Re: [Xen-devel] [PATCH v3 08/10] tools/libxc: Rework xc_cpuid_apply_policy() to use {get, set}_cpu_policy()

[Andrew Cooper <andrew.cooper3@xxxxxxxxxx>]

On 26/09/2019 09:04, Jan Beulich wrote:
> On 25.09.2019 20:11, Andrew Cooper wrote:
>> +int xc_cpuid_apply_policy(xc_interface *xch, uint32_t domid,
>> +                          const uint32_t *featureset, unsigned int 
>> nr_features)
>> +{
>> +    int rc;
>> +    xc_dominfo_t di;
>> +    unsigned int i, nr_leaves, nr_msrs;
>> +    xen_cpuid_leaf_t *leaves = NULL;
>> +    struct cpuid_policy *p = NULL;
>> +    uint32_t err_leaf = -1, err_subleaf = -1, err_msr = -1;
>> +
>> +    if ( xc_domain_getinfo(xch, domid, 1, &di) != 1 ||
>> +         di.domid != domid )
>> +    {
>> +        ERROR("Failed to obtain d%d info", domid);
>> +        rc = -ESRCH;
>> +        goto out;
>> +    }
>> +
>> +    rc = xc_get_cpu_policy_size(xch, &nr_leaves, &nr_msrs);
>> +    if ( rc )
>> +    {
>> +        PERROR("Failed to obtain policy info size");
>> +        rc = -errno;
>> +        goto out;
>> +    }
>> +
>> +    rc = -ENOMEM;
>> +    if ( (leaves = calloc(nr_leaves, sizeof(*leaves))) == NULL ||
>> +         (p = calloc(1, sizeof(*p))) == NULL )
>> +        goto out;
>> +
>> +    /* Get the domain's default policy. */
>> +    nr_msrs = 0;
>> +    rc = xc_get_system_cpu_policy(xch, di.hvm ? 
>> XEN_SYSCTL_cpu_policy_hvm_default
>> +                                              : 
>> XEN_SYSCTL_cpu_policy_pv_default,
>> +                                  &nr_leaves, leaves, &nr_msrs, NULL);
>> +    if ( rc )
>> +    {
>> +        PERROR("Failed to obtain %s default policy", di.hvm ? "hvm" : "pv");
>> +        rc = -errno;
>> +        goto out;
>> +    }
>> +
>> +    rc = x86_cpuid_copy_from_buffer(p, leaves, nr_leaves,
>> +                                    &err_leaf, &err_subleaf);
>> +    if ( rc )
>> +    {
>> +        ERROR("Failed to deserialise CPUID (err leaf %#x, subleaf %#x) (%d 
>> = %s)",
>> +              err_leaf, err_subleaf, -rc, strerror(-rc));
>> +        goto out;
>> +    }
>> +
>> +    if ( featureset )
>> +    {
>> +        uint32_t disabled_features[FEATURESET_NR_ENTRIES],
>> +            feat[FEATURESET_NR_ENTRIES] = {};
>> +        static const uint32_t deep_features[] = INIT_DEEP_FEATURES;
>> +        unsigned int i, b;
>> +
>> +        /*
>> +         * The user supplied featureset may be shorter or longer than
>> +         * FEATURESET_NR_ENTRIES.  Shorter is fine, and we will zero-extend.
>> +         * Longer is fine, so long as it only padded with zeros.
>> +         */
>> +        unsigned int user_len = min(FEATURESET_NR_ENTRIES + 0u, 
>> nr_features);
>> +
>> +        /* Check for truncated set bits. */
>> +        rc = -EOPNOTSUPP;
>> +        for ( i = user_len; i < nr_features; ++i )
>> +            if ( featureset[i] != 0 )
>> +                goto out;
>> +
>> +        memcpy(feat, featureset, sizeof(*featureset) * user_len);
>> +
>> +        /* Disable deep dependencies of disabled features. */
>> +        for ( i = 0; i < ARRAY_SIZE(disabled_features); ++i )
>> +            disabled_features[i] = ~feat[i] & deep_features[i];
>> +
>> +        for ( b = 0; b < sizeof(disabled_features) * CHAR_BIT; ++b )
>> +        {
>> +            const uint32_t *dfs;
>> +
>> +            if ( !test_bit(b, disabled_features) ||
>> +                 !(dfs = x86_cpuid_lookup_deep_deps(b)) )
>> +                continue;
>> +
>> +            for ( i = 0; i < ARRAY_SIZE(disabled_features); ++i )
>> +            {
>> +                feat[i] &= ~dfs[i];
>> +                disabled_features[i] &= ~dfs[i];
>> +            }
>> +        }
>> +
>> +        cpuid_featureset_to_policy(feat, p);
>> +    }
>> +
>> +    if ( !di.hvm )
>> +    {
>> +        uint32_t host_featureset[FEATURESET_NR_ENTRIES] = {};
>> +        uint32_t len = ARRAY_SIZE(host_featureset);
>> +
>> +        rc = xc_get_cpu_featureset(xch, XEN_SYSCTL_cpu_featureset_host,
>> +                                   &len, host_featureset);
>> +        if ( rc )
>> +        {
>> +            /* Tolerate "buffer too small", as we've got the bits we need. 
>> */
>> +            if ( errno == ENOBUFS )
>> +                rc = 0;
>> +            else
>> +            {
>> +                PERROR("Failed to obtain host featureset");
>> +                rc = -errno;
>> +                goto out;
>> +            }
>> +        }
>> +
>> +        /*
>> +         * On hardware without CPUID Faulting, PV guests see real topology.
>> +         * As a consequence, they also need to see the host htt/cmp fields.
>> +         */
>> +        p->basic.htt       = test_bit(X86_FEATURE_HTT, host_featureset);
>> +        p->extd.cmp_legacy = test_bit(X86_FEATURE_CMP_LEGACY, 
>> host_featureset);
>> +    }
>> +    else
>> +    {
>> +        /*
>> +         * Topology for HVM guests is entirely controlled by Xen.  For now, 
>> we
>> +         * hardcode APIC_ID = vcpu_id * 2 to give the illusion of no SMT.
>> +         */
>> +        p->basic.htt = true;
>> +        p->extd.cmp_legacy = false;
>> +
>> +        /*
>> +         * EBX[23:16] is Maximum Logical Processors Per Package.
>> +         * Update to reflect vLAPIC_ID = vCPU_ID * 2, but make sure to avoid
>> +         * overflow.
>> +         */
>> +        if ( !(p->basic.lppp & 0x80) )
>> +            p->basic.lppp *= 2;
> I think you want to start the comment with "Leaf 1 EBX[23:16] ...",
> as p->basic covers all basic leaves.
>
> Additionally, while using masking instead of a relational operator
> is correct here, ...
>
>> +        switch ( p->x86_vendor )
>> +        {
>> +        case X86_VENDOR_INTEL:
>> +            for ( i = 0; (p->cache.subleaf[i].type &&
>> +                          i < ARRAY_SIZE(p->cache.raw)); ++i )
>> +            {
>> +                p->cache.subleaf[i].cores_per_package =
>> +                    (p->cache.subleaf[i].cores_per_package << 1) | 1;
>> +                p->cache.subleaf[i].threads_per_cache = 0;
>> +            }
>> +            break;
>> +
>> +        case X86_VENDOR_AMD:
>> +        case X86_VENDOR_HYGON:
>> +            /*
>> +             * ECX[15:12] is ApicIdCoreSize.
>> +             * ECX[7:0] is NumberOfCores (minus one).
>> +             * Update to reflect vLAPIC_ID = vCPU_ID * 2.  But avoid
>> +             * - overflow,
>> +             * - going out of sync with leaf 1 EBX[23:16],
>> +             * - incrementing ApicIdCoreSize when it's zero (which changes 
>> the
>> +             *   meaning of bits 7:0).
>> +             */
>> +            if ( !(p->extd.nc & 0x80) )
> ... it isn't here, i.e. this isn't a correct transformation of the
> recent change for Rome): If the value is 0x7f here, the value in
> leaf 1 would be 0x80. An adjustment, however, needs to be done
> either to both leaves, or to none of them, to keep the values in
> sufficient sync (and I think you'd break Rome again otherwise, as
> p->extd.nc _is_ 0x7f there). Hence the "(regs[2] & 0xffu) < 0x7fu"
> check in my recent patch.

Urgh yes - I questioned this when doing the rebase a second time.  I'll
revert to the logic you had.

>
> Like above I think you want to name the (extended) leaf in the
> comment, as p->extd similarly covers all extended leaves.

Done.

~Andrew

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxxx
https://lists.xenproject.org/mailman/listinfo/xen-devel