powerpc/powernv: move OPAL call wrapper tracing and interrupt handling to C

The OPAL call wrapper gets interrupt disabling wrong. It disables
interrupts just by clearing MSR[EE], which has two problems:

- It doesn't call into the IRQ tracing subsystem, which means tracing
  across OPAL calls does not always notice IRQs have been disabled.

- It doesn't go through the IRQ soft-mask code, which causes a minor
  bug. MSR[EE] can not be restored by saving the MSR then clearing
  MSR[EE], because a racing interrupt while soft-masked could clear
  MSR[EE] between the two steps. This can cause MSR[EE] to be
  incorrectly enabled when the OPAL call returns. Fortunately that
  should only result in another masked interrupt being taken to
  disable MSR[EE] again, but it's a bit sloppy.

The existing code also saves MSR to PACA, which is not re-entrant if
there is a nested OPAL call from different MSR contexts, which can
happen these days with SRESET interrupts on bare metal.

To fix these issues, move the tracing and IRQ handling code to C, and
call into asm just for the low level call when everything is ready to
go. Save the MSR on stack rather than PACA.

Performance cost is kept to a minimum with a few optimisations:

- The endian switch upon return is combined with the MSR restore,
  which avoids an expensive context synchronizing operation for LE
  kernels. This makes up for the additional mtmsrd to enable
  interrupts with local_irq_enable().

- blr is now used to return from the opal_* functions that are called
  as C functions, to avoid link stack corruption. This requires a
  skiboot fix as well to keep the call stack balanced.

A NULL call is more costly after this, (410ns->430ns on POWER9), but
OPAL calls are generally not performance critical at this scale.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

4 files changed, 328 insertions, 314 deletions

diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index e01f31fb0865..effdd096fa4c 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -37,13 +37,11 @@ void kexec_copy_flush(struct kimage *image);
 extern struct static_key hcall_tracepoint_key;
 void __trace_hcall_entry(unsigned long opcode, unsigned long *args);
 void __trace_hcall_exit(long opcode, long retval, unsigned long *retbuf);
-/* OPAL tracing */
-#ifdef CONFIG_JUMP_LABEL
-extern struct static_key opal_tracepoint_key;
-#endif
 
-void __trace_opal_entry(unsigned long opcode, unsigned long *args);
-void __trace_opal_exit(long opcode, unsigned long retval);
+/* OPAL */
+int64_t __opal_call(int64_t a0, int64_t a1, int64_t a2, int64_t a3,
+		    int64_t a4, int64_t a5, int64_t a6, int64_t a7,
+		    int64_t opcode, uint64_t msr);
 
 /* VMX copying */
 int enter_vmx_usercopy(void);
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index b540ce8eec55..da2e99efbd04 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
-obj-y			+= setup.o opal-wrappers.o opal.o opal-async.o idle.o
-obj-y			+= opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o
+obj-y			+= setup.o opal-call.o opal-wrappers.o opal.o opal-async.o
+obj-y			+= idle.o opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o
 obj-y			+= rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o
 obj-y			+= opal-msglog.o opal-hmi.o opal-power.o opal-irqchip.o
 obj-y			+= opal-kmsg.o opal-powercap.o opal-psr.o opal-sensor-groups.o
@@ -11,7 +11,6 @@ obj-$(CONFIG_CXL_BASE)	+= pci-cxl.o
 obj-$(CONFIG_EEH)	+= eeh-powernv.o
 obj-$(CONFIG_PPC_SCOM)	+= opal-xscom.o
 obj-$(CONFIG_MEMORY_FAILURE)	+= opal-memory-errors.o
-obj-$(CONFIG_TRACEPOINTS)	+= opal-tracepoints.o
 obj-$(CONFIG_OPAL_PRD)	+= opal-prd.o
 obj-$(CONFIG_PERF_EVENTS) += opal-imc.o
 obj-$(CONFIG_PPC_MEMTRACE)	+= memtrace.o
diff --git a/arch/powerpc/platforms/powernv/opal-call.c b/arch/powerpc/platforms/powernv/opal-call.c
new file mode 100644
index 000000000000..578757d403ab
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-call.c
@@ -0,0 +1,283 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/percpu.h>
+#include <linux/jump_label.h>
+#include <asm/opal-api.h>
+#include <asm/trace.h>
+#include <asm/asm-prototypes.h>
+
+#ifdef CONFIG_TRACEPOINTS
+/*
+ * Since the tracing code might execute OPAL calls we need to guard against
+ * recursion.
+ */
+static DEFINE_PER_CPU(unsigned int, opal_trace_depth);
+
+static void __trace_opal_entry(s64 a0, s64 a1, s64 a2, s64 a3,
+			       s64 a4, s64 a5, s64 a6, s64 a7,
+			       unsigned long opcode)
+{
+	unsigned int *depth;
+	unsigned long args[8];
+
+	depth = this_cpu_ptr(&opal_trace_depth);
+
+	if (*depth)
+		return;
+
+	args[0] = a0;
+	args[1] = a1;
+	args[2] = a2;
+	args[3] = a3;
+	args[4] = a4;
+	args[5] = a5;
+	args[6] = a6;
+	args[7] = a7;
+
+	(*depth)++;
+	trace_opal_entry(opcode, &args[0]);
+	(*depth)--;
+}
+
+static void __trace_opal_exit(unsigned long opcode, unsigned long retval)
+{
+	unsigned int *depth;
+
+	depth = this_cpu_ptr(&opal_trace_depth);
+
+	if (*depth)
+		return;
+
+	(*depth)++;
+	trace_opal_exit(opcode, retval);
+	(*depth)--;
+}
+
+static DEFINE_STATIC_KEY_FALSE(opal_tracepoint_key);
+
+int opal_tracepoint_regfunc(void)
+{
+	static_branch_inc(&opal_tracepoint_key);
+	return 0;
+}
+
+void opal_tracepoint_unregfunc(void)
+{
+	static_branch_dec(&opal_tracepoint_key);
+}
+
+static s64 __opal_call_trace(s64 a0, s64 a1, s64 a2, s64 a3,
+			     s64 a4, s64 a5, s64 a6, s64 a7,
+			      unsigned long opcode, unsigned long msr)
+{
+	s64 ret;
+
+	__trace_opal_entry(a0, a1, a2, a3, a4, a5, a6, a7, opcode);
+	ret = __opal_call(a0, a1, a2, a3, a4, a5, a6, a7, opcode, msr);
+	__trace_opal_exit(opcode, ret);
+
+	return ret;
+}
+
+#define DO_TRACE (static_branch_unlikely(&opal_tracepoint_key))
+
+#else /* CONFIG_TRACEPOINTS */
+
+static s64 __opal_call_trace(s64 a0, s64 a1, s64 a2, s64 a3,
+			     s64 a4, s64 a5, s64 a6, s64 a7,
+			      unsigned long opcode, unsigned long msr)
+{
+}
+
+#define DO_TRACE false
+#endif /* CONFIG_TRACEPOINTS */
+
+static int64_t opal_call(int64_t a0, int64_t a1, int64_t a2, int64_t a3,
+	     int64_t a4, int64_t a5, int64_t a6, int64_t a7, int64_t opcode)
+{
+	unsigned long flags;
+	unsigned long msr = mfmsr();
+	bool mmu = (msr & (MSR_IR|MSR_DR));
+	int64_t ret;
+
+	msr &= ~MSR_EE;
+
+	if (unlikely(!mmu))
+		return __opal_call(a0, a1, a2, a3, a4, a5, a6, a7, opcode, msr);
+
+	local_save_flags(flags);
+	hard_irq_disable();
+
+	if (DO_TRACE) {
+		ret = __opal_call_trace(a0, a1, a2, a3, a4, a5, a6, a7, opcode, msr);
+	} else {
+		ret = __opal_call(a0, a1, a2, a3, a4, a5, a6, a7, opcode, msr);
+	}
+
+	local_irq_restore(flags);
+
+	return ret;
+}
+
+#define OPAL_CALL(name, opcode)					\
+int64_t name(int64_t a0, int64_t a1, int64_t a2, int64_t a3,	\
+	     int64_t a4, int64_t a5, int64_t a6, int64_t a7)	\
+{								\
+	return opal_call(a0, a1, a2, a3, a4, a5, a6, a7, opcode); \
+}
+
+OPAL_CALL(opal_invalid_call,			OPAL_INVALID_CALL);
+OPAL_CALL(opal_console_write,			OPAL_CONSOLE_WRITE);
+OPAL_CALL(opal_console_read,			OPAL_CONSOLE_READ);
+OPAL_CALL(opal_console_write_buffer_space,	OPAL_CONSOLE_WRITE_BUFFER_SPACE);
+OPAL_CALL(opal_rtc_read,			OPAL_RTC_READ);
+OPAL_CALL(opal_rtc_write,			OPAL_RTC_WRITE);
+OPAL_CALL(opal_cec_power_down,			OPAL_CEC_POWER_DOWN);
+OPAL_CALL(opal_cec_reboot,			OPAL_CEC_REBOOT);
+OPAL_CALL(opal_cec_reboot2,			OPAL_CEC_REBOOT2);
+OPAL_CALL(opal_read_nvram,			OPAL_READ_NVRAM);
+OPAL_CALL(opal_write_nvram,			OPAL_WRITE_NVRAM);
+OPAL_CALL(opal_handle_interrupt,		OPAL_HANDLE_INTERRUPT);
+OPAL_CALL(opal_poll_events,			OPAL_POLL_EVENTS);
+OPAL_CALL(opal_pci_set_hub_tce_memory,		OPAL_PCI_SET_HUB_TCE_MEMORY);
+OPAL_CALL(opal_pci_set_phb_tce_memory,		OPAL_PCI_SET_PHB_TCE_MEMORY);
+OPAL_CALL(opal_pci_config_read_byte,		OPAL_PCI_CONFIG_READ_BYTE);
+OPAL_CALL(opal_pci_config_read_half_word,	OPAL_PCI_CONFIG_READ_HALF_WORD);
+OPAL_CALL(opal_pci_config_read_word,		OPAL_PCI_CONFIG_READ_WORD);
+OPAL_CALL(opal_pci_config_write_byte,		OPAL_PCI_CONFIG_WRITE_BYTE);
+OPAL_CALL(opal_pci_config_write_half_word,	OPAL_PCI_CONFIG_WRITE_HALF_WORD);
+OPAL_CALL(opal_pci_config_write_word,		OPAL_PCI_CONFIG_WRITE_WORD);
+OPAL_CALL(opal_set_xive,			OPAL_SET_XIVE);
+OPAL_CALL(opal_get_xive,			OPAL_GET_XIVE);
+OPAL_CALL(opal_register_exception_handler,	OPAL_REGISTER_OPAL_EXCEPTION_HANDLER);
+OPAL_CALL(opal_pci_eeh_freeze_status,		OPAL_PCI_EEH_FREEZE_STATUS);
+OPAL_CALL(opal_pci_eeh_freeze_clear,		OPAL_PCI_EEH_FREEZE_CLEAR);
+OPAL_CALL(opal_pci_eeh_freeze_set,		OPAL_PCI_EEH_FREEZE_SET);
+OPAL_CALL(opal_pci_err_inject,			OPAL_PCI_ERR_INJECT);
+OPAL_CALL(opal_pci_shpc,			OPAL_PCI_SHPC);
+OPAL_CALL(opal_pci_phb_mmio_enable,		OPAL_PCI_PHB_MMIO_ENABLE);
+OPAL_CALL(opal_pci_set_phb_mem_window,		OPAL_PCI_SET_PHB_MEM_WINDOW);
+OPAL_CALL(opal_pci_map_pe_mmio_window,		OPAL_PCI_MAP_PE_MMIO_WINDOW);
+OPAL_CALL(opal_pci_set_phb_table_memory,	OPAL_PCI_SET_PHB_TABLE_MEMORY);
+OPAL_CALL(opal_pci_set_pe,			OPAL_PCI_SET_PE);
+OPAL_CALL(opal_pci_set_peltv,			OPAL_PCI_SET_PELTV);
+OPAL_CALL(opal_pci_set_mve,			OPAL_PCI_SET_MVE);
+OPAL_CALL(opal_pci_set_mve_enable,		OPAL_PCI_SET_MVE_ENABLE);
+OPAL_CALL(opal_pci_get_xive_reissue,		OPAL_PCI_GET_XIVE_REISSUE);
+OPAL_CALL(opal_pci_set_xive_reissue,		OPAL_PCI_SET_XIVE_REISSUE);
+OPAL_CALL(opal_pci_set_xive_pe,			OPAL_PCI_SET_XIVE_PE);
+OPAL_CALL(opal_get_xive_source,			OPAL_GET_XIVE_SOURCE);
+OPAL_CALL(opal_get_msi_32,			OPAL_GET_MSI_32);
+OPAL_CALL(opal_get_msi_64,			OPAL_GET_MSI_64);
+OPAL_CALL(opal_start_cpu,			OPAL_START_CPU);
+OPAL_CALL(opal_query_cpu_status,		OPAL_QUERY_CPU_STATUS);
+OPAL_CALL(opal_write_oppanel,			OPAL_WRITE_OPPANEL);
+OPAL_CALL(opal_pci_map_pe_dma_window,		OPAL_PCI_MAP_PE_DMA_WINDOW);
+OPAL_CALL(opal_pci_map_pe_dma_window_real,	OPAL_PCI_MAP_PE_DMA_WINDOW_REAL);
+OPAL_CALL(opal_pci_reset,			OPAL_PCI_RESET);
+OPAL_CALL(opal_pci_get_hub_diag_data,		OPAL_PCI_GET_HUB_DIAG_DATA);
+OPAL_CALL(opal_pci_get_phb_diag_data,		OPAL_PCI_GET_PHB_DIAG_DATA);
+OPAL_CALL(opal_pci_fence_phb,			OPAL_PCI_FENCE_PHB);
+OPAL_CALL(opal_pci_reinit,			OPAL_PCI_REINIT);
+OPAL_CALL(opal_pci_mask_pe_error,		OPAL_PCI_MASK_PE_ERROR);
+OPAL_CALL(opal_set_slot_led_status,		OPAL_SET_SLOT_LED_STATUS);
+OPAL_CALL(opal_get_epow_status,			OPAL_GET_EPOW_STATUS);
+OPAL_CALL(opal_get_dpo_status,			OPAL_GET_DPO_STATUS);
+OPAL_CALL(opal_set_system_attention_led,	OPAL_SET_SYSTEM_ATTENTION_LED);
+OPAL_CALL(opal_pci_next_error,			OPAL_PCI_NEXT_ERROR);
+OPAL_CALL(opal_pci_poll,			OPAL_PCI_POLL);
+OPAL_CALL(opal_pci_msi_eoi,			OPAL_PCI_MSI_EOI);
+OPAL_CALL(opal_pci_get_phb_diag_data2,		OPAL_PCI_GET_PHB_DIAG_DATA2);
+OPAL_CALL(opal_xscom_read,			OPAL_XSCOM_READ);
+OPAL_CALL(opal_xscom_write,			OPAL_XSCOM_WRITE);
+OPAL_CALL(opal_lpc_read,			OPAL_LPC_READ);
+OPAL_CALL(opal_lpc_write,			OPAL_LPC_WRITE);
+OPAL_CALL(opal_return_cpu,			OPAL_RETURN_CPU);
+OPAL_CALL(opal_reinit_cpus,			OPAL_REINIT_CPUS);
+OPAL_CALL(opal_read_elog,			OPAL_ELOG_READ);
+OPAL_CALL(opal_send_ack_elog,			OPAL_ELOG_ACK);
+OPAL_CALL(opal_get_elog_size,			OPAL_ELOG_SIZE);
+OPAL_CALL(opal_resend_pending_logs,		OPAL_ELOG_RESEND);
+OPAL_CALL(opal_write_elog,			OPAL_ELOG_WRITE);
+OPAL_CALL(opal_validate_flash,			OPAL_FLASH_VALIDATE);
+OPAL_CALL(opal_manage_flash,			OPAL_FLASH_MANAGE);
+OPAL_CALL(opal_update_flash,			OPAL_FLASH_UPDATE);
+OPAL_CALL(opal_resync_timebase,			OPAL_RESYNC_TIMEBASE);
+OPAL_CALL(opal_check_token,			OPAL_CHECK_TOKEN);
+OPAL_CALL(opal_dump_init,			OPAL_DUMP_INIT);
+OPAL_CALL(opal_dump_info,			OPAL_DUMP_INFO);
+OPAL_CALL(opal_dump_info2,			OPAL_DUMP_INFO2);
+OPAL_CALL(opal_dump_read,			OPAL_DUMP_READ);
+OPAL_CALL(opal_dump_ack,			OPAL_DUMP_ACK);
+OPAL_CALL(opal_get_msg,				OPAL_GET_MSG);
+OPAL_CALL(opal_write_oppanel_async,		OPAL_WRITE_OPPANEL_ASYNC);
+OPAL_CALL(opal_check_completion,		OPAL_CHECK_ASYNC_COMPLETION);
+OPAL_CALL(opal_dump_resend_notification,	OPAL_DUMP_RESEND);
+OPAL_CALL(opal_sync_host_reboot,		OPAL_SYNC_HOST_REBOOT);
+OPAL_CALL(opal_sensor_read,			OPAL_SENSOR_READ);
+OPAL_CALL(opal_get_param,			OPAL_GET_PARAM);
+OPAL_CALL(opal_set_param,			OPAL_SET_PARAM);
+OPAL_CALL(opal_handle_hmi,			OPAL_HANDLE_HMI);
+OPAL_CALL(opal_config_cpu_idle_state,		OPAL_CONFIG_CPU_IDLE_STATE);
+OPAL_CALL(opal_slw_set_reg,			OPAL_SLW_SET_REG);
+OPAL_CALL(opal_register_dump_region,		OPAL_REGISTER_DUMP_REGION);
+OPAL_CALL(opal_unregister_dump_region,		OPAL_UNREGISTER_DUMP_REGION);
+OPAL_CALL(opal_pci_set_phb_cxl_mode,		OPAL_PCI_SET_PHB_CAPI_MODE);
+OPAL_CALL(opal_tpo_write,			OPAL_WRITE_TPO);
+OPAL_CALL(opal_tpo_read,			OPAL_READ_TPO);
+OPAL_CALL(opal_ipmi_send,			OPAL_IPMI_SEND);
+OPAL_CALL(opal_ipmi_recv,			OPAL_IPMI_RECV);
+OPAL_CALL(opal_i2c_request,			OPAL_I2C_REQUEST);
+OPAL_CALL(opal_flash_read,			OPAL_FLASH_READ);
+OPAL_CALL(opal_flash_write,			OPAL_FLASH_WRITE);
+OPAL_CALL(opal_flash_erase,			OPAL_FLASH_ERASE);
+OPAL_CALL(opal_prd_msg,				OPAL_PRD_MSG);
+OPAL_CALL(opal_leds_get_ind,			OPAL_LEDS_GET_INDICATOR);
+OPAL_CALL(opal_leds_set_ind,			OPAL_LEDS_SET_INDICATOR);
+OPAL_CALL(opal_console_flush,			OPAL_CONSOLE_FLUSH);
+OPAL_CALL(opal_get_device_tree,			OPAL_GET_DEVICE_TREE);
+OPAL_CALL(opal_pci_get_presence_state,		OPAL_PCI_GET_PRESENCE_STATE);
+OPAL_CALL(opal_pci_get_power_state,		OPAL_PCI_GET_POWER_STATE);
+OPAL_CALL(opal_pci_set_power_state,		OPAL_PCI_SET_POWER_STATE);
+OPAL_CALL(opal_int_get_xirr,			OPAL_INT_GET_XIRR);
+OPAL_CALL(opal_int_set_cppr,			OPAL_INT_SET_CPPR);
+OPAL_CALL(opal_int_eoi,				OPAL_INT_EOI);
+OPAL_CALL(opal_int_set_mfrr,			OPAL_INT_SET_MFRR);
+OPAL_CALL(opal_pci_tce_kill,			OPAL_PCI_TCE_KILL);
+OPAL_CALL(opal_nmmu_set_ptcr,			OPAL_NMMU_SET_PTCR);
+OPAL_CALL(opal_xive_reset,			OPAL_XIVE_RESET);
+OPAL_CALL(opal_xive_get_irq_info,		OPAL_XIVE_GET_IRQ_INFO);
+OPAL_CALL(opal_xive_get_irq_config,		OPAL_XIVE_GET_IRQ_CONFIG);
+OPAL_CALL(opal_xive_set_irq_config,		OPAL_XIVE_SET_IRQ_CONFIG);
+OPAL_CALL(opal_xive_get_queue_info,		OPAL_XIVE_GET_QUEUE_INFO);
+OPAL_CALL(opal_xive_set_queue_info,		OPAL_XIVE_SET_QUEUE_INFO);
+OPAL_CALL(opal_xive_donate_page,		OPAL_XIVE_DONATE_PAGE);
+OPAL_CALL(opal_xive_alloc_vp_block,		OPAL_XIVE_ALLOCATE_VP_BLOCK);
+OPAL_CALL(opal_xive_free_vp_block,		OPAL_XIVE_FREE_VP_BLOCK);
+OPAL_CALL(opal_xive_allocate_irq,		OPAL_XIVE_ALLOCATE_IRQ);
+OPAL_CALL(opal_xive_free_irq,			OPAL_XIVE_FREE_IRQ);
+OPAL_CALL(opal_xive_get_vp_info,		OPAL_XIVE_GET_VP_INFO);
+OPAL_CALL(opal_xive_set_vp_info,		OPAL_XIVE_SET_VP_INFO);
+OPAL_CALL(opal_xive_sync,			OPAL_XIVE_SYNC);
+OPAL_CALL(opal_xive_dump,			OPAL_XIVE_DUMP);
+OPAL_CALL(opal_signal_system_reset,		OPAL_SIGNAL_SYSTEM_RESET);
+OPAL_CALL(opal_npu_init_context,		OPAL_NPU_INIT_CONTEXT);
+OPAL_CALL(opal_npu_destroy_context,		OPAL_NPU_DESTROY_CONTEXT);
+OPAL_CALL(opal_npu_map_lpar,			OPAL_NPU_MAP_LPAR);
+OPAL_CALL(opal_imc_counters_init,		OPAL_IMC_COUNTERS_INIT);
+OPAL_CALL(opal_imc_counters_start,		OPAL_IMC_COUNTERS_START);
+OPAL_CALL(opal_imc_counters_stop,		OPAL_IMC_COUNTERS_STOP);
+OPAL_CALL(opal_pci_set_p2p,			OPAL_PCI_SET_P2P);
+OPAL_CALL(opal_get_powercap,			OPAL_GET_POWERCAP);
+OPAL_CALL(opal_set_powercap,			OPAL_SET_POWERCAP);
+OPAL_CALL(opal_get_power_shift_ratio,		OPAL_GET_POWER_SHIFT_RATIO);
+OPAL_CALL(opal_set_power_shift_ratio,		OPAL_SET_POWER_SHIFT_RATIO);
+OPAL_CALL(opal_sensor_group_clear,		OPAL_SENSOR_GROUP_CLEAR);
+OPAL_CALL(opal_quiesce,				OPAL_QUIESCE);
+OPAL_CALL(opal_npu_spa_setup,			OPAL_NPU_SPA_SETUP);
+OPAL_CALL(opal_npu_spa_clear_cache,		OPAL_NPU_SPA_CLEAR_CACHE);
+OPAL_CALL(opal_npu_tl_set,			OPAL_NPU_TL_SET);
+OPAL_CALL(opal_pci_get_pbcq_tunnel_bar,		OPAL_PCI_GET_PBCQ_TUNNEL_BAR);
+OPAL_CALL(opal_pci_set_pbcq_tunnel_bar,		OPAL_PCI_SET_PBCQ_TUNNEL_BAR);
+OPAL_CALL(opal_sensor_read_u64,			OPAL_SENSOR_READ_U64);
+OPAL_CALL(opal_sensor_group_enable,		OPAL_SENSOR_GROUP_ENABLE);
+OPAL_CALL(opal_nx_coproc_init,			OPAL_NX_COPROC_INIT);
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index f4875fe3f8ff..7d2052d8af9d 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -17,317 +17,51 @@
 #include <asm/asm-compat.h>
 #include <asm/feature-fixups.h>
 
-	.section	".text"
-
-#ifdef CONFIG_TRACEPOINTS
-#ifdef CONFIG_JUMP_LABEL
-#define OPAL_BRANCH(LABEL)					\
-	ARCH_STATIC_BRANCH(LABEL, opal_tracepoint_key)
-#else
-
-	.section	".toc","aw"
-
-	.globl opal_tracepoint_refcount
-opal_tracepoint_refcount:
-	.8byte	0
-
-	.section	".text"
-
-/*
- * We branch around this in early init by using an unconditional cpu
- * feature.
- */
-#define OPAL_BRANCH(LABEL)					\
-BEGIN_FTR_SECTION;						\
-	b	1f;						\
-END_FTR_SECTION(0, 1);						\
-	ld	r11,opal_tracepoint_refcount@toc(r2);		\
-	cmpdi	r11,0;						\
-	bne-	LABEL;						\
-1:
-
-#endif
-
-#else
-#define OPAL_BRANCH(LABEL)
-#endif
+	.section ".text"
 
 /*
- * DO_OPAL_CALL assumes:
- * r0  = opal call token
- * r12 = msr
- * LR has been saved
+ * r3-r10		- OPAL call arguments
+ * STK_PARAM(R11)	- OPAL opcode
+ * STK_PARAM(R12)	- MSR to restore
  */
-#define DO_OPAL_CALL()			\
-	mfcr	r11;			\
-	stw	r11,8(r1);		\
-	li	r11,0;			\
-	ori	r11,r11,MSR_EE;		\
-	std	r12,PACASAVEDMSR(r13);	\
-	andc	r12,r12,r11;		\
-	mtmsrd	r12,1;			\
-	LOAD_REG_ADDR(r11,opal_return);	\
-	mtlr	r11;			\
-	li	r11,MSR_DR|MSR_IR|MSR_LE;\
-	andc	r12,r12,r11;		\
-	mtspr	SPRN_HSRR1,r12;		\
-	LOAD_REG_ADDR(r11,opal);	\
-	ld	r12,8(r11);		\
-	ld	r2,0(r11);		\
-	mtspr	SPRN_HSRR0,r12;		\
+_GLOBAL_TOC(__opal_call)
+	mflr	r0
+	std	r0,PPC_LR_STKOFF(r1)
+	ld	r12,STK_PARAM(R12)(r1)
+	li	r0,MSR_IR|MSR_DR|MSR_LE
+	andc	r12,r12,r0
+	LOAD_REG_ADDR(r11, opal_return)
+	mtlr	r11
+	LOAD_REG_ADDR(r11, opal)
+	ld	r2,0(r11)
+	ld	r11,8(r11)
+	mtspr	SPRN_HSRR0,r11
+	mtspr	SPRN_HSRR1,r12
+	/* set token to r0 */
+	ld	r0,STK_PARAM(R11)(r1)
 	hrfid
-
-#define OPAL_CALL(name, token)		\
- _GLOBAL_TOC(name);			\
-	mfmsr	r12;			\
-	mflr	r0;			\
-	andi.	r11,r12,MSR_IR|MSR_DR; 	\
-	std	r0,PPC_LR_STKOFF(r1);	\
-	li	r0,token;		\
-	beq	opal_real_call;         \
-	OPAL_BRANCH(opal_tracepoint_entry) \
-	DO_OPAL_CALL()
-
-
 opal_return:
 	/*
-	 * Fixup endian on OPAL return... we should be able to simplify
-	 * this by instead converting the below trampoline to a set of
-	 * bytes (always BE) since MSR:LE will end up fixed up as a side
-	 * effect of the rfid.
+	 * Restore MSR on OPAL return. The MSR is set to big-endian.
 	 */
-	FIXUP_ENDIAN_HV
-	ld	r2,PACATOC(r13);
-	lwz	r4,8(r1);
-	ld	r5,PPC_LR_STKOFF(r1);
-	ld	r6,PACASAVEDMSR(r13);
-	mtcr	r4;
-	mtspr	SPRN_HSRR0,r5;
-	mtspr	SPRN_HSRR1,r6;
-	hrfid
-
-opal_real_call:
-	mfcr	r11
-	stw	r11,8(r1)
-	/* Set opal return address */
-	LOAD_REG_ADDR(r11, opal_return_realmode)
-	mtlr	r11
-	li	r11,MSR_LE
-	andc	r12,r12,r11
-	mtspr	SPRN_HSRR1,r12
-	LOAD_REG_ADDR(r11,opal)
-	ld	r12,8(r11)
-	ld	r2,0(r11)
-	mtspr	SPRN_HSRR0,r12
-	hrfid
-
-opal_return_realmode:
-	FIXUP_ENDIAN_HV
-	ld	r2,PACATOC(r13);
-	lwz	r11,8(r1);
-	ld	r12,PPC_LR_STKOFF(r1)
-	mtcr	r11;
-	mtlr	r12
-	blr
-
-#ifdef CONFIG_TRACEPOINTS
-opal_tracepoint_entry:
-	stdu	r1,-STACKFRAMESIZE(r1)
-	std	r0,STK_REG(R23)(r1)
-	std	r3,STK_REG(R24)(r1)
-	std	r4,STK_REG(R25)(r1)
-	std	r5,STK_REG(R26)(r1)
-	std	r6,STK_REG(R27)(r1)
-	std	r7,STK_REG(R28)(r1)
-	std	r8,STK_REG(R29)(r1)
-	std	r9,STK_REG(R30)(r1)
-	std	r10,STK_REG(R31)(r1)
-	mr	r3,r0
-	addi	r4,r1,STK_REG(R24)
-	bl	__trace_opal_entry
-	ld	r0,STK_REG(R23)(r1)
-	ld	r3,STK_REG(R24)(r1)
-	ld	r4,STK_REG(R25)(r1)
-	ld	r5,STK_REG(R26)(r1)
-	ld	r6,STK_REG(R27)(r1)
-	ld	r7,STK_REG(R28)(r1)
-	ld	r8,STK_REG(R29)(r1)
-	ld	r9,STK_REG(R30)(r1)
-	ld	r10,STK_REG(R31)(r1)
-
-	/* setup LR so we return via tracepoint_return */
-	LOAD_REG_ADDR(r11,opal_tracepoint_return)
-	std	r11,16(r1)
-
-	mfmsr	r12
-	DO_OPAL_CALL()
-
-opal_tracepoint_return:
-	std	r3,STK_REG(R31)(r1)
-	mr	r4,r3
-	ld	r3,STK_REG(R23)(r1)
-	bl	__trace_opal_exit
-	ld	r3,STK_REG(R31)(r1)
-	addi	r1,r1,STACKFRAMESIZE
-	ld	r0,16(r1)
+#ifdef __BIG_ENDIAN__
+	ld	r11,STK_PARAM(R12)(r1)
+	mtmsrd	r11
+#else
+	/* Endian can only be switched with rfi, must byte reverse MSR load */
+	.short 0x4039	 /* li r10,STK_PARAM(R12)		*/
+	.byte (STK_PARAM(R12) >> 8) & 0xff
+	.byte STK_PARAM(R12) & 0xff
+
+	.long 0x280c6a7d /* ldbrx r11,r10,r1			*/
+	.long 0x05009f42 /* bcl 20,31,$+4			*/
+	.long 0xa602487d /* mflr r10				*/
+	.long 0x14004a39 /* addi r10,r10,20			*/
+	.long 0xa64b5a7d /* mthsrr0 r10				*/
+	.long 0xa64b7b7d /* mthsrr1 r11				*/
+	.long 0x2402004c /* hrfid				*/
+#endif
+	ld	r2,PACATOC(r13)
+	ld	r0,PPC_LR_STKOFF(r1)
 	mtlr	r0
 	blr
-#endif
-
-
-OPAL_CALL(opal_invalid_call,			OPAL_INVALID_CALL);
-OPAL_CALL(opal_console_write,			OPAL_CONSOLE_WRITE);
-OPAL_CALL(opal_console_read,			OPAL_CONSOLE_READ);
-OPAL_CALL(opal_console_write_buffer_space,	OPAL_CONSOLE_WRITE_BUFFER_SPACE);
-OPAL_CALL(opal_rtc_read,			OPAL_RTC_READ);
-OPAL_CALL(opal_rtc_write,			OPAL_RTC_WRITE);
-OPAL_CALL(opal_cec_power_down,			OPAL_CEC_POWER_DOWN);
-OPAL_CALL(opal_cec_reboot,			OPAL_CEC_REBOOT);
-OPAL_CALL(opal_cec_reboot2,			OPAL_CEC_REBOOT2);
-OPAL_CALL(opal_read_nvram,			OPAL_READ_NVRAM);
-OPAL_CALL(opal_write_nvram,			OPAL_WRITE_NVRAM);
-OPAL_CALL(opal_handle_interrupt,		OPAL_HANDLE_INTERRUPT);
-OPAL_CALL(opal_poll_events,			OPAL_POLL_EVENTS);
-OPAL_CALL(opal_pci_set_hub_tce_memory,		OPAL_PCI_SET_HUB_TCE_MEMORY);
-OPAL_CALL(opal_pci_set_phb_tce_memory,		OPAL_PCI_SET_PHB_TCE_MEMORY);
-OPAL_CALL(opal_pci_config_read_byte,		OPAL_PCI_CONFIG_READ_BYTE);
-OPAL_CALL(opal_pci_config_read_half_word,	OPAL_PCI_CONFIG_READ_HALF_WORD);
-OPAL_CALL(opal_pci_config_read_word,		OPAL_PCI_CONFIG_READ_WORD);
-OPAL_CALL(opal_pci_config_write_byte,		OPAL_PCI_CONFIG_WRITE_BYTE);
-OPAL_CALL(opal_pci_config_write_half_word,	OPAL_PCI_CONFIG_WRITE_HALF_WORD);
-OPAL_CALL(opal_pci_config_write_word,		OPAL_PCI_CONFIG_WRITE_WORD);
-OPAL_CALL(opal_set_xive,			OPAL_SET_XIVE);
-OPAL_CALL(opal_get_xive,			OPAL_GET_XIVE);
-OPAL_CALL(opal_register_exception_handler,	OPAL_REGISTER_OPAL_EXCEPTION_HANDLER);
-OPAL_CALL(opal_pci_eeh_freeze_status,		OPAL_PCI_EEH_FREEZE_STATUS);
-OPAL_CALL(opal_pci_eeh_freeze_clear,		OPAL_PCI_EEH_FREEZE_CLEAR);
-OPAL_CALL(opal_pci_eeh_freeze_set,		OPAL_PCI_EEH_FREEZE_SET);
-OPAL_CALL(opal_pci_err_inject,			OPAL_PCI_ERR_INJECT);
-OPAL_CALL(opal_pci_shpc,			OPAL_PCI_SHPC);
-OPAL_CALL(opal_pci_phb_mmio_enable,		OPAL_PCI_PHB_MMIO_ENABLE);
-OPAL_CALL(opal_pci_set_phb_mem_window,		OPAL_PCI_SET_PHB_MEM_WINDOW);
-OPAL_CALL(opal_pci_map_pe_mmio_window,		OPAL_PCI_MAP_PE_MMIO_WINDOW);
-OPAL_CALL(opal_pci_set_phb_table_memory,	OPAL_PCI_SET_PHB_TABLE_MEMORY);
-OPAL_CALL(opal_pci_set_pe,			OPAL_PCI_SET_PE);
-OPAL_CALL(opal_pci_set_peltv,			OPAL_PCI_SET_PELTV);
-OPAL_CALL(opal_pci_set_mve,			OPAL_PCI_SET_MVE);
-OPAL_CALL(opal_pci_set_mve_enable,		OPAL_PCI_SET_MVE_ENABLE);
-OPAL_CALL(opal_pci_get_xive_reissue,		OPAL_PCI_GET_XIVE_REISSUE);
-OPAL_CALL(opal_pci_set_xive_reissue,		OPAL_PCI_SET_XIVE_REISSUE);
-OPAL_CALL(opal_pci_set_xive_pe,			OPAL_PCI_SET_XIVE_PE);
-OPAL_CALL(opal_get_xive_source,			OPAL_GET_XIVE_SOURCE);
-OPAL_CALL(opal_get_msi_32,			OPAL_GET_MSI_32);
-OPAL_CALL(opal_get_msi_64,			OPAL_GET_MSI_64);
-OPAL_CALL(opal_start_cpu,			OPAL_START_CPU);
-OPAL_CALL(opal_query_cpu_status,		OPAL_QUERY_CPU_STATUS);
-OPAL_CALL(opal_write_oppanel,			OPAL_WRITE_OPPANEL);
-OPAL_CALL(opal_pci_map_pe_dma_window,		OPAL_PCI_MAP_PE_DMA_WINDOW);
-OPAL_CALL(opal_pci_map_pe_dma_window_real,	OPAL_PCI_MAP_PE_DMA_WINDOW_REAL);
-OPAL_CALL(opal_pci_reset,			OPAL_PCI_RESET);
-OPAL_CALL(opal_pci_get_hub_diag_data,		OPAL_PCI_GET_HUB_DIAG_DATA);
-OPAL_CALL(opal_pci_get_phb_diag_data,		OPAL_PCI_GET_PHB_DIAG_DATA);
-OPAL_CALL(opal_pci_fence_phb,			OPAL_PCI_FENCE_PHB);
-OPAL_CALL(opal_pci_reinit,			OPAL_PCI_REINIT);
-OPAL_CALL(opal_pci_mask_pe_error,		OPAL_PCI_MASK_PE_ERROR);
-OPAL_CALL(opal_set_slot_led_status,		OPAL_SET_SLOT_LED_STATUS);
-OPAL_CALL(opal_get_epow_status,			OPAL_GET_EPOW_STATUS);
-OPAL_CALL(opal_get_dpo_status,			OPAL_GET_DPO_STATUS);
-OPAL_CALL(opal_set_system_attention_led,	OPAL_SET_SYSTEM_ATTENTION_LED);
-OPAL_CALL(opal_pci_next_error,			OPAL_PCI_NEXT_ERROR);
-OPAL_CALL(opal_pci_poll,			OPAL_PCI_POLL);
-OPAL_CALL(opal_pci_msi_eoi,			OPAL_PCI_MSI_EOI);
-OPAL_CALL(opal_pci_get_phb_diag_data2,		OPAL_PCI_GET_PHB_DIAG_DATA2);
-OPAL_CALL(opal_xscom_read,			OPAL_XSCOM_READ);
-OPAL_CALL(opal_xscom_write,			OPAL_XSCOM_WRITE);
-OPAL_CALL(opal_lpc_read,			OPAL_LPC_READ);
-OPAL_CALL(opal_lpc_write,			OPAL_LPC_WRITE);
-OPAL_CALL(opal_return_cpu,			OPAL_RETURN_CPU);
-OPAL_CALL(opal_reinit_cpus,			OPAL_REINIT_CPUS);
-OPAL_CALL(opal_read_elog,			OPAL_ELOG_READ);
-OPAL_CALL(opal_send_ack_elog,			OPAL_ELOG_ACK);
-OPAL_CALL(opal_get_elog_size,			OPAL_ELOG_SIZE);
-OPAL_CALL(opal_resend_pending_logs,		OPAL_ELOG_RESEND);
-OPAL_CALL(opal_write_elog,			OPAL_ELOG_WRITE);
-OPAL_CALL(opal_validate_flash,			OPAL_FLASH_VALIDATE);
-OPAL_CALL(opal_manage_flash,			OPAL_FLASH_MANAGE);
-OPAL_CALL(opal_update_flash,			OPAL_FLASH_UPDATE);
-OPAL_CALL(opal_resync_timebase,			OPAL_RESYNC_TIMEBASE);
-OPAL_CALL(opal_check_token,			OPAL_CHECK_TOKEN);
-OPAL_CALL(opal_dump_init,			OPAL_DUMP_INIT);
-OPAL_CALL(opal_dump_info,			OPAL_DUMP_INFO);
-OPAL_CALL(opal_dump_info2,			OPAL_DUMP_INFO2);
-OPAL_CALL(opal_dump_read,			OPAL_DUMP_READ);
-OPAL_CALL(opal_dump_ack,			OPAL_DUMP_ACK);
-OPAL_CALL(opal_get_msg,				OPAL_GET_MSG);
-OPAL_CALL(opal_write_oppanel_async,		OPAL_WRITE_OPPANEL_ASYNC);
-OPAL_CALL(opal_check_completion,		OPAL_CHECK_ASYNC_COMPLETION);
-OPAL_CALL(opal_dump_resend_notification,	OPAL_DUMP_RESEND);
-OPAL_CALL(opal_sync_host_reboot,		OPAL_SYNC_HOST_REBOOT);
-OPAL_CALL(opal_sensor_read,			OPAL_SENSOR_READ);
-OPAL_CALL(opal_get_param,			OPAL_GET_PARAM);
-OPAL_CALL(opal_set_param,			OPAL_SET_PARAM);
-OPAL_CALL(opal_handle_hmi,			OPAL_HANDLE_HMI);
-OPAL_CALL(opal_config_cpu_idle_state,		OPAL_CONFIG_CPU_IDLE_STATE);
-OPAL_CALL(opal_slw_set_reg,			OPAL_SLW_SET_REG);
-OPAL_CALL(opal_register_dump_region,		OPAL_REGISTER_DUMP_REGION);
-OPAL_CALL(opal_unregister_dump_region,		OPAL_UNREGISTER_DUMP_REGION);
-OPAL_CALL(opal_pci_set_phb_cxl_mode,		OPAL_PCI_SET_PHB_CAPI_MODE);
-OPAL_CALL(opal_tpo_write,			OPAL_WRITE_TPO);
-OPAL_CALL(opal_tpo_read,			OPAL_READ_TPO);
-OPAL_CALL(opal_ipmi_send,			OPAL_IPMI_SEND);
-OPAL_CALL(opal_ipmi_recv,			OPAL_IPMI_RECV);
-OPAL_CALL(opal_i2c_request,			OPAL_I2C_REQUEST);
-OPAL_CALL(opal_flash_read,			OPAL_FLASH_READ);
-OPAL_CALL(opal_flash_write,			OPAL_FLASH_WRITE);
-OPAL_CALL(opal_flash_erase,			OPAL_FLASH_ERASE);
-OPAL_CALL(opal_prd_msg,				OPAL_PRD_MSG);
-OPAL_CALL(opal_leds_get_ind,			OPAL_LEDS_GET_INDICATOR);
-OPAL_CALL(opal_leds_set_ind,			OPAL_LEDS_SET_INDICATOR);
-OPAL_CALL(opal_console_flush,			OPAL_CONSOLE_FLUSH);
-OPAL_CALL(opal_get_device_tree,			OPAL_GET_DEVICE_TREE);
-OPAL_CALL(opal_pci_get_presence_state,		OPAL_PCI_GET_PRESENCE_STATE);
-OPAL_CALL(opal_pci_get_power_state,		OPAL_PCI_GET_POWER_STATE);
-OPAL_CALL(opal_pci_set_power_state,		OPAL_PCI_SET_POWER_STATE);
-OPAL_CALL(opal_int_get_xirr,			OPAL_INT_GET_XIRR);
-OPAL_CALL(opal_int_set_cppr,			OPAL_INT_SET_CPPR);
-OPAL_CALL(opal_int_eoi,				OPAL_INT_EOI);
-OPAL_CALL(opal_int_set_mfrr,			OPAL_INT_SET_MFRR);
-OPAL_CALL(opal_pci_tce_kill,			OPAL_PCI_TCE_KILL);
-OPAL_CALL(opal_nmmu_set_ptcr,			OPAL_NMMU_SET_PTCR);
-OPAL_CALL(opal_xive_reset,			OPAL_XIVE_RESET);
-OPAL_CALL(opal_xive_get_irq_info,		OPAL_XIVE_GET_IRQ_INFO);
-OPAL_CALL(opal_xive_get_irq_config,		OPAL_XIVE_GET_IRQ_CONFIG);
-OPAL_CALL(opal_xive_set_irq_config,		OPAL_XIVE_SET_IRQ_CONFIG);
-OPAL_CALL(opal_xive_get_queue_info,		OPAL_XIVE_GET_QUEUE_INFO);
-OPAL_CALL(opal_xive_set_queue_info,		OPAL_XIVE_SET_QUEUE_INFO);
-OPAL_CALL(opal_xive_donate_page,		OPAL_XIVE_DONATE_PAGE);
-OPAL_CALL(opal_xive_alloc_vp_block,		OPAL_XIVE_ALLOCATE_VP_BLOCK);
-OPAL_CALL(opal_xive_free_vp_block,		OPAL_XIVE_FREE_VP_BLOCK);
-OPAL_CALL(opal_xive_allocate_irq,		OPAL_XIVE_ALLOCATE_IRQ);
-OPAL_CALL(opal_xive_free_irq,			OPAL_XIVE_FREE_IRQ);
-OPAL_CALL(opal_xive_get_vp_info,		OPAL_XIVE_GET_VP_INFO);
-OPAL_CALL(opal_xive_set_vp_info,		OPAL_XIVE_SET_VP_INFO);
-OPAL_CALL(opal_xive_sync,			OPAL_XIVE_SYNC);
-OPAL_CALL(opal_xive_dump,			OPAL_XIVE_DUMP);
-OPAL_CALL(opal_signal_system_reset,		OPAL_SIGNAL_SYSTEM_RESET);
-OPAL_CALL(opal_npu_init_context,		OPAL_NPU_INIT_CONTEXT);
-OPAL_CALL(opal_npu_destroy_context,		OPAL_NPU_DESTROY_CONTEXT);
-OPAL_CALL(opal_npu_map_lpar,			OPAL_NPU_MAP_LPAR);
-OPAL_CALL(opal_imc_counters_init,		OPAL_IMC_COUNTERS_INIT);
-OPAL_CALL(opal_imc_counters_start,		OPAL_IMC_COUNTERS_START);
-OPAL_CALL(opal_imc_counters_stop,		OPAL_IMC_COUNTERS_STOP);
-OPAL_CALL(opal_pci_set_p2p,			OPAL_PCI_SET_P2P);
-OPAL_CALL(opal_get_powercap,			OPAL_GET_POWERCAP);
-OPAL_CALL(opal_set_powercap,			OPAL_SET_POWERCAP);
-OPAL_CALL(opal_get_power_shift_ratio,		OPAL_GET_POWER_SHIFT_RATIO);
-OPAL_CALL(opal_set_power_shift_ratio,		OPAL_SET_POWER_SHIFT_RATIO);
-OPAL_CALL(opal_sensor_group_clear,		OPAL_SENSOR_GROUP_CLEAR);
-OPAL_CALL(opal_quiesce,				OPAL_QUIESCE);
-OPAL_CALL(opal_npu_spa_setup,			OPAL_NPU_SPA_SETUP);
-OPAL_CALL(opal_npu_spa_clear_cache,		OPAL_NPU_SPA_CLEAR_CACHE);
-OPAL_CALL(opal_npu_tl_set,			OPAL_NPU_TL_SET);
-OPAL_CALL(opal_pci_get_pbcq_tunnel_bar,		OPAL_PCI_GET_PBCQ_TUNNEL_BAR);
-OPAL_CALL(opal_pci_set_pbcq_tunnel_bar,		OPAL_PCI_SET_PBCQ_TUNNEL_BAR);
-OPAL_CALL(opal_sensor_read_u64,			OPAL_SENSOR_READ_U64);
-OPAL_CALL(opal_sensor_group_enable,		OPAL_SENSOR_GROUP_ENABLE);
-OPAL_CALL(opal_nx_coproc_init,			OPAL_NX_COPROC_INIT);