From: Krzysztof Halasa Date: Tue, 1 Jan 2008 20:55:23 +0000 (+0100) Subject: [ARM] 4713/3: Adds drivers for IXP4xx QMgr and NPE features X-Git-Tag: v2.6.25-rc1~1055^2^2~7 X-Git-Url: http://pilppa.com/gitweb/?a=commitdiff_plain;h=82a96f5790ac93a406be72ed8f308dd29ad7e6af;p=linux-2.6-omap-h63xx.git [ARM] 4713/3: Adds drivers for IXP4xx QMgr and NPE features This patch adds drivers for IXP4xx hardware Queue Manager and for Network Processor Engines. Requires patch #4712 (reading/writing CPU feature (aka fuse) bits). Posted to linux-arm-kernel on 2 Dec 2007 and revised. Signed-off-by: Krzysztof Halasa Signed-off-by: Russell King --- diff --git a/arch/arm/mach-ixp4xx/Kconfig b/arch/arm/mach-ixp4xx/Kconfig index 61b2dfcb89d..e774447c059 100644 --- a/arch/arm/mach-ixp4xx/Kconfig +++ b/arch/arm/mach-ixp4xx/Kconfig @@ -189,6 +189,20 @@ config IXP4XX_INDIRECT_PCI need to use the indirect method instead. If you don't know what you need, leave this option unselected. +config IXP4XX_QMGR + tristate "IXP4xx Queue Manager support" + help + This driver supports IXP4xx built-in hardware queue manager + and is automatically selected by Ethernet and HSS drivers. + +config IXP4XX_NPE + tristate "IXP4xx Network Processor Engine support" + select HOTPLUG + select FW_LOADER + help + This driver supports IXP4xx built-in network coprocessors + and is automatically selected by Ethernet and HSS drivers. + endmenu endif diff --git a/arch/arm/mach-ixp4xx/Makefile b/arch/arm/mach-ixp4xx/Makefile index 77e00ade558..4bb97e13f95 100644 --- a/arch/arm/mach-ixp4xx/Makefile +++ b/arch/arm/mach-ixp4xx/Makefile @@ -30,3 +30,5 @@ obj-$(CONFIG_MACH_GATEWAY7001) += gateway7001-setup.o obj-$(CONFIG_MACH_WG302V2) += wg302v2-setup.o obj-$(CONFIG_PCI) += $(obj-pci-$(CONFIG_PCI)) common-pci.o +obj-$(CONFIG_IXP4XX_QMGR) += ixp4xx_qmgr.o +obj-$(CONFIG_IXP4XX_NPE) += ixp4xx_npe.o diff --git a/arch/arm/mach-ixp4xx/ixp4xx_npe.c b/arch/arm/mach-ixp4xx/ixp4xx_npe.c new file mode 100644 index 00000000000..83c137ec582 --- /dev/null +++ b/arch/arm/mach-ixp4xx/ixp4xx_npe.c @@ -0,0 +1,741 @@ +/* + * Intel IXP4xx Network Processor Engine driver for Linux + * + * Copyright (C) 2007 Krzysztof Halasa + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2 of the GNU General Public License + * as published by the Free Software Foundation. + * + * The code is based on publicly available information: + * - Intel IXP4xx Developer's Manual and other e-papers + * - Intel IXP400 Access Library Software (BSD license) + * - previous works by Christian Hohnstaedt + * Thanks, Christian. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#define DEBUG_MSG 0 +#define DEBUG_FW 0 + +#define NPE_COUNT 3 +#define MAX_RETRIES 1000 /* microseconds */ +#define NPE_42X_DATA_SIZE 0x800 /* in dwords */ +#define NPE_46X_DATA_SIZE 0x1000 +#define NPE_A_42X_INSTR_SIZE 0x1000 +#define NPE_B_AND_C_42X_INSTR_SIZE 0x800 +#define NPE_46X_INSTR_SIZE 0x1000 +#define REGS_SIZE 0x1000 + +#define NPE_PHYS_REG 32 + +#define FW_MAGIC 0xFEEDF00D +#define FW_BLOCK_TYPE_INSTR 0x0 +#define FW_BLOCK_TYPE_DATA 0x1 +#define FW_BLOCK_TYPE_EOF 0xF + +/* NPE exec status (read) and command (write) */ +#define CMD_NPE_STEP 0x01 +#define CMD_NPE_START 0x02 +#define CMD_NPE_STOP 0x03 +#define CMD_NPE_CLR_PIPE 0x04 +#define CMD_CLR_PROFILE_CNT 0x0C +#define CMD_RD_INS_MEM 0x10 /* instruction memory */ +#define CMD_WR_INS_MEM 0x11 +#define CMD_RD_DATA_MEM 0x12 /* data memory */ +#define CMD_WR_DATA_MEM 0x13 +#define CMD_RD_ECS_REG 0x14 /* exec access register */ +#define CMD_WR_ECS_REG 0x15 + +#define STAT_RUN 0x80000000 +#define STAT_STOP 0x40000000 +#define STAT_CLEAR 0x20000000 +#define STAT_ECS_K 0x00800000 /* pipeline clean */ + +#define NPE_STEVT 0x1B +#define NPE_STARTPC 0x1C +#define NPE_REGMAP 0x1E +#define NPE_CINDEX 0x1F + +#define INSTR_WR_REG_SHORT 0x0000C000 +#define INSTR_WR_REG_BYTE 0x00004000 +#define INSTR_RD_FIFO 0x0F888220 +#define INSTR_RESET_MBOX 0x0FAC8210 + +#define ECS_BG_CTXT_REG_0 0x00 /* Background Executing Context */ +#define ECS_BG_CTXT_REG_1 0x01 /* Stack level */ +#define ECS_BG_CTXT_REG_2 0x02 +#define ECS_PRI_1_CTXT_REG_0 0x04 /* Priority 1 Executing Context */ +#define ECS_PRI_1_CTXT_REG_1 0x05 /* Stack level */ +#define ECS_PRI_1_CTXT_REG_2 0x06 +#define ECS_PRI_2_CTXT_REG_0 0x08 /* Priority 2 Executing Context */ +#define ECS_PRI_2_CTXT_REG_1 0x09 /* Stack level */ +#define ECS_PRI_2_CTXT_REG_2 0x0A +#define ECS_DBG_CTXT_REG_0 0x0C /* Debug Executing Context */ +#define ECS_DBG_CTXT_REG_1 0x0D /* Stack level */ +#define ECS_DBG_CTXT_REG_2 0x0E +#define ECS_INSTRUCT_REG 0x11 /* NPE Instruction Register */ + +#define ECS_REG_0_ACTIVE 0x80000000 /* all levels */ +#define ECS_REG_0_NEXTPC_MASK 0x1FFF0000 /* BG/PRI1/PRI2 levels */ +#define ECS_REG_0_LDUR_BITS 8 +#define ECS_REG_0_LDUR_MASK 0x00000700 /* all levels */ +#define ECS_REG_1_CCTXT_BITS 16 +#define ECS_REG_1_CCTXT_MASK 0x000F0000 /* all levels */ +#define ECS_REG_1_SELCTXT_BITS 0 +#define ECS_REG_1_SELCTXT_MASK 0x0000000F /* all levels */ +#define ECS_DBG_REG_2_IF 0x00100000 /* debug level */ +#define ECS_DBG_REG_2_IE 0x00080000 /* debug level */ + +/* NPE watchpoint_fifo register bit */ +#define WFIFO_VALID 0x80000000 + +/* NPE messaging_status register bit definitions */ +#define MSGSTAT_OFNE 0x00010000 /* OutFifoNotEmpty */ +#define MSGSTAT_IFNF 0x00020000 /* InFifoNotFull */ +#define MSGSTAT_OFNF 0x00040000 /* OutFifoNotFull */ +#define MSGSTAT_IFNE 0x00080000 /* InFifoNotEmpty */ +#define MSGSTAT_MBINT 0x00100000 /* Mailbox interrupt */ +#define MSGSTAT_IFINT 0x00200000 /* InFifo interrupt */ +#define MSGSTAT_OFINT 0x00400000 /* OutFifo interrupt */ +#define MSGSTAT_WFINT 0x00800000 /* WatchFifo interrupt */ + +/* NPE messaging_control register bit definitions */ +#define MSGCTL_OUT_FIFO 0x00010000 /* enable output FIFO */ +#define MSGCTL_IN_FIFO 0x00020000 /* enable input FIFO */ +#define MSGCTL_OUT_FIFO_WRITE 0x01000000 /* enable FIFO + WRITE */ +#define MSGCTL_IN_FIFO_WRITE 0x02000000 + +/* NPE mailbox_status value for reset */ +#define RESET_MBOX_STAT 0x0000F0F0 + +const char *npe_names[] = { "NPE-A", "NPE-B", "NPE-C" }; + +#define print_npe(pri, npe, fmt, ...) \ + printk(pri "%s: " fmt, npe_name(npe), ## __VA_ARGS__) + +#if DEBUG_MSG +#define debug_msg(npe, fmt, ...) \ + print_npe(KERN_DEBUG, npe, fmt, ## __VA_ARGS__) +#else +#define debug_msg(npe, fmt, ...) +#endif + +static struct { + u32 reg, val; +} ecs_reset[] = { + { ECS_BG_CTXT_REG_0, 0xA0000000 }, + { ECS_BG_CTXT_REG_1, 0x01000000 }, + { ECS_BG_CTXT_REG_2, 0x00008000 }, + { ECS_PRI_1_CTXT_REG_0, 0x20000080 }, + { ECS_PRI_1_CTXT_REG_1, 0x01000000 }, + { ECS_PRI_1_CTXT_REG_2, 0x00008000 }, + { ECS_PRI_2_CTXT_REG_0, 0x20000080 }, + { ECS_PRI_2_CTXT_REG_1, 0x01000000 }, + { ECS_PRI_2_CTXT_REG_2, 0x00008000 }, + { ECS_DBG_CTXT_REG_0, 0x20000000 }, + { ECS_DBG_CTXT_REG_1, 0x00000000 }, + { ECS_DBG_CTXT_REG_2, 0x001E0000 }, + { ECS_INSTRUCT_REG, 0x1003C00F }, +}; + +static struct npe npe_tab[NPE_COUNT] = { + { + .id = 0, + .regs = (struct npe_regs __iomem *)IXP4XX_NPEA_BASE_VIRT, + .regs_phys = IXP4XX_NPEA_BASE_PHYS, + }, { + .id = 1, + .regs = (struct npe_regs __iomem *)IXP4XX_NPEB_BASE_VIRT, + .regs_phys = IXP4XX_NPEB_BASE_PHYS, + }, { + .id = 2, + .regs = (struct npe_regs __iomem *)IXP4XX_NPEC_BASE_VIRT, + .regs_phys = IXP4XX_NPEC_BASE_PHYS, + } +}; + +int npe_running(struct npe *npe) +{ + return (__raw_readl(&npe->regs->exec_status_cmd) & STAT_RUN) != 0; +} + +static void npe_cmd_write(struct npe *npe, u32 addr, int cmd, u32 data) +{ + __raw_writel(data, &npe->regs->exec_data); + __raw_writel(addr, &npe->regs->exec_addr); + __raw_writel(cmd, &npe->regs->exec_status_cmd); +} + +static u32 npe_cmd_read(struct npe *npe, u32 addr, int cmd) +{ + __raw_writel(addr, &npe->regs->exec_addr); + __raw_writel(cmd, &npe->regs->exec_status_cmd); + /* Iintroduce extra read cycles after issuing read command to NPE + so that we read the register after the NPE has updated it. + This is to overcome race condition between XScale and NPE */ + __raw_readl(&npe->regs->exec_data); + __raw_readl(&npe->regs->exec_data); + return __raw_readl(&npe->regs->exec_data); +} + +static void npe_clear_active(struct npe *npe, u32 reg) +{ + u32 val = npe_cmd_read(npe, reg, CMD_RD_ECS_REG); + npe_cmd_write(npe, reg, CMD_WR_ECS_REG, val & ~ECS_REG_0_ACTIVE); +} + +static void npe_start(struct npe *npe) +{ + /* ensure only Background Context Stack Level is active */ + npe_clear_active(npe, ECS_PRI_1_CTXT_REG_0); + npe_clear_active(npe, ECS_PRI_2_CTXT_REG_0); + npe_clear_active(npe, ECS_DBG_CTXT_REG_0); + + __raw_writel(CMD_NPE_CLR_PIPE, &npe->regs->exec_status_cmd); + __raw_writel(CMD_NPE_START, &npe->regs->exec_status_cmd); +} + +static void npe_stop(struct npe *npe) +{ + __raw_writel(CMD_NPE_STOP, &npe->regs->exec_status_cmd); + __raw_writel(CMD_NPE_CLR_PIPE, &npe->regs->exec_status_cmd); /*FIXME?*/ +} + +static int __must_check npe_debug_instr(struct npe *npe, u32 instr, u32 ctx, + u32 ldur) +{ + u32 wc; + int i; + + /* set the Active bit, and the LDUR, in the debug level */ + npe_cmd_write(npe, ECS_DBG_CTXT_REG_0, CMD_WR_ECS_REG, + ECS_REG_0_ACTIVE | (ldur << ECS_REG_0_LDUR_BITS)); + + /* set CCTXT at ECS DEBUG L3 to specify in which context to execute + the instruction, and set SELCTXT at ECS DEBUG Level to specify + which context store to access. + Debug ECS Level Reg 1 has form 0x000n000n, where n = context number + */ + npe_cmd_write(npe, ECS_DBG_CTXT_REG_1, CMD_WR_ECS_REG, + (ctx << ECS_REG_1_CCTXT_BITS) | + (ctx << ECS_REG_1_SELCTXT_BITS)); + + /* clear the pipeline */ + __raw_writel(CMD_NPE_CLR_PIPE, &npe->regs->exec_status_cmd); + + /* load NPE instruction into the instruction register */ + npe_cmd_write(npe, ECS_INSTRUCT_REG, CMD_WR_ECS_REG, instr); + + /* we need this value later to wait for completion of NPE execution + step */ + wc = __raw_readl(&npe->regs->watch_count); + + /* issue a Step One command via the Execution Control register */ + __raw_writel(CMD_NPE_STEP, &npe->regs->exec_status_cmd); + + /* Watch Count register increments when NPE completes an instruction */ + for (i = 0; i < MAX_RETRIES; i++) { + if (wc != __raw_readl(&npe->regs->watch_count)) + return 0; + udelay(1); + } + + print_npe(KERN_ERR, npe, "reset: npe_debug_instr(): timeout\n"); + return -ETIMEDOUT; +} + +static int __must_check npe_logical_reg_write8(struct npe *npe, u32 addr, + u8 val, u32 ctx) +{ + /* here we build the NPE assembler instruction: mov8 d0, #0 */ + u32 instr = INSTR_WR_REG_BYTE | /* OpCode */ + addr << 9 | /* base Operand */ + (val & 0x1F) << 4 | /* lower 5 bits to immediate data */ + (val & ~0x1F) << (18 - 5);/* higher 3 bits to CoProc instr. */ + return npe_debug_instr(npe, instr, ctx, 1); /* execute it */ +} + +static int __must_check npe_logical_reg_write16(struct npe *npe, u32 addr, + u16 val, u32 ctx) +{ + /* here we build the NPE assembler instruction: mov16 d0, #0 */ + u32 instr = INSTR_WR_REG_SHORT | /* OpCode */ + addr << 9 | /* base Operand */ + (val & 0x1F) << 4 | /* lower 5 bits to immediate data */ + (val & ~0x1F) << (18 - 5);/* higher 11 bits to CoProc instr. */ + return npe_debug_instr(npe, instr, ctx, 1); /* execute it */ +} + +static int __must_check npe_logical_reg_write32(struct npe *npe, u32 addr, + u32 val, u32 ctx) +{ + /* write in 16 bit steps first the high and then the low value */ + if (npe_logical_reg_write16(npe, addr, val >> 16, ctx)) + return -ETIMEDOUT; + return npe_logical_reg_write16(npe, addr + 2, val & 0xFFFF, ctx); +} + +static int npe_reset(struct npe *npe) +{ + u32 val, ctl, exec_count, ctx_reg2; + int i; + + ctl = (__raw_readl(&npe->regs->messaging_control) | 0x3F000000) & + 0x3F3FFFFF; + + /* disable parity interrupt */ + __raw_writel(ctl & 0x3F00FFFF, &npe->regs->messaging_control); + + /* pre exec - debug instruction */ + /* turn off the halt bit by clearing Execution Count register. */ + exec_count = __raw_readl(&npe->regs->exec_count); + __raw_writel(0, &npe->regs->exec_count); + /* ensure that IF and IE are on (temporarily), so that we don't end up + stepping forever */ + ctx_reg2 = npe_cmd_read(npe, ECS_DBG_CTXT_REG_2, CMD_RD_ECS_REG); + npe_cmd_write(npe, ECS_DBG_CTXT_REG_2, CMD_WR_ECS_REG, ctx_reg2 | + ECS_DBG_REG_2_IF | ECS_DBG_REG_2_IE); + + /* clear the FIFOs */ + while (__raw_readl(&npe->regs->watchpoint_fifo) & WFIFO_VALID) + ; + while (__raw_readl(&npe->regs->messaging_status) & MSGSTAT_OFNE) + /* read from the outFIFO until empty */ + print_npe(KERN_DEBUG, npe, "npe_reset: read FIFO = 0x%X\n", + __raw_readl(&npe->regs->in_out_fifo)); + + while (__raw_readl(&npe->regs->messaging_status) & MSGSTAT_IFNE) + /* step execution of the NPE intruction to read inFIFO using + the Debug Executing Context stack */ + if (npe_debug_instr(npe, INSTR_RD_FIFO, 0, 0)) + return -ETIMEDOUT; + + /* reset the mailbox reg from the XScale side */ + __raw_writel(RESET_MBOX_STAT, &npe->regs->mailbox_status); + /* from NPE side */ + if (npe_debug_instr(npe, INSTR_RESET_MBOX, 0, 0)) + return -ETIMEDOUT; + + /* Reset the physical registers in the NPE register file */ + for (val = 0; val < NPE_PHYS_REG; val++) { + if (npe_logical_reg_write16(npe, NPE_REGMAP, val >> 1, 0)) + return -ETIMEDOUT; + /* address is either 0 or 4 */ + if (npe_logical_reg_write32(npe, (val & 1) * 4, 0, 0)) + return -ETIMEDOUT; + } + + /* Reset the context store = each context's Context Store registers */ + + /* Context 0 has no STARTPC. Instead, this value is used to set NextPC + for Background ECS, to set where NPE starts executing code */ + val = npe_cmd_read(npe, ECS_BG_CTXT_REG_0, CMD_RD_ECS_REG); + val &= ~ECS_REG_0_NEXTPC_MASK; + val |= (0 /* NextPC */ << 16) & ECS_REG_0_NEXTPC_MASK; + npe_cmd_write(npe, ECS_BG_CTXT_REG_0, CMD_WR_ECS_REG, val); + + for (i = 0; i < 16; i++) { + if (i) { /* Context 0 has no STEVT nor STARTPC */ + /* STEVT = off, 0x80 */ + if (npe_logical_reg_write8(npe, NPE_STEVT, 0x80, i)) + return -ETIMEDOUT; + if (npe_logical_reg_write16(npe, NPE_STARTPC, 0, i)) + return -ETIMEDOUT; + } + /* REGMAP = d0->p0, d8->p2, d16->p4 */ + if (npe_logical_reg_write16(npe, NPE_REGMAP, 0x820, i)) + return -ETIMEDOUT; + if (npe_logical_reg_write8(npe, NPE_CINDEX, 0, i)) + return -ETIMEDOUT; + } + + /* post exec */ + /* clear active bit in debug level */ + npe_cmd_write(npe, ECS_DBG_CTXT_REG_0, CMD_WR_ECS_REG, 0); + /* clear the pipeline */ + __raw_writel(CMD_NPE_CLR_PIPE, &npe->regs->exec_status_cmd); + /* restore previous values */ + __raw_writel(exec_count, &npe->regs->exec_count); + npe_cmd_write(npe, ECS_DBG_CTXT_REG_2, CMD_WR_ECS_REG, ctx_reg2); + + /* write reset values to Execution Context Stack registers */ + for (val = 0; val < ARRAY_SIZE(ecs_reset); val++) + npe_cmd_write(npe, ecs_reset[val].reg, CMD_WR_ECS_REG, + ecs_reset[val].val); + + /* clear the profile counter */ + __raw_writel(CMD_CLR_PROFILE_CNT, &npe->regs->exec_status_cmd); + + __raw_writel(0, &npe->regs->exec_count); + __raw_writel(0, &npe->regs->action_points[0]); + __raw_writel(0, &npe->regs->action_points[1]); + __raw_writel(0, &npe->regs->action_points[2]); + __raw_writel(0, &npe->regs->action_points[3]); + __raw_writel(0, &npe->regs->watch_count); + + val = ixp4xx_read_feature_bits(); + /* reset the NPE */ + ixp4xx_write_feature_bits(val & + ~(IXP4XX_FEATURE_RESET_NPEA << npe->id)); + for (i = 0; i < MAX_RETRIES; i++) { + if (!(ixp4xx_read_feature_bits() & + (IXP4XX_FEATURE_RESET_NPEA << npe->id))) + break; /* reset completed */ + udelay(1); + } + if (i == MAX_RETRIES) + return -ETIMEDOUT; + + /* deassert reset */ + ixp4xx_write_feature_bits(val | + (IXP4XX_FEATURE_RESET_NPEA << npe->id)); + for (i = 0; i < MAX_RETRIES; i++) { + if (ixp4xx_read_feature_bits() & + (IXP4XX_FEATURE_RESET_NPEA << npe->id)) + break; /* NPE is back alive */ + udelay(1); + } + if (i == MAX_RETRIES) + return -ETIMEDOUT; + + npe_stop(npe); + + /* restore NPE configuration bus Control Register - parity settings */ + __raw_writel(ctl, &npe->regs->messaging_control); + return 0; +} + + +int npe_send_message(struct npe *npe, const void *msg, const char *what) +{ + const u32 *send = msg; + int cycles = 0; + + debug_msg(npe, "Trying to send message %s [%08X:%08X]\n", + what, send[0], send[1]); + + if (__raw_readl(&npe->regs->messaging_status) & MSGSTAT_IFNE) { + debug_msg(npe, "NPE input FIFO not empty\n"); + return -EIO; + } + + __raw_writel(send[0], &npe->regs->in_out_fifo); + + if (!(__raw_readl(&npe->regs->messaging_status) & MSGSTAT_IFNF)) { + debug_msg(npe, "NPE input FIFO full\n"); + return -EIO; + } + + __raw_writel(send[1], &npe->regs->in_out_fifo); + + while ((cycles < MAX_RETRIES) && + (__raw_readl(&npe->regs->messaging_status) & MSGSTAT_IFNE)) { + udelay(1); + cycles++; + } + + if (cycles == MAX_RETRIES) { + debug_msg(npe, "Timeout sending message\n"); + return -ETIMEDOUT; + } + + debug_msg(npe, "Sending a message took %i cycles\n", cycles); + return 0; +} + +int npe_recv_message(struct npe *npe, void *msg, const char *what) +{ + u32 *recv = msg; + int cycles = 0, cnt = 0; + + debug_msg(npe, "Trying to receive message %s\n", what); + + while (cycles < MAX_RETRIES) { + if (__raw_readl(&npe->regs->messaging_status) & MSGSTAT_OFNE) { + recv[cnt++] = __raw_readl(&npe->regs->in_out_fifo); + if (cnt == 2) + break; + } else { + udelay(1); + cycles++; + } + } + + switch(cnt) { + case 1: + debug_msg(npe, "Received [%08X]\n", recv[0]); + break; + case 2: + debug_msg(npe, "Received [%08X:%08X]\n", recv[0], recv[1]); + break; + } + + if (cycles == MAX_RETRIES) { + debug_msg(npe, "Timeout waiting for message\n"); + return -ETIMEDOUT; + } + + debug_msg(npe, "Receiving a message took %i cycles\n", cycles); + return 0; +} + +int npe_send_recv_message(struct npe *npe, void *msg, const char *what) +{ + int result; + u32 *send = msg, recv[2]; + + if ((result = npe_send_message(npe, msg, what)) != 0) + return result; + if ((result = npe_recv_message(npe, recv, what)) != 0) + return result; + + if ((recv[0] != send[0]) || (recv[1] != send[1])) { + debug_msg(npe, "Message %s: unexpected message received\n", + what); + return -EIO; + } + return 0; +} + + +int npe_load_firmware(struct npe *npe, const char *name, struct device *dev) +{ + const struct firmware *fw_entry; + + struct dl_block { + u32 type; + u32 offset; + } *blk; + + struct dl_image { + u32 magic; + u32 id; + u32 size; + union { + u32 data[0]; + struct dl_block blocks[0]; + }; + } *image; + + struct dl_codeblock { + u32 npe_addr; + u32 size; + u32 data[0]; + } *cb; + + int i, j, err, data_size, instr_size, blocks, table_end; + u32 cmd; + + if ((err = request_firmware(&fw_entry, name, dev)) != 0) + return err; + + err = -EINVAL; + if (fw_entry->size < sizeof(struct dl_image)) { + print_npe(KERN_ERR, npe, "incomplete firmware file\n"); + goto err; + } + image = (struct dl_image*)fw_entry->data; + +#if DEBUG_FW + print_npe(KERN_DEBUG, npe, "firmware: %08X %08X %08X (0x%X bytes)\n", + image->magic, image->id, image->size, image->size * 4); +#endif + + if (image->magic == swab32(FW_MAGIC)) { /* swapped file */ + image->id = swab32(image->id); + image->size = swab32(image->size); + } else if (image->magic != FW_MAGIC) { + print_npe(KERN_ERR, npe, "bad firmware file magic: 0x%X\n", + image->magic); + goto err; + } + if ((image->size * 4 + sizeof(struct dl_image)) != fw_entry->size) { + print_npe(KERN_ERR, npe, + "inconsistent size of firmware file\n"); + goto err; + } + if (((image->id >> 24) & 0xF /* NPE ID */) != npe->id) { + print_npe(KERN_ERR, npe, "firmware file NPE ID mismatch\n"); + goto err; + } + if (image->magic == swab32(FW_MAGIC)) + for (i = 0; i < image->size; i++) + image->data[i] = swab32(image->data[i]); + + if (!cpu_is_ixp46x() && ((image->id >> 28) & 0xF /* device ID */)) { + print_npe(KERN_INFO, npe, "IXP46x firmware ignored on " + "IXP42x\n"); + goto err; + } + + if (npe_running(npe)) { + print_npe(KERN_INFO, npe, "unable to load firmware, NPE is " + "already running\n"); + err = -EBUSY; + goto err; + } +#if 0 + npe_stop(npe); + npe_reset(npe); +#endif + + print_npe(KERN_INFO, npe, "firmware functionality 0x%X, " + "revision 0x%X:%X\n", (image->id >> 16) & 0xFF, + (image->id >> 8) & 0xFF, image->id & 0xFF); + + if (!cpu_is_ixp46x()) { + if (!npe->id) + instr_size = NPE_A_42X_INSTR_SIZE; + else + instr_size = NPE_B_AND_C_42X_INSTR_SIZE; + data_size = NPE_42X_DATA_SIZE; + } else { + instr_size = NPE_46X_INSTR_SIZE; + data_size = NPE_46X_DATA_SIZE; + } + + for (blocks = 0; blocks * sizeof(struct dl_block) / 4 < image->size; + blocks++) + if (image->blocks[blocks].type == FW_BLOCK_TYPE_EOF) + break; + if (blocks * sizeof(struct dl_block) / 4 >= image->size) { + print_npe(KERN_INFO, npe, "firmware EOF block marker not " + "found\n"); + goto err; + } + +#if DEBUG_FW + print_npe(KERN_DEBUG, npe, "%i firmware blocks found\n", blocks); +#endif + + table_end = blocks * sizeof(struct dl_block) / 4 + 1 /* EOF marker */; + for (i = 0, blk = image->blocks; i < blocks; i++, blk++) { + if (blk->offset > image->size - sizeof(struct dl_codeblock) / 4 + || blk->offset < table_end) { + print_npe(KERN_INFO, npe, "invalid offset 0x%X of " + "firmware block #%i\n", blk->offset, i); + goto err; + } + + cb = (struct dl_codeblock*)&image->data[blk->offset]; + if (blk->type == FW_BLOCK_TYPE_INSTR) { + if (cb->npe_addr + cb->size > instr_size) + goto too_big; + cmd = CMD_WR_INS_MEM; + } else if (blk->type == FW_BLOCK_TYPE_DATA) { + if (cb->npe_addr + cb->size > data_size) + goto too_big; + cmd = CMD_WR_DATA_MEM; + } else { + print_npe(KERN_INFO, npe, "invalid firmware block #%i " + "type 0x%X\n", i, blk->type); + goto err; + } + if (blk->offset + sizeof(*cb) / 4 + cb->size > image->size) { + print_npe(KERN_INFO, npe, "firmware block #%i doesn't " + "fit in firmware image: type %c, start 0x%X," + " length 0x%X\n", i, + blk->type == FW_BLOCK_TYPE_INSTR ? 'I' : 'D', + cb->npe_addr, cb->size); + goto err; + } + + for (j = 0; j < cb->size; j++) + npe_cmd_write(npe, cb->npe_addr + j, cmd, cb->data[j]); + } + + npe_start(npe); + if (!npe_running(npe)) + print_npe(KERN_ERR, npe, "unable to start\n"); + release_firmware(fw_entry); + return 0; + +too_big: + print_npe(KERN_INFO, npe, "firmware block #%i doesn't fit in NPE " + "memory: type %c, start 0x%X, length 0x%X\n", i, + blk->type == FW_BLOCK_TYPE_INSTR ? 'I' : 'D', + cb->npe_addr, cb->size); +err: + release_firmware(fw_entry); + return err; +} + + +struct npe *npe_request(int id) +{ + if (id < NPE_COUNT) + if (npe_tab[id].valid) + if (try_module_get(THIS_MODULE)) + return &npe_tab[id]; + return NULL; +} + +void npe_release(struct npe *npe) +{ + module_put(THIS_MODULE); +} + + +static int __init npe_init_module(void) +{ + + int i, found = 0; + + for (i = 0; i < NPE_COUNT; i++) { + struct npe *npe = &npe_tab[i]; + if (!(ixp4xx_read_feature_bits() & + (IXP4XX_FEATURE_RESET_NPEA << i))) + continue; /* NPE already disabled or not present */ + if (!(npe->mem_res = request_mem_region(npe->regs_phys, + REGS_SIZE, + npe_name(npe)))) { + print_npe(KERN_ERR, npe, + "failed to request memory region\n"); + continue; + } + + if (npe_reset(npe)) + continue; + npe->valid = 1; + found++; + } + + if (!found) + return -ENOSYS; + return 0; +} + +static void __exit npe_cleanup_module(void) +{ + int i; + + for (i = 0; i < NPE_COUNT; i++) + if (npe_tab[i].mem_res) { + npe_reset(&npe_tab[i]); + release_resource(npe_tab[i].mem_res); + } +} + +module_init(npe_init_module); +module_exit(npe_cleanup_module); + +MODULE_AUTHOR("Krzysztof Halasa"); +MODULE_LICENSE("GPL v2"); + +EXPORT_SYMBOL(npe_names); +EXPORT_SYMBOL(npe_running); +EXPORT_SYMBOL(npe_request); +EXPORT_SYMBOL(npe_release); +EXPORT_SYMBOL(npe_load_firmware); +EXPORT_SYMBOL(npe_send_message); +EXPORT_SYMBOL(npe_recv_message); +EXPORT_SYMBOL(npe_send_recv_message); diff --git a/arch/arm/mach-ixp4xx/ixp4xx_qmgr.c b/arch/arm/mach-ixp4xx/ixp4xx_qmgr.c new file mode 100644 index 00000000000..e8330132530 --- /dev/null +++ b/arch/arm/mach-ixp4xx/ixp4xx_qmgr.c @@ -0,0 +1,274 @@ +/* + * Intel IXP4xx Queue Manager driver for Linux + * + * Copyright (C) 2007 Krzysztof Halasa + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2 of the GNU General Public License + * as published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include + +#define DEBUG 0 + +struct qmgr_regs __iomem *qmgr_regs; +static struct resource *mem_res; +static spinlock_t qmgr_lock; +static u32 used_sram_bitmap[4]; /* 128 16-dword pages */ +static void (*irq_handlers[HALF_QUEUES])(void *pdev); +static void *irq_pdevs[HALF_QUEUES]; + +void qmgr_set_irq(unsigned int queue, int src, + void (*handler)(void *pdev), void *pdev) +{ + u32 __iomem *reg = &qmgr_regs->irqsrc[queue / 8]; /* 8 queues / u32 */ + int bit = (queue % 8) * 4; /* 3 bits + 1 reserved bit per queue */ + unsigned long flags; + + src &= 7; + spin_lock_irqsave(&qmgr_lock, flags); + __raw_writel((__raw_readl(reg) & ~(7 << bit)) | (src << bit), reg); + irq_handlers[queue] = handler; + irq_pdevs[queue] = pdev; + spin_unlock_irqrestore(&qmgr_lock, flags); +} + + +static irqreturn_t qmgr_irq1(int irq, void *pdev) +{ + int i; + u32 val = __raw_readl(&qmgr_regs->irqstat[0]); + __raw_writel(val, &qmgr_regs->irqstat[0]); /* ACK */ + + for (i = 0; i < HALF_QUEUES; i++) + if (val & (1 << i)) + irq_handlers[i](irq_pdevs[i]); + + return val ? IRQ_HANDLED : 0; +} + + +void qmgr_enable_irq(unsigned int queue) +{ + unsigned long flags; + + spin_lock_irqsave(&qmgr_lock, flags); + __raw_writel(__raw_readl(&qmgr_regs->irqen[0]) | (1 << queue), + &qmgr_regs->irqen[0]); + spin_unlock_irqrestore(&qmgr_lock, flags); +} + +void qmgr_disable_irq(unsigned int queue) +{ + unsigned long flags; + + spin_lock_irqsave(&qmgr_lock, flags); + __raw_writel(__raw_readl(&qmgr_regs->irqen[0]) & ~(1 << queue), + &qmgr_regs->irqen[0]); + spin_unlock_irqrestore(&qmgr_lock, flags); +} + +static inline void shift_mask(u32 *mask) +{ + mask[3] = mask[3] << 1 | mask[2] >> 31; + mask[2] = mask[2] << 1 | mask[1] >> 31; + mask[1] = mask[1] << 1 | mask[0] >> 31; + mask[0] <<= 1; +} + +int qmgr_request_queue(unsigned int queue, unsigned int len /* dwords */, + unsigned int nearly_empty_watermark, + unsigned int nearly_full_watermark) +{ + u32 cfg, addr = 0, mask[4]; /* in 16-dwords */ + int err; + + if (queue >= HALF_QUEUES) + return -ERANGE; + + if ((nearly_empty_watermark | nearly_full_watermark) & ~7) + return -EINVAL; + + switch (len) { + case 16: + cfg = 0 << 24; + mask[0] = 0x1; + break; + case 32: + cfg = 1 << 24; + mask[0] = 0x3; + break; + case 64: + cfg = 2 << 24; + mask[0] = 0xF; + break; + case 128: + cfg = 3 << 24; + mask[0] = 0xFF; + break; + default: + return -EINVAL; + } + + cfg |= nearly_empty_watermark << 26; + cfg |= nearly_full_watermark << 29; + len /= 16; /* in 16-dwords: 1, 2, 4 or 8 */ + mask[1] = mask[2] = mask[3] = 0; + + if (!try_module_get(THIS_MODULE)) + return -ENODEV; + + spin_lock_irq(&qmgr_lock); + if (__raw_readl(&qmgr_regs->sram[queue])) { + err = -EBUSY; + goto err; + } + + while (1) { + if (!(used_sram_bitmap[0] & mask[0]) && + !(used_sram_bitmap[1] & mask[1]) && + !(used_sram_bitmap[2] & mask[2]) && + !(used_sram_bitmap[3] & mask[3])) + break; /* found free space */ + + addr++; + shift_mask(mask); + if (addr + len > ARRAY_SIZE(qmgr_regs->sram)) { + printk(KERN_ERR "qmgr: no free SRAM space for" + " queue %i\n", queue); + err = -ENOMEM; + goto err; + } + } + + used_sram_bitmap[0] |= mask[0]; + used_sram_bitmap[1] |= mask[1]; + used_sram_bitmap[2] |= mask[2]; + used_sram_bitmap[3] |= mask[3]; + __raw_writel(cfg | (addr << 14), &qmgr_regs->sram[queue]); + spin_unlock_irq(&qmgr_lock); + +#if DEBUG + printk(KERN_DEBUG "qmgr: requested queue %i, addr = 0x%02X\n", + queue, addr); +#endif + return 0; + +err: + spin_unlock_irq(&qmgr_lock); + module_put(THIS_MODULE); + return err; +} + +void qmgr_release_queue(unsigned int queue) +{ + u32 cfg, addr, mask[4]; + + BUG_ON(queue >= HALF_QUEUES); /* not in valid range */ + + spin_lock_irq(&qmgr_lock); + cfg = __raw_readl(&qmgr_regs->sram[queue]); + addr = (cfg >> 14) & 0xFF; + + BUG_ON(!addr); /* not requested */ + + switch ((cfg >> 24) & 3) { + case 0: mask[0] = 0x1; break; + case 1: mask[0] = 0x3; break; + case 2: mask[0] = 0xF; break; + case 3: mask[0] = 0xFF; break; + } + + while (addr--) + shift_mask(mask); + + __raw_writel(0, &qmgr_regs->sram[queue]); + + used_sram_bitmap[0] &= ~mask[0]; + used_sram_bitmap[1] &= ~mask[1]; + used_sram_bitmap[2] &= ~mask[2]; + used_sram_bitmap[3] &= ~mask[3]; + irq_handlers[queue] = NULL; /* catch IRQ bugs */ + spin_unlock_irq(&qmgr_lock); + + module_put(THIS_MODULE); +#if DEBUG + printk(KERN_DEBUG "qmgr: released queue %i\n", queue); +#endif +} + +static int qmgr_init(void) +{ + int i, err; + mem_res = request_mem_region(IXP4XX_QMGR_BASE_PHYS, + IXP4XX_QMGR_REGION_SIZE, + "IXP4xx Queue Manager"); + if (mem_res == NULL) + return -EBUSY; + + qmgr_regs = ioremap(IXP4XX_QMGR_BASE_PHYS, IXP4XX_QMGR_REGION_SIZE); + if (qmgr_regs == NULL) { + err = -ENOMEM; + goto error_map; + } + + /* reset qmgr registers */ + for (i = 0; i < 4; i++) { + __raw_writel(0x33333333, &qmgr_regs->stat1[i]); + __raw_writel(0, &qmgr_regs->irqsrc[i]); + } + for (i = 0; i < 2; i++) { + __raw_writel(0, &qmgr_regs->stat2[i]); + __raw_writel(0xFFFFFFFF, &qmgr_regs->irqstat[i]); /* clear */ + __raw_writel(0, &qmgr_regs->irqen[i]); + } + + for (i = 0; i < QUEUES; i++) + __raw_writel(0, &qmgr_regs->sram[i]); + + err = request_irq(IRQ_IXP4XX_QM1, qmgr_irq1, 0, + "IXP4xx Queue Manager", NULL); + if (err) { + printk(KERN_ERR "qmgr: failed to request IRQ%i\n", + IRQ_IXP4XX_QM1); + goto error_irq; + } + + used_sram_bitmap[0] = 0xF; /* 4 first pages reserved for config */ + spin_lock_init(&qmgr_lock); + + printk(KERN_INFO "IXP4xx Queue Manager initialized.\n"); + return 0; + +error_irq: + iounmap(qmgr_regs); +error_map: + release_mem_region(IXP4XX_QMGR_BASE_PHYS, IXP4XX_QMGR_REGION_SIZE); + return err; +} + +static void qmgr_remove(void) +{ + free_irq(IRQ_IXP4XX_QM1, NULL); + synchronize_irq(IRQ_IXP4XX_QM1); + iounmap(qmgr_regs); + release_mem_region(IXP4XX_QMGR_BASE_PHYS, IXP4XX_QMGR_REGION_SIZE); +} + +module_init(qmgr_init); +module_exit(qmgr_remove); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Krzysztof Halasa"); + +EXPORT_SYMBOL(qmgr_regs); +EXPORT_SYMBOL(qmgr_set_irq); +EXPORT_SYMBOL(qmgr_enable_irq); +EXPORT_SYMBOL(qmgr_disable_irq); +EXPORT_SYMBOL(qmgr_request_queue); +EXPORT_SYMBOL(qmgr_release_queue); diff --git a/include/asm-arm/arch-ixp4xx/npe.h b/include/asm-arm/arch-ixp4xx/npe.h new file mode 100644 index 00000000000..37d0511689d --- /dev/null +++ b/include/asm-arm/arch-ixp4xx/npe.h @@ -0,0 +1,39 @@ +#ifndef __IXP4XX_NPE_H +#define __IXP4XX_NPE_H + +#include + +extern const char *npe_names[]; + +struct npe_regs { + u32 exec_addr, exec_data, exec_status_cmd, exec_count; + u32 action_points[4]; + u32 watchpoint_fifo, watch_count; + u32 profile_count; + u32 messaging_status, messaging_control; + u32 mailbox_status, /*messaging_*/ in_out_fifo; +}; + +struct npe { + struct resource *mem_res; + struct npe_regs __iomem *regs; + u32 regs_phys; + int id; + int valid; +}; + + +static inline const char *npe_name(struct npe *npe) +{ + return npe_names[npe->id]; +} + +int npe_running(struct npe *npe); +int npe_send_message(struct npe *npe, const void *msg, const char *what); +int npe_recv_message(struct npe *npe, void *msg, const char *what); +int npe_send_recv_message(struct npe *npe, void *msg, const char *what); +int npe_load_firmware(struct npe *npe, const char *name, struct device *dev); +struct npe *npe_request(int id); +void npe_release(struct npe *npe); + +#endif /* __IXP4XX_NPE_H */ diff --git a/include/asm-arm/arch-ixp4xx/qmgr.h b/include/asm-arm/arch-ixp4xx/qmgr.h new file mode 100644 index 00000000000..1e52b95cede --- /dev/null +++ b/include/asm-arm/arch-ixp4xx/qmgr.h @@ -0,0 +1,126 @@ +/* + * Copyright (C) 2007 Krzysztof Halasa + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2 of the GNU General Public License + * as published by the Free Software Foundation. + */ + +#ifndef IXP4XX_QMGR_H +#define IXP4XX_QMGR_H + +#include +#include + +#define HALF_QUEUES 32 +#define QUEUES 64 /* only 32 lower queues currently supported */ +#define MAX_QUEUE_LENGTH 4 /* in dwords */ + +#define QUEUE_STAT1_EMPTY 1 /* queue status bits */ +#define QUEUE_STAT1_NEARLY_EMPTY 2 +#define QUEUE_STAT1_NEARLY_FULL 4 +#define QUEUE_STAT1_FULL 8 +#define QUEUE_STAT2_UNDERFLOW 1 +#define QUEUE_STAT2_OVERFLOW 2 + +#define QUEUE_WATERMARK_0_ENTRIES 0 +#define QUEUE_WATERMARK_1_ENTRY 1 +#define QUEUE_WATERMARK_2_ENTRIES 2 +#define QUEUE_WATERMARK_4_ENTRIES 3 +#define QUEUE_WATERMARK_8_ENTRIES 4 +#define QUEUE_WATERMARK_16_ENTRIES 5 +#define QUEUE_WATERMARK_32_ENTRIES 6 +#define QUEUE_WATERMARK_64_ENTRIES 7 + +/* queue interrupt request conditions */ +#define QUEUE_IRQ_SRC_EMPTY 0 +#define QUEUE_IRQ_SRC_NEARLY_EMPTY 1 +#define QUEUE_IRQ_SRC_NEARLY_FULL 2 +#define QUEUE_IRQ_SRC_FULL 3 +#define QUEUE_IRQ_SRC_NOT_EMPTY 4 +#define QUEUE_IRQ_SRC_NOT_NEARLY_EMPTY 5 +#define QUEUE_IRQ_SRC_NOT_NEARLY_FULL 6 +#define QUEUE_IRQ_SRC_NOT_FULL 7 + +struct qmgr_regs { + u32 acc[QUEUES][MAX_QUEUE_LENGTH]; /* 0x000 - 0x3FF */ + u32 stat1[4]; /* 0x400 - 0x40F */ + u32 stat2[2]; /* 0x410 - 0x417 */ + u32 statne_h; /* 0x418 - queue nearly empty */ + u32 statf_h; /* 0x41C - queue full */ + u32 irqsrc[4]; /* 0x420 - 0x42F IRC source */ + u32 irqen[2]; /* 0x430 - 0x437 IRQ enabled */ + u32 irqstat[2]; /* 0x438 - 0x43F - IRQ access only */ + u32 reserved[1776]; + u32 sram[2048]; /* 0x2000 - 0x3FFF - config and buffer */ +}; + +void qmgr_set_irq(unsigned int queue, int src, + void (*handler)(void *pdev), void *pdev); +void qmgr_enable_irq(unsigned int queue); +void qmgr_disable_irq(unsigned int queue); + +/* request_ and release_queue() must be called from non-IRQ context */ +int qmgr_request_queue(unsigned int queue, unsigned int len /* dwords */, + unsigned int nearly_empty_watermark, + unsigned int nearly_full_watermark); +void qmgr_release_queue(unsigned int queue); + + +static inline void qmgr_put_entry(unsigned int queue, u32 val) +{ + extern struct qmgr_regs __iomem *qmgr_regs; + __raw_writel(val, &qmgr_regs->acc[queue][0]); +} + +static inline u32 qmgr_get_entry(unsigned int queue) +{ + extern struct qmgr_regs __iomem *qmgr_regs; + return __raw_readl(&qmgr_regs->acc[queue][0]); +} + +static inline int qmgr_get_stat1(unsigned int queue) +{ + extern struct qmgr_regs __iomem *qmgr_regs; + return (__raw_readl(&qmgr_regs->stat1[queue >> 3]) + >> ((queue & 7) << 2)) & 0xF; +} + +static inline int qmgr_get_stat2(unsigned int queue) +{ + extern struct qmgr_regs __iomem *qmgr_regs; + return (__raw_readl(&qmgr_regs->stat2[queue >> 4]) + >> ((queue & 0xF) << 1)) & 0x3; +} + +static inline int qmgr_stat_empty(unsigned int queue) +{ + return !!(qmgr_get_stat1(queue) & QUEUE_STAT1_EMPTY); +} + +static inline int qmgr_stat_nearly_empty(unsigned int queue) +{ + return !!(qmgr_get_stat1(queue) & QUEUE_STAT1_NEARLY_EMPTY); +} + +static inline int qmgr_stat_nearly_full(unsigned int queue) +{ + return !!(qmgr_get_stat1(queue) & QUEUE_STAT1_NEARLY_FULL); +} + +static inline int qmgr_stat_full(unsigned int queue) +{ + return !!(qmgr_get_stat1(queue) & QUEUE_STAT1_FULL); +} + +static inline int qmgr_stat_underflow(unsigned int queue) +{ + return !!(qmgr_get_stat2(queue) & QUEUE_STAT2_UNDERFLOW); +} + +static inline int qmgr_stat_overflow(unsigned int queue) +{ + return !!(qmgr_get_stat2(queue) & QUEUE_STAT2_OVERFLOW); +} + +#endif