diff options
Diffstat (limited to 'arch/powerpc/platforms')
80 files changed, 3044 insertions, 6837 deletions
diff --git a/arch/powerpc/platforms/85xx/common.c b/arch/powerpc/platforms/85xx/common.c index 4a9ad871a168..7bfb9b184dd4 100644 --- a/arch/powerpc/platforms/85xx/common.c +++ b/arch/powerpc/platforms/85xx/common.c @@ -40,6 +40,7 @@ static const struct of_device_id mpc85xx_common_ids[] __initconst = { { .compatible = "fsl,qoriq-pcie-v2.4", }, { .compatible = "fsl,qoriq-pcie-v2.3", }, { .compatible = "fsl,qoriq-pcie-v2.2", }, + { .compatible = "fsl,fman", }, {}, }; diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c index 1f309ccb096e..9824d2cf79bd 100644 --- a/arch/powerpc/platforms/85xx/corenet_generic.c +++ b/arch/powerpc/platforms/85xx/corenet_generic.c @@ -88,6 +88,15 @@ static const struct of_device_id of_device_ids[] = { .compatible = "simple-bus" }, { + .compatible = "mdio-mux-gpio" + }, + { + .compatible = "fsl,fpga-ngpixis" + }, + { + .compatible = "fsl,fpga-qixis" + }, + { .compatible = "fsl,srio", }, { @@ -108,6 +117,9 @@ static const struct of_device_id of_device_ids[] = { { .compatible = "fsl,qe", }, + { + .compatible = "fsl,fman", + }, /* The following two are for the Freescale hypervisor */ { .name = "hypervisor", diff --git a/arch/powerpc/platforms/85xx/p1022_rdk.c b/arch/powerpc/platforms/85xx/p1022_rdk.c index 7a180f0308d5..680232d6ba48 100644 --- a/arch/powerpc/platforms/85xx/p1022_rdk.c +++ b/arch/powerpc/platforms/85xx/p1022_rdk.c @@ -50,14 +50,14 @@ void p1022rdk_set_pixel_clock(unsigned int pixclock) /* Map the global utilities registers. */ guts_np = of_find_compatible_node(NULL, NULL, "fsl,p1022-guts"); if (!guts_np) { - pr_err("p1022rdk: missing global utilties device node\n"); + pr_err("p1022rdk: missing global utilities device node\n"); return; } guts = of_iomap(guts_np, 0); of_node_put(guts_np); if (!guts) { - pr_err("p1022rdk: could not map global utilties device\n"); + pr_err("p1022rdk: could not map global utilities device\n"); return; } diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c index d7c1e69f3070..8631ac5f0e57 100644 --- a/arch/powerpc/platforms/85xx/smp.c +++ b/arch/powerpc/platforms/85xx/smp.c @@ -360,10 +360,10 @@ static void mpc85xx_smp_kexec_down(void *arg) static void map_and_flush(unsigned long paddr) { struct page *page = pfn_to_page(paddr >> PAGE_SHIFT); - unsigned long kaddr = (unsigned long)kmap(page); + unsigned long kaddr = (unsigned long)kmap_atomic(page); flush_dcache_range(kaddr, kaddr + PAGE_SIZE); - kunmap(page); + kunmap_atomic((void *)kaddr); } /** diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index 391b3f6b54a3..b7f9c408bf24 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -72,11 +72,6 @@ config PPC_SMP_MUXED_IPI cpu. This will enable the generic code to multiplex the 4 messages on to one ipi. -config PPC_UDBG_BEAT - bool "BEAT based debug console" - depends on PPC_CELLEB - default n - config IPIC bool default n diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 76483e3acd60..7264e91190be 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -2,6 +2,7 @@ config PPC64 bool "64-bit kernel" default n select HAVE_VIRT_CPU_ACCOUNTING + select ZLIB_DEFLATE help This option selects whether a 32-bit or a 64-bit kernel will be built. @@ -15,7 +16,7 @@ choice The most common ones are the desktop and server CPUs (601, 603, 604, 740, 750, 74xx) CPUs from Freescale and IBM, with their embedded 512x/52xx/82xx/83xx/86xx counterparts. - The other embeeded parts, namely 4xx, 8xx, e200 (55xx) and e500 + The other embedded parts, namely 4xx, 8xx, e200 (55xx) and e500 (85xx) each form a family of their own that is not compatible with the others. diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig index 870b6dbd4d18..2f23133ab3d1 100644 --- a/arch/powerpc/platforms/cell/Kconfig +++ b/arch/powerpc/platforms/cell/Kconfig @@ -33,17 +33,6 @@ config PPC_IBM_CELL_BLADE select PPC_UDBG_16550 select UDBG_RTAS_CONSOLE -config PPC_CELLEB - bool "Toshiba's Cell Reference Set 'Celleb' Architecture" - depends on PPC64 && PPC_BOOK3S - select PPC_CELL_NATIVE - select PPC_OF_PLATFORM_PCI - select PCI - select HAS_TXX9_SERIAL - select PPC_UDBG_BEAT - select USB_OHCI_BIG_ENDIAN_MMIO - select USB_EHCI_BIG_ENDIAN_MMIO - config PPC_CELL_QPACE bool "IBM Cell - QPACE" depends on PPC64 && PPC_BOOK3S diff --git a/arch/powerpc/platforms/cell/Makefile b/arch/powerpc/platforms/cell/Makefile index 2d16884f67b9..34699bddfddd 100644 --- a/arch/powerpc/platforms/cell/Makefile +++ b/arch/powerpc/platforms/cell/Makefile @@ -29,18 +29,3 @@ obj-$(CONFIG_AXON_MSI) += axon_msi.o # qpace setup obj-$(CONFIG_PPC_CELL_QPACE) += qpace_setup.o - -# celleb stuff -ifeq ($(CONFIG_PPC_CELLEB),y) -obj-y += celleb_setup.o \ - celleb_pci.o celleb_scc_epci.o \ - celleb_scc_pciex.o \ - celleb_scc_uhc.o \ - spider-pci.o beat.o beat_htab.o \ - beat_hvCall.o beat_interrupt.o \ - beat_iommu.o - -obj-$(CONFIG_PPC_UDBG_BEAT) += beat_udbg.o -obj-$(CONFIG_SERIAL_TXX9) += celleb_scc_sio.o -obj-$(CONFIG_SPU_BASE) += beat_spu_priv1.o -endif diff --git a/arch/powerpc/platforms/cell/beat.c b/arch/powerpc/platforms/cell/beat.c deleted file mode 100644 index affcf566d460..000000000000 --- a/arch/powerpc/platforms/cell/beat.c +++ /dev/null @@ -1,264 +0,0 @@ -/* - * Simple routines for Celleb/Beat - * - * (C) Copyright 2006-2007 TOSHIBA CORPORATION - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#include <linux/export.h> -#include <linux/init.h> -#include <linux/err.h> -#include <linux/rtc.h> -#include <linux/interrupt.h> -#include <linux/irqreturn.h> -#include <linux/reboot.h> - -#include <asm/hvconsole.h> -#include <asm/time.h> -#include <asm/machdep.h> -#include <asm/firmware.h> - -#include "beat_wrapper.h" -#include "beat.h" -#include "beat_interrupt.h" - -static int beat_pm_poweroff_flag; - -void beat_restart(char *cmd) -{ - beat_shutdown_logical_partition(!beat_pm_poweroff_flag); -} - -void beat_power_off(void) -{ - beat_shutdown_logical_partition(0); -} - -u64 beat_halt_code = 0x1000000000000000UL; -EXPORT_SYMBOL(beat_halt_code); - -void beat_halt(void) -{ - beat_shutdown_logical_partition(beat_halt_code); -} - -int beat_set_rtc_time(struct rtc_time *rtc_time) -{ - u64 tim; - tim = mktime(rtc_time->tm_year+1900, - rtc_time->tm_mon+1, rtc_time->tm_mday, - rtc_time->tm_hour, rtc_time->tm_min, rtc_time->tm_sec); - if (beat_rtc_write(tim)) - return -1; - return 0; -} - -void beat_get_rtc_time(struct rtc_time *rtc_time) -{ - u64 tim; - - if (beat_rtc_read(&tim)) - tim = 0; - to_tm(tim, rtc_time); - rtc_time->tm_year -= 1900; - rtc_time->tm_mon -= 1; -} - -#define BEAT_NVRAM_SIZE 4096 - -ssize_t beat_nvram_read(char *buf, size_t count, loff_t *index) -{ - unsigned int i; - unsigned long len; - char *p = buf; - - if (*index >= BEAT_NVRAM_SIZE) - return -ENODEV; - i = *index; - if (i + count > BEAT_NVRAM_SIZE) - count = BEAT_NVRAM_SIZE - i; - - for (; count != 0; count -= len) { - len = count; - if (len > BEAT_NVRW_CNT) - len = BEAT_NVRW_CNT; - if (beat_eeprom_read(i, len, p)) - return -EIO; - - p += len; - i += len; - } - *index = i; - return p - buf; -} - -ssize_t beat_nvram_write(char *buf, size_t count, loff_t *index) -{ - unsigned int i; - unsigned long len; - char *p = buf; - - if (*index >= BEAT_NVRAM_SIZE) - return -ENODEV; - i = *index; - if (i + count > BEAT_NVRAM_SIZE) - count = BEAT_NVRAM_SIZE - i; - - for (; count != 0; count -= len) { - len = count; - if (len > BEAT_NVRW_CNT) - len = BEAT_NVRW_CNT; - if (beat_eeprom_write(i, len, p)) - return -EIO; - - p += len; - i += len; - } - *index = i; - return p - buf; -} - -ssize_t beat_nvram_get_size(void) -{ - return BEAT_NVRAM_SIZE; -} - -int beat_set_xdabr(unsigned long dabr, unsigned long dabrx) -{ - if (beat_set_dabr(dabr, dabrx)) - return -1; - return 0; -} - -int64_t beat_get_term_char(u64 vterm, u64 *len, u64 *t1, u64 *t2) -{ - u64 db[2]; - s64 ret; - - ret = beat_get_characters_from_console(vterm, len, (u8 *)db); - if (ret == 0) { - *t1 = db[0]; - *t2 = db[1]; - } - return ret; -} -EXPORT_SYMBOL(beat_get_term_char); - -int64_t beat_put_term_char(u64 vterm, u64 len, u64 t1, u64 t2) -{ - u64 db[2]; - - db[0] = t1; - db[1] = t2; - return beat_put_characters_to_console(vterm, len, (u8 *)db); -} -EXPORT_SYMBOL(beat_put_term_char); - -void beat_power_save(void) -{ - beat_pause(0); -} - -#ifdef CONFIG_KEXEC -void beat_kexec_cpu_down(int crash, int secondary) -{ - beatic_deinit_IRQ(); -} -#endif - -static irqreturn_t beat_power_event(int virq, void *arg) -{ - printk(KERN_DEBUG "Beat: power button pressed\n"); - beat_pm_poweroff_flag = 1; - ctrl_alt_del(); - return IRQ_HANDLED; -} - -static irqreturn_t beat_reset_event(int virq, void *arg) -{ - printk(KERN_DEBUG "Beat: reset button pressed\n"); - beat_pm_poweroff_flag = 0; - ctrl_alt_del(); - return IRQ_HANDLED; -} - -static struct beat_event_list { - const char *typecode; - irq_handler_t handler; - unsigned int virq; -} beat_event_list[] = { - { "power", beat_power_event, 0 }, - { "reset", beat_reset_event, 0 }, -}; - -static int __init beat_register_event(void) -{ - u64 path[4], data[2]; - int rc, i; - unsigned int virq; - - for (i = 0; i < ARRAY_SIZE(beat_event_list); i++) { - struct beat_event_list *ev = &beat_event_list[i]; - - if (beat_construct_event_receive_port(data) != 0) { - printk(KERN_ERR "Beat: " - "cannot construct event receive port for %s\n", - ev->typecode); - return -EINVAL; - } - - virq = irq_create_mapping(NULL, data[0]); - if (virq == NO_IRQ) { - printk(KERN_ERR "Beat: failed to get virtual IRQ" - " for event receive port for %s\n", - ev->typecode); - beat_destruct_event_receive_port(data[0]); - return -EIO; - } - ev->virq = virq; - - rc = request_irq(virq, ev->handler, 0, - ev->typecode, NULL); - if (rc != 0) { - printk(KERN_ERR "Beat: failed to request virtual IRQ" - " for event receive port for %s\n", - ev->typecode); - beat_destruct_event_receive_port(data[0]); - return rc; - } - - path[0] = 0x1000000065780000ul; /* 1,ex */ - path[1] = 0x627574746f6e0000ul; /* button */ - path[2] = 0; - strncpy((char *)&path[2], ev->typecode, 8); - path[3] = 0; - data[1] = 0; - - beat_create_repository_node(path, data); - } - return 0; -} - -static int __init beat_event_init(void) -{ - if (!firmware_has_feature(FW_FEATURE_BEAT)) - return -EINVAL; - - beat_pm_poweroff_flag = 0; - return beat_register_event(); -} - -device_initcall(beat_event_init); diff --git a/arch/powerpc/platforms/cell/beat.h b/arch/powerpc/platforms/cell/beat.h deleted file mode 100644 index bfcb8e351ae5..000000000000 --- a/arch/powerpc/platforms/cell/beat.h +++ /dev/null @@ -1,39 +0,0 @@ -/* - * Guest OS Interfaces. - * - * (C) Copyright 2006 TOSHIBA CORPORATION - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#ifndef _CELLEB_BEAT_H -#define _CELLEB_BEAT_H - -int64_t beat_get_term_char(uint64_t, uint64_t *, uint64_t *, uint64_t *); -int64_t beat_put_term_char(uint64_t, uint64_t, uint64_t, uint64_t); -int64_t beat_repository_encode(int, const char *, uint64_t[4]); -void beat_restart(char *); -void beat_power_off(void); -void beat_halt(void); -int beat_set_rtc_time(struct rtc_time *); -void beat_get_rtc_time(struct rtc_time *); -ssize_t beat_nvram_get_size(void); -ssize_t beat_nvram_read(char *, size_t, loff_t *); -ssize_t beat_nvram_write(char *, size_t, loff_t *); -int beat_set_xdabr(unsigned long, unsigned long); -void beat_power_save(void); -void beat_kexec_cpu_down(int, int); - -#endif /* _CELLEB_BEAT_H */ diff --git a/arch/powerpc/platforms/cell/beat_htab.c b/arch/powerpc/platforms/cell/beat_htab.c deleted file mode 100644 index bee9232fe619..000000000000 --- a/arch/powerpc/platforms/cell/beat_htab.c +++ /dev/null @@ -1,445 +0,0 @@ -/* - * "Cell Reference Set" HTAB support. - * - * (C) Copyright 2006-2007 TOSHIBA CORPORATION - * - * This code is based on arch/powerpc/platforms/pseries/lpar.c: - * Copyright (C) 2001 Todd Inglett, IBM Corporation - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#undef DEBUG_LOW - -#include <linux/kernel.h> -#include <linux/spinlock.h> - -#include <asm/mmu.h> -#include <asm/page.h> -#include <asm/pgtable.h> -#include <asm/machdep.h> -#include <asm/udbg.h> - -#include "beat_wrapper.h" - -#ifdef DEBUG_LOW -#define DBG_LOW(fmt...) do { udbg_printf(fmt); } while (0) -#else -#define DBG_LOW(fmt...) do { } while (0) -#endif - -static DEFINE_RAW_SPINLOCK(beat_htab_lock); - -static inline unsigned int beat_read_mask(unsigned hpte_group) -{ - unsigned long rmask = 0; - u64 hpte_v[5]; - - beat_read_htab_entries(0, hpte_group + 0, hpte_v); - if (!(hpte_v[0] & HPTE_V_BOLTED)) - rmask |= 0x8000; - if (!(hpte_v[1] & HPTE_V_BOLTED)) - rmask |= 0x4000; - if (!(hpte_v[2] & HPTE_V_BOLTED)) - rmask |= 0x2000; - if (!(hpte_v[3] & HPTE_V_BOLTED)) - rmask |= 0x1000; - beat_read_htab_entries(0, hpte_group + 4, hpte_v); - if (!(hpte_v[0] & HPTE_V_BOLTED)) - rmask |= 0x0800; - if (!(hpte_v[1] & HPTE_V_BOLTED)) - rmask |= 0x0400; - if (!(hpte_v[2] & HPTE_V_BOLTED)) - rmask |= 0x0200; - if (!(hpte_v[3] & HPTE_V_BOLTED)) - rmask |= 0x0100; - hpte_group = ~hpte_group & (htab_hash_mask * HPTES_PER_GROUP); - beat_read_htab_entries(0, hpte_group + 0, hpte_v); - if (!(hpte_v[0] & HPTE_V_BOLTED)) - rmask |= 0x80; - if (!(hpte_v[1] & HPTE_V_BOLTED)) - rmask |= 0x40; - if (!(hpte_v[2] & HPTE_V_BOLTED)) - rmask |= 0x20; - if (!(hpte_v[3] & HPTE_V_BOLTED)) - rmask |= 0x10; - beat_read_htab_entries(0, hpte_group + 4, hpte_v); - if (!(hpte_v[0] & HPTE_V_BOLTED)) - rmask |= 0x08; - if (!(hpte_v[1] & HPTE_V_BOLTED)) - rmask |= 0x04; - if (!(hpte_v[2] & HPTE_V_BOLTED)) - rmask |= 0x02; - if (!(hpte_v[3] & HPTE_V_BOLTED)) - rmask |= 0x01; - return rmask; -} - -static long beat_lpar_hpte_insert(unsigned long hpte_group, - unsigned long vpn, unsigned long pa, - unsigned long rflags, unsigned long vflags, - int psize, int apsize, int ssize) -{ - unsigned long lpar_rc; - u64 hpte_v, hpte_r, slot; - - if (vflags & HPTE_V_SECONDARY) - return -1; - - if (!(vflags & HPTE_V_BOLTED)) - DBG_LOW("hpte_insert(group=%lx, va=%016lx, pa=%016lx, " - "rflags=%lx, vflags=%lx, psize=%d)\n", - hpte_group, va, pa, rflags, vflags, psize); - - hpte_v = hpte_encode_v(vpn, psize, apsize, MMU_SEGSIZE_256M) | - vflags | HPTE_V_VALID; - hpte_r = hpte_encode_r(pa, psize, apsize) | rflags; - - if (!(vflags & HPTE_V_BOLTED)) - DBG_LOW(" hpte_v=%016lx, hpte_r=%016lx\n", hpte_v, hpte_r); - - if (rflags & _PAGE_NO_CACHE) - hpte_r &= ~HPTE_R_M; - - raw_spin_lock(&beat_htab_lock); - lpar_rc = beat_read_mask(hpte_group); - if (lpar_rc == 0) { - if (!(vflags & HPTE_V_BOLTED)) - DBG_LOW(" full\n"); - raw_spin_unlock(&beat_htab_lock); - return -1; - } - - lpar_rc = beat_insert_htab_entry(0, hpte_group, lpar_rc << 48, - hpte_v, hpte_r, &slot); - raw_spin_unlock(&beat_htab_lock); - - /* - * Since we try and ioremap PHBs we don't own, the pte insert - * will fail. However we must catch the failure in hash_page - * or we will loop forever, so return -2 in this case. - */ - if (unlikely(lpar_rc != 0)) { - if (!(vflags & HPTE_V_BOLTED)) - DBG_LOW(" lpar err %lx\n", lpar_rc); - return -2; - } - if (!(vflags & HPTE_V_BOLTED)) - DBG_LOW(" -> slot: %lx\n", slot); - - /* We have to pass down the secondary bucket bit here as well */ - return (slot ^ hpte_group) & 15; -} - -static long beat_lpar_hpte_remove(unsigned long hpte_group) -{ - DBG_LOW("hpte_remove(group=%lx)\n", hpte_group); - return -1; -} - -static unsigned long beat_lpar_hpte_getword0(unsigned long slot) -{ - unsigned long dword0; - unsigned long lpar_rc; - u64 dword[5]; - - lpar_rc = beat_read_htab_entries(0, slot & ~3UL, dword); - - dword0 = dword[slot&3]; - - BUG_ON(lpar_rc != 0); - - return dword0; -} - -static void beat_lpar_hptab_clear(void) -{ - unsigned long size_bytes = 1UL << ppc64_pft_size; - unsigned long hpte_count = size_bytes >> 4; - int i; - u64 dummy0, dummy1; - - /* TODO: Use bulk call */ - for (i = 0; i < hpte_count; i++) - beat_write_htab_entry(0, i, 0, 0, -1UL, -1UL, &dummy0, &dummy1); -} - -/* - * NOTE: for updatepp ops we are fortunate that the linux "newpp" bits and - * the low 3 bits of flags happen to line up. So no transform is needed. - * We can probably optimize here and assume the high bits of newpp are - * already zero. For now I am paranoid. - */ -static long beat_lpar_hpte_updatepp(unsigned long slot, - unsigned long newpp, - unsigned long vpn, - int psize, int apsize, - int ssize, unsigned long flags) -{ - unsigned long lpar_rc; - u64 dummy0, dummy1; - unsigned long want_v; - - want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M); - - DBG_LOW(" update: " - "avpnv=%016lx, slot=%016lx, psize: %d, newpp %016lx ... ", - want_v & HPTE_V_AVPN, slot, psize, newpp); - - raw_spin_lock(&beat_htab_lock); - dummy0 = beat_lpar_hpte_getword0(slot); - if ((dummy0 & ~0x7FUL) != (want_v & ~0x7FUL)) { - DBG_LOW("not found !\n"); - raw_spin_unlock(&beat_htab_lock); - return -1; - } - - lpar_rc = beat_write_htab_entry(0, slot, 0, newpp, 0, 7, &dummy0, - &dummy1); - raw_spin_unlock(&beat_htab_lock); - if (lpar_rc != 0 || dummy0 == 0) { - DBG_LOW("not found !\n"); - return -1; - } - - DBG_LOW("ok %lx %lx\n", dummy0, dummy1); - - BUG_ON(lpar_rc != 0); - - return 0; -} - -static long beat_lpar_hpte_find(unsigned long vpn, int psize) -{ - unsigned long hash; - unsigned long i, j; - long slot; - unsigned long want_v, hpte_v; - - hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, MMU_SEGSIZE_256M); - want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M); - - for (j = 0; j < 2; j++) { - slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; - for (i = 0; i < HPTES_PER_GROUP; i++) { - hpte_v = beat_lpar_hpte_getword0(slot); - - if (HPTE_V_COMPARE(hpte_v, want_v) - && (hpte_v & HPTE_V_VALID) - && (!!(hpte_v & HPTE_V_SECONDARY) == j)) { - /* HPTE matches */ - if (j) - slot = -slot; - return slot; - } - ++slot; - } - hash = ~hash; - } - - return -1; -} - -static void beat_lpar_hpte_updateboltedpp(unsigned long newpp, - unsigned long ea, - int psize, int ssize) -{ - unsigned long vpn; - unsigned long lpar_rc, slot, vsid; - u64 dummy0, dummy1; - - vsid = get_kernel_vsid(ea, MMU_SEGSIZE_256M); - vpn = hpt_vpn(ea, vsid, MMU_SEGSIZE_256M); - - raw_spin_lock(&beat_htab_lock); - slot = beat_lpar_hpte_find(vpn, psize); - BUG_ON(slot == -1); - - lpar_rc = beat_write_htab_entry(0, slot, 0, newpp, 0, 7, - &dummy0, &dummy1); - raw_spin_unlock(&beat_htab_lock); - - BUG_ON(lpar_rc != 0); -} - -static void beat_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn, - int psize, int apsize, - int ssize, int local) -{ - unsigned long want_v; - unsigned long lpar_rc; - u64 dummy1, dummy2; - unsigned long flags; - - DBG_LOW(" inval : slot=%lx, va=%016lx, psize: %d, local: %d\n", - slot, va, psize, local); - want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M); - - raw_spin_lock_irqsave(&beat_htab_lock, flags); - dummy1 = beat_lpar_hpte_getword0(slot); - - if ((dummy1 & ~0x7FUL) != (want_v & ~0x7FUL)) { - DBG_LOW("not found !\n"); - raw_spin_unlock_irqrestore(&beat_htab_lock, flags); - return; - } - - lpar_rc = beat_write_htab_entry(0, slot, 0, 0, HPTE_V_VALID, 0, - &dummy1, &dummy2); - raw_spin_unlock_irqrestore(&beat_htab_lock, flags); - - BUG_ON(lpar_rc != 0); -} - -void __init hpte_init_beat(void) -{ - ppc_md.hpte_invalidate = beat_lpar_hpte_invalidate; - ppc_md.hpte_updatepp = beat_lpar_hpte_updatepp; - ppc_md.hpte_updateboltedpp = beat_lpar_hpte_updateboltedpp; - ppc_md.hpte_insert = beat_lpar_hpte_insert; - ppc_md.hpte_remove = beat_lpar_hpte_remove; - ppc_md.hpte_clear_all = beat_lpar_hptab_clear; -} - -static long beat_lpar_hpte_insert_v3(unsigned long hpte_group, - unsigned long vpn, unsigned long pa, - unsigned long rflags, unsigned long vflags, - int psize, int apsize, int ssize) -{ - unsigned long lpar_rc; - u64 hpte_v, hpte_r, slot; - - if (vflags & HPTE_V_SECONDARY) - return -1; - - if (!(vflags & HPTE_V_BOLTED)) - DBG_LOW("hpte_insert(group=%lx, vpn=%016lx, pa=%016lx, " - "rflags=%lx, vflags=%lx, psize=%d)\n", - hpte_group, vpn, pa, rflags, vflags, psize); - - hpte_v = hpte_encode_v(vpn, psize, apsize, MMU_SEGSIZE_256M) | - vflags | HPTE_V_VALID; - hpte_r = hpte_encode_r(pa, psize, apsize) | rflags; - - if (!(vflags & HPTE_V_BOLTED)) - DBG_LOW(" hpte_v=%016lx, hpte_r=%016lx\n", hpte_v, hpte_r); - - if (rflags & _PAGE_NO_CACHE) - hpte_r &= ~HPTE_R_M; - - /* insert into not-volted entry */ - lpar_rc = beat_insert_htab_entry3(0, hpte_group, hpte_v, hpte_r, - HPTE_V_BOLTED, 0, &slot); - /* - * Since we try and ioremap PHBs we don't own, the pte insert - * will fail. However we must catch the failure in hash_page - * or we will loop forever, so return -2 in this case. - */ - if (unlikely(lpar_rc != 0)) { - if (!(vflags & HPTE_V_BOLTED)) - DBG_LOW(" lpar err %lx\n", lpar_rc); - return -2; - } - if (!(vflags & HPTE_V_BOLTED)) - DBG_LOW(" -> slot: %lx\n", slot); - - /* We have to pass down the secondary bucket bit here as well */ - return (slot ^ hpte_group) & 15; -} - -/* - * NOTE: for updatepp ops we are fortunate that the linux "newpp" bits and - * the low 3 bits of flags happen to line up. So no transform is needed. - * We can probably optimize here and assume the high bits of newpp are - * already zero. For now I am paranoid. - */ -static long beat_lpar_hpte_updatepp_v3(unsigned long slot, - unsigned long newpp, - unsigned long vpn, - int psize, int apsize, - int ssize, unsigned long flags) -{ - unsigned long lpar_rc; - unsigned long want_v; - unsigned long pss; - - want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M); - pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc[psize]; - - DBG_LOW(" update: " - "avpnv=%016lx, slot=%016lx, psize: %d, newpp %016lx ... ", - want_v & HPTE_V_AVPN, slot, psize, newpp); - - lpar_rc = beat_update_htab_permission3(0, slot, want_v, pss, 7, newpp); - - if (lpar_rc == 0xfffffff7) { - DBG_LOW("not found !\n"); - return -1; - } - - DBG_LOW("ok\n"); - - BUG_ON(lpar_rc != 0); - - return 0; -} - -static void beat_lpar_hpte_invalidate_v3(unsigned long slot, unsigned long vpn, - int psize, int apsize, - int ssize, int local) -{ - unsigned long want_v; - unsigned long lpar_rc; - unsigned long pss; - - DBG_LOW(" inval : slot=%lx, vpn=%016lx, psize: %d, local: %d\n", - slot, vpn, psize, local); - want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M); - pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc[psize]; - - lpar_rc = beat_invalidate_htab_entry3(0, slot, want_v, pss); - - /* E_busy can be valid output: page may be already replaced */ - BUG_ON(lpar_rc != 0 && lpar_rc != 0xfffffff7); -} - -static int64_t _beat_lpar_hptab_clear_v3(void) -{ - return beat_clear_htab3(0); -} - -static void beat_lpar_hptab_clear_v3(void) -{ - _beat_lpar_hptab_clear_v3(); -} - -void __init hpte_init_beat_v3(void) -{ - if (_beat_lpar_hptab_clear_v3() == 0) { - ppc_md.hpte_invalidate = beat_lpar_hpte_invalidate_v3; - ppc_md.hpte_updatepp = beat_lpar_hpte_updatepp_v3; - ppc_md.hpte_updateboltedpp = beat_lpar_hpte_updateboltedpp; - ppc_md.hpte_insert = beat_lpar_hpte_insert_v3; - ppc_md.hpte_remove = beat_lpar_hpte_remove; - ppc_md.hpte_clear_all = beat_lpar_hptab_clear_v3; - } else { - ppc_md.hpte_invalidate = beat_lpar_hpte_invalidate; - ppc_md.hpte_updatepp = beat_lpar_hpte_updatepp; - ppc_md.hpte_updateboltedpp = beat_lpar_hpte_updateboltedpp; - ppc_md.hpte_insert = beat_lpar_hpte_insert; - ppc_md.hpte_remove = beat_lpar_hpte_remove; - ppc_md.hpte_clear_all = beat_lpar_hptab_clear; - } -} diff --git a/arch/powerpc/platforms/cell/beat_hvCall.S b/arch/powerpc/platforms/cell/beat_hvCall.S deleted file mode 100644 index 96c801907126..000000000000 --- a/arch/powerpc/platforms/cell/beat_hvCall.S +++ /dev/null @@ -1,285 +0,0 @@ -/* - * Beat hypervisor call I/F - * - * (C) Copyright 2007 TOSHIBA CORPORATION - * - * This code is based on arch/powerpc/platforms/pseries/hvCall.S. - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#include <asm/ppc_asm.h> - -/* Not implemented on Beat, now */ -#define HCALL_INST_PRECALL -#define HCALL_INST_POSTCALL - - .text - -#define HVSC .long 0x44000022 - -/* Note: takes only 7 input parameters at maximum */ -_GLOBAL(beat_hcall_norets) - HMT_MEDIUM - - mfcr r0 - stw r0,8(r1) - - HCALL_INST_PRECALL - - mr r11,r3 - mr r3,r4 - mr r4,r5 - mr r5,r6 - mr r6,r7 - mr r7,r8 - mr r8,r9 - - HVSC /* invoke the hypervisor */ - - HCALL_INST_POSTCALL - - lwz r0,8(r1) - mtcrf 0xff,r0 - - blr /* return r3 = status */ - -/* Note: takes 8 input parameters at maximum */ -_GLOBAL(beat_hcall_norets8) - HMT_MEDIUM - - mfcr r0 - stw r0,8(r1) - - HCALL_INST_PRECALL - - mr r11,r3 - mr r3,r4 - mr r4,r5 - mr r5,r6 - mr r6,r7 - mr r7,r8 - mr r8,r9 - ld r10,STK_PARAM(R10)(r1) - - HVSC /* invoke the hypervisor */ - - HCALL_INST_POSTCALL - - lwz r0,8(r1) - mtcrf 0xff,r0 - - blr /* return r3 = status */ - -/* Note: takes only 6 input parameters, 1 output parameters at maximum */ -_GLOBAL(beat_hcall1) - HMT_MEDIUM - - mfcr r0 - stw r0,8(r1) - - HCALL_INST_PRECALL - - std r4,STK_PARAM(R4)(r1) /* save ret buffer */ - - mr r11,r3 - mr r3,r5 - mr r4,r6 - mr r5,r7 - mr r6,r8 - mr r7,r9 - mr r8,r10 - - HVSC /* invoke the hypervisor */ - - HCALL_INST_POSTCALL - - ld r12,STK_PARAM(R4)(r1) - std r4, 0(r12) - - lwz r0,8(r1) - mtcrf 0xff,r0 - - blr /* return r3 = status */ - -/* Note: takes only 6 input parameters, 2 output parameters at maximum */ -_GLOBAL(beat_hcall2) - HMT_MEDIUM - - mfcr r0 - stw r0,8(r1) - - HCALL_INST_PRECALL - - std r4,STK_PARAM(R4)(r1) /* save ret buffer */ - - mr r11,r3 - mr r3,r5 - mr r4,r6 - mr r5,r7 - mr r6,r8 - mr r7,r9 - mr r8,r10 - - HVSC /* invoke the hypervisor */ - - HCALL_INST_POSTCALL - - ld r12,STK_PARAM(R4)(r1) - std r4, 0(r12) - std r5, 8(r12) - - lwz r0,8(r1) - mtcrf 0xff,r0 - - blr /* return r3 = status */ - -/* Note: takes only 6 input parameters, 3 output parameters at maximum */ -_GLOBAL(beat_hcall3) - HMT_MEDIUM - - mfcr r0 - stw r0,8(r1) - - HCALL_INST_PRECALL - - std r4,STK_PARAM(R4)(r1) /* save ret buffer */ - - mr r11,r3 - mr r3,r5 - mr r4,r6 - mr r5,r7 - mr r6,r8 - mr r7,r9 - mr r8,r10 - - HVSC /* invoke the hypervisor */ - - HCALL_INST_POSTCALL - - ld r12,STK_PARAM(R4)(r1) - std r4, 0(r12) - std r5, 8(r12) - std r6, 16(r12) - - lwz r0,8(r1) - mtcrf 0xff,r0 - - blr /* return r3 = status */ - -/* Note: takes only 6 input parameters, 4 output parameters at maximum */ -_GLOBAL(beat_hcall4) - HMT_MEDIUM - - mfcr r0 - stw r0,8(r1) - - HCALL_INST_PRECALL - - std r4,STK_PARAM(R4)(r1) /* save ret buffer */ - - mr r11,r3 - mr r3,r5 - mr r4,r6 - mr r5,r7 - mr r6,r8 - mr r7,r9 - mr r8,r10 - - HVSC /* invoke the hypervisor */ - - HCALL_INST_POSTCALL - - ld r12,STK_PARAM(R4)(r1) - std r4, 0(r12) - std r5, 8(r12) - std r6, 16(r12) - std r7, 24(r12) - - lwz r0,8(r1) - mtcrf 0xff,r0 - - blr /* return r3 = status */ - -/* Note: takes only 6 input parameters, 5 output parameters at maximum */ -_GLOBAL(beat_hcall5) - HMT_MEDIUM - - mfcr r0 - stw r0,8(r1) - - HCALL_INST_PRECALL - - std r4,STK_PARAM(R4)(r1) /* save ret buffer */ - - mr r11,r3 - mr r3,r5 - mr r4,r6 - mr r5,r7 - mr r6,r8 - mr r7,r9 - mr r8,r10 - - HVSC /* invoke the hypervisor */ - - HCALL_INST_POSTCALL - - ld r12,STK_PARAM(R4)(r1) - std r4, 0(r12) - std r5, 8(r12) - std r6, 16(r12) - std r7, 24(r12) - std r8, 32(r12) - - lwz r0,8(r1) - mtcrf 0xff,r0 - - blr /* return r3 = status */ - -/* Note: takes only 6 input parameters, 6 output parameters at maximum */ -_GLOBAL(beat_hcall6) - HMT_MEDIUM - - mfcr r0 - stw r0,8(r1) - - HCALL_INST_PRECALL - - std r4,STK_PARAM(R4)(r1) /* save ret buffer */ - - mr r11,r3 - mr r3,r5 - mr r4,r6 - mr r5,r7 - mr r6,r8 - mr r7,r9 - mr r8,r10 - - HVSC /* invoke the hypervisor */ - - HCALL_INST_POSTCALL - - ld r12,STK_PARAM(R4)(r1) - std r4, 0(r12) - std r5, 8(r12) - std r6, 16(r12) - std r7, 24(r12) - std r8, 32(r12) - std r9, 40(r12) - - lwz r0,8(r1) - mtcrf 0xff,r0 - - blr /* return r3 = status */ diff --git a/arch/powerpc/platforms/cell/beat_interrupt.c b/arch/powerpc/platforms/cell/beat_interrupt.c deleted file mode 100644 index 9e5dfbcc00af..000000000000 --- a/arch/powerpc/platforms/cell/beat_interrupt.c +++ /dev/null @@ -1,253 +0,0 @@ -/* - * Celleb/Beat Interrupt controller - * - * (C) Copyright 2006-2007 TOSHIBA CORPORATION - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#include <linux/init.h> -#include <linux/interrupt.h> -#include <linux/irq.h> -#include <linux/percpu.h> -#include <linux/types.h> - -#include <asm/machdep.h> - -#include "beat_interrupt.h" -#include "beat_wrapper.h" - -#define MAX_IRQS NR_IRQS -static DEFINE_RAW_SPINLOCK(beatic_irq_mask_lock); -static uint64_t beatic_irq_mask_enable[(MAX_IRQS+255)/64]; -static uint64_t beatic_irq_mask_ack[(MAX_IRQS+255)/64]; - -static struct irq_domain *beatic_host; - -/* - * In this implementation, "virq" == "IRQ plug number", - * "(irq_hw_number_t)hwirq" == "IRQ outlet number". - */ - -/* assumption: locked */ -static inline void beatic_update_irq_mask(unsigned int irq_plug) -{ - int off; - unsigned long masks[4]; - - off = (irq_plug / 256) * 4; - masks[0] = beatic_irq_mask_enable[off + 0] - & beatic_irq_mask_ack[off + 0]; - masks[1] = beatic_irq_mask_enable[off + 1] - & beatic_irq_mask_ack[off + 1]; - masks[2] = beatic_irq_mask_enable[off + 2] - & beatic_irq_mask_ack[off + 2]; - masks[3] = beatic_irq_mask_enable[off + 3] - & beatic_irq_mask_ack[off + 3]; - if (beat_set_interrupt_mask(irq_plug&~255UL, - masks[0], masks[1], masks[2], masks[3]) != 0) - panic("Failed to set mask IRQ!"); -} - -static void beatic_mask_irq(struct irq_data *d) -{ - unsigned long flags; - - raw_spin_lock_irqsave(&beatic_irq_mask_lock, flags); - beatic_irq_mask_enable[d->irq/64] &= ~(1UL << (63 - (d->irq%64))); - beatic_update_irq_mask(d->irq); - raw_spin_unlock_irqrestore(&beatic_irq_mask_lock, flags); -} - -static void beatic_unmask_irq(struct irq_data *d) -{ - unsigned long flags; - - raw_spin_lock_irqsave(&beatic_irq_mask_lock, flags); - beatic_irq_mask_enable[d->irq/64] |= 1UL << (63 - (d->irq%64)); - beatic_update_irq_mask(d->irq); - raw_spin_unlock_irqrestore(&beatic_irq_mask_lock, flags); -} - -static void beatic_ack_irq(struct irq_data *d) -{ - unsigned long flags; - - raw_spin_lock_irqsave(&beatic_irq_mask_lock, flags); - beatic_irq_mask_ack[d->irq/64] &= ~(1UL << (63 - (d->irq%64))); - beatic_update_irq_mask(d->irq); - raw_spin_unlock_irqrestore(&beatic_irq_mask_lock, flags); -} - -static void beatic_end_irq(struct irq_data *d) -{ - s64 err; - unsigned long flags; - - err = beat_downcount_of_interrupt(d->irq); - if (err != 0) { - if ((err & 0xFFFFFFFF) != 0xFFFFFFF5) /* -11: wrong state */ - panic("Failed to downcount IRQ! Error = %16llx", err); - - printk(KERN_ERR "IRQ over-downcounted, plug %d\n", d->irq); - } - raw_spin_lock_irqsave(&beatic_irq_mask_lock, flags); - beatic_irq_mask_ack[d->irq/64] |= 1UL << (63 - (d->irq%64)); - beatic_update_irq_mask(d->irq); - raw_spin_unlock_irqrestore(&beatic_irq_mask_lock, flags); -} - -static struct irq_chip beatic_pic = { - .name = "CELL-BEAT", - .irq_unmask = beatic_unmask_irq, - .irq_mask = beatic_mask_irq, - .irq_eoi = beatic_end_irq, -}; - -/* - * Dispose binding hardware IRQ number (hw) and Virtuql IRQ number (virq), - * update flags. - * - * Note that the number (virq) is already assigned at upper layer. - */ -static void beatic_pic_host_unmap(struct irq_domain *h, unsigned int virq) -{ - beat_destruct_irq_plug(virq); -} - -/* - * Create or update binding hardware IRQ number (hw) and Virtuql - * IRQ number (virq). This is called only once for a given mapping. - * - * Note that the number (virq) is already assigned at upper layer. - */ -static int beatic_pic_host_map(struct irq_domain *h, unsigned int virq, - irq_hw_number_t hw) -{ - int64_t err; - - err = beat_construct_and_connect_irq_plug(virq, hw); - if (err < 0) - return -EIO; - - irq_set_status_flags(virq, IRQ_LEVEL); - irq_set_chip_and_handler(virq, &beatic_pic, handle_fasteoi_irq); - return 0; -} - -/* - * Translate device-tree interrupt spec to irq_hw_number_t style (ulong), - * to pass away to irq_create_mapping(). - * - * Called from irq_create_of_mapping() only. - * Note: We have only 1 entry to translate. - */ -static int beatic_pic_host_xlate(struct irq_domain *h, struct device_node *ct, - const u32 *intspec, unsigned int intsize, - irq_hw_number_t *out_hwirq, - unsigned int *out_flags) -{ - const u64 *intspec2 = (const u64 *)intspec; - - *out_hwirq = *intspec2; - *out_flags |= IRQ_TYPE_LEVEL_LOW; - return 0; -} - -static int beatic_pic_host_match(struct irq_domain *h, struct device_node *np) -{ - /* Match all */ - return 1; -} - -static const struct irq_domain_ops beatic_pic_host_ops = { - .map = beatic_pic_host_map, - .unmap = beatic_pic_host_unmap, - .xlate = beatic_pic_host_xlate, - .match = beatic_pic_host_match, -}; - -/* - * Get an IRQ number - * Note: returns VIRQ - */ -static inline unsigned int beatic_get_irq_plug(void) -{ - int i; - uint64_t pending[4], ub; - - for (i = 0; i < MAX_IRQS; i += 256) { - beat_detect_pending_interrupts(i, pending); - __asm__ ("cntlzd %0,%1":"=r"(ub): - "r"(pending[0] & beatic_irq_mask_enable[i/64+0] - & beatic_irq_mask_ack[i/64+0])); - if (ub != 64) - return i + ub + 0; - __asm__ ("cntlzd %0,%1":"=r"(ub): - "r"(pending[1] & beatic_irq_mask_enable[i/64+1] - & beatic_irq_mask_ack[i/64+1])); - if (ub != 64) - return i + ub + 64; - __asm__ ("cntlzd %0,%1":"=r"(ub): - "r"(pending[2] & beatic_irq_mask_enable[i/64+2] - & beatic_irq_mask_ack[i/64+2])); - if (ub != 64) - return i + ub + 128; - __asm__ ("cntlzd %0,%1":"=r"(ub): - "r"(pending[3] & beatic_irq_mask_enable[i/64+3] - & beatic_irq_mask_ack[i/64+3])); - if (ub != 64) - return i + ub + 192; - } - - return NO_IRQ; -} -unsigned int beatic_get_irq(void) -{ - unsigned int ret; - - ret = beatic_get_irq_plug(); - if (ret != NO_IRQ) - beatic_ack_irq(irq_get_irq_data(ret)); - return ret; -} - -/* - */ -void __init beatic_init_IRQ(void) -{ - int i; - - memset(beatic_irq_mask_enable, 0, sizeof(beatic_irq_mask_enable)); - memset(beatic_irq_mask_ack, 255, sizeof(beatic_irq_mask_ack)); - for (i = 0; i < MAX_IRQS; i += 256) - beat_set_interrupt_mask(i, 0L, 0L, 0L, 0L); - - /* Set out get_irq function */ - ppc_md.get_irq = beatic_get_irq; - - /* Allocate an irq host */ - beatic_host = irq_domain_add_nomap(NULL, ~0, &beatic_pic_host_ops, NULL); - BUG_ON(beatic_host == NULL); - irq_set_default_host(beatic_host); -} - -void beatic_deinit_IRQ(void) -{ - int i; - - for (i = 1; i < nr_irqs; i++) - beat_destruct_irq_plug(i); -} diff --git a/arch/powerpc/platforms/cell/beat_interrupt.h b/arch/powerpc/platforms/cell/beat_interrupt.h deleted file mode 100644 index a7e52f91a078..000000000000 --- a/arch/powerpc/platforms/cell/beat_interrupt.h +++ /dev/null @@ -1,30 +0,0 @@ -/* - * Celleb/Beat Interrupt controller - * - * (C) Copyright 2006 TOSHIBA CORPORATION - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#ifndef ASM_BEAT_PIC_H -#define ASM_BEAT_PIC_H -#ifdef __KERNEL__ - -extern void beatic_init_IRQ(void); -extern unsigned int beatic_get_irq(void); -extern void beatic_deinit_IRQ(void); - -#endif -#endif /* ASM_BEAT_PIC_H */ diff --git a/arch/powerpc/platforms/cell/beat_iommu.c b/arch/powerpc/platforms/cell/beat_iommu.c deleted file mode 100644 index 3ce685568935..000000000000 --- a/arch/powerpc/platforms/cell/beat_iommu.c +++ /dev/null @@ -1,115 +0,0 @@ -/* - * Support for IOMMU on Celleb platform. - * - * (C) Copyright 2006-2007 TOSHIBA CORPORATION - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/dma-mapping.h> -#include <linux/pci.h> -#include <linux/of_platform.h> - -#include <asm/machdep.h> - -#include "beat_wrapper.h" - -#define DMA_FLAGS 0xf800000000000000UL /* r/w permitted, coherency required, - strongest order */ - -static int __init find_dma_window(u64 *io_space_id, u64 *ioid, - u64 *base, u64 *size, u64 *io_page_size) -{ - struct device_node *dn; - const unsigned long *dma_window; - - for_each_node_by_type(dn, "ioif") { - dma_window = of_get_property(dn, "toshiba,dma-window", NULL); - if (dma_window) { - *io_space_id = (dma_window[0] >> 32) & 0xffffffffUL; - *ioid = dma_window[0] & 0x7ffUL; - *base = dma_window[1]; - *size = dma_window[2]; - *io_page_size = 1 << dma_window[3]; - of_node_put(dn); - return 1; - } - } - return 0; -} - -static unsigned long celleb_dma_direct_offset; - -static void __init celleb_init_direct_mapping(void) -{ - u64 lpar_addr, io_addr; - u64 io_space_id, ioid, dma_base, dma_size, io_page_size; - - if (!find_dma_window(&io_space_id, &ioid, &dma_base, &dma_size, - &io_page_size)) { - pr_info("No dma window found !\n"); - return; - } - - for (lpar_addr = 0; lpar_addr < dma_size; lpar_addr += io_page_size) { - io_addr = lpar_addr + dma_base; - (void)beat_put_iopte(io_space_id, io_addr, lpar_addr, - ioid, DMA_FLAGS); - } - - celleb_dma_direct_offset = dma_base; -} - -static void celleb_dma_dev_setup(struct device *dev) -{ - set_dma_ops(dev, &dma_direct_ops); - set_dma_offset(dev, celleb_dma_direct_offset); -} - -static void celleb_pci_dma_dev_setup(struct pci_dev *pdev) -{ - celleb_dma_dev_setup(&pdev->dev); -} - -static int celleb_of_bus_notify(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct device *dev = data; - - /* We are only intereted in device addition */ - if (action != BUS_NOTIFY_ADD_DEVICE) - return 0; - - celleb_dma_dev_setup(dev); - - return 0; -} - -static struct notifier_block celleb_of_bus_notifier = { - .notifier_call = celleb_of_bus_notify -}; - -static int __init celleb_init_iommu(void) -{ - celleb_init_direct_mapping(); - ppc_md.pci_dma_dev_setup = celleb_pci_dma_dev_setup; - bus_register_notifier(&platform_bus_type, &celleb_of_bus_notifier); - - return 0; -} - -machine_arch_initcall(celleb_beat, celleb_init_iommu); diff --git a/arch/powerpc/platforms/cell/beat_spu_priv1.c b/arch/powerpc/platforms/cell/beat_spu_priv1.c deleted file mode 100644 index 13f52589d3a9..000000000000 --- a/arch/powerpc/platforms/cell/beat_spu_priv1.c +++ /dev/null @@ -1,205 +0,0 @@ -/* - * spu hypervisor abstraction for Beat - * - * (C) Copyright 2006-2007 TOSHIBA CORPORATION - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#include <asm/types.h> -#include <asm/spu.h> -#include <asm/spu_priv1.h> - -#include "beat_wrapper.h" - -static inline void _int_mask_set(struct spu *spu, int class, u64 mask) -{ - spu->shadow_int_mask_RW[class] = mask; - beat_set_irq_mask_for_spe(spu->spe_id, class, mask); -} - -static inline u64 _int_mask_get(struct spu *spu, int class) -{ - return spu->shadow_int_mask_RW[class]; -} - -static void int_mask_set(struct spu *spu, int class, u64 mask) -{ - _int_mask_set(spu, class, mask); -} - -static u64 int_mask_get(struct spu *spu, int class) -{ - return _int_mask_get(spu, class); -} - -static void int_mask_and(struct spu *spu, int class, u64 mask) -{ - u64 old_mask; - old_mask = _int_mask_get(spu, class); - _int_mask_set(spu, class, old_mask & mask); -} - -static void int_mask_or(struct spu *spu, int class, u64 mask) -{ - u64 old_mask; - old_mask = _int_mask_get(spu, class); - _int_mask_set(spu, class, old_mask | mask); -} - -static void int_stat_clear(struct spu *spu, int class, u64 stat) -{ - beat_clear_interrupt_status_of_spe(spu->spe_id, class, stat); -} - -static u64 int_stat_get(struct spu *spu, int class) -{ - u64 int_stat; - beat_get_interrupt_status_of_spe(spu->spe_id, class, &int_stat); - return int_stat; -} - -static void cpu_affinity_set(struct spu *spu, int cpu) -{ - return; -} - -static u64 mfc_dar_get(struct spu *spu) -{ - u64 dar; - beat_get_spe_privileged_state_1_registers( - spu->spe_id, - offsetof(struct spu_priv1, mfc_dar_RW), &dar); - return dar; -} - -static u64 mfc_dsisr_get(struct spu *spu) -{ - u64 dsisr; - beat_get_spe_privileged_state_1_registers( - spu->spe_id, - offsetof(struct spu_priv1, mfc_dsisr_RW), &dsisr); - return dsisr; -} - -static void mfc_dsisr_set(struct spu *spu, u64 dsisr) -{ - beat_set_spe_privileged_state_1_registers( - spu->spe_id, - offsetof(struct spu_priv1, mfc_dsisr_RW), dsisr); -} - -static void mfc_sdr_setup(struct spu *spu) -{ - return; -} - -static void mfc_sr1_set(struct spu *spu, u64 sr1) -{ - beat_set_spe_privileged_state_1_registers( - spu->spe_id, - offsetof(struct spu_priv1, mfc_sr1_RW), sr1); -} - -static u64 mfc_sr1_get(struct spu *spu) -{ - u64 sr1; - beat_get_spe_privileged_state_1_registers( - spu->spe_id, - offsetof(struct spu_priv1, mfc_sr1_RW), &sr1); - return sr1; -} - -static void mfc_tclass_id_set(struct spu *spu, u64 tclass_id) -{ - beat_set_spe_privileged_state_1_registers( - spu->spe_id, - offsetof(struct spu_priv1, mfc_tclass_id_RW), tclass_id); -} - -static u64 mfc_tclass_id_get(struct spu *spu) -{ - u64 tclass_id; - beat_get_spe_privileged_state_1_registers( - spu->spe_id, - offsetof(struct spu_priv1, mfc_tclass_id_RW), &tclass_id); - return tclass_id; -} - -static void tlb_invalidate(struct spu *spu) -{ - beat_set_spe_privileged_state_1_registers( - spu->spe_id, - offsetof(struct spu_priv1, tlb_invalidate_entry_W), 0ul); -} - -static void resource_allocation_groupID_set(struct spu *spu, u64 id) -{ - beat_set_spe_privileged_state_1_registers( - spu->spe_id, - offsetof(struct spu_priv1, resource_allocation_groupID_RW), - id); -} - -static u64 resource_allocation_groupID_get(struct spu *spu) -{ - u64 id; - beat_get_spe_privileged_state_1_registers( - spu->spe_id, - offsetof(struct spu_priv1, resource_allocation_groupID_RW), - &id); - return id; -} - -static void resource_allocation_enable_set(struct spu *spu, u64 enable) -{ - beat_set_spe_privileged_state_1_registers( - spu->spe_id, - offsetof(struct spu_priv1, resource_allocation_enable_RW), - enable); -} - -static u64 resource_allocation_enable_get(struct spu *spu) -{ - u64 enable; - beat_get_spe_privileged_state_1_registers( - spu->spe_id, - offsetof(struct spu_priv1, resource_allocation_enable_RW), - &enable); - return enable; -} - -const struct spu_priv1_ops spu_priv1_beat_ops = { - .int_mask_and = int_mask_and, - .int_mask_or = int_mask_or, - .int_mask_set = int_mask_set, - .int_mask_get = int_mask_get, - .int_stat_clear = int_stat_clear, - .int_stat_get = int_stat_get, - .cpu_affinity_set = cpu_affinity_set, - .mfc_dar_get = mfc_dar_get, - .mfc_dsisr_get = mfc_dsisr_get, - .mfc_dsisr_set = mfc_dsisr_set, - .mfc_sdr_setup = mfc_sdr_setup, - .mfc_sr1_set = mfc_sr1_set, - .mfc_sr1_get = mfc_sr1_get, - .mfc_tclass_id_set = mfc_tclass_id_set, - .mfc_tclass_id_get = mfc_tclass_id_get, - .tlb_invalidate = tlb_invalidate, - .resource_allocation_groupID_set = resource_allocation_groupID_set, - .resource_allocation_groupID_get = resource_allocation_groupID_get, - .resource_allocation_enable_set = resource_allocation_enable_set, - .resource_allocation_enable_get = resource_allocation_enable_get, -}; diff --git a/arch/powerpc/platforms/cell/beat_syscall.h b/arch/powerpc/platforms/cell/beat_syscall.h deleted file mode 100644 index 8580dc7e1798..000000000000 --- a/arch/powerpc/platforms/cell/beat_syscall.h +++ /dev/null @@ -1,164 +0,0 @@ -/* - * Beat hypervisor call numbers - * - * (C) Copyright 2004-2007 TOSHIBA CORPORATION - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#ifndef BEAT_BEAT_syscall_H -#define BEAT_BEAT_syscall_H - -#ifdef __ASSEMBLY__ -#define __BEAT_ADD_VENDOR_ID(__x, __v) ((__v)<<60|(__x)) -#else -#define __BEAT_ADD_VENDOR_ID(__x, __v) ((u64)(__v)<<60|(__x)) -#endif -#define HV_allocate_memory __BEAT_ADD_VENDOR_ID(0, 0) -#define HV_construct_virtual_address_space __BEAT_ADD_VENDOR_ID(2, 0) -#define HV_destruct_virtual_address_space __BEAT_ADD_VENDOR_ID(10, 0) -#define HV_get_virtual_address_space_id_of_ppe __BEAT_ADD_VENDOR_ID(4, 0) -#define HV_query_logical_partition_address_region_info \ - __BEAT_ADD_VENDOR_ID(6, 0) -#define HV_release_memory __BEAT_ADD_VENDOR_ID(13, 0) -#define HV_select_virtual_address_space __BEAT_ADD_VENDOR_ID(7, 0) -#define HV_load_range_registers __BEAT_ADD_VENDOR_ID(68, 0) -#define HV_set_ppe_l2cache_rmt_entry __BEAT_ADD_VENDOR_ID(70, 0) -#define HV_set_ppe_tlb_rmt_entry __BEAT_ADD_VENDOR_ID(71, 0) -#define HV_set_spe_tlb_rmt_entry __BEAT_ADD_VENDOR_ID(72, 0) -#define HV_get_io_address_translation_fault_info __BEAT_ADD_VENDOR_ID(14, 0) -#define HV_get_iopte __BEAT_ADD_VENDOR_ID(16, 0) -#define HV_preload_iopt_cache __BEAT_ADD_VENDOR_ID(17, 0) -#define HV_put_iopte __BEAT_ADD_VENDOR_ID(15, 0) -#define HV_connect_event_ports __BEAT_ADD_VENDOR_ID(21, 0) -#define HV_construct_event_receive_port __BEAT_ADD_VENDOR_ID(18, 0) -#define HV_destruct_event_receive_port __BEAT_ADD_VENDOR_ID(19, 0) -#define HV_destruct_event_send_port __BEAT_ADD_VENDOR_ID(22, 0) -#define HV_get_state_of_event_send_port __BEAT_ADD_VENDOR_ID(25, 0) -#define HV_request_to_connect_event_ports __BEAT_ADD_VENDOR_ID(20, 0) -#define HV_send_event_externally __BEAT_ADD_VENDOR_ID(23, 0) -#define HV_send_event_locally __BEAT_ADD_VENDOR_ID(24, 0) -#define HV_construct_and_connect_irq_plug __BEAT_ADD_VENDOR_ID(28, 0) -#define HV_destruct_irq_plug __BEAT_ADD_VENDOR_ID(29, 0) -#define HV_detect_pending_interrupts __BEAT_ADD_VENDOR_ID(26, 0) -#define HV_end_of_interrupt __BEAT_ADD_VENDOR_ID(27, 0) -#define HV_assign_control_signal_notification_port __BEAT_ADD_VENDOR_ID(45, 0) -#define HV_end_of_control_signal_processing __BEAT_ADD_VENDOR_ID(48, 0) -#define HV_get_control_signal __BEAT_ADD_VENDOR_ID(46, 0) -#define HV_set_irq_mask_for_spe __BEAT_ADD_VENDOR_ID(61, 0) -#define HV_shutdown_logical_partition __BEAT_ADD_VENDOR_ID(44, 0) -#define HV_connect_message_ports __BEAT_ADD_VENDOR_ID(35, 0) -#define HV_destruct_message_port __BEAT_ADD_VENDOR_ID(36, 0) -#define HV_receive_message __BEAT_ADD_VENDOR_ID(37, 0) -#define HV_get_message_port_info __BEAT_ADD_VENDOR_ID(34, 0) -#define HV_request_to_connect_message_ports __BEAT_ADD_VENDOR_ID(33, 0) -#define HV_send_message __BEAT_ADD_VENDOR_ID(32, 0) -#define HV_get_logical_ppe_id __BEAT_ADD_VENDOR_ID(69, 0) -#define HV_pause __BEAT_ADD_VENDOR_ID(9, 0) -#define HV_destruct_shared_memory_handle __BEAT_ADD_VENDOR_ID(51, 0) -#define HV_get_shared_memory_info __BEAT_ADD_VENDOR_ID(52, 0) -#define HV_permit_sharing_memory __BEAT_ADD_VENDOR_ID(50, 0) -#define HV_request_to_attach_shared_memory __BEAT_ADD_VENDOR_ID(49, 0) -#define HV_enable_logical_spe_execution __BEAT_ADD_VENDOR_ID(55, 0) -#define HV_construct_logical_spe __BEAT_ADD_VENDOR_ID(53, 0) -#define HV_disable_logical_spe_execution __BEAT_ADD_VENDOR_ID(56, 0) -#define HV_destruct_logical_spe __BEAT_ADD_VENDOR_ID(54, 0) -#define HV_sense_spe_execution_status __BEAT_ADD_VENDOR_ID(58, 0) -#define HV_insert_htab_entry __BEAT_ADD_VENDOR_ID(101, 0) -#define HV_read_htab_entries __BEAT_ADD_VENDOR_ID(95, 0) -#define HV_write_htab_entry __BEAT_ADD_VENDOR_ID(94, 0) -#define HV_assign_io_address_translation_fault_port \ - __BEAT_ADD_VENDOR_ID(100, 0) -#define HV_set_interrupt_mask __BEAT_ADD_VENDOR_ID(73, 0) -#define HV_get_logical_partition_id __BEAT_ADD_VENDOR_ID(74, 0) -#define HV_create_repository_node2 __BEAT_ADD_VENDOR_ID(90, 0) -#define HV_create_repository_node __BEAT_ADD_VENDOR_ID(90, 0) /* alias */ -#define HV_get_repository_node_value2 __BEAT_ADD_VENDOR_ID(91, 0) -#define HV_get_repository_node_value __BEAT_ADD_VENDOR_ID(91, 0) /* alias */ -#define HV_modify_repository_node_value2 __BEAT_ADD_VENDOR_ID(92, 0) -#define HV_modify_repository_node_value __BEAT_ADD_VENDOR_ID(92, 0) /* alias */ -#define HV_remove_repository_node2 __BEAT_ADD_VENDOR_ID(93, 0) -#define HV_remove_repository_node __BEAT_ADD_VENDOR_ID(93, 0) /* alias */ -#define HV_cancel_shared_memory __BEAT_ADD_VENDOR_ID(104, 0) -#define HV_clear_interrupt_status_of_spe __BEAT_ADD_VENDOR_ID(206, 0) -#define HV_construct_spe_irq_outlet __BEAT_ADD_VENDOR_ID(80, 0) -#define HV_destruct_spe_irq_outlet __BEAT_ADD_VENDOR_ID(81, 0) -#define HV_disconnect_ipspc_service __BEAT_ADD_VENDOR_ID(88, 0) -#define HV_execute_ipspc_command __BEAT_ADD_VENDOR_ID(86, 0) -#define HV_get_interrupt_status_of_spe __BEAT_ADD_VENDOR_ID(205, 0) -#define HV_get_spe_privileged_state_1_registers __BEAT_ADD_VENDOR_ID(208, 0) -#define HV_permit_use_of_ipspc_service __BEAT_ADD_VENDOR_ID(85, 0) -#define HV_reinitialize_logical_spe __BEAT_ADD_VENDOR_ID(82, 0) -#define HV_request_ipspc_service __BEAT_ADD_VENDOR_ID(84, 0) -#define HV_stop_ipspc_command __BEAT_ADD_VENDOR_ID(87, 0) -#define HV_set_spe_privileged_state_1_registers __BEAT_ADD_VENDOR_ID(204, 0) -#define HV_get_status_of_ipspc_service __BEAT_ADD_VENDOR_ID(203, 0) -#define HV_put_characters_to_console __BEAT_ADD_VENDOR_ID(0x101, 1) -#define HV_get_characters_from_console __BEAT_ADD_VENDOR_ID(0x102, 1) -#define HV_get_base_clock __BEAT_ADD_VENDOR_ID(0x111, 1) -#define HV_set_base_clock __BEAT_ADD_VENDOR_ID(0x112, 1) -#define HV_get_frame_cycle __BEAT_ADD_VENDOR_ID(0x114, 1) -#define HV_disable_console __BEAT_ADD_VENDOR_ID(0x115, 1) -#define HV_disable_all_console __BEAT_ADD_VENDOR_ID(0x116, 1) -#define HV_oneshot_timer __BEAT_ADD_VENDOR_ID(0x117, 1) -#define HV_set_dabr __BEAT_ADD_VENDOR_ID(0x118, 1) -#define HV_get_dabr __BEAT_ADD_VENDOR_ID(0x119, 1) -#define HV_start_hv_stats __BEAT_ADD_VENDOR_ID(0x21c, 1) -#define HV_stop_hv_stats __BEAT_ADD_VENDOR_ID(0x21d, 1) -#define HV_get_hv_stats __BEAT_ADD_VENDOR_ID(0x21e, 1) -#define HV_get_hv_error_stats __BEAT_ADD_VENDOR_ID(0x221, 1) -#define HV_get_stats __BEAT_ADD_VENDOR_ID(0x224, 1) -#define HV_get_heap_stats __BEAT_ADD_VENDOR_ID(0x225, 1) -#define HV_get_memory_stats __BEAT_ADD_VENDOR_ID(0x227, 1) -#define HV_get_memory_detail __BEAT_ADD_VENDOR_ID(0x228, 1) -#define HV_set_priority_of_irq_outlet __BEAT_ADD_VENDOR_ID(0x122, 1) -#define HV_get_physical_spe_by_reservation_id __BEAT_ADD_VENDOR_ID(0x128, 1) -#define HV_get_spe_context __BEAT_ADD_VENDOR_ID(0x129, 1) -#define HV_set_spe_context __BEAT_ADD_VENDOR_ID(0x12a, 1) -#define HV_downcount_of_interrupt __BEAT_ADD_VENDOR_ID(0x12e, 1) -#define HV_peek_spe_context __BEAT_ADD_VENDOR_ID(0x12f, 1) -#define HV_read_bpa_register __BEAT_ADD_VENDOR_ID(0x131, 1) -#define HV_write_bpa_register __BEAT_ADD_VENDOR_ID(0x132, 1) -#define HV_map_context_table_of_spe __BEAT_ADD_VENDOR_ID(0x137, 1) -#define HV_get_slb_for_logical_spe __BEAT_ADD_VENDOR_ID(0x138, 1) -#define HV_set_slb_for_logical_spe __BEAT_ADD_VENDOR_ID(0x139, 1) -#define HV_init_pm __BEAT_ADD_VENDOR_ID(0x150, 1) -#define HV_set_pm_signal __BEAT_ADD_VENDOR_ID(0x151, 1) -#define HV_get_pm_signal __BEAT_ADD_VENDOR_ID(0x152, 1) -#define HV_set_pm_config __BEAT_ADD_VENDOR_ID(0x153, 1) -#define HV_get_pm_config __BEAT_ADD_VENDOR_ID(0x154, 1) -#define HV_get_inner_trace_data __BEAT_ADD_VENDOR_ID(0x155, 1) -#define HV_set_ext_trace_buffer __BEAT_ADD_VENDOR_ID(0x156, 1) -#define HV_get_ext_trace_buffer __BEAT_ADD_VENDOR_ID(0x157, 1) -#define HV_set_pm_interrupt __BEAT_ADD_VENDOR_ID(0x158, 1) -#define HV_get_pm_interrupt __BEAT_ADD_VENDOR_ID(0x159, 1) -#define HV_kick_pm __BEAT_ADD_VENDOR_ID(0x160, 1) -#define HV_construct_pm_context __BEAT_ADD_VENDOR_ID(0x164, 1) -#define HV_destruct_pm_context __BEAT_ADD_VENDOR_ID(0x165, 1) -#define HV_be_slow __BEAT_ADD_VENDOR_ID(0x170, 1) -#define HV_assign_ipspc_server_connection_status_notification_port \ - __BEAT_ADD_VENDOR_ID(0x173, 1) -#define HV_get_raid_of_physical_spe __BEAT_ADD_VENDOR_ID(0x174, 1) -#define HV_set_physical_spe_to_rag __BEAT_ADD_VENDOR_ID(0x175, 1) -#define HV_release_physical_spe_from_rag __BEAT_ADD_VENDOR_ID(0x176, 1) -#define HV_rtc_read __BEAT_ADD_VENDOR_ID(0x190, 1) -#define HV_rtc_write __BEAT_ADD_VENDOR_ID(0x191, 1) -#define HV_eeprom_read __BEAT_ADD_VENDOR_ID(0x192, 1) -#define HV_eeprom_write __BEAT_ADD_VENDOR_ID(0x193, 1) -#define HV_insert_htab_entry3 __BEAT_ADD_VENDOR_ID(0x104, 1) -#define HV_invalidate_htab_entry3 __BEAT_ADD_VENDOR_ID(0x105, 1) -#define HV_update_htab_permission3 __BEAT_ADD_VENDOR_ID(0x106, 1) -#define HV_clear_htab3 __BEAT_ADD_VENDOR_ID(0x107, 1) -#endif diff --git a/arch/powerpc/platforms/cell/beat_udbg.c b/arch/powerpc/platforms/cell/beat_udbg.c deleted file mode 100644 index 350735bc8888..000000000000 --- a/arch/powerpc/platforms/cell/beat_udbg.c +++ /dev/null @@ -1,98 +0,0 @@ -/* - * udbg function for Beat - * - * (C) Copyright 2006 TOSHIBA CORPORATION - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#include <linux/kernel.h> -#include <linux/console.h> - -#include <asm/machdep.h> -#include <asm/prom.h> -#include <asm/udbg.h> - -#include "beat.h" - -#define celleb_vtermno 0 - -static void udbg_putc_beat(char c) -{ - unsigned long rc; - - if (c == '\n') - udbg_putc_beat('\r'); - - rc = beat_put_term_char(celleb_vtermno, 1, (uint64_t)c << 56, 0); -} - -/* Buffered chars getc */ -static u64 inbuflen; -static u64 inbuf[2]; /* must be 2 u64s */ - -static int udbg_getc_poll_beat(void) -{ - /* The interface is tricky because it may return up to 16 chars. - * We save them statically for future calls to udbg_getc(). - */ - char ch, *buf = (char *)inbuf; - int i; - long rc; - if (inbuflen == 0) { - /* get some more chars. */ - inbuflen = 0; - rc = beat_get_term_char(celleb_vtermno, &inbuflen, - inbuf+0, inbuf+1); - if (rc != 0) - inbuflen = 0; /* otherwise inbuflen is garbage */ - } - if (inbuflen <= 0 || inbuflen > 16) { - /* Catch error case as well as other oddities (corruption) */ - inbuflen = 0; - return -1; - } - ch = buf[0]; - for (i = 1; i < inbuflen; i++) /* shuffle them down. */ - buf[i-1] = buf[i]; - inbuflen--; - return ch; -} - -static int udbg_getc_beat(void) -{ - int ch; - for (;;) { - ch = udbg_getc_poll_beat(); - if (ch == -1) { - /* This shouldn't be needed...but... */ - volatile unsigned long delay; - for (delay = 0; delay < 2000000; delay++) - ; - } else { - return ch; - } - } -} - -/* call this from early_init() for a working debug console on - * vterm capable LPAR machines - */ -void __init udbg_init_debug_beat(void) -{ - udbg_putc = udbg_putc_beat; - udbg_getc = udbg_getc_beat; - udbg_getc_poll = udbg_getc_poll_beat; -} diff --git a/arch/powerpc/platforms/cell/beat_wrapper.h b/arch/powerpc/platforms/cell/beat_wrapper.h deleted file mode 100644 index c1109969f242..000000000000 --- a/arch/powerpc/platforms/cell/beat_wrapper.h +++ /dev/null @@ -1,290 +0,0 @@ -/* - * Beat hypervisor call I/F - * - * (C) Copyright 2007 TOSHIBA CORPORATION - * - * This code is based on arch/powerpc/platforms/pseries/plpar_wrapper.h. - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ -#ifndef BEAT_HCALL -#include <linux/string.h> -#include "beat_syscall.h" - -/* defined in hvCall.S */ -extern s64 beat_hcall_norets(u64 opcode, ...); -extern s64 beat_hcall_norets8(u64 opcode, u64 arg1, u64 arg2, u64 arg3, - u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8); -extern s64 beat_hcall1(u64 opcode, u64 retbuf[1], ...); -extern s64 beat_hcall2(u64 opcode, u64 retbuf[2], ...); -extern s64 beat_hcall3(u64 opcode, u64 retbuf[3], ...); -extern s64 beat_hcall4(u64 opcode, u64 retbuf[4], ...); -extern s64 beat_hcall5(u64 opcode, u64 retbuf[5], ...); -extern s64 beat_hcall6(u64 opcode, u64 retbuf[6], ...); - -static inline s64 beat_downcount_of_interrupt(u64 plug_id) -{ - return beat_hcall_norets(HV_downcount_of_interrupt, plug_id); -} - -static inline s64 beat_set_interrupt_mask(u64 index, - u64 val0, u64 val1, u64 val2, u64 val3) -{ - return beat_hcall_norets(HV_set_interrupt_mask, index, - val0, val1, val2, val3); -} - -static inline s64 beat_destruct_irq_plug(u64 plug_id) -{ - return beat_hcall_norets(HV_destruct_irq_plug, plug_id); -} - -static inline s64 beat_construct_and_connect_irq_plug(u64 plug_id, - u64 outlet_id) -{ - return beat_hcall_norets(HV_construct_and_connect_irq_plug, plug_id, - outlet_id); -} - -static inline s64 beat_detect_pending_interrupts(u64 index, u64 *retbuf) -{ - return beat_hcall4(HV_detect_pending_interrupts, retbuf, index); -} - -static inline s64 beat_pause(u64 style) -{ - return beat_hcall_norets(HV_pause, style); -} - -static inline s64 beat_read_htab_entries(u64 htab_id, u64 index, u64 *retbuf) -{ - return beat_hcall5(HV_read_htab_entries, retbuf, htab_id, index); -} - -static inline s64 beat_insert_htab_entry(u64 htab_id, u64 group, - u64 bitmask, u64 hpte_v, u64 hpte_r, u64 *slot) -{ - u64 dummy[3]; - s64 ret; - - ret = beat_hcall3(HV_insert_htab_entry, dummy, htab_id, group, - bitmask, hpte_v, hpte_r); - *slot = dummy[0]; - return ret; -} - -static inline s64 beat_write_htab_entry(u64 htab_id, u64 slot, - u64 hpte_v, u64 hpte_r, u64 mask_v, u64 mask_r, - u64 *ret_v, u64 *ret_r) -{ - u64 dummy[2]; - s64 ret; - - ret = beat_hcall2(HV_write_htab_entry, dummy, htab_id, slot, - hpte_v, hpte_r, mask_v, mask_r); - *ret_v = dummy[0]; - *ret_r = dummy[1]; - return ret; -} - -static inline s64 beat_insert_htab_entry3(u64 htab_id, u64 group, - u64 hpte_v, u64 hpte_r, u64 mask_v, u64 value_v, u64 *slot) -{ - u64 dummy[1]; - s64 ret; - - ret = beat_hcall1(HV_insert_htab_entry3, dummy, htab_id, group, - hpte_v, hpte_r, mask_v, value_v); - *slot = dummy[0]; - return ret; -} - -static inline s64 beat_invalidate_htab_entry3(u64 htab_id, u64 group, - u64 va, u64 pss) -{ - return beat_hcall_norets(HV_invalidate_htab_entry3, - htab_id, group, va, pss); -} - -static inline s64 beat_update_htab_permission3(u64 htab_id, u64 group, - u64 va, u64 pss, u64 ptel_mask, u64 ptel_value) -{ - return beat_hcall_norets(HV_update_htab_permission3, - htab_id, group, va, pss, ptel_mask, ptel_value); -} - -static inline s64 beat_clear_htab3(u64 htab_id) -{ - return beat_hcall_norets(HV_clear_htab3, htab_id); -} - -static inline void beat_shutdown_logical_partition(u64 code) -{ - (void)beat_hcall_norets(HV_shutdown_logical_partition, code); -} - -static inline s64 beat_rtc_write(u64 time_from_epoch) -{ - return beat_hcall_norets(HV_rtc_write, time_from_epoch); -} - -static inline s64 beat_rtc_read(u64 *time_from_epoch) -{ - u64 dummy[1]; - s64 ret; - - ret = beat_hcall1(HV_rtc_read, dummy); - *time_from_epoch = dummy[0]; - return ret; -} - -#define BEAT_NVRW_CNT (sizeof(u64) * 6) - -static inline s64 beat_eeprom_write(u64 index, u64 length, u8 *buffer) -{ - u64 b[6]; - - if (length > BEAT_NVRW_CNT) - return -1; - memcpy(b, buffer, sizeof(b)); - return beat_hcall_norets8(HV_eeprom_write, index, length, - b[0], b[1], b[2], b[3], b[4], b[5]); -} - -static inline s64 beat_eeprom_read(u64 index, u64 length, u8 *buffer) -{ - u64 b[6]; - s64 ret; - - if (length > BEAT_NVRW_CNT) - return -1; - ret = beat_hcall6(HV_eeprom_read, b, index, length); - memcpy(buffer, b, length); - return ret; -} - -static inline s64 beat_set_dabr(u64 value, u64 style) -{ - return beat_hcall_norets(HV_set_dabr, value, style); -} - -static inline s64 beat_get_characters_from_console(u64 termno, u64 *len, - u8 *buffer) -{ - u64 dummy[3]; - s64 ret; - - ret = beat_hcall3(HV_get_characters_from_console, dummy, termno, len); - *len = dummy[0]; - memcpy(buffer, dummy + 1, *len); - return ret; -} - -static inline s64 beat_put_characters_to_console(u64 termno, u64 len, - u8 *buffer) -{ - u64 b[2]; - - memcpy(b, buffer, len); - return beat_hcall_norets(HV_put_characters_to_console, termno, len, - b[0], b[1]); -} - -static inline s64 beat_get_spe_privileged_state_1_registers( - u64 id, u64 offsetof, u64 *value) -{ - u64 dummy[1]; - s64 ret; - - ret = beat_hcall1(HV_get_spe_privileged_state_1_registers, dummy, id, - offsetof); - *value = dummy[0]; - return ret; -} - -static inline s64 beat_set_irq_mask_for_spe(u64 id, u64 class, u64 mask) -{ - return beat_hcall_norets(HV_set_irq_mask_for_spe, id, class, mask); -} - -static inline s64 beat_clear_interrupt_status_of_spe(u64 id, u64 class, - u64 mask) -{ - return beat_hcall_norets(HV_clear_interrupt_status_of_spe, - id, class, mask); -} - -static inline s64 beat_set_spe_privileged_state_1_registers( - u64 id, u64 offsetof, u64 value) -{ - return beat_hcall_norets(HV_set_spe_privileged_state_1_registers, - id, offsetof, value); -} - -static inline s64 beat_get_interrupt_status_of_spe(u64 id, u64 class, u64 *val) -{ - u64 dummy[1]; - s64 ret; - - ret = beat_hcall1(HV_get_interrupt_status_of_spe, dummy, id, class); - *val = dummy[0]; - return ret; -} - -static inline s64 beat_put_iopte(u64 ioas_id, u64 io_addr, u64 real_addr, - u64 ioid, u64 flags) -{ - return beat_hcall_norets(HV_put_iopte, ioas_id, io_addr, real_addr, - ioid, flags); -} - -static inline s64 beat_construct_event_receive_port(u64 *port) -{ - u64 dummy[1]; - s64 ret; - - ret = beat_hcall1(HV_construct_event_receive_port, dummy); - *port = dummy[0]; - return ret; -} - -static inline s64 beat_destruct_event_receive_port(u64 port) -{ - s64 ret; - - ret = beat_hcall_norets(HV_destruct_event_receive_port, port); - return ret; -} - -static inline s64 beat_create_repository_node(u64 path[4], u64 data[2]) -{ - s64 ret; - - ret = beat_hcall_norets(HV_create_repository_node2, - path[0], path[1], path[2], path[3], data[0], data[1]); - return ret; -} - -static inline s64 beat_get_repository_node_value(u64 lpid, u64 path[4], - u64 data[2]) -{ - s64 ret; - - ret = beat_hcall2(HV_get_repository_node_value2, data, - lpid, path[0], path[1], path[2], path[3]); - return ret; -} - -#endif diff --git a/arch/powerpc/platforms/cell/cell.h b/arch/powerpc/platforms/cell/cell.h new file mode 100644 index 000000000000..ef143dfee068 --- /dev/null +++ b/arch/powerpc/platforms/cell/cell.h @@ -0,0 +1,24 @@ +/* + * Cell Platform common data structures + * + * Copyright 2015, Daniel Axtens, IBM Corporation + * + * 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, or (at your option) + * any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef CELL_H +#define CELL_H + +#include <asm/pci-bridge.h> + +extern struct pci_controller_ops cell_pci_controller_ops; + +#endif diff --git a/arch/powerpc/platforms/cell/celleb_pci.c b/arch/powerpc/platforms/cell/celleb_pci.c deleted file mode 100644 index 3ce70ded2d6a..000000000000 --- a/arch/powerpc/platforms/cell/celleb_pci.c +++ /dev/null @@ -1,500 +0,0 @@ -/* - * Support for PCI on Celleb platform. - * - * (C) Copyright 2006-2007 TOSHIBA CORPORATION - * - * This code is based on arch/powerpc/kernel/rtas_pci.c: - * Copyright (C) 2001 Dave Engebretsen, IBM Corporation - * Copyright (C) 2003 Anton Blanchard <anton@au.ibm.com>, IBM - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#undef DEBUG - -#include <linux/kernel.h> -#include <linux/threads.h> -#include <linux/pci.h> -#include <linux/string.h> -#include <linux/init.h> -#include <linux/memblock.h> -#include <linux/pci_regs.h> -#include <linux/of.h> -#include <linux/of_device.h> -#include <linux/slab.h> - -#include <asm/io.h> -#include <asm/irq.h> -#include <asm/prom.h> -#include <asm/pci-bridge.h> -#include <asm/ppc-pci.h> - -#include "celleb_pci.h" - -#define MAX_PCI_DEVICES 32 -#define MAX_PCI_FUNCTIONS 8 -#define MAX_PCI_BASE_ADDRS 3 /* use 64 bit address */ - -/* definition for fake pci configuration area for GbE, .... ,and etc. */ - -struct celleb_pci_resource { - struct resource r[MAX_PCI_BASE_ADDRS]; -}; - -struct celleb_pci_private { - unsigned char *fake_config[MAX_PCI_DEVICES][MAX_PCI_FUNCTIONS]; - struct celleb_pci_resource *res[MAX_PCI_DEVICES][MAX_PCI_FUNCTIONS]; -}; - -static inline u8 celleb_fake_config_readb(void *addr) -{ - u8 *p = addr; - return *p; -} - -static inline u16 celleb_fake_config_readw(void *addr) -{ - __le16 *p = addr; - return le16_to_cpu(*p); -} - -static inline u32 celleb_fake_config_readl(void *addr) -{ - __le32 *p = addr; - return le32_to_cpu(*p); -} - -static inline void celleb_fake_config_writeb(u32 val, void *addr) -{ - u8 *p = addr; - *p = val; -} - -static inline void celleb_fake_config_writew(u32 val, void *addr) -{ - __le16 val16; - __le16 *p = addr; - val16 = cpu_to_le16(val); - *p = val16; -} - -static inline void celleb_fake_config_writel(u32 val, void *addr) -{ - __le32 val32; - __le32 *p = addr; - val32 = cpu_to_le32(val); - *p = val32; -} - -static unsigned char *get_fake_config_start(struct pci_controller *hose, - int devno, int fn) -{ - struct celleb_pci_private *private = hose->private_data; - - if (private == NULL) - return NULL; - - return private->fake_config[devno][fn]; -} - -static struct celleb_pci_resource *get_resource_start( - struct pci_controller *hose, - int devno, int fn) -{ - struct celleb_pci_private *private = hose->private_data; - - if (private == NULL) - return NULL; - - return private->res[devno][fn]; -} - - -static void celleb_config_read_fake(unsigned char *config, int where, - int size, u32 *val) -{ - char *p = config + where; - - switch (size) { - case 1: - *val = celleb_fake_config_readb(p); - break; - case 2: - *val = celleb_fake_config_readw(p); - break; - case 4: - *val = celleb_fake_config_readl(p); - break; - } -} - -static void celleb_config_write_fake(unsigned char *config, int where, - int size, u32 val) -{ - char *p = config + where; - - switch (size) { - case 1: - celleb_fake_config_writeb(val, p); - break; - case 2: - celleb_fake_config_writew(val, p); - break; - case 4: - celleb_fake_config_writel(val, p); - break; - } -} - -static int celleb_fake_pci_read_config(struct pci_bus *bus, - unsigned int devfn, int where, int size, u32 *val) -{ - char *config; - struct pci_controller *hose = pci_bus_to_host(bus); - unsigned int devno = devfn >> 3; - unsigned int fn = devfn & 0x7; - - /* allignment check */ - BUG_ON(where % size); - - pr_debug(" fake read: bus=0x%x, ", bus->number); - config = get_fake_config_start(hose, devno, fn); - - pr_debug("devno=0x%x, where=0x%x, size=0x%x, ", devno, where, size); - if (!config) { - pr_debug("failed\n"); - return PCIBIOS_DEVICE_NOT_FOUND; - } - - celleb_config_read_fake(config, where, size, val); - pr_debug("val=0x%x\n", *val); - - return PCIBIOS_SUCCESSFUL; -} - - -static int celleb_fake_pci_write_config(struct pci_bus *bus, - unsigned int devfn, int where, int size, u32 val) -{ - char *config; - struct pci_controller *hose = pci_bus_to_host(bus); - struct celleb_pci_resource *res; - unsigned int devno = devfn >> 3; - unsigned int fn = devfn & 0x7; - - /* allignment check */ - BUG_ON(where % size); - - config = get_fake_config_start(hose, devno, fn); - - if (!config) - return PCIBIOS_DEVICE_NOT_FOUND; - - if (val == ~0) { - int i = (where - PCI_BASE_ADDRESS_0) >> 3; - - switch (where) { - case PCI_BASE_ADDRESS_0: - case PCI_BASE_ADDRESS_2: - if (size != 4) - return PCIBIOS_DEVICE_NOT_FOUND; - res = get_resource_start(hose, devno, fn); - if (!res) - return PCIBIOS_DEVICE_NOT_FOUND; - celleb_config_write_fake(config, where, size, - (res->r[i].end - res->r[i].start)); - return PCIBIOS_SUCCESSFUL; - case PCI_BASE_ADDRESS_1: - case PCI_BASE_ADDRESS_3: - case PCI_BASE_ADDRESS_4: - case PCI_BASE_ADDRESS_5: - break; - default: - break; - } - } - - celleb_config_write_fake(config, where, size, val); - pr_debug(" fake write: where=%x, size=%d, val=%x\n", - where, size, val); - - return PCIBIOS_SUCCESSFUL; -} - -static struct pci_ops celleb_fake_pci_ops = { - .read = celleb_fake_pci_read_config, - .write = celleb_fake_pci_write_config, -}; - -static inline void celleb_setup_pci_base_addrs(struct pci_controller *hose, - unsigned int devno, unsigned int fn, - unsigned int num_base_addr) -{ - u32 val; - unsigned char *config; - struct celleb_pci_resource *res; - - config = get_fake_config_start(hose, devno, fn); - res = get_resource_start(hose, devno, fn); - - if (!config || !res) - return; - - switch (num_base_addr) { - case 3: - val = (res->r[2].start & 0xfffffff0) - | PCI_BASE_ADDRESS_MEM_TYPE_64; - celleb_config_write_fake(config, PCI_BASE_ADDRESS_4, 4, val); - val = res->r[2].start >> 32; - celleb_config_write_fake(config, PCI_BASE_ADDRESS_5, 4, val); - /* FALLTHROUGH */ - case 2: - val = (res->r[1].start & 0xfffffff0) - | PCI_BASE_ADDRESS_MEM_TYPE_64; - celleb_config_write_fake(config, PCI_BASE_ADDRESS_2, 4, val); - val = res->r[1].start >> 32; - celleb_config_write_fake(config, PCI_BASE_ADDRESS_3, 4, val); - /* FALLTHROUGH */ - case 1: - val = (res->r[0].start & 0xfffffff0) - | PCI_BASE_ADDRESS_MEM_TYPE_64; - celleb_config_write_fake(config, PCI_BASE_ADDRESS_0, 4, val); - val = res->r[0].start >> 32; - celleb_config_write_fake(config, PCI_BASE_ADDRESS_1, 4, val); - break; - } - - val = PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER; - celleb_config_write_fake(config, PCI_COMMAND, 2, val); -} - -static int __init celleb_setup_fake_pci_device(struct device_node *node, - struct pci_controller *hose) -{ - unsigned int rlen; - int num_base_addr = 0; - u32 val; - const u32 *wi0, *wi1, *wi2, *wi3, *wi4; - unsigned int devno, fn; - struct celleb_pci_private *private = hose->private_data; - unsigned char **config = NULL; - struct celleb_pci_resource **res = NULL; - const char *name; - const unsigned long *li; - int size, result; - - if (private == NULL) { - printk(KERN_ERR "PCI: " - "memory space for pci controller is not assigned\n"); - goto error; - } - - name = of_get_property(node, "model", &rlen); - if (!name) { - printk(KERN_ERR "PCI: model property not found.\n"); - goto error; - } - - wi4 = of_get_property(node, "reg", &rlen); - if (wi4 == NULL) - goto error; - - devno = ((wi4[0] >> 8) & 0xff) >> 3; - fn = (wi4[0] >> 8) & 0x7; - - pr_debug("PCI: celleb_setup_fake_pci() %s devno=%x fn=%x\n", name, - devno, fn); - - size = 256; - config = &private->fake_config[devno][fn]; - *config = zalloc_maybe_bootmem(size, GFP_KERNEL); - if (*config == NULL) { - printk(KERN_ERR "PCI: " - "not enough memory for fake configuration space\n"); - goto error; - } - pr_debug("PCI: fake config area assigned 0x%016lx\n", - (unsigned long)*config); - - size = sizeof(struct celleb_pci_resource); - res = &private->res[devno][fn]; - *res = zalloc_maybe_bootmem(size, GFP_KERNEL); - if (*res == NULL) { - printk(KERN_ERR - "PCI: not enough memory for resource data space\n"); - goto error; - } - pr_debug("PCI: res assigned 0x%016lx\n", (unsigned long)*res); - - wi0 = of_get_property(node, "device-id", NULL); - wi1 = of_get_property(node, "vendor-id", NULL); - wi2 = of_get_property(node, "class-code", NULL); - wi3 = of_get_property(node, "revision-id", NULL); - if (!wi0 || !wi1 || !wi2 || !wi3) { - printk(KERN_ERR "PCI: Missing device tree properties.\n"); - goto error; - } - - celleb_config_write_fake(*config, PCI_DEVICE_ID, 2, wi0[0] & 0xffff); - celleb_config_write_fake(*config, PCI_VENDOR_ID, 2, wi1[0] & 0xffff); - pr_debug("class-code = 0x%08x\n", wi2[0]); - - celleb_config_write_fake(*config, PCI_CLASS_PROG, 1, wi2[0] & 0xff); - celleb_config_write_fake(*config, PCI_CLASS_DEVICE, 2, - (wi2[0] >> 8) & 0xffff); - celleb_config_write_fake(*config, PCI_REVISION_ID, 1, wi3[0]); - - while (num_base_addr < MAX_PCI_BASE_ADDRS) { - result = of_address_to_resource(node, - num_base_addr, &(*res)->r[num_base_addr]); - if (result) - break; - num_base_addr++; - } - - celleb_setup_pci_base_addrs(hose, devno, fn, num_base_addr); - - li = of_get_property(node, "interrupts", &rlen); - if (!li) { - printk(KERN_ERR "PCI: interrupts not found.\n"); - goto error; - } - val = li[0]; - celleb_config_write_fake(*config, PCI_INTERRUPT_PIN, 1, 1); - celleb_config_write_fake(*config, PCI_INTERRUPT_LINE, 1, val); - -#ifdef DEBUG - pr_debug("PCI: %s irq=%ld\n", name, li[0]); - for (i = 0; i < 6; i++) { - celleb_config_read_fake(*config, - PCI_BASE_ADDRESS_0 + 0x4 * i, 4, - &val); - pr_debug("PCI: %s fn=%d base_address_%d=0x%x\n", - name, fn, i, val); - } -#endif - - celleb_config_write_fake(*config, PCI_HEADER_TYPE, 1, - PCI_HEADER_TYPE_NORMAL); - - return 0; - -error: - if (mem_init_done) { - if (config && *config) - kfree(*config); - if (res && *res) - kfree(*res); - - } else { - if (config && *config) { - size = 256; - memblock_free(__pa(*config), size); - } - if (res && *res) { - size = sizeof(struct celleb_pci_resource); - memblock_free(__pa(*res), size); - } - } - - return 1; -} - -static int __init phb_set_bus_ranges(struct device_node *dev, - struct pci_controller *phb) -{ - const int *bus_range; - unsigned int len; - - bus_range = of_get_property(dev, "bus-range", &len); - if (bus_range == NULL || len < 2 * sizeof(int)) - return 1; - - phb->first_busno = bus_range[0]; - phb->last_busno = bus_range[1]; - - return 0; -} - -static void __init celleb_alloc_private_mem(struct pci_controller *hose) -{ - hose->private_data = - zalloc_maybe_bootmem(sizeof(struct celleb_pci_private), - GFP_KERNEL); -} - -static int __init celleb_setup_fake_pci(struct device_node *dev, - struct pci_controller *phb) -{ - struct device_node *node; - - phb->ops = &celleb_fake_pci_ops; - celleb_alloc_private_mem(phb); - - for (node = of_get_next_child(dev, NULL); - node != NULL; node = of_get_next_child(dev, node)) - celleb_setup_fake_pci_device(node, phb); - - return 0; -} - -static struct celleb_phb_spec celleb_fake_pci_spec __initdata = { - .setup = celleb_setup_fake_pci, -}; - -static const struct of_device_id celleb_phb_match[] __initconst = { - { - .name = "pci-pseudo", - .data = &celleb_fake_pci_spec, - }, { - .name = "epci", - .data = &celleb_epci_spec, - }, { - .name = "pcie", - .data = &celleb_pciex_spec, - }, { - }, -}; - -int __init celleb_setup_phb(struct pci_controller *phb) -{ - struct device_node *dev = phb->dn; - const struct of_device_id *match; - const struct celleb_phb_spec *phb_spec; - int rc; - - match = of_match_node(celleb_phb_match, dev); - if (!match) - return 1; - - phb_set_bus_ranges(dev, phb); - phb->buid = 1; - - phb_spec = match->data; - rc = (*phb_spec->setup)(dev, phb); - if (rc) - return 1; - - if (phb_spec->ops) - iowa_register_bus(phb, phb_spec->ops, - phb_spec->iowa_init, - phb_spec->iowa_data); - return 0; -} - -int celleb_pci_probe_mode(struct pci_bus *bus) -{ - return PCI_PROBE_DEVTREE; -} diff --git a/arch/powerpc/platforms/cell/celleb_pci.h b/arch/powerpc/platforms/cell/celleb_pci.h deleted file mode 100644 index a801fcc5f389..000000000000 --- a/arch/powerpc/platforms/cell/celleb_pci.h +++ /dev/null @@ -1,46 +0,0 @@ -/* - * pci prototypes for Celleb platform - * - * (C) Copyright 2006-2007 TOSHIBA CORPORATION - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#ifndef _CELLEB_PCI_H -#define _CELLEB_PCI_H - -#include <linux/pci.h> - -#include <asm/pci-bridge.h> -#include <asm/prom.h> -#include <asm/ppc-pci.h> -#include <asm/io-workarounds.h> - -struct iowa_bus; - -struct celleb_phb_spec { - int (*setup)(struct device_node *, struct pci_controller *); - struct ppc_pci_io *ops; - int (*iowa_init)(struct iowa_bus *, void *); - void *iowa_data; -}; - -extern int celleb_setup_phb(struct pci_controller *); -extern int celleb_pci_probe_mode(struct pci_bus *); - -extern struct celleb_phb_spec celleb_epci_spec; -extern struct celleb_phb_spec celleb_pciex_spec; - -#endif /* _CELLEB_PCI_H */ diff --git a/arch/powerpc/platforms/cell/celleb_scc.h b/arch/powerpc/platforms/cell/celleb_scc.h deleted file mode 100644 index b596a711c348..000000000000 --- a/arch/powerpc/platforms/cell/celleb_scc.h +++ /dev/null @@ -1,232 +0,0 @@ -/* - * SCC (Super Companion Chip) definitions - * - * (C) Copyright 2004-2006 TOSHIBA CORPORATION - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#ifndef _CELLEB_SCC_H -#define _CELLEB_SCC_H - -#define PCI_VENDOR_ID_TOSHIBA_2 0x102f -#define PCI_DEVICE_ID_TOSHIBA_SCC_PCIEXC_BRIDGE 0x01b0 -#define PCI_DEVICE_ID_TOSHIBA_SCC_EPCI_BRIDGE 0x01b1 -#define PCI_DEVICE_ID_TOSHIBA_SCC_BRIDGE 0x01b2 -#define PCI_DEVICE_ID_TOSHIBA_SCC_GBE 0x01b3 -#define PCI_DEVICE_ID_TOSHIBA_SCC_ATA 0x01b4 -#define PCI_DEVICE_ID_TOSHIBA_SCC_USB2 0x01b5 -#define PCI_DEVICE_ID_TOSHIBA_SCC_USB 0x01b6 -#define PCI_DEVICE_ID_TOSHIBA_SCC_ENCDEC 0x01b7 - -#define SCC_EPCI_REG 0x0000d000 - -/* EPCI registers */ -#define SCC_EPCI_CNF10_REG 0x010 -#define SCC_EPCI_CNF14_REG 0x014 -#define SCC_EPCI_CNF18_REG 0x018 -#define SCC_EPCI_PVBAT 0x100 -#define SCC_EPCI_VPMBAT 0x104 -#define SCC_EPCI_VPIBAT 0x108 -#define SCC_EPCI_VCSR 0x110 -#define SCC_EPCI_VIENAB 0x114 -#define SCC_EPCI_VISTAT 0x118 -#define SCC_EPCI_VRDCOUNT 0x124 -#define SCC_EPCI_BAM0 0x12c -#define SCC_EPCI_BAM1 0x134 -#define SCC_EPCI_BAM2 0x13c -#define SCC_EPCI_IADR 0x164 -#define SCC_EPCI_CLKRST 0x800 -#define SCC_EPCI_INTSET 0x804 -#define SCC_EPCI_STATUS 0x808 -#define SCC_EPCI_ABTSET 0x80c -#define SCC_EPCI_WATRP 0x810 -#define SCC_EPCI_DUMYRADR 0x814 -#define SCC_EPCI_SWRESP 0x818 -#define SCC_EPCI_CNTOPT 0x81c -#define SCC_EPCI_ECMODE 0xf00 -#define SCC_EPCI_IOM_AC_NUM 5 -#define SCC_EPCI_IOM_ACTE(n) (0xf10 + (n) * 4) -#define SCC_EPCI_IOT_AC_NUM 4 -#define SCC_EPCI_IOT_ACTE(n) (0xf30 + (n) * 4) -#define SCC_EPCI_MAEA 0xf50 -#define SCC_EPCI_MAEC 0xf54 -#define SCC_EPCI_CKCTRL 0xff0 - -/* bits for SCC_EPCI_VCSR */ -#define SCC_EPCI_VCSR_FRE 0x00020000 -#define SCC_EPCI_VCSR_FWE 0x00010000 -#define SCC_EPCI_VCSR_DR 0x00000400 -#define SCC_EPCI_VCSR_SR 0x00000008 -#define SCC_EPCI_VCSR_AT 0x00000004 - -/* bits for SCC_EPCI_VIENAB/SCC_EPCI_VISTAT */ -#define SCC_EPCI_VISTAT_PMPE 0x00000008 -#define SCC_EPCI_VISTAT_PMFE 0x00000004 -#define SCC_EPCI_VISTAT_PRA 0x00000002 -#define SCC_EPCI_VISTAT_PRD 0x00000001 -#define SCC_EPCI_VISTAT_ALL 0x0000000f - -#define SCC_EPCI_VIENAB_PMPEE 0x00000008 -#define SCC_EPCI_VIENAB_PMFEE 0x00000004 -#define SCC_EPCI_VIENAB_PRA 0x00000002 -#define SCC_EPCI_VIENAB_PRD 0x00000001 -#define SCC_EPCI_VIENAB_ALL 0x0000000f - -/* bits for SCC_EPCI_CLKRST */ -#define SCC_EPCI_CLKRST_CKS_MASK 0x00030000 -#define SCC_EPCI_CLKRST_CKS_2 0x00000000 -#define SCC_EPCI_CLKRST_CKS_4 0x00010000 -#define SCC_EPCI_CLKRST_CKS_8 0x00020000 -#define SCC_EPCI_CLKRST_PCICRST 0x00000400 -#define SCC_EPCI_CLKRST_BC 0x00000200 -#define SCC_EPCI_CLKRST_PCIRST 0x00000100 -#define SCC_EPCI_CLKRST_PCKEN 0x00000001 - -/* bits for SCC_EPCI_INTSET/SCC_EPCI_STATUS */ -#define SCC_EPCI_INT_2M 0x01000000 -#define SCC_EPCI_INT_RERR 0x00200000 -#define SCC_EPCI_INT_SERR 0x00100000 -#define SCC_EPCI_INT_PRTER 0x00080000 -#define SCC_EPCI_INT_SER 0x00040000 -#define SCC_EPCI_INT_PER 0x00020000 -#define SCC_EPCI_INT_PAI 0x00010000 -#define SCC_EPCI_INT_1M 0x00000100 -#define SCC_EPCI_INT_PME 0x00000010 -#define SCC_EPCI_INT_INTD 0x00000008 -#define SCC_EPCI_INT_INTC 0x00000004 -#define SCC_EPCI_INT_INTB 0x00000002 -#define SCC_EPCI_INT_INTA 0x00000001 -#define SCC_EPCI_INT_DEVINT 0x0000000f -#define SCC_EPCI_INT_ALL 0x003f001f -#define SCC_EPCI_INT_ALLERR 0x003f0000 - -/* bits for SCC_EPCI_CKCTRL */ -#define SCC_EPCI_CKCTRL_CRST0 0x00010000 -#define SCC_EPCI_CKCTRL_CRST1 0x00020000 -#define SCC_EPCI_CKCTRL_OCLKEN 0x00000100 -#define SCC_EPCI_CKCTRL_LCLKEN 0x00000001 - -#define SCC_EPCI_IDSEL_AD_TO_SLOT(ad) ((ad) - 10) -#define SCC_EPCI_MAX_DEVNU SCC_EPCI_IDSEL_AD_TO_SLOT(32) - -/* bits for SCC_EPCI_CNTOPT */ -#define SCC_EPCI_CNTOPT_O2PMB 0x00000002 - -/* SCC PCIEXC SMMIO registers */ -#define PEXCADRS 0x000 -#define PEXCWDATA 0x004 -#define PEXCRDATA 0x008 -#define PEXDADRS 0x010 -#define PEXDCMND 0x014 -#define PEXDWDATA 0x018 -#define PEXDRDATA 0x01c -#define PEXREQID 0x020 -#define PEXTIDMAP 0x024 -#define PEXINTMASK 0x028 -#define PEXINTSTS 0x02c -#define PEXAERRMASK 0x030 -#define PEXAERRSTS 0x034 -#define PEXPRERRMASK 0x040 -#define PEXPRERRSTS 0x044 -#define PEXPRERRID01 0x048 -#define PEXPRERRID23 0x04c -#define PEXVDMASK 0x050 -#define PEXVDSTS 0x054 -#define PEXRCVCPLIDA 0x060 -#define PEXLENERRIDA 0x068 -#define PEXPHYPLLST 0x070 -#define PEXDMRDEN0 0x100 -#define PEXDMRDADR0 0x104 -#define PEXDMRDENX 0x110 -#define PEXDMRDADRX 0x114 -#define PEXECMODE 0xf00 -#define PEXMAEA(n) (0xf50 + (8 * n)) -#define PEXMAEC(n) (0xf54 + (8 * n)) -#define PEXCCRCTRL 0xff0 - -/* SCC PCIEXC bits and shifts for PEXCADRS */ -#define PEXCADRS_BYTE_EN_SHIFT 20 -#define PEXCADRS_CMD_SHIFT 16 -#define PEXCADRS_CMD_READ (0xa << PEXCADRS_CMD_SHIFT) -#define PEXCADRS_CMD_WRITE (0xb << PEXCADRS_CMD_SHIFT) - -/* SCC PCIEXC shifts for PEXDADRS */ -#define PEXDADRS_BUSNO_SHIFT 20 -#define PEXDADRS_DEVNO_SHIFT 15 -#define PEXDADRS_FUNCNO_SHIFT 12 - -/* SCC PCIEXC bits and shifts for PEXDCMND */ -#define PEXDCMND_BYTE_EN_SHIFT 4 -#define PEXDCMND_IO_READ 0x2 -#define PEXDCMND_IO_WRITE 0x3 -#define PEXDCMND_CONFIG_READ 0xa -#define PEXDCMND_CONFIG_WRITE 0xb - -/* SCC PCIEXC bits for PEXPHYPLLST */ -#define PEXPHYPLLST_PEXPHYAPLLST 0x00000001 - -/* SCC PCIEXC bits for PEXECMODE */ -#define PEXECMODE_ALL_THROUGH 0x00000000 -#define PEXECMODE_ALL_8BIT 0x00550155 -#define PEXECMODE_ALL_16BIT 0x00aa02aa - -/* SCC PCIEXC bits for PEXCCRCTRL */ -#define PEXCCRCTRL_PEXIPCOREEN 0x00040000 -#define PEXCCRCTRL_PEXIPCONTEN 0x00020000 -#define PEXCCRCTRL_PEXPHYPLLEN 0x00010000 -#define PEXCCRCTRL_PCIEXCAOCKEN 0x00000100 - -/* SCC PCIEXC port configuration registers */ -#define PEXTCERRCHK 0x21c -#define PEXTAMAPB0 0x220 -#define PEXTAMAPL0 0x224 -#define PEXTAMAPB(n) (PEXTAMAPB0 + 8 * (n)) -#define PEXTAMAPL(n) (PEXTAMAPL0 + 8 * (n)) -#define PEXCHVC0P 0x500 -#define PEXCHVC0NP 0x504 -#define PEXCHVC0C 0x508 -#define PEXCDVC0P 0x50c -#define PEXCDVC0NP 0x510 -#define PEXCDVC0C 0x514 -#define PEXCHVCXP 0x518 -#define PEXCHVCXNP 0x51c -#define PEXCHVCXC 0x520 -#define PEXCDVCXP 0x524 -#define PEXCDVCXNP 0x528 -#define PEXCDVCXC 0x52c -#define PEXCTTRG 0x530 -#define PEXTSCTRL 0x700 -#define PEXTSSTS 0x704 -#define PEXSKPCTRL 0x708 - -/* UHC registers */ -#define SCC_UHC_CKRCTRL 0xff0 -#define SCC_UHC_ECMODE 0xf00 - -/* bits for SCC_UHC_CKRCTRL */ -#define SCC_UHC_F48MCKLEN 0x00000001 -#define SCC_UHC_P_SUSPEND 0x00000002 -#define SCC_UHC_PHY_SUSPEND_SEL 0x00000004 -#define SCC_UHC_HCLKEN 0x00000100 -#define SCC_UHC_USBEN 0x00010000 -#define SCC_UHC_USBCEN 0x00020000 -#define SCC_UHC_PHYEN 0x00040000 - -/* bits for SCC_UHC_ECMODE */ -#define SCC_UHC_ECMODE_BY_BYTE 0x00000555 -#define SCC_UHC_ECMODE_BY_WORD 0x00000aaa - -#endif /* _CELLEB_SCC_H */ diff --git a/arch/powerpc/platforms/cell/celleb_scc_epci.c b/arch/powerpc/platforms/cell/celleb_scc_epci.c deleted file mode 100644 index 9438bbed402f..000000000000 --- a/arch/powerpc/platforms/cell/celleb_scc_epci.c +++ /dev/null @@ -1,428 +0,0 @@ -/* - * Support for SCC external PCI - * - * (C) Copyright 2004-2007 TOSHIBA CORPORATION - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#undef DEBUG - -#include <linux/kernel.h> -#include <linux/threads.h> -#include <linux/pci.h> -#include <linux/init.h> -#include <linux/pci_regs.h> - -#include <asm/io.h> -#include <asm/irq.h> -#include <asm/prom.h> -#include <asm/pci-bridge.h> -#include <asm/ppc-pci.h> - -#include "celleb_scc.h" -#include "celleb_pci.h" - -#define MAX_PCI_DEVICES 32 -#define MAX_PCI_FUNCTIONS 8 - -#define iob() __asm__ __volatile__("eieio; sync":::"memory") - -static inline PCI_IO_ADDR celleb_epci_get_epci_base( - struct pci_controller *hose) -{ - /* - * Note: - * Celleb epci uses cfg_addr as a base address for - * epci control registers. - */ - - return hose->cfg_addr; -} - -static inline PCI_IO_ADDR celleb_epci_get_epci_cfg( - struct pci_controller *hose) -{ - /* - * Note: - * Celleb epci uses cfg_data as a base address for - * configuration area for epci devices. - */ - - return hose->cfg_data; -} - -static inline void clear_and_disable_master_abort_interrupt( - struct pci_controller *hose) -{ - PCI_IO_ADDR epci_base; - PCI_IO_ADDR reg; - epci_base = celleb_epci_get_epci_base(hose); - reg = epci_base + PCI_COMMAND; - out_be32(reg, in_be32(reg) | (PCI_STATUS_REC_MASTER_ABORT << 16)); -} - -static int celleb_epci_check_abort(struct pci_controller *hose, - PCI_IO_ADDR addr) -{ - PCI_IO_ADDR reg; - PCI_IO_ADDR epci_base; - u32 val; - - iob(); - epci_base = celleb_epci_get_epci_base(hose); - - reg = epci_base + PCI_COMMAND; - val = in_be32(reg); - - if (val & (PCI_STATUS_REC_MASTER_ABORT << 16)) { - out_be32(reg, - (val & 0xffff) | (PCI_STATUS_REC_MASTER_ABORT << 16)); - - /* clear PCI Controller error, FRE, PMFE */ - reg = epci_base + SCC_EPCI_STATUS; - out_be32(reg, SCC_EPCI_INT_PAI); - - reg = epci_base + SCC_EPCI_VCSR; - val = in_be32(reg) & 0xffff; - val |= SCC_EPCI_VCSR_FRE; - out_be32(reg, val); - - reg = epci_base + SCC_EPCI_VISTAT; - out_be32(reg, SCC_EPCI_VISTAT_PMFE); - return PCIBIOS_DEVICE_NOT_FOUND; - } - - return PCIBIOS_SUCCESSFUL; -} - -static PCI_IO_ADDR celleb_epci_make_config_addr(struct pci_bus *bus, - struct pci_controller *hose, unsigned int devfn, int where) -{ - PCI_IO_ADDR addr; - - if (bus != hose->bus) - addr = celleb_epci_get_epci_cfg(hose) + - (((bus->number & 0xff) << 16) - | ((devfn & 0xff) << 8) - | (where & 0xff) - | 0x01000000); - else - addr = celleb_epci_get_epci_cfg(hose) + - (((devfn & 0xff) << 8) | (where & 0xff)); - - pr_debug("EPCI: config_addr = 0x%p\n", addr); - - return addr; -} - -static int celleb_epci_read_config(struct pci_bus *bus, - unsigned int devfn, int where, int size, u32 *val) -{ - PCI_IO_ADDR epci_base; - PCI_IO_ADDR addr; - struct pci_controller *hose = pci_bus_to_host(bus); - - /* allignment check */ - BUG_ON(where % size); - - if (!celleb_epci_get_epci_cfg(hose)) - return PCIBIOS_DEVICE_NOT_FOUND; - - if (bus->number == hose->first_busno && devfn == 0) { - /* EPCI controller self */ - - epci_base = celleb_epci_get_epci_base(hose); - addr = epci_base + where; - - switch (size) { - case 1: - *val = in_8(addr); - break; - case 2: - *val = in_be16(addr); - break; - case 4: - *val = in_be32(addr); - break; - default: - return PCIBIOS_DEVICE_NOT_FOUND; - } - - } else { - - clear_and_disable_master_abort_interrupt(hose); - addr = celleb_epci_make_config_addr(bus, hose, devfn, where); - - switch (size) { - case 1: - *val = in_8(addr); - break; - case 2: - *val = in_le16(addr); - break; - case 4: - *val = in_le32(addr); - break; - default: - return PCIBIOS_DEVICE_NOT_FOUND; - } - } - - pr_debug("EPCI: " - "addr=0x%p, devfn=0x%x, where=0x%x, size=0x%x, val=0x%x\n", - addr, devfn, where, size, *val); - - return celleb_epci_check_abort(hose, NULL); -} - -static int celleb_epci_write_config(struct pci_bus *bus, - unsigned int devfn, int where, int size, u32 val) -{ - PCI_IO_ADDR epci_base; - PCI_IO_ADDR addr; - struct pci_controller *hose = pci_bus_to_host(bus); - - /* allignment check */ - BUG_ON(where % size); - - if (!celleb_epci_get_epci_cfg(hose)) - return PCIBIOS_DEVICE_NOT_FOUND; - - if (bus->number == hose->first_busno && devfn == 0) { - /* EPCI controller self */ - - epci_base = celleb_epci_get_epci_base(hose); - addr = epci_base + where; - - switch (size) { - case 1: - out_8(addr, val); - break; - case 2: - out_be16(addr, val); - break; - case 4: - out_be32(addr, val); - break; - default: - return PCIBIOS_DEVICE_NOT_FOUND; - } - - } else { - - clear_and_disable_master_abort_interrupt(hose); - addr = celleb_epci_make_config_addr(bus, hose, devfn, where); - - switch (size) { - case 1: - out_8(addr, val); - break; - case 2: - out_le16(addr, val); - break; - case 4: - out_le32(addr, val); - break; - default: - return PCIBIOS_DEVICE_NOT_FOUND; - } - } - - return celleb_epci_check_abort(hose, addr); -} - -struct pci_ops celleb_epci_ops = { - .read = celleb_epci_read_config, - .write = celleb_epci_write_config, -}; - -/* to be moved in FW */ -static int __init celleb_epci_init(struct pci_controller *hose) -{ - u32 val; - PCI_IO_ADDR reg; - PCI_IO_ADDR epci_base; - int hwres = 0; - - epci_base = celleb_epci_get_epci_base(hose); - - /* PCI core reset(Internal bus and PCI clock) */ - reg = epci_base + SCC_EPCI_CKCTRL; - val = in_be32(reg); - if (val == 0x00030101) - hwres = 1; - else { - val &= ~(SCC_EPCI_CKCTRL_CRST0 | SCC_EPCI_CKCTRL_CRST1); - out_be32(reg, val); - - /* set PCI core clock */ - val = in_be32(reg); - val |= (SCC_EPCI_CKCTRL_OCLKEN | SCC_EPCI_CKCTRL_LCLKEN); - out_be32(reg, val); - - /* release PCI core reset (internal bus) */ - val = in_be32(reg); - val |= SCC_EPCI_CKCTRL_CRST0; - out_be32(reg, val); - - /* set PCI clock select */ - reg = epci_base + SCC_EPCI_CLKRST; - val = in_be32(reg); - val &= ~SCC_EPCI_CLKRST_CKS_MASK; - val |= SCC_EPCI_CLKRST_CKS_2; - out_be32(reg, val); - - /* set arbiter */ - reg = epci_base + SCC_EPCI_ABTSET; - out_be32(reg, 0x0f1f001f); /* temporary value */ - - /* buffer on */ - reg = epci_base + SCC_EPCI_CLKRST; - val = in_be32(reg); - val |= SCC_EPCI_CLKRST_BC; - out_be32(reg, val); - - /* PCI clock enable */ - val = in_be32(reg); - val |= SCC_EPCI_CLKRST_PCKEN; - out_be32(reg, val); - - /* release PCI core reset (all) */ - reg = epci_base + SCC_EPCI_CKCTRL; - val = in_be32(reg); - val |= (SCC_EPCI_CKCTRL_CRST0 | SCC_EPCI_CKCTRL_CRST1); - out_be32(reg, val); - - /* set base translation registers. (already set by Beat) */ - - /* set base address masks. (already set by Beat) */ - } - - /* release interrupt masks and clear all interrupts */ - reg = epci_base + SCC_EPCI_INTSET; - out_be32(reg, 0x013f011f); /* all interrupts enable */ - reg = epci_base + SCC_EPCI_VIENAB; - val = SCC_EPCI_VIENAB_PMPEE | SCC_EPCI_VIENAB_PMFEE; - out_be32(reg, val); - reg = epci_base + SCC_EPCI_STATUS; - out_be32(reg, 0xffffffff); - reg = epci_base + SCC_EPCI_VISTAT; - out_be32(reg, 0xffffffff); - - /* disable PCI->IB address translation */ - reg = epci_base + SCC_EPCI_VCSR; - val = in_be32(reg); - val &= ~(SCC_EPCI_VCSR_DR | SCC_EPCI_VCSR_AT); - out_be32(reg, val); - - /* set base addresses. (no need to set?) */ - - /* memory space, bus master enable */ - reg = epci_base + PCI_COMMAND; - val = PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER; - out_be32(reg, val); - - /* endian mode setup */ - reg = epci_base + SCC_EPCI_ECMODE; - val = 0x00550155; - out_be32(reg, val); - - /* set control option */ - reg = epci_base + SCC_EPCI_CNTOPT; - val = in_be32(reg); - val |= SCC_EPCI_CNTOPT_O2PMB; - out_be32(reg, val); - - /* XXX: temporay: set registers for address conversion setup */ - reg = epci_base + SCC_EPCI_CNF10_REG; - out_be32(reg, 0x80000008); - reg = epci_base + SCC_EPCI_CNF14_REG; - out_be32(reg, 0x40000008); - - reg = epci_base + SCC_EPCI_BAM0; - out_be32(reg, 0x80000000); - reg = epci_base + SCC_EPCI_BAM1; - out_be32(reg, 0xe0000000); - - reg = epci_base + SCC_EPCI_PVBAT; - out_be32(reg, 0x80000000); - - if (!hwres) { - /* release external PCI reset */ - reg = epci_base + SCC_EPCI_CLKRST; - val = in_be32(reg); - val |= SCC_EPCI_CLKRST_PCIRST; - out_be32(reg, val); - } - - return 0; -} - -static int __init celleb_setup_epci(struct device_node *node, - struct pci_controller *hose) -{ - struct resource r; - - pr_debug("PCI: celleb_setup_epci()\n"); - - /* - * Note: - * Celleb epci uses cfg_addr and cfg_data member of - * pci_controller structure in irregular way. - * - * cfg_addr is used to map for control registers of - * celleb epci. - * - * cfg_data is used for configuration area of devices - * on Celleb epci buses. - */ - - if (of_address_to_resource(node, 0, &r)) - goto error; - hose->cfg_addr = ioremap(r.start, resource_size(&r)); - if (!hose->cfg_addr) - goto error; - pr_debug("EPCI: cfg_addr map 0x%016llx->0x%016lx + 0x%016llx\n", - r.start, (unsigned long)hose->cfg_addr, resource_size(&r)); - - if (of_address_to_resource(node, 2, &r)) - goto error; - hose->cfg_data = ioremap(r.start, resource_size(&r)); - if (!hose->cfg_data) - goto error; - pr_debug("EPCI: cfg_data map 0x%016llx->0x%016lx + 0x%016llx\n", - r.start, (unsigned long)hose->cfg_data, resource_size(&r)); - - hose->ops = &celleb_epci_ops; - celleb_epci_init(hose); - - return 0; - -error: - if (hose->cfg_addr) - iounmap(hose->cfg_addr); - - if (hose->cfg_data) - iounmap(hose->cfg_data); - return 1; -} - -struct celleb_phb_spec celleb_epci_spec __initdata = { - .setup = celleb_setup_epci, - .ops = &spiderpci_ops, - .iowa_init = &spiderpci_iowa_init, - .iowa_data = (void *)0, -}; diff --git a/arch/powerpc/platforms/cell/celleb_scc_pciex.c b/arch/powerpc/platforms/cell/celleb_scc_pciex.c deleted file mode 100644 index 94170e4f2ce7..000000000000 --- a/arch/powerpc/platforms/cell/celleb_scc_pciex.c +++ /dev/null @@ -1,538 +0,0 @@ -/* - * Support for Celleb PCI-Express. - * - * (C) Copyright 2007-2008 TOSHIBA CORPORATION - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#undef DEBUG - -#include <linux/kernel.h> -#include <linux/pci.h> -#include <linux/string.h> -#include <linux/slab.h> -#include <linux/init.h> -#include <linux/delay.h> -#include <linux/interrupt.h> - -#include <asm/io.h> -#include <asm/irq.h> -#include <asm/iommu.h> -#include <asm/byteorder.h> - -#include "celleb_scc.h" -#include "celleb_pci.h" - -#define PEX_IN(base, off) in_be32((void __iomem *)(base) + (off)) -#define PEX_OUT(base, off, data) out_be32((void __iomem *)(base) + (off), (data)) - -static void scc_pciex_io_flush(struct iowa_bus *bus) -{ - (void)PEX_IN(bus->phb->cfg_addr, PEXDMRDEN0); -} - -/* - * Memory space access to device on PCIEX - */ -#define PCIEX_MMIO_READ(name, ret) \ -static ret scc_pciex_##name(const PCI_IO_ADDR addr) \ -{ \ - ret val = __do_##name(addr); \ - scc_pciex_io_flush(iowa_mem_find_bus(addr)); \ - return val; \ -} - -#define PCIEX_MMIO_READ_STR(name) \ -static void scc_pciex_##name(const PCI_IO_ADDR addr, void *buf, \ - unsigned long count) \ -{ \ - __do_##name(addr, buf, count); \ - scc_pciex_io_flush(iowa_mem_find_bus(addr)); \ -} - -PCIEX_MMIO_READ(readb, u8) -PCIEX_MMIO_READ(readw, u16) -PCIEX_MMIO_READ(readl, u32) -PCIEX_MMIO_READ(readq, u64) -PCIEX_MMIO_READ(readw_be, u16) -PCIEX_MMIO_READ(readl_be, u32) -PCIEX_MMIO_READ(readq_be, u64) -PCIEX_MMIO_READ_STR(readsb) -PCIEX_MMIO_READ_STR(readsw) -PCIEX_MMIO_READ_STR(readsl) - -static void scc_pciex_memcpy_fromio(void *dest, const PCI_IO_ADDR src, - unsigned long n) -{ - __do_memcpy_fromio(dest, src, n); - scc_pciex_io_flush(iowa_mem_find_bus(src)); -} - -/* - * I/O port access to devices on PCIEX. - */ - -static inline unsigned long get_bus_address(struct pci_controller *phb, - unsigned long port) -{ - return port - ((unsigned long)(phb->io_base_virt) - _IO_BASE); -} - -static u32 scc_pciex_read_port(struct pci_controller *phb, - unsigned long port, int size) -{ - unsigned int byte_enable; - unsigned int cmd, shift; - unsigned long addr; - u32 data, ret; - - BUG_ON(((port & 0x3ul) + size) > 4); - - addr = get_bus_address(phb, port); - shift = addr & 0x3ul; - byte_enable = ((1 << size) - 1) << shift; - cmd = PEXDCMND_IO_READ | (byte_enable << PEXDCMND_BYTE_EN_SHIFT); - PEX_OUT(phb->cfg_addr, PEXDADRS, (addr & ~0x3ul)); - PEX_OUT(phb->cfg_addr, PEXDCMND, cmd); - data = PEX_IN(phb->cfg_addr, PEXDRDATA); - ret = (data >> (shift * 8)) & (0xFFFFFFFF >> ((4 - size) * 8)); - - pr_debug("PCIEX:PIO READ:port=0x%lx, addr=0x%lx, size=%d, be=%x," - " cmd=%x, data=%x, ret=%x\n", port, addr, size, byte_enable, - cmd, data, ret); - - return ret; -} - -static void scc_pciex_write_port(struct pci_controller *phb, - unsigned long port, int size, u32 val) -{ - unsigned int byte_enable; - unsigned int cmd, shift; - unsigned long addr; - u32 data; - - BUG_ON(((port & 0x3ul) + size) > 4); - - addr = get_bus_address(phb, port); - shift = addr & 0x3ul; - byte_enable = ((1 << size) - 1) << shift; - cmd = PEXDCMND_IO_WRITE | (byte_enable << PEXDCMND_BYTE_EN_SHIFT); - data = (val & (0xFFFFFFFF >> (4 - size) * 8)) << (shift * 8); - PEX_OUT(phb->cfg_addr, PEXDADRS, (addr & ~0x3ul)); - PEX_OUT(phb->cfg_addr, PEXDCMND, cmd); - PEX_OUT(phb->cfg_addr, PEXDWDATA, data); - - pr_debug("PCIEX:PIO WRITE:port=0x%lx, addr=%lx, size=%d, val=%x," - " be=%x, cmd=%x, data=%x\n", port, addr, size, val, - byte_enable, cmd, data); -} - -static u8 __scc_pciex_inb(struct pci_controller *phb, unsigned long port) -{ - return (u8)scc_pciex_read_port(phb, port, 1); -} - -static u16 __scc_pciex_inw(struct pci_controller *phb, unsigned long port) -{ - u32 data; - if ((port & 0x3ul) < 3) - data = scc_pciex_read_port(phb, port, 2); - else { - u32 d1 = scc_pciex_read_port(phb, port, 1); - u32 d2 = scc_pciex_read_port(phb, port + 1, 1); - data = d1 | (d2 << 8); - } - return (u16)data; -} - -static u32 __scc_pciex_inl(struct pci_controller *phb, unsigned long port) -{ - unsigned int mod = port & 0x3ul; - u32 data; - if (mod == 0) - data = scc_pciex_read_port(phb, port, 4); - else { - u32 d1 = scc_pciex_read_port(phb, port, 4 - mod); - u32 d2 = scc_pciex_read_port(phb, port + 1, mod); - data = d1 | (d2 << (mod * 8)); - } - return data; -} - -static void __scc_pciex_outb(struct pci_controller *phb, - u8 val, unsigned long port) -{ - scc_pciex_write_port(phb, port, 1, (u32)val); -} - -static void __scc_pciex_outw(struct pci_controller *phb, - u16 val, unsigned long port) -{ - if ((port & 0x3ul) < 3) - scc_pciex_write_port(phb, port, 2, (u32)val); - else { - u32 d1 = val & 0x000000FF; - u32 d2 = (val & 0x0000FF00) >> 8; - scc_pciex_write_port(phb, port, 1, d1); - scc_pciex_write_port(phb, port + 1, 1, d2); - } -} - -static void __scc_pciex_outl(struct pci_controller *phb, - u32 val, unsigned long port) -{ - unsigned int mod = port & 0x3ul; - if (mod == 0) - scc_pciex_write_port(phb, port, 4, val); - else { - u32 d1 = val & (0xFFFFFFFFul >> (mod * 8)); - u32 d2 = val >> ((4 - mod) * 8); - scc_pciex_write_port(phb, port, 4 - mod, d1); - scc_pciex_write_port(phb, port + 1, mod, d2); - } -} - -#define PCIEX_PIO_FUNC(size, name) \ -static u##size scc_pciex_in##name(unsigned long port) \ -{ \ - struct iowa_bus *bus = iowa_pio_find_bus(port); \ - u##size data = __scc_pciex_in##name(bus->phb, port); \ - scc_pciex_io_flush(bus); \ - return data; \ -} \ -static void scc_pciex_ins##name(unsigned long p, void *b, unsigned long c) \ -{ \ - struct iowa_bus *bus = iowa_pio_find_bus(p); \ - __le##size *dst = b; \ - for (; c != 0; c--, dst++) \ - *dst = cpu_to_le##size(__scc_pciex_in##name(bus->phb, p)); \ - scc_pciex_io_flush(bus); \ -} \ -static void scc_pciex_out##name(u##size val, unsigned long port) \ -{ \ - struct iowa_bus *bus = iowa_pio_find_bus(port); \ - __scc_pciex_out##name(bus->phb, val, port); \ -} \ -static void scc_pciex_outs##name(unsigned long p, const void *b, \ - unsigned long c) \ -{ \ - struct iowa_bus *bus = iowa_pio_find_bus(p); \ - const __le##size *src = b; \ - for (; c != 0; c--, src++) \ - __scc_pciex_out##name(bus->phb, le##size##_to_cpu(*src), p); \ -} -#define __le8 u8 -#define cpu_to_le8(x) (x) -#define le8_to_cpu(x) (x) -PCIEX_PIO_FUNC(8, b) -PCIEX_PIO_FUNC(16, w) -PCIEX_PIO_FUNC(32, l) - -static struct ppc_pci_io scc_pciex_ops = { - .readb = scc_pciex_readb, - .readw = scc_pciex_readw, - .readl = scc_pciex_readl, - .readq = scc_pciex_readq, - .readw_be = scc_pciex_readw_be, - .readl_be = scc_pciex_readl_be, - .readq_be = scc_pciex_readq_be, - .readsb = scc_pciex_readsb, - .readsw = scc_pciex_readsw, - .readsl = scc_pciex_readsl, - .memcpy_fromio = scc_pciex_memcpy_fromio, - .inb = scc_pciex_inb, - .inw = scc_pciex_inw, - .inl = scc_pciex_inl, - .outb = scc_pciex_outb, - .outw = scc_pciex_outw, - .outl = scc_pciex_outl, - .insb = scc_pciex_insb, - .insw = scc_pciex_insw, - .insl = scc_pciex_insl, - .outsb = scc_pciex_outsb, - .outsw = scc_pciex_outsw, - .outsl = scc_pciex_outsl, -}; - -static int __init scc_pciex_iowa_init(struct iowa_bus *bus, void *data) -{ - dma_addr_t dummy_page_da; - void *dummy_page_va; - - dummy_page_va = kmalloc(PAGE_SIZE, GFP_KERNEL); - if (!dummy_page_va) { - pr_err("PCIEX:Alloc dummy_page_va failed\n"); - return -1; - } - - dummy_page_da = dma_map_single(bus->phb->parent, dummy_page_va, - PAGE_SIZE, DMA_FROM_DEVICE); - if (dma_mapping_error(bus->phb->parent, dummy_page_da)) { - pr_err("PCIEX:Map dummy page failed.\n"); - kfree(dummy_page_va); - return -1; - } - - PEX_OUT(bus->phb->cfg_addr, PEXDMRDADR0, dummy_page_da); - - return 0; -} - -/* - * config space access - */ -#define MK_PEXDADRS(bus_no, dev_no, func_no, addr) \ - ((uint32_t)(((addr) & ~0x3UL) | \ - ((bus_no) << PEXDADRS_BUSNO_SHIFT) | \ - ((dev_no) << PEXDADRS_DEVNO_SHIFT) | \ - ((func_no) << PEXDADRS_FUNCNO_SHIFT))) - -#define MK_PEXDCMND_BYTE_EN(addr, size) \ - ((((0x1 << (size))-1) << ((addr) & 0x3)) << PEXDCMND_BYTE_EN_SHIFT) -#define MK_PEXDCMND(cmd, addr, size) ((cmd) | MK_PEXDCMND_BYTE_EN(addr, size)) - -static uint32_t config_read_pciex_dev(unsigned int __iomem *base, - uint64_t bus_no, uint64_t dev_no, uint64_t func_no, - uint64_t off, uint64_t size) -{ - uint32_t ret; - uint32_t addr, cmd; - - addr = MK_PEXDADRS(bus_no, dev_no, func_no, off); - cmd = MK_PEXDCMND(PEXDCMND_CONFIG_READ, off, size); - PEX_OUT(base, PEXDADRS, addr); - PEX_OUT(base, PEXDCMND, cmd); - ret = (PEX_IN(base, PEXDRDATA) - >> ((off & (4-size)) * 8)) & ((0x1 << (size * 8)) - 1); - return ret; -} - -static void config_write_pciex_dev(unsigned int __iomem *base, uint64_t bus_no, - uint64_t dev_no, uint64_t func_no, uint64_t off, uint64_t size, - uint32_t data) -{ - uint32_t addr, cmd; - - addr = MK_PEXDADRS(bus_no, dev_no, func_no, off); - cmd = MK_PEXDCMND(PEXDCMND_CONFIG_WRITE, off, size); - PEX_OUT(base, PEXDADRS, addr); - PEX_OUT(base, PEXDCMND, cmd); - PEX_OUT(base, PEXDWDATA, - (data & ((0x1 << (size * 8)) - 1)) << ((off & (4-size)) * 8)); -} - -#define MK_PEXCADRS_BYTE_EN(off, len) \ - ((((0x1 << (len)) - 1) << ((off) & 0x3)) << PEXCADRS_BYTE_EN_SHIFT) -#define MK_PEXCADRS(cmd, addr, size) \ - ((cmd) | MK_PEXCADRS_BYTE_EN(addr, size) | ((addr) & ~0x3)) -static uint32_t config_read_pciex_rc(unsigned int __iomem *base, - uint32_t where, uint32_t size) -{ - PEX_OUT(base, PEXCADRS, MK_PEXCADRS(PEXCADRS_CMD_READ, where, size)); - return (PEX_IN(base, PEXCRDATA) - >> ((where & (4 - size)) * 8)) & ((0x1 << (size * 8)) - 1); -} - -static void config_write_pciex_rc(unsigned int __iomem *base, uint32_t where, - uint32_t size, uint32_t val) -{ - uint32_t data; - - data = (val & ((0x1 << (size * 8)) - 1)) << ((where & (4 - size)) * 8); - PEX_OUT(base, PEXCADRS, MK_PEXCADRS(PEXCADRS_CMD_WRITE, where, size)); - PEX_OUT(base, PEXCWDATA, data); -} - -/* Interfaces */ -/* Note: Work-around - * On SCC PCIEXC, one device is seen on all 32 dev_no. - * As SCC PCIEXC can have only one device on the bus, we look only one dev_no. - * (dev_no = 1) - */ -static int scc_pciex_read_config(struct pci_bus *bus, unsigned int devfn, - int where, int size, unsigned int *val) -{ - struct pci_controller *phb = pci_bus_to_host(bus); - - if (bus->number == phb->first_busno && PCI_SLOT(devfn) != 1) { - *val = ~0; - return PCIBIOS_DEVICE_NOT_FOUND; - } - - if (bus->number == 0 && PCI_SLOT(devfn) == 0) - *val = config_read_pciex_rc(phb->cfg_addr, where, size); - else - *val = config_read_pciex_dev(phb->cfg_addr, bus->number, - PCI_SLOT(devfn), PCI_FUNC(devfn), where, size); - - return PCIBIOS_SUCCESSFUL; -} - -static int scc_pciex_write_config(struct pci_bus *bus, unsigned int devfn, - int where, int size, unsigned int val) -{ - struct pci_controller *phb = pci_bus_to_host(bus); - - if (bus->number == phb->first_busno && PCI_SLOT(devfn) != 1) - return PCIBIOS_DEVICE_NOT_FOUND; - - if (bus->number == 0 && PCI_SLOT(devfn) == 0) - config_write_pciex_rc(phb->cfg_addr, where, size, val); - else - config_write_pciex_dev(phb->cfg_addr, bus->number, - PCI_SLOT(devfn), PCI_FUNC(devfn), where, size, val); - return PCIBIOS_SUCCESSFUL; -} - -static struct pci_ops scc_pciex_pci_ops = { - .read = scc_pciex_read_config, - .write = scc_pciex_write_config, -}; - -static void pciex_clear_intr_all(unsigned int __iomem *base) -{ - PEX_OUT(base, PEXAERRSTS, 0xffffffff); - PEX_OUT(base, PEXPRERRSTS, 0xffffffff); - PEX_OUT(base, PEXINTSTS, 0xffffffff); -} - -#if 0 -static void pciex_disable_intr_all(unsigned int *base) -{ - PEX_OUT(base, PEXINTMASK, 0x0); - PEX_OUT(base, PEXAERRMASK, 0x0); - PEX_OUT(base, PEXPRERRMASK, 0x0); - PEX_OUT(base, PEXVDMASK, 0x0); -} -#endif - -static void pciex_enable_intr_all(unsigned int __iomem *base) -{ - PEX_OUT(base, PEXINTMASK, 0x0000e7f1); - PEX_OUT(base, PEXAERRMASK, 0x03ff01ff); - PEX_OUT(base, PEXPRERRMASK, 0x0001010f); - PEX_OUT(base, PEXVDMASK, 0x00000001); -} - -static void pciex_check_status(unsigned int __iomem *base) -{ - uint32_t err = 0; - uint32_t intsts, aerr, prerr, rcvcp, lenerr; - uint32_t maea, maec; - - intsts = PEX_IN(base, PEXINTSTS); - aerr = PEX_IN(base, PEXAERRSTS); - prerr = PEX_IN(base, PEXPRERRSTS); - rcvcp = PEX_IN(base, PEXRCVCPLIDA); - lenerr = PEX_IN(base, PEXLENERRIDA); - - if (intsts || aerr || prerr || rcvcp || lenerr) - err = 1; - - pr_info("PCEXC interrupt!!\n"); - pr_info("PEXINTSTS :0x%08x\n", intsts); - pr_info("PEXAERRSTS :0x%08x\n", aerr); - pr_info("PEXPRERRSTS :0x%08x\n", prerr); - pr_info("PEXRCVCPLIDA :0x%08x\n", rcvcp); - pr_info("PEXLENERRIDA :0x%08x\n", lenerr); - - /* print detail of Protection Error */ - if (intsts & 0x00004000) { - uint32_t i, n; - for (i = 0; i < 4; i++) { - n = 1 << i; - if (prerr & n) { - maea = PEX_IN(base, PEXMAEA(i)); - maec = PEX_IN(base, PEXMAEC(i)); - pr_info("PEXMAEC%d :0x%08x\n", i, maec); - pr_info("PEXMAEA%d :0x%08x\n", i, maea); - } - } - } - - if (err) - pciex_clear_intr_all(base); -} - -static irqreturn_t pciex_handle_internal_irq(int irq, void *dev_id) -{ - struct pci_controller *phb = dev_id; - - pr_debug("PCIEX:pciex_handle_internal_irq(irq=%d)\n", irq); - - BUG_ON(phb->cfg_addr == NULL); - - pciex_check_status(phb->cfg_addr); - - return IRQ_HANDLED; -} - -static __init int celleb_setup_pciex(struct device_node *node, - struct pci_controller *phb) -{ - struct resource r; - int virq; - - /* SMMIO registers; used inside this file */ - if (of_address_to_resource(node, 0, &r)) { - pr_err("PCIEXC:Failed to get config resource.\n"); - return 1; - } - phb->cfg_addr = ioremap(r.start, resource_size(&r)); - if (!phb->cfg_addr) { - pr_err("PCIEXC:Failed to remap SMMIO region.\n"); - return 1; - } - - /* Not use cfg_data, cmd and data regs are near address reg */ - phb->cfg_data = NULL; - - /* set pci_ops */ - phb->ops = &scc_pciex_pci_ops; - - /* internal interrupt handler */ - virq = irq_of_parse_and_map(node, 1); - if (!virq) { - pr_err("PCIEXC:Failed to map irq\n"); - goto error; - } - if (request_irq(virq, pciex_handle_internal_irq, - 0, "pciex", (void *)phb)) { - pr_err("PCIEXC:Failed to request irq\n"); - goto error; - } - - /* enable all interrupts */ - pciex_clear_intr_all(phb->cfg_addr); - pciex_enable_intr_all(phb->cfg_addr); - /* MSI: TBD */ - - return 0; - -error: - phb->cfg_data = NULL; - if (phb->cfg_addr) - iounmap(phb->cfg_addr); - phb->cfg_addr = NULL; - return 1; -} - -struct celleb_phb_spec celleb_pciex_spec __initdata = { - .setup = celleb_setup_pciex, - .ops = &scc_pciex_ops, - .iowa_init = &scc_pciex_iowa_init, -}; diff --git a/arch/powerpc/platforms/cell/celleb_scc_sio.c b/arch/powerpc/platforms/cell/celleb_scc_sio.c deleted file mode 100644 index c8eb57193826..000000000000 --- a/arch/powerpc/platforms/cell/celleb_scc_sio.c +++ /dev/null @@ -1,99 +0,0 @@ -/* - * setup serial port in SCC - * - * (C) Copyright 2006-2007 TOSHIBA CORPORATION - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#include <linux/tty.h> -#include <linux/serial.h> -#include <linux/serial_core.h> -#include <linux/console.h> - -#include <asm/io.h> -#include <asm/prom.h> - -/* sio irq0=0xb00010022 irq0=0xb00010023 irq2=0xb00010024 - mmio=0xfff000-0x1000,0xff2000-0x1000 */ -static int txx9_serial_bitmap __initdata; - -static struct { - uint32_t offset; - uint32_t index; -} txx9_scc_tab[3] __initdata = { - { 0x300, 0 }, /* 0xFFF300 */ - { 0x400, 0 }, /* 0xFFF400 */ - { 0x800, 1 } /* 0xFF2800 */ -}; - -static int __init txx9_serial_init(void) -{ - extern int early_serial_txx9_setup(struct uart_port *port); - struct device_node *node; - int i; - struct uart_port req; - struct of_phandle_args irq; - struct resource res; - - for_each_compatible_node(node, "serial", "toshiba,sio-scc") { - for (i = 0; i < ARRAY_SIZE(txx9_scc_tab); i++) { - if (!(txx9_serial_bitmap & (1<<i))) - continue; - - if (of_irq_parse_one(node, i, &irq)) - continue; - if (of_address_to_resource(node, - txx9_scc_tab[i].index, &res)) - continue; - - memset(&req, 0, sizeof(req)); - req.line = i; - req.iotype = UPIO_MEM; - req.mapbase = res.start + txx9_scc_tab[i].offset; -#ifdef CONFIG_SERIAL_TXX9_CONSOLE - req.membase = ioremap(req.mapbase, 0x24); -#endif - req.irq = irq_create_of_mapping(&irq); - req.flags |= UPF_IOREMAP | UPF_BUGGY_UART - /*HAVE_CTS_LINE*/; - req.uartclk = 83300000; - early_serial_txx9_setup(&req); - } - } - - return 0; -} - -static int __init txx9_serial_config(char *ptr) -{ - int i; - - for (;;) { - switch (get_option(&ptr, &i)) { - default: - return 0; - case 2: - txx9_serial_bitmap |= 1 << i; - break; - case 1: - txx9_serial_bitmap |= 1 << i; - return 0; - } - } -} -__setup("txx9_serial=", txx9_serial_config); - -console_initcall(txx9_serial_init); diff --git a/arch/powerpc/platforms/cell/celleb_scc_uhc.c b/arch/powerpc/platforms/cell/celleb_scc_uhc.c deleted file mode 100644 index d63b720bfe3a..000000000000 --- a/arch/powerpc/platforms/cell/celleb_scc_uhc.c +++ /dev/null @@ -1,95 +0,0 @@ -/* - * SCC (Super Companion Chip) UHC setup - * - * (C) Copyright 2006-2007 TOSHIBA CORPORATION - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#include <linux/kernel.h> -#include <linux/pci.h> - -#include <asm/delay.h> -#include <asm/io.h> -#include <asm/machdep.h> - -#include "celleb_scc.h" - -#define UHC_RESET_WAIT_MAX 10000 - -static inline int uhc_clkctrl_ready(u32 val) -{ - const u32 mask = SCC_UHC_USBCEN | SCC_UHC_USBCEN; - return((val & mask) == mask); -} - -/* - * UHC(usb host controller) enable function. - * affect to both of OHCI and EHCI core module. - */ -static void enable_scc_uhc(struct pci_dev *dev) -{ - void __iomem *uhc_base; - u32 __iomem *uhc_clkctrl; - u32 __iomem *uhc_ecmode; - u32 val = 0; - int i; - - if (!machine_is(celleb_beat) && - !machine_is(celleb_native)) - return; - - uhc_base = ioremap(pci_resource_start(dev, 0), - pci_resource_len(dev, 0)); - if (!uhc_base) { - printk(KERN_ERR "failed to map UHC register base.\n"); - return; - } - uhc_clkctrl = uhc_base + SCC_UHC_CKRCTRL; - uhc_ecmode = uhc_base + SCC_UHC_ECMODE; - - /* setup for normal mode */ - val |= SCC_UHC_F48MCKLEN; - out_be32(uhc_clkctrl, val); - val |= SCC_UHC_PHY_SUSPEND_SEL; - out_be32(uhc_clkctrl, val); - udelay(10); - val |= SCC_UHC_PHYEN; - out_be32(uhc_clkctrl, val); - udelay(50); - - /* disable reset */ - val |= SCC_UHC_HCLKEN; - out_be32(uhc_clkctrl, val); - val |= (SCC_UHC_USBCEN | SCC_UHC_USBEN); - out_be32(uhc_clkctrl, val); - i = 0; - while (!uhc_clkctrl_ready(in_be32(uhc_clkctrl))) { - udelay(10); - if (i++ > UHC_RESET_WAIT_MAX) { - printk(KERN_ERR "Failed to disable UHC reset %x\n", - in_be32(uhc_clkctrl)); - break; - } - } - - /* Endian Conversion Mode for Master ALL area */ - out_be32(uhc_ecmode, SCC_UHC_ECMODE_BY_BYTE); - - iounmap(uhc_base); -} - -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TOSHIBA_2, - PCI_DEVICE_ID_TOSHIBA_SCC_USB, enable_scc_uhc); diff --git a/arch/powerpc/platforms/cell/celleb_setup.c b/arch/powerpc/platforms/cell/celleb_setup.c deleted file mode 100644 index 90be8ec51686..000000000000 --- a/arch/powerpc/platforms/cell/celleb_setup.c +++ /dev/null @@ -1,243 +0,0 @@ -/* - * Celleb setup code - * - * (C) Copyright 2006-2007 TOSHIBA CORPORATION - * - * This code is based on arch/powerpc/platforms/cell/setup.c: - * Copyright (C) 1995 Linus Torvalds - * Adapted from 'alpha' version by Gary Thomas - * Modified by Cort Dougan (cort@cs.nmt.edu) - * Modified by PPC64 Team, IBM Corp - * Modified by Cell Team, IBM Deutschland Entwicklung GmbH - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#undef DEBUG - -#include <linux/cpu.h> -#include <linux/sched.h> -#include <linux/kernel.h> -#include <linux/export.h> -#include <linux/mm.h> -#include <linux/stddef.h> -#include <linux/unistd.h> -#include <linux/reboot.h> -#include <linux/init.h> -#include <linux/delay.h> -#include <linux/irq.h> -#include <linux/seq_file.h> -#include <linux/root_dev.h> -#include <linux/console.h> -#include <linux/of_platform.h> - -#include <asm/mmu.h> -#include <asm/processor.h> -#include <asm/io.h> -#include <asm/prom.h> -#include <asm/machdep.h> -#include <asm/cputable.h> -#include <asm/irq.h> -#include <asm/time.h> -#include <asm/spu_priv1.h> -#include <asm/firmware.h> -#include <asm/rtas.h> -#include <asm/cell-regs.h> - -#include "beat_interrupt.h" -#include "beat_wrapper.h" -#include "beat.h" -#include "celleb_pci.h" -#include "interrupt.h" -#include "pervasive.h" -#include "ras.h" - -static char celleb_machine_type[128] = "Celleb"; - -static void celleb_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); - /* using "CHRP" is to trick anaconda into installing FCx into Celleb */ - seq_printf(m, "machine\t\t: %s %s\n", celleb_machine_type, model); - of_node_put(root); -} - -static int __init celleb_machine_type_hack(char *ptr) -{ - strlcpy(celleb_machine_type, ptr, sizeof(celleb_machine_type)); - return 0; -} - -__setup("celleb_machine_type_hack=", celleb_machine_type_hack); - -static void celleb_progress(char *s, unsigned short hex) -{ - printk("*** %04x : %s\n", hex, s ? s : ""); -} - -static void __init celleb_setup_arch_common(void) -{ - /* init to some ~sane value until calibrate_delay() runs */ - loops_per_jiffy = 50000000; - -#ifdef CONFIG_DUMMY_CONSOLE - conswitchp = &dummy_con; -#endif -} - -static const struct of_device_id celleb_bus_ids[] __initconst = { - { .type = "scc", }, - { .type = "ioif", }, /* old style */ - {}, -}; - -static int __init celleb_publish_devices(void) -{ - /* Publish OF platform devices for southbridge IOs */ - of_platform_bus_probe(NULL, celleb_bus_ids, NULL); - - return 0; -} -machine_device_initcall(celleb_beat, celleb_publish_devices); -machine_device_initcall(celleb_native, celleb_publish_devices); - - -/* - * functions for Celleb-Beat - */ -static void __init celleb_setup_arch_beat(void) -{ -#ifdef CONFIG_SPU_BASE - spu_priv1_ops = &spu_priv1_beat_ops; - spu_management_ops = &spu_management_of_ops; -#endif - - celleb_setup_arch_common(); -} - -static int __init celleb_probe_beat(void) -{ - unsigned long root = of_get_flat_dt_root(); - - if (!of_flat_dt_is_compatible(root, "Beat")) - return 0; - - powerpc_firmware_features |= FW_FEATURE_CELLEB_ALWAYS - | FW_FEATURE_BEAT | FW_FEATURE_LPAR; - hpte_init_beat_v3(); - pm_power_off = beat_power_off; - - return 1; -} - - -/* - * functions for Celleb-native - */ -static void __init celleb_init_IRQ_native(void) -{ - iic_init_IRQ(); - spider_init_IRQ(); -} - -static void __init celleb_setup_arch_native(void) -{ -#ifdef CONFIG_SPU_BASE - spu_priv1_ops = &spu_priv1_mmio_ops; - spu_management_ops = &spu_management_of_ops; -#endif - - cbe_regs_init(); - -#ifdef CONFIG_CBE_RAS - cbe_ras_init(); -#endif - -#ifdef CONFIG_SMP - smp_init_cell(); -#endif - - cbe_pervasive_init(); - - /* XXX: nvram initialization should be added */ - - celleb_setup_arch_common(); -} - -static int __init celleb_probe_native(void) -{ - unsigned long root = of_get_flat_dt_root(); - - if (of_flat_dt_is_compatible(root, "Beat") || - !of_flat_dt_is_compatible(root, "TOSHIBA,Celleb")) - return 0; - - powerpc_firmware_features |= FW_FEATURE_CELLEB_ALWAYS; - hpte_init_native(); - pm_power_off = rtas_power_off; - - return 1; -} - - -/* - * machine definitions - */ -define_machine(celleb_beat) { - .name = "Cell Reference Set (Beat)", - .probe = celleb_probe_beat, - .setup_arch = celleb_setup_arch_beat, - .show_cpuinfo = celleb_show_cpuinfo, - .restart = beat_restart, - .halt = beat_halt, - .get_rtc_time = beat_get_rtc_time, - .set_rtc_time = beat_set_rtc_time, - .calibrate_decr = generic_calibrate_decr, - .progress = celleb_progress, - .power_save = beat_power_save, - .nvram_size = beat_nvram_get_size, - .nvram_read = beat_nvram_read, - .nvram_write = beat_nvram_write, - .set_dabr = beat_set_xdabr, - .init_IRQ = beatic_init_IRQ, - .get_irq = beatic_get_irq, - .pci_probe_mode = celleb_pci_probe_mode, - .pci_setup_phb = celleb_setup_phb, -#ifdef CONFIG_KEXEC - .kexec_cpu_down = beat_kexec_cpu_down, -#endif -}; - -define_machine(celleb_native) { - .name = "Cell Reference Set (native)", - .probe = celleb_probe_native, - .setup_arch = celleb_setup_arch_native, - .show_cpuinfo = celleb_show_cpuinfo, - .restart = rtas_restart, - .halt = rtas_halt, - .get_boot_time = rtas_get_boot_time, - .get_rtc_time = rtas_get_rtc_time, - .set_rtc_time = rtas_set_rtc_time, - .calibrate_decr = generic_calibrate_decr, - .progress = celleb_progress, - .pci_probe_mode = celleb_pci_probe_mode, - .pci_setup_phb = celleb_setup_phb, - .init_IRQ = celleb_init_IRQ_native, -}; diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c index 4c11421847be..3af8324c122e 100644 --- a/arch/powerpc/platforms/cell/interrupt.c +++ b/arch/powerpc/platforms/cell/interrupt.c @@ -163,7 +163,7 @@ static unsigned int iic_get_irq(void) void iic_setup_cpu(void) { - out_be64(this_cpu_ptr(&cpu_iic.regs->prio), 0xff); + out_be64(&this_cpu_ptr(&cpu_iic)->regs->prio, 0xff); } u8 iic_get_target_id(int cpu) diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index c7c8720aa39f..21b502398bf3 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -39,6 +39,7 @@ #include <asm/firmware.h> #include <asm/cell-regs.h> +#include "cell.h" #include "interrupt.h" /* Define CELL_IOMMU_REAL_UNMAP to actually unmap non-used pages @@ -197,7 +198,7 @@ static int tce_build_cell(struct iommu_table *tbl, long index, long npages, io_pte = (unsigned long *)tbl->it_base + (index - tbl->it_offset); - for (i = 0; i < npages; i++, uaddr += tbl->it_page_shift) + for (i = 0; i < npages; i++, uaddr += (1 << tbl->it_page_shift)) io_pte[i] = base_pte | (__pa(uaddr) & CBE_IOPTE_RPN_Mask); mb(); @@ -857,7 +858,7 @@ static int __init cell_iommu_init_disabled(void) cell_dma_direct_offset += base; if (cell_dma_direct_offset != 0) - ppc_md.pci_dma_dev_setup = cell_pci_dma_dev_setup; + cell_pci_controller_ops.dma_dev_setup = cell_pci_dma_dev_setup; printk("iommu: disabled, direct DMA offset is 0x%lx\n", cell_dma_direct_offset); @@ -1197,8 +1198,8 @@ static int __init cell_iommu_init(void) if (cell_iommu_init_disabled() == 0) goto bail; - /* Setup various ppc_md. callbacks */ - ppc_md.pci_dma_dev_setup = cell_pci_dma_dev_setup; + /* Setup various callbacks */ + cell_pci_controller_ops.dma_dev_setup = cell_pci_dma_dev_setup; ppc_md.dma_get_required_mask = cell_dma_get_required_mask; ppc_md.tce_build = tce_build_cell; ppc_md.tce_free = tce_free_cell; @@ -1234,5 +1235,3 @@ static int __init cell_iommu_init(void) return 0; } machine_arch_initcall(cell, cell_iommu_init); -machine_arch_initcall(celleb_native, cell_iommu_init); - diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c index d62aa982d530..36cff28d0293 100644 --- a/arch/powerpc/platforms/cell/setup.c +++ b/arch/powerpc/platforms/cell/setup.c @@ -54,6 +54,7 @@ #include <asm/cell-regs.h> #include <asm/io-workarounds.h> +#include "cell.h" #include "interrupt.h" #include "pervasive.h" #include "ras.h" @@ -126,6 +127,8 @@ static int cell_setup_phb(struct pci_controller *phb) if (rc) return rc; + phb->controller_ops = cell_pci_controller_ops; + np = phb->dn; model = of_get_property(np, "model", NULL); if (model == NULL || strcmp(np->name, "pci")) @@ -279,3 +282,5 @@ define_machine(cell) { .init_IRQ = cell_init_irq, .pci_setup_phb = cell_setup_phb, }; + +struct pci_controller_ops cell_pci_controller_ops; diff --git a/arch/powerpc/platforms/cell/smp.c b/arch/powerpc/platforms/cell/smp.c index b64e7ead752f..895560f4be69 100644 --- a/arch/powerpc/platforms/cell/smp.c +++ b/arch/powerpc/platforms/cell/smp.c @@ -102,13 +102,6 @@ static inline int smp_startup_cpu(unsigned int lcpu) return 1; } -static int __init smp_iic_probe(void) -{ - iic_request_IPIs(); - - return num_possible_cpus(); -} - static void smp_cell_setup_cpu(int cpu) { if (cpu != boot_cpuid) @@ -139,7 +132,7 @@ static int smp_cell_kick_cpu(int nr) static struct smp_ops_t bpa_iic_smp_ops = { .message_pass = iic_message_pass, - .probe = smp_iic_probe, + .probe = iic_request_IPIs, .kick_cpu = smp_cell_kick_cpu, .setup_cpu = smp_cell_setup_cpu, .cpu_bootable = smp_generic_cpu_bootable, diff --git a/arch/powerpc/platforms/cell/spu_callbacks.c b/arch/powerpc/platforms/cell/spu_callbacks.c index b0ec78e8ad68..a494028b2cdf 100644 --- a/arch/powerpc/platforms/cell/spu_callbacks.c +++ b/arch/powerpc/platforms/cell/spu_callbacks.c @@ -39,6 +39,7 @@ static void *spu_syscall_table[] = { #define PPC_SYS(func) sys_ni_syscall, #define OLDSYS(func) sys_ni_syscall, #define SYS32ONLY(func) sys_ni_syscall, +#define PPC64ONLY(func) sys_ni_syscall, #define SYSX(f, f3264, f32) sys_ni_syscall, #define SYSCALL_SPU(func) sys_##func, diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c index 860a59eb8ea2..15ebc4e8a151 100644 --- a/arch/powerpc/platforms/chrp/setup.c +++ b/arch/powerpc/platforms/chrp/setup.c @@ -253,7 +253,7 @@ static void briq_restart(char *cmd) * But unfortunately, the firmware does not connect /chosen/{stdin,stdout} * the the built-in serial node. Instead, a /failsafe node is created. */ -static void chrp_init_early(void) +static __init void chrp_init_early(void) { struct device_node *node; const char *property; diff --git a/arch/powerpc/platforms/maple/maple.h b/arch/powerpc/platforms/maple/maple.h index c6911ddc479f..eecfa182b06e 100644 --- a/arch/powerpc/platforms/maple/maple.h +++ b/arch/powerpc/platforms/maple/maple.h @@ -10,3 +10,5 @@ extern void maple_calibrate_decr(void); extern void maple_pci_init(void); extern void maple_pci_irq_fixup(struct pci_dev *dev); extern int maple_pci_get_legacy_ide_irq(struct pci_dev *dev, int channel); + +extern struct pci_controller_ops maple_pci_controller_ops; diff --git a/arch/powerpc/platforms/maple/pci.c b/arch/powerpc/platforms/maple/pci.c index d3a13067ec42..a923230e575b 100644 --- a/arch/powerpc/platforms/maple/pci.c +++ b/arch/powerpc/platforms/maple/pci.c @@ -510,6 +510,7 @@ static int __init maple_add_bridge(struct device_node *dev) return -ENOMEM; hose->first_busno = bus_range ? bus_range[0] : 0; hose->last_busno = bus_range ? bus_range[1] : 0xff; + hose->controller_ops = maple_pci_controller_ops; disp_name = NULL; if (of_device_is_compatible(dev, "u3-agp")) { @@ -660,3 +661,6 @@ static void quirk_ipr_msi(struct pci_dev *dev) } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_OBSIDIAN, quirk_ipr_msi); + +struct pci_controller_ops maple_pci_controller_ops = { +}; diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c index 56b85cd61aaf..a837188544c8 100644 --- a/arch/powerpc/platforms/maple/setup.c +++ b/arch/powerpc/platforms/maple/setup.c @@ -203,7 +203,7 @@ static void __init maple_init_early(void) { DBG(" -> maple_init_early\n"); - iommu_init_early_dart(); + iommu_init_early_dart(&maple_pci_controller_ops); DBG(" <- maple_init_early\n"); } diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c index 2e576f2ae442..b8f567b2ea19 100644 --- a/arch/powerpc/platforms/pasemi/iommu.c +++ b/arch/powerpc/platforms/pasemi/iommu.c @@ -27,6 +27,8 @@ #include <asm/machdep.h> #include <asm/firmware.h> +#include "pasemi.h" + #define IOBMAP_PAGE_SHIFT 12 #define IOBMAP_PAGE_SIZE (1 << IOBMAP_PAGE_SHIFT) #define IOBMAP_PAGE_MASK (IOBMAP_PAGE_SIZE - 1) @@ -248,8 +250,8 @@ void __init iommu_init_early_pasemi(void) iob_init(NULL); - ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_pasemi; - ppc_md.pci_dma_bus_setup = pci_dma_bus_setup_pasemi; + pasemi_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pasemi; + pasemi_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pasemi; ppc_md.tce_build = iobmap_build; ppc_md.tce_free = iobmap_free; set_pci_dma_ops(&dma_iommu_ops); diff --git a/arch/powerpc/platforms/pasemi/pasemi.h b/arch/powerpc/platforms/pasemi/pasemi.h index ea65bf0eb897..11f230a48227 100644 --- a/arch/powerpc/platforms/pasemi/pasemi.h +++ b/arch/powerpc/platforms/pasemi/pasemi.h @@ -30,5 +30,6 @@ static inline void restore_astate(int cpu) } #endif +extern struct pci_controller_ops pasemi_pci_controller_ops; #endif /* _PASEMI_PASEMI_H */ diff --git a/arch/powerpc/platforms/pasemi/pci.c b/arch/powerpc/platforms/pasemi/pci.c index aa862713258c..f3a68a0fef23 100644 --- a/arch/powerpc/platforms/pasemi/pci.c +++ b/arch/powerpc/platforms/pasemi/pci.c @@ -31,6 +31,8 @@ #include <asm/ppc-pci.h> +#include "pasemi.h" + #define PA_PXP_CFA(bus, devfn, off) (((bus) << 20) | ((devfn) << 12) | (off)) static inline int pa_pxp_offset_valid(u8 bus, u8 devfn, int offset) @@ -199,6 +201,7 @@ static int __init pas_add_bridge(struct device_node *dev) hose->first_busno = 0; hose->last_busno = 0xff; + hose->controller_ops = pasemi_pci_controller_ops; setup_pa_pxp(hose); @@ -239,3 +242,5 @@ void __iomem *pasemi_pci_getcfgaddr(struct pci_dev *dev, int offset) return (void __iomem *)pa_pxp_cfg_addr(hose, dev->bus->number, dev->devfn, offset); } + +struct pci_controller_ops pasemi_pci_controller_ops; diff --git a/arch/powerpc/platforms/powermac/bootx_init.c b/arch/powerpc/platforms/powermac/bootx_init.c index 3e91ef538114..76f5013c35e5 100644 --- a/arch/powerpc/platforms/powermac/bootx_init.c +++ b/arch/powerpc/platforms/powermac/bootx_init.c @@ -246,7 +246,7 @@ static void __init bootx_scan_dt_build_strings(unsigned long base, DBG(" detected display ! adding properties names !\n"); bootx_dt_add_string("linux,boot-display", mem_end); bootx_dt_add_string("linux,opened", mem_end); - strncpy(bootx_disp_path, namep, 255); + strlcpy(bootx_disp_path, namep, sizeof(bootx_disp_path)); } /* get and store all property names */ diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c index f4071a67ad00..59ab16fa600f 100644 --- a/arch/powerpc/platforms/powermac/pci.c +++ b/arch/powerpc/platforms/powermac/pci.c @@ -27,6 +27,8 @@ #include <asm/grackle.h> #include <asm/ppc-pci.h> +#include "pmac.h" + #undef DEBUG #ifdef DEBUG @@ -798,6 +800,7 @@ static int __init pmac_add_bridge(struct device_node *dev) return -ENOMEM; hose->first_busno = bus_range ? bus_range[0] : 0; hose->last_busno = bus_range ? bus_range[1] : 0xff; + hose->controller_ops = pmac_pci_controller_ops; disp_name = NULL; @@ -942,7 +945,7 @@ void __init pmac_pci_init(void) } #ifdef CONFIG_PPC32 -int pmac_pci_enable_device_hook(struct pci_dev *dev) +static bool pmac_pci_enable_device_hook(struct pci_dev *dev) { struct device_node* node; int updatecfg = 0; @@ -958,11 +961,11 @@ int pmac_pci_enable_device_hook(struct pci_dev *dev) && !node) { printk(KERN_INFO "Apple USB OHCI %s disabled by firmware\n", pci_name(dev)); - return -EINVAL; + return false; } if (!node) - return 0; + return true; uninorth_child = node->parent && of_device_is_compatible(node->parent, "uni-north"); @@ -1003,7 +1006,7 @@ int pmac_pci_enable_device_hook(struct pci_dev *dev) L1_CACHE_BYTES >> 2); } - return 0; + return true; } void pmac_pci_fixup_ohci(struct pci_dev *dev) @@ -1223,3 +1226,30 @@ static void fixup_u4_pcie(struct pci_dev* dev) pci_write_config_dword(dev, PCI_PREF_MEMORY_BASE, 0); } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_APPLE, PCI_DEVICE_ID_APPLE_U4_PCIE, fixup_u4_pcie); + +#ifdef CONFIG_PPC64 +static int pmac_pci_probe_mode(struct pci_bus *bus) +{ + struct device_node *node = pci_bus_to_OF_node(bus); + + /* We need to use normal PCI probing for the AGP bus, + * since the device for the AGP bridge isn't in the tree. + * Same for the PCIe host on U4 and the HT host bridge. + */ + if (bus->self == NULL && (of_device_is_compatible(node, "u3-agp") || + of_device_is_compatible(node, "u4-pcie") || + of_device_is_compatible(node, "u3-ht"))) + return PCI_PROBE_NORMAL; + return PCI_PROBE_DEVTREE; +} +#endif /* CONFIG_PPC64 */ + +struct pci_controller_ops pmac_pci_controller_ops = { +#ifdef CONFIG_PPC64 + .probe_mode = pmac_pci_probe_mode, +#endif +#ifdef CONFIG_PPC32 + .enable_device_hook = pmac_pci_enable_device_hook, +#endif +}; + diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c index 4c24bf60d39d..59cfc9d63c2d 100644 --- a/arch/powerpc/platforms/powermac/pic.c +++ b/arch/powerpc/platforms/powermac/pic.c @@ -321,6 +321,9 @@ static void __init pmac_pic_probe_oldstyle(void) max_irqs = max_real_irqs = 64; /* We might have a second cascaded heathrow */ + + /* Compensate for of_node_put() in of_find_node_by_name() */ + of_node_get(master); slave = of_find_node_by_name(master, "mac-io"); /* Check ordering of master & slave */ diff --git a/arch/powerpc/platforms/powermac/pmac.h b/arch/powerpc/platforms/powermac/pmac.h index 8327cce2bdb0..e7f8163d6769 100644 --- a/arch/powerpc/platforms/powermac/pmac.h +++ b/arch/powerpc/platforms/powermac/pmac.h @@ -25,7 +25,6 @@ extern void pmac_pci_init(void); extern void pmac_nvram_update(void); extern unsigned char pmac_nvram_read_byte(int addr); extern void pmac_nvram_write_byte(int addr, unsigned char val); -extern int pmac_pci_enable_device_hook(struct pci_dev *dev); extern void pmac_pcibios_after_init(void); extern int of_show_percpuinfo(struct seq_file *m, int i); @@ -39,4 +38,6 @@ extern void low_cpu_die(void) __attribute__((noreturn)); extern int pmac_nvram_init(void); extern void pmac_pic_init(void); +extern struct pci_controller_ops pmac_pci_controller_ops; + #endif /* __PMAC_H__ */ diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c index 713d36d45d1d..8dd78f4e1af4 100644 --- a/arch/powerpc/platforms/powermac/setup.c +++ b/arch/powerpc/platforms/powermac/setup.c @@ -473,7 +473,7 @@ static void __init pmac_init_early(void) udbg_adb_init(!!strstr(boot_command_line, "btextdbg")); #ifdef CONFIG_PPC64 - iommu_init_early_dart(); + iommu_init_early_dart(&pmac_pci_controller_ops); #endif /* SMP Init has to be done early as we need to patch up @@ -637,24 +637,6 @@ static int __init pmac_probe(void) return 1; } -#ifdef CONFIG_PPC64 -/* Move that to pci.c */ -static int pmac_pci_probe_mode(struct pci_bus *bus) -{ - struct device_node *node = pci_bus_to_OF_node(bus); - - /* We need to use normal PCI probing for the AGP bus, - * since the device for the AGP bridge isn't in the tree. - * Same for the PCIe host on U4 and the HT host bridge. - */ - if (bus->self == NULL && (of_device_is_compatible(node, "u3-agp") || - of_device_is_compatible(node, "u4-pcie") || - of_device_is_compatible(node, "u3-ht"))) - return PCI_PROBE_NORMAL; - return PCI_PROBE_DEVTREE; -} -#endif /* CONFIG_PPC64 */ - define_machine(powermac) { .name = "PowerMac", .probe = pmac_probe, @@ -674,12 +656,10 @@ define_machine(powermac) { .feature_call = pmac_do_feature_call, .progress = udbg_progress, #ifdef CONFIG_PPC64 - .pci_probe_mode = pmac_pci_probe_mode, .power_save = power4_idle, .enable_pmcs = power4_enable_pmcs, #endif /* CONFIG_PPC64 */ #ifdef CONFIG_PPC32 - .pcibios_enable_device_hook = pmac_pci_enable_device_hook, .pcibios_after_init = pmac_pcibios_after_init, .phys_mem_access_prot = pci_phys_mem_access_prot, #endif diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index af094ae03dbb..28a147ca32ba 100644 --- a/arch/powerpc/platforms/powermac/smp.c +++ b/arch/powerpc/platforms/powermac/smp.c @@ -268,14 +268,14 @@ static void __init psurge_quad_init(void) mdelay(33); } -static int __init smp_psurge_probe(void) +static void __init smp_psurge_probe(void) { int i, ncpus; struct device_node *dn; /* We don't do SMP on the PPC601 -- paulus */ if (PVR_VER(mfspr(SPRN_PVR)) == 1) - return 1; + return; /* * The powersurge cpu board can be used in the generation @@ -289,7 +289,7 @@ static int __init smp_psurge_probe(void) */ dn = of_find_node_by_name(NULL, "hammerhead"); if (dn == NULL) - return 1; + return; of_node_put(dn); hhead_base = ioremap(HAMMERHEAD_BASE, 0x800); @@ -310,13 +310,13 @@ static int __init smp_psurge_probe(void) /* not a dual-cpu card */ iounmap(hhead_base); psurge_type = PSURGE_NONE; - return 1; + return; } ncpus = 2; } if (psurge_secondary_ipi_init()) - return 1; + return; psurge_start = ioremap(PSURGE_START, 4); psurge_pri_intr = ioremap(PSURGE_PRI_INTR, 4); @@ -332,8 +332,6 @@ static int __init smp_psurge_probe(void) set_cpu_present(i, true); if (ppc_md.progress) ppc_md.progress("smp_psurge_probe - done", 0x352); - - return ncpus; } static int __init smp_psurge_kick_cpu(int nr) @@ -766,7 +764,7 @@ static void __init smp_core99_setup(int ncpus) powersave_nap = 0; } -static int __init smp_core99_probe(void) +static void __init smp_core99_probe(void) { struct device_node *cpus; int ncpus = 0; @@ -781,7 +779,7 @@ static int __init smp_core99_probe(void) /* Nothing more to do if less than 2 of them */ if (ncpus <= 1) - return 1; + return; /* We need to perform some early initialisations before we can start * setting up SMP as we are running before initcalls @@ -797,8 +795,6 @@ static int __init smp_core99_probe(void) /* Collect l2cr and l3cr values from CPU 0 */ core99_init_caches(0); - - return ncpus; } static int smp_core99_kick_cpu(int nr) diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig index 45a8ed0585cd..4b044d8cb49a 100644 --- a/arch/powerpc/platforms/powernv/Kconfig +++ b/arch/powerpc/platforms/powernv/Kconfig @@ -19,10 +19,3 @@ config PPC_POWERNV select CPU_FREQ_GOV_CONSERVATIVE select PPC_DOORBELL 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 index 6f3c5d33c3af..33e44f37212f 100644 --- a/arch/powerpc/platforms/powernv/Makefile +++ b/arch/powerpc/platforms/powernv/Makefile @@ -5,7 +5,7 @@ obj-y += opal-msglog.o opal-hmi.o opal-power.o obj-$(CONFIG_SMP) += smp.o subcore.o subcore-asm.o obj-$(CONFIG_PCI) += pci.o pci-p5ioc2.o pci-ioda.o -obj-$(CONFIG_EEH) += eeh-ioda.o eeh-powernv.o +obj-$(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 diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c deleted file mode 100644 index 2809c9895288..000000000000 --- a/arch/powerpc/platforms/powernv/eeh-ioda.c +++ /dev/null @@ -1,1149 +0,0 @@ -/* - * The file intends to implement the functions needed by EEH, which is - * built on IODA compliant chip. Actually, lots of functions related - * to EEH would be built based on the OPAL APIs. - * - * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2013. - * - * 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/debugfs.h> -#include <linux/delay.h> -#include <linux/io.h> -#include <linux/irq.h> -#include <linux/kernel.h> -#include <linux/msi.h> -#include <linux/notifier.h> -#include <linux/pci.h> -#include <linux/string.h> - -#include <asm/eeh.h> -#include <asm/eeh_event.h> -#include <asm/io.h> -#include <asm/iommu.h> -#include <asm/msi_bitmap.h> -#include <asm/opal.h> -#include <asm/pci-bridge.h> -#include <asm/ppc-pci.h> -#include <asm/tce.h> - -#include "powernv.h" -#include "pci.h" - -static int ioda_eeh_nb_init = 0; - -static int ioda_eeh_event(struct notifier_block *nb, - unsigned long events, void *change) -{ - uint64_t changed_evts = (uint64_t)change; - - /* - * We simply send special EEH event if EEH has - * been enabled, or clear pending events in - * case that we enable EEH soon - */ - if (!(changed_evts & OPAL_EVENT_PCI_ERROR) || - !(events & OPAL_EVENT_PCI_ERROR)) - return 0; - - if (eeh_enabled()) - eeh_send_failure_event(NULL); - else - opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul); - - return 0; -} - -static struct notifier_block ioda_eeh_nb = { - .notifier_call = ioda_eeh_event, - .next = NULL, - .priority = 0 -}; - -#ifdef CONFIG_DEBUG_FS -static ssize_t ioda_eeh_ei_write(struct file *filp, - const char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct pci_controller *hose = filp->private_data; - struct pnv_phb *phb = hose->private_data; - struct eeh_dev *edev; - struct eeh_pe *pe; - int pe_no, type, func; - unsigned long addr, mask; - char buf[50]; - int ret; - - if (!phb->eeh_ops || !phb->eeh_ops->err_inject) - return -ENXIO; - - ret = simple_write_to_buffer(buf, sizeof(buf), ppos, user_buf, count); - if (!ret) - return -EFAULT; - - /* Retrieve parameters */ - ret = sscanf(buf, "%x:%x:%x:%lx:%lx", - &pe_no, &type, &func, &addr, &mask); - if (ret != 5) - return -EINVAL; - - /* Retrieve PE */ - edev = kzalloc(sizeof(*edev), GFP_KERNEL); - if (!edev) - return -ENOMEM; - edev->phb = hose; - edev->pe_config_addr = pe_no; - pe = eeh_pe_get(edev); - kfree(edev); - if (!pe) - return -ENODEV; - - /* Do error injection */ - ret = phb->eeh_ops->err_inject(pe, type, func, addr, mask); - return ret < 0 ? ret : count; -} - -static const struct file_operations ioda_eeh_ei_fops = { - .open = simple_open, - .llseek = no_llseek, - .write = ioda_eeh_ei_write, -}; - -static int ioda_eeh_dbgfs_set(void *data, int offset, u64 val) -{ - struct pci_controller *hose = data; - struct pnv_phb *phb = hose->private_data; - - out_be64(phb->regs + offset, val); - return 0; -} - -static int ioda_eeh_dbgfs_get(void *data, int offset, u64 *val) -{ - struct pci_controller *hose = data; - struct pnv_phb *phb = hose->private_data; - - *val = in_be64(phb->regs + offset); - return 0; -} - -static int ioda_eeh_outb_dbgfs_set(void *data, u64 val) -{ - return ioda_eeh_dbgfs_set(data, 0xD10, val); -} - -static int ioda_eeh_outb_dbgfs_get(void *data, u64 *val) -{ - return ioda_eeh_dbgfs_get(data, 0xD10, val); -} - -static int ioda_eeh_inbA_dbgfs_set(void *data, u64 val) -{ - return ioda_eeh_dbgfs_set(data, 0xD90, val); -} - -static int ioda_eeh_inbA_dbgfs_get(void *data, u64 *val) -{ - return ioda_eeh_dbgfs_get(data, 0xD90, val); -} - -static int ioda_eeh_inbB_dbgfs_set(void *data, u64 val) -{ - return ioda_eeh_dbgfs_set(data, 0xE10, val); -} - -static int ioda_eeh_inbB_dbgfs_get(void *data, u64 *val) -{ - return ioda_eeh_dbgfs_get(data, 0xE10, val); -} - -DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_outb_dbgfs_ops, ioda_eeh_outb_dbgfs_get, - ioda_eeh_outb_dbgfs_set, "0x%llx\n"); -DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_inbA_dbgfs_ops, ioda_eeh_inbA_dbgfs_get, - ioda_eeh_inbA_dbgfs_set, "0x%llx\n"); -DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_inbB_dbgfs_ops, ioda_eeh_inbB_dbgfs_get, - ioda_eeh_inbB_dbgfs_set, "0x%llx\n"); -#endif /* CONFIG_DEBUG_FS */ - - -/** - * ioda_eeh_post_init - Chip dependent post initialization - * @hose: PCI controller - * - * The function will be called after eeh PEs and devices - * have been built. That means the EEH is ready to supply - * service with I/O cache. - */ -static int ioda_eeh_post_init(struct pci_controller *hose) -{ - struct pnv_phb *phb = hose->private_data; - int ret; - - /* Register OPAL event notifier */ - if (!ioda_eeh_nb_init) { - ret = opal_notifier_register(&ioda_eeh_nb); - if (ret) { - pr_err("%s: Can't register OPAL event notifier (%d)\n", - __func__, ret); - return ret; - } - - ioda_eeh_nb_init = 1; - } - -#ifdef CONFIG_DEBUG_FS - if (!phb->has_dbgfs && phb->dbgfs) { - phb->has_dbgfs = 1; - - debugfs_create_file("err_injct", 0200, - phb->dbgfs, hose, - &ioda_eeh_ei_fops); - - debugfs_create_file("err_injct_outbound", 0600, - phb->dbgfs, hose, - &ioda_eeh_outb_dbgfs_ops); - debugfs_create_file("err_injct_inboundA", 0600, - phb->dbgfs, hose, - &ioda_eeh_inbA_dbgfs_ops); - debugfs_create_file("err_injct_inboundB", 0600, - phb->dbgfs, hose, - &ioda_eeh_inbB_dbgfs_ops); - } -#endif - - /* If EEH is enabled, we're going to rely on that. - * Otherwise, we restore to conventional mechanism - * to clear frozen PE during PCI config access. - */ - if (eeh_enabled()) - phb->flags |= PNV_PHB_FLAG_EEH; - else - phb->flags &= ~PNV_PHB_FLAG_EEH; - - return 0; -} - -/** - * ioda_eeh_set_option - Set EEH operation or I/O setting - * @pe: EEH PE - * @option: options - * - * Enable or disable EEH option for the indicated PE. The - * function also can be used to enable I/O or DMA for the - * PE. - */ -static int ioda_eeh_set_option(struct eeh_pe *pe, int option) -{ - struct pci_controller *hose = pe->phb; - struct pnv_phb *phb = hose->private_data; - bool freeze_pe = false; - int enable, ret = 0; - s64 rc; - - /* Check on PE number */ - if (pe->addr < 0 || pe->addr >= phb->ioda.total_pe) { - pr_err("%s: PE address %x out of range [0, %x] " - "on PHB#%x\n", - __func__, pe->addr, phb->ioda.total_pe, - hose->global_number); - return -EINVAL; - } - - switch (option) { - case EEH_OPT_DISABLE: - return -EPERM; - case EEH_OPT_ENABLE: - return 0; - case EEH_OPT_THAW_MMIO: - enable = OPAL_EEH_ACTION_CLEAR_FREEZE_MMIO; - break; - case EEH_OPT_THAW_DMA: - enable = OPAL_EEH_ACTION_CLEAR_FREEZE_DMA; - break; - case EEH_OPT_FREEZE_PE: - freeze_pe = true; - enable = OPAL_EEH_ACTION_SET_FREEZE_ALL; - break; - default: - pr_warn("%s: Invalid option %d\n", - __func__, option); - return -EINVAL; - } - - /* If PHB supports compound PE, to handle it */ - if (freeze_pe) { - if (phb->freeze_pe) { - phb->freeze_pe(phb, pe->addr); - } else { - rc = opal_pci_eeh_freeze_set(phb->opal_id, - pe->addr, - enable); - if (rc != OPAL_SUCCESS) { - pr_warn("%s: Failure %lld freezing " - "PHB#%x-PE#%x\n", - __func__, rc, - phb->hose->global_number, pe->addr); - ret = -EIO; - } - } - } else { - if (phb->unfreeze_pe) { - ret = phb->unfreeze_pe(phb, pe->addr, enable); - } else { - rc = opal_pci_eeh_freeze_clear(phb->opal_id, - pe->addr, - enable); - if (rc != OPAL_SUCCESS) { - pr_warn("%s: Failure %lld enable %d " - "for PHB#%x-PE#%x\n", - __func__, rc, option, - phb->hose->global_number, pe->addr); - ret = -EIO; - } - } - } - - return ret; -} - -static void ioda_eeh_phb_diag(struct eeh_pe *pe) -{ - struct pnv_phb *phb = pe->phb->private_data; - long rc; - - rc = opal_pci_get_phb_diag_data2(phb->opal_id, pe->data, - PNV_PCI_DIAG_BUF_SIZE); - if (rc != OPAL_SUCCESS) - pr_warn("%s: Failed to get diag-data for PHB#%x (%ld)\n", - __func__, pe->phb->global_number, rc); -} - -static int ioda_eeh_get_phb_state(struct eeh_pe *pe) -{ - struct pnv_phb *phb = pe->phb->private_data; - u8 fstate; - __be16 pcierr; - s64 rc; - int result = 0; - - rc = opal_pci_eeh_freeze_status(phb->opal_id, - pe->addr, - &fstate, - &pcierr, - NULL); - if (rc != OPAL_SUCCESS) { - pr_warn("%s: Failure %lld getting PHB#%x state\n", - __func__, rc, phb->hose->global_number); - return EEH_STATE_NOT_SUPPORT; - } - - /* - * Check PHB state. If the PHB is frozen for the - * first time, to dump the PHB diag-data. - */ - if (be16_to_cpu(pcierr) != OPAL_EEH_PHB_ERROR) { - result = (EEH_STATE_MMIO_ACTIVE | - EEH_STATE_DMA_ACTIVE | - EEH_STATE_MMIO_ENABLED | - EEH_STATE_DMA_ENABLED); - } else if (!(pe->state & EEH_PE_ISOLATED)) { - eeh_pe_state_mark(pe, EEH_PE_ISOLATED); - ioda_eeh_phb_diag(pe); - - if (eeh_has_flag(EEH_EARLY_DUMP_LOG)) - pnv_pci_dump_phb_diag_data(pe->phb, pe->data); - } - - return result; -} - -static int ioda_eeh_get_pe_state(struct eeh_pe *pe) -{ - struct pnv_phb *phb = pe->phb->private_data; - u8 fstate; - __be16 pcierr; - s64 rc; - int result; - - /* - * We don't clobber hardware frozen state until PE - * reset is completed. In order to keep EEH core - * moving forward, we have to return operational - * state during PE reset. - */ - if (pe->state & EEH_PE_RESET) { - result = (EEH_STATE_MMIO_ACTIVE | - EEH_STATE_DMA_ACTIVE | - EEH_STATE_MMIO_ENABLED | - EEH_STATE_DMA_ENABLED); - return result; - } - - /* - * Fetch PE state from hardware. If the PHB - * supports compound PE, let it handle that. - */ - if (phb->get_pe_state) { - fstate = phb->get_pe_state(phb, pe->addr); - } else { - rc = opal_pci_eeh_freeze_status(phb->opal_id, - pe->addr, - &fstate, - &pcierr, - NULL); - if (rc != OPAL_SUCCESS) { - pr_warn("%s: Failure %lld getting PHB#%x-PE%x state\n", - __func__, rc, phb->hose->global_number, pe->addr); - return EEH_STATE_NOT_SUPPORT; - } - } - - /* Figure out state */ - switch (fstate) { - case OPAL_EEH_STOPPED_NOT_FROZEN: - result = (EEH_STATE_MMIO_ACTIVE | - EEH_STATE_DMA_ACTIVE | - EEH_STATE_MMIO_ENABLED | - EEH_STATE_DMA_ENABLED); - break; - case OPAL_EEH_STOPPED_MMIO_FREEZE: - result = (EEH_STATE_DMA_ACTIVE | - EEH_STATE_DMA_ENABLED); - break; - case OPAL_EEH_STOPPED_DMA_FREEZE: - result = (EEH_STATE_MMIO_ACTIVE | - EEH_STATE_MMIO_ENABLED); - break; - case OPAL_EEH_STOPPED_MMIO_DMA_FREEZE: - result = 0; - break; - case OPAL_EEH_STOPPED_RESET: - result = EEH_STATE_RESET_ACTIVE; - break; - case OPAL_EEH_STOPPED_TEMP_UNAVAIL: - result = EEH_STATE_UNAVAILABLE; - break; - case OPAL_EEH_STOPPED_PERM_UNAVAIL: - result = EEH_STATE_NOT_SUPPORT; - break; - default: - result = EEH_STATE_NOT_SUPPORT; - pr_warn("%s: Invalid PHB#%x-PE#%x state %x\n", - __func__, phb->hose->global_number, - pe->addr, fstate); - } - - /* - * If PHB supports compound PE, to freeze all - * slave PEs for consistency. - * - * If the PE is switching to frozen state for the - * first time, to dump the PHB diag-data. - */ - if (!(result & EEH_STATE_NOT_SUPPORT) && - !(result & EEH_STATE_UNAVAILABLE) && - !(result & EEH_STATE_MMIO_ACTIVE) && - !(result & EEH_STATE_DMA_ACTIVE) && - !(pe->state & EEH_PE_ISOLATED)) { - if (phb->freeze_pe) - phb->freeze_pe(phb, pe->addr); - - eeh_pe_state_mark(pe, EEH_PE_ISOLATED); - ioda_eeh_phb_diag(pe); - - if (eeh_has_flag(EEH_EARLY_DUMP_LOG)) - pnv_pci_dump_phb_diag_data(pe->phb, pe->data); - } - - return result; -} - -/** - * ioda_eeh_get_state - Retrieve the state of PE - * @pe: EEH PE - * - * The PE's state should be retrieved from the PEEV, PEST - * IODA tables. Since the OPAL has exported the function - * to do it, it'd better to use that. - */ -static int ioda_eeh_get_state(struct eeh_pe *pe) -{ - struct pnv_phb *phb = pe->phb->private_data; - - /* Sanity check on PE number. PHB PE should have 0 */ - if (pe->addr < 0 || - pe->addr >= phb->ioda.total_pe) { - pr_warn("%s: PHB#%x-PE#%x out of range [0, %x]\n", - __func__, phb->hose->global_number, - pe->addr, phb->ioda.total_pe); - return EEH_STATE_NOT_SUPPORT; - } - - if (pe->type & EEH_PE_PHB) - return ioda_eeh_get_phb_state(pe); - - return ioda_eeh_get_pe_state(pe); -} - -static s64 ioda_eeh_phb_poll(struct pnv_phb *phb) -{ - s64 rc = OPAL_HARDWARE; - - while (1) { - rc = opal_pci_poll(phb->opal_id); - if (rc <= 0) - break; - - if (system_state < SYSTEM_RUNNING) - udelay(1000 * rc); - else - msleep(rc); - } - - return rc; -} - -int ioda_eeh_phb_reset(struct pci_controller *hose, int option) -{ - struct pnv_phb *phb = hose->private_data; - s64 rc = OPAL_HARDWARE; - - pr_debug("%s: Reset PHB#%x, option=%d\n", - __func__, hose->global_number, option); - - /* Issue PHB complete reset request */ - if (option == EEH_RESET_FUNDAMENTAL || - option == EEH_RESET_HOT) - rc = opal_pci_reset(phb->opal_id, - OPAL_RESET_PHB_COMPLETE, - OPAL_ASSERT_RESET); - else if (option == EEH_RESET_DEACTIVATE) - rc = opal_pci_reset(phb->opal_id, - OPAL_RESET_PHB_COMPLETE, - OPAL_DEASSERT_RESET); - if (rc < 0) - goto out; - - /* - * Poll state of the PHB until the request is done - * successfully. The PHB reset is usually PHB complete - * reset followed by hot reset on root bus. So we also - * need the PCI bus settlement delay. - */ - rc = ioda_eeh_phb_poll(phb); - if (option == EEH_RESET_DEACTIVATE) { - if (system_state < SYSTEM_RUNNING) - udelay(1000 * EEH_PE_RST_SETTLE_TIME); - else - msleep(EEH_PE_RST_SETTLE_TIME); - } -out: - if (rc != OPAL_SUCCESS) - return -EIO; - - return 0; -} - -static int ioda_eeh_root_reset(struct pci_controller *hose, int option) -{ - struct pnv_phb *phb = hose->private_data; - s64 rc = OPAL_SUCCESS; - - pr_debug("%s: Reset PHB#%x, option=%d\n", - __func__, hose->global_number, option); - - /* - * During the reset deassert time, we needn't care - * the reset scope because the firmware does nothing - * for fundamental or hot reset during deassert phase. - */ - if (option == EEH_RESET_FUNDAMENTAL) - rc = opal_pci_reset(phb->opal_id, - OPAL_RESET_PCI_FUNDAMENTAL, - OPAL_ASSERT_RESET); - else if (option == EEH_RESET_HOT) - rc = opal_pci_reset(phb->opal_id, - OPAL_RESET_PCI_HOT, - OPAL_ASSERT_RESET); - else if (option == EEH_RESET_DEACTIVATE) - rc = opal_pci_reset(phb->opal_id, - OPAL_RESET_PCI_HOT, - OPAL_DEASSERT_RESET); - if (rc < 0) - goto out; - - /* Poll state of the PHB until the request is done */ - rc = ioda_eeh_phb_poll(phb); - if (option == EEH_RESET_DEACTIVATE) - msleep(EEH_PE_RST_SETTLE_TIME); -out: - if (rc != OPAL_SUCCESS) - return -EIO; - - return 0; -} - -static int ioda_eeh_bridge_reset(struct pci_dev *dev, int option) - -{ - struct device_node *dn = pci_device_to_OF_node(dev); - struct eeh_dev *edev = of_node_to_eeh_dev(dn); - int aer = edev ? edev->aer_cap : 0; - u32 ctrl; - - pr_debug("%s: Reset PCI bus %04x:%02x with option %d\n", - __func__, pci_domain_nr(dev->bus), - dev->bus->number, option); - - switch (option) { - case EEH_RESET_FUNDAMENTAL: - case EEH_RESET_HOT: - /* Don't report linkDown event */ - if (aer) { - eeh_ops->read_config(dn, aer + PCI_ERR_UNCOR_MASK, - 4, &ctrl); - ctrl |= PCI_ERR_UNC_SURPDN; - eeh_ops->write_config(dn, aer + PCI_ERR_UNCOR_MASK, - 4, ctrl); - } - - eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &ctrl); - ctrl |= PCI_BRIDGE_CTL_BUS_RESET; - eeh_ops->write_config(dn, PCI_BRIDGE_CONTROL, 2, ctrl); - msleep(EEH_PE_RST_HOLD_TIME); - - break; - case EEH_RESET_DEACTIVATE: - eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &ctrl); - ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET; - eeh_ops->write_config(dn, PCI_BRIDGE_CONTROL, 2, ctrl); - msleep(EEH_PE_RST_SETTLE_TIME); - - /* Continue reporting linkDown event */ - if (aer) { - eeh_ops->read_config(dn, aer + PCI_ERR_UNCOR_MASK, - 4, &ctrl); - ctrl &= ~PCI_ERR_UNC_SURPDN; - eeh_ops->write_config(dn, aer + PCI_ERR_UNCOR_MASK, - 4, ctrl); - } - - break; - } - - return 0; -} - -void pnv_pci_reset_secondary_bus(struct pci_dev *dev) -{ - struct pci_controller *hose; - - if (pci_is_root_bus(dev->bus)) { - hose = pci_bus_to_host(dev->bus); - ioda_eeh_root_reset(hose, EEH_RESET_HOT); - ioda_eeh_root_reset(hose, EEH_RESET_DEACTIVATE); - } else { - ioda_eeh_bridge_reset(dev, EEH_RESET_HOT); - ioda_eeh_bridge_reset(dev, EEH_RESET_DEACTIVATE); - } -} - -/** - * ioda_eeh_reset - Reset the indicated PE - * @pe: EEH PE - * @option: reset option - * - * Do reset on the indicated PE. For PCI bus sensitive PE, - * we need to reset the parent p2p bridge. The PHB has to - * be reinitialized if the p2p bridge is root bridge. For - * PCI device sensitive PE, we will try to reset the device - * through FLR. For now, we don't have OPAL APIs to do HARD - * reset yet, so all reset would be SOFT (HOT) reset. - */ -static int ioda_eeh_reset(struct eeh_pe *pe, int option) -{ - struct pci_controller *hose = pe->phb; - struct pci_bus *bus; - int ret; - - /* - * For PHB reset, we always have complete reset. For those PEs whose - * primary bus derived from root complex (root bus) or root port - * (usually bus#1), we apply hot or fundamental reset on the root port. - * For other PEs, we always have hot reset on the PE primary bus. - * - * Here, we have different design to pHyp, which always clear the - * frozen state during PE reset. However, the good idea here from - * benh is to keep frozen state before we get PE reset done completely - * (until BAR restore). With the frozen state, HW drops illegal IO - * or MMIO access, which can incur recrusive frozen PE during PE - * reset. The side effect is that EEH core has to clear the frozen - * state explicitly after BAR restore. - */ - if (pe->type & EEH_PE_PHB) { - ret = ioda_eeh_phb_reset(hose, option); - } else { - struct pnv_phb *phb; - s64 rc; - - /* - * The frozen PE might be caused by PAPR error injection - * registers, which are expected to be cleared after hitting - * frozen PE as stated in the hardware spec. Unfortunately, - * that's not true on P7IOC. So we have to clear it manually - * to avoid recursive EEH errors during recovery. - */ - phb = hose->private_data; - if (phb->model == PNV_PHB_MODEL_P7IOC && - (option == EEH_RESET_HOT || - option == EEH_RESET_FUNDAMENTAL)) { - rc = opal_pci_reset(phb->opal_id, - OPAL_RESET_PHB_ERROR, - OPAL_ASSERT_RESET); - if (rc != OPAL_SUCCESS) { - pr_warn("%s: Failure %lld clearing " - "error injection registers\n", - __func__, rc); - return -EIO; - } - } - - bus = eeh_pe_bus_get(pe); - if (pci_is_root_bus(bus) || - pci_is_root_bus(bus->parent)) - ret = ioda_eeh_root_reset(hose, option); - else - ret = ioda_eeh_bridge_reset(bus->self, option); - } - - return ret; -} - -/** - * ioda_eeh_get_log - Retrieve error log - * @pe: frozen PE - * @severity: permanent or temporary error - * @drv_log: device driver log - * @len: length of device driver log - * - * Retrieve error log, which contains log from device driver - * and firmware. - */ -static int ioda_eeh_get_log(struct eeh_pe *pe, int severity, - char *drv_log, unsigned long len) -{ - if (!eeh_has_flag(EEH_EARLY_DUMP_LOG)) - pnv_pci_dump_phb_diag_data(pe->phb, pe->data); - - return 0; -} - -/** - * ioda_eeh_configure_bridge - Configure the PCI bridges for the indicated PE - * @pe: EEH PE - * - * For particular PE, it might have included PCI bridges. In order - * to make the PE work properly, those PCI bridges should be configured - * correctly. However, we need do nothing on P7IOC since the reset - * function will do everything that should be covered by the function. - */ -static int ioda_eeh_configure_bridge(struct eeh_pe *pe) -{ - return 0; -} - -static int ioda_eeh_err_inject(struct eeh_pe *pe, int type, int func, - unsigned long addr, unsigned long mask) -{ - struct pci_controller *hose = pe->phb; - struct pnv_phb *phb = hose->private_data; - s64 ret; - - /* Sanity check on error type */ - if (type != OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR && - type != OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR64) { - pr_warn("%s: Invalid error type %d\n", - __func__, type); - return -ERANGE; - } - - if (func < OPAL_ERR_INJECT_FUNC_IOA_LD_MEM_ADDR || - func > OPAL_ERR_INJECT_FUNC_IOA_DMA_WR_TARGET) { - pr_warn("%s: Invalid error function %d\n", - __func__, func); - return -ERANGE; - } - - /* Firmware supports error injection ? */ - if (!opal_check_token(OPAL_PCI_ERR_INJECT)) { - pr_warn("%s: Firmware doesn't support error injection\n", - __func__); - return -ENXIO; - } - - /* Do error injection */ - ret = opal_pci_err_inject(phb->opal_id, pe->addr, - type, func, addr, mask); - if (ret != OPAL_SUCCESS) { - pr_warn("%s: Failure %lld injecting error " - "%d-%d to PHB#%x-PE#%x\n", - __func__, ret, type, func, - hose->global_number, pe->addr); - return -EIO; - } - - return 0; -} - -static void ioda_eeh_hub_diag_common(struct OpalIoP7IOCErrorData *data) -{ - /* GEM */ - if (data->gemXfir || data->gemRfir || - data->gemRirqfir || data->gemMask || data->gemRwof) - pr_info(" GEM: %016llx %016llx %016llx %016llx %016llx\n", - be64_to_cpu(data->gemXfir), - be64_to_cpu(data->gemRfir), - be64_to_cpu(data->gemRirqfir), - be64_to_cpu(data->gemMask), - be64_to_cpu(data->gemRwof)); - - /* LEM */ - if (data->lemFir || data->lemErrMask || - data->lemAction0 || data->lemAction1 || data->lemWof) - pr_info(" LEM: %016llx %016llx %016llx %016llx %016llx\n", - be64_to_cpu(data->lemFir), - be64_to_cpu(data->lemErrMask), - be64_to_cpu(data->lemAction0), - be64_to_cpu(data->lemAction1), - be64_to_cpu(data->lemWof)); -} - -static void ioda_eeh_hub_diag(struct pci_controller *hose) -{ - struct pnv_phb *phb = hose->private_data; - struct OpalIoP7IOCErrorData *data = &phb->diag.hub_diag; - long rc; - - rc = opal_pci_get_hub_diag_data(phb->hub_id, data, sizeof(*data)); - if (rc != OPAL_SUCCESS) { - pr_warn("%s: Failed to get HUB#%llx diag-data (%ld)\n", - __func__, phb->hub_id, rc); - return; - } - - switch (data->type) { - case OPAL_P7IOC_DIAG_TYPE_RGC: - pr_info("P7IOC diag-data for RGC\n\n"); - ioda_eeh_hub_diag_common(data); - if (data->rgc.rgcStatus || data->rgc.rgcLdcp) - pr_info(" RGC: %016llx %016llx\n", - be64_to_cpu(data->rgc.rgcStatus), - be64_to_cpu(data->rgc.rgcLdcp)); - break; - case OPAL_P7IOC_DIAG_TYPE_BI: - pr_info("P7IOC diag-data for BI %s\n\n", - data->bi.biDownbound ? "Downbound" : "Upbound"); - ioda_eeh_hub_diag_common(data); - if (data->bi.biLdcp0 || data->bi.biLdcp1 || - data->bi.biLdcp2 || data->bi.biFenceStatus) - pr_info(" BI: %016llx %016llx %016llx %016llx\n", - be64_to_cpu(data->bi.biLdcp0), - be64_to_cpu(data->bi.biLdcp1), - be64_to_cpu(data->bi.biLdcp2), - be64_to_cpu(data->bi.biFenceStatus)); - break; - case OPAL_P7IOC_DIAG_TYPE_CI: - pr_info("P7IOC diag-data for CI Port %d\n\n", - data->ci.ciPort); - ioda_eeh_hub_diag_common(data); - if (data->ci.ciPortStatus || data->ci.ciPortLdcp) - pr_info(" CI: %016llx %016llx\n", - be64_to_cpu(data->ci.ciPortStatus), - be64_to_cpu(data->ci.ciPortLdcp)); - break; - case OPAL_P7IOC_DIAG_TYPE_MISC: - pr_info("P7IOC diag-data for MISC\n\n"); - ioda_eeh_hub_diag_common(data); - break; - case OPAL_P7IOC_DIAG_TYPE_I2C: - pr_info("P7IOC diag-data for I2C\n\n"); - ioda_eeh_hub_diag_common(data); - break; - default: - pr_warn("%s: Invalid type of HUB#%llx diag-data (%d)\n", - __func__, phb->hub_id, data->type); - } -} - -static int ioda_eeh_get_pe(struct pci_controller *hose, - u16 pe_no, struct eeh_pe **pe) -{ - struct pnv_phb *phb = hose->private_data; - struct pnv_ioda_pe *pnv_pe; - struct eeh_pe *dev_pe; - struct eeh_dev edev; - - /* - * If PHB supports compound PE, to fetch - * the master PE because slave PE is invisible - * to EEH core. - */ - pnv_pe = &phb->ioda.pe_array[pe_no]; - if (pnv_pe->flags & PNV_IODA_PE_SLAVE) { - pnv_pe = pnv_pe->master; - WARN_ON(!pnv_pe || - !(pnv_pe->flags & PNV_IODA_PE_MASTER)); - pe_no = pnv_pe->pe_number; - } - - /* Find the PE according to PE# */ - memset(&edev, 0, sizeof(struct eeh_dev)); - edev.phb = hose; - edev.pe_config_addr = pe_no; - dev_pe = eeh_pe_get(&edev); - if (!dev_pe) - return -EEXIST; - - /* Freeze the (compound) PE */ - *pe = dev_pe; - if (!(dev_pe->state & EEH_PE_ISOLATED)) - phb->freeze_pe(phb, pe_no); - - /* - * At this point, we're sure the (compound) PE should - * have been frozen. However, we still need poke until - * hitting the frozen PE on top level. - */ - dev_pe = dev_pe->parent; - while (dev_pe && !(dev_pe->type & EEH_PE_PHB)) { - int ret; - int active_flags = (EEH_STATE_MMIO_ACTIVE | - EEH_STATE_DMA_ACTIVE); - - ret = eeh_ops->get_state(dev_pe, NULL); - if (ret <= 0 || (ret & active_flags) == active_flags) { - dev_pe = dev_pe->parent; - continue; - } - - /* Frozen parent PE */ - *pe = dev_pe; - if (!(dev_pe->state & EEH_PE_ISOLATED)) - phb->freeze_pe(phb, dev_pe->addr); - - /* Next one */ - dev_pe = dev_pe->parent; - } - - return 0; -} - -/** - * ioda_eeh_next_error - Retrieve next error for EEH core to handle - * @pe: The affected PE - * - * The function is expected to be called by EEH core while it gets - * special EEH event (without binding PE). The function calls to - * OPAL APIs for next error to handle. The informational error is - * handled internally by platform. However, the dead IOC, dead PHB, - * fenced PHB and frozen PE should be handled by EEH core eventually. - */ -static int ioda_eeh_next_error(struct eeh_pe **pe) -{ - struct pci_controller *hose; - struct pnv_phb *phb; - struct eeh_pe *phb_pe, *parent_pe; - __be64 frozen_pe_no; - __be16 err_type, severity; - int active_flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE); - long rc; - int state, ret = EEH_NEXT_ERR_NONE; - - /* - * While running here, it's safe to purge the event queue. - * And we should keep the cached OPAL notifier event sychronized - * between the kernel and firmware. - */ - eeh_remove_event(NULL, false); - opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul); - - list_for_each_entry(hose, &hose_list, list_node) { - /* - * If the subordinate PCI buses of the PHB has been - * removed or is exactly under error recovery, we - * needn't take care of it any more. - */ - phb = hose->private_data; - phb_pe = eeh_phb_pe_get(hose); - if (!phb_pe || (phb_pe->state & EEH_PE_ISOLATED)) - continue; - - rc = opal_pci_next_error(phb->opal_id, - &frozen_pe_no, &err_type, &severity); - - /* If OPAL API returns error, we needn't proceed */ - if (rc != OPAL_SUCCESS) { - pr_devel("%s: Invalid return value on " - "PHB#%x (0x%lx) from opal_pci_next_error", - __func__, hose->global_number, rc); - continue; - } - - /* If the PHB doesn't have error, stop processing */ - if (be16_to_cpu(err_type) == OPAL_EEH_NO_ERROR || - be16_to_cpu(severity) == OPAL_EEH_SEV_NO_ERROR) { - pr_devel("%s: No error found on PHB#%x\n", - __func__, hose->global_number); - continue; - } - - /* - * Processing the error. We're expecting the error with - * highest priority reported upon multiple errors on the - * specific PHB. - */ - pr_devel("%s: Error (%d, %d, %llu) on PHB#%x\n", - __func__, be16_to_cpu(err_type), be16_to_cpu(severity), - be64_to_cpu(frozen_pe_no), hose->global_number); - switch (be16_to_cpu(err_type)) { - case OPAL_EEH_IOC_ERROR: - if (be16_to_cpu(severity) == OPAL_EEH_SEV_IOC_DEAD) { - pr_err("EEH: dead IOC detected\n"); - ret = EEH_NEXT_ERR_DEAD_IOC; - } else if (be16_to_cpu(severity) == OPAL_EEH_SEV_INF) { - pr_info("EEH: IOC informative error " - "detected\n"); - ioda_eeh_hub_diag(hose); - ret = EEH_NEXT_ERR_NONE; - } - - break; - case OPAL_EEH_PHB_ERROR: - if (be16_to_cpu(severity) == OPAL_EEH_SEV_PHB_DEAD) { - *pe = phb_pe; - pr_err("EEH: dead PHB#%x detected, " - "location: %s\n", - hose->global_number, - eeh_pe_loc_get(phb_pe)); - ret = EEH_NEXT_ERR_DEAD_PHB; - } else if (be16_to_cpu(severity) == - OPAL_EEH_SEV_PHB_FENCED) { - *pe = phb_pe; - pr_err("EEH: Fenced PHB#%x detected, " - "location: %s\n", - hose->global_number, - eeh_pe_loc_get(phb_pe)); - ret = EEH_NEXT_ERR_FENCED_PHB; - } else if (be16_to_cpu(severity) == OPAL_EEH_SEV_INF) { - pr_info("EEH: PHB#%x informative error " - "detected, location: %s\n", - hose->global_number, - eeh_pe_loc_get(phb_pe)); - ioda_eeh_phb_diag(phb_pe); - pnv_pci_dump_phb_diag_data(hose, phb_pe->data); - ret = EEH_NEXT_ERR_NONE; - } - - break; - case OPAL_EEH_PE_ERROR: - /* - * If we can't find the corresponding PE, we - * just try to unfreeze. - */ - if (ioda_eeh_get_pe(hose, - be64_to_cpu(frozen_pe_no), pe)) { - /* Try best to clear it */ - pr_info("EEH: Clear non-existing PHB#%x-PE#%llx\n", - hose->global_number, frozen_pe_no); - pr_info("EEH: PHB location: %s\n", - eeh_pe_loc_get(phb_pe)); - opal_pci_eeh_freeze_clear(phb->opal_id, frozen_pe_no, - OPAL_EEH_ACTION_CLEAR_FREEZE_ALL); - ret = EEH_NEXT_ERR_NONE; - } else if ((*pe)->state & EEH_PE_ISOLATED || - eeh_pe_passed(*pe)) { - ret = EEH_NEXT_ERR_NONE; - } else { - pr_err("EEH: Frozen PE#%x on PHB#%x detected\n", - (*pe)->addr, (*pe)->phb->global_number); - pr_err("EEH: PE location: %s, PHB location: %s\n", - eeh_pe_loc_get(*pe), eeh_pe_loc_get(phb_pe)); - ret = EEH_NEXT_ERR_FROZEN_PE; - } - - break; - default: - pr_warn("%s: Unexpected error type %d\n", - __func__, be16_to_cpu(err_type)); - } - - /* - * EEH core will try recover from fenced PHB or - * frozen PE. In the time for frozen PE, EEH core - * enable IO path for that before collecting logs, - * but it ruins the site. So we have to dump the - * log in advance here. - */ - if ((ret == EEH_NEXT_ERR_FROZEN_PE || - ret == EEH_NEXT_ERR_FENCED_PHB) && - !((*pe)->state & EEH_PE_ISOLATED)) { - eeh_pe_state_mark(*pe, EEH_PE_ISOLATED); - ioda_eeh_phb_diag(*pe); - - if (eeh_has_flag(EEH_EARLY_DUMP_LOG)) - pnv_pci_dump_phb_diag_data((*pe)->phb, - (*pe)->data); - } - - /* - * We probably have the frozen parent PE out there and - * we need have to handle frozen parent PE firstly. - */ - if (ret == EEH_NEXT_ERR_FROZEN_PE) { - parent_pe = (*pe)->parent; - while (parent_pe) { - /* Hit the ceiling ? */ - if (parent_pe->type & EEH_PE_PHB) - break; - - /* Frozen parent PE ? */ - state = ioda_eeh_get_state(parent_pe); - if (state > 0 && - (state & active_flags) != active_flags) - *pe = parent_pe; - - /* Next parent level */ - parent_pe = parent_pe->parent; - } - - /* We possibly migrate to another PE */ - eeh_pe_state_mark(*pe, EEH_PE_ISOLATED); - } - - /* - * If we have no errors on the specific PHB or only - * informative error there, we continue poking it. - * Otherwise, we need actions to be taken by upper - * layer. - */ - if (ret > EEH_NEXT_ERR_INF) - break; - } - - return ret; -} - -struct pnv_eeh_ops ioda_eeh_ops = { - .post_init = ioda_eeh_post_init, - .set_option = ioda_eeh_set_option, - .get_state = ioda_eeh_get_state, - .reset = ioda_eeh_reset, - .get_log = ioda_eeh_get_log, - .configure_bridge = ioda_eeh_configure_bridge, - .err_inject = ioda_eeh_err_inject, - .next_error = ioda_eeh_next_error -}; diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index e261869adc86..ce738ab3d5a9 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -12,6 +12,7 @@ */ #include <linux/atomic.h> +#include <linux/debugfs.h> #include <linux/delay.h> #include <linux/export.h> #include <linux/init.h> @@ -38,12 +39,14 @@ #include "powernv.h" #include "pci.h" +static bool pnv_eeh_nb_init = false; + /** - * powernv_eeh_init - EEH platform dependent initialization + * pnv_eeh_init - EEH platform dependent initialization * * EEH platform dependent initialization on powernv */ -static int powernv_eeh_init(void) +static int pnv_eeh_init(void) { struct pci_controller *hose; struct pnv_phb *phb; @@ -85,37 +88,280 @@ static int powernv_eeh_init(void) return 0; } +static int pnv_eeh_event(struct notifier_block *nb, + unsigned long events, void *change) +{ + uint64_t changed_evts = (uint64_t)change; + + /* + * We simply send special EEH event if EEH has + * been enabled, or clear pending events in + * case that we enable EEH soon + */ + if (!(changed_evts & OPAL_EVENT_PCI_ERROR) || + !(events & OPAL_EVENT_PCI_ERROR)) + return 0; + + if (eeh_enabled()) + eeh_send_failure_event(NULL); + else + opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul); + + return 0; +} + +static struct notifier_block pnv_eeh_nb = { + .notifier_call = pnv_eeh_event, + .next = NULL, + .priority = 0 +}; + +#ifdef CONFIG_DEBUG_FS +static ssize_t pnv_eeh_ei_write(struct file *filp, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct pci_controller *hose = filp->private_data; + struct eeh_dev *edev; + struct eeh_pe *pe; + int pe_no, type, func; + unsigned long addr, mask; + char buf[50]; + int ret; + + if (!eeh_ops || !eeh_ops->err_inject) + return -ENXIO; + + /* Copy over argument buffer */ + ret = simple_write_to_buffer(buf, sizeof(buf), ppos, user_buf, count); + if (!ret) + return -EFAULT; + + /* Retrieve parameters */ + ret = sscanf(buf, "%x:%x:%x:%lx:%lx", + &pe_no, &type, &func, &addr, &mask); + if (ret != 5) + return -EINVAL; + + /* Retrieve PE */ + edev = kzalloc(sizeof(*edev), GFP_KERNEL); + if (!edev) + return -ENOMEM; + edev->phb = hose; + edev->pe_config_addr = pe_no; + pe = eeh_pe_get(edev); + kfree(edev); + if (!pe) + return -ENODEV; + + /* Do error injection */ + ret = eeh_ops->err_inject(pe, type, func, addr, mask); + return ret < 0 ? ret : count; +} + +static const struct file_operations pnv_eeh_ei_fops = { + .open = simple_open, + .llseek = no_llseek, + .write = pnv_eeh_ei_write, +}; + +static int pnv_eeh_dbgfs_set(void *data, int offset, u64 val) +{ + struct pci_controller *hose = data; + struct pnv_phb *phb = hose->private_data; + + out_be64(phb->regs + offset, val); + return 0; +} + +static int pnv_eeh_dbgfs_get(void *data, int offset, u64 *val) +{ + struct pci_controller *hose = data; + struct pnv_phb *phb = hose->private_data; + + *val = in_be64(phb->regs + offset); + return 0; +} + +static int pnv_eeh_outb_dbgfs_set(void *data, u64 val) +{ + return pnv_eeh_dbgfs_set(data, 0xD10, val); +} + +static int pnv_eeh_outb_dbgfs_get(void *data, u64 *val) +{ + return pnv_eeh_dbgfs_get(data, 0xD10, val); +} + +static int pnv_eeh_inbA_dbgfs_set(void *data, u64 val) +{ + return pnv_eeh_dbgfs_set(data, 0xD90, val); +} + +static int pnv_eeh_inbA_dbgfs_get(void *data, u64 *val) +{ + return pnv_eeh_dbgfs_get(data, 0xD90, val); +} + +static int pnv_eeh_inbB_dbgfs_set(void *data, u64 val) +{ + return pnv_eeh_dbgfs_set(data, 0xE10, val); +} + +static int pnv_eeh_inbB_dbgfs_get(void *data, u64 *val) +{ + return pnv_eeh_dbgfs_get(data, 0xE10, val); +} + +DEFINE_SIMPLE_ATTRIBUTE(pnv_eeh_outb_dbgfs_ops, pnv_eeh_outb_dbgfs_get, + pnv_eeh_outb_dbgfs_set, "0x%llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(pnv_eeh_inbA_dbgfs_ops, pnv_eeh_inbA_dbgfs_get, + pnv_eeh_inbA_dbgfs_set, "0x%llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(pnv_eeh_inbB_dbgfs_ops, pnv_eeh_inbB_dbgfs_get, + pnv_eeh_inbB_dbgfs_set, "0x%llx\n"); +#endif /* CONFIG_DEBUG_FS */ + /** - * powernv_eeh_post_init - EEH platform dependent post initialization + * pnv_eeh_post_init - EEH platform dependent post initialization * * EEH platform dependent post initialization on powernv. When * the function is called, the EEH PEs and devices should have * been built. If the I/O cache staff has been built, EEH is * ready to supply service. */ -static int powernv_eeh_post_init(void) +static int pnv_eeh_post_init(void) { struct pci_controller *hose; struct pnv_phb *phb; int ret = 0; + /* Register OPAL event notifier */ + if (!pnv_eeh_nb_init) { + ret = opal_notifier_register(&pnv_eeh_nb); + if (ret) { + pr_warn("%s: Can't register OPAL event notifier (%d)\n", + __func__, ret); + return ret; + } + + pnv_eeh_nb_init = true; + } + list_for_each_entry(hose, &hose_list, list_node) { phb = hose->private_data; - if (phb->eeh_ops && phb->eeh_ops->post_init) { - ret = phb->eeh_ops->post_init(hose); - if (ret) - break; - } + /* + * If EEH is enabled, we're going to rely on that. + * Otherwise, we restore to conventional mechanism + * to clear frozen PE during PCI config access. + */ + if (eeh_enabled()) + phb->flags |= PNV_PHB_FLAG_EEH; + else + phb->flags &= ~PNV_PHB_FLAG_EEH; + + /* Create debugfs entries */ +#ifdef CONFIG_DEBUG_FS + if (phb->has_dbgfs || !phb->dbgfs) + continue; + + phb->has_dbgfs = 1; + debugfs_create_file("err_injct", 0200, + phb->dbgfs, hose, + &pnv_eeh_ei_fops); + + debugfs_create_file("err_injct_outbound", 0600, + phb->dbgfs, hose, + &pnv_eeh_outb_dbgfs_ops); + debugfs_create_file("err_injct_inboundA", 0600, + phb->dbgfs, hose, + &pnv_eeh_inbA_dbgfs_ops); + debugfs_create_file("err_injct_inboundB", 0600, + phb->dbgfs, hose, + &pnv_eeh_inbB_dbgfs_ops); +#endif /* CONFIG_DEBUG_FS */ } + return ret; } +static int pnv_eeh_cap_start(struct pci_dn *pdn) +{ + u32 status; + + if (!pdn) + return 0; + + pnv_pci_cfg_read(pdn, PCI_STATUS, 2, &status); + if (!(status & PCI_STATUS_CAP_LIST)) + return 0; + + return PCI_CAPABILITY_LIST; +} + +static int pnv_eeh_find_cap(struct pci_dn *pdn, int cap) +{ + int pos = pnv_eeh_cap_start(pdn); + int cnt = 48; /* Maximal number of capabilities */ + u32 id; + + if (!pos) + return 0; + + while (cnt--) { + pnv_pci_cfg_read(pdn, pos, 1, &pos); + if (pos < 0x40) + break; + + pos &= ~3; + pnv_pci_cfg_read(pdn, pos + PCI_CAP_LIST_ID, 1, &id); + if (id == 0xff) + break; + + /* Found */ + if (id == cap) + return pos; + + /* Next one */ + pos += PCI_CAP_LIST_NEXT; + } + + return 0; +} + +static int pnv_eeh_find_ecap(struct pci_dn *pdn, int cap) +{ + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); + u32 header; + int pos = 256, ttl = (4096 - 256) / 8; + + if (!edev || !edev->pcie_cap) + return 0; + if (pnv_pci_cfg_read(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL) + return 0; + else if (!header) + return 0; + + while (ttl-- > 0) { + if (PCI_EXT_CAP_ID(header) == cap && pos) + return pos; + + pos = PCI_EXT_CAP_NEXT(header); + if (pos < 256) + break; + + if (pnv_pci_cfg_read(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL) + break; + } + + return 0; +} + /** - * powernv_eeh_dev_probe - Do probe on PCI device - * @dev: PCI device - * @flag: unused + * pnv_eeh_probe - Do probe on PCI device + * @pdn: PCI device node + * @data: unused * * When EEH module is installed during system boot, all PCI devices * are checked one by one to see if it supports EEH. The function @@ -129,12 +375,12 @@ static int powernv_eeh_post_init(void) * was possiblly triggered by EEH core, the binding between EEH device * and the PCI device isn't built yet. */ -static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) +static void *pnv_eeh_probe(struct pci_dn *pdn, void *data) { - struct pci_controller *hose = pci_bus_to_host(dev->bus); + struct pci_controller *hose = pdn->phb; struct pnv_phb *phb = hose->private_data; - struct device_node *dn = pci_device_to_OF_node(dev); - struct eeh_dev *edev = of_node_to_eeh_dev(dn); + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); + uint32_t pcie_flags; int ret; /* @@ -143,40 +389,42 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) * the root bridge. So it's not reasonable to continue * the probing. */ - if (!dn || !edev || edev->pe) - return 0; + if (!edev || edev->pe) + return NULL; /* Skip for PCI-ISA bridge */ - if ((dev->class >> 8) == PCI_CLASS_BRIDGE_ISA) - return 0; + if ((pdn->class_code >> 8) == PCI_CLASS_BRIDGE_ISA) + return NULL; /* Initialize eeh device */ - edev->class_code = dev->class; + edev->class_code = pdn->class_code; edev->mode &= 0xFFFFFF00; - if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) + edev->pcix_cap = pnv_eeh_find_cap(pdn, PCI_CAP_ID_PCIX); + edev->pcie_cap = pnv_eeh_find_cap(pdn, PCI_CAP_ID_EXP); + edev->aer_cap = pnv_eeh_find_ecap(pdn, PCI_EXT_CAP_ID_ERR); + if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) { edev->mode |= EEH_DEV_BRIDGE; - edev->pcix_cap = pci_find_capability(dev, PCI_CAP_ID_PCIX); - if (pci_is_pcie(dev)) { - edev->pcie_cap = pci_pcie_cap(dev); - - if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) - edev->mode |= EEH_DEV_ROOT_PORT; - else if (pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM) - edev->mode |= EEH_DEV_DS_PORT; - - edev->aer_cap = pci_find_ext_capability(dev, - PCI_EXT_CAP_ID_ERR); + if (edev->pcie_cap) { + pnv_pci_cfg_read(pdn, edev->pcie_cap + PCI_EXP_FLAGS, + 2, &pcie_flags); + pcie_flags = (pcie_flags & PCI_EXP_FLAGS_TYPE) >> 4; + if (pcie_flags == PCI_EXP_TYPE_ROOT_PORT) + edev->mode |= EEH_DEV_ROOT_PORT; + else if (pcie_flags == PCI_EXP_TYPE_DOWNSTREAM) + edev->mode |= EEH_DEV_DS_PORT; + } } - edev->config_addr = ((dev->bus->number << 8) | dev->devfn); - edev->pe_config_addr = phb->bdfn_to_pe(phb, dev->bus, dev->devfn & 0xff); + edev->config_addr = (pdn->busno << 8) | (pdn->devfn); + edev->pe_config_addr = phb->ioda.pe_rmap[edev->config_addr]; /* Create PE */ ret = eeh_add_to_parent_pe(edev); if (ret) { - pr_warn("%s: Can't add PCI dev %s to parent PE (%d)\n", - __func__, pci_name(dev), ret); - return ret; + pr_warn("%s: Can't add PCI dev %04x:%02x:%02x.%01x to parent PE (%d)\n", + __func__, hose->global_number, pdn->busno, + PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn), ret); + return NULL; } /* @@ -195,8 +443,10 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) * Broadcom Austin 4-ports NICs (14e4:1657) * Broadcom Shiner 2-ports 10G NICs (14e4:168e) */ - if ((dev->vendor == PCI_VENDOR_ID_BROADCOM && dev->device == 0x1657) || - (dev->vendor == PCI_VENDOR_ID_BROADCOM && dev->device == 0x168e)) + if ((pdn->vendor_id == PCI_VENDOR_ID_BROADCOM && + pdn->device_id == 0x1657) || + (pdn->vendor_id == PCI_VENDOR_ID_BROADCOM && + pdn->device_id == 0x168e)) edev->pe->state |= EEH_PE_CFG_RESTRICTED; /* @@ -206,7 +456,8 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) * to PE reset. */ if (!edev->pe->bus) - edev->pe->bus = dev->bus; + edev->pe->bus = pci_find_bus(hose->global_number, + pdn->busno); /* * Enable EEH explicitly so that we will do EEH check @@ -217,11 +468,11 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) /* Save memory bars */ eeh_save_bars(edev); - return 0; + return NULL; } /** - * powernv_eeh_set_option - Initialize EEH or MMIO/DMA reenable + * pnv_eeh_set_option - Initialize EEH or MMIO/DMA reenable * @pe: EEH PE * @option: operation to be issued * @@ -229,36 +480,236 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) * Currently, following options are support according to PAPR: * Enable EEH, Disable EEH, Enable MMIO and Enable DMA */ -static int powernv_eeh_set_option(struct eeh_pe *pe, int option) +static int pnv_eeh_set_option(struct eeh_pe *pe, int option) { struct pci_controller *hose = pe->phb; struct pnv_phb *phb = hose->private_data; - int ret = -EEXIST; + bool freeze_pe = false; + int opt, ret = 0; + s64 rc; + + /* Sanity check on option */ + switch (option) { + case EEH_OPT_DISABLE: + return -EPERM; + case EEH_OPT_ENABLE: + return 0; + case EEH_OPT_THAW_MMIO: + opt = OPAL_EEH_ACTION_CLEAR_FREEZE_MMIO; + break; + case EEH_OPT_THAW_DMA: + opt = OPAL_EEH_ACTION_CLEAR_FREEZE_DMA; + break; + case EEH_OPT_FREEZE_PE: + freeze_pe = true; + opt = OPAL_EEH_ACTION_SET_FREEZE_ALL; + break; + default: + pr_warn("%s: Invalid option %d\n", __func__, option); + return -EINVAL; + } - /* - * What we need do is pass it down for hardware - * implementation to handle it. - */ - if (phb->eeh_ops && phb->eeh_ops->set_option) - ret = phb->eeh_ops->set_option(pe, option); + /* If PHB supports compound PE, to handle it */ + if (freeze_pe) { + if (phb->freeze_pe) { + phb->freeze_pe(phb, pe->addr); + } else { + rc = opal_pci_eeh_freeze_set(phb->opal_id, + pe->addr, opt); + if (rc != OPAL_SUCCESS) { + pr_warn("%s: Failure %lld freezing " + "PHB#%x-PE#%x\n", + __func__, rc, + phb->hose->global_number, pe->addr); + ret = -EIO; + } + } + } else { + if (phb->unfreeze_pe) { + ret = phb->unfreeze_pe(phb, pe->addr, opt); + } else { + rc = opal_pci_eeh_freeze_clear(phb->opal_id, + pe->addr, opt); + if (rc != OPAL_SUCCESS) { + pr_warn("%s: Failure %lld enable %d " + "for PHB#%x-PE#%x\n", + __func__, rc, option, + phb->hose->global_number, pe->addr); + ret = -EIO; + } + } + } return ret; } /** - * powernv_eeh_get_pe_addr - Retrieve PE address + * pnv_eeh_get_pe_addr - Retrieve PE address * @pe: EEH PE * * Retrieve the PE address according to the given tranditional * PCI BDF (Bus/Device/Function) address. */ -static int powernv_eeh_get_pe_addr(struct eeh_pe *pe) +static int pnv_eeh_get_pe_addr(struct eeh_pe *pe) { return pe->addr; } +static void pnv_eeh_get_phb_diag(struct eeh_pe *pe) +{ + struct pnv_phb *phb = pe->phb->private_data; + s64 rc; + + rc = opal_pci_get_phb_diag_data2(phb->opal_id, pe->data, + PNV_PCI_DIAG_BUF_SIZE); + if (rc != OPAL_SUCCESS) + pr_warn("%s: Failure %lld getting PHB#%x diag-data\n", + __func__, rc, pe->phb->global_number); +} + +static int pnv_eeh_get_phb_state(struct eeh_pe *pe) +{ + struct pnv_phb *phb = pe->phb->private_data; + u8 fstate; + __be16 pcierr; + s64 rc; + int result = 0; + + rc = opal_pci_eeh_freeze_status(phb->opal_id, + pe->addr, + &fstate, + &pcierr, + NULL); + if (rc != OPAL_SUCCESS) { + pr_warn("%s: Failure %lld getting PHB#%x state\n", + __func__, rc, phb->hose->global_number); + return EEH_STATE_NOT_SUPPORT; + } + + /* + * Check PHB state. If the PHB is frozen for the + * first time, to dump the PHB diag-data. + */ + if (be16_to_cpu(pcierr) != OPAL_EEH_PHB_ERROR) { + result = (EEH_STATE_MMIO_ACTIVE | + EEH_STATE_DMA_ACTIVE | + EEH_STATE_MMIO_ENABLED | + EEH_STATE_DMA_ENABLED); + } else if (!(pe->state & EEH_PE_ISOLATED)) { + eeh_pe_state_mark(pe, EEH_PE_ISOLATED); + pnv_eeh_get_phb_diag(pe); + + if (eeh_has_flag(EEH_EARLY_DUMP_LOG)) + pnv_pci_dump_phb_diag_data(pe->phb, pe->data); + } + + return result; +} + +static int pnv_eeh_get_pe_state(struct eeh_pe *pe) +{ + struct pnv_phb *phb = pe->phb->private_data; + u8 fstate; + __be16 pcierr; + s64 rc; + int result; + + /* + * We don't clobber hardware frozen state until PE + * reset is completed. In order to keep EEH core + * moving forward, we have to return operational + * state during PE reset. + */ + if (pe->state & EEH_PE_RESET) { + result = (EEH_STATE_MMIO_ACTIVE | + EEH_STATE_DMA_ACTIVE | + EEH_STATE_MMIO_ENABLED | + EEH_STATE_DMA_ENABLED); + return result; + } + + /* + * Fetch PE state from hardware. If the PHB + * supports compound PE, let it handle that. + */ + if (phb->get_pe_state) { + fstate = phb->get_pe_state(phb, pe->addr); + } else { + rc = opal_pci_eeh_freeze_status(phb->opal_id, + pe->addr, + &fstate, + &pcierr, + NULL); + if (rc != OPAL_SUCCESS) { + pr_warn("%s: Failure %lld getting PHB#%x-PE%x state\n", + __func__, rc, phb->hose->global_number, + pe->addr); + return EEH_STATE_NOT_SUPPORT; + } + } + + /* Figure out state */ + switch (fstate) { + case OPAL_EEH_STOPPED_NOT_FROZEN: + result = (EEH_STATE_MMIO_ACTIVE | + EEH_STATE_DMA_ACTIVE | + EEH_STATE_MMIO_ENABLED | + EEH_STATE_DMA_ENABLED); + break; + case OPAL_EEH_STOPPED_MMIO_FREEZE: + result = (EEH_STATE_DMA_ACTIVE | + EEH_STATE_DMA_ENABLED); + break; + case OPAL_EEH_STOPPED_DMA_FREEZE: + result = (EEH_STATE_MMIO_ACTIVE | + EEH_STATE_MMIO_ENABLED); + break; + case OPAL_EEH_STOPPED_MMIO_DMA_FREEZE: + result = 0; + break; + case OPAL_EEH_STOPPED_RESET: + result = EEH_STATE_RESET_ACTIVE; + break; + case OPAL_EEH_STOPPED_TEMP_UNAVAIL: + result = EEH_STATE_UNAVAILABLE; + break; + case OPAL_EEH_STOPPED_PERM_UNAVAIL: + result = EEH_STATE_NOT_SUPPORT; + break; + default: + result = EEH_STATE_NOT_SUPPORT; + pr_warn("%s: Invalid PHB#%x-PE#%x state %x\n", + __func__, phb->hose->global_number, + pe->addr, fstate); + } + + /* + * If PHB supports compound PE, to freeze all + * slave PEs for consistency. + * + * If the PE is switching to frozen state for the + * first time, to dump the PHB diag-data. + */ + if (!(result & EEH_STATE_NOT_SUPPORT) && + !(result & EEH_STATE_UNAVAILABLE) && + !(result & EEH_STATE_MMIO_ACTIVE) && + !(result & EEH_STATE_DMA_ACTIVE) && + !(pe->state & EEH_PE_ISOLATED)) { + if (phb->freeze_pe) + phb->freeze_pe(phb, pe->addr); + + eeh_pe_state_mark(pe, EEH_PE_ISOLATED); + pnv_eeh_get_phb_diag(pe); + + if (eeh_has_flag(EEH_EARLY_DUMP_LOG)) + pnv_pci_dump_phb_diag_data(pe->phb, pe->data); + } + + return result; +} + /** - * powernv_eeh_get_state - Retrieve PE state + * pnv_eeh_get_state - Retrieve PE state * @pe: EEH PE * @delay: delay while PE state is temporarily unavailable * @@ -267,64 +718,279 @@ static int powernv_eeh_get_pe_addr(struct eeh_pe *pe) * we prefer passing down to hardware implementation to handle * it. */ -static int powernv_eeh_get_state(struct eeh_pe *pe, int *delay) +static int pnv_eeh_get_state(struct eeh_pe *pe, int *delay) +{ + int ret; + + if (pe->type & EEH_PE_PHB) + ret = pnv_eeh_get_phb_state(pe); + else + ret = pnv_eeh_get_pe_state(pe); + + if (!delay) + return ret; + + /* + * If the PE state is temporarily unavailable, + * to inform the EEH core delay for default + * period (1 second) + */ + *delay = 0; + if (ret & EEH_STATE_UNAVAILABLE) + *delay = 1000; + + return ret; +} + +static s64 pnv_eeh_phb_poll(struct pnv_phb *phb) +{ + s64 rc = OPAL_HARDWARE; + + while (1) { + rc = opal_pci_poll(phb->opal_id); + if (rc <= 0) + break; + + if (system_state < SYSTEM_RUNNING) + udelay(1000 * rc); + else + msleep(rc); + } + + return rc; +} + +int pnv_eeh_phb_reset(struct pci_controller *hose, int option) { - struct pci_controller *hose = pe->phb; struct pnv_phb *phb = hose->private_data; - int ret = EEH_STATE_NOT_SUPPORT; + s64 rc = OPAL_HARDWARE; + + pr_debug("%s: Reset PHB#%x, option=%d\n", + __func__, hose->global_number, option); + + /* Issue PHB complete reset request */ + if (option == EEH_RESET_FUNDAMENTAL || + option == EEH_RESET_HOT) + rc = opal_pci_reset(phb->opal_id, + OPAL_RESET_PHB_COMPLETE, + OPAL_ASSERT_RESET); + else if (option == EEH_RESET_DEACTIVATE) + rc = opal_pci_reset(phb->opal_id, + OPAL_RESET_PHB_COMPLETE, + OPAL_DEASSERT_RESET); + if (rc < 0) + goto out; - if (phb->eeh_ops && phb->eeh_ops->get_state) { - ret = phb->eeh_ops->get_state(pe); + /* + * Poll state of the PHB until the request is done + * successfully. The PHB reset is usually PHB complete + * reset followed by hot reset on root bus. So we also + * need the PCI bus settlement delay. + */ + rc = pnv_eeh_phb_poll(phb); + if (option == EEH_RESET_DEACTIVATE) { + if (system_state < SYSTEM_RUNNING) + udelay(1000 * EEH_PE_RST_SETTLE_TIME); + else + msleep(EEH_PE_RST_SETTLE_TIME); + } +out: + if (rc != OPAL_SUCCESS) + return -EIO; - /* - * If the PE state is temporarily unavailable, - * to inform the EEH core delay for default - * period (1 second) - */ - if (delay) { - *delay = 0; - if (ret & EEH_STATE_UNAVAILABLE) - *delay = 1000; + return 0; +} + +static int pnv_eeh_root_reset(struct pci_controller *hose, int option) +{ + struct pnv_phb *phb = hose->private_data; + s64 rc = OPAL_HARDWARE; + + pr_debug("%s: Reset PHB#%x, option=%d\n", + __func__, hose->global_number, option); + + /* + * During the reset deassert time, we needn't care + * the reset scope because the firmware does nothing + * for fundamental or hot reset during deassert phase. + */ + if (option == EEH_RESET_FUNDAMENTAL) + rc = opal_pci_reset(phb->opal_id, + OPAL_RESET_PCI_FUNDAMENTAL, + OPAL_ASSERT_RESET); + else if (option == EEH_RESET_HOT) + rc = opal_pci_reset(phb->opal_id, + OPAL_RESET_PCI_HOT, + OPAL_ASSERT_RESET); + else if (option == EEH_RESET_DEACTIVATE) + rc = opal_pci_reset(phb->opal_id, + OPAL_RESET_PCI_HOT, + OPAL_DEASSERT_RESET); + if (rc < 0) + goto out; + + /* Poll state of the PHB until the request is done */ + rc = pnv_eeh_phb_poll(phb); + if (option == EEH_RESET_DEACTIVATE) + msleep(EEH_PE_RST_SETTLE_TIME); +out: + if (rc != OPAL_SUCCESS) + return -EIO; + + return 0; +} + +static int pnv_eeh_bridge_reset(struct pci_dev *dev, int option) +{ + struct pci_dn *pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn); + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); + int aer = edev ? edev->aer_cap : 0; + u32 ctrl; + + pr_debug("%s: Reset PCI bus %04x:%02x with option %d\n", + __func__, pci_domain_nr(dev->bus), + dev->bus->number, option); + + switch (option) { + case EEH_RESET_FUNDAMENTAL: + case EEH_RESET_HOT: + /* Don't report linkDown event */ + if (aer) { + eeh_ops->read_config(pdn, aer + PCI_ERR_UNCOR_MASK, + 4, &ctrl); + ctrl |= PCI_ERR_UNC_SURPDN; + eeh_ops->write_config(pdn, aer + PCI_ERR_UNCOR_MASK, + 4, ctrl); } + + eeh_ops->read_config(pdn, PCI_BRIDGE_CONTROL, 2, &ctrl); + ctrl |= PCI_BRIDGE_CTL_BUS_RESET; + eeh_ops->write_config(pdn, PCI_BRIDGE_CONTROL, 2, ctrl); + + msleep(EEH_PE_RST_HOLD_TIME); + break; + case EEH_RESET_DEACTIVATE: + eeh_ops->read_config(pdn, PCI_BRIDGE_CONTROL, 2, &ctrl); + ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET; + eeh_ops->write_config(pdn, PCI_BRIDGE_CONTROL, 2, ctrl); + + msleep(EEH_PE_RST_SETTLE_TIME); + + /* Continue reporting linkDown event */ + if (aer) { + eeh_ops->read_config(pdn, aer + PCI_ERR_UNCOR_MASK, + 4, &ctrl); + ctrl &= ~PCI_ERR_UNC_SURPDN; + eeh_ops->write_config(pdn, aer + PCI_ERR_UNCOR_MASK, + 4, ctrl); + } + + break; } - return ret; + return 0; +} + +void pnv_pci_reset_secondary_bus(struct pci_dev *dev) +{ + struct pci_controller *hose; + + if (pci_is_root_bus(dev->bus)) { + hose = pci_bus_to_host(dev->bus); + pnv_eeh_root_reset(hose, EEH_RESET_HOT); + pnv_eeh_root_reset(hose, EEH_RESET_DEACTIVATE); + } else { + pnv_eeh_bridge_reset(dev, EEH_RESET_HOT); + pnv_eeh_bridge_reset(dev, EEH_RESET_DEACTIVATE); + } } /** - * powernv_eeh_reset - Reset the specified PE + * pnv_eeh_reset - Reset the specified PE * @pe: EEH PE * @option: reset option * - * Reset the specified PE + * Do reset on the indicated PE. For PCI bus sensitive PE, + * we need to reset the parent p2p bridge. The PHB has to + * be reinitialized if the p2p bridge is root bridge. For + * PCI device sensitive PE, we will try to reset the device + * through FLR. For now, we don't have OPAL APIs to do HARD + * reset yet, so all reset would be SOFT (HOT) reset. */ -static int powernv_eeh_reset(struct eeh_pe *pe, int option) +static int pnv_eeh_reset(struct eeh_pe *pe, int option) { struct pci_controller *hose = pe->phb; - struct pnv_phb *phb = hose->private_data; - int ret = -EEXIST; + struct pci_bus *bus; + int ret; + + /* + * For PHB reset, we always have complete reset. For those PEs whose + * primary bus derived from root complex (root bus) or root port + * (usually bus#1), we apply hot or fundamental reset on the root port. + * For other PEs, we always have hot reset on the PE primary bus. + * + * Here, we have different design to pHyp, which always clear the + * frozen state during PE reset. However, the good idea here from + * benh is to keep frozen state before we get PE reset done completely + * (until BAR restore). With the frozen state, HW drops illegal IO + * or MMIO access, which can incur recrusive frozen PE during PE + * reset. The side effect is that EEH core has to clear the frozen + * state explicitly after BAR restore. + */ + if (pe->type & EEH_PE_PHB) { + ret = pnv_eeh_phb_reset(hose, option); + } else { + struct pnv_phb *phb; + s64 rc; - if (phb->eeh_ops && phb->eeh_ops->reset) - ret = phb->eeh_ops->reset(pe, option); + /* + * The frozen PE might be caused by PAPR error injection + * registers, which are expected to be cleared after hitting + * frozen PE as stated in the hardware spec. Unfortunately, + * that's not true on P7IOC. So we have to clear it manually + * to avoid recursive EEH errors during recovery. + */ + phb = hose->private_data; + if (phb->model == PNV_PHB_MODEL_P7IOC && + (option == EEH_RESET_HOT || + option == EEH_RESET_FUNDAMENTAL)) { + rc = opal_pci_reset(phb->opal_id, + OPAL_RESET_PHB_ERROR, + OPAL_ASSERT_RESET); + if (rc != OPAL_SUCCESS) { + pr_warn("%s: Failure %lld clearing " + "error injection registers\n", + __func__, rc); + return -EIO; + } + } + + bus = eeh_pe_bus_get(pe); + if (pci_is_root_bus(bus) || + pci_is_root_bus(bus->parent)) + ret = pnv_eeh_root_reset(hose, option); + else + ret = pnv_eeh_bridge_reset(bus->self, option); + } return ret; } /** - * powernv_eeh_wait_state - Wait for PE state + * pnv_eeh_wait_state - Wait for PE state * @pe: EEH PE * @max_wait: maximal period in microsecond * * Wait for the state of associated PE. It might take some time * to retrieve the PE's state. */ -static int powernv_eeh_wait_state(struct eeh_pe *pe, int max_wait) +static int pnv_eeh_wait_state(struct eeh_pe *pe, int max_wait) { int ret; int mwait; while (1) { - ret = powernv_eeh_get_state(pe, &mwait); + ret = pnv_eeh_get_state(pe, &mwait); /* * If the PE's state is temporarily unavailable, @@ -348,7 +1014,7 @@ static int powernv_eeh_wait_state(struct eeh_pe *pe, int max_wait) } /** - * powernv_eeh_get_log - Retrieve error log + * pnv_eeh_get_log - Retrieve error log * @pe: EEH PE * @severity: temporary or permanent error log * @drv_log: driver log to be combined with retrieved error log @@ -356,41 +1022,30 @@ static int powernv_eeh_wait_state(struct eeh_pe *pe, int max_wait) * * Retrieve the temporary or permanent error from the PE. */ -static int powernv_eeh_get_log(struct eeh_pe *pe, int severity, - char *drv_log, unsigned long len) +static int pnv_eeh_get_log(struct eeh_pe *pe, int severity, + char *drv_log, unsigned long len) { - struct pci_controller *hose = pe->phb; - struct pnv_phb *phb = hose->private_data; - int ret = -EEXIST; + if (!eeh_has_flag(EEH_EARLY_DUMP_LOG)) + pnv_pci_dump_phb_diag_data(pe->phb, pe->data); - if (phb->eeh_ops && phb->eeh_ops->get_log) - ret = phb->eeh_ops->get_log(pe, severity, drv_log, len); - - return ret; + return 0; } /** - * powernv_eeh_configure_bridge - Configure PCI bridges in the indicated PE + * pnv_eeh_configure_bridge - Configure PCI bridges in the indicated PE * @pe: EEH PE * * The function will be called to reconfigure the bridges included * in the specified PE so that the mulfunctional PE would be recovered * again. */ -static int powernv_eeh_configure_bridge(struct eeh_pe *pe) +static int pnv_eeh_configure_bridge(struct eeh_pe *pe) { - struct pci_controller *hose = pe->phb; - struct pnv_phb *phb = hose->private_data; - int ret = 0; - - if (phb->eeh_ops && phb->eeh_ops->configure_bridge) - ret = phb->eeh_ops->configure_bridge(pe); - - return ret; + return 0; } /** - * powernv_pe_err_inject - Inject specified error to the indicated PE + * pnv_pe_err_inject - Inject specified error to the indicated PE * @pe: the indicated PE * @type: error type * @func: specific error type @@ -401,22 +1056,52 @@ static int powernv_eeh_configure_bridge(struct eeh_pe *pe) * determined by @type and @func, to the indicated PE for * testing purpose. */ -static int powernv_eeh_err_inject(struct eeh_pe *pe, int type, int func, - unsigned long addr, unsigned long mask) +static int pnv_eeh_err_inject(struct eeh_pe *pe, int type, int func, + unsigned long addr, unsigned long mask) { struct pci_controller *hose = pe->phb; struct pnv_phb *phb = hose->private_data; - int ret = -EEXIST; + s64 rc; + + /* Sanity check on error type */ + if (type != OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR && + type != OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR64) { + pr_warn("%s: Invalid error type %d\n", + __func__, type); + return -ERANGE; + } - if (phb->eeh_ops && phb->eeh_ops->err_inject) - ret = phb->eeh_ops->err_inject(pe, type, func, addr, mask); + if (func < OPAL_ERR_INJECT_FUNC_IOA_LD_MEM_ADDR || + func > OPAL_ERR_INJECT_FUNC_IOA_DMA_WR_TARGET) { + pr_warn("%s: Invalid error function %d\n", + __func__, func); + return -ERANGE; + } - return ret; + /* Firmware supports error injection ? */ + if (!opal_check_token(OPAL_PCI_ERR_INJECT)) { + pr_warn("%s: Firmware doesn't support error injection\n", + __func__); + return -ENXIO; + } + + /* Do error injection */ + rc = opal_pci_err_inject(phb->opal_id, pe->addr, + type, func, addr, mask); + if (rc != OPAL_SUCCESS) { + pr_warn("%s: Failure %lld injecting error " + "%d-%d to PHB#%x-PE#%x\n", + __func__, rc, type, func, + hose->global_number, pe->addr); + return -EIO; + } + + return 0; } -static inline bool powernv_eeh_cfg_blocked(struct device_node *dn) +static inline bool pnv_eeh_cfg_blocked(struct pci_dn *pdn) { - struct eeh_dev *edev = of_node_to_eeh_dev(dn); + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); if (!edev || !edev->pe) return false; @@ -427,51 +1112,377 @@ static inline bool powernv_eeh_cfg_blocked(struct device_node *dn) return false; } -static int powernv_eeh_read_config(struct device_node *dn, - int where, int size, u32 *val) +static int pnv_eeh_read_config(struct pci_dn *pdn, + int where, int size, u32 *val) { - if (powernv_eeh_cfg_blocked(dn)) { + if (!pdn) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (pnv_eeh_cfg_blocked(pdn)) { *val = 0xFFFFFFFF; return PCIBIOS_SET_FAILED; } - return pnv_pci_cfg_read(dn, where, size, val); + return pnv_pci_cfg_read(pdn, where, size, val); } -static int powernv_eeh_write_config(struct device_node *dn, - int where, int size, u32 val) +static int pnv_eeh_write_config(struct pci_dn *pdn, + int where, int size, u32 val) { - if (powernv_eeh_cfg_blocked(dn)) + if (!pdn) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (pnv_eeh_cfg_blocked(pdn)) return PCIBIOS_SET_FAILED; - return pnv_pci_cfg_write(dn, where, size, val); + return pnv_pci_cfg_write(pdn, where, size, val); +} + +static void pnv_eeh_dump_hub_diag_common(struct OpalIoP7IOCErrorData *data) +{ + /* GEM */ + if (data->gemXfir || data->gemRfir || + data->gemRirqfir || data->gemMask || data->gemRwof) + pr_info(" GEM: %016llx %016llx %016llx %016llx %016llx\n", + be64_to_cpu(data->gemXfir), + be64_to_cpu(data->gemRfir), + be64_to_cpu(data->gemRirqfir), + be64_to_cpu(data->gemMask), + be64_to_cpu(data->gemRwof)); + + /* LEM */ + if (data->lemFir || data->lemErrMask || + data->lemAction0 || data->lemAction1 || data->lemWof) + pr_info(" LEM: %016llx %016llx %016llx %016llx %016llx\n", + be64_to_cpu(data->lemFir), + be64_to_cpu(data->lemErrMask), + be64_to_cpu(data->lemAction0), + be64_to_cpu(data->lemAction1), + be64_to_cpu(data->lemWof)); +} + +static void pnv_eeh_get_and_dump_hub_diag(struct pci_controller *hose) +{ + struct pnv_phb *phb = hose->private_data; + struct OpalIoP7IOCErrorData *data = &phb->diag.hub_diag; + long rc; + + rc = opal_pci_get_hub_diag_data(phb->hub_id, data, sizeof(*data)); + if (rc != OPAL_SUCCESS) { + pr_warn("%s: Failed to get HUB#%llx diag-data (%ld)\n", + __func__, phb->hub_id, rc); + return; + } + + switch (data->type) { + case OPAL_P7IOC_DIAG_TYPE_RGC: + pr_info("P7IOC diag-data for RGC\n\n"); + pnv_eeh_dump_hub_diag_common(data); + if (data->rgc.rgcStatus || data->rgc.rgcLdcp) + pr_info(" RGC: %016llx %016llx\n", + be64_to_cpu(data->rgc.rgcStatus), + be64_to_cpu(data->rgc.rgcLdcp)); + break; + case OPAL_P7IOC_DIAG_TYPE_BI: + pr_info("P7IOC diag-data for BI %s\n\n", + data->bi.biDownbound ? "Downbound" : "Upbound"); + pnv_eeh_dump_hub_diag_common(data); + if (data->bi.biLdcp0 || data->bi.biLdcp1 || + data->bi.biLdcp2 || data->bi.biFenceStatus) + pr_info(" BI: %016llx %016llx %016llx %016llx\n", + be64_to_cpu(data->bi.biLdcp0), + be64_to_cpu(data->bi.biLdcp1), + be64_to_cpu(data->bi.biLdcp2), + be64_to_cpu(data->bi.biFenceStatus)); + break; + case OPAL_P7IOC_DIAG_TYPE_CI: + pr_info("P7IOC diag-data for CI Port %d\n\n", + data->ci.ciPort); + pnv_eeh_dump_hub_diag_common(data); + if (data->ci.ciPortStatus || data->ci.ciPortLdcp) + pr_info(" CI: %016llx %016llx\n", + be64_to_cpu(data->ci.ciPortStatus), + be64_to_cpu(data->ci.ciPortLdcp)); + break; + case OPAL_P7IOC_DIAG_TYPE_MISC: + pr_info("P7IOC diag-data for MISC\n\n"); + pnv_eeh_dump_hub_diag_common(data); + break; + case OPAL_P7IOC_DIAG_TYPE_I2C: + pr_info("P7IOC diag-data for I2C\n\n"); + pnv_eeh_dump_hub_diag_common(data); + break; + default: + pr_warn("%s: Invalid type of HUB#%llx diag-data (%d)\n", + __func__, phb->hub_id, data->type); + } +} + +static int pnv_eeh_get_pe(struct pci_controller *hose, + u16 pe_no, struct eeh_pe **pe) +{ + struct pnv_phb *phb = hose->private_data; + struct pnv_ioda_pe *pnv_pe; + struct eeh_pe *dev_pe; + struct eeh_dev edev; + + /* + * If PHB supports compound PE, to fetch + * the master PE because slave PE is invisible + * to EEH core. + */ + pnv_pe = &phb->ioda.pe_array[pe_no]; + if (pnv_pe->flags & PNV_IODA_PE_SLAVE) { + pnv_pe = pnv_pe->master; + WARN_ON(!pnv_pe || + !(pnv_pe->flags & PNV_IODA_PE_MASTER)); + pe_no = pnv_pe->pe_number; + } + + /* Find the PE according to PE# */ + memset(&edev, 0, sizeof(struct eeh_dev)); + edev.phb = hose; + edev.pe_config_addr = pe_no; + dev_pe = eeh_pe_get(&edev); + if (!dev_pe) + return -EEXIST; + + /* Freeze the (compound) PE */ + *pe = dev_pe; + if (!(dev_pe->state & EEH_PE_ISOLATED)) + phb->freeze_pe(phb, pe_no); + + /* + * At this point, we're sure the (compound) PE should + * have been frozen. However, we still need poke until + * hitting the frozen PE on top level. + */ + dev_pe = dev_pe->parent; + while (dev_pe && !(dev_pe->type & EEH_PE_PHB)) { + int ret; + int active_flags = (EEH_STATE_MMIO_ACTIVE | + EEH_STATE_DMA_ACTIVE); + + ret = eeh_ops->get_state(dev_pe, NULL); + if (ret <= 0 || (ret & active_flags) == active_flags) { + dev_pe = dev_pe->parent; + continue; + } + + /* Frozen parent PE */ + *pe = dev_pe; + if (!(dev_pe->state & EEH_PE_ISOLATED)) + phb->freeze_pe(phb, dev_pe->addr); + + /* Next one */ + dev_pe = dev_pe->parent; + } + + return 0; } /** - * powernv_eeh_next_error - Retrieve next EEH error to handle + * pnv_eeh_next_error - Retrieve next EEH error to handle * @pe: Affected PE * - * Using OPAL API, to retrieve next EEH error for EEH core to handle + * The function is expected to be called by EEH core while it gets + * special EEH event (without binding PE). The function calls to + * OPAL APIs for next error to handle. The informational error is + * handled internally by platform. However, the dead IOC, dead PHB, + * fenced PHB and frozen PE should be handled by EEH core eventually. */ -static int powernv_eeh_next_error(struct eeh_pe **pe) +static int pnv_eeh_next_error(struct eeh_pe **pe) { struct pci_controller *hose; - struct pnv_phb *phb = NULL; + struct pnv_phb *phb; + struct eeh_pe *phb_pe, *parent_pe; + __be64 frozen_pe_no; + __be16 err_type, severity; + int active_flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE); + long rc; + int state, ret = EEH_NEXT_ERR_NONE; + + /* + * While running here, it's safe to purge the event queue. + * And we should keep the cached OPAL notifier event sychronized + * between the kernel and firmware. + */ + eeh_remove_event(NULL, false); + opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul); list_for_each_entry(hose, &hose_list, list_node) { + /* + * If the subordinate PCI buses of the PHB has been + * removed or is exactly under error recovery, we + * needn't take care of it any more. + */ phb = hose->private_data; - break; - } + phb_pe = eeh_phb_pe_get(hose); + if (!phb_pe || (phb_pe->state & EEH_PE_ISOLATED)) + continue; + + rc = opal_pci_next_error(phb->opal_id, + &frozen_pe_no, &err_type, &severity); + if (rc != OPAL_SUCCESS) { + pr_devel("%s: Invalid return value on " + "PHB#%x (0x%lx) from opal_pci_next_error", + __func__, hose->global_number, rc); + continue; + } + + /* If the PHB doesn't have error, stop processing */ + if (be16_to_cpu(err_type) == OPAL_EEH_NO_ERROR || + be16_to_cpu(severity) == OPAL_EEH_SEV_NO_ERROR) { + pr_devel("%s: No error found on PHB#%x\n", + __func__, hose->global_number); + continue; + } + + /* + * Processing the error. We're expecting the error with + * highest priority reported upon multiple errors on the + * specific PHB. + */ + pr_devel("%s: Error (%d, %d, %llu) on PHB#%x\n", + __func__, be16_to_cpu(err_type), + be16_to_cpu(severity), be64_to_cpu(frozen_pe_no), + hose->global_number); + switch (be16_to_cpu(err_type)) { + case OPAL_EEH_IOC_ERROR: + if (be16_to_cpu(severity) == OPAL_EEH_SEV_IOC_DEAD) { + pr_err("EEH: dead IOC detected\n"); + ret = EEH_NEXT_ERR_DEAD_IOC; + } else if (be16_to_cpu(severity) == OPAL_EEH_SEV_INF) { + pr_info("EEH: IOC informative error " + "detected\n"); + pnv_eeh_get_and_dump_hub_diag(hose); + ret = EEH_NEXT_ERR_NONE; + } + + break; + case OPAL_EEH_PHB_ERROR: + if (be16_to_cpu(severity) == OPAL_EEH_SEV_PHB_DEAD) { + *pe = phb_pe; + pr_err("EEH: dead PHB#%x detected, " + "location: %s\n", + hose->global_number, + eeh_pe_loc_get(phb_pe)); + ret = EEH_NEXT_ERR_DEAD_PHB; + } else if (be16_to_cpu(severity) == + OPAL_EEH_SEV_PHB_FENCED) { + *pe = phb_pe; + pr_err("EEH: Fenced PHB#%x detected, " + "location: %s\n", + hose->global_number, + eeh_pe_loc_get(phb_pe)); + ret = EEH_NEXT_ERR_FENCED_PHB; + } else if (be16_to_cpu(severity) == OPAL_EEH_SEV_INF) { + pr_info("EEH: PHB#%x informative error " + "detected, location: %s\n", + hose->global_number, + eeh_pe_loc_get(phb_pe)); + pnv_eeh_get_phb_diag(phb_pe); + pnv_pci_dump_phb_diag_data(hose, phb_pe->data); + ret = EEH_NEXT_ERR_NONE; + } + + break; + case OPAL_EEH_PE_ERROR: + /* + * If we can't find the corresponding PE, we + * just try to unfreeze. + */ + if (pnv_eeh_get_pe(hose, + be64_to_cpu(frozen_pe_no), pe)) { + /* Try best to clear it */ + pr_info("EEH: Clear non-existing PHB#%x-PE#%llx\n", + hose->global_number, frozen_pe_no); + pr_info("EEH: PHB location: %s\n", + eeh_pe_loc_get(phb_pe)); + opal_pci_eeh_freeze_clear(phb->opal_id, + frozen_pe_no, + OPAL_EEH_ACTION_CLEAR_FREEZE_ALL); + ret = EEH_NEXT_ERR_NONE; + } else if ((*pe)->state & EEH_PE_ISOLATED || + eeh_pe_passed(*pe)) { + ret = EEH_NEXT_ERR_NONE; + } else { + pr_err("EEH: Frozen PE#%x " + "on PHB#%x detected\n", + (*pe)->addr, + (*pe)->phb->global_number); + pr_err("EEH: PE location: %s, " + "PHB location: %s\n", + eeh_pe_loc_get(*pe), + eeh_pe_loc_get(phb_pe)); + ret = EEH_NEXT_ERR_FROZEN_PE; + } + + break; + default: + pr_warn("%s: Unexpected error type %d\n", + __func__, be16_to_cpu(err_type)); + } - if (phb && phb->eeh_ops->next_error) - return phb->eeh_ops->next_error(pe); + /* + * EEH core will try recover from fenced PHB or + * frozen PE. In the time for frozen PE, EEH core + * enable IO path for that before collecting logs, + * but it ruins the site. So we have to dump the + * log in advance here. + */ + if ((ret == EEH_NEXT_ERR_FROZEN_PE || + ret == EEH_NEXT_ERR_FENCED_PHB) && + !((*pe)->state & EEH_PE_ISOLATED)) { + eeh_pe_state_mark(*pe, EEH_PE_ISOLATED); + pnv_eeh_get_phb_diag(*pe); + + if (eeh_has_flag(EEH_EARLY_DUMP_LOG)) + pnv_pci_dump_phb_diag_data((*pe)->phb, + (*pe)->data); + } - return -EEXIST; + /* + * We probably have the frozen parent PE out there and + * we need have to handle frozen parent PE firstly. + */ + if (ret == EEH_NEXT_ERR_FROZEN_PE) { + parent_pe = (*pe)->parent; + while (parent_pe) { + /* Hit the ceiling ? */ + if (parent_pe->type & EEH_PE_PHB) + break; + + /* Frozen parent PE ? */ + state = eeh_ops->get_state(parent_pe, NULL); + if (state > 0 && + (state & active_flags) != active_flags) + *pe = parent_pe; + + /* Next parent level */ + parent_pe = parent_pe->parent; + } + + /* We possibly migrate to another PE */ + eeh_pe_state_mark(*pe, EEH_PE_ISOLATED); + } + + /* + * If we have no errors on the specific PHB or only + * informative error there, we continue poking it. + * Otherwise, we need actions to be taken by upper + * layer. + */ + if (ret > EEH_NEXT_ERR_INF) + break; + } + + return ret; } -static int powernv_eeh_restore_config(struct device_node *dn) +static int pnv_eeh_restore_config(struct pci_dn *pdn) { - struct eeh_dev *edev = of_node_to_eeh_dev(dn); + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); struct pnv_phb *phb; s64 ret; @@ -490,24 +1501,23 @@ static int powernv_eeh_restore_config(struct device_node *dn) return 0; } -static struct eeh_ops powernv_eeh_ops = { +static struct eeh_ops pnv_eeh_ops = { .name = "powernv", - .init = powernv_eeh_init, - .post_init = powernv_eeh_post_init, - .of_probe = NULL, - .dev_probe = powernv_eeh_dev_probe, - .set_option = powernv_eeh_set_option, - .get_pe_addr = powernv_eeh_get_pe_addr, - .get_state = powernv_eeh_get_state, - .reset = powernv_eeh_reset, - .wait_state = powernv_eeh_wait_state, - .get_log = powernv_eeh_get_log, - .configure_bridge = powernv_eeh_configure_bridge, - .err_inject = powernv_eeh_err_inject, - .read_config = powernv_eeh_read_config, - .write_config = powernv_eeh_write_config, - .next_error = powernv_eeh_next_error, - .restore_config = powernv_eeh_restore_config + .init = pnv_eeh_init, + .post_init = pnv_eeh_post_init, + .probe = pnv_eeh_probe, + .set_option = pnv_eeh_set_option, + .get_pe_addr = pnv_eeh_get_pe_addr, + .get_state = pnv_eeh_get_state, + .reset = pnv_eeh_reset, + .wait_state = pnv_eeh_wait_state, + .get_log = pnv_eeh_get_log, + .configure_bridge = pnv_eeh_configure_bridge, + .err_inject = pnv_eeh_err_inject, + .read_config = pnv_eeh_read_config, + .write_config = pnv_eeh_write_config, + .next_error = pnv_eeh_next_error, + .restore_config = pnv_eeh_restore_config }; /** @@ -521,7 +1531,7 @@ static int __init eeh_powernv_init(void) int ret = -EINVAL; eeh_set_pe_aux_size(PNV_PCI_DIAG_BUF_SIZE); - ret = eeh_ops_register(&powernv_eeh_ops); + ret = eeh_ops_register(&pnv_eeh_ops); if (!ret) pr_info("EEH: PowerNV platform initialized\n"); else diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c index 23260f7dfa7a..5aa9c1ce4de3 100644 --- a/arch/powerpc/platforms/powernv/opal-dump.c +++ b/arch/powerpc/platforms/powernv/opal-dump.c @@ -452,5 +452,6 @@ void __init opal_platform_dump_init(void) return; } - opal_dump_resend_notification(); + if (opal_check_token(OPAL_DUMP_RESEND)) + opal_dump_resend_notification(); } diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c index 518fe95dbf24..38ce757e5e2a 100644 --- a/arch/powerpc/platforms/powernv/opal-elog.c +++ b/arch/powerpc/platforms/powernv/opal-elog.c @@ -313,7 +313,8 @@ int __init opal_elog_init(void) } /* We are now ready to pull error logs from opal. */ - opal_resend_pending_logs(); + if (opal_check_token(OPAL_ELOG_RESEND)) + opal_resend_pending_logs(); return 0; } diff --git a/arch/powerpc/platforms/powernv/opal-flash.c b/arch/powerpc/platforms/powernv/opal-flash.c index 5c21d9c07f45..4ec6219287fc 100644 --- a/arch/powerpc/platforms/powernv/opal-flash.c +++ b/arch/powerpc/platforms/powernv/opal-flash.c @@ -120,7 +120,11 @@ static struct image_header_t image_header; static struct image_data_t image_data; static struct validate_flash_t validate_flash_data; static struct manage_flash_t manage_flash_data; -static struct update_flash_t update_flash_data; + +/* Initialize update_flash_data status to No Operation */ +static struct update_flash_t update_flash_data = { + .status = FLASH_NO_OP, +}; static DEFINE_MUTEX(image_data_mutex); @@ -542,7 +546,7 @@ static struct attribute_group image_op_attr_group = { .attrs = image_op_attrs, }; -void __init opal_flash_init(void) +void __init opal_flash_update_init(void) { int ret; diff --git a/arch/powerpc/platforms/powernv/opal-nvram.c b/arch/powerpc/platforms/powernv/opal-nvram.c index f9896fd5d04a..9db4398ded5d 100644 --- a/arch/powerpc/platforms/powernv/opal-nvram.c +++ b/arch/powerpc/platforms/powernv/opal-nvram.c @@ -16,6 +16,7 @@ #include <linux/of.h> #include <asm/opal.h> +#include <asm/nvram.h> #include <asm/machdep.h> static unsigned int nvram_size; @@ -62,6 +63,15 @@ static ssize_t opal_nvram_write(char *buf, size_t count, loff_t *index) return count; } +static int __init opal_nvram_init_log_partitions(void) +{ + /* Scan nvram for partitions */ + nvram_scan_partitions(); + nvram_init_oops_partition(0); + return 0; +} +machine_arch_initcall(powernv, opal_nvram_init_log_partitions); + void __init opal_nvram_init(void) { struct device_node *np; diff --git a/arch/powerpc/platforms/powernv/opal-power.c b/arch/powerpc/platforms/powernv/opal-power.c index 48bf5b080bcf..ac46c2c24f99 100644 --- a/arch/powerpc/platforms/powernv/opal-power.c +++ b/arch/powerpc/platforms/powernv/opal-power.c @@ -29,8 +29,9 @@ static int opal_power_control_event(struct notifier_block *nb, switch (type) { case SOFT_REBOOT: - /* Fall through. The service processor is responsible for - * bringing the machine back up */ + pr_info("OPAL: reboot requested\n"); + orderly_reboot(); + break; case SOFT_OFF: pr_info("OPAL: poweroff requested\n"); orderly_poweroff(true); diff --git a/arch/powerpc/platforms/powernv/opal-sensor.c b/arch/powerpc/platforms/powernv/opal-sensor.c index 4ab67ef7abc9..655250499d18 100644 --- a/arch/powerpc/platforms/powernv/opal-sensor.c +++ b/arch/powerpc/platforms/powernv/opal-sensor.c @@ -46,18 +46,28 @@ int opal_get_sensor_data(u32 sensor_hndl, u32 *sensor_data) mutex_lock(&opal_sensor_mutex); ret = opal_sensor_read(sensor_hndl, token, &data); - if (ret != OPAL_ASYNC_COMPLETION) - goto out_token; + switch (ret) { + case OPAL_ASYNC_COMPLETION: + ret = opal_async_wait_response(token, &msg); + if (ret) { + pr_err("%s: Failed to wait for the async response, %d\n", + __func__, ret); + goto out_token; + } - ret = opal_async_wait_response(token, &msg); - if (ret) { - pr_err("%s: Failed to wait for the async response, %d\n", - __func__, ret); - goto out_token; - } + ret = opal_error_code(be64_to_cpu(msg.params[1])); + *sensor_data = be32_to_cpu(data); + break; + + case OPAL_SUCCESS: + ret = 0; + *sensor_data = be32_to_cpu(data); + break; - *sensor_data = be32_to_cpu(data); - ret = be64_to_cpu(msg.params[1]); + default: + ret = opal_error_code(ret); + break; + } out_token: mutex_unlock(&opal_sensor_mutex); diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index 0509bca5e830..a7ade94cdf87 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -9,11 +9,11 @@ * 2 of the License, or (at your option) any later version. */ +#include <linux/jump_label.h> #include <asm/ppc_asm.h> #include <asm/hvcall.h> #include <asm/asm-offsets.h> #include <asm/opal.h> -#include <asm/jump_label.h> .section ".text" @@ -286,9 +286,12 @@ OPAL_CALL(opal_handle_hmi, OPAL_HANDLE_HMI); 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_CXL_MODE); +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); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 18fd4e71c9c1..2241565b0739 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -23,6 +23,8 @@ #include <linux/kobject.h> #include <linux/delay.h> #include <linux/memblock.h> +#include <linux/kthread.h> +#include <linux/freezer.h> #include <asm/machdep.h> #include <asm/opal.h> @@ -58,6 +60,7 @@ static struct atomic_notifier_head opal_msg_notifier_head[OPAL_MSG_TYPE_MAX]; static DEFINE_SPINLOCK(opal_notifier_lock); static uint64_t last_notified_mask = 0x0ul; static atomic_t opal_notifier_hold = ATOMIC_INIT(0); +static uint32_t opal_heartbeat; static void opal_reinit_cores(void) { @@ -302,23 +305,26 @@ void opal_notifier_disable(void) * Opal message notifier based on message type. Allow subscribers to get * notified for specific messgae type. */ -int opal_message_notifier_register(enum OpalMessageType msg_type, +int opal_message_notifier_register(enum opal_msg_type msg_type, struct notifier_block *nb) { - if (!nb) { - pr_warning("%s: Invalid argument (%p)\n", - __func__, nb); - return -EINVAL; - } - if (msg_type > OPAL_MSG_TYPE_MAX) { - pr_warning("%s: Invalid message type argument (%d)\n", + if (!nb || msg_type >= OPAL_MSG_TYPE_MAX) { + pr_warning("%s: Invalid arguments, msg_type:%d\n", __func__, msg_type); return -EINVAL; } + return atomic_notifier_chain_register( &opal_msg_notifier_head[msg_type], nb); } +int opal_message_notifier_unregister(enum opal_msg_type msg_type, + struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister( + &opal_msg_notifier_head[msg_type], nb); +} + static void opal_message_do_notify(uint32_t msg_type, void *msg) { /* notify subscribers */ @@ -351,7 +357,7 @@ static void opal_handle_message(void) type = be32_to_cpu(msg.msg_type); /* Sanity check */ - if (type > OPAL_MSG_TYPE_MAX) { + if (type >= OPAL_MSG_TYPE_MAX) { pr_warning("%s: Unknown message type: %u\n", __func__, type); return; } @@ -665,6 +671,9 @@ static void __init opal_dump_region_init(void) uint64_t size; int rc; + if (!opal_check_token(OPAL_REGISTER_DUMP_REGION)) + return; + /* Register kernel log buffer */ addr = log_buf_addr_get(); if (addr == NULL) @@ -684,6 +693,15 @@ static void __init opal_dump_region_init(void) "rc = %d\n", rc); } +static void opal_flash_init(struct device_node *opal_node) +{ + struct device_node *np; + + for_each_child_of_node(opal_node, np) + if (of_device_is_compatible(np, "ibm,opal-flash")) + of_platform_device_create(np, NULL, NULL); +} + static void opal_ipmi_init(struct device_node *opal_node) { struct device_node *np; @@ -741,6 +759,29 @@ static void __init opal_irq_init(struct device_node *dn) } } +static int kopald(void *unused) +{ + set_freezable(); + do { + try_to_freeze(); + opal_poll_events(NULL); + msleep_interruptible(opal_heartbeat); + } while (!kthread_should_stop()); + + return 0; +} + +static void opal_init_heartbeat(void) +{ + /* Old firwmware, we assume the HVC heartbeat is sufficient */ + if (of_property_read_u32(opal_node, "ibm,heartbeat-ms", + &opal_heartbeat) != 0) + opal_heartbeat = 0; + + if (opal_heartbeat) + kthread_run(kopald, NULL, "kopald"); +} + static int __init opal_init(void) { struct device_node *np, *consoles; @@ -769,6 +810,9 @@ static int __init opal_init(void) /* Create i2c platform devices */ opal_i2c_create_devs(); + /* Setup a heatbeat thread if requested by OPAL */ + opal_init_heartbeat(); + /* Find all OPAL interrupts and request them */ opal_irq_init(opal_node); @@ -782,7 +826,7 @@ static int __init opal_init(void) /* Setup error log interface */ rc = opal_elog_init(); /* Setup code update interface */ - opal_flash_init(); + opal_flash_update_init(); /* Setup platform dump extract interface */ opal_platform_dump_init(); /* Setup system parameters interface */ @@ -791,8 +835,11 @@ static int __init opal_init(void) opal_msglog_init(); } + /* Initialize OPAL IPMI backend */ opal_ipmi_init(opal_node); + opal_flash_init(opal_node); + return 0; } machine_subsys_initcall(powernv, opal_init); @@ -823,13 +870,17 @@ void opal_shutdown(void) } /* Unregister memory dump region */ - opal_unregister_dump_region(OPAL_DUMP_REGION_LOG_BUF); + if (opal_check_token(OPAL_UNREGISTER_DUMP_REGION)) + opal_unregister_dump_region(OPAL_DUMP_REGION_LOG_BUF); } /* Export this so that test modules can use it */ EXPORT_SYMBOL_GPL(opal_invalid_call); EXPORT_SYMBOL_GPL(opal_ipmi_send); EXPORT_SYMBOL_GPL(opal_ipmi_recv); +EXPORT_SYMBOL_GPL(opal_flash_read); +EXPORT_SYMBOL_GPL(opal_flash_write); +EXPORT_SYMBOL_GPL(opal_flash_erase); /* Convert a region of vmalloc memory to an opal sg list */ struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr, @@ -894,6 +945,25 @@ void opal_free_sg_list(struct opal_sg_list *sg) } } +int opal_error_code(int rc) +{ + switch (rc) { + case OPAL_SUCCESS: return 0; + + case OPAL_PARAMETER: return -EINVAL; + case OPAL_ASYNC_COMPLETION: return -EINPROGRESS; + case OPAL_BUSY_EVENT: return -EBUSY; + case OPAL_NO_MEM: return -ENOMEM; + + case OPAL_UNSUPPORTED: return -EIO; + case OPAL_HARDWARE: return -EIO; + case OPAL_INTERNAL_ERROR: return -EIO; + default: + pr_err("%s: unexpected OPAL error %d\n", __func__, rc); + return -EIO; + } +} + EXPORT_SYMBOL_GPL(opal_poll_events); EXPORT_SYMBOL_GPL(opal_rtc_read); EXPORT_SYMBOL_GPL(opal_rtc_write); diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 6c9ff2b95119..920c252d1f49 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -44,6 +44,9 @@ #include "powernv.h" #include "pci.h" +/* 256M DMA window, 4K TCE pages, 8 bytes TCE */ +#define TCE32_TABLE_SIZE ((0x10000000 / 0x1000) * 8) + static void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level, const char *fmt, ...) { @@ -56,11 +59,18 @@ static void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level, vaf.fmt = fmt; vaf.va = &args; - if (pe->pdev) + if (pe->flags & PNV_IODA_PE_DEV) strlcpy(pfix, dev_name(&pe->pdev->dev), sizeof(pfix)); - else + else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) sprintf(pfix, "%04x:%02x ", pci_domain_nr(pe->pbus), pe->pbus->number); +#ifdef CONFIG_PCI_IOV + else if (pe->flags & PNV_IODA_PE_VF) + sprintf(pfix, "%04x:%02x:%2x.%d", + pci_domain_nr(pe->parent_dev->bus), + (pe->rid & 0xff00) >> 8, + PCI_SLOT(pe->rid), PCI_FUNC(pe->rid)); +#endif /* CONFIG_PCI_IOV*/ printk("%spci %s: [PE# %.3d] %pV", level, pfix, pe->pe_number, &vaf); @@ -591,7 +601,7 @@ static int pnv_ioda_set_peltv(struct pnv_phb *phb, bool is_add) { struct pnv_ioda_pe *slave; - struct pci_dev *pdev; + struct pci_dev *pdev = NULL; int ret; /* @@ -630,8 +640,12 @@ static int pnv_ioda_set_peltv(struct pnv_phb *phb, if (pe->flags & (PNV_IODA_PE_BUS_ALL | PNV_IODA_PE_BUS)) pdev = pe->pbus->self; - else + else if (pe->flags & PNV_IODA_PE_DEV) pdev = pe->pdev->bus->self; +#ifdef CONFIG_PCI_IOV + else if (pe->flags & PNV_IODA_PE_VF) + pdev = pe->parent_dev->bus->self; +#endif /* CONFIG_PCI_IOV */ while (pdev) { struct pci_dn *pdn = pci_get_pdn(pdev); struct pnv_ioda_pe *parent; @@ -649,6 +663,87 @@ static int pnv_ioda_set_peltv(struct pnv_phb *phb, return 0; } +#ifdef CONFIG_PCI_IOV +static int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) +{ + struct pci_dev *parent; + uint8_t bcomp, dcomp, fcomp; + int64_t rc; + long rid_end, rid; + + /* Currently, we just deconfigure VF PE. Bus PE will always there.*/ + if (pe->pbus) { + int count; + + dcomp = OPAL_IGNORE_RID_DEVICE_NUMBER; + fcomp = OPAL_IGNORE_RID_FUNCTION_NUMBER; + parent = pe->pbus->self; + if (pe->flags & PNV_IODA_PE_BUS_ALL) + count = pe->pbus->busn_res.end - pe->pbus->busn_res.start + 1; + else + count = 1; + + switch(count) { + case 1: bcomp = OpalPciBusAll; break; + case 2: bcomp = OpalPciBus7Bits; break; + case 4: bcomp = OpalPciBus6Bits; break; + case 8: bcomp = OpalPciBus5Bits; break; + case 16: bcomp = OpalPciBus4Bits; break; + case 32: bcomp = OpalPciBus3Bits; break; + default: + dev_err(&pe->pbus->dev, "Number of subordinate buses %d unsupported\n", + count); + /* Do an exact match only */ + bcomp = OpalPciBusAll; + } + rid_end = pe->rid + (count << 8); + } else { + if (pe->flags & PNV_IODA_PE_VF) + parent = pe->parent_dev; + else + parent = pe->pdev->bus->self; + bcomp = OpalPciBusAll; + dcomp = OPAL_COMPARE_RID_DEVICE_NUMBER; + fcomp = OPAL_COMPARE_RID_FUNCTION_NUMBER; + rid_end = pe->rid + 1; + } + + /* Clear the reverse map */ + for (rid = pe->rid; rid < rid_end; rid++) + phb->ioda.pe_rmap[rid] = 0; + + /* Release from all parents PELT-V */ + while (parent) { + struct pci_dn *pdn = pci_get_pdn(parent); + if (pdn && pdn->pe_number != IODA_INVALID_PE) { + rc = opal_pci_set_peltv(phb->opal_id, pdn->pe_number, + pe->pe_number, OPAL_REMOVE_PE_FROM_DOMAIN); + /* XXX What to do in case of error ? */ + } + parent = parent->bus->self; + } + + opal_pci_eeh_freeze_set(phb->opal_id, pe->pe_number, + OPAL_EEH_ACTION_CLEAR_FREEZE_ALL); + + /* Disassociate PE in PELT */ + rc = opal_pci_set_peltv(phb->opal_id, pe->pe_number, + pe->pe_number, OPAL_REMOVE_PE_FROM_DOMAIN); + if (rc) + pe_warn(pe, "OPAL error %ld remove self from PELTV\n", rc); + rc = opal_pci_set_pe(phb->opal_id, pe->pe_number, pe->rid, + bcomp, dcomp, fcomp, OPAL_UNMAP_PE); + if (rc) + pe_err(pe, "OPAL error %ld trying to setup PELT table\n", rc); + + pe->pbus = NULL; + pe->pdev = NULL; + pe->parent_dev = NULL; + + return 0; +} +#endif /* CONFIG_PCI_IOV */ + static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) { struct pci_dev *parent; @@ -675,15 +770,19 @@ static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) case 16: bcomp = OpalPciBus4Bits; break; case 32: bcomp = OpalPciBus3Bits; break; default: - pr_err("%s: Number of subordinate busses %d" - " unsupported\n", - pci_name(pe->pbus->self), count); + dev_err(&pe->pbus->dev, "Number of subordinate buses %d unsupported\n", + count); /* Do an exact match only */ bcomp = OpalPciBusAll; } rid_end = pe->rid + (count << 8); } else { - parent = pe->pdev->bus->self; +#ifdef CONFIG_PCI_IOV + if (pe->flags & PNV_IODA_PE_VF) + parent = pe->parent_dev; + else +#endif /* CONFIG_PCI_IOV */ + parent = pe->pdev->bus->self; bcomp = OpalPciBusAll; dcomp = OPAL_COMPARE_RID_DEVICE_NUMBER; fcomp = OPAL_COMPARE_RID_FUNCTION_NUMBER; @@ -774,6 +873,78 @@ static unsigned int pnv_ioda_dma_weight(struct pci_dev *dev) return 10; } +#ifdef CONFIG_PCI_IOV +static int pnv_pci_vf_resource_shift(struct pci_dev *dev, int offset) +{ + struct pci_dn *pdn = pci_get_pdn(dev); + int i; + struct resource *res, res2; + resource_size_t size; + u16 num_vfs; + + if (!dev->is_physfn) + return -EINVAL; + + /* + * "offset" is in VFs. The M64 windows are sized so that when they + * are segmented, each segment is the same size as the IOV BAR. + * Each segment is in a separate PE, and the high order bits of the + * address are the PE number. Therefore, each VF's BAR is in a + * separate PE, and changing the IOV BAR start address changes the + * range of PEs the VFs are in. + */ + num_vfs = pdn->num_vfs; + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + res = &dev->resource[i + PCI_IOV_RESOURCES]; + if (!res->flags || !res->parent) + continue; + + if (!pnv_pci_is_mem_pref_64(res->flags)) + continue; + + /* + * The actual IOV BAR range is determined by the start address + * and the actual size for num_vfs VFs BAR. This check is to + * make sure that after shifting, the range will not overlap + * with another device. + */ + size = pci_iov_resource_size(dev, i + PCI_IOV_RESOURCES); + res2.flags = res->flags; + res2.start = res->start + (size * offset); + res2.end = res2.start + (size * num_vfs) - 1; + + if (res2.end > res->end) { + dev_err(&dev->dev, "VF BAR%d: %pR would extend past %pR (trying to enable %d VFs shifted by %d)\n", + i, &res2, res, num_vfs, offset); + return -EBUSY; + } + } + + /* + * After doing so, there would be a "hole" in the /proc/iomem when + * offset is a positive value. It looks like the device return some + * mmio back to the system, which actually no one could use it. + */ + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + res = &dev->resource[i + PCI_IOV_RESOURCES]; + if (!res->flags || !res->parent) + continue; + + if (!pnv_pci_is_mem_pref_64(res->flags)) + continue; + + size = pci_iov_resource_size(dev, i + PCI_IOV_RESOURCES); + res2 = *res; + res->start += size * offset; + + dev_info(&dev->dev, "VF BAR%d: %pR shifted to %pR (enabling %d VFs shifted by %d)\n", + i, &res2, res, num_vfs, offset); + pci_update_resource(dev, i + PCI_IOV_RESOURCES); + } + return 0; +} +#endif /* CONFIG_PCI_IOV */ + #if 0 static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev) { @@ -857,7 +1028,6 @@ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe) pci_name(dev)); continue; } - pdn->pcidev = dev; pdn->pe_number = pe->pe_number; pe->dma_weight += pnv_ioda_dma_weight(dev); if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate) @@ -916,6 +1086,10 @@ static void pnv_ioda_setup_bus_PE(struct pci_bus *bus, int all) return; } + pe->tce32_table = kzalloc_node(sizeof(struct iommu_table), + GFP_KERNEL, hose->node); + pe->tce32_table->data = pe; + /* Associate it with all child devices */ pnv_ioda_setup_same_PE(bus, pe); @@ -974,6 +1148,441 @@ static void pnv_pci_ioda_setup_PEs(void) } } +#ifdef CONFIG_PCI_IOV +static int pnv_pci_vf_release_m64(struct pci_dev *pdev) +{ + struct pci_bus *bus; + struct pci_controller *hose; + struct pnv_phb *phb; + struct pci_dn *pdn; + int i, j; + + bus = pdev->bus; + hose = pci_bus_to_host(bus); + phb = hose->private_data; + pdn = pci_get_pdn(pdev); + + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) + for (j = 0; j < M64_PER_IOV; j++) { + if (pdn->m64_wins[i][j] == IODA_INVALID_M64) + continue; + opal_pci_phb_mmio_enable(phb->opal_id, + OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 0); + clear_bit(pdn->m64_wins[i][j], &phb->ioda.m64_bar_alloc); + pdn->m64_wins[i][j] = IODA_INVALID_M64; + } + + return 0; +} + +static int pnv_pci_vf_assign_m64(struct pci_dev *pdev, u16 num_vfs) +{ + struct pci_bus *bus; + struct pci_controller *hose; + struct pnv_phb *phb; + struct pci_dn *pdn; + unsigned int win; + struct resource *res; + int i, j; + int64_t rc; + int total_vfs; + resource_size_t size, start; + int pe_num; + int vf_groups; + int vf_per_group; + + bus = pdev->bus; + hose = pci_bus_to_host(bus); + phb = hose->private_data; + pdn = pci_get_pdn(pdev); + total_vfs = pci_sriov_get_totalvfs(pdev); + + /* Initialize the m64_wins to IODA_INVALID_M64 */ + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) + for (j = 0; j < M64_PER_IOV; j++) + pdn->m64_wins[i][j] = IODA_INVALID_M64; + + if (pdn->m64_per_iov == M64_PER_IOV) { + vf_groups = (num_vfs <= M64_PER_IOV) ? num_vfs: M64_PER_IOV; + vf_per_group = (num_vfs <= M64_PER_IOV)? 1: + roundup_pow_of_two(num_vfs) / pdn->m64_per_iov; + } else { + vf_groups = 1; + vf_per_group = 1; + } + + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + res = &pdev->resource[i + PCI_IOV_RESOURCES]; + if (!res->flags || !res->parent) + continue; + + if (!pnv_pci_is_mem_pref_64(res->flags)) + continue; + + for (j = 0; j < vf_groups; j++) { + do { + win = find_next_zero_bit(&phb->ioda.m64_bar_alloc, + phb->ioda.m64_bar_idx + 1, 0); + + if (win >= phb->ioda.m64_bar_idx + 1) + goto m64_failed; + } while (test_and_set_bit(win, &phb->ioda.m64_bar_alloc)); + + pdn->m64_wins[i][j] = win; + + if (pdn->m64_per_iov == M64_PER_IOV) { + size = pci_iov_resource_size(pdev, + PCI_IOV_RESOURCES + i); + size = size * vf_per_group; + start = res->start + size * j; + } else { + size = resource_size(res); + start = res->start; + } + + /* Map the M64 here */ + if (pdn->m64_per_iov == M64_PER_IOV) { + pe_num = pdn->offset + j; + rc = opal_pci_map_pe_mmio_window(phb->opal_id, + pe_num, OPAL_M64_WINDOW_TYPE, + pdn->m64_wins[i][j], 0); + } + + rc = opal_pci_set_phb_mem_window(phb->opal_id, + OPAL_M64_WINDOW_TYPE, + pdn->m64_wins[i][j], + start, + 0, /* unused */ + size); + + + if (rc != OPAL_SUCCESS) { + dev_err(&pdev->dev, "Failed to map M64 window #%d: %lld\n", + win, rc); + goto m64_failed; + } + + if (pdn->m64_per_iov == M64_PER_IOV) + rc = opal_pci_phb_mmio_enable(phb->opal_id, + OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 2); + else + rc = opal_pci_phb_mmio_enable(phb->opal_id, + OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 1); + + if (rc != OPAL_SUCCESS) { + dev_err(&pdev->dev, "Failed to enable M64 window #%d: %llx\n", + win, rc); + goto m64_failed; + } + } + } + return 0; + +m64_failed: + pnv_pci_vf_release_m64(pdev); + return -EBUSY; +} + +static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe *pe) +{ + struct pci_bus *bus; + struct pci_controller *hose; + struct pnv_phb *phb; + struct iommu_table *tbl; + unsigned long addr; + int64_t rc; + + bus = dev->bus; + hose = pci_bus_to_host(bus); + phb = hose->private_data; + tbl = pe->tce32_table; + addr = tbl->it_base; + + opal_pci_map_pe_dma_window(phb->opal_id, pe->pe_number, + pe->pe_number << 1, 1, __pa(addr), + 0, 0x1000); + + rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id, + pe->pe_number, + (pe->pe_number << 1) + 1, + pe->tce_bypass_base, + 0); + if (rc) + pe_warn(pe, "OPAL error %ld release DMA window\n", rc); + + iommu_free_table(tbl, of_node_full_name(dev->dev.of_node)); + free_pages(addr, get_order(TCE32_TABLE_SIZE)); + pe->tce32_table = NULL; +} + +static void pnv_ioda_release_vf_PE(struct pci_dev *pdev, u16 num_vfs) +{ + struct pci_bus *bus; + struct pci_controller *hose; + struct pnv_phb *phb; + struct pnv_ioda_pe *pe, *pe_n; + struct pci_dn *pdn; + u16 vf_index; + int64_t rc; + + bus = pdev->bus; + hose = pci_bus_to_host(bus); + phb = hose->private_data; + pdn = pci_get_pdn(pdev); + + if (!pdev->is_physfn) + return; + + if (pdn->m64_per_iov == M64_PER_IOV && num_vfs > M64_PER_IOV) { + int vf_group; + int vf_per_group; + int vf_index1; + + vf_per_group = roundup_pow_of_two(num_vfs) / pdn->m64_per_iov; + + for (vf_group = 0; vf_group < M64_PER_IOV; vf_group++) + for (vf_index = vf_group * vf_per_group; + vf_index < (vf_group + 1) * vf_per_group && + vf_index < num_vfs; + vf_index++) + for (vf_index1 = vf_group * vf_per_group; + vf_index1 < (vf_group + 1) * vf_per_group && + vf_index1 < num_vfs; + vf_index1++){ + + rc = opal_pci_set_peltv(phb->opal_id, + pdn->offset + vf_index, + pdn->offset + vf_index1, + OPAL_REMOVE_PE_FROM_DOMAIN); + + if (rc) + dev_warn(&pdev->dev, "%s: Failed to unlink same group PE#%d(%lld)\n", + __func__, + pdn->offset + vf_index1, rc); + } + } + + list_for_each_entry_safe(pe, pe_n, &phb->ioda.pe_list, list) { + if (pe->parent_dev != pdev) + continue; + + pnv_pci_ioda2_release_dma_pe(pdev, pe); + + /* Remove from list */ + mutex_lock(&phb->ioda.pe_list_mutex); + list_del(&pe->list); + mutex_unlock(&phb->ioda.pe_list_mutex); + + pnv_ioda_deconfigure_pe(phb, pe); + + pnv_ioda_free_pe(phb, pe->pe_number); + } +} + +void pnv_pci_sriov_disable(struct pci_dev *pdev) +{ + struct pci_bus *bus; + struct pci_controller *hose; + struct pnv_phb *phb; + struct pci_dn *pdn; + struct pci_sriov *iov; + u16 num_vfs; + + bus = pdev->bus; + hose = pci_bus_to_host(bus); + phb = hose->private_data; + pdn = pci_get_pdn(pdev); + iov = pdev->sriov; + num_vfs = pdn->num_vfs; + + /* Release VF PEs */ + pnv_ioda_release_vf_PE(pdev, num_vfs); + + if (phb->type == PNV_PHB_IODA2) { + if (pdn->m64_per_iov == 1) + pnv_pci_vf_resource_shift(pdev, -pdn->offset); + + /* Release M64 windows */ + pnv_pci_vf_release_m64(pdev); + + /* Release PE numbers */ + bitmap_clear(phb->ioda.pe_alloc, pdn->offset, num_vfs); + pdn->offset = 0; + } +} + +static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, + struct pnv_ioda_pe *pe); +static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs) +{ + struct pci_bus *bus; + struct pci_controller *hose; + struct pnv_phb *phb; + struct pnv_ioda_pe *pe; + int pe_num; + u16 vf_index; + struct pci_dn *pdn; + int64_t rc; + + bus = pdev->bus; + hose = pci_bus_to_host(bus); + phb = hose->private_data; + pdn = pci_get_pdn(pdev); + + if (!pdev->is_physfn) + return; + + /* Reserve PE for each VF */ + for (vf_index = 0; vf_index < num_vfs; vf_index++) { + pe_num = pdn->offset + vf_index; + + pe = &phb->ioda.pe_array[pe_num]; + pe->pe_number = pe_num; + pe->phb = phb; + pe->flags = PNV_IODA_PE_VF; + pe->pbus = NULL; + pe->parent_dev = pdev; + pe->tce32_seg = -1; + pe->mve_number = -1; + pe->rid = (pci_iov_virtfn_bus(pdev, vf_index) << 8) | + pci_iov_virtfn_devfn(pdev, vf_index); + + pe_info(pe, "VF %04d:%02d:%02d.%d associated with PE#%d\n", + hose->global_number, pdev->bus->number, + PCI_SLOT(pci_iov_virtfn_devfn(pdev, vf_index)), + PCI_FUNC(pci_iov_virtfn_devfn(pdev, vf_index)), pe_num); + + if (pnv_ioda_configure_pe(phb, pe)) { + /* XXX What do we do here ? */ + if (pe_num) + pnv_ioda_free_pe(phb, pe_num); + pe->pdev = NULL; + continue; + } + + pe->tce32_table = kzalloc_node(sizeof(struct iommu_table), + GFP_KERNEL, hose->node); + pe->tce32_table->data = pe; + + /* Put PE to the list */ + mutex_lock(&phb->ioda.pe_list_mutex); + list_add_tail(&pe->list, &phb->ioda.pe_list); + mutex_unlock(&phb->ioda.pe_list_mutex); + + pnv_pci_ioda2_setup_dma_pe(phb, pe); + } + + if (pdn->m64_per_iov == M64_PER_IOV && num_vfs > M64_PER_IOV) { + int vf_group; + int vf_per_group; + int vf_index1; + + vf_per_group = roundup_pow_of_two(num_vfs) / pdn->m64_per_iov; + + for (vf_group = 0; vf_group < M64_PER_IOV; vf_group++) { + for (vf_index = vf_group * vf_per_group; + vf_index < (vf_group + 1) * vf_per_group && + vf_index < num_vfs; + vf_index++) { + for (vf_index1 = vf_group * vf_per_group; + vf_index1 < (vf_group + 1) * vf_per_group && + vf_index1 < num_vfs; + vf_index1++) { + + rc = opal_pci_set_peltv(phb->opal_id, + pdn->offset + vf_index, + pdn->offset + vf_index1, + OPAL_ADD_PE_TO_DOMAIN); + + if (rc) + dev_warn(&pdev->dev, "%s: Failed to link same group PE#%d(%lld)\n", + __func__, + pdn->offset + vf_index1, rc); + } + } + } + } +} + +int pnv_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs) +{ + struct pci_bus *bus; + struct pci_controller *hose; + struct pnv_phb *phb; + struct pci_dn *pdn; + int ret; + + bus = pdev->bus; + hose = pci_bus_to_host(bus); + phb = hose->private_data; + pdn = pci_get_pdn(pdev); + + if (phb->type == PNV_PHB_IODA2) { + /* Calculate available PE for required VFs */ + mutex_lock(&phb->ioda.pe_alloc_mutex); + pdn->offset = bitmap_find_next_zero_area( + phb->ioda.pe_alloc, phb->ioda.total_pe, + 0, num_vfs, 0); + if (pdn->offset >= phb->ioda.total_pe) { + mutex_unlock(&phb->ioda.pe_alloc_mutex); + dev_info(&pdev->dev, "Failed to enable VF%d\n", num_vfs); + pdn->offset = 0; + return -EBUSY; + } + bitmap_set(phb->ioda.pe_alloc, pdn->offset, num_vfs); + pdn->num_vfs = num_vfs; + mutex_unlock(&phb->ioda.pe_alloc_mutex); + + /* Assign M64 window accordingly */ + ret = pnv_pci_vf_assign_m64(pdev, num_vfs); + if (ret) { + dev_info(&pdev->dev, "Not enough M64 window resources\n"); + goto m64_failed; + } + + /* + * When using one M64 BAR to map one IOV BAR, we need to shift + * the IOV BAR according to the PE# allocated to the VFs. + * Otherwise, the PE# for the VF will conflict with others. + */ + if (pdn->m64_per_iov == 1) { + ret = pnv_pci_vf_resource_shift(pdev, pdn->offset); + if (ret) + goto m64_failed; + } + } + + /* Setup VF PEs */ + pnv_ioda_setup_vf_PE(pdev, num_vfs); + + return 0; + +m64_failed: + bitmap_clear(phb->ioda.pe_alloc, pdn->offset, num_vfs); + pdn->offset = 0; + + return ret; +} + +int pcibios_sriov_disable(struct pci_dev *pdev) +{ + pnv_pci_sriov_disable(pdev); + + /* Release PCI data */ + remove_dev_pci_data(pdev); + return 0; +} + +int pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs) +{ + /* Allocate PCI data */ + add_dev_pci_data(pdev); + + pnv_pci_sriov_enable(pdev, num_vfs); + return 0; +} +#endif /* CONFIG_PCI_IOV */ + static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev) { struct pci_dn *pdn = pci_get_pdn(pdev); @@ -989,7 +1598,7 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev pe = &phb->ioda.pe_array[pdn->pe_number]; WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops); - set_iommu_table_base_and_group(&pdev->dev, &pe->tce32_table); + set_iommu_table_base_and_group(&pdev->dev, pe->tce32_table); } static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb, @@ -1016,7 +1625,7 @@ static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb, } else { dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n"); set_dma_ops(&pdev->dev, &dma_iommu_ops); - set_iommu_table_base(&pdev->dev, &pe->tce32_table); + set_iommu_table_base(&pdev->dev, pe->tce32_table); } *pdev->dev.dma_mask = dma_mask; return 0; @@ -1053,9 +1662,9 @@ static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, list_for_each_entry(dev, &bus->devices, bus_list) { if (add_to_iommu_group) set_iommu_table_base_and_group(&dev->dev, - &pe->tce32_table); + pe->tce32_table); else - set_iommu_table_base(&dev->dev, &pe->tce32_table); + set_iommu_table_base(&dev->dev, pe->tce32_table); if (dev->subordinate) pnv_ioda_setup_bus_dma(pe, dev->subordinate, @@ -1145,8 +1754,7 @@ static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe, void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl, __be64 *startp, __be64 *endp, bool rm) { - struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe, - tce32_table); + struct pnv_ioda_pe *pe = tbl->data; struct pnv_phb *phb = pe->phb; if (phb->type == PNV_PHB_IODA1) @@ -1167,9 +1775,6 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, int64_t rc; void *addr; - /* 256M DMA window, 4K TCE pages, 8 bytes TCE */ -#define TCE32_TABLE_SIZE ((0x10000000 / 0x1000) * 8) - /* XXX FIXME: Handle 64-bit only DMA devices */ /* XXX FIXME: Provide 64-bit DMA facilities & non-4K TCE tables etc.. */ /* XXX FIXME: Allocate multi-level tables on PHB3 */ @@ -1212,7 +1817,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, } /* Setup linux iommu table */ - tbl = &pe->tce32_table; + tbl = pe->tce32_table; pnv_pci_setup_iommu_table(tbl, addr, TCE32_TABLE_SIZE * segs, base << 28, IOMMU_PAGE_SHIFT_4K); @@ -1232,12 +1837,19 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, TCE_PCI_SWINV_PAIR); } iommu_init_table(tbl, phb->hose->node); - iommu_register_group(tbl, phb->hose->global_number, pe->pe_number); - if (pe->pdev) + if (pe->flags & PNV_IODA_PE_DEV) { + iommu_register_group(tbl, phb->hose->global_number, + pe->pe_number); set_iommu_table_base_and_group(&pe->pdev->dev, tbl); - else + } else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) { + iommu_register_group(tbl, phb->hose->global_number, + pe->pe_number); pnv_ioda_setup_bus_dma(pe, pe->pbus, true); + } else if (pe->flags & PNV_IODA_PE_VF) { + iommu_register_group(tbl, phb->hose->global_number, + pe->pe_number); + } return; fail: @@ -1250,8 +1862,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable) { - struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe, - tce32_table); + struct pnv_ioda_pe *pe = tbl->data; uint16_t window_id = (pe->pe_number << 1 ) + 1; int64_t rc; @@ -1296,10 +1907,10 @@ static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb, pe->tce_bypass_base = 1ull << 59; /* Install set_bypass callback for VFIO */ - pe->tce32_table.set_bypass = pnv_pci_ioda2_set_bypass; + pe->tce32_table->set_bypass = pnv_pci_ioda2_set_bypass; /* Enable bypass by default */ - pnv_pci_ioda2_set_bypass(&pe->tce32_table, true); + pnv_pci_ioda2_set_bypass(pe->tce32_table, true); } static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, @@ -1347,7 +1958,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, } /* Setup linux iommu table */ - tbl = &pe->tce32_table; + tbl = pe->tce32_table; pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, 0, IOMMU_PAGE_SHIFT_4K); @@ -1365,12 +1976,19 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, tbl->it_type |= (TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE); } iommu_init_table(tbl, phb->hose->node); - iommu_register_group(tbl, phb->hose->global_number, pe->pe_number); - if (pe->pdev) + if (pe->flags & PNV_IODA_PE_DEV) { + iommu_register_group(tbl, phb->hose->global_number, + pe->pe_number); set_iommu_table_base_and_group(&pe->pdev->dev, tbl); - else + } else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) { + iommu_register_group(tbl, phb->hose->global_number, + pe->pe_number); pnv_ioda_setup_bus_dma(pe, pe->pbus, true); + } else if (pe->flags & PNV_IODA_PE_VF) { + iommu_register_group(tbl, phb->hose->global_number, + pe->pe_number); + } /* Also create a bypass window */ if (!pnv_iommu_bypass_disabled) @@ -1731,6 +2349,73 @@ static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) { } #endif /* CONFIG_PCI_MSI */ +#ifdef CONFIG_PCI_IOV +static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev) +{ + struct pci_controller *hose; + struct pnv_phb *phb; + struct resource *res; + int i; + resource_size_t size; + struct pci_dn *pdn; + int mul, total_vfs; + + if (!pdev->is_physfn || pdev->is_added) + return; + + hose = pci_bus_to_host(pdev->bus); + phb = hose->private_data; + + pdn = pci_get_pdn(pdev); + pdn->vfs_expanded = 0; + + total_vfs = pci_sriov_get_totalvfs(pdev); + pdn->m64_per_iov = 1; + mul = phb->ioda.total_pe; + + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + res = &pdev->resource[i + PCI_IOV_RESOURCES]; + if (!res->flags || res->parent) + continue; + if (!pnv_pci_is_mem_pref_64(res->flags)) { + dev_warn(&pdev->dev, " non M64 VF BAR%d: %pR\n", + i, res); + continue; + } + + size = pci_iov_resource_size(pdev, i + PCI_IOV_RESOURCES); + + /* bigger than 64M */ + if (size > (1 << 26)) { + dev_info(&pdev->dev, "PowerNV: VF BAR%d: %pR IOV size is bigger than 64M, roundup power2\n", + i, res); + pdn->m64_per_iov = M64_PER_IOV; + mul = roundup_pow_of_two(total_vfs); + break; + } + } + + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + res = &pdev->resource[i + PCI_IOV_RESOURCES]; + if (!res->flags || res->parent) + continue; + if (!pnv_pci_is_mem_pref_64(res->flags)) { + dev_warn(&pdev->dev, "Skipping expanding VF BAR%d: %pR\n", + i, res); + continue; + } + + dev_dbg(&pdev->dev, " Fixing VF BAR%d: %pR to\n", i, res); + size = pci_iov_resource_size(pdev, i + PCI_IOV_RESOURCES); + res->end = res->start + size * mul - 1; + dev_dbg(&pdev->dev, " %pR\n", res); + dev_info(&pdev->dev, "VF BAR%d: %pR (expanded to %d VFs for PE alignment)", + i, res, mul); + } + pdn->vfs_expanded = mul; +} +#endif /* CONFIG_PCI_IOV */ + /* * This function is supposed to be called on basis of PE from top * to bottom style. So the the I/O or MMIO segment assigned to @@ -1777,7 +2462,8 @@ static void pnv_ioda_setup_pe_seg(struct pci_controller *hose, region.start += phb->ioda.io_segsize; index++; } - } else if (res->flags & IORESOURCE_MEM) { + } else if ((res->flags & IORESOURCE_MEM) && + !pnv_pci_is_mem_pref_64(res->flags)) { region.start = res->start - hose->mem_offset[0] - phb->ioda.m32_pci_base; @@ -1907,10 +2593,29 @@ static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus, return phb->ioda.io_segsize; } +#ifdef CONFIG_PCI_IOV +static resource_size_t pnv_pci_iov_resource_alignment(struct pci_dev *pdev, + int resno) +{ + struct pci_dn *pdn = pci_get_pdn(pdev); + resource_size_t align, iov_align; + + iov_align = resource_size(&pdev->resource[resno]); + if (iov_align) + return iov_align; + + align = pci_iov_resource_size(pdev, resno); + if (pdn->vfs_expanded) + return pdn->vfs_expanded * align; + + return align; +} +#endif /* CONFIG_PCI_IOV */ + /* Prevent enabling devices for which we couldn't properly * assign a PE */ -static int pnv_pci_enable_device_hook(struct pci_dev *dev) +static bool pnv_pci_enable_device_hook(struct pci_dev *dev) { struct pci_controller *hose = pci_bus_to_host(dev->bus); struct pnv_phb *phb = hose->private_data; @@ -1922,13 +2627,13 @@ static int pnv_pci_enable_device_hook(struct pci_dev *dev) * PEs isn't ready. */ if (!phb->initialized) - return 0; + return true; pdn = pci_get_pdn(dev); if (!pdn || pdn->pe_number == IODA_INVALID_PE) - return -EINVAL; + return false; - return 0; + return true; } static u32 pnv_ioda_bdfn_to_pe(struct pnv_phb *phb, struct pci_bus *bus, @@ -1988,9 +2693,11 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, hose->last_busno = 0xff; } hose->private_data = phb; + hose->controller_ops = pnv_pci_controller_ops; phb->hub_id = hub_id; phb->opal_id = phb_id; phb->type = ioda_type; + mutex_init(&phb->ioda.pe_alloc_mutex); /* Detect specific models for error handling */ if (of_device_is_compatible(np, "ibm,p7ioc-pciex")) @@ -2050,6 +2757,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, INIT_LIST_HEAD(&phb->ioda.pe_dma_list); INIT_LIST_HEAD(&phb->ioda.pe_list); + mutex_init(&phb->ioda.pe_list_mutex); /* Calculate how many 32-bit TCE segments we have */ phb->ioda.tce32_count = phb->ioda.m32_pci_base >> 28; @@ -2078,9 +2786,6 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, phb->get_pe_state = pnv_ioda_get_pe_state; phb->freeze_pe = pnv_ioda_freeze_pe; phb->unfreeze_pe = pnv_ioda_unfreeze_pe; -#ifdef CONFIG_EEH - phb->eeh_ops = &ioda_eeh_ops; -#endif /* Setup RID -> PE mapping function */ phb->bdfn_to_pe = pnv_ioda_bdfn_to_pe; @@ -2104,9 +2809,15 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, * the child P2P bridges) can form individual PE. */ ppc_md.pcibios_fixup = pnv_pci_ioda_fixup; - ppc_md.pcibios_enable_device_hook = pnv_pci_enable_device_hook; - ppc_md.pcibios_window_alignment = pnv_pci_window_alignment; - ppc_md.pcibios_reset_secondary_bus = pnv_pci_reset_secondary_bus; + pnv_pci_controller_ops.enable_device_hook = pnv_pci_enable_device_hook; + pnv_pci_controller_ops.window_alignment = pnv_pci_window_alignment; + pnv_pci_controller_ops.reset_secondary_bus = pnv_pci_reset_secondary_bus; + +#ifdef CONFIG_PCI_IOV + ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov_resources; + ppc_md.pcibios_iov_resource_alignment = pnv_pci_iov_resource_alignment; +#endif + pci_add_flags(PCI_REASSIGN_ALL_RSRC); /* Reset IODA tables to a clean state */ @@ -2121,8 +2832,8 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, */ if (is_kdump_kernel()) { pr_info(" Issue PHB reset ...\n"); - ioda_eeh_phb_reset(hose, EEH_RESET_FUNDAMENTAL); - ioda_eeh_phb_reset(hose, EEH_RESET_DEACTIVATE); + pnv_eeh_phb_reset(hose, EEH_RESET_FUNDAMENTAL); + pnv_eeh_phb_reset(hose, EEH_RESET_DEACTIVATE); } /* Remove M64 resource if we can't configure it successfully */ diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c index 6ef6d4d8e7e2..4729ca793813 100644 --- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c +++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c @@ -133,6 +133,7 @@ static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id, phb->hose->first_busno = 0; phb->hose->last_busno = 0xff; phb->hose->private_data = phb; + phb->hose->controller_ops = pnv_pci_controller_ops; phb->hub_id = hub_id; phb->opal_id = phb_id; phb->type = PNV_PHB_P5IOC2; diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index e69142f4af08..bca2aeb6e4b6 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -366,9 +366,9 @@ static void pnv_pci_handle_eeh_config(struct pnv_phb *phb, u32 pe_no) spin_unlock_irqrestore(&phb->lock, flags); } -static void pnv_pci_config_check_eeh(struct pnv_phb *phb, - struct device_node *dn) +static void pnv_pci_config_check_eeh(struct pci_dn *pdn) { + struct pnv_phb *phb = pdn->phb->private_data; u8 fstate; __be16 pcierr; int pe_no; @@ -379,7 +379,7 @@ static void pnv_pci_config_check_eeh(struct pnv_phb *phb, * setup that yet. So all ER errors should be mapped to * reserved PE. */ - pe_no = PCI_DN(dn)->pe_number; + pe_no = pdn->pe_number; if (pe_no == IODA_INVALID_PE) { if (phb->type == PNV_PHB_P5IOC2) pe_no = 0; @@ -407,8 +407,7 @@ static void pnv_pci_config_check_eeh(struct pnv_phb *phb, } cfg_dbg(" -> EEH check, bdfn=%04x PE#%d fstate=%x\n", - (PCI_DN(dn)->busno << 8) | (PCI_DN(dn)->devfn), - pe_no, fstate); + (pdn->busno << 8) | (pdn->devfn), pe_no, fstate); /* Clear the frozen state if applicable */ if (fstate == OPAL_EEH_STOPPED_MMIO_FREEZE || @@ -425,10 +424,9 @@ static void pnv_pci_config_check_eeh(struct pnv_phb *phb, } } -int pnv_pci_cfg_read(struct device_node *dn, +int pnv_pci_cfg_read(struct pci_dn *pdn, int where, int size, u32 *val) { - struct pci_dn *pdn = PCI_DN(dn); struct pnv_phb *phb = pdn->phb->private_data; u32 bdfn = (pdn->busno << 8) | pdn->devfn; s64 rc; @@ -462,10 +460,9 @@ int pnv_pci_cfg_read(struct device_node *dn, return PCIBIOS_SUCCESSFUL; } -int pnv_pci_cfg_write(struct device_node *dn, +int pnv_pci_cfg_write(struct pci_dn *pdn, int where, int size, u32 val) { - struct pci_dn *pdn = PCI_DN(dn); struct pnv_phb *phb = pdn->phb->private_data; u32 bdfn = (pdn->busno << 8) | pdn->devfn; @@ -489,18 +486,17 @@ int pnv_pci_cfg_write(struct device_node *dn, } #if CONFIG_EEH -static bool pnv_pci_cfg_check(struct pci_controller *hose, - struct device_node *dn) +static bool pnv_pci_cfg_check(struct pci_dn *pdn) { struct eeh_dev *edev = NULL; - struct pnv_phb *phb = hose->private_data; + struct pnv_phb *phb = pdn->phb->private_data; /* EEH not enabled ? */ if (!(phb->flags & PNV_PHB_FLAG_EEH)) return true; /* PE reset or device removed ? */ - edev = of_node_to_eeh_dev(dn); + edev = pdn->edev; if (edev) { if (edev->pe && (edev->pe->state & EEH_PE_CFG_BLOCKED)) @@ -513,8 +509,7 @@ static bool pnv_pci_cfg_check(struct pci_controller *hose, return true; } #else -static inline pnv_pci_cfg_check(struct pci_controller *hose, - struct device_node *dn) +static inline pnv_pci_cfg_check(struct pci_dn *pdn) { return true; } @@ -524,32 +519,26 @@ static int pnv_pci_read_config(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val) { - struct device_node *dn, *busdn = pci_bus_to_OF_node(bus); struct pci_dn *pdn; struct pnv_phb *phb; - bool found = false; int ret; *val = 0xFFFFFFFF; - for (dn = busdn->child; dn; dn = dn->sibling) { - pdn = PCI_DN(dn); - if (pdn && pdn->devfn == devfn) { - phb = pdn->phb->private_data; - found = true; - break; - } - } + pdn = pci_get_pdn_by_devfn(bus, devfn); + if (!pdn) + return PCIBIOS_DEVICE_NOT_FOUND; - if (!found || !pnv_pci_cfg_check(pdn->phb, dn)) + if (!pnv_pci_cfg_check(pdn)) return PCIBIOS_DEVICE_NOT_FOUND; - ret = pnv_pci_cfg_read(dn, where, size, val); - if (phb->flags & PNV_PHB_FLAG_EEH) { + ret = pnv_pci_cfg_read(pdn, where, size, val); + phb = pdn->phb->private_data; + if (phb->flags & PNV_PHB_FLAG_EEH && pdn->edev) { if (*val == EEH_IO_ERROR_VALUE(size) && - eeh_dev_check_failure(of_node_to_eeh_dev(dn))) + eeh_dev_check_failure(pdn->edev)) return PCIBIOS_DEVICE_NOT_FOUND; } else { - pnv_pci_config_check_eeh(phb, dn); + pnv_pci_config_check_eeh(pdn); } return ret; @@ -559,27 +548,21 @@ static int pnv_pci_write_config(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 val) { - struct device_node *dn, *busdn = pci_bus_to_OF_node(bus); struct pci_dn *pdn; struct pnv_phb *phb; - bool found = false; int ret; - for (dn = busdn->child; dn; dn = dn->sibling) { - pdn = PCI_DN(dn); - if (pdn && pdn->devfn == devfn) { - phb = pdn->phb->private_data; - found = true; - break; - } - } + pdn = pci_get_pdn_by_devfn(bus, devfn); + if (!pdn) + return PCIBIOS_DEVICE_NOT_FOUND; - if (!found || !pnv_pci_cfg_check(pdn->phb, dn)) + if (!pnv_pci_cfg_check(pdn)) return PCIBIOS_DEVICE_NOT_FOUND; - ret = pnv_pci_cfg_write(dn, where, size, val); + ret = pnv_pci_cfg_write(pdn, where, size, val); + phb = pdn->phb->private_data; if (!(phb->flags & PNV_PHB_FLAG_EEH)) - pnv_pci_config_check_eeh(phb, dn); + pnv_pci_config_check_eeh(pdn); return ret; } @@ -679,66 +662,31 @@ void pnv_pci_setup_iommu_table(struct iommu_table *tbl, tbl->it_type = TCE_PCI; } -static struct iommu_table *pnv_pci_setup_bml_iommu(struct pci_controller *hose) -{ - struct iommu_table *tbl; - const __be64 *basep, *swinvp; - 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_PAGE_SHIFT_4K); - iommu_init_table(tbl, hose->node); - iommu_register_group(tbl, pci_domain_nr(hose->bus), 0); - - /* Deal with SW invalidated TCEs when needed (BML way) */ - swinvp = of_get_property(hose->dn, "linux,tce-sw-invalidate-info", - NULL); - if (swinvp) { - tbl->it_busno = be64_to_cpu(swinvp[1]); - tbl->it_index = (unsigned long)ioremap(be64_to_cpup(swinvp), 8); - tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE; - } - return tbl; -} - -static void 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_and_group(&pdev->dev, pdn->iommu_table); -} - static void 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; +#ifdef CONFIG_PCI_IOV + struct pnv_ioda_pe *pe; + struct pci_dn *pdn; + + /* Fix the VF pdn PE number */ + if (pdev->is_virtfn) { + pdn = pci_get_pdn(pdev); + WARN_ON(pdn->pe_number != IODA_INVALID_PE); + list_for_each_entry(pe, &phb->ioda.pe_list, list) { + if (pe->rid == ((pdev->bus->number << 8) | + (pdev->devfn & 0xff))) { + pdn->pe_number = pe->pe_number; + pe->pdev = pdev; + break; + } + } + } +#endif /* CONFIG_PCI_IOV */ - /* 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); } int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask) @@ -784,44 +732,36 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_IBM, 0x3b9, pnv_p7ioc_rc_quirk); void __init pnv_pci_init(void) { struct device_node *np; + bool found_ioda = false; pci_add_flags(PCI_CAN_SKIP_ISA_ALIGN); - /* 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 */ - } - /* OPAL is here, do our normal stuff */ - else { - int found_ioda = 0; + /* If we don't have OPAL, eg. in sim, just skip PCI probe */ + if (!firmware_has_feature(FW_FEATURE_OPAL)) + return; - /* Look for IODA IO-Hubs. We don't support mixing IODA - * and p5ioc2 due to the need to change some global - * probing flags - */ - for_each_compatible_node(np, NULL, "ibm,ioda-hub") { - pnv_pci_init_ioda_hub(np); - found_ioda = 1; - } + /* Look for IODA IO-Hubs. We don't support mixing IODA + * and p5ioc2 due to the need to change some global + * probing flags + */ + for_each_compatible_node(np, NULL, "ibm,ioda-hub") { + pnv_pci_init_ioda_hub(np); + found_ioda = true; + } - /* Look for p5ioc2 IO-Hubs */ - if (!found_ioda) - for_each_compatible_node(np, NULL, "ibm,p5ioc2") - pnv_pci_init_p5ioc2_hub(np); + /* Look for p5ioc2 IO-Hubs */ + if (!found_ioda) + for_each_compatible_node(np, NULL, "ibm,p5ioc2") + pnv_pci_init_p5ioc2_hub(np); - /* Look for ioda2 built-in PHB3's */ - for_each_compatible_node(np, NULL, "ibm,ioda2-phb") - pnv_pci_init_ioda2_phb(np); - } + /* Look for ioda2 built-in PHB3's */ + for_each_compatible_node(np, NULL, "ibm,ioda2-phb") + pnv_pci_init_ioda2_phb(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_vm; ppc_md.tce_free = pnv_tce_free_vm; ppc_md.tce_build_rm = pnv_tce_build_rm; @@ -836,30 +776,8 @@ void __init pnv_pci_init(void) #endif } -static int tce_iommu_bus_notifier(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct device *dev = data; - - switch (action) { - case BUS_NOTIFY_ADD_DEVICE: - return iommu_add_device(dev); - case BUS_NOTIFY_DEL_DEVICE: - if (dev->iommu_group) - iommu_del_device(dev); - return 0; - default: - return 0; - } -} +machine_subsys_initcall_sync(powernv, tce_iommu_bus_notifier_init); -static struct notifier_block tce_iommu_bus_nb = { - .notifier_call = tce_iommu_bus_notifier, +struct pci_controller_ops pnv_pci_controller_ops = { + .dma_dev_setup = pnv_pci_dma_dev_setup, }; - -static int __init tce_iommu_bus_notifier_init(void) -{ - bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb); - return 0; -} -machine_subsys_initcall_sync(powernv, tce_iommu_bus_notifier_init); diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index 6c02ff8dd69f..070ee888fc95 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -23,6 +23,7 @@ enum pnv_phb_model { #define PNV_IODA_PE_BUS_ALL (1 << 2) /* PE has subordinate buses */ #define PNV_IODA_PE_MASTER (1 << 3) /* Master PE in compound case */ #define PNV_IODA_PE_SLAVE (1 << 4) /* Slave PE in compound case */ +#define PNV_IODA_PE_VF (1 << 5) /* PE for one VF */ /* Data associated with a PE, including IOMMU tracking etc.. */ struct pnv_phb; @@ -34,6 +35,9 @@ struct pnv_ioda_pe { * entire bus (& children). In the former case, pdev * is populated, in the later case, pbus is. */ +#ifdef CONFIG_PCI_IOV + struct pci_dev *parent_dev; +#endif struct pci_dev *pdev; struct pci_bus *pbus; @@ -53,7 +57,7 @@ struct pnv_ioda_pe { /* "Base" iommu table, ie, 4K TCEs, 32-bit DMA */ int tce32_seg; int tce32_segcount; - struct iommu_table tce32_table; + struct iommu_table *tce32_table; phys_addr_t tce_inval_reg_phys; /* 64-bit TCE bypass region */ @@ -75,22 +79,6 @@ struct pnv_ioda_pe { struct list_head list; }; -/* IOC dependent EEH operations */ -#ifdef CONFIG_EEH -struct pnv_eeh_ops { - int (*post_init)(struct pci_controller *hose); - int (*set_option)(struct eeh_pe *pe, int option); - int (*get_state)(struct eeh_pe *pe); - int (*reset)(struct eeh_pe *pe, int option); - int (*get_log)(struct eeh_pe *pe, int severity, - char *drv_log, unsigned long len); - int (*configure_bridge)(struct eeh_pe *pe); - int (*err_inject)(struct eeh_pe *pe, int type, int func, - unsigned long addr, unsigned long mask); - int (*next_error)(struct eeh_pe **pe); -}; -#endif /* CONFIG_EEH */ - #define PNV_PHB_FLAG_EEH (1 << 0) struct pnv_phb { @@ -104,10 +92,6 @@ struct pnv_phb { int initialized; spinlock_t lock; -#ifdef CONFIG_EEH - struct pnv_eeh_ops *eeh_ops; -#endif - #ifdef CONFIG_DEBUG_FS int has_dbgfs; struct dentry *dbgfs; @@ -165,6 +149,8 @@ struct pnv_phb { /* PE allocation bitmap */ unsigned long *pe_alloc; + /* PE allocation mutex */ + struct mutex pe_alloc_mutex; /* M32 & IO segment maps */ unsigned int *m32_segmap; @@ -179,6 +165,7 @@ struct pnv_phb { * on the sequence of creation */ struct list_head pe_list; + struct mutex pe_list_mutex; /* Reverse map of PEs, will have to extend if * we are to support more than 256 PEs, indexed @@ -213,15 +200,12 @@ struct pnv_phb { }; extern struct pci_ops pnv_pci_ops; -#ifdef CONFIG_EEH -extern struct pnv_eeh_ops ioda_eeh_ops; -#endif void pnv_pci_dump_phb_diag_data(struct pci_controller *hose, unsigned char *log_buff); -int pnv_pci_cfg_read(struct device_node *dn, +int pnv_pci_cfg_read(struct pci_dn *pdn, int where, int size, u32 *val); -int pnv_pci_cfg_write(struct device_node *dn, +int pnv_pci_cfg_write(struct pci_dn *pdn, int where, int size, u32 val); extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl, void *tce_mem, u64 tce_size, @@ -232,6 +216,6 @@ extern void pnv_pci_init_ioda2_phb(struct device_node *np); extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl, __be64 *startp, __be64 *endp, bool rm); extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev); -extern int ioda_eeh_phb_reset(struct pci_controller *hose, int option); +extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option); #endif /* __POWERNV_PCI_H */ diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h index 604c48e7879a..826d2c9bea56 100644 --- a/arch/powerpc/platforms/powernv/powernv.h +++ b/arch/powerpc/platforms/powernv/powernv.h @@ -29,6 +29,8 @@ static inline u64 pnv_pci_dma_get_required_mask(struct pci_dev *pdev) } #endif +extern struct pci_controller_ops pnv_pci_controller_ops; + extern u32 pnv_get_supported_cpuidle_states(void); extern void pnv_lpc_init(void); diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index d2de7d5d7574..16fdcb23f4c3 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -32,7 +32,6 @@ #include <asm/machdep.h> #include <asm/firmware.h> #include <asm/xics.h> -#include <asm/rtas.h> #include <asm/opal.h> #include <asm/kexec.h> #include <asm/smp.h> @@ -278,20 +277,6 @@ static void __init pnv_setup_machdep_opal(void) ppc_md.handle_hmi_exception = opal_handle_hmi_exception; } -#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; - pm_power_off = rtas_power_off; - ppc_md.halt = rtas_halt; -} -#endif /* CONFIG_PPC_POWERNV_RTAS */ - static u32 supported_cpuidle_states; int pnv_save_sprs_for_winkle(void) @@ -409,37 +394,39 @@ static int __init pnv_init_idle_states(void) { struct device_node *power_mgt; int dt_idle_states; - const __be32 *idle_state_flags; - u32 len_flags, flags; + u32 *flags; int i; supported_cpuidle_states = 0; if (cpuidle_disable != IDLE_NO_OVERRIDE) - return 0; + goto out; if (!firmware_has_feature(FW_FEATURE_OPALv3)) - return 0; + goto out; power_mgt = of_find_node_by_path("/ibm,opal/power-mgt"); if (!power_mgt) { pr_warn("opal: PowerMgmt Node not found\n"); - return 0; + goto out; + } + dt_idle_states = of_property_count_u32_elems(power_mgt, + "ibm,cpu-idle-state-flags"); + if (dt_idle_states < 0) { + pr_warn("cpuidle-powernv: no idle states found in the DT\n"); + goto out; } - idle_state_flags = of_get_property(power_mgt, - "ibm,cpu-idle-state-flags", &len_flags); - if (!idle_state_flags) { - pr_warn("DT-PowerMgmt: missing ibm,cpu-idle-state-flags\n"); - return 0; + flags = kzalloc(sizeof(*flags) * dt_idle_states, GFP_KERNEL); + if (of_property_read_u32_array(power_mgt, + "ibm,cpu-idle-state-flags", flags, dt_idle_states)) { + pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-flags in DT\n"); + goto out_free; } - dt_idle_states = len_flags / sizeof(u32); + for (i = 0; i < dt_idle_states; i++) + supported_cpuidle_states |= flags[i]; - for (i = 0; i < dt_idle_states; i++) { - flags = be32_to_cpu(idle_state_flags[i]); - supported_cpuidle_states |= flags; - } if (!(supported_cpuidle_states & OPAL_PM_SLEEP_ENABLED_ER1)) { patch_instruction( (unsigned int *)pnv_fastsleep_workaround_at_entry, @@ -449,6 +436,9 @@ static int __init pnv_init_idle_states(void) PPC_INST_NOP); } pnv_alloc_idle_core_states(); +out_free: + kfree(flags); +out: return 0; } @@ -465,10 +455,6 @@ static int __init pnv_probe(void) 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"); diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index fc34025ef822..8f70ba681a78 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -25,7 +25,6 @@ #include <asm/machdep.h> #include <asm/cputable.h> #include <asm/firmware.h> -#include <asm/rtas.h> #include <asm/vdso_datapage.h> #include <asm/cputhreads.h> #include <asm/xics.h> @@ -33,6 +32,8 @@ #include <asm/runlatch.h> #include <asm/code-patching.h> #include <asm/dbell.h> +#include <asm/kvm_ppc.h> +#include <asm/ppc-opcode.h> #include "powernv.h" @@ -149,7 +150,7 @@ static int pnv_smp_cpu_disable(void) static void pnv_smp_cpu_kill_self(void) { unsigned int cpu; - unsigned long srr1; + unsigned long srr1, wmask; u32 idle_states; /* Standard hot unplug procedure */ @@ -161,6 +162,10 @@ static void pnv_smp_cpu_kill_self(void) generic_set_cpu_dead(cpu); smp_wmb(); + wmask = SRR1_WAKEMASK; + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + wmask = SRR1_WAKEMASK_P8; + idle_states = pnv_get_supported_cpuidle_states(); /* We don't want to take decrementer interrupts while we are offline, * so clear LPCR:PECE1. We keep PECE2 enabled. @@ -191,10 +196,14 @@ static void pnv_smp_cpu_kill_self(void) * having finished executing in a KVM guest, then srr1 * contains 0. */ - if ((srr1 & SRR1_WAKEMASK) == SRR1_WAKEEE) { + if ((srr1 & wmask) == SRR1_WAKEEE) { icp_native_flush_interrupt(); local_paca->irq_happened &= PACA_IRQ_HARD_DIS; smp_mb(); + } else if ((srr1 & wmask) == SRR1_WAKEHDBELL) { + unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER); + asm volatile(PPC_MSGCLR(%0) : : "r" (msg)); + kvmppc_set_host_ipi(cpu, 0); } if (cpu_core_split_required()) @@ -241,18 +250,6 @@ 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 diff --git a/arch/powerpc/platforms/ps3/smp.c b/arch/powerpc/platforms/ps3/smp.c index b358bec6c8cb..3c7707af3384 100644 --- a/arch/powerpc/platforms/ps3/smp.c +++ b/arch/powerpc/platforms/ps3/smp.c @@ -57,7 +57,7 @@ static void ps3_smp_message_pass(int cpu, int msg) " (%d)\n", __func__, __LINE__, cpu, msg, result); } -static int __init ps3_smp_probe(void) +static void __init ps3_smp_probe(void) { int cpu; @@ -100,8 +100,6 @@ static int __init ps3_smp_probe(void) DBG(" <- %s:%d: (%d)\n", __func__, __LINE__, cpu); } - - return 2; } void ps3_smp_cleanup_cpu(int cpu) diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index a758a9c3bbba..54c87d5d349d 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -16,7 +16,6 @@ config PPC_PSERIES select PPC_UDBG_16550 select PPC_NATIVE select PPC_PCI_CHOICE if EXPERT - select ZLIB_DEFLATE select PPC_DOORBELL select HAVE_CONTEXT_TRACKING select HOTPLUG_CPU if SMP diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index c22bb1b4beb8..b4b11096ea8b 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -10,6 +10,8 @@ * 2 as published by the Free Software Foundation. */ +#define pr_fmt(fmt) "dlpar: " fmt + #include <linux/kernel.h> #include <linux/notifier.h> #include <linux/spinlock.h> @@ -535,13 +537,125 @@ static ssize_t dlpar_cpu_release(const char *buf, size_t count) return count; } +#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ + +static int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog) +{ + int rc; + + /* pseries error logs are in BE format, convert to cpu type */ + switch (hp_elog->id_type) { + case PSERIES_HP_ELOG_ID_DRC_COUNT: + hp_elog->_drc_u.drc_count = + be32_to_cpu(hp_elog->_drc_u.drc_count); + break; + case PSERIES_HP_ELOG_ID_DRC_INDEX: + hp_elog->_drc_u.drc_index = + be32_to_cpu(hp_elog->_drc_u.drc_index); + } + + switch (hp_elog->resource) { + case PSERIES_HP_ELOG_RESOURCE_MEM: + rc = dlpar_memory(hp_elog); + break; + default: + pr_warn_ratelimited("Invalid resource (%d) specified\n", + hp_elog->resource); + rc = -EINVAL; + } + + return rc; +} + +static ssize_t dlpar_store(struct class *class, struct class_attribute *attr, + const char *buf, size_t count) +{ + struct pseries_hp_errorlog *hp_elog; + const char *arg; + int rc; + + hp_elog = kzalloc(sizeof(*hp_elog), GFP_KERNEL); + if (!hp_elog) { + rc = -ENOMEM; + goto dlpar_store_out; + } + + /* Parse out the request from the user, this will be in the form + * <resource> <action> <id_type> <id> + */ + arg = buf; + if (!strncmp(arg, "memory", 6)) { + hp_elog->resource = PSERIES_HP_ELOG_RESOURCE_MEM; + arg += strlen("memory "); + } else { + pr_err("Invalid resource specified: \"%s\"\n", buf); + rc = -EINVAL; + goto dlpar_store_out; + } + + if (!strncmp(arg, "add", 3)) { + hp_elog->action = PSERIES_HP_ELOG_ACTION_ADD; + arg += strlen("add "); + } else if (!strncmp(arg, "remove", 6)) { + hp_elog->action = PSERIES_HP_ELOG_ACTION_REMOVE; + arg += strlen("remove "); + } else { + pr_err("Invalid action specified: \"%s\"\n", buf); + rc = -EINVAL; + goto dlpar_store_out; + } + + if (!strncmp(arg, "index", 5)) { + u32 index; + + hp_elog->id_type = PSERIES_HP_ELOG_ID_DRC_INDEX; + arg += strlen("index "); + if (kstrtou32(arg, 0, &index)) { + rc = -EINVAL; + pr_err("Invalid drc_index specified: \"%s\"\n", buf); + goto dlpar_store_out; + } + + hp_elog->_drc_u.drc_index = cpu_to_be32(index); + } else if (!strncmp(arg, "count", 5)) { + u32 count; + + hp_elog->id_type = PSERIES_HP_ELOG_ID_DRC_COUNT; + arg += strlen("count "); + if (kstrtou32(arg, 0, &count)) { + rc = -EINVAL; + pr_err("Invalid count specified: \"%s\"\n", buf); + goto dlpar_store_out; + } + + hp_elog->_drc_u.drc_count = cpu_to_be32(count); + } else { + pr_err("Invalid id_type specified: \"%s\"\n", buf); + rc = -EINVAL; + goto dlpar_store_out; + } + + rc = handle_dlpar_errorlog(hp_elog); + +dlpar_store_out: + kfree(hp_elog); + return rc ? rc : count; +} + +static CLASS_ATTR(dlpar, S_IWUSR, NULL, dlpar_store); + static int __init pseries_dlpar_init(void) { + int rc; + +#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE ppc_md.cpu_probe = dlpar_cpu_probe; ppc_md.cpu_release = dlpar_cpu_release; +#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ - return 0; + rc = sysfs_create_file(kernel_kobj, &class_attr_dlpar.attr); + + return rc; } machine_device_initcall(pseries, pseries_dlpar_init); -#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index a6c7e19f5eb3..2039397cc75d 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -118,9 +118,8 @@ static int pseries_eeh_init(void) return 0; } -static int pseries_eeh_cap_start(struct device_node *dn) +static int pseries_eeh_cap_start(struct pci_dn *pdn) { - struct pci_dn *pdn = PCI_DN(dn); u32 status; if (!pdn) @@ -134,10 +133,9 @@ static int pseries_eeh_cap_start(struct device_node *dn) } -static int pseries_eeh_find_cap(struct device_node *dn, int cap) +static int pseries_eeh_find_cap(struct pci_dn *pdn, int cap) { - struct pci_dn *pdn = PCI_DN(dn); - int pos = pseries_eeh_cap_start(dn); + int pos = pseries_eeh_cap_start(pdn); int cnt = 48; /* Maximal number of capabilities */ u32 id; @@ -160,10 +158,9 @@ static int pseries_eeh_find_cap(struct device_node *dn, int cap) return 0; } -static int pseries_eeh_find_ecap(struct device_node *dn, int cap) +static int pseries_eeh_find_ecap(struct pci_dn *pdn, int cap) { - struct pci_dn *pdn = PCI_DN(dn); - struct eeh_dev *edev = of_node_to_eeh_dev(dn); + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); u32 header; int pos = 256; int ttl = (4096 - 256) / 8; @@ -191,53 +188,44 @@ static int pseries_eeh_find_ecap(struct device_node *dn, int cap) } /** - * pseries_eeh_of_probe - EEH probe on the given device - * @dn: OF node - * @flag: Unused + * pseries_eeh_probe - EEH probe on the given device + * @pdn: PCI device node + * @data: Unused * * When EEH module is installed during system boot, all PCI devices * are checked one by one to see if it supports EEH. The function * is introduced for the purpose. */ -static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) +static void *pseries_eeh_probe(struct pci_dn *pdn, void *data) { struct eeh_dev *edev; struct eeh_pe pe; - struct pci_dn *pdn = PCI_DN(dn); - const __be32 *classp, *vendorp, *devicep; - u32 class_code; - const __be32 *regs; u32 pcie_flags; int enable = 0; int ret; /* Retrieve OF node and eeh device */ - edev = of_node_to_eeh_dev(dn); - if (edev->pe || !of_device_is_available(dn)) + edev = pdn_to_eeh_dev(pdn); + if (!edev || edev->pe) return NULL; - /* Retrieve class/vendor/device IDs */ - classp = of_get_property(dn, "class-code", NULL); - vendorp = of_get_property(dn, "vendor-id", NULL); - devicep = of_get_property(dn, "device-id", NULL); - - /* Skip for bad OF node or PCI-ISA bridge */ - if (!classp || !vendorp || !devicep) - return NULL; - if (dn->type && !strcmp(dn->type, "isa")) + /* Check class/vendor/device IDs */ + if (!pdn->vendor_id || !pdn->device_id || !pdn->class_code) return NULL; - class_code = of_read_number(classp, 1); + /* Skip for PCI-ISA bridge */ + if ((pdn->class_code >> 8) == PCI_CLASS_BRIDGE_ISA) + return NULL; /* * Update class code and mode of eeh device. We need * correctly reflects that current device is root port * or PCIe switch downstream port. */ - edev->class_code = class_code; - edev->pcix_cap = pseries_eeh_find_cap(dn, PCI_CAP_ID_PCIX); - edev->pcie_cap = pseries_eeh_find_cap(dn, PCI_CAP_ID_EXP); - edev->aer_cap = pseries_eeh_find_ecap(dn, PCI_EXT_CAP_ID_ERR); + edev->class_code = pdn->class_code; + edev->pcix_cap = pseries_eeh_find_cap(pdn, PCI_CAP_ID_PCIX); + edev->pcie_cap = pseries_eeh_find_cap(pdn, PCI_CAP_ID_EXP); + edev->aer_cap = pseries_eeh_find_ecap(pdn, PCI_EXT_CAP_ID_ERR); edev->mode &= 0xFFFFFF00; if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) { edev->mode |= EEH_DEV_BRIDGE; @@ -252,24 +240,16 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) } } - /* Retrieve the device address */ - regs = of_get_property(dn, "reg", NULL); - if (!regs) { - pr_warn("%s: OF node property %s::reg not found\n", - __func__, dn->full_name); - return NULL; - } - /* Initialize the fake PE */ memset(&pe, 0, sizeof(struct eeh_pe)); pe.phb = edev->phb; - pe.config_addr = of_read_number(regs, 1); + pe.config_addr = (pdn->busno << 16) | (pdn->devfn << 8); /* Enable EEH on the device */ ret = eeh_ops->set_option(&pe, EEH_OPT_ENABLE); if (!ret) { - edev->config_addr = of_read_number(regs, 1); /* Retrieve PE address */ + edev->config_addr = (pdn->busno << 16) | (pdn->devfn << 8); edev->pe_config_addr = eeh_ops->get_pe_addr(&pe); pe.addr = edev->pe_config_addr; @@ -285,16 +265,17 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) eeh_add_flag(EEH_ENABLED); eeh_add_to_parent_pe(edev); - pr_debug("%s: EEH enabled on %s PHB#%d-PE#%x, config addr#%x\n", - __func__, dn->full_name, pe.phb->global_number, - pe.addr, pe.config_addr); - } else if (dn->parent && of_node_to_eeh_dev(dn->parent) && - (of_node_to_eeh_dev(dn->parent))->pe) { + pr_debug("%s: EEH enabled on %02x:%02x.%01x PHB#%d-PE#%x\n", + __func__, pdn->busno, PCI_SLOT(pdn->devfn), + PCI_FUNC(pdn->devfn), pe.phb->global_number, + pe.addr); + } else if (pdn->parent && pdn_to_eeh_dev(pdn->parent) && + (pdn_to_eeh_dev(pdn->parent))->pe) { /* This device doesn't support EEH, but it may have an * EEH parent, in which case we mark it as supported. */ - edev->config_addr = of_node_to_eeh_dev(dn->parent)->config_addr; - edev->pe_config_addr = of_node_to_eeh_dev(dn->parent)->pe_config_addr; + edev->config_addr = pdn_to_eeh_dev(pdn->parent)->config_addr; + edev->pe_config_addr = pdn_to_eeh_dev(pdn->parent)->pe_config_addr; eeh_add_to_parent_pe(edev); } } @@ -670,45 +651,36 @@ static int pseries_eeh_configure_bridge(struct eeh_pe *pe) /** * pseries_eeh_read_config - Read PCI config space - * @dn: device node + * @pdn: PCI device node * @where: PCI address * @size: size to read * @val: return value * * Read config space from the speicifed device */ -static int pseries_eeh_read_config(struct device_node *dn, int where, int size, u32 *val) +static int pseries_eeh_read_config(struct pci_dn *pdn, int where, int size, u32 *val) { - struct pci_dn *pdn; - - pdn = PCI_DN(dn); - return rtas_read_config(pdn, where, size, val); } /** * pseries_eeh_write_config - Write PCI config space - * @dn: device node + * @pdn: PCI device node * @where: PCI address * @size: size to write * @val: value to be written * * Write config space to the specified device */ -static int pseries_eeh_write_config(struct device_node *dn, int where, int size, u32 val) +static int pseries_eeh_write_config(struct pci_dn *pdn, int where, int size, u32 val) { - struct pci_dn *pdn; - - pdn = PCI_DN(dn); - return rtas_write_config(pdn, where, size, val); } static struct eeh_ops pseries_eeh_ops = { .name = "pseries", .init = pseries_eeh_init, - .of_probe = pseries_eeh_of_probe, - .dev_probe = NULL, + .probe = pseries_eeh_probe, .set_option = pseries_eeh_set_option, .get_pe_addr = pseries_eeh_get_pe_addr, .get_state = pseries_eeh_get_state, diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index fa41f0da5b6f..0ced387e1463 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -9,11 +9,14 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) "pseries-hotplug-mem: " fmt + #include <linux/of.h> #include <linux/of_address.h> #include <linux/memblock.h> #include <linux/memory.h> #include <linux/memory_hotplug.h> +#include <linux/slab.h> #include <asm/firmware.h> #include <asm/machdep.h> @@ -21,6 +24,8 @@ #include <asm/sparsemem.h> #include "pseries.h" +static bool rtas_hp_event; + unsigned long pseries_memory_block_size(void) { struct device_node *np; @@ -64,6 +69,67 @@ unsigned long pseries_memory_block_size(void) return memblock_size; } +static void dlpar_free_drconf_property(struct property *prop) +{ + kfree(prop->name); + kfree(prop->value); + kfree(prop); +} + +static struct property *dlpar_clone_drconf_property(struct device_node *dn) +{ + struct property *prop, *new_prop; + struct of_drconf_cell *lmbs; + u32 num_lmbs, *p; + int i; + + prop = of_find_property(dn, "ibm,dynamic-memory", NULL); + if (!prop) + return NULL; + + new_prop = kzalloc(sizeof(*new_prop), GFP_KERNEL); + if (!new_prop) + return NULL; + + new_prop->name = kstrdup(prop->name, GFP_KERNEL); + new_prop->value = kmalloc(prop->length, GFP_KERNEL); + if (!new_prop->name || !new_prop->value) { + dlpar_free_drconf_property(new_prop); + return NULL; + } + + memcpy(new_prop->value, prop->value, prop->length); + new_prop->length = prop->length; + + /* Convert the property to cpu endian-ness */ + p = new_prop->value; + *p = be32_to_cpu(*p); + + num_lmbs = *p++; + lmbs = (struct of_drconf_cell *)p; + + for (i = 0; i < num_lmbs; i++) { + lmbs[i].base_addr = be64_to_cpu(lmbs[i].base_addr); + lmbs[i].drc_index = be32_to_cpu(lmbs[i].drc_index); + lmbs[i].flags = be32_to_cpu(lmbs[i].flags); + } + + return new_prop; +} + +static struct memory_block *lmb_to_memblock(struct of_drconf_cell *lmb) +{ + unsigned long section_nr; + struct mem_section *mem_sect; + struct memory_block *mem_block; + + section_nr = pfn_to_section_nr(PFN_DOWN(lmb->base_addr)); + mem_sect = __nr_to_section(section_nr); + + mem_block = find_memory_block(mem_sect); + return mem_block; +} + #ifdef CONFIG_MEMORY_HOTREMOVE static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size) { @@ -122,6 +188,173 @@ static int pseries_remove_mem_node(struct device_node *np) pseries_remove_memblock(base, lmb_size); return 0; } + +static bool lmb_is_removable(struct of_drconf_cell *lmb) +{ + int i, scns_per_block; + int rc = 1; + unsigned long pfn, block_sz; + u64 phys_addr; + + if (!(lmb->flags & DRCONF_MEM_ASSIGNED)) + return false; + + block_sz = memory_block_size_bytes(); + scns_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE; + phys_addr = lmb->base_addr; + + for (i = 0; i < scns_per_block; i++) { + pfn = PFN_DOWN(phys_addr); + if (!pfn_present(pfn)) + continue; + + rc &= is_mem_section_removable(pfn, PAGES_PER_SECTION); + phys_addr += MIN_MEMORY_BLOCK_SIZE; + } + + return rc ? true : false; +} + +static int dlpar_add_lmb(struct of_drconf_cell *); + +static int dlpar_remove_lmb(struct of_drconf_cell *lmb) +{ + struct memory_block *mem_block; + unsigned long block_sz; + int nid, rc; + + if (!lmb_is_removable(lmb)) + return -EINVAL; + + mem_block = lmb_to_memblock(lmb); + if (!mem_block) + return -EINVAL; + + rc = device_offline(&mem_block->dev); + put_device(&mem_block->dev); + if (rc) + return rc; + + block_sz = pseries_memory_block_size(); + nid = memory_add_physaddr_to_nid(lmb->base_addr); + + remove_memory(nid, lmb->base_addr, block_sz); + + /* Update memory regions for memory remove */ + memblock_remove(lmb->base_addr, block_sz); + + dlpar_release_drc(lmb->drc_index); + + lmb->flags &= ~DRCONF_MEM_ASSIGNED; + return 0; +} + +static int dlpar_memory_remove_by_count(u32 lmbs_to_remove, + struct property *prop) +{ + struct of_drconf_cell *lmbs; + int lmbs_removed = 0; + int lmbs_available = 0; + u32 num_lmbs, *p; + int i, rc; + + pr_info("Attempting to hot-remove %d LMB(s)\n", lmbs_to_remove); + + if (lmbs_to_remove == 0) + return -EINVAL; + + p = prop->value; + num_lmbs = *p++; + lmbs = (struct of_drconf_cell *)p; + + /* Validate that there are enough LMBs to satisfy the request */ + for (i = 0; i < num_lmbs; i++) { + if (lmbs[i].flags & DRCONF_MEM_ASSIGNED) + lmbs_available++; + } + + if (lmbs_available < lmbs_to_remove) + return -EINVAL; + + for (i = 0; i < num_lmbs && lmbs_removed < lmbs_to_remove; i++) { + rc = dlpar_remove_lmb(&lmbs[i]); + if (rc) + continue; + + lmbs_removed++; + + /* Mark this lmb so we can add it later if all of the + * requested LMBs cannot be removed. + */ + lmbs[i].reserved = 1; + } + + if (lmbs_removed != lmbs_to_remove) { + pr_err("Memory hot-remove failed, adding LMB's back\n"); + + for (i = 0; i < num_lmbs; i++) { + if (!lmbs[i].reserved) + continue; + + rc = dlpar_add_lmb(&lmbs[i]); + if (rc) + pr_err("Failed to add LMB back, drc index %x\n", + lmbs[i].drc_index); + + lmbs[i].reserved = 0; + } + + rc = -EINVAL; + } else { + for (i = 0; i < num_lmbs; i++) { + if (!lmbs[i].reserved) + continue; + + pr_info("Memory at %llx was hot-removed\n", + lmbs[i].base_addr); + + lmbs[i].reserved = 0; + } + rc = 0; + } + + return rc; +} + +static int dlpar_memory_remove_by_index(u32 drc_index, struct property *prop) +{ + struct of_drconf_cell *lmbs; + u32 num_lmbs, *p; + int lmb_found; + int i, rc; + + pr_info("Attempting to hot-remove LMB, drc index %x\n", drc_index); + + p = prop->value; + num_lmbs = *p++; + lmbs = (struct of_drconf_cell *)p; + + lmb_found = 0; + for (i = 0; i < num_lmbs; i++) { + if (lmbs[i].drc_index == drc_index) { + lmb_found = 1; + rc = dlpar_remove_lmb(&lmbs[i]); + break; + } + } + + if (!lmb_found) + rc = -EINVAL; + + if (rc) + pr_info("Failed to hot-remove memory at %llx\n", + lmbs[i].base_addr); + else + pr_info("Memory at %llx was hot-removed\n", lmbs[i].base_addr); + + return rc; +} + #else static inline int pseries_remove_memblock(unsigned long base, unsigned int memblock_size) @@ -132,8 +365,261 @@ static inline int pseries_remove_mem_node(struct device_node *np) { return 0; } +static inline int dlpar_memory_remove(struct pseries_hp_errorlog *hp_elog) +{ + return -EOPNOTSUPP; +} +static int dlpar_remove_lmb(struct of_drconf_cell *lmb) +{ + return -EOPNOTSUPP; +} +static int dlpar_memory_remove_by_count(u32 lmbs_to_remove, + struct property *prop) +{ + return -EOPNOTSUPP; +} +static int dlpar_memory_remove_by_index(u32 drc_index, struct property *prop) +{ + return -EOPNOTSUPP; +} + #endif /* CONFIG_MEMORY_HOTREMOVE */ +static int dlpar_add_lmb(struct of_drconf_cell *lmb) +{ + struct memory_block *mem_block; + unsigned long block_sz; + int nid, rc; + + if (lmb->flags & DRCONF_MEM_ASSIGNED) + return -EINVAL; + + block_sz = memory_block_size_bytes(); + + rc = dlpar_acquire_drc(lmb->drc_index); + if (rc) + return rc; + + /* Find the node id for this address */ + nid = memory_add_physaddr_to_nid(lmb->base_addr); + + /* Add the memory */ + rc = add_memory(nid, lmb->base_addr, block_sz); + if (rc) { + dlpar_release_drc(lmb->drc_index); + return rc; + } + + /* Register this block of memory */ + rc = memblock_add(lmb->base_addr, block_sz); + if (rc) { + remove_memory(nid, lmb->base_addr, block_sz); + dlpar_release_drc(lmb->drc_index); + return rc; + } + + mem_block = lmb_to_memblock(lmb); + if (!mem_block) { + remove_memory(nid, lmb->base_addr, block_sz); + dlpar_release_drc(lmb->drc_index); + return -EINVAL; + } + + rc = device_online(&mem_block->dev); + put_device(&mem_block->dev); + if (rc) { + remove_memory(nid, lmb->base_addr, block_sz); + dlpar_release_drc(lmb->drc_index); + return rc; + } + + lmb->flags |= DRCONF_MEM_ASSIGNED; + return 0; +} + +static int dlpar_memory_add_by_count(u32 lmbs_to_add, struct property *prop) +{ + struct of_drconf_cell *lmbs; + u32 num_lmbs, *p; + int lmbs_available = 0; + int lmbs_added = 0; + int i, rc; + + pr_info("Attempting to hot-add %d LMB(s)\n", lmbs_to_add); + + if (lmbs_to_add == 0) + return -EINVAL; + + p = prop->value; + num_lmbs = *p++; + lmbs = (struct of_drconf_cell *)p; + + /* Validate that there are enough LMBs to satisfy the request */ + for (i = 0; i < num_lmbs; i++) { + if (!(lmbs[i].flags & DRCONF_MEM_ASSIGNED)) + lmbs_available++; + } + + if (lmbs_available < lmbs_to_add) + return -EINVAL; + + for (i = 0; i < num_lmbs && lmbs_to_add != lmbs_added; i++) { + rc = dlpar_add_lmb(&lmbs[i]); + if (rc) + continue; + + lmbs_added++; + + /* Mark this lmb so we can remove it later if all of the + * requested LMBs cannot be added. + */ + lmbs[i].reserved = 1; + } + + if (lmbs_added != lmbs_to_add) { + pr_err("Memory hot-add failed, removing any added LMBs\n"); + + for (i = 0; i < num_lmbs; i++) { + if (!lmbs[i].reserved) + continue; + + rc = dlpar_remove_lmb(&lmbs[i]); + if (rc) + pr_err("Failed to remove LMB, drc index %x\n", + be32_to_cpu(lmbs[i].drc_index)); + } + rc = -EINVAL; + } else { + for (i = 0; i < num_lmbs; i++) { + if (!lmbs[i].reserved) + continue; + + pr_info("Memory at %llx (drc index %x) was hot-added\n", + lmbs[i].base_addr, lmbs[i].drc_index); + lmbs[i].reserved = 0; + } + } + + return rc; +} + +static int dlpar_memory_add_by_index(u32 drc_index, struct property *prop) +{ + struct of_drconf_cell *lmbs; + u32 num_lmbs, *p; + int i, lmb_found; + int rc; + + pr_info("Attempting to hot-add LMB, drc index %x\n", drc_index); + + p = prop->value; + num_lmbs = *p++; + lmbs = (struct of_drconf_cell *)p; + + lmb_found = 0; + for (i = 0; i < num_lmbs; i++) { + if (lmbs[i].drc_index == drc_index) { + lmb_found = 1; + rc = dlpar_add_lmb(&lmbs[i]); + break; + } + } + + if (!lmb_found) + rc = -EINVAL; + + if (rc) + pr_info("Failed to hot-add memory, drc index %x\n", drc_index); + else + pr_info("Memory at %llx (drc index %x) was hot-added\n", + lmbs[i].base_addr, drc_index); + + return rc; +} + +static void dlpar_update_drconf_property(struct device_node *dn, + struct property *prop) +{ + struct of_drconf_cell *lmbs; + u32 num_lmbs, *p; + int i; + + /* Convert the property back to BE */ + p = prop->value; + num_lmbs = *p; + *p = cpu_to_be32(*p); + p++; + + lmbs = (struct of_drconf_cell *)p; + for (i = 0; i < num_lmbs; i++) { + lmbs[i].base_addr = cpu_to_be64(lmbs[i].base_addr); + lmbs[i].drc_index = cpu_to_be32(lmbs[i].drc_index); + lmbs[i].flags = cpu_to_be32(lmbs[i].flags); + } + + rtas_hp_event = true; + of_update_property(dn, prop); + rtas_hp_event = false; +} + +int dlpar_memory(struct pseries_hp_errorlog *hp_elog) +{ + struct device_node *dn; + struct property *prop; + u32 count, drc_index; + int rc; + + count = hp_elog->_drc_u.drc_count; + drc_index = hp_elog->_drc_u.drc_index; + + lock_device_hotplug(); + + dn = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); + if (!dn) { + rc = -EINVAL; + goto dlpar_memory_out; + } + + prop = dlpar_clone_drconf_property(dn); + if (!prop) { + rc = -EINVAL; + goto dlpar_memory_out; + } + + switch (hp_elog->action) { + case PSERIES_HP_ELOG_ACTION_ADD: + if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_COUNT) + rc = dlpar_memory_add_by_count(count, prop); + else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX) + rc = dlpar_memory_add_by_index(drc_index, prop); + else + rc = -EINVAL; + break; + case PSERIES_HP_ELOG_ACTION_REMOVE: + if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_COUNT) + rc = dlpar_memory_remove_by_count(count, prop); + else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX) + rc = dlpar_memory_remove_by_index(drc_index, prop); + else + rc = -EINVAL; + break; + default: + pr_err("Invalid action (%d) specified\n", hp_elog->action); + rc = -EINVAL; + break; + } + + if (rc) + dlpar_free_drconf_property(prop); + else + dlpar_update_drconf_property(dn, prop); + +dlpar_memory_out: + of_node_put(dn); + unlock_device_hotplug(); + return rc; +} + static int pseries_add_mem_node(struct device_node *np) { const char *type; @@ -174,6 +660,9 @@ static int pseries_update_drconf_memory(struct of_reconfig_data *pr) __be32 *p; int i, rc = -EINVAL; + if (rtas_hp_event) + return 0; + memblock_size = pseries_memory_block_size(); if (!memblock_size) return -EINVAL; diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index ccd53f91e8aa..74b5b8e239c8 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -7,12 +7,12 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ +#include <linux/jump_label.h> #include <asm/hvcall.h> #include <asm/processor.h> #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> #include <asm/ptrace.h> -#include <asm/jump_label.h> .section ".text" diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 1d3d52dc3ff3..61d5a17f45c0 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -49,6 +49,7 @@ #include <asm/mmzone.h> #include <asm/plpar_wrappers.h> +#include "pseries.h" static void tce_invalidate_pSeries_sw(struct iommu_table *tbl, __be64 *startp, __be64 *endp) @@ -1307,16 +1308,16 @@ void iommu_init_early_pSeries(void) ppc_md.tce_free = tce_free_pSeriesLP; } ppc_md.tce_get = tce_get_pSeriesLP; - ppc_md.pci_dma_bus_setup = pci_dma_bus_setup_pSeriesLP; - ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_pSeriesLP; + pseries_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pSeriesLP; + pseries_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pSeriesLP; ppc_md.dma_set_mask = dma_set_mask_pSeriesLP; ppc_md.dma_get_required_mask = dma_get_required_mask_pSeriesLP; } else { ppc_md.tce_build = tce_build_pSeries; ppc_md.tce_free = tce_free_pSeries; ppc_md.tce_get = tce_get_pseries; - ppc_md.pci_dma_bus_setup = pci_dma_bus_setup_pSeries; - ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_pSeries; + pseries_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pSeries; + pseries_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pSeries; } @@ -1340,3 +1341,5 @@ static int __init disable_multitce(char *str) } __setup("multitce=", disable_multitce); + +machine_subsys_initcall_sync(pseries, tce_iommu_bus_notifier_init); diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index b5682fd6c984..b7a67e3d2201 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -26,7 +26,7 @@ #include <linux/dma-mapping.h> #include <linux/console.h> #include <linux/export.h> -#include <linux/static_key.h> +#include <linux/jump_label.h> #include <asm/processor.h> #include <asm/mmu.h> #include <asm/page.h> diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 90cf3dcbd9f2..ceb18d349459 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -25,10 +25,10 @@ static struct kobject *mobility_kobj; struct update_props_workarea { - u32 phandle; - u32 state; - u64 reserved; - u32 nprops; + __be32 phandle; + __be32 state; + __be64 reserved; + __be32 nprops; } __packed; #define NODE_ACTION_MASK 0xff000000 @@ -54,11 +54,11 @@ static int mobility_rtas_call(int token, char *buf, s32 scope) return rc; } -static int delete_dt_node(u32 phandle) +static int delete_dt_node(__be32 phandle) { struct device_node *dn; - dn = of_find_node_by_phandle(phandle); + dn = of_find_node_by_phandle(be32_to_cpu(phandle)); if (!dn) return -ENOENT; @@ -127,7 +127,7 @@ static int update_dt_property(struct device_node *dn, struct property **prop, return 0; } -static int update_dt_node(u32 phandle, s32 scope) +static int update_dt_node(__be32 phandle, s32 scope) { struct update_props_workarea *upwa; struct device_node *dn; @@ -136,6 +136,7 @@ static int update_dt_node(u32 phandle, s32 scope) char *prop_data; char *rtas_buf; int update_properties_token; + u32 nprops; u32 vd; update_properties_token = rtas_token("ibm,update-properties"); @@ -146,7 +147,7 @@ static int update_dt_node(u32 phandle, s32 scope) if (!rtas_buf) return -ENOMEM; - dn = of_find_node_by_phandle(phandle); + dn = of_find_node_by_phandle(be32_to_cpu(phandle)); if (!dn) { kfree(rtas_buf); return -ENOENT; @@ -162,6 +163,7 @@ static int update_dt_node(u32 phandle, s32 scope) break; prop_data = rtas_buf + sizeof(*upwa); + nprops = be32_to_cpu(upwa->nprops); /* On the first call to ibm,update-properties for a node the * the first property value descriptor contains an empty @@ -170,17 +172,17 @@ static int update_dt_node(u32 phandle, s32 scope) */ if (*prop_data == 0) { prop_data++; - vd = *(u32 *)prop_data; + vd = be32_to_cpu(*(__be32 *)prop_data); prop_data += vd + sizeof(vd); - upwa->nprops--; + nprops--; } - for (i = 0; i < upwa->nprops; i++) { + for (i = 0; i < nprops; i++) { char *prop_name; prop_name = prop_data; prop_data += strlen(prop_name) + 1; - vd = *(u32 *)prop_data; + vd = be32_to_cpu(*(__be32 *)prop_data); prop_data += sizeof(vd); switch (vd) { @@ -212,13 +214,13 @@ static int update_dt_node(u32 phandle, s32 scope) return 0; } -static int add_dt_node(u32 parent_phandle, u32 drc_index) +static int add_dt_node(__be32 parent_phandle, __be32 drc_index) { struct device_node *dn; struct device_node *parent_dn; int rc; - parent_dn = of_find_node_by_phandle(parent_phandle); + parent_dn = of_find_node_by_phandle(be32_to_cpu(parent_phandle)); if (!parent_dn) return -ENOENT; @@ -237,7 +239,7 @@ static int add_dt_node(u32 parent_phandle, u32 drc_index) int pseries_devicetree_update(s32 scope) { char *rtas_buf; - u32 *data; + __be32 *data; int update_nodes_token; int rc; @@ -254,17 +256,17 @@ int pseries_devicetree_update(s32 scope) if (rc && rc != 1) break; - data = (u32 *)rtas_buf + 4; - while (*data & NODE_ACTION_MASK) { + data = (__be32 *)rtas_buf + 4; + while (be32_to_cpu(*data) & NODE_ACTION_MASK) { int i; - u32 action = *data & NODE_ACTION_MASK; - int node_count = *data & NODE_COUNT_MASK; + u32 action = be32_to_cpu(*data) & NODE_ACTION_MASK; + u32 node_count = be32_to_cpu(*data) & NODE_COUNT_MASK; data++; for (i = 0; i < node_count; i++) { - u32 phandle = *data++; - u32 drc_index; + __be32 phandle = *data++; + __be32 drc_index; switch (action) { case DELETE_DT_NODE: @@ -318,28 +320,34 @@ static ssize_t migrate_store(struct class *class, struct class_attribute *attr, { u64 streamid; int rc; - int vasi_rc = 0; rc = kstrtou64(buf, 0, &streamid); if (rc) return rc; do { - rc = rtas_ibm_suspend_me(streamid, &vasi_rc); - if (!rc && vasi_rc == RTAS_NOT_SUSPENDABLE) + rc = rtas_ibm_suspend_me(streamid); + if (rc == -EAGAIN) ssleep(1); - } while (!rc && vasi_rc == RTAS_NOT_SUSPENDABLE); + } while (rc == -EAGAIN); if (rc) return rc; - if (vasi_rc) - return vasi_rc; post_mobility_fixup(); return count; } +/* + * Used by drmgr to determine the kernel behavior of the migration interface. + * + * Version 1: Performs all PAPR requirements for migration including + * firmware activation and device tree update. + */ +#define MIGRATION_API_VERSION 1 + static CLASS_ATTR(migration, S_IWUSR, NULL, migrate_store); +static CLASS_ATTR_STRING(api_version, S_IRUGO, __stringify(MIGRATION_API_VERSION)); static int __init mobility_sysfs_init(void) { @@ -350,7 +358,13 @@ static int __init mobility_sysfs_init(void) return -ENOMEM; rc = sysfs_create_file(mobility_kobj, &class_attr_migration.attr); + if (rc) + pr_err("mobility: unable to create migration sysfs file (%d)\n", rc); - return rc; + rc = sysfs_create_file(mobility_kobj, &class_attr_api_version.attr.attr); + if (rc) + pr_err("mobility: unable to create api_version sysfs file (%d)\n", rc); + + return 0; } machine_device_initcall(pseries, mobility_sysfs_init); diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index 691a154c286d..c8d24f9a6948 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -195,6 +195,7 @@ static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total) static struct device_node *find_pe_dn(struct pci_dev *dev, int *total) { struct device_node *dn; + struct pci_dn *pdn; struct eeh_dev *edev; /* Found our PE and assume 8 at that point. */ @@ -204,10 +205,11 @@ static struct device_node *find_pe_dn(struct pci_dev *dev, int *total) return NULL; /* Get the top level device in the PE */ - edev = of_node_to_eeh_dev(dn); + edev = pdn_to_eeh_dev(PCI_DN(dn)); if (edev->pe) edev = list_first_entry(&edev->pe->edevs, struct eeh_dev, list); - dn = eeh_dev_to_of_node(edev); + pdn = eeh_dev_to_pdn(edev); + dn = pdn ? pdn->node : NULL; if (!dn) return NULL; diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c index 054a0ed5c7ee..9f8184175c86 100644 --- a/arch/powerpc/platforms/pseries/nvram.c +++ b/arch/powerpc/platforms/pseries/nvram.c @@ -20,7 +20,6 @@ #include <linux/kmsg_dump.h> #include <linux/pstore.h> #include <linux/ctype.h> -#include <linux/zlib.h> #include <asm/uaccess.h> #include <asm/nvram.h> #include <asm/rtas.h> @@ -30,129 +29,17 @@ /* Max bytes to read/write in one go */ #define NVRW_CNT 0x20 -/* - * Set oops header version to distinguish between old and new format header. - * lnx,oops-log partition max size is 4000, header version > 4000 will - * help in identifying new header. - */ -#define OOPS_HDR_VERSION 5000 - static unsigned int nvram_size; static int nvram_fetch, nvram_store; static char nvram_buf[NVRW_CNT]; /* assume this is in the first 4GB */ static DEFINE_SPINLOCK(nvram_lock); -struct err_log_info { - __be32 error_type; - __be32 seq_num; -}; - -struct nvram_os_partition { - const char *name; - int req_size; /* desired size, in bytes */ - int min_size; /* minimum acceptable size (0 means req_size) */ - long size; /* size of data portion (excluding err_log_info) */ - long index; /* offset of data portion of partition */ - bool os_partition; /* partition initialized by OS, not FW */ -}; - -static struct nvram_os_partition rtas_log_partition = { - .name = "ibm,rtas-log", - .req_size = 2079, - .min_size = 1055, - .index = -1, - .os_partition = true -}; - -static struct nvram_os_partition oops_log_partition = { - .name = "lnx,oops-log", - .req_size = 4000, - .min_size = 2000, - .index = -1, - .os_partition = true -}; - -static const char *pseries_nvram_os_partitions[] = { - "ibm,rtas-log", - "lnx,oops-log", - NULL -}; - -struct oops_log_info { - __be16 version; - __be16 report_length; - __be64 timestamp; -} __attribute__((packed)); - -static void oops_to_nvram(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason); - -static struct kmsg_dumper nvram_kmsg_dumper = { - .dump = oops_to_nvram -}; - /* See clobbering_unread_rtas_event() */ #define NVRAM_RTAS_READ_TIMEOUT 5 /* seconds */ -static unsigned long last_unread_rtas_event; /* timestamp */ - -/* - * For capturing and compressing an oops or panic report... - - * big_oops_buf[] holds the uncompressed text we're capturing. - * - * oops_buf[] holds the compressed text, preceded by a oops header. - * oops header has u16 holding the version of oops header (to differentiate - * between old and new format header) followed by u16 holding the length of - * the compressed* text (*Or uncompressed, if compression fails.) and u64 - * holding the timestamp. oops_buf[] gets written to NVRAM. - * - * oops_log_info points to the header. oops_data points to the compressed text. - * - * +- oops_buf - * | +- oops_data - * v v - * +-----------+-----------+-----------+------------------------+ - * | version | length | timestamp | text | - * | (2 bytes) | (2 bytes) | (8 bytes) | (oops_data_sz bytes) | - * +-----------+-----------+-----------+------------------------+ - * ^ - * +- oops_log_info - * - * We preallocate these buffers during init to avoid kmalloc during oops/panic. - */ -static size_t big_oops_buf_sz; -static char *big_oops_buf, *oops_buf; -static char *oops_data; -static size_t oops_data_sz; - -/* Compression parameters */ -#define COMPR_LEVEL 6 -#define WINDOW_BITS 12 -#define MEM_LEVEL 4 -static struct z_stream_s stream; +static time64_t last_unread_rtas_event; /* timestamp */ #ifdef CONFIG_PSTORE -static struct nvram_os_partition of_config_partition = { - .name = "of-config", - .index = -1, - .os_partition = false -}; - -static struct nvram_os_partition common_partition = { - .name = "common", - .index = -1, - .os_partition = false -}; - -static enum pstore_type_id nvram_type_ids[] = { - PSTORE_TYPE_DMESG, - PSTORE_TYPE_PPC_RTAS, - PSTORE_TYPE_PPC_OF, - PSTORE_TYPE_PPC_COMMON, - -1 -}; -static int read_type; -static unsigned long last_rtas_event; +time64_t last_rtas_event; #endif static ssize_t pSeries_nvram_read(char *buf, size_t count, loff_t *index) @@ -246,132 +133,26 @@ static ssize_t pSeries_nvram_get_size(void) return nvram_size ? nvram_size : -ENODEV; } - -/* nvram_write_os_partition, nvram_write_error_log +/* nvram_write_error_log * * We need to buffer the error logs into nvram to ensure that we have - * the failure information to decode. If we have a severe error there - * is no way to guarantee that the OS or the machine is in a state to - * get back to user land and write the error to disk. For example if - * the SCSI device driver causes a Machine Check by writing to a bad - * IO address, there is no way of guaranteeing that the device driver - * is in any state that is would also be able to write the error data - * captured to disk, thus we buffer it in NVRAM for analysis on the - * next boot. - * - * In NVRAM the partition containing the error log buffer will looks like: - * Header (in bytes): - * +-----------+----------+--------+------------+------------------+ - * | signature | checksum | length | name | data | - * |0 |1 |2 3|4 15|16 length-1| - * +-----------+----------+--------+------------+------------------+ - * - * The 'data' section would look like (in bytes): - * +--------------+------------+-----------------------------------+ - * | event_logged | sequence # | error log | - * |0 3|4 7|8 error_log_size-1| - * +--------------+------------+-----------------------------------+ - * - * event_logged: 0 if event has not been logged to syslog, 1 if it has - * sequence #: The unique sequence # for each event. (until it wraps) - * error log: The error log from event_scan + * the failure information to decode. */ -static int nvram_write_os_partition(struct nvram_os_partition *part, - char *buff, int length, - unsigned int err_type, - unsigned int error_log_cnt) -{ - int rc; - loff_t tmp_index; - struct err_log_info info; - - if (part->index == -1) { - return -ESPIPE; - } - - if (length > part->size) { - length = part->size; - } - - info.error_type = cpu_to_be32(err_type); - info.seq_num = cpu_to_be32(error_log_cnt); - - tmp_index = part->index; - - rc = ppc_md.nvram_write((char *)&info, sizeof(struct err_log_info), &tmp_index); - if (rc <= 0) { - pr_err("%s: Failed nvram_write (%d)\n", __func__, rc); - return rc; - } - - rc = ppc_md.nvram_write(buff, length, &tmp_index); - if (rc <= 0) { - pr_err("%s: Failed nvram_write (%d)\n", __func__, rc); - return rc; - } - - return 0; -} - int nvram_write_error_log(char * buff, int length, unsigned int err_type, unsigned int error_log_cnt) { int rc = nvram_write_os_partition(&rtas_log_partition, buff, length, err_type, error_log_cnt); if (!rc) { - last_unread_rtas_event = get_seconds(); + last_unread_rtas_event = ktime_get_real_seconds(); #ifdef CONFIG_PSTORE - last_rtas_event = get_seconds(); + last_rtas_event = ktime_get_real_seconds(); #endif } return rc; } -/* nvram_read_partition - * - * Reads nvram partition for at most 'length' - */ -static int nvram_read_partition(struct nvram_os_partition *part, char *buff, - int length, unsigned int *err_type, - unsigned int *error_log_cnt) -{ - int rc; - loff_t tmp_index; - struct err_log_info info; - - if (part->index == -1) - return -1; - - if (length > part->size) - length = part->size; - - tmp_index = part->index; - - if (part->os_partition) { - rc = ppc_md.nvram_read((char *)&info, - sizeof(struct err_log_info), - &tmp_index); - if (rc <= 0) { - pr_err("%s: Failed nvram_read (%d)\n", __func__, rc); - return rc; - } - } - - rc = ppc_md.nvram_read(buff, length, &tmp_index); - if (rc <= 0) { - pr_err("%s: Failed nvram_read (%d)\n", __func__, rc); - return rc; - } - - if (part->os_partition) { - *error_log_cnt = be32_to_cpu(info.seq_num); - *err_type = be32_to_cpu(info.error_type); - } - - return 0; -} - /* nvram_read_error_log * * Reads nvram for error log for at most 'length' @@ -407,67 +188,6 @@ int nvram_clear_error_log(void) return 0; } -/* pseries_nvram_init_os_partition - * - * This sets up a partition with an "OS" signature. - * - * The general strategy is the following: - * 1.) If a partition with the indicated name already exists... - * - If it's large enough, use it. - * - Otherwise, recycle it and keep going. - * 2.) Search for a free partition that is large enough. - * 3.) If there's not a free partition large enough, recycle any obsolete - * OS partitions and try again. - * 4.) Will first try getting a chunk that will satisfy the requested size. - * 5.) If a chunk of the requested size cannot be allocated, then try finding - * a chunk that will satisfy the minum needed. - * - * Returns 0 on success, else -1. - */ -static int __init pseries_nvram_init_os_partition(struct nvram_os_partition - *part) -{ - loff_t p; - int size; - - /* Look for ours */ - p = nvram_find_partition(part->name, NVRAM_SIG_OS, &size); - - /* Found one but too small, remove it */ - if (p && size < part->min_size) { - pr_info("nvram: Found too small %s partition," - " removing it...\n", part->name); - nvram_remove_partition(part->name, NVRAM_SIG_OS, NULL); - p = 0; - } - - /* Create one if we didn't find */ - if (!p) { - p = nvram_create_partition(part->name, NVRAM_SIG_OS, - part->req_size, part->min_size); - if (p == -ENOSPC) { - pr_info("nvram: No room to create %s partition, " - "deleting any obsolete OS partitions...\n", - part->name); - nvram_remove_partition(NULL, NVRAM_SIG_OS, - pseries_nvram_os_partitions); - p = nvram_create_partition(part->name, NVRAM_SIG_OS, - part->req_size, part->min_size); - } - } - - if (p <= 0) { - pr_err("nvram: Failed to find or create %s" - " partition, err %d\n", part->name, (int)p); - return -1; - } - - part->index = p; - part->size = nvram_get_partition_size(p) - sizeof(struct err_log_info); - - return 0; -} - /* * Are we using the ibm,rtas-log for oops/panic reports? And if so, * would logging this oops/panic overwrite an RTAS event that rtas_errd @@ -476,321 +196,14 @@ static int __init pseries_nvram_init_os_partition(struct nvram_os_partition * We assume that if rtas_errd hasn't read the RTAS event in * NVRAM_RTAS_READ_TIMEOUT seconds, it's probably not going to. */ -static int clobbering_unread_rtas_event(void) +int clobbering_unread_rtas_event(void) { return (oops_log_partition.index == rtas_log_partition.index && last_unread_rtas_event - && get_seconds() - last_unread_rtas_event <= + && ktime_get_real_seconds() - last_unread_rtas_event <= NVRAM_RTAS_READ_TIMEOUT); } -/* Derived from logfs_compress() */ -static int nvram_compress(const void *in, void *out, size_t inlen, - size_t outlen) -{ - int err, ret; - - ret = -EIO; - err = zlib_deflateInit2(&stream, COMPR_LEVEL, Z_DEFLATED, WINDOW_BITS, - MEM_LEVEL, Z_DEFAULT_STRATEGY); - if (err != Z_OK) - goto error; - - stream.next_in = in; - stream.avail_in = inlen; - stream.total_in = 0; - stream.next_out = out; - stream.avail_out = outlen; - stream.total_out = 0; - - err = zlib_deflate(&stream, Z_FINISH); - if (err != Z_STREAM_END) - goto error; - - err = zlib_deflateEnd(&stream); - if (err != Z_OK) - goto error; - - if (stream.total_out >= stream.total_in) - goto error; - - ret = stream.total_out; -error: - return ret; -} - -/* Compress the text from big_oops_buf into oops_buf. */ -static int zip_oops(size_t text_len) -{ - struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf; - int zipped_len = nvram_compress(big_oops_buf, oops_data, text_len, - oops_data_sz); - if (zipped_len < 0) { - pr_err("nvram: compression failed; returned %d\n", zipped_len); - pr_err("nvram: logging uncompressed oops/panic report\n"); - return -1; - } - oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION); - oops_hdr->report_length = cpu_to_be16(zipped_len); - oops_hdr->timestamp = cpu_to_be64(get_seconds()); - return 0; -} - -#ifdef CONFIG_PSTORE -static int nvram_pstore_open(struct pstore_info *psi) -{ - /* Reset the iterator to start reading partitions again */ - read_type = -1; - return 0; -} - -/** - * nvram_pstore_write - pstore write callback for nvram - * @type: Type of message logged - * @reason: reason behind dump (oops/panic) - * @id: identifier to indicate the write performed - * @part: pstore writes data to registered buffer in parts, - * part number will indicate the same. - * @count: Indicates oops count - * @compressed: Flag to indicate the log is compressed - * @size: number of bytes written to the registered buffer - * @psi: registered pstore_info structure - * - * Called by pstore_dump() when an oops or panic report is logged in the - * printk buffer. - * Returns 0 on successful write. - */ -static int nvram_pstore_write(enum pstore_type_id type, - enum kmsg_dump_reason reason, - u64 *id, unsigned int part, int count, - bool compressed, size_t size, - struct pstore_info *psi) -{ - int rc; - unsigned int err_type = ERR_TYPE_KERNEL_PANIC; - struct oops_log_info *oops_hdr = (struct oops_log_info *) oops_buf; - - /* part 1 has the recent messages from printk buffer */ - if (part > 1 || type != PSTORE_TYPE_DMESG || - clobbering_unread_rtas_event()) - return -1; - - oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION); - oops_hdr->report_length = cpu_to_be16(size); - oops_hdr->timestamp = cpu_to_be64(get_seconds()); - - if (compressed) - err_type = ERR_TYPE_KERNEL_PANIC_GZ; - - rc = nvram_write_os_partition(&oops_log_partition, oops_buf, - (int) (sizeof(*oops_hdr) + size), err_type, count); - - if (rc != 0) - return rc; - - *id = part; - return 0; -} - -/* - * Reads the oops/panic report, rtas, of-config and common partition. - * Returns the length of the data we read from each partition. - * Returns 0 if we've been called before. - */ -static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type, - int *count, struct timespec *time, char **buf, - bool *compressed, struct pstore_info *psi) -{ - struct oops_log_info *oops_hdr; - unsigned int err_type, id_no, size = 0; - struct nvram_os_partition *part = NULL; - char *buff = NULL; - int sig = 0; - loff_t p; - - read_type++; - - switch (nvram_type_ids[read_type]) { - case PSTORE_TYPE_DMESG: - part = &oops_log_partition; - *type = PSTORE_TYPE_DMESG; - break; - case PSTORE_TYPE_PPC_RTAS: - part = &rtas_log_partition; - *type = PSTORE_TYPE_PPC_RTAS; - time->tv_sec = last_rtas_event; - time->tv_nsec = 0; - break; - case PSTORE_TYPE_PPC_OF: - sig = NVRAM_SIG_OF; - part = &of_config_partition; - *type = PSTORE_TYPE_PPC_OF; - *id = PSTORE_TYPE_PPC_OF; - time->tv_sec = 0; - time->tv_nsec = 0; - break; - case PSTORE_TYPE_PPC_COMMON: - sig = NVRAM_SIG_SYS; - part = &common_partition; - *type = PSTORE_TYPE_PPC_COMMON; - *id = PSTORE_TYPE_PPC_COMMON; - time->tv_sec = 0; - time->tv_nsec = 0; - break; - default: - return 0; - } - - if (!part->os_partition) { - p = nvram_find_partition(part->name, sig, &size); - if (p <= 0) { - pr_err("nvram: Failed to find partition %s, " - "err %d\n", part->name, (int)p); - return 0; - } - part->index = p; - part->size = size; - } - - buff = kmalloc(part->size, GFP_KERNEL); - - if (!buff) - return -ENOMEM; - - if (nvram_read_partition(part, buff, part->size, &err_type, &id_no)) { - kfree(buff); - return 0; - } - - *count = 0; - - if (part->os_partition) - *id = id_no; - - if (nvram_type_ids[read_type] == PSTORE_TYPE_DMESG) { - size_t length, hdr_size; - - oops_hdr = (struct oops_log_info *)buff; - if (be16_to_cpu(oops_hdr->version) < OOPS_HDR_VERSION) { - /* Old format oops header had 2-byte record size */ - hdr_size = sizeof(u16); - length = be16_to_cpu(oops_hdr->version); - time->tv_sec = 0; - time->tv_nsec = 0; - } else { - hdr_size = sizeof(*oops_hdr); - length = be16_to_cpu(oops_hdr->report_length); - time->tv_sec = be64_to_cpu(oops_hdr->timestamp); - time->tv_nsec = 0; - } - *buf = kmalloc(length, GFP_KERNEL); - if (*buf == NULL) - return -ENOMEM; - memcpy(*buf, buff + hdr_size, length); - kfree(buff); - - if (err_type == ERR_TYPE_KERNEL_PANIC_GZ) - *compressed = true; - else - *compressed = false; - return length; - } - - *buf = buff; - return part->size; -} - -static struct pstore_info nvram_pstore_info = { - .owner = THIS_MODULE, - .name = "nvram", - .open = nvram_pstore_open, - .read = nvram_pstore_read, - .write = nvram_pstore_write, -}; - -static int nvram_pstore_init(void) -{ - int rc = 0; - - nvram_pstore_info.buf = oops_data; - nvram_pstore_info.bufsize = oops_data_sz; - - spin_lock_init(&nvram_pstore_info.buf_lock); - - rc = pstore_register(&nvram_pstore_info); - if (rc != 0) - pr_err("nvram: pstore_register() failed, defaults to " - "kmsg_dump; returned %d\n", rc); - - return rc; -} -#else -static int nvram_pstore_init(void) -{ - return -1; -} -#endif - -static void __init nvram_init_oops_partition(int rtas_partition_exists) -{ - int rc; - - rc = pseries_nvram_init_os_partition(&oops_log_partition); - if (rc != 0) { - if (!rtas_partition_exists) - return; - pr_notice("nvram: Using %s partition to log both" - " RTAS errors and oops/panic reports\n", - rtas_log_partition.name); - memcpy(&oops_log_partition, &rtas_log_partition, - sizeof(rtas_log_partition)); - } - oops_buf = kmalloc(oops_log_partition.size, GFP_KERNEL); - if (!oops_buf) { - pr_err("nvram: No memory for %s partition\n", - oops_log_partition.name); - return; - } - oops_data = oops_buf + sizeof(struct oops_log_info); - oops_data_sz = oops_log_partition.size - sizeof(struct oops_log_info); - - rc = nvram_pstore_init(); - - if (!rc) - return; - - /* - * Figure compression (preceded by elimination of each line's <n> - * severity prefix) will reduce the oops/panic report to at most - * 45% of its original size. - */ - big_oops_buf_sz = (oops_data_sz * 100) / 45; - big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL); - if (big_oops_buf) { - stream.workspace = kmalloc(zlib_deflate_workspacesize( - WINDOW_BITS, MEM_LEVEL), GFP_KERNEL); - if (!stream.workspace) { - pr_err("nvram: No memory for compression workspace; " - "skipping compression of %s partition data\n", - oops_log_partition.name); - kfree(big_oops_buf); - big_oops_buf = NULL; - } - } else { - pr_err("No memory for uncompressed %s data; " - "skipping compression\n", oops_log_partition.name); - stream.workspace = NULL; - } - - rc = kmsg_dump_register(&nvram_kmsg_dumper); - if (rc != 0) { - pr_err("nvram: kmsg_dump_register() failed; returned %d\n", rc); - kfree(oops_buf); - kfree(big_oops_buf); - kfree(stream.workspace); - } -} - static int __init pseries_nvram_init_log_partitions(void) { int rc; @@ -798,7 +211,7 @@ static int __init pseries_nvram_init_log_partitions(void) /* Scan nvram for partitions */ nvram_scan_partitions(); - rc = pseries_nvram_init_os_partition(&rtas_log_partition); + rc = nvram_init_os_partition(&rtas_log_partition); nvram_init_oops_partition(rc == 0); return 0; } @@ -834,72 +247,3 @@ int __init pSeries_nvram_init(void) return 0; } - -/* - * This is our kmsg_dump callback, called after an oops or panic report - * has been written to the printk buffer. We want to capture as much - * of the printk buffer as possible. First, capture as much as we can - * that we think will compress sufficiently to fit in the lnx,oops-log - * partition. If that's too much, go back and capture uncompressed text. - */ -static void oops_to_nvram(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason) -{ - struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf; - static unsigned int oops_count = 0; - static bool panicking = false; - static DEFINE_SPINLOCK(lock); - unsigned long flags; - size_t text_len; - unsigned int err_type = ERR_TYPE_KERNEL_PANIC_GZ; - int rc = -1; - - switch (reason) { - case KMSG_DUMP_RESTART: - case KMSG_DUMP_HALT: - case KMSG_DUMP_POWEROFF: - /* These are almost always orderly shutdowns. */ - return; - case KMSG_DUMP_OOPS: - break; - case KMSG_DUMP_PANIC: - panicking = true; - break; - case KMSG_DUMP_EMERG: - if (panicking) - /* Panic report already captured. */ - return; - break; - default: - pr_err("%s: ignoring unrecognized KMSG_DUMP_* reason %d\n", - __func__, (int) reason); - return; - } - - if (clobbering_unread_rtas_event()) - return; - - if (!spin_trylock_irqsave(&lock, flags)) - return; - - if (big_oops_buf) { - kmsg_dump_get_buffer(dumper, false, - big_oops_buf, big_oops_buf_sz, &text_len); - rc = zip_oops(text_len); - } - if (rc != 0) { - kmsg_dump_rewind(dumper); - kmsg_dump_get_buffer(dumper, false, - oops_data, oops_data_sz, &text_len); - err_type = ERR_TYPE_KERNEL_PANIC; - oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION); - oops_hdr->report_length = cpu_to_be16(text_len); - oops_hdr->timestamp = cpu_to_be64(get_seconds()); - } - - (void) nvram_write_os_partition(&oops_log_partition, oops_buf, - (int) (sizeof(*oops_hdr) + text_len), err_type, - ++oops_count); - - spin_unlock_irqrestore(&lock, flags); -} diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index 89e23811199c..5d4a3df59d0c 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -32,6 +32,8 @@ #include <asm/firmware.h> #include <asm/eeh.h> +#include "pseries.h" + static struct pci_bus * find_bus_among_children(struct pci_bus *bus, struct device_node *dn) @@ -75,6 +77,7 @@ struct pci_controller *init_phb_dynamic(struct device_node *dn) return NULL; rtas_setup_phb(phb); pci_process_bridge_OF_ranges(phb, dn, 0); + phb->controller_ops = pseries_pci_controller_ops; pci_devs_phb_init_dynamic(phb); @@ -82,7 +85,7 @@ struct pci_controller *init_phb_dynamic(struct device_node *dn) eeh_dev_phb_init_dynamic(phb); if (dn->child) - eeh_add_device_tree_early(dn); + eeh_add_device_tree_early(PCI_DN(dn)); pcibios_scan_phb(phb); pcibios_finish_adding_to_bus(phb->bus); diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 1796c5438cc6..8411c27293e4 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -11,6 +11,7 @@ #define _PSERIES_PSERIES_H #include <linux/interrupt.h> +#include <asm/rtas.h> struct device_node; @@ -60,11 +61,24 @@ extern struct device_node *dlpar_configure_connector(__be32, struct device_node *); extern int dlpar_attach_node(struct device_node *); extern int dlpar_detach_node(struct device_node *); +extern int dlpar_acquire_drc(u32 drc_index); +extern int dlpar_release_drc(u32 drc_index); + +#ifdef CONFIG_MEMORY_HOTPLUG +int dlpar_memory(struct pseries_hp_errorlog *hp_elog); +#else +static inline int dlpar_memory(struct pseries_hp_errorlog *hp_elog) +{ + return -EOPNOTSUPP; +} +#endif /* PCI root bridge prepare function override for pseries */ struct pci_host_bridge; int pseries_root_bridge_prepare(struct pci_host_bridge *bridge); +extern struct pci_controller_ops pseries_pci_controller_ops; + unsigned long pseries_memory_block_size(void); #endif /* _PSERIES_PSERIES_H */ diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index e445b6701f50..df6a7041922b 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -265,7 +265,7 @@ static int pci_dn_reconfig_notifier(struct notifier_block *nb, unsigned long act update_dn_pci_info(np, pci->phb); /* Create EEH device for the OF node */ - eeh_dev_init(np, pci->phb); + eeh_dev_init(PCI_DN(np), pci->phb); } break; default: @@ -461,6 +461,47 @@ static long pseries_little_endian_exceptions(void) } #endif +static void __init find_and_init_phbs(void) +{ + struct device_node *node; + struct pci_controller *phb; + struct device_node *root = of_find_node_by_path("/"); + + for_each_child_of_node(root, node) { + if (node->type == NULL || (strcmp(node->type, "pci") != 0 && + strcmp(node->type, "pciex") != 0)) + continue; + + phb = pcibios_alloc_controller(node); + if (!phb) + continue; + rtas_setup_phb(phb); + pci_process_bridge_OF_ranges(phb, node, 0); + isa_bridge_find_early(phb); + phb->controller_ops = pseries_pci_controller_ops; + } + + of_node_put(root); + pci_devs_phb_init(); + + /* + * PCI_PROBE_ONLY and PCI_REASSIGN_ALL_BUS can be set via properties + * in chosen. + */ + if (of_chosen) { + const int *prop; + + prop = of_get_property(of_chosen, + "linux,pci-probe-only", NULL); + if (prop) { + if (*prop) + pci_add_flags(PCI_PROBE_ONLY); + else + pci_clear_flags(PCI_PROBE_ONLY); + } + } +} + static void __init pSeries_setup_arch(void) { set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT); @@ -793,6 +834,10 @@ static int pSeries_pci_probe_mode(struct pci_bus *bus) void pSeries_final_fixup(void) { } #endif +struct pci_controller_ops pseries_pci_controller_ops = { + .probe_mode = pSeries_pci_probe_mode, +}; + define_machine(pseries) { .name = "pSeries", .probe = pSeries_probe, @@ -801,7 +846,6 @@ define_machine(pseries) { .show_cpuinfo = pSeries_show_cpuinfo, .log_error = pSeries_log_error, .pcibios_fixup = pSeries_final_fixup, - .pci_probe_mode = pSeries_pci_probe_mode, .restart = rtas_restart, .halt = rtas_halt, .panic = rtas_os_term, diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c index a3555b10c1a5..6932ea803e33 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -197,16 +197,14 @@ static void pSeries_cause_ipi_mux(int cpu, unsigned long data) xics_cause_ipi(cpu, data); } -static __init int pSeries_smp_probe(void) +static __init void pSeries_smp_probe(void) { - int ret = xics_smp_probe(); + xics_smp_probe(); if (cpu_has_feature(CPU_FTR_DBELL)) { xics_cause_ipi = smp_ops->cause_ipi; smp_ops->cause_ipi = pSeries_cause_ipi_mux; } - - return ret; } static struct smp_ops_t pSeries_mpic_smp_ops = { |