diff options
| author | Mario Preksavec <mario@slackware.hr> | 2018-08-25 14:16:23 +0200 |
|---|---|---|
| committer | Willy Sudiarto Raharjo <willysr@slackbuilds.org> | 2018-09-01 07:32:30 +0700 |
| commit | 9be84725e758c71832b27d3b3918cd67cc65f182 (patch) | |
| tree | 7617b9cb8c97051797f9464a2b0e396a1b303d20 | |
| parent | 78ff47b691fb8043946cb8bcc3b820b7369d9d7f (diff) | |
system/xen: Updated for version 4.11.0
Signed-off-by: Mario Preksavec <mario@slackware.hr>
19 files changed, 4126 insertions, 3936 deletions
diff --git a/system/xen/dom0/README.dom0 b/system/xen/dom0/README.dom0 index 09f8373b8c2fa..025189788bfe0 100644 --- a/system/xen/dom0/README.dom0 +++ b/system/xen/dom0/README.dom0 @@ -46,7 +46,7 @@ Xen EFI binary. To make things a bit easier, a copy of Xen EFI binary can be found here: - http://slackware.hr/~mario/xen/xen-4.10.1.efi.gz + http://slackware.hr/~mario/xen/xen-4.11.0.efi.gz If an automatic boot to Xen kernel is desired, the binary should be renamed and copied to the following location: /boot/efi/EFI/BOOT/bootx64.efi diff --git a/system/xen/dom0/kernel-xen.sh b/system/xen/dom0/kernel-xen.sh index 74075da12d8a4..0829676da6347 100644 --- a/system/xen/dom0/kernel-xen.sh +++ b/system/xen/dom0/kernel-xen.sh @@ -6,7 +6,7 @@ # Modified by Mario Preksavec <mario@slackware.hr> KERNEL=${KERNEL:-4.4.118} -XEN=${XEN:-4.10.1} +XEN=${XEN:-4.11.0} BOOTLOADER=${BOOTLOADER:-lilo} ROOTMOD=${ROOTMOD:-ext4} diff --git a/system/xen/patches/xen-4.10.2-pre.patch b/system/xen/patches/xen-4.10.2-pre.patch deleted file mode 100644 index 42477696e15fa..0000000000000 --- a/system/xen/patches/xen-4.10.2-pre.patch +++ /dev/null @@ -1,1631 +0,0 @@ -diff --git a/tools/libacpi/Makefile b/tools/libacpi/Makefile -index a47a658a25..c17f3924cc 100644 ---- a/tools/libacpi/Makefile -+++ b/tools/libacpi/Makefile -@@ -43,7 +43,7 @@ all: $(C_SRC) $(H_SRC) - - $(H_SRC): $(ACPI_BUILD_DIR)/%.h: %.asl iasl - iasl -vs -p $(ACPI_BUILD_DIR)/$*.$(TMP_SUFFIX) -tc $< -- sed -e 's/AmlCode/$*/g' $(ACPI_BUILD_DIR)/$*.hex >$@ -+ sed -e 's/AmlCode/$*/g' -e 's/_aml_code//g' $(ACPI_BUILD_DIR)/$*.hex >$@ - rm -f $(addprefix $(ACPI_BUILD_DIR)/, $*.aml $*.hex) - - $(MK_DSDT): mk_dsdt.c -@@ -76,7 +76,7 @@ $(ACPI_BUILD_DIR)/dsdt_anycpu_arm.asl: $(MK_DSDT) - - $(C_SRC): $(ACPI_BUILD_DIR)/%.c: iasl $(ACPI_BUILD_DIR)/%.asl - iasl -vs -p $(ACPI_BUILD_DIR)/$*.$(TMP_SUFFIX) -tc $(ACPI_BUILD_DIR)/$*.asl -- sed -e 's/AmlCode/$*/g' $(ACPI_BUILD_DIR)/$*.hex > $@.$(TMP_SUFFIX) -+ sed -e 's/AmlCode/$*/g' -e 's/_aml_code//g' $(ACPI_BUILD_DIR)/$*.hex > $@.$(TMP_SUFFIX) - echo "int $*_len=sizeof($*);" >> $@.$(TMP_SUFFIX) - mv -f $@.$(TMP_SUFFIX) $@ - rm -f $(addprefix $(ACPI_BUILD_DIR)/, $*.aml $*.hex) -#diff --git a/xen/Makefile b/xen/Makefile -#index ecec297b9b..580af86931 100644 -#--- a/xen/Makefile -#+++ b/xen/Makefile -#@@ -2,7 +2,7 @@ -# # All other places this is stored (eg. compile.h) should be autogenerated. -# export XEN_VERSION = 4 -# export XEN_SUBVERSION = 10 -#-export XEN_EXTRAVERSION ?= .1$(XEN_VENDORVERSION) -#+export XEN_EXTRAVERSION ?= .2-pre$(XEN_VENDORVERSION) -# export XEN_FULLVERSION = $(XEN_VERSION).$(XEN_SUBVERSION)$(XEN_EXTRAVERSION) -# -include xen-version -# -diff --git a/xen/arch/x86/acpi/power.c b/xen/arch/x86/acpi/power.c -index 1e4e5680a7..f7085d3c7b 100644 ---- a/xen/arch/x86/acpi/power.c -+++ b/xen/arch/x86/acpi/power.c -@@ -28,6 +28,7 @@ - #include <asm/tboot.h> - #include <asm/apic.h> - #include <asm/io_apic.h> -+#include <asm/spec_ctrl.h> - #include <acpi/cpufreq/cpufreq.h> - - uint32_t system_reset_counter = 1; -@@ -163,6 +164,7 @@ static int enter_state(u32 state) - { - unsigned long flags; - int error; -+ struct cpu_info *ci; - unsigned long cr4; - - if ( (state <= ACPI_STATE_S0) || (state > ACPI_S_STATES_MAX) ) -@@ -203,12 +205,18 @@ static int enter_state(u32 state) - printk(XENLOG_ERR "Some devices failed to power down."); - system_state = SYS_STATE_resume; - device_power_up(error); -+ console_end_sync(); - error = -EIO; - goto done; - } - else - error = 0; - -+ ci = get_cpu_info(); -+ spec_ctrl_enter_idle(ci); -+ /* Avoid NMI/#MC using MSR_SPEC_CTRL until we've reloaded microcode. */ -+ ci->bti_ist_info = 0; -+ - ACPI_FLUSH_CPU_CACHE(); - - switch ( state ) -@@ -243,17 +251,23 @@ static int enter_state(u32 state) - if ( (state == ACPI_STATE_S3) && error ) - tboot_s3_error(error); - -+ console_end_sync(); -+ -+ microcode_resume_cpu(0); -+ -+ /* Re-enabled default NMI/#MC use of MSR_SPEC_CTRL. */ -+ ci->bti_ist_info = default_bti_ist_info; -+ spec_ctrl_exit_idle(ci); -+ - done: - spin_debug_enable(); - local_irq_restore(flags); -- console_end_sync(); - acpi_sleep_post(state); - if ( hvm_cpu_up() ) - BUG(); -+ cpufreq_add_cpu(0); - - enable_cpu: -- cpufreq_add_cpu(0); -- microcode_resume_cpu(0); - rcu_barrier(); - mtrr_aps_sync_begin(); - enable_nonboot_cpus(); -diff --git a/xen/arch/x86/cpu/common.c b/xen/arch/x86/cpu/common.c -index fdb2bf1779..136adadb63 100644 ---- a/xen/arch/x86/cpu/common.c -+++ b/xen/arch/x86/cpu/common.c -@@ -747,6 +747,7 @@ void load_system_tables(void) - [IST_MCE - 1] = stack_top + IST_MCE * PAGE_SIZE, - [IST_DF - 1] = stack_top + IST_DF * PAGE_SIZE, - [IST_NMI - 1] = stack_top + IST_NMI * PAGE_SIZE, -+ [IST_DB - 1] = stack_top + IST_DB * PAGE_SIZE, - - [IST_MAX ... ARRAY_SIZE(tss->ist) - 1] = - 0x8600111111111111ul, -@@ -774,6 +775,7 @@ void load_system_tables(void) - set_ist(&idt_tables[cpu][TRAP_double_fault], IST_DF); - set_ist(&idt_tables[cpu][TRAP_nmi], IST_NMI); - set_ist(&idt_tables[cpu][TRAP_machine_check], IST_MCE); -+ set_ist(&idt_tables[cpu][TRAP_debug], IST_DB); - - /* - * Bottom-of-stack must be 16-byte aligned! -diff --git a/xen/arch/x86/hpet.c b/xen/arch/x86/hpet.c -index 8229c635e4..f18cbbd55a 100644 ---- a/xen/arch/x86/hpet.c -+++ b/xen/arch/x86/hpet.c -@@ -509,6 +509,8 @@ static void hpet_attach_channel(unsigned int cpu, - static void hpet_detach_channel(unsigned int cpu, - struct hpet_event_channel *ch) - { -+ unsigned int next; -+ - spin_lock_irq(&ch->lock); - - ASSERT(ch == per_cpu(cpu_bc_channel, cpu)); -@@ -517,7 +519,7 @@ static void hpet_detach_channel(unsigned int cpu, - - if ( cpu != ch->cpu ) - spin_unlock_irq(&ch->lock); -- else if ( cpumask_empty(ch->cpumask) ) -+ else if ( (next = cpumask_first(ch->cpumask)) >= nr_cpu_ids ) - { - ch->cpu = -1; - clear_bit(HPET_EVT_USED_BIT, &ch->flags); -@@ -525,7 +527,7 @@ static void hpet_detach_channel(unsigned int cpu, - } - else - { -- ch->cpu = cpumask_first(ch->cpumask); -+ ch->cpu = next; - set_channel_irq_affinity(ch); - local_irq_enable(); - } -diff --git a/xen/arch/x86/hvm/emulate.c b/xen/arch/x86/hvm/emulate.c -index b282089e03..131480fdd9 100644 ---- a/xen/arch/x86/hvm/emulate.c -+++ b/xen/arch/x86/hvm/emulate.c -@@ -2113,22 +2113,20 @@ static int _hvm_emulate_one(struct hvm_emulate_ctxt *hvmemul_ctxt, - - vio->mmio_retry = 0; - -- switch ( rc = x86_emulate(&hvmemul_ctxt->ctxt, ops) ) -+ rc = x86_emulate(&hvmemul_ctxt->ctxt, ops); -+ if ( rc == X86EMUL_OKAY && vio->mmio_retry ) -+ rc = X86EMUL_RETRY; -+ -+ if ( !hvm_vcpu_io_need_completion(vio) ) - { -- case X86EMUL_OKAY: -- if ( vio->mmio_retry ) -- rc = X86EMUL_RETRY; -- /* fall through */ -- default: - vio->mmio_cache_count = 0; - vio->mmio_insn_bytes = 0; -- break; -- -- case X86EMUL_RETRY: -+ } -+ else -+ { - BUILD_BUG_ON(sizeof(vio->mmio_insn) < sizeof(hvmemul_ctxt->insn_buf)); - vio->mmio_insn_bytes = hvmemul_ctxt->insn_buf_bytes; - memcpy(vio->mmio_insn, hvmemul_ctxt->insn_buf, vio->mmio_insn_bytes); -- break; - } - - if ( hvmemul_ctxt->ctxt.retire.singlestep ) -diff --git a/xen/arch/x86/hvm/hpet.c b/xen/arch/x86/hvm/hpet.c -index f7aed7f69e..28377091ca 100644 ---- a/xen/arch/x86/hvm/hpet.c -+++ b/xen/arch/x86/hvm/hpet.c -@@ -264,13 +264,20 @@ static void hpet_set_timer(HPETState *h, unsigned int tn, - diff = (timer_is_32bit(h, tn) && (-diff > HPET_TINY_TIME_SPAN)) - ? (uint32_t)diff : 0; - -+ destroy_periodic_time(&h->pt[tn]); - if ( (tn <= 1) && (h->hpet.config & HPET_CFG_LEGACY) ) -+ { - /* if LegacyReplacementRoute bit is set, HPET specification requires - timer0 be routed to IRQ0 in NON-APIC or IRQ2 in the I/O APIC, - timer1 be routed to IRQ8 in NON-APIC or IRQ8 in the I/O APIC. */ - irq = (tn == 0) ? 0 : 8; -+ h->pt[tn].source = PTSRC_isa; -+ } - else -+ { - irq = timer_int_route(h, tn); -+ h->pt[tn].source = PTSRC_ioapic; -+ } - - /* - * diff is the time from now when the timer should fire, for a periodic -diff --git a/xen/arch/x86/hvm/ioreq.c b/xen/arch/x86/hvm/ioreq.c -index d5afe20cc8..25b2445429 100644 ---- a/xen/arch/x86/hvm/ioreq.c -+++ b/xen/arch/x86/hvm/ioreq.c -@@ -87,14 +87,17 @@ static void hvm_io_assist(struct hvm_ioreq_vcpu *sv, uint64_t data) - - static bool hvm_wait_for_io(struct hvm_ioreq_vcpu *sv, ioreq_t *p) - { -+ unsigned int prev_state = STATE_IOREQ_NONE; -+ - while ( sv->pending ) - { - unsigned int state = p->state; - -- rmb(); -- switch ( state ) -+ smp_rmb(); -+ -+ recheck: -+ if ( unlikely(state == STATE_IOREQ_NONE) ) - { -- case STATE_IOREQ_NONE: - /* - * The only reason we should see this case is when an - * emulator is dying and it races with an I/O being -@@ -102,14 +105,30 @@ static bool hvm_wait_for_io(struct hvm_ioreq_vcpu *sv, ioreq_t *p) - */ - hvm_io_assist(sv, ~0ul); - break; -+ } -+ -+ if ( unlikely(state < prev_state) ) -+ { -+ gdprintk(XENLOG_ERR, "Weird HVM ioreq state transition %u -> %u\n", -+ prev_state, state); -+ sv->pending = false; -+ domain_crash(sv->vcpu->domain); -+ return false; /* bail */ -+ } -+ -+ switch ( prev_state = state ) -+ { - case STATE_IORESP_READY: /* IORESP_READY -> NONE */ - p->state = STATE_IOREQ_NONE; - hvm_io_assist(sv, p->data); - break; - case STATE_IOREQ_READY: /* IOREQ_{READY,INPROCESS} -> IORESP_READY */ - case STATE_IOREQ_INPROCESS: -- wait_on_xen_event_channel(sv->ioreq_evtchn, p->state != state); -- break; -+ wait_on_xen_event_channel(sv->ioreq_evtchn, -+ ({ state = p->state; -+ smp_rmb(); -+ state != prev_state; })); -+ goto recheck; - default: - gdprintk(XENLOG_ERR, "Weird HVM iorequest state %u\n", state); - sv->pending = false; -diff --git a/xen/arch/x86/hvm/irq.c b/xen/arch/x86/hvm/irq.c -index f528e2d081..c85d004402 100644 ---- a/xen/arch/x86/hvm/irq.c -+++ b/xen/arch/x86/hvm/irq.c -@@ -41,6 +41,26 @@ static void assert_gsi(struct domain *d, unsigned ioapic_gsi) - vioapic_irq_positive_edge(d, ioapic_gsi); - } - -+int hvm_ioapic_assert(struct domain *d, unsigned int gsi, bool level) -+{ -+ struct hvm_irq *hvm_irq = hvm_domain_irq(d); -+ int vector; -+ -+ if ( gsi >= hvm_irq->nr_gsis ) -+ { -+ ASSERT_UNREACHABLE(); -+ return -1; -+ } -+ -+ spin_lock(&d->arch.hvm_domain.irq_lock); -+ if ( !level || hvm_irq->gsi_assert_count[gsi]++ == 0 ) -+ assert_gsi(d, gsi); -+ vector = vioapic_get_vector(d, gsi); -+ spin_unlock(&d->arch.hvm_domain.irq_lock); -+ -+ return vector; -+} -+ - static void assert_irq(struct domain *d, unsigned ioapic_gsi, unsigned pic_irq) - { - assert_gsi(d, ioapic_gsi); -diff --git a/xen/arch/x86/hvm/svm/svm.c b/xen/arch/x86/hvm/svm/svm.c -index dedec5752d..3b72b4dc2a 100644 ---- a/xen/arch/x86/hvm/svm/svm.c -+++ b/xen/arch/x86/hvm/svm/svm.c -@@ -1046,6 +1046,7 @@ static void svm_ctxt_switch_from(struct vcpu *v) - set_ist(&idt_tables[cpu][TRAP_double_fault], IST_DF); - set_ist(&idt_tables[cpu][TRAP_nmi], IST_NMI); - set_ist(&idt_tables[cpu][TRAP_machine_check], IST_MCE); -+ set_ist(&idt_tables[cpu][TRAP_debug], IST_DB); - } - - static void svm_ctxt_switch_to(struct vcpu *v) -@@ -1067,6 +1068,7 @@ static void svm_ctxt_switch_to(struct vcpu *v) - set_ist(&idt_tables[cpu][TRAP_double_fault], IST_NONE); - set_ist(&idt_tables[cpu][TRAP_nmi], IST_NONE); - set_ist(&idt_tables[cpu][TRAP_machine_check], IST_NONE); -+ set_ist(&idt_tables[cpu][TRAP_debug], IST_NONE); - - svm_restore_dr(v); - -@@ -1836,6 +1838,25 @@ static int svm_msr_read_intercept(unsigned int msr, uint64_t *msr_content) - struct vcpu *v = current; - struct vmcb_struct *vmcb = v->arch.hvm_svm.vmcb; - -+ switch ( msr ) -+ { -+ /* -+ * Sync not needed while the cross-vendor logic is in unilateral effect. -+ case MSR_IA32_SYSENTER_CS: -+ case MSR_IA32_SYSENTER_ESP: -+ case MSR_IA32_SYSENTER_EIP: -+ */ -+ case MSR_STAR: -+ case MSR_LSTAR: -+ case MSR_CSTAR: -+ case MSR_SYSCALL_MASK: -+ case MSR_FS_BASE: -+ case MSR_GS_BASE: -+ case MSR_SHADOW_GS_BASE: -+ svm_sync_vmcb(v); -+ break; -+ } -+ - switch ( msr ) - { - case MSR_IA32_SYSENTER_CS: -@@ -1848,6 +1869,34 @@ static int svm_msr_read_intercept(unsigned int msr, uint64_t *msr_content) - *msr_content = v->arch.hvm_svm.guest_sysenter_eip; - break; - -+ case MSR_STAR: -+ *msr_content = vmcb->star; -+ break; -+ -+ case MSR_LSTAR: -+ *msr_content = vmcb->lstar; -+ break; -+ -+ case MSR_CSTAR: -+ *msr_content = vmcb->cstar; -+ break; -+ -+ case MSR_SYSCALL_MASK: -+ *msr_content = vmcb->sfmask; -+ break; -+ -+ case MSR_FS_BASE: -+ *msr_content = vmcb->fs.base; -+ break; -+ -+ case MSR_GS_BASE: -+ *msr_content = vmcb->gs.base; -+ break; -+ -+ case MSR_SHADOW_GS_BASE: -+ *msr_content = vmcb->kerngsbase; -+ break; -+ - case MSR_IA32_MCx_MISC(4): /* Threshold register */ - case MSR_F10_MC4_MISC1 ... MSR_F10_MC4_MISC3: - /* -@@ -1976,32 +2025,81 @@ static int svm_msr_write_intercept(unsigned int msr, uint64_t msr_content) - int ret, result = X86EMUL_OKAY; - struct vcpu *v = current; - struct vmcb_struct *vmcb = v->arch.hvm_svm.vmcb; -- int sync = 0; -+ bool sync = false; - - switch ( msr ) - { - case MSR_IA32_SYSENTER_CS: - case MSR_IA32_SYSENTER_ESP: - case MSR_IA32_SYSENTER_EIP: -- sync = 1; -- break; -- default: -+ case MSR_STAR: -+ case MSR_LSTAR: -+ case MSR_CSTAR: -+ case MSR_SYSCALL_MASK: -+ case MSR_FS_BASE: -+ case MSR_GS_BASE: -+ case MSR_SHADOW_GS_BASE: -+ sync = true; - break; - } - - if ( sync ) -- svm_sync_vmcb(v); -+ svm_sync_vmcb(v); - - switch ( msr ) - { -+ case MSR_IA32_SYSENTER_ESP: -+ case MSR_IA32_SYSENTER_EIP: -+ case MSR_LSTAR: -+ case MSR_CSTAR: -+ case MSR_FS_BASE: -+ case MSR_GS_BASE: -+ case MSR_SHADOW_GS_BASE: -+ if ( !is_canonical_address(msr_content) ) -+ goto gpf; -+ -+ switch ( msr ) -+ { -+ case MSR_IA32_SYSENTER_ESP: -+ vmcb->sysenter_esp = v->arch.hvm_svm.guest_sysenter_esp = msr_content; -+ break; -+ -+ case MSR_IA32_SYSENTER_EIP: -+ vmcb->sysenter_eip = v->arch.hvm_svm.guest_sysenter_eip = msr_content; -+ break; -+ -+ case MSR_LSTAR: -+ vmcb->lstar = msr_content; -+ break; -+ -+ case MSR_CSTAR: -+ vmcb->cstar = msr_content; -+ break; -+ -+ case MSR_FS_BASE: -+ vmcb->fs.base = msr_content; -+ break; -+ -+ case MSR_GS_BASE: -+ vmcb->gs.base = msr_content; -+ break; -+ -+ case MSR_SHADOW_GS_BASE: -+ vmcb->kerngsbase = msr_content; -+ break; -+ } -+ break; -+ - case MSR_IA32_SYSENTER_CS: - vmcb->sysenter_cs = v->arch.hvm_svm.guest_sysenter_cs = msr_content; - break; -- case MSR_IA32_SYSENTER_ESP: -- vmcb->sysenter_esp = v->arch.hvm_svm.guest_sysenter_esp = msr_content; -+ -+ case MSR_STAR: -+ vmcb->star = msr_content; - break; -- case MSR_IA32_SYSENTER_EIP: -- vmcb->sysenter_eip = v->arch.hvm_svm.guest_sysenter_eip = msr_content; -+ -+ case MSR_SYSCALL_MASK: -+ vmcb->sfmask = msr_content; - break; - - case MSR_IA32_DEBUGCTLMSR: -diff --git a/xen/arch/x86/hvm/svm/svmdebug.c b/xen/arch/x86/hvm/svm/svmdebug.c -index 89ef2db932..b5b946aa94 100644 ---- a/xen/arch/x86/hvm/svm/svmdebug.c -+++ b/xen/arch/x86/hvm/svm/svmdebug.c -@@ -131,9 +131,8 @@ bool svm_vmcb_isvalid(const char *from, const struct vmcb_struct *vmcb, - PRINTF("DR7: bits [63:32] are not zero (%#"PRIx64")\n", - vmcb_get_dr7(vmcb)); - -- if ( efer & ~(EFER_SCE | EFER_LME | EFER_LMA | EFER_NX | EFER_SVME | -- EFER_LMSLE | EFER_FFXSE) ) -- PRINTF("EFER: undefined bits are not zero (%#"PRIx64")\n", efer); -+ if ( efer & ~EFER_KNOWN_MASK ) -+ PRINTF("EFER: unknown bits are not zero (%#"PRIx64")\n", efer); - - if ( hvm_efer_valid(v, efer, -1) ) - PRINTF("EFER: %s (%"PRIx64")\n", hvm_efer_valid(v, efer, -1), efer); -diff --git a/xen/arch/x86/hvm/viridian.c b/xen/arch/x86/hvm/viridian.c -index f0fa59d7d5..b02a70d086 100644 ---- a/xen/arch/x86/hvm/viridian.c -+++ b/xen/arch/x86/hvm/viridian.c -@@ -245,7 +245,7 @@ void cpuid_viridian_leaves(const struct vcpu *v, uint32_t leaf, - }; - union { - HV_PARTITION_PRIVILEGE_MASK mask; -- uint32_t lo, hi; -+ struct { uint32_t lo, hi; }; - } u; - - if ( !(viridian_feature_mask(d) & HVMPV_no_freq) ) -@@ -966,12 +966,10 @@ int viridian_hypercall(struct cpu_user_regs *regs) - gprintk(XENLOG_WARNING, "unimplemented hypercall %04x\n", - input.call_code); - /* Fallthrough. */ -- case HvGetPartitionId: - case HvExtCallQueryCapabilities: - /* -- * These hypercalls seem to be erroneously issued by Windows -- * despite neither AccessPartitionId nor EnableExtendedHypercalls -- * being set in CPUID leaf 2. -+ * This hypercall seems to be erroneously issued by Windows -+ * despite EnableExtendedHypercalls not being set in CPUID leaf 2. - * Given that return a status of 'invalid code' has not so far - * caused any problems it's not worth logging. - */ -diff --git a/xen/arch/x86/hvm/vpt.c b/xen/arch/x86/hvm/vpt.c -index 181f4cb631..04e3c2e15b 100644 ---- a/xen/arch/x86/hvm/vpt.c -+++ b/xen/arch/x86/hvm/vpt.c -@@ -107,31 +107,49 @@ static int pt_irq_vector(struct periodic_time *pt, enum hvm_intsrc src) - static int pt_irq_masked(struct periodic_time *pt) - { - struct vcpu *v = pt->vcpu; -- unsigned int gsi, isa_irq; -- int mask; -- uint8_t pic_imr; -+ unsigned int gsi = pt->irq; - -- if ( pt->source == PTSRC_lapic ) -+ switch ( pt->source ) -+ { -+ case PTSRC_lapic: - { - struct vlapic *vlapic = vcpu_vlapic(v); -+ - return (!vlapic_enabled(vlapic) || - (vlapic_get_reg(vlapic, APIC_LVTT) & APIC_LVT_MASKED)); - } - -- isa_irq = pt->irq; -- gsi = hvm_isa_irq_to_gsi(isa_irq); -- pic_imr = v->domain->arch.hvm_domain.vpic[isa_irq >> 3].imr; -- mask = vioapic_get_mask(v->domain, gsi); -- if ( mask < 0 ) -+ case PTSRC_isa: - { -- dprintk(XENLOG_WARNING, "d%u: invalid GSI (%u) for platform timer\n", -- v->domain->domain_id, gsi); -- domain_crash(v->domain); -- return -1; -+ uint8_t pic_imr = v->domain->arch.hvm_domain.vpic[pt->irq >> 3].imr; -+ -+ /* Check if the interrupt is unmasked in the PIC. */ -+ if ( !(pic_imr & (1 << (pt->irq & 7))) && vlapic_accept_pic_intr(v) ) -+ return 0; -+ -+ gsi = hvm_isa_irq_to_gsi(pt->irq); -+ } -+ -+ /* Fallthrough to check if the interrupt is masked on the IO APIC. */ -+ case PTSRC_ioapic: -+ { -+ int mask = vioapic_get_mask(v->domain, gsi); -+ -+ if ( mask < 0 ) -+ { -+ dprintk(XENLOG_WARNING, -+ "d%d: invalid GSI (%u) for platform timer\n", -+ v->domain->domain_id, gsi); -+ domain_crash(v->domain); -+ return -1; -+ } -+ -+ return mask; -+ } - } - -- return (((pic_imr & (1 << (isa_irq & 7))) || !vlapic_accept_pic_intr(v)) && -- mask); -+ ASSERT_UNREACHABLE(); -+ return 1; - } - - static void pt_lock(struct periodic_time *pt) -@@ -252,7 +270,7 @@ int pt_update_irq(struct vcpu *v) - struct list_head *head = &v->arch.hvm_vcpu.tm_list; - struct periodic_time *pt, *temp, *earliest_pt; - uint64_t max_lag; -- int irq, is_lapic, pt_vector; -+ int irq, pt_vector = -1; - - spin_lock(&v->arch.hvm_vcpu.tm_lock); - -@@ -288,29 +306,26 @@ int pt_update_irq(struct vcpu *v) - - earliest_pt->irq_issued = 1; - irq = earliest_pt->irq; -- is_lapic = (earliest_pt->source == PTSRC_lapic); - - spin_unlock(&v->arch.hvm_vcpu.tm_lock); - -- /* -- * If periodic timer interrut is handled by lapic, its vector in -- * IRR is returned and used to set eoi_exit_bitmap for virtual -- * interrupt delivery case. Otherwise return -1 to do nothing. -- */ -- if ( is_lapic ) -+ switch ( earliest_pt->source ) - { -+ case PTSRC_lapic: -+ /* -+ * If periodic timer interrupt is handled by lapic, its vector in -+ * IRR is returned and used to set eoi_exit_bitmap for virtual -+ * interrupt delivery case. Otherwise return -1 to do nothing. -+ */ - vlapic_set_irq(vcpu_vlapic(v), irq, 0); - pt_vector = irq; -- } -- else -- { -+ break; -+ -+ case PTSRC_isa: - hvm_isa_irq_deassert(v->domain, irq); - if ( platform_legacy_irq(irq) && vlapic_accept_pic_intr(v) && - v->domain->arch.hvm_domain.vpic[irq >> 3].int_output ) -- { - hvm_isa_irq_assert(v->domain, irq, NULL); -- pt_vector = -1; -- } - else - { - pt_vector = hvm_isa_irq_assert(v->domain, irq, vioapic_get_vector); -@@ -321,6 +336,17 @@ int pt_update_irq(struct vcpu *v) - if ( pt_vector < 0 || !vlapic_test_irq(vcpu_vlapic(v), pt_vector) ) - pt_vector = -1; - } -+ break; -+ -+ case PTSRC_ioapic: -+ /* -+ * NB: At the moment IO-APIC routed interrupts generated by vpt devices -+ * (HPET) are edge-triggered. -+ */ -+ pt_vector = hvm_ioapic_assert(v->domain, irq, false); -+ if ( pt_vector < 0 || !vlapic_test_irq(vcpu_vlapic(v), pt_vector) ) -+ pt_vector = -1; -+ break; - } - - return pt_vector; -@@ -418,7 +444,14 @@ void create_periodic_time( - struct vcpu *v, struct periodic_time *pt, uint64_t delta, - uint64_t period, uint8_t irq, time_cb *cb, void *data) - { -- ASSERT(pt->source != 0); -+ if ( !pt->source || -+ (pt->irq >= NR_ISAIRQS && pt->source == PTSRC_isa) || -+ (pt->irq >= hvm_domain_irq(v->domain)->nr_gsis && -+ pt->source == PTSRC_ioapic) ) -+ { -+ ASSERT_UNREACHABLE(); -+ return; -+ } - - destroy_periodic_time(pt); - -@@ -498,7 +531,7 @@ static void pt_adjust_vcpu(struct periodic_time *pt, struct vcpu *v) - { - int on_list; - -- ASSERT(pt->source == PTSRC_isa); -+ ASSERT(pt->source == PTSRC_isa || pt->source == PTSRC_ioapic); - - if ( pt->vcpu == NULL ) - return; -diff --git a/xen/arch/x86/pv/emul-priv-op.c b/xen/arch/x86/pv/emul-priv-op.c -index 642ca312bf..c281936af0 100644 ---- a/xen/arch/x86/pv/emul-priv-op.c -+++ b/xen/arch/x86/pv/emul-priv-op.c -@@ -813,26 +813,6 @@ static int write_cr(unsigned int reg, unsigned long val, - return X86EMUL_UNHANDLEABLE; - } - --static int read_dr(unsigned int reg, unsigned long *val, -- struct x86_emulate_ctxt *ctxt) --{ -- unsigned long res = do_get_debugreg(reg); -- -- if ( IS_ERR_VALUE(res) ) -- return X86EMUL_UNHANDLEABLE; -- -- *val = res; -- -- return X86EMUL_OKAY; --} -- --static int write_dr(unsigned int reg, unsigned long val, -- struct x86_emulate_ctxt *ctxt) --{ -- return do_set_debugreg(reg, val) == 0 -- ? X86EMUL_OKAY : X86EMUL_UNHANDLEABLE; --} -- - static inline uint64_t guest_misc_enable(uint64_t val) - { - val &= ~(MSR_IA32_MISC_ENABLE_PERF_AVAIL | -@@ -906,9 +886,16 @@ static int read_msr(unsigned int reg, uint64_t *val, - return X86EMUL_OKAY; - - case MSR_EFER: -- *val = read_efer(); -+ /* Hide unknown bits, and unconditionally hide SVME from guests. */ -+ *val = read_efer() & EFER_KNOWN_MASK & ~EFER_SVME; -+ /* -+ * Hide the 64-bit features from 32-bit guests. SCE has -+ * vendor-dependent behaviour. -+ */ - if ( is_pv_32bit_domain(currd) ) -- *val &= ~(EFER_LME | EFER_LMA | EFER_LMSLE); -+ *val &= ~(EFER_LME | EFER_LMA | EFER_LMSLE | -+ (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL -+ ? EFER_SCE : 0)); - return X86EMUL_OKAY; - - case MSR_K7_FID_VID_CTL: -@@ -1326,8 +1313,8 @@ static const struct x86_emulate_ops priv_op_ops = { - .read_segment = read_segment, - .read_cr = read_cr, - .write_cr = write_cr, -- .read_dr = read_dr, -- .write_dr = write_dr, -+ .read_dr = x86emul_read_dr, -+ .write_dr = x86emul_write_dr, - .read_msr = read_msr, - .write_msr = write_msr, - .cpuid = pv_emul_cpuid, -diff --git a/xen/arch/x86/pv/misc-hypercalls.c b/xen/arch/x86/pv/misc-hypercalls.c -index 5862130697..1619be7874 100644 ---- a/xen/arch/x86/pv/misc-hypercalls.c -+++ b/xen/arch/x86/pv/misc-hypercalls.c -@@ -30,22 +30,10 @@ long do_set_debugreg(int reg, unsigned long value) - - unsigned long do_get_debugreg(int reg) - { -- struct vcpu *curr = current; -+ unsigned long val; -+ int res = x86emul_read_dr(reg, &val, NULL); - -- switch ( reg ) -- { -- case 0 ... 3: -- case 6: -- return curr->arch.debugreg[reg]; -- case 7: -- return (curr->arch.debugreg[7] | -- curr->arch.debugreg[5]); -- case 4 ... 5: -- return ((curr->arch.pv_vcpu.ctrlreg[4] & X86_CR4_DE) ? -- curr->arch.debugreg[reg + 2] : 0); -- } -- -- return -EINVAL; -+ return res == X86EMUL_OKAY ? val : -ENODEV; - } - - long do_fpu_taskswitch(int set) -diff --git a/xen/arch/x86/smpboot.c b/xen/arch/x86/smpboot.c -index e1d023428c..f81fc2ca65 100644 ---- a/xen/arch/x86/smpboot.c -+++ b/xen/arch/x86/smpboot.c -@@ -968,6 +968,7 @@ static int cpu_smpboot_alloc(unsigned int cpu) - set_ist(&idt_tables[cpu][TRAP_double_fault], IST_NONE); - set_ist(&idt_tables[cpu][TRAP_nmi], IST_NONE); - set_ist(&idt_tables[cpu][TRAP_machine_check], IST_NONE); -+ set_ist(&idt_tables[cpu][TRAP_debug], IST_NONE); - - for ( stub_page = 0, i = cpu & ~(STUBS_PER_PAGE - 1); - i < nr_cpu_ids && i <= (cpu | (STUBS_PER_PAGE - 1)); ++i ) -diff --git a/xen/arch/x86/spec_ctrl.c b/xen/arch/x86/spec_ctrl.c -index 3c7447bfe6..fa67a0ffbd 100644 ---- a/xen/arch/x86/spec_ctrl.c -+++ b/xen/arch/x86/spec_ctrl.c -@@ -97,12 +97,13 @@ static void __init print_details(enum ind_thunk thunk) - printk(XENLOG_DEBUG "Speculative mitigation facilities:\n"); - - /* Hardware features which pertain to speculative mitigations. */ -- printk(XENLOG_DEBUG " Hardware features:%s%s%s%s%s\n", -+ printk(XENLOG_DEBUG " Hardware features:%s%s%s%s%s%s\n", - (_7d0 & cpufeat_mask(X86_FEATURE_IBRSB)) ? " IBRS/IBPB" : "", - (_7d0 & cpufeat_mask(X86_FEATURE_STIBP)) ? " STIBP" : "", - (e8b & cpufeat_mask(X86_FEATURE_IBPB)) ? " IBPB" : "", - (caps & ARCH_CAPABILITIES_IBRS_ALL) ? " IBRS_ALL" : "", -- (caps & ARCH_CAPABILITIES_RDCL_NO) ? " RDCL_NO" : ""); -+ (caps & ARCH_CAPABILITIES_RDCL_NO) ? " RDCL_NO" : "", -+ (caps & ARCH_CAPS_RSBA) ? " RSBA" : ""); - - /* Compiled-in support which pertains to BTI mitigations. */ - if ( IS_ENABLED(CONFIG_INDIRECT_THUNK) ) -@@ -135,6 +136,20 @@ static bool __init retpoline_safe(void) - boot_cpu_data.x86 != 6 ) - return false; - -+ if ( boot_cpu_has(X86_FEATURE_ARCH_CAPS) ) -+ { -+ uint64_t caps; -+ -+ rdmsrl(MSR_ARCH_CAPABILITIES, caps); -+ -+ /* -+ * RBSA may be set by a hypervisor to indicate that we may move to a -+ * processor which isn't retpoline-safe. -+ */ -+ if ( caps & ARCH_CAPS_RSBA ) -+ return false; -+ } -+ - switch ( boot_cpu_data.x86_model ) - { - case 0x17: /* Penryn */ -@@ -161,18 +176,40 @@ static bool __init retpoline_safe(void) - * versions. - */ - case 0x3d: /* Broadwell */ -- return ucode_rev >= 0x28; -+ return ucode_rev >= 0x2a; - case 0x47: /* Broadwell H */ -- return ucode_rev >= 0x1b; -+ return ucode_rev >= 0x1d; - case 0x4f: /* Broadwell EP/EX */ -- return ucode_rev >= 0xb000025; -+ return ucode_rev >= 0xb000021; - case 0x56: /* Broadwell D */ -- return false; /* TBD. */ -+ switch ( boot_cpu_data.x86_mask ) -+ { -+ case 2: return ucode_rev >= 0x15; -+ case 3: return ucode_rev >= 0x7000012; -+ case 4: return ucode_rev >= 0xf000011; -+ case 5: return ucode_rev >= 0xe000009; -+ default: -+ printk("Unrecognised CPU stepping %#x - assuming not reptpoline safe\n", -+ boot_cpu_data.x86_mask); -+ return false; -+ } -+ break; - - /* -- * Skylake and later processors are not retpoline-safe. -+ * Skylake, Kabylake and Cannonlake processors are not retpoline-safe. - */ -+ case 0x4e: -+ case 0x55: -+ case 0x5e: -+ case 0x66: -+ case 0x67: -+ case 0x8e: -+ case 0x9e: -+ return false; -+ - default: -+ printk("Unrecognised CPU model %#x - assuming not reptpoline safe\n", -+ boot_cpu_data.x86_model); - return false; - } - } -diff --git a/xen/arch/x86/traps.c b/xen/arch/x86/traps.c -index 906124331b..e217b0d6e2 100644 ---- a/xen/arch/x86/traps.c -+++ b/xen/arch/x86/traps.c -@@ -325,13 +325,13 @@ static void show_guest_stack(struct vcpu *v, const struct cpu_user_regs *regs) - /* - * Notes for get_stack_trace_bottom() and get_stack_dump_bottom() - * -- * Stack pages 0, 1 and 2: -+ * Stack pages 0 - 3: - * These are all 1-page IST stacks. Each of these stacks have an exception - * frame and saved register state at the top. The interesting bound for a - * trace is the word adjacent to this, while the bound for a dump is the - * very top, including the exception frame. - * -- * Stack pages 3, 4 and 5: -+ * Stack pages 4 and 5: - * None of these are particularly interesting. With MEMORY_GUARD, page 5 is - * explicitly not present, so attempting to dump or trace it is - * counterproductive. Without MEMORY_GUARD, it is possible for a call chain -@@ -352,12 +352,12 @@ unsigned long get_stack_trace_bottom(unsigned long sp) - { - switch ( get_stack_page(sp) ) - { -- case 0 ... 2: -+ case 0 ... 3: - return ROUNDUP(sp, PAGE_SIZE) - - offsetof(struct cpu_user_regs, es) - sizeof(unsigned long); - - #ifndef MEMORY_GUARD -- case 3 ... 5: -+ case 4 ... 5: - #endif - case 6 ... 7: - return ROUNDUP(sp, STACK_SIZE) - -@@ -372,11 +372,11 @@ unsigned long get_stack_dump_bottom(unsigned long sp) - { - switch ( get_stack_page(sp) ) - { -- case 0 ... 2: -+ case 0 ... 3: - return ROUNDUP(sp, PAGE_SIZE) - sizeof(unsigned long); - - #ifndef MEMORY_GUARD -- case 3 ... 5: -+ case 4 ... 5: - #endif - case 6 ... 7: - return ROUNDUP(sp, STACK_SIZE) - sizeof(unsigned long); -@@ -1761,11 +1761,36 @@ static void ler_enable(void) - - void do_debug(struct cpu_user_regs *regs) - { -+ unsigned long dr6; - struct vcpu *v = current; - -+ /* Stash dr6 as early as possible. */ -+ dr6 = read_debugreg(6); -+ - if ( debugger_trap_entry(TRAP_debug, regs) ) - return; - -+ /* -+ * At the time of writing (March 2018), on the subject of %dr6: -+ * -+ * The Intel manual says: -+ * Certain debug exceptions may clear bits 0-3. The remaining contents -+ * of the DR6 register are never cleared by the processor. To avoid -+ * confusion in identifying debug exceptions, debug handlers should -+ * clear the register (except bit 16, which they should set) before -+ * returning to the interrupted task. -+ * -+ * The AMD manual says: -+ * Bits 15:13 of the DR6 register are not cleared by the processor and -+ * must be cleared by software after the contents have been read. -+ * -+ * Some bits are reserved set, some are reserved clear, and some bits -+ * which were previously reserved set are reused and cleared by hardware. -+ * For future compatibility, reset to the default value, which will allow -+ * us to spot any bit being changed by hardware to its non-default value. -+ */ -+ write_debugreg(6, X86_DR6_DEFAULT); -+ - if ( !guest_mode(regs) ) - { - if ( regs->eflags & X86_EFLAGS_TF ) -@@ -1784,21 +1809,50 @@ void do_debug(struct cpu_user_regs *regs) - regs->eflags &= ~X86_EFLAGS_TF; - } - } -- else -+ -+ /* -+ * Check for fault conditions. General Detect, and instruction -+ * breakpoints are faults rather than traps, at which point attempting -+ * to ignore and continue will result in a livelock. -+ */ -+ if ( dr6 & DR_GENERAL_DETECT ) - { -- /* -- * We ignore watchpoints when they trigger within Xen. This may -- * happen when a buffer is passed to us which previously had a -- * watchpoint set on it. No need to bump EIP; the only faulting -- * trap is an instruction breakpoint, which can't happen to us. -- */ -- WARN_ON(!search_exception_table(regs)); -+ printk(XENLOG_ERR "Hit General Detect in Xen context\n"); -+ fatal_trap(regs, 0); -+ } -+ -+ if ( dr6 & (DR_TRAP3 | DR_TRAP2 | DR_TRAP1 | DR_TRAP0) ) -+ { -+ unsigned int bp, dr7 = read_debugreg(7) >> DR_CONTROL_SHIFT; -+ -+ for ( bp = 0; bp < 4; ++bp ) -+ { -+ if ( (dr6 & (1u << bp)) && /* Breakpoint triggered? */ -+ ((dr7 & (3u << (bp * DR_CONTROL_SIZE))) == 0) /* Insn? */ ) -+ { -+ printk(XENLOG_ERR -+ "Hit instruction breakpoint in Xen context\n"); -+ fatal_trap(regs, 0); -+ } -+ } - } -+ -+ /* -+ * Whatever caused this #DB should be a trap. Note it and continue. -+ * Guests can trigger this in certain corner cases, so ensure the -+ * message is ratelimited. -+ */ -+ gprintk(XENLOG_WARNING, -+ "Hit #DB in Xen context: %04x:%p [%ps], stk %04x:%p, dr6 %lx\n", -+ regs->cs, _p(regs->rip), _p(regs->rip), -+ regs->ss, _p(regs->rsp), dr6); -+ - goto out; - } - - /* Save debug status register where guest OS can peek at it */ -- v->arch.debugreg[6] = read_debugreg(6); -+ v->arch.debugreg[6] |= (dr6 & ~X86_DR6_DEFAULT); -+ v->arch.debugreg[6] &= (dr6 | ~X86_DR6_DEFAULT); - - ler_enable(); - pv_inject_hw_exception(TRAP_debug, X86_EVENT_NO_EC); -@@ -1917,6 +1971,7 @@ void __init init_idt_traps(void) - set_ist(&idt_table[TRAP_double_fault], IST_DF); - set_ist(&idt_table[TRAP_nmi], IST_NMI); - set_ist(&idt_table[TRAP_machine_check], IST_MCE); -+ set_ist(&idt_table[TRAP_debug], IST_DB); - - /* CPU0 uses the master IDT. */ - idt_tables[0] = idt_table; -@@ -1984,6 +2039,12 @@ void activate_debugregs(const struct vcpu *curr) - } - } - -+/* -+ * Used by hypercalls and the emulator. -+ * -ENODEV => #UD -+ * -EINVAL => #GP Invalid bit -+ * -EPERM => #GP Valid bit, but not permitted to use -+ */ - long set_debugreg(struct vcpu *v, unsigned int reg, unsigned long value) - { - int i; -@@ -2015,7 +2076,17 @@ long set_debugreg(struct vcpu *v, unsigned int reg, unsigned long value) - if ( v == curr ) - write_debugreg(3, value); - break; -+ -+ case 4: -+ if ( v->arch.pv_vcpu.ctrlreg[4] & X86_CR4_DE ) -+ return -ENODEV; -+ -+ /* Fallthrough */ - case 6: -+ /* The upper 32 bits are strictly reserved. */ -+ if ( value != (uint32_t)value ) -+ return -EINVAL; -+ - /* - * DR6: Bits 4-11,16-31 reserved (set to 1). - * Bit 12 reserved (set to 0). -@@ -2025,7 +2096,17 @@ long set_debugreg(struct vcpu *v, unsigned int reg, unsigned long value) - if ( v == curr ) - write_debugreg(6, value); - break; -+ -+ case 5: -+ if ( v->arch.pv_vcpu.ctrlreg[4] & X86_CR4_DE ) -+ return -ENODEV; -+ -+ /* Fallthrough */ - case 7: -+ /* The upper 32 bits are strictly reserved. */ -+ if ( value != (uint32_t)value ) -+ return -EINVAL; -+ - /* - * DR7: Bit 10 reserved (set to 1). - * Bits 11-12,14-15 reserved (set to 0). -@@ -2038,6 +2119,10 @@ long set_debugreg(struct vcpu *v, unsigned int reg, unsigned long value) - */ - if ( value & DR_GENERAL_DETECT ) - return -EPERM; -+ -+ /* Zero the IO shadow before recalculating the real %dr7 */ -+ v->arch.debugreg[5] = 0; -+ - /* DR7.{G,L}E = 0 => debugging disabled for this domain. */ - if ( value & DR7_ACTIVE_MASK ) - { -@@ -2070,7 +2155,7 @@ long set_debugreg(struct vcpu *v, unsigned int reg, unsigned long value) - write_debugreg(7, value); - break; - default: -- return -EINVAL; -+ return -ENODEV; - } - - v->arch.debugreg[reg] = value; -diff --git a/xen/arch/x86/x86_64/compat/entry.S b/xen/arch/x86/x86_64/compat/entry.S -index 75497bc292..a47cb9dc19 100644 ---- a/xen/arch/x86/x86_64/compat/entry.S -+++ b/xen/arch/x86/x86_64/compat/entry.S -@@ -39,6 +39,12 @@ ENTRY(compat_test_all_events) - leaq irq_stat+IRQSTAT_softirq_pending(%rip),%rcx - cmpl $0,(%rcx,%rax,1) - jne compat_process_softirqs -+ -+ /* Inject exception if pending. */ -+ lea VCPU_trap_bounce(%rbx), %rdx -+ testb $TBF_EXCEPTION, TRAPBOUNCE_flags(%rdx) -+ jnz .Lcompat_process_trapbounce -+ - testb $1,VCPU_mce_pending(%rbx) - jnz compat_process_mce - .Lcompat_test_guest_nmi: -@@ -68,15 +74,24 @@ compat_process_softirqs: - call do_softirq - jmp compat_test_all_events - -+ ALIGN -+/* %rbx: struct vcpu, %rdx: struct trap_bounce */ -+.Lcompat_process_trapbounce: -+ sti -+.Lcompat_bounce_exception: -+ call compat_create_bounce_frame -+ movb $0, TRAPBOUNCE_flags(%rdx) -+ jmp compat_test_all_events -+ - ALIGN - /* %rbx: struct vcpu */ - compat_process_mce: - testb $1 << VCPU_TRAP_MCE,VCPU_async_exception_mask(%rbx) - jnz .Lcompat_test_guest_nmi - sti -- movb $0,VCPU_mce_pending(%rbx) -- call set_guest_machinecheck_trapbounce -- testl %eax,%eax -+ movb $0, VCPU_mce_pending(%rbx) -+ call set_guest_machinecheck_trapbounce -+ test %al, %al - jz compat_test_all_events - movzbl VCPU_async_exception_mask(%rbx),%edx # save mask for the - movb %dl,VCPU_mce_old_mask(%rbx) # iret hypercall -@@ -88,11 +103,11 @@ compat_process_mce: - /* %rbx: struct vcpu */ - compat_process_nmi: - testb $1 << VCPU_TRAP_NMI,VCPU_async_exception_mask(%rbx) -- jnz compat_test_guest_events -+ jnz compat_test_guest_events - sti -- movb $0,VCPU_nmi_pending(%rbx) -+ movb $0, VCPU_nmi_pending(%rbx) - call set_guest_nmi_trapbounce -- testl %eax,%eax -+ test %al, %al - jz compat_test_all_events - movzbl VCPU_async_exception_mask(%rbx),%edx # save mask for the - movb %dl,VCPU_nmi_old_mask(%rbx) # iret hypercall -@@ -189,15 +204,6 @@ ENTRY(cr4_pv32_restore) - xor %eax, %eax - ret - --/* %rdx: trap_bounce, %rbx: struct vcpu */ --ENTRY(compat_post_handle_exception) -- testb $TBF_EXCEPTION,TRAPBOUNCE_flags(%rdx) -- jz compat_test_all_events --.Lcompat_bounce_exception: -- call compat_create_bounce_frame -- movb $0,TRAPBOUNCE_flags(%rdx) -- jmp compat_test_all_events -- - .section .text.entry, "ax", @progbits - - /* See lstar_enter for entry register state. */ -diff --git a/xen/arch/x86/x86_64/entry.S b/xen/arch/x86/x86_64/entry.S -index bdd33e727f..41d3ec21a1 100644 ---- a/xen/arch/x86/x86_64/entry.S -+++ b/xen/arch/x86/x86_64/entry.S -@@ -42,6 +42,12 @@ test_all_events: - leaq irq_stat+IRQSTAT_softirq_pending(%rip), %rcx - cmpl $0, (%rcx, %rax, 1) - jne process_softirqs -+ -+ /* Inject exception if pending. */ -+ lea VCPU_trap_bounce(%rbx), %rdx -+ testb $TBF_EXCEPTION, TRAPBOUNCE_flags(%rdx) -+ jnz .Lprocess_trapbounce -+ - cmpb $0, VCPU_mce_pending(%rbx) - jne process_mce - .Ltest_guest_nmi: -@@ -69,6 +75,15 @@ process_softirqs: - call do_softirq - jmp test_all_events - -+ ALIGN -+/* %rbx: struct vcpu, %rdx struct trap_bounce */ -+.Lprocess_trapbounce: -+ sti -+.Lbounce_exception: -+ call create_bounce_frame -+ movb $0, TRAPBOUNCE_flags(%rdx) -+ jmp test_all_events -+ - ALIGN - /* %rbx: struct vcpu */ - process_mce: -@@ -77,7 +92,7 @@ process_mce: - sti - movb $0, VCPU_mce_pending(%rbx) - call set_guest_machinecheck_trapbounce -- test %eax, %eax -+ test %al, %al - jz test_all_events - movzbl VCPU_async_exception_mask(%rbx), %edx # save mask for the - movb %dl, VCPU_mce_old_mask(%rbx) # iret hypercall -@@ -93,7 +108,7 @@ process_nmi: - sti - movb $0, VCPU_nmi_pending(%rbx) - call set_guest_nmi_trapbounce -- test %eax, %eax -+ test %al, %al - jz test_all_events - movzbl VCPU_async_exception_mask(%rbx), %edx # save mask for the - movb %dl, VCPU_nmi_old_mask(%rbx) # iret hypercall -@@ -667,15 +682,9 @@ handle_exception_saved: - mov %r15, STACK_CPUINFO_FIELD(xen_cr3)(%r14) - testb $3,UREGS_cs(%rsp) - jz restore_all_xen -- leaq VCPU_trap_bounce(%rbx),%rdx - movq VCPU_domain(%rbx),%rax - testb $1,DOMAIN_is_32bit_pv(%rax) -- jnz compat_post_handle_exception -- testb $TBF_EXCEPTION,TRAPBOUNCE_flags(%rdx) -- jz test_all_events --.Lbounce_exception: -- call create_bounce_frame -- movb $0,TRAPBOUNCE_flags(%rdx) -+ jnz compat_test_all_events - jmp test_all_events - - /* No special register assumptions. */ -@@ -730,7 +739,7 @@ ENTRY(device_not_available) - ENTRY(debug) - pushq $0 - movl $TRAP_debug,4(%rsp) -- jmp handle_exception -+ jmp handle_ist_exception - - ENTRY(int3) - pushq $0 -@@ -783,12 +792,14 @@ ENTRY(double_fault) - /* WARNING! `ret`, `call *`, `jmp *` not safe before this point. */ - - mov STACK_CPUINFO_FIELD(xen_cr3)(%r14), %rbx -- test %rbx, %rbx -+ neg %rbx - jz .Ldblf_cr3_okay - jns .Ldblf_cr3_load -+ mov %rbx, STACK_CPUINFO_FIELD(xen_cr3)(%r14) - neg %rbx - .Ldblf_cr3_load: - mov %rbx, %cr3 -+ movq $0, STACK_CPUINFO_FIELD(xen_cr3)(%r14) - .Ldblf_cr3_okay: - - movq %rsp,%rdi -diff --git a/xen/arch/x86/x86_emulate.c b/xen/arch/x86/x86_emulate.c -index c7ba221d11..9125c67c9e 100644 ---- a/xen/arch/x86/x86_emulate.c -+++ b/xen/arch/x86/x86_emulate.c -@@ -14,6 +14,7 @@ - #include <asm/processor.h> /* current_cpu_info */ - #include <asm/xstate.h> - #include <asm/amd.h> /* cpu_has_amd_erratum() */ -+#include <asm/debugreg.h> - - /* Avoid namespace pollution. */ - #undef cmpxchg -@@ -41,3 +42,75 @@ - }) - - #include "x86_emulate/x86_emulate.c" -+ -+/* Called with NULL ctxt in hypercall context. */ -+int x86emul_read_dr(unsigned int reg, unsigned long *val, -+ struct x86_emulate_ctxt *ctxt) -+{ -+ struct vcpu *curr = current; -+ -+ /* HVM support requires a bit more plumbing before it will work. */ -+ ASSERT(is_pv_vcpu(curr)); -+ -+ switch ( reg ) -+ { -+ case 0 ... 3: -+ case 6: -+ *val = curr->arch.debugreg[reg]; -+ break; -+ -+ case 7: -+ *val = (curr->arch.debugreg[7] | -+ curr->arch.debugreg[5]); -+ break; -+ -+ case 4 ... 5: -+ if ( !(curr->arch.pv_vcpu.ctrlreg[4] & X86_CR4_DE) ) -+ { -+ *val = curr->arch.debugreg[reg + 2]; -+ break; -+ } -+ -+ /* Fallthrough */ -+ default: -+ if ( ctxt ) -+ x86_emul_hw_exception(TRAP_invalid_op, X86_EVENT_NO_EC, ctxt); -+ -+ return X86EMUL_EXCEPTION; -+ } -+ -+ return X86EMUL_OKAY; -+} -+ -+int x86emul_write_dr(unsigned int reg, unsigned long val, -+ struct x86_emulate_ctxt *ctxt) -+{ -+ struct vcpu *curr = current; -+ -+ /* HVM support requires a bit more plumbing before it will work. */ -+ ASSERT(is_pv_vcpu(curr)); -+ -+ switch ( set_debugreg(curr, reg, val) ) -+ { -+ case 0: -+ return X86EMUL_OKAY; -+ -+ case -ENODEV: -+ x86_emul_hw_exception(TRAP_invalid_op, X86_EVENT_NO_EC, ctxt); -+ return X86EMUL_EXCEPTION; -+ -+ default: -+ x86_emul_hw_exception(TRAP_gp_fault, 0, ctxt); -+ return X86EMUL_EXCEPTION; -+ } -+} -+ -+/* -+ * Local variables: -+ * mode: C -+ * c-file-style: "BSD" -+ * c-basic-offset: 4 -+ * tab-width: 4 -+ * indent-tabs-mode: nil -+ * End: -+ */ -diff --git a/xen/arch/x86/x86_emulate/x86_emulate.h b/xen/arch/x86/x86_emulate/x86_emulate.h -index 0c8c80ad5a..9c2bb8157c 100644 ---- a/xen/arch/x86/x86_emulate/x86_emulate.h -+++ b/xen/arch/x86/x86_emulate/x86_emulate.h -@@ -662,6 +662,11 @@ static inline void x86_emulate_free_state(struct x86_emulate_state *state) {} - void x86_emulate_free_state(struct x86_emulate_state *state); - #endif - -+int x86emul_read_dr(unsigned int reg, unsigned long *val, -+ struct x86_emulate_ctxt *ctxt); -+int x86emul_write_dr(unsigned int reg, unsigned long val, -+ struct x86_emulate_ctxt *ctxt); -+ - #endif - - static inline void x86_emul_hw_exception( -diff --git a/xen/common/schedule.c b/xen/common/schedule.c -index b7884263f2..f21c3e5a64 100644 ---- a/xen/common/schedule.c -+++ b/xen/common/schedule.c -@@ -436,14 +436,9 @@ void sched_destroy_domain(struct domain *d) - cpupool_rm_domain(d); - } - --void vcpu_sleep_nosync(struct vcpu *v) -+void vcpu_sleep_nosync_locked(struct vcpu *v) - { -- unsigned long flags; -- spinlock_t *lock; -- -- TRACE_2D(TRC_SCHED_SLEEP, v->domain->domain_id, v->vcpu_id); -- -- lock = vcpu_schedule_lock_irqsave(v, &flags); -+ ASSERT(spin_is_locked(per_cpu(schedule_data,v->processor).schedule_lock)); - - if ( likely(!vcpu_runnable(v)) ) - { -@@ -452,6 +447,18 @@ void vcpu_sleep_nosync(struct vcpu *v) - - SCHED_OP(vcpu_scheduler(v), sleep, v); - } -+} -+ -+void vcpu_sleep_nosync(struct vcpu *v) -+{ -+ unsigned long flags; -+ spinlock_t *lock; -+ -+ TRACE_2D(TRC_SCHED_SLEEP, v->domain->domain_id, v->vcpu_id); -+ -+ lock = vcpu_schedule_lock_irqsave(v, &flags); -+ -+ vcpu_sleep_nosync_locked(v); - - vcpu_schedule_unlock_irqrestore(lock, flags, v); - } -@@ -567,13 +574,54 @@ static void vcpu_move_nosched(struct vcpu *v, unsigned int new_cpu) - sched_move_irqs(v); - } - --static void vcpu_migrate(struct vcpu *v) -+/* -+ * Initiating migration -+ * -+ * In order to migrate, we need the vcpu in question to have stopped -+ * running and had SCHED_OP(sleep) called (to take it off any -+ * runqueues, for instance); and if it is currently running, it needs -+ * to be scheduled out. Finally, we need to hold the scheduling locks -+ * for both the processor we're migrating from, and the processor -+ * we're migrating to. -+ * -+ * In order to avoid deadlock while satisfying the final requirement, -+ * we must release any scheduling lock we hold, then try to grab both -+ * locks we want, then double-check to make sure that what we started -+ * to do hasn't been changed in the mean time. -+ * -+ * These steps are encapsulated in the following two functions; they -+ * should be called like this: -+ * -+ * lock = vcpu_schedule_lock_irq(v); -+ * vcpu_migrate_start(v); -+ * vcpu_schedule_unlock_irq(lock, v) -+ * vcpu_migrate_finish(v); -+ * -+ * vcpu_migrate_finish() will do the work now if it can, or simply -+ * return if it can't (because v is still running); in that case -+ * vcpu_migrate_finish() will be called by context_saved(). -+ */ -+void vcpu_migrate_start(struct vcpu *v) -+{ -+ set_bit(_VPF_migrating, &v->pause_flags); -+ vcpu_sleep_nosync_locked(v); -+} -+ -+static void vcpu_migrate_finish(struct vcpu *v) - { - unsigned long flags; - unsigned int old_cpu, new_cpu; - spinlock_t *old_lock, *new_lock; - bool_t pick_called = 0; - -+ /* -+ * If the vcpu is currently running, this will be handled by -+ * context_saved(); and in any case, if the bit is cleared, then -+ * someone else has already done the work so we don't need to. -+ */ -+ if ( v->is_running || !test_bit(_VPF_migrating, &v->pause_flags) ) -+ return; -+ - old_cpu = new_cpu = v->processor; - for ( ; ; ) - { -@@ -653,14 +701,11 @@ void vcpu_force_reschedule(struct vcpu *v) - spinlock_t *lock = vcpu_schedule_lock_irq(v); - - if ( v->is_running ) -- set_bit(_VPF_migrating, &v->pause_flags); -+ vcpu_migrate_start(v); -+ - vcpu_schedule_unlock_irq(lock, v); - -- if ( v->pause_flags & VPF_migrating ) -- { -- vcpu_sleep_nosync(v); -- vcpu_migrate(v); -- } -+ vcpu_migrate_finish(v); - } - - void restore_vcpu_affinity(struct domain *d) -@@ -812,10 +857,10 @@ int cpu_disable_scheduler(unsigned int cpu) - * * the scheduler will always fine a suitable solution, or - * things would have failed before getting in here. - */ -- set_bit(_VPF_migrating, &v->pause_flags); -+ vcpu_migrate_start(v); - vcpu_schedule_unlock_irqrestore(lock, flags, v); -- vcpu_sleep_nosync(v); -- vcpu_migrate(v); -+ -+ vcpu_migrate_finish(v); - - /* - * The only caveat, in this case, is that if a vcpu active in -@@ -849,18 +894,14 @@ static int vcpu_set_affinity( - * Always ask the scheduler to re-evaluate placement - * when changing the affinity. - */ -- set_bit(_VPF_migrating, &v->pause_flags); -+ vcpu_migrate_start(v); - } - - vcpu_schedule_unlock_irq(lock, v); - - domain_update_node_affinity(v->domain); - -- if ( v->pause_flags & VPF_migrating ) -- { -- vcpu_sleep_nosync(v); -- vcpu_migrate(v); -- } -+ vcpu_migrate_finish(v); - - return ret; - } -@@ -1088,7 +1129,6 @@ int vcpu_pin_override(struct vcpu *v, int cpu) - { - cpumask_copy(v->cpu_hard_affinity, v->cpu_hard_affinity_saved); - v->affinity_broken = 0; -- set_bit(_VPF_migrating, &v->pause_flags); - ret = 0; - } - } -@@ -1101,20 +1141,18 @@ int vcpu_pin_override(struct vcpu *v, int cpu) - cpumask_copy(v->cpu_hard_affinity_saved, v->cpu_hard_affinity); - v->affinity_broken = 1; - cpumask_copy(v->cpu_hard_affinity, cpumask_of(cpu)); -- set_bit(_VPF_migrating, &v->pause_flags); - ret = 0; - } - } - -+ if ( ret == 0 ) -+ vcpu_migrate_start(v); -+ - vcpu_schedule_unlock_irq(lock, v); - - domain_update_node_affinity(v->domain); - -- if ( v->pause_flags & VPF_migrating ) -- { -- vcpu_sleep_nosync(v); -- vcpu_migrate(v); -- } -+ vcpu_migrate_finish(v); - - return ret; - } -@@ -1501,8 +1539,7 @@ void context_saved(struct vcpu *prev) - - SCHED_OP(vcpu_scheduler(prev), context_saved, prev); - -- if ( unlikely(prev->pause_flags & VPF_migrating) ) -- vcpu_migrate(prev); -+ vcpu_migrate_finish(prev); - } - - /* The scheduler timer: force a run through the scheduler */ -diff --git a/xen/include/asm-x86/debugreg.h b/xen/include/asm-x86/debugreg.h -index c57914efc6..b3b10eaf40 100644 ---- a/xen/include/asm-x86/debugreg.h -+++ b/xen/include/asm-x86/debugreg.h -@@ -24,6 +24,8 @@ - #define DR_STATUS_RESERVED_ZERO (~0xffffeffful) /* Reserved, read as zero */ - #define DR_STATUS_RESERVED_ONE 0xffff0ff0ul /* Reserved, read as one */ - -+#define X86_DR6_DEFAULT 0xffff0ff0ul /* Default %dr6 value. */ -+ - /* Now define a bunch of things for manipulating the control register. - The top two bytes of the control register consist of 4 fields of 4 - bits - each field corresponds to one of the four debug registers, -diff --git a/xen/include/asm-x86/hvm/irq.h b/xen/include/asm-x86/hvm/irq.h -index f756cb5a0d..1a52ec6045 100644 ---- a/xen/include/asm-x86/hvm/irq.h -+++ b/xen/include/asm-x86/hvm/irq.h -@@ -207,6 +207,9 @@ int hvm_set_pci_link_route(struct domain *d, u8 link, u8 isa_irq); - - int hvm_inject_msi(struct domain *d, uint64_t addr, uint32_t data); - -+/* Assert an IO APIC pin. */ -+int hvm_ioapic_assert(struct domain *d, unsigned int gsi, bool level); -+ - void hvm_maybe_deassert_evtchn_irq(void); - void hvm_assert_evtchn_irq(struct vcpu *v); - void hvm_set_callback_via(struct domain *d, uint64_t via); -diff --git a/xen/include/asm-x86/hvm/vpt.h b/xen/include/asm-x86/hvm/vpt.h -index 21166edd06..0eb5ff632e 100644 ---- a/xen/include/asm-x86/hvm/vpt.h -+++ b/xen/include/asm-x86/hvm/vpt.h -@@ -44,6 +44,7 @@ struct periodic_time { - bool_t warned_timeout_too_short; - #define PTSRC_isa 1 /* ISA time source */ - #define PTSRC_lapic 2 /* LAPIC time source */ -+#define PTSRC_ioapic 3 /* IOAPIC time source */ - u8 source; /* PTSRC_ */ - u8 irq; - struct vcpu *vcpu; /* vcpu timer interrupt delivers to */ -diff --git a/xen/include/asm-x86/msr-index.h b/xen/include/asm-x86/msr-index.h -index a8ceecf3e2..68fae91567 100644 ---- a/xen/include/asm-x86/msr-index.h -+++ b/xen/include/asm-x86/msr-index.h -@@ -31,6 +31,9 @@ - #define EFER_LMSLE (1<<_EFER_LMSLE) - #define EFER_FFXSE (1<<_EFER_FFXSE) - -+#define EFER_KNOWN_MASK (EFER_SCE | EFER_LME | EFER_LMA | EFER_NX | \ -+ EFER_SVME | EFER_LMSLE | EFER_FFXSE) -+ - /* Speculation Controls. */ - #define MSR_SPEC_CTRL 0x00000048 - #define SPEC_CTRL_IBRS (_AC(1, ULL) << 0) -@@ -42,6 +45,7 @@ - #define MSR_ARCH_CAPABILITIES 0x0000010a - #define ARCH_CAPABILITIES_RDCL_NO (_AC(1, ULL) << 0) - #define ARCH_CAPABILITIES_IBRS_ALL (_AC(1, ULL) << 1) -+#define ARCH_CAPS_RSBA (_AC(1, ULL) << 2) - - /* Intel MSRs. Some also available on other CPUs */ - #define MSR_IA32_PERFCTR0 0x000000c1 -diff --git a/xen/include/asm-x86/processor.h b/xen/include/asm-x86/processor.h -index 80f8411355..a152f1d413 100644 ---- a/xen/include/asm-x86/processor.h -+++ b/xen/include/asm-x86/processor.h -@@ -445,7 +445,8 @@ struct __packed __cacheline_aligned tss_struct { - #define IST_DF 1UL - #define IST_NMI 2UL - #define IST_MCE 3UL --#define IST_MAX 3UL -+#define IST_DB 4UL -+#define IST_MAX 4UL - - /* Set the interrupt stack table used by a particular interrupt - * descriptor table entry. */ diff --git a/system/xen/xen.SlackBuild b/system/xen/xen.SlackBuild index 07b3865e90466..29c2ddf3cd2ff 100644 --- a/system/xen/xen.SlackBuild +++ b/system/xen/xen.SlackBuild @@ -23,11 +23,11 @@ # ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. PRGNAM=xen -VERSION=${VERSION:-4.10.1} -BUILD=${BUILD:-2} +VERSION=${VERSION:-4.11.0} +BUILD=${BUILD:-1} TAG=${TAG:-_SBo} -SEABIOS=${SEABIOS:-1.10.2} +SEABIOS=${SEABIOS:-1.11.1} OVMF=${OVMF:-20170920_947f3737a} IPXE=${IPXE:-356f6c1b64d7a97746d1816cef8ca22bdd8d0b5d} @@ -125,9 +125,6 @@ find -L . \ \( -perm 666 -o -perm 664 -o -perm 640 -o -perm 600 -o -perm 444 \ -o -perm 440 -o -perm 400 \) -exec chmod 644 {} \; -# Needed by XSA-263 (for now...) -patch -p1 <$CWD/patches/xen-4.10.2-pre.patch - # Apply Xen Security Advisory patches for i in $CWD/xsa/* ; do case $i in @@ -145,7 +142,7 @@ cp $CWD/ipxe-git-$IPXE.tar.gz tools/firmware/etherboot/_ipxe.tar.gz ( # Seabios cd tools/firmware - tar -xf $CWD/seabios-$SEABIOS.tar.gz + tar -xf $CWD/seabios-$SEABIOS.tar.xz mv seabios-$SEABIOS seabios-dir-remote ln -s seabios-dir-remote seabios-dir make -C seabios-dir defconfig diff --git a/system/xen/xen.info b/system/xen/xen.info index 906a067f603a9..2e6b41b5828f6 100644 --- a/system/xen/xen.info +++ b/system/xen/xen.info @@ -1,7 +1,7 @@ PRGNAM="xen" -VERSION="4.10.1" +VERSION="4.11.0" HOMEPAGE="http://www.xenproject.org/" -DOWNLOAD="http://mirror.slackware.hr/sources/xen/xen-4.10.1.tar.gz \ +DOWNLOAD="http://mirror.slackware.hr/sources/xen/xen-4.11.0.tar.gz \ http://mirror.slackware.hr/sources/xen-extfiles/ipxe-git-356f6c1b64d7a97746d1816cef8ca22bdd8d0b5d.tar.gz \ http://mirror.slackware.hr/sources/xen-extfiles/lwip-1.3.0.tar.gz \ http://mirror.slackware.hr/sources/xen-extfiles/zlib-1.2.3.tar.gz \ @@ -11,9 +11,9 @@ DOWNLOAD="http://mirror.slackware.hr/sources/xen/xen-4.10.1.tar.gz \ http://mirror.slackware.hr/sources/xen-extfiles/polarssl-1.1.4-gpl.tgz \ http://mirror.slackware.hr/sources/xen-extfiles/gmp-4.3.2.tar.bz2 \ http://mirror.slackware.hr/sources/xen-extfiles/tpm_emulator-0.7.4.tar.gz \ - http://mirror.slackware.hr/sources/xen-seabios/seabios-1.10.2.tar.gz \ + http://mirror.slackware.hr/sources/xen-seabios/seabios-1.11.1.tar.xz \ http://mirror.slackware.hr/sources/xen-ovmf/xen-ovmf-20170920_947f3737a.tar.bz2" -MD5SUM="d1b1d14ce76622062c9977d9c8ba772e \ +MD5SUM="cbec0600284921744bc14119f4ed3fff \ 0061f103c84b25c2e6ac47649b909bde \ 36cc57650cffda9a0269493be2a169bb \ debc62758716a169df9f62e6ab2bc634 \ @@ -23,7 +23,7 @@ MD5SUM="d1b1d14ce76622062c9977d9c8ba772e \ 7b72caf22b01464ee7d6165f2fd85f44 \ dd60683d7057917e34630b4a787932e8 \ e26becb8a6a2b6695f6b3e8097593db8 \ - 03387d3c84c7f43d6b8ab894155e1289 \ + d63261e22f6423972fd484d995c85f9a \ 779a40b927fb78a0d1732bb688d7a257" DOWNLOAD_x86_64="" MD5SUM_x86_64="" diff --git a/system/xen/xsa/xsa263-4.10-0001-x86-spec_ctrl-Read-MSR_ARCH_CAPABILITIES-only-once.patch b/system/xen/xsa/xsa263-4.10-0001-x86-spec_ctrl-Read-MSR_ARCH_CAPABILITIES-only-once.patch deleted file mode 100644 index c26afebc201d6..0000000000000 --- a/system/xen/xsa/xsa263-4.10-0001-x86-spec_ctrl-Read-MSR_ARCH_CAPABILITIES-only-once.patch +++ /dev/null @@ -1,110 +0,0 @@ -From 13fafdf5c97d3bc2a8851c4d1796feac0f82d498 Mon Sep 17 00:00:00 2001 -From: Andrew Cooper <andrew.cooper3@citrix.com> -Date: Thu, 26 Apr 2018 12:21:00 +0100 -Subject: [PATCH] x86/spec_ctrl: Read MSR_ARCH_CAPABILITIES only once - -Make it available from the beginning of init_speculation_mitigations(), and -pass it into appropriate functions. Fix an RSBA typo while moving the -affected comment. - -Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com> -Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> -Reviewed-by: Wei Liu <wei.liu2@citrix.com> -Reviewed-by: Jan Beulich <jbeulich@suse.com> -Release-acked-by: Juergen Gross <jgross@suse.com> -(cherry picked from commit d6c65187252a6c1810fd24c4d46f812840de8d3c) ---- - xen/arch/x86/spec_ctrl.c | 34 ++++++++++++++-------------------- - 1 file changed, 14 insertions(+), 20 deletions(-) - -diff --git a/xen/arch/x86/spec_ctrl.c b/xen/arch/x86/spec_ctrl.c -index fa67a0f..dc90743 100644 ---- a/xen/arch/x86/spec_ctrl.c -+++ b/xen/arch/x86/spec_ctrl.c -@@ -81,18 +81,15 @@ static int __init parse_bti(const char *s) - } - custom_param("bti", parse_bti); - --static void __init print_details(enum ind_thunk thunk) -+static void __init print_details(enum ind_thunk thunk, uint64_t caps) - { - unsigned int _7d0 = 0, e8b = 0, tmp; -- uint64_t caps = 0; - - /* Collect diagnostics about available mitigations. */ - if ( boot_cpu_data.cpuid_level >= 7 ) - cpuid_count(7, 0, &tmp, &tmp, &tmp, &_7d0); - if ( boot_cpu_data.extended_cpuid_level >= 0x80000008 ) - cpuid(0x80000008, &tmp, &e8b, &tmp, &tmp); -- if ( _7d0 & cpufeat_mask(X86_FEATURE_ARCH_CAPS) ) -- rdmsrl(MSR_ARCH_CAPABILITIES, caps); - - printk(XENLOG_DEBUG "Speculative mitigation facilities:\n"); - -@@ -125,7 +122,7 @@ static void __init print_details(enum ind_thunk thunk) - } - - /* Calculate whether Retpoline is known-safe on this CPU. */ --static bool __init retpoline_safe(void) -+static bool __init retpoline_safe(uint64_t caps) - { - unsigned int ucode_rev = this_cpu(ucode_cpu_info).cpu_sig.rev; - -@@ -136,19 +133,12 @@ static bool __init retpoline_safe(void) - boot_cpu_data.x86 != 6 ) - return false; - -- if ( boot_cpu_has(X86_FEATURE_ARCH_CAPS) ) -- { -- uint64_t caps; -- -- rdmsrl(MSR_ARCH_CAPABILITIES, caps); -- -- /* -- * RBSA may be set by a hypervisor to indicate that we may move to a -- * processor which isn't retpoline-safe. -- */ -- if ( caps & ARCH_CAPS_RSBA ) -- return false; -- } -+ /* -+ * RSBA may be set by a hypervisor to indicate that we may move to a -+ * processor which isn't retpoline-safe. -+ */ -+ if ( caps & ARCH_CAPS_RSBA ) -+ return false; - - switch ( boot_cpu_data.x86_model ) - { -@@ -218,6 +208,10 @@ void __init init_speculation_mitigations(void) - { - enum ind_thunk thunk = THUNK_DEFAULT; - bool ibrs = false; -+ uint64_t caps = 0; -+ -+ if ( boot_cpu_has(X86_FEATURE_ARCH_CAPS) ) -+ rdmsrl(MSR_ARCH_CAPABILITIES, caps); - - /* - * Has the user specified any custom BTI mitigations? If so, follow their -@@ -246,7 +240,7 @@ void __init init_speculation_mitigations(void) - * On Intel hardware, we'd like to use retpoline in preference to - * IBRS, but only if it is safe on this hardware. - */ -- else if ( retpoline_safe() ) -+ else if ( retpoline_safe(caps) ) - thunk = THUNK_RETPOLINE; - else if ( boot_cpu_has(X86_FEATURE_IBRSB) ) - ibrs = true; -@@ -331,7 +325,7 @@ void __init init_speculation_mitigations(void) - /* (Re)init BSP state now that default_bti_ist_info has been calculated. */ - init_shadow_spec_ctrl_state(); - -- print_details(thunk); -+ print_details(thunk, caps); - } - - static void __init __maybe_unused build_assertions(void) --- -2.1.4 - diff --git a/system/xen/xsa/xsa263-4.10-0002-x86-spec_ctrl-Express-Xen-s-choice-of-MSR_SPEC_CTRL-.patch b/system/xen/xsa/xsa263-4.10-0002-x86-spec_ctrl-Express-Xen-s-choice-of-MSR_SPEC_CTRL-.patch deleted file mode 100644 index a954943b71949..0000000000000 --- a/system/xen/xsa/xsa263-4.10-0002-x86-spec_ctrl-Express-Xen-s-choice-of-MSR_SPEC_CTRL-.patch +++ /dev/null @@ -1,138 +0,0 @@ -From d7b345e4ca136a995bfaaf2ee20901ee20e63570 Mon Sep 17 00:00:00 2001 -From: Andrew Cooper <andrew.cooper3@citrix.com> -Date: Tue, 17 Apr 2018 14:15:04 +0100 -Subject: [PATCH] x86/spec_ctrl: Express Xen's choice of MSR_SPEC_CTRL value as - a variable - -At the moment, we have two different encodings of Xen's MSR_SPEC_CTRL value, -which is a side effect of how the Spectre series developed. One encoding is -via an alias with the bottom bit of bti_ist_info, and can encode IBRS or not, -but not other configurations such as STIBP. - -Break Xen's value out into a separate variable (in the top of stack block for -XPTI reasons) and use this instead of bti_ist_info in the IST path. - -Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com> -Reviewed-by: Wei Liu <wei.liu2@citrix.com> -Reviewed-by: Jan Beulich <jbeulich@suse.com> -Release-acked-by: Juergen Gross <jgross@suse.com> -(cherry picked from commit 66dfae0f32bfbc899c2f3446d5ee57068cb7f957) ---- - xen/arch/x86/spec_ctrl.c | 8 +++++--- - xen/arch/x86/x86_64/asm-offsets.c | 1 + - xen/include/asm-x86/current.h | 1 + - xen/include/asm-x86/spec_ctrl.h | 2 ++ - xen/include/asm-x86/spec_ctrl_asm.h | 8 ++------ - 5 files changed, 11 insertions(+), 9 deletions(-) - -diff --git a/xen/arch/x86/spec_ctrl.c b/xen/arch/x86/spec_ctrl.c -index dc90743..1143521 100644 ---- a/xen/arch/x86/spec_ctrl.c -+++ b/xen/arch/x86/spec_ctrl.c -@@ -38,6 +38,7 @@ static int8_t __initdata opt_ibrs = -1; - static bool __initdata opt_rsb_native = true; - static bool __initdata opt_rsb_vmexit = true; - bool __read_mostly opt_ibpb = true; -+uint8_t __read_mostly default_xen_spec_ctrl; - uint8_t __read_mostly default_bti_ist_info; - - static int __init parse_bti(const char *s) -@@ -285,11 +286,14 @@ void __init init_speculation_mitigations(void) - * guests. - */ - if ( ibrs ) -+ { -+ default_xen_spec_ctrl |= SPEC_CTRL_IBRS; - setup_force_cpu_cap(X86_FEATURE_XEN_IBRS_SET); -+ } - else - setup_force_cpu_cap(X86_FEATURE_XEN_IBRS_CLEAR); - -- default_bti_ist_info |= BTI_IST_WRMSR | ibrs; -+ default_bti_ist_info |= BTI_IST_WRMSR; - } - - /* -@@ -330,8 +334,6 @@ void __init init_speculation_mitigations(void) - - static void __init __maybe_unused build_assertions(void) - { -- /* The optimised assembly relies on this alias. */ -- BUILD_BUG_ON(BTI_IST_IBRS != SPEC_CTRL_IBRS); - } - - /* -diff --git a/xen/arch/x86/x86_64/asm-offsets.c b/xen/arch/x86/x86_64/asm-offsets.c -index 13478d4..0726147 100644 ---- a/xen/arch/x86/x86_64/asm-offsets.c -+++ b/xen/arch/x86/x86_64/asm-offsets.c -@@ -142,6 +142,7 @@ void __dummy__(void) - OFFSET(CPUINFO_xen_cr3, struct cpu_info, xen_cr3); - OFFSET(CPUINFO_pv_cr3, struct cpu_info, pv_cr3); - OFFSET(CPUINFO_shadow_spec_ctrl, struct cpu_info, shadow_spec_ctrl); -+ OFFSET(CPUINFO_xen_spec_ctrl, struct cpu_info, xen_spec_ctrl); - OFFSET(CPUINFO_use_shadow_spec_ctrl, struct cpu_info, use_shadow_spec_ctrl); - OFFSET(CPUINFO_bti_ist_info, struct cpu_info, bti_ist_info); - DEFINE(CPUINFO_sizeof, sizeof(struct cpu_info)); -diff --git a/xen/include/asm-x86/current.h b/xen/include/asm-x86/current.h -index 4678a0f..d10b13c 100644 ---- a/xen/include/asm-x86/current.h -+++ b/xen/include/asm-x86/current.h -@@ -56,6 +56,7 @@ struct cpu_info { - - /* See asm-x86/spec_ctrl_asm.h for usage. */ - unsigned int shadow_spec_ctrl; -+ uint8_t xen_spec_ctrl; - bool use_shadow_spec_ctrl; - uint8_t bti_ist_info; - -diff --git a/xen/include/asm-x86/spec_ctrl.h b/xen/include/asm-x86/spec_ctrl.h -index 5ab4ff3..5e4fc84 100644 ---- a/xen/include/asm-x86/spec_ctrl.h -+++ b/xen/include/asm-x86/spec_ctrl.h -@@ -27,6 +27,7 @@ - void init_speculation_mitigations(void); - - extern bool opt_ibpb; -+extern uint8_t default_xen_spec_ctrl; - extern uint8_t default_bti_ist_info; - - static inline void init_shadow_spec_ctrl_state(void) -@@ -34,6 +35,7 @@ static inline void init_shadow_spec_ctrl_state(void) - struct cpu_info *info = get_cpu_info(); - - info->shadow_spec_ctrl = info->use_shadow_spec_ctrl = 0; -+ info->xen_spec_ctrl = default_xen_spec_ctrl; - info->bti_ist_info = default_bti_ist_info; - } - -diff --git a/xen/include/asm-x86/spec_ctrl_asm.h b/xen/include/asm-x86/spec_ctrl_asm.h -index 1f2b6f3..697da13 100644 ---- a/xen/include/asm-x86/spec_ctrl_asm.h -+++ b/xen/include/asm-x86/spec_ctrl_asm.h -@@ -21,7 +21,6 @@ - #define __X86_SPEC_CTRL_ASM_H__ - - /* Encoding of the bottom bits in cpuinfo.bti_ist_info */ --#define BTI_IST_IBRS (1 << 0) - #define BTI_IST_WRMSR (1 << 1) - #define BTI_IST_RSB (1 << 2) - -@@ -286,12 +285,9 @@ - setz %dl - and %dl, STACK_CPUINFO_FIELD(use_shadow_spec_ctrl)(%r14) - -- /* -- * Load Xen's intended value. SPEC_CTRL_IBRS vs 0 is encoded in the -- * bottom bit of bti_ist_info, via a deliberate alias with BTI_IST_IBRS. -- */ -+ /* Load Xen's intended value. */ - mov $MSR_SPEC_CTRL, %ecx -- and $BTI_IST_IBRS, %eax -+ movzbl STACK_CPUINFO_FIELD(xen_spec_ctrl)(%r14), %eax - xor %edx, %edx - wrmsr - --- -2.1.4 - diff --git a/system/xen/xsa/xsa263-4.10-0003-x86-spec_ctrl-Merge-bti_ist_info-and-use_shadow_spec.patch b/system/xen/xsa/xsa263-4.10-0003-x86-spec_ctrl-Merge-bti_ist_info-and-use_shadow_spec.patch deleted file mode 100644 index 7468f9ce286b0..0000000000000 --- a/system/xen/xsa/xsa263-4.10-0003-x86-spec_ctrl-Merge-bti_ist_info-and-use_shadow_spec.patch +++ /dev/null @@ -1,340 +0,0 @@ -From a0c2f734b4c683cb407e10ff943671c413480287 Mon Sep 17 00:00:00 2001 -From: Andrew Cooper <andrew.cooper3@citrix.com> -Date: Tue, 17 Apr 2018 14:15:04 +0100 -Subject: [PATCH] x86/spec_ctrl: Merge bti_ist_info and use_shadow_spec_ctrl - into spec_ctrl_flags - -All 3 bits of information here are control flags for the entry/exit code -behaviour. Treat them as such, rather than having two different variables. - -Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com> -Reviewed-by: Wei Liu <wei.liu2@citrix.com> -Reviewed-by: Jan Beulich <jbeulich@suse.com> -Release-acked-by: Juergen Gross <jgross@suse.com> -(cherry picked from commit 5262ba2e7799001402dfe139ff944e035dfff928) ---- - xen/arch/x86/acpi/power.c | 4 +-- - xen/arch/x86/spec_ctrl.c | 10 ++++--- - xen/arch/x86/x86_64/asm-offsets.c | 3 +-- - xen/include/asm-x86/current.h | 3 +-- - xen/include/asm-x86/nops.h | 5 ++-- - xen/include/asm-x86/spec_ctrl.h | 10 +++---- - xen/include/asm-x86/spec_ctrl_asm.h | 52 ++++++++++++++++++++----------------- - 7 files changed, 45 insertions(+), 42 deletions(-) - -diff --git a/xen/arch/x86/acpi/power.c b/xen/arch/x86/acpi/power.c -index f7085d3..f3480aa 100644 ---- a/xen/arch/x86/acpi/power.c -+++ b/xen/arch/x86/acpi/power.c -@@ -215,7 +215,7 @@ static int enter_state(u32 state) - ci = get_cpu_info(); - spec_ctrl_enter_idle(ci); - /* Avoid NMI/#MC using MSR_SPEC_CTRL until we've reloaded microcode. */ -- ci->bti_ist_info = 0; -+ ci->spec_ctrl_flags &= ~SCF_ist_wrmsr; - - ACPI_FLUSH_CPU_CACHE(); - -@@ -256,7 +256,7 @@ static int enter_state(u32 state) - microcode_resume_cpu(0); - - /* Re-enabled default NMI/#MC use of MSR_SPEC_CTRL. */ -- ci->bti_ist_info = default_bti_ist_info; -+ ci->spec_ctrl_flags |= (default_spec_ctrl_flags & SCF_ist_wrmsr); - spec_ctrl_exit_idle(ci); - - done: -diff --git a/xen/arch/x86/spec_ctrl.c b/xen/arch/x86/spec_ctrl.c -index 1143521..2d69910 100644 ---- a/xen/arch/x86/spec_ctrl.c -+++ b/xen/arch/x86/spec_ctrl.c -@@ -39,7 +39,7 @@ static bool __initdata opt_rsb_native = true; - static bool __initdata opt_rsb_vmexit = true; - bool __read_mostly opt_ibpb = true; - uint8_t __read_mostly default_xen_spec_ctrl; --uint8_t __read_mostly default_bti_ist_info; -+uint8_t __read_mostly default_spec_ctrl_flags; - - static int __init parse_bti(const char *s) - { -@@ -293,7 +293,7 @@ void __init init_speculation_mitigations(void) - else - setup_force_cpu_cap(X86_FEATURE_XEN_IBRS_CLEAR); - -- default_bti_ist_info |= BTI_IST_WRMSR; -+ default_spec_ctrl_flags |= SCF_ist_wrmsr; - } - - /* -@@ -312,7 +312,7 @@ void __init init_speculation_mitigations(void) - if ( opt_rsb_native ) - { - setup_force_cpu_cap(X86_FEATURE_RSB_NATIVE); -- default_bti_ist_info |= BTI_IST_RSB; -+ default_spec_ctrl_flags |= SCF_ist_rsb; - } - - /* -@@ -326,7 +326,7 @@ void __init init_speculation_mitigations(void) - if ( !boot_cpu_has(X86_FEATURE_IBRSB) && !boot_cpu_has(X86_FEATURE_IBPB) ) - opt_ibpb = false; - -- /* (Re)init BSP state now that default_bti_ist_info has been calculated. */ -+ /* (Re)init BSP state now that default_spec_ctrl_flags has been calculated. */ - init_shadow_spec_ctrl_state(); - - print_details(thunk, caps); -@@ -334,6 +334,8 @@ void __init init_speculation_mitigations(void) - - static void __init __maybe_unused build_assertions(void) - { -+ /* The optimised assembly relies on this alias. */ -+ BUILD_BUG_ON(SCF_use_shadow != 1); - } - - /* -diff --git a/xen/arch/x86/x86_64/asm-offsets.c b/xen/arch/x86/x86_64/asm-offsets.c -index 0726147..97242e5 100644 ---- a/xen/arch/x86/x86_64/asm-offsets.c -+++ b/xen/arch/x86/x86_64/asm-offsets.c -@@ -143,8 +143,7 @@ void __dummy__(void) - OFFSET(CPUINFO_pv_cr3, struct cpu_info, pv_cr3); - OFFSET(CPUINFO_shadow_spec_ctrl, struct cpu_info, shadow_spec_ctrl); - OFFSET(CPUINFO_xen_spec_ctrl, struct cpu_info, xen_spec_ctrl); -- OFFSET(CPUINFO_use_shadow_spec_ctrl, struct cpu_info, use_shadow_spec_ctrl); -- OFFSET(CPUINFO_bti_ist_info, struct cpu_info, bti_ist_info); -+ OFFSET(CPUINFO_spec_ctrl_flags, struct cpu_info, spec_ctrl_flags); - DEFINE(CPUINFO_sizeof, sizeof(struct cpu_info)); - BLANK(); - -diff --git a/xen/include/asm-x86/current.h b/xen/include/asm-x86/current.h -index d10b13c..7afff0e 100644 ---- a/xen/include/asm-x86/current.h -+++ b/xen/include/asm-x86/current.h -@@ -57,8 +57,7 @@ struct cpu_info { - /* See asm-x86/spec_ctrl_asm.h for usage. */ - unsigned int shadow_spec_ctrl; - uint8_t xen_spec_ctrl; -- bool use_shadow_spec_ctrl; -- uint8_t bti_ist_info; -+ uint8_t spec_ctrl_flags; - - unsigned long __pad; - /* get_stack_bottom() must be 16-byte aligned */ -diff --git a/xen/include/asm-x86/nops.h b/xen/include/asm-x86/nops.h -index 37f9819..b744895 100644 ---- a/xen/include/asm-x86/nops.h -+++ b/xen/include/asm-x86/nops.h -@@ -62,10 +62,9 @@ - #define ASM_NOP8 _ASM_MK_NOP(K8_NOP8) - - #define ASM_NOP17 ASM_NOP8; ASM_NOP7; ASM_NOP2 --#define ASM_NOP21 ASM_NOP8; ASM_NOP8; ASM_NOP5 -+#define ASM_NOP22 ASM_NOP8; ASM_NOP8; ASM_NOP6 - #define ASM_NOP24 ASM_NOP8; ASM_NOP8; ASM_NOP8 --#define ASM_NOP29 ASM_NOP8; ASM_NOP8; ASM_NOP8; ASM_NOP5 --#define ASM_NOP32 ASM_NOP8; ASM_NOP8; ASM_NOP8; ASM_NOP8 -+#define ASM_NOP33 ASM_NOP8; ASM_NOP8; ASM_NOP8; ASM_NOP7; ASM_NOP2 - #define ASM_NOP40 ASM_NOP8; ASM_NOP8; ASM_NOP8; ASM_NOP8; ASM_NOP8 - - #define ASM_NOP_MAX 8 -diff --git a/xen/include/asm-x86/spec_ctrl.h b/xen/include/asm-x86/spec_ctrl.h -index 5e4fc84..059e291 100644 ---- a/xen/include/asm-x86/spec_ctrl.h -+++ b/xen/include/asm-x86/spec_ctrl.h -@@ -28,15 +28,15 @@ void init_speculation_mitigations(void); - - extern bool opt_ibpb; - extern uint8_t default_xen_spec_ctrl; --extern uint8_t default_bti_ist_info; -+extern uint8_t default_spec_ctrl_flags; - - static inline void init_shadow_spec_ctrl_state(void) - { - struct cpu_info *info = get_cpu_info(); - -- info->shadow_spec_ctrl = info->use_shadow_spec_ctrl = 0; -+ info->shadow_spec_ctrl = 0; - info->xen_spec_ctrl = default_xen_spec_ctrl; -- info->bti_ist_info = default_bti_ist_info; -+ info->spec_ctrl_flags = default_spec_ctrl_flags; - } - - /* WARNING! `ret`, `call *`, `jmp *` not safe after this call. */ -@@ -50,7 +50,7 @@ static always_inline void spec_ctrl_enter_idle(struct cpu_info *info) - */ - info->shadow_spec_ctrl = val; - barrier(); -- info->use_shadow_spec_ctrl = true; -+ info->spec_ctrl_flags |= SCF_use_shadow; - barrier(); - asm volatile ( ALTERNATIVE(ASM_NOP3, "wrmsr", X86_FEATURE_XEN_IBRS_SET) - :: "a" (val), "c" (MSR_SPEC_CTRL), "d" (0) : "memory" ); -@@ -65,7 +65,7 @@ static always_inline void spec_ctrl_exit_idle(struct cpu_info *info) - * Disable shadowing before updating the MSR. There are no SMP issues - * here; only local processor ordering concerns. - */ -- info->use_shadow_spec_ctrl = false; -+ info->spec_ctrl_flags &= ~SCF_use_shadow; - barrier(); - asm volatile ( ALTERNATIVE(ASM_NOP3, "wrmsr", X86_FEATURE_XEN_IBRS_SET) - :: "a" (val), "c" (MSR_SPEC_CTRL), "d" (0) : "memory" ); -diff --git a/xen/include/asm-x86/spec_ctrl_asm.h b/xen/include/asm-x86/spec_ctrl_asm.h -index 697da13..39fb4f8 100644 ---- a/xen/include/asm-x86/spec_ctrl_asm.h -+++ b/xen/include/asm-x86/spec_ctrl_asm.h -@@ -20,9 +20,10 @@ - #ifndef __X86_SPEC_CTRL_ASM_H__ - #define __X86_SPEC_CTRL_ASM_H__ - --/* Encoding of the bottom bits in cpuinfo.bti_ist_info */ --#define BTI_IST_WRMSR (1 << 1) --#define BTI_IST_RSB (1 << 2) -+/* Encoding of cpuinfo.spec_ctrl_flags */ -+#define SCF_use_shadow (1 << 0) -+#define SCF_ist_wrmsr (1 << 1) -+#define SCF_ist_rsb (1 << 2) - - #ifdef __ASSEMBLY__ - #include <asm/msr-index.h> -@@ -49,20 +50,20 @@ - * after VMEXIT. The VMEXIT-specific code reads MSR_SPEC_CTRL and updates - * current before loading Xen's MSR_SPEC_CTRL setting. - * -- * Factor 2 is harder. We maintain a shadow_spec_ctrl value, and -- * use_shadow_spec_ctrl boolean per cpu. The synchronous use is: -+ * Factor 2 is harder. We maintain a shadow_spec_ctrl value, and a use_shadow -+ * boolean in the per cpu spec_ctrl_flags. The synchronous use is: - * - * 1) Store guest value in shadow_spec_ctrl -- * 2) Set use_shadow_spec_ctrl boolean -+ * 2) Set the use_shadow boolean - * 3) Load guest value into MSR_SPEC_CTRL - * 4) Exit to guest - * 5) Entry from guest -- * 6) Clear use_shadow_spec_ctrl boolean -+ * 6) Clear the use_shadow boolean - * 7) Load Xen's value into MSR_SPEC_CTRL - * - * The asynchronous use for interrupts/exceptions is: - * - Set/clear IBRS on entry to Xen -- * - On exit to Xen, check use_shadow_spec_ctrl -+ * - On exit to Xen, check use_shadow - * - If set, load shadow_spec_ctrl - * - * Therefore, an interrupt/exception which hits the synchronous path between -@@ -134,7 +135,7 @@ - xor %edx, %edx - - /* Clear SPEC_CTRL shadowing *before* loading Xen's value. */ -- movb %dl, CPUINFO_use_shadow_spec_ctrl(%rsp) -+ andb $~SCF_use_shadow, CPUINFO_spec_ctrl_flags(%rsp) - - /* Load Xen's intended value. */ - mov $\ibrs_val, %eax -@@ -160,12 +161,14 @@ - * block so calculate the position directly. - */ - .if \maybexen -+ xor %eax, %eax - /* Branchless `if ( !xen ) clear_shadowing` */ - testb $3, UREGS_cs(%rsp) -- setz %al -- and %al, STACK_CPUINFO_FIELD(use_shadow_spec_ctrl)(%r14) -+ setnz %al -+ not %eax -+ and %al, STACK_CPUINFO_FIELD(spec_ctrl_flags)(%r14) - .else -- movb %dl, CPUINFO_use_shadow_spec_ctrl(%rsp) -+ andb $~SCF_use_shadow, CPUINFO_spec_ctrl_flags(%rsp) - .endif - - /* Load Xen's intended value. */ -@@ -184,8 +187,8 @@ - */ - xor %edx, %edx - -- cmpb %dl, STACK_CPUINFO_FIELD(use_shadow_spec_ctrl)(%rbx) -- je .L\@_skip -+ testb $SCF_use_shadow, STACK_CPUINFO_FIELD(spec_ctrl_flags)(%rbx) -+ jz .L\@_skip - - mov STACK_CPUINFO_FIELD(shadow_spec_ctrl)(%rbx), %eax - mov $MSR_SPEC_CTRL, %ecx -@@ -206,7 +209,7 @@ - mov %eax, CPUINFO_shadow_spec_ctrl(%rsp) - - /* Set SPEC_CTRL shadowing *before* loading the guest value. */ -- movb $1, CPUINFO_use_shadow_spec_ctrl(%rsp) -+ orb $SCF_use_shadow, CPUINFO_spec_ctrl_flags(%rsp) - - mov $MSR_SPEC_CTRL, %ecx - xor %edx, %edx -@@ -217,7 +220,7 @@ - #define SPEC_CTRL_ENTRY_FROM_VMEXIT \ - ALTERNATIVE __stringify(ASM_NOP40), \ - DO_OVERWRITE_RSB, X86_FEATURE_RSB_VMEXIT; \ -- ALTERNATIVE_2 __stringify(ASM_NOP32), \ -+ ALTERNATIVE_2 __stringify(ASM_NOP33), \ - __stringify(DO_SPEC_CTRL_ENTRY_FROM_VMEXIT \ - ibrs_val=SPEC_CTRL_IBRS), \ - X86_FEATURE_XEN_IBRS_SET, \ -@@ -229,7 +232,7 @@ - #define SPEC_CTRL_ENTRY_FROM_PV \ - ALTERNATIVE __stringify(ASM_NOP40), \ - DO_OVERWRITE_RSB, X86_FEATURE_RSB_NATIVE; \ -- ALTERNATIVE_2 __stringify(ASM_NOP21), \ -+ ALTERNATIVE_2 __stringify(ASM_NOP22), \ - __stringify(DO_SPEC_CTRL_ENTRY maybexen=0 \ - ibrs_val=SPEC_CTRL_IBRS), \ - X86_FEATURE_XEN_IBRS_SET, \ -@@ -240,7 +243,7 @@ - #define SPEC_CTRL_ENTRY_FROM_INTR \ - ALTERNATIVE __stringify(ASM_NOP40), \ - DO_OVERWRITE_RSB, X86_FEATURE_RSB_NATIVE; \ -- ALTERNATIVE_2 __stringify(ASM_NOP29), \ -+ ALTERNATIVE_2 __stringify(ASM_NOP33), \ - __stringify(DO_SPEC_CTRL_ENTRY maybexen=1 \ - ibrs_val=SPEC_CTRL_IBRS), \ - X86_FEATURE_XEN_IBRS_SET, \ -@@ -268,22 +271,23 @@ - * This is logical merge of DO_OVERWRITE_RSB and DO_SPEC_CTRL_ENTRY - * maybexen=1, but with conditionals rather than alternatives. - */ -- movzbl STACK_CPUINFO_FIELD(bti_ist_info)(%r14), %eax -+ movzbl STACK_CPUINFO_FIELD(spec_ctrl_flags)(%r14), %eax - -- testb $BTI_IST_RSB, %al -+ test $SCF_ist_rsb, %al - jz .L\@_skip_rsb - - DO_OVERWRITE_RSB tmp=rdx /* Clobbers %rcx/%rdx */ - - .L\@_skip_rsb: - -- testb $BTI_IST_WRMSR, %al -+ test $SCF_ist_wrmsr, %al - jz .L\@_skip_wrmsr - - xor %edx, %edx - testb $3, UREGS_cs(%rsp) -- setz %dl -- and %dl, STACK_CPUINFO_FIELD(use_shadow_spec_ctrl)(%r14) -+ setnz %dl -+ not %edx -+ and %dl, STACK_CPUINFO_FIELD(spec_ctrl_flags)(%r14) - - /* Load Xen's intended value. */ - mov $MSR_SPEC_CTRL, %ecx -@@ -310,7 +314,7 @@ UNLIKELY_DISPATCH_LABEL(\@_serialise): - * Requires %rbx=stack_end - * Clobbers %rax, %rcx, %rdx - */ -- testb $BTI_IST_WRMSR, STACK_CPUINFO_FIELD(bti_ist_info)(%rbx) -+ testb $SCF_ist_wrmsr, STACK_CPUINFO_FIELD(spec_ctrl_flags)(%rbx) - jz .L\@_skip - - DO_SPEC_CTRL_EXIT_TO_XEN --- -2.1.4 - diff --git a/system/xen/xsa/xsa263-4.10-0004-x86-spec_ctrl-Fold-the-XEN_IBRS_-SET-CLEAR-ALTERNATI.patch b/system/xen/xsa/xsa263-4.10-0004-x86-spec_ctrl-Fold-the-XEN_IBRS_-SET-CLEAR-ALTERNATI.patch deleted file mode 100644 index f6e87244dc52f..0000000000000 --- a/system/xen/xsa/xsa263-4.10-0004-x86-spec_ctrl-Fold-the-XEN_IBRS_-SET-CLEAR-ALTERNATI.patch +++ /dev/null @@ -1,221 +0,0 @@ -From 0b1aded85866f48cdede20c54d30cf593f8a83f7 Mon Sep 17 00:00:00 2001 -From: Andrew Cooper <andrew.cooper3@citrix.com> -Date: Tue, 17 Apr 2018 14:15:04 +0100 -Subject: [PATCH] x86/spec_ctrl: Fold the XEN_IBRS_{SET,CLEAR} ALTERNATIVES - together - -Currently, the SPEC_CTRL_{ENTRY,EXIT}_* macros encode Xen's choice of -MSR_SPEC_CTRL as an immediate constant, and chooses between IBRS or not by -doubling up the entire alternative block. - -There is now a variable holding Xen's choice of value, so use that and -simplify the alternatives. - -Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com> -Reviewed-by: Wei Liu <wei.liu2@citrix.com> -Reviewed-by: Jan Beulich <jbeulich@suse.com> -Release-acked-by: Juergen Gross <jgross@suse.com> -(cherry picked from commit af949407eaba7af71067f23d5866cd0bf1f1144d) ---- - xen/arch/x86/spec_ctrl.c | 12 +++++----- - xen/include/asm-x86/cpufeatures.h | 3 +-- - xen/include/asm-x86/nops.h | 3 ++- - xen/include/asm-x86/spec_ctrl.h | 6 ++--- - xen/include/asm-x86/spec_ctrl_asm.h | 45 +++++++++++++------------------------ - 5 files changed, 26 insertions(+), 43 deletions(-) - -diff --git a/xen/arch/x86/spec_ctrl.c b/xen/arch/x86/spec_ctrl.c -index 2d69910..b62cfcc 100644 ---- a/xen/arch/x86/spec_ctrl.c -+++ b/xen/arch/x86/spec_ctrl.c -@@ -112,8 +112,9 @@ static void __init print_details(enum ind_thunk thunk, uint64_t caps) - thunk == THUNK_RETPOLINE ? "RETPOLINE" : - thunk == THUNK_LFENCE ? "LFENCE" : - thunk == THUNK_JMP ? "JMP" : "?", -- boot_cpu_has(X86_FEATURE_XEN_IBRS_SET) ? " IBRS+" : -- boot_cpu_has(X86_FEATURE_XEN_IBRS_CLEAR) ? " IBRS-" : "", -+ boot_cpu_has(X86_FEATURE_SC_MSR) ? -+ default_xen_spec_ctrl & SPEC_CTRL_IBRS ? " IBRS+" : -+ " IBRS-" : "", - opt_ibpb ? " IBPB" : "", - boot_cpu_has(X86_FEATURE_RSB_NATIVE) ? " RSB_NATIVE" : "", - boot_cpu_has(X86_FEATURE_RSB_VMEXIT) ? " RSB_VMEXIT" : ""); -@@ -285,13 +286,10 @@ void __init init_speculation_mitigations(void) - * need the IBRS entry/exit logic to virtualise IBRS support for - * guests. - */ -+ setup_force_cpu_cap(X86_FEATURE_SC_MSR); -+ - if ( ibrs ) -- { - default_xen_spec_ctrl |= SPEC_CTRL_IBRS; -- setup_force_cpu_cap(X86_FEATURE_XEN_IBRS_SET); -- } -- else -- setup_force_cpu_cap(X86_FEATURE_XEN_IBRS_CLEAR); - - default_spec_ctrl_flags |= SCF_ist_wrmsr; - } -diff --git a/xen/include/asm-x86/cpufeatures.h b/xen/include/asm-x86/cpufeatures.h -index c9b1a48..ca58b0e 100644 ---- a/xen/include/asm-x86/cpufeatures.h -+++ b/xen/include/asm-x86/cpufeatures.h -@@ -26,8 +26,7 @@ XEN_CPUFEATURE(LFENCE_DISPATCH, (FSCAPINTS+0)*32+12) /* lfence set as Dispatch S - XEN_CPUFEATURE(IND_THUNK_LFENCE,(FSCAPINTS+0)*32+13) /* Use IND_THUNK_LFENCE */ - XEN_CPUFEATURE(IND_THUNK_JMP, (FSCAPINTS+0)*32+14) /* Use IND_THUNK_JMP */ - XEN_CPUFEATURE(XEN_IBPB, (FSCAPINTS+0)*32+15) /* IBRSB || IBPB */ --XEN_CPUFEATURE(XEN_IBRS_SET, (FSCAPINTS+0)*32+16) /* IBRSB && IRBS set in Xen */ --XEN_CPUFEATURE(XEN_IBRS_CLEAR, (FSCAPINTS+0)*32+17) /* IBRSB && IBRS clear in Xen */ -+XEN_CPUFEATURE(SC_MSR, (FSCAPINTS+0)*32+16) /* MSR_SPEC_CTRL used by Xen */ - XEN_CPUFEATURE(RSB_NATIVE, (FSCAPINTS+0)*32+18) /* RSB overwrite needed for native */ - XEN_CPUFEATURE(RSB_VMEXIT, (FSCAPINTS+0)*32+19) /* RSB overwrite needed for vmexit */ - XEN_CPUFEATURE(NO_XPTI, (FSCAPINTS+0)*32+20) /* XPTI mitigation not in use */ -diff --git a/xen/include/asm-x86/nops.h b/xen/include/asm-x86/nops.h -index b744895..913e9f0 100644 ---- a/xen/include/asm-x86/nops.h -+++ b/xen/include/asm-x86/nops.h -@@ -62,9 +62,10 @@ - #define ASM_NOP8 _ASM_MK_NOP(K8_NOP8) - - #define ASM_NOP17 ASM_NOP8; ASM_NOP7; ASM_NOP2 --#define ASM_NOP22 ASM_NOP8; ASM_NOP8; ASM_NOP6 - #define ASM_NOP24 ASM_NOP8; ASM_NOP8; ASM_NOP8 -+#define ASM_NOP25 ASM_NOP8; ASM_NOP8; ASM_NOP7; ASM_NOP2 - #define ASM_NOP33 ASM_NOP8; ASM_NOP8; ASM_NOP8; ASM_NOP7; ASM_NOP2 -+#define ASM_NOP36 ASM_NOP8; ASM_NOP8; ASM_NOP8; ASM_NOP8; ASM_NOP4 - #define ASM_NOP40 ASM_NOP8; ASM_NOP8; ASM_NOP8; ASM_NOP8; ASM_NOP8 - - #define ASM_NOP_MAX 8 -diff --git a/xen/include/asm-x86/spec_ctrl.h b/xen/include/asm-x86/spec_ctrl.h -index 059e291..7d7c42e 100644 ---- a/xen/include/asm-x86/spec_ctrl.h -+++ b/xen/include/asm-x86/spec_ctrl.h -@@ -52,14 +52,14 @@ static always_inline void spec_ctrl_enter_idle(struct cpu_info *info) - barrier(); - info->spec_ctrl_flags |= SCF_use_shadow; - barrier(); -- asm volatile ( ALTERNATIVE(ASM_NOP3, "wrmsr", X86_FEATURE_XEN_IBRS_SET) -+ asm volatile ( ALTERNATIVE(ASM_NOP3, "wrmsr", X86_FEATURE_SC_MSR) - :: "a" (val), "c" (MSR_SPEC_CTRL), "d" (0) : "memory" ); - } - - /* WARNING! `ret`, `call *`, `jmp *` not safe before this call. */ - static always_inline void spec_ctrl_exit_idle(struct cpu_info *info) - { -- uint32_t val = SPEC_CTRL_IBRS; -+ uint32_t val = info->xen_spec_ctrl; - - /* - * Disable shadowing before updating the MSR. There are no SMP issues -@@ -67,7 +67,7 @@ static always_inline void spec_ctrl_exit_idle(struct cpu_info *info) - */ - info->spec_ctrl_flags &= ~SCF_use_shadow; - barrier(); -- asm volatile ( ALTERNATIVE(ASM_NOP3, "wrmsr", X86_FEATURE_XEN_IBRS_SET) -+ asm volatile ( ALTERNATIVE(ASM_NOP3, "wrmsr", X86_FEATURE_SC_MSR) - :: "a" (val), "c" (MSR_SPEC_CTRL), "d" (0) : "memory" ); - } - -diff --git a/xen/include/asm-x86/spec_ctrl_asm.h b/xen/include/asm-x86/spec_ctrl_asm.h -index 39fb4f8..17dd2cc 100644 ---- a/xen/include/asm-x86/spec_ctrl_asm.h -+++ b/xen/include/asm-x86/spec_ctrl_asm.h -@@ -117,7 +117,7 @@ - mov %\tmp, %rsp /* Restore old %rsp */ - .endm - --.macro DO_SPEC_CTRL_ENTRY_FROM_VMEXIT ibrs_val:req -+.macro DO_SPEC_CTRL_ENTRY_FROM_VMEXIT - /* - * Requires %rbx=current, %rsp=regs/cpuinfo - * Clobbers %rax, %rcx, %rdx -@@ -138,11 +138,11 @@ - andb $~SCF_use_shadow, CPUINFO_spec_ctrl_flags(%rsp) - - /* Load Xen's intended value. */ -- mov $\ibrs_val, %eax -+ movzbl CPUINFO_xen_spec_ctrl(%rsp), %eax - wrmsr - .endm - --.macro DO_SPEC_CTRL_ENTRY maybexen:req ibrs_val:req -+.macro DO_SPEC_CTRL_ENTRY maybexen:req - /* - * Requires %rsp=regs (also cpuinfo if !maybexen) - * Requires %r14=stack_end (if maybexen) -@@ -167,12 +167,12 @@ - setnz %al - not %eax - and %al, STACK_CPUINFO_FIELD(spec_ctrl_flags)(%r14) -+ movzbl STACK_CPUINFO_FIELD(xen_spec_ctrl)(%r14), %eax - .else - andb $~SCF_use_shadow, CPUINFO_spec_ctrl_flags(%rsp) -+ movzbl CPUINFO_xen_spec_ctrl(%rsp), %eax - .endif - -- /* Load Xen's intended value. */ -- mov $\ibrs_val, %eax - wrmsr - .endm - -@@ -220,47 +220,32 @@ - #define SPEC_CTRL_ENTRY_FROM_VMEXIT \ - ALTERNATIVE __stringify(ASM_NOP40), \ - DO_OVERWRITE_RSB, X86_FEATURE_RSB_VMEXIT; \ -- ALTERNATIVE_2 __stringify(ASM_NOP33), \ -- __stringify(DO_SPEC_CTRL_ENTRY_FROM_VMEXIT \ -- ibrs_val=SPEC_CTRL_IBRS), \ -- X86_FEATURE_XEN_IBRS_SET, \ -- __stringify(DO_SPEC_CTRL_ENTRY_FROM_VMEXIT \ -- ibrs_val=0), \ -- X86_FEATURE_XEN_IBRS_CLEAR -+ ALTERNATIVE __stringify(ASM_NOP36), \ -+ DO_SPEC_CTRL_ENTRY_FROM_VMEXIT, X86_FEATURE_SC_MSR - - /* Use after an entry from PV context (syscall/sysenter/int80/int82/etc). */ - #define SPEC_CTRL_ENTRY_FROM_PV \ - ALTERNATIVE __stringify(ASM_NOP40), \ - DO_OVERWRITE_RSB, X86_FEATURE_RSB_NATIVE; \ -- ALTERNATIVE_2 __stringify(ASM_NOP22), \ -- __stringify(DO_SPEC_CTRL_ENTRY maybexen=0 \ -- ibrs_val=SPEC_CTRL_IBRS), \ -- X86_FEATURE_XEN_IBRS_SET, \ -- __stringify(DO_SPEC_CTRL_ENTRY maybexen=0 ibrs_val=0), \ -- X86_FEATURE_XEN_IBRS_CLEAR -+ ALTERNATIVE __stringify(ASM_NOP25), \ -+ __stringify(DO_SPEC_CTRL_ENTRY maybexen=0), X86_FEATURE_SC_MSR - - /* Use in interrupt/exception context. May interrupt Xen or PV context. */ - #define SPEC_CTRL_ENTRY_FROM_INTR \ - ALTERNATIVE __stringify(ASM_NOP40), \ - DO_OVERWRITE_RSB, X86_FEATURE_RSB_NATIVE; \ -- ALTERNATIVE_2 __stringify(ASM_NOP33), \ -- __stringify(DO_SPEC_CTRL_ENTRY maybexen=1 \ -- ibrs_val=SPEC_CTRL_IBRS), \ -- X86_FEATURE_XEN_IBRS_SET, \ -- __stringify(DO_SPEC_CTRL_ENTRY maybexen=1 ibrs_val=0), \ -- X86_FEATURE_XEN_IBRS_CLEAR -+ ALTERNATIVE __stringify(ASM_NOP33), \ -+ __stringify(DO_SPEC_CTRL_ENTRY maybexen=1), X86_FEATURE_SC_MSR - - /* Use when exiting to Xen context. */ - #define SPEC_CTRL_EXIT_TO_XEN \ -- ALTERNATIVE_2 __stringify(ASM_NOP17), \ -- DO_SPEC_CTRL_EXIT_TO_XEN, X86_FEATURE_XEN_IBRS_SET, \ -- DO_SPEC_CTRL_EXIT_TO_XEN, X86_FEATURE_XEN_IBRS_CLEAR -+ ALTERNATIVE __stringify(ASM_NOP17), \ -+ DO_SPEC_CTRL_EXIT_TO_XEN, X86_FEATURE_SC_MSR - - /* Use when exiting to guest context. */ - #define SPEC_CTRL_EXIT_TO_GUEST \ -- ALTERNATIVE_2 __stringify(ASM_NOP24), \ -- DO_SPEC_CTRL_EXIT_TO_GUEST, X86_FEATURE_XEN_IBRS_SET, \ -- DO_SPEC_CTRL_EXIT_TO_GUEST, X86_FEATURE_XEN_IBRS_CLEAR -+ ALTERNATIVE __stringify(ASM_NOP24), \ -+ DO_SPEC_CTRL_EXIT_TO_GUEST, X86_FEATURE_SC_MSR - - /* TODO: Drop these when the alternatives infrastructure is NMI/#MC safe. */ - .macro SPEC_CTRL_ENTRY_FROM_INTR_IST --- -2.1.4 - diff --git a/system/xen/xsa/xsa263-4.10-0005-x86-spec_ctrl-Rename-bits-of-infrastructure-to-avoid.patch b/system/xen/xsa/xsa263-4.10-0005-x86-spec_ctrl-Rename-bits-of-infrastructure-to-avoid.patch deleted file mode 100644 index f4efabeb462bb..0000000000000 --- a/system/xen/xsa/xsa263-4.10-0005-x86-spec_ctrl-Rename-bits-of-infrastructure-to-avoid.patch +++ /dev/null @@ -1,273 +0,0 @@ -From 5cc3611de7d09140e55caa2c2d120ad326fff937 Mon Sep 17 00:00:00 2001 -From: Andrew Cooper <andrew.cooper3@citrix.com> -Date: Mon, 30 Apr 2018 14:20:23 +0100 -Subject: [PATCH] x86/spec_ctrl: Rename bits of infrastructure to avoid NATIVE - and VMEXIT - -In hindsight, using NATIVE and VMEXIT as naming terminology was not clever. -A future change wants to split SPEC_CTRL_EXIT_TO_GUEST into PV and HVM -specific implementations, and using VMEXIT as a term is completely wrong. - -Take the opportunity to fix some stale documentation in spec_ctrl_asm.h. The -IST helpers were missing from the large comment block, and since -SPEC_CTRL_ENTRY_FROM_INTR_IST was introduced, we've gained a new piece of -functionality which currently depends on the fine grain control, which exists -in lieu of livepatching. Note this in the comment. - -No functional change. - -Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com> -Reviewed-by: Wei Liu <wei.liu2@citrix.com> -Reviewed-by: Jan Beulich <jbeulich@suse.com> -Release-acked-by: Juergen Gross <jgross@suse.com> -(cherry picked from commit d9822b8a38114e96e4516dc998f4055249364d5d) ---- - xen/arch/x86/hvm/svm/entry.S | 4 ++-- - xen/arch/x86/hvm/vmx/entry.S | 4 ++-- - xen/arch/x86/spec_ctrl.c | 20 ++++++++++---------- - xen/arch/x86/x86_64/compat/entry.S | 2 +- - xen/arch/x86/x86_64/entry.S | 2 +- - xen/include/asm-x86/cpufeatures.h | 4 ++-- - xen/include/asm-x86/spec_ctrl_asm.h | 36 +++++++++++++++++++++++++----------- - 7 files changed, 43 insertions(+), 29 deletions(-) - -diff --git a/xen/arch/x86/hvm/svm/entry.S b/xen/arch/x86/hvm/svm/entry.S -index bf092fe..5e7c080 100644 ---- a/xen/arch/x86/hvm/svm/entry.S -+++ b/xen/arch/x86/hvm/svm/entry.S -@@ -83,7 +83,7 @@ UNLIKELY_END(svm_trace) - mov VCPUMSR_spec_ctrl_raw(%rax), %eax - - /* WARNING! `ret`, `call *`, `jmp *` not safe beyond this point. */ -- SPEC_CTRL_EXIT_TO_GUEST /* Req: a=spec_ctrl %rsp=regs/cpuinfo, Clob: cd */ -+ SPEC_CTRL_EXIT_TO_HVM /* Req: a=spec_ctrl %rsp=regs/cpuinfo, Clob: cd */ - - pop %r15 - pop %r14 -@@ -108,7 +108,7 @@ UNLIKELY_END(svm_trace) - - GET_CURRENT(bx) - -- SPEC_CTRL_ENTRY_FROM_VMEXIT /* Req: b=curr %rsp=regs/cpuinfo, Clob: acd */ -+ SPEC_CTRL_ENTRY_FROM_HVM /* Req: b=curr %rsp=regs/cpuinfo, Clob: acd */ - /* WARNING! `ret`, `call *`, `jmp *` not safe before this point. */ - - mov VCPU_svm_vmcb(%rbx),%rcx -diff --git a/xen/arch/x86/hvm/vmx/entry.S b/xen/arch/x86/hvm/vmx/entry.S -index e750544..aa2f103 100644 ---- a/xen/arch/x86/hvm/vmx/entry.S -+++ b/xen/arch/x86/hvm/vmx/entry.S -@@ -38,7 +38,7 @@ ENTRY(vmx_asm_vmexit_handler) - movb $1,VCPU_vmx_launched(%rbx) - mov %rax,VCPU_hvm_guest_cr2(%rbx) - -- SPEC_CTRL_ENTRY_FROM_VMEXIT /* Req: b=curr %rsp=regs/cpuinfo, Clob: acd */ -+ SPEC_CTRL_ENTRY_FROM_HVM /* Req: b=curr %rsp=regs/cpuinfo, Clob: acd */ - /* WARNING! `ret`, `call *`, `jmp *` not safe before this point. */ - - mov %rsp,%rdi -@@ -76,7 +76,7 @@ UNLIKELY_END(realmode) - mov VCPUMSR_spec_ctrl_raw(%rax), %eax - - /* WARNING! `ret`, `call *`, `jmp *` not safe beyond this point. */ -- SPEC_CTRL_EXIT_TO_GUEST /* Req: a=spec_ctrl %rsp=regs/cpuinfo, Clob: cd */ -+ SPEC_CTRL_EXIT_TO_HVM /* Req: a=spec_ctrl %rsp=regs/cpuinfo, Clob: cd */ - - mov VCPU_hvm_guest_cr2(%rbx),%rax - -diff --git a/xen/arch/x86/spec_ctrl.c b/xen/arch/x86/spec_ctrl.c -index b62cfcc..015a9e2 100644 ---- a/xen/arch/x86/spec_ctrl.c -+++ b/xen/arch/x86/spec_ctrl.c -@@ -35,8 +35,8 @@ static enum ind_thunk { - THUNK_JMP, - } opt_thunk __initdata = THUNK_DEFAULT; - static int8_t __initdata opt_ibrs = -1; --static bool __initdata opt_rsb_native = true; --static bool __initdata opt_rsb_vmexit = true; -+static bool __initdata opt_rsb_pv = true; -+static bool __initdata opt_rsb_hvm = true; - bool __read_mostly opt_ibpb = true; - uint8_t __read_mostly default_xen_spec_ctrl; - uint8_t __read_mostly default_spec_ctrl_flags; -@@ -69,9 +69,9 @@ static int __init parse_bti(const char *s) - else if ( (val = parse_boolean("ibpb", s, ss)) >= 0 ) - opt_ibpb = val; - else if ( (val = parse_boolean("rsb_native", s, ss)) >= 0 ) -- opt_rsb_native = val; -+ opt_rsb_pv = val; - else if ( (val = parse_boolean("rsb_vmexit", s, ss)) >= 0 ) -- opt_rsb_vmexit = val; -+ opt_rsb_hvm = val; - else - rc = -EINVAL; - -@@ -116,8 +116,8 @@ static void __init print_details(enum ind_thunk thunk, uint64_t caps) - default_xen_spec_ctrl & SPEC_CTRL_IBRS ? " IBRS+" : - " IBRS-" : "", - opt_ibpb ? " IBPB" : "", -- boot_cpu_has(X86_FEATURE_RSB_NATIVE) ? " RSB_NATIVE" : "", -- boot_cpu_has(X86_FEATURE_RSB_VMEXIT) ? " RSB_VMEXIT" : ""); -+ boot_cpu_has(X86_FEATURE_SC_RSB_PV) ? " RSB_NATIVE" : "", -+ boot_cpu_has(X86_FEATURE_SC_RSB_HVM) ? " RSB_VMEXIT" : ""); - - printk("XPTI: %s\n", - boot_cpu_has(X86_FEATURE_NO_XPTI) ? "disabled" : "enabled"); -@@ -307,9 +307,9 @@ void __init init_speculation_mitigations(void) - * If a processors speculates to 32bit PV guest kernel mappings, it is - * speculating in 64bit supervisor mode, and can leak data. - */ -- if ( opt_rsb_native ) -+ if ( opt_rsb_pv ) - { -- setup_force_cpu_cap(X86_FEATURE_RSB_NATIVE); -+ setup_force_cpu_cap(X86_FEATURE_SC_RSB_PV); - default_spec_ctrl_flags |= SCF_ist_rsb; - } - -@@ -317,8 +317,8 @@ void __init init_speculation_mitigations(void) - * HVM guests can always poison the RSB to point at Xen supervisor - * mappings. - */ -- if ( opt_rsb_vmexit ) -- setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT); -+ if ( opt_rsb_hvm ) -+ setup_force_cpu_cap(X86_FEATURE_SC_RSB_HVM); - - /* Check we have hardware IBPB support before using it... */ - if ( !boot_cpu_has(X86_FEATURE_IBRSB) && !boot_cpu_has(X86_FEATURE_IBPB) ) -diff --git a/xen/arch/x86/x86_64/compat/entry.S b/xen/arch/x86/x86_64/compat/entry.S -index a47cb9d..6a27d98 100644 ---- a/xen/arch/x86/x86_64/compat/entry.S -+++ b/xen/arch/x86/x86_64/compat/entry.S -@@ -166,7 +166,7 @@ ENTRY(compat_restore_all_guest) - mov VCPUMSR_spec_ctrl_raw(%rax), %eax - - /* WARNING! `ret`, `call *`, `jmp *` not safe beyond this point. */ -- SPEC_CTRL_EXIT_TO_GUEST /* Req: a=spec_ctrl %rsp=regs/cpuinfo, Clob: cd */ -+ SPEC_CTRL_EXIT_TO_PV /* Req: a=spec_ctrl %rsp=regs/cpuinfo, Clob: cd */ - - RESTORE_ALL adj=8 compat=1 - .Lft0: iretq -diff --git a/xen/arch/x86/x86_64/entry.S b/xen/arch/x86/x86_64/entry.S -index 41d3ec2..0a0763a 100644 ---- a/xen/arch/x86/x86_64/entry.S -+++ b/xen/arch/x86/x86_64/entry.S -@@ -196,7 +196,7 @@ restore_all_guest: - mov %r15d, %eax - - /* WARNING! `ret`, `call *`, `jmp *` not safe beyond this point. */ -- SPEC_CTRL_EXIT_TO_GUEST /* Req: a=spec_ctrl %rsp=regs/cpuinfo, Clob: cd */ -+ SPEC_CTRL_EXIT_TO_PV /* Req: a=spec_ctrl %rsp=regs/cpuinfo, Clob: cd */ - - RESTORE_ALL - testw $TRAP_syscall,4(%rsp) -diff --git a/xen/include/asm-x86/cpufeatures.h b/xen/include/asm-x86/cpufeatures.h -index ca58b0e..f9aa5d7 100644 ---- a/xen/include/asm-x86/cpufeatures.h -+++ b/xen/include/asm-x86/cpufeatures.h -@@ -27,6 +27,6 @@ XEN_CPUFEATURE(IND_THUNK_LFENCE,(FSCAPINTS+0)*32+13) /* Use IND_THUNK_LFENCE */ - XEN_CPUFEATURE(IND_THUNK_JMP, (FSCAPINTS+0)*32+14) /* Use IND_THUNK_JMP */ - XEN_CPUFEATURE(XEN_IBPB, (FSCAPINTS+0)*32+15) /* IBRSB || IBPB */ - XEN_CPUFEATURE(SC_MSR, (FSCAPINTS+0)*32+16) /* MSR_SPEC_CTRL used by Xen */ --XEN_CPUFEATURE(RSB_NATIVE, (FSCAPINTS+0)*32+18) /* RSB overwrite needed for native */ --XEN_CPUFEATURE(RSB_VMEXIT, (FSCAPINTS+0)*32+19) /* RSB overwrite needed for vmexit */ -+XEN_CPUFEATURE(SC_RSB_PV, (FSCAPINTS+0)*32+18) /* RSB overwrite needed for PV */ -+XEN_CPUFEATURE(SC_RSB_HVM, (FSCAPINTS+0)*32+19) /* RSB overwrite needed for HVM */ - XEN_CPUFEATURE(NO_XPTI, (FSCAPINTS+0)*32+20) /* XPTI mitigation not in use */ -diff --git a/xen/include/asm-x86/spec_ctrl_asm.h b/xen/include/asm-x86/spec_ctrl_asm.h -index 17dd2cc..3d156ed 100644 ---- a/xen/include/asm-x86/spec_ctrl_asm.h -+++ b/xen/include/asm-x86/spec_ctrl_asm.h -@@ -72,11 +72,14 @@ - * - * The following ASM fragments implement this algorithm. See their local - * comments for further details. -- * - SPEC_CTRL_ENTRY_FROM_VMEXIT -+ * - SPEC_CTRL_ENTRY_FROM_HVM - * - SPEC_CTRL_ENTRY_FROM_PV - * - SPEC_CTRL_ENTRY_FROM_INTR -+ * - SPEC_CTRL_ENTRY_FROM_INTR_IST -+ * - SPEC_CTRL_EXIT_TO_XEN_IST - * - SPEC_CTRL_EXIT_TO_XEN -- * - SPEC_CTRL_EXIT_TO_GUEST -+ * - SPEC_CTRL_EXIT_TO_PV -+ * - SPEC_CTRL_EXIT_TO_HVM - */ - - .macro DO_OVERWRITE_RSB tmp=rax -@@ -117,7 +120,7 @@ - mov %\tmp, %rsp /* Restore old %rsp */ - .endm - --.macro DO_SPEC_CTRL_ENTRY_FROM_VMEXIT -+.macro DO_SPEC_CTRL_ENTRY_FROM_HVM - /* - * Requires %rbx=current, %rsp=regs/cpuinfo - * Clobbers %rax, %rcx, %rdx -@@ -217,23 +220,23 @@ - .endm - - /* Use after a VMEXIT from an HVM guest. */ --#define SPEC_CTRL_ENTRY_FROM_VMEXIT \ -+#define SPEC_CTRL_ENTRY_FROM_HVM \ - ALTERNATIVE __stringify(ASM_NOP40), \ -- DO_OVERWRITE_RSB, X86_FEATURE_RSB_VMEXIT; \ -+ DO_OVERWRITE_RSB, X86_FEATURE_SC_RSB_HVM; \ - ALTERNATIVE __stringify(ASM_NOP36), \ -- DO_SPEC_CTRL_ENTRY_FROM_VMEXIT, X86_FEATURE_SC_MSR -+ DO_SPEC_CTRL_ENTRY_FROM_HVM, X86_FEATURE_SC_MSR - - /* Use after an entry from PV context (syscall/sysenter/int80/int82/etc). */ - #define SPEC_CTRL_ENTRY_FROM_PV \ - ALTERNATIVE __stringify(ASM_NOP40), \ -- DO_OVERWRITE_RSB, X86_FEATURE_RSB_NATIVE; \ -+ DO_OVERWRITE_RSB, X86_FEATURE_SC_RSB_PV; \ - ALTERNATIVE __stringify(ASM_NOP25), \ - __stringify(DO_SPEC_CTRL_ENTRY maybexen=0), X86_FEATURE_SC_MSR - - /* Use in interrupt/exception context. May interrupt Xen or PV context. */ - #define SPEC_CTRL_ENTRY_FROM_INTR \ - ALTERNATIVE __stringify(ASM_NOP40), \ -- DO_OVERWRITE_RSB, X86_FEATURE_RSB_NATIVE; \ -+ DO_OVERWRITE_RSB, X86_FEATURE_SC_RSB_PV; \ - ALTERNATIVE __stringify(ASM_NOP33), \ - __stringify(DO_SPEC_CTRL_ENTRY maybexen=1), X86_FEATURE_SC_MSR - -@@ -242,12 +245,22 @@ - ALTERNATIVE __stringify(ASM_NOP17), \ - DO_SPEC_CTRL_EXIT_TO_XEN, X86_FEATURE_SC_MSR - --/* Use when exiting to guest context. */ --#define SPEC_CTRL_EXIT_TO_GUEST \ -+/* Use when exiting to PV guest context. */ -+#define SPEC_CTRL_EXIT_TO_PV \ - ALTERNATIVE __stringify(ASM_NOP24), \ - DO_SPEC_CTRL_EXIT_TO_GUEST, X86_FEATURE_SC_MSR - --/* TODO: Drop these when the alternatives infrastructure is NMI/#MC safe. */ -+/* Use when exiting to HVM guest context. */ -+#define SPEC_CTRL_EXIT_TO_HVM \ -+ ALTERNATIVE __stringify(ASM_NOP24), \ -+ DO_SPEC_CTRL_EXIT_TO_GUEST, X86_FEATURE_SC_MSR -+ -+/* -+ * Use in IST interrupt/exception context. May interrupt Xen or PV context. -+ * Fine grain control of SCF_ist_wrmsr is needed for safety in the S3 resume -+ * path to avoid using MSR_SPEC_CTRL before the microcode introducing it has -+ * been reloaded. -+ */ - .macro SPEC_CTRL_ENTRY_FROM_INTR_IST - /* - * Requires %rsp=regs, %r14=stack_end -@@ -294,6 +307,7 @@ UNLIKELY_DISPATCH_LABEL(\@_serialise): - UNLIKELY_END(\@_serialise) - .endm - -+/* Use when exiting to Xen in IST context. */ - .macro SPEC_CTRL_EXIT_TO_XEN_IST - /* - * Requires %rbx=stack_end --- -2.1.4 - diff --git a/system/xen/xsa/xsa263-4.10-0006-x86-spec_ctrl-Elide-MSR_SPEC_CTRL-handling-in-idle-c.patch b/system/xen/xsa/xsa263-4.10-0006-x86-spec_ctrl-Elide-MSR_SPEC_CTRL-handling-in-idle-c.patch deleted file mode 100644 index cbc7fb48d0b96..0000000000000 --- a/system/xen/xsa/xsa263-4.10-0006-x86-spec_ctrl-Elide-MSR_SPEC_CTRL-handling-in-idle-c.patch +++ /dev/null @@ -1,71 +0,0 @@ -From 811fcf5137abdcd5b9ea7e5212098adb5bedae0f Mon Sep 17 00:00:00 2001 -From: Andrew Cooper <andrew.cooper3@citrix.com> -Date: Mon, 7 May 2018 14:06:16 +0100 -Subject: [PATCH] x86/spec_ctrl: Elide MSR_SPEC_CTRL handling in idle context - when possible - -If Xen is virtualising MSR_SPEC_CTRL handling for guests, but using 0 as its -own MSR_SPEC_CTRL value, spec_ctrl_{enter,exit}_idle() need not write to the -MSR. - -Requested-by: Jan Beulich <JBeulich@suse.com> -Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com> -Reviewed-by: Wei Liu <wei.liu2@citrix.com> -Reviewed-by: Jan Beulich <jbeulich@suse.com> -Release-acked-by: Juergen Gross <jgross@suse.com> -(cherry picked from commit 94df6e8588e35cc2028ccb3fd2921c6e6360605e) ---- - xen/arch/x86/spec_ctrl.c | 4 ++++ - xen/include/asm-x86/cpufeatures.h | 1 + - xen/include/asm-x86/spec_ctrl.h | 4 ++-- - 3 files changed, 7 insertions(+), 2 deletions(-) - -diff --git a/xen/arch/x86/spec_ctrl.c b/xen/arch/x86/spec_ctrl.c -index 015a9e2..55ef79f 100644 ---- a/xen/arch/x86/spec_ctrl.c -+++ b/xen/arch/x86/spec_ctrl.c -@@ -327,6 +327,10 @@ void __init init_speculation_mitigations(void) - /* (Re)init BSP state now that default_spec_ctrl_flags has been calculated. */ - init_shadow_spec_ctrl_state(); - -+ /* If Xen is using any MSR_SPEC_CTRL settings, adjust the idle path. */ -+ if ( default_xen_spec_ctrl ) -+ setup_force_cpu_cap(X86_FEATURE_SC_MSR_IDLE); -+ - print_details(thunk, caps); - } - -diff --git a/xen/include/asm-x86/cpufeatures.h b/xen/include/asm-x86/cpufeatures.h -index f9aa5d7..32b7f04 100644 ---- a/xen/include/asm-x86/cpufeatures.h -+++ b/xen/include/asm-x86/cpufeatures.h -@@ -30,3 +30,4 @@ XEN_CPUFEATURE(SC_MSR, (FSCAPINTS+0)*32+16) /* MSR_SPEC_CTRL used by Xe - XEN_CPUFEATURE(SC_RSB_PV, (FSCAPINTS+0)*32+18) /* RSB overwrite needed for PV */ - XEN_CPUFEATURE(SC_RSB_HVM, (FSCAPINTS+0)*32+19) /* RSB overwrite needed for HVM */ - XEN_CPUFEATURE(NO_XPTI, (FSCAPINTS+0)*32+20) /* XPTI mitigation not in use */ -+XEN_CPUFEATURE(SC_MSR_IDLE, (FSCAPINTS+0)*32+21) /* SC_MSR && default_xen_spec_ctrl */ -diff --git a/xen/include/asm-x86/spec_ctrl.h b/xen/include/asm-x86/spec_ctrl.h -index 7d7c42e..77f92ba 100644 ---- a/xen/include/asm-x86/spec_ctrl.h -+++ b/xen/include/asm-x86/spec_ctrl.h -@@ -52,7 +52,7 @@ static always_inline void spec_ctrl_enter_idle(struct cpu_info *info) - barrier(); - info->spec_ctrl_flags |= SCF_use_shadow; - barrier(); -- asm volatile ( ALTERNATIVE(ASM_NOP3, "wrmsr", X86_FEATURE_SC_MSR) -+ asm volatile ( ALTERNATIVE(ASM_NOP3, "wrmsr", X86_FEATURE_SC_MSR_IDLE) - :: "a" (val), "c" (MSR_SPEC_CTRL), "d" (0) : "memory" ); - } - -@@ -67,7 +67,7 @@ static always_inline void spec_ctrl_exit_idle(struct cpu_info *info) - */ - info->spec_ctrl_flags &= ~SCF_use_shadow; - barrier(); -- asm volatile ( ALTERNATIVE(ASM_NOP3, "wrmsr", X86_FEATURE_SC_MSR) -+ asm volatile ( ALTERNATIVE(ASM_NOP3, "wrmsr", X86_FEATURE_SC_MSR_IDLE) - :: "a" (val), "c" (MSR_SPEC_CTRL), "d" (0) : "memory" ); - } - --- -2.1.4 - diff --git a/system/xen/xsa/xsa263-4.10-0007-x86-spec_ctrl-Split-X86_FEATURE_SC_MSR-into-PV-and-H.patch b/system/xen/xsa/xsa263-4.10-0007-x86-spec_ctrl-Split-X86_FEATURE_SC_MSR-into-PV-and-H.patch deleted file mode 100644 index a4e59aae9f037..0000000000000 --- a/system/xen/xsa/xsa263-4.10-0007-x86-spec_ctrl-Split-X86_FEATURE_SC_MSR-into-PV-and-H.patch +++ /dev/null @@ -1,111 +0,0 @@ -From 2acc4cba7eb2559bafdd4d8238466ad81322a35a Mon Sep 17 00:00:00 2001 -From: Andrew Cooper <andrew.cooper3@citrix.com> -Date: Tue, 17 Apr 2018 14:15:04 +0100 -Subject: [PATCH] x86/spec_ctrl: Split X86_FEATURE_SC_MSR into PV and HVM - variants - -In order to separately control whether MSR_SPEC_CTRL is virtualised for PV and -HVM guests, split the feature used to control runtime alternatives into two. -Xen will use MSR_SPEC_CTRL itself if either of these features are active. - -Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com> -Reviewed-by: Wei Liu <wei.liu2@citrix.com> -Reviewed-by: Jan Beulich <jbeulich@suse.com> -Release-acked-by: Juergen Gross <jgross@suse.com> -(cherry picked from commit fa9eb09d446a1279f5e861e6b84fa8675dabf148) ---- - xen/arch/x86/spec_ctrl.c | 6 ++++-- - xen/include/asm-x86/cpufeatures.h | 5 +++-- - xen/include/asm-x86/spec_ctrl_asm.h | 12 ++++++------ - 3 files changed, 13 insertions(+), 10 deletions(-) - -diff --git a/xen/arch/x86/spec_ctrl.c b/xen/arch/x86/spec_ctrl.c -index 55ef79f..a940308 100644 ---- a/xen/arch/x86/spec_ctrl.c -+++ b/xen/arch/x86/spec_ctrl.c -@@ -112,7 +112,8 @@ static void __init print_details(enum ind_thunk thunk, uint64_t caps) - thunk == THUNK_RETPOLINE ? "RETPOLINE" : - thunk == THUNK_LFENCE ? "LFENCE" : - thunk == THUNK_JMP ? "JMP" : "?", -- boot_cpu_has(X86_FEATURE_SC_MSR) ? -+ (boot_cpu_has(X86_FEATURE_SC_MSR_PV) || -+ boot_cpu_has(X86_FEATURE_SC_MSR_HVM)) ? - default_xen_spec_ctrl & SPEC_CTRL_IBRS ? " IBRS+" : - " IBRS-" : "", - opt_ibpb ? " IBPB" : "", -@@ -286,7 +287,8 @@ void __init init_speculation_mitigations(void) - * need the IBRS entry/exit logic to virtualise IBRS support for - * guests. - */ -- setup_force_cpu_cap(X86_FEATURE_SC_MSR); -+ setup_force_cpu_cap(X86_FEATURE_SC_MSR_PV); -+ setup_force_cpu_cap(X86_FEATURE_SC_MSR_HVM); - - if ( ibrs ) - default_xen_spec_ctrl |= SPEC_CTRL_IBRS; -diff --git a/xen/include/asm-x86/cpufeatures.h b/xen/include/asm-x86/cpufeatures.h -index 32b7f04..b90aa2d 100644 ---- a/xen/include/asm-x86/cpufeatures.h -+++ b/xen/include/asm-x86/cpufeatures.h -@@ -26,8 +26,9 @@ XEN_CPUFEATURE(LFENCE_DISPATCH, (FSCAPINTS+0)*32+12) /* lfence set as Dispatch S - XEN_CPUFEATURE(IND_THUNK_LFENCE,(FSCAPINTS+0)*32+13) /* Use IND_THUNK_LFENCE */ - XEN_CPUFEATURE(IND_THUNK_JMP, (FSCAPINTS+0)*32+14) /* Use IND_THUNK_JMP */ - XEN_CPUFEATURE(XEN_IBPB, (FSCAPINTS+0)*32+15) /* IBRSB || IBPB */ --XEN_CPUFEATURE(SC_MSR, (FSCAPINTS+0)*32+16) /* MSR_SPEC_CTRL used by Xen */ -+XEN_CPUFEATURE(SC_MSR_PV, (FSCAPINTS+0)*32+16) /* MSR_SPEC_CTRL used by Xen for PV */ -+XEN_CPUFEATURE(SC_MSR_HVM, (FSCAPINTS+0)*32+17) /* MSR_SPEC_CTRL used by Xen for HVM */ - XEN_CPUFEATURE(SC_RSB_PV, (FSCAPINTS+0)*32+18) /* RSB overwrite needed for PV */ - XEN_CPUFEATURE(SC_RSB_HVM, (FSCAPINTS+0)*32+19) /* RSB overwrite needed for HVM */ - XEN_CPUFEATURE(NO_XPTI, (FSCAPINTS+0)*32+20) /* XPTI mitigation not in use */ --XEN_CPUFEATURE(SC_MSR_IDLE, (FSCAPINTS+0)*32+21) /* SC_MSR && default_xen_spec_ctrl */ -+XEN_CPUFEATURE(SC_MSR_IDLE, (FSCAPINTS+0)*32+21) /* (SC_MSR_PV || SC_MSR_HVM) && default_xen_spec_ctrl */ -diff --git a/xen/include/asm-x86/spec_ctrl_asm.h b/xen/include/asm-x86/spec_ctrl_asm.h -index 3d156ed..c659f3f 100644 ---- a/xen/include/asm-x86/spec_ctrl_asm.h -+++ b/xen/include/asm-x86/spec_ctrl_asm.h -@@ -224,36 +224,36 @@ - ALTERNATIVE __stringify(ASM_NOP40), \ - DO_OVERWRITE_RSB, X86_FEATURE_SC_RSB_HVM; \ - ALTERNATIVE __stringify(ASM_NOP36), \ -- DO_SPEC_CTRL_ENTRY_FROM_HVM, X86_FEATURE_SC_MSR -+ DO_SPEC_CTRL_ENTRY_FROM_HVM, X86_FEATURE_SC_MSR_HVM - - /* Use after an entry from PV context (syscall/sysenter/int80/int82/etc). */ - #define SPEC_CTRL_ENTRY_FROM_PV \ - ALTERNATIVE __stringify(ASM_NOP40), \ - DO_OVERWRITE_RSB, X86_FEATURE_SC_RSB_PV; \ - ALTERNATIVE __stringify(ASM_NOP25), \ -- __stringify(DO_SPEC_CTRL_ENTRY maybexen=0), X86_FEATURE_SC_MSR -+ __stringify(DO_SPEC_CTRL_ENTRY maybexen=0), X86_FEATURE_SC_MSR_PV - - /* Use in interrupt/exception context. May interrupt Xen or PV context. */ - #define SPEC_CTRL_ENTRY_FROM_INTR \ - ALTERNATIVE __stringify(ASM_NOP40), \ - DO_OVERWRITE_RSB, X86_FEATURE_SC_RSB_PV; \ - ALTERNATIVE __stringify(ASM_NOP33), \ -- __stringify(DO_SPEC_CTRL_ENTRY maybexen=1), X86_FEATURE_SC_MSR -+ __stringify(DO_SPEC_CTRL_ENTRY maybexen=1), X86_FEATURE_SC_MSR_PV - - /* Use when exiting to Xen context. */ - #define SPEC_CTRL_EXIT_TO_XEN \ - ALTERNATIVE __stringify(ASM_NOP17), \ -- DO_SPEC_CTRL_EXIT_TO_XEN, X86_FEATURE_SC_MSR -+ DO_SPEC_CTRL_EXIT_TO_XEN, X86_FEATURE_SC_MSR_PV - - /* Use when exiting to PV guest context. */ - #define SPEC_CTRL_EXIT_TO_PV \ - ALTERNATIVE __stringify(ASM_NOP24), \ -- DO_SPEC_CTRL_EXIT_TO_GUEST, X86_FEATURE_SC_MSR -+ DO_SPEC_CTRL_EXIT_TO_GUEST, X86_FEATURE_SC_MSR_PV - - /* Use when exiting to HVM guest context. */ - #define SPEC_CTRL_EXIT_TO_HVM \ - ALTERNATIVE __stringify(ASM_NOP24), \ -- DO_SPEC_CTRL_EXIT_TO_GUEST, X86_FEATURE_SC_MSR -+ DO_SPEC_CTRL_EXIT_TO_GUEST, X86_FEATURE_SC_MSR_HVM - - /* - * Use in IST interrupt/exception context. May interrupt Xen or PV context. --- -2.1.4 - diff --git a/system/xen/xsa/xsa263-4.10-0008-x86-spec_ctrl-Explicitly-set-Xen-s-default-MSR_SPEC_.patch b/system/xen/xsa/xsa263-4.10-0008-x86-spec_ctrl-Explicitly-set-Xen-s-default-MSR_SPEC_.patch deleted file mode 100644 index 966ce7ee3f55c..0000000000000 --- a/system/xen/xsa/xsa263-4.10-0008-x86-spec_ctrl-Explicitly-set-Xen-s-default-MSR_SPEC_.patch +++ /dev/null @@ -1,134 +0,0 @@ -From 5b223f41d59887ea5d13e2406597ff472ba6f2fc Mon Sep 17 00:00:00 2001 -From: Andrew Cooper <andrew.cooper3@citrix.com> -Date: Wed, 9 May 2018 13:59:56 +0100 -Subject: [PATCH] x86/spec_ctrl: Explicitly set Xen's default MSR_SPEC_CTRL - value - -With the impending ability to disable MSR_SPEC_CTRL handling on a -per-guest-type basis, the first exit-from-guest may not have the side effect -of loading Xen's choice of value. Explicitly set Xen's default during the BSP -and AP boot paths. - -For the BSP however, delay setting a non-zero MSR_SPEC_CTRL default until -after dom0 has been constructed when safe to do so. Oracle report that this -speeds up boots of some hardware by 50s. - -"when safe to do so" is based on whether we are virtualised. A native boot -won't have any other code running in a position to mount an attack. - -Reported-by: Zhenzhong Duan <zhenzhong.duan@oracle.com> -Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com> -Reviewed-by: Wei Liu <wei.liu2@citrix.com> -Reviewed-by: Jan Beulich <jbeulich@suse.com> -Release-acked-by: Juergen Gross <jgross@suse.com> -(cherry picked from commit cb8c12020307b39a89273d7699e89000451987ab) ---- - xen/arch/x86/setup.c | 7 +++++++ - xen/arch/x86/smpboot.c | 8 ++++++++ - xen/arch/x86/spec_ctrl.c | 32 ++++++++++++++++++++++++++++++++ - xen/include/asm-x86/spec_ctrl.h | 2 ++ - 4 files changed, 49 insertions(+) - -diff --git a/xen/arch/x86/setup.c b/xen/arch/x86/setup.c -index 482fe11..1995c4c 100644 ---- a/xen/arch/x86/setup.c -+++ b/xen/arch/x86/setup.c -@@ -1746,6 +1746,13 @@ void __init noreturn __start_xen(unsigned long mbi_p) - - setup_io_bitmap(dom0); - -+ if ( bsp_delay_spec_ctrl ) -+ { -+ get_cpu_info()->spec_ctrl_flags &= ~SCF_use_shadow; -+ barrier(); -+ wrmsrl(MSR_SPEC_CTRL, default_xen_spec_ctrl); -+ } -+ - /* Jump to the 1:1 virtual mappings of cpu0_stack. */ - asm volatile ("mov %[stk], %%rsp; jmp %c[fn]" :: - [stk] "g" (__va(__pa(get_stack_bottom()))), -diff --git a/xen/arch/x86/smpboot.c b/xen/arch/x86/smpboot.c -index f81fc2c..ee8b183 100644 ---- a/xen/arch/x86/smpboot.c -+++ b/xen/arch/x86/smpboot.c -@@ -351,6 +351,14 @@ void start_secondary(void *unused) - else - microcode_resume_cpu(cpu); - -+ /* -+ * If MSR_SPEC_CTRL is available, apply Xen's default setting and discard -+ * any firmware settings. Note: MSR_SPEC_CTRL may only become available -+ * after loading microcode. -+ */ -+ if ( boot_cpu_has(X86_FEATURE_IBRSB) ) -+ wrmsrl(MSR_SPEC_CTRL, default_xen_spec_ctrl); -+ - if ( xen_guest ) - hypervisor_ap_setup(); - -diff --git a/xen/arch/x86/spec_ctrl.c b/xen/arch/x86/spec_ctrl.c -index a940308..3adec1a 100644 ---- a/xen/arch/x86/spec_ctrl.c -+++ b/xen/arch/x86/spec_ctrl.c -@@ -38,6 +38,8 @@ static int8_t __initdata opt_ibrs = -1; - static bool __initdata opt_rsb_pv = true; - static bool __initdata opt_rsb_hvm = true; - bool __read_mostly opt_ibpb = true; -+ -+bool __initdata bsp_delay_spec_ctrl; - uint8_t __read_mostly default_xen_spec_ctrl; - uint8_t __read_mostly default_spec_ctrl_flags; - -@@ -334,6 +336,36 @@ void __init init_speculation_mitigations(void) - setup_force_cpu_cap(X86_FEATURE_SC_MSR_IDLE); - - print_details(thunk, caps); -+ -+ /* -+ * If MSR_SPEC_CTRL is available, apply Xen's default setting and discard -+ * any firmware settings. For performance reasons, when safe to do so, we -+ * delay applying non-zero settings until after dom0 has been constructed. -+ * -+ * "when safe to do so" is based on whether we are virtualised. A native -+ * boot won't have any other code running in a position to mount an -+ * attack. -+ */ -+ if ( boot_cpu_has(X86_FEATURE_IBRSB) ) -+ { -+ bsp_delay_spec_ctrl = !cpu_has_hypervisor && default_xen_spec_ctrl; -+ -+ /* -+ * If delaying MSR_SPEC_CTRL setup, use the same mechanism as -+ * spec_ctrl_enter_idle(), by using a shadow value of zero. -+ */ -+ if ( bsp_delay_spec_ctrl ) -+ { -+ struct cpu_info *info = get_cpu_info(); -+ -+ info->shadow_spec_ctrl = 0; -+ barrier(); -+ info->spec_ctrl_flags |= SCF_use_shadow; -+ barrier(); -+ } -+ -+ wrmsrl(MSR_SPEC_CTRL, bsp_delay_spec_ctrl ? 0 : default_xen_spec_ctrl); -+ } - } - - static void __init __maybe_unused build_assertions(void) -diff --git a/xen/include/asm-x86/spec_ctrl.h b/xen/include/asm-x86/spec_ctrl.h -index 77f92ba..c6a38f4 100644 ---- a/xen/include/asm-x86/spec_ctrl.h -+++ b/xen/include/asm-x86/spec_ctrl.h -@@ -27,6 +27,8 @@ - void init_speculation_mitigations(void); - - extern bool opt_ibpb; -+ -+extern bool bsp_delay_spec_ctrl; - extern uint8_t default_xen_spec_ctrl; - extern uint8_t default_spec_ctrl_flags; - --- -2.1.4 - diff --git a/system/xen/xsa/xsa263-4.10-0009-x86-cpuid-Improvements-to-guest-policies-for-specula.patch b/system/xen/xsa/xsa263-4.10-0009-x86-cpuid-Improvements-to-guest-policies-for-specula.patch deleted file mode 100644 index 90b1ffc87f576..0000000000000 --- a/system/xen/xsa/xsa263-4.10-0009-x86-cpuid-Improvements-to-guest-policies-for-specula.patch +++ /dev/null @@ -1,132 +0,0 @@ -From bce7a2145abc3c7e5bfd7e2168714d194124a3ab Mon Sep 17 00:00:00 2001 -From: Andrew Cooper <andrew.cooper3@citrix.com> -Date: Tue, 1 May 2018 11:59:03 +0100 -Subject: [PATCH] x86/cpuid: Improvements to guest policies for speculative - sidechannel features - -If Xen isn't virtualising MSR_SPEC_CTRL for guests, IBRSB shouldn't be -advertised. It is not currently possible to express this via the existing -command line options, but such an ability will be introduced. - -Another useful option in some usecases is to offer IBPB without IBRS. When a -guest kernel is known to be compatible (uses retpoline and knows about the AMD -IBPB feature bit), an administrator with pre-Skylake hardware may wish to hide -IBRS. This allows the VM to have full protection, without Xen or the VM -needing to touch MSR_SPEC_CTRL, which can reduce the overhead of Spectre -mitigations. - -Break the logic common to both PV and HVM CPUID calculations into a common -helper, to avoid duplication. - -Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com> -Reviewed-by: Wei Liu <wei.liu2@citrix.com> -Reviewed-by: Jan Beulich <jbeulich@suse.com> -Release-acked-by: Juergen Gross <jgross@suse.com> -(cherry picked from commit cb06b308ec71b23f37a44f5e2351fe2cae0306e9) ---- - xen/arch/x86/cpuid.c | 60 ++++++++++++++++++++++++++++++++-------------------- - 1 file changed, 37 insertions(+), 23 deletions(-) - -diff --git a/xen/arch/x86/cpuid.c b/xen/arch/x86/cpuid.c -index b3c9ac6..b45b145 100644 ---- a/xen/arch/x86/cpuid.c -+++ b/xen/arch/x86/cpuid.c -@@ -368,6 +368,28 @@ static void __init calculate_host_policy(void) - } - } - -+static void __init guest_common_feature_adjustments(uint32_t *fs) -+{ -+ /* Unconditionally claim to be able to set the hypervisor bit. */ -+ __set_bit(X86_FEATURE_HYPERVISOR, fs); -+ -+ /* -+ * If IBRS is offered to the guest, unconditionally offer STIBP. It is a -+ * nop on non-HT hardware, and has this behaviour to make heterogeneous -+ * setups easier to manage. -+ */ -+ if ( test_bit(X86_FEATURE_IBRSB, fs) ) -+ __set_bit(X86_FEATURE_STIBP, fs); -+ -+ /* -+ * On hardware which supports IBRS/IBPB, we can offer IBPB independently -+ * of IBRS by using the AMD feature bit. An administrator may wish for -+ * performance reasons to offer IBPB without IBRS. -+ */ -+ if ( host_cpuid_policy.feat.ibrsb ) -+ __set_bit(X86_FEATURE_IBPB, fs); -+} -+ - static void __init calculate_pv_max_policy(void) - { - struct cpuid_policy *p = &pv_max_cpuid_policy; -@@ -380,18 +402,14 @@ static void __init calculate_pv_max_policy(void) - for ( i = 0; i < ARRAY_SIZE(pv_featureset); ++i ) - pv_featureset[i] &= pv_featuremask[i]; - -- /* Unconditionally claim to be able to set the hypervisor bit. */ -- __set_bit(X86_FEATURE_HYPERVISOR, pv_featureset); -- -- /* On hardware with IBRS/IBPB support, there are further adjustments. */ -- if ( test_bit(X86_FEATURE_IBRSB, pv_featureset) ) -- { -- /* Offer STIBP unconditionally. It is a nop on non-HT hardware. */ -- __set_bit(X86_FEATURE_STIBP, pv_featureset); -+ /* -+ * If Xen isn't virtualising MSR_SPEC_CTRL for PV guests because of -+ * administrator choice, hide the feature. -+ */ -+ if ( !boot_cpu_has(X86_FEATURE_SC_MSR_PV) ) -+ __clear_bit(X86_FEATURE_IBRSB, pv_featureset); - -- /* AMD's IBPB is a subset of IBRS/IBPB. */ -- __set_bit(X86_FEATURE_IBPB, pv_featureset); -- } -+ guest_common_feature_adjustments(pv_featureset); - - sanitise_featureset(pv_featureset); - cpuid_featureset_to_policy(pv_featureset, p); -@@ -419,9 +437,6 @@ static void __init calculate_hvm_max_policy(void) - for ( i = 0; i < ARRAY_SIZE(hvm_featureset); ++i ) - hvm_featureset[i] &= hvm_featuremask[i]; - -- /* Unconditionally claim to be able to set the hypervisor bit. */ -- __set_bit(X86_FEATURE_HYPERVISOR, hvm_featureset); -- - /* - * Xen can provide an APIC emulation to HVM guests even if the host's APIC - * isn't enabled. -@@ -438,6 +453,13 @@ static void __init calculate_hvm_max_policy(void) - __set_bit(X86_FEATURE_SEP, hvm_featureset); - - /* -+ * If Xen isn't virtualising MSR_SPEC_CTRL for HVM guests because of -+ * administrator choice, hide the feature. -+ */ -+ if ( !boot_cpu_has(X86_FEATURE_SC_MSR_HVM) ) -+ __clear_bit(X86_FEATURE_IBRSB, hvm_featureset); -+ -+ /* - * With VT-x, some features are only supported by Xen if dedicated - * hardware support is also available. - */ -@@ -450,15 +472,7 @@ static void __init calculate_hvm_max_policy(void) - __clear_bit(X86_FEATURE_XSAVES, hvm_featureset); - } - -- /* On hardware with IBRS/IBPB support, there are further adjustments. */ -- if ( test_bit(X86_FEATURE_IBRSB, hvm_featureset) ) -- { -- /* Offer STIBP unconditionally. It is a nop on non-HT hardware. */ -- __set_bit(X86_FEATURE_STIBP, hvm_featureset); -- -- /* AMD's IBPB is a subset of IBRS/IBPB. */ -- __set_bit(X86_FEATURE_IBPB, hvm_featureset); -- } -+ guest_common_feature_adjustments(hvm_featureset); - - sanitise_featureset(hvm_featureset); - cpuid_featureset_to_policy(hvm_featureset, p); --- -2.1.4 - diff --git a/system/xen/xsa/xsa263-4.10-0010-x86-spec_ctrl-Introduce-a-new-spec-ctrl-command-line.patch b/system/xen/xsa/xsa263-4.10-0010-x86-spec_ctrl-Introduce-a-new-spec-ctrl-command-line.patch deleted file mode 100644 index 9c8c3560bdf93..0000000000000 --- a/system/xen/xsa/xsa263-4.10-0010-x86-spec_ctrl-Introduce-a-new-spec-ctrl-command-line.patch +++ /dev/null @@ -1,344 +0,0 @@ -From 952ff9f5590e37952d7dd3d89e16a47a238ab079 Mon Sep 17 00:00:00 2001 -From: Andrew Cooper <andrew.cooper3@citrix.com> -Date: Thu, 26 Apr 2018 10:52:55 +0100 -Subject: [PATCH] x86/spec_ctrl: Introduce a new `spec-ctrl=` command line - argument to replace `bti=` - -In hindsight, the options for `bti=` aren't as flexible or useful as expected -(including several options which don't appear to behave as intended). -Changing the behaviour of an existing option is problematic for compatibility, -so introduce a new `spec-ctrl=` in the hopes that we can do better. - -One common way of deploying Xen is with a single PV dom0 and all domUs being -HVM domains. In such a setup, an administrator who has weighed up the risks -may wish to forgo protection against malicious PV domains, to reduce the -overall performance hit. To cater for this usecase, `spec-ctrl=no-pv` will -disable all speculative protection for PV domains, while leaving all -speculative protection for HVM domains intact. - -For coding clarity as much as anything else, the suboptions are grouped by -logical area; those which affect the alternatives blocks, and those which -affect Xen's in-hypervisor settings. See the xen-command-line.markdown for -full details of the new options. - -While changing the command line options, take the time to change how the data -is reported to the user. The three DEBUG printks are upgraded to unilateral, -as they are all relevant pieces of information, and the old "mitigations:" -line is split in the two logical areas described above. - -Sample output from booting with `spec-ctrl=no-pv` looks like: - - (XEN) Speculative mitigation facilities: - (XEN) Hardware features: IBRS/IBPB STIBP IBPB - (XEN) Compiled-in support: INDIRECT_THUNK - (XEN) Xen settings: BTI-Thunk RETPOLINE, SPEC_CTRL: IBRS-, Other: IBPB - (XEN) Support for VMs: PV: None, HVM: MSR_SPEC_CTRL RSB - (XEN) XPTI (64-bit PV only): Dom0 enabled, DomU enabled - -Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com> -Reviewed-by: Wei Liu <wei.liu2@citrix.com> -Reviewed-by: Jan Beulich <jbeulich@suse.com> -Release-acked-by: Juergen Gross <jgross@suse.com> -(cherry picked from commit 3352afc26c497d26ecb70527db3cb29daf7b1422) ---- - docs/misc/xen-command-line.markdown | 49 +++++++++++ - xen/arch/x86/spec_ctrl.c | 160 ++++++++++++++++++++++++++++++------ - 2 files changed, 186 insertions(+), 23 deletions(-) - -diff --git a/docs/misc/xen-command-line.markdown b/docs/misc/xen-command-line.markdown -index 6c673ee..43a6ddb 100644 ---- a/docs/misc/xen-command-line.markdown -+++ b/docs/misc/xen-command-line.markdown -@@ -248,6 +248,9 @@ the NMI watchdog is also enabled. - ### bti (x86) - > `= List of [ thunk=retpoline|lfence|jmp, ibrs=<bool>, ibpb=<bool>, rsb_{vmexit,native}=<bool> ]` - -+**WARNING: This command line option is deprecated, and superseded by -+_spec-ctrl=_ - using both options in combination is undefined.** -+ - Branch Target Injection controls. By default, Xen will pick the most - appropriate BTI mitigations based on compiled in support, loaded microcode, - and hardware details. -@@ -1698,6 +1701,52 @@ enforces the maximum theoretically necessary timeout of 670ms. Any number - is being interpreted as a custom timeout in milliseconds. Zero or boolean - false disable the quirk workaround, which is also the default. - -+### spec-ctrl (x86) -+> `= List of [ <bool>, xen=<bool>, {pv,hvm,msr-sc,rsb}=<bool>, -+> bti-thunk=retpoline|lfence|jmp, {ibrs,ibpb}=<bool> ]` -+ -+Controls for speculative execution sidechannel mitigations. By default, Xen -+will pick the most appropriate mitigations based on compiled in support, -+loaded microcode, and hardware details, and will virtualise appropriate -+mitigations for guests to use. -+ -+**WARNING: Any use of this option may interfere with heuristics. Use with -+extreme care.** -+ -+An overall boolean value, `spec-ctrl=no`, can be specified to turn off all -+mitigations, including pieces of infrastructure used to virtualise certain -+mitigation features for guests. Alternatively, a slightly more restricted -+`spec-ctrl=no-xen` can be used to turn off all of Xen's mitigations, while -+leaving the virtualisation support in place for guests to use. Use of a -+positive boolean value for either of these options is invalid. -+ -+The booleans `pv=`, `hvm=`, `msr-sc=` and `rsb=` offer fine grained control -+over the alternative blocks used by Xen. These impact Xen's ability to -+protect itself, and Xen's ability to virtualise support for guests to use. -+ -+* `pv=` and `hvm=` offer control over all suboptions for PV and HVM guests -+ respectively. -+* `msr-sc=` offers control over Xen's support for manipulating MSR\_SPEC\_CTRL -+ on entry and exit. These blocks are necessary to virtualise support for -+ guests and if disabled, guests will be unable to use IBRS/STIBP/etc. -+* `rsb=` offers control over whether to overwrite the Return Stack Buffer / -+ Return Address Stack on entry to Xen. -+ -+If Xen was compiled with INDIRECT\_THUNK support, `bti-thunk=` can be used to -+select which of the thunks gets patched into the `__x86_indirect_thunk_%reg` -+locations. The default thunk is `retpoline` (generally preferred for Intel -+hardware), with the alternatives being `jmp` (a `jmp *%reg` gadget, minimal -+overhead), and `lfence` (an `lfence; jmp *%reg` gadget, preferred for AMD). -+ -+On hardware supporting IBRS (Indirect Branch Restricted Speculation), the -+`ibrs=` option can be used to force or prevent Xen using the feature itself. -+If Xen is not using IBRS itself, functionality is still set up so IBRS can be -+virtualised for guests. -+ -+On hardware supporting IBPB (Indirect Branch Prediction Barrier), the `ibpb=` -+option can be used to force (the default) or prevent Xen from issuing branch -+prediction barriers on vcpu context switches. -+ - ### sync\_console - > `= <boolean>` - -diff --git a/xen/arch/x86/spec_ctrl.c b/xen/arch/x86/spec_ctrl.c -index 3adec1a..4f9282f 100644 ---- a/xen/arch/x86/spec_ctrl.c -+++ b/xen/arch/x86/spec_ctrl.c -@@ -26,6 +26,13 @@ - #include <asm/spec_ctrl.h> - #include <asm/spec_ctrl_asm.h> - -+/* Cmdline controls for Xen's alternative blocks. */ -+static bool __initdata opt_msr_sc_pv = true; -+static bool __initdata opt_msr_sc_hvm = true; -+static bool __initdata opt_rsb_pv = true; -+static bool __initdata opt_rsb_hvm = true; -+ -+/* Cmdline controls for Xen's speculative settings. */ - static enum ind_thunk { - THUNK_DEFAULT, /* Decide which thunk to use at boot time. */ - THUNK_NONE, /* Missing compiler support for thunks. */ -@@ -35,8 +42,6 @@ static enum ind_thunk { - THUNK_JMP, - } opt_thunk __initdata = THUNK_DEFAULT; - static int8_t __initdata opt_ibrs = -1; --static bool __initdata opt_rsb_pv = true; --static bool __initdata opt_rsb_hvm = true; - bool __read_mostly opt_ibpb = true; - - bool __initdata bsp_delay_spec_ctrl; -@@ -84,8 +89,95 @@ static int __init parse_bti(const char *s) - } - custom_param("bti", parse_bti); - -+static int __init parse_spec_ctrl(const char *s) -+{ -+ const char *ss; -+ int val, rc = 0; -+ -+ do { -+ ss = strchr(s, ','); -+ if ( !ss ) -+ ss = strchr(s, '\0'); -+ -+ /* Global and Xen-wide disable. */ -+ val = parse_bool(s, ss); -+ if ( !val ) -+ { -+ opt_msr_sc_pv = false; -+ opt_msr_sc_hvm = false; -+ -+ disable_common: -+ opt_rsb_pv = false; -+ opt_rsb_hvm = false; -+ -+ opt_thunk = THUNK_JMP; -+ opt_ibrs = 0; -+ opt_ibpb = false; -+ } -+ else if ( val > 0 ) -+ rc = -EINVAL; -+ else if ( (val = parse_boolean("xen", s, ss)) >= 0 ) -+ { -+ if ( !val ) -+ goto disable_common; -+ -+ rc = -EINVAL; -+ } -+ -+ /* Xen's alternative blocks. */ -+ else if ( (val = parse_boolean("pv", s, ss)) >= 0 ) -+ { -+ opt_msr_sc_pv = val; -+ opt_rsb_pv = val; -+ } -+ else if ( (val = parse_boolean("hvm", s, ss)) >= 0 ) -+ { -+ opt_msr_sc_hvm = val; -+ opt_rsb_hvm = val; -+ } -+ else if ( (val = parse_boolean("msr-sc", s, ss)) >= 0 ) -+ { -+ opt_msr_sc_pv = val; -+ opt_msr_sc_hvm = val; -+ } -+ else if ( (val = parse_boolean("rsb", s, ss)) >= 0 ) -+ { -+ opt_rsb_pv = val; -+ opt_rsb_hvm = val; -+ } -+ -+ /* Xen's speculative sidechannel mitigation settings. */ -+ else if ( !strncmp(s, "bti-thunk=", 10) ) -+ { -+ s += 10; -+ -+ if ( !strncmp(s, "retpoline", ss - s) ) -+ opt_thunk = THUNK_RETPOLINE; -+ else if ( !strncmp(s, "lfence", ss - s) ) -+ opt_thunk = THUNK_LFENCE; -+ else if ( !strncmp(s, "jmp", ss - s) ) -+ opt_thunk = THUNK_JMP; -+ else -+ rc = -EINVAL; -+ } -+ else if ( (val = parse_boolean("ibrs", s, ss)) >= 0 ) -+ opt_ibrs = val; -+ else if ( (val = parse_boolean("ibpb", s, ss)) >= 0 ) -+ opt_ibpb = val; -+ else -+ rc = -EINVAL; -+ -+ s = ss + 1; -+ } while ( *ss ); -+ -+ return rc; -+} -+custom_param("spec-ctrl", parse_spec_ctrl); -+ - static void __init print_details(enum ind_thunk thunk, uint64_t caps) - { -+ bool use_spec_ctrl = (boot_cpu_has(X86_FEATURE_SC_MSR_PV) || -+ boot_cpu_has(X86_FEATURE_SC_MSR_HVM)); - unsigned int _7d0 = 0, e8b = 0, tmp; - - /* Collect diagnostics about available mitigations. */ -@@ -94,10 +186,10 @@ static void __init print_details(enum ind_thunk thunk, uint64_t caps) - if ( boot_cpu_data.extended_cpuid_level >= 0x80000008 ) - cpuid(0x80000008, &tmp, &e8b, &tmp, &tmp); - -- printk(XENLOG_DEBUG "Speculative mitigation facilities:\n"); -+ printk("Speculative mitigation facilities:\n"); - - /* Hardware features which pertain to speculative mitigations. */ -- printk(XENLOG_DEBUG " Hardware features:%s%s%s%s%s%s\n", -+ printk(" Hardware features:%s%s%s%s%s%s\n", - (_7d0 & cpufeat_mask(X86_FEATURE_IBRSB)) ? " IBRS/IBPB" : "", - (_7d0 & cpufeat_mask(X86_FEATURE_STIBP)) ? " STIBP" : "", - (e8b & cpufeat_mask(X86_FEATURE_IBPB)) ? " IBPB" : "", -@@ -107,20 +199,31 @@ static void __init print_details(enum ind_thunk thunk, uint64_t caps) - - /* Compiled-in support which pertains to BTI mitigations. */ - if ( IS_ENABLED(CONFIG_INDIRECT_THUNK) ) -- printk(XENLOG_DEBUG " Compiled-in support: INDIRECT_THUNK\n"); -+ printk(" Compiled-in support: INDIRECT_THUNK\n"); - -- printk("BTI mitigations: Thunk %s, Others:%s%s%s%s\n", -+ /* Settings for Xen's protection, irrespective of guests. */ -+ printk(" Xen settings: BTI-Thunk %s, SPEC_CTRL: %s, Other:%s\n", - thunk == THUNK_NONE ? "N/A" : - thunk == THUNK_RETPOLINE ? "RETPOLINE" : - thunk == THUNK_LFENCE ? "LFENCE" : - thunk == THUNK_JMP ? "JMP" : "?", -+ !use_spec_ctrl ? "No" : -+ (default_xen_spec_ctrl & SPEC_CTRL_IBRS) ? "IBRS+" : "IBRS-", -+ opt_ibpb ? " IBPB" : ""); -+ -+ /* -+ * Alternatives blocks for protecting against and/or virtualising -+ * mitigation support for guests. -+ */ -+ printk(" Support for VMs: PV:%s%s%s, HVM:%s%s%s\n", - (boot_cpu_has(X86_FEATURE_SC_MSR_PV) || -- boot_cpu_has(X86_FEATURE_SC_MSR_HVM)) ? -- default_xen_spec_ctrl & SPEC_CTRL_IBRS ? " IBRS+" : -- " IBRS-" : "", -- opt_ibpb ? " IBPB" : "", -- boot_cpu_has(X86_FEATURE_SC_RSB_PV) ? " RSB_NATIVE" : "", -- boot_cpu_has(X86_FEATURE_SC_RSB_HVM) ? " RSB_VMEXIT" : ""); -+ boot_cpu_has(X86_FEATURE_SC_RSB_PV)) ? "" : " None", -+ boot_cpu_has(X86_FEATURE_SC_MSR_PV) ? " MSR_SPEC_CTRL" : "", -+ boot_cpu_has(X86_FEATURE_SC_RSB_PV) ? " RSB" : "", -+ (boot_cpu_has(X86_FEATURE_SC_MSR_HVM) || -+ boot_cpu_has(X86_FEATURE_SC_RSB_HVM)) ? "" : " None", -+ boot_cpu_has(X86_FEATURE_SC_MSR_HVM) ? " MSR_SPEC_CTRL" : "", -+ boot_cpu_has(X86_FEATURE_SC_RSB_HVM) ? " RSB" : ""); - - printk("XPTI: %s\n", - boot_cpu_has(X86_FEATURE_NO_XPTI) ? "disabled" : "enabled"); -@@ -212,7 +315,7 @@ static bool __init retpoline_safe(uint64_t caps) - void __init init_speculation_mitigations(void) - { - enum ind_thunk thunk = THUNK_DEFAULT; -- bool ibrs = false; -+ bool use_spec_ctrl = false, ibrs = false; - uint64_t caps = 0; - - if ( boot_cpu_has(X86_FEATURE_ARCH_CAPS) ) -@@ -282,20 +385,31 @@ void __init init_speculation_mitigations(void) - else if ( thunk == THUNK_JMP ) - setup_force_cpu_cap(X86_FEATURE_IND_THUNK_JMP); - -+ /* -+ * If we are on hardware supporting MSR_SPEC_CTRL, see about setting up -+ * the alternatives blocks so we can virtualise support for guests. -+ */ - if ( boot_cpu_has(X86_FEATURE_IBRSB) ) - { -- /* -- * Even if we've chosen to not have IBRS set in Xen context, we still -- * need the IBRS entry/exit logic to virtualise IBRS support for -- * guests. -- */ -- setup_force_cpu_cap(X86_FEATURE_SC_MSR_PV); -- setup_force_cpu_cap(X86_FEATURE_SC_MSR_HVM); -+ if ( opt_msr_sc_pv ) -+ { -+ use_spec_ctrl = true; -+ setup_force_cpu_cap(X86_FEATURE_SC_MSR_PV); -+ } - -- if ( ibrs ) -- default_xen_spec_ctrl |= SPEC_CTRL_IBRS; -+ if ( opt_msr_sc_hvm ) -+ { -+ use_spec_ctrl = true; -+ setup_force_cpu_cap(X86_FEATURE_SC_MSR_HVM); -+ } -+ -+ if ( use_spec_ctrl ) -+ { -+ if ( ibrs ) -+ default_xen_spec_ctrl |= SPEC_CTRL_IBRS; - -- default_spec_ctrl_flags |= SCF_ist_wrmsr; -+ default_spec_ctrl_flags |= SCF_ist_wrmsr; -+ } - } - - /* --- -2.1.4 - diff --git a/system/xen/xsa/xsa263-4.10-0011-x86-AMD-Mitigations-for-GPZ-SP4-Speculative-Store-By.patch b/system/xen/xsa/xsa263-4.10-0011-x86-AMD-Mitigations-for-GPZ-SP4-Speculative-Store-By.patch deleted file mode 100644 index 8603f1d56ed96..0000000000000 --- a/system/xen/xsa/xsa263-4.10-0011-x86-AMD-Mitigations-for-GPZ-SP4-Speculative-Store-By.patch +++ /dev/null @@ -1,123 +0,0 @@ -From 918320daf34931cd5c1c0d9c439ce853f6575970 Mon Sep 17 00:00:00 2001 -From: Andrew Cooper <andrew.cooper3@citrix.com> -Date: Thu, 26 Apr 2018 10:56:28 +0100 -Subject: [PATCH] x86/AMD: Mitigations for GPZ SP4 - Speculative Store Bypass - -AMD processors will execute loads and stores with the same base register in -program order, which is typically how a compiler emits code. - -Therefore, by default no mitigating actions are taken, despite there being -corner cases which are vulnerable to the issue. - -For performance testing, or for users with particularly sensitive workloads, -the `spec-ctrl=ssbd` command line option is available to force Xen to disable -Memory Disambiguation on applicable hardware. - -Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com> -Reviewed-by: Jan Beulich <jbeulich@suse.com> ---- - docs/misc/xen-command-line.markdown | 7 ++++++- - xen/arch/x86/cpu/amd.c | 20 ++++++++++++++++++++ - xen/arch/x86/spec_ctrl.c | 3 +++ - xen/include/asm-x86/spec_ctrl.h | 1 + - 4 files changed, 30 insertions(+), 1 deletion(-) - -diff --git a/docs/misc/xen-command-line.markdown b/docs/misc/xen-command-line.markdown -index 43a6ddb..4e0e580 100644 ---- a/docs/misc/xen-command-line.markdown -+++ b/docs/misc/xen-command-line.markdown -@@ -1703,7 +1703,7 @@ false disable the quirk workaround, which is also the default. - - ### spec-ctrl (x86) - > `= List of [ <bool>, xen=<bool>, {pv,hvm,msr-sc,rsb}=<bool>, --> bti-thunk=retpoline|lfence|jmp, {ibrs,ibpb}=<bool> ]` -+> bti-thunk=retpoline|lfence|jmp, {ibrs,ibpb,ssbd}=<bool> ]` - - Controls for speculative execution sidechannel mitigations. By default, Xen - will pick the most appropriate mitigations based on compiled in support, -@@ -1747,6 +1747,11 @@ On hardware supporting IBPB (Indirect Branch Prediction Barrier), the `ibpb=` - option can be used to force (the default) or prevent Xen from issuing branch - prediction barriers on vcpu context switches. - -+On hardware supporting SSBD (Speculative Store Bypass Disable), the `ssbd=` -+option can be used to force or prevent Xen using the feature itself. On AMD -+hardware, this is a global option applied at boot, and not virtualised for -+guest use. -+ - ### sync\_console - > `= <boolean>` - -diff --git a/xen/arch/x86/cpu/amd.c b/xen/arch/x86/cpu/amd.c -index fc9677f..458a3fe 100644 ---- a/xen/arch/x86/cpu/amd.c -+++ b/xen/arch/x86/cpu/amd.c -@@ -9,6 +9,7 @@ - #include <asm/amd.h> - #include <asm/hvm/support.h> - #include <asm/setup.h> /* amd_init_cpu */ -+#include <asm/spec_ctrl.h> - #include <asm/acpi.h> - #include <asm/apic.h> - -@@ -594,6 +595,25 @@ static void init_amd(struct cpuinfo_x86 *c) - c->x86_capability); - } - -+ /* -+ * If the user has explicitly chosen to disable Memory Disambiguation -+ * to mitigiate Speculative Store Bypass, poke the appropriate MSR. -+ */ -+ if (opt_ssbd) { -+ int bit = -1; -+ -+ switch (c->x86) { -+ case 0x15: bit = 54; break; -+ case 0x16: bit = 33; break; -+ case 0x17: bit = 10; break; -+ } -+ -+ if (bit >= 0 && !rdmsr_safe(MSR_AMD64_LS_CFG, value)) { -+ value |= 1ull << bit; -+ wrmsr_safe(MSR_AMD64_LS_CFG, value); -+ } -+ } -+ - /* MFENCE stops RDTSC speculation */ - if (!cpu_has_lfence_dispatch) - __set_bit(X86_FEATURE_MFENCE_RDTSC, c->x86_capability); -diff --git a/xen/arch/x86/spec_ctrl.c b/xen/arch/x86/spec_ctrl.c -index 4f9282f..e326056 100644 ---- a/xen/arch/x86/spec_ctrl.c -+++ b/xen/arch/x86/spec_ctrl.c -@@ -43,6 +43,7 @@ static enum ind_thunk { - } opt_thunk __initdata = THUNK_DEFAULT; - static int8_t __initdata opt_ibrs = -1; - bool __read_mostly opt_ibpb = true; -+bool __read_mostly opt_ssbd = false; - - bool __initdata bsp_delay_spec_ctrl; - uint8_t __read_mostly default_xen_spec_ctrl; -@@ -164,6 +165,8 @@ static int __init parse_spec_ctrl(const char *s) - opt_ibrs = val; - else if ( (val = parse_boolean("ibpb", s, ss)) >= 0 ) - opt_ibpb = val; -+ else if ( (val = parse_boolean("ssbd", s, ss)) >= 0 ) -+ opt_ssbd = val; - else - rc = -EINVAL; - -diff --git a/xen/include/asm-x86/spec_ctrl.h b/xen/include/asm-x86/spec_ctrl.h -index c6a38f4..4678a40 100644 ---- a/xen/include/asm-x86/spec_ctrl.h -+++ b/xen/include/asm-x86/spec_ctrl.h -@@ -27,6 +27,7 @@ - void init_speculation_mitigations(void); - - extern bool opt_ibpb; -+extern bool opt_ssbd; - - extern bool bsp_delay_spec_ctrl; - extern uint8_t default_xen_spec_ctrl; --- -2.1.4 - diff --git a/system/xen/xsa/xsa263-4.10-0012-x86-Intel-Mitigations-for-GPZ-SP4-Speculative-Store-.patch b/system/xen/xsa/xsa263-4.10-0012-x86-Intel-Mitigations-for-GPZ-SP4-Speculative-Store-.patch deleted file mode 100644 index 7f2556d42ba81..0000000000000 --- a/system/xen/xsa/xsa263-4.10-0012-x86-Intel-Mitigations-for-GPZ-SP4-Speculative-Store-.patch +++ /dev/null @@ -1,224 +0,0 @@ -From db6adc8e55dd43a1b4bb20e06a69475c503cb934 Mon Sep 17 00:00:00 2001 -From: Andrew Cooper <andrew.cooper3@citrix.com> -Date: Wed, 28 Mar 2018 15:21:39 +0100 -Subject: [PATCH] x86/Intel: Mitigations for GPZ SP4 - Speculative Store Bypass - -To combat GPZ SP4 "Speculative Store Bypass", Intel have extended their -speculative sidechannel mitigations specification as follows: - - * A feature bit to indicate that Speculative Store Bypass Disable is - supported. - * A new bit in MSR_SPEC_CTRL which, when set, disables memory disambiguation - in the pipeline. - * A new bit in MSR_ARCH_CAPABILITIES, which will be set in future hardware, - indicating that the hardware is not susceptible to Speculative Store Bypass - sidechannels. - -For contemporary processors, this interface will be implemented via a -microcode update. - -Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com> -Reviewed-by: Jan Beulich <jbeulich@suse.com> ---- - docs/misc/xen-command-line.markdown | 12 +++++++----- - tools/libxl/libxl_cpuid.c | 1 + - tools/misc/xen-cpuid.c | 3 +-- - xen/arch/x86/cpuid.c | 5 +++++ - xen/arch/x86/spec_ctrl.c | 15 ++++++++++++--- - xen/include/asm-x86/msr-index.h | 2 ++ - xen/include/public/arch-x86/cpufeatureset.h | 1 + - xen/tools/gen-cpuid.py | 17 +++++++++++++---- - 8 files changed, 42 insertions(+), 14 deletions(-) - -diff --git a/docs/misc/xen-command-line.markdown b/docs/misc/xen-command-line.markdown -index 4e0e580..107889d 100644 ---- a/docs/misc/xen-command-line.markdown -+++ b/docs/misc/xen-command-line.markdown -@@ -496,9 +496,10 @@ accounting for hardware capabilities as enumerated via CPUID. - - Currently accepted: - --The Speculation Control hardware features `ibrsb`, `stibp`, `ibpb` are used by --default if avaiable. They can be ignored, e.g. `no-ibrsb`, at which point Xen --won't use them itself, and won't offer them to guests. -+The Speculation Control hardware features `ibrsb`, `stibp`, `ibpb`, `ssbd` are -+used by default if available and applicable. They can be ignored, -+e.g. `no-ibrsb`, at which point Xen won't use them itself, and won't offer -+them to guests. - - ### cpuid\_mask\_cpu (AMD only) - > `= fam_0f_rev_c | fam_0f_rev_d | fam_0f_rev_e | fam_0f_rev_f | fam_0f_rev_g | fam_10_rev_b | fam_10_rev_c | fam_11_rev_b` -@@ -1728,7 +1729,7 @@ protect itself, and Xen's ability to virtualise support for guests to use. - respectively. - * `msr-sc=` offers control over Xen's support for manipulating MSR\_SPEC\_CTRL - on entry and exit. These blocks are necessary to virtualise support for -- guests and if disabled, guests will be unable to use IBRS/STIBP/etc. -+ guests and if disabled, guests will be unable to use IBRS/STIBP/SSBD/etc. - * `rsb=` offers control over whether to overwrite the Return Stack Buffer / - Return Address Stack on entry to Xen. - -@@ -1750,7 +1751,8 @@ prediction barriers on vcpu context switches. - On hardware supporting SSBD (Speculative Store Bypass Disable), the `ssbd=` - option can be used to force or prevent Xen using the feature itself. On AMD - hardware, this is a global option applied at boot, and not virtualised for --guest use. -+guest use. On Intel hardware, the feature is virtualised for guests, -+independently of Xen's choice of setting. - - ### sync\_console - > `= <boolean>` -diff --git a/tools/libxl/libxl_cpuid.c b/tools/libxl/libxl_cpuid.c -index 3a21f4e..7b0f594 100644 ---- a/tools/libxl/libxl_cpuid.c -+++ b/tools/libxl/libxl_cpuid.c -@@ -205,6 +205,7 @@ int libxl_cpuid_parse_config(libxl_cpuid_policy_list *cpuid, const char* str) - {"ibrsb", 0x00000007, 0, CPUID_REG_EDX, 26, 1}, - {"stibp", 0x00000007, 0, CPUID_REG_EDX, 27, 1}, - {"arch-caps", 0x00000007, 0, CPUID_REG_EDX, 29, 1}, -+ {"ssbd", 0x00000007, 0, CPUID_REG_EDX, 31, 1}, - - {"lahfsahf", 0x80000001, NA, CPUID_REG_ECX, 0, 1}, - {"cmplegacy", 0x80000001, NA, CPUID_REG_ECX, 1, 1}, -diff --git a/tools/misc/xen-cpuid.c b/tools/misc/xen-cpuid.c -index b1a46c6..2483a81 100644 ---- a/tools/misc/xen-cpuid.c -+++ b/tools/misc/xen-cpuid.c -@@ -166,8 +166,7 @@ static const char *str_7d0[32] = - - [26] = "ibrsb", [27] = "stibp", - [28] = "REZ", [29] = "arch_caps", -- -- [30 ... 31] = "REZ", -+ [30] = "REZ", [31] = "ssbd", - }; - - static struct { -diff --git a/xen/arch/x86/cpuid.c b/xen/arch/x86/cpuid.c -index b45b145..6a710b7 100644 ---- a/xen/arch/x86/cpuid.c -+++ b/xen/arch/x86/cpuid.c -@@ -43,6 +43,11 @@ static int __init parse_xen_cpuid(const char *s) - if ( !val ) - setup_clear_cpu_cap(X86_FEATURE_STIBP); - } -+ else if ( (val = parse_boolean("ssbd", s, ss)) >= 0 ) -+ { -+ if ( !val ) -+ setup_clear_cpu_cap(X86_FEATURE_SSBD); -+ } - else - rc = -EINVAL; - -diff --git a/xen/arch/x86/spec_ctrl.c b/xen/arch/x86/spec_ctrl.c -index e326056..89e3825 100644 ---- a/xen/arch/x86/spec_ctrl.c -+++ b/xen/arch/x86/spec_ctrl.c -@@ -192,26 +192,31 @@ static void __init print_details(enum ind_thunk thunk, uint64_t caps) - printk("Speculative mitigation facilities:\n"); - - /* Hardware features which pertain to speculative mitigations. */ -- printk(" Hardware features:%s%s%s%s%s%s\n", -+ printk(" Hardware features:%s%s%s%s%s%s%s%s\n", - (_7d0 & cpufeat_mask(X86_FEATURE_IBRSB)) ? " IBRS/IBPB" : "", - (_7d0 & cpufeat_mask(X86_FEATURE_STIBP)) ? " STIBP" : "", -+ (_7d0 & cpufeat_mask(X86_FEATURE_SSBD)) ? " SSBD" : "", - (e8b & cpufeat_mask(X86_FEATURE_IBPB)) ? " IBPB" : "", - (caps & ARCH_CAPABILITIES_IBRS_ALL) ? " IBRS_ALL" : "", - (caps & ARCH_CAPABILITIES_RDCL_NO) ? " RDCL_NO" : "", -- (caps & ARCH_CAPS_RSBA) ? " RSBA" : ""); -+ (caps & ARCH_CAPS_RSBA) ? " RSBA" : "", -+ (caps & ARCH_CAPS_SSB_NO) ? " SSB_NO" : ""); - - /* Compiled-in support which pertains to BTI mitigations. */ - if ( IS_ENABLED(CONFIG_INDIRECT_THUNK) ) - printk(" Compiled-in support: INDIRECT_THUNK\n"); - - /* Settings for Xen's protection, irrespective of guests. */ -- printk(" Xen settings: BTI-Thunk %s, SPEC_CTRL: %s, Other:%s\n", -+ printk(" Xen settings: BTI-Thunk %s, SPEC_CTRL: %s%s, Other:%s\n", - thunk == THUNK_NONE ? "N/A" : - thunk == THUNK_RETPOLINE ? "RETPOLINE" : - thunk == THUNK_LFENCE ? "LFENCE" : - thunk == THUNK_JMP ? "JMP" : "?", - !use_spec_ctrl ? "No" : - (default_xen_spec_ctrl & SPEC_CTRL_IBRS) ? "IBRS+" : "IBRS-", -+ !use_spec_ctrl || !boot_cpu_has(X86_FEATURE_SSBD) -+ ? "" : -+ (default_xen_spec_ctrl & SPEC_CTRL_SSBD) ? " SSBD+" : " SSBD-", - opt_ibpb ? " IBPB" : ""); - - /* -@@ -415,6 +420,10 @@ void __init init_speculation_mitigations(void) - } - } - -+ /* If we have SSBD available, see whether we should use it. */ -+ if ( boot_cpu_has(X86_FEATURE_SSBD) && use_spec_ctrl && opt_ssbd ) -+ default_xen_spec_ctrl |= SPEC_CTRL_SSBD; -+ - /* - * PV guests can poison the RSB to any virtual address from which - * they can execute a call instruction. This is necessarily outside -diff --git a/xen/include/asm-x86/msr-index.h b/xen/include/asm-x86/msr-index.h -index 68fae91..93d6f4e 100644 ---- a/xen/include/asm-x86/msr-index.h -+++ b/xen/include/asm-x86/msr-index.h -@@ -38,6 +38,7 @@ - #define MSR_SPEC_CTRL 0x00000048 - #define SPEC_CTRL_IBRS (_AC(1, ULL) << 0) - #define SPEC_CTRL_STIBP (_AC(1, ULL) << 1) -+#define SPEC_CTRL_SSBD (_AC(1, ULL) << 2) - - #define MSR_PRED_CMD 0x00000049 - #define PRED_CMD_IBPB (_AC(1, ULL) << 0) -@@ -46,6 +47,7 @@ - #define ARCH_CAPABILITIES_RDCL_NO (_AC(1, ULL) << 0) - #define ARCH_CAPABILITIES_IBRS_ALL (_AC(1, ULL) << 1) - #define ARCH_CAPS_RSBA (_AC(1, ULL) << 2) -+#define ARCH_CAPS_SSB_NO (_AC(1, ULL) << 4) - - /* Intel MSRs. Some also available on other CPUs */ - #define MSR_IA32_PERFCTR0 0x000000c1 -diff --git a/xen/include/public/arch-x86/cpufeatureset.h b/xen/include/public/arch-x86/cpufeatureset.h -index 8da5783..7acf822 100644 ---- a/xen/include/public/arch-x86/cpufeatureset.h -+++ b/xen/include/public/arch-x86/cpufeatureset.h -@@ -245,6 +245,7 @@ XEN_CPUFEATURE(AVX512_4FMAPS, 9*32+ 3) /*A AVX512 Multiply Accumulation Single - XEN_CPUFEATURE(IBRSB, 9*32+26) /*A IBRS and IBPB support (used by Intel) */ - XEN_CPUFEATURE(STIBP, 9*32+27) /*A! STIBP */ - XEN_CPUFEATURE(ARCH_CAPS, 9*32+29) /* IA32_ARCH_CAPABILITIES MSR */ -+XEN_CPUFEATURE(SSBD, 9*32+31) /* MSR_SPEC_CTRL.SSBD available */ - - #endif /* XEN_CPUFEATURE */ - -diff --git a/xen/tools/gen-cpuid.py b/xen/tools/gen-cpuid.py -index 613b909..65526ff 100755 ---- a/xen/tools/gen-cpuid.py -+++ b/xen/tools/gen-cpuid.py -@@ -257,10 +257,19 @@ def crunch_numbers(state): - AVX512BW, AVX512VL, AVX512VBMI, AVX512_4VNNIW, - AVX512_4FMAPS, AVX512_VPOPCNTDQ], - -- # Single Thread Indirect Branch Predictors enumerates a new bit in the -- # MSR enumerated by Indirect Branch Restricted Speculation/Indirect -- # Branch Prediction Barrier enumeration. -- IBRSB: [STIBP], -+ # The features: -+ # * Single Thread Indirect Branch Predictors -+ # * Speculative Store Bypass Disable -+ # -+ # enumerate new bits in MSR_SPEC_CTRL, which is enumerated by Indirect -+ # Branch Restricted Speculation/Indirect Branch Prediction Barrier. -+ # -+ # In practice, these features also enumerate the presense of -+ # MSR_SPEC_CTRL. However, no real hardware will exist with SSBD but -+ # not IBRSB, and we pass this MSR directly to guests. Treating them -+ # as dependent features simplifies Xen's logic, and prevents the guest -+ # from seeing implausible configurations. -+ IBRSB: [STIBP, SSBD], - } - - deep_features = tuple(sorted(deps.keys())) --- -2.1.4 - diff --git a/system/xen/xsa/xsa263-4.10-0013-x86-msr-Virtualise-MSR_SPEC_CTRL.SSBD-for-guests-to-.patch b/system/xen/xsa/xsa263-4.10-0013-x86-msr-Virtualise-MSR_SPEC_CTRL.SSBD-for-guests-to-.patch deleted file mode 100644 index cb8cdb3c561db..0000000000000 --- a/system/xen/xsa/xsa263-4.10-0013-x86-msr-Virtualise-MSR_SPEC_CTRL.SSBD-for-guests-to-.patch +++ /dev/null @@ -1,70 +0,0 @@ -From 02d0027a89dc49875a41e939498936874a32360f Mon Sep 17 00:00:00 2001 -From: Andrew Cooper <andrew.cooper3@citrix.com> -Date: Fri, 13 Apr 2018 15:42:34 +0000 -Subject: [PATCH] x86/msr: Virtualise MSR_SPEC_CTRL.SSBD for guests to use - -Almost all infrastructure is already in place. Update the reserved bits -calculation in guest_wrmsr(), and offer SSBD to guests by default. - -Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com> -Reviewed-by: Jan Beulich <jbeulich@suse.com> ---- - xen/arch/x86/msr.c | 8 ++++++-- - xen/include/public/arch-x86/cpufeatureset.h | 2 +- - 2 files changed, 7 insertions(+), 3 deletions(-) - -diff --git a/xen/arch/x86/msr.c b/xen/arch/x86/msr.c -index 48d061d..21219c4 100644 ---- a/xen/arch/x86/msr.c -+++ b/xen/arch/x86/msr.c -@@ -178,6 +178,8 @@ int guest_wrmsr(struct vcpu *v, uint32_t msr, uint64_t val) - - switch ( msr ) - { -+ uint64_t rsvd; -+ - case MSR_INTEL_PLATFORM_INFO: - case MSR_ARCH_CAPABILITIES: - /* Read-only */ -@@ -213,8 +215,10 @@ int guest_wrmsr(struct vcpu *v, uint32_t msr, uint64_t val) - * Note: SPEC_CTRL_STIBP is specified as safe to use (i.e. ignored) - * when STIBP isn't enumerated in hardware. - */ -+ rsvd = ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | -+ (cp->feat.ssbd ? SPEC_CTRL_SSBD : 0)); - -- if ( val & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP) ) -+ if ( val & rsvd ) - goto gp_fault; /* Rsvd bit set? */ - - vp->spec_ctrl.raw = val; -@@ -233,12 +237,12 @@ int guest_wrmsr(struct vcpu *v, uint32_t msr, uint64_t val) - - case MSR_INTEL_MISC_FEATURES_ENABLES: - { -- uint64_t rsvd = ~0ull; - bool old_cpuid_faulting = vp->misc_features_enables.cpuid_faulting; - - if ( !vp->misc_features_enables.available ) - goto gp_fault; - -+ rsvd = ~0ull; - if ( dp->plaform_info.cpuid_faulting ) - rsvd &= ~MSR_MISC_FEATURES_CPUID_FAULTING; - -diff --git a/xen/include/public/arch-x86/cpufeatureset.h b/xen/include/public/arch-x86/cpufeatureset.h -index 7acf822..c721c12 100644 ---- a/xen/include/public/arch-x86/cpufeatureset.h -+++ b/xen/include/public/arch-x86/cpufeatureset.h -@@ -245,7 +245,7 @@ XEN_CPUFEATURE(AVX512_4FMAPS, 9*32+ 3) /*A AVX512 Multiply Accumulation Single - XEN_CPUFEATURE(IBRSB, 9*32+26) /*A IBRS and IBPB support (used by Intel) */ - XEN_CPUFEATURE(STIBP, 9*32+27) /*A! STIBP */ - XEN_CPUFEATURE(ARCH_CAPS, 9*32+29) /* IA32_ARCH_CAPABILITIES MSR */ --XEN_CPUFEATURE(SSBD, 9*32+31) /* MSR_SPEC_CTRL.SSBD available */ -+XEN_CPUFEATURE(SSBD, 9*32+31) /*A MSR_SPEC_CTRL.SSBD available */ - - #endif /* XEN_CPUFEATURE */ - --- -2.1.4 - diff --git a/system/xen/xsa/xsa273-d757c29ffe2e31b15397e43cd58da88b6318b654.patch b/system/xen/xsa/xsa273-d757c29ffe2e31b15397e43cd58da88b6318b654.patch new file mode 100644 index 0000000000000..ab9794df5e883 --- /dev/null +++ b/system/xen/xsa/xsa273-d757c29ffe2e31b15397e43cd58da88b6318b654.patch @@ -0,0 +1,4115 @@ +diff --git a/docs/man/xl.conf.pod.5 b/docs/man/xl.conf.pod.5 +index da91b8626c..37262a7ef8 100644 +--- a/docs/man/xl.conf.pod.5 ++++ b/docs/man/xl.conf.pod.5 +@@ -185,6 +185,28 @@ massively huge guests). + + =back + ++=item B<vm.cpumask>="CPULIST" ++ ++=item B<vm.hvm.cpumask>="CPULIST" ++ ++=item B<vm.pv.cpumask>="CPULIST" ++ ++Global masks that are applied when creating guests and pinning vcpus ++to indicate which cpus they are allowed to run on. Specifically, ++C<vm.cpumask> applies to all guest types, C<vm.hvm.cpumask> applies to ++both HVM and PVH guests and C<vm.pv.cpumask> applies to PV guests. ++ ++The hard affinity of guest's vcpus are logical-AND'ed with respective ++masks. If the resulting affinity mask is empty, operation will fail. ++ ++Use --ignore-global-affinity-masks to skip applying global masks. ++ ++The default value for these masks are all 1's, i.e. all cpus are allowed. ++ ++Due to bug(s), these options may not interact well with other options ++concerning CPU affinity. One example is CPU pools. Users should always double ++check that the required affinity has taken effect. ++ + =back + + =head1 SEE ALSO +diff --git a/docs/misc/xen-command-line.markdown b/docs/misc/xen-command-line.markdown +index 075e5ea159..0886706368 100644 +--- a/docs/misc/xen-command-line.markdown ++++ b/docs/misc/xen-command-line.markdown +@@ -489,10 +489,10 @@ accounting for hardware capabilities as enumerated via CPUID. + + Currently accepted: + +-The Speculation Control hardware features `ibrsb`, `stibp`, `ibpb`, `ssbd` are +-used by default if available and applicable. They can be ignored, +-e.g. `no-ibrsb`, at which point Xen won't use them itself, and won't offer +-them to guests. ++The Speculation Control hardware features `ibrsb`, `stibp`, `ibpb`, ++`l1d-flush` and `ssbd` are used by default if available and applicable. They can ++be ignored, e.g. `no-ibrsb`, at which point Xen won't use them itself, and ++won't offer them to guests. + + ### cpuid\_mask\_cpu (AMD only) + > `= fam_0f_rev_c | fam_0f_rev_d | fam_0f_rev_e | fam_0f_rev_f | fam_0f_rev_g | fam_10_rev_b | fam_10_rev_c | fam_11_rev_b` +@@ -936,6 +936,8 @@ version are 1 and 2. + use of grant table v2 without transitive grants is an ABI breakage from the + guests point of view. + ++The usage of gnttab v2 is not security supported on ARM platforms. ++ + ### gnttab\_max\_frames + > `= <integer>` + +@@ -1544,6 +1546,30 @@ do; there may be other custom operating systems which do. If you're + certain you don't plan on having PV guests which use this feature, + turning it off can reduce the attack surface. + ++### pv-l1tf (x86) ++> `= List of [ <bool>, dom0=<bool>, domu=<bool> ]` ++ ++> Default: `false` on believed-unaffected hardware, or in pv-shim mode. ++> `domu` on believed-affected hardware. ++ ++Mitigations for L1TF / XSA-273 / CVE-2018-3620 for PV guests. ++ ++For backwards compatibility, we may not alter an architecturally-legitimate ++pagetable entry a PV guest chooses to write. We can however force such a ++guest into shadow mode so that Xen controls the PTEs which are reachable by ++the CPU pagewalk. ++ ++Shadowing is performed at the point where a PV guest first tries to write an ++L1TF-vulnerable PTE. Therefore, a PV guest kernel which has been updated with ++its own L1TF mitigations will not trigger shadow mode if it is well behaved. ++ ++If CONFIG\_SHADOW\_PAGING is not compiled in, this mitigation instead crashes ++the guest when an L1TF-vulnerable PTE is written, which still allows updated, ++well-behaved PV guests to run, despite Shadow being compiled out. ++ ++In the pv-shim case, Shadow is expected to be compiled out, and a malicious ++guest kernel can only leak data from the shim Xen, rather than the host Xen. ++ + ### pv-shim (x86) + > `= <boolean>` + +@@ -1748,6 +1774,13 @@ Use `smap=hvm` to allow SMAP use by HVM guests only. + Flag to enable Supervisor Mode Execution Protection + Use `smep=hvm` to allow SMEP use by HVM guests only. + ++### smt (x86) ++> `= <boolean>` ++ ++Default: `true` ++ ++Control bring up of multiple hyper-threads per CPU core. ++ + ### snb\_igd\_quirk + > `= <boolean> | cap | <integer>` + +@@ -1758,7 +1791,8 @@ false disable the quirk workaround, which is also the default. + + ### spec-ctrl (x86) + > `= List of [ <bool>, xen=<bool>, {pv,hvm,msr-sc,rsb}=<bool>, +-> bti-thunk=retpoline|lfence|jmp, {ibrs,ibpb,ssbd,eager-fpu}=<bool> ]` ++> bti-thunk=retpoline|lfence|jmp, {ibrs,ibpb,ssbd,eager-fpu, ++> l1d-flush}=<bool> ]` + + Controls for speculative execution sidechannel mitigations. By default, Xen + will pick the most appropriate mitigations based on compiled in support, +@@ -1770,10 +1804,15 @@ extreme care.** + + An overall boolean value, `spec-ctrl=no`, can be specified to turn off all + mitigations, including pieces of infrastructure used to virtualise certain +-mitigation features for guests. Alternatively, a slightly more restricted +-`spec-ctrl=no-xen` can be used to turn off all of Xen's mitigations, while +-leaving the virtualisation support in place for guests to use. Use of a +-positive boolean value for either of these options is invalid. ++mitigation features for guests. This also includes settings which `xpti`, ++`smt`, `pv-l1tf` control, unless the respective option(s) have been ++specified earlier on the command line. ++ ++Alternatively, a slightly more restricted `spec-ctrl=no-xen` can be used to ++turn off all of Xen's mitigations, while leaving the virtualisation support ++in place for guests to use. ++ ++Use of a positive boolean value for either of these options is invalid. + + The booleans `pv=`, `hvm=`, `msr-sc=` and `rsb=` offer fine grained control + over the alternative blocks used by Xen. These impact Xen's ability to +@@ -1813,6 +1852,12 @@ from using fully eager FPU context switches. This is currently implemented as + a global control. By default, Xen will choose to use fully eager context + switches on hardware believed to speculate past #NM exceptions. + ++On hardware supporting L1D_FLUSH, the `l1d-flush=` option can be used to force ++or prevent Xen from issuing an L1 data cache flush on each VMEntry. ++Irrespective of Xen's setting, the feature is virtualised for HVM guests to ++use. By default, Xen will enable this mitigation on hardware believed to be ++vulnerable to L1TF. ++ + ### sync\_console + > `= <boolean>` + +diff --git a/tools/examples/xl.conf b/tools/examples/xl.conf +index 374b6bbc2e..0446deb304 100644 +--- a/tools/examples/xl.conf ++++ b/tools/examples/xl.conf +@@ -37,3 +37,8 @@ + # (which can take a long time to find out if launching huge guests). + # see xl.conf(5) for details. + #claim_mode=1 ++ ++# Specify global vcpu hard affinity masks. See xl.conf(5) for details. ++#vm.cpumask="0-7" ++#vm.pv.cpumask="0-3" ++#vm.hvm.cpumask="3-7" +diff --git a/tools/libxl/libxl_cpuid.c b/tools/libxl/libxl_cpuid.c +index 7b0f594c3d..52e16c20ed 100644 +--- a/tools/libxl/libxl_cpuid.c ++++ b/tools/libxl/libxl_cpuid.c +@@ -204,6 +204,7 @@ int libxl_cpuid_parse_config(libxl_cpuid_policy_list *cpuid, const char* str) + {"avx512-4fmaps",0x00000007, 0, CPUID_REG_EDX, 3, 1}, + {"ibrsb", 0x00000007, 0, CPUID_REG_EDX, 26, 1}, + {"stibp", 0x00000007, 0, CPUID_REG_EDX, 27, 1}, ++ {"l1d-flush", 0x00000007, 0, CPUID_REG_EDX, 28, 1}, + {"arch-caps", 0x00000007, 0, CPUID_REG_EDX, 29, 1}, + {"ssbd", 0x00000007, 0, CPUID_REG_EDX, 31, 1}, + +diff --git a/tools/misc/xen-cpuid.c b/tools/misc/xen-cpuid.c +index e116339733..3888b4e158 100644 +--- a/tools/misc/xen-cpuid.c ++++ b/tools/misc/xen-cpuid.c +@@ -143,7 +143,7 @@ static const char *str_7d0[32] = + [ 2] = "avx512_4vnniw", [ 3] = "avx512_4fmaps", + + [26] = "ibrsb", [27] = "stibp", +- /* 28 */ [29] = "arch_caps", ++ [28] = "l1d_flush", [29] = "arch_caps", + /* 30 */ [31] = "ssbd", + }; + +diff --git a/tools/ocaml/xenstored/store.ml b/tools/ocaml/xenstored/store.ml +index 13cf3b5bf4..5a8c377603 100644 +--- a/tools/ocaml/xenstored/store.ml ++++ b/tools/ocaml/xenstored/store.ml +@@ -262,7 +262,8 @@ let path_write store perm path value = + Node.check_perm store.root perm Perms.WRITE; + Node.set_value store.root value, false + ) else +- Path.apply_modify store.root path do_write, !node_created ++ let root = Path.apply_modify store.root path do_write in ++ root, !node_created + + let path_rm store perm path = + let do_rm node name = +diff --git a/tools/xl/xl.c b/tools/xl/xl.c +index 179908b4f6..7d2142f16f 100644 +--- a/tools/xl/xl.c ++++ b/tools/xl/xl.c +@@ -28,6 +28,9 @@ + #include <libxl_utils.h> + #include <libxlutil.h> + #include "xl.h" ++#include "xl_parse.h" ++ ++#include "xl_utils.h" + + xentoollog_logger_stdiostream *logger; + int dryrun_only; +@@ -42,6 +45,9 @@ char *default_gatewaydev = NULL; + char *default_vifbackend = NULL; + char *default_remus_netbufscript = NULL; + char *default_colo_proxy_script = NULL; ++libxl_bitmap global_vm_affinity_mask; ++libxl_bitmap global_hvm_affinity_mask; ++libxl_bitmap global_pv_affinity_mask; + enum output_format default_output_format = OUTPUT_FORMAT_JSON; + int claim_mode = 1; + bool progress_use_cr = 0; +@@ -203,6 +209,26 @@ static void parse_global_config(const char *configfile, + if (!xlu_cfg_get_long (config, "max_maptrack_frames", &l, 0)) + max_maptrack_frames = l; + ++ libxl_bitmap_init(&global_vm_affinity_mask); ++ libxl_cpu_bitmap_alloc(ctx, &global_vm_affinity_mask, 0); ++ libxl_bitmap_init(&global_hvm_affinity_mask); ++ libxl_cpu_bitmap_alloc(ctx, &global_hvm_affinity_mask, 0); ++ libxl_bitmap_init(&global_pv_affinity_mask); ++ libxl_cpu_bitmap_alloc(ctx, &global_pv_affinity_mask, 0); ++ ++ if (!xlu_cfg_get_string (config, "vm.cpumask", &buf, 0)) ++ parse_cpurange(buf, &global_vm_affinity_mask); ++ else ++ libxl_bitmap_set_any(&global_vm_affinity_mask); ++ if (!xlu_cfg_get_string (config, "vm.hvm.cpumask", &buf, 0)) ++ parse_cpurange(buf, &global_hvm_affinity_mask); ++ else ++ libxl_bitmap_set_any(&global_hvm_affinity_mask); ++ if (!xlu_cfg_get_string (config, "vm.pv.cpumask", &buf, 0)) ++ parse_cpurange(buf, &global_pv_affinity_mask); ++ else ++ libxl_bitmap_set_any(&global_pv_affinity_mask); ++ + xlu_cfg_destroy(config); + } + +diff --git a/tools/xl/xl.h b/tools/xl/xl.h +index 4e784ff402..7e97144b50 100644 +--- a/tools/xl/xl.h ++++ b/tools/xl/xl.h +@@ -41,6 +41,7 @@ struct domain_create { + int vncautopass; + int console_autoconnect; + int checkpointed_stream; ++ int ignore_global_affinity_masks; + const char *config_file; + char *extra_config; /* extra config string */ + const char *restore_file; +@@ -279,6 +280,9 @@ extern char *default_colo_proxy_script; + extern char *blkdev_start; + extern int max_grant_frames; + extern int max_maptrack_frames; ++extern libxl_bitmap global_vm_affinity_mask; ++extern libxl_bitmap global_hvm_affinity_mask; ++extern libxl_bitmap global_pv_affinity_mask; + + enum output_format { + OUTPUT_FORMAT_JSON, +@@ -294,6 +298,9 @@ typedef enum { + } domain_restart_type; + + extern void printf_info_sexp(int domid, libxl_domain_config *d_config, FILE *fh); ++extern void apply_global_affinity_masks(libxl_domain_type type, ++ libxl_bitmap *vcpu_affinity_array, ++ unsigned int size); + + #define XL_GLOBAL_CONFIG XEN_CONFIG_DIR "/xl.conf" + #define XL_LOCK_FILE XEN_LOCK_DIR "/xl" +diff --git a/tools/xl/xl_cmdtable.c b/tools/xl/xl_cmdtable.c +index bf2ced8140..54c2db6022 100644 +--- a/tools/xl/xl_cmdtable.c ++++ b/tools/xl/xl_cmdtable.c +@@ -34,7 +34,8 @@ struct cmd_spec cmd_table[] = { + "-e Do not wait in the background for the death of the domain.\n" + "-V, --vncviewer Connect to the VNC display after the domain is created.\n" + "-A, --vncviewer-autopass\n" +- " Pass VNC password to viewer via stdin." ++ " Pass VNC password to viewer via stdin.\n" ++ "--ignore-global-affinity-masks Ignore global masks in xl.conf." + }, + { "config-update", + &main_config_update, 1, 1, +@@ -224,7 +225,8 @@ struct cmd_spec cmd_table[] = { + &main_vcpupin, 1, 1, + "Set which CPUs a VCPU can use", + "[option] <Domain> <VCPU|all> <Hard affinity|-|all> <Soft affinity|-|all>", +- "-f, --force undo an override pinning done by the kernel", ++ "-f, --force undo an override pinning done by the kernel\n" ++ "--ignore-global-affinity-masks Ignore global masks in xl.conf", + }, + { "vcpu-set", + &main_vcpuset, 0, 1, +diff --git a/tools/xl/xl_vcpu.c b/tools/xl/xl_vcpu.c +index 8e735b38c1..3384eeed06 100644 +--- a/tools/xl/xl_vcpu.c ++++ b/tools/xl/xl_vcpu.c +@@ -68,6 +68,61 @@ static void print_domain_vcpuinfo(uint32_t domid, uint32_t nr_cpus) + libxl_vcpuinfo_list_free(vcpuinfo, nb_vcpu); + } + ++void apply_global_affinity_masks(libxl_domain_type type, ++ libxl_bitmap *vcpu_affinity_array, ++ unsigned int size) ++{ ++ libxl_bitmap *mask = &global_vm_affinity_mask; ++ libxl_bitmap *type_mask; ++ unsigned int i; ++ ++ switch (type) { ++ case LIBXL_DOMAIN_TYPE_HVM: ++ case LIBXL_DOMAIN_TYPE_PVH: ++ type_mask = &global_hvm_affinity_mask; ++ break; ++ case LIBXL_DOMAIN_TYPE_PV: ++ type_mask = &global_pv_affinity_mask; ++ break; ++ default: ++ fprintf(stderr, "Unknown guest type\n"); ++ exit(EXIT_FAILURE); ++ } ++ ++ for (i = 0; i < size; i++) { ++ int rc; ++ libxl_bitmap *t = &vcpu_affinity_array[i]; ++ libxl_bitmap b1, b2; ++ ++ libxl_bitmap_init(&b1); ++ libxl_bitmap_init(&b2); ++ ++ rc = libxl_bitmap_and(ctx, &b1, t, mask); ++ if (rc) { ++ fprintf(stderr, "libxl_bitmap_and errored\n"); ++ exit(EXIT_FAILURE); ++ } ++ rc = libxl_bitmap_and(ctx, &b2, &b1, type_mask); ++ if (rc) { ++ fprintf(stderr, "libxl_bitmap_and errored\n"); ++ exit(EXIT_FAILURE); ++ } ++ ++ if (libxl_bitmap_is_empty(&b2)) { ++ fprintf(stderr, "vcpu hard affinity map is empty\n"); ++ exit(EXIT_FAILURE); ++ } ++ ++ /* Replace target bitmap with the result */ ++ libxl_bitmap_dispose(t); ++ libxl_bitmap_init(t); ++ libxl_bitmap_copy_alloc(ctx, t, &b2); ++ ++ libxl_bitmap_dispose(&b1); ++ libxl_bitmap_dispose(&b2); ++ } ++} ++ + static void vcpulist(int argc, char **argv) + { + libxl_dominfo *dominfo; +@@ -118,6 +173,7 @@ int main_vcpupin(int argc, char **argv) + { + static struct option opts[] = { + {"force", 0, 0, 'f'}, ++ {"ignore-global-affinity-masks", 0, 0, 'i'}, + COMMON_LONG_OPTS + }; + libxl_vcpuinfo *vcpuinfo; +@@ -132,15 +188,18 @@ int main_vcpupin(int argc, char **argv) + const char *vcpu, *hard_str, *soft_str; + char *endptr; + int opt, nb_cpu, nb_vcpu, rc = EXIT_FAILURE; +- bool force = false; ++ bool force = false, ignore_masks = false; + + libxl_bitmap_init(&cpumap_hard); + libxl_bitmap_init(&cpumap_soft); + +- SWITCH_FOREACH_OPT(opt, "f", opts, "vcpu-pin", 3) { ++ SWITCH_FOREACH_OPT(opt, "fi", opts, "vcpu-pin", 3) { + case 'f': + force = true; + break; ++ case 'i': ++ ignore_masks = true; ++ break; + default: + break; + } +@@ -222,6 +281,23 @@ int main_vcpupin(int argc, char **argv) + goto out; + } + ++ /* Only hard affinity matters here */ ++ if (!ignore_masks) { ++ libxl_domain_config d_config; ++ ++ libxl_domain_config_init(&d_config); ++ rc = libxl_retrieve_domain_configuration(ctx, domid, &d_config); ++ if (rc) { ++ fprintf(stderr, "Could not retrieve domain configuration\n"); ++ libxl_domain_config_dispose(&d_config); ++ goto out; ++ } ++ ++ apply_global_affinity_masks(d_config.b_info.type, hard, 1); ++ ++ libxl_domain_config_dispose(&d_config); ++ } ++ + if (force) { + if (libxl_set_vcpuaffinity_force(ctx, domid, vcpuid, hard, soft)) { + fprintf(stderr, "Could not set affinity for vcpu `%ld'.\n", +diff --git a/tools/xl/xl_vmcontrol.c b/tools/xl/xl_vmcontrol.c +index 89c2b25ded..a1d633795c 100644 +--- a/tools/xl/xl_vmcontrol.c ++++ b/tools/xl/xl_vmcontrol.c +@@ -804,6 +804,36 @@ int create_domain(struct domain_create *dom_info) + parse_config_data(config_source, config_data, config_len, &d_config); + } + ++ if (!dom_info->ignore_global_affinity_masks) { ++ libxl_domain_build_info *b_info = &d_config.b_info; ++ ++ /* It is possible that no hard affinity is specified in config file. ++ * Generate hard affinity maps now if we care about those. ++ */ ++ if (b_info->num_vcpu_hard_affinity == 0 && ++ (!libxl_bitmap_is_full(&global_vm_affinity_mask) || ++ (b_info->type == LIBXL_DOMAIN_TYPE_PV && ++ !libxl_bitmap_is_full(&global_pv_affinity_mask)) || ++ (b_info->type != LIBXL_DOMAIN_TYPE_PV && ++ !libxl_bitmap_is_full(&global_hvm_affinity_mask)) ++ )) { ++ b_info->num_vcpu_hard_affinity = b_info->max_vcpus; ++ b_info->vcpu_hard_affinity = ++ xmalloc(b_info->max_vcpus * sizeof(libxl_bitmap)); ++ ++ for (i = 0; i < b_info->num_vcpu_hard_affinity; i++) { ++ libxl_bitmap *m = &b_info->vcpu_hard_affinity[i]; ++ libxl_bitmap_init(m); ++ libxl_cpu_bitmap_alloc(ctx, m, 0); ++ libxl_bitmap_set_any(m); ++ } ++ } ++ ++ apply_global_affinity_masks(b_info->type, ++ b_info->vcpu_hard_affinity, ++ b_info->num_vcpu_hard_affinity); ++ } ++ + if (migrate_fd >= 0) { + if (d_config.c_info.name) { + /* when we receive a domain we get its name from the config +@@ -1124,7 +1154,7 @@ int main_create(int argc, char **argv) + const char *filename = NULL; + struct domain_create dom_info; + int paused = 0, debug = 0, daemonize = 1, console_autoconnect = 0, +- quiet = 0, monitor = 1, vnc = 0, vncautopass = 0; ++ quiet = 0, monitor = 1, vnc = 0, vncautopass = 0, ignore_masks = 0; + int opt, rc; + static struct option opts[] = { + {"dryrun", 0, 0, 'n'}, +@@ -1132,6 +1162,7 @@ int main_create(int argc, char **argv) + {"defconfig", 1, 0, 'f'}, + {"vncviewer", 0, 0, 'V'}, + {"vncviewer-autopass", 0, 0, 'A'}, ++ {"ignore-global-affinity-masks", 0, 0, 'i'}, + COMMON_LONG_OPTS + }; + +@@ -1142,7 +1173,7 @@ int main_create(int argc, char **argv) + argc--; argv++; + } + +- SWITCH_FOREACH_OPT(opt, "Fnqf:pcdeVA", opts, "create", 0) { ++ SWITCH_FOREACH_OPT(opt, "Fnqf:pcdeVAi", opts, "create", 0) { + case 'f': + filename = optarg; + break; +@@ -1174,6 +1205,9 @@ int main_create(int argc, char **argv) + case 'A': + vnc = vncautopass = 1; + break; ++ case 'i': ++ ignore_masks = 1; ++ break; + } + + memset(&dom_info, 0, sizeof(dom_info)); +@@ -1203,6 +1237,7 @@ int main_create(int argc, char **argv) + dom_info.vnc = vnc; + dom_info.vncautopass = vncautopass; + dom_info.console_autoconnect = console_autoconnect; ++ dom_info.ignore_global_affinity_masks = ignore_masks; + + rc = create_domain(&dom_info); + if (rc < 0) { +#diff --git a/xen/Makefile b/xen/Makefile +#index 4d075c381f..a922a1b7b5 100644 +#--- a/xen/Makefile +#+++ b/xen/Makefile +#@@ -2,7 +2,7 @@ +# # All other places this is stored (eg. compile.h) should be autogenerated. +# export XEN_VERSION = 4 +# export XEN_SUBVERSION = 11 +#-export XEN_EXTRAVERSION ?= .0$(XEN_VENDORVERSION) +#+export XEN_EXTRAVERSION ?= .1-pre$(XEN_VENDORVERSION) +# export XEN_FULLVERSION = $(XEN_VERSION).$(XEN_SUBVERSION)$(XEN_EXTRAVERSION) +# -include xen-version +# +diff --git a/xen/arch/x86/Kconfig b/xen/arch/x86/Kconfig +index f64fc56739..cfba4a708c 100644 +--- a/xen/arch/x86/Kconfig ++++ b/xen/arch/x86/Kconfig +@@ -72,6 +72,7 @@ config SHADOW_PAGING + * Running HVM guests on hardware lacking hardware paging support + (First-generation Intel VT-x or AMD SVM). + * Live migration of PV guests. ++ * L1TF sidechannel mitigation for PV guests. + + Under a small number of specific workloads, shadow paging may be + deliberately used as a performance optimisation. +diff --git a/xen/arch/x86/cpu/amd.c b/xen/arch/x86/cpu/amd.c +index 458a3fe60c..76078b55b2 100644 +--- a/xen/arch/x86/cpu/amd.c ++++ b/xen/arch/x86/cpu/amd.c +@@ -505,17 +505,23 @@ static void amd_get_topology(struct cpuinfo_x86 *c) + u32 eax, ebx, ecx, edx; + + cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); +- c->compute_unit_id = ebx & 0xFF; + c->x86_num_siblings = ((ebx >> 8) & 0x3) + 1; ++ ++ if (c->x86 < 0x17) ++ c->compute_unit_id = ebx & 0xFF; ++ else { ++ c->cpu_core_id = ebx & 0xFF; ++ c->x86_max_cores /= c->x86_num_siblings; ++ } + } + + if (opt_cpu_info) + printk("CPU %d(%d) -> Processor %d, %s %d\n", + cpu, c->x86_max_cores, c->phys_proc_id, +- cpu_has(c, X86_FEATURE_TOPOEXT) ? "Compute Unit" : +- "Core", +- cpu_has(c, X86_FEATURE_TOPOEXT) ? c->compute_unit_id : +- c->cpu_core_id); ++ c->compute_unit_id != INVALID_CUID ? "Compute Unit" ++ : "Core", ++ c->compute_unit_id != INVALID_CUID ? c->compute_unit_id ++ : c->cpu_core_id); + } + + static void early_init_amd(struct cpuinfo_x86 *c) +diff --git a/xen/arch/x86/cpu/common.c b/xen/arch/x86/cpu/common.c +index 528aff1811..fdb022875a 100644 +--- a/xen/arch/x86/cpu/common.c ++++ b/xen/arch/x86/cpu/common.c +@@ -14,6 +14,7 @@ + #include <public/sysctl.h> /* for XEN_INVALID_{SOCKET,CORE}_ID */ + + #include "cpu.h" ++#include "mcheck/x86_mca.h" + + bool_t opt_arat = 1; + boolean_param("arat", opt_arat); +@@ -355,6 +356,9 @@ static void __init early_cpu_detect(void) + hap_paddr_bits = PADDR_BITS; + } + ++ if (c->x86_vendor != X86_VENDOR_AMD) ++ park_offline_cpus = opt_mce; ++ + initialize_cpu_data(0); + } + +diff --git a/xen/arch/x86/cpu/mcheck/mce.c b/xen/arch/x86/cpu/mcheck/mce.c +index a8c287d124..32273d9208 100644 +--- a/xen/arch/x86/cpu/mcheck/mce.c ++++ b/xen/arch/x86/cpu/mcheck/mce.c +@@ -692,12 +692,15 @@ static void cpu_bank_free(unsigned int cpu) + + mcabanks_free(poll); + mcabanks_free(clr); ++ ++ per_cpu(poll_bankmask, cpu) = NULL; ++ per_cpu(mce_clear_banks, cpu) = NULL; + } + + static int cpu_bank_alloc(unsigned int cpu) + { +- struct mca_banks *poll = mcabanks_alloc(); +- struct mca_banks *clr = mcabanks_alloc(); ++ struct mca_banks *poll = per_cpu(poll_bankmask, cpu) ?: mcabanks_alloc(); ++ struct mca_banks *clr = per_cpu(mce_clear_banks, cpu) ?: mcabanks_alloc(); + + if ( !poll || !clr ) + { +@@ -725,7 +728,13 @@ static int cpu_callback( + + case CPU_UP_CANCELED: + case CPU_DEAD: +- cpu_bank_free(cpu); ++ if ( !park_offline_cpus ) ++ cpu_bank_free(cpu); ++ break; ++ ++ case CPU_REMOVE: ++ if ( park_offline_cpus ) ++ cpu_bank_free(cpu); + break; + } + +diff --git a/xen/arch/x86/cpu/mcheck/mce_intel.c b/xen/arch/x86/cpu/mcheck/mce_intel.c +index e5dd956a24..4474a34e34 100644 +--- a/xen/arch/x86/cpu/mcheck/mce_intel.c ++++ b/xen/arch/x86/cpu/mcheck/mce_intel.c +@@ -636,8 +636,6 @@ static void clear_cmci(void) + + static void cpu_mcheck_disable(void) + { +- clear_in_cr4(X86_CR4_MCE); +- + if ( cmci_support && opt_mce ) + clear_cmci(); + } +diff --git a/xen/arch/x86/cpu/vpmu_intel.c b/xen/arch/x86/cpu/vpmu_intel.c +index 207e2e712c..6e27f6ec8e 100644 +--- a/xen/arch/x86/cpu/vpmu_intel.c ++++ b/xen/arch/x86/cpu/vpmu_intel.c +@@ -454,13 +454,11 @@ static int core2_vpmu_alloc_resource(struct vcpu *v) + + if ( is_hvm_vcpu(v) ) + { +- wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0); +- if ( vmx_add_host_load_msr(MSR_CORE_PERF_GLOBAL_CTRL) ) ++ if ( vmx_add_host_load_msr(v, MSR_CORE_PERF_GLOBAL_CTRL, 0) ) + goto out_err; + +- if ( vmx_add_guest_msr(MSR_CORE_PERF_GLOBAL_CTRL) ) ++ if ( vmx_add_guest_msr(v, MSR_CORE_PERF_GLOBAL_CTRL, 0) ) + goto out_err; +- vmx_write_guest_msr(MSR_CORE_PERF_GLOBAL_CTRL, 0); + } + + core2_vpmu_cxt = xzalloc_bytes(sizeof(*core2_vpmu_cxt) + +@@ -535,27 +533,7 @@ static int core2_vpmu_do_wrmsr(unsigned int msr, uint64_t msr_content, + uint64_t *enabled_cntrs; + + if ( !core2_vpmu_msr_common_check(msr, &type, &index) ) +- { +- /* Special handling for BTS */ +- if ( msr == MSR_IA32_DEBUGCTLMSR ) +- { +- supported |= IA32_DEBUGCTLMSR_TR | IA32_DEBUGCTLMSR_BTS | +- IA32_DEBUGCTLMSR_BTINT; +- +- if ( cpu_has(¤t_cpu_data, X86_FEATURE_DSCPL) ) +- supported |= IA32_DEBUGCTLMSR_BTS_OFF_OS | +- IA32_DEBUGCTLMSR_BTS_OFF_USR; +- if ( !(msr_content & ~supported) && +- vpmu_is_set(vpmu, VPMU_CPU_HAS_BTS) ) +- return 0; +- if ( (msr_content & supported) && +- !vpmu_is_set(vpmu, VPMU_CPU_HAS_BTS) ) +- printk(XENLOG_G_WARNING +- "%pv: Debug Store unsupported on this CPU\n", +- current); +- } + return -EINVAL; +- } + + ASSERT(!supported); + +@@ -613,7 +591,7 @@ static int core2_vpmu_do_wrmsr(unsigned int msr, uint64_t msr_content, + return -EINVAL; + + if ( is_hvm_vcpu(v) ) +- vmx_read_guest_msr(MSR_CORE_PERF_GLOBAL_CTRL, ++ vmx_read_guest_msr(v, MSR_CORE_PERF_GLOBAL_CTRL, + &core2_vpmu_cxt->global_ctrl); + else + rdmsrl(MSR_CORE_PERF_GLOBAL_CTRL, core2_vpmu_cxt->global_ctrl); +@@ -682,7 +660,7 @@ static int core2_vpmu_do_wrmsr(unsigned int msr, uint64_t msr_content, + return -EINVAL; + + if ( is_hvm_vcpu(v) ) +- vmx_read_guest_msr(MSR_CORE_PERF_GLOBAL_CTRL, ++ vmx_read_guest_msr(v, MSR_CORE_PERF_GLOBAL_CTRL, + &core2_vpmu_cxt->global_ctrl); + else + rdmsrl(MSR_CORE_PERF_GLOBAL_CTRL, core2_vpmu_cxt->global_ctrl); +@@ -701,7 +679,7 @@ static int core2_vpmu_do_wrmsr(unsigned int msr, uint64_t msr_content, + else + { + if ( is_hvm_vcpu(v) ) +- vmx_write_guest_msr(MSR_CORE_PERF_GLOBAL_CTRL, msr_content); ++ vmx_write_guest_msr(v, MSR_CORE_PERF_GLOBAL_CTRL, msr_content); + else + wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, msr_content); + } +@@ -735,7 +713,7 @@ static int core2_vpmu_do_rdmsr(unsigned int msr, uint64_t *msr_content) + break; + case MSR_CORE_PERF_GLOBAL_CTRL: + if ( is_hvm_vcpu(v) ) +- vmx_read_guest_msr(MSR_CORE_PERF_GLOBAL_CTRL, msr_content); ++ vmx_read_guest_msr(v, MSR_CORE_PERF_GLOBAL_CTRL, msr_content); + else + rdmsrl(MSR_CORE_PERF_GLOBAL_CTRL, *msr_content); + break; +diff --git a/xen/arch/x86/cpuid.c b/xen/arch/x86/cpuid.c +index beee47d0ed..5cc89e2b34 100644 +--- a/xen/arch/x86/cpuid.c ++++ b/xen/arch/x86/cpuid.c +@@ -43,6 +43,11 @@ static int __init parse_xen_cpuid(const char *s) + if ( !val ) + setup_clear_cpu_cap(X86_FEATURE_STIBP); + } ++ else if ( (val = parse_boolean("l1d-flush", s, ss)) >= 0 ) ++ { ++ if ( !val ) ++ setup_clear_cpu_cap(X86_FEATURE_L1D_FLUSH); ++ } + else if ( (val = parse_boolean("ssbd", s, ss)) >= 0 ) + { + if ( !val ) +diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c +index 9850a782ec..c39cf2c6e5 100644 +--- a/xen/arch/x86/domain.c ++++ b/xen/arch/x86/domain.c +@@ -107,10 +107,11 @@ static void play_dead(void) + local_irq_disable(); + + /* +- * NOTE: After cpu_exit_clear, per-cpu variables are no longer accessible, +- * as they may be freed at any time. In this case, heap corruption or +- * #PF can occur (when heap debugging is enabled). For example, even +- * printk() can involve tasklet scheduling, which touches per-cpu vars. ++ * NOTE: After cpu_exit_clear, per-cpu variables may no longer accessible, ++ * as they may be freed at any time if offline CPUs don't get parked. In ++ * this case, heap corruption or #PF can occur (when heap debugging is ++ * enabled). For example, even printk() can involve tasklet scheduling, ++ * which touches per-cpu vars. + * + * Consider very carefully when adding code to *dead_idle. Most hypervisor + * subsystems are unsafe to call. +diff --git a/xen/arch/x86/domctl.c b/xen/arch/x86/domctl.c +index 8fbbf3aeb3..dd91038a67 100644 +--- a/xen/arch/x86/domctl.c ++++ b/xen/arch/x86/domctl.c +@@ -225,7 +225,8 @@ static int update_domain_cpuid_info(struct domain *d, + */ + call_policy_changed = (is_hvm_domain(d) && + ((old_7d0 ^ p->feat.raw[0].d) & +- cpufeat_mask(X86_FEATURE_IBRSB))); ++ (cpufeat_mask(X86_FEATURE_IBRSB) | ++ cpufeat_mask(X86_FEATURE_L1D_FLUSH)))); + break; + + case 0xa: +@@ -1163,7 +1164,7 @@ long arch_do_domctl( + if ( _xcr0_accum ) + { + if ( evc->size >= PV_XSAVE_HDR_SIZE + XSTATE_AREA_MIN_SIZE ) +- ret = validate_xstate(_xcr0, _xcr0_accum, ++ ret = validate_xstate(d, _xcr0, _xcr0_accum, + &_xsave_area->xsave_hdr); + } + else if ( !_xcr0 ) +@@ -1187,8 +1188,7 @@ long arch_do_domctl( + vcpu_pause(v); + v->arch.xcr0 = _xcr0; + v->arch.xcr0_accum = _xcr0_accum; +- if ( _xcr0_accum & XSTATE_NONLAZY ) +- v->arch.nonlazy_xstate_used = 1; ++ v->arch.nonlazy_xstate_used = _xcr0_accum & XSTATE_NONLAZY; + compress_xsave_states(v, _xsave_area, + evc->size - PV_XSAVE_HDR_SIZE); + vcpu_unpause(v); +diff --git a/xen/arch/x86/genapic/x2apic.c b/xen/arch/x86/genapic/x2apic.c +index 4779b0d0d5..d997806272 100644 +--- a/xen/arch/x86/genapic/x2apic.c ++++ b/xen/arch/x86/genapic/x2apic.c +@@ -201,18 +201,21 @@ static int update_clusterinfo( + if ( !cluster_cpus_spare ) + cluster_cpus_spare = xzalloc(cpumask_t); + if ( !cluster_cpus_spare || +- !alloc_cpumask_var(&per_cpu(scratch_mask, cpu)) ) ++ !cond_alloc_cpumask_var(&per_cpu(scratch_mask, cpu)) ) + err = -ENOMEM; + break; + case CPU_UP_CANCELED: + case CPU_DEAD: ++ case CPU_REMOVE: ++ if ( park_offline_cpus == (action != CPU_REMOVE) ) ++ break; + if ( per_cpu(cluster_cpus, cpu) ) + { + cpumask_clear_cpu(cpu, per_cpu(cluster_cpus, cpu)); + if ( cpumask_empty(per_cpu(cluster_cpus, cpu)) ) +- xfree(per_cpu(cluster_cpus, cpu)); ++ XFREE(per_cpu(cluster_cpus, cpu)); + } +- free_cpumask_var(per_cpu(scratch_mask, cpu)); ++ FREE_CPUMASK_VAR(per_cpu(scratch_mask, cpu)); + break; + } + +diff --git a/xen/arch/x86/hvm/hvm.c b/xen/arch/x86/hvm/hvm.c +index c23983cdff..4cbb688c05 100644 +--- a/xen/arch/x86/hvm/hvm.c ++++ b/xen/arch/x86/hvm/hvm.c +@@ -907,6 +907,9 @@ const char *hvm_efer_valid(const struct vcpu *v, uint64_t value, + else + p = &host_cpuid_policy; + ++ if ( value & ~EFER_KNOWN_MASK ) ++ return "Unknown bits set"; ++ + if ( (value & EFER_SCE) && !p->extd.syscall ) + return "SCE without feature"; + +@@ -1269,7 +1272,7 @@ static int hvm_load_cpu_xsave_states(struct domain *d, hvm_domain_context_t *h) + ctxt = (struct hvm_hw_cpu_xsave *)&h->data[h->cur]; + h->cur += desc->length; + +- err = validate_xstate(ctxt->xcr0, ctxt->xcr0_accum, ++ err = validate_xstate(d, ctxt->xcr0, ctxt->xcr0_accum, + (const void *)&ctxt->save_area.xsave_hdr); + if ( err ) + { +@@ -1324,8 +1327,7 @@ static int hvm_load_cpu_xsave_states(struct domain *d, hvm_domain_context_t *h) + + v->arch.xcr0 = ctxt->xcr0; + v->arch.xcr0_accum = ctxt->xcr0_accum; +- if ( ctxt->xcr0_accum & XSTATE_NONLAZY ) +- v->arch.nonlazy_xstate_used = 1; ++ v->arch.nonlazy_xstate_used = ctxt->xcr0_accum & XSTATE_NONLAZY; + compress_xsave_states(v, &ctxt->save_area, + size - offsetof(struct hvm_hw_cpu_xsave, save_area)); + +diff --git a/xen/arch/x86/hvm/svm/svm.c b/xen/arch/x86/hvm/svm/svm.c +index 165500e3f2..b964c59dad 100644 +--- a/xen/arch/x86/hvm/svm/svm.c ++++ b/xen/arch/x86/hvm/svm/svm.c +@@ -1432,24 +1432,18 @@ static void svm_inject_event(const struct x86_event *event) + * Xen must emulate enough of the event injection to be sure that a + * further fault shouldn't occur during delivery. This covers the fact + * that hardware doesn't perform DPL checking on injection. +- * +- * Also, it accounts for proper positioning of %rip for an event with trap +- * semantics (where %rip should point after the instruction) which suffers +- * a fault during injection (at which point %rip should point at the +- * instruction). + */ + if ( event->type == X86_EVENTTYPE_PRI_SW_EXCEPTION || +- (!cpu_has_svm_nrips && (event->type == X86_EVENTTYPE_SW_INTERRUPT || +- event->type == X86_EVENTTYPE_SW_EXCEPTION)) ) ++ (!cpu_has_svm_nrips && (event->type >= X86_EVENTTYPE_SW_INTERRUPT)) ) + svm_emul_swint_injection(&_event); + +- switch ( _event.vector ) ++ switch ( _event.vector | -(_event.type == X86_EVENTTYPE_SW_INTERRUPT) ) + { + case TRAP_debug: + if ( regs->eflags & X86_EFLAGS_TF ) + { + __restore_debug_registers(vmcb, curr); +- vmcb_set_dr6(vmcb, vmcb_get_dr6(vmcb) | 0x4000); ++ vmcb_set_dr6(vmcb, vmcb_get_dr6(vmcb) | DR_STEP); + } + /* fall through */ + case TRAP_int3: +@@ -1459,6 +1453,13 @@ static void svm_inject_event(const struct x86_event *event) + domain_pause_for_debugger(); + return; + } ++ break; ++ ++ case TRAP_page_fault: ++ ASSERT(_event.type == X86_EVENTTYPE_HW_EXCEPTION); ++ curr->arch.hvm_vcpu.guest_cr[2] = _event.cr2; ++ vmcb_set_cr2(vmcb, _event.cr2); ++ break; + } + + if ( unlikely(eventinj.fields.v) && +@@ -1481,13 +1482,9 @@ static void svm_inject_event(const struct x86_event *event) + * icebp, software events with trap semantics need emulating, so %rip in + * the trap frame points after the instruction. + * +- * The x86 emulator (if requested by the x86_swint_emulate_* choice) will +- * have performed checks such as presence/dpl/etc and believes that the +- * event injection will succeed without faulting. +- * +- * The x86 emulator will always provide fault semantics for software +- * events, with _trap.insn_len set appropriately. If the injection +- * requires emulation, move %rip forwards at this point. ++ * svm_emul_swint_injection() has already confirmed that events with trap ++ * semantics won't fault on injection. Position %rip/NextRIP suitably, ++ * and restrict the event type to what hardware will tolerate. + */ + switch ( _event.type ) + { +@@ -1544,16 +1541,12 @@ static void svm_inject_event(const struct x86_event *event) + eventinj.fields.errorcode == (uint16_t)eventinj.fields.errorcode); + vmcb->eventinj = eventinj; + +- if ( _event.vector == TRAP_page_fault ) +- { +- curr->arch.hvm_vcpu.guest_cr[2] = _event.cr2; +- vmcb_set_cr2(vmcb, _event.cr2); +- HVMTRACE_LONG_2D(PF_INJECT, _event.error_code, TRC_PAR_LONG(_event.cr2)); +- } ++ if ( _event.vector == TRAP_page_fault && ++ _event.type == X86_EVENTTYPE_HW_EXCEPTION ) ++ HVMTRACE_LONG_2D(PF_INJECT, _event.error_code, ++ TRC_PAR_LONG(_event.cr2)); + else +- { + HVMTRACE_2D(INJ_EXC, _event.vector, _event.error_code); +- } + } + + static int svm_event_pending(struct vcpu *v) +diff --git a/xen/arch/x86/hvm/vmx/entry.S b/xen/arch/x86/hvm/vmx/entry.S +index aa2f103895..afd552f2b9 100644 +--- a/xen/arch/x86/hvm/vmx/entry.S ++++ b/xen/arch/x86/hvm/vmx/entry.S +@@ -41,6 +41,15 @@ ENTRY(vmx_asm_vmexit_handler) + SPEC_CTRL_ENTRY_FROM_HVM /* Req: b=curr %rsp=regs/cpuinfo, Clob: acd */ + /* WARNING! `ret`, `call *`, `jmp *` not safe before this point. */ + ++ /* Hardware clears MSR_DEBUGCTL on VMExit. Reinstate it if debugging Xen. */ ++ .macro restore_lbr ++ mov $IA32_DEBUGCTLMSR_LBR, %eax ++ mov $MSR_IA32_DEBUGCTLMSR, %ecx ++ xor %edx, %edx ++ wrmsr ++ .endm ++ ALTERNATIVE "", restore_lbr, X86_FEATURE_XEN_LBR ++ + mov %rsp,%rdi + call vmx_vmexit_handler + +diff --git a/xen/arch/x86/hvm/vmx/vmcs.c b/xen/arch/x86/hvm/vmx/vmcs.c +index 258fc08f72..2ba0c40808 100644 +--- a/xen/arch/x86/hvm/vmx/vmcs.c ++++ b/xen/arch/x86/hvm/vmx/vmcs.c +@@ -38,6 +38,7 @@ + #include <asm/flushtlb.h> + #include <asm/monitor.h> + #include <asm/shadow.h> ++#include <asm/spec_ctrl.h> + #include <asm/tboot.h> + #include <asm/apic.h> + +@@ -996,6 +997,7 @@ static int construct_vmcs(struct vcpu *v) + struct domain *d = v->domain; + u32 vmexit_ctl = vmx_vmexit_control; + u32 vmentry_ctl = vmx_vmentry_control; ++ int rc = 0; + + vmx_vmcs_enter(v); + +@@ -1083,8 +1085,8 @@ static int construct_vmcs(struct vcpu *v) + + if ( msr_bitmap == NULL ) + { +- vmx_vmcs_exit(v); +- return -ENOMEM; ++ rc = -ENOMEM; ++ goto out; + } + + memset(msr_bitmap, ~0, PAGE_SIZE); +@@ -1268,141 +1270,197 @@ static int construct_vmcs(struct vcpu *v) + if ( cpu_has_vmx_tsc_scaling ) + __vmwrite(TSC_MULTIPLIER, d->arch.hvm_domain.tsc_scaling_ratio); + +- vmx_vmcs_exit(v); +- + /* will update HOST & GUEST_CR3 as reqd */ + paging_update_paging_modes(v); + + vmx_vlapic_msr_changed(v); + +- return 0; ++ if ( opt_l1d_flush && paging_mode_hap(d) ) ++ rc = vmx_add_msr(v, MSR_FLUSH_CMD, FLUSH_CMD_L1D, ++ VMX_MSR_GUEST_LOADONLY); ++ ++ out: ++ vmx_vmcs_exit(v); ++ ++ return rc; + } + +-static int vmx_msr_entry_key_cmp(const void *key, const void *elt) ++/* ++ * Search an MSR list looking for an MSR entry, or the slot in which it should ++ * live (to keep the data sorted) if an entry is not found. ++ * ++ * The return pointer is guaranteed to be bounded by start and end. However, ++ * it may point at end, and may be invalid for the caller to dereference. ++ */ ++static struct vmx_msr_entry *locate_msr_entry( ++ struct vmx_msr_entry *start, struct vmx_msr_entry *end, uint32_t msr) + { +- const u32 *msr = key; +- const struct vmx_msr_entry *entry = elt; ++ while ( start < end ) ++ { ++ struct vmx_msr_entry *mid = start + (end - start) / 2; + +- if ( *msr > entry->index ) +- return 1; +- if ( *msr < entry->index ) +- return -1; ++ if ( msr < mid->index ) ++ end = mid; ++ else if ( msr > mid->index ) ++ start = mid + 1; ++ else ++ return mid; ++ } + +- return 0; ++ return start; + } + +-struct vmx_msr_entry *vmx_find_msr(u32 msr, int type) ++struct vmx_msr_entry *vmx_find_msr(const struct vcpu *v, uint32_t msr, ++ enum vmx_msr_list_type type) + { +- struct vcpu *curr = current; +- unsigned int msr_count; +- struct vmx_msr_entry *msr_area; ++ const struct arch_vmx_struct *vmx = &v->arch.hvm_vmx; ++ struct vmx_msr_entry *start = NULL, *ent, *end; ++ unsigned int substart = 0, subend = vmx->msr_save_count; ++ unsigned int total = vmx->msr_load_count; + +- if ( type == VMX_GUEST_MSR ) +- { +- msr_count = curr->arch.hvm_vmx.msr_count; +- msr_area = curr->arch.hvm_vmx.msr_area; +- } +- else ++ ASSERT(v == current || !vcpu_runnable(v)); ++ ++ switch ( type ) + { +- ASSERT(type == VMX_HOST_MSR); +- msr_count = curr->arch.hvm_vmx.host_msr_count; +- msr_area = curr->arch.hvm_vmx.host_msr_area; ++ case VMX_MSR_HOST: ++ start = vmx->host_msr_area; ++ subend = vmx->host_msr_count; ++ total = subend; ++ break; ++ ++ case VMX_MSR_GUEST: ++ start = vmx->msr_area; ++ break; ++ ++ case VMX_MSR_GUEST_LOADONLY: ++ start = vmx->msr_area; ++ substart = subend; ++ subend = total; ++ break; ++ ++ default: ++ ASSERT_UNREACHABLE(); + } + +- if ( msr_area == NULL ) ++ if ( !start ) + return NULL; + +- return bsearch(&msr, msr_area, msr_count, sizeof(struct vmx_msr_entry), +- vmx_msr_entry_key_cmp); ++ end = start + total; ++ ent = locate_msr_entry(start + substart, start + subend, msr); ++ ++ return ((ent < end) && (ent->index == msr)) ? ent : NULL; + } + +-int vmx_read_guest_msr(u32 msr, u64 *val) ++int vmx_add_msr(struct vcpu *v, uint32_t msr, uint64_t val, ++ enum vmx_msr_list_type type) + { +- struct vmx_msr_entry *ent; ++ struct arch_vmx_struct *vmx = &v->arch.hvm_vmx; ++ struct vmx_msr_entry **ptr, *start = NULL, *ent, *end; ++ unsigned int substart, subend, total; ++ int rc; + +- if ( (ent = vmx_find_msr(msr, VMX_GUEST_MSR)) != NULL ) ++ ASSERT(v == current || !vcpu_runnable(v)); ++ ++ switch ( type ) + { +- *val = ent->data; +- return 0; +- } ++ case VMX_MSR_HOST: ++ ptr = &vmx->host_msr_area; ++ substart = 0; ++ subend = vmx->host_msr_count; ++ total = subend; ++ break; + +- return -ESRCH; +-} ++ case VMX_MSR_GUEST: ++ ptr = &vmx->msr_area; ++ substart = 0; ++ subend = vmx->msr_save_count; ++ total = vmx->msr_load_count; ++ break; + +-int vmx_write_guest_msr(u32 msr, u64 val) +-{ +- struct vmx_msr_entry *ent; ++ case VMX_MSR_GUEST_LOADONLY: ++ ptr = &vmx->msr_area; ++ substart = vmx->msr_save_count; ++ subend = vmx->msr_load_count; ++ total = subend; ++ break; + +- if ( (ent = vmx_find_msr(msr, VMX_GUEST_MSR)) != NULL ) +- { +- ent->data = val; +- return 0; ++ default: ++ ASSERT_UNREACHABLE(); ++ return -EINVAL; + } + +- return -ESRCH; +-} +- +-int vmx_add_msr(u32 msr, int type) +-{ +- struct vcpu *curr = current; +- unsigned int idx, *msr_count; +- struct vmx_msr_entry **msr_area, *msr_area_elem; ++ vmx_vmcs_enter(v); + +- if ( type == VMX_GUEST_MSR ) +- { +- msr_count = &curr->arch.hvm_vmx.msr_count; +- msr_area = &curr->arch.hvm_vmx.msr_area; +- } +- else ++ /* Allocate memory on first use. */ ++ if ( unlikely(!*ptr) ) + { +- ASSERT(type == VMX_HOST_MSR); +- msr_count = &curr->arch.hvm_vmx.host_msr_count; +- msr_area = &curr->arch.hvm_vmx.host_msr_area; +- } ++ paddr_t addr; + +- if ( *msr_area == NULL ) +- { +- if ( (*msr_area = alloc_xenheap_page()) == NULL ) +- return -ENOMEM; ++ if ( (*ptr = alloc_xenheap_page()) == NULL ) ++ { ++ rc = -ENOMEM; ++ goto out; ++ } + +- if ( type == VMX_GUEST_MSR ) ++ addr = virt_to_maddr(*ptr); ++ ++ switch ( type ) + { +- __vmwrite(VM_EXIT_MSR_STORE_ADDR, virt_to_maddr(*msr_area)); +- __vmwrite(VM_ENTRY_MSR_LOAD_ADDR, virt_to_maddr(*msr_area)); ++ case VMX_MSR_HOST: ++ __vmwrite(VM_EXIT_MSR_LOAD_ADDR, addr); ++ break; ++ ++ case VMX_MSR_GUEST: ++ case VMX_MSR_GUEST_LOADONLY: ++ __vmwrite(VM_EXIT_MSR_STORE_ADDR, addr); ++ __vmwrite(VM_ENTRY_MSR_LOAD_ADDR, addr); ++ break; + } +- else +- __vmwrite(VM_EXIT_MSR_LOAD_ADDR, virt_to_maddr(*msr_area)); + } + +- for ( idx = 0; idx < *msr_count && (*msr_area)[idx].index <= msr; idx++ ) +- if ( (*msr_area)[idx].index == msr ) +- return 0; ++ start = *ptr; ++ end = start + total; ++ ent = locate_msr_entry(start + substart, start + subend, msr); + +- if ( *msr_count == (PAGE_SIZE / sizeof(struct vmx_msr_entry)) ) +- return -ENOSPC; ++ if ( (ent < end) && (ent->index == msr) ) ++ goto found; + +- memmove(*msr_area + idx + 1, *msr_area + idx, +- sizeof(*msr_area_elem) * (*msr_count - idx)); ++ /* If there isn't an existing entry for msr, insert room for one. */ ++ if ( total == (PAGE_SIZE / sizeof(*ent)) ) ++ { ++ rc = -ENOSPC; ++ goto out; ++ } + +- msr_area_elem = *msr_area + idx; +- msr_area_elem->index = msr; +- msr_area_elem->mbz = 0; ++ memmove(ent + 1, ent, sizeof(*ent) * (end - ent)); + +- ++*msr_count; ++ ent->index = msr; ++ ent->mbz = 0; + +- if ( type == VMX_GUEST_MSR ) ++ switch ( type ) + { +- msr_area_elem->data = 0; +- __vmwrite(VM_EXIT_MSR_STORE_COUNT, *msr_count); +- __vmwrite(VM_ENTRY_MSR_LOAD_COUNT, *msr_count); +- } +- else +- { +- rdmsrl(msr, msr_area_elem->data); +- __vmwrite(VM_EXIT_MSR_LOAD_COUNT, *msr_count); ++ case VMX_MSR_HOST: ++ __vmwrite(VM_EXIT_MSR_LOAD_COUNT, ++vmx->host_msr_count); ++ break; ++ ++ case VMX_MSR_GUEST: ++ __vmwrite(VM_EXIT_MSR_STORE_COUNT, ++vmx->msr_save_count); ++ ++ /* Fallthrough */ ++ case VMX_MSR_GUEST_LOADONLY: ++ __vmwrite(VM_ENTRY_MSR_LOAD_COUNT, ++vmx->msr_load_count); ++ break; + } + +- return 0; ++ /* Set the msr's value. */ ++ found: ++ ent->data = val; ++ rc = 0; ++ ++ out: ++ vmx_vmcs_exit(v); ++ ++ return rc; + } + + void vmx_set_eoi_exit_bitmap(struct vcpu *v, u8 vector) +diff --git a/xen/arch/x86/hvm/vmx/vmx.c b/xen/arch/x86/hvm/vmx/vmx.c +index 610c8d6eb9..b0fababede 100644 +--- a/xen/arch/x86/hvm/vmx/vmx.c ++++ b/xen/arch/x86/hvm/vmx/vmx.c +@@ -583,6 +583,12 @@ static void vmx_cpuid_policy_changed(struct vcpu *v) + vmx_clear_msr_intercept(v, MSR_PRED_CMD, VMX_MSR_RW); + else + vmx_set_msr_intercept(v, MSR_PRED_CMD, VMX_MSR_RW); ++ ++ /* MSR_FLUSH_CMD is safe to pass through if the guest knows about it. */ ++ if ( cp->feat.l1d_flush ) ++ vmx_clear_msr_intercept(v, MSR_FLUSH_CMD, VMX_MSR_RW); ++ else ++ vmx_set_msr_intercept(v, MSR_FLUSH_CMD, VMX_MSR_RW); + } + + int vmx_guest_x86_mode(struct vcpu *v) +@@ -2758,8 +2764,10 @@ enum + + #define LBR_FROM_SIGNEXT_2MSB ((1ULL << 59) | (1ULL << 60)) + +-#define FIXUP_LBR_TSX (1u << 0) +-#define FIXUP_BDW_ERRATUM_BDF14 (1u << 1) ++#define LBR_MSRS_INSERTED (1u << 0) ++#define LBR_FIXUP_TSX (1u << 1) ++#define LBR_FIXUP_BDF14 (1u << 2) ++#define LBR_FIXUP_MASK (LBR_FIXUP_TSX | LBR_FIXUP_BDF14) + + static bool __read_mostly lbr_tsx_fixup_needed; + static bool __read_mostly bdw_erratum_bdf14_fixup_needed; +@@ -2822,7 +2830,7 @@ static int is_last_branch_msr(u32 ecx) + + static int vmx_msr_read_intercept(unsigned int msr, uint64_t *msr_content) + { +- const struct vcpu *curr = current; ++ struct vcpu *curr = current; + + HVM_DBG_LOG(DBG_LEVEL_MSR, "ecx=%#x", msr); + +@@ -2901,7 +2909,7 @@ static int vmx_msr_read_intercept(unsigned int msr, uint64_t *msr_content) + if ( passive_domain_do_rdmsr(msr, msr_content) ) + goto done; + +- if ( vmx_read_guest_msr(msr, msr_content) == 0 ) ++ if ( vmx_read_guest_msr(curr, msr, msr_content) == 0 ) + break; + + if ( is_last_branch_msr(msr) ) +@@ -3036,11 +3044,14 @@ void vmx_vlapic_msr_changed(struct vcpu *v) + static int vmx_msr_write_intercept(unsigned int msr, uint64_t msr_content) + { + struct vcpu *v = current; ++ const struct cpuid_policy *cp = v->domain->arch.cpuid; + + HVM_DBG_LOG(DBG_LEVEL_MSR, "ecx=%#x, msr_value=%#"PRIx64, msr, msr_content); + + switch ( msr ) + { ++ uint64_t rsvd; ++ + case MSR_IA32_SYSENTER_CS: + __vmwrite(GUEST_SYSENTER_CS, msr_content); + break; +@@ -3093,45 +3104,85 @@ static int vmx_msr_write_intercept(unsigned int msr, uint64_t msr_content) + wrmsrl(MSR_SYSCALL_MASK, msr_content); + break; + +- case MSR_IA32_DEBUGCTLMSR: { +- int i, rc = 0; +- uint64_t supported = IA32_DEBUGCTLMSR_LBR | IA32_DEBUGCTLMSR_BTF; ++ case MSR_IA32_DEBUGCTLMSR: ++ rsvd = ~(IA32_DEBUGCTLMSR_LBR | IA32_DEBUGCTLMSR_BTF); + +- if ( boot_cpu_has(X86_FEATURE_RTM) ) +- supported |= IA32_DEBUGCTLMSR_RTM; +- if ( msr_content & ~supported ) ++ /* TODO: Wire vPMU settings properly through the CPUID policy */ ++ if ( vpmu_is_set(vcpu_vpmu(v), VPMU_CPU_HAS_BTS) ) + { +- /* Perhaps some other bits are supported in vpmu. */ +- if ( vpmu_do_wrmsr(msr, msr_content, supported) ) +- break; ++ rsvd &= ~(IA32_DEBUGCTLMSR_TR | IA32_DEBUGCTLMSR_BTS | ++ IA32_DEBUGCTLMSR_BTINT); ++ ++ if ( cpu_has(¤t_cpu_data, X86_FEATURE_DSCPL) ) ++ rsvd &= ~(IA32_DEBUGCTLMSR_BTS_OFF_OS | ++ IA32_DEBUGCTLMSR_BTS_OFF_USR); + } +- if ( msr_content & IA32_DEBUGCTLMSR_LBR ) ++ ++ if ( cp->feat.rtm ) ++ rsvd &= ~IA32_DEBUGCTLMSR_RTM; ++ ++ if ( msr_content & rsvd ) ++ goto gp_fault; ++ ++ /* ++ * When a guest first enables LBR, arrange to save and restore the LBR ++ * MSRs and allow the guest direct access. ++ * ++ * MSR_DEBUGCTL and LBR has existed almost as long as MSRs have ++ * existed, and there is no architectural way to hide the feature, or ++ * fail the attempt to enable LBR. ++ * ++ * Unknown host LBR MSRs or hitting -ENOSPC with the guest load/save ++ * list are definitely hypervisor bugs, whereas -ENOMEM for allocating ++ * the load/save list is simply unlucky (and shouldn't occur with ++ * sensible management by the toolstack). ++ * ++ * Either way, there is nothing we can do right now to recover, and ++ * the guest won't execute correctly either. Simply crash the domain ++ * to make the failure obvious. ++ */ ++ if ( !(v->arch.hvm_vmx.lbr_flags & LBR_MSRS_INSERTED) && ++ (msr_content & IA32_DEBUGCTLMSR_LBR) ) + { + const struct lbr_info *lbr = last_branch_msr_get(); +- if ( lbr == NULL ) +- break; + +- for ( ; (rc == 0) && lbr->count; lbr++ ) +- for ( i = 0; (rc == 0) && (i < lbr->count); i++ ) +- if ( (rc = vmx_add_guest_msr(lbr->base + i)) == 0 ) ++ if ( unlikely(!lbr) ) ++ { ++ gprintk(XENLOG_ERR, "Unknown Host LBR MSRs\n"); ++ domain_crash(v->domain); ++ return X86EMUL_OKAY; ++ } ++ ++ for ( ; lbr->count; lbr++ ) ++ { ++ unsigned int i; ++ ++ for ( i = 0; i < lbr->count; i++ ) ++ { ++ int rc = vmx_add_guest_msr(v, lbr->base + i, 0); ++ ++ if ( unlikely(rc) ) + { +- vmx_clear_msr_intercept(v, lbr->base + i, VMX_MSR_RW); +- if ( lbr_tsx_fixup_needed ) +- v->arch.hvm_vmx.lbr_fixup_enabled |= FIXUP_LBR_TSX; +- if ( bdw_erratum_bdf14_fixup_needed ) +- v->arch.hvm_vmx.lbr_fixup_enabled |= +- FIXUP_BDW_ERRATUM_BDF14; ++ gprintk(XENLOG_ERR, ++ "Guest load/save list error %d\n", rc); ++ domain_crash(v->domain); ++ return X86EMUL_OKAY; + } +- } + +- if ( (rc < 0) || +- (msr_content && (vmx_add_host_load_msr(msr) < 0)) ) +- hvm_inject_hw_exception(TRAP_machine_check, X86_EVENT_NO_EC); +- else +- __vmwrite(GUEST_IA32_DEBUGCTL, msr_content); ++ vmx_clear_msr_intercept(v, lbr->base + i, VMX_MSR_RW); ++ } ++ } ++ ++ v->arch.hvm_vmx.lbr_flags |= LBR_MSRS_INSERTED; ++ if ( lbr_tsx_fixup_needed ) ++ v->arch.hvm_vmx.lbr_flags |= LBR_FIXUP_TSX; ++ if ( bdw_erratum_bdf14_fixup_needed ) ++ v->arch.hvm_vmx.lbr_flags |= LBR_FIXUP_BDF14; ++ } + ++ __vmwrite(GUEST_IA32_DEBUGCTL, msr_content); + break; +- } ++ + case MSR_IA32_FEATURE_CONTROL: + case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: + /* None of these MSRs are writeable. */ +@@ -3154,7 +3205,7 @@ static int vmx_msr_write_intercept(unsigned int msr, uint64_t msr_content) + if ( wrmsr_viridian_regs(msr, msr_content) ) + break; + +- if ( vmx_write_guest_msr(msr, msr_content) == 0 || ++ if ( vmx_write_guest_msr(v, msr, msr_content) == 0 || + is_last_branch_msr(msr) ) + break; + +@@ -3701,6 +3752,7 @@ void vmx_vmexit_handler(struct cpu_user_regs *regs) + */ + __vmread(EXIT_QUALIFICATION, &exit_qualification); + HVMTRACE_1D(TRAP_DEBUG, exit_qualification); ++ __restore_debug_registers(v); + write_debugreg(6, exit_qualification | DR_STATUS_RESERVED_ONE); + if ( !v->domain->debugger_attached ) + { +@@ -4165,11 +4217,11 @@ out: + static void lbr_tsx_fixup(void) + { + struct vcpu *curr = current; +- unsigned int msr_count = curr->arch.hvm_vmx.msr_count; ++ unsigned int msr_count = curr->arch.hvm_vmx.msr_save_count; + struct vmx_msr_entry *msr_area = curr->arch.hvm_vmx.msr_area; + struct vmx_msr_entry *msr; + +- if ( (msr = vmx_find_msr(lbr_from_start, VMX_GUEST_MSR)) != NULL ) ++ if ( (msr = vmx_find_msr(curr, lbr_from_start, VMX_MSR_GUEST)) != NULL ) + { + /* + * Sign extend into bits 61:62 while preserving bit 63 +@@ -4179,15 +4231,15 @@ static void lbr_tsx_fixup(void) + msr->data |= ((LBR_FROM_SIGNEXT_2MSB & msr->data) << 2); + } + +- if ( (msr = vmx_find_msr(lbr_lastint_from, VMX_GUEST_MSR)) != NULL ) ++ if ( (msr = vmx_find_msr(curr, lbr_lastint_from, VMX_MSR_GUEST)) != NULL ) + msr->data |= ((LBR_FROM_SIGNEXT_2MSB & msr->data) << 2); + } + +-static void sign_extend_msr(u32 msr, int type) ++static void sign_extend_msr(struct vcpu *v, u32 msr, int type) + { + struct vmx_msr_entry *entry; + +- if ( (entry = vmx_find_msr(msr, type)) != NULL ) ++ if ( (entry = vmx_find_msr(v, msr, type)) != NULL ) + { + if ( entry->data & VADDR_TOP_BIT ) + entry->data |= CANONICAL_MASK; +@@ -4198,6 +4250,8 @@ static void sign_extend_msr(u32 msr, int type) + + static void bdw_erratum_bdf14_fixup(void) + { ++ struct vcpu *curr = current; ++ + /* + * Occasionally, on certain Broadwell CPUs MSR_IA32_LASTINTTOIP has + * been observed to have the top three bits corrupted as though the +@@ -4207,17 +4261,17 @@ static void bdw_erratum_bdf14_fixup(void) + * erratum BDF14. Fix up MSR_IA32_LASTINT{FROM,TO}IP by + * sign-extending into bits 48:63. + */ +- sign_extend_msr(MSR_IA32_LASTINTFROMIP, VMX_GUEST_MSR); +- sign_extend_msr(MSR_IA32_LASTINTTOIP, VMX_GUEST_MSR); ++ sign_extend_msr(curr, MSR_IA32_LASTINTFROMIP, VMX_MSR_GUEST); ++ sign_extend_msr(curr, MSR_IA32_LASTINTTOIP, VMX_MSR_GUEST); + } + + static void lbr_fixup(void) + { + struct vcpu *curr = current; + +- if ( curr->arch.hvm_vmx.lbr_fixup_enabled & FIXUP_LBR_TSX ) ++ if ( curr->arch.hvm_vmx.lbr_flags & LBR_FIXUP_TSX ) + lbr_tsx_fixup(); +- if ( curr->arch.hvm_vmx.lbr_fixup_enabled & FIXUP_BDW_ERRATUM_BDF14 ) ++ if ( curr->arch.hvm_vmx.lbr_flags & LBR_FIXUP_BDF14 ) + bdw_erratum_bdf14_fixup(); + } + +@@ -4285,7 +4339,7 @@ bool vmx_vmenter_helper(const struct cpu_user_regs *regs) + } + + out: +- if ( unlikely(curr->arch.hvm_vmx.lbr_fixup_enabled) ) ++ if ( unlikely(curr->arch.hvm_vmx.lbr_flags & LBR_FIXUP_MASK) ) + lbr_fixup(); + + HVMTRACE_ND(VMENTRY, 0, 1/*cycles*/, 0, 0, 0, 0, 0, 0, 0); +diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c +index bcf46c0743..7d4871b791 100644 +--- a/xen/arch/x86/mm.c ++++ b/xen/arch/x86/mm.c +@@ -613,6 +613,9 @@ static int alloc_segdesc_page(struct page_info *page) + return i == 512 ? 0 : -EINVAL; + } + ++static int _get_page_type(struct page_info *page, unsigned long type, ++ bool preemptible); ++ + static int get_page_and_type_from_mfn( + mfn_t mfn, unsigned long type, struct domain *d, + int partial, int preemptible) +@@ -624,9 +627,7 @@ static int get_page_and_type_from_mfn( + unlikely(!get_page_from_mfn(mfn, d)) ) + return -EINVAL; + +- rc = (preemptible ? +- get_page_type_preemptible(page, type) : +- (get_page_type(page, type) ? 0 : -EINVAL)); ++ rc = _get_page_type(page, type, preemptible); + + if ( unlikely(rc) && partial >= 0 && + (!preemptible || page != current->arch.old_guest_table) ) +@@ -1115,7 +1116,7 @@ get_page_from_l2e( + int rc; + + if ( !(l2e_get_flags(l2e) & _PAGE_PRESENT) ) +- return 1; ++ return pv_l1tf_check_l2e(d, l2e) ? -ERESTART : 1; + + if ( unlikely((l2e_get_flags(l2e) & L2_DISALLOW_MASK)) ) + { +@@ -1146,7 +1147,7 @@ get_page_from_l3e( + int rc; + + if ( !(l3e_get_flags(l3e) & _PAGE_PRESENT) ) +- return 1; ++ return pv_l1tf_check_l3e(d, l3e) ? -ERESTART : 1; + + if ( unlikely((l3e_get_flags(l3e) & l3_disallow_mask(d))) ) + { +@@ -1179,7 +1180,7 @@ get_page_from_l4e( + int rc; + + if ( !(l4e_get_flags(l4e) & _PAGE_PRESENT) ) +- return 1; ++ return pv_l1tf_check_l4e(d, l4e) ? -ERESTART : 1; + + if ( unlikely((l4e_get_flags(l4e) & L4_DISALLOW_MASK)) ) + { +@@ -1389,6 +1390,13 @@ static int alloc_l1_table(struct page_info *page) + + for ( i = 0; i < L1_PAGETABLE_ENTRIES; i++ ) + { ++ if ( !(l1e_get_flags(pl1e[i]) & _PAGE_PRESENT) ) ++ { ++ ret = pv_l1tf_check_l1e(d, pl1e[i]) ? -ERESTART : 0; ++ if ( ret ) ++ goto out; ++ } ++ + switch ( ret = get_page_from_l1e(pl1e[i], d, d) ) + { + default: +@@ -1409,6 +1417,7 @@ static int alloc_l1_table(struct page_info *page) + + fail: + gdprintk(XENLOG_WARNING, "Failure in alloc_l1_table: slot %#x\n", i); ++ out: + while ( i-- > 0 ) + put_page_from_l1e(pl1e[i], d); + +@@ -1456,8 +1465,7 @@ static int create_pae_xen_mappings(struct domain *d, l3_pgentry_t *pl3e) + return 1; + } + +-static int alloc_l2_table(struct page_info *page, unsigned long type, +- int preemptible) ++static int alloc_l2_table(struct page_info *page, unsigned long type) + { + struct domain *d = page_get_owner(page); + unsigned long pfn = mfn_x(page_to_mfn(page)); +@@ -1469,8 +1477,7 @@ static int alloc_l2_table(struct page_info *page, unsigned long type, + + for ( i = page->nr_validated_ptes; i < L2_PAGETABLE_ENTRIES; i++ ) + { +- if ( preemptible && i > page->nr_validated_ptes +- && hypercall_preempt_check() ) ++ if ( i > page->nr_validated_ptes && hypercall_preempt_check() ) + { + page->nr_validated_ptes = i; + rc = -ERESTART; +@@ -1481,6 +1488,12 @@ static int alloc_l2_table(struct page_info *page, unsigned long type, + (rc = get_page_from_l2e(pl2e[i], pfn, d)) > 0 ) + continue; + ++ if ( unlikely(rc == -ERESTART) ) ++ { ++ page->nr_validated_ptes = i; ++ break; ++ } ++ + if ( rc < 0 ) + { + gdprintk(XENLOG_WARNING, "Failure in alloc_l2_table: slot %#x\n", i); +@@ -1763,7 +1776,7 @@ static void free_l1_table(struct page_info *page) + } + + +-static int free_l2_table(struct page_info *page, int preemptible) ++static int free_l2_table(struct page_info *page) + { + struct domain *d = page_get_owner(page); + unsigned long pfn = mfn_x(page_to_mfn(page)); +@@ -1777,7 +1790,7 @@ static int free_l2_table(struct page_info *page, int preemptible) + do { + if ( is_guest_l2_slot(d, page->u.inuse.type_info, i) && + put_page_from_l2e(pl2e[i], pfn) == 0 && +- preemptible && i && hypercall_preempt_check() ) ++ i && hypercall_preempt_check() ) + { + page->nr_validated_ptes = i; + err = -ERESTART; +@@ -2055,6 +2068,8 @@ static int mod_l1_entry(l1_pgentry_t *pl1e, l1_pgentry_t nl1e, + rc = -EBUSY; + } + } ++ else if ( pv_l1tf_check_l1e(pt_dom, nl1e) ) ++ return -ERESTART; + else if ( unlikely(!UPDATE_ENTRY(l1, pl1e, ol1e, nl1e, gl1mfn, pt_vcpu, + preserve_ad)) ) + { +@@ -2118,6 +2133,8 @@ static int mod_l2_entry(l2_pgentry_t *pl2e, + rc = -EBUSY; + } + } ++ else if ( pv_l1tf_check_l2e(d, nl2e) ) ++ return -ERESTART; + else if ( unlikely(!UPDATE_ENTRY(l2, pl2e, ol2e, nl2e, pfn, vcpu, + preserve_ad)) ) + { +@@ -2179,6 +2196,8 @@ static int mod_l3_entry(l3_pgentry_t *pl3e, + rc = -EFAULT; + } + } ++ else if ( pv_l1tf_check_l3e(d, nl3e) ) ++ return -ERESTART; + else if ( unlikely(!UPDATE_ENTRY(l3, pl3e, ol3e, nl3e, pfn, vcpu, + preserve_ad)) ) + { +@@ -2244,6 +2263,8 @@ static int mod_l4_entry(l4_pgentry_t *pl4e, + rc = -EFAULT; + } + } ++ else if ( pv_l1tf_check_l4e(d, nl4e) ) ++ return -ERESTART; + else if ( unlikely(!UPDATE_ENTRY(l4, pl4e, ol4e, nl4e, pfn, vcpu, + preserve_ad)) ) + { +@@ -2373,7 +2394,8 @@ static int alloc_page_type(struct page_info *page, unsigned long type, + rc = alloc_l1_table(page); + break; + case PGT_l2_page_table: +- rc = alloc_l2_table(page, type, preemptible); ++ ASSERT(preemptible); ++ rc = alloc_l2_table(page, type); + break; + case PGT_l3_page_table: + ASSERT(preemptible); +@@ -2463,7 +2485,8 @@ int free_page_type(struct page_info *page, unsigned long type, + rc = 0; + break; + case PGT_l2_page_table: +- rc = free_l2_table(page, preemptible); ++ ASSERT(preemptible); ++ rc = free_l2_table(page); + break; + case PGT_l3_page_table: + ASSERT(preemptible); +@@ -3550,12 +3573,9 @@ long do_mmuext_op( + } + + if ( rc == -ERESTART ) +- { +- ASSERT(i < count); + rc = hypercall_create_continuation( + __HYPERVISOR_mmuext_op, "hihi", + uops, (count - i) | MMU_UPDATE_PREEMPTED, pdone, foreigndom); +- } + else if ( curr->arch.old_guest_table ) + { + XEN_GUEST_HANDLE_PARAM(void) null; +@@ -3861,12 +3881,9 @@ long do_mmu_update( + } + + if ( rc == -ERESTART ) +- { +- ASSERT(i < count); + rc = hypercall_create_continuation( + __HYPERVISOR_mmu_update, "hihi", + ureqs, (count - i) | MMU_UPDATE_PREEMPTED, pdone, foreigndom); +- } + else if ( curr->arch.old_guest_table ) + { + XEN_GUEST_HANDLE_PARAM(void) null; +@@ -4121,7 +4138,13 @@ static int __do_update_va_mapping( + long do_update_va_mapping(unsigned long va, u64 val64, + unsigned long flags) + { +- return __do_update_va_mapping(va, val64, flags, current->domain); ++ int rc = __do_update_va_mapping(va, val64, flags, current->domain); ++ ++ if ( rc == -ERESTART ) ++ rc = hypercall_create_continuation( ++ __HYPERVISOR_update_va_mapping, "lll", va, val64, flags); ++ ++ return rc; + } + + long do_update_va_mapping_otherdomain(unsigned long va, u64 val64, +@@ -4138,6 +4161,46 @@ long do_update_va_mapping_otherdomain(unsigned long va, u64 val64, + + put_pg_owner(pg_owner); + ++ if ( rc == -ERESTART ) ++ rc = hypercall_create_continuation( ++ __HYPERVISOR_update_va_mapping_otherdomain, ++ "llli", va, val64, flags, domid); ++ ++ return rc; ++} ++ ++int compat_update_va_mapping(unsigned int va, uint32_t lo, uint32_t hi, ++ unsigned int flags) ++{ ++ int rc = __do_update_va_mapping(va, ((uint64_t)hi << 32) | lo, ++ flags, current->domain); ++ ++ if ( rc == -ERESTART ) ++ rc = hypercall_create_continuation( ++ __HYPERVISOR_update_va_mapping, "iiii", va, lo, hi, flags); ++ ++ return rc; ++} ++ ++int compat_update_va_mapping_otherdomain(unsigned int va, ++ uint32_t lo, uint32_t hi, ++ unsigned int flags, domid_t domid) ++{ ++ struct domain *pg_owner; ++ int rc; ++ ++ if ( (pg_owner = get_pg_owner(domid)) == NULL ) ++ return -ESRCH; ++ ++ rc = __do_update_va_mapping(va, ((uint64_t)hi << 32) | lo, flags, pg_owner); ++ ++ put_pg_owner(pg_owner); ++ ++ if ( rc == -ERESTART ) ++ rc = hypercall_create_continuation( ++ __HYPERVISOR_update_va_mapping_otherdomain, ++ "iiiii", va, lo, hi, flags, domid); ++ + return rc; + } + +diff --git a/xen/arch/x86/mm/paging.c b/xen/arch/x86/mm/paging.c +index 2b0445ffe9..dcee496eb0 100644 +--- a/xen/arch/x86/mm/paging.c ++++ b/xen/arch/x86/mm/paging.c +@@ -873,6 +873,8 @@ void paging_dump_domain_info(struct domain *d) + printk(" paging assistance: "); + if ( paging_mode_shadow(d) ) + printk("shadow "); ++ if ( paging_mode_sh_forced(d) ) ++ printk("forced "); + if ( paging_mode_hap(d) ) + printk("hap "); + if ( paging_mode_refcounts(d) ) +diff --git a/xen/arch/x86/mm/shadow/common.c b/xen/arch/x86/mm/shadow/common.c +index dd61b50eb7..fd42d734e7 100644 +--- a/xen/arch/x86/mm/shadow/common.c ++++ b/xen/arch/x86/mm/shadow/common.c +@@ -3177,6 +3177,15 @@ static void sh_new_mode(struct domain *d, u32 new_mode) + ASSERT(paging_locked_by_me(d)); + ASSERT(d != current->domain); + ++ /* ++ * If PG_SH_forced has previously been activated because of writing an ++ * L1TF-vulnerable PTE, it must remain active for the remaining lifetime ++ * of the domain, even if the logdirty mode needs to be controlled for ++ * migration purposes. ++ */ ++ if ( paging_mode_sh_forced(d) ) ++ new_mode |= PG_SH_forced | PG_SH_enable; ++ + d->arch.paging.mode = new_mode; + for_each_vcpu(d, v) + sh_update_paging_modes(v); +@@ -4057,6 +4066,33 @@ void shadow_audit_tables(struct vcpu *v) + + #endif /* Shadow audit */ + ++#ifdef CONFIG_PV ++ ++void pv_l1tf_tasklet(unsigned long data) ++{ ++ struct domain *d = (void *)data; ++ ++ domain_pause(d); ++ paging_lock(d); ++ ++ if ( !paging_mode_sh_forced(d) && !d->is_dying ) ++ { ++ int ret = shadow_one_bit_enable(d, PG_SH_forced); ++ ++ if ( ret ) ++ { ++ printk(XENLOG_G_ERR "d%d Failed to enable PG_SH_forced: %d\n", ++ d->domain_id, ret); ++ domain_crash(d); ++ } ++ } ++ ++ paging_unlock(d); ++ domain_unpause(d); ++} ++ ++#endif /* CONFIG_PV */ ++ + /* + * Local variables: + * mode: C +diff --git a/xen/arch/x86/mpparse.c b/xen/arch/x86/mpparse.c +index 49140e46f0..f3f6d48668 100644 +--- a/xen/arch/x86/mpparse.c ++++ b/xen/arch/x86/mpparse.c +@@ -68,19 +68,26 @@ physid_mask_t phys_cpu_present_map; + + void __init set_nr_cpu_ids(unsigned int max_cpus) + { ++ unsigned int tot_cpus = num_processors + disabled_cpus; ++ + if (!max_cpus) +- max_cpus = num_processors + disabled_cpus; ++ max_cpus = tot_cpus; + if (max_cpus > NR_CPUS) + max_cpus = NR_CPUS; + else if (!max_cpus) + max_cpus = 1; + printk(XENLOG_INFO "SMP: Allowing %u CPUs (%d hotplug CPUs)\n", + max_cpus, max_t(int, max_cpus - num_processors, 0)); +- nr_cpu_ids = max_cpus; ++ ++ if (!park_offline_cpus) ++ tot_cpus = max_cpus; ++ nr_cpu_ids = min(tot_cpus, NR_CPUS + 0u); ++ if (park_offline_cpus && nr_cpu_ids < num_processors) ++ printk(XENLOG_WARNING "SMP: Cannot bring up %u further CPUs\n", ++ num_processors - nr_cpu_ids); + + #ifndef nr_cpumask_bits +- nr_cpumask_bits = (max_cpus + (BITS_PER_LONG - 1)) & +- ~(BITS_PER_LONG - 1); ++ nr_cpumask_bits = ROUNDUP(nr_cpu_ids, BITS_PER_LONG); + printk(XENLOG_DEBUG "NR_CPUS:%u nr_cpumask_bits:%u\n", + NR_CPUS, nr_cpumask_bits); + #endif +diff --git a/xen/arch/x86/msr.c b/xen/arch/x86/msr.c +index 1e12ccb729..1a591dd2b5 100644 +--- a/xen/arch/x86/msr.c ++++ b/xen/arch/x86/msr.c +@@ -150,6 +150,7 @@ int guest_rdmsr(const struct vcpu *v, uint32_t msr, uint64_t *val) + case MSR_AMD_PATCHLOADER: + case MSR_IA32_UCODE_WRITE: + case MSR_PRED_CMD: ++ case MSR_FLUSH_CMD: + /* Write-only */ + goto gp_fault; + +@@ -254,6 +255,17 @@ int guest_wrmsr(struct vcpu *v, uint32_t msr, uint64_t val) + wrmsrl(MSR_PRED_CMD, val); + break; + ++ case MSR_FLUSH_CMD: ++ if ( !cp->feat.l1d_flush ) ++ goto gp_fault; /* MSR available? */ ++ ++ if ( val & ~FLUSH_CMD_L1D ) ++ goto gp_fault; /* Rsvd bit set? */ ++ ++ if ( v == curr ) ++ wrmsrl(MSR_FLUSH_CMD, val); ++ break; ++ + case MSR_INTEL_MISC_FEATURES_ENABLES: + { + bool old_cpuid_faulting = vp->misc_features_enables.cpuid_faulting; +diff --git a/xen/arch/x86/oprofile/nmi_int.c b/xen/arch/x86/oprofile/nmi_int.c +index d8f5230906..3dfb8fef93 100644 +--- a/xen/arch/x86/oprofile/nmi_int.c ++++ b/xen/arch/x86/oprofile/nmi_int.c +@@ -182,7 +182,7 @@ int nmi_reserve_counters(void) + if (!allocate_msrs()) + return -ENOMEM; + +- /* We walk a thin line between law and rape here. ++ /* + * We need to be careful to install our NMI handler + * without actually triggering any NMIs as this will + * break the core code horrifically. +diff --git a/xen/arch/x86/percpu.c b/xen/arch/x86/percpu.c +index c9997b7937..8be4ebddf4 100644 +--- a/xen/arch/x86/percpu.c ++++ b/xen/arch/x86/percpu.c +@@ -28,7 +28,7 @@ static int init_percpu_area(unsigned int cpu) + char *p; + + if ( __per_cpu_offset[cpu] != INVALID_PERCPU_AREA ) +- return -EBUSY; ++ return 0; + + if ( (p = alloc_xenheap_pages(PERCPU_ORDER, 0)) == NULL ) + return -ENOMEM; +@@ -76,9 +76,12 @@ static int cpu_percpu_callback( + break; + case CPU_UP_CANCELED: + case CPU_DEAD: +- free_percpu_area(cpu); ++ if ( !park_offline_cpus ) ++ free_percpu_area(cpu); + break; +- default: ++ case CPU_REMOVE: ++ if ( park_offline_cpus ) ++ free_percpu_area(cpu); + break; + } + +diff --git a/xen/arch/x86/pv/domain.c b/xen/arch/x86/pv/domain.c +index a4f0bd239d..3230ac6a22 100644 +--- a/xen/arch/x86/pv/domain.c ++++ b/xen/arch/x86/pv/domain.c +@@ -13,6 +13,7 @@ + #include <asm/invpcid.h> + #include <asm/spec_ctrl.h> + #include <asm/pv/domain.h> ++#include <asm/shadow.h> + + static __read_mostly enum { + PCID_OFF, +@@ -209,6 +210,8 @@ int pv_vcpu_initialise(struct vcpu *v) + + void pv_domain_destroy(struct domain *d) + { ++ pv_l1tf_domain_destroy(d); ++ + destroy_perdomain_mapping(d, GDT_LDT_VIRT_START, + GDT_LDT_MBYTES << (20 - PAGE_SHIFT)); + +@@ -229,6 +232,8 @@ int pv_domain_initialise(struct domain *d) + }; + int rc = -ENOMEM; + ++ pv_l1tf_domain_init(d); ++ + d->arch.pv_domain.gdt_ldt_l1tab = + alloc_xenheap_pages(0, MEMF_node(domain_to_node(d))); + if ( !d->arch.pv_domain.gdt_ldt_l1tab ) +diff --git a/xen/arch/x86/pv/ro-page-fault.c b/xen/arch/x86/pv/ro-page-fault.c +index aa8d5a7556..a3c0c2dd19 100644 +--- a/xen/arch/x86/pv/ro-page-fault.c ++++ b/xen/arch/x86/pv/ro-page-fault.c +@@ -29,6 +29,7 @@ + #include <asm/mm.h> + #include <asm/pci.h> + #include <asm/pv/mm.h> ++#include <asm/shadow.h> + + #include "emulate.h" + #include "mm.h" +@@ -129,6 +130,10 @@ static int ptwr_emulated_update(unsigned long addr, intpte_t *p_old, + + /* Check the new PTE. */ + nl1e = l1e_from_intpte(val); ++ ++ if ( !(l1e_get_flags(nl1e) & _PAGE_PRESENT) && pv_l1tf_check_l1e(d, nl1e) ) ++ return X86EMUL_RETRY; ++ + switch ( ret = get_page_from_l1e(nl1e, d, d) ) + { + default: +diff --git a/xen/arch/x86/setup.c b/xen/arch/x86/setup.c +index a3172ca92c..3cd3e81b30 100644 +--- a/xen/arch/x86/setup.c ++++ b/xen/arch/x86/setup.c +@@ -62,6 +62,9 @@ boolean_param("nosmp", opt_nosmp); + static unsigned int __initdata max_cpus; + integer_param("maxcpus", max_cpus); + ++int8_t __read_mostly opt_smt = -1; ++boolean_param("smt", opt_smt); ++ + /* opt_invpcid: If false, don't use INVPCID instruction even if available. */ + static bool __initdata opt_invpcid = true; + boolean_param("invpcid", opt_invpcid); +@@ -665,7 +668,7 @@ void __init noreturn __start_xen(unsigned long mbi_p) + { + char *memmap_type = NULL; + char *cmdline, *kextra, *loader; +- unsigned int initrdidx; ++ unsigned int initrdidx, num_parked = 0; + multiboot_info_t *mbi; + module_t *mod; + unsigned long nr_pages, raw_max_page, modules_headroom, *module_map; +@@ -909,6 +912,18 @@ void __init noreturn __start_xen(unsigned long mbi_p) + /* Sanitise the raw E820 map to produce a final clean version. */ + max_page = raw_max_page = init_e820(memmap_type, &e820_raw); + ++ if ( !efi_enabled(EFI_BOOT) ) ++ { ++ /* ++ * Supplement the heuristics in l1tf_calculations() by assuming that ++ * anything referenced in the E820 may be cacheable. ++ */ ++ l1tf_safe_maddr = ++ max(l1tf_safe_maddr, ++ ROUNDUP(e820_raw.map[e820_raw.nr_map - 1].addr + ++ e820_raw.map[e820_raw.nr_map - 1].size, PAGE_SIZE)); ++ } ++ + /* Create a temporary copy of the E820 map. */ + memcpy(&boot_e820, &e820, sizeof(e820)); + +@@ -1494,7 +1509,8 @@ void __init noreturn __start_xen(unsigned long mbi_p) + else + { + set_nr_cpu_ids(max_cpus); +- max_cpus = nr_cpu_ids; ++ if ( !max_cpus ) ++ max_cpus = nr_cpu_ids; + } + + if ( xen_guest ) +@@ -1617,16 +1633,30 @@ void __init noreturn __start_xen(unsigned long mbi_p) + /* Set up node_to_cpumask based on cpu_to_node[]. */ + numa_add_cpu(i); + +- if ( (num_online_cpus() < max_cpus) && !cpu_online(i) ) ++ if ( (park_offline_cpus || num_online_cpus() < max_cpus) && ++ !cpu_online(i) ) + { + int ret = cpu_up(i); + if ( ret != 0 ) + printk("Failed to bring up CPU %u (error %d)\n", i, ret); ++ else if ( num_online_cpus() > max_cpus || ++ (!opt_smt && ++ cpu_data[i].compute_unit_id == INVALID_CUID && ++ cpumask_weight(per_cpu(cpu_sibling_mask, i)) > 1) ) ++ { ++ ret = cpu_down(i); ++ if ( !ret ) ++ ++num_parked; ++ else ++ printk("Could not re-offline CPU%u (%d)\n", i, ret); ++ } + } + } + } + + printk("Brought up %ld CPUs\n", (long)num_online_cpus()); ++ if ( num_parked ) ++ printk(XENLOG_INFO "Parked %u CPUs\n", num_parked); + smp_cpus_done(); + + do_initcalls(); +diff --git a/xen/arch/x86/smpboot.c b/xen/arch/x86/smpboot.c +index d4478e6132..7e76cc3d68 100644 +--- a/xen/arch/x86/smpboot.c ++++ b/xen/arch/x86/smpboot.c +@@ -63,6 +63,8 @@ static cpumask_t scratch_cpu0mask; + cpumask_t cpu_online_map __read_mostly; + EXPORT_SYMBOL(cpu_online_map); + ++bool __read_mostly park_offline_cpus; ++ + unsigned int __read_mostly nr_sockets; + cpumask_t **__read_mostly socket_cpumask; + static cpumask_t *secondary_socket_cpumask; +@@ -234,33 +236,41 @@ static void link_thread_siblings(int cpu1, int cpu2) + cpumask_set_cpu(cpu2, per_cpu(cpu_core_mask, cpu1)); + } + +-static void set_cpu_sibling_map(int cpu) ++static void set_cpu_sibling_map(unsigned int cpu) + { +- int i; ++ unsigned int i; + struct cpuinfo_x86 *c = cpu_data; + + cpumask_set_cpu(cpu, &cpu_sibling_setup_map); + + cpumask_set_cpu(cpu, socket_cpumask[cpu_to_socket(cpu)]); ++ cpumask_set_cpu(cpu, per_cpu(cpu_core_mask, cpu)); ++ cpumask_set_cpu(cpu, per_cpu(cpu_sibling_mask, cpu)); + + if ( c[cpu].x86_num_siblings > 1 ) + { + for_each_cpu ( i, &cpu_sibling_setup_map ) + { +- if ( cpu_has(c, X86_FEATURE_TOPOEXT) ) { +- if ( (c[cpu].phys_proc_id == c[i].phys_proc_id) && +- (c[cpu].compute_unit_id == c[i].compute_unit_id) ) ++ if ( cpu == i || c[cpu].phys_proc_id != c[i].phys_proc_id ) ++ continue; ++ if ( c[cpu].compute_unit_id != INVALID_CUID && ++ c[i].compute_unit_id != INVALID_CUID ) ++ { ++ if ( c[cpu].compute_unit_id == c[i].compute_unit_id ) + link_thread_siblings(cpu, i); +- } else if ( (c[cpu].phys_proc_id == c[i].phys_proc_id) && +- (c[cpu].cpu_core_id == c[i].cpu_core_id) ) { +- link_thread_siblings(cpu, i); + } ++ else if ( c[cpu].cpu_core_id != XEN_INVALID_CORE_ID && ++ c[i].cpu_core_id != XEN_INVALID_CORE_ID ) ++ { ++ if ( c[cpu].cpu_core_id == c[i].cpu_core_id ) ++ link_thread_siblings(cpu, i); ++ } ++ else ++ printk(XENLOG_WARNING ++ "CPU%u: unclear relationship with CPU%u\n", ++ cpu, i); + } + } +- else +- { +- cpumask_set_cpu(cpu, per_cpu(cpu_sibling_mask, cpu)); +- } + + if ( c[cpu].x86_max_cores == 1 ) + { +@@ -887,7 +897,14 @@ static void cleanup_cpu_root_pgt(unsigned int cpu) + } + } + +-static void cpu_smpboot_free(unsigned int cpu) ++/* ++ * The 'remove' boolean controls whether a CPU is just getting offlined (and ++ * parked), or outright removed / offlined without parking. Parked CPUs need ++ * things like their stack, GDT, IDT, TSS, and per-CPU data still available. ++ * A few other items, in particular CPU masks, are also retained, as it's ++ * difficult to prove that they're entirely unreferenced from parked CPUs. ++ */ ++static void cpu_smpboot_free(unsigned int cpu, bool remove) + { + unsigned int order, socket = cpu_to_socket(cpu); + struct cpuinfo_x86 *c = cpu_data; +@@ -898,15 +915,19 @@ static void cpu_smpboot_free(unsigned int cpu) + socket_cpumask[socket] = NULL; + } + +- c[cpu].phys_proc_id = XEN_INVALID_SOCKET_ID; +- c[cpu].cpu_core_id = XEN_INVALID_CORE_ID; +- c[cpu].compute_unit_id = INVALID_CUID; + cpumask_clear_cpu(cpu, &cpu_sibling_setup_map); + +- free_cpumask_var(per_cpu(cpu_sibling_mask, cpu)); +- free_cpumask_var(per_cpu(cpu_core_mask, cpu)); +- if ( per_cpu(scratch_cpumask, cpu) != &scratch_cpu0mask ) +- free_cpumask_var(per_cpu(scratch_cpumask, cpu)); ++ if ( remove ) ++ { ++ c[cpu].phys_proc_id = XEN_INVALID_SOCKET_ID; ++ c[cpu].cpu_core_id = XEN_INVALID_CORE_ID; ++ c[cpu].compute_unit_id = INVALID_CUID; ++ ++ FREE_CPUMASK_VAR(per_cpu(cpu_sibling_mask, cpu)); ++ FREE_CPUMASK_VAR(per_cpu(cpu_core_mask, cpu)); ++ if ( per_cpu(scratch_cpumask, cpu) != &scratch_cpu0mask ) ++ FREE_CPUMASK_VAR(per_cpu(scratch_cpumask, cpu)); ++ } + + cleanup_cpu_root_pgt(cpu); + +@@ -928,19 +949,21 @@ static void cpu_smpboot_free(unsigned int cpu) + } + + order = get_order_from_pages(NR_RESERVED_GDT_PAGES); +- free_xenheap_pages(per_cpu(gdt_table, cpu), order); ++ if ( remove ) ++ FREE_XENHEAP_PAGES(per_cpu(gdt_table, cpu), order); + + free_xenheap_pages(per_cpu(compat_gdt_table, cpu), order); + +- order = get_order_from_bytes(IDT_ENTRIES * sizeof(idt_entry_t)); +- free_xenheap_pages(idt_tables[cpu], order); +- idt_tables[cpu] = NULL; +- +- if ( stack_base[cpu] != NULL ) ++ if ( remove ) + { +- memguard_unguard_stack(stack_base[cpu]); +- free_xenheap_pages(stack_base[cpu], STACK_ORDER); +- stack_base[cpu] = NULL; ++ order = get_order_from_bytes(IDT_ENTRIES * sizeof(idt_entry_t)); ++ FREE_XENHEAP_PAGES(idt_tables[cpu], order); ++ ++ if ( stack_base[cpu] ) ++ { ++ memguard_unguard_stack(stack_base[cpu]); ++ FREE_XENHEAP_PAGES(stack_base[cpu], STACK_ORDER); ++ } + } + } + +@@ -955,15 +978,17 @@ static int cpu_smpboot_alloc(unsigned int cpu) + if ( node != NUMA_NO_NODE ) + memflags = MEMF_node(node); + +- stack_base[cpu] = alloc_xenheap_pages(STACK_ORDER, memflags); ++ if ( stack_base[cpu] == NULL ) ++ stack_base[cpu] = alloc_xenheap_pages(STACK_ORDER, memflags); + if ( stack_base[cpu] == NULL ) + goto out; + memguard_guard_stack(stack_base[cpu]); + + order = get_order_from_pages(NR_RESERVED_GDT_PAGES); +- per_cpu(gdt_table, cpu) = gdt = alloc_xenheap_pages(order, memflags); ++ gdt = per_cpu(gdt_table, cpu) ?: alloc_xenheap_pages(order, memflags); + if ( gdt == NULL ) + goto out; ++ per_cpu(gdt_table, cpu) = gdt; + memcpy(gdt, boot_cpu_gdt_table, NR_RESERVED_GDT_PAGES * PAGE_SIZE); + BUILD_BUG_ON(NR_CPUS > 0x10000); + gdt[PER_CPU_GDT_ENTRY - FIRST_RESERVED_GDT_ENTRY].a = cpu; +@@ -975,7 +1000,8 @@ static int cpu_smpboot_alloc(unsigned int cpu) + gdt[PER_CPU_GDT_ENTRY - FIRST_RESERVED_GDT_ENTRY].a = cpu; + + order = get_order_from_bytes(IDT_ENTRIES * sizeof(idt_entry_t)); +- idt_tables[cpu] = alloc_xenheap_pages(order, memflags); ++ if ( idt_tables[cpu] == NULL ) ++ idt_tables[cpu] = alloc_xenheap_pages(order, memflags); + if ( idt_tables[cpu] == NULL ) + goto out; + memcpy(idt_tables[cpu], idt_table, IDT_ENTRIES * sizeof(idt_entry_t)); +@@ -1003,16 +1029,16 @@ static int cpu_smpboot_alloc(unsigned int cpu) + (secondary_socket_cpumask = xzalloc(cpumask_t)) == NULL ) + goto out; + +- if ( !(zalloc_cpumask_var(&per_cpu(cpu_sibling_mask, cpu)) && +- zalloc_cpumask_var(&per_cpu(cpu_core_mask, cpu)) && +- alloc_cpumask_var(&per_cpu(scratch_cpumask, cpu))) ) ++ if ( !(cond_zalloc_cpumask_var(&per_cpu(cpu_sibling_mask, cpu)) && ++ cond_zalloc_cpumask_var(&per_cpu(cpu_core_mask, cpu)) && ++ cond_alloc_cpumask_var(&per_cpu(scratch_cpumask, cpu))) ) + goto out; + + rc = 0; + + out: + if ( rc ) +- cpu_smpboot_free(cpu); ++ cpu_smpboot_free(cpu, true); + + return rc; + } +@@ -1030,9 +1056,10 @@ static int cpu_smpboot_callback( + break; + case CPU_UP_CANCELED: + case CPU_DEAD: +- cpu_smpboot_free(cpu); ++ cpu_smpboot_free(cpu, !park_offline_cpus); + break; +- default: ++ case CPU_REMOVE: ++ cpu_smpboot_free(cpu, true); + break; + } + +diff --git a/xen/arch/x86/spec_ctrl.c b/xen/arch/x86/spec_ctrl.c +index 08e6784c4c..f0c50d6703 100644 +--- a/xen/arch/x86/spec_ctrl.c ++++ b/xen/arch/x86/spec_ctrl.c +@@ -19,10 +19,13 @@ + #include <xen/errno.h> + #include <xen/init.h> + #include <xen/lib.h> ++#include <xen/warning.h> + + #include <asm/microcode.h> + #include <asm/msr.h> + #include <asm/processor.h> ++#include <asm/pv/shim.h> ++#include <asm/setup.h> + #include <asm/spec_ctrl.h> + #include <asm/spec_ctrl_asm.h> + +@@ -45,11 +48,16 @@ static int8_t __initdata opt_ibrs = -1; + bool __read_mostly opt_ibpb = true; + bool __read_mostly opt_ssbd = false; + int8_t __read_mostly opt_eager_fpu = -1; ++int8_t __read_mostly opt_l1d_flush = -1; + + bool __initdata bsp_delay_spec_ctrl; + uint8_t __read_mostly default_xen_spec_ctrl; + uint8_t __read_mostly default_spec_ctrl_flags; + ++paddr_t __read_mostly l1tf_addr_mask, __read_mostly l1tf_safe_maddr; ++static bool __initdata cpu_has_bug_l1tf; ++static unsigned int __initdata l1d_maxphysaddr; ++ + static int __init parse_bti(const char *s) + { + const char *ss; +@@ -124,6 +132,17 @@ static int __init parse_spec_ctrl(const char *s) + opt_msr_sc_pv = false; + opt_msr_sc_hvm = false; + ++ opt_eager_fpu = 0; ++ ++ if ( opt_xpti < 0 ) ++ opt_xpti = 0; ++ ++ if ( opt_smt < 0 ) ++ opt_smt = 1; ++ ++ if ( opt_pv_l1tf < 0 ) ++ opt_pv_l1tf = 0; ++ + disable_common: + opt_rsb_pv = false; + opt_rsb_hvm = false; +@@ -131,7 +150,8 @@ static int __init parse_spec_ctrl(const char *s) + opt_thunk = THUNK_JMP; + opt_ibrs = 0; + opt_ibpb = false; +- opt_eager_fpu = 0; ++ opt_ssbd = false; ++ opt_l1d_flush = 0; + } + else if ( val > 0 ) + rc = -EINVAL; +@@ -187,6 +207,8 @@ static int __init parse_spec_ctrl(const char *s) + opt_ssbd = val; + else if ( (val = parse_boolean("eager-fpu", s, ss)) >= 0 ) + opt_eager_fpu = val; ++ else if ( (val = parse_boolean("l1d-flush", s, ss)) >= 0 ) ++ opt_l1d_flush = val; + else + rc = -EINVAL; + +@@ -197,6 +219,55 @@ static int __init parse_spec_ctrl(const char *s) + } + custom_param("spec-ctrl", parse_spec_ctrl); + ++int8_t __read_mostly opt_pv_l1tf = -1; ++ ++static __init int parse_pv_l1tf(const char *s) ++{ ++ const char *ss; ++ int val, rc = 0; ++ ++ /* Inhibit the defaults as an explicit choice has been given. */ ++ if ( opt_pv_l1tf == -1 ) ++ opt_pv_l1tf = 0; ++ ++ /* Interpret 'pv-l1tf' alone in its positive boolean form. */ ++ if ( *s == '\0' ) ++ opt_xpti = OPT_PV_L1TF_DOM0 | OPT_PV_L1TF_DOMU; ++ ++ do { ++ ss = strchr(s, ','); ++ if ( !ss ) ++ ss = strchr(s, '\0'); ++ ++ switch ( parse_bool(s, ss) ) ++ { ++ case 0: ++ opt_pv_l1tf = 0; ++ break; ++ ++ case 1: ++ opt_pv_l1tf = OPT_PV_L1TF_DOM0 | OPT_PV_L1TF_DOMU; ++ break; ++ ++ default: ++ if ( (val = parse_boolean("dom0", s, ss)) >= 0 ) ++ opt_pv_l1tf = ((opt_pv_l1tf & ~OPT_PV_L1TF_DOM0) | ++ (val ? OPT_PV_L1TF_DOM0 : 0)); ++ else if ( (val = parse_boolean("domu", s, ss)) >= 0 ) ++ opt_pv_l1tf = ((opt_pv_l1tf & ~OPT_PV_L1TF_DOMU) | ++ (val ? OPT_PV_L1TF_DOMU : 0)); ++ else ++ rc = -EINVAL; ++ break; ++ } ++ ++ s = ss + 1; ++ } while ( *ss ); ++ ++ return rc; ++} ++custom_param("pv-l1tf", parse_pv_l1tf); ++ + static void __init print_details(enum ind_thunk thunk, uint64_t caps) + { + unsigned int _7d0 = 0, e8b = 0, tmp; +@@ -210,22 +281,31 @@ static void __init print_details(enum ind_thunk thunk, uint64_t caps) + printk("Speculative mitigation facilities:\n"); + + /* Hardware features which pertain to speculative mitigations. */ +- printk(" Hardware features:%s%s%s%s%s%s%s%s\n", ++ printk(" Hardware features:%s%s%s%s%s%s%s%s%s%s\n", + (_7d0 & cpufeat_mask(X86_FEATURE_IBRSB)) ? " IBRS/IBPB" : "", + (_7d0 & cpufeat_mask(X86_FEATURE_STIBP)) ? " STIBP" : "", ++ (_7d0 & cpufeat_mask(X86_FEATURE_L1D_FLUSH)) ? " L1D_FLUSH" : "", + (_7d0 & cpufeat_mask(X86_FEATURE_SSBD)) ? " SSBD" : "", + (e8b & cpufeat_mask(X86_FEATURE_IBPB)) ? " IBPB" : "", + (caps & ARCH_CAPABILITIES_IBRS_ALL) ? " IBRS_ALL" : "", + (caps & ARCH_CAPABILITIES_RDCL_NO) ? " RDCL_NO" : "", + (caps & ARCH_CAPS_RSBA) ? " RSBA" : "", ++ (caps & ARCH_CAPS_SKIP_L1DFL) ? " SKIP_L1DFL": "", + (caps & ARCH_CAPS_SSB_NO) ? " SSB_NO" : ""); + +- /* Compiled-in support which pertains to BTI mitigations. */ +- if ( IS_ENABLED(CONFIG_INDIRECT_THUNK) ) +- printk(" Compiled-in support: INDIRECT_THUNK\n"); ++ /* Compiled-in support which pertains to mitigations. */ ++ if ( IS_ENABLED(CONFIG_INDIRECT_THUNK) || IS_ENABLED(CONFIG_SHADOW_PAGING) ) ++ printk(" Compiled-in support:" ++#ifdef CONFIG_INDIRECT_THUNK ++ " INDIRECT_THUNK" ++#endif ++#ifdef CONFIG_SHADOW_PAGING ++ " SHADOW_PAGING" ++#endif ++ "\n"); + + /* Settings for Xen's protection, irrespective of guests. */ +- printk(" Xen settings: BTI-Thunk %s, SPEC_CTRL: %s%s, Other:%s\n", ++ printk(" Xen settings: BTI-Thunk %s, SPEC_CTRL: %s%s, Other:%s%s\n", + thunk == THUNK_NONE ? "N/A" : + thunk == THUNK_RETPOLINE ? "RETPOLINE" : + thunk == THUNK_LFENCE ? "LFENCE" : +@@ -234,7 +314,15 @@ static void __init print_details(enum ind_thunk thunk, uint64_t caps) + (default_xen_spec_ctrl & SPEC_CTRL_IBRS) ? "IBRS+" : "IBRS-", + !boot_cpu_has(X86_FEATURE_SSBD) ? "" : + (default_xen_spec_ctrl & SPEC_CTRL_SSBD) ? " SSBD+" : " SSBD-", +- opt_ibpb ? " IBPB" : ""); ++ opt_ibpb ? " IBPB" : "", ++ opt_l1d_flush ? " L1D_FLUSH" : ""); ++ ++ /* L1TF diagnostics, printed if vulnerable or PV shadowing is in use. */ ++ if ( cpu_has_bug_l1tf || opt_pv_l1tf ) ++ printk(" L1TF: believed%s vulnerable, maxphysaddr L1D %u, CPUID %u" ++ ", Safe address %"PRIx64"\n", ++ cpu_has_bug_l1tf ? "" : " not", ++ l1d_maxphysaddr, paddr_bits, l1tf_safe_maddr); + + /* + * Alternatives blocks for protecting against and/or virtualising +@@ -257,6 +345,10 @@ static void __init print_details(enum ind_thunk thunk, uint64_t caps) + printk(" XPTI (64-bit PV only): Dom0 %s, DomU %s\n", + opt_xpti & OPT_XPTI_DOM0 ? "enabled" : "disabled", + opt_xpti & OPT_XPTI_DOMU ? "enabled" : "disabled"); ++ ++ printk(" PV L1TF shadowing: Dom0 %s, DomU %s\n", ++ opt_pv_l1tf & OPT_PV_L1TF_DOM0 ? "enabled" : "disabled", ++ opt_pv_l1tf & OPT_PV_L1TF_DOMU ? "enabled" : "disabled"); + } + + /* Calculate whether Retpoline is known-safe on this CPU. */ +@@ -418,20 +510,159 @@ static bool __init should_use_eager_fpu(void) + } + } + +-#define OPT_XPTI_DEFAULT 0xff +-uint8_t __read_mostly opt_xpti = OPT_XPTI_DEFAULT; +- +-static __init void xpti_init_default(bool force) ++/* Calculate whether this CPU is vulnerable to L1TF. */ ++static __init void l1tf_calculations(uint64_t caps) + { +- uint64_t caps = 0; ++ bool hit_default = false; ++ ++ l1d_maxphysaddr = paddr_bits; ++ ++ /* L1TF is only known to affect Intel Family 6 processors at this time. */ ++ if ( boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && ++ boot_cpu_data.x86 == 6 ) ++ { ++ switch ( boot_cpu_data.x86_model ) ++ { ++ /* ++ * Core processors since at least Penryn are vulnerable. ++ */ ++ case 0x17: /* Penryn */ ++ case 0x1d: /* Dunnington */ ++ cpu_has_bug_l1tf = true; ++ break; ++ ++ case 0x1f: /* Auburndale / Havendale */ ++ case 0x1e: /* Nehalem */ ++ case 0x1a: /* Nehalem EP */ ++ case 0x2e: /* Nehalem EX */ ++ case 0x25: /* Westmere */ ++ case 0x2c: /* Westmere EP */ ++ case 0x2f: /* Westmere EX */ ++ cpu_has_bug_l1tf = true; ++ l1d_maxphysaddr = 44; ++ break; ++ ++ case 0x2a: /* SandyBridge */ ++ case 0x2d: /* SandyBridge EP/EX */ ++ case 0x3a: /* IvyBridge */ ++ case 0x3e: /* IvyBridge EP/EX */ ++ case 0x3c: /* Haswell */ ++ case 0x3f: /* Haswell EX/EP */ ++ case 0x45: /* Haswell D */ ++ case 0x46: /* Haswell H */ ++ case 0x3d: /* Broadwell */ ++ case 0x47: /* Broadwell H */ ++ case 0x4f: /* Broadwell EP/EX */ ++ case 0x56: /* Broadwell D */ ++ case 0x4e: /* Skylake M */ ++ case 0x55: /* Skylake X */ ++ case 0x5e: /* Skylake D */ ++ case 0x66: /* Cannonlake */ ++ case 0x67: /* Cannonlake? */ ++ case 0x8e: /* Kabylake M */ ++ case 0x9e: /* Kabylake D */ ++ cpu_has_bug_l1tf = true; ++ l1d_maxphysaddr = 46; ++ break; ++ ++ /* ++ * Atom processors are not vulnerable. ++ */ ++ case 0x1c: /* Pineview */ ++ case 0x26: /* Lincroft */ ++ case 0x27: /* Penwell */ ++ case 0x35: /* Cloverview */ ++ case 0x36: /* Cedarview */ ++ case 0x37: /* Baytrail / Valleyview (Silvermont) */ ++ case 0x4d: /* Avaton / Rangely (Silvermont) */ ++ case 0x4c: /* Cherrytrail / Brasswell */ ++ case 0x4a: /* Merrifield */ ++ case 0x5a: /* Moorefield */ ++ case 0x5c: /* Goldmont */ ++ case 0x5f: /* Denverton */ ++ case 0x7a: /* Gemini Lake */ ++ break; ++ ++ /* ++ * Knights processors are not vulnerable. ++ */ ++ case 0x57: /* Knights Landing */ ++ case 0x85: /* Knights Mill */ ++ break; ++ ++ default: ++ /* Defer printk() until we've accounted for RDCL_NO. */ ++ hit_default = true; ++ cpu_has_bug_l1tf = true; ++ break; ++ } ++ } ++ ++ /* Any processor advertising RDCL_NO should be not vulnerable to L1TF. */ ++ if ( caps & ARCH_CAPABILITIES_RDCL_NO ) ++ cpu_has_bug_l1tf = false; ++ ++ if ( cpu_has_bug_l1tf && hit_default ) ++ printk("Unrecognised CPU model %#x - assuming vulnerable to L1TF\n", ++ boot_cpu_data.x86_model); ++ ++ /* ++ * L1TF safe address heuristics. These apply to the real hardware we are ++ * running on, and are best-effort-only if Xen is virtualised. ++ * ++ * The address mask which the L1D cache uses, which might be wider than ++ * the CPUID-reported maxphysaddr. ++ */ ++ l1tf_addr_mask = ((1ul << l1d_maxphysaddr) - 1) & PAGE_MASK; ++ ++ /* ++ * To be safe, l1tf_safe_maddr must be above the highest cacheable entity ++ * in system physical address space. However, to preserve space for ++ * paged-out metadata, it should be as low as possible above the highest ++ * cacheable address, so as to require fewer high-order bits being set. ++ * ++ * These heuristics are based on some guesswork to improve the likelihood ++ * of safety in the common case, including Linux's L1TF mitigation of ++ * inverting all address bits in a non-present PTE. ++ * ++ * - If L1D is wider than CPUID (Nehalem and later mobile/desktop/low end ++ * server), setting any address bit beyond CPUID maxphysaddr guarantees ++ * to make the PTE safe. This case doesn't require all the high-order ++ * bits being set, and doesn't require any other source of information ++ * for safety. ++ * ++ * - If L1D is the same as CPUID (Pre-Nehalem, or high end server), we ++ * must sacrifice high order bits from the real address space for ++ * safety. Therefore, make a blind guess that there is nothing ++ * cacheable in the top quarter of physical address space. ++ * ++ * It is exceedingly unlikely for machines to be populated with this ++ * much RAM (likely 512G on pre-Nehalem, 16T on Nehalem/Westmere, 64T on ++ * Sandybridge and later) due to the sheer volume of DIMMs this would ++ * actually take. ++ * ++ * However, it is possible to find machines this large, so the "top ++ * quarter" guess is supplemented to push the limit higher if references ++ * to cacheable mappings (E820/SRAT/EFI/etc) are found above the top ++ * quarter boundary. ++ * ++ * Finally, this top quarter guess gives us a good chance of being safe ++ * when running virtualised (and the CPUID maxphysaddr hasn't been ++ * levelled for heterogeneous migration safety), where the safety ++ * consideration is still in terms of host details, but all E820/etc ++ * information is in terms of guest physical layout. ++ */ ++ l1tf_safe_maddr = max(l1tf_safe_maddr, ((l1d_maxphysaddr > paddr_bits) ++ ? (1ul << paddr_bits) ++ : (3ul << (paddr_bits - 2)))); ++} + +- if ( !force && (opt_xpti != OPT_XPTI_DEFAULT) ) +- return; ++int8_t __read_mostly opt_xpti = -1; + ++static __init void xpti_init_default(uint64_t caps) ++{ + if ( boot_cpu_data.x86_vendor == X86_VENDOR_AMD ) + caps = ARCH_CAPABILITIES_RDCL_NO; +- else if ( boot_cpu_has(X86_FEATURE_ARCH_CAPS) ) +- rdmsrl(MSR_ARCH_CAPABILITIES, caps); + + if ( caps & ARCH_CAPABILITIES_RDCL_NO ) + opt_xpti = 0; +@@ -444,7 +675,13 @@ static __init int parse_xpti(const char *s) + const char *ss; + int val, rc = 0; + +- xpti_init_default(false); ++ /* Inhibit the defaults as an explicit choice has been given. */ ++ if ( opt_xpti == -1 ) ++ opt_xpti = 0; ++ ++ /* Interpret 'xpti' alone in its positive boolean form. */ ++ if ( *s == '\0' ) ++ opt_xpti = OPT_XPTI_DOM0 | OPT_XPTI_DOMU; + + do { + ss = strchr(s, ','); +@@ -463,7 +700,7 @@ static __init int parse_xpti(const char *s) + + default: + if ( !strcmp(s, "default") ) +- xpti_init_default(true); ++ opt_xpti = -1; + else if ( (val = parse_boolean("dom0", s, ss)) >= 0 ) + opt_xpti = (opt_xpti & ~OPT_XPTI_DOM0) | + (val ? OPT_XPTI_DOM0 : 0); +@@ -625,12 +862,58 @@ void __init init_speculation_mitigations(void) + if ( default_xen_spec_ctrl ) + setup_force_cpu_cap(X86_FEATURE_SC_MSR_IDLE); + +- xpti_init_default(false); ++ if ( opt_xpti == -1 ) ++ xpti_init_default(caps); ++ + if ( opt_xpti == 0 ) + setup_force_cpu_cap(X86_FEATURE_NO_XPTI); + else + setup_clear_cpu_cap(X86_FEATURE_NO_XPTI); + ++ l1tf_calculations(caps); ++ ++ /* ++ * By default, enable PV domU L1TF mitigations on all L1TF-vulnerable ++ * hardware, except when running in shim mode. ++ * ++ * In shim mode, SHADOW is expected to be compiled out, and a malicious ++ * guest kernel can only attack the shim Xen, not the host Xen. ++ */ ++ if ( opt_pv_l1tf == -1 ) ++ { ++ if ( pv_shim || !cpu_has_bug_l1tf ) ++ opt_pv_l1tf = 0; ++ else ++ opt_pv_l1tf = OPT_PV_L1TF_DOMU; ++ } ++ ++ /* ++ * By default, enable L1D_FLUSH on L1TF-vulnerable hardware, unless ++ * instructed to skip the flush on vmentry by our outer hypervisor. ++ */ ++ if ( !boot_cpu_has(X86_FEATURE_L1D_FLUSH) ) ++ opt_l1d_flush = 0; ++ else if ( opt_l1d_flush == -1 ) ++ opt_l1d_flush = cpu_has_bug_l1tf && !(caps & ARCH_CAPS_SKIP_L1DFL); ++ ++ /* ++ * We do not disable HT by default on affected hardware. ++ * ++ * Firstly, if the user intends to use exclusively PV, or HVM shadow ++ * guests, HT isn't a concern and should remain fully enabled. Secondly, ++ * safety for HVM HAP guests can be arranged by the toolstack with core ++ * parking, pinning or cpupool configurations, including mixed setups. ++ * ++ * However, if we are on affected hardware, with HT enabled, and the user ++ * hasn't explicitly chosen whether to use HT or not, nag them to do so. ++ */ ++ if ( opt_smt == -1 && cpu_has_bug_l1tf && !pv_shim && ++ boot_cpu_data.x86_num_siblings > 1 ) ++ warning_add( ++ "Booted on L1TF-vulnerable hardware with SMT/Hyperthreading\n" ++ "enabled. Please assess your configuration and choose an\n" ++ "explicit 'smt=<bool>' setting. See XSA-273.\n"); ++ + print_details(thunk, caps); + + /* +diff --git a/xen/arch/x86/srat.c b/xen/arch/x86/srat.c +index 166eb44fe2..2d70b45909 100644 +--- a/xen/arch/x86/srat.c ++++ b/xen/arch/x86/srat.c +@@ -20,6 +20,7 @@ + #include <xen/pfn.h> + #include <asm/e820.h> + #include <asm/page.h> ++#include <asm/spec_ctrl.h> + + static struct acpi_table_slit *__read_mostly acpi_slit; + +@@ -284,6 +285,11 @@ acpi_numa_memory_affinity_init(const struct acpi_srat_mem_affinity *ma) + if (!(ma->flags & ACPI_SRAT_MEM_ENABLED)) + return; + ++ start = ma->base_address; ++ end = start + ma->length; ++ /* Supplement the heuristics in l1tf_calculations(). */ ++ l1tf_safe_maddr = max(l1tf_safe_maddr, ROUNDUP(end, PAGE_SIZE)); ++ + if (num_node_memblks >= NR_NODE_MEMBLKS) + { + dprintk(XENLOG_WARNING, +@@ -292,8 +298,6 @@ acpi_numa_memory_affinity_init(const struct acpi_srat_mem_affinity *ma) + return; + } + +- start = ma->base_address; +- end = start + ma->length; + pxm = ma->proximity_domain; + if (srat_rev < 2) + pxm &= 0xff; +diff --git a/xen/arch/x86/sysctl.c b/xen/arch/x86/sysctl.c +index 4d372db12b..e704ed7f1c 100644 +--- a/xen/arch/x86/sysctl.c ++++ b/xen/arch/x86/sysctl.c +@@ -23,6 +23,7 @@ + #include <asm/hvm/hvm.h> + #include <asm/hvm/support.h> + #include <asm/processor.h> ++#include <asm/setup.h> + #include <asm/smp.h> + #include <asm/numa.h> + #include <xen/nodemask.h> +@@ -48,14 +49,27 @@ static void l3_cache_get(void *arg) + + long cpu_up_helper(void *data) + { +- int cpu = (unsigned long)data; ++ unsigned int cpu = (unsigned long)data; + int ret = cpu_up(cpu); ++ + if ( ret == -EBUSY ) + { + /* On EBUSY, flush RCU work and have one more go. */ + rcu_barrier(); + ret = cpu_up(cpu); + } ++ ++ if ( !ret && !opt_smt && ++ cpu_data[cpu].compute_unit_id == INVALID_CUID && ++ cpumask_weight(per_cpu(cpu_sibling_mask, cpu)) > 1 ) ++ { ++ ret = cpu_down_helper(data); ++ if ( ret ) ++ printk("Could not re-offline CPU%u (%d)\n", cpu, ret); ++ else ++ ret = -EPERM; ++ } ++ + return ret; + } + +diff --git a/xen/arch/x86/traps.c b/xen/arch/x86/traps.c +index 9f045a2045..789d7ff8cd 100644 +--- a/xen/arch/x86/traps.c ++++ b/xen/arch/x86/traps.c +@@ -96,8 +96,6 @@ string_param("nmi", opt_nmi); + DEFINE_PER_CPU(uint64_t, efer); + static DEFINE_PER_CPU(unsigned long, last_extable_addr); + +-DEFINE_PER_CPU_READ_MOSTLY(u32, ler_msr); +- + DEFINE_PER_CPU_READ_MOSTLY(struct desc_struct *, gdt_table); + DEFINE_PER_CPU_READ_MOSTLY(struct desc_struct *, compat_gdt_table); + +@@ -117,6 +115,9 @@ integer_param("debug_stack_lines", debug_stack_lines); + static bool opt_ler; + boolean_param("ler", opt_ler); + ++/* LastExceptionFromIP on this hardware. Zero if LER is not in use. */ ++unsigned int __read_mostly ler_msr; ++ + #define stack_words_per_line 4 + #define ESP_BEFORE_EXCEPTION(regs) ((unsigned long *)regs->rsp) + +@@ -1778,17 +1779,6 @@ void do_device_not_available(struct cpu_user_regs *regs) + return; + } + +-static void ler_enable(void) +-{ +- u64 debugctl; +- +- if ( !this_cpu(ler_msr) ) +- return; +- +- rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); +- wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl | IA32_DEBUGCTLMSR_LBR); +-} +- + void do_debug(struct cpu_user_regs *regs) + { + unsigned long dr6; +@@ -1821,6 +1811,10 @@ void do_debug(struct cpu_user_regs *regs) + */ + write_debugreg(6, X86_DR6_DEFAULT); + ++ /* #DB automatically disabled LBR. Reinstate it if debugging Xen. */ ++ if ( cpu_has_xen_lbr ) ++ wrmsrl(MSR_IA32_DEBUGCTLMSR, IA32_DEBUGCTLMSR_LBR); ++ + if ( !guest_mode(regs) ) + { + /* +@@ -1838,7 +1832,7 @@ void do_debug(struct cpu_user_regs *regs) + { + if ( regs->rip == (unsigned long)sysenter_eflags_saved ) + regs->eflags &= ~X86_EFLAGS_TF; +- goto out; ++ return; + } + if ( !debugger_trap_fatal(TRAP_debug, regs) ) + { +@@ -1895,20 +1889,14 @@ void do_debug(struct cpu_user_regs *regs) + regs->cs, _p(regs->rip), _p(regs->rip), + regs->ss, _p(regs->rsp), dr6); + +- goto out; ++ return; + } + + /* Save debug status register where guest OS can peek at it */ + v->arch.debugreg[6] |= (dr6 & ~X86_DR6_DEFAULT); + v->arch.debugreg[6] &= (dr6 | ~X86_DR6_DEFAULT); + +- ler_enable(); + pv_inject_hw_exception(TRAP_debug, X86_EVENT_NO_EC); +- return; +- +- out: +- ler_enable(); +- return; + } + + static void __init noinline __set_intr_gate(unsigned int n, +@@ -1952,38 +1940,46 @@ void load_TR(void) + : "=m" (old_gdt) : "rm" (TSS_ENTRY << 3), "m" (tss_gdt) : "memory" ); + } + +-void percpu_traps_init(void) ++static unsigned int calc_ler_msr(void) + { +- subarch_percpu_traps_init(); +- +- if ( !opt_ler ) +- return; +- + switch ( boot_cpu_data.x86_vendor ) + { + case X86_VENDOR_INTEL: + switch ( boot_cpu_data.x86 ) + { + case 6: +- this_cpu(ler_msr) = MSR_IA32_LASTINTFROMIP; +- break; ++ return MSR_IA32_LASTINTFROMIP; ++ + case 15: +- this_cpu(ler_msr) = MSR_P4_LER_FROM_LIP; +- break; ++ return MSR_P4_LER_FROM_LIP; + } + break; ++ + case X86_VENDOR_AMD: + switch ( boot_cpu_data.x86 ) + { + case 6: + case 0xf ... 0x17: +- this_cpu(ler_msr) = MSR_IA32_LASTINTFROMIP; +- break; ++ return MSR_IA32_LASTINTFROMIP; + } + break; + } + +- ler_enable(); ++ return 0; ++} ++ ++void percpu_traps_init(void) ++{ ++ subarch_percpu_traps_init(); ++ ++ if ( !opt_ler ) ++ return; ++ ++ if ( !ler_msr && (ler_msr = calc_ler_msr()) ) ++ setup_force_cpu_cap(X86_FEATURE_XEN_LBR); ++ ++ if ( cpu_has_xen_lbr ) ++ wrmsrl(MSR_IA32_DEBUGCTLMSR, IA32_DEBUGCTLMSR_LBR); + } + + void __init init_idt_traps(void) +diff --git a/xen/arch/x86/x86_64/compat/mm.c b/xen/arch/x86/x86_64/compat/mm.c +index c2aa6f2fdb..02bc75b91e 100644 +--- a/xen/arch/x86/x86_64/compat/mm.c ++++ b/xen/arch/x86/x86_64/compat/mm.c +@@ -163,19 +163,6 @@ int compat_arch_memory_op(unsigned long cmd, XEN_GUEST_HANDLE_PARAM(void) arg) + return rc; + } + +-int compat_update_va_mapping(unsigned int va, u32 lo, u32 hi, +- unsigned int flags) +-{ +- return do_update_va_mapping(va, lo | ((u64)hi << 32), flags); +-} +- +-int compat_update_va_mapping_otherdomain(unsigned long va, u32 lo, u32 hi, +- unsigned long flags, +- domid_t domid) +-{ +- return do_update_va_mapping_otherdomain(va, lo | ((u64)hi << 32), flags, domid); +-} +- + DEFINE_XEN_GUEST_HANDLE(mmuext_op_compat_t); + + int compat_mmuext_op(XEN_GUEST_HANDLE_PARAM(void) arg, +diff --git a/xen/arch/x86/x86_64/traps.c b/xen/arch/x86/x86_64/traps.c +index f7f6928d70..b0401850ef 100644 +--- a/xen/arch/x86/x86_64/traps.c ++++ b/xen/arch/x86/x86_64/traps.c +@@ -144,11 +144,12 @@ void show_registers(const struct cpu_user_regs *regs) + printk("CPU: %d\n", smp_processor_id()); + _show_registers(&fault_regs, fault_crs, context, v); + +- if ( this_cpu(ler_msr) && !guest_mode(regs) ) ++ if ( ler_msr && !guest_mode(regs) ) + { + u64 from, to; +- rdmsrl(this_cpu(ler_msr), from); +- rdmsrl(this_cpu(ler_msr) + 1, to); ++ ++ rdmsrl(ler_msr, from); ++ rdmsrl(ler_msr + 1, to); + printk("ler: %016lx -> %016lx\n", from, to); + } + } +diff --git a/xen/arch/x86/xstate.c b/xen/arch/x86/xstate.c +index b4aea4b50a..15edd5df96 100644 +--- a/xen/arch/x86/xstate.c ++++ b/xen/arch/x86/xstate.c +@@ -670,12 +670,17 @@ static bool valid_xcr0(u64 xcr0) + return !(xcr0 & X86_XCR0_BNDREGS) == !(xcr0 & X86_XCR0_BNDCSR); + } + +-int validate_xstate(u64 xcr0, u64 xcr0_accum, const struct xsave_hdr *hdr) ++int validate_xstate(const struct domain *d, uint64_t xcr0, uint64_t xcr0_accum, ++ const struct xsave_hdr *hdr) + { ++ const struct cpuid_policy *cp = d->arch.cpuid; ++ uint64_t xcr0_max = ++ ((uint64_t)cp->xstate.xcr0_high << 32) | cp->xstate.xcr0_low; + unsigned int i; + + if ( (hdr->xstate_bv & ~xcr0_accum) || + (xcr0 & ~xcr0_accum) || ++ (xcr0_accum & ~xcr0_max) || + !valid_xcr0(xcr0) || + !valid_xcr0(xcr0_accum) ) + return -EINVAL; +@@ -694,20 +699,40 @@ int validate_xstate(u64 xcr0, u64 xcr0_accum, const struct xsave_hdr *hdr) + int handle_xsetbv(u32 index, u64 new_bv) + { + struct vcpu *curr = current; ++ const struct cpuid_policy *cp = curr->domain->arch.cpuid; ++ uint64_t xcr0_max = ++ ((uint64_t)cp->xstate.xcr0_high << 32) | cp->xstate.xcr0_low; + u64 mask; + + if ( index != XCR_XFEATURE_ENABLED_MASK ) + return -EOPNOTSUPP; + +- if ( (new_bv & ~xfeature_mask) || !valid_xcr0(new_bv) ) ++ /* ++ * The CPUID logic shouldn't be able to hand out an XCR0 exceeding Xen's ++ * maximum features, but keep the check for robustness. ++ */ ++ if ( unlikely(xcr0_max & ~xfeature_mask) ) ++ { ++ gprintk(XENLOG_ERR, ++ "xcr0_max %016" PRIx64 " exceeds hardware max %016" PRIx64 "\n", ++ xcr0_max, xfeature_mask); ++ domain_crash(curr->domain); ++ ++ return -EINVAL; ++ } ++ ++ if ( (new_bv & ~xcr0_max) || !valid_xcr0(new_bv) ) + return -EINVAL; + +- /* XCR0.PKRU is disabled on PV mode. */ +- if ( is_pv_vcpu(curr) && (new_bv & X86_XCR0_PKRU) ) +- return -EOPNOTSUPP; ++ /* By this point, new_bv really should be accepted by hardware. */ ++ if ( unlikely(!set_xcr0(new_bv)) ) ++ { ++ gprintk(XENLOG_ERR, "new_bv %016" PRIx64 " rejected by hardware\n", ++ new_bv); ++ domain_crash(curr->domain); + +- if ( !set_xcr0(new_bv) ) + return -EFAULT; ++ } + + mask = new_bv & ~curr->arch.xcr0_accum; + curr->arch.xcr0 = new_bv; +diff --git a/xen/common/cpu.c b/xen/common/cpu.c +index 6350f150bd..653a56b840 100644 +--- a/xen/common/cpu.c ++++ b/xen/common/cpu.c +@@ -67,12 +67,17 @@ void __init register_cpu_notifier(struct notifier_block *nb) + spin_unlock(&cpu_add_remove_lock); + } + +-static int take_cpu_down(void *unused) ++static void _take_cpu_down(void *unused) + { + void *hcpu = (void *)(long)smp_processor_id(); + int notifier_rc = notifier_call_chain(&cpu_chain, CPU_DYING, hcpu, NULL); + BUG_ON(notifier_rc != NOTIFY_DONE); + __cpu_disable(); ++} ++ ++static int take_cpu_down(void *arg) ++{ ++ _take_cpu_down(arg); + return 0; + } + +@@ -98,7 +103,9 @@ int cpu_down(unsigned int cpu) + goto fail; + } + +- if ( (err = stop_machine_run(take_cpu_down, NULL, cpu)) < 0 ) ++ if ( unlikely(system_state < SYS_STATE_active) ) ++ on_selected_cpus(cpumask_of(cpu), _take_cpu_down, NULL, true); ++ else if ( (err = stop_machine_run(take_cpu_down, NULL, cpu)) < 0 ) + goto fail; + + __cpu_die(cpu); +diff --git a/xen/common/cpupool.c b/xen/common/cpupool.c +index 999839444e..1e8edcbd57 100644 +--- a/xen/common/cpupool.c ++++ b/xen/common/cpupool.c +@@ -490,7 +490,7 @@ static int cpupool_cpu_add(unsigned int cpu) + cpumask_clear_cpu(cpu, &cpupool_locked_cpus); + cpumask_set_cpu(cpu, &cpupool_free_cpus); + +- if ( system_state == SYS_STATE_resume ) ++ if ( system_state == SYS_STATE_suspend || system_state == SYS_STATE_resume ) + { + struct cpupool **c; + +@@ -522,6 +522,7 @@ static int cpupool_cpu_add(unsigned int cpu) + * (or unplugging would have failed) and that is the default behavior + * anyway. + */ ++ per_cpu(cpupool, cpu) = NULL; + ret = cpupool_assign_cpu_locked(cpupool0, cpu); + } + out: +diff --git a/xen/common/efi/boot.c b/xen/common/efi/boot.c +index 64d12685d3..6be0b3986f 100644 +--- a/xen/common/efi/boot.c ++++ b/xen/common/efi/boot.c +@@ -1304,6 +1304,8 @@ efi_start(EFI_HANDLE ImageHandle, EFI_SYSTEM_TABLE *SystemTable) + + #ifndef CONFIG_ARM /* TODO - runtime service support */ + ++#include <asm/spec_ctrl.h> ++ + static bool __initdata efi_map_uc; + + static int __init parse_efi_param(const char *s) +@@ -1419,6 +1421,16 @@ void __init efi_init_memory(void) + desc->PhysicalStart, desc->PhysicalStart + len - 1, + desc->Type, desc->Attribute); + ++ if ( (desc->Attribute & (EFI_MEMORY_WB | EFI_MEMORY_WT)) || ++ (efi_bs_revision >= EFI_REVISION(2, 5) && ++ (desc->Attribute & EFI_MEMORY_WP)) ) ++ { ++ /* Supplement the heuristics in l1tf_calculations(). */ ++ l1tf_safe_maddr = ++ max(l1tf_safe_maddr, ++ ROUNDUP(desc->PhysicalStart + len, PAGE_SIZE)); ++ } ++ + if ( !efi_enabled(EFI_RS) || + (!(desc->Attribute & EFI_MEMORY_RUNTIME) && + (!map_bs || +diff --git a/xen/common/grant_table.c b/xen/common/grant_table.c +index c757b7f6f5..231ecf509a 100644 +--- a/xen/common/grant_table.c ++++ b/xen/common/grant_table.c +@@ -97,7 +97,11 @@ static unsigned int __read_mostly max_maptrack_frames = + DEFAULT_MAX_MAPTRACK_FRAMES; + integer_runtime_param("gnttab_max_maptrack_frames", max_maptrack_frames); + +-static unsigned int __read_mostly opt_gnttab_max_version = 2; ++#ifndef GNTTAB_MAX_VERSION ++#define GNTTAB_MAX_VERSION 2 ++#endif ++ ++static unsigned int __read_mostly opt_gnttab_max_version = GNTTAB_MAX_VERSION; + static bool __read_mostly opt_transitive_grants = true; + + static int __init parse_gnttab(const char *s) +diff --git a/xen/common/page_alloc.c b/xen/common/page_alloc.c +index 20ee1e4897..02aeed7c47 100644 +--- a/xen/common/page_alloc.c ++++ b/xen/common/page_alloc.c +@@ -1426,7 +1426,7 @@ static void free_heap_pages( + + page_list_del(predecessor, &heap(node, zone, order)); + +- /* Keep predecessor's first_dirty if it is already set. */ ++ /* Update predecessor's first_dirty if necessary. */ + if ( predecessor->u.free.first_dirty == INVALID_DIRTY_IDX && + pg->u.free.first_dirty != INVALID_DIRTY_IDX ) + predecessor->u.free.first_dirty = (1U << order) + +@@ -1447,6 +1447,12 @@ static void free_heap_pages( + + check_and_stop_scrub(successor); + ++ /* Update pg's first_dirty if necessary. */ ++ if ( pg->u.free.first_dirty == INVALID_DIRTY_IDX && ++ successor->u.free.first_dirty != INVALID_DIRTY_IDX ) ++ pg->u.free.first_dirty = (1U << order) + ++ successor->u.free.first_dirty; ++ + page_list_del(successor, &heap(node, zone, order)); + } + +diff --git a/xen/common/tasklet.c b/xen/common/tasklet.c +index 0f0a6f8365..d4fea3151c 100644 +--- a/xen/common/tasklet.c ++++ b/xen/common/tasklet.c +@@ -156,6 +156,10 @@ void tasklet_kill(struct tasklet *t) + + spin_lock_irqsave(&tasklet_lock, flags); + ++ /* Cope with uninitialised tasklets. */ ++ if ( list_head_is_null(&t->list) ) ++ goto unlock; ++ + if ( !list_empty(&t->list) ) + { + BUG_ON(t->is_dead || t->is_running || (t->scheduled_on < 0)); +@@ -172,6 +176,7 @@ void tasklet_kill(struct tasklet *t) + spin_lock_irqsave(&tasklet_lock, flags); + } + ++ unlock: + spin_unlock_irqrestore(&tasklet_lock, flags); + } + +diff --git a/xen/include/asm-arm/arm32/system.h b/xen/include/asm-arm/arm32/system.h +index c617b40438..ab57abfbc5 100644 +--- a/xen/include/asm-arm/arm32/system.h ++++ b/xen/include/asm-arm/arm32/system.h +@@ -48,6 +48,24 @@ static inline int local_fiq_is_enabled(void) + return !(flags & PSR_FIQ_MASK); + } + ++#define CSDB ".inst 0xe320f014" ++ ++static inline unsigned long array_index_mask_nospec(unsigned long idx, ++ unsigned long sz) ++{ ++ unsigned long mask; ++ ++ asm volatile( "cmp %1, %2\n" ++ "sbc %0, %1, %1\n" ++ CSDB ++ : "=r" (mask) ++ : "r" (idx), "Ir" (sz) ++ : "cc" ); ++ ++ return mask; ++} ++#define array_index_mask_nospec array_index_mask_nospec ++ + #endif + /* + * Local variables: +diff --git a/xen/include/asm-arm/arm64/system.h b/xen/include/asm-arm/arm64/system.h +index 2e2ee212a1..2e36573ac6 100644 +--- a/xen/include/asm-arm/arm64/system.h ++++ b/xen/include/asm-arm/arm64/system.h +@@ -58,6 +58,28 @@ static inline int local_fiq_is_enabled(void) + return !(flags & PSR_FIQ_MASK); + } + ++#define csdb() asm volatile ( "hint #20" : : : "memory" ) ++ ++/* ++ * Generate a mask for array_index__nospec() that is ~0UL when 0 <= idx < sz ++ * and 0 otherwise. ++ */ ++static inline unsigned long array_index_mask_nospec(unsigned long idx, ++ unsigned long sz) ++{ ++ unsigned long mask; ++ ++ asm volatile ( "cmp %1, %2\n" ++ "sbc %0, xzr, xzr\n" ++ : "=r" (mask) ++ : "r" (idx), "Ir" (sz) ++ : "cc" ); ++ csdb(); ++ ++ return mask; ++} ++#define array_index_mask_nospec array_index_mask_nospec ++ + #endif + /* + * Local variables: +diff --git a/xen/include/asm-arm/grant_table.h b/xen/include/asm-arm/grant_table.h +index e52936c79f..24958e4670 100644 +--- a/xen/include/asm-arm/grant_table.h ++++ b/xen/include/asm-arm/grant_table.h +@@ -7,6 +7,7 @@ + #include <xen/sched.h> + + #define INITIAL_NR_GRANT_FRAMES 1U ++#define GNTTAB_MAX_VERSION 1 + + struct grant_table_arch { + gfn_t *shared_gfn; +diff --git a/xen/include/asm-x86/cpufeature.h b/xen/include/asm-x86/cpufeature.h +index 2cf8f7ea2a..b237da165c 100644 +--- a/xen/include/asm-x86/cpufeature.h ++++ b/xen/include/asm-x86/cpufeature.h +@@ -113,6 +113,7 @@ + #define cpu_has_aperfmperf boot_cpu_has(X86_FEATURE_APERFMPERF) + #define cpu_has_lfence_dispatch boot_cpu_has(X86_FEATURE_LFENCE_DISPATCH) + #define cpu_has_no_xpti boot_cpu_has(X86_FEATURE_NO_XPTI) ++#define cpu_has_xen_lbr boot_cpu_has(X86_FEATURE_XEN_LBR) + + enum _cache_type { + CACHE_TYPE_NULL = 0, +diff --git a/xen/include/asm-x86/cpufeatures.h b/xen/include/asm-x86/cpufeatures.h +index b90aa2d046..8e5cc53dde 100644 +--- a/xen/include/asm-x86/cpufeatures.h ++++ b/xen/include/asm-x86/cpufeatures.h +@@ -32,3 +32,4 @@ XEN_CPUFEATURE(SC_RSB_PV, (FSCAPINTS+0)*32+18) /* RSB overwrite needed for + XEN_CPUFEATURE(SC_RSB_HVM, (FSCAPINTS+0)*32+19) /* RSB overwrite needed for HVM */ + XEN_CPUFEATURE(NO_XPTI, (FSCAPINTS+0)*32+20) /* XPTI mitigation not in use */ + XEN_CPUFEATURE(SC_MSR_IDLE, (FSCAPINTS+0)*32+21) /* (SC_MSR_PV || SC_MSR_HVM) && default_xen_spec_ctrl */ ++XEN_CPUFEATURE(XEN_LBR, (FSCAPINTS+0)*32+22) /* Xen uses MSR_DEBUGCTL.LBR */ +diff --git a/xen/include/asm-x86/domain.h b/xen/include/asm-x86/domain.h +index e0d413c7de..61e6900465 100644 +--- a/xen/include/asm-x86/domain.h ++++ b/xen/include/asm-x86/domain.h +@@ -121,6 +121,11 @@ struct shadow_domain { + + /* Has this domain ever used HVMOP_pagetable_dying? */ + bool_t pagetable_dying_op; ++ ++#ifdef CONFIG_PV ++ /* PV L1 Terminal Fault mitigation. */ ++ struct tasklet pv_l1tf_tasklet; ++#endif /* CONFIG_PV */ + #endif + }; + +@@ -257,6 +262,8 @@ struct pv_domain + bool xpti; + /* Use PCID feature? */ + bool pcid; ++ /* Mitigate L1TF with shadow/crashing? */ ++ bool check_l1tf; + + /* map_domain_page() mapping cache. */ + struct mapcache_domain mapcache; +diff --git a/xen/include/asm-x86/hvm/vmx/vmcs.h b/xen/include/asm-x86/hvm/vmx/vmcs.h +index 06c3179cec..57e5098b99 100644 +--- a/xen/include/asm-x86/hvm/vmx/vmcs.h ++++ b/xen/include/asm-x86/hvm/vmx/vmcs.h +@@ -130,10 +130,18 @@ struct arch_vmx_struct { + uint64_t sfmask; + + struct vmx_msr_bitmap *msr_bitmap; +- unsigned int msr_count; ++ ++ /* ++ * Most accesses to the MSR host/guest load/save lists are in current ++ * context. However, the data can be modified by toolstack/migration ++ * actions. Remote access is only permitted for paused vcpus, and is ++ * protected under the domctl lock. ++ */ + struct vmx_msr_entry *msr_area; +- unsigned int host_msr_count; + struct vmx_msr_entry *host_msr_area; ++ unsigned int msr_load_count; ++ unsigned int msr_save_count; ++ unsigned int host_msr_count; + + unsigned long eoi_exitmap_changed; + DECLARE_BITMAP(eoi_exit_bitmap, NR_VECTORS); +@@ -149,7 +157,7 @@ struct arch_vmx_struct { + /* Are we emulating rather than VMENTERing? */ + uint8_t vmx_emulate; + +- uint8_t lbr_fixup_enabled; ++ uint8_t lbr_flags; + + /* Bitmask of segments that we can't safely use in virtual 8086 mode */ + uint16_t vm86_segment_mask; +@@ -514,9 +522,6 @@ enum vmcs_field { + + #define VMCS_VPID_WIDTH 16 + +-#define VMX_GUEST_MSR 0 +-#define VMX_HOST_MSR 1 +- + /* VM Instruction error numbers */ + enum vmx_insn_errno + { +@@ -534,6 +539,67 @@ enum vmx_insn_errno + VMX_INSN_FAIL_INVALID = ~0, + }; + ++/* MSR load/save list infrastructure. */ ++enum vmx_msr_list_type { ++ VMX_MSR_HOST, /* MSRs loaded on VMExit. */ ++ VMX_MSR_GUEST, /* MSRs saved on VMExit, loaded on VMEntry. */ ++ VMX_MSR_GUEST_LOADONLY, /* MSRs loaded on VMEntry only. */ ++}; ++ ++/** ++ * Add an MSR to an MSR list (inserting space for the entry if necessary), and ++ * set the MSRs value. ++ * ++ * It is undefined behaviour to try and insert the same MSR into both the ++ * GUEST and GUEST_LOADONLY list. ++ * ++ * May fail if unable to allocate memory for the list, or the total number of ++ * entries exceeds the memory allocated. ++ */ ++int vmx_add_msr(struct vcpu *v, uint32_t msr, uint64_t val, ++ enum vmx_msr_list_type type); ++ ++static inline int vmx_add_guest_msr(struct vcpu *v, uint32_t msr, uint64_t val) ++{ ++ return vmx_add_msr(v, msr, val, VMX_MSR_GUEST); ++} ++static inline int vmx_add_host_load_msr(struct vcpu *v, uint32_t msr, ++ uint64_t val) ++{ ++ return vmx_add_msr(v, msr, val, VMX_MSR_HOST); ++} ++ ++struct vmx_msr_entry *vmx_find_msr(const struct vcpu *v, uint32_t msr, ++ enum vmx_msr_list_type type); ++ ++static inline int vmx_read_guest_msr(const struct vcpu *v, uint32_t msr, ++ uint64_t *val) ++{ ++ const struct vmx_msr_entry *ent = vmx_find_msr(v, msr, VMX_MSR_GUEST); ++ ++ if ( !ent ) ++ return -ESRCH; ++ ++ *val = ent->data; ++ ++ return 0; ++} ++ ++static inline int vmx_write_guest_msr(struct vcpu *v, uint32_t msr, ++ uint64_t val) ++{ ++ struct vmx_msr_entry *ent = vmx_find_msr(v, msr, VMX_MSR_GUEST); ++ ++ if ( !ent ) ++ return -ESRCH; ++ ++ ent->data = val; ++ ++ return 0; ++} ++ ++ ++/* MSR intercept bitmap infrastructure. */ + enum vmx_msr_intercept_type { + VMX_MSR_R = 1, + VMX_MSR_W = 2, +@@ -544,10 +610,6 @@ void vmx_clear_msr_intercept(struct vcpu *v, unsigned int msr, + enum vmx_msr_intercept_type type); + void vmx_set_msr_intercept(struct vcpu *v, unsigned int msr, + enum vmx_msr_intercept_type type); +-int vmx_read_guest_msr(u32 msr, u64 *val); +-int vmx_write_guest_msr(u32 msr, u64 val); +-struct vmx_msr_entry *vmx_find_msr(u32 msr, int type); +-int vmx_add_msr(u32 msr, int type); + void vmx_vmcs_switch(paddr_t from, paddr_t to); + void vmx_set_eoi_exit_bitmap(struct vcpu *v, u8 vector); + void vmx_clear_eoi_exit_bitmap(struct vcpu *v, u8 vector); +@@ -562,15 +624,6 @@ void virtual_vmcs_vmwrite(const struct vcpu *, u32 encoding, u64 val); + enum vmx_insn_errno virtual_vmcs_vmwrite_safe(const struct vcpu *v, + u32 vmcs_encoding, u64 val); + +-static inline int vmx_add_guest_msr(u32 msr) +-{ +- return vmx_add_msr(msr, VMX_GUEST_MSR); +-} +-static inline int vmx_add_host_load_msr(u32 msr) +-{ +- return vmx_add_msr(msr, VMX_HOST_MSR); +-} +- + DECLARE_PER_CPU(bool_t, vmxon); + + bool_t vmx_vcpu_pml_enabled(const struct vcpu *v); +diff --git a/xen/include/asm-x86/hypercall.h b/xen/include/asm-x86/hypercall.h +index 1cc2e37d5c..da38b7991c 100644 +--- a/xen/include/asm-x86/hypercall.h ++++ b/xen/include/asm-x86/hypercall.h +@@ -165,7 +165,7 @@ extern int compat_update_va_mapping( + unsigned int va, u32 lo, u32 hi, unsigned int flags); + + extern int compat_update_va_mapping_otherdomain( +- unsigned long va, u32 lo, u32 hi, unsigned long flags, domid_t domid); ++ unsigned int va, u32 lo, u32 hi, unsigned int flags, domid_t domid); + + DEFINE_XEN_GUEST_HANDLE(trap_info_compat_t); + extern int compat_set_trap_table(XEN_GUEST_HANDLE(trap_info_compat_t) traps); +diff --git a/xen/include/asm-x86/msr-index.h b/xen/include/asm-x86/msr-index.h +index 8fbccc88a7..7235623c86 100644 +--- a/xen/include/asm-x86/msr-index.h ++++ b/xen/include/asm-x86/msr-index.h +@@ -47,8 +47,12 @@ + #define ARCH_CAPABILITIES_RDCL_NO (_AC(1, ULL) << 0) + #define ARCH_CAPABILITIES_IBRS_ALL (_AC(1, ULL) << 1) + #define ARCH_CAPS_RSBA (_AC(1, ULL) << 2) ++#define ARCH_CAPS_SKIP_L1DFL (_AC(1, ULL) << 3) + #define ARCH_CAPS_SSB_NO (_AC(1, ULL) << 4) + ++#define MSR_FLUSH_CMD 0x0000010b ++#define FLUSH_CMD_L1D (_AC(1, ULL) << 0) ++ + /* Intel MSRs. Some also available on other CPUs */ + #define MSR_IA32_PERFCTR0 0x000000c1 + #define MSR_IA32_A_PERFCTR0 0x000004c1 +diff --git a/xen/include/asm-x86/msr.h b/xen/include/asm-x86/msr.h +index f14f265aa5..afbeb7f155 100644 +--- a/xen/include/asm-x86/msr.h ++++ b/xen/include/asm-x86/msr.h +@@ -241,7 +241,7 @@ static inline void write_efer(uint64_t val) + wrmsrl(MSR_EFER, val); + } + +-DECLARE_PER_CPU(u32, ler_msr); ++extern unsigned int ler_msr; + + DECLARE_PER_CPU(uint32_t, tsc_aux); + +diff --git a/xen/include/asm-x86/paging.h b/xen/include/asm-x86/paging.h +index f0085511c7..f440e3e53c 100644 +--- a/xen/include/asm-x86/paging.h ++++ b/xen/include/asm-x86/paging.h +@@ -37,11 +37,14 @@ + + #define PG_SH_shift 20 + #define PG_HAP_shift 21 ++#define PG_SHF_shift 22 + /* We're in one of the shadow modes */ + #ifdef CONFIG_SHADOW_PAGING + #define PG_SH_enable (1U << PG_SH_shift) ++#define PG_SH_forced (1U << PG_SHF_shift) + #else + #define PG_SH_enable 0 ++#define PG_SH_forced 0 + #endif + #define PG_HAP_enable (1U << PG_HAP_shift) + +@@ -62,6 +65,7 @@ + + #define paging_mode_enabled(_d) (!!(_d)->arch.paging.mode) + #define paging_mode_shadow(_d) (!!((_d)->arch.paging.mode & PG_SH_enable)) ++#define paging_mode_sh_forced(_d) (!!((_d)->arch.paging.mode & PG_SH_forced)) + #define paging_mode_hap(_d) (!!((_d)->arch.paging.mode & PG_HAP_enable)) + + #define paging_mode_refcounts(_d) (!!((_d)->arch.paging.mode & PG_refcounts)) +diff --git a/xen/include/asm-x86/processor.h b/xen/include/asm-x86/processor.h +index 9924cdf1f3..2bd9e69684 100644 +--- a/xen/include/asm-x86/processor.h ++++ b/xen/include/asm-x86/processor.h +@@ -337,12 +337,6 @@ static always_inline void set_in_cr4 (unsigned long mask) + write_cr4(read_cr4() | mask); + } + +-static always_inline void clear_in_cr4 (unsigned long mask) +-{ +- mmu_cr4_features &= ~mask; +- write_cr4(read_cr4() & ~mask); +-} +- + static inline unsigned int read_pkru(void) + { + unsigned int pkru; +diff --git a/xen/include/asm-x86/setup.h b/xen/include/asm-x86/setup.h +index 19232afa01..c09a5ff381 100644 +--- a/xen/include/asm-x86/setup.h ++++ b/xen/include/asm-x86/setup.h +@@ -66,6 +66,8 @@ extern uint8_t kbd_shift_flags; + extern unsigned long highmem_start; + #endif + ++extern int8_t opt_smt; ++ + #ifdef CONFIG_SHADOW_PAGING + extern bool opt_dom0_shadow; + #else +diff --git a/xen/include/asm-x86/shadow.h b/xen/include/asm-x86/shadow.h +index 94a34fd16a..f40f411871 100644 +--- a/xen/include/asm-x86/shadow.h ++++ b/xen/include/asm-x86/shadow.h +@@ -29,6 +29,7 @@ + #include <asm/flushtlb.h> + #include <asm/paging.h> + #include <asm/p2m.h> ++#include <asm/spec_ctrl.h> + + /***************************************************************************** + * Macros to tell which shadow paging mode a domain is in*/ +@@ -115,6 +116,131 @@ static inline int shadow_domctl(struct domain *d, + + #endif /* CONFIG_SHADOW_PAGING */ + ++/* ++ * Mitigations for L1TF / CVE-2018-3620 for PV guests. ++ * ++ * We cannot alter an architecturally-legitimate PTE which a PV guest has ++ * chosen to write, as traditional paged-out metadata is L1TF-vulnerable. ++ * What we can do is force a PV guest which writes a vulnerable PTE into ++ * shadow mode, so Xen controls the pagetables which are reachable by the CPU ++ * pagewalk. ++ * ++ * The core of the L1TF vulnerability is that the address bits of the PTE ++ * (accounting for PSE and factoring in the level-relevant part of the linear ++ * access) are sent for an L1D lookup (to retrieve the next-level PTE, or ++ * eventual memory address) before the Present or reserved bits (which would ++ * cause a terminal fault) are accounted for. If an L1D hit occurs, the ++ * resulting data is available for potentially dependent instructions. ++ * ++ * For Present PTEs, the PV type-count safety logic ensures that the address ++ * bits always point at a guest-accessible frame, which is safe WRT L1TF from ++ * Xen's point of view. In practice, a PV guest should be unable to set any ++ * reserved bits, so should be unable to create any present L1TF-vulnerable ++ * PTEs at all. ++ * ++ * Therefore, these safety checks apply to Not-Present PTEs only, where ++ * traditionally, Xen would have let the guest write any value it chose. ++ * ++ * The all-zero PTE potentially leaks mfn 0. All software on the system is ++ * expected to cooperate and not put any secrets there. In a Xen system, ++ * neither Xen nor dom0 are expected to touch mfn 0, as it typically contains ++ * the real mode IVT and Bios Data Area. Therefore, mfn 0 is considered safe. ++ * ++ * Any PTE whose address is higher than the maximum cacheable address is safe, ++ * as it won't get an L1D hit. ++ * ++ * Speculative superpages also need accounting for, as PSE is considered ++ * irrespective of Present. We disallow PSE being set, as it allows an ++ * attacker to leak 2M or 1G of data starting from mfn 0. Also, because of ++ * recursive/linear pagetables, we must consider PSE even at L4, as hardware ++ * will interpret an L4e as an L3e during a recursive walk. ++ */ ++ ++static inline bool is_l1tf_safe_maddr(intpte_t pte) ++{ ++ paddr_t maddr = pte & l1tf_addr_mask; ++ ++ return maddr == 0 || maddr >= l1tf_safe_maddr; ++} ++ ++static inline bool pv_l1tf_check_pte(struct domain *d, unsigned int level, ++ intpte_t pte) ++{ ++ ASSERT(is_pv_domain(d)); ++ ASSERT(!(pte & _PAGE_PRESENT)); ++ ++ if ( d->arch.pv_domain.check_l1tf && !paging_mode_sh_forced(d) && ++ (((level > 1) && (pte & _PAGE_PSE)) || !is_l1tf_safe_maddr(pte)) ) ++ { ++#ifdef CONFIG_SHADOW_PAGING ++ struct tasklet *t = &d->arch.paging.shadow.pv_l1tf_tasklet; ++ ++ printk(XENLOG_G_WARNING ++ "d%d L1TF-vulnerable L%ue %016"PRIx64" - Shadowing\n", ++ d->domain_id, level, pte); ++ /* ++ * Safety consideration for accessing tasklet.scheduled_on without the ++ * tasklet lock. This is a singleshot tasklet with the side effect of ++ * setting PG_SH_forced (checked just above). Multiple vcpus can race ++ * to schedule the tasklet, but if we observe it scheduled anywhere, ++ * that is good enough. ++ */ ++ smp_rmb(); ++ if ( !tasklet_is_scheduled(t) ) ++ tasklet_schedule(t); ++#else ++ printk(XENLOG_G_ERR ++ "d%d L1TF-vulnerable L%ue %016"PRIx64" - Crashing\n", ++ d->domain_id, level, pte); ++ domain_crash(d); ++#endif ++ return true; ++ } ++ ++ return false; ++} ++ ++static inline bool pv_l1tf_check_l1e(struct domain *d, l1_pgentry_t l1e) ++{ ++ return pv_l1tf_check_pte(d, 1, l1e.l1); ++} ++ ++static inline bool pv_l1tf_check_l2e(struct domain *d, l2_pgentry_t l2e) ++{ ++ return pv_l1tf_check_pte(d, 2, l2e.l2); ++} ++ ++static inline bool pv_l1tf_check_l3e(struct domain *d, l3_pgentry_t l3e) ++{ ++ return pv_l1tf_check_pte(d, 3, l3e.l3); ++} ++ ++static inline bool pv_l1tf_check_l4e(struct domain *d, l4_pgentry_t l4e) ++{ ++ return pv_l1tf_check_pte(d, 4, l4e.l4); ++} ++ ++void pv_l1tf_tasklet(unsigned long data); ++ ++static inline void pv_l1tf_domain_init(struct domain *d) ++{ ++ d->arch.pv_domain.check_l1tf = ++ opt_pv_l1tf & (is_hardware_domain(d) ++ ? OPT_PV_L1TF_DOM0 : OPT_PV_L1TF_DOMU); ++ ++#if defined(CONFIG_SHADOW_PAGING) && defined(CONFIG_PV) ++ tasklet_init(&d->arch.paging.shadow.pv_l1tf_tasklet, ++ pv_l1tf_tasklet, (unsigned long)d); ++#endif ++} ++ ++static inline void pv_l1tf_domain_destroy(struct domain *d) ++{ ++#if defined(CONFIG_SHADOW_PAGING) && defined(CONFIG_PV) ++ tasklet_kill(&d->arch.paging.shadow.pv_l1tf_tasklet); ++#endif ++} ++ + /* Remove all shadows of the guest mfn. */ + static inline void shadow_remove_all_shadows(struct domain *d, mfn_t gmfn) + { +diff --git a/xen/include/asm-x86/smp.h b/xen/include/asm-x86/smp.h +index 4e5f673fec..09c55458df 100644 +--- a/xen/include/asm-x86/smp.h ++++ b/xen/include/asm-x86/smp.h +@@ -26,6 +26,8 @@ DECLARE_PER_CPU(cpumask_var_t, cpu_sibling_mask); + DECLARE_PER_CPU(cpumask_var_t, cpu_core_mask); + DECLARE_PER_CPU(cpumask_var_t, scratch_cpumask); + ++extern bool park_offline_cpus; ++ + void smp_send_nmi_allbutself(void); + + void send_IPI_mask(const cpumask_t *, int vector); +diff --git a/xen/include/asm-x86/spec_ctrl.h b/xen/include/asm-x86/spec_ctrl.h +index 5b40afbab0..8f8aad40bb 100644 +--- a/xen/include/asm-x86/spec_ctrl.h ++++ b/xen/include/asm-x86/spec_ctrl.h +@@ -29,15 +29,27 @@ void init_speculation_mitigations(void); + extern bool opt_ibpb; + extern bool opt_ssbd; + extern int8_t opt_eager_fpu; ++extern int8_t opt_l1d_flush; + + extern bool bsp_delay_spec_ctrl; + extern uint8_t default_xen_spec_ctrl; + extern uint8_t default_spec_ctrl_flags; + +-extern uint8_t opt_xpti; ++extern int8_t opt_xpti; + #define OPT_XPTI_DOM0 0x01 + #define OPT_XPTI_DOMU 0x02 + ++extern int8_t opt_pv_l1tf; ++#define OPT_PV_L1TF_DOM0 0x01 ++#define OPT_PV_L1TF_DOMU 0x02 ++ ++/* ++ * The L1D address mask, which might be wider than reported in CPUID, and the ++ * system physical address above which there are believed to be no cacheable ++ * memory regions, thus unable to leak data via the L1TF vulnerability. ++ */ ++extern paddr_t l1tf_addr_mask, l1tf_safe_maddr; ++ + static inline void init_shadow_spec_ctrl_state(void) + { + struct cpu_info *info = get_cpu_info(); +diff --git a/xen/include/asm-x86/system.h b/xen/include/asm-x86/system.h +index 43fb6fe489..483cd20afd 100644 +--- a/xen/include/asm-x86/system.h ++++ b/xen/include/asm-x86/system.h +@@ -221,6 +221,30 @@ static always_inline unsigned long __xadd( + #define set_mb(var, value) do { xchg(&var, value); } while (0) + #define set_wmb(var, value) do { var = value; smp_wmb(); } while (0) + ++/** ++ * array_index_mask_nospec() - generate a mask that is ~0UL when the ++ * bounds check succeeds and 0 otherwise ++ * @index: array element index ++ * @size: number of elements in array ++ * ++ * Returns: ++ * 0 - (index < size) ++ */ ++static inline unsigned long array_index_mask_nospec(unsigned long index, ++ unsigned long size) ++{ ++ unsigned long mask; ++ ++ asm volatile ( "cmp %[size], %[index]; sbb %[mask], %[mask];" ++ : [mask] "=r" (mask) ++ : [size] "g" (size), [index] "r" (index) ); ++ ++ return mask; ++} ++ ++/* Override default implementation in nospec.h. */ ++#define array_index_mask_nospec array_index_mask_nospec ++ + #define local_irq_disable() asm volatile ( "cli" : : : "memory" ) + #define local_irq_enable() asm volatile ( "sti" : : : "memory" ) + +diff --git a/xen/include/asm-x86/xstate.h b/xen/include/asm-x86/xstate.h +index 86a4a1f75c..47f602b855 100644 +--- a/xen/include/asm-x86/xstate.h ++++ b/xen/include/asm-x86/xstate.h +@@ -97,8 +97,9 @@ void xsave(struct vcpu *v, uint64_t mask); + void xrstor(struct vcpu *v, uint64_t mask); + void xstate_set_init(uint64_t mask); + bool xsave_enabled(const struct vcpu *v); +-int __must_check validate_xstate(u64 xcr0, u64 xcr0_accum, +- const struct xsave_hdr *); ++int __must_check validate_xstate(const struct domain *d, ++ uint64_t xcr0, uint64_t xcr0_accum, ++ const struct xsave_hdr *hdr); + int __must_check handle_xsetbv(u32 index, u64 new_bv); + void expand_xsave_states(struct vcpu *v, void *dest, unsigned int size); + void compress_xsave_states(struct vcpu *v, const void *src, unsigned int size); +diff --git a/xen/include/public/arch-x86/cpufeatureset.h b/xen/include/public/arch-x86/cpufeatureset.h +index f1a5ed93e0..6c82816fd3 100644 +--- a/xen/include/public/arch-x86/cpufeatureset.h ++++ b/xen/include/public/arch-x86/cpufeatureset.h +@@ -244,6 +244,7 @@ XEN_CPUFEATURE(AVX512_4VNNIW, 9*32+ 2) /*A AVX512 Neural Network Instructions * + XEN_CPUFEATURE(AVX512_4FMAPS, 9*32+ 3) /*A AVX512 Multiply Accumulation Single Precision */ + XEN_CPUFEATURE(IBRSB, 9*32+26) /*A IBRS and IBPB support (used by Intel) */ + XEN_CPUFEATURE(STIBP, 9*32+27) /*A STIBP */ ++XEN_CPUFEATURE(L1D_FLUSH, 9*32+28) /*S MSR_FLUSH_CMD and L1D flush. */ + XEN_CPUFEATURE(ARCH_CAPS, 9*32+29) /* IA32_ARCH_CAPABILITIES MSR */ + XEN_CPUFEATURE(SSBD, 9*32+31) /*A MSR_SPEC_CTRL.SSBD available */ + +diff --git a/xen/include/xen/compiler.h b/xen/include/xen/compiler.h +index 533a8ea0f3..a7e05681c9 100644 +--- a/xen/include/xen/compiler.h ++++ b/xen/include/xen/compiler.h +@@ -81,6 +81,9 @@ + #pragma GCC visibility push(hidden) + #endif + ++/* Make the optimizer believe the variable can be manipulated arbitrarily. */ ++#define OPTIMIZER_HIDE_VAR(var) __asm__ ( "" : "+g" (var) ) ++ + /* This macro obfuscates arithmetic on a variable address so that gcc + shouldn't recognize the original var, and make assumptions about it */ + /* +diff --git a/xen/include/xen/cpu.h b/xen/include/xen/cpu.h +index ffefc09f8e..2fe3ec05d8 100644 +--- a/xen/include/xen/cpu.h ++++ b/xen/include/xen/cpu.h +@@ -47,6 +47,8 @@ void register_cpu_notifier(struct notifier_block *nb); + #define CPU_DYING (0x0007 | NOTIFY_REVERSE) + /* CPU_DEAD: CPU is dead. */ + #define CPU_DEAD (0x0008 | NOTIFY_REVERSE) ++/* CPU_REMOVE: CPU was removed. */ ++#define CPU_REMOVE (0x0009 | NOTIFY_REVERSE) + + /* Perform CPU hotplug. May return -EAGAIN. */ + int cpu_down(unsigned int cpu); +diff --git a/xen/include/xen/cpumask.h b/xen/include/xen/cpumask.h +index 42340a098e..4a11bcc3f3 100644 +--- a/xen/include/xen/cpumask.h ++++ b/xen/include/xen/cpumask.h +@@ -351,16 +351,35 @@ static inline bool_t alloc_cpumask_var(cpumask_var_t *mask) + return *mask != NULL; + } + ++static inline bool cond_alloc_cpumask_var(cpumask_var_t *mask) ++{ ++ if (*mask == NULL) ++ *mask = _xmalloc(nr_cpumask_bits / 8, sizeof(long)); ++ return *mask != NULL; ++} ++ + static inline bool_t zalloc_cpumask_var(cpumask_var_t *mask) + { + *(void **)mask = _xzalloc(nr_cpumask_bits / 8, sizeof(long)); + return *mask != NULL; + } + ++static inline bool cond_zalloc_cpumask_var(cpumask_var_t *mask) ++{ ++ if (*mask == NULL) ++ *mask = _xzalloc(nr_cpumask_bits / 8, sizeof(long)); ++ else ++ cpumask_clear(*mask); ++ return *mask != NULL; ++} ++ + static inline void free_cpumask_var(cpumask_var_t mask) + { + xfree(mask); + } ++ ++/* Free an allocated mask, and zero the pointer to it. */ ++#define FREE_CPUMASK_VAR(m) XFREE(m) + #else + typedef cpumask_t cpumask_var_t[1]; + +@@ -368,16 +387,20 @@ static inline bool_t alloc_cpumask_var(cpumask_var_t *mask) + { + return 1; + } ++#define cond_alloc_cpumask_var alloc_cpumask_var + + static inline bool_t zalloc_cpumask_var(cpumask_var_t *mask) + { + cpumask_clear(*mask); + return 1; + } ++#define cond_zalloc_cpumask_var zalloc_cpumask_var + + static inline void free_cpumask_var(cpumask_var_t mask) + { + } ++ ++#define FREE_CPUMASK_VAR(m) free_cpumask_var(m) + #endif + + #if NR_CPUS > 1 +diff --git a/xen/include/xen/list.h b/xen/include/xen/list.h +index fa07d720ee..1387abb211 100644 +--- a/xen/include/xen/list.h ++++ b/xen/include/xen/list.h +@@ -51,6 +51,11 @@ static inline void INIT_LIST_HEAD(struct list_head *list) + list->prev = list; + } + ++static inline bool list_head_is_null(const struct list_head *list) ++{ ++ return !list->next && !list->prev; ++} ++ + /* + * Insert a new entry between two known consecutive entries. + * +diff --git a/xen/include/xen/mm.h b/xen/include/xen/mm.h +index e928551c91..24654e8e22 100644 +--- a/xen/include/xen/mm.h ++++ b/xen/include/xen/mm.h +@@ -162,6 +162,14 @@ void free_xenheap_pages(void *v, unsigned int order); + bool scrub_free_pages(void); + #define alloc_xenheap_page() (alloc_xenheap_pages(0,0)) + #define free_xenheap_page(v) (free_xenheap_pages(v,0)) ++ ++/* Free an allocation, and zero the pointer to it. */ ++#define FREE_XENHEAP_PAGES(p, o) do { \ ++ free_xenheap_pages(p, o); \ ++ (p) = NULL; \ ++} while ( false ) ++#define FREE_XENHEAP_PAGE(p) FREE_XENHEAP_PAGES(p, 0) ++ + /* Map machine page range in Xen virtual address space. */ + int map_pages_to_xen( + unsigned long virt, +diff --git a/xen/include/xen/nospec.h b/xen/include/xen/nospec.h +new file mode 100644 +index 0000000000..48793996e8 +--- /dev/null ++++ b/xen/include/xen/nospec.h +@@ -0,0 +1,70 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* Copyright(c) 2018 Linus Torvalds. All rights reserved. */ ++/* Copyright(c) 2018 Alexei Starovoitov. All rights reserved. */ ++/* Copyright(c) 2018 Intel Corporation. All rights reserved. */ ++/* Copyright(c) 2018 Citrix Systems R&D Ltd. All rights reserved. */ ++ ++#ifndef XEN_NOSPEC_H ++#define XEN_NOSPEC_H ++ ++#include <asm/system.h> ++ ++/** ++ * array_index_mask_nospec() - generate a ~0 mask when index < size, 0 otherwise ++ * @index: array element index ++ * @size: number of elements in array ++ * ++ * When @index is out of bounds (@index >= @size), the sign bit will be ++ * set. Extend the sign bit to all bits and invert, giving a result of ++ * zero for an out of bounds index, or ~0 if within bounds [0, @size). ++ */ ++#ifndef array_index_mask_nospec ++static inline unsigned long array_index_mask_nospec(unsigned long index, ++ unsigned long size) ++{ ++ /* ++ * Always calculate and emit the mask even if the compiler ++ * thinks the mask is not needed. The compiler does not take ++ * into account the value of @index under speculation. ++ */ ++ OPTIMIZER_HIDE_VAR(index); ++ return ~(long)(index | (size - 1UL - index)) >> (BITS_PER_LONG - 1); ++} ++#endif ++ ++/* ++ * array_index_nospec - sanitize an array index after a bounds check ++ * ++ * For a code sequence like: ++ * ++ * if (index < size) { ++ * index = array_index_nospec(index, size); ++ * val = array[index]; ++ * } ++ * ++ * ...if the CPU speculates past the bounds check then ++ * array_index_nospec() will clamp the index within the range of [0, ++ * size). ++ */ ++#define array_index_nospec(index, size) \ ++({ \ ++ typeof(index) _i = (index); \ ++ typeof(size) _s = (size); \ ++ unsigned long _mask = array_index_mask_nospec(_i, _s); \ ++ \ ++ BUILD_BUG_ON(sizeof(_i) > sizeof(long)); \ ++ BUILD_BUG_ON(sizeof(_s) > sizeof(long)); \ ++ \ ++ (typeof(_i)) (_i & _mask); \ ++}) ++ ++#endif /* XEN_NOSPEC_H */ ++ ++/* ++ * Local variables: ++ * mode: C ++ * c-file-style: "BSD" ++ * c-basic-offset: 4 ++ * indent-tabs-mode: nil ++ * End: ++ */ +diff --git a/xen/include/xen/sched.h b/xen/include/xen/sched.h +index 99d2af2e1f..e79d5a36ca 100644 +--- a/xen/include/xen/sched.h ++++ b/xen/include/xen/sched.h +@@ -788,7 +788,7 @@ static inline struct domain *next_domain_in_cpupool( + #define _VPF_parked 8 + #define VPF_parked (1UL<<_VPF_parked) + +-static inline int vcpu_runnable(struct vcpu *v) ++static inline bool vcpu_runnable(const struct vcpu *v) + { + return !(v->pause_flags | + atomic_read(&v->pause_count) | +diff --git a/xen/include/xen/tasklet.h b/xen/include/xen/tasklet.h +index 23d69c738e..bc9ddace6d 100644 +--- a/xen/include/xen/tasklet.h ++++ b/xen/include/xen/tasklet.h +@@ -50,6 +50,11 @@ static inline bool tasklet_work_to_do(unsigned int cpu) + TASKLET_scheduled); + } + ++static inline bool tasklet_is_scheduled(const struct tasklet *t) ++{ ++ return t->scheduled_on != -1; ++} ++ + void tasklet_schedule_on_cpu(struct tasklet *t, unsigned int cpu); + void tasklet_schedule(struct tasklet *t); + void do_tasklet(void); +diff --git a/xen/include/xen/xmalloc.h b/xen/include/xen/xmalloc.h +index cc2673d8ae..9aa5edf593 100644 +--- a/xen/include/xen/xmalloc.h ++++ b/xen/include/xen/xmalloc.h +@@ -26,6 +26,12 @@ + /* Free any of the above. */ + extern void xfree(void *); + ++/* Free an allocation, and zero the pointer to it. */ ++#define XFREE(p) do { \ ++ xfree(p); \ ++ (p) = NULL; \ ++} while ( false ) ++ + /* Underlying functions */ + extern void *_xmalloc(unsigned long size, unsigned long align); + extern void *_xzalloc(unsigned long size, unsigned long align); |