diff options
Diffstat (limited to 'arch/powerpc/platforms')
223 files changed, 12033 insertions, 13276 deletions
diff --git a/arch/powerpc/platforms/40x/Kconfig b/arch/powerpc/platforms/40x/Kconfig index a392d12dd21..6e287f1294f 100644 --- a/arch/powerpc/platforms/40x/Kconfig +++ b/arch/powerpc/platforms/40x/Kconfig @@ -20,7 +20,6 @@ config HOTFOOT bool "Hotfoot" depends on 40x default n - select 405EP select PPC40x_SIMPLE select PCI help @@ -105,9 +104,6 @@ config 405GP select IBM405_ERR51 select IBM_EMAC_ZMII -config 405EP - bool - config 405EX bool select IBM_EMAC_EMAC4 @@ -119,9 +115,6 @@ config 405EZ select IBM_EMAC_MAL_CLR_ICINTSTAT select IBM_EMAC_MAL_COMMON_ERR -config 405GPR - bool - config XILINX_VIRTEX bool select DEFAULT_UIMAGE @@ -145,7 +138,6 @@ config PPC4xx_GPIO bool "PPC4xx GPIO support" depends on 40x select ARCH_REQUIRE_GPIOLIB - select GENERIC_GPIO help Enable gpiolib support for ppc40x based boards diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig index 8abf6fb8f41..4d88f6a1905 100644 --- a/arch/powerpc/platforms/44x/Kconfig +++ b/arch/powerpc/platforms/44x/Kconfig @@ -199,6 +199,34 @@ config CURRITUCK help This option enables support for the IBM Currituck (476fpe) evaluation board +config AKEBONO + bool "IBM Akebono (476gtr) Support" + depends on PPC_47x + default n + select SWIOTLB + select 476FPE + select PPC4xx_PCI_EXPRESS + select PCI_MSI + select PPC4xx_HSTA_MSI + select I2C + select I2C_IBM_IIC + select NETDEVICES + select ETHERNET + select NET_VENDOR_IBM + select IBM_EMAC_EMAC4 + select IBM_EMAC_RGMII_WOL + select USB + select USB_OHCI_HCD_PLATFORM + select USB_EHCI_HCD_PLATFORM + select MMC_SDHCI + select MMC_SDHCI_PLTFM + select MMC_SDHCI_OF_476GTR + select ATA + select SATA_AHCI_PLATFORM + help + This option enables support for the IBM Akebono (476gtr) evaluation board + + config ICON bool "Icon" depends on 44x @@ -248,17 +276,23 @@ config PPC4xx_GPIO bool "PPC4xx GPIO support" depends on 44x select ARCH_REQUIRE_GPIOLIB - select GENERIC_GPIO help Enable gpiolib support for ppc440 based boards +config PPC4xx_OCM + bool "PPC4xx On Chip Memory (OCM) support" + depends on 4xx + select PPC_LIB_RHEAP + help + Enable OCM support for PowerPC 4xx platforms with on chip memory, + OCM provides the fast place for memory access to improve performance. + # 44x specific CPU modules, selected based on the board above. config 440EP bool select PPC_FPU select IBM440EP_ERR42 select IBM_EMAC_ZMII - select USB_ARCH_HAS_OHCI config 440EPX bool @@ -266,6 +300,8 @@ config 440EPX select IBM_EMAC_EMAC4 select IBM_EMAC_RGMII select IBM_EMAC_ZMII + select USB_EHCI_BIG_ENDIAN_MMIO + select USB_EHCI_BIG_ENDIAN_DESC config 440GRX bool @@ -315,6 +351,20 @@ config APM821xx select IBM_EMAC_EMAC4 select IBM_EMAC_TAH +config 476FPE_ERR46 + depends on 476FPE + bool "Enable linker work around for PPC476FPE errata #46" + help + This option enables a work around for an icache bug on 476 + that can cause execution of stale instructions when falling + through pages (IBM errata #46). It requires a recent version + of binutils which supports the --ppc476-workaround option. + + The work around enables the appropriate linker options and + ensures that all module output sections are aligned to 4K + page boundaries. The work around is only required when + building modules. + # 44x errata/workaround config symbols, selected by the CPU models above config IBM440EP_ERR42 bool diff --git a/arch/powerpc/platforms/44x/Makefile b/arch/powerpc/platforms/44x/Makefile index d03833abec0..26d35b5941f 100644 --- a/arch/powerpc/platforms/44x/Makefile +++ b/arch/powerpc/platforms/44x/Makefile @@ -10,4 +10,5 @@ obj-$(CONFIG_XILINX_VIRTEX_5_FXT) += virtex.o obj-$(CONFIG_XILINX_ML510) += virtex_ml510.o obj-$(CONFIG_ISS4xx) += iss4xx.o obj-$(CONFIG_CANYONLANDS)+= canyonlands.o -obj-$(CONFIG_CURRITUCK) += currituck.o +obj-$(CONFIG_CURRITUCK) += ppc476.o +obj-$(CONFIG_AKEBONO) += ppc476.o diff --git a/arch/powerpc/platforms/44x/iss4xx.c b/arch/powerpc/platforms/44x/iss4xx.c index a28a8629727..4241bc82580 100644 --- a/arch/powerpc/platforms/44x/iss4xx.c +++ b/arch/powerpc/platforms/44x/iss4xx.c @@ -81,12 +81,12 @@ static void __init iss4xx_init_irq(void) } #ifdef CONFIG_SMP -static void __cpuinit smp_iss4xx_setup_cpu(int cpu) +static void smp_iss4xx_setup_cpu(int cpu) { mpic_setup_this_cpu(); } -static int __cpuinit smp_iss4xx_kick_cpu(int cpu) +static int smp_iss4xx_kick_cpu(int cpu) { struct device_node *cpunode = of_get_cpu_node(cpu, NULL); const u64 *spin_table_addr_prop; diff --git a/arch/powerpc/platforms/44x/currituck.c b/arch/powerpc/platforms/44x/ppc476.c index ecd3890c40d..33986c1a05d 100644 --- a/arch/powerpc/platforms/44x/currituck.c +++ b/arch/powerpc/platforms/44x/ppc476.c @@ -1,7 +1,8 @@ /* - * Currituck board specific routines + * PowerPC 476FPE board specific routines * - * Copyright © 2011 Tony Breeds IBM Corporation + * Copyright © 2013 Tony Breeds IBM Corporation + * Copyright © 2013 Alistair Popple IBM Corporation * * Based on earlier code: * Matt Porter <mporter@kernel.crashing.org> @@ -35,8 +36,9 @@ #include <asm/mmu.h> #include <linux/pci.h> +#include <linux/i2c.h> -static __initdata struct of_device_id ppc47x_of_bus[] = { +static struct of_device_id ppc47x_of_bus[] __initdata = { { .compatible = "ibm,plb4", }, { .compatible = "ibm,plb6", }, { .compatible = "ibm,opb", }, @@ -55,15 +57,69 @@ static void quirk_ppc_currituck_usb_fixup(struct pci_dev *dev) } DECLARE_PCI_FIXUP_HEADER(0x1033, 0x0035, quirk_ppc_currituck_usb_fixup); +/* Akebono has an AVR microcontroller attached to the I2C bus + * which is used to power off/reset the system. */ + +/* AVR I2C Commands */ +#define AVR_PWRCTL_CMD (0x26) + +/* Flags for the power control I2C commands */ +#define AVR_PWRCTL_PWROFF (0x01) +#define AVR_PWRCTL_RESET (0x02) + +static struct i2c_client *avr_i2c_client; +static void avr_halt_system(int pwrctl_flags) +{ + /* Request the AVR to reset the system */ + i2c_smbus_write_byte_data(avr_i2c_client, + AVR_PWRCTL_CMD, pwrctl_flags); + + /* Wait for system to be reset */ + while (1) + ; +} + +static void avr_power_off_system(void) +{ + avr_halt_system(AVR_PWRCTL_PWROFF); +} + +static void avr_reset_system(char *cmd) +{ + avr_halt_system(AVR_PWRCTL_RESET); +} + +static int avr_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + avr_i2c_client = client; + ppc_md.restart = avr_reset_system; + ppc_md.power_off = avr_power_off_system; + return 0; +} + +static const struct i2c_device_id avr_id[] = { + { "akebono-avr", 0 }, + { } +}; + +static struct i2c_driver avr_driver = { + .driver = { + .name = "akebono-avr", + }, + .probe = avr_probe, + .id_table = avr_id, +}; + static int __init ppc47x_device_probe(void) { + i2c_add_driver(&avr_driver); of_platform_bus_probe(NULL, ppc47x_of_bus, NULL); return 0; } machine_device_initcall(ppc47x, ppc47x_device_probe); -/* We can have either UICs or MPICs */ static void __init ppc47x_init_irq(void) { struct device_node *np; @@ -91,12 +147,12 @@ static void __init ppc47x_init_irq(void) } #ifdef CONFIG_SMP -static void __cpuinit smp_ppc47x_setup_cpu(int cpu) +static void smp_ppc47x_setup_cpu(int cpu) { mpic_setup_this_cpu(); } -static int __cpuinit smp_ppc47x_kick_cpu(int cpu) +static int smp_ppc47x_kick_cpu(int cpu) { struct device_node *cpunode = of_get_cpu_node(cpu, NULL); const u64 *spin_table_addr_prop; @@ -157,33 +213,79 @@ static void __init ppc47x_setup_arch(void) { /* No need to check the DMA config as we /know/ our windows are all of - * RAM. Lets hope that doesn't change */ + * RAM. Lets hope that doesn't change */ swiotlb_detect_4g(); ppc47x_smp_init(); } -/* - * Called very early, MMU is off, device-tree isn't unflattened - */ -static int __init ppc47x_probe(void) +static int board_rev = -1; +static int __init ppc47x_get_board_rev(void) { - unsigned long root = of_get_flat_dt_root(); + int reg; + u8 *fpga; + struct device_node *np = NULL; + + if (of_machine_is_compatible("ibm,currituck")) { + np = of_find_compatible_node(NULL, NULL, "ibm,currituck-fpga"); + reg = 0; + } else if (of_machine_is_compatible("ibm,akebono")) { + np = of_find_compatible_node(NULL, NULL, "ibm,akebono-fpga"); + reg = 2; + } + + if (!np) + goto fail; - if (!of_flat_dt_is_compatible(root, "ibm,currituck")) - return 0; + fpga = (u8 *) of_iomap(np, 0); + of_node_put(np); + if (!fpga) + goto fail; - return 1; + board_rev = ioread8(fpga + reg) & 0x03; + pr_info("%s: Found board revision %d\n", __func__, board_rev); + iounmap(fpga); + return 0; + +fail: + pr_info("%s: Unable to find board revision\n", __func__); + return 0; } +machine_arch_initcall(ppc47x, ppc47x_get_board_rev); /* Use USB controller should have been hardware swizzled but it wasn't :( */ static void ppc47x_pci_irq_fixup(struct pci_dev *dev) { if (dev->vendor == 0x1033 && (dev->device == 0x0035 || - dev->device == 0x00e0)) { - dev->irq = irq_create_mapping(NULL, 47); - pr_info("%s: Mapping irq 47 %d\n", __func__, dev->irq); + dev->device == 0x00e0)) { + if (board_rev == 0) { + dev->irq = irq_create_mapping(NULL, 47); + pr_info("%s: Mapping irq %d\n", __func__, dev->irq); + } else if (board_rev == 2) { + dev->irq = irq_create_mapping(NULL, 49); + pr_info("%s: Mapping irq %d\n", __func__, dev->irq); + } else { + pr_alert("%s: Unknown board revision\n", __func__); + } + } +} + +/* + * Called very early, MMU is off, device-tree isn't unflattened + */ +static int __init ppc47x_probe(void) +{ + unsigned long root = of_get_flat_dt_root(); + + if (of_flat_dt_is_compatible(root, "ibm,akebono")) + return 1; + + if (of_flat_dt_is_compatible(root, "ibm,currituck")) { + ppc_md.pci_irq_fixup = ppc47x_pci_irq_fixup; + return 1; } + + return 0; } define_machine(ppc47x) { @@ -192,7 +294,6 @@ define_machine(ppc47x) { .progress = udbg_progress, .init_IRQ = ppc47x_init_irq, .setup_arch = ppc47x_setup_arch, - .pci_irq_fixup = ppc47x_pci_irq_fixup, .restart = ppc4xx_reset_system, .calibrate_decr = generic_calibrate_decr, }; diff --git a/arch/powerpc/platforms/44x/ppc476_modules.lds b/arch/powerpc/platforms/44x/ppc476_modules.lds new file mode 100644 index 00000000000..9fec5d34ba8 --- /dev/null +++ b/arch/powerpc/platforms/44x/ppc476_modules.lds @@ -0,0 +1,15 @@ +SECTIONS +{ + .text : ALIGN(4096) + { + *(.text .text.* .fixup) + } + .init.text : ALIGN(4096) + { + *(.init.text .init.text.*) + } + .exit.text : ALIGN(4096) + { + *(.exit.text .exit.text.*) + } +} diff --git a/arch/powerpc/platforms/44x/warp.c b/arch/powerpc/platforms/44x/warp.c index 4cfa49901c0..534574a97ec 100644 --- a/arch/powerpc/platforms/44x/warp.c +++ b/arch/powerpc/platforms/44x/warp.c @@ -16,7 +16,6 @@ #include <linux/interrupt.h> #include <linux/delay.h> #include <linux/of_gpio.h> -#include <linux/of_i2c.h> #include <linux/slab.h> #include <linux/export.h> diff --git a/arch/powerpc/platforms/512x/Kconfig b/arch/powerpc/platforms/512x/Kconfig index c16999802ec..5aa3f4b5332 100644 --- a/arch/powerpc/platforms/512x/Kconfig +++ b/arch/powerpc/platforms/512x/Kconfig @@ -1,12 +1,14 @@ config PPC_MPC512x bool "512x-based boards" depends on 6xx + select COMMON_CLK select FSL_SOC select IPIC - select PPC_CLOCK select PPC_PCI_CHOICE select FSL_PCI if PCI select ARCH_WANT_OPTIONAL_GPIOLIB + select USB_EHCI_BIG_ENDIAN_MMIO + select USB_EHCI_BIG_ENDIAN_DESC config MPC5121_ADS bool "Freescale MPC5121E ADS" @@ -15,16 +17,16 @@ config MPC5121_ADS help This option enables support for the MPC5121E ADS board. -config MPC5121_GENERIC - bool "Generic support for simple MPC5121 based boards" +config MPC512x_GENERIC + bool "Generic support for simple MPC512x based boards" depends on PPC_MPC512x select DEFAULT_UIMAGE help - This option enables support for simple MPC5121 based boards + This option enables support for simple MPC512x based boards which do not need custom platform specific setup. Compatible boards include: Protonic LVT base boards (ZANMCU - and VICVT2). + and VICVT2), Freescale MPC5125 Tower system. config PDM360NG bool "ifm PDM360NG board" diff --git a/arch/powerpc/platforms/512x/Makefile b/arch/powerpc/platforms/512x/Makefile index 4efc1c4b6fb..01693121a2b 100644 --- a/arch/powerpc/platforms/512x/Makefile +++ b/arch/powerpc/platforms/512x/Makefile @@ -1,7 +1,8 @@ # # Makefile for the Freescale PowerPC 512x linux kernel. # -obj-y += clock.o mpc512x_shared.o +obj-$(CONFIG_COMMON_CLK) += clock-commonclk.o +obj-y += mpc512x_shared.o obj-$(CONFIG_MPC5121_ADS) += mpc5121_ads.o mpc5121_ads_cpld.o -obj-$(CONFIG_MPC5121_GENERIC) += mpc5121_generic.o +obj-$(CONFIG_MPC512x_GENERIC) += mpc512x_generic.o obj-$(CONFIG_PDM360NG) += pdm360ng.o diff --git a/arch/powerpc/platforms/512x/clock-commonclk.c b/arch/powerpc/platforms/512x/clock-commonclk.c new file mode 100644 index 00000000000..6eb614a271f --- /dev/null +++ b/arch/powerpc/platforms/512x/clock-commonclk.c @@ -0,0 +1,1221 @@ +/* + * Copyright (C) 2013 DENX Software Engineering + * + * Gerhard Sittig, <gsi@denx.de> + * + * common clock driver support for the MPC512x platform + * + * This 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/bitops.h> +#include <linux/clk-provider.h> +#include <linux/clkdev.h> +#include <linux/device.h> +#include <linux/errno.h> +#include <linux/io.h> +#include <linux/of.h> +#include <linux/of_address.h> + +#include <asm/mpc5121.h> +#include <dt-bindings/clock/mpc512x-clock.h> + +#include "mpc512x.h" /* our public mpc5121_clk_init() API */ + +/* helpers to keep the MCLK intermediates "somewhere" in our table */ +enum { + MCLK_IDX_MUX0, + MCLK_IDX_EN0, + MCLK_IDX_DIV0, + MCLK_MAX_IDX, +}; + +#define NR_PSCS 12 +#define NR_MSCANS 4 +#define NR_SPDIFS 1 +#define NR_OUTCLK 4 +#define NR_MCLKS (NR_PSCS + NR_MSCANS + NR_SPDIFS + NR_OUTCLK) + +/* extend the public set of clocks by adding internal slots for management */ +enum { + /* arrange for adjacent numbers after the public set */ + MPC512x_CLK_START_PRIVATE = MPC512x_CLK_LAST_PUBLIC, + /* clocks which aren't announced to the public */ + MPC512x_CLK_DDR, + MPC512x_CLK_MEM, + MPC512x_CLK_IIM, + /* intermediates in div+gate combos or fractional dividers */ + MPC512x_CLK_DDR_UG, + MPC512x_CLK_SDHC_x4, + MPC512x_CLK_SDHC_UG, + MPC512x_CLK_SDHC2_UG, + MPC512x_CLK_DIU_x4, + MPC512x_CLK_DIU_UG, + MPC512x_CLK_MBX_BUS_UG, + MPC512x_CLK_MBX_UG, + MPC512x_CLK_MBX_3D_UG, + MPC512x_CLK_PCI_UG, + MPC512x_CLK_NFC_UG, + MPC512x_CLK_LPC_UG, + MPC512x_CLK_SPDIF_TX_IN, + /* intermediates for the mux+gate+div+mux MCLK generation */ + MPC512x_CLK_MCLKS_FIRST, + MPC512x_CLK_MCLKS_LAST = MPC512x_CLK_MCLKS_FIRST + + NR_MCLKS * MCLK_MAX_IDX, + /* internal, symbolic spec for the number of slots */ + MPC512x_CLK_LAST_PRIVATE, +}; + +/* data required for the OF clock provider registration */ +static struct clk *clks[MPC512x_CLK_LAST_PRIVATE]; +static struct clk_onecell_data clk_data; + +/* CCM register access */ +static struct mpc512x_ccm __iomem *clkregs; +static DEFINE_SPINLOCK(clklock); + +/* SoC variants {{{ */ + +/* + * tell SoC variants apart as they are rather similar yet not identical, + * cache the result in an enum to not repeatedly run the expensive OF test + * + * MPC5123 is an MPC5121 without the MBX graphics accelerator + * + * MPC5125 has many more differences: no MBX, no AXE, no VIU, no SPDIF, + * no PATA, no SATA, no PCI, two FECs (of different compatibility name), + * only 10 PSCs (of different compatibility name), two SDHCs, different + * NFC IP block, output clocks, system PLL status query, different CPMF + * interpretation, no CFM, different fourth PSC/CAN mux0 input -- yet + * those differences can get folded into this clock provider support + * code and don't warrant a separate highly redundant implementation + */ + +static enum soc_type { + MPC512x_SOC_MPC5121, + MPC512x_SOC_MPC5123, + MPC512x_SOC_MPC5125, +} soc; + +static void mpc512x_clk_determine_soc(void) +{ + if (of_machine_is_compatible("fsl,mpc5121")) { + soc = MPC512x_SOC_MPC5121; + return; + } + if (of_machine_is_compatible("fsl,mpc5123")) { + soc = MPC512x_SOC_MPC5123; + return; + } + if (of_machine_is_compatible("fsl,mpc5125")) { + soc = MPC512x_SOC_MPC5125; + return; + } +} + +static bool soc_has_mbx(void) +{ + if (soc == MPC512x_SOC_MPC5121) + return true; + return false; +} + +static bool soc_has_axe(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return false; + return true; +} + +static bool soc_has_viu(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return false; + return true; +} + +static bool soc_has_spdif(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return false; + return true; +} + +static bool soc_has_pata(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return false; + return true; +} + +static bool soc_has_sata(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return false; + return true; +} + +static bool soc_has_pci(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return false; + return true; +} + +static bool soc_has_fec2(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return true; + return false; +} + +static int soc_max_pscnum(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return 10; + return 12; +} + +static bool soc_has_sdhc2(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return true; + return false; +} + +static bool soc_has_nfc_5125(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return true; + return false; +} + +static bool soc_has_outclk(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return true; + return false; +} + +static bool soc_has_cpmf_0_bypass(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return true; + return false; +} + +static bool soc_has_mclk_mux0_canin(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return true; + return false; +} + +/* }}} SoC variants */ +/* common clk API wrappers {{{ */ + +/* convenience wrappers around the common clk API */ +static inline struct clk *mpc512x_clk_fixed(const char *name, int rate) +{ + return clk_register_fixed_rate(NULL, name, NULL, CLK_IS_ROOT, rate); +} + +static inline struct clk *mpc512x_clk_factor( + const char *name, const char *parent_name, + int mul, int div) +{ + int clkflags; + + clkflags = CLK_SET_RATE_PARENT; + return clk_register_fixed_factor(NULL, name, parent_name, clkflags, + mul, div); +} + +static inline struct clk *mpc512x_clk_divider( + const char *name, const char *parent_name, u8 clkflags, + u32 __iomem *reg, u8 pos, u8 len, int divflags) +{ + return clk_register_divider(NULL, name, parent_name, clkflags, + reg, pos, len, divflags, &clklock); +} + +static inline struct clk *mpc512x_clk_divtable( + const char *name, const char *parent_name, + u32 __iomem *reg, u8 pos, u8 len, + const struct clk_div_table *divtab) +{ + u8 divflags; + + divflags = 0; + return clk_register_divider_table(NULL, name, parent_name, 0, + reg, pos, len, divflags, + divtab, &clklock); +} + +static inline struct clk *mpc512x_clk_gated( + const char *name, const char *parent_name, + u32 __iomem *reg, u8 pos) +{ + int clkflags; + + clkflags = CLK_SET_RATE_PARENT; + return clk_register_gate(NULL, name, parent_name, clkflags, + reg, pos, 0, &clklock); +} + +static inline struct clk *mpc512x_clk_muxed(const char *name, + const char **parent_names, int parent_count, + u32 __iomem *reg, u8 pos, u8 len) +{ + int clkflags; + u8 muxflags; + + clkflags = CLK_SET_RATE_PARENT; + muxflags = 0; + return clk_register_mux(NULL, name, + parent_names, parent_count, clkflags, + reg, pos, len, muxflags, &clklock); +} + +/* }}} common clk API wrappers */ + +/* helper to isolate a bit field from a register */ +static inline int get_bit_field(uint32_t __iomem *reg, uint8_t pos, uint8_t len) +{ + uint32_t val; + + val = in_be32(reg); + val >>= pos; + val &= (1 << len) - 1; + return val; +} + +/* get the SPMF and translate it into the "sys pll" multiplier */ +static int get_spmf_mult(void) +{ + static int spmf_to_mult[] = { + 68, 1, 12, 16, 20, 24, 28, 32, + 36, 40, 44, 48, 52, 56, 60, 64, + }; + int spmf; + + spmf = get_bit_field(&clkregs->spmr, 24, 4); + return spmf_to_mult[spmf]; +} + +/* + * get the SYS_DIV value and translate it into a divide factor + * + * values returned from here are a multiple of the real factor since the + * divide ratio is fractional + */ +static int get_sys_div_x2(void) +{ + static int sysdiv_code_to_x2[] = { + 4, 5, 6, 7, 8, 9, 10, 14, + 12, 16, 18, 22, 20, 24, 26, 30, + 28, 32, 34, 38, 36, 40, 42, 46, + 44, 48, 50, 54, 52, 56, 58, 62, + 60, 64, 66, + }; + int divcode; + + divcode = get_bit_field(&clkregs->scfr2, 26, 6); + return sysdiv_code_to_x2[divcode]; +} + +/* + * get the CPMF value and translate it into a multiplier factor + * + * values returned from here are a multiple of the real factor since the + * multiplier ratio is fractional + */ +static int get_cpmf_mult_x2(void) +{ + static int cpmf_to_mult_x36[] = { + /* 0b000 is "times 36" */ + 72, 2, 2, 3, 4, 5, 6, 7, + }; + static int cpmf_to_mult_0by[] = { + /* 0b000 is "bypass" */ + 2, 2, 2, 3, 4, 5, 6, 7, + }; + + int *cpmf_to_mult; + int cpmf; + + cpmf = get_bit_field(&clkregs->spmr, 16, 4); + if (soc_has_cpmf_0_bypass()) + cpmf_to_mult = cpmf_to_mult_0by; + else + cpmf_to_mult = cpmf_to_mult_x36; + return cpmf_to_mult[cpmf]; +} + +/* + * some of the clock dividers do scale in a linear way, yet not all of + * their bit combinations are legal; use a divider table to get a + * resulting set of applicable divider values + */ + +/* applies to the IPS_DIV, and PCI_DIV values */ +static struct clk_div_table divtab_2346[] = { + { .val = 2, .div = 2, }, + { .val = 3, .div = 3, }, + { .val = 4, .div = 4, }, + { .val = 6, .div = 6, }, + { .div = 0, }, +}; + +/* applies to the MBX_DIV, LPC_DIV, and NFC_DIV values */ +static struct clk_div_table divtab_1234[] = { + { .val = 1, .div = 1, }, + { .val = 2, .div = 2, }, + { .val = 3, .div = 3, }, + { .val = 4, .div = 4, }, + { .div = 0, }, +}; + +static int get_freq_from_dt(char *propname) +{ + struct device_node *np; + const unsigned int *prop; + int val; + + val = 0; + np = of_find_compatible_node(NULL, NULL, "fsl,mpc5121-immr"); + if (np) { + prop = of_get_property(np, propname, NULL); + if (prop) + val = *prop; + of_node_put(np); + } + return val; +} + +static void mpc512x_clk_preset_data(void) +{ + size_t i; + + for (i = 0; i < ARRAY_SIZE(clks); i++) + clks[i] = ERR_PTR(-ENODEV); +} + +/* + * - receives the "bus frequency" from the caller (that's the IPS clock + * rate, the historical source of clock information) + * - fetches the system PLL multiplier and divider values as well as the + * IPS divider value from hardware + * - determines the REF clock rate either from the XTAL/OSC spec (if + * there is a device tree node describing the oscillator) or from the + * IPS bus clock (supported for backwards compatibility, such that + * setups without XTAL/OSC specs keep working) + * - creates the "ref" clock item in the clock tree, such that + * subsequent code can create the remainder of the hierarchy (REF -> + * SYS -> CSB -> IPS) from the REF clock rate and the returned mul/div + * values + */ +static void mpc512x_clk_setup_ref_clock(struct device_node *np, int bus_freq, + int *sys_mul, int *sys_div, + int *ips_div) +{ + struct clk *osc_clk; + int calc_freq; + + /* fetch mul/div factors from the hardware */ + *sys_mul = get_spmf_mult(); + *sys_mul *= 2; /* compensate for the fractional divider */ + *sys_div = get_sys_div_x2(); + *ips_div = get_bit_field(&clkregs->scfr1, 23, 3); + + /* lookup the oscillator clock for its rate */ + osc_clk = of_clk_get_by_name(np, "osc"); + + /* + * either descend from OSC to REF (and in bypassing verify the + * IPS rate), or backtrack from IPS and multiplier values that + * were fetched from hardware to REF and thus to the OSC value + * + * in either case the REF clock gets created here and the + * remainder of the clock tree can get spanned from there + */ + if (!IS_ERR(osc_clk)) { + clks[MPC512x_CLK_REF] = mpc512x_clk_factor("ref", "osc", 1, 1); + calc_freq = clk_get_rate(clks[MPC512x_CLK_REF]); + calc_freq *= *sys_mul; + calc_freq /= *sys_div; + calc_freq /= 2; + calc_freq /= *ips_div; + if (bus_freq && calc_freq != bus_freq) + pr_warn("calc rate %d != OF spec %d\n", + calc_freq, bus_freq); + } else { + calc_freq = bus_freq; /* start with IPS */ + calc_freq *= *ips_div; /* IPS -> CSB */ + calc_freq *= 2; /* CSB -> SYS */ + calc_freq *= *sys_div; /* SYS -> PLL out */ + calc_freq /= *sys_mul; /* PLL out -> REF == OSC */ + clks[MPC512x_CLK_REF] = mpc512x_clk_fixed("ref", calc_freq); + } +} + +/* MCLK helpers {{{ */ + +/* + * helper code for the MCLK subtree setup + * + * the overview in section 5.2.4 of the MPC5121e Reference Manual rev4 + * suggests that all instances of the "PSC clock generation" are equal, + * and that one might re-use the PSC setup for MSCAN clock generation + * (section 5.2.5) as well, at least the logic if not the data for + * description + * + * the details (starting at page 5-20) show differences in the specific + * inputs of the first mux stage ("can clk in", "spdif tx"), and the + * factual non-availability of the second mux stage (it's present yet + * only one input is valid) + * + * the MSCAN clock related registers (starting at page 5-35) all + * reference "spdif clk" at the first mux stage and don't mention any + * "can clk" at all, which somehow is unexpected + * + * TODO re-check the document, and clarify whether the RM is correct in + * the overview or in the details, and whether the difference is a + * clipboard induced error or results from chip revisions + * + * it turns out that the RM rev4 as of 2012-06 talks about "can" for the + * PSCs while RM rev3 as of 2008-10 talks about "spdif", so I guess that + * first a doc update is required which better reflects reality in the + * SoC before the implementation should follow while no questions remain + */ + +/* + * note that this declaration raises a checkpatch warning, but + * it's the very data type dictated by <linux/clk-provider.h>, + * "fixing" this warning will break compilation + */ +static const char *parent_names_mux0_spdif[] = { + "sys", "ref", "psc-mclk-in", "spdif-tx", +}; + +static const char *parent_names_mux0_canin[] = { + "sys", "ref", "psc-mclk-in", "can-clk-in", +}; + +enum mclk_type { + MCLK_TYPE_PSC, + MCLK_TYPE_MSCAN, + MCLK_TYPE_SPDIF, + MCLK_TYPE_OUTCLK, +}; + +struct mclk_setup_data { + enum mclk_type type; + bool has_mclk1; + const char *name_mux0; + const char *name_en0; + const char *name_div0; + const char *parent_names_mux1[2]; + const char *name_mclk; +}; + +#define MCLK_SETUP_DATA_PSC(id) { \ + MCLK_TYPE_PSC, 0, \ + "psc" #id "-mux0", \ + "psc" #id "-en0", \ + "psc" #id "_mclk_div", \ + { "psc" #id "_mclk_div", "dummy", }, \ + "psc" #id "_mclk", \ +} + +#define MCLK_SETUP_DATA_MSCAN(id) { \ + MCLK_TYPE_MSCAN, 0, \ + "mscan" #id "-mux0", \ + "mscan" #id "-en0", \ + "mscan" #id "_mclk_div", \ + { "mscan" #id "_mclk_div", "dummy", }, \ + "mscan" #id "_mclk", \ +} + +#define MCLK_SETUP_DATA_SPDIF { \ + MCLK_TYPE_SPDIF, 1, \ + "spdif-mux0", \ + "spdif-en0", \ + "spdif_mclk_div", \ + { "spdif_mclk_div", "spdif-rx", }, \ + "spdif_mclk", \ +} + +#define MCLK_SETUP_DATA_OUTCLK(id) { \ + MCLK_TYPE_OUTCLK, 0, \ + "out" #id "-mux0", \ + "out" #id "-en0", \ + "out" #id "_mclk_div", \ + { "out" #id "_mclk_div", "dummy", }, \ + "out" #id "_clk", \ +} + +static struct mclk_setup_data mclk_psc_data[] = { + MCLK_SETUP_DATA_PSC(0), + MCLK_SETUP_DATA_PSC(1), + MCLK_SETUP_DATA_PSC(2), + MCLK_SETUP_DATA_PSC(3), + MCLK_SETUP_DATA_PSC(4), + MCLK_SETUP_DATA_PSC(5), + MCLK_SETUP_DATA_PSC(6), + MCLK_SETUP_DATA_PSC(7), + MCLK_SETUP_DATA_PSC(8), + MCLK_SETUP_DATA_PSC(9), + MCLK_SETUP_DATA_PSC(10), + MCLK_SETUP_DATA_PSC(11), +}; + +static struct mclk_setup_data mclk_mscan_data[] = { + MCLK_SETUP_DATA_MSCAN(0), + MCLK_SETUP_DATA_MSCAN(1), + MCLK_SETUP_DATA_MSCAN(2), + MCLK_SETUP_DATA_MSCAN(3), +}; + +static struct mclk_setup_data mclk_spdif_data[] = { + MCLK_SETUP_DATA_SPDIF, +}; + +static struct mclk_setup_data mclk_outclk_data[] = { + MCLK_SETUP_DATA_OUTCLK(0), + MCLK_SETUP_DATA_OUTCLK(1), + MCLK_SETUP_DATA_OUTCLK(2), + MCLK_SETUP_DATA_OUTCLK(3), +}; + +/* setup the MCLK clock subtree of an individual PSC/MSCAN/SPDIF */ +static void mpc512x_clk_setup_mclk(struct mclk_setup_data *entry, size_t idx) +{ + size_t clks_idx_pub, clks_idx_int; + u32 __iomem *mccr_reg; /* MCLK control register (mux, en, div) */ + int div; + + /* derive a few parameters from the component type and index */ + switch (entry->type) { + case MCLK_TYPE_PSC: + clks_idx_pub = MPC512x_CLK_PSC0_MCLK + idx; + clks_idx_int = MPC512x_CLK_MCLKS_FIRST + + (idx) * MCLK_MAX_IDX; + mccr_reg = &clkregs->psc_ccr[idx]; + break; + case MCLK_TYPE_MSCAN: + clks_idx_pub = MPC512x_CLK_MSCAN0_MCLK + idx; + clks_idx_int = MPC512x_CLK_MCLKS_FIRST + + (NR_PSCS + idx) * MCLK_MAX_IDX; + mccr_reg = &clkregs->mscan_ccr[idx]; + break; + case MCLK_TYPE_SPDIF: + clks_idx_pub = MPC512x_CLK_SPDIF_MCLK; + clks_idx_int = MPC512x_CLK_MCLKS_FIRST + + (NR_PSCS + NR_MSCANS) * MCLK_MAX_IDX; + mccr_reg = &clkregs->spccr; + break; + case MCLK_TYPE_OUTCLK: + clks_idx_pub = MPC512x_CLK_OUT0_CLK + idx; + clks_idx_int = MPC512x_CLK_MCLKS_FIRST + + (NR_PSCS + NR_MSCANS + NR_SPDIFS + idx) + * MCLK_MAX_IDX; + mccr_reg = &clkregs->out_ccr[idx]; + break; + default: + return; + } + + /* + * this was grabbed from the PPC_CLOCK implementation, which + * enforced a specific MCLK divider while the clock was gated + * during setup (that's a documented hardware requirement) + * + * the PPC_CLOCK implementation might even have violated the + * "MCLK <= IPS" constraint, the fixed divider value of 1 + * results in a divider of 2 and thus MCLK = SYS/2 which equals + * CSB which is greater than IPS; the serial port setup may have + * adjusted the divider which the clock setup might have left in + * an undesirable state + * + * initial setup is: + * - MCLK 0 from SYS + * - MCLK DIV such to not exceed the IPS clock + * - MCLK 0 enabled + * - MCLK 1 from MCLK DIV + */ + div = clk_get_rate(clks[MPC512x_CLK_SYS]); + div /= clk_get_rate(clks[MPC512x_CLK_IPS]); + out_be32(mccr_reg, (0 << 16)); + out_be32(mccr_reg, (0 << 16) | ((div - 1) << 17)); + out_be32(mccr_reg, (1 << 16) | ((div - 1) << 17)); + + /* + * create the 'struct clk' items of the MCLK's clock subtree + * + * note that by design we always create all nodes and won't take + * shortcuts here, because + * - the "internal" MCLK_DIV and MCLK_OUT signal in turn are + * selectable inputs to the CFM while those who "actually use" + * the PSC/MSCAN/SPDIF (serial drivers et al) need the MCLK + * for their bitrate + * - in the absence of "aliases" for clocks we need to create + * individial 'struct clk' items for whatever might get + * referenced or looked up, even if several of those items are + * identical from the logical POV (their rate value) + * - for easier future maintenance and for better reflection of + * the SoC's documentation, it appears appropriate to generate + * clock items even for those muxers which actually are NOPs + * (those with two inputs of which one is reserved) + */ + clks[clks_idx_int + MCLK_IDX_MUX0] = mpc512x_clk_muxed( + entry->name_mux0, + soc_has_mclk_mux0_canin() + ? &parent_names_mux0_canin[0] + : &parent_names_mux0_spdif[0], + ARRAY_SIZE(parent_names_mux0_spdif), + mccr_reg, 14, 2); + clks[clks_idx_int + MCLK_IDX_EN0] = mpc512x_clk_gated( + entry->name_en0, entry->name_mux0, + mccr_reg, 16); + clks[clks_idx_int + MCLK_IDX_DIV0] = mpc512x_clk_divider( + entry->name_div0, + entry->name_en0, CLK_SET_RATE_GATE, + mccr_reg, 17, 15, 0); + if (entry->has_mclk1) { + clks[clks_idx_pub] = mpc512x_clk_muxed( + entry->name_mclk, + &entry->parent_names_mux1[0], + ARRAY_SIZE(entry->parent_names_mux1), + mccr_reg, 7, 1); + } else { + clks[clks_idx_pub] = mpc512x_clk_factor( + entry->name_mclk, + entry->parent_names_mux1[0], + 1, 1); + } +} + +/* }}} MCLK helpers */ + +static void mpc512x_clk_setup_clock_tree(struct device_node *np, int busfreq) +{ + int sys_mul, sys_div, ips_div; + int mul, div; + size_t mclk_idx; + int freq; + + /* + * developer's notes: + * - consider whether to handle clocks which have both gates and + * dividers via intermediates or by means of composites + * - fractional dividers appear to not map well to composites + * since they can be seen as a fixed multiplier and an + * adjustable divider, while composites can only combine at + * most one of a mux, div, and gate each into one 'struct clk' + * item + * - PSC/MSCAN/SPDIF clock generation OTOH already is very + * specific and cannot get mapped to componsites (at least not + * a single one, maybe two of them, but then some of these + * intermediate clock signals get referenced elsewhere (e.g. + * in the clock frequency measurement, CFM) and thus need + * publicly available names + * - the current source layout appropriately reflects the + * hardware setup, and it works, so it's questionable whether + * further changes will result in big enough a benefit + */ + + /* regardless of whether XTAL/OSC exists, have REF created */ + mpc512x_clk_setup_ref_clock(np, busfreq, &sys_mul, &sys_div, &ips_div); + + /* now setup the REF -> SYS -> CSB -> IPS hierarchy */ + clks[MPC512x_CLK_SYS] = mpc512x_clk_factor("sys", "ref", + sys_mul, sys_div); + clks[MPC512x_CLK_CSB] = mpc512x_clk_factor("csb", "sys", 1, 2); + clks[MPC512x_CLK_IPS] = mpc512x_clk_divtable("ips", "csb", + &clkregs->scfr1, 23, 3, + divtab_2346); + /* now setup anything below SYS and CSB and IPS */ + + clks[MPC512x_CLK_DDR_UG] = mpc512x_clk_factor("ddr-ug", "sys", 1, 2); + + /* + * the Reference Manual discusses that for SDHC only even divide + * ratios are supported because clock domain synchronization + * between 'per' and 'ipg' is broken; + * keep the divider's bit 0 cleared (per reset value), and only + * allow to setup the divider's bits 7:1, which results in that + * only even divide ratios can get configured upon rate changes; + * keep the "x4" name because this bit shift hack is an internal + * implementation detail, the "fractional divider with quarters" + * semantics remains + */ + clks[MPC512x_CLK_SDHC_x4] = mpc512x_clk_factor("sdhc-x4", "csb", 2, 1); + clks[MPC512x_CLK_SDHC_UG] = mpc512x_clk_divider("sdhc-ug", "sdhc-x4", 0, + &clkregs->scfr2, 1, 7, + CLK_DIVIDER_ONE_BASED); + if (soc_has_sdhc2()) { + clks[MPC512x_CLK_SDHC2_UG] = mpc512x_clk_divider( + "sdhc2-ug", "sdhc-x4", 0, &clkregs->scfr2, + 9, 7, CLK_DIVIDER_ONE_BASED); + } + + clks[MPC512x_CLK_DIU_x4] = mpc512x_clk_factor("diu-x4", "csb", 4, 1); + clks[MPC512x_CLK_DIU_UG] = mpc512x_clk_divider("diu-ug", "diu-x4", 0, + &clkregs->scfr1, 0, 8, + CLK_DIVIDER_ONE_BASED); + + /* + * the "power architecture PLL" was setup from data which was + * sampled from the reset config word, at this point in time the + * configuration can be considered fixed and read only (i.e. no + * longer adjustable, or no longer in need of adjustment), which + * is why we don't register a PLL here but assume fixed factors + */ + mul = get_cpmf_mult_x2(); + div = 2; /* compensate for the fractional factor */ + clks[MPC512x_CLK_E300] = mpc512x_clk_factor("e300", "csb", mul, div); + + if (soc_has_mbx()) { + clks[MPC512x_CLK_MBX_BUS_UG] = mpc512x_clk_factor( + "mbx-bus-ug", "csb", 1, 2); + clks[MPC512x_CLK_MBX_UG] = mpc512x_clk_divtable( + "mbx-ug", "mbx-bus-ug", &clkregs->scfr1, + 14, 3, divtab_1234); + clks[MPC512x_CLK_MBX_3D_UG] = mpc512x_clk_factor( + "mbx-3d-ug", "mbx-ug", 1, 1); + } + if (soc_has_pci()) { + clks[MPC512x_CLK_PCI_UG] = mpc512x_clk_divtable( + "pci-ug", "csb", &clkregs->scfr1, + 20, 3, divtab_2346); + } + if (soc_has_nfc_5125()) { + /* + * XXX TODO implement 5125 NFC clock setup logic, + * with high/low period counters in clkregs->scfr3, + * currently there are no users so it's ENOIMPL + */ + clks[MPC512x_CLK_NFC_UG] = ERR_PTR(-ENOTSUPP); + } else { + clks[MPC512x_CLK_NFC_UG] = mpc512x_clk_divtable( + "nfc-ug", "ips", &clkregs->scfr1, + 8, 3, divtab_1234); + } + clks[MPC512x_CLK_LPC_UG] = mpc512x_clk_divtable("lpc-ug", "ips", + &clkregs->scfr1, 11, 3, + divtab_1234); + + clks[MPC512x_CLK_LPC] = mpc512x_clk_gated("lpc", "lpc-ug", + &clkregs->sccr1, 30); + clks[MPC512x_CLK_NFC] = mpc512x_clk_gated("nfc", "nfc-ug", + &clkregs->sccr1, 29); + if (soc_has_pata()) { + clks[MPC512x_CLK_PATA] = mpc512x_clk_gated( + "pata", "ips", &clkregs->sccr1, 28); + } + /* for PSCs there is a "registers" gate and a bitrate MCLK subtree */ + for (mclk_idx = 0; mclk_idx < soc_max_pscnum(); mclk_idx++) { + char name[12]; + snprintf(name, sizeof(name), "psc%d", mclk_idx); + clks[MPC512x_CLK_PSC0 + mclk_idx] = mpc512x_clk_gated( + name, "ips", &clkregs->sccr1, 27 - mclk_idx); + mpc512x_clk_setup_mclk(&mclk_psc_data[mclk_idx], mclk_idx); + } + clks[MPC512x_CLK_PSC_FIFO] = mpc512x_clk_gated("psc-fifo", "ips", + &clkregs->sccr1, 15); + if (soc_has_sata()) { + clks[MPC512x_CLK_SATA] = mpc512x_clk_gated( + "sata", "ips", &clkregs->sccr1, 14); + } + clks[MPC512x_CLK_FEC] = mpc512x_clk_gated("fec", "ips", + &clkregs->sccr1, 13); + if (soc_has_pci()) { + clks[MPC512x_CLK_PCI] = mpc512x_clk_gated( + "pci", "pci-ug", &clkregs->sccr1, 11); + } + clks[MPC512x_CLK_DDR] = mpc512x_clk_gated("ddr", "ddr-ug", + &clkregs->sccr1, 10); + if (soc_has_fec2()) { + clks[MPC512x_CLK_FEC2] = mpc512x_clk_gated( + "fec2", "ips", &clkregs->sccr1, 9); + } + + clks[MPC512x_CLK_DIU] = mpc512x_clk_gated("diu", "diu-ug", + &clkregs->sccr2, 31); + if (soc_has_axe()) { + clks[MPC512x_CLK_AXE] = mpc512x_clk_gated( + "axe", "csb", &clkregs->sccr2, 30); + } + clks[MPC512x_CLK_MEM] = mpc512x_clk_gated("mem", "ips", + &clkregs->sccr2, 29); + clks[MPC512x_CLK_USB1] = mpc512x_clk_gated("usb1", "csb", + &clkregs->sccr2, 28); + clks[MPC512x_CLK_USB2] = mpc512x_clk_gated("usb2", "csb", + &clkregs->sccr2, 27); + clks[MPC512x_CLK_I2C] = mpc512x_clk_gated("i2c", "ips", + &clkregs->sccr2, 26); + /* MSCAN differs from PSC with just one gate for multiple components */ + clks[MPC512x_CLK_BDLC] = mpc512x_clk_gated("bdlc", "ips", + &clkregs->sccr2, 25); + for (mclk_idx = 0; mclk_idx < ARRAY_SIZE(mclk_mscan_data); mclk_idx++) + mpc512x_clk_setup_mclk(&mclk_mscan_data[mclk_idx], mclk_idx); + clks[MPC512x_CLK_SDHC] = mpc512x_clk_gated("sdhc", "sdhc-ug", + &clkregs->sccr2, 24); + /* there is only one SPDIF component, which shares MCLK support code */ + if (soc_has_spdif()) { + clks[MPC512x_CLK_SPDIF] = mpc512x_clk_gated( + "spdif", "ips", &clkregs->sccr2, 23); + mpc512x_clk_setup_mclk(&mclk_spdif_data[0], 0); + } + if (soc_has_mbx()) { + clks[MPC512x_CLK_MBX_BUS] = mpc512x_clk_gated( + "mbx-bus", "mbx-bus-ug", &clkregs->sccr2, 22); + clks[MPC512x_CLK_MBX] = mpc512x_clk_gated( + "mbx", "mbx-ug", &clkregs->sccr2, 21); + clks[MPC512x_CLK_MBX_3D] = mpc512x_clk_gated( + "mbx-3d", "mbx-3d-ug", &clkregs->sccr2, 20); + } + clks[MPC512x_CLK_IIM] = mpc512x_clk_gated("iim", "csb", + &clkregs->sccr2, 19); + if (soc_has_viu()) { + clks[MPC512x_CLK_VIU] = mpc512x_clk_gated( + "viu", "csb", &clkregs->sccr2, 18); + } + if (soc_has_sdhc2()) { + clks[MPC512x_CLK_SDHC2] = mpc512x_clk_gated( + "sdhc-2", "sdhc2-ug", &clkregs->sccr2, 17); + } + + if (soc_has_outclk()) { + size_t idx; /* used as mclk_idx, just to trim line length */ + for (idx = 0; idx < ARRAY_SIZE(mclk_outclk_data); idx++) + mpc512x_clk_setup_mclk(&mclk_outclk_data[idx], idx); + } + + /* + * externally provided clocks (when implemented in hardware, + * device tree may specify values which otherwise were unknown) + */ + freq = get_freq_from_dt("psc_mclk_in"); + if (!freq) + freq = 25000000; + clks[MPC512x_CLK_PSC_MCLK_IN] = mpc512x_clk_fixed("psc_mclk_in", freq); + if (soc_has_mclk_mux0_canin()) { + freq = get_freq_from_dt("can_clk_in"); + clks[MPC512x_CLK_CAN_CLK_IN] = mpc512x_clk_fixed( + "can_clk_in", freq); + } else { + freq = get_freq_from_dt("spdif_tx_in"); + clks[MPC512x_CLK_SPDIF_TX_IN] = mpc512x_clk_fixed( + "spdif_tx_in", freq); + freq = get_freq_from_dt("spdif_rx_in"); + clks[MPC512x_CLK_SPDIF_TX_IN] = mpc512x_clk_fixed( + "spdif_rx_in", freq); + } + + /* fixed frequency for AC97, always 24.567MHz */ + clks[MPC512x_CLK_AC97] = mpc512x_clk_fixed("ac97", 24567000); + + /* + * pre-enable those "internal" clock items which never get + * claimed by any peripheral driver, to not have the clock + * subsystem disable them late at startup + */ + clk_prepare_enable(clks[MPC512x_CLK_DUMMY]); + clk_prepare_enable(clks[MPC512x_CLK_E300]); /* PowerPC CPU */ + clk_prepare_enable(clks[MPC512x_CLK_DDR]); /* DRAM */ + clk_prepare_enable(clks[MPC512x_CLK_MEM]); /* SRAM */ + clk_prepare_enable(clks[MPC512x_CLK_IPS]); /* SoC periph */ + clk_prepare_enable(clks[MPC512x_CLK_LPC]); /* boot media */ +} + +/* + * registers the set of public clocks (those listed in the dt-bindings/ + * header file) for OF lookups, keeps the intermediates private to us + */ +static void mpc5121_clk_register_of_provider(struct device_node *np) +{ + clk_data.clks = clks; + clk_data.clk_num = MPC512x_CLK_LAST_PUBLIC + 1; /* _not_ ARRAY_SIZE() */ + of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data); +} + +/* + * temporary support for the period of time between introduction of CCF + * support and the adjustment of peripheral drivers to OF based lookups + */ +static void mpc5121_clk_provide_migration_support(void) +{ + + /* + * pre-enable those clock items which are not yet appropriately + * acquired by their peripheral driver + * + * the PCI clock cannot get acquired by its peripheral driver, + * because for this platform the driver won't probe(), instead + * initialization is done from within the .setup_arch() routine + * at a point in time where the clock provider has not been + * setup yet and thus isn't available yet + * + * so we "pre-enable" the clock here, to not have the clock + * subsystem automatically disable this item in a late init call + * + * this PCI clock pre-enable workaround only applies when there + * are device tree nodes for PCI and thus the peripheral driver + * has attached to bridges, otherwise the PCI clock remains + * unused and so it gets disabled + */ + clk_prepare_enable(clks[MPC512x_CLK_PSC3_MCLK]);/* serial console */ + if (of_find_compatible_node(NULL, "pci", "fsl,mpc5121-pci")) + clk_prepare_enable(clks[MPC512x_CLK_PCI]); +} + +/* + * those macros are not exactly pretty, but they encapsulate a lot + * of copy'n'paste heavy code which is even more ugly, and reduce + * the potential for inconsistencies in those many code copies + */ +#define FOR_NODES(compatname) \ + for_each_compatible_node(np, NULL, compatname) + +#define NODE_PREP do { \ + of_address_to_resource(np, 0, &res); \ + snprintf(devname, sizeof(devname), "%08x.%s", res.start, np->name); \ +} while (0) + +#define NODE_CHK(clkname, clkitem, regnode, regflag) do { \ + struct clk *clk; \ + clk = of_clk_get_by_name(np, clkname); \ + if (IS_ERR(clk)) { \ + clk = clkitem; \ + clk_register_clkdev(clk, clkname, devname); \ + if (regnode) \ + clk_register_clkdev(clk, clkname, np->name); \ + did_register |= DID_REG_ ## regflag; \ + pr_debug("clock alias name '%s' for dev '%s' pointer %p\n", \ + clkname, devname, clk); \ + } else { \ + clk_put(clk); \ + } \ +} while (0) + +/* + * register source code provided fallback results for clock lookups, + * these get consulted when OF based clock lookup fails (that is in the + * case of not yet adjusted device tree data, where clock related specs + * are missing) + */ +static void mpc5121_clk_provide_backwards_compat(void) +{ + enum did_reg_flags { + DID_REG_PSC = BIT(0), + DID_REG_PSCFIFO = BIT(1), + DID_REG_NFC = BIT(2), + DID_REG_CAN = BIT(3), + DID_REG_I2C = BIT(4), + DID_REG_DIU = BIT(5), + DID_REG_VIU = BIT(6), + DID_REG_FEC = BIT(7), + DID_REG_USB = BIT(8), + DID_REG_PATA = BIT(9), + }; + + int did_register; + struct device_node *np; + struct resource res; + int idx; + char devname[32]; + + did_register = 0; + + FOR_NODES(mpc512x_select_psc_compat()) { + NODE_PREP; + idx = (res.start >> 8) & 0xf; + NODE_CHK("ipg", clks[MPC512x_CLK_PSC0 + idx], 0, PSC); + NODE_CHK("mclk", clks[MPC512x_CLK_PSC0_MCLK + idx], 0, PSC); + } + + FOR_NODES("fsl,mpc5121-psc-fifo") { + NODE_PREP; + NODE_CHK("ipg", clks[MPC512x_CLK_PSC_FIFO], 1, PSCFIFO); + } + + FOR_NODES("fsl,mpc5121-nfc") { + NODE_PREP; + NODE_CHK("ipg", clks[MPC512x_CLK_NFC], 0, NFC); + } + + FOR_NODES("fsl,mpc5121-mscan") { + NODE_PREP; + idx = 0; + idx += (res.start & 0x2000) ? 2 : 0; + idx += (res.start & 0x0080) ? 1 : 0; + NODE_CHK("ipg", clks[MPC512x_CLK_BDLC], 0, CAN); + NODE_CHK("mclk", clks[MPC512x_CLK_MSCAN0_MCLK + idx], 0, CAN); + } + + /* + * do register the 'ips', 'sys', and 'ref' names globally + * instead of inside each individual CAN node, as there is no + * potential for a name conflict (in contrast to 'ipg' and 'mclk') + */ + if (did_register & DID_REG_CAN) { + clk_register_clkdev(clks[MPC512x_CLK_IPS], "ips", NULL); + clk_register_clkdev(clks[MPC512x_CLK_SYS], "sys", NULL); + clk_register_clkdev(clks[MPC512x_CLK_REF], "ref", NULL); + } + + FOR_NODES("fsl,mpc5121-i2c") { + NODE_PREP; + NODE_CHK("ipg", clks[MPC512x_CLK_I2C], 0, I2C); + } + + /* + * workaround for the fact that the I2C driver does an "anonymous" + * lookup (NULL name spec, which yields the first clock spec) for + * which we cannot register an alias -- a _global_ 'ipg' alias that + * is not bound to any device name and returns the I2C clock item + * is not a good idea + * + * so we have the lookup in the peripheral driver fail, which is + * silent and non-fatal, and pre-enable the clock item here such + * that register access is possible + * + * see commit b3bfce2b "i2c: mpc: cleanup clock API use" for + * details, adjusting s/NULL/"ipg"/ in i2c-mpc.c would make this + * workaround obsolete + */ + if (did_register & DID_REG_I2C) + clk_prepare_enable(clks[MPC512x_CLK_I2C]); + + FOR_NODES("fsl,mpc5121-diu") { + NODE_PREP; + NODE_CHK("ipg", clks[MPC512x_CLK_DIU], 1, DIU); + } + + FOR_NODES("fsl,mpc5121-viu") { + NODE_PREP; + NODE_CHK("ipg", clks[MPC512x_CLK_VIU], 0, VIU); + } + + /* + * note that 2771399a "fs_enet: cleanup clock API use" did use the + * "per" string for the clock lookup in contrast to the "ipg" name + * which most other nodes are using -- this is not a fatal thing + * but just something to keep in mind when doing compatibility + * registration, it's a non-issue with up-to-date device tree data + */ + FOR_NODES("fsl,mpc5121-fec") { + NODE_PREP; + NODE_CHK("per", clks[MPC512x_CLK_FEC], 0, FEC); + } + FOR_NODES("fsl,mpc5121-fec-mdio") { + NODE_PREP; + NODE_CHK("per", clks[MPC512x_CLK_FEC], 0, FEC); + } + /* + * MPC5125 has two FECs: FEC1 at 0x2800, FEC2 at 0x4800; + * the clock items don't "form an array" since FEC2 was + * added only later and was not allowed to shift all other + * clock item indices, so the numbers aren't adjacent + */ + FOR_NODES("fsl,mpc5125-fec") { + NODE_PREP; + if (res.start & 0x4000) + idx = MPC512x_CLK_FEC2; + else + idx = MPC512x_CLK_FEC; + NODE_CHK("per", clks[idx], 0, FEC); + } + + FOR_NODES("fsl,mpc5121-usb2-dr") { + NODE_PREP; + idx = (res.start & 0x4000) ? 1 : 0; + NODE_CHK("ipg", clks[MPC512x_CLK_USB1 + idx], 0, USB); + } + + FOR_NODES("fsl,mpc5121-pata") { + NODE_PREP; + NODE_CHK("ipg", clks[MPC512x_CLK_PATA], 0, PATA); + } + + /* + * try to collapse diagnostics into a single line of output yet + * provide a full list of what is missing, to avoid noise in the + * absence of up-to-date device tree data -- backwards + * compatibility to old DTBs is a requirement, updates may be + * desirable or preferrable but are not at all mandatory + */ + if (did_register) { + pr_notice("device tree lacks clock specs, adding fallbacks (0x%x,%s%s%s%s%s%s%s%s%s%s)\n", + did_register, + (did_register & DID_REG_PSC) ? " PSC" : "", + (did_register & DID_REG_PSCFIFO) ? " PSCFIFO" : "", + (did_register & DID_REG_NFC) ? " NFC" : "", + (did_register & DID_REG_CAN) ? " CAN" : "", + (did_register & DID_REG_I2C) ? " I2C" : "", + (did_register & DID_REG_DIU) ? " DIU" : "", + (did_register & DID_REG_VIU) ? " VIU" : "", + (did_register & DID_REG_FEC) ? " FEC" : "", + (did_register & DID_REG_USB) ? " USB" : "", + (did_register & DID_REG_PATA) ? " PATA" : ""); + } else { + pr_debug("device tree has clock specs, no fallbacks added\n"); + } +} + +int __init mpc5121_clk_init(void) +{ + struct device_node *clk_np; + int busfreq; + + /* map the clock control registers */ + clk_np = of_find_compatible_node(NULL, NULL, "fsl,mpc5121-clock"); + if (!clk_np) + return -ENODEV; + clkregs = of_iomap(clk_np, 0); + WARN_ON(!clkregs); + + /* determine the SoC variant we run on */ + mpc512x_clk_determine_soc(); + + /* invalidate all not yet registered clock slots */ + mpc512x_clk_preset_data(); + + /* + * have the device tree scanned for "fixed-clock" nodes (which + * includes the oscillator node if the board's DT provides one) + */ + of_clk_init(NULL); + + /* + * add a dummy clock for those situations where a clock spec is + * required yet no real clock is involved + */ + clks[MPC512x_CLK_DUMMY] = mpc512x_clk_fixed("dummy", 0); + + /* + * have all the real nodes in the clock tree populated from REF + * down to all leaves, either starting from the OSC node or from + * a REF root that was created from the IPS bus clock input + */ + busfreq = get_freq_from_dt("bus-frequency"); + mpc512x_clk_setup_clock_tree(clk_np, busfreq); + + /* register as an OF clock provider */ + mpc5121_clk_register_of_provider(clk_np); + + /* + * unbreak not yet adjusted peripheral drivers during migration + * towards fully operational common clock support, and allow + * operation in the absence of clock related device tree specs + */ + mpc5121_clk_provide_migration_support(); + mpc5121_clk_provide_backwards_compat(); + + return 0; +} diff --git a/arch/powerpc/platforms/512x/clock.c b/arch/powerpc/platforms/512x/clock.c deleted file mode 100644 index 9f771e05457..00000000000 --- a/arch/powerpc/platforms/512x/clock.c +++ /dev/null @@ -1,746 +0,0 @@ -/* - * Copyright (C) 2007,2008 Freescale Semiconductor, Inc. All rights reserved. - * - * Author: John Rigby <jrigby@freescale.com> - * - * Implements the clk api defined in include/linux/clk.h - * - * Original based on linux/arch/arm/mach-integrator/clock.c - * - * Copyright (C) 2004 ARM Limited. - * Written by Deep Blue Solutions Limited. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#include <linux/kernel.h> -#include <linux/list.h> -#include <linux/errno.h> -#include <linux/err.h> -#include <linux/module.h> -#include <linux/string.h> -#include <linux/clk.h> -#include <linux/mutex.h> -#include <linux/io.h> - -#include <linux/of_platform.h> -#include <asm/mpc5xxx.h> -#include <asm/clk_interface.h> - -#undef CLK_DEBUG - -static int clocks_initialized; - -#define CLK_HAS_RATE 0x1 /* has rate in MHz */ -#define CLK_HAS_CTRL 0x2 /* has control reg and bit */ - -struct clk { - struct list_head node; - char name[32]; - int flags; - struct device *dev; - unsigned long rate; - struct module *owner; - void (*calc) (struct clk *); - struct clk *parent; - int reg, bit; /* CLK_HAS_CTRL */ - int div_shift; /* only used by generic_div_clk_calc */ -}; - -static LIST_HEAD(clocks); -static DEFINE_MUTEX(clocks_mutex); - -static struct clk *mpc5121_clk_get(struct device *dev, const char *id) -{ - struct clk *p, *clk = ERR_PTR(-ENOENT); - int dev_match; - int id_match; - - if (dev == NULL || id == NULL) - return clk; - - mutex_lock(&clocks_mutex); - list_for_each_entry(p, &clocks, node) { - dev_match = id_match = 0; - - if (dev == p->dev) - dev_match++; - if (strcmp(id, p->name) == 0) - id_match++; - if ((dev_match || id_match) && try_module_get(p->owner)) { - clk = p; - break; - } - } - mutex_unlock(&clocks_mutex); - - return clk; -} - -#ifdef CLK_DEBUG -static void dump_clocks(void) -{ - struct clk *p; - - mutex_lock(&clocks_mutex); - printk(KERN_INFO "CLOCKS:\n"); - list_for_each_entry(p, &clocks, node) { - pr_info(" %s=%ld", p->name, p->rate); - if (p->parent) - pr_cont(" %s=%ld", p->parent->name, - p->parent->rate); - if (p->flags & CLK_HAS_CTRL) - pr_cont(" reg/bit=%d/%d", p->reg, p->bit); - pr_cont("\n"); - } - mutex_unlock(&clocks_mutex); -} -#define DEBUG_CLK_DUMP() dump_clocks() -#else -#define DEBUG_CLK_DUMP() -#endif - - -static void mpc5121_clk_put(struct clk *clk) -{ - module_put(clk->owner); -} - -#define NRPSC 12 - -struct mpc512x_clockctl { - u32 spmr; /* System PLL Mode Reg */ - u32 sccr[2]; /* System Clk Ctrl Reg 1 & 2 */ - u32 scfr1; /* System Clk Freq Reg 1 */ - u32 scfr2; /* System Clk Freq Reg 2 */ - u32 reserved; - u32 bcr; /* Bread Crumb Reg */ - u32 pccr[NRPSC]; /* PSC Clk Ctrl Reg 0-11 */ - u32 spccr; /* SPDIF Clk Ctrl Reg */ - u32 cccr; /* CFM Clk Ctrl Reg */ - u32 dccr; /* DIU Clk Cnfg Reg */ -}; - -struct mpc512x_clockctl __iomem *clockctl; - -static int mpc5121_clk_enable(struct clk *clk) -{ - unsigned int mask; - - if (clk->flags & CLK_HAS_CTRL) { - mask = in_be32(&clockctl->sccr[clk->reg]); - mask |= 1 << clk->bit; - out_be32(&clockctl->sccr[clk->reg], mask); - } - return 0; -} - -static void mpc5121_clk_disable(struct clk *clk) -{ - unsigned int mask; - - if (clk->flags & CLK_HAS_CTRL) { - mask = in_be32(&clockctl->sccr[clk->reg]); - mask &= ~(1 << clk->bit); - out_be32(&clockctl->sccr[clk->reg], mask); - } -} - -static unsigned long mpc5121_clk_get_rate(struct clk *clk) -{ - if (clk->flags & CLK_HAS_RATE) - return clk->rate; - else - return 0; -} - -static long mpc5121_clk_round_rate(struct clk *clk, unsigned long rate) -{ - return rate; -} - -static int mpc5121_clk_set_rate(struct clk *clk, unsigned long rate) -{ - return 0; -} - -static int clk_register(struct clk *clk) -{ - mutex_lock(&clocks_mutex); - list_add(&clk->node, &clocks); - mutex_unlock(&clocks_mutex); - return 0; -} - -static unsigned long spmf_mult(void) -{ - /* - * Convert spmf to multiplier - */ - static int spmf_to_mult[] = { - 68, 1, 12, 16, - 20, 24, 28, 32, - 36, 40, 44, 48, - 52, 56, 60, 64 - }; - int spmf = (clockctl->spmr >> 24) & 0xf; - return spmf_to_mult[spmf]; -} - -static unsigned long sysdiv_div_x_2(void) -{ - /* - * Convert sysdiv to divisor x 2 - * Some divisors have fractional parts so - * multiply by 2 then divide by this value - */ - static int sysdiv_to_div_x_2[] = { - 4, 5, 6, 7, - 8, 9, 10, 14, - 12, 16, 18, 22, - 20, 24, 26, 30, - 28, 32, 34, 38, - 36, 40, 42, 46, - 44, 48, 50, 54, - 52, 56, 58, 62, - 60, 64, 66, - }; - int sysdiv = (clockctl->scfr2 >> 26) & 0x3f; - return sysdiv_to_div_x_2[sysdiv]; -} - -static unsigned long ref_to_sys(unsigned long rate) -{ - rate *= spmf_mult(); - rate *= 2; - rate /= sysdiv_div_x_2(); - - return rate; -} - -static unsigned long sys_to_ref(unsigned long rate) -{ - rate *= sysdiv_div_x_2(); - rate /= 2; - rate /= spmf_mult(); - - return rate; -} - -static long ips_to_ref(unsigned long rate) -{ - int ips_div = (clockctl->scfr1 >> 23) & 0x7; - - rate *= ips_div; /* csb_clk = ips_clk * ips_div */ - rate *= 2; /* sys_clk = csb_clk * 2 */ - return sys_to_ref(rate); -} - -static unsigned long devtree_getfreq(char *clockname) -{ - struct device_node *np; - const unsigned int *prop; - unsigned int val = 0; - - np = of_find_compatible_node(NULL, NULL, "fsl,mpc5121-immr"); - if (np) { - prop = of_get_property(np, clockname, NULL); - if (prop) - val = *prop; - of_node_put(np); - } - return val; -} - -static void ref_clk_calc(struct clk *clk) -{ - unsigned long rate; - - rate = devtree_getfreq("bus-frequency"); - if (rate == 0) { - printk(KERN_ERR "No bus-frequency in dev tree\n"); - clk->rate = 0; - return; - } - clk->rate = ips_to_ref(rate); -} - -static struct clk ref_clk = { - .name = "ref_clk", - .calc = ref_clk_calc, -}; - - -static void sys_clk_calc(struct clk *clk) -{ - clk->rate = ref_to_sys(ref_clk.rate); -} - -static struct clk sys_clk = { - .name = "sys_clk", - .calc = sys_clk_calc, -}; - -static void diu_clk_calc(struct clk *clk) -{ - int diudiv_x_2 = clockctl->scfr1 & 0xff; - unsigned long rate; - - rate = sys_clk.rate; - - rate *= 2; - rate /= diudiv_x_2; - - clk->rate = rate; -} - -static void viu_clk_calc(struct clk *clk) -{ - unsigned long rate; - - rate = sys_clk.rate; - rate /= 2; - clk->rate = rate; -} - -static void half_clk_calc(struct clk *clk) -{ - clk->rate = clk->parent->rate / 2; -} - -static void generic_div_clk_calc(struct clk *clk) -{ - int div = (clockctl->scfr1 >> clk->div_shift) & 0x7; - - clk->rate = clk->parent->rate / div; -} - -static void unity_clk_calc(struct clk *clk) -{ - clk->rate = clk->parent->rate; -} - -static struct clk csb_clk = { - .name = "csb_clk", - .calc = half_clk_calc, - .parent = &sys_clk, -}; - -static void e300_clk_calc(struct clk *clk) -{ - int spmf = (clockctl->spmr >> 16) & 0xf; - int ratex2 = clk->parent->rate * spmf; - - clk->rate = ratex2 / 2; -} - -static struct clk e300_clk = { - .name = "e300_clk", - .calc = e300_clk_calc, - .parent = &csb_clk, -}; - -static struct clk ips_clk = { - .name = "ips_clk", - .calc = generic_div_clk_calc, - .parent = &csb_clk, - .div_shift = 23, -}; - -/* - * Clocks controlled by SCCR1 (.reg = 0) - */ -static struct clk lpc_clk = { - .name = "lpc_clk", - .flags = CLK_HAS_CTRL, - .reg = 0, - .bit = 30, - .calc = generic_div_clk_calc, - .parent = &ips_clk, - .div_shift = 11, -}; - -static struct clk nfc_clk = { - .name = "nfc_clk", - .flags = CLK_HAS_CTRL, - .reg = 0, - .bit = 29, - .calc = generic_div_clk_calc, - .parent = &ips_clk, - .div_shift = 8, -}; - -static struct clk pata_clk = { - .name = "pata_clk", - .flags = CLK_HAS_CTRL, - .reg = 0, - .bit = 28, - .calc = unity_clk_calc, - .parent = &ips_clk, -}; - -/* - * PSC clocks (bits 27 - 16) - * are setup elsewhere - */ - -static struct clk sata_clk = { - .name = "sata_clk", - .flags = CLK_HAS_CTRL, - .reg = 0, - .bit = 14, - .calc = unity_clk_calc, - .parent = &ips_clk, -}; - -static struct clk fec_clk = { - .name = "fec_clk", - .flags = CLK_HAS_CTRL, - .reg = 0, - .bit = 13, - .calc = unity_clk_calc, - .parent = &ips_clk, -}; - -static struct clk pci_clk = { - .name = "pci_clk", - .flags = CLK_HAS_CTRL, - .reg = 0, - .bit = 11, - .calc = generic_div_clk_calc, - .parent = &csb_clk, - .div_shift = 20, -}; - -/* - * Clocks controlled by SCCR2 (.reg = 1) - */ -static struct clk diu_clk = { - .name = "diu_clk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 31, - .calc = diu_clk_calc, -}; - -static struct clk viu_clk = { - .name = "viu_clk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 18, - .calc = viu_clk_calc, -}; - -static struct clk axe_clk = { - .name = "axe_clk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 30, - .calc = unity_clk_calc, - .parent = &csb_clk, -}; - -static struct clk usb1_clk = { - .name = "usb1_clk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 28, - .calc = unity_clk_calc, - .parent = &csb_clk, -}; - -static struct clk usb2_clk = { - .name = "usb2_clk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 27, - .calc = unity_clk_calc, - .parent = &csb_clk, -}; - -static struct clk i2c_clk = { - .name = "i2c_clk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 26, - .calc = unity_clk_calc, - .parent = &ips_clk, -}; - -static struct clk mscan_clk = { - .name = "mscan_clk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 25, - .calc = unity_clk_calc, - .parent = &ips_clk, -}; - -static struct clk sdhc_clk = { - .name = "sdhc_clk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 24, - .calc = unity_clk_calc, - .parent = &ips_clk, -}; - -static struct clk mbx_bus_clk = { - .name = "mbx_bus_clk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 22, - .calc = half_clk_calc, - .parent = &csb_clk, -}; - -static struct clk mbx_clk = { - .name = "mbx_clk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 21, - .calc = unity_clk_calc, - .parent = &csb_clk, -}; - -static struct clk mbx_3d_clk = { - .name = "mbx_3d_clk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 20, - .calc = generic_div_clk_calc, - .parent = &mbx_bus_clk, - .div_shift = 14, -}; - -static void psc_mclk_in_calc(struct clk *clk) -{ - clk->rate = devtree_getfreq("psc_mclk_in"); - if (!clk->rate) - clk->rate = 25000000; -} - -static struct clk psc_mclk_in = { - .name = "psc_mclk_in", - .calc = psc_mclk_in_calc, -}; - -static struct clk spdif_txclk = { - .name = "spdif_txclk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 23, -}; - -static struct clk spdif_rxclk = { - .name = "spdif_rxclk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 23, -}; - -static void ac97_clk_calc(struct clk *clk) -{ - /* ac97 bit clock is always 24.567 MHz */ - clk->rate = 24567000; -} - -static struct clk ac97_clk = { - .name = "ac97_clk_in", - .calc = ac97_clk_calc, -}; - -struct clk *rate_clks[] = { - &ref_clk, - &sys_clk, - &diu_clk, - &viu_clk, - &csb_clk, - &e300_clk, - &ips_clk, - &fec_clk, - &sata_clk, - &pata_clk, - &nfc_clk, - &lpc_clk, - &mbx_bus_clk, - &mbx_clk, - &mbx_3d_clk, - &axe_clk, - &usb1_clk, - &usb2_clk, - &i2c_clk, - &mscan_clk, - &sdhc_clk, - &pci_clk, - &psc_mclk_in, - &spdif_txclk, - &spdif_rxclk, - &ac97_clk, - NULL -}; - -static void rate_clk_init(struct clk *clk) -{ - if (clk->calc) { - clk->calc(clk); - clk->flags |= CLK_HAS_RATE; - clk_register(clk); - } else { - printk(KERN_WARNING - "Could not initialize clk %s without a calc routine\n", - clk->name); - } -} - -static void rate_clks_init(void) -{ - struct clk **cpp, *clk; - - cpp = rate_clks; - while ((clk = *cpp++)) - rate_clk_init(clk); -} - -/* - * There are two clk enable registers with 32 enable bits each - * psc clocks and device clocks are all stored in dev_clks - */ -struct clk dev_clks[2][32]; - -/* - * Given a psc number return the dev_clk - * associated with it - */ -static struct clk *psc_dev_clk(int pscnum) -{ - int reg, bit; - struct clk *clk; - - reg = 0; - bit = 27 - pscnum; - - clk = &dev_clks[reg][bit]; - clk->reg = 0; - clk->bit = bit; - return clk; -} - -/* - * PSC clock rate calculation - */ -static void psc_calc_rate(struct clk *clk, int pscnum, struct device_node *np) -{ - unsigned long mclk_src = sys_clk.rate; - unsigned long mclk_div; - - /* - * Can only change value of mclk divider - * when the divider is disabled. - * - * Zero is not a valid divider so minimum - * divider is 1 - * - * disable/set divider/enable - */ - out_be32(&clockctl->pccr[pscnum], 0); - out_be32(&clockctl->pccr[pscnum], 0x00020000); - out_be32(&clockctl->pccr[pscnum], 0x00030000); - - if (clockctl->pccr[pscnum] & 0x80) { - clk->rate = spdif_rxclk.rate; - return; - } - - switch ((clockctl->pccr[pscnum] >> 14) & 0x3) { - case 0: - mclk_src = sys_clk.rate; - break; - case 1: - mclk_src = ref_clk.rate; - break; - case 2: - mclk_src = psc_mclk_in.rate; - break; - case 3: - mclk_src = spdif_txclk.rate; - break; - } - - mclk_div = ((clockctl->pccr[pscnum] >> 17) & 0x7fff) + 1; - clk->rate = mclk_src / mclk_div; -} - -/* - * Find all psc nodes in device tree and assign a clock - * with name "psc%d_mclk" and dev pointing at the device - * returned from of_find_device_by_node - */ -static void psc_clks_init(void) -{ - struct device_node *np; - const u32 *cell_index; - struct platform_device *ofdev; - - for_each_compatible_node(np, NULL, "fsl,mpc5121-psc") { - cell_index = of_get_property(np, "cell-index", NULL); - if (cell_index) { - int pscnum = *cell_index; - struct clk *clk = psc_dev_clk(pscnum); - - clk->flags = CLK_HAS_RATE | CLK_HAS_CTRL; - ofdev = of_find_device_by_node(np); - clk->dev = &ofdev->dev; - /* - * AC97 is special rate clock does - * not go through normal path - */ - if (strcmp("ac97", np->name) == 0) - clk->rate = ac97_clk.rate; - else - psc_calc_rate(clk, pscnum, np); - sprintf(clk->name, "psc%d_mclk", pscnum); - clk_register(clk); - clk_enable(clk); - } - } -} - -static struct clk_interface mpc5121_clk_functions = { - .clk_get = mpc5121_clk_get, - .clk_enable = mpc5121_clk_enable, - .clk_disable = mpc5121_clk_disable, - .clk_get_rate = mpc5121_clk_get_rate, - .clk_put = mpc5121_clk_put, - .clk_round_rate = mpc5121_clk_round_rate, - .clk_set_rate = mpc5121_clk_set_rate, - .clk_set_parent = NULL, - .clk_get_parent = NULL, -}; - -int __init mpc5121_clk_init(void) -{ - struct device_node *np; - - np = of_find_compatible_node(NULL, NULL, "fsl,mpc5121-clock"); - if (np) { - clockctl = of_iomap(np, 0); - of_node_put(np); - } - - if (!clockctl) { - printk(KERN_ERR "Could not map clock control registers\n"); - return 0; - } - - rate_clks_init(); - psc_clks_init(); - - /* leave clockctl mapped forever */ - /*iounmap(clockctl); */ - DEBUG_CLK_DUMP(); - clocks_initialized++; - clk_functions = mpc5121_clk_functions; - return 0; -} diff --git a/arch/powerpc/platforms/512x/mpc5121_ads.c b/arch/powerpc/platforms/512x/mpc5121_ads.c index 0a134e0469e..3e90ece10ae 100644 --- a/arch/powerpc/platforms/512x/mpc5121_ads.c +++ b/arch/powerpc/platforms/512x/mpc5121_ads.c @@ -43,9 +43,7 @@ static void __init mpc5121_ads_setup_arch(void) mpc83xx_add_bridge(np); #endif -#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE) - mpc512x_setup_diu(); -#endif + mpc512x_setup_arch(); } static void __init mpc5121_ads_init_IRQ(void) @@ -69,7 +67,7 @@ define_machine(mpc5121_ads) { .probe = mpc5121_ads_probe, .setup_arch = mpc5121_ads_setup_arch, .init = mpc512x_init, - .init_early = mpc512x_init_diu, + .init_early = mpc512x_init_early, .init_IRQ = mpc5121_ads_init_IRQ, .get_irq = ipic_get_irq, .calibrate_decr = generic_calibrate_decr, diff --git a/arch/powerpc/platforms/512x/mpc512x.h b/arch/powerpc/platforms/512x/mpc512x.h index c32b399eb95..cc97f022d02 100644 --- a/arch/powerpc/platforms/512x/mpc512x.h +++ b/arch/powerpc/platforms/512x/mpc512x.h @@ -12,17 +12,12 @@ #ifndef __MPC512X_H__ #define __MPC512X_H__ extern void __init mpc512x_init_IRQ(void); +extern void __init mpc512x_init_early(void); extern void __init mpc512x_init(void); +extern void __init mpc512x_setup_arch(void); extern int __init mpc5121_clk_init(void); -void __init mpc512x_declare_of_platform_devices(void); +extern const char *mpc512x_select_psc_compat(void); +extern const char *mpc512x_select_reset_compat(void); extern void mpc512x_restart(char *cmd); -#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE) -void mpc512x_init_diu(void); -void mpc512x_setup_diu(void); -#else -#define mpc512x_init_diu NULL -#define mpc512x_setup_diu NULL -#endif - #endif /* __MPC512X_H__ */ diff --git a/arch/powerpc/platforms/512x/mpc5121_generic.c b/arch/powerpc/platforms/512x/mpc512x_generic.c index ca1ca666999..ce71408781a 100644 --- a/arch/powerpc/platforms/512x/mpc5121_generic.c +++ b/arch/powerpc/platforms/512x/mpc512x_generic.c @@ -4,7 +4,7 @@ * Author: John Rigby, <jrigby@freescale.com> * * Description: - * MPC5121 SoC setup + * MPC512x SoC setup * * This is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by @@ -28,23 +28,25 @@ */ static const char * const board[] __initconst = { "prt,prtlvt", + "fsl,mpc5125ads", + "ifm,ac14xx", NULL }; /* * Called very early, MMU is off, device-tree isn't unflattened */ -static int __init mpc5121_generic_probe(void) +static int __init mpc512x_generic_probe(void) { return of_flat_dt_match(of_get_flat_dt_root(), board); } -define_machine(mpc5121_generic) { - .name = "MPC5121 generic", - .probe = mpc5121_generic_probe, +define_machine(mpc512x_generic) { + .name = "MPC512x generic", + .probe = mpc512x_generic_probe, .init = mpc512x_init, - .init_early = mpc512x_init_diu, - .setup_arch = mpc512x_setup_diu, + .init_early = mpc512x_init_early, + .setup_arch = mpc512x_setup_arch, .init_IRQ = mpc512x_init_IRQ, .get_irq = ipic_get_irq, .calibrate_decr = generic_calibrate_decr, diff --git a/arch/powerpc/platforms/512x/mpc512x_shared.c b/arch/powerpc/platforms/512x/mpc512x_shared.c index 35f14fda108..adb95f03d4d 100644 --- a/arch/powerpc/platforms/512x/mpc512x_shared.c +++ b/arch/powerpc/platforms/512x/mpc512x_shared.c @@ -12,6 +12,7 @@ * (at your option) any later version. */ +#include <linux/clk.h> #include <linux/kernel.h> #include <linux/io.h> #include <linux/irq.h> @@ -35,8 +36,10 @@ static struct mpc512x_reset_module __iomem *reset_module_base; static void __init mpc512x_restart_init(void) { struct device_node *np; + const char *reset_compat; - np = of_find_compatible_node(NULL, NULL, "fsl,mpc5121-reset"); + reset_compat = mpc512x_select_reset_compat(); + np = of_find_compatible_node(NULL, NULL, reset_compat); if (!np) return; @@ -58,8 +61,6 @@ void mpc512x_restart(char *cmd) ; } -#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE) - struct fsl_diu_shared_fb { u8 gamma[0x300]; /* 32-bit aligned! */ struct diu_ad ad0; /* 32-bit aligned! */ @@ -68,105 +69,115 @@ struct fsl_diu_shared_fb { bool in_use; }; -void mpc512x_set_monitor_port(enum fsl_diu_monitor_port port) -{ -} - -#define DIU_DIV_MASK 0x000000ff -void mpc512x_set_pixel_clock(unsigned int pixclock) +/* receives a pixel clock spec in pico seconds, adjusts the DIU clock rate */ +static void mpc512x_set_pixel_clock(unsigned int pixclock) { - unsigned long bestval, bestfreq, speed, busfreq; - unsigned long minpixclock, maxpixclock, pixval; - struct mpc512x_ccm __iomem *ccm; struct device_node *np; - u32 temp; - long err; - int i; + struct clk *clk_diu; + unsigned long epsilon, minpixclock, maxpixclock; + unsigned long offset, want, got, delta; - np = of_find_compatible_node(NULL, NULL, "fsl,mpc5121-clock"); + /* lookup and enable the DIU clock */ + np = of_find_compatible_node(NULL, NULL, "fsl,mpc5121-diu"); if (!np) { - pr_err("Can't find clock control module.\n"); + pr_err("Could not find DIU device tree node.\n"); return; } - - ccm = of_iomap(np, 0); + clk_diu = of_clk_get(np, 0); + if (IS_ERR(clk_diu)) { + /* backwards compat with device trees that lack clock specs */ + clk_diu = clk_get_sys(np->name, "ipg"); + } of_node_put(np); - if (!ccm) { - pr_err("Can't map clock control module reg.\n"); + if (IS_ERR(clk_diu)) { + pr_err("Could not lookup DIU clock.\n"); return; } - - np = of_find_node_by_type(NULL, "cpu"); - if (np) { - const unsigned int *prop = - of_get_property(np, "bus-frequency", NULL); - - of_node_put(np); - if (prop) { - busfreq = *prop; - } else { - pr_err("Can't get bus-frequency property\n"); - return; - } - } else { - pr_err("Can't find 'cpu' node.\n"); + if (clk_prepare_enable(clk_diu)) { + pr_err("Could not enable DIU clock.\n"); return; } - /* Pixel Clock configuration */ - pr_debug("DIU: Bus Frequency = %lu\n", busfreq); - speed = busfreq * 4; /* DIU_DIV ratio is 4 * CSB_CLK / DIU_CLK */ - - /* Calculate the pixel clock with the smallest error */ - /* calculate the following in steps to avoid overflow */ - pr_debug("DIU pixclock in ps - %d\n", pixclock); - temp = (1000000000 / pixclock) * 1000; - pixclock = temp; - pr_debug("DIU pixclock freq - %u\n", pixclock); - - temp = temp / 20; /* pixclock * 0.05 */ - pr_debug("deviation = %d\n", temp); - minpixclock = pixclock - temp; - maxpixclock = pixclock + temp; - pr_debug("DIU minpixclock - %lu\n", minpixclock); - pr_debug("DIU maxpixclock - %lu\n", maxpixclock); - pixval = speed/pixclock; - pr_debug("DIU pixval = %lu\n", pixval); - - err = LONG_MAX; - bestval = pixval; - pr_debug("DIU bestval = %lu\n", bestval); - - bestfreq = 0; - for (i = -1; i <= 1; i++) { - temp = speed / (pixval+i); - pr_debug("DIU test pixval i=%d, pixval=%lu, temp freq. = %u\n", - i, pixval, temp); - if ((temp < minpixclock) || (temp > maxpixclock)) - pr_debug("DIU exceeds monitor range (%lu to %lu)\n", - minpixclock, maxpixclock); - else if (abs(temp - pixclock) < err) { - pr_debug("Entered the else if block %d\n", i); - err = abs(temp - pixclock); - bestval = pixval + i; - bestfreq = temp; - } + /* + * convert the picoseconds spec into the desired clock rate, + * determine the acceptable clock range for the monitor (+/- 5%), + * do the calculation in steps to avoid integer overflow + */ + pr_debug("DIU pixclock in ps - %u\n", pixclock); + pixclock = (1000000000 / pixclock) * 1000; + pr_debug("DIU pixclock freq - %u\n", pixclock); + epsilon = pixclock / 20; /* pixclock * 0.05 */ + pr_debug("DIU deviation - %lu\n", epsilon); + minpixclock = pixclock - epsilon; + maxpixclock = pixclock + epsilon; + pr_debug("DIU minpixclock - %lu\n", minpixclock); + pr_debug("DIU maxpixclock - %lu\n", maxpixclock); + + /* + * check whether the DIU supports the desired pixel clock + * + * - simply request the desired clock and see what the + * platform's clock driver will make of it, assuming that it + * will setup the best approximation of the requested value + * - try other candidate frequencies in the order of decreasing + * preference (i.e. with increasing distance from the desired + * pixel clock, and checking the lower frequency before the + * higher frequency to not overload the hardware) until the + * first match is found -- any potential subsequent match + * would only be as good as the former match or typically + * would be less preferrable + * + * the offset increment of pixelclock divided by 64 is an + * arbitrary choice -- it's simple to calculate, in the typical + * case we expect the first check to succeed already, in the + * worst case seven frequencies get tested (the exact center and + * three more values each to the left and to the right) before + * the 5% tolerance window is exceeded, resulting in fast enough + * execution yet high enough probability of finding a suitable + * value, while the error rate will be in the order of single + * percents + */ + for (offset = 0; offset <= epsilon; offset += pixclock / 64) { + want = pixclock - offset; + pr_debug("DIU checking clock - %lu\n", want); + clk_set_rate(clk_diu, want); + got = clk_get_rate(clk_diu); + delta = abs(pixclock - got); + if (delta < epsilon) + break; + if (!offset) + continue; + want = pixclock + offset; + pr_debug("DIU checking clock - %lu\n", want); + clk_set_rate(clk_diu, want); + got = clk_get_rate(clk_diu); + delta = abs(pixclock - got); + if (delta < epsilon) + break; + } + if (offset <= epsilon) { + pr_debug("DIU clock accepted - %lu\n", want); + pr_debug("DIU pixclock want %u, got %lu, delta %lu, eps %lu\n", + pixclock, got, delta, epsilon); + return; } + pr_warn("DIU pixclock auto search unsuccessful\n"); - pr_debug("DIU chose = %lx\n", bestval); - pr_debug("DIU error = %ld\n NomPixClk ", err); - pr_debug("DIU: Best Freq = %lx\n", bestfreq); - /* Modify DIU_DIV in CCM SCFR1 */ - temp = in_be32(&ccm->scfr1); - pr_debug("DIU: Current value of SCFR1: 0x%08x\n", temp); - temp &= ~DIU_DIV_MASK; - temp |= (bestval & DIU_DIV_MASK); - out_be32(&ccm->scfr1, temp); - pr_debug("DIU: Modified value of SCFR1: 0x%08x\n", temp); - iounmap(ccm); + /* + * what is the most appropriate action to take when the search + * for an available pixel clock which is acceptable to the + * monitor has failed? disable the DIU (clock) or just provide + * a "best effort"? we go with the latter + */ + pr_warn("DIU pixclock best effort fallback (backend's choice)\n"); + clk_set_rate(clk_diu, pixclock); + got = clk_get_rate(clk_diu); + delta = abs(pixclock - got); + pr_debug("DIU pixclock want %u, got %lu, delta %lu, eps %lu\n", + pixclock, got, delta, epsilon); } -enum fsl_diu_monitor_port +static enum fsl_diu_monitor_port mpc512x_valid_monitor_port(enum fsl_diu_monitor_port port) { return FSL_DIU_PORT_DVI; @@ -176,15 +187,12 @@ static struct fsl_diu_shared_fb __attribute__ ((__aligned__(8))) diu_shared_fb; static inline void mpc512x_free_bootmem(struct page *page) { - __ClearPageReserved(page); BUG_ON(PageTail(page)); BUG_ON(atomic_read(&page->_count) > 1); - atomic_set(&page->_count, 1); - __free_page(page); - totalram_pages++; + free_reserved_page(page); } -void mpc512x_release_bootmem(void) +static void mpc512x_release_bootmem(void) { unsigned long addr = diu_shared_fb.fb_phys & PAGE_MASK; unsigned long size = diu_shared_fb.fb_len; @@ -210,7 +218,7 @@ void mpc512x_release_bootmem(void) * address range will be reserved in setup_arch() after bootmem * allocator is up. */ -void __init mpc512x_init_diu(void) +static void __init mpc512x_init_diu(void) { struct device_node *np; struct diu __iomem *diu_reg; @@ -279,7 +287,7 @@ out: iounmap(diu_reg); } -void __init mpc512x_setup_diu(void) +static void __init mpc512x_setup_diu(void) { int ret; @@ -303,14 +311,11 @@ void __init mpc512x_setup_diu(void) } } - diu_ops.set_monitor_port = mpc512x_set_monitor_port; diu_ops.set_pixel_clock = mpc512x_set_pixel_clock; diu_ops.valid_monitor_port = mpc512x_valid_monitor_port; diu_ops.release_bootmem = mpc512x_release_bootmem; } -#endif - void __init mpc512x_init_IRQ(void) { struct device_node *np; @@ -335,26 +340,45 @@ void __init mpc512x_init_IRQ(void) static struct of_device_id __initdata of_bus_ids[] = { { .compatible = "fsl,mpc5121-immr", }, { .compatible = "fsl,mpc5121-localbus", }, + { .compatible = "fsl,mpc5121-mbx", }, + { .compatible = "fsl,mpc5121-nfc", }, + { .compatible = "fsl,mpc5121-sram", }, + { .compatible = "fsl,mpc5121-pci", }, + { .compatible = "gpio-leds", }, {}, }; -void __init mpc512x_declare_of_platform_devices(void) +static void __init mpc512x_declare_of_platform_devices(void) { - struct device_node *np; - if (of_platform_bus_probe(NULL, of_bus_ids, NULL)) printk(KERN_ERR __FILE__ ": " "Error while probing of_platform bus\n"); - - np = of_find_compatible_node(NULL, NULL, "fsl,mpc5121-nfc"); - if (np) { - of_platform_device_create(np, NULL, NULL); - of_node_put(np); - } } #define DEFAULT_FIFO_SIZE 16 +const char *mpc512x_select_psc_compat(void) +{ + if (of_machine_is_compatible("fsl,mpc5121")) + return "fsl,mpc5121-psc"; + + if (of_machine_is_compatible("fsl,mpc5125")) + return "fsl,mpc5125-psc"; + + return NULL; +} + +const char *mpc512x_select_reset_compat(void) +{ + if (of_machine_is_compatible("fsl,mpc5121")) + return "fsl,mpc5121-reset"; + + if (of_machine_is_compatible("fsl,mpc5125")) + return "fsl,mpc5125-reset"; + + return NULL; +} + static unsigned int __init get_fifo_size(struct device_node *np, char *prop_name) { @@ -374,15 +398,22 @@ static unsigned int __init get_fifo_size(struct device_node *np, ((u32)(_base) + sizeof(struct mpc52xx_psc))) /* Init PSC FIFO space for TX and RX slices */ -void __init mpc512x_psc_fifo_init(void) +static void __init mpc512x_psc_fifo_init(void) { struct device_node *np; void __iomem *psc; unsigned int tx_fifo_size; unsigned int rx_fifo_size; + const char *psc_compat; int fifobase = 0; /* current fifo address in 32 bit words */ - for_each_compatible_node(np, NULL, "fsl,mpc5121-psc") { + psc_compat = mpc512x_select_psc_compat(); + if (!psc_compat) { + pr_err("%s: no compatible devices found\n", __func__); + return; + } + + for_each_compatible_node(np, NULL, psc_compat) { tx_fifo_size = get_fifo_size(np, "fsl,tx-fifo-size"); rx_fifo_size = get_fifo_size(np, "fsl,rx-fifo-size"); @@ -429,10 +460,52 @@ void __init mpc512x_psc_fifo_init(void) } } +void __init mpc512x_init_early(void) +{ + mpc512x_restart_init(); + if (IS_ENABLED(CONFIG_FB_FSL_DIU)) + mpc512x_init_diu(); +} + void __init mpc512x_init(void) { - mpc512x_declare_of_platform_devices(); mpc5121_clk_init(); - mpc512x_restart_init(); + mpc512x_declare_of_platform_devices(); mpc512x_psc_fifo_init(); } + +void __init mpc512x_setup_arch(void) +{ + if (IS_ENABLED(CONFIG_FB_FSL_DIU)) + mpc512x_setup_diu(); +} + +/** + * mpc512x_cs_config - Setup chip select configuration + * @cs: chip select number + * @val: chip select configuration value + * + * Perform chip select configuration for devices on LocalPlus Bus. + * Intended to dynamically reconfigure the chip select parameters + * for configurable devices on the bus. + */ +int mpc512x_cs_config(unsigned int cs, u32 val) +{ + static struct mpc512x_lpc __iomem *lpc; + struct device_node *np; + + if (cs > 7) + return -EINVAL; + + if (!lpc) { + np = of_find_compatible_node(NULL, NULL, "fsl,mpc5121-lpc"); + lpc = of_iomap(np, 0); + of_node_put(np); + if (!lpc) + return -ENOMEM; + } + + out_be32(&lpc->cs_cfg[cs], val); + return 0; +} +EXPORT_SYMBOL(mpc512x_cs_config); diff --git a/arch/powerpc/platforms/512x/pdm360ng.c b/arch/powerpc/platforms/512x/pdm360ng.c index 0575e858291..116f2325b20 100644 --- a/arch/powerpc/platforms/512x/pdm360ng.c +++ b/arch/powerpc/platforms/512x/pdm360ng.c @@ -14,6 +14,8 @@ #include <linux/kernel.h> #include <linux/io.h> +#include <linux/of_address.h> +#include <linux/of_fdt.h> #include <linux/of_platform.h> #include <asm/machdep.h> @@ -119,9 +121,9 @@ static int __init pdm360ng_probe(void) define_machine(pdm360ng) { .name = "PDM360NG", .probe = pdm360ng_probe, - .setup_arch = mpc512x_setup_diu, + .setup_arch = mpc512x_setup_arch, .init = pdm360ng_init, - .init_early = mpc512x_init_diu, + .init_early = mpc512x_init_early, .init_IRQ = mpc512x_init_IRQ, .get_irq = ipic_get_irq, .calibrate_decr = generic_calibrate_decr, diff --git a/arch/powerpc/platforms/52xx/Kconfig b/arch/powerpc/platforms/52xx/Kconfig index 90f4496017e..b625a2c6f4f 100644 --- a/arch/powerpc/platforms/52xx/Kconfig +++ b/arch/powerpc/platforms/52xx/Kconfig @@ -1,7 +1,7 @@ config PPC_MPC52xx bool "52xx-based boards" depends on 6xx - select PPC_CLOCK + select COMMON_CLK select PPC_PCI_CHOICE config PPC_MPC5200_SIMPLE @@ -57,5 +57,5 @@ config PPC_MPC5200_BUGFIX config PPC_MPC5200_LPBFIFO tristate "MPC5200 LocalPlus bus FIFO driver" - depends on PPC_MPC52xx + depends on PPC_MPC52xx && PPC_BESTCOMM select PPC_BESTCOMM_GEN_BD diff --git a/arch/powerpc/platforms/52xx/efika.c b/arch/powerpc/platforms/52xx/efika.c index 18c10482019..6e19b0ad5d2 100644 --- a/arch/powerpc/platforms/52xx/efika.c +++ b/arch/powerpc/platforms/52xx/efika.c @@ -199,8 +199,8 @@ static void __init efika_setup_arch(void) static int __init efika_probe(void) { - char *model = of_get_flat_dt_prop(of_get_flat_dt_root(), - "model", NULL); + const char *model = of_get_flat_dt_prop(of_get_flat_dt_root(), + "model", NULL); if (model == NULL) return 0; diff --git a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c index f9f4537f546..37f7a89c10f 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c @@ -20,9 +20,9 @@ #include <asm/mpc52xx.h> #include <asm/time.h> -#include <sysdev/bestcomm/bestcomm.h> -#include <sysdev/bestcomm/bestcomm_priv.h> -#include <sysdev/bestcomm/gen_bd.h> +#include <linux/fsl/bestcomm/bestcomm.h> +#include <linux/fsl/bestcomm/bestcomm_priv.h> +#include <linux/fsl/bestcomm/gen_bd.h> MODULE_AUTHOR("Grant Likely <grant.likely@secretlab.ca>"); MODULE_DESCRIPTION("MPC5200 LocalPlus FIFO device driver"); @@ -245,7 +245,7 @@ static irqreturn_t mpc52xx_lpbfifo_irq(int irq, void *dev_id) if (dma && !write) { spin_unlock_irqrestore(&lpbfifo.lock, flags); - pr_err("bogus LPBFIFO IRQ (dma and not writting)\n"); + pr_err("bogus LPBFIFO IRQ (dma and not writing)\n"); return IRQ_HANDLED; } diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pic.c b/arch/powerpc/platforms/52xx/mpc52xx_pic.c index b89ef65392d..2898b737deb 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_pic.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_pic.c @@ -340,7 +340,7 @@ static int mpc52xx_irqhost_map(struct irq_domain *h, unsigned int virq, { int l1irq; int l2irq; - struct irq_chip *irqchip; + struct irq_chip *uninitialized_var(irqchip); void *hndlr; int type; u32 reg; diff --git a/arch/powerpc/platforms/82xx/km82xx.c b/arch/powerpc/platforms/82xx/km82xx.c index cf964e19573..058cc1895c8 100644 --- a/arch/powerpc/platforms/82xx/km82xx.c +++ b/arch/powerpc/platforms/82xx/km82xx.c @@ -18,11 +18,11 @@ #include <linux/fsl_devices.h> #include <linux/of_platform.h> -#include <asm/io.h> +#include <linux/io.h> #include <asm/cpm2.h> #include <asm/udbg.h> #include <asm/machdep.h> -#include <asm/time.h> +#include <linux/time.h> #include <asm/mpc8260.h> #include <asm/prom.h> @@ -36,7 +36,7 @@ static void __init km82xx_pic_init(void) struct device_node *np = of_find_compatible_node(NULL, NULL, "fsl,pq2-pic"); if (!np) { - printk(KERN_ERR "PIC init: can not find cpm-pic node\n"); + pr_err("PIC init: can not find cpm-pic node\n"); return; } diff --git a/arch/powerpc/platforms/82xx/mpc8272_ads.c b/arch/powerpc/platforms/82xx/mpc8272_ads.c index 30394b409b3..6a14cf50f4a 100644 --- a/arch/powerpc/platforms/82xx/mpc8272_ads.c +++ b/arch/powerpc/platforms/82xx/mpc8272_ads.c @@ -16,6 +16,8 @@ #include <linux/init.h> #include <linux/interrupt.h> #include <linux/fsl_devices.h> +#include <linux/of_address.h> +#include <linux/of_fdt.h> #include <linux/of_platform.h> #include <linux/io.h> diff --git a/arch/powerpc/platforms/82xx/pq2.c b/arch/powerpc/platforms/82xx/pq2.c index fb94d10e5a4..fc8b2d6a7d8 100644 --- a/arch/powerpc/platforms/82xx/pq2.c +++ b/arch/powerpc/platforms/82xx/pq2.c @@ -71,11 +71,11 @@ err: void __init pq2_init_pci(void) { - struct device_node *np = NULL; + struct device_node *np; ppc_md.pci_exclude_device = pq2_pci_exclude_device; - while ((np = of_find_compatible_node(np, NULL, "fsl,pq2-pci"))) + for_each_compatible_node(np, NULL, "fsl,pq2-pci") pq2_pci_add_bridge(np); } #endif diff --git a/arch/powerpc/platforms/82xx/pq2fads.c b/arch/powerpc/platforms/82xx/pq2fads.c index e1dceeec499..e5f82ec8df1 100644 --- a/arch/powerpc/platforms/82xx/pq2fads.c +++ b/arch/powerpc/platforms/82xx/pq2fads.c @@ -15,6 +15,8 @@ #include <linux/init.h> #include <linux/interrupt.h> #include <linux/fsl_devices.h> +#include <linux/of_address.h> +#include <linux/of_fdt.h> #include <linux/of_platform.h> #include <asm/io.h> diff --git a/arch/powerpc/platforms/83xx/Kconfig b/arch/powerpc/platforms/83xx/Kconfig index 670a033264c..2bdc8c862c4 100644 --- a/arch/powerpc/platforms/83xx/Kconfig +++ b/arch/powerpc/platforms/83xx/Kconfig @@ -99,7 +99,6 @@ config SBC834x config ASP834x bool "Analogue & Micro ASP 834x" select PPC_MPC834x - select REDBOOT help This enables support for the Analogue & Micro ASP 83xx board. diff --git a/arch/powerpc/platforms/83xx/km83xx.c b/arch/powerpc/platforms/83xx/km83xx.c index 89923d72334..bf4c4473abb 100644 --- a/arch/powerpc/platforms/83xx/km83xx.c +++ b/arch/powerpc/platforms/83xx/km83xx.c @@ -28,8 +28,8 @@ #include <linux/of_device.h> #include <linux/atomic.h> -#include <asm/time.h> -#include <asm/io.h> +#include <linux/time.h> +#include <linux/io.h> #include <asm/machdep.h> #include <asm/ipic.h> #include <asm/irq.h> @@ -43,6 +43,82 @@ #include "mpc83xx.h" #define SVR_REV(svr) (((svr) >> 0) & 0xFFFF) /* Revision field */ + +static void quirk_mpc8360e_qe_enet10(void) +{ + /* + * handle mpc8360E Erratum QE_ENET10: + * RGMII AC values do not meet the specification + */ + uint svid = mfspr(SPRN_SVR); + struct device_node *np_par; + struct resource res; + void __iomem *base; + int ret; + + np_par = of_find_node_by_name(NULL, "par_io"); + if (np_par == NULL) { + pr_warn("%s couldn;t find par_io node\n", __func__); + return; + } + /* Map Parallel I/O ports registers */ + ret = of_address_to_resource(np_par, 0, &res); + if (ret) { + pr_warn("%s couldn;t map par_io registers\n", __func__); + return; + } + + base = ioremap(res.start, res.end - res.start + 1); + + /* + * set output delay adjustments to default values according + * table 5 in Errata Rev. 5, 9/2011: + * + * write 0b01 to UCC1 bits 18:19 + * write 0b01 to UCC2 option 1 bits 4:5 + * write 0b01 to UCC2 option 2 bits 16:17 + */ + clrsetbits_be32((base + 0xa8), 0x0c00f000, 0x04005000); + + /* + * set output delay adjustments to default values according + * table 3-13 in Reference Manual Rev.3 05/2010: + * + * write 0b01 to UCC2 option 2 bits 16:17 + * write 0b0101 to UCC1 bits 20:23 + * write 0b0101 to UCC2 option 1 bits 24:27 + */ + clrsetbits_be32((base + 0xac), 0x0000cff0, 0x00004550); + + if (SVR_REV(svid) == 0x0021) { + /* + * UCC2 option 1: write 0b1010 to bits 24:27 + * at address IMMRBAR+0x14AC + */ + clrsetbits_be32((base + 0xac), 0x000000f0, 0x000000a0); + } else if (SVR_REV(svid) == 0x0020) { + /* + * UCC1: write 0b11 to bits 18:19 + * at address IMMRBAR+0x14A8 + */ + setbits32((base + 0xa8), 0x00003000); + + /* + * UCC2 option 1: write 0b11 to bits 4:5 + * at address IMMRBAR+0x14A8 + */ + setbits32((base + 0xa8), 0x0c000000); + + /* + * UCC2 option 2: write 0b11 to bits 16:17 + * at address IMMRBAR+0x14AC + */ + setbits32((base + 0xac), 0x0000c000); + } + iounmap(base); + of_node_put(np_par); +} + /* ************************************************************************ * * Setup the architecture @@ -72,84 +148,13 @@ static void __init mpc83xx_km_setup_arch(void) for_each_node_by_name(np, "ucc") par_io_of_config(np); - } - - np = of_find_compatible_node(NULL, "network", "ucc_geth"); - if (np != NULL) { - /* - * handle mpc8360E Erratum QE_ENET10: - * RGMII AC values do not meet the specification - */ - uint svid = mfspr(SPRN_SVR); - struct device_node *np_par; - struct resource res; - void __iomem *base; - int ret; - - np_par = of_find_node_by_name(NULL, "par_io"); - if (np_par == NULL) { - printk(KERN_WARNING "%s couldn;t find par_io node\n", - __func__); - return; - } - /* Map Parallel I/O ports registers */ - ret = of_address_to_resource(np_par, 0, &res); - if (ret) { - printk(KERN_WARNING "%s couldn;t map par_io registers\n", - __func__); - return; - } - - base = ioremap(res.start, res.end - res.start + 1); - - /* - * set output delay adjustments to default values according - * table 5 in Errata Rev. 5, 9/2011: - * - * write 0b01 to UCC1 bits 18:19 - * write 0b01 to UCC2 option 1 bits 4:5 - * write 0b01 to UCC2 option 2 bits 16:17 - */ - clrsetbits_be32((base + 0xa8), 0x0c00f000, 0x04005000); - /* - * set output delay adjustments to default values according - * table 3-13 in Reference Manual Rev.3 05/2010: - * - * write 0b01 to UCC2 option 2 bits 16:17 - * write 0b0101 to UCC1 bits 20:23 - * write 0b0101 to UCC2 option 1 bits 24:27 - */ - clrsetbits_be32((base + 0xac), 0x0000cff0, 0x00004550); - - if (SVR_REV(svid) == 0x0021) { - /* - * UCC2 option 1: write 0b1010 to bits 24:27 - * at address IMMRBAR+0x14AC - */ - clrsetbits_be32((base + 0xac), 0x000000f0, 0x000000a0); - } else if (SVR_REV(svid) == 0x0020) { - /* - * UCC1: write 0b11 to bits 18:19 - * at address IMMRBAR+0x14A8 - */ - setbits32((base + 0xa8), 0x00003000); - - /* - * UCC2 option 1: write 0b11 to bits 4:5 - * at address IMMRBAR+0x14A8 - */ - setbits32((base + 0xa8), 0x0c000000); - - /* - * UCC2 option 2: write 0b11 to bits 16:17 - * at address IMMRBAR+0x14AC - */ - setbits32((base + 0xac), 0x0000c000); + /* Only apply this quirk when par_io is available */ + np = of_find_compatible_node(NULL, "network", "ucc_geth"); + if (np != NULL) { + quirk_mpc8360e_qe_enet10(); + of_node_put(np); } - iounmap(base); - of_node_put(np_par); - of_node_put(np); } #endif /* CONFIG_QUICC_ENGINE */ } diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c index 624cb51d19c..e238b6a55b1 100644 --- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c +++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c @@ -11,7 +11,6 @@ * (at your option) any later version. */ -#include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/device.h> @@ -204,7 +203,6 @@ static int mcu_remove(struct i2c_client *client) ret = mcu_gpiochip_remove(mcu); if (ret) return ret; - i2c_set_clientdata(client, NULL); kfree(mcu); return 0; } @@ -231,17 +229,7 @@ static struct i2c_driver mcu_driver = { .id_table = mcu_ids, }; -static int __init mcu_init(void) -{ - return i2c_add_driver(&mcu_driver); -} -module_init(mcu_init); - -static void __exit mcu_exit(void) -{ - i2c_del_driver(&mcu_driver); -} -module_exit(mcu_exit); +module_i2c_driver(mcu_driver); MODULE_DESCRIPTION("Power Management and GPIO expander driver for " "MPC8349E-mITX-compatible MCU"); diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c index 1d769a29249..4b4c081df94 100644 --- a/arch/powerpc/platforms/83xx/suspend.c +++ b/arch/powerpc/platforms/83xx/suspend.c @@ -10,7 +10,6 @@ * by the Free Software Foundation. */ -#include <linux/init.h> #include <linux/pm.h> #include <linux/types.h> #include <linux/ioport.h> @@ -20,6 +19,8 @@ #include <linux/freezer.h> #include <linux/suspend.h> #include <linux/fsl_devices.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> #include <linux/of_platform.h> #include <linux/export.h> diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig index 02d02a09942..f442120e003 100644 --- a/arch/powerpc/platforms/85xx/Kconfig +++ b/arch/powerpc/platforms/85xx/Kconfig @@ -32,6 +32,21 @@ config BSC9131_RDB StarCore SC3850 DSP Manufacturer : Freescale Semiconductor, Inc +config C293_PCIE + bool "Freescale C293PCIE" + select DEFAULT_UIMAGE + help + This option enables support for the C293PCIE board + +config BSC9132_QDS + bool "Freescale BSC9132QDS" + select DEFAULT_UIMAGE + help + This option enables support for the Freescale BSC9132 QDS board. + BSC9132 is a heterogeneous SoC containing dual e500v2 powerpc cores + and dual StarCore SC3850 DSP cores. + Manufacturer : Freescale Semiconductor, Inc + config MPC8540_ADS bool "Freescale MPC8540 ADS" select DEFAULT_UIMAGE @@ -111,11 +126,17 @@ config P1022_RDK This option enables support for the Freescale / iVeia P1022RDK reference board. -config P1023_RDS - bool "Freescale P1023 RDS" +config P1023_RDB + bool "Freescale P1023 RDB" select DEFAULT_UIMAGE help - This option enables support for the P1023 RDS board + This option enables support for the P1023 RDB board. + +config TWR_P102x + bool "Freescale TWR-P102x" + select DEFAULT_UIMAGE + help + This option enables support for the TWR-P1025 board. config SOCRATES bool "Socrates" @@ -191,12 +212,18 @@ config SBC8548 help This option enables support for the Wind River SBC8548 board +config PPA8548 + bool "Prodrive PPA8548" + help + This option enables support for the Prodrive PPA8548 board. + select DEFAULT_UIMAGE + select HAS_RAPIDIO + config GE_IMP3A bool "GE Intelligent Platforms IMP3A" select DEFAULT_UIMAGE select SWIOTLB select MMIO_NVRAM - select GENERIC_GPIO select ARCH_REQUIRE_GPIOLIB select GE_FPGA help @@ -206,78 +233,18 @@ config GE_IMP3A This board is a 3U CompactPCI Single Board Computer with a Freescale P2020 processor. -config P2041_RDB - bool "Freescale P2041 RDB" - select DEFAULT_UIMAGE - select PPC_E500MC - select PHYS_64BIT - select SWIOTLB - select ARCH_REQUIRE_GPIOLIB - select GPIO_MPC8XXX - select HAS_RAPIDIO - select PPC_EPAPR_HV_PIC - help - This option enables support for the P2041 RDB board - -config P3041_DS - bool "Freescale P3041 DS" - select DEFAULT_UIMAGE - select PPC_E500MC - select PHYS_64BIT - select SWIOTLB - select ARCH_REQUIRE_GPIOLIB - select GPIO_MPC8XXX - select HAS_RAPIDIO - select PPC_EPAPR_HV_PIC - help - This option enables support for the P3041 DS board - -config P4080_DS - bool "Freescale P4080 DS" - select DEFAULT_UIMAGE - select PPC_E500MC - select PHYS_64BIT - select SWIOTLB - select ARCH_REQUIRE_GPIOLIB - select GPIO_MPC8XXX - select HAS_RAPIDIO - select PPC_EPAPR_HV_PIC +config SGY_CTS1000 + tristate "Servergy CTS-1000 support" + select GPIOLIB + select OF_GPIO + depends on CORENET_GENERIC help - This option enables support for the P4080 DS board + Enable this to support functionality in Servergy's CTS-1000 systems. endif # PPC32 -config P5020_DS - bool "Freescale P5020 DS" - select DEFAULT_UIMAGE - select E500 - select PPC_E500MC - select PHYS_64BIT - select SWIOTLB - select ARCH_REQUIRE_GPIOLIB - select GPIO_MPC8XXX - select HAS_RAPIDIO - select PPC_EPAPR_HV_PIC - help - This option enables support for the P5020 DS board - -config P5040_DS - bool "Freescale P5040 DS" - select DEFAULT_UIMAGE - select E500 - select PPC_E500MC - select PHYS_64BIT - select SWIOTLB - select ARCH_REQUIRE_GPIOLIB - select GPIO_MPC8XXX - select HAS_RAPIDIO - select PPC_EPAPR_HV_PIC - help - This option enables support for the P5040 DS board - config PPC_QEMU_E500 bool "QEMU generic e500 platform" - depends on EXPERIMENTAL select DEFAULT_UIMAGE help This option enables support for running as a QEMU guest using @@ -291,6 +258,26 @@ config PPC_QEMU_E500 unset based on the emulated CPU (or actual host CPU in the case of KVM). +config CORENET_GENERIC + bool "Freescale CoreNet Generic" + select DEFAULT_UIMAGE + select E500 + select PPC_E500MC + select PHYS_64BIT + select SWIOTLB + select ARCH_REQUIRE_GPIOLIB + select GPIO_MPC8XXX + select HAS_RAPIDIO + select PPC_EPAPR_HV_PIC + help + This option enables support for the FSL CoreNet based boards. + For 32bit kernel, the following boards are supported: + P2041 RDB, P3041 DS, P4080 DS, kmcoge4, and OCA4080 + For 64bit kernel, the following boards are supported: + T4240 QDS and B4 QDS + The following boards are supported for both 32bit and 64bit kernel: + P5020 DS, P5040 DS and T104xQDS + endif # FSL_SOC_BOOKE config TQM85xx diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile index 76f679cb04a..73032604662 100644 --- a/arch/powerpc/platforms/85xx/Makefile +++ b/arch/powerpc/platforms/85xx/Makefile @@ -6,6 +6,8 @@ obj-$(CONFIG_SMP) += smp.o obj-y += common.o obj-$(CONFIG_BSC9131_RDB) += bsc913x_rdb.o +obj-$(CONFIG_BSC9132_QDS) += bsc913x_qds.o +obj-$(CONFIG_C293_PCIE) += c293pcie.o obj-$(CONFIG_MPC8540_ADS) += mpc85xx_ads.o obj-$(CONFIG_MPC8560_ADS) += mpc85xx_ads.o obj-$(CONFIG_MPC85xx_CDS) += mpc85xx_cds.o @@ -16,17 +18,16 @@ obj-$(CONFIG_MPC85xx_RDB) += mpc85xx_rdb.o obj-$(CONFIG_P1010_RDB) += p1010rdb.o obj-$(CONFIG_P1022_DS) += p1022_ds.o obj-$(CONFIG_P1022_RDK) += p1022_rdk.o -obj-$(CONFIG_P1023_RDS) += p1023_rds.o -obj-$(CONFIG_P2041_RDB) += p2041_rdb.o corenet_ds.o -obj-$(CONFIG_P3041_DS) += p3041_ds.o corenet_ds.o -obj-$(CONFIG_P4080_DS) += p4080_ds.o corenet_ds.o -obj-$(CONFIG_P5020_DS) += p5020_ds.o corenet_ds.o -obj-$(CONFIG_P5040_DS) += p5040_ds.o corenet_ds.o +obj-$(CONFIG_P1023_RDB) += p1023_rdb.o +obj-$(CONFIG_TWR_P102x) += twr_p102x.o +obj-$(CONFIG_CORENET_GENERIC) += corenet_generic.o obj-$(CONFIG_STX_GP3) += stx_gp3.o obj-$(CONFIG_TQM85xx) += tqm85xx.o obj-$(CONFIG_SBC8548) += sbc8548.o +obj-$(CONFIG_PPA8548) += ppa8548.o obj-$(CONFIG_SOCRATES) += socrates.o socrates_fpga_pic.o obj-$(CONFIG_KSI8560) += ksi8560.o obj-$(CONFIG_XES_MPC85xx) += xes_mpc85xx.o obj-$(CONFIG_GE_IMP3A) += ge_imp3a.o obj-$(CONFIG_PPC_QEMU_E500) += qemu_e500.o +obj-$(CONFIG_SGY_CTS1000) += sgy_cts1000.o diff --git a/arch/powerpc/platforms/85xx/bsc913x_qds.c b/arch/powerpc/platforms/85xx/bsc913x_qds.c new file mode 100644 index 00000000000..f0927e58af2 --- /dev/null +++ b/arch/powerpc/platforms/85xx/bsc913x_qds.c @@ -0,0 +1,74 @@ +/* + * BSC913xQDS Board Setup + * + * Author: + * Harninder Rai <harninder.rai@freescale.com> + * Priyanka Jain <Priyanka.Jain@freescale.com> + * + * Copyright 2014 Freescale Semiconductor Inc. + * + * 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/of_platform.h> +#include <linux/pci.h> +#include <asm/mpic.h> +#include <sysdev/fsl_soc.h> +#include <asm/udbg.h> + +#include "mpc85xx.h" +#include "smp.h" + +void __init bsc913x_qds_pic_init(void) +{ + struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN | + MPIC_SINGLE_DEST_CPU, + 0, 256, " OpenPIC "); + + if (!mpic) + pr_err("bsc913x: Failed to allocate MPIC structure\n"); + else + mpic_init(mpic); +} + +/* + * Setup the architecture + */ +static void __init bsc913x_qds_setup_arch(void) +{ + if (ppc_md.progress) + ppc_md.progress("bsc913x_qds_setup_arch()", 0); + +#if defined(CONFIG_SMP) + mpc85xx_smp_init(); +#endif + + pr_info("bsc913x board from Freescale Semiconductor\n"); +} + +machine_device_initcall(bsc9132_qds, mpc85xx_common_publish_devices); + +/* + * Called very early, device-tree isn't unflattened + */ + +static int __init bsc9132_qds_probe(void) +{ + unsigned long root = of_get_flat_dt_root(); + + return of_flat_dt_is_compatible(root, "fsl,bsc9132qds"); +} + +define_machine(bsc9132_qds) { + .name = "BSC9132 QDS", + .probe = bsc9132_qds_probe, + .setup_arch = bsc913x_qds_setup_arch, + .init_IRQ = bsc913x_qds_pic_init, + .get_irq = mpic_get_irq, + .restart = fsl_rstcr_restart, + .calibrate_decr = generic_calibrate_decr, + .progress = udbg_progress, +}; diff --git a/arch/powerpc/platforms/85xx/c293pcie.c b/arch/powerpc/platforms/85xx/c293pcie.c new file mode 100644 index 00000000000..84476b64600 --- /dev/null +++ b/arch/powerpc/platforms/85xx/c293pcie.c @@ -0,0 +1,77 @@ +/* + * C293PCIE Board Setup + * + * Copyright 2013 Freescale Semiconductor Inc. + * + * 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/stddef.h> +#include <linux/kernel.h> +#include <linux/of_fdt.h> +#include <linux/of_platform.h> + +#include <asm/machdep.h> +#include <asm/udbg.h> +#include <asm/mpic.h> + +#include <sysdev/fsl_soc.h> +#include <sysdev/fsl_pci.h> + +#include "mpc85xx.h" + +void __init c293_pcie_pic_init(void) +{ + struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN | + MPIC_SINGLE_DEST_CPU, 0, 256, " OpenPIC "); + + BUG_ON(mpic == NULL); + + mpic_init(mpic); +} + + +/* + * Setup the architecture + */ +static void __init c293_pcie_setup_arch(void) +{ + if (ppc_md.progress) + ppc_md.progress("c293_pcie_setup_arch()", 0); + + fsl_pci_assign_primary(); + + printk(KERN_INFO "C293 PCIE board from Freescale Semiconductor\n"); +} + +machine_arch_initcall(c293_pcie, mpc85xx_common_publish_devices); + +/* + * Called very early, device-tree isn't unflattened + */ +static int __init c293_pcie_probe(void) +{ + unsigned long root = of_get_flat_dt_root(); + + if (of_flat_dt_is_compatible(root, "fsl,C293PCIE")) + return 1; + return 0; +} + +define_machine(c293_pcie) { + .name = "C293 PCIE", + .probe = c293_pcie_probe, + .setup_arch = c293_pcie_setup_arch, + .init_IRQ = c293_pcie_pic_init, +#ifdef CONFIG_PCI + .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, +#endif + .get_irq = mpic_get_irq, + .restart = fsl_rstcr_restart, + .calibrate_decr = generic_calibrate_decr, + .progress = udbg_progress, +}; diff --git a/arch/powerpc/platforms/85xx/common.c b/arch/powerpc/platforms/85xx/common.c index d0861a0d836..b564b5e23f7 100644 --- a/arch/powerpc/platforms/85xx/common.c +++ b/arch/powerpc/platforms/85xx/common.c @@ -5,8 +5,11 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ + +#include <linux/of_irq.h> #include <linux/of_platform.h> +#include <asm/qe.h> #include <sysdev/cpm2_pic.h> #include "mpc85xx.h" @@ -80,3 +83,46 @@ void __init mpc85xx_cpm2_pic_init(void) irq_set_chained_handler(irq, cpm2_cascade); } #endif + +#ifdef CONFIG_QUICC_ENGINE +void __init mpc85xx_qe_init(void) +{ + struct device_node *np; + + np = of_find_compatible_node(NULL, NULL, "fsl,qe"); + if (!np) { + np = of_find_node_by_name(NULL, "qe"); + if (!np) { + pr_err("%s: Could not find Quicc Engine node\n", + __func__); + return; + } + } + + if (!of_device_is_available(np)) { + of_node_put(np); + return; + } + + qe_reset(); + of_node_put(np); + +} + +void __init mpc85xx_qe_par_io_init(void) +{ + struct device_node *np; + + np = of_find_node_by_name(NULL, "par_io"); + if (np) { + struct device_node *ucc; + + par_io_init(np); + of_node_put(np); + + for_each_node_by_name(ucc, "ucc") + par_io_of_config(ucc); + + } +} +#endif diff --git a/arch/powerpc/platforms/85xx/corenet_ds.c b/arch/powerpc/platforms/85xx/corenet_ds.c deleted file mode 100644 index 6f355d8c92f..00000000000 --- a/arch/powerpc/platforms/85xx/corenet_ds.c +++ /dev/null @@ -1,99 +0,0 @@ -/* - * Corenet based SoC DS Setup - * - * Maintained by Kumar Gala (see MAINTAINERS for contact information) - * - * Copyright 2009-2011 Freescale Semiconductor Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - */ - -#include <linux/kernel.h> -#include <linux/pci.h> -#include <linux/kdev_t.h> -#include <linux/delay.h> -#include <linux/interrupt.h> - -#include <asm/time.h> -#include <asm/machdep.h> -#include <asm/pci-bridge.h> -#include <asm/ppc-pci.h> -#include <mm/mmu_decl.h> -#include <asm/prom.h> -#include <asm/udbg.h> -#include <asm/mpic.h> - -#include <linux/of_platform.h> -#include <sysdev/fsl_soc.h> -#include <sysdev/fsl_pci.h> -#include "smp.h" - -void __init corenet_ds_pic_init(void) -{ - struct mpic *mpic; - unsigned int flags = MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU | - MPIC_NO_RESET; - - if (ppc_md.get_irq == mpic_get_coreint_irq) - flags |= MPIC_ENABLE_COREINT; - - mpic = mpic_alloc(NULL, 0, flags, 0, 256, " OpenPIC "); - BUG_ON(mpic == NULL); - - mpic_init(mpic); -} - -/* - * Setup the architecture - */ -void __init corenet_ds_setup_arch(void) -{ - mpc85xx_smp_init(); - -#if defined(CONFIG_PCI) && defined(CONFIG_PPC64) - pci_devs_phb_init(); -#endif - - fsl_pci_assign_primary(); - - swiotlb_detect_4g(); - - pr_info("%s board from Freescale Semiconductor\n", ppc_md.name); -} - -static const struct of_device_id of_device_ids[] = { - { - .compatible = "simple-bus" - }, - { - .compatible = "fsl,srio", - }, - { - .compatible = "fsl,p4080-pcie", - }, - { - .compatible = "fsl,qoriq-pcie-v2.2", - }, - { - .compatible = "fsl,qoriq-pcie-v2.3", - }, - { - .compatible = "fsl,qoriq-pcie-v2.4", - }, - /* The following two are for the Freescale hypervisor */ - { - .name = "hypervisor", - }, - { - .name = "handles", - }, - {} -}; - -int __init corenet_ds_publish_devices(void) -{ - return of_platform_bus_probe(NULL, of_device_ids, NULL); -} diff --git a/arch/powerpc/platforms/85xx/corenet_ds.h b/arch/powerpc/platforms/85xx/corenet_ds.h deleted file mode 100644 index ddd700b2303..00000000000 --- a/arch/powerpc/platforms/85xx/corenet_ds.h +++ /dev/null @@ -1,19 +0,0 @@ -/* - * Corenet based SoC DS Setup - * - * Copyright 2009 Freescale Semiconductor Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - */ - -#ifndef CORENET_DS_H -#define CORENET_DS_H - -extern void __init corenet_ds_pic_init(void); -extern void __init corenet_ds_setup_arch(void); -extern int __init corenet_ds_publish_devices(void); - -#endif diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c new file mode 100644 index 00000000000..5db1e117fdd --- /dev/null +++ b/arch/powerpc/platforms/85xx/corenet_generic.c @@ -0,0 +1,206 @@ +/* + * Corenet based SoC DS Setup + * + * Maintained by Kumar Gala (see MAINTAINERS for contact information) + * + * Copyright 2009-2011 Freescale Semiconductor Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/pci.h> +#include <linux/kdev_t.h> +#include <linux/delay.h> +#include <linux/interrupt.h> + +#include <asm/time.h> +#include <asm/machdep.h> +#include <asm/pci-bridge.h> +#include <asm/ppc-pci.h> +#include <mm/mmu_decl.h> +#include <asm/prom.h> +#include <asm/udbg.h> +#include <asm/mpic.h> +#include <asm/ehv_pic.h> +#include <asm/qe_ic.h> + +#include <linux/of_platform.h> +#include <sysdev/fsl_soc.h> +#include <sysdev/fsl_pci.h> +#include "smp.h" +#include "mpc85xx.h" + +void __init corenet_gen_pic_init(void) +{ + struct mpic *mpic; + unsigned int flags = MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU | + MPIC_NO_RESET; + + struct device_node *np; + + if (ppc_md.get_irq == mpic_get_coreint_irq) + flags |= MPIC_ENABLE_COREINT; + + mpic = mpic_alloc(NULL, 0, flags, 0, 512, " OpenPIC "); + BUG_ON(mpic == NULL); + + mpic_init(mpic); + + np = of_find_compatible_node(NULL, NULL, "fsl,qe-ic"); + if (np) { + qe_ic_init(np, 0, qe_ic_cascade_low_mpic, + qe_ic_cascade_high_mpic); + of_node_put(np); + } +} + +/* + * Setup the architecture + */ +void __init corenet_gen_setup_arch(void) +{ + mpc85xx_smp_init(); + + swiotlb_detect_4g(); + + pr_info("%s board\n", ppc_md.name); + + mpc85xx_qe_init(); +} + +static const struct of_device_id of_device_ids[] = { + { + .compatible = "simple-bus" + }, + { + .compatible = "fsl,srio", + }, + { + .compatible = "fsl,p4080-pcie", + }, + { + .compatible = "fsl,qoriq-pcie-v2.2", + }, + { + .compatible = "fsl,qoriq-pcie-v2.3", + }, + { + .compatible = "fsl,qoriq-pcie-v2.4", + }, + { + .compatible = "fsl,qoriq-pcie-v3.0", + }, + { + .compatible = "fsl,qe", + }, + /* The following two are for the Freescale hypervisor */ + { + .name = "hypervisor", + }, + { + .name = "handles", + }, + {} +}; + +int __init corenet_gen_publish_devices(void) +{ + return of_platform_bus_probe(NULL, of_device_ids, NULL); +} + +static const char * const boards[] __initconst = { + "fsl,P2041RDB", + "fsl,P3041DS", + "fsl,OCA4080", + "fsl,P4080DS", + "fsl,P5020DS", + "fsl,P5040DS", + "fsl,T4240QDS", + "fsl,B4860QDS", + "fsl,B4420QDS", + "fsl,B4220QDS", + "fsl,T1040QDS", + "fsl,T1042QDS", + "keymile,kmcoge4", + NULL +}; + +static const char * const hv_boards[] __initconst = { + "fsl,P2041RDB-hv", + "fsl,P3041DS-hv", + "fsl,OCA4080-hv", + "fsl,P4080DS-hv", + "fsl,P5020DS-hv", + "fsl,P5040DS-hv", + "fsl,T4240QDS-hv", + "fsl,B4860QDS-hv", + "fsl,B4420QDS-hv", + "fsl,B4220QDS-hv", + "fsl,T1040QDS-hv", + "fsl,T1042QDS-hv", + NULL +}; + +/* + * Called very early, device-tree isn't unflattened + */ +static int __init corenet_generic_probe(void) +{ + unsigned long root = of_get_flat_dt_root(); +#ifdef CONFIG_SMP + extern struct smp_ops_t smp_85xx_ops; +#endif + + if (of_flat_dt_match(root, boards)) + return 1; + + /* Check if we're running under the Freescale hypervisor */ + if (of_flat_dt_match(root, hv_boards)) { + ppc_md.init_IRQ = ehv_pic_init; + ppc_md.get_irq = ehv_pic_get_irq; + ppc_md.restart = fsl_hv_restart; + ppc_md.power_off = fsl_hv_halt; + ppc_md.halt = fsl_hv_halt; +#ifdef CONFIG_SMP + /* + * Disable the timebase sync operations because we can't write + * to the timebase registers under the hypervisor. + */ + smp_85xx_ops.give_timebase = NULL; + smp_85xx_ops.take_timebase = NULL; +#endif + return 1; + } + + return 0; +} + +define_machine(corenet_generic) { + .name = "CoreNet Generic", + .probe = corenet_generic_probe, + .setup_arch = corenet_gen_setup_arch, + .init_IRQ = corenet_gen_pic_init, +#ifdef CONFIG_PCI + .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, +#endif + .get_irq = mpic_get_coreint_irq, + .restart = fsl_rstcr_restart, + .calibrate_decr = generic_calibrate_decr, + .progress = udbg_progress, +#ifdef CONFIG_PPC64 + .power_save = book3e_idle, +#else + .power_save = e500_idle, +#endif +}; + +machine_arch_initcall(corenet_generic, corenet_gen_publish_devices); + +#ifdef CONFIG_SWIOTLB +machine_arch_initcall(corenet_generic, swiotlb_setup_bus_notifier); +#endif diff --git a/arch/powerpc/platforms/85xx/ge_imp3a.c b/arch/powerpc/platforms/85xx/ge_imp3a.c index e6285ae6f42..11790e074c8 100644 --- a/arch/powerpc/platforms/85xx/ge_imp3a.c +++ b/arch/powerpc/platforms/85xx/ge_imp3a.c @@ -215,6 +215,7 @@ define_machine(ge_imp3a) { .show_cpuinfo = ge_imp3a_show_cpuinfo, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, .restart = fsl_rstcr_restart, diff --git a/arch/powerpc/platforms/85xx/mpc8536_ds.c b/arch/powerpc/platforms/85xx/mpc8536_ds.c index 15ce4b55f11..a378ba3519e 100644 --- a/arch/powerpc/platforms/85xx/mpc8536_ds.c +++ b/arch/powerpc/platforms/85xx/mpc8536_ds.c @@ -76,6 +76,7 @@ define_machine(mpc8536_ds) { .init_IRQ = mpc8536_ds_pic_init, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, .restart = fsl_rstcr_restart, diff --git a/arch/powerpc/platforms/85xx/mpc85xx.h b/arch/powerpc/platforms/85xx/mpc85xx.h index 2aa7c5dc2c7..39056f6befe 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx.h +++ b/arch/powerpc/platforms/85xx/mpc85xx.h @@ -8,4 +8,12 @@ extern void mpc85xx_cpm2_pic_init(void); static inline void __init mpc85xx_cpm2_pic_init(void) {} #endif /* CONFIG_CPM2 */ +#ifdef CONFIG_QUICC_ENGINE +extern void mpc85xx_qe_init(void); +extern void mpc85xx_qe_par_io_init(void); +#else +static inline void __init mpc85xx_qe_init(void) {} +static inline void __init mpc85xx_qe_par_io_init(void) {} +#endif + #endif diff --git a/arch/powerpc/platforms/85xx/mpc85xx_cds.c b/arch/powerpc/platforms/85xx/mpc85xx_cds.c index 7a31a0e1df2..b0753e22208 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_cds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_cds.c @@ -385,6 +385,7 @@ define_machine(mpc85xx_cds) { #ifdef CONFIG_PCI .restart = mpc85xx_cds_restart, .pcibios_fixup_bus = mpc85xx_cds_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #else .restart = fsl_rstcr_restart, #endif diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c index 9ebb91ed96a..ffdf02121a7 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c @@ -209,6 +209,7 @@ define_machine(mpc8544_ds) { .init_IRQ = mpc85xx_ds_pic_init, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, .restart = fsl_rstcr_restart, @@ -223,6 +224,7 @@ define_machine(mpc8572_ds) { .init_IRQ = mpc85xx_ds_pic_init, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, .restart = fsl_rstcr_restart, @@ -237,6 +239,7 @@ define_machine(p2020_ds) { .init_IRQ = mpc85xx_ds_pic_init, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, .restart = fsl_rstcr_restart, diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c index bd12588fa25..a392e94a07f 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2006-2010, 2012 Freescale Semiconductor, Inc. + * Copyright (C) 2006-2010, 2012-2013 Freescale Semiconductor, Inc. * All rights reserved. * * Author: Andy Fleming <afleming@freescale.com> @@ -206,9 +206,7 @@ static void __init mpc85xx_mds_reset_ucc_phys(void) setbits8(&bcsr_regs[7], BCSR7_UCC12_GETHnRST); clrbits8(&bcsr_regs[8], BCSR8_UEM_MARVELL_RST); - for (np = NULL; (np = of_find_compatible_node(np, - "network", - "ucc_geth")) != NULL;) { + for_each_compatible_node(np, "network", "ucc_geth") { const unsigned int *prop; int ucc_num; @@ -240,32 +238,8 @@ static void __init mpc85xx_mds_qe_init(void) { struct device_node *np; - np = of_find_compatible_node(NULL, NULL, "fsl,qe"); - if (!np) { - np = of_find_node_by_name(NULL, "qe"); - if (!np) - return; - } - - if (!of_device_is_available(np)) { - of_node_put(np); - return; - } - - qe_reset(); - of_node_put(np); - - np = of_find_node_by_name(NULL, "par_io"); - if (np) { - struct device_node *ucc; - - par_io_init(np); - of_node_put(np); - - for_each_node_by_name(ucc, "ucc") - par_io_of_config(ucc); - } - + mpc85xx_qe_init(); + mpc85xx_qe_par_io_init(); mpc85xx_mds_reset_ucc_phys(); if (machine_is(p1021_mds)) { @@ -418,6 +392,7 @@ define_machine(mpc8568_mds) { .progress = udbg_progress, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif }; @@ -439,6 +414,7 @@ define_machine(mpc8569_mds) { .progress = udbg_progress, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif }; @@ -461,6 +437,7 @@ define_machine(p1021_mds) { .progress = udbg_progress, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif }; diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c index ede8771d6f0..e358bed66d0 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c @@ -1,7 +1,7 @@ /* * MPC85xx RDB Board Setup * - * Copyright 2009,2012 Freescale Semiconductor Inc. + * Copyright 2009,2012-2013 Freescale Semiconductor Inc. * * 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 @@ -86,10 +86,6 @@ void __init mpc85xx_rdb_pic_init(void) */ static void __init mpc85xx_rdb_setup_arch(void) { -#ifdef CONFIG_QUICC_ENGINE - struct device_node *np; -#endif - if (ppc_md.progress) ppc_md.progress("mpc85xx_rdb_setup_arch()", 0); @@ -98,28 +94,11 @@ static void __init mpc85xx_rdb_setup_arch(void) fsl_pci_assign_primary(); #ifdef CONFIG_QUICC_ENGINE - np = of_find_compatible_node(NULL, NULL, "fsl,qe"); - if (!np) { - pr_err("%s: Could not find Quicc Engine node\n", __func__); - goto qe_fail; - } - - qe_reset(); - of_node_put(np); - - np = of_find_node_by_name(NULL, "par_io"); - if (np) { - struct device_node *ucc; - - par_io_init(np); - of_node_put(np); - - for_each_node_by_name(ucc, "ucc") - par_io_of_config(ucc); - - } + mpc85xx_qe_init(); + mpc85xx_qe_par_io_init(); #if defined(CONFIG_UCC_GETH) || defined(CONFIG_SERIAL_QE) if (machine_is(p1025_rdb)) { + struct device_node *np; struct ccsr_guts __iomem *guts; @@ -148,8 +127,6 @@ static void __init mpc85xx_rdb_setup_arch(void) } #endif - -qe_fail: #endif /* CONFIG_QUICC_ENGINE */ printk(KERN_INFO "MPC85xx RDB board from Freescale Semiconductor\n"); @@ -160,6 +137,7 @@ machine_arch_initcall(p2020_rdb_pc, mpc85xx_common_publish_devices); machine_arch_initcall(p1020_mbg_pc, mpc85xx_common_publish_devices); machine_arch_initcall(p1020_rdb, mpc85xx_common_publish_devices); machine_arch_initcall(p1020_rdb_pc, mpc85xx_common_publish_devices); +machine_arch_initcall(p1020_rdb_pd, mpc85xx_common_publish_devices); machine_arch_initcall(p1020_utm_pc, mpc85xx_common_publish_devices); machine_arch_initcall(p1021_rdb_pc, mpc85xx_common_publish_devices); machine_arch_initcall(p1025_rdb, mpc85xx_common_publish_devices); @@ -193,6 +171,13 @@ static int __init p1020_rdb_pc_probe(void) return of_flat_dt_is_compatible(root, "fsl,P1020RDB-PC"); } +static int __init p1020_rdb_pd_probe(void) +{ + unsigned long root = of_get_flat_dt_root(); + + return of_flat_dt_is_compatible(root, "fsl,P1020RDB-PD"); +} + static int __init p1021_rdb_pc_probe(void) { unsigned long root = of_get_flat_dt_root(); @@ -246,6 +231,7 @@ define_machine(p2020_rdb) { .init_IRQ = mpc85xx_rdb_pic_init, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, .restart = fsl_rstcr_restart, @@ -260,6 +246,7 @@ define_machine(p1020_rdb) { .init_IRQ = mpc85xx_rdb_pic_init, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, .restart = fsl_rstcr_restart, @@ -274,6 +261,7 @@ define_machine(p1021_rdb_pc) { .init_IRQ = mpc85xx_rdb_pic_init, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, .restart = fsl_rstcr_restart, @@ -288,6 +276,7 @@ define_machine(p2020_rdb_pc) { .init_IRQ = mpc85xx_rdb_pic_init, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, .restart = fsl_rstcr_restart, @@ -302,6 +291,7 @@ define_machine(p1025_rdb) { .init_IRQ = mpc85xx_rdb_pic_init, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, .restart = fsl_rstcr_restart, @@ -316,6 +306,7 @@ define_machine(p1020_mbg_pc) { .init_IRQ = mpc85xx_rdb_pic_init, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, .restart = fsl_rstcr_restart, @@ -330,6 +321,7 @@ define_machine(p1020_utm_pc) { .init_IRQ = mpc85xx_rdb_pic_init, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, .restart = fsl_rstcr_restart, @@ -344,6 +336,22 @@ define_machine(p1020_rdb_pc) { .init_IRQ = mpc85xx_rdb_pic_init, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, +#endif + .get_irq = mpic_get_irq, + .restart = fsl_rstcr_restart, + .calibrate_decr = generic_calibrate_decr, + .progress = udbg_progress, +}; + +define_machine(p1020_rdb_pd) { + .name = "P1020RDB-PD", + .probe = p1020_rdb_pd_probe, + .setup_arch = mpc85xx_rdb_setup_arch, + .init_IRQ = mpc85xx_rdb_pic_init, +#ifdef CONFIG_PCI + .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, .restart = fsl_rstcr_restart, @@ -358,6 +366,7 @@ define_machine(p1024_rdb) { .init_IRQ = mpc85xx_rdb_pic_init, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, .restart = fsl_rstcr_restart, diff --git a/arch/powerpc/platforms/85xx/p1010rdb.c b/arch/powerpc/platforms/85xx/p1010rdb.c index 0252961392d..ad1a3d438a9 100644 --- a/arch/powerpc/platforms/85xx/p1010rdb.c +++ b/arch/powerpc/platforms/85xx/p1010rdb.c @@ -66,6 +66,8 @@ static int __init p1010_rdb_probe(void) if (of_flat_dt_is_compatible(root, "fsl,P1010RDB")) return 1; + if (of_flat_dt_is_compatible(root, "fsl,P1010RDB-PB")) + return 1; return 0; } @@ -76,6 +78,7 @@ define_machine(p1010_rdb) { .init_IRQ = p1010_rdb_pic_init, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, .restart = fsl_rstcr_restart, diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c index 7328b8d7412..6ac986d3f8a 100644 --- a/arch/powerpc/platforms/85xx/p1022_ds.c +++ b/arch/powerpc/platforms/85xx/p1022_ds.c @@ -106,42 +106,6 @@ (c2 << AD_COMP_2_SHIFT) | (c1 << AD_COMP_1_SHIFT) | \ (c0 << AD_COMP_0_SHIFT) | (size << AD_PIXEL_S_SHIFT)) -/** - * p1022ds_get_pixel_format: return the Area Descriptor for a given pixel depth - * - * The Area Descriptor is a 32-bit value that determine which bits in each - * pixel are to be used for each color. - */ -static u32 p1022ds_get_pixel_format(enum fsl_diu_monitor_port port, - unsigned int bits_per_pixel) -{ - switch (bits_per_pixel) { - case 32: - /* 0x88883316 */ - return MAKE_AD(3, 2, 0, 1, 3, 8, 8, 8, 8); - case 24: - /* 0x88082219 */ - return MAKE_AD(4, 0, 1, 2, 2, 0, 8, 8, 8); - case 16: - /* 0x65053118 */ - return MAKE_AD(4, 2, 1, 0, 1, 5, 6, 5, 0); - default: - pr_err("fsl-diu: unsupported pixel depth %u\n", bits_per_pixel); - return 0; - } -} - -/** - * p1022ds_set_gamma_table: update the gamma table, if necessary - * - * On some boards, the gamma table for some ports may need to be modified. - * This is not the case on the P1022DS, so we do nothing. -*/ -static void p1022ds_set_gamma_table(enum fsl_diu_monitor_port port, - char *gamma_table_base) -{ -} - struct fsl_law { u32 lawbar; u32 reserved1; @@ -215,13 +179,13 @@ static void p1022ds_set_monitor_port(enum fsl_diu_monitor_port port) /* Map the global utilities registers. */ guts_node = of_find_compatible_node(NULL, NULL, "fsl,p1022-guts"); if (!guts_node) { - pr_err("p1022ds: missing global utilties device node\n"); + pr_err("p1022ds: missing global utilities device node\n"); return; } guts = of_iomap(guts_node, 0); if (!guts) { - pr_err("p1022ds: could not map global utilties device\n"); + pr_err("p1022ds: could not map global utilities device\n"); goto exit; } @@ -302,7 +266,7 @@ static void p1022ds_set_monitor_port(enum fsl_diu_monitor_port port) goto exit; } cs1_addr = lbc_br_to_phys(ecm, num_laws, br1); - if (!cs0_addr) { + if (!cs1_addr) { pr_err("p1022ds: could not determine physical address for CS1" " (BR1=%08x)\n", br1); goto exit; @@ -416,14 +380,14 @@ void p1022ds_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("p1022ds: missing global utilties device node\n"); + pr_err("p1022ds: missing global utilities device node\n"); return; } guts = of_iomap(guts_np, 0); of_node_put(guts_np); if (!guts) { - pr_err("p1022ds: could not map global utilties device\n"); + pr_err("p1022ds: could not map global utilities device\n"); return; } @@ -510,8 +474,6 @@ static void __init p1022_ds_setup_arch(void) ppc_md.progress("p1022_ds_setup_arch()", 0); #if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE) - diu_ops.get_pixel_format = p1022ds_get_pixel_format; - diu_ops.set_gamma_table = p1022ds_set_gamma_table; diu_ops.set_monitor_port = p1022ds_set_monitor_port; diu_ops.set_pixel_clock = p1022ds_set_pixel_clock; diu_ops.valid_monitor_port = p1022ds_valid_monitor_port; @@ -605,6 +567,7 @@ define_machine(p1022_ds) { .init_IRQ = p1022_ds_pic_init, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, .restart = fsl_rstcr_restart, diff --git a/arch/powerpc/platforms/85xx/p1022_rdk.c b/arch/powerpc/platforms/85xx/p1022_rdk.c index 55ffa1cc380..7a180f0308d 100644 --- a/arch/powerpc/platforms/85xx/p1022_rdk.c +++ b/arch/powerpc/platforms/85xx/p1022_rdk.c @@ -35,17 +35,6 @@ #define CLKDVDR_PXCLK_MASK 0x00FF0000 /** - * p1022rdk_set_monitor_port: switch the output to a different monitor port - */ -static void p1022rdk_set_monitor_port(enum fsl_diu_monitor_port port) -{ - if (port != FSL_DIU_PORT_DVI) { - pr_err("p1022rdk: unsupported monitor port %i\n", port); - return; - } -} - -/** * p1022rdk_set_pixel_clock: program the DIU's clock * * @pixclock: the wavelength, in picoseconds, of the clock @@ -124,7 +113,6 @@ static void __init p1022_rdk_setup_arch(void) ppc_md.progress("p1022_rdk_setup_arch()", 0); #if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE) - diu_ops.set_monitor_port = p1022rdk_set_monitor_port; diu_ops.set_pixel_clock = p1022rdk_set_pixel_clock; diu_ops.valid_monitor_port = p1022rdk_valid_monitor_port; #endif @@ -159,6 +147,7 @@ define_machine(p1022_rdk) { .init_IRQ = p1022_rdk_pic_init, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, .restart = fsl_rstcr_restart, diff --git a/arch/powerpc/platforms/85xx/p1023_rds.c b/arch/powerpc/platforms/85xx/p1023_rdb.c index 9cc60a73883..d5b7509825d 100644 --- a/arch/powerpc/platforms/85xx/p1023_rds.c +++ b/arch/powerpc/platforms/85xx/p1023_rdb.c @@ -1,10 +1,10 @@ /* - * Copyright 2010-2011 Freescale Semiconductor, Inc. + * Copyright 2010-2011, 2013 Freescale Semiconductor, Inc. * * Author: Roy Zang <tie-fei.zang@freescale.com> * * Description: - * P1023 RDS Board Setup + * P1023 RDB Board Setup * * 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 @@ -41,12 +41,12 @@ * Setup the architecture * */ -static void __init mpc85xx_rds_setup_arch(void) +static void __init mpc85xx_rdb_setup_arch(void) { struct device_node *np; if (ppc_md.progress) - ppc_md.progress("p1023_rds_setup_arch()", 0); + ppc_md.progress("p1023_rdb_setup_arch()", 0); /* Map BCSR area */ np = of_find_node_by_name(NULL, "bcsr"); @@ -85,9 +85,9 @@ static void __init mpc85xx_rds_setup_arch(void) fsl_pci_assign_primary(); } -machine_arch_initcall(p1023_rds, mpc85xx_common_publish_devices); +machine_arch_initcall(p1023_rdb, mpc85xx_common_publish_devices); -static void __init mpc85xx_rds_pic_init(void) +static void __init mpc85xx_rdb_pic_init(void) { struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU, @@ -98,25 +98,25 @@ static void __init mpc85xx_rds_pic_init(void) mpic_init(mpic); } -static int __init p1023_rds_probe(void) +static int __init p1023_rdb_probe(void) { unsigned long root = of_get_flat_dt_root(); - return of_flat_dt_is_compatible(root, "fsl,P1023RDS"); + return of_flat_dt_is_compatible(root, "fsl,P1023RDB"); } -define_machine(p1023_rds) { - .name = "P1023 RDS", - .probe = p1023_rds_probe, - .setup_arch = mpc85xx_rds_setup_arch, - .init_IRQ = mpc85xx_rds_pic_init, +define_machine(p1023_rdb) { + .name = "P1023 RDB", + .probe = p1023_rdb_probe, + .setup_arch = mpc85xx_rdb_setup_arch, + .init_IRQ = mpc85xx_rdb_pic_init, .get_irq = mpic_get_irq, .restart = fsl_rstcr_restart, .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif }; - diff --git a/arch/powerpc/platforms/85xx/p2041_rdb.c b/arch/powerpc/platforms/85xx/p2041_rdb.c deleted file mode 100644 index 000c0892fc4..00000000000 --- a/arch/powerpc/platforms/85xx/p2041_rdb.c +++ /dev/null @@ -1,87 +0,0 @@ -/* - * P2041 RDB Setup - * - * Copyright 2011 Freescale Semiconductor Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - */ - -#include <linux/kernel.h> -#include <linux/pci.h> -#include <linux/kdev_t.h> -#include <linux/delay.h> -#include <linux/interrupt.h> -#include <linux/phy.h> - -#include <asm/time.h> -#include <asm/machdep.h> -#include <asm/pci-bridge.h> -#include <mm/mmu_decl.h> -#include <asm/prom.h> -#include <asm/udbg.h> -#include <asm/mpic.h> - -#include <linux/of_platform.h> -#include <sysdev/fsl_soc.h> -#include <sysdev/fsl_pci.h> -#include <asm/ehv_pic.h> - -#include "corenet_ds.h" - -/* - * Called very early, device-tree isn't unflattened - */ -static int __init p2041_rdb_probe(void) -{ - unsigned long root = of_get_flat_dt_root(); -#ifdef CONFIG_SMP - extern struct smp_ops_t smp_85xx_ops; -#endif - - if (of_flat_dt_is_compatible(root, "fsl,P2041RDB")) - return 1; - - /* Check if we're running under the Freescale hypervisor */ - if (of_flat_dt_is_compatible(root, "fsl,P2041RDB-hv")) { - ppc_md.init_IRQ = ehv_pic_init; - ppc_md.get_irq = ehv_pic_get_irq; - ppc_md.restart = fsl_hv_restart; - ppc_md.power_off = fsl_hv_halt; - ppc_md.halt = fsl_hv_halt; -#ifdef CONFIG_SMP - /* - * Disable the timebase sync operations because we can't write - * to the timebase registers under the hypervisor. - */ - smp_85xx_ops.give_timebase = NULL; - smp_85xx_ops.take_timebase = NULL; -#endif - return 1; - } - - return 0; -} - -define_machine(p2041_rdb) { - .name = "P2041 RDB", - .probe = p2041_rdb_probe, - .setup_arch = corenet_ds_setup_arch, - .init_IRQ = corenet_ds_pic_init, -#ifdef CONFIG_PCI - .pcibios_fixup_bus = fsl_pcibios_fixup_bus, -#endif - .get_irq = mpic_get_coreint_irq, - .restart = fsl_rstcr_restart, - .calibrate_decr = generic_calibrate_decr, - .progress = udbg_progress, - .power_save = e500_idle, -}; - -machine_arch_initcall(p2041_rdb, corenet_ds_publish_devices); - -#ifdef CONFIG_SWIOTLB -machine_arch_initcall(p2041_rdb, swiotlb_setup_bus_notifier); -#endif diff --git a/arch/powerpc/platforms/85xx/p3041_ds.c b/arch/powerpc/platforms/85xx/p3041_ds.c deleted file mode 100644 index b3edc205daa..00000000000 --- a/arch/powerpc/platforms/85xx/p3041_ds.c +++ /dev/null @@ -1,89 +0,0 @@ -/* - * P3041 DS Setup - * - * Maintained by Kumar Gala (see MAINTAINERS for contact information) - * - * Copyright 2009-2010 Freescale Semiconductor Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - */ - -#include <linux/kernel.h> -#include <linux/pci.h> -#include <linux/kdev_t.h> -#include <linux/delay.h> -#include <linux/interrupt.h> -#include <linux/phy.h> - -#include <asm/time.h> -#include <asm/machdep.h> -#include <asm/pci-bridge.h> -#include <mm/mmu_decl.h> -#include <asm/prom.h> -#include <asm/udbg.h> -#include <asm/mpic.h> - -#include <linux/of_platform.h> -#include <sysdev/fsl_soc.h> -#include <sysdev/fsl_pci.h> -#include <asm/ehv_pic.h> - -#include "corenet_ds.h" - -/* - * Called very early, device-tree isn't unflattened - */ -static int __init p3041_ds_probe(void) -{ - unsigned long root = of_get_flat_dt_root(); -#ifdef CONFIG_SMP - extern struct smp_ops_t smp_85xx_ops; -#endif - - if (of_flat_dt_is_compatible(root, "fsl,P3041DS")) - return 1; - - /* Check if we're running under the Freescale hypervisor */ - if (of_flat_dt_is_compatible(root, "fsl,P3041DS-hv")) { - ppc_md.init_IRQ = ehv_pic_init; - ppc_md.get_irq = ehv_pic_get_irq; - ppc_md.restart = fsl_hv_restart; - ppc_md.power_off = fsl_hv_halt; - ppc_md.halt = fsl_hv_halt; -#ifdef CONFIG_SMP - /* - * Disable the timebase sync operations because we can't write - * to the timebase registers under the hypervisor. - */ - smp_85xx_ops.give_timebase = NULL; - smp_85xx_ops.take_timebase = NULL; -#endif - return 1; - } - - return 0; -} - -define_machine(p3041_ds) { - .name = "P3041 DS", - .probe = p3041_ds_probe, - .setup_arch = corenet_ds_setup_arch, - .init_IRQ = corenet_ds_pic_init, -#ifdef CONFIG_PCI - .pcibios_fixup_bus = fsl_pcibios_fixup_bus, -#endif - .get_irq = mpic_get_coreint_irq, - .restart = fsl_rstcr_restart, - .calibrate_decr = generic_calibrate_decr, - .progress = udbg_progress, - .power_save = e500_idle, -}; - -machine_arch_initcall(p3041_ds, corenet_ds_publish_devices); - -#ifdef CONFIG_SWIOTLB -machine_arch_initcall(p3041_ds, swiotlb_setup_bus_notifier); -#endif diff --git a/arch/powerpc/platforms/85xx/p4080_ds.c b/arch/powerpc/platforms/85xx/p4080_ds.c deleted file mode 100644 index 54df10632ae..00000000000 --- a/arch/powerpc/platforms/85xx/p4080_ds.c +++ /dev/null @@ -1,87 +0,0 @@ -/* - * P4080 DS Setup - * - * Maintained by Kumar Gala (see MAINTAINERS for contact information) - * - * Copyright 2009 Freescale Semiconductor Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - */ - -#include <linux/kernel.h> -#include <linux/pci.h> -#include <linux/kdev_t.h> -#include <linux/delay.h> -#include <linux/interrupt.h> - -#include <asm/time.h> -#include <asm/machdep.h> -#include <asm/pci-bridge.h> -#include <mm/mmu_decl.h> -#include <asm/prom.h> -#include <asm/udbg.h> -#include <asm/mpic.h> - -#include <linux/of_platform.h> -#include <sysdev/fsl_soc.h> -#include <sysdev/fsl_pci.h> -#include <asm/ehv_pic.h> - -#include "corenet_ds.h" - -/* - * Called very early, device-tree isn't unflattened - */ -static int __init p4080_ds_probe(void) -{ - unsigned long root = of_get_flat_dt_root(); -#ifdef CONFIG_SMP - extern struct smp_ops_t smp_85xx_ops; -#endif - - if (of_flat_dt_is_compatible(root, "fsl,P4080DS")) - return 1; - - /* Check if we're running under the Freescale hypervisor */ - if (of_flat_dt_is_compatible(root, "fsl,P4080DS-hv")) { - ppc_md.init_IRQ = ehv_pic_init; - ppc_md.get_irq = ehv_pic_get_irq; - ppc_md.restart = fsl_hv_restart; - ppc_md.power_off = fsl_hv_halt; - ppc_md.halt = fsl_hv_halt; -#ifdef CONFIG_SMP - /* - * Disable the timebase sync operations because we can't write - * to the timebase registers under the hypervisor. - */ - smp_85xx_ops.give_timebase = NULL; - smp_85xx_ops.take_timebase = NULL; -#endif - return 1; - } - - return 0; -} - -define_machine(p4080_ds) { - .name = "P4080 DS", - .probe = p4080_ds_probe, - .setup_arch = corenet_ds_setup_arch, - .init_IRQ = corenet_ds_pic_init, -#ifdef CONFIG_PCI - .pcibios_fixup_bus = fsl_pcibios_fixup_bus, -#endif - .get_irq = mpic_get_coreint_irq, - .restart = fsl_rstcr_restart, - .calibrate_decr = generic_calibrate_decr, - .progress = udbg_progress, - .power_save = e500_idle, -}; - -machine_arch_initcall(p4080_ds, corenet_ds_publish_devices); -#ifdef CONFIG_SWIOTLB -machine_arch_initcall(p4080_ds, swiotlb_setup_bus_notifier); -#endif diff --git a/arch/powerpc/platforms/85xx/p5020_ds.c b/arch/powerpc/platforms/85xx/p5020_ds.c deleted file mode 100644 index 753a42c29d4..00000000000 --- a/arch/powerpc/platforms/85xx/p5020_ds.c +++ /dev/null @@ -1,98 +0,0 @@ -/* - * P5020 DS Setup - * - * Maintained by Kumar Gala (see MAINTAINERS for contact information) - * - * Copyright 2009-2010 Freescale Semiconductor Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - */ - -#include <linux/kernel.h> -#include <linux/pci.h> -#include <linux/kdev_t.h> -#include <linux/delay.h> -#include <linux/interrupt.h> -#include <linux/phy.h> - -#include <asm/time.h> -#include <asm/machdep.h> -#include <asm/pci-bridge.h> -#include <mm/mmu_decl.h> -#include <asm/prom.h> -#include <asm/udbg.h> -#include <asm/mpic.h> - -#include <linux/of_platform.h> -#include <sysdev/fsl_soc.h> -#include <sysdev/fsl_pci.h> -#include <asm/ehv_pic.h> - -#include "corenet_ds.h" - -/* - * Called very early, device-tree isn't unflattened - */ -static int __init p5020_ds_probe(void) -{ - unsigned long root = of_get_flat_dt_root(); -#ifdef CONFIG_SMP - extern struct smp_ops_t smp_85xx_ops; -#endif - - if (of_flat_dt_is_compatible(root, "fsl,P5020DS")) - return 1; - - /* Check if we're running under the Freescale hypervisor */ - if (of_flat_dt_is_compatible(root, "fsl,P5020DS-hv")) { - ppc_md.init_IRQ = ehv_pic_init; - ppc_md.get_irq = ehv_pic_get_irq; - ppc_md.restart = fsl_hv_restart; - ppc_md.power_off = fsl_hv_halt; - ppc_md.halt = fsl_hv_halt; -#ifdef CONFIG_SMP - /* - * Disable the timebase sync operations because we can't write - * to the timebase registers under the hypervisor. - */ - smp_85xx_ops.give_timebase = NULL; - smp_85xx_ops.take_timebase = NULL; -#endif - return 1; - } - - return 0; -} - -define_machine(p5020_ds) { - .name = "P5020 DS", - .probe = p5020_ds_probe, - .setup_arch = corenet_ds_setup_arch, - .init_IRQ = corenet_ds_pic_init, -#ifdef CONFIG_PCI - .pcibios_fixup_bus = fsl_pcibios_fixup_bus, -#endif -/* coreint doesn't play nice with lazy EE, use legacy mpic for now */ -#ifdef CONFIG_PPC64 - .get_irq = mpic_get_irq, -#else - .get_irq = mpic_get_coreint_irq, -#endif - .restart = fsl_rstcr_restart, - .calibrate_decr = generic_calibrate_decr, - .progress = udbg_progress, -#ifdef CONFIG_PPC64 - .power_save = book3e_idle, -#else - .power_save = e500_idle, -#endif -}; - -machine_arch_initcall(p5020_ds, corenet_ds_publish_devices); - -#ifdef CONFIG_SWIOTLB -machine_arch_initcall(p5020_ds, swiotlb_setup_bus_notifier); -#endif diff --git a/arch/powerpc/platforms/85xx/p5040_ds.c b/arch/powerpc/platforms/85xx/p5040_ds.c deleted file mode 100644 index 11381851828..00000000000 --- a/arch/powerpc/platforms/85xx/p5040_ds.c +++ /dev/null @@ -1,89 +0,0 @@ -/* - * P5040 DS Setup - * - * Copyright 2009-2010 Freescale Semiconductor Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - */ - -#include <linux/kernel.h> -#include <linux/pci.h> - -#include <asm/machdep.h> -#include <asm/udbg.h> -#include <asm/mpic.h> - -#include <linux/of_fdt.h> - -#include <sysdev/fsl_soc.h> -#include <sysdev/fsl_pci.h> -#include <asm/ehv_pic.h> - -#include "corenet_ds.h" - -/* - * Called very early, device-tree isn't unflattened - */ -static int __init p5040_ds_probe(void) -{ - unsigned long root = of_get_flat_dt_root(); -#ifdef CONFIG_SMP - extern struct smp_ops_t smp_85xx_ops; -#endif - - if (of_flat_dt_is_compatible(root, "fsl,P5040DS")) - return 1; - - /* Check if we're running under the Freescale hypervisor */ - if (of_flat_dt_is_compatible(root, "fsl,P5040DS-hv")) { - ppc_md.init_IRQ = ehv_pic_init; - ppc_md.get_irq = ehv_pic_get_irq; - ppc_md.restart = fsl_hv_restart; - ppc_md.power_off = fsl_hv_halt; - ppc_md.halt = fsl_hv_halt; -#ifdef CONFIG_SMP - /* - * Disable the timebase sync operations because we can't write - * to the timebase registers under the hypervisor. - */ - smp_85xx_ops.give_timebase = NULL; - smp_85xx_ops.take_timebase = NULL; -#endif - return 1; - } - - return 0; -} - -define_machine(p5040_ds) { - .name = "P5040 DS", - .probe = p5040_ds_probe, - .setup_arch = corenet_ds_setup_arch, - .init_IRQ = corenet_ds_pic_init, -#ifdef CONFIG_PCI - .pcibios_fixup_bus = fsl_pcibios_fixup_bus, -#endif -/* coreint doesn't play nice with lazy EE, use legacy mpic for now */ -#ifdef CONFIG_PPC64 - .get_irq = mpic_get_irq, -#else - .get_irq = mpic_get_coreint_irq, -#endif - .restart = fsl_rstcr_restart, - .calibrate_decr = generic_calibrate_decr, - .progress = udbg_progress, -#ifdef CONFIG_PPC64 - .power_save = book3e_idle, -#else - .power_save = e500_idle, -#endif -}; - -machine_arch_initcall(p5040_ds, corenet_ds_publish_devices); - -#ifdef CONFIG_SWIOTLB -machine_arch_initcall(p5040_ds, swiotlb_setup_bus_notifier); -#endif diff --git a/arch/powerpc/platforms/85xx/ppa8548.c b/arch/powerpc/platforms/85xx/ppa8548.c new file mode 100644 index 00000000000..3daff7c6356 --- /dev/null +++ b/arch/powerpc/platforms/85xx/ppa8548.c @@ -0,0 +1,99 @@ +/* + * ppa8548 setup and early boot code. + * + * Copyright 2009 Prodrive B.V.. + * + * By Stef van Os (see MAINTAINERS for contact information) + * + * Based on the SBC8548 support - Copyright 2007 Wind River Systems Inc. + * Based on the MPC8548CDS support - Copyright 2005 Freescale Inc. + * + * 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/stddef.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/reboot.h> +#include <linux/seq_file.h> +#include <linux/of_fdt.h> +#include <linux/of_platform.h> + +#include <asm/machdep.h> +#include <asm/udbg.h> +#include <asm/mpic.h> + +#include <sysdev/fsl_soc.h> + +static void __init ppa8548_pic_init(void) +{ + struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN, + 0, 256, " OpenPIC "); + BUG_ON(mpic == NULL); + mpic_init(mpic); +} + +/* + * Setup the architecture + */ +static void __init ppa8548_setup_arch(void) +{ + if (ppc_md.progress) + ppc_md.progress("ppa8548_setup_arch()", 0); +} + +static void ppa8548_show_cpuinfo(struct seq_file *m) +{ + uint32_t svid, phid1; + + svid = mfspr(SPRN_SVR); + + seq_printf(m, "Vendor\t\t: Prodrive B.V.\n"); + seq_printf(m, "SVR\t\t: 0x%x\n", svid); + + /* Display cpu Pll setting */ + phid1 = mfspr(SPRN_HID1); + seq_printf(m, "PLL setting\t: 0x%x\n", ((phid1 >> 24) & 0x3f)); +} + +static struct of_device_id __initdata of_bus_ids[] = { + { .name = "soc", }, + { .type = "soc", }, + { .compatible = "simple-bus", }, + { .compatible = "gianfar", }, + { .compatible = "fsl,srio", }, + {}, +}; + +static int __init declare_of_platform_devices(void) +{ + of_platform_bus_probe(NULL, of_bus_ids, NULL); + + return 0; +} +machine_device_initcall(ppa8548, declare_of_platform_devices); + +/* + * Called very early, device-tree isn't unflattened + */ +static int __init ppa8548_probe(void) +{ + unsigned long root = of_get_flat_dt_root(); + + return of_flat_dt_is_compatible(root, "ppa8548"); +} + +define_machine(ppa8548) { + .name = "ppa8548", + .probe = ppa8548_probe, + .setup_arch = ppa8548_setup_arch, + .init_IRQ = ppa8548_pic_init, + .show_cpuinfo = ppa8548_show_cpuinfo, + .get_irq = mpic_get_irq, + .restart = fsl_rstcr_restart, + .calibrate_decr = generic_calibrate_decr, + .progress = udbg_progress, +}; diff --git a/arch/powerpc/platforms/85xx/qemu_e500.c b/arch/powerpc/platforms/85xx/qemu_e500.c index f6ea5618c73..7f267329354 100644 --- a/arch/powerpc/platforms/85xx/qemu_e500.c +++ b/arch/powerpc/platforms/85xx/qemu_e500.c @@ -29,9 +29,10 @@ void __init qemu_e500_pic_init(void) { struct mpic *mpic; + unsigned int flags = MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU | + MPIC_ENABLE_COREINT; - mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU, - 0, 256, " OpenPIC "); + mpic = mpic_alloc(NULL, 0, flags, 0, 256, " OpenPIC "); BUG_ON(mpic == NULL); mpic_init(mpic); @@ -65,8 +66,9 @@ define_machine(qemu_e500) { .init_IRQ = qemu_e500_pic_init, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif - .get_irq = mpic_get_irq, + .get_irq = mpic_get_coreint_irq, .restart = fsl_rstcr_restart, .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, diff --git a/arch/powerpc/platforms/85xx/sbc8548.c b/arch/powerpc/platforms/85xx/sbc8548.c index f6212182591..b07214666d6 100644 --- a/arch/powerpc/platforms/85xx/sbc8548.c +++ b/arch/powerpc/platforms/85xx/sbc8548.c @@ -135,6 +135,7 @@ define_machine(sbc8548) { .restart = fsl_rstcr_restart, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, diff --git a/arch/powerpc/platforms/85xx/sgy_cts1000.c b/arch/powerpc/platforms/85xx/sgy_cts1000.c new file mode 100644 index 00000000000..bb75add6708 --- /dev/null +++ b/arch/powerpc/platforms/85xx/sgy_cts1000.c @@ -0,0 +1,176 @@ +/* + * Servergy CTS-1000 Setup + * + * Maintained by Ben Collins <ben.c@servergy.com> + * + * Copyright 2012 by Servergy, Inc. + * + * 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/platform_device.h> +#include <linux/device.h> +#include <linux/module.h> +#include <linux/of_gpio.h> +#include <linux/of_irq.h> +#include <linux/workqueue.h> +#include <linux/reboot.h> +#include <linux/interrupt.h> + +#include <asm/machdep.h> + +static struct device_node *halt_node; + +static struct of_device_id child_match[] = { + { + .compatible = "sgy,gpio-halt", + }, + {}, +}; + +static void gpio_halt_wfn(struct work_struct *work) +{ + /* Likely wont return */ + orderly_poweroff(true); +} +static DECLARE_WORK(gpio_halt_wq, gpio_halt_wfn); + +static void gpio_halt_cb(void) +{ + enum of_gpio_flags flags; + int trigger, gpio; + + if (!halt_node) + return; + + gpio = of_get_gpio_flags(halt_node, 0, &flags); + + if (!gpio_is_valid(gpio)) + return; + + trigger = (flags == OF_GPIO_ACTIVE_LOW); + + printk(KERN_INFO "gpio-halt: triggering GPIO.\n"); + + /* Probably wont return */ + gpio_set_value(gpio, trigger); +} + +/* This IRQ means someone pressed the power button and it is waiting for us + * to handle the shutdown/poweroff. */ +static irqreturn_t gpio_halt_irq(int irq, void *__data) +{ + printk(KERN_INFO "gpio-halt: shutdown due to power button IRQ.\n"); + schedule_work(&gpio_halt_wq); + + return IRQ_HANDLED; +}; + +static int gpio_halt_probe(struct platform_device *pdev) +{ + enum of_gpio_flags flags; + struct device_node *node = pdev->dev.of_node; + int gpio, err, irq; + int trigger; + + if (!node) + return -ENODEV; + + /* If there's no matching child, this isn't really an error */ + halt_node = of_find_matching_node(node, child_match); + if (!halt_node) + return 0; + + /* Technically we could just read the first one, but punish + * DT writers for invalid form. */ + if (of_gpio_count(halt_node) != 1) + return -EINVAL; + + /* Get the gpio number relative to the dynamic base. */ + gpio = of_get_gpio_flags(halt_node, 0, &flags); + if (!gpio_is_valid(gpio)) + return -EINVAL; + + err = gpio_request(gpio, "gpio-halt"); + if (err) { + printk(KERN_ERR "gpio-halt: error requesting GPIO %d.\n", + gpio); + halt_node = NULL; + return err; + } + + trigger = (flags == OF_GPIO_ACTIVE_LOW); + + gpio_direction_output(gpio, !trigger); + + /* Now get the IRQ which tells us when the power button is hit */ + irq = irq_of_parse_and_map(halt_node, 0); + err = request_irq(irq, gpio_halt_irq, IRQF_TRIGGER_RISING | + IRQF_TRIGGER_FALLING, "gpio-halt", halt_node); + if (err) { + printk(KERN_ERR "gpio-halt: error requesting IRQ %d for " + "GPIO %d.\n", irq, gpio); + gpio_free(gpio); + halt_node = NULL; + return err; + } + + /* Register our halt function */ + ppc_md.halt = gpio_halt_cb; + ppc_md.power_off = gpio_halt_cb; + + printk(KERN_INFO "gpio-halt: registered GPIO %d (%d trigger, %d" + " irq).\n", gpio, trigger, irq); + + return 0; +} + +static int gpio_halt_remove(struct platform_device *pdev) +{ + if (halt_node) { + int gpio = of_get_gpio(halt_node, 0); + int irq = irq_of_parse_and_map(halt_node, 0); + + free_irq(irq, halt_node); + + ppc_md.halt = NULL; + ppc_md.power_off = NULL; + + gpio_free(gpio); + + halt_node = NULL; + } + + return 0; +} + +static struct of_device_id gpio_halt_match[] = { + /* We match on the gpio bus itself and scan the children since they + * wont be matched against us. We know the bus wont match until it + * has been registered too. */ + { + .compatible = "fsl,qoriq-gpio", + }, + {}, +}; +MODULE_DEVICE_TABLE(of, gpio_halt_match); + +static struct platform_driver gpio_halt_driver = { + .driver = { + .name = "gpio-halt", + .owner = THIS_MODULE, + .of_match_table = gpio_halt_match, + }, + .probe = gpio_halt_probe, + .remove = gpio_halt_remove, +}; + +module_platform_driver(gpio_halt_driver); + +MODULE_DESCRIPTION("Driver to support GPIO triggered system halt for Servergy CTS-1000 Systems."); +MODULE_VERSION("1.0"); +MODULE_AUTHOR("Ben Collins <ben.c@servergy.com>"); +MODULE_LICENSE("GPL"); diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c index 148c2f2d978..ba093f55367 100644 --- a/arch/powerpc/platforms/85xx/smp.c +++ b/arch/powerpc/platforms/85xx/smp.c @@ -15,6 +15,7 @@ #include <linux/init.h> #include <linux/delay.h> #include <linux/of.h> +#include <linux/of_address.h> #include <linux/kexec.h> #include <linux/highmem.h> #include <linux/cpu.h> @@ -26,6 +27,7 @@ #include <asm/cacheflush.h> #include <asm/dbell.h> #include <asm/fsl_guts.h> +#include <asm/code-patching.h> #include <sysdev/fsl_soc.h> #include <sysdev/mpic.h> @@ -69,7 +71,32 @@ static void mpc85xx_give_timebase(void) tb_req = 0; mpc85xx_timebase_freeze(1); +#ifdef CONFIG_PPC64 + /* + * e5500/e6500 have a workaround for erratum A-006958 in place + * that will reread the timebase until TBL is non-zero. + * That would be a bad thing when the timebase is frozen. + * + * Thus, we read it manually, and instead of checking that + * TBL is non-zero, we ensure that TB does not change. We don't + * do that for the main mftb implementation, because it requires + * a scratch register + */ + { + u64 prev; + + asm volatile("mfspr %0, %1" : "=r" (timebase) : + "i" (SPRN_TBRL)); + + do { + prev = timebase; + asm volatile("mfspr %0, %1" : "=r" (timebase) : + "i" (SPRN_TBRL)); + } while (prev != timebase); + } +#else timebase = get_tb(); +#endif mb(); tb_valid = 1; @@ -99,7 +126,7 @@ static void mpc85xx_take_timebase(void) } #ifdef CONFIG_HOTPLUG_CPU -static void __cpuinit smp_85xx_mach_cpu_die(void) +static void smp_85xx_mach_cpu_die(void) { unsigned int cpu = smp_processor_id(); u32 tmp; @@ -141,7 +168,7 @@ static inline u32 read_spin_table_addr_l(void *spin_table) return in_be32(&((struct epapr_spin_table *)spin_table)->addr_l); } -static int __cpuinit smp_85xx_kick_cpu(int nr) +static int smp_85xx_kick_cpu(int nr) { unsigned long flags; const u64 *cpu_rel_addr; @@ -201,7 +228,7 @@ static int __cpuinit smp_85xx_kick_cpu(int nr) * We don't set the BPTR register here since it already points * to the boot page properly. */ - mpic_reset_core(hw_cpu); + mpic_reset_core(nr); /* * wait until core is ready... @@ -241,7 +268,7 @@ out: flush_spin_table(spin_table); out_be32(&spin_table->pir, hw_cpu); out_be64((u64 *)(&spin_table->addr_h), - __pa((u64)*((unsigned long long *)generic_secondary_smp_init))); + __pa(ppc_function_entry(generic_secondary_smp_init))); flush_spin_table(spin_table); #endif @@ -255,6 +282,7 @@ out: struct smp_ops_t smp_85xx_ops = { .kick_cpu = smp_85xx_kick_cpu, + .cpu_bootable = smp_generic_cpu_bootable, #ifdef CONFIG_HOTPLUG_CPU .cpu_disable = generic_cpu_disable, .cpu_die = generic_cpu_die, @@ -362,15 +390,18 @@ static void mpc85xx_smp_machine_kexec(struct kimage *image) } #endif /* CONFIG_KEXEC */ -static void __cpuinit smp_85xx_setup_cpu(int cpu_nr) +static void smp_85xx_basic_setup(int cpu_nr) { - if (smp_85xx_ops.probe == smp_mpic_probe) - mpic_setup_this_cpu(); - if (cpu_has_feature(CPU_FTR_DBELL)) doorbell_setup_this_cpu(); } +static void smp_85xx_setup_cpu(int cpu_nr) +{ + mpic_setup_this_cpu(); + smp_85xx_basic_setup(cpu_nr); +} + static const struct of_device_id mpc85xx_smp_guts_ids[] = { { .compatible = "fsl,mpc8572-guts", }, { .compatible = "fsl,p1020-guts", }, @@ -385,13 +416,14 @@ void __init mpc85xx_smp_init(void) { struct device_node *np; - smp_85xx_ops.setup_cpu = smp_85xx_setup_cpu; np = of_find_node_by_type(NULL, "open-pic"); if (np) { smp_85xx_ops.probe = smp_mpic_probe; + smp_85xx_ops.setup_cpu = smp_85xx_setup_cpu; smp_85xx_ops.message_pass = smp_mpic_message_pass; - } + } else + smp_85xx_ops.setup_cpu = smp_85xx_basic_setup; if (cpu_has_feature(CPU_FTR_DBELL)) { /* @@ -400,6 +432,7 @@ void __init mpc85xx_smp_init(void) */ smp_85xx_ops.message_pass = NULL; smp_85xx_ops.cause_ipi = doorbell_cause_ipi; + smp_85xx_ops.probe = NULL; } np = of_find_matching_node(NULL, mpc85xx_smp_guts_ids); diff --git a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c index 3bbbf748948..55a9682b952 100644 --- a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c +++ b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c @@ -9,6 +9,8 @@ */ #include <linux/irq.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> #include <linux/of_platform.h> #include <linux/io.h> diff --git a/arch/powerpc/platforms/85xx/twr_p102x.c b/arch/powerpc/platforms/85xx/twr_p102x.c new file mode 100644 index 00000000000..1eadb6d0dc6 --- /dev/null +++ b/arch/powerpc/platforms/85xx/twr_p102x.c @@ -0,0 +1,148 @@ +/* + * Copyright 2010-2011, 2013 Freescale Semiconductor, Inc. + * + * Author: Michael Johnston <michael.johnston@freescale.com> + * + * Description: + * TWR-P102x Board Setup + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/errno.h> +#include <linux/pci.h> +#include <linux/of_platform.h> + +#include <asm/pci-bridge.h> +#include <asm/udbg.h> +#include <asm/mpic.h> +#include <asm/qe.h> +#include <asm/qe_ic.h> +#include <asm/fsl_guts.h> + +#include <sysdev/fsl_soc.h> +#include <sysdev/fsl_pci.h> +#include "smp.h" + +#include "mpc85xx.h" + +static void __init twr_p1025_pic_init(void) +{ + struct mpic *mpic; + +#ifdef CONFIG_QUICC_ENGINE + struct device_node *np; +#endif + + mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN | + MPIC_SINGLE_DEST_CPU, + 0, 256, " OpenPIC "); + + BUG_ON(mpic == NULL); + mpic_init(mpic); + +#ifdef CONFIG_QUICC_ENGINE + np = of_find_compatible_node(NULL, NULL, "fsl,qe-ic"); + if (np) { + qe_ic_init(np, 0, qe_ic_cascade_low_mpic, + qe_ic_cascade_high_mpic); + of_node_put(np); + } else + pr_err("Could not find qe-ic node\n"); +#endif +} + +/* ************************************************************************ + * + * Setup the architecture + * + */ +static void __init twr_p1025_setup_arch(void) +{ +#ifdef CONFIG_QUICC_ENGINE + struct device_node *np; +#endif + + if (ppc_md.progress) + ppc_md.progress("twr_p1025_setup_arch()", 0); + + mpc85xx_smp_init(); + + fsl_pci_assign_primary(); + +#ifdef CONFIG_QUICC_ENGINE + mpc85xx_qe_init(); + mpc85xx_qe_par_io_init(); + +#if defined(CONFIG_UCC_GETH) || defined(CONFIG_SERIAL_QE) + if (machine_is(twr_p1025)) { + struct ccsr_guts __iomem *guts; + + np = of_find_compatible_node(NULL, NULL, "fsl,p1021-guts"); + if (np) { + guts = of_iomap(np, 0); + if (!guts) + pr_err("twr_p1025: could not map global utilities register\n"); + else { + /* P1025 has pins muxed for QE and other functions. To + * enable QE UEC mode, we need to set bit QE0 for UCC1 + * in Eth mode, QE0 and QE3 for UCC5 in Eth mode, QE9 + * and QE12 for QE MII management signals in PMUXCR + * register. + * Set QE mux bits in PMUXCR */ + setbits32(&guts->pmuxcr, MPC85xx_PMUXCR_QE(0) | + MPC85xx_PMUXCR_QE(3) | + MPC85xx_PMUXCR_QE(9) | + MPC85xx_PMUXCR_QE(12)); + iounmap(guts); + +#if defined(CONFIG_SERIAL_QE) + /* On P1025TWR board, the UCC7 acted as UART port. + * However, The UCC7's CTS pin is low level in default, + * it will impact the transmission in full duplex + * communication. So disable the Flow control pin PA18. + * The UCC7 UART just can use RXD and TXD pins. + */ + par_io_config_pin(0, 18, 0, 0, 0, 0); +#endif + /* Drive PB29 to CPLD low - CPLD will then change + * muxing from LBC to QE */ + par_io_config_pin(1, 29, 1, 0, 0, 0); + par_io_data_set(1, 29, 0); + } + of_node_put(np); + } + } +#endif +#endif /* CONFIG_QUICC_ENGINE */ + + pr_info("TWR-P1025 board from Freescale Semiconductor\n"); +} + +machine_arch_initcall(twr_p1025, mpc85xx_common_publish_devices); + +static int __init twr_p1025_probe(void) +{ + unsigned long root = of_get_flat_dt_root(); + + return of_flat_dt_is_compatible(root, "fsl,TWR-P1025"); +} + +define_machine(twr_p1025) { + .name = "TWR-P1025", + .probe = twr_p1025_probe, + .setup_arch = twr_p1025_setup_arch, + .init_IRQ = twr_p1025_pic_init, +#ifdef CONFIG_PCI + .pcibios_fixup_bus = fsl_pcibios_fixup_bus, +#endif + .get_irq = mpic_get_irq, + .restart = fsl_rstcr_restart, + .calibrate_decr = generic_calibrate_decr, + .progress = udbg_progress, +}; diff --git a/arch/powerpc/platforms/85xx/xes_mpc85xx.c b/arch/powerpc/platforms/85xx/xes_mpc85xx.c index dcbf7e42dce..1a9c1085855 100644 --- a/arch/powerpc/platforms/85xx/xes_mpc85xx.c +++ b/arch/powerpc/platforms/85xx/xes_mpc85xx.c @@ -170,6 +170,7 @@ define_machine(xes_mpc8572) { .init_IRQ = xes_mpc85xx_pic_init, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, .restart = fsl_rstcr_restart, @@ -184,6 +185,7 @@ define_machine(xes_mpc8548) { .init_IRQ = xes_mpc85xx_pic_init, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, .restart = fsl_rstcr_restart, @@ -198,6 +200,7 @@ define_machine(xes_mpc8540) { .init_IRQ = xes_mpc85xx_pic_init, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, .restart = fsl_rstcr_restart, diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig index 7a6279e3821..1afd1e4a2dd 100644 --- a/arch/powerpc/platforms/86xx/Kconfig +++ b/arch/powerpc/platforms/86xx/Kconfig @@ -37,7 +37,6 @@ config GEF_PPC9A bool "GE PPC9A" select DEFAULT_UIMAGE select MMIO_NVRAM - select GENERIC_GPIO select ARCH_REQUIRE_GPIOLIB select GE_FPGA help @@ -47,7 +46,6 @@ config GEF_SBC310 bool "GE SBC310" select DEFAULT_UIMAGE select MMIO_NVRAM - select GENERIC_GPIO select ARCH_REQUIRE_GPIOLIB select GE_FPGA help @@ -57,7 +55,6 @@ config GEF_SBC610 bool "GE SBC610" select DEFAULT_UIMAGE select MMIO_NVRAM - select GENERIC_GPIO select ARCH_REQUIRE_GPIOLIB select GE_FPGA select HAS_RAPIDIO diff --git a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c index 04d9d317f74..d479d68fbb2 100644 --- a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c +++ b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c @@ -236,14 +236,14 @@ void mpc8610hpcd_set_pixel_clock(unsigned int pixclock) /* Map the global utilities registers. */ guts_np = of_find_compatible_node(NULL, NULL, "fsl,mpc8610-guts"); if (!guts_np) { - pr_err("mpc8610hpcd: missing global utilties device node\n"); + pr_err("mpc8610hpcd: missing global utilities device node\n"); return; } guts = of_iomap(guts_np, 0); of_node_put(guts_np); if (!guts) { - pr_err("mpc8610hpcd: could not map global utilties device\n"); + pr_err("mpc8610hpcd: could not map global utilities device\n"); return; } diff --git a/arch/powerpc/platforms/86xx/pic.c b/arch/powerpc/platforms/86xx/pic.c index 9982f57c98b..d5b98c0f958 100644 --- a/arch/powerpc/platforms/86xx/pic.c +++ b/arch/powerpc/platforms/86xx/pic.c @@ -10,6 +10,7 @@ #include <linux/stddef.h> #include <linux/kernel.h> #include <linux/interrupt.h> +#include <linux/of_irq.h> #include <linux/of_platform.h> #include <asm/mpic.h> diff --git a/arch/powerpc/platforms/8xx/Kconfig b/arch/powerpc/platforms/8xx/Kconfig index 1fb0b3cddeb..bd6f1a1cf92 100644 --- a/arch/powerpc/platforms/8xx/Kconfig +++ b/arch/powerpc/platforms/8xx/Kconfig @@ -45,7 +45,6 @@ config PPC_EP88XC config PPC_ADDER875 bool "Analogue & Micro Adder 875" select CPM1 - select REDBOOT help This enables support for the Analogue & Micro Adder 875 board. @@ -114,7 +113,6 @@ config 8xx_COPYBACK config 8xx_GPIO bool "GPIO API Support" - select GENERIC_GPIO select ARCH_REQUIRE_GPIOLIB help Saying Y here will cause the ports on an MPC8xx processor to be used diff --git a/arch/powerpc/platforms/8xx/ep88xc.c b/arch/powerpc/platforms/8xx/ep88xc.c index 7d9ac6040d6..e62166681d0 100644 --- a/arch/powerpc/platforms/8xx/ep88xc.c +++ b/arch/powerpc/platforms/8xx/ep88xc.c @@ -10,6 +10,8 @@ */ #include <linux/init.h> +#include <linux/of_address.h> +#include <linux/of_fdt.h> #include <linux/of_platform.h> #include <asm/machdep.h> diff --git a/arch/powerpc/platforms/8xx/m8xx_setup.c b/arch/powerpc/platforms/8xx/m8xx_setup.c index 1e121088826..587a2828b06 100644 --- a/arch/powerpc/platforms/8xx/m8xx_setup.c +++ b/arch/powerpc/platforms/8xx/m8xx_setup.c @@ -43,6 +43,7 @@ static irqreturn_t timebase_interrupt(int irq, void *dev) static struct irqaction tbint_irqaction = { .handler = timebase_interrupt, + .flags = IRQF_NO_THREAD, .name = "tbint", }; @@ -218,19 +219,12 @@ void mpc8xx_restart(char *cmd) static void cpm_cascade(unsigned int irq, struct irq_desc *desc) { - struct irq_chip *chip; - int cascade_irq; - - if ((cascade_irq = cpm_get_irq()) >= 0) { - struct irq_desc *cdesc = irq_to_desc(cascade_irq); + struct irq_chip *chip = irq_desc_get_chip(desc); + int cascade_irq = cpm_get_irq(); + if (cascade_irq >= 0) generic_handle_irq(cascade_irq); - chip = irq_desc_get_chip(cdesc); - chip->irq_eoi(&cdesc->irq_data); - } - - chip = irq_desc_get_chip(desc); chip->irq_eoi(&desc->irq_data); } diff --git a/arch/powerpc/platforms/8xx/mpc86xads_setup.c b/arch/powerpc/platforms/8xx/mpc86xads_setup.c index 866feff83c9..63084640c5c 100644 --- a/arch/powerpc/platforms/8xx/mpc86xads_setup.c +++ b/arch/powerpc/platforms/8xx/mpc86xads_setup.c @@ -15,6 +15,8 @@ */ #include <linux/init.h> +#include <linux/of_address.h> +#include <linux/of_fdt.h> #include <linux/of_platform.h> #include <asm/io.h> diff --git a/arch/powerpc/platforms/8xx/mpc885ads_setup.c b/arch/powerpc/platforms/8xx/mpc885ads_setup.c index 5d98398c2f5..c1262581b63 100644 --- a/arch/powerpc/platforms/8xx/mpc885ads_setup.c +++ b/arch/powerpc/platforms/8xx/mpc885ads_setup.c @@ -25,6 +25,8 @@ #include <linux/fs_uart_pd.h> #include <linux/fsl_devices.h> #include <linux/mii.h> +#include <linux/of_address.h> +#include <linux/of_fdt.h> #include <linux/of_platform.h> #include <asm/delay.h> diff --git a/arch/powerpc/platforms/8xx/tqm8xx_setup.c b/arch/powerpc/platforms/8xx/tqm8xx_setup.c index 8d21ab70e06..251aba8759e 100644 --- a/arch/powerpc/platforms/8xx/tqm8xx_setup.c +++ b/arch/powerpc/platforms/8xx/tqm8xx_setup.c @@ -28,6 +28,7 @@ #include <linux/fs_uart_pd.h> #include <linux/fsl_devices.h> #include <linux/mii.h> +#include <linux/of_fdt.h> #include <linux/of_platform.h> #include <asm/delay.h> @@ -48,7 +49,7 @@ struct cpm_pin { int port, pin, flags; }; -static struct __initdata cpm_pin tqm8xx_pins[] = { +static struct cpm_pin tqm8xx_pins[] __initdata = { /* SMC1 */ {CPM_PORTB, 24, CPM_PIN_INPUT}, /* RX */ {CPM_PORTB, 25, CPM_PIN_INPUT | CPM_PIN_SECONDARY}, /* TX */ @@ -63,7 +64,7 @@ static struct __initdata cpm_pin tqm8xx_pins[] = { {CPM_PORTC, 11, CPM_PIN_INPUT | CPM_PIN_SECONDARY | CPM_PIN_GPIO}, }; -static struct __initdata cpm_pin tqm8xx_fec_pins[] = { +static struct cpm_pin tqm8xx_fec_pins[] __initdata = { /* MII */ {CPM_PORTD, 3, CPM_PIN_OUTPUT}, {CPM_PORTD, 4, CPM_PIN_OUTPUT}, diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index 48a920d5148..391b3f6b54a 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -6,7 +6,6 @@ source "arch/powerpc/platforms/chrp/Kconfig" source "arch/powerpc/platforms/512x/Kconfig" source "arch/powerpc/platforms/52xx/Kconfig" source "arch/powerpc/platforms/powermac/Kconfig" -source "arch/powerpc/platforms/prep/Kconfig" source "arch/powerpc/platforms/maple/Kconfig" source "arch/powerpc/platforms/pasemi/Kconfig" source "arch/powerpc/platforms/ps3/Kconfig" @@ -20,7 +19,6 @@ source "arch/powerpc/platforms/embedded6xx/Kconfig" source "arch/powerpc/platforms/44x/Kconfig" source "arch/powerpc/platforms/40x/Kconfig" source "arch/powerpc/platforms/amigaone/Kconfig" -source "arch/powerpc/platforms/wsp/Kconfig" config KVM_GUEST bool "KVM Guest support" @@ -87,6 +85,27 @@ config MPIC bool default n +config MPIC_TIMER + bool "MPIC Global Timer" + depends on MPIC && FSL_SOC + default n + help + The MPIC global timer is a hardware timer inside the + Freescale PIC complying with OpenPIC standard. When the + specified interval times out, the hardware timer generates + an interrupt. The driver currently is only tested on fsl + chip, but it can potentially support other global timers + complying with the OpenPIC standard. + +config FSL_MPIC_TIMER_WAKEUP + tristate "Freescale MPIC global timer wakeup driver" + depends on FSL_SOC && MPIC_TIMER && PM + default n + help + The driver provides a way to wake up the system by MPIC + timer. + e.g. "echo 5 > /sys/devices/system/mpic/timer_wakeup" + config PPC_EPAPR_HV_PIC bool default n @@ -129,7 +148,7 @@ config PPC_RTAS_DAEMON config RTAS_PROC bool "Proc interface to RTAS" - depends on PPC_RTAS + depends on PPC_RTAS && PROC_FS default y config RTAS_FLASH @@ -165,6 +184,11 @@ config IBMEBUS help Bus device driver for GX bus based adapters. +config EEH + bool + depends on (PPC_POWERNV || PPC_PSERIES) && PCI + default y + config PPC_MPC106 bool default n @@ -177,54 +201,18 @@ config PPC_P7_NAP bool default n -config PPC_INDIRECT_IO - bool - select GENERIC_IOMAP - config PPC_INDIRECT_PIO bool - select PPC_INDIRECT_IO + select GENERIC_IOMAP config PPC_INDIRECT_MMIO bool - select PPC_INDIRECT_IO config PPC_IO_WORKAROUNDS bool source "drivers/cpufreq/Kconfig" -menu "CPU Frequency drivers" - depends on CPU_FREQ - -config CPU_FREQ_PMAC - bool "Support for Apple PowerBooks" - depends on ADB_PMU && PPC32 - select CPU_FREQ_TABLE - help - This adds support for frequency switching on Apple PowerBooks, - this currently includes some models of iBook & Titanium - PowerBook. - -config CPU_FREQ_PMAC64 - bool "Support for some Apple G5s" - depends on PPC_PMAC && PPC64 - select CPU_FREQ_TABLE - help - This adds support for frequency switching on Apple iMac G5, - and some of the more recent desktop G5 machines as well. - -config PPC_PASEMI_CPUFREQ - bool "Support for PA Semi PWRficient" - depends on PPC_PASEMI - default y - select CPU_FREQ_TABLE - help - This adds the support for frequency switching on PA Semi - PWRficient processors. - -endmenu - menu "CPUIdle driver" source "drivers/cpuidle/Kconfig" @@ -233,7 +221,7 @@ endmenu config PPC601_SYNC_FIX bool "Workarounds for PPC601 bugs" - depends on 6xx && (PPC_PREP || PPC_PMAC) + depends on 6xx && PPC_PMAC help Some versions of the PPC601 (the first PowerPC chip) have bugs which mean that extra synchronization instructions are required near @@ -303,7 +291,6 @@ config QUICC_ENGINE config QE_GPIO bool "QE GPIO support" depends on QUICC_ENGINE - select GENERIC_GPIO select ARCH_REQUIRE_GPIOLIB help Say Y here if you're going to use hardware that connects to the @@ -316,7 +303,6 @@ config CPM2 select PPC_LIB_RHEAP select PPC_PCI_CHOICE select ARCH_REQUIRE_GPIOLIB - select GENERIC_GPIO help The CPM2 (Communications Processor Module) is a coprocessor on embedded CPUs made by Freescale. Selecting this option means that @@ -344,7 +330,6 @@ config FSL_ULI1575 config CPM bool - select PPC_CLOCK config OF_RTC bool @@ -352,12 +337,9 @@ config OF_RTC Uses information from the OF or flattened device tree to instantiate platform devices for direct mapped RTC chips like the DS1742 or DS1743. -source "arch/powerpc/sysdev/bestcomm/Kconfig" - config SIMPLE_GPIO bool "Support for simple, memory-mapped GPIO controllers" depends on PPC - select GENERIC_GPIO select ARCH_REQUIRE_GPIOLIB help Say Y here to support simple, memory-mapped GPIO controllers. @@ -368,7 +350,6 @@ config SIMPLE_GPIO config MCU_MPC8349EMITX bool "MPC8349E-mITX MCU driver" depends on I2C=y && PPC_83xx - select GENERIC_GPIO select ARCH_REQUIRE_GPIOLIB help Say Y here to enable soft power-off functionality on the Freescale diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 72afd2888ca..a41bd023647 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -71,11 +71,15 @@ config PPC_BOOK3S_64 select PPC_FPU select PPC_HAVE_PMU_SUPPORT select SYS_SUPPORTS_HUGETLBFS + select HAVE_ARCH_TRANSPARENT_HUGEPAGE if PPC_64K_PAGES + select ARCH_SUPPORTS_NUMA_BALANCING + select IRQ_WORK config PPC_BOOK3E_64 bool "Embedded processors" select PPC_FPU # Make it a choice ? select PPC_SMP_MUXED_IPI + select PPC_DOORBELL endchoice @@ -91,21 +95,35 @@ choice config GENERIC_CPU bool "Generic" + depends on !CPU_LITTLE_ENDIAN config CELL_CPU bool "Cell Broadband Engine" + depends on PPC_BOOK3S_64 && !CPU_LITTLE_ENDIAN config POWER4_CPU bool "POWER4" + depends on PPC_BOOK3S_64 && !CPU_LITTLE_ENDIAN config POWER5_CPU bool "POWER5" + depends on PPC_BOOK3S_64 && !CPU_LITTLE_ENDIAN config POWER6_CPU bool "POWER6" + depends on PPC_BOOK3S_64 && !CPU_LITTLE_ENDIAN config POWER7_CPU bool "POWER7" + depends on PPC_BOOK3S_64 + +config E5500_CPU + bool "Freescale e5500" + depends on E500 + +config E6500_CPU + bool "Freescale e6500" + depends on E500 endchoice @@ -123,18 +141,13 @@ config 6xx select PPC_HAVE_PMU_SUPPORT config POWER3 - bool depends on PPC64 && PPC_BOOK3S - default y if !POWER4_ONLY + def_bool y config POWER4 depends on PPC64 && PPC_BOOK3S def_bool y -config PPC_A2 - bool - depends on PPC_BOOK3E_64 - config TUNE_CELL bool "Optimize for Cell Broadband Engine" depends on PPC64 && PPC_BOOK3S @@ -144,8 +157,7 @@ config TUNE_CELL but somewhat slower on other machines. This option only changes the scheduling of instructions, not the selection of instructions itself, so the resulting kernel will keep running on all other - machines. When building a kernel that is supposed to run only - on Cell, you should also select the POWER4_ONLY option. + machines. # this is temp to handle compat with arch=ppc config 8xx @@ -159,6 +171,7 @@ config E500 config PPC_E500MC bool "e500mc Support" select PPC_FPU + select COMMON_CLK depends on E500 help This must be enabled for running on e500mc (and derivatives @@ -208,6 +221,7 @@ config PPC_FSL_BOOK3E select FSL_EMB_PERFMON select PPC_SMP_MUXED_IPI select SYS_SUPPORTS_HUGETLBFS if PHYS_64BIT || PPC64 + select PPC_DOORBELL default y if FSL_BOOKE config PTE_64BIT @@ -230,7 +244,7 @@ config PHYS_64BIT config ALTIVEC bool "AltiVec Support" - depends on 6xx || POWER4 + depends on 6xx || POWER4 || (PPC_E500MC && PPC64) ---help--- This option enables kernel support for the Altivec extensions to the PowerPC processor. The kernel currently supports saving and restoring @@ -262,7 +276,7 @@ config VSX config PPC_ICSWX bool "Support for PowerPC icswx coprocessor instruction" - depends on POWER4 || PPC_A2 + depends on POWER4 default n ---help--- @@ -382,4 +396,38 @@ config NOT_COHERENT_CACHE config CHECK_CACHE_COHERENCY bool +config PPC_DOORBELL + bool + default n + endmenu + +choice + prompt "Endianness selection" + default CPU_BIG_ENDIAN + help + This option selects whether a big endian or little endian kernel will + be built. + +config CPU_BIG_ENDIAN + bool "Build big endian kernel" + help + Build a big endian kernel. + + If unsure, select this option. + +config CPU_LITTLE_ENDIAN + bool "Build little endian kernel" + select PPC64_BOOT_WRAPPER + help + Build a little endian kernel. + + Note that if cross compiling a little endian kernel, + CROSS_COMPILE must point to a toolchain capable of targeting + little endian powerpc. + +endchoice + +config PPC64_BOOT_WRAPPER + def_bool n + depends on CPU_LITTLE_ENDIAN diff --git a/arch/powerpc/platforms/Makefile b/arch/powerpc/platforms/Makefile index 879b4a44849..469ef170d21 100644 --- a/arch/powerpc/platforms/Makefile +++ b/arch/powerpc/platforms/Makefile @@ -22,4 +22,3 @@ obj-$(CONFIG_PPC_CELL) += cell/ obj-$(CONFIG_PPC_PS3) += ps3/ obj-$(CONFIG_EMBEDDED6xx) += embedded6xx/ obj-$(CONFIG_AMIGAONE) += amigaone/ -obj-$(CONFIG_PPC_WSP) += wsp/ diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig index 2e7ff0c5cf4..9978f594cac 100644 --- a/arch/powerpc/platforms/cell/Kconfig +++ b/arch/powerpc/platforms/cell/Kconfig @@ -113,34 +113,10 @@ config CBE_THERM default m depends on CBE_RAS && SPU_BASE -config CBE_CPUFREQ - tristate "CBE frequency scaling" - depends on CBE_RAS && CPU_FREQ - default m - help - This adds the cpufreq driver for Cell BE processors. - For details, take a look at <file:Documentation/cpu-freq/>. - If you don't have such processor, say N - -config CBE_CPUFREQ_PMI_ENABLE - bool "CBE frequency scaling using PMI interface" - depends on CBE_CPUFREQ && EXPERIMENTAL - default n - help - Select this, if you want to use the PMI interface - to switch frequencies. Using PMI, the - processor will not only be able to run at lower speed, - but also at lower core voltage. - -config CBE_CPUFREQ_PMI - tristate - depends on CBE_CPUFREQ_PMI_ENABLE - default CBE_CPUFREQ - config PPC_PMI tristate default y - depends on CBE_CPUFREQ_PMI || PPC_IBM_CELL_POWERBUTTON + depends on CPU_FREQ_CBE_PMI || PPC_IBM_CELL_POWERBUTTON help PMI (Platform Management Interrupt) is a way to communicate with the BMC (Baseboard Management Controller). diff --git a/arch/powerpc/platforms/cell/Makefile b/arch/powerpc/platforms/cell/Makefile index a4a89350bcf..fe053e7c73e 100644 --- a/arch/powerpc/platforms/cell/Makefile +++ b/arch/powerpc/platforms/cell/Makefile @@ -5,9 +5,6 @@ obj-$(CONFIG_PPC_CELL_NATIVE) += iommu.o setup.o spider-pic.o \ obj-$(CONFIG_CBE_RAS) += ras.o obj-$(CONFIG_CBE_THERM) += cbe_thermal.o -obj-$(CONFIG_CBE_CPUFREQ_PMI) += cbe_cpufreq_pmi.o -obj-$(CONFIG_CBE_CPUFREQ) += cbe-cpufreq.o -cbe-cpufreq-y += cbe_cpufreq_pervasive.o cbe_cpufreq.o obj-$(CONFIG_CBE_CPUFREQ_SPU_GOVERNOR) += cpufreq_spudemand.o obj-$(CONFIG_PPC_IBM_CELL_POWERBUTTON) += cbe_powerbutton.o diff --git a/arch/powerpc/platforms/cell/beat_htab.c b/arch/powerpc/platforms/cell/beat_htab.c index 0f6f83988b3..d4d245c0d78 100644 --- a/arch/powerpc/platforms/cell/beat_htab.c +++ b/arch/powerpc/platforms/cell/beat_htab.c @@ -90,7 +90,7 @@ static inline unsigned int beat_read_mask(unsigned hpte_group) 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 ssize) + int psize, int apsize, int ssize) { unsigned long lpar_rc; u64 hpte_v, hpte_r, slot; @@ -103,15 +103,15 @@ static long beat_lpar_hpte_insert(unsigned long hpte_group, "rflags=%lx, vflags=%lx, psize=%d)\n", hpte_group, va, pa, rflags, vflags, psize); - hpte_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M) | + hpte_v = hpte_encode_v(vpn, psize, apsize, MMU_SEGSIZE_256M) | vflags | HPTE_V_VALID; - hpte_r = hpte_encode_r(pa, psize) | rflags; + 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 &= ~_PAGE_COHERENT; + hpte_r &= ~HPTE_R_M; raw_spin_lock(&beat_htab_lock); lpar_rc = beat_read_mask(hpte_group); @@ -185,13 +185,14 @@ static void beat_lpar_hptab_clear(void) static long beat_lpar_hpte_updatepp(unsigned long slot, unsigned long newpp, unsigned long vpn, - int psize, int ssize, int local) + int psize, int apsize, + int ssize, int local) { unsigned long lpar_rc; u64 dummy0, dummy1; unsigned long want_v; - want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M); + want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M); DBG_LOW(" update: " "avpnv=%016lx, slot=%016lx, psize: %d, newpp %016lx ... ", @@ -228,7 +229,7 @@ static long beat_lpar_hpte_find(unsigned long vpn, int psize) unsigned long want_v, hpte_v; hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, MMU_SEGSIZE_256M); - want_v = hpte_encode_v(vpn, psize, 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; @@ -274,7 +275,8 @@ static void beat_lpar_hpte_updateboltedpp(unsigned long newpp, } static void beat_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn, - int psize, int ssize, int local) + int psize, int apsize, + int ssize, int local) { unsigned long want_v; unsigned long lpar_rc; @@ -283,7 +285,7 @@ static void beat_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn, DBG_LOW(" inval : slot=%lx, va=%016lx, psize: %d, local: %d\n", slot, va, psize, local); - want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M); + want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M); raw_spin_lock_irqsave(&beat_htab_lock, flags); dummy1 = beat_lpar_hpte_getword0(slot); @@ -314,7 +316,7 @@ void __init hpte_init_beat(void) 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 ssize) + int psize, int apsize, int ssize) { unsigned long lpar_rc; u64 hpte_v, hpte_r, slot; @@ -327,15 +329,15 @@ static long beat_lpar_hpte_insert_v3(unsigned long hpte_group, "rflags=%lx, vflags=%lx, psize=%d)\n", hpte_group, vpn, pa, rflags, vflags, psize); - hpte_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M) | + hpte_v = hpte_encode_v(vpn, psize, apsize, MMU_SEGSIZE_256M) | vflags | HPTE_V_VALID; - hpte_r = hpte_encode_r(pa, psize) | rflags; + 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 &= ~_PAGE_COHERENT; + hpte_r &= ~HPTE_R_M; /* insert into not-volted entry */ lpar_rc = beat_insert_htab_entry3(0, hpte_group, hpte_v, hpte_r, @@ -364,16 +366,17 @@ static long beat_lpar_hpte_insert_v3(unsigned long hpte_group, * 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 ssize, int local) + unsigned long newpp, + unsigned long vpn, + int psize, int apsize, + int ssize, int local) { unsigned long lpar_rc; unsigned long want_v; unsigned long pss; - want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M); - pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc; + 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 ... ", @@ -394,7 +397,8 @@ static long beat_lpar_hpte_updatepp_v3(unsigned long slot, } static void beat_lpar_hpte_invalidate_v3(unsigned long slot, unsigned long vpn, - int psize, int ssize, int local) + int psize, int apsize, + int ssize, int local) { unsigned long want_v; unsigned long lpar_rc; @@ -402,8 +406,8 @@ static void beat_lpar_hpte_invalidate_v3(unsigned long slot, unsigned long vpn, DBG_LOW(" inval : slot=%lx, vpn=%016lx, psize: %d, local: %d\n", slot, vpn, psize, local); - want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M); - pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc; + 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); diff --git a/arch/powerpc/platforms/cell/beat_interrupt.c b/arch/powerpc/platforms/cell/beat_interrupt.c index 8c6dc42ecf6..9e5dfbcc00a 100644 --- a/arch/powerpc/platforms/cell/beat_interrupt.c +++ b/arch/powerpc/platforms/cell/beat_interrupt.c @@ -239,7 +239,7 @@ void __init beatic_init_IRQ(void) ppc_md.get_irq = beatic_get_irq; /* Allocate an irq host */ - beatic_host = irq_domain_add_nomap(NULL, 0, &beatic_pic_host_ops, NULL); + beatic_host = irq_domain_add_nomap(NULL, ~0, &beatic_pic_host_ops, NULL); BUG_ON(beatic_host == NULL); irq_set_default_host(beatic_host); } diff --git a/arch/powerpc/platforms/cell/cbe_cpufreq.c b/arch/powerpc/platforms/cell/cbe_cpufreq.c deleted file mode 100644 index d4c39e32f14..00000000000 --- a/arch/powerpc/platforms/cell/cbe_cpufreq.c +++ /dev/null @@ -1,209 +0,0 @@ -/* - * cpufreq driver for the cell processor - * - * (C) Copyright IBM Deutschland Entwicklung GmbH 2005-2007 - * - * Author: Christian Krafft <krafft@de.ibm.com> - * - * 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. - * - * 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., 675 Mass Ave, Cambridge, MA 02139, USA. - */ - -#include <linux/cpufreq.h> -#include <linux/module.h> -#include <linux/of_platform.h> - -#include <asm/machdep.h> -#include <asm/prom.h> -#include <asm/cell-regs.h> -#include "cbe_cpufreq.h" - -static DEFINE_MUTEX(cbe_switch_mutex); - - -/* the CBE supports an 8 step frequency scaling */ -static struct cpufreq_frequency_table cbe_freqs[] = { - {1, 0}, - {2, 0}, - {3, 0}, - {4, 0}, - {5, 0}, - {6, 0}, - {8, 0}, - {10, 0}, - {0, CPUFREQ_TABLE_END}, -}; - -/* - * hardware specific functions - */ - -static int set_pmode(unsigned int cpu, unsigned int slow_mode) -{ - int rc; - - if (cbe_cpufreq_has_pmi) - rc = cbe_cpufreq_set_pmode_pmi(cpu, slow_mode); - else - rc = cbe_cpufreq_set_pmode(cpu, slow_mode); - - pr_debug("register contains slow mode %d\n", cbe_cpufreq_get_pmode(cpu)); - - return rc; -} - -/* - * cpufreq functions - */ - -static int cbe_cpufreq_cpu_init(struct cpufreq_policy *policy) -{ - const u32 *max_freqp; - u32 max_freq; - int i, cur_pmode; - struct device_node *cpu; - - cpu = of_get_cpu_node(policy->cpu, NULL); - - if (!cpu) - return -ENODEV; - - pr_debug("init cpufreq on CPU %d\n", policy->cpu); - - /* - * Let's check we can actually get to the CELL regs - */ - if (!cbe_get_cpu_pmd_regs(policy->cpu) || - !cbe_get_cpu_mic_tm_regs(policy->cpu)) { - pr_info("invalid CBE regs pointers for cpufreq\n"); - return -EINVAL; - } - - max_freqp = of_get_property(cpu, "clock-frequency", NULL); - - of_node_put(cpu); - - if (!max_freqp) - return -EINVAL; - - /* we need the freq in kHz */ - max_freq = *max_freqp / 1000; - - pr_debug("max clock-frequency is at %u kHz\n", max_freq); - pr_debug("initializing frequency table\n"); - - /* initialize frequency table */ - for (i=0; cbe_freqs[i].frequency!=CPUFREQ_TABLE_END; i++) { - cbe_freqs[i].frequency = max_freq / cbe_freqs[i].index; - pr_debug("%d: %d\n", i, cbe_freqs[i].frequency); - } - - /* if DEBUG is enabled set_pmode() measures the latency - * of a transition */ - policy->cpuinfo.transition_latency = 25000; - - cur_pmode = cbe_cpufreq_get_pmode(policy->cpu); - pr_debug("current pmode is at %d\n",cur_pmode); - - policy->cur = cbe_freqs[cur_pmode].frequency; - -#ifdef CONFIG_SMP - cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu)); -#endif - - cpufreq_frequency_table_get_attr(cbe_freqs, policy->cpu); - - /* this ensures that policy->cpuinfo_min - * and policy->cpuinfo_max are set correctly */ - return cpufreq_frequency_table_cpuinfo(policy, cbe_freqs); -} - -static int cbe_cpufreq_cpu_exit(struct cpufreq_policy *policy) -{ - cpufreq_frequency_table_put_attr(policy->cpu); - return 0; -} - -static int cbe_cpufreq_verify(struct cpufreq_policy *policy) -{ - return cpufreq_frequency_table_verify(policy, cbe_freqs); -} - -static int cbe_cpufreq_target(struct cpufreq_policy *policy, - unsigned int target_freq, - unsigned int relation) -{ - int rc; - struct cpufreq_freqs freqs; - unsigned int cbe_pmode_new; - - cpufreq_frequency_table_target(policy, - cbe_freqs, - target_freq, - relation, - &cbe_pmode_new); - - freqs.old = policy->cur; - freqs.new = cbe_freqs[cbe_pmode_new].frequency; - freqs.cpu = policy->cpu; - - mutex_lock(&cbe_switch_mutex); - cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); - - pr_debug("setting frequency for cpu %d to %d kHz, " \ - "1/%d of max frequency\n", - policy->cpu, - cbe_freqs[cbe_pmode_new].frequency, - cbe_freqs[cbe_pmode_new].index); - - rc = set_pmode(policy->cpu, cbe_pmode_new); - - cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); - mutex_unlock(&cbe_switch_mutex); - - return rc; -} - -static struct cpufreq_driver cbe_cpufreq_driver = { - .verify = cbe_cpufreq_verify, - .target = cbe_cpufreq_target, - .init = cbe_cpufreq_cpu_init, - .exit = cbe_cpufreq_cpu_exit, - .name = "cbe-cpufreq", - .owner = THIS_MODULE, - .flags = CPUFREQ_CONST_LOOPS, -}; - -/* - * module init and destoy - */ - -static int __init cbe_cpufreq_init(void) -{ - if (!machine_is(cell)) - return -ENODEV; - - return cpufreq_register_driver(&cbe_cpufreq_driver); -} - -static void __exit cbe_cpufreq_exit(void) -{ - cpufreq_unregister_driver(&cbe_cpufreq_driver); -} - -module_init(cbe_cpufreq_init); -module_exit(cbe_cpufreq_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Christian Krafft <krafft@de.ibm.com>"); diff --git a/arch/powerpc/platforms/cell/cbe_cpufreq.h b/arch/powerpc/platforms/cell/cbe_cpufreq.h deleted file mode 100644 index c1d86bfa92f..00000000000 --- a/arch/powerpc/platforms/cell/cbe_cpufreq.h +++ /dev/null @@ -1,24 +0,0 @@ -/* - * cbe_cpufreq.h - * - * This file contains the definitions used by the cbe_cpufreq driver. - * - * (C) Copyright IBM Deutschland Entwicklung GmbH 2005-2007 - * - * Author: Christian Krafft <krafft@de.ibm.com> - * - */ - -#include <linux/cpufreq.h> -#include <linux/types.h> - -int cbe_cpufreq_set_pmode(int cpu, unsigned int pmode); -int cbe_cpufreq_get_pmode(int cpu); - -int cbe_cpufreq_set_pmode_pmi(int cpu, unsigned int pmode); - -#if defined(CONFIG_CBE_CPUFREQ_PMI) || defined(CONFIG_CBE_CPUFREQ_PMI_MODULE) -extern bool cbe_cpufreq_has_pmi; -#else -#define cbe_cpufreq_has_pmi (0) -#endif diff --git a/arch/powerpc/platforms/cell/cbe_cpufreq_pervasive.c b/arch/powerpc/platforms/cell/cbe_cpufreq_pervasive.c deleted file mode 100644 index 20472e487b6..00000000000 --- a/arch/powerpc/platforms/cell/cbe_cpufreq_pervasive.c +++ /dev/null @@ -1,115 +0,0 @@ -/* - * pervasive backend for the cbe_cpufreq driver - * - * This driver makes use of the pervasive unit to - * engage the desired frequency. - * - * (C) Copyright IBM Deutschland Entwicklung GmbH 2005-2007 - * - * Author: Christian Krafft <krafft@de.ibm.com> - * - * 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. - * - * 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., 675 Mass Ave, Cambridge, MA 02139, USA. - */ - -#include <linux/io.h> -#include <linux/kernel.h> -#include <linux/time.h> -#include <asm/machdep.h> -#include <asm/hw_irq.h> -#include <asm/cell-regs.h> - -#include "cbe_cpufreq.h" - -/* to write to MIC register */ -static u64 MIC_Slow_Fast_Timer_table[] = { - [0 ... 7] = 0x007fc00000000000ull, -}; - -/* more values for the MIC */ -static u64 MIC_Slow_Next_Timer_table[] = { - 0x0000240000000000ull, - 0x0000268000000000ull, - 0x000029C000000000ull, - 0x00002D0000000000ull, - 0x0000300000000000ull, - 0x0000334000000000ull, - 0x000039C000000000ull, - 0x00003FC000000000ull, -}; - - -int cbe_cpufreq_set_pmode(int cpu, unsigned int pmode) -{ - struct cbe_pmd_regs __iomem *pmd_regs; - struct cbe_mic_tm_regs __iomem *mic_tm_regs; - unsigned long flags; - u64 value; -#ifdef DEBUG - long time; -#endif - - local_irq_save(flags); - - mic_tm_regs = cbe_get_cpu_mic_tm_regs(cpu); - pmd_regs = cbe_get_cpu_pmd_regs(cpu); - -#ifdef DEBUG - time = jiffies; -#endif - - out_be64(&mic_tm_regs->slow_fast_timer_0, MIC_Slow_Fast_Timer_table[pmode]); - out_be64(&mic_tm_regs->slow_fast_timer_1, MIC_Slow_Fast_Timer_table[pmode]); - - out_be64(&mic_tm_regs->slow_next_timer_0, MIC_Slow_Next_Timer_table[pmode]); - out_be64(&mic_tm_regs->slow_next_timer_1, MIC_Slow_Next_Timer_table[pmode]); - - value = in_be64(&pmd_regs->pmcr); - /* set bits to zero */ - value &= 0xFFFFFFFFFFFFFFF8ull; - /* set bits to next pmode */ - value |= pmode; - - out_be64(&pmd_regs->pmcr, value); - -#ifdef DEBUG - /* wait until new pmode appears in status register */ - value = in_be64(&pmd_regs->pmsr) & 0x07; - while (value != pmode) { - cpu_relax(); - value = in_be64(&pmd_regs->pmsr) & 0x07; - } - - time = jiffies - time; - time = jiffies_to_msecs(time); - pr_debug("had to wait %lu ms for a transition using " \ - "pervasive unit\n", time); -#endif - local_irq_restore(flags); - - return 0; -} - - -int cbe_cpufreq_get_pmode(int cpu) -{ - int ret; - struct cbe_pmd_regs __iomem *pmd_regs; - - pmd_regs = cbe_get_cpu_pmd_regs(cpu); - ret = in_be64(&pmd_regs->pmsr) & 0x07; - - return ret; -} - diff --git a/arch/powerpc/platforms/cell/cbe_cpufreq_pmi.c b/arch/powerpc/platforms/cell/cbe_cpufreq_pmi.c deleted file mode 100644 index 60a07a4f932..00000000000 --- a/arch/powerpc/platforms/cell/cbe_cpufreq_pmi.c +++ /dev/null @@ -1,156 +0,0 @@ -/* - * pmi backend for the cbe_cpufreq driver - * - * (C) Copyright IBM Deutschland Entwicklung GmbH 2005-2007 - * - * Author: Christian Krafft <krafft@de.ibm.com> - * - * 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. - * - * 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., 675 Mass Ave, Cambridge, MA 02139, USA. - */ - -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/timer.h> -#include <linux/module.h> -#include <linux/of_platform.h> - -#include <asm/processor.h> -#include <asm/prom.h> -#include <asm/pmi.h> -#include <asm/cell-regs.h> - -#ifdef DEBUG -#include <asm/time.h> -#endif - -#include "cbe_cpufreq.h" - -static u8 pmi_slow_mode_limit[MAX_CBE]; - -bool cbe_cpufreq_has_pmi = false; -EXPORT_SYMBOL_GPL(cbe_cpufreq_has_pmi); - -/* - * hardware specific functions - */ - -int cbe_cpufreq_set_pmode_pmi(int cpu, unsigned int pmode) -{ - int ret; - pmi_message_t pmi_msg; -#ifdef DEBUG - long time; -#endif - pmi_msg.type = PMI_TYPE_FREQ_CHANGE; - pmi_msg.data1 = cbe_cpu_to_node(cpu); - pmi_msg.data2 = pmode; - -#ifdef DEBUG - time = jiffies; -#endif - pmi_send_message(pmi_msg); - -#ifdef DEBUG - time = jiffies - time; - time = jiffies_to_msecs(time); - pr_debug("had to wait %lu ms for a transition using " \ - "PMI\n", time); -#endif - ret = pmi_msg.data2; - pr_debug("PMI returned slow mode %d\n", ret); - - return ret; -} -EXPORT_SYMBOL_GPL(cbe_cpufreq_set_pmode_pmi); - - -static void cbe_cpufreq_handle_pmi(pmi_message_t pmi_msg) -{ - u8 node, slow_mode; - - BUG_ON(pmi_msg.type != PMI_TYPE_FREQ_CHANGE); - - node = pmi_msg.data1; - slow_mode = pmi_msg.data2; - - pmi_slow_mode_limit[node] = slow_mode; - - pr_debug("cbe_handle_pmi: node: %d max_freq: %d\n", node, slow_mode); -} - -static int pmi_notifier(struct notifier_block *nb, - unsigned long event, void *data) -{ - struct cpufreq_policy *policy = data; - struct cpufreq_frequency_table *cbe_freqs; - u8 node; - - /* Should this really be called for CPUFREQ_ADJUST, CPUFREQ_INCOMPATIBLE - * and CPUFREQ_NOTIFY policy events?) - */ - if (event == CPUFREQ_START) - return 0; - - cbe_freqs = cpufreq_frequency_get_table(policy->cpu); - node = cbe_cpu_to_node(policy->cpu); - - pr_debug("got notified, event=%lu, node=%u\n", event, node); - - if (pmi_slow_mode_limit[node] != 0) { - pr_debug("limiting node %d to slow mode %d\n", - node, pmi_slow_mode_limit[node]); - - cpufreq_verify_within_limits(policy, 0, - - cbe_freqs[pmi_slow_mode_limit[node]].frequency); - } - - return 0; -} - -static struct notifier_block pmi_notifier_block = { - .notifier_call = pmi_notifier, -}; - -static struct pmi_handler cbe_pmi_handler = { - .type = PMI_TYPE_FREQ_CHANGE, - .handle_pmi_message = cbe_cpufreq_handle_pmi, -}; - - - -static int __init cbe_cpufreq_pmi_init(void) -{ - cbe_cpufreq_has_pmi = pmi_register_handler(&cbe_pmi_handler) == 0; - - if (!cbe_cpufreq_has_pmi) - return -ENODEV; - - cpufreq_register_notifier(&pmi_notifier_block, CPUFREQ_POLICY_NOTIFIER); - - return 0; -} - -static void __exit cbe_cpufreq_pmi_exit(void) -{ - cpufreq_unregister_notifier(&pmi_notifier_block, CPUFREQ_POLICY_NOTIFIER); - pmi_unregister_handler(&cbe_pmi_handler); -} - -module_init(cbe_cpufreq_pmi_init); -module_exit(cbe_cpufreq_pmi_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Christian Krafft <krafft@de.ibm.com>"); diff --git a/arch/powerpc/platforms/cell/cbe_thermal.c b/arch/powerpc/platforms/cell/cbe_thermal.c index 94560db788b..2c15ff09448 100644 --- a/arch/powerpc/platforms/cell/cbe_thermal.c +++ b/arch/powerpc/platforms/cell/cbe_thermal.c @@ -125,7 +125,7 @@ static ssize_t show_throttle(struct cbe_pmd_regs __iomem *pmd_regs, char *buf, i static ssize_t store_throttle(struct cbe_pmd_regs __iomem *pmd_regs, const char *buf, size_t size, int pos) { u64 reg_value; - int temp; + unsigned int temp; u64 new_value; int ret; diff --git a/arch/powerpc/platforms/cell/celleb_scc_pciex.c b/arch/powerpc/platforms/cell/celleb_scc_pciex.c index 14be2bd358b..4278acfa2ed 100644 --- a/arch/powerpc/platforms/cell/celleb_scc_pciex.c +++ b/arch/powerpc/platforms/cell/celleb_scc_pciex.c @@ -486,7 +486,6 @@ static __init int celleb_setup_pciex(struct device_node *node, struct pci_controller *phb) { struct resource r; - struct of_irq oirq; int virq; /* SMMIO registers; used inside this file */ @@ -507,12 +506,11 @@ static __init int celleb_setup_pciex(struct device_node *node, phb->ops = &scc_pciex_pci_ops; /* internal interrupt handler */ - if (of_irq_map_one(node, 1, &oirq)) { + virq = irq_of_parse_and_map(node, 1); + if (!virq) { pr_err("PCIEXC:Failed to map irq\n"); goto error; } - virq = irq_create_of_mapping(oirq.controller, oirq.specifier, - oirq.size); if (request_irq(virq, pciex_handle_internal_irq, 0, "pciex", (void *)phb)) { pr_err("PCIEXC:Failed to request irq\n"); diff --git a/arch/powerpc/platforms/cell/celleb_scc_sio.c b/arch/powerpc/platforms/cell/celleb_scc_sio.c index 3a16c5b3c46..c8eb5719382 100644 --- a/arch/powerpc/platforms/cell/celleb_scc_sio.c +++ b/arch/powerpc/platforms/cell/celleb_scc_sio.c @@ -42,19 +42,18 @@ static struct { static int __init txx9_serial_init(void) { extern int early_serial_txx9_setup(struct uart_port *port); - struct device_node *node = NULL; + struct device_node *node; int i; struct uart_port req; - struct of_irq irq; + struct of_phandle_args irq; struct resource res; - while ((node = of_find_compatible_node(node, - "serial", "toshiba,sio-scc")) != NULL) { + 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_map_one(node, i, &irq)) + if (of_irq_parse_one(node, i, &irq)) continue; if (of_address_to_resource(node, txx9_scc_tab[i].index, &res)) @@ -67,8 +66,7 @@ static int __init txx9_serial_init(void) #ifdef CONFIG_SERIAL_TXX9_CONSOLE req.membase = ioremap(req.mapbase, 0x24); #endif - req.irq = irq_create_of_mapping(irq.controller, - irq.specifier, irq.size); + req.irq = irq_create_of_mapping(&irq); req.flags |= UPF_IOREMAP | UPF_BUGGY_UART /*HAVE_CTS_LINE*/; req.uartclk = 83300000; diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c index 2d42f3bb66d..8a106b4172e 100644 --- a/arch/powerpc/platforms/cell/interrupt.c +++ b/arch/powerpc/platforms/cell/interrupt.c @@ -215,7 +215,7 @@ void iic_request_IPIs(void) { iic_request_ipi(PPC_MSG_CALL_FUNCTION); iic_request_ipi(PPC_MSG_RESCHEDULE); - iic_request_ipi(PPC_MSG_CALL_FUNC_SINGLE); + iic_request_ipi(PPC_MSG_TICK_BROADCAST); iic_request_ipi(PPC_MSG_DEBUGGER_BREAK); } diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index e56bb651da1..2b90ff8a93b 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -197,7 +197,7 @@ 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 += IOMMU_PAGE_SIZE) + for (i = 0; i < npages; i++, uaddr += tbl->it_page_shift) io_pte[i] = base_pte | (__pa(uaddr) & CBE_IOPTE_RPN_Mask); mb(); @@ -430,7 +430,7 @@ static void cell_iommu_setup_hardware(struct cbe_iommu *iommu, { cell_iommu_setup_stab(iommu, base, size, 0, 0); iommu->ptab = cell_iommu_alloc_ptab(iommu, base, size, 0, 0, - IOMMU_PAGE_SHIFT); + IOMMU_PAGE_SHIFT_4K); cell_iommu_enable_hardware(iommu); } @@ -487,8 +487,10 @@ cell_iommu_setup_window(struct cbe_iommu *iommu, struct device_node *np, window->table.it_blocksize = 16; window->table.it_base = (unsigned long)iommu->ptab; window->table.it_index = iommu->nid; - window->table.it_offset = (offset >> IOMMU_PAGE_SHIFT) + pte_offset; - window->table.it_size = size >> IOMMU_PAGE_SHIFT; + window->table.it_page_shift = IOMMU_PAGE_SHIFT_4K; + window->table.it_offset = + (offset >> window->table.it_page_shift) + pte_offset; + window->table.it_size = size >> window->table.it_page_shift; iommu_init_table(&window->table, iommu->nid); @@ -550,7 +552,7 @@ static struct iommu_table *cell_get_iommu_table(struct device *dev) */ iommu = cell_iommu_for_node(dev_to_node(dev)); if (iommu == NULL || list_empty(&iommu->windows)) { - printk(KERN_ERR "iommu: missing iommu for %s (node %d)\n", + dev_err(dev, "iommu: missing iommu for %s (node %d)\n", of_node_full_name(dev->of_node), dev_to_node(dev)); return NULL; } @@ -697,7 +699,7 @@ static int __init cell_iommu_get_window(struct device_node *np, unsigned long *base, unsigned long *size) { - const void *dma_window; + const __be32 *dma_window; unsigned long index; /* Use ibm,dma-window if available, else, hard code ! */ @@ -773,7 +775,7 @@ static void __init cell_iommu_init_one(struct device_node *np, /* Setup the iommu_table */ cell_iommu_setup_window(iommu, np, base, size, - offset >> IOMMU_PAGE_SHIFT); + offset >> IOMMU_PAGE_SHIFT_4K); } static void __init cell_disable_iommus(void) @@ -1122,7 +1124,7 @@ static int __init cell_iommu_fixed_mapping_init(void) cell_iommu_setup_stab(iommu, dbase, dsize, fbase, fsize); iommu->ptab = cell_iommu_alloc_ptab(iommu, dbase, dsize, 0, 0, - IOMMU_PAGE_SHIFT); + IOMMU_PAGE_SHIFT_4K); cell_iommu_setup_fixed_ptab(iommu, np, dbase, dsize, fbase, fsize); cell_iommu_enable_hardware(iommu); diff --git a/arch/powerpc/platforms/cell/pmu.c b/arch/powerpc/platforms/cell/pmu.c index 59c1a169410..348a27b1251 100644 --- a/arch/powerpc/platforms/cell/pmu.c +++ b/arch/powerpc/platforms/cell/pmu.c @@ -382,7 +382,7 @@ static int __init cbe_init_pm_irq(void) unsigned int irq; int rc, node; - for_each_node(node) { + for_each_online_node(node) { irq = irq_create_mapping(NULL, IIC_IRQ_IOEX_PMI | (node << IIC_IRQ_NODE_SHIFT)); if (irq == NO_IRQ) { diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c index 5ec1e47a0d7..e865d748179 100644 --- a/arch/powerpc/platforms/cell/ras.c +++ b/arch/powerpc/platforms/cell/ras.c @@ -123,7 +123,8 @@ static int __init cbe_ptcal_enable_on_node(int nid, int order) area->nid = nid; area->order = order; - area->pages = alloc_pages_exact_node(area->nid, GFP_KERNEL|GFP_THISNODE, + area->pages = alloc_pages_exact_node(area->nid, + GFP_KERNEL|__GFP_THISNODE, area->order); if (!area->pages) { diff --git a/arch/powerpc/platforms/cell/smp.c b/arch/powerpc/platforms/cell/smp.c index d35dbbc8ec7..c8017a7bcab 100644 --- a/arch/powerpc/platforms/cell/smp.c +++ b/arch/powerpc/platforms/cell/smp.c @@ -40,6 +40,7 @@ #include <asm/firmware.h> #include <asm/rtas.h> #include <asm/cputhreads.h> +#include <asm/code-patching.h> #include "interrupt.h" #include <asm/udbg.h> @@ -70,8 +71,8 @@ static cpumask_t of_spin_map; static inline int smp_startup_cpu(unsigned int lcpu) { int status; - unsigned long start_here = __pa((u32)*((unsigned long *) - generic_secondary_smp_init)); + unsigned long start_here = + __pa(ppc_function_entry(generic_secondary_smp_init)); unsigned int pcpu; int start_cpu; @@ -136,25 +137,12 @@ static int smp_cell_kick_cpu(int nr) return 0; } -static int smp_cell_cpu_bootable(unsigned int nr) -{ - /* Special case - we inhibit secondary thread startup - * during boot if the user requests it. Odd-numbered - * cpus are assumed to be secondary threads. - */ - if (system_state < SYSTEM_RUNNING && - cpu_has_feature(CPU_FTR_SMT) && - !smt_enabled_at_boot && cpu_thread_in_core(nr) != 0) - return 0; - - return 1; -} static struct smp_ops_t bpa_iic_smp_ops = { .message_pass = iic_message_pass, .probe = smp_iic_probe, .kick_cpu = smp_cell_kick_cpu, .setup_cpu = smp_cell_setup_cpu, - .cpu_bootable = smp_cell_cpu_bootable, + .cpu_bootable = smp_generic_cpu_bootable, }; /* This is called very early */ diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c index 8e299447127..1f72f4ab635 100644 --- a/arch/powerpc/platforms/cell/spider-pic.c +++ b/arch/powerpc/platforms/cell/spider-pic.c @@ -235,12 +235,9 @@ static unsigned int __init spider_find_cascade_and_node(struct spider_pic *pic) /* First, we check whether we have a real "interrupts" in the device * tree in case the device-tree is ever fixed */ - struct of_irq oirq; - if (of_irq_map_one(pic->host->of_node, 0, &oirq) == 0) { - virq = irq_create_of_mapping(oirq.controller, oirq.specifier, - oirq.size); + virq = irq_of_parse_and_map(pic->host->of_node, 0); + if (virq) return virq; - } /* Now do the horrible hacks */ tmp = of_get_property(pic->host->of_node, "#interrupt-cells", NULL); diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c index 8b1213993b1..f85db3a69b4 100644 --- a/arch/powerpc/platforms/cell/spu_base.c +++ b/arch/powerpc/platforms/cell/spu_base.c @@ -715,7 +715,7 @@ static ssize_t spu_stat_show(struct device *dev, spu->stats.libassist); } -static DEVICE_ATTR(stat, 0644, spu_stat_show, NULL); +static DEVICE_ATTR(stat, 0444, spu_stat_show, NULL); #ifdef CONFIG_KEXEC diff --git a/arch/powerpc/platforms/cell/spu_callbacks.c b/arch/powerpc/platforms/cell/spu_callbacks.c index 75d613313f1..b0ec78e8ad6 100644 --- a/arch/powerpc/platforms/cell/spu_callbacks.c +++ b/arch/powerpc/platforms/cell/spu_callbacks.c @@ -60,13 +60,12 @@ long spu_sys_callback(struct spu_syscall_block *s) syscall = spu_syscall_table[s->nr_ret]; -#ifdef DEBUG - print_symbol(KERN_DEBUG "SPU-syscall %s:", (unsigned long)syscall); - printk("syscall%ld(%lx, %lx, %lx, %lx, %lx, %lx)\n", - s->nr_ret, - s->parm[0], s->parm[1], s->parm[2], - s->parm[3], s->parm[4], s->parm[5]); -#endif + pr_debug("SPU-syscall " + "%pSR:syscall%lld(%llx, %llx, %llx, %llx, %llx, %llx)\n", + syscall, + s->nr_ret, + s->parm[0], s->parm[1], s->parm[2], + s->parm[3], s->parm[4], s->parm[5]); return syscall(s->parm[0], s->parm[1], s->parm[2], s->parm[3], s->parm[4], s->parm[5]); diff --git a/arch/powerpc/platforms/cell/spu_manage.c b/arch/powerpc/platforms/cell/spu_manage.c index 2bb6977c0a5..c3327f3d8cf 100644 --- a/arch/powerpc/platforms/cell/spu_manage.c +++ b/arch/powerpc/platforms/cell/spu_manage.c @@ -177,21 +177,20 @@ out: static int __init spu_map_interrupts(struct spu *spu, struct device_node *np) { - struct of_irq oirq; + struct of_phandle_args oirq; int ret; int i; for (i=0; i < 3; i++) { - ret = of_irq_map_one(np, i, &oirq); + ret = of_irq_parse_one(np, i, &oirq); if (ret) { pr_debug("spu_new: failed to get irq %d\n", i); goto err; } ret = -EINVAL; - pr_debug(" irq %d no 0x%x on %s\n", i, oirq.specifier[0], - oirq.controller->full_name); - spu->irqs[i] = irq_create_of_mapping(oirq.controller, - oirq.specifier, oirq.size); + pr_debug(" irq %d no 0x%x on %s\n", i, oirq.args[0], + oirq.np->full_name); + spu->irqs[i] = irq_create_of_mapping(&oirq); if (spu->irqs[i] == NO_IRQ) { pr_debug("spu_new: failed to map it !\n"); goto err; @@ -200,7 +199,7 @@ static int __init spu_map_interrupts(struct spu *spu, struct device_node *np) return 0; err: - pr_debug("failed to map irq %x for spu %s\n", *oirq.specifier, + pr_debug("failed to map irq %x for spu %s\n", *oirq.args, spu->name); for (; i >= 0; i--) { if (spu->irqs[i] != NO_IRQ) diff --git a/arch/powerpc/platforms/cell/spu_syscalls.c b/arch/powerpc/platforms/cell/spu_syscalls.c index db4e638cf40..5e6e0bad6db 100644 --- a/arch/powerpc/platforms/cell/spu_syscalls.c +++ b/arch/powerpc/platforms/cell/spu_syscalls.c @@ -25,6 +25,7 @@ #include <linux/module.h> #include <linux/syscalls.h> #include <linux/rcupdate.h> +#include <linux/binfmts.h> #include <asm/spu.h> @@ -110,6 +111,7 @@ asmlinkage long sys_spu_run(int fd, __u32 __user *unpc, __u32 __user *ustatus) return ret; } +#ifdef CONFIG_COREDUMP int elf_coredump_extra_notes_size(void) { struct spufs_calls *calls; @@ -126,7 +128,7 @@ int elf_coredump_extra_notes_size(void) return ret; } -int elf_coredump_extra_notes_write(struct file *file, loff_t *foffset) +int elf_coredump_extra_notes_write(struct coredump_params *cprm) { struct spufs_calls *calls; int ret; @@ -135,12 +137,13 @@ int elf_coredump_extra_notes_write(struct file *file, loff_t *foffset) if (!calls) return 0; - ret = calls->coredump_extra_notes_write(file, foffset); + ret = calls->coredump_extra_notes_write(cprm); spufs_calls_put(calls); return ret; } +#endif void notify_spus_active(void) { @@ -169,7 +172,7 @@ EXPORT_SYMBOL_GPL(register_spu_syscalls); void unregister_spu_syscalls(struct spufs_calls *calls) { BUG_ON(spufs_calls->owner != calls->owner); - rcu_assign_pointer(spufs_calls, NULL); + RCU_INIT_POINTER(spufs_calls, NULL); synchronize_rcu(); } EXPORT_SYMBOL_GPL(unregister_spu_syscalls); diff --git a/arch/powerpc/platforms/cell/spufs/Makefile b/arch/powerpc/platforms/cell/spufs/Makefile index b9d5d678aa4..52a7d2596d3 100644 --- a/arch/powerpc/platforms/cell/spufs/Makefile +++ b/arch/powerpc/platforms/cell/spufs/Makefile @@ -1,8 +1,9 @@ obj-$(CONFIG_SPU_FS) += spufs.o -spufs-y += inode.o file.o context.o syscalls.o coredump.o +spufs-y += inode.o file.o context.o syscalls.o spufs-y += sched.o backing_ops.o hw_ops.o run.o gang.o spufs-y += switch.o fault.o lscsa_alloc.o +spufs-$(CONFIG_COREDUMP) += coredump.o # magic for the trace events CFLAGS_sched.o := -I$(src) diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c index 657e3f233a6..be6212ddbf0 100644 --- a/arch/powerpc/platforms/cell/spufs/coredump.c +++ b/arch/powerpc/platforms/cell/spufs/coredump.c @@ -27,6 +27,8 @@ #include <linux/gfp.h> #include <linux/list.h> #include <linux/syscalls.h> +#include <linux/coredump.h> +#include <linux/binfmts.h> #include <asm/uaccess.h> @@ -48,44 +50,6 @@ static ssize_t do_coredump_read(int num, struct spu_context *ctx, void *buffer, return ++ret; /* count trailing NULL */ } -/* - * These are the only things you should do on a core-file: use only these - * functions to write out all the necessary info. - */ -static int spufs_dump_write(struct file *file, const void *addr, int nr, loff_t *foffset) -{ - unsigned long limit = rlimit(RLIMIT_CORE); - ssize_t written; - - if (*foffset + nr > limit) - return -EIO; - - written = file->f_op->write(file, addr, nr, &file->f_pos); - *foffset += written; - - if (written != nr) - return -EIO; - - return 0; -} - -static int spufs_dump_align(struct file *file, char *buf, loff_t new_off, - loff_t *foffset) -{ - int rc, size; - - size = min((loff_t)PAGE_SIZE, new_off - *foffset); - memset(buf, 0, size); - - rc = 0; - while (rc == 0 && new_off > *foffset) { - size = min((loff_t)PAGE_SIZE, new_off - *foffset); - rc = spufs_dump_write(file, buf, size, foffset); - } - - return rc; -} - static int spufs_ctx_note_size(struct spu_context *ctx, int dfd) { int i, sz, total = 0; @@ -111,7 +75,7 @@ static int match_context(const void *v, struct file *file, unsigned fd) struct spu_context *ctx; if (file->f_op != &spufs_context_fops) return 0; - ctx = SPUFS_I(file->f_dentry->d_inode)->i_ctx; + ctx = SPUFS_I(file_inode(file))->i_ctx; if (ctx->flags & SPU_CREATE_NOSCHED) return 0; return fd + 1; @@ -137,7 +101,7 @@ static struct spu_context *coredump_next_context(int *fd) return NULL; *fd = n - 1; file = fcheck(*fd); - return SPUFS_I(file->f_dentry->d_inode)->i_ctx; + return SPUFS_I(file_inode(file))->i_ctx; } int spufs_coredump_extra_notes_size(void) @@ -165,10 +129,10 @@ int spufs_coredump_extra_notes_size(void) } static int spufs_arch_write_note(struct spu_context *ctx, int i, - struct file *file, int dfd, loff_t *foffset) + struct coredump_params *cprm, int dfd) { loff_t pos = 0; - int sz, rc, nread, total = 0; + int sz, rc, total = 0; const int bufsz = PAGE_SIZE; char *name; char fullname[80], *buf; @@ -186,42 +150,39 @@ static int spufs_arch_write_note(struct spu_context *ctx, int i, en.n_descsz = sz; en.n_type = NT_SPU; - rc = spufs_dump_write(file, &en, sizeof(en), foffset); - if (rc) - goto out; + if (!dump_emit(cprm, &en, sizeof(en))) + goto Eio; - rc = spufs_dump_write(file, fullname, en.n_namesz, foffset); - if (rc) - goto out; + if (!dump_emit(cprm, fullname, en.n_namesz)) + goto Eio; - rc = spufs_dump_align(file, buf, roundup(*foffset, 4), foffset); - if (rc) - goto out; + if (!dump_align(cprm, 4)) + goto Eio; do { - nread = do_coredump_read(i, ctx, buf, bufsz, &pos); - if (nread > 0) { - rc = spufs_dump_write(file, buf, nread, foffset); - if (rc) - goto out; - total += nread; + rc = do_coredump_read(i, ctx, buf, bufsz, &pos); + if (rc > 0) { + if (!dump_emit(cprm, buf, rc)) + goto Eio; + total += rc; } - } while (nread == bufsz && total < sz); + } while (rc == bufsz && total < sz); - if (nread < 0) { - rc = nread; + if (rc < 0) goto out; - } - - rc = spufs_dump_align(file, buf, roundup(*foffset - total + sz, 4), - foffset); + if (!dump_skip(cprm, + roundup(cprm->written - total + sz, 4) - cprm->written)) + goto Eio; out: free_page((unsigned long)buf); return rc; +Eio: + free_page((unsigned long)buf); + return -EIO; } -int spufs_coredump_extra_notes_write(struct file *file, loff_t *foffset) +int spufs_coredump_extra_notes_write(struct coredump_params *cprm) { struct spu_context *ctx; int fd, j, rc; @@ -233,7 +194,7 @@ int spufs_coredump_extra_notes_write(struct file *file, loff_t *foffset) return rc; for (j = 0; spufs_coredump_read[j].name != NULL; j++) { - rc = spufs_arch_write_note(ctx, j, file, fd, foffset); + rc = spufs_arch_write_note(ctx, j, cprm, fd); if (rc) { spu_release_saved(ctx); return rc; diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index 0cfece4cf6e..90986923a53 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -149,7 +149,6 @@ static int __fops ## _open(struct inode *inode, struct file *file) \ return spufs_attr_open(inode, file, __get, __set, __fmt); \ } \ static const struct file_operations __fops = { \ - .owner = THIS_MODULE, \ .open = __fops ## _open, \ .release = spufs_attr_release, \ .read = spufs_attr_read, \ @@ -352,7 +351,7 @@ static unsigned long spufs_get_unmapped_area(struct file *file, /* Else, try to obtain a 64K pages slice */ return slice_get_unmapped_area(addr, len, flags, - MMU_PAGE_64K, 1, 0); + MMU_PAGE_64K, 1); } #endif /* CONFIG_SPU_FS_64K_LS */ @@ -1852,7 +1851,7 @@ out: static int spufs_mfc_fsync(struct file *file, loff_t start, loff_t end, int datasync) { - struct inode *inode = file->f_path.dentry->d_inode; + struct inode *inode = file_inode(file); int err = filemap_write_and_wait_range(inode->i_mapping, start, end); if (!err) { mutex_lock(&inode->i_mutex); @@ -2501,7 +2500,7 @@ static int switch_log_sprint(struct spu_context *ctx, char *tbuf, int n) static ssize_t spufs_switch_log_read(struct file *file, char __user *buf, size_t len, loff_t *ppos) { - struct inode *inode = file->f_path.dentry->d_inode; + struct inode *inode = file_inode(file); struct spu_context *ctx = SPUFS_I(inode)->i_ctx; int error = 0, cnt = 0; @@ -2571,7 +2570,7 @@ static ssize_t spufs_switch_log_read(struct file *file, char __user *buf, static unsigned int spufs_switch_log_poll(struct file *file, poll_table *wait) { - struct inode *inode = file->f_path.dentry->d_inode; + struct inode *inode = file_inode(file); struct spu_context *ctx = SPUFS_I(inode)->i_ctx; unsigned int mask = 0; int rc; @@ -2591,7 +2590,6 @@ static unsigned int spufs_switch_log_poll(struct file *file, poll_table *wait) } static const struct file_operations spufs_switch_log_fops = { - .owner = THIS_MODULE, .open = spufs_switch_log_open, .read = spufs_switch_log_read, .poll = spufs_switch_log_poll, diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index dba1ce235da..87ba7cf99cd 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -99,6 +99,7 @@ spufs_new_inode(struct super_block *sb, umode_t mode) if (!inode) goto out; + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); @@ -199,37 +200,18 @@ static int spufs_fill_dir(struct dentry *dir, const struct spufs_tree_descr *files, umode_t mode, struct spu_context *ctx) { - struct dentry *dentry, *tmp; - int ret; - while (files->name && files->name[0]) { - ret = -ENOMEM; - dentry = d_alloc_name(dir, files->name); + int ret; + struct dentry *dentry = d_alloc_name(dir, files->name); if (!dentry) - goto out; + return -ENOMEM; ret = spufs_new_file(dir->d_sb, dentry, files->ops, files->mode & mode, files->size, ctx); if (ret) - goto out; + return ret; files++; } return 0; -out: - /* - * remove all children from dir. dir->inode is not set so don't - * just simply use spufs_prune_dir() and panic afterwards :) - * dput() looks like it will do the right thing: - * - dec parent's ref counter - * - remove child from parent's child list - * - free child's inode if possible - * - free child - */ - list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_u.d_child) { - dput(dentry); - } - - shrink_dcache_parent(dir); - return ret; } static int spufs_dir_close(struct inode *inode, struct file *file) @@ -256,7 +238,7 @@ const struct file_operations spufs_context_fops = { .release = spufs_dir_close, .llseek = dcache_dir_lseek, .read = generic_read_dir, - .readdir = dcache_readdir, + .iterate = dcache_readdir, .fsync = noop_fsync, }; EXPORT_SYMBOL_GPL(spufs_context_fops); @@ -269,10 +251,9 @@ spufs_mkdir(struct inode *dir, struct dentry *dentry, unsigned int flags, struct inode *inode; struct spu_context *ctx; - ret = -ENOSPC; inode = spufs_new_inode(dir->i_sb, mode | S_IFDIR); if (!inode) - goto out; + return -ENOSPC; if (dir->i_mode & S_ISGID) { inode->i_gid = dir->i_gid; @@ -280,40 +261,38 @@ spufs_mkdir(struct inode *dir, struct dentry *dentry, unsigned int flags, } ctx = alloc_spu_context(SPUFS_I(dir)->i_gang); /* XXX gang */ SPUFS_I(inode)->i_ctx = ctx; - if (!ctx) - goto out_iput; + if (!ctx) { + iput(inode); + return -ENOSPC; + } ctx->flags = flags; inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; + + mutex_lock(&inode->i_mutex); + + dget(dentry); + inc_nlink(dir); + inc_nlink(inode); + + d_instantiate(dentry, inode); + if (flags & SPU_CREATE_NOSCHED) ret = spufs_fill_dir(dentry, spufs_dir_nosched_contents, mode, ctx); else ret = spufs_fill_dir(dentry, spufs_dir_contents, mode, ctx); - if (ret) - goto out_free_ctx; - - if (spufs_get_sb_info(dir->i_sb)->debug) + if (!ret && spufs_get_sb_info(dir->i_sb)->debug) ret = spufs_fill_dir(dentry, spufs_dir_debug_contents, mode, ctx); if (ret) - goto out_free_ctx; + spufs_rmdir(dir, dentry); - d_instantiate(dentry, inode); - dget(dentry); - inc_nlink(dir); - inc_nlink(dentry->d_inode); - goto out; + mutex_unlock(&inode->i_mutex); -out_free_ctx: - spu_forget(ctx); - put_spu_context(ctx); -out_iput: - iput(inode); -out: return ret; } @@ -368,7 +347,7 @@ spufs_assert_affinity(unsigned int flags, struct spu_gang *gang, return ERR_PTR(-EINVAL); neighbor = get_spu_context( - SPUFS_I(filp->f_dentry->d_inode)->i_ctx); + SPUFS_I(file_inode(filp))->i_ctx); if (!list_empty(&neighbor->aff_list) && !(neighbor->aff_head) && !list_is_last(&neighbor->aff_list, &gang->aff_list_head) && @@ -641,12 +620,16 @@ spufs_parse_options(struct super_block *sb, char *options, struct inode *root) case Opt_uid: if (match_int(&args[0], &option)) return 0; - root->i_uid = option; + root->i_uid = make_kuid(current_user_ns(), option); + if (!uid_valid(root->i_uid)) + return 0; break; case Opt_gid: if (match_int(&args[0], &option)) return 0; - root->i_gid = option; + root->i_gid = make_kgid(current_user_ns(), option); + if (!gid_valid(root->i_gid)) + return 0; break; case Opt_mode: if (match_octal(&args[0], &option)) @@ -771,6 +754,7 @@ static struct file_system_type spufs_type = { .mount = spufs_mount, .kill_sb = kill_litter_super, }; +MODULE_ALIAS_FS("spufs"); static int __init spufs_init(void) { diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c index 25db92a8e1c..4a0a64fe25d 100644 --- a/arch/powerpc/platforms/cell/spufs/sched.c +++ b/arch/powerpc/platforms/cell/spufs/sched.c @@ -24,6 +24,7 @@ #include <linux/errno.h> #include <linux/sched.h> +#include <linux/sched/rt.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/slab.h> @@ -82,7 +83,6 @@ static struct timer_list spuloadavg_timer; #define MIN_SPU_TIMESLICE max(5 * HZ / (1000 * SPUSCHED_TICK), 1) #define DEF_SPU_TIMESLICE (100 * HZ / (1000 * SPUSCHED_TICK)) -#define MAX_USER_PRIO (MAX_PRIO - MAX_RT_PRIO) #define SCALE_PRIO(x, prio) \ max(x * (MAX_PRIO - prio) / (MAX_USER_PRIO / 2), MIN_SPU_TIMESLICE) diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h index 67852ade4c0..bcfd6f063ef 100644 --- a/arch/powerpc/platforms/cell/spufs/spufs.h +++ b/arch/powerpc/platforms/cell/spufs/spufs.h @@ -35,7 +35,6 @@ #define SPUFS_PS_MAP_SIZE 0x20000 #define SPUFS_MFC_MAP_SIZE 0x1000 #define SPUFS_CNTL_MAP_SIZE 0x1000 -#define SPUFS_CNTL_MAP_SIZE 0x1000 #define SPUFS_SIGNAL_MAP_SIZE PAGE_SIZE #define SPUFS_MSS_MAP_SIZE 0x1000 @@ -247,12 +246,13 @@ extern const struct spufs_tree_descr spufs_dir_debug_contents[]; /* system call implementation */ extern struct spufs_calls spufs_calls; +struct coredump_params; long spufs_run_spu(struct spu_context *ctx, u32 *npc, u32 *status); long spufs_create(struct path *nd, struct dentry *dentry, unsigned int flags, umode_t mode, struct file *filp); /* ELF coredump callbacks for writing SPU ELF notes */ extern int spufs_coredump_extra_notes_size(void); -extern int spufs_coredump_extra_notes_write(struct file *file, loff_t *foffset); +extern int spufs_coredump_extra_notes_write(struct coredump_params *cprm); extern const struct file_operations spufs_context_fops; diff --git a/arch/powerpc/platforms/cell/spufs/syscalls.c b/arch/powerpc/platforms/cell/spufs/syscalls.c index baee994fe81..a87200a535f 100644 --- a/arch/powerpc/platforms/cell/spufs/syscalls.c +++ b/arch/powerpc/platforms/cell/spufs/syscalls.c @@ -47,7 +47,7 @@ static long do_spu_run(struct file *filp, if (filp->f_op != &spufs_context_fops) goto out; - i = SPUFS_I(filp->f_path.dentry->d_inode); + i = SPUFS_I(file_inode(filp)); ret = spufs_run_spu(i->i_ctx, &npc, &status); if (put_user(npc, unpc)) @@ -79,8 +79,10 @@ static long do_spu_create(const char __user *pathname, unsigned int flags, struct spufs_calls spufs_calls = { .create_thread = do_spu_create, .spu_run = do_spu_run, - .coredump_extra_notes_size = spufs_coredump_extra_notes_size, - .coredump_extra_notes_write = spufs_coredump_extra_notes_write, .notify_spus_active = do_notify_spus_active, .owner = THIS_MODULE, +#ifdef CONFIG_COREDUMP + .coredump_extra_notes_size = spufs_coredump_extra_notes_size, + .coredump_extra_notes_write = spufs_coredump_extra_notes_write, +#endif }; diff --git a/arch/powerpc/platforms/chrp/nvram.c b/arch/powerpc/platforms/chrp/nvram.c index d3ceff04ffc..9ef8cc3378d 100644 --- a/arch/powerpc/platforms/chrp/nvram.c +++ b/arch/powerpc/platforms/chrp/nvram.c @@ -66,7 +66,7 @@ static void chrp_nvram_write(int addr, unsigned char val) void __init chrp_nvram_init(void) { struct device_node *nvram; - const unsigned int *nbytes_p; + const __be32 *nbytes_p; unsigned int proplen; nvram = of_find_node_by_type(NULL, "nvram"); @@ -79,7 +79,7 @@ void __init chrp_nvram_init(void) return; } - nvram_size = *nbytes_p; + nvram_size = be32_to_cpup(nbytes_p); printk(KERN_INFO "CHRP nvram contains %u bytes\n", nvram_size); of_node_put(nvram); diff --git a/arch/powerpc/platforms/chrp/pegasos_eth.c b/arch/powerpc/platforms/chrp/pegasos_eth.c index 039fc8e8219..2b4dc6abde6 100644 --- a/arch/powerpc/platforms/chrp/pegasos_eth.c +++ b/arch/powerpc/platforms/chrp/pegasos_eth.c @@ -47,6 +47,25 @@ static struct platform_device mv643xx_eth_shared_device = { .resource = mv643xx_eth_shared_resources, }; +/* + * The orion mdio driver only covers shared + 0x4 up to shared + 0x84 - 1 + */ +static struct resource mv643xx_eth_mvmdio_resources[] = { + [0] = { + .name = "ethernet mdio base", + .start = 0xf1000000 + MV643XX_ETH_SHARED_REGS + 0x4, + .end = 0xf1000000 + MV643XX_ETH_SHARED_REGS + 0x83, + .flags = IORESOURCE_MEM, + }, +}; + +static struct platform_device mv643xx_eth_mvmdio_device = { + .name = "orion-mdio", + .id = -1, + .num_resources = ARRAY_SIZE(mv643xx_eth_mvmdio_resources), + .resource = mv643xx_eth_shared_resources, +}; + static struct resource mv643xx_eth_port1_resources[] = { [0] = { .name = "eth port1 irq", @@ -82,6 +101,7 @@ static struct platform_device eth_port1_device = { static struct platform_device *mv643xx_eth_pd_devs[] __initdata = { &mv643xx_eth_shared_device, + &mv643xx_eth_mvmdio_device, ð_port1_device, }; diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c index c665d7de6c9..7044fd36197 100644 --- a/arch/powerpc/platforms/chrp/setup.c +++ b/arch/powerpc/platforms/chrp/setup.c @@ -574,8 +574,8 @@ chrp_init2(void) static int __init chrp_probe(void) { - char *dtype = of_get_flat_dt_prop(of_get_flat_dt_root(), - "device_type", NULL); + const char *dtype = of_get_flat_dt_prop(of_get_flat_dt_root(), + "device_type", NULL); if (dtype == NULL) return 0; if (strcmp(dtype, "chrp")) diff --git a/arch/powerpc/platforms/chrp/smp.c b/arch/powerpc/platforms/chrp/smp.c index dead91b177b..b6c9a0dcc92 100644 --- a/arch/powerpc/platforms/chrp/smp.c +++ b/arch/powerpc/platforms/chrp/smp.c @@ -14,7 +14,6 @@ #include <linux/interrupt.h> #include <linux/kernel_stat.h> #include <linux/delay.h> -#include <linux/init.h> #include <linux/spinlock.h> #include <asm/ptrace.h> diff --git a/arch/powerpc/platforms/embedded6xx/Kconfig b/arch/powerpc/platforms/embedded6xx/Kconfig index 5a8f50a9afa..a25f496c2ef 100644 --- a/arch/powerpc/platforms/embedded6xx/Kconfig +++ b/arch/powerpc/platforms/embedded6xx/Kconfig @@ -9,7 +9,6 @@ config LINKSTATION select FSL_SOC select PPC_UDBG_16550 if SERIAL_8250 select DEFAULT_UIMAGE - select MPC10X_OPENPIC select MPC10X_BRIDGE help Select LINKSTATION if configuring for one of PPC- (MPC8241) @@ -24,7 +23,6 @@ config STORCENTER select MPIC select FSL_SOC select PPC_UDBG_16550 if SERIAL_8250 - select MPC10X_OPENPIC select MPC10X_BRIDGE help Select STORCENTER if configuring for the iomega StorCenter @@ -36,7 +34,6 @@ config MPC7448HPC2 select TSI108_BRIDGE select DEFAULT_UIMAGE select PPC_UDBG_16550 - select TSI108_BRIDGE help Select MPC7448HPC2 if configuring for Freescale MPC7448HPC2 (Taiga) platform @@ -46,19 +43,10 @@ config PPC_HOLLY depends on EMBEDDED6xx select TSI108_BRIDGE select PPC_UDBG_16550 - select TSI108_BRIDGE help Select PPC_HOLLY if configuring for an IBM 750GX/CL Eval Board with TSI108/9 bridge (Hickory/Holly) -config PPC_PRPMC2800 - bool "Motorola-PrPMC2800" - depends on EMBEDDED6xx - select MV64X60 - select NOT_COHERENT_CACHE - help - This option enables support for the Motorola PrPMC2800 board - config PPC_C2K bool "SBS/GEFanuc C2K board" depends on EMBEDDED6xx @@ -69,6 +57,19 @@ config PPC_C2K This option enables support for the GE Fanuc C2K board (formerly an SBS board). +config MVME5100 + bool "Motorola/Emerson MVME5100" + depends on EMBEDDED6xx + select MPIC + select PCI + select PPC_INDIRECT_PCI + select PPC_I8259 + select PPC_NATIVE + select PPC_UDBG_16550 + help + This option enables support for the Motorola (now Emerson) MVME5100 + board. + config TSI108_BRIDGE bool select PCI @@ -84,9 +85,6 @@ config MV64X60 select PPC_INDIRECT_PCI select CHECK_CACHE_COHERENCY -config MPC10X_OPENPIC - bool - config GAMECUBE_COMMON bool @@ -118,4 +116,3 @@ config WII help Select WII if configuring for the Nintendo Wii. More information at: <http://gc-linux.sourceforge.net/> - diff --git a/arch/powerpc/platforms/embedded6xx/Makefile b/arch/powerpc/platforms/embedded6xx/Makefile index 66c23e423f4..f126a2a0998 100644 --- a/arch/powerpc/platforms/embedded6xx/Makefile +++ b/arch/powerpc/platforms/embedded6xx/Makefile @@ -5,9 +5,9 @@ obj-$(CONFIG_MPC7448HPC2) += mpc7448_hpc2.o obj-$(CONFIG_LINKSTATION) += linkstation.o ls_uart.o obj-$(CONFIG_STORCENTER) += storcenter.o obj-$(CONFIG_PPC_HOLLY) += holly.o -obj-$(CONFIG_PPC_PRPMC2800) += prpmc2800.o obj-$(CONFIG_PPC_C2K) += c2k.o obj-$(CONFIG_USBGECKO_UDBG) += usbgecko_udbg.o obj-$(CONFIG_GAMECUBE_COMMON) += flipper-pic.o obj-$(CONFIG_GAMECUBE) += gamecube.o obj-$(CONFIG_WII) += wii.o hlwd-pic.o +obj-$(CONFIG_MVME5100) += mvme5100.o diff --git a/arch/powerpc/platforms/embedded6xx/flipper-pic.c b/arch/powerpc/platforms/embedded6xx/flipper-pic.c index 53d6eee0196..4cde8e7da4b 100644 --- a/arch/powerpc/platforms/embedded6xx/flipper-pic.c +++ b/arch/powerpc/platforms/embedded6xx/flipper-pic.c @@ -18,6 +18,7 @@ #include <linux/init.h> #include <linux/irq.h> #include <linux/of.h> +#include <linux/of_address.h> #include <asm/io.h> #include "flipper-pic.h" diff --git a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c index 3006b5117ec..c269caee58f 100644 --- a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c +++ b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c @@ -15,9 +15,10 @@ #define pr_fmt(fmt) DRV_MODULE_NAME ": " fmt #include <linux/kernel.h> -#include <linux/init.h> #include <linux/irq.h> #include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> #include <asm/io.h> #include "hlwd-pic.h" @@ -181,6 +182,7 @@ struct irq_domain *hlwd_pic_init(struct device_node *np) &hlwd_irq_domain_ops, io_base); if (!irq_domain) { pr_err("failed to allocate irq_domain\n"); + iounmap(io_base); return NULL; } diff --git a/arch/powerpc/platforms/embedded6xx/mpc10x.h b/arch/powerpc/platforms/embedded6xx/mpc10x.h index b30a6a3b5bd..b290b63661f 100644 --- a/arch/powerpc/platforms/embedded6xx/mpc10x.h +++ b/arch/powerpc/platforms/embedded6xx/mpc10x.h @@ -81,17 +81,6 @@ #define MPC10X_MAPB_PCI_MEM_OFFSET (MPC10X_MAPB_ISA_MEM_BASE - \ MPC10X_MAPB_PCI_MEM_START) -/* Set hose members to values appropriate for the mem map used */ -#define MPC10X_SETUP_HOSE(hose, map) { \ - (hose)->pci_mem_offset = MPC10X_MAP##map##_PCI_MEM_OFFSET; \ - (hose)->io_space.start = MPC10X_MAP##map##_PCI_IO_START; \ - (hose)->io_space.end = MPC10X_MAP##map##_PCI_IO_END; \ - (hose)->mem_space.start = MPC10X_MAP##map##_PCI_MEM_START; \ - (hose)->mem_space.end = MPC10X_MAP##map##_PCI_MEM_END; \ - (hose)->io_base_virt = (void *)MPC10X_MAP##map##_ISA_IO_BASE; \ -} - - /* Miscellaneous Configuration register offsets */ #define MPC10X_CFG_PIR_REG 0x09 #define MPC10X_CFG_PIR_HOST_BRIDGE 0x00 diff --git a/arch/powerpc/platforms/embedded6xx/mvme5100.c b/arch/powerpc/platforms/embedded6xx/mvme5100.c new file mode 100644 index 00000000000..25e3bfb64ef --- /dev/null +++ b/arch/powerpc/platforms/embedded6xx/mvme5100.c @@ -0,0 +1,221 @@ +/* + * Board setup routines for the Motorola/Emerson MVME5100. + * + * Copyright 2013 CSC Australia Pty. Ltd. + * + * Based on earlier code by: + * + * Matt Porter, MontaVista Software Inc. + * Copyright 2001 MontaVista Software Inc. + * + * 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. + * + * Author: Stephen Chivers <schivers@csc.com> + * + */ + +#include <linux/of_platform.h> + +#include <asm/i8259.h> +#include <asm/pci-bridge.h> +#include <asm/mpic.h> +#include <asm/prom.h> +#include <mm/mmu_decl.h> +#include <asm/udbg.h> + +#define HAWK_MPIC_SIZE 0x00040000U +#define MVME5100_PCI_MEM_OFFSET 0x00000000 + +/* Board register addresses. */ +#define BOARD_STATUS_REG 0xfef88080 +#define BOARD_MODFAIL_REG 0xfef88090 +#define BOARD_MODRST_REG 0xfef880a0 +#define BOARD_TBEN_REG 0xfef880c0 +#define BOARD_SW_READ_REG 0xfef880e0 +#define BOARD_GEO_ADDR_REG 0xfef880e8 +#define BOARD_EXT_FEATURE1_REG 0xfef880f0 +#define BOARD_EXT_FEATURE2_REG 0xfef88100 + +static phys_addr_t pci_membase; +static u_char *restart; + +static void mvme5100_8259_cascade(unsigned int irq, struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + unsigned int cascade_irq = i8259_irq(); + + if (cascade_irq != NO_IRQ) + generic_handle_irq(cascade_irq); + + chip->irq_eoi(&desc->irq_data); +} + +static void __init mvme5100_pic_init(void) +{ + struct mpic *mpic; + struct device_node *np; + struct device_node *cp = NULL; + unsigned int cirq; + unsigned long intack = 0; + const u32 *prop = NULL; + + np = of_find_node_by_type(NULL, "open-pic"); + if (!np) { + pr_err("Could not find open-pic node\n"); + return; + } + + mpic = mpic_alloc(np, pci_membase, 0, 16, 256, " OpenPIC "); + + BUG_ON(mpic == NULL); + of_node_put(np); + + mpic_assign_isu(mpic, 0, pci_membase + 0x10000); + + mpic_init(mpic); + + cp = of_find_compatible_node(NULL, NULL, "chrp,iic"); + if (cp == NULL) { + pr_warn("mvme5100_pic_init: couldn't find i8259\n"); + return; + } + + cirq = irq_of_parse_and_map(cp, 0); + if (cirq == NO_IRQ) { + pr_warn("mvme5100_pic_init: no cascade interrupt?\n"); + return; + } + + np = of_find_compatible_node(NULL, "pci", "mpc10x-pci"); + if (np) { + prop = of_get_property(np, "8259-interrupt-acknowledge", NULL); + + if (prop) + intack = prop[0]; + + of_node_put(np); + } + + if (intack) + pr_debug("mvme5100_pic_init: PCI 8259 intack at 0x%016lx\n", + intack); + + i8259_init(cp, intack); + of_node_put(cp); + irq_set_chained_handler(cirq, mvme5100_8259_cascade); +} + +static int __init mvme5100_add_bridge(struct device_node *dev) +{ + const int *bus_range; + int len; + struct pci_controller *hose; + unsigned short devid; + + pr_info("Adding PCI host bridge %s\n", dev->full_name); + + bus_range = of_get_property(dev, "bus-range", &len); + + hose = pcibios_alloc_controller(dev); + if (hose == NULL) + return -ENOMEM; + + hose->first_busno = bus_range ? bus_range[0] : 0; + hose->last_busno = bus_range ? bus_range[1] : 0xff; + + setup_indirect_pci(hose, 0xfe000cf8, 0xfe000cfc, 0); + + pci_process_bridge_OF_ranges(hose, dev, 1); + + early_read_config_word(hose, 0, 0, PCI_DEVICE_ID, &devid); + + if (devid != PCI_DEVICE_ID_MOTOROLA_HAWK) { + pr_err("HAWK PHB not present?\n"); + return 0; + } + + early_read_config_dword(hose, 0, 0, PCI_BASE_ADDRESS_1, &pci_membase); + + if (pci_membase == 0) { + pr_err("HAWK PHB mibar not correctly set?\n"); + return 0; + } + + pr_info("mvme5100_pic_init: pci_membase: %x\n", pci_membase); + + return 0; +} + +static struct of_device_id mvme5100_of_bus_ids[] __initdata = { + { .compatible = "hawk-bridge", }, + {}, +}; + +/* + * Setup the architecture + */ +static void __init mvme5100_setup_arch(void) +{ + struct device_node *np; + + if (ppc_md.progress) + ppc_md.progress("mvme5100_setup_arch()", 0); + + for_each_compatible_node(np, "pci", "hawk-pci") + mvme5100_add_bridge(np); + + restart = ioremap(BOARD_MODRST_REG, 4); +} + + +static void mvme5100_show_cpuinfo(struct seq_file *m) +{ + seq_puts(m, "Vendor\t\t: Motorola/Emerson\n"); + seq_puts(m, "Machine\t\t: MVME5100\n"); +} + +static void mvme5100_restart(char *cmd) +{ + + local_irq_disable(); + mtmsr(mfmsr() | MSR_IP); + + out_8((u_char *) restart, 0x01); + + while (1) + ; +} + +/* + * Called very early, device-tree isn't unflattened + */ +static int __init mvme5100_probe(void) +{ + unsigned long root = of_get_flat_dt_root(); + + return of_flat_dt_is_compatible(root, "MVME5100"); +} + +static int __init probe_of_platform_devices(void) +{ + + of_platform_bus_probe(NULL, mvme5100_of_bus_ids, NULL); + return 0; +} + +machine_device_initcall(mvme5100, probe_of_platform_devices); + +define_machine(mvme5100) { + .name = "MVME5100", + .probe = mvme5100_probe, + .setup_arch = mvme5100_setup_arch, + .init_IRQ = mvme5100_pic_init, + .show_cpuinfo = mvme5100_show_cpuinfo, + .get_irq = mpic_get_irq, + .restart = mvme5100_restart, + .calibrate_decr = generic_calibrate_decr, + .progress = udbg_progress, +}; diff --git a/arch/powerpc/platforms/embedded6xx/prpmc2800.c b/arch/powerpc/platforms/embedded6xx/prpmc2800.c deleted file mode 100644 index d455f08bea5..00000000000 --- a/arch/powerpc/platforms/embedded6xx/prpmc2800.c +++ /dev/null @@ -1,156 +0,0 @@ -/* - * Board setup routines for the Motorola PrPMC2800 - * - * Author: Dale Farnsworth <dale@farnsworth.org> - * - * 2007 (c) MontaVista, Software, Inc. This file is licensed under - * the terms of the GNU General Public License version 2. This program - * is licensed "as is" without any warranty of any kind, whether express - * or implied. - */ - -#include <linux/stddef.h> -#include <linux/kernel.h> -#include <linux/delay.h> -#include <linux/interrupt.h> -#include <linux/seq_file.h> - -#include <asm/machdep.h> -#include <asm/prom.h> -#include <asm/time.h> - -#include <mm/mmu_decl.h> - -#include <sysdev/mv64x60.h> - -#define MV64x60_MPP_CNTL_0 0x0000 -#define MV64x60_MPP_CNTL_2 0x0008 - -#define MV64x60_GPP_IO_CNTL 0x0000 -#define MV64x60_GPP_LEVEL_CNTL 0x0010 -#define MV64x60_GPP_VALUE_SET 0x0018 - -#define PLATFORM_NAME_MAX 32 - -static char prpmc2800_platform_name[PLATFORM_NAME_MAX]; - -static void __iomem *mv64x60_mpp_reg_base; -static void __iomem *mv64x60_gpp_reg_base; - -static void __init prpmc2800_setup_arch(void) -{ - struct device_node *np; - phys_addr_t paddr; - const unsigned int *reg; - - /* - * ioremap mpp and gpp registers in case they are later - * needed by prpmc2800_reset_board(). - */ - np = of_find_compatible_node(NULL, NULL, "marvell,mv64360-mpp"); - reg = of_get_property(np, "reg", NULL); - paddr = of_translate_address(np, reg); - of_node_put(np); - mv64x60_mpp_reg_base = ioremap(paddr, reg[1]); - - np = of_find_compatible_node(NULL, NULL, "marvell,mv64360-gpp"); - reg = of_get_property(np, "reg", NULL); - paddr = of_translate_address(np, reg); - of_node_put(np); - mv64x60_gpp_reg_base = ioremap(paddr, reg[1]); - -#ifdef CONFIG_PCI - mv64x60_pci_init(); -#endif - - printk("Motorola %s\n", prpmc2800_platform_name); -} - -static void prpmc2800_reset_board(void) -{ - u32 temp; - - local_irq_disable(); - - temp = in_le32(mv64x60_mpp_reg_base + MV64x60_MPP_CNTL_0); - temp &= 0xFFFF0FFF; - out_le32(mv64x60_mpp_reg_base + MV64x60_MPP_CNTL_0, temp); - - temp = in_le32(mv64x60_gpp_reg_base + MV64x60_GPP_LEVEL_CNTL); - temp |= 0x00000004; - out_le32(mv64x60_gpp_reg_base + MV64x60_GPP_LEVEL_CNTL, temp); - - temp = in_le32(mv64x60_gpp_reg_base + MV64x60_GPP_IO_CNTL); - temp |= 0x00000004; - out_le32(mv64x60_gpp_reg_base + MV64x60_GPP_IO_CNTL, temp); - - temp = in_le32(mv64x60_mpp_reg_base + MV64x60_MPP_CNTL_2); - temp &= 0xFFFF0FFF; - out_le32(mv64x60_mpp_reg_base + MV64x60_MPP_CNTL_2, temp); - - temp = in_le32(mv64x60_gpp_reg_base + MV64x60_GPP_LEVEL_CNTL); - temp |= 0x00080000; - out_le32(mv64x60_gpp_reg_base + MV64x60_GPP_LEVEL_CNTL, temp); - - temp = in_le32(mv64x60_gpp_reg_base + MV64x60_GPP_IO_CNTL); - temp |= 0x00080000; - out_le32(mv64x60_gpp_reg_base + MV64x60_GPP_IO_CNTL, temp); - - out_le32(mv64x60_gpp_reg_base + MV64x60_GPP_VALUE_SET, 0x00080004); -} - -static void prpmc2800_restart(char *cmd) -{ - volatile ulong i = 10000000; - - prpmc2800_reset_board(); - - while (i-- > 0); - panic("restart failed\n"); -} - -#ifdef CONFIG_NOT_COHERENT_CACHE -#define PPRPM2800_COHERENCY_SETTING "off" -#else -#define PPRPM2800_COHERENCY_SETTING "on" -#endif - -void prpmc2800_show_cpuinfo(struct seq_file *m) -{ - seq_printf(m, "Vendor\t\t: Motorola\n"); - seq_printf(m, "coherency\t: %s\n", PPRPM2800_COHERENCY_SETTING); -} - -/* - * Called very early, device-tree isn't unflattened - */ -static int __init prpmc2800_probe(void) -{ - unsigned long root = of_get_flat_dt_root(); - unsigned long len = PLATFORM_NAME_MAX; - void *m; - - if (!of_flat_dt_is_compatible(root, "motorola,PrPMC2800")) - return 0; - - /* Update ppc_md.name with name from dt */ - m = of_get_flat_dt_prop(root, "model", &len); - if (m) - strncpy(prpmc2800_platform_name, m, - min((int)len, PLATFORM_NAME_MAX - 1)); - - _set_L2CR(_get_L2CR() | L2CR_L2E); - return 1; -} - -define_machine(prpmc2800){ - .name = prpmc2800_platform_name, - .probe = prpmc2800_probe, - .setup_arch = prpmc2800_setup_arch, - .init_early = mv64x60_init_early, - .show_cpuinfo = prpmc2800_show_cpuinfo, - .init_IRQ = mv64x60_init_irq, - .get_irq = mv64x60_get_irq, - .restart = prpmc2800_restart, - .calibrate_decr = generic_calibrate_decr, -}; diff --git a/arch/powerpc/platforms/fsl_uli1575.c b/arch/powerpc/platforms/fsl_uli1575.c index 92ac9b52b32..b97f6f3d3c5 100644 --- a/arch/powerpc/platforms/fsl_uli1575.c +++ b/arch/powerpc/platforms/fsl_uli1575.c @@ -321,8 +321,7 @@ static void hpcd_final_uli5288(struct pci_dev *dev) { struct pci_controller *hose = pci_bus_to_host(dev->bus); struct device_node *hosenode = hose ? hose->dn : NULL; - struct of_irq oirq; - int virq, pin = 2; + struct of_phandle_args oirq; u32 laddr[3]; if (!machine_is(mpc86xx_hpcd)) @@ -331,12 +330,13 @@ static void hpcd_final_uli5288(struct pci_dev *dev) if (!hosenode) return; + oirq.np = hosenode; + oirq.args[0] = 2; + oirq.args_count = 1; laddr[0] = (hose->first_busno << 16) | (PCI_DEVFN(31, 0) << 8); laddr[1] = laddr[2] = 0; - of_irq_map_raw(hosenode, &pin, 1, laddr, &oirq); - virq = irq_create_of_mapping(oirq.controller, oirq.specifier, - oirq.size); - dev->irq = virq; + of_irq_parse_raw(laddr, &oirq); + dev->irq = irq_create_of_mapping(&oirq); } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AL, 0x1575, hpcd_quirk_uli1575); diff --git a/arch/powerpc/platforms/pasemi/Makefile b/arch/powerpc/platforms/pasemi/Makefile index ce6d789e074..8e8d4cae5eb 100644 --- a/arch/powerpc/platforms/pasemi/Makefile +++ b/arch/powerpc/platforms/pasemi/Makefile @@ -1,3 +1,2 @@ obj-y += setup.o pci.o time.o idle.o powersave.o iommu.o dma_lib.o misc.o obj-$(CONFIG_PPC_PASEMI_MDIO) += gpio_mdio.o -obj-$(CONFIG_PPC_PASEMI_CPUFREQ) += cpufreq.o diff --git a/arch/powerpc/platforms/pasemi/cpufreq.c b/arch/powerpc/platforms/pasemi/cpufreq.c deleted file mode 100644 index 95d00173029..00000000000 --- a/arch/powerpc/platforms/pasemi/cpufreq.c +++ /dev/null @@ -1,324 +0,0 @@ -/* - * Copyright (C) 2007 PA Semi, Inc - * - * Authors: Egor Martovetsky <egor@pasemi.com> - * Olof Johansson <olof@lixom.net> - * - * Maintained by: Olof Johansson <olof@lixom.net> - * - * Based on arch/powerpc/platforms/cell/cbe_cpufreq.c: - * (C) Copyright IBM Deutschland Entwicklung GmbH 2005 - * - * 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. - * - * 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., 675 Mass Ave, Cambridge, MA 02139, USA. - * - */ - -#include <linux/cpufreq.h> -#include <linux/timer.h> -#include <linux/module.h> - -#include <asm/hw_irq.h> -#include <asm/io.h> -#include <asm/prom.h> -#include <asm/time.h> -#include <asm/smp.h> - -#define SDCASR_REG 0x0100 -#define SDCASR_REG_STRIDE 0x1000 -#define SDCPWR_CFGA0_REG 0x0100 -#define SDCPWR_PWST0_REG 0x0000 -#define SDCPWR_GIZTIME_REG 0x0440 - -/* SDCPWR_GIZTIME_REG fields */ -#define SDCPWR_GIZTIME_GR 0x80000000 -#define SDCPWR_GIZTIME_LONGLOCK 0x000000ff - -/* Offset of ASR registers from SDC base */ -#define SDCASR_OFFSET 0x120000 - -static void __iomem *sdcpwr_mapbase; -static void __iomem *sdcasr_mapbase; - -static DEFINE_MUTEX(pas_switch_mutex); - -/* Current astate, is used when waking up from power savings on - * one core, in case the other core has switched states during - * the idle time. - */ -static int current_astate; - -/* We support 5(A0-A4) power states excluding turbo(A5-A6) modes */ -static struct cpufreq_frequency_table pas_freqs[] = { - {0, 0}, - {1, 0}, - {2, 0}, - {3, 0}, - {4, 0}, - {0, CPUFREQ_TABLE_END}, -}; - -static struct freq_attr *pas_cpu_freqs_attr[] = { - &cpufreq_freq_attr_scaling_available_freqs, - NULL, -}; - -/* - * hardware specific functions - */ - -static int get_astate_freq(int astate) -{ - u32 ret; - ret = in_le32(sdcpwr_mapbase + SDCPWR_CFGA0_REG + (astate * 0x10)); - - return ret & 0x3f; -} - -static int get_cur_astate(int cpu) -{ - u32 ret; - - ret = in_le32(sdcpwr_mapbase + SDCPWR_PWST0_REG); - ret = (ret >> (cpu * 4)) & 0x7; - - return ret; -} - -static int get_gizmo_latency(void) -{ - u32 giztime, ret; - - giztime = in_le32(sdcpwr_mapbase + SDCPWR_GIZTIME_REG); - - /* just provide the upper bound */ - if (giztime & SDCPWR_GIZTIME_GR) - ret = (giztime & SDCPWR_GIZTIME_LONGLOCK) * 128000; - else - ret = (giztime & SDCPWR_GIZTIME_LONGLOCK) * 1000; - - return ret; -} - -static void set_astate(int cpu, unsigned int astate) -{ - unsigned long flags; - - /* Return if called before init has run */ - if (unlikely(!sdcasr_mapbase)) - return; - - local_irq_save(flags); - - out_le32(sdcasr_mapbase + SDCASR_REG + SDCASR_REG_STRIDE*cpu, astate); - - local_irq_restore(flags); -} - -int check_astate(void) -{ - return get_cur_astate(hard_smp_processor_id()); -} - -void restore_astate(int cpu) -{ - set_astate(cpu, current_astate); -} - -/* - * cpufreq functions - */ - -static int pas_cpufreq_cpu_init(struct cpufreq_policy *policy) -{ - const u32 *max_freqp; - u32 max_freq; - int i, cur_astate; - struct resource res; - struct device_node *cpu, *dn; - int err = -ENODEV; - - cpu = of_get_cpu_node(policy->cpu, NULL); - - if (!cpu) - goto out; - - dn = of_find_compatible_node(NULL, NULL, "1682m-sdc"); - if (!dn) - dn = of_find_compatible_node(NULL, NULL, - "pasemi,pwrficient-sdc"); - if (!dn) - goto out; - err = of_address_to_resource(dn, 0, &res); - of_node_put(dn); - if (err) - goto out; - sdcasr_mapbase = ioremap(res.start + SDCASR_OFFSET, 0x2000); - if (!sdcasr_mapbase) { - err = -EINVAL; - goto out; - } - - dn = of_find_compatible_node(NULL, NULL, "1682m-gizmo"); - if (!dn) - dn = of_find_compatible_node(NULL, NULL, - "pasemi,pwrficient-gizmo"); - if (!dn) { - err = -ENODEV; - goto out_unmap_sdcasr; - } - err = of_address_to_resource(dn, 0, &res); - of_node_put(dn); - if (err) - goto out_unmap_sdcasr; - sdcpwr_mapbase = ioremap(res.start, 0x1000); - if (!sdcpwr_mapbase) { - err = -EINVAL; - goto out_unmap_sdcasr; - } - - pr_debug("init cpufreq on CPU %d\n", policy->cpu); - - max_freqp = of_get_property(cpu, "clock-frequency", NULL); - if (!max_freqp) { - err = -EINVAL; - goto out_unmap_sdcpwr; - } - - /* we need the freq in kHz */ - max_freq = *max_freqp / 1000; - - pr_debug("max clock-frequency is at %u kHz\n", max_freq); - pr_debug("initializing frequency table\n"); - - /* initialize frequency table */ - for (i=0; pas_freqs[i].frequency!=CPUFREQ_TABLE_END; i++) { - pas_freqs[i].frequency = get_astate_freq(pas_freqs[i].index) * 100000; - pr_debug("%d: %d\n", i, pas_freqs[i].frequency); - } - - policy->cpuinfo.transition_latency = get_gizmo_latency(); - - cur_astate = get_cur_astate(policy->cpu); - pr_debug("current astate is at %d\n",cur_astate); - - policy->cur = pas_freqs[cur_astate].frequency; - cpumask_copy(policy->cpus, cpu_online_mask); - - ppc_proc_freq = policy->cur * 1000ul; - - cpufreq_frequency_table_get_attr(pas_freqs, policy->cpu); - - /* this ensures that policy->cpuinfo_min and policy->cpuinfo_max - * are set correctly - */ - return cpufreq_frequency_table_cpuinfo(policy, pas_freqs); - -out_unmap_sdcpwr: - iounmap(sdcpwr_mapbase); - -out_unmap_sdcasr: - iounmap(sdcasr_mapbase); -out: - return err; -} - -static int pas_cpufreq_cpu_exit(struct cpufreq_policy *policy) -{ - if (sdcasr_mapbase) - iounmap(sdcasr_mapbase); - if (sdcpwr_mapbase) - iounmap(sdcpwr_mapbase); - - cpufreq_frequency_table_put_attr(policy->cpu); - return 0; -} - -static int pas_cpufreq_verify(struct cpufreq_policy *policy) -{ - return cpufreq_frequency_table_verify(policy, pas_freqs); -} - -static int pas_cpufreq_target(struct cpufreq_policy *policy, - unsigned int target_freq, - unsigned int relation) -{ - struct cpufreq_freqs freqs; - int pas_astate_new; - int i; - - cpufreq_frequency_table_target(policy, - pas_freqs, - target_freq, - relation, - &pas_astate_new); - - freqs.old = policy->cur; - freqs.new = pas_freqs[pas_astate_new].frequency; - freqs.cpu = policy->cpu; - - mutex_lock(&pas_switch_mutex); - cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); - - pr_debug("setting frequency for cpu %d to %d kHz, 1/%d of max frequency\n", - policy->cpu, - pas_freqs[pas_astate_new].frequency, - pas_freqs[pas_astate_new].index); - - current_astate = pas_astate_new; - - for_each_online_cpu(i) - set_astate(i, pas_astate_new); - - cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); - mutex_unlock(&pas_switch_mutex); - - ppc_proc_freq = freqs.new * 1000ul; - return 0; -} - -static struct cpufreq_driver pas_cpufreq_driver = { - .name = "pas-cpufreq", - .owner = THIS_MODULE, - .flags = CPUFREQ_CONST_LOOPS, - .init = pas_cpufreq_cpu_init, - .exit = pas_cpufreq_cpu_exit, - .verify = pas_cpufreq_verify, - .target = pas_cpufreq_target, - .attr = pas_cpu_freqs_attr, -}; - -/* - * module init and destoy - */ - -static int __init pas_cpufreq_init(void) -{ - if (!of_machine_is_compatible("PA6T-1682M") && - !of_machine_is_compatible("pasemi,pwrficient")) - return -ENODEV; - - return cpufreq_register_driver(&pas_cpufreq_driver); -} - -static void __exit pas_cpufreq_exit(void) -{ - cpufreq_unregister_driver(&pas_cpufreq_driver); -} - -module_init(pas_cpufreq_init); -module_exit(pas_cpufreq_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Egor Martovetsky <egor@pasemi.com>, Olof Johansson <olof@lixom.net>"); diff --git a/arch/powerpc/platforms/pasemi/dma_lib.c b/arch/powerpc/platforms/pasemi/dma_lib.c index f3defd8a280..aafa01ba062 100644 --- a/arch/powerpc/platforms/pasemi/dma_lib.c +++ b/arch/powerpc/platforms/pasemi/dma_lib.c @@ -18,7 +18,6 @@ */ #include <linux/kernel.h> -#include <linux/init.h> #include <linux/export.h> #include <linux/pci.h> #include <linux/slab.h> diff --git a/arch/powerpc/platforms/pasemi/gpio_mdio.c b/arch/powerpc/platforms/pasemi/gpio_mdio.c index 0237ab782fb..15adee54463 100644 --- a/arch/powerpc/platforms/pasemi/gpio_mdio.c +++ b/arch/powerpc/platforms/pasemi/gpio_mdio.c @@ -30,6 +30,7 @@ #include <linux/ioport.h> #include <linux/interrupt.h> #include <linux/phy.h> +#include <linux/of_address.h> #include <linux/of_mdio.h> #include <linux/of_platform.h> diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c index 7d2d036754b..2e576f2ae44 100644 --- a/arch/powerpc/platforms/pasemi/iommu.c +++ b/arch/powerpc/platforms/pasemi/iommu.c @@ -138,8 +138,11 @@ static void iommu_table_iobmap_setup(void) pr_debug(" -> %s\n", __func__); iommu_table_iobmap.it_busno = 0; iommu_table_iobmap.it_offset = 0; + iommu_table_iobmap.it_page_shift = IOBMAP_PAGE_SHIFT; + /* it_size is in number of entries */ - iommu_table_iobmap.it_size = 0x80000000 >> IOBMAP_PAGE_SHIFT; + iommu_table_iobmap.it_size = + 0x80000000 >> iommu_table_iobmap.it_page_shift; /* Initialize the common IOMMU code */ iommu_table_iobmap.it_base = (unsigned long)iob_l2_base; diff --git a/arch/powerpc/platforms/pasemi/powersave.S b/arch/powerpc/platforms/pasemi/powersave.S index 56f45adcd08..81ab555aa49 100644 --- a/arch/powerpc/platforms/pasemi/powersave.S +++ b/arch/powerpc/platforms/pasemi/powersave.S @@ -66,7 +66,7 @@ sleep_common: std r3, 48(r1) /* Only do power savings when in astate 0 */ - bl .check_astate + bl check_astate cmpwi r3,0 bne 1f diff --git a/arch/powerpc/platforms/powermac/Makefile b/arch/powerpc/platforms/powermac/Makefile index ea47df66fee..52c6ce1cc98 100644 --- a/arch/powerpc/platforms/powermac/Makefile +++ b/arch/powerpc/platforms/powermac/Makefile @@ -9,8 +9,6 @@ obj-y += pic.o setup.o time.o feature.o pci.o \ sleep.o low_i2c.o cache.o pfunc_core.o \ pfunc_base.o udbg_scc.o udbg_adb.o obj-$(CONFIG_PMAC_BACKLIGHT) += backlight.o -obj-$(CONFIG_CPU_FREQ_PMAC) += cpufreq_32.o -obj-$(CONFIG_CPU_FREQ_PMAC64) += cpufreq_64.o # CONFIG_NVRAM is an arch. independent tristate symbol, for pmac32 we really # need this to be a bool. Cheat here and pretend CONFIG_NVRAM=m is really # CONFIG_NVRAM=y diff --git a/arch/powerpc/platforms/powermac/cpufreq_32.c b/arch/powerpc/platforms/powermac/cpufreq_32.c deleted file mode 100644 index 311b804353b..00000000000 --- a/arch/powerpc/platforms/powermac/cpufreq_32.c +++ /dev/null @@ -1,721 +0,0 @@ -/* - * Copyright (C) 2002 - 2005 Benjamin Herrenschmidt <benh@kernel.crashing.org> - * Copyright (C) 2004 John Steele Scott <toojays@toojays.net> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * TODO: Need a big cleanup here. Basically, we need to have different - * cpufreq_driver structures for the different type of HW instead of the - * current mess. We also need to better deal with the detection of the - * type of machine. - * - */ - -#include <linux/module.h> -#include <linux/types.h> -#include <linux/errno.h> -#include <linux/kernel.h> -#include <linux/delay.h> -#include <linux/sched.h> -#include <linux/adb.h> -#include <linux/pmu.h> -#include <linux/cpufreq.h> -#include <linux/init.h> -#include <linux/device.h> -#include <linux/hardirq.h> -#include <asm/prom.h> -#include <asm/machdep.h> -#include <asm/irq.h> -#include <asm/pmac_feature.h> -#include <asm/mmu_context.h> -#include <asm/sections.h> -#include <asm/cputable.h> -#include <asm/time.h> -#include <asm/mpic.h> -#include <asm/keylargo.h> -#include <asm/switch_to.h> - -/* WARNING !!! This will cause calibrate_delay() to be called, - * but this is an __init function ! So you MUST go edit - * init/main.c to make it non-init before enabling DEBUG_FREQ - */ -#undef DEBUG_FREQ - -extern void low_choose_7447a_dfs(int dfs); -extern void low_choose_750fx_pll(int pll); -extern void low_sleep_handler(void); - -/* - * Currently, PowerMac cpufreq supports only high & low frequencies - * that are set by the firmware - */ -static unsigned int low_freq; -static unsigned int hi_freq; -static unsigned int cur_freq; -static unsigned int sleep_freq; -static unsigned long transition_latency; - -/* - * Different models uses different mechanisms to switch the frequency - */ -static int (*set_speed_proc)(int low_speed); -static unsigned int (*get_speed_proc)(void); - -/* - * Some definitions used by the various speedprocs - */ -static u32 voltage_gpio; -static u32 frequency_gpio; -static u32 slew_done_gpio; -static int no_schedule; -static int has_cpu_l2lve; -static int is_pmu_based; - -/* There are only two frequency states for each processor. Values - * are in kHz for the time being. - */ -#define CPUFREQ_HIGH 0 -#define CPUFREQ_LOW 1 - -static struct cpufreq_frequency_table pmac_cpu_freqs[] = { - {CPUFREQ_HIGH, 0}, - {CPUFREQ_LOW, 0}, - {0, CPUFREQ_TABLE_END}, -}; - -static struct freq_attr* pmac_cpu_freqs_attr[] = { - &cpufreq_freq_attr_scaling_available_freqs, - NULL, -}; - -static inline void local_delay(unsigned long ms) -{ - if (no_schedule) - mdelay(ms); - else - msleep(ms); -} - -#ifdef DEBUG_FREQ -static inline void debug_calc_bogomips(void) -{ - /* This will cause a recalc of bogomips and display the - * result. We backup/restore the value to avoid affecting the - * core cpufreq framework's own calculation. - */ - unsigned long save_lpj = loops_per_jiffy; - calibrate_delay(); - loops_per_jiffy = save_lpj; -} -#endif /* DEBUG_FREQ */ - -/* Switch CPU speed under 750FX CPU control - */ -static int cpu_750fx_cpu_speed(int low_speed) -{ - u32 hid2; - - if (low_speed == 0) { - /* ramping up, set voltage first */ - pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, voltage_gpio, 0x05); - /* Make sure we sleep for at least 1ms */ - local_delay(10); - - /* tweak L2 for high voltage */ - if (has_cpu_l2lve) { - hid2 = mfspr(SPRN_HID2); - hid2 &= ~0x2000; - mtspr(SPRN_HID2, hid2); - } - } -#ifdef CONFIG_6xx - low_choose_750fx_pll(low_speed); -#endif - if (low_speed == 1) { - /* tweak L2 for low voltage */ - if (has_cpu_l2lve) { - hid2 = mfspr(SPRN_HID2); - hid2 |= 0x2000; - mtspr(SPRN_HID2, hid2); - } - - /* ramping down, set voltage last */ - pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, voltage_gpio, 0x04); - local_delay(10); - } - - return 0; -} - -static unsigned int cpu_750fx_get_cpu_speed(void) -{ - if (mfspr(SPRN_HID1) & HID1_PS) - return low_freq; - else - return hi_freq; -} - -/* Switch CPU speed using DFS */ -static int dfs_set_cpu_speed(int low_speed) -{ - if (low_speed == 0) { - /* ramping up, set voltage first */ - pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, voltage_gpio, 0x05); - /* Make sure we sleep for at least 1ms */ - local_delay(1); - } - - /* set frequency */ -#ifdef CONFIG_6xx - low_choose_7447a_dfs(low_speed); -#endif - udelay(100); - - if (low_speed == 1) { - /* ramping down, set voltage last */ - pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, voltage_gpio, 0x04); - local_delay(1); - } - - return 0; -} - -static unsigned int dfs_get_cpu_speed(void) -{ - if (mfspr(SPRN_HID1) & HID1_DFS) - return low_freq; - else - return hi_freq; -} - - -/* Switch CPU speed using slewing GPIOs - */ -static int gpios_set_cpu_speed(int low_speed) -{ - int gpio, timeout = 0; - - /* If ramping up, set voltage first */ - if (low_speed == 0) { - pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, voltage_gpio, 0x05); - /* Delay is way too big but it's ok, we schedule */ - local_delay(10); - } - - /* Set frequency */ - gpio = pmac_call_feature(PMAC_FTR_READ_GPIO, NULL, frequency_gpio, 0); - if (low_speed == ((gpio & 0x01) == 0)) - goto skip; - - pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, frequency_gpio, - low_speed ? 0x04 : 0x05); - udelay(200); - do { - if (++timeout > 100) - break; - local_delay(1); - gpio = pmac_call_feature(PMAC_FTR_READ_GPIO, NULL, slew_done_gpio, 0); - } while((gpio & 0x02) == 0); - skip: - /* If ramping down, set voltage last */ - if (low_speed == 1) { - pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, voltage_gpio, 0x04); - /* Delay is way too big but it's ok, we schedule */ - local_delay(10); - } - -#ifdef DEBUG_FREQ - debug_calc_bogomips(); -#endif - - return 0; -} - -/* Switch CPU speed under PMU control - */ -static int pmu_set_cpu_speed(int low_speed) -{ - struct adb_request req; - unsigned long save_l2cr; - unsigned long save_l3cr; - unsigned int pic_prio; - unsigned long flags; - - preempt_disable(); - -#ifdef DEBUG_FREQ - printk(KERN_DEBUG "HID1, before: %x\n", mfspr(SPRN_HID1)); -#endif - pmu_suspend(); - - /* Disable all interrupt sources on openpic */ - pic_prio = mpic_cpu_get_priority(); - mpic_cpu_set_priority(0xf); - - /* Make sure the decrementer won't interrupt us */ - asm volatile("mtdec %0" : : "r" (0x7fffffff)); - /* Make sure any pending DEC interrupt occurring while we did - * the above didn't re-enable the DEC */ - mb(); - asm volatile("mtdec %0" : : "r" (0x7fffffff)); - - /* We can now disable MSR_EE */ - local_irq_save(flags); - - /* Giveup the FPU & vec */ - enable_kernel_fp(); - -#ifdef CONFIG_ALTIVEC - if (cpu_has_feature(CPU_FTR_ALTIVEC)) - enable_kernel_altivec(); -#endif /* CONFIG_ALTIVEC */ - - /* Save & disable L2 and L3 caches */ - save_l3cr = _get_L3CR(); /* (returns -1 if not available) */ - save_l2cr = _get_L2CR(); /* (returns -1 if not available) */ - - /* Send the new speed command. My assumption is that this command - * will cause PLL_CFG[0..3] to be changed next time CPU goes to sleep - */ - pmu_request(&req, NULL, 6, PMU_CPU_SPEED, 'W', 'O', 'O', 'F', low_speed); - while (!req.complete) - pmu_poll(); - - /* Prepare the northbridge for the speed transition */ - pmac_call_feature(PMAC_FTR_SLEEP_STATE,NULL,1,1); - - /* Call low level code to backup CPU state and recover from - * hardware reset - */ - low_sleep_handler(); - - /* Restore the northbridge */ - pmac_call_feature(PMAC_FTR_SLEEP_STATE,NULL,1,0); - - /* Restore L2 cache */ - if (save_l2cr != 0xffffffff && (save_l2cr & L2CR_L2E) != 0) - _set_L2CR(save_l2cr); - /* Restore L3 cache */ - if (save_l3cr != 0xffffffff && (save_l3cr & L3CR_L3E) != 0) - _set_L3CR(save_l3cr); - - /* Restore userland MMU context */ - switch_mmu_context(NULL, current->active_mm); - -#ifdef DEBUG_FREQ - printk(KERN_DEBUG "HID1, after: %x\n", mfspr(SPRN_HID1)); -#endif - - /* Restore low level PMU operations */ - pmu_unlock(); - - /* - * Restore decrementer; we'll take a decrementer interrupt - * as soon as interrupts are re-enabled and the generic - * clockevents code will reprogram it with the right value. - */ - set_dec(1); - - /* Restore interrupts */ - mpic_cpu_set_priority(pic_prio); - - /* Let interrupts flow again ... */ - local_irq_restore(flags); - -#ifdef DEBUG_FREQ - debug_calc_bogomips(); -#endif - - pmu_resume(); - - preempt_enable(); - - return 0; -} - -static int do_set_cpu_speed(int speed_mode, int notify) -{ - struct cpufreq_freqs freqs; - unsigned long l3cr; - static unsigned long prev_l3cr; - - freqs.old = cur_freq; - freqs.new = (speed_mode == CPUFREQ_HIGH) ? hi_freq : low_freq; - freqs.cpu = smp_processor_id(); - - if (freqs.old == freqs.new) - return 0; - - if (notify) - cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); - if (speed_mode == CPUFREQ_LOW && - cpu_has_feature(CPU_FTR_L3CR)) { - l3cr = _get_L3CR(); - if (l3cr & L3CR_L3E) { - prev_l3cr = l3cr; - _set_L3CR(0); - } - } - set_speed_proc(speed_mode == CPUFREQ_LOW); - if (speed_mode == CPUFREQ_HIGH && - cpu_has_feature(CPU_FTR_L3CR)) { - l3cr = _get_L3CR(); - if ((prev_l3cr & L3CR_L3E) && l3cr != prev_l3cr) - _set_L3CR(prev_l3cr); - } - if (notify) - cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); - cur_freq = (speed_mode == CPUFREQ_HIGH) ? hi_freq : low_freq; - - return 0; -} - -static unsigned int pmac_cpufreq_get_speed(unsigned int cpu) -{ - return cur_freq; -} - -static int pmac_cpufreq_verify(struct cpufreq_policy *policy) -{ - return cpufreq_frequency_table_verify(policy, pmac_cpu_freqs); -} - -static int pmac_cpufreq_target( struct cpufreq_policy *policy, - unsigned int target_freq, - unsigned int relation) -{ - unsigned int newstate = 0; - int rc; - - if (cpufreq_frequency_table_target(policy, pmac_cpu_freqs, - target_freq, relation, &newstate)) - return -EINVAL; - - rc = do_set_cpu_speed(newstate, 1); - - ppc_proc_freq = cur_freq * 1000ul; - return rc; -} - -static int pmac_cpufreq_cpu_init(struct cpufreq_policy *policy) -{ - if (policy->cpu != 0) - return -ENODEV; - - policy->cpuinfo.transition_latency = transition_latency; - policy->cur = cur_freq; - - cpufreq_frequency_table_get_attr(pmac_cpu_freqs, policy->cpu); - return cpufreq_frequency_table_cpuinfo(policy, pmac_cpu_freqs); -} - -static u32 read_gpio(struct device_node *np) -{ - const u32 *reg = of_get_property(np, "reg", NULL); - u32 offset; - - if (reg == NULL) - return 0; - /* That works for all keylargos but shall be fixed properly - * some day... The problem is that it seems we can't rely - * on the "reg" property of the GPIO nodes, they are either - * relative to the base of KeyLargo or to the base of the - * GPIO space, and the device-tree doesn't help. - */ - offset = *reg; - if (offset < KEYLARGO_GPIO_LEVELS0) - offset += KEYLARGO_GPIO_LEVELS0; - return offset; -} - -static int pmac_cpufreq_suspend(struct cpufreq_policy *policy) -{ - /* Ok, this could be made a bit smarter, but let's be robust for now. We - * always force a speed change to high speed before sleep, to make sure - * we have appropriate voltage and/or bus speed for the wakeup process, - * and to make sure our loops_per_jiffies are "good enough", that is will - * not cause too short delays if we sleep in low speed and wake in high - * speed.. - */ - no_schedule = 1; - sleep_freq = cur_freq; - if (cur_freq == low_freq && !is_pmu_based) - do_set_cpu_speed(CPUFREQ_HIGH, 0); - return 0; -} - -static int pmac_cpufreq_resume(struct cpufreq_policy *policy) -{ - /* If we resume, first check if we have a get() function */ - if (get_speed_proc) - cur_freq = get_speed_proc(); - else - cur_freq = 0; - - /* We don't, hrm... we don't really know our speed here, best - * is that we force a switch to whatever it was, which is - * probably high speed due to our suspend() routine - */ - do_set_cpu_speed(sleep_freq == low_freq ? - CPUFREQ_LOW : CPUFREQ_HIGH, 0); - - ppc_proc_freq = cur_freq * 1000ul; - - no_schedule = 0; - return 0; -} - -static struct cpufreq_driver pmac_cpufreq_driver = { - .verify = pmac_cpufreq_verify, - .target = pmac_cpufreq_target, - .get = pmac_cpufreq_get_speed, - .init = pmac_cpufreq_cpu_init, - .suspend = pmac_cpufreq_suspend, - .resume = pmac_cpufreq_resume, - .flags = CPUFREQ_PM_NO_WARN, - .attr = pmac_cpu_freqs_attr, - .name = "powermac", - .owner = THIS_MODULE, -}; - - -static int pmac_cpufreq_init_MacRISC3(struct device_node *cpunode) -{ - struct device_node *volt_gpio_np = of_find_node_by_name(NULL, - "voltage-gpio"); - struct device_node *freq_gpio_np = of_find_node_by_name(NULL, - "frequency-gpio"); - struct device_node *slew_done_gpio_np = of_find_node_by_name(NULL, - "slewing-done"); - const u32 *value; - - /* - * Check to see if it's GPIO driven or PMU only - * - * The way we extract the GPIO address is slightly hackish, but it - * works well enough for now. We need to abstract the whole GPIO - * stuff sooner or later anyway - */ - - if (volt_gpio_np) - voltage_gpio = read_gpio(volt_gpio_np); - if (freq_gpio_np) - frequency_gpio = read_gpio(freq_gpio_np); - if (slew_done_gpio_np) - slew_done_gpio = read_gpio(slew_done_gpio_np); - - /* If we use the frequency GPIOs, calculate the min/max speeds based - * on the bus frequencies - */ - if (frequency_gpio && slew_done_gpio) { - int lenp, rc; - const u32 *freqs, *ratio; - - freqs = of_get_property(cpunode, "bus-frequencies", &lenp); - lenp /= sizeof(u32); - if (freqs == NULL || lenp != 2) { - printk(KERN_ERR "cpufreq: bus-frequencies incorrect or missing\n"); - return 1; - } - ratio = of_get_property(cpunode, "processor-to-bus-ratio*2", - NULL); - if (ratio == NULL) { - printk(KERN_ERR "cpufreq: processor-to-bus-ratio*2 missing\n"); - return 1; - } - - /* Get the min/max bus frequencies */ - low_freq = min(freqs[0], freqs[1]); - hi_freq = max(freqs[0], freqs[1]); - - /* Grrrr.. It _seems_ that the device-tree is lying on the low bus - * frequency, it claims it to be around 84Mhz on some models while - * it appears to be approx. 101Mhz on all. Let's hack around here... - * fortunately, we don't need to be too precise - */ - if (low_freq < 98000000) - low_freq = 101000000; - - /* Convert those to CPU core clocks */ - low_freq = (low_freq * (*ratio)) / 2000; - hi_freq = (hi_freq * (*ratio)) / 2000; - - /* Now we get the frequencies, we read the GPIO to see what is out current - * speed - */ - rc = pmac_call_feature(PMAC_FTR_READ_GPIO, NULL, frequency_gpio, 0); - cur_freq = (rc & 0x01) ? hi_freq : low_freq; - - set_speed_proc = gpios_set_cpu_speed; - return 1; - } - - /* If we use the PMU, look for the min & max frequencies in the - * device-tree - */ - value = of_get_property(cpunode, "min-clock-frequency", NULL); - if (!value) - return 1; - low_freq = (*value) / 1000; - /* The PowerBook G4 12" (PowerBook6,1) has an error in the device-tree - * here */ - if (low_freq < 100000) - low_freq *= 10; - - value = of_get_property(cpunode, "max-clock-frequency", NULL); - if (!value) - return 1; - hi_freq = (*value) / 1000; - set_speed_proc = pmu_set_cpu_speed; - is_pmu_based = 1; - - return 0; -} - -static int pmac_cpufreq_init_7447A(struct device_node *cpunode) -{ - struct device_node *volt_gpio_np; - - if (of_get_property(cpunode, "dynamic-power-step", NULL) == NULL) - return 1; - - volt_gpio_np = of_find_node_by_name(NULL, "cpu-vcore-select"); - if (volt_gpio_np) - voltage_gpio = read_gpio(volt_gpio_np); - if (!voltage_gpio){ - printk(KERN_ERR "cpufreq: missing cpu-vcore-select gpio\n"); - return 1; - } - - /* OF only reports the high frequency */ - hi_freq = cur_freq; - low_freq = cur_freq/2; - - /* Read actual frequency from CPU */ - cur_freq = dfs_get_cpu_speed(); - set_speed_proc = dfs_set_cpu_speed; - get_speed_proc = dfs_get_cpu_speed; - - return 0; -} - -static int pmac_cpufreq_init_750FX(struct device_node *cpunode) -{ - struct device_node *volt_gpio_np; - u32 pvr; - const u32 *value; - - if (of_get_property(cpunode, "dynamic-power-step", NULL) == NULL) - return 1; - - hi_freq = cur_freq; - value = of_get_property(cpunode, "reduced-clock-frequency", NULL); - if (!value) - return 1; - low_freq = (*value) / 1000; - - volt_gpio_np = of_find_node_by_name(NULL, "cpu-vcore-select"); - if (volt_gpio_np) - voltage_gpio = read_gpio(volt_gpio_np); - - pvr = mfspr(SPRN_PVR); - has_cpu_l2lve = !((pvr & 0xf00) == 0x100); - - set_speed_proc = cpu_750fx_cpu_speed; - get_speed_proc = cpu_750fx_get_cpu_speed; - cur_freq = cpu_750fx_get_cpu_speed(); - - return 0; -} - -/* Currently, we support the following machines: - * - * - Titanium PowerBook 1Ghz (PMU based, 667Mhz & 1Ghz) - * - Titanium PowerBook 800 (PMU based, 667Mhz & 800Mhz) - * - Titanium PowerBook 400 (PMU based, 300Mhz & 400Mhz) - * - Titanium PowerBook 500 (PMU based, 300Mhz & 500Mhz) - * - iBook2 500/600 (PMU based, 400Mhz & 500/600Mhz) - * - iBook2 700 (CPU based, 400Mhz & 700Mhz, support low voltage) - * - Recent MacRISC3 laptops - * - All new machines with 7447A CPUs - */ -static int __init pmac_cpufreq_setup(void) -{ - struct device_node *cpunode; - const u32 *value; - - if (strstr(cmd_line, "nocpufreq")) - return 0; - - /* Assume only one CPU */ - cpunode = of_find_node_by_type(NULL, "cpu"); - if (!cpunode) - goto out; - - /* Get current cpu clock freq */ - value = of_get_property(cpunode, "clock-frequency", NULL); - if (!value) - goto out; - cur_freq = (*value) / 1000; - transition_latency = CPUFREQ_ETERNAL; - - /* Check for 7447A based MacRISC3 */ - if (of_machine_is_compatible("MacRISC3") && - of_get_property(cpunode, "dynamic-power-step", NULL) && - PVR_VER(mfspr(SPRN_PVR)) == 0x8003) { - pmac_cpufreq_init_7447A(cpunode); - transition_latency = 8000000; - /* Check for other MacRISC3 machines */ - } else if (of_machine_is_compatible("PowerBook3,4") || - of_machine_is_compatible("PowerBook3,5") || - of_machine_is_compatible("MacRISC3")) { - pmac_cpufreq_init_MacRISC3(cpunode); - /* Else check for iBook2 500/600 */ - } else if (of_machine_is_compatible("PowerBook4,1")) { - hi_freq = cur_freq; - low_freq = 400000; - set_speed_proc = pmu_set_cpu_speed; - is_pmu_based = 1; - } - /* Else check for TiPb 550 */ - else if (of_machine_is_compatible("PowerBook3,3") && cur_freq == 550000) { - hi_freq = cur_freq; - low_freq = 500000; - set_speed_proc = pmu_set_cpu_speed; - is_pmu_based = 1; - } - /* Else check for TiPb 400 & 500 */ - else if (of_machine_is_compatible("PowerBook3,2")) { - /* We only know about the 400 MHz and the 500Mhz model - * they both have 300 MHz as low frequency - */ - if (cur_freq < 350000 || cur_freq > 550000) - goto out; - hi_freq = cur_freq; - low_freq = 300000; - set_speed_proc = pmu_set_cpu_speed; - is_pmu_based = 1; - } - /* Else check for 750FX */ - else if (PVR_VER(mfspr(SPRN_PVR)) == 0x7000) - pmac_cpufreq_init_750FX(cpunode); -out: - of_node_put(cpunode); - if (set_speed_proc == NULL) - return -ENODEV; - - pmac_cpu_freqs[CPUFREQ_LOW].frequency = low_freq; - pmac_cpu_freqs[CPUFREQ_HIGH].frequency = hi_freq; - ppc_proc_freq = cur_freq * 1000ul; - - printk(KERN_INFO "Registering PowerMac CPU frequency driver\n"); - printk(KERN_INFO "Low: %d Mhz, High: %d Mhz, Boot: %d Mhz\n", - low_freq/1000, hi_freq/1000, cur_freq/1000); - - return cpufreq_register_driver(&pmac_cpufreq_driver); -} - -module_init(pmac_cpufreq_setup); - diff --git a/arch/powerpc/platforms/powermac/cpufreq_64.c b/arch/powerpc/platforms/powermac/cpufreq_64.c deleted file mode 100644 index 9650c6029c8..00000000000 --- a/arch/powerpc/platforms/powermac/cpufreq_64.c +++ /dev/null @@ -1,747 +0,0 @@ -/* - * Copyright (C) 2002 - 2005 Benjamin Herrenschmidt <benh@kernel.crashing.org> - * and Markus Demleitner <msdemlei@cl.uni-heidelberg.de> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This driver adds basic cpufreq support for SMU & 970FX based G5 Macs, - * that is iMac G5 and latest single CPU desktop. - */ - -#undef DEBUG - -#include <linux/module.h> -#include <linux/types.h> -#include <linux/errno.h> -#include <linux/kernel.h> -#include <linux/delay.h> -#include <linux/sched.h> -#include <linux/cpufreq.h> -#include <linux/init.h> -#include <linux/completion.h> -#include <linux/mutex.h> -#include <asm/prom.h> -#include <asm/machdep.h> -#include <asm/irq.h> -#include <asm/sections.h> -#include <asm/cputable.h> -#include <asm/time.h> -#include <asm/smu.h> -#include <asm/pmac_pfunc.h> - -#define DBG(fmt...) pr_debug(fmt) - -/* see 970FX user manual */ - -#define SCOM_PCR 0x0aa001 /* PCR scom addr */ - -#define PCR_HILO_SELECT 0x80000000U /* 1 = PCR, 0 = PCRH */ -#define PCR_SPEED_FULL 0x00000000U /* 1:1 speed value */ -#define PCR_SPEED_HALF 0x00020000U /* 1:2 speed value */ -#define PCR_SPEED_QUARTER 0x00040000U /* 1:4 speed value */ -#define PCR_SPEED_MASK 0x000e0000U /* speed mask */ -#define PCR_SPEED_SHIFT 17 -#define PCR_FREQ_REQ_VALID 0x00010000U /* freq request valid */ -#define PCR_VOLT_REQ_VALID 0x00008000U /* volt request valid */ -#define PCR_TARGET_TIME_MASK 0x00006000U /* target time */ -#define PCR_STATLAT_MASK 0x00001f00U /* STATLAT value */ -#define PCR_SNOOPLAT_MASK 0x000000f0U /* SNOOPLAT value */ -#define PCR_SNOOPACC_MASK 0x0000000fU /* SNOOPACC value */ - -#define SCOM_PSR 0x408001 /* PSR scom addr */ -/* warning: PSR is a 64 bits register */ -#define PSR_CMD_RECEIVED 0x2000000000000000U /* command received */ -#define PSR_CMD_COMPLETED 0x1000000000000000U /* command completed */ -#define PSR_CUR_SPEED_MASK 0x0300000000000000U /* current speed */ -#define PSR_CUR_SPEED_SHIFT (56) - -/* - * The G5 only supports two frequencies (Quarter speed is not supported) - */ -#define CPUFREQ_HIGH 0 -#define CPUFREQ_LOW 1 - -static struct cpufreq_frequency_table g5_cpu_freqs[] = { - {CPUFREQ_HIGH, 0}, - {CPUFREQ_LOW, 0}, - {0, CPUFREQ_TABLE_END}, -}; - -static struct freq_attr* g5_cpu_freqs_attr[] = { - &cpufreq_freq_attr_scaling_available_freqs, - NULL, -}; - -/* Power mode data is an array of the 32 bits PCR values to use for - * the various frequencies, retrieved from the device-tree - */ -static int g5_pmode_cur; - -static void (*g5_switch_volt)(int speed_mode); -static int (*g5_switch_freq)(int speed_mode); -static int (*g5_query_freq)(void); - -static DEFINE_MUTEX(g5_switch_mutex); - -static unsigned long transition_latency; - -#ifdef CONFIG_PMAC_SMU - -static const u32 *g5_pmode_data; -static int g5_pmode_max; - -static struct smu_sdbp_fvt *g5_fvt_table; /* table of op. points */ -static int g5_fvt_count; /* number of op. points */ -static int g5_fvt_cur; /* current op. point */ - -/* - * SMU based voltage switching for Neo2 platforms - */ - -static void g5_smu_switch_volt(int speed_mode) -{ - struct smu_simple_cmd cmd; - - DECLARE_COMPLETION_ONSTACK(comp); - smu_queue_simple(&cmd, SMU_CMD_POWER_COMMAND, 8, smu_done_complete, - &comp, 'V', 'S', 'L', 'E', 'W', - 0xff, g5_fvt_cur+1, speed_mode); - wait_for_completion(&comp); -} - -/* - * Platform function based voltage/vdnap switching for Neo2 - */ - -static struct pmf_function *pfunc_set_vdnap0; -static struct pmf_function *pfunc_vdnap0_complete; - -static void g5_vdnap_switch_volt(int speed_mode) -{ - struct pmf_args args; - u32 slew, done = 0; - unsigned long timeout; - - slew = (speed_mode == CPUFREQ_LOW) ? 1 : 0; - args.count = 1; - args.u[0].p = &slew; - - pmf_call_one(pfunc_set_vdnap0, &args); - - /* It's an irq GPIO so we should be able to just block here, - * I'll do that later after I've properly tested the IRQ code for - * platform functions - */ - timeout = jiffies + HZ/10; - while(!time_after(jiffies, timeout)) { - args.count = 1; - args.u[0].p = &done; - pmf_call_one(pfunc_vdnap0_complete, &args); - if (done) - break; - msleep(1); - } - if (done == 0) - printk(KERN_WARNING "cpufreq: Timeout in clock slewing !\n"); -} - - -/* - * SCOM based frequency switching for 970FX rev3 - */ -static int g5_scom_switch_freq(int speed_mode) -{ - unsigned long flags; - int to; - - /* If frequency is going up, first ramp up the voltage */ - if (speed_mode < g5_pmode_cur) - g5_switch_volt(speed_mode); - - local_irq_save(flags); - - /* Clear PCR high */ - scom970_write(SCOM_PCR, 0); - /* Clear PCR low */ - scom970_write(SCOM_PCR, PCR_HILO_SELECT | 0); - /* Set PCR low */ - scom970_write(SCOM_PCR, PCR_HILO_SELECT | - g5_pmode_data[speed_mode]); - - /* Wait for completion */ - for (to = 0; to < 10; to++) { - unsigned long psr = scom970_read(SCOM_PSR); - - if ((psr & PSR_CMD_RECEIVED) == 0 && - (((psr >> PSR_CUR_SPEED_SHIFT) ^ - (g5_pmode_data[speed_mode] >> PCR_SPEED_SHIFT)) & 0x3) - == 0) - break; - if (psr & PSR_CMD_COMPLETED) - break; - udelay(100); - } - - local_irq_restore(flags); - - /* If frequency is going down, last ramp the voltage */ - if (speed_mode > g5_pmode_cur) - g5_switch_volt(speed_mode); - - g5_pmode_cur = speed_mode; - ppc_proc_freq = g5_cpu_freqs[speed_mode].frequency * 1000ul; - - return 0; -} - -static int g5_scom_query_freq(void) -{ - unsigned long psr = scom970_read(SCOM_PSR); - int i; - - for (i = 0; i <= g5_pmode_max; i++) - if ((((psr >> PSR_CUR_SPEED_SHIFT) ^ - (g5_pmode_data[i] >> PCR_SPEED_SHIFT)) & 0x3) == 0) - break; - return i; -} - -/* - * Fake voltage switching for platforms with missing support - */ - -static void g5_dummy_switch_volt(int speed_mode) -{ -} - -#endif /* CONFIG_PMAC_SMU */ - -/* - * Platform function based voltage switching for PowerMac7,2 & 7,3 - */ - -static struct pmf_function *pfunc_cpu0_volt_high; -static struct pmf_function *pfunc_cpu0_volt_low; -static struct pmf_function *pfunc_cpu1_volt_high; -static struct pmf_function *pfunc_cpu1_volt_low; - -static void g5_pfunc_switch_volt(int speed_mode) -{ - if (speed_mode == CPUFREQ_HIGH) { - if (pfunc_cpu0_volt_high) - pmf_call_one(pfunc_cpu0_volt_high, NULL); - if (pfunc_cpu1_volt_high) - pmf_call_one(pfunc_cpu1_volt_high, NULL); - } else { - if (pfunc_cpu0_volt_low) - pmf_call_one(pfunc_cpu0_volt_low, NULL); - if (pfunc_cpu1_volt_low) - pmf_call_one(pfunc_cpu1_volt_low, NULL); - } - msleep(10); /* should be faster , to fix */ -} - -/* - * Platform function based frequency switching for PowerMac7,2 & 7,3 - */ - -static struct pmf_function *pfunc_cpu_setfreq_high; -static struct pmf_function *pfunc_cpu_setfreq_low; -static struct pmf_function *pfunc_cpu_getfreq; -static struct pmf_function *pfunc_slewing_done; - -static int g5_pfunc_switch_freq(int speed_mode) -{ - struct pmf_args args; - u32 done = 0; - unsigned long timeout; - int rc; - - DBG("g5_pfunc_switch_freq(%d)\n", speed_mode); - - /* If frequency is going up, first ramp up the voltage */ - if (speed_mode < g5_pmode_cur) - g5_switch_volt(speed_mode); - - /* Do it */ - if (speed_mode == CPUFREQ_HIGH) - rc = pmf_call_one(pfunc_cpu_setfreq_high, NULL); - else - rc = pmf_call_one(pfunc_cpu_setfreq_low, NULL); - - if (rc) - printk(KERN_WARNING "cpufreq: pfunc switch error %d\n", rc); - - /* It's an irq GPIO so we should be able to just block here, - * I'll do that later after I've properly tested the IRQ code for - * platform functions - */ - timeout = jiffies + HZ/10; - while(!time_after(jiffies, timeout)) { - args.count = 1; - args.u[0].p = &done; - pmf_call_one(pfunc_slewing_done, &args); - if (done) - break; - msleep(1); - } - if (done == 0) - printk(KERN_WARNING "cpufreq: Timeout in clock slewing !\n"); - - /* If frequency is going down, last ramp the voltage */ - if (speed_mode > g5_pmode_cur) - g5_switch_volt(speed_mode); - - g5_pmode_cur = speed_mode; - ppc_proc_freq = g5_cpu_freqs[speed_mode].frequency * 1000ul; - - return 0; -} - -static int g5_pfunc_query_freq(void) -{ - struct pmf_args args; - u32 val = 0; - - args.count = 1; - args.u[0].p = &val; - pmf_call_one(pfunc_cpu_getfreq, &args); - return val ? CPUFREQ_HIGH : CPUFREQ_LOW; -} - - -/* - * Common interface to the cpufreq core - */ - -static int g5_cpufreq_verify(struct cpufreq_policy *policy) -{ - return cpufreq_frequency_table_verify(policy, g5_cpu_freqs); -} - -static int g5_cpufreq_target(struct cpufreq_policy *policy, - unsigned int target_freq, unsigned int relation) -{ - unsigned int newstate = 0; - struct cpufreq_freqs freqs; - int rc; - - if (cpufreq_frequency_table_target(policy, g5_cpu_freqs, - target_freq, relation, &newstate)) - return -EINVAL; - - if (g5_pmode_cur == newstate) - return 0; - - mutex_lock(&g5_switch_mutex); - - freqs.old = g5_cpu_freqs[g5_pmode_cur].frequency; - freqs.new = g5_cpu_freqs[newstate].frequency; - freqs.cpu = 0; - - cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); - rc = g5_switch_freq(newstate); - cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); - - mutex_unlock(&g5_switch_mutex); - - return rc; -} - -static unsigned int g5_cpufreq_get_speed(unsigned int cpu) -{ - return g5_cpu_freqs[g5_pmode_cur].frequency; -} - -static int g5_cpufreq_cpu_init(struct cpufreq_policy *policy) -{ - policy->cpuinfo.transition_latency = transition_latency; - policy->cur = g5_cpu_freqs[g5_query_freq()].frequency; - /* secondary CPUs are tied to the primary one by the - * cpufreq core if in the secondary policy we tell it that - * it actually must be one policy together with all others. */ - cpumask_copy(policy->cpus, cpu_online_mask); - cpufreq_frequency_table_get_attr(g5_cpu_freqs, policy->cpu); - - return cpufreq_frequency_table_cpuinfo(policy, - g5_cpu_freqs); -} - - -static struct cpufreq_driver g5_cpufreq_driver = { - .name = "powermac", - .owner = THIS_MODULE, - .flags = CPUFREQ_CONST_LOOPS, - .init = g5_cpufreq_cpu_init, - .verify = g5_cpufreq_verify, - .target = g5_cpufreq_target, - .get = g5_cpufreq_get_speed, - .attr = g5_cpu_freqs_attr, -}; - - -#ifdef CONFIG_PMAC_SMU - -static int __init g5_neo2_cpufreq_init(struct device_node *cpus) -{ - struct device_node *cpunode; - unsigned int psize, ssize; - unsigned long max_freq; - char *freq_method, *volt_method; - const u32 *valp; - u32 pvr_hi; - int use_volts_vdnap = 0; - int use_volts_smu = 0; - int rc = -ENODEV; - - /* Check supported platforms */ - if (of_machine_is_compatible("PowerMac8,1") || - of_machine_is_compatible("PowerMac8,2") || - of_machine_is_compatible("PowerMac9,1")) - use_volts_smu = 1; - else if (of_machine_is_compatible("PowerMac11,2")) - use_volts_vdnap = 1; - else - return -ENODEV; - - /* Get first CPU node */ - for (cpunode = NULL; - (cpunode = of_get_next_child(cpus, cpunode)) != NULL;) { - const u32 *reg = of_get_property(cpunode, "reg", NULL); - if (reg == NULL || (*reg) != 0) - continue; - if (!strcmp(cpunode->type, "cpu")) - break; - } - if (cpunode == NULL) { - printk(KERN_ERR "cpufreq: Can't find any CPU 0 node\n"); - return -ENODEV; - } - - /* Check 970FX for now */ - valp = of_get_property(cpunode, "cpu-version", NULL); - if (!valp) { - DBG("No cpu-version property !\n"); - goto bail_noprops; - } - pvr_hi = (*valp) >> 16; - if (pvr_hi != 0x3c && pvr_hi != 0x44) { - printk(KERN_ERR "cpufreq: Unsupported CPU version\n"); - goto bail_noprops; - } - - /* Look for the powertune data in the device-tree */ - g5_pmode_data = of_get_property(cpunode, "power-mode-data",&psize); - if (!g5_pmode_data) { - DBG("No power-mode-data !\n"); - goto bail_noprops; - } - g5_pmode_max = psize / sizeof(u32) - 1; - - if (use_volts_smu) { - const struct smu_sdbp_header *shdr; - - /* Look for the FVT table */ - shdr = smu_get_sdb_partition(SMU_SDB_FVT_ID, NULL); - if (!shdr) - goto bail_noprops; - g5_fvt_table = (struct smu_sdbp_fvt *)&shdr[1]; - ssize = (shdr->len * sizeof(u32)) - - sizeof(struct smu_sdbp_header); - g5_fvt_count = ssize / sizeof(struct smu_sdbp_fvt); - g5_fvt_cur = 0; - - /* Sanity checking */ - if (g5_fvt_count < 1 || g5_pmode_max < 1) - goto bail_noprops; - - g5_switch_volt = g5_smu_switch_volt; - volt_method = "SMU"; - } else if (use_volts_vdnap) { - struct device_node *root; - - root = of_find_node_by_path("/"); - if (root == NULL) { - printk(KERN_ERR "cpufreq: Can't find root of " - "device tree\n"); - goto bail_noprops; - } - pfunc_set_vdnap0 = pmf_find_function(root, "set-vdnap0"); - pfunc_vdnap0_complete = - pmf_find_function(root, "slewing-done"); - if (pfunc_set_vdnap0 == NULL || - pfunc_vdnap0_complete == NULL) { - printk(KERN_ERR "cpufreq: Can't find required " - "platform function\n"); - goto bail_noprops; - } - - g5_switch_volt = g5_vdnap_switch_volt; - volt_method = "GPIO"; - } else { - g5_switch_volt = g5_dummy_switch_volt; - volt_method = "none"; - } - - /* - * From what I see, clock-frequency is always the maximal frequency. - * The current driver can not slew sysclk yet, so we really only deal - * with powertune steps for now. We also only implement full freq and - * half freq in this version. So far, I haven't yet seen a machine - * supporting anything else. - */ - valp = of_get_property(cpunode, "clock-frequency", NULL); - if (!valp) - return -ENODEV; - max_freq = (*valp)/1000; - g5_cpu_freqs[0].frequency = max_freq; - g5_cpu_freqs[1].frequency = max_freq/2; - - /* Set callbacks */ - transition_latency = 12000; - g5_switch_freq = g5_scom_switch_freq; - g5_query_freq = g5_scom_query_freq; - freq_method = "SCOM"; - - /* Force apply current frequency to make sure everything is in - * sync (voltage is right for example). Firmware may leave us with - * a strange setting ... - */ - g5_switch_volt(CPUFREQ_HIGH); - msleep(10); - g5_pmode_cur = -1; - g5_switch_freq(g5_query_freq()); - - printk(KERN_INFO "Registering G5 CPU frequency driver\n"); - printk(KERN_INFO "Frequency method: %s, Voltage method: %s\n", - freq_method, volt_method); - printk(KERN_INFO "Low: %d Mhz, High: %d Mhz, Cur: %d MHz\n", - g5_cpu_freqs[1].frequency/1000, - g5_cpu_freqs[0].frequency/1000, - g5_cpu_freqs[g5_pmode_cur].frequency/1000); - - rc = cpufreq_register_driver(&g5_cpufreq_driver); - - /* We keep the CPU node on hold... hopefully, Apple G5 don't have - * hotplug CPU with a dynamic device-tree ... - */ - return rc; - - bail_noprops: - of_node_put(cpunode); - - return rc; -} - -#endif /* CONFIG_PMAC_SMU */ - - -static int __init g5_pm72_cpufreq_init(struct device_node *cpus) -{ - struct device_node *cpuid = NULL, *hwclock = NULL, *cpunode = NULL; - const u8 *eeprom = NULL; - const u32 *valp; - u64 max_freq, min_freq, ih, il; - int has_volt = 1, rc = 0; - - DBG("cpufreq: Initializing for PowerMac7,2, PowerMac7,3 and" - " RackMac3,1...\n"); - - /* Get first CPU node */ - for (cpunode = NULL; - (cpunode = of_get_next_child(cpus, cpunode)) != NULL;) { - if (!strcmp(cpunode->type, "cpu")) - break; - } - if (cpunode == NULL) { - printk(KERN_ERR "cpufreq: Can't find any CPU node\n"); - return -ENODEV; - } - - /* Lookup the cpuid eeprom node */ - cpuid = of_find_node_by_path("/u3@0,f8000000/i2c@f8001000/cpuid@a0"); - if (cpuid != NULL) - eeprom = of_get_property(cpuid, "cpuid", NULL); - if (eeprom == NULL) { - printk(KERN_ERR "cpufreq: Can't find cpuid EEPROM !\n"); - rc = -ENODEV; - goto bail; - } - - /* Lookup the i2c hwclock */ - for (hwclock = NULL; - (hwclock = of_find_node_by_name(hwclock, "i2c-hwclock")) != NULL;){ - const char *loc = of_get_property(hwclock, - "hwctrl-location", NULL); - if (loc == NULL) - continue; - if (strcmp(loc, "CPU CLOCK")) - continue; - if (!of_get_property(hwclock, "platform-get-frequency", NULL)) - continue; - break; - } - if (hwclock == NULL) { - printk(KERN_ERR "cpufreq: Can't find i2c clock chip !\n"); - rc = -ENODEV; - goto bail; - } - - DBG("cpufreq: i2c clock chip found: %s\n", hwclock->full_name); - - /* Now get all the platform functions */ - pfunc_cpu_getfreq = - pmf_find_function(hwclock, "get-frequency"); - pfunc_cpu_setfreq_high = - pmf_find_function(hwclock, "set-frequency-high"); - pfunc_cpu_setfreq_low = - pmf_find_function(hwclock, "set-frequency-low"); - pfunc_slewing_done = - pmf_find_function(hwclock, "slewing-done"); - pfunc_cpu0_volt_high = - pmf_find_function(hwclock, "set-voltage-high-0"); - pfunc_cpu0_volt_low = - pmf_find_function(hwclock, "set-voltage-low-0"); - pfunc_cpu1_volt_high = - pmf_find_function(hwclock, "set-voltage-high-1"); - pfunc_cpu1_volt_low = - pmf_find_function(hwclock, "set-voltage-low-1"); - - /* Check we have minimum requirements */ - if (pfunc_cpu_getfreq == NULL || pfunc_cpu_setfreq_high == NULL || - pfunc_cpu_setfreq_low == NULL || pfunc_slewing_done == NULL) { - printk(KERN_ERR "cpufreq: Can't find platform functions !\n"); - rc = -ENODEV; - goto bail; - } - - /* Check that we have complete sets */ - if (pfunc_cpu0_volt_high == NULL || pfunc_cpu0_volt_low == NULL) { - pmf_put_function(pfunc_cpu0_volt_high); - pmf_put_function(pfunc_cpu0_volt_low); - pfunc_cpu0_volt_high = pfunc_cpu0_volt_low = NULL; - has_volt = 0; - } - if (!has_volt || - pfunc_cpu1_volt_high == NULL || pfunc_cpu1_volt_low == NULL) { - pmf_put_function(pfunc_cpu1_volt_high); - pmf_put_function(pfunc_cpu1_volt_low); - pfunc_cpu1_volt_high = pfunc_cpu1_volt_low = NULL; - } - - /* Note: The device tree also contains a "platform-set-values" - * function for which I haven't quite figured out the usage. It - * might have to be called on init and/or wakeup, I'm not too sure - * but things seem to work fine without it so far ... - */ - - /* Get max frequency from device-tree */ - valp = of_get_property(cpunode, "clock-frequency", NULL); - if (!valp) { - printk(KERN_ERR "cpufreq: Can't find CPU frequency !\n"); - rc = -ENODEV; - goto bail; - } - - max_freq = (*valp)/1000; - - /* Now calculate reduced frequency by using the cpuid input freq - * ratio. This requires 64 bits math unless we are willing to lose - * some precision - */ - ih = *((u32 *)(eeprom + 0x10)); - il = *((u32 *)(eeprom + 0x20)); - - /* Check for machines with no useful settings */ - if (il == ih) { - printk(KERN_WARNING "cpufreq: No low frequency mode available" - " on this model !\n"); - rc = -ENODEV; - goto bail; - } - - min_freq = 0; - if (ih != 0 && il != 0) - min_freq = (max_freq * il) / ih; - - /* Sanity check */ - if (min_freq >= max_freq || min_freq < 1000) { - printk(KERN_ERR "cpufreq: Can't calculate low frequency !\n"); - rc = -ENXIO; - goto bail; - } - g5_cpu_freqs[0].frequency = max_freq; - g5_cpu_freqs[1].frequency = min_freq; - - /* Set callbacks */ - transition_latency = CPUFREQ_ETERNAL; - g5_switch_volt = g5_pfunc_switch_volt; - g5_switch_freq = g5_pfunc_switch_freq; - g5_query_freq = g5_pfunc_query_freq; - - /* Force apply current frequency to make sure everything is in - * sync (voltage is right for example). Firmware may leave us with - * a strange setting ... - */ - g5_switch_volt(CPUFREQ_HIGH); - msleep(10); - g5_pmode_cur = -1; - g5_switch_freq(g5_query_freq()); - - printk(KERN_INFO "Registering G5 CPU frequency driver\n"); - printk(KERN_INFO "Frequency method: i2c/pfunc, " - "Voltage method: %s\n", has_volt ? "i2c/pfunc" : "none"); - printk(KERN_INFO "Low: %d Mhz, High: %d Mhz, Cur: %d MHz\n", - g5_cpu_freqs[1].frequency/1000, - g5_cpu_freqs[0].frequency/1000, - g5_cpu_freqs[g5_pmode_cur].frequency/1000); - - rc = cpufreq_register_driver(&g5_cpufreq_driver); - bail: - if (rc != 0) { - pmf_put_function(pfunc_cpu_getfreq); - pmf_put_function(pfunc_cpu_setfreq_high); - pmf_put_function(pfunc_cpu_setfreq_low); - pmf_put_function(pfunc_slewing_done); - pmf_put_function(pfunc_cpu0_volt_high); - pmf_put_function(pfunc_cpu0_volt_low); - pmf_put_function(pfunc_cpu1_volt_high); - pmf_put_function(pfunc_cpu1_volt_low); - } - of_node_put(hwclock); - of_node_put(cpuid); - of_node_put(cpunode); - - return rc; -} - -static int __init g5_cpufreq_init(void) -{ - struct device_node *cpus; - int rc = 0; - - cpus = of_find_node_by_path("/cpus"); - if (cpus == NULL) { - DBG("No /cpus node !\n"); - return -ENODEV; - } - - if (of_machine_is_compatible("PowerMac7,2") || - of_machine_is_compatible("PowerMac7,3") || - of_machine_is_compatible("RackMac3,1")) - rc = g5_pm72_cpufreq_init(cpus); -#ifdef CONFIG_PMAC_SMU - else - rc = g5_neo2_cpufreq_init(cpus); -#endif /* CONFIG_PMAC_SMU */ - - of_node_put(cpus); - return rc; -} - -module_init(g5_cpufreq_init); - - -MODULE_LICENSE("GPL"); diff --git a/arch/powerpc/platforms/powermac/low_i2c.c b/arch/powerpc/platforms/powermac/low_i2c.c index fc536f2971c..7553b6a77c6 100644 --- a/arch/powerpc/platforms/powermac/low_i2c.c +++ b/arch/powerpc/platforms/powermac/low_i2c.c @@ -452,7 +452,7 @@ static int kw_i2c_xfer(struct pmac_i2c_bus *bus, u8 addrdir, int subsize, */ if (use_irq) { /* Clear completion */ - INIT_COMPLETION(host->complete); + reinit_completion(&host->complete); /* Ack stale interrupts */ kw_write_reg(reg_isr, kw_read_reg(reg_isr)); /* Arm timeout */ @@ -717,7 +717,7 @@ static int pmu_i2c_xfer(struct pmac_i2c_bus *bus, u8 addrdir, int subsize, return -EINVAL; } - INIT_COMPLETION(comp); + reinit_completion(&comp); req->data[0] = PMU_I2C_CMD; req->reply[0] = 0xff; req->nbytes = sizeof(struct pmu_i2c_hdr) + 1; @@ -748,7 +748,7 @@ static int pmu_i2c_xfer(struct pmac_i2c_bus *bus, u8 addrdir, int subsize, hdr->bus = PMU_I2C_BUS_STATUS; - INIT_COMPLETION(comp); + reinit_completion(&comp); req->data[0] = PMU_I2C_CMD; req->reply[0] = 0xff; req->nbytes = 2; diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c index 2b8af75abc2..cf7009b8c7b 100644 --- a/arch/powerpc/platforms/powermac/pci.c +++ b/arch/powerpc/platforms/powermac/pci.c @@ -824,6 +824,7 @@ static void __init parse_region_decode(struct pci_controller *hose, hose->mem_resources[cur].name = hose->dn->full_name; hose->mem_resources[cur].start = base; hose->mem_resources[cur].end = end; + hose->mem_offset[cur] = 0; DBG(" %d: 0x%08lx-0x%08lx\n", cur, base, end); } else { DBG(" : -0x%08lx\n", end); @@ -866,7 +867,6 @@ static void __init setup_u3_ht(struct pci_controller* hose) hose->io_resource.start = 0; hose->io_resource.end = 0x003fffff; hose->io_resource.flags = IORESOURCE_IO; - hose->pci_mem_offset = 0; hose->first_busno = 0; hose->last_busno = 0xef; diff --git a/arch/powerpc/platforms/powermac/pfunc_base.c b/arch/powerpc/platforms/powermac/pfunc_base.c index f5e3cda6660..e49d07f3d54 100644 --- a/arch/powerpc/platforms/powermac/pfunc_base.c +++ b/arch/powerpc/platforms/powermac/pfunc_base.c @@ -4,6 +4,7 @@ #include <linux/kernel.h> #include <linux/interrupt.h> #include <linux/spinlock.h> +#include <linux/of_irq.h> #include <asm/pmac_feature.h> #include <asm/pmac_pfunc.h> diff --git a/arch/powerpc/platforms/powermac/pfunc_core.c b/arch/powerpc/platforms/powermac/pfunc_core.c index d588e48dff7..43075081721 100644 --- a/arch/powerpc/platforms/powermac/pfunc_core.c +++ b/arch/powerpc/platforms/powermac/pfunc_core.c @@ -5,7 +5,6 @@ * FIXME: LOCKING !!! */ -#include <linux/init.h> #include <linux/delay.h> #include <linux/kernel.h> #include <linux/spinlock.h> diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c index 31036b56670..4c24bf60d39 100644 --- a/arch/powerpc/platforms/powermac/pic.c +++ b/arch/powerpc/platforms/powermac/pic.c @@ -393,8 +393,8 @@ static void __init pmac_pic_probe_oldstyle(void) #endif } -int of_irq_map_oldworld(struct device_node *device, int index, - struct of_irq *out_irq) +int of_irq_parse_oldworld(struct device_node *device, int index, + struct of_phandle_args *out_irq) { const u32 *ints = NULL; int intlen; @@ -422,9 +422,9 @@ int of_irq_map_oldworld(struct device_node *device, int index, if (index >= intlen) return -EINVAL; - out_irq->controller = NULL; - out_irq->specifier[0] = ints[index]; - out_irq->size = 1; + out_irq->np = NULL; + out_irq->args[0] = ints[index]; + out_irq->args_count = 1; return 0; } diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index bdb738a69e4..5cbd4d67d5c 100644 --- a/arch/powerpc/platforms/powermac/smp.c +++ b/arch/powerpc/platforms/powermac/smp.c @@ -192,7 +192,7 @@ static int psurge_secondary_ipi_init(void) { int rc = -ENOMEM; - psurge_host = irq_domain_add_nomap(NULL, 0, &psurge_host_ops, NULL); + psurge_host = irq_domain_add_nomap(NULL, ~0, &psurge_host_ops, NULL); if (psurge_host) psurge_secondary_virq = irq_create_direct_mapping(psurge_host); @@ -885,7 +885,7 @@ static int smp_core99_cpu_notify(struct notifier_block *self, return NOTIFY_OK; } -static struct notifier_block __cpuinitdata smp_core99_cpu_nb = { +static struct notifier_block smp_core99_cpu_nb = { .notifier_call = smp_core99_cpu_notify, }; #endif /* CONFIG_HOTPLUG_CPU */ diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig index 74fea5c2183..45a8ed0585c 100644 --- a/arch/powerpc/platforms/powernv/Kconfig +++ b/arch/powerpc/platforms/powernv/Kconfig @@ -6,6 +6,18 @@ config PPC_POWERNV select PPC_ICP_NATIVE select PPC_P7_NAP select PPC_PCI_CHOICE if EMBEDDED + select EPAPR_BOOT + select PPC_INDIRECT_PIO + select PPC_UDBG_16550 + select PPC_SCOM + select ARCH_RANDOM + select CPU_FREQ + select CPU_FREQ_GOV_PERFORMANCE + select CPU_FREQ_GOV_POWERSAVE + select CPU_FREQ_GOV_USERSPACE + select CPU_FREQ_GOV_ONDEMAND + select CPU_FREQ_GOV_CONSERVATIVE + select PPC_DOORBELL default y config PPC_POWERNV_RTAS diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile index bcc3cb48a44..4ad227d04c1 100644 --- a/arch/powerpc/platforms/powernv/Makefile +++ b/arch/powerpc/platforms/powernv/Makefile @@ -1,5 +1,10 @@ -obj-y += setup.o opal-takeover.o opal-wrappers.o opal.o -obj-y += opal-rtc.o opal-nvram.o +obj-y += setup.o opal-wrappers.o opal.o opal-async.o +obj-y += opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o +obj-y += rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o +obj-y += opal-msglog.o -obj-$(CONFIG_SMP) += smp.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_PPC_SCOM) += opal-xscom.o +obj-$(CONFIG_MEMORY_FAILURE) += opal-memory-errors.o diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c new file mode 100644 index 00000000000..8ad0c5b891f --- /dev/null +++ b/arch/powerpc/platforms/powernv/eeh-ioda.c @@ -0,0 +1,890 @@ +/* + * 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/bootmem.h> +#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 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_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) +{ + s64 ret; + u32 pe_no; + struct pci_controller *hose = pe->phb; + struct pnv_phb *phb = hose->private_data; + + /* 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; + } + + pe_no = pe->addr; + switch (option) { + case EEH_OPT_DISABLE: + ret = -EEXIST; + break; + case EEH_OPT_ENABLE: + ret = 0; + break; + case EEH_OPT_THAW_MMIO: + ret = opal_pci_eeh_freeze_clear(phb->opal_id, pe_no, + OPAL_EEH_ACTION_CLEAR_FREEZE_MMIO); + if (ret) { + pr_warning("%s: Failed to enable MMIO for " + "PHB#%x-PE#%x, err=%lld\n", + __func__, hose->global_number, pe_no, ret); + return -EIO; + } + + break; + case EEH_OPT_THAW_DMA: + ret = opal_pci_eeh_freeze_clear(phb->opal_id, pe_no, + OPAL_EEH_ACTION_CLEAR_FREEZE_DMA); + if (ret) { + pr_warning("%s: Failed to enable DMA for " + "PHB#%x-PE#%x, err=%lld\n", + __func__, hose->global_number, pe_no, ret); + return -EIO; + } + + break; + default: + pr_warning("%s: Invalid option %d\n", __func__, option); + return -EINVAL; + } + + return ret; +} + +static void ioda_eeh_phb_diag(struct pci_controller *hose) +{ + struct pnv_phb *phb = hose->private_data; + long rc; + + rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob, + PNV_PCI_DIAG_BUF_SIZE); + if (rc != OPAL_SUCCESS) { + pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n", + __func__, hose->global_number, rc); + return; + } + + pnv_pci_dump_phb_diag_data(hose, phb->diag.blob); +} + +/** + * 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) +{ + s64 ret = 0; + u8 fstate; + __be16 pcierr; + u32 pe_no; + int result; + struct pci_controller *hose = pe->phb; + struct pnv_phb *phb = hose->private_data; + + /* + * Sanity check on PE address. The PHB PE address should + * be zero. + */ + 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 EEH_STATE_NOT_SUPPORT; + } + + /* + * If we're in middle of PE reset, return normal + * state to keep EEH core going. For PHB reset, we + * still expect to have fenced PHB cleared with + * PHB reset. + */ + if (!(pe->type & EEH_PE_PHB) && + (pe->state & EEH_PE_RESET)) { + result = (EEH_STATE_MMIO_ACTIVE | + EEH_STATE_DMA_ACTIVE | + EEH_STATE_MMIO_ENABLED | + EEH_STATE_DMA_ENABLED); + return result; + } + + /* Retrieve PE status through OPAL */ + pe_no = pe->addr; + ret = opal_pci_eeh_freeze_status(phb->opal_id, pe_no, + &fstate, &pcierr, NULL); + if (ret) { + pr_err("%s: Failed to get EEH status on " + "PHB#%x-PE#%x\n, err=%lld\n", + __func__, hose->global_number, pe_no, ret); + return EEH_STATE_NOT_SUPPORT; + } + + /* Check PHB status */ + if (pe->type & EEH_PE_PHB) { + result = 0; + result &= ~EEH_STATE_RESET_ACTIVE; + + if (be16_to_cpu(pcierr) != OPAL_EEH_PHB_ERROR) { + result |= EEH_STATE_MMIO_ACTIVE; + result |= EEH_STATE_DMA_ACTIVE; + result |= EEH_STATE_MMIO_ENABLED; + result |= EEH_STATE_DMA_ENABLED; + } else if (!(pe->state & EEH_PE_ISOLATED)) { + eeh_pe_state_mark(pe, EEH_PE_ISOLATED); + ioda_eeh_phb_diag(hose); + } + + return result; + } + + /* Parse result out */ + result = 0; + switch (fstate) { + case OPAL_EEH_STOPPED_NOT_FROZEN: + result &= ~EEH_STATE_RESET_ACTIVE; + result |= EEH_STATE_MMIO_ACTIVE; + result |= EEH_STATE_DMA_ACTIVE; + result |= EEH_STATE_MMIO_ENABLED; + result |= EEH_STATE_DMA_ENABLED; + break; + case OPAL_EEH_STOPPED_MMIO_FREEZE: + result &= ~EEH_STATE_RESET_ACTIVE; + result |= EEH_STATE_DMA_ACTIVE; + result |= EEH_STATE_DMA_ENABLED; + break; + case OPAL_EEH_STOPPED_DMA_FREEZE: + result &= ~EEH_STATE_RESET_ACTIVE; + result |= EEH_STATE_MMIO_ACTIVE; + result |= EEH_STATE_MMIO_ENABLED; + break; + case OPAL_EEH_STOPPED_MMIO_DMA_FREEZE: + result &= ~EEH_STATE_RESET_ACTIVE; + 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: + pr_warning("%s: Unexpected EEH status 0x%x " + "on PHB#%x-PE#%x\n", + __func__, fstate, hose->global_number, pe_no); + } + + /* Dump PHB diag-data for frozen PE */ + if (result != EEH_STATE_NOT_SUPPORT && + (result & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) != + (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE) && + !(pe->state & EEH_PE_ISOLATED)) { + eeh_pe_state_mark(pe, EEH_PE_ISOLATED); + ioda_eeh_phb_diag(hose); + } + + return result; +} + +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_PHB_COMPLETE, + OPAL_ASSERT_RESET); + else if (option == EEH_RESET_DEACTIVATE) + rc = opal_pci_reset(phb->opal_id, + OPAL_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_PCI_FUNDAMENTAL_RESET, + OPAL_ASSERT_RESET); + else if (option == EEH_RESET_HOT) + rc = opal_pci_reset(phb->opal_id, + OPAL_PCI_HOT_RESET, + OPAL_ASSERT_RESET); + else if (option == EEH_RESET_DEACTIVATE) + rc = opal_pci_reset(phb->opal_id, + OPAL_PCI_HOT_RESET, + 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 { + 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_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 void ioda_eeh_hub_diag_common(struct OpalIoP7IOCErrorData *data) +{ + /* GEM */ + pr_info(" GEM XFIR: %016llx\n", data->gemXfir); + pr_info(" GEM RFIR: %016llx\n", data->gemRfir); + pr_info(" GEM RIRQFIR: %016llx\n", data->gemRirqfir); + pr_info(" GEM Mask: %016llx\n", data->gemMask); + pr_info(" GEM RWOF: %016llx\n", data->gemRwof); + + /* LEM */ + pr_info(" LEM FIR: %016llx\n", data->lemFir); + pr_info(" LEM Error Mask: %016llx\n", data->lemErrMask); + pr_info(" LEM Action 0: %016llx\n", data->lemAction0); + pr_info(" LEM Action 1: %016llx\n", data->lemAction1); + pr_info(" LEM WOF: %016llx\n", 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_warning("%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); + pr_info(" RGC Status: %016llx\n", data->rgc.rgcStatus); + pr_info(" RGC LDCP: %016llx\n", 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); + pr_info(" BI LDCP 0: %016llx\n", data->bi.biLdcp0); + pr_info(" BI LDCP 1: %016llx\n", data->bi.biLdcp1); + pr_info(" BI LDCP 2: %016llx\n", data->bi.biLdcp2); + pr_info(" BI Fence Status: %016llx\n", data->bi.biFenceStatus); + break; + case OPAL_P7IOC_DIAG_TYPE_CI: + pr_info("P7IOC diag-data for CI Port %d\\nn", + data->ci.ciPort); + ioda_eeh_hub_diag_common(data); + pr_info(" CI Port Status: %016llx\n", data->ci.ciPortStatus); + pr_info(" CI Port LDCP: %016llx\n", 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_warning("%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 eeh_pe *phb_pe, *dev_pe; + struct eeh_dev dev; + + /* Find the PHB PE */ + phb_pe = eeh_phb_pe_get(hose); + if (!phb_pe) + return -EEXIST; + + /* Find the PE according to PE# */ + memset(&dev, 0, sizeof(struct eeh_dev)); + dev.phb = hose; + dev.pe_config_addr = pe_no; + dev_pe = eeh_pe_get(&dev); + if (!dev_pe) return -EEXIST; + + *pe = dev_pe; + 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(hose); + 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) { + 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(hose); + } + + /* + * 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, + .configure_bridge = ioda_eeh_configure_bridge, + .next_error = ioda_eeh_next_error +}; diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c new file mode 100644 index 00000000000..56a206f32f7 --- /dev/null +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -0,0 +1,413 @@ +/* + * The file intends to implement the platform dependent EEH operations on + * powernv platform. Actually, the powernv was created in order to fully + * hypervisor support. + * + * 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/atomic.h> +#include <linux/delay.h> +#include <linux/export.h> +#include <linux/init.h> +#include <linux/list.h> +#include <linux/msi.h> +#include <linux/of.h> +#include <linux/pci.h> +#include <linux/proc_fs.h> +#include <linux/rbtree.h> +#include <linux/sched.h> +#include <linux/seq_file.h> +#include <linux/spinlock.h> + +#include <asm/eeh.h> +#include <asm/eeh_event.h> +#include <asm/firmware.h> +#include <asm/io.h> +#include <asm/iommu.h> +#include <asm/machdep.h> +#include <asm/msi_bitmap.h> +#include <asm/opal.h> +#include <asm/ppc-pci.h> + +#include "powernv.h" +#include "pci.h" + +/** + * powernv_eeh_init - EEH platform dependent initialization + * + * EEH platform dependent initialization on powernv + */ +static int powernv_eeh_init(void) +{ + /* We require OPALv3 */ + if (!firmware_has_feature(FW_FEATURE_OPALv3)) { + pr_warning("%s: OPALv3 is required !\n", __func__); + return -EINVAL; + } + + /* Set EEH probe mode */ + eeh_probe_mode_set(EEH_PROBE_MODE_DEV); + + return 0; +} + +/** + * powernv_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) +{ + struct pci_controller *hose; + struct pnv_phb *phb; + int ret = 0; + + 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; + } + } + + return ret; +} + +/** + * powernv_eeh_dev_probe - Do probe on PCI device + * @dev: PCI device + * @flag: 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. By default, EEH has been enabled + * on all PCI devices. That's to say, we only need do necessary + * initialization on the corresponding eeh device and create PE + * accordingly. + * + * It's notable that's unsafe to retrieve the EEH device through + * the corresponding PCI device. During the PCI device hotplug, which + * 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) +{ + struct pci_controller *hose = pci_bus_to_host(dev->bus); + 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); + + /* + * When probing the root bridge, which doesn't have any + * subordinate PCI devices. We don't have OF node for + * the root bridge. So it's not reasonable to continue + * the probing. + */ + if (!dn || !edev || edev->pe) + return 0; + + /* Skip for PCI-ISA bridge */ + if ((dev->class >> 8) == PCI_CLASS_BRIDGE_ISA) + return 0; + + /* Initialize eeh device */ + edev->class_code = dev->class; + edev->mode &= 0xFFFFFF00; + if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) + 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); + } + + edev->config_addr = ((dev->bus->number << 8) | dev->devfn); + edev->pe_config_addr = phb->bdfn_to_pe(phb, dev->bus, dev->devfn & 0xff); + + /* Create PE */ + eeh_add_to_parent_pe(edev); + + /* + * Enable EEH explicitly so that we will do EEH check + * while accessing I/O stuff + */ + eeh_set_enable(true); + + /* Save memory bars */ + eeh_save_bars(edev); + + return 0; +} + +/** + * powernv_eeh_set_option - Initialize EEH or MMIO/DMA reenable + * @pe: EEH PE + * @option: operation to be issued + * + * The function is used to control the EEH functionality globally. + * 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) +{ + struct pci_controller *hose = pe->phb; + struct pnv_phb *phb = hose->private_data; + int ret = -EEXIST; + + /* + * 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); + + return ret; +} + +/** + * powernv_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) +{ + return pe->addr; +} + +/** + * powernv_eeh_get_state - Retrieve PE state + * @pe: EEH PE + * @delay: delay while PE state is temporarily unavailable + * + * Retrieve the state of the specified PE. For IODA-compitable + * platform, it should be retrieved from IODA table. Therefore, + * we prefer passing down to hardware implementation to handle + * it. + */ +static int powernv_eeh_get_state(struct eeh_pe *pe, int *delay) +{ + struct pci_controller *hose = pe->phb; + struct pnv_phb *phb = hose->private_data; + int ret = EEH_STATE_NOT_SUPPORT; + + if (phb->eeh_ops && phb->eeh_ops->get_state) { + ret = phb->eeh_ops->get_state(pe); + + /* + * 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 ret; +} + +/** + * powernv_eeh_reset - Reset the specified PE + * @pe: EEH PE + * @option: reset option + * + * Reset the specified PE + */ +static int powernv_eeh_reset(struct eeh_pe *pe, int option) +{ + struct pci_controller *hose = pe->phb; + struct pnv_phb *phb = hose->private_data; + int ret = -EEXIST; + + if (phb->eeh_ops && phb->eeh_ops->reset) + ret = phb->eeh_ops->reset(pe, option); + + return ret; +} + +/** + * powernv_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) +{ + int ret; + int mwait; + + while (1) { + ret = powernv_eeh_get_state(pe, &mwait); + + /* + * If the PE's state is temporarily unavailable, + * we have to wait for the specified time. Otherwise, + * the PE's state will be returned immediately. + */ + if (ret != EEH_STATE_UNAVAILABLE) + return ret; + + max_wait -= mwait; + if (max_wait <= 0) { + pr_warning("%s: Timeout getting PE#%x's state (%d)\n", + __func__, pe->addr, max_wait); + return EEH_STATE_NOT_SUPPORT; + } + + msleep(mwait); + } + + return EEH_STATE_NOT_SUPPORT; +} + +/** + * powernv_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 + * @len: length of driver log + * + * 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) +{ + struct pci_controller *hose = pe->phb; + struct pnv_phb *phb = hose->private_data; + int ret = -EEXIST; + + if (phb->eeh_ops && phb->eeh_ops->get_log) + ret = phb->eeh_ops->get_log(pe, severity, drv_log, len); + + return ret; +} + +/** + * powernv_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) +{ + 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; +} + +/** + * powernv_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 + */ +static int powernv_eeh_next_error(struct eeh_pe **pe) +{ + struct pci_controller *hose; + struct pnv_phb *phb = NULL; + + list_for_each_entry(hose, &hose_list, list_node) { + phb = hose->private_data; + break; + } + + if (phb && phb->eeh_ops->next_error) + return phb->eeh_ops->next_error(pe); + + return -EEXIST; +} + +static int powernv_eeh_restore_config(struct device_node *dn) +{ + struct eeh_dev *edev = of_node_to_eeh_dev(dn); + struct pnv_phb *phb; + s64 ret; + + if (!edev) + return -EEXIST; + + phb = edev->phb->private_data; + ret = opal_pci_reinit(phb->opal_id, + OPAL_REINIT_PCI_DEV, edev->config_addr); + if (ret) { + pr_warn("%s: Can't reinit PCI dev 0x%x (%lld)\n", + __func__, edev->config_addr, ret); + return -EIO; + } + + return 0; +} + +static struct eeh_ops powernv_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, + .read_config = pnv_pci_cfg_read, + .write_config = pnv_pci_cfg_write, + .next_error = powernv_eeh_next_error, + .restore_config = powernv_eeh_restore_config +}; + +/** + * eeh_powernv_init - Register platform dependent EEH operations + * + * EEH initialization on powernv platform. This function should be + * called before any EEH related functions. + */ +static int __init eeh_powernv_init(void) +{ + int ret = -EINVAL; + + if (!machine_is(powernv)) + return ret; + + ret = eeh_ops_register(&powernv_eeh_ops); + if (!ret) + pr_info("EEH: PowerNV platform initialized\n"); + else + pr_info("EEH: Failed to initialize PowerNV platform (%d)\n", ret); + + return ret; +} + +early_initcall(eeh_powernv_init); diff --git a/arch/powerpc/platforms/powernv/opal-async.c b/arch/powerpc/platforms/powernv/opal-async.c new file mode 100644 index 00000000000..32e2adfa532 --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-async.c @@ -0,0 +1,204 @@ +/* + * PowerNV OPAL asynchronous completion interfaces + * + * Copyright 2013 IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#undef DEBUG + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <linux/sched.h> +#include <linux/semaphore.h> +#include <linux/spinlock.h> +#include <linux/wait.h> +#include <linux/gfp.h> +#include <linux/of.h> +#include <asm/opal.h> + +#define N_ASYNC_COMPLETIONS 64 + +static DECLARE_BITMAP(opal_async_complete_map, N_ASYNC_COMPLETIONS) = {~0UL}; +static DECLARE_BITMAP(opal_async_token_map, N_ASYNC_COMPLETIONS); +static DECLARE_WAIT_QUEUE_HEAD(opal_async_wait); +static DEFINE_SPINLOCK(opal_async_comp_lock); +static struct semaphore opal_async_sem; +static struct opal_msg *opal_async_responses; +static unsigned int opal_max_async_tokens; + +int __opal_async_get_token(void) +{ + unsigned long flags; + int token; + + spin_lock_irqsave(&opal_async_comp_lock, flags); + token = find_first_bit(opal_async_complete_map, opal_max_async_tokens); + if (token >= opal_max_async_tokens) { + token = -EBUSY; + goto out; + } + + if (__test_and_set_bit(token, opal_async_token_map)) { + token = -EBUSY; + goto out; + } + + __clear_bit(token, opal_async_complete_map); + +out: + spin_unlock_irqrestore(&opal_async_comp_lock, flags); + return token; +} + +int opal_async_get_token_interruptible(void) +{ + int token; + + /* Wait until a token is available */ + if (down_interruptible(&opal_async_sem)) + return -ERESTARTSYS; + + token = __opal_async_get_token(); + if (token < 0) + up(&opal_async_sem); + + return token; +} + +int __opal_async_release_token(int token) +{ + unsigned long flags; + + if (token < 0 || token >= opal_max_async_tokens) { + pr_err("%s: Passed token is out of range, token %d\n", + __func__, token); + return -EINVAL; + } + + spin_lock_irqsave(&opal_async_comp_lock, flags); + __set_bit(token, opal_async_complete_map); + __clear_bit(token, opal_async_token_map); + spin_unlock_irqrestore(&opal_async_comp_lock, flags); + + return 0; +} + +int opal_async_release_token(int token) +{ + int ret; + + ret = __opal_async_release_token(token); + if (ret) + return ret; + + up(&opal_async_sem); + + return 0; +} + +int opal_async_wait_response(uint64_t token, struct opal_msg *msg) +{ + if (token >= opal_max_async_tokens) { + pr_err("%s: Invalid token passed\n", __func__); + return -EINVAL; + } + + if (!msg) { + pr_err("%s: Invalid message pointer passed\n", __func__); + return -EINVAL; + } + + wait_event(opal_async_wait, test_bit(token, opal_async_complete_map)); + memcpy(msg, &opal_async_responses[token], sizeof(*msg)); + + return 0; +} + +static int opal_async_comp_event(struct notifier_block *nb, + unsigned long msg_type, void *msg) +{ + struct opal_msg *comp_msg = msg; + unsigned long flags; + uint64_t token; + + if (msg_type != OPAL_MSG_ASYNC_COMP) + return 0; + + token = be64_to_cpu(comp_msg->params[0]); + memcpy(&opal_async_responses[token], comp_msg, sizeof(*comp_msg)); + spin_lock_irqsave(&opal_async_comp_lock, flags); + __set_bit(token, opal_async_complete_map); + spin_unlock_irqrestore(&opal_async_comp_lock, flags); + + wake_up(&opal_async_wait); + + return 0; +} + +static struct notifier_block opal_async_comp_nb = { + .notifier_call = opal_async_comp_event, + .next = NULL, + .priority = 0, +}; + +static int __init opal_async_comp_init(void) +{ + struct device_node *opal_node; + const __be32 *async; + int err; + + opal_node = of_find_node_by_path("/ibm,opal"); + if (!opal_node) { + pr_err("%s: Opal node not found\n", __func__); + err = -ENOENT; + goto out; + } + + async = of_get_property(opal_node, "opal-msg-async-num", NULL); + if (!async) { + pr_err("%s: %s has no opal-msg-async-num\n", + __func__, opal_node->full_name); + err = -ENOENT; + goto out_opal_node; + } + + opal_max_async_tokens = be32_to_cpup(async); + if (opal_max_async_tokens > N_ASYNC_COMPLETIONS) + opal_max_async_tokens = N_ASYNC_COMPLETIONS; + + err = opal_message_notifier_register(OPAL_MSG_ASYNC_COMP, + &opal_async_comp_nb); + if (err) { + pr_err("%s: Can't register OPAL event notifier (%d)\n", + __func__, err); + goto out_opal_node; + } + + opal_async_responses = kzalloc( + sizeof(*opal_async_responses) * opal_max_async_tokens, + GFP_KERNEL); + if (!opal_async_responses) { + pr_err("%s: Out of memory, failed to do asynchronous " + "completion init\n", __func__); + err = -ENOMEM; + goto out_opal_node; + } + + /* Initialize to 1 less than the maximum tokens available, as we may + * require to pop one during emergency through synchronous call to + * __opal_async_get_token() + */ + sema_init(&opal_async_sem, opal_max_async_tokens - 1); + +out_opal_node: + of_node_put(opal_node); +out: + return err; +} +subsys_initcall(opal_async_comp_init); diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c new file mode 100644 index 00000000000..788a1977b9a --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-dump.c @@ -0,0 +1,448 @@ +/* + * PowerNV OPAL Dump Interface + * + * Copyright 2013,2014 IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/kobject.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> +#include <linux/pagemap.h> +#include <linux/delay.h> + +#include <asm/opal.h> + +#define DUMP_TYPE_FSP 0x01 + +struct dump_obj { + struct kobject kobj; + struct bin_attribute dump_attr; + uint32_t id; /* becomes object name */ + uint32_t type; + uint32_t size; + char *buffer; +}; +#define to_dump_obj(x) container_of(x, struct dump_obj, kobj) + +struct dump_attribute { + struct attribute attr; + ssize_t (*show)(struct dump_obj *dump, struct dump_attribute *attr, + char *buf); + ssize_t (*store)(struct dump_obj *dump, struct dump_attribute *attr, + const char *buf, size_t count); +}; +#define to_dump_attr(x) container_of(x, struct dump_attribute, attr) + +static ssize_t dump_id_show(struct dump_obj *dump_obj, + struct dump_attribute *attr, + char *buf) +{ + return sprintf(buf, "0x%x\n", dump_obj->id); +} + +static const char* dump_type_to_string(uint32_t type) +{ + switch (type) { + case 0x01: return "SP Dump"; + case 0x02: return "System/Platform Dump"; + case 0x03: return "SMA Dump"; + default: return "unknown"; + } +} + +static ssize_t dump_type_show(struct dump_obj *dump_obj, + struct dump_attribute *attr, + char *buf) +{ + + return sprintf(buf, "0x%x %s\n", dump_obj->type, + dump_type_to_string(dump_obj->type)); +} + +static ssize_t dump_ack_show(struct dump_obj *dump_obj, + struct dump_attribute *attr, + char *buf) +{ + return sprintf(buf, "ack - acknowledge dump\n"); +} + +/* + * Send acknowledgement to OPAL + */ +static int64_t dump_send_ack(uint32_t dump_id) +{ + int rc; + + rc = opal_dump_ack(dump_id); + if (rc) + pr_warn("%s: Failed to send ack to Dump ID 0x%x (%d)\n", + __func__, dump_id, rc); + return rc; +} + +static ssize_t dump_ack_store(struct dump_obj *dump_obj, + struct dump_attribute *attr, + const char *buf, + size_t count) +{ + dump_send_ack(dump_obj->id); + sysfs_remove_file_self(&dump_obj->kobj, &attr->attr); + kobject_put(&dump_obj->kobj); + return count; +} + +/* Attributes of a dump + * The binary attribute of the dump itself is dynamic + * due to the dynamic size of the dump + */ +static struct dump_attribute id_attribute = + __ATTR(id, 0666, dump_id_show, NULL); +static struct dump_attribute type_attribute = + __ATTR(type, 0666, dump_type_show, NULL); +static struct dump_attribute ack_attribute = + __ATTR(acknowledge, 0660, dump_ack_show, dump_ack_store); + +static ssize_t init_dump_show(struct dump_obj *dump_obj, + struct dump_attribute *attr, + char *buf) +{ + return sprintf(buf, "1 - initiate dump\n"); +} + +static int64_t dump_fips_init(uint8_t type) +{ + int rc; + + rc = opal_dump_init(type); + if (rc) + pr_warn("%s: Failed to initiate FipS dump (%d)\n", + __func__, rc); + return rc; +} + +static ssize_t init_dump_store(struct dump_obj *dump_obj, + struct dump_attribute *attr, + const char *buf, + size_t count) +{ + dump_fips_init(DUMP_TYPE_FSP); + pr_info("%s: Initiated FSP dump\n", __func__); + return count; +} + +static struct dump_attribute initiate_attribute = + __ATTR(initiate_dump, 0600, init_dump_show, init_dump_store); + +static struct attribute *initiate_attrs[] = { + &initiate_attribute.attr, + NULL, +}; + +static struct attribute_group initiate_attr_group = { + .attrs = initiate_attrs, +}; + +static struct kset *dump_kset; + +static ssize_t dump_attr_show(struct kobject *kobj, + struct attribute *attr, + char *buf) +{ + struct dump_attribute *attribute; + struct dump_obj *dump; + + attribute = to_dump_attr(attr); + dump = to_dump_obj(kobj); + + if (!attribute->show) + return -EIO; + + return attribute->show(dump, attribute, buf); +} + +static ssize_t dump_attr_store(struct kobject *kobj, + struct attribute *attr, + const char *buf, size_t len) +{ + struct dump_attribute *attribute; + struct dump_obj *dump; + + attribute = to_dump_attr(attr); + dump = to_dump_obj(kobj); + + if (!attribute->store) + return -EIO; + + return attribute->store(dump, attribute, buf, len); +} + +static const struct sysfs_ops dump_sysfs_ops = { + .show = dump_attr_show, + .store = dump_attr_store, +}; + +static void dump_release(struct kobject *kobj) +{ + struct dump_obj *dump; + + dump = to_dump_obj(kobj); + vfree(dump->buffer); + kfree(dump); +} + +static struct attribute *dump_default_attrs[] = { + &id_attribute.attr, + &type_attribute.attr, + &ack_attribute.attr, + NULL, +}; + +static struct kobj_type dump_ktype = { + .sysfs_ops = &dump_sysfs_ops, + .release = &dump_release, + .default_attrs = dump_default_attrs, +}; + +static int64_t dump_read_info(uint32_t *dump_id, uint32_t *dump_size, uint32_t *dump_type) +{ + __be32 id, size, type; + int rc; + + type = cpu_to_be32(0xffffffff); + + rc = opal_dump_info2(&id, &size, &type); + if (rc == OPAL_PARAMETER) + rc = opal_dump_info(&id, &size); + + *dump_id = be32_to_cpu(id); + *dump_size = be32_to_cpu(size); + *dump_type = be32_to_cpu(type); + + if (rc) + pr_warn("%s: Failed to get dump info (%d)\n", + __func__, rc); + return rc; +} + +static int64_t dump_read_data(struct dump_obj *dump) +{ + struct opal_sg_list *list; + uint64_t addr; + int64_t rc; + + /* Allocate memory */ + dump->buffer = vzalloc(PAGE_ALIGN(dump->size)); + if (!dump->buffer) { + pr_err("%s : Failed to allocate memory\n", __func__); + rc = -ENOMEM; + goto out; + } + + /* Generate SG list */ + list = opal_vmalloc_to_sg_list(dump->buffer, dump->size); + if (!list) { + rc = -ENOMEM; + goto out; + } + + /* First entry address */ + addr = __pa(list); + + /* Fetch data */ + rc = OPAL_BUSY_EVENT; + while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { + rc = opal_dump_read(dump->id, addr); + if (rc == OPAL_BUSY_EVENT) { + opal_poll_events(NULL); + msleep(20); + } + } + + if (rc != OPAL_SUCCESS && rc != OPAL_PARTIAL) + pr_warn("%s: Extract dump failed for ID 0x%x\n", + __func__, dump->id); + + /* Free SG list */ + opal_free_sg_list(list); + +out: + return rc; +} + +static ssize_t dump_attr_read(struct file *filep, struct kobject *kobj, + struct bin_attribute *bin_attr, + char *buffer, loff_t pos, size_t count) +{ + ssize_t rc; + + struct dump_obj *dump = to_dump_obj(kobj); + + if (!dump->buffer) { + rc = dump_read_data(dump); + + if (rc != OPAL_SUCCESS && rc != OPAL_PARTIAL) { + vfree(dump->buffer); + dump->buffer = NULL; + + return -EIO; + } + if (rc == OPAL_PARTIAL) { + /* On a partial read, we just return EIO + * and rely on userspace to ask us to try + * again. + */ + pr_info("%s: Platform dump partially read.ID = 0x%x\n", + __func__, dump->id); + return -EIO; + } + } + + memcpy(buffer, dump->buffer + pos, count); + + /* You may think we could free the dump buffer now and retrieve + * it again later if needed, but due to current firmware limitation, + * that's not the case. So, once read into userspace once, + * we keep the dump around until it's acknowledged by userspace. + */ + + return count; +} + +static struct dump_obj *create_dump_obj(uint32_t id, size_t size, + uint32_t type) +{ + struct dump_obj *dump; + int rc; + + dump = kzalloc(sizeof(*dump), GFP_KERNEL); + if (!dump) + return NULL; + + dump->kobj.kset = dump_kset; + + kobject_init(&dump->kobj, &dump_ktype); + + sysfs_bin_attr_init(&dump->dump_attr); + + dump->dump_attr.attr.name = "dump"; + dump->dump_attr.attr.mode = 0400; + dump->dump_attr.size = size; + dump->dump_attr.read = dump_attr_read; + + dump->id = id; + dump->size = size; + dump->type = type; + + rc = kobject_add(&dump->kobj, NULL, "0x%x-0x%x", type, id); + if (rc) { + kobject_put(&dump->kobj); + return NULL; + } + + rc = sysfs_create_bin_file(&dump->kobj, &dump->dump_attr); + if (rc) { + kobject_put(&dump->kobj); + return NULL; + } + + pr_info("%s: New platform dump. ID = 0x%x Size %u\n", + __func__, dump->id, dump->size); + + kobject_uevent(&dump->kobj, KOBJ_ADD); + + return dump; +} + +static int process_dump(void) +{ + int rc; + uint32_t dump_id, dump_size, dump_type; + struct dump_obj *dump; + char name[22]; + + rc = dump_read_info(&dump_id, &dump_size, &dump_type); + if (rc != OPAL_SUCCESS) + return rc; + + sprintf(name, "0x%x-0x%x", dump_type, dump_id); + + /* we may get notified twice, let's handle + * that gracefully and not create two conflicting + * entries. + */ + if (kset_find_obj(dump_kset, name)) + return 0; + + dump = create_dump_obj(dump_id, dump_size, dump_type); + if (!dump) + return -1; + + return 0; +} + +static void dump_work_fn(struct work_struct *work) +{ + process_dump(); +} + +static DECLARE_WORK(dump_work, dump_work_fn); + +static void schedule_process_dump(void) +{ + schedule_work(&dump_work); +} + +/* + * New dump available notification + * + * Once we get notification, we add sysfs entries for it. + * We only fetch the dump on demand, and create sysfs asynchronously. + */ +static int dump_event(struct notifier_block *nb, + unsigned long events, void *change) +{ + if (events & OPAL_EVENT_DUMP_AVAIL) + schedule_process_dump(); + + return 0; +} + +static struct notifier_block dump_nb = { + .notifier_call = dump_event, + .next = NULL, + .priority = 0 +}; + +void __init opal_platform_dump_init(void) +{ + int rc; + + dump_kset = kset_create_and_add("dump", NULL, opal_kobj); + if (!dump_kset) { + pr_warn("%s: Failed to create dump kset\n", __func__); + return; + } + + rc = sysfs_create_group(&dump_kset->kobj, &initiate_attr_group); + if (rc) { + pr_warn("%s: Failed to create initiate dump attr group\n", + __func__); + kobject_put(&dump_kset->kobj); + return; + } + + rc = opal_notifier_register(&dump_nb); + if (rc) { + pr_warn("%s: Can't register OPAL event notifier (%d)\n", + __func__, rc); + return; + } + + opal_dump_resend_notification(); +} diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c new file mode 100644 index 00000000000..0ad533b617f --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-elog.c @@ -0,0 +1,315 @@ +/* + * Error log support on PowerNV. + * + * Copyright 2013,2014 IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/of.h> +#include <linux/slab.h> +#include <linux/sysfs.h> +#include <linux/fs.h> +#include <linux/vmalloc.h> +#include <linux/fcntl.h> +#include <linux/kobject.h> +#include <asm/uaccess.h> +#include <asm/opal.h> + +struct elog_obj { + struct kobject kobj; + struct bin_attribute raw_attr; + uint64_t id; + uint64_t type; + size_t size; + char *buffer; +}; +#define to_elog_obj(x) container_of(x, struct elog_obj, kobj) + +struct elog_attribute { + struct attribute attr; + ssize_t (*show)(struct elog_obj *elog, struct elog_attribute *attr, + char *buf); + ssize_t (*store)(struct elog_obj *elog, struct elog_attribute *attr, + const char *buf, size_t count); +}; +#define to_elog_attr(x) container_of(x, struct elog_attribute, attr) + +static ssize_t elog_id_show(struct elog_obj *elog_obj, + struct elog_attribute *attr, + char *buf) +{ + return sprintf(buf, "0x%llx\n", elog_obj->id); +} + +static const char *elog_type_to_string(uint64_t type) +{ + switch (type) { + case 0: return "PEL"; + default: return "unknown"; + } +} + +static ssize_t elog_type_show(struct elog_obj *elog_obj, + struct elog_attribute *attr, + char *buf) +{ + return sprintf(buf, "0x%llx %s\n", + elog_obj->type, + elog_type_to_string(elog_obj->type)); +} + +static ssize_t elog_ack_show(struct elog_obj *elog_obj, + struct elog_attribute *attr, + char *buf) +{ + return sprintf(buf, "ack - acknowledge log message\n"); +} + +static ssize_t elog_ack_store(struct elog_obj *elog_obj, + struct elog_attribute *attr, + const char *buf, + size_t count) +{ + opal_send_ack_elog(elog_obj->id); + sysfs_remove_file_self(&elog_obj->kobj, &attr->attr); + kobject_put(&elog_obj->kobj); + return count; +} + +static struct elog_attribute id_attribute = + __ATTR(id, 0666, elog_id_show, NULL); +static struct elog_attribute type_attribute = + __ATTR(type, 0666, elog_type_show, NULL); +static struct elog_attribute ack_attribute = + __ATTR(acknowledge, 0660, elog_ack_show, elog_ack_store); + +static struct kset *elog_kset; + +static ssize_t elog_attr_show(struct kobject *kobj, + struct attribute *attr, + char *buf) +{ + struct elog_attribute *attribute; + struct elog_obj *elog; + + attribute = to_elog_attr(attr); + elog = to_elog_obj(kobj); + + if (!attribute->show) + return -EIO; + + return attribute->show(elog, attribute, buf); +} + +static ssize_t elog_attr_store(struct kobject *kobj, + struct attribute *attr, + const char *buf, size_t len) +{ + struct elog_attribute *attribute; + struct elog_obj *elog; + + attribute = to_elog_attr(attr); + elog = to_elog_obj(kobj); + + if (!attribute->store) + return -EIO; + + return attribute->store(elog, attribute, buf, len); +} + +static const struct sysfs_ops elog_sysfs_ops = { + .show = elog_attr_show, + .store = elog_attr_store, +}; + +static void elog_release(struct kobject *kobj) +{ + struct elog_obj *elog; + + elog = to_elog_obj(kobj); + kfree(elog->buffer); + kfree(elog); +} + +static struct attribute *elog_default_attrs[] = { + &id_attribute.attr, + &type_attribute.attr, + &ack_attribute.attr, + NULL, +}; + +static struct kobj_type elog_ktype = { + .sysfs_ops = &elog_sysfs_ops, + .release = &elog_release, + .default_attrs = elog_default_attrs, +}; + +/* Maximum size of a single log on FSP is 16KB */ +#define OPAL_MAX_ERRLOG_SIZE 16384 + +static ssize_t raw_attr_read(struct file *filep, struct kobject *kobj, + struct bin_attribute *bin_attr, + char *buffer, loff_t pos, size_t count) +{ + int opal_rc; + + struct elog_obj *elog = to_elog_obj(kobj); + + /* We may have had an error reading before, so let's retry */ + if (!elog->buffer) { + elog->buffer = kzalloc(elog->size, GFP_KERNEL); + if (!elog->buffer) + return -EIO; + + opal_rc = opal_read_elog(__pa(elog->buffer), + elog->size, elog->id); + if (opal_rc != OPAL_SUCCESS) { + pr_err("ELOG: log read failed for log-id=%llx\n", + elog->id); + kfree(elog->buffer); + elog->buffer = NULL; + return -EIO; + } + } + + memcpy(buffer, elog->buffer + pos, count); + + return count; +} + +static struct elog_obj *create_elog_obj(uint64_t id, size_t size, uint64_t type) +{ + struct elog_obj *elog; + int rc; + + elog = kzalloc(sizeof(*elog), GFP_KERNEL); + if (!elog) + return NULL; + + elog->kobj.kset = elog_kset; + + kobject_init(&elog->kobj, &elog_ktype); + + sysfs_bin_attr_init(&elog->raw_attr); + + elog->raw_attr.attr.name = "raw"; + elog->raw_attr.attr.mode = 0400; + elog->raw_attr.size = size; + elog->raw_attr.read = raw_attr_read; + + elog->id = id; + elog->size = size; + elog->type = type; + + elog->buffer = kzalloc(elog->size, GFP_KERNEL); + + if (elog->buffer) { + rc = opal_read_elog(__pa(elog->buffer), + elog->size, elog->id); + if (rc != OPAL_SUCCESS) { + pr_err("ELOG: log read failed for log-id=%llx\n", + elog->id); + kfree(elog->buffer); + elog->buffer = NULL; + } + } + + rc = kobject_add(&elog->kobj, NULL, "0x%llx", id); + if (rc) { + kobject_put(&elog->kobj); + return NULL; + } + + rc = sysfs_create_bin_file(&elog->kobj, &elog->raw_attr); + if (rc) { + kobject_put(&elog->kobj); + return NULL; + } + + kobject_uevent(&elog->kobj, KOBJ_ADD); + + return elog; +} + +static void elog_work_fn(struct work_struct *work) +{ + __be64 size; + __be64 id; + __be64 type; + uint64_t elog_size; + uint64_t log_id; + uint64_t elog_type; + int rc; + char name[2+16+1]; + + rc = opal_get_elog_size(&id, &size, &type); + if (rc != OPAL_SUCCESS) { + pr_err("ELOG: OPAL log info read failed\n"); + return; + } + + elog_size = be64_to_cpu(size); + log_id = be64_to_cpu(id); + elog_type = be64_to_cpu(type); + + WARN_ON(elog_size > OPAL_MAX_ERRLOG_SIZE); + + if (elog_size >= OPAL_MAX_ERRLOG_SIZE) + elog_size = OPAL_MAX_ERRLOG_SIZE; + + sprintf(name, "0x%llx", log_id); + + /* we may get notified twice, let's handle + * that gracefully and not create two conflicting + * entries. + */ + if (kset_find_obj(elog_kset, name)) + return; + + create_elog_obj(log_id, elog_size, elog_type); +} + +static DECLARE_WORK(elog_work, elog_work_fn); + +static int elog_event(struct notifier_block *nb, + unsigned long events, void *change) +{ + /* check for error log event */ + if (events & OPAL_EVENT_ERROR_LOG_AVAIL) + schedule_work(&elog_work); + return 0; +} + +static struct notifier_block elog_nb = { + .notifier_call = elog_event, + .next = NULL, + .priority = 0 +}; + +int __init opal_elog_init(void) +{ + int rc = 0; + + elog_kset = kset_create_and_add("elog", NULL, opal_kobj); + if (!elog_kset) { + pr_warn("%s: failed to create elog kset\n", __func__); + return -1; + } + + rc = opal_notifier_register(&elog_nb); + if (rc) { + pr_err("%s: Can't register OPAL event notifier (%d)\n", + __func__, rc); + return rc; + } + + /* We are now ready to pull error logs from opal. */ + opal_resend_pending_logs(); + + return 0; +} diff --git a/arch/powerpc/platforms/powernv/opal-flash.c b/arch/powerpc/platforms/powernv/opal-flash.c new file mode 100644 index 00000000000..5c21d9c07f4 --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-flash.c @@ -0,0 +1,588 @@ +/* + * PowerNV OPAL Firmware Update Interface + * + * Copyright 2013 IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#define DEBUG + +#include <linux/kernel.h> +#include <linux/reboot.h> +#include <linux/init.h> +#include <linux/kobject.h> +#include <linux/sysfs.h> +#include <linux/slab.h> +#include <linux/mm.h> +#include <linux/vmalloc.h> +#include <linux/pagemap.h> +#include <linux/delay.h> + +#include <asm/opal.h> + +/* FLASH status codes */ +#define FLASH_NO_OP -1099 /* No operation initiated by user */ +#define FLASH_NO_AUTH -9002 /* Not a service authority partition */ + +/* Validate image status values */ +#define VALIDATE_IMG_READY -1001 /* Image ready for validation */ +#define VALIDATE_IMG_INCOMPLETE -1002 /* User copied < VALIDATE_BUF_SIZE */ + +/* Manage image status values */ +#define MANAGE_ACTIVE_ERR -9001 /* Cannot overwrite active img */ + +/* Flash image status values */ +#define FLASH_IMG_READY 0 /* Img ready for flash on reboot */ +#define FLASH_INVALID_IMG -1003 /* Flash image shorter than expected */ +#define FLASH_IMG_NULL_DATA -1004 /* Bad data in sg list entry */ +#define FLASH_IMG_BAD_LEN -1005 /* Bad length in sg list entry */ + +/* Manage operation tokens */ +#define FLASH_REJECT_TMP_SIDE 0 /* Reject temporary fw image */ +#define FLASH_COMMIT_TMP_SIDE 1 /* Commit temporary fw image */ + +/* Update tokens */ +#define FLASH_UPDATE_CANCEL 0 /* Cancel update request */ +#define FLASH_UPDATE_INIT 1 /* Initiate update */ + +/* Validate image update result tokens */ +#define VALIDATE_TMP_UPDATE 0 /* T side will be updated */ +#define VALIDATE_FLASH_AUTH 1 /* Partition does not have authority */ +#define VALIDATE_INVALID_IMG 2 /* Candidate image is not valid */ +#define VALIDATE_CUR_UNKNOWN 3 /* Current fixpack level is unknown */ +/* + * Current T side will be committed to P side before being replace with new + * image, and the new image is downlevel from current image + */ +#define VALIDATE_TMP_COMMIT_DL 4 +/* + * Current T side will be committed to P side before being replaced with new + * image + */ +#define VALIDATE_TMP_COMMIT 5 +/* + * T side will be updated with a downlevel image + */ +#define VALIDATE_TMP_UPDATE_DL 6 +/* + * The candidate image's release date is later than the system's firmware + * service entitlement date - service warranty period has expired + */ +#define VALIDATE_OUT_OF_WRNTY 7 + +/* Validate buffer size */ +#define VALIDATE_BUF_SIZE 4096 + +/* XXX: Assume candidate image size is <= 1GB */ +#define MAX_IMAGE_SIZE 0x40000000 + +/* Image status */ +enum { + IMAGE_INVALID, + IMAGE_LOADING, + IMAGE_READY, +}; + +/* Candidate image data */ +struct image_data_t { + int status; + void *data; + uint32_t size; +}; + +/* Candidate image header */ +struct image_header_t { + uint16_t magic; + uint16_t version; + uint32_t size; +}; + +struct validate_flash_t { + int status; /* Return status */ + void *buf; /* Candidate image buffer */ + uint32_t buf_size; /* Image size */ + uint32_t result; /* Update results token */ +}; + +struct manage_flash_t { + int status; /* Return status */ +}; + +struct update_flash_t { + int status; /* Return status */ +}; + +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; + +static DEFINE_MUTEX(image_data_mutex); + +/* + * Validate candidate image + */ +static inline void opal_flash_validate(void) +{ + long ret; + void *buf = validate_flash_data.buf; + __be32 size = cpu_to_be32(validate_flash_data.buf_size); + __be32 result; + + ret = opal_validate_flash(__pa(buf), &size, &result); + + validate_flash_data.status = ret; + validate_flash_data.buf_size = be32_to_cpu(size); + validate_flash_data.result = be32_to_cpu(result); +} + +/* + * Validate output format: + * validate result token + * current image version details + * new image version details + */ +static ssize_t validate_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct validate_flash_t *args_buf = &validate_flash_data; + int len; + + /* Candidate image is not validated */ + if (args_buf->status < VALIDATE_TMP_UPDATE) { + len = sprintf(buf, "%d\n", args_buf->status); + goto out; + } + + /* Result token */ + len = sprintf(buf, "%d\n", args_buf->result); + + /* Current and candidate image version details */ + if ((args_buf->result != VALIDATE_TMP_UPDATE) && + (args_buf->result < VALIDATE_CUR_UNKNOWN)) + goto out; + + if (args_buf->buf_size > (VALIDATE_BUF_SIZE - len)) { + memcpy(buf + len, args_buf->buf, VALIDATE_BUF_SIZE - len); + len = VALIDATE_BUF_SIZE; + } else { + memcpy(buf + len, args_buf->buf, args_buf->buf_size); + len += args_buf->buf_size; + } +out: + /* Set status to default */ + args_buf->status = FLASH_NO_OP; + return len; +} + +/* + * Validate candidate firmware image + * + * Note: + * We are only interested in first 4K bytes of the + * candidate image. + */ +static ssize_t validate_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct validate_flash_t *args_buf = &validate_flash_data; + + if (buf[0] != '1') + return -EINVAL; + + mutex_lock(&image_data_mutex); + + if (image_data.status != IMAGE_READY || + image_data.size < VALIDATE_BUF_SIZE) { + args_buf->result = VALIDATE_INVALID_IMG; + args_buf->status = VALIDATE_IMG_INCOMPLETE; + goto out; + } + + /* Copy first 4k bytes of candidate image */ + memcpy(args_buf->buf, image_data.data, VALIDATE_BUF_SIZE); + + args_buf->status = VALIDATE_IMG_READY; + args_buf->buf_size = VALIDATE_BUF_SIZE; + + /* Validate candidate image */ + opal_flash_validate(); + +out: + mutex_unlock(&image_data_mutex); + return count; +} + +/* + * Manage flash routine + */ +static inline void opal_flash_manage(uint8_t op) +{ + struct manage_flash_t *const args_buf = &manage_flash_data; + + args_buf->status = opal_manage_flash(op); +} + +/* + * Show manage flash status + */ +static ssize_t manage_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct manage_flash_t *const args_buf = &manage_flash_data; + int rc; + + rc = sprintf(buf, "%d\n", args_buf->status); + /* Set status to default*/ + args_buf->status = FLASH_NO_OP; + return rc; +} + +/* + * Manage operations: + * 0 - Reject + * 1 - Commit + */ +static ssize_t manage_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + uint8_t op; + switch (buf[0]) { + case '0': + op = FLASH_REJECT_TMP_SIDE; + break; + case '1': + op = FLASH_COMMIT_TMP_SIDE; + break; + default: + return -EINVAL; + } + + /* commit/reject temporary image */ + opal_flash_manage(op); + return count; +} + +/* + * OPAL update flash + */ +static int opal_flash_update(int op) +{ + struct opal_sg_list *list; + unsigned long addr; + int64_t rc = OPAL_PARAMETER; + + if (op == FLASH_UPDATE_CANCEL) { + pr_alert("FLASH: Image update cancelled\n"); + addr = '\0'; + goto flash; + } + + list = opal_vmalloc_to_sg_list(image_data.data, image_data.size); + if (!list) + goto invalid_img; + + /* First entry address */ + addr = __pa(list); + +flash: + rc = opal_update_flash(addr); + +invalid_img: + return rc; +} + +/* Return CPUs to OPAL before starting FW update */ +static void flash_return_cpu(void *info) +{ + int cpu = smp_processor_id(); + + if (!cpu_online(cpu)) + return; + + /* Disable IRQ */ + hard_irq_disable(); + + /* Return the CPU to OPAL */ + opal_return_cpu(); +} + +/* This gets called just before system reboots */ +void opal_flash_term_callback(void) +{ + struct cpumask mask; + + if (update_flash_data.status != FLASH_IMG_READY) + return; + + pr_alert("FLASH: Flashing new firmware\n"); + pr_alert("FLASH: Image is %u bytes\n", image_data.size); + pr_alert("FLASH: Performing flash and reboot/shutdown\n"); + pr_alert("FLASH: This will take several minutes. Do not power off!\n"); + + /* Small delay to help getting the above message out */ + msleep(500); + + /* Return secondary CPUs to firmware */ + cpumask_copy(&mask, cpu_online_mask); + cpumask_clear_cpu(smp_processor_id(), &mask); + if (!cpumask_empty(&mask)) + smp_call_function_many(&mask, + flash_return_cpu, NULL, false); + /* Hard disable interrupts */ + hard_irq_disable(); +} + +/* + * Show candidate image status + */ +static ssize_t update_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct update_flash_t *const args_buf = &update_flash_data; + return sprintf(buf, "%d\n", args_buf->status); +} + +/* + * Set update image flag + * 1 - Flash new image + * 0 - Cancel flash request + */ +static ssize_t update_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct update_flash_t *const args_buf = &update_flash_data; + int rc = count; + + mutex_lock(&image_data_mutex); + + switch (buf[0]) { + case '0': + if (args_buf->status == FLASH_IMG_READY) + opal_flash_update(FLASH_UPDATE_CANCEL); + args_buf->status = FLASH_NO_OP; + break; + case '1': + /* Image is loaded? */ + if (image_data.status == IMAGE_READY) + args_buf->status = + opal_flash_update(FLASH_UPDATE_INIT); + else + args_buf->status = FLASH_INVALID_IMG; + break; + default: + rc = -EINVAL; + } + + mutex_unlock(&image_data_mutex); + return rc; +} + +/* + * Free image buffer + */ +static void free_image_buf(void) +{ + void *addr; + int size; + + addr = image_data.data; + size = PAGE_ALIGN(image_data.size); + while (size > 0) { + ClearPageReserved(vmalloc_to_page(addr)); + addr += PAGE_SIZE; + size -= PAGE_SIZE; + } + vfree(image_data.data); + image_data.data = NULL; + image_data.status = IMAGE_INVALID; +} + +/* + * Allocate image buffer. + */ +static int alloc_image_buf(char *buffer, size_t count) +{ + void *addr; + int size; + + if (count < sizeof(struct image_header_t)) { + pr_warn("FLASH: Invalid candidate image\n"); + return -EINVAL; + } + + memcpy(&image_header, (void *)buffer, sizeof(struct image_header_t)); + image_data.size = be32_to_cpu(image_header.size); + pr_debug("FLASH: Candidate image size = %u\n", image_data.size); + + if (image_data.size > MAX_IMAGE_SIZE) { + pr_warn("FLASH: Too large image\n"); + return -EINVAL; + } + if (image_data.size < VALIDATE_BUF_SIZE) { + pr_warn("FLASH: Image is shorter than expected\n"); + return -EINVAL; + } + + image_data.data = vzalloc(PAGE_ALIGN(image_data.size)); + if (!image_data.data) { + pr_err("%s : Failed to allocate memory\n", __func__); + return -ENOMEM; + } + + /* Pin memory */ + addr = image_data.data; + size = PAGE_ALIGN(image_data.size); + while (size > 0) { + SetPageReserved(vmalloc_to_page(addr)); + addr += PAGE_SIZE; + size -= PAGE_SIZE; + } + + image_data.status = IMAGE_LOADING; + return 0; +} + +/* + * Copy candidate image + * + * Parse candidate image header to get total image size + * and pre-allocate required memory. + */ +static ssize_t image_data_write(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, + char *buffer, loff_t pos, size_t count) +{ + int rc; + + mutex_lock(&image_data_mutex); + + /* New image ? */ + if (pos == 0) { + /* Free memory, if already allocated */ + if (image_data.data) + free_image_buf(); + + /* Cancel outstanding image update request */ + if (update_flash_data.status == FLASH_IMG_READY) + opal_flash_update(FLASH_UPDATE_CANCEL); + + /* Allocate memory */ + rc = alloc_image_buf(buffer, count); + if (rc) + goto out; + } + + if (image_data.status != IMAGE_LOADING) { + rc = -ENOMEM; + goto out; + } + + if ((pos + count) > image_data.size) { + rc = -EINVAL; + goto out; + } + + memcpy(image_data.data + pos, (void *)buffer, count); + rc = count; + + /* Set image status */ + if ((pos + count) == image_data.size) { + pr_debug("FLASH: Candidate image loaded....\n"); + image_data.status = IMAGE_READY; + } + +out: + mutex_unlock(&image_data_mutex); + return rc; +} + +/* + * sysfs interface : + * OPAL uses below sysfs files for code update. + * We create these files under /sys/firmware/opal. + * + * image : Interface to load candidate firmware image + * validate_flash : Validate firmware image + * manage_flash : Commit/Reject firmware image + * update_flash : Flash new firmware image + * + */ +static struct bin_attribute image_data_attr = { + .attr = {.name = "image", .mode = 0200}, + .size = MAX_IMAGE_SIZE, /* Limit image size */ + .write = image_data_write, +}; + +static struct kobj_attribute validate_attribute = + __ATTR(validate_flash, 0600, validate_show, validate_store); + +static struct kobj_attribute manage_attribute = + __ATTR(manage_flash, 0600, manage_show, manage_store); + +static struct kobj_attribute update_attribute = + __ATTR(update_flash, 0600, update_show, update_store); + +static struct attribute *image_op_attrs[] = { + &validate_attribute.attr, + &manage_attribute.attr, + &update_attribute.attr, + NULL /* need to NULL terminate the list of attributes */ +}; + +static struct attribute_group image_op_attr_group = { + .attrs = image_op_attrs, +}; + +void __init opal_flash_init(void) +{ + int ret; + + /* Allocate validate image buffer */ + validate_flash_data.buf = kzalloc(VALIDATE_BUF_SIZE, GFP_KERNEL); + if (!validate_flash_data.buf) { + pr_err("%s : Failed to allocate memory\n", __func__); + return; + } + + /* Make sure /sys/firmware/opal directory is created */ + if (!opal_kobj) { + pr_warn("FLASH: opal kobject is not available\n"); + goto nokobj; + } + + /* Create the sysfs files */ + ret = sysfs_create_group(opal_kobj, &image_op_attr_group); + if (ret) { + pr_warn("FLASH: Failed to create sysfs files\n"); + goto nokobj; + } + + ret = sysfs_create_bin_file(opal_kobj, &image_data_attr); + if (ret) { + pr_warn("FLASH: Failed to create sysfs files\n"); + goto nosysfs_file; + } + + /* Set default status */ + validate_flash_data.status = FLASH_NO_OP; + manage_flash_data.status = FLASH_NO_OP; + update_flash_data.status = FLASH_NO_OP; + image_data.status = IMAGE_INVALID; + return; + +nosysfs_file: + sysfs_remove_group(opal_kobj, &image_op_attr_group); + +nokobj: + kfree(validate_flash_data.buf); + return; +} diff --git a/arch/powerpc/platforms/powernv/opal-lpc.c b/arch/powerpc/platforms/powernv/opal-lpc.c new file mode 100644 index 00000000000..f04b4d8aca5 --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-lpc.c @@ -0,0 +1,355 @@ +/* + * PowerNV LPC bus handling. + * + * Copyright 2013 IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/of.h> +#include <linux/bug.h> +#include <linux/debugfs.h> +#include <linux/io.h> +#include <linux/slab.h> + +#include <asm/machdep.h> +#include <asm/firmware.h> +#include <asm/xics.h> +#include <asm/opal.h> +#include <asm/prom.h> +#include <asm/uaccess.h> +#include <asm/debug.h> + +static int opal_lpc_chip_id = -1; + +static u8 opal_lpc_inb(unsigned long port) +{ + int64_t rc; + __be32 data; + + if (opal_lpc_chip_id < 0 || port > 0xffff) + return 0xff; + rc = opal_lpc_read(opal_lpc_chip_id, OPAL_LPC_IO, port, &data, 1); + return rc ? 0xff : be32_to_cpu(data); +} + +static __le16 __opal_lpc_inw(unsigned long port) +{ + int64_t rc; + __be32 data; + + if (opal_lpc_chip_id < 0 || port > 0xfffe) + return 0xffff; + if (port & 1) + return (__le16)opal_lpc_inb(port) << 8 | opal_lpc_inb(port + 1); + rc = opal_lpc_read(opal_lpc_chip_id, OPAL_LPC_IO, port, &data, 2); + return rc ? 0xffff : be32_to_cpu(data); +} +static u16 opal_lpc_inw(unsigned long port) +{ + return le16_to_cpu(__opal_lpc_inw(port)); +} + +static __le32 __opal_lpc_inl(unsigned long port) +{ + int64_t rc; + __be32 data; + + if (opal_lpc_chip_id < 0 || port > 0xfffc) + return 0xffffffff; + if (port & 3) + return (__le32)opal_lpc_inb(port ) << 24 | + (__le32)opal_lpc_inb(port + 1) << 16 | + (__le32)opal_lpc_inb(port + 2) << 8 | + opal_lpc_inb(port + 3); + rc = opal_lpc_read(opal_lpc_chip_id, OPAL_LPC_IO, port, &data, 4); + return rc ? 0xffffffff : be32_to_cpu(data); +} + +static u32 opal_lpc_inl(unsigned long port) +{ + return le32_to_cpu(__opal_lpc_inl(port)); +} + +static void opal_lpc_outb(u8 val, unsigned long port) +{ + if (opal_lpc_chip_id < 0 || port > 0xffff) + return; + opal_lpc_write(opal_lpc_chip_id, OPAL_LPC_IO, port, val, 1); +} + +static void __opal_lpc_outw(__le16 val, unsigned long port) +{ + if (opal_lpc_chip_id < 0 || port > 0xfffe) + return; + if (port & 1) { + opal_lpc_outb(val >> 8, port); + opal_lpc_outb(val , port + 1); + return; + } + opal_lpc_write(opal_lpc_chip_id, OPAL_LPC_IO, port, val, 2); +} + +static void opal_lpc_outw(u16 val, unsigned long port) +{ + __opal_lpc_outw(cpu_to_le16(val), port); +} + +static void __opal_lpc_outl(__le32 val, unsigned long port) +{ + if (opal_lpc_chip_id < 0 || port > 0xfffc) + return; + if (port & 3) { + opal_lpc_outb(val >> 24, port); + opal_lpc_outb(val >> 16, port + 1); + opal_lpc_outb(val >> 8, port + 2); + opal_lpc_outb(val , port + 3); + return; + } + opal_lpc_write(opal_lpc_chip_id, OPAL_LPC_IO, port, val, 4); +} + +static void opal_lpc_outl(u32 val, unsigned long port) +{ + __opal_lpc_outl(cpu_to_le32(val), port); +} + +static void opal_lpc_insb(unsigned long p, void *b, unsigned long c) +{ + u8 *ptr = b; + + while(c--) + *(ptr++) = opal_lpc_inb(p); +} + +static void opal_lpc_insw(unsigned long p, void *b, unsigned long c) +{ + __le16 *ptr = b; + + while(c--) + *(ptr++) = __opal_lpc_inw(p); +} + +static void opal_lpc_insl(unsigned long p, void *b, unsigned long c) +{ + __le32 *ptr = b; + + while(c--) + *(ptr++) = __opal_lpc_inl(p); +} + +static void opal_lpc_outsb(unsigned long p, const void *b, unsigned long c) +{ + const u8 *ptr = b; + + while(c--) + opal_lpc_outb(*(ptr++), p); +} + +static void opal_lpc_outsw(unsigned long p, const void *b, unsigned long c) +{ + const __le16 *ptr = b; + + while(c--) + __opal_lpc_outw(*(ptr++), p); +} + +static void opal_lpc_outsl(unsigned long p, const void *b, unsigned long c) +{ + const __le32 *ptr = b; + + while(c--) + __opal_lpc_outl(*(ptr++), p); +} + +static const struct ppc_pci_io opal_lpc_io = { + .inb = opal_lpc_inb, + .inw = opal_lpc_inw, + .inl = opal_lpc_inl, + .outb = opal_lpc_outb, + .outw = opal_lpc_outw, + .outl = opal_lpc_outl, + .insb = opal_lpc_insb, + .insw = opal_lpc_insw, + .insl = opal_lpc_insl, + .outsb = opal_lpc_outsb, + .outsw = opal_lpc_outsw, + .outsl = opal_lpc_outsl, +}; + +#ifdef CONFIG_DEBUG_FS +struct lpc_debugfs_entry { + enum OpalLPCAddressType lpc_type; +}; + +static ssize_t lpc_debug_read(struct file *filp, char __user *ubuf, + size_t count, loff_t *ppos) +{ + struct lpc_debugfs_entry *lpc = filp->private_data; + u32 data, pos, len, todo; + int rc; + + if (!access_ok(VERIFY_WRITE, ubuf, count)) + return -EFAULT; + + todo = count; + while (todo) { + pos = *ppos; + + /* + * Select access size based on count and alignment and + * access type. IO and MEM only support byte acceses, + * FW supports all 3. + */ + len = 1; + if (lpc->lpc_type == OPAL_LPC_FW) { + if (todo > 3 && (pos & 3) == 0) + len = 4; + else if (todo > 1 && (pos & 1) == 0) + len = 2; + } + rc = opal_lpc_read(opal_lpc_chip_id, lpc->lpc_type, pos, + &data, len); + if (rc) + return -ENXIO; + switch(len) { + case 4: + rc = __put_user((u32)data, (u32 __user *)ubuf); + break; + case 2: + rc = __put_user((u16)data, (u16 __user *)ubuf); + break; + default: + rc = __put_user((u8)data, (u8 __user *)ubuf); + break; + } + if (rc) + return -EFAULT; + *ppos += len; + ubuf += len; + todo -= len; + } + + return count; +} + +static ssize_t lpc_debug_write(struct file *filp, const char __user *ubuf, + size_t count, loff_t *ppos) +{ + struct lpc_debugfs_entry *lpc = filp->private_data; + u32 data, pos, len, todo; + int rc; + + if (!access_ok(VERIFY_READ, ubuf, count)) + return -EFAULT; + + todo = count; + while (todo) { + pos = *ppos; + + /* + * Select access size based on count and alignment and + * access type. IO and MEM only support byte acceses, + * FW supports all 3. + */ + len = 1; + if (lpc->lpc_type == OPAL_LPC_FW) { + if (todo > 3 && (pos & 3) == 0) + len = 4; + else if (todo > 1 && (pos & 1) == 0) + len = 2; + } + switch(len) { + case 4: + rc = __get_user(data, (u32 __user *)ubuf); + break; + case 2: + rc = __get_user(data, (u16 __user *)ubuf); + break; + default: + rc = __get_user(data, (u8 __user *)ubuf); + break; + } + if (rc) + return -EFAULT; + + rc = opal_lpc_write(opal_lpc_chip_id, lpc->lpc_type, pos, + data, len); + if (rc) + return -ENXIO; + *ppos += len; + ubuf += len; + todo -= len; + } + + return count; +} + +static const struct file_operations lpc_fops = { + .read = lpc_debug_read, + .write = lpc_debug_write, + .open = simple_open, + .llseek = default_llseek, +}; + +static int opal_lpc_debugfs_create_type(struct dentry *folder, + const char *fname, + enum OpalLPCAddressType type) +{ + struct lpc_debugfs_entry *entry; + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + return -ENOMEM; + entry->lpc_type = type; + debugfs_create_file(fname, 0600, folder, entry, &lpc_fops); + return 0; +} + +static int opal_lpc_init_debugfs(void) +{ + struct dentry *root; + int rc = 0; + + if (opal_lpc_chip_id < 0) + return -ENODEV; + + root = debugfs_create_dir("lpc", powerpc_debugfs_root); + + rc |= opal_lpc_debugfs_create_type(root, "io", OPAL_LPC_IO); + rc |= opal_lpc_debugfs_create_type(root, "mem", OPAL_LPC_MEM); + rc |= opal_lpc_debugfs_create_type(root, "fw", OPAL_LPC_FW); + return rc; +} +device_initcall(opal_lpc_init_debugfs); +#endif /* CONFIG_DEBUG_FS */ + +void opal_lpc_init(void) +{ + struct device_node *np; + + /* + * Look for a Power8 LPC bus tagged as "primary", + * we currently support only one though the OPAL APIs + * support any number. + */ + for_each_compatible_node(np, NULL, "ibm,power8-lpc") { + if (!of_device_is_available(np)) + continue; + if (!of_get_property(np, "primary", NULL)) + continue; + opal_lpc_chip_id = of_get_ibm_chip_id(np); + break; + } + if (opal_lpc_chip_id < 0) + return; + + /* Setup special IO ops */ + ppc_pci_io = opal_lpc_io; + isa_io_special = true; + + pr_info("OPAL: Power8 LPC bus found, chip ID %d\n", opal_lpc_chip_id); +} diff --git a/arch/powerpc/platforms/powernv/opal-memory-errors.c b/arch/powerpc/platforms/powernv/opal-memory-errors.c new file mode 100644 index 00000000000..b17a34b695e --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-memory-errors.c @@ -0,0 +1,146 @@ +/* + * OPAL asynchronus Memory error handling support in PowreNV. + * + * 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., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright 2013 IBM Corporation + * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> + */ + +#undef DEBUG + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/of.h> +#include <linux/mm.h> +#include <linux/slab.h> + +#include <asm/opal.h> +#include <asm/cputable.h> + +static int opal_mem_err_nb_init; +static LIST_HEAD(opal_memory_err_list); +static DEFINE_SPINLOCK(opal_mem_err_lock); + +struct OpalMsgNode { + struct list_head list; + struct opal_msg msg; +}; + +static void handle_memory_error_event(struct OpalMemoryErrorData *merr_evt) +{ + uint64_t paddr_start, paddr_end; + + pr_debug("%s: Retrived memory error event, type: 0x%x\n", + __func__, merr_evt->type); + switch (merr_evt->type) { + case OPAL_MEM_ERR_TYPE_RESILIENCE: + paddr_start = be64_to_cpu(merr_evt->u.resilience.physical_address_start); + paddr_end = be64_to_cpu(merr_evt->u.resilience.physical_address_end); + break; + case OPAL_MEM_ERR_TYPE_DYN_DALLOC: + paddr_start = be64_to_cpu(merr_evt->u.dyn_dealloc.physical_address_start); + paddr_end = be64_to_cpu(merr_evt->u.dyn_dealloc.physical_address_end); + break; + default: + return; + } + + for (; paddr_start < paddr_end; paddr_start += PAGE_SIZE) { + memory_failure(paddr_start >> PAGE_SHIFT, 0, 0); + } +} + +static void handle_memory_error(void) +{ + unsigned long flags; + struct OpalMemoryErrorData *merr_evt; + struct OpalMsgNode *msg_node; + + spin_lock_irqsave(&opal_mem_err_lock, flags); + while (!list_empty(&opal_memory_err_list)) { + msg_node = list_entry(opal_memory_err_list.next, + struct OpalMsgNode, list); + list_del(&msg_node->list); + spin_unlock_irqrestore(&opal_mem_err_lock, flags); + + merr_evt = (struct OpalMemoryErrorData *) + &msg_node->msg.params[0]; + handle_memory_error_event(merr_evt); + kfree(msg_node); + spin_lock_irqsave(&opal_mem_err_lock, flags); + } + spin_unlock_irqrestore(&opal_mem_err_lock, flags); +} + +static void mem_error_handler(struct work_struct *work) +{ + handle_memory_error(); +} + +static DECLARE_WORK(mem_error_work, mem_error_handler); + +/* + * opal_memory_err_event - notifier handler that queues up the opal message + * to be preocessed later. + */ +static int opal_memory_err_event(struct notifier_block *nb, + unsigned long msg_type, void *msg) +{ + unsigned long flags; + struct OpalMsgNode *msg_node; + + if (msg_type != OPAL_MSG_MEM_ERR) + return 0; + + msg_node = kzalloc(sizeof(*msg_node), GFP_ATOMIC); + if (!msg_node) { + pr_err("MEMORY_ERROR: out of memory, Opal message event not" + "handled\n"); + return -ENOMEM; + } + memcpy(&msg_node->msg, msg, sizeof(struct opal_msg)); + + spin_lock_irqsave(&opal_mem_err_lock, flags); + list_add(&msg_node->list, &opal_memory_err_list); + spin_unlock_irqrestore(&opal_mem_err_lock, flags); + + schedule_work(&mem_error_work); + return 0; +} + +static struct notifier_block opal_mem_err_nb = { + .notifier_call = opal_memory_err_event, + .next = NULL, + .priority = 0, +}; + +static int __init opal_mem_err_init(void) +{ + int ret; + + if (!opal_mem_err_nb_init) { + ret = opal_message_notifier_register( + OPAL_MSG_MEM_ERR, &opal_mem_err_nb); + if (ret) { + pr_err("%s: Can't register OPAL event notifier (%d)\n", + __func__, ret); + return ret; + } + opal_mem_err_nb_init = 1; + } + return 0; +} +subsys_initcall(opal_mem_err_init); diff --git a/arch/powerpc/platforms/powernv/opal-msglog.c b/arch/powerpc/platforms/powernv/opal-msglog.c new file mode 100644 index 00000000000..44ed78af1a0 --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-msglog.c @@ -0,0 +1,124 @@ +/* + * PowerNV OPAL in-memory console interface + * + * Copyright 2014 IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <asm/io.h> +#include <asm/opal.h> +#include <linux/debugfs.h> +#include <linux/of.h> +#include <linux/types.h> +#include <asm/barrier.h> + +/* OPAL in-memory console. Defined in OPAL source at core/console.c */ +struct memcons { + __be64 magic; +#define MEMCONS_MAGIC 0x6630696567726173L + __be64 obuf_phys; + __be64 ibuf_phys; + __be32 obuf_size; + __be32 ibuf_size; + __be32 out_pos; +#define MEMCONS_OUT_POS_WRAP 0x80000000u +#define MEMCONS_OUT_POS_MASK 0x00ffffffu + __be32 in_prod; + __be32 in_cons; +}; + +static ssize_t opal_msglog_read(struct file *file, struct kobject *kobj, + struct bin_attribute *bin_attr, char *to, + loff_t pos, size_t count) +{ + struct memcons *mc = bin_attr->private; + const char *conbuf; + ssize_t ret; + size_t first_read = 0; + uint32_t out_pos, avail; + + if (!mc) + return -ENODEV; + + out_pos = be32_to_cpu(ACCESS_ONCE(mc->out_pos)); + + /* Now we've read out_pos, put a barrier in before reading the new + * data it points to in conbuf. */ + smp_rmb(); + + conbuf = phys_to_virt(be64_to_cpu(mc->obuf_phys)); + + /* When the buffer has wrapped, read from the out_pos marker to the end + * of the buffer, and then read the remaining data as in the un-wrapped + * case. */ + if (out_pos & MEMCONS_OUT_POS_WRAP) { + + out_pos &= MEMCONS_OUT_POS_MASK; + avail = be32_to_cpu(mc->obuf_size) - out_pos; + + ret = memory_read_from_buffer(to, count, &pos, + conbuf + out_pos, avail); + + if (ret < 0) + goto out; + + first_read = ret; + to += first_read; + count -= first_read; + pos -= avail; + + if (count <= 0) + goto out; + } + + /* Sanity check. The firmware should not do this to us. */ + if (out_pos > be32_to_cpu(mc->obuf_size)) { + pr_err("OPAL: memory console corruption. Aborting read.\n"); + return -EINVAL; + } + + ret = memory_read_from_buffer(to, count, &pos, conbuf, out_pos); + + if (ret < 0) + goto out; + + ret += first_read; +out: + return ret; +} + +static struct bin_attribute opal_msglog_attr = { + .attr = {.name = "msglog", .mode = 0444}, + .read = opal_msglog_read +}; + +void __init opal_msglog_init(void) +{ + u64 mcaddr; + struct memcons *mc; + + if (of_property_read_u64(opal_node, "ibm,opal-memcons", &mcaddr)) { + pr_warn("OPAL: Property ibm,opal-memcons not found, no message log\n"); + return; + } + + mc = phys_to_virt(mcaddr); + if (!mc) { + pr_warn("OPAL: memory console address is invalid\n"); + return; + } + + if (be64_to_cpu(mc->magic) != MEMCONS_MAGIC) { + pr_warn("OPAL: memory console version is invalid\n"); + return; + } + + opal_msglog_attr.private = mc; + + if (sysfs_create_bin_file(opal_kobj, &opal_msglog_attr) != 0) + pr_warn("OPAL: sysfs file creation failed\n"); +} diff --git a/arch/powerpc/platforms/powernv/opal-nvram.c b/arch/powerpc/platforms/powernv/opal-nvram.c index 3f83e1ae26a..acd9f7e9667 100644 --- a/arch/powerpc/platforms/powernv/opal-nvram.c +++ b/arch/powerpc/platforms/powernv/opal-nvram.c @@ -65,7 +65,7 @@ static ssize_t opal_nvram_write(char *buf, size_t count, loff_t *index) void __init opal_nvram_init(void) { struct device_node *np; - const u32 *nbytes_p; + const __be32 *nbytes_p; np = of_find_compatible_node(NULL, NULL, "ibm,opal-nvram"); if (np == NULL) @@ -76,7 +76,7 @@ void __init opal_nvram_init(void) of_node_put(np); return; } - nvram_size = *nbytes_p; + nvram_size = be32_to_cpup(nbytes_p); printk(KERN_INFO "OPAL nvram setup, %u bytes\n", nvram_size); of_node_put(np); diff --git a/arch/powerpc/platforms/powernv/opal-rtc.c b/arch/powerpc/platforms/powernv/opal-rtc.c index 2aa7641aac9..b1885db8fdf 100644 --- a/arch/powerpc/platforms/powernv/opal-rtc.c +++ b/arch/powerpc/platforms/powernv/opal-rtc.c @@ -18,6 +18,7 @@ #include <asm/opal.h> #include <asm/firmware.h> +#include <asm/machdep.h> static void opal_to_tm(u32 y_m_d, u64 h_m_s_ms, struct rtc_time *tm) { @@ -37,17 +38,24 @@ unsigned long __init opal_get_boot_time(void) struct rtc_time tm; u32 y_m_d; u64 h_m_s_ms; + __be32 __y_m_d; + __be64 __h_m_s_ms; long rc = OPAL_BUSY; while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { - rc = opal_rtc_read(&y_m_d, &h_m_s_ms); + rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms); if (rc == OPAL_BUSY_EVENT) opal_poll_events(NULL); else mdelay(10); } - if (rc != OPAL_SUCCESS) + if (rc != OPAL_SUCCESS) { + ppc_md.get_rtc_time = NULL; + ppc_md.set_rtc_time = NULL; return 0; + } + y_m_d = be32_to_cpu(__y_m_d); + h_m_s_ms = be64_to_cpu(__h_m_s_ms); opal_to_tm(y_m_d, h_m_s_ms, &tm); return mktime(tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday, tm.tm_hour, tm.tm_min, tm.tm_sec); @@ -58,9 +66,11 @@ void opal_get_rtc_time(struct rtc_time *tm) long rc = OPAL_BUSY; u32 y_m_d; u64 h_m_s_ms; + __be32 __y_m_d; + __be64 __h_m_s_ms; while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { - rc = opal_rtc_read(&y_m_d, &h_m_s_ms); + rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms); if (rc == OPAL_BUSY_EVENT) opal_poll_events(NULL); else @@ -68,6 +78,8 @@ void opal_get_rtc_time(struct rtc_time *tm) } if (rc != OPAL_SUCCESS) return; + y_m_d = be32_to_cpu(__y_m_d); + h_m_s_ms = be64_to_cpu(__h_m_s_ms); opal_to_tm(y_m_d, h_m_s_ms, tm); } diff --git a/arch/powerpc/platforms/powernv/opal-sensor.c b/arch/powerpc/platforms/powernv/opal-sensor.c new file mode 100644 index 00000000000..10271ad1fac --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-sensor.c @@ -0,0 +1,66 @@ +/* + * PowerNV sensor code + * + * Copyright (C) 2013 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include <linux/delay.h> +#include <linux/mutex.h> +#include <asm/opal.h> + +static DEFINE_MUTEX(opal_sensor_mutex); + +/* + * This will return sensor information to driver based on the requested sensor + * handle. A handle is an opaque id for the powernv, read by the driver from the + * device tree.. + */ +int opal_get_sensor_data(u32 sensor_hndl, u32 *sensor_data) +{ + int ret, token; + struct opal_msg msg; + __be32 data; + + token = opal_async_get_token_interruptible(); + if (token < 0) { + pr_err("%s: Couldn't get the token, returning\n", __func__); + ret = token; + goto out; + } + + mutex_lock(&opal_sensor_mutex); + ret = opal_sensor_read(sensor_hndl, token, &data); + if (ret != OPAL_ASYNC_COMPLETION) + 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; + } + + *sensor_data = be32_to_cpu(data); + ret = be64_to_cpu(msg.params[1]); + +out_token: + mutex_unlock(&opal_sensor_mutex); + opal_async_release_token(token); +out: + return ret; +} +EXPORT_SYMBOL_GPL(opal_get_sensor_data); diff --git a/arch/powerpc/platforms/powernv/opal-sysparam.c b/arch/powerpc/platforms/powernv/opal-sysparam.c new file mode 100644 index 00000000000..9d1acf22a09 --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-sysparam.c @@ -0,0 +1,304 @@ +/* + * PowerNV system parameter code + * + * Copyright (C) 2013 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include <linux/kobject.h> +#include <linux/mutex.h> +#include <linux/slab.h> +#include <linux/of.h> +#include <linux/gfp.h> +#include <linux/stat.h> +#include <asm/opal.h> + +#define MAX_PARAM_DATA_LEN 64 + +static DEFINE_MUTEX(opal_sysparam_mutex); +static struct kobject *sysparam_kobj; +static void *param_data_buf; + +struct param_attr { + struct list_head list; + u32 param_id; + u32 param_size; + struct kobj_attribute kobj_attr; +}; + +static ssize_t opal_get_sys_param(u32 param_id, u32 length, void *buffer) +{ + struct opal_msg msg; + ssize_t ret; + int token; + + token = opal_async_get_token_interruptible(); + if (token < 0) { + if (token != -ERESTARTSYS) + pr_err("%s: Couldn't get the token, returning\n", + __func__); + ret = token; + goto out; + } + + ret = opal_get_param(token, param_id, (u64)buffer, length); + if (ret != OPAL_ASYNC_COMPLETION) + goto out_token; + + ret = opal_async_wait_response(token, &msg); + if (ret) { + pr_err("%s: Failed to wait for the async response, %zd\n", + __func__, ret); + goto out_token; + } + + ret = be64_to_cpu(msg.params[1]); + +out_token: + opal_async_release_token(token); +out: + return ret; +} + +static int opal_set_sys_param(u32 param_id, u32 length, void *buffer) +{ + struct opal_msg msg; + int ret, token; + + token = opal_async_get_token_interruptible(); + if (token < 0) { + if (token != -ERESTARTSYS) + pr_err("%s: Couldn't get the token, returning\n", + __func__); + ret = token; + goto out; + } + + ret = opal_set_param(token, param_id, (u64)buffer, length); + + if (ret != OPAL_ASYNC_COMPLETION) + 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 = be64_to_cpu(msg.params[1]); + +out_token: + opal_async_release_token(token); +out: + return ret; +} + +static ssize_t sys_param_show(struct kobject *kobj, + struct kobj_attribute *kobj_attr, char *buf) +{ + struct param_attr *attr = container_of(kobj_attr, struct param_attr, + kobj_attr); + ssize_t ret; + + mutex_lock(&opal_sysparam_mutex); + ret = opal_get_sys_param(attr->param_id, attr->param_size, + param_data_buf); + if (ret) + goto out; + + memcpy(buf, param_data_buf, attr->param_size); + + ret = attr->param_size; +out: + mutex_unlock(&opal_sysparam_mutex); + return ret; +} + +static ssize_t sys_param_store(struct kobject *kobj, + struct kobj_attribute *kobj_attr, const char *buf, size_t count) +{ + struct param_attr *attr = container_of(kobj_attr, struct param_attr, + kobj_attr); + ssize_t ret; + + /* MAX_PARAM_DATA_LEN is sizeof(param_data_buf) */ + if (count > MAX_PARAM_DATA_LEN) + count = MAX_PARAM_DATA_LEN; + + mutex_lock(&opal_sysparam_mutex); + memcpy(param_data_buf, buf, count); + ret = opal_set_sys_param(attr->param_id, attr->param_size, + param_data_buf); + mutex_unlock(&opal_sysparam_mutex); + if (!ret) + ret = count; + return ret; +} + +void __init opal_sys_param_init(void) +{ + struct device_node *sysparam; + struct param_attr *attr; + u32 *id, *size; + int count, i; + u8 *perm; + + if (!opal_kobj) { + pr_warn("SYSPARAM: opal kobject is not available\n"); + goto out; + } + + sysparam_kobj = kobject_create_and_add("sysparams", opal_kobj); + if (!sysparam_kobj) { + pr_err("SYSPARAM: Failed to create sysparam kobject\n"); + goto out; + } + + /* Allocate big enough buffer for any get/set transactions */ + param_data_buf = kzalloc(MAX_PARAM_DATA_LEN, GFP_KERNEL); + if (!param_data_buf) { + pr_err("SYSPARAM: Failed to allocate memory for param data " + "buf\n"); + goto out_kobj_put; + } + + sysparam = of_find_node_by_path("/ibm,opal/sysparams"); + if (!sysparam) { + pr_err("SYSPARAM: Opal sysparam node not found\n"); + goto out_param_buf; + } + + if (!of_device_is_compatible(sysparam, "ibm,opal-sysparams")) { + pr_err("SYSPARAM: Opal sysparam node not compatible\n"); + goto out_node_put; + } + + /* Number of parameters exposed through DT */ + count = of_property_count_strings(sysparam, "param-name"); + if (count < 0) { + pr_err("SYSPARAM: No string found of property param-name in " + "the node %s\n", sysparam->name); + goto out_node_put; + } + + id = kzalloc(sizeof(*id) * count, GFP_KERNEL); + if (!id) { + pr_err("SYSPARAM: Failed to allocate memory to read parameter " + "id\n"); + goto out_node_put; + } + + size = kzalloc(sizeof(*size) * count, GFP_KERNEL); + if (!size) { + pr_err("SYSPARAM: Failed to allocate memory to read parameter " + "size\n"); + goto out_free_id; + } + + perm = kzalloc(sizeof(*perm) * count, GFP_KERNEL); + if (!perm) { + pr_err("SYSPARAM: Failed to allocate memory to read supported " + "action on the parameter"); + goto out_free_size; + } + + if (of_property_read_u32_array(sysparam, "param-id", id, count)) { + pr_err("SYSPARAM: Missing property param-id in the DT\n"); + goto out_free_perm; + } + + if (of_property_read_u32_array(sysparam, "param-len", size, count)) { + pr_err("SYSPARAM: Missing property param-len in the DT\n"); + goto out_free_perm; + } + + + if (of_property_read_u8_array(sysparam, "param-perm", perm, count)) { + pr_err("SYSPARAM: Missing property param-perm in the DT\n"); + goto out_free_perm; + } + + attr = kzalloc(sizeof(*attr) * count, GFP_KERNEL); + if (!attr) { + pr_err("SYSPARAM: Failed to allocate memory for parameter " + "attributes\n"); + goto out_free_perm; + } + + /* For each of the parameters, populate the parameter attributes */ + for (i = 0; i < count; i++) { + if (size[i] > MAX_PARAM_DATA_LEN) { + pr_warn("SYSPARAM: Not creating parameter %d as size " + "exceeds buffer length\n", i); + continue; + } + + sysfs_attr_init(&attr[i].kobj_attr.attr); + attr[i].param_id = id[i]; + attr[i].param_size = size[i]; + if (of_property_read_string_index(sysparam, "param-name", i, + &attr[i].kobj_attr.attr.name)) + continue; + + /* If the parameter is read-only or read-write */ + switch (perm[i] & 3) { + case OPAL_SYSPARAM_READ: + attr[i].kobj_attr.attr.mode = S_IRUGO; + break; + case OPAL_SYSPARAM_WRITE: + attr[i].kobj_attr.attr.mode = S_IWUSR; + break; + case OPAL_SYSPARAM_RW: + attr[i].kobj_attr.attr.mode = S_IRUGO | S_IWUSR; + break; + default: + break; + } + + attr[i].kobj_attr.show = sys_param_show; + attr[i].kobj_attr.store = sys_param_store; + + if (sysfs_create_file(sysparam_kobj, &attr[i].kobj_attr.attr)) { + pr_err("SYSPARAM: Failed to create sysfs file %s\n", + attr[i].kobj_attr.attr.name); + goto out_free_attr; + } + } + + kfree(perm); + kfree(size); + kfree(id); + of_node_put(sysparam); + return; + +out_free_attr: + kfree(attr); +out_free_perm: + kfree(perm); +out_free_size: + kfree(size); +out_free_id: + kfree(id); +out_node_put: + of_node_put(sysparam); +out_param_buf: + kfree(param_data_buf); +out_kobj_put: + kobject_put(sysparam_kobj); +out: + return; +} diff --git a/arch/powerpc/platforms/powernv/opal-takeover.S b/arch/powerpc/platforms/powernv/opal-takeover.S deleted file mode 100644 index 3cd262897c2..00000000000 --- a/arch/powerpc/platforms/powernv/opal-takeover.S +++ /dev/null @@ -1,138 +0,0 @@ -/* - * PowerNV OPAL takeover assembly code, for use by prom_init.c - * - * Copyright 2011 IBM Corp. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <asm/ppc_asm.h> -#include <asm/hvcall.h> -#include <asm/asm-offsets.h> -#include <asm/opal.h> - -#define H_HAL_TAKEOVER 0x5124 -#define H_HAL_TAKEOVER_QUERY_MAGIC -1 - - .text -_GLOBAL(opal_query_takeover) - mfcr r0 - stw r0,8(r1) - std r3,STK_PARAM(R3)(r1) - std r4,STK_PARAM(R4)(r1) - li r3,H_HAL_TAKEOVER - li r4,H_HAL_TAKEOVER_QUERY_MAGIC - HVSC - ld r10,STK_PARAM(R3)(r1) - std r4,0(r10) - ld r10,STK_PARAM(R4)(r1) - std r5,0(r10) - lwz r0,8(r1) - mtcrf 0xff,r0 - blr - -_GLOBAL(opal_do_takeover) - mfcr r0 - stw r0,8(r1) - mflr r0 - std r0,16(r1) - bl __opal_do_takeover - ld r0,16(r1) - mtlr r0 - lwz r0,8(r1) - mtcrf 0xff,r0 - blr - -__opal_do_takeover: - ld r4,0(r3) - ld r5,0x8(r3) - ld r6,0x10(r3) - ld r7,0x18(r3) - ld r8,0x20(r3) - ld r9,0x28(r3) - ld r10,0x30(r3) - ld r11,0x38(r3) - li r3,H_HAL_TAKEOVER - HVSC - blr - - .globl opal_secondary_entry -opal_secondary_entry: - mr r31,r3 - mfmsr r11 - li r12,(MSR_SF | MSR_ISF)@highest - sldi r12,r12,48 - or r11,r11,r12 - mtmsrd r11 - isync - mfspr r4,SPRN_PIR - std r4,0(r3) -1: HMT_LOW - ld r4,8(r3) - cmpli cr0,r4,0 - beq 1b - HMT_MEDIUM -1: addi r3,r31,16 - bl __opal_do_takeover - b 1b - -_GLOBAL(opal_enter_rtas) - mflr r0 - std r0,16(r1) - stdu r1,-PROM_FRAME_SIZE(r1) /* Save SP and create stack space */ - - /* Because PROM is running in 32b mode, it clobbers the high order half - * of all registers that it saves. We therefore save those registers - * PROM might touch to the stack. (r0, r3-r13 are caller saved) - */ - SAVE_GPR(2, r1) - SAVE_GPR(13, r1) - SAVE_8GPRS(14, r1) - SAVE_10GPRS(22, r1) - mfcr r10 - mfmsr r11 - std r10,_CCR(r1) - std r11,_MSR(r1) - - /* Get the PROM entrypoint */ - mtlr r5 - - /* Switch MSR to 32 bits mode - */ - li r12,1 - rldicr r12,r12,MSR_SF_LG,(63-MSR_SF_LG) - andc r11,r11,r12 - li r12,1 - rldicr r12,r12,MSR_ISF_LG,(63-MSR_ISF_LG) - andc r11,r11,r12 - mtmsrd r11 - isync - - /* Enter RTAS here... */ - blrl - - /* Just make sure that r1 top 32 bits didn't get - * corrupt by OF - */ - rldicl r1,r1,0,32 - - /* Restore the MSR (back to 64 bits) */ - ld r0,_MSR(r1) - MTMSRD(r0) - isync - - /* Restore other registers */ - REST_GPR(2, r1) - REST_GPR(13, r1) - REST_8GPRS(14, r1) - REST_10GPRS(22, r1) - ld r4,_CCR(r1) - mtcr r4 - - addi r1,r1,PROM_FRAME_SIZE - ld r0,16(r1) - mtlr r0 - blr diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index 3bb07e5e43c..4abbff22a61 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -24,7 +24,7 @@ mflr r0; \ mfcr r12; \ std r0,16(r1); \ - std r12,8(r1); \ + stw r12,8(r1); \ std r1,PACAR1(r13); \ li r0,0; \ mfmsr r12; \ @@ -32,9 +32,9 @@ std r12,PACASAVEDMSR(r13); \ andc r12,r12,r0; \ mtmsrd r12,1; \ - LOAD_REG_ADDR(r0,.opal_return); \ + LOAD_REG_ADDR(r0,opal_return); \ mtlr r0; \ - li r0,MSR_DR|MSR_IR; \ + li r0,MSR_DR|MSR_IR|MSR_LE;\ andc r12,r12,r0; \ li r0,token; \ mtspr SPRN_HSRR1,r12; \ @@ -44,9 +44,16 @@ mtspr SPRN_HSRR0,r12; \ hrfid -_STATIC(opal_return) +opal_return: + /* + * Fixup endian on OPAL return... we should be able to simplify + * this by instead converting the below trampoline to a set of + * bytes (always BE) since MSR:LE will end up fixed up as a side + * effect of the rfid. + */ + FIXUP_ENDIAN ld r2,PACATOC(r13); - ld r4,8(r1); + lwz r4,8(r1); ld r5,16(r1); ld r6,PACASAVEDMSR(r13); mtspr SPRN_SRR0,r5; @@ -54,6 +61,7 @@ _STATIC(opal_return) mtcr r4; rfid +OPAL_CALL(opal_invalid_call, OPAL_INVALID_CALL); OPAL_CALL(opal_console_write, OPAL_CONSOLE_WRITE); OPAL_CALL(opal_console_read, OPAL_CONSOLE_READ); OPAL_CALL(opal_console_write_buffer_space, OPAL_CONSOLE_WRITE_BUFFER_SPACE); @@ -107,3 +115,34 @@ OPAL_CALL(opal_pci_mask_pe_error, OPAL_PCI_MASK_PE_ERROR); OPAL_CALL(opal_set_slot_led_status, OPAL_SET_SLOT_LED_STATUS); OPAL_CALL(opal_get_epow_status, OPAL_GET_EPOW_STATUS); OPAL_CALL(opal_set_system_attention_led, OPAL_SET_SYSTEM_ATTENTION_LED); +OPAL_CALL(opal_pci_next_error, OPAL_PCI_NEXT_ERROR); +OPAL_CALL(opal_pci_poll, OPAL_PCI_POLL); +OPAL_CALL(opal_pci_msi_eoi, OPAL_PCI_MSI_EOI); +OPAL_CALL(opal_pci_get_phb_diag_data2, OPAL_PCI_GET_PHB_DIAG_DATA2); +OPAL_CALL(opal_xscom_read, OPAL_XSCOM_READ); +OPAL_CALL(opal_xscom_write, OPAL_XSCOM_WRITE); +OPAL_CALL(opal_lpc_read, OPAL_LPC_READ); +OPAL_CALL(opal_lpc_write, OPAL_LPC_WRITE); +OPAL_CALL(opal_return_cpu, OPAL_RETURN_CPU); +OPAL_CALL(opal_reinit_cpus, OPAL_REINIT_CPUS); +OPAL_CALL(opal_read_elog, OPAL_ELOG_READ); +OPAL_CALL(opal_send_ack_elog, OPAL_ELOG_ACK); +OPAL_CALL(opal_get_elog_size, OPAL_ELOG_SIZE); +OPAL_CALL(opal_resend_pending_logs, OPAL_ELOG_RESEND); +OPAL_CALL(opal_write_elog, OPAL_ELOG_WRITE); +OPAL_CALL(opal_validate_flash, OPAL_FLASH_VALIDATE); +OPAL_CALL(opal_manage_flash, OPAL_FLASH_MANAGE); +OPAL_CALL(opal_update_flash, OPAL_FLASH_UPDATE); +OPAL_CALL(opal_resync_timebase, OPAL_RESYNC_TIMEBASE); +OPAL_CALL(opal_dump_init, OPAL_DUMP_INIT); +OPAL_CALL(opal_dump_info, OPAL_DUMP_INFO); +OPAL_CALL(opal_dump_info2, OPAL_DUMP_INFO2); +OPAL_CALL(opal_dump_read, OPAL_DUMP_READ); +OPAL_CALL(opal_dump_ack, OPAL_DUMP_ACK); +OPAL_CALL(opal_get_msg, OPAL_GET_MSG); +OPAL_CALL(opal_check_completion, OPAL_CHECK_ASYNC_COMPLETION); +OPAL_CALL(opal_dump_resend_notification, OPAL_DUMP_RESEND); +OPAL_CALL(opal_sync_host_reboot, OPAL_SYNC_HOST_REBOOT); +OPAL_CALL(opal_sensor_read, OPAL_SENSOR_READ); +OPAL_CALL(opal_get_param, OPAL_GET_PARAM); +OPAL_CALL(opal_set_param, OPAL_SET_PARAM); diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c new file mode 100644 index 00000000000..4cd2ea6c0db --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-xscom.c @@ -0,0 +1,133 @@ +/* + * PowerNV LPC bus handling. + * + * Copyright 2013 IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/of.h> +#include <linux/bug.h> +#include <linux/gfp.h> +#include <linux/slab.h> + +#include <asm/machdep.h> +#include <asm/firmware.h> +#include <asm/opal.h> +#include <asm/scom.h> + +/* + * We could probably fit that inside the scom_map_t + * which is a void* after all but it's really too ugly + * so let's kmalloc it for now + */ +struct opal_scom_map { + uint32_t chip; + uint64_t addr; +}; + +static scom_map_t opal_scom_map(struct device_node *dev, u64 reg, u64 count) +{ + struct opal_scom_map *m; + const __be32 *gcid; + + if (!of_get_property(dev, "scom-controller", NULL)) { + pr_err("%s: device %s is not a SCOM controller\n", + __func__, dev->full_name); + return SCOM_MAP_INVALID; + } + gcid = of_get_property(dev, "ibm,chip-id", NULL); + if (!gcid) { + pr_err("%s: device %s has no ibm,chip-id\n", + __func__, dev->full_name); + return SCOM_MAP_INVALID; + } + m = kmalloc(sizeof(struct opal_scom_map), GFP_KERNEL); + if (!m) + return NULL; + m->chip = be32_to_cpup(gcid); + m->addr = reg; + + return (scom_map_t)m; +} + +static void opal_scom_unmap(scom_map_t map) +{ + kfree(map); +} + +static int opal_xscom_err_xlate(int64_t rc) +{ + switch(rc) { + case 0: + return 0; + /* Add more translations if necessary */ + default: + return -EIO; + } +} + +static u64 opal_scom_unmangle(u64 addr) +{ + /* + * XSCOM indirect addresses have the top bit set. Additionally + * the rest of the top 3 nibbles is always 0. + * + * Because the debugfs interface uses signed offsets and shifts + * the address left by 3, we basically cannot use the top 4 bits + * of the 64-bit address, and thus cannot use the indirect bit. + * + * To deal with that, we support the indirect bit being in bit + * 4 (IBM notation) instead of bit 0 in this API, we do the + * conversion here. To leave room for further xscom address + * expansion, we only clear out the top byte + * + * For in-kernel use, we also support the real indirect bit, so + * we test for any of the top 5 bits + * + */ + if (addr & (0x1full << 59)) + addr = (addr & ~(0xffull << 56)) | (1ull << 63); + return addr; +} + +static int opal_scom_read(scom_map_t map, u64 reg, u64 *value) +{ + struct opal_scom_map *m = map; + int64_t rc; + __be64 v; + + reg = opal_scom_unmangle(m->addr + reg); + rc = opal_xscom_read(m->chip, reg, (__be64 *)__pa(&v)); + *value = be64_to_cpu(v); + return opal_xscom_err_xlate(rc); +} + +static int opal_scom_write(scom_map_t map, u64 reg, u64 value) +{ + struct opal_scom_map *m = map; + int64_t rc; + + reg = opal_scom_unmangle(m->addr + reg); + rc = opal_xscom_write(m->chip, reg, value); + return opal_xscom_err_xlate(rc); +} + +static const struct scom_controller opal_scom_controller = { + .map = opal_scom_map, + .unmap = opal_scom_unmap, + .read = opal_scom_read, + .write = opal_scom_write +}; + +static int opal_xscom_init(void) +{ + if (firmware_has_feature(FW_FEATURE_OPALv3)) + scom_init(&opal_scom_controller); + return 0; +} +arch_initcall(opal_xscom_init); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index aaa0dba4947..199975613fe 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -13,93 +13,387 @@ #include <linux/types.h> #include <linux/of.h> +#include <linux/of_fdt.h> #include <linux/of_platform.h> #include <linux/interrupt.h> +#include <linux/notifier.h> +#include <linux/slab.h> +#include <linux/sched.h> +#include <linux/kobject.h> +#include <linux/delay.h> +#include <linux/memblock.h> #include <asm/opal.h> #include <asm/firmware.h> +#include <asm/mce.h> #include "powernv.h" +/* /sys/firmware/opal */ +struct kobject *opal_kobj; + struct opal { u64 base; u64 entry; + u64 size; } opal; -static struct device_node *opal_node; +struct mcheck_recoverable_range { + u64 start_addr; + u64 end_addr; + u64 recover_addr; +}; + +static struct mcheck_recoverable_range *mc_recoverable_range; +static int mc_recoverable_range_len; + +struct device_node *opal_node; static DEFINE_SPINLOCK(opal_write_lock); extern u64 opal_mc_secondary_handler[]; +static unsigned int *opal_irqs; +static unsigned int opal_irq_count; +static ATOMIC_NOTIFIER_HEAD(opal_notifier_head); +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 void opal_reinit_cores(void) +{ + /* Do the actual re-init, This will clobber all FPRs, VRs, etc... + * + * It will preserve non volatile GPRs and HSPRG0/1. It will + * also restore HIDs and other SPRs to their original value + * but it might clobber a bunch. + */ +#ifdef __BIG_ENDIAN__ + opal_reinit_cpus(OPAL_REINIT_CPUS_HILE_BE); +#else + opal_reinit_cpus(OPAL_REINIT_CPUS_HILE_LE); +#endif +} int __init early_init_dt_scan_opal(unsigned long node, const char *uname, int depth, void *data) { - const void *basep, *entryp; - unsigned long basesz, entrysz; - u64 glue; + const void *basep, *entryp, *sizep; + int basesz, entrysz, runtimesz; if (depth != 1 || strcmp(uname, "ibm,opal") != 0) return 0; basep = of_get_flat_dt_prop(node, "opal-base-address", &basesz); entryp = of_get_flat_dt_prop(node, "opal-entry-address", &entrysz); + sizep = of_get_flat_dt_prop(node, "opal-runtime-size", &runtimesz); - if (!basep || !entryp) + if (!basep || !entryp || !sizep) return 1; opal.base = of_read_number(basep, basesz/4); opal.entry = of_read_number(entryp, entrysz/4); + opal.size = of_read_number(sizep, runtimesz/4); - pr_debug("OPAL Base = 0x%llx (basep=%p basesz=%ld)\n", + pr_debug("OPAL Base = 0x%llx (basep=%p basesz=%d)\n", opal.base, basep, basesz); - pr_debug("OPAL Entry = 0x%llx (entryp=%p basesz=%ld)\n", + pr_debug("OPAL Entry = 0x%llx (entryp=%p basesz=%d)\n", opal.entry, entryp, entrysz); + pr_debug("OPAL Entry = 0x%llx (sizep=%p runtimesz=%d)\n", + opal.size, sizep, runtimesz); powerpc_firmware_features |= FW_FEATURE_OPAL; - if (of_flat_dt_is_compatible(node, "ibm,opal-v2")) { + if (of_flat_dt_is_compatible(node, "ibm,opal-v3")) { + powerpc_firmware_features |= FW_FEATURE_OPALv2; + powerpc_firmware_features |= FW_FEATURE_OPALv3; + printk("OPAL V3 detected !\n"); + } else if (of_flat_dt_is_compatible(node, "ibm,opal-v2")) { powerpc_firmware_features |= FW_FEATURE_OPALv2; printk("OPAL V2 detected !\n"); } else { printk("OPAL V1 detected !\n"); } - /* Hookup some exception handlers. We use the fwnmi area at 0x7000 - * to provide the glue space to OPAL + /* Reinit all cores with the right endian */ + opal_reinit_cores(); + + /* Restore some bits */ + if (cur_cpu_spec->cpu_restore) + cur_cpu_spec->cpu_restore(); + + return 1; +} + +int __init early_init_dt_scan_recoverable_ranges(unsigned long node, + const char *uname, int depth, void *data) +{ + int i, psize, size; + const __be32 *prop; + + if (depth != 1 || strcmp(uname, "ibm,opal") != 0) + return 0; + + prop = of_get_flat_dt_prop(node, "mcheck-recoverable-ranges", &psize); + + if (!prop) + return 1; + + pr_debug("Found machine check recoverable ranges.\n"); + + /* + * Calculate number of available entries. + * + * Each recoverable address range entry is (start address, len, + * recovery address), 2 cells each for start and recovery address, + * 1 cell for len, totalling 5 cells per entry. + */ + mc_recoverable_range_len = psize / (sizeof(*prop) * 5); + + /* Sanity check */ + if (!mc_recoverable_range_len) + return 1; + + /* Size required to hold all the entries. */ + size = mc_recoverable_range_len * + sizeof(struct mcheck_recoverable_range); + + /* + * Allocate a buffer to hold the MC recoverable ranges. We would be + * accessing them in real mode, hence it needs to be within + * RMO region. + */ + mc_recoverable_range =__va(memblock_alloc_base(size, __alignof__(u64), + ppc64_rma_size)); + memset(mc_recoverable_range, 0, size); + + for (i = 0; i < mc_recoverable_range_len; i++) { + mc_recoverable_range[i].start_addr = + of_read_number(prop + (i * 5) + 0, 2); + mc_recoverable_range[i].end_addr = + mc_recoverable_range[i].start_addr + + of_read_number(prop + (i * 5) + 2, 1); + mc_recoverable_range[i].recover_addr = + of_read_number(prop + (i * 5) + 3, 2); + + pr_debug("Machine check recoverable range: %llx..%llx: %llx\n", + mc_recoverable_range[i].start_addr, + mc_recoverable_range[i].end_addr, + mc_recoverable_range[i].recover_addr); + } + return 1; +} + +static int __init opal_register_exception_handlers(void) +{ +#ifdef __BIG_ENDIAN__ + u64 glue; + + if (!(powerpc_firmware_features & FW_FEATURE_OPAL)) + return -ENODEV; + + /* Hookup some exception handlers except machine check. We use the + * fwnmi area at 0x7000 to provide the glue space to OPAL */ glue = 0x7000; - opal_register_exception_handler(OPAL_MACHINE_CHECK_HANDLER, - __pa(opal_mc_secondary_handler[0]), - glue); - glue += 128; opal_register_exception_handler(OPAL_HYPERVISOR_MAINTENANCE_HANDLER, 0, glue); glue += 128; opal_register_exception_handler(OPAL_SOFTPATCH_HANDLER, 0, glue); +#endif - return 1; + return 0; +} + +early_initcall(opal_register_exception_handlers); + +int opal_notifier_register(struct notifier_block *nb) +{ + if (!nb) { + pr_warning("%s: Invalid argument (%p)\n", + __func__, nb); + return -EINVAL; + } + + atomic_notifier_chain_register(&opal_notifier_head, nb); + return 0; +} +EXPORT_SYMBOL_GPL(opal_notifier_register); + +int opal_notifier_unregister(struct notifier_block *nb) +{ + if (!nb) { + pr_warning("%s: Invalid argument (%p)\n", + __func__, nb); + return -EINVAL; + } + + atomic_notifier_chain_unregister(&opal_notifier_head, nb); + return 0; +} +EXPORT_SYMBOL_GPL(opal_notifier_unregister); + +static void opal_do_notifier(uint64_t events) +{ + unsigned long flags; + uint64_t changed_mask; + + if (atomic_read(&opal_notifier_hold)) + return; + + spin_lock_irqsave(&opal_notifier_lock, flags); + changed_mask = last_notified_mask ^ events; + last_notified_mask = events; + spin_unlock_irqrestore(&opal_notifier_lock, flags); + + /* + * We feed with the event bits and changed bits for + * enough information to the callback. + */ + atomic_notifier_call_chain(&opal_notifier_head, + events, (void *)changed_mask); +} + +void opal_notifier_update_evt(uint64_t evt_mask, + uint64_t evt_val) +{ + unsigned long flags; + + spin_lock_irqsave(&opal_notifier_lock, flags); + last_notified_mask &= ~evt_mask; + last_notified_mask |= evt_val; + spin_unlock_irqrestore(&opal_notifier_lock, flags); +} + +void opal_notifier_enable(void) +{ + int64_t rc; + __be64 evt = 0; + + atomic_set(&opal_notifier_hold, 0); + + /* Process pending events */ + rc = opal_poll_events(&evt); + if (rc == OPAL_SUCCESS && evt) + opal_do_notifier(be64_to_cpu(evt)); +} + +void opal_notifier_disable(void) +{ + atomic_set(&opal_notifier_hold, 1); +} + +/* + * 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, + 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", + __func__, msg_type); + return -EINVAL; + } + return atomic_notifier_chain_register( + &opal_msg_notifier_head[msg_type], nb); +} + +static void opal_message_do_notify(uint32_t msg_type, void *msg) +{ + /* notify subscribers */ + atomic_notifier_call_chain(&opal_msg_notifier_head[msg_type], + msg_type, msg); +} + +static void opal_handle_message(void) +{ + s64 ret; + /* + * TODO: pre-allocate a message buffer depending on opal-msg-size + * value in /proc/device-tree. + */ + static struct opal_msg msg; + u32 type; + + ret = opal_get_msg(__pa(&msg), sizeof(msg)); + /* No opal message pending. */ + if (ret == OPAL_RESOURCE) + return; + + /* check for errors. */ + if (ret) { + pr_warning("%s: Failed to retrive opal message, err=%lld\n", + __func__, ret); + return; + } + + type = be32_to_cpu(msg.msg_type); + + /* Sanity check */ + if (type > OPAL_MSG_TYPE_MAX) { + pr_warning("%s: Unknown message type: %u\n", __func__, type); + return; + } + opal_message_do_notify(type, (void *)&msg); } +static int opal_message_notify(struct notifier_block *nb, + unsigned long events, void *change) +{ + if (events & OPAL_EVENT_MSG_PENDING) + opal_handle_message(); + return 0; +} + +static struct notifier_block opal_message_nb = { + .notifier_call = opal_message_notify, + .next = NULL, + .priority = 0, +}; + +static int __init opal_message_init(void) +{ + int ret, i; + + for (i = 0; i < OPAL_MSG_TYPE_MAX; i++) + ATOMIC_INIT_NOTIFIER_HEAD(&opal_msg_notifier_head[i]); + + ret = opal_notifier_register(&opal_message_nb); + if (ret) { + pr_err("%s: Can't register OPAL event notifier (%d)\n", + __func__, ret); + return ret; + } + return 0; +} +early_initcall(opal_message_init); + int opal_get_chars(uint32_t vtermno, char *buf, int count) { - s64 len, rc; - u64 evt; + s64 rc; + __be64 evt, len; if (!opal.entry) return -ENODEV; opal_poll_events(&evt); - if ((evt & OPAL_EVENT_CONSOLE_INPUT) == 0) + if ((be64_to_cpu(evt) & OPAL_EVENT_CONSOLE_INPUT) == 0) return 0; - len = count; + len = cpu_to_be64(count); rc = opal_console_read(vtermno, &len, buf); if (rc == OPAL_SUCCESS) - return len; + return be64_to_cpu(len); return 0; } int opal_put_chars(uint32_t vtermno, const char *data, int total_len) { int written = 0; + __be64 olen; s64 len, rc; unsigned long flags; - u64 evt; + __be64 evt; if (!opal.entry) return -ENODEV; @@ -114,13 +408,14 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len) */ spin_lock_irqsave(&opal_write_lock, flags); if (firmware_has_feature(FW_FEATURE_OPALv2)) { - rc = opal_console_write_buffer_space(vtermno, &len); + rc = opal_console_write_buffer_space(vtermno, &olen); + len = be64_to_cpu(olen); if (rc || len < total_len) { spin_unlock_irqrestore(&opal_write_lock, flags); /* Closed -> drop characters */ if (rc) return total_len; - opal_poll_events(&evt); + opal_poll_events(NULL); return -EAGAIN; } } @@ -131,8 +426,16 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len) rc = OPAL_BUSY; while(total_len > 0 && (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT || rc == OPAL_SUCCESS)) { - len = total_len; - rc = opal_console_write(vtermno, &len, data); + olen = cpu_to_be64(total_len); + rc = opal_console_write(vtermno, &olen, data); + len = be64_to_cpu(olen); + + /* Closed or other error drop */ + if (rc != OPAL_SUCCESS && rc != OPAL_BUSY && + rc != OPAL_BUSY_EVENT) { + written = total_len; + break; + } if (rc == OPAL_SUCCESS) { total_len -= len; data += len; @@ -145,142 +448,129 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len) */ do opal_poll_events(&evt); - while(rc == OPAL_SUCCESS && (evt & OPAL_EVENT_CONSOLE_OUTPUT)); + while(rc == OPAL_SUCCESS && + (be64_to_cpu(evt) & OPAL_EVENT_CONSOLE_OUTPUT)); } spin_unlock_irqrestore(&opal_write_lock, flags); return written; } +static int opal_recover_mce(struct pt_regs *regs, + struct machine_check_event *evt) +{ + int recovered = 0; + uint64_t ea = get_mce_fault_addr(evt); + + if (!(regs->msr & MSR_RI)) { + /* If MSR_RI isn't set, we cannot recover */ + recovered = 0; + } else if (evt->disposition == MCE_DISPOSITION_RECOVERED) { + /* Platform corrected itself */ + recovered = 1; + } else if (ea && !is_kernel_addr(ea)) { + /* + * Faulting address is not in kernel text. We should be fine. + * We need to find which process uses this address. + * For now, kill the task if we have received exception when + * in userspace. + * + * TODO: Queue up this address for hwpoisioning later. + */ + if (user_mode(regs) && !is_global_init(current)) { + _exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip); + recovered = 1; + } else + recovered = 0; + } else if (user_mode(regs) && !is_global_init(current) && + evt->severity == MCE_SEV_ERROR_SYNC) { + /* + * If we have received a synchronous error when in userspace + * kill the task. + */ + _exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip); + recovered = 1; + } + return recovered; +} + int opal_machine_check(struct pt_regs *regs) { - struct opal_machine_check_event *opal_evt = get_paca()->opal_mc_evt; - struct opal_machine_check_event evt; - const char *level, *sevstr, *subtype; - static const char *opal_mc_ue_types[] = { - "Indeterminate", - "Instruction fetch", - "Page table walk ifetch", - "Load/Store", - "Page table walk Load/Store", - }; - static const char *opal_mc_slb_types[] = { - "Indeterminate", - "Parity", - "Multihit", - }; - static const char *opal_mc_erat_types[] = { - "Indeterminate", - "Parity", - "Multihit", - }; - static const char *opal_mc_tlb_types[] = { - "Indeterminate", - "Parity", - "Multihit", - }; - - /* Copy the event structure and release the original */ - evt = *opal_evt; - opal_evt->in_use = 0; + struct machine_check_event evt; + + if (!get_mce_event(&evt, MCE_EVENT_RELEASE)) + return 0; /* Print things out */ - if (evt.version != OpalMCE_V1) { + if (evt.version != MCE_V1) { pr_err("Machine Check Exception, Unknown event version %d !\n", evt.version); return 0; } - switch(evt.severity) { - case OpalMCE_SEV_NO_ERROR: - level = KERN_INFO; - sevstr = "Harmless"; - break; - case OpalMCE_SEV_WARNING: - level = KERN_WARNING; - sevstr = ""; - break; - case OpalMCE_SEV_ERROR_SYNC: - level = KERN_ERR; - sevstr = "Severe"; - break; - case OpalMCE_SEV_FATAL: - default: - level = KERN_ERR; - sevstr = "Fatal"; - break; - } + machine_check_print_event_info(&evt); - printk("%s%s Machine check interrupt [%s]\n", level, sevstr, - evt.disposition == OpalMCE_DISPOSITION_RECOVERED ? - "Recovered" : "[Not recovered"); - printk("%s Initiator: %s\n", level, - evt.initiator == OpalMCE_INITIATOR_CPU ? "CPU" : "Unknown"); - switch(evt.error_type) { - case OpalMCE_ERROR_TYPE_UE: - subtype = evt.u.ue_error.ue_error_type < - ARRAY_SIZE(opal_mc_ue_types) ? - opal_mc_ue_types[evt.u.ue_error.ue_error_type] - : "Unknown"; - printk("%s Error type: UE [%s]\n", level, subtype); - if (evt.u.ue_error.effective_address_provided) - printk("%s Effective address: %016llx\n", - level, evt.u.ue_error.effective_address); - if (evt.u.ue_error.physical_address_provided) - printk("%s Physial address: %016llx\n", - level, evt.u.ue_error.physical_address); - break; - case OpalMCE_ERROR_TYPE_SLB: - subtype = evt.u.slb_error.slb_error_type < - ARRAY_SIZE(opal_mc_slb_types) ? - opal_mc_slb_types[evt.u.slb_error.slb_error_type] - : "Unknown"; - printk("%s Error type: SLB [%s]\n", level, subtype); - if (evt.u.slb_error.effective_address_provided) - printk("%s Effective address: %016llx\n", - level, evt.u.slb_error.effective_address); - break; - case OpalMCE_ERROR_TYPE_ERAT: - subtype = evt.u.erat_error.erat_error_type < - ARRAY_SIZE(opal_mc_erat_types) ? - opal_mc_erat_types[evt.u.erat_error.erat_error_type] - : "Unknown"; - printk("%s Error type: ERAT [%s]\n", level, subtype); - if (evt.u.erat_error.effective_address_provided) - printk("%s Effective address: %016llx\n", - level, evt.u.erat_error.effective_address); - break; - case OpalMCE_ERROR_TYPE_TLB: - subtype = evt.u.tlb_error.tlb_error_type < - ARRAY_SIZE(opal_mc_tlb_types) ? - opal_mc_tlb_types[evt.u.tlb_error.tlb_error_type] - : "Unknown"; - printk("%s Error type: TLB [%s]\n", level, subtype); - if (evt.u.tlb_error.effective_address_provided) - printk("%s Effective address: %016llx\n", - level, evt.u.tlb_error.effective_address); - break; - default: - case OpalMCE_ERROR_TYPE_UNKNOWN: - printk("%s Error type: Unknown\n", level); - break; - } - return evt.severity == OpalMCE_SEV_FATAL ? 0 : 1; + if (opal_recover_mce(regs, &evt)) + return 1; + return 0; +} + +static uint64_t find_recovery_address(uint64_t nip) +{ + int i; + + for (i = 0; i < mc_recoverable_range_len; i++) + if ((nip >= mc_recoverable_range[i].start_addr) && + (nip < mc_recoverable_range[i].end_addr)) + return mc_recoverable_range[i].recover_addr; + return 0; +} + +bool opal_mce_check_early_recovery(struct pt_regs *regs) +{ + uint64_t recover_addr = 0; + + if (!opal.base || !opal.size) + goto out; + + if ((regs->nip >= opal.base) && + (regs->nip <= (opal.base + opal.size))) + recover_addr = find_recovery_address(regs->nip); + + /* + * Setup regs->nip to rfi into fixup address. + */ + if (recover_addr) + regs->nip = recover_addr; + +out: + return !!recover_addr; } static irqreturn_t opal_interrupt(int irq, void *data) { - uint64_t events; + __be64 events; opal_handle_interrupt(virq_to_hw(irq), &events); - /* XXX TODO: Do something with the events */ + opal_do_notifier(be64_to_cpu(events)); return IRQ_HANDLED; } +static int opal_sysfs_init(void) +{ + opal_kobj = kobject_create_and_add("opal", firmware_kobj); + if (!opal_kobj) { + pr_warn("kobject_create_and_add opal failed\n"); + return -ENOMEM; + } + + return 0; +} + static int __init opal_init(void) { struct device_node *np, *consoles; - const u32 *irqs; + const __be32 *irqs; int rc, i, irqlen; opal_node = of_find_node_by_path("/ibm,opal"); @@ -288,23 +578,27 @@ static int __init opal_init(void) pr_warn("opal: Node not found\n"); return -ENODEV; } + + /* Register OPAL consoles if any ports */ if (firmware_has_feature(FW_FEATURE_OPALv2)) consoles = of_find_node_by_path("/ibm,opal/consoles"); else consoles = of_node_get(opal_node); - - /* Register serial ports */ - for_each_child_of_node(consoles, np) { - if (strcmp(np->name, "serial")) - continue; - of_platform_device_create(np, NULL, NULL); + if (consoles) { + for_each_child_of_node(consoles, np) { + if (strcmp(np->name, "serial")) + continue; + of_platform_device_create(np, NULL, NULL); + } + of_node_put(consoles); } - of_node_put(consoles); /* Find all OPAL interrupts and request them */ irqs = of_get_property(opal_node, "opal-interrupts", &irqlen); pr_debug("opal: Found %d interrupts reserved for OPAL\n", irqs ? (irqlen / 4) : 0); + opal_irq_count = irqlen / 4; + opal_irqs = kzalloc(opal_irq_count * sizeof(unsigned int), GFP_KERNEL); for (i = 0; irqs && i < (irqlen / 4); i++, irqs++) { unsigned int hwirq = be32_to_cpup(irqs); unsigned int irq = irq_create_mapping(NULL, hwirq); @@ -316,7 +610,116 @@ static int __init opal_init(void) if (rc) pr_warning("opal: Error %d requesting irq %d" " (0x%x)\n", rc, irq, hwirq); + opal_irqs[i] = irq; } + + /* Create "opal" kobject under /sys/firmware */ + rc = opal_sysfs_init(); + if (rc == 0) { + /* Setup error log interface */ + rc = opal_elog_init(); + /* Setup code update interface */ + opal_flash_init(); + /* Setup platform dump extract interface */ + opal_platform_dump_init(); + /* Setup system parameters interface */ + opal_sys_param_init(); + /* Setup message log interface. */ + opal_msglog_init(); + } + return 0; } subsys_initcall(opal_init); + +void opal_shutdown(void) +{ + unsigned int i; + long rc = OPAL_BUSY; + + /* First free interrupts, which will also mask them */ + for (i = 0; i < opal_irq_count; i++) { + if (opal_irqs[i]) + free_irq(opal_irqs[i], NULL); + opal_irqs[i] = 0; + } + + /* + * Then sync with OPAL which ensure anything that can + * potentially write to our memory has completed such + * as an ongoing dump retrieval + */ + while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { + rc = opal_sync_host_reboot(); + if (rc == OPAL_BUSY) + opal_poll_events(NULL); + else + mdelay(10); + } +} + +/* Export this so that test modules can use it */ +EXPORT_SYMBOL_GPL(opal_invalid_call); + +/* Convert a region of vmalloc memory to an opal sg list */ +struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr, + unsigned long vmalloc_size) +{ + struct opal_sg_list *sg, *first = NULL; + unsigned long i = 0; + + sg = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!sg) + goto nomem; + + first = sg; + + while (vmalloc_size > 0) { + uint64_t data = vmalloc_to_pfn(vmalloc_addr) << PAGE_SHIFT; + uint64_t length = min(vmalloc_size, PAGE_SIZE); + + sg->entry[i].data = cpu_to_be64(data); + sg->entry[i].length = cpu_to_be64(length); + i++; + + if (i >= SG_ENTRIES_PER_NODE) { + struct opal_sg_list *next; + + next = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!next) + goto nomem; + + sg->length = cpu_to_be64( + i * sizeof(struct opal_sg_entry) + 16); + i = 0; + sg->next = cpu_to_be64(__pa(next)); + sg = next; + } + + vmalloc_addr += length; + vmalloc_size -= length; + } + + sg->length = cpu_to_be64(i * sizeof(struct opal_sg_entry) + 16); + + return first; + +nomem: + pr_err("%s : Failed to allocate memory\n", __func__); + opal_free_sg_list(first); + return NULL; +} + +void opal_free_sg_list(struct opal_sg_list *sg) +{ + while (sg) { + uint64_t next = be64_to_cpu(sg->next); + + kfree(sg); + + if (next) + sg = __va(next); + else + sg = NULL; + } +} diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 8e90e8906df..de19edeaa7a 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -13,6 +13,8 @@ #include <linux/kernel.h> #include <linux/pci.h> +#include <linux/crash_dump.h> +#include <linux/debugfs.h> #include <linux/delay.h> #include <linux/string.h> #include <linux/init.h> @@ -20,16 +22,20 @@ #include <linux/irq.h> #include <linux/io.h> #include <linux/msi.h> +#include <linux/memblock.h> #include <asm/sections.h> #include <asm/io.h> #include <asm/prom.h> #include <asm/pci-bridge.h> #include <asm/machdep.h> +#include <asm/msi_bitmap.h> #include <asm/ppc-pci.h> #include <asm/opal.h> #include <asm/iommu.h> #include <asm/tce.h> +#include <asm/xics.h> +#include <asm/debug.h> #include "powernv.h" #include "pci.h" @@ -66,14 +72,14 @@ define_pe_printk_level(pe_err, KERN_ERR); define_pe_printk_level(pe_warn, KERN_WARNING); define_pe_printk_level(pe_info, KERN_INFO); -static struct pci_dn *pnv_ioda_get_pdn(struct pci_dev *dev) +/* + * stdcix is only supposed to be used in hypervisor real mode as per + * the architecture spec + */ +static inline void __raw_rm_writeq(u64 val, volatile void __iomem *paddr) { - struct device_node *np; - - np = pci_device_to_OF_node(dev); - if (!np) - return NULL; - return PCI_DN(np); + __asm__ __volatile__("stdcix %0,0,%1" + : : "r" (val), "r" (paddr) : "memory"); } static int pnv_ioda_alloc_pe(struct pnv_phb *phb) @@ -87,6 +93,7 @@ static int pnv_ioda_alloc_pe(struct pnv_phb *phb) return IODA_INVALID_PE; } while(test_and_set_bit(pe, phb->ioda.pe_alloc)); + phb->ioda.pe_array[pe].phb = phb; phb->ioda.pe_array[pe].pe_number = pe; return pe; } @@ -107,7 +114,7 @@ static struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev) { struct pci_controller *hose = pci_bus_to_host(dev->bus); struct pnv_phb *phb = hose->private_data; - struct pci_dn *pdn = pnv_ioda_get_pdn(dev); + struct pci_dn *pdn = pci_get_pdn(dev); if (!pdn) return NULL; @@ -158,19 +165,29 @@ static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) rid_end = pe->rid + 1; } - /* Associate PE in PELT */ + /* + * Associate PE in PELT. We need add the PE into the + * corresponding PELT-V as well. Otherwise, the error + * originated from the PE might contribute to other + * PEs. + */ rc = opal_pci_set_pe(phb->opal_id, pe->pe_number, pe->rid, bcomp, dcomp, fcomp, OPAL_MAP_PE); if (rc) { pe_err(pe, "OPAL error %ld trying to setup PELT table\n", rc); return -ENXIO; } + + rc = opal_pci_set_peltv(phb->opal_id, pe->pe_number, + pe->pe_number, OPAL_ADD_PE_TO_DOMAIN); + if (rc) + pe_warn(pe, "OPAL error %d adding self to PELTV\n", rc); opal_pci_eeh_freeze_clear(phb->opal_id, pe->pe_number, OPAL_EEH_ACTION_CLEAR_FREEZE_ALL); /* Add to all parents PELT-V */ while (parent) { - struct pci_dn *pdn = pnv_ioda_get_pdn(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_ADD_PE_TO_DOMAIN); @@ -249,7 +266,7 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev) { struct pci_controller *hose = pci_bus_to_host(dev->bus); struct pnv_phb *phb = hose->private_data; - struct pci_dn *pdn = pnv_ioda_get_pdn(dev); + struct pci_dn *pdn = pci_get_pdn(dev); struct pnv_ioda_pe *pe; int pe_num; @@ -320,14 +337,13 @@ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe) struct pci_dev *dev; list_for_each_entry(dev, &bus->devices, bus_list) { - struct pci_dn *pdn = pnv_ioda_get_pdn(dev); + struct pci_dn *pdn = pci_get_pdn(dev); if (pdn == NULL) { pr_warn("%s: No device node associated with device !\n", pci_name(dev)); continue; } - pci_dev_get(dev); pdn->pcidev = dev; pdn->pe_number = pe->pe_number; pe->dma_weight += pnv_ioda_dma_weight(dev); @@ -431,9 +447,51 @@ static void pnv_pci_ioda_setup_PEs(void) } } -static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *dev) +static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev) { - /* We delay DMA setup after we have assigned all PE# */ + struct pci_dn *pdn = pci_get_pdn(pdev); + struct pnv_ioda_pe *pe; + + /* + * The function can be called while the PE# + * hasn't been assigned. Do nothing for the + * case. + */ + if (!pdn || pdn->pe_number == IODA_INVALID_PE) + return; + + pe = &phb->ioda.pe_array[pdn->pe_number]; + WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops); + set_iommu_table_base(&pdev->dev, &pe->tce32_table); +} + +static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb, + struct pci_dev *pdev, u64 dma_mask) +{ + struct pci_dn *pdn = pci_get_pdn(pdev); + struct pnv_ioda_pe *pe; + uint64_t top; + bool bypass = false; + + if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE)) + return -ENODEV;; + + pe = &phb->ioda.pe_array[pdn->pe_number]; + if (pe->tce_bypass_enabled) { + top = pe->tce_bypass_base + memblock_end_of_DRAM() - 1; + bypass = (dma_mask >= top); + } + + if (bypass) { + dev_info(&pdev->dev, "Using 64-bit DMA iommu bypass\n"); + set_dma_ops(&pdev->dev, &dma_direct_ops); + set_dma_offset(&pdev->dev, pe->tce_bypass_base); + } 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); + } + return 0; } static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus) @@ -441,12 +499,102 @@ static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus) struct pci_dev *dev; list_for_each_entry(dev, &bus->devices, bus_list) { - set_iommu_table_base(&dev->dev, &pe->tce32_table); + set_iommu_table_base_and_group(&dev->dev, &pe->tce32_table); if (dev->subordinate) pnv_ioda_setup_bus_dma(pe, dev->subordinate); } } +static void pnv_pci_ioda1_tce_invalidate(struct pnv_ioda_pe *pe, + struct iommu_table *tbl, + __be64 *startp, __be64 *endp, bool rm) +{ + __be64 __iomem *invalidate = rm ? + (__be64 __iomem *)pe->tce_inval_reg_phys : + (__be64 __iomem *)tbl->it_index; + unsigned long start, end, inc; + + start = __pa(startp); + end = __pa(endp); + + /* BML uses this case for p6/p7/galaxy2: Shift addr and put in node */ + if (tbl->it_busno) { + start <<= 12; + end <<= 12; + inc = 128 << 12; + start |= tbl->it_busno; + end |= tbl->it_busno; + } else if (tbl->it_type & TCE_PCI_SWINV_PAIR) { + /* p7ioc-style invalidation, 2 TCEs per write */ + start |= (1ull << 63); + end |= (1ull << 63); + inc = 16; + } else { + /* Default (older HW) */ + inc = 128; + } + + end |= inc - 1; /* round up end to be different than start */ + + mb(); /* Ensure above stores are visible */ + while (start <= end) { + if (rm) + __raw_rm_writeq(cpu_to_be64(start), invalidate); + else + __raw_writeq(cpu_to_be64(start), invalidate); + start += inc; + } + + /* + * The iommu layer will do another mb() for us on build() + * and we don't care on free() + */ +} + +static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe, + struct iommu_table *tbl, + __be64 *startp, __be64 *endp, bool rm) +{ + unsigned long start, end, inc; + __be64 __iomem *invalidate = rm ? + (__be64 __iomem *)pe->tce_inval_reg_phys : + (__be64 __iomem *)tbl->it_index; + + /* We'll invalidate DMA address in PE scope */ + start = 0x2ul << 60; + start |= (pe->pe_number & 0xFF); + end = start; + + /* Figure out the start, end and step */ + inc = tbl->it_offset + (((u64)startp - tbl->it_base) / sizeof(u64)); + start |= (inc << 12); + inc = tbl->it_offset + (((u64)endp - tbl->it_base) / sizeof(u64)); + end |= (inc << 12); + inc = (0x1ul << 12); + mb(); + + while (start <= end) { + if (rm) + __raw_rm_writeq(cpu_to_be64(start), invalidate); + else + __raw_writeq(cpu_to_be64(start), invalidate); + start += inc; + } +} + +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_phb *phb = pe->phb; + + if (phb->type == PNV_PHB_IODA1) + pnv_pci_ioda1_tce_invalidate(pe, tbl, startp, endp, rm); + else + pnv_pci_ioda2_tce_invalidate(pe, tbl, startp, endp, rm); +} + static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe, unsigned int base, unsigned int segs) @@ -516,15 +664,18 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, * errors, and on the first pass the data will be a relative * bus number, print that out instead. */ - tbl->it_busno = 0; - tbl->it_index = (unsigned long)ioremap(be64_to_cpup(swinvp), 8); - tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE - | TCE_PCI_SWINV_PAIR; + pe->tce_inval_reg_phys = be64_to_cpup(swinvp); + tbl->it_index = (unsigned long)ioremap(pe->tce_inval_reg_phys, + 8); + tbl->it_type |= (TCE_PCI_SWINV_CREATE | + TCE_PCI_SWINV_FREE | + 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) - set_iommu_table_base(&pe->pdev->dev, tbl); + set_iommu_table_base_and_group(&pe->pdev->dev, tbl); else pnv_ioda_setup_bus_dma(pe, pe->pbus); @@ -537,6 +688,135 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, __free_pages(tce_mem, get_order(TCE32_TABLE_SIZE * segs)); } +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); + uint16_t window_id = (pe->pe_number << 1 ) + 1; + int64_t rc; + + pe_info(pe, "%sabling 64-bit DMA bypass\n", enable ? "En" : "Dis"); + if (enable) { + phys_addr_t top = memblock_end_of_DRAM(); + + top = roundup_pow_of_two(top); + rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id, + pe->pe_number, + window_id, + pe->tce_bypass_base, + top); + } else { + rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id, + pe->pe_number, + window_id, + pe->tce_bypass_base, + 0); + + /* + * We might want to reset the DMA ops of all devices on + * this PE. However in theory, that shouldn't be necessary + * as this is used for VFIO/KVM pass-through and the device + * hasn't yet been returned to its kernel driver + */ + } + if (rc) + pe_err(pe, "OPAL error %lld configuring bypass window\n", rc); + else + pe->tce_bypass_enabled = enable; +} + +static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb, + struct pnv_ioda_pe *pe) +{ + /* TVE #1 is selected by PCI address bit 59 */ + pe->tce_bypass_base = 1ull << 59; + + /* Install set_bypass callback for VFIO */ + pe->tce32_table.set_bypass = pnv_pci_ioda2_set_bypass; + + /* Enable bypass by default */ + pnv_pci_ioda2_set_bypass(&pe->tce32_table, true); +} + +static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, + struct pnv_ioda_pe *pe) +{ + struct page *tce_mem = NULL; + void *addr; + const __be64 *swinvp; + struct iommu_table *tbl; + unsigned int tce_table_size, end; + int64_t rc; + + /* We shouldn't already have a 32-bit DMA associated */ + if (WARN_ON(pe->tce32_seg >= 0)) + return; + + /* The PE will reserve all possible 32-bits space */ + pe->tce32_seg = 0; + end = (1 << ilog2(phb->ioda.m32_pci_base)); + tce_table_size = (end / 0x1000) * 8; + pe_info(pe, "Setting up 32-bit TCE table at 0..%08x\n", + end); + + /* Allocate TCE table */ + tce_mem = alloc_pages_node(phb->hose->node, GFP_KERNEL, + get_order(tce_table_size)); + if (!tce_mem) { + pe_err(pe, "Failed to allocate a 32-bit TCE memory\n"); + goto fail; + } + addr = page_address(tce_mem); + memset(addr, 0, tce_table_size); + + /* + * Map TCE table through TVT. The TVE index is the PE number + * shifted by 1 bit for 32-bits DMA space. + */ + rc = opal_pci_map_pe_dma_window(phb->opal_id, pe->pe_number, + pe->pe_number << 1, 1, __pa(addr), + tce_table_size, 0x1000); + if (rc) { + pe_err(pe, "Failed to configure 32-bit TCE table," + " err %ld\n", rc); + goto fail; + } + + /* Setup linux iommu table */ + tbl = &pe->tce32_table; + pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, 0); + + /* OPAL variant of PHB3 invalidated TCEs */ + swinvp = of_get_property(phb->hose->dn, "ibm,opal-tce-kill", NULL); + if (swinvp) { + /* We need a couple more fields -- an address and a data + * to or. Since the bus is only printed out on table free + * errors, and on the first pass the data will be a relative + * bus number, print that out instead. + */ + pe->tce_inval_reg_phys = be64_to_cpup(swinvp); + tbl->it_index = (unsigned long)ioremap(pe->tce_inval_reg_phys, + 8); + 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) + set_iommu_table_base_and_group(&pe->pdev->dev, tbl); + else + pnv_ioda_setup_bus_dma(pe, pe->pbus); + + /* Also create a bypass window */ + pnv_pci_ioda2_setup_bypass_pe(phb, pe); + return; +fail: + if (pe->tce32_seg >= 0) + pe->tce32_seg = -1; + if (tce_mem) + __free_pages(tce_mem, get_order(tce_table_size)); +} + static void pnv_ioda_setup_dma(struct pnv_phb *phb) { struct pci_controller *hose = phb->hose; @@ -579,23 +859,52 @@ static void pnv_ioda_setup_dma(struct pnv_phb *phb) if (segs > remaining) segs = remaining; } - pe_info(pe, "DMA weight %d, assigned %d DMA32 segments\n", - pe->dma_weight, segs); - pnv_pci_ioda_setup_dma_pe(phb, pe, base, segs); + + /* + * For IODA2 compliant PHB3, we needn't care about the weight. + * The all available 32-bits DMA space will be assigned to + * the specific PE. + */ + if (phb->type == PNV_PHB_IODA1) { + pe_info(pe, "DMA weight %d, assigned %d DMA32 segments\n", + pe->dma_weight, segs); + pnv_pci_ioda_setup_dma_pe(phb, pe, base, segs); + } else { + pe_info(pe, "Assign DMA32 space\n"); + segs = 0; + pnv_pci_ioda2_setup_dma_pe(phb, pe); + } + remaining -= segs; base += segs; } } #ifdef CONFIG_PCI_MSI +static void pnv_ioda2_msi_eoi(struct irq_data *d) +{ + unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d); + struct irq_chip *chip = irq_data_get_irq_chip(d); + struct pnv_phb *phb = container_of(chip, struct pnv_phb, + ioda.irq_chip); + int64_t rc; + + rc = opal_pci_msi_eoi(phb->opal_id, hw_irq); + WARN_ON_ONCE(rc); + + icp_native_eoi(d); +} + static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, - unsigned int hwirq, unsigned int is_64, - struct msi_msg *msg) + unsigned int hwirq, unsigned int virq, + unsigned int is_64, struct msi_msg *msg) { struct pnv_ioda_pe *pe = pnv_ioda_get_pe(dev); + struct pci_dn *pdn = pci_get_pdn(dev); + struct irq_data *idata; + struct irq_chip *ichip; unsigned int xive_num = hwirq - phb->msi_base; - uint64_t addr64; - uint32_t addr32, data; + __be32 data; int rc; /* No PE assigned ? bail out ... no MSI for you ! */ @@ -606,6 +915,10 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, if (pe->mve_number < 0) return -ENXIO; + /* Force 32-bit MSI on some broken devices */ + if (pdn && pdn->force_32bit_msi) + is_64 = 0; + /* Assign XIVE to PE */ rc = opal_pci_set_xive_pe(phb->opal_id, pe->pe_number, xive_num); if (rc) { @@ -615,6 +928,8 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, } if (is_64) { + __be64 addr64; + rc = opal_get_msi_64(phb->opal_id, pe->mve_number, xive_num, 1, &addr64, &data); if (rc) { @@ -622,9 +937,11 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, pci_name(dev), rc); return -EIO; } - msg->address_hi = addr64 >> 32; - msg->address_lo = addr64 & 0xfffffffful; + msg->address_hi = be64_to_cpu(addr64) >> 32; + msg->address_lo = be64_to_cpu(addr64) & 0xfffffffful; } else { + __be32 addr32; + rc = opal_get_msi_32(phb->opal_id, pe->mve_number, xive_num, 1, &addr32, &data); if (rc) { @@ -633,9 +950,26 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, return -EIO; } msg->address_hi = 0; - msg->address_lo = addr32; + msg->address_lo = be32_to_cpu(addr32); + } + msg->data = be32_to_cpu(data); + + /* + * Change the IRQ chip for the MSI interrupts on PHB3. + * The corresponding IRQ chip should be populated for + * the first time. + */ + if (phb->type == PNV_PHB_IODA2) { + if (!phb->ioda.irq_chip_init) { + idata = irq_get_irq_data(virq); + ichip = irq_data_get_irq_chip(idata); + phb->ioda.irq_chip_init = 1; + phb->ioda.irq_chip = *ichip; + phb->ioda.irq_chip.irq_eoi = pnv_ioda2_msi_eoi; + } + + irq_set_chip(virq, &phb->ioda.irq_chip); } - msg->data = data; pr_devel("%s: %s-bit MSI on hwirq %x (xive #%d)," " address=%x_%08x data=%x PE# %d\n", @@ -647,7 +981,7 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) { - unsigned int bmap_size; + unsigned int count; const __be32 *prop = of_get_property(phb->hose->dn, "ibm,opal-msi-ranges", NULL); if (!prop) { @@ -658,18 +992,17 @@ static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) return; phb->msi_base = be32_to_cpup(prop); - phb->msi_count = be32_to_cpup(prop + 1); - bmap_size = BITS_TO_LONGS(phb->msi_count) * sizeof(unsigned long); - phb->msi_map = zalloc_maybe_bootmem(bmap_size, GFP_KERNEL); - if (!phb->msi_map) { + count = be32_to_cpup(prop + 1); + if (msi_bitmap_alloc(&phb->msi_bmp, count, phb->hose->dn)) { pr_err("PCI %d: Failed to allocate MSI bitmap !\n", phb->hose->global_number); return; } + phb->msi_setup = pnv_pci_ioda_msi_setup; phb->msi32_support = 1; pr_info(" Allocated bitmap for %d MSIs (base IRQ 0x%x)\n", - phb->msi_count, phb->msi_base); + count, phb->msi_base); } #else static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) { } @@ -722,11 +1055,14 @@ static void pnv_ioda_setup_pe_seg(struct pci_controller *hose, index++; } } else if (res->flags & IORESOURCE_MEM) { + /* WARNING: Assumes M32 is mem region 0 in PHB. We need to + * harden that algorithm when we start supporting M64 + */ region.start = res->start - - hose->pci_mem_offset - + hose->mem_offset[0] - phb->ioda.m32_pci_base; region.end = res->end - - hose->pci_mem_offset - + hose->mem_offset[0] - phb->ioda.m32_pci_base; index = region.start / phb->ioda.m32_segsize; @@ -777,11 +1113,38 @@ static void pnv_pci_ioda_setup_DMA(void) } } +static void pnv_pci_ioda_create_dbgfs(void) +{ +#ifdef CONFIG_DEBUG_FS + struct pci_controller *hose, *tmp; + struct pnv_phb *phb; + char name[16]; + + list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { + phb = hose->private_data; + + sprintf(name, "PCI%04x", hose->global_number); + phb->dbgfs = debugfs_create_dir(name, powerpc_debugfs_root); + if (!phb->dbgfs) + pr_warning("%s: Error on creating debugfs on PHB#%x\n", + __func__, hose->global_number); + } +#endif /* CONFIG_DEBUG_FS */ +} + static void pnv_pci_ioda_fixup(void) { pnv_pci_ioda_setup_PEs(); pnv_pci_ioda_setup_seg(); pnv_pci_ioda_setup_DMA(); + + pnv_pci_ioda_create_dbgfs(); + +#ifdef CONFIG_EEH + eeh_probe_mode_set(EEH_PROBE_MODE_DEV); + eeh_addr_cache_build(); + eeh_init(); +#endif } /* @@ -839,7 +1202,7 @@ static int pnv_pci_enable_device_hook(struct pci_dev *dev) if (!phb->initialized) return 0; - pdn = pnv_ioda_get_pdn(dev); + pdn = pci_get_pdn(dev); if (!pdn || pdn->pe_number == IODA_INVALID_PE) return -EINVAL; @@ -852,18 +1215,26 @@ static u32 pnv_ioda_bdfn_to_pe(struct pnv_phb *phb, struct pci_bus *bus, return phb->ioda.pe_rmap[(bus->number << 8) | devfn]; } -void __init pnv_pci_init_ioda1_phb(struct device_node *np) +static void pnv_pci_ioda_shutdown(struct pnv_phb *phb) +{ + opal_pci_reset(phb->opal_id, OPAL_PCI_IODA_TABLE_RESET, + OPAL_ASSERT_RESET); +} + +void __init pnv_pci_init_ioda_phb(struct device_node *np, + u64 hub_id, int ioda_type) { struct pci_controller *hose; - static int primary = 1; struct pnv_phb *phb; - unsigned long size, m32map_off, iomap_off, pemap_off; - const u64 *prop64; + unsigned long size, m32map_off, pemap_off, iomap_off = 0; + const __be64 *prop64; + const __be32 *prop32; + int len; u64 phb_id; void *aux; long rc; - pr_info(" Initializing IODA OPAL PHB %s\n", np->full_name); + pr_info("Initializing IODA%d OPAL PHB %s\n", ioda_type, np->full_name); prop64 = of_get_property(np, "ibm,opal-phbid", NULL); if (!prop64) { @@ -874,77 +1245,88 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np) pr_debug(" PHB-ID : 0x%016llx\n", phb_id); phb = alloc_bootmem(sizeof(struct pnv_phb)); - if (phb) { - memset(phb, 0, sizeof(struct pnv_phb)); - phb->hose = hose = pcibios_alloc_controller(np); + if (!phb) { + pr_err(" Out of memory !\n"); + return; } - if (!phb || !phb->hose) { - pr_err("PCI: Failed to allocate PCI controller for %s\n", + + /* Allocate PCI controller */ + memset(phb, 0, sizeof(struct pnv_phb)); + phb->hose = hose = pcibios_alloc_controller(np); + if (!phb->hose) { + pr_err(" Can't allocate PCI controller for %s\n", np->full_name); + free_bootmem((unsigned long)phb, sizeof(struct pnv_phb)); return; } spin_lock_init(&phb->lock); - /* XXX Use device-tree */ - hose->first_busno = 0; - hose->last_busno = 0xff; + prop32 = of_get_property(np, "bus-range", &len); + if (prop32 && len == 8) { + hose->first_busno = be32_to_cpu(prop32[0]); + hose->last_busno = be32_to_cpu(prop32[1]); + } else { + pr_warn(" Broken <bus-range> on %s\n", np->full_name); + hose->first_busno = 0; + hose->last_busno = 0xff; + } hose->private_data = phb; + phb->hub_id = hub_id; phb->opal_id = phb_id; - phb->type = PNV_PHB_IODA1; + phb->type = ioda_type; /* Detect specific models for error handling */ if (of_device_is_compatible(np, "ibm,p7ioc-pciex")) phb->model = PNV_PHB_MODEL_P7IOC; + else if (of_device_is_compatible(np, "ibm,power8-pciex")) + phb->model = PNV_PHB_MODEL_PHB3; else phb->model = PNV_PHB_MODEL_UNKNOWN; - /* We parse "ranges" now since we need to deduce the register base - * from the IO base - */ - pci_process_bridge_OF_ranges(phb->hose, np, primary); - primary = 0; + /* Parse 32-bit and IO ranges (if any) */ + pci_process_bridge_OF_ranges(hose, np, !hose->global_number); - /* Magic formula from Milton */ + /* Get registers */ phb->regs = of_iomap(np, 0); if (phb->regs == NULL) pr_err(" Failed to map registers !\n"); - - /* XXX This is hack-a-thon. This needs to be changed so that: - * - we obtain stuff like PE# etc... from device-tree - * - we properly re-allocate M32 ourselves - * (the OFW one isn't very good) - */ - /* Initialize more IODA stuff */ - phb->ioda.total_pe = 128; - + phb->ioda.total_pe = 1; + prop32 = of_get_property(np, "ibm,opal-num-pes", NULL); + if (prop32) + phb->ioda.total_pe = be32_to_cpup(prop32); + prop32 = of_get_property(np, "ibm,opal-reserved-pe", NULL); + if (prop32) + phb->ioda.reserved_pe = be32_to_cpup(prop32); phb->ioda.m32_size = resource_size(&hose->mem_resources[0]); - /* OFW Has already off top 64k of M32 space (MSI space) */ + /* FW Has already off top 64k of M32 space (MSI space) */ phb->ioda.m32_size += 0x10000; phb->ioda.m32_segsize = phb->ioda.m32_size / phb->ioda.total_pe; - phb->ioda.m32_pci_base = hose->mem_resources[0].start - - hose->pci_mem_offset; + phb->ioda.m32_pci_base = hose->mem_resources[0].start - hose->mem_offset[0]; phb->ioda.io_size = hose->pci_io_size; phb->ioda.io_segsize = phb->ioda.io_size / phb->ioda.total_pe; phb->ioda.io_pci_base = 0; /* XXX calculate this ? */ - /* Allocate aux data & arrays */ + /* Allocate aux data & arrays. We don't have IO ports on PHB3 */ size = _ALIGN_UP(phb->ioda.total_pe / 8, sizeof(unsigned long)); m32map_off = size; size += phb->ioda.total_pe * sizeof(phb->ioda.m32_segmap[0]); - iomap_off = size; - size += phb->ioda.total_pe * sizeof(phb->ioda.io_segmap[0]); + if (phb->type == PNV_PHB_IODA1) { + iomap_off = size; + size += phb->ioda.total_pe * sizeof(phb->ioda.io_segmap[0]); + } pemap_off = size; size += phb->ioda.total_pe * sizeof(struct pnv_ioda_pe); aux = alloc_bootmem(size); memset(aux, 0, size); phb->ioda.pe_alloc = aux; phb->ioda.m32_segmap = aux + m32map_off; - phb->ioda.io_segmap = aux + iomap_off; + if (phb->type == PNV_PHB_IODA1) + phb->ioda.io_segmap = aux + iomap_off; phb->ioda.pe_array = aux + pemap_off; - set_bit(0, phb->ioda.pe_alloc); + set_bit(phb->ioda.reserved_pe, phb->ioda.pe_alloc); INIT_LIST_HEAD(&phb->ioda.pe_dma_list); INIT_LIST_HEAD(&phb->ioda.pe_list); @@ -960,7 +1342,7 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np) hose->mem_resources[2].start = 0; hose->mem_resources[2].end = 0; -#if 0 +#if 0 /* We should really do that ... */ rc = opal_pci_set_phb_mem_window(opal->phb_id, window_type, window_num, @@ -969,28 +1351,27 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np) segment_size); #endif - pr_info(" %d PE's M32: 0x%x [segment=0x%x] IO: 0x%x [segment=0x%x]\n", + pr_info(" %d (%d) PE's M32: 0x%x [segment=0x%x]" + " IO: 0x%x [segment=0x%x]\n", phb->ioda.total_pe, + phb->ioda.reserved_pe, phb->ioda.m32_size, phb->ioda.m32_segsize, phb->ioda.io_size, phb->ioda.io_segsize); - if (phb->regs) { - pr_devel(" BUID = 0x%016llx\n", in_be64(phb->regs + 0x100)); - pr_devel(" PHB2_CR = 0x%016llx\n", in_be64(phb->regs + 0x160)); - pr_devel(" IO_BAR = 0x%016llx\n", in_be64(phb->regs + 0x170)); - pr_devel(" IO_BAMR = 0x%016llx\n", in_be64(phb->regs + 0x178)); - pr_devel(" IO_SAR = 0x%016llx\n", in_be64(phb->regs + 0x180)); - pr_devel(" M32_BAR = 0x%016llx\n", in_be64(phb->regs + 0x190)); - pr_devel(" M32_BAMR = 0x%016llx\n", in_be64(phb->regs + 0x198)); - pr_devel(" M32_SAR = 0x%016llx\n", in_be64(phb->regs + 0x1a0)); - } phb->hose->ops = &pnv_pci_ops; +#ifdef CONFIG_EEH + phb->eeh_ops = &ioda_eeh_ops; +#endif /* Setup RID -> PE mapping function */ phb->bdfn_to_pe = pnv_ioda_bdfn_to_pe; /* Setup TCEs */ phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup; + phb->dma_set_mask = pnv_pci_ioda_dma_set_mask; + + /* Setup shutdown function for kexec */ + phb->shutdown = pnv_pci_ioda_shutdown; /* Setup MSI support */ pnv_pci_init_ioda_msis(phb); @@ -1005,19 +1386,35 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np) 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; pci_add_flags(PCI_REASSIGN_ALL_RSRC); /* Reset IODA tables to a clean state */ rc = opal_pci_reset(phb_id, OPAL_PCI_IODA_TABLE_RESET, OPAL_ASSERT_RESET); if (rc) pr_warning(" OPAL Error %ld performing IODA table reset !\n", rc); - opal_pci_set_pe(phb_id, 0, 0, 7, 1, 1 , OPAL_MAP_PE); + + /* If we're running in kdump kerenl, the previous kerenl never + * shutdown PCI devices correctly. We already got IODA table + * cleaned out. So we have to issue PHB reset to stop all PCI + * transactions from previous kerenl. + */ + if (is_kdump_kernel()) { + pr_info(" Issue PHB reset ...\n"); + ioda_eeh_phb_reset(hose, EEH_RESET_FUNDAMENTAL); + ioda_eeh_phb_reset(hose, OPAL_DEASSERT_RESET); + } +} + +void __init pnv_pci_init_ioda2_phb(struct device_node *np) +{ + pnv_pci_init_ioda_phb(np, 0, PNV_PHB_IODA2); } void __init pnv_pci_init_ioda_hub(struct device_node *np) { struct device_node *phbn; - const u64 *prop64; + const __be64 *prop64; u64 hub_id; pr_info("Probing IODA IO-Hub %s\n", np->full_name); @@ -1034,6 +1431,6 @@ void __init pnv_pci_init_ioda_hub(struct device_node *np) for_each_child_of_node(np, phbn) { /* Look for IODA1 PHBs */ if (of_device_is_compatible(phbn, "ibm,ioda-phb")) - pnv_pci_init_ioda1_phb(phbn); + pnv_pci_init_ioda_phb(phbn, hub_id, PNV_PHB_IODA1); } } diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c index 7db8771a40f..e3807d69393 100644 --- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c +++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c @@ -26,6 +26,7 @@ #include <asm/prom.h> #include <asm/pci-bridge.h> #include <asm/machdep.h> +#include <asm/msi_bitmap.h> #include <asm/ppc-pci.h> #include <asm/opal.h> #include <asm/iommu.h> @@ -41,8 +42,8 @@ #ifdef CONFIG_PCI_MSI static int pnv_pci_p5ioc2_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, - unsigned int hwirq, unsigned int is_64, - struct msi_msg *msg) + unsigned int hwirq, unsigned int virq, + unsigned int is_64, struct msi_msg *msg) { if (WARN_ON(!is_64)) return -ENXIO; @@ -55,7 +56,7 @@ static int pnv_pci_p5ioc2_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) { - unsigned int bmap_size; + unsigned int count; const __be32 *prop = of_get_property(phb->hose->dn, "ibm,opal-msi-ranges", NULL); if (!prop) @@ -67,10 +68,8 @@ static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) if (of_device_is_compatible(phb->hose->dn, "ibm,p5ioc2-pcix")) return; phb->msi_base = be32_to_cpup(prop); - phb->msi_count = be32_to_cpup(prop + 1); - bmap_size = BITS_TO_LONGS(phb->msi_count) * sizeof(unsigned long); - phb->msi_map = zalloc_maybe_bootmem(bmap_size, GFP_KERNEL); - if (!phb->msi_map) { + count = be32_to_cpup(prop + 1); + if (msi_bitmap_alloc(&phb->msi_bmp, count, phb->hose->dn)) { pr_err("PCI %d: Failed to allocate MSI bitmap !\n", phb->hose->global_number); return; @@ -78,7 +77,7 @@ static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) phb->msi_setup = pnv_pci_p5ioc2_msi_setup; phb->msi32_support = 0; pr_info(" Allocated bitmap for %d MSIs (base IRQ 0x%x)\n", - phb->msi_count, phb->msi_base); + count, phb->msi_base); } #else static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) { } @@ -87,17 +86,20 @@ static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) { } static void pnv_pci_p5ioc2_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev) { - if (phb->p5ioc2.iommu_table.it_map == NULL) + if (phb->p5ioc2.iommu_table.it_map == NULL) { iommu_init_table(&phb->p5ioc2.iommu_table, phb->hose->node); + iommu_register_group(&phb->p5ioc2.iommu_table, + pci_domain_nr(phb->hose->bus), phb->opal_id); + } - set_iommu_table_base(&pdev->dev, &phb->p5ioc2.iommu_table); + set_iommu_table_base_and_group(&pdev->dev, &phb->p5ioc2.iommu_table); } -static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, +static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id, void *tce_mem, u64 tce_size) { struct pnv_phb *phb; - const u64 *prop64; + const __be64 *prop64; u64 phb_id; int64_t rc; static int primary = 1; @@ -134,6 +136,7 @@ static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, phb->hose->first_busno = 0; phb->hose->last_busno = 0xff; phb->hose->private_data = phb; + phb->hub_id = hub_id; phb->opal_id = phb_id; phb->type = PNV_PHB_P5IOC2; phb->model = PNV_PHB_MODEL_P5IOC2; @@ -175,7 +178,7 @@ static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, void __init pnv_pci_init_p5ioc2_hub(struct device_node *np) { struct device_node *phbn; - const u64 *prop64; + const __be64 *prop64; u64 hub_id; void *tce_mem; uint64_t tce_per_phb; @@ -227,7 +230,8 @@ void __init pnv_pci_init_p5ioc2_hub(struct device_node *np) for_each_child_of_node(np, phbn) { if (of_device_is_compatible(phbn, "ibm,p5ioc2-pcix") || of_device_is_compatible(phbn, "ibm,p5ioc2-pciex")) { - pnv_pci_init_p5ioc2_phb(phbn, tce_mem, tce_per_phb); + pnv_pci_init_p5ioc2_phb(phbn, hub_id, + tce_mem, tce_per_phb); tce_mem += tce_per_phb; } } diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index b8b8e0bd989..f91a4e5d872 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -20,17 +20,21 @@ #include <linux/irq.h> #include <linux/io.h> #include <linux/msi.h> +#include <linux/iommu.h> #include <asm/sections.h> #include <asm/io.h> #include <asm/prom.h> #include <asm/pci-bridge.h> #include <asm/machdep.h> +#include <asm/msi_bitmap.h> #include <asm/ppc-pci.h> #include <asm/opal.h> #include <asm/iommu.h> #include <asm/tce.h> #include <asm/firmware.h> +#include <asm/eeh_event.h> +#include <asm/eeh.h> #include "powernv.h" #include "pci.h" @@ -46,44 +50,12 @@ static int pnv_msi_check_device(struct pci_dev* pdev, int nvec, int type) { struct pci_controller *hose = pci_bus_to_host(pdev->bus); struct pnv_phb *phb = hose->private_data; + struct pci_dn *pdn = pci_get_pdn(pdev); - return (phb && phb->msi_map) ? 0 : -ENODEV; -} - -static unsigned int pnv_get_one_msi(struct pnv_phb *phb) -{ - unsigned long flags; - unsigned int id, rc; - - spin_lock_irqsave(&phb->lock, flags); - - id = find_next_zero_bit(phb->msi_map, phb->msi_count, phb->msi_next); - if (id >= phb->msi_count && phb->msi_next) - id = find_next_zero_bit(phb->msi_map, phb->msi_count, 0); - if (id >= phb->msi_count) { - rc = 0; - goto out; - } - __set_bit(id, phb->msi_map); - rc = id + phb->msi_base; -out: - spin_unlock_irqrestore(&phb->lock, flags); - return rc; -} - -static void pnv_put_msi(struct pnv_phb *phb, unsigned int hwirq) -{ - unsigned long flags; - unsigned int id; - - if (WARN_ON(hwirq < phb->msi_base || - hwirq >= (phb->msi_base + phb->msi_count))) - return; - id = hwirq - phb->msi_base; + if (pdn && pdn->force_32bit_msi && !phb->msi32_support) + return -ENODEV; - spin_lock_irqsave(&phb->lock, flags); - __clear_bit(id, phb->msi_map); - spin_unlock_irqrestore(&phb->lock, flags); + return (phb && phb->msi_bmp.bitmap) ? 0 : -ENODEV; } static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) @@ -92,7 +64,8 @@ static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) struct pnv_phb *phb = hose->private_data; struct msi_desc *entry; struct msi_msg msg; - unsigned int hwirq, virq; + int hwirq; + unsigned int virq; int rc; if (WARN_ON(!phb)) @@ -104,25 +77,25 @@ static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) pci_name(pdev)); return -ENXIO; } - hwirq = pnv_get_one_msi(phb); - if (!hwirq) { + hwirq = msi_bitmap_alloc_hwirqs(&phb->msi_bmp, 1); + if (hwirq < 0) { pr_warn("%s: Failed to find a free MSI\n", pci_name(pdev)); return -ENOSPC; } - virq = irq_create_mapping(NULL, hwirq); + virq = irq_create_mapping(NULL, phb->msi_base + hwirq); if (virq == NO_IRQ) { pr_warn("%s: Failed to map MSI to linux irq\n", pci_name(pdev)); - pnv_put_msi(phb, hwirq); + msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq, 1); return -ENOMEM; } - rc = phb->msi_setup(phb, pdev, hwirq, entry->msi_attrib.is_64, - &msg); + rc = phb->msi_setup(phb, pdev, phb->msi_base + hwirq, + virq, entry->msi_attrib.is_64, &msg); if (rc) { pr_warn("%s: Failed to setup MSI\n", pci_name(pdev)); irq_dispose_mapping(virq); - pnv_put_msi(phb, hwirq); + msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq, 1); return rc; } irq_set_msi_desc(virq, entry); @@ -144,83 +117,202 @@ static void pnv_teardown_msi_irqs(struct pci_dev *pdev) if (entry->irq == NO_IRQ) continue; irq_set_msi_desc(entry->irq, NULL); - pnv_put_msi(phb, virq_to_hw(entry->irq)); + msi_bitmap_free_hwirqs(&phb->msi_bmp, + virq_to_hw(entry->irq) - phb->msi_base, 1); irq_dispose_mapping(entry->irq); } } #endif /* CONFIG_PCI_MSI */ -static void pnv_pci_dump_p7ioc_diag_data(struct pnv_phb *phb) +static void pnv_pci_dump_p7ioc_diag_data(struct pci_controller *hose, + struct OpalIoPhbErrorCommon *common) { - struct OpalIoP7IOCPhbErrorData *data = &phb->diag.p7ioc; + struct OpalIoP7IOCPhbErrorData *data; int i; - pr_info("PHB %d diagnostic data:\n", phb->hose->global_number); - - pr_info(" brdgCtl = 0x%08x\n", data->brdgCtl); - - pr_info(" portStatusReg = 0x%08x\n", data->portStatusReg); - pr_info(" rootCmplxStatus = 0x%08x\n", data->rootCmplxStatus); - pr_info(" busAgentStatus = 0x%08x\n", data->busAgentStatus); - - pr_info(" deviceStatus = 0x%08x\n", data->deviceStatus); - pr_info(" slotStatus = 0x%08x\n", data->slotStatus); - pr_info(" linkStatus = 0x%08x\n", data->linkStatus); - pr_info(" devCmdStatus = 0x%08x\n", data->devCmdStatus); - pr_info(" devSecStatus = 0x%08x\n", data->devSecStatus); - - pr_info(" rootErrorStatus = 0x%08x\n", data->rootErrorStatus); - pr_info(" uncorrErrorStatus = 0x%08x\n", data->uncorrErrorStatus); - pr_info(" corrErrorStatus = 0x%08x\n", data->corrErrorStatus); - pr_info(" tlpHdr1 = 0x%08x\n", data->tlpHdr1); - pr_info(" tlpHdr2 = 0x%08x\n", data->tlpHdr2); - pr_info(" tlpHdr3 = 0x%08x\n", data->tlpHdr3); - pr_info(" tlpHdr4 = 0x%08x\n", data->tlpHdr4); - pr_info(" sourceId = 0x%08x\n", data->sourceId); - - pr_info(" errorClass = 0x%016llx\n", data->errorClass); - pr_info(" correlator = 0x%016llx\n", data->correlator); - - pr_info(" p7iocPlssr = 0x%016llx\n", data->p7iocPlssr); - pr_info(" p7iocCsr = 0x%016llx\n", data->p7iocCsr); - pr_info(" lemFir = 0x%016llx\n", data->lemFir); - pr_info(" lemErrorMask = 0x%016llx\n", data->lemErrorMask); - pr_info(" lemWOF = 0x%016llx\n", data->lemWOF); - pr_info(" phbErrorStatus = 0x%016llx\n", data->phbErrorStatus); - pr_info(" phbFirstErrorStatus = 0x%016llx\n", data->phbFirstErrorStatus); - pr_info(" phbErrorLog0 = 0x%016llx\n", data->phbErrorLog0); - pr_info(" phbErrorLog1 = 0x%016llx\n", data->phbErrorLog1); - pr_info(" mmioErrorStatus = 0x%016llx\n", data->mmioErrorStatus); - pr_info(" mmioFirstErrorStatus = 0x%016llx\n", data->mmioFirstErrorStatus); - pr_info(" mmioErrorLog0 = 0x%016llx\n", data->mmioErrorLog0); - pr_info(" mmioErrorLog1 = 0x%016llx\n", data->mmioErrorLog1); - pr_info(" dma0ErrorStatus = 0x%016llx\n", data->dma0ErrorStatus); - pr_info(" dma0FirstErrorStatus = 0x%016llx\n", data->dma0FirstErrorStatus); - pr_info(" dma0ErrorLog0 = 0x%016llx\n", data->dma0ErrorLog0); - pr_info(" dma0ErrorLog1 = 0x%016llx\n", data->dma0ErrorLog1); - pr_info(" dma1ErrorStatus = 0x%016llx\n", data->dma1ErrorStatus); - pr_info(" dma1FirstErrorStatus = 0x%016llx\n", data->dma1FirstErrorStatus); - pr_info(" dma1ErrorLog0 = 0x%016llx\n", data->dma1ErrorLog0); - pr_info(" dma1ErrorLog1 = 0x%016llx\n", data->dma1ErrorLog1); + data = (struct OpalIoP7IOCPhbErrorData *)common; + pr_info("P7IOC PHB#%d Diag-data (Version: %d)\n", + hose->global_number, common->version); + + if (data->brdgCtl) + pr_info("brdgCtl: %08x\n", + data->brdgCtl); + if (data->portStatusReg || data->rootCmplxStatus || + data->busAgentStatus) + pr_info("UtlSts: %08x %08x %08x\n", + data->portStatusReg, data->rootCmplxStatus, + data->busAgentStatus); + if (data->deviceStatus || data->slotStatus || + data->linkStatus || data->devCmdStatus || + data->devSecStatus) + pr_info("RootSts: %08x %08x %08x %08x %08x\n", + data->deviceStatus, data->slotStatus, + data->linkStatus, data->devCmdStatus, + data->devSecStatus); + if (data->rootErrorStatus || data->uncorrErrorStatus || + data->corrErrorStatus) + pr_info("RootErrSts: %08x %08x %08x\n", + data->rootErrorStatus, data->uncorrErrorStatus, + data->corrErrorStatus); + if (data->tlpHdr1 || data->tlpHdr2 || + data->tlpHdr3 || data->tlpHdr4) + pr_info("RootErrLog: %08x %08x %08x %08x\n", + data->tlpHdr1, data->tlpHdr2, + data->tlpHdr3, data->tlpHdr4); + if (data->sourceId || data->errorClass || + data->correlator) + pr_info("RootErrLog1: %08x %016llx %016llx\n", + data->sourceId, data->errorClass, + data->correlator); + if (data->p7iocPlssr || data->p7iocCsr) + pr_info("PhbSts: %016llx %016llx\n", + data->p7iocPlssr, data->p7iocCsr); + if (data->lemFir) + pr_info("Lem: %016llx %016llx %016llx\n", + data->lemFir, data->lemErrorMask, + data->lemWOF); + if (data->phbErrorStatus) + pr_info("PhbErr: %016llx %016llx %016llx %016llx\n", + data->phbErrorStatus, data->phbFirstErrorStatus, + data->phbErrorLog0, data->phbErrorLog1); + if (data->mmioErrorStatus) + pr_info("OutErr: %016llx %016llx %016llx %016llx\n", + data->mmioErrorStatus, data->mmioFirstErrorStatus, + data->mmioErrorLog0, data->mmioErrorLog1); + if (data->dma0ErrorStatus) + pr_info("InAErr: %016llx %016llx %016llx %016llx\n", + data->dma0ErrorStatus, data->dma0FirstErrorStatus, + data->dma0ErrorLog0, data->dma0ErrorLog1); + if (data->dma1ErrorStatus) + pr_info("InBErr: %016llx %016llx %016llx %016llx\n", + data->dma1ErrorStatus, data->dma1FirstErrorStatus, + data->dma1ErrorLog0, data->dma1ErrorLog1); for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) { if ((data->pestA[i] >> 63) == 0 && (data->pestB[i] >> 63) == 0) continue; - pr_info(" PE[%3d] PESTA = 0x%016llx\n", i, data->pestA[i]); - pr_info(" PESTB = 0x%016llx\n", data->pestB[i]); + + pr_info("PE[%3d] A/B: %016llx %016llx\n", + i, data->pestA[i], data->pestB[i]); } } -static void pnv_pci_dump_phb_diag_data(struct pnv_phb *phb) +static void pnv_pci_dump_phb3_diag_data(struct pci_controller *hose, + struct OpalIoPhbErrorCommon *common) { - switch(phb->model) { - case PNV_PHB_MODEL_P7IOC: - pnv_pci_dump_p7ioc_diag_data(phb); + struct OpalIoPhb3ErrorData *data; + int i; + + data = (struct OpalIoPhb3ErrorData*)common; + pr_info("PHB3 PHB#%d Diag-data (Version: %d)\n", + hose->global_number, be32_to_cpu(common->version)); + if (data->brdgCtl) + pr_info("brdgCtl: %08x\n", + be32_to_cpu(data->brdgCtl)); + if (data->portStatusReg || data->rootCmplxStatus || + data->busAgentStatus) + pr_info("UtlSts: %08x %08x %08x\n", + be32_to_cpu(data->portStatusReg), + be32_to_cpu(data->rootCmplxStatus), + be32_to_cpu(data->busAgentStatus)); + if (data->deviceStatus || data->slotStatus || + data->linkStatus || data->devCmdStatus || + data->devSecStatus) + pr_info("RootSts: %08x %08x %08x %08x %08x\n", + be32_to_cpu(data->deviceStatus), + be32_to_cpu(data->slotStatus), + be32_to_cpu(data->linkStatus), + be32_to_cpu(data->devCmdStatus), + be32_to_cpu(data->devSecStatus)); + if (data->rootErrorStatus || data->uncorrErrorStatus || + data->corrErrorStatus) + pr_info("RootErrSts: %08x %08x %08x\n", + be32_to_cpu(data->rootErrorStatus), + be32_to_cpu(data->uncorrErrorStatus), + be32_to_cpu(data->corrErrorStatus)); + if (data->tlpHdr1 || data->tlpHdr2 || + data->tlpHdr3 || data->tlpHdr4) + pr_info("RootErrLog: %08x %08x %08x %08x\n", + be32_to_cpu(data->tlpHdr1), + be32_to_cpu(data->tlpHdr2), + be32_to_cpu(data->tlpHdr3), + be32_to_cpu(data->tlpHdr4)); + if (data->sourceId || data->errorClass || + data->correlator) + pr_info("RootErrLog1: %08x %016llx %016llx\n", + be32_to_cpu(data->sourceId), + be64_to_cpu(data->errorClass), + be64_to_cpu(data->correlator)); + if (data->nFir) + pr_info("nFir: %016llx %016llx %016llx\n", + be64_to_cpu(data->nFir), + be64_to_cpu(data->nFirMask), + be64_to_cpu(data->nFirWOF)); + if (data->phbPlssr || data->phbCsr) + pr_info("PhbSts: %016llx %016llx\n", + be64_to_cpu(data->phbPlssr), + be64_to_cpu(data->phbCsr)); + if (data->lemFir) + pr_info("Lem: %016llx %016llx %016llx\n", + be64_to_cpu(data->lemFir), + be64_to_cpu(data->lemErrorMask), + be64_to_cpu(data->lemWOF)); + if (data->phbErrorStatus) + pr_info("PhbErr: %016llx %016llx %016llx %016llx\n", + be64_to_cpu(data->phbErrorStatus), + be64_to_cpu(data->phbFirstErrorStatus), + be64_to_cpu(data->phbErrorLog0), + be64_to_cpu(data->phbErrorLog1)); + if (data->mmioErrorStatus) + pr_info("OutErr: %016llx %016llx %016llx %016llx\n", + be64_to_cpu(data->mmioErrorStatus), + be64_to_cpu(data->mmioFirstErrorStatus), + be64_to_cpu(data->mmioErrorLog0), + be64_to_cpu(data->mmioErrorLog1)); + if (data->dma0ErrorStatus) + pr_info("InAErr: %016llx %016llx %016llx %016llx\n", + be64_to_cpu(data->dma0ErrorStatus), + be64_to_cpu(data->dma0FirstErrorStatus), + be64_to_cpu(data->dma0ErrorLog0), + be64_to_cpu(data->dma0ErrorLog1)); + if (data->dma1ErrorStatus) + pr_info("InBErr: %016llx %016llx %016llx %016llx\n", + be64_to_cpu(data->dma1ErrorStatus), + be64_to_cpu(data->dma1FirstErrorStatus), + be64_to_cpu(data->dma1ErrorLog0), + be64_to_cpu(data->dma1ErrorLog1)); + + for (i = 0; i < OPAL_PHB3_NUM_PEST_REGS; i++) { + if ((be64_to_cpu(data->pestA[i]) >> 63) == 0 && + (be64_to_cpu(data->pestB[i]) >> 63) == 0) + continue; + + pr_info("PE[%3d] A/B: %016llx %016llx\n", + i, be64_to_cpu(data->pestA[i]), + be64_to_cpu(data->pestB[i])); + } +} + +void pnv_pci_dump_phb_diag_data(struct pci_controller *hose, + unsigned char *log_buff) +{ + struct OpalIoPhbErrorCommon *common; + + if (!hose || !log_buff) + return; + + common = (struct OpalIoPhbErrorCommon *)log_buff; + switch (be32_to_cpu(common->ioType)) { + case OPAL_PHB_ERROR_DATA_TYPE_P7IOC: + pnv_pci_dump_p7ioc_diag_data(hose, common); + break; + case OPAL_PHB_ERROR_DATA_TYPE_PHB3: + pnv_pci_dump_phb3_diag_data(hose, common); break; default: - pr_warning("PCI %d: Can't decode this PHB diag data\n", - phb->hose->global_number); + pr_warn("%s: Unrecognized ioType %d\n", + __func__, be32_to_cpu(common->ioType)); } } @@ -231,7 +323,8 @@ static void pnv_pci_handle_eeh_config(struct pnv_phb *phb, u32 pe_no) spin_lock_irqsave(&phb->lock, flags); - rc = opal_pci_get_phb_diag_data(phb->opal_id, phb->diag.blob, PNV_PCI_DIAG_BUF_SIZE); + rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob, + PNV_PCI_DIAG_BUF_SIZE); has_diag = (rc == OPAL_SUCCESS); rc = opal_pci_eeh_freeze_clear(phb->opal_id, pe_no, @@ -247,7 +340,7 @@ static void pnv_pci_handle_eeh_config(struct pnv_phb *phb, u32 pe_no) * with the normal errors generated when probing empty slots */ if (has_diag) - pnv_pci_dump_phb_diag_data(phb); + pnv_pci_dump_phb_diag_data(phb->hose, phb->diag.blob); else pr_warning("PCI %d: No diag data available\n", phb->hose->global_number); @@ -256,43 +349,51 @@ 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 pci_bus *bus, - u32 bdfn) +static void pnv_pci_config_check_eeh(struct pnv_phb *phb, + struct device_node *dn) { s64 rc; u8 fstate; - u16 pcierr; + __be16 pcierr; u32 pe_no; - /* Get PE# if we support IODA */ - pe_no = phb->bdfn_to_pe ? phb->bdfn_to_pe(phb, bus, bdfn & 0xff) : 0; + /* + * Get the PE#. During the PCI probe stage, we might not + * setup that yet. So all ER errors should be mapped to + * reserved PE. + */ + pe_no = PCI_DN(dn)->pe_number; + if (pe_no == IODA_INVALID_PE) { + if (phb->type == PNV_PHB_P5IOC2) + pe_no = 0; + else + pe_no = phb->ioda.reserved_pe; + } /* Read freeze status */ rc = opal_pci_eeh_freeze_status(phb->opal_id, pe_no, &fstate, &pcierr, NULL); if (rc) { - pr_warning("PCI %d: Failed to read EEH status for PE#%d," - " err %lld\n", phb->hose->global_number, pe_no, rc); + pr_warning("%s: Can't read EEH status (PE#%d) for " + "%s, err %lld\n", + __func__, pe_no, dn->full_name, rc); return; } - cfg_dbg(" -> EEH check, bdfn=%04x PE%d fstate=%x\n", - bdfn, pe_no, fstate); + cfg_dbg(" -> EEH check, bdfn=%04x PE#%d fstate=%x\n", + (PCI_DN(dn)->busno << 8) | (PCI_DN(dn)->devfn), + pe_no, fstate); if (fstate != 0) pnv_pci_handle_eeh_config(phb, pe_no); } -static int pnv_pci_read_config(struct pci_bus *bus, - unsigned int devfn, - int where, int size, u32 *val) +int pnv_pci_cfg_read(struct device_node *dn, + int where, int size, u32 *val) { - struct pci_controller *hose = pci_bus_to_host(bus); - struct pnv_phb *phb = hose->private_data; - u32 bdfn = (((uint64_t)bus->number) << 8) | devfn; + struct pci_dn *pdn = PCI_DN(dn); + struct pnv_phb *phb = pdn->phb->private_data; + u32 bdfn = (pdn->busno << 8) | pdn->devfn; s64 rc; - if (hose == NULL) - return PCIBIOS_DEVICE_NOT_FOUND; - switch (size) { case 1: { u8 v8; @@ -301,43 +402,36 @@ static int pnv_pci_read_config(struct pci_bus *bus, break; } case 2: { - u16 v16; + __be16 v16; rc = opal_pci_config_read_half_word(phb->opal_id, bdfn, where, &v16); - *val = (rc == OPAL_SUCCESS) ? v16 : 0xffff; + *val = (rc == OPAL_SUCCESS) ? be16_to_cpu(v16) : 0xffff; break; } case 4: { - u32 v32; + __be32 v32; rc = opal_pci_config_read_word(phb->opal_id, bdfn, where, &v32); - *val = (rc == OPAL_SUCCESS) ? v32 : 0xffffffff; + *val = (rc == OPAL_SUCCESS) ? be32_to_cpu(v32) : 0xffffffff; break; } default: return PCIBIOS_FUNC_NOT_SUPPORTED; } - cfg_dbg("pnv_pci_read_config bus: %x devfn: %x +%x/%x -> %08x\n", - bus->number, devfn, where, size, *val); - - /* Check if the PHB got frozen due to an error (no response) */ - pnv_pci_config_check_eeh(phb, bus, bdfn); + cfg_dbg("%s: bus: %x devfn: %x +%x/%x -> %08x\n", + __func__, pdn->busno, pdn->devfn, where, size, *val); return PCIBIOS_SUCCESSFUL; } -static int pnv_pci_write_config(struct pci_bus *bus, - unsigned int devfn, - int where, int size, u32 val) +int pnv_pci_cfg_write(struct device_node *dn, + int where, int size, u32 val) { - struct pci_controller *hose = pci_bus_to_host(bus); - struct pnv_phb *phb = hose->private_data; - u32 bdfn = (((uint64_t)bus->number) << 8) | devfn; + struct pci_dn *pdn = PCI_DN(dn); + struct pnv_phb *phb = pdn->phb->private_data; + u32 bdfn = (pdn->busno << 8) | pdn->devfn; - if (hose == NULL) - return PCIBIOS_DEVICE_NOT_FOUND; - - cfg_dbg("pnv_pci_write_config bus: %x devfn: %x +%x/%x -> %08x\n", - bus->number, devfn, where, size, val); + cfg_dbg("%s: bus: %x devfn: %x +%x/%x -> %08x\n", + pdn->busno, pdn->devfn, where, size, val); switch (size) { case 1: opal_pci_config_write_byte(phb->opal_id, bdfn, where, val); @@ -351,65 +445,117 @@ static int pnv_pci_write_config(struct pci_bus *bus, default: return PCIBIOS_FUNC_NOT_SUPPORTED; } - /* Check if the PHB got frozen due to an error (no response) */ - pnv_pci_config_check_eeh(phb, bus, bdfn); return PCIBIOS_SUCCESSFUL; } -struct pci_ops pnv_pci_ops = { - .read = pnv_pci_read_config, - .write = pnv_pci_write_config, -}; +#if CONFIG_EEH +static bool pnv_pci_cfg_check(struct pci_controller *hose, + struct device_node *dn) +{ + struct eeh_dev *edev = NULL; + struct pnv_phb *phb = hose->private_data; + /* EEH not enabled ? */ + if (!(phb->flags & PNV_PHB_FLAG_EEH)) + return true; -static void pnv_tce_invalidate(struct iommu_table *tbl, - u64 *startp, u64 *endp) -{ - u64 __iomem *invalidate = (u64 __iomem *)tbl->it_index; - unsigned long start, end, inc; + /* PE reset or device removed ? */ + edev = of_node_to_eeh_dev(dn); + if (edev) { + if (edev->pe && + (edev->pe->state & EEH_PE_RESET)) + return false; - start = __pa(startp); - end = __pa(endp); + if (edev->mode & EEH_DEV_REMOVED) + return false; + } + return true; +} +#else +static inline pnv_pci_cfg_check(struct pci_controller *hose, + struct device_node *dn) +{ + return true; +} +#endif /* CONFIG_EEH */ - /* BML uses this case for p6/p7/galaxy2: Shift addr and put in node */ - if (tbl->it_busno) { - start <<= 12; - end <<= 12; - inc = 128 << 12; - start |= tbl->it_busno; - end |= tbl->it_busno; +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; + } } - /* p7ioc-style invalidation, 2 TCEs per write */ - else if (tbl->it_type & TCE_PCI_SWINV_PAIR) { - start |= (1ull << 63); - end |= (1ull << 63); - inc = 16; + + if (!found || !pnv_pci_cfg_check(pdn->phb, dn)) + return PCIBIOS_DEVICE_NOT_FOUND; + + ret = pnv_pci_cfg_read(dn, where, size, val); + if (phb->flags & PNV_PHB_FLAG_EEH) { + if (*val == EEH_IO_ERROR_VALUE(size) && + eeh_dev_check_failure(of_node_to_eeh_dev(dn))) + return PCIBIOS_DEVICE_NOT_FOUND; + } else { + pnv_pci_config_check_eeh(phb, dn); } - /* Default (older HW) */ - else - inc = 128; - end |= inc - 1; /* round up end to be different than start */ + return ret; +} - mb(); /* Ensure above stores are visible */ - while (start <= end) { - __raw_writeq(start, invalidate); - start += inc; +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; + } } - /* The iommu layer will do another mb() for us on build() and - * we don't care on free() - */ + + if (!found || !pnv_pci_cfg_check(pdn->phb, dn)) + return PCIBIOS_DEVICE_NOT_FOUND; + + ret = pnv_pci_cfg_write(dn, where, size, val); + if (!(phb->flags & PNV_PHB_FLAG_EEH)) + pnv_pci_config_check_eeh(phb, dn); + + return ret; } +struct pci_ops pnv_pci_ops = { + .read = pnv_pci_read_config, + .write = pnv_pci_write_config, +}; static int pnv_tce_build(struct iommu_table *tbl, long index, long npages, unsigned long uaddr, enum dma_data_direction direction, - struct dma_attrs *attrs) + struct dma_attrs *attrs, bool rm) { u64 proto_tce; - u64 *tcep, *tces; + __be64 *tcep, *tces; u64 rpn; proto_tce = TCE_PCI_READ; // Read allowed @@ -417,33 +563,48 @@ static int pnv_tce_build(struct iommu_table *tbl, long index, long npages, if (direction != DMA_TO_DEVICE) proto_tce |= TCE_PCI_WRITE; - tces = tcep = ((u64 *)tbl->it_base) + index - tbl->it_offset; + tces = tcep = ((__be64 *)tbl->it_base) + index - tbl->it_offset; rpn = __pa(uaddr) >> TCE_SHIFT; while (npages--) - *(tcep++) = proto_tce | (rpn++ << TCE_RPN_SHIFT); + *(tcep++) = cpu_to_be64(proto_tce | (rpn++ << TCE_RPN_SHIFT)); /* Some implementations won't cache invalid TCEs and thus may not * need that flush. We'll probably turn it_type into a bit mask * of flags if that becomes the case */ if (tbl->it_type & TCE_PCI_SWINV_CREATE) - pnv_tce_invalidate(tbl, tces, tcep - 1); + pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1, rm); return 0; } -static void pnv_tce_free(struct iommu_table *tbl, long index, long npages) +static int pnv_tce_build_vm(struct iommu_table *tbl, long index, long npages, + unsigned long uaddr, + enum dma_data_direction direction, + struct dma_attrs *attrs) { - u64 *tcep, *tces; + return pnv_tce_build(tbl, index, npages, uaddr, direction, attrs, + false); +} - tces = tcep = ((u64 *)tbl->it_base) + index - tbl->it_offset; +static void pnv_tce_free(struct iommu_table *tbl, long index, long npages, + bool rm) +{ + __be64 *tcep, *tces; + + tces = tcep = ((__be64 *)tbl->it_base) + index - tbl->it_offset; while (npages--) - *(tcep++) = 0; + *(tcep++) = cpu_to_be64(0); if (tbl->it_type & TCE_PCI_SWINV_FREE) - pnv_tce_invalidate(tbl, tces, tcep - 1); + pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1, rm); +} + +static void pnv_tce_free_vm(struct iommu_table *tbl, long index, long npages) +{ + pnv_tce_free(tbl, index, npages, false); } static unsigned long pnv_tce_get(struct iommu_table *tbl, long index) @@ -451,13 +612,27 @@ static unsigned long pnv_tce_get(struct iommu_table *tbl, long index) return ((u64 *)tbl->it_base)[index - tbl->it_offset]; } +static int pnv_tce_build_rm(struct iommu_table *tbl, long index, long npages, + unsigned long uaddr, + enum dma_data_direction direction, + struct dma_attrs *attrs) +{ + return pnv_tce_build(tbl, index, npages, uaddr, direction, attrs, true); +} + +static void pnv_tce_free_rm(struct iommu_table *tbl, long index, long npages) +{ + pnv_tce_free(tbl, index, npages, true); +} + void pnv_pci_setup_iommu_table(struct iommu_table *tbl, void *tce_mem, u64 tce_size, u64 dma_offset) { tbl->it_blocksize = 16; tbl->it_base = (unsigned long)tce_mem; - tbl->it_offset = dma_offset >> IOMMU_PAGE_SHIFT; + tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K; + tbl->it_offset = dma_offset >> tbl->it_page_shift; tbl->it_index = 0; tbl->it_size = tce_size >> 3; tbl->it_busno = 0; @@ -483,13 +658,14 @@ static struct iommu_table *pnv_pci_setup_bml_iommu(struct pci_controller *hose) pnv_pci_setup_iommu_table(tbl, __va(be64_to_cpup(basep)), be32_to_cpup(sizep), 0); 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 = swinvp[1]; - tbl->it_index = (unsigned long)ioremap(swinvp[0], 8); + 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; @@ -508,7 +684,7 @@ static void pnv_pci_dma_fallback_setup(struct pci_controller *hose, pdn->iommu_table = pnv_pci_setup_bml_iommu(hose); if (!pdn->iommu_table) return; - set_iommu_table_base(&pdev->dev, pdn->iommu_table); + set_iommu_table_base_and_group(&pdev->dev, pdn->iommu_table); } static void pnv_pci_dma_dev_setup(struct pci_dev *pdev) @@ -525,7 +701,29 @@ static void pnv_pci_dma_dev_setup(struct pci_dev *pdev) pnv_pci_dma_fallback_setup(hose, pdev); } -/* Fixup wrong class code in p7ioc root complex */ +int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask) +{ + struct pci_controller *hose = pci_bus_to_host(pdev->bus); + struct pnv_phb *phb = hose->private_data; + + if (phb && phb->dma_set_mask) + return phb->dma_set_mask(phb, pdev, dma_mask); + return __dma_set_mask(&pdev->dev, dma_mask); +} + +void pnv_pci_shutdown(void) +{ + struct pci_controller *hose; + + list_for_each_entry(hose, &hose_list, list_node) { + struct pnv_phb *phb = hose->private_data; + + if (phb && phb->shutdown) + phb->shutdown(phb); + } +} + +/* Fixup wrong class code in p7ioc and p8 root complex */ static void pnv_p7ioc_rc_quirk(struct pci_dev *dev) { dev->class = PCI_CLASS_BRIDGE_PCI << 8; @@ -591,6 +789,10 @@ void __init pnv_pci_init(void) 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); } /* Setup the linkage between OF nodes and PHBs */ @@ -598,8 +800,10 @@ void __init pnv_pci_init(void) /* Configure IOMMU DMA hooks */ ppc_md.pci_dma_dev_setup = pnv_pci_dma_dev_setup; - ppc_md.tce_build = pnv_tce_build; - ppc_md.tce_free = pnv_tce_free; + ppc_md.tce_build = pnv_tce_build_vm; + ppc_md.tce_free = pnv_tce_free_vm; + ppc_md.tce_build_rm = pnv_tce_build_rm; + ppc_md.tce_free_rm = pnv_tce_free_rm; ppc_md.tce_get = pnv_tce_get; ppc_md.pci_probe_mode = pnv_pci_probe_mode; set_pci_dma_ops(&dma_iommu_ops); @@ -611,3 +815,32 @@ void __init pnv_pci_init(void) ppc_md.teardown_msi_irqs = pnv_teardown_msi_irqs; #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; + } +} + +static struct notifier_block tce_iommu_bus_nb = { + .notifier_call = tce_iommu_bus_notifier, +}; + +static int __init tce_iommu_bus_notifier_init(void) +{ + bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb); + return 0; +} + +subsys_initcall_sync(tce_iommu_bus_notifier_init); diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index 7cfb7c883de..676232c3432 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -4,9 +4,9 @@ struct pci_dn; enum pnv_phb_type { - PNV_PHB_P5IOC2, - PNV_PHB_IODA1, - PNV_PHB_IODA2, + PNV_PHB_P5IOC2 = 0, + PNV_PHB_IODA1 = 1, + PNV_PHB_IODA2 = 2, }; /* Precise PHB model for error management */ @@ -14,16 +14,19 @@ enum pnv_phb_model { PNV_PHB_MODEL_UNKNOWN, PNV_PHB_MODEL_P5IOC2, PNV_PHB_MODEL_P7IOC, + PNV_PHB_MODEL_PHB3, }; -#define PNV_PCI_DIAG_BUF_SIZE 4096 +#define PNV_PCI_DIAG_BUF_SIZE 8192 #define PNV_IODA_PE_DEV (1 << 0) /* PE has single PCI device */ #define PNV_IODA_PE_BUS (1 << 1) /* PE has primary PCI bus */ #define PNV_IODA_PE_BUS_ALL (1 << 2) /* PE has subordinate buses */ /* Data associated with a PE, including IOMMU tracking etc.. */ +struct pnv_phb; struct pnv_ioda_pe { unsigned long flags; + struct pnv_phb *phb; /* A PE can be associated with a single device or an * entire bus (& children). In the former case, pdev @@ -49,8 +52,11 @@ struct pnv_ioda_pe { int tce32_seg; int tce32_segcount; struct iommu_table tce32_table; + phys_addr_t tce_inval_reg_phys; - /* XXX TODO: Add support for additional 64-bit iommus */ + /* 64-bit TCE bypass region */ + bool tce_bypass_enabled; + uint64_t tce_bypass_base; /* MSIs. MVE index is identical for for 32 and 64 bit MSI * and -1 if not supported. (It's actually identical to the @@ -63,28 +69,56 @@ 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 (*next_error)(struct eeh_pe **pe); +}; +#endif /* CONFIG_EEH */ + +#define PNV_PHB_FLAG_EEH (1 << 0) + struct pnv_phb { struct pci_controller *hose; enum pnv_phb_type type; enum pnv_phb_model model; + u64 hub_id; u64 opal_id; + int flags; void __iomem *regs; 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; +#endif + #ifdef CONFIG_PCI_MSI - unsigned long *msi_map; unsigned int msi_base; - unsigned int msi_count; - unsigned int msi_next; unsigned int msi32_support; + struct msi_bitmap msi_bmp; #endif int (*msi_setup)(struct pnv_phb *phb, struct pci_dev *dev, - unsigned int hwirq, unsigned int is_64, - struct msi_msg *msg); + unsigned int hwirq, unsigned int virq, + unsigned int is_64, struct msi_msg *msg); void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev); + int (*dma_set_mask)(struct pnv_phb *phb, struct pci_dev *pdev, + u64 dma_mask); void (*fixup_phb)(struct pci_controller *hose); u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn); + void (*shutdown)(struct pnv_phb *phb); union { struct { @@ -94,6 +128,7 @@ struct pnv_phb { struct { /* Global bridge info */ unsigned int total_pe; + unsigned int reserved_pe; unsigned int m32_size; unsigned int m32_segsize; unsigned int m32_pci_base; @@ -109,6 +144,10 @@ struct pnv_phb { unsigned int *io_segmap; struct pnv_ioda_pe *pe_array; + /* IRQ chip */ + int irq_chip_init; + struct irq_chip irq_chip; + /* Sorted list of used PE's based * on the sequence of creation */ @@ -136,20 +175,36 @@ struct pnv_phb { } ioda; }; - /* PHB status structure */ + /* PHB and hub status structure */ union { unsigned char blob[PNV_PCI_DIAG_BUF_SIZE]; struct OpalIoP7IOCPhbErrorData p7ioc; + struct OpalIoPhb3ErrorData phb3; + struct OpalIoP7IOCErrorData hub_diag; } diag; + }; 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 where, int size, u32 *val); +int pnv_pci_cfg_write(struct device_node *dn, + int where, int size, u32 val); extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl, void *tce_mem, u64 tce_size, u64 dma_offset); extern void pnv_pci_init_p5ioc2_hub(struct device_node *np); extern void pnv_pci_init_ioda_hub(struct device_node *np); - +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); #endif /* __POWERNV_PCI_H */ diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h index 8a9df7f9667..75501bfede7 100644 --- a/arch/powerpc/platforms/powernv/powernv.h +++ b/arch/powerpc/platforms/powernv/powernv.h @@ -7,10 +7,24 @@ extern void pnv_smp_init(void); static inline void pnv_smp_init(void) { } #endif +struct pci_dev; + #ifdef CONFIG_PCI extern void pnv_pci_init(void); +extern void pnv_pci_shutdown(void); +extern int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask); #else static inline void pnv_pci_init(void) { } +static inline void pnv_pci_shutdown(void) { } + +static inline int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask) +{ + return -ENODEV; +} #endif +extern void pnv_lpc_init(void); + +bool cpu_core_split_required(void); + #endif /* _POWERNV_H */ diff --git a/arch/powerpc/platforms/powernv/rng.c b/arch/powerpc/platforms/powernv/rng.c new file mode 100644 index 00000000000..1cb160dc160 --- /dev/null +++ b/arch/powerpc/platforms/powernv/rng.c @@ -0,0 +1,126 @@ +/* + * Copyright 2013, Michael Ellerman, 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. + */ + +#define pr_fmt(fmt) "powernv-rng: " fmt + +#include <linux/kernel.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_platform.h> +#include <linux/slab.h> +#include <linux/smp.h> +#include <asm/archrandom.h> +#include <asm/io.h> +#include <asm/prom.h> +#include <asm/machdep.h> +#include <asm/smp.h> + + +struct powernv_rng { + void __iomem *regs; + unsigned long mask; +}; + +static DEFINE_PER_CPU(struct powernv_rng *, powernv_rng); + + +static unsigned long rng_whiten(struct powernv_rng *rng, unsigned long val) +{ + unsigned long parity; + + /* Calculate the parity of the value */ + asm ("popcntd %0,%1" : "=r" (parity) : "r" (val)); + + /* xor our value with the previous mask */ + val ^= rng->mask; + + /* update the mask based on the parity of this value */ + rng->mask = (rng->mask << 1) | (parity & 1); + + return val; +} + +int powernv_get_random_long(unsigned long *v) +{ + struct powernv_rng *rng; + + rng = get_cpu_var(powernv_rng); + + *v = rng_whiten(rng, in_be64(rng->regs)); + + put_cpu_var(rng); + + return 1; +} +EXPORT_SYMBOL_GPL(powernv_get_random_long); + +static __init void rng_init_per_cpu(struct powernv_rng *rng, + struct device_node *dn) +{ + int chip_id, cpu; + + chip_id = of_get_ibm_chip_id(dn); + if (chip_id == -1) + pr_warn("No ibm,chip-id found for %s.\n", dn->full_name); + + for_each_possible_cpu(cpu) { + if (per_cpu(powernv_rng, cpu) == NULL || + cpu_to_chip_id(cpu) == chip_id) { + per_cpu(powernv_rng, cpu) = rng; + } + } +} + +static __init int rng_create(struct device_node *dn) +{ + struct powernv_rng *rng; + unsigned long val; + + rng = kzalloc(sizeof(*rng), GFP_KERNEL); + if (!rng) + return -ENOMEM; + + rng->regs = of_iomap(dn, 0); + if (!rng->regs) { + kfree(rng); + return -ENXIO; + } + + val = in_be64(rng->regs); + rng->mask = val; + + rng_init_per_cpu(rng, dn); + + pr_info_once("Registering arch random hook.\n"); + + ppc_md.get_random_long = powernv_get_random_long; + + return 0; +} + +static __init int rng_init(void) +{ + struct device_node *dn; + int rc; + + for_each_compatible_node(dn, NULL, "ibm,power-rng") { + rc = rng_create(dn); + if (rc) { + pr_err("Failed creating rng for %s (%d).\n", + dn->full_name, rc); + continue; + } + + /* Create devices for hwrng driver */ + of_platform_device_create(dn, NULL, NULL); + } + + return 0; +} +subsys_initcall(rng_init); diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index db1ad1c8f68..d9b88fa7c5a 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -23,19 +23,26 @@ #include <linux/irq.h> #include <linux/seq_file.h> #include <linux/of.h> +#include <linux/of_fdt.h> #include <linux/interrupt.h> #include <linux/bug.h> +#include <linux/pci.h> +#include <linux/cpufreq.h> #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> #include "powernv.h" static void __init pnv_setup_arch(void) { + set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT); + /* Initialize SMP */ pnv_smp_init(); @@ -54,6 +61,12 @@ static void __init pnv_setup_arch(void) static void __init pnv_init_early(void) { + /* + * Initialize the LPC bus now so that legacy serial + * ports can be found on it + */ + opal_lpc_init(); + #ifdef CONFIG_HVC_OPAL if (firmware_has_feature(FW_FEATURE_OPAL)) hvc_opal_init_early(); @@ -78,7 +91,9 @@ static void pnv_show_cpuinfo(struct seq_file *m) if (root) model = of_get_property(root, "model", NULL); seq_printf(m, "machine\t\t: PowerNV %s\n", model); - if (firmware_has_feature(FW_FEATURE_OPALv2)) + if (firmware_has_feature(FW_FEATURE_OPALv3)) + seq_printf(m, "firmware\t: OPAL v3\n"); + else if (firmware_has_feature(FW_FEATURE_OPALv2)) seq_printf(m, "firmware\t: OPAL v2\n"); else if (firmware_has_feature(FW_FEATURE_OPAL)) seq_printf(m, "firmware\t: OPAL v1\n"); @@ -87,10 +102,33 @@ static void pnv_show_cpuinfo(struct seq_file *m) of_node_put(root); } +static void pnv_prepare_going_down(void) +{ + /* + * Disable all notifiers from OPAL, we can't + * service interrupts anymore anyway + */ + opal_notifier_disable(); + + /* Soft disable interrupts */ + local_irq_disable(); + + /* + * Return secondary CPUs to firwmare if a flash update + * is pending otherwise we will get all sort of error + * messages about CPU being stuck etc.. This will also + * have the side effect of hard disabling interrupts so + * past this point, the kernel is effectively dead. + */ + opal_flash_term_callback(); +} + static void __noreturn pnv_restart(char *cmd) { long rc = OPAL_BUSY; + pnv_prepare_going_down(); + while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { rc = opal_cec_reboot(); if (rc == OPAL_BUSY_EVENT) @@ -106,6 +144,8 @@ static void __noreturn pnv_power_off(void) { long rc = OPAL_BUSY; + pnv_prepare_going_down(); + while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { rc = opal_cec_power_down(0); if (rc == OPAL_BUSY_EVENT) @@ -126,13 +166,94 @@ static void pnv_progress(char *s, unsigned short hex) { } +static int pnv_dma_set_mask(struct device *dev, u64 dma_mask) +{ + if (dev_is_pci(dev)) + return pnv_pci_dma_set_mask(to_pci_dev(dev), dma_mask); + return __dma_set_mask(dev, dma_mask); +} + +static void pnv_shutdown(void) +{ + /* Let the PCI code clear up IODA tables */ + pnv_pci_shutdown(); + + /* + * Stop OPAL activity: Unregister all OPAL interrupts so they + * don't fire up while we kexec and make sure all potentially + * DMA'ing ops are complete (such as dump retrieval). + */ + opal_shutdown(); +} + #ifdef CONFIG_KEXEC +static void pnv_kexec_wait_secondaries_down(void) +{ + int my_cpu, i, notified = -1; + + my_cpu = get_cpu(); + + for_each_online_cpu(i) { + uint8_t status; + int64_t rc; + + if (i == my_cpu) + continue; + + for (;;) { + rc = opal_query_cpu_status(get_hard_smp_processor_id(i), + &status); + if (rc != OPAL_SUCCESS || status != OPAL_THREAD_STARTED) + break; + barrier(); + if (i != notified) { + printk(KERN_INFO "kexec: waiting for cpu %d " + "(physical %d) to enter OPAL\n", + i, paca[i].hw_cpu_id); + notified = i; + } + } + } +} + static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) { xics_kexec_teardown_cpu(secondary); + + /* On OPAL v3, we return all CPUs to firmware */ + + if (!firmware_has_feature(FW_FEATURE_OPALv3)) + return; + + if (secondary) { + /* Return secondary CPUs to firmware on OPAL v3 */ + mb(); + get_paca()->kexec_state = KEXEC_STATE_REAL_MODE; + mb(); + + /* Return the CPU to OPAL */ + opal_return_cpu(); + } else if (crash_shutdown) { + /* + * On crash, we don't wait for secondaries to go + * down as they might be unreachable or hung, so + * instead we just wait a bit and move on. + */ + mdelay(1); + } else { + /* Primary waits for the secondaries to have reached OPAL */ + pnv_kexec_wait_secondaries_down(); + } } #endif /* CONFIG_KEXEC */ +#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +static unsigned long pnv_memory_block_size(void) +{ + return 256UL * 1024 * 1024; +} +#endif + static void __init pnv_setup_machdep_opal(void) { ppc_md.get_boot_time = opal_get_boot_time; @@ -142,6 +263,7 @@ static void __init pnv_setup_machdep_opal(void) ppc_md.power_off = pnv_power_off; ppc_md.halt = pnv_halt; ppc_md.machine_check_exception = opal_machine_check; + ppc_md.mce_check_early_recovery = opal_mce_check_early_recovery; } #ifdef CONFIG_PPC_POWERNV_RTAS @@ -179,6 +301,25 @@ static int __init pnv_probe(void) return 1; } +/* + * Returns the cpu frequency for 'cpu' in Hz. This is used by + * /proc/cpuinfo + */ +unsigned long pnv_get_proc_freq(unsigned int cpu) +{ + unsigned long ret_freq; + + ret_freq = cpufreq_quick_get(cpu) * 1000ul; + + /* + * If the backend cpufreq driver does not exist, + * then fallback to old way of reporting the clockrate. + */ + if (!ret_freq) + ret_freq = ppc_proc_freq; + return ret_freq; +} + define_machine(powernv) { .name = "PowerNV", .probe = pnv_probe, @@ -186,10 +327,16 @@ define_machine(powernv) { .setup_arch = pnv_setup_arch, .init_IRQ = pnv_init_IRQ, .show_cpuinfo = pnv_show_cpuinfo, + .get_proc_freq = pnv_get_proc_freq, .progress = pnv_progress, + .machine_shutdown = pnv_shutdown, .power_save = power7_idle, .calibrate_decr = generic_calibrate_decr, + .dma_set_mask = pnv_dma_set_mask, #ifdef CONFIG_KEXEC .kexec_cpu_down = pnv_kexec_cpu_down, #endif +#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE + .memory_block_size = pnv_memory_block_size, +#endif }; diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index 0bdc735db16..5fcfcf44e3a 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -30,6 +30,9 @@ #include <asm/cputhreads.h> #include <asm/xics.h> #include <asm/opal.h> +#include <asm/runlatch.h> +#include <asm/code-patching.h> +#include <asm/dbell.h> #include "powernv.h" @@ -40,47 +43,88 @@ #define DBG(fmt...) #endif -static void __cpuinit pnv_smp_setup_cpu(int cpu) +static void pnv_smp_setup_cpu(int cpu) { if (cpu != boot_cpuid) xics_setup_cpu(); -} - -static int pnv_smp_cpu_bootable(unsigned int nr) -{ - /* Special case - we inhibit secondary thread startup - * during boot if the user requests it. - */ - if (system_state < SYSTEM_RUNNING && cpu_has_feature(CPU_FTR_SMT)) { - if (!smt_enabled_at_boot && cpu_thread_in_core(nr) != 0) - return 0; - if (smt_enabled_at_boot - && cpu_thread_in_core(nr) >= smt_enabled_at_boot) - return 0; - } - return 1; +#ifdef CONFIG_PPC_DOORBELL + if (cpu_has_feature(CPU_FTR_DBELL)) + doorbell_setup_this_cpu(); +#endif } int pnv_smp_kick_cpu(int nr) { unsigned int pcpu = get_hard_smp_processor_id(nr); - unsigned long start_here = __pa(*((unsigned long *) - generic_secondary_smp_init)); + unsigned long start_here = + __pa(ppc_function_entry(generic_secondary_smp_init)); long rc; BUG_ON(nr < 0 || nr >= NR_CPUS); - /* On OPAL v2 the CPU are still spinning inside OPAL itself, - * get them back now + /* + * If we already started or OPALv2 is not supported, we just + * kick the CPU via the PACA + */ + if (paca[nr].cpu_start || !firmware_has_feature(FW_FEATURE_OPALv2)) + goto kick; + + /* + * At this point, the CPU can either be spinning on the way in + * from kexec or be inside OPAL waiting to be started for the + * first time. OPAL v3 allows us to query OPAL to know if it + * has the CPUs, so we do that */ - if (!paca[nr].cpu_start && firmware_has_feature(FW_FEATURE_OPALv2)) { - pr_devel("OPAL: Starting CPU %d (HW 0x%x)...\n", nr, pcpu); - rc = opal_start_cpu(pcpu, start_here); - if (rc != OPAL_SUCCESS) - pr_warn("OPAL Error %ld starting CPU %d\n", + if (firmware_has_feature(FW_FEATURE_OPALv3)) { + uint8_t status; + + rc = opal_query_cpu_status(pcpu, &status); + if (rc != OPAL_SUCCESS) { + pr_warn("OPAL Error %ld querying CPU %d state\n", rc, nr); + return -ENODEV; + } + + /* + * Already started, just kick it, probably coming from + * kexec and spinning + */ + if (status == OPAL_THREAD_STARTED) + goto kick; + + /* + * Available/inactive, let's kick it + */ + if (status == OPAL_THREAD_INACTIVE) { + pr_devel("OPAL: Starting CPU %d (HW 0x%x)...\n", + nr, pcpu); + rc = opal_start_cpu(pcpu, start_here); + if (rc != OPAL_SUCCESS) { + pr_warn("OPAL Error %ld starting CPU %d\n", + rc, nr); + return -ENODEV; + } + } else { + /* + * An unavailable CPU (or any other unknown status) + * shouldn't be started. It should also + * not be in the possible map but currently it can + * happen + */ + pr_devel("OPAL: CPU %d (HW 0x%x) is unavailable" + " (status %d)...\n", nr, pcpu, status); + return -ENODEV; + } + } else { + /* + * On OPAL v2, we just kick it and hope for the best, + * we must not test the error from opal_start_cpu() or + * we would fail to get CPUs from kexec. + */ + opal_start_cpu(pcpu, start_here); } + kick: return smp_generic_kick_cpu(nr); } @@ -120,16 +164,20 @@ static void pnv_smp_cpu_kill_self(void) */ mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1); while (!generic_check_cpu_restart(cpu)) { - power7_nap(); - if (!generic_check_cpu_restart(cpu)) { + ppc64_runlatch_off(); + power7_nap(1); + ppc64_runlatch_on(); + + /* Reenable IRQs briefly to clear the IPI that woke us */ + local_irq_enable(); + local_irq_disable(); + mb(); + + if (cpu_core_split_required()) + continue; + + if (!generic_check_cpu_restart(cpu)) DBG("CPU%d Unexpected exit while offline !\n", cpu); - /* We may be getting an IPI, so we re-enable - * interrupts to process it, it will be ignored - * since we aren't online (hopefully) - */ - local_irq_enable(); - local_irq_disable(); - } } mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_PECE1); DBG("CPU%d coming online...\n", cpu); @@ -143,7 +191,7 @@ static struct smp_ops_t pnv_smp_ops = { .probe = xics_smp_probe, .kick_cpu = pnv_smp_kick_cpu, .setup_cpu = pnv_smp_setup_cpu, - .cpu_bootable = pnv_smp_cpu_bootable, + .cpu_bootable = smp_generic_cpu_bootable, #ifdef CONFIG_HOTPLUG_CPU .cpu_disable = pnv_smp_cpu_disable, .cpu_die = generic_cpu_die, diff --git a/arch/powerpc/platforms/powernv/subcore-asm.S b/arch/powerpc/platforms/powernv/subcore-asm.S new file mode 100644 index 00000000000..39bb24aa8f3 --- /dev/null +++ b/arch/powerpc/platforms/powernv/subcore-asm.S @@ -0,0 +1,95 @@ +/* + * Copyright 2013, Michael (Ellerman|Neuling), 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. + */ + +#include <asm/asm-offsets.h> +#include <asm/ppc_asm.h> +#include <asm/reg.h> + +#include "subcore.h" + + +_GLOBAL(split_core_secondary_loop) + /* + * r3 = u8 *state, used throughout the routine + * r4 = temp + * r5 = temp + * .. + * r12 = MSR + */ + mfmsr r12 + + /* Disable interrupts so SRR0/1 don't get trashed */ + li r4,0 + ori r4,r4,MSR_EE|MSR_SE|MSR_BE|MSR_RI + andc r4,r12,r4 + sync + mtmsrd r4 + + /* Switch to real mode and leave interrupts off */ + li r5, MSR_IR|MSR_DR + andc r5, r4, r5 + + LOAD_REG_ADDR(r4, real_mode) + + mtspr SPRN_SRR0,r4 + mtspr SPRN_SRR1,r5 + rfid + b . /* prevent speculative execution */ + +real_mode: + /* Grab values from unsplit SPRs */ + mfspr r6, SPRN_LDBAR + mfspr r7, SPRN_PMMAR + mfspr r8, SPRN_PMCR + mfspr r9, SPRN_RPR + mfspr r10, SPRN_SDR1 + + /* Order reading the SPRs vs telling the primary we are ready to split */ + sync + + /* Tell thread 0 we are in real mode */ + li r4, SYNC_STEP_REAL_MODE + stb r4, 0(r3) + + li r5, (HID0_POWER8_4LPARMODE | HID0_POWER8_2LPARMODE)@highest + sldi r5, r5, 48 + + /* Loop until we see the split happen in HID0 */ +1: mfspr r4, SPRN_HID0 + and. r4, r4, r5 + beq 1b + + /* + * We only need to initialise the below regs once for each subcore, + * but it's simpler and harmless to do it on each thread. + */ + + /* Make sure various SPRS have sane values */ + li r4, 0 + mtspr SPRN_LPID, r4 + mtspr SPRN_PCR, r4 + mtspr SPRN_HDEC, r4 + + /* Restore SPR values now we are split */ + mtspr SPRN_LDBAR, r6 + mtspr SPRN_PMMAR, r7 + mtspr SPRN_PMCR, r8 + mtspr SPRN_RPR, r9 + mtspr SPRN_SDR1, r10 + + LOAD_REG_ADDR(r5, virtual_mode) + + /* Get out of real mode */ + mtspr SPRN_SRR0,r5 + mtspr SPRN_SRR1,r12 + rfid + b . /* prevent speculative execution */ + +virtual_mode: + blr diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c new file mode 100644 index 00000000000..894ecb3eb59 --- /dev/null +++ b/arch/powerpc/platforms/powernv/subcore.c @@ -0,0 +1,392 @@ +/* + * Copyright 2013, Michael (Ellerman|Neuling), 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. + */ + +#define pr_fmt(fmt) "powernv: " fmt + +#include <linux/kernel.h> +#include <linux/cpu.h> +#include <linux/cpumask.h> +#include <linux/device.h> +#include <linux/gfp.h> +#include <linux/smp.h> +#include <linux/stop_machine.h> + +#include <asm/cputhreads.h> +#include <asm/kvm_ppc.h> +#include <asm/machdep.h> +#include <asm/opal.h> +#include <asm/smp.h> + +#include "subcore.h" + + +/* + * Split/unsplit procedure: + * + * A core can be in one of three states, unsplit, 2-way split, and 4-way split. + * + * The mapping to subcores_per_core is simple: + * + * State | subcores_per_core + * ------------|------------------ + * Unsplit | 1 + * 2-way split | 2 + * 4-way split | 4 + * + * The core is split along thread boundaries, the mapping between subcores and + * threads is as follows: + * + * Unsplit: + * ---------------------------- + * Subcore | 0 | + * ---------------------------- + * Thread | 0 1 2 3 4 5 6 7 | + * ---------------------------- + * + * 2-way split: + * ------------------------------------- + * Subcore | 0 | 1 | + * ------------------------------------- + * Thread | 0 1 2 3 | 4 5 6 7 | + * ------------------------------------- + * + * 4-way split: + * ----------------------------------------- + * Subcore | 0 | 1 | 2 | 3 | + * ----------------------------------------- + * Thread | 0 1 | 2 3 | 4 5 | 6 7 | + * ----------------------------------------- + * + * + * Transitions + * ----------- + * + * It is not possible to transition between either of the split states, the + * core must first be unsplit. The legal transitions are: + * + * ----------- --------------- + * | | <----> | 2-way split | + * | | --------------- + * | Unsplit | + * | | --------------- + * | | <----> | 4-way split | + * ----------- --------------- + * + * Unsplitting + * ----------- + * + * Unsplitting is the simpler procedure. It requires thread 0 to request the + * unsplit while all other threads NAP. + * + * Thread 0 clears HID0_POWER8_DYNLPARDIS (Dynamic LPAR Disable). This tells + * the hardware that if all threads except 0 are napping, the hardware should + * unsplit the core. + * + * Non-zero threads are sent to a NAP loop, they don't exit the loop until they + * see the core unsplit. + * + * Core 0 spins waiting for the hardware to see all the other threads napping + * and perform the unsplit. + * + * Once thread 0 sees the unsplit, it IPIs the secondary threads to wake them + * out of NAP. They will then see the core unsplit and exit the NAP loop. + * + * Splitting + * --------- + * + * The basic splitting procedure is fairly straight forward. However it is + * complicated by the fact that after the split occurs, the newly created + * subcores are not in a fully initialised state. + * + * Most notably the subcores do not have the correct value for SDR1, which + * means they must not be running in virtual mode when the split occurs. The + * subcores have separate timebases SPRs but these are pre-synchronised by + * opal. + * + * To begin with secondary threads are sent to an assembly routine. There they + * switch to real mode, so they are immune to the uninitialised SDR1 value. + * Once in real mode they indicate that they are in real mode, and spin waiting + * to see the core split. + * + * Thread 0 waits to see that all secondaries are in real mode, and then begins + * the splitting procedure. It firstly sets HID0_POWER8_DYNLPARDIS, which + * prevents the hardware from unsplitting. Then it sets the appropriate HID bit + * to request the split, and spins waiting to see that the split has happened. + * + * Concurrently the secondaries will notice the split. When they do they set up + * their SPRs, notably SDR1, and then they can return to virtual mode and exit + * the procedure. + */ + +/* Initialised at boot by subcore_init() */ +static int subcores_per_core; + +/* + * Used to communicate to offline cpus that we want them to pop out of the + * offline loop and do a split or unsplit. + * + * 0 - no split happening + * 1 - unsplit in progress + * 2 - split to 2 in progress + * 4 - split to 4 in progress + */ +static int new_split_mode; + +static cpumask_var_t cpu_offline_mask; + +struct split_state { + u8 step; + u8 master; +}; + +static DEFINE_PER_CPU(struct split_state, split_state); + +static void wait_for_sync_step(int step) +{ + int i, cpu = smp_processor_id(); + + for (i = cpu + 1; i < cpu + threads_per_core; i++) + while(per_cpu(split_state, i).step < step) + barrier(); + + /* Order the wait loop vs any subsequent loads/stores. */ + mb(); +} + +static void unsplit_core(void) +{ + u64 hid0, mask; + int i, cpu; + + mask = HID0_POWER8_2LPARMODE | HID0_POWER8_4LPARMODE; + + cpu = smp_processor_id(); + if (cpu_thread_in_core(cpu) != 0) { + while (mfspr(SPRN_HID0) & mask) + power7_nap(0); + + per_cpu(split_state, cpu).step = SYNC_STEP_UNSPLIT; + return; + } + + hid0 = mfspr(SPRN_HID0); + hid0 &= ~HID0_POWER8_DYNLPARDIS; + mtspr(SPRN_HID0, hid0); + + while (mfspr(SPRN_HID0) & mask) + cpu_relax(); + + /* Wake secondaries out of NAP */ + for (i = cpu + 1; i < cpu + threads_per_core; i++) + smp_send_reschedule(i); + + wait_for_sync_step(SYNC_STEP_UNSPLIT); +} + +static void split_core(int new_mode) +{ + struct { u64 value; u64 mask; } split_parms[2] = { + { HID0_POWER8_1TO2LPAR, HID0_POWER8_2LPARMODE }, + { HID0_POWER8_1TO4LPAR, HID0_POWER8_4LPARMODE } + }; + int i, cpu; + u64 hid0; + + /* Convert new_mode (2 or 4) into an index into our parms array */ + i = (new_mode >> 1) - 1; + BUG_ON(i < 0 || i > 1); + + cpu = smp_processor_id(); + if (cpu_thread_in_core(cpu) != 0) { + split_core_secondary_loop(&per_cpu(split_state, cpu).step); + return; + } + + wait_for_sync_step(SYNC_STEP_REAL_MODE); + + /* Write new mode */ + hid0 = mfspr(SPRN_HID0); + hid0 |= HID0_POWER8_DYNLPARDIS | split_parms[i].value; + mtspr(SPRN_HID0, hid0); + + /* Wait for it to happen */ + while (!(mfspr(SPRN_HID0) & split_parms[i].mask)) + cpu_relax(); +} + +static void cpu_do_split(int new_mode) +{ + /* + * At boot subcores_per_core will be 0, so we will always unsplit at + * boot. In the usual case where the core is already unsplit it's a + * nop, and this just ensures the kernel's notion of the mode is + * consistent with the hardware. + */ + if (subcores_per_core != 1) + unsplit_core(); + + if (new_mode != 1) + split_core(new_mode); + + mb(); + per_cpu(split_state, smp_processor_id()).step = SYNC_STEP_FINISHED; +} + +bool cpu_core_split_required(void) +{ + smp_rmb(); + + if (!new_split_mode) + return false; + + cpu_do_split(new_split_mode); + + return true; +} + +static int cpu_update_split_mode(void *data) +{ + int cpu, new_mode = *(int *)data; + + if (this_cpu_ptr(&split_state)->master) { + new_split_mode = new_mode; + smp_wmb(); + + cpumask_andnot(cpu_offline_mask, cpu_present_mask, + cpu_online_mask); + + /* This should work even though the cpu is offline */ + for_each_cpu(cpu, cpu_offline_mask) + smp_send_reschedule(cpu); + } + + cpu_do_split(new_mode); + + if (this_cpu_ptr(&split_state)->master) { + /* Wait for all cpus to finish before we touch subcores_per_core */ + for_each_present_cpu(cpu) { + if (cpu >= setup_max_cpus) + break; + + while(per_cpu(split_state, cpu).step < SYNC_STEP_FINISHED) + barrier(); + } + + new_split_mode = 0; + + /* Make the new mode public */ + subcores_per_core = new_mode; + threads_per_subcore = threads_per_core / subcores_per_core; + + /* Make sure the new mode is written before we exit */ + mb(); + } + + return 0; +} + +static int set_subcores_per_core(int new_mode) +{ + struct split_state *state; + int cpu; + + if (kvm_hv_mode_active()) { + pr_err("Unable to change split core mode while KVM active.\n"); + return -EBUSY; + } + + /* + * We are only called at boot, or from the sysfs write. If that ever + * changes we'll need a lock here. + */ + BUG_ON(new_mode < 1 || new_mode > 4 || new_mode == 3); + + for_each_present_cpu(cpu) { + state = &per_cpu(split_state, cpu); + state->step = SYNC_STEP_INITIAL; + state->master = 0; + } + + get_online_cpus(); + + /* This cpu will update the globals before exiting stop machine */ + this_cpu_ptr(&split_state)->master = 1; + + /* Ensure state is consistent before we call the other cpus */ + mb(); + + stop_machine(cpu_update_split_mode, &new_mode, cpu_online_mask); + + put_online_cpus(); + + return 0; +} + +static ssize_t __used store_subcores_per_core(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) +{ + unsigned long val; + int rc; + + /* We are serialised by the attribute lock */ + + rc = sscanf(buf, "%lx", &val); + if (rc != 1) + return -EINVAL; + + switch (val) { + case 1: + case 2: + case 4: + if (subcores_per_core == val) + /* Nothing to do */ + goto out; + break; + default: + return -EINVAL; + } + + rc = set_subcores_per_core(val); + if (rc) + return rc; + +out: + return count; +} + +static ssize_t show_subcores_per_core(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "%x\n", subcores_per_core); +} + +static DEVICE_ATTR(subcores_per_core, 0644, + show_subcores_per_core, store_subcores_per_core); + +static int subcore_init(void) +{ + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + return 0; + + /* + * We need all threads in a core to be present to split/unsplit so + * continue only if max_cpus are aligned to threads_per_core. + */ + if (setup_max_cpus % threads_per_core) + return 0; + + BUG_ON(!alloc_cpumask_var(&cpu_offline_mask, GFP_KERNEL)); + + set_subcores_per_core(1); + + return device_create_file(cpu_subsys.dev_root, + &dev_attr_subcores_per_core); +} +machine_device_initcall(powernv, subcore_init); diff --git a/arch/powerpc/platforms/powernv/subcore.h b/arch/powerpc/platforms/powernv/subcore.h new file mode 100644 index 00000000000..148abc91deb --- /dev/null +++ b/arch/powerpc/platforms/powernv/subcore.h @@ -0,0 +1,18 @@ +/* + * Copyright 2013, Michael Ellerman, 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. + */ + +/* These are ordered and tested with <= */ +#define SYNC_STEP_INITIAL 0 +#define SYNC_STEP_UNSPLIT 1 /* Set by secondary when it sees unsplit */ +#define SYNC_STEP_REAL_MODE 2 /* Set by secondary when in real mode */ +#define SYNC_STEP_FINISHED 3 /* Set by secondary when split/unsplit is done */ + +#ifndef __ASSEMBLY__ +void split_core_secondary_loop(u8 *state); +#endif diff --git a/arch/powerpc/platforms/prep/Kconfig b/arch/powerpc/platforms/prep/Kconfig deleted file mode 100644 index 1547f66235d..00000000000 --- a/arch/powerpc/platforms/prep/Kconfig +++ /dev/null @@ -1,23 +0,0 @@ -config PPC_PREP - bool "PowerPC Reference Platform (PReP) based machines" - depends on 6xx && BROKEN - select HAVE_PCSPKR_PLATFORM - select MPIC - select PPC_I8259 - select PPC_INDIRECT_PCI - select PPC_UDBG_16550 - select PPC_NATIVE - default n - -config PREP_RESIDUAL - bool "Support for PReP Residual Data" - depends on PPC_PREP - help - Some PReP systems have residual data passed to the kernel by the - firmware. This allows detection of memory size, devices present and - other useful pieces of information. Sometimes this information is - not present or incorrect, in which case it could lead to the machine - behaving incorrectly. If this happens, either disable PREP_RESIDUAL - or pass the 'noresidual' option to the kernel. - - If you are running a PReP system, say Y here, otherwise say N. diff --git a/arch/powerpc/platforms/ps3/Kconfig b/arch/powerpc/platforms/ps3/Kconfig index 46b7f023252..56f274064d6 100644 --- a/arch/powerpc/platforms/ps3/Kconfig +++ b/arch/powerpc/platforms/ps3/Kconfig @@ -2,10 +2,8 @@ config PPC_PS3 bool "Sony PS3" depends on PPC64 && PPC_BOOK3S select PPC_CELL - select USB_ARCH_HAS_OHCI select USB_OHCI_LITTLE_ENDIAN select USB_OHCI_BIG_ENDIAN_MMIO - select USB_ARCH_HAS_EHCI select USB_EHCI_BIG_ENDIAN_MMIO select PPC_PCI_CHOICE help @@ -48,7 +46,7 @@ config PS3_HTAB_SIZE system will have optimal runtime performance. config PS3_DYNAMIC_DMA - depends on PPC_PS3 && EXPERIMENTAL + depends on PPC_PS3 bool "PS3 Platform dynamic DMA page table management" default n help diff --git a/arch/powerpc/platforms/ps3/htab.c b/arch/powerpc/platforms/ps3/htab.c index d00d7b0a3bd..3e270e3412a 100644 --- a/arch/powerpc/platforms/ps3/htab.c +++ b/arch/powerpc/platforms/ps3/htab.c @@ -27,6 +27,7 @@ #include <asm/lv1call.h> #include <asm/ps3fb.h> +#define PS3_VERBOSE_RESULT #include "platform.h" /** @@ -45,7 +46,7 @@ static DEFINE_SPINLOCK(ps3_htab_lock); static long ps3_hpte_insert(unsigned long hpte_group, unsigned long vpn, unsigned long pa, unsigned long rflags, unsigned long vflags, - int psize, int ssize) + int psize, int apsize, int ssize) { int result; u64 hpte_v, hpte_r; @@ -61,8 +62,8 @@ static long ps3_hpte_insert(unsigned long hpte_group, unsigned long vpn, */ vflags &= ~HPTE_V_SECONDARY; - hpte_v = hpte_encode_v(vpn, psize, ssize) | vflags | HPTE_V_VALID; - hpte_r = hpte_encode_r(ps3_mm_phys_to_lpar(pa), psize) | rflags; + hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID; + hpte_r = hpte_encode_r(ps3_mm_phys_to_lpar(pa), psize, apsize) | rflags; spin_lock_irqsave(&ps3_htab_lock, flags); @@ -75,8 +76,9 @@ static long ps3_hpte_insert(unsigned long hpte_group, unsigned long vpn, if (result) { /* all entries bolted !*/ - pr_info("%s:result=%d vpn=%lx pa=%lx ix=%lx v=%llx r=%llx\n", - __func__, result, vpn, pa, hpte_group, hpte_v, hpte_r); + pr_info("%s:result=%s vpn=%lx pa=%lx ix=%lx v=%llx r=%llx\n", + __func__, ps3_result(result), vpn, pa, hpte_group, + hpte_v, hpte_r); BUG(); } @@ -107,7 +109,8 @@ static long ps3_hpte_remove(unsigned long hpte_group) } static long ps3_hpte_updatepp(unsigned long slot, unsigned long newpp, - unsigned long vpn, int psize, int ssize, int local) + unsigned long vpn, int psize, int apsize, + int ssize, int local) { int result; u64 hpte_v, want_v, hpte_rs; @@ -115,7 +118,7 @@ static long ps3_hpte_updatepp(unsigned long slot, unsigned long newpp, unsigned long flags; long ret; - want_v = hpte_encode_v(vpn, psize, ssize); + want_v = hpte_encode_avpn(vpn, psize, ssize); spin_lock_irqsave(&ps3_htab_lock, flags); @@ -125,8 +128,8 @@ static long ps3_hpte_updatepp(unsigned long slot, unsigned long newpp, &hpte_rs); if (result) { - pr_info("%s: res=%d read vpn=%lx slot=%lx psize=%d\n", - __func__, result, vpn, slot, psize); + pr_info("%s: result=%s read vpn=%lx slot=%lx psize=%d\n", + __func__, ps3_result(result), vpn, slot, psize); BUG(); } @@ -160,7 +163,7 @@ static void ps3_hpte_updateboltedpp(unsigned long newpp, unsigned long ea, } static void ps3_hpte_invalidate(unsigned long slot, unsigned long vpn, - int psize, int ssize, int local) + int psize, int apsize, int ssize, int local) { unsigned long flags; int result; @@ -170,8 +173,8 @@ static void ps3_hpte_invalidate(unsigned long slot, unsigned long vpn, result = lv1_write_htab_entry(PS3_LPAR_VAS_ID_CURRENT, slot, 0, 0); if (result) { - pr_info("%s: res=%d vpn=%lx slot=%lx psize=%d\n", - __func__, result, vpn, slot, psize); + pr_info("%s: result=%s vpn=%lx slot=%lx psize=%d\n", + __func__, ps3_result(result), vpn, slot, psize); BUG(); } diff --git a/arch/powerpc/platforms/ps3/smp.c b/arch/powerpc/platforms/ps3/smp.c index 4b35166229f..b358bec6c8c 100644 --- a/arch/powerpc/platforms/ps3/smp.c +++ b/arch/powerpc/platforms/ps3/smp.c @@ -76,7 +76,7 @@ static int __init ps3_smp_probe(void) BUILD_BUG_ON(PPC_MSG_CALL_FUNCTION != 0); BUILD_BUG_ON(PPC_MSG_RESCHEDULE != 1); - BUILD_BUG_ON(PPC_MSG_CALL_FUNC_SINGLE != 2); + BUILD_BUG_ON(PPC_MSG_TICK_BROADCAST != 2); BUILD_BUG_ON(PPC_MSG_DEBUGGER_BREAK != 3); for (i = 0; i < MSG_COUNT; i++) { diff --git a/arch/powerpc/platforms/ps3/spu.c b/arch/powerpc/platforms/ps3/spu.c index e17fa1432d8..a0bca05e26b 100644 --- a/arch/powerpc/platforms/ps3/spu.c +++ b/arch/powerpc/platforms/ps3/spu.c @@ -143,7 +143,7 @@ static void _dump_areas(unsigned int spe_id, unsigned long priv2, pr_debug("%s:%d: shadow: %lxh\n", func, line, shadow); } -inline u64 ps3_get_spe_id(void *arg) +u64 ps3_get_spe_id(void *arg) { return spu_pdata(arg)->spe_id; } diff --git a/arch/powerpc/platforms/ps3/time.c b/arch/powerpc/platforms/ps3/time.c index 40b5cb43300..ce73ce86561 100644 --- a/arch/powerpc/platforms/ps3/time.c +++ b/arch/powerpc/platforms/ps3/time.c @@ -89,10 +89,8 @@ static int __init ps3_rtc_init(void) return -ENODEV; pdev = platform_device_register_simple("rtc-ps3", -1, NULL, 0); - if (IS_ERR(pdev)) - return PTR_ERR(pdev); - return 0; + return PTR_ERR_OR_ZERO(pdev); } module_init(ps3_rtc_init); diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 837cf49357e..756b482f819 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -17,6 +17,11 @@ config PPC_PSERIES select PPC_NATIVE select PPC_PCI_CHOICE if EXPERT select ZLIB_DEFLATE + select PPC_DOORBELL + select HAVE_CONTEXT_TRACKING + select HOTPLUG_CPU if SMP + select ARCH_RANDOM + select PPC_DOORBELL default y config PPC_SPLPAR @@ -29,14 +34,9 @@ config PPC_SPLPAR processors, that is, which share physical processors between two or more partitions. -config EEH - bool - depends on PPC_PSERIES && PCI - default y - config PSERIES_MSI bool - depends on PCI_MSI && EEH + depends on PCI_MSI && PPC_PSERIES && EEH default y config PSERIES_ENERGY @@ -112,6 +112,18 @@ config CMM will be reused for other LPARs. The interface allows firmware to balance memory across many LPARs. +config HV_PERF_CTRS + bool "Hypervisor supplied PMU events (24x7 & GPCI)" + default y + depends on PERF_EVENTS && PPC_PSERIES + help + Enable access to hypervisor supplied counters in perf. Currently, + this enables code that uses the hcall GetPerfCounterInfo and 24x7 + interfaces to retrieve counters. GPCI exists on Power 6 and later + systems. 24x7 is available on Power 8 systems. + + If unsure, select Y. + config DTL bool "Dispatch Trace Log" depends on PPC_SPLPAR && DEBUG_FS @@ -121,12 +133,3 @@ config DTL which are accessible through a debugfs file. Say N if you are unsure. - -config PSERIES_IDLE - bool "Cpuidle driver for pSeries platforms" - depends on CPU_IDLE - depends on PPC_PSERIES - default y - help - Select this option to enable processor idle state management - through cpuidle subsystem. diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index 890622b87c8..03480796af9 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -1,14 +1,12 @@ -ccflags-$(CONFIG_PPC64) := -mno-minimal-toc +ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC) ccflags-$(CONFIG_PPC_PSERIES_DEBUG) += -DDEBUG obj-y := lpar.o hvCall.o nvram.o reconfig.o \ setup.o iommu.o event_sources.o ras.o \ - firmware.o power.o dlpar.o mobility.o + firmware.o power.o dlpar.o mobility.o rng.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_SCANLOG) += scanlog.o -obj-$(CONFIG_EEH) += eeh.o eeh_pe.o eeh_dev.o eeh_cache.o \ - eeh_driver.o eeh_event.o eeh_sysfs.o \ - eeh_pseries.o +obj-$(CONFIG_EEH) += eeh_pseries.o obj-$(CONFIG_KEXEC) += kexec.o obj-$(CONFIG_PCI) += pci.o pci_dlpar.o obj-$(CONFIG_PSERIES_MSI) += msi.o @@ -23,7 +21,7 @@ obj-$(CONFIG_HCALL_STATS) += hvCall_inst.o obj-$(CONFIG_CMM) += cmm.o obj-$(CONFIG_DTL) += dtl.o obj-$(CONFIG_IO_EVENT_IRQ) += io_event_irq.o -obj-$(CONFIG_PSERIES_IDLE) += processor_idle.o +obj-$(CONFIG_LPARCFG) += lparcfg.o ifeq ($(CONFIG_PPC_PSERIES),y) obj-$(CONFIG_SUSPEND) += suspend.o diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c index c638535753d..2d8bf15879f 100644 --- a/arch/powerpc/platforms/pseries/cmm.c +++ b/arch/powerpc/platforms/pseries/cmm.c @@ -25,7 +25,6 @@ #include <linux/errno.h> #include <linux/fs.h> #include <linux/gfp.h> -#include <linux/init.h> #include <linux/kthread.h> #include <linux/module.h> #include <linux/oom.h> @@ -40,8 +39,7 @@ #include <asm/pgalloc.h> #include <asm/uaccess.h> #include <linux/memory.h> - -#include "plpar_wrappers.h" +#include <asm/plpar_wrappers.h> #define CMM_DRIVER_VERSION "1.0.0" #define CMM_DEFAULT_DELAY 1 diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index a1a7b9a67ff..2d0b4d68a40 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -11,7 +11,6 @@ */ #include <linux/kernel.h> -#include <linux/kref.h> #include <linux/notifier.h> #include <linux/spinlock.h> #include <linux/cpu.h> @@ -63,26 +62,32 @@ static struct property *dlpar_parse_cc_property(struct cc_workarea *ccwa) return prop; } -static struct device_node *dlpar_parse_cc_node(struct cc_workarea *ccwa) +static struct device_node *dlpar_parse_cc_node(struct cc_workarea *ccwa, + const char *path) { struct device_node *dn; char *name; + /* If parent node path is "/" advance path to NULL terminator to + * prevent double leading slashs in full_name. + */ + if (!path[1]) + path++; + dn = kzalloc(sizeof(*dn), GFP_KERNEL); if (!dn) return NULL; - /* The configure connector reported name does not contain a - * preceding '/', so we allocate a buffer large enough to - * prepend this to the full_name. - */ name = (char *)ccwa + ccwa->name_offset; - dn->full_name = kasprintf(GFP_KERNEL, "/%s", name); + dn->full_name = kasprintf(GFP_KERNEL, "%s/%s", path, name); if (!dn->full_name) { kfree(dn); return NULL; } + of_node_set_flag(dn, OF_DYNAMIC); + of_node_init(dn); + return dn; } @@ -120,7 +125,8 @@ void dlpar_free_cc_nodes(struct device_node *dn) #define CALL_AGAIN -2 #define ERR_CFG_USE -9003 -struct device_node *dlpar_configure_connector(u32 drc_index) +struct device_node *dlpar_configure_connector(u32 drc_index, + struct device_node *parent) { struct device_node *dn; struct device_node *first_dn = NULL; @@ -129,6 +135,7 @@ struct device_node *dlpar_configure_connector(u32 drc_index) struct property *last_property = NULL; struct cc_workarea *ccwa; char *data_buf; + const char *parent_path = parent->full_name; int cc_token; int rc = -1; @@ -162,7 +169,7 @@ struct device_node *dlpar_configure_connector(u32 drc_index) break; case NEXT_SIBLING: - dn = dlpar_parse_cc_node(ccwa); + dn = dlpar_parse_cc_node(ccwa, parent_path); if (!dn) goto cc_error; @@ -172,13 +179,17 @@ struct device_node *dlpar_configure_connector(u32 drc_index) break; case NEXT_CHILD: - dn = dlpar_parse_cc_node(ccwa); + if (first_dn) + parent_path = last_dn->full_name; + + dn = dlpar_parse_cc_node(ccwa, parent_path); if (!dn) goto cc_error; - if (!first_dn) + if (!first_dn) { + dn->parent = parent; first_dn = dn; - else { + } else { dn->parent = last_dn; if (last_dn) last_dn->child = dn; @@ -202,6 +213,7 @@ struct device_node *dlpar_configure_connector(u32 drc_index) case PREV_PARENT: last_dn = last_dn->parent; + parent_path = last_dn->parent->full_name; break; case CALL_AGAIN: @@ -256,8 +268,6 @@ int dlpar_attach_node(struct device_node *dn) { int rc; - of_node_set_flag(dn, OF_DYNAMIC); - kref_init(&dn->kref); dn->parent = derive_parent(dn->full_name); if (!dn->parent) return -ENOMEM; @@ -275,8 +285,15 @@ int dlpar_attach_node(struct device_node *dn) int dlpar_detach_node(struct device_node *dn) { + struct device_node *child; int rc; + child = of_get_next_child(dn, NULL); + while (child) { + dlpar_detach_node(child); + child = of_get_next_child(dn, child); + } + rc = of_detach_node(dn); if (rc) return rc; @@ -382,57 +399,42 @@ out: static ssize_t dlpar_cpu_probe(const char *buf, size_t count) { - struct device_node *dn; + struct device_node *dn, *parent; unsigned long drc_index; - char *cpu_name; int rc; - cpu_hotplug_driver_lock(); rc = strict_strtoul(buf, 0, &drc_index); - if (rc) { - rc = -EINVAL; - goto out; - } + if (rc) + return -EINVAL; - dn = dlpar_configure_connector(drc_index); - if (!dn) { - rc = -EINVAL; - goto out; - } + parent = of_find_node_by_path("/cpus"); + if (!parent) + return -ENODEV; - /* configure-connector reports cpus as living in the base - * directory of the device tree. CPUs actually live in the - * cpus directory so we need to fixup the full_name. - */ - cpu_name = kasprintf(GFP_KERNEL, "/cpus%s", dn->full_name); - if (!cpu_name) { - dlpar_free_cc_nodes(dn); - rc = -ENOMEM; - goto out; - } + dn = dlpar_configure_connector(drc_index, parent); + if (!dn) + return -EINVAL; - kfree(dn->full_name); - dn->full_name = cpu_name; + of_node_put(parent); rc = dlpar_acquire_drc(drc_index); if (rc) { dlpar_free_cc_nodes(dn); - rc = -EINVAL; - goto out; + return -EINVAL; } rc = dlpar_attach_node(dn); if (rc) { dlpar_release_drc(drc_index); dlpar_free_cc_nodes(dn); - goto out; + return rc; } rc = dlpar_online_cpu(dn); -out: - cpu_hotplug_driver_unlock(); + if (rc) + return rc; - return rc ? rc : count; + return count; } static int dlpar_offline_cpu(struct device_node *dn) @@ -505,30 +507,27 @@ static ssize_t dlpar_cpu_release(const char *buf, size_t count) return -EINVAL; } - cpu_hotplug_driver_lock(); rc = dlpar_offline_cpu(dn); if (rc) { of_node_put(dn); - rc = -EINVAL; - goto out; + return -EINVAL; } rc = dlpar_release_drc(*drc_index); if (rc) { of_node_put(dn); - goto out; + return rc; } rc = dlpar_detach_node(dn); if (rc) { dlpar_acquire_drc(*drc_index); - goto out; + return rc; } of_node_put(dn); -out: - cpu_hotplug_driver_unlock(); - return rc ? rc : count; + + return count; } static int __init pseries_dlpar_init(void) diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c index a7648543c59..7d61498e45c 100644 --- a/arch/powerpc/platforms/pseries/dtl.c +++ b/arch/powerpc/platforms/pseries/dtl.c @@ -20,7 +20,6 @@ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ -#include <linux/init.h> #include <linux/slab.h> #include <linux/debugfs.h> #include <linux/spinlock.h> @@ -29,8 +28,7 @@ #include <asm/firmware.h> #include <asm/lppaca.h> #include <asm/debug.h> - -#include "plpar_wrappers.h" +#include <asm/plpar_wrappers.h> struct dtl { struct dtl_entry *buf; @@ -57,7 +55,7 @@ static u8 dtl_event_mask = 0x7; */ static int dtl_buf_entries = N_DISPATCH_LOG; -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE struct dtl_ring { u64 write_index; struct dtl_entry *write_ptr; @@ -87,7 +85,7 @@ static void consume_dtle(struct dtl_entry *dtle, u64 index) barrier(); /* check for hypervisor ring buffer overflow, ignore this entry if so */ - if (index + N_DISPATCH_LOG < vpa->dtl_idx) + if (index + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx)) return; ++wp; @@ -142,7 +140,7 @@ static u64 dtl_current_index(struct dtl *dtl) return per_cpu(dtl_rings, dtl->cpu).write_index; } -#else /* CONFIG_VIRT_CPU_ACCOUNTING */ +#else /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ static int dtl_start(struct dtl *dtl) { @@ -188,7 +186,7 @@ static u64 dtl_current_index(struct dtl *dtl) { return lppaca_of(dtl->cpu).dtl_idx; } -#endif /* CONFIG_VIRT_CPU_ACCOUNTING */ +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ static int dtl_enable(struct dtl *dtl) { diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c deleted file mode 100644 index 9a04322b173..00000000000 --- a/arch/powerpc/platforms/pseries/eeh.c +++ /dev/null @@ -1,920 +0,0 @@ -/* - * Copyright IBM Corporation 2001, 2005, 2006 - * Copyright Dave Engebretsen & Todd Inglett 2001 - * Copyright Linas Vepstas 2005, 2006 - * Copyright 2001-2012 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * - * Please address comments and feedback to Linas Vepstas <linas@austin.ibm.com> - */ - -#include <linux/delay.h> -#include <linux/sched.h> -#include <linux/init.h> -#include <linux/list.h> -#include <linux/pci.h> -#include <linux/proc_fs.h> -#include <linux/rbtree.h> -#include <linux/seq_file.h> -#include <linux/spinlock.h> -#include <linux/export.h> -#include <linux/of.h> - -#include <linux/atomic.h> -#include <asm/eeh.h> -#include <asm/eeh_event.h> -#include <asm/io.h> -#include <asm/machdep.h> -#include <asm/ppc-pci.h> -#include <asm/rtas.h> - - -/** Overview: - * EEH, or "Extended Error Handling" is a PCI bridge technology for - * dealing with PCI bus errors that can't be dealt with within the - * usual PCI framework, except by check-stopping the CPU. Systems - * that are designed for high-availability/reliability cannot afford - * to crash due to a "mere" PCI error, thus the need for EEH. - * An EEH-capable bridge operates by converting a detected error - * into a "slot freeze", taking the PCI adapter off-line, making - * the slot behave, from the OS'es point of view, as if the slot - * were "empty": all reads return 0xff's and all writes are silently - * ignored. EEH slot isolation events can be triggered by parity - * errors on the address or data busses (e.g. during posted writes), - * which in turn might be caused by low voltage on the bus, dust, - * vibration, humidity, radioactivity or plain-old failed hardware. - * - * Note, however, that one of the leading causes of EEH slot - * freeze events are buggy device drivers, buggy device microcode, - * or buggy device hardware. This is because any attempt by the - * device to bus-master data to a memory address that is not - * assigned to the device will trigger a slot freeze. (The idea - * is to prevent devices-gone-wild from corrupting system memory). - * Buggy hardware/drivers will have a miserable time co-existing - * with EEH. - * - * Ideally, a PCI device driver, when suspecting that an isolation - * event has occurred (e.g. by reading 0xff's), will then ask EEH - * whether this is the case, and then take appropriate steps to - * reset the PCI slot, the PCI device, and then resume operations. - * However, until that day, the checking is done here, with the - * eeh_check_failure() routine embedded in the MMIO macros. If - * the slot is found to be isolated, an "EEH Event" is synthesized - * and sent out for processing. - */ - -/* If a device driver keeps reading an MMIO register in an interrupt - * handler after a slot isolation event, it might be broken. - * This sets the threshold for how many read attempts we allow - * before printing an error message. - */ -#define EEH_MAX_FAILS 2100000 - -/* Time to wait for a PCI slot to report status, in milliseconds */ -#define PCI_BUS_RESET_WAIT_MSEC (60*1000) - -/* Platform dependent EEH operations */ -struct eeh_ops *eeh_ops = NULL; - -int eeh_subsystem_enabled; -EXPORT_SYMBOL(eeh_subsystem_enabled); - -/* - * EEH probe mode support. The intention is to support multiple - * platforms for EEH. Some platforms like pSeries do PCI emunation - * based on device tree. However, other platforms like powernv probe - * PCI devices from hardware. The flag is used to distinguish that. - * In addition, struct eeh_ops::probe would be invoked for particular - * OF node or PCI device so that the corresponding PE would be created - * there. - */ -int eeh_probe_mode; - -/* Global EEH mutex */ -DEFINE_MUTEX(eeh_mutex); - -/* Lock to avoid races due to multiple reports of an error */ -static DEFINE_RAW_SPINLOCK(confirm_error_lock); - -/* Buffer for reporting pci register dumps. Its here in BSS, and - * not dynamically alloced, so that it ends up in RMO where RTAS - * can access it. - */ -#define EEH_PCI_REGS_LOG_LEN 4096 -static unsigned char pci_regs_buf[EEH_PCI_REGS_LOG_LEN]; - -/* - * The struct is used to maintain the EEH global statistic - * information. Besides, the EEH global statistics will be - * exported to user space through procfs - */ -struct eeh_stats { - u64 no_device; /* PCI device not found */ - u64 no_dn; /* OF node not found */ - u64 no_cfg_addr; /* Config address not found */ - u64 ignored_check; /* EEH check skipped */ - u64 total_mmio_ffs; /* Total EEH checks */ - u64 false_positives; /* Unnecessary EEH checks */ - u64 slot_resets; /* PE reset */ -}; - -static struct eeh_stats eeh_stats; - -#define IS_BRIDGE(class_code) (((class_code)<<16) == PCI_BASE_CLASS_BRIDGE) - -/** - * eeh_gather_pci_data - Copy assorted PCI config space registers to buff - * @edev: device to report data for - * @buf: point to buffer in which to log - * @len: amount of room in buffer - * - * This routine captures assorted PCI configuration space data, - * and puts them into a buffer for RTAS error logging. - */ -static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len) -{ - struct device_node *dn = eeh_dev_to_of_node(edev); - struct pci_dev *dev = eeh_dev_to_pci_dev(edev); - u32 cfg; - int cap, i; - int n = 0; - - n += scnprintf(buf+n, len-n, "%s\n", dn->full_name); - printk(KERN_WARNING "EEH: of node=%s\n", dn->full_name); - - eeh_ops->read_config(dn, PCI_VENDOR_ID, 4, &cfg); - n += scnprintf(buf+n, len-n, "dev/vend:%08x\n", cfg); - printk(KERN_WARNING "EEH: PCI device/vendor: %08x\n", cfg); - - eeh_ops->read_config(dn, PCI_COMMAND, 4, &cfg); - n += scnprintf(buf+n, len-n, "cmd/stat:%x\n", cfg); - printk(KERN_WARNING "EEH: PCI cmd/status register: %08x\n", cfg); - - if (!dev) { - printk(KERN_WARNING "EEH: no PCI device for this of node\n"); - return n; - } - - /* Gather bridge-specific registers */ - if (dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) { - eeh_ops->read_config(dn, PCI_SEC_STATUS, 2, &cfg); - n += scnprintf(buf+n, len-n, "sec stat:%x\n", cfg); - printk(KERN_WARNING "EEH: Bridge secondary status: %04x\n", cfg); - - eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &cfg); - n += scnprintf(buf+n, len-n, "brdg ctl:%x\n", cfg); - printk(KERN_WARNING "EEH: Bridge control: %04x\n", cfg); - } - - /* Dump out the PCI-X command and status regs */ - cap = pci_find_capability(dev, PCI_CAP_ID_PCIX); - if (cap) { - eeh_ops->read_config(dn, cap, 4, &cfg); - n += scnprintf(buf+n, len-n, "pcix-cmd:%x\n", cfg); - printk(KERN_WARNING "EEH: PCI-X cmd: %08x\n", cfg); - - eeh_ops->read_config(dn, cap+4, 4, &cfg); - n += scnprintf(buf+n, len-n, "pcix-stat:%x\n", cfg); - printk(KERN_WARNING "EEH: PCI-X status: %08x\n", cfg); - } - - /* If PCI-E capable, dump PCI-E cap 10, and the AER */ - cap = pci_find_capability(dev, PCI_CAP_ID_EXP); - if (cap) { - n += scnprintf(buf+n, len-n, "pci-e cap10:\n"); - printk(KERN_WARNING - "EEH: PCI-E capabilities and status follow:\n"); - - for (i=0; i<=8; i++) { - eeh_ops->read_config(dn, cap+4*i, 4, &cfg); - n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg); - printk(KERN_WARNING "EEH: PCI-E %02x: %08x\n", i, cfg); - } - - cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); - if (cap) { - n += scnprintf(buf+n, len-n, "pci-e AER:\n"); - printk(KERN_WARNING - "EEH: PCI-E AER capability register set follows:\n"); - - for (i=0; i<14; i++) { - eeh_ops->read_config(dn, cap+4*i, 4, &cfg); - n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg); - printk(KERN_WARNING "EEH: PCI-E AER %02x: %08x\n", i, cfg); - } - } - } - - return n; -} - -/** - * eeh_slot_error_detail - Generate combined log including driver log and error log - * @pe: EEH PE - * @severity: temporary or permanent error log - * - * This routine should be called to generate the combined log, which - * is comprised of driver log and error log. The driver log is figured - * out from the config space of the corresponding PCI device, while - * the error log is fetched through platform dependent function call. - */ -void eeh_slot_error_detail(struct eeh_pe *pe, int severity) -{ - size_t loglen = 0; - struct eeh_dev *edev; - - eeh_pci_enable(pe, EEH_OPT_THAW_MMIO); - eeh_ops->configure_bridge(pe); - eeh_pe_restore_bars(pe); - - pci_regs_buf[0] = 0; - eeh_pe_for_each_dev(pe, edev) { - loglen += eeh_gather_pci_data(edev, pci_regs_buf, - EEH_PCI_REGS_LOG_LEN); - } - - eeh_ops->get_log(pe, severity, pci_regs_buf, loglen); -} - -/** - * eeh_token_to_phys - Convert EEH address token to phys address - * @token: I/O token, should be address in the form 0xA.... - * - * This routine should be called to convert virtual I/O address - * to physical one. - */ -static inline unsigned long eeh_token_to_phys(unsigned long token) -{ - pte_t *ptep; - unsigned long pa; - - ptep = find_linux_pte(init_mm.pgd, token); - if (!ptep) - return token; - pa = pte_pfn(*ptep) << PAGE_SHIFT; - - return pa | (token & (PAGE_SIZE-1)); -} - -/** - * eeh_dev_check_failure - Check if all 1's data is due to EEH slot freeze - * @edev: eeh device - * - * Check for an EEH failure for the given device node. Call this - * routine if the result of a read was all 0xff's and you want to - * find out if this is due to an EEH slot freeze. This routine - * will query firmware for the EEH status. - * - * Returns 0 if there has not been an EEH error; otherwise returns - * a non-zero value and queues up a slot isolation event notification. - * - * It is safe to call this routine in an interrupt context. - */ -int eeh_dev_check_failure(struct eeh_dev *edev) -{ - int ret; - unsigned long flags; - struct device_node *dn; - struct pci_dev *dev; - struct eeh_pe *pe; - int rc = 0; - const char *location; - - eeh_stats.total_mmio_ffs++; - - if (!eeh_subsystem_enabled) - return 0; - - if (!edev) { - eeh_stats.no_dn++; - return 0; - } - dn = eeh_dev_to_of_node(edev); - dev = eeh_dev_to_pci_dev(edev); - pe = edev->pe; - - /* Access to IO BARs might get this far and still not want checking. */ - if (!pe) { - eeh_stats.ignored_check++; - pr_debug("EEH: Ignored check for %s %s\n", - eeh_pci_name(dev), dn->full_name); - return 0; - } - - if (!pe->addr && !pe->config_addr) { - eeh_stats.no_cfg_addr++; - return 0; - } - - /* If we already have a pending isolation event for this - * slot, we know it's bad already, we don't need to check. - * Do this checking under a lock; as multiple PCI devices - * in one slot might report errors simultaneously, and we - * only want one error recovery routine running. - */ - raw_spin_lock_irqsave(&confirm_error_lock, flags); - rc = 1; - if (pe->state & EEH_PE_ISOLATED) { - pe->check_count++; - if (pe->check_count % EEH_MAX_FAILS == 0) { - location = of_get_property(dn, "ibm,loc-code", NULL); - printk(KERN_ERR "EEH: %d reads ignored for recovering device at " - "location=%s driver=%s pci addr=%s\n", - pe->check_count, location, - eeh_driver_name(dev), eeh_pci_name(dev)); - printk(KERN_ERR "EEH: Might be infinite loop in %s driver\n", - eeh_driver_name(dev)); - dump_stack(); - } - goto dn_unlock; - } - - /* - * Now test for an EEH failure. This is VERY expensive. - * Note that the eeh_config_addr may be a parent device - * in the case of a device behind a bridge, or it may be - * function zero of a multi-function device. - * In any case they must share a common PHB. - */ - ret = eeh_ops->get_state(pe, NULL); - - /* Note that config-io to empty slots may fail; - * they are empty when they don't have children. - * We will punt with the following conditions: Failure to get - * PE's state, EEH not support and Permanently unavailable - * state, PE is in good state. - */ - if ((ret < 0) || - (ret == EEH_STATE_NOT_SUPPORT) || - (ret & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) == - (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) { - eeh_stats.false_positives++; - pe->false_positives++; - rc = 0; - goto dn_unlock; - } - - eeh_stats.slot_resets++; - - /* Avoid repeated reports of this failure, including problems - * with other functions on this device, and functions under - * bridges. - */ - eeh_pe_state_mark(pe, EEH_PE_ISOLATED); - raw_spin_unlock_irqrestore(&confirm_error_lock, flags); - - eeh_send_failure_event(pe); - - /* Most EEH events are due to device driver bugs. Having - * a stack trace will help the device-driver authors figure - * out what happened. So print that out. - */ - WARN(1, "EEH: failure detected\n"); - return 1; - -dn_unlock: - raw_spin_unlock_irqrestore(&confirm_error_lock, flags); - return rc; -} - -EXPORT_SYMBOL_GPL(eeh_dev_check_failure); - -/** - * eeh_check_failure - Check if all 1's data is due to EEH slot freeze - * @token: I/O token, should be address in the form 0xA.... - * @val: value, should be all 1's (XXX why do we need this arg??) - * - * Check for an EEH failure at the given token address. Call this - * routine if the result of a read was all 0xff's and you want to - * find out if this is due to an EEH slot freeze event. This routine - * will query firmware for the EEH status. - * - * Note this routine is safe to call in an interrupt context. - */ -unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned long val) -{ - unsigned long addr; - struct eeh_dev *edev; - - /* Finding the phys addr + pci device; this is pretty quick. */ - addr = eeh_token_to_phys((unsigned long __force) token); - edev = eeh_addr_cache_get_dev(addr); - if (!edev) { - eeh_stats.no_device++; - return val; - } - - eeh_dev_check_failure(edev); - - pci_dev_put(eeh_dev_to_pci_dev(edev)); - return val; -} - -EXPORT_SYMBOL(eeh_check_failure); - - -/** - * eeh_pci_enable - Enable MMIO or DMA transfers for this slot - * @pe: EEH PE - * - * This routine should be called to reenable frozen MMIO or DMA - * so that it would work correctly again. It's useful while doing - * recovery or log collection on the indicated device. - */ -int eeh_pci_enable(struct eeh_pe *pe, int function) -{ - int rc; - - rc = eeh_ops->set_option(pe, function); - if (rc) - pr_warning("%s: Unexpected state change %d on PHB#%d-PE#%x, err=%d\n", - __func__, function, pe->phb->global_number, pe->addr, rc); - - rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC); - if (rc > 0 && (rc & EEH_STATE_MMIO_ENABLED) && - (function == EEH_OPT_THAW_MMIO)) - return 0; - - return rc; -} - -/** - * pcibios_set_pcie_slot_reset - Set PCI-E reset state - * @dev: pci device struct - * @state: reset state to enter - * - * Return value: - * 0 if success - */ -int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state state) -{ - struct eeh_dev *edev = pci_dev_to_eeh_dev(dev); - struct eeh_pe *pe = edev->pe; - - if (!pe) { - pr_err("%s: No PE found on PCI device %s\n", - __func__, pci_name(dev)); - return -EINVAL; - } - - switch (state) { - case pcie_deassert_reset: - eeh_ops->reset(pe, EEH_RESET_DEACTIVATE); - break; - case pcie_hot_reset: - eeh_ops->reset(pe, EEH_RESET_HOT); - break; - case pcie_warm_reset: - eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL); - break; - default: - return -EINVAL; - }; - - return 0; -} - -/** - * eeh_set_pe_freset - Check the required reset for the indicated device - * @data: EEH device - * @flag: return value - * - * Each device might have its preferred reset type: fundamental or - * hot reset. The routine is used to collected the information for - * the indicated device and its children so that the bunch of the - * devices could be reset properly. - */ -static void *eeh_set_dev_freset(void *data, void *flag) -{ - struct pci_dev *dev; - unsigned int *freset = (unsigned int *)flag; - struct eeh_dev *edev = (struct eeh_dev *)data; - - dev = eeh_dev_to_pci_dev(edev); - if (dev) - *freset |= dev->needs_freset; - - return NULL; -} - -/** - * eeh_reset_pe_once - Assert the pci #RST line for 1/4 second - * @pe: EEH PE - * - * Assert the PCI #RST line for 1/4 second. - */ -static void eeh_reset_pe_once(struct eeh_pe *pe) -{ - unsigned int freset = 0; - - /* Determine type of EEH reset required for - * Partitionable Endpoint, a hot-reset (1) - * or a fundamental reset (3). - * A fundamental reset required by any device under - * Partitionable Endpoint trumps hot-reset. - */ - eeh_pe_dev_traverse(pe, eeh_set_dev_freset, &freset); - - if (freset) - eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL); - else - eeh_ops->reset(pe, EEH_RESET_HOT); - - /* The PCI bus requires that the reset be held high for at least - * a 100 milliseconds. We wait a bit longer 'just in case'. - */ -#define PCI_BUS_RST_HOLD_TIME_MSEC 250 - msleep(PCI_BUS_RST_HOLD_TIME_MSEC); - - /* We might get hit with another EEH freeze as soon as the - * pci slot reset line is dropped. Make sure we don't miss - * these, and clear the flag now. - */ - eeh_pe_state_clear(pe, EEH_PE_ISOLATED); - - eeh_ops->reset(pe, EEH_RESET_DEACTIVATE); - - /* After a PCI slot has been reset, the PCI Express spec requires - * a 1.5 second idle time for the bus to stabilize, before starting - * up traffic. - */ -#define PCI_BUS_SETTLE_TIME_MSEC 1800 - msleep(PCI_BUS_SETTLE_TIME_MSEC); -} - -/** - * eeh_reset_pe - Reset the indicated PE - * @pe: EEH PE - * - * This routine should be called to reset indicated device, including - * PE. A PE might include multiple PCI devices and sometimes PCI bridges - * might be involved as well. - */ -int eeh_reset_pe(struct eeh_pe *pe) -{ - int i, rc; - - /* Take three shots at resetting the bus */ - for (i=0; i<3; i++) { - eeh_reset_pe_once(pe); - - rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC); - if (rc == (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) - return 0; - - if (rc < 0) { - pr_err("%s: Unrecoverable slot failure on PHB#%d-PE#%x", - __func__, pe->phb->global_number, pe->addr); - return -1; - } - pr_err("EEH: bus reset %d failed on PHB#%d-PE#%x, rc=%d\n", - i+1, pe->phb->global_number, pe->addr, rc); - } - - return -1; -} - -/** - * eeh_save_bars - Save device bars - * @edev: PCI device associated EEH device - * - * Save the values of the device bars. Unlike the restore - * routine, this routine is *not* recursive. This is because - * PCI devices are added individually; but, for the restore, - * an entire slot is reset at a time. - */ -void eeh_save_bars(struct eeh_dev *edev) -{ - int i; - struct device_node *dn; - - if (!edev) - return; - dn = eeh_dev_to_of_node(edev); - - for (i = 0; i < 16; i++) - eeh_ops->read_config(dn, i * 4, 4, &edev->config_space[i]); -} - -/** - * eeh_ops_register - Register platform dependent EEH operations - * @ops: platform dependent EEH operations - * - * Register the platform dependent EEH operation callback - * functions. The platform should call this function before - * any other EEH operations. - */ -int __init eeh_ops_register(struct eeh_ops *ops) -{ - if (!ops->name) { - pr_warning("%s: Invalid EEH ops name for %p\n", - __func__, ops); - return -EINVAL; - } - - if (eeh_ops && eeh_ops != ops) { - pr_warning("%s: EEH ops of platform %s already existing (%s)\n", - __func__, eeh_ops->name, ops->name); - return -EEXIST; - } - - eeh_ops = ops; - - return 0; -} - -/** - * eeh_ops_unregister - Unreigster platform dependent EEH operations - * @name: name of EEH platform operations - * - * Unregister the platform dependent EEH operation callback - * functions. - */ -int __exit eeh_ops_unregister(const char *name) -{ - if (!name || !strlen(name)) { - pr_warning("%s: Invalid EEH ops name\n", - __func__); - return -EINVAL; - } - - if (eeh_ops && !strcmp(eeh_ops->name, name)) { - eeh_ops = NULL; - return 0; - } - - return -EEXIST; -} - -/** - * eeh_init - EEH initialization - * - * Initialize EEH by trying to enable it for all of the adapters in the system. - * As a side effect we can determine here if eeh is supported at all. - * Note that we leave EEH on so failed config cycles won't cause a machine - * check. If a user turns off EEH for a particular adapter they are really - * telling Linux to ignore errors. Some hardware (e.g. POWER5) won't - * grant access to a slot if EEH isn't enabled, and so we always enable - * EEH for all slots/all devices. - * - * The eeh-force-off option disables EEH checking globally, for all slots. - * Even if force-off is set, the EEH hardware is still enabled, so that - * newer systems can boot. - */ -static int __init eeh_init(void) -{ - struct pci_controller *hose, *tmp; - struct device_node *phb; - int ret; - - /* call platform initialization function */ - if (!eeh_ops) { - pr_warning("%s: Platform EEH operation not found\n", - __func__); - return -EEXIST; - } else if ((ret = eeh_ops->init())) { - pr_warning("%s: Failed to call platform init function (%d)\n", - __func__, ret); - return ret; - } - - raw_spin_lock_init(&confirm_error_lock); - - /* Enable EEH for all adapters */ - if (eeh_probe_mode_devtree()) { - list_for_each_entry_safe(hose, tmp, - &hose_list, list_node) { - phb = hose->dn; - traverse_pci_devices(phb, eeh_ops->of_probe, NULL); - } - } - - if (eeh_subsystem_enabled) - pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n"); - else - pr_warning("EEH: No capable adapters found\n"); - - return ret; -} - -core_initcall_sync(eeh_init); - -/** - * eeh_add_device_early - Enable EEH for the indicated device_node - * @dn: device node for which to set up EEH - * - * This routine must be used to perform EEH initialization for PCI - * devices that were added after system boot (e.g. hotplug, dlpar). - * This routine must be called before any i/o is performed to the - * adapter (inluding any config-space i/o). - * Whether this actually enables EEH or not for this device depends - * on the CEC architecture, type of the device, on earlier boot - * command-line arguments & etc. - */ -static void eeh_add_device_early(struct device_node *dn) -{ - struct pci_controller *phb; - - if (!of_node_to_eeh_dev(dn)) - return; - phb = of_node_to_eeh_dev(dn)->phb; - - /* USB Bus children of PCI devices will not have BUID's */ - if (NULL == phb || 0 == phb->buid) - return; - - /* FIXME: hotplug support on POWERNV */ - eeh_ops->of_probe(dn, NULL); -} - -/** - * eeh_add_device_tree_early - Enable EEH for the indicated device - * @dn: device node - * - * This routine must be used to perform EEH initialization for the - * indicated PCI device that was added after system boot (e.g. - * hotplug, dlpar). - */ -void eeh_add_device_tree_early(struct device_node *dn) -{ - struct device_node *sib; - - for_each_child_of_node(dn, sib) - eeh_add_device_tree_early(sib); - eeh_add_device_early(dn); -} -EXPORT_SYMBOL_GPL(eeh_add_device_tree_early); - -/** - * eeh_add_device_late - Perform EEH initialization for the indicated pci device - * @dev: pci device for which to set up EEH - * - * This routine must be used to complete EEH initialization for PCI - * devices that were added after system boot (e.g. hotplug, dlpar). - */ -static void eeh_add_device_late(struct pci_dev *dev) -{ - struct device_node *dn; - struct eeh_dev *edev; - - if (!dev || !eeh_subsystem_enabled) - return; - - pr_debug("EEH: Adding device %s\n", pci_name(dev)); - - dn = pci_device_to_OF_node(dev); - edev = of_node_to_eeh_dev(dn); - if (edev->pdev == dev) { - pr_debug("EEH: Already referenced !\n"); - return; - } - WARN_ON(edev->pdev); - - pci_dev_get(dev); - edev->pdev = dev; - dev->dev.archdata.edev = edev; - - eeh_addr_cache_insert_dev(dev); - eeh_sysfs_add_device(dev); -} - -/** - * eeh_add_device_tree_late - Perform EEH initialization for the indicated PCI bus - * @bus: PCI bus - * - * This routine must be used to perform EEH initialization for PCI - * devices which are attached to the indicated PCI bus. The PCI bus - * is added after system boot through hotplug or dlpar. - */ -void eeh_add_device_tree_late(struct pci_bus *bus) -{ - struct pci_dev *dev; - - list_for_each_entry(dev, &bus->devices, bus_list) { - eeh_add_device_late(dev); - if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) { - struct pci_bus *subbus = dev->subordinate; - if (subbus) - eeh_add_device_tree_late(subbus); - } - } -} -EXPORT_SYMBOL_GPL(eeh_add_device_tree_late); - -/** - * eeh_remove_device - Undo EEH setup for the indicated pci device - * @dev: pci device to be removed - * @purge_pe: remove the PE or not - * - * This routine should be called when a device is removed from - * a running system (e.g. by hotplug or dlpar). It unregisters - * the PCI device from the EEH subsystem. I/O errors affecting - * this device will no longer be detected after this call; thus, - * i/o errors affecting this slot may leave this device unusable. - */ -static void eeh_remove_device(struct pci_dev *dev, int purge_pe) -{ - struct eeh_dev *edev; - - if (!dev || !eeh_subsystem_enabled) - return; - edev = pci_dev_to_eeh_dev(dev); - - /* Unregister the device with the EEH/PCI address search system */ - pr_debug("EEH: Removing device %s\n", pci_name(dev)); - - if (!edev || !edev->pdev) { - pr_debug("EEH: Not referenced !\n"); - return; - } - edev->pdev = NULL; - dev->dev.archdata.edev = NULL; - pci_dev_put(dev); - - eeh_rmv_from_parent_pe(edev, purge_pe); - eeh_addr_cache_rmv_dev(dev); - eeh_sysfs_remove_device(dev); -} - -/** - * eeh_remove_bus_device - Undo EEH setup for the indicated PCI device - * @dev: PCI device - * @purge_pe: remove the corresponding PE or not - * - * This routine must be called when a device is removed from the - * running system through hotplug or dlpar. The corresponding - * PCI address cache will be removed. - */ -void eeh_remove_bus_device(struct pci_dev *dev, int purge_pe) -{ - struct pci_bus *bus = dev->subordinate; - struct pci_dev *child, *tmp; - - eeh_remove_device(dev, purge_pe); - - if (bus && dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) { - list_for_each_entry_safe(child, tmp, &bus->devices, bus_list) - eeh_remove_bus_device(child, purge_pe); - } -} -EXPORT_SYMBOL_GPL(eeh_remove_bus_device); - -static int proc_eeh_show(struct seq_file *m, void *v) -{ - if (0 == eeh_subsystem_enabled) { - seq_printf(m, "EEH Subsystem is globally disabled\n"); - seq_printf(m, "eeh_total_mmio_ffs=%llu\n", eeh_stats.total_mmio_ffs); - } else { - seq_printf(m, "EEH Subsystem is enabled\n"); - seq_printf(m, - "no device=%llu\n" - "no device node=%llu\n" - "no config address=%llu\n" - "check not wanted=%llu\n" - "eeh_total_mmio_ffs=%llu\n" - "eeh_false_positives=%llu\n" - "eeh_slot_resets=%llu\n", - eeh_stats.no_device, - eeh_stats.no_dn, - eeh_stats.no_cfg_addr, - eeh_stats.ignored_check, - eeh_stats.total_mmio_ffs, - eeh_stats.false_positives, - eeh_stats.slot_resets); - } - - return 0; -} - -static int proc_eeh_open(struct inode *inode, struct file *file) -{ - return single_open(file, proc_eeh_show, NULL); -} - -static const struct file_operations proc_eeh_operations = { - .open = proc_eeh_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static int __init eeh_init_proc(void) -{ - if (machine_is(pseries)) - proc_create("powerpc/eeh", 0, NULL, &proc_eeh_operations); - return 0; -} -__initcall(eeh_init_proc); diff --git a/arch/powerpc/platforms/pseries/eeh_cache.c b/arch/powerpc/platforms/pseries/eeh_cache.c deleted file mode 100644 index 5a4c8790305..00000000000 --- a/arch/powerpc/platforms/pseries/eeh_cache.c +++ /dev/null @@ -1,319 +0,0 @@ -/* - * PCI address cache; allows the lookup of PCI devices based on I/O address - * - * Copyright IBM Corporation 2004 - * Copyright Linas Vepstas <linas@austin.ibm.com> 2004 - * - * 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#include <linux/list.h> -#include <linux/pci.h> -#include <linux/rbtree.h> -#include <linux/slab.h> -#include <linux/spinlock.h> -#include <linux/atomic.h> -#include <asm/pci-bridge.h> -#include <asm/ppc-pci.h> - - -/** - * The pci address cache subsystem. This subsystem places - * PCI device address resources into a red-black tree, sorted - * according to the address range, so that given only an i/o - * address, the corresponding PCI device can be **quickly** - * found. It is safe to perform an address lookup in an interrupt - * context; this ability is an important feature. - * - * Currently, the only customer of this code is the EEH subsystem; - * thus, this code has been somewhat tailored to suit EEH better. - * In particular, the cache does *not* hold the addresses of devices - * for which EEH is not enabled. - * - * (Implementation Note: The RB tree seems to be better/faster - * than any hash algo I could think of for this problem, even - * with the penalty of slow pointer chases for d-cache misses). - */ -struct pci_io_addr_range { - struct rb_node rb_node; - unsigned long addr_lo; - unsigned long addr_hi; - struct eeh_dev *edev; - struct pci_dev *pcidev; - unsigned int flags; -}; - -static struct pci_io_addr_cache { - struct rb_root rb_root; - spinlock_t piar_lock; -} pci_io_addr_cache_root; - -static inline struct eeh_dev *__eeh_addr_cache_get_device(unsigned long addr) -{ - struct rb_node *n = pci_io_addr_cache_root.rb_root.rb_node; - - while (n) { - struct pci_io_addr_range *piar; - piar = rb_entry(n, struct pci_io_addr_range, rb_node); - - if (addr < piar->addr_lo) { - n = n->rb_left; - } else { - if (addr > piar->addr_hi) { - n = n->rb_right; - } else { - pci_dev_get(piar->pcidev); - return piar->edev; - } - } - } - - return NULL; -} - -/** - * eeh_addr_cache_get_dev - Get device, given only address - * @addr: mmio (PIO) phys address or i/o port number - * - * Given an mmio phys address, or a port number, find a pci device - * that implements this address. Be sure to pci_dev_put the device - * when finished. I/O port numbers are assumed to be offset - * from zero (that is, they do *not* have pci_io_addr added in). - * It is safe to call this function within an interrupt. - */ -struct eeh_dev *eeh_addr_cache_get_dev(unsigned long addr) -{ - struct eeh_dev *edev; - unsigned long flags; - - spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags); - edev = __eeh_addr_cache_get_device(addr); - spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags); - return edev; -} - -#ifdef DEBUG -/* - * Handy-dandy debug print routine, does nothing more - * than print out the contents of our addr cache. - */ -static void eeh_addr_cache_print(struct pci_io_addr_cache *cache) -{ - struct rb_node *n; - int cnt = 0; - - n = rb_first(&cache->rb_root); - while (n) { - struct pci_io_addr_range *piar; - piar = rb_entry(n, struct pci_io_addr_range, rb_node); - pr_debug("PCI: %s addr range %d [%lx-%lx]: %s\n", - (piar->flags & IORESOURCE_IO) ? "i/o" : "mem", cnt, - piar->addr_lo, piar->addr_hi, pci_name(piar->pcidev)); - cnt++; - n = rb_next(n); - } -} -#endif - -/* Insert address range into the rb tree. */ -static struct pci_io_addr_range * -eeh_addr_cache_insert(struct pci_dev *dev, unsigned long alo, - unsigned long ahi, unsigned int flags) -{ - struct rb_node **p = &pci_io_addr_cache_root.rb_root.rb_node; - struct rb_node *parent = NULL; - struct pci_io_addr_range *piar; - - /* Walk tree, find a place to insert into tree */ - while (*p) { - parent = *p; - piar = rb_entry(parent, struct pci_io_addr_range, rb_node); - if (ahi < piar->addr_lo) { - p = &parent->rb_left; - } else if (alo > piar->addr_hi) { - p = &parent->rb_right; - } else { - if (dev != piar->pcidev || - alo != piar->addr_lo || ahi != piar->addr_hi) { - pr_warning("PIAR: overlapping address range\n"); - } - return piar; - } - } - piar = kzalloc(sizeof(struct pci_io_addr_range), GFP_ATOMIC); - if (!piar) - return NULL; - - pci_dev_get(dev); - piar->addr_lo = alo; - piar->addr_hi = ahi; - piar->edev = pci_dev_to_eeh_dev(dev); - piar->pcidev = dev; - piar->flags = flags; - -#ifdef DEBUG - pr_debug("PIAR: insert range=[%lx:%lx] dev=%s\n", - alo, ahi, pci_name(dev)); -#endif - - rb_link_node(&piar->rb_node, parent, p); - rb_insert_color(&piar->rb_node, &pci_io_addr_cache_root.rb_root); - - return piar; -} - -static void __eeh_addr_cache_insert_dev(struct pci_dev *dev) -{ - struct device_node *dn; - struct eeh_dev *edev; - int i; - - dn = pci_device_to_OF_node(dev); - if (!dn) { - pr_warning("PCI: no pci dn found for dev=%s\n", pci_name(dev)); - return; - } - - edev = of_node_to_eeh_dev(dn); - if (!edev) { - pr_warning("PCI: no EEH dev found for dn=%s\n", - dn->full_name); - return; - } - - /* Skip any devices for which EEH is not enabled. */ - if (!edev->pe) { -#ifdef DEBUG - pr_info("PCI: skip building address cache for=%s - %s\n", - pci_name(dev), dn->full_name); -#endif - return; - } - - /* Walk resources on this device, poke them into the tree */ - for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) { - unsigned long start = pci_resource_start(dev,i); - unsigned long end = pci_resource_end(dev,i); - unsigned int flags = pci_resource_flags(dev,i); - - /* We are interested only bus addresses, not dma or other stuff */ - if (0 == (flags & (IORESOURCE_IO | IORESOURCE_MEM))) - continue; - if (start == 0 || ~start == 0 || end == 0 || ~end == 0) - continue; - eeh_addr_cache_insert(dev, start, end, flags); - } -} - -/** - * eeh_addr_cache_insert_dev - Add a device to the address cache - * @dev: PCI device whose I/O addresses we are interested in. - * - * In order to support the fast lookup of devices based on addresses, - * we maintain a cache of devices that can be quickly searched. - * This routine adds a device to that cache. - */ -void eeh_addr_cache_insert_dev(struct pci_dev *dev) -{ - unsigned long flags; - - /* Ignore PCI bridges */ - if ((dev->class >> 16) == PCI_BASE_CLASS_BRIDGE) - return; - - spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags); - __eeh_addr_cache_insert_dev(dev); - spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags); -} - -static inline void __eeh_addr_cache_rmv_dev(struct pci_dev *dev) -{ - struct rb_node *n; - -restart: - n = rb_first(&pci_io_addr_cache_root.rb_root); - while (n) { - struct pci_io_addr_range *piar; - piar = rb_entry(n, struct pci_io_addr_range, rb_node); - - if (piar->pcidev == dev) { - rb_erase(n, &pci_io_addr_cache_root.rb_root); - pci_dev_put(piar->pcidev); - kfree(piar); - goto restart; - } - n = rb_next(n); - } -} - -/** - * eeh_addr_cache_rmv_dev - remove pci device from addr cache - * @dev: device to remove - * - * Remove a device from the addr-cache tree. - * This is potentially expensive, since it will walk - * the tree multiple times (once per resource). - * But so what; device removal doesn't need to be that fast. - */ -void eeh_addr_cache_rmv_dev(struct pci_dev *dev) -{ - unsigned long flags; - - spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags); - __eeh_addr_cache_rmv_dev(dev); - spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags); -} - -/** - * eeh_addr_cache_build - Build a cache of I/O addresses - * - * Build a cache of pci i/o addresses. This cache will be used to - * find the pci device that corresponds to a given address. - * This routine scans all pci busses to build the cache. - * Must be run late in boot process, after the pci controllers - * have been scanned for devices (after all device resources are known). - */ -void __init eeh_addr_cache_build(void) -{ - struct device_node *dn; - struct eeh_dev *edev; - struct pci_dev *dev = NULL; - - spin_lock_init(&pci_io_addr_cache_root.piar_lock); - - for_each_pci_dev(dev) { - eeh_addr_cache_insert_dev(dev); - - dn = pci_device_to_OF_node(dev); - if (!dn) - continue; - - edev = of_node_to_eeh_dev(dn); - if (!edev) - continue; - - pci_dev_get(dev); /* matching put is in eeh_remove_device() */ - dev->dev.archdata.edev = edev; - edev->pdev = dev; - - eeh_sysfs_add_device(dev); - } - -#ifdef DEBUG - /* Verify tree built up above, echo back the list of addrs. */ - eeh_addr_cache_print(&pci_io_addr_cache_root); -#endif -} - diff --git a/arch/powerpc/platforms/pseries/eeh_dev.c b/arch/powerpc/platforms/pseries/eeh_dev.c deleted file mode 100644 index 1efa28f5fc5..00000000000 --- a/arch/powerpc/platforms/pseries/eeh_dev.c +++ /dev/null @@ -1,112 +0,0 @@ -/* - * The file intends to implement dynamic creation of EEH device, which will - * be bound with OF node and PCI device simutaneously. The EEH devices would - * be foundamental information for EEH core components to work proerly. Besides, - * We have to support multiple situations where dynamic creation of EEH device - * is required: - * - * 1) Before PCI emunation starts, we need create EEH devices according to the - * PCI sensitive OF nodes. - * 2) When PCI emunation is done, we need do the binding between PCI device and - * the associated EEH device. - * 3) DR (Dynamic Reconfiguration) would create PCI sensitive OF node. EEH device - * will be created while PCI sensitive OF node is detected from DR. - * 4) PCI hotplug needs redoing the binding between PCI device and EEH device. If - * PHB is newly inserted, we also need create EEH devices accordingly. - * - * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2012. - * - * 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#include <linux/export.h> -#include <linux/gfp.h> -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/pci.h> -#include <linux/string.h> - -#include <asm/pci-bridge.h> -#include <asm/ppc-pci.h> - -/** - * eeh_dev_init - Create EEH device according to OF node - * @dn: device node - * @data: PHB - * - * It will create EEH device according to the given OF node. The function - * might be called by PCI emunation, DR, PHB hotplug. - */ -void *eeh_dev_init(struct device_node *dn, void *data) -{ - struct pci_controller *phb = data; - struct eeh_dev *edev; - - /* Allocate EEH device */ - edev = kzalloc(sizeof(*edev), GFP_KERNEL); - if (!edev) { - pr_warning("%s: out of memory\n", __func__); - return NULL; - } - - /* Associate EEH device with OF node */ - PCI_DN(dn)->edev = edev; - edev->dn = dn; - edev->phb = phb; - INIT_LIST_HEAD(&edev->list); - - return NULL; -} - -/** - * eeh_dev_phb_init_dynamic - Create EEH devices for devices included in PHB - * @phb: PHB - * - * Scan the PHB OF node and its child association, then create the - * EEH devices accordingly - */ -void eeh_dev_phb_init_dynamic(struct pci_controller *phb) -{ - struct device_node *dn = phb->dn; - - /* EEH PE for PHB */ - eeh_phb_pe_create(phb); - - /* EEH device for PHB */ - eeh_dev_init(dn, phb); - - /* EEH devices for children OF nodes */ - traverse_pci_devices(dn, eeh_dev_init, phb); -} - -/** - * eeh_dev_phb_init - Create EEH devices for devices included in existing PHBs - * - * Scan all the existing PHBs and create EEH devices for their OF - * nodes and their children OF nodes - */ -static int __init eeh_dev_phb_init(void) -{ - struct pci_controller *phb, *tmp; - - list_for_each_entry_safe(phb, tmp, &hose_list, list_node) - eeh_dev_phb_init_dynamic(phb); - - pr_info("EEH: devices created\n"); - - return 0; -} - -core_initcall(eeh_dev_phb_init); diff --git a/arch/powerpc/platforms/pseries/eeh_driver.c b/arch/powerpc/platforms/pseries/eeh_driver.c deleted file mode 100644 index a3fefb61097..00000000000 --- a/arch/powerpc/platforms/pseries/eeh_driver.c +++ /dev/null @@ -1,552 +0,0 @@ -/* - * PCI Error Recovery Driver for RPA-compliant PPC64 platform. - * Copyright IBM Corp. 2004 2005 - * Copyright Linas Vepstas <linas@linas.org> 2004, 2005 - * - * All rights reserved. - * - * 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, GOOD TITLE or - * NON INFRINGEMENT. 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., 675 Mass Ave, Cambridge, MA 02139, USA. - * - * Send comments and feedback to Linas Vepstas <linas@austin.ibm.com> - */ -#include <linux/delay.h> -#include <linux/interrupt.h> -#include <linux/irq.h> -#include <linux/module.h> -#include <linux/pci.h> -#include <asm/eeh.h> -#include <asm/eeh_event.h> -#include <asm/ppc-pci.h> -#include <asm/pci-bridge.h> -#include <asm/prom.h> -#include <asm/rtas.h> - -/** - * eeh_pcid_name - Retrieve name of PCI device driver - * @pdev: PCI device - * - * This routine is used to retrieve the name of PCI device driver - * if that's valid. - */ -static inline const char *eeh_pcid_name(struct pci_dev *pdev) -{ - if (pdev && pdev->dev.driver) - return pdev->dev.driver->name; - return ""; -} - -/** - * eeh_pcid_get - Get the PCI device driver - * @pdev: PCI device - * - * The function is used to retrieve the PCI device driver for - * the indicated PCI device. Besides, we will increase the reference - * of the PCI device driver to prevent that being unloaded on - * the fly. Otherwise, kernel crash would be seen. - */ -static inline struct pci_driver *eeh_pcid_get(struct pci_dev *pdev) -{ - if (!pdev || !pdev->driver) - return NULL; - - if (!try_module_get(pdev->driver->driver.owner)) - return NULL; - - return pdev->driver; -} - -/** - * eeh_pcid_put - Dereference on the PCI device driver - * @pdev: PCI device - * - * The function is called to do dereference on the PCI device - * driver of the indicated PCI device. - */ -static inline void eeh_pcid_put(struct pci_dev *pdev) -{ - if (!pdev || !pdev->driver) - return; - - module_put(pdev->driver->driver.owner); -} - -#if 0 -static void print_device_node_tree(struct pci_dn *pdn, int dent) -{ - int i; - struct device_node *pc; - - if (!pdn) - return; - for (i = 0; i < dent; i++) - printk(" "); - printk("dn=%s mode=%x \tcfg_addr=%x pe_addr=%x \tfull=%s\n", - pdn->node->name, pdn->eeh_mode, pdn->eeh_config_addr, - pdn->eeh_pe_config_addr, pdn->node->full_name); - dent += 3; - pc = pdn->node->child; - while (pc) { - print_device_node_tree(PCI_DN(pc), dent); - pc = pc->sibling; - } -} -#endif - -/** - * eeh_disable_irq - Disable interrupt for the recovering device - * @dev: PCI device - * - * This routine must be called when reporting temporary or permanent - * error to the particular PCI device to disable interrupt of that - * device. If the device has enabled MSI or MSI-X interrupt, we needn't - * do real work because EEH should freeze DMA transfers for those PCI - * devices encountering EEH errors, which includes MSI or MSI-X. - */ -static void eeh_disable_irq(struct pci_dev *dev) -{ - struct eeh_dev *edev = pci_dev_to_eeh_dev(dev); - - /* Don't disable MSI and MSI-X interrupts. They are - * effectively disabled by the DMA Stopped state - * when an EEH error occurs. - */ - if (dev->msi_enabled || dev->msix_enabled) - return; - - if (!irq_has_action(dev->irq)) - return; - - edev->mode |= EEH_DEV_IRQ_DISABLED; - disable_irq_nosync(dev->irq); -} - -/** - * eeh_enable_irq - Enable interrupt for the recovering device - * @dev: PCI device - * - * This routine must be called to enable interrupt while failed - * device could be resumed. - */ -static void eeh_enable_irq(struct pci_dev *dev) -{ - struct eeh_dev *edev = pci_dev_to_eeh_dev(dev); - - if ((edev->mode) & EEH_DEV_IRQ_DISABLED) { - edev->mode &= ~EEH_DEV_IRQ_DISABLED; - enable_irq(dev->irq); - } -} - -/** - * eeh_report_error - Report pci error to each device driver - * @data: eeh device - * @userdata: return value - * - * Report an EEH error to each device driver, collect up and - * merge the device driver responses. Cumulative response - * passed back in "userdata". - */ -static void *eeh_report_error(void *data, void *userdata) -{ - struct eeh_dev *edev = (struct eeh_dev *)data; - struct pci_dev *dev = eeh_dev_to_pci_dev(edev); - enum pci_ers_result rc, *res = userdata; - struct pci_driver *driver; - - /* We might not have the associated PCI device, - * then we should continue for next one. - */ - if (!dev) return NULL; - dev->error_state = pci_channel_io_frozen; - - driver = eeh_pcid_get(dev); - if (!driver) return NULL; - - eeh_disable_irq(dev); - - if (!driver->err_handler || - !driver->err_handler->error_detected) { - eeh_pcid_put(dev); - return NULL; - } - - rc = driver->err_handler->error_detected(dev, pci_channel_io_frozen); - - /* A driver that needs a reset trumps all others */ - if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc; - if (*res == PCI_ERS_RESULT_NONE) *res = rc; - - eeh_pcid_put(dev); - return NULL; -} - -/** - * eeh_report_mmio_enabled - Tell drivers that MMIO has been enabled - * @data: eeh device - * @userdata: return value - * - * Tells each device driver that IO ports, MMIO and config space I/O - * are now enabled. Collects up and merges the device driver responses. - * Cumulative response passed back in "userdata". - */ -static void *eeh_report_mmio_enabled(void *data, void *userdata) -{ - struct eeh_dev *edev = (struct eeh_dev *)data; - struct pci_dev *dev = eeh_dev_to_pci_dev(edev); - enum pci_ers_result rc, *res = userdata; - struct pci_driver *driver; - - driver = eeh_pcid_get(dev); - if (!driver) return NULL; - - if (!driver->err_handler || - !driver->err_handler->mmio_enabled) { - eeh_pcid_put(dev); - return NULL; - } - - rc = driver->err_handler->mmio_enabled(dev); - - /* A driver that needs a reset trumps all others */ - if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc; - if (*res == PCI_ERS_RESULT_NONE) *res = rc; - - eeh_pcid_put(dev); - return NULL; -} - -/** - * eeh_report_reset - Tell device that slot has been reset - * @data: eeh device - * @userdata: return value - * - * This routine must be called while EEH tries to reset particular - * PCI device so that the associated PCI device driver could take - * some actions, usually to save data the driver needs so that the - * driver can work again while the device is recovered. - */ -static void *eeh_report_reset(void *data, void *userdata) -{ - struct eeh_dev *edev = (struct eeh_dev *)data; - struct pci_dev *dev = eeh_dev_to_pci_dev(edev); - enum pci_ers_result rc, *res = userdata; - struct pci_driver *driver; - - if (!dev) return NULL; - dev->error_state = pci_channel_io_normal; - - driver = eeh_pcid_get(dev); - if (!driver) return NULL; - - eeh_enable_irq(dev); - - if (!driver->err_handler || - !driver->err_handler->slot_reset) { - eeh_pcid_put(dev); - return NULL; - } - - rc = driver->err_handler->slot_reset(dev); - if ((*res == PCI_ERS_RESULT_NONE) || - (*res == PCI_ERS_RESULT_RECOVERED)) *res = rc; - if (*res == PCI_ERS_RESULT_DISCONNECT && - rc == PCI_ERS_RESULT_NEED_RESET) *res = rc; - - eeh_pcid_put(dev); - return NULL; -} - -/** - * eeh_report_resume - Tell device to resume normal operations - * @data: eeh device - * @userdata: return value - * - * This routine must be called to notify the device driver that it - * could resume so that the device driver can do some initialization - * to make the recovered device work again. - */ -static void *eeh_report_resume(void *data, void *userdata) -{ - struct eeh_dev *edev = (struct eeh_dev *)data; - struct pci_dev *dev = eeh_dev_to_pci_dev(edev); - struct pci_driver *driver; - - if (!dev) return NULL; - dev->error_state = pci_channel_io_normal; - - driver = eeh_pcid_get(dev); - if (!driver) return NULL; - - eeh_enable_irq(dev); - - if (!driver->err_handler || - !driver->err_handler->resume) { - eeh_pcid_put(dev); - return NULL; - } - - driver->err_handler->resume(dev); - - eeh_pcid_put(dev); - return NULL; -} - -/** - * eeh_report_failure - Tell device driver that device is dead. - * @data: eeh device - * @userdata: return value - * - * This informs the device driver that the device is permanently - * dead, and that no further recovery attempts will be made on it. - */ -static void *eeh_report_failure(void *data, void *userdata) -{ - struct eeh_dev *edev = (struct eeh_dev *)data; - struct pci_dev *dev = eeh_dev_to_pci_dev(edev); - struct pci_driver *driver; - - if (!dev) return NULL; - dev->error_state = pci_channel_io_perm_failure; - - driver = eeh_pcid_get(dev); - if (!driver) return NULL; - - eeh_disable_irq(dev); - - if (!driver->err_handler || - !driver->err_handler->error_detected) { - eeh_pcid_put(dev); - return NULL; - } - - driver->err_handler->error_detected(dev, pci_channel_io_perm_failure); - - eeh_pcid_put(dev); - return NULL; -} - -/** - * eeh_reset_device - Perform actual reset of a pci slot - * @pe: EEH PE - * @bus: PCI bus corresponding to the isolcated slot - * - * This routine must be called to do reset on the indicated PE. - * During the reset, udev might be invoked because those affected - * PCI devices will be removed and then added. - */ -static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) -{ - int cnt, rc; - - /* pcibios will clear the counter; save the value */ - cnt = pe->freeze_count; - - /* - * We don't remove the corresponding PE instances because - * we need the information afterwords. The attached EEH - * devices are expected to be attached soon when calling - * into pcibios_add_pci_devices(). - */ - if (bus) - __pcibios_remove_pci_devices(bus, 0); - - /* Reset the pci controller. (Asserts RST#; resets config space). - * Reconfigure bridges and devices. Don't try to bring the system - * up if the reset failed for some reason. - */ - rc = eeh_reset_pe(pe); - if (rc) - return rc; - - /* Restore PE */ - eeh_ops->configure_bridge(pe); - eeh_pe_restore_bars(pe); - - /* Give the system 5 seconds to finish running the user-space - * hotplug shutdown scripts, e.g. ifdown for ethernet. Yes, - * this is a hack, but if we don't do this, and try to bring - * the device up before the scripts have taken it down, - * potentially weird things happen. - */ - if (bus) { - ssleep(5); - pcibios_add_pci_devices(bus); - } - pe->freeze_count = cnt; - - return 0; -} - -/* The longest amount of time to wait for a pci device - * to come back on line, in seconds. - */ -#define MAX_WAIT_FOR_RECOVERY 150 - -/** - * eeh_handle_event - Reset a PCI device after hard lockup. - * @pe: EEH PE - * - * While PHB detects address or data parity errors on particular PCI - * slot, the associated PE will be frozen. Besides, DMA's occurring - * to wild addresses (which usually happen due to bugs in device - * drivers or in PCI adapter firmware) can cause EEH error. #SERR, - * #PERR or other misc PCI-related errors also can trigger EEH errors. - * - * Recovery process consists of unplugging the device driver (which - * generated hotplug events to userspace), then issuing a PCI #RST to - * the device, then reconfiguring the PCI config space for all bridges - * & devices under this slot, and then finally restarting the device - * drivers (which cause a second set of hotplug events to go out to - * userspace). - */ -void eeh_handle_event(struct eeh_pe *pe) -{ - struct pci_bus *frozen_bus; - int rc = 0; - enum pci_ers_result result = PCI_ERS_RESULT_NONE; - - frozen_bus = eeh_pe_bus_get(pe); - if (!frozen_bus) { - pr_err("%s: Cannot find PCI bus for PHB#%d-PE#%x\n", - __func__, pe->phb->global_number, pe->addr); - return; - } - - pe->freeze_count++; - if (pe->freeze_count > EEH_MAX_ALLOWED_FREEZES) - goto excess_failures; - pr_warning("EEH: This PCI device has failed %d times in the last hour\n", - pe->freeze_count); - - /* Walk the various device drivers attached to this slot through - * a reset sequence, giving each an opportunity to do what it needs - * to accomplish the reset. Each child gets a report of the - * status ... if any child can't handle the reset, then the entire - * slot is dlpar removed and added. - */ - eeh_pe_dev_traverse(pe, eeh_report_error, &result); - - /* Get the current PCI slot state. This can take a long time, - * sometimes over 3 seconds for certain systems. - */ - rc = eeh_ops->wait_state(pe, MAX_WAIT_FOR_RECOVERY*1000); - if (rc < 0 || rc == EEH_STATE_NOT_SUPPORT) { - printk(KERN_WARNING "EEH: Permanent failure\n"); - goto hard_fail; - } - - /* Since rtas may enable MMIO when posting the error log, - * don't post the error log until after all dev drivers - * have been informed. - */ - eeh_slot_error_detail(pe, EEH_LOG_TEMP); - - /* If all device drivers were EEH-unaware, then shut - * down all of the device drivers, and hope they - * go down willingly, without panicing the system. - */ - if (result == PCI_ERS_RESULT_NONE) { - rc = eeh_reset_device(pe, frozen_bus); - if (rc) { - printk(KERN_WARNING "EEH: Unable to reset, rc=%d\n", rc); - goto hard_fail; - } - } - - /* If all devices reported they can proceed, then re-enable MMIO */ - if (result == PCI_ERS_RESULT_CAN_RECOVER) { - rc = eeh_pci_enable(pe, EEH_OPT_THAW_MMIO); - - if (rc < 0) - goto hard_fail; - if (rc) { - result = PCI_ERS_RESULT_NEED_RESET; - } else { - result = PCI_ERS_RESULT_NONE; - eeh_pe_dev_traverse(pe, eeh_report_mmio_enabled, &result); - } - } - - /* If all devices reported they can proceed, then re-enable DMA */ - if (result == PCI_ERS_RESULT_CAN_RECOVER) { - rc = eeh_pci_enable(pe, EEH_OPT_THAW_DMA); - - if (rc < 0) - goto hard_fail; - if (rc) - result = PCI_ERS_RESULT_NEED_RESET; - else - result = PCI_ERS_RESULT_RECOVERED; - } - - /* If any device has a hard failure, then shut off everything. */ - if (result == PCI_ERS_RESULT_DISCONNECT) { - printk(KERN_WARNING "EEH: Device driver gave up\n"); - goto hard_fail; - } - - /* If any device called out for a reset, then reset the slot */ - if (result == PCI_ERS_RESULT_NEED_RESET) { - rc = eeh_reset_device(pe, NULL); - if (rc) { - printk(KERN_WARNING "EEH: Cannot reset, rc=%d\n", rc); - goto hard_fail; - } - result = PCI_ERS_RESULT_NONE; - eeh_pe_dev_traverse(pe, eeh_report_reset, &result); - } - - /* All devices should claim they have recovered by now. */ - if ((result != PCI_ERS_RESULT_RECOVERED) && - (result != PCI_ERS_RESULT_NONE)) { - printk(KERN_WARNING "EEH: Not recovered\n"); - goto hard_fail; - } - - /* Tell all device drivers that they can resume operations */ - eeh_pe_dev_traverse(pe, eeh_report_resume, NULL); - - return; - -excess_failures: - /* - * About 90% of all real-life EEH failures in the field - * are due to poorly seated PCI cards. Only 10% or so are - * due to actual, failed cards. - */ - pr_err("EEH: PHB#%d-PE#%x has failed %d times in the\n" - "last hour and has been permanently disabled.\n" - "Please try reseating or replacing it.\n", - pe->phb->global_number, pe->addr, - pe->freeze_count); - goto perm_error; - -hard_fail: - pr_err("EEH: Unable to recover from failure from PHB#%d-PE#%x.\n" - "Please try reseating or replacing it\n", - pe->phb->global_number, pe->addr); - -perm_error: - eeh_slot_error_detail(pe, EEH_LOG_PERM); - - /* Notify all devices that they're about to go down. */ - eeh_pe_dev_traverse(pe, eeh_report_failure, NULL); - - /* Shut down the device drivers for good. */ - if (frozen_bus) - pcibios_remove_pci_devices(frozen_bus); -} - diff --git a/arch/powerpc/platforms/pseries/eeh_event.c b/arch/powerpc/platforms/pseries/eeh_event.c deleted file mode 100644 index 185bedd926d..00000000000 --- a/arch/powerpc/platforms/pseries/eeh_event.c +++ /dev/null @@ -1,142 +0,0 @@ -/* - * 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * - * Copyright (c) 2005 Linas Vepstas <linas@linas.org> - */ - -#include <linux/delay.h> -#include <linux/list.h> -#include <linux/mutex.h> -#include <linux/sched.h> -#include <linux/pci.h> -#include <linux/slab.h> -#include <linux/workqueue.h> -#include <linux/kthread.h> -#include <asm/eeh_event.h> -#include <asm/ppc-pci.h> - -/** Overview: - * EEH error states may be detected within exception handlers; - * however, the recovery processing needs to occur asynchronously - * in a normal kernel context and not an interrupt context. - * This pair of routines creates an event and queues it onto a - * work-queue, where a worker thread can drive recovery. - */ - -/* EEH event workqueue setup. */ -static DEFINE_SPINLOCK(eeh_eventlist_lock); -LIST_HEAD(eeh_eventlist); -static void eeh_thread_launcher(struct work_struct *); -DECLARE_WORK(eeh_event_wq, eeh_thread_launcher); - -/* Serialize reset sequences for a given pci device */ -DEFINE_MUTEX(eeh_event_mutex); - -/** - * eeh_event_handler - Dispatch EEH events. - * @dummy - unused - * - * The detection of a frozen slot can occur inside an interrupt, - * where it can be hard to do anything about it. The goal of this - * routine is to pull these detection events out of the context - * of the interrupt handler, and re-dispatch them for processing - * at a later time in a normal context. - */ -static int eeh_event_handler(void * dummy) -{ - unsigned long flags; - struct eeh_event *event; - struct eeh_pe *pe; - - spin_lock_irqsave(&eeh_eventlist_lock, flags); - event = NULL; - - /* Unqueue the event, get ready to process. */ - if (!list_empty(&eeh_eventlist)) { - event = list_entry(eeh_eventlist.next, struct eeh_event, list); - list_del(&event->list); - } - spin_unlock_irqrestore(&eeh_eventlist_lock, flags); - - if (event == NULL) - return 0; - - /* Serialize processing of EEH events */ - mutex_lock(&eeh_event_mutex); - pe = event->pe; - eeh_pe_state_mark(pe, EEH_PE_RECOVERING); - pr_info("EEH: Detected PCI bus error on PHB#%d-PE#%x\n", - pe->phb->global_number, pe->addr); - - set_current_state(TASK_INTERRUPTIBLE); /* Don't add to load average */ - eeh_handle_event(pe); - eeh_pe_state_clear(pe, EEH_PE_RECOVERING); - - kfree(event); - mutex_unlock(&eeh_event_mutex); - - /* If there are no new errors after an hour, clear the counter. */ - if (pe && pe->freeze_count > 0) { - msleep_interruptible(3600*1000); - if (pe->freeze_count > 0) - pe->freeze_count--; - - } - - return 0; -} - -/** - * eeh_thread_launcher - Start kernel thread to handle EEH events - * @dummy - unused - * - * This routine is called to start the kernel thread for processing - * EEH event. - */ -static void eeh_thread_launcher(struct work_struct *dummy) -{ - if (IS_ERR(kthread_run(eeh_event_handler, NULL, "eehd"))) - printk(KERN_ERR "Failed to start EEH daemon\n"); -} - -/** - * eeh_send_failure_event - Generate a PCI error event - * @pe: EEH PE - * - * This routine can be called within an interrupt context; - * the actual event will be delivered in a normal context - * (from a workqueue). - */ -int eeh_send_failure_event(struct eeh_pe *pe) -{ - unsigned long flags; - struct eeh_event *event; - - event = kzalloc(sizeof(*event), GFP_ATOMIC); - if (!event) { - pr_err("EEH: out of memory, event not handled\n"); - return -ENOMEM; - } - event->pe = pe; - - /* We may or may not be called in an interrupt context */ - spin_lock_irqsave(&eeh_eventlist_lock, flags); - list_add(&event->list, &eeh_eventlist); - spin_unlock_irqrestore(&eeh_eventlist_lock, flags); - - schedule_work(&eeh_event_wq); - - return 0; -} diff --git a/arch/powerpc/platforms/pseries/eeh_pe.c b/arch/powerpc/platforms/pseries/eeh_pe.c deleted file mode 100644 index fe43d1aa2cf..00000000000 --- a/arch/powerpc/platforms/pseries/eeh_pe.c +++ /dev/null @@ -1,652 +0,0 @@ -/* - * The file intends to implement PE based on the information from - * platforms. Basically, there have 3 types of PEs: PHB/Bus/Device. - * All the PEs should be organized as hierarchy tree. The first level - * of the tree will be associated to existing PHBs since the particular - * PE is only meaningful in one PHB domain. - * - * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2012. - * - * 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#include <linux/export.h> -#include <linux/gfp.h> -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/pci.h> -#include <linux/string.h> - -#include <asm/pci-bridge.h> -#include <asm/ppc-pci.h> - -static LIST_HEAD(eeh_phb_pe); - -/** - * eeh_pe_alloc - Allocate PE - * @phb: PCI controller - * @type: PE type - * - * Allocate PE instance dynamically. - */ -static struct eeh_pe *eeh_pe_alloc(struct pci_controller *phb, int type) -{ - struct eeh_pe *pe; - - /* Allocate PHB PE */ - pe = kzalloc(sizeof(struct eeh_pe), GFP_KERNEL); - if (!pe) return NULL; - - /* Initialize PHB PE */ - pe->type = type; - pe->phb = phb; - INIT_LIST_HEAD(&pe->child_list); - INIT_LIST_HEAD(&pe->child); - INIT_LIST_HEAD(&pe->edevs); - - return pe; -} - -/** - * eeh_phb_pe_create - Create PHB PE - * @phb: PCI controller - * - * The function should be called while the PHB is detected during - * system boot or PCI hotplug in order to create PHB PE. - */ -int eeh_phb_pe_create(struct pci_controller *phb) -{ - struct eeh_pe *pe; - - /* Allocate PHB PE */ - pe = eeh_pe_alloc(phb, EEH_PE_PHB); - if (!pe) { - pr_err("%s: out of memory!\n", __func__); - return -ENOMEM; - } - - /* Put it into the list */ - eeh_lock(); - list_add_tail(&pe->child, &eeh_phb_pe); - eeh_unlock(); - - pr_debug("EEH: Add PE for PHB#%d\n", phb->global_number); - - return 0; -} - -/** - * eeh_phb_pe_get - Retrieve PHB PE based on the given PHB - * @phb: PCI controller - * - * The overall PEs form hierarchy tree. The first layer of the - * hierarchy tree is composed of PHB PEs. The function is used - * to retrieve the corresponding PHB PE according to the given PHB. - */ -static struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb) -{ - struct eeh_pe *pe; - - list_for_each_entry(pe, &eeh_phb_pe, child) { - /* - * Actually, we needn't check the type since - * the PE for PHB has been determined when that - * was created. - */ - if ((pe->type & EEH_PE_PHB) && pe->phb == phb) - return pe; - } - - return NULL; -} - -/** - * eeh_pe_next - Retrieve the next PE in the tree - * @pe: current PE - * @root: root PE - * - * The function is used to retrieve the next PE in the - * hierarchy PE tree. - */ -static struct eeh_pe *eeh_pe_next(struct eeh_pe *pe, - struct eeh_pe *root) -{ - struct list_head *next = pe->child_list.next; - - if (next == &pe->child_list) { - while (1) { - if (pe == root) - return NULL; - next = pe->child.next; - if (next != &pe->parent->child_list) - break; - pe = pe->parent; - } - } - - return list_entry(next, struct eeh_pe, child); -} - -/** - * eeh_pe_traverse - Traverse PEs in the specified PHB - * @root: root PE - * @fn: callback - * @flag: extra parameter to callback - * - * The function is used to traverse the specified PE and its - * child PEs. The traversing is to be terminated once the - * callback returns something other than NULL, or no more PEs - * to be traversed. - */ -static void *eeh_pe_traverse(struct eeh_pe *root, - eeh_traverse_func fn, void *flag) -{ - struct eeh_pe *pe; - void *ret; - - for (pe = root; pe; pe = eeh_pe_next(pe, root)) { - ret = fn(pe, flag); - if (ret) return ret; - } - - return NULL; -} - -/** - * eeh_pe_dev_traverse - Traverse the devices from the PE - * @root: EEH PE - * @fn: function callback - * @flag: extra parameter to callback - * - * The function is used to traverse the devices of the specified - * PE and its child PEs. - */ -void *eeh_pe_dev_traverse(struct eeh_pe *root, - eeh_traverse_func fn, void *flag) -{ - struct eeh_pe *pe; - struct eeh_dev *edev; - void *ret; - - if (!root) { - pr_warning("%s: Invalid PE %p\n", __func__, root); - return NULL; - } - - eeh_lock(); - - /* Traverse root PE */ - for (pe = root; pe; pe = eeh_pe_next(pe, root)) { - eeh_pe_for_each_dev(pe, edev) { - ret = fn(edev, flag); - if (ret) { - eeh_unlock(); - return ret; - } - } - } - - eeh_unlock(); - - return NULL; -} - -/** - * __eeh_pe_get - Check the PE address - * @data: EEH PE - * @flag: EEH device - * - * For one particular PE, it can be identified by PE address - * or tranditional BDF address. BDF address is composed of - * Bus/Device/Function number. The extra data referred by flag - * indicates which type of address should be used. - */ -static void *__eeh_pe_get(void *data, void *flag) -{ - struct eeh_pe *pe = (struct eeh_pe *)data; - struct eeh_dev *edev = (struct eeh_dev *)flag; - - /* Unexpected PHB PE */ - if (pe->type & EEH_PE_PHB) - return NULL; - - /* We prefer PE address */ - if (edev->pe_config_addr && - (edev->pe_config_addr == pe->addr)) - return pe; - - /* Try BDF address */ - if (edev->pe_config_addr && - (edev->config_addr == pe->config_addr)) - return pe; - - return NULL; -} - -/** - * eeh_pe_get - Search PE based on the given address - * @edev: EEH device - * - * Search the corresponding PE based on the specified address which - * is included in the eeh device. The function is used to check if - * the associated PE has been created against the PE address. It's - * notable that the PE address has 2 format: traditional PE address - * which is composed of PCI bus/device/function number, or unified - * PE address. - */ -static struct eeh_pe *eeh_pe_get(struct eeh_dev *edev) -{ - struct eeh_pe *root = eeh_phb_pe_get(edev->phb); - struct eeh_pe *pe; - - pe = eeh_pe_traverse(root, __eeh_pe_get, edev); - - return pe; -} - -/** - * eeh_pe_get_parent - Retrieve the parent PE - * @edev: EEH device - * - * The whole PEs existing in the system are organized as hierarchy - * tree. The function is used to retrieve the parent PE according - * to the parent EEH device. - */ -static struct eeh_pe *eeh_pe_get_parent(struct eeh_dev *edev) -{ - struct device_node *dn; - struct eeh_dev *parent; - - /* - * It might have the case for the indirect parent - * EEH device already having associated PE, but - * the direct parent EEH device doesn't have yet. - */ - dn = edev->dn->parent; - while (dn) { - /* We're poking out of PCI territory */ - if (!PCI_DN(dn)) return NULL; - - parent = of_node_to_eeh_dev(dn); - /* We're poking out of PCI territory */ - if (!parent) return NULL; - - if (parent->pe) - return parent->pe; - - dn = dn->parent; - } - - return NULL; -} - -/** - * eeh_add_to_parent_pe - Add EEH device to parent PE - * @edev: EEH device - * - * Add EEH device to the parent PE. If the parent PE already - * exists, the PE type will be changed to EEH_PE_BUS. Otherwise, - * we have to create new PE to hold the EEH device and the new - * PE will be linked to its parent PE as well. - */ -int eeh_add_to_parent_pe(struct eeh_dev *edev) -{ - struct eeh_pe *pe, *parent; - - eeh_lock(); - - /* - * Search the PE has been existing or not according - * to the PE address. If that has been existing, the - * PE should be composed of PCI bus and its subordinate - * components. - */ - pe = eeh_pe_get(edev); - if (pe && !(pe->type & EEH_PE_INVALID)) { - if (!edev->pe_config_addr) { - eeh_unlock(); - pr_err("%s: PE with addr 0x%x already exists\n", - __func__, edev->config_addr); - return -EEXIST; - } - - /* Mark the PE as type of PCI bus */ - pe->type = EEH_PE_BUS; - edev->pe = pe; - - /* Put the edev to PE */ - list_add_tail(&edev->list, &pe->edevs); - eeh_unlock(); - pr_debug("EEH: Add %s to Bus PE#%x\n", - edev->dn->full_name, pe->addr); - - return 0; - } else if (pe && (pe->type & EEH_PE_INVALID)) { - list_add_tail(&edev->list, &pe->edevs); - edev->pe = pe; - /* - * We're running to here because of PCI hotplug caused by - * EEH recovery. We need clear EEH_PE_INVALID until the top. - */ - parent = pe; - while (parent) { - if (!(parent->type & EEH_PE_INVALID)) - break; - parent->type &= ~EEH_PE_INVALID; - parent = parent->parent; - } - eeh_unlock(); - pr_debug("EEH: Add %s to Device PE#%x, Parent PE#%x\n", - edev->dn->full_name, pe->addr, pe->parent->addr); - - return 0; - } - - /* Create a new EEH PE */ - pe = eeh_pe_alloc(edev->phb, EEH_PE_DEVICE); - if (!pe) { - eeh_unlock(); - pr_err("%s: out of memory!\n", __func__); - return -ENOMEM; - } - pe->addr = edev->pe_config_addr; - pe->config_addr = edev->config_addr; - - /* - * Put the new EEH PE into hierarchy tree. If the parent - * can't be found, the newly created PE will be attached - * to PHB directly. Otherwise, we have to associate the - * PE with its parent. - */ - parent = eeh_pe_get_parent(edev); - if (!parent) { - parent = eeh_phb_pe_get(edev->phb); - if (!parent) { - eeh_unlock(); - pr_err("%s: No PHB PE is found (PHB Domain=%d)\n", - __func__, edev->phb->global_number); - edev->pe = NULL; - kfree(pe); - return -EEXIST; - } - } - pe->parent = parent; - - /* - * Put the newly created PE into the child list and - * link the EEH device accordingly. - */ - list_add_tail(&pe->child, &parent->child_list); - list_add_tail(&edev->list, &pe->edevs); - edev->pe = pe; - eeh_unlock(); - pr_debug("EEH: Add %s to Device PE#%x, Parent PE#%x\n", - edev->dn->full_name, pe->addr, pe->parent->addr); - - return 0; -} - -/** - * eeh_rmv_from_parent_pe - Remove one EEH device from the associated PE - * @edev: EEH device - * @purge_pe: remove PE or not - * - * The PE hierarchy tree might be changed when doing PCI hotplug. - * Also, the PCI devices or buses could be removed from the system - * during EEH recovery. So we have to call the function remove the - * corresponding PE accordingly if necessary. - */ -int eeh_rmv_from_parent_pe(struct eeh_dev *edev, int purge_pe) -{ - struct eeh_pe *pe, *parent, *child; - int cnt; - - if (!edev->pe) { - pr_warning("%s: No PE found for EEH device %s\n", - __func__, edev->dn->full_name); - return -EEXIST; - } - - eeh_lock(); - - /* Remove the EEH device */ - pe = edev->pe; - edev->pe = NULL; - list_del(&edev->list); - - /* - * Check if the parent PE includes any EEH devices. - * If not, we should delete that. Also, we should - * delete the parent PE if it doesn't have associated - * child PEs and EEH devices. - */ - while (1) { - parent = pe->parent; - if (pe->type & EEH_PE_PHB) - break; - - if (purge_pe) { - if (list_empty(&pe->edevs) && - list_empty(&pe->child_list)) { - list_del(&pe->child); - kfree(pe); - } else { - break; - } - } else { - if (list_empty(&pe->edevs)) { - cnt = 0; - list_for_each_entry(child, &pe->child_list, child) { - if (!(child->type & EEH_PE_INVALID)) { - cnt++; - break; - } - } - - if (!cnt) - pe->type |= EEH_PE_INVALID; - else - break; - } - } - - pe = parent; - } - - eeh_unlock(); - - return 0; -} - -/** - * __eeh_pe_state_mark - Mark the state for the PE - * @data: EEH PE - * @flag: state - * - * The function is used to mark the indicated state for the given - * PE. Also, the associated PCI devices will be put into IO frozen - * state as well. - */ -static void *__eeh_pe_state_mark(void *data, void *flag) -{ - struct eeh_pe *pe = (struct eeh_pe *)data; - int state = *((int *)flag); - struct eeh_dev *tmp; - struct pci_dev *pdev; - - /* - * Mark the PE with the indicated state. Also, - * the associated PCI device will be put into - * I/O frozen state to avoid I/O accesses from - * the PCI device driver. - */ - pe->state |= state; - eeh_pe_for_each_dev(pe, tmp) { - pdev = eeh_dev_to_pci_dev(tmp); - if (pdev) - pdev->error_state = pci_channel_io_frozen; - } - - return NULL; -} - -/** - * eeh_pe_state_mark - Mark specified state for PE and its associated device - * @pe: EEH PE - * - * EEH error affects the current PE and its child PEs. The function - * is used to mark appropriate state for the affected PEs and the - * associated devices. - */ -void eeh_pe_state_mark(struct eeh_pe *pe, int state) -{ - eeh_lock(); - eeh_pe_traverse(pe, __eeh_pe_state_mark, &state); - eeh_unlock(); -} - -/** - * __eeh_pe_state_clear - Clear state for the PE - * @data: EEH PE - * @flag: state - * - * The function is used to clear the indicated state from the - * given PE. Besides, we also clear the check count of the PE - * as well. - */ -static void *__eeh_pe_state_clear(void *data, void *flag) -{ - struct eeh_pe *pe = (struct eeh_pe *)data; - int state = *((int *)flag); - - pe->state &= ~state; - pe->check_count = 0; - - return NULL; -} - -/** - * eeh_pe_state_clear - Clear state for the PE and its children - * @pe: PE - * @state: state to be cleared - * - * When the PE and its children has been recovered from error, - * we need clear the error state for that. The function is used - * for the purpose. - */ -void eeh_pe_state_clear(struct eeh_pe *pe, int state) -{ - eeh_lock(); - eeh_pe_traverse(pe, __eeh_pe_state_clear, &state); - eeh_unlock(); -} - -/** - * eeh_restore_one_device_bars - Restore the Base Address Registers for one device - * @data: EEH device - * @flag: Unused - * - * Loads the PCI configuration space base address registers, - * the expansion ROM base address, the latency timer, and etc. - * from the saved values in the device node. - */ -static void *eeh_restore_one_device_bars(void *data, void *flag) -{ - int i; - u32 cmd; - struct eeh_dev *edev = (struct eeh_dev *)data; - struct device_node *dn = eeh_dev_to_of_node(edev); - - for (i = 4; i < 10; i++) - eeh_ops->write_config(dn, i*4, 4, edev->config_space[i]); - /* 12 == Expansion ROM Address */ - eeh_ops->write_config(dn, 12*4, 4, edev->config_space[12]); - -#define BYTE_SWAP(OFF) (8*((OFF)/4)+3-(OFF)) -#define SAVED_BYTE(OFF) (((u8 *)(edev->config_space))[BYTE_SWAP(OFF)]) - - eeh_ops->write_config(dn, PCI_CACHE_LINE_SIZE, 1, - SAVED_BYTE(PCI_CACHE_LINE_SIZE)); - eeh_ops->write_config(dn, PCI_LATENCY_TIMER, 1, - SAVED_BYTE(PCI_LATENCY_TIMER)); - - /* max latency, min grant, interrupt pin and line */ - eeh_ops->write_config(dn, 15*4, 4, edev->config_space[15]); - - /* - * Restore PERR & SERR bits, some devices require it, - * don't touch the other command bits - */ - eeh_ops->read_config(dn, PCI_COMMAND, 4, &cmd); - if (edev->config_space[1] & PCI_COMMAND_PARITY) - cmd |= PCI_COMMAND_PARITY; - else - cmd &= ~PCI_COMMAND_PARITY; - if (edev->config_space[1] & PCI_COMMAND_SERR) - cmd |= PCI_COMMAND_SERR; - else - cmd &= ~PCI_COMMAND_SERR; - eeh_ops->write_config(dn, PCI_COMMAND, 4, cmd); - - return NULL; -} - -/** - * eeh_pe_restore_bars - Restore the PCI config space info - * @pe: EEH PE - * - * This routine performs a recursive walk to the children - * of this device as well. - */ -void eeh_pe_restore_bars(struct eeh_pe *pe) -{ - /* - * We needn't take the EEH lock since eeh_pe_dev_traverse() - * will take that. - */ - eeh_pe_dev_traverse(pe, eeh_restore_one_device_bars, NULL); -} - -/** - * eeh_pe_bus_get - Retrieve PCI bus according to the given PE - * @pe: EEH PE - * - * Retrieve the PCI bus according to the given PE. Basically, - * there're 3 types of PEs: PHB/Bus/Device. For PHB PE, the - * primary PCI bus will be retrieved. The parent bus will be - * returned for BUS PE. However, we don't have associated PCI - * bus for DEVICE PE. - */ -struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe) -{ - struct pci_bus *bus = NULL; - struct eeh_dev *edev; - struct pci_dev *pdev; - - eeh_lock(); - - if (pe->type & EEH_PE_PHB) { - bus = pe->phb->bus; - } else if (pe->type & EEH_PE_BUS) { - edev = list_first_entry(&pe->edevs, struct eeh_dev, list); - pdev = eeh_dev_to_pci_dev(edev); - if (pdev) - bus = pdev->bus; - } - - eeh_unlock(); - - return bus; -} diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index 19506f93573..0bec0c02c5e 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -83,7 +83,11 @@ static int pseries_eeh_init(void) ibm_configure_pe = rtas_token("ibm,configure-pe"); ibm_configure_bridge = rtas_token("ibm,configure-bridge"); - /* necessary sanity check */ + /* + * Necessary sanity check. We needn't check "get-config-addr-info" + * and its variant since the old firmware probably support address + * of domain/bus/slot/function for EEH RTAS operations. + */ if (ibm_set_eeh_option == RTAS_UNKNOWN_SERVICE) { pr_warning("%s: RTAS service <ibm,set-eeh-option> invalid\n", __func__); @@ -102,12 +106,6 @@ static int pseries_eeh_init(void) pr_warning("%s: RTAS service <ibm,slot-error-detail> invalid\n", __func__); return -EINVAL; - } else if (ibm_get_config_addr_info2 == RTAS_UNKNOWN_SERVICE && - ibm_get_config_addr_info == RTAS_UNKNOWN_SERVICE) { - pr_warning("%s: RTAS service <ibm,get-config-addr-info2> and " - "<ibm,get-config-addr-info> invalid\n", - __func__); - return -EINVAL; } else if (ibm_configure_pe == RTAS_UNKNOWN_SERVICE && ibm_configure_bridge == RTAS_UNKNOWN_SERVICE) { pr_warning("%s: RTAS service <ibm,configure-pe> and " @@ -135,6 +133,78 @@ static int pseries_eeh_init(void) return 0; } +static int pseries_eeh_cap_start(struct device_node *dn) +{ + struct pci_dn *pdn = PCI_DN(dn); + u32 status; + + if (!pdn) + return 0; + + rtas_read_config(pdn, PCI_STATUS, 2, &status); + if (!(status & PCI_STATUS_CAP_LIST)) + return 0; + + return PCI_CAPABILITY_LIST; +} + + +static int pseries_eeh_find_cap(struct device_node *dn, int cap) +{ + struct pci_dn *pdn = PCI_DN(dn); + int pos = pseries_eeh_cap_start(dn); + int cnt = 48; /* Maximal number of capabilities */ + u32 id; + + if (!pos) + return 0; + + while (cnt--) { + rtas_read_config(pdn, pos, 1, &pos); + if (pos < 0x40) + break; + pos &= ~3; + rtas_read_config(pdn, pos + PCI_CAP_LIST_ID, 1, &id); + if (id == 0xff) + break; + if (id == cap) + return pos; + pos += PCI_CAP_LIST_NEXT; + } + + return 0; +} + +static int pseries_eeh_find_ecap(struct device_node *dn, int cap) +{ + struct pci_dn *pdn = PCI_DN(dn); + struct eeh_dev *edev = of_node_to_eeh_dev(dn); + u32 header; + int pos = 256; + int ttl = (4096 - 256) / 8; + + if (!edev || !edev->pcie_cap) + return 0; + if (rtas_read_config(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 (rtas_read_config(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL) + break; + } + + return 0; +} + /** * pseries_eeh_of_probe - EEH probe on the given device * @dn: OF node @@ -148,30 +218,54 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) { struct eeh_dev *edev; struct eeh_pe pe; - const u32 *class_code, *vendor_id, *device_id; - const u32 *regs; + 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 (!of_device_is_available(dn)) + if (edev->pe || !of_device_is_available(dn)) return NULL; /* Retrieve class/vendor/device IDs */ - class_code = of_get_property(dn, "class-code", NULL); - vendor_id = of_get_property(dn, "vendor-id", NULL); - device_id = of_get_property(dn, "device-id", NULL); + 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 (!class_code || !vendor_id || !device_id) + if (!classp || !vendorp || !devicep) return NULL; if (dn->type && !strcmp(dn->type, "isa")) return NULL; - /* Update class code and mode of eeh device */ - edev->class_code = *class_code; - edev->mode = 0; + class_code = of_read_number(classp, 1); + + /* + * 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->mode &= 0xFFFFFF00; + if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) { + edev->mode |= EEH_DEV_BRIDGE; + if (edev->pcie_cap) { + rtas_read_config(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; + } + } /* Retrieve the device address */ regs = of_get_property(dn, "reg", NULL); @@ -184,12 +278,12 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) /* Initialize the fake PE */ memset(&pe, 0, sizeof(struct eeh_pe)); pe.phb = edev->phb; - pe.config_addr = regs[0]; + pe.config_addr = of_read_number(regs, 1); /* Enable EEH on the device */ ret = eeh_ops->set_option(&pe, EEH_OPT_ENABLE); if (!ret) { - edev->config_addr = regs[0]; + edev->config_addr = of_read_number(regs, 1); /* Retrieve PE address */ edev->pe_config_addr = eeh_ops->get_pe_addr(&pe); pe.addr = edev->pe_config_addr; @@ -203,7 +297,7 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) enable = 1; if (enable) { - eeh_subsystem_enabled = 1; + eeh_set_enable(true); eeh_add_to_parent_pe(edev); pr_debug("%s: EEH enabled on %s PHB#%d-PE#%x, config addr#%x\n", @@ -402,6 +496,7 @@ static int pseries_eeh_get_state(struct eeh_pe *pe, int *state) } else { result = EEH_STATE_NOT_SUPPORT; } + break; default: result = EEH_STATE_NOT_SUPPORT; } @@ -437,11 +532,19 @@ static int pseries_eeh_reset(struct eeh_pe *pe, int option) /* If fundamental-reset not supported, try hot-reset */ if (option == EEH_RESET_FUNDAMENTAL && ret == -8) { + option = EEH_RESET_HOT; ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL, config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid), EEH_RESET_HOT); + BUID_LO(pe->phb->buid), option); } + /* We need reset hold or settlement delay */ + if (option == EEH_RESET_FUNDAMENTAL || + option == EEH_RESET_HOT) + msleep(EEH_PE_RST_HOLD_TIME); + else + msleep(EEH_PE_RST_SETTLE_TIME); + return ret; } @@ -627,7 +730,9 @@ static struct eeh_ops pseries_eeh_ops = { .get_log = pseries_eeh_get_log, .configure_bridge = pseries_eeh_configure_bridge, .read_config = pseries_eeh_read_config, - .write_config = pseries_eeh_write_config + .write_config = pseries_eeh_write_config, + .next_error = NULL, + .restore_config = NULL }; /** diff --git a/arch/powerpc/platforms/pseries/eeh_sysfs.c b/arch/powerpc/platforms/pseries/eeh_sysfs.c deleted file mode 100644 index d37708360f2..00000000000 --- a/arch/powerpc/platforms/pseries/eeh_sysfs.c +++ /dev/null @@ -1,75 +0,0 @@ -/* - * Sysfs entries for PCI Error Recovery for PAPR-compliant platform. - * Copyright IBM Corporation 2007 - * Copyright Linas Vepstas <linas@austin.ibm.com> 2007 - * - * All rights reserved. - * - * 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, GOOD TITLE or - * NON INFRINGEMENT. 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., 675 Mass Ave, Cambridge, MA 02139, USA. - * - * Send comments and feedback to Linas Vepstas <linas@austin.ibm.com> - */ -#include <linux/pci.h> -#include <linux/stat.h> -#include <asm/ppc-pci.h> -#include <asm/pci-bridge.h> - -/** - * EEH_SHOW_ATTR -- Create sysfs entry for eeh statistic - * @_name: name of file in sysfs directory - * @_memb: name of member in struct pci_dn to access - * @_format: printf format for display - * - * All of the attributes look very similar, so just - * auto-gen a cut-n-paste routine to display them. - */ -#define EEH_SHOW_ATTR(_name,_memb,_format) \ -static ssize_t eeh_show_##_name(struct device *dev, \ - struct device_attribute *attr, char *buf) \ -{ \ - struct pci_dev *pdev = to_pci_dev(dev); \ - struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev); \ - \ - if (!edev) \ - return 0; \ - \ - return sprintf(buf, _format "\n", edev->_memb); \ -} \ -static DEVICE_ATTR(_name, S_IRUGO, eeh_show_##_name, NULL); - -EEH_SHOW_ATTR(eeh_mode, mode, "0x%x"); -EEH_SHOW_ATTR(eeh_config_addr, config_addr, "0x%x"); -EEH_SHOW_ATTR(eeh_pe_config_addr, pe_config_addr, "0x%x"); - -void eeh_sysfs_add_device(struct pci_dev *pdev) -{ - int rc=0; - - rc += device_create_file(&pdev->dev, &dev_attr_eeh_mode); - rc += device_create_file(&pdev->dev, &dev_attr_eeh_config_addr); - rc += device_create_file(&pdev->dev, &dev_attr_eeh_pe_config_addr); - - if (rc) - printk(KERN_WARNING "EEH: Unable to create sysfs entries\n"); -} - -void eeh_sysfs_remove_device(struct pci_dev *pdev) -{ - device_remove_file(&pdev->dev, &dev_attr_eeh_mode); - device_remove_file(&pdev->dev, &dev_attr_eeh_config_addr); - device_remove_file(&pdev->dev, &dev_attr_eeh_pe_config_addr); -} - diff --git a/arch/powerpc/platforms/pseries/event_sources.c b/arch/powerpc/platforms/pseries/event_sources.c index 2605c310166..18380e8f6df 100644 --- a/arch/powerpc/platforms/pseries/event_sources.c +++ b/arch/powerpc/platforms/pseries/event_sources.c @@ -25,7 +25,7 @@ void request_event_sources_irqs(struct device_node *np, const char *name) { int i, index, count = 0; - struct of_irq oirq; + struct of_phandle_args oirq; const u32 *opicprop; unsigned int opicplen; unsigned int virqs[16]; @@ -55,13 +55,11 @@ void request_event_sources_irqs(struct device_node *np, /* Else use normal interrupt tree parsing */ else { /* First try to do a proper OF tree parsing */ - for (index = 0; of_irq_map_one(np, index, &oirq) == 0; + for (index = 0; of_irq_parse_one(np, index, &oirq) == 0; index++) { if (count > 15) break; - virqs[count] = irq_create_of_mapping(oirq.controller, - oirq.specifier, - oirq.size); + virqs[count] = irq_create_of_mapping(&oirq); if (virqs[count] == NO_IRQ) { pr_err("event-sources: Unable to allocate " "interrupt number for %s\n", diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c index 7b56118f531..8c80588abac 100644 --- a/arch/powerpc/platforms/pseries/firmware.c +++ b/arch/powerpc/platforms/pseries/firmware.c @@ -28,13 +28,18 @@ #include "pseries.h" -typedef struct { +struct hypertas_fw_feature { unsigned long val; char * name; -} firmware_feature_t; +}; -static __initdata firmware_feature_t -firmware_features_table[FIRMWARE_MAX_FEATURES] = { +/* + * The names in this table match names in rtas/ibm,hypertas-functions. If the + * entry ends in a '*', only upto the '*' is matched. Otherwise the entire + * string must match. + */ +static __initdata struct hypertas_fw_feature +hypertas_fw_features_table[] = { {FW_FEATURE_PFT, "hcall-pft"}, {FW_FEATURE_TCE, "hcall-tce"}, {FW_FEATURE_SPRG0, "hcall-sprg0"}, @@ -57,32 +62,72 @@ firmware_features_table[FIRMWARE_MAX_FEATURES] = { {FW_FEATURE_SPLPAR, "hcall-splpar"}, {FW_FEATURE_VPHN, "hcall-vphn"}, {FW_FEATURE_SET_MODE, "hcall-set-mode"}, + {FW_FEATURE_BEST_ENERGY, "hcall-best-energy-1*"}, }; /* Build up the firmware features bitmask using the contents of * device-tree/ibm,hypertas-functions. Ultimately this functionality may * be moved into prom.c prom_init(). */ -void __init fw_feature_init(const char *hypertas, unsigned long len) +void __init fw_hypertas_feature_init(const char *hypertas, unsigned long len) { const char *s; int i; - pr_debug(" -> fw_feature_init()\n"); + pr_debug(" -> fw_hypertas_feature_init()\n"); for (s = hypertas; s < hypertas + len; s += strlen(s) + 1) { - for (i = 0; i < FIRMWARE_MAX_FEATURES; i++) { - /* check value against table of strings */ - if (!firmware_features_table[i].name || - strcmp(firmware_features_table[i].name, s)) + for (i = 0; i < ARRAY_SIZE(hypertas_fw_features_table); i++) { + const char *name = hypertas_fw_features_table[i].name; + size_t size; + + /* + * If there is a '*' at the end of name, only check + * upto there + */ + size = strlen(name); + if (size && name[size - 1] == '*') { + if (strncmp(name, s, size - 1)) + continue; + } else if (strcmp(name, s)) continue; /* we have a match */ powerpc_firmware_features |= - firmware_features_table[i].val; + hypertas_fw_features_table[i].val; break; } } - pr_debug(" <- fw_feature_init()\n"); + pr_debug(" <- fw_hypertas_feature_init()\n"); +} + +struct vec5_fw_feature { + unsigned long val; + unsigned int feature; +}; + +static __initdata struct vec5_fw_feature +vec5_fw_features_table[] = { + {FW_FEATURE_TYPE1_AFFINITY, OV5_TYPE1_AFFINITY}, + {FW_FEATURE_PRRN, OV5_PRRN}, +}; + +void __init fw_vec5_feature_init(const char *vec5, unsigned long len) +{ + unsigned int index, feat; + int i; + + pr_debug(" -> fw_vec5_feature_init()\n"); + + for (i = 0; i < ARRAY_SIZE(vec5_fw_features_table); i++) { + index = OV5_INDX(vec5_fw_features_table[i].feature); + feat = OV5_FEAT(vec5_fw_features_table[i].feature); + + if (vec5[index] & feat) + powerpc_firmware_features |= + vec5_fw_features_table[i].val; + } + + pr_debug(" <- fw_vec5_feature_init()\n"); } diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index a38956269fb..20d62975856 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -30,16 +30,12 @@ #include <asm/machdep.h> #include <asm/vdso_datapage.h> #include <asm/xics.h> -#include "plpar_wrappers.h" +#include <asm/plpar_wrappers.h> + #include "offline_states.h" /* This version can't take the spinlock, because it never returns */ -static struct rtas_args rtas_stop_self_args = { - .token = RTAS_UNKNOWN_SERVICE, - .nargs = 0, - .nret = 1, - .rets = &rtas_stop_self_args.args[0], -}; +static int rtas_stop_self_token = RTAS_UNKNOWN_SERVICE; static DEFINE_PER_CPU(enum cpu_state_vals, preferred_offline_state) = CPU_STATE_OFFLINE; @@ -92,15 +88,21 @@ void set_default_offline_state(int cpu) static void rtas_stop_self(void) { - struct rtas_args *args = &rtas_stop_self_args; + static struct rtas_args args = { + .nargs = 0, + .nret = 1, + .rets = &args.args[0], + }; + + args.token = cpu_to_be32(rtas_stop_self_token); local_irq_disable(); - BUG_ON(args->token == RTAS_UNKNOWN_SERVICE); + BUG_ON(rtas_stop_self_token == RTAS_UNKNOWN_SERVICE); printk("cpu %u (hwid %u) Ready to die...\n", smp_processor_id(), hard_smp_processor_id()); - enter_rtas(__pa(args)); + enter_rtas(__pa(&args)); panic("Alas, I survived.\n"); } @@ -123,20 +125,28 @@ static void pseries_mach_cpu_die(void) cede_latency_hint = 2; get_lppaca()->idle = 1; - if (!get_lppaca()->shared_proc) + if (!lppaca_shared_proc(get_lppaca())) get_lppaca()->donate_dedicated_cpu = 1; while (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) { + while (!prep_irq_for_idle()) { + local_irq_enable(); + local_irq_disable(); + } + extended_cede_processor(cede_latency_hint); } - if (!get_lppaca()->shared_proc) + local_irq_disable(); + + if (!lppaca_shared_proc(get_lppaca())) get_lppaca()->donate_dedicated_cpu = 0; get_lppaca()->idle = 0; if (get_preferred_offline_state(cpu) == CPU_STATE_ONLINE) { unregister_slb_shadow(hwcpu); + hard_irq_disable(); /* * Call to start_secondary_resume() will not return. * Kernel stack will be reset and start_secondary() @@ -383,10 +393,10 @@ static int __init pseries_cpu_hotplug_init(void) } } - rtas_stop_self_args.token = rtas_token("stop-self"); + rtas_stop_self_token = rtas_token("stop-self"); qcss_tok = rtas_token("query-cpu-stopped-state"); - if (rtas_stop_self_args.token == RTAS_UNKNOWN_SERVICE || + if (rtas_stop_self_token == RTAS_UNKNOWN_SERVICE || qcss_tok == RTAS_UNKNOWN_SERVICE) { printk(KERN_INFO "CPU Hotplug not supported by firmware " "- disabling.\n"); @@ -411,4 +421,4 @@ static int __init pseries_cpu_hotplug_init(void) return 0; } -arch_initcall(pseries_cpu_hotplug_init); +machine_arch_initcall(pseries, pseries_cpu_hotplug_init); diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 2372c609fa2..7995135170a 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -10,15 +10,18 @@ */ #include <linux/of.h> +#include <linux/of_address.h> #include <linux/memblock.h> #include <linux/vmalloc.h> #include <linux/memory.h> +#include <linux/memory_hotplug.h> #include <asm/firmware.h> #include <asm/machdep.h> +#include <asm/prom.h> #include <asm/sparsemem.h> -static unsigned long get_memblock_size(void) +unsigned long pseries_memory_block_size(void) { struct device_node *np; unsigned int memblock_size = MIN_MEMORY_BLOCK_SIZE; @@ -61,71 +64,53 @@ static unsigned long get_memblock_size(void) return memblock_size; } -/* WARNING: This is going to override the generic definition whenever - * pseries is built-in regardless of what platform is active at boot - * time. This is fine for now as this is the only "option" and it - * should work everywhere. If not, we'll have to turn this into a - * ppc_md. callback - */ -unsigned long memory_block_size_bytes(void) +#ifdef CONFIG_MEMORY_HOTREMOVE +static int pseries_remove_memory(u64 start, u64 size) { - return get_memblock_size(); + int ret; + + /* Remove htab bolted mappings for this section of memory */ + start = (unsigned long)__va(start); + ret = remove_section_mapping(start, start + size); + + /* Ensure all vmalloc mappings are flushed in case they also + * hit that section of memory + */ + vm_unmap_aliases(); + + return ret; } static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size) { - unsigned long start, start_pfn; - struct zone *zone; - int ret; - unsigned long section; - unsigned long sections_to_remove; + unsigned long block_sz, start_pfn; + int sections_per_block; + int i, nid; start_pfn = base >> PAGE_SHIFT; - if (!pfn_valid(start_pfn)) { - memblock_remove(base, memblock_size); - return 0; - } + lock_device_hotplug(); - zone = page_zone(pfn_to_page(start_pfn)); + if (!pfn_valid(start_pfn)) + goto out; - /* - * Remove section mappings and sysfs entries for the - * section of the memory we are removing. - * - * NOTE: Ideally, this should be done in generic code like - * remove_memory(). But remove_memory() gets called by writing - * to sysfs "state" file and we can't remove sysfs entries - * while writing to it. So we have to defer it to here. - */ - sections_to_remove = (memblock_size >> PAGE_SHIFT) / PAGES_PER_SECTION; - for (section = 0; section < sections_to_remove; section++) { - unsigned long pfn = start_pfn + section * PAGES_PER_SECTION; - ret = __remove_pages(zone, pfn, PAGES_PER_SECTION); - if (ret) - return ret; + block_sz = pseries_memory_block_size(); + sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE; + nid = memory_add_physaddr_to_nid(base); + + for (i = 0; i < sections_per_block; i++) { + remove_memory(nid, base, MIN_MEMORY_BLOCK_SIZE); + base += MIN_MEMORY_BLOCK_SIZE; } - /* - * Update memory regions for memory remove - */ +out: + /* Update memory regions for memory remove */ memblock_remove(base, memblock_size); - - /* - * Remove htab bolted mappings for this section of memory - */ - start = (unsigned long)__va(base); - ret = remove_section_mapping(start, start + memblock_size); - - /* Ensure all vmalloc mappings are flushed in case they also - * hit that section of memory - */ - vm_unmap_aliases(); - - return ret; + unlock_device_hotplug(); + return 0; } -static int pseries_remove_memory(struct device_node *np) +static int pseries_remove_mem_node(struct device_node *np) { const char *type; const unsigned int *regs; @@ -150,11 +135,22 @@ static int pseries_remove_memory(struct device_node *np) base = *(unsigned long *)regs; lmb_size = regs[3]; - ret = pseries_remove_memblock(base, lmb_size); - return ret; + pseries_remove_memblock(base, lmb_size); + return 0; } +#else +static inline int pseries_remove_memblock(unsigned long base, + unsigned int memblock_size) +{ + return -EOPNOTSUPP; +} +static inline int pseries_remove_mem_node(struct device_node *np) +{ + return -EOPNOTSUPP; +} +#endif /* CONFIG_MEMORY_HOTREMOVE */ -static int pseries_add_memory(struct device_node *np) +static int pseries_add_mem_node(struct device_node *np) { const char *type; const unsigned int *regs; @@ -194,7 +190,7 @@ static int pseries_update_drconf_memory(struct of_prop_reconfig *pr) u32 *p; int i, rc = -EINVAL; - memblock_size = get_memblock_size(); + memblock_size = pseries_memory_block_size(); if (!memblock_size) return -EINVAL; @@ -240,10 +236,10 @@ static int pseries_memory_notifier(struct notifier_block *nb, switch (action) { case OF_RECONFIG_ATTACH_NODE: - err = pseries_add_memory(node); + err = pseries_add_mem_node(node); break; case OF_RECONFIG_DETACH_NODE: - err = pseries_remove_memory(node); + err = pseries_remove_mem_node(node); break; case OF_RECONFIG_UPDATE_PROPERTY: pr = (struct of_prop_reconfig *)node; @@ -263,6 +259,10 @@ static int __init pseries_memory_hotplug_init(void) if (firmware_has_feature(FW_FEATURE_LPAR)) of_reconfig_notifier_register(&pseries_mem_nb); +#ifdef CONFIG_MEMORY_HOTREMOVE + ppc_md.remove_memory = pseries_remove_memory; +#endif + return 0; } machine_device_initcall(pseries, pseries_memory_hotplug_init); diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index 444fe7759e5..99ecf0a5a92 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -49,7 +49,7 @@ END_FTR_SECTION(0, 1); \ std r0,16(r1); \ addi r4,r1,STK_PARAM(FIRST_REG); \ stdu r1,-STACK_FRAME_OVERHEAD(r1); \ - bl .__trace_hcall_entry; \ + bl __trace_hcall_entry; \ addi r1,r1,STACK_FRAME_OVERHEAD; \ ld r0,16(r1); \ ld r3,STK_PARAM(R3)(r1); \ @@ -83,7 +83,7 @@ END_FTR_SECTION(0, 1); \ mr r3,r6; \ std r0,16(r1); \ stdu r1,-STACK_FRAME_OVERHEAD(r1); \ - bl .__trace_hcall_exit; \ + bl __trace_hcall_exit; \ addi r1,r1,STACK_FRAME_OVERHEAD; \ ld r0,16(r1); \ ld r3,STK_PARAM(R3)(r1); \ @@ -106,7 +106,7 @@ END_FTR_SECTION(0, 1); \ .text -_GLOBAL(plpar_hcall_norets) +_GLOBAL_TOC(plpar_hcall_norets) HMT_MEDIUM mfcr r0 @@ -122,7 +122,7 @@ _GLOBAL(plpar_hcall_norets) mtcrf 0xff,r0 blr /* return r3 = status */ -_GLOBAL(plpar_hcall) +_GLOBAL_TOC(plpar_hcall) HMT_MEDIUM mfcr r0 @@ -188,7 +188,7 @@ _GLOBAL(plpar_hcall_raw) blr /* return r3 = status */ -_GLOBAL(plpar_hcall9) +_GLOBAL_TOC(plpar_hcall9) HMT_MEDIUM mfcr r0 diff --git a/arch/powerpc/platforms/pseries/hvCall_inst.c b/arch/powerpc/platforms/pseries/hvCall_inst.c index c9311cfdfca..cf4e7736e4f 100644 --- a/arch/powerpc/platforms/pseries/hvCall_inst.c +++ b/arch/powerpc/platforms/pseries/hvCall_inst.c @@ -86,7 +86,7 @@ static int hcall_inst_seq_open(struct inode *inode, struct file *file) rc = seq_open(file, &hcall_inst_seq_ops); seq = file->private_data; - seq->private = file->f_path.dentry->d_inode->i_private; + seq->private = file_inode(file)->i_private; return rc; } diff --git a/arch/powerpc/platforms/pseries/hvconsole.c b/arch/powerpc/platforms/pseries/hvconsole.c index b344f94b040..849b29b3e9a 100644 --- a/arch/powerpc/platforms/pseries/hvconsole.c +++ b/arch/powerpc/platforms/pseries/hvconsole.c @@ -28,7 +28,7 @@ #include <linux/errno.h> #include <asm/hvcall.h> #include <asm/hvconsole.h> -#include "plpar_wrappers.h" +#include <asm/plpar_wrappers.h> /** * hvc_get_chars - retrieve characters from firmware for denoted vterm adatper @@ -40,10 +40,16 @@ */ int hvc_get_chars(uint32_t vtermno, char *buf, int count) { - unsigned long got; + long ret; + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + unsigned long *lbuf = (unsigned long *)buf; + + ret = plpar_hcall(H_GET_TERM_CHAR, retbuf, vtermno); + lbuf[0] = be64_to_cpu(retbuf[1]); + lbuf[1] = be64_to_cpu(retbuf[2]); - if (plpar_get_term_char(vtermno, &got, buf) == H_SUCCESS) - return got; + if (ret == H_SUCCESS) + return retbuf[0]; return 0; } @@ -69,8 +75,9 @@ int hvc_put_chars(uint32_t vtermno, const char *buf, int count) if (count > MAX_VIO_PUT_CHARS) count = MAX_VIO_PUT_CHARS; - ret = plpar_hcall_norets(H_PUT_TERM_CHAR, vtermno, count, lbuf[0], - lbuf[1]); + ret = plpar_hcall_norets(H_PUT_TERM_CHAR, vtermno, count, + cpu_to_be64(lbuf[0]), + cpu_to_be64(lbuf[1])); if (ret == H_SUCCESS) return count; if (ret == H_BUSY) diff --git a/arch/powerpc/platforms/pseries/hvcserver.c b/arch/powerpc/platforms/pseries/hvcserver.c index fcf4b4cbeaf..4557e91626c 100644 --- a/arch/powerpc/platforms/pseries/hvcserver.c +++ b/arch/powerpc/platforms/pseries/hvcserver.c @@ -23,6 +23,7 @@ #include <linux/list.h> #include <linux/module.h> #include <linux/slab.h> +#include <linux/string.h> #include <asm/hvcall.h> #include <asm/hvcserver.h> @@ -188,9 +189,9 @@ int hvcs_get_partner_info(uint32_t unit_address, struct list_head *head, = (unsigned int)last_p_partition_ID; /* copy the Null-term char too */ - strncpy(&next_partner_info->location_code[0], + strlcpy(&next_partner_info->location_code[0], (char *)&pi_buff[2], - strlen((char *)&pi_buff[2]) + 1); + sizeof(next_partner_info->location_code)); list_add_tail(&(next_partner_info->node), head); next_partner_info = NULL; diff --git a/arch/powerpc/platforms/pseries/io_event_irq.c b/arch/powerpc/platforms/pseries/io_event_irq.c index ef9d9d84c7d..0240c4ff878 100644 --- a/arch/powerpc/platforms/pseries/io_event_irq.c +++ b/arch/powerpc/platforms/pseries/io_event_irq.c @@ -82,9 +82,9 @@ static struct pseries_io_event * ioei_find_event(struct rtas_error_log *elog) * RTAS_TYPE_IO only exists in extended event log version 6 or later. * No need to check event log version. */ - if (unlikely(elog->type != RTAS_TYPE_IO)) { - printk_once(KERN_WARNING "io_event_irq: Unexpected event type %d", - elog->type); + if (unlikely(rtas_error_type(elog) != RTAS_TYPE_IO)) { + printk_once(KERN_WARNING"io_event_irq: Unexpected event type %d", + rtas_error_type(elog)); return NULL; } @@ -115,7 +115,7 @@ static struct pseries_io_event * ioei_find_event(struct rtas_error_log *elog) * by scope or event type alone. For example, Torrent ISR route change * event is reported with scope 0x00 (Not Applicatable) rather than * 0x3B (Torrent-hub). It is better to let the clients to identify - * who owns the the event. + * who owns the event. */ static irqreturn_t ioei_interrupt(int irq, void *dev_id) diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index e2685badb5d..33b552ffbe5 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -48,12 +48,11 @@ #include <asm/ppc-pci.h> #include <asm/udbg.h> #include <asm/mmzone.h> - -#include "plpar_wrappers.h" +#include <asm/plpar_wrappers.h> static void tce_invalidate_pSeries_sw(struct iommu_table *tbl, - u64 *startp, u64 *endp) + __be64 *startp, __be64 *endp) { u64 __iomem *invalidate = (u64 __iomem *)tbl->it_index; unsigned long start, end, inc; @@ -87,7 +86,7 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index, struct dma_attrs *attrs) { u64 proto_tce; - u64 *tcep, *tces; + __be64 *tcep, *tces; u64 rpn; proto_tce = TCE_PCI_READ; // Read allowed @@ -95,12 +94,12 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index, if (direction != DMA_TO_DEVICE) proto_tce |= TCE_PCI_WRITE; - tces = tcep = ((u64 *)tbl->it_base) + index; + tces = tcep = ((__be64 *)tbl->it_base) + index; while (npages--) { /* can't move this out since we might cross MEMBLOCK boundary */ rpn = __pa(uaddr) >> TCE_SHIFT; - *tcep = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT; + *tcep = cpu_to_be64(proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT); uaddr += TCE_PAGE_SIZE; tcep++; @@ -114,9 +113,9 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index, static void tce_free_pSeries(struct iommu_table *tbl, long index, long npages) { - u64 *tcep, *tces; + __be64 *tcep, *tces; - tces = tcep = ((u64 *)tbl->it_base) + index; + tces = tcep = ((__be64 *)tbl->it_base) + index; while (npages--) *(tcep++) = 0; @@ -127,11 +126,11 @@ static void tce_free_pSeries(struct iommu_table *tbl, long index, long npages) static unsigned long tce_get_pseries(struct iommu_table *tbl, long index) { - u64 *tcep; + __be64 *tcep; - tcep = ((u64 *)tbl->it_base) + index; + tcep = ((__be64 *)tbl->it_base) + index; - return *tcep; + return be64_to_cpu(*tcep); } static void tce_free_pSeriesLP(struct iommu_table*, long, long); @@ -178,7 +177,7 @@ static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum, return ret; } -static DEFINE_PER_CPU(u64 *, tce_page); +static DEFINE_PER_CPU(__be64 *, tce_page); static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages, unsigned long uaddr, @@ -187,7 +186,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, { u64 rc = 0; u64 proto_tce; - u64 *tcep; + __be64 *tcep; u64 rpn; long l, limit; long tcenum_start = tcenum, npages_start = npages; @@ -207,7 +206,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, * from iommu_alloc{,_sg}() */ if (!tcep) { - tcep = (u64 *)__get_free_page(GFP_ATOMIC); + tcep = (__be64 *)__get_free_page(GFP_ATOMIC); /* If allocation fails, fall back to the loop implementation */ if (!tcep) { local_irq_restore(flags); @@ -231,7 +230,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, limit = min_t(long, npages, 4096/TCE_ENTRY_SIZE); for (l = 0; l < limit; l++) { - tcep[l] = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT; + tcep[l] = cpu_to_be64(proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT); rpn++; } @@ -330,16 +329,16 @@ struct direct_window { /* Dynamic DMA Window support */ struct ddw_query_response { - u32 windows_available; - u32 largest_available_block; - u32 page_size; - u32 migration_capable; + __be32 windows_available; + __be32 largest_available_block; + __be32 page_size; + __be32 migration_capable; }; struct ddw_create_response { - u32 liobn; - u32 addr_hi; - u32 addr_lo; + __be32 liobn; + __be32 addr_hi; + __be32 addr_lo; }; static LIST_HEAD(direct_window_list); @@ -382,6 +381,7 @@ static int tce_clearrange_multi_pSeriesLP(unsigned long start_pfn, rc = plpar_tce_stuff((u64)be32_to_cpu(maprange->liobn), dma_offset, 0, limit); + next += limit * tce_size; num_tce -= limit; } while (num_tce > 0 && !rc); @@ -392,7 +392,8 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn, unsigned long num_pfn, const void *arg) { const struct dynamic_dma_window_prop *maprange = arg; - u64 *tcep, tce_size, num_tce, dma_offset, next, proto_tce, liobn; + u64 tce_size, num_tce, dma_offset, next, proto_tce, liobn; + __be64 *tcep; u32 tce_shift; u64 rc = 0; long l, limit; @@ -401,7 +402,7 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn, tcep = __get_cpu_var(tce_page); if (!tcep) { - tcep = (u64 *)__get_free_page(GFP_ATOMIC); + tcep = (__be64 *)__get_free_page(GFP_ATOMIC); if (!tcep) { local_irq_enable(); return -ENOMEM; @@ -435,7 +436,7 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn, dma_offset = next + be64_to_cpu(maprange->dma_base); for (l = 0; l < limit; l++) { - tcep[l] = proto_tce | next; + tcep[l] = cpu_to_be64(proto_tce | next); next += tce_size; } @@ -485,9 +486,10 @@ static void iommu_table_setparms(struct pci_controller *phb, memset((void *)tbl->it_base, 0, *sizep); tbl->it_busno = phb->bus->number; + tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K; /* Units of tce entries */ - tbl->it_offset = phb->dma_window_base_cur >> IOMMU_PAGE_SHIFT; + tbl->it_offset = phb->dma_window_base_cur >> tbl->it_page_shift; /* Test if we are going over 2GB of DMA space */ if (phb->dma_window_base_cur + phb->dma_window_size > 0x80000000ul) { @@ -498,7 +500,7 @@ static void iommu_table_setparms(struct pci_controller *phb, phb->dma_window_base_cur += phb->dma_window_size; /* Set the tce table size - measured in entries */ - tbl->it_size = phb->dma_window_size >> IOMMU_PAGE_SHIFT; + tbl->it_size = phb->dma_window_size >> tbl->it_page_shift; tbl->it_index = 0; tbl->it_blocksize = 16; @@ -529,18 +531,19 @@ static void iommu_table_setparms(struct pci_controller *phb, static void iommu_table_setparms_lpar(struct pci_controller *phb, struct device_node *dn, struct iommu_table *tbl, - const void *dma_window) + const __be32 *dma_window) { unsigned long offset, size; of_parse_dma_window(dn, dma_window, &tbl->it_index, &offset, &size); tbl->it_busno = phb->bus->number; + tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K; tbl->it_base = 0; tbl->it_blocksize = 16; tbl->it_type = TCE_PCI; - tbl->it_offset = offset >> IOMMU_PAGE_SHIFT; - tbl->it_size = size >> IOMMU_PAGE_SHIFT; + tbl->it_offset = offset >> tbl->it_page_shift; + tbl->it_size = size >> tbl->it_page_shift; } static void pci_dma_bus_setup_pSeries(struct pci_bus *bus) @@ -613,6 +616,7 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus) iommu_table_setparms(pci->phb, dn, tbl); pci->iommu_table = iommu_init_table(tbl, pci->phb->node); + iommu_register_group(tbl, pci_domain_nr(bus), 0); /* Divide the rest (1.75GB) among the children */ pci->phb->dma_window_size = 0x80000000ul; @@ -628,7 +632,7 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) struct iommu_table *tbl; struct device_node *dn, *pdn; struct pci_dn *ppci; - const void *dma_window = NULL; + const __be32 *dma_window = NULL; dn = pci_bus_to_OF_node(bus); @@ -657,6 +661,7 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) ppci->phb->node); iommu_table_setparms_lpar(ppci->phb, pdn, tbl, dma_window); ppci->iommu_table = iommu_init_table(tbl, ppci->phb->node); + iommu_register_group(tbl, pci_domain_nr(bus), 0); pr_debug(" created table: %p\n", ppci->iommu_table); } } @@ -683,7 +688,9 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev) phb->node); iommu_table_setparms(phb, dn, tbl); PCI_DN(dn)->iommu_table = iommu_init_table(tbl, phb->node); - set_iommu_table_base(&dev->dev, PCI_DN(dn)->iommu_table); + iommu_register_group(tbl, pci_domain_nr(phb->bus), 0); + set_iommu_table_base_and_group(&dev->dev, + PCI_DN(dn)->iommu_table); return; } @@ -695,7 +702,8 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev) dn = dn->parent; if (dn && PCI_DN(dn)) - set_iommu_table_base(&dev->dev, PCI_DN(dn)->iommu_table); + set_iommu_table_base_and_group(&dev->dev, + PCI_DN(dn)->iommu_table); else printk(KERN_WARNING "iommu: Device %s has no iommu table\n", pci_name(dev)); @@ -713,21 +721,6 @@ static int __init disable_ddw_setup(char *str) early_param("disable_ddw", disable_ddw_setup); -static inline void __remove_ddw(struct device_node *np, const u32 *ddw_avail, u64 liobn) -{ - int ret; - - ret = rtas_call(ddw_avail[2], 1, 1, NULL, liobn); - if (ret) - pr_warning("%s: failed to remove DMA window: rtas returned " - "%d to ibm,remove-pe-dma-window(%x) %llx\n", - np->full_name, ret, ddw_avail[2], liobn); - else - pr_debug("%s: successfully removed DMA window: rtas returned " - "%d to ibm,remove-pe-dma-window(%x) %llx\n", - np->full_name, ret, ddw_avail[2], liobn); -} - static void remove_ddw(struct device_node *np) { struct dynamic_dma_window_prop *dwp; @@ -757,7 +750,15 @@ static void remove_ddw(struct device_node *np) pr_debug("%s successfully cleared tces in window.\n", np->full_name); - __remove_ddw(np, ddw_avail, liobn); + ret = rtas_call(ddw_avail[2], 1, 1, NULL, liobn); + if (ret) + pr_warning("%s: failed to remove direct window: rtas returned " + "%d to ibm,remove-pe-dma-window(%x) %llx\n", + np->full_name, ret, ddw_avail[2], liobn); + else + pr_debug("%s: successfully removed direct window: rtas returned " + "%d to ibm,remove-pe-dma-window(%x) %llx\n", + np->full_name, ret, ddw_avail[2], liobn); delprop: ret = of_remove_property(np, win64); @@ -777,7 +778,7 @@ static u64 find_existing_ddw(struct device_node *pdn) list_for_each_entry(window, &direct_window_list, list) { if (window->device == pdn) { direct64 = window->prop; - dma_addr = direct64->dma_base; + dma_addr = be64_to_cpu(direct64->dma_base); break; } } @@ -882,34 +883,12 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail, return ret; } -static void restore_default_window(struct pci_dev *dev, - u32 ddw_restore_token, unsigned long liobn) -{ - struct eeh_dev *edev; - u32 cfg_addr; - u64 buid; - int ret; - - /* - * Get the config address and phb buid of the PE window. - * Rely on eeh to retrieve this for us. - * Retrieve them from the pci device, not the node with the - * dma-window property - */ - edev = pci_dev_to_eeh_dev(dev); - cfg_addr = edev->config_addr; - if (edev->pe_config_addr) - cfg_addr = edev->pe_config_addr; - buid = edev->phb->buid; +struct failed_ddw_pdn { + struct device_node *pdn; + struct list_head list; +}; - do { - ret = rtas_call(ddw_restore_token, 3, 1, NULL, cfg_addr, - BUID_HI(buid), BUID_LO(buid)); - } while (rtas_busy_delay(ret)); - dev_info(&dev->dev, - "ibm,reset-pe-dma-windows(%x) %x %x %x returned %d\n", - ddw_restore_token, cfg_addr, BUID_HI(buid), BUID_LO(buid), ret); -} +static LIST_HEAD(failed_ddw_pdn_list); /* * If the PE supports dynamic dma windows, and there is space for a table @@ -931,13 +910,10 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) u64 dma_addr, max_addr; struct device_node *dn; const u32 *uninitialized_var(ddw_avail); - const u32 *uninitialized_var(ddw_extensions); - u32 ddw_restore_token = 0; struct direct_window *window; struct property *win64; struct dynamic_dma_window_prop *ddwprop; - const void *dma_window = NULL; - unsigned long liobn, offset, size; + struct failed_ddw_pdn *fpdn; mutex_lock(&direct_window_init_mutex); @@ -946,6 +922,18 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) goto out_unlock; /* + * If we already went through this for a previous function of + * the same device and failed, we don't want to muck with the + * DMA window again, as it will race with in-flight operations + * and can lead to EEHs. The above mutex protects access to the + * list. + */ + list_for_each_entry(fpdn, &failed_ddw_pdn_list, list) { + if (!strcmp(fpdn->pdn->full_name, pdn->full_name)) + goto out_unlock; + } + + /* * the ibm,ddw-applicable property holds the tokens for: * ibm,query-pe-dma-window * ibm,create-pe-dma-window @@ -955,42 +943,9 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) */ ddw_avail = of_get_property(pdn, "ibm,ddw-applicable", &len); if (!ddw_avail || len < 3 * sizeof(u32)) - goto out_unlock; - - /* - * the extensions property is only required to exist in certain - * levels of firmware and later - * the ibm,ddw-extensions property is a list with the first - * element containing the number of extensions and each - * subsequent entry is a value corresponding to that extension - */ - ddw_extensions = of_get_property(pdn, "ibm,ddw-extensions", &len); - if (ddw_extensions) { - /* - * each new defined extension length should be added to - * the top of the switch so the "earlier" entries also - * get picked up - */ - switch (ddw_extensions[0]) { - /* ibm,reset-pe-dma-windows */ - case 1: - ddw_restore_token = ddw_extensions[1]; - break; - } - } + goto out_failed; - /* - * Only remove the existing DMA window if we can restore back to - * the default state. Removing the existing window maximizes the - * resources available to firmware for dynamic window creation. - */ - if (ddw_restore_token) { - dma_window = of_get_property(pdn, "ibm,dma-window", NULL); - of_parse_dma_window(pdn, dma_window, &liobn, &offset, &size); - __remove_ddw(pdn, ddw_avail, liobn); - } - - /* + /* * Query if there is a second window of size to map the * whole partition. Query returns number of windows, largest * block assigned to PE (partition endpoint), and two bitmasks @@ -999,7 +954,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) dn = pci_device_to_OF_node(dev); ret = query_ddw(dev, ddw_avail, &query); if (ret != 0) - goto out_restore_window; + goto out_failed; if (query.windows_available == 0) { /* @@ -1008,34 +963,34 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) * trading in for a larger page size. */ dev_dbg(&dev->dev, "no free dynamic windows"); - goto out_restore_window; + goto out_failed; } - if (query.page_size & 4) { + if (be32_to_cpu(query.page_size) & 4) { page_shift = 24; /* 16MB */ - } else if (query.page_size & 2) { + } else if (be32_to_cpu(query.page_size) & 2) { page_shift = 16; /* 64kB */ - } else if (query.page_size & 1) { + } else if (be32_to_cpu(query.page_size) & 1) { page_shift = 12; /* 4kB */ } else { dev_dbg(&dev->dev, "no supported direct page size in mask %x", query.page_size); - goto out_restore_window; + goto out_failed; } /* verify the window * number of ptes will map the partition */ /* check largest block * page size > max memory hotplug addr */ max_addr = memory_hotplug_max(); - if (query.largest_available_block < (max_addr >> page_shift)) { + if (be32_to_cpu(query.largest_available_block) < (max_addr >> page_shift)) { dev_dbg(&dev->dev, "can't map partiton max 0x%llx with %u " "%llu-sized pages\n", max_addr, query.largest_available_block, 1ULL << page_shift); - goto out_restore_window; + goto out_failed; } len = order_base_2(max_addr); win64 = kzalloc(sizeof(struct property), GFP_KERNEL); if (!win64) { dev_info(&dev->dev, "couldn't allocate property for 64bit dma window\n"); - goto out_restore_window; + goto out_failed; } win64->name = kstrdup(DIRECT64_PROPNAME, GFP_KERNEL); win64->value = ddwprop = kmalloc(sizeof(*ddwprop), GFP_KERNEL); @@ -1050,7 +1005,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) if (ret != 0) goto out_free_prop; - ddwprop->liobn = cpu_to_be32(create.liobn); + ddwprop->liobn = create.liobn; ddwprop->dma_base = cpu_to_be64(of_read_number(&create.addr_hi, 2)); ddwprop->tce_shift = cpu_to_be32(page_shift); ddwprop->window_shift = cpu_to_be32(len); @@ -1097,9 +1052,13 @@ out_free_prop: kfree(win64->value); kfree(win64); -out_restore_window: - if (ddw_restore_token) - restore_default_window(dev, ddw_restore_token, liobn); +out_failed: + + fpdn = kzalloc(sizeof(*fpdn), GFP_KERNEL); + if (!fpdn) + goto out_unlock; + fpdn->pdn = pdn; + list_add(&fpdn->list, &failed_ddw_pdn_list); out_unlock: mutex_unlock(&direct_window_init_mutex); @@ -1110,7 +1069,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) { struct device_node *pdn, *dn; struct iommu_table *tbl; - const void *dma_window = NULL; + const __be32 *dma_window = NULL; struct pci_dn *pci; pr_debug("pci_dma_dev_setup_pSeriesLP: %s\n", pci_name(dev)); @@ -1145,12 +1104,13 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) pci->phb->node); iommu_table_setparms_lpar(pci->phb, pdn, tbl, dma_window); pci->iommu_table = iommu_init_table(tbl, pci->phb->node); + iommu_register_group(tbl, pci_domain_nr(pci->phb->bus), 0); pr_debug(" created table: %p\n", pci->iommu_table); } else { pr_debug(" found DMA window, table: %p\n", pci->iommu_table); } - set_iommu_table_base(&dev->dev, pci->iommu_table); + set_iommu_table_base_and_group(&dev->dev, pci->iommu_table); } static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask) @@ -1158,7 +1118,7 @@ static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask) bool ddw_enabled = false; struct device_node *pdn, *dn; struct pci_dev *pdev; - const void *dma_window = NULL; + const __be32 *dma_window = NULL; u64 dma_offset; if (!dev->dma_mask) @@ -1295,6 +1255,7 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti switch (action) { case OF_RECONFIG_DETACH_NODE: + remove_ddw(np); if (pci && pci->iommu_table) iommu_free_table(pci->iommu_table, np->full_name); @@ -1307,16 +1268,6 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti } } spin_unlock(&direct_window_list_lock); - - /* - * Because the notifier runs after isolation of the - * slot, we are guaranteed any DMA window has already - * been revoked and the TCEs have been marked invalid, - * so we don't need a call to remove_ddw(np). However, - * if an additional notifier action is added before the - * isolate call, we should update this code for - * completeness with such a call. - */ break; default: err = NOTIFY_DONE; diff --git a/arch/powerpc/platforms/pseries/kexec.c b/arch/powerpc/platforms/pseries/kexec.c index 7d94bdc63d5..13fa95b3aa8 100644 --- a/arch/powerpc/platforms/pseries/kexec.c +++ b/arch/powerpc/platforms/pseries/kexec.c @@ -17,9 +17,9 @@ #include <asm/mpic.h> #include <asm/xics.h> #include <asm/smp.h> +#include <asm/plpar_wrappers.h> #include "pseries.h" -#include "plpar_wrappers.h" static void pseries_kexec_cpu_down(int crash_shutdown, int secondary) { diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 0da39fed355..b02af9ef3ff 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -41,10 +41,17 @@ #include <asm/smp.h> #include <asm/trace.h> #include <asm/firmware.h> +#include <asm/plpar_wrappers.h> -#include "plpar_wrappers.h" #include "pseries.h" +/* Flag bits for H_BULK_REMOVE */ +#define HBR_REQUEST 0x4000000000000000UL +#define HBR_RESPONSE 0x8000000000000000UL +#define HBR_END 0xc000000000000000UL +#define HBR_AVPN 0x0200000000000000UL +#define HBR_ANDCOND 0x0100000000000000UL + /* in hvCall.S */ EXPORT_SYMBOL(plpar_hcall); @@ -61,9 +68,18 @@ void vpa_init(int cpu) struct paca_struct *pp; struct dtl_entry *dtl; + /* + * The spec says it "may be problematic" if CPU x registers the VPA of + * CPU y. We should never do that, but wail if we ever do. + */ + WARN_ON(cpu != smp_processor_id()); + if (cpu_has_feature(CPU_FTR_ALTIVEC)) lppaca_of(cpu).vmxregs_in_use = 1; + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + lppaca_of(cpu).ebb_regs_in_use = 1; + addr = __pa(&lppaca_of(cpu)); ret = register_vpa(hwcpu, addr); @@ -76,7 +92,7 @@ void vpa_init(int cpu) * PAPR says this feature is SLB-Buffer but firmware never * reports that. All SPLPAR support SLB shadow buffer. */ - addr = __pa(&slb_shadow[cpu]); + addr = __pa(paca[cpu].slb_shadow_ptr); if (firmware_has_feature(FW_FEATURE_SPLPAR)) { ret = register_slb_shadow(hwcpu, addr); if (ret) @@ -96,7 +112,7 @@ void vpa_init(int cpu) lppaca_of(cpu).dtl_idx = 0; /* hypervisor reads buffer length from this field */ - dtl->enqueue_to_dispatch_time = DISPATCH_LOG_BYTES; + dtl->enqueue_to_dispatch_time = cpu_to_be32(DISPATCH_LOG_BYTES); ret = register_dtl(hwcpu, __pa(dtl)); if (ret) pr_err("WARNING: DTL registration of cpu %d (hw %d) " @@ -109,7 +125,7 @@ void vpa_init(int cpu) static long pSeries_lpar_hpte_insert(unsigned long hpte_group, unsigned long vpn, unsigned long pa, unsigned long rflags, unsigned long vflags, - int psize, int ssize) + int psize, int apsize, int ssize) { unsigned long lpar_rc; unsigned long flags; @@ -121,8 +137,8 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group, "pa=%016lx, rflags=%lx, vflags=%lx, psize=%d)\n", hpte_group, vpn, pa, rflags, vflags, psize); - hpte_v = hpte_encode_v(vpn, psize, ssize) | vflags | HPTE_V_VALID; - hpte_r = hpte_encode_r(pa, psize) | rflags; + hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID; + hpte_r = hpte_encode_r(pa, psize, apsize) | rflags; if (!(vflags & HPTE_V_BOLTED)) pr_devel(" hpte_v=%016lx, hpte_r=%016lx\n", hpte_v, hpte_r); @@ -136,8 +152,9 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group, flags = 0; /* Make pHyp happy */ - if ((rflags & _PAGE_NO_CACHE) & !(rflags & _PAGE_WRITETHRU)) - hpte_r &= ~_PAGE_COHERENT; + if ((rflags & _PAGE_NO_CACHE) && !(rflags & _PAGE_WRITETHRU)) + hpte_r &= ~HPTE_R_M; + if (firmware_has_feature(FW_FEATURE_XCMO) && !(hpte_r & HPTE_R_N)) flags |= H_COALESCE_CAND; @@ -155,7 +172,7 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group, */ if (unlikely(lpar_rc != H_SUCCESS)) { if (!(vflags & HPTE_V_BOLTED)) - pr_devel(" lpar err %lu\n", lpar_rc); + pr_devel(" lpar err %ld\n", lpar_rc); return -2; } if (!(vflags & HPTE_V_BOLTED)) @@ -186,7 +203,13 @@ static long pSeries_lpar_hpte_remove(unsigned long hpte_group) (0x1UL << 4), &dummy1, &dummy2); if (lpar_rc == H_SUCCESS) return i; - BUG_ON(lpar_rc != H_NOT_FOUND); + + /* + * The test for adjunct partition is performed before the + * ANDCOND test. H_RESOURCE may be returned, so we need to + * check for that as well. + */ + BUG_ON(lpar_rc != H_NOT_FOUND && lpar_rc != H_RESOURCE); slot_offset++; slot_offset &= 0x7; @@ -223,6 +246,23 @@ static void pSeries_lpar_hptab_clear(void) &(ptes[j].pteh), &(ptes[j].ptel)); } } + +#ifdef __LITTLE_ENDIAN__ + /* Reset exceptions to big endian */ + if (firmware_has_feature(FW_FEATURE_SET_MODE)) { + long rc; + + rc = pseries_big_endian_exceptions(); + /* + * At this point it is unlikely panic() will get anything + * out to the user, but at least this will stop us from + * continuing on further and creating an even more + * difficult to debug situation. + */ + if (rc) + panic("Could not enable big endian exceptions"); + } +#endif } /* @@ -234,7 +274,8 @@ static void pSeries_lpar_hptab_clear(void) static long pSeries_lpar_hpte_updatepp(unsigned long slot, unsigned long newpp, unsigned long vpn, - int psize, int ssize, int local) + int psize, int apsize, + int ssize, int local) { unsigned long lpar_rc; unsigned long flags = (newpp & 7) | H_AVPN; @@ -322,7 +363,8 @@ static void pSeries_lpar_hpte_updateboltedpp(unsigned long newpp, } static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn, - int psize, int ssize, int local) + int psize, int apsize, + int ssize, int local) { unsigned long want_v; unsigned long lpar_rc; @@ -339,6 +381,113 @@ static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn, BUG_ON(lpar_rc != H_SUCCESS); } +/* + * Limit iterations holding pSeries_lpar_tlbie_lock to 3. We also need + * to make sure that we avoid bouncing the hypervisor tlbie lock. + */ +#define PPC64_HUGE_HPTE_BATCH 12 + +static void __pSeries_lpar_hugepage_invalidate(unsigned long *slot, + unsigned long *vpn, int count, + int psize, int ssize) +{ + unsigned long param[8]; + int i = 0, pix = 0, rc; + unsigned long flags = 0; + int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE); + + if (lock_tlbie) + spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags); + + for (i = 0; i < count; i++) { + + if (!firmware_has_feature(FW_FEATURE_BULK_REMOVE)) { + pSeries_lpar_hpte_invalidate(slot[i], vpn[i], psize, 0, + ssize, 0); + } else { + param[pix] = HBR_REQUEST | HBR_AVPN | slot[i]; + param[pix+1] = hpte_encode_avpn(vpn[i], psize, ssize); + pix += 2; + if (pix == 8) { + rc = plpar_hcall9(H_BULK_REMOVE, param, + param[0], param[1], param[2], + param[3], param[4], param[5], + param[6], param[7]); + BUG_ON(rc != H_SUCCESS); + pix = 0; + } + } + } + if (pix) { + param[pix] = HBR_END; + rc = plpar_hcall9(H_BULK_REMOVE, param, param[0], param[1], + param[2], param[3], param[4], param[5], + param[6], param[7]); + BUG_ON(rc != H_SUCCESS); + } + + if (lock_tlbie) + spin_unlock_irqrestore(&pSeries_lpar_tlbie_lock, flags); +} + +static void pSeries_lpar_hugepage_invalidate(struct mm_struct *mm, + unsigned char *hpte_slot_array, + unsigned long addr, int psize) +{ + int ssize = 0, i, index = 0; + unsigned long s_addr = addr; + unsigned int max_hpte_count, valid; + unsigned long vpn_array[PPC64_HUGE_HPTE_BATCH]; + unsigned long slot_array[PPC64_HUGE_HPTE_BATCH]; + unsigned long shift, hidx, vpn = 0, vsid, hash, slot; + + shift = mmu_psize_defs[psize].shift; + max_hpte_count = 1U << (PMD_SHIFT - shift); + + for (i = 0; i < max_hpte_count; i++) { + valid = hpte_valid(hpte_slot_array, i); + if (!valid) + continue; + hidx = hpte_hash_index(hpte_slot_array, i); + + /* get the vpn */ + addr = s_addr + (i * (1ul << shift)); + if (!is_kernel_addr(addr)) { + ssize = user_segment_size(addr); + vsid = get_vsid(mm->context.id, addr, ssize); + WARN_ON(vsid == 0); + } else { + vsid = get_kernel_vsid(addr, mmu_kernel_ssize); + ssize = mmu_kernel_ssize; + } + + vpn = hpt_vpn(addr, vsid, ssize); + hash = hpt_hash(vpn, shift, ssize); + if (hidx & _PTEIDX_SECONDARY) + hash = ~hash; + + slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; + slot += hidx & _PTEIDX_GROUP_IX; + + slot_array[index] = slot; + vpn_array[index] = vpn; + if (index == PPC64_HUGE_HPTE_BATCH - 1) { + /* + * Now do a bluk invalidate + */ + __pSeries_lpar_hugepage_invalidate(slot_array, + vpn_array, + PPC64_HUGE_HPTE_BATCH, + psize, ssize); + index = 0; + } else + index++; + } + if (index) + __pSeries_lpar_hugepage_invalidate(slot_array, vpn_array, + index, psize, ssize); +} + static void pSeries_lpar_hpte_removebolted(unsigned long ea, int psize, int ssize) { @@ -350,17 +499,12 @@ static void pSeries_lpar_hpte_removebolted(unsigned long ea, slot = pSeries_lpar_hpte_find(vpn, psize, ssize); BUG_ON(slot == -1); - - pSeries_lpar_hpte_invalidate(slot, vpn, psize, ssize, 0); + /* + * lpar doesn't use the passed actual page size + */ + pSeries_lpar_hpte_invalidate(slot, vpn, psize, 0, ssize, 0); } -/* Flag bits for H_BULK_REMOVE */ -#define HBR_REQUEST 0x4000000000000000UL -#define HBR_RESPONSE 0x8000000000000000UL -#define HBR_END 0xc000000000000000UL -#define HBR_AVPN 0x0200000000000000UL -#define HBR_ANDCOND 0x0100000000000000UL - /* * Take a spinlock around flushes to avoid bouncing the hypervisor tlbie * lock. @@ -394,8 +538,11 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local) slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; slot += hidx & _PTEIDX_GROUP_IX; if (!firmware_has_feature(FW_FEATURE_BULK_REMOVE)) { + /* + * lpar doesn't use the passed actual page size + */ pSeries_lpar_hpte_invalidate(slot, vpn, psize, - ssize, local); + 0, ssize, local); } else { param[pix] = HBR_REQUEST | HBR_AVPN | slot; param[pix+1] = hpte_encode_avpn(vpn, psize, @@ -446,6 +593,7 @@ void __init hpte_init_lpar(void) ppc_md.hpte_removebolted = pSeries_lpar_hpte_removebolted; ppc_md.flush_hash_range = pSeries_lpar_flush_hash_range; ppc_md.hpte_clear_all = pSeries_lpar_hptab_clear; + ppc_md.hugepage_invalidate = pSeries_lpar_hugepage_invalidate; } #ifdef CONFIG_PPC_SMLPAR @@ -600,7 +748,7 @@ int h_get_mpp(struct hvcall_mpp_data *mpp_data) mpp_data->mem_weight = (retbuf[3] >> 7 * 8) & 0xff; mpp_data->unallocated_mem_weight = (retbuf[3] >> 6 * 8) & 0xff; - mpp_data->unallocated_entitlement = retbuf[3] & 0xffffffffffff; + mpp_data->unallocated_entitlement = retbuf[3] & 0xffffffffffffUL; mpp_data->pool_size = retbuf[4]; mpp_data->loan_request = retbuf[5]; diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c new file mode 100644 index 00000000000..c9fecf09b8f --- /dev/null +++ b/arch/powerpc/platforms/pseries/lparcfg.c @@ -0,0 +1,710 @@ +/* + * PowerPC64 LPAR Configuration Information Driver + * + * Dave Engebretsen engebret@us.ibm.com + * Copyright (c) 2003 Dave Engebretsen + * Will Schmidt willschm@us.ibm.com + * SPLPAR updates, Copyright (c) 2003 Will Schmidt IBM Corporation. + * seq_file updates, Copyright (c) 2004 Will Schmidt IBM Corporation. + * Nathan Lynch nathanl@austin.ibm.com + * Added lparcfg_write, Copyright (C) 2004 Nathan Lynch 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 driver creates a proc file at /proc/ppc64/lparcfg which contains + * keyword - value pairs that specify the configuration of the partition. + */ + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/errno.h> +#include <linux/proc_fs.h> +#include <linux/init.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <asm/uaccess.h> +#include <asm/lppaca.h> +#include <asm/hvcall.h> +#include <asm/firmware.h> +#include <asm/rtas.h> +#include <asm/time.h> +#include <asm/prom.h> +#include <asm/vdso_datapage.h> +#include <asm/vio.h> +#include <asm/mmu.h> +#include <asm/machdep.h> + + +/* + * This isn't a module but we expose that to userspace + * via /proc so leave the definitions here + */ +#define MODULE_VERS "1.9" +#define MODULE_NAME "lparcfg" + +/* #define LPARCFG_DEBUG */ + +/* + * Track sum of all purrs across all processors. This is used to further + * calculate usage values by different applications + */ +static unsigned long get_purr(void) +{ + unsigned long sum_purr = 0; + int cpu; + + for_each_possible_cpu(cpu) { + struct cpu_usage *cu; + + cu = &per_cpu(cpu_usage_array, cpu); + sum_purr += cu->current_tb; + } + return sum_purr; +} + +/* + * Methods used to fetch LPAR data when running on a pSeries platform. + */ + +struct hvcall_ppp_data { + u64 entitlement; + u64 unallocated_entitlement; + u16 group_num; + u16 pool_num; + u8 capped; + u8 weight; + u8 unallocated_weight; + u16 active_procs_in_pool; + u16 active_system_procs; + u16 phys_platform_procs; + u32 max_proc_cap_avail; + u32 entitled_proc_cap_avail; +}; + +/* + * H_GET_PPP hcall returns info in 4 parms. + * entitled_capacity,unallocated_capacity, + * aggregation, resource_capability). + * + * R4 = Entitled Processor Capacity Percentage. + * R5 = Unallocated Processor Capacity Percentage. + * R6 (AABBCCDDEEFFGGHH). + * XXXX - reserved (0) + * XXXX - reserved (0) + * XXXX - Group Number + * XXXX - Pool Number. + * R7 (IIJJKKLLMMNNOOPP). + * XX - reserved. (0) + * XX - bit 0-6 reserved (0). bit 7 is Capped indicator. + * XX - variable processor Capacity Weight + * XX - Unallocated Variable Processor Capacity Weight. + * XXXX - Active processors in Physical Processor Pool. + * XXXX - Processors active on platform. + * R8 (QQQQRRRRRRSSSSSS). if ibm,partition-performance-parameters-level >= 1 + * XXXX - Physical platform procs allocated to virtualization. + * XXXXXX - Max procs capacity % available to the partitions pool. + * XXXXXX - Entitled procs capacity % available to the + * partitions pool. + */ +static unsigned int h_get_ppp(struct hvcall_ppp_data *ppp_data) +{ + unsigned long rc; + unsigned long retbuf[PLPAR_HCALL9_BUFSIZE]; + + rc = plpar_hcall9(H_GET_PPP, retbuf); + + ppp_data->entitlement = retbuf[0]; + ppp_data->unallocated_entitlement = retbuf[1]; + + ppp_data->group_num = (retbuf[2] >> 2 * 8) & 0xffff; + ppp_data->pool_num = retbuf[2] & 0xffff; + + ppp_data->capped = (retbuf[3] >> 6 * 8) & 0x01; + ppp_data->weight = (retbuf[3] >> 5 * 8) & 0xff; + ppp_data->unallocated_weight = (retbuf[3] >> 4 * 8) & 0xff; + ppp_data->active_procs_in_pool = (retbuf[3] >> 2 * 8) & 0xffff; + ppp_data->active_system_procs = retbuf[3] & 0xffff; + + ppp_data->phys_platform_procs = retbuf[4] >> 6 * 8; + ppp_data->max_proc_cap_avail = (retbuf[4] >> 3 * 8) & 0xffffff; + ppp_data->entitled_proc_cap_avail = retbuf[4] & 0xffffff; + + return rc; +} + +static unsigned h_pic(unsigned long *pool_idle_time, + unsigned long *num_procs) +{ + unsigned long rc; + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + + rc = plpar_hcall(H_PIC, retbuf); + + *pool_idle_time = retbuf[0]; + *num_procs = retbuf[1]; + + return rc; +} + +/* + * parse_ppp_data + * Parse out the data returned from h_get_ppp and h_pic + */ +static void parse_ppp_data(struct seq_file *m) +{ + struct hvcall_ppp_data ppp_data; + struct device_node *root; + const __be32 *perf_level; + int rc; + + rc = h_get_ppp(&ppp_data); + if (rc) + return; + + seq_printf(m, "partition_entitled_capacity=%lld\n", + ppp_data.entitlement); + seq_printf(m, "group=%d\n", ppp_data.group_num); + seq_printf(m, "system_active_processors=%d\n", + ppp_data.active_system_procs); + + /* pool related entries are appropriate for shared configs */ + if (lppaca_shared_proc(get_lppaca())) { + unsigned long pool_idle_time, pool_procs; + + seq_printf(m, "pool=%d\n", ppp_data.pool_num); + + /* report pool_capacity in percentage */ + seq_printf(m, "pool_capacity=%d\n", + ppp_data.active_procs_in_pool * 100); + + h_pic(&pool_idle_time, &pool_procs); + seq_printf(m, "pool_idle_time=%ld\n", pool_idle_time); + seq_printf(m, "pool_num_procs=%ld\n", pool_procs); + } + + seq_printf(m, "unallocated_capacity_weight=%d\n", + ppp_data.unallocated_weight); + seq_printf(m, "capacity_weight=%d\n", ppp_data.weight); + seq_printf(m, "capped=%d\n", ppp_data.capped); + seq_printf(m, "unallocated_capacity=%lld\n", + ppp_data.unallocated_entitlement); + + /* The last bits of information returned from h_get_ppp are only + * valid if the ibm,partition-performance-parameters-level + * property is >= 1. + */ + root = of_find_node_by_path("/"); + if (root) { + perf_level = of_get_property(root, + "ibm,partition-performance-parameters-level", + NULL); + if (perf_level && (be32_to_cpup(perf_level) >= 1)) { + seq_printf(m, + "physical_procs_allocated_to_virtualization=%d\n", + ppp_data.phys_platform_procs); + seq_printf(m, "max_proc_capacity_available=%d\n", + ppp_data.max_proc_cap_avail); + seq_printf(m, "entitled_proc_capacity_available=%d\n", + ppp_data.entitled_proc_cap_avail); + } + + of_node_put(root); + } +} + +/** + * parse_mpp_data + * Parse out data returned from h_get_mpp + */ +static void parse_mpp_data(struct seq_file *m) +{ + struct hvcall_mpp_data mpp_data; + int rc; + + rc = h_get_mpp(&mpp_data); + if (rc) + return; + + seq_printf(m, "entitled_memory=%ld\n", mpp_data.entitled_mem); + + if (mpp_data.mapped_mem != -1) + seq_printf(m, "mapped_entitled_memory=%ld\n", + mpp_data.mapped_mem); + + seq_printf(m, "entitled_memory_group_number=%d\n", mpp_data.group_num); + seq_printf(m, "entitled_memory_pool_number=%d\n", mpp_data.pool_num); + + seq_printf(m, "entitled_memory_weight=%d\n", mpp_data.mem_weight); + seq_printf(m, "unallocated_entitled_memory_weight=%d\n", + mpp_data.unallocated_mem_weight); + seq_printf(m, "unallocated_io_mapping_entitlement=%ld\n", + mpp_data.unallocated_entitlement); + + if (mpp_data.pool_size != -1) + seq_printf(m, "entitled_memory_pool_size=%ld bytes\n", + mpp_data.pool_size); + + seq_printf(m, "entitled_memory_loan_request=%ld\n", + mpp_data.loan_request); + + seq_printf(m, "backing_memory=%ld bytes\n", mpp_data.backing_mem); +} + +/** + * parse_mpp_x_data + * Parse out data returned from h_get_mpp_x + */ +static void parse_mpp_x_data(struct seq_file *m) +{ + struct hvcall_mpp_x_data mpp_x_data; + + if (!firmware_has_feature(FW_FEATURE_XCMO)) + return; + if (h_get_mpp_x(&mpp_x_data)) + return; + + seq_printf(m, "coalesced_bytes=%ld\n", mpp_x_data.coalesced_bytes); + + if (mpp_x_data.pool_coalesced_bytes) + seq_printf(m, "pool_coalesced_bytes=%ld\n", + mpp_x_data.pool_coalesced_bytes); + if (mpp_x_data.pool_purr_cycles) + seq_printf(m, "coalesce_pool_purr=%ld\n", mpp_x_data.pool_purr_cycles); + if (mpp_x_data.pool_spurr_cycles) + seq_printf(m, "coalesce_pool_spurr=%ld\n", mpp_x_data.pool_spurr_cycles); +} + +#define SPLPAR_CHARACTERISTICS_TOKEN 20 +#define SPLPAR_MAXLENGTH 1026*(sizeof(char)) + +/* + * parse_system_parameter_string() + * Retrieve the potential_processors, max_entitled_capacity and friends + * through the get-system-parameter rtas call. Replace keyword strings as + * necessary. + */ +static void parse_system_parameter_string(struct seq_file *m) +{ + int call_status; + + unsigned char *local_buffer = kmalloc(SPLPAR_MAXLENGTH, GFP_KERNEL); + if (!local_buffer) { + printk(KERN_ERR "%s %s kmalloc failure at line %d\n", + __FILE__, __func__, __LINE__); + return; + } + + spin_lock(&rtas_data_buf_lock); + memset(rtas_data_buf, 0, SPLPAR_MAXLENGTH); + call_status = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1, + NULL, + SPLPAR_CHARACTERISTICS_TOKEN, + __pa(rtas_data_buf), + RTAS_DATA_BUF_SIZE); + memcpy(local_buffer, rtas_data_buf, SPLPAR_MAXLENGTH); + local_buffer[SPLPAR_MAXLENGTH - 1] = '\0'; + spin_unlock(&rtas_data_buf_lock); + + if (call_status != 0) { + printk(KERN_INFO + "%s %s Error calling get-system-parameter (0x%x)\n", + __FILE__, __func__, call_status); + } else { + int splpar_strlen; + int idx, w_idx; + char *workbuffer = kzalloc(SPLPAR_MAXLENGTH, GFP_KERNEL); + if (!workbuffer) { + printk(KERN_ERR "%s %s kmalloc failure at line %d\n", + __FILE__, __func__, __LINE__); + kfree(local_buffer); + return; + } +#ifdef LPARCFG_DEBUG + printk(KERN_INFO "success calling get-system-parameter\n"); +#endif + splpar_strlen = local_buffer[0] * 256 + local_buffer[1]; + local_buffer += 2; /* step over strlen value */ + + w_idx = 0; + idx = 0; + while ((*local_buffer) && (idx < splpar_strlen)) { + workbuffer[w_idx++] = local_buffer[idx++]; + if ((local_buffer[idx] == ',') + || (local_buffer[idx] == '\0')) { + workbuffer[w_idx] = '\0'; + if (w_idx) { + /* avoid the empty string */ + seq_printf(m, "%s\n", workbuffer); + } + memset(workbuffer, 0, SPLPAR_MAXLENGTH); + idx++; /* skip the comma */ + w_idx = 0; + } else if (local_buffer[idx] == '=') { + /* code here to replace workbuffer contents + with different keyword strings */ + if (0 == strcmp(workbuffer, "MaxEntCap")) { + strcpy(workbuffer, + "partition_max_entitled_capacity"); + w_idx = strlen(workbuffer); + } + if (0 == strcmp(workbuffer, "MaxPlatProcs")) { + strcpy(workbuffer, + "system_potential_processors"); + w_idx = strlen(workbuffer); + } + } + } + kfree(workbuffer); + local_buffer -= 2; /* back up over strlen value */ + } + kfree(local_buffer); +} + +/* Return the number of processors in the system. + * This function reads through the device tree and counts + * the virtual processors, this does not include threads. + */ +static int lparcfg_count_active_processors(void) +{ + struct device_node *cpus_dn = NULL; + int count = 0; + + while ((cpus_dn = of_find_node_by_type(cpus_dn, "cpu"))) { +#ifdef LPARCFG_DEBUG + printk(KERN_ERR "cpus_dn %p\n", cpus_dn); +#endif + count++; + } + return count; +} + +static void pseries_cmo_data(struct seq_file *m) +{ + int cpu; + unsigned long cmo_faults = 0; + unsigned long cmo_fault_time = 0; + + seq_printf(m, "cmo_enabled=%d\n", firmware_has_feature(FW_FEATURE_CMO)); + + if (!firmware_has_feature(FW_FEATURE_CMO)) + return; + + for_each_possible_cpu(cpu) { + cmo_faults += be64_to_cpu(lppaca_of(cpu).cmo_faults); + cmo_fault_time += be64_to_cpu(lppaca_of(cpu).cmo_fault_time); + } + + seq_printf(m, "cmo_faults=%lu\n", cmo_faults); + seq_printf(m, "cmo_fault_time_usec=%lu\n", + cmo_fault_time / tb_ticks_per_usec); + seq_printf(m, "cmo_primary_psp=%d\n", cmo_get_primary_psp()); + seq_printf(m, "cmo_secondary_psp=%d\n", cmo_get_secondary_psp()); + seq_printf(m, "cmo_page_size=%lu\n", cmo_get_page_size()); +} + +static void splpar_dispatch_data(struct seq_file *m) +{ + int cpu; + unsigned long dispatches = 0; + unsigned long dispatch_dispersions = 0; + + for_each_possible_cpu(cpu) { + dispatches += be32_to_cpu(lppaca_of(cpu).yield_count); + dispatch_dispersions += + be32_to_cpu(lppaca_of(cpu).dispersion_count); + } + + seq_printf(m, "dispatches=%lu\n", dispatches); + seq_printf(m, "dispatch_dispersions=%lu\n", dispatch_dispersions); +} + +static void parse_em_data(struct seq_file *m) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + + if (firmware_has_feature(FW_FEATURE_LPAR) && + plpar_hcall(H_GET_EM_PARMS, retbuf) == H_SUCCESS) + seq_printf(m, "power_mode_data=%016lx\n", retbuf[0]); +} + +static int pseries_lparcfg_data(struct seq_file *m, void *v) +{ + int partition_potential_processors; + int partition_active_processors; + struct device_node *rtas_node; + const __be32 *lrdrp = NULL; + + rtas_node = of_find_node_by_path("/rtas"); + if (rtas_node) + lrdrp = of_get_property(rtas_node, "ibm,lrdr-capacity", NULL); + + if (lrdrp == NULL) { + partition_potential_processors = vdso_data->processorCount; + } else { + partition_potential_processors = be32_to_cpup(lrdrp + 4); + } + of_node_put(rtas_node); + + partition_active_processors = lparcfg_count_active_processors(); + + if (firmware_has_feature(FW_FEATURE_SPLPAR)) { + /* this call handles the ibm,get-system-parameter contents */ + parse_system_parameter_string(m); + parse_ppp_data(m); + parse_mpp_data(m); + parse_mpp_x_data(m); + pseries_cmo_data(m); + splpar_dispatch_data(m); + + seq_printf(m, "purr=%ld\n", get_purr()); + } else { /* non SPLPAR case */ + + seq_printf(m, "system_active_processors=%d\n", + partition_potential_processors); + + seq_printf(m, "system_potential_processors=%d\n", + partition_potential_processors); + + seq_printf(m, "partition_max_entitled_capacity=%d\n", + partition_potential_processors * 100); + + seq_printf(m, "partition_entitled_capacity=%d\n", + partition_active_processors * 100); + } + + seq_printf(m, "partition_active_processors=%d\n", + partition_active_processors); + + seq_printf(m, "partition_potential_processors=%d\n", + partition_potential_processors); + + seq_printf(m, "shared_processor_mode=%d\n", + lppaca_shared_proc(get_lppaca())); + + seq_printf(m, "slb_size=%d\n", mmu_slb_size); + + parse_em_data(m); + + return 0; +} + +static ssize_t update_ppp(u64 *entitlement, u8 *weight) +{ + struct hvcall_ppp_data ppp_data; + u8 new_weight; + u64 new_entitled; + ssize_t retval; + + /* Get our current parameters */ + retval = h_get_ppp(&ppp_data); + if (retval) + return retval; + + if (entitlement) { + new_weight = ppp_data.weight; + new_entitled = *entitlement; + } else if (weight) { + new_weight = *weight; + new_entitled = ppp_data.entitlement; + } else + return -EINVAL; + + pr_debug("%s: current_entitled = %llu, current_weight = %u\n", + __func__, ppp_data.entitlement, ppp_data.weight); + + pr_debug("%s: new_entitled = %llu, new_weight = %u\n", + __func__, new_entitled, new_weight); + + retval = plpar_hcall_norets(H_SET_PPP, new_entitled, new_weight); + return retval; +} + +/** + * update_mpp + * + * Update the memory entitlement and weight for the partition. Caller must + * specify either a new entitlement or weight, not both, to be updated + * since the h_set_mpp call takes both entitlement and weight as parameters. + */ +static ssize_t update_mpp(u64 *entitlement, u8 *weight) +{ + struct hvcall_mpp_data mpp_data; + u64 new_entitled; + u8 new_weight; + ssize_t rc; + + if (entitlement) { + /* Check with vio to ensure the new memory entitlement + * can be handled. + */ + rc = vio_cmo_entitlement_update(*entitlement); + if (rc) + return rc; + } + + rc = h_get_mpp(&mpp_data); + if (rc) + return rc; + + if (entitlement) { + new_weight = mpp_data.mem_weight; + new_entitled = *entitlement; + } else if (weight) { + new_weight = *weight; + new_entitled = mpp_data.entitled_mem; + } else + return -EINVAL; + + pr_debug("%s: current_entitled = %lu, current_weight = %u\n", + __func__, mpp_data.entitled_mem, mpp_data.mem_weight); + + pr_debug("%s: new_entitled = %llu, new_weight = %u\n", + __func__, new_entitled, new_weight); + + rc = plpar_hcall_norets(H_SET_MPP, new_entitled, new_weight); + return rc; +} + +/* + * Interface for changing system parameters (variable capacity weight + * and entitled capacity). Format of input is "param_name=value"; + * anything after value is ignored. Valid parameters at this time are + * "partition_entitled_capacity" and "capacity_weight". We use + * H_SET_PPP to alter parameters. + * + * This function should be invoked only on systems with + * FW_FEATURE_SPLPAR. + */ +static ssize_t lparcfg_write(struct file *file, const char __user * buf, + size_t count, loff_t * off) +{ + int kbuf_sz = 64; + char kbuf[kbuf_sz]; + char *tmp; + u64 new_entitled, *new_entitled_ptr = &new_entitled; + u8 new_weight, *new_weight_ptr = &new_weight; + ssize_t retval; + + if (!firmware_has_feature(FW_FEATURE_SPLPAR)) + return -EINVAL; + + if (count > kbuf_sz) + return -EINVAL; + + if (copy_from_user(kbuf, buf, count)) + return -EFAULT; + + kbuf[count - 1] = '\0'; + tmp = strchr(kbuf, '='); + if (!tmp) + return -EINVAL; + + *tmp++ = '\0'; + + if (!strcmp(kbuf, "partition_entitled_capacity")) { + char *endp; + *new_entitled_ptr = (u64) simple_strtoul(tmp, &endp, 10); + if (endp == tmp) + return -EINVAL; + + retval = update_ppp(new_entitled_ptr, NULL); + } else if (!strcmp(kbuf, "capacity_weight")) { + char *endp; + *new_weight_ptr = (u8) simple_strtoul(tmp, &endp, 10); + if (endp == tmp) + return -EINVAL; + + retval = update_ppp(NULL, new_weight_ptr); + } else if (!strcmp(kbuf, "entitled_memory")) { + char *endp; + *new_entitled_ptr = (u64) simple_strtoul(tmp, &endp, 10); + if (endp == tmp) + return -EINVAL; + + retval = update_mpp(new_entitled_ptr, NULL); + } else if (!strcmp(kbuf, "entitled_memory_weight")) { + char *endp; + *new_weight_ptr = (u8) simple_strtoul(tmp, &endp, 10); + if (endp == tmp) + return -EINVAL; + + retval = update_mpp(NULL, new_weight_ptr); + } else + return -EINVAL; + + if (retval == H_SUCCESS || retval == H_CONSTRAINED) { + retval = count; + } else if (retval == H_BUSY) { + retval = -EBUSY; + } else if (retval == H_HARDWARE) { + retval = -EIO; + } else if (retval == H_PARAMETER) { + retval = -EINVAL; + } + + return retval; +} + +static int lparcfg_data(struct seq_file *m, void *v) +{ + struct device_node *rootdn; + const char *model = ""; + const char *system_id = ""; + const char *tmp; + const __be32 *lp_index_ptr; + unsigned int lp_index = 0; + + seq_printf(m, "%s %s\n", MODULE_NAME, MODULE_VERS); + + rootdn = of_find_node_by_path("/"); + if (rootdn) { + tmp = of_get_property(rootdn, "model", NULL); + if (tmp) + model = tmp; + tmp = of_get_property(rootdn, "system-id", NULL); + if (tmp) + system_id = tmp; + lp_index_ptr = of_get_property(rootdn, "ibm,partition-no", + NULL); + if (lp_index_ptr) + lp_index = be32_to_cpup(lp_index_ptr); + of_node_put(rootdn); + } + seq_printf(m, "serial_number=%s\n", system_id); + seq_printf(m, "system_type=%s\n", model); + seq_printf(m, "partition_id=%d\n", (int)lp_index); + + return pseries_lparcfg_data(m, v); +} + +static int lparcfg_open(struct inode *inode, struct file *file) +{ + return single_open(file, lparcfg_data, NULL); +} + +static const struct file_operations lparcfg_fops = { + .read = seq_read, + .write = lparcfg_write, + .open = lparcfg_open, + .release = single_release, + .llseek = seq_lseek, +}; + +static int __init lparcfg_init(void) +{ + umode_t mode = S_IRUSR | S_IRGRP | S_IROTH; + + /* Allow writing if we have FW_FEATURE_SPLPAR */ + if (firmware_has_feature(FW_FEATURE_SPLPAR)) + mode |= S_IWUSR; + + if (!proc_create("powerpc/lparcfg", mode, NULL, &lparcfg_fops)) { + printk(KERN_ERR "Failed to create powerpc/lparcfg\n"); + return -EIO; + } + return 0; +} +machine_device_initcall(pseries, lparcfg_init); diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 6573808cc5f..bde7ebad394 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -28,7 +28,7 @@ struct update_props_workarea { u32 state; u64 reserved; u32 nprops; -}; +} __packed; #define NODE_ACTION_MASK 0xff000000 #define NODE_COUNT_MASK 0x00ffffff @@ -37,14 +37,16 @@ struct update_props_workarea { #define UPDATE_DT_NODE 0x02000000 #define ADD_DT_NODE 0x03000000 -static int mobility_rtas_call(int token, char *buf) +#define MIGRATION_SCOPE (1) + +static int mobility_rtas_call(int token, char *buf, s32 scope) { int rc; spin_lock(&rtas_data_buf_lock); memcpy(rtas_data_buf, buf, RTAS_DATA_BUF_SIZE); - rc = rtas_call(token, 2, 1, NULL, rtas_data_buf, 1); + rc = rtas_call(token, 2, 1, NULL, rtas_data_buf, scope); memcpy(buf, rtas_data_buf, RTAS_DATA_BUF_SIZE); spin_unlock(&rtas_data_buf_lock); @@ -60,6 +62,7 @@ static int delete_dt_node(u32 phandle) return -ENOENT; dlpar_detach_node(dn); + of_node_put(dn); return 0; } @@ -117,21 +120,22 @@ static int update_dt_property(struct device_node *dn, struct property **prop, if (!more) { of_update_property(dn, new_prop); - new_prop = NULL; + *prop = NULL; } return 0; } -static int update_dt_node(u32 phandle) +static int update_dt_node(u32 phandle, s32 scope) { struct update_props_workarea *upwa; struct device_node *dn; struct property *prop = NULL; - int i, rc; + int i, rc, rtas_rc; char *prop_data; char *rtas_buf; int update_properties_token; + u32 vd; update_properties_token = rtas_token("ibm,update-properties"); if (update_properties_token == RTAS_UNKNOWN_SERVICE) @@ -151,19 +155,32 @@ static int update_dt_node(u32 phandle) upwa->phandle = phandle; do { - rc = mobility_rtas_call(update_properties_token, rtas_buf); - if (rc < 0) + rtas_rc = mobility_rtas_call(update_properties_token, rtas_buf, + scope); + if (rtas_rc < 0) break; prop_data = rtas_buf + sizeof(*upwa); + /* On the first call to ibm,update-properties for a node the + * the first property value descriptor contains an empty + * property name, the property value length encoded as u32, + * and the property value is the node path being updated. + */ + if (*prop_data == 0) { + prop_data++; + vd = *(u32 *)prop_data; + prop_data += vd + sizeof(vd); + upwa->nprops--; + } + for (i = 0; i < upwa->nprops; i++) { char *prop_name; - u32 vd; - prop_name = prop_data + 1; + prop_name = prop_data; prop_data += strlen(prop_name) + 1; - vd = *prop_data++; + vd = *(u32 *)prop_data; + prop_data += sizeof(vd); switch (vd) { case 0x00000000: @@ -187,7 +204,7 @@ static int update_dt_node(u32 phandle) prop_data += vd; } } - } while (rc == 1); + } while (rtas_rc == 1); of_node_put(dn); kfree(rtas_buf); @@ -200,17 +217,14 @@ static int add_dt_node(u32 parent_phandle, u32 drc_index) struct device_node *parent_dn; int rc; - dn = dlpar_configure_connector(drc_index); - if (!dn) + parent_dn = of_find_node_by_phandle(parent_phandle); + if (!parent_dn) return -ENOENT; - parent_dn = of_find_node_by_phandle(parent_phandle); - if (!parent_dn) { - dlpar_free_cc_nodes(dn); + dn = dlpar_configure_connector(drc_index, parent_dn); + if (!dn) return -ENOENT; - } - dn->parent = parent_dn; rc = dlpar_attach_node(dn); if (rc) dlpar_free_cc_nodes(dn); @@ -219,7 +233,7 @@ static int add_dt_node(u32 parent_phandle, u32 drc_index) return rc; } -static int pseries_devicetree_update(void) +int pseries_devicetree_update(s32 scope) { char *rtas_buf; u32 *data; @@ -235,7 +249,7 @@ static int pseries_devicetree_update(void) return -ENOMEM; do { - rc = mobility_rtas_call(update_nodes_token, rtas_buf); + rc = mobility_rtas_call(update_nodes_token, rtas_buf, scope); if (rc && rc != 1) break; @@ -256,7 +270,7 @@ static int pseries_devicetree_update(void) delete_dt_node(phandle); break; case UPDATE_DT_NODE: - update_dt_node(phandle); + update_dt_node(phandle, scope); break; case ADD_DT_NODE: drc_index = *data++; @@ -276,13 +290,6 @@ void post_mobility_fixup(void) int rc; int activate_fw_token; - rc = pseries_devicetree_update(); - if (rc) { - printk(KERN_ERR "Initial post-mobility device tree update " - "failed: %d\n", rc); - return; - } - activate_fw_token = rtas_token("ibm,activate-firmware"); if (activate_fw_token == RTAS_UNKNOWN_SERVICE) { printk(KERN_ERR "Could not make post-mobility " @@ -290,16 +297,17 @@ void post_mobility_fixup(void) return; } - rc = rtas_call(activate_fw_token, 0, 1, NULL); - if (!rc) { - rc = pseries_devicetree_update(); - if (rc) - printk(KERN_ERR "Secondary post-mobility device tree " - "update failed: %d\n", rc); - } else { + do { + rc = rtas_call(activate_fw_token, 0, 1, NULL); + } while (rtas_busy_delay(rc)); + + if (rc) printk(KERN_ERR "Post-mobility activate-fw failed: %d\n", rc); - return; - } + + rc = pseries_devicetree_update(MIGRATION_SCOPE); + if (rc) + printk(KERN_ERR "Post-mobility device tree update " + "failed: %d\n", rc); return; } diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index e5b08472313..0c882e83c4c 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -24,26 +24,7 @@ static int query_token, change_token; #define RTAS_RESET_FN 2 #define RTAS_CHANGE_MSI_FN 3 #define RTAS_CHANGE_MSIX_FN 4 - -static struct pci_dn *get_pdn(struct pci_dev *pdev) -{ - struct device_node *dn; - struct pci_dn *pdn; - - dn = pci_device_to_OF_node(pdev); - if (!dn) { - dev_dbg(&pdev->dev, "rtas_msi: No OF device node\n"); - return NULL; - } - - pdn = PCI_DN(dn); - if (!pdn) { - dev_dbg(&pdev->dev, "rtas_msi: No PCI DN\n"); - return NULL; - } - - return pdn; -} +#define RTAS_CHANGE_32MSI_FN 5 /* RTAS Helpers */ @@ -58,7 +39,8 @@ static int rtas_change_msi(struct pci_dn *pdn, u32 func, u32 num_irqs) seq_num = 1; do { - if (func == RTAS_CHANGE_MSI_FN || func == RTAS_CHANGE_MSIX_FN) + if (func == RTAS_CHANGE_MSI_FN || func == RTAS_CHANGE_MSIX_FN || + func == RTAS_CHANGE_32MSI_FN) rc = rtas_call(change_token, 6, 4, rtas_ret, addr, BUID_HI(buid), BUID_LO(buid), func, num_irqs, seq_num); @@ -89,7 +71,7 @@ static void rtas_disable_msi(struct pci_dev *pdev) { struct pci_dn *pdn; - pdn = get_pdn(pdev); + pdn = pci_get_pdn(pdev); if (!pdn) return; @@ -148,27 +130,29 @@ static int check_req(struct pci_dev *pdev, int nvec, char *prop_name) { struct device_node *dn; struct pci_dn *pdn; - const u32 *req_msi; + const __be32 *p; + u32 req_msi; - pdn = get_pdn(pdev); + pdn = pci_get_pdn(pdev); if (!pdn) return -ENODEV; dn = pdn->node; - req_msi = of_get_property(dn, prop_name, NULL); - if (!req_msi) { + p = of_get_property(dn, prop_name, NULL); + if (!p) { pr_debug("rtas_msi: No %s on %s\n", prop_name, dn->full_name); return -ENOENT; } - if (*req_msi < nvec) { + req_msi = be32_to_cpup(p); + if (req_msi < nvec) { pr_debug("rtas_msi: %s requests < %d MSIs\n", prop_name, nvec); - if (*req_msi == 0) /* Be paranoid */ + if (req_msi == 0) /* Be paranoid */ return -ENOSPC; - return *req_msi; + return req_msi; } return 0; @@ -189,7 +173,7 @@ static int check_req_msix(struct pci_dev *pdev, int nvec) static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total) { struct device_node *dn; - const u32 *p; + const __be32 *p; dn = of_node_get(pci_device_to_OF_node(dev)); while (dn) { @@ -197,7 +181,7 @@ static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total) if (p) { pr_debug("rtas_msi: found prop on dn %s\n", dn->full_name); - *total = *p; + *total = be32_to_cpup(p); return dn; } @@ -250,13 +234,13 @@ struct msi_counts { static void *count_non_bridge_devices(struct device_node *dn, void *data) { struct msi_counts *counts = data; - const u32 *p; + const __be32 *p; u32 class; pr_debug("rtas_msi: counting %s\n", dn->full_name); p = of_get_property(dn, "class-code", NULL); - class = p ? *p : 0; + class = p ? be32_to_cpup(p) : 0; if ((class >> 8) != PCI_CLASS_BRIDGE_PCI) counts->num_devices++; @@ -267,7 +251,7 @@ static void *count_non_bridge_devices(struct device_node *dn, void *data) static void *count_spare_msis(struct device_node *dn, void *data) { struct msi_counts *counts = data; - const u32 *p; + const __be32 *p; int req; if (dn == counts->requestor) @@ -278,11 +262,11 @@ static void *count_spare_msis(struct device_node *dn, void *data) req = 0; p = of_get_property(dn, "ibm,req#msi", NULL); if (p) - req = *p; + req = be32_to_cpup(p); p = of_get_property(dn, "ibm,req#msi-x", NULL); if (p) - req = max(req, (int)*p); + req = max(req, (int)be32_to_cpup(p)); } if (req < counts->quota) @@ -392,6 +376,23 @@ static int check_msix_entries(struct pci_dev *pdev) return 0; } +static void rtas_hack_32bit_msi_gen2(struct pci_dev *pdev) +{ + u32 addr_hi, addr_lo; + + /* + * We should only get in here for IODA1 configs. This is based on the + * fact that we using RTAS for MSIs, we don't have the 32 bit MSI RTAS + * support, and we are in a PCIe Gen2 slot. + */ + dev_info(&pdev->dev, + "rtas_msi: No 32 bit MSI firmware support, forcing 32 bit MSI\n"); + pci_read_config_dword(pdev, pdev->msi_cap + PCI_MSI_ADDRESS_HI, &addr_hi); + addr_lo = 0xffff0000 | ((addr_hi >> (48 - 32)) << 4); + pci_write_config_dword(pdev, pdev->msi_cap + PCI_MSI_ADDRESS_LO, addr_lo); + pci_write_config_dword(pdev, pdev->msi_cap + PCI_MSI_ADDRESS_HI, 0); +} + static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type) { struct pci_dn *pdn; @@ -399,8 +400,9 @@ static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type) struct msi_desc *entry; struct msi_msg msg; int nvec = nvec_in; + int use_32bit_msi_hack = 0; - pdn = get_pdn(pdev); + pdn = pci_get_pdn(pdev); if (!pdn) return -ENODEV; @@ -426,12 +428,31 @@ static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type) */ again: if (type == PCI_CAP_ID_MSI) { - rc = rtas_change_msi(pdn, RTAS_CHANGE_MSI_FN, nvec); + if (pdn->force_32bit_msi) { + rc = rtas_change_msi(pdn, RTAS_CHANGE_32MSI_FN, nvec); + if (rc < 0) { + /* + * We only want to run the 32 bit MSI hack below if + * the max bus speed is Gen2 speed + */ + if (pdev->bus->max_bus_speed != PCIE_SPEED_5_0GT) + return rc; + + use_32bit_msi_hack = 1; + } + } else + rc = -1; + + if (rc < 0) + rc = rtas_change_msi(pdn, RTAS_CHANGE_MSI_FN, nvec); if (rc < 0) { pr_debug("rtas_msi: trying the old firmware call.\n"); rc = rtas_change_msi(pdn, RTAS_CHANGE_FN, nvec); } + + if (use_32bit_msi_hack && rc > 0) + rtas_hack_32bit_msi_gen2(pdev); } else rc = rtas_change_msi(pdn, RTAS_CHANGE_MSIX_FN, nvec); @@ -512,3 +533,4 @@ static int rtas_msi_init(void) return 0; } arch_initcall(rtas_msi_init); + diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c index 8733a86ad52..0cc240b7f69 100644 --- a/arch/powerpc/platforms/pseries/nvram.c +++ b/arch/powerpc/platforms/pseries/nvram.c @@ -18,6 +18,7 @@ #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/kmsg_dump.h> +#include <linux/pstore.h> #include <linux/ctype.h> #include <linux/zlib.h> #include <asm/uaccess.h> @@ -29,14 +30,21 @@ /* 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 { - int error_type; - unsigned int seq_num; + __be32 error_type; + __be32 seq_num; }; struct nvram_os_partition { @@ -45,20 +53,23 @@ struct nvram_os_partition { 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 + .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 + .index = -1, + .os_partition = true }; static const char *pseries_nvram_os_partitions[] = { @@ -67,6 +78,12 @@ static const char *pseries_nvram_os_partitions[] = { 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); @@ -83,28 +100,28 @@ static unsigned long last_unread_rtas_event; /* timestamp */ * big_oops_buf[] holds the uncompressed text we're capturing. * - * oops_buf[] holds the compressed text, preceded by a prefix. - * The prefix is just a u16 holding the length of the compressed* text. - * (*Or uncompressed, if compression fails.) oops_buf[] gets written - * to NVRAM. + * 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_len points to the prefix. oops_data points to the compressed text. + * oops_log_info points to the header. oops_data points to the compressed text. * * +- oops_buf - * | +- oops_data - * v v - * +------------+-----------------------------------------------+ - * | length | text | - * | (2 bytes) | (oops_data_sz bytes) | - * +------------+-----------------------------------------------+ + * | +- oops_data + * v v + * +-----------+-----------+-----------+------------------------+ + * | version | length | timestamp | text | + * | (2 bytes) | (2 bytes) | (8 bytes) | (oops_data_sz bytes) | + * +-----------+-----------+-----------+------------------------+ * ^ - * +- oops_len + * +- 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 u16 *oops_len; static char *oops_data; static size_t oops_data_sz; @@ -114,6 +131,30 @@ static size_t oops_data_sz; #define MEM_LEVEL 4 static struct z_stream_s stream; +#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; +#endif + static ssize_t pSeries_nvram_read(char *buf, size_t count, loff_t *index) { unsigned int i; @@ -250,20 +291,20 @@ int nvram_write_os_partition(struct nvram_os_partition *part, char * buff, length = part->size; } - info.error_type = err_type; - info.seq_num = error_log_cnt; + 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", __FUNCTION__, rc); + 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", __FUNCTION__, rc); + pr_err("%s: Failed nvram_write (%d)\n", __func__, rc); return rc; } @@ -275,48 +316,71 @@ int nvram_write_error_log(char * buff, int length, { int rc = nvram_write_os_partition(&rtas_log_partition, buff, length, err_type, error_log_cnt); - if (!rc) + if (!rc) { last_unread_rtas_event = get_seconds(); +#ifdef CONFIG_PSTORE + last_rtas_event = get_seconds(); +#endif + } + return rc; } -/* nvram_read_error_log +/* nvram_read_partition * - * Reads nvram for error log for at most 'length' + * Reads nvram partition for at most 'length' */ -int nvram_read_error_log(char * buff, int length, - unsigned int * err_type, unsigned int * error_log_cnt) +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 (rtas_log_partition.index == -1) + if (part->index == -1) return -1; - if (length > rtas_log_partition.size) - length = rtas_log_partition.size; + if (length > part->size) + length = part->size; - tmp_index = rtas_log_partition.index; + tmp_index = part->index; - rc = ppc_md.nvram_read((char *)&info, sizeof(struct err_log_info), &tmp_index); - if (rc <= 0) { - printk(KERN_ERR "nvram_read_error_log: Failed nvram_read (%d)\n", rc); - return rc; + 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) { - printk(KERN_ERR "nvram_read_error_log: Failed nvram_read (%d)\n", rc); + pr_err("%s: Failed nvram_read (%d)\n", __func__, rc); return rc; } - *error_log_cnt = info.seq_num; - *err_type = info.error_type; + 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' + */ +int nvram_read_error_log(char *buff, int length, + unsigned int *err_type, unsigned int *error_log_cnt) +{ + return nvram_read_partition(&rtas_log_partition, buff, length, + err_type, error_log_cnt); +} + /* This doesn't actually zero anything, but it sets the event_logged * word to tell that this event is safely in syslog. */ @@ -364,9 +428,6 @@ static int __init pseries_nvram_init_os_partition(struct nvram_os_partition loff_t p; int size; - /* Scan nvram for partitions */ - nvram_scan_partitions(); - /* Look for ours */ p = nvram_find_partition(part->name, NVRAM_SIG_OS, &size); @@ -405,6 +466,267 @@ static int __init pseries_nvram_init_os_partition(struct nvram_os_partition 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 + * hasn't had a chance to read and process? Return 1 if so, else 0. + * + * 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) +{ + return (oops_log_partition.index == rtas_log_partition.index + && last_unread_rtas_event + && get_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; + + 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; @@ -425,9 +747,13 @@ static void __init nvram_init_oops_partition(int rtas_partition_exists) oops_log_partition.name); return; } - oops_len = (u16*) oops_buf; - oops_data = oops_buf + sizeof(u16); - oops_data_sz = oops_log_partition.size - sizeof(u16); + 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> @@ -437,8 +763,8 @@ static void __init nvram_init_oops_partition(int rtas_partition_exists) 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); + 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", @@ -465,6 +791,9 @@ static int __init pseries_nvram_init_log_partitions(void) { int rc; + /* Scan nvram for partitions */ + nvram_scan_partitions(); + rc = pseries_nvram_init_os_partition(&rtas_log_partition); nvram_init_oops_partition(rc == 0); return 0; @@ -474,7 +803,7 @@ machine_arch_initcall(pseries, pseries_nvram_init_log_partitions); int __init pSeries_nvram_init(void) { struct device_node *nvram; - const unsigned int *nbytes_p; + const __be32 *nbytes_p; unsigned int proplen; nvram = of_find_node_by_type(NULL, "nvram"); @@ -487,7 +816,7 @@ int __init pSeries_nvram_init(void) return -EIO; } - nvram_size = *nbytes_p; + nvram_size = be32_to_cpup(nbytes_p); nvram_fetch = rtas_token("nvram-fetch"); nvram_store = rtas_token("nvram-store"); @@ -501,70 +830,6 @@ int __init pSeries_nvram_init(void) 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 - * hasn't had a chance to read and process? Return 1 if so, else 0. - * - * 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) -{ - return (oops_log_partition.index == rtas_log_partition.index - && last_unread_rtas_event - && get_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) -{ - 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_len = (u16) zipped_len; - return 0; -} /* * This is our kmsg_dump callback, called after an oops or panic report @@ -576,6 +841,7 @@ static int zip_oops(size_t text_len) 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); @@ -602,7 +868,7 @@ static void oops_to_nvram(struct kmsg_dumper *dumper, break; default: pr_err("%s: ignoring unrecognized KMSG_DUMP_* reason %d\n", - __FUNCTION__, (int) reason); + __func__, (int) reason); return; } @@ -619,14 +885,17 @@ static void oops_to_nvram(struct kmsg_dumper *dumper, } if (rc != 0) { kmsg_dump_rewind(dumper); - kmsg_dump_get_buffer(dumper, true, + kmsg_dump_get_buffer(dumper, false, oops_data, oops_data_sz, &text_len); err_type = ERR_TYPE_KERNEL_PANIC; - *oops_len = (u16) text_len; + 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_len) + *oops_len), err_type, ++oops_count); + (int) (sizeof(*oops_hdr) + text_len), err_type, + ++oops_count); spin_unlock_irqrestore(&lock, flags); } diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c index 56b864d777e..c413ec158ff 100644 --- a/arch/powerpc/platforms/pseries/pci.c +++ b/arch/powerpc/platforms/pseries/pci.c @@ -40,7 +40,8 @@ void pcibios_name_device(struct pci_dev *dev) */ dn = pci_device_to_OF_node(dev); if (dn) { - const char *loc_code = of_get_property(dn, "ibm,loc-code", 0); + const char *loc_code = of_get_property(dn, "ibm,loc-code", + NULL); if (loc_code) { int loc_len = strlen(loc_code); if (loc_len < sizeof(dev->dev.name)) { @@ -107,3 +108,64 @@ static void fixup_winbond_82c105(struct pci_dev* dev) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_WINBOND, PCI_DEVICE_ID_WINBOND_82C105, fixup_winbond_82c105); + +int pseries_root_bridge_prepare(struct pci_host_bridge *bridge) +{ + struct device_node *dn, *pdn; + struct pci_bus *bus; + u32 pcie_link_speed_stats[2]; + int rc; + + bus = bridge->bus; + + dn = pcibios_get_phb_of_node(bus); + if (!dn) + return 0; + + for (pdn = dn; pdn != NULL; pdn = of_get_next_parent(pdn)) { + rc = of_property_read_u32_array(pdn, + "ibm,pcie-link-speed-stats", + &pcie_link_speed_stats[0], 2); + if (!rc) + break; + } + + of_node_put(pdn); + + if (rc) { + pr_err("no ibm,pcie-link-speed-stats property\n"); + return 0; + } + + switch (pcie_link_speed_stats[0]) { + case 0x01: + bus->max_bus_speed = PCIE_SPEED_2_5GT; + break; + case 0x02: + bus->max_bus_speed = PCIE_SPEED_5_0GT; + break; + case 0x04: + bus->max_bus_speed = PCIE_SPEED_8_0GT; + break; + default: + bus->max_bus_speed = PCI_SPEED_UNKNOWN; + break; + } + + switch (pcie_link_speed_stats[1]) { + case 0x01: + bus->cur_bus_speed = PCIE_SPEED_2_5GT; + break; + case 0x02: + bus->cur_bus_speed = PCIE_SPEED_5_0GT; + break; + case 0x04: + bus->cur_bus_speed = PCIE_SPEED_8_0GT; + break; + default: + bus->cur_bus_speed = PCI_SPEED_UNKNOWN; + break; + } + + return 0; +} diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index c91b22be928..203cbf0dc10 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -37,15 +37,15 @@ find_bus_among_children(struct pci_bus *bus, struct device_node *dn) { struct pci_bus *child = NULL; - struct list_head *tmp; + struct pci_bus *tmp; struct device_node *busdn; busdn = pci_bus_to_OF_node(bus); if (busdn == dn) return bus; - list_for_each(tmp, &bus->children) { - child = find_bus_among_children(pci_bus_b(tmp), dn); + list_for_each_entry(tmp, &bus->children, node) { + child = find_bus_among_children(tmp, dn); if (child) break; }; @@ -64,91 +64,6 @@ pcibios_find_pci_bus(struct device_node *dn) } EXPORT_SYMBOL_GPL(pcibios_find_pci_bus); -/** - * __pcibios_remove_pci_devices - remove all devices under this bus - * @bus: the indicated PCI bus - * @purge_pe: destroy the PE on removal of PCI devices - * - * Remove all of the PCI devices under this bus both from the - * linux pci device tree, and from the powerpc EEH address cache. - * By default, the corresponding PE will be destroied during the - * normal PCI hotplug path. For PCI hotplug during EEH recovery, - * the corresponding PE won't be destroied and deallocated. - */ -void __pcibios_remove_pci_devices(struct pci_bus *bus, int purge_pe) -{ - struct pci_dev *dev, *tmp; - struct pci_bus *child_bus; - - /* First go down child busses */ - list_for_each_entry(child_bus, &bus->children, node) - __pcibios_remove_pci_devices(child_bus, purge_pe); - - pr_debug("PCI: Removing devices on bus %04x:%02x\n", - pci_domain_nr(bus), bus->number); - list_for_each_entry_safe(dev, tmp, &bus->devices, bus_list) { - pr_debug(" * Removing %s...\n", pci_name(dev)); - eeh_remove_bus_device(dev, purge_pe); - pci_stop_and_remove_bus_device(dev); - } -} - -/** - * pcibios_remove_pci_devices - remove all devices under this bus - * - * Remove all of the PCI devices under this bus both from the - * linux pci device tree, and from the powerpc EEH address cache. - */ -void pcibios_remove_pci_devices(struct pci_bus *bus) -{ - __pcibios_remove_pci_devices(bus, 1); -} -EXPORT_SYMBOL_GPL(pcibios_remove_pci_devices); - -/** - * pcibios_add_pci_devices - adds new pci devices to bus - * - * This routine will find and fixup new pci devices under - * the indicated bus. This routine presumes that there - * might already be some devices under this bridge, so - * it carefully tries to add only new devices. (And that - * is how this routine differs from other, similar pcibios - * routines.) - */ -void pcibios_add_pci_devices(struct pci_bus * bus) -{ - int slotno, num, mode, pass, max; - struct pci_dev *dev; - struct device_node *dn = pci_bus_to_OF_node(bus); - - eeh_add_device_tree_early(dn); - - mode = PCI_PROBE_NORMAL; - if (ppc_md.pci_probe_mode) - mode = ppc_md.pci_probe_mode(bus); - - if (mode == PCI_PROBE_DEVTREE) { - /* use ofdt-based probe */ - of_rescan_bus(dn, bus); - } else if (mode == PCI_PROBE_NORMAL) { - /* use legacy probe */ - slotno = PCI_SLOT(PCI_DN(dn->child)->devfn); - num = pci_scan_slot(bus, PCI_DEVFN(slotno, 0)); - if (!num) - return; - pcibios_setup_bus_devices(bus); - max = bus->busn_res.start; - for (pass=0; pass < 2; pass++) - list_for_each_entry(dev, &bus->devices, bus_list) { - if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE || - dev->hdr_type == PCI_HEADER_TYPE_CARDBUS) - max = pci_scan_bridge(bus, dev, max, pass); - } - } - pcibios_finish_adding_to_bus(bus); -} -EXPORT_SYMBOL_GPL(pcibios_add_pci_devices); - struct pci_controller *init_phb_dynamic(struct device_node *dn) { struct pci_controller *phb; diff --git a/arch/powerpc/platforms/pseries/plpar_wrappers.h b/arch/powerpc/platforms/pseries/plpar_wrappers.h deleted file mode 100644 index e6cc34a6705..00000000000 --- a/arch/powerpc/platforms/pseries/plpar_wrappers.h +++ /dev/null @@ -1,307 +0,0 @@ -#ifndef _PSERIES_PLPAR_WRAPPERS_H -#define _PSERIES_PLPAR_WRAPPERS_H - -#include <linux/string.h> - -#include <asm/hvcall.h> -#include <asm/paca.h> -#include <asm/page.h> - -/* Get state of physical CPU from query_cpu_stopped */ -int smp_query_cpu_stopped(unsigned int pcpu); -#define QCSS_STOPPED 0 -#define QCSS_STOPPING 1 -#define QCSS_NOT_STOPPED 2 -#define QCSS_HARDWARE_ERROR -1 -#define QCSS_HARDWARE_BUSY -2 - -static inline long poll_pending(void) -{ - return plpar_hcall_norets(H_POLL_PENDING); -} - -static inline u8 get_cede_latency_hint(void) -{ - return get_lppaca()->cede_latency_hint; -} - -static inline void set_cede_latency_hint(u8 latency_hint) -{ - get_lppaca()->cede_latency_hint = latency_hint; -} - -static inline long cede_processor(void) -{ - return plpar_hcall_norets(H_CEDE); -} - -static inline long extended_cede_processor(unsigned long latency_hint) -{ - long rc; - u8 old_latency_hint = get_cede_latency_hint(); - - set_cede_latency_hint(latency_hint); - rc = cede_processor(); - set_cede_latency_hint(old_latency_hint); - - return rc; -} - -static inline long vpa_call(unsigned long flags, unsigned long cpu, - unsigned long vpa) -{ - /* flags are in bits 16-18 (counting from most significant bit) */ - flags = flags << (63 - 18); - - return plpar_hcall_norets(H_REGISTER_VPA, flags, cpu, vpa); -} - -static inline long unregister_vpa(unsigned long cpu) -{ - return vpa_call(0x5, cpu, 0); -} - -static inline long register_vpa(unsigned long cpu, unsigned long vpa) -{ - return vpa_call(0x1, cpu, vpa); -} - -static inline long unregister_slb_shadow(unsigned long cpu) -{ - return vpa_call(0x7, cpu, 0); -} - -static inline long register_slb_shadow(unsigned long cpu, unsigned long vpa) -{ - return vpa_call(0x3, cpu, vpa); -} - -static inline long unregister_dtl(unsigned long cpu) -{ - return vpa_call(0x6, cpu, 0); -} - -static inline long register_dtl(unsigned long cpu, unsigned long vpa) -{ - return vpa_call(0x2, cpu, vpa); -} - -static inline long plpar_page_set_loaned(unsigned long vpa) -{ - unsigned long cmo_page_sz = cmo_get_page_size(); - long rc = 0; - int i; - - for (i = 0; !rc && i < PAGE_SIZE; i += cmo_page_sz) - rc = plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_LOANED, vpa + i, 0); - - for (i -= cmo_page_sz; rc && i != 0; i -= cmo_page_sz) - plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_ACTIVE, - vpa + i - cmo_page_sz, 0); - - return rc; -} - -static inline long plpar_page_set_active(unsigned long vpa) -{ - unsigned long cmo_page_sz = cmo_get_page_size(); - long rc = 0; - int i; - - for (i = 0; !rc && i < PAGE_SIZE; i += cmo_page_sz) - rc = plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_ACTIVE, vpa + i, 0); - - for (i -= cmo_page_sz; rc && i != 0; i -= cmo_page_sz) - plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_LOANED, - vpa + i - cmo_page_sz, 0); - - return rc; -} - -extern void vpa_init(int cpu); - -static inline long plpar_pte_enter(unsigned long flags, - unsigned long hpte_group, unsigned long hpte_v, - unsigned long hpte_r, unsigned long *slot) -{ - long rc; - unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; - - rc = plpar_hcall(H_ENTER, retbuf, flags, hpte_group, hpte_v, hpte_r); - - *slot = retbuf[0]; - - return rc; -} - -static inline long plpar_pte_remove(unsigned long flags, unsigned long ptex, - unsigned long avpn, unsigned long *old_pteh_ret, - unsigned long *old_ptel_ret) -{ - long rc; - unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; - - rc = plpar_hcall(H_REMOVE, retbuf, flags, ptex, avpn); - - *old_pteh_ret = retbuf[0]; - *old_ptel_ret = retbuf[1]; - - return rc; -} - -/* plpar_pte_remove_raw can be called in real mode. It calls plpar_hcall_raw */ -static inline long plpar_pte_remove_raw(unsigned long flags, unsigned long ptex, - unsigned long avpn, unsigned long *old_pteh_ret, - unsigned long *old_ptel_ret) -{ - long rc; - unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; - - rc = plpar_hcall_raw(H_REMOVE, retbuf, flags, ptex, avpn); - - *old_pteh_ret = retbuf[0]; - *old_ptel_ret = retbuf[1]; - - return rc; -} - -static inline long plpar_pte_read(unsigned long flags, unsigned long ptex, - unsigned long *old_pteh_ret, unsigned long *old_ptel_ret) -{ - long rc; - unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; - - rc = plpar_hcall(H_READ, retbuf, flags, ptex); - - *old_pteh_ret = retbuf[0]; - *old_ptel_ret = retbuf[1]; - - return rc; -} - -/* plpar_pte_read_raw can be called in real mode. It calls plpar_hcall_raw */ -static inline long plpar_pte_read_raw(unsigned long flags, unsigned long ptex, - unsigned long *old_pteh_ret, unsigned long *old_ptel_ret) -{ - long rc; - unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; - - rc = plpar_hcall_raw(H_READ, retbuf, flags, ptex); - - *old_pteh_ret = retbuf[0]; - *old_ptel_ret = retbuf[1]; - - return rc; -} - -/* - * plpar_pte_read_4_raw can be called in real mode. - * ptes must be 8*sizeof(unsigned long) - */ -static inline long plpar_pte_read_4_raw(unsigned long flags, unsigned long ptex, - unsigned long *ptes) - -{ - long rc; - unsigned long retbuf[PLPAR_HCALL9_BUFSIZE]; - - rc = plpar_hcall9_raw(H_READ, retbuf, flags | H_READ_4, ptex); - - memcpy(ptes, retbuf, 8*sizeof(unsigned long)); - - return rc; -} - -static inline long plpar_pte_protect(unsigned long flags, unsigned long ptex, - unsigned long avpn) -{ - return plpar_hcall_norets(H_PROTECT, flags, ptex, avpn); -} - -static inline long plpar_tce_get(unsigned long liobn, unsigned long ioba, - unsigned long *tce_ret) -{ - long rc; - unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; - - rc = plpar_hcall(H_GET_TCE, retbuf, liobn, ioba); - - *tce_ret = retbuf[0]; - - return rc; -} - -static inline long plpar_tce_put(unsigned long liobn, unsigned long ioba, - unsigned long tceval) -{ - return plpar_hcall_norets(H_PUT_TCE, liobn, ioba, tceval); -} - -static inline long plpar_tce_put_indirect(unsigned long liobn, - unsigned long ioba, unsigned long page, unsigned long count) -{ - return plpar_hcall_norets(H_PUT_TCE_INDIRECT, liobn, ioba, page, count); -} - -static inline long plpar_tce_stuff(unsigned long liobn, unsigned long ioba, - unsigned long tceval, unsigned long count) -{ - return plpar_hcall_norets(H_STUFF_TCE, liobn, ioba, tceval, count); -} - -static inline long plpar_get_term_char(unsigned long termno, - unsigned long *len_ret, char *buf_ret) -{ - long rc; - unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; - unsigned long *lbuf = (unsigned long *)buf_ret; /* TODO: alignment? */ - - rc = plpar_hcall(H_GET_TERM_CHAR, retbuf, termno); - - *len_ret = retbuf[0]; - lbuf[0] = retbuf[1]; - lbuf[1] = retbuf[2]; - - return rc; -} - -static inline long plpar_put_term_char(unsigned long termno, unsigned long len, - const char *buffer) -{ - unsigned long *lbuf = (unsigned long *)buffer; /* TODO: alignment? */ - return plpar_hcall_norets(H_PUT_TERM_CHAR, termno, len, lbuf[0], - lbuf[1]); -} - -/* Set various resource mode parameters */ -static inline long plpar_set_mode(unsigned long mflags, unsigned long resource, - unsigned long value1, unsigned long value2) -{ - return plpar_hcall_norets(H_SET_MODE, mflags, resource, value1, value2); -} - -/* - * Enable relocation on exceptions on this partition - * - * Note: this call has a partition wide scope and can take a while to complete. - * If it returns H_LONG_BUSY_* it should be retried periodically until it - * returns H_SUCCESS. - */ -static inline long enable_reloc_on_exceptions(void) -{ - /* mflags = 3: Exceptions at 0xC000000000004000 */ - return plpar_set_mode(3, 3, 0, 0); -} - -/* - * Disable relocation on exceptions on this partition - * - * Note: this call has a partition wide scope and can take a while to complete. - * If it returns H_LONG_BUSY_* it should be retried periodically until it - * returns H_SUCCESS. - */ -static inline long disable_reloc_on_exceptions(void) { - return plpar_set_mode(0, 3, 0, 0); -} - -#endif /* _PSERIES_PLPAR_WRAPPERS_H */ diff --git a/arch/powerpc/platforms/pseries/processor_idle.c b/arch/powerpc/platforms/pseries/processor_idle.c deleted file mode 100644 index 4d806b41960..00000000000 --- a/arch/powerpc/platforms/pseries/processor_idle.c +++ /dev/null @@ -1,368 +0,0 @@ -/* - * processor_idle - idle state cpuidle driver. - * Adapted from drivers/idle/intel_idle.c and - * drivers/acpi/processor_idle.c - * - */ - -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/init.h> -#include <linux/moduleparam.h> -#include <linux/cpuidle.h> -#include <linux/cpu.h> -#include <linux/notifier.h> - -#include <asm/paca.h> -#include <asm/reg.h> -#include <asm/machdep.h> -#include <asm/firmware.h> -#include <asm/runlatch.h> - -#include "plpar_wrappers.h" -#include "pseries.h" - -struct cpuidle_driver pseries_idle_driver = { - .name = "pseries_idle", - .owner = THIS_MODULE, -}; - -#define MAX_IDLE_STATE_COUNT 2 - -static int max_idle_state = MAX_IDLE_STATE_COUNT - 1; -static struct cpuidle_device __percpu *pseries_cpuidle_devices; -static struct cpuidle_state *cpuidle_state_table; - -static inline void idle_loop_prolog(unsigned long *in_purr, ktime_t *kt_before) -{ - - *kt_before = ktime_get(); - *in_purr = mfspr(SPRN_PURR); - /* - * Indicate to the HV that we are idle. Now would be - * a good time to find other work to dispatch. - */ - get_lppaca()->idle = 1; -} - -static inline s64 idle_loop_epilog(unsigned long in_purr, ktime_t kt_before) -{ - get_lppaca()->wait_state_cycles += mfspr(SPRN_PURR) - in_purr; - get_lppaca()->idle = 0; - - return ktime_to_us(ktime_sub(ktime_get(), kt_before)); -} - -static int snooze_loop(struct cpuidle_device *dev, - struct cpuidle_driver *drv, - int index) -{ - unsigned long in_purr; - ktime_t kt_before; - int cpu = dev->cpu; - - idle_loop_prolog(&in_purr, &kt_before); - local_irq_enable(); - set_thread_flag(TIF_POLLING_NRFLAG); - - while ((!need_resched()) && cpu_online(cpu)) { - ppc64_runlatch_off(); - HMT_low(); - HMT_very_low(); - } - - HMT_medium(); - clear_thread_flag(TIF_POLLING_NRFLAG); - smp_mb(); - - dev->last_residency = - (int)idle_loop_epilog(in_purr, kt_before); - return index; -} - -static void check_and_cede_processor(void) -{ - /* - * Ensure our interrupt state is properly tracked, - * also checks if no interrupt has occurred while we - * were soft-disabled - */ - if (prep_irq_for_idle()) { - cede_processor(); -#ifdef CONFIG_TRACE_IRQFLAGS - /* Ensure that H_CEDE returns with IRQs on */ - if (WARN_ON(!(mfmsr() & MSR_EE))) - __hard_irq_enable(); -#endif - } -} - -static int dedicated_cede_loop(struct cpuidle_device *dev, - struct cpuidle_driver *drv, - int index) -{ - unsigned long in_purr; - ktime_t kt_before; - - idle_loop_prolog(&in_purr, &kt_before); - get_lppaca()->donate_dedicated_cpu = 1; - - ppc64_runlatch_off(); - HMT_medium(); - check_and_cede_processor(); - - get_lppaca()->donate_dedicated_cpu = 0; - dev->last_residency = - (int)idle_loop_epilog(in_purr, kt_before); - return index; -} - -static int shared_cede_loop(struct cpuidle_device *dev, - struct cpuidle_driver *drv, - int index) -{ - unsigned long in_purr; - ktime_t kt_before; - - idle_loop_prolog(&in_purr, &kt_before); - - /* - * Yield the processor to the hypervisor. We return if - * an external interrupt occurs (which are driven prior - * to returning here) or if a prod occurs from another - * processor. When returning here, external interrupts - * are enabled. - */ - check_and_cede_processor(); - - dev->last_residency = - (int)idle_loop_epilog(in_purr, kt_before); - return index; -} - -/* - * States for dedicated partition case. - */ -static struct cpuidle_state dedicated_states[MAX_IDLE_STATE_COUNT] = { - { /* Snooze */ - .name = "snooze", - .desc = "snooze", - .flags = CPUIDLE_FLAG_TIME_VALID, - .exit_latency = 0, - .target_residency = 0, - .enter = &snooze_loop }, - { /* CEDE */ - .name = "CEDE", - .desc = "CEDE", - .flags = CPUIDLE_FLAG_TIME_VALID, - .exit_latency = 10, - .target_residency = 100, - .enter = &dedicated_cede_loop }, -}; - -/* - * States for shared partition case. - */ -static struct cpuidle_state shared_states[MAX_IDLE_STATE_COUNT] = { - { /* Shared Cede */ - .name = "Shared Cede", - .desc = "Shared Cede", - .flags = CPUIDLE_FLAG_TIME_VALID, - .exit_latency = 0, - .target_residency = 0, - .enter = &shared_cede_loop }, -}; - -void update_smt_snooze_delay(int cpu, int residency) -{ - struct cpuidle_driver *drv = cpuidle_get_driver(); - struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu); - - if (cpuidle_state_table != dedicated_states) - return; - - if (residency < 0) { - /* Disable the Nap state on that cpu */ - if (dev) - dev->states_usage[1].disable = 1; - } else - if (drv) - drv->states[1].target_residency = residency; -} - -static int pseries_cpuidle_add_cpu_notifier(struct notifier_block *n, - unsigned long action, void *hcpu) -{ - int hotcpu = (unsigned long)hcpu; - struct cpuidle_device *dev = - per_cpu_ptr(pseries_cpuidle_devices, hotcpu); - - if (dev && cpuidle_get_driver()) { - switch (action) { - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - cpuidle_pause_and_lock(); - cpuidle_enable_device(dev); - cpuidle_resume_and_unlock(); - break; - - case CPU_DEAD: - case CPU_DEAD_FROZEN: - cpuidle_pause_and_lock(); - cpuidle_disable_device(dev); - cpuidle_resume_and_unlock(); - break; - - default: - return NOTIFY_DONE; - } - } - return NOTIFY_OK; -} - -static struct notifier_block setup_hotplug_notifier = { - .notifier_call = pseries_cpuidle_add_cpu_notifier, -}; - -/* - * pseries_cpuidle_driver_init() - */ -static int pseries_cpuidle_driver_init(void) -{ - int idle_state; - struct cpuidle_driver *drv = &pseries_idle_driver; - - drv->state_count = 0; - - for (idle_state = 0; idle_state < MAX_IDLE_STATE_COUNT; ++idle_state) { - - if (idle_state > max_idle_state) - break; - - /* is the state not enabled? */ - if (cpuidle_state_table[idle_state].enter == NULL) - continue; - - drv->states[drv->state_count] = /* structure copy */ - cpuidle_state_table[idle_state]; - - drv->state_count += 1; - } - - return 0; -} - -/* pseries_idle_devices_uninit(void) - * unregister cpuidle devices and de-allocate memory - */ -static void pseries_idle_devices_uninit(void) -{ - int i; - struct cpuidle_device *dev; - - for_each_possible_cpu(i) { - dev = per_cpu_ptr(pseries_cpuidle_devices, i); - cpuidle_unregister_device(dev); - } - - free_percpu(pseries_cpuidle_devices); - return; -} - -/* pseries_idle_devices_init() - * allocate, initialize and register cpuidle device - */ -static int pseries_idle_devices_init(void) -{ - int i; - struct cpuidle_driver *drv = &pseries_idle_driver; - struct cpuidle_device *dev; - - pseries_cpuidle_devices = alloc_percpu(struct cpuidle_device); - if (pseries_cpuidle_devices == NULL) - return -ENOMEM; - - for_each_possible_cpu(i) { - dev = per_cpu_ptr(pseries_cpuidle_devices, i); - dev->state_count = drv->state_count; - dev->cpu = i; - if (cpuidle_register_device(dev)) { - printk(KERN_DEBUG \ - "cpuidle_register_device %d failed!\n", i); - return -EIO; - } - } - - return 0; -} - -/* - * pseries_idle_probe() - * Choose state table for shared versus dedicated partition - */ -static int pseries_idle_probe(void) -{ - - if (!firmware_has_feature(FW_FEATURE_SPLPAR)) - return -ENODEV; - - if (cpuidle_disable != IDLE_NO_OVERRIDE) - return -ENODEV; - - if (max_idle_state == 0) { - printk(KERN_DEBUG "pseries processor idle disabled.\n"); - return -EPERM; - } - - if (get_lppaca()->shared_proc) - cpuidle_state_table = shared_states; - else - cpuidle_state_table = dedicated_states; - - return 0; -} - -static int __init pseries_processor_idle_init(void) -{ - int retval; - - retval = pseries_idle_probe(); - if (retval) - return retval; - - pseries_cpuidle_driver_init(); - retval = cpuidle_register_driver(&pseries_idle_driver); - if (retval) { - printk(KERN_DEBUG "Registration of pseries driver failed.\n"); - return retval; - } - - retval = pseries_idle_devices_init(); - if (retval) { - pseries_idle_devices_uninit(); - cpuidle_unregister_driver(&pseries_idle_driver); - return retval; - } - - register_cpu_notifier(&setup_hotplug_notifier); - printk(KERN_DEBUG "pseries_idle_driver registered\n"); - - return 0; -} - -static void __exit pseries_processor_idle_exit(void) -{ - - unregister_cpu_notifier(&setup_hotplug_notifier); - pseries_idle_devices_uninit(); - cpuidle_unregister_driver(&pseries_idle_driver); - - return; -} - -module_init(pseries_processor_idle_init); -module_exit(pseries_processor_idle_exit); - -MODULE_AUTHOR("Deepthi Dharwar <deepthi@linux.vnet.ibm.com>"); -MODULE_DESCRIPTION("Cpuidle driver for POWER"); -MODULE_LICENSE("GPL"); diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 9a3dda07566..361add62abf 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -19,7 +19,10 @@ extern void request_event_sources_irqs(struct device_node *np, #include <linux/of.h> -extern void __init fw_feature_init(const char *hypertas, unsigned long len); +extern void __init fw_hypertas_feature_init(const char *hypertas, + unsigned long len); +extern void __init fw_vec5_feature_init(const char *hypertas, + unsigned long len); struct pt_regs; @@ -53,11 +56,14 @@ extern void hvc_vio_init_early(void); /* Dynamic logical Partitioning/Mobility */ extern void dlpar_free_cc_nodes(struct device_node *); extern void dlpar_free_cc_property(struct property *); -extern struct device_node *dlpar_configure_connector(u32); +extern struct device_node *dlpar_configure_connector(u32, struct device_node *); extern int dlpar_attach_node(struct device_node *); extern int dlpar_detach_node(struct device_node *); -/* Snooze Delay, pseries_idle */ -DECLARE_PER_CPU(long, smt_snooze_delay); +/* PCI root bridge prepare function override for pseries */ +struct pci_host_bridge; +int pseries_root_bridge_prepare(struct pci_host_bridge *bridge); + +unsigned long pseries_memory_block_size(void); #endif /* _PSERIES_PSERIES_H */ diff --git a/arch/powerpc/platforms/pseries/pseries_energy.c b/arch/powerpc/platforms/pseries/pseries_energy.c index af281dce510..92767791f93 100644 --- a/arch/powerpc/platforms/pseries/pseries_energy.c +++ b/arch/powerpc/platforms/pseries/pseries_energy.c @@ -21,6 +21,7 @@ #include <asm/cputhreads.h> #include <asm/page.h> #include <asm/hvcall.h> +#include <asm/firmware.h> #define MODULE_VERS "1.0" @@ -32,40 +33,6 @@ static int sysfs_entries; /* Helper routines */ -/* - * Routine to detect firmware support for hcall - * return 1 if H_BEST_ENERGY is supported - * else return 0 - */ - -static int check_for_h_best_energy(void) -{ - struct device_node *rtas = NULL; - const char *hypertas, *s; - int length; - int rc = 0; - - rtas = of_find_node_by_path("/rtas"); - if (!rtas) - return 0; - - hypertas = of_get_property(rtas, "ibm,hypertas-functions", &length); - if (!hypertas) { - of_node_put(rtas); - return 0; - } - - /* hypertas will have list of strings with hcall names */ - for (s = hypertas; s < hypertas + length; s += strlen(s) + 1) { - if (!strncmp("hcall-best-energy-1", s, 19)) { - rc = 1; /* Found the string */ - break; - } - } - of_node_put(rtas); - return rc; -} - /* Helper Routines to convert between drc_index to cpu numbers */ static u32 cpu_to_drc_index(int cpu) @@ -141,8 +108,8 @@ err: * energy consumption. */ -#define FLAGS_MODE1 0x004E200000080E01 -#define FLAGS_MODE2 0x004E200000080401 +#define FLAGS_MODE1 0x004E200000080E01UL +#define FLAGS_MODE2 0x004E200000080401UL #define FLAGS_ACTIVATE 0x100 static ssize_t get_best_energy_list(char *page, int activate) @@ -262,7 +229,7 @@ static int __init pseries_energy_init(void) int cpu, err; struct device *cpu_dev; - if (!check_for_h_best_energy()) { + if (!firmware_has_feature(FW_FEATURE_BEST_ENERGY)) { printk(KERN_INFO "Hypercall H_BEST_ENERGY not supported\n"); return 0; } diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index c4dfccd3a3d..9c5778e6ed4 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -83,7 +83,7 @@ static void handle_system_shutdown(char event_modifier) switch (event_modifier) { case EPOW_SHUTDOWN_NORMAL: pr_emerg("Firmware initiated power off"); - orderly_poweroff(1); + orderly_poweroff(true); break; case EPOW_SHUTDOWN_ON_UPS: @@ -95,13 +95,13 @@ static void handle_system_shutdown(char event_modifier) pr_emerg("Loss of system critical functions reported by " "firmware"); pr_emerg("Check RTAS error log for details"); - orderly_poweroff(1); + orderly_poweroff(true); break; case EPOW_SHUTDOWN_AMBIENT_TEMPERATURE_TOO_HIGH: pr_emerg("Ambient temperature too high reported by firmware"); pr_emerg("Check RTAS error log for details"); - orderly_poweroff(1); + orderly_poweroff(true); break; default: @@ -162,7 +162,7 @@ void rtas_parse_epow_errlog(struct rtas_error_log *log) case EPOW_SYSTEM_HALT: pr_emerg("Firmware initiated power off"); - orderly_poweroff(1); + orderly_poweroff(true); break; case EPOW_MAIN_ENCLOSURE: @@ -236,7 +236,8 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id) rtas_elog = (struct rtas_error_log *)ras_log_buf; - if ((status == 0) && (rtas_elog->severity >= RTAS_SEVERITY_ERROR_SYNC)) + if (status == 0 && + rtas_error_severity(rtas_elog) >= RTAS_SEVERITY_ERROR_SYNC) fatal = 1; else fatal = 0; @@ -287,6 +288,9 @@ static struct rtas_error_log *fwnmi_get_errinfo(struct pt_regs *regs) unsigned long *savep; struct rtas_error_log *h, *errhdr = NULL; + /* Mask top two bits */ + regs->gpr[3] &= ~(0x3UL << 62); + if (!VALID_FWNMI_BUFFER(regs->gpr[3])) { printk(KERN_ERR "FWNMI: corrupt r3 0x%016lx\n", regs->gpr[3]); return NULL; @@ -297,13 +301,14 @@ static struct rtas_error_log *fwnmi_get_errinfo(struct pt_regs *regs) /* If it isn't an extended log we can use the per cpu 64bit buffer */ h = (struct rtas_error_log *)&savep[1]; - if (!h->extended) { + if (!rtas_error_extended(h)) { memcpy(&__get_cpu_var(mce_data_buf), h, sizeof(__u64)); errhdr = (struct rtas_error_log *)&__get_cpu_var(mce_data_buf); } else { - int len; + int len, error_log_length; - len = max_t(int, 8+h->extended_log_length, RTAS_ERROR_LOG_MAX); + error_log_length = 8 + rtas_error_extended_log_length(h); + len = max_t(int, error_log_length, RTAS_ERROR_LOG_MAX); memset(global_mce_data_buf, 0, RTAS_ERROR_LOG_MAX); memcpy(global_mce_data_buf, h, len); errhdr = (struct rtas_error_log *)global_mce_data_buf; @@ -347,23 +352,24 @@ int pSeries_system_reset_exception(struct pt_regs *regs) static int recover_mce(struct pt_regs *regs, struct rtas_error_log *err) { int recovered = 0; + int disposition = rtas_error_disposition(err); if (!(regs->msr & MSR_RI)) { /* If MSR_RI isn't set, we cannot recover */ recovered = 0; - } else if (err->disposition == RTAS_DISP_FULLY_RECOVERED) { + } else if (disposition == RTAS_DISP_FULLY_RECOVERED) { /* Platform corrected itself */ recovered = 1; - } else if (err->disposition == RTAS_DISP_LIMITED_RECOVERY) { + } else if (disposition == RTAS_DISP_LIMITED_RECOVERY) { /* Platform corrected itself but could be degraded */ printk(KERN_ERR "MCE: limited recovery, system may " "be degraded\n"); recovered = 1; } else if (user_mode(regs) && !is_global_init(current) && - err->severity == RTAS_SEVERITY_ERROR_SYNC) { + rtas_error_severity(err) == RTAS_SEVERITY_ERROR_SYNC) { /* * If we received a synchronous error when in userspace diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c index d6491bd481d..1c0a60d9886 100644 --- a/arch/powerpc/platforms/pseries/reconfig.c +++ b/arch/powerpc/platforms/pseries/reconfig.c @@ -12,7 +12,6 @@ */ #include <linux/kernel.h> -#include <linux/kref.h> #include <linux/notifier.h> #include <linux/proc_fs.h> #include <linux/slab.h> @@ -70,7 +69,7 @@ static int pSeries_reconfig_add_node(const char *path, struct property *proplist np->properties = proplist; of_node_set_flag(np, OF_DYNAMIC); - kref_init(&np->kref); + of_node_init(np); np->parent = derive_parent(path); if (IS_ERR(np->parent)) { @@ -452,7 +451,7 @@ static int proc_ppc64_create_ofdt(void) ent = proc_create("powerpc/ofdt", S_IWUSR, NULL, &ofdt_fops); if (ent) - ent->size = 0; + proc_set_size(ent, 0); return 0; } diff --git a/arch/powerpc/platforms/pseries/rng.c b/arch/powerpc/platforms/pseries/rng.c new file mode 100644 index 00000000000..72a102758d4 --- /dev/null +++ b/arch/powerpc/platforms/pseries/rng.c @@ -0,0 +1,45 @@ +/* + * Copyright 2013, Michael Ellerman, 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. + */ + +#define pr_fmt(fmt) "pseries-rng: " fmt + +#include <linux/kernel.h> +#include <linux/of.h> +#include <asm/archrandom.h> +#include <asm/machdep.h> +#include <asm/plpar_wrappers.h> + + +static int pseries_get_random_long(unsigned long *v) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + + if (plpar_hcall(H_RANDOM, retbuf) == H_SUCCESS) { + *v = retbuf[0]; + return 1; + } + + return 0; +} + +static __init int rng_init(void) +{ + struct device_node *dn; + + dn = of_find_compatible_node(NULL, NULL, "ibm,random"); + if (!dn) + return -ENODEV; + + pr_info("Registering arch random hook.\n"); + + ppc_md.get_random_long = pseries_get_random_long; + + return 0; +} +subsys_initcall(rng_init); diff --git a/arch/powerpc/platforms/pseries/scanlog.c b/arch/powerpc/platforms/pseries/scanlog.c index 554457294a2..b502ab61aaf 100644 --- a/arch/powerpc/platforms/pseries/scanlog.c +++ b/arch/powerpc/platforms/pseries/scanlog.c @@ -41,21 +41,16 @@ static unsigned int ibm_scan_log_dump; /* RTAS token */ -static struct proc_dir_entry *proc_ppc64_scan_log_dump; /* The proc file */ +static unsigned int *scanlog_buffer; /* The data buffer */ static ssize_t scanlog_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { - struct inode * inode = file->f_path.dentry->d_inode; - struct proc_dir_entry *dp; - unsigned int *data; + unsigned int *data = scanlog_buffer; int status; unsigned long len, off; unsigned int wait_time; - dp = PDE(inode); - data = (unsigned int *)dp->data; - if (count > RTAS_DATA_BUF_SIZE) count = RTAS_DATA_BUF_SIZE; @@ -139,8 +134,7 @@ static ssize_t scanlog_write(struct file * file, const char __user * buf, static int scanlog_open(struct inode * inode, struct file * file) { - struct proc_dir_entry *dp = PDE(inode); - unsigned int *data = (unsigned int *)dp->data; + unsigned int *data = scanlog_buffer; if (data[0] != 0) { /* This imperfect test stops a second copy of the @@ -156,11 +150,9 @@ static int scanlog_open(struct inode * inode, struct file * file) static int scanlog_release(struct inode * inode, struct file * file) { - struct proc_dir_entry *dp = PDE(inode); - unsigned int *data = (unsigned int *)dp->data; + unsigned int *data = scanlog_buffer; data[0] = 0; - return 0; } @@ -176,7 +168,6 @@ const struct file_operations scanlog_fops = { static int __init scanlog_init(void) { struct proc_dir_entry *ent; - void *data; int err = -ENOMEM; ibm_scan_log_dump = rtas_token("ibm,scan-log-dump"); @@ -184,29 +175,24 @@ static int __init scanlog_init(void) return -ENODEV; /* Ideally we could allocate a buffer < 4G */ - data = kzalloc(RTAS_DATA_BUF_SIZE, GFP_KERNEL); - if (!data) + scanlog_buffer = kzalloc(RTAS_DATA_BUF_SIZE, GFP_KERNEL); + if (!scanlog_buffer) goto err; - ent = proc_create_data("powerpc/rtas/scan-log-dump", S_IRUSR, NULL, - &scanlog_fops, data); + ent = proc_create("powerpc/rtas/scan-log-dump", S_IRUSR, NULL, + &scanlog_fops); if (!ent) goto err; - - proc_ppc64_scan_log_dump = ent; - return 0; err: - kfree(data); + kfree(scanlog_buffer); return err; } static void __exit scanlog_cleanup(void) { - if (proc_ppc64_scan_log_dump) { - kfree(proc_ppc64_scan_log_dump->data); - remove_proc_entry("scan-log-dump", proc_ppc64_scan_log_dump->parent); - } + remove_proc_entry("powerpc/rtas/scan-log-dump", NULL); + kfree(scanlog_buffer); } module_init(scanlog_init); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index ca55882465d..f2f40e64658 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -39,7 +39,6 @@ #include <linux/irq.h> #include <linux/seq_file.h> #include <linux/root_dev.h> -#include <linux/cpuidle.h> #include <linux/of.h> #include <linux/kexec.h> @@ -65,13 +64,14 @@ #include <asm/smp.h> #include <asm/firmware.h> #include <asm/eeh.h> +#include <asm/reg.h> +#include <asm/plpar_wrappers.h> -#include "plpar_wrappers.h" #include "pseries.h" int CMO_PrPSP = -1; int CMO_SecPSP = -1; -unsigned long CMO_PageSize = (ASM_CONST(1) << IOMMU_PAGE_SHIFT); +unsigned long CMO_PageSize = (ASM_CONST(1) << IOMMU_PAGE_SHIFT_4K); EXPORT_SYMBOL(CMO_PageSize); int fwnmi_active; /* TRUE if an FWNMI handler is present */ @@ -182,7 +182,7 @@ static void __init pseries_mpic_init_IRQ(void) np = of_find_node_by_path("/"); naddr = of_n_addr_cells(np); opprop = of_get_property(np, "platform-open-pic", &opplen); - if (opprop != 0) { + if (opprop != NULL) { openpic_addr = of_read_number(opprop, naddr); printk(KERN_DEBUG "OpenPIC addr: %lx\n", openpic_addr); } @@ -281,7 +281,7 @@ static struct notifier_block pci_dn_reconfig_nb = { struct kmem_cache *dtl_cache; -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE /* * Allocate space for the dispatch trace log for all possible cpus * and register the buffers with the hypervisor. This is used for @@ -322,7 +322,7 @@ static int alloc_dispatch_logs(void) get_paca()->lppaca_ptr->dtl_idx = 0; /* hypervisor reads buffer length from this field */ - dtl->enqueue_to_dispatch_time = DISPATCH_LOG_BYTES; + dtl->enqueue_to_dispatch_time = cpu_to_be32(DISPATCH_LOG_BYTES); ret = register_dtl(hard_smp_processor_id(), __pa(dtl)); if (ret) pr_err("WARNING: DTL registration of cpu %d (hw %d) failed " @@ -332,12 +332,12 @@ static int alloc_dispatch_logs(void) return 0; } -#else /* !CONFIG_VIRT_CPU_ACCOUNTING */ +#else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ static inline int alloc_dispatch_logs(void) { return 0; } -#endif /* CONFIG_VIRT_CPU_ACCOUNTING */ +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ static int alloc_dispatch_log_kmem_cache(void) { @@ -353,19 +353,26 @@ static int alloc_dispatch_log_kmem_cache(void) } early_initcall(alloc_dispatch_log_kmem_cache); -static void pSeries_idle(void) +static void pseries_lpar_idle(void) { - /* This would call on the cpuidle framework, and the back-end pseries - * driver to go to idle states + /* + * Default handler to go into low thread priority and possibly + * low power mode by cedeing processor to hypervisor */ - if (cpuidle_idle_call()) { - /* On error, execute default handler - * to go into low thread priority and possibly - * low power mode. - */ - HMT_low(); - HMT_very_low(); - } + + /* Indicate to hypervisor that we are idle. */ + get_lppaca()->idle = 1; + + /* + * Yield the processor to the hypervisor. We return if + * an external interrupt occurs (which are driven prior + * to returning here) or if a prod occurs from another + * processor. When returning here, external interrupts + * are enabled. + */ + cede_processor(); + + get_lppaca()->idle = 0; } /* @@ -375,7 +382,7 @@ static void pSeries_idle(void) * to ever be a problem in practice we can move this into a kernel thread to * finish off the process later in boot. */ -static int __init pSeries_enable_reloc_on_exc(void) +long pSeries_enable_reloc_on_exc(void) { long rc; unsigned int delay, total_delay = 0; @@ -397,9 +404,9 @@ static int __init pSeries_enable_reloc_on_exc(void) mdelay(delay); } } +EXPORT_SYMBOL(pSeries_enable_reloc_on_exc); -#ifdef CONFIG_KEXEC -static long pSeries_disable_reloc_on_exc(void) +long pSeries_disable_reloc_on_exc(void) { long rc; @@ -410,13 +417,14 @@ static long pSeries_disable_reloc_on_exc(void) mdelay(get_longbusy_msecs(rc)); } } +EXPORT_SYMBOL(pSeries_disable_reloc_on_exc); +#ifdef CONFIG_KEXEC static void pSeries_machine_kexec(struct kimage *image) { long rc; - if (firmware_has_feature(FW_FEATURE_SET_MODE) && - (image->type != KEXEC_TYPE_CRASH)) { + if (firmware_has_feature(FW_FEATURE_SET_MODE)) { rc = pSeries_disable_reloc_on_exc(); if (rc != H_SUCCESS) pr_warning("Warning: Failed to disable relocation on " @@ -427,9 +435,35 @@ static void pSeries_machine_kexec(struct kimage *image) } #endif +#ifdef __LITTLE_ENDIAN__ +long pseries_big_endian_exceptions(void) +{ + long rc; + + while (1) { + rc = enable_big_endian_exceptions(); + if (!H_IS_LONG_BUSY(rc)) + return rc; + mdelay(get_longbusy_msecs(rc)); + } +} + +static long pseries_little_endian_exceptions(void) +{ + long rc; + + while (1) { + rc = enable_little_endian_exceptions(); + if (!H_IS_LONG_BUSY(rc)) + return rc; + mdelay(get_longbusy_msecs(rc)); + } +} +#endif + static void __init pSeries_setup_arch(void) { - panic_timeout = 10; + set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT); /* Discover PIC type and setup ppc_md accordingly */ pseries_discover_pic(); @@ -453,15 +487,16 @@ static void __init pSeries_setup_arch(void) pSeries_nvram_init(); - if (firmware_has_feature(FW_FEATURE_SPLPAR)) { + if (firmware_has_feature(FW_FEATURE_LPAR)) { vpa_init(boot_cpuid); - ppc_md.power_save = pSeries_idle; - } - - if (firmware_has_feature(FW_FEATURE_LPAR)) + ppc_md.power_save = pseries_lpar_idle; ppc_md.enable_pmcs = pseries_lpar_enable_pmcs; - else + } else { + /* No special idle routine */ ppc_md.enable_pmcs = power4_enable_pmcs; + } + + ppc_md.pcibios_root_bridge_prepare = pseries_root_bridge_prepare; if (firmware_has_feature(FW_FEATURE_SET_MODE)) { long rc; @@ -475,7 +510,11 @@ static void __init pSeries_setup_arch(void) static int __init pSeries_init_panel(void) { /* Manually leave the kernel version on the panel. */ +#ifdef __BIG_ENDIAN__ ppc_md.progress("Linux ppc64\n", 0); +#else + ppc_md.progress("Linux ppc64le\n", 0); +#endif ppc_md.progress(init_utsname()->version, 0); return 0; @@ -498,6 +537,14 @@ static int pseries_set_xdabr(unsigned long dabr, unsigned long dabrx) return plpar_hcall_norets(H_SET_XDABR, dabr, dabrx); } +static int pseries_set_dawr(unsigned long dawr, unsigned long dawrx) +{ + /* PAPR says we can't set HYP */ + dawrx &= ~DAWRX_HYP; + + return plapr_set_watchpoint0(dawr, dawrx); +} + #define CMO_CHARACTERISTICS_TOKEN 44 #define CMO_MAXLENGTH 1026 @@ -519,7 +566,7 @@ void pSeries_cmo_feature_init(void) { char *ptr, *key, *value, *end; int call_status; - int page_order = IOMMU_PAGE_SHIFT; + int page_order = IOMMU_PAGE_SHIFT_4K; pr_debug(" -> fw_cmo_feature_init()\n"); spin_lock(&rtas_data_buf_lock); @@ -604,6 +651,9 @@ static void __init pSeries_init_early(void) else if (firmware_has_feature(FW_FEATURE_DABR)) ppc_md.set_dabr = pseries_set_dabr; + if (firmware_has_feature(FW_FEATURE_SET_MODE)) + ppc_md.set_dawr = pseries_set_dawr; + pSeries_cmo_feature_init(); iommu_init_early_pSeries(); @@ -614,31 +664,45 @@ static void __init pSeries_init_early(void) * Called very early, MMU is off, device-tree isn't unflattened */ -static int __init pSeries_probe_hypertas(unsigned long node, - const char *uname, int depth, - void *data) +static int __init pseries_probe_fw_features(unsigned long node, + const char *uname, int depth, + void *data) { - const char *hypertas; - unsigned long len; + const char *prop; + int len; + static int hypertas_found; + static int vec5_found; - if (depth != 1 || - (strcmp(uname, "rtas") != 0 && strcmp(uname, "rtas@0") != 0)) + if (depth != 1) return 0; - hypertas = of_get_flat_dt_prop(node, "ibm,hypertas-functions", &len); - if (!hypertas) - return 1; + if (!strcmp(uname, "rtas") || !strcmp(uname, "rtas@0")) { + prop = of_get_flat_dt_prop(node, "ibm,hypertas-functions", + &len); + if (prop) { + powerpc_firmware_features |= FW_FEATURE_LPAR; + fw_hypertas_feature_init(prop, len); + } + + hypertas_found = 1; + } - powerpc_firmware_features |= FW_FEATURE_LPAR; - fw_feature_init(hypertas, len); + if (!strcmp(uname, "chosen")) { + prop = of_get_flat_dt_prop(node, "ibm,architecture-vec-5", + &len); + if (prop) + fw_vec5_feature_init(prop, len); - return 1; + vec5_found = 1; + } + + return hypertas_found && vec5_found; } static int __init pSeries_probe(void) { unsigned long root = of_get_flat_dt_root(); - char *dtype = of_get_flat_dt_prop(root, "device_type", NULL); + const char *dtype = of_get_flat_dt_prop(root, "device_type", NULL); if (dtype == NULL) return 0; @@ -655,7 +719,23 @@ static int __init pSeries_probe(void) pr_debug("pSeries detected, looking for LPAR capability...\n"); /* Now try to figure out if we are running on LPAR */ - of_scan_flat_dt(pSeries_probe_hypertas, NULL); + of_scan_flat_dt(pseries_probe_fw_features, NULL); + +#ifdef __LITTLE_ENDIAN__ + if (firmware_has_feature(FW_FEATURE_SET_MODE)) { + long rc; + /* + * Tell the hypervisor that we want our exceptions to + * be taken in little endian mode. If this fails we don't + * want to use BUG() because it will trigger an exception. + */ + rc = pseries_little_endian_exceptions(); + if (rc) { + ppc_md.progress("H_SET_MODE LE exception fail", 0); + panic("Could not enable little endian exceptions"); + } + } +#endif if (firmware_has_feature(FW_FEATURE_LPAR)) hpte_init_lpar(); @@ -730,4 +810,7 @@ define_machine(pseries) { #ifdef CONFIG_KEXEC .machine_kexec = pSeries_machine_kexec, #endif +#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE + .memory_block_size = pseries_memory_block_size, +#endif }; diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c index 80cd0be71e0..a3555b10c1a 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -42,8 +42,10 @@ #include <asm/vdso_datapage.h> #include <asm/cputhreads.h> #include <asm/xics.h> +#include <asm/dbell.h> +#include <asm/plpar_wrappers.h> +#include <asm/code-patching.h> -#include "plpar_wrappers.h" #include "pseries.h" #include "offline_states.h" @@ -54,6 +56,11 @@ */ static cpumask_var_t of_spin_mask; +/* + * If we multiplex IPI mechanisms, store the appropriate XICS IPI mechanism here + */ +static void (*xics_cause_ipi)(int cpu, unsigned long data); + /* Query where a cpu is now. Return codes #defined in plpar_wrappers.h */ int smp_query_cpu_stopped(unsigned int pcpu) { @@ -90,8 +97,8 @@ int smp_query_cpu_stopped(unsigned int pcpu) static inline int smp_startup_cpu(unsigned int lcpu) { int status; - unsigned long start_here = __pa((u32)*((unsigned long *) - generic_secondary_smp_init)); + unsigned long start_here = + __pa(ppc_function_entry(generic_secondary_smp_init)); unsigned int pcpu; int start_cpu; @@ -137,6 +144,8 @@ static void smp_xics_setup_cpu(int cpu) { if (cpu != boot_cpuid) xics_setup_cpu(); + if (cpu_has_feature(CPU_FTR_DBELL)) + doorbell_setup_this_cpu(); if (firmware_has_feature(FW_FEATURE_SPLPAR)) vpa_init(cpu); @@ -179,20 +188,25 @@ static int smp_pSeries_kick_cpu(int nr) return 0; } -static int smp_pSeries_cpu_bootable(unsigned int nr) +/* Only used on systems that support multiple IPI mechanisms */ +static void pSeries_cause_ipi_mux(int cpu, unsigned long data) { - /* Special case - we inhibit secondary thread startup - * during boot if the user requests it. - */ - if (system_state < SYSTEM_RUNNING && cpu_has_feature(CPU_FTR_SMT)) { - if (!smt_enabled_at_boot && cpu_thread_in_core(nr) != 0) - return 0; - if (smt_enabled_at_boot - && cpu_thread_in_core(nr) >= smt_enabled_at_boot) - return 0; + if (cpumask_test_cpu(cpu, cpu_sibling_mask(smp_processor_id()))) + doorbell_cause_ipi(cpu, data); + else + xics_cause_ipi(cpu, data); +} + +static __init int pSeries_smp_probe(void) +{ + int ret = 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 1; + return ret; } static struct smp_ops_t pSeries_mpic_smp_ops = { @@ -204,11 +218,11 @@ static struct smp_ops_t pSeries_mpic_smp_ops = { static struct smp_ops_t pSeries_xics_smp_ops = { .message_pass = NULL, /* Use smp_muxed_ipi_message_pass */ - .cause_ipi = NULL, /* Filled at runtime by xics_smp_probe() */ - .probe = xics_smp_probe, + .cause_ipi = NULL, /* Filled at runtime by pSeries_smp_probe() */ + .probe = pSeries_smp_probe, .kick_cpu = smp_pSeries_kick_cpu, .setup_cpu = smp_xics_setup_cpu, - .cpu_bootable = smp_pSeries_cpu_bootable, + .cpu_bootable = smp_generic_cpu_bootable, }; /* This is called very early */ @@ -220,18 +234,24 @@ static void __init smp_init_pseries(void) alloc_bootmem_cpumask_var(&of_spin_mask); - /* Mark threads which are still spinning in hold loops. */ - if (cpu_has_feature(CPU_FTR_SMT)) { - for_each_present_cpu(i) { - if (cpu_thread_in_core(i) == 0) - cpumask_set_cpu(i, of_spin_mask); - } - } else { - cpumask_copy(of_spin_mask, cpu_present_mask); + /* + * Mark threads which are still spinning in hold loops + * + * We know prom_init will not have started them if RTAS supports + * query-cpu-stopped-state. + */ + if (rtas_token("query-cpu-stopped-state") == RTAS_UNKNOWN_SERVICE) { + if (cpu_has_feature(CPU_FTR_SMT)) { + for_each_present_cpu(i) { + if (cpu_thread_in_core(i) == 0) + cpumask_set_cpu(i, of_spin_mask); + } + } else + cpumask_copy(of_spin_mask, cpu_present_mask); + + cpumask_clear_cpu(boot_cpuid, of_spin_mask); } - cpumask_clear_cpu(boot_cpuid, of_spin_mask); - /* Non-lpar has additional take/give timebase */ if (rtas_token("freeze-time-base") != RTAS_UNKNOWN_SERVICE) { smp_ops->give_timebase = rtas_give_timebase; diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c index 47226e04126..b87b97849d4 100644 --- a/arch/powerpc/platforms/pseries/suspend.c +++ b/arch/powerpc/platforms/pseries/suspend.c @@ -16,6 +16,7 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#include <linux/cpu.h> #include <linux/delay.h> #include <linux/suspend.h> #include <linux/stat.h> @@ -25,6 +26,7 @@ #include <asm/mmu.h> #include <asm/rtas.h> #include <asm/topology.h> +#include "../../kernel/cacheinfo.h" static u64 stream_id; static struct device suspend_dev; @@ -78,6 +80,23 @@ static int pseries_suspend_cpu(void) } /** + * pseries_suspend_enable_irqs + * + * Post suspend configuration updates + * + **/ +static void pseries_suspend_enable_irqs(void) +{ + /* + * Update configuration which can be modified based on device tree + * changes during resume. + */ + cacheinfo_cpu_offline(smp_processor_id()); + post_mobility_fixup(); + cacheinfo_cpu_online(smp_processor_id()); +} + +/** * pseries_suspend_enter - Final phase of hibernation * * Return value: @@ -105,7 +124,7 @@ static int pseries_prepare_late(void) atomic_set(&suspend_data.done, 0); atomic_set(&suspend_data.error, 0); suspend_data.complete = &suspend_work; - INIT_COMPLETION(suspend_work); + reinit_completion(&suspend_work); return 0; } @@ -126,11 +145,15 @@ static ssize_t store_hibernate(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { + cpumask_var_t offline_mask; int rc; if (!capable(CAP_SYS_ADMIN)) return -EPERM; + if (!alloc_cpumask_var(&offline_mask, GFP_TEMPORARY)) + return -ENOMEM; + stream_id = simple_strtoul(buf, NULL, 16); do { @@ -140,19 +163,59 @@ static ssize_t store_hibernate(struct device *dev, } while (rc == -EAGAIN); if (!rc) { + /* All present CPUs must be online */ + cpumask_andnot(offline_mask, cpu_present_mask, + cpu_online_mask); + rc = rtas_online_cpus_mask(offline_mask); + if (rc) { + pr_err("%s: Could not bring present CPUs online.\n", + __func__); + goto out; + } + stop_topology_update(); rc = pm_suspend(PM_SUSPEND_MEM); start_topology_update(); + + /* Take down CPUs not online prior to suspend */ + if (!rtas_offline_cpus_mask(offline_mask)) + pr_warn("%s: Could not restore CPUs to offline " + "state.\n", __func__); } stream_id = 0; if (!rc) rc = count; +out: + free_cpumask_var(offline_mask); return rc; } -static DEVICE_ATTR(hibernate, S_IWUSR, NULL, store_hibernate); +#define USER_DT_UPDATE 0 +#define KERN_DT_UPDATE 1 + +/** + * show_hibernate - Report device tree update responsibilty + * @dev: subsys root device + * @attr: device attribute struct + * @buf: buffer + * + * Report whether a device tree update is performed by the kernel after a + * resume, or if drmgr must coordinate the update from user space. + * + * Return value: + * 0 if drmgr is to initiate update, and 1 otherwise + **/ +static ssize_t show_hibernate(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return sprintf(buf, "%d\n", KERN_DT_UPDATE); +} + +static DEVICE_ATTR(hibernate, S_IWUSR | S_IRUGO, + show_hibernate, store_hibernate); static struct bus_type suspend_subsys = { .name = "power", @@ -213,6 +276,7 @@ static int __init pseries_suspend_init(void) return rc; ppc_md.suspend_disable_cpu = pseries_suspend_cpu; + ppc_md.suspend_enable_irqs = pseries_suspend_enable_irqs; suspend_set_ops(&pseries_suspend_ops); return 0; } diff --git a/arch/powerpc/platforms/wsp/Kconfig b/arch/powerpc/platforms/wsp/Kconfig deleted file mode 100644 index 79d2225b760..00000000000 --- a/arch/powerpc/platforms/wsp/Kconfig +++ /dev/null @@ -1,35 +0,0 @@ -config PPC_WSP - bool - select PPC_A2 - select GENERIC_TBSYNC - select PPC_ICSWX - select PPC_SCOM - select PPC_XICS - select PPC_ICP_NATIVE - select PCI - select PPC_IO_WORKAROUNDS if PCI - select PPC_INDIRECT_PIO if PCI - select PPC_WSP_COPRO - default n - -menu "WSP platform selection" - depends on PPC_BOOK3E_64 - -config PPC_PSR2 - bool "PowerEN System Reference Platform 2" - select EPAPR_BOOT - select PPC_WSP - default y - -config PPC_CHROMA - bool "PowerEN PCIe Chroma Card" - select EPAPR_BOOT - select PPC_WSP - select OF_DYNAMIC - default y - -endmenu - -config PPC_A2_DD2 - bool "Support for DD2 based A2/WSP systems" - depends on PPC_A2 diff --git a/arch/powerpc/platforms/wsp/Makefile b/arch/powerpc/platforms/wsp/Makefile deleted file mode 100644 index 56817ac98fc..00000000000 --- a/arch/powerpc/platforms/wsp/Makefile +++ /dev/null @@ -1,10 +0,0 @@ -ccflags-y += -mno-minimal-toc - -obj-y += setup.o ics.o wsp.o -obj-$(CONFIG_PPC_PSR2) += psr2.o -obj-$(CONFIG_PPC_CHROMA) += chroma.o h8.o -obj-$(CONFIG_PPC_WSP) += opb_pic.o -obj-$(CONFIG_PPC_WSP) += scom_wsp.o -obj-$(CONFIG_SMP) += smp.o scom_smp.o -obj-$(CONFIG_PCI) += wsp_pci.o -obj-$(CONFIG_PCI_MSI) += msi.o diff --git a/arch/powerpc/platforms/wsp/chroma.c b/arch/powerpc/platforms/wsp/chroma.c deleted file mode 100644 index 8ef53bc2e70..00000000000 --- a/arch/powerpc/platforms/wsp/chroma.c +++ /dev/null @@ -1,55 +0,0 @@ -/* - * Copyright 2008-2011, 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. - */ - -#include <linux/delay.h> -#include <linux/init.h> -#include <linux/irq.h> -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/of.h> -#include <linux/smp.h> -#include <linux/time.h> - -#include <asm/machdep.h> -#include <asm/udbg.h> - -#include "ics.h" -#include "wsp.h" - -void __init chroma_setup_arch(void) -{ - wsp_setup_arch(); - wsp_setup_h8(); - -} - -static int __init chroma_probe(void) -{ - unsigned long root = of_get_flat_dt_root(); - - if (!of_flat_dt_is_compatible(root, "ibm,wsp-chroma")) - return 0; - - return 1; -} - -define_machine(chroma_md) { - .name = "Chroma PCIe", - .probe = chroma_probe, - .setup_arch = chroma_setup_arch, - .restart = wsp_h8_restart, - .power_off = wsp_h8_power_off, - .halt = wsp_halt, - .calibrate_decr = generic_calibrate_decr, - .init_IRQ = wsp_setup_irq, - .progress = udbg_progress, - .power_save = book3e_idle, -}; - -machine_arch_initcall(chroma_md, wsp_probe_devices); diff --git a/arch/powerpc/platforms/wsp/h8.c b/arch/powerpc/platforms/wsp/h8.c deleted file mode 100644 index d18e6cc19df..00000000000 --- a/arch/powerpc/platforms/wsp/h8.c +++ /dev/null @@ -1,134 +0,0 @@ -/* - * Copyright 2008-2011, 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. - */ - -#include <linux/kernel.h> -#include <linux/of.h> -#include <linux/io.h> - -#include "wsp.h" - -/* - * The UART connection to the H8 is over ttyS1 which is just a 16550. - * We assume that FW has it setup right and no one messes with it. - */ - - -static u8 __iomem *h8; - -#define RBR 0 /* Receiver Buffer Register */ -#define THR 0 /* Transmitter Holding Register */ -#define LSR 5 /* Line Status Register */ -#define LSR_DR 0x01 /* LSR value for Data-Ready */ -#define LSR_THRE 0x20 /* LSR value for Transmitter-Holding-Register-Empty */ -static void wsp_h8_putc(int c) -{ - u8 lsr; - - do { - lsr = readb(h8 + LSR); - } while ((lsr & LSR_THRE) != LSR_THRE); - writeb(c, h8 + THR); -} - -static int wsp_h8_getc(void) -{ - u8 lsr; - - do { - lsr = readb(h8 + LSR); - } while ((lsr & LSR_DR) != LSR_DR); - - return readb(h8 + RBR); -} - -static void wsp_h8_puts(const char *s, int sz) -{ - int i; - - for (i = 0; i < sz; i++) { - wsp_h8_putc(s[i]); - - /* no flow control so wait for echo */ - wsp_h8_getc(); - } - wsp_h8_putc('\r'); - wsp_h8_putc('\n'); -} - -static void wsp_h8_terminal_cmd(const char *cmd, int sz) -{ - hard_irq_disable(); - wsp_h8_puts(cmd, sz); - /* should never return, but just in case */ - for (;;) - continue; -} - - -void wsp_h8_restart(char *cmd) -{ - static const char restart[] = "warm-reset"; - - (void)cmd; - wsp_h8_terminal_cmd(restart, sizeof(restart) - 1); -} - -void wsp_h8_power_off(void) -{ - static const char off[] = "power-off"; - - wsp_h8_terminal_cmd(off, sizeof(off) - 1); -} - -static void __iomem *wsp_h8_getaddr(void) -{ - struct device_node *aliases; - struct device_node *uart; - struct property *path; - void __iomem *va = NULL; - - /* - * there is nothing in the devtree to tell us which is mapped - * to the H8, but se know it is the second serial port. - */ - - aliases = of_find_node_by_path("/aliases"); - if (aliases == NULL) - return NULL; - - path = of_find_property(aliases, "serial1", NULL); - if (path == NULL) - goto out; - - uart = of_find_node_by_path(path->value); - if (uart == NULL) - goto out; - - va = of_iomap(uart, 0); - - /* remove it so no one messes with it */ - of_detach_node(uart); - of_node_put(uart); - -out: - of_node_put(aliases); - - return va; -} - -void __init wsp_setup_h8(void) -{ - h8 = wsp_h8_getaddr(); - - /* Devtree change? lets hard map it anyway */ - if (h8 == NULL) { - pr_warn("UART to H8 could not be found"); - h8 = ioremap(0xffc0008000ULL, 0x100); - } -} diff --git a/arch/powerpc/platforms/wsp/ics.c b/arch/powerpc/platforms/wsp/ics.c deleted file mode 100644 index 97fe82ee863..00000000000 --- a/arch/powerpc/platforms/wsp/ics.c +++ /dev/null @@ -1,760 +0,0 @@ -/* - * Copyright 2008-2011 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. - */ - -#include <linux/cpu.h> -#include <linux/init.h> -#include <linux/interrupt.h> -#include <linux/irq.h> -#include <linux/kernel.h> -#include <linux/msi.h> -#include <linux/of.h> -#include <linux/slab.h> -#include <linux/smp.h> -#include <linux/spinlock.h> -#include <linux/types.h> - -#include <asm/io.h> -#include <asm/irq.h> -#include <asm/xics.h> - -#include "wsp.h" -#include "ics.h" - - -/* WSP ICS */ - -struct wsp_ics { - struct ics ics; - struct device_node *dn; - void __iomem *regs; - spinlock_t lock; - unsigned long *bitmap; - u32 chip_id; - u32 lsi_base; - u32 lsi_count; - u64 hwirq_start; - u64 count; -#ifdef CONFIG_SMP - int *hwirq_cpu_map; -#endif -}; - -#define to_wsp_ics(ics) container_of(ics, struct wsp_ics, ics) - -#define INT_SRC_LAYER_BUID_REG(base) ((base) + 0x00) -#define IODA_TBL_ADDR_REG(base) ((base) + 0x18) -#define IODA_TBL_DATA_REG(base) ((base) + 0x20) -#define XIVE_UPDATE_REG(base) ((base) + 0x28) -#define ICS_INT_CAPS_REG(base) ((base) + 0x30) - -#define TBL_AUTO_INCREMENT ((1UL << 63) | (1UL << 15)) -#define TBL_SELECT_XIST (1UL << 48) -#define TBL_SELECT_XIVT (1UL << 49) - -#define IODA_IRQ(irq) ((irq) & (0x7FFULL)) /* HRM 5.1.3.4 */ - -#define XIST_REQUIRED 0x8 -#define XIST_REJECTED 0x4 -#define XIST_PRESENTED 0x2 -#define XIST_PENDING 0x1 - -#define XIVE_SERVER_SHIFT 42 -#define XIVE_SERVER_MASK 0xFFFFULL -#define XIVE_PRIORITY_MASK 0xFFULL -#define XIVE_PRIORITY_SHIFT 32 -#define XIVE_WRITE_ENABLE (1ULL << 63) - -/* - * The docs refer to a 6 bit field called ChipID, which consists of a - * 3 bit NodeID and a 3 bit ChipID. On WSP the ChipID is always zero - * so we ignore it, and every where we use "chip id" in this code we - * mean the NodeID. - */ -#define WSP_ICS_CHIP_SHIFT 17 - - -static struct wsp_ics *ics_list; -static int num_ics; - -/* ICS Source controller accessors */ - -static u64 wsp_ics_get_xive(struct wsp_ics *ics, unsigned int irq) -{ - unsigned long flags; - u64 xive; - - spin_lock_irqsave(&ics->lock, flags); - out_be64(IODA_TBL_ADDR_REG(ics->regs), TBL_SELECT_XIVT | IODA_IRQ(irq)); - xive = in_be64(IODA_TBL_DATA_REG(ics->regs)); - spin_unlock_irqrestore(&ics->lock, flags); - - return xive; -} - -static void wsp_ics_set_xive(struct wsp_ics *ics, unsigned int irq, u64 xive) -{ - xive &= ~XIVE_ADDR_MASK; - xive |= (irq & XIVE_ADDR_MASK); - xive |= XIVE_WRITE_ENABLE; - - out_be64(XIVE_UPDATE_REG(ics->regs), xive); -} - -static u64 xive_set_server(u64 xive, unsigned int server) -{ - u64 mask = ~(XIVE_SERVER_MASK << XIVE_SERVER_SHIFT); - - xive &= mask; - xive |= (server & XIVE_SERVER_MASK) << XIVE_SERVER_SHIFT; - - return xive; -} - -static u64 xive_set_priority(u64 xive, unsigned int priority) -{ - u64 mask = ~(XIVE_PRIORITY_MASK << XIVE_PRIORITY_SHIFT); - - xive &= mask; - xive |= (priority & XIVE_PRIORITY_MASK) << XIVE_PRIORITY_SHIFT; - - return xive; -} - - -#ifdef CONFIG_SMP -/* Find logical CPUs within mask on a given chip and store result in ret */ -void cpus_on_chip(int chip_id, cpumask_t *mask, cpumask_t *ret) -{ - int cpu, chip; - struct device_node *cpu_dn, *dn; - const u32 *prop; - - cpumask_clear(ret); - for_each_cpu(cpu, mask) { - cpu_dn = of_get_cpu_node(cpu, NULL); - if (!cpu_dn) - continue; - - prop = of_get_property(cpu_dn, "at-node", NULL); - if (!prop) { - of_node_put(cpu_dn); - continue; - } - - dn = of_find_node_by_phandle(*prop); - of_node_put(cpu_dn); - - chip = wsp_get_chip_id(dn); - if (chip == chip_id) - cpumask_set_cpu(cpu, ret); - - of_node_put(dn); - } -} - -/* Store a suitable CPU to handle a hwirq in the ics->hwirq_cpu_map cache */ -static int cache_hwirq_map(struct wsp_ics *ics, unsigned int hwirq, - const cpumask_t *affinity) -{ - cpumask_var_t avail, newmask; - int ret = -ENOMEM, cpu, cpu_rover = 0, target; - int index = hwirq - ics->hwirq_start; - unsigned int nodeid; - - BUG_ON(index < 0 || index >= ics->count); - - if (!ics->hwirq_cpu_map) - return -ENOMEM; - - if (!distribute_irqs) { - ics->hwirq_cpu_map[hwirq - ics->hwirq_start] = xics_default_server; - return 0; - } - - /* Allocate needed CPU masks */ - if (!alloc_cpumask_var(&avail, GFP_KERNEL)) - goto ret; - if (!alloc_cpumask_var(&newmask, GFP_KERNEL)) - goto freeavail; - - /* Find PBus attached to the source of this IRQ */ - nodeid = (hwirq >> WSP_ICS_CHIP_SHIFT) & 0x3; /* 12:14 */ - - /* Find CPUs that could handle this IRQ */ - if (affinity) - cpumask_and(avail, cpu_online_mask, affinity); - else - cpumask_copy(avail, cpu_online_mask); - - /* Narrow selection down to logical CPUs on the same chip */ - cpus_on_chip(nodeid, avail, newmask); - - /* Ensure we haven't narrowed it down to 0 */ - if (unlikely(cpumask_empty(newmask))) { - if (unlikely(cpumask_empty(avail))) { - ret = -1; - goto out; - } - cpumask_copy(newmask, avail); - } - - /* Choose a CPU out of those we narrowed it down to in round robin */ - target = hwirq % cpumask_weight(newmask); - for_each_cpu(cpu, newmask) { - if (cpu_rover++ >= target) { - ics->hwirq_cpu_map[index] = get_hard_smp_processor_id(cpu); - ret = 0; - goto out; - } - } - - /* Shouldn't happen */ - WARN_ON(1); - -out: - free_cpumask_var(newmask); -freeavail: - free_cpumask_var(avail); -ret: - if (ret < 0) { - ics->hwirq_cpu_map[index] = cpumask_first(cpu_online_mask); - pr_warning("Error, falling hwirq 0x%x routing back to CPU %i\n", - hwirq, ics->hwirq_cpu_map[index]); - } - return ret; -} - -static void alloc_irq_map(struct wsp_ics *ics) -{ - int i; - - ics->hwirq_cpu_map = kmalloc(sizeof(int) * ics->count, GFP_KERNEL); - if (!ics->hwirq_cpu_map) { - pr_warning("Allocate hwirq_cpu_map failed, " - "IRQ balancing disabled\n"); - return; - } - - for (i=0; i < ics->count; i++) - ics->hwirq_cpu_map[i] = xics_default_server; -} - -static int get_irq_server(struct wsp_ics *ics, unsigned int hwirq) -{ - int index = hwirq - ics->hwirq_start; - - BUG_ON(index < 0 || index >= ics->count); - - if (!ics->hwirq_cpu_map) - return xics_default_server; - - return ics->hwirq_cpu_map[index]; -} -#else /* !CONFIG_SMP */ -static int cache_hwirq_map(struct wsp_ics *ics, unsigned int hwirq, - const cpumask_t *affinity) -{ - return 0; -} - -static int get_irq_server(struct wsp_ics *ics, unsigned int hwirq) -{ - return xics_default_server; -} - -static void alloc_irq_map(struct wsp_ics *ics) { } -#endif - -static void wsp_chip_unmask_irq(struct irq_data *d) -{ - unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d); - struct wsp_ics *ics; - int server; - u64 xive; - - if (hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS) - return; - - ics = d->chip_data; - if (WARN_ON(!ics)) - return; - - server = get_irq_server(ics, hw_irq); - - xive = wsp_ics_get_xive(ics, hw_irq); - xive = xive_set_server(xive, server); - xive = xive_set_priority(xive, DEFAULT_PRIORITY); - wsp_ics_set_xive(ics, hw_irq, xive); -} - -static unsigned int wsp_chip_startup(struct irq_data *d) -{ - /* unmask it */ - wsp_chip_unmask_irq(d); - return 0; -} - -static void wsp_mask_real_irq(unsigned int hw_irq, struct wsp_ics *ics) -{ - u64 xive; - - if (hw_irq == XICS_IPI) - return; - - if (WARN_ON(!ics)) - return; - xive = wsp_ics_get_xive(ics, hw_irq); - xive = xive_set_server(xive, xics_default_server); - xive = xive_set_priority(xive, LOWEST_PRIORITY); - wsp_ics_set_xive(ics, hw_irq, xive); -} - -static void wsp_chip_mask_irq(struct irq_data *d) -{ - unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d); - struct wsp_ics *ics = d->chip_data; - - if (hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS) - return; - - wsp_mask_real_irq(hw_irq, ics); -} - -static int wsp_chip_set_affinity(struct irq_data *d, - const struct cpumask *cpumask, bool force) -{ - unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d); - struct wsp_ics *ics; - int ret; - u64 xive; - - if (hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS) - return -1; - - ics = d->chip_data; - if (WARN_ON(!ics)) - return -1; - xive = wsp_ics_get_xive(ics, hw_irq); - - /* - * For the moment only implement delivery to all cpus or one cpu. - * Get current irq_server for the given irq - */ - ret = cache_hwirq_map(ics, hw_irq, cpumask); - if (ret == -1) { - char cpulist[128]; - cpumask_scnprintf(cpulist, sizeof(cpulist), cpumask); - pr_warning("%s: No online cpus in the mask %s for irq %d\n", - __func__, cpulist, d->irq); - return -1; - } else if (ret == -ENOMEM) { - pr_warning("%s: Out of memory\n", __func__); - return -1; - } - - xive = xive_set_server(xive, get_irq_server(ics, hw_irq)); - wsp_ics_set_xive(ics, hw_irq, xive); - - return 0; -} - -static struct irq_chip wsp_irq_chip = { - .name = "WSP ICS", - .irq_startup = wsp_chip_startup, - .irq_mask = wsp_chip_mask_irq, - .irq_unmask = wsp_chip_unmask_irq, - .irq_set_affinity = wsp_chip_set_affinity -}; - -static int wsp_ics_host_match(struct ics *ics, struct device_node *dn) -{ - /* All ICSs in the system implement a global irq number space, - * so match against them all. */ - return of_device_is_compatible(dn, "ibm,ppc-xics"); -} - -static int wsp_ics_match_hwirq(struct wsp_ics *wsp_ics, unsigned int hwirq) -{ - if (hwirq >= wsp_ics->hwirq_start && - hwirq < wsp_ics->hwirq_start + wsp_ics->count) - return 1; - - return 0; -} - -static int wsp_ics_map(struct ics *ics, unsigned int virq) -{ - struct wsp_ics *wsp_ics = to_wsp_ics(ics); - unsigned int hw_irq = virq_to_hw(virq); - unsigned long flags; - - if (!wsp_ics_match_hwirq(wsp_ics, hw_irq)) - return -ENOENT; - - irq_set_chip_and_handler(virq, &wsp_irq_chip, handle_fasteoi_irq); - - irq_set_chip_data(virq, wsp_ics); - - spin_lock_irqsave(&wsp_ics->lock, flags); - bitmap_allocate_region(wsp_ics->bitmap, hw_irq - wsp_ics->hwirq_start, 0); - spin_unlock_irqrestore(&wsp_ics->lock, flags); - - return 0; -} - -static void wsp_ics_mask_unknown(struct ics *ics, unsigned long hw_irq) -{ - struct wsp_ics *wsp_ics = to_wsp_ics(ics); - - if (!wsp_ics_match_hwirq(wsp_ics, hw_irq)) - return; - - pr_err("%s: IRQ %lu (real) is invalid, disabling it.\n", __func__, hw_irq); - wsp_mask_real_irq(hw_irq, wsp_ics); -} - -static long wsp_ics_get_server(struct ics *ics, unsigned long hw_irq) -{ - struct wsp_ics *wsp_ics = to_wsp_ics(ics); - - if (!wsp_ics_match_hwirq(wsp_ics, hw_irq)) - return -ENOENT; - - return get_irq_server(wsp_ics, hw_irq); -} - -/* HW Number allocation API */ - -static struct wsp_ics *wsp_ics_find_dn_ics(struct device_node *dn) -{ - struct device_node *iparent; - int i; - - iparent = of_irq_find_parent(dn); - if (!iparent) { - pr_err("wsp_ics: Failed to find interrupt parent!\n"); - return NULL; - } - - for(i = 0; i < num_ics; i++) { - if(ics_list[i].dn == iparent) - break; - } - - if (i >= num_ics) { - pr_err("wsp_ics: Unable to find parent bitmap!\n"); - return NULL; - } - - return &ics_list[i]; -} - -int wsp_ics_alloc_irq(struct device_node *dn, int num) -{ - struct wsp_ics *ics; - int order, offset; - - ics = wsp_ics_find_dn_ics(dn); - if (!ics) - return -ENODEV; - - /* Fast, but overly strict if num isn't a power of two */ - order = get_count_order(num); - - spin_lock_irq(&ics->lock); - offset = bitmap_find_free_region(ics->bitmap, ics->count, order); - spin_unlock_irq(&ics->lock); - - if (offset < 0) - return offset; - - return offset + ics->hwirq_start; -} - -void wsp_ics_free_irq(struct device_node *dn, unsigned int irq) -{ - struct wsp_ics *ics; - - ics = wsp_ics_find_dn_ics(dn); - if (WARN_ON(!ics)) - return; - - spin_lock_irq(&ics->lock); - bitmap_release_region(ics->bitmap, irq, 0); - spin_unlock_irq(&ics->lock); -} - -/* Initialisation */ - -static int __init wsp_ics_bitmap_setup(struct wsp_ics *ics, - struct device_node *dn) -{ - int len, i, j, size; - u32 start, count; - const u32 *p; - - size = BITS_TO_LONGS(ics->count) * sizeof(long); - ics->bitmap = kzalloc(size, GFP_KERNEL); - if (!ics->bitmap) { - pr_err("wsp_ics: ENOMEM allocating IRQ bitmap!\n"); - return -ENOMEM; - } - - spin_lock_init(&ics->lock); - - p = of_get_property(dn, "available-ranges", &len); - if (!p || !len) { - /* FIXME this should be a WARN() once mambo is updated */ - pr_err("wsp_ics: No available-ranges defined for %s\n", - dn->full_name); - return 0; - } - - if (len % (2 * sizeof(u32)) != 0) { - /* FIXME this should be a WARN() once mambo is updated */ - pr_err("wsp_ics: Invalid available-ranges for %s\n", - dn->full_name); - return 0; - } - - bitmap_fill(ics->bitmap, ics->count); - - for (i = 0; i < len / sizeof(u32); i += 2) { - start = of_read_number(p + i, 1); - count = of_read_number(p + i + 1, 1); - - pr_devel("%s: start: %d count: %d\n", __func__, start, count); - - if ((start + count) > (ics->hwirq_start + ics->count) || - start < ics->hwirq_start) { - pr_err("wsp_ics: Invalid range! -> %d to %d\n", - start, start + count); - break; - } - - for (j = 0; j < count; j++) - bitmap_release_region(ics->bitmap, - (start + j) - ics->hwirq_start, 0); - } - - /* Ensure LSIs are not available for allocation */ - bitmap_allocate_region(ics->bitmap, ics->lsi_base, - get_count_order(ics->lsi_count)); - - return 0; -} - -static int __init wsp_ics_setup(struct wsp_ics *ics, struct device_node *dn) -{ - u32 lsi_buid, msi_buid, msi_base, msi_count; - void __iomem *regs; - const u32 *p; - int rc, len, i; - u64 caps, buid; - - p = of_get_property(dn, "interrupt-ranges", &len); - if (!p || len < (2 * sizeof(u32))) { - pr_err("wsp_ics: No/bad interrupt-ranges found on %s\n", - dn->full_name); - return -ENOENT; - } - - if (len > (2 * sizeof(u32))) { - pr_err("wsp_ics: Multiple ics ranges not supported.\n"); - return -EINVAL; - } - - regs = of_iomap(dn, 0); - if (!regs) { - pr_err("wsp_ics: of_iomap(%s) failed\n", dn->full_name); - return -ENXIO; - } - - ics->hwirq_start = of_read_number(p, 1); - ics->count = of_read_number(p + 1, 1); - ics->regs = regs; - - ics->chip_id = wsp_get_chip_id(dn); - if (WARN_ON(ics->chip_id < 0)) - ics->chip_id = 0; - - /* Get some informations about the critter */ - caps = in_be64(ICS_INT_CAPS_REG(ics->regs)); - buid = in_be64(INT_SRC_LAYER_BUID_REG(ics->regs)); - ics->lsi_count = caps >> 56; - msi_count = (caps >> 44) & 0x7ff; - - /* Note: LSI BUID is 9 bits, but really only 3 are BUID and the - * rest is mixed in the interrupt number. We store the whole - * thing though - */ - lsi_buid = (buid >> 48) & 0x1ff; - ics->lsi_base = (ics->chip_id << WSP_ICS_CHIP_SHIFT) | lsi_buid << 5; - msi_buid = (buid >> 37) & 0x7; - msi_base = (ics->chip_id << WSP_ICS_CHIP_SHIFT) | msi_buid << 11; - - pr_info("wsp_ics: Found %s\n", dn->full_name); - pr_info("wsp_ics: irq range : 0x%06llx..0x%06llx\n", - ics->hwirq_start, ics->hwirq_start + ics->count - 1); - pr_info("wsp_ics: %4d LSIs : 0x%06x..0x%06x\n", - ics->lsi_count, ics->lsi_base, - ics->lsi_base + ics->lsi_count - 1); - pr_info("wsp_ics: %4d MSIs : 0x%06x..0x%06x\n", - msi_count, msi_base, - msi_base + msi_count - 1); - - /* Let's check the HW config is sane */ - if (ics->lsi_base < ics->hwirq_start || - (ics->lsi_base + ics->lsi_count) > (ics->hwirq_start + ics->count)) - pr_warning("wsp_ics: WARNING ! LSIs out of interrupt-ranges !\n"); - if (msi_base < ics->hwirq_start || - (msi_base + msi_count) > (ics->hwirq_start + ics->count)) - pr_warning("wsp_ics: WARNING ! MSIs out of interrupt-ranges !\n"); - - /* We don't check for overlap between LSI and MSI, which will happen - * if we use the same BUID, I'm not sure yet how legit that is. - */ - - rc = wsp_ics_bitmap_setup(ics, dn); - if (rc) { - iounmap(regs); - return rc; - } - - ics->dn = of_node_get(dn); - alloc_irq_map(ics); - - for(i = 0; i < ics->count; i++) - wsp_mask_real_irq(ics->hwirq_start + i, ics); - - ics->ics.map = wsp_ics_map; - ics->ics.mask_unknown = wsp_ics_mask_unknown; - ics->ics.get_server = wsp_ics_get_server; - ics->ics.host_match = wsp_ics_host_match; - - xics_register_ics(&ics->ics); - - return 0; -} - -static void __init wsp_ics_set_default_server(void) -{ - struct device_node *np; - u32 hwid; - - /* Find the server number for the boot cpu. */ - np = of_get_cpu_node(boot_cpuid, NULL); - BUG_ON(!np); - - hwid = get_hard_smp_processor_id(boot_cpuid); - - pr_info("wsp_ics: default server is %#x, CPU %s\n", hwid, np->full_name); - xics_default_server = hwid; - - of_node_put(np); -} - -static int __init wsp_ics_init(void) -{ - struct device_node *dn; - struct wsp_ics *ics; - int rc, found; - - wsp_ics_set_default_server(); - - found = 0; - for_each_compatible_node(dn, NULL, "ibm,ppc-xics") - found++; - - if (found == 0) { - pr_err("wsp_ics: No ICS's found!\n"); - return -ENODEV; - } - - ics_list = kmalloc(sizeof(*ics) * found, GFP_KERNEL); - if (!ics_list) { - pr_err("wsp_ics: No memory for structs.\n"); - return -ENOMEM; - } - - num_ics = 0; - ics = ics_list; - for_each_compatible_node(dn, NULL, "ibm,wsp-xics") { - rc = wsp_ics_setup(ics, dn); - if (rc == 0) { - ics++; - num_ics++; - } - } - - if (found != num_ics) { - pr_err("wsp_ics: Failed setting up %d ICS's\n", - found - num_ics); - return -1; - } - - return 0; -} - -void __init wsp_init_irq(void) -{ - wsp_ics_init(); - xics_init(); - - /* We need to patch our irq chip's EOI to point to the right ICP */ - wsp_irq_chip.irq_eoi = icp_ops->eoi; -} - -#ifdef CONFIG_PCI_MSI -static void wsp_ics_msi_unmask_irq(struct irq_data *d) -{ - wsp_chip_unmask_irq(d); - unmask_msi_irq(d); -} - -static unsigned int wsp_ics_msi_startup(struct irq_data *d) -{ - wsp_ics_msi_unmask_irq(d); - return 0; -} - -static void wsp_ics_msi_mask_irq(struct irq_data *d) -{ - mask_msi_irq(d); - wsp_chip_mask_irq(d); -} - -/* - * we do it this way because we reassinge default EOI handling in - * irq_init() above - */ -static void wsp_ics_eoi(struct irq_data *data) -{ - wsp_irq_chip.irq_eoi(data); -} - -static struct irq_chip wsp_ics_msi = { - .name = "WSP ICS MSI", - .irq_startup = wsp_ics_msi_startup, - .irq_mask = wsp_ics_msi_mask_irq, - .irq_unmask = wsp_ics_msi_unmask_irq, - .irq_eoi = wsp_ics_eoi, - .irq_set_affinity = wsp_chip_set_affinity -}; - -void wsp_ics_set_msi_chip(unsigned int irq) -{ - irq_set_chip(irq, &wsp_ics_msi); -} - -void wsp_ics_set_std_chip(unsigned int irq) -{ - irq_set_chip(irq, &wsp_irq_chip); -} -#endif /* CONFIG_PCI_MSI */ diff --git a/arch/powerpc/platforms/wsp/ics.h b/arch/powerpc/platforms/wsp/ics.h deleted file mode 100644 index 07b644e0cf9..00000000000 --- a/arch/powerpc/platforms/wsp/ics.h +++ /dev/null @@ -1,25 +0,0 @@ -/* - * Copyright 2009 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. - */ - -#ifndef __ICS_H -#define __ICS_H - -#define XIVE_ADDR_MASK 0x7FFULL - -extern void wsp_init_irq(void); - -extern int wsp_ics_alloc_irq(struct device_node *dn, int num); -extern void wsp_ics_free_irq(struct device_node *dn, unsigned int irq); - -#ifdef CONFIG_PCI_MSI -extern void wsp_ics_set_msi_chip(unsigned int irq); -extern void wsp_ics_set_std_chip(unsigned int irq); -#endif /* CONFIG_PCI_MSI */ - -#endif /* __ICS_H */ diff --git a/arch/powerpc/platforms/wsp/msi.c b/arch/powerpc/platforms/wsp/msi.c deleted file mode 100644 index 380882f27ad..00000000000 --- a/arch/powerpc/platforms/wsp/msi.c +++ /dev/null @@ -1,102 +0,0 @@ -/* - * Copyright 2011 Michael Ellerman, IBM Corp. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <linux/kernel.h> -#include <linux/pci.h> -#include <linux/msi.h> -#include <linux/irq.h> -#include <linux/interrupt.h> - -#include "msi.h" -#include "ics.h" -#include "wsp_pci.h" - -/* Magic addresses for 32 & 64-bit MSIs with hardcoded MVE 0 */ -#define MSI_ADDR_32 0xFFFF0000ul -#define MSI_ADDR_64 0x1000000000000000ul - -int wsp_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) -{ - struct pci_controller *phb; - struct msi_desc *entry; - struct msi_msg msg; - unsigned int virq; - int hwirq; - - phb = pci_bus_to_host(dev->bus); - if (!phb) - return -ENOENT; - - entry = list_first_entry(&dev->msi_list, struct msi_desc, list); - if (entry->msi_attrib.is_64) { - msg.address_lo = 0; - msg.address_hi = MSI_ADDR_64 >> 32; - } else { - msg.address_lo = MSI_ADDR_32; - msg.address_hi = 0; - } - - list_for_each_entry(entry, &dev->msi_list, list) { - hwirq = wsp_ics_alloc_irq(phb->dn, 1); - if (hwirq < 0) { - dev_warn(&dev->dev, "wsp_msi: hwirq alloc failed!\n"); - return hwirq; - } - - virq = irq_create_mapping(NULL, hwirq); - if (virq == NO_IRQ) { - dev_warn(&dev->dev, "wsp_msi: virq alloc failed!\n"); - return -1; - } - - dev_dbg(&dev->dev, "wsp_msi: allocated irq %#x/%#x\n", - hwirq, virq); - - wsp_ics_set_msi_chip(virq); - irq_set_msi_desc(virq, entry); - msg.data = hwirq & XIVE_ADDR_MASK; - write_msi_msg(virq, &msg); - } - - return 0; -} - -void wsp_teardown_msi_irqs(struct pci_dev *dev) -{ - struct pci_controller *phb; - struct msi_desc *entry; - int hwirq; - - phb = pci_bus_to_host(dev->bus); - - dev_dbg(&dev->dev, "wsp_msi: tearing down msi irqs\n"); - - list_for_each_entry(entry, &dev->msi_list, list) { - if (entry->irq == NO_IRQ) - continue; - - irq_set_msi_desc(entry->irq, NULL); - wsp_ics_set_std_chip(entry->irq); - - hwirq = virq_to_hw(entry->irq); - /* In this order to avoid racing with irq_create_mapping() */ - irq_dispose_mapping(entry->irq); - wsp_ics_free_irq(phb->dn, hwirq); - } -} - -void wsp_setup_phb_msi(struct pci_controller *phb) -{ - /* Create a single MVE at offset 0 that matches everything */ - out_be64(phb->cfg_data + PCIE_REG_IODA_ADDR, PCIE_REG_IODA_AD_TBL_MVT); - out_be64(phb->cfg_data + PCIE_REG_IODA_DATA0, 1ull << 63); - - ppc_md.setup_msi_irqs = wsp_setup_msi_irqs; - ppc_md.teardown_msi_irqs = wsp_teardown_msi_irqs; -} diff --git a/arch/powerpc/platforms/wsp/msi.h b/arch/powerpc/platforms/wsp/msi.h deleted file mode 100644 index 0ab27b71b24..00000000000 --- a/arch/powerpc/platforms/wsp/msi.h +++ /dev/null @@ -1,19 +0,0 @@ -/* - * Copyright 2011 Michael Ellerman, IBM Corp. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#ifndef __WSP_MSI_H -#define __WSP_MSI_H - -#ifdef CONFIG_PCI_MSI -extern void wsp_setup_phb_msi(struct pci_controller *phb); -#else -static inline void wsp_setup_phb_msi(struct pci_controller *phb) { } -#endif - -#endif /* __WSP_MSI_H */ diff --git a/arch/powerpc/platforms/wsp/opb_pic.c b/arch/powerpc/platforms/wsp/opb_pic.c deleted file mode 100644 index cb565bf9365..00000000000 --- a/arch/powerpc/platforms/wsp/opb_pic.c +++ /dev/null @@ -1,319 +0,0 @@ -/* - * IBM Onboard Peripheral Bus Interrupt Controller - * - * Copyright 2010 Jack Miller, 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. - */ - -#include <linux/interrupt.h> -#include <linux/io.h> -#include <linux/irq.h> -#include <linux/of.h> -#include <linux/slab.h> -#include <linux/time.h> - -#include <asm/reg_a2.h> -#include <asm/irq.h> - -#define OPB_NR_IRQS 32 - -#define OPB_MLSASIER 0x04 /* MLS Accumulated Status IER */ -#define OPB_MLSIR 0x50 /* MLS Interrupt Register */ -#define OPB_MLSIER 0x54 /* MLS Interrupt Enable Register */ -#define OPB_MLSIPR 0x58 /* MLS Interrupt Polarity Register */ -#define OPB_MLSIIR 0x5c /* MLS Interrupt Inputs Register */ - -static int opb_index = 0; - -struct opb_pic { - struct irq_domain *host; - void *regs; - int index; - spinlock_t lock; -}; - -static u32 opb_in(struct opb_pic *opb, int offset) -{ - return in_be32(opb->regs + offset); -} - -static void opb_out(struct opb_pic *opb, int offset, u32 val) -{ - out_be32(opb->regs + offset, val); -} - -static void opb_unmask_irq(struct irq_data *d) -{ - struct opb_pic *opb; - unsigned long flags; - u32 ier, bitset; - - opb = d->chip_data; - bitset = (1 << (31 - irqd_to_hwirq(d))); - - spin_lock_irqsave(&opb->lock, flags); - - ier = opb_in(opb, OPB_MLSIER); - opb_out(opb, OPB_MLSIER, ier | bitset); - ier = opb_in(opb, OPB_MLSIER); - - spin_unlock_irqrestore(&opb->lock, flags); -} - -static void opb_mask_irq(struct irq_data *d) -{ - struct opb_pic *opb; - unsigned long flags; - u32 ier, mask; - - opb = d->chip_data; - mask = ~(1 << (31 - irqd_to_hwirq(d))); - - spin_lock_irqsave(&opb->lock, flags); - - ier = opb_in(opb, OPB_MLSIER); - opb_out(opb, OPB_MLSIER, ier & mask); - ier = opb_in(opb, OPB_MLSIER); // Flush posted writes - - spin_unlock_irqrestore(&opb->lock, flags); -} - -static void opb_ack_irq(struct irq_data *d) -{ - struct opb_pic *opb; - unsigned long flags; - u32 bitset; - - opb = d->chip_data; - bitset = (1 << (31 - irqd_to_hwirq(d))); - - spin_lock_irqsave(&opb->lock, flags); - - opb_out(opb, OPB_MLSIR, bitset); - opb_in(opb, OPB_MLSIR); // Flush posted writes - - spin_unlock_irqrestore(&opb->lock, flags); -} - -static void opb_mask_ack_irq(struct irq_data *d) -{ - struct opb_pic *opb; - unsigned long flags; - u32 bitset; - u32 ier, ir; - - opb = d->chip_data; - bitset = (1 << (31 - irqd_to_hwirq(d))); - - spin_lock_irqsave(&opb->lock, flags); - - ier = opb_in(opb, OPB_MLSIER); - opb_out(opb, OPB_MLSIER, ier & ~bitset); - ier = opb_in(opb, OPB_MLSIER); // Flush posted writes - - opb_out(opb, OPB_MLSIR, bitset); - ir = opb_in(opb, OPB_MLSIR); // Flush posted writes - - spin_unlock_irqrestore(&opb->lock, flags); -} - -static int opb_set_irq_type(struct irq_data *d, unsigned int flow) -{ - struct opb_pic *opb; - unsigned long flags; - int invert, ipr, mask, bit; - - opb = d->chip_data; - - /* The only information we're interested in in the type is whether it's - * a high or low trigger. For high triggered interrupts, the polarity - * set for it in the MLS Interrupt Polarity Register is 0, for low - * interrupts it's 1 so that the proper input in the MLS Interrupt Input - * Register is interrupted as asserting the interrupt. */ - - switch (flow) { - case IRQ_TYPE_NONE: - opb_mask_irq(d); - return 0; - - case IRQ_TYPE_LEVEL_HIGH: - invert = 0; - break; - - case IRQ_TYPE_LEVEL_LOW: - invert = 1; - break; - - default: - return -EINVAL; - } - - bit = (1 << (31 - irqd_to_hwirq(d))); - mask = ~bit; - - spin_lock_irqsave(&opb->lock, flags); - - ipr = opb_in(opb, OPB_MLSIPR); - ipr = (ipr & mask) | (invert ? bit : 0); - opb_out(opb, OPB_MLSIPR, ipr); - ipr = opb_in(opb, OPB_MLSIPR); // Flush posted writes - - spin_unlock_irqrestore(&opb->lock, flags); - - /* Record the type in the interrupt descriptor */ - irqd_set_trigger_type(d, flow); - - return 0; -} - -static struct irq_chip opb_irq_chip = { - .name = "OPB", - .irq_mask = opb_mask_irq, - .irq_unmask = opb_unmask_irq, - .irq_mask_ack = opb_mask_ack_irq, - .irq_ack = opb_ack_irq, - .irq_set_type = opb_set_irq_type -}; - -static int opb_host_map(struct irq_domain *host, unsigned int virq, - irq_hw_number_t hwirq) -{ - struct opb_pic *opb; - - opb = host->host_data; - - /* Most of the important stuff is handled by the generic host code, like - * the lookup, so just attach some info to the virtual irq */ - - irq_set_chip_data(virq, opb); - irq_set_chip_and_handler(virq, &opb_irq_chip, handle_level_irq); - irq_set_irq_type(virq, IRQ_TYPE_NONE); - - return 0; -} - -static const struct irq_domain_ops opb_host_ops = { - .map = opb_host_map, - .xlate = irq_domain_xlate_twocell, -}; - -irqreturn_t opb_irq_handler(int irq, void *private) -{ - struct opb_pic *opb; - u32 ir, src, subvirq; - - opb = (struct opb_pic *) private; - - /* Read the OPB MLS Interrupt Register for - * asserted interrupts */ - ir = opb_in(opb, OPB_MLSIR); - if (!ir) - return IRQ_NONE; - - do { - /* Get 1 - 32 source, *NOT* bit */ - src = 32 - ffs(ir); - - /* Translate from the OPB's conception of interrupt number to - * Linux's virtual IRQ */ - - subvirq = irq_linear_revmap(opb->host, src); - - generic_handle_irq(subvirq); - } while ((ir = opb_in(opb, OPB_MLSIR))); - - return IRQ_HANDLED; -} - -struct opb_pic *opb_pic_init_one(struct device_node *dn) -{ - struct opb_pic *opb; - struct resource res; - - if (of_address_to_resource(dn, 0, &res)) { - printk(KERN_ERR "opb: Couldn't translate resource\n"); - return NULL; - } - - opb = kzalloc(sizeof(struct opb_pic), GFP_KERNEL); - if (!opb) { - printk(KERN_ERR "opb: Failed to allocate opb struct!\n"); - return NULL; - } - - /* Get access to the OPB MMIO registers */ - opb->regs = ioremap(res.start + 0x10000, 0x1000); - if (!opb->regs) { - printk(KERN_ERR "opb: Failed to allocate register space!\n"); - goto free_opb; - } - - /* Allocate an irq domain so that Linux knows that despite only - * having one interrupt to issue, we're the controller for multiple - * hardware IRQs, so later we can lookup their virtual IRQs. */ - - opb->host = irq_domain_add_linear(dn, OPB_NR_IRQS, &opb_host_ops, opb); - if (!opb->host) { - printk(KERN_ERR "opb: Failed to allocate IRQ host!\n"); - goto free_regs; - } - - opb->index = opb_index++; - spin_lock_init(&opb->lock); - - /* Disable all interrupts by default */ - opb_out(opb, OPB_MLSASIER, 0); - opb_out(opb, OPB_MLSIER, 0); - - /* ACK any interrupts left by FW */ - opb_out(opb, OPB_MLSIR, 0xFFFFFFFF); - - return opb; - -free_regs: - iounmap(opb->regs); -free_opb: - kfree(opb); - return NULL; -} - -void __init opb_pic_init(void) -{ - struct device_node *dn; - struct opb_pic *opb; - int virq; - int rc; - - /* Call init_one for each OPB device */ - for_each_compatible_node(dn, NULL, "ibm,opb") { - - /* Fill in an OPB struct */ - opb = opb_pic_init_one(dn); - if (!opb) { - printk(KERN_WARNING "opb: Failed to init node, skipped!\n"); - continue; - } - - /* Map / get opb's hardware virtual irq */ - virq = irq_of_parse_and_map(dn, 0); - if (virq <= 0) { - printk("opb: irq_op_parse_and_map failed!\n"); - continue; - } - - /* Attach opb interrupt handler to new virtual IRQ */ - rc = request_irq(virq, opb_irq_handler, IRQF_NO_THREAD, - "OPB LS Cascade", opb); - if (rc) { - printk("opb: request_irq failed: %d\n", rc); - continue; - } - - printk("OPB%d init with %d IRQs at %p\n", opb->index, - OPB_NR_IRQS, opb->regs); - } -} diff --git a/arch/powerpc/platforms/wsp/psr2.c b/arch/powerpc/platforms/wsp/psr2.c deleted file mode 100644 index 508ec8282b9..00000000000 --- a/arch/powerpc/platforms/wsp/psr2.c +++ /dev/null @@ -1,66 +0,0 @@ -/* - * Copyright 2008-2011, 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. - */ - -#include <linux/delay.h> -#include <linux/init.h> -#include <linux/irq.h> -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/of.h> -#include <linux/smp.h> -#include <linux/time.h> - -#include <asm/machdep.h> -#include <asm/udbg.h> - -#include "ics.h" -#include "wsp.h" - - -static void psr2_spin(void) -{ - hard_irq_disable(); - for (;;) - continue; -} - -static void psr2_restart(char *cmd) -{ - psr2_spin(); -} - -static int __init psr2_probe(void) -{ - unsigned long root = of_get_flat_dt_root(); - - if (of_flat_dt_is_compatible(root, "ibm,wsp-chroma")) { - /* chroma systems also claim they are psr2s */ - return 0; - } - - if (!of_flat_dt_is_compatible(root, "ibm,psr2")) - return 0; - - return 1; -} - -define_machine(psr2_md) { - .name = "PSR2 A2", - .probe = psr2_probe, - .setup_arch = wsp_setup_arch, - .restart = psr2_restart, - .power_off = psr2_spin, - .halt = psr2_spin, - .calibrate_decr = generic_calibrate_decr, - .init_IRQ = wsp_setup_irq, - .progress = udbg_progress, - .power_save = book3e_idle, -}; - -machine_arch_initcall(psr2_md, wsp_probe_devices); diff --git a/arch/powerpc/platforms/wsp/scom_smp.c b/arch/powerpc/platforms/wsp/scom_smp.c deleted file mode 100644 index b56b70aeb49..00000000000 --- a/arch/powerpc/platforms/wsp/scom_smp.c +++ /dev/null @@ -1,426 +0,0 @@ -/* - * SCOM support for A2 platforms - * - * Copyright 2007-2011 Benjamin Herrenschmidt, David Gibson, - * Michael Ellerman, IBM Corp. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <linux/cpumask.h> -#include <linux/io.h> -#include <linux/of.h> -#include <linux/spinlock.h> -#include <linux/types.h> - -#include <asm/cputhreads.h> -#include <asm/reg_a2.h> -#include <asm/scom.h> -#include <asm/udbg.h> - -#include "wsp.h" - -#define SCOM_RAMC 0x2a /* Ram Command */ -#define SCOM_RAMC_TGT1_EXT 0x80000000 -#define SCOM_RAMC_SRC1_EXT 0x40000000 -#define SCOM_RAMC_SRC2_EXT 0x20000000 -#define SCOM_RAMC_SRC3_EXT 0x10000000 -#define SCOM_RAMC_ENABLE 0x00080000 -#define SCOM_RAMC_THREADSEL 0x00060000 -#define SCOM_RAMC_EXECUTE 0x00010000 -#define SCOM_RAMC_MSR_OVERRIDE 0x00008000 -#define SCOM_RAMC_MSR_PR 0x00004000 -#define SCOM_RAMC_MSR_GS 0x00002000 -#define SCOM_RAMC_FORCE 0x00001000 -#define SCOM_RAMC_FLUSH 0x00000800 -#define SCOM_RAMC_INTERRUPT 0x00000004 -#define SCOM_RAMC_ERROR 0x00000002 -#define SCOM_RAMC_DONE 0x00000001 -#define SCOM_RAMI 0x29 /* Ram Instruction */ -#define SCOM_RAMIC 0x28 /* Ram Instruction and Command */ -#define SCOM_RAMIC_INSN 0xffffffff00000000 -#define SCOM_RAMD 0x2d /* Ram Data */ -#define SCOM_RAMDH 0x2e /* Ram Data High */ -#define SCOM_RAMDL 0x2f /* Ram Data Low */ -#define SCOM_PCCR0 0x33 /* PC Configuration Register 0 */ -#define SCOM_PCCR0_ENABLE_DEBUG 0x80000000 -#define SCOM_PCCR0_ENABLE_RAM 0x40000000 -#define SCOM_THRCTL 0x30 /* Thread Control and Status */ -#define SCOM_THRCTL_T0_STOP 0x80000000 -#define SCOM_THRCTL_T1_STOP 0x40000000 -#define SCOM_THRCTL_T2_STOP 0x20000000 -#define SCOM_THRCTL_T3_STOP 0x10000000 -#define SCOM_THRCTL_T0_STEP 0x08000000 -#define SCOM_THRCTL_T1_STEP 0x04000000 -#define SCOM_THRCTL_T2_STEP 0x02000000 -#define SCOM_THRCTL_T3_STEP 0x01000000 -#define SCOM_THRCTL_T0_RUN 0x00800000 -#define SCOM_THRCTL_T1_RUN 0x00400000 -#define SCOM_THRCTL_T2_RUN 0x00200000 -#define SCOM_THRCTL_T3_RUN 0x00100000 -#define SCOM_THRCTL_T0_PM 0x00080000 -#define SCOM_THRCTL_T1_PM 0x00040000 -#define SCOM_THRCTL_T2_PM 0x00020000 -#define SCOM_THRCTL_T3_PM 0x00010000 -#define SCOM_THRCTL_T0_UDE 0x00008000 -#define SCOM_THRCTL_T1_UDE 0x00004000 -#define SCOM_THRCTL_T2_UDE 0x00002000 -#define SCOM_THRCTL_T3_UDE 0x00001000 -#define SCOM_THRCTL_ASYNC_DIS 0x00000800 -#define SCOM_THRCTL_TB_DIS 0x00000400 -#define SCOM_THRCTL_DEC_DIS 0x00000200 -#define SCOM_THRCTL_AND 0x31 /* Thread Control and Status */ -#define SCOM_THRCTL_OR 0x32 /* Thread Control and Status */ - - -static DEFINE_PER_CPU(scom_map_t, scom_ptrs); - -static scom_map_t get_scom(int cpu, struct device_node *np, int *first_thread) -{ - scom_map_t scom = per_cpu(scom_ptrs, cpu); - int tcpu; - - if (scom_map_ok(scom)) { - *first_thread = 0; - return scom; - } - - *first_thread = 1; - - scom = scom_map_device(np, 0); - - for (tcpu = cpu_first_thread_sibling(cpu); - tcpu <= cpu_last_thread_sibling(cpu); tcpu++) - per_cpu(scom_ptrs, tcpu) = scom; - - /* Hack: for the boot core, this will actually get called on - * the second thread up, not the first so our test above will - * set first_thread incorrectly. */ - if (cpu_first_thread_sibling(cpu) == 0) - *first_thread = 0; - - return scom; -} - -static int a2_scom_ram(scom_map_t scom, int thread, u32 insn, int extmask) -{ - u64 cmd, mask, val; - int n = 0; - - cmd = ((u64)insn << 32) | (((u64)extmask & 0xf) << 28) - | ((u64)thread << 17) | SCOM_RAMC_ENABLE | SCOM_RAMC_EXECUTE; - mask = SCOM_RAMC_DONE | SCOM_RAMC_INTERRUPT | SCOM_RAMC_ERROR; - - scom_write(scom, SCOM_RAMIC, cmd); - - while (!((val = scom_read(scom, SCOM_RAMC)) & mask)) { - pr_devel("Waiting on RAMC = 0x%llx\n", val); - if (++n == 3) { - pr_err("RAMC timeout on instruction 0x%08x, thread %d\n", - insn, thread); - return -1; - } - } - - if (val & SCOM_RAMC_INTERRUPT) { - pr_err("RAMC interrupt on instruction 0x%08x, thread %d\n", - insn, thread); - return -SCOM_RAMC_INTERRUPT; - } - - if (val & SCOM_RAMC_ERROR) { - pr_err("RAMC error on instruction 0x%08x, thread %d\n", - insn, thread); - return -SCOM_RAMC_ERROR; - } - - return 0; -} - -static int a2_scom_getgpr(scom_map_t scom, int thread, int gpr, int alt, - u64 *out_gpr) -{ - int rc; - - /* or rN, rN, rN */ - u32 insn = 0x7c000378 | (gpr << 21) | (gpr << 16) | (gpr << 11); - rc = a2_scom_ram(scom, thread, insn, alt ? 0xf : 0x0); - if (rc) - return rc; - - *out_gpr = scom_read(scom, SCOM_RAMD); - - return 0; -} - -static int a2_scom_getspr(scom_map_t scom, int thread, int spr, u64 *out_spr) -{ - int rc, sprhi, sprlo; - u32 insn; - - sprhi = spr >> 5; - sprlo = spr & 0x1f; - insn = 0x7c2002a6 | (sprlo << 16) | (sprhi << 11); /* mfspr r1,spr */ - - if (spr == 0x0ff0) - insn = 0x7c2000a6; /* mfmsr r1 */ - - rc = a2_scom_ram(scom, thread, insn, 0xf); - if (rc) - return rc; - return a2_scom_getgpr(scom, thread, 1, 1, out_spr); -} - -static int a2_scom_setgpr(scom_map_t scom, int thread, int gpr, - int alt, u64 val) -{ - u32 lis = 0x3c000000 | (gpr << 21); - u32 li = 0x38000000 | (gpr << 21); - u32 oris = 0x64000000 | (gpr << 21) | (gpr << 16); - u32 ori = 0x60000000 | (gpr << 21) | (gpr << 16); - u32 rldicr32 = 0x780007c6 | (gpr << 21) | (gpr << 16); - u32 highest = val >> 48; - u32 higher = (val >> 32) & 0xffff; - u32 high = (val >> 16) & 0xffff; - u32 low = val & 0xffff; - int lext = alt ? 0x8 : 0x0; - int oext = alt ? 0xf : 0x0; - int rc = 0; - - if (highest) - rc |= a2_scom_ram(scom, thread, lis | highest, lext); - - if (higher) { - if (highest) - rc |= a2_scom_ram(scom, thread, oris | higher, oext); - else - rc |= a2_scom_ram(scom, thread, li | higher, lext); - } - - if (highest || higher) - rc |= a2_scom_ram(scom, thread, rldicr32, oext); - - if (high) { - if (highest || higher) - rc |= a2_scom_ram(scom, thread, oris | high, oext); - else - rc |= a2_scom_ram(scom, thread, lis | high, lext); - } - - if (highest || higher || high) - rc |= a2_scom_ram(scom, thread, ori | low, oext); - else - rc |= a2_scom_ram(scom, thread, li | low, lext); - - return rc; -} - -static int a2_scom_setspr(scom_map_t scom, int thread, int spr, u64 val) -{ - int sprhi = spr >> 5; - int sprlo = spr & 0x1f; - /* mtspr spr, r1 */ - u32 insn = 0x7c2003a6 | (sprlo << 16) | (sprhi << 11); - - if (spr == 0x0ff0) - insn = 0x7c200124; /* mtmsr r1 */ - - if (a2_scom_setgpr(scom, thread, 1, 1, val)) - return -1; - - return a2_scom_ram(scom, thread, insn, 0xf); -} - -static int a2_scom_initial_tlb(scom_map_t scom, int thread) -{ - extern u32 a2_tlbinit_code_start[], a2_tlbinit_code_end[]; - extern u32 a2_tlbinit_after_iprot_flush[]; - extern u32 a2_tlbinit_after_linear_map[]; - u32 assoc, entries, i; - u64 epn, tlbcfg; - u32 *p; - int rc; - - /* Invalidate all entries (including iprot) */ - - rc = a2_scom_getspr(scom, thread, SPRN_TLB0CFG, &tlbcfg); - if (rc) - goto scom_fail; - entries = tlbcfg & TLBnCFG_N_ENTRY; - assoc = (tlbcfg & TLBnCFG_ASSOC) >> 24; - epn = 0; - - /* Set MMUCR2 to enable 4K, 64K, 1M, 16M and 1G pages */ - a2_scom_setspr(scom, thread, SPRN_MMUCR2, 0x000a7531); - /* Set MMUCR3 to write all thids bit to the TLB */ - a2_scom_setspr(scom, thread, SPRN_MMUCR3, 0x0000000f); - - /* Set MAS1 for 1G page size, and MAS2 to our initial EPN */ - a2_scom_setspr(scom, thread, SPRN_MAS1, MAS1_TSIZE(BOOK3E_PAGESZ_1GB)); - a2_scom_setspr(scom, thread, SPRN_MAS2, epn); - for (i = 0; i < entries; i++) { - - a2_scom_setspr(scom, thread, SPRN_MAS0, MAS0_ESEL(i % assoc)); - - /* tlbwe */ - rc = a2_scom_ram(scom, thread, 0x7c0007a4, 0); - if (rc) - goto scom_fail; - - /* Next entry is new address? */ - if((i + 1) % assoc == 0) { - epn += (1 << 30); - a2_scom_setspr(scom, thread, SPRN_MAS2, epn); - } - } - - /* Setup args for linear mapping */ - rc = a2_scom_setgpr(scom, thread, 3, 0, MAS0_TLBSEL(0)); - if (rc) - goto scom_fail; - - /* Linear mapping */ - for (p = a2_tlbinit_code_start; p < a2_tlbinit_after_linear_map; p++) { - rc = a2_scom_ram(scom, thread, *p, 0); - if (rc) - goto scom_fail; - } - - /* - * For the boot thread, between the linear mapping and the debug - * mappings there is a loop to flush iprot mappings. Ramming doesn't do - * branches, but the secondary threads don't need to be nearly as smart - * (i.e. we don't need to worry about invalidating the mapping we're - * standing on). - */ - - /* Debug mappings. Expects r11 = MAS0 from linear map (set above) */ - for (p = a2_tlbinit_after_iprot_flush; p < a2_tlbinit_code_end; p++) { - rc = a2_scom_ram(scom, thread, *p, 0); - if (rc) - goto scom_fail; - } - -scom_fail: - if (rc) - pr_err("Setting up initial TLB failed, err %d\n", rc); - - if (rc == -SCOM_RAMC_INTERRUPT) { - /* Interrupt, dump some status */ - int rc[10]; - u64 iar, srr0, srr1, esr, mas0, mas1, mas2, mas7_3, mas8, ccr2; - rc[0] = a2_scom_getspr(scom, thread, SPRN_IAR, &iar); - rc[1] = a2_scom_getspr(scom, thread, SPRN_SRR0, &srr0); - rc[2] = a2_scom_getspr(scom, thread, SPRN_SRR1, &srr1); - rc[3] = a2_scom_getspr(scom, thread, SPRN_ESR, &esr); - rc[4] = a2_scom_getspr(scom, thread, SPRN_MAS0, &mas0); - rc[5] = a2_scom_getspr(scom, thread, SPRN_MAS1, &mas1); - rc[6] = a2_scom_getspr(scom, thread, SPRN_MAS2, &mas2); - rc[7] = a2_scom_getspr(scom, thread, SPRN_MAS7_MAS3, &mas7_3); - rc[8] = a2_scom_getspr(scom, thread, SPRN_MAS8, &mas8); - rc[9] = a2_scom_getspr(scom, thread, SPRN_A2_CCR2, &ccr2); - pr_err(" -> retreived IAR =0x%llx (err %d)\n", iar, rc[0]); - pr_err(" retreived SRR0=0x%llx (err %d)\n", srr0, rc[1]); - pr_err(" retreived SRR1=0x%llx (err %d)\n", srr1, rc[2]); - pr_err(" retreived ESR =0x%llx (err %d)\n", esr, rc[3]); - pr_err(" retreived MAS0=0x%llx (err %d)\n", mas0, rc[4]); - pr_err(" retreived MAS1=0x%llx (err %d)\n", mas1, rc[5]); - pr_err(" retreived MAS2=0x%llx (err %d)\n", mas2, rc[6]); - pr_err(" retreived MS73=0x%llx (err %d)\n", mas7_3, rc[7]); - pr_err(" retreived MAS8=0x%llx (err %d)\n", mas8, rc[8]); - pr_err(" retreived CCR2=0x%llx (err %d)\n", ccr2, rc[9]); - } - - return rc; -} - -int a2_scom_startup_cpu(unsigned int lcpu, int thr_idx, struct device_node *np) -{ - u64 init_iar, init_msr, init_ccr2; - unsigned long start_here; - int rc, core_setup; - scom_map_t scom; - u64 pccr0; - - scom = get_scom(lcpu, np, &core_setup); - if (!scom) { - printk(KERN_ERR "Couldn't map SCOM for CPU%d\n", lcpu); - return -1; - } - - pr_devel("Bringing up CPU%d using SCOM...\n", lcpu); - - pccr0 = scom_read(scom, SCOM_PCCR0); - scom_write(scom, SCOM_PCCR0, pccr0 | SCOM_PCCR0_ENABLE_DEBUG | - SCOM_PCCR0_ENABLE_RAM); - - /* Stop the thead with THRCTL. If we are setting up the TLB we stop all - * threads. We also disable asynchronous interrupts while RAMing. - */ - if (core_setup) - scom_write(scom, SCOM_THRCTL_OR, - SCOM_THRCTL_T0_STOP | - SCOM_THRCTL_T1_STOP | - SCOM_THRCTL_T2_STOP | - SCOM_THRCTL_T3_STOP | - SCOM_THRCTL_ASYNC_DIS); - else - scom_write(scom, SCOM_THRCTL_OR, SCOM_THRCTL_T0_STOP >> thr_idx); - - /* Flush its pipeline just in case */ - scom_write(scom, SCOM_RAMC, ((u64)thr_idx << 17) | - SCOM_RAMC_FLUSH | SCOM_RAMC_ENABLE); - - a2_scom_getspr(scom, thr_idx, SPRN_IAR, &init_iar); - a2_scom_getspr(scom, thr_idx, 0x0ff0, &init_msr); - a2_scom_getspr(scom, thr_idx, SPRN_A2_CCR2, &init_ccr2); - - /* Set MSR to MSR_CM (0x0ff0 is magic value for MSR_CM) */ - rc = a2_scom_setspr(scom, thr_idx, 0x0ff0, MSR_CM); - if (rc) { - pr_err("Failed to set MSR ! err %d\n", rc); - return rc; - } - - /* RAM in an sync/isync for the sake of it */ - a2_scom_ram(scom, thr_idx, 0x7c0004ac, 0); - a2_scom_ram(scom, thr_idx, 0x4c00012c, 0); - - if (core_setup) { - pr_devel("CPU%d is first thread in core, initializing TLB...\n", - lcpu); - rc = a2_scom_initial_tlb(scom, thr_idx); - if (rc) - goto fail; - } - - start_here = *(unsigned long *)(core_setup ? generic_secondary_smp_init - : generic_secondary_thread_init); - pr_devel("CPU%d entry point at 0x%lx...\n", lcpu, start_here); - - rc |= a2_scom_setspr(scom, thr_idx, SPRN_IAR, start_here); - rc |= a2_scom_setgpr(scom, thr_idx, 3, 0, - get_hard_smp_processor_id(lcpu)); - /* - * Tell book3e_secondary_core_init not to set up the TLB, we've - * already done that. - */ - rc |= a2_scom_setgpr(scom, thr_idx, 4, 0, 1); - - rc |= a2_scom_setspr(scom, thr_idx, SPRN_TENS, 0x1 << thr_idx); - - scom_write(scom, SCOM_RAMC, 0); - scom_write(scom, SCOM_THRCTL_AND, ~(SCOM_THRCTL_T0_STOP >> thr_idx)); - scom_write(scom, SCOM_PCCR0, pccr0); -fail: - pr_devel(" SCOM initialization %s\n", rc ? "failed" : "succeeded"); - if (rc) { - pr_err("Old IAR=0x%08llx MSR=0x%08llx CCR2=0x%08llx\n", - init_iar, init_msr, init_ccr2); - } - - return rc; -} diff --git a/arch/powerpc/platforms/wsp/scom_wsp.c b/arch/powerpc/platforms/wsp/scom_wsp.c deleted file mode 100644 index 4052e2259f3..00000000000 --- a/arch/powerpc/platforms/wsp/scom_wsp.c +++ /dev/null @@ -1,77 +0,0 @@ -/* - * SCOM backend for WSP - * - * Copyright 2010 Benjamin Herrenschmidt, IBM Corp. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <linux/cpumask.h> -#include <linux/io.h> -#include <linux/of.h> -#include <linux/spinlock.h> -#include <linux/types.h> - -#include <asm/cputhreads.h> -#include <asm/reg_a2.h> -#include <asm/scom.h> -#include <asm/udbg.h> - -#include "wsp.h" - - -static scom_map_t wsp_scom_map(struct device_node *dev, u64 reg, u64 count) -{ - struct resource r; - u64 xscom_addr; - - if (!of_get_property(dev, "scom-controller", NULL)) { - pr_err("%s: device %s is not a SCOM controller\n", - __func__, dev->full_name); - return SCOM_MAP_INVALID; - } - - if (of_address_to_resource(dev, 0, &r)) { - pr_debug("Failed to find SCOM controller address\n"); - return 0; - } - - /* Transform the SCOM address into an XSCOM offset */ - xscom_addr = ((reg & 0x7f000000) >> 1) | ((reg & 0xfffff) << 3); - - return (scom_map_t)ioremap(r.start + xscom_addr, count << 3); -} - -static void wsp_scom_unmap(scom_map_t map) -{ - iounmap((void *)map); -} - -static u64 wsp_scom_read(scom_map_t map, u32 reg) -{ - u64 __iomem *addr = (u64 __iomem *)map; - - return in_be64(addr + reg); -} - -static void wsp_scom_write(scom_map_t map, u32 reg, u64 value) -{ - u64 __iomem *addr = (u64 __iomem *)map; - - return out_be64(addr + reg, value); -} - -static const struct scom_controller wsp_scom_controller = { - .map = wsp_scom_map, - .unmap = wsp_scom_unmap, - .read = wsp_scom_read, - .write = wsp_scom_write -}; - -void scom_init_wsp(void) -{ - scom_init(&wsp_scom_controller); -} diff --git a/arch/powerpc/platforms/wsp/setup.c b/arch/powerpc/platforms/wsp/setup.c deleted file mode 100644 index 11ac2f05e01..00000000000 --- a/arch/powerpc/platforms/wsp/setup.c +++ /dev/null @@ -1,36 +0,0 @@ -/* - * Copyright 2010 Michael Ellerman, 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. - */ - -#include <linux/kernel.h> -#include <linux/of_platform.h> - -#include "wsp.h" - -/* - * Find chip-id by walking up device tree looking for ibm,wsp-chip-id property. - * Won't work for nodes that are not a descendant of a wsp node. - */ -int wsp_get_chip_id(struct device_node *dn) -{ - const u32 *p; - int rc; - - /* Start looking at the specified node, not its parent */ - dn = of_node_get(dn); - while (dn && !(p = of_get_property(dn, "ibm,wsp-chip-id", NULL))) - dn = of_get_next_parent(dn); - - if (!dn) - return -1; - - rc = *p; - of_node_put(dn); - - return rc; -} diff --git a/arch/powerpc/platforms/wsp/smp.c b/arch/powerpc/platforms/wsp/smp.c deleted file mode 100644 index 332a18b8140..00000000000 --- a/arch/powerpc/platforms/wsp/smp.c +++ /dev/null @@ -1,88 +0,0 @@ -/* - * SMP Support for A2 platforms - * - * Copyright 2007 Benjamin Herrenschmidt, IBM Corp. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - */ - -#include <linux/cpumask.h> -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/of.h> -#include <linux/smp.h> - -#include <asm/dbell.h> -#include <asm/machdep.h> -#include <asm/xics.h> - -#include "ics.h" -#include "wsp.h" - -static void smp_a2_setup_cpu(int cpu) -{ - doorbell_setup_this_cpu(); - - if (cpu != boot_cpuid) - xics_setup_cpu(); -} - -int smp_a2_kick_cpu(int nr) -{ - const char *enable_method; - struct device_node *np; - int thr_idx; - - if (nr < 0 || nr >= NR_CPUS) - return -ENOENT; - - np = of_get_cpu_node(nr, &thr_idx); - if (!np) - return -ENODEV; - - enable_method = of_get_property(np, "enable-method", NULL); - pr_devel("CPU%d has enable-method: \"%s\"\n", nr, enable_method); - - if (!enable_method) { - printk(KERN_ERR "CPU%d has no enable-method\n", nr); - return -ENOENT; - } else if (strcmp(enable_method, "ibm,a2-scom") == 0) { - if (a2_scom_startup_cpu(nr, thr_idx, np)) - return -1; - } else { - printk(KERN_ERR "CPU%d: Don't understand enable-method \"%s\"\n", - nr, enable_method); - return -EINVAL; - } - - /* - * The processor is currently spinning, waiting for the - * cpu_start field to become non-zero After we set cpu_start, - * the processor will continue on to secondary_start - */ - paca[nr].cpu_start = 1; - - return 0; -} - -static int __init smp_a2_probe(void) -{ - return num_possible_cpus(); -} - -static struct smp_ops_t a2_smp_ops = { - .message_pass = NULL, /* Use smp_muxed_ipi_message_pass */ - .cause_ipi = doorbell_cause_ipi, - .probe = smp_a2_probe, - .kick_cpu = smp_a2_kick_cpu, - .setup_cpu = smp_a2_setup_cpu, -}; - -void __init a2_setup_smp(void) -{ - smp_ops = &a2_smp_ops; -} diff --git a/arch/powerpc/platforms/wsp/wsp.c b/arch/powerpc/platforms/wsp/wsp.c deleted file mode 100644 index d25cc96c21b..00000000000 --- a/arch/powerpc/platforms/wsp/wsp.c +++ /dev/null @@ -1,115 +0,0 @@ -/* - * Copyright 2008-2011, 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. - */ - -#include <linux/kernel.h> -#include <linux/of.h> -#include <linux/of_device.h> -#include <linux/smp.h> -#include <linux/delay.h> -#include <linux/time.h> - -#include <asm/scom.h> - -#include "wsp.h" -#include "ics.h" - -#define WSP_SOC_COMPATIBLE "ibm,wsp-soc" -#define PBIC_COMPATIBLE "ibm,wsp-pbic" -#define COPRO_COMPATIBLE "ibm,wsp-coprocessor" - -static int __init wsp_probe_buses(void) -{ - static __initdata struct of_device_id bus_ids[] = { - /* - * every node in between needs to be here or you won't - * find it - */ - { .compatible = WSP_SOC_COMPATIBLE, }, - { .compatible = PBIC_COMPATIBLE, }, - { .compatible = COPRO_COMPATIBLE, }, - {}, - }; - of_platform_bus_probe(NULL, bus_ids, NULL); - - return 0; -} - -void __init wsp_setup_arch(void) -{ - /* init to some ~sane value until calibrate_delay() runs */ - loops_per_jiffy = 50000000; - - scom_init_wsp(); - - /* Setup SMP callback */ -#ifdef CONFIG_SMP - a2_setup_smp(); -#endif -#ifdef CONFIG_PCI - wsp_setup_pci(); -#endif -} - -void __init wsp_setup_irq(void) -{ - wsp_init_irq(); - opb_pic_init(); -} - - -int __init wsp_probe_devices(void) -{ - struct device_node *np; - - /* Our RTC is a ds1500. It seems to be programatically compatible - * with the ds1511 for which we have a driver so let's use that - */ - np = of_find_compatible_node(NULL, NULL, "dallas,ds1500"); - if (np != NULL) { - struct resource res; - if (of_address_to_resource(np, 0, &res) == 0) - platform_device_register_simple("ds1511", 0, &res, 1); - } - - wsp_probe_buses(); - - return 0; -} - -void wsp_halt(void) -{ - u64 val; - scom_map_t m; - struct device_node *dn; - struct device_node *mine; - struct device_node *me; - - me = of_get_cpu_node(smp_processor_id(), NULL); - mine = scom_find_parent(me); - - /* This will halt all the A2s but not power off the chip */ - for_each_node_with_property(dn, "scom-controller") { - if (dn == mine) - continue; - m = scom_map(dn, 0, 1); - - /* read-modify-write it so the HW probe does not get - * confused */ - val = scom_read(m, 0); - val |= 1; - scom_write(m, 0, val); - scom_unmap(m); - } - m = scom_map(mine, 0, 1); - val = scom_read(m, 0); - val |= 1; - scom_write(m, 0, val); - /* should never return */ - scom_unmap(m); -} diff --git a/arch/powerpc/platforms/wsp/wsp.h b/arch/powerpc/platforms/wsp/wsp.h deleted file mode 100644 index 62ef21afb89..00000000000 --- a/arch/powerpc/platforms/wsp/wsp.h +++ /dev/null @@ -1,30 +0,0 @@ -#ifndef __WSP_H -#define __WSP_H - -#include <asm/wsp.h> - -/* Devtree compatible strings for major devices */ -#define PCIE_COMPATIBLE "ibm,wsp-pciex" - -extern void wsp_setup_arch(void); -extern void wsp_setup_irq(void); -extern int wsp_probe_devices(void); -extern void wsp_halt(void); - -extern void wsp_setup_pci(void); -extern void scom_init_wsp(void); - -extern void a2_setup_smp(void); -extern int a2_scom_startup_cpu(unsigned int lcpu, int thr_idx, - struct device_node *np); -extern int smp_a2_cpu_bootable(unsigned int nr); -extern int smp_a2_kick_cpu(int nr); - -extern void opb_pic_init(void); - -/* chroma specific managment */ -extern void wsp_h8_restart(char *cmd); -extern void wsp_h8_power_off(void); -extern void __init wsp_setup_h8(void); - -#endif /* __WSP_H */ diff --git a/arch/powerpc/platforms/wsp/wsp_pci.c b/arch/powerpc/platforms/wsp/wsp_pci.c deleted file mode 100644 index 8e22f561d17..00000000000 --- a/arch/powerpc/platforms/wsp/wsp_pci.c +++ /dev/null @@ -1,1133 +0,0 @@ -/* - * Copyright 2010 Ben Herrenschmidt, 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. - */ - -#define DEBUG - -#include <linux/kernel.h> -#include <linux/pci.h> -#include <linux/delay.h> -#include <linux/string.h> -#include <linux/init.h> -#include <linux/bootmem.h> -#include <linux/irq.h> -#include <linux/interrupt.h> -#include <linux/debugfs.h> - -#include <asm/sections.h> -#include <asm/io.h> -#include <asm/prom.h> -#include <asm/pci-bridge.h> -#include <asm/machdep.h> -#include <asm/ppc-pci.h> -#include <asm/iommu.h> -#include <asm/io-workarounds.h> -#include <asm/debug.h> - -#include "wsp.h" -#include "wsp_pci.h" -#include "msi.h" - - -/* Max number of TVTs for one table. Only 32-bit tables can use - * multiple TVTs and so the max currently supported is thus 8 - * since only 2G of DMA space is supported - */ -#define MAX_TABLE_TVT_COUNT 8 - -struct wsp_dma_table { - struct list_head link; - struct iommu_table table; - struct wsp_phb *phb; - struct page *tces[MAX_TABLE_TVT_COUNT]; -}; - -/* We support DMA regions from 0...2G in 32bit space (no support for - * 64-bit DMA just yet). Each device gets a separate TCE table (TVT - * entry) with validation enabled (though not supported by SimiCS - * just yet). - * - * To simplify things, we divide this 2G space into N regions based - * on the constant below which could be turned into a tunable eventually - * - * We then assign dynamically those regions to devices as they show up. - * - * We use a bitmap as an allocator for these. - * - * Tables are allocated/created dynamically as devices are discovered, - * multiple TVT entries are used if needed - * - * When 64-bit DMA support is added we should simply use a separate set - * of larger regions (the HW supports 64 TVT entries). We can - * additionally create a bypass region in 64-bit space for performances - * though that would have a cost in term of security. - * - * If you set NUM_DMA32_REGIONS to 1, then a single table is shared - * for all devices and bus/dev/fn validation is disabled - * - * Note that a DMA32 region cannot be smaller than 256M so the max - * supported here for now is 8. We don't yet support sharing regions - * between multiple devices so the max number of devices supported - * is MAX_TABLE_TVT_COUNT. - */ -#define NUM_DMA32_REGIONS 1 - -struct wsp_phb { - struct pci_controller *hose; - - /* Lock controlling access to the list of dma tables. - * It does -not- protect against dma_* operations on - * those tables, those should be stopped before an entry - * is removed from the list. - * - * The lock is also used for error handling operations - */ - spinlock_t lock; - struct list_head dma_tables; - unsigned long dma32_map; - unsigned long dma32_base; - unsigned int dma32_num_regions; - unsigned long dma32_region_size; - - /* Debugfs stuff */ - struct dentry *ddir; - - struct list_head all; -}; -static LIST_HEAD(wsp_phbs); - -//#define cfg_debug(fmt...) pr_debug(fmt) -#define cfg_debug(fmt...) - - -static int wsp_pcie_read_config(struct pci_bus *bus, unsigned int devfn, - int offset, int len, u32 *val) -{ - struct pci_controller *hose; - int suboff; - u64 addr; - - hose = pci_bus_to_host(bus); - if (hose == NULL) - return PCIBIOS_DEVICE_NOT_FOUND; - if (offset >= 0x1000) - return PCIBIOS_BAD_REGISTER_NUMBER; - addr = PCIE_REG_CA_ENABLE | - ((u64)bus->number) << PCIE_REG_CA_BUS_SHIFT | - ((u64)devfn) << PCIE_REG_CA_FUNC_SHIFT | - ((u64)offset & ~3) << PCIE_REG_CA_REG_SHIFT; - suboff = offset & 3; - - /* - * Note: the caller has already checked that offset is - * suitably aligned and that len is 1, 2 or 4. - */ - - switch (len) { - case 1: - addr |= (0x8ul >> suboff) << PCIE_REG_CA_BE_SHIFT; - out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr); - *val = (in_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA) - >> (suboff << 3)) & 0xff; - cfg_debug("read 1 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%02x\n", - bus->number, devfn >> 3, devfn & 7, - offset, suboff, addr, *val); - break; - case 2: - addr |= (0xcul >> suboff) << PCIE_REG_CA_BE_SHIFT; - out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr); - *val = (in_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA) - >> (suboff << 3)) & 0xffff; - cfg_debug("read 2 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%04x\n", - bus->number, devfn >> 3, devfn & 7, - offset, suboff, addr, *val); - break; - default: - addr |= 0xful << PCIE_REG_CA_BE_SHIFT; - out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr); - *val = in_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA); - cfg_debug("read 4 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%08x\n", - bus->number, devfn >> 3, devfn & 7, - offset, suboff, addr, *val); - break; - } - return PCIBIOS_SUCCESSFUL; -} - -static int wsp_pcie_write_config(struct pci_bus *bus, unsigned int devfn, - int offset, int len, u32 val) -{ - struct pci_controller *hose; - int suboff; - u64 addr; - - hose = pci_bus_to_host(bus); - if (hose == NULL) - return PCIBIOS_DEVICE_NOT_FOUND; - if (offset >= 0x1000) - return PCIBIOS_BAD_REGISTER_NUMBER; - addr = PCIE_REG_CA_ENABLE | - ((u64)bus->number) << PCIE_REG_CA_BUS_SHIFT | - ((u64)devfn) << PCIE_REG_CA_FUNC_SHIFT | - ((u64)offset & ~3) << PCIE_REG_CA_REG_SHIFT; - suboff = offset & 3; - - /* - * Note: the caller has already checked that offset is - * suitably aligned and that len is 1, 2 or 4. - */ - switch (len) { - case 1: - addr |= (0x8ul >> suboff) << PCIE_REG_CA_BE_SHIFT; - val <<= suboff << 3; - out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr); - out_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA, val); - cfg_debug("write 1 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%02x\n", - bus->number, devfn >> 3, devfn & 7, - offset, suboff, addr, val); - break; - case 2: - addr |= (0xcul >> suboff) << PCIE_REG_CA_BE_SHIFT; - val <<= suboff << 3; - out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr); - out_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA, val); - cfg_debug("write 2 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%04x\n", - bus->number, devfn >> 3, devfn & 7, - offset, suboff, addr, val); - break; - default: - addr |= 0xful << PCIE_REG_CA_BE_SHIFT; - out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr); - out_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA, val); - cfg_debug("write 4 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%08x\n", - bus->number, devfn >> 3, devfn & 7, - offset, suboff, addr, val); - break; - } - return PCIBIOS_SUCCESSFUL; -} - -static struct pci_ops wsp_pcie_pci_ops = -{ - .read = wsp_pcie_read_config, - .write = wsp_pcie_write_config, -}; - -#define TCE_SHIFT 12 -#define TCE_PAGE_SIZE (1 << TCE_SHIFT) -#define TCE_PCI_WRITE 0x2 /* write from PCI allowed */ -#define TCE_PCI_READ 0x1 /* read from PCI allowed */ -#define TCE_RPN_MASK 0x3fffffffffful /* 42-bit RPN (4K pages) */ -#define TCE_RPN_SHIFT 12 - -//#define dma_debug(fmt...) pr_debug(fmt) -#define dma_debug(fmt...) - -static int tce_build_wsp(struct iommu_table *tbl, long index, long npages, - unsigned long uaddr, enum dma_data_direction direction, - struct dma_attrs *attrs) -{ - struct wsp_dma_table *ptbl = container_of(tbl, - struct wsp_dma_table, - table); - u64 proto_tce; - u64 *tcep; - u64 rpn; - - proto_tce = TCE_PCI_READ; -#ifdef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS - proto_tce |= TCE_PCI_WRITE; -#else - if (direction != DMA_TO_DEVICE) - proto_tce |= TCE_PCI_WRITE; -#endif - - /* XXX Make this faster by factoring out the page address for - * within a TCE table - */ - while (npages--) { - /* We don't use it->base as the table can be scattered */ - tcep = (u64 *)page_address(ptbl->tces[index >> 16]); - tcep += (index & 0xffff); - - /* can't move this out since we might cross LMB boundary */ - rpn = __pa(uaddr) >> TCE_SHIFT; - *tcep = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT; - - dma_debug("[DMA] TCE %p set to 0x%016llx (dma addr: 0x%lx)\n", - tcep, *tcep, (tbl->it_offset + index) << IOMMU_PAGE_SHIFT); - - uaddr += TCE_PAGE_SIZE; - index++; - } - return 0; -} - -static void tce_free_wsp(struct iommu_table *tbl, long index, long npages) -{ - struct wsp_dma_table *ptbl = container_of(tbl, - struct wsp_dma_table, - table); -#ifndef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS - struct pci_controller *hose = ptbl->phb->hose; -#endif - u64 *tcep; - - /* XXX Make this faster by factoring out the page address for - * within a TCE table. Also use line-kill option to kill multiple - * TCEs at once - */ - while (npages--) { - /* We don't use it->base as the table can be scattered */ - tcep = (u64 *)page_address(ptbl->tces[index >> 16]); - tcep += (index & 0xffff); - dma_debug("[DMA] TCE %p cleared\n", tcep); - *tcep = 0; -#ifndef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS - /* Don't write there since it would pollute other MMIO accesses */ - out_be64(hose->cfg_data + PCIE_REG_TCE_KILL, - PCIE_REG_TCEKILL_SINGLE | PCIE_REG_TCEKILL_PS_4K | - (__pa(tcep) & PCIE_REG_TCEKILL_ADDR_MASK)); -#endif - index++; - } -} - -static struct wsp_dma_table *wsp_pci_create_dma32_table(struct wsp_phb *phb, - unsigned int region, - struct pci_dev *validate) -{ - struct pci_controller *hose = phb->hose; - unsigned long size = phb->dma32_region_size; - unsigned long addr = phb->dma32_region_size * region + phb->dma32_base; - struct wsp_dma_table *tbl; - int tvts_per_table, i, tvt, nid; - unsigned long flags; - - nid = of_node_to_nid(phb->hose->dn); - - /* Calculate how many TVTs are needed */ - tvts_per_table = size / 0x10000000; - if (tvts_per_table == 0) - tvts_per_table = 1; - - /* Calculate the base TVT index. We know all tables have the same - * size so we just do a simple multiply here - */ - tvt = region * tvts_per_table; - - pr_debug(" Region : %d\n", region); - pr_debug(" DMA range : 0x%08lx..0x%08lx\n", addr, addr + size - 1); - pr_debug(" Number of TVTs : %d\n", tvts_per_table); - pr_debug(" Base TVT : %d\n", tvt); - pr_debug(" Node : %d\n", nid); - - tbl = kzalloc_node(sizeof(struct wsp_dma_table), GFP_KERNEL, nid); - if (!tbl) - return ERR_PTR(-ENOMEM); - tbl->phb = phb; - - /* Create as many TVTs as needed, each represents 256M at most */ - for (i = 0; i < tvts_per_table; i++) { - u64 tvt_data1, tvt_data0; - - /* Allocate table. We use a 4K TCE size for now always so - * one table is always 8 * (258M / 4K) == 512K - */ - tbl->tces[i] = alloc_pages_node(nid, GFP_KERNEL, get_order(0x80000)); - if (tbl->tces[i] == NULL) - goto fail; - memset(page_address(tbl->tces[i]), 0, 0x80000); - - pr_debug(" TCE table %d at : %p\n", i, page_address(tbl->tces[i])); - - /* Table size. We currently set it to be the whole 256M region */ - tvt_data0 = 2ull << IODA_TVT0_TCE_TABLE_SIZE_SHIFT; - /* IO page size set to 4K */ - tvt_data1 = 1ull << IODA_TVT1_IO_PAGE_SIZE_SHIFT; - /* Shift in the address */ - tvt_data0 |= __pa(page_address(tbl->tces[i])) << IODA_TVT0_TTA_SHIFT; - - /* Validation stuff. We only validate fully bus/dev/fn for now - * one day maybe we can group devices but that isn't the case - * at the moment - */ - if (validate) { - tvt_data0 |= IODA_TVT0_BUSNUM_VALID_MASK; - tvt_data0 |= validate->bus->number; - tvt_data1 |= IODA_TVT1_DEVNUM_VALID; - tvt_data1 |= ((u64)PCI_SLOT(validate->devfn)) - << IODA_TVT1_DEVNUM_VALUE_SHIFT; - tvt_data1 |= IODA_TVT1_FUNCNUM_VALID; - tvt_data1 |= ((u64)PCI_FUNC(validate->devfn)) - << IODA_TVT1_FUNCNUM_VALUE_SHIFT; - } - - /* XX PE number is always 0 for now */ - - /* Program the values using the PHB lock */ - spin_lock_irqsave(&phb->lock, flags); - out_be64(hose->cfg_data + PCIE_REG_IODA_ADDR, - (tvt + i) | PCIE_REG_IODA_AD_TBL_TVT); - out_be64(hose->cfg_data + PCIE_REG_IODA_DATA1, tvt_data1); - out_be64(hose->cfg_data + PCIE_REG_IODA_DATA0, tvt_data0); - spin_unlock_irqrestore(&phb->lock, flags); - } - - /* Init bits and pieces */ - tbl->table.it_blocksize = 16; - tbl->table.it_offset = addr >> IOMMU_PAGE_SHIFT; - tbl->table.it_size = size >> IOMMU_PAGE_SHIFT; - - /* - * It's already blank but we clear it anyway. - * Consider an aditiona interface that makes cleaing optional - */ - iommu_init_table(&tbl->table, nid); - - list_add(&tbl->link, &phb->dma_tables); - return tbl; - - fail: - pr_debug(" Failed to allocate a 256M TCE table !\n"); - for (i = 0; i < tvts_per_table; i++) - if (tbl->tces[i]) - __free_pages(tbl->tces[i], get_order(0x80000)); - kfree(tbl); - return ERR_PTR(-ENOMEM); -} - -static void wsp_pci_dma_dev_setup(struct pci_dev *pdev) -{ - struct dev_archdata *archdata = &pdev->dev.archdata; - struct pci_controller *hose = pci_bus_to_host(pdev->bus); - struct wsp_phb *phb = hose->private_data; - struct wsp_dma_table *table = NULL; - unsigned long flags; - int i; - - /* Don't assign an iommu table to a bridge */ - if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE) - return; - - pr_debug("%s: Setting up DMA...\n", pci_name(pdev)); - - spin_lock_irqsave(&phb->lock, flags); - - /* If only one region, check if it already exist */ - if (phb->dma32_num_regions == 1) { - spin_unlock_irqrestore(&phb->lock, flags); - if (list_empty(&phb->dma_tables)) - table = wsp_pci_create_dma32_table(phb, 0, NULL); - else - table = list_first_entry(&phb->dma_tables, - struct wsp_dma_table, - link); - } else { - /* else find a free region */ - for (i = 0; i < phb->dma32_num_regions && !table; i++) { - if (__test_and_set_bit(i, &phb->dma32_map)) - continue; - spin_unlock_irqrestore(&phb->lock, flags); - table = wsp_pci_create_dma32_table(phb, i, pdev); - } - } - - /* Check if we got an error */ - if (IS_ERR(table)) { - pr_err("%s: Failed to create DMA table, err %ld !\n", - pci_name(pdev), PTR_ERR(table)); - return; - } - - /* Or a valid table */ - if (table) { - pr_info("%s: Setup iommu: 32-bit DMA region 0x%08lx..0x%08lx\n", - pci_name(pdev), - table->table.it_offset << IOMMU_PAGE_SHIFT, - (table->table.it_offset << IOMMU_PAGE_SHIFT) - + phb->dma32_region_size - 1); - archdata->dma_data.iommu_table_base = &table->table; - return; - } - - /* Or no room */ - spin_unlock_irqrestore(&phb->lock, flags); - pr_err("%s: Out of DMA space !\n", pci_name(pdev)); -} - -static void __init wsp_pcie_configure_hw(struct pci_controller *hose) -{ - u64 val; - int i; - -#define DUMP_REG(x) \ - pr_debug("%-30s : 0x%016llx\n", #x, in_be64(hose->cfg_data + x)) - - /* - * Some WSP variants has a bogus class code by default in the PCI-E - * root complex's built-in P2P bridge - */ - val = in_be64(hose->cfg_data + PCIE_REG_SYS_CFG1); - pr_debug("PCI-E SYS_CFG1 : 0x%llx\n", val); - out_be64(hose->cfg_data + PCIE_REG_SYS_CFG1, - (val & ~PCIE_REG_SYS_CFG1_CLASS_CODE) | (PCI_CLASS_BRIDGE_PCI << 8)); - pr_debug("PCI-E SYS_CFG1 : 0x%llx\n", in_be64(hose->cfg_data + PCIE_REG_SYS_CFG1)); - -#ifdef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS - /* XXX Disable TCE caching, it doesn't work on DD1 */ - out_be64(hose->cfg_data + 0xe50, - in_be64(hose->cfg_data + 0xe50) | (3ull << 62)); - printk("PCI-E DEBUG CONTROL 5 = 0x%llx\n", in_be64(hose->cfg_data + 0xe50)); -#endif - - /* Configure M32A and IO. IO is hard wired to be 1M for now */ - out_be64(hose->cfg_data + PCIE_REG_IO_BASE_ADDR, hose->io_base_phys); - out_be64(hose->cfg_data + PCIE_REG_IO_BASE_MASK, - (~(hose->io_resource.end - hose->io_resource.start)) & - 0x3fffffff000ul); - out_be64(hose->cfg_data + PCIE_REG_IO_START_ADDR, 0 | 1); - - out_be64(hose->cfg_data + PCIE_REG_M32A_BASE_ADDR, - hose->mem_resources[0].start); - printk("Want to write to M32A_BASE_MASK : 0x%llx\n", - (~(hose->mem_resources[0].end - - hose->mem_resources[0].start)) & 0x3ffffff0000ul); - out_be64(hose->cfg_data + PCIE_REG_M32A_BASE_MASK, - (~(hose->mem_resources[0].end - - hose->mem_resources[0].start)) & 0x3ffffff0000ul); - out_be64(hose->cfg_data + PCIE_REG_M32A_START_ADDR, - (hose->mem_resources[0].start - hose->pci_mem_offset) | 1); - - /* Clear all TVT entries - * - * XX Might get TVT count from device-tree - */ - for (i = 0; i < IODA_TVT_COUNT; i++) { - out_be64(hose->cfg_data + PCIE_REG_IODA_ADDR, - PCIE_REG_IODA_AD_TBL_TVT | i); - out_be64(hose->cfg_data + PCIE_REG_IODA_DATA1, 0); - out_be64(hose->cfg_data + PCIE_REG_IODA_DATA0, 0); - } - - /* Kill the TCE cache */ - out_be64(hose->cfg_data + PCIE_REG_PHB_CONFIG, - in_be64(hose->cfg_data + PCIE_REG_PHB_CONFIG) | - PCIE_REG_PHBC_64B_TCE_EN); - - /* Enable 32 & 64-bit MSIs, IO space and M32A */ - val = PCIE_REG_PHBC_32BIT_MSI_EN | - PCIE_REG_PHBC_IO_EN | - PCIE_REG_PHBC_64BIT_MSI_EN | - PCIE_REG_PHBC_M32A_EN; - if (iommu_is_off) - val |= PCIE_REG_PHBC_DMA_XLATE_BYPASS; - pr_debug("Will write config: 0x%llx\n", val); - out_be64(hose->cfg_data + PCIE_REG_PHB_CONFIG, val); - - /* Enable error reporting */ - out_be64(hose->cfg_data + 0xe00, - in_be64(hose->cfg_data + 0xe00) | 0x0008000000000000ull); - - /* Mask an error that's generated when doing config space probe - * - * XXX Maybe we should only mask it around config space cycles... that or - * ignore it when we know we had a config space cycle recently ? - */ - out_be64(hose->cfg_data + PCIE_REG_DMA_ERR_STATUS_MASK, 0x8000000000000000ull); - out_be64(hose->cfg_data + PCIE_REG_DMA_ERR1_STATUS_MASK, 0x8000000000000000ull); - - /* Enable UTL errors, for now, all of them got to UTL irq 1 - * - * We similarily mask one UTL error caused apparently during normal - * probing. We also mask the link up error - */ - out_be64(hose->cfg_data + PCIE_UTL_SYS_BUS_AGENT_ERR_SEV, 0); - out_be64(hose->cfg_data + PCIE_UTL_RC_ERR_SEVERITY, 0); - out_be64(hose->cfg_data + PCIE_UTL_PCIE_PORT_ERROR_SEV, 0); - out_be64(hose->cfg_data + PCIE_UTL_SYS_BUS_AGENT_IRQ_EN, 0xffffffff00000000ull); - out_be64(hose->cfg_data + PCIE_UTL_PCIE_PORT_IRQ_EN, 0xff5fffff00000000ull); - out_be64(hose->cfg_data + PCIE_UTL_EP_ERR_IRQ_EN, 0xffffffff00000000ull); - - DUMP_REG(PCIE_REG_IO_BASE_ADDR); - DUMP_REG(PCIE_REG_IO_BASE_MASK); - DUMP_REG(PCIE_REG_IO_START_ADDR); - DUMP_REG(PCIE_REG_M32A_BASE_ADDR); - DUMP_REG(PCIE_REG_M32A_BASE_MASK); - DUMP_REG(PCIE_REG_M32A_START_ADDR); - DUMP_REG(PCIE_REG_M32B_BASE_ADDR); - DUMP_REG(PCIE_REG_M32B_BASE_MASK); - DUMP_REG(PCIE_REG_M32B_START_ADDR); - DUMP_REG(PCIE_REG_M64_BASE_ADDR); - DUMP_REG(PCIE_REG_M64_BASE_MASK); - DUMP_REG(PCIE_REG_M64_START_ADDR); - DUMP_REG(PCIE_REG_PHB_CONFIG); -} - -static void wsp_pci_wait_io_idle(struct wsp_phb *phb, unsigned long port) -{ - u64 val; - int i; - - for (i = 0; i < 10000; i++) { - val = in_be64(phb->hose->cfg_data + 0xe08); - if ((val & 0x1900000000000000ull) == 0x0100000000000000ull) - return; - udelay(1); - } - pr_warning("PCI IO timeout on domain %d port 0x%lx\n", - phb->hose->global_number, port); -} - -#define DEF_PCI_AC_RET_pio(name, ret, at, al, aa) \ -static ret wsp_pci_##name at \ -{ \ - struct iowa_bus *bus; \ - struct wsp_phb *phb; \ - unsigned long flags; \ - ret rval; \ - bus = iowa_pio_find_bus(aa); \ - WARN_ON(!bus); \ - phb = bus->private; \ - spin_lock_irqsave(&phb->lock, flags); \ - wsp_pci_wait_io_idle(phb, aa); \ - rval = __do_##name al; \ - spin_unlock_irqrestore(&phb->lock, flags); \ - return rval; \ -} - -#define DEF_PCI_AC_NORET_pio(name, at, al, aa) \ -static void wsp_pci_##name at \ -{ \ - struct iowa_bus *bus; \ - struct wsp_phb *phb; \ - unsigned long flags; \ - bus = iowa_pio_find_bus(aa); \ - WARN_ON(!bus); \ - phb = bus->private; \ - spin_lock_irqsave(&phb->lock, flags); \ - wsp_pci_wait_io_idle(phb, aa); \ - __do_##name al; \ - spin_unlock_irqrestore(&phb->lock, flags); \ -} - -#define DEF_PCI_AC_RET_mem(name, ret, at, al, aa) -#define DEF_PCI_AC_NORET_mem(name, at, al, aa) - -#define DEF_PCI_AC_RET(name, ret, at, al, space, aa) \ - DEF_PCI_AC_RET_##space(name, ret, at, al, aa) - -#define DEF_PCI_AC_NORET(name, at, al, space, aa) \ - DEF_PCI_AC_NORET_##space(name, at, al, aa) \ - - -#include <asm/io-defs.h> - -#undef DEF_PCI_AC_RET -#undef DEF_PCI_AC_NORET - -static struct ppc_pci_io wsp_pci_iops = { - .inb = wsp_pci_inb, - .inw = wsp_pci_inw, - .inl = wsp_pci_inl, - .outb = wsp_pci_outb, - .outw = wsp_pci_outw, - .outl = wsp_pci_outl, - .insb = wsp_pci_insb, - .insw = wsp_pci_insw, - .insl = wsp_pci_insl, - .outsb = wsp_pci_outsb, - .outsw = wsp_pci_outsw, - .outsl = wsp_pci_outsl, -}; - -static int __init wsp_setup_one_phb(struct device_node *np) -{ - struct pci_controller *hose; - struct wsp_phb *phb; - - pr_info("PCI: Setting up PCIe host bridge 0x%s\n", np->full_name); - - phb = zalloc_maybe_bootmem(sizeof(struct wsp_phb), GFP_KERNEL); - if (!phb) - return -ENOMEM; - hose = pcibios_alloc_controller(np); - if (!hose) { - /* Can't really free the phb */ - return -ENOMEM; - } - hose->private_data = phb; - phb->hose = hose; - - INIT_LIST_HEAD(&phb->dma_tables); - spin_lock_init(&phb->lock); - - /* XXX Use bus-range property ? */ - hose->first_busno = 0; - hose->last_busno = 0xff; - - /* We use cfg_data as the address for the whole bridge MMIO space - */ - hose->cfg_data = of_iomap(hose->dn, 0); - - pr_debug("PCIe registers mapped at 0x%p\n", hose->cfg_data); - - /* Get the ranges of the device-tree */ - pci_process_bridge_OF_ranges(hose, np, 0); - - /* XXX Force re-assigning of everything for now */ - pci_add_flags(PCI_REASSIGN_ALL_BUS | PCI_REASSIGN_ALL_RSRC | - PCI_ENABLE_PROC_DOMAINS); - - /* Calculate how the TCE space is divided */ - phb->dma32_base = 0; - phb->dma32_num_regions = NUM_DMA32_REGIONS; - if (phb->dma32_num_regions > MAX_TABLE_TVT_COUNT) { - pr_warning("IOMMU: Clamped to %d DMA32 regions\n", - MAX_TABLE_TVT_COUNT); - phb->dma32_num_regions = MAX_TABLE_TVT_COUNT; - } - phb->dma32_region_size = 0x80000000 / phb->dma32_num_regions; - - BUG_ON(!is_power_of_2(phb->dma32_region_size)); - - /* Setup config ops */ - hose->ops = &wsp_pcie_pci_ops; - - /* Configure the HW */ - wsp_pcie_configure_hw(hose); - - /* Instanciate IO workarounds */ - iowa_register_bus(hose, &wsp_pci_iops, NULL, phb); -#ifdef CONFIG_PCI_MSI - wsp_setup_phb_msi(hose); -#endif - - /* Add to global list */ - list_add(&phb->all, &wsp_phbs); - - return 0; -} - -void __init wsp_setup_pci(void) -{ - struct device_node *np; - int rc; - - /* Find host bridges */ - for_each_compatible_node(np, "pciex", PCIE_COMPATIBLE) { - rc = wsp_setup_one_phb(np); - if (rc) - pr_err("Failed to setup PCIe bridge %s, rc=%d\n", - np->full_name, rc); - } - - /* Establish device-tree linkage */ - pci_devs_phb_init(); - - /* Set DMA ops to use TCEs */ - if (iommu_is_off) { - pr_info("PCI-E: Disabled TCEs, using direct DMA\n"); - set_pci_dma_ops(&dma_direct_ops); - } else { - ppc_md.pci_dma_dev_setup = wsp_pci_dma_dev_setup; - ppc_md.tce_build = tce_build_wsp; - ppc_md.tce_free = tce_free_wsp; - set_pci_dma_ops(&dma_iommu_ops); - } -} - -#define err_debug(fmt...) pr_debug(fmt) -//#define err_debug(fmt...) - -static int __init wsp_pci_get_err_irq_no_dt(struct device_node *np) -{ - const u32 *prop; - int hw_irq; - - /* Ok, no interrupts property, let's try to find our child P2P */ - np = of_get_next_child(np, NULL); - if (np == NULL) - return 0; - - /* Grab it's interrupt map */ - prop = of_get_property(np, "interrupt-map", NULL); - if (prop == NULL) - return 0; - - /* Grab one of the interrupts in there, keep the low 4 bits */ - hw_irq = prop[5] & 0xf; - - /* 0..4 for PHB 0 and 5..9 for PHB 1 */ - if (hw_irq < 5) - hw_irq = 4; - else - hw_irq = 9; - hw_irq |= prop[5] & ~0xf; - - err_debug("PCI: Using 0x%x as error IRQ for %s\n", - hw_irq, np->parent->full_name); - return irq_create_mapping(NULL, hw_irq); -} - -static const struct { - u32 offset; - const char *name; -} wsp_pci_regs[] = { -#define DREG(x) { PCIE_REG_##x, #x } -#define DUTL(x) { PCIE_UTL_##x, "UTL_" #x } - /* Architected registers except CONFIG_ and IODA - * to avoid side effects - */ - DREG(DMA_CHAN_STATUS), - DREG(CPU_LOADSTORE_STATUS), - DREG(LOCK0), - DREG(LOCK1), - DREG(PHB_CONFIG), - DREG(IO_BASE_ADDR), - DREG(IO_BASE_MASK), - DREG(IO_START_ADDR), - DREG(M32A_BASE_ADDR), - DREG(M32A_BASE_MASK), - DREG(M32A_START_ADDR), - DREG(M32B_BASE_ADDR), - DREG(M32B_BASE_MASK), - DREG(M32B_START_ADDR), - DREG(M64_BASE_ADDR), - DREG(M64_BASE_MASK), - DREG(M64_START_ADDR), - DREG(TCE_KILL), - DREG(LOCK2), - DREG(PHB_GEN_CAP), - DREG(PHB_TCE_CAP), - DREG(PHB_IRQ_CAP), - DREG(PHB_EEH_CAP), - DREG(PAPR_ERR_INJ_CONTROL), - DREG(PAPR_ERR_INJ_ADDR), - DREG(PAPR_ERR_INJ_MASK), - - /* UTL core regs */ - DUTL(SYS_BUS_CONTROL), - DUTL(STATUS), - DUTL(SYS_BUS_AGENT_STATUS), - DUTL(SYS_BUS_AGENT_ERR_SEV), - DUTL(SYS_BUS_AGENT_IRQ_EN), - DUTL(SYS_BUS_BURST_SZ_CONF), - DUTL(REVISION_ID), - DUTL(OUT_POST_HDR_BUF_ALLOC), - DUTL(OUT_POST_DAT_BUF_ALLOC), - DUTL(IN_POST_HDR_BUF_ALLOC), - DUTL(IN_POST_DAT_BUF_ALLOC), - DUTL(OUT_NP_BUF_ALLOC), - DUTL(IN_NP_BUF_ALLOC), - DUTL(PCIE_TAGS_ALLOC), - DUTL(GBIF_READ_TAGS_ALLOC), - - DUTL(PCIE_PORT_CONTROL), - DUTL(PCIE_PORT_STATUS), - DUTL(PCIE_PORT_ERROR_SEV), - DUTL(PCIE_PORT_IRQ_EN), - DUTL(RC_STATUS), - DUTL(RC_ERR_SEVERITY), - DUTL(RC_IRQ_EN), - DUTL(EP_STATUS), - DUTL(EP_ERR_SEVERITY), - DUTL(EP_ERR_IRQ_EN), - DUTL(PCI_PM_CTRL1), - DUTL(PCI_PM_CTRL2), - - /* PCIe stack regs */ - DREG(SYSTEM_CONFIG1), - DREG(SYSTEM_CONFIG2), - DREG(EP_SYSTEM_CONFIG), - DREG(EP_FLR), - DREG(EP_BAR_CONFIG), - DREG(LINK_CONFIG), - DREG(PM_CONFIG), - DREG(DLP_CONTROL), - DREG(DLP_STATUS), - DREG(ERR_REPORT_CONTROL), - DREG(SLOT_CONTROL1), - DREG(SLOT_CONTROL2), - DREG(UTL_CONFIG), - DREG(BUFFERS_CONFIG), - DREG(ERROR_INJECT), - DREG(SRIOV_CONFIG), - DREG(PF0_SRIOV_STATUS), - DREG(PF1_SRIOV_STATUS), - DREG(PORT_NUMBER), - DREG(POR_SYSTEM_CONFIG), - - /* Internal logic regs */ - DREG(PHB_VERSION), - DREG(RESET), - DREG(PHB_CONTROL), - DREG(PHB_TIMEOUT_CONTROL1), - DREG(PHB_QUIESCE_DMA), - DREG(PHB_DMA_READ_TAG_ACTV), - DREG(PHB_TCE_READ_TAG_ACTV), - - /* FIR registers */ - DREG(LEM_FIR_ACCUM), - DREG(LEM_FIR_AND_MASK), - DREG(LEM_FIR_OR_MASK), - DREG(LEM_ACTION0), - DREG(LEM_ACTION1), - DREG(LEM_ERROR_MASK), - DREG(LEM_ERROR_AND_MASK), - DREG(LEM_ERROR_OR_MASK), - - /* Error traps registers */ - DREG(PHB_ERR_STATUS), - DREG(PHB_ERR_STATUS), - DREG(PHB_ERR1_STATUS), - DREG(PHB_ERR_INJECT), - DREG(PHB_ERR_LEM_ENABLE), - DREG(PHB_ERR_IRQ_ENABLE), - DREG(PHB_ERR_FREEZE_ENABLE), - DREG(PHB_ERR_SIDE_ENABLE), - DREG(PHB_ERR_LOG_0), - DREG(PHB_ERR_LOG_1), - DREG(PHB_ERR_STATUS_MASK), - DREG(PHB_ERR1_STATUS_MASK), - DREG(MMIO_ERR_STATUS), - DREG(MMIO_ERR1_STATUS), - DREG(MMIO_ERR_INJECT), - DREG(MMIO_ERR_LEM_ENABLE), - DREG(MMIO_ERR_IRQ_ENABLE), - DREG(MMIO_ERR_FREEZE_ENABLE), - DREG(MMIO_ERR_SIDE_ENABLE), - DREG(MMIO_ERR_LOG_0), - DREG(MMIO_ERR_LOG_1), - DREG(MMIO_ERR_STATUS_MASK), - DREG(MMIO_ERR1_STATUS_MASK), - DREG(DMA_ERR_STATUS), - DREG(DMA_ERR1_STATUS), - DREG(DMA_ERR_INJECT), - DREG(DMA_ERR_LEM_ENABLE), - DREG(DMA_ERR_IRQ_ENABLE), - DREG(DMA_ERR_FREEZE_ENABLE), - DREG(DMA_ERR_SIDE_ENABLE), - DREG(DMA_ERR_LOG_0), - DREG(DMA_ERR_LOG_1), - DREG(DMA_ERR_STATUS_MASK), - DREG(DMA_ERR1_STATUS_MASK), - - /* Debug and Trace registers */ - DREG(PHB_DEBUG_CONTROL0), - DREG(PHB_DEBUG_STATUS0), - DREG(PHB_DEBUG_CONTROL1), - DREG(PHB_DEBUG_STATUS1), - DREG(PHB_DEBUG_CONTROL2), - DREG(PHB_DEBUG_STATUS2), - DREG(PHB_DEBUG_CONTROL3), - DREG(PHB_DEBUG_STATUS3), - DREG(PHB_DEBUG_CONTROL4), - DREG(PHB_DEBUG_STATUS4), - DREG(PHB_DEBUG_CONTROL5), - DREG(PHB_DEBUG_STATUS5), - - /* Don't seem to exist ... - DREG(PHB_DEBUG_CONTROL6), - DREG(PHB_DEBUG_STATUS6), - */ -}; - -static int wsp_pci_regs_show(struct seq_file *m, void *private) -{ - struct wsp_phb *phb = m->private; - struct pci_controller *hose = phb->hose; - int i; - - for (i = 0; i < ARRAY_SIZE(wsp_pci_regs); i++) { - /* Skip write-only regs */ - if (wsp_pci_regs[i].offset == 0xc08 || - wsp_pci_regs[i].offset == 0xc10 || - wsp_pci_regs[i].offset == 0xc38 || - wsp_pci_regs[i].offset == 0xc40) - continue; - seq_printf(m, "0x%03x: 0x%016llx %s\n", - wsp_pci_regs[i].offset, - in_be64(hose->cfg_data + wsp_pci_regs[i].offset), - wsp_pci_regs[i].name); - } - return 0; -} - -static int wsp_pci_regs_open(struct inode *inode, struct file *file) -{ - return single_open(file, wsp_pci_regs_show, inode->i_private); -} - -static const struct file_operations wsp_pci_regs_fops = { - .open = wsp_pci_regs_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static int wsp_pci_reg_set(void *data, u64 val) -{ - out_be64((void __iomem *)data, val); - return 0; -} - -static int wsp_pci_reg_get(void *data, u64 *val) -{ - *val = in_be64((void __iomem *)data); - return 0; -} - -DEFINE_SIMPLE_ATTRIBUTE(wsp_pci_reg_fops, wsp_pci_reg_get, wsp_pci_reg_set, "0x%llx\n"); - -static irqreturn_t wsp_pci_err_irq(int irq, void *dev_id) -{ - struct wsp_phb *phb = dev_id; - struct pci_controller *hose = phb->hose; - irqreturn_t handled = IRQ_NONE; - struct wsp_pcie_err_log_data ed; - - pr_err("PCI: Error interrupt on %s (PHB %d)\n", - hose->dn->full_name, hose->global_number); - again: - memset(&ed, 0, sizeof(ed)); - - /* Read and clear UTL errors */ - ed.utl_sys_err = in_be64(hose->cfg_data + PCIE_UTL_SYS_BUS_AGENT_STATUS); - if (ed.utl_sys_err) - out_be64(hose->cfg_data + PCIE_UTL_SYS_BUS_AGENT_STATUS, ed.utl_sys_err); - ed.utl_port_err = in_be64(hose->cfg_data + PCIE_UTL_PCIE_PORT_STATUS); - if (ed.utl_port_err) - out_be64(hose->cfg_data + PCIE_UTL_PCIE_PORT_STATUS, ed.utl_port_err); - ed.utl_rc_err = in_be64(hose->cfg_data + PCIE_UTL_RC_STATUS); - if (ed.utl_rc_err) - out_be64(hose->cfg_data + PCIE_UTL_RC_STATUS, ed.utl_rc_err); - - /* Read and clear main trap errors */ - ed.phb_err = in_be64(hose->cfg_data + PCIE_REG_PHB_ERR_STATUS); - if (ed.phb_err) { - ed.phb_err1 = in_be64(hose->cfg_data + PCIE_REG_PHB_ERR1_STATUS); - ed.phb_log0 = in_be64(hose->cfg_data + PCIE_REG_PHB_ERR_LOG_0); - ed.phb_log1 = in_be64(hose->cfg_data + PCIE_REG_PHB_ERR_LOG_1); - out_be64(hose->cfg_data + PCIE_REG_PHB_ERR1_STATUS, 0); - out_be64(hose->cfg_data + PCIE_REG_PHB_ERR_STATUS, 0); - } - ed.mmio_err = in_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_STATUS); - if (ed.mmio_err) { - ed.mmio_err1 = in_be64(hose->cfg_data + PCIE_REG_MMIO_ERR1_STATUS); - ed.mmio_log0 = in_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_LOG_0); - ed.mmio_log1 = in_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_LOG_1); - out_be64(hose->cfg_data + PCIE_REG_MMIO_ERR1_STATUS, 0); - out_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_STATUS, 0); - } - ed.dma_err = in_be64(hose->cfg_data + PCIE_REG_DMA_ERR_STATUS); - if (ed.dma_err) { - ed.dma_err1 = in_be64(hose->cfg_data + PCIE_REG_DMA_ERR1_STATUS); - ed.dma_log0 = in_be64(hose->cfg_data + PCIE_REG_DMA_ERR_LOG_0); - ed.dma_log1 = in_be64(hose->cfg_data + PCIE_REG_DMA_ERR_LOG_1); - out_be64(hose->cfg_data + PCIE_REG_DMA_ERR1_STATUS, 0); - out_be64(hose->cfg_data + PCIE_REG_DMA_ERR_STATUS, 0); - } - - /* Now print things out */ - if (ed.phb_err) { - pr_err(" PHB Error Status : 0x%016llx\n", ed.phb_err); - pr_err(" PHB First Error Status: 0x%016llx\n", ed.phb_err1); - pr_err(" PHB Error Log 0 : 0x%016llx\n", ed.phb_log0); - pr_err(" PHB Error Log 1 : 0x%016llx\n", ed.phb_log1); - } - if (ed.mmio_err) { - pr_err(" MMIO Error Status : 0x%016llx\n", ed.mmio_err); - pr_err(" MMIO First Error Status: 0x%016llx\n", ed.mmio_err1); - pr_err(" MMIO Error Log 0 : 0x%016llx\n", ed.mmio_log0); - pr_err(" MMIO Error Log 1 : 0x%016llx\n", ed.mmio_log1); - } - if (ed.dma_err) { - pr_err(" DMA Error Status : 0x%016llx\n", ed.dma_err); - pr_err(" DMA First Error Status: 0x%016llx\n", ed.dma_err1); - pr_err(" DMA Error Log 0 : 0x%016llx\n", ed.dma_log0); - pr_err(" DMA Error Log 1 : 0x%016llx\n", ed.dma_log1); - } - if (ed.utl_sys_err) - pr_err(" UTL Sys Error Status : 0x%016llx\n", ed.utl_sys_err); - if (ed.utl_port_err) - pr_err(" UTL Port Error Status : 0x%016llx\n", ed.utl_port_err); - if (ed.utl_rc_err) - pr_err(" UTL RC Error Status : 0x%016llx\n", ed.utl_rc_err); - - /* Interrupts are caused by the error traps. If we had any error there - * we loop again in case the UTL buffered some new stuff between - * going there and going to the traps - */ - if (ed.dma_err || ed.mmio_err || ed.phb_err) { - handled = IRQ_HANDLED; - goto again; - } - return handled; -} - -static void __init wsp_setup_pci_err_reporting(struct wsp_phb *phb) -{ - struct pci_controller *hose = phb->hose; - int err_irq, i, rc; - char fname[16]; - - /* Create a debugfs file for that PHB */ - sprintf(fname, "phb%d", phb->hose->global_number); - phb->ddir = debugfs_create_dir(fname, powerpc_debugfs_root); - - /* Some useful debug output */ - if (phb->ddir) { - struct dentry *d = debugfs_create_dir("regs", phb->ddir); - char tmp[64]; - - for (i = 0; i < ARRAY_SIZE(wsp_pci_regs); i++) { - sprintf(tmp, "%03x_%s", wsp_pci_regs[i].offset, - wsp_pci_regs[i].name); - debugfs_create_file(tmp, 0600, d, - hose->cfg_data + wsp_pci_regs[i].offset, - &wsp_pci_reg_fops); - } - debugfs_create_file("all_regs", 0600, phb->ddir, phb, &wsp_pci_regs_fops); - } - - /* Find the IRQ number for that PHB */ - err_irq = irq_of_parse_and_map(hose->dn, 0); - if (err_irq == 0) - /* XXX Error IRQ lacking from device-tree */ - err_irq = wsp_pci_get_err_irq_no_dt(hose->dn); - if (err_irq == 0) { - pr_err("PCI: Failed to fetch error interrupt for %s\n", - hose->dn->full_name); - return; - } - /* Request it */ - rc = request_irq(err_irq, wsp_pci_err_irq, 0, "wsp_pci error", phb); - if (rc) { - pr_err("PCI: Failed to request interrupt for %s\n", - hose->dn->full_name); - } - /* Enable interrupts for all errors for now */ - out_be64(hose->cfg_data + PCIE_REG_PHB_ERR_IRQ_ENABLE, 0xffffffffffffffffull); - out_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_IRQ_ENABLE, 0xffffffffffffffffull); - out_be64(hose->cfg_data + PCIE_REG_DMA_ERR_IRQ_ENABLE, 0xffffffffffffffffull); -} - -/* - * This is called later to hookup with the error interrupt - */ -static int __init wsp_setup_pci_late(void) -{ - struct wsp_phb *phb; - - list_for_each_entry(phb, &wsp_phbs, all) - wsp_setup_pci_err_reporting(phb); - - return 0; -} -arch_initcall(wsp_setup_pci_late); diff --git a/arch/powerpc/platforms/wsp/wsp_pci.h b/arch/powerpc/platforms/wsp/wsp_pci.h deleted file mode 100644 index 52e9bd95250..00000000000 --- a/arch/powerpc/platforms/wsp/wsp_pci.h +++ /dev/null @@ -1,268 +0,0 @@ -/* - * Copyright 2010 Ben Herrenschmidt, 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. - */ - -#ifndef __WSP_PCI_H -#define __WSP_PCI_H - -/* Architected registers */ -#define PCIE_REG_DMA_CHAN_STATUS 0x110 -#define PCIE_REG_CPU_LOADSTORE_STATUS 0x120 - -#define PCIE_REG_CONFIG_DATA 0x130 -#define PCIE_REG_LOCK0 0x138 -#define PCIE_REG_CONFIG_ADDRESS 0x140 -#define PCIE_REG_CA_ENABLE 0x8000000000000000ull -#define PCIE_REG_CA_BUS_MASK 0x0ff0000000000000ull -#define PCIE_REG_CA_BUS_SHIFT (20+32) -#define PCIE_REG_CA_DEV_MASK 0x000f800000000000ull -#define PCIE_REG_CA_DEV_SHIFT (15+32) -#define PCIE_REG_CA_FUNC_MASK 0x0000700000000000ull -#define PCIE_REG_CA_FUNC_SHIFT (12+32) -#define PCIE_REG_CA_REG_MASK 0x00000fff00000000ull -#define PCIE_REG_CA_REG_SHIFT ( 0+32) -#define PCIE_REG_CA_BE_MASK 0x00000000f0000000ull -#define PCIE_REG_CA_BE_SHIFT ( 28) -#define PCIE_REG_LOCK1 0x148 - -#define PCIE_REG_PHB_CONFIG 0x160 -#define PCIE_REG_PHBC_64B_TCE_EN 0x2000000000000000ull -#define PCIE_REG_PHBC_MMIO_DMA_FREEZE_EN 0x1000000000000000ull -#define PCIE_REG_PHBC_32BIT_MSI_EN 0x0080000000000000ull -#define PCIE_REG_PHBC_M64_EN 0x0040000000000000ull -#define PCIE_REG_PHBC_IO_EN 0x0008000000000000ull -#define PCIE_REG_PHBC_64BIT_MSI_EN 0x0002000000000000ull -#define PCIE_REG_PHBC_M32A_EN 0x0000800000000000ull -#define PCIE_REG_PHBC_M32B_EN 0x0000400000000000ull -#define PCIE_REG_PHBC_MSI_PE_VALIDATE 0x0000200000000000ull -#define PCIE_REG_PHBC_DMA_XLATE_BYPASS 0x0000100000000000ull - -#define PCIE_REG_IO_BASE_ADDR 0x170 -#define PCIE_REG_IO_BASE_MASK 0x178 -#define PCIE_REG_IO_START_ADDR 0x180 - -#define PCIE_REG_M32A_BASE_ADDR 0x190 -#define PCIE_REG_M32A_BASE_MASK 0x198 -#define PCIE_REG_M32A_START_ADDR 0x1a0 - -#define PCIE_REG_M32B_BASE_ADDR 0x1b0 -#define PCIE_REG_M32B_BASE_MASK 0x1b8 -#define PCIE_REG_M32B_START_ADDR 0x1c0 - -#define PCIE_REG_M64_BASE_ADDR 0x1e0 -#define PCIE_REG_M64_BASE_MASK 0x1e8 -#define PCIE_REG_M64_START_ADDR 0x1f0 - -#define PCIE_REG_TCE_KILL 0x210 -#define PCIE_REG_TCEKILL_SINGLE 0x8000000000000000ull -#define PCIE_REG_TCEKILL_ADDR_MASK 0x000003fffffffff8ull -#define PCIE_REG_TCEKILL_PS_4K 0 -#define PCIE_REG_TCEKILL_PS_64K 1 -#define PCIE_REG_TCEKILL_PS_16M 2 -#define PCIE_REG_TCEKILL_PS_16G 3 - -#define PCIE_REG_IODA_ADDR 0x220 -#define PCIE_REG_IODA_AD_AUTOINC 0x8000000000000000ull -#define PCIE_REG_IODA_AD_TBL_MVT 0x0005000000000000ull -#define PCIE_REG_IODA_AD_TBL_PELT 0x0006000000000000ull -#define PCIE_REG_IODA_AD_TBL_PESTA 0x0007000000000000ull -#define PCIE_REG_IODA_AD_TBL_PESTB 0x0008000000000000ull -#define PCIE_REG_IODA_AD_TBL_TVT 0x0009000000000000ull -#define PCIE_REG_IODA_AD_TBL_TCE 0x000a000000000000ull -#define PCIE_REG_IODA_DATA0 0x228 -#define PCIE_REG_IODA_DATA1 0x230 - -#define PCIE_REG_LOCK2 0x240 - -#define PCIE_REG_PHB_GEN_CAP 0x250 -#define PCIE_REG_PHB_TCE_CAP 0x258 -#define PCIE_REG_PHB_IRQ_CAP 0x260 -#define PCIE_REG_PHB_EEH_CAP 0x268 - -#define PCIE_REG_PAPR_ERR_INJ_CONTROL 0x2b0 -#define PCIE_REG_PAPR_ERR_INJ_ADDR 0x2b8 -#define PCIE_REG_PAPR_ERR_INJ_MASK 0x2c0 - - -#define PCIE_REG_SYS_CFG1 0x600 -#define PCIE_REG_SYS_CFG1_CLASS_CODE 0x0000000000ffffffull - -#define IODA_TVT0_TTA_MASK 0x000fffffffff0000ull -#define IODA_TVT0_TTA_SHIFT 4 -#define IODA_TVT0_BUSNUM_VALID_MASK 0x000000000000e000ull -#define IODA_TVT0_TCE_TABLE_SIZE_MASK 0x0000000000001f00ull -#define IODA_TVT0_TCE_TABLE_SIZE_SHIFT 8 -#define IODA_TVT0_BUSNUM_VALUE_MASK 0x00000000000000ffull -#define IODA_TVT0_BUSNUM_VALID_SHIFT 0 -#define IODA_TVT1_DEVNUM_VALID 0x2000000000000000ull -#define IODA_TVT1_DEVNUM_VALUE_MASK 0x1f00000000000000ull -#define IODA_TVT1_DEVNUM_VALUE_SHIFT 56 -#define IODA_TVT1_FUNCNUM_VALID 0x0008000000000000ull -#define IODA_TVT1_FUNCNUM_VALUE_MASK 0x0007000000000000ull -#define IODA_TVT1_FUNCNUM_VALUE_SHIFT 48 -#define IODA_TVT1_IO_PAGE_SIZE_MASK 0x00001f0000000000ull -#define IODA_TVT1_IO_PAGE_SIZE_SHIFT 40 -#define IODA_TVT1_PE_NUMBER_MASK 0x000000000000003full -#define IODA_TVT1_PE_NUMBER_SHIFT 0 - -#define IODA_TVT_COUNT 64 - -/* UTL Core registers */ -#define PCIE_UTL_SYS_BUS_CONTROL 0x400 -#define PCIE_UTL_STATUS 0x408 -#define PCIE_UTL_SYS_BUS_AGENT_STATUS 0x410 -#define PCIE_UTL_SYS_BUS_AGENT_ERR_SEV 0x418 -#define PCIE_UTL_SYS_BUS_AGENT_IRQ_EN 0x420 -#define PCIE_UTL_SYS_BUS_BURST_SZ_CONF 0x440 -#define PCIE_UTL_REVISION_ID 0x448 - -#define PCIE_UTL_OUT_POST_HDR_BUF_ALLOC 0x4c0 -#define PCIE_UTL_OUT_POST_DAT_BUF_ALLOC 0x4d0 -#define PCIE_UTL_IN_POST_HDR_BUF_ALLOC 0x4e0 -#define PCIE_UTL_IN_POST_DAT_BUF_ALLOC 0x4f0 -#define PCIE_UTL_OUT_NP_BUF_ALLOC 0x500 -#define PCIE_UTL_IN_NP_BUF_ALLOC 0x510 -#define PCIE_UTL_PCIE_TAGS_ALLOC 0x520 -#define PCIE_UTL_GBIF_READ_TAGS_ALLOC 0x530 - -#define PCIE_UTL_PCIE_PORT_CONTROL 0x540 -#define PCIE_UTL_PCIE_PORT_STATUS 0x548 -#define PCIE_UTL_PCIE_PORT_ERROR_SEV 0x550 -#define PCIE_UTL_PCIE_PORT_IRQ_EN 0x558 -#define PCIE_UTL_RC_STATUS 0x560 -#define PCIE_UTL_RC_ERR_SEVERITY 0x568 -#define PCIE_UTL_RC_IRQ_EN 0x570 -#define PCIE_UTL_EP_STATUS 0x578 -#define PCIE_UTL_EP_ERR_SEVERITY 0x580 -#define PCIE_UTL_EP_ERR_IRQ_EN 0x588 - -#define PCIE_UTL_PCI_PM_CTRL1 0x590 -#define PCIE_UTL_PCI_PM_CTRL2 0x598 - -/* PCIe stack registers */ -#define PCIE_REG_SYSTEM_CONFIG1 0x600 -#define PCIE_REG_SYSTEM_CONFIG2 0x608 -#define PCIE_REG_EP_SYSTEM_CONFIG 0x618 -#define PCIE_REG_EP_FLR 0x620 -#define PCIE_REG_EP_BAR_CONFIG 0x628 -#define PCIE_REG_LINK_CONFIG 0x630 -#define PCIE_REG_PM_CONFIG 0x640 -#define PCIE_REG_DLP_CONTROL 0x650 -#define PCIE_REG_DLP_STATUS 0x658 -#define PCIE_REG_ERR_REPORT_CONTROL 0x660 -#define PCIE_REG_SLOT_CONTROL1 0x670 -#define PCIE_REG_SLOT_CONTROL2 0x678 -#define PCIE_REG_UTL_CONFIG 0x680 -#define PCIE_REG_BUFFERS_CONFIG 0x690 -#define PCIE_REG_ERROR_INJECT 0x698 -#define PCIE_REG_SRIOV_CONFIG 0x6a0 -#define PCIE_REG_PF0_SRIOV_STATUS 0x6a8 -#define PCIE_REG_PF1_SRIOV_STATUS 0x6b0 -#define PCIE_REG_PORT_NUMBER 0x700 -#define PCIE_REG_POR_SYSTEM_CONFIG 0x708 - -/* PHB internal logic registers */ -#define PCIE_REG_PHB_VERSION 0x800 -#define PCIE_REG_RESET 0x808 -#define PCIE_REG_PHB_CONTROL 0x810 -#define PCIE_REG_PHB_TIMEOUT_CONTROL1 0x878 -#define PCIE_REG_PHB_QUIESCE_DMA 0x888 -#define PCIE_REG_PHB_DMA_READ_TAG_ACTV 0x900 -#define PCIE_REG_PHB_TCE_READ_TAG_ACTV 0x908 - -/* FIR registers */ -#define PCIE_REG_LEM_FIR_ACCUM 0xc00 -#define PCIE_REG_LEM_FIR_AND_MASK 0xc08 -#define PCIE_REG_LEM_FIR_OR_MASK 0xc10 -#define PCIE_REG_LEM_ACTION0 0xc18 -#define PCIE_REG_LEM_ACTION1 0xc20 -#define PCIE_REG_LEM_ERROR_MASK 0xc30 -#define PCIE_REG_LEM_ERROR_AND_MASK 0xc38 -#define PCIE_REG_LEM_ERROR_OR_MASK 0xc40 - -/* PHB Error registers */ -#define PCIE_REG_PHB_ERR_STATUS 0xc80 -#define PCIE_REG_PHB_ERR1_STATUS 0xc88 -#define PCIE_REG_PHB_ERR_INJECT 0xc90 -#define PCIE_REG_PHB_ERR_LEM_ENABLE 0xc98 -#define PCIE_REG_PHB_ERR_IRQ_ENABLE 0xca0 -#define PCIE_REG_PHB_ERR_FREEZE_ENABLE 0xca8 -#define PCIE_REG_PHB_ERR_SIDE_ENABLE 0xcb8 -#define PCIE_REG_PHB_ERR_LOG_0 0xcc0 -#define PCIE_REG_PHB_ERR_LOG_1 0xcc8 -#define PCIE_REG_PHB_ERR_STATUS_MASK 0xcd0 -#define PCIE_REG_PHB_ERR1_STATUS_MASK 0xcd8 - -#define PCIE_REG_MMIO_ERR_STATUS 0xd00 -#define PCIE_REG_MMIO_ERR1_STATUS 0xd08 -#define PCIE_REG_MMIO_ERR_INJECT 0xd10 -#define PCIE_REG_MMIO_ERR_LEM_ENABLE 0xd18 -#define PCIE_REG_MMIO_ERR_IRQ_ENABLE 0xd20 -#define PCIE_REG_MMIO_ERR_FREEZE_ENABLE 0xd28 -#define PCIE_REG_MMIO_ERR_SIDE_ENABLE 0xd38 -#define PCIE_REG_MMIO_ERR_LOG_0 0xd40 -#define PCIE_REG_MMIO_ERR_LOG_1 0xd48 -#define PCIE_REG_MMIO_ERR_STATUS_MASK 0xd50 -#define PCIE_REG_MMIO_ERR1_STATUS_MASK 0xd58 - -#define PCIE_REG_DMA_ERR_STATUS 0xd80 -#define PCIE_REG_DMA_ERR1_STATUS 0xd88 -#define PCIE_REG_DMA_ERR_INJECT 0xd90 -#define PCIE_REG_DMA_ERR_LEM_ENABLE 0xd98 -#define PCIE_REG_DMA_ERR_IRQ_ENABLE 0xda0 -#define PCIE_REG_DMA_ERR_FREEZE_ENABLE 0xda8 -#define PCIE_REG_DMA_ERR_SIDE_ENABLE 0xdb8 -#define PCIE_REG_DMA_ERR_LOG_0 0xdc0 -#define PCIE_REG_DMA_ERR_LOG_1 0xdc8 -#define PCIE_REG_DMA_ERR_STATUS_MASK 0xdd0 -#define PCIE_REG_DMA_ERR1_STATUS_MASK 0xdd8 - -/* Shortcuts for access to the above using the PHB definitions - * with an offset - */ -#define PCIE_REG_ERR_PHB_OFFSET 0x0 -#define PCIE_REG_ERR_MMIO_OFFSET 0x80 -#define PCIE_REG_ERR_DMA_OFFSET 0x100 - -/* Debug and Trace registers */ -#define PCIE_REG_PHB_DEBUG_CONTROL0 0xe00 -#define PCIE_REG_PHB_DEBUG_STATUS0 0xe08 -#define PCIE_REG_PHB_DEBUG_CONTROL1 0xe10 -#define PCIE_REG_PHB_DEBUG_STATUS1 0xe18 -#define PCIE_REG_PHB_DEBUG_CONTROL2 0xe20 -#define PCIE_REG_PHB_DEBUG_STATUS2 0xe28 -#define PCIE_REG_PHB_DEBUG_CONTROL3 0xe30 -#define PCIE_REG_PHB_DEBUG_STATUS3 0xe38 -#define PCIE_REG_PHB_DEBUG_CONTROL4 0xe40 -#define PCIE_REG_PHB_DEBUG_STATUS4 0xe48 -#define PCIE_REG_PHB_DEBUG_CONTROL5 0xe50 -#define PCIE_REG_PHB_DEBUG_STATUS5 0xe58 -#define PCIE_REG_PHB_DEBUG_CONTROL6 0xe60 -#define PCIE_REG_PHB_DEBUG_STATUS6 0xe68 - -/* Definition for PCIe errors */ -struct wsp_pcie_err_log_data { - __u64 phb_err; - __u64 phb_err1; - __u64 phb_log0; - __u64 phb_log1; - __u64 mmio_err; - __u64 mmio_err1; - __u64 mmio_log0; - __u64 mmio_log1; - __u64 dma_err; - __u64 dma_err1; - __u64 dma_log0; - __u64 dma_log1; - __u64 utl_sys_err; - __u64 utl_port_err; - __u64 utl_rc_err; - __u64 unused; -}; - -#endif /* __WSP_PCI_H */ |