linux-kernel - Re: [PATCH v5 09/10] x86/hyper-v: support extended CPU ranges for TLB flush hypercalls

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <CAHp75VeR155gFD4L8fG-XxkcZNZOkmvPtuEdHNYBVWi_QoJ6MQ@mail.gmail.com>
Date:   Tue, 30 May 2017 20:02:58 +0300
From:   Andy Shevchenko <andy.shevchenko@...il.com>
To:     Vitaly Kuznetsov <vkuznets@...hat.com>
Cc:     "x86@...nel.org" <x86@...nel.org>, devel@...uxdriverproject.org,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
        "K. Y. Srinivasan" <kys@...rosoft.com>,
        Haiyang Zhang <haiyangz@...rosoft.com>,
        Stephen Hemminger <sthemmin@...rosoft.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...hat.com>,
        "H. Peter Anvin" <hpa@...or.com>,
        Steven Rostedt <rostedt@...dmis.org>,
        Jork Loeser <Jork.Loeser@...rosoft.com>,
        Simon Xiao <sixiao@...rosoft.com>,
        Andy Lutomirski <luto@...nel.org>
Subject: Re: [PATCH v5 09/10] x86/hyper-v: support extended CPU ranges for TLB
 flush hypercalls

On Tue, May 30, 2017 at 2:34 PM, Vitaly Kuznetsov <vkuznets@...hat.com> wrote:
> Hyper-V hosts may support more than 64 vCPUs, we need to use
> HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX/LIST_EX hypercalls in this
> case.

> +/* HvFlushVirtualAddressSpaceEx, HvFlushVirtualAddressListEx hypercalls */
> +struct hv_flush_pcpu_ex {
> +       __u64 address_space;
> +       __u64 flags;
> +       struct {
> +               __u64 format;
> +               __u64 valid_bank_mask;
> +               __u64 bank_contents[];
> +       } hv_vp_set;
> +       __u64 gva_list[];
> +};

Same question about use of uXX vs __uXX types.

> +static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
> +                                      struct mm_struct *mm,
> +                                      unsigned long start,
> +                                      unsigned long end)
> +{
> +       struct hv_flush_pcpu_ex *flush;
> +       unsigned long cur, flags;
> +       u64 status = U64_MAX;
> +       int nr_bank = 0, max_gvas, gva_n;
> +
> +       if (!pcpu_flush_ex || !hv_hypercall_pg)
> +               goto do_native;
> +
> +       if (cpumask_empty(cpus))
> +               return;
> +
> +       local_irq_save(flags);
> +
> +       flush = this_cpu_ptr(pcpu_flush_ex);
> +
> +       if (mm) {
> +               flush->address_space = virt_to_phys(mm->pgd);

(u64), phys_addr_t is arch-dependent.

> +               flush->flags = 0;
> +       } else {
> +               flush->address_space = 0;
> +               flush->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES;
> +       }
> +
> +       flush->hv_vp_set.valid_bank_mask = 0;
> +
> +       if (cpumask_equal(cpus, cpu_present_mask)) {
> +               flush->hv_vp_set.format = HV_GENERIC_SET_ALL;
> +               flush->flags |= HV_FLUSH_ALL_PROCESSORS;
> +       } else {
> +               flush->hv_vp_set.format = HV_GENERIC_SET_SPARCE_4K;
> +               nr_bank = cpumask_to_vp_set(flush, cpus);
> +       }
> +
> +       /*
> +        * We can flush not more than max_gvas with one hypercall. Flush the
> +        * whole address space if we were asked to do more.
> +        */
> +       max_gvas = (PAGE_SIZE - sizeof(*flush) - nr_bank*8) / 8;
> +
> +       if (end == TLB_FLUSH_ALL) {
> +               flush->flags |= HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY;
> +               status = hv_do_rep_hypercall(
> +                       HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX,
> +                       0, nr_bank + 2, flush, NULL);
> +       } else if (end && ((end - start)/HV_TLB_FLUSH_UNIT) > max_gvas) {
> +               status = hv_do_rep_hypercall(
> +                       HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX,
> +                       0, nr_bank + 2, flush, NULL);
> +       } else {
> +               cur = start;
> +               gva_n = nr_bank;
> +               do {
> +                       flush->gva_list[gva_n] = cur & PAGE_MASK;
> +                       /*
> +                        * Lower 12 bits encode the number of additional
> +                        * pages to flush (in addition to the 'cur' page).
> +                        */
> +                       if (end >= cur + HV_TLB_FLUSH_UNIT)
> +                               flush->gva_list[gva_n] |= ~PAGE_MASK;
> +                       else if (end > cur)
> +                               flush->gva_list[gva_n] |=
> +                                       (end - cur - 1) >> PAGE_SHIFT;
> +
> +                       cur += HV_TLB_FLUSH_UNIT;
> +                       ++gva_n;

Same comments as per previous similar code.

Moreover, since it's similar, can it have some common code shared?

> +
> +               } while (cur < end);
> +
> +               status = hv_do_rep_hypercall(
> +                       HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX,
> +                       gva_n, nr_bank + 2, flush, NULL);
> +       }
> +
> +       local_irq_restore(flags);
> +

> +       if (!(status & 0xffff))

Magic.

-- 
With Best Regards,
Andy Shevchenko