diff options
Diffstat (limited to 'arch')
47 files changed, 401 insertions, 206 deletions
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h index 0c70eb688a00..2a0739a2350b 100644 --- a/arch/arm/include/asm/io.h +++ b/arch/arm/include/asm/io.h @@ -440,6 +440,9 @@ extern void pci_iounmap(struct pci_dev *dev, void __iomem *addr); #define ARCH_HAS_VALID_PHYS_ADDR_RANGE extern int valid_phys_addr_range(phys_addr_t addr, size_t size); extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size); +extern bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size, + unsigned long flags); +#define arch_memremap_can_ram_remap arch_memremap_can_ram_remap #endif /* diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index aa08bcb72db9..290702328a33 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -493,3 +493,11 @@ void __init early_ioremap_init(void) { early_ioremap_setup(); } + +bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size, + unsigned long flags) +{ + unsigned long pfn = PHYS_PFN(offset); + + return memblock_is_map_memory(pfn); +} diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 7fd836bea7eb..3995652daf81 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -192,4 +192,8 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size); extern int valid_phys_addr_range(phys_addr_t addr, size_t size); extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size); +extern bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size, + unsigned long flags); +#define arch_memremap_can_ram_remap arch_memremap_can_ram_remap + #endif /* __ASM_IO_H */ diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 986837d7ec82..fa7981d0d917 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -75,6 +75,10 @@ obj-$(CONFIG_ARM64_MTE) += mte.o obj-y += vdso-wrap.o obj-$(CONFIG_COMPAT_VDSO) += vdso32-wrap.o +# Force dependency (vdso*-wrap.S includes vdso.so through incbin) +$(obj)/vdso-wrap.o: $(obj)/vdso/vdso.so +$(obj)/vdso32-wrap.o: $(obj)/vdso32/vdso.so + obj-y += probes/ head-y := head.o extra-y += $(head-y) vmlinux.lds diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 4c9b5b4b7a0b..a0f3d0aaa3c5 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -208,6 +208,8 @@ static const struct arm64_cpu_capabilities arm64_repeat_tlbi_list[] = { #ifdef CONFIG_ARM64_ERRATUM_1286807 { ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 0), + /* Kryo4xx Gold (rcpe to rfpe) => (r0p0 to r3p0) */ + ERRATA_MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xe), }, #endif {}, diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index d72c4b4d389c..2cb9cc9e0eff 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -654,7 +654,6 @@ static const struct __ftr_reg_entry { ARM64_FTR_REG(SYS_ID_AA64ISAR0_EL1, ftr_id_aa64isar0), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64ISAR1_EL1, ftr_id_aa64isar1, &id_aa64isar1_override), - ARM64_FTR_REG(SYS_ID_AA64ISAR2_EL1, ftr_id_aa64isar2), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64ISAR2_EL1, ftr_id_aa64isar2, &id_aa64isar2_override), @@ -810,7 +809,7 @@ static void __init sort_ftr_regs(void) * to sys_id for subsequent binary search in get_arm64_ftr_reg() * to work correctly. */ - BUG_ON(arm64_ftr_regs[i].sys_id < arm64_ftr_regs[i - 1].sys_id); + BUG_ON(arm64_ftr_regs[i].sys_id <= arm64_ftr_regs[i - 1].sys_id); } } diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index 172452f79e46..ac1964ebed1e 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -52,9 +52,6 @@ GCOV_PROFILE := n targets += vdso.lds CPPFLAGS_vdso.lds += -P -C -U$(ARCH) -# Force dependency (incbin is bad) -$(obj)/vdso.o : $(obj)/vdso.so - # Link rule for the .so file, .lds has to be first $(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE $(call if_changed,vdsold_and_vdso_check) diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index ed181bedbffc..05ba1aae1b6f 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -131,9 +131,6 @@ obj-vdso := $(c-obj-vdso) $(c-obj-vdso-gettimeofday) $(asm-obj-vdso) targets += vdso.lds CPPFLAGS_vdso.lds += -P -C -U$(ARCH) -# Force dependency (vdso.s includes vdso.so through incbin) -$(obj)/vdso.o: $(obj)/vdso.so - include/generated/vdso32-offsets.h: $(obj)/vdso.so.dbg FORCE $(call if_changed,vdsosym) diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c index b7c81dacabf0..b21f91cd830d 100644 --- a/arch/arm64/mm/ioremap.c +++ b/arch/arm64/mm/ioremap.c @@ -99,3 +99,11 @@ void __init early_ioremap_init(void) { early_ioremap_setup(); } + +bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size, + unsigned long flags) +{ + unsigned long pfn = PHYS_PFN(offset); + + return pfn_is_map_memory(pfn); +} diff --git a/arch/mips/include/asm/timex.h b/arch/mips/include/asm/timex.h index b05bb70a2e46..8026baf46e72 100644 --- a/arch/mips/include/asm/timex.h +++ b/arch/mips/include/asm/timex.h @@ -40,9 +40,9 @@ typedef unsigned int cycles_t; /* - * On R4000/R4400 before version 5.0 an erratum exists such that if the - * cycle counter is read in the exact moment that it is matching the - * compare register, no interrupt will be generated. + * On R4000/R4400 an erratum exists such that if the cycle counter is + * read in the exact moment that it is matching the compare register, + * no interrupt will be generated. * * There is a suggested workaround and also the erratum can't strike if * the compare interrupt isn't being used as the clock source device. @@ -63,7 +63,7 @@ static inline int can_use_mips_counter(unsigned int prid) if (!__builtin_constant_p(cpu_has_counter)) asm volatile("" : "=m" (cpu_data[0].options)); if (likely(cpu_has_counter && - prid >= (PRID_IMP_R4000 | PRID_REV_ENCODE_44(5, 0)))) + prid > (PRID_IMP_R4000 | PRID_REV_ENCODE_44(15, 15)))) return 1; else return 0; diff --git a/arch/mips/kernel/time.c b/arch/mips/kernel/time.c index caa01457dce6..ed339d7979f3 100644 --- a/arch/mips/kernel/time.c +++ b/arch/mips/kernel/time.c @@ -141,15 +141,10 @@ static __init int cpu_has_mfc0_count_bug(void) case CPU_R4400MC: /* * The published errata for the R4400 up to 3.0 say the CPU - * has the mfc0 from count bug. + * has the mfc0 from count bug. This seems the last version + * produced. */ - if ((current_cpu_data.processor_id & 0xff) <= 0x30) - return 1; - - /* - * we assume newer revisions are ok - */ - return 0; + return 1; } return 0; diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 52e550b45692..bd22578859d0 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -38,6 +38,7 @@ config PARISC select ARCH_HAVE_NMI_SAFE_CMPXCHG select GENERIC_SMP_IDLE_THREAD select GENERIC_ARCH_TOPOLOGY if SMP + select GENERIC_CPU_DEVICES if !SMP select GENERIC_LIB_DEVMEM_IS_ALLOWED select SYSCTL_ARCH_UNALIGN_ALLOW select SYSCTL_EXCEPTION_TRACE diff --git a/arch/parisc/configs/generic-32bit_defconfig b/arch/parisc/configs/generic-32bit_defconfig index a5fee10d76ee..8ce0ae370680 100644 --- a/arch/parisc/configs/generic-32bit_defconfig +++ b/arch/parisc/configs/generic-32bit_defconfig @@ -6,6 +6,9 @@ CONFIG_BSD_PROCESS_ACCT=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=16 +CONFIG_CGROUPS=y +CONFIG_NAMESPACES=y +CONFIG_USER_NS=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y CONFIG_PERF_EVENTS=y @@ -47,7 +50,6 @@ CONFIG_PARPORT=y CONFIG_PARPORT_PC=m CONFIG_PARPORT_1284=y CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_CRYPTOLOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=6144 CONFIG_BLK_DEV_SD=y diff --git a/arch/parisc/configs/generic-64bit_defconfig b/arch/parisc/configs/generic-64bit_defconfig index 1b8fd80cbe7f..57501b0aed92 100644 --- a/arch/parisc/configs/generic-64bit_defconfig +++ b/arch/parisc/configs/generic-64bit_defconfig @@ -16,6 +16,7 @@ CONFIG_CGROUPS=y CONFIG_MEMCG=y CONFIG_CGROUP_PIDS=y CONFIG_CPUSETS=y +CONFIG_USER_NS=y CONFIG_RELAY=y CONFIG_BLK_DEV_INITRD=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y @@ -267,9 +268,9 @@ CONFIG_CRYPTO_DEFLATE=m CONFIG_CRC_CCITT=m CONFIG_LIBCRC32C=y CONFIG_PRINTK_TIME=y +CONFIG_DEBUG_KERNEL=y CONFIG_STRIP_ASM_SYMS=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_FS=y -CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_STACKOVERFLOW=y # CONFIG_SCHED_DEBUG is not set diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 939db6fe620b..69765a6dbe89 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -160,7 +160,7 @@ extern void __update_cache(pte_t pte); #define SPACEID_SHIFT (MAX_ADDRBITS - 32) #else #define MAX_ADDRBITS (BITS_PER_LONG) -#define MAX_ADDRESS (1UL << MAX_ADDRBITS) +#define MAX_ADDRESS (1ULL << MAX_ADDRBITS) #define SPACEID_SHIFT 0 #endif diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 23348199f3f8..e7911225a4f8 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -403,7 +403,7 @@ void __init parisc_setup_cache_timing(void) { unsigned long rangetime, alltime; unsigned long size; - unsigned long threshold, threshold2; + unsigned long threshold; alltime = mfctl(16); flush_data_cache(); @@ -418,20 +418,8 @@ void __init parisc_setup_cache_timing(void) alltime, size, rangetime); threshold = L1_CACHE_ALIGN(size * alltime / rangetime); - - /* - * The threshold computed above isn't very reliable since the - * flush times depend greatly on the percentage of dirty lines - * in the flush range. Further, the whole cache time doesn't - * include the time to refill lines that aren't in the mm/vma - * being flushed. By timing glibc build and checks on mako cpus, - * the following formula seems to work reasonably well. The - * value from the timing calculation is too small, and increases - * build and check times by almost a factor two. - */ - threshold2 = cache_info.dc_size * num_online_cpus(); - if (threshold2 > threshold) - threshold = threshold2; + if (threshold > cache_info.dc_size) + threshold = cache_info.dc_size; if (threshold) parisc_cache_flush_threshold = threshold; printk(KERN_INFO "Cache flush threshold set to %lu KiB\n", diff --git a/arch/parisc/kernel/kprobes.c b/arch/parisc/kernel/kprobes.c index 3343d2fb7889..6e0b86652f30 100644 --- a/arch/parisc/kernel/kprobes.c +++ b/arch/parisc/kernel/kprobes.c @@ -152,7 +152,7 @@ int __kprobes parisc_kprobe_ss_handler(struct pt_regs *regs) /* for absolute branch instructions we can copy iaoq_b. for relative * branch instructions we need to calculate the new address based on the * difference between iaoq_f and iaoq_b. We cannot use iaoq_b without - * modificationt because it's based on our ainsn.insn address. + * modifications because it's based on our ainsn.insn address. */ if (p->post_handler) diff --git a/arch/parisc/kernel/patch.c b/arch/parisc/kernel/patch.c index e59574f65e64..80a0ab372802 100644 --- a/arch/parisc/kernel/patch.c +++ b/arch/parisc/kernel/patch.c @@ -40,7 +40,10 @@ static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags, *need_unmap = 1; set_fixmap(fixmap, page_to_phys(page)); - raw_spin_lock_irqsave(&patch_lock, *flags); + if (flags) + raw_spin_lock_irqsave(&patch_lock, *flags); + else + __acquire(&patch_lock); return (void *) (__fix_to_virt(fixmap) + (uintaddr & ~PAGE_MASK)); } @@ -49,7 +52,10 @@ static void __kprobes patch_unmap(int fixmap, unsigned long *flags) { clear_fixmap(fixmap); - raw_spin_unlock_irqrestore(&patch_lock, *flags); + if (flags) + raw_spin_unlock_irqrestore(&patch_lock, *flags); + else + __release(&patch_lock); } void __kprobes __patch_text_multiple(void *addr, u32 *insn, unsigned int len) @@ -61,9 +67,8 @@ void __kprobes __patch_text_multiple(void *addr, u32 *insn, unsigned int len) int mapped; /* Make sure we don't have any aliases in cache */ - flush_kernel_dcache_range_asm(start, end); - flush_kernel_icache_range_asm(start, end); - flush_tlb_kernel_range(start, end); + flush_kernel_vmap_range(addr, len); + flush_icache_range(start, end); p = fixmap = patch_map(addr, FIX_TEXT_POKE0, &flags, &mapped); @@ -76,10 +81,8 @@ void __kprobes __patch_text_multiple(void *addr, u32 *insn, unsigned int len) * We're crossing a page boundary, so * need to remap */ - flush_kernel_dcache_range_asm((unsigned long)fixmap, - (unsigned long)p); - flush_tlb_kernel_range((unsigned long)fixmap, - (unsigned long)p); + flush_kernel_vmap_range((void *)fixmap, + (p-fixmap) * sizeof(*p)); if (mapped) patch_unmap(FIX_TEXT_POKE0, &flags); p = fixmap = patch_map(addr, FIX_TEXT_POKE0, &flags, @@ -87,10 +90,10 @@ void __kprobes __patch_text_multiple(void *addr, u32 *insn, unsigned int len) } } - flush_kernel_dcache_range_asm((unsigned long)fixmap, (unsigned long)p); - flush_tlb_kernel_range((unsigned long)fixmap, (unsigned long)p); + flush_kernel_vmap_range((void *)fixmap, (p-fixmap) * sizeof(*p)); if (mapped) patch_unmap(FIX_TEXT_POKE0, &flags); + flush_icache_range(start, end); } void __kprobes __patch_text(void *addr, u32 insn) diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c index d98692115221..26eb568f8b96 100644 --- a/arch/parisc/kernel/processor.c +++ b/arch/parisc/kernel/processor.c @@ -171,6 +171,7 @@ static int __init processor_probe(struct parisc_device *dev) p->cpu_num = cpu_info.cpu_num; p->cpu_loc = cpu_info.cpu_loc; + set_cpu_possible(cpuid, true); store_cpu_topology(cpuid); #ifdef CONFIG_SMP @@ -419,8 +420,7 @@ show_cpuinfo (struct seq_file *m, void *v) } seq_printf(m, " (0x%02lx)\n", boot_cpu_data.pdc.capabilities); - seq_printf(m, "model\t\t: %s\n" - "model name\t: %s\n", + seq_printf(m, "model\t\t: %s - %s\n", boot_cpu_data.pdc.sys_model_name, cpuinfo->dev ? cpuinfo->dev->name : "Unknown"); @@ -461,6 +461,13 @@ static struct parisc_driver cpu_driver __refdata = { */ void __init processor_init(void) { + unsigned int cpu; + reset_cpu_topology(); + + /* reset possible mask. We will mark those which are possible. */ + for_each_possible_cpu(cpu) + set_cpu_possible(cpu, false); + register_parisc_driver(&cpu_driver); } diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index b91cb45ffd4e..f005ddedb50e 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -161,6 +161,8 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_PA11 dma_ops_init(); #endif + + clear_sched_clock_stable(); } /* diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c index bb27dfeeddfc..9714fbd7c42d 100644 --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -251,13 +251,9 @@ void __init time_init(void) static int __init init_cr16_clocksource(void) { /* - * The cr16 interval timers are not syncronized across CPUs, even if - * they share the same socket. + * The cr16 interval timers are not synchronized across CPUs. */ if (num_online_cpus() > 1 && !running_on_qemu) { - /* mark sched_clock unstable */ - clear_sched_clock_stable(); - clocksource_cr16.name = "cr16_unstable"; clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE; clocksource_cr16.rating = 0; diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index a6e61cf2cad0..b78f1b9d45c1 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -469,7 +469,7 @@ void parisc_terminate(char *msg, struct pt_regs *regs, int code, unsigned long o * panic notifiers, and we should call panic * directly from the location that we wish. * e.g. We should not call panic from - * parisc_terminate, but rather the oter way around. + * parisc_terminate, but rather the other way around. * This hack works, prints the panic message twice, * and it enables reboot timers! */ diff --git a/arch/parisc/math-emu/dfadd.c b/arch/parisc/math-emu/dfadd.c index ec487e07f004..00e561d4aa55 100644 --- a/arch/parisc/math-emu/dfadd.c +++ b/arch/parisc/math-emu/dfadd.c @@ -253,7 +253,7 @@ dbl_fadd( return(NOEXCEPTION); } right_exponent = 1; /* Set exponent to reflect different bias - * with denomalized numbers. */ + * with denormalized numbers. */ } else { diff --git a/arch/parisc/math-emu/dfsub.c b/arch/parisc/math-emu/dfsub.c index c4f30acf2d48..4f03782284bd 100644 --- a/arch/parisc/math-emu/dfsub.c +++ b/arch/parisc/math-emu/dfsub.c @@ -256,7 +256,7 @@ dbl_fsub( return(NOEXCEPTION); } right_exponent = 1; /* Set exponent to reflect different bias - * with denomalized numbers. */ + * with denormalized numbers. */ } else { diff --git a/arch/parisc/math-emu/sfadd.c b/arch/parisc/math-emu/sfadd.c index 838758279d5b..9b98c874dfac 100644 --- a/arch/parisc/math-emu/sfadd.c +++ b/arch/parisc/math-emu/sfadd.c @@ -249,7 +249,7 @@ sgl_fadd( return(NOEXCEPTION); } right_exponent = 1; /* Set exponent to reflect different bias - * with denomalized numbers. */ + * with denormalized numbers. */ } else { diff --git a/arch/parisc/math-emu/sfsub.c b/arch/parisc/math-emu/sfsub.c index 583d3ace4634..29d9eed09d12 100644 --- a/arch/parisc/math-emu/sfsub.c +++ b/arch/parisc/math-emu/sfsub.c @@ -252,7 +252,7 @@ sgl_fsub( return(NOEXCEPTION); } right_exponent = 1; /* Set exponent to reflect different bias - * with denomalized numbers. */ + * with denormalized numbers. */ } else { diff --git a/arch/powerpc/kernel/vdso/gettimeofday.S b/arch/powerpc/kernel/vdso/gettimeofday.S index eb9c81e1c218..0c4ecc8fec5a 100644 --- a/arch/powerpc/kernel/vdso/gettimeofday.S +++ b/arch/powerpc/kernel/vdso/gettimeofday.S @@ -22,12 +22,15 @@ .macro cvdso_call funct call_time=0 .cfi_startproc PPC_STLU r1, -PPC_MIN_STKFRM(r1) + .cfi_adjust_cfa_offset PPC_MIN_STKFRM mflr r0 - .cfi_register lr, r0 PPC_STLU r1, -PPC_MIN_STKFRM(r1) + .cfi_adjust_cfa_offset PPC_MIN_STKFRM PPC_STL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) + .cfi_rel_offset lr, PPC_MIN_STKFRM + PPC_LR_STKOFF #ifdef __powerpc64__ PPC_STL r2, PPC_MIN_STKFRM + STK_GOT(r1) + .cfi_rel_offset r2, PPC_MIN_STKFRM + STK_GOT #endif get_datapage r5 .ifeq \call_time @@ -39,13 +42,15 @@ PPC_LL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) #ifdef __powerpc64__ PPC_LL r2, PPC_MIN_STKFRM + STK_GOT(r1) + .cfi_restore r2 #endif .ifeq \call_time cmpwi r3, 0 .endif mtlr r0 - .cfi_restore lr addi r1, r1, 2 * PPC_MIN_STKFRM + .cfi_restore lr + .cfi_def_cfa_offset 0 crclr so .ifeq \call_time beqlr+ diff --git a/arch/powerpc/kvm/book3s_32_sr.S b/arch/powerpc/kvm/book3s_32_sr.S index e3ab9df6cf19..6cfcd20d4668 100644 --- a/arch/powerpc/kvm/book3s_32_sr.S +++ b/arch/powerpc/kvm/book3s_32_sr.S @@ -122,11 +122,27 @@ /* 0x0 - 0xb */ - /* 'current->mm' needs to be in r4 */ - tophys(r4, r2) - lwz r4, MM(r4) - tophys(r4, r4) - /* This only clobbers r0, r3, r4 and r5 */ + /* switch_mmu_context() needs paging, let's enable it */ + mfmsr r9 + ori r11, r9, MSR_DR + mtmsr r11 + sync + + /* switch_mmu_context() clobbers r12, rescue it */ + SAVE_GPR(12, r1) + + /* Calling switch_mmu_context(<inv>, current->mm, <inv>); */ + lwz r4, MM(r2) bl switch_mmu_context + /* restore r12 */ + REST_GPR(12, r1) + + /* Disable paging again */ + mfmsr r9 + li r6, MSR_DR + andc r9, r9, r6 + mtmsr r9 + sync + .endm diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index f58728d5f10d..39962c905542 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -462,7 +462,6 @@ static int papr_scm_pmu_check_events(struct papr_scm_priv *p, struct nvdimm_pmu { struct papr_scm_perf_stat *stat; struct papr_scm_perf_stats *stats; - char *statid; int index, rc, count; u32 available_events; @@ -493,14 +492,12 @@ static int papr_scm_pmu_check_events(struct papr_scm_priv *p, struct nvdimm_pmu for (index = 0, stat = stats->scm_statistic, count = 0; index < available_events; index++, ++stat) { - statid = kzalloc(strlen(stat->stat_id) + 1, GFP_KERNEL); - if (!statid) { + p->nvdimm_events_map[count] = kmemdup_nul(stat->stat_id, 8, GFP_KERNEL); + if (!p->nvdimm_events_map[count]) { rc = -ENOMEM; goto out_nvdimm_events_map; } - strcpy(statid, stat->stat_id); - p->nvdimm_events_map[count] = statid; count++; } p->nvdimm_events_map[count] = NULL; diff --git a/arch/powerpc/platforms/pseries/vas-sysfs.c b/arch/powerpc/platforms/pseries/vas-sysfs.c index 909535ca513a..ec65586cbeb3 100644 --- a/arch/powerpc/platforms/pseries/vas-sysfs.c +++ b/arch/powerpc/platforms/pseries/vas-sysfs.c @@ -27,22 +27,31 @@ struct vas_caps_entry { /* * This function is used to get the notification from the drmgr when - * QoS credits are changed. Though receiving the target total QoS - * credits here, get the official QoS capabilities from the hypervisor. + * QoS credits are changed. */ -static ssize_t update_total_credits_trigger(struct vas_cop_feat_caps *caps, +static ssize_t update_total_credits_store(struct vas_cop_feat_caps *caps, const char *buf, size_t count) { int err; u16 creds; err = kstrtou16(buf, 0, &creds); + /* + * The user space interface from the management console + * notifies OS with the new QoS credits and then the + * hypervisor. So OS has to use this new credits value + * and reconfigure VAS windows (close or reopen depends + * on the credits available) instead of depending on VAS + * QoS capabilities from the hypervisor. + */ if (!err) - err = vas_reconfig_capabilties(caps->win_type); + err = vas_reconfig_capabilties(caps->win_type, creds); if (err) return -EINVAL; + pr_info("Set QoS total credits %u\n", creds); + return count; } @@ -92,7 +101,7 @@ VAS_ATTR_RO(nr_total_credits); VAS_ATTR_RO(nr_used_credits); static struct vas_sysfs_entry update_total_credits_attribute = - __ATTR(update_total_credits, 0200, NULL, update_total_credits_trigger); + __ATTR(update_total_credits, 0200, NULL, update_total_credits_store); static struct attribute *vas_def_capab_attrs[] = { &nr_total_credits_attribute.attr, diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c index 1f59d78c77a1..ec643bbdb67f 100644 --- a/arch/powerpc/platforms/pseries/vas.c +++ b/arch/powerpc/platforms/pseries/vas.c @@ -779,10 +779,10 @@ static int reconfig_close_windows(struct vas_caps *vcap, int excess_creds, * changes. Reconfig window configurations based on the credits * availability from this new capabilities. */ -int vas_reconfig_capabilties(u8 type) +int vas_reconfig_capabilties(u8 type, int new_nr_creds) { struct vas_cop_feat_caps *caps; - int old_nr_creds, new_nr_creds; + int old_nr_creds; struct vas_caps *vcaps; int rc = 0, nr_active_wins; @@ -795,12 +795,6 @@ int vas_reconfig_capabilties(u8 type) caps = &vcaps->caps; mutex_lock(&vas_pseries_mutex); - rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES, vcaps->feat, - (u64)virt_to_phys(&hv_cop_caps)); - if (rc) - goto out; - - new_nr_creds = be16_to_cpu(hv_cop_caps.target_lpar_creds); old_nr_creds = atomic_read(&caps->nr_total_credits); @@ -832,7 +826,6 @@ int vas_reconfig_capabilties(u8 type) false); } -out: mutex_unlock(&vas_pseries_mutex); return rc; } @@ -850,7 +843,7 @@ static int pseries_vas_notifier(struct notifier_block *nb, struct of_reconfig_data *rd = data; struct device_node *dn = rd->dn; const __be32 *intserv = NULL; - int len, rc = 0; + int new_nr_creds, len, rc = 0; if ((action == OF_RECONFIG_ATTACH_NODE) || (action == OF_RECONFIG_DETACH_NODE)) @@ -862,7 +855,15 @@ static int pseries_vas_notifier(struct notifier_block *nb, if (!intserv) return NOTIFY_OK; - rc = vas_reconfig_capabilties(VAS_GZIP_DEF_FEAT_TYPE); + rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES, + vascaps[VAS_GZIP_DEF_FEAT_TYPE].feat, + (u64)virt_to_phys(&hv_cop_caps)); + if (!rc) { + new_nr_creds = be16_to_cpu(hv_cop_caps.target_lpar_creds); + rc = vas_reconfig_capabilties(VAS_GZIP_DEF_FEAT_TYPE, + new_nr_creds); + } + if (rc) pr_err("Failed reconfig VAS capabilities with DLPAR\n"); diff --git a/arch/powerpc/platforms/pseries/vas.h b/arch/powerpc/platforms/pseries/vas.h index 34177881e998..333ffa2f9f42 100644 --- a/arch/powerpc/platforms/pseries/vas.h +++ b/arch/powerpc/platforms/pseries/vas.h @@ -135,7 +135,7 @@ struct pseries_vas_window { }; int sysfs_add_vas_caps(struct vas_cop_feat_caps *caps); -int vas_reconfig_capabilties(u8 type); +int vas_reconfig_capabilties(u8 type, int new_nr_creds); int __init sysfs_pseries_vas_init(struct vas_all_caps *vas_caps); #ifdef CONFIG_PPC_VAS diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index b0793dc0c291..05ed641a1134 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -208,8 +208,25 @@ static void __init setup_bootmem(void) * early_init_fdt_reserve_self() since __pa() does * not work for DTB pointers that are fixmap addresses */ - if (!IS_ENABLED(CONFIG_BUILTIN_DTB)) - memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va)); + if (!IS_ENABLED(CONFIG_BUILTIN_DTB)) { + /* + * In case the DTB is not located in a memory region we won't + * be able to locate it later on via the linear mapping and + * get a segfault when accessing it via __va(dtb_early_pa). + * To avoid this situation copy DTB to a memory region. + * Note that memblock_phys_alloc will also reserve DTB region. + */ + if (!memblock_is_memory(dtb_early_pa)) { + size_t fdt_size = fdt_totalsize(dtb_early_va); + phys_addr_t new_dtb_early_pa = memblock_phys_alloc(fdt_size, PAGE_SIZE); + void *new_dtb_early_va = early_memremap(new_dtb_early_pa, fdt_size); + + memcpy(new_dtb_early_va, dtb_early_va, fdt_size); + early_memunmap(new_dtb_early_va, fdt_size); + _dtb_early_pa = new_dtb_early_pa; + } else + memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va)); + } early_init_fdt_scan_reserved_mem(); dma_contiguous_reserve(dma32_phys_limit); diff --git a/arch/s390/Makefile b/arch/s390/Makefile index e441b60b1812..df325eacf62d 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -30,6 +30,16 @@ KBUILD_CFLAGS_DECOMPRESSOR += -fno-stack-protector KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-disable-warning, address-of-packed-member) KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),-g) KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO_DWARF4), $(call cc-option, -gdwarf-4,)) + +ifdef CONFIG_CC_IS_GCC + ifeq ($(call cc-ifversion, -ge, 1200, y), y) + ifeq ($(call cc-ifversion, -lt, 1300, y), y) + KBUILD_CFLAGS += $(call cc-disable-warning, array-bounds) + KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-disable-warning, array-bounds) + endif + endif +endif + UTS_MACHINE := s390x STACK_SIZE := $(if $(CONFIG_KASAN),65536,16384) CHECKFLAGS += -D__s390__ -D__s390x__ diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index da3dabda1a12..76ad6408cb2c 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2384,7 +2384,16 @@ static int kvm_s390_vm_mem_op(struct kvm *kvm, struct kvm_s390_mem_op *mop) return -EINVAL; if (mop->size > MEM_OP_MAX_SIZE) return -E2BIG; - if (kvm_s390_pv_is_protected(kvm)) + /* + * This is technically a heuristic only, if the kvm->lock is not + * taken, it is not guaranteed that the vm is/remains non-protected. + * This is ok from a kernel perspective, wrongdoing is detected + * on the access, -EFAULT is returned and the vm may crash the + * next time it accesses the memory in question. + * There is no sane usecase to do switching and a memop on two + * different CPUs at the same time. + */ + if (kvm_s390_pv_get_handle(kvm)) return -EINVAL; if (mop->flags & KVM_S390_MEMOP_F_SKEY_PROTECTION) { if (access_key_invalid(mop->key)) diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index af03cacf34ec..1ac73917a8d3 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -1183,6 +1183,7 @@ EXPORT_SYMBOL_GPL(gmap_read_table); static inline void gmap_insert_rmap(struct gmap *sg, unsigned long vmaddr, struct gmap_rmap *rmap) { + struct gmap_rmap *temp; void __rcu **slot; BUG_ON(!gmap_is_shadow(sg)); @@ -1190,6 +1191,12 @@ static inline void gmap_insert_rmap(struct gmap *sg, unsigned long vmaddr, if (slot) { rmap->next = radix_tree_deref_slot_protected(slot, &sg->guest_table_lock); + for (temp = rmap->next; temp; temp = temp->next) { + if (temp->raddr == rmap->raddr) { + kfree(rmap); + return; + } + } radix_tree_replace_slot(&sg->host_to_rmap, slot, rmap); } else { rmap->next = NULL; diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index c049561f373a..e28ab0ecc537 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -41,17 +41,7 @@ struct fpu_state_config fpu_user_cfg __ro_after_init; */ struct fpstate init_fpstate __ro_after_init; -/* - * Track whether the kernel is using the FPU state - * currently. - * - * This flag is used: - * - * - by IRQ context code to potentially use the FPU - * if it's unused. - * - * - to debug kernel_fpu_begin()/end() correctness - */ +/* Track in-kernel FPU usage */ static DEFINE_PER_CPU(bool, in_kernel_fpu); /* @@ -59,42 +49,37 @@ static DEFINE_PER_CPU(bool, in_kernel_fpu); */ DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); -static bool kernel_fpu_disabled(void) -{ - return this_cpu_read(in_kernel_fpu); -} - -static bool interrupted_kernel_fpu_idle(void) -{ - return !kernel_fpu_disabled(); -} - -/* - * Were we in user mode (or vm86 mode) when we were - * interrupted? - * - * Doing kernel_fpu_begin/end() is ok if we are running - * in an interrupt context from user mode - we'll just - * save the FPU state as required. - */ -static bool interrupted_user_mode(void) -{ - struct pt_regs *regs = get_irq_regs(); - return regs && user_mode(regs); -} - /* * Can we use the FPU in kernel mode with the * whole "kernel_fpu_begin/end()" sequence? - * - * It's always ok in process context (ie "not interrupt") - * but it is sometimes ok even from an irq. */ bool irq_fpu_usable(void) { - return !in_interrupt() || - interrupted_user_mode() || - interrupted_kernel_fpu_idle(); + if (WARN_ON_ONCE(in_nmi())) + return false; + + /* In kernel FPU usage already active? */ + if (this_cpu_read(in_kernel_fpu)) + return false; + + /* + * When not in NMI or hard interrupt context, FPU can be used in: + * + * - Task context except from within fpregs_lock()'ed critical + * regions. + * + * - Soft interrupt processing context which cannot happen + * while in a fpregs_lock()'ed critical region. + */ + if (!in_hardirq()) + return true; + + /* + * In hard interrupt context it's safe when soft interrupts + * are enabled, which means the interrupt did not hit in + * a fpregs_lock()'ed critical region. + */ + return !softirq_count(); } EXPORT_SYMBOL(irq_fpu_usable); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 598334ed5fbc..0c1ba6aa0765 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -887,6 +887,11 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) union cpuid10_eax eax; union cpuid10_edx edx; + if (!static_cpu_has(X86_FEATURE_ARCH_PERFMON)) { + entry->eax = entry->ebx = entry->ecx = entry->edx = 0; + break; + } + perf_get_x86_pmu_capability(&cap); /* diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 64a2a7e2be90..311e4e1d7870 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -473,30 +473,6 @@ retry: } #endif -static bool spte_has_volatile_bits(u64 spte) -{ - if (!is_shadow_present_pte(spte)) - return false; - - /* - * Always atomically update spte if it can be updated - * out of mmu-lock, it can ensure dirty bit is not lost, - * also, it can help us to get a stable is_writable_pte() - * to ensure tlb flush is not missed. - */ - if (spte_can_locklessly_be_made_writable(spte) || - is_access_track_spte(spte)) - return true; - - if (spte_ad_enabled(spte)) { - if ((spte & shadow_accessed_mask) == 0 || - (is_writable_pte(spte) && (spte & shadow_dirty_mask) == 0)) - return true; - } - - return false; -} - /* Rules for using mmu_spte_set: * Set the sptep from nonpresent to present. * Note: the sptep being assigned *must* be either not present @@ -557,7 +533,7 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte) * we always atomically update it, see the comments in * spte_has_volatile_bits(). */ - if (spte_can_locklessly_be_made_writable(old_spte) && + if (is_mmu_writable_spte(old_spte) && !is_writable_pte(new_spte)) flush = true; @@ -591,7 +567,8 @@ static int mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep) u64 old_spte = *sptep; int level = sptep_to_sp(sptep)->role.level; - if (!spte_has_volatile_bits(old_spte)) + if (!is_shadow_present_pte(old_spte) || + !spte_has_volatile_bits(old_spte)) __update_clear_spte_fast(sptep, 0ull); else old_spte = __update_clear_spte_slow(sptep, 0ull); @@ -1187,7 +1164,7 @@ static bool spte_write_protect(u64 *sptep, bool pt_protect) u64 spte = *sptep; if (!is_writable_pte(spte) && - !(pt_protect && spte_can_locklessly_be_made_writable(spte))) + !(pt_protect && is_mmu_writable_spte(spte))) return false; rmap_printk("spte %p %llx\n", sptep, *sptep); @@ -3196,8 +3173,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) * be removed in the fast path only if the SPTE was * write-protected for dirty-logging or access tracking. */ - if (fault->write && - spte_can_locklessly_be_made_writable(spte)) { + if (fault->write && is_mmu_writable_spte(spte)) { new_spte |= PT_WRITABLE_MASK; /* diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index 4739b53c9734..e5c0b6db6f2c 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -90,6 +90,34 @@ static bool kvm_is_mmio_pfn(kvm_pfn_t pfn) E820_TYPE_RAM); } +/* + * Returns true if the SPTE has bits that may be set without holding mmu_lock. + * The caller is responsible for checking if the SPTE is shadow-present, and + * for determining whether or not the caller cares about non-leaf SPTEs. + */ +bool spte_has_volatile_bits(u64 spte) +{ + /* + * Always atomically update spte if it can be updated + * out of mmu-lock, it can ensure dirty bit is not lost, + * also, it can help us to get a stable is_writable_pte() + * to ensure tlb flush is not missed. + */ + if (!is_writable_pte(spte) && is_mmu_writable_spte(spte)) + return true; + + if (is_access_track_spte(spte)) + return true; + + if (spte_ad_enabled(spte)) { + if (!(spte & shadow_accessed_mask) || + (is_writable_pte(spte) && !(spte & shadow_dirty_mask))) + return true; + } + + return false; +} + bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, const struct kvm_memory_slot *slot, unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn, diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index e4abeb5df1b1..80ab0f5cff01 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -390,7 +390,7 @@ static inline void check_spte_writable_invariants(u64 spte) "kvm: Writable SPTE is not MMU-writable: %llx", spte); } -static inline bool spte_can_locklessly_be_made_writable(u64 spte) +static inline bool is_mmu_writable_spte(u64 spte) { return spte & shadow_mmu_writable_mask; } @@ -404,6 +404,8 @@ static inline u64 get_mmio_spte_generation(u64 spte) return gen; } +bool spte_has_volatile_bits(u64 spte); + bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, const struct kvm_memory_slot *slot, unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn, diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h index b1eaf6ec0e0b..f0af385c56e0 100644 --- a/arch/x86/kvm/mmu/tdp_iter.h +++ b/arch/x86/kvm/mmu/tdp_iter.h @@ -6,6 +6,7 @@ #include <linux/kvm_host.h> #include "mmu.h" +#include "spte.h" /* * TDP MMU SPTEs are RCU protected to allow paging structures (non-leaf SPTEs) @@ -17,9 +18,38 @@ static inline u64 kvm_tdp_mmu_read_spte(tdp_ptep_t sptep) { return READ_ONCE(*rcu_dereference(sptep)); } -static inline void kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 val) + +static inline u64 kvm_tdp_mmu_write_spte_atomic(tdp_ptep_t sptep, u64 new_spte) +{ + return xchg(rcu_dereference(sptep), new_spte); +} + +static inline void __kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 new_spte) +{ + WRITE_ONCE(*rcu_dereference(sptep), new_spte); +} + +static inline u64 kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 old_spte, + u64 new_spte, int level) { - WRITE_ONCE(*rcu_dereference(sptep), val); + /* + * Atomically write the SPTE if it is a shadow-present, leaf SPTE with + * volatile bits, i.e. has bits that can be set outside of mmu_lock. + * The Writable bit can be set by KVM's fast page fault handler, and + * Accessed and Dirty bits can be set by the CPU. + * + * Note, non-leaf SPTEs do have Accessed bits and those bits are + * technically volatile, but KVM doesn't consume the Accessed bit of + * non-leaf SPTEs, i.e. KVM doesn't care if it clobbers the bit. This + * logic needs to be reassessed if KVM were to use non-leaf Accessed + * bits, e.g. to skip stepping down into child SPTEs when aging SPTEs. + */ + if (is_shadow_present_pte(old_spte) && is_last_spte(old_spte, level) && + spte_has_volatile_bits(old_spte)) + return kvm_tdp_mmu_write_spte_atomic(sptep, new_spte); + + __kvm_tdp_mmu_write_spte(sptep, new_spte); + return old_spte; } /* diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index edc68538819b..922b06bf4b94 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -426,9 +426,9 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) tdp_mmu_unlink_sp(kvm, sp, shared); for (i = 0; i < PT64_ENT_PER_PAGE; i++) { - u64 *sptep = rcu_dereference(pt) + i; + tdp_ptep_t sptep = pt + i; gfn_t gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level); - u64 old_child_spte; + u64 old_spte; if (shared) { /* @@ -440,8 +440,8 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) * value to the removed SPTE value. */ for (;;) { - old_child_spte = xchg(sptep, REMOVED_SPTE); - if (!is_removed_spte(old_child_spte)) + old_spte = kvm_tdp_mmu_write_spte_atomic(sptep, REMOVED_SPTE); + if (!is_removed_spte(old_spte)) break; cpu_relax(); } @@ -455,23 +455,43 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) * are guarded by the memslots generation, not by being * unreachable. */ - old_child_spte = READ_ONCE(*sptep); - if (!is_shadow_present_pte(old_child_spte)) + old_spte = kvm_tdp_mmu_read_spte(sptep); + if (!is_shadow_present_pte(old_spte)) continue; /* - * Marking the SPTE as a removed SPTE is not - * strictly necessary here as the MMU lock will - * stop other threads from concurrently modifying - * this SPTE. Using the removed SPTE value keeps - * the two branches consistent and simplifies - * the function. + * Use the common helper instead of a raw WRITE_ONCE as + * the SPTE needs to be updated atomically if it can be + * modified by a different vCPU outside of mmu_lock. + * Even though the parent SPTE is !PRESENT, the TLB + * hasn't yet been flushed, and both Intel and AMD + * document that A/D assists can use upper-level PxE + * entries that are cached in the TLB, i.e. the CPU can + * still access the page and mark it dirty. + * + * No retry is needed in the atomic update path as the + * sole concern is dropping a Dirty bit, i.e. no other + * task can zap/remove the SPTE as mmu_lock is held for + * write. Marking the SPTE as a removed SPTE is not + * strictly necessary for the same reason, but using + * the remove SPTE value keeps the shared/exclusive + * paths consistent and allows the handle_changed_spte() + * call below to hardcode the new value to REMOVED_SPTE. + * + * Note, even though dropping a Dirty bit is the only + * scenario where a non-atomic update could result in a + * functional bug, simply checking the Dirty bit isn't + * sufficient as a fast page fault could read the upper + * level SPTE before it is zapped, and then make this + * target SPTE writable, resume the guest, and set the + * Dirty bit between reading the SPTE above and writing + * it here. */ - WRITE_ONCE(*sptep, REMOVED_SPTE); + old_spte = kvm_tdp_mmu_write_spte(sptep, old_spte, + REMOVED_SPTE, level); } handle_changed_spte(kvm, kvm_mmu_page_as_id(sp), gfn, - old_child_spte, REMOVED_SPTE, level, - shared); + old_spte, REMOVED_SPTE, level, shared); } call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback); @@ -667,14 +687,13 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm, KVM_PAGES_PER_HPAGE(iter->level)); /* - * No other thread can overwrite the removed SPTE as they - * must either wait on the MMU lock or use - * tdp_mmu_set_spte_atomic which will not overwrite the - * special removed SPTE value. No bookkeeping is needed - * here since the SPTE is going from non-present - * to non-present. + * No other thread can overwrite the removed SPTE as they must either + * wait on the MMU lock or use tdp_mmu_set_spte_atomic() which will not + * overwrite the special removed SPTE value. No bookkeeping is needed + * here since the SPTE is going from non-present to non-present. Use + * the raw write helper to avoid an unnecessary check on volatile bits. */ - kvm_tdp_mmu_write_spte(iter->sptep, 0); + __kvm_tdp_mmu_write_spte(iter->sptep, 0); return 0; } @@ -699,10 +718,13 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm, * unless performing certain dirty logging operations. * Leaving record_dirty_log unset in that case prevents page * writes from being double counted. + * + * Returns the old SPTE value, which _may_ be different than @old_spte if the + * SPTE had voldatile bits. */ -static void __tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, - u64 old_spte, u64 new_spte, gfn_t gfn, int level, - bool record_acc_track, bool record_dirty_log) +static u64 __tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, + u64 old_spte, u64 new_spte, gfn_t gfn, int level, + bool record_acc_track, bool record_dirty_log) { lockdep_assert_held_write(&kvm->mmu_lock); @@ -715,7 +737,7 @@ static void __tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, */ WARN_ON(is_removed_spte(old_spte) || is_removed_spte(new_spte)); - kvm_tdp_mmu_write_spte(sptep, new_spte); + old_spte = kvm_tdp_mmu_write_spte(sptep, old_spte, new_spte, level); __handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level, false); @@ -724,6 +746,7 @@ static void __tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, if (record_dirty_log) handle_changed_spte_dirty_log(kvm, as_id, gfn, old_spte, new_spte, level); + return old_spte; } static inline void _tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, @@ -732,9 +755,10 @@ static inline void _tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, { WARN_ON_ONCE(iter->yielded); - __tdp_mmu_set_spte(kvm, iter->as_id, iter->sptep, iter->old_spte, - new_spte, iter->gfn, iter->level, - record_acc_track, record_dirty_log); + iter->old_spte = __tdp_mmu_set_spte(kvm, iter->as_id, iter->sptep, + iter->old_spte, new_spte, + iter->gfn, iter->level, + record_acc_track, record_dirty_log); } static inline void tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index b14860863c39..16a5ebb420cf 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -45,6 +45,22 @@ static struct kvm_event_hw_type_mapping amd_event_mapping[] = { [7] = { 0xd1, 0x00, PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, }; +/* duplicated from amd_f17h_perfmon_event_map. */ +static struct kvm_event_hw_type_mapping amd_f17h_event_mapping[] = { + [0] = { 0x76, 0x00, PERF_COUNT_HW_CPU_CYCLES }, + [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS }, + [2] = { 0x60, 0xff, PERF_COUNT_HW_CACHE_REFERENCES }, + [3] = { 0x64, 0x09, PERF_COUNT_HW_CACHE_MISSES }, + [4] = { 0xc2, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, + [5] = { 0xc3, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, + [6] = { 0x87, 0x02, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND }, + [7] = { 0x87, 0x01, PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, +}; + +/* amd_pmc_perf_hw_id depends on these being the same size */ +static_assert(ARRAY_SIZE(amd_event_mapping) == + ARRAY_SIZE(amd_f17h_event_mapping)); + static unsigned int get_msr_base(struct kvm_pmu *pmu, enum pmu_type type) { struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); @@ -140,6 +156,7 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, static unsigned int amd_pmc_perf_hw_id(struct kvm_pmc *pmc) { + struct kvm_event_hw_type_mapping *event_mapping; u8 event_select = pmc->eventsel & ARCH_PERFMON_EVENTSEL_EVENT; u8 unit_mask = (pmc->eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; int i; @@ -148,15 +165,20 @@ static unsigned int amd_pmc_perf_hw_id(struct kvm_pmc *pmc) if (WARN_ON(pmc_is_fixed(pmc))) return PERF_COUNT_HW_MAX; + if (guest_cpuid_family(pmc->vcpu) >= 0x17) + event_mapping = amd_f17h_event_mapping; + else + event_mapping = amd_event_mapping; + for (i = 0; i < ARRAY_SIZE(amd_event_mapping); i++) - if (amd_event_mapping[i].eventsel == event_select - && amd_event_mapping[i].unit_mask == unit_mask) + if (event_mapping[i].eventsel == event_select + && event_mapping[i].unit_mask == unit_mask) break; if (i == ARRAY_SIZE(amd_event_mapping)) return PERF_COUNT_HW_MAX; - return amd_event_mapping[i].event_type; + return event_mapping[i].event_type; } /* check if a PMC is enabled by comparing it against global_ctrl bits. Because diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 0ad70c12c7c3..7c392873626f 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1594,24 +1594,51 @@ static void sev_unlock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm) atomic_set_release(&src_sev->migration_in_progress, 0); } +/* vCPU mutex subclasses. */ +enum sev_migration_role { + SEV_MIGRATION_SOURCE = 0, + SEV_MIGRATION_TARGET, + SEV_NR_MIGRATION_ROLES, +}; -static int sev_lock_vcpus_for_migration(struct kvm *kvm) +static int sev_lock_vcpus_for_migration(struct kvm *kvm, + enum sev_migration_role role) { struct kvm_vcpu *vcpu; unsigned long i, j; + bool first = true; kvm_for_each_vcpu(i, vcpu, kvm) { - if (mutex_lock_killable(&vcpu->mutex)) + if (mutex_lock_killable_nested(&vcpu->mutex, role)) goto out_unlock; + + if (first) { + /* + * Reset the role to one that avoids colliding with + * the role used for the first vcpu mutex. + */ + role = SEV_NR_MIGRATION_ROLES; + first = false; + } else { + mutex_release(&vcpu->mutex.dep_map, _THIS_IP_); + } } return 0; out_unlock: + + first = true; kvm_for_each_vcpu(j, vcpu, kvm) { if (i == j) break; + if (first) + first = false; + else + mutex_acquire(&vcpu->mutex.dep_map, role, 0, _THIS_IP_); + + mutex_unlock(&vcpu->mutex); } return -EINTR; @@ -1621,8 +1648,15 @@ static void sev_unlock_vcpus_for_migration(struct kvm *kvm) { struct kvm_vcpu *vcpu; unsigned long i; + bool first = true; kvm_for_each_vcpu(i, vcpu, kvm) { + if (first) + first = false; + else + mutex_acquire(&vcpu->mutex.dep_map, + SEV_NR_MIGRATION_ROLES, 0, _THIS_IP_); + mutex_unlock(&vcpu->mutex); } } @@ -1748,10 +1782,10 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd) charged = true; } - ret = sev_lock_vcpus_for_migration(kvm); + ret = sev_lock_vcpus_for_migration(kvm, SEV_MIGRATION_SOURCE); if (ret) goto out_dst_cgroup; - ret = sev_lock_vcpus_for_migration(source_kvm); + ret = sev_lock_vcpus_for_migration(source_kvm, SEV_MIGRATION_TARGET); if (ret) goto out_dst_vcpu; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index d58b763df855..610355b9ccce 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -5472,7 +5472,7 @@ 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.pending || vcpu->arch.exception.injected); } static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 96d34ebb20a9..e2942335d143 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -902,6 +902,8 @@ static void __meminit vmemmap_use_sub_pmd(unsigned long start, unsigned long end static void __meminit vmemmap_use_new_sub_pmd(unsigned long start, unsigned long end) { + const unsigned long page = ALIGN_DOWN(start, PMD_SIZE); + vmemmap_flush_unused_pmd(); /* @@ -914,8 +916,7 @@ static void __meminit vmemmap_use_new_sub_pmd(unsigned long start, unsigned long * Mark with PAGE_UNUSED the unused parts of the new memmap range */ if (!IS_ALIGNED(start, PMD_SIZE)) - memset((void *)start, PAGE_UNUSED, - start - ALIGN_DOWN(start, PMD_SIZE)); + memset((void *)page, PAGE_UNUSED, start - page); /* * We want to avoid memset(PAGE_UNUSED) when populating the vmemmap of |