diff options
Diffstat (limited to 'arch/powerpc/platforms/powernv')
-rw-r--r-- | arch/powerpc/platforms/powernv/Kconfig | 16 | ||||
-rw-r--r-- | arch/powerpc/platforms/powernv/Makefile | 5 | ||||
-rw-r--r-- | arch/powerpc/platforms/powernv/opal-nvram.c | 88 | ||||
-rw-r--r-- | arch/powerpc/platforms/powernv/opal-rtc.c | 97 | ||||
-rw-r--r-- | arch/powerpc/platforms/powernv/opal-takeover.S | 140 | ||||
-rw-r--r-- | arch/powerpc/platforms/powernv/opal-wrappers.S | 101 | ||||
-rw-r--r-- | arch/powerpc/platforms/powernv/opal.c | 322 | ||||
-rw-r--r-- | arch/powerpc/platforms/powernv/pci-p5ioc2.c | 234 | ||||
-rw-r--r-- | arch/powerpc/platforms/powernv/pci.c | 427 | ||||
-rw-r--r-- | arch/powerpc/platforms/powernv/pci.h | 48 | ||||
-rw-r--r-- | arch/powerpc/platforms/powernv/powernv.h | 16 | ||||
-rw-r--r-- | arch/powerpc/platforms/powernv/setup.c | 196 | ||||
-rw-r--r-- | arch/powerpc/platforms/powernv/smp.c | 182 |
13 files changed, 1872 insertions, 0 deletions
diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig new file mode 100644 index 00000000000..74fea5c2183 --- /dev/null +++ b/arch/powerpc/platforms/powernv/Kconfig @@ -0,0 +1,16 @@ +config PPC_POWERNV + depends on PPC64 && PPC_BOOK3S + bool "IBM PowerNV (Non-Virtualized) platform support" + select PPC_NATIVE + select PPC_XICS + select PPC_ICP_NATIVE + select PPC_P7_NAP + select PPC_PCI_CHOICE if EMBEDDED + default y + +config PPC_POWERNV_RTAS + depends on PPC_POWERNV + bool "Support for RTAS based PowerNV platforms such as BML" + default y + select PPC_ICS_RTAS + select PPC_RTAS diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile new file mode 100644 index 00000000000..31853008b41 --- /dev/null +++ b/arch/powerpc/platforms/powernv/Makefile @@ -0,0 +1,5 @@ +obj-y += setup.o opal-takeover.o opal-wrappers.o opal.o +obj-y += opal-rtc.o opal-nvram.o + +obj-$(CONFIG_SMP) += smp.o +obj-$(CONFIG_PCI) += pci.o pci-p5ioc2.o diff --git a/arch/powerpc/platforms/powernv/opal-nvram.c b/arch/powerpc/platforms/powernv/opal-nvram.c new file mode 100644 index 00000000000..3f83e1ae26a --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-nvram.c @@ -0,0 +1,88 @@ +/* + * PowerNV nvram code. + * + * Copyright 2011 IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#define DEBUG + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/of.h> + +#include <asm/opal.h> +#include <asm/machdep.h> + +static unsigned int nvram_size; + +static ssize_t opal_nvram_size(void) +{ + return nvram_size; +} + +static ssize_t opal_nvram_read(char *buf, size_t count, loff_t *index) +{ + s64 rc; + int off; + + if (*index >= nvram_size) + return 0; + off = *index; + if ((off + count) > nvram_size) + count = nvram_size - off; + rc = opal_read_nvram(__pa(buf), count, off); + if (rc != OPAL_SUCCESS) + return -EIO; + *index += count; + return count; +} + +static ssize_t opal_nvram_write(char *buf, size_t count, loff_t *index) +{ + s64 rc = OPAL_BUSY; + int off; + + if (*index >= nvram_size) + return 0; + off = *index; + if ((off + count) > nvram_size) + count = nvram_size - off; + + while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { + rc = opal_write_nvram(__pa(buf), count, off); + if (rc == OPAL_BUSY_EVENT) + opal_poll_events(NULL); + } + *index += count; + return count; +} + +void __init opal_nvram_init(void) +{ + struct device_node *np; + const u32 *nbytes_p; + + np = of_find_compatible_node(NULL, NULL, "ibm,opal-nvram"); + if (np == NULL) + return; + + nbytes_p = of_get_property(np, "#bytes", NULL); + if (!nbytes_p) { + of_node_put(np); + return; + } + nvram_size = *nbytes_p; + + printk(KERN_INFO "OPAL nvram setup, %u bytes\n", nvram_size); + of_node_put(np); + + ppc_md.nvram_read = opal_nvram_read; + ppc_md.nvram_write = opal_nvram_write; + ppc_md.nvram_size = opal_nvram_size; +} + diff --git a/arch/powerpc/platforms/powernv/opal-rtc.c b/arch/powerpc/platforms/powernv/opal-rtc.c new file mode 100644 index 00000000000..2aa7641aac9 --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-rtc.c @@ -0,0 +1,97 @@ +/* + * PowerNV Real Time Clock. + * + * Copyright 2011 IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + + +#include <linux/kernel.h> +#include <linux/time.h> +#include <linux/bcd.h> +#include <linux/rtc.h> +#include <linux/delay.h> + +#include <asm/opal.h> +#include <asm/firmware.h> + +static void opal_to_tm(u32 y_m_d, u64 h_m_s_ms, struct rtc_time *tm) +{ + tm->tm_year = ((bcd2bin(y_m_d >> 24) * 100) + + bcd2bin((y_m_d >> 16) & 0xff)) - 1900; + tm->tm_mon = bcd2bin((y_m_d >> 8) & 0xff) - 1; + tm->tm_mday = bcd2bin(y_m_d & 0xff); + tm->tm_hour = bcd2bin((h_m_s_ms >> 56) & 0xff); + tm->tm_min = bcd2bin((h_m_s_ms >> 48) & 0xff); + tm->tm_sec = bcd2bin((h_m_s_ms >> 40) & 0xff); + + GregorianDay(tm); +} + +unsigned long __init opal_get_boot_time(void) +{ + struct rtc_time tm; + u32 y_m_d; + u64 h_m_s_ms; + long rc = OPAL_BUSY; + + while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { + rc = opal_rtc_read(&y_m_d, &h_m_s_ms); + if (rc == OPAL_BUSY_EVENT) + opal_poll_events(NULL); + else + mdelay(10); + } + if (rc != OPAL_SUCCESS) + return 0; + opal_to_tm(y_m_d, h_m_s_ms, &tm); + return mktime(tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday, + tm.tm_hour, tm.tm_min, tm.tm_sec); +} + +void opal_get_rtc_time(struct rtc_time *tm) +{ + long rc = OPAL_BUSY; + u32 y_m_d; + u64 h_m_s_ms; + + while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { + rc = opal_rtc_read(&y_m_d, &h_m_s_ms); + if (rc == OPAL_BUSY_EVENT) + opal_poll_events(NULL); + else + mdelay(10); + } + if (rc != OPAL_SUCCESS) + return; + opal_to_tm(y_m_d, h_m_s_ms, tm); +} + +int opal_set_rtc_time(struct rtc_time *tm) +{ + long rc = OPAL_BUSY; + u32 y_m_d = 0; + u64 h_m_s_ms = 0; + + y_m_d |= ((u32)bin2bcd((tm->tm_year + 1900) / 100)) << 24; + y_m_d |= ((u32)bin2bcd((tm->tm_year + 1900) % 100)) << 16; + y_m_d |= ((u32)bin2bcd((tm->tm_mon + 1))) << 8; + y_m_d |= ((u32)bin2bcd(tm->tm_mday)); + + h_m_s_ms |= ((u64)bin2bcd(tm->tm_hour)) << 56; + h_m_s_ms |= ((u64)bin2bcd(tm->tm_min)) << 48; + h_m_s_ms |= ((u64)bin2bcd(tm->tm_sec)) << 40; + + while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { + rc = opal_rtc_write(y_m_d, h_m_s_ms); + if (rc == OPAL_BUSY_EVENT) + opal_poll_events(NULL); + else + mdelay(10); + } + return rc == OPAL_SUCCESS ? 0 : -EIO; +} diff --git a/arch/powerpc/platforms/powernv/opal-takeover.S b/arch/powerpc/platforms/powernv/opal-takeover.S new file mode 100644 index 00000000000..77b48b2b930 --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-takeover.S @@ -0,0 +1,140 @@ +/* + * PowerNV OPAL takeover assembly code, for use by prom_init.c + * + * Copyright 2011 IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <asm/ppc_asm.h> +#include <asm/hvcall.h> +#include <asm/asm-offsets.h> +#include <asm/opal.h> + +#define STK_PARAM(i) (48 + ((i)-3)*8) + +#define H_HAL_TAKEOVER 0x5124 +#define H_HAL_TAKEOVER_QUERY_MAGIC -1 + + .text +_GLOBAL(opal_query_takeover) + mfcr r0 + stw r0,8(r1) + std r3,STK_PARAM(r3)(r1) + std r4,STK_PARAM(r4)(r1) + li r3,H_HAL_TAKEOVER + li r4,H_HAL_TAKEOVER_QUERY_MAGIC + HVSC + ld r10,STK_PARAM(r3)(r1) + std r4,0(r10) + ld r10,STK_PARAM(r4)(r1) + std r5,0(r10) + lwz r0,8(r1) + mtcrf 0xff,r0 + blr + +_GLOBAL(opal_do_takeover) + mfcr r0 + stw r0,8(r1) + mflr r0 + std r0,16(r1) + bl __opal_do_takeover + ld r0,16(r1) + mtlr r0 + lwz r0,8(r1) + mtcrf 0xff,r0 + blr + +__opal_do_takeover: + ld r4,0(r3) + ld r5,0x8(r3) + ld r6,0x10(r3) + ld r7,0x18(r3) + ld r8,0x20(r3) + ld r9,0x28(r3) + ld r10,0x30(r3) + ld r11,0x38(r3) + li r3,H_HAL_TAKEOVER + HVSC + blr + + .globl opal_secondary_entry +opal_secondary_entry: + mr r31,r3 + mfmsr r11 + li r12,(MSR_SF | MSR_ISF)@highest + sldi r12,r12,48 + or r11,r11,r12 + mtmsrd r11 + isync + mfspr r4,SPRN_PIR + std r4,0(r3) +1: HMT_LOW + ld r4,8(r3) + cmpli cr0,r4,0 + beq 1b + HMT_MEDIUM +1: addi r3,r31,16 + bl __opal_do_takeover + b 1b + +_GLOBAL(opal_enter_rtas) + mflr r0 + std r0,16(r1) + stdu r1,-PROM_FRAME_SIZE(r1) /* Save SP and create stack space */ + + /* Because PROM is running in 32b mode, it clobbers the high order half + * of all registers that it saves. We therefore save those registers + * PROM might touch to the stack. (r0, r3-r13 are caller saved) + */ + SAVE_GPR(2, r1) + SAVE_GPR(13, r1) + SAVE_8GPRS(14, r1) + SAVE_10GPRS(22, r1) + mfcr r10 + mfmsr r11 + std r10,_CCR(r1) + std r11,_MSR(r1) + + /* Get the PROM entrypoint */ + mtlr r5 + + /* Switch MSR to 32 bits mode + */ + li r12,1 + rldicr r12,r12,MSR_SF_LG,(63-MSR_SF_LG) + andc r11,r11,r12 + li r12,1 + rldicr r12,r12,MSR_ISF_LG,(63-MSR_ISF_LG) + andc r11,r11,r12 + mtmsrd r11 + isync + + /* Enter RTAS here... */ + blrl + + /* Just make sure that r1 top 32 bits didn't get + * corrupt by OF + */ + rldicl r1,r1,0,32 + + /* Restore the MSR (back to 64 bits) */ + ld r0,_MSR(r1) + MTMSRD(r0) + isync + + /* Restore other registers */ + REST_GPR(2, r1) + REST_GPR(13, r1) + REST_8GPRS(14, r1) + REST_10GPRS(22, r1) + ld r4,_CCR(r1) + mtcr r4 + + addi r1,r1,PROM_FRAME_SIZE + ld r0,16(r1) + mtlr r0 + blr diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S new file mode 100644 index 00000000000..4a3f46d8533 --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -0,0 +1,101 @@ +/* + * PowerNV OPAL API wrappers + * + * Copyright 2011 IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <asm/ppc_asm.h> +#include <asm/hvcall.h> +#include <asm/asm-offsets.h> +#include <asm/opal.h> + +/* TODO: + * + * - Trace irqs in/off (needs saving/restoring all args, argh...) + * - Get r11 feed up by Dave so I can have better register usage + */ +#define OPAL_CALL(name, token) \ + _GLOBAL(name); \ + mflr r0; \ + mfcr r12; \ + std r0,16(r1); \ + std r12,8(r1); \ + std r1,PACAR1(r13); \ + li r0,0; \ + mfmsr r12; \ + ori r0,r0,MSR_EE; \ + std r12,PACASAVEDMSR(r13); \ + andc r12,r12,r0; \ + mtmsrd r12,1; \ + LOAD_REG_ADDR(r0,.opal_return); \ + mtlr r0; \ + li r0,MSR_DR|MSR_IR; \ + andc r12,r12,r0; \ + li r0,token; \ + mtspr SPRN_HSRR1,r12; \ + LOAD_REG_ADDR(r11,opal); \ + ld r12,8(r11); \ + ld r2,0(r11); \ + mtspr SPRN_HSRR0,r12; \ + hrfid + +_STATIC(opal_return) + ld r2,PACATOC(r13); + ld r4,8(r1); + ld r5,16(r1); + ld r6,PACASAVEDMSR(r13); + mtspr SPRN_SRR0,r5; + mtspr SPRN_SRR1,r6; + mtcr r4; + rfid + +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_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_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); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c new file mode 100644 index 00000000000..aaa0dba4947 --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal.c @@ -0,0 +1,322 @@ +/* + * PowerNV OPAL high level interfaces + * + * Copyright 2011 IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#undef DEBUG + +#include <linux/types.h> +#include <linux/of.h> +#include <linux/of_platform.h> +#include <linux/interrupt.h> +#include <asm/opal.h> +#include <asm/firmware.h> + +#include "powernv.h" + +struct opal { + u64 base; + u64 entry; +} opal; + +static struct device_node *opal_node; +static DEFINE_SPINLOCK(opal_write_lock); +extern u64 opal_mc_secondary_handler[]; + +int __init early_init_dt_scan_opal(unsigned long node, + const char *uname, int depth, void *data) +{ + const void *basep, *entryp; + unsigned long basesz, entrysz; + u64 glue; + + if (depth != 1 || strcmp(uname, "ibm,opal") != 0) + return 0; + + basep = of_get_flat_dt_prop(node, "opal-base-address", &basesz); + entryp = of_get_flat_dt_prop(node, "opal-entry-address", &entrysz); + + if (!basep || !entryp) + return 1; + + opal.base = of_read_number(basep, basesz/4); + opal.entry = of_read_number(entryp, entrysz/4); + + pr_debug("OPAL Base = 0x%llx (basep=%p basesz=%ld)\n", + opal.base, basep, basesz); + pr_debug("OPAL Entry = 0x%llx (entryp=%p basesz=%ld)\n", + opal.entry, entryp, entrysz); + + powerpc_firmware_features |= FW_FEATURE_OPAL; + if (of_flat_dt_is_compatible(node, "ibm,opal-v2")) { + powerpc_firmware_features |= FW_FEATURE_OPALv2; + printk("OPAL V2 detected !\n"); + } else { + printk("OPAL V1 detected !\n"); + } + + /* Hookup some exception handlers. We use the fwnmi area at 0x7000 + * to provide the glue space to OPAL + */ + glue = 0x7000; + opal_register_exception_handler(OPAL_MACHINE_CHECK_HANDLER, + __pa(opal_mc_secondary_handler[0]), + glue); + glue += 128; + opal_register_exception_handler(OPAL_HYPERVISOR_MAINTENANCE_HANDLER, + 0, glue); + glue += 128; + opal_register_exception_handler(OPAL_SOFTPATCH_HANDLER, 0, glue); + + return 1; +} + +int opal_get_chars(uint32_t vtermno, char *buf, int count) +{ + s64 len, rc; + u64 evt; + + if (!opal.entry) + return -ENODEV; + opal_poll_events(&evt); + if ((evt & OPAL_EVENT_CONSOLE_INPUT) == 0) + return 0; + len = count; + rc = opal_console_read(vtermno, &len, buf); + if (rc == OPAL_SUCCESS) + return len; + return 0; +} + +int opal_put_chars(uint32_t vtermno, const char *data, int total_len) +{ + int written = 0; + s64 len, rc; + unsigned long flags; + u64 evt; + + if (!opal.entry) + return -ENODEV; + + /* We want put_chars to be atomic to avoid mangling of hvsi + * packets. To do that, we first test for room and return + * -EAGAIN if there isn't enough. + * + * Unfortunately, opal_console_write_buffer_space() doesn't + * appear to work on opal v1, so we just assume there is + * enough room and be done with it + */ + spin_lock_irqsave(&opal_write_lock, flags); + if (firmware_has_feature(FW_FEATURE_OPALv2)) { + rc = opal_console_write_buffer_space(vtermno, &len); + if (rc || len < total_len) { + spin_unlock_irqrestore(&opal_write_lock, flags); + /* Closed -> drop characters */ + if (rc) + return total_len; + opal_poll_events(&evt); + return -EAGAIN; + } + } + + /* We still try to handle partial completions, though they + * should no longer happen. + */ + rc = OPAL_BUSY; + while(total_len > 0 && (rc == OPAL_BUSY || + rc == OPAL_BUSY_EVENT || rc == OPAL_SUCCESS)) { + len = total_len; + rc = opal_console_write(vtermno, &len, data); + if (rc == OPAL_SUCCESS) { + total_len -= len; + data += len; + written += len; + } + /* This is a bit nasty but we need that for the console to + * flush when there aren't any interrupts. We will clean + * things a bit later to limit that to synchronous path + * such as the kernel console and xmon/udbg + */ + do + opal_poll_events(&evt); + while(rc == OPAL_SUCCESS && (evt & OPAL_EVENT_CONSOLE_OUTPUT)); + } + spin_unlock_irqrestore(&opal_write_lock, flags); + return written; +} + +int opal_machine_check(struct pt_regs *regs) +{ + struct opal_machine_check_event *opal_evt = get_paca()->opal_mc_evt; + struct opal_machine_check_event evt; + const char *level, *sevstr, *subtype; + static const char *opal_mc_ue_types[] = { + "Indeterminate", + "Instruction fetch", + "Page table walk ifetch", + "Load/Store", + "Page table walk Load/Store", + }; + static const char *opal_mc_slb_types[] = { + "Indeterminate", + "Parity", + "Multihit", + }; + static const char *opal_mc_erat_types[] = { + "Indeterminate", + "Parity", + "Multihit", + }; + static const char *opal_mc_tlb_types[] = { + "Indeterminate", + "Parity", + "Multihit", + }; + + /* Copy the event structure and release the original */ + evt = *opal_evt; + opal_evt->in_use = 0; + + /* Print things out */ + if (evt.version != OpalMCE_V1) { + pr_err("Machine Check Exception, Unknown event version %d !\n", + evt.version); + return 0; + } + switch(evt.severity) { + case OpalMCE_SEV_NO_ERROR: + level = KERN_INFO; + sevstr = "Harmless"; + break; + case OpalMCE_SEV_WARNING: + level = KERN_WARNING; + sevstr = ""; + break; + case OpalMCE_SEV_ERROR_SYNC: + level = KERN_ERR; + sevstr = "Severe"; + break; + case OpalMCE_SEV_FATAL: + default: + level = KERN_ERR; + sevstr = "Fatal"; + break; + } + + printk("%s%s Machine check interrupt [%s]\n", level, sevstr, + evt.disposition == OpalMCE_DISPOSITION_RECOVERED ? + "Recovered" : "[Not recovered"); + printk("%s Initiator: %s\n", level, + evt.initiator == OpalMCE_INITIATOR_CPU ? "CPU" : "Unknown"); + switch(evt.error_type) { + case OpalMCE_ERROR_TYPE_UE: + subtype = evt.u.ue_error.ue_error_type < + ARRAY_SIZE(opal_mc_ue_types) ? + opal_mc_ue_types[evt.u.ue_error.ue_error_type] + : "Unknown"; + printk("%s Error type: UE [%s]\n", level, subtype); + if (evt.u.ue_error.effective_address_provided) + printk("%s Effective address: %016llx\n", + level, evt.u.ue_error.effective_address); + if (evt.u.ue_error.physical_address_provided) + printk("%s Physial address: %016llx\n", + level, evt.u.ue_error.physical_address); + break; + case OpalMCE_ERROR_TYPE_SLB: + subtype = evt.u.slb_error.slb_error_type < + ARRAY_SIZE(opal_mc_slb_types) ? + opal_mc_slb_types[evt.u.slb_error.slb_error_type] + : "Unknown"; + printk("%s Error type: SLB [%s]\n", level, subtype); + if (evt.u.slb_error.effective_address_provided) + printk("%s Effective address: %016llx\n", + level, evt.u.slb_error.effective_address); + break; + case OpalMCE_ERROR_TYPE_ERAT: + subtype = evt.u.erat_error.erat_error_type < + ARRAY_SIZE(opal_mc_erat_types) ? + opal_mc_erat_types[evt.u.erat_error.erat_error_type] + : "Unknown"; + printk("%s Error type: ERAT [%s]\n", level, subtype); + if (evt.u.erat_error.effective_address_provided) + printk("%s Effective address: %016llx\n", + level, evt.u.erat_error.effective_address); + break; + case OpalMCE_ERROR_TYPE_TLB: + subtype = evt.u.tlb_error.tlb_error_type < + ARRAY_SIZE(opal_mc_tlb_types) ? + opal_mc_tlb_types[evt.u.tlb_error.tlb_error_type] + : "Unknown"; + printk("%s Error type: TLB [%s]\n", level, subtype); + if (evt.u.tlb_error.effective_address_provided) + printk("%s Effective address: %016llx\n", + level, evt.u.tlb_error.effective_address); + break; + default: + case OpalMCE_ERROR_TYPE_UNKNOWN: + printk("%s Error type: Unknown\n", level); + break; + } + return evt.severity == OpalMCE_SEV_FATAL ? 0 : 1; +} + +static irqreturn_t opal_interrupt(int irq, void *data) +{ + uint64_t events; + + opal_handle_interrupt(virq_to_hw(irq), &events); + + /* XXX TODO: Do something with the events */ + + return IRQ_HANDLED; +} + +static int __init opal_init(void) +{ + struct device_node *np, *consoles; + const u32 *irqs; + int rc, i, irqlen; + + opal_node = of_find_node_by_path("/ibm,opal"); + if (!opal_node) { + pr_warn("opal: Node not found\n"); + return -ENODEV; + } + if (firmware_has_feature(FW_FEATURE_OPALv2)) + consoles = of_find_node_by_path("/ibm,opal/consoles"); + else + consoles = of_node_get(opal_node); + + /* Register serial ports */ + for_each_child_of_node(consoles, np) { + if (strcmp(np->name, "serial")) + continue; + of_platform_device_create(np, NULL, NULL); + } + of_node_put(consoles); + + /* Find all OPAL interrupts and request them */ + irqs = of_get_property(opal_node, "opal-interrupts", &irqlen); + pr_debug("opal: Found %d interrupts reserved for OPAL\n", + irqs ? (irqlen / 4) : 0); + for (i = 0; irqs && i < (irqlen / 4); i++, irqs++) { + unsigned int hwirq = be32_to_cpup(irqs); + unsigned int irq = irq_create_mapping(NULL, hwirq); + if (irq == NO_IRQ) { + pr_warning("opal: Failed to map irq 0x%x\n", hwirq); + continue; + } + rc = request_irq(irq, opal_interrupt, 0, "opal", NULL); + if (rc) + pr_warning("opal: Error %d requesting irq %d" + " (0x%x)\n", rc, irq, hwirq); + } + return 0; +} +subsys_initcall(opal_init); diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c new file mode 100644 index 00000000000..4c80f7c77d5 --- /dev/null +++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c @@ -0,0 +1,234 @@ +/* + * Support PCI/PCIe on PowerNV platforms + * + * Currently supports only P5IOC2 + * + * Copyright 2011 Benjamin Herrenschmidt, IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/pci.h> +#include <linux/delay.h> +#include <linux/string.h> +#include <linux/init.h> +#include <linux/bootmem.h> +#include <linux/irq.h> +#include <linux/io.h> +#include <linux/msi.h> + +#include <asm/sections.h> +#include <asm/io.h> +#include <asm/prom.h> +#include <asm/pci-bridge.h> +#include <asm/machdep.h> +#include <asm/ppc-pci.h> +#include <asm/opal.h> +#include <asm/iommu.h> +#include <asm/tce.h> +#include <asm/abs_addr.h> + +#include "powernv.h" +#include "pci.h" + +/* For now, use a fixed amount of TCE memory for each p5ioc2 + * hub, 16M will do + */ +#define P5IOC2_TCE_MEMORY 0x01000000 + +#ifdef CONFIG_PCI_MSI +static int pnv_pci_p5ioc2_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, + unsigned int hwirq, unsigned int is_64, + struct msi_msg *msg) +{ + if (WARN_ON(!is_64)) + return -ENXIO; + msg->data = hwirq - phb->msi_base; + msg->address_hi = 0x10000000; + msg->address_lo = 0; + + return 0; +} + +static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) +{ + unsigned int bmap_size; + const __be32 *prop = of_get_property(phb->hose->dn, + "ibm,opal-msi-ranges", NULL); + if (!prop) + return; + + /* Don't do MSI's on p5ioc2 PCI-X are they are not properly + * verified in HW + */ + if (of_device_is_compatible(phb->hose->dn, "ibm,p5ioc2-pcix")) + return; + phb->msi_base = be32_to_cpup(prop); + phb->msi_count = be32_to_cpup(prop + 1); + bmap_size = BITS_TO_LONGS(phb->msi_count) * sizeof(unsigned long); + phb->msi_map = zalloc_maybe_bootmem(bmap_size, GFP_KERNEL); + if (!phb->msi_map) { + pr_err("PCI %d: Failed to allocate MSI bitmap !\n", + phb->hose->global_number); + return; + } + phb->msi_setup = pnv_pci_p5ioc2_msi_setup; + phb->msi32_support = 0; + pr_info(" Allocated bitmap for %d MSIs (base IRQ 0x%x)\n", + phb->msi_count, phb->msi_base); +} +#else +static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) { } +#endif /* CONFIG_PCI_MSI */ + +static void __devinit pnv_pci_p5ioc2_dma_dev_setup(struct pnv_phb *phb, + struct pci_dev *pdev) +{ + if (phb->p5ioc2.iommu_table.it_map == NULL) + iommu_init_table(&phb->p5ioc2.iommu_table, phb->hose->node); + + set_iommu_table_base(&pdev->dev, &phb->p5ioc2.iommu_table); +} + +static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, + void *tce_mem, u64 tce_size) +{ + struct pnv_phb *phb; + const u64 *prop64; + u64 phb_id; + int64_t rc; + static int primary = 1; + + pr_info(" Initializing p5ioc2 PHB %s\n", np->full_name); + + prop64 = of_get_property(np, "ibm,opal-phbid", NULL); + if (!prop64) { + pr_err(" Missing \"ibm,opal-phbid\" property !\n"); + return; + } + phb_id = be64_to_cpup(prop64); + pr_devel(" PHB-ID : 0x%016llx\n", phb_id); + pr_devel(" TCE AT : 0x%016lx\n", __pa(tce_mem)); + pr_devel(" TCE SZ : 0x%016llx\n", tce_size); + + rc = opal_pci_set_phb_tce_memory(phb_id, __pa(tce_mem), tce_size); + if (rc != OPAL_SUCCESS) { + pr_err(" Failed to set TCE memory, OPAL error %lld\n", rc); + return; + } + + phb = alloc_bootmem(sizeof(struct pnv_phb)); + if (phb) { + memset(phb, 0, sizeof(struct pnv_phb)); + phb->hose = pcibios_alloc_controller(np); + } + if (!phb || !phb->hose) { + pr_err(" Failed to allocate PCI controller\n"); + return; + } + + spin_lock_init(&phb->lock); + phb->hose->first_busno = 0; + phb->hose->last_busno = 0xff; + phb->hose->private_data = phb; + phb->opal_id = phb_id; + phb->type = PNV_PHB_P5IOC2; + + phb->regs = of_iomap(np, 0); + + if (phb->regs == NULL) + pr_err(" Failed to map registers !\n"); + else { + pr_devel(" P_BUID = 0x%08x\n", in_be32(phb->regs + 0x100)); + pr_devel(" P_IOSZ = 0x%08x\n", in_be32(phb->regs + 0x1b0)); + pr_devel(" P_IO_ST = 0x%08x\n", in_be32(phb->regs + 0x1e0)); + pr_devel(" P_MEM1_H = 0x%08x\n", in_be32(phb->regs + 0x1a0)); + pr_devel(" P_MEM1_L = 0x%08x\n", in_be32(phb->regs + 0x190)); + pr_devel(" P_MSZ1_L = 0x%08x\n", in_be32(phb->regs + 0x1c0)); + pr_devel(" P_MEM_ST = 0x%08x\n", in_be32(phb->regs + 0x1d0)); + pr_devel(" P_MEM2_H = 0x%08x\n", in_be32(phb->regs + 0x2c0)); + pr_devel(" P_MEM2_L = 0x%08x\n", in_be32(phb->regs + 0x2b0)); + pr_devel(" P_MSZ2_H = 0x%08x\n", in_be32(phb->regs + 0x2d0)); + pr_devel(" P_MSZ2_L = 0x%08x\n", in_be32(phb->regs + 0x2e0)); + } + + /* Interpret the "ranges" property */ + /* This also maps the I/O region and sets isa_io/mem_base */ + pci_process_bridge_OF_ranges(phb->hose, np, primary); + primary = 0; + + phb->hose->ops = &pnv_pci_ops; + + /* Setup MSI support */ + pnv_pci_init_p5ioc2_msis(phb); + + /* Setup TCEs */ + phb->dma_dev_setup = pnv_pci_p5ioc2_dma_dev_setup; + pnv_pci_setup_iommu_table(&phb->p5ioc2.iommu_table, + tce_mem, tce_size, 0); +} + +void __init pnv_pci_init_p5ioc2_hub(struct device_node *np) +{ + struct device_node *phbn; + const u64 *prop64; + u64 hub_id; + void *tce_mem; + uint64_t tce_per_phb; + int64_t rc; + int phb_count = 0; + + pr_info("Probing p5ioc2 IO-Hub %s\n", np->full_name); + + prop64 = of_get_property(np, "ibm,opal-hubid", NULL); + if (!prop64) { + pr_err(" Missing \"ibm,opal-hubid\" property !\n"); + return; + } + hub_id = be64_to_cpup(prop64); + pr_info(" HUB-ID : 0x%016llx\n", hub_id); + + /* Currently allocate 16M of TCE memory for every Hub + * + * XXX TODO: Make it chip local if possible + */ + tce_mem = __alloc_bootmem(P5IOC2_TCE_MEMORY, P5IOC2_TCE_MEMORY, + __pa(MAX_DMA_ADDRESS)); + if (!tce_mem) { + pr_err(" Failed to allocate TCE Memory !\n"); + return; + } + pr_debug(" TCE : 0x%016lx..0x%016lx\n", + __pa(tce_mem), __pa(tce_mem) + P5IOC2_TCE_MEMORY - 1); + rc = opal_pci_set_hub_tce_memory(hub_id, __pa(tce_mem), + P5IOC2_TCE_MEMORY); + if (rc != OPAL_SUCCESS) { + pr_err(" Failed to allocate TCE memory, OPAL error %lld\n", rc); + return; + } + + /* Count child PHBs */ + for_each_child_of_node(np, phbn) { + if (of_device_is_compatible(phbn, "ibm,p5ioc2-pcix") || + of_device_is_compatible(phbn, "ibm,p5ioc2-pciex")) + phb_count++; + } + + /* Calculate how much TCE space we can give per PHB */ + tce_per_phb = __rounddown_pow_of_two(P5IOC2_TCE_MEMORY / phb_count); + pr_info(" Allocating %lld MB of TCE memory per PHB\n", + tce_per_phb >> 20); + + /* Initialize PHBs */ + for_each_child_of_node(np, phbn) { + if (of_device_is_compatible(phbn, "ibm,p5ioc2-pcix") || + of_device_is_compatible(phbn, "ibm,p5ioc2-pciex")) { + pnv_pci_init_p5ioc2_phb(phbn, tce_mem, tce_per_phb); + tce_mem += tce_per_phb; + } + } +} diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c new file mode 100644 index 00000000000..85bb66d7f93 --- /dev/null +++ b/arch/powerpc/platforms/powernv/pci.c @@ -0,0 +1,427 @@ +/* + * Support PCI/PCIe on PowerNV platforms + * + * Currently supports only P5IOC2 + * + * Copyright 2011 Benjamin Herrenschmidt, IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/pci.h> +#include <linux/delay.h> +#include <linux/string.h> +#include <linux/init.h> +#include <linux/bootmem.h> +#include <linux/irq.h> +#include <linux/io.h> +#include <linux/msi.h> + +#include <asm/sections.h> +#include <asm/io.h> +#include <asm/prom.h> +#include <asm/pci-bridge.h> +#include <asm/machdep.h> +#include <asm/ppc-pci.h> +#include <asm/opal.h> +#include <asm/iommu.h> +#include <asm/tce.h> +#include <asm/abs_addr.h> + +#include "powernv.h" +#include "pci.h" + +/* Delay in usec */ +#define PCI_RESET_DELAY_US 3000000 + +#define cfg_dbg(fmt...) do { } while(0) +//#define cfg_dbg(fmt...) printk(fmt) + +#ifdef CONFIG_PCI_MSI +static int pnv_msi_check_device(struct pci_dev* pdev, int nvec, int type) +{ + struct pci_controller *hose = pci_bus_to_host(pdev->bus); + struct pnv_phb *phb = hose->private_data; + + return (phb && phb->msi_map) ? 0 : -ENODEV; +} + +static unsigned int pnv_get_one_msi(struct pnv_phb *phb) +{ + unsigned int id; + + spin_lock(&phb->lock); + id = find_next_zero_bit(phb->msi_map, phb->msi_count, phb->msi_next); + if (id >= phb->msi_count && phb->msi_next) + id = find_next_zero_bit(phb->msi_map, phb->msi_count, 0); + if (id >= phb->msi_count) { + spin_unlock(&phb->lock); + return 0; + } + __set_bit(id, phb->msi_map); + spin_unlock(&phb->lock); + return id + phb->msi_base; +} + +static void pnv_put_msi(struct pnv_phb *phb, unsigned int hwirq) +{ + unsigned int id; + + if (WARN_ON(hwirq < phb->msi_base || + hwirq >= (phb->msi_base + phb->msi_count))) + return; + id = hwirq - phb->msi_base; + spin_lock(&phb->lock); + __clear_bit(id, phb->msi_map); + spin_unlock(&phb->lock); +} + +static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) +{ + struct pci_controller *hose = pci_bus_to_host(pdev->bus); + struct pnv_phb *phb = hose->private_data; + struct msi_desc *entry; + struct msi_msg msg; + unsigned int hwirq, virq; + int rc; + + if (WARN_ON(!phb)) + return -ENODEV; + + list_for_each_entry(entry, &pdev->msi_list, list) { + if (!entry->msi_attrib.is_64 && !phb->msi32_support) { + pr_warn("%s: Supports only 64-bit MSIs\n", + pci_name(pdev)); + return -ENXIO; + } + hwirq = pnv_get_one_msi(phb); + if (!hwirq) { + pr_warn("%s: Failed to find a free MSI\n", + pci_name(pdev)); + return -ENOSPC; + } + virq = irq_create_mapping(NULL, hwirq); + if (virq == NO_IRQ) { + pr_warn("%s: Failed to map MSI to linux irq\n", + pci_name(pdev)); + pnv_put_msi(phb, hwirq); + return -ENOMEM; + } + rc = phb->msi_setup(phb, pdev, hwirq, entry->msi_attrib.is_64, + &msg); + if (rc) { + pr_warn("%s: Failed to setup MSI\n", pci_name(pdev)); + irq_dispose_mapping(virq); + pnv_put_msi(phb, hwirq); + return rc; + } + irq_set_msi_desc(virq, entry); + write_msi_msg(virq, &msg); + } + return 0; +} + +static void pnv_teardown_msi_irqs(struct pci_dev *pdev) +{ + struct pci_controller *hose = pci_bus_to_host(pdev->bus); + struct pnv_phb *phb = hose->private_data; + struct msi_desc *entry; + + if (WARN_ON(!phb)) + return; + + list_for_each_entry(entry, &pdev->msi_list, list) { + if (entry->irq == NO_IRQ) + continue; + irq_set_msi_desc(entry->irq, NULL); + pnv_put_msi(phb, virq_to_hw(entry->irq)); + irq_dispose_mapping(entry->irq); + } +} +#endif /* CONFIG_PCI_MSI */ + +static void pnv_pci_config_check_eeh(struct pnv_phb *phb, struct pci_bus *bus, + u32 bdfn) +{ + s64 rc; + u8 fstate; + u16 pcierr; + u32 pe_no; + + /* Get PE# if we support IODA */ + pe_no = phb->bdfn_to_pe ? phb->bdfn_to_pe(phb, bus, bdfn & 0xff) : 0; + + /* Read freeze status */ + rc = opal_pci_eeh_freeze_status(phb->opal_id, pe_no, &fstate, &pcierr, + NULL); + if (rc) { + pr_warning("PCI %d: Failed to read EEH status for PE#%d," + " err %lld\n", phb->hose->global_number, pe_no, rc); + return; + } + cfg_dbg(" -> EEH check, bdfn=%04x PE%d fstate=%x\n", + bdfn, pe_no, fstate); + if (fstate != 0) { + rc = opal_pci_eeh_freeze_clear(phb->opal_id, pe_no, + OPAL_EEH_ACTION_CLEAR_FREEZE_ALL); + if (rc) { + pr_warning("PCI %d: Failed to clear EEH freeze state" + " for PE#%d, err %lld\n", + phb->hose->global_number, pe_no, rc); + } + } +} + +static int pnv_pci_read_config(struct pci_bus *bus, + unsigned int devfn, + int where, int size, u32 *val) +{ + struct pci_controller *hose = pci_bus_to_host(bus); + struct pnv_phb *phb = hose->private_data; + u32 bdfn = (((uint64_t)bus->number) << 8) | devfn; + s64 rc; + + if (hose == NULL) + return PCIBIOS_DEVICE_NOT_FOUND; + + switch (size) { + case 1: { + u8 v8; + rc = opal_pci_config_read_byte(phb->opal_id, bdfn, where, &v8); + *val = (rc == OPAL_SUCCESS) ? v8 : 0xff; + break; + } + case 2: { + u16 v16; + rc = opal_pci_config_read_half_word(phb->opal_id, bdfn, where, + &v16); + *val = (rc == OPAL_SUCCESS) ? v16 : 0xffff; + break; + } + case 4: { + u32 v32; + rc = opal_pci_config_read_word(phb->opal_id, bdfn, where, &v32); + *val = (rc == OPAL_SUCCESS) ? v32 : 0xffffffff; + break; + } + default: + return PCIBIOS_FUNC_NOT_SUPPORTED; + } + cfg_dbg("pnv_pci_read_config bus: %x devfn: %x +%x/%x -> %08x\n", + bus->number, devfn, where, size, *val); + + /* Check if the PHB got frozen due to an error (no response) */ + pnv_pci_config_check_eeh(phb, bus, bdfn); + + return PCIBIOS_SUCCESSFUL; +} + +static int pnv_pci_write_config(struct pci_bus *bus, + unsigned int devfn, + int where, int size, u32 val) +{ + struct pci_controller *hose = pci_bus_to_host(bus); + struct pnv_phb *phb = hose->private_data; + u32 bdfn = (((uint64_t)bus->number) << 8) | devfn; + + if (hose == NULL) + return PCIBIOS_DEVICE_NOT_FOUND; + + cfg_dbg("pnv_pci_write_config bus: %x devfn: %x +%x/%x -> %08x\n", + bus->number, devfn, where, size, val); + switch (size) { + case 1: + opal_pci_config_write_byte(phb->opal_id, bdfn, where, val); + break; + case 2: + opal_pci_config_write_half_word(phb->opal_id, bdfn, where, val); + break; + case 4: + opal_pci_config_write_word(phb->opal_id, bdfn, where, val); + break; + default: + return PCIBIOS_FUNC_NOT_SUPPORTED; + } + /* Check if the PHB got frozen due to an error (no response) */ + pnv_pci_config_check_eeh(phb, bus, bdfn); + + return PCIBIOS_SUCCESSFUL; +} + +struct pci_ops pnv_pci_ops = { + .read = pnv_pci_read_config, + .write = pnv_pci_write_config, +}; + +static int pnv_tce_build(struct iommu_table *tbl, long index, long npages, + unsigned long uaddr, enum dma_data_direction direction, + struct dma_attrs *attrs) +{ + u64 proto_tce; + u64 *tcep; + u64 rpn; + + proto_tce = TCE_PCI_READ; // Read allowed + + if (direction != DMA_TO_DEVICE) + proto_tce |= TCE_PCI_WRITE; + + tcep = ((u64 *)tbl->it_base) + index; + + while (npages--) { + /* can't move this out since we might cross LMB boundary */ + rpn = (virt_to_abs(uaddr)) >> TCE_SHIFT; + *tcep = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT; + + uaddr += TCE_PAGE_SIZE; + tcep++; + } + return 0; +} + +static void pnv_tce_free(struct iommu_table *tbl, long index, long npages) +{ + u64 *tcep = ((u64 *)tbl->it_base) + index; + + while (npages--) + *(tcep++) = 0; +} + +void pnv_pci_setup_iommu_table(struct iommu_table *tbl, + void *tce_mem, u64 tce_size, + u64 dma_offset) +{ + tbl->it_blocksize = 16; + tbl->it_base = (unsigned long)tce_mem; + tbl->it_offset = dma_offset >> IOMMU_PAGE_SHIFT; + tbl->it_index = 0; + tbl->it_size = tce_size >> 3; + tbl->it_busno = 0; + tbl->it_type = TCE_PCI; +} + +static struct iommu_table * __devinit +pnv_pci_setup_bml_iommu(struct pci_controller *hose) +{ + struct iommu_table *tbl; + const __be64 *basep; + const __be32 *sizep; + + basep = of_get_property(hose->dn, "linux,tce-base", NULL); + sizep = of_get_property(hose->dn, "linux,tce-size", NULL); + if (basep == NULL || sizep == NULL) { + pr_err("PCI: %s has missing tce entries !\n", hose->dn->full_name); + return NULL; + } + tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, hose->node); + if (WARN_ON(!tbl)) + return NULL; + pnv_pci_setup_iommu_table(tbl, __va(be64_to_cpup(basep)), + be32_to_cpup(sizep), 0); + iommu_init_table(tbl, hose->node); + return tbl; +} + +static void __devinit pnv_pci_dma_fallback_setup(struct pci_controller *hose, + struct pci_dev *pdev) +{ + struct device_node *np = pci_bus_to_OF_node(hose->bus); + struct pci_dn *pdn; + + if (np == NULL) + return; + pdn = PCI_DN(np); + if (!pdn->iommu_table) + pdn->iommu_table = pnv_pci_setup_bml_iommu(hose); + if (!pdn->iommu_table) + return; + set_iommu_table_base(&pdev->dev, pdn->iommu_table); +} + +static void __devinit pnv_pci_dma_dev_setup(struct pci_dev *pdev) +{ + struct pci_controller *hose = pci_bus_to_host(pdev->bus); + struct pnv_phb *phb = hose->private_data; + + /* If we have no phb structure, try to setup a fallback based on + * the device-tree (RTAS PCI for example) + */ + if (phb && phb->dma_dev_setup) + phb->dma_dev_setup(phb, pdev); + else + pnv_pci_dma_fallback_setup(hose, pdev); +} + +static int pnv_pci_probe_mode(struct pci_bus *bus) +{ + struct pci_controller *hose = pci_bus_to_host(bus); + const __be64 *tstamp; + u64 now, target; + + + /* We hijack this as a way to ensure we have waited long + * enough since the reset was lifted on the PCI bus + */ + if (bus != hose->bus) + return PCI_PROBE_NORMAL; + tstamp = of_get_property(hose->dn, "reset-clear-timestamp", NULL); + if (!tstamp || !*tstamp) + return PCI_PROBE_NORMAL; + + now = mftb() / tb_ticks_per_usec; + target = (be64_to_cpup(tstamp) / tb_ticks_per_usec) + + PCI_RESET_DELAY_US; + + pr_devel("pci %04d: Reset target: 0x%llx now: 0x%llx\n", + hose->global_number, target, now); + + if (now < target) + msleep((target - now + 999) / 1000); + + return PCI_PROBE_NORMAL; +} + +void __init pnv_pci_init(void) +{ + struct device_node *np; + + pci_set_flags(PCI_CAN_SKIP_ISA_ALIGN); + + /* We do not want to just probe */ + pci_probe_only = 0; + + /* OPAL absent, try POPAL first then RTAS detection of PHBs */ + if (!firmware_has_feature(FW_FEATURE_OPAL)) { +#ifdef CONFIG_PPC_POWERNV_RTAS + init_pci_config_tokens(); + find_and_init_phbs(); +#endif /* CONFIG_PPC_POWERNV_RTAS */ + } else { + /* OPAL is here, do our normal stuff */ + + /* Look for p5ioc2 IO-Hubs */ + for_each_compatible_node(np, NULL, "ibm,p5ioc2") + pnv_pci_init_p5ioc2_hub(np); + } + + /* Setup the linkage between OF nodes and PHBs */ + pci_devs_phb_init(); + + /* Configure IOMMU DMA hooks */ + ppc_md.pci_dma_dev_setup = pnv_pci_dma_dev_setup; + ppc_md.tce_build = pnv_tce_build; + ppc_md.tce_free = pnv_tce_free; + ppc_md.pci_probe_mode = pnv_pci_probe_mode; + set_pci_dma_ops(&dma_iommu_ops); + + /* Configure MSIs */ +#ifdef CONFIG_PCI_MSI + ppc_md.msi_check_device = pnv_msi_check_device; + ppc_md.setup_msi_irqs = pnv_setup_msi_irqs; + ppc_md.teardown_msi_irqs = pnv_teardown_msi_irqs; +#endif +} diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h new file mode 100644 index 00000000000..d4dbc495093 --- /dev/null +++ b/arch/powerpc/platforms/powernv/pci.h @@ -0,0 +1,48 @@ +#ifndef __POWERNV_PCI_H +#define __POWERNV_PCI_H + +struct pci_dn; + +enum pnv_phb_type { + PNV_PHB_P5IOC2, + PNV_PHB_IODA1, + PNV_PHB_IODA2, +}; + +struct pnv_phb { + struct pci_controller *hose; + enum pnv_phb_type type; + u64 opal_id; + void __iomem *regs; + spinlock_t lock; + +#ifdef CONFIG_PCI_MSI + unsigned long *msi_map; + unsigned int msi_base; + unsigned int msi_count; + unsigned int msi_next; + unsigned int msi32_support; +#endif + int (*msi_setup)(struct pnv_phb *phb, struct pci_dev *dev, + unsigned int hwirq, unsigned int is_64, + struct msi_msg *msg); + void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev); + void (*fixup_phb)(struct pci_controller *hose); + u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn); + + union { + struct { + struct iommu_table iommu_table; + } p5ioc2; + }; +}; + +extern struct pci_ops pnv_pci_ops; + +extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl, + void *tce_mem, u64 tce_size, + u64 dma_offset); +extern void pnv_pci_init_p5ioc2_hub(struct device_node *np); + + +#endif /* __POWERNV_PCI_H */ diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h new file mode 100644 index 00000000000..8a9df7f9667 --- /dev/null +++ b/arch/powerpc/platforms/powernv/powernv.h @@ -0,0 +1,16 @@ +#ifndef _POWERNV_H +#define _POWERNV_H + +#ifdef CONFIG_SMP +extern void pnv_smp_init(void); +#else +static inline void pnv_smp_init(void) { } +#endif + +#ifdef CONFIG_PCI +extern void pnv_pci_init(void); +#else +static inline void pnv_pci_init(void) { } +#endif + +#endif /* _POWERNV_H */ diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c new file mode 100644 index 00000000000..467bd4ac682 --- /dev/null +++ b/arch/powerpc/platforms/powernv/setup.c @@ -0,0 +1,196 @@ +/* + * PowerNV setup code. + * + * Copyright 2011 IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#undef DEBUG + +#include <linux/cpu.h> +#include <linux/errno.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/tty.h> +#include <linux/reboot.h> +#include <linux/init.h> +#include <linux/console.h> +#include <linux/delay.h> +#include <linux/irq.h> +#include <linux/seq_file.h> +#include <linux/of.h> +#include <linux/interrupt.h> +#include <linux/bug.h> + +#include <asm/machdep.h> +#include <asm/firmware.h> +#include <asm/xics.h> +#include <asm/rtas.h> +#include <asm/opal.h> +#include <asm/xics.h> + +#include "powernv.h" + +static void __init pnv_setup_arch(void) +{ + /* Initialize SMP */ + pnv_smp_init(); + + /* Setup PCI */ + pnv_pci_init(); + + /* Setup RTC and NVRAM callbacks */ + if (firmware_has_feature(FW_FEATURE_OPAL)) + opal_nvram_init(); + + /* Enable NAP mode */ + powersave_nap = 1; + + /* XXX PMCS */ +} + +static void __init pnv_init_early(void) +{ +#ifdef CONFIG_HVC_OPAL + if (firmware_has_feature(FW_FEATURE_OPAL)) + hvc_opal_init_early(); + else +#endif + add_preferred_console("hvc", 0, NULL); +} + +static void __init pnv_init_IRQ(void) +{ + xics_init(); + + WARN_ON(!ppc_md.get_irq); +} + +static void pnv_show_cpuinfo(struct seq_file *m) +{ + struct device_node *root; + const char *model = ""; + + root = of_find_node_by_path("/"); + if (root) + model = of_get_property(root, "model", NULL); + seq_printf(m, "machine\t\t: PowerNV %s\n", model); + if (firmware_has_feature(FW_FEATURE_OPALv2)) + seq_printf(m, "firmware\t: OPAL v2\n"); + else if (firmware_has_feature(FW_FEATURE_OPAL)) + seq_printf(m, "firmware\t: OPAL v1\n"); + else + seq_printf(m, "firmware\t: BML\n"); + of_node_put(root); +} + +static void __noreturn pnv_restart(char *cmd) +{ + long rc = OPAL_BUSY; + + while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { + rc = opal_cec_reboot(); + if (rc == OPAL_BUSY_EVENT) + opal_poll_events(NULL); + else + mdelay(10); + } + for (;;) + opal_poll_events(NULL); +} + +static void __noreturn pnv_power_off(void) +{ + long rc = OPAL_BUSY; + + while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { + rc = opal_cec_power_down(0); + if (rc == OPAL_BUSY_EVENT) + opal_poll_events(NULL); + else + mdelay(10); + } + for (;;) + opal_poll_events(NULL); +} + +static void __noreturn pnv_halt(void) +{ + pnv_power_off(); +} + +static void pnv_progress(char *s, unsigned short hex) +{ +} + +#ifdef CONFIG_KEXEC +static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) +{ + xics_kexec_teardown_cpu(secondary); +} +#endif /* CONFIG_KEXEC */ + +static void __init pnv_setup_machdep_opal(void) +{ + ppc_md.get_boot_time = opal_get_boot_time; + ppc_md.get_rtc_time = opal_get_rtc_time; + ppc_md.set_rtc_time = opal_set_rtc_time; + ppc_md.restart = pnv_restart; + ppc_md.power_off = pnv_power_off; + ppc_md.halt = pnv_halt; + ppc_md.machine_check_exception = opal_machine_check; +} + +#ifdef CONFIG_PPC_POWERNV_RTAS +static void __init pnv_setup_machdep_rtas(void) +{ + if (rtas_token("get-time-of-day") != RTAS_UNKNOWN_SERVICE) { + ppc_md.get_boot_time = rtas_get_boot_time; + ppc_md.get_rtc_time = rtas_get_rtc_time; + ppc_md.set_rtc_time = rtas_set_rtc_time; + } + ppc_md.restart = rtas_restart; + ppc_md.power_off = rtas_power_off; + ppc_md.halt = rtas_halt; +} +#endif /* CONFIG_PPC_POWERNV_RTAS */ + +static int __init pnv_probe(void) +{ + unsigned long root = of_get_flat_dt_root(); + + if (!of_flat_dt_is_compatible(root, "ibm,powernv")) + return 0; + + hpte_init_native(); + + if (firmware_has_feature(FW_FEATURE_OPAL)) + pnv_setup_machdep_opal(); +#ifdef CONFIG_PPC_POWERNV_RTAS + else if (rtas.base) + pnv_setup_machdep_rtas(); +#endif /* CONFIG_PPC_POWERNV_RTAS */ + + pr_debug("PowerNV detected !\n"); + + return 1; +} + +define_machine(powernv) { + .name = "PowerNV", + .probe = pnv_probe, + .init_early = pnv_init_early, + .setup_arch = pnv_setup_arch, + .init_IRQ = pnv_init_IRQ, + .show_cpuinfo = pnv_show_cpuinfo, + .progress = pnv_progress, + .power_save = power7_idle, + .calibrate_decr = generic_calibrate_decr, +#ifdef CONFIG_KEXEC + .kexec_cpu_down = pnv_kexec_cpu_down, +#endif +}; diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c new file mode 100644 index 00000000000..e8773668524 --- /dev/null +++ b/arch/powerpc/platforms/powernv/smp.c @@ -0,0 +1,182 @@ +/* + * SMP support for PowerNV machines. + * + * Copyright 2011 IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/smp.h> +#include <linux/interrupt.h> +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/spinlock.h> +#include <linux/cpu.h> + +#include <asm/irq.h> +#include <asm/smp.h> +#include <asm/paca.h> +#include <asm/machdep.h> +#include <asm/cputable.h> +#include <asm/firmware.h> +#include <asm/system.h> +#include <asm/rtas.h> +#include <asm/vdso_datapage.h> +#include <asm/cputhreads.h> +#include <asm/xics.h> +#include <asm/opal.h> + +#include "powernv.h" + +#ifdef DEBUG +#include <asm/udbg.h> +#define DBG(fmt...) udbg_printf(fmt) +#else +#define DBG(fmt...) +#endif + +static void __cpuinit pnv_smp_setup_cpu(int cpu) +{ + if (cpu != boot_cpuid) + xics_setup_cpu(); +} + +static int pnv_smp_cpu_bootable(unsigned int nr) +{ + /* Special case - we inhibit secondary thread startup + * during boot if the user requests it. + */ + if (system_state < SYSTEM_RUNNING && cpu_has_feature(CPU_FTR_SMT)) { + if (!smt_enabled_at_boot && cpu_thread_in_core(nr) != 0) + return 0; + if (smt_enabled_at_boot + && cpu_thread_in_core(nr) >= smt_enabled_at_boot) + return 0; + } + + return 1; +} + +int __devinit pnv_smp_kick_cpu(int nr) +{ + unsigned int pcpu = get_hard_smp_processor_id(nr); + unsigned long start_here = __pa(*((unsigned long *) + generic_secondary_smp_init)); + long rc; + + BUG_ON(nr < 0 || nr >= NR_CPUS); + + /* On OPAL v2 the CPU are still spinning inside OPAL itself, + * get them back now + */ + if (firmware_has_feature(FW_FEATURE_OPALv2)) { + pr_devel("OPAL: Starting CPU %d (HW 0x%x)...\n", nr, pcpu); + rc = opal_start_cpu(pcpu, start_here); + if (rc != OPAL_SUCCESS) + pr_warn("OPAL Error %ld starting CPU %d\n", + rc, nr); + } + return smp_generic_kick_cpu(nr); +} + +#ifdef CONFIG_HOTPLUG_CPU + +static int pnv_smp_cpu_disable(void) +{ + int cpu = smp_processor_id(); + + /* This is identical to pSeries... might consolidate by + * moving migrate_irqs_away to a ppc_md with default to + * the generic fixup_irqs. --BenH. + */ + set_cpu_online(cpu, false); + vdso_data->processorCount--; + if (cpu == boot_cpuid) + boot_cpuid = cpumask_any(cpu_online_mask); + xics_migrate_irqs_away(); + return 0; +} + +static void pnv_smp_cpu_kill_self(void) +{ + unsigned int cpu; + + /* If powersave_nap is enabled, use NAP mode, else just + * spin aimlessly + */ + if (!powersave_nap) { + generic_mach_cpu_die(); + return; + } + + /* Standard hot unplug procedure */ + local_irq_disable(); + idle_task_exit(); + current->active_mm = NULL; /* for sanity */ + cpu = smp_processor_id(); + DBG("CPU%d offline\n", cpu); + generic_set_cpu_dead(cpu); + smp_wmb(); + + /* We don't want to take decrementer interrupts while we are offline, + * so clear LPCR:PECE1. We keep PECE2 enabled. + */ + mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1); + while (!generic_check_cpu_restart(cpu)) { + power7_idle(); + if (!generic_check_cpu_restart(cpu)) { + DBG("CPU%d Unexpected exit while offline !\n", cpu); + /* We may be getting an IPI, so we re-enable + * interrupts to process it, it will be ignored + * since we aren't online (hopefully) + */ + local_irq_enable(); + local_irq_disable(); + } + } + mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_PECE1); + DBG("CPU%d coming online...\n", cpu); +} + +#endif /* CONFIG_HOTPLUG_CPU */ + +static struct smp_ops_t pnv_smp_ops = { + .message_pass = smp_muxed_ipi_message_pass, + .cause_ipi = NULL, /* Filled at runtime by xics_smp_probe() */ + .probe = xics_smp_probe, + .kick_cpu = pnv_smp_kick_cpu, + .setup_cpu = pnv_smp_setup_cpu, + .cpu_bootable = pnv_smp_cpu_bootable, +#ifdef CONFIG_HOTPLUG_CPU + .cpu_disable = pnv_smp_cpu_disable, + .cpu_die = generic_cpu_die, +#endif /* CONFIG_HOTPLUG_CPU */ +}; + +/* This is called very early during platform setup_arch */ +void __init pnv_smp_init(void) +{ + smp_ops = &pnv_smp_ops; + + /* XXX We don't yet have a proper entry point from HAL, for + * now we rely on kexec-style entry from BML + */ + +#ifdef CONFIG_PPC_RTAS + /* Non-lpar has additional take/give timebase */ + if (rtas_token("freeze-time-base") != RTAS_UNKNOWN_SERVICE) { + smp_ops->give_timebase = rtas_give_timebase; + smp_ops->take_timebase = rtas_take_timebase; + } +#endif /* CONFIG_PPC_RTAS */ + +#ifdef CONFIG_HOTPLUG_CPU + ppc_md.cpu_die = pnv_smp_cpu_kill_self; +#endif +} |