search for: this_cpu_read

...+490,9 @@ DEFINE_IDTENTRY_RAW(exc_nmi) this_cpu_write(nmi_cr2, read_cr2()); nmi_restart: + /* Needs to happen before DR7 is accessed */ + sev_es_ist_enter(regs); + this_cpu_write(nmi_dr7, local_db_save()); nmi_enter(); @@ -502,6 +506,8 @@ DEFINE_IDTENTRY_RAW(exc_nmi) local_db_restore(this_cpu_read(nmi_dr7)); + sev_es_ist_exit(); + if (unlikely(this_cpu_read(nmi_cr2) != read_cr2())) write_cr2(this_cpu_read(nmi_cr2)); if (this_cpu_dec_return(nmi_state)) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index d415368f16ec..2a7cc72db1d5 100644 --- a/arch/x86/kernel/sev-es...

..._RAW(exc_nmi) this_cpu_write(nmi_cr2, read_cr2()); nmi_restart: + /* Needs to happen before DR7 is accessed */ + sev_es_ist_enter(regs); + this_cpu_write(nmi_dr7, local_db_save()); irq_state = idtentry_enter_nmi(regs); @@ -501,6 +505,8 @@ DEFINE_IDTENTRY_RAW(exc_nmi) local_db_restore(this_cpu_read(nmi_dr7)); + sev_es_ist_exit(); + if (unlikely(this_cpu_read(nmi_cr2) != read_cr2())) write_cr2(this_cpu_read(nmi_cr2)); if (this_cpu_dec_return(nmi_state)) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 64002d86a237..95831d103418 100644 --- a/arch/x86/kernel/sev-es...

...(nmi_cr2, read_cr2()); > nmi_restart: > > + /* Needs to happen before DR7 is accessed */ > + sev_es_ist_enter(regs); > + > this_cpu_write(nmi_dr7, local_db_save()); > > nmi_enter(); > @@ -502,6 +506,8 @@ DEFINE_IDTENTRY_RAW(exc_nmi) > > local_db_restore(this_cpu_read(nmi_dr7)); > > + sev_es_ist_exit(); > + > if (unlikely(this_cpu_read(nmi_cr2) != read_cr2())) > write_cr2(this_cpu_read(nmi_cr2)); > if (this_cpu_dec_return(nmi_state)) I really hate all this #VC stuff :-( So the above will make the NMI do 4 unconditional extra CALL+RET...

...(nmi_cr2, read_cr2()); > nmi_restart: > > + /* Needs to happen before DR7 is accessed */ > + sev_es_ist_enter(regs); > + > this_cpu_write(nmi_dr7, local_db_save()); > > nmi_enter(); > @@ -502,6 +506,8 @@ DEFINE_IDTENTRY_RAW(exc_nmi) > > local_db_restore(this_cpu_read(nmi_dr7)); > > + sev_es_ist_exit(); > + > if (unlikely(this_cpu_read(nmi_cr2) != read_cr2())) > write_cr2(this_cpu_read(nmi_cr2)); > if (this_cpu_dec_return(nmi_state)) I really hate all this #VC stuff :-( So the above will make the NMI do 4 unconditional extra CALL+RET...

On Tue, Aug 11, 2020 at 11:20:54AM +0200, peterz at infradead.org wrote: > On Tue, Aug 11, 2020 at 10:38:50AM +0200, J?rgen Gro? wrote: > > In case you don't want to do it I can send the patch for the Xen > > variants. > > I might've opened a whole new can of worms here. I'm not sure we > can/want to fix the entire fallout this release :/ > > Let me

On Tue, Aug 11, 2020 at 11:20:54AM +0200, peterz at infradead.org wrote: > On Tue, Aug 11, 2020 at 10:38:50AM +0200, J?rgen Gro? wrote: > > In case you don't want to do it I can send the patch for the Xen > > variants. > > I might've opened a whole new can of worms here. I'm not sure we > can/want to fix the entire fallout this release :/ > > Let me

...old * grow; + if (val > max) + val = max; + + return val; +} + +static unsigned int shrink_poll_ns(unsigned int old, unsigned int shrink) +{ + if (shrink == 0) + return 0; + + return old / shrink; +} + +static void kvm_idle_update_poll_duration(ktime_t idle) +{ + unsigned long poll_duration = this_cpu_read(poll_duration_ns); + + /* so far poll duration is based on nohz */ + if (idle == -1ULL) + return; + + if (poll_duration && idle > paravirt_poll_threshold_ns) + poll_duration = shrink_poll_ns(poll_duration, + paravirt_poll_shrink); + else if (poll_duration < paravirt_poll_...

...old * grow; + if (val > max) + val = max; + + return val; +} + +static unsigned int shrink_poll_ns(unsigned int old, unsigned int shrink) +{ + if (shrink == 0) + return 0; + + return old / shrink; +} + +static void kvm_idle_update_poll_duration(ktime_t idle) +{ + unsigned long poll_duration = this_cpu_read(poll_duration_ns); + + /* so far poll duration is based on nohz */ + if (idle == -1ULL) + return; + + if (poll_duration && idle > paravirt_poll_threshold_ns) + poll_duration = shrink_poll_ns(poll_duration, + paravirt_poll_shrink); + else if (poll_duration < paravirt_poll_...

...it(). This is needed when an NMI hits in the #VC handlers @@ -70,6 +87,53 @@ void sev_es_nmi_exit(void) tss->x86_tss.ist[IST_INDEX_VC] += VC_STACK_OFFSET; } +static struct ghcb *sev_es_get_ghcb(struct ghcb_state *state) +{ + struct sev_es_runtime_data *data; + struct ghcb *ghcb; + + data = this_cpu_read(runtime_data); + ghcb = &data->ghcb_page; + + if (unlikely(data->ghcb_active)) { + /* GHCB is already in use - save its contents */ + + if (unlikely(data->backup_ghcb_active)) + return NULL; + + /* Mark backup_ghcb active before writing to it */ + data->backup_ghcb_active = tr...

...cb, struct es_em_ctxt *ctxt, unsigned int bytes, bool read) { @@ -720,6 +744,61 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, return ret; } +static enum es_result vc_handle_dr7_write(struct ghcb *ghcb, + struct es_em_ctxt *ctxt) +{ + struct sev_es_runtime_data *data = this_cpu_read(runtime_data); + long val, *reg = vc_insn_get_rm(ctxt); + enum es_result ret; + + if (!reg) + return ES_DECODE_FAILED; + + val = *reg; + + /* Upper 32 bits must be written as zeroes */ + if (val >> 32) { + ctxt->fi.vector = X86_TRAP_GP; + ctxt->fi.error_code = 0; + return ES_EXCEPTI...

...DA_BITMAP_BITS)) > +#define XB_MAX_PATH (DIV_ROUND_UP(XB_INDEX_BITS, \ > + RADIX_TREE_MAP_SHIFT)) > +#define XB_PRELOAD_SIZE (XB_MAX_PATH * 2 - 1) > + > > ... > > +void xb_preload(gfp_t gfp) > +{ > + __radix_tree_preload(gfp, XB_PRELOAD_SIZE); > + if (!this_cpu_read(ida_bitmap)) { > + struct ida_bitmap *bitmap = kmalloc(sizeof(*bitmap), gfp); > + > + if (!bitmap) > + return; > + bitmap = this_cpu_cmpxchg(ida_bitmap, NULL, bitmap); > + kfree(bitmap); > + } > +} > +EXPORT_SYMBOL(xb_preload); Please document the exported API. It...

...DA_BITMAP_BITS)) > +#define XB_MAX_PATH (DIV_ROUND_UP(XB_INDEX_BITS, \ > + RADIX_TREE_MAP_SHIFT)) > +#define XB_PRELOAD_SIZE (XB_MAX_PATH * 2 - 1) > + > > ... > > +void xb_preload(gfp_t gfp) > +{ > + __radix_tree_preload(gfp, XB_PRELOAD_SIZE); > + if (!this_cpu_read(ida_bitmap)) { > + struct ida_bitmap *bitmap = kmalloc(sizeof(*bitmap), gfp); > + > + if (!bitmap) > + return; > + bitmap = this_cpu_cmpxchg(ida_bitmap, NULL, bitmap); > + kfree(bitmap); > + } > +} > +EXPORT_SYMBOL(xb_preload); Please document the exported API. It...

...+ enum tlb_flush_reason reason = TLB_REMOTE_SHOOTDOWN; + bool local = false; + + if (f->cpu == smp_processor_id()) { + local = true; + reason = (f->mm == NULL) ? TLB_LOCAL_SHOOTDOWN : TLB_LOCAL_MM_SHOOTDOWN; + } else { + inc_irq_stat(irq_tlb_count); + + if (f->mm && f->mm != this_cpu_read(cpu_tlbstate.loaded_mm)) + return; + + count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); + } + + flush_tlb_func_common(f, local, reason); +} + static bool tlb_is_not_lazy(int cpu) { return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu);

...+ enum tlb_flush_reason reason = TLB_REMOTE_SHOOTDOWN; + bool local = false; + + if (f->cpu == smp_processor_id()) { + local = true; + reason = (f->mm == NULL) ? TLB_LOCAL_SHOOTDOWN : TLB_LOCAL_MM_SHOOTDOWN; + } else { + inc_irq_stat(irq_tlb_count); + + if (f->mm && f->mm != this_cpu_read(cpu_tlbstate.loaded_mm)) + return; + + count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); + } + + flush_tlb_func_common(f, local, reason); +} + static bool tlb_is_not_lazy(int cpu) { return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu);

On Sat, Sep 30, 2017 at 12:05:52PM +0800, Wei Wang wrote: > +static inline void xb_set_page(struct virtio_balloon *vb, > + struct page *page, > + unsigned long *pfn_min, > + unsigned long *pfn_max) > +{ > + unsigned long pfn = page_to_pfn(page); > + > + *pfn_min = min(pfn, *pfn_min); > + *pfn_max = max(pfn, *pfn_max); > +

On Sat, Sep 30, 2017 at 12:05:52PM +0800, Wei Wang wrote: > +static inline void xb_set_page(struct virtio_balloon *vb, > + struct page *page, > + unsigned long *pfn_min, > + unsigned long *pfn_max) > +{ > + unsigned long pfn = page_to_pfn(page); > + > + *pfn_min = min(pfn, *pfn_min); > + *pfn_max = max(pfn, *pfn_max); > +

...> Then, kmalloc() is called with preemption disabled, isn't it? > But xb_set_page() calls xb_preload(GFP_KERNEL) which might sleep with > preemption disabled. Yes, I think that should not be expected, thanks. I plan to change it like this: bool xb_preload(gfp_t gfp) { if (!this_cpu_read(ida_bitmap)) { struct ida_bitmap *bitmap = kmalloc(sizeof(*bitmap), gfp); if (!bitmap) return false; bitmap = this_cpu_cmpxchg(ida_bitmap, NULL, bitmap); kfree(bitmap); } if (__radix_tre...

...;>> But xb_set_page() calls xb_preload(GFP_KERNEL) which might sleep with >>> preemption disabled. >> Yes, I think that should not be expected, thanks. >> >> I plan to change it like this: >> >> bool xb_preload(gfp_t gfp) >> { >> if (!this_cpu_read(ida_bitmap)) { >> struct ida_bitmap *bitmap = kmalloc(sizeof(*bitmap), gfp); >> >> if (!bitmap) >> return false; >> bitmap = this_cpu_cmpxchg(ida_bitmap, NULL, bitmap); >> kfr...

On Tue, Apr 28, 2020 at 05:17:04PM +0200, Joerg Roedel wrote: > +static enum es_result vc_handle_dr7_write(struct ghcb *ghcb, > + struct es_em_ctxt *ctxt) > +{ > + struct sev_es_runtime_data *data = this_cpu_read(runtime_data); > + long val, *reg = vc_insn_get_rm(ctxt); > + enum es_result ret; > + > + if (!reg) > + return ES_DECODE_FAILED; > + > + val = *reg; > + > + /* Upper 32 bits must be written as zeroes */ > + if (val >> 32) { > + ctxt->fi.vector = X86_TRAP_...

...HOOTDOWN; > + bool local = false; > + > + if (f->cpu == smp_processor_id()) { > + local = true; > + reason = (f->mm == NULL) ? TLB_LOCAL_SHOOTDOWN : TLB_LOCAL_MM_SHOOTDOWN; > + } else { > + inc_irq_stat(irq_tlb_count); > + > + if (f->mm && f->mm != this_cpu_read(cpu_tlbstate.loaded_mm)) > + return; > + > + count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); > + } > + > + flush_tlb_func_common(f, local, reason); > +} > + > static bool tlb_is_not_lazy(int cpu) > { > return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu); Nice!...