qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Klaus Jensen <its@irrelevant.dk>
To: "Keith Busch" <kbusch@kernel.org>,
	"Klaus Jensen" <its@irrelevant.dk>,
	"Eduardo Habkost" <eduardo@habkost.net>,
	"Marcel Apfelbaum" <marcel.apfelbaum@gmail.com>,
	"Philippe Mathieu-Daudé" <philmd@linaro.org>,
	"Yanan Wang" <wangyanan55@huawei.com>
Cc: Julien Grall <julien@xen.org>,
	qemu-block@nongnu.org,  qemu-devel@nongnu.org,
	Klaus Jensen <k.jensen@samsung.com>
Subject: [PATCH 2/2] hw/nvme: add machine compatibility parameter to enable msix exclusive bar
Date: Sun, 10 Mar 2024 12:07:26 +0100	[thread overview]
Message-ID: <20240310-fix-msix-exclusive-bar-v1-2-4483205ae22e@samsung.com> (raw)
In-Reply-To: <20240310-fix-msix-exclusive-bar-v1-0-4483205ae22e@samsung.com>

From: Klaus Jensen <k.jensen@samsung.com>

Commit 1901b4967c3f ("hw/block/nvme: move msix table and pba to BAR 0")
moved the MSI-X table and PBA to BAR 0 to make room for enabling CMR and
PMR at the same time. As reported by Julien Grall in #2184, this breaks
migration through system hibernation.

Add a machine compatibility parameter and set it on machines pre 6.0 to
enable the old behavior automatically, restoring the hibernation
migration support.

Reported-by: Julien Grall <julien@xen.org>
Tested-by: Julien Grall <julien@xen.org>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
---
 hw/core/machine.c |  1 +
 hw/nvme/ctrl.c    | 51 +++++++++++++++++++++++++++++++++++----------------
 hw/nvme/nvme.h    |  1 +
 3 files changed, 37 insertions(+), 16 deletions(-)

diff --git a/hw/core/machine.c b/hw/core/machine.c
index 9ac5d5389a6c..f3012bca1370 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -100,6 +100,7 @@ GlobalProperty hw_compat_5_2[] = {
     { "PIIX4_PM", "smm-compat", "on"},
     { "virtio-blk-device", "report-discard-granularity", "off" },
     { "virtio-net-pci-base", "vectors", "3"},
+    { "nvme", "msix-exclusive-bar", "on"},
 };
 const size_t hw_compat_5_2_len = G_N_ELEMENTS(hw_compat_5_2);
 
diff --git a/hw/nvme/ctrl.c b/hw/nvme/ctrl.c
index 8cca8a762124..649467723e7e 100644
--- a/hw/nvme/ctrl.c
+++ b/hw/nvme/ctrl.c
@@ -7798,6 +7798,11 @@ static bool nvme_check_params(NvmeCtrl *n, Error **errp)
     }
 
     if (n->pmr.dev) {
+        if (params->msix_exclusive_bar) {
+            error_setg(errp, "not enough BARs available to enable PMR");
+            return false;
+        }
+
         if (host_memory_backend_is_mapped(n->pmr.dev)) {
             error_setg(errp, "can't use already busy memdev: %s",
                        object_get_canonical_path_component(OBJECT(n->pmr.dev)));
@@ -8101,24 +8106,36 @@ static bool nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp)
         pcie_ari_init(pci_dev, 0x100);
     }
 
-    /* add one to max_ioqpairs to account for the admin queue pair */
-    bar_size = nvme_mbar_size(n->params.max_ioqpairs + 1, n->params.msix_qsize,
-                              &msix_table_offset, &msix_pba_offset);
-
-    memory_region_init(&n->bar0, OBJECT(n), "nvme-bar0", bar_size);
-    memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n, "nvme",
-                          msix_table_offset);
-    memory_region_add_subregion(&n->bar0, 0, &n->iomem);
-
-    if (pci_is_vf(pci_dev)) {
-        pcie_sriov_vf_register_bar(pci_dev, 0, &n->bar0);
-    } else {
+    if (n->params.msix_exclusive_bar && !pci_is_vf(pci_dev)) {
+        bar_size = nvme_mbar_size(n->params.max_ioqpairs + 1, 0, NULL, NULL);
+        memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n, "nvme",
+                              bar_size);
         pci_register_bar(pci_dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY |
-                         PCI_BASE_ADDRESS_MEM_TYPE_64, &n->bar0);
+                         PCI_BASE_ADDRESS_MEM_TYPE_64, &n->iomem);
+        ret = msix_init_exclusive_bar(pci_dev, n->params.msix_qsize, 4, errp);
+    } else {
+        /* add one to max_ioqpairs to account for the admin queue pair */
+        bar_size = nvme_mbar_size(n->params.max_ioqpairs + 1,
+                                  n->params.msix_qsize, &msix_table_offset,
+                                  &msix_pba_offset);
+
+        memory_region_init(&n->bar0, OBJECT(n), "nvme-bar0", bar_size);
+        memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n, "nvme",
+                              msix_table_offset);
+        memory_region_add_subregion(&n->bar0, 0, &n->iomem);
+
+        if (pci_is_vf(pci_dev)) {
+            pcie_sriov_vf_register_bar(pci_dev, 0, &n->bar0);
+        } else {
+            pci_register_bar(pci_dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY |
+                             PCI_BASE_ADDRESS_MEM_TYPE_64, &n->bar0);
+        }
+
+        ret = msix_init(pci_dev, n->params.msix_qsize,
+                        &n->bar0, 0, msix_table_offset,
+                        &n->bar0, 0, msix_pba_offset, 0, errp);
     }
-    ret = msix_init(pci_dev, n->params.msix_qsize,
-                    &n->bar0, 0, msix_table_offset,
-                    &n->bar0, 0, msix_pba_offset, 0, errp);
+
     if (ret == -ENOTSUP) {
         /* report that msix is not supported, but do not error out */
         warn_report_err(*errp);
@@ -8416,6 +8433,8 @@ static Property nvme_props[] = {
                       params.sriov_max_vi_per_vf, 0),
     DEFINE_PROP_UINT8("sriov_max_vq_per_vf", NvmeCtrl,
                       params.sriov_max_vq_per_vf, 0),
+    DEFINE_PROP_BOOL("msix-exclusive-bar", NvmeCtrl, params.msix_exclusive_bar,
+                     false),
     DEFINE_PROP_END_OF_LIST(),
 };
 
diff --git a/hw/nvme/nvme.h b/hw/nvme/nvme.h
index 5f2ae7b28b9c..eccf14acc906 100644
--- a/hw/nvme/nvme.h
+++ b/hw/nvme/nvme.h
@@ -522,6 +522,7 @@ typedef struct NvmeParams {
     uint16_t sriov_vi_flexible;
     uint8_t  sriov_max_vq_per_vf;
     uint8_t  sriov_max_vi_per_vf;
+    bool     msix_exclusive_bar;
 } NvmeParams;
 
 typedef struct NvmeCtrl {

-- 
2.43.0



  parent reply	other threads:[~2024-03-10 11:09 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-03-10 11:07 [PATCH 0/2] hw/nvme: fix hibernation-based migration Klaus Jensen
2024-03-10 11:07 ` [PATCH 1/2] hw/nvme: generalize the mbar size helper Klaus Jensen
2024-03-10 11:07 ` Klaus Jensen [this message]
2024-03-10 11:12 ` [PATCH 0/2] hw/nvme: fix hibernation-based migration Klaus Jensen
2024-03-11 11:15 ` Jesper Wendel Devantier

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=20240310-fix-msix-exclusive-bar-v1-2-4483205ae22e@samsung.com \
    --to=its@irrelevant.dk \
    --cc=eduardo@habkost.net \
    --cc=julien@xen.org \
    --cc=k.jensen@samsung.com \
    --cc=kbusch@kernel.org \
    --cc=marcel.apfelbaum@gmail.com \
    --cc=philmd@linaro.org \
    --cc=qemu-block@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    --cc=wangyanan55@huawei.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;
as well as URLs for NNTP newsgroup(s).