All of lore.kernel.org
 help / color / mirror / Atom feed
From: Klaus Jensen <its@irrelevant.dk>
To: Peter Maydell <peter.maydell@linaro.org>, qemu-devel@nongnu.org
Cc: "Stefan Hajnoczi" <stefanha@redhat.com>,
	"Igor Mammedov" <imammedo@redhat.com>,
	"Ani Sinha" <ani@anisinha.ca>, "Hanna Reitz" <hreitz@redhat.com>,
	"Kevin Wolf" <kwolf@redhat.com>,
	"Michael S. Tsirkin" <mst@redhat.com>,
	"Klaus Jensen" <its@irrelevant.dk>,
	qemu-block@nongnu.org, "Keith Busch" <kbusch@kernel.org>,
	"Fam Zheng" <fam@euphon.net>,
	"Philippe Mathieu-Daudé" <f4bug@amsat.org>,
	"Marcel Apfelbaum" <marcel.apfelbaum@gmail.com>,
	"Łukasz Gieryk" <lukasz.gieryk@linux.intel.com>,
	"Klaus Jensen" <k.jensen@samsung.com>
Subject: [PULL 04/15] hw/nvme: Implement the Function Level Reset
Date: Thu, 23 Jun 2022 23:34:31 +0200	[thread overview]
Message-ID: <20220623213442.67789-5-its@irrelevant.dk> (raw)
In-Reply-To: <20220623213442.67789-1-its@irrelevant.dk>

From: Łukasz Gieryk <lukasz.gieryk@linux.intel.com>

This patch implements the Function Level Reset, a feature currently not
implemented for the Nvme device, while listed as a mandatory ("shall")
in the 1.4 spec.

The implementation reuses FLR-related building blocks defined for the
pci-bridge module, and follows the same logic:
    - FLR capability is advertised in the PCIE config,
    - custom pci_write_config callback detects a write to the trigger
      register and performs the PCI reset,
    - which, eventually, calls the custom dc->reset handler.

Depending on reset type, parts of the state should (or should not) be
cleared. To distinguish the type of reset, an additional parameter is
passed to the reset function.

This patch also enables advertisement of the Power Management PCI
capability. The main reason behind it is to announce the no_soft_reset=1
bit, to signal SR-IOV support where each VF can be reset individually.

The implementation purposedly ignores writes to the PMCS.PS register,
as even such naïve behavior is enough to correctly handle the D3->D0
transition.

It’s worth to note, that the power state transition back to to D3, with
all the corresponding side effects, wasn't and stil isn't handled
properly.

Signed-off-by: Łukasz Gieryk <lukasz.gieryk@linux.intel.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
---
 hw/nvme/ctrl.c       | 52 ++++++++++++++++++++++++++++++++++++++++----
 hw/nvme/nvme.h       |  5 +++++
 hw/nvme/trace-events |  1 +
 3 files changed, 54 insertions(+), 4 deletions(-)

diff --git a/hw/nvme/ctrl.c b/hw/nvme/ctrl.c
index b031212758cb..5ae80f114003 100644
--- a/hw/nvme/ctrl.c
+++ b/hw/nvme/ctrl.c
@@ -5903,7 +5903,7 @@ static void nvme_process_sq(void *opaque)
     }
 }
 
-static void nvme_ctrl_reset(NvmeCtrl *n)
+static void nvme_ctrl_reset(NvmeCtrl *n, NvmeResetType rst)
 {
     NvmeNamespace *ns;
     int i;
@@ -5935,7 +5935,9 @@ static void nvme_ctrl_reset(NvmeCtrl *n)
     }
 
     if (!pci_is_vf(&n->parent_obj) && n->params.sriov_max_vfs) {
-        pcie_sriov_pf_disable_vfs(&n->parent_obj);
+        if (rst != NVME_RESET_CONTROLLER) {
+            pcie_sriov_pf_disable_vfs(&n->parent_obj);
+        }
     }
 
     n->aer_queued = 0;
@@ -6169,7 +6171,7 @@ static void nvme_write_bar(NvmeCtrl *n, hwaddr offset, uint64_t data,
             }
         } else if (!NVME_CC_EN(data) && NVME_CC_EN(cc)) {
             trace_pci_nvme_mmio_stopped();
-            nvme_ctrl_reset(n);
+            nvme_ctrl_reset(n, NVME_RESET_CONTROLLER);
             cc = 0;
             csts &= ~NVME_CSTS_READY;
         }
@@ -6727,6 +6729,28 @@ static void nvme_init_sriov(NvmeCtrl *n, PCIDevice *pci_dev, uint16_t offset,
                               PCI_BASE_ADDRESS_MEM_TYPE_64, bar_size);
 }
 
+static int nvme_add_pm_capability(PCIDevice *pci_dev, uint8_t offset)
+{
+    Error *err = NULL;
+    int ret;
+
+    ret = pci_add_capability(pci_dev, PCI_CAP_ID_PM, offset,
+                             PCI_PM_SIZEOF, &err);
+    if (err) {
+        error_report_err(err);
+        return ret;
+    }
+
+    pci_set_word(pci_dev->config + offset + PCI_PM_PMC,
+                 PCI_PM_CAP_VER_1_2);
+    pci_set_word(pci_dev->config + offset + PCI_PM_CTRL,
+                 PCI_PM_CTRL_NO_SOFT_RESET);
+    pci_set_word(pci_dev->wmask + offset + PCI_PM_CTRL,
+                 PCI_PM_CTRL_STATE_MASK);
+
+    return 0;
+}
+
 static int nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp)
 {
     uint8_t *pci_conf = pci_dev->config;
@@ -6748,7 +6772,9 @@ static int nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp)
     }
 
     pci_config_set_class(pci_conf, PCI_CLASS_STORAGE_EXPRESS);
+    nvme_add_pm_capability(pci_dev, 0x60);
     pcie_endpoint_cap_init(pci_dev, 0x80);
+    pcie_cap_flr_init(pci_dev);
     if (n->params.sriov_max_vfs) {
         pcie_ari_init(pci_dev, 0x100, 1);
     }
@@ -6999,7 +7025,7 @@ static void nvme_exit(PCIDevice *pci_dev)
     NvmeNamespace *ns;
     int i;
 
-    nvme_ctrl_reset(n);
+    nvme_ctrl_reset(n, NVME_RESET_FUNCTION);
 
     if (n->subsys) {
         for (i = 1; i <= NVME_MAX_NAMESPACES; i++) {
@@ -7098,6 +7124,22 @@ static void nvme_set_smart_warning(Object *obj, Visitor *v, const char *name,
     }
 }
 
+static void nvme_pci_reset(DeviceState *qdev)
+{
+    PCIDevice *pci_dev = PCI_DEVICE(qdev);
+    NvmeCtrl *n = NVME(pci_dev);
+
+    trace_pci_nvme_pci_reset();
+    nvme_ctrl_reset(n, NVME_RESET_FUNCTION);
+}
+
+static void nvme_pci_write_config(PCIDevice *dev, uint32_t address,
+                                  uint32_t val, int len)
+{
+    pci_default_write_config(dev, address, val, len);
+    pcie_cap_flr_write_config(dev, address, val, len);
+}
+
 static const VMStateDescription nvme_vmstate = {
     .name = "nvme",
     .unmigratable = 1,
@@ -7109,6 +7151,7 @@ static void nvme_class_init(ObjectClass *oc, void *data)
     PCIDeviceClass *pc = PCI_DEVICE_CLASS(oc);
 
     pc->realize = nvme_realize;
+    pc->config_write = nvme_pci_write_config;
     pc->exit = nvme_exit;
     pc->class_id = PCI_CLASS_STORAGE_EXPRESS;
     pc->revision = 2;
@@ -7117,6 +7160,7 @@ static void nvme_class_init(ObjectClass *oc, void *data)
     dc->desc = "Non-Volatile Memory Express";
     device_class_set_props(dc, nvme_props);
     dc->vmsd = &nvme_vmstate;
+    dc->reset = nvme_pci_reset;
 }
 
 static void nvme_instance_init(Object *obj)
diff --git a/hw/nvme/nvme.h b/hw/nvme/nvme.h
index b66421cdf9e8..7b317d3dc469 100644
--- a/hw/nvme/nvme.h
+++ b/hw/nvme/nvme.h
@@ -488,6 +488,11 @@ typedef struct NvmeCtrl {
     NvmeSecCtrlList sec_ctrl_list;
 } NvmeCtrl;
 
+typedef enum NvmeResetType {
+    NVME_RESET_FUNCTION   = 0,
+    NVME_RESET_CONTROLLER = 1,
+} NvmeResetType;
+
 static inline NvmeNamespace *nvme_ns(NvmeCtrl *n, uint32_t nsid)
 {
     if (!nsid || nsid > NVME_MAX_NAMESPACES) {
diff --git a/hw/nvme/trace-events b/hw/nvme/trace-events
index 889bbb3101e4..b07864c57322 100644
--- a/hw/nvme/trace-events
+++ b/hw/nvme/trace-events
@@ -110,6 +110,7 @@ pci_nvme_zd_extension_set(uint32_t zone_idx) "set descriptor extension for zone_
 pci_nvme_clear_ns_close(uint32_t state, uint64_t slba) "zone state=%"PRIu32", slba=%"PRIu64" transitioned to Closed state"
 pci_nvme_clear_ns_reset(uint32_t state, uint64_t slba) "zone state=%"PRIu32", slba=%"PRIu64" transitioned to Empty state"
 pci_nvme_zoned_zrwa_implicit_flush(uint64_t zslba, uint32_t nlb) "zslba 0x%"PRIx64" nlb %"PRIu32""
+pci_nvme_pci_reset(void) "PCI Function Level Reset"
 
 # error conditions
 pci_nvme_err_mdts(size_t len) "len %zu"
-- 
2.36.1



  parent reply	other threads:[~2022-06-23 21:47 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-06-23 21:34 [PULL 00/15] hw/nvme updates Klaus Jensen
2022-06-23 21:34 ` [PULL 01/15] hw/nvme: Add support for SR-IOV Klaus Jensen
2022-06-23 21:34 ` [PULL 02/15] hw/nvme: Add support for Primary Controller Capabilities Klaus Jensen
2022-06-23 21:34 ` [PULL 03/15] hw/nvme: Add support for Secondary Controller List Klaus Jensen
2022-06-23 21:34 ` Klaus Jensen [this message]
2022-06-23 21:34 ` [PULL 05/15] hw/nvme: Make max_ioqpairs and msix_qsize configurable in runtime Klaus Jensen
2022-06-23 21:34 ` [PULL 06/15] hw/nvme: Remove reg_size variable and update BAR0 size calculation Klaus Jensen
2022-06-23 21:34 ` [PULL 07/15] hw/nvme: Calculate BAR attributes in a function Klaus Jensen
2022-06-23 21:34 ` [PULL 08/15] hw/nvme: Initialize capability structures for primary/secondary controllers Klaus Jensen
2022-06-23 21:34 ` [PULL 09/15] hw/nvme: Add support for the Virtualization Management command Klaus Jensen
2022-06-23 21:34 ` [PULL 10/15] docs: Add documentation for SR-IOV and Virtualization Enhancements Klaus Jensen
2022-06-23 21:34 ` [PULL 11/15] hw/nvme: Update the initalization place for the AER queue Klaus Jensen
2022-06-23 21:34 ` [PULL 12/15] hw/acpi: Make the PCI hot-plug aware of SR-IOV Klaus Jensen
2022-06-23 21:34 ` [PULL 13/15] hw/nvme: clean up CC register write logic Klaus Jensen
2022-06-23 21:34 ` [PULL 14/15] Revert "hw/block/nvme: add support for sgl bit bucket descriptor" Klaus Jensen
2022-06-23 21:34 ` [PULL 15/15] hw/nvme: clear aen mask on reset Klaus Jensen
2022-06-23 23:28 ` [PULL 00/15] hw/nvme updates Richard Henderson

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=20220623213442.67789-5-its@irrelevant.dk \
    --to=its@irrelevant.dk \
    --cc=ani@anisinha.ca \
    --cc=f4bug@amsat.org \
    --cc=fam@euphon.net \
    --cc=hreitz@redhat.com \
    --cc=imammedo@redhat.com \
    --cc=k.jensen@samsung.com \
    --cc=kbusch@kernel.org \
    --cc=kwolf@redhat.com \
    --cc=lukasz.gieryk@linux.intel.com \
    --cc=marcel.apfelbaum@gmail.com \
    --cc=mst@redhat.com \
    --cc=peter.maydell@linaro.org \
    --cc=qemu-block@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    --cc=stefanha@redhat.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.