On Tue, Oct 22, 2024 at 05:34:50PM -0400, Gregory Price wrote:
> Capacity is stranded when CFMWS regions are not aligned to block size.
> On x86, block size increases with capacity (2G blocks @ 64G capacity).
>
> Use CFMWS base/size to report memory block size alignment advice.
>
> After the alignment, the acpi code begins populating numa nodes with
> memblocks, so probe the value just prior to lock it in. All future
> callers should be providing advice prior to this point.
>
> Suggested-by: Dan Williams <dan.j.williams@xxxxxxxxx>
> Signed-off-by: Gregory Price <gourry@xxxxxxxxxx>
> ---
> drivers/acpi/numa/srat.c | 33 +++++++++++++++++++++++++++++++++
> 1 file changed, 33 insertions(+)
>
> diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c
> index 44f91f2c6c5d..35e6f7c17f60 100644
> --- a/drivers/acpi/numa/srat.c
> +++ b/drivers/acpi/numa/srat.c
> @@ -14,6 +14,7 @@
> #include <linux/errno.h>
> #include <linux/acpi.h>
> #include <linux/memblock.h>
> +#include <linux/memory.h>
> #include <linux/numa.h>
> #include <linux/nodemask.h>
> #include <linux/topology.h>
> @@ -333,6 +334,29 @@ acpi_parse_memory_affinity(union acpi_subtable_headers *header,
> return 0;
> }
>
> +/* Advise memblock on maximum block size to avoid stranded capacity. */
> +static int __init acpi_align_cfmws(union acpi_subtable_headers *header,
> + void *arg, const unsigned long table_end)
> +{
> + struct acpi_cedt_cfmws *cfmws = (struct acpi_cedt_cfmws *)header;
> + u64 start = cfmws->base_hpa;
> + u64 size = cfmws->window_size;
> + unsigned long bz;
Maybe unsigned long size?
> +
> + for (bz = SZ_64T; bz >= SZ_256M; bz >>= 1) {
> + if (IS_ALIGNED(start, bz) && IS_ALIGNED(size, bz))
> + break;
> + }
> +
> + if (bz >= SZ_256M) {
> + if (memory_block_advise_max_size(bz) < 0)
> + pr_warn("CFMWS: memblock size advise failed\n");
> + } else
Nit: braces needed for else arm as well
> + pr_err("CFMWS: [BIOS BUG] base/size alignment violates spec\n");
> +
> + return 0;
> +}
> +
> static int __init acpi_parse_cfmws(union acpi_subtable_headers *header,
> void *arg, const unsigned long table_end)
> {
> @@ -545,6 +569,15 @@ int __init acpi_numa_init(void)
> * Initialize a fake_pxm as the first available PXM to emulate.
> */
>
> + /* Align memblock size to CFMW regions if possible */
> + acpi_table_parse_cedt(ACPI_CEDT_TYPE_CFMWS, acpi_align_cfmws, NULL);
> +
> + /*
> + * Nodes start populating with blocks after this, so probe the max
> + * block size to prevent it from changing in the future.
> + */
> + memory_block_probe_max_size();
> +
It won't change, but how drivers/base/memory.c will know about the probed
size if architecture does not override memory_block_size_bytes()?
> /* fake_pxm is the next unused PXM value after SRAT parsing */
> for (i = 0, fake_pxm = -1; i < MAX_NUMNODES; i++) {
> if (node_to_pxm_map[i] > fake_pxm)
> --
> 2.43.0
>
--
Sincerely yours,
Mike.
