From: Thomas Gleixner The Intel PEBS/BTS debug store is a design trainwreck as it expects virtual addresses which must be visible in any execution context. So it is required to make these mappings visible to user space when kernel page table isolation is active. Provide enough room for the buffer mappings in the cpu_entry_area so the buffers are available in the user space visible page tables. At the point where the kernel side entry area is populated there is no buffer available yet, but the kernel PMD must be populated. To achieve this set the entries for these buffers to non present. Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar Cc: Andy Lutomirski Cc: Boris Ostrovsky Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: David Laight Cc: Denys Vlasenko Cc: Eduardo Valentin Cc: Greg KH Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Juergen Gross Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Will Deacon Cc: aliguori@amazon.com Cc: daniel.gruss@iaik.tugraz.at Cc: hughd@google.com Cc: keescook@google.com --- arch/x86/events/intel/ds.c | 5 ++-- arch/x86/events/perf_event.h | 21 +------------------ arch/x86/include/asm/cpu_entry_area.h | 13 ++++++++++++ arch/x86/include/asm/intel_ds.h | 36 ++++++++++++++++++++++++++++++++++ arch/x86/mm/cpu_entry_area.c | 32 ++++++++++++++++++++++++++++++ 5 files changed, 86 insertions(+), 21 deletions(-) --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -8,11 +8,12 @@ #include "../perf_event.h" +/* Waste a full page so it can be mapped into the cpu_entry_area */ +DEFINE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store); + /* The size of a BTS record in bytes: */ #define BTS_RECORD_SIZE 24 -#define BTS_BUFFER_SIZE (PAGE_SIZE << 4) -#define PEBS_BUFFER_SIZE (PAGE_SIZE << 4) #define PEBS_FIXUP_SIZE PAGE_SIZE /* --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -14,6 +14,8 @@ #include +#include + /* To enable MSR tracing please use the generic trace points. */ /* @@ -77,8 +79,6 @@ struct amd_nb { struct event_constraint event_constraints[X86_PMC_IDX_MAX]; }; -/* The maximal number of PEBS events: */ -#define MAX_PEBS_EVENTS 8 #define PEBS_COUNTER_MASK ((1ULL << MAX_PEBS_EVENTS) - 1) /* @@ -95,23 +95,6 @@ struct amd_nb { PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR | \ PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER) -/* - * A debug store configuration. - * - * We only support architectures that use 64bit fields. - */ -struct debug_store { - u64 bts_buffer_base; - u64 bts_index; - u64 bts_absolute_maximum; - u64 bts_interrupt_threshold; - u64 pebs_buffer_base; - u64 pebs_index; - u64 pebs_absolute_maximum; - u64 pebs_interrupt_threshold; - u64 pebs_event_reset[MAX_PEBS_EVENTS]; -}; - #define PEBS_REGS \ (PERF_REG_X86_AX | \ PERF_REG_X86_BX | \ --- a/arch/x86/include/asm/cpu_entry_area.h +++ b/arch/x86/include/asm/cpu_entry_area.h @@ -5,6 +5,7 @@ #include #include +#include /* * cpu_entry_area is a percpu region that contains things needed by the CPU @@ -40,6 +41,18 @@ struct cpu_entry_area { */ char exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]; #endif +#ifdef CONFIG_CPU_SUP_INTEL + /* + * Per CPU debug store for Intel performance monitoring. Wastes a + * full page at the moment. + */ + struct debug_store cpu_debug_store; + /* + * The actual PEBS/BTS buffers must be mapped to user space + * Reserve enough fixmap PTEs. + */ + struct debug_store_buffers cpu_debug_buffers; +#endif }; #define CPU_ENTRY_AREA_SIZE (sizeof(struct cpu_entry_area)) --- /dev/null +++ b/arch/x86/include/asm/intel_ds.h @@ -0,0 +1,36 @@ +#ifndef _ASM_INTEL_DS_H +#define _ASM_INTEL_DS_H + +#include + +#define BTS_BUFFER_SIZE (PAGE_SIZE << 4) +#define PEBS_BUFFER_SIZE (PAGE_SIZE << 4) + +/* The maximal number of PEBS events: */ +#define MAX_PEBS_EVENTS 8 + +/* + * A debug store configuration. + * + * We only support architectures that use 64bit fields. + */ +struct debug_store { + u64 bts_buffer_base; + u64 bts_index; + u64 bts_absolute_maximum; + u64 bts_interrupt_threshold; + u64 pebs_buffer_base; + u64 pebs_index; + u64 pebs_absolute_maximum; + u64 pebs_interrupt_threshold; + u64 pebs_event_reset[MAX_PEBS_EVENTS]; +} __aligned(PAGE_SIZE); + +DECLARE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store); + +struct debug_store_buffers { + char bts_buffer[BTS_BUFFER_SIZE]; + char pebs_buffer[PEBS_BUFFER_SIZE]; +}; + +#endif --- a/arch/x86/mm/cpu_entry_area.c +++ b/arch/x86/mm/cpu_entry_area.c @@ -20,6 +20,16 @@ void cea_set_pte(void *cea_vaddr, phys_a set_pte_vaddr(va, pfn_pte(pa >> PAGE_SHIFT, flags)); } +/* + * Force the population of PMDs for not yet allocated per cpu + * memory like debug store buffers. + */ +static void __init cea_allocate_ptes(void *cea_vaddr, int pages) +{ + for (; pages; pages--, cea_vaddr += PAGE_SIZE) + cea_set_pte(cea_vaddr, 0, PAGE_NONE); +} + static void __init cea_map_percpu_pages(void *cea_vaddr, void *ptr, int pages, pgprot_t prot) { @@ -27,6 +37,27 @@ cea_map_percpu_pages(void *cea_vaddr, vo cea_set_pte(cea_vaddr, per_cpu_ptr_to_phys(ptr), prot); } +static void percpu_setup_debug_store(int cpu) +{ +#ifdef CONFIG_CPU_SUP_INTEL + int npages; + void *cea; + + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return; + + cea = &get_cpu_entry_area(cpu)->cpu_debug_store; + npages = sizeof(struct debug_store) / PAGE_SIZE; + BUILD_BUG_ON(sizeof(struct debug_store) % PAGE_SIZE != 0); + cea_map_percpu_pages(cea, &per_cpu(cpu_debug_store, cpu), npages, + PAGE_KERNEL); + + cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers; + npages = sizeof(struct debug_store_buffers) / PAGE_SIZE; + cea_allocate_ptes(cea, npages); +#endif +} + /* Setup the fixmap mappings only once per-processor */ static void __init setup_cpu_entry_area(int cpu) { @@ -98,6 +129,7 @@ static void __init setup_cpu_entry_area( cea_set_pte(&get_cpu_entry_area(cpu)->entry_trampoline, __pa_symbol(_entry_trampoline), PAGE_KERNEL_RX); #endif + percpu_setup_debug_store(cpu); } static __init void setup_cpu_entry_area_ptes(void)