| Message ID | 20230713084405.24545-6-yongxuan.wang@sifive.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | Add RISC-V KVM AIA Support | expand |
On Thu, Jul 13, 2023 at 08:43:57AM +0000, Yong-Xuan Wang wrote: > Select KVM AIA when the host kernel has in-kernel AIA chip support. > Since KVM AIA only has one APLIC instance, we map the QEMU APLIC > devices to KVM APLIC. > We also extend virt machine to specify the KVM AIA mode. The "kvm-aia" > parameter is passed along with machine name in QEMU command-line. > 1) "kvm-aia=emul": IMSIC is emulated by hypervisor > 2) "kvm-aia=hwaccel": use hardware guest IMSIC > 3) "kvm-aia=auto": use the hardware guest IMSICs whenever available > otherwise we fallback to software emulation. > > Signed-off-by: Yong-Xuan Wang <yongxuan.wang@sifive.com> > Reviewed-by: Jim Shu <jim.shu@sifive.com> > Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com> > --- > hw/riscv/virt.c | 125 ++++++++++++++++++++++++++++++---------- > include/hw/riscv/virt.h | 1 + > 2 files changed, 97 insertions(+), 29 deletions(-) > > diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c > index 26b3aff28e..b74142d978 100644 > --- a/hw/riscv/virt.c > +++ b/hw/riscv/virt.c > @@ -35,6 +35,7 @@ > #include "hw/riscv/virt.h" > #include "hw/riscv/boot.h" > #include "hw/riscv/numa.h" > +#include "kvm_riscv.h" > #include "hw/intc/riscv_aclint.h" > #include "hw/intc/riscv_aplic.h" > #include "hw/intc/riscv_imsic.h" > @@ -75,6 +76,12 @@ > #error "Can't accomodate all IMSIC groups in address space" > #endif > > +/* KVM AIA only supports APLIC MSI. APLIC Wired is always emulated by QEMU. */ > +static bool virt_use_kvm_aia(RISCVVirtState *s) > +{ > + return kvm_irqchip_in_kernel() && s->aia_type == VIRT_AIA_TYPE_APLIC_IMSIC; > +} > + > static const MemMapEntry virt_memmap[] = { > [VIRT_DEBUG] = { 0x0, 0x100 }, > [VIRT_MROM] = { 0x1000, 0xf000 }, > @@ -609,16 +616,16 @@ static void create_fdt_one_aplic(RISCVVirtState *s, int socket, > uint32_t *intc_phandles, > uint32_t aplic_phandle, > uint32_t aplic_child_phandle, > - bool m_mode) > + bool m_mode, int num_harts) > { > int cpu; > char *aplic_name; > uint32_t *aplic_cells; > MachineState *ms = MACHINE(s); > > - aplic_cells = g_new0(uint32_t, s->soc[socket].num_harts * 2); > + aplic_cells = g_new0(uint32_t, num_harts * 2); > > - for (cpu = 0; cpu < s->soc[socket].num_harts; cpu++) { > + for (cpu = 0; cpu < num_harts; cpu++) { > aplic_cells[cpu * 2 + 0] = cpu_to_be32(intc_phandles[cpu]); > aplic_cells[cpu * 2 + 1] = cpu_to_be32(m_mode ? IRQ_M_EXT : IRQ_S_EXT); > } > @@ -632,7 +639,7 @@ static void create_fdt_one_aplic(RISCVVirtState *s, int socket, > > if (s->aia_type == VIRT_AIA_TYPE_APLIC) { > qemu_fdt_setprop(ms->fdt, aplic_name, "interrupts-extended", > - aplic_cells, s->soc[socket].num_harts * sizeof(uint32_t) * 2); > + aplic_cells, num_harts * sizeof(uint32_t) * 2); > } else { > qemu_fdt_setprop_cell(ms->fdt, aplic_name, "msi-parent", msi_phandle); > } > @@ -662,7 +669,8 @@ static void create_fdt_socket_aplic(RISCVVirtState *s, > uint32_t msi_s_phandle, > uint32_t *phandle, > uint32_t *intc_phandles, > - uint32_t *aplic_phandles) > + uint32_t *aplic_phandles, > + int num_harts) > { > char *aplic_name; > unsigned long aplic_addr; > @@ -679,7 +687,7 @@ static void create_fdt_socket_aplic(RISCVVirtState *s, > create_fdt_one_aplic(s, socket, aplic_addr, memmap[VIRT_APLIC_M].size, > msi_m_phandle, intc_phandles, > aplic_m_phandle, aplic_s_phandle, > - true); > + true, num_harts); > } > > /* S-level APLIC node */ > @@ -688,7 +696,7 @@ static void create_fdt_socket_aplic(RISCVVirtState *s, > create_fdt_one_aplic(s, socket, aplic_addr, memmap[VIRT_APLIC_S].size, > msi_s_phandle, intc_phandles, > aplic_s_phandle, 0, > - false); > + false, num_harts); > > aplic_name = g_strdup_printf("/soc/aplic@%lx", aplic_addr); > > @@ -772,34 +780,48 @@ static void create_fdt_sockets(RISCVVirtState *s, const MemMapEntry *memmap, > *msi_pcie_phandle = msi_s_phandle; > } > > - phandle_pos = ms->smp.cpus; > - for (socket = (socket_count - 1); socket >= 0; socket--) { > - phandle_pos -= s->soc[socket].num_harts; > + /* KVM AIA only has one APLIC instance */ > + if (virt_use_kvm_aia(s)) { > + create_fdt_socket_aplic(s, memmap, 0, > + msi_m_phandle, msi_s_phandle, phandle, > + &intc_phandles[0], xplic_phandles, ms->smp.cpus); > + } else { > + phandle_pos = ms->smp.cpus; > + for (socket = (socket_count - 1); socket >= 0; socket--) { > + phandle_pos -= s->soc[socket].num_harts; > > - if (s->aia_type == VIRT_AIA_TYPE_NONE) { > - create_fdt_socket_plic(s, memmap, socket, phandle, > - &intc_phandles[phandle_pos], xplic_phandles); > - } else { > - create_fdt_socket_aplic(s, memmap, socket, > - msi_m_phandle, msi_s_phandle, phandle, > - &intc_phandles[phandle_pos], xplic_phandles); > + if (s->aia_type == VIRT_AIA_TYPE_NONE) { > + create_fdt_socket_plic(s, memmap, socket, phandle, > + &intc_phandles[phandle_pos], xplic_phandles); > + } else { > + create_fdt_socket_aplic(s, memmap, socket, > + msi_m_phandle, msi_s_phandle, phandle, > + &intc_phandles[phandle_pos], xplic_phandles, > + s->soc[socket].num_harts); > + } > } > } > > g_free(intc_phandles); > > - for (socket = 0; socket < socket_count; socket++) { > - if (socket == 0) { > - *irq_mmio_phandle = xplic_phandles[socket]; > - *irq_virtio_phandle = xplic_phandles[socket]; > - *irq_pcie_phandle = xplic_phandles[socket]; > - } > - if (socket == 1) { > - *irq_virtio_phandle = xplic_phandles[socket]; > - *irq_pcie_phandle = xplic_phandles[socket]; > - } > - if (socket == 2) { > - *irq_pcie_phandle = xplic_phandles[socket]; > + if (virt_use_kvm_aia(s)) { > + *irq_mmio_phandle = xplic_phandles[0]; > + *irq_virtio_phandle = xplic_phandles[0]; > + *irq_pcie_phandle = xplic_phandles[0]; > + } else { > + for (socket = 0; socket < socket_count; socket++) { > + if (socket == 0) { > + *irq_mmio_phandle = xplic_phandles[socket]; > + *irq_virtio_phandle = xplic_phandles[socket]; > + *irq_pcie_phandle = xplic_phandles[socket]; > + } > + if (socket == 1) { > + *irq_virtio_phandle = xplic_phandles[socket]; > + *irq_pcie_phandle = xplic_phandles[socket]; > + } > + if (socket == 2) { > + *irq_pcie_phandle = xplic_phandles[socket]; > + } > } > } > > @@ -1430,6 +1452,14 @@ static void virt_machine_init(MachineState *machine) > } > } > > + if (virt_use_kvm_aia(s)) { > + kvm_riscv_aia_create( > + machine, s->kvm_aia_mode, IMSIC_MMIO_GROUP_MIN_SHIFT, > + VIRT_IRQCHIP_NUM_SOURCES, VIRT_IRQCHIP_NUM_MSIS, > + memmap[VIRT_APLIC_S].base, memmap[VIRT_IMSIC_S].base, > + s->aia_guests); > + } > + > if (riscv_is_32bit(&s->soc[0])) { > #if HOST_LONG_BITS == 64 > /* limit RAM size in a 32-bit system */ > @@ -1575,6 +1605,31 @@ static void virt_set_aia(Object *obj, const char *val, Error **errp) > } > } > > +#if defined(CONFIG_KVM) > +static char *virt_get_kvm_aia(Object *obj, Error **errp) > +{ > + RISCVVirtState *s = RISCV_VIRT_MACHINE(obj); > + > + return g_strdup(kvm_aia_mode_str(s->kvm_aia_mode)); > +} > + > +static void virt_set_kvm_aia(Object *obj, const char *val, Error **errp) > +{ > + RISCVVirtState *s = RISCV_VIRT_MACHINE(obj); > + > + if (!strcmp(val, "emul")) { > + s->kvm_aia_mode = KVM_DEV_RISCV_AIA_MODE_EMUL; > + } else if (!strcmp(val, "hwaccel")) { > + s->kvm_aia_mode = KVM_DEV_RISCV_AIA_MODE_HWACCEL; > + } else if (!strcmp(val, "auto")) { > + s->kvm_aia_mode = KVM_DEV_RISCV_AIA_MODE_AUTO; > + } else { > + error_setg(errp, "Invalid KVM AIA mode"); > + error_append_hint(errp, "Valid values are emul, hwaccel, and auto.\n"); > + } > +} > +#endif > + > static bool virt_get_aclint(Object *obj, Error **errp) > { > RISCVVirtState *s = RISCV_VIRT_MACHINE(obj); > @@ -1685,6 +1740,18 @@ static void virt_machine_class_init(ObjectClass *oc, void *data) > sprintf(str, "Set number of guest MMIO pages for AIA IMSIC. Valid value " > "should be between 0 and %d.", VIRT_IRQCHIP_MAX_GUESTS); > object_class_property_set_description(oc, "aia-guests", str); > + > +#if defined(CONFIG_KVM) > + object_class_property_add_str(oc, "kvm-aia", virt_get_kvm_aia, > + virt_set_kvm_aia); > + object_class_property_set_description(oc, "kvm-aia", > + "Set KVM AIA mode. Valid values are " > + "emul, hwaccel, and auto. Default " > + "is auto."); > + object_property_set_default_str(object_class_property_find(oc, "kvm-aia"), > + "auto"); > + > +#endif > object_class_property_add(oc, "acpi", "OnOffAuto", > virt_get_acpi, virt_set_acpi, > NULL, NULL); > diff --git a/include/hw/riscv/virt.h b/include/hw/riscv/virt.h > index e5c474b26e..d0140feeff 100644 > --- a/include/hw/riscv/virt.h > +++ b/include/hw/riscv/virt.h > @@ -56,6 +56,7 @@ struct RISCVVirtState { > bool have_aclint; > RISCVVirtAIAType aia_type; > int aia_guests; > + uint64_t kvm_aia_mode; > char *oem_id; > char *oem_table_id; > OnOffAuto acpi; > -- > 2.17.1 > Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c index 26b3aff28e..b74142d978 100644 --- a/hw/riscv/virt.c +++ b/hw/riscv/virt.c @@ -35,6 +35,7 @@ #include "hw/riscv/virt.h" #include "hw/riscv/boot.h" #include "hw/riscv/numa.h" +#include "kvm_riscv.h" #include "hw/intc/riscv_aclint.h" #include "hw/intc/riscv_aplic.h" #include "hw/intc/riscv_imsic.h" @@ -75,6 +76,12 @@ #error "Can't accomodate all IMSIC groups in address space" #endif +/* KVM AIA only supports APLIC MSI. APLIC Wired is always emulated by QEMU. */ +static bool virt_use_kvm_aia(RISCVVirtState *s) +{ + return kvm_irqchip_in_kernel() && s->aia_type == VIRT_AIA_TYPE_APLIC_IMSIC; +} + static const MemMapEntry virt_memmap[] = { [VIRT_DEBUG] = { 0x0, 0x100 }, [VIRT_MROM] = { 0x1000, 0xf000 }, @@ -609,16 +616,16 @@ static void create_fdt_one_aplic(RISCVVirtState *s, int socket, uint32_t *intc_phandles, uint32_t aplic_phandle, uint32_t aplic_child_phandle, - bool m_mode) + bool m_mode, int num_harts) { int cpu; char *aplic_name; uint32_t *aplic_cells; MachineState *ms = MACHINE(s); - aplic_cells = g_new0(uint32_t, s->soc[socket].num_harts * 2); + aplic_cells = g_new0(uint32_t, num_harts * 2); - for (cpu = 0; cpu < s->soc[socket].num_harts; cpu++) { + for (cpu = 0; cpu < num_harts; cpu++) { aplic_cells[cpu * 2 + 0] = cpu_to_be32(intc_phandles[cpu]); aplic_cells[cpu * 2 + 1] = cpu_to_be32(m_mode ? IRQ_M_EXT : IRQ_S_EXT); } @@ -632,7 +639,7 @@ static void create_fdt_one_aplic(RISCVVirtState *s, int socket, if (s->aia_type == VIRT_AIA_TYPE_APLIC) { qemu_fdt_setprop(ms->fdt, aplic_name, "interrupts-extended", - aplic_cells, s->soc[socket].num_harts * sizeof(uint32_t) * 2); + aplic_cells, num_harts * sizeof(uint32_t) * 2); } else { qemu_fdt_setprop_cell(ms->fdt, aplic_name, "msi-parent", msi_phandle); } @@ -662,7 +669,8 @@ static void create_fdt_socket_aplic(RISCVVirtState *s, uint32_t msi_s_phandle, uint32_t *phandle, uint32_t *intc_phandles, - uint32_t *aplic_phandles) + uint32_t *aplic_phandles, + int num_harts) { char *aplic_name; unsigned long aplic_addr; @@ -679,7 +687,7 @@ static void create_fdt_socket_aplic(RISCVVirtState *s, create_fdt_one_aplic(s, socket, aplic_addr, memmap[VIRT_APLIC_M].size, msi_m_phandle, intc_phandles, aplic_m_phandle, aplic_s_phandle, - true); + true, num_harts); } /* S-level APLIC node */ @@ -688,7 +696,7 @@ static void create_fdt_socket_aplic(RISCVVirtState *s, create_fdt_one_aplic(s, socket, aplic_addr, memmap[VIRT_APLIC_S].size, msi_s_phandle, intc_phandles, aplic_s_phandle, 0, - false); + false, num_harts); aplic_name = g_strdup_printf("/soc/aplic@%lx", aplic_addr); @@ -772,34 +780,48 @@ static void create_fdt_sockets(RISCVVirtState *s, const MemMapEntry *memmap, *msi_pcie_phandle = msi_s_phandle; } - phandle_pos = ms->smp.cpus; - for (socket = (socket_count - 1); socket >= 0; socket--) { - phandle_pos -= s->soc[socket].num_harts; + /* KVM AIA only has one APLIC instance */ + if (virt_use_kvm_aia(s)) { + create_fdt_socket_aplic(s, memmap, 0, + msi_m_phandle, msi_s_phandle, phandle, + &intc_phandles[0], xplic_phandles, ms->smp.cpus); + } else { + phandle_pos = ms->smp.cpus; + for (socket = (socket_count - 1); socket >= 0; socket--) { + phandle_pos -= s->soc[socket].num_harts; - if (s->aia_type == VIRT_AIA_TYPE_NONE) { - create_fdt_socket_plic(s, memmap, socket, phandle, - &intc_phandles[phandle_pos], xplic_phandles); - } else { - create_fdt_socket_aplic(s, memmap, socket, - msi_m_phandle, msi_s_phandle, phandle, - &intc_phandles[phandle_pos], xplic_phandles); + if (s->aia_type == VIRT_AIA_TYPE_NONE) { + create_fdt_socket_plic(s, memmap, socket, phandle, + &intc_phandles[phandle_pos], xplic_phandles); + } else { + create_fdt_socket_aplic(s, memmap, socket, + msi_m_phandle, msi_s_phandle, phandle, + &intc_phandles[phandle_pos], xplic_phandles, + s->soc[socket].num_harts); + } } } g_free(intc_phandles); - for (socket = 0; socket < socket_count; socket++) { - if (socket == 0) { - *irq_mmio_phandle = xplic_phandles[socket]; - *irq_virtio_phandle = xplic_phandles[socket]; - *irq_pcie_phandle = xplic_phandles[socket]; - } - if (socket == 1) { - *irq_virtio_phandle = xplic_phandles[socket]; - *irq_pcie_phandle = xplic_phandles[socket]; - } - if (socket == 2) { - *irq_pcie_phandle = xplic_phandles[socket]; + if (virt_use_kvm_aia(s)) { + *irq_mmio_phandle = xplic_phandles[0]; + *irq_virtio_phandle = xplic_phandles[0]; + *irq_pcie_phandle = xplic_phandles[0]; + } else { + for (socket = 0; socket < socket_count; socket++) { + if (socket == 0) { + *irq_mmio_phandle = xplic_phandles[socket]; + *irq_virtio_phandle = xplic_phandles[socket]; + *irq_pcie_phandle = xplic_phandles[socket]; + } + if (socket == 1) { + *irq_virtio_phandle = xplic_phandles[socket]; + *irq_pcie_phandle = xplic_phandles[socket]; + } + if (socket == 2) { + *irq_pcie_phandle = xplic_phandles[socket]; + } } } @@ -1430,6 +1452,14 @@ static void virt_machine_init(MachineState *machine) } } + if (virt_use_kvm_aia(s)) { + kvm_riscv_aia_create( + machine, s->kvm_aia_mode, IMSIC_MMIO_GROUP_MIN_SHIFT, + VIRT_IRQCHIP_NUM_SOURCES, VIRT_IRQCHIP_NUM_MSIS, + memmap[VIRT_APLIC_S].base, memmap[VIRT_IMSIC_S].base, + s->aia_guests); + } + if (riscv_is_32bit(&s->soc[0])) { #if HOST_LONG_BITS == 64 /* limit RAM size in a 32-bit system */ @@ -1575,6 +1605,31 @@ static void virt_set_aia(Object *obj, const char *val, Error **errp) } } +#if defined(CONFIG_KVM) +static char *virt_get_kvm_aia(Object *obj, Error **errp) +{ + RISCVVirtState *s = RISCV_VIRT_MACHINE(obj); + + return g_strdup(kvm_aia_mode_str(s->kvm_aia_mode)); +} + +static void virt_set_kvm_aia(Object *obj, const char *val, Error **errp) +{ + RISCVVirtState *s = RISCV_VIRT_MACHINE(obj); + + if (!strcmp(val, "emul")) { + s->kvm_aia_mode = KVM_DEV_RISCV_AIA_MODE_EMUL; + } else if (!strcmp(val, "hwaccel")) { + s->kvm_aia_mode = KVM_DEV_RISCV_AIA_MODE_HWACCEL; + } else if (!strcmp(val, "auto")) { + s->kvm_aia_mode = KVM_DEV_RISCV_AIA_MODE_AUTO; + } else { + error_setg(errp, "Invalid KVM AIA mode"); + error_append_hint(errp, "Valid values are emul, hwaccel, and auto.\n"); + } +} +#endif + static bool virt_get_aclint(Object *obj, Error **errp) { RISCVVirtState *s = RISCV_VIRT_MACHINE(obj); @@ -1685,6 +1740,18 @@ static void virt_machine_class_init(ObjectClass *oc, void *data) sprintf(str, "Set number of guest MMIO pages for AIA IMSIC. Valid value " "should be between 0 and %d.", VIRT_IRQCHIP_MAX_GUESTS); object_class_property_set_description(oc, "aia-guests", str); + +#if defined(CONFIG_KVM) + object_class_property_add_str(oc, "kvm-aia", virt_get_kvm_aia, + virt_set_kvm_aia); + object_class_property_set_description(oc, "kvm-aia", + "Set KVM AIA mode. Valid values are " + "emul, hwaccel, and auto. Default " + "is auto."); + object_property_set_default_str(object_class_property_find(oc, "kvm-aia"), + "auto"); + +#endif object_class_property_add(oc, "acpi", "OnOffAuto", virt_get_acpi, virt_set_acpi, NULL, NULL); diff --git a/include/hw/riscv/virt.h b/include/hw/riscv/virt.h index e5c474b26e..d0140feeff 100644 --- a/include/hw/riscv/virt.h +++ b/include/hw/riscv/virt.h @@ -56,6 +56,7 @@ struct RISCVVirtState { bool have_aclint; RISCVVirtAIAType aia_type; int aia_guests; + uint64_t kvm_aia_mode; char *oem_id; char *oem_table_id; OnOffAuto acpi;
Select KVM AIA when the host kernel has in-kernel AIA chip support. Since KVM AIA only has one APLIC instance, we map the QEMU APLIC devices to KVM APLIC. We also extend virt machine to specify the KVM AIA mode. The "kvm-aia" parameter is passed along with machine name in QEMU command-line. 1) "kvm-aia=emul": IMSIC is emulated by hypervisor 2) "kvm-aia=hwaccel": use hardware guest IMSIC 3) "kvm-aia=auto": use the hardware guest IMSICs whenever available otherwise we fallback to software emulation. Signed-off-by: Yong-Xuan Wang <yongxuan.wang@sifive.com> Reviewed-by: Jim Shu <jim.shu@sifive.com> Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com> --- hw/riscv/virt.c | 125 ++++++++++++++++++++++++++++++---------- include/hw/riscv/virt.h | 1 + 2 files changed, 97 insertions(+), 29 deletions(-)