| Message ID | 20200924195058.362984-5-danielhb413@gmail.com |
|---|---|
| State | New |
| Headers | show |
| Series | pseries NUMA distance calculation | expand |
On Thu, Sep 24, 2020 at 04:50:56PM -0300, Daniel Henrique Barboza wrote: > This is the first guest visible change introduced in > spapr_numa.c. The previous settings of both reference-points > and maxdomains were too restrictive, but enough for the > existing associativity we're setting in the resources. > > We'll change that in the following patches, populating the > associativity arrays based on user input. For those changes > to be effective, reference-points and maxdomains must be > more flexible. After this patch, we'll have 4 distinct > levels of NUMA (0x4, 0x3, 0x2, 0x1) and maxdomains will > allow for any type of configuration the user intends to > do - under the scope and limitations of PAPR itself, of > course. > > Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Although.. > --- > hw/ppc/spapr_numa.c | 40 ++++++++++++++++++++++++++++++++-------- > 1 file changed, 32 insertions(+), 8 deletions(-) > > diff --git a/hw/ppc/spapr_numa.c b/hw/ppc/spapr_numa.c > index 990a5fce08..ea33439a15 100644 > --- a/hw/ppc/spapr_numa.c > +++ b/hw/ppc/spapr_numa.c > @@ -222,24 +222,48 @@ int spapr_numa_write_assoc_lookup_arrays(SpaprMachineState *spapr, void *fdt, > */ > void spapr_numa_write_rtas_dt(SpaprMachineState *spapr, void *fdt, int rtas) > { > + MachineState *ms = MACHINE(spapr); > SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr); > uint32_t refpoints[] = { > cpu_to_be32(0x4), > - cpu_to_be32(0x4), > + cpu_to_be32(0x3), > cpu_to_be32(0x2), > + cpu_to_be32(0x1), > }; > uint32_t nr_refpoints = ARRAY_SIZE(refpoints); > - uint32_t maxdomain = cpu_to_be32(spapr->gpu_numa_id > 1 ? 1 : 0); > + uint32_t maxdomain = ms->numa_state->num_nodes + spapr->gpu_numa_id; > uint32_t maxdomains[] = { > cpu_to_be32(4), > - maxdomain, > - maxdomain, > - maxdomain, > - cpu_to_be32(spapr->gpu_numa_id), > + cpu_to_be32(maxdomain), > + cpu_to_be32(maxdomain), > + cpu_to_be32(maxdomain), > + cpu_to_be32(maxdomain) > }; > > - if (smc->pre_5_1_assoc_refpoints) { > - nr_refpoints = 2; > + if (spapr_machine_using_legacy_numa(spapr)) { > + uint32_t legacy_refpoints[] = { > + cpu_to_be32(0x4), > + cpu_to_be32(0x4), > + cpu_to_be32(0x2), > + }; > + uint32_t legacy_maxdomain = spapr->gpu_numa_id > 1 ? 1 : 0; > + uint32_t legacy_maxdomains[] = { > + cpu_to_be32(4), > + cpu_to_be32(legacy_maxdomain), > + cpu_to_be32(legacy_maxdomain), > + cpu_to_be32(legacy_maxdomain), > + cpu_to_be32(spapr->gpu_numa_id), > + }; > + > + nr_refpoints = 3; > + > + memcpy(refpoints, legacy_refpoints, sizeof(legacy_refpoints)); > + memcpy(maxdomains, legacy_maxdomains, sizeof(legacy_maxdomains)); It would be nice to have a G_STATIC_ASSERT() or QEMU_BUILD_BUG_MSG() ro ensure that the two structures are the same size, if they became different the memcpy is wildly unsafe. > + /* pseries-5.0 and older reference-points array is {0x4, 0x4} */ > + if (smc->pre_5_1_assoc_refpoints) { > + nr_refpoints = 2; > + } > } > > _FDT(fdt_setprop(fdt, rtas, "ibm,associativity-reference-points", -- David Gibson | I'll have my music baroque, and my code david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_ | _way_ _around_! http://www.ozlabs.org/~dgibson
On Thu, 24 Sep 2020 16:50:56 -0300 Daniel Henrique Barboza <danielhb413@gmail.com> wrote: > This is the first guest visible change introduced in > spapr_numa.c. The previous settings of both reference-points > and maxdomains were too restrictive, but enough for the > existing associativity we're setting in the resources. > > We'll change that in the following patches, populating the > associativity arrays based on user input. For those changes > to be effective, reference-points and maxdomains must be > more flexible. After this patch, we'll have 4 distinct > levels of NUMA (0x4, 0x3, 0x2, 0x1) and maxdomains will > allow for any type of configuration the user intends to > do - under the scope and limitations of PAPR itself, of > course. > > Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com> > --- Reviewed-by: Greg Kurz <groug@kaod.org> > hw/ppc/spapr_numa.c | 40 ++++++++++++++++++++++++++++++++-------- > 1 file changed, 32 insertions(+), 8 deletions(-) > > diff --git a/hw/ppc/spapr_numa.c b/hw/ppc/spapr_numa.c > index 990a5fce08..ea33439a15 100644 > --- a/hw/ppc/spapr_numa.c > +++ b/hw/ppc/spapr_numa.c > @@ -222,24 +222,48 @@ int spapr_numa_write_assoc_lookup_arrays(SpaprMachineState *spapr, void *fdt, > */ > void spapr_numa_write_rtas_dt(SpaprMachineState *spapr, void *fdt, int rtas) > { > + MachineState *ms = MACHINE(spapr); > SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr); > uint32_t refpoints[] = { > cpu_to_be32(0x4), > - cpu_to_be32(0x4), > + cpu_to_be32(0x3), > cpu_to_be32(0x2), > + cpu_to_be32(0x1), > }; > uint32_t nr_refpoints = ARRAY_SIZE(refpoints); > - uint32_t maxdomain = cpu_to_be32(spapr->gpu_numa_id > 1 ? 1 : 0); > + uint32_t maxdomain = ms->numa_state->num_nodes + spapr->gpu_numa_id; > uint32_t maxdomains[] = { > cpu_to_be32(4), > - maxdomain, > - maxdomain, > - maxdomain, > - cpu_to_be32(spapr->gpu_numa_id), > + cpu_to_be32(maxdomain), > + cpu_to_be32(maxdomain), > + cpu_to_be32(maxdomain), > + cpu_to_be32(maxdomain) > }; > > - if (smc->pre_5_1_assoc_refpoints) { > - nr_refpoints = 2; > + if (spapr_machine_using_legacy_numa(spapr)) { > + uint32_t legacy_refpoints[] = { > + cpu_to_be32(0x4), > + cpu_to_be32(0x4), > + cpu_to_be32(0x2), > + }; > + uint32_t legacy_maxdomain = spapr->gpu_numa_id > 1 ? 1 : 0; > + uint32_t legacy_maxdomains[] = { > + cpu_to_be32(4), > + cpu_to_be32(legacy_maxdomain), > + cpu_to_be32(legacy_maxdomain), > + cpu_to_be32(legacy_maxdomain), > + cpu_to_be32(spapr->gpu_numa_id), > + }; > + > + nr_refpoints = 3; > + > + memcpy(refpoints, legacy_refpoints, sizeof(legacy_refpoints)); > + memcpy(maxdomains, legacy_maxdomains, sizeof(legacy_maxdomains)); > + > + /* pseries-5.0 and older reference-points array is {0x4, 0x4} */ > + if (smc->pre_5_1_assoc_refpoints) { > + nr_refpoints = 2; > + } > } > > _FDT(fdt_setprop(fdt, rtas, "ibm,associativity-reference-points",
diff --git a/hw/ppc/spapr_numa.c b/hw/ppc/spapr_numa.c index 990a5fce08..ea33439a15 100644 --- a/hw/ppc/spapr_numa.c +++ b/hw/ppc/spapr_numa.c @@ -222,24 +222,48 @@ int spapr_numa_write_assoc_lookup_arrays(SpaprMachineState *spapr, void *fdt, */ void spapr_numa_write_rtas_dt(SpaprMachineState *spapr, void *fdt, int rtas) { + MachineState *ms = MACHINE(spapr); SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr); uint32_t refpoints[] = { cpu_to_be32(0x4), - cpu_to_be32(0x4), + cpu_to_be32(0x3), cpu_to_be32(0x2), + cpu_to_be32(0x1), }; uint32_t nr_refpoints = ARRAY_SIZE(refpoints); - uint32_t maxdomain = cpu_to_be32(spapr->gpu_numa_id > 1 ? 1 : 0); + uint32_t maxdomain = ms->numa_state->num_nodes + spapr->gpu_numa_id; uint32_t maxdomains[] = { cpu_to_be32(4), - maxdomain, - maxdomain, - maxdomain, - cpu_to_be32(spapr->gpu_numa_id), + cpu_to_be32(maxdomain), + cpu_to_be32(maxdomain), + cpu_to_be32(maxdomain), + cpu_to_be32(maxdomain) }; - if (smc->pre_5_1_assoc_refpoints) { - nr_refpoints = 2; + if (spapr_machine_using_legacy_numa(spapr)) { + uint32_t legacy_refpoints[] = { + cpu_to_be32(0x4), + cpu_to_be32(0x4), + cpu_to_be32(0x2), + }; + uint32_t legacy_maxdomain = spapr->gpu_numa_id > 1 ? 1 : 0; + uint32_t legacy_maxdomains[] = { + cpu_to_be32(4), + cpu_to_be32(legacy_maxdomain), + cpu_to_be32(legacy_maxdomain), + cpu_to_be32(legacy_maxdomain), + cpu_to_be32(spapr->gpu_numa_id), + }; + + nr_refpoints = 3; + + memcpy(refpoints, legacy_refpoints, sizeof(legacy_refpoints)); + memcpy(maxdomains, legacy_maxdomains, sizeof(legacy_maxdomains)); + + /* pseries-5.0 and older reference-points array is {0x4, 0x4} */ + if (smc->pre_5_1_assoc_refpoints) { + nr_refpoints = 2; + } } _FDT(fdt_setprop(fdt, rtas, "ibm,associativity-reference-points",
This is the first guest visible change introduced in spapr_numa.c. The previous settings of both reference-points and maxdomains were too restrictive, but enough for the existing associativity we're setting in the resources. We'll change that in the following patches, populating the associativity arrays based on user input. For those changes to be effective, reference-points and maxdomains must be more flexible. After this patch, we'll have 4 distinct levels of NUMA (0x4, 0x3, 0x2, 0x1) and maxdomains will allow for any type of configuration the user intends to do - under the scope and limitations of PAPR itself, of course. Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com> --- hw/ppc/spapr_numa.c | 40 ++++++++++++++++++++++++++++++++-------- 1 file changed, 32 insertions(+), 8 deletions(-)