lkml.org 
[lkml]   [2022]   [Dec]   [6]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRE: [PATCH v3 2/6] cxl/mbox: Add GET_POISON_LIST mailbox command
alison.schofield@ wrote:
> From: Alison Schofield <alison.schofield@intel.com>
>
> CXL devices maintain a list of locations that are poisoned or result
> in poison if the addresses are accessed by the host.
>
> Per the spec (CXL 3.0 8.2.9.8.4.1), the device returns this Poison
> list as a set of Media Error Records that include the source of the
> error, the starting device physical address and length. The length is
> the number of adjacent DPAs in the record and is in units of 64 bytes.
>
> Retrieve the list and log each Media Error Record as a trace event of
> type 'cxl_poison'.
>
> When the poison list is requested by region, include the region name
> and uuid in the trace event.
>
> Signed-off-by: Alison Schofield <alison.schofield@intel.com>
> ---
> drivers/cxl/core/mbox.c | 81 +++++++++++++++++++++++++++++++++++++++++
> drivers/cxl/cxlmem.h | 37 +++++++++++++++++++
> 2 files changed, 118 insertions(+)
>
> diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
> index 0c90f13870a4..88f034e97812 100644
> --- a/drivers/cxl/core/mbox.c
> +++ b/drivers/cxl/core/mbox.c
> @@ -9,6 +9,9 @@
>
> #include "core.h"
>
> +#define CREATE_TRACE_POINTS
> +#include <trace/events/cxl.h>
> +
> static bool cxl_raw_allow_all;
>
> /**
> @@ -752,6 +755,7 @@ int cxl_dev_state_identify(struct cxl_dev_state *cxlds)
> {
> /* See CXL 2.0 Table 175 Identify Memory Device Output Payload */
> struct cxl_mbox_identify id;
> + __le32 val = 0;
> int rc;
>
> rc = cxl_mbox_send_cmd(cxlds, CXL_MBOX_OP_IDENTIFY, NULL, 0, &id,
> @@ -771,6 +775,9 @@ int cxl_dev_state_identify(struct cxl_dev_state *cxlds)
> cxlds->lsa_size = le32_to_cpu(id.lsa_size);
> memcpy(cxlds->firmware_version, id.fw_revision, sizeof(id.fw_revision));
>
> + memcpy(&val, id.poison_list_max_mer, 3);

I see Jonathan already commented on the need for get_unaligned_le24()
here, seconded.


> + cxlds->poison_max = min_t(u32, le32_to_cpu(val), CXL_POISON_LIST_MAX);
> +
> return 0;
> }
> EXPORT_SYMBOL_NS_GPL(cxl_dev_state_identify, CXL);
> @@ -835,6 +842,79 @@ int cxl_mem_create_range_info(struct cxl_dev_state *cxlds)
> }
> EXPORT_SYMBOL_NS_GPL(cxl_mem_create_range_info, CXL);
>
> +static void cxl_trace_poison(struct cxl_mbox_poison_payload_out *po,
> + struct cxl_region *cxlr,
> + const char *memdev_name,
> + const char *pcidev_name)

Type-safety please. Pass a 'struct cxl_memdev *' and 'struct pci_dev *'.
Might need to be 'struct device *' instead of 'struct pci_dev *'
depending on if this needs to be called from cxl_test, but anything is
better than a non-specific string.

> +{
> + const char *region_name = cxlr ? dev_name(&cxlr->dev) : NULL;

...and push this conversion into the trace point.

> + struct cxl_region_params *p = cxlr ? &cxlr->params : NULL;
> + uuid_t *uuid = p ? &p->uuid : NULL;
> + u64 addr, dpa, overflow_t = 0;
> + u8 source;
> + u32 len;
> +
> + if (po->flags & CXL_POISON_FLAG_OVERFLOW)
> + overflow_t = le64_to_cpu(po->overflow_timestamp);
> +
> + for (int i = 0; i < le16_to_cpu(po->count); i++) {
> + len = le32_to_cpu(po->record[i].length) * CXL_POISON_LEN_MULT;
> + addr = le64_to_cpu(po->record[i].address);
> + source = addr & CXL_POISON_SOURCE_MASK;
> + dpa = addr & CXL_POISON_START_MASK;
> +
> + trace_cxl_poison(memdev_name, pcidev_name, region_name, uuid,
> + dpa, len, source, po->flags, overflow_t);
> + }
> +}
> +
> +int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len,
> + struct cxl_region *cxlr)
> +{
> + struct cxl_dev_state *cxlds = cxlmd->cxlds;
> + const char *memdev_name = dev_name(&cxlmd->dev);
> + const char *pcidev_name = dev_name(cxlds->dev);
> + struct cxl_mbox_poison_payload_out *po;
> + struct cxl_mbox_poison_payload_in pi;
> + int nr_records = 0;
> + int rc;
> +
> + po = kvmalloc(cxlds->payload_size, GFP_KERNEL);
> + if (!po)
> + return -ENOMEM;
> +
> + pi.offset = cpu_to_le64(offset);
> + pi.length = cpu_to_le64(len);
> +
> + rc = mutex_lock_interruptible(&cxlds->poison_list_mutex);

So I do not know what this mutex is protecting if there is an allocation
per cxl_mem_get_poison() invocation. Although I suspect that's somewhat
wasteful. Just allocate one buffer at the beginning of time and then use
the lock to protect that buffer.

Although, I wonder if this and Event handling should share locks and one
preallocated buffer? Otherwise I do think it is important for Events and
Poison handling to be able to make forward progress without needing to
allocate up to a megabyte of memory at runtime. The other payload_size
allocations are for one-off things that run at the beginning of time,
but Poison and Events run repeatedly.

> + if (rc)
> + goto out;
> +
> + do {
> + rc = cxl_mbox_send_cmd(cxlds, CXL_MBOX_OP_GET_POISON, &pi,
> + sizeof(pi), po, cxlds->payload_size);
> + if (rc)
> + break;
> +
> + if (trace_cxl_poison_enabled())
> + cxl_trace_poison(po, cxlr, memdev_name, pcidev_name);
> +
> + /* Protect against an uncleared _FLAG_MORE */
> + nr_records = nr_records + le16_to_cpu(po->count);
> + if (nr_records >= cxlds->poison_max) {
> + dev_dbg(&cxlmd->dev, "Max Error Records reached: %d\n",
> + nr_records);
> + break;
> + }
> + } while (po->flags & CXL_POISON_FLAG_MORE);
> +
> + mutex_unlock(&cxlds->poison_list_mutex);
> +out:
> + kvfree(po);
> + return rc;
> +}
> +EXPORT_SYMBOL_NS_GPL(cxl_mem_get_poison, CXL);
> +
> struct cxl_dev_state *cxl_dev_state_create(struct device *dev)
> {
> struct cxl_dev_state *cxlds;
> @@ -846,6 +926,7 @@ struct cxl_dev_state *cxl_dev_state_create(struct device *dev)
> }
>
> mutex_init(&cxlds->mbox_mutex);
> + mutex_init(&cxlds->poison_list_mutex);
> cxlds->dev = dev;
>
> return cxlds;
> diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
> index 669868cc1553..49d891347e39 100644
> --- a/drivers/cxl/cxlmem.h
> +++ b/drivers/cxl/cxlmem.h
> @@ -192,6 +192,8 @@ struct cxl_endpoint_dvsec_info {
> * (CXL 2.0 8.2.8.4.3 Mailbox Capabilities Register)
> * @lsa_size: Size of Label Storage Area
> * (CXL 2.0 8.2.9.5.1.1 Identify Memory Device)
> + * @poison_max: maximum media error records held in device cache
> + * @poison_list_mutex: Mutex to synchronize poison list retrieval
> * @mbox_mutex: Mutex to synchronize mailbox access.
> * @firmware_version: Firmware version for the memory device.
> * @enabled_cmds: Hardware commands found enabled in CEL.
> @@ -224,6 +226,8 @@ struct cxl_dev_state {
>
> size_t payload_size;
> size_t lsa_size;
> + u32 poison_max;
> + struct mutex poison_list_mutex; /* Protect reads of poison list */
> struct mutex mbox_mutex; /* Protects device mailbox and firmware */
> char firmware_version[0x10];
> DECLARE_BITMAP(enabled_cmds, CXL_MEM_COMMAND_ID_MAX);
> @@ -349,6 +353,37 @@ struct cxl_mbox_set_partition_info {
>
> /* Get Poison List CXL 3.0 Spec 8.2.9.8.4.1 */
>
> +struct cxl_mbox_poison_payload_in {
> + __le64 offset;
> + __le64 length;
> +} __packed;
> +
> +struct cxl_mbox_poison_payload_out {
> + u8 flags;
> + u8 rsvd1;
> + __le64 overflow_timestamp;
> + __le16 count;
> + u8 rsvd2[0x14];

Let's use decimal values for size.

> + struct cxl_poison_record {
> + __le64 address;
> + __le32 length;
> + __le32 rsvd;
> + } __packed record[];
> +} __packed;
> +
> +/*
> + * Get Poison List address field encodes the starting
> + * address of poison, and the source of the poison.
> + */
> +#define CXL_POISON_START_MASK GENMASK_ULL(63, 6)
> +#define CXL_POISON_SOURCE_MASK GENMASK(2, 0)
> +
> +/* Get Poison List record length is in units of 64 bytes */
> +#define CXL_POISON_LEN_MULT 64
> +
> +/* Kernel defined maximum for a list of poison errors */
> +#define CXL_POISON_LIST_MAX 1024
> +
> /* Get Poison List: Payload out flags */
> #define CXL_POISON_FLAG_MORE BIT(0)
> #define CXL_POISON_FLAG_OVERFLOW BIT(1)
> @@ -395,6 +430,8 @@ int cxl_mem_create_range_info(struct cxl_dev_state *cxlds);
> struct cxl_dev_state *cxl_dev_state_create(struct device *dev);
> void set_exclusive_cxl_commands(struct cxl_dev_state *cxlds, unsigned long *cmds);
> void clear_exclusive_cxl_commands(struct cxl_dev_state *cxlds, unsigned long *cmds);
> +int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len,
> + struct cxl_region *cxlr);
> #ifdef CONFIG_CXL_SUSPEND
> void cxl_mem_active_inc(void);
> void cxl_mem_active_dec(void);
> --
> 2.37.3
>


\
 
 \ /
  Last update: 2022-12-07 03:42    [W:0.124 / U:0.476 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site