From 8ad68bbf7a06cdd77c170be792418488dbb65da4 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Mon, 31 Oct 2005 14:25:02 +0000 Subject: [ARM] Add support for ARM RealView board Support for RealView EB. Signed-off-by: Catalin Marinas Signed-off-by: Russell King --- arch/arm/Kconfig | 9 + arch/arm/Makefile | 1 + arch/arm/mach-realview/Kconfig | 11 + arch/arm/mach-realview/Makefile | 6 + arch/arm/mach-realview/Makefile.boot | 4 + arch/arm/mach-realview/clock.c | 145 +++++++++ arch/arm/mach-realview/clock.h | 25 ++ arch/arm/mach-realview/core.c | 605 +++++++++++++++++++++++++++++++++++ arch/arm/mach-realview/core.h | 118 +++++++ arch/arm/mach-realview/realview_eb.c | 142 ++++++++ arch/arm/mm/Kconfig | 6 +- 11 files changed, 1069 insertions(+), 3 deletions(-) create mode 100644 arch/arm/mach-realview/Kconfig create mode 100644 arch/arm/mach-realview/Makefile create mode 100644 arch/arm/mach-realview/Makefile.boot create mode 100644 arch/arm/mach-realview/clock.c create mode 100644 arch/arm/mach-realview/clock.h create mode 100644 arch/arm/mach-realview/core.c create mode 100644 arch/arm/mach-realview/core.h create mode 100644 arch/arm/mach-realview/realview_eb.c (limited to 'arch') diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 682367bd0f6..dc6d8342e5e 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -194,6 +194,13 @@ config ARCH_VERSATILE help This enables support for ARM Ltd Versatile board. +config ARCH_REALVIEW + bool "RealView" + select ARM_AMBA + select ICST307 + help + This enables support for ARM Ltd RealView boards. + config ARCH_IMX bool "IMX" @@ -244,6 +251,8 @@ source "arch/arm/mach-versatile/Kconfig" source "arch/arm/mach-aaec2000/Kconfig" +source "arch/arm/mach-realview/Kconfig" + # Definitions to make life easier config ARCH_ACORN bool diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 64cf480b0b0..d80749ae2a7 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -99,6 +99,7 @@ textaddr-$(CONFIG_ARCH_FORTUNET) := 0xc0008000 machine-$(CONFIG_ARCH_IMX) := imx machine-$(CONFIG_ARCH_H720X) := h720x machine-$(CONFIG_ARCH_AAEC2000) := aaec2000 + machine-$(CONFIG_ARCH_REALVIEW) := realview ifeq ($(CONFIG_ARCH_EBSA110),y) # This is what happens if you forget the IOCS16 line. diff --git a/arch/arm/mach-realview/Kconfig b/arch/arm/mach-realview/Kconfig new file mode 100644 index 00000000000..4b63dc9eabf --- /dev/null +++ b/arch/arm/mach-realview/Kconfig @@ -0,0 +1,11 @@ +menu "RealView platform type" + depends on ARCH_REALVIEW + +config MACH_REALVIEW_EB + bool "Support RealView/EB platform" + default n + select ARM_GIC + help + Include support for the ARM(R) RealView Emulation Baseboard platform. + +endmenu diff --git a/arch/arm/mach-realview/Makefile b/arch/arm/mach-realview/Makefile new file mode 100644 index 00000000000..8d37ea1605f --- /dev/null +++ b/arch/arm/mach-realview/Makefile @@ -0,0 +1,6 @@ +# +# Makefile for the linux kernel. +# + +obj-y := core.o clock.o +obj-$(CONFIG_MACH_REALVIEW_EB) += realview_eb.o diff --git a/arch/arm/mach-realview/Makefile.boot b/arch/arm/mach-realview/Makefile.boot new file mode 100644 index 00000000000..c7e75acfe6c --- /dev/null +++ b/arch/arm/mach-realview/Makefile.boot @@ -0,0 +1,4 @@ + zreladdr-y := 0x00008000 +params_phys-y := 0x00000100 +initrd_phys-y := 0x00800000 + diff --git a/arch/arm/mach-realview/clock.c b/arch/arm/mach-realview/clock.c new file mode 100644 index 00000000000..002635c97bb --- /dev/null +++ b/arch/arm/mach-realview/clock.c @@ -0,0 +1,145 @@ +/* + * linux/arch/arm/mach-realview/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 +#include +#include +#include +#include + +#include +#include +#include + +#include "clock.h" + +static LIST_HEAD(clocks); +static DECLARE_MUTEX(clocks_sem); + +struct clk *clk_get(struct device *dev, const char *id) +{ + struct clk *p, *clk = ERR_PTR(-ENOENT); + + down(&clocks_sem); + list_for_each_entry(p, &clocks, node) { + if (strcmp(id, p->name) == 0 && try_module_get(p->owner)) { + clk = p; + break; + } + } + up(&clocks_sem); + + return clk; +} +EXPORT_SYMBOL(clk_get); + +void clk_put(struct clk *clk) +{ + module_put(clk->owner); +} +EXPORT_SYMBOL(clk_put); + +int clk_enable(struct clk *clk) +{ + return 0; +} +EXPORT_SYMBOL(clk_enable); + +void clk_disable(struct clk *clk) +{ +} +EXPORT_SYMBOL(clk_disable); + +int clk_use(struct clk *clk) +{ + return 0; +} +EXPORT_SYMBOL(clk_use); + +void clk_unuse(struct clk *clk) +{ +} +EXPORT_SYMBOL(clk_unuse); + +unsigned long clk_get_rate(struct clk *clk) +{ + return clk->rate; +} +EXPORT_SYMBOL(clk_get_rate); + +long clk_round_rate(struct clk *clk, unsigned long rate) +{ + return rate; +} +EXPORT_SYMBOL(clk_round_rate); + +int clk_set_rate(struct clk *clk, unsigned long rate) +{ + int ret = -EIO; + + if (clk->setvco) { + struct icst307_vco vco; + + vco = icst307_khz_to_vco(clk->params, rate / 1000); + clk->rate = icst307_khz(clk->params, vco) * 1000; + + printk("Clock %s: setting VCO reg params: S=%d R=%d V=%d\n", + clk->name, vco.s, vco.r, vco.v); + + clk->setvco(clk, vco); + ret = 0; + } + return ret; +} +EXPORT_SYMBOL(clk_set_rate); + +/* + * These are fixed clocks. + */ +static struct clk kmi_clk = { + .name = "KMIREFCLK", + .rate = 24000000, +}; + +static struct clk uart_clk = { + .name = "UARTCLK", + .rate = 24000000, +}; + +static struct clk mmci_clk = { + .name = "MCLK", + .rate = 33000000, +}; + +int clk_register(struct clk *clk) +{ + down(&clocks_sem); + list_add(&clk->node, &clocks); + up(&clocks_sem); + return 0; +} +EXPORT_SYMBOL(clk_register); + +void clk_unregister(struct clk *clk) +{ + down(&clocks_sem); + list_del(&clk->node); + up(&clocks_sem); +} +EXPORT_SYMBOL(clk_unregister); + +static int __init clk_init(void) +{ + clk_register(&kmi_clk); + clk_register(&uart_clk); + clk_register(&mmci_clk); + return 0; +} +arch_initcall(clk_init); diff --git a/arch/arm/mach-realview/clock.h b/arch/arm/mach-realview/clock.h new file mode 100644 index 00000000000..dadba695e18 --- /dev/null +++ b/arch/arm/mach-realview/clock.h @@ -0,0 +1,25 @@ +/* + * linux/arch/arm/mach-realview/clock.h + * + * 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. + */ +struct module; +struct icst307_params; + +struct clk { + struct list_head node; + unsigned long rate; + struct module *owner; + const char *name; + const struct icst307_params *params; + void *data; + void (*setvco)(struct clk *, struct icst307_vco vco); +}; + +int clk_register(struct clk *clk); +void clk_unregister(struct clk *clk); diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c new file mode 100644 index 00000000000..4f98f13ad3a --- /dev/null +++ b/arch/arm/mach-realview/core.c @@ -0,0 +1,605 @@ +/* + * linux/arch/arm/mach-realview/core.c + * + * Copyright (C) 1999 - 2003 ARM Limited + * Copyright (C) 2000 Deep Blue Solutions Ltd + * + * 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 +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include + +#include + +#include "core.h" +#include "clock.h" + +#define REALVIEW_REFCOUNTER (__io_address(REALVIEW_SYS_BASE) + REALVIEW_SYS_24MHz_OFFSET) + +/* + * This is the RealView sched_clock implementation. This has + * a resolution of 41.7ns, and a maximum value of about 179s. + */ +unsigned long long sched_clock(void) +{ + unsigned long long v; + + v = (unsigned long long)readl(REALVIEW_REFCOUNTER) * 125; + do_div(v, 3); + + return v; +} + + +#define REALVIEW_FLASHCTRL (__io_address(REALVIEW_SYS_BASE) + REALVIEW_SYS_FLASH_OFFSET) + +static int realview_flash_init(void) +{ + u32 val; + + val = __raw_readl(REALVIEW_FLASHCTRL); + val &= ~REALVIEW_FLASHPROG_FLVPPEN; + __raw_writel(val, REALVIEW_FLASHCTRL); + + return 0; +} + +static void realview_flash_exit(void) +{ + u32 val; + + val = __raw_readl(REALVIEW_FLASHCTRL); + val &= ~REALVIEW_FLASHPROG_FLVPPEN; + __raw_writel(val, REALVIEW_FLASHCTRL); +} + +static void realview_flash_set_vpp(int on) +{ + u32 val; + + val = __raw_readl(REALVIEW_FLASHCTRL); + if (on) + val |= REALVIEW_FLASHPROG_FLVPPEN; + else + val &= ~REALVIEW_FLASHPROG_FLVPPEN; + __raw_writel(val, REALVIEW_FLASHCTRL); +} + +static struct flash_platform_data realview_flash_data = { + .map_name = "cfi_probe", + .width = 4, + .init = realview_flash_init, + .exit = realview_flash_exit, + .set_vpp = realview_flash_set_vpp, +}; + +static struct resource realview_flash_resource = { + .start = REALVIEW_FLASH_BASE, + .end = REALVIEW_FLASH_BASE + REALVIEW_FLASH_SIZE, + .flags = IORESOURCE_MEM, +}; + +struct platform_device realview_flash_device = { + .name = "armflash", + .id = 0, + .dev = { + .platform_data = &realview_flash_data, + }, + .num_resources = 1, + .resource = &realview_flash_resource, +}; + +static struct resource realview_smc91x_resources[] = { + [0] = { + .start = REALVIEW_ETH_BASE, + .end = REALVIEW_ETH_BASE + SZ_64K - 1, + .flags = IORESOURCE_MEM, + }, + [1] = { + .start = IRQ_ETH, + .end = IRQ_ETH, + .flags = IORESOURCE_IRQ, + }, +}; + +struct platform_device realview_smc91x_device = { + .name = "smc91x", + .id = 0, + .num_resources = ARRAY_SIZE(realview_smc91x_resources), + .resource = realview_smc91x_resources, +}; + +#define REALVIEW_SYSMCI (__io_address(REALVIEW_SYS_BASE) + REALVIEW_SYS_MCI_OFFSET) + +static unsigned int realview_mmc_status(struct device *dev) +{ + struct amba_device *adev = container_of(dev, struct amba_device, dev); + u32 mask; + + if (adev->res.start == REALVIEW_MMCI0_BASE) + mask = 1; + else + mask = 2; + + return readl(REALVIEW_SYSMCI) & mask; +} + +struct mmc_platform_data realview_mmc0_plat_data = { + .ocr_mask = MMC_VDD_32_33|MMC_VDD_33_34, + .status = realview_mmc_status, +}; + +struct mmc_platform_data realview_mmc1_plat_data = { + .ocr_mask = MMC_VDD_32_33|MMC_VDD_33_34, + .status = realview_mmc_status, +}; + +/* + * Clock handling + */ +static const struct icst307_params realview_oscvco_params = { + .ref = 24000, + .vco_max = 200000, + .vd_min = 4 + 8, + .vd_max = 511 + 8, + .rd_min = 1 + 2, + .rd_max = 127 + 2, +}; + +static void realview_oscvco_set(struct clk *clk, struct icst307_vco vco) +{ + void __iomem *sys_lock = __io_address(REALVIEW_SYS_BASE) + REALVIEW_SYS_LOCK_OFFSET; + void __iomem *sys_osc = __io_address(REALVIEW_SYS_BASE) + REALVIEW_SYS_OSC1_OFFSET; + u32 val; + + val = readl(sys_osc) & ~0x7ffff; + val |= vco.v | (vco.r << 9) | (vco.s << 16); + + writel(0xa05f, sys_lock); + writel(val, sys_osc); + writel(0, sys_lock); +} + +struct clk realview_clcd_clk = { + .name = "CLCDCLK", + .params = &realview_oscvco_params, + .setvco = realview_oscvco_set, +}; + +/* + * CLCD support. + */ +#define SYS_CLCD_MODE_MASK (3 << 0) +#define SYS_CLCD_MODE_888 (0 << 0) +#define SYS_CLCD_MODE_5551 (1 << 0) +#define SYS_CLCD_MODE_565_RLSB (2 << 0) +#define SYS_CLCD_MODE_565_BLSB (3 << 0) +#define SYS_CLCD_NLCDIOON (1 << 2) +#define SYS_CLCD_VDDPOSSWITCH (1 << 3) +#define SYS_CLCD_PWR3V5SWITCH (1 << 4) +#define SYS_CLCD_ID_MASK (0x1f << 8) +#define SYS_CLCD_ID_SANYO_3_8 (0x00 << 8) +#define SYS_CLCD_ID_UNKNOWN_8_4 (0x01 << 8) +#define SYS_CLCD_ID_EPSON_2_2 (0x02 << 8) +#define SYS_CLCD_ID_SANYO_2_5 (0x07 << 8) +#define SYS_CLCD_ID_VGA (0x1f << 8) + +static struct clcd_panel vga = { + .mode = { + .name = "VGA", + .refresh = 60, + .xres = 640, + .yres = 480, + .pixclock = 39721, + .left_margin = 40, + .right_margin = 24, + .upper_margin = 32, + .lower_margin = 11, + .hsync_len = 96, + .vsync_len = 2, + .sync = 0, + .vmode = FB_VMODE_NONINTERLACED, + }, + .width = -1, + .height = -1, + .tim2 = TIM2_BCD | TIM2_IPC, + .cntl = CNTL_LCDTFT | CNTL_LCDVCOMP(1), + .bpp = 16, +}; + +static struct clcd_panel sanyo_3_8_in = { + .mode = { + .name = "Sanyo QVGA", + .refresh = 116, + .xres = 320, + .yres = 240, + .pixclock = 100000, + .left_margin = 6, + .right_margin = 6, + .upper_margin = 5, + .lower_margin = 5, + .hsync_len = 6, + .vsync_len = 6, + .sync = 0, + .vmode = FB_VMODE_NONINTERLACED, + }, + .width = -1, + .height = -1, + .tim2 = TIM2_BCD, + .cntl = CNTL_LCDTFT | CNTL_LCDVCOMP(1), + .bpp = 16, +}; + +static struct clcd_panel sanyo_2_5_in = { + .mode = { + .name = "Sanyo QVGA Portrait", + .refresh = 116, + .xres = 240, + .yres = 320, + .pixclock = 100000, + .left_margin = 20, + .right_margin = 10, + .upper_margin = 2, + .lower_margin = 2, + .hsync_len = 10, + .vsync_len = 2, + .sync = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT, + .vmode = FB_VMODE_NONINTERLACED, + }, + .width = -1, + .height = -1, + .tim2 = TIM2_IVS | TIM2_IHS | TIM2_IPC, + .cntl = CNTL_LCDTFT | CNTL_LCDVCOMP(1), + .bpp = 16, +}; + +static struct clcd_panel epson_2_2_in = { + .mode = { + .name = "Epson QCIF", + .refresh = 390, + .xres = 176, + .yres = 220, + .pixclock = 62500, + .left_margin = 3, + .right_margin = 2, + .upper_margin = 1, + .lower_margin = 0, + .hsync_len = 3, + .vsync_len = 2, + .sync = 0, + .vmode = FB_VMODE_NONINTERLACED, + }, + .width = -1, + .height = -1, + .tim2 = TIM2_BCD | TIM2_IPC, + .cntl = CNTL_LCDTFT | CNTL_LCDVCOMP(1), + .bpp = 16, +}; + +/* + * Detect which LCD panel is connected, and return the appropriate + * clcd_panel structure. Note: we do not have any information on + * the required timings for the 8.4in panel, so we presently assume + * VGA timings. + */ +static struct clcd_panel *realview_clcd_panel(void) +{ + void __iomem *sys_clcd = __io_address(REALVIEW_SYS_BASE) + REALVIEW_SYS_CLCD_OFFSET; + struct clcd_panel *panel = &vga; + u32 val; + + val = readl(sys_clcd) & SYS_CLCD_ID_MASK; + if (val == SYS_CLCD_ID_SANYO_3_8) + panel = &sanyo_3_8_in; + else if (val == SYS_CLCD_ID_SANYO_2_5) + panel = &sanyo_2_5_in; + else if (val == SYS_CLCD_ID_EPSON_2_2) + panel = &epson_2_2_in; + else if (val == SYS_CLCD_ID_VGA) + panel = &vga; + else { + printk(KERN_ERR "CLCD: unknown LCD panel ID 0x%08x, using VGA\n", + val); + panel = &vga; + } + + return panel; +} + +/* + * Disable all display connectors on the interface module. + */ +static void realview_clcd_disable(struct clcd_fb *fb) +{ + void __iomem *sys_clcd = __io_address(REALVIEW_SYS_BASE) + REALVIEW_SYS_CLCD_OFFSET; + u32 val; + + val = readl(sys_clcd); + val &= ~SYS_CLCD_NLCDIOON | SYS_CLCD_PWR3V5SWITCH; + writel(val, sys_clcd); +} + +/* + * Enable the relevant connector on the interface module. + */ +static void realview_clcd_enable(struct clcd_fb *fb) +{ + void __iomem *sys_clcd = __io_address(REALVIEW_SYS_BASE) + REALVIEW_SYS_CLCD_OFFSET; + u32 val; + + val = readl(sys_clcd); + val &= ~SYS_CLCD_MODE_MASK; + + switch (fb->fb.var.green.length) { + case 5: + val |= SYS_CLCD_MODE_5551; + break; + case 6: + val |= SYS_CLCD_MODE_565_RLSB; + break; + case 8: + val |= SYS_CLCD_MODE_888; + break; + } + + /* + * Set the MUX + */ + writel(val, sys_clcd); + + /* + * And now enable the PSUs + */ + val |= SYS_CLCD_NLCDIOON | SYS_CLCD_PWR3V5SWITCH; + writel(val, sys_clcd); +} + +static unsigned long framesize = SZ_1M; + +static int realview_clcd_setup(struct clcd_fb *fb) +{ + dma_addr_t dma; + + fb->panel = realview_clcd_panel(); + + fb->fb.screen_base = dma_alloc_writecombine(&fb->dev->dev, framesize, + &dma, GFP_KERNEL); + if (!fb->fb.screen_base) { + printk(KERN_ERR "CLCD: unable to map framebuffer\n"); + return -ENOMEM; + } + + fb->fb.fix.smem_start = dma; + fb->fb.fix.smem_len = framesize; + + return 0; +} + +static int realview_clcd_mmap(struct clcd_fb *fb, struct vm_area_struct *vma) +{ + return dma_mmap_writecombine(&fb->dev->dev, vma, + fb->fb.screen_base, + fb->fb.fix.smem_start, + fb->fb.fix.smem_len); +} + +static void realview_clcd_remove(struct clcd_fb *fb) +{ + dma_free_writecombine(&fb->dev->dev, fb->fb.fix.smem_len, + fb->fb.screen_base, fb->fb.fix.smem_start); +} + +struct clcd_board clcd_plat_data = { + .name = "RealView", + .check = clcdfb_check, + .decode = clcdfb_decode, + .disable = realview_clcd_disable, + .enable = realview_clcd_enable, + .setup = realview_clcd_setup, + .mmap = realview_clcd_mmap, + .remove = realview_clcd_remove, +}; + +#ifdef CONFIG_LEDS +#define VA_LEDS_BASE (__io_address(REALVIEW_SYS_BASE) + REALVIEW_SYS_LED_OFFSET) + +void realview_leds_event(led_event_t ledevt) +{ + unsigned long flags; + u32 val; + + local_irq_save(flags); + val = readl(VA_LEDS_BASE); + + switch (ledevt) { + case led_idle_start: + val = val & ~REALVIEW_SYS_LED0; + break; + + case led_idle_end: + val = val | REALVIEW_SYS_LED0; + break; + + case led_timer: + val = val ^ REALVIEW_SYS_LED1; + break; + + case led_halted: + val = 0; + break; + + default: + break; + } + + writel(val, VA_LEDS_BASE); + local_irq_restore(flags); +} +#endif /* CONFIG_LEDS */ + +/* + * Where is the timer (VA)? + */ +#define TIMER0_VA_BASE __io_address(REALVIEW_TIMER0_1_BASE) +#define TIMER1_VA_BASE (__io_address(REALVIEW_TIMER0_1_BASE) + 0x20) +#define TIMER2_VA_BASE __io_address(REALVIEW_TIMER2_3_BASE) +#define TIMER3_VA_BASE (__io_address(REALVIEW_TIMER2_3_BASE) + 0x20) + +/* + * How long is the timer interval? + */ +#define TIMER_INTERVAL (TICKS_PER_uSEC * mSEC_10) +#if TIMER_INTERVAL >= 0x100000 +#define TIMER_RELOAD (TIMER_INTERVAL >> 8) +#define TIMER_DIVISOR (TIMER_CTRL_DIV256) +#define TICKS2USECS(x) (256 * (x) / TICKS_PER_uSEC) +#elif TIMER_INTERVAL >= 0x10000 +#define TIMER_RELOAD (TIMER_INTERVAL >> 4) /* Divide by 16 */ +#define TIMER_DIVISOR (TIMER_CTRL_DIV16) +#define TICKS2USECS(x) (16 * (x) / TICKS_PER_uSEC) +#else +#define TIMER_RELOAD (TIMER_INTERVAL) +#define TIMER_DIVISOR (TIMER_CTRL_DIV1) +#define TICKS2USECS(x) ((x) / TICKS_PER_uSEC) +#endif + +/* + * Returns number of ms since last clock interrupt. Note that interrupts + * will have been disabled by do_gettimeoffset() + */ +static unsigned long realview_gettimeoffset(void) +{ + unsigned long ticks1, ticks2, status; + + /* + * Get the current number of ticks. Note that there is a race + * condition between us reading the timer and checking for + * an interrupt. We get around this by ensuring that the + * counter has not reloaded between our two reads. + */ + ticks2 = readl(TIMER0_VA_BASE + TIMER_VALUE) & 0xffff; + do { + ticks1 = ticks2; + status = __raw_readl(__io_address(REALVIEW_GIC_DIST_BASE + GIC_DIST_PENDING_SET) + + ((IRQ_TIMERINT0_1 >> 5) << 2)); + ticks2 = readl(TIMER0_VA_BASE + TIMER_VALUE) & 0xffff; + } while (ticks2 > ticks1); + + /* + * Number of ticks since last interrupt. + */ + ticks1 = TIMER_RELOAD - ticks2; + + /* + * Interrupt pending? If so, we've reloaded once already. + * + * FIXME: Need to check this is effectively timer 0 that expires + */ + if (status & IRQMASK_TIMERINT0_1) + ticks1 += TIMER_RELOAD; + + /* + * Convert the ticks to usecs + */ + return TICKS2USECS(ticks1); +} + +/* + * IRQ handler for the timer + */ +static irqreturn_t realview_timer_interrupt(int irq, void *dev_id, struct pt_regs *regs) +{ + write_seqlock(&xtime_lock); + + // ...clear the interrupt + writel(1, TIMER0_VA_BASE + TIMER_INTCLR); + + timer_tick(regs); + + write_sequnlock(&xtime_lock); + + return IRQ_HANDLED; +} + +static struct irqaction realview_timer_irq = { + .name = "RealView Timer Tick", + .flags = SA_INTERRUPT | SA_TIMER, + .handler = realview_timer_interrupt, +}; + +/* + * Set up timer interrupt, and return the current time in seconds. + */ +static void __init realview_timer_init(void) +{ + u32 val; + + /* + * set clock frequency: + * REALVIEW_REFCLK is 32KHz + * REALVIEW_TIMCLK is 1MHz + */ + val = readl(__io_address(REALVIEW_SCTL_BASE)); + writel((REALVIEW_TIMCLK << REALVIEW_TIMER1_EnSel) | + (REALVIEW_TIMCLK << REALVIEW_TIMER2_EnSel) | + (REALVIEW_TIMCLK << REALVIEW_TIMER3_EnSel) | + (REALVIEW_TIMCLK << REALVIEW_TIMER4_EnSel) | val, + __io_address(REALVIEW_SCTL_BASE)); + + /* + * Initialise to a known state (all timers off) + */ + writel(0, TIMER0_VA_BASE + TIMER_CTRL); + writel(0, TIMER1_VA_BASE + TIMER_CTRL); + writel(0, TIMER2_VA_BASE + TIMER_CTRL); + writel(0, TIMER3_VA_BASE + TIMER_CTRL); + + writel(TIMER_RELOAD, TIMER0_VA_BASE + TIMER_LOAD); + writel(TIMER_RELOAD, TIMER0_VA_BASE + TIMER_VALUE); + writel(TIMER_DIVISOR | TIMER_CTRL_ENABLE | TIMER_CTRL_PERIODIC | + TIMER_CTRL_IE, TIMER0_VA_BASE + TIMER_CTRL); + + /* + * Make irqs happen for the system timer + */ + setup_irq(IRQ_TIMERINT0_1, &realview_timer_irq); +} + +struct sys_timer realview_timer = { + .init = realview_timer_init, + .offset = realview_gettimeoffset, +}; diff --git a/arch/arm/mach-realview/core.h b/arch/arm/mach-realview/core.h new file mode 100644 index 00000000000..575599db74d --- /dev/null +++ b/arch/arm/mach-realview/core.h @@ -0,0 +1,118 @@ +/* + * linux/arch/arm/mach-realview/core.h + * + * Copyright (C) 2004 ARM Limited + * Copyright (C) 2000 Deep Blue Solutions Ltd + * + * 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 + */ + +#ifndef __ASM_ARCH_REALVIEW_H +#define __ASM_ARCH_REALVIEW_H + +#include +#include + +#define __io_address(n) __io(IO_ADDRESS(n)) + +extern struct sys_timer realview_timer; + +#define AMBA_DEVICE(name,busid,base,plat) \ +static struct amba_device name##_device = { \ + .dev = { \ + .coherent_dma_mask = ~0, \ + .bus_id = busid, \ + .platform_data = plat, \ + }, \ + .res = { \ + .start = REALVIEW_##base##_BASE, \ + .end = (REALVIEW_##base##_BASE) + SZ_4K - 1,\ + .flags = IORESOURCE_MEM, \ + }, \ + .dma_mask = ~0, \ + .irq = base##_IRQ, \ + /* .dma = base##_DMA,*/ \ +} + +/* + * These devices are connected via the core APB bridge + */ +#define GPIO2_IRQ { IRQ_GPIOINT2, NO_IRQ } +#define GPIO2_DMA { 0, 0 } +#define GPIO3_IRQ { IRQ_GPIOINT3, NO_IRQ } +#define GPIO3_DMA { 0, 0 } + +#define AACI_IRQ { IRQ_AACI, NO_IRQ } +#define AACI_DMA { 0x80, 0x81 } +#define MMCI0_IRQ { IRQ_MMCI0A,IRQ_MMCI0B } +#define MMCI0_DMA { 0x84, 0 } +#define KMI0_IRQ { IRQ_KMI0, NO_IRQ } +#define KMI0_DMA { 0, 0 } +#define KMI1_IRQ { IRQ_KMI1, NO_IRQ } +#define KMI1_DMA { 0, 0 } + +/* + * These devices are connected directly to the multi-layer AHB switch + */ +#define SMC_IRQ { NO_IRQ, NO_IRQ } +#define SMC_DMA { 0, 0 } +#define MPMC_IRQ { NO_IRQ, NO_IRQ } +#define MPMC_DMA { 0, 0 } +#define CLCD_IRQ { IRQ_CLCDINT, NO_IRQ } +#define CLCD_DMA { 0, 0 } +#define DMAC_IRQ { IRQ_DMAINT, NO_IRQ } +#define DMAC_DMA { 0, 0 } + +/* + * These devices are connected via the core APB bridge + */ +#define SCTL_IRQ { NO_IRQ, NO_IRQ } +#define SCTL_DMA { 0, 0 } +#define WATCHDOG_IRQ { IRQ_WDOGINT, NO_IRQ } +#define WATCHDOG_DMA { 0, 0 } +#define GPIO0_IRQ { IRQ_GPIOINT0, NO_IRQ } +#define GPIO0_DMA { 0, 0 } +#define GPIO1_IRQ { IRQ_GPIOINT1, NO_IRQ } +#define GPIO1_DMA { 0, 0 } +#define RTC_IRQ { IRQ_RTCINT, NO_IRQ } +#define RTC_DMA { 0, 0 } + +/* + * These devices are connected via the DMA APB bridge + */ +#define SCI_IRQ { IRQ_SCIINT, NO_IRQ } +#define SCI_DMA { 7, 6 } +#define UART0_IRQ { IRQ_UARTINT0, NO_IRQ } +#define UART0_DMA { 15, 14 } +#define UART1_IRQ { IRQ_UARTINT1, NO_IRQ } +#define UART1_DMA { 13, 12 } +#define UART2_IRQ { IRQ_UARTINT2, NO_IRQ } +#define UART2_DMA { 11, 10 } +#define UART3_IRQ { IRQ_UART3, NO_IRQ } +#define UART3_DMA { 0x86, 0x87 } +#define SSP_IRQ { IRQ_SSPINT, NO_IRQ } +#define SSP_DMA { 9, 8 } + + +extern struct platform_device realview_flash_device; +extern struct platform_device realview_smc91x_device; +extern struct mmc_platform_data realview_mmc0_plat_data; +extern struct mmc_platform_data realview_mmc1_plat_data; +extern struct clk realview_clcd_clk; +extern struct clcd_board clcd_plat_data; + +extern void realview_leds_event(led_event_t ledevt); + +#endif diff --git a/arch/arm/mach-realview/realview_eb.c b/arch/arm/mach-realview/realview_eb.c new file mode 100644 index 00000000000..1279feeecf7 --- /dev/null +++ b/arch/arm/mach-realview/realview_eb.c @@ -0,0 +1,142 @@ +/* + * linux/arch/arm/mach-realview/realview_eb.c + * + * Copyright (C) 2004 ARM Limited + * Copyright (C) 2000 Deep Blue Solutions Ltd + * + * 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 +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#include + +#include "core.h" +#include "clock.h" + +static struct map_desc realview_eb_io_desc[] __initdata = { + { IO_ADDRESS(REALVIEW_SYS_BASE), REALVIEW_SYS_BASE, SZ_4K, MT_DEVICE }, + { IO_ADDRESS(REALVIEW_GIC_CPU_BASE), REALVIEW_GIC_CPU_BASE, SZ_4K, MT_DEVICE }, + { IO_ADDRESS(REALVIEW_GIC_DIST_BASE), REALVIEW_GIC_DIST_BASE, SZ_4K, MT_DEVICE }, + { IO_ADDRESS(REALVIEW_SCTL_BASE), REALVIEW_SCTL_BASE, SZ_4K, MT_DEVICE }, + { IO_ADDRESS(REALVIEW_TIMER0_1_BASE), REALVIEW_TIMER0_1_BASE, SZ_4K, MT_DEVICE }, + { IO_ADDRESS(REALVIEW_TIMER2_3_BASE), REALVIEW_TIMER2_3_BASE, SZ_4K, MT_DEVICE }, +#ifdef CONFIG_DEBUG_LL + { IO_ADDRESS(REALVIEW_UART0_BASE), REALVIEW_UART0_BASE, SZ_4K, MT_DEVICE }, +#endif +}; + +static void __init realview_eb_map_io(void) +{ + iotable_init(realview_eb_io_desc, ARRAY_SIZE(realview_eb_io_desc)); +} + +/* FPGA Primecells */ +AMBA_DEVICE(aaci, "fpga:04", AACI, NULL); +AMBA_DEVICE(mmc0, "fpga:05", MMCI0, &realview_mmc0_plat_data); +AMBA_DEVICE(kmi0, "fpga:06", KMI0, NULL); +AMBA_DEVICE(kmi1, "fpga:07", KMI1, NULL); +AMBA_DEVICE(uart3, "fpga:09", UART3, NULL); + +/* DevChip Primecells */ +AMBA_DEVICE(smc, "dev:00", SMC, NULL); +AMBA_DEVICE(clcd, "dev:20", CLCD, &clcd_plat_data); +AMBA_DEVICE(dmac, "dev:30", DMAC, NULL); +AMBA_DEVICE(sctl, "dev:e0", SCTL, NULL); +AMBA_DEVICE(wdog, "dev:e1", WATCHDOG, NULL); +AMBA_DEVICE(gpio0, "dev:e4", GPIO0, NULL); +AMBA_DEVICE(gpio1, "dev:e5", GPIO1, NULL); +AMBA_DEVICE(gpio2, "dev:e6", GPIO2, NULL); +AMBA_DEVICE(rtc, "dev:e8", RTC, NULL); +AMBA_DEVICE(sci0, "dev:f0", SCI, NULL); +AMBA_DEVICE(uart0, "dev:f1", UART0, NULL); +AMBA_DEVICE(uart1, "dev:f2", UART1, NULL); +AMBA_DEVICE(uart2, "dev:f3", UART2, NULL); +AMBA_DEVICE(ssp0, "dev:f4", SSP, NULL); + +static struct amba_device *amba_devs[] __initdata = { + &dmac_device, + &uart0_device, + &uart1_device, + &uart2_device, + &uart3_device, + &smc_device, + &clcd_device, + &sctl_device, + &wdog_device, + &gpio0_device, + &gpio1_device, + &gpio2_device, + &rtc_device, + &sci0_device, + &ssp0_device, + &aaci_device, + &mmc0_device, + &kmi0_device, + &kmi1_device, +}; + +static void __init gic_init_irq(void) +{ + gic_dist_init(__io_address(REALVIEW_GIC_DIST_BASE)); + gic_cpu_init(__io_address(REALVIEW_GIC_CPU_BASE)); +} + +static void __init realview_eb_init(void) +{ + int i; + + clk_register(&realview_clcd_clk); + + platform_device_register(&realview_flash_device); + platform_device_register(&realview_smc91x_device); + + for (i = 0; i < ARRAY_SIZE(amba_devs); i++) { + struct amba_device *d = amba_devs[i]; + amba_device_register(d, &iomem_resource); + } + +#ifdef CONFIG_LEDS + leds_event = realview_leds_event; +#endif +} + +MACHINE_START(REALVIEW_EB, "ARM-RealView EB") + /* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */ + .phys_ram = 0x00000000, + .phys_io = REALVIEW_UART0_BASE, + .io_pg_offst = (IO_ADDRESS(REALVIEW_UART0_BASE) >> 18) & 0xfffc, + .boot_params = 0x00000100, + .map_io = realview_eb_map_io, + .init_irq = gic_init_irq, + .timer = &realview_timer, + .init_machine = realview_eb_init, +MACHINE_END diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index c54e04c995e..5568403e984 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -120,8 +120,8 @@ config CPU_ARM925T # ARM926T config CPU_ARM926T - bool "Support ARM926T processor" if ARCH_INTEGRATOR - depends on ARCH_INTEGRATOR || ARCH_VERSATILE_PB || MACH_VERSATILE_AB || ARCH_OMAP730 || ARCH_OMAP16XX + bool "Support ARM926T processor" + depends on ARCH_INTEGRATOR || ARCH_VERSATILE_PB || MACH_VERSATILE_AB || ARCH_OMAP730 || ARCH_OMAP16XX || MACH_REALVIEW_EB default y if ARCH_VERSATILE_PB || MACH_VERSATILE_AB || ARCH_OMAP730 || ARCH_OMAP16XX select CPU_32v5 select CPU_ABRT_EV5TJ @@ -242,7 +242,7 @@ config CPU_XSCALE # ARMv6 config CPU_V6 bool "Support ARM V6 processor" - depends on ARCH_INTEGRATOR + depends on ARCH_INTEGRATOR || MACH_REALVIEW_EB select CPU_32v6 select CPU_ABRT_EV6 select CPU_CACHE_V6 -- cgit v1.2.3 From 1be7228da280252167150346dcec4e7c50a79eb4 Mon Sep 17 00:00:00 2001 From: Russell King Date: Mon, 31 Oct 2005 16:57:06 +0000 Subject: [ARM] Fixup platform device.h includes for realview board Signed-off-by: Russell King --- arch/arm/mach-realview/core.c | 2 +- arch/arm/mach-realview/realview_eb.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c index 4f98f13ad3a..482eb512ebe 100644 --- a/arch/arm/mach-realview/core.c +++ b/arch/arm/mach-realview/core.c @@ -20,7 +20,7 @@ */ #include #include -#include +#include #include #include #include diff --git a/arch/arm/mach-realview/realview_eb.c b/arch/arm/mach-realview/realview_eb.c index 1279feeecf7..01b264be502 100644 --- a/arch/arm/mach-realview/realview_eb.c +++ b/arch/arm/mach-realview/realview_eb.c @@ -21,7 +21,7 @@ #include #include -#include +#include #include #include -- cgit v1.2.3 From 37bb30e86bc2e48d9affb25f6ce9eb3d8e65b2ac Mon Sep 17 00:00:00 2001 From: Russell King Date: Mon, 31 Oct 2005 17:14:57 +0000 Subject: [ARM] Convert EBSA110 network driver to a platform driver Signed-off-by: Russell King --- arch/arm/mach-ebsa110/core.c | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/mach-ebsa110/core.c b/arch/arm/mach-ebsa110/core.c index 15261646dcd..ed4614983ad 100644 --- a/arch/arm/mach-ebsa110/core.c +++ b/arch/arm/mach-ebsa110/core.c @@ -251,9 +251,33 @@ static struct platform_device serial_device = { }, }; +static struct resource am79c961_resources[] = { + { + .start = 0x220, + .end = 0x238, + .flags = IORESOURCE_IO, + }, { + .start = IRQ_EBSA110_ETHERNET, + .end = IRQ_EBSA110_ETHERNET, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device am79c961_device = { + .name = "am79c961", + .id = -1, + .num_resources = ARRAY_SIZE(am79c961_resources), + .resource = am79c961_resources, +}; + +static struct platform_device *ebsa110_devices[] = { + &serial_device, + &am79c961_device, +}; + static int __init ebsa110_init(void) { - return platform_device_register(&serial_device); + return platform_add_devices(ebsa110_devices, ARRAY_SIZE(ebsa110_devices)); } arch_initcall(ebsa110_init); -- cgit v1.2.3 From a6f1063b388cfd48a598cc7971eae1f83ebc8ba4 Mon Sep 17 00:00:00 2001 From: Lennert Buytenhek Date: Tue, 1 Nov 2005 19:44:24 +0000 Subject: [ARM] 3062/1: map in various enp2611 peripherals for the ixp2000 netdev driver Patch from Lennert Buytenhek The enp2611 version of the ixp2000 netdev driver needs to be able to access a number of on-board peripherals. ioremap() is not suitable for this, as that will cause XCB=000 mappings to be done, which will make the cpu susceptible to crashing on ixp2400 erratum #66. Properly aligned iotable mappings with MT_IXP2000_DEVICE will cause section mappings with XCB=101 to be done, which is safe. Signed-off-by: Lennert Buytenhek Signed-off-by: Deepak Saxena Signed-off-by: Russell King --- arch/arm/mach-ixp2000/enp2611.c | 31 ++++++++++++++++++++++++++++++- 1 file changed, 30 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/mach-ixp2000/enp2611.c b/arch/arm/mach-ixp2000/enp2611.c index 9aa54de4474..b91fe7c80fa 100644 --- a/arch/arm/mach-ixp2000/enp2611.c +++ b/arch/arm/mach-ixp2000/enp2611.c @@ -63,6 +63,35 @@ static struct sys_timer enp2611_timer = { }; +/************************************************************************* + * ENP-2611 I/O + *************************************************************************/ +static struct map_desc enp2611_io_desc[] __initdata = { + { + .virtual = ENP2611_CALEB_VIRT_BASE, + .physical = ENP2611_CALEB_PHYS_BASE, + .length = ENP2611_CALEB_SIZE, + .type = MT_IXP2000_DEVICE + }, { + .virtual = ENP2611_PM3386_0_VIRT_BASE, + .physical = ENP2611_PM3386_0_PHYS_BASE, + .length = ENP2611_PM3386_0_SIZE, + .type = MT_IXP2000_DEVICE + }, { + .virtual = ENP2611_PM3386_1_VIRT_BASE, + .physical = ENP2611_PM3386_1_PHYS_BASE, + .length = ENP2611_PM3386_1_SIZE, + .type = MT_IXP2000_DEVICE + } +}; + +void __init enp2611_map_io(void) +{ + ixp2000_map_io(); + iotable_init(enp2611_io_desc, ARRAY_SIZE(enp2611_io_desc)); +} + + /************************************************************************* * ENP-2611 PCI *************************************************************************/ @@ -229,7 +258,7 @@ MACHINE_START(ENP2611, "Radisys ENP-2611 PCI network processor board") .phys_io = IXP2000_UART_PHYS_BASE, .io_pg_offst = ((IXP2000_UART_VIRT_BASE) >> 18) & 0xfffc, .boot_params = 0x00000100, - .map_io = ixp2000_map_io, + .map_io = enp2611_map_io, .init_irq = ixp2000_init_irq, .timer = &enp2611_timer, .init_machine = enp2611_init_machine, -- cgit v1.2.3 From e9b72e43d96a1ea2be0f513c78f16743a835d252 Mon Sep 17 00:00:00 2001 From: Lennert Buytenhek Date: Tue, 1 Nov 2005 19:44:26 +0000 Subject: [ARM] 3064/1: start using ixp2000_reg_wrb Patch from Lennert Buytenhek Switch the users of ixp2000_reg_write that depend on writes being flushed out of the write buffer by the time that function returns over to ixp2000_reg_wrb. When using XCB=101, writes to the same functional unit are still guaranteed to complete in order, so we only need to protect against: - reordering of writes to different functional units - masking an interrupt and then reenabling the IRQ bit in CPSR Signed-off-by: Lennert Buytenhek Signed-off-by: Deepak Saxena Signed-off-by: Russell King --- arch/arm/mach-ixp2000/core.c | 30 +++++++++++++++--------------- arch/arm/mach-ixp2000/ixdp2x00.c | 4 ++-- arch/arm/mach-ixp2000/ixdp2x01.c | 8 ++++---- arch/arm/mach-ixp2000/pci.c | 6 +++--- 4 files changed, 24 insertions(+), 24 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-ixp2000/core.c b/arch/arm/mach-ixp2000/core.c index 01c393c504d..69c6cf81a44 100644 --- a/arch/arm/mach-ixp2000/core.c +++ b/arch/arm/mach-ixp2000/core.c @@ -62,7 +62,7 @@ void ixp2000_acquire_slowport(struct slowport_cfg *new_cfg, struct slowport_cfg ixp2000_reg_write(IXP2000_SLOWPORT_WTC2, new_cfg->WTC); ixp2000_reg_write(IXP2000_SLOWPORT_RTC2, new_cfg->RTC); ixp2000_reg_write(IXP2000_SLOWPORT_PCR, new_cfg->PCR); - ixp2000_reg_write(IXP2000_SLOWPORT_ADC, new_cfg->ADC); + ixp2000_reg_wrb(IXP2000_SLOWPORT_ADC, new_cfg->ADC); } void ixp2000_release_slowport(struct slowport_cfg *old_cfg) @@ -71,7 +71,7 @@ void ixp2000_release_slowport(struct slowport_cfg *old_cfg) ixp2000_reg_write(IXP2000_SLOWPORT_WTC2, old_cfg->WTC); ixp2000_reg_write(IXP2000_SLOWPORT_RTC2, old_cfg->RTC); ixp2000_reg_write(IXP2000_SLOWPORT_PCR, old_cfg->PCR); - ixp2000_reg_write(IXP2000_SLOWPORT_ADC, old_cfg->ADC); + ixp2000_reg_wrb(IXP2000_SLOWPORT_ADC, old_cfg->ADC); spin_unlock_irqrestore(&ixp2000_slowport_lock, ixp2000_slowport_irq_flags); @@ -145,7 +145,7 @@ void __init ixp2000_map_io(void) iotable_init(ixp2000_io_desc, ARRAY_SIZE(ixp2000_io_desc)); /* Set slowport to 8-bit mode. */ - ixp2000_reg_write(IXP2000_SLOWPORT_FRM, 1); + ixp2000_reg_wrb(IXP2000_SLOWPORT_FRM, 1); } @@ -209,7 +209,7 @@ static int ixp2000_timer_interrupt(int irq, void *dev_id, struct pt_regs *regs) write_seqlock(&xtime_lock); /* clear timer 1 */ - ixp2000_reg_write(IXP2000_T1_CLR, 1); + ixp2000_reg_wrb(IXP2000_T1_CLR, 1); while ((next_jiffy_time - *missing_jiffy_timer_csr) > ticks_per_jiffy) { timer_tick(regs); @@ -252,12 +252,12 @@ void __init ixp2000_init_time(unsigned long tick_rate) ixp2000_reg_write(IXP2000_T4_CLR, 0); ixp2000_reg_write(IXP2000_T4_CLD, -1); - ixp2000_reg_write(IXP2000_T4_CTL, (1 << 7)); + ixp2000_reg_wrb(IXP2000_T4_CTL, (1 << 7)); missing_jiffy_timer_csr = IXP2000_T4_CSR; } else { ixp2000_reg_write(IXP2000_T2_CLR, 0); ixp2000_reg_write(IXP2000_T2_CLD, -1); - ixp2000_reg_write(IXP2000_T2_CTL, (1 << 7)); + ixp2000_reg_wrb(IXP2000_T2_CTL, (1 << 7)); missing_jiffy_timer_csr = IXP2000_T2_CSR; } next_jiffy_time = 0xffffffff; @@ -279,7 +279,7 @@ static void update_gpio_int_csrs(void) ixp2000_reg_write(IXP2000_GPIO_FEDR, GPIO_IRQ_falling_edge); ixp2000_reg_write(IXP2000_GPIO_REDR, GPIO_IRQ_rising_edge); ixp2000_reg_write(IXP2000_GPIO_LSLR, GPIO_IRQ_level_low); - ixp2000_reg_write(IXP2000_GPIO_LSHR, GPIO_IRQ_level_high); + ixp2000_reg_wrb(IXP2000_GPIO_LSHR, GPIO_IRQ_level_high); } void gpio_line_config(int line, int direction) @@ -297,9 +297,9 @@ void gpio_line_config(int line, int direction) GPIO_IRQ_level_high &= ~(1 << line); update_gpio_int_csrs(); - ixp2000_reg_write(IXP2000_GPIO_PDSR, 1 << line); + ixp2000_reg_wrb(IXP2000_GPIO_PDSR, 1 << line); } else if (direction == GPIO_IN) { - ixp2000_reg_write(IXP2000_GPIO_PDCR, 1 << line); + ixp2000_reg_wrb(IXP2000_GPIO_PDCR, 1 << line); } local_irq_restore(flags); } @@ -365,12 +365,12 @@ static void ixp2000_GPIO_irq_mask_ack(unsigned int irq) ixp2000_reg_write(IXP2000_GPIO_EDSR, (1 << (irq - IRQ_IXP2000_GPIO0))); ixp2000_reg_write(IXP2000_GPIO_LDSR, (1 << (irq - IRQ_IXP2000_GPIO0))); - ixp2000_reg_write(IXP2000_GPIO_INST, (1 << (irq - IRQ_IXP2000_GPIO0))); + ixp2000_reg_wrb(IXP2000_GPIO_INST, (1 << (irq - IRQ_IXP2000_GPIO0))); } static void ixp2000_GPIO_irq_mask(unsigned int irq) { - ixp2000_reg_write(IXP2000_GPIO_INCR, (1 << (irq - IRQ_IXP2000_GPIO0))); + ixp2000_reg_wrb(IXP2000_GPIO_INCR, (1 << (irq - IRQ_IXP2000_GPIO0))); } static void ixp2000_GPIO_irq_unmask(unsigned int irq) @@ -389,9 +389,9 @@ static void ixp2000_pci_irq_mask(unsigned int irq) { unsigned long temp = *IXP2000_PCI_XSCALE_INT_ENABLE; if (irq == IRQ_IXP2000_PCIA) - ixp2000_reg_write(IXP2000_PCI_XSCALE_INT_ENABLE, (temp & ~(1 << 26))); + ixp2000_reg_wrb(IXP2000_PCI_XSCALE_INT_ENABLE, (temp & ~(1 << 26))); else if (irq == IRQ_IXP2000_PCIB) - ixp2000_reg_write(IXP2000_PCI_XSCALE_INT_ENABLE, (temp & ~(1 << 27))); + ixp2000_reg_wrb(IXP2000_PCI_XSCALE_INT_ENABLE, (temp & ~(1 << 27))); } static void ixp2000_pci_irq_unmask(unsigned int irq) @@ -411,7 +411,7 @@ static struct irqchip ixp2000_pci_irq_chip = { static void ixp2000_irq_mask(unsigned int irq) { - ixp2000_reg_write(IXP2000_IRQ_ENABLE_CLR, (1 << irq)); + ixp2000_reg_wrb(IXP2000_IRQ_ENABLE_CLR, (1 << irq)); } static void ixp2000_irq_unmask(unsigned int irq) @@ -443,7 +443,7 @@ void __init ixp2000_init_irq(void) ixp2000_reg_write(IXP2000_GPIO_INCR, -1); /* clear PCI interrupt sources */ - ixp2000_reg_write(IXP2000_PCI_XSCALE_INT_ENABLE, 0); + ixp2000_reg_wrb(IXP2000_PCI_XSCALE_INT_ENABLE, 0); /* * Certain bits in the IRQ status register of the diff --git a/arch/arm/mach-ixp2000/ixdp2x00.c b/arch/arm/mach-ixp2000/ixdp2x00.c index 8b4a839b627..00af934dea3 100644 --- a/arch/arm/mach-ixp2000/ixdp2x00.c +++ b/arch/arm/mach-ixp2000/ixdp2x00.c @@ -81,7 +81,7 @@ static void ixdp2x00_irq_mask(unsigned int irq) dummy = *board_irq_mask; dummy |= IXP2000_BOARD_IRQ_MASK(irq); - ixp2000_reg_write(board_irq_mask, dummy); + ixp2000_reg_wrb(board_irq_mask, dummy); #ifdef CONFIG_ARCH_IXDP2400 if (machine_is_ixdp2400()) @@ -101,7 +101,7 @@ static void ixdp2x00_irq_unmask(unsigned int irq) dummy = *board_irq_mask; dummy &= ~IXP2000_BOARD_IRQ_MASK(irq); - ixp2000_reg_write(board_irq_mask, dummy); + ixp2000_reg_wrb(board_irq_mask, dummy); if (machine_is_ixdp2400()) ixp2000_release_slowport(&old_cfg); diff --git a/arch/arm/mach-ixp2000/ixdp2x01.c b/arch/arm/mach-ixp2000/ixdp2x01.c index fee1d7b7350..dfaaa2d281e 100644 --- a/arch/arm/mach-ixp2000/ixdp2x01.c +++ b/arch/arm/mach-ixp2000/ixdp2x01.c @@ -51,7 +51,7 @@ *************************************************************************/ static void ixdp2x01_irq_mask(unsigned int irq) { - ixp2000_reg_write(IXDP2X01_INT_MASK_SET_REG, + ixp2000_reg_wrb(IXDP2X01_INT_MASK_SET_REG, IXP2000_BOARD_IRQ_MASK(irq)); } @@ -114,7 +114,7 @@ void __init ixdp2x01_init_irq(void) /* Mask all interrupts from CPLD, disable simulation */ ixp2000_reg_write(IXDP2X01_INT_MASK_SET_REG, 0xffffffff); - ixp2000_reg_write(IXDP2X01_INT_SIM_REG, 0); + ixp2000_reg_wrb(IXDP2X01_INT_SIM_REG, 0); for (irq = NR_IXP2000_IRQS; irq < NR_IXDP2X01_IRQS; irq++) { if (irq & valid_irq_mask) { @@ -316,7 +316,7 @@ static struct flash_platform_data ixdp2x01_flash_platform_data = { static unsigned long ixdp2x01_flash_bank_setup(unsigned long ofs) { - ixp2000_reg_write(IXDP2X01_CPLD_FLASH_REG, + ixp2000_reg_wrb(IXDP2X01_CPLD_FLASH_REG, ((ofs >> IXDP2X01_FLASH_WINDOW_BITS) | IXDP2X01_CPLD_FLASH_INTERN)); return (ofs & IXDP2X01_FLASH_WINDOW_MASK); } @@ -363,7 +363,7 @@ static struct platform_device *ixdp2x01_devices[] __initdata = { static void __init ixdp2x01_init_machine(void) { - ixp2000_reg_write(IXDP2X01_CPLD_FLASH_REG, + ixp2000_reg_wrb(IXDP2X01_CPLD_FLASH_REG, (IXDP2X01_CPLD_FLASH_BANK_MASK | IXDP2X01_CPLD_FLASH_INTERN)); ixdp2x01_flash_data.nr_banks = diff --git a/arch/arm/mach-ixp2000/pci.c b/arch/arm/mach-ixp2000/pci.c index 522205acb31..d4bf1e1c003 100644 --- a/arch/arm/mach-ixp2000/pci.c +++ b/arch/arm/mach-ixp2000/pci.c @@ -148,7 +148,7 @@ int ixp2000_pci_abort_handler(unsigned long addr, unsigned int fsr, struct pt_re local_irq_save(flags); temp = *(IXP2000_PCI_CONTROL); if (temp & ((1 << 8) | (1 << 5))) { - ixp2000_reg_write(IXP2000_PCI_CONTROL, temp); + ixp2000_reg_wrb(IXP2000_PCI_CONTROL, temp); } temp = *(IXP2000_PCI_CMDSTAT); @@ -178,8 +178,8 @@ clear_master_aborts(void) local_irq_save(flags); temp = *(IXP2000_PCI_CONTROL); - if (temp & ((1 << 8) | (1 << 5))) { - ixp2000_reg_write(IXP2000_PCI_CONTROL, temp); + if (temp & ((1 << 8) | (1 << 5))) { + ixp2000_reg_wrb(IXP2000_PCI_CONTROL, temp); } temp = *(IXP2000_PCI_CMDSTAT); -- cgit v1.2.3 From fa87cedd4e89ea29bda622d5cd6dbf19a915fc40 Mon Sep 17 00:00:00 2001 From: Lennert Buytenhek Date: Tue, 1 Nov 2005 19:44:27 +0000 Subject: [ARM] 3065/1: ixp2000 typo and whitespace fixes Patch from Lennert Buytenhek Misc ixp2000 typo and whitespace fixes. Signed-off-by: Lennert Buytenhek Signed-off-by: Deepak Saxena Signed-off-by: Russell King --- arch/arm/mach-ixp2000/core.c | 3 +-- arch/arm/mach-ixp2000/ixdp2x01.c | 1 - 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-ixp2000/core.c b/arch/arm/mach-ixp2000/core.c index 69c6cf81a44..c93a98b2a32 100644 --- a/arch/arm/mach-ixp2000/core.c +++ b/arch/arm/mach-ixp2000/core.c @@ -1,5 +1,5 @@ /* - * arch/arm/mach-ixp2000/common.c + * arch/arm/mach-ixp2000/core.c * * Common routines used by all IXP2400/2800 based platforms. * @@ -49,7 +49,6 @@ static unsigned long ixp2000_slowport_irq_flags; *************************************************************************/ void ixp2000_acquire_slowport(struct slowport_cfg *new_cfg, struct slowport_cfg *old_cfg) { - spin_lock_irqsave(&ixp2000_slowport_lock, ixp2000_slowport_irq_flags); old_cfg->CCR = *IXP2000_SLOWPORT_CCR; diff --git a/arch/arm/mach-ixp2000/ixdp2x01.c b/arch/arm/mach-ixp2000/ixdp2x01.c index dfaaa2d281e..a4e507c8a1d 100644 --- a/arch/arm/mach-ixp2000/ixdp2x01.c +++ b/arch/arm/mach-ixp2000/ixdp2x01.c @@ -299,7 +299,6 @@ struct hw_pci ixdp2x01_pci __initdata = { int __init ixdp2x01_pci_init(void) { - pci_common_init(&ixdp2x01_pci); return 0; } -- cgit v1.2.3 From e838ffc2e5c9afa81451cf21dcd3f3246e2adcd2 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Tue, 1 Nov 2005 19:44:28 +0000 Subject: [ARM] 3071/1: RX3715 - add lcd/fb platform setup Patch from Ben Dooks Platform data for the LCD/framebuffer driver for the RX3715 LCD panel. Signed-off-by: Ben Dooks Signed-off-by: Russell King --- arch/arm/mach-s3c2410/mach-rx3715.c | 70 ++++++++++++++++++++++++++++++++++--- 1 file changed, 66 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-s3c2410/mach-rx3715.c b/arch/arm/mach-s3c2410/mach-rx3715.c index 22d9e070fd6..7ff8e4d574c 100644 --- a/arch/arm/mach-s3c2410/mach-rx3715.c +++ b/arch/arm/mach-s3c2410/mach-rx3715.c @@ -17,6 +17,7 @@ * 10-Mar-2005 LCVR Changed S3C2410_VA to S3C24XX_VA * 14-Mar-2005 BJD Fixed __iomem warnings * 20-Sep-2005 BJD Added static to non-exported items + * 31-Oct-2005 BJD Added LCD setup for framebuffer */ #include @@ -42,6 +43,9 @@ #include #include +#include + +#include #include "clock.h" #include "devs.h" @@ -96,6 +100,66 @@ static struct s3c2410_uartcfg rx3715_uartcfgs[] = { } }; +/* framebuffer lcd controller information */ + +static struct s3c2410fb_mach_info rx3715_lcdcfg __initdata = { + .regs = { + .lcdcon1 = S3C2410_LCDCON1_TFT16BPP | \ + S3C2410_LCDCON1_TFT | \ + S3C2410_LCDCON1_CLKVAL(0x0C), + + .lcdcon2 = S3C2410_LCDCON2_VBPD(5) | \ + S3C2410_LCDCON2_LINEVAL(319) | \ + S3C2410_LCDCON2_VFPD(6) | \ + S3C2410_LCDCON2_VSPW(2), + + .lcdcon3 = S3C2410_LCDCON3_HBPD(35) | \ + S3C2410_LCDCON3_HOZVAL(239) | \ + S3C2410_LCDCON3_HFPD(35), + + .lcdcon4 = S3C2410_LCDCON4_MVAL(0) | \ + S3C2410_LCDCON4_HSPW(7), + + .lcdcon5 = S3C2410_LCDCON5_INVVLINE | + S3C2410_LCDCON5_FRM565 | + S3C2410_LCDCON5_HWSWP, + }, + + .lpcsel = 0xf82, + + .gpccon = 0xaa955699, + .gpccon_mask = 0xffc003cc, + .gpcup = 0x0000ffff, + .gpcup_mask = 0xffffffff, + + .gpdcon = 0xaa95aaa1, + .gpdcon_mask = 0xffc0fff0, + .gpdup = 0x0000faff, + .gpdup_mask = 0xffffffff, + + .fixed_syncs = 1, + .width = 240, + .height = 320, + + .xres = { + .min = 240, + .max = 240, + .defval = 240, + }, + + .yres = { + .max = 320, + .min = 320, + .defval = 320, + }, + + .bpp = { + .min = 16, + .max = 16, + .defval = 16, + }, +}; + static struct platform_device *rx3715_devices[] __initdata = { &s3c_device_usb, &s3c_device_lcd, @@ -122,14 +186,12 @@ static void __init rx3715_init_irq(void) s3c24xx_init_irq(); } -#ifdef CONFIG_PM static void __init rx3715_init_machine(void) { s3c2410_pm_init(); + s3c24xx_fb_set_platdata(&rx3715_lcdcfg); } -#else -#define rx3715_init_machine NULL -#endif + MACHINE_START(RX3715, "IPAQ-RX3715") /* Maintainer: Ben Dooks */ -- cgit v1.2.3 From 85eb226c446a017996859093cbfb5d3ae2c2117a Mon Sep 17 00:00:00 2001 From: David Brownell Date: Tue, 1 Nov 2005 19:44:30 +0000 Subject: [ARM] 3078/1: lubbock platform updates, mostly mmc detection Patch from David Brownell Lubbock updates: * Provide an address for the SMC91x chip that doesn't generate a boot-time warning (matching the EEPROM). * Update MMC support to (a) detect card insert/remove, and (b) report the readonly switch setting for SD cards. Previously, MMC/SD cards had to be present at boot time else they couldn't be detected. Signed-off-by: David Brownell Signed-off-by: Russell King --- arch/arm/mach-pxa/lubbock.c | 63 ++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 60 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-pxa/lubbock.c b/arch/arm/mach-pxa/lubbock.c index beccf455f79..689f31349bd 100644 --- a/arch/arm/mach-pxa/lubbock.c +++ b/arch/arm/mach-pxa/lubbock.c @@ -175,7 +175,7 @@ static struct platform_device sa1111_device = { static struct resource smc91x_resources[] = { [0] = { .name = "smc91x-regs", - .start = 0x0c000000, + .start = 0x0c000c00, .end = 0x0c0fffff, .flags = IORESOURCE_MEM, }, @@ -224,18 +224,75 @@ static struct pxafb_mach_info sharp_lm8v31 __initdata = { .lccr3 = LCCR3_PCP | LCCR3_Acb(255), }; -static int lubbock_mci_init(struct device *dev, irqreturn_t (*lubbock_detect_int)(int, void *, struct pt_regs *), void *data) +#define MMC_POLL_RATE msecs_to_jiffies(1000) + +static void lubbock_mmc_poll(unsigned long); +static irqreturn_t (*mmc_detect_int)(int, void *, struct pt_regs *); + +static struct timer_list mmc_timer = { + .function = lubbock_mmc_poll, +}; + +static void lubbock_mmc_poll(unsigned long data) +{ + unsigned long flags; + + /* clear any previous irq state, then ... */ + local_irq_save(flags); + LUB_IRQ_SET_CLR &= ~(1 << 0); + local_irq_restore(flags); + + /* poll until mmc/sd card is removed */ + if (LUB_IRQ_SET_CLR & (1 << 0)) + mod_timer(&mmc_timer, jiffies + MMC_POLL_RATE); + else { + (void) mmc_detect_int(LUBBOCK_SD_IRQ, (void *)data, NULL); + enable_irq(LUBBOCK_SD_IRQ); + } +} + +static irqreturn_t lubbock_detect_int(int irq, void *data, struct pt_regs *regs) +{ + /* IRQ is level triggered; disable, and poll for removal */ + disable_irq(irq); + mod_timer(&mmc_timer, jiffies + MMC_POLL_RATE); + + return mmc_detect_int(irq, data, regs); +} + +static int lubbock_mci_init(struct device *dev, + irqreturn_t (*detect_int)(int, void *, struct pt_regs *), + void *data) { /* setup GPIO for PXA25x MMC controller */ pxa_gpio_mode(GPIO6_MMCCLK_MD); pxa_gpio_mode(GPIO8_MMCCS0_MD); - return 0; + /* detect card insert/eject */ + mmc_detect_int = detect_int; + init_timer(&mmc_timer); + mmc_timer.data = (unsigned long) data; + return request_irq(LUBBOCK_SD_IRQ, lubbock_detect_int, + SA_SAMPLE_RANDOM, "lubbock-sd-detect", data); +} + +static int lubbock_mci_get_ro(struct device *dev) +{ + return (LUB_MISC_RD & (1 << 2)) != 0; +} + +static void lubbock_mci_exit(struct device *dev, void *data) +{ + free_irq(LUBBOCK_SD_IRQ, data); + del_timer_sync(&mmc_timer); } static struct pxamci_platform_data lubbock_mci_platform_data = { .ocr_mask = MMC_VDD_32_33|MMC_VDD_33_34, + .detect_delay = 1, .init = lubbock_mci_init, + .get_ro = lubbock_mci_get_ro, + .exit = lubbock_mci_exit, }; static void lubbock_irda_transceiver_mode(struct device *dev, int mode) -- cgit v1.2.3 From a0c6fdb987860e6c7f9b8e57439ca2703f462578 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 1 Nov 2005 19:52:22 +0000 Subject: [ARM] 2946/2: split --arch_clear_user() out of lib/uaccess.S Patch from Nicolas Pitre Required for future enhancement patches. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King --- arch/arm/lib/Makefile | 5 +++-- arch/arm/lib/clear_user.S | 52 +++++++++++++++++++++++++++++++++++++++++++++++ arch/arm/lib/uaccess.S | 38 ---------------------------------- 3 files changed, 55 insertions(+), 40 deletions(-) create mode 100644 arch/arm/lib/clear_user.S (limited to 'arch') diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile index 71e5b99e519..d3d9b21eb7e 100644 --- a/arch/arm/lib/Makefile +++ b/arch/arm/lib/Makefile @@ -9,8 +9,9 @@ lib-y := backtrace.o changebit.o csumipv6.o csumpartial.o \ copy_page.o delay.o findbit.o memchr.o memcpy.o \ memset.o memzero.o setbit.o strncpy_from_user.o \ strnlen_user.o strchr.o strrchr.o testchangebit.o \ - testclearbit.o testsetbit.o uaccess.o getuser.o \ - putuser.o ashldi3.o ashrdi3.o lshrdi3.o muldi3.o \ + testclearbit.o testsetbit.o uaccess.o \ + getuser.o putuser.o clear_user.o \ + ashldi3.o ashrdi3.o lshrdi3.o muldi3.o \ ucmpdi2.o lib1funcs.o div64.o sha1.o \ io-readsb.o io-writesb.o io-readsl.o io-writesl.o diff --git a/arch/arm/lib/clear_user.S b/arch/arm/lib/clear_user.S new file mode 100644 index 00000000000..7ff9f831b3f --- /dev/null +++ b/arch/arm/lib/clear_user.S @@ -0,0 +1,52 @@ +/* + * linux/arch/arm/lib/clear_user.S + * + * Copyright (C) 1995, 1996,1997,1998 Russell King + * + * 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 +#include + + .text + +/* Prototype: int __arch_clear_user(void *addr, size_t sz) + * Purpose : clear some user memory + * Params : addr - user memory address to clear + * : sz - number of bytes to clear + * Returns : number of bytes NOT cleared + */ +ENTRY(__arch_clear_user) + stmfd sp!, {r1, lr} + mov r2, #0 + cmp r1, #4 + blt 2f + ands ip, r0, #3 + beq 1f + cmp ip, #2 +USER( strbt r2, [r0], #1) +USER( strlebt r2, [r0], #1) +USER( strltbt r2, [r0], #1) + rsb ip, ip, #4 + sub r1, r1, ip @ 7 6 5 4 3 2 1 +1: subs r1, r1, #8 @ -1 -2 -3 -4 -5 -6 -7 +USER( strplt r2, [r0], #4) +USER( strplt r2, [r0], #4) + bpl 1b + adds r1, r1, #4 @ 3 2 1 0 -1 -2 -3 +USER( strplt r2, [r0], #4) +2: tst r1, #2 @ 1x 1x 0x 0x 1x 1x 0x +USER( strnebt r2, [r0], #1) +USER( strnebt r2, [r0], #1) + tst r1, #1 @ x1 x0 x1 x0 x1 x0 x1 +USER( strnebt r2, [r0], #1) + mov r0, #0 + LOADREGS(fd,sp!, {r1, pc}) + + .section .fixup,"ax" + .align 0 +9001: LOADREGS(fd,sp!, {r0, pc}) + .previous + diff --git a/arch/arm/lib/uaccess.S b/arch/arm/lib/uaccess.S index d3ed0636c00..c28449157be 100644 --- a/arch/arm/lib/uaccess.S +++ b/arch/arm/lib/uaccess.S @@ -657,41 +657,3 @@ USER( ldrgtbt r3, [r1], #1) @ May fault LOADREGS(fd,sp!, {r4 - r7, pc}) .previous -/* Prototype: int __arch_clear_user(void *addr, size_t sz) - * Purpose : clear some user memory - * Params : addr - user memory address to clear - * : sz - number of bytes to clear - * Returns : number of bytes NOT cleared - */ -ENTRY(__arch_clear_user) - stmfd sp!, {r1, lr} - mov r2, #0 - cmp r1, #4 - blt 2f - ands ip, r0, #3 - beq 1f - cmp ip, #2 -USER( strbt r2, [r0], #1) -USER( strlebt r2, [r0], #1) -USER( strltbt r2, [r0], #1) - rsb ip, ip, #4 - sub r1, r1, ip @ 7 6 5 4 3 2 1 -1: subs r1, r1, #8 @ -1 -2 -3 -4 -5 -6 -7 -USER( strplt r2, [r0], #4) -USER( strplt r2, [r0], #4) - bpl 1b - adds r1, r1, #4 @ 3 2 1 0 -1 -2 -3 -USER( strplt r2, [r0], #4) -2: tst r1, #2 @ 1x 1x 0x 0x 1x 1x 0x -USER( strnebt r2, [r0], #1) -USER( strnebt r2, [r0], #1) - tst r1, #1 @ x1 x0 x1 x0 x1 x0 x1 -USER( strnebt r2, [r0], #1) - mov r0, #0 - LOADREGS(fd,sp!, {r1, pc}) - - .section .fixup,"ax" - .align 0 -9001: LOADREGS(fd,sp!, {r0, pc}) - .previous - -- cgit v1.2.3 From 7549423000fc38d39a8b81c601dea0332c113a42 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 1 Nov 2005 19:52:23 +0000 Subject: [ARM] 2947/1: copy template with new memcpy/memmove Patch from Nicolas Pitre This patch provides a new implementation for optimized memory copy functions on ARM. It is made of two levels: a template that consists of the core copy code and separate files that define macros to be used with the core code depending on the type of copy needed. This allows for best performances while sharing the same core for implementing memcpy(), copy_from_user() and copy_to_user() for instance. Two reasons for this work: 1) the current copy_to_user/copy_from_user implementation assumes no task switch will ever occur in the middle of each copied page making it completely unsafe with CONFIG_PREEMPT=y. 2) current copy implementations are measurably suboptimal and optimizing different implementations separately is a pain and more opportunities for bugs. The reason for (1) is the fact that copy inside user pages are performed with the ldm instruction which has no mean for testing user protections and could possibly race with process preemption bypassing the COW mechanism for example. This is a longstanding issue that we said ought to be fixed for about two years now. The solution is to substitute those ldm insns with a series of ldrt or strt insns to enforce user memory protection. At least on StrongARM and XScale cores the ldm is not faster than the equivalent ldr/str insns with a warm i-cache so there is no measurable performance degradation with that change. The fact that the copy code is a template makes it pretty easy to reuse the same core code as for memcpy and benefit from the same performance optimizations. Now (2) is best demonstrated with actual throughput measurements. First, here is a summary of memcopy tests performed on a StrongARM core: PTR alignment buffer size kernel version this version ------------------------------------------------------------ aligned 32 59.73 107.43 unaligned 32 61.31 74.72 aligned 100 132.47 136.15 unaligned 100 103.84 123.76 aligned 4096 130.67 130.80 unaligned 4096 130.68 130.64 aligned 1048576 68.03 68.18 unaligned 1048576 68.03 68.18 The buffer size is in bytes and the measured speed in MB/s. The copy was performed repeatedly with given buffer and throughput averaged over 3 seconds. Here we can see that the current kernel version has a higher entry cost that shows up with small buffers. As buffer size grows both implementation converge to the same throughput. Now here's the exact same test performed on an XScale core (PXA255): PTR alignment buffer size kernel version this version ------------------------------------------------------------ aligned 32 46.99 77.58 unaligned 32 53.61 59.59 aligned 100 107.19 136.59 unaligned 100 83.61 97.58 aligned 4096 129.13 129.98 unaligned 4096 128.36 128.53 aligned 1048576 53.76 59.41 unaligned 1048576 33.67 56.96 Again we can see the entry setup cost being higher for the current kernel before getting to the main copy loop. Then throughput results converge as long as the buffer remains in the cache. Then the 1MB case shows more differences probably due to better pld placement and/or less instruction interlocks in this proposed implementation. Disclaimer: The PXA system was running with slower clocks than the StrongARM system so trying to infer any conclusion by comparing those separate sets of results side by side would be completely inappropriate. So... What this patch does is to replace both memcpy and memmove with an implementation based on the provided copy code template. The memmove code is kept separate since it is used only if the memory areas involved do overlap in which case the code is a transposition of the template but with the copy occurring in the opposite direction (trying to fit that mode into the template turned it into a mess not worth it for memmove alone). And obviously both memcpy and memmove were tested with all kinds of pointer alignments and buffer sizes to exercise all code paths for correctness. The next patch will provide the now trivial replacement implementation copy_to_user and copy_from_user. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King --- arch/arm/lib/Makefile | 5 +- arch/arm/lib/copy_template.S | 255 +++++++++++++++++++++++++++ arch/arm/lib/memcpy.S | 410 ++++--------------------------------------- arch/arm/lib/memmove.S | 206 ++++++++++++++++++++++ 4 files changed, 502 insertions(+), 374 deletions(-) create mode 100644 arch/arm/lib/copy_template.S create mode 100644 arch/arm/lib/memmove.S (limited to 'arch') diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile index d3d9b21eb7e..8f9770f1af1 100644 --- a/arch/arm/lib/Makefile +++ b/arch/arm/lib/Makefile @@ -7,8 +7,9 @@ lib-y := backtrace.o changebit.o csumipv6.o csumpartial.o \ csumpartialcopy.o csumpartialcopyuser.o clearbit.o \ copy_page.o delay.o findbit.o memchr.o memcpy.o \ - memset.o memzero.o setbit.o strncpy_from_user.o \ - strnlen_user.o strchr.o strrchr.o testchangebit.o \ + memmove.o memset.o memzero.o setbit.o \ + strncpy_from_user.o strnlen_user.o \ + strchr.o strrchr.o testchangebit.o \ testclearbit.o testsetbit.o uaccess.o \ getuser.o putuser.o clear_user.o \ ashldi3.o ashrdi3.o lshrdi3.o muldi3.o \ diff --git a/arch/arm/lib/copy_template.S b/arch/arm/lib/copy_template.S new file mode 100644 index 00000000000..838e435e492 --- /dev/null +++ b/arch/arm/lib/copy_template.S @@ -0,0 +1,255 @@ +/* + * linux/arch/arm/lib/copy_template.s + * + * Code template for optimized memory copy functions + * + * Author: Nicolas Pitre + * Created: Sep 28, 2005 + * Copyright: 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 version 2 as + * published by the Free Software Foundation. + */ + +/* + * This can be used to enable code to cacheline align the source pointer. + * Experiments on tested architectures (StrongARM and XScale) didn't show + * this a worthwhile thing to do. That might be different in the future. + */ +//#define CALGN(code...) code +#define CALGN(code...) + +/* + * Theory of operation + * ------------------- + * + * This file provides the core code for a forward memory copy used in + * the implementation of memcopy(), copy_to_user() and copy_from_user(). + * + * The including file must define the following accessor macros + * according to the need of the given function: + * + * ldr1w ptr reg abort + * + * This loads one word from 'ptr', stores it in 'reg' and increments + * 'ptr' to the next word. The 'abort' argument is used for fixup tables. + * + * ldr4w ptr reg1 reg2 reg3 reg4 abort + * ldr8w ptr, reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort + * + * This loads four or eight words starting from 'ptr', stores them + * in provided registers and increments 'ptr' past those words. + * The'abort' argument is used for fixup tables. + * + * ldr1b ptr reg cond abort + * + * Similar to ldr1w, but it loads a byte and increments 'ptr' one byte. + * It also must apply the condition code if provided, otherwise the + * "al" condition is assumed by default. + * + * str1w ptr reg abort + * str8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort + * str1b ptr reg cond abort + * + * Same as their ldr* counterparts, but data is stored to 'ptr' location + * rather than being loaded. + * + * enter reg1 reg2 + * + * Preserve the provided registers on the stack plus any additional + * data as needed by the implementation including this code. Called + * upon code entry. + * + * exit reg1 reg2 + * + * Restore registers with the values previously saved with the + * 'preserv' macro. Called upon code termination. + */ + + + enter r4, lr + + subs r2, r2, #4 + blt 8f + ands ip, r0, #3 + PLD( pld [r1, #0] ) + bne 9f + ands ip, r1, #3 + bne 10f + +1: subs r2, r2, #(28) + stmfd sp!, {r5 - r8} + blt 5f + + CALGN( ands ip, r1, #31 ) + CALGN( rsb r3, ip, #32 ) + CALGN( sbcnes r4, r3, r2 ) @ C is always set here + CALGN( bcs 2f ) + CALGN( adr r4, 6f ) + CALGN( subs r2, r2, r3 ) @ C gets set + CALGN( add pc, r4, ip ) + + PLD( pld [r1, #0] ) +2: PLD( subs r2, r2, #96 ) + PLD( pld [r1, #28] ) + PLD( blt 4f ) + PLD( pld [r1, #60] ) + PLD( pld [r1, #92] ) + +3: PLD( pld [r1, #124] ) +4: ldr8w r1, r3, r4, r5, r6, r7, r8, ip, lr, abort=20f + subs r2, r2, #32 + str8w r0, r3, r4, r5, r6, r7, r8, ip, lr, abort=20f + bge 3b + PLD( cmn r2, #96 ) + PLD( bge 4b ) + +5: ands ip, r2, #28 + rsb ip, ip, #32 + addne pc, pc, ip @ C is always clear here + b 7f +6: nop + ldr1w r1, r3, abort=20f + ldr1w r1, r4, abort=20f + ldr1w r1, r5, abort=20f + ldr1w r1, r6, abort=20f + ldr1w r1, r7, abort=20f + ldr1w r1, r8, abort=20f + ldr1w r1, lr, abort=20f + + add pc, pc, ip + nop + nop + str1w r0, r3, abort=20f + str1w r0, r4, abort=20f + str1w r0, r5, abort=20f + str1w r0, r6, abort=20f + str1w r0, r7, abort=20f + str1w r0, r8, abort=20f + str1w r0, lr, abort=20f + + CALGN( bcs 2b ) + +7: ldmfd sp!, {r5 - r8} + +8: movs r2, r2, lsl #31 + ldr1b r1, r3, ne, abort=21f + ldr1b r1, r4, cs, abort=21f + ldr1b r1, ip, cs, abort=21f + str1b r0, r3, ne, abort=21f + str1b r0, r4, cs, abort=21f + str1b r0, ip, cs, abort=21f + + exit r4, pc + +9: rsb ip, ip, #4 + cmp ip, #2 + ldr1b r1, r3, gt, abort=21f + ldr1b r1, r4, ge, abort=21f + ldr1b r1, lr, abort=21f + str1b r0, r3, gt, abort=21f + str1b r0, r4, ge, abort=21f + subs r2, r2, ip + str1b r0, lr, abort=21f + blt 8b + ands ip, r1, #3 + beq 1b + +10: bic r1, r1, #3 + cmp ip, #2 + ldr1w r1, lr, abort=21f + beq 17f + bgt 18f + + + .macro forward_copy_shift pull push + + subs r2, r2, #28 + blt 14f + + CALGN( ands ip, r1, #31 ) + CALGN( rsb ip, ip, #32 ) + CALGN( sbcnes r4, ip, r2 ) @ C is always set here + CALGN( subcc r2, r2, ip ) + CALGN( bcc 15f ) + +11: stmfd sp!, {r5 - r9} + + PLD( pld [r1, #0] ) + PLD( subs r2, r2, #96 ) + PLD( pld [r1, #28] ) + PLD( blt 13f ) + PLD( pld [r1, #60] ) + PLD( pld [r1, #92] ) + +12: PLD( pld [r1, #124] ) +13: ldr4w r1, r4, r5, r6, r7, abort=19f + mov r3, lr, pull #\pull + subs r2, r2, #32 + ldr4w r1, r8, r9, ip, lr, abort=19f + orr r3, r3, r4, push #\push + mov r4, r4, pull #\pull + orr r4, r4, r5, push #\push + mov r5, r5, pull #\pull + orr r5, r5, r6, push #\push + mov r6, r6, pull #\pull + orr r6, r6, r7, push #\push + mov r7, r7, pull #\pull + orr r7, r7, r8, push #\push + mov r8, r8, pull #\pull + orr r8, r8, r9, push #\push + mov r9, r9, pull #\pull + orr r9, r9, ip, push #\push + mov ip, ip, pull #\pull + orr ip, ip, lr, push #\push + str8w r0, r3, r4, r5, r6, r7, r8, r9, ip, , abort=19f + bge 12b + PLD( cmn r2, #96 ) + PLD( bge 13b ) + + ldmfd sp!, {r5 - r9} + +14: ands ip, r2, #28 + beq 16f + +15: mov r3, lr, pull #\pull + ldr1w r1, lr, abort=21f + subs ip, ip, #4 + orr r3, r3, lr, push #\push + str1w r0, r3, abort=21f + bgt 15b + CALGN( cmp r2, #0 ) + CALGN( bge 11b ) + +16: sub r1, r1, #(\push / 8) + b 8b + + .endm + + + forward_copy_shift pull=8 push=24 + +17: forward_copy_shift pull=16 push=16 + +18: forward_copy_shift pull=24 push=8 + + +/* + * Abort preanble and completion macros. + * If a fixup handler is required then those macros must surround it. + * It is assumed that the fixup code will handle the private part of + * the exit macro. + */ + + .macro copy_abort_preamble +19: ldmfd sp!, {r5 - r9} + b 21f +20: ldmfd sp!, {r5 - r8} +21: + .endm + + .macro copy_abort_end + ldmfd sp!, {r4, pc} + .endm + diff --git a/arch/arm/lib/memcpy.S b/arch/arm/lib/memcpy.S index f5a593ceb8c..7e71d6708a8 100644 --- a/arch/arm/lib/memcpy.S +++ b/arch/arm/lib/memcpy.S @@ -1,393 +1,59 @@ /* * linux/arch/arm/lib/memcpy.S * - * Copyright (C) 1995-1999 Russell King + * Author: Nicolas Pitre + * Created: Sep 28, 2005 + * Copyright: 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 version 2 as - * published by the Free Software Foundation. - * - * ASM optimised string functions + * 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 #include - .text - -#define ENTER \ - mov ip,sp ;\ - stmfd sp!,{r0,r4-r9,fp,ip,lr,pc} ;\ - sub fp,ip,#4 - -#define EXIT \ - LOADREGS(ea, fp, {r0, r4 - r9, fp, sp, pc}) - -#define EXITEQ \ - LOADREGS(eqea, fp, {r0, r4 - r9, fp, sp, pc}) - -/* - * Prototype: void memcpy(void *to,const void *from,unsigned long n); - */ -ENTRY(memcpy) -ENTRY(memmove) - ENTER - cmp r1, r0 - bcc 23f - subs r2, r2, #4 - blt 6f - PLD( pld [r1, #0] ) - ands ip, r0, #3 - bne 7f - ands ip, r1, #3 - bne 8f + .macro ldr1w ptr reg abort + ldr \reg, [\ptr], #4 + .endm -1: subs r2, r2, #8 - blt 5f - subs r2, r2, #20 - blt 4f - PLD( pld [r1, #28] ) - PLD( subs r2, r2, #64 ) - PLD( blt 3f ) -2: PLD( pld [r1, #60] ) - PLD( pld [r1, #92] ) - ldmia r1!, {r3 - r9, ip} - subs r2, r2, #32 - stmgeia r0!, {r3 - r9, ip} - ldmgeia r1!, {r3 - r9, ip} - subges r2, r2, #32 - stmia r0!, {r3 - r9, ip} - bge 2b -3: PLD( ldmia r1!, {r3 - r9, ip} ) - PLD( adds r2, r2, #32 ) - PLD( stmgeia r0!, {r3 - r9, ip} ) - PLD( ldmgeia r1!, {r3 - r9, ip} ) - PLD( subges r2, r2, #32 ) - PLD( stmia r0!, {r3 - r9, ip} ) -4: cmn r2, #16 - ldmgeia r1!, {r3 - r6} - subge r2, r2, #16 - stmgeia r0!, {r3 - r6} - adds r2, r2, #20 - ldmgeia r1!, {r3 - r5} - subge r2, r2, #12 - stmgeia r0!, {r3 - r5} -5: adds r2, r2, #8 - blt 6f - subs r2, r2, #4 - ldrlt r3, [r1], #4 - ldmgeia r1!, {r4, r5} - subge r2, r2, #4 - strlt r3, [r0], #4 - stmgeia r0!, {r4, r5} + .macro ldr4w ptr reg1 reg2 reg3 reg4 abort + ldmia \ptr!, {\reg1, \reg2, \reg3, \reg4} + .endm -6: adds r2, r2, #4 - EXITEQ - cmp r2, #2 - ldrb r3, [r1], #1 - ldrgeb r4, [r1], #1 - ldrgtb r5, [r1], #1 - strb r3, [r0], #1 - strgeb r4, [r0], #1 - strgtb r5, [r0], #1 - EXIT + .macro ldr8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort + ldmia \ptr!, {\reg1, \reg2, \reg3, \reg4, \reg5, \reg6, \reg7, \reg8} + .endm -7: rsb ip, ip, #4 - cmp ip, #2 - ldrb r3, [r1], #1 - ldrgeb r4, [r1], #1 - ldrgtb r5, [r1], #1 - strb r3, [r0], #1 - strgeb r4, [r0], #1 - strgtb r5, [r0], #1 - subs r2, r2, ip - blt 6b - ands ip, r1, #3 - beq 1b + .macro ldr1b ptr reg cond=al abort + ldr\cond\()b \reg, [\ptr], #1 + .endm -8: bic r1, r1, #3 - ldr r7, [r1], #4 - cmp ip, #2 - bgt 18f - beq 13f - cmp r2, #12 - blt 11f - PLD( pld [r1, #12] ) - sub r2, r2, #12 - PLD( subs r2, r2, #32 ) - PLD( blt 10f ) - PLD( pld [r1, #28] ) -9: PLD( pld [r1, #44] ) -10: mov r3, r7, pull #8 - ldmia r1!, {r4 - r7} - subs r2, r2, #16 - orr r3, r3, r4, push #24 - mov r4, r4, pull #8 - orr r4, r4, r5, push #24 - mov r5, r5, pull #8 - orr r5, r5, r6, push #24 - mov r6, r6, pull #8 - orr r6, r6, r7, push #24 - stmia r0!, {r3 - r6} - bge 9b - PLD( cmn r2, #32 ) - PLD( bge 10b ) - PLD( add r2, r2, #32 ) - adds r2, r2, #12 - blt 12f -11: mov r3, r7, pull #8 - ldr r7, [r1], #4 - subs r2, r2, #4 - orr r3, r3, r7, push #24 - str r3, [r0], #4 - bge 11b -12: sub r1, r1, #3 - b 6b + .macro str1w ptr reg abort + str \reg, [\ptr], #4 + .endm -13: cmp r2, #12 - blt 16f - PLD( pld [r1, #12] ) - sub r2, r2, #12 - PLD( subs r2, r2, #32 ) - PLD( blt 15f ) - PLD( pld [r1, #28] ) -14: PLD( pld [r1, #44] ) -15: mov r3, r7, pull #16 - ldmia r1!, {r4 - r7} - subs r2, r2, #16 - orr r3, r3, r4, push #16 - mov r4, r4, pull #16 - orr r4, r4, r5, push #16 - mov r5, r5, pull #16 - orr r5, r5, r6, push #16 - mov r6, r6, pull #16 - orr r6, r6, r7, push #16 - stmia r0!, {r3 - r6} - bge 14b - PLD( cmn r2, #32 ) - PLD( bge 15b ) - PLD( add r2, r2, #32 ) - adds r2, r2, #12 - blt 17f -16: mov r3, r7, pull #16 - ldr r7, [r1], #4 - subs r2, r2, #4 - orr r3, r3, r7, push #16 - str r3, [r0], #4 - bge 16b -17: sub r1, r1, #2 - b 6b + .macro str8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort + stmia \ptr!, {\reg1, \reg2, \reg3, \reg4, \reg5, \reg6, \reg7, \reg8} + .endm -18: cmp r2, #12 - blt 21f - PLD( pld [r1, #12] ) - sub r2, r2, #12 - PLD( subs r2, r2, #32 ) - PLD( blt 20f ) - PLD( pld [r1, #28] ) -19: PLD( pld [r1, #44] ) -20: mov r3, r7, pull #24 - ldmia r1!, {r4 - r7} - subs r2, r2, #16 - orr r3, r3, r4, push #8 - mov r4, r4, pull #24 - orr r4, r4, r5, push #8 - mov r5, r5, pull #24 - orr r5, r5, r6, push #8 - mov r6, r6, pull #24 - orr r6, r6, r7, push #8 - stmia r0!, {r3 - r6} - bge 19b - PLD( cmn r2, #32 ) - PLD( bge 20b ) - PLD( add r2, r2, #32 ) - adds r2, r2, #12 - blt 22f -21: mov r3, r7, pull #24 - ldr r7, [r1], #4 - subs r2, r2, #4 - orr r3, r3, r7, push #8 - str r3, [r0], #4 - bge 21b -22: sub r1, r1, #1 - b 6b + .macro str1b ptr reg cond=al abort + str\cond\()b \reg, [\ptr], #1 + .endm + .macro enter reg1 reg2 + stmdb sp!, {r0, \reg1, \reg2} + .endm -23: add r1, r1, r2 - add r0, r0, r2 - subs r2, r2, #4 - blt 29f - PLD( pld [r1, #-4] ) - ands ip, r0, #3 - bne 30f - ands ip, r1, #3 - bne 31f + .macro exit reg1 reg2 + ldmfd sp!, {r0, \reg1, \reg2} + .endm -24: subs r2, r2, #8 - blt 28f - subs r2, r2, #20 - blt 27f - PLD( pld [r1, #-32] ) - PLD( subs r2, r2, #64 ) - PLD( blt 26f ) -25: PLD( pld [r1, #-64] ) - PLD( pld [r1, #-96] ) - ldmdb r1!, {r3 - r9, ip} - subs r2, r2, #32 - stmgedb r0!, {r3 - r9, ip} - ldmgedb r1!, {r3 - r9, ip} - subges r2, r2, #32 - stmdb r0!, {r3 - r9, ip} - bge 25b -26: PLD( ldmdb r1!, {r3 - r9, ip} ) - PLD( adds r2, r2, #32 ) - PLD( stmgedb r0!, {r3 - r9, ip} ) - PLD( ldmgedb r1!, {r3 - r9, ip} ) - PLD( subges r2, r2, #32 ) - PLD( stmdb r0!, {r3 - r9, ip} ) -27: cmn r2, #16 - ldmgedb r1!, {r3 - r6} - subge r2, r2, #16 - stmgedb r0!, {r3 - r6} - adds r2, r2, #20 - ldmgedb r1!, {r3 - r5} - subge r2, r2, #12 - stmgedb r0!, {r3 - r5} -28: adds r2, r2, #8 - blt 29f - subs r2, r2, #4 - ldrlt r3, [r1, #-4]! - ldmgedb r1!, {r4, r5} - subge r2, r2, #4 - strlt r3, [r0, #-4]! - stmgedb r0!, {r4, r5} + .text -29: adds r2, r2, #4 - EXITEQ - cmp r2, #2 - ldrb r3, [r1, #-1]! - ldrgeb r4, [r1, #-1]! - ldrgtb r5, [r1, #-1]! - strb r3, [r0, #-1]! - strgeb r4, [r0, #-1]! - strgtb r5, [r0, #-1]! - EXIT +/* Prototype: void *memcpy(void *dest, const void *src, size_t n); */ -30: cmp ip, #2 - ldrb r3, [r1, #-1]! - ldrgeb r4, [r1, #-1]! - ldrgtb r5, [r1, #-1]! - strb r3, [r0, #-1]! - strgeb r4, [r0, #-1]! - strgtb r5, [r0, #-1]! - subs r2, r2, ip - blt 29b - ands ip, r1, #3 - beq 24b - -31: bic r1, r1, #3 - ldr r3, [r1], #0 - cmp ip, #2 - blt 41f - beq 36f - cmp r2, #12 - blt 34f - PLD( pld [r1, #-16] ) - sub r2, r2, #12 - PLD( subs r2, r2, #32 ) - PLD( blt 33f ) - PLD( pld [r1, #-32] ) -32: PLD( pld [r1, #-48] ) -33: mov r7, r3, push #8 - ldmdb r1!, {r3, r4, r5, r6} - subs r2, r2, #16 - orr r7, r7, r6, pull #24 - mov r6, r6, push #8 - orr r6, r6, r5, pull #24 - mov r5, r5, push #8 - orr r5, r5, r4, pull #24 - mov r4, r4, push #8 - orr r4, r4, r3, pull #24 - stmdb r0!, {r4, r5, r6, r7} - bge 32b - PLD( cmn r2, #32 ) - PLD( bge 33b ) - PLD( add r2, r2, #32 ) - adds r2, r2, #12 - blt 35f -34: mov ip, r3, push #8 - ldr r3, [r1, #-4]! - subs r2, r2, #4 - orr ip, ip, r3, pull #24 - str ip, [r0, #-4]! - bge 34b -35: add r1, r1, #3 - b 29b - -36: cmp r2, #12 - blt 39f - PLD( pld [r1, #-16] ) - sub r2, r2, #12 - PLD( subs r2, r2, #32 ) - PLD( blt 38f ) - PLD( pld [r1, #-32] ) -37: PLD( pld [r1, #-48] ) -38: mov r7, r3, push #16 - ldmdb r1!, {r3, r4, r5, r6} - subs r2, r2, #16 - orr r7, r7, r6, pull #16 - mov r6, r6, push #16 - orr r6, r6, r5, pull #16 - mov r5, r5, push #16 - orr r5, r5, r4, pull #16 - mov r4, r4, push #16 - orr r4, r4, r3, pull #16 - stmdb r0!, {r4, r5, r6, r7} - bge 37b - PLD( cmn r2, #32 ) - PLD( bge 38b ) - PLD( add r2, r2, #32 ) - adds r2, r2, #12 - blt 40f -39: mov ip, r3, push #16 - ldr r3, [r1, #-4]! - subs r2, r2, #4 - orr ip, ip, r3, pull #16 - str ip, [r0, #-4]! - bge 39b -40: add r1, r1, #2 - b 29b +ENTRY(memcpy) -41: cmp r2, #12 - blt 44f - PLD( pld [r1, #-16] ) - sub r2, r2, #12 - PLD( subs r2, r2, #32 ) - PLD( blt 43f ) - PLD( pld [r1, #-32] ) -42: PLD( pld [r1, #-48] ) -43: mov r7, r3, push #24 - ldmdb r1!, {r3, r4, r5, r6} - subs r2, r2, #16 - orr r7, r7, r6, pull #8 - mov r6, r6, push #24 - orr r6, r6, r5, pull #8 - mov r5, r5, push #24 - orr r5, r5, r4, pull #8 - mov r4, r4, push #24 - orr r4, r4, r3, pull #8 - stmdb r0!, {r4, r5, r6, r7} - bge 42b - PLD( cmn r2, #32 ) - PLD( bge 43b ) - PLD( add r2, r2, #32 ) - adds r2, r2, #12 - blt 45f -44: mov ip, r3, push #24 - ldr r3, [r1, #-4]! - subs r2, r2, #4 - orr ip, ip, r3, pull #8 - str ip, [r0, #-4]! - bge 44b -45: add r1, r1, #1 - b 29b +#include "copy_template.S" diff --git a/arch/arm/lib/memmove.S b/arch/arm/lib/memmove.S new file mode 100644 index 00000000000..ef7fddc14ac --- /dev/null +++ b/arch/arm/lib/memmove.S @@ -0,0 +1,206 @@ +/* + * linux/arch/arm/lib/memmove.S + * + * Author: Nicolas Pitre + * Created: Sep 28, 2005 + * Copyright: (C) 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 version 2 as + * published by the Free Software Foundation. + */ + +#include +#include + +/* + * This can be used to enable code to cacheline align the source pointer. + * Experiments on tested architectures (StrongARM and XScale) didn't show + * this a worthwhile thing to do. That might be different in the future. + */ +//#define CALGN(code...) code +#define CALGN(code...) + + .text + +/* + * Prototype: void *memmove(void *dest, const void *src, size_t n); + * + * Note: + * + * If the memory regions don't overlap, we simply branch to memcpy which is + * normally a bit faster. Otherwise the copy is done going downwards. This + * is a transposition of the code from copy_template.S but with the copy + * occurring in the opposite direction. + */ + +ENTRY(memmove) + + subs ip, r0, r1 + cmphi r2, ip + bls memcpy + + stmfd sp!, {r0, r4, lr} + add r1, r1, r2 + add r0, r0, r2 + subs r2, r2, #4 + blt 8f + ands ip, r0, #3 + PLD( pld [r1, #-4] ) + bne 9f + ands ip, r1, #3 + bne 10f + +1: subs r2, r2, #(28) + stmfd sp!, {r5 - r8} + blt 5f + + CALGN( ands ip, r1, #31 ) + CALGN( sbcnes r4, ip, r2 ) @ C is always set here + CALGN( bcs 2f ) + CALGN( adr r4, 6f ) + CALGN( subs r2, r2, ip ) @ C is set here + CALGN( add pc, r4, ip ) + + PLD( pld [r1, #-4] ) +2: PLD( subs r2, r2, #96 ) + PLD( pld [r1, #-32] ) + PLD( blt 4f ) + PLD( pld [r1, #-64] ) + PLD( pld [r1, #-96] ) + +3: PLD( pld [r1, #-128] ) +4: ldmdb r1!, {r3, r4, r5, r6, r7, r8, ip, lr} + subs r2, r2, #32 + stmdb r0!, {r3, r4, r5, r6, r7, r8, ip, lr} + bge 3b + PLD( cmn r2, #96 ) + PLD( bge 4b ) + +5: ands ip, r2, #28 + rsb ip, ip, #32 + addne pc, pc, ip @ C is always clear here + b 7f +6: nop + ldr r3, [r1, #-4]! + ldr r4, [r1, #-4]! + ldr r5, [r1, #-4]! + ldr r6, [r1, #-4]! + ldr r7, [r1, #-4]! + ldr r8, [r1, #-4]! + ldr lr, [r1, #-4]! + + add pc, pc, ip + nop + nop + str r3, [r0, #-4]! + str r4, [r0, #-4]! + str r5, [r0, #-4]! + str r6, [r0, #-4]! + str r7, [r0, #-4]! + str r8, [r0, #-4]! + str lr, [r0, #-4]! + + CALGN( bcs 2b ) + +7: ldmfd sp!, {r5 - r8} + +8: movs r2, r2, lsl #31 + ldrneb r3, [r1, #-1]! + ldrcsb r4, [r1, #-1]! + ldrcsb ip, [r1, #-1] + strneb r3, [r0, #-1]! + strcsb r4, [r0, #-1]! + strcsb ip, [r0, #-1] + ldmfd sp!, {r0, r4, pc} + +9: cmp ip, #2 + ldrgtb r3, [r1, #-1]! + ldrgeb r4, [r1, #-1]! + ldrb lr, [r1, #-1]! + strgtb r3, [r0, #-1]! + strgeb r4, [r0, #-1]! + subs r2, r2, ip + strb lr, [r0, #-1]! + blt 8b + ands ip, r1, #3 + beq 1b + +10: bic r1, r1, #3 + cmp ip, #2 + ldr r3, [r1, #0] + beq 17f + blt 18f + + + .macro backward_copy_shift push pull + + subs r2, r2, #28 + blt 14f + + CALGN( ands ip, r1, #31 ) + CALGN( rsb ip, ip, #32 ) + CALGN( sbcnes r4, ip, r2 ) @ C is always set here + CALGN( subcc r2, r2, ip ) + CALGN( bcc 15f ) + +11: stmfd sp!, {r5 - r9} + + PLD( pld [r1, #-4] ) + PLD( subs r2, r2, #96 ) + PLD( pld [r1, #-32] ) + PLD( blt 13f ) + PLD( pld [r1, #-64] ) + PLD( pld [r1, #-96] ) + +12: PLD( pld [r1, #-128] ) +13: ldmdb r1!, {r7, r8, r9, ip} + mov lr, r3, push #\push + subs r2, r2, #32 + ldmdb r1!, {r3, r4, r5, r6} + orr lr, lr, ip, pull #\pull + mov ip, ip, push #\push + orr ip, ip, r9, pull #\pull + mov r9, r9, push #\push + orr r9, r9, r8, pull #\pull + mov r8, r8, push #\push + orr r8, r8, r7, pull #\pull + mov r7, r7, push #\push + orr r7, r7, r6, pull #\pull + mov r6, r6, push #\push + orr r6, r6, r5, pull #\pull + mov r5, r5, push #\push + orr r5, r5, r4, pull #\pull + mov r4, r4, push #\push + orr r4, r4, r3, pull #\pull + stmdb r0!, {r4 - r9, ip, lr} + bge 12b + PLD( cmn r2, #96 ) + PLD( bge 13b ) + + ldmfd sp!, {r5 - r9} + +14: ands ip, r2, #28 + beq 16f + +15: mov lr, r3, push #\push + ldr r3, [r1, #-4]! + subs ip, ip, #4 + orr lr, lr, r3, pull #\pull + str lr, [r0, #-4]! + bgt 15b + CALGN( cmp r2, #0 ) + CALGN( bge 11b ) + +16: add r1, r1, #(\pull / 8) + b 8b + + .endm + + + backward_copy_shift push=8 pull=24 + +17: backward_copy_shift push=16 pull=16 + +18: backward_copy_shift push=24 pull=8 + -- cgit v1.2.3 From fadab0943d1c5b652a66858bb99b204fedaad96b Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 1 Nov 2005 19:52:24 +0000 Subject: [ARM] 2948/1: new preemption safe copy_{to|from}_user implementation Patch from Nicolas Pitre This patch provides a preemption safe implementation of copy_to_user and copy_from_user based on the copy template also used for memcpy. It is enabled unconditionally when CONFIG_PREEMPT=y. Otherwise if the configured architecture is not ARMv3 then it is enabled as well as it gives better performances at least on StrongARM and XScale cores. If ARMv3 is not too affected or if it doesn't matter too much then uaccess.S could be removed altogether. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King --- arch/arm/lib/Makefile | 16 ++++++- arch/arm/lib/copy_from_user.S | 101 ++++++++++++++++++++++++++++++++++++++++++ arch/arm/lib/copy_to_user.S | 101 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 216 insertions(+), 2 deletions(-) create mode 100644 arch/arm/lib/copy_from_user.S create mode 100644 arch/arm/lib/copy_to_user.S (limited to 'arch') diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile index 8f9770f1af1..391f3ab3ff3 100644 --- a/arch/arm/lib/Makefile +++ b/arch/arm/lib/Makefile @@ -9,13 +9,25 @@ lib-y := backtrace.o changebit.o csumipv6.o csumpartial.o \ copy_page.o delay.o findbit.o memchr.o memcpy.o \ memmove.o memset.o memzero.o setbit.o \ strncpy_from_user.o strnlen_user.o \ - strchr.o strrchr.o testchangebit.o \ - testclearbit.o testsetbit.o uaccess.o \ + strchr.o strrchr.o \ + testchangebit.o testclearbit.o testsetbit.o \ getuser.o putuser.o clear_user.o \ ashldi3.o ashrdi3.o lshrdi3.o muldi3.o \ ucmpdi2.o lib1funcs.o div64.o sha1.o \ io-readsb.o io-writesb.o io-readsl.o io-writesl.o +# the code in uaccess.S is not preemption safe and +# probably faster on ARMv3 only +ifeq ($CONFIG_PREEMPT,y) + lib-y += copy_from_user.o copy_to_user.o +else +ifneq ($(CONFIG_CPU_32v3),y) + lib-y += copy_from_user.o copy_to_user.o +else + lib-y += uaccess.o +endif +endif + ifeq ($(CONFIG_CPU_32v3),y) lib-y += io-readsw-armv3.o io-writesw-armv3.o else diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S new file mode 100644 index 00000000000..7497393a0e8 --- /dev/null +++ b/arch/arm/lib/copy_from_user.S @@ -0,0 +1,101 @@ +/* + * linux/arch/arm/lib/copy_from_user.S + * + * Author: Nicolas Pitre + * Created: Sep 29, 2005 + * Copyright: 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 version 2 as + * published by the Free Software Foundation. + */ + +#include +#include + +/* + * Prototype: + * + * size_t __arch_copy_from_user(void *to, const void *from, size_t n) + * + * Purpose: + * + * copy a block to kernel memory from user memory + * + * Params: + * + * to = kernel memory + * from = user memory + * n = number of bytes to copy + * + * Return value: + * + * Number of bytes NOT copied. + */ + + .macro ldr1w ptr reg abort +100: ldrt \reg, [\ptr], #4 + .section __ex_table, "a" + .long 100b, \abort + .previous + .endm + + .macro ldr4w ptr reg1 reg2 reg3 reg4 abort + ldr1w \ptr, \reg1, \abort + ldr1w \ptr, \reg2, \abort + ldr1w \ptr, \reg3, \abort + ldr1w \ptr, \reg4, \abort + .endm + + .macro ldr8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort + ldr4w \ptr, \reg1, \reg2, \reg3, \reg4, \abort + ldr4w \ptr, \reg5, \reg6, \reg7, \reg8, \abort + .endm + + .macro ldr1b ptr reg cond=al abort +100: ldr\cond\()bt \reg, [\ptr], #1 + .section __ex_table, "a" + .long 100b, \abort + .previous + .endm + + .macro str1w ptr reg abort + str \reg, [\ptr], #4 + .endm + + .macro str8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort + stmia \ptr!, {\reg1, \reg2, \reg3, \reg4, \reg5, \reg6, \reg7, \reg8} + .endm + + .macro str1b ptr reg cond=al abort + str\cond\()b \reg, [\ptr], #1 + .endm + + .macro enter reg1 reg2 + mov r3, #0 + stmdb sp!, {r0, r2, r3, \reg1, \reg2} + .endm + + .macro exit reg1 reg2 + add sp, sp, #8 + ldmfd sp!, {r0, \reg1, \reg2} + .endm + + .text + +ENTRY(__arch_copy_from_user) + +#include "copy_template.S" + + .section .fixup,"ax" + .align 0 + copy_abort_preamble + ldmfd sp!, {r1, r2} + sub r3, r0, r1 + rsb r1, r3, r2 + str r1, [sp] + bl __memzero + ldr r0, [sp], #4 + copy_abort_end + .previous + diff --git a/arch/arm/lib/copy_to_user.S b/arch/arm/lib/copy_to_user.S new file mode 100644 index 00000000000..4a6d8ea1402 --- /dev/null +++ b/arch/arm/lib/copy_to_user.S @@ -0,0 +1,101 @@ +/* + * linux/arch/arm/lib/copy_to_user.S + * + * Author: Nicolas Pitre + * Created: Sep 29, 2005 + * Copyright: 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 version 2 as + * published by the Free Software Foundation. + */ + +#include +#include + +/* + * Prototype: + * + * size_t __arch_copy_to_user(void *to, const void *from, size_t n) + * + * Purpose: + * + * copy a block to user memory from kernel memory + * + * Params: + * + * to = user memory + * from = kernel memory + * n = number of bytes to copy + * + * Return value: + * + * Number of bytes NOT copied. + */ + + .macro ldr1w ptr reg abort + ldr \reg, [\ptr], #4 + .endm + + .macro ldr4w ptr reg1 reg2 reg3 reg4 abort + ldmia \ptr!, {\reg1, \reg2, \reg3, \reg4} + .endm + + .macro ldr8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort + ldmia \ptr!, {\reg1, \reg2, \reg3, \reg4, \reg5, \reg6, \reg7, \reg8} + .endm + + .macro ldr1b ptr reg cond=al abort + ldr\cond\()b \reg, [\ptr], #1 + .endm + + .macro str1w ptr reg abort +100: strt \reg, [\ptr], #4 + .section __ex_table, "a" + .long 100b, \abort + .previous + .endm + + .macro str8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort + str1w \ptr, \reg1, \abort + str1w \ptr, \reg2, \abort + str1w \ptr, \reg3, \abort + str1w \ptr, \reg4, \abort + str1w \ptr, \reg5, \abort + str1w \ptr, \reg6, \abort + str1w \ptr, \reg7, \abort + str1w \ptr, \reg8, \abort + .endm + + .macro str1b ptr reg cond=al abort +100: str\cond\()bt \reg, [\ptr], #1 + .section __ex_table, "a" + .long 100b, \abort + .previous + .endm + + .macro enter reg1 reg2 + mov r3, #0 + stmdb sp!, {r0, r2, r3, \reg1, \reg2} + .endm + + .macro exit reg1 reg2 + add sp, sp, #8 + ldmfd sp!, {r0, \reg1, \reg2} + .endm + + .text + +ENTRY(__arch_copy_to_user) + +#include "copy_template.S" + + .section .fixup,"ax" + .align 0 + copy_abort_preamble + ldmfd sp!, {r1, r2, r3} + sub r0, r0, r1 + rsb r0, r0, r2 + copy_abort_end + .previous + -- cgit v1.2.3 From d01e8897fcf597f62d84f626fdced8d94c70deaf Mon Sep 17 00:00:00 2001 From: Lennert Buytenhek Date: Tue, 1 Nov 2005 19:53:50 +0000 Subject: [ARM] 3052/1: add ixp2000 microcode loader Patch from Lennert Buytenhek This patch adds a microcode loader for the ixp2000 architecture. The ixp2000 is an xscale-based CPU with a number of additional small CPUs ('microengines') on die that can be programmed to do various things. Depending on the ixp2000 model, there are between 2 and 16 microengines. This code provides an API that allows configuring the microengines, loading code into them, and starting and stopping them and reading out a number of status registers, and is used by the microengine network driver that was recently announced to netdev. Signed-off-by: Lennert Buytenhek Signed-off-by: Deepak Saxena Signed-off-by: Russell King --- arch/arm/mach-ixp2000/Makefile | 2 +- arch/arm/mach-ixp2000/uengine.c | 474 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 475 insertions(+), 1 deletion(-) create mode 100644 arch/arm/mach-ixp2000/uengine.c (limited to 'arch') diff --git a/arch/arm/mach-ixp2000/Makefile b/arch/arm/mach-ixp2000/Makefile index 1e6139d42a9..9621aeb61f4 100644 --- a/arch/arm/mach-ixp2000/Makefile +++ b/arch/arm/mach-ixp2000/Makefile @@ -1,7 +1,7 @@ # # Makefile for the linux kernel. # -obj-y := core.o pci.o +obj-y := core.o pci.o uengine.o obj-m := obj-n := obj- := diff --git a/arch/arm/mach-ixp2000/uengine.c b/arch/arm/mach-ixp2000/uengine.c new file mode 100644 index 00000000000..43e234349d4 --- /dev/null +++ b/arch/arm/mach-ixp2000/uengine.c @@ -0,0 +1,474 @@ +/* + * Generic library functions for the microengines found on the Intel + * IXP2000 series of network processors. + * + * Copyright (C) 2004, 2005 Lennert Buytenhek + * Dedicated to Marija Kulikova. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License as + * published by the Free Software Foundation; either version 2.1 of the + * License, or (at your option) any later version. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define USTORE_ADDRESS 0x000 +#define USTORE_DATA_LOWER 0x004 +#define USTORE_DATA_UPPER 0x008 +#define CTX_ENABLES 0x018 +#define CC_ENABLE 0x01c +#define CSR_CTX_POINTER 0x020 +#define INDIRECT_CTX_STS 0x040 +#define ACTIVE_CTX_STS 0x044 +#define INDIRECT_CTX_SIG_EVENTS 0x048 +#define INDIRECT_CTX_WAKEUP_EVENTS 0x050 +#define NN_PUT 0x080 +#define NN_GET 0x084 +#define TIMESTAMP_LOW 0x0c0 +#define TIMESTAMP_HIGH 0x0c4 +#define T_INDEX_BYTE_INDEX 0x0f4 +#define LOCAL_CSR_STATUS 0x180 + +u32 ixp2000_uengine_mask; + +static void *ixp2000_uengine_csr_area(int uengine) +{ + return ((void *)IXP2000_UENGINE_CSR_VIRT_BASE) + (uengine << 10); +} + +/* + * LOCAL_CSR_STATUS=1 after a read or write to a microengine's CSR + * space means that the microengine we tried to access was also trying + * to access its own CSR space on the same clock cycle as we did. When + * this happens, we lose the arbitration process by default, and the + * read or write we tried to do was not actually performed, so we try + * again until it succeeds. + */ +u32 ixp2000_uengine_csr_read(int uengine, int offset) +{ + void *uebase; + u32 *local_csr_status; + u32 *reg; + u32 value; + + uebase = ixp2000_uengine_csr_area(uengine); + + local_csr_status = (u32 *)(uebase + LOCAL_CSR_STATUS); + reg = (u32 *)(uebase + offset); + do { + value = ixp2000_reg_read(reg); + } while (ixp2000_reg_read(local_csr_status) & 1); + + return value; +} +EXPORT_SYMBOL(ixp2000_uengine_csr_read); + +void ixp2000_uengine_csr_write(int uengine, int offset, u32 value) +{ + void *uebase; + u32 *local_csr_status; + u32 *reg; + + uebase = ixp2000_uengine_csr_area(uengine); + + local_csr_status = (u32 *)(uebase + LOCAL_CSR_STATUS); + reg = (u32 *)(uebase + offset); + do { + ixp2000_reg_write(reg, value); + } while (ixp2000_reg_read(local_csr_status) & 1); +} +EXPORT_SYMBOL(ixp2000_uengine_csr_write); + +void ixp2000_uengine_reset(u32 uengine_mask) +{ + ixp2000_reg_write(IXP2000_RESET1, uengine_mask & ixp2000_uengine_mask); + ixp2000_reg_write(IXP2000_RESET1, 0); +} +EXPORT_SYMBOL(ixp2000_uengine_reset); + +void ixp2000_uengine_set_mode(int uengine, u32 mode) +{ + /* + * CTL_STR_PAR_EN: unconditionally enable parity checking on + * control store. + */ + mode |= 0x10000000; + ixp2000_uengine_csr_write(uengine, CTX_ENABLES, mode); + + /* + * Enable updating of condition codes. + */ + ixp2000_uengine_csr_write(uengine, CC_ENABLE, 0x00002000); + + /* + * Initialise other per-microengine registers. + */ + ixp2000_uengine_csr_write(uengine, NN_PUT, 0x00); + ixp2000_uengine_csr_write(uengine, NN_GET, 0x00); + ixp2000_uengine_csr_write(uengine, T_INDEX_BYTE_INDEX, 0); +} +EXPORT_SYMBOL(ixp2000_uengine_set_mode); + +static int make_even_parity(u32 x) +{ + return hweight32(x) & 1; +} + +static void ustore_write(int uengine, u64 insn) +{ + /* + * Generate even parity for top and bottom 20 bits. + */ + insn |= (u64)make_even_parity((insn >> 20) & 0x000fffff) << 41; + insn |= (u64)make_even_parity(insn & 0x000fffff) << 40; + + /* + * Write to microstore. The second write auto-increments + * the USTORE_ADDRESS index register. + */ + ixp2000_uengine_csr_write(uengine, USTORE_DATA_LOWER, (u32)insn); + ixp2000_uengine_csr_write(uengine, USTORE_DATA_UPPER, (u32)(insn >> 32)); +} + +void ixp2000_uengine_load_microcode(int uengine, u8 *ucode, int insns) +{ + int i; + + /* + * Start writing to microstore at address 0. + */ + ixp2000_uengine_csr_write(uengine, USTORE_ADDRESS, 0x80000000); + for (i = 0; i < insns; i++) { + u64 insn; + + insn = (((u64)ucode[0]) << 32) | + (((u64)ucode[1]) << 24) | + (((u64)ucode[2]) << 16) | + (((u64)ucode[3]) << 8) | + ((u64)ucode[4]); + ucode += 5; + + ustore_write(uengine, insn); + } + + /* + * Pad with a few NOPs at the end (to avoid the microengine + * aborting as it prefetches beyond the last instruction), unless + * we run off the end of the instruction store first, at which + * point the address register will wrap back to zero. + */ + for (i = 0; i < 4; i++) { + u32 addr; + + addr = ixp2000_uengine_csr_read(uengine, USTORE_ADDRESS); + if (addr == 0x80000000) + break; + ustore_write(uengine, 0xf0000c0300ULL); + } + + /* + * End programming. + */ + ixp2000_uengine_csr_write(uengine, USTORE_ADDRESS, 0x00000000); +} +EXPORT_SYMBOL(ixp2000_uengine_load_microcode); + +void ixp2000_uengine_init_context(int uengine, int context, int pc) +{ + /* + * Select the right context for indirect access. + */ + ixp2000_uengine_csr_write(uengine, CSR_CTX_POINTER, context); + + /* + * Initialise signal masks to immediately go to Ready state. + */ + ixp2000_uengine_csr_write(uengine, INDIRECT_CTX_SIG_EVENTS, 1); + ixp2000_uengine_csr_write(uengine, INDIRECT_CTX_WAKEUP_EVENTS, 1); + + /* + * Set program counter. + */ + ixp2000_uengine_csr_write(uengine, INDIRECT_CTX_STS, pc); +} +EXPORT_SYMBOL(ixp2000_uengine_init_context); + +void ixp2000_uengine_start_contexts(int uengine, u8 ctx_mask) +{ + u32 mask; + + /* + * Enable the specified context to go to Executing state. + */ + mask = ixp2000_uengine_csr_read(uengine, CTX_ENABLES); + mask |= ctx_mask << 8; + ixp2000_uengine_csr_write(uengine, CTX_ENABLES, mask); +} +EXPORT_SYMBOL(ixp2000_uengine_start_contexts); + +void ixp2000_uengine_stop_contexts(int uengine, u8 ctx_mask) +{ + u32 mask; + + /* + * Disable the Ready->Executing transition. Note that this + * does not stop the context until it voluntarily yields. + */ + mask = ixp2000_uengine_csr_read(uengine, CTX_ENABLES); + mask &= ~(ctx_mask << 8); + ixp2000_uengine_csr_write(uengine, CTX_ENABLES, mask); +} +EXPORT_SYMBOL(ixp2000_uengine_stop_contexts); + +static int check_ixp_type(struct ixp2000_uengine_code *c) +{ + u32 product_id; + u32 rev; + + product_id = ixp2000_reg_read(IXP2000_PRODUCT_ID); + if (((product_id >> 16) & 0x1f) != 0) + return 0; + + switch ((product_id >> 8) & 0xff) { + case 0: /* IXP2800 */ + if (!(c->cpu_model_bitmask & 4)) + return 0; + break; + + case 1: /* IXP2850 */ + if (!(c->cpu_model_bitmask & 8)) + return 0; + break; + + case 2: /* IXP2400 */ + if (!(c->cpu_model_bitmask & 2)) + return 0; + break; + + default: + return 0; + } + + rev = product_id & 0xff; + if (rev < c->cpu_min_revision || rev > c->cpu_max_revision) + return 0; + + return 1; +} + +static void generate_ucode(u8 *ucode, u32 *gpr_a, u32 *gpr_b) +{ + int offset; + int i; + + offset = 0; + + for (i = 0; i < 128; i++) { + u8 b3; + u8 b2; + u8 b1; + u8 b0; + + b3 = (gpr_a[i] >> 24) & 0xff; + b2 = (gpr_a[i] >> 16) & 0xff; + b1 = (gpr_a[i] >> 8) & 0xff; + b0 = gpr_a[i] & 0xff; + + // immed[@ai, (b1 << 8) | b0] + // 11110000 0000VVVV VVVV11VV VVVVVV00 1IIIIIII + ucode[offset++] = 0xf0; + ucode[offset++] = (b1 >> 4); + ucode[offset++] = (b1 << 4) | 0x0c | (b0 >> 6); + ucode[offset++] = (b0 << 2); + ucode[offset++] = 0x80 | i; + + // immed_w1[@ai, (b3 << 8) | b2] + // 11110100 0100VVVV VVVV11VV VVVVVV00 1IIIIIII + ucode[offset++] = 0xf4; + ucode[offset++] = 0x40 | (b3 >> 4); + ucode[offset++] = (b3 << 4) | 0x0c | (b2 >> 6); + ucode[offset++] = (b2 << 2); + ucode[offset++] = 0x80 | i; + } + + for (i = 0; i < 128; i++) { + u8 b3; + u8 b2; + u8 b1; + u8 b0; + + b3 = (gpr_b[i] >> 24) & 0xff; + b2 = (gpr_b[i] >> 16) & 0xff; + b1 = (gpr_b[i] >> 8) & 0xff; + b0 = gpr_b[i] & 0xff; + + // immed[@bi, (b1 << 8) | b0] + // 11110000 0000VVVV VVVV001I IIIIII11 VVVVVVVV + ucode[offset++] = 0xf0; + ucode[offset++] = (b1 >> 4); + ucode[offset++] = (b1 << 4) | 0x02 | (i >> 6); + ucode[offset++] = (i << 2) | 0x03; + ucode[offset++] = b0; + + // immed_w1[@bi, (b3 << 8) | b2] + // 11110100 0100VVVV VVVV001I IIIIII11 VVVVVVVV + ucode[offset++] = 0xf4; + ucode[offset++] = 0x40 | (b3 >> 4); + ucode[offset++] = (b3 << 4) | 0x02 | (i >> 6); + ucode[offset++] = (i << 2) | 0x03; + ucode[offset++] = b2; + } + + // ctx_arb[kill] + ucode[offset++] = 0xe0; + ucode[offset++] = 0x00; + ucode[offset++] = 0x01; + ucode[offset++] = 0x00; + ucode[offset++] = 0x00; +} + +static int set_initial_registers(int uengine, struct ixp2000_uengine_code *c) +{ + int per_ctx_regs; + u32 *gpr_a; + u32 *gpr_b; + u8 *ucode; + int i; + + gpr_a = kmalloc(128 * sizeof(u32), GFP_KERNEL); + gpr_b = kmalloc(128 * sizeof(u32), GFP_KERNEL); + ucode = kmalloc(513 * 5, GFP_KERNEL); + if (gpr_a == NULL || gpr_b == NULL || ucode == NULL) { + kfree(ucode); + kfree(gpr_b); + kfree(gpr_a); + return 1; + } + + per_ctx_regs = 16; + if (c->uengine_parameters & IXP2000_UENGINE_4_CONTEXTS) + per_ctx_regs = 32; + + memset(gpr_a, 0, sizeof(gpr_a)); + memset(gpr_b, 0, sizeof(gpr_b)); + for (i = 0; i < 256; i++) { + struct ixp2000_reg_value *r = c->initial_reg_values + i; + u32 *bank; + int inc; + int j; + + if (r->reg == -1) + break; + + bank = (r->reg & 0x400) ? gpr_b : gpr_a; + inc = (r->reg & 0x80) ? 128 : per_ctx_regs; + + j = r->reg & 0x7f; + while (j < 128) { + bank[j] = r->value; + j += inc; + } + } + + generate_ucode(ucode, gpr_a, gpr_b); + ixp2000_uengine_load_microcode(uengine, ucode, 513); + ixp2000_uengine_init_context(uengine, 0, 0); + ixp2000_uengine_start_contexts(uengine, 0x01); + for (i = 0; i < 100; i++) { + u32 status; + + status = ixp2000_uengine_csr_read(uengine, ACTIVE_CTX_STS); + if (!(status & 0x80000000)) + break; + } + ixp2000_uengine_stop_contexts(uengine, 0x01); + + kfree(ucode); + kfree(gpr_b); + kfree(gpr_a); + + return !!(i == 100); +} + +int ixp2000_uengine_load(int uengine, struct ixp2000_uengine_code *c) +{ + int ctx; + + if (!check_ixp_type(c)) + return 1; + + if (!(ixp2000_uengine_mask & (1 << uengine))) + return 1; + + ixp2000_uengine_reset(1 << uengine); + ixp2000_uengine_set_mode(uengine, c->uengine_parameters); + if (set_initial_registers(uengine, c)) + return 1; + ixp2000_uengine_load_microcode(uengine, c->insns, c->num_insns); + + for (ctx = 0; ctx < 8; ctx++) + ixp2000_uengine_init_context(uengine, ctx, 0); + + return 0; +} +EXPORT_SYMBOL(ixp2000_uengine_load); + + +static int __init ixp2000_uengine_init(void) +{ + int uengine; + u32 value; + + /* + * Determine number of microengines present. + */ + switch ((ixp2000_reg_read(IXP2000_PRODUCT_ID) >> 8) & 0x1fff) { + case 0: /* IXP2800 */ + case 1: /* IXP2850 */ + ixp2000_uengine_mask = 0x00ff00ff; + break; + + case 2: /* IXP2400 */ + ixp2000_uengine_mask = 0x000f000f; + break; + + default: + printk(KERN_INFO "Detected unknown IXP2000 model (%.8x)\n", + (unsigned int)ixp2000_reg_read(IXP2000_PRODUCT_ID)); + ixp2000_uengine_mask = 0x00000000; + break; + } + + /* + * Reset microengines. + */ + ixp2000_reg_write(IXP2000_RESET1, ixp2000_uengine_mask); + ixp2000_reg_write(IXP2000_RESET1, 0); + + /* + * Synchronise timestamp counters across all microengines. + */ + value = ixp2000_reg_read(IXP2000_MISC_CONTROL); + ixp2000_reg_write(IXP2000_MISC_CONTROL, value & ~0x80); + for (uengine = 0; uengine < 32; uengine++) { + if (ixp2000_uengine_mask & (1 << uengine)) { + ixp2000_uengine_csr_write(uengine, TIMESTAMP_LOW, 0); + ixp2000_uengine_csr_write(uengine, TIMESTAMP_HIGH, 0); + } + } + ixp2000_reg_write(IXP2000_MISC_CONTROL, value | 0x80); + + return 0; +} + +subsys_initcall(ixp2000_uengine_init); -- cgit v1.2.3 From 73ee723e4c6d179c2e9496cc4caf160a18d95603 Mon Sep 17 00:00:00 2001 From: Deepak Saxena Date: Tue, 1 Nov 2005 22:32:12 +0000 Subject: [ARM] 3081/1: Remove GTWX5715 from ixp4xx_defconfig Patch from Deepak Saxena CONFIG_MACH_GTWX5715 hardcodes the machine type in head-xscale.S so we can no longer boot on any other machine types. The proper fix would be to remove the hardcoding, but that machine is an off-the-shelf system and most users won't have access to the bootloader. :( Signed-off-by: Deepak Saxena Signed-off-by: Russell King --- arch/arm/configs/ixp4xx_defconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/configs/ixp4xx_defconfig b/arch/arm/configs/ixp4xx_defconfig index c279e41ed10..f74c926beb4 100644 --- a/arch/arm/configs/ixp4xx_defconfig +++ b/arch/arm/configs/ixp4xx_defconfig @@ -104,7 +104,7 @@ CONFIG_ARCH_IXCDP1100=y CONFIG_ARCH_PRPMC1100=y CONFIG_ARCH_IXDP4XX=y CONFIG_CPU_IXP46X=y -CONFIG_MACH_GTWX5715=y +# CONFIG_MACH_GTWX5715 is not set # # IXP4xx Options -- cgit v1.2.3