/*
 * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
 *
 * 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
 */

#include <linux/ptrace.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/kdev_t.h>
#include <linux/fs_struct.h>
#include <linux/proc_fs.h>
#include <linux/file.h>
#include <asm/arcregs.h>
#include <asm/irqflags.h>
#include <asm/board/troubleshoot.h>
#include <asm/cacheflush.h>
#include <linux/kmsg_dump.h>
#include <linux/vmalloc.h>
#include <linux/zlib.h>
#include <linux/slab.h>

/* 3.8 times seems safe for LHost, MuC and/or AuC crash - found by trial and error */
#define CORE_DUMP_COMPRESS_RATIO  (380)

static void kmsg_dumper_core_dump(struct kmsg_dumper *dumper, enum kmsg_dump_reason reason);

static unsigned long sram_safe_start;
static unsigned long sram_safe_size;

static arc_troubleshoot_start_hook_cbk troubleshoot_start;
static void *troubleshoot_ctx;

static struct kmsg_dumper dumper_core_dump = {.dump = kmsg_dumper_core_dump, .max_reason = KMSG_DUMP_PANIC};

/*
 * Common routine to print scratch regs (r0-r12) or callee regs (r13-r25)
 *   -Prints 3 regs per line and a CR.
 *   -To continue, callee regs right after scratch, special handling of CR
 */
static noinline void print_reg_file(long *reg_rev, int start_num)
{
	unsigned int i;
	char buf[512];
	int n = 0, len = sizeof(buf);

	for (i = start_num; i < start_num + 13; i++) {
		n += scnprintf(buf + n, len - n, "r%02u: 0x%08lx\t",
			       i, (unsigned long)*reg_rev);

		if (((i + 1) % 3) == 0)
			n += scnprintf(buf + n, len - n, "\n");

		/* because pt_regs has regs reversed: r12..r0, r25..r13 */
		if (is_isa_arcv2() && start_num == 0)
			reg_rev++;
		else
			reg_rev--;
	}

	if (start_num != 0)
		n += scnprintf(buf + n, len - n, "\n\n");

	/* To continue printing callee regs on same line as scratch regs */
	if (start_num == 0)
		pr_info("%s", buf);
	else
		pr_cont("%s\n", buf);
}

static void show_callee_regs(struct callee_regs *cregs)
{
	print_reg_file(&(cregs->r13), 13);
}

static void print_task_path_n_nm(struct task_struct *tsk, char *buf)
{
	char *path_nm = NULL;
	struct mm_struct *mm;
	struct file *exe_file;

	mm = get_task_mm(tsk);
	if (!mm)
		goto done;

	exe_file = get_mm_exe_file(mm);
	mmput(mm);

	if (exe_file) {
		path_nm = file_path(exe_file, buf, 255);
		fput(exe_file);
	}

done:
	pr_info("Path: %s\n", !IS_ERR(path_nm) ? path_nm : "?");
}

static void show_faulting_vma(unsigned long address, char *buf)
{
	struct vm_area_struct *vma;
	struct inode *inode;
	unsigned long ino = 0;
	dev_t dev = 0;
	char *nm = buf;
	struct mm_struct *active_mm = current->active_mm;

	/* can't use print_vma_addr() yet as it doesn't check for
	 * non-inclusive vma
	 */
	down_read(&active_mm->mmap_sem);
	vma = find_vma(active_mm, address);

	/* check against the find_vma( ) behaviour which returns the next VMA
	 * if the container VMA is not found
	 */
	if (vma && (vma->vm_start <= address)) {
		struct file *file = vma->vm_file;
		if (file) {
			nm = file_path(file, buf, PAGE_SIZE - 1);
			inode = file_inode(vma->vm_file);
			dev = inode->i_sb->s_dev;
			ino = inode->i_ino;
		}
		pr_info("    @off 0x%lx in [%s]\n"
			"    VMA: 0x%08lx to 0x%08lx\n",
			vma->vm_start < TASK_UNMAPPED_BASE ?
				address : address - vma->vm_start,
			nm, vma->vm_start, vma->vm_end);
	} else
		pr_info("    @No matching VMA found\n");

	up_read(&active_mm->mmap_sem);
}

static void show_ecr_verbose(struct pt_regs *regs)
{
	unsigned int vec, cause_code;
	unsigned long address;

	pr_info("\n[ECR   ]: 0x%08lx => ", regs->event);

	/* For Data fault, this is data address not instruction addr */
	address = current->thread.fault_address;

	vec = regs->ecr_vec;
	cause_code = regs->ecr_cause;

	/* For DTLB Miss or ProtV, display the memory involved too */
	if (vec == ECR_V_DTLB_MISS) {
		pr_cont("Invalid %s @ 0x%08lx by insn @ 0x%08lx\n",
		       (cause_code == 0x01) ? "Read" :
		       ((cause_code == 0x02) ? "Write" : "EX"),
		       address, regs->ret);
	} else if (vec == ECR_V_ITLB_MISS) {
		pr_cont("Insn could not be fetched\n");
	} else if (vec == ECR_V_MACH_CHK) {
		pr_cont("%s\n", (cause_code == 0x0) ?
					"Double Fault" : "Other Fatal Err");

	} else if (vec == ECR_V_PROTV) {
		if (cause_code == ECR_C_PROTV_INST_FETCH)
			pr_cont("Execute from Non-exec Page\n");
		else if (cause_code == ECR_C_PROTV_MISALIG_DATA)
			pr_cont("Misaligned r/w from 0x%08lx\n", address);
		else
			pr_cont("%s access not allowed on page\n",
				(cause_code == 0x01) ? "Read" :
				((cause_code == 0x02) ? "Write" : "EX"));
	} else if (vec == ECR_V_INSN_ERR) {
		pr_cont("Illegal Insn\n");
#ifdef CONFIG_ISA_ARCV2
	} else if (vec == ECR_V_MEM_ERR) {
		if (cause_code == 0x00)
			pr_cont("Bus Error from Insn Mem\n");
		else if (cause_code == 0x10)
			pr_cont("Bus Error from Data Mem\n");
		else
			pr_cont("Bus Error, check PRM\n");
#endif
	} else {
		pr_cont("Check Programmer's Manual\n");
	}
}

static int32_t compress_chunk(z_stream *stream, const bool is_last_stream)
{
	int32_t zlib_retval;

	if (!stream) {
		printk(KERN_ERR "%s: stream is NULL\n", __func__);
		return -EINVAL;
	}

	if (is_last_stream) {
		zlib_retval = zlib_deflate(stream, Z_FINISH);
		if (zlib_retval != Z_STREAM_END) {
			if (zlib_retval != Z_OK) {
				printk(KERN_ERR "%s: only chunk; zlib_deflate returned %d\n", __func__,
					zlib_retval);
				return -1;
			}

			printk(KERN_WARNING "%s: zlib_deflate (only chunk): some data would be missing\n",
				__func__);
		}
	} else {
		zlib_retval = zlib_deflate(stream, Z_SYNC_FLUSH);
		if (zlib_retval != Z_OK) {
			printk(KERN_ERR "%s: first chunk, zlib_deflate returned %d\n", __func__,
				zlib_retval);
			return -1;
		}

		/*
		 * If stream.avail_in is not 0, some logs could be missing; we should recheck len_max_input in
		 * arc_save_to_sram_safe_area()
		 */
		if (stream->avail_in != 0)
			printk(KERN_WARNING "%s: stream->avail_in (%ld) is not 0\n", __func__, stream->avail_in);
	}

	return 0;
}

static int32_t compress_circular_buffer(const char *buf_chunk_one, uint32_t len_chunk_one,
					const char *buf_chunk_two, uint32_t len_chunk_two,
					char *buf_out, uint32_t len_buf_out,
					uint32_t *len_compress_data)
{
	int32_t retval = -1;
	int32_t zlib_retval;
	int32_t workspace_size;
	z_stream stream;

	if (!len_compress_data) {
		printk(KERN_ERR "%s: len_compress_data is NULL\n", __func__);
		return -EINVAL;
	}

	*len_compress_data = 0;

	workspace_size = zlib_deflate_workspacesize(MAX_WBITS, MAX_MEM_LEVEL);
	printk(KERN_ERR "%s: workspace_size = %d\n", __func__, workspace_size);

	stream.workspace = kmalloc(workspace_size, GFP_ATOMIC);
	if (!stream.workspace) {
		printk(KERN_ERR "%s: Failed to allocate %d bytes for deflate workspace\n", __func__,
			workspace_size);
		return -ENOMEM;
	}

	/* Use zlib format because gzip is not available */
	zlib_retval = zlib_deflateInit(&stream, Z_DEFAULT_COMPRESSION);
	if (zlib_retval != Z_OK) {
		printk(KERN_ERR "%s: zlib_deflateInit failed, zlib_retval = %d\n", __func__, zlib_retval);
		kfree(stream.workspace);
		return retval;
	}

	stream.next_out = (Byte *) buf_out;
	stream.avail_out = len_buf_out;
	stream.total_out = 0;

	if (len_chunk_one) {
		/* Compress the first chunk */
		stream.next_in = (Byte *) buf_chunk_one;
		stream.avail_in = len_chunk_one;
		stream.total_in = 0;

		if (compress_chunk(&stream, len_chunk_two ? false : true))
			goto deflate_end;
	}

	if (len_chunk_two) {
		/* Compress the second chunk */
		stream.next_in = (Byte *) buf_chunk_two;
		stream.avail_in = len_chunk_two;
		stream.total_in = 0;

		if (compress_chunk(&stream, true))
			goto deflate_end;
	}

	*len_compress_data = stream.total_out;
	printk(KERN_ERR "%s: compressed data length = %u\n", __func__, *len_compress_data);

	retval = 0;

deflate_end:
	zlib_retval = zlib_deflateEnd(&stream);
	if (zlib_retval != Z_OK) {
		printk(KERN_WARNING "%s: zlib_deflateEnd failed, zlib_retval = %d\n", __func__, zlib_retval);
	}

	kfree(stream.workspace);

	return retval;
}

/* Save the printk circular buffer to the SRAM safe area */
void arc_save_to_sram_safe_area(const char *buf_chunk_one, uint32_t len_chunk_one,
				const char *buf_chunk_two, uint32_t len_chunk_two,
				uint32_t len_max_input)
{
	uint32_t extra_margin;
	uint32_t len_compress_data;

	/* Ensure that there is something in the printk circular buffer */
	if (!(len_chunk_one + len_chunk_two)) {
		printk(KERN_ERR "%s: len_chunk_one + len_chunk_two is 0\n", __func__);
		return;
	}

	if (len_max_input < len_chunk_one + len_chunk_two) {
		if (len_max_input <= len_chunk_two) {
			buf_chunk_one = NULL;
			len_chunk_one = 0;

			buf_chunk_two += (len_chunk_two - len_max_input);
			len_chunk_two = len_max_input;
		} else {
			len_max_input -= len_chunk_two;

			buf_chunk_one += (len_chunk_one - len_max_input);
			len_chunk_one = len_max_input;
		}
	}

	/* Refer to include/linux/zlib.h */
	extra_margin = (len_chunk_one + len_chunk_two) - (((len_chunk_one + len_chunk_two) * 1000) / 1001)
			+ 12;

	if (extra_margin < len_chunk_one) {
		buf_chunk_one += extra_margin;
		len_chunk_one -= extra_margin;
	} else {
		extra_margin -= len_chunk_one;

		buf_chunk_one = NULL;
		len_chunk_one = 0;

		buf_chunk_two += extra_margin;
		len_chunk_two -= extra_margin;
	}

	/*
	 * Compress the printk circular buffer and store it in SRAM safe aread (so as to retrieve it on the
	 * next reboot)
	 */
	compress_circular_buffer(buf_chunk_one, len_chunk_one, buf_chunk_two, len_chunk_two,
					(char *) (sram_safe_start + 4), sram_safe_size - 4,
					&len_compress_data);

	*((uint16_t *) sram_safe_start) = HEADER_CORE_DUMP;
	*((uint16_t *) (sram_safe_start + 2)) = (uint16_t) len_compress_data;

	flush_cache_all();
}

static void kmsg_dumper_core_dump(struct kmsg_dumper *dumper, enum kmsg_dump_reason reason)
{
	char *buf;
	uint32_t buf_in_len;
	uint32_t buf_out_len = 0;

	if (reason < KMSG_DUMP_PANIC)
		return;

	/*
	 * Format of buffer:
	 *      2 bytes: Header (HEADER_CORE_DUMP)
	 *      2 bytes: Length of the compressed logs (n)
	 *      n bytes: Compressed logs
	 */

	/* Expecting sram_safe_start to be 2 byte aligned */
	if ((sram_safe_start & 0x1) != 0) {
		printk(KERN_ERR "%s: sram_safe_start (%lu) is not 2 bytes aligned\n", __func__,
			sram_safe_start);
		return;
	}

	/* Needed to inform the owner that its memory is about to be used */
	if (!troubleshoot_start) {
		printk(KERN_ERR "%s: troubleshoot_start not set\n", __func__);
		return;
	}

	/*
	 * Find the max input length that could be fed into the compression algo [remove the header (2b)
	 * and length (2b)]
	 */
	buf_in_len = (CORE_DUMP_COMPRESS_RATIO * (sram_safe_size - 4)) / 100;

	buf = kmalloc(buf_in_len, GFP_ATOMIC);
	if (!buf) {
		printk(KERN_ERR "%s: Failed to allocate %u bytes for core dump buffer\n", __func__,
			buf_in_len);
		return;
	}

	if (false == kmsg_dump_get_buffer(dumper, false, buf, buf_in_len, &buf_out_len)) {
		printk(KERN_ERR "%s: kmsg_dump_get_buffer failed\n", __func__);
		kfree(buf);
		return;
	}

	(*troubleshoot_start)(troubleshoot_ctx);

	arc_save_to_sram_safe_area(buf, buf_out_len, NULL, 0, buf_out_len);

	kfree(buf);
}

/************************************************************************
 *  API called by rest of kernel
 ***********************************************************************/

void show_regs(struct pt_regs *regs)
{
	struct task_struct *tsk = current;
	struct callee_regs *cregs;
	char *buf;

	buf = (char *)__get_free_page(GFP_TEMPORARY);
	if (!buf)
		return;

	print_task_path_n_nm(tsk, buf);
	show_regs_print_info(KERN_INFO);

	show_ecr_verbose(regs);

	pr_info("[EFA   ]: 0x%08lx\n[BLINK ]: %pS\n[ERET  ]: %pS\n",
		current->thread.fault_address,
		(void *)regs->blink, (void *)regs->ret);

	if (user_mode(regs))
		show_faulting_vma(regs->ret, buf); /* faulting code, not data */

	pr_info("[STAT32]: 0x%08lx", regs->status32);

#define STS_BIT(r, bit)	r->status32 & STATUS_##bit##_MASK ? #bit" " : ""

#ifdef CONFIG_ISA_ARCOMPACT
	pr_cont(" : %2s%2s%2s%2s%2s%2s%2s\n",
			(regs->status32 & STATUS_U_MASK) ? "U " : "K ",
			STS_BIT(regs, DE), STS_BIT(regs, AE),
			STS_BIT(regs, A2), STS_BIT(regs, A1),
			STS_BIT(regs, E2), STS_BIT(regs, E1));
#else
	pr_cont(" : %2s%2s%2s%2s\n",
			STS_BIT(regs, IE),
			(regs->status32 & STATUS_U_MASK) ? "U " : "K ",
			STS_BIT(regs, DE), STS_BIT(regs, AE));
#endif
	pr_info("BTA: 0x%08lx\t SP: 0x%08lx\t FP: 0x%08lx\n",
		regs->bta, regs->sp, regs->fp);
	pr_info("LPS: 0x%08lx\tLPE: 0x%08lx\tLPC: 0x%08lx\n",
	       regs->lp_start, regs->lp_end, regs->lp_count);

	/* print regs->r0 thru regs->r12
	 * Sequential printing was generating horrible code
	 */
	print_reg_file(&(regs->r0), 0);

	/* If Callee regs were saved, display them too */
	cregs = (struct callee_regs *)current->thread.callee_reg;
	if (cregs)
		show_callee_regs(cregs);

	free_page((unsigned long)buf);
}

void show_kernel_fault_diag(const char *str, struct pt_regs *regs,
			    unsigned long address)
{
	current->thread.fault_address = address;

	/* Caller and Callee regs */
	show_regs(regs);

	/* Show stack trace if this Fatality happened in kernel mode */
	if (!user_mode(regs))
		show_stacktrace(current, regs);

	kmsg_dump(KMSG_DUMP_PANIC);
}

void arc_set_sram_safe_area(unsigned long sram_start, unsigned long sram_end)
{
	int retval;

	sram_safe_start = sram_start;
	sram_safe_size = sram_end - sram_safe_start;

	printk("%s: sram_safe_start=%p, size=%#x\n", sram_safe_start, sram_safe_size);
	/* Register the kmsg dumper - will be called if LHost, MuC and/or AuC crashes */
	retval = kmsg_dump_register(&dumper_core_dump);
	if (retval)
		printk(KERN_ERR "%s: Could not register dumper_core_dump\n", __func__);
}
EXPORT_SYMBOL(arc_set_sram_safe_area);

void arc_set_troubleshoot_start_hook(arc_troubleshoot_start_hook_cbk start, void *ctx)
{
	troubleshoot_start = start;
	troubleshoot_ctx = ctx;
}
EXPORT_SYMBOL(arc_set_troubleshoot_start_hook);

#ifdef CONFIG_DEBUG_FS

#include <linux/module.h>
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/pagemap.h>
#include <linux/init.h>
#include <linux/namei.h>
#include <linux/debugfs.h>

static struct dentry *test_dentry;
static struct dentry *test_dir;
static struct dentry *test_u32_dentry;

static u32 clr_on_read = 1;

#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
u32 numitlb, numdtlb, num_pte_not_present;

static int fill_display_data(char *kbuf)
{
	size_t num = 0;
	num += sprintf(kbuf + num, "I-TLB Miss %x\n", numitlb);
	num += sprintf(kbuf + num, "D-TLB Miss %x\n", numdtlb);
	num += sprintf(kbuf + num, "PTE not present %x\n", num_pte_not_present);

	if (clr_on_read)
		numitlb = numdtlb = num_pte_not_present = 0;

	return num;
}

static int tlb_stats_open(struct inode *inode, struct file *file)
{
	file->private_data = (void *)__get_free_page(GFP_KERNEL);
	return 0;
}

/* called on user read(): display the counters */
static ssize_t tlb_stats_output(struct file *file,	/* file descriptor */
				char __user *user_buf,	/* user buffer */
				size_t len,		/* length of buffer */
				loff_t *offset)		/* offset in the file */
{
	size_t num;
	char *kbuf = (char *)file->private_data;

	/* All of the data can he shoved in one iteration */
	if (*offset != 0)
		return 0;

	num = fill_display_data(kbuf);

	/* simple_read_from_buffer() is helper for copy to user space
	   It copies up to @2 (num) bytes from kernel buffer @4 (kbuf) at offset
	   @3 (offset) into the user space address starting at @1 (user_buf).
	   @5 (len) is max size of user buffer
	 */
	return simple_read_from_buffer(user_buf, num, offset, kbuf, len);
}

/* called on user write : clears the counters */
static ssize_t tlb_stats_clear(struct file *file, const char __user *user_buf,
			       size_t length, loff_t *offset)
{
	numitlb = numdtlb = num_pte_not_present = 0;
	return length;
}

static int tlb_stats_close(struct inode *inode, struct file *file)
{
	free_page((unsigned long)(file->private_data));
	return 0;
}

static const struct file_operations tlb_stats_file_ops = {
	.read = tlb_stats_output,
	.write = tlb_stats_clear,
	.open = tlb_stats_open,
	.release = tlb_stats_close
};
#endif

static int __init arc_debugfs_init(void)
{
	test_dir = debugfs_create_dir("arc", NULL);

#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
	test_dentry = debugfs_create_file("tlb_stats", 0444, test_dir, NULL,
					  &tlb_stats_file_ops);
#endif

	test_u32_dentry =
	    debugfs_create_u32("clr_on_read", 0444, test_dir, &clr_on_read);

	return 0;
}

module_init(arc_debugfs_init);

static void __exit arc_debugfs_exit(void)
{
	debugfs_remove(test_u32_dentry);
	debugfs_remove(test_dentry);
	debugfs_remove(test_dir);
}
module_exit(arc_debugfs_exit);

#endif