[PATCH v2] virtio-balloon-pci: Allow setting nvectors, so we can use MSI-X

2025-01-15 Thread Reza Arbab
g nvectors, so we can use MSI-X") bad9c5a5166f ("virtio-rng-pci: fix migration compat for vectors") 62bdb8871512 ("virtio-rng-pci: fix transitional migration compat for vectors") Acked-by: David Hildenbrand Signed-off-by: Reza Arbab --- v2: - Remove

Re: [PATCH] virtio-balloon-pci: Allow setting nvectors, so we can use MSI-X

2025-01-15 Thread Reza Arbab
since commit 5fcabe628b8 ("include/hw/qdev-properties: Remove DEFINE_PROP_END_OF_LIST"). Ah, yes, that happened after I sent this. Also, this array can be declared const. Funny, commit 1577a9180f37 ("hw/virtio: Constify all Property") also happened not long after I sent.

Re: [PATCH] virtio-balloon-pci: Allow setting nvectors, so we can use MSI-X

2025-01-15 Thread Reza Arbab
); | ^~ Ah, I need to declare virtio_balloon_properties as const. -- Reza Arbab

Re: [PATCH] virtio-balloon-pci: Allow setting nvectors, so we can use MSI-X

2025-01-08 Thread Reza Arbab
On Wed, Dec 18, 2024 at 11:37:05AM +0100, David Hildenbrand wrote: No expert on any of that MSi-X / PCI magic, but LGTM Acked-by: David Hildenbrand Thanks David! Did anyone else have any comments? Just want to make sure I have things in order to get this into the next release. -- Reza

[PATCH] virtio-balloon-pci: Allow setting nvectors, so we can use MSI-X

2024-12-16 Thread Reza Arbab
g nvectors, so we can use MSI-X") bad9c5a5166f ("virtio-rng-pci: fix migration compat for vectors") 62bdb8871512 ("virtio-rng-pci: fix transitional migration compat for vectors") Signed-off-by: Reza Arbab --- hw/core/machine.c | 6 +- hw/virtio/virtio-

[PATCH v4] spapr: Add a new level of NUMA for GPUs

2020-07-16 Thread Reza Arbab
80 80 80 80 80 10 These are the same distances as on the host, mirroring the change made to host firmware in skiboot commit f845a648b8cb ("numa/associativity: Add a new level of NUMA for GPU's"). Signed-off-by: Reza Arbab --- v4: * Use nvslot->numa_id for distin

Re: [PATCH v3] spapr: Add a new level of NUMA for GPUs

2020-07-16 Thread Reza Arbab
t;numa_id), cpu_to_be32(nvslot->numa_id), }; Sure, that's how it originally was in v1 of the patch. I'll send a v4 today. It's been a while so I need to rebase anyway. -- Reza Arbab

Re: [PATCH v3] spapr: Add a new level of NUMA for GPUs

2020-05-25 Thread Reza Arbab
On Mon, May 25, 2020 at 03:05:50PM +1000, David Gibson wrote: On Fri, May 22, 2020 at 02:53:33PM -0500, Reza Arbab wrote: --- a/hw/ppc/spapr_pci_nvlink2.c +++ b/hw/ppc/spapr_pci_nvlink2.c @@ -362,7 +362,7 @@ void spapr_phb_nvgpu_ram_populate_dt(SpaprPhbState *sphb, void *fdt) uint32_t

Re: [PATCH v3] spapr: Add a new level of NUMA for GPUs

2020-05-22 Thread Reza Arbab
On Fri, May 22, 2020 at 02:53:33PM -0500, Reza Arbab wrote: --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -889,10 +889,16 @@ static int spapr_dt_rng(void *fdt) static void spapr_dt_rtas(SpaprMachineState *spapr, void *fdt) { MachineState *ms = MACHINE(spapr); +SpaprMachineClass *smc

[PATCH v3] spapr: Add a new level of NUMA for GPUs

2020-05-22 Thread Reza Arbab
80 80 80 80 80 10 These are the same distances as on the host, mirroring the change made to host firmware in skiboot commit f845a648b8cb ("numa/associativity: Add a new level of NUMA for GPU's"). Signed-off-by: Reza Arbab --- v3: * Squash into one patch * Add PHB compat prope

Re: [PATCH v2 1/2] spapr: Add associativity reference point count to machine info

2020-05-21 Thread Reza Arbab
On Thu, May 21, 2020 at 01:34:37AM +0200, Greg Kurz wrote: On Mon, 18 May 2020 16:44:17 -0500 Reza Arbab wrote: @@ -944,8 +946,9 @@ static void spapr_dt_rtas(SpaprMachineState *spapr, void *fdt) qemu_hypertas->str, qemu_hypertas->len)); g_string_free(qemu_hy

[PATCH v2 2/2] spapr: Add a new level of NUMA for GPUs

2020-05-18 Thread Reza Arbab
80 80 80 80 80 10 These are the same distances as on the host, mirroring the change made to host firmware in skiboot commit f845a648b8cb ("numa/associativity: Add a new level of NUMA for GPU's"). Signed-off-by: Reza Arbab --- hw/ppc/spapr.c | 11 +-- hw/

[PATCH v2 1/2] spapr: Add associativity reference point count to machine info

2020-05-18 Thread Reza Arbab
Make the number of NUMA associativity reference points a machine-specific value, using the currently assumed default (two reference points). This preps the next patch to conditionally change it. Signed-off-by: Reza Arbab --- hw/ppc/spapr.c | 6 +- include/hw/ppc/spapr.h | 1 + 2

Re: [PATCH] spapr: Add a new level of NUMA for GPUs

2020-05-13 Thread Reza Arbab
t associativity[] = { cpu_to_be32(0x4), SPAPR_GPU_NUMA_ID, -SPAPR_GPU_NUMA_ID, +cpu_to_be32(nvslot->numa_id), SPAPR_GPU_NUMA_ID, cpu_to_be32(nvslot->numa_id) }; I think the rationale is that if those other levels got added to reference-points in the future, you'd likely want the GPU to be distinct there too. -- Reza Arbab

[PATCH] spapr: Add a new level of NUMA for GPUs

2020-05-08 Thread Reza Arbab
quot;). Signed-off-by: Reza Arbab --- hw/ppc/spapr.c | 6 +- hw/ppc/spapr_pci_nvlink2.c | 8 +++- 2 files changed, 8 insertions(+), 6 deletions(-) diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index c18eab0a2305..53567f98f0c6 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@