* THE SOFTWARE.
*/
#include "hw/hw.h"
+#include "hw/sysbus.h"
#include "hw/pci/pci.h"
#include "hw/pci/msi.h"
#include "hw/pci/msix.h"
#include <libfdt.h>
#include "trace.h"
#include "qemu/error-report.h"
+#include "qapi/qmp/qerror.h"
+#include "hw/pci/pci_bridge.h"
#include "hw/pci/pci_bus.h"
+#include "hw/ppc/spapr_drc.h"
+#include "sysemu/device_tree.h"
/* Copied from the kernel arch/powerpc/platforms/pseries/msi.c */
#define RTAS_QUERY_FN 0
#define RTAS_TYPE_MSI 1
#define RTAS_TYPE_MSIX 2
-static sPAPRPHBState *find_phb(sPAPREnvironment *spapr, uint64_t buid)
+#define FDT_NAME_MAX 128
+
+#define _FDT(exp) \
+ do { \
+ int ret = (exp); \
+ if (ret < 0) { \
+ return ret; \
+ } \
+ } while (0)
+
+sPAPRPHBState *spapr_pci_find_phb(sPAPRMachineState *spapr, uint64_t buid)
{
sPAPRPHBState *sphb;
return NULL;
}
-static PCIDevice *find_dev(sPAPREnvironment *spapr, uint64_t buid,
- uint32_t config_addr)
+PCIDevice *spapr_pci_find_dev(sPAPRMachineState *spapr, uint64_t buid,
+ uint32_t config_addr)
{
- sPAPRPHBState *sphb = find_phb(spapr, buid);
+ sPAPRPHBState *sphb = spapr_pci_find_phb(spapr, buid);
PCIHostState *phb = PCI_HOST_BRIDGE(sphb);
int bus_num = (config_addr >> 16) & 0xFF;
int devfn = (config_addr >> 8) & 0xFF;
return ((arg >> 20) & 0xf00) | (arg & 0xff);
}
-static void finish_read_pci_config(sPAPREnvironment *spapr, uint64_t buid,
+static void finish_read_pci_config(sPAPRMachineState *spapr, uint64_t buid,
uint32_t addr, uint32_t size,
target_ulong rets)
{
return;
}
- pci_dev = find_dev(spapr, buid, addr);
+ pci_dev = spapr_pci_find_dev(spapr, buid, addr);
addr = rtas_pci_cfgaddr(addr);
if (!pci_dev || (addr % size) || (addr >= pci_config_size(pci_dev))) {
rtas_st(rets, 1, val);
}
-static void rtas_ibm_read_pci_config(PowerPCCPU *cpu, sPAPREnvironment *spapr,
+static void rtas_ibm_read_pci_config(PowerPCCPU *cpu, sPAPRMachineState *spapr,
uint32_t token, uint32_t nargs,
target_ulong args,
uint32_t nret, target_ulong rets)
return;
}
- buid = ((uint64_t)rtas_ld(args, 1) << 32) | rtas_ld(args, 2);
+ buid = rtas_ldq(args, 1);
size = rtas_ld(args, 3);
addr = rtas_ld(args, 0);
finish_read_pci_config(spapr, buid, addr, size, rets);
}
-static void rtas_read_pci_config(PowerPCCPU *cpu, sPAPREnvironment *spapr,
+static void rtas_read_pci_config(PowerPCCPU *cpu, sPAPRMachineState *spapr,
uint32_t token, uint32_t nargs,
target_ulong args,
uint32_t nret, target_ulong rets)
finish_read_pci_config(spapr, 0, addr, size, rets);
}
-static void finish_write_pci_config(sPAPREnvironment *spapr, uint64_t buid,
+static void finish_write_pci_config(sPAPRMachineState *spapr, uint64_t buid,
uint32_t addr, uint32_t size,
uint32_t val, target_ulong rets)
{
return;
}
- pci_dev = find_dev(spapr, buid, addr);
+ pci_dev = spapr_pci_find_dev(spapr, buid, addr);
addr = rtas_pci_cfgaddr(addr);
if (!pci_dev || (addr % size) || (addr >= pci_config_size(pci_dev))) {
rtas_st(rets, 0, RTAS_OUT_SUCCESS);
}
-static void rtas_ibm_write_pci_config(PowerPCCPU *cpu, sPAPREnvironment *spapr,
+static void rtas_ibm_write_pci_config(PowerPCCPU *cpu, sPAPRMachineState *spapr,
uint32_t token, uint32_t nargs,
target_ulong args,
uint32_t nret, target_ulong rets)
return;
}
- buid = ((uint64_t)rtas_ld(args, 1) << 32) | rtas_ld(args, 2);
+ buid = rtas_ldq(args, 1);
val = rtas_ld(args, 4);
size = rtas_ld(args, 3);
addr = rtas_ld(args, 0);
finish_write_pci_config(spapr, buid, addr, size, val, rets);
}
-static void rtas_write_pci_config(PowerPCCPU *cpu, sPAPREnvironment *spapr,
+static void rtas_write_pci_config(PowerPCCPU *cpu, sPAPRMachineState *spapr,
uint32_t token, uint32_t nargs,
target_ulong args,
uint32_t nret, target_ulong rets)
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().
+ *
+ * If hwaddr == 0, all entries will have .data == first_irq i.e.
+ * table will be reset.
*/
static void spapr_msi_setmsg(PCIDevice *pdev, hwaddr addr, bool msix,
unsigned first_irq, unsigned req_num)
return;
}
- for (i = 0; i < req_num; ++i, ++msg.data) {
+ for (i = 0; i < req_num; ++i) {
msix_set_message(pdev, i, msg);
trace_spapr_pci_msi_setup(pdev->name, i, msg.address);
+ if (addr) {
+ ++msg.data;
+ }
}
}
-static void rtas_ibm_change_msi(PowerPCCPU *cpu, sPAPREnvironment *spapr,
+static void rtas_ibm_change_msi(PowerPCCPU *cpu, sPAPRMachineState *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);
+ uint64_t buid = rtas_ldq(args, 1);
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;
+ unsigned int irq, max_irqs = 0, num = 0;
sPAPRPHBState *phb = NULL;
PCIDevice *pdev = NULL;
+ spapr_pci_msi *msi;
+ int *config_addr_key;
switch (func) {
case RTAS_CHANGE_MSI_FN:
}
/* Fins sPAPRPHBState */
- phb = find_phb(spapr, buid);
+ phb = spapr_pci_find_phb(spapr, buid);
if (phb) {
- pdev = find_dev(spapr, buid, config_addr);
+ pdev = spapr_pci_find_dev(spapr, buid, config_addr);
}
if (!phb || !pdev) {
rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR);
/* 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);
+ msi = (spapr_pci_msi *) g_hash_table_lookup(phb->msi, &config_addr);
+ if (!msi) {
+ trace_spapr_pci_msi("Releasing wrong config", config_addr);
rtas_st(rets, 0, RTAS_OUT_HW_ERROR);
return;
}
- trace_spapr_pci_msi("Released MSIs", ndev, config_addr);
+
+ xics_free(spapr->icp, msi->first_irq, msi->num);
+ if (msi_present(pdev)) {
+ spapr_msi_setmsg(pdev, 0, false, 0, num);
+ }
+ if (msix_present(pdev)) {
+ spapr_msi_setmsg(pdev, 0, true, 0, num);
+ }
+ g_hash_table_remove(phb->msi, &config_addr);
+
+ trace_spapr_pci_msi("Released MSIs", config_addr);
rtas_st(rets, 0, RTAS_OUT_SUCCESS);
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) {
- error_report("No free entry for a new MSI device");
- rtas_st(rets, 0, RTAS_OUT_HW_ERROR);
+ /* Check if the device supports as many IRQs as requested */
+ if (ret_intr_type == RTAS_TYPE_MSI) {
+ max_irqs = msi_nr_vectors_allocated(pdev);
+ } else if (ret_intr_type == RTAS_TYPE_MSIX) {
+ max_irqs = pdev->msix_entries_nr;
+ }
+ if (!max_irqs) {
+ error_report("Requested interrupt type %d is not enabled for device %x",
+ ret_intr_type, config_addr);
+ rtas_st(rets, 0, -1); /* Hardware error */
return;
}
- trace_spapr_pci_msi("Configuring MSI", ndev, config_addr);
+ /* Correct the number if the guest asked for too many */
+ if (req_num > max_irqs) {
+ trace_spapr_pci_msi_retry(config_addr, req_num, max_irqs);
+ req_num = max_irqs;
+ irq = 0; /* to avoid misleading trace */
+ goto out;
+ }
- /* 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 */
- error_report("Cannot reuse MSI config for device#%d", ndev);
+ /* Allocate MSIs */
+ irq = xics_alloc_block(spapr->icp, 0, req_num, false,
+ ret_intr_type == RTAS_TYPE_MSI);
+ if (!irq) {
+ error_report("Cannot allocate MSIs for device %x", config_addr);
rtas_st(rets, 0, RTAS_OUT_HW_ERROR);
return;
}
- /* There is no cached config, allocate MSIs */
- if (!phb->msi_table[ndev].nvec) {
- irq = spapr_allocate_irq_block(req_num, false,
- ret_intr_type == RTAS_TYPE_MSI);
- if (irq < 0) {
- error_report("Cannot allocate MSIs for device#%d", ndev);
- rtas_st(rets, 0, RTAS_OUT_HW_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, spapr->msi_win_addr, ret_intr_type == RTAS_TYPE_MSIX,
- phb->msi_table[ndev].irq, req_num);
-
+ spapr_msi_setmsg(pdev, SPAPR_PCI_MSI_WINDOW, ret_intr_type == RTAS_TYPE_MSIX,
+ irq, req_num);
+
+ /* Add MSI device to cache */
+ msi = g_new(spapr_pci_msi, 1);
+ msi->first_irq = irq;
+ msi->num = req_num;
+ config_addr_key = g_new(int, 1);
+ *config_addr_key = config_addr;
+ g_hash_table_insert(phb->msi, config_addr_key, msi);
+
+out:
rtas_st(rets, 0, RTAS_OUT_SUCCESS);
rtas_st(rets, 1, req_num);
rtas_st(rets, 2, ++seq_num);
- rtas_st(rets, 3, ret_intr_type);
+ if (nret > 3) {
+ rtas_st(rets, 3, ret_intr_type);
+ }
- trace_spapr_pci_rtas_ibm_change_msi(func, req_num);
+ trace_spapr_pci_rtas_ibm_change_msi(config_addr, func, req_num, irq);
}
static void rtas_ibm_query_interrupt_source_number(PowerPCCPU *cpu,
- sPAPREnvironment *spapr,
+ sPAPRMachineState *spapr,
uint32_t token,
uint32_t nargs,
target_ulong args,
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);
+ uint64_t buid = rtas_ldq(args, 1);
unsigned int intr_src_num = -1, ioa_intr_num = rtas_ld(args, 3);
- int ndev;
sPAPRPHBState *phb = NULL;
+ PCIDevice *pdev = NULL;
+ spapr_pci_msi *msi;
- /* Fins sPAPRPHBState */
- phb = find_phb(spapr, buid);
- if (!phb) {
+ /* Find sPAPRPHBState */
+ phb = spapr_pci_find_phb(spapr, buid);
+ if (phb) {
+ pdev = spapr_pci_find_dev(spapr, buid, config_addr);
+ }
+ if (!phb || !pdev) {
rtas_st(rets, 0, RTAS_OUT_PARAM_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);
+ msi = (spapr_pci_msi *) g_hash_table_lookup(phb->msi, &config_addr);
+ if (!msi || !msi->first_irq || !msi->num || (ioa_intr_num >= msi->num)) {
+ trace_spapr_pci_msi("Failed to return vector", config_addr);
rtas_st(rets, 0, RTAS_OUT_HW_ERROR);
return;
}
-
- intr_src_num = phb->msi_table[ndev].irq + ioa_intr_num;
+ intr_src_num = msi->first_irq + ioa_intr_num;
trace_spapr_pci_rtas_ibm_query_interrupt_source_number(ioa_intr_num,
intr_src_num);
rtas_st(rets, 2, 1);/* 0 == level; 1 == edge */
}
+static void rtas_ibm_set_eeh_option(PowerPCCPU *cpu,
+ sPAPRMachineState *spapr,
+ uint32_t token, uint32_t nargs,
+ target_ulong args, uint32_t nret,
+ target_ulong rets)
+{
+ sPAPRPHBState *sphb;
+ sPAPRPHBClass *spc;
+ uint32_t addr, option;
+ uint64_t buid;
+ int ret;
+
+ if ((nargs != 4) || (nret != 1)) {
+ goto param_error_exit;
+ }
+
+ buid = rtas_ldq(args, 1);
+ addr = rtas_ld(args, 0);
+ option = rtas_ld(args, 3);
+
+ sphb = spapr_pci_find_phb(spapr, buid);
+ if (!sphb) {
+ goto param_error_exit;
+ }
+
+ spc = SPAPR_PCI_HOST_BRIDGE_GET_CLASS(sphb);
+ if (!spc->eeh_set_option) {
+ goto param_error_exit;
+ }
+
+ ret = spc->eeh_set_option(sphb, addr, option);
+ rtas_st(rets, 0, ret);
+ return;
+
+param_error_exit:
+ rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR);
+}
+
+static void rtas_ibm_get_config_addr_info2(PowerPCCPU *cpu,
+ sPAPRMachineState *spapr,
+ uint32_t token, uint32_t nargs,
+ target_ulong args, uint32_t nret,
+ target_ulong rets)
+{
+ sPAPRPHBState *sphb;
+ sPAPRPHBClass *spc;
+ PCIDevice *pdev;
+ uint32_t addr, option;
+ uint64_t buid;
+
+ if ((nargs != 4) || (nret != 2)) {
+ goto param_error_exit;
+ }
+
+ buid = rtas_ldq(args, 1);
+ sphb = spapr_pci_find_phb(spapr, buid);
+ if (!sphb) {
+ goto param_error_exit;
+ }
+
+ spc = SPAPR_PCI_HOST_BRIDGE_GET_CLASS(sphb);
+ if (!spc->eeh_set_option) {
+ goto param_error_exit;
+ }
+
+ /*
+ * We always have PE address of form "00BB0001". "BB"
+ * represents the bus number of PE's primary bus.
+ */
+ option = rtas_ld(args, 3);
+ switch (option) {
+ case RTAS_GET_PE_ADDR:
+ addr = rtas_ld(args, 0);
+ pdev = spapr_pci_find_dev(spapr, buid, addr);
+ if (!pdev) {
+ goto param_error_exit;
+ }
+
+ rtas_st(rets, 1, (pci_bus_num(pdev->bus) << 16) + 1);
+ break;
+ case RTAS_GET_PE_MODE:
+ rtas_st(rets, 1, RTAS_PE_MODE_SHARED);
+ break;
+ default:
+ goto param_error_exit;
+ }
+
+ rtas_st(rets, 0, RTAS_OUT_SUCCESS);
+ return;
+
+param_error_exit:
+ rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR);
+}
+
+static void rtas_ibm_read_slot_reset_state2(PowerPCCPU *cpu,
+ sPAPRMachineState *spapr,
+ uint32_t token, uint32_t nargs,
+ target_ulong args, uint32_t nret,
+ target_ulong rets)
+{
+ sPAPRPHBState *sphb;
+ sPAPRPHBClass *spc;
+ uint64_t buid;
+ int state, ret;
+
+ if ((nargs != 3) || (nret != 4 && nret != 5)) {
+ goto param_error_exit;
+ }
+
+ buid = rtas_ldq(args, 1);
+ sphb = spapr_pci_find_phb(spapr, buid);
+ if (!sphb) {
+ goto param_error_exit;
+ }
+
+ spc = SPAPR_PCI_HOST_BRIDGE_GET_CLASS(sphb);
+ if (!spc->eeh_get_state) {
+ goto param_error_exit;
+ }
+
+ ret = spc->eeh_get_state(sphb, &state);
+ rtas_st(rets, 0, ret);
+ if (ret != RTAS_OUT_SUCCESS) {
+ return;
+ }
+
+ rtas_st(rets, 1, state);
+ rtas_st(rets, 2, RTAS_EEH_SUPPORT);
+ rtas_st(rets, 3, RTAS_EEH_PE_UNAVAIL_INFO);
+ if (nret >= 5) {
+ rtas_st(rets, 4, RTAS_EEH_PE_RECOVER_INFO);
+ }
+ return;
+
+param_error_exit:
+ rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR);
+}
+
+static void rtas_ibm_set_slot_reset(PowerPCCPU *cpu,
+ sPAPRMachineState *spapr,
+ uint32_t token, uint32_t nargs,
+ target_ulong args, uint32_t nret,
+ target_ulong rets)
+{
+ sPAPRPHBState *sphb;
+ sPAPRPHBClass *spc;
+ uint32_t option;
+ uint64_t buid;
+ int ret;
+
+ if ((nargs != 4) || (nret != 1)) {
+ goto param_error_exit;
+ }
+
+ buid = rtas_ldq(args, 1);
+ option = rtas_ld(args, 3);
+ sphb = spapr_pci_find_phb(spapr, buid);
+ if (!sphb) {
+ goto param_error_exit;
+ }
+
+ spc = SPAPR_PCI_HOST_BRIDGE_GET_CLASS(sphb);
+ if (!spc->eeh_reset) {
+ goto param_error_exit;
+ }
+
+ ret = spc->eeh_reset(sphb, option);
+ rtas_st(rets, 0, ret);
+ return;
+
+param_error_exit:
+ rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR);
+}
+
+static void rtas_ibm_configure_pe(PowerPCCPU *cpu,
+ sPAPRMachineState *spapr,
+ uint32_t token, uint32_t nargs,
+ target_ulong args, uint32_t nret,
+ target_ulong rets)
+{
+ sPAPRPHBState *sphb;
+ sPAPRPHBClass *spc;
+ uint64_t buid;
+ int ret;
+
+ if ((nargs != 3) || (nret != 1)) {
+ goto param_error_exit;
+ }
+
+ buid = rtas_ldq(args, 1);
+ sphb = spapr_pci_find_phb(spapr, buid);
+ if (!sphb) {
+ goto param_error_exit;
+ }
+
+ spc = SPAPR_PCI_HOST_BRIDGE_GET_CLASS(sphb);
+ if (!spc->eeh_configure) {
+ goto param_error_exit;
+ }
+
+ ret = spc->eeh_configure(sphb);
+ rtas_st(rets, 0, ret);
+ return;
+
+param_error_exit:
+ rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR);
+}
+
+/* To support it later */
+static void rtas_ibm_slot_error_detail(PowerPCCPU *cpu,
+ sPAPRMachineState *spapr,
+ uint32_t token, uint32_t nargs,
+ target_ulong args, uint32_t nret,
+ target_ulong rets)
+{
+ sPAPRPHBState *sphb;
+ sPAPRPHBClass *spc;
+ int option;
+ uint64_t buid;
+
+ if ((nargs != 8) || (nret != 1)) {
+ goto param_error_exit;
+ }
+
+ buid = rtas_ldq(args, 1);
+ sphb = spapr_pci_find_phb(spapr, buid);
+ if (!sphb) {
+ goto param_error_exit;
+ }
+
+ spc = SPAPR_PCI_HOST_BRIDGE_GET_CLASS(sphb);
+ if (!spc->eeh_set_option) {
+ goto param_error_exit;
+ }
+
+ option = rtas_ld(args, 7);
+ switch (option) {
+ case RTAS_SLOT_TEMP_ERR_LOG:
+ case RTAS_SLOT_PERM_ERR_LOG:
+ break;
+ default:
+ goto param_error_exit;
+ }
+
+ /* We don't have error log yet */
+ rtas_st(rets, 0, RTAS_OUT_NO_ERRORS_FOUND);
+ return;
+
+param_error_exit:
+ rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR);
+}
+
static int pci_spapr_swizzle(int slot, int pin)
{
return (slot + pin) % PCI_NUM_PINS;
static void spapr_msi_write(void *opaque, hwaddr addr,
uint64_t data, unsigned size)
{
+ sPAPRMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
uint32_t irq = data;
trace_spapr_pci_msi_write(addr, data, irq);
.endianness = DEVICE_LITTLE_ENDIAN
};
-void spapr_pci_msi_init(sPAPREnvironment *spapr, hwaddr addr)
+/*
+ * PHB PCI device
+ */
+static AddressSpace *spapr_pci_dma_iommu(PCIBus *bus, void *opaque, int devfn)
{
- uint64_t window_size = 4096;
+ sPAPRPHBState *phb = opaque;
+ return &phb->iommu_as;
+}
+
+static char *spapr_phb_vfio_get_loc_code(sPAPRPHBState *sphb, PCIDevice *pdev)
+{
+ char *path = NULL, *buf = NULL, *host = NULL;
+
+ /* Get the PCI VFIO host id */
+ host = object_property_get_str(OBJECT(pdev), "host", NULL);
+ if (!host) {
+ goto err_out;
+ }
+
+ /* Construct the path of the file that will give us the DT location */
+ path = g_strdup_printf("/sys/bus/pci/devices/%s/devspec", host);
+ g_free(host);
+ if (!path || !g_file_get_contents(path, &buf, NULL, NULL)) {
+ goto err_out;
+ }
+ g_free(path);
+
+ /* Construct and read from host device tree the loc-code */
+ path = g_strdup_printf("/proc/device-tree%s/ibm,loc-code", buf);
+ g_free(buf);
+ if (!path || !g_file_get_contents(path, &buf, NULL, NULL)) {
+ goto err_out;
+ }
+ return buf;
+
+err_out:
+ g_free(path);
+ return NULL;
+}
+
+static char *spapr_phb_get_loc_code(sPAPRPHBState *sphb, PCIDevice *pdev)
+{
+ char *buf;
+ const char *devtype = "qemu";
+ uint32_t busnr = pci_bus_num(PCI_BUS(qdev_get_parent_bus(DEVICE(pdev))));
+
+ if (object_dynamic_cast(OBJECT(pdev), "vfio-pci")) {
+ buf = spapr_phb_vfio_get_loc_code(sphb, pdev);
+ if (buf) {
+ return buf;
+ }
+ devtype = "vfio";
+ }
/*
- * 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().
- * As MSIMessage:addr is going to be the same and MSIMessage:data
- * is going to be a VIRQ number, 4 bytes of the MSI MR will only
- * be used.
- *
- * For KVM we want to ensure that this memory is a full page so that
- * our memory slot is of page size granularity.
+ * For emulated devices and VFIO-failure case, make up
+ * the loc-code.
*/
-#ifdef CONFIG_KVM
- if (kvm_enabled()) {
- window_size = getpagesize();
+ buf = g_strdup_printf("%s_%s:%04x:%02x:%02x.%x",
+ devtype, pdev->name, sphb->index, busnr,
+ PCI_SLOT(pdev->devfn), PCI_FUNC(pdev->devfn));
+ return buf;
+}
+
+/* Macros to operate with address in OF binding to PCI */
+#define b_x(x, p, l) (((x) & ((1<<(l))-1)) << (p))
+#define b_n(x) b_x((x), 31, 1) /* 0 if relocatable */
+#define b_p(x) b_x((x), 30, 1) /* 1 if prefetchable */
+#define b_t(x) b_x((x), 29, 1) /* 1 if the address is aliased */
+#define b_ss(x) b_x((x), 24, 2) /* the space code */
+#define b_bbbbbbbb(x) b_x((x), 16, 8) /* bus number */
+#define b_ddddd(x) b_x((x), 11, 5) /* device number */
+#define b_fff(x) b_x((x), 8, 3) /* function number */
+#define b_rrrrrrrr(x) b_x((x), 0, 8) /* register number */
+
+/* for 'reg'/'assigned-addresses' OF properties */
+#define RESOURCE_CELLS_SIZE 2
+#define RESOURCE_CELLS_ADDRESS 3
+
+typedef struct ResourceFields {
+ uint32_t phys_hi;
+ uint32_t phys_mid;
+ uint32_t phys_lo;
+ uint32_t size_hi;
+ uint32_t size_lo;
+} QEMU_PACKED ResourceFields;
+
+typedef struct ResourceProps {
+ ResourceFields reg[8];
+ ResourceFields assigned[7];
+ uint32_t reg_len;
+ uint32_t assigned_len;
+} ResourceProps;
+
+/* fill in the 'reg'/'assigned-resources' OF properties for
+ * a PCI device. 'reg' describes resource requirements for a
+ * device's IO/MEM regions, 'assigned-addresses' describes the
+ * actual resource assignments.
+ *
+ * the properties are arrays of ('phys-addr', 'size') pairs describing
+ * the addressable regions of the PCI device, where 'phys-addr' is a
+ * RESOURCE_CELLS_ADDRESS-tuple of 32-bit integers corresponding to
+ * (phys.hi, phys.mid, phys.lo), and 'size' is a
+ * RESOURCE_CELLS_SIZE-tuple corresponding to (size.hi, size.lo).
+ *
+ * phys.hi = 0xYYXXXXZZ, where:
+ * 0xYY = npt000ss
+ * ||| |
+ * ||| +-- space code
+ * ||| |
+ * ||| + 00 if configuration space
+ * ||| + 01 if IO region,
+ * ||| + 10 if 32-bit MEM region
+ * ||| + 11 if 64-bit MEM region
+ * |||
+ * ||+------ for non-relocatable IO: 1 if aliased
+ * || for relocatable IO: 1 if below 64KB
+ * || for MEM: 1 if below 1MB
+ * |+------- 1 if region is prefetchable
+ * +-------- 1 if region is non-relocatable
+ * 0xXXXX = bbbbbbbb dddddfff, encoding bus, slot, and function
+ * bits respectively
+ * 0xZZ = rrrrrrrr, the register number of the BAR corresponding
+ * to the region
+ *
+ * phys.mid and phys.lo correspond respectively to the hi/lo portions
+ * of the actual address of the region.
+ *
+ * how the phys-addr/size values are used differ slightly between
+ * 'reg' and 'assigned-addresses' properties. namely, 'reg' has
+ * an additional description for the config space region of the
+ * device, and in the case of QEMU has n=0 and phys.mid=phys.lo=0
+ * to describe the region as relocatable, with an address-mapping
+ * that corresponds directly to the PHB's address space for the
+ * resource. 'assigned-addresses' always has n=1 set with an absolute
+ * address assigned for the resource. in general, 'assigned-addresses'
+ * won't be populated, since addresses for PCI devices are generally
+ * unmapped initially and left to the guest to assign.
+ *
+ * note also that addresses defined in these properties are, at least
+ * for PAPR guests, relative to the PHBs IO/MEM windows, and
+ * correspond directly to the addresses in the BARs.
+ *
+ * in accordance with PCI Bus Binding to Open Firmware,
+ * IEEE Std 1275-1994, section 4.1.1, as implemented by PAPR+ v2.7,
+ * Appendix C.
+ */
+static void populate_resource_props(PCIDevice *d, ResourceProps *rp)
+{
+ int bus_num = pci_bus_num(PCI_BUS(qdev_get_parent_bus(DEVICE(d))));
+ uint32_t dev_id = (b_bbbbbbbb(bus_num) |
+ b_ddddd(PCI_SLOT(d->devfn)) |
+ b_fff(PCI_FUNC(d->devfn)));
+ ResourceFields *reg, *assigned;
+ int i, reg_idx = 0, assigned_idx = 0;
+
+ /* config space region */
+ reg = &rp->reg[reg_idx++];
+ reg->phys_hi = cpu_to_be32(dev_id);
+ reg->phys_mid = 0;
+ reg->phys_lo = 0;
+ reg->size_hi = 0;
+ reg->size_lo = 0;
+
+ for (i = 0; i < PCI_NUM_REGIONS; i++) {
+ if (!d->io_regions[i].size) {
+ continue;
+ }
+
+ reg = &rp->reg[reg_idx++];
+
+ reg->phys_hi = cpu_to_be32(dev_id | b_rrrrrrrr(pci_bar(d, i)));
+ if (d->io_regions[i].type & PCI_BASE_ADDRESS_SPACE_IO) {
+ reg->phys_hi |= cpu_to_be32(b_ss(1));
+ } else if (d->io_regions[i].type & PCI_BASE_ADDRESS_MEM_TYPE_64) {
+ reg->phys_hi |= cpu_to_be32(b_ss(3));
+ } else {
+ reg->phys_hi |= cpu_to_be32(b_ss(2));
+ }
+ reg->phys_mid = 0;
+ reg->phys_lo = 0;
+ reg->size_hi = cpu_to_be32(d->io_regions[i].size >> 32);
+ reg->size_lo = cpu_to_be32(d->io_regions[i].size);
+
+ if (d->io_regions[i].addr == PCI_BAR_UNMAPPED) {
+ continue;
+ }
+
+ assigned = &rp->assigned[assigned_idx++];
+ assigned->phys_hi = cpu_to_be32(reg->phys_hi | b_n(1));
+ assigned->phys_mid = cpu_to_be32(d->io_regions[i].addr >> 32);
+ assigned->phys_lo = cpu_to_be32(d->io_regions[i].addr);
+ assigned->size_hi = reg->size_hi;
+ assigned->size_lo = reg->size_lo;
}
-#endif
- spapr->msi_win_addr = addr;
- memory_region_init_io(&spapr->msiwindow, NULL, &spapr_msi_ops, spapr,
- "msi", window_size);
- memory_region_add_subregion(get_system_memory(), spapr->msi_win_addr,
- &spapr->msiwindow);
+ rp->reg_len = reg_idx * sizeof(ResourceFields);
+ rp->assigned_len = assigned_idx * sizeof(ResourceFields);
}
-/*
- * PHB PCI device
- */
-static AddressSpace *spapr_pci_dma_iommu(PCIBus *bus, void *opaque, int devfn)
+static uint32_t spapr_phb_get_pci_drc_index(sPAPRPHBState *phb,
+ PCIDevice *pdev);
+
+static int spapr_populate_pci_child_dt(PCIDevice *dev, void *fdt, int offset,
+ sPAPRPHBState *sphb)
{
- sPAPRPHBState *phb = opaque;
+ ResourceProps rp;
+ bool is_bridge = false;
+ int pci_status, err;
+ char *buf = NULL;
+ uint32_t drc_index = spapr_phb_get_pci_drc_index(sphb, dev);
+ uint32_t max_msi, max_msix;
+
+ if (pci_default_read_config(dev, PCI_HEADER_TYPE, 1) ==
+ PCI_HEADER_TYPE_BRIDGE) {
+ is_bridge = true;
+ }
- return &phb->iommu_as;
+ /* in accordance with PAPR+ v2.7 13.6.3, Table 181 */
+ _FDT(fdt_setprop_cell(fdt, offset, "vendor-id",
+ pci_default_read_config(dev, PCI_VENDOR_ID, 2)));
+ _FDT(fdt_setprop_cell(fdt, offset, "device-id",
+ pci_default_read_config(dev, PCI_DEVICE_ID, 2)));
+ _FDT(fdt_setprop_cell(fdt, offset, "revision-id",
+ pci_default_read_config(dev, PCI_REVISION_ID, 1)));
+ _FDT(fdt_setprop_cell(fdt, offset, "class-code",
+ pci_default_read_config(dev, PCI_CLASS_PROG, 3)));
+ if (pci_default_read_config(dev, PCI_INTERRUPT_PIN, 1)) {
+ _FDT(fdt_setprop_cell(fdt, offset, "interrupts",
+ pci_default_read_config(dev, PCI_INTERRUPT_PIN, 1)));
+ }
+
+ if (!is_bridge) {
+ _FDT(fdt_setprop_cell(fdt, offset, "min-grant",
+ pci_default_read_config(dev, PCI_MIN_GNT, 1)));
+ _FDT(fdt_setprop_cell(fdt, offset, "max-latency",
+ pci_default_read_config(dev, PCI_MAX_LAT, 1)));
+ }
+
+ if (pci_default_read_config(dev, PCI_SUBSYSTEM_ID, 2)) {
+ _FDT(fdt_setprop_cell(fdt, offset, "subsystem-id",
+ pci_default_read_config(dev, PCI_SUBSYSTEM_ID, 2)));
+ }
+
+ if (pci_default_read_config(dev, PCI_SUBSYSTEM_VENDOR_ID, 2)) {
+ _FDT(fdt_setprop_cell(fdt, offset, "subsystem-vendor-id",
+ pci_default_read_config(dev, PCI_SUBSYSTEM_VENDOR_ID, 2)));
+ }
+
+ _FDT(fdt_setprop_cell(fdt, offset, "cache-line-size",
+ pci_default_read_config(dev, PCI_CACHE_LINE_SIZE, 1)));
+
+ /* the following fdt cells are masked off the pci status register */
+ pci_status = pci_default_read_config(dev, PCI_STATUS, 2);
+ _FDT(fdt_setprop_cell(fdt, offset, "devsel-speed",
+ PCI_STATUS_DEVSEL_MASK & pci_status));
+
+ if (pci_status & PCI_STATUS_FAST_BACK) {
+ _FDT(fdt_setprop(fdt, offset, "fast-back-to-back", NULL, 0));
+ }
+ if (pci_status & PCI_STATUS_66MHZ) {
+ _FDT(fdt_setprop(fdt, offset, "66mhz-capable", NULL, 0));
+ }
+ if (pci_status & PCI_STATUS_UDF) {
+ _FDT(fdt_setprop(fdt, offset, "udf-supported", NULL, 0));
+ }
+
+ /* NOTE: this is normally generated by firmware via path/unit name,
+ * but in our case we must set it manually since it does not get
+ * processed by OF beforehand
+ */
+ _FDT(fdt_setprop_string(fdt, offset, "name", "pci"));
+ buf = spapr_phb_get_loc_code(sphb, dev);
+ if (!buf) {
+ error_report("Failed setting the ibm,loc-code");
+ return -1;
+ }
+
+ err = fdt_setprop_string(fdt, offset, "ibm,loc-code", buf);
+ g_free(buf);
+ if (err < 0) {
+ return err;
+ }
+
+ if (drc_index) {
+ _FDT(fdt_setprop_cell(fdt, offset, "ibm,my-drc-index", drc_index));
+ }
+
+ _FDT(fdt_setprop_cell(fdt, offset, "#address-cells",
+ RESOURCE_CELLS_ADDRESS));
+ _FDT(fdt_setprop_cell(fdt, offset, "#size-cells",
+ RESOURCE_CELLS_SIZE));
+
+ max_msi = msi_nr_vectors_allocated(dev);
+ if (max_msi) {
+ _FDT(fdt_setprop_cell(fdt, offset, "ibm,req#msi", max_msi));
+ }
+ max_msix = dev->msix_entries_nr;
+ if (max_msix) {
+ _FDT(fdt_setprop_cell(fdt, offset, "ibm,req#msi-x", max_msix));
+ }
+
+ populate_resource_props(dev, &rp);
+ _FDT(fdt_setprop(fdt, offset, "reg", (uint8_t *)rp.reg, rp.reg_len));
+ _FDT(fdt_setprop(fdt, offset, "assigned-addresses",
+ (uint8_t *)rp.assigned, rp.assigned_len));
+
+ return 0;
+}
+
+/* create OF node for pci device and required OF DT properties */
+static int spapr_create_pci_child_dt(sPAPRPHBState *phb, PCIDevice *dev,
+ void *fdt, int node_offset)
+{
+ int offset, ret;
+ int slot = PCI_SLOT(dev->devfn);
+ int func = PCI_FUNC(dev->devfn);
+ char nodename[FDT_NAME_MAX];
+
+ if (func != 0) {
+ snprintf(nodename, FDT_NAME_MAX, "pci@%x,%x", slot, func);
+ } else {
+ snprintf(nodename, FDT_NAME_MAX, "pci@%x", slot);
+ }
+ offset = fdt_add_subnode(fdt, node_offset, nodename);
+ ret = spapr_populate_pci_child_dt(dev, fdt, offset, phb);
+
+ g_assert(!ret);
+ if (ret) {
+ return 0;
+ }
+ return offset;
+}
+
+static void spapr_phb_add_pci_device(sPAPRDRConnector *drc,
+ sPAPRPHBState *phb,
+ PCIDevice *pdev,
+ Error **errp)
+{
+ sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
+ DeviceState *dev = DEVICE(pdev);
+ void *fdt = NULL;
+ int fdt_start_offset = 0, fdt_size;
+
+ if (dev->hotplugged) {
+ fdt = create_device_tree(&fdt_size);
+ fdt_start_offset = spapr_create_pci_child_dt(phb, pdev, fdt, 0);
+ if (!fdt_start_offset) {
+ error_setg(errp, "Failed to create pci child device tree node");
+ goto out;
+ }
+ }
+
+ drck->attach(drc, DEVICE(pdev),
+ fdt, fdt_start_offset, !dev->hotplugged, errp);
+out:
+ if (*errp) {
+ g_free(fdt);
+ }
+}
+
+static void spapr_phb_remove_pci_device_cb(DeviceState *dev, void *opaque)
+{
+ /* some version guests do not wait for completion of a device
+ * cleanup (generally done asynchronously by the kernel) before
+ * signaling to QEMU that the device is safe, but instead sleep
+ * for some 'safe' period of time. unfortunately on a busy host
+ * this sleep isn't guaranteed to be long enough, resulting in
+ * bad things like IRQ lines being left asserted during final
+ * device removal. to deal with this we call reset just prior
+ * to finalizing the device, which will put the device back into
+ * an 'idle' state, as the device cleanup code expects.
+ */
+ pci_device_reset(PCI_DEVICE(dev));
+ object_unparent(OBJECT(dev));
+}
+
+static void spapr_phb_remove_pci_device(sPAPRDRConnector *drc,
+ sPAPRPHBState *phb,
+ PCIDevice *pdev,
+ Error **errp)
+{
+ sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
+
+ drck->detach(drc, DEVICE(pdev), spapr_phb_remove_pci_device_cb, phb, errp);
+}
+
+static sPAPRDRConnector *spapr_phb_get_pci_drc(sPAPRPHBState *phb,
+ PCIDevice *pdev)
+{
+ uint32_t busnr = pci_bus_num(PCI_BUS(qdev_get_parent_bus(DEVICE(pdev))));
+ return spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_PCI,
+ (phb->index << 16) |
+ (busnr << 8) |
+ pdev->devfn);
+}
+
+static uint32_t spapr_phb_get_pci_drc_index(sPAPRPHBState *phb,
+ PCIDevice *pdev)
+{
+ sPAPRDRConnector *drc = spapr_phb_get_pci_drc(phb, pdev);
+ sPAPRDRConnectorClass *drck;
+
+ if (!drc) {
+ return 0;
+ }
+
+ drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
+ return drck->get_index(drc);
+}
+
+static void spapr_phb_hot_plug_child(HotplugHandler *plug_handler,
+ DeviceState *plugged_dev, Error **errp)
+{
+ sPAPRPHBState *phb = SPAPR_PCI_HOST_BRIDGE(DEVICE(plug_handler));
+ PCIDevice *pdev = PCI_DEVICE(plugged_dev);
+ sPAPRDRConnector *drc = spapr_phb_get_pci_drc(phb, pdev);
+ Error *local_err = NULL;
+
+ /* if DR is disabled we don't need to do anything in the case of
+ * hotplug or coldplug callbacks
+ */
+ if (!phb->dr_enabled) {
+ /* if this is a hotplug operation initiated by the user
+ * we need to let them know it's not enabled
+ */
+ if (plugged_dev->hotplugged) {
+ error_setg(errp, QERR_BUS_NO_HOTPLUG,
+ object_get_typename(OBJECT(phb)));
+ }
+ return;
+ }
+
+ g_assert(drc);
+
+ spapr_phb_add_pci_device(drc, phb, pdev, &local_err);
+ if (local_err) {
+ error_propagate(errp, local_err);
+ return;
+ }
+ if (plugged_dev->hotplugged) {
+ spapr_hotplug_req_add_by_index(drc);
+ }
+}
+
+static void spapr_phb_hot_unplug_child(HotplugHandler *plug_handler,
+ DeviceState *plugged_dev, Error **errp)
+{
+ sPAPRPHBState *phb = SPAPR_PCI_HOST_BRIDGE(DEVICE(plug_handler));
+ PCIDevice *pdev = PCI_DEVICE(plugged_dev);
+ sPAPRDRConnectorClass *drck;
+ sPAPRDRConnector *drc = spapr_phb_get_pci_drc(phb, pdev);
+ Error *local_err = NULL;
+
+ if (!phb->dr_enabled) {
+ error_setg(errp, QERR_BUS_NO_HOTPLUG,
+ object_get_typename(OBJECT(phb)));
+ return;
+ }
+
+ g_assert(drc);
+
+ drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
+ if (!drck->release_pending(drc)) {
+ spapr_phb_remove_pci_device(drc, phb, pdev, &local_err);
+ if (local_err) {
+ error_propagate(errp, local_err);
+ return;
+ }
+ spapr_hotplug_req_remove_by_index(drc);
+ }
}
static void spapr_phb_realize(DeviceState *dev, Error **errp)
{
+ sPAPRMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
SysBusDevice *s = SYS_BUS_DEVICE(dev);
sPAPRPHBState *sphb = SPAPR_PCI_HOST_BRIDGE(s);
PCIHostState *phb = PCI_HOST_BRIDGE(s);
+ sPAPRPHBClass *info = SPAPR_PCI_HOST_BRIDGE_GET_CLASS(s);
char *namebuf;
int i;
PCIBus *bus;
+ uint64_t msi_window_size = 4096;
- if (sphb->index != -1) {
+ if (sphb->index != (uint32_t)-1) {
hwaddr windows_base;
- if ((sphb->buid != -1) || (sphb->dma_liobn != -1)
- || (sphb->mem_win_addr != -1)
- || (sphb->io_win_addr != -1)) {
+ if ((sphb->buid != (uint64_t)-1) || (sphb->dma_liobn != (uint32_t)-1)
+ || (sphb->mem_win_addr != (hwaddr)-1)
+ || (sphb->io_win_addr != (hwaddr)-1)) {
error_setg(errp, "Either \"index\" or other parameters must"
" be specified for PAPR PHB, not both");
return;
}
+ if (sphb->index > SPAPR_PCI_MAX_INDEX) {
+ error_setg(errp, "\"index\" for PAPR PHB is too large (max %u)",
+ SPAPR_PCI_MAX_INDEX);
+ return;
+ }
+
sphb->buid = SPAPR_PCI_BASE_BUID + sphb->index;
- sphb->dma_liobn = SPAPR_PCI_BASE_LIOBN + sphb->index;
+ sphb->dma_liobn = SPAPR_PCI_LIOBN(sphb->index, 0);
windows_base = SPAPR_PCI_WINDOW_BASE
+ sphb->index * SPAPR_PCI_WINDOW_SPACING;
sphb->io_win_addr = windows_base + SPAPR_PCI_IO_WIN_OFF;
}
- if (sphb->buid == -1) {
+ if (sphb->buid == (uint64_t)-1) {
error_setg(errp, "BUID not specified for PHB");
return;
}
- if (sphb->dma_liobn == -1) {
+ if (sphb->dma_liobn == (uint32_t)-1) {
error_setg(errp, "LIOBN not specified for PHB");
return;
}
- if (sphb->mem_win_addr == -1) {
+ if (sphb->mem_win_addr == (hwaddr)-1) {
error_setg(errp, "Memory window address not specified for PHB");
return;
}
- if (sphb->io_win_addr == -1) {
+ if (sphb->io_win_addr == (hwaddr)-1) {
error_setg(errp, "IO window address not specified for PHB");
return;
}
- if (find_phb(spapr, sphb->buid)) {
+ if (spapr_pci_find_phb(spapr, sphb->buid)) {
error_setg(errp, "PCI host bridges must have unique BUIDs");
return;
}
memory_region_add_subregion(get_system_memory(), sphb->mem_win_addr,
&sphb->memwindow);
- /* On ppc, we only have MMIO no specific IO space from the CPU
- * perspective. In theory we ought to be able to embed the PCI IO
- * memory region direction in the system memory space. However,
- * if any of the IO BAR subregions use the old_portio mechanism,
- * that won't be processed properly unless accessed from the
- * system io address space. This hack to bounce things via
- * system_io works around the problem until all the users of
- * old_portion are updated */
+ /* Initialize IO regions */
sprintf(namebuf, "%s.io", sphb->dtbusname);
memory_region_init(&sphb->iospace, OBJECT(sphb),
namebuf, SPAPR_PCI_IO_WIN_SIZE);
- /* FIXME: fix to support multiple PHBs */
- memory_region_add_subregion(get_system_io(), 0, &sphb->iospace);
sprintf(namebuf, "%s.io-alias", sphb->dtbusname);
memory_region_init_alias(&sphb->iowindow, OBJECT(sphb), namebuf,
- get_system_io(), 0, SPAPR_PCI_IO_WIN_SIZE);
+ &sphb->iospace, 0, SPAPR_PCI_IO_WIN_SIZE);
memory_region_add_subregion(get_system_memory(), sphb->io_win_addr,
&sphb->iowindow);
&sphb->memspace, &sphb->iospace,
PCI_DEVFN(0, 0), PCI_NUM_PINS, TYPE_PCI_BUS);
phb->bus = bus;
+ qbus_set_hotplug_handler(BUS(phb->bus), DEVICE(sphb), NULL);
- sphb->dma_window_start = 0;
- sphb->dma_window_size = 0x40000000;
- sphb->tcet = spapr_tce_new_table(dev, sphb->dma_liobn,
- sphb->dma_window_size);
- if (!sphb->tcet) {
- error_setg(errp, "Unable to create TCE table for %s",
- sphb->dtbusname);
- return;
- }
- address_space_init(&sphb->iommu_as, spapr_tce_get_iommu(sphb->tcet),
+ /*
+ * Initialize PHB address space.
+ * By default there will be at least one subregion for default
+ * 32bit DMA window.
+ * Later the guest might want to create another DMA window
+ * which will become another memory subregion.
+ */
+ sprintf(namebuf, "%s.iommu-root", sphb->dtbusname);
+
+ memory_region_init(&sphb->iommu_root, OBJECT(sphb),
+ namebuf, UINT64_MAX);
+ address_space_init(&sphb->iommu_as, &sphb->iommu_root,
sphb->dtbusname);
+ /*
+ * 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().
+ * As MSIMessage:addr is going to be the same and MSIMessage:data
+ * is going to be a VIRQ number, 4 bytes of the MSI MR will only
+ * be used.
+ *
+ * For KVM we want to ensure that this memory is a full page so that
+ * our memory slot is of page size granularity.
+ */
+#ifdef CONFIG_KVM
+ if (kvm_enabled()) {
+ msi_window_size = getpagesize();
+ }
+#endif
+
+ memory_region_init_io(&sphb->msiwindow, NULL, &spapr_msi_ops, spapr,
+ "msi", msi_window_size);
+ memory_region_add_subregion(&sphb->iommu_root, SPAPR_PCI_MSI_WINDOW,
+ &sphb->msiwindow);
+
pci_setup_iommu(bus, spapr_pci_dma_iommu, sphb);
pci_bus_set_route_irq_fn(bus, spapr_route_intx_pin_to_irq);
for (i = 0; i < PCI_NUM_PINS; i++) {
uint32_t irq;
- irq = spapr_allocate_lsi(0);
+ irq = xics_alloc_block(spapr->icp, 0, 1, true, false);
if (!irq) {
error_setg(errp, "spapr_allocate_lsi failed");
return;
sphb->lsi_table[i].irq = irq;
}
+
+ /* allocate connectors for child PCI devices */
+ if (sphb->dr_enabled) {
+ for (i = 0; i < PCI_SLOT_MAX * 8; i++) {
+ spapr_dr_connector_new(OBJECT(phb),
+ SPAPR_DR_CONNECTOR_TYPE_PCI,
+ (sphb->index << 16) | i);
+ }
+ }
+
+ if (!info->finish_realize) {
+ error_setg(errp, "finish_realize not defined");
+ return;
+ }
+
+ info->finish_realize(sphb, errp);
+
+ sphb->msi = g_hash_table_new_full(g_int_hash, g_int_equal, g_free, g_free);
}
-static void spapr_phb_reset(DeviceState *qdev)
+static void spapr_phb_finish_realize(sPAPRPHBState *sphb, Error **errp)
{
- SysBusDevice *s = SYS_BUS_DEVICE(qdev);
- sPAPRPHBState *sphb = SPAPR_PCI_HOST_BRIDGE(s);
+ sPAPRTCETable *tcet;
+ uint32_t nb_table;
+
+ nb_table = SPAPR_PCI_DMA32_SIZE >> SPAPR_TCE_PAGE_SHIFT;
+ tcet = spapr_tce_new_table(DEVICE(sphb), sphb->dma_liobn,
+ 0, SPAPR_TCE_PAGE_SHIFT, nb_table, false);
+ if (!tcet) {
+ error_setg(errp, "Unable to create TCE table for %s",
+ sphb->dtbusname);
+ return ;
+ }
+
+ /* Register default 32bit DMA window */
+ memory_region_add_subregion(&sphb->iommu_root, 0,
+ spapr_tce_get_iommu(tcet));
+}
+
+static int spapr_phb_children_reset(Object *child, void *opaque)
+{
+ DeviceState *dev = (DeviceState *) object_dynamic_cast(child, TYPE_DEVICE);
+
+ if (dev) {
+ device_reset(dev);
+ }
+
+ return 0;
+}
+static void spapr_phb_reset(DeviceState *qdev)
+{
/* Reset the IOMMU state */
- device_reset(DEVICE(sphb->tcet));
+ object_child_foreach(OBJECT(qdev), spapr_phb_children_reset, NULL);
}
static Property spapr_phb_properties[] = {
- DEFINE_PROP_INT32("index", sPAPRPHBState, index, -1),
+ DEFINE_PROP_UINT32("index", sPAPRPHBState, index, -1),
DEFINE_PROP_UINT64("buid", sPAPRPHBState, buid, -1),
DEFINE_PROP_UINT32("liobn", sPAPRPHBState, dma_liobn, -1),
DEFINE_PROP_UINT64("mem_win_addr", sPAPRPHBState, mem_win_addr, -1),
DEFINE_PROP_UINT64("io_win_addr", sPAPRPHBState, io_win_addr, -1),
DEFINE_PROP_UINT64("io_win_size", sPAPRPHBState, io_win_size,
SPAPR_PCI_IO_WIN_SIZE),
+ DEFINE_PROP_BOOL("dynamic-reconfiguration", sPAPRPHBState, dr_enabled,
+ true),
DEFINE_PROP_END_OF_LIST(),
};
.name = "spapr_pci/lsi",
.version_id = 1,
.minimum_version_id = 1,
- .minimum_version_id_old = 1,
- .fields = (VMStateField []) {
+ .fields = (VMStateField[]) {
VMSTATE_UINT32_EQUAL(irq, struct spapr_pci_lsi),
VMSTATE_END_OF_LIST()
};
static const VMStateDescription vmstate_spapr_pci_msi = {
- .name = "spapr_pci/lsi",
+ .name = "spapr_pci/msi",
.version_id = 1,
.minimum_version_id = 1,
- .minimum_version_id_old = 1,
- .fields = (VMStateField []) {
- VMSTATE_UINT32(config_addr, struct spapr_pci_msi),
- VMSTATE_UINT32(irq, struct spapr_pci_msi),
- VMSTATE_UINT32(nvec, struct spapr_pci_msi),
-
+ .fields = (VMStateField []) {
+ VMSTATE_UINT32(key, spapr_pci_msi_mig),
+ VMSTATE_UINT32(value.first_irq, spapr_pci_msi_mig),
+ VMSTATE_UINT32(value.num, spapr_pci_msi_mig),
VMSTATE_END_OF_LIST()
},
};
+static void spapr_pci_pre_save(void *opaque)
+{
+ sPAPRPHBState *sphb = opaque;
+ GHashTableIter iter;
+ gpointer key, value;
+ int i;
+
+ g_free(sphb->msi_devs);
+ sphb->msi_devs = NULL;
+ sphb->msi_devs_num = g_hash_table_size(sphb->msi);
+ if (!sphb->msi_devs_num) {
+ return;
+ }
+ sphb->msi_devs = g_malloc(sphb->msi_devs_num * sizeof(spapr_pci_msi_mig));
+
+ g_hash_table_iter_init(&iter, sphb->msi);
+ for (i = 0; g_hash_table_iter_next(&iter, &key, &value); ++i) {
+ sphb->msi_devs[i].key = *(uint32_t *) key;
+ sphb->msi_devs[i].value = *(spapr_pci_msi *) value;
+ }
+}
+
+static int spapr_pci_post_load(void *opaque, int version_id)
+{
+ sPAPRPHBState *sphb = opaque;
+ gpointer key, value;
+ int i;
+
+ for (i = 0; i < sphb->msi_devs_num; ++i) {
+ key = g_memdup(&sphb->msi_devs[i].key,
+ sizeof(sphb->msi_devs[i].key));
+ value = g_memdup(&sphb->msi_devs[i].value,
+ sizeof(sphb->msi_devs[i].value));
+ g_hash_table_insert(sphb->msi, key, value);
+ }
+ g_free(sphb->msi_devs);
+ sphb->msi_devs = NULL;
+ sphb->msi_devs_num = 0;
+
+ return 0;
+}
+
static const VMStateDescription vmstate_spapr_pci = {
.name = "spapr_pci",
- .version_id = 1,
- .minimum_version_id = 1,
- .minimum_version_id_old = 1,
- .fields = (VMStateField []) {
+ .version_id = 2,
+ .minimum_version_id = 2,
+ .pre_save = spapr_pci_pre_save,
+ .post_load = spapr_pci_post_load,
+ .fields = (VMStateField[]) {
VMSTATE_UINT64_EQUAL(buid, sPAPRPHBState),
VMSTATE_UINT32_EQUAL(dma_liobn, sPAPRPHBState),
VMSTATE_UINT64_EQUAL(mem_win_addr, sPAPRPHBState),
VMSTATE_UINT64_EQUAL(io_win_size, sPAPRPHBState),
VMSTATE_STRUCT_ARRAY(lsi_table, sPAPRPHBState, PCI_NUM_PINS, 0,
vmstate_spapr_pci_lsi, struct spapr_pci_lsi),
- VMSTATE_STRUCT_ARRAY(msi_table, sPAPRPHBState, SPAPR_MSIX_MAX_DEVS, 0,
- vmstate_spapr_pci_msi, struct spapr_pci_msi),
-
+ VMSTATE_INT32(msi_devs_num, sPAPRPHBState),
+ VMSTATE_STRUCT_VARRAY_ALLOC(msi_devs, sPAPRPHBState, msi_devs_num, 0,
+ vmstate_spapr_pci_msi, spapr_pci_msi_mig),
VMSTATE_END_OF_LIST()
},
};
{
PCIHostBridgeClass *hc = PCI_HOST_BRIDGE_CLASS(klass);
DeviceClass *dc = DEVICE_CLASS(klass);
+ sPAPRPHBClass *spc = SPAPR_PCI_HOST_BRIDGE_CLASS(klass);
+ HotplugHandlerClass *hp = HOTPLUG_HANDLER_CLASS(klass);
hc->root_bus_path = spapr_phb_root_bus_path;
dc->realize = spapr_phb_realize;
dc->vmsd = &vmstate_spapr_pci;
set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
dc->cannot_instantiate_with_device_add_yet = false;
+ spc->finish_realize = spapr_phb_finish_realize;
+ hp->plug = spapr_phb_hot_plug_child;
+ hp->unplug = spapr_phb_hot_unplug_child;
}
static const TypeInfo spapr_phb_info = {
.parent = TYPE_PCI_HOST_BRIDGE,
.instance_size = sizeof(sPAPRPHBState),
.class_init = spapr_phb_class_init,
+ .class_size = sizeof(sPAPRPHBClass),
+ .interfaces = (InterfaceInfo[]) {
+ { TYPE_HOTPLUG_HANDLER },
+ { }
+ }
};
-PCIHostState *spapr_create_phb(sPAPREnvironment *spapr, int index)
+PCIHostState *spapr_create_phb(sPAPRMachineState *spapr, int index)
{
DeviceState *dev;
return PCI_HOST_BRIDGE(dev);
}
-/* Macros to operate with address in OF binding to PCI */
-#define b_x(x, p, l) (((x) & ((1<<(l))-1)) << (p))
-#define b_n(x) b_x((x), 31, 1) /* 0 if relocatable */
-#define b_p(x) b_x((x), 30, 1) /* 1 if prefetchable */
-#define b_t(x) b_x((x), 29, 1) /* 1 if the address is aliased */
-#define b_ss(x) b_x((x), 24, 2) /* the space code */
-#define b_bbbbbbbb(x) b_x((x), 16, 8) /* bus number */
-#define b_ddddd(x) b_x((x), 11, 5) /* device number */
-#define b_fff(x) b_x((x), 8, 3) /* function number */
-#define b_rrrrrrrr(x) b_x((x), 0, 8) /* register number */
+typedef struct sPAPRFDT {
+ void *fdt;
+ int node_off;
+ sPAPRPHBState *sphb;
+} sPAPRFDT;
+
+static void spapr_populate_pci_devices_dt(PCIBus *bus, PCIDevice *pdev,
+ void *opaque)
+{
+ PCIBus *sec_bus;
+ sPAPRFDT *p = opaque;
+ int offset;
+ sPAPRFDT s_fdt;
+
+ offset = spapr_create_pci_child_dt(p->sphb, pdev, p->fdt, p->node_off);
+ if (!offset) {
+ error_report("Failed to create pci child device tree node");
+ return;
+ }
+
+ if ((pci_default_read_config(pdev, PCI_HEADER_TYPE, 1) !=
+ PCI_HEADER_TYPE_BRIDGE)) {
+ return;
+ }
+
+ sec_bus = pci_bridge_get_sec_bus(PCI_BRIDGE(pdev));
+ if (!sec_bus) {
+ return;
+ }
+
+ s_fdt.fdt = p->fdt;
+ s_fdt.node_off = offset;
+ s_fdt.sphb = p->sphb;
+ pci_for_each_device(sec_bus, pci_bus_num(sec_bus),
+ spapr_populate_pci_devices_dt,
+ &s_fdt);
+}
+
+static void spapr_phb_pci_enumerate_bridge(PCIBus *bus, PCIDevice *pdev,
+ void *opaque)
+{
+ unsigned int *bus_no = opaque;
+ unsigned int primary = *bus_no;
+ unsigned int subordinate = 0xff;
+ PCIBus *sec_bus = NULL;
+
+ if ((pci_default_read_config(pdev, PCI_HEADER_TYPE, 1) !=
+ PCI_HEADER_TYPE_BRIDGE)) {
+ return;
+ }
+
+ (*bus_no)++;
+ pci_default_write_config(pdev, PCI_PRIMARY_BUS, primary, 1);
+ pci_default_write_config(pdev, PCI_SECONDARY_BUS, *bus_no, 1);
+ pci_default_write_config(pdev, PCI_SUBORDINATE_BUS, *bus_no, 1);
+
+ sec_bus = pci_bridge_get_sec_bus(PCI_BRIDGE(pdev));
+ if (!sec_bus) {
+ return;
+ }
+
+ pci_default_write_config(pdev, PCI_SUBORDINATE_BUS, subordinate, 1);
+ pci_for_each_device(sec_bus, pci_bus_num(sec_bus),
+ spapr_phb_pci_enumerate_bridge, bus_no);
+ pci_default_write_config(pdev, PCI_SUBORDINATE_BUS, *bus_no, 1);
+}
+
+static void spapr_phb_pci_enumerate(sPAPRPHBState *phb)
+{
+ PCIBus *bus = PCI_HOST_BRIDGE(phb)->bus;
+ unsigned int bus_no = 0;
+
+ pci_for_each_device(bus, pci_bus_num(bus),
+ spapr_phb_pci_enumerate_bridge,
+ &bus_no);
+
+}
int spapr_populate_pci_dt(sPAPRPHBState *phb,
uint32_t xics_phandle,
void *fdt)
{
- int bus_off, i, j;
- char nodename[256];
+ int bus_off, i, j, ret;
+ char nodename[FDT_NAME_MAX];
uint32_t bus_range[] = { cpu_to_be32(0), cpu_to_be32(0xff) };
+ const uint64_t mmiosize = memory_region_size(&phb->memwindow);
+ const uint64_t w32max = (1ULL << 32) - SPAPR_PCI_MEM_WIN_BUS_OFFSET;
+ const uint64_t w32size = MIN(w32max, mmiosize);
+ const uint64_t w64size = (mmiosize > w32size) ? (mmiosize - w32size) : 0;
struct {
uint32_t hi;
uint64_t child;
{
cpu_to_be32(b_ss(2)), cpu_to_be64(SPAPR_PCI_MEM_WIN_BUS_OFFSET),
cpu_to_be64(phb->mem_win_addr),
- cpu_to_be64(memory_region_size(&phb->memwindow)),
+ cpu_to_be64(w32size),
+ },
+ {
+ cpu_to_be32(b_ss(3)), cpu_to_be64(1ULL << 32),
+ cpu_to_be64(phb->mem_win_addr + w32size),
+ cpu_to_be64(w64size)
},
};
+ const unsigned sizeof_ranges = (w64size ? 3 : 2) * sizeof(ranges[0]);
uint64_t bus_reg[] = { cpu_to_be64(phb->buid), 0 };
uint32_t interrupt_map_mask[] = {
cpu_to_be32(b_ddddd(-1)|b_fff(0)), 0x0, 0x0, cpu_to_be32(-1)};
uint32_t interrupt_map[PCI_SLOT_MAX * PCI_NUM_PINS][7];
+ sPAPRTCETable *tcet;
+ PCIBus *bus = PCI_HOST_BRIDGE(phb)->bus;
+ sPAPRFDT s_fdt;
/* Start populating the FDT */
- sprintf(nodename, "pci@%" PRIx64, phb->buid);
+ snprintf(nodename, FDT_NAME_MAX, "pci@%" PRIx64, phb->buid);
bus_off = fdt_add_subnode(fdt, 0, nodename);
if (bus_off < 0) {
return bus_off;
}
-#define _FDT(exp) \
- do { \
- int ret = (exp); \
- if (ret < 0) { \
- return ret; \
- } \
- } while (0)
-
/* Write PHB properties */
_FDT(fdt_setprop_string(fdt, bus_off, "device_type", "pci"));
_FDT(fdt_setprop_string(fdt, bus_off, "compatible", "IBM,Logical_PHB"));
_FDT(fdt_setprop_cell(fdt, bus_off, "#interrupt-cells", 0x1));
_FDT(fdt_setprop(fdt, bus_off, "used-by-rtas", NULL, 0));
_FDT(fdt_setprop(fdt, bus_off, "bus-range", &bus_range, sizeof(bus_range)));
- _FDT(fdt_setprop(fdt, bus_off, "ranges", &ranges, sizeof(ranges)));
+ _FDT(fdt_setprop(fdt, bus_off, "ranges", &ranges, sizeof_ranges));
_FDT(fdt_setprop(fdt, bus_off, "reg", &bus_reg, sizeof(bus_reg)));
_FDT(fdt_setprop_cell(fdt, bus_off, "ibm,pci-config-space-type", 0x1));
+ _FDT(fdt_setprop_cell(fdt, bus_off, "ibm,pe-total-#msi", XICS_IRQS));
/* Build the interrupt-map, this must matches what is done
* in pci_spapr_map_irq
_FDT(fdt_setprop(fdt, bus_off, "interrupt-map", &interrupt_map,
sizeof(interrupt_map)));
+ tcet = spapr_tce_find_by_liobn(SPAPR_PCI_LIOBN(phb->index, 0));
spapr_dma_dt(fdt, bus_off, "ibm,dma-window",
- phb->dma_liobn, phb->dma_window_start,
- phb->dma_window_size);
+ tcet->liobn, tcet->bus_offset,
+ tcet->nb_table << tcet->page_shift);
+
+ /* Walk the bridges and program the bus numbers*/
+ spapr_phb_pci_enumerate(phb);
+ _FDT(fdt_setprop_cell(fdt, bus_off, "qemu,phb-enumerated", 0x1));
+
+ /* Populate tree nodes with PCI devices attached */
+ s_fdt.fdt = fdt;
+ s_fdt.node_off = bus_off;
+ s_fdt.sphb = phb;
+ pci_for_each_device(bus, pci_bus_num(bus),
+ spapr_populate_pci_devices_dt,
+ &s_fdt);
+
+ ret = spapr_drc_populate_dt(fdt, bus_off, OBJECT(phb),
+ SPAPR_DR_CONNECTOR_TYPE_PCI);
+ if (ret) {
+ return ret;
+ }
return 0;
}
void spapr_pci_rtas_init(void)
{
- spapr_rtas_register("read-pci-config", rtas_read_pci_config);
- 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);
+ spapr_rtas_register(RTAS_READ_PCI_CONFIG, "read-pci-config",
+ rtas_read_pci_config);
+ spapr_rtas_register(RTAS_WRITE_PCI_CONFIG, "write-pci-config",
+ rtas_write_pci_config);
+ spapr_rtas_register(RTAS_IBM_READ_PCI_CONFIG, "ibm,read-pci-config",
+ rtas_ibm_read_pci_config);
+ spapr_rtas_register(RTAS_IBM_WRITE_PCI_CONFIG, "ibm,write-pci-config",
+ rtas_ibm_write_pci_config);
if (msi_supported) {
- spapr_rtas_register("ibm,query-interrupt-source-number",
+ spapr_rtas_register(RTAS_IBM_QUERY_INTERRUPT_SOURCE_NUMBER,
+ "ibm,query-interrupt-source-number",
rtas_ibm_query_interrupt_source_number);
- spapr_rtas_register("ibm,change-msi", rtas_ibm_change_msi);
+ spapr_rtas_register(RTAS_IBM_CHANGE_MSI, "ibm,change-msi",
+ rtas_ibm_change_msi);
}
+
+ spapr_rtas_register(RTAS_IBM_SET_EEH_OPTION,
+ "ibm,set-eeh-option",
+ rtas_ibm_set_eeh_option);
+ spapr_rtas_register(RTAS_IBM_GET_CONFIG_ADDR_INFO2,
+ "ibm,get-config-addr-info2",
+ rtas_ibm_get_config_addr_info2);
+ spapr_rtas_register(RTAS_IBM_READ_SLOT_RESET_STATE2,
+ "ibm,read-slot-reset-state2",
+ rtas_ibm_read_slot_reset_state2);
+ spapr_rtas_register(RTAS_IBM_SET_SLOT_RESET,
+ "ibm,set-slot-reset",
+ rtas_ibm_set_slot_reset);
+ spapr_rtas_register(RTAS_IBM_CONFIGURE_PE,
+ "ibm,configure-pe",
+ rtas_ibm_configure_pe);
+ spapr_rtas_register(RTAS_IBM_SLOT_ERROR_DETAIL,
+ "ibm,slot-error-detail",
+ rtas_ibm_slot_error_detail);
}
static void spapr_pci_register_types(void)
}
type_init(spapr_pci_register_types)
+
+static int spapr_switch_one_vga(DeviceState *dev, void *opaque)
+{
+ bool be = *(bool *)opaque;
+
+ if (object_dynamic_cast(OBJECT(dev), "VGA")
+ || object_dynamic_cast(OBJECT(dev), "secondary-vga")) {
+ object_property_set_bool(OBJECT(dev), be, "big-endian-framebuffer",
+ &error_abort);
+ }
+ return 0;
+}
+
+void spapr_pci_switch_vga(bool big_endian)
+{
+ sPAPRMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
+ sPAPRPHBState *sphb;
+
+ /*
+ * For backward compatibility with existing guests, we switch
+ * the endianness of the VGA controller when changing the guest
+ * interrupt mode
+ */
+ QLIST_FOREACH(sphb, &spapr->phbs, list) {
+ BusState *bus = &PCI_HOST_BRIDGE(sphb)->bus->qbus;
+ qbus_walk_children(bus, spapr_switch_one_vga, NULL, NULL, NULL,
+ &big_endian);
+ }
+}