From: Akihiko Odaki <akihiko.odaki@daynix.com>
To: "Philippe Mathieu-Daudé" <philmd@linaro.org>,
"Michael S. Tsirkin" <mst@redhat.com>,
"Marcel Apfelbaum" <marcel.apfelbaum@gmail.com>,
"Alex Williamson" <alex.williamson@redhat.com>,
"Cédric Le Goater" <clg@redhat.com>,
"Paolo Bonzini" <pbonzini@redhat.com>,
"Daniel P. Berrangé" <berrange@redhat.com>,
"Eduardo Habkost" <eduardo@habkost.net>,
"Sriram Yagnaraman" <sriram.yagnaraman@ericsson.com>,
"Jason Wang" <jasowang@redhat.com>,
"Keith Busch" <kbusch@kernel.org>,
"Klaus Jensen" <its@irrelevant.dk>,
"Markus Armbruster" <armbru@redhat.com>,
"Matthew Rosato" <mjrosato@linux.ibm.com>,
"Eric Farman" <farman@linux.ibm.com>,
"Harsh Prateek Bora" <harshpb@linux.ibm.com>,
"Shivaprasad G Bhat" <sbhat@linux.ibm.com>
Cc: qemu-devel@nongnu.org, qemu-block@nongnu.org,
Akihiko Odaki <akihiko.odaki@daynix.com>
Subject: [PATCH v17 09/14] pcie_sriov: Reuse SR-IOV VF device instances
Date: Tue, 22 Oct 2024 17:36:46 +0900 [thread overview]
Message-ID: <20241022-reuse-v17-9-bd7c133237e4@daynix.com> (raw)
In-Reply-To: <20241022-reuse-v17-0-bd7c133237e4@daynix.com>
Disable SR-IOV VF devices by reusing code to power down PCI devices
instead of removing them when the guest requests to disable VFs. This
allows to realize devices and report VF realization errors at PF
realization time.
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
---
include/hw/pci/pci.h | 5 ---
include/hw/pci/pci_device.h | 15 ++++++++
include/hw/pci/pcie_sriov.h | 1 -
hw/pci/pci.c | 2 +-
hw/pci/pcie_sriov.c | 94 +++++++++++++++++++--------------------------
5 files changed, 55 insertions(+), 62 deletions(-)
diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h
index fe04b4fafd04..14a869eeaa71 100644
--- a/include/hw/pci/pci.h
+++ b/include/hw/pci/pci.h
@@ -680,9 +680,4 @@ static inline void pci_irq_pulse(PCIDevice *pci_dev)
MSIMessage pci_get_msi_message(PCIDevice *dev, int vector);
void pci_set_enabled(PCIDevice *pci_dev, bool state);
-static inline void pci_set_power(PCIDevice *pci_dev, bool state)
-{
- pci_set_enabled(pci_dev, state);
-}
-
#endif
diff --git a/include/hw/pci/pci_device.h b/include/hw/pci/pci_device.h
index cbc42349d561..5dcabb94d679 100644
--- a/include/hw/pci/pci_device.h
+++ b/include/hw/pci/pci_device.h
@@ -215,6 +215,21 @@ static inline uint16_t pci_get_bdf(PCIDevice *dev)
return PCI_BUILD_BDF(pci_bus_num(pci_get_bus(dev)), dev->devfn);
}
+static inline void pci_set_power(PCIDevice *pci_dev, bool state)
+{
+ /*
+ * Don't change the enabled state of VFs when powering on/off the device.
+ *
+ * When powering on, VFs must not be enabled immediately but they must
+ * wait until the guest configures SR-IOV.
+ * When powering off, their corresponding PFs will be reset and disable
+ * VFs.
+ */
+ if (!pci_is_vf(pci_dev)) {
+ pci_set_enabled(pci_dev, state);
+ }
+}
+
uint16_t pci_requester_id(PCIDevice *dev);
/* DMA access functions */
diff --git a/include/hw/pci/pcie_sriov.h b/include/hw/pci/pcie_sriov.h
index aa704e8f9d9f..70649236c18a 100644
--- a/include/hw/pci/pcie_sriov.h
+++ b/include/hw/pci/pcie_sriov.h
@@ -18,7 +18,6 @@
typedef struct PCIESriovPF {
uint16_t num_vfs; /* Number of virtual functions created */
uint8_t vf_bar_type[PCI_NUM_REGIONS]; /* Store type for each VF bar */
- const char *vfname; /* Reference to the device type used for the VFs */
PCIDevice **vf; /* Pointer to an array of num_vfs VF devices */
} PCIESriovPF;
diff --git a/hw/pci/pci.c b/hw/pci/pci.c
index eff408b4e9f4..7ea751fb869d 100644
--- a/hw/pci/pci.c
+++ b/hw/pci/pci.c
@@ -2904,7 +2904,7 @@ void pci_set_enabled(PCIDevice *d, bool state)
memory_region_set_enabled(&d->bus_master_enable_region,
(pci_get_word(d->config + PCI_COMMAND)
& PCI_COMMAND_MASTER) && d->enabled);
- if (!d->enabled) {
+ if (d->qdev.realized) {
pci_device_reset(d);
}
}
diff --git a/hw/pci/pcie_sriov.c b/hw/pci/pcie_sriov.c
index 91c64c988eb4..f1993bc553c0 100644
--- a/hw/pci/pcie_sriov.c
+++ b/hw/pci/pcie_sriov.c
@@ -20,9 +20,16 @@
#include "qapi/error.h"
#include "trace.h"
-static PCIDevice *register_vf(PCIDevice *pf, int devfn,
- const char *name, uint16_t vf_num);
-static void unregister_vfs(PCIDevice *dev);
+static void unparent_vfs(PCIDevice *dev, uint16_t total_vfs)
+{
+ for (uint16_t i = 0; i < total_vfs; i++) {
+ PCIDevice *vf = dev->exp.sriov_pf.vf[i];
+ object_unparent(OBJECT(vf));
+ object_unref(OBJECT(vf));
+ }
+ g_free(dev->exp.sriov_pf.vf);
+ dev->exp.sriov_pf.vf = NULL;
+}
bool pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset,
const char *vfname, uint16_t vf_dev_id,
@@ -30,6 +37,7 @@ bool pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset,
uint16_t vf_offset, uint16_t vf_stride,
Error **errp)
{
+ BusState *bus = qdev_get_parent_bus(&dev->qdev);
int32_t devfn = dev->devfn + vf_offset;
uint8_t *cfg = dev->config + offset;
uint8_t *wmask;
@@ -44,7 +52,6 @@ bool pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset,
offset, PCI_EXT_CAP_SRIOV_SIZEOF);
dev->exp.sriov_cap = offset;
dev->exp.sriov_pf.num_vfs = 0;
- dev->exp.sriov_pf.vfname = g_strdup(vfname);
dev->exp.sriov_pf.vf = NULL;
pci_set_word(cfg + PCI_SRIOV_VF_OFFSET, vf_offset);
@@ -78,14 +85,34 @@ bool pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset,
qdev_prop_set_bit(&dev->qdev, "multifunction", true);
+ dev->exp.sriov_pf.vf = g_new(PCIDevice *, total_vfs);
+
+ for (uint16_t i = 0; i < total_vfs; i++) {
+ PCIDevice *vf = pci_new(devfn, vfname);
+ vf->exp.sriov_vf.pf = dev;
+ vf->exp.sriov_vf.vf_number = i;
+
+ if (!qdev_realize(&vf->qdev, bus, errp)) {
+ unparent_vfs(dev, i);
+ return false;
+ }
+
+ /* set vid/did according to sr/iov spec - they are not used */
+ pci_config_set_vendor_id(vf->config, 0xffff);
+ pci_config_set_device_id(vf->config, 0xffff);
+
+ dev->exp.sriov_pf.vf[i] = vf;
+ devfn += vf_stride;
+ }
+
return true;
}
void pcie_sriov_pf_exit(PCIDevice *dev)
{
- unregister_vfs(dev);
- g_free((char *)dev->exp.sriov_pf.vfname);
- dev->exp.sriov_pf.vfname = NULL;
+ uint8_t *cfg = dev->config + dev->exp.sriov_cap;
+
+ unparent_vfs(dev, pci_get_word(cfg + PCI_SRIOV_TOTAL_VF));
}
void pcie_sriov_pf_init_vf_bar(PCIDevice *dev, int region_num,
@@ -151,38 +178,11 @@ void pcie_sriov_vf_register_bar(PCIDevice *dev, int region_num,
}
}
-static PCIDevice *register_vf(PCIDevice *pf, int devfn, const char *name,
- uint16_t vf_num)
-{
- PCIDevice *dev = pci_new(devfn, name);
- dev->exp.sriov_vf.pf = pf;
- dev->exp.sriov_vf.vf_number = vf_num;
- PCIBus *bus = pci_get_bus(pf);
- Error *local_err = NULL;
-
- qdev_realize(&dev->qdev, &bus->qbus, &local_err);
- if (local_err) {
- error_report_err(local_err);
- return NULL;
- }
-
- /* set vid/did according to sr/iov spec - they are not used */
- pci_config_set_vendor_id(dev->config, 0xffff);
- pci_config_set_device_id(dev->config, 0xffff);
-
- return dev;
-}
-
static void register_vfs(PCIDevice *dev)
{
uint16_t num_vfs;
uint16_t i;
uint16_t sriov_cap = dev->exp.sriov_cap;
- uint16_t vf_offset =
- pci_get_word(dev->config + sriov_cap + PCI_SRIOV_VF_OFFSET);
- uint16_t vf_stride =
- pci_get_word(dev->config + sriov_cap + PCI_SRIOV_VF_STRIDE);
- int32_t devfn = dev->devfn + vf_offset;
assert(sriov_cap > 0);
num_vfs = pci_get_word(dev->config + sriov_cap + PCI_SRIOV_NUM_VF);
@@ -190,18 +190,10 @@ static void register_vfs(PCIDevice *dev)
return;
}
- dev->exp.sriov_pf.vf = g_new(PCIDevice *, num_vfs);
-
trace_sriov_register_vfs(dev->name, PCI_SLOT(dev->devfn),
PCI_FUNC(dev->devfn), num_vfs);
for (i = 0; i < num_vfs; i++) {
- dev->exp.sriov_pf.vf[i] = register_vf(dev, devfn,
- dev->exp.sriov_pf.vfname, i);
- if (!dev->exp.sriov_pf.vf[i]) {
- num_vfs = i;
- break;
- }
- devfn += vf_stride;
+ pci_set_enabled(dev->exp.sriov_pf.vf[i], true);
}
dev->exp.sriov_pf.num_vfs = num_vfs;
}
@@ -214,12 +206,8 @@ static void unregister_vfs(PCIDevice *dev)
trace_sriov_unregister_vfs(dev->name, PCI_SLOT(dev->devfn),
PCI_FUNC(dev->devfn), num_vfs);
for (i = 0; i < num_vfs; i++) {
- PCIDevice *vf = dev->exp.sriov_pf.vf[i];
- object_unparent(OBJECT(vf));
- object_unref(OBJECT(vf));
+ pci_set_enabled(dev->exp.sriov_pf.vf[i], false);
}
- g_free(dev->exp.sriov_pf.vf);
- dev->exp.sriov_pf.vf = NULL;
dev->exp.sriov_pf.num_vfs = 0;
}
@@ -241,14 +229,10 @@ void pcie_sriov_config_write(PCIDevice *dev, uint32_t address,
PCI_FUNC(dev->devfn), off, val, len);
if (range_covers_byte(off, len, PCI_SRIOV_CTRL)) {
- if (dev->exp.sriov_pf.num_vfs) {
- if (!(val & PCI_SRIOV_CTRL_VFE)) {
- unregister_vfs(dev);
- }
+ if (val & PCI_SRIOV_CTRL_VFE) {
+ register_vfs(dev);
} else {
- if (val & PCI_SRIOV_CTRL_VFE) {
- register_vfs(dev);
- }
+ unregister_vfs(dev);
}
}
}
--
2.47.0
next prev parent reply other threads:[~2024-10-22 8:39 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-10-22 8:36 [PATCH v17 00/14] hw/pci: SR-IOV related fixes and improvements Akihiko Odaki
2024-10-22 8:36 ` [PATCH v17 01/14] hw/pci: Rename has_power to enabled Akihiko Odaki
2024-10-22 8:36 ` [PATCH v17 02/14] hw/ppc/spapr_pci: Do not create DT for disabled PCI device Akihiko Odaki
2024-10-28 3:08 ` Shivaprasad G Bhat
2024-10-28 5:58 ` Akihiko Odaki
2024-11-04 5:01 ` Shivaprasad G Bhat
2024-10-22 8:36 ` [PATCH v17 03/14] hw/ppc/spapr_pci: Do not reject VFs created after a PF Akihiko Odaki
2024-10-22 8:36 ` [PATCH v17 04/14] s390x/pci: Avoid creating zpci for VFs Akihiko Odaki
2024-10-22 8:36 ` [PATCH v17 05/14] s390x/pci: Allow plugging SR-IOV devices Akihiko Odaki
2024-10-22 8:36 ` [PATCH v17 06/14] s390x/pci: Check for multifunction after device realization Akihiko Odaki
2024-10-22 8:36 ` [PATCH v17 07/14] pcie_sriov: Do not manually unrealize Akihiko Odaki
2024-10-22 8:36 ` [PATCH v17 08/14] pcie_sriov: Ensure VF addr does not overflow Akihiko Odaki
2024-10-22 8:36 ` Akihiko Odaki [this message]
2024-10-22 8:36 ` [PATCH v17 10/14] pcie_sriov: Release VFs failed to realize Akihiko Odaki
2024-10-22 8:36 ` [PATCH v17 11/14] pcie_sriov: Remove num_vfs from PCIESriovPF Akihiko Odaki
2024-10-22 8:36 ` [PATCH v17 12/14] pcie_sriov: Register VFs after migration Akihiko Odaki
2024-10-22 8:36 ` [PATCH v17 13/14] hw/pci: Use -1 as the default value for rombar Akihiko Odaki
2024-10-22 8:36 ` [PATCH v17 14/14] hw/qdev: Remove opts member Akihiko Odaki
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=20241022-reuse-v17-9-bd7c133237e4@daynix.com \
--to=akihiko.odaki@daynix.com \
--cc=alex.williamson@redhat.com \
--cc=armbru@redhat.com \
--cc=berrange@redhat.com \
--cc=clg@redhat.com \
--cc=eduardo@habkost.net \
--cc=farman@linux.ibm.com \
--cc=harshpb@linux.ibm.com \
--cc=its@irrelevant.dk \
--cc=jasowang@redhat.com \
--cc=kbusch@kernel.org \
--cc=marcel.apfelbaum@gmail.com \
--cc=mjrosato@linux.ibm.com \
--cc=mst@redhat.com \
--cc=pbonzini@redhat.com \
--cc=philmd@linaro.org \
--cc=qemu-block@nongnu.org \
--cc=qemu-devel@nongnu.org \
--cc=sbhat@linux.ibm.com \
--cc=sriram.yagnaraman@ericsson.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).