From 5a169bf04cd2bfdbac967d12eb5b70915b29d7ee Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Mon, 19 Oct 2020 15:55:56 +0100 Subject: x86/kvm: Reserve KVM_FEATURE_MSI_EXT_DEST_ID No functional change; just reserve the feature bit for now so that VMMs can start to implement it. This will allow the host to indicate that MSI emulation supports 15-bit destination IDs, allowing up to 32768 CPUs without interrupt remapping. cf. https://patchwork.kernel.org/patch/11816693/ for qemu Signed-off-by: David Woodhouse Acked-by: Paolo Bonzini Message-Id: <4cd59bed05f4b7410d3d1ffd1e997ab53683874d.camel@infradead.org> Signed-off-by: Paolo Bonzini --- arch/x86/include/uapi/asm/kvm_para.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 812e9b4c1114..950afebfba88 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -32,6 +32,7 @@ #define KVM_FEATURE_POLL_CONTROL 12 #define KVM_FEATURE_PV_SCHED_YIELD 13 #define KVM_FEATURE_ASYNC_PF_INT 14 +#define KVM_FEATURE_MSI_EXT_DEST_ID 15 #define KVM_HINTS_REALTIME 0 -- cgit v1.2.3 From cadbaa039b99a6d5c26ce1c7f2fc0325943e605a Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Wed, 28 Oct 2020 12:42:47 -0700 Subject: perf/x86/intel: Make anythread filter support conditional Starting with Arch Perfmon v5, the anythread filter on generic counters may be deprecated. The current kernel was exporting the any filter without checking. On Icelake, it means you could do cpu/event=0x3c,any/ even though the filter does not exist. This patch corrects the problem by relying on the CPUID 0xa leaf function to determine if anythread is supported or not as described in the Intel SDM Vol3b 18.2.5.1 AnyThread Deprecation section. Signed-off-by: Stephane Eranian Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20201028194247.3160610-1-eranian@google.com --- arch/x86/events/intel/core.c | 10 ++++++++++ arch/x86/events/perf_event.h | 1 + arch/x86/include/asm/perf_event.h | 4 +++- arch/x86/kvm/cpuid.c | 4 +++- 4 files changed, 17 insertions(+), 2 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index c37387c8212a..af457f8cb29d 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4987,6 +4987,12 @@ __init int intel_pmu_init(void) x86_add_quirk(intel_arch_events_quirk); /* Install first, so it runs last */ + if (version >= 5) { + x86_pmu.intel_cap.anythread_deprecated = edx.split.anythread_deprecated; + if (x86_pmu.intel_cap.anythread_deprecated) + pr_cont(" AnyThread deprecated, "); + } + /* * Install the hw-cache-events table: */ @@ -5512,6 +5518,10 @@ __init int intel_pmu_init(void) x86_pmu.intel_ctrl |= ((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED; + /* AnyThread may be deprecated on arch perfmon v5 or later */ + if (x86_pmu.intel_cap.anythread_deprecated) + x86_pmu.format_attrs = intel_arch_formats_attr; + if (x86_pmu.event_constraints) { /* * event on fixed counter2 (REF_CYCLES) only works on this diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 1d1fe46552ba..6a8edfe59b09 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -585,6 +585,7 @@ union perf_capabilities { u64 pebs_baseline:1; u64 perf_metrics:1; u64 pebs_output_pt_available:1; + u64 anythread_deprecated:1; }; u64 capabilities; }; diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 6960cd6d1f23..b9a7fd0a27e2 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -137,7 +137,9 @@ union cpuid10_edx { struct { unsigned int num_counters_fixed:5; unsigned int bit_width_fixed:8; - unsigned int reserved:19; + unsigned int reserved1:2; + unsigned int anythread_deprecated:1; + unsigned int reserved2:16; } split; unsigned int full; }; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 06a278b3701d..0752dec66e29 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -672,7 +672,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) edx.split.num_counters_fixed = min(cap.num_counters_fixed, MAX_FIXED_COUNTERS); edx.split.bit_width_fixed = cap.bit_width_fixed; - edx.split.reserved = 0; + edx.split.anythread_deprecated = 1; + edx.split.reserved1 = 0; + edx.split.reserved2 = 0; entry->eax = eax.full; entry->ebx = cap.events_mask; -- cgit v1.2.3 From b2896458b850ec7cb69b054b195b4b399f7e1f22 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Mon, 9 Nov 2020 10:36:53 +0100 Subject: x86/platform/uv: Drop last traces of uv_flush_tlb_others Commit 39297dde7390 ("x86/platform/uv: Remove UV BAU TLB Shootdown Handler") removed uv_flush_tlb_others. Its declaration was removed also from asm/uv/uv.h. But only for the CONFIG_X86_UV=y case. The inline definition (!X86_UV case) is still in place. So remove this implementation with everything what was added to support uv_flush_tlb_others: * include of asm/tlbflush.h * forward declarations of struct cpumask, mm_struct, and flush_tlb_info Signed-off-by: Jiri Slaby Signed-off-by: Thomas Gleixner Acked-by: Mike Travis Acked-by: Steve Wahl Link: https://lore.kernel.org/r/20201109093653.2042-1-jslaby@suse.cz --- arch/x86/include/asm/uv/uv.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h index 172d3e4a9e4b..648eb23fe7f0 100644 --- a/arch/x86/include/asm/uv/uv.h +++ b/arch/x86/include/asm/uv/uv.h @@ -2,14 +2,8 @@ #ifndef _ASM_X86_UV_UV_H #define _ASM_X86_UV_UV_H -#include - enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC}; -struct cpumask; -struct mm_struct; -struct flush_tlb_info; - #ifdef CONFIG_X86_UV #include @@ -44,10 +38,6 @@ static inline int is_uv_system(void) { return 0; } static inline int is_uv_hubbed(int uv) { return 0; } static inline void uv_cpu_init(void) { } static inline void uv_system_init(void) { } -static inline const struct cpumask * -uv_flush_tlb_others(const struct cpumask *cpumask, - const struct flush_tlb_info *info) -{ return cpumask; } #endif /* X86_UV */ -- cgit v1.2.3 From 0107973a80adad5b73232d3fbcd26f710ab1f851 Mon Sep 17 00:00:00 2001 From: Babu Moger Date: Thu, 12 Nov 2020 16:17:56 -0600 Subject: KVM: x86: Introduce cr3_lm_rsvd_bits in kvm_vcpu_arch SEV guests fail to boot on a system that supports the PCID feature. While emulating the RSM instruction, KVM reads the guest CR3 and calls kvm_set_cr3(). If the vCPU is in the long mode, kvm_set_cr3() does a sanity check for the CR3 value. In this case, it validates whether the value has any reserved bits set. The reserved bit range is 63:cpuid_maxphysaddr(). When AMD memory encryption is enabled, the memory encryption bit is set in the CR3 value. The memory encryption bit may fall within the KVM reserved bit range, causing the KVM emulation failure. Introduce a new field cr3_lm_rsvd_bits in kvm_vcpu_arch which will cache the reserved bits in the CR3 value. This will be initialized to rsvd_bits(cpuid_maxphyaddr(vcpu), 63). If the architecture has any special bits(like AMD SEV encryption bit) that needs to be masked from the reserved bits, should be cleared in vendor specific kvm_x86_ops.vcpu_after_set_cpuid handler. Fixes: a780a3ea628268b2 ("KVM: X86: Fix reserved bits check for MOV to CR3") Signed-off-by: Babu Moger Message-Id: <160521947657.32054.3264016688005356563.stgit@bmoger-ubuntu> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/cpuid.c | 2 ++ arch/x86/kvm/x86.c | 2 +- 3 files changed, 4 insertions(+), 1 deletion(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index d44858b69353..324ddd7fd0aa 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -639,6 +639,7 @@ struct kvm_vcpu_arch { int cpuid_nent; struct kvm_cpuid_entry2 *cpuid_entries; + unsigned long cr3_lm_rsvd_bits; int maxphyaddr; int max_tdp_level; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index d50041f570e8..f87b5dfbaba4 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -178,6 +178,8 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vcpu->arch.cr4_guest_rsvd_bits = __cr4_reserved_bits(guest_cpuid_has, vcpu); + vcpu->arch.cr3_lm_rsvd_bits = rsvd_bits(cpuid_maxphyaddr(vcpu), 63); + /* Invoke the vendor callback only after the above state is updated. */ kvm_x86_ops.vcpu_after_set_cpuid(vcpu); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 447edc0d1d5a..078a39d489fe 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1041,7 +1041,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) } if (is_long_mode(vcpu) && - (cr3 & rsvd_bits(cpuid_maxphyaddr(vcpu), 63))) + (cr3 & vcpu->arch.cr3_lm_rsvd_bits)) return 1; else if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) -- cgit v1.2.3 From a927bd6ba952d13c52b8b385030943032f659a3e Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Sat, 21 Nov 2020 22:17:05 -0800 Subject: mm: fix phys_to_target_node() and memory_add_physaddr_to_nid() exports The core-mm has a default __weak implementation of phys_to_target_node() to mirror the weak definition of memory_add_physaddr_to_nid(). That symbol is exported for modules. However, while the export in mm/memory_hotplug.c exported the symbol in the configuration cases of: CONFIG_NUMA_KEEP_MEMINFO=y CONFIG_MEMORY_HOTPLUG=y ...and: CONFIG_NUMA_KEEP_MEMINFO=n CONFIG_MEMORY_HOTPLUG=y ...it failed to export the symbol in the case of: CONFIG_NUMA_KEEP_MEMINFO=y CONFIG_MEMORY_HOTPLUG=n Not only is that broken, but Christoph points out that the kernel should not be exporting any __weak symbol, which means that memory_add_physaddr_to_nid() example that phys_to_target_node() copied is broken too. Rework the definition of phys_to_target_node() and memory_add_physaddr_to_nid() to not require weak symbols. Move to the common arch override design-pattern of an asm header defining a symbol to replace the default implementation. The only common header that all memory_add_physaddr_to_nid() producing architectures implement is asm/sparsemem.h. In fact, powerpc already defines its memory_add_physaddr_to_nid() helper in sparsemem.h. Double-down on that observation and define phys_to_target_node() where necessary in asm/sparsemem.h. An alternate consideration that was discarded was to put this override in asm/numa.h, but that entangles with the definition of MAX_NUMNODES relative to the inclusion of linux/nodemask.h, and requires powerpc to grow a new header. The dependency on NUMA_KEEP_MEMINFO for DEV_DAX_HMEM_DEVICES is invalid now that the symbol is properly exported / stubbed in all combinations of CONFIG_NUMA_KEEP_MEMINFO and CONFIG_MEMORY_HOTPLUG. [dan.j.williams@intel.com: v4] Link: https://lkml.kernel.org/r/160461461867.1505359.5301571728749534585.stgit@dwillia2-desk3.amr.corp.intel.com [dan.j.williams@intel.com: powerpc: fix create_section_mapping compile warning] Link: https://lkml.kernel.org/r/160558386174.2948926.2740149041249041764.stgit@dwillia2-desk3.amr.corp.intel.com Fixes: a035b6bf863e ("mm/memory_hotplug: introduce default phys_to_target_node() implementation") Reported-by: Randy Dunlap Reported-by: Thomas Gleixner Reported-by: kernel test robot Reported-by: Christoph Hellwig Signed-off-by: Dan Williams Signed-off-by: Andrew Morton Tested-by: Randy Dunlap Tested-by: Thomas Gleixner Reviewed-by: Thomas Gleixner Reviewed-by: Christoph Hellwig Cc: Joao Martins Cc: Tony Luck Cc: Fenghua Yu Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Vishal Verma Cc: Stephen Rothwell Link: https://lkml.kernel.org/r/160447639846.1133764.7044090803980177548.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds --- arch/ia64/include/asm/sparsemem.h | 6 ++++++ arch/powerpc/include/asm/mmzone.h | 5 +++++ arch/powerpc/include/asm/sparsemem.h | 5 ++--- arch/powerpc/mm/mem.c | 1 + arch/x86/include/asm/sparsemem.h | 10 ++++++++++ arch/x86/mm/numa.c | 2 ++ drivers/dax/Kconfig | 1 - include/linux/memory_hotplug.h | 14 -------------- include/linux/numa.h | 30 +++++++++++++++++++++++++++++- mm/memory_hotplug.c | 18 ------------------ 10 files changed, 55 insertions(+), 37 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/ia64/include/asm/sparsemem.h b/arch/ia64/include/asm/sparsemem.h index 336d0570e1fa..dd8c166ffd7b 100644 --- a/arch/ia64/include/asm/sparsemem.h +++ b/arch/ia64/include/asm/sparsemem.h @@ -18,4 +18,10 @@ #endif #endif /* CONFIG_SPARSEMEM */ + +#ifdef CONFIG_MEMORY_HOTPLUG +int memory_add_physaddr_to_nid(u64 addr); +#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid +#endif + #endif /* _ASM_IA64_SPARSEMEM_H */ diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h index 91c69ff53a8a..6cda76b57c5d 100644 --- a/arch/powerpc/include/asm/mmzone.h +++ b/arch/powerpc/include/asm/mmzone.h @@ -46,5 +46,10 @@ u64 memory_hotplug_max(void); #define __HAVE_ARCH_RESERVED_KERNEL_PAGES #endif +#ifdef CONFIG_MEMORY_HOTPLUG +extern int create_section_mapping(unsigned long start, unsigned long end, + int nid, pgprot_t prot); +#endif + #endif /* __KERNEL__ */ #endif /* _ASM_MMZONE_H_ */ diff --git a/arch/powerpc/include/asm/sparsemem.h b/arch/powerpc/include/asm/sparsemem.h index 1e6fa371cc38..d072866842e4 100644 --- a/arch/powerpc/include/asm/sparsemem.h +++ b/arch/powerpc/include/asm/sparsemem.h @@ -13,9 +13,9 @@ #endif /* CONFIG_SPARSEMEM */ #ifdef CONFIG_MEMORY_HOTPLUG -extern int create_section_mapping(unsigned long start, unsigned long end, - int nid, pgprot_t prot); extern int remove_section_mapping(unsigned long start, unsigned long end); +extern int memory_add_physaddr_to_nid(u64 start); +#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid #ifdef CONFIG_NUMA extern int hot_add_scn_to_nid(unsigned long scn_addr); @@ -26,6 +26,5 @@ static inline int hot_add_scn_to_nid(unsigned long scn_addr) } #endif /* CONFIG_NUMA */ #endif /* CONFIG_MEMORY_HOTPLUG */ - #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_SPARSEMEM_H */ diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 01ec2a252f09..3fc325bebe4d 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -50,6 +50,7 @@ #include #include #include +#include #include diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h index 6bfc878f6771..6a9ccc1b2be5 100644 --- a/arch/x86/include/asm/sparsemem.h +++ b/arch/x86/include/asm/sparsemem.h @@ -28,4 +28,14 @@ #endif #endif /* CONFIG_SPARSEMEM */ + +#ifndef __ASSEMBLY__ +#ifdef CONFIG_NUMA_KEEP_MEMINFO +extern int phys_to_target_node(phys_addr_t start); +#define phys_to_target_node phys_to_target_node +extern int memory_add_physaddr_to_nid(u64 start); +#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid +#endif +#endif /* __ASSEMBLY__ */ + #endif /* _ASM_X86_SPARSEMEM_H */ diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 44148691d78b..5eb4dc2b97da 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -938,6 +938,7 @@ int phys_to_target_node(phys_addr_t start) return meminfo_to_nid(&numa_reserved_meminfo, start); } +EXPORT_SYMBOL_GPL(phys_to_target_node); int memory_add_physaddr_to_nid(u64 start) { @@ -947,4 +948,5 @@ int memory_add_physaddr_to_nid(u64 start) nid = numa_meminfo.blk[0].nid; return nid; } +EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); #endif diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig index 567428e10b7b..d2834c2cfa10 100644 --- a/drivers/dax/Kconfig +++ b/drivers/dax/Kconfig @@ -50,7 +50,6 @@ config DEV_DAX_HMEM Say M if unsure. config DEV_DAX_HMEM_DEVICES - depends on NUMA_KEEP_MEMINFO # for phys_to_target_node() depends on DEV_DAX_HMEM && DAX=y def_bool y diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index d65c6fdc5cfc..551093b74596 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -281,20 +281,6 @@ static inline bool movable_node_is_enabled(void) } #endif /* ! CONFIG_MEMORY_HOTPLUG */ -#ifdef CONFIG_NUMA -extern int memory_add_physaddr_to_nid(u64 start); -extern int phys_to_target_node(u64 start); -#else -static inline int memory_add_physaddr_to_nid(u64 start) -{ - return 0; -} -static inline int phys_to_target_node(u64 start) -{ - return 0; -} -#endif - #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT) /* * pgdat resizing functions diff --git a/include/linux/numa.h b/include/linux/numa.h index 8cb33ccfb671..cb44cfe2b725 100644 --- a/include/linux/numa.h +++ b/include/linux/numa.h @@ -21,13 +21,41 @@ #endif #ifdef CONFIG_NUMA +#include +#include + /* Generic implementation available */ int numa_map_to_online_node(int node); -#else + +#ifndef memory_add_physaddr_to_nid +static inline int memory_add_physaddr_to_nid(u64 start) +{ + pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n", + start); + return 0; +} +#endif +#ifndef phys_to_target_node +static inline int phys_to_target_node(u64 start) +{ + pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n", + start); + return 0; +} +#endif +#else /* !CONFIG_NUMA */ static inline int numa_map_to_online_node(int node) { return NUMA_NO_NODE; } +static inline int memory_add_physaddr_to_nid(u64 start) +{ + return 0; +} +static inline int phys_to_target_node(u64 start) +{ + return 0; +} #endif #endif /* _LINUX_NUMA_H */ diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index b44d4c7ba73b..63b2e46b6555 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -350,24 +350,6 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages, return err; } -#ifdef CONFIG_NUMA -int __weak memory_add_physaddr_to_nid(u64 start) -{ - pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n", - start); - return 0; -} -EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); - -int __weak phys_to_target_node(u64 start) -{ - pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n", - start); - return 0; -} -EXPORT_SYMBOL_GPL(phys_to_target_node); -#endif - /* find the smallest valid pfn in the range [start_pfn, end_pfn) */ static unsigned long find_smallest_section_pfn(int nid, struct zone *zone, unsigned long start_pfn, -- cgit v1.2.3 From 58c644ba512cfbc2e39b758dd979edd1d6d00e27 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 20 Nov 2020 11:50:35 +0100 Subject: sched/idle: Fix arch_cpu_idle() vs tracing We call arch_cpu_idle() with RCU disabled, but then use local_irq_{en,dis}able(), which invokes tracing, which relies on RCU. Switch all arch_cpu_idle() implementations to use raw_local_irq_{en,dis}able() and carefully manage the lockdep,rcu,tracing state like we do in entry. (XXX: we really should change arch_cpu_idle() to not return with interrupts enabled) Reported-by: Sven Schnelle Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Mark Rutland Tested-by: Mark Rutland Link: https://lkml.kernel.org/r/20201120114925.594122626@infradead.org --- arch/alpha/kernel/process.c | 2 +- arch/arm/kernel/process.c | 2 +- arch/arm64/kernel/process.c | 2 +- arch/csky/kernel/process.c | 2 +- arch/h8300/kernel/process.c | 2 +- arch/hexagon/kernel/process.c | 2 +- arch/ia64/kernel/process.c | 2 +- arch/microblaze/kernel/process.c | 2 +- arch/mips/kernel/idle.c | 12 ++++++------ arch/nios2/kernel/process.c | 2 +- arch/openrisc/kernel/process.c | 2 +- arch/parisc/kernel/process.c | 2 +- arch/powerpc/kernel/idle.c | 4 ++-- arch/riscv/kernel/process.c | 2 +- arch/s390/kernel/idle.c | 6 +++--- arch/sh/kernel/idle.c | 2 +- arch/sparc/kernel/leon_pmc.c | 4 ++-- arch/sparc/kernel/process_32.c | 2 +- arch/sparc/kernel/process_64.c | 4 ++-- arch/um/kernel/process.c | 2 +- arch/x86/include/asm/mwait.h | 2 -- arch/x86/kernel/process.c | 12 +++++++----- kernel/sched/idle.c | 28 +++++++++++++++++++++++++++- 23 files changed, 64 insertions(+), 38 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index 7462a7911002..4c7b0414a3ff 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -57,7 +57,7 @@ EXPORT_SYMBOL(pm_power_off); void arch_cpu_idle(void) { wtint(0); - local_irq_enable(); + raw_local_irq_enable(); } void arch_cpu_idle_dead(void) diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 8e6ace03e960..9f199b1e8383 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -71,7 +71,7 @@ void arch_cpu_idle(void) arm_pm_idle(); else cpu_do_idle(); - local_irq_enable(); + raw_local_irq_enable(); } void arch_cpu_idle_prepare(void) diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 4784011cecac..9ebe02574127 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -126,7 +126,7 @@ void arch_cpu_idle(void) * tricks */ cpu_do_idle(); - local_irq_enable(); + raw_local_irq_enable(); } #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/csky/kernel/process.c b/arch/csky/kernel/process.c index f730869e21ee..69af6bc87e64 100644 --- a/arch/csky/kernel/process.c +++ b/arch/csky/kernel/process.c @@ -102,6 +102,6 @@ void arch_cpu_idle(void) #ifdef CONFIG_CPU_PM_STOP asm volatile("stop\n"); #endif - local_irq_enable(); + raw_local_irq_enable(); } #endif diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c index aea0a40b77a9..bc1364db58fe 100644 --- a/arch/h8300/kernel/process.c +++ b/arch/h8300/kernel/process.c @@ -57,7 +57,7 @@ asmlinkage void ret_from_kernel_thread(void); */ void arch_cpu_idle(void) { - local_irq_enable(); + raw_local_irq_enable(); __asm__("sleep"); } diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c index 5a0a95d93ddb..67767c5ed98c 100644 --- a/arch/hexagon/kernel/process.c +++ b/arch/hexagon/kernel/process.c @@ -44,7 +44,7 @@ void arch_cpu_idle(void) { __vmwait(); /* interrupts wake us up, but irqs are still disabled */ - local_irq_enable(); + raw_local_irq_enable(); } /* diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index 6b61a703bcf5..c9ff8796b509 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -239,7 +239,7 @@ void arch_cpu_idle(void) if (mark_idle) (*mark_idle)(1); - safe_halt(); + raw_safe_halt(); if (mark_idle) (*mark_idle)(0); diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c index a9e46e525cd0..f99860771ff4 100644 --- a/arch/microblaze/kernel/process.c +++ b/arch/microblaze/kernel/process.c @@ -149,5 +149,5 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpregs) void arch_cpu_idle(void) { - local_irq_enable(); + raw_local_irq_enable(); } diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c index 5bc3b04693c7..18e69ebf5691 100644 --- a/arch/mips/kernel/idle.c +++ b/arch/mips/kernel/idle.c @@ -33,19 +33,19 @@ static void __cpuidle r3081_wait(void) { unsigned long cfg = read_c0_conf(); write_c0_conf(cfg | R30XX_CONF_HALT); - local_irq_enable(); + raw_local_irq_enable(); } static void __cpuidle r39xx_wait(void) { if (!need_resched()) write_c0_conf(read_c0_conf() | TX39_CONF_HALT); - local_irq_enable(); + raw_local_irq_enable(); } void __cpuidle r4k_wait(void) { - local_irq_enable(); + raw_local_irq_enable(); __r4k_wait(); } @@ -64,7 +64,7 @@ void __cpuidle r4k_wait_irqoff(void) " .set arch=r4000 \n" " wait \n" " .set pop \n"); - local_irq_enable(); + raw_local_irq_enable(); } /* @@ -84,7 +84,7 @@ static void __cpuidle rm7k_wait_irqoff(void) " wait \n" " mtc0 $1, $12 # stalls until W stage \n" " .set pop \n"); - local_irq_enable(); + raw_local_irq_enable(); } /* @@ -257,7 +257,7 @@ void arch_cpu_idle(void) if (cpu_wait) cpu_wait(); else - local_irq_enable(); + raw_local_irq_enable(); } #ifdef CONFIG_CPU_IDLE diff --git a/arch/nios2/kernel/process.c b/arch/nios2/kernel/process.c index 4ffe857e6ada..50b4eb19a6cc 100644 --- a/arch/nios2/kernel/process.c +++ b/arch/nios2/kernel/process.c @@ -33,7 +33,7 @@ EXPORT_SYMBOL(pm_power_off); void arch_cpu_idle(void) { - local_irq_enable(); + raw_local_irq_enable(); } /* diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c index 0ff391f00334..3c98728cce24 100644 --- a/arch/openrisc/kernel/process.c +++ b/arch/openrisc/kernel/process.c @@ -79,7 +79,7 @@ void machine_power_off(void) */ void arch_cpu_idle(void) { - local_irq_enable(); + raw_local_irq_enable(); if (mfspr(SPR_UPR) & SPR_UPR_PMP) mtspr(SPR_PMR, mfspr(SPR_PMR) | SPR_PMR_DME); } diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index f196d96e2f9f..a92a23d6acd9 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -169,7 +169,7 @@ void __cpuidle arch_cpu_idle_dead(void) void __cpuidle arch_cpu_idle(void) { - local_irq_enable(); + raw_local_irq_enable(); /* nop on real hardware, qemu will idle sleep. */ asm volatile("or %%r10,%%r10,%%r10\n":::); diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index ae0e2632393d..1f835539fda4 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -52,9 +52,9 @@ void arch_cpu_idle(void) * interrupts enabled, some don't. */ if (irqs_disabled()) - local_irq_enable(); + raw_local_irq_enable(); } else { - local_irq_enable(); + raw_local_irq_enable(); /* * Go into low thread priority and possibly * low power mode. diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 19225ec65db6..dd5f985b1f40 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -36,7 +36,7 @@ extern asmlinkage void ret_from_kernel_thread(void); void arch_cpu_idle(void) { wait_for_interrupt(); - local_irq_enable(); + raw_local_irq_enable(); } void show_regs(struct pt_regs *regs) diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c index f7f1e64e0d98..2b85096964f8 100644 --- a/arch/s390/kernel/idle.c +++ b/arch/s390/kernel/idle.c @@ -33,10 +33,10 @@ void enabled_wait(void) PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; clear_cpu_flag(CIF_NOHZ_DELAY); - local_irq_save(flags); + raw_local_irq_save(flags); /* Call the assembler magic in entry.S */ psw_idle(idle, psw_mask); - local_irq_restore(flags); + raw_local_irq_restore(flags); /* Account time spent with enabled wait psw loaded as idle time. */ raw_write_seqcount_begin(&idle->seqcount); @@ -123,7 +123,7 @@ void arch_cpu_idle_enter(void) void arch_cpu_idle(void) { enabled_wait(); - local_irq_enable(); + raw_local_irq_enable(); } void arch_cpu_idle_exit(void) diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c index 0dc0f52f9bb8..f59814983bd5 100644 --- a/arch/sh/kernel/idle.c +++ b/arch/sh/kernel/idle.c @@ -22,7 +22,7 @@ static void (*sh_idle)(void); void default_idle(void) { set_bl_bit(); - local_irq_enable(); + raw_local_irq_enable(); /* Isn't this racy ? */ cpu_sleep(); clear_bl_bit(); diff --git a/arch/sparc/kernel/leon_pmc.c b/arch/sparc/kernel/leon_pmc.c index 065e2d4b7290..396f46bca52e 100644 --- a/arch/sparc/kernel/leon_pmc.c +++ b/arch/sparc/kernel/leon_pmc.c @@ -50,7 +50,7 @@ static void pmc_leon_idle_fixup(void) register unsigned int address = (unsigned int)leon3_irqctrl_regs; /* Interrupts need to be enabled to not hang the CPU */ - local_irq_enable(); + raw_local_irq_enable(); __asm__ __volatile__ ( "wr %%g0, %%asr19\n" @@ -66,7 +66,7 @@ static void pmc_leon_idle_fixup(void) static void pmc_leon_idle(void) { /* Interrupts need to be enabled to not hang the CPU */ - local_irq_enable(); + raw_local_irq_enable(); /* For systems without power-down, this will be no-op */ __asm__ __volatile__ ("wr %g0, %asr19\n\t"); diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index adfcaeab3ddc..a02363735915 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -74,7 +74,7 @@ void arch_cpu_idle(void) { if (sparc_idle) (*sparc_idle)(); - local_irq_enable(); + raw_local_irq_enable(); } /* XXX cli/sti -> local_irq_xxx here, check this works once SMP is fixed. */ diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index a75093b993f9..6f8c7822fc06 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -62,11 +62,11 @@ void arch_cpu_idle(void) { if (tlb_type != hypervisor) { touch_nmi_watchdog(); - local_irq_enable(); + raw_local_irq_enable(); } else { unsigned long pstate; - local_irq_enable(); + raw_local_irq_enable(); /* The sun4v sleeping code requires that we have PSTATE.IE cleared over * the cpu sleep hypervisor call. diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 3bed09538dd9..9505a7e87396 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -217,7 +217,7 @@ void arch_cpu_idle(void) { cpu_tasks[current_thread_info()->cpu].pid = os_getpid(); um_idle_sleep(); - local_irq_enable(); + raw_local_irq_enable(); } int __cant_sleep(void) { diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index e039a933aca3..29dd27b5a339 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -88,8 +88,6 @@ static inline void __mwaitx(unsigned long eax, unsigned long ebx, static inline void __sti_mwait(unsigned long eax, unsigned long ecx) { - trace_hardirqs_on(); - mds_idle_clear_cpu_buffers(); /* "mwait %eax, %ecx;" */ asm volatile("sti; .byte 0x0f, 0x01, 0xc9;" diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index ba4593a913fa..145a7ac0c19a 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -685,7 +685,7 @@ void arch_cpu_idle(void) */ void __cpuidle default_idle(void) { - safe_halt(); + raw_safe_halt(); } #if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE) EXPORT_SYMBOL(default_idle); @@ -736,6 +736,8 @@ void stop_this_cpu(void *dummy) /* * AMD Erratum 400 aware idle routine. We handle it the same way as C3 power * states (local apic timer and TSC stop). + * + * XXX this function is completely buggered vs RCU and tracing. */ static void amd_e400_idle(void) { @@ -757,9 +759,9 @@ static void amd_e400_idle(void) * The switch back from broadcast mode needs to be called with * interrupts disabled. */ - local_irq_disable(); + raw_local_irq_disable(); tick_broadcast_exit(); - local_irq_enable(); + raw_local_irq_enable(); } /* @@ -801,9 +803,9 @@ static __cpuidle void mwait_idle(void) if (!need_resched()) __sti_mwait(0, 0); else - local_irq_enable(); + raw_local_irq_enable(); } else { - local_irq_enable(); + raw_local_irq_enable(); } __current_clr_polling(); } diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 24d0ee26377d..c6932b8f4467 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -78,7 +78,7 @@ void __weak arch_cpu_idle_dead(void) { } void __weak arch_cpu_idle(void) { cpu_idle_force_poll = 1; - local_irq_enable(); + raw_local_irq_enable(); } /** @@ -94,9 +94,35 @@ void __cpuidle default_idle_call(void) trace_cpu_idle(1, smp_processor_id()); stop_critical_timings(); + + /* + * arch_cpu_idle() is supposed to enable IRQs, however + * we can't do that because of RCU and tracing. + * + * Trace IRQs enable here, then switch off RCU, and have + * arch_cpu_idle() use raw_local_irq_enable(). Note that + * rcu_idle_enter() relies on lockdep IRQ state, so switch that + * last -- this is very similar to the entry code. + */ + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(_THIS_IP_); rcu_idle_enter(); + lockdep_hardirqs_on(_THIS_IP_); + arch_cpu_idle(); + + /* + * OK, so IRQs are enabled here, but RCU needs them disabled to + * turn itself back on.. funny thing is that disabling IRQs + * will cause tracing, which needs RCU. Jump through hoops to + * make it 'work'. + */ + raw_local_irq_disable(); + lockdep_hardirqs_off(_THIS_IP_); rcu_idle_exit(); + lockdep_hardirqs_on(_THIS_IP_); + raw_local_irq_enable(); + start_critical_timings(); trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); } -- cgit v1.2.3 From 71cc849b7093bb83af966c0e60cb11b7f35cd746 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Fri, 27 Nov 2020 09:18:20 +0100 Subject: KVM: x86: Fix split-irqchip vs interrupt injection window request kvm_cpu_accept_dm_intr and kvm_vcpu_ready_for_interrupt_injection are a hodge-podge of conditions, hacked together to get something that more or less works. But what is actually needed is much simpler; in both cases the fundamental question is, do we have a place to stash an interrupt if userspace does KVM_INTERRUPT? In userspace irqchip mode, that is !vcpu->arch.interrupt.injected. Currently kvm_event_needs_reinjection(vcpu) covers it, but it is unnecessarily restrictive. In split irqchip mode it's a bit more complicated, we need to check kvm_apic_accept_pic_intr(vcpu) (the IRQ window exit is basically an INTACK cycle and thus requires ExtINTs not to be masked) as well as !pending_userspace_extint(vcpu). However, there is no need to check kvm_event_needs_reinjection(vcpu), since split irqchip keeps pending ExtINT state separate from event injection state, and checking kvm_cpu_has_interrupt(vcpu) is wrong too since ExtINT has higher priority than APIC interrupts. In fact the latter fixes a bug: when userspace requests an IRQ window vmexit, an interrupt in the local APIC can cause kvm_cpu_has_interrupt() to be true and thus kvm_vcpu_ready_for_interrupt_injection() to return false. When this happens, vcpu_run does not exit to userspace but the interrupt window vmexits keep occurring. The VM loops without any hope of making progress. Once we try to fix these with something like return kvm_arch_interrupt_allowed(vcpu) && - !kvm_cpu_has_interrupt(vcpu) && - !kvm_event_needs_reinjection(vcpu) && - kvm_cpu_accept_dm_intr(vcpu); + (!lapic_in_kernel(vcpu) + ? !vcpu->arch.interrupt.injected + : (kvm_apic_accept_pic_intr(vcpu) + && !pending_userspace_extint(v))); we realize two things. First, thanks to the previous patch the complex conditional can reuse !kvm_cpu_has_extint(vcpu). Second, the interrupt window request in vcpu_enter_guest() bool req_int_win = dm_request_for_irq_injection(vcpu) && kvm_cpu_accept_dm_intr(vcpu); should be kept in sync with kvm_vcpu_ready_for_interrupt_injection(): it is unnecessary to ask the processor for an interrupt window if we would not be able to return to userspace. Therefore, kvm_cpu_accept_dm_intr(vcpu) is basically !kvm_cpu_has_extint(vcpu) ANDed with the existing check for masked ExtINT. It all makes sense: - we can accept an interrupt from userspace if there is a place to stash it (and, for irqchip split, ExtINTs are not masked). Interrupts from userspace _can_ be accepted even if right now EFLAGS.IF=0. - in order to tell userspace we will inject its interrupt ("IRQ window open" i.e. kvm_vcpu_ready_for_interrupt_injection), both KVM and the vCPU need to be ready to accept the interrupt. ... and this is what the patch implements. Reported-by: David Woodhouse Analyzed-by: David Woodhouse Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini Reviewed-by: Nikos Tsironis Reviewed-by: David Woodhouse Tested-by: David Woodhouse --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/irq.c | 2 +- arch/x86/kvm/x86.c | 18 ++++++++++-------- 3 files changed, 12 insertions(+), 9 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 324ddd7fd0aa..7e5f33a0d0e2 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1656,6 +1656,7 @@ int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); +int kvm_cpu_has_extint(struct kvm_vcpu *v); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index ee94671272e3..814698e5b152 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -40,7 +40,7 @@ static int pending_userspace_extint(struct kvm_vcpu *v) * check if there is pending interrupt from * non-APIC source without intack. */ -static int kvm_cpu_has_extint(struct kvm_vcpu *v) +int kvm_cpu_has_extint(struct kvm_vcpu *v) { /* * FIXME: interrupt.injected represents an interrupt whose diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 078a39d489fe..e545a8a613b1 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4051,21 +4051,23 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu) { + /* + * We can accept userspace's request for interrupt injection + * as long as we have a place to store the interrupt number. + * The actual injection will happen when the CPU is able to + * deliver the interrupt. + */ + if (kvm_cpu_has_extint(vcpu)) + return false; + + /* Acknowledging ExtINT does not happen if LINT0 is masked. */ return (!lapic_in_kernel(vcpu) || kvm_apic_accept_pic_intr(vcpu)); } -/* - * if userspace requested an interrupt window, check that the - * interrupt window is open. - * - * No need to exit to userspace if we already have an interrupt queued. - */ static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu) { return kvm_arch_interrupt_allowed(vcpu) && - !kvm_cpu_has_interrupt(vcpu) && - !kvm_event_needs_reinjection(vcpu) && kvm_cpu_accept_dm_intr(vcpu); } -- cgit v1.2.3