From 7ef9b9c593da98ad32ad20c28d17bb2700a35c29 Mon Sep 17 00:00:00 2001
From: Cornelia Huck <cohuck@redhat.com>
Date: Tue, 19 Jan 2021 12:50:45 -0500
Subject: [PATCH 6/7] s390x/pci: Honor DMA limits set by vfio
RH-Author: Cornelia Huck <cohuck@redhat.com>
Message-id: <20210119125046.472811-7-cohuck@redhat.com>
Patchwork-id: 100680
O-Subject: [RHEL-8.4.0 qemu-kvm PATCH 6/7] s390x/pci: Honor DMA limits set by vfio
Bugzilla: 1905391
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Auger Eric <eric.auger@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
From: Matthew Rosato <mjrosato@linux.ibm.com>
When an s390 guest is using lazy unmapping, it can result in a very
large number of oustanding DMA requests, far beyond the default
limit configured for vfio. Let's track DMA usage similar to vfio
in the host, and trigger the guest to flush their DMA mappings
before vfio runs out.
Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
[aw: non-Linux build fixes]
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
(cherry picked from commit 37fa32de707340f3a93959ad5a1ebc41ba1520ee)
Signed-off-by: Cornelia Huck <cohuck@redhat.com>
Conflicts:
hw/s390x/s390-pci-bus.c
--> adapt to missing 981c3dcd9489 ("qdev: Convert to
qdev_unrealize() with Coccinelle")
hw/s390x/s390-pci-inst.c
--> adapt to out of order inclusion of 5039caf3c449 ("memory:
Add IOMMUTLBEvent")
include/hw/s390x/s390-pci-bus.h
--> adapt to missing db1015e92e04 ("Move QOM typedefs and
add missing includes")
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
hw/s390x/s390-pci-bus.c | 16 ++++++++----
hw/s390x/s390-pci-inst.c | 45 +++++++++++++++++++++++++++-----
hw/s390x/s390-pci-vfio.c | 42 +++++++++++++++++++++++++++++
include/hw/s390x/s390-pci-bus.h | 9 +++++++
include/hw/s390x/s390-pci-inst.h | 3 +++
include/hw/s390x/s390-pci-vfio.h | 12 +++++++++
6 files changed, 116 insertions(+), 11 deletions(-)
diff --git a/hw/s390x/s390-pci-bus.c b/hw/s390x/s390-pci-bus.c
index 6daef2b6d57..a9f6f550472 100644
--- a/hw/s390x/s390-pci-bus.c
+++ b/hw/s390x/s390-pci-bus.c
@@ -17,6 +17,7 @@
#include "cpu.h"
#include "hw/s390x/s390-pci-bus.h"
#include "hw/s390x/s390-pci-inst.h"
+#include "hw/s390x/s390-pci-vfio.h"
#include "hw/pci/pci_bus.h"
#include "hw/qdev-properties.h"
#include "hw/pci/pci_bridge.h"
@@ -771,6 +772,7 @@ static void s390_pcihost_realize(DeviceState *dev, Error **errp)
s->bus_no = 0;
QTAILQ_INIT(&s->pending_sei);
QTAILQ_INIT(&s->zpci_devs);
+ QTAILQ_INIT(&s->zpci_dma_limit);
css_register_io_adapters(CSS_IO_ADAPTER_PCI, true, false,
S390_ADAPTER_SUPPRESSIBLE, &local_err);
@@ -951,17 +953,18 @@ static void s390_pcihost_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
}
}
+ pbdev->pdev = pdev;
+ pbdev->iommu = s390_pci_get_iommu(s, pci_get_bus(pdev), pdev->devfn);
+ pbdev->iommu->pbdev = pbdev;
+ pbdev->state = ZPCI_FS_DISABLED;
+
if (object_dynamic_cast(OBJECT(dev), "vfio-pci")) {
pbdev->fh |= FH_SHM_VFIO;
+ pbdev->iommu->dma_limit = s390_pci_start_dma_count(s, pbdev);
} else {
pbdev->fh |= FH_SHM_EMUL;
}
- pbdev->pdev = pdev;
- pbdev->iommu = s390_pci_get_iommu(s, pci_get_bus(pdev), pdev->devfn);
- pbdev->iommu->pbdev = pbdev;
- pbdev->state = ZPCI_FS_DISABLED;
-
if (s390_pci_msix_init(pbdev)) {
error_setg(errp, "MSI-X support is mandatory "
"in the S390 architecture");
@@ -1014,6 +1017,9 @@ static void s390_pcihost_unplug(HotplugHandler *hotplug_dev, DeviceState *dev,
pbdev->fid = 0;
QTAILQ_REMOVE(&s->zpci_devs, pbdev, link);
g_hash_table_remove(s->zpci_table, &pbdev->idx);
+ if (pbdev->iommu->dma_limit) {
+ s390_pci_end_dma_count(s, pbdev->iommu->dma_limit);
+ }
object_property_set_bool(OBJECT(dev), false, "realized", NULL);
}
}
diff --git a/hw/s390x/s390-pci-inst.c b/hw/s390x/s390-pci-inst.c
index b1885344f18..edbdf727984 100644
--- a/hw/s390x/s390-pci-inst.c
+++ b/hw/s390x/s390-pci-inst.c
@@ -32,6 +32,20 @@
} \
} while (0)
+static inline void inc_dma_avail(S390PCIIOMMU *iommu)
+{
+ if (iommu->dma_limit) {
+ iommu->dma_limit->avail++;
+ }
+}
+
+static inline void dec_dma_avail(S390PCIIOMMU *iommu)
+{
+ if (iommu->dma_limit) {
+ iommu->dma_limit->avail--;
+ }
+}
+
static void s390_set_status_code(CPUS390XState *env,
uint8_t r, uint64_t status_code)
{
@@ -572,7 +586,8 @@ int pcistg_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra)
return 0;
}
-static void s390_pci_update_iotlb(S390PCIIOMMU *iommu, S390IOTLBEntry *entry)
+static uint32_t s390_pci_update_iotlb(S390PCIIOMMU *iommu,
+ S390IOTLBEntry *entry)
{
S390IOTLBEntry *cache = g_hash_table_lookup(iommu->iotlb, &entry->iova);
IOMMUTLBEvent event = {
@@ -588,14 +603,15 @@ static void s390_pci_update_iotlb(S390PCIIOMMU *iommu, S390IOTLBEntry *entry)
if (event.type == IOMMU_NOTIFIER_UNMAP) {
if (!cache) {
- return;
+ goto out;
}
g_hash_table_remove(iommu->iotlb, &entry->iova);
+ inc_dma_avail(iommu);
} else {
if (cache) {
if (cache->perm == entry->perm &&
cache->translated_addr == entry->translated_addr) {
- return;
+ goto out;
}
event.type = IOMMU_NOTIFIER_UNMAP;
@@ -611,9 +627,13 @@ static void s390_pci_update_iotlb(S390PCIIOMMU *iommu, S390IOTLBEntry *entry)
cache->len = PAGE_SIZE;
cache->perm = entry->perm;
g_hash_table_replace(iommu->iotlb, &cache->iova, cache);
+ dec_dma_avail(iommu);
}
memory_region_notify_iommu(&iommu->iommu_mr, 0, event);
+
+out:
+ return iommu->dma_limit ? iommu->dma_limit->avail : 1;
}
int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra)
@@ -625,6 +645,7 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra)
S390PCIIOMMU *iommu;
S390IOTLBEntry entry;
hwaddr start, end;
+ uint32_t dma_avail;
if (env->psw.mask & PSW_MASK_PSTATE) {
s390_program_interrupt(env, PGM_PRIVILEGED, ra);
@@ -663,6 +684,11 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra)
}
iommu = pbdev->iommu;
+ if (iommu->dma_limit) {
+ dma_avail = iommu->dma_limit->avail;
+ } else {
+ dma_avail = 1;
+ }
if (!iommu->g_iota) {
error = ERR_EVENT_INVALAS;
goto err;
@@ -680,8 +706,9 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra)
}
start += entry.len;
- while (entry.iova < start && entry.iova < end) {
- s390_pci_update_iotlb(iommu, &entry);
+ while (entry.iova < start && entry.iova < end &&
+ (dma_avail > 0 || entry.perm == IOMMU_NONE)) {
+ dma_avail = s390_pci_update_iotlb(iommu, &entry);
entry.iova += PAGE_SIZE;
entry.translated_addr += PAGE_SIZE;
}
@@ -694,7 +721,13 @@ err:
s390_pci_generate_error_event(error, pbdev->fh, pbdev->fid, start, 0);
} else {
pbdev->fmb.counter[ZPCI_FMB_CNT_RPCIT]++;
- setcc(cpu, ZPCI_PCI_LS_OK);
+ if (dma_avail > 0) {
+ setcc(cpu, ZPCI_PCI_LS_OK);
+ } else {
+ /* vfio DMA mappings are exhausted, trigger a RPCIT */
+ setcc(cpu, ZPCI_PCI_LS_ERR);
+ s390_set_status_code(env, r1, ZPCI_RPCIT_ST_INSUFF_RES);
+ }
}
return 0;
}
diff --git a/hw/s390x/s390-pci-vfio.c b/hw/s390x/s390-pci-vfio.c
index 0eb22ffec4c..01c1e8ac89a 100644
--- a/hw/s390x/s390-pci-vfio.c
+++ b/hw/s390x/s390-pci-vfio.c
@@ -12,7 +12,9 @@
#include <sys/ioctl.h>
#include "qemu/osdep.h"
+#include "hw/s390x/s390-pci-bus.h"
#include "hw/s390x/s390-pci-vfio.h"
+#include "hw/vfio/pci.h"
#include "hw/vfio/vfio-common.h"
/*
@@ -52,3 +54,43 @@ retry:
return vfio_get_info_dma_avail(info, avail);
}
+S390PCIDMACount *s390_pci_start_dma_count(S390pciState *s,
+ S390PCIBusDevice *pbdev)
+{
+ S390PCIDMACount *cnt;
+ uint32_t avail;
+ VFIOPCIDevice *vpdev = container_of(pbdev->pdev, VFIOPCIDevice, pdev);
+ int id;
+
+ assert(vpdev);
+
+ id = vpdev->vbasedev.group->container->fd;
+
+ if (!s390_pci_update_dma_avail(id, &avail)) {
+ return NULL;
+ }
+
+ QTAILQ_FOREACH(cnt, &s->zpci_dma_limit, link) {
+ if (cnt->id == id) {
+ cnt->users++;
+ return cnt;
+ }
+ }
+
+ cnt = g_new0(S390PCIDMACount, 1);
+ cnt->id = id;
+ cnt->users = 1;
+ cnt->avail = avail;
+ QTAILQ_INSERT_TAIL(&s->zpci_dma_limit, cnt, link);
+ return cnt;
+}
+
+void s390_pci_end_dma_count(S390pciState *s, S390PCIDMACount *cnt)
+{
+ assert(cnt);
+
+ cnt->users--;
+ if (cnt->users == 0) {
+ QTAILQ_REMOVE(&s->zpci_dma_limit, cnt, link);
+ }
+}
diff --git a/include/hw/s390x/s390-pci-bus.h b/include/hw/s390x/s390-pci-bus.h
index 550f3cc5e92..2f2edbd0bf3 100644
--- a/include/hw/s390x/s390-pci-bus.h
+++ b/include/hw/s390x/s390-pci-bus.h
@@ -266,6 +266,13 @@ typedef struct S390IOTLBEntry {
} S390IOTLBEntry;
typedef struct S390PCIBusDevice S390PCIBusDevice;
+typedef struct S390PCIDMACount {
+ int id;
+ int users;
+ uint32_t avail;
+ QTAILQ_ENTRY(S390PCIDMACount) link;
+} S390PCIDMACount;
+
typedef struct S390PCIIOMMU {
Object parent_obj;
S390PCIBusDevice *pbdev;
@@ -277,6 +284,7 @@ typedef struct S390PCIIOMMU {
uint64_t pba;
uint64_t pal;
GHashTable *iotlb;
+ S390PCIDMACount *dma_limit;
} S390PCIIOMMU;
typedef struct S390PCIIOMMUTable {
@@ -352,6 +360,7 @@ typedef struct S390pciState {
GHashTable *zpci_table;
QTAILQ_HEAD(, SeiContainer) pending_sei;
QTAILQ_HEAD(, S390PCIBusDevice) zpci_devs;
+ QTAILQ_HEAD(, S390PCIDMACount) zpci_dma_limit;
} S390pciState;
S390pciState *s390_get_phb(void);
diff --git a/include/hw/s390x/s390-pci-inst.h b/include/hw/s390x/s390-pci-inst.h
index fa3bf8b5aad..8ee3a3c2375 100644
--- a/include/hw/s390x/s390-pci-inst.h
+++ b/include/hw/s390x/s390-pci-inst.h
@@ -254,6 +254,9 @@ typedef struct ClpReqRspQueryPciGrp {
#define ZPCI_STPCIFC_ST_INVAL_DMAAS 28
#define ZPCI_STPCIFC_ST_ERROR_RECOVER 40
+/* Refresh PCI Translations status codes */
+#define ZPCI_RPCIT_ST_INSUFF_RES 16
+
/* FIB function controls */
#define ZPCI_FIB_FC_ENABLED 0x80
#define ZPCI_FIB_FC_ERROR 0x40
diff --git a/include/hw/s390x/s390-pci-vfio.h b/include/hw/s390x/s390-pci-vfio.h
index 1727292e9b5..539bcf04eb5 100644
--- a/include/hw/s390x/s390-pci-vfio.h
+++ b/include/hw/s390x/s390-pci-vfio.h
@@ -12,13 +12,25 @@
#ifndef HW_S390_PCI_VFIO_H
#define HW_S390_PCI_VFIO_H
+#include "hw/s390x/s390-pci-bus.h"
+
#ifdef CONFIG_LINUX
bool s390_pci_update_dma_avail(int fd, unsigned int *avail);
+S390PCIDMACount *s390_pci_start_dma_count(S390pciState *s,
+ S390PCIBusDevice *pbdev);
+void s390_pci_end_dma_count(S390pciState *s, S390PCIDMACount *cnt);
#else
static inline bool s390_pci_update_dma_avail(int fd, unsigned int *avail)
{
return false;
}
+static inline S390PCIDMACount *s390_pci_start_dma_count(S390pciState *s,
+ S390PCIBusDevice *pbdev)
+{
+ return NULL;
+}
+static inline void s390_pci_end_dma_count(S390pciState *s,
+ S390PCIDMACount *cnt) { }
#endif
#endif
--
2.27.0