From baa035227b2e8b4bfba8f6176dc06c60477f1634 Mon Sep 17 00:00:00 2001 From: Tiejun Chen Date: Tue, 23 Dec 2014 16:21:11 +0800 Subject: kvm: x86: vmx: reorder some msr writing The commit 34a1cd60d17f, "x86: vmx: move some vmx setting from vmx_init() to hardware_setup()", tried to refactor some codes specific to vmx hardware setting into hardware_setup(), but some msr writing should depend on our previous setting condition like enable_apicv, enable_ept and so on. Reported-by: Jamie Heilman Tested-by: Jamie Heilman Signed-off-by: Tiejun Chen Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx.c | 88 +++++++++++++++++++++++++++--------------------------- 1 file changed, 44 insertions(+), 44 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index feb852b04598..d4c58d884838 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -5840,53 +5840,10 @@ static __init int hardware_setup(void) memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE); memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE); - vmx_disable_intercept_for_msr(MSR_FS_BASE, false); - vmx_disable_intercept_for_msr(MSR_GS_BASE, false); - vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false); - vmx_disable_intercept_for_msr(MSR_IA32_BNDCFGS, true); - - memcpy(vmx_msr_bitmap_legacy_x2apic, - vmx_msr_bitmap_legacy, PAGE_SIZE); - memcpy(vmx_msr_bitmap_longmode_x2apic, - vmx_msr_bitmap_longmode, PAGE_SIZE); - - if (enable_apicv) { - for (msr = 0x800; msr <= 0x8ff; msr++) - vmx_disable_intercept_msr_read_x2apic(msr); - - /* According SDM, in x2apic mode, the whole id reg is used. - * But in KVM, it only use the highest eight bits. Need to - * intercept it */ - vmx_enable_intercept_msr_read_x2apic(0x802); - /* TMCCT */ - vmx_enable_intercept_msr_read_x2apic(0x839); - /* TPR */ - vmx_disable_intercept_msr_write_x2apic(0x808); - /* EOI */ - vmx_disable_intercept_msr_write_x2apic(0x80b); - /* SELF-IPI */ - vmx_disable_intercept_msr_write_x2apic(0x83f); - } - - if (enable_ept) { - kvm_mmu_set_mask_ptes(0ull, - (enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull, - (enable_ept_ad_bits) ? VMX_EPT_DIRTY_BIT : 0ull, - 0ull, VMX_EPT_EXECUTABLE_MASK); - ept_set_mmio_spte_mask(); - kvm_enable_tdp(); - } else - kvm_disable_tdp(); - - update_ple_window_actual_max(); - if (setup_vmcs_config(&vmcs_config) < 0) { r = -EIO; goto out7; - } + } if (boot_cpu_has(X86_FEATURE_NX)) kvm_enable_efer_bits(EFER_NX); @@ -5945,6 +5902,49 @@ static __init int hardware_setup(void) if (nested) nested_vmx_setup_ctls_msrs(); + vmx_disable_intercept_for_msr(MSR_FS_BASE, false); + vmx_disable_intercept_for_msr(MSR_GS_BASE, false); + vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true); + vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false); + vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false); + vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false); + vmx_disable_intercept_for_msr(MSR_IA32_BNDCFGS, true); + + memcpy(vmx_msr_bitmap_legacy_x2apic, + vmx_msr_bitmap_legacy, PAGE_SIZE); + memcpy(vmx_msr_bitmap_longmode_x2apic, + vmx_msr_bitmap_longmode, PAGE_SIZE); + + if (enable_apicv) { + for (msr = 0x800; msr <= 0x8ff; msr++) + vmx_disable_intercept_msr_read_x2apic(msr); + + /* According SDM, in x2apic mode, the whole id reg is used. + * But in KVM, it only use the highest eight bits. Need to + * intercept it */ + vmx_enable_intercept_msr_read_x2apic(0x802); + /* TMCCT */ + vmx_enable_intercept_msr_read_x2apic(0x839); + /* TPR */ + vmx_disable_intercept_msr_write_x2apic(0x808); + /* EOI */ + vmx_disable_intercept_msr_write_x2apic(0x80b); + /* SELF-IPI */ + vmx_disable_intercept_msr_write_x2apic(0x83f); + } + + if (enable_ept) { + kvm_mmu_set_mask_ptes(0ull, + (enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull, + (enable_ept_ad_bits) ? VMX_EPT_DIRTY_BIT : 0ull, + 0ull, VMX_EPT_EXECUTABLE_MASK); + ept_set_mmio_spte_mask(); + kvm_enable_tdp(); + } else + kvm_disable_tdp(); + + update_ple_window_actual_max(); + return alloc_kvm_area(); out7: -- cgit v1.2.3 From a629df7eadffb03e6ce4a8616e62ea29fdf69b6b Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 22 Dec 2014 10:43:39 +0100 Subject: kvm: x86: drop severity of "generation wraparound" message Since most virtual machines raise this message once, it is a bit annoying. Make it KERN_DEBUG severity. Cc: stable@vger.kernel.org Fixes: 7a2e8aaf0f6873b47bc2347f216ea5b0e4c258ab Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 10fbed126b11..f83fc6c5e0ba 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4448,7 +4448,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm) * zap all shadow pages. */ if (unlikely(kvm_current_mmio_generation(kvm) == 0)) { - printk_ratelimited(KERN_INFO "kvm: zapping shadow pages for mmio generation wraparound\n"); + printk_ratelimited(KERN_DEBUG "kvm: zapping shadow pages for mmio generation wraparound\n"); kvm_mmu_invalidate_zap_all_pages(kvm); } } -- cgit v1.2.3 From b485342bd79af363c77ef1a421c4a0aef2de9812 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 3 Jan 2015 13:11:10 +0100 Subject: x86, um: actually mark system call tables readonly Commit a074335a370e ("x86, um: Mark system call tables readonly") was supposed to mark the sys_call_table in UML as RO by adding the const, but it doesn't have the desired effect as it's nevertheless being placed into the data section since __cacheline_aligned enforces sys_call_table being placed into .data..cacheline_aligned instead. We need to use the ____cacheline_aligned version instead to fix this issue. Before: $ nm -v arch/x86/um/sys_call_table_64.o | grep -1 "sys_call_table" U sys_writev 0000000000000000 D sys_call_table 0000000000000000 D syscall_table_size After: $ nm -v arch/x86/um/sys_call_table_64.o | grep -1 "sys_call_table" U sys_writev 0000000000000000 R sys_call_table 0000000000000000 D syscall_table_size Fixes: a074335a370e ("x86, um: Mark system call tables readonly") Cc: H. Peter Anvin Cc: Andrew Morton Signed-off-by: Daniel Borkmann Signed-off-by: Richard Weinberger --- arch/x86/um/sys_call_table_32.c | 2 +- arch/x86/um/sys_call_table_64.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c index 531d4269e2e3..bd16d6c370ec 100644 --- a/arch/x86/um/sys_call_table_32.c +++ b/arch/x86/um/sys_call_table_32.c @@ -34,7 +34,7 @@ typedef asmlinkage void (*sys_call_ptr_t)(void); extern asmlinkage void sys_ni_syscall(void); -const sys_call_ptr_t sys_call_table[] __cacheline_aligned = { +const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = { /* * Smells like a compiler bug -- it doesn't work * when the & below is removed. diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c index 20c3649d0691..5cdfa9db2217 100644 --- a/arch/x86/um/sys_call_table_64.c +++ b/arch/x86/um/sys_call_table_64.c @@ -47,7 +47,7 @@ typedef void (*sys_call_ptr_t)(void); extern void sys_ni_syscall(void); -const sys_call_ptr_t sys_call_table[] __cacheline_aligned = { +const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = { /* * Smells like a compiler bug -- it doesn't work * when the & below is removed. -- cgit v1.2.3 From cbf6ab52add20b845f903decc973afbd5463c527 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Mon, 5 Jan 2015 19:29:32 +0800 Subject: kprobes: Pass the original kprobe for preparing optimized kprobe Pass the original kprobe for preparing an optimized kprobe arch-dep part, since for some architecture (e.g. ARM32) requires the information in original kprobe. Signed-off-by: Masami Hiramatsu Signed-off-by: Wang Nan Signed-off-by: Jon Medhurst --- arch/x86/kernel/kprobes/opt.c | 3 ++- include/linux/kprobes.h | 3 ++- kernel/kprobes.c | 4 ++-- 3 files changed, 6 insertions(+), 4 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 7c523bbf3dc8..0dd8d089c315 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -322,7 +322,8 @@ void arch_remove_optimized_kprobe(struct optimized_kprobe *op) * Target instructions MUST be relocatable (checked inside) * This is called when new aggr(opt)probe is allocated or reused. */ -int arch_prepare_optimized_kprobe(struct optimized_kprobe *op) +int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, + struct kprobe *__unused) { u8 *buf; int ret; diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 5297f9fa0ef2..1ab54754a86d 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -308,7 +308,8 @@ struct optimized_kprobe { /* Architecture dependent functions for direct jump optimization */ extern int arch_prepared_optinsn(struct arch_optimized_insn *optinsn); extern int arch_check_optimized_kprobe(struct optimized_kprobe *op); -extern int arch_prepare_optimized_kprobe(struct optimized_kprobe *op); +extern int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, + struct kprobe *orig); extern void arch_remove_optimized_kprobe(struct optimized_kprobe *op); extern void arch_optimize_kprobes(struct list_head *oplist); extern void arch_unoptimize_kprobes(struct list_head *oplist, diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 06f58309fed2..bad4e959f2f7 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -717,7 +717,7 @@ static void prepare_optimized_kprobe(struct kprobe *p) struct optimized_kprobe *op; op = container_of(p, struct optimized_kprobe, kp); - arch_prepare_optimized_kprobe(op); + arch_prepare_optimized_kprobe(op, p); } /* Allocate new optimized_kprobe and try to prepare optimized instructions */ @@ -731,7 +731,7 @@ static struct kprobe *alloc_aggr_kprobe(struct kprobe *p) INIT_LIST_HEAD(&op->list); op->kp.addr = p->addr; - arch_prepare_optimized_kprobe(op); + arch_prepare_optimized_kprobe(op, p); return &op->kp; } -- cgit v1.2.3