[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <aCI0JC88vIhcTGNH@smc-140338-bm01>
Date: Mon, 12 May 2025 17:47:16 +0000
From: Fan Ni <nifan.cxl@...il.com>
To: Ira Weiny <ira.weiny@...el.com>
Cc: Dave Jiang <dave.jiang@...el.com>,
Jonathan Cameron <Jonathan.Cameron@...wei.com>,
Dan Williams <dan.j.williams@...el.com>,
Davidlohr Bueso <dave@...olabs.net>,
Alison Schofield <alison.schofield@...el.com>,
Vishal Verma <vishal.l.verma@...el.com>, linux-cxl@...r.kernel.org,
nvdimm@...ts.linux.dev, linux-kernel@...r.kernel.org,
Li Ming <ming.li@...omail.com>
Subject: Re: [PATCH v9 12/19] cxl/extent: Process dynamic partition events
and realize region extents
On Sun, Apr 13, 2025 at 05:52:20PM -0500, Ira Weiny wrote:
> A dynamic capacity device (DCD) sends events to signal the host for
> changes in the availability of Dynamic Capacity (DC) memory. These
> events contain extents describing a DPA range and meta data for memory
> to be added or removed. Events may be sent from the device at any time.
>
...
> Tag support within the DAX layer is not yet supported. To maintain
> compatibility with legacy DAX/region processing only tags with a value
> of 0 are allowed. This defines existing DAX devices as having a 0 tag
> which makes the most logical sense as a default.
>
> Process DCD events and create region devices.
>
> Based on an original patch by Navneet Singh.
>
> Reviewed-by: Dave Jiang <dave.jiang@...el.com>
> Reviewed-by: Li Ming <ming.li@...omail.com>
> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@...wei.com>
> Signed-off-by: Ira Weiny <ira.weiny@...el.com>
>
Hi Ira,
I have some comments inline.
There is one that will need to fix if I understand the code correctly.
> ---
> Changes:
> [iweiny: rebase]
> [djbw: s/region/partition/]
> [iweiny: Adapt to new partition arch]
> [iweiny: s/tag/uuid/ throughout the code]
> ---
> drivers/cxl/core/Makefile | 2 +-
> drivers/cxl/core/core.h | 13 ++
> drivers/cxl/core/extent.c | 366 ++++++++++++++++++++++++++++++++++++++++++++++
> drivers/cxl/core/mbox.c | 292 +++++++++++++++++++++++++++++++++++-
> drivers/cxl/core/region.c | 3 +
> drivers/cxl/cxl.h | 53 ++++++-
> drivers/cxl/cxlmem.h | 27 ++++
> include/cxl/event.h | 31 ++++
> tools/testing/cxl/Kbuild | 3 +-
> 9 files changed, 786 insertions(+), 4 deletions(-)
...
> +static int send_one_response(struct cxl_mailbox *cxl_mbox,
I feel like the name is not that informative, maybe
send_one_dc_response?
> + struct cxl_mbox_dc_response *response,
> + int opcode, u32 extent_list_size, u8 flags)
> +{
> + struct cxl_mbox_cmd mbox_cmd = (struct cxl_mbox_cmd) {
> + .opcode = opcode,
> + .size_in = struct_size(response, extent_list, extent_list_size),
> + .payload_in = response,
> + };
> +
> + response->extent_list_size = cpu_to_le32(extent_list_size);
> + response->flags = flags;
> + return cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
> +}
> +
> +static int cxl_send_dc_response(struct cxl_memdev_state *mds, int opcode,
> + struct xarray *extent_array, int cnt)
> +{
> + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
> + struct cxl_mbox_dc_response *p;
> + struct cxl_extent *extent;
> + unsigned long index;
> + u32 pl_index;
> +
> + size_t pl_size = struct_size(p, extent_list, cnt);
> + u32 max_extents = cnt;
> +
> + /* May have to use more bit on response. */
> + if (pl_size > cxl_mbox->payload_size) {
> + max_extents = (cxl_mbox->payload_size - sizeof(*p)) /
> + sizeof(struct updated_extent_list);
> + pl_size = struct_size(p, extent_list, max_extents);
> + }
> +
> + struct cxl_mbox_dc_response *response __free(kfree) =
> + kzalloc(pl_size, GFP_KERNEL);
> + if (!response)
> + return -ENOMEM;
> +
> + if (cnt == 0)
> + return send_one_response(cxl_mbox, response, opcode, 0, 0);
> +
> + pl_index = 0;
> + xa_for_each(extent_array, index, extent) {
> + response->extent_list[pl_index].dpa_start = extent->start_dpa;
> + response->extent_list[pl_index].length = extent->length;
> + pl_index++;
> +
> + if (pl_index == max_extents) {
> + u8 flags = 0;
> + int rc;
> +
> + if (pl_index < cnt)
> + flags |= CXL_DCD_EVENT_MORE;
> + rc = send_one_response(cxl_mbox, response, opcode,
> + pl_index, flags);
> + if (rc)
> + return rc;
> + cnt -= pl_index;
> + pl_index = 0;
The logic here seems incorrect.
Let's say cnt = 8, and max_extents = 5.
For the first 5 extents, it works fine. But after the first 5 extents
are processed (response sent), the cnt will become 8-5=3, however,
max_extents is still 5, so there is no chance we can send response for
the last 3 extents.
I think we need to update max_extents based on "cnt" after each
iteration.
> + }
> + }
> +
> + if (!pl_index) /* nothing more to do */
> + return 0;
...
> +/*
> + * Add Dynamic Capacity Response
> + * CXL rev 3.1 section 8.2.9.9.9.3; Table 8-168 & Table 8-169
> + */
> +struct cxl_mbox_dc_response {
> + __le32 extent_list_size;
As jonathan mentioned, "size" may be not a good name.
Maybe "nr_extents"?
Fan
> + u8 flags;
> + u8 reserved[3];
> + struct updated_extent_list {
> + __le64 dpa_start;
> + __le64 length;
> + u8 reserved[8];
> + } __packed extent_list[];
> +} __packed;
> +
> struct cxl_mbox_get_supported_logs {
> __le16 entries;
> u8 rsvd[6];
> @@ -644,6 +662,14 @@ struct cxl_mbox_identify {
> UUID_INIT(0xfe927475, 0xdd59, 0x4339, 0xa5, 0x86, 0x79, 0xba, 0xb1, \
> 0x13, 0xb7, 0x74)
>
> +/*
> + * Dynamic Capacity Event Record
> + * CXL rev 3.1 section 8.2.9.2.1; Table 8-43
> + */
> +#define CXL_EVENT_DC_EVENT_UUID \
> + UUID_INIT(0xca95afa7, 0xf183, 0x4018, 0x8c, 0x2f, 0x95, 0x26, 0x8e, \
> + 0x10, 0x1a, 0x2a)
> +
> /*
> * Get Event Records output payload
> * CXL rev 3.0 section 8.2.9.2.2; Table 8-50
> @@ -669,6 +695,7 @@ enum cxl_event_log_type {
> CXL_EVENT_TYPE_WARN,
> CXL_EVENT_TYPE_FAIL,
> CXL_EVENT_TYPE_FATAL,
> + CXL_EVENT_TYPE_DCD,
> CXL_EVENT_TYPE_MAX
> };
>
> diff --git a/include/cxl/event.h b/include/cxl/event.h
> index f9ae1796da85..0c159eac4337 100644
> --- a/include/cxl/event.h
> +++ b/include/cxl/event.h
> @@ -108,11 +108,42 @@ struct cxl_event_mem_module {
> u8 reserved[0x2a];
> } __packed;
>
> +/*
> + * CXL rev 3.1 section 8.2.9.2.1.6; Table 8-51
> + */
> +struct cxl_extent {
> + __le64 start_dpa;
> + __le64 length;
> + u8 uuid[UUID_SIZE];
> + __le16 shared_extn_seq;
> + u8 reserved[0x6];
> +} __packed;
> +
> +/*
> + * Dynamic Capacity Event Record
> + * CXL rev 3.1 section 8.2.9.2.1.6; Table 8-50
> + */
> +#define CXL_DCD_EVENT_MORE BIT(0)
> +struct cxl_event_dcd {
> + struct cxl_event_record_hdr hdr;
> + u8 event_type;
> + u8 validity_flags;
> + __le16 host_id;
> + u8 partition_index;
> + u8 flags;
> + u8 reserved1[0x2];
> + struct cxl_extent extent;
> + u8 reserved2[0x18];
> + __le32 num_avail_extents;
> + __le32 num_avail_tags;
> +} __packed;
> +
> union cxl_event {
> struct cxl_event_generic generic;
> struct cxl_event_gen_media gen_media;
> struct cxl_event_dram dram;
> struct cxl_event_mem_module mem_module;
> + struct cxl_event_dcd dcd;
> /* dram & gen_media event header */
> struct cxl_event_media_hdr media_hdr;
> } __packed;
> diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild
> index 387f3df8b988..916f2b30e2f3 100644
> --- a/tools/testing/cxl/Kbuild
> +++ b/tools/testing/cxl/Kbuild
> @@ -64,7 +64,8 @@ cxl_core-y += $(CXL_CORE_SRC)/cdat.o
> cxl_core-y += $(CXL_CORE_SRC)/ras.o
> cxl_core-y += $(CXL_CORE_SRC)/acpi.o
> cxl_core-$(CONFIG_TRACING) += $(CXL_CORE_SRC)/trace.o
> -cxl_core-$(CONFIG_CXL_REGION) += $(CXL_CORE_SRC)/region.o
> +cxl_core-$(CONFIG_CXL_REGION) += $(CXL_CORE_SRC)/region.o \
> + $(CXL_CORE_SRC)/extent.o
> cxl_core-$(CONFIG_CXL_MCE) += $(CXL_CORE_SRC)/mce.o
> cxl_core-$(CONFIG_CXL_FEATURES) += $(CXL_CORE_SRC)/features.o
> cxl_core-y += config_check.o
>
> --
> 2.49.0
>
--
Fan Ni (From gmail)
Powered by blists - more mailing lists