From: Dave Jiang <dave.jiang@intel.com>
To: Srirangan Madhavan <smadhavan@nvidia.com>,
Alison Schofield <alison.schofield@intel.com>,
Bjorn Helgaas <bhelgaas@google.com>,
Davidlohr Bueso <dave@stgolabs.net>,
Ira Weiny <ira.weiny@intel.com>,
Jonathan Cameron <jic23@kernel.org>,
Vishal Verma <vishal.l.verma@intel.com>,
linux-cxl@vger.kernel.org, linux-pci@vger.kernel.org,
linux-kernel@vger.kernel.org
Cc: Alex Williamson <alex.williamson@redhat.com>,
vsethi@nvidia.com, alwilliamson@nvidia.com,
Sai Yashwanth Reddy Kancherla <skancherla@nvidia.com>,
Vishal Aslot <vaslot@nvidia.com>,
Manish Honap <mhonap@nvidia.com>, Jiandi An <jan@nvidia.com>,
Richard Cheng <icheng@nvidia.com>,
linux-tegra@vger.kernel.org
Subject: Re: [PATCH v15 08/16] cxl: Refresh cached PCI HDM decoder settings
Date: Mon, 26 Oct 2026 15:56:16 -0700 [thread overview]
Message-ID: <db212bda-9642-4b78-9bb0-c75aa60df401@intel.com> (raw)
In-Reply-To: <20261011021422.3428136-9-smadhavan@nvidia.com>
On 10/10/26 7:14 PM, Srirangan Madhavan wrote:
> Early PCI discovery creates the HDM cache, while later CXL enumeration and
> decoder operations provide updated programming state.
>
> Refresh the PCI snapshot when decoders are enumerated, committed, or reset
> so reset recovery need not walk the CXL topology. Ignore updates when no
> cache exists and reject decoder-count mismatches.
>
> Use CXL_RESET for the PCI HDM cache. Shared HDM register helpers do not
> require it.
>
> Skip cache checks and updates for DVSEC-emulated decoders, which do not
> use HDM registers. Keep cached global control when MMIO reads return all
> ones.
>
> Skip non-PCI mock ports to avoid test wrappers and a circular dependency
> between cxl_core and cxl_mock.
Maybe consider saying:
Non-PCI mock ports have no upstream PCI device, so the cache helpers ignore them. This avoids test wrappers and a circular dependency between cxl_core and cxl_mock.
>
> Link: https://git.kernel.org/pub/scm/linux/kernel/git/djiang/linux.git/commit/?id=50a88f5194e5df38590d413f925d8d5afa8a8488
> Suggested-by: Dave Jiang <dave.jiang@intel.com>
> Signed-off-by: Srirangan Madhavan <smadhavan@nvidia.com>
> Assisted-by: LLM
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
> ---
> drivers/cxl/Kconfig | 5 +++
> drivers/cxl/core/core.h | 3 ++
> drivers/cxl/core/hdm.c | 55 +++++++++++++++++++++++++++++++-
> drivers/cxl/core/pci.c | 70 +++++++++++++++++++++++++++++++++++++++++
> include/cxl/cxl.h | 1 +
> include/cxl/hdm.h | 25 +++++++++++++++
> include/linux/pci.h | 6 ++++
> 7 files changed, 164 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/cxl/Kconfig b/drivers/cxl/Kconfig
> index 80aeb0d556bd..8b08bfdc4982 100644
> --- a/drivers/cxl/Kconfig
> +++ b/drivers/cxl/Kconfig
> @@ -6,6 +6,7 @@ menuconfig CXL_BUS
> select FW_UPLOAD
> select PCI_DOE
> select FIRMWARE_TABLE
> + select CXL_RESET
> select NUMA_KEEP_MEMINFO if NUMA_MEMBLKS
> select FWCTL if CXL_FEATURES
> help
> @@ -244,3 +245,7 @@ config CXL_ATL
> depends on ACPI_PRMT && AMD_NB
>
> endif
> +
> +# CXL_BUS requires the PCI HDM cache and built-in state helpers, even when modular.
> +config CXL_RESET
> + bool
> diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
> index d69864b25656..77bc4f7d2e99 100644
> --- a/drivers/cxl/core/core.h
> +++ b/drivers/cxl/core/core.h
> @@ -222,6 +222,9 @@ static inline void devm_cxl_dport_ras_setup(struct cxl_dport *dport) { }
> int cxl_gpf_port_setup(struct cxl_dport *dport);
>
> struct cxl_hdm;
> +/* Hold cxl_rwsem.dpa for write while using the returned cache. */
> +struct cxl_hdm_info *cxl_hdm_get_cached_info(struct cxl_hdm *cxlhdm, int id);
> +int cxl_hdm_check_decoder_count(struct cxl_hdm *cxlhdm);
> int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm,
> struct cxl_endpoint_dvsec_info *info);
> int cxl_port_get_possible_dports(struct cxl_port *port);
> diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c
> index 1a19078e6c6c..b57257efbf4e 100644
> --- a/drivers/cxl/core/hdm.c
> +++ b/drivers/cxl/core/hdm.c
> @@ -730,6 +730,47 @@ static void cxlsd_set_targets(struct cxl_switch_decoder *cxlsd, u64 *tgt)
> *tgt |= FIELD_PREP(GENMASK_ULL(63, 56), t[7]->port_id);
> }
>
> +static void cxl_hdm_refresh_decoder(struct cxl_hdm *cxlhdm,
> + struct cxl_decoder *cxld)
> +{
> + void __iomem *hdm = cxlhdm->regs.hdm_decoder;
> + struct cxl_endpoint_decoder_settings *settings;
> + struct cxl_hdm_info *info;
> + u32 global_ctrl;
> +
> + if (!hdm)
> + return;
> + if (!is_endpoint_decoder(&cxld->dev))
> + return;
> +
> + guard(rwsem_write)(&cxl_rwsem.dpa);
> + info = cxl_hdm_get_cached_info(cxlhdm, cxld->config.id);
> + if (!info)
> + return;
> +
> + /* Preserve the last good value when the device does not respond. */
> + global_ctrl = readl(hdm + CXL_HDM_DECODER_CTRL_OFFSET);
> + if (global_ctrl != U32_MAX)
> + info->global_ctrl = global_ctrl;
> + settings = &info->settings[cxld->config.id];
> +
> + /*
> + * A disabled decoder's software object may retain its old range and
> + * skip state. Leave only the decoder id in the cached settings so stale
> + * state is not restored as an enabled decode.
> + */
> + *settings = (struct cxl_endpoint_decoder_settings) {
> + .config.id = cxld->config.id,
> + };
> + if (cxld->config.flags & CXL_DECODER_F_ENABLE) {
> + struct cxl_endpoint_decoder *cxled =
> + to_cxl_endpoint_decoder(&cxld->dev);
> +
> + settings->config = cxld->config;
> + settings->skip = cxled->skip;
> + }
> +}
> +
> static void
> cxl_endpoint_decoder_snapshot(struct cxl_endpoint_decoder *cxled,
> struct cxl_endpoint_decoder_settings *settings)
> @@ -811,6 +852,7 @@ static int cxl_decoder_commit(struct cxl_decoder *cxld)
> }
> port->commit_end++;
> cxld->config.flags |= CXL_DECODER_F_ENABLE;
> + cxl_hdm_refresh_decoder(cxlhdm, cxld);
>
> return 0;
> }
> @@ -883,6 +925,7 @@ static void cxl_decoder_reset(struct cxl_decoder *cxld)
> writel(0, hdm + CXL_HDM_DECODER0_BASE_LOW_OFFSET(id));
>
> cxld->config.flags &= ~CXL_DECODER_F_ENABLE;
> + cxl_hdm_refresh_decoder(cxlhdm, cxld);
>
> /* Userspace is now responsible for reconfiguring this decoder */
> if (is_endpoint_decoder(&cxld->dev)) {
> @@ -1090,9 +1133,17 @@ static int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm,
> {
> void __iomem *hdm = cxlhdm->regs.hdm_decoder;
> struct cxl_port *port = cxlhdm->port;
> - int i;
> + /* DVSEC-emulated decoders do not describe the cached HDM registers. */
> + bool emulated = should_emulate_decoders(info);
> + int check_rc, i;
> u64 dpa_base = 0;
>
> + if (is_cxl_endpoint(port) && hdm && !emulated) {
> + check_rc = cxl_hdm_check_decoder_count(cxlhdm);
> + if (check_rc)
> + return check_rc;
> + }
> +
> cxl_settle_decoders(cxlhdm);
>
> for (i = 0; i < cxlhdm->decoder_count; i++) {
> @@ -1131,6 +1182,8 @@ static int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm,
> put_device(&cxld->dev);
> return rc;
> }
> + if (!emulated)
> + cxl_hdm_refresh_decoder(cxlhdm, cxld);
> rc = add_hdm_decoder(port, cxld);
> if (rc) {
> dev_warn(&port->dev,
> diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
> index 33b21c8dcb21..2acddb472103 100644
> --- a/drivers/cxl/core/pci.c
> +++ b/drivers/cxl/core/pci.c
> @@ -6,6 +6,7 @@
> #include <linux/delay.h>
> #include <linux/pci.h>
> #include <linux/pci-doe.h>
> +#include <cxl/hdm.h>
> #include <cxl/pci.h>
> #include <linux/aer.h>
> #include <cxlpci.h>
> @@ -180,6 +181,75 @@ int cxl_await_media_ready(struct cxl_dev_state *cxlds)
> }
> EXPORT_SYMBOL_NS_GPL(cxl_await_media_ready, "CXL");
>
> +/**
> + * cxl_hdm_get_cached_info() - get the PCI-owned HDM cache for a decoder
> + * @cxlhdm: HDM capability whose port identifies the upstream PCI device
> + * @id: decoder ID to validate against the cached decoder count
> + *
> + * The caller must hold cxl_rwsem.dpa for write throughout this call and
> + * all access through the returned pointer. The pointer refers to the live
> + * cache; ownership remains with the PCI device.
> + *
> + * Return: the cache containing @id, or NULL if no upstream PCI device or
> + * cache exists, or @id is outside the cached decoder count.
> + */
> +struct cxl_hdm_info *cxl_hdm_get_cached_info(struct cxl_hdm *cxlhdm, int id)
> +{
> + struct cxl_hdm_info *info;
> +
> + struct pci_dev *pdev __free(pci_dev_put) =
> + cxl_port_get_uport_pci_dev(cxlhdm->port);
> +
> + if (!pdev)
> + return NULL;
> +
> + lockdep_assert_held_write(&cxl_rwsem.dpa);
> + info = pdev->hdm;
> + if (!info)
> + return NULL;
> +
> + if (id < 0 || id >= info->decoder_count) {
> + pci_warn(pdev, "CXL HDM decoder %d exceeds cached count %d\n",
> + id, info->decoder_count);
> + return NULL;
> + }
> +
> + return info;
> +}
> +EXPORT_SYMBOL_NS_GPL(cxl_hdm_get_cached_info, "CXL");
> +
> +/**
> + * cxl_hdm_check_decoder_count() - check enumeration against the PCI HDM cache
> + * @cxlhdm: HDM capability containing the decoder count to check
> + *
> + * Take cxl_rwsem.dpa for read while comparing the cached count. Call only
> + * for hardware HDM decoders, since DVSEC-emulated ranges do not describe
> + * the HDM registers represented by the cache.
> + *
> + * Return: 0 if the counts match or no upstream PCI device or cache exists,
> + * or -ENXIO if the cached and enumerated decoder counts differ.
> + */
> +int cxl_hdm_check_decoder_count(struct cxl_hdm *cxlhdm)
> +{
> + struct pci_dev *pdev __free(pci_dev_put) =
> + cxl_port_get_uport_pci_dev(cxlhdm->port);
> +
> + if (!pdev)
> + return 0;
> +
> + guard(rwsem_read)(&cxl_rwsem.dpa);
> + if (pdev->hdm &&
> + pdev->hdm->decoder_count != cxlhdm->decoder_count) {
> + pci_warn(pdev,
> + "CXL HDM cache decoder count mismatch: cached=%d hdm=%d\n",
> + pdev->hdm->decoder_count, cxlhdm->decoder_count);
> + return -ENXIO;
> + }
> +
> + return 0;
> +}
> +EXPORT_SYMBOL_NS_GPL(cxl_hdm_check_decoder_count, "CXL");
> +
> static int cxl_set_mem_enable(struct cxl_dev_state *cxlds, u16 val)
> {
> struct pci_dev *pdev = to_pci_dev(cxlds->dev);
> diff --git a/include/cxl/cxl.h b/include/cxl/cxl.h
> index 9af01e1f45ba..b29374b34cfa 100644
> --- a/include/cxl/cxl.h
> +++ b/include/cxl/cxl.h
> @@ -26,6 +26,7 @@ enum cxl_devtype {
> };
>
> struct cxl_region;
> +struct cxl_hdm_info;
>
> enum cxl_decoder_type {
> CXL_DECODER_DEVMEM = 2,
> diff --git a/include/cxl/hdm.h b/include/cxl/hdm.h
> index 219b9bb67440..d5e7efd2ffc0 100644
> --- a/include/cxl/hdm.h
> +++ b/include/cxl/hdm.h
> @@ -16,4 +16,29 @@ struct cxl_endpoint_decoder_settings {
> u64 skip;
> };
>
> +/**
> + * struct cxl_hdm_info - cached CXL HDM state for a PCI device
> + * @decoder_count: number of entries in @settings
> + * @hdm_bar: PCI BAR containing the HDM decoder capability
> + * @hdm_offset: offset of the HDM decoder capability in @hdm_bar
> + * @hdm_size: size of the HDM decoder register block
> + * @global_ctrl: HDM decoder global control register
> + * @dvsec_ctrl: CXL DVSEC control register
> + * @dvsec_ctrl_valid: whether @dvsec_ctrl contains valid state
> + * @settings: per-endpoint-decoder programming state
> + *
> + * Publication through pci_dev.hdm and all mutable fields are protected by
> + * cxl_rwsem.dpa.
> + */
> +struct cxl_hdm_info {
> + int decoder_count;
> + int hdm_bar;
> + resource_size_t hdm_offset;
> + resource_size_t hdm_size;
> + u32 global_ctrl;
> + u16 dvsec_ctrl;
> + bool dvsec_ctrl_valid;
> + struct cxl_endpoint_decoder_settings settings[] __counted_by(decoder_count);
> +};
> +
> #endif /* __CXL_HDM_H__ */
> diff --git a/include/linux/pci.h b/include/linux/pci.h
> index d31a8d107b1e..7bb37fcb556d 100644
> --- a/include/linux/pci.h
> +++ b/include/linux/pci.h
> @@ -339,6 +339,9 @@ struct pcie_link_state;
> struct pci_sriov;
> struct pci_p2pdma;
> struct rcec_ea;
> +#ifdef CONFIG_CXL_RESET
> +struct cxl_hdm_info;
> +#endif
>
> /* struct pci_dev - describes a PCI device
> *
> @@ -566,6 +569,9 @@ struct pci_dev {
> #ifdef CONFIG_PCI_DOE
> struct xarray doe_mbs; /* Data Object Exchange mailboxes */
> #endif
> +#ifdef CONFIG_CXL_RESET
> + struct cxl_hdm_info *hdm; /* CXL HDM decoder state */
> +#endif
> #ifdef CONFIG_PCI_NPEM
> struct npem *npem; /* Native PCIe Enclosure Management */
> #endif
next prev parent reply other threads:[~2026-10-26 22:56 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-11 2:14 [PATCH v15 00/16] PCI/CXL: Add CXL reset support for Type 2 devices Srirangan Madhavan
2026-10-11 2:14 ` [PATCH v15 01/16] cxl: Drop stale decoder interleave limit comment Srirangan Madhavan
2026-10-27 4:13 ` Alison Schofield
2026-10-11 2:14 ` [PATCH v15 02/16] cxl: Share CXL port upstream PCI device lookup Srirangan Madhavan
2026-10-11 2:14 ` [PATCH v15 03/16] cxl: Move decoder declarations to shared header Srirangan Madhavan
2026-10-11 2:14 ` [PATCH v15 04/16] cxl: Embed decoder configuration in a standalone structure Srirangan Madhavan
2026-10-11 2:14 ` [PATCH v15 05/16] cxl: Introduce endpoint HDM decoder settings Srirangan Madhavan
2026-10-26 22:20 ` Dave Jiang
2026-10-27 6:23 ` Li Ming
2026-10-11 2:14 ` [PATCH v15 06/16] cxl: Move HDM decoder helpers to built-in code Srirangan Madhavan
2026-10-26 22:32 ` Dave Jiang
2026-10-27 6:24 ` Li Ming
2026-10-11 2:14 ` [PATCH v15 07/16] cxl: Share HDM decoder register unpacking Srirangan Madhavan
2026-10-26 22:41 ` Dave Jiang
2026-10-27 6:31 ` Li Ming
2026-10-11 2:14 ` [PATCH v15 08/16] cxl: Refresh cached PCI HDM decoder settings Srirangan Madhavan
2026-10-26 22:56 ` Dave Jiang [this message]
2026-10-27 6:50 ` Li Ming
2026-10-11 2:14 ` [PATCH v15 09/16] PCI/CXL: Cache endpoint HDM state during PCI enumeration Srirangan Madhavan
2026-10-27 8:07 ` Li Ming
2026-10-11 2:14 ` [PATCH v15 10/16] PCI/CXL: Add CXL Device Reset sequencing Srirangan Madhavan
2026-10-11 2:14 ` [PATCH v15 11/16] cxl: Validate and synchronize HDM ranges around reset Srirangan Madhavan
2026-10-27 3:25 ` Alison Schofield
2026-10-27 4:32 ` Alison Schofield
2026-10-11 2:14 ` [PATCH v15 12/16] PCI/CXL: Reject reset with unsafe function scope Srirangan Madhavan
2026-10-11 2:14 ` [PATCH v15 13/16] PCI/CXL: Restore CXL state after PCI reset Srirangan Madhavan
2026-10-27 3:56 ` Alison Schofield
2026-10-11 2:14 ` [PATCH v15 14/16] PCI/CXL: Expose CXL Reset as a PCI reset method Srirangan Madhavan
2026-10-11 2:14 ` [PATCH v15 15/16] PCI/CXL: Restore CXL state after CXL bus reset Srirangan Madhavan
2026-10-11 2:14 ` [PATCH v15 16/16] tools/testing/cxl: Add HDM decoder range checks Srirangan Madhavan
2026-10-27 2:41 ` Alison Schofield
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=db212bda-9642-4b78-9bb0-c75aa60df401@intel.com \
--to=dave.jiang@intel.com \
--cc=alex.williamson@redhat.com \
--cc=alison.schofield@intel.com \
--cc=alwilliamson@nvidia.com \
--cc=bhelgaas@google.com \
--cc=dave@stgolabs.net \
--cc=icheng@nvidia.com \
--cc=ira.weiny@intel.com \
--cc=jan@nvidia.com \
--cc=jic23@kernel.org \
--cc=linux-cxl@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pci@vger.kernel.org \
--cc=linux-tegra@vger.kernel.org \
--cc=mhonap@nvidia.com \
--cc=skancherla@nvidia.com \
--cc=smadhavan@nvidia.com \
--cc=vaslot@nvidia.com \
--cc=vishal.l.verma@intel.com \
--cc=vsethi@nvidia.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®