aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorAlexey Kardashevskiy <aik@ozlabs.ru>2012-08-07 16:10:37 +0000
committerAlexander Graf <agraf@suse.de>2012-08-15 19:43:16 +0200
commit0ee2c058a3fe485b8901186179102e251a33d082 (patch)
treeacc8e7fb4ba8901e8d5aa3868aa4a88cc123082d
parenta2950fb6e795e3e10fed35d347a7aa28a44be2ff (diff)
downloadqemu-0ee2c058a3fe485b8901186179102e251a33d082.zip
qemu-0ee2c058a3fe485b8901186179102e251a33d082.tar.gz
qemu-0ee2c058a3fe485b8901186179102e251a33d082.tar.bz2
pseries: Add PCI MSI/MSI-X support
This patch implements MSI and MSI-X support for the pseries PCI host bridge. To do this it adds: * A "config_space_address to msi_table" map, since the MSI RTAS calls take a PCI config space address as an identifier. * A MSIX memory region to catch msi_notify()/msix_notiry() from virtio-pci and pass them to the guest via qemu_irq_pulse(). * RTAS call "ibm,change-msi" which sets up MSI vectors for a device. Note that this call may configure and return lesser number of vectors than requested. * RTAS call "ibm,query-interrupt-source-number" which translates MSI vector to interrupt controller (XICS) IRQ number. Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> Signed-off-by: David Gibson <david@gibson.dropbear.id.au> [agraf: fix error case ndev < 0] Signed-off-by: Alexander Graf <agraf@suse.de>
-rw-r--r--hw/spapr.c7
-rw-r--r--hw/spapr_pci.c245
-rw-r--r--hw/spapr_pci.h15
-rw-r--r--trace-events5
4 files changed, 268 insertions, 4 deletions
diff --git a/hw/spapr.c b/hw/spapr.c
index afbdbc5..5178721 100644
--- a/hw/spapr.c
+++ b/hw/spapr.c
@@ -41,6 +41,7 @@
#include "hw/spapr_vio.h"
#include "hw/spapr_pci.h"
#include "hw/xics.h"
+#include "hw/msi.h"
#include "kvm.h"
#include "kvm_ppc.h"
@@ -79,6 +80,7 @@
#define SPAPR_PCI_MEM_WIN_ADDR (0x10000000000ULL + 0xA0000000)
#define SPAPR_PCI_MEM_WIN_SIZE 0x20000000
#define SPAPR_PCI_IO_WIN_ADDR (0x10000000000ULL + 0x80000000)
+#define SPAPR_PCI_MSI_WIN_ADDR (0x10000000000ULL + 0x90000000)
#define PHANDLE_XICP 0x00001111
@@ -619,6 +621,8 @@ static void ppc_spapr_init(ram_addr_t ram_size,
long pteg_shift = 17;
char *filename;
+ msi_supported = true;
+
spapr = g_malloc0(sizeof(*spapr));
QLIST_INIT(&spapr->phbs);
@@ -735,7 +739,8 @@ static void ppc_spapr_init(ram_addr_t ram_size,
spapr_create_phb(spapr, "pci", SPAPR_PCI_BUID,
SPAPR_PCI_MEM_WIN_ADDR,
SPAPR_PCI_MEM_WIN_SIZE,
- SPAPR_PCI_IO_WIN_ADDR);
+ SPAPR_PCI_IO_WIN_ADDR,
+ SPAPR_PCI_MSI_WIN_ADDR);
for (i = 0; i < nb_nics; i++) {
NICInfo *nd = &nd_table[i];
diff --git a/hw/spapr_pci.c b/hw/spapr_pci.c
index 1eb1a7e..780a4d6 100644
--- a/hw/spapr_pci.c
+++ b/hw/spapr_pci.c
@@ -24,6 +24,8 @@
*/
#include "hw.h"
#include "pci.h"
+#include "msi.h"
+#include "msix.h"
#include "pci_host.h"
#include "hw/spapr.h"
#include "hw/spapr_pci.h"
@@ -33,6 +35,17 @@
#include "hw/pci_internals.h"
+/* Copied from the kernel arch/powerpc/platforms/pseries/msi.c */
+#define RTAS_QUERY_FN 0
+#define RTAS_CHANGE_FN 1
+#define RTAS_RESET_FN 2
+#define RTAS_CHANGE_MSI_FN 3
+#define RTAS_CHANGE_MSIX_FN 4
+
+/* Interrupt types to return on RTAS_CHANGE_* */
+#define RTAS_TYPE_MSI 1
+#define RTAS_TYPE_MSIX 2
+
static sPAPRPHBState *find_phb(sPAPREnvironment *spapr, uint64_t buid)
{
sPAPRPHBState *phb;
@@ -211,6 +224,191 @@ static void rtas_write_pci_config(sPAPREnvironment *spapr,
finish_write_pci_config(spapr, 0, addr, size, val, rets);
}
+/*
+ * Find an entry with config_addr or returns the empty one if not found AND
+ * alloc_new is set.
+ * At the moment the msi_table entries are never released so there is
+ * no point to look till the end of the list if we need to find the free entry.
+ */
+static int spapr_msicfg_find(sPAPRPHBState *phb, uint32_t config_addr,
+ bool alloc_new)
+{
+ int i;
+
+ for (i = 0; i < SPAPR_MSIX_MAX_DEVS; ++i) {
+ if (!phb->msi_table[i].nvec) {
+ break;
+ }
+ if (phb->msi_table[i].config_addr == config_addr) {
+ return i;
+ }
+ }
+ if ((i < SPAPR_MSIX_MAX_DEVS) && alloc_new) {
+ trace_spapr_pci_msi("Allocating new MSI config", i, config_addr);
+ return i;
+ }
+
+ return -1;
+}
+
+/*
+ * Set MSI/MSIX message data.
+ * This is required for msi_notify()/msix_notify() which
+ * will write at the addresses via spapr_msi_write().
+ */
+static void spapr_msi_setmsg(PCIDevice *pdev, target_phys_addr_t addr,
+ bool msix, unsigned req_num)
+{
+ unsigned i;
+ MSIMessage msg = { .address = addr, .data = 0 };
+
+ if (!msix) {
+ msi_set_message(pdev, msg);
+ trace_spapr_pci_msi_setup(pdev->name, 0, msg.address);
+ return;
+ }
+
+ for (i = 0; i < req_num; ++i) {
+ msg.address = addr | (i << 2);
+ msix_set_message(pdev, i, msg);
+ trace_spapr_pci_msi_setup(pdev->name, i, msg.address);
+ }
+}
+
+static void rtas_ibm_change_msi(sPAPREnvironment *spapr,
+ uint32_t token, uint32_t nargs,
+ target_ulong args, uint32_t nret,
+ target_ulong rets)
+{
+ uint32_t config_addr = rtas_ld(args, 0);
+ uint64_t buid = ((uint64_t)rtas_ld(args, 1) << 32) | rtas_ld(args, 2);
+ unsigned int func = rtas_ld(args, 3);
+ unsigned int req_num = rtas_ld(args, 4); /* 0 == remove all */
+ unsigned int seq_num = rtas_ld(args, 5);
+ unsigned int ret_intr_type;
+ int ndev, irq;
+ sPAPRPHBState *phb = NULL;
+ PCIDevice *pdev = NULL;
+
+ switch (func) {
+ case RTAS_CHANGE_MSI_FN:
+ case RTAS_CHANGE_FN:
+ ret_intr_type = RTAS_TYPE_MSI;
+ break;
+ case RTAS_CHANGE_MSIX_FN:
+ ret_intr_type = RTAS_TYPE_MSIX;
+ break;
+ default:
+ fprintf(stderr, "rtas_ibm_change_msi(%u) is not implemented\n", func);
+ rtas_st(rets, 0, -3); /* Parameter error */
+ return;
+ }
+
+ /* Fins sPAPRPHBState */
+ phb = find_phb(spapr, buid);
+ if (phb) {
+ pdev = find_dev(spapr, buid, config_addr);
+ }
+ if (!phb || !pdev) {
+ rtas_st(rets, 0, -3); /* Parameter error */
+ return;
+ }
+
+ /* Releasing MSIs */
+ if (!req_num) {
+ ndev = spapr_msicfg_find(phb, config_addr, false);
+ if (ndev < 0) {
+ trace_spapr_pci_msi("MSI has not been enabled", -1, config_addr);
+ rtas_st(rets, 0, -1); /* Hardware error */
+ return;
+ }
+ trace_spapr_pci_msi("Released MSIs", ndev, config_addr);
+ rtas_st(rets, 0, 0);
+ rtas_st(rets, 1, 0);
+ return;
+ }
+
+ /* Enabling MSI */
+
+ /* Find a device number in the map to add or reuse the existing one */
+ ndev = spapr_msicfg_find(phb, config_addr, true);
+ if (ndev >= SPAPR_MSIX_MAX_DEVS || ndev < 0) {
+ fprintf(stderr, "No free entry for a new MSI device\n");
+ rtas_st(rets, 0, -1); /* Hardware error */
+ return;
+ }
+ trace_spapr_pci_msi("Configuring MSI", ndev, config_addr);
+
+ /* Check if there is an old config and MSI number has not changed */
+ if (phb->msi_table[ndev].nvec && (req_num != phb->msi_table[ndev].nvec)) {
+ /* Unexpected behaviour */
+ fprintf(stderr, "Cannot reuse MSI config for device#%d", ndev);
+ rtas_st(rets, 0, -1); /* Hardware error */
+ return;
+ }
+
+ /* There is no cached config, allocate MSIs */
+ if (!phb->msi_table[ndev].nvec) {
+ irq = spapr_allocate_irq_block(req_num, XICS_MSI);
+ if (irq < 0) {
+ fprintf(stderr, "Cannot allocate MSIs for device#%d", ndev);
+ rtas_st(rets, 0, -1); /* Hardware error */
+ return;
+ }
+ phb->msi_table[ndev].irq = irq;
+ phb->msi_table[ndev].nvec = req_num;
+ phb->msi_table[ndev].config_addr = config_addr;
+ }
+
+ /* Setup MSI/MSIX vectors in the device (via cfgspace or MSIX BAR) */
+ spapr_msi_setmsg(pdev, phb->msi_win_addr | (ndev << 16),
+ ret_intr_type == RTAS_TYPE_MSIX, req_num);
+
+ rtas_st(rets, 0, 0);
+ rtas_st(rets, 1, req_num);
+ rtas_st(rets, 2, ++seq_num);
+ rtas_st(rets, 3, ret_intr_type);
+
+ trace_spapr_pci_rtas_ibm_change_msi(func, req_num);
+}
+
+static void rtas_ibm_query_interrupt_source_number(sPAPREnvironment *spapr,
+ uint32_t token,
+ uint32_t nargs,
+ target_ulong args,
+ uint32_t nret,
+ target_ulong rets)
+{
+ uint32_t config_addr = rtas_ld(args, 0);
+ uint64_t buid = ((uint64_t)rtas_ld(args, 1) << 32) | rtas_ld(args, 2);
+ unsigned int intr_src_num = -1, ioa_intr_num = rtas_ld(args, 3);
+ int ndev;
+ sPAPRPHBState *phb = NULL;
+
+ /* Fins sPAPRPHBState */
+ phb = find_phb(spapr, buid);
+ if (!phb) {
+ rtas_st(rets, 0, -3); /* Parameter error */
+ return;
+ }
+
+ /* Find device descriptor and start IRQ */
+ ndev = spapr_msicfg_find(phb, config_addr, false);
+ if (ndev < 0) {
+ trace_spapr_pci_msi("MSI has not been enabled", -1, config_addr);
+ rtas_st(rets, 0, -1); /* Hardware error */
+ return;
+ }
+
+ intr_src_num = phb->msi_table[ndev].irq + ioa_intr_num;
+ trace_spapr_pci_rtas_ibm_query_interrupt_source_number(ioa_intr_num,
+ intr_src_num);
+
+ rtas_st(rets, 0, 0);
+ rtas_st(rets, 1, intr_src_num);
+ rtas_st(rets, 2, 1);/* 0 == level; 1 == edge */
+}
+
static int pci_spapr_swizzle(int slot, int pin)
{
return (slot + pin) % PCI_NUM_PINS;
@@ -277,6 +475,33 @@ static const MemoryRegionOps spapr_io_ops = {
};
/*
+ * MSI/MSIX memory region implementation.
+ * The handler handles both MSI and MSIX.
+ * For MSI-X, the vector number is encoded as a part of the address,
+ * data is set to 0.
+ * For MSI, the vector number is encoded in least bits in data.
+ */
+static void spapr_msi_write(void *opaque, target_phys_addr_t addr,
+ uint64_t data, unsigned size)
+{
+ sPAPRPHBState *phb = opaque;
+ int ndev = addr >> 16;
+ int vec = ((addr & 0xFFFF) >> 2) | data;
+ uint32_t irq = phb->msi_table[ndev].irq + vec;
+
+ trace_spapr_pci_msi_write(addr, data, irq);
+
+ qemu_irq_pulse(xics_get_qirq(spapr->icp, irq));
+}
+
+static const MemoryRegionOps spapr_msi_ops = {
+ /* There is no .read as the read result is undefined by PCI spec */
+ .read = NULL,
+ .write = spapr_msi_write,
+ .endianness = DEVICE_LITTLE_ENDIAN
+};
+
+/*
* PHB PCI device
*/
static DMAContext *spapr_pci_dma_context_fn(PCIBus *bus, void *opaque,
@@ -327,6 +552,17 @@ static int spapr_phb_init(SysBusDevice *s)
memory_region_add_subregion(get_system_memory(), phb->io_win_addr,
&phb->iowindow);
+ /* As MSI/MSIX interrupts trigger by writing at MSI/MSIX vectors,
+ * we need to allocate some memory to catch those writes coming
+ * from msi_notify()/msix_notify() */
+ if (msi_supported) {
+ sprintf(namebuf, "%s.msi", phb->dtbusname);
+ memory_region_init_io(&phb->msiwindow, &spapr_msi_ops, phb,
+ namebuf, SPAPR_MSIX_MAX_DEVS * 0x10000);
+ memory_region_add_subregion(get_system_memory(), phb->msi_win_addr,
+ &phb->msiwindow);
+ }
+
bus = pci_register_bus(&phb->host_state.busdev.qdev,
phb->busname ? phb->busname : phb->dtbusname,
pci_spapr_set_irq, pci_spapr_map_irq, phb,
@@ -362,6 +598,7 @@ static Property spapr_phb_properties[] = {
DEFINE_PROP_HEX64("mem_win_size", sPAPRPHBState, mem_win_size, 0x20000000),
DEFINE_PROP_HEX64("io_win_addr", sPAPRPHBState, io_win_addr, 0),
DEFINE_PROP_HEX64("io_win_size", sPAPRPHBState, io_win_size, 0x10000),
+ DEFINE_PROP_HEX64("msi_win_addr", sPAPRPHBState, msi_win_addr, 0),
DEFINE_PROP_END_OF_LIST(),
};
@@ -384,7 +621,7 @@ static TypeInfo spapr_phb_info = {
void spapr_create_phb(sPAPREnvironment *spapr,
const char *busname, uint64_t buid,
uint64_t mem_win_addr, uint64_t mem_win_size,
- uint64_t io_win_addr)
+ uint64_t io_win_addr, uint64_t msi_win_addr)
{
DeviceState *dev;
@@ -397,6 +634,7 @@ void spapr_create_phb(sPAPREnvironment *spapr,
qdev_prop_set_uint64(dev, "mem_win_addr", mem_win_addr);
qdev_prop_set_uint64(dev, "mem_win_size", mem_win_size);
qdev_prop_set_uint64(dev, "io_win_addr", io_win_addr);
+ qdev_prop_set_uint64(dev, "msi_win_addr", msi_win_addr);
qdev_init_nofail(dev);
}
@@ -502,6 +740,11 @@ void spapr_pci_rtas_init(void)
spapr_rtas_register("write-pci-config", rtas_write_pci_config);
spapr_rtas_register("ibm,read-pci-config", rtas_ibm_read_pci_config);
spapr_rtas_register("ibm,write-pci-config", rtas_ibm_write_pci_config);
+ if (msi_supported) {
+ spapr_rtas_register("ibm,query-interrupt-source-number",
+ rtas_ibm_query_interrupt_source_number);
+ spapr_rtas_register("ibm,change-msi", rtas_ibm_change_msi);
+ }
}
static void register_types(void)
diff --git a/hw/spapr_pci.h b/hw/spapr_pci.h
index 2aee67f..6892e4f 100644
--- a/hw/spapr_pci.h
+++ b/hw/spapr_pci.h
@@ -27,6 +27,8 @@
#include "hw/pci_host.h"
#include "hw/xics.h"
+#define SPAPR_MSIX_MAX_DEVS 32
+
typedef struct sPAPRPHBState {
PCIHostState host_state;
@@ -36,13 +38,22 @@ typedef struct sPAPRPHBState {
MemoryRegion memspace, iospace;
target_phys_addr_t mem_win_addr, mem_win_size, io_win_addr, io_win_size;
- MemoryRegion memwindow, iowindow;
+ target_phys_addr_t msi_win_addr;
+ MemoryRegion memwindow, iowindow, msiwindow;
+
+
DMAContext *dma;
struct {
uint32_t irq;
} lsi_table[PCI_NUM_PINS];
+ struct {
+ uint32_t config_addr;
+ uint32_t irq;
+ int nvec;
+ } msi_table[SPAPR_MSIX_MAX_DEVS];
+
QLIST_ENTRY(sPAPRPHBState) list;
} sPAPRPHBState;
@@ -57,7 +68,7 @@ static inline qemu_irq spapr_phb_lsi_qirq(struct sPAPRPHBState *phb, int pin)
void spapr_create_phb(sPAPREnvironment *spapr,
const char *busname, uint64_t buid,
uint64_t mem_win_addr, uint64_t mem_win_size,
- uint64_t io_win_addr);
+ uint64_t io_win_addr, uint64_t msi_win_addr);
int spapr_populate_pci_dt(sPAPRPHBState *phb,
uint32_t xics_phandle,
diff --git a/trace-events b/trace-events
index 191b39e..04b0723 100644
--- a/trace-events
+++ b/trace-events
@@ -972,4 +972,9 @@ qxl_render_guest_primary_resized(int32_t width, int32_t height, int32_t stride,
qxl_render_update_area_done(void *cookie) "%p"
# hw/spapr_pci.c
+spapr_pci_msi(const char *msg, uint32_t n, uint32_t ca) "%s (device#%d, cfg=%x)"
+spapr_pci_msi_setup(const char *name, unsigned vector, uint64_t addr) "dev\"%s\" vector %u, addr=%"PRIx64
+spapr_pci_rtas_ibm_change_msi(unsigned func, unsigned req) "func %u, requested %u"
+spapr_pci_rtas_ibm_query_interrupt_source_number(unsigned ioa, unsigned intr) "queries for #%u, IRQ%u"
+spapr_pci_msi_write(uint64_t addr, uint64_t data, uint32_t dt_irq) "@%"PRIx64"<=%"PRIx64" IRQ %u"
spapr_pci_lsi_set(const char *busname, int pin, uint32_t irq) "%s PIN%d IRQ %u"