@@ -128,6 +128,8 @@ ifeq ($(uname_M), ppc64)
OBJS += powerpc/irq.o
OBJS += powerpc/kvm.o
OBJS += powerpc/kvm-cpu.o
+ OBJS += powerpc/spapr_hcall.o
+ OBJS += powerpc/spapr_rtas.o
ARCH_INCLUDE := powerpc/include
CFLAGS += -m64
LIBS += -lfdt
@@ -14,6 +14,8 @@
#include "kvm/util.h"
#include "kvm/kvm.h"
+#include "spapr.h"
+
#include <sys/ioctl.h>
#include <sys/mman.h>
#include <signal.h>
@@ -156,6 +158,9 @@ bool kvm_cpu__handle_exit(struct kvm_cpu *vcpu)
bool ret = true;
struct kvm_run *run = vcpu->kvm_run;
switch(run->exit_reason) {
+ case KVM_EXIT_PAPR_HCALL:
+ run->papr_hcall.ret = spapr_hypercall(vcpu, run->papr_hcall.nr, run->papr_hcall.args);
+ break;
default:
ret = false;
}
@@ -14,6 +14,8 @@
#include "kvm/kvm.h"
#include "kvm/util.h"
+#include "spapr.h"
+
#include <linux/kvm.h>
#include <sys/types.h>
@@ -153,6 +155,10 @@ void kvm__arch_init(struct kvm *kvm, const char *kvm_dev, const char *hugetlbfs_
cap_ppc_rma = ioctl(kvm->sys_fd, KVM_CHECK_EXTENSION, KVM_CAP_PPC_RMA);
if (cap_ppc_rma == 2)
die("Need contiguous RMA allocation on this hardware, which is not yet supported.");
+
+ /* Do these before FDT setup, IRQ setup, etc. */
+ hypercall_init();
+ register_core_rtas();
}
void kvm__irq_line(struct kvm *kvm, int irq, int level)
@@ -262,6 +268,20 @@ static void setup_fdt(struct kvm *kvm)
_FDT(fdt_property_cell(fdt, "#address-cells", 0x2));
_FDT(fdt_property_cell(fdt, "#size-cells", 0x2));
+ /* RTAS */
+ _FDT(fdt_begin_node(fdt, "rtas"));
+ /* This is what the kernel uses to switch 'We're an LPAR'! */
+ _FDT(fdt_property(fdt, "ibm,hypertas-functions", hypertas_prop_kvm,
+ sizeof(hypertas_prop_kvm)));
+ _FDT(fdt_property_cell(fdt, "linux,rtas-base", kvm->rtas_gra));
+ _FDT(fdt_property_cell(fdt, "linux,rtas-entry", kvm->rtas_gra));
+ _FDT(fdt_property_cell(fdt, "rtas-size", kvm->rtas_size));
+ /* Now add properties for all RTAS tokens: */
+ if (spapr_rtas_fdt_setup(kvm, fdt))
+ die("Couldn't create RTAS FDT properties\n");
+
+ _FDT(fdt_end_node(fdt));
+
/* /chosen */
_FDT(fdt_begin_node(fdt, "chosen"));
/* cmdline */
@@ -363,7 +383,24 @@ static void setup_fdt(struct kvm *kvm)
*/
void kvm__arch_setup_firmware(struct kvm *kvm)
{
- /* Load RTAS */
+ /* Set up RTAS stub. All it is is a single hypercall:
+ 0: 7c 64 1b 78 mr r4,r3
+ 4: 3c 60 00 00 lis r3,0
+ 8: 60 63 f0 00 ori r3,r3,61440
+ c: 44 00 00 22 sc 1
+ 10: 4e 80 00 20 blr
+ */
+ uint32_t *rtas = guest_flat_to_host(kvm, kvm->rtas_gra);
+
+ rtas[0] = 0x7c641b78;
+ rtas[1] = 0x3c600000;
+ rtas[2] = 0x6063f000;
+ rtas[3] = 0x44000022;
+ rtas[4] = 0x4e800020;
+ kvm->rtas_size = 20;
+
+ pr_info("Set up %ld bytes of RTAS at 0x%lx\n",
+ kvm->rtas_size, kvm->rtas_gra);
/* Load SLOF */
new file mode 100644
@@ -0,0 +1,308 @@
+/*
+ * SPAPR definitions and declarations
+ *
+ * Borrowed heavily from QEMU's spapr.h,
+ * Copyright (c) 2010 David Gibson, IBM Corporation.
+ *
+ * Modifications by Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#if !defined(__HW_SPAPR_H__)
+#define __HW_SPAPR_H__
+
+#include <inttypes.h>
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+
+typedef unsigned long target_ulong;
+typedef uintptr_t target_phys_addr_t;
+
+
+#define H_SUCCESS 0
+#define H_BUSY 1 /* Hardware busy -- retry later */
+#define H_CLOSED 2 /* Resource closed */
+#define H_NOT_AVAILABLE 3
+#define H_CONSTRAINED 4 /* Resource request constrained to max allowed */
+#define H_PARTIAL 5
+#define H_IN_PROGRESS 14 /* Kind of like busy */
+#define H_PAGE_REGISTERED 15
+#define H_PARTIAL_STORE 16
+#define H_PENDING 17 /* returned from H_POLL_PENDING */
+#define H_CONTINUE 18 /* Returned from H_Join on success */
+#define H_LONG_BUSY_START_RANGE 9900 /* Start of long busy range */
+#define H_LONG_BUSY_ORDER_1_MSEC 9900 /* Long busy, hint that 1msec \
+ is a good time to retry */
+#define H_LONG_BUSY_ORDER_10_MSEC 9901 /* Long busy, hint that 10msec \
+ is a good time to retry */
+#define H_LONG_BUSY_ORDER_100_MSEC 9902 /* Long busy, hint that 100msec \
+ is a good time to retry */
+#define H_LONG_BUSY_ORDER_1_SEC 9903 /* Long busy, hint that 1sec \
+ is a good time to retry */
+#define H_LONG_BUSY_ORDER_10_SEC 9904 /* Long busy, hint that 10sec \
+ is a good time to retry */
+#define H_LONG_BUSY_ORDER_100_SEC 9905 /* Long busy, hint that 100sec \
+ is a good time to retry */
+#define H_LONG_BUSY_END_RANGE 9905 /* End of long busy range */
+#define H_HARDWARE -1 /* Hardware error */
+#define H_FUNCTION -2 /* Function not supported */
+#define H_PRIVILEGE -3 /* Caller not privileged */
+#define H_PARAMETER -4 /* Parameter invalid, out-of-range or conflicting */
+#define H_BAD_MODE -5 /* Illegal msr value */
+#define H_PTEG_FULL -6 /* PTEG is full */
+#define H_NOT_FOUND -7 /* PTE was not found" */
+#define H_RESERVED_DABR -8 /* DABR address is reserved by the hypervisor on this processor" */
+#define H_NO_MEM -9
+#define H_AUTHORITY -10
+#define H_PERMISSION -11
+#define H_DROPPED -12
+#define H_SOURCE_PARM -13
+#define H_DEST_PARM -14
+#define H_REMOTE_PARM -15
+#define H_RESOURCE -16
+#define H_ADAPTER_PARM -17
+#define H_RH_PARM -18
+#define H_RCQ_PARM -19
+#define H_SCQ_PARM -20
+#define H_EQ_PARM -21
+#define H_RT_PARM -22
+#define H_ST_PARM -23
+#define H_SIGT_PARM -24
+#define H_TOKEN_PARM -25
+#define H_MLENGTH_PARM -27
+#define H_MEM_PARM -28
+#define H_MEM_ACCESS_PARM -29
+#define H_ATTR_PARM -30
+#define H_PORT_PARM -31
+#define H_MCG_PARM -32
+#define H_VL_PARM -33
+#define H_TSIZE_PARM -34
+#define H_TRACE_PARM -35
+
+#define H_MASK_PARM -37
+#define H_MCG_FULL -38
+#define H_ALIAS_EXIST -39
+#define H_P_COUNTER -40
+#define H_TABLE_FULL -41
+#define H_ALT_TABLE -42
+#define H_MR_CONDITION -43
+#define H_NOT_ENOUGH_RESOURCES -44
+#define H_R_STATE -45
+#define H_RESCINDEND -46
+#define H_MULTI_THREADS_ACTIVE -9005
+
+
+/* Long Busy is a condition that can be returned by the firmware
+ * when a call cannot be completed now, but the identical call
+ * should be retried later. This prevents calls blocking in the
+ * firmware for long periods of time. Annoyingly the firmware can return
+ * a range of return codes, hinting at how long we should wait before
+ * retrying. If you don't care for the hint, the macro below is a good
+ * way to check for the long_busy return codes
+ */
+#define H_IS_LONG_BUSY(x) ((x >= H_LONG_BUSY_START_RANGE) \
+ && (x <= H_LONG_BUSY_END_RANGE))
+
+/* Flags */
+#define H_LARGE_PAGE (1ULL<<(63-16))
+#define H_EXACT (1ULL<<(63-24)) /* Use exact PTE or return H_PTEG_FULL */
+#define H_R_XLATE (1ULL<<(63-25)) /* include a valid logical page num in the pte if the valid bit is set */
+#define H_READ_4 (1ULL<<(63-26)) /* Return 4 PTEs */
+#define H_PAGE_STATE_CHANGE (1ULL<<(63-28))
+#define H_PAGE_UNUSED ((1ULL<<(63-29)) | (1ULL<<(63-30)))
+#define H_PAGE_SET_UNUSED (H_PAGE_STATE_CHANGE | H_PAGE_UNUSED)
+#define H_PAGE_SET_LOANED (H_PAGE_SET_UNUSED | (1ULL<<(63-31)))
+#define H_PAGE_SET_ACTIVE H_PAGE_STATE_CHANGE
+#define H_AVPN (1ULL<<(63-32)) /* An avpn is provided as a sanity test */
+#define H_ANDCOND (1ULL<<(63-33))
+#define H_ICACHE_INVALIDATE (1ULL<<(63-40)) /* icbi, etc. (ignored for IO pages) */
+#define H_ICACHE_SYNCHRONIZE (1ULL<<(63-41)) /* dcbst, icbi, etc (ignored for IO pages */
+#define H_ZERO_PAGE (1ULL<<(63-48)) /* zero the page before mapping (ignored for IO pages) */
+#define H_COPY_PAGE (1ULL<<(63-49))
+#define H_N (1ULL<<(63-61))
+#define H_PP1 (1ULL<<(63-62))
+#define H_PP2 (1ULL<<(63-63))
+
+/* VASI States */
+#define H_VASI_INVALID 0
+#define H_VASI_ENABLED 1
+#define H_VASI_ABORTED 2
+#define H_VASI_SUSPENDING 3
+#define H_VASI_SUSPENDED 4
+#define H_VASI_RESUMED 5
+#define H_VASI_COMPLETED 6
+
+/* DABRX flags */
+#define H_DABRX_HYPERVISOR (1ULL<<(63-61))
+#define H_DABRX_KERNEL (1ULL<<(63-62))
+#define H_DABRX_USER (1ULL<<(63-63))
+
+/* Each control block has to be on a 4K bondary */
+#define H_CB_ALIGNMENT 4096
+
+/* pSeries hypervisor opcodes */
+#define H_REMOVE 0x04
+#define H_ENTER 0x08
+#define H_READ 0x0c
+#define H_CLEAR_MOD 0x10
+#define H_CLEAR_REF 0x14
+#define H_PROTECT 0x18
+#define H_GET_TCE 0x1c
+#define H_PUT_TCE 0x20
+#define H_SET_SPRG0 0x24
+#define H_SET_DABR 0x28
+#define H_PAGE_INIT 0x2c
+#define H_SET_ASR 0x30
+#define H_ASR_ON 0x34
+#define H_ASR_OFF 0x38
+#define H_LOGICAL_CI_LOAD 0x3c
+#define H_LOGICAL_CI_STORE 0x40
+#define H_LOGICAL_CACHE_LOAD 0x44
+#define H_LOGICAL_CACHE_STORE 0x48
+#define H_LOGICAL_ICBI 0x4c
+#define H_LOGICAL_DCBF 0x50
+#define H_GET_TERM_CHAR 0x54
+#define H_PUT_TERM_CHAR 0x58
+#define H_REAL_TO_LOGICAL 0x5c
+#define H_HYPERVISOR_DATA 0x60
+#define H_EOI 0x64
+#define H_CPPR 0x68
+#define H_IPI 0x6c
+#define H_IPOLL 0x70
+#define H_XIRR 0x74
+#define H_PERFMON 0x7c
+#define H_MIGRATE_DMA 0x78
+#define H_REGISTER_VPA 0xDC
+#define H_CEDE 0xE0
+#define H_CONFER 0xE4
+#define H_PROD 0xE8
+#define H_GET_PPP 0xEC
+#define H_SET_PPP 0xF0
+#define H_PURR 0xF4
+#define H_PIC 0xF8
+#define H_REG_CRQ 0xFC
+#define H_FREE_CRQ 0x100
+#define H_VIO_SIGNAL 0x104
+#define H_SEND_CRQ 0x108
+#define H_COPY_RDMA 0x110
+#define H_REGISTER_LOGICAL_LAN 0x114
+#define H_FREE_LOGICAL_LAN 0x118
+#define H_ADD_LOGICAL_LAN_BUFFER 0x11C
+#define H_SEND_LOGICAL_LAN 0x120
+#define H_BULK_REMOVE 0x124
+#define H_MULTICAST_CTRL 0x130
+#define H_SET_XDABR 0x134
+#define H_STUFF_TCE 0x138
+#define H_PUT_TCE_INDIRECT 0x13C
+#define H_CHANGE_LOGICAL_LAN_MAC 0x14C
+#define H_VTERM_PARTNER_INFO 0x150
+#define H_REGISTER_VTERM 0x154
+#define H_FREE_VTERM 0x158
+#define H_RESET_EVENTS 0x15C
+#define H_ALLOC_RESOURCE 0x160
+#define H_FREE_RESOURCE 0x164
+#define H_MODIFY_QP 0x168
+#define H_QUERY_QP 0x16C
+#define H_REREGISTER_PMR 0x170
+#define H_REGISTER_SMR 0x174
+#define H_QUERY_MR 0x178
+#define H_QUERY_MW 0x17C
+#define H_QUERY_HCA 0x180
+#define H_QUERY_PORT 0x184
+#define H_MODIFY_PORT 0x188
+#define H_DEFINE_AQP1 0x18C
+#define H_GET_TRACE_BUFFER 0x190
+#define H_DEFINE_AQP0 0x194
+#define H_RESIZE_MR 0x198
+#define H_ATTACH_MCQP 0x19C
+#define H_DETACH_MCQP 0x1A0
+#define H_CREATE_RPT 0x1A4
+#define H_REMOVE_RPT 0x1A8
+#define H_REGISTER_RPAGES 0x1AC
+#define H_DISABLE_AND_GETC 0x1B0
+#define H_ERROR_DATA 0x1B4
+#define H_GET_HCA_INFO 0x1B8
+#define H_GET_PERF_COUNT 0x1BC
+#define H_MANAGE_TRACE 0x1C0
+#define H_FREE_LOGICAL_LAN_BUFFER 0x1D4
+#define H_QUERY_INT_STATE 0x1E4
+#define H_POLL_PENDING 0x1D8
+#define H_ILLAN_ATTRIBUTES 0x244
+#define H_MODIFY_HEA_QP 0x250
+#define H_QUERY_HEA_QP 0x254
+#define H_QUERY_HEA 0x258
+#define H_QUERY_HEA_PORT 0x25C
+#define H_MODIFY_HEA_PORT 0x260
+#define H_REG_BCMC 0x264
+#define H_DEREG_BCMC 0x268
+#define H_REGISTER_HEA_RPAGES 0x26C
+#define H_DISABLE_AND_GET_HEA 0x270
+#define H_GET_HEA_INFO 0x274
+#define H_ALLOC_HEA_RESOURCE 0x278
+#define H_ADD_CONN 0x284
+#define H_DEL_CONN 0x288
+#define H_JOIN 0x298
+#define H_VASI_STATE 0x2A4
+#define H_ENABLE_CRQ 0x2B0
+#define H_GET_EM_PARMS 0x2B8
+#define H_SET_MPP 0x2D0
+#define H_GET_MPP 0x2D4
+#define MAX_HCALL_OPCODE H_GET_MPP
+
+/* The hcalls above are standardized in PAPR and implemented by pHyp
+ * as well.
+ *
+ * We also need some hcalls which are specific to qemu / KVM-on-POWER.
+ * So far we just need one for H_RTAS, but in future we'll need more
+ * for extensions like virtio. We put those into the 0xf000-0xfffc
+ * range which is reserved by PAPR for "platform-specific" hcalls.
+ */
+#define KVMPPC_HCALL_BASE 0xf000
+#define KVMPPC_H_RTAS (KVMPPC_HCALL_BASE + 0x0)
+#define KVMPPC_HCALL_MAX KVMPPC_H_RTAS
+
+#define DEBUG_SPAPR_HCALLS
+
+#ifdef DEBUG_SPAPR_HCALLS
+#define hcall_dprintf(fmt, ...) \
+ do { fprintf(stderr, fmt, ## __VA_ARGS__); } while (0)
+#else
+#define hcall_dprintf(fmt, ...) \
+ do { } while (0)
+#endif
+
+typedef target_ulong (*spapr_hcall_fn)(struct kvm_cpu *vcpu,
+ target_ulong opcode,
+ target_ulong *args);
+
+void hypercall_init(void);
+void register_core_rtas(void);
+
+void spapr_register_hypercall(target_ulong opcode, spapr_hcall_fn fn);
+target_ulong spapr_hypercall(struct kvm_cpu *vcpu, target_ulong opcode,
+ target_ulong *args);
+
+int spapr_rtas_fdt_setup(struct kvm *kvm, void *fdt);
+
+static inline uint32_t rtas_ld(struct kvm *kvm, target_ulong phys, int n)
+{
+ return *((uint32_t *)guest_flat_to_host(kvm, phys + 4*n));
+}
+
+static inline void rtas_st(struct kvm *kvm, target_ulong phys, int n, uint32_t val)
+{
+ *((uint32_t *)guest_flat_to_host(kvm, phys + 4*n)) = val;
+}
+
+typedef void (*spapr_rtas_fn)(struct kvm_cpu *vcpu, uint32_t token,
+ uint32_t nargs, target_ulong args,
+ uint32_t nret, target_ulong rets);
+void spapr_rtas_register(const char *name, spapr_rtas_fn fn);
+target_ulong spapr_rtas_call(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs, target_ulong args,
+ uint32_t nret, target_ulong rets);
+
+#endif /* !defined (__HW_SPAPR_H__) */
new file mode 100644
@@ -0,0 +1,151 @@
+/*
+ * SPAPR hypercalls
+ *
+ * Borrowed heavily from QEMU's spapr_hcall.c,
+ * Copyright (c) 2010 David Gibson, IBM Corporation.
+ *
+ * Copyright (c) 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include "spapr.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+
+#include <stdio.h>
+#include <assert.h>
+
+
+static target_ulong h_set_dabr(struct kvm_cpu *vcpu, target_ulong opcode, target_ulong *args)
+{
+ pr_warning("Implement %s!\n", __PRETTY_FUNCTION__);
+ return H_HARDWARE;
+}
+
+static target_ulong h_register_vpa(struct kvm_cpu *vcpu, target_ulong opcode, target_ulong *args)
+{
+ pr_warning("Implement %s!\n", __PRETTY_FUNCTION__);
+ return H_SUCCESS;
+}
+
+static target_ulong h_cede(struct kvm_cpu *vcpu, target_ulong opcode, target_ulong *args)
+{
+ pr_warning("Implement %s!\n", __PRETTY_FUNCTION__);
+ return H_SUCCESS;
+}
+
+static target_ulong h_rtas(struct kvm_cpu *vcpu, target_ulong opcode, target_ulong *args)
+{
+ target_ulong rtas_r3 = args[0];
+ /* Pointer read from phys mem; I hereby state these can't be MMIO...
+ * so just referencing memory directly.
+ */
+ uint32_t token, nargs, nret;
+
+ token = rtas_ld(vcpu->kvm, rtas_r3, 0);
+ nargs = rtas_ld(vcpu->kvm, rtas_r3, 1);
+ nret = rtas_ld(vcpu->kvm, rtas_r3, 2);
+
+ return spapr_rtas_call(vcpu, token, nargs, rtas_r3 + 12,
+ nret, rtas_r3 + 12 + 4*nargs);
+}
+
+static target_ulong h_logical_load(struct kvm_cpu *vcpu, target_ulong opcode, target_ulong *args)
+{
+ /* SLOF will require these, though kernel doesn't. */
+ die(__PRETTY_FUNCTION__);
+ return H_PARAMETER;
+}
+
+static target_ulong h_logical_store(struct kvm_cpu *vcpu, target_ulong opcode, target_ulong *args)
+{
+ /* SLOF will require these, though kernel doesn't. */
+ die(__PRETTY_FUNCTION__);
+ return H_PARAMETER;
+}
+
+static target_ulong h_logical_icbi(struct kvm_cpu *vcpu, target_ulong opcode, target_ulong *args)
+{
+ /* Nothing to do on emulation, KVM will trap this in the kernel */
+ return H_SUCCESS;
+}
+
+static target_ulong h_logical_dcbf(struct kvm_cpu *vcpu, target_ulong opcode, target_ulong *args)
+{
+ /* Nothing to do on emulation, KVM will trap this in the kernel */
+ return H_SUCCESS;
+}
+
+static spapr_hcall_fn papr_hypercall_table[(MAX_HCALL_OPCODE / 4) + 1];
+static spapr_hcall_fn kvmppc_hypercall_table[KVMPPC_HCALL_MAX - KVMPPC_HCALL_BASE + 1];
+
+void spapr_register_hypercall(target_ulong opcode, spapr_hcall_fn fn)
+{
+ spapr_hcall_fn *slot;
+
+ if (opcode <= MAX_HCALL_OPCODE) {
+ assert((opcode & 0x3) == 0);
+
+ slot = &papr_hypercall_table[opcode / 4];
+ } else {
+ assert((opcode >= KVMPPC_HCALL_BASE) && (opcode <= KVMPPC_HCALL_MAX));
+
+
+ slot = &kvmppc_hypercall_table[opcode - KVMPPC_HCALL_BASE];
+ }
+
+ assert(!(*slot) || (fn == *slot));
+ *slot = fn;
+}
+
+target_ulong spapr_hypercall(struct kvm_cpu *vcpu, target_ulong opcode,
+ target_ulong *args)
+{
+ if ((opcode <= MAX_HCALL_OPCODE)
+ && ((opcode & 0x3) == 0)) {
+ spapr_hcall_fn fn = papr_hypercall_table[opcode / 4];
+
+ if (fn) {
+ return fn(vcpu, opcode, args);
+ }
+ } else if ((opcode >= KVMPPC_HCALL_BASE) &&
+ (opcode <= KVMPPC_HCALL_MAX)) {
+ spapr_hcall_fn fn = kvmppc_hypercall_table[opcode - KVMPPC_HCALL_BASE];
+
+ if (fn) {
+ return fn(vcpu, opcode, args);
+ }
+ }
+
+ hcall_dprintf("Unimplemented hcall 0x%lx\n", opcode);
+ return H_FUNCTION;
+}
+
+void hypercall_init(void)
+{
+ /* hcall-dabr */
+ spapr_register_hypercall(H_SET_DABR, h_set_dabr);
+
+ /* hcall-splpar */
+ spapr_register_hypercall(H_REGISTER_VPA, h_register_vpa);
+ spapr_register_hypercall(H_CEDE, h_cede);
+
+ /* "debugger" hcalls (also used by SLOF). Note: We do -not- differentiate
+ * here between the "CI" and the "CACHE" variants, they will use whatever
+ * mapping attributes qemu is using. When using KVM, the kernel will
+ * enforce the attributes more strongly
+ */
+ spapr_register_hypercall(H_LOGICAL_CI_LOAD, h_logical_load);
+ spapr_register_hypercall(H_LOGICAL_CI_STORE, h_logical_store);
+ spapr_register_hypercall(H_LOGICAL_CACHE_LOAD, h_logical_load);
+ spapr_register_hypercall(H_LOGICAL_CACHE_STORE, h_logical_store);
+ spapr_register_hypercall(H_LOGICAL_ICBI, h_logical_icbi);
+ spapr_register_hypercall(H_LOGICAL_DCBF, h_logical_dcbf);
+
+ /* KVM-PPC specific hcalls */
+ spapr_register_hypercall(KVMPPC_H_RTAS, h_rtas);
+}
new file mode 100644
@@ -0,0 +1,226 @@
+/*
+ * SPAPR base RTAS calls
+ *
+ * Borrowed heavily from QEMU's spapr_rtas.c
+ * Copyright (c) 2010-2011 David Gibson, IBM Corporation.
+ *
+ * Modifications copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/util.h"
+#include "kvm/term.h"
+
+#include "spapr.h"
+
+#include <stdio.h>
+#include <assert.h>
+#include <libfdt.h>
+
+#define TOKEN_BASE 0x2000
+#define TOKEN_MAX 0x100
+
+#define RTAS_CONSOLE
+
+static void rtas_display_character(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ char c = rtas_ld(vcpu->kvm, args, 0);
+ term_putc(CONSOLE_HV, &c, 1, 0);
+ rtas_st(vcpu->kvm, rets, 0, 0);
+}
+
+#ifdef RTAS_CONSOLE
+static void rtas_put_term_char(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ char c = rtas_ld(vcpu->kvm, args, 0);
+ term_putc(CONSOLE_HV, &c, 1, 0);
+ rtas_st(vcpu->kvm, rets, 0, 0);
+}
+
+static void rtas_get_term_char(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ int c;
+ if (term_readable(CONSOLE_HV, 0) && (c = term_getc(CONSOLE_HV, 0)) >= 0) {
+ rtas_st(vcpu->kvm, rets, 0, 0);
+ rtas_st(vcpu->kvm, rets, 1, c);
+ } else {
+ rtas_st(vcpu->kvm, rets, 0, -2);
+ }
+}
+#endif
+
+static void rtas_get_time_of_day(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ struct tm tm;
+ time_t tnow;
+
+ if (nret != 8) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+
+ tnow = time(NULL);
+ /* Guest time is currently not offset in any way. */
+ gmtime_r(&tnow, &tm);
+
+ rtas_st(vcpu->kvm, rets, 0, 0); /* Success */
+ rtas_st(vcpu->kvm, rets, 1, tm.tm_year + 1900);
+ rtas_st(vcpu->kvm, rets, 2, tm.tm_mon + 1);
+ rtas_st(vcpu->kvm, rets, 3, tm.tm_mday);
+ rtas_st(vcpu->kvm, rets, 4, tm.tm_hour);
+ rtas_st(vcpu->kvm, rets, 5, tm.tm_min);
+ rtas_st(vcpu->kvm, rets, 6, tm.tm_sec);
+ rtas_st(vcpu->kvm, rets, 7, 0);
+}
+
+static void rtas_set_time_of_day(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ pr_warning("%s called; TOD set ignored.\n", __FUNCTION__);
+}
+
+static void rtas_power_off(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs, target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ if (nargs != 2 || nret != 1) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+ kvm_cpu__reboot();
+}
+
+static void rtas_query_cpu_stopped_state(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ unsigned long id;
+
+ if (nargs != 1 || nret != 2) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+
+ id = rtas_ld(vcpu->kvm, args, 0);
+
+ /* We do start all CPUs. So just return true. */
+ rtas_st(vcpu->kvm, rets, 0, 0);
+ rtas_st(vcpu->kvm, rets, 1, 2);
+}
+
+static void rtas_start_cpu(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ die(__FUNCTION__);
+}
+
+static struct rtas_call {
+ const char *name;
+ spapr_rtas_fn fn;
+} rtas_table[TOKEN_MAX];
+
+struct rtas_call *rtas_next = rtas_table;
+
+target_ulong spapr_rtas_call(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs, target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ if ((token >= TOKEN_BASE)
+ && ((token - TOKEN_BASE) < TOKEN_MAX)) {
+ struct rtas_call *call = rtas_table + (token - TOKEN_BASE);
+
+ if (call->fn) {
+ call->fn(vcpu, token, nargs, args, nret, rets);
+ return H_SUCCESS;
+ }
+ }
+
+ /* HACK: Some Linux early debug code uses RTAS display-character,
+ * but assumes the token value is 0xa (which it is on some real
+ * machines) without looking it up in the device tree. This
+ * special case makes this work */
+ if (token == 0xa) {
+ rtas_display_character(vcpu, 0xa, nargs, args, nret, rets);
+ return H_SUCCESS;
+ }
+
+ hcall_dprintf("Unknown RTAS token 0x%x\n", token);
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return H_PARAMETER;
+}
+
+void spapr_rtas_register(const char *name, spapr_rtas_fn fn)
+{
+ assert(rtas_next < (rtas_table + TOKEN_MAX));
+
+ rtas_next->name = name;
+ rtas_next->fn = fn;
+
+ rtas_next++;
+}
+
+/* This is called from the context of an open /rtas node, in order to add
+ * properties for the rtas call tokens.
+ */
+int spapr_rtas_fdt_setup(struct kvm *kvm, void *fdt)
+{
+ int ret;
+ int i;
+
+ for (i = 0; i < TOKEN_MAX; i++) {
+ struct rtas_call *call = &rtas_table[i];
+
+ if (!call->fn) {
+ continue;
+ }
+
+ /* HACK borrowed from QEMU */
+ ret = fdt_property_cell(fdt, call->name, i + TOKEN_BASE);
+
+ if (ret < 0) {
+ pr_warning("Couldn't add rtas token for %s: %s\n",
+ call->name, fdt_strerror(ret));
+ return ret;
+ }
+
+ }
+ return 0;
+}
+
+void register_core_rtas(void)
+{
+ spapr_rtas_register("display-character", rtas_display_character);
+ spapr_rtas_register("get-time-of-day", rtas_get_time_of_day);
+ spapr_rtas_register("set-time-of-day", rtas_set_time_of_day);
+ spapr_rtas_register("power-off", rtas_power_off);
+ spapr_rtas_register("query-cpu-stopped-state",
+ rtas_query_cpu_stopped_state);
+ spapr_rtas_register("start-cpu", rtas_start_cpu);
+#ifdef RTAS_CONSOLE
+ /* These are unused: We do console I/O via hcalls, not rtas. */
+ spapr_rtas_register("put-term-char", rtas_put_term_char);
+ spapr_rtas_register("get-term-char", rtas_get_term_char);
+#endif
+}
This patch adds the basic structure for HV calls, their registration and some of the simpler calls. A similar layout for RTAS calls is also added, again with some of the simpler RTAS calls used by the guest. The SPAPR RTAS stub is generated inline. Also, nodes for RTAS are added to the device tree. Signed-off-by: Matt Evans <matt@ozlabs.org> --- tools/kvm/Makefile | 2 + tools/kvm/powerpc/kvm-cpu.c | 5 + tools/kvm/powerpc/kvm.c | 39 +++++- tools/kvm/powerpc/spapr.h | 308 +++++++++++++++++++++++++++++++++++++++ tools/kvm/powerpc/spapr_hcall.c | 151 +++++++++++++++++++ tools/kvm/powerpc/spapr_rtas.c | 226 ++++++++++++++++++++++++++++ 6 files changed, 730 insertions(+), 1 deletions(-) create mode 100644 tools/kvm/powerpc/spapr.h create mode 100644 tools/kvm/powerpc/spapr_hcall.c create mode 100644 tools/kvm/powerpc/spapr_rtas.c -- To unsubscribe from this list: send the line "unsubscribe kvm-ppc" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html