diff options
author | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2023-03-20 09:06:37 +0100 |
---|---|---|
committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2023-03-20 09:06:37 +0100 |
commit | abae262640ef9c7f24bad65acade25b44c7ba0eb (patch) | |
tree | c5d9a340af15969f4b3fe2485e2e3589933e7efe /arch | |
parent | 6ca8f8bf706d874090b74f811194e94ebbc560df (diff) | |
parent | e8d018dd0257f744ca50a729e3d042cf2ec9da65 (diff) | |
download | linux-stable-abae262640ef9c7f24bad65acade25b44c7ba0eb.tar.gz linux-stable-abae262640ef9c7f24bad65acade25b44c7ba0eb.tar.bz2 linux-stable-abae262640ef9c7f24bad65acade25b44c7ba0eb.zip |
Merge 6.3-rc3 into char-misc-next
We need the mainline fixes in this branch for testing and other
subsystem changes to be based properly on.
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'arch')
62 files changed, 339 insertions, 226 deletions
diff --git a/arch/alpha/lib/fpreg.c b/arch/alpha/lib/fpreg.c index 612c5eca71bc..7c08b225261c 100644 --- a/arch/alpha/lib/fpreg.c +++ b/arch/alpha/lib/fpreg.c @@ -23,7 +23,7 @@ alpha_read_fp_reg (unsigned long reg) if (unlikely(reg >= 32)) return 0; - preempt_enable(); + preempt_disable(); if (current_thread_info()->status & TS_SAVED_FP) val = current_thread_info()->fp[reg]; else switch (reg) { @@ -133,7 +133,7 @@ alpha_read_fp_reg_s (unsigned long reg) if (unlikely(reg >= 32)) return 0; - preempt_enable(); + preempt_disable(); if (current_thread_info()->status & TS_SAVED_FP) { LDT(0, current_thread_info()->fp[reg]); STS(0, val); diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index a1892a8f6032..bcd774d74f34 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -193,6 +193,9 @@ struct kvm_arch { /* Interrupt controller */ struct vgic_dist vgic; + /* Timers */ + struct arch_timer_vm_data timer_data; + /* Mandated version of PSCI */ u32 psci_version; diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 00610477ec7b..e1af4301b913 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -84,14 +84,10 @@ u64 timer_get_cval(struct arch_timer_context *ctxt) static u64 timer_get_offset(struct arch_timer_context *ctxt) { - struct kvm_vcpu *vcpu = ctxt->vcpu; + if (ctxt->offset.vm_offset) + return *ctxt->offset.vm_offset; - switch(arch_timer_ctx_index(ctxt)) { - case TIMER_VTIMER: - return __vcpu_sys_reg(vcpu, CNTVOFF_EL2); - default: - return 0; - } + return 0; } static void timer_set_ctl(struct arch_timer_context *ctxt, u32 ctl) @@ -128,15 +124,12 @@ static void timer_set_cval(struct arch_timer_context *ctxt, u64 cval) static void timer_set_offset(struct arch_timer_context *ctxt, u64 offset) { - struct kvm_vcpu *vcpu = ctxt->vcpu; - - switch(arch_timer_ctx_index(ctxt)) { - case TIMER_VTIMER: - __vcpu_sys_reg(vcpu, CNTVOFF_EL2) = offset; - break; - default: + if (!ctxt->offset.vm_offset) { WARN(offset, "timer %ld\n", arch_timer_ctx_index(ctxt)); + return; } + + WRITE_ONCE(*ctxt->offset.vm_offset, offset); } u64 kvm_phys_timer_read(void) @@ -765,25 +758,6 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) return 0; } -/* Make the updates of cntvoff for all vtimer contexts atomic */ -static void update_vtimer_cntvoff(struct kvm_vcpu *vcpu, u64 cntvoff) -{ - unsigned long i; - struct kvm *kvm = vcpu->kvm; - struct kvm_vcpu *tmp; - - mutex_lock(&kvm->lock); - kvm_for_each_vcpu(i, tmp, kvm) - timer_set_offset(vcpu_vtimer(tmp), cntvoff); - - /* - * When called from the vcpu create path, the CPU being created is not - * included in the loop above, so we just set it here as well. - */ - timer_set_offset(vcpu_vtimer(vcpu), cntvoff); - mutex_unlock(&kvm->lock); -} - void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = vcpu_timer(vcpu); @@ -791,10 +765,11 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); vtimer->vcpu = vcpu; + vtimer->offset.vm_offset = &vcpu->kvm->arch.timer_data.voffset; ptimer->vcpu = vcpu; /* Synchronize cntvoff across all vtimers of a VM. */ - update_vtimer_cntvoff(vcpu, kvm_phys_timer_read()); + timer_set_offset(vtimer, kvm_phys_timer_read()); timer_set_offset(ptimer, 0); hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); @@ -840,7 +815,7 @@ int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value) break; case KVM_REG_ARM_TIMER_CNT: timer = vcpu_vtimer(vcpu); - update_vtimer_cntvoff(vcpu, kvm_phys_timer_read() - value); + timer_set_offset(timer, kvm_phys_timer_read() - value); break; case KVM_REG_ARM_TIMER_CVAL: timer = vcpu_vtimer(vcpu); diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c index 64c086c02c60..5da884e11337 100644 --- a/arch/arm64/kvm/hypercalls.c +++ b/arch/arm64/kvm/hypercalls.c @@ -44,7 +44,7 @@ static void kvm_ptp_get_time(struct kvm_vcpu *vcpu, u64 *val) feature = smccc_get_arg1(vcpu); switch (feature) { case KVM_PTP_VIRT_COUNTER: - cycles = systime_snapshot.cycles - vcpu_read_sys_reg(vcpu, CNTVOFF_EL2); + cycles = systime_snapshot.cycles - vcpu->kvm->arch.timer_data.voffset; break; case KVM_PTP_PHYS_COUNTER: cycles = systime_snapshot.cycles; diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c index 3a2bb2e8fdad..fbff1cea62ca 100644 --- a/arch/m68k/kernel/setup_mm.c +++ b/arch/m68k/kernel/setup_mm.c @@ -326,16 +326,16 @@ void __init setup_arch(char **cmdline_p) panic("No configuration setup"); } -#ifdef CONFIG_BLK_DEV_INITRD - if (m68k_ramdisk.size) { + if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && m68k_ramdisk.size) memblock_reserve(m68k_ramdisk.addr, m68k_ramdisk.size); + + paging_init(); + + if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && m68k_ramdisk.size) { initrd_start = (unsigned long)phys_to_virt(m68k_ramdisk.addr); initrd_end = initrd_start + m68k_ramdisk.size; pr_info("initrd: %08lx - %08lx\n", initrd_start, initrd_end); } -#endif - - paging_init(); #ifdef CONFIG_NATFEAT nf_init(); diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c index 5c8cba0efc63..a700807c9b6d 100644 --- a/arch/m68k/kernel/traps.c +++ b/arch/m68k/kernel/traps.c @@ -30,6 +30,7 @@ #include <linux/init.h> #include <linux/ptrace.h> #include <linux/kallsyms.h> +#include <linux/extable.h> #include <asm/setup.h> #include <asm/fpu.h> @@ -545,7 +546,8 @@ static inline void bus_error030 (struct frame *fp) errorcode |= 2; if (mmusr & (MMU_I | MMU_WP)) { - if (ssw & 4) { + /* We might have an exception table for this PC */ + if (ssw & 4 && !search_exception_tables(fp->ptregs.pc)) { pr_err("Data %s fault at %#010lx in %s (pc=%#lx)\n", ssw & RW ? "read" : "write", fp->un.fmtb.daddr, diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c index 2a375637e007..911301224078 100644 --- a/arch/m68k/mm/motorola.c +++ b/arch/m68k/mm/motorola.c @@ -437,7 +437,7 @@ void __init paging_init(void) } min_addr = m68k_memory[0].addr; - max_addr = min_addr + m68k_memory[0].size; + max_addr = min_addr + m68k_memory[0].size - 1; memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0, MEMBLOCK_NONE); for (i = 1; i < m68k_num_memory;) { @@ -452,21 +452,21 @@ void __init paging_init(void) } memblock_add_node(m68k_memory[i].addr, m68k_memory[i].size, i, MEMBLOCK_NONE); - addr = m68k_memory[i].addr + m68k_memory[i].size; + addr = m68k_memory[i].addr + m68k_memory[i].size - 1; if (addr > max_addr) max_addr = addr; i++; } m68k_memoffset = min_addr - PAGE_OFFSET; - m68k_virt_to_node_shift = fls(max_addr - min_addr - 1) - 6; + m68k_virt_to_node_shift = fls(max_addr - min_addr) - 6; module_fixup(NULL, __start_fixup, __stop_fixup); flush_icache(); - high_memory = phys_to_virt(max_addr); + high_memory = phys_to_virt(max_addr) + 1; min_low_pfn = availmem >> PAGE_SHIFT; - max_pfn = max_low_pfn = max_addr >> PAGE_SHIFT; + max_pfn = max_low_pfn = (max_addr >> PAGE_SHIFT) + 1; /* Reserve kernel text/data/bss and the memory allocated in head.S */ memblock_reserve(m68k_memory[0].addr, availmem - m68k_memory[0].addr); diff --git a/arch/mips/configs/mtx1_defconfig b/arch/mips/configs/mtx1_defconfig index 89a1511d2ee4..edf9634aa8ee 100644 --- a/arch/mips/configs/mtx1_defconfig +++ b/arch/mips/configs/mtx1_defconfig @@ -284,6 +284,7 @@ CONFIG_IXGB=m CONFIG_SKGE=m CONFIG_SKY2=m CONFIG_MYRI10GE=m +CONFIG_FEALNX=m CONFIG_NATSEMI=m CONFIG_NS83820=m CONFIG_S2IO=m diff --git a/arch/powerpc/boot/dts/fsl/t1040rdb-rev-a.dts b/arch/powerpc/boot/dts/fsl/t1040rdb-rev-a.dts index 73f8c998c64d..d4f5f159d6f2 100644 --- a/arch/powerpc/boot/dts/fsl/t1040rdb-rev-a.dts +++ b/arch/powerpc/boot/dts/fsl/t1040rdb-rev-a.dts @@ -10,7 +10,6 @@ / { model = "fsl,T1040RDB-REV-A"; - compatible = "fsl,T1040RDB-REV-A"; }; &seville_port0 { diff --git a/arch/powerpc/boot/dts/fsl/t1040rdb.dts b/arch/powerpc/boot/dts/fsl/t1040rdb.dts index b6733e7e6580..dd3aab81e9de 100644 --- a/arch/powerpc/boot/dts/fsl/t1040rdb.dts +++ b/arch/powerpc/boot/dts/fsl/t1040rdb.dts @@ -180,6 +180,9 @@ }; &seville_port8 { - ethernet = <&enet0>; + status = "okay"; +}; + +&seville_port9 { status = "okay"; }; diff --git a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi index f58eb820eb5e..ad0ab33336b8 100644 --- a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi @@ -686,6 +686,7 @@ seville_port8: port@8 { reg = <8>; phy-mode = "internal"; + ethernet = <&enet0>; status = "disabled"; fixed-link { @@ -697,6 +698,7 @@ seville_port9: port@9 { reg = <9>; phy-mode = "internal"; + ethernet = <&enet1>; status = "disabled"; fixed-link { diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index d8729b94400e..9cb866b63553 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -461,6 +461,7 @@ CONFIG_MV643XX_ETH=m CONFIG_SKGE=m CONFIG_SKY2=m CONFIG_MYRI10GE=m +CONFIG_FEALNX=m CONFIG_NATSEMI=m CONFIG_NS83820=m CONFIG_PCMCIA_AXNET=m diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 2bef19cc1b98..af46aa88422b 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -271,11 +271,16 @@ static bool access_error(bool is_write, bool is_exec, struct vm_area_struct *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. + * VM_READ, VM_WRITE and VM_EXEC all imply read permissions, as + * defined in protection_map[]. Read faults can only be caused by + * a PROT_NONE mapping, or with a PROT_EXEC-only mapping on Radix. */ - if (unlikely(!(vma->vm_flags & VM_READ))) + if (unlikely(!vma_is_accessible(vma))) return true; + + if (unlikely(radix_enabled() && ((vma->vm_flags & VM_ACCESS_FLAGS) == VM_EXEC))) + return true; + /* * We should ideally do the vma pkey access check here. But in the * fault path, handle_mm_fault() also does the same check. To avoid diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index b481c5c8bae1..21b22bf16ce6 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -7,6 +7,7 @@ config PPC_PSERIES select OF_DYNAMIC select FORCE_PCI select PCI_MSI + select GENERIC_ALLOCATOR select PPC_XICS select PPC_XIVE_SPAPR select PPC_ICP_NATIVE diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 73c620c2a3a1..e753a6bd4888 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -1275,7 +1275,7 @@ static int xmon_batch_next_cpu(void) while (!cpumask_empty(&xmon_batch_cpus)) { cpu = cpumask_next_wrap(smp_processor_id(), &xmon_batch_cpus, xmon_batch_start_cpu, true); - if (cpu == nr_cpumask_bits) + if (cpu >= nr_cpu_ids) break; if (xmon_batch_start_cpu == -1) xmon_batch_start_cpu = cpu; diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 6203c3378922..4de83b9b1772 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -84,6 +84,13 @@ endif # Avoid generating .eh_frame sections. KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables +# The RISC-V attributes frequently cause compatibility issues and provide no +# information, so just turn them off. +KBUILD_CFLAGS += $(call cc-option,-mno-riscv-attribute) +KBUILD_AFLAGS += $(call cc-option,-mno-riscv-attribute) +KBUILD_CFLAGS += $(call as-option,-Wa$(comma)-mno-arch-attr) +KBUILD_AFLAGS += $(call as-option,-Wa$(comma)-mno-arch-attr) + KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-relax) KBUILD_AFLAGS_MODULE += $(call as-option,-Wa$(comma)-mno-relax) diff --git a/arch/riscv/errata/sifive/errata.c b/arch/riscv/errata/sifive/errata.c index da55cb247e89..31d2ebea4286 100644 --- a/arch/riscv/errata/sifive/errata.c +++ b/arch/riscv/errata/sifive/errata.c @@ -111,7 +111,7 @@ void __init_or_module sifive_errata_patch_func(struct alt_entry *begin, mutex_lock(&text_mutex); patch_text_nosync(ALT_OLD_PTR(alt), ALT_ALT_PTR(alt), alt->alt_len); - mutex_lock(&text_mutex); + mutex_unlock(&text_mutex); cpu_apply_errata |= tmp; } } diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h index 9e73922e1e2e..d47d87c2d7e3 100644 --- a/arch/riscv/include/asm/ftrace.h +++ b/arch/riscv/include/asm/ftrace.h @@ -109,6 +109,6 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec); #define ftrace_init_nop ftrace_init_nop #endif -#endif +#endif /* CONFIG_DYNAMIC_FTRACE */ #endif /* _ASM_RISCV_FTRACE_H */ diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h index 5ff1f19fd45c..0099dc116168 100644 --- a/arch/riscv/include/asm/mmu.h +++ b/arch/riscv/include/asm/mmu.h @@ -19,8 +19,6 @@ typedef struct { #ifdef CONFIG_SMP /* A local icache flush is needed before user execution can resume. */ cpumask_t icache_stale_mask; - /* A local tlb flush is needed before user execution can resume. */ - cpumask_t tlb_stale_mask; #endif } mm_context_t; diff --git a/arch/riscv/include/asm/patch.h b/arch/riscv/include/asm/patch.h index f433121774c0..63c98833d510 100644 --- a/arch/riscv/include/asm/patch.h +++ b/arch/riscv/include/asm/patch.h @@ -9,4 +9,6 @@ int patch_text_nosync(void *addr, const void *insns, size_t len); int patch_text(void *addr, u32 *insns, int ninsns); +extern int riscv_patch_in_stop_machine; + #endif /* _ASM_RISCV_PATCH_H */ diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h index 907b9efd39a8..801019381dea 100644 --- a/arch/riscv/include/asm/tlbflush.h +++ b/arch/riscv/include/asm/tlbflush.h @@ -22,24 +22,6 @@ static inline void local_flush_tlb_page(unsigned long addr) { ALT_FLUSH_TLB_PAGE(__asm__ __volatile__ ("sfence.vma %0" : : "r" (addr) : "memory")); } - -static inline void local_flush_tlb_all_asid(unsigned long asid) -{ - __asm__ __volatile__ ("sfence.vma x0, %0" - : - : "r" (asid) - : "memory"); -} - -static inline void local_flush_tlb_page_asid(unsigned long addr, - unsigned long asid) -{ - __asm__ __volatile__ ("sfence.vma %0, %1" - : - : "r" (addr), "r" (asid) - : "memory"); -} - #else /* CONFIG_MMU */ #define local_flush_tlb_all() do { } while (0) #define local_flush_tlb_page(addr) do { } while (0) diff --git a/arch/riscv/kernel/compat_vdso/Makefile b/arch/riscv/kernel/compat_vdso/Makefile index 260daf3236d3..7f34f3c7c882 100644 --- a/arch/riscv/kernel/compat_vdso/Makefile +++ b/arch/riscv/kernel/compat_vdso/Makefile @@ -14,6 +14,10 @@ COMPAT_LD := $(LD) COMPAT_CC_FLAGS := -march=rv32g -mabi=ilp32 COMPAT_LD_FLAGS := -melf32lriscv +# Disable attributes, as they're useless and break the build. +COMPAT_CC_FLAGS += $(call cc-option,-mno-riscv-attribute) +COMPAT_CC_FLAGS += $(call as-option,-Wa$(comma)-mno-arch-attr) + # Files to link into the compat_vdso obj-compat_vdso = $(patsubst %, %.o, $(compat_vdso-syms)) note.o diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 5bff37af4770..03a6434a8cdd 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -15,10 +15,19 @@ void ftrace_arch_code_modify_prepare(void) __acquires(&text_mutex) { mutex_lock(&text_mutex); + + /* + * The code sequences we use for ftrace can't be patched while the + * kernel is running, so we need to use stop_machine() to modify them + * for now. This doesn't play nice with text_mutex, we use this flag + * to elide the check. + */ + riscv_patch_in_stop_machine = true; } void ftrace_arch_code_modify_post_process(void) __releases(&text_mutex) { + riscv_patch_in_stop_machine = false; mutex_unlock(&text_mutex); } @@ -107,9 +116,9 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) { int out; - ftrace_arch_code_modify_prepare(); + mutex_lock(&text_mutex); out = ftrace_make_nop(mod, rec, MCOUNT_ADDR); - ftrace_arch_code_modify_post_process(); + mutex_unlock(&text_mutex); return out; } diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c index 8086d1a281cd..575e71d6c8ae 100644 --- a/arch/riscv/kernel/patch.c +++ b/arch/riscv/kernel/patch.c @@ -11,6 +11,7 @@ #include <asm/kprobes.h> #include <asm/cacheflush.h> #include <asm/fixmap.h> +#include <asm/ftrace.h> #include <asm/patch.h> struct patch_insn { @@ -20,6 +21,8 @@ struct patch_insn { atomic_t cpu_count; }; +int riscv_patch_in_stop_machine = false; + #ifdef CONFIG_MMU /* * The fix_to_virt(, idx) needs a const value (not a dynamic variable of @@ -60,8 +63,15 @@ static int patch_insn_write(void *addr, const void *insn, size_t len) * Before reaching here, it was expected to lock the text_mutex * already, so we don't need to give another lock here and could * ensure that it was safe between each cores. + * + * We're currently using stop_machine() for ftrace & kprobes, and while + * that ensures text_mutex is held before installing the mappings it + * does not ensure text_mutex is held by the calling thread. That's + * safe but triggers a lockdep failure, so just elide it for that + * specific case. */ - lockdep_assert_held(&text_mutex); + if (!riscv_patch_in_stop_machine) + lockdep_assert_held(&text_mutex); if (across_pages) patch_map(addr + len, FIX_TEXT_POKE1); @@ -125,6 +135,7 @@ NOKPROBE_SYMBOL(patch_text_cb); int patch_text(void *addr, u32 *insns, int ninsns) { + int ret; struct patch_insn patch = { .addr = addr, .insns = insns, @@ -132,7 +143,18 @@ int patch_text(void *addr, u32 *insns, int ninsns) .cpu_count = ATOMIC_INIT(0), }; - return stop_machine_cpuslocked(patch_text_cb, - &patch, cpu_online_mask); + /* + * kprobes takes text_mutex, before calling patch_text(), but as we call + * calls stop_machine(), the lockdep assertion in patch_insn_write() + * gets confused by the context in which the lock is taken. + * Instead, ensure the lock is held before calling stop_machine(), and + * set riscv_patch_in_stop_machine to skip the check in + * patch_insn_write(). + */ + lockdep_assert_held(&text_mutex); + riscv_patch_in_stop_machine = true; + ret = stop_machine_cpuslocked(patch_text_cb, &patch, cpu_online_mask); + riscv_patch_in_stop_machine = false; + return ret; } NOKPROBE_SYMBOL(patch_text); diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index f9a5a7c90ff0..64a9c093aef9 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -101,7 +101,7 @@ void notrace walk_stackframe(struct task_struct *task, while (!kstack_end(ksp)) { if (__kernel_text_address(pc) && unlikely(!fn(arg, pc))) break; - pc = (*ksp++) - 0x4; + pc = READ_ONCE_NOCHECK(*ksp++) - 0x4; } } diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c index 80ce9caba8d2..0f784e3d307b 100644 --- a/arch/riscv/mm/context.c +++ b/arch/riscv/mm/context.c @@ -196,16 +196,6 @@ switch_mm_fast: if (need_flush_tlb) local_flush_tlb_all(); -#ifdef CONFIG_SMP - else { - cpumask_t *mask = &mm->context.tlb_stale_mask; - - if (cpumask_test_cpu(cpu, mask)) { - cpumask_clear_cpu(cpu, mask); - local_flush_tlb_all_asid(cntx & asid_mask); - } - } -#endif } static void set_mm_noasid(struct mm_struct *mm) @@ -215,12 +205,24 @@ static void set_mm_noasid(struct mm_struct *mm) local_flush_tlb_all(); } -static inline void set_mm(struct mm_struct *mm, unsigned int cpu) +static inline void set_mm(struct mm_struct *prev, + struct mm_struct *next, unsigned int cpu) { - if (static_branch_unlikely(&use_asid_allocator)) - set_mm_asid(mm, cpu); - else - set_mm_noasid(mm); + /* + * The mm_cpumask indicates which harts' TLBs contain the virtual + * address mapping of the mm. Compared to noasid, using asid + * can't guarantee that stale TLB entries are invalidated because + * the asid mechanism wouldn't flush TLB for every switch_mm for + * performance. So when using asid, keep all CPUs footmarks in + * cpumask() until mm reset. + */ + cpumask_set_cpu(cpu, mm_cpumask(next)); + if (static_branch_unlikely(&use_asid_allocator)) { + set_mm_asid(next, cpu); + } else { + cpumask_clear_cpu(cpu, mm_cpumask(prev)); + set_mm_noasid(next); + } } static int __init asids_init(void) @@ -274,7 +276,8 @@ static int __init asids_init(void) } early_initcall(asids_init); #else -static inline void set_mm(struct mm_struct *mm, unsigned int cpu) +static inline void set_mm(struct mm_struct *prev, + struct mm_struct *next, unsigned int cpu) { /* Nothing to do here when there is no MMU */ } @@ -327,10 +330,7 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next, */ cpu = smp_processor_id(); - cpumask_clear_cpu(cpu, mm_cpumask(prev)); - cpumask_set_cpu(cpu, mm_cpumask(next)); - - set_mm(next, cpu); + set_mm(prev, next, cpu); flush_icache_deferred(next, cpu); } diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 460f785f6e09..d5f3e501dffb 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -143,6 +143,8 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a no_context(regs, addr); return; } + if (pud_leaf(*pud_k)) + goto flush_tlb; /* * Since the vmalloc area is global, it is unnecessary @@ -153,6 +155,8 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a no_context(regs, addr); return; } + if (pmd_leaf(*pmd_k)) + goto flush_tlb; /* * Make sure the actual PTE exists as well to @@ -172,6 +176,7 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a * ordering constraint, not a cache flush; it is * necessary even after writing invalid entries. */ +flush_tlb: local_flush_tlb_page(addr); } diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c index ce7dfc81bb3f..37ed760d007c 100644 --- a/arch/riscv/mm/tlbflush.c +++ b/arch/riscv/mm/tlbflush.c @@ -5,7 +5,23 @@ #include <linux/sched.h> #include <asm/sbi.h> #include <asm/mmu_context.h> -#include <asm/tlbflush.h> + +static inline void local_flush_tlb_all_asid(unsigned long asid) +{ + __asm__ __volatile__ ("sfence.vma x0, %0" + : + : "r" (asid) + : "memory"); +} + +static inline void local_flush_tlb_page_asid(unsigned long addr, + unsigned long asid) +{ + __asm__ __volatile__ ("sfence.vma %0, %1" + : + : "r" (addr), "r" (asid) + : "memory"); +} void flush_tlb_all(void) { @@ -15,7 +31,6 @@ void flush_tlb_all(void) static void __sbi_tlb_flush_range(struct mm_struct *mm, unsigned long start, unsigned long size, unsigned long stride) { - struct cpumask *pmask = &mm->context.tlb_stale_mask; struct cpumask *cmask = mm_cpumask(mm); unsigned int cpuid; bool broadcast; @@ -29,15 +44,6 @@ static void __sbi_tlb_flush_range(struct mm_struct *mm, unsigned long start, if (static_branch_unlikely(&use_asid_allocator)) { unsigned long asid = atomic_long_read(&mm->context.id); - /* - * TLB will be immediately flushed on harts concurrently - * executing this MM context. TLB flush on other harts - * is deferred until this MM context migrates there. - */ - cpumask_setall(pmask); - cpumask_clear_cpu(cpuid, pmask); - cpumask_andnot(pmask, pmask, cmask); - if (broadcast) { sbi_remote_sfence_vma_asid(cmask, start, size, asid); } else if (size <= stride) { diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index f5a668736c79..acdc3f040195 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -10,6 +10,7 @@ #include <linux/filter.h> #include <linux/memory.h> #include <linux/stop_machine.h> +#include <asm/patch.h> #include "bpf_jit.h" #define RV_REG_TCC RV_REG_A6 diff --git a/arch/s390/boot/ipl_report.c b/arch/s390/boot/ipl_report.c index 9b14045065b6..74b5cd264862 100644 --- a/arch/s390/boot/ipl_report.c +++ b/arch/s390/boot/ipl_report.c @@ -57,11 +57,19 @@ repeat: if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && initrd_data.start && initrd_data.size && intersects(initrd_data.start, initrd_data.size, safe_addr, size)) safe_addr = initrd_data.start + initrd_data.size; + if (intersects(safe_addr, size, (unsigned long)comps, comps->len)) { + safe_addr = (unsigned long)comps + comps->len; + goto repeat; + } for_each_rb_entry(comp, comps) if (intersects(safe_addr, size, comp->addr, comp->len)) { safe_addr = comp->addr + comp->len; goto repeat; } + if (intersects(safe_addr, size, (unsigned long)certs, certs->len)) { + safe_addr = (unsigned long)certs + certs->len; + goto repeat; + } for_each_rb_entry(cert, certs) if (intersects(safe_addr, size, cert->addr, cert->len)) { safe_addr = cert->addr + cert->len; diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 3c68fe49042c..4ccf66d29fc2 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -23,7 +23,6 @@ CONFIG_NUMA_BALANCING=y CONFIG_MEMCG=y CONFIG_BLK_CGROUP=y CONFIG_CFS_BANDWIDTH=y -CONFIG_RT_GROUP_SCHED=y CONFIG_CGROUP_PIDS=y CONFIG_CGROUP_RDMA=y CONFIG_CGROUP_FREEZER=y @@ -90,7 +89,6 @@ CONFIG_MINIX_SUBPARTITION=y CONFIG_SOLARIS_X86_PARTITION=y CONFIG_UNIXWARE_DISKLABEL=y CONFIG_IOSCHED_BFQ=y -CONFIG_BFQ_GROUP_IOSCHED=y CONFIG_BINFMT_MISC=m CONFIG_ZSWAP=y CONFIG_ZSMALLOC_STAT=y @@ -298,7 +296,6 @@ CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_MANGLE=m -CONFIG_IP_NF_TARGET_CLUSTERIP=m CONFIG_IP_NF_TARGET_ECN=m CONFIG_IP_NF_TARGET_TTL=m CONFIG_IP_NF_RAW=m @@ -340,7 +337,6 @@ CONFIG_BRIDGE_MRP=y CONFIG_VLAN_8021Q=m CONFIG_VLAN_8021Q_GVRP=y CONFIG_NET_SCHED=y -CONFIG_NET_SCH_CBQ=m CONFIG_NET_SCH_HTB=m CONFIG_NET_SCH_HFSC=m CONFIG_NET_SCH_PRIO=m @@ -351,7 +347,6 @@ CONFIG_NET_SCH_SFQ=m CONFIG_NET_SCH_TEQL=m CONFIG_NET_SCH_TBF=m CONFIG_NET_SCH_GRED=m -CONFIG_NET_SCH_DSMARK=m CONFIG_NET_SCH_NETEM=m CONFIG_NET_SCH_DRR=m CONFIG_NET_SCH_MQPRIO=m @@ -363,14 +358,11 @@ CONFIG_NET_SCH_INGRESS=m CONFIG_NET_SCH_PLUG=m CONFIG_NET_SCH_ETS=m CONFIG_NET_CLS_BASIC=m -CONFIG_NET_CLS_TCINDEX=m CONFIG_NET_CLS_ROUTE4=m CONFIG_NET_CLS_FW=m CONFIG_NET_CLS_U32=m CONFIG_CLS_U32_PERF=y CONFIG_CLS_U32_MARK=y -CONFIG_NET_CLS_RSVP=m -CONFIG_NET_CLS_RSVP6=m CONFIG_NET_CLS_FLOW=m CONFIG_NET_CLS_CGROUP=y CONFIG_NET_CLS_BPF=m @@ -584,7 +576,7 @@ CONFIG_DIAG288_WATCHDOG=m CONFIG_FB=y CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y -# CONFIG_HID is not set +# CONFIG_HID_SUPPORT is not set # CONFIG_USB_SUPPORT is not set CONFIG_INFINIBAND=m CONFIG_INFINIBAND_USER_ACCESS=m @@ -828,6 +820,7 @@ CONFIG_PANIC_ON_OOPS=y CONFIG_DETECT_HUNG_TASK=y CONFIG_WQ_WATCHDOG=y CONFIG_TEST_LOCKUP=m +CONFIG_DEBUG_PREEMPT=y CONFIG_PROVE_LOCKING=y CONFIG_LOCK_STAT=y CONFIG_DEBUG_ATOMIC_SLEEP=y @@ -843,6 +836,7 @@ CONFIG_RCU_CPU_STALL_TIMEOUT=300 # CONFIG_RCU_TRACE is not set CONFIG_LATENCYTOP=y CONFIG_BOOTTIME_TRACING=y +CONFIG_FPROBE=y CONFIG_FUNCTION_PROFILER=y CONFIG_STACK_TRACER=y CONFIG_IRQSOFF_TRACER=y @@ -857,6 +851,7 @@ CONFIG_SAMPLES=y CONFIG_SAMPLE_TRACE_PRINTK=m CONFIG_SAMPLE_FTRACE_DIRECT=m CONFIG_SAMPLE_FTRACE_DIRECT_MULTI=m +CONFIG_SAMPLE_FTRACE_OPS=m CONFIG_DEBUG_ENTRY=y CONFIG_CIO_INJECT=y CONFIG_KUNIT=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 9ab91632f74c..693297a2e897 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -21,7 +21,6 @@ CONFIG_NUMA_BALANCING=y CONFIG_MEMCG=y CONFIG_BLK_CGROUP=y CONFIG_CFS_BANDWIDTH=y -CONFIG_RT_GROUP_SCHED=y CONFIG_CGROUP_PIDS=y CONFIG_CGROUP_RDMA=y CONFIG_CGROUP_FREEZER=y @@ -85,7 +84,6 @@ CONFIG_MINIX_SUBPARTITION=y CONFIG_SOLARIS_X86_PARTITION=y CONFIG_UNIXWARE_DISKLABEL=y CONFIG_IOSCHED_BFQ=y -CONFIG_BFQ_GROUP_IOSCHED=y CONFIG_BINFMT_MISC=m CONFIG_ZSWAP=y CONFIG_ZSMALLOC_STAT=y @@ -289,7 +287,6 @@ CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_MANGLE=m -CONFIG_IP_NF_TARGET_CLUSTERIP=m CONFIG_IP_NF_TARGET_ECN=m CONFIG_IP_NF_TARGET_TTL=m CONFIG_IP_NF_RAW=m @@ -330,7 +327,6 @@ CONFIG_BRIDGE_MRP=y CONFIG_VLAN_8021Q=m CONFIG_VLAN_8021Q_GVRP=y CONFIG_NET_SCHED=y -CONFIG_NET_SCH_CBQ=m CONFIG_NET_SCH_HTB=m CONFIG_NET_SCH_HFSC=m CONFIG_NET_SCH_PRIO=m @@ -341,7 +337,6 @@ CONFIG_NET_SCH_SFQ=m CONFIG_NET_SCH_TEQL=m CONFIG_NET_SCH_TBF=m CONFIG_NET_SCH_GRED=m -CONFIG_NET_SCH_DSMARK=m CONFIG_NET_SCH_NETEM=m CONFIG_NET_SCH_DRR=m CONFIG_NET_SCH_MQPRIO=m @@ -353,14 +348,11 @@ CONFIG_NET_SCH_INGRESS=m CONFIG_NET_SCH_PLUG=m CONFIG_NET_SCH_ETS=m CONFIG_NET_CLS_BASIC=m -CONFIG_NET_CLS_TCINDEX=m CONFIG_NET_CLS_ROUTE4=m CONFIG_NET_CLS_FW=m CONFIG_NET_CLS_U32=m CONFIG_CLS_U32_PERF=y CONFIG_CLS_U32_MARK=y -CONFIG_NET_CLS_RSVP=m -CONFIG_NET_CLS_RSVP6=m CONFIG_NET_CLS_FLOW=m CONFIG_NET_CLS_CGROUP=y CONFIG_NET_CLS_BPF=m @@ -573,7 +565,7 @@ CONFIG_DIAG288_WATCHDOG=m CONFIG_FB=y CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y -# CONFIG_HID is not set +# CONFIG_HID_SUPPORT is not set # CONFIG_USB_SUPPORT is not set CONFIG_INFINIBAND=m CONFIG_INFINIBAND_USER_ACCESS=m @@ -795,6 +787,7 @@ CONFIG_RCU_REF_SCALE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=60 CONFIG_LATENCYTOP=y CONFIG_BOOTTIME_TRACING=y +CONFIG_FPROBE=y CONFIG_FUNCTION_PROFILER=y CONFIG_STACK_TRACER=y CONFIG_SCHED_TRACER=y @@ -805,6 +798,7 @@ CONFIG_SAMPLES=y CONFIG_SAMPLE_TRACE_PRINTK=m CONFIG_SAMPLE_FTRACE_DIRECT=m CONFIG_SAMPLE_FTRACE_DIRECT_MULTI=m +CONFIG_SAMPLE_FTRACE_OPS=m CONFIG_KUNIT=m CONFIG_KUNIT_DEBUGFS=y CONFIG_LKDTM=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index a9c0c81d1de9..33a232bb68af 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -58,7 +58,7 @@ CONFIG_ZFCP=y # CONFIG_VMCP is not set # CONFIG_MONWRITER is not set # CONFIG_S390_VMUR is not set -# CONFIG_HID is not set +# CONFIG_HID_SUPPORT is not set # CONFIG_VIRTIO_MENU is not set # CONFIG_VHOST_MENU is not set # CONFIG_IOMMU_SUPPORT is not set diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index ef38b1514c77..e16afacc8fd1 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -544,8 +544,7 @@ static struct resource *__alloc_res(struct zpci_dev *zdev, unsigned long start, return r; } -int zpci_setup_bus_resources(struct zpci_dev *zdev, - struct list_head *resources) +int zpci_setup_bus_resources(struct zpci_dev *zdev) { unsigned long addr, size, flags; struct resource *res; @@ -581,7 +580,6 @@ int zpci_setup_bus_resources(struct zpci_dev *zdev, return -ENOMEM; } zdev->bars[i].res = res; - pci_add_resource(resources, res); } zdev->has_resources = 1; @@ -590,17 +588,23 @@ int zpci_setup_bus_resources(struct zpci_dev *zdev, static void zpci_cleanup_bus_resources(struct zpci_dev *zdev) { + struct resource *res; int i; + pci_lock_rescan_remove(); for (i = 0; i < PCI_STD_NUM_BARS; i++) { - if (!zdev->bars[i].size || !zdev->bars[i].res) + res = zdev->bars[i].res; + if (!res) continue; + release_resource(res); + pci_bus_remove_resource(zdev->zbus->bus, res); zpci_free_iomap(zdev, zdev->bars[i].map_idx); - release_resource(zdev->bars[i].res); - kfree(zdev->bars[i].res); + zdev->bars[i].res = NULL; + kfree(res); } zdev->has_resources = 0; + pci_unlock_rescan_remove(); } int pcibios_device_add(struct pci_dev *pdev) diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c index 6a8da1b742ae..a99926af2b69 100644 --- a/arch/s390/pci/pci_bus.c +++ b/arch/s390/pci/pci_bus.c @@ -41,9 +41,7 @@ static int zpci_nb_devices; */ static int zpci_bus_prepare_device(struct zpci_dev *zdev) { - struct resource_entry *window, *n; - struct resource *res; - int rc; + int rc, i; if (!zdev_enabled(zdev)) { rc = zpci_enable_device(zdev); @@ -57,10 +55,10 @@ static int zpci_bus_prepare_device(struct zpci_dev *zdev) } if (!zdev->has_resources) { - zpci_setup_bus_resources(zdev, &zdev->zbus->resources); - resource_list_for_each_entry_safe(window, n, &zdev->zbus->resources) { - res = window->res; - pci_bus_add_resource(zdev->zbus->bus, res, 0); + zpci_setup_bus_resources(zdev); + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + if (zdev->bars[i].res) + pci_bus_add_resource(zdev->zbus->bus, zdev->bars[i].res, 0); } } diff --git a/arch/s390/pci/pci_bus.h b/arch/s390/pci/pci_bus.h index e96c9860e064..af9f0ac79a1b 100644 --- a/arch/s390/pci/pci_bus.h +++ b/arch/s390/pci/pci_bus.h @@ -30,8 +30,7 @@ static inline void zpci_zdev_get(struct zpci_dev *zdev) int zpci_alloc_domain(int domain); void zpci_free_domain(int domain); -int zpci_setup_bus_resources(struct zpci_dev *zdev, - struct list_head *resources); +int zpci_setup_bus_resources(struct zpci_dev *zdev); static inline struct zpci_dev *zdev_from_bus(struct pci_bus *bus, unsigned int devfn) diff --git a/arch/sh/include/asm/processor_32.h b/arch/sh/include/asm/processor_32.h index 27aebf1e75a2..3ef7adf739c8 100644 --- a/arch/sh/include/asm/processor_32.h +++ b/arch/sh/include/asm/processor_32.h @@ -50,6 +50,7 @@ #define SR_FD 0x00008000 #define SR_MD 0x40000000 +#define SR_USER_MASK 0x00000303 // M, Q, S, T bits /* * DSP structure and data */ diff --git a/arch/sh/kernel/signal_32.c b/arch/sh/kernel/signal_32.c index 90f495d35db2..a6bfc6f37491 100644 --- a/arch/sh/kernel/signal_32.c +++ b/arch/sh/kernel/signal_32.c @@ -115,6 +115,7 @@ static int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, int *r0_p) { unsigned int err = 0; + unsigned int sr = regs->sr & ~SR_USER_MASK; #define COPY(x) err |= __get_user(regs->x, &sc->sc_##x) COPY(regs[1]); @@ -130,6 +131,8 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, int *r0_p COPY(sr); COPY(pc); #undef COPY + regs->sr = (regs->sr & SR_USER_MASK) | sr; + #ifdef CONFIG_SH_FPU if (boot_cpu_data.flags & CPU_HAS_FPU) { int owned_fp; diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h index 52788f79786f..255a78d9d906 100644 --- a/arch/x86/include/asm/resctrl.h +++ b/arch/x86/include/asm/resctrl.h @@ -49,7 +49,7 @@ DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); * simple as possible. * Must be called with preemption disabled. */ -static void __resctrl_sched_in(void) +static inline void __resctrl_sched_in(struct task_struct *tsk) { struct resctrl_pqr_state *state = this_cpu_ptr(&pqr_state); u32 closid = state->default_closid; @@ -61,13 +61,13 @@ static void __resctrl_sched_in(void) * Else use the closid/rmid assigned to this cpu. */ if (static_branch_likely(&rdt_alloc_enable_key)) { - tmp = READ_ONCE(current->closid); + tmp = READ_ONCE(tsk->closid); if (tmp) closid = tmp; } if (static_branch_likely(&rdt_mon_enable_key)) { - tmp = READ_ONCE(current->rmid); + tmp = READ_ONCE(tsk->rmid); if (tmp) rmid = tmp; } @@ -88,17 +88,17 @@ static inline unsigned int resctrl_arch_round_mon_val(unsigned int val) return val * scale; } -static inline void resctrl_sched_in(void) +static inline void resctrl_sched_in(struct task_struct *tsk) { if (static_branch_likely(&rdt_enable_key)) - __resctrl_sched_in(); + __resctrl_sched_in(tsk); } void resctrl_cpu_detect(struct cpuinfo_x86 *c); #else -static inline void resctrl_sched_in(void) {} +static inline void resctrl_sched_in(struct task_struct *tsk) {} static inline void resctrl_cpu_detect(struct cpuinfo_x86 *c) {} #endif /* CONFIG_X86_CPU_RESCTRL */ diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h index b8357d6ecd47..b63be696b776 100644 --- a/arch/x86/include/asm/sev-common.h +++ b/arch/x86/include/asm/sev-common.h @@ -128,8 +128,9 @@ struct snp_psc_desc { struct psc_entry entries[VMGEXIT_PSC_MAX_ENTRY]; } __packed; -/* Guest message request error code */ +/* Guest message request error codes */ #define SNP_GUEST_REQ_INVALID_LEN BIT_ULL(32) +#define SNP_GUEST_REQ_ERR_BUSY BIT_ULL(33) #define GHCB_MSR_TERM_REQ 0x100 #define GHCB_MSR_TERM_REASON_SET_POS 12 diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index cb1ee53ad3b1..770dcf75eaa9 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -261,20 +261,22 @@ enum avic_ipi_failure_cause { AVIC_IPI_FAILURE_INVALID_BACKING_PAGE, }; -#define AVIC_PHYSICAL_MAX_INDEX_MASK GENMASK_ULL(9, 0) +#define AVIC_PHYSICAL_MAX_INDEX_MASK GENMASK_ULL(8, 0) /* - * For AVIC, the max index allowed for physical APIC ID - * table is 0xff (255). + * For AVIC, the max index allowed for physical APIC ID table is 0xfe (254), as + * 0xff is a broadcast to all CPUs, i.e. can't be targeted individually. */ #define AVIC_MAX_PHYSICAL_ID 0XFEULL /* - * For x2AVIC, the max index allowed for physical APIC ID - * table is 0x1ff (511). + * For x2AVIC, the max index allowed for physical APIC ID table is 0x1ff (511). */ #define X2AVIC_MAX_PHYSICAL_ID 0x1FFUL +static_assert((AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == AVIC_MAX_PHYSICAL_ID); +static_assert((X2AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == X2AVIC_MAX_PHYSICAL_ID); + #define AVIC_HPA_MASK ~((0xFFFULL << 52) | 0xFFF) #define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL diff --git a/arch/x86/include/asm/xen/cpuid.h b/arch/x86/include/asm/xen/cpuid.h index 6daa9b0c8d11..a3c29b1496c8 100644 --- a/arch/x86/include/asm/xen/cpuid.h +++ b/arch/x86/include/asm/xen/cpuid.h @@ -89,11 +89,21 @@ * Sub-leaf 2: EAX: host tsc frequency in kHz */ +#define XEN_CPUID_TSC_EMULATED (1u << 0) +#define XEN_CPUID_HOST_TSC_RELIABLE (1u << 1) +#define XEN_CPUID_RDTSCP_INSTR_AVAIL (1u << 2) + +#define XEN_CPUID_TSC_MODE_DEFAULT (0) +#define XEN_CPUID_TSC_MODE_ALWAYS_EMULATE (1u) +#define XEN_CPUID_TSC_MODE_NEVER_EMULATE (2u) +#define XEN_CPUID_TSC_MODE_PVRDTSCP (3u) + /* * Leaf 5 (0x40000x04) * HVM-specific features * Sub-leaf 0: EAX: Features * Sub-leaf 0: EBX: vcpu id (iff EAX has XEN_HVM_CPUID_VCPU_ID_PRESENT flag) + * Sub-leaf 0: ECX: domain id (iff EAX has XEN_HVM_CPUID_DOMID_PRESENT flag) */ #define XEN_HVM_CPUID_APIC_ACCESS_VIRT (1u << 0) /* Virtualized APIC registers */ #define XEN_HVM_CPUID_X2APIC_VIRT (1u << 1) /* Virtualized x2APIC accesses */ @@ -102,12 +112,16 @@ #define XEN_HVM_CPUID_VCPU_ID_PRESENT (1u << 3) /* vcpu id is present in EBX */ #define XEN_HVM_CPUID_DOMID_PRESENT (1u << 4) /* domid is present in ECX */ /* - * Bits 55:49 from the IO-APIC RTE and bits 11:5 from the MSI address can be - * used to store high bits for the Destination ID. This expands the Destination - * ID field from 8 to 15 bits, allowing to target APIC IDs up 32768. + * With interrupt format set to 0 (non-remappable) bits 55:49 from the + * IO-APIC RTE and bits 11:5 from the MSI address can be used to store + * high bits for the Destination ID. This expands the Destination ID + * field from 8 to 15 bits, allowing to target APIC IDs up 32768. */ #define XEN_HVM_CPUID_EXT_DEST_ID (1u << 5) -/* Per-vCPU event channel upcalls */ +/* + * Per-vCPU event channel upcalls work correctly with physical IRQs + * bound to event channels. + */ #define XEN_HVM_CPUID_UPCALL_VECTOR (1u << 6) /* diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 380753b14cab..95cdd08c4cbb 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -880,6 +880,15 @@ void init_spectral_chicken(struct cpuinfo_x86 *c) } } #endif + /* + * Work around Erratum 1386. The XSAVES instruction malfunctions in + * certain circumstances on Zen1/2 uarch, and not all parts have had + * updated microcode at the time of writing (March 2023). + * + * Affected parts all have no supervisor XSAVE states, meaning that + * the XSAVEC instruction (which works fine) is equivalent. + */ + clear_cpu_cap(c, X86_FEATURE_XSAVES); } static void init_amd_zn(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 7832a69d170e..2eec60f50057 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -2355,6 +2355,7 @@ static void mce_restart(void) { mce_timer_delete_all(); on_each_cpu(mce_cpu_restart, NULL, 1); + mce_schedule_work(); } /* Toggle features for corrected errors */ diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index eb07d4435391..b44c487727d4 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -368,7 +368,6 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, { struct resctrl_schema *s; struct rdtgroup *rdtgrp; - struct rdt_domain *dom; struct rdt_resource *r; char *tok, *resname; int ret = 0; @@ -397,10 +396,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, goto out; } - list_for_each_entry(s, &resctrl_schema_all, list) { - list_for_each_entry(dom, &s->res->domains, list) - memset(dom->staged_config, 0, sizeof(dom->staged_config)); - } + rdt_staged_configs_clear(); while ((tok = strsep(&buf, "\n")) != NULL) { resname = strim(strsep(&tok, ":")); @@ -445,6 +441,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, } out: + rdt_staged_configs_clear(); rdtgroup_kn_unlock(of->kn); cpus_read_unlock(); return ret ?: nbytes; diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 8edecc5763d8..85ceaf9a31ac 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -555,5 +555,6 @@ void __check_limbo(struct rdt_domain *d, bool force_free); void rdt_domain_reconfigure_cdp(struct rdt_resource *r); void __init thread_throttle_mode_init(void); void __init mbm_config_rftype_init(const char *config); +void rdt_staged_configs_clear(void); #endif /* _ASM_X86_RESCTRL_INTERNAL_H */ diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index e2c1599d1b37..6ad33f355861 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -78,6 +78,19 @@ void rdt_last_cmd_printf(const char *fmt, ...) va_end(ap); } +void rdt_staged_configs_clear(void) +{ + struct rdt_resource *r; + struct rdt_domain *dom; + + lockdep_assert_held(&rdtgroup_mutex); + + for_each_alloc_capable_rdt_resource(r) { + list_for_each_entry(dom, &r->domains, list) + memset(dom->staged_config, 0, sizeof(dom->staged_config)); + } +} + /* * Trivial allocator for CLOSIDs. Since h/w only supports a small number, * we can keep a bitmap of free CLOSIDs in a single integer. @@ -314,7 +327,7 @@ static void update_cpu_closid_rmid(void *info) * executing task might have its own closid selected. Just reuse * the context switch code. */ - resctrl_sched_in(); + resctrl_sched_in(current); } /* @@ -530,7 +543,7 @@ static void _update_task_closid_rmid(void *task) * Otherwise, the MSR is updated when the task is scheduled in. */ if (task == current) - resctrl_sched_in(); + resctrl_sched_in(task); } static void update_task_closid_rmid(struct task_struct *t) @@ -3107,7 +3120,9 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) { struct resctrl_schema *s; struct rdt_resource *r; - int ret; + int ret = 0; + + rdt_staged_configs_clear(); list_for_each_entry(s, &resctrl_schema_all, list) { r = s->res; @@ -3119,20 +3134,22 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) } else { ret = rdtgroup_init_cat(s, rdtgrp->closid); if (ret < 0) - return ret; + goto out; } ret = resctrl_arch_update_domains(r, rdtgrp->closid); if (ret < 0) { rdt_last_cmd_puts("Failed to initialize allocations\n"); - return ret; + goto out; } } rdtgrp->mode = RDT_MODE_SHAREABLE; - return 0; +out: + rdt_staged_configs_clear(); + return ret; } static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 1265ad519249..fb4f1e01b64a 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -136,10 +136,12 @@ SYM_TYPED_FUNC_START(ftrace_stub) RET SYM_FUNC_END(ftrace_stub) +#ifdef CONFIG_FUNCTION_GRAPH_TRACER SYM_TYPED_FUNC_START(ftrace_stub_graph) CALL_DEPTH_ACCOUNT RET SYM_FUNC_END(ftrace_stub_graph) +#endif #ifdef CONFIG_DYNAMIC_FTRACE diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 470c128759ea..708c87b88cc1 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -212,7 +212,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) switch_fpu_finish(); /* Load the Intel cache allocation PQR MSR. */ - resctrl_sched_in(); + resctrl_sched_in(next_p); return prev_p; } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 4e34b3b68ebd..bb65a68b4b49 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -656,7 +656,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) } /* Load the Intel cache allocation PQR MSR. */ - resctrl_sched_in(); + resctrl_sched_in(next_p); return prev_p; } diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index 679026a640ef..3f664ab277c4 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -2183,9 +2183,6 @@ int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned struct ghcb *ghcb; int ret; - if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) - return -ENODEV; - if (!fw_err) return -EINVAL; @@ -2212,15 +2209,26 @@ int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned if (ret) goto e_put; - if (ghcb->save.sw_exit_info_2) { - /* Number of expected pages are returned in RBX */ - if (exit_code == SVM_VMGEXIT_EXT_GUEST_REQUEST && - ghcb->save.sw_exit_info_2 == SNP_GUEST_REQ_INVALID_LEN) - input->data_npages = ghcb_get_rbx(ghcb); + *fw_err = ghcb->save.sw_exit_info_2; + switch (*fw_err) { + case 0: + break; - *fw_err = ghcb->save.sw_exit_info_2; + case SNP_GUEST_REQ_ERR_BUSY: + ret = -EAGAIN; + break; + case SNP_GUEST_REQ_INVALID_LEN: + /* Number of expected pages are returned in RBX */ + if (exit_code == SVM_VMGEXIT_EXT_GUEST_REQUEST) { + input->data_npages = ghcb_get_rbx(ghcb); + ret = -ENOSPC; + break; + } + fallthrough; + default: ret = -EIO; + break; } e_put: diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index ca684979e90d..cfc8ab773025 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -27,19 +27,38 @@ #include "irq.h" #include "svm.h" -/* AVIC GATAG is encoded using VM and VCPU IDs */ -#define AVIC_VCPU_ID_BITS 8 -#define AVIC_VCPU_ID_MASK ((1 << AVIC_VCPU_ID_BITS) - 1) +/* + * Encode the arbitrary VM ID and the vCPU's default APIC ID, i.e the vCPU ID, + * into the GATag so that KVM can retrieve the correct vCPU from a GALog entry + * if an interrupt can't be delivered, e.g. because the vCPU isn't running. + * + * For the vCPU ID, use however many bits are currently allowed for the max + * guest physical APIC ID (limited by the size of the physical ID table), and + * use whatever bits remain to assign arbitrary AVIC IDs to VMs. Note, the + * size of the GATag is defined by hardware (32 bits), but is an opaque value + * as far as hardware is concerned. + */ +#define AVIC_VCPU_ID_MASK AVIC_PHYSICAL_MAX_INDEX_MASK -#define AVIC_VM_ID_BITS 24 -#define AVIC_VM_ID_NR (1 << AVIC_VM_ID_BITS) -#define AVIC_VM_ID_MASK ((1 << AVIC_VM_ID_BITS) - 1) +#define AVIC_VM_ID_SHIFT HWEIGHT32(AVIC_PHYSICAL_MAX_INDEX_MASK) +#define AVIC_VM_ID_MASK (GENMASK(31, AVIC_VM_ID_SHIFT) >> AVIC_VM_ID_SHIFT) -#define AVIC_GATAG(x, y) (((x & AVIC_VM_ID_MASK) << AVIC_VCPU_ID_BITS) | \ - (y & AVIC_VCPU_ID_MASK)) -#define AVIC_GATAG_TO_VMID(x) ((x >> AVIC_VCPU_ID_BITS) & AVIC_VM_ID_MASK) +#define AVIC_GATAG_TO_VMID(x) ((x >> AVIC_VM_ID_SHIFT) & AVIC_VM_ID_MASK) #define AVIC_GATAG_TO_VCPUID(x) (x & AVIC_VCPU_ID_MASK) +#define __AVIC_GATAG(vm_id, vcpu_id) ((((vm_id) & AVIC_VM_ID_MASK) << AVIC_VM_ID_SHIFT) | \ + ((vcpu_id) & AVIC_VCPU_ID_MASK)) +#define AVIC_GATAG(vm_id, vcpu_id) \ +({ \ + u32 ga_tag = __AVIC_GATAG(vm_id, vcpu_id); \ + \ + WARN_ON_ONCE(AVIC_GATAG_TO_VCPUID(ga_tag) != (vcpu_id)); \ + WARN_ON_ONCE(AVIC_GATAG_TO_VMID(ga_tag) != (vm_id)); \ + ga_tag; \ +}) + +static_assert(__AVIC_GATAG(AVIC_VM_ID_MASK, AVIC_VCPU_ID_MASK) == -1u); + static bool force_avic; module_param_unsafe(force_avic, bool, 0444); diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 7c4f5ca405c7..1bc2b80273c9 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2903,7 +2903,7 @@ static int nested_vmx_check_address_space_size(struct kvm_vcpu *vcpu, static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - bool ia32e; + bool ia32e = !!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE); if (CC(!nested_host_cr0_valid(vcpu, vmcs12->host_cr0)) || CC(!nested_host_cr4_valid(vcpu, vmcs12->host_cr4)) || @@ -2923,12 +2923,6 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, vmcs12->host_ia32_perf_global_ctrl))) return -EINVAL; -#ifdef CONFIG_X86_64 - ia32e = !!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE); -#else - ia32e = false; -#endif - if (ia32e) { if (CC(!(vmcs12->host_cr4 & X86_CR4_PAE))) return -EINVAL; @@ -3022,7 +3016,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, enum vm_entry_failure_code *entry_failure_code) { - bool ia32e; + bool ia32e = !!(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE); *entry_failure_code = ENTRY_FAIL_DEFAULT; @@ -3048,6 +3042,13 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, vmcs12->guest_ia32_perf_global_ctrl))) return -EINVAL; + if (CC((vmcs12->guest_cr0 & (X86_CR0_PG | X86_CR0_PE)) == X86_CR0_PG)) + return -EINVAL; + + if (CC(ia32e && !(vmcs12->guest_cr4 & X86_CR4_PAE)) || + CC(ia32e && !(vmcs12->guest_cr0 & X86_CR0_PG))) + return -EINVAL; + /* * If the load IA32_EFER VM-entry control is 1, the following checks * are performed on the field for the IA32_EFER MSR: @@ -3059,7 +3060,6 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, */ if (to_vmx(vcpu)->nested.nested_run_pending && (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)) { - ia32e = (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) != 0; if (CC(!kvm_valid_efer(vcpu, vmcs12->guest_ia32_efer)) || CC(ia32e != !!(vmcs12->guest_ia32_efer & EFER_LMA)) || CC(((vmcs12->guest_cr0 & X86_CR0_PG) && diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index f550540ed54e..631fd7da2bc3 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -262,7 +262,7 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL) * eIBRS has its own protection against poisoned RSB, so it doesn't * need the RSB filling sequence. But it does need to be enabled, and a * single call to retire, before the first unbalanced RET. - */ + */ FILL_RETURN_BUFFER %_ASM_CX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT,\ X86_FEATURE_RSB_VMEXIT_LITE @@ -311,7 +311,7 @@ SYM_FUNC_END(vmx_do_nmi_irqoff) * vmread_error_trampoline - Trampoline from inline asm to vmread_error() * @field: VMCS field encoding that failed * @fault: %true if the VMREAD faulted, %false if it failed - + * * Save and restore volatile registers across a call to vmread_error(). Note, * all parameters are passed on the stack. */ diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index bcac3efcde41..d2d6e1b6c788 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -874,7 +874,7 @@ void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu) */ if (is_guest_mode(vcpu)) eb |= get_vmcs12(vcpu)->exception_bitmap; - else { + else { int mask = 0, match = 0; if (enable_ept && (eb & (1u << PF_VECTOR))) { @@ -1282,7 +1282,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) } } - if (vmx->nested.need_vmcs12_to_shadow_sync) + if (vmx->nested.need_vmcs12_to_shadow_sync) nested_sync_vmcs12_to_shadow(vcpu); if (vmx->guest_state_loaded) @@ -5049,10 +5049,10 @@ static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) if (to_vmx(vcpu)->nested.nested_run_pending) return -EBUSY; - /* - * An IRQ must not be injected into L2 if it's supposed to VM-Exit, - * e.g. if the IRQ arrived asynchronously after checking nested events. - */ + /* + * An IRQ must not be injected into L2 if it's supposed to VM-Exit, + * e.g. if the IRQ arrived asynchronously after checking nested events. + */ if (for_injection && is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) return -EBUSY; diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index 88cccd65029d..c6efcf559d88 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -600,7 +600,8 @@ void __init sme_enable(struct boot_params *bp) cmdline_ptr = (const char *)((u64)bp->hdr.cmd_line_ptr | ((u64)bp->ext_cmd_line_ptr << 32)); - cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)); + if (cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)) < 0) + return; if (!strncmp(buffer, cmdline_on, sizeof(buffer))) sme_me_mask = me_mask; diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 3c5b52fbe4a7..a9ec8c9f5c5d 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -45,6 +45,6 @@ obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o -obj-$(CONFIG_XEN_PV_DOM0) += vga.o +obj-$(CONFIG_XEN_DOM0) += vga.o obj-$(CONFIG_XEN_EFI) += efi.o diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index bb59cc6ddb2d..093b78c8bbec 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1390,7 +1390,8 @@ asmlinkage __visible void __init xen_start_kernel(struct start_info *si) x86_platform.set_legacy_features = xen_dom0_set_legacy_features; - xen_init_vga(info, xen_start_info->console.dom0.info_size); + xen_init_vga(info, xen_start_info->console.dom0.info_size, + &boot_params.screen_info); xen_start_info->console.domU.mfn = 0; xen_start_info->console.domU.evtchn = 0; diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index bcae606bbc5c..1da44aca896c 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -43,6 +43,19 @@ void __init xen_pvh_init(struct boot_params *boot_params) x86_init.oem.banner = xen_banner; xen_efi_init(boot_params); + + if (xen_initial_domain()) { + struct xen_platform_op op = { + .cmd = XENPF_get_dom0_console, + }; + long ret = HYPERVISOR_platform_op(&op); + + if (ret > 0) + xen_init_vga(&op.u.dom0_console, + min(ret * sizeof(char), + sizeof(op.u.dom0_console)), + &boot_params->screen_info); + } } void __init mem_map_via_hcall(struct boot_params *boot_params_p) diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 1d597364b49d..b74ac2562cfb 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -20,6 +20,7 @@ #include <asm/pvclock.h> #include <asm/xen/hypervisor.h> #include <asm/xen/hypercall.h> +#include <asm/xen/cpuid.h> #include <xen/events.h> #include <xen/features.h> @@ -503,11 +504,7 @@ static int __init xen_tsc_safe_clocksource(void) /* Leaf 4, sub-leaf 0 (0x40000x03) */ cpuid_count(xen_cpuid_base() + 3, 0, &eax, &ebx, &ecx, &edx); - /* tsc_mode = no_emulate (2) */ - if (ebx != 2) - return 0; - - return 1; + return ebx == XEN_CPUID_TSC_MODE_NEVER_EMULATE; } static void __init xen_time_init(void) diff --git a/arch/x86/xen/vga.c b/arch/x86/xen/vga.c index 14ea32e734d5..d97adab8420f 100644 --- a/arch/x86/xen/vga.c +++ b/arch/x86/xen/vga.c @@ -9,10 +9,9 @@ #include "xen-ops.h" -void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size) +void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size, + struct screen_info *screen_info) { - struct screen_info *screen_info = &boot_params.screen_info; - /* This is drawn from a dump from vgacon:startup in * standard Linux. */ screen_info->orig_video_mode = 3; diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 9a8bb972193d..a10903785a33 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -108,11 +108,12 @@ static inline void xen_uninit_lock_cpu(int cpu) struct dom0_vga_console_info; -#ifdef CONFIG_XEN_PV_DOM0 -void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size); +#ifdef CONFIG_XEN_DOM0 +void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size, + struct screen_info *); #else static inline void __init xen_init_vga(const struct dom0_vga_console_info *info, - size_t size) + size_t size, struct screen_info *si) { } #endif |