), + K(node_page_state(pgdat, NR_SECONDARY_PAGETABLE)), pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ? "yes" : "no"); } diff --git a/mm/vmstat.c b/mm/vmstat.c index 528a17135bc8..ac798de3d55e 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1245,6 +1245,7 @@ const char * const vmstat_text[] = { "nr_shadow_call_stack", #endif "nr_page_table_pages", + "nr_sec_page_table_pages", #ifdef CONFIG_SWAP "nr_swapcached", #endif diff --git a/security/security.c b/security/security.c index 8312b3bf1169..79d82cb6e469 100644 --- a/security/security.c +++ b/security/security.c @@ -52,6 +52,7 @@ const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1] = { [LOCKDOWN_IOPORT] = "raw io port access", [LOCKDOWN_MSR] = "raw MSR access", [LOCKDOWN_ACPI_TABLES] = "modifying ACPI tables", + [LOCKDOWN_DEVICE_TREE] = "modifying device tree contents", [LOCKDOWN_PCMCIA_CIS] = "direct PCMCIA CIS storage", [LOCKDOWN_TIOCSSERIAL] = "reconfiguration of serial port IO", [LOCKDOWN_MODULE_PARAMETERS] = "unsafe module parameters", @@ -60,6 +61,7 @@ const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1] = { [LOCKDOWN_XMON_WR] = "xmon write access", [LOCKDOWN_BPF_WRITE_USER] = "use of bpf to write user RAM", [LOCKDOWN_DBG_WRITE_KERNEL] = "use of kgdb/kdb to write kernel RAM", + [LOCKDOWN_RTAS_ERROR_INJECTION] = "RTAS error injection", [LOCKDOWN_INTEGRITY_MAX] = "integrity", [LOCKDOWN_KCORE] = "/proc/kcore access", [LOCKDOWN_KPROBES] = "use of kprobes", diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 2600b4237292..2bca64f96164 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -110,7 +110,7 @@ 79 common settimeofday sys_settimeofday compat_sys_settimeofday 80 common getgroups sys_getgroups 81 common setgroups sys_setgroups -82 32 select ppc_select sys_ni_syscall +82 32 select sys_old_select compat_sys_old_select 82 64 select sys_ni_syscall 82 spu select sys_ni_syscall 83 common symlink sys_symlink @@ -178,9 +178,9 @@ 133 common fchdir sys_fchdir 134 common bdflush sys_ni_syscall 135 common sysfs sys_sysfs -136 32 personality sys_personality ppc64_personality -136 64 personality ppc64_personality -136 spu personality ppc64_personality +136 32 personality sys_personality compat_sys_ppc64_personality +136 64 personality sys_ppc64_personality +136 spu personality sys_ppc64_personality 137 common afs_syscall sys_ni_syscall 138 common setfsuid sys_setfsuid 139 common setfsgid sys_setfsgid @@ -228,8 +228,8 @@ 176 64 rt_sigtimedwait sys_rt_sigtimedwait 177 nospu rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo 178 nospu rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend -179 common pread64 sys_pread64 compat_sys_pread64 -180 common pwrite64 sys_pwrite64 compat_sys_pwrite64 +179 common pread64 sys_pread64 compat_sys_ppc_pread64 +180 common pwrite64 sys_pwrite64 compat_sys_ppc_pwrite64 181 common chown sys_chown 182 common getcwd sys_getcwd 183 common capget sys_capget @@ -242,10 +242,10 @@ 188 common putpmsg sys_ni_syscall 189 nospu vfork sys_vfork 190 common ugetrlimit sys_getrlimit compat_sys_getrlimit -191 common readahead sys_readahead compat_sys_readahead +191 common readahead sys_readahead compat_sys_ppc_readahead 192 32 mmap2 sys_mmap2 compat_sys_mmap2 -193 32 truncate64 sys_truncate64 compat_sys_truncate64 -194 32 ftruncate64 sys_ftruncate64 compat_sys_ftruncate64 +193 32 truncate64 sys_truncate64 compat_sys_ppc_truncate64 +194 32 ftruncate64 sys_ftruncate64 compat_sys_ppc_ftruncate64 195 32 stat64 sys_stat64 196 32 lstat64 sys_lstat64 197 32 fstat64 sys_fstat64 @@ -288,7 +288,7 @@ 230 common io_submit sys_io_submit compat_sys_io_submit 231 common io_cancel sys_io_cancel 232 nospu set_tid_address sys_set_tid_address -233 common fadvise64 sys_fadvise64 ppc32_fadvise64 +233 common fadvise64 sys_fadvise64 compat_sys_ppc32_fadvise64 234 nospu exit_group sys_exit_group 235 nospu lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie 236 common epoll_create sys_epoll_create @@ -323,7 +323,7 @@ 251 spu utimes sys_utimes 252 common statfs64 sys_statfs64 compat_sys_statfs64 253 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 -254 32 fadvise64_64 ppc_fadvise64_64 +254 32 fadvise64_64 sys_ppc_fadvise64_64 254 spu fadvise64_64 sys_ni_syscall 255 common rtas sys_rtas 256 32 sys_debug_setcontext sys_debug_setcontext sys_ni_syscall @@ -390,7 +390,7 @@ 305 common signalfd sys_signalfd compat_sys_signalfd 306 common timerfd_create sys_timerfd_create 307 common eventfd sys_eventfd -308 common sync_file_range2 sys_sync_file_range2 compat_sys_sync_file_range2 +308 common sync_file_range2 sys_sync_file_range2 compat_sys_ppc_sync_file_range2 309 nospu fallocate sys_fallocate compat_sys_fallocate 310 nospu subpage_prot sys_subpage_prot 311 32 timerfd_settime sys_timerfd_settime32 diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index d625a3f83780..45d9aee1c0d8 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -28,6 +28,7 @@ /x86_64/max_vcpuid_cap_test /x86_64/mmio_warning_test /x86_64/monitor_mwait_test +/x86_64/nested_exceptions_test /x86_64/nx_huge_pages_test /x86_64/platform_info_test /x86_64/pmu_event_filter_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 6448cb9f710f..fde3ae8cfa4c 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -91,6 +91,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/kvm_clock_test TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test TEST_GEN_PROGS_x86_64 += x86_64/monitor_mwait_test +TEST_GEN_PROGS_x86_64 += x86_64/nested_exceptions_test TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test TEST_GEN_PROGS_x86_64 += x86_64/pmu_event_filter_test TEST_GEN_PROGS_x86_64 += x86_64/set_boot_cpu_id diff --git a/tools/testing/selftests/kvm/include/x86_64/evmcs.h b/tools/testing/selftests/kvm/include/x86_64/evmcs.h index 3c9260f8e116..58db74f68af2 100644 --- a/tools/testing/selftests/kvm/include/x86_64/evmcs.h +++ b/tools/testing/selftests/kvm/include/x86_64/evmcs.h @@ -203,14 +203,25 @@ struct hv_enlightened_vmcs { u32 reserved:30; } hv_enlightenments_control; u32 hv_vp_id; - + u32 padding32_2; u64 hv_vm_id; u64 partition_assist_page; u64 padding64_4[4]; u64 guest_bndcfgs; - u64 padding64_5[7]; + u64 guest_ia32_perf_global_ctrl; + u64 guest_ia32_s_cet; + u64 guest_ssp; + u64 guest_ia32_int_ssp_table_addr; + u64 guest_ia32_lbr_ctl; + u64 padding64_5[2]; u64 xss_exit_bitmap; - u64 padding64_6[7]; + u64 encls_exiting_bitmap; + u64 host_ia32_perf_global_ctrl; + u64 tsc_multiplier; + u64 host_ia32_s_cet; + u64 host_ssp; + u64 host_ia32_int_ssp_table_addr; + u64 padding64_6; }; #define HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE 0 @@ -656,6 +667,18 @@ static inline int evmcs_vmread(uint64_t encoding, uint64_t *value) case VIRTUAL_PROCESSOR_ID: *value = current_evmcs->virtual_processor_id; break; + case HOST_IA32_PERF_GLOBAL_CTRL: + *value = current_evmcs->host_ia32_perf_global_ctrl; + break; + case GUEST_IA32_PERF_GLOBAL_CTRL: + *value = current_evmcs->guest_ia32_perf_global_ctrl; + break; + case ENCLS_EXITING_BITMAP: + *value = current_evmcs->encls_exiting_bitmap; + break; + case TSC_MULTIPLIER: + *value = current_evmcs->tsc_multiplier; + break; default: return 1; } @@ -1169,6 +1192,22 @@ static inline int evmcs_vmwrite(uint64_t encoding, uint64_t value) current_evmcs->virtual_processor_id = value; current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT; break; + case HOST_IA32_PERF_GLOBAL_CTRL: + current_evmcs->host_ia32_perf_global_ctrl = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; + break; + case GUEST_IA32_PERF_GLOBAL_CTRL: + current_evmcs->guest_ia32_perf_global_ctrl = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; + break; + case ENCLS_EXITING_BITMAP: + current_evmcs->encls_exiting_bitmap = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2; + break; + case TSC_MULTIPLIER: + current_evmcs->tsc_multiplier = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2; + break; default: return 1; } diff --git a/tools/testing/selftests/kvm/include/x86_64/svm_util.h b/tools/testing/selftests/kvm/include/x86_64/svm_util.h index a339b537a575..7aee6244ab6a 100644 --- a/tools/testing/selftests/kvm/include/x86_64/svm_util.h +++ b/tools/testing/selftests/kvm/include/x86_64/svm_util.h @@ -9,15 +9,12 @@ #ifndef SELFTEST_KVM_SVM_UTILS_H #define SELFTEST_KVM_SVM_UTILS_H +#include + #include #include "svm.h" #include "processor.h" -#define SVM_EXIT_EXCP_BASE 0x040 -#define SVM_EXIT_HLT 0x078 -#define SVM_EXIT_MSR 0x07c -#define SVM_EXIT_VMMCALL 0x081 - struct svm_test_data { /* VMCB */ struct vmcb *vmcb; /* gva */ diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h index 790c6d1ecb34..71b290b6469d 100644 --- a/tools/testing/selftests/kvm/include/x86_64/vmx.h +++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h @@ -8,6 +8,8 @@ #ifndef SELFTEST_KVM_VMX_H #define SELFTEST_KVM_VMX_H +#include + #include #include "processor.h" #include "apic.h" @@ -100,55 +102,6 @@ #define VMX_EPT_VPID_CAP_AD_BITS 0x00200000 #define EXIT_REASON_FAILED_VMENTRY 0x80000000 -#define EXIT_REASON_EXCEPTION_NMI 0 -#define EXIT_REASON_EXTERNAL_INTERRUPT 1 -#define EXIT_REASON_TRIPLE_FAULT 2 -#define EXIT_REASON_INTERRUPT_WINDOW 7 -#define EXIT_REASON_NMI_WINDOW 8 -#define EXIT_REASON_TASK_SWITCH 9 -#define EXIT_REASON_CPUID 10 -#define EXIT_REASON_HLT 12 -#define EXIT_REASON_INVD 13 -#define EXIT_REASON_INVLPG 14 -#define EXIT_REASON_RDPMC 15 -#define EXIT_REASON_RDTSC 16 -#define EXIT_REASON_VMCALL 18 -#define EXIT_REASON_VMCLEAR 19 -#define EXIT_REASON_VMLAUNCH 20 -#define EXIT_REASON_VMPTRLD 21 -#define EXIT_REASON_VMPTRST 22 -#define EXIT_REASON_VMREAD 23 -#define EXIT_REASON_VMRESUME 24 -#define EXIT_REASON_VMWRITE 25 -#define EXIT_REASON_VMOFF 26 -#define EXIT_REASON_VMON 27 -#define EXIT_REASON_CR_ACCESS 28 -#define EXIT_REASON_DR_ACCESS 29 -#define EXIT_REASON_IO_INSTRUCTION 30 -#define EXIT_REASON_MSR_READ 31 -#define EXIT_REASON_MSR_WRITE 32 -#define EXIT_REASON_INVALID_STATE 33 -#define EXIT_REASON_MWAIT_INSTRUCTION 36 -#define EXIT_REASON_MONITOR_INSTRUCTION 39 -#define EXIT_REASON_PAUSE_INSTRUCTION 40 -#define EXIT_REASON_MCE_DURING_VMENTRY 41 -#define EXIT_REASON_TPR_BELOW_THRESHOLD 43 -#define EXIT_REASON_APIC_ACCESS 44 -#define EXIT_REASON_EOI_INDUCED 45 -#define EXIT_REASON_EPT_VIOLATION 48 -#define EXIT_REASON_EPT_MISCONFIG 49 -#define EXIT_REASON_INVEPT 50 -#define EXIT_REASON_RDTSCP 51 -#define EXIT_REASON_PREEMPTION_TIMER 52 -#define EXIT_REASON_INVVPID 53 -#define EXIT_REASON_WBINVD 54 -#define EXIT_REASON_XSETBV 55 -#define EXIT_REASON_APIC_WRITE 56 -#define EXIT_REASON_INVPCID 58 -#define EXIT_REASON_PML_FULL 62 -#define EXIT_REASON_XSAVES 63 -#define EXIT_REASON_XRSTORS 64 -#define LAST_EXIT_REASON 64 enum vmcs_field { VIRTUAL_PROCESSOR_ID = 0x00000000, @@ -208,6 +161,8 @@ enum vmcs_field { VMWRITE_BITMAP_HIGH = 0x00002029, XSS_EXIT_BITMAP = 0x0000202C, XSS_EXIT_BITMAP_HIGH = 0x0000202D, + ENCLS_EXITING_BITMAP = 0x0000202E, + ENCLS_EXITING_BITMAP_HIGH = 0x0000202F, TSC_MULTIPLIER = 0x00002032, TSC_MULTIPLIER_HIGH = 0x00002033, GUEST_PHYSICAL_ADDRESS = 0x00002400, diff --git a/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c b/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c new file mode 100644 index 000000000000..ac33835f78f4 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c @@ -0,0 +1,295 @@ +// SPDX-License-Identifier: GPL-2.0-only +#define _GNU_SOURCE /* for program_invocation_short_name */ + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "vmx.h" +#include "svm_util.h" + +#define L2_GUEST_STACK_SIZE 256 + +/* + * Arbitrary, never shoved into KVM/hardware, just need to avoid conflict with + * the "real" exceptions used, #SS/#GP/#DF (12/13/8). + */ +#define FAKE_TRIPLE_FAULT_VECTOR 0xaa + +/* Arbitrary 32-bit error code injected by this test. */ +#define SS_ERROR_CODE 0xdeadbeef + +/* + * Bit '0' is set on Intel if the exception occurs while delivering a previous + * event/exception. AMD's wording is ambiguous, but presumably the bit is set + * if the exception occurs while delivering an external event, e.g. NMI or INTR, + * but not for exceptions that occur when delivering other exceptions or + * software interrupts. + * + * Note, Intel's name for it, "External event", is misleading and much more + * aligned with AMD's behavior, but the SDM is quite clear on its behavior. + */ +#define ERROR_CODE_EXT_FLAG BIT(0) + +/* + * Bit '1' is set if the fault occurred when looking up a descriptor in the + * IDT, which is the case here as the IDT is empty/NULL. + */ +#define ERROR_CODE_IDT_FLAG BIT(1) + +/* + * The #GP that occurs when vectoring #SS should show the index into the IDT + * for #SS, plus have the "IDT flag" set. + */ +#define GP_ERROR_CODE_AMD ((SS_VECTOR * 8) | ERROR_CODE_IDT_FLAG) +#define GP_ERROR_CODE_INTEL ((SS_VECTOR * 8) | ERROR_CODE_IDT_FLAG | ERROR_CODE_EXT_FLAG) + +/* + * Intel and AMD both shove '0' into the error code on #DF, regardless of what + * led to the double fault. + */ +#define DF_ERROR_CODE 0 + +#define INTERCEPT_SS (BIT_ULL(SS_VECTOR)) +#define INTERCEPT_SS_DF (INTERCEPT_SS | BIT_ULL(DF_VECTOR)) +#define INTERCEPT_SS_GP_DF (INTERCEPT_SS_DF | BIT_ULL(GP_VECTOR)) + +static void l2_ss_pending_test(void) +{ + GUEST_SYNC(SS_VECTOR); +} + +static void l2_ss_injected_gp_test(void) +{ + GUEST_SYNC(GP_VECTOR); +} + +static void l2_ss_injected_df_test(void) +{ + GUEST_SYNC(DF_VECTOR); +} + +static void l2_ss_injected_tf_test(void) +{ + GUEST_SYNC(FAKE_TRIPLE_FAULT_VECTOR); +} + +static void svm_run_l2(struct svm_test_data *svm, void *l2_code, int vector, + uint32_t error_code) +{ + struct vmcb *vmcb = svm->vmcb; + struct vmcb_control_area *ctrl = &vmcb->control; + + vmcb->save.rip = (u64)l2_code; + run_guest(vmcb, svm->vmcb_gpa); + + if (vector == FAKE_TRIPLE_FAULT_VECTOR) + return; + + GUEST_ASSERT_EQ(ctrl->exit_code, (SVM_EXIT_EXCP_BASE + vector)); + GUEST_ASSERT_EQ(ctrl->exit_info_1, error_code); +} + +static void l1_svm_code(struct svm_test_data *svm) +{ + struct vmcb_control_area *ctrl = &svm->vmcb->control; + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + + generic_svm_setup(svm, NULL, &l2_guest_stack[L2_GUEST_STACK_SIZE]); + svm->vmcb->save.idtr.limit = 0; + ctrl->intercept |= BIT_ULL(INTERCEPT_SHUTDOWN); + + ctrl->intercept_exceptions = INTERCEPT_SS_GP_DF; + svm_run_l2(svm, l2_ss_pending_test, SS_VECTOR, SS_ERROR_CODE); + svm_run_l2(svm, l2_ss_injected_gp_test, GP_VECTOR, GP_ERROR_CODE_AMD); + + ctrl->intercept_exceptions = INTERCEPT_SS_DF; + svm_run_l2(svm, l2_ss_injected_df_test, DF_VECTOR, DF_ERROR_CODE); + + ctrl->intercept_exceptions = INTERCEPT_SS; + svm_run_l2(svm, l2_ss_injected_tf_test, FAKE_TRIPLE_FAULT_VECTOR, 0); + GUEST_ASSERT_EQ(ctrl->exit_code, SVM_EXIT_SHUTDOWN); + + GUEST_DONE(); +} + +static void vmx_run_l2(void *l2_code, int vector, uint32_t error_code) +{ + GUEST_ASSERT(!vmwrite(GUEST_RIP, (u64)l2_code)); + + GUEST_ASSERT_EQ(vector == SS_VECTOR ? vmlaunch() : vmresume(), 0); + + if (vector == FAKE_TRIPLE_FAULT_VECTOR) + return; + + GUEST_ASSERT_EQ(vmreadz(VM_EXIT_REASON), EXIT_REASON_EXCEPTION_NMI); + GUEST_ASSERT_EQ((vmreadz(VM_EXIT_INTR_INFO) & 0xff), vector); + GUEST_ASSERT_EQ(vmreadz(VM_EXIT_INTR_ERROR_CODE), error_code); +} + +static void l1_vmx_code(struct vmx_pages *vmx) +{ + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + + GUEST_ASSERT_EQ(prepare_for_vmx_operation(vmx), true); + + GUEST_ASSERT_EQ(load_vmcs(vmx), true); + + prepare_vmcs(vmx, NULL, &l2_guest_stack[L2_GUEST_STACK_SIZE]); + GUEST_ASSERT_EQ(vmwrite(GUEST_IDTR_LIMIT, 0), 0); + + /* + * VMX disallows injecting an exception with error_code[31:16] != 0, + * and hardware will never generate a VM-Exit with bits 31:16 set. + * KVM should likewise truncate the "bad" userspace value. + */ + GUEST_ASSERT_EQ(vmwrite(EXCEPTION_BITMAP, INTERCEPT_SS_GP_DF), 0); + vmx_run_l2(l2_ss_pending_test, SS_VECTOR, (u16)SS_ERROR_CODE); + vmx_run_l2(l2_ss_injected_gp_test, GP_VECTOR, GP_ERROR_CODE_INTEL); + + GUEST_ASSERT_EQ(vmwrite(EXCEPTION_BITMAP, INTERCEPT_SS_DF), 0); + vmx_run_l2(l2_ss_injected_df_test, DF_VECTOR, DF_ERROR_CODE); + + GUEST_ASSERT_EQ(vmwrite(EXCEPTION_BITMAP, INTERCEPT_SS), 0); + vmx_run_l2(l2_ss_injected_tf_test, FAKE_TRIPLE_FAULT_VECTOR, 0); + GUEST_ASSERT_EQ(vmreadz(VM_EXIT_REASON), EXIT_REASON_TRIPLE_FAULT); + + GUEST_DONE(); +} + +static void __attribute__((__flatten__)) l1_guest_code(void *test_data) +{ + if (this_cpu_has(X86_FEATURE_SVM)) + l1_svm_code(test_data); + else + l1_vmx_code(test_data); +} + +static void assert_ucall_vector(struct kvm_vcpu *vcpu, int vector) +{ + struct kvm_run *run = vcpu->run; + struct ucall uc; + + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s),\n", + run->exit_reason, exit_reason_str(run->exit_reason)); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_SYNC: + TEST_ASSERT(vector == uc.args[1], + "Expected L2 to ask for %d, got %ld", vector, uc.args[1]); + break; + case UCALL_DONE: + TEST_ASSERT(vector == -1, + "Expected L2 to ask for %d, L2 says it's done", vector); + break; + case UCALL_ABORT: + TEST_FAIL("%s at %s:%ld (0x%lx != 0x%lx)", + (const char *)uc.args[0], __FILE__, uc.args[1], + uc.args[2], uc.args[3]); + break; + default: + TEST_FAIL("Expected L2 to ask for %d, got unexpected ucall %lu", vector, uc.cmd); + } +} + +static void queue_ss_exception(struct kvm_vcpu *vcpu, bool inject) +{ + struct kvm_vcpu_events events; + + vcpu_events_get(vcpu, &events); + + TEST_ASSERT(!events.exception.pending, + "Vector %d unexpectedlt pending", events.exception.nr); + TEST_ASSERT(!events.exception.injected, + "Vector %d unexpectedly injected", events.exception.nr); + + events.flags = KVM_VCPUEVENT_VALID_PAYLOAD; + events.exception.pending = !inject; + events.exception.injected = inject; + events.exception.nr = SS_VECTOR; + events.exception.has_error_code = true; + events.exception.error_code = SS_ERROR_CODE; + vcpu_events_set(vcpu, &events); +} + +/* + * Verify KVM_{G,S}ET_EVENTS play nice with pending vs. injected exceptions + * when an exception is being queued for L2. Specifically, verify that KVM + * honors L1 exception intercept controls when a #SS is pending/injected, + * triggers a #GP on vectoring the #SS, morphs to #DF if #GP isn't intercepted + * by L1, and finally causes (nested) SHUTDOWN if #DF isn't intercepted by L1. + */ +int main(int argc, char *argv[]) +{ + vm_vaddr_t nested_test_data_gva; + struct kvm_vcpu_events events; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_EXCEPTION_PAYLOAD)); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM) || kvm_cpu_has(X86_FEATURE_VMX)); + + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); + vm_enable_cap(vm, KVM_CAP_EXCEPTION_PAYLOAD, -2ul); + + if (kvm_cpu_has(X86_FEATURE_SVM)) + vcpu_alloc_svm(vm, &nested_test_data_gva); + else + vcpu_alloc_vmx(vm, &nested_test_data_gva); + + vcpu_args_set(vcpu, 1, nested_test_data_gva); + + /* Run L1 => L2. L2 should sync and request #SS. */ + vcpu_run(vcpu); + assert_ucall_vector(vcpu, SS_VECTOR); + + /* Pend #SS and request immediate exit. #SS should still be pending. */ + queue_ss_exception(vcpu, false); + vcpu->run->immediate_exit = true; + vcpu_run_complete_io(vcpu); + + /* Verify the pending events comes back out the same as it went in. */ + vcpu_events_get(vcpu, &events); + ASSERT_EQ(events.flags & KVM_VCPUEVENT_VALID_PAYLOAD, + KVM_VCPUEVENT_VALID_PAYLOAD); + ASSERT_EQ(events.exception.pending, true); + ASSERT_EQ(events.exception.nr, SS_VECTOR); + ASSERT_EQ(events.exception.has_error_code, true); + ASSERT_EQ(events.exception.error_code, SS_ERROR_CODE); + + /* + * Run for real with the pending #SS, L1 should get a VM-Exit due to + * #SS interception and re-enter L2 to request #GP (via injected #SS). + */ + vcpu->run->immediate_exit = false; + vcpu_run(vcpu); + assert_ucall_vector(vcpu, GP_VECTOR); + + /* + * Inject #SS, the #SS should bypass interception and cause #GP, which + * L1 should intercept before KVM morphs it to #DF. L1 should then + * disable #GP interception and run L2 to request #DF (via #SS => #GP). + */ + queue_ss_exception(vcpu, true); + vcpu_run(vcpu); + assert_ucall_vector(vcpu, DF_VECTOR); + + /* + * Inject #SS, the #SS should bypass interception and cause #GP, which + * L1 is no longer interception, and so should see a #DF VM-Exit. L1 + * should then signal that is done. + */ + queue_ss_exception(vcpu, true); + vcpu_run(vcpu); + assert_ucall_vector(vcpu, FAKE_TRIPLE_FAULT_VECTOR); + + /* + * Inject #SS yet again. L1 is not intercepting #GP or #DF, and so + * should see nested TRIPLE_FAULT / SHUTDOWN. + */ + queue_ss_exception(vcpu, true); + vcpu_run(vcpu); + assert_ucall_vector(vcpu, -1); + + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c index cc6421716400..e19933ea34ca 100644 --- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c +++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c @@ -118,13 +118,6 @@ void run_test(int reclaim_period_ms, bool disable_nx_huge_pages, vm = vm_create(1); if (disable_nx_huge_pages) { - /* - * Cannot run the test without NX huge pages if the kernel - * does not support it. - */ - if (!kvm_check_cap(KVM_CAP_VM_DISABLE_NX_HUGE_PAGES)) - return; - r = __vm_disable_nx_huge_pages(vm); if (reboot_permissions) { TEST_ASSERT(!r, "Disabling NX huge pages should succeed if process has reboot permissions"); @@ -248,18 +241,13 @@ int main(int argc, char **argv) } } - if (token != MAGIC_TOKEN) { - print_skip("This test must be run with the magic token %d.\n" - "This is done by nx_huge_pages_test.sh, which\n" - "also handles environment setup for the test.", - MAGIC_TOKEN); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_has_cap(KVM_CAP_VM_DISABLE_NX_HUGE_PAGES)); + TEST_REQUIRE(reclaim_period_ms > 0); - if (!reclaim_period_ms) { - print_skip("The NX reclaim period must be specified and non-zero"); - exit(KSFT_SKIP); - } + __TEST_REQUIRE(token == MAGIC_TOKEN, + "This test must be run with the magic token %d.\n" + "This is done by nx_huge_pages_test.sh, which\n" + "also handles environment setup for the test."); run_test(reclaim_period_ms, false, reboot_permissions); run_test(reclaim_period_ms, true, reboot_permissions); diff --git a/tools/testing/selftests/powerpc/benchmarks/gettimeofday.c b/tools/testing/selftests/powerpc/benchmarks/gettimeofday.c index 6b415683357b..580fcac0a09f 100644 --- a/tools/testing/selftests/powerpc/benchmarks/gettimeofday.c +++ b/tools/testing/selftests/powerpc/benchmarks/gettimeofday.c @@ -12,7 +12,7 @@ static int test_gettimeofday(void) { int i; - struct timeval tv_start, tv_end; + struct timeval tv_start, tv_end, tv_diff; gettimeofday(&tv_start, NULL); @@ -20,7 +20,9 @@ static int test_gettimeofday(void) gettimeofday(&tv_end, NULL); } - printf("time = %.6f\n", tv_end.tv_sec - tv_start.tv_sec + (tv_end.tv_usec - tv_start.tv_usec) * 1e-6); + timersub(&tv_start, &tv_end, &tv_diff); + + printf("time = %.6f\n", tv_diff.tv_sec + (tv_diff.tv_usec) * 1e-6); return 0; } diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile index 27dc09d0bfee..19dd0b2ea397 100644 --- a/tools/testing/selftests/powerpc/mm/Makefile +++ b/tools/testing/selftests/powerpc/mm/Makefile @@ -3,7 +3,7 @@ noarg: $(MAKE) -C ../ TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao segv_errors wild_bctr \ - large_vm_fork_separation bad_accesses pkey_exec_prot \ + large_vm_fork_separation bad_accesses exec_prot pkey_exec_prot \ pkey_siginfo stack_expansion_signal stack_expansion_ldst \ large_vm_gpr_corruption TEST_PROGS := stress_code_patching.sh @@ -22,6 +22,7 @@ $(OUTPUT)/wild_bctr: CFLAGS += -m64 $(OUTPUT)/large_vm_fork_separation: CFLAGS += -m64 $(OUTPUT)/large_vm_gpr_corruption: CFLAGS += -m64 $(OUTPUT)/bad_accesses: CFLAGS += -m64 +$(OUTPUT)/exec_prot: CFLAGS += -m64 $(OUTPUT)/pkey_exec_prot: CFLAGS += -m64 $(OUTPUT)/pkey_siginfo: CFLAGS += -m64 diff --git a/tools/testing/selftests/powerpc/mm/exec_prot.c b/tools/testing/selftests/powerpc/mm/exec_prot.c new file mode 100644 index 000000000000..db75b2225de1 --- /dev/null +++ b/tools/testing/selftests/powerpc/mm/exec_prot.c @@ -0,0 +1,231 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright 2022, Nicholas Miehlbradt, IBM Corporation + * based on pkey_exec_prot.c + * + * Test if applying execute protection on pages works as expected. + */ + +#define _GNU_SOURCE +#include +#include +#include +#include + +#include +#include + +#include "pkeys.h" + + +#define PPC_INST_NOP 0x60000000 +#define PPC_INST_TRAP 0x7fe00008 +#define PPC_INST_BLR 0x4e800020 + +static volatile sig_atomic_t fault_code; +static volatile sig_atomic_t remaining_faults; +static volatile unsigned int *fault_addr; +static unsigned long pgsize, numinsns; +static unsigned int *insns; +static bool pkeys_supported; + +static bool is_fault_expected(int fault_code) +{ + if (fault_code == SEGV_ACCERR) + return true; + + /* Assume any pkey error is fine since pkey_exec_prot test covers them */ + if (fault_code == SEGV_PKUERR && pkeys_supported) + return true; + + return false; +} + +static void trap_handler(int signum, siginfo_t *sinfo, void *ctx) +{ + /* Check if this fault originated from the expected address */ + if (sinfo->si_addr != (void *)fault_addr) + sigsafe_err("got a fault for an unexpected address\n"); + + _exit(1); +} + +static void segv_handler(int signum, siginfo_t *sinfo, void *ctx) +{ + fault_code = sinfo->si_code; + + /* Check if this fault originated from the expected address */ + if (sinfo->si_addr != (void *)fault_addr) { + sigsafe_err("got a fault for an unexpected address\n"); + _exit(1); + } + + /* Check if too many faults have occurred for a single test case */ + if (!remaining_faults) { + sigsafe_err("got too many faults for the same address\n"); + _exit(1); + } + + + /* Restore permissions in order to continue */ + if (is_fault_expected(fault_code)) { + if (mprotect(insns, pgsize, PROT_READ | PROT_WRITE | PROT_EXEC)) { + sigsafe_err("failed to set access permissions\n"); + _exit(1); + } + } else { + sigsafe_err("got a fault with an unexpected code\n"); + _exit(1); + } + + remaining_faults--; +} + +static int check_exec_fault(int rights) +{ + /* + * Jump to the executable region. + * + * The first iteration also checks if the overwrite of the + * first instruction word from a trap to a no-op succeeded. + */ + fault_code = -1; + remaining_faults = 0; + if (!(rights & PROT_EXEC)) + remaining_faults = 1; + + FAIL_IF(mprotect(insns, pgsize, rights) != 0); + asm volatile("mtctr %0; bctrl" : : "r"(insns)); + + FAIL_IF(remaining_faults != 0); + if (!(rights & PROT_EXEC)) + FAIL_IF(!is_fault_expected(fault_code)); + + return 0; +} + +static int test(void) +{ + struct sigaction segv_act, trap_act; + int i; + + /* Skip the test if the CPU doesn't support Radix */ + SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_00)); + + /* Check if pkeys are supported */ + pkeys_supported = pkeys_unsupported() == 0; + + /* Setup SIGSEGV handler */ + segv_act.sa_handler = 0; + segv_act.sa_sigaction = segv_handler; + FAIL_IF(sigprocmask(SIG_SETMASK, 0, &segv_act.sa_mask) != 0); + segv_act.sa_flags = SA_SIGINFO; + segv_act.sa_restorer = 0; + FAIL_IF(sigaction(SIGSEGV, &segv_act, NULL) != 0); + + /* Setup SIGTRAP handler */ + trap_act.sa_handler = 0; + trap_act.sa_sigaction = trap_handler; + FAIL_IF(sigprocmask(SIG_SETMASK, 0, &trap_act.sa_mask) != 0); + trap_act.sa_flags = SA_SIGINFO; + trap_act.sa_restorer = 0; + FAIL_IF(sigaction(SIGTRAP, &trap_act, NULL) != 0); + + /* Setup executable region */ + pgsize = getpagesize(); + numinsns = pgsize / sizeof(unsigned int); + insns = (unsigned int *)mmap(NULL, pgsize, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + FAIL_IF(insns == MAP_FAILED); + + /* Write the instruction words */ + for (i = 1; i < numinsns - 1; i++) + insns[i] = PPC_INST_NOP; + + /* + * Set the first instruction as an unconditional trap. If + * the last write to this address succeeds, this should + * get overwritten by a no-op. + */ + insns[0] = PPC_INST_TRAP; + + /* + * Later, to jump to the executable region, we use a branch + * and link instruction (bctrl) which sets the return address + * automatically in LR. Use that to return back. + */ + insns[numinsns - 1] = PPC_INST_BLR; + + /* + * Pick the first instruction's address from the executable + * region. + */ + fault_addr = insns; + + /* + * Read an instruction word from the address when the page + * is execute only. This should generate an access fault. + */ + fault_code = -1; + remaining_faults = 1; + printf("Testing read on --x, should fault..."); + FAIL_IF(mprotect(insns, pgsize, PROT_EXEC) != 0); + i = *fault_addr; + FAIL_IF(remaining_faults != 0 || !is_fault_expected(fault_code)); + printf("ok!\n"); + + /* + * Write an instruction word to the address when the page + * execute only. This should also generate an access fault. + */ + fault_code = -1; + remaining_faults = 1; + printf("Testing write on --x, should fault..."); + FAIL_IF(mprotect(insns, pgsize, PROT_EXEC) != 0); + *fault_addr = PPC_INST_NOP; + FAIL_IF(remaining_faults != 0 || !is_fault_expected(fault_code)); + printf("ok!\n"); + + printf("Testing exec on ---, should fault..."); + FAIL_IF(check_exec_fault(PROT_NONE)); + printf("ok!\n"); + + printf("Testing exec on r--, should fault..."); + FAIL_IF(check_exec_fault(PROT_READ)); + printf("ok!\n"); + + printf("Testing exec on -w-, should fault..."); + FAIL_IF(check_exec_fault(PROT_WRITE)); + printf("ok!\n"); + + printf("Testing exec on rw-, should fault..."); + FAIL_IF(check_exec_fault(PROT_READ | PROT_WRITE)); + printf("ok!\n"); + + printf("Testing exec on --x, should succeed..."); + FAIL_IF(check_exec_fault(PROT_EXEC)); + printf("ok!\n"); + + printf("Testing exec on r-x, should succeed..."); + FAIL_IF(check_exec_fault(PROT_READ | PROT_EXEC)); + printf("ok!\n"); + + printf("Testing exec on -wx, should succeed..."); + FAIL_IF(check_exec_fault(PROT_WRITE | PROT_EXEC)); + printf("ok!\n"); + + printf("Testing exec on rwx, should succeed..."); + FAIL_IF(check_exec_fault(PROT_READ | PROT_WRITE | PROT_EXEC)); + printf("ok!\n"); + + /* Cleanup */ + FAIL_IF(munmap((void *)insns, pgsize)); + + return 0; +} + +int main(void) +{ + return test_harness(test, "exec_prot"); +} diff --git a/tools/testing/selftests/powerpc/mm/large_vm_gpr_corruption.c b/tools/testing/selftests/powerpc/mm/large_vm_gpr_corruption.c index 927bfae99ed9..7da515f1da72 100644 --- a/tools/testing/selftests/powerpc/mm/large_vm_gpr_corruption.c +++ b/tools/testing/selftests/powerpc/mm/large_vm_gpr_corruption.c @@ -112,6 +112,8 @@ static int test(void) // This tests a hash MMU specific bug. FAIL_IF(using_hash_mmu(&hash_mmu)); SKIP_IF(!hash_mmu); + // 4K kernels don't support 4PB address space + SKIP_IF(sysconf(_SC_PAGESIZE) < 65536); page_size = sysconf(_SC_PAGESIZE); diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/bhrb_filter_map_test.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/bhrb_filter_map_test.c index 8182647c63c8..3f43c315c666 100644 --- a/tools/testing/selftests/powerpc/pmu/sampling_tests/bhrb_filter_map_test.c +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/bhrb_filter_map_test.c @@ -96,6 +96,15 @@ static int bhrb_filter_map_test(void) } } + /* + * Combine filter maps which includes a valid branch filter and an invalid branch + * filter. Example: any ( PERF_SAMPLE_BRANCH_ANY) and any_call + * (PERF_SAMPLE_BRANCH_ANY_CALL). + * The perf_event_open should fail in this case. + */ + event.attr.branch_sample_type = PERF_SAMPLE_BRANCH_ANY | PERF_SAMPLE_BRANCH_ANY_CALL; + FAIL_IF(!event_open(&event)); + return 0; } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 584a5bab3af3..26383e63d9dd 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3409,10 +3409,8 @@ static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu) int ret = -EINTR; int idx = srcu_read_lock(&vcpu->kvm->srcu); - if (kvm_arch_vcpu_runnable(vcpu)) { - kvm_make_request(KVM_REQ_UNHALT, vcpu); + if (kvm_arch_vcpu_runnable(vcpu)) goto out; - } if (kvm_cpu_has_pending_timer(vcpu)) goto out; if (signal_pending(current)) @@ -5881,7 +5879,7 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, r = kvm_async_pf_init(); if (r) - goto out_free_5; + goto out_free_4; kvm_chardev_ops.owner = module; @@ -5905,10 +5903,9 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, out_unreg: kvm_async_pf_deinit(); -out_free_5: +out_free_4: for_each_possible_cpu(cpu) free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); -out_free_4: kmem_cache_destroy(kvm_vcpu_cache); out_free_3: unregister_reboot_notifier(&kvm_reboot_notifier);