From: Srirangan Madhavan <smadhavan@nvidia.com>
To: linux-cxl@vger.kernel.org, linux-pci@vger.kernel.org,
linux-kernel@vger.kernel.org
Cc: vsethi@nvidia.com, alwilliamson@nvidia.com,
Dan Williams <danwilliams@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,
Srirangan Madhavan <smadhavan@nvidia.com>
Subject: [PATCH v6 4/9] PCI/CXL: Add sibling function coordination for reset
Date: Thu, 28 May 2026 08:31:49 +0000 [thread overview]
Message-ID: <20260528083154.137979-5-smadhavan@nvidia.com> (raw)
In-Reply-To: <20260528083154.137979-1-smadhavan@nvidia.com>
Add helpers to collect CXL sibling PCI functions affected by a CXL reset
and prepare them for reset by saving and disabling them. Restore those
siblings and drop their references when reset coordination completes.
Use the Non-CXL Function Map DVSEC to exclude non-CXL functions, and
filter remaining siblings to functions that advertise CXL.cache or
CXL.mem capability.
Use pci_dev_trylock() for sibling locking and unwind on contention or
allocation failure, so competing reset paths fail with an errno.
Signed-off-by: Srirangan Madhavan <smadhavan@nvidia.com>
---
drivers/cxl/core/pci.c | 207 ++++++++++++++++++++++++++++++++++
include/uapi/linux/pci_regs.h | 2 +
2 files changed, 209 insertions(+)
diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index 318744695f62..01effbb4e7cd 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -1,9 +1,11 @@
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright(c) 2021 Intel Corporation. All rights reserved. */
#include <linux/units.h>
+#include <linux/bitmap.h>
#include <linux/io-64-nonatomic-lo-hi.h>
#include <linux/device.h>
#include <linux/delay.h>
+#include <linux/iommu.h>
#include <linux/memregion.h>
#include <linux/pci.h>
#include <linux/pci-doe.h>
@@ -15,6 +17,10 @@
#include "core.h"
#include "trace.h"
+#define CXL_RESET_MAX_FUNCTIONS 256
+#define CXL_RESET_FUNCTION_MAP_REGS (CXL_RESET_MAX_FUNCTIONS / 32)
+#define CXL_RESET_SIBLINGS_INIT 8
+
/**
* DOC: cxl core pci
*
@@ -1096,3 +1102,204 @@ cxl_reset_flush_cpu_caches(struct cxl_reset_region_context *ctx)
return 0;
}
+
+struct cxl_reset_context {
+ struct pci_dev *target;
+ struct pci_dev **siblings;
+ int nr_siblings;
+ int sibling_capacity;
+ int nr_siblings_prepared;
+};
+
+struct cxl_reset_walk_ctx {
+ struct cxl_reset_context *ctx;
+ unsigned long *non_cxl_func_map;
+ int rc;
+};
+
+static void
+cxl_reset_read_non_cxl_func_map(struct pci_dev *pdev,
+ unsigned long *non_cxl_func_map)
+{
+ u32 map[CXL_RESET_FUNCTION_MAP_REGS] = {};
+ u16 dvsec;
+ int rc, i;
+
+ bitmap_zero(non_cxl_func_map, CXL_RESET_MAX_FUNCTIONS);
+
+ dvsec = pci_find_dvsec_capability(pdev, PCI_VENDOR_ID_CXL,
+ PCI_DVSEC_CXL_FUNCTION_MAP);
+ if (!dvsec)
+ return;
+
+ for (i = 0; i < CXL_RESET_FUNCTION_MAP_REGS; i++) {
+ rc = pci_read_config_dword(pdev,
+ dvsec + PCI_DVSEC_CXL_FUNCTION_MAP_REG +
+ i * sizeof(map[i]), &map[i]);
+ if (rc) {
+ pci_warn(pdev,
+ "failed to read CXL Function Map; treating all siblings as CXL: %d\n",
+ rc);
+ bitmap_zero(non_cxl_func_map, CXL_RESET_MAX_FUNCTIONS);
+ return;
+ }
+ }
+
+ bitmap_from_arr32(non_cxl_func_map, map, CXL_RESET_MAX_FUNCTIONS);
+}
+
+static bool cxl_reset_is_cxl_sibling(struct pci_dev *pdev,
+ struct pci_dev *sibling,
+ unsigned long *non_cxl_func_map)
+{
+ if (sibling == pdev || sibling->bus != pdev->bus)
+ return false;
+
+ if (pci_ari_enabled(pdev->bus))
+ return !test_bit(sibling->devfn, non_cxl_func_map);
+
+ if (PCI_SLOT(sibling->devfn) != PCI_SLOT(pdev->devfn))
+ return false;
+
+ return !test_bit(PCI_FUNC(sibling->devfn) * 32 +
+ PCI_SLOT(sibling->devfn), non_cxl_func_map);
+}
+
+static bool cxl_reset_has_cache_or_mem(struct pci_dev *pdev)
+{
+ u16 dvsec, cap;
+
+ dvsec = pci_find_dvsec_capability(pdev, PCI_VENDOR_ID_CXL,
+ PCI_DVSEC_CXL_DEVICE);
+ if (!dvsec)
+ return false;
+
+ if (pci_read_config_word(pdev, dvsec + PCI_DVSEC_CXL_CAP, &cap))
+ return false;
+
+ return cap & (PCI_DVSEC_CXL_CACHE_CAPABLE | PCI_DVSEC_CXL_MEM_CAPABLE);
+}
+
+static int cxl_reset_add_sibling(struct cxl_reset_context *ctx,
+ struct pci_dev *sibling)
+{
+ struct pci_dev **siblings;
+ int capacity;
+
+ if (ctx->nr_siblings < ctx->sibling_capacity)
+ goto add;
+
+ capacity = ctx->sibling_capacity ? ctx->sibling_capacity * 2 :
+ CXL_RESET_SIBLINGS_INIT;
+ siblings = krealloc(ctx->siblings, capacity * sizeof(*siblings),
+ GFP_KERNEL);
+ if (!siblings)
+ return -ENOMEM;
+
+ ctx->siblings = siblings;
+ ctx->sibling_capacity = capacity;
+
+add:
+ pci_dev_get(sibling);
+ ctx->siblings[ctx->nr_siblings++] = sibling;
+ return 0;
+}
+
+static int cxl_reset_collect_sibling(struct pci_dev *sibling, void *data)
+{
+ struct cxl_reset_walk_ctx *wctx = data;
+ struct cxl_reset_context *ctx = wctx->ctx;
+ struct pci_dev *pdev = ctx->target;
+
+ if (!cxl_reset_is_cxl_sibling(pdev, sibling, wctx->non_cxl_func_map))
+ return 0;
+
+ if (!cxl_reset_has_cache_or_mem(sibling))
+ return 0;
+
+ wctx->rc = cxl_reset_add_sibling(ctx, sibling);
+ return wctx->rc;
+}
+
+static int cxl_reset_collect_siblings(struct cxl_reset_context *ctx)
+{
+ DECLARE_BITMAP(non_cxl_func_map, CXL_RESET_MAX_FUNCTIONS);
+ struct cxl_reset_walk_ctx wctx = {
+ .ctx = ctx,
+ .non_cxl_func_map = non_cxl_func_map,
+ };
+
+ cxl_reset_read_non_cxl_func_map(ctx->target, non_cxl_func_map);
+ pci_walk_bus(ctx->target->bus, cxl_reset_collect_sibling, &wctx);
+ return wctx.rc;
+}
+
+static void cxl_pci_functions_reset_done(struct cxl_reset_context *ctx)
+{
+ int i;
+
+ for (i = ctx->nr_siblings_prepared - 1; i >= 0; i--) {
+ struct pci_dev *sibling = ctx->siblings[i];
+
+ pci_dev_reset_iommu_done(sibling);
+ pci_dev_restore(sibling);
+ pci_dev_unlock(sibling);
+ }
+
+ for (i = 0; i < ctx->nr_siblings; i++)
+ pci_dev_put(ctx->siblings[i]);
+
+ kfree(ctx->siblings);
+ ctx->siblings = NULL;
+ ctx->nr_siblings = 0;
+ ctx->sibling_capacity = 0;
+ ctx->nr_siblings_prepared = 0;
+}
+
+static int __maybe_unused
+cxl_pci_functions_reset_prepare(struct cxl_reset_context *ctx)
+{
+ int rc, i;
+
+ ctx->siblings = NULL;
+ ctx->nr_siblings = 0;
+ ctx->sibling_capacity = 0;
+ ctx->nr_siblings_prepared = 0;
+
+ rc = cxl_reset_collect_siblings(ctx);
+ if (rc)
+ goto err;
+
+ for (i = 0; i < ctx->nr_siblings; i++) {
+ struct pci_dev *sibling = ctx->siblings[i];
+
+ if (!pci_dev_trylock(sibling)) {
+ rc = -EAGAIN;
+ goto err;
+ }
+
+ pci_dev_save_and_disable(sibling);
+ rc = pci_dev_reset_iommu_prepare(sibling);
+ if (rc) {
+ pci_err(sibling,
+ "failed to block IOMMU for CXL reset: %d\n",
+ rc);
+ /*
+ * Undo save_and_disable() for this sibling. IOMMU
+ * prepare failed, so this sibling is not counted in
+ * nr_siblings_prepared and must not get iommu_done().
+ */
+ pci_dev_restore(sibling);
+ pci_dev_unlock(sibling);
+ goto err;
+ }
+
+ ctx->nr_siblings_prepared++;
+ }
+
+ return 0;
+
+err:
+ cxl_pci_functions_reset_done(ctx);
+ return rc;
+}
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index 14f634ab9350..fa1fcd26af01 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -1349,6 +1349,7 @@
/* CXL r4.0, 8.1.3: PCIe DVSEC for CXL Device */
#define PCI_DVSEC_CXL_DEVICE 0
#define PCI_DVSEC_CXL_CAP 0xA
+#define PCI_DVSEC_CXL_CACHE_CAPABLE _BITUL(0)
#define PCI_DVSEC_CXL_MEM_CAPABLE _BITUL(2)
#define PCI_DVSEC_CXL_HDM_COUNT __GENMASK(5, 4)
#define PCI_DVSEC_CXL_CTRL 0xC
@@ -1366,6 +1367,7 @@
/* CXL r4.0, 8.1.4: Non-CXL Function Map DVSEC */
#define PCI_DVSEC_CXL_FUNCTION_MAP 2
+#define PCI_DVSEC_CXL_FUNCTION_MAP_REG 0x0C
/* CXL r4.0, 8.1.5: Extensions DVSEC for Ports */
#define PCI_DVSEC_CXL_PORT 3
--
2.43.0
next prev parent reply other threads:[~2026-05-28 8:32 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-05-28 8:31 [PATCH v6 0/9] cxl: Add cxl_reset sysfs attribute for memdevs Srirangan Madhavan
2026-05-28 8:31 ` [PATCH v6 1/9] cxl/hdm: Add helpers to restore and commit memdev decoders Srirangan Madhavan
2026-05-28 11:06 ` Richard Cheng
2026-05-28 8:31 ` [PATCH v6 2/9] PCI: Export pci_dev_save_and_disable() and pci_dev_restore() Srirangan Madhavan
2026-05-28 8:31 ` [PATCH v6 3/9] cxl: Add reset-idle and cache flush helpers Srirangan Madhavan
2026-05-28 8:31 ` Srirangan Madhavan [this message]
2026-05-28 11:15 ` [PATCH v6 4/9] PCI/CXL: Add sibling function coordination for reset Richard Cheng
2026-05-28 8:31 ` [PATCH v6 5/9] cxl/pci: Add CXL DVSEC reset helper Srirangan Madhavan
2026-05-28 8:31 ` [PATCH v6 6/9] cxl/pci: Track memdevs affected by CXL reset Srirangan Madhavan
2026-05-28 8:31 ` [PATCH v6 7/9] cxl/pci: Orchestrate CXL reset for affected memdevs Srirangan Madhavan
2026-05-28 8:31 ` [PATCH v6 8/9] cxl/memdev: Add cxl_reset sysfs attribute Srirangan Madhavan
2026-05-28 8:31 ` [PATCH v6 9/9] Documentation/ABI: Document CXL memdev cxl_reset Srirangan Madhavan
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=20260528083154.137979-5-smadhavan@nvidia.com \
--to=smadhavan@nvidia.com \
--cc=alwilliamson@nvidia.com \
--cc=danwilliams@nvidia.com \
--cc=icheng@nvidia.com \
--cc=jan@nvidia.com \
--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=vaslot@nvidia.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