aboutsummaryrefslogtreecommitdiffstats
path: root/target/linux/generic/hack-4.14/300-MIPS-r4k_cache-use-more-efficient-cache-blast.patch
blob: c07ccf9474e0e9947f97ce68c9eeee0b02204ace (plain) 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66

From: Ben Menchaca <ben.menchaca@qca.qualcomm.com>
Date: Fri, 7 Jun 2013 18:35:22 -0500
Subject: MIPS: r4k_cache: use more efficient cache blast

Optimize the compiler output for larger cache blast cases that are
common for DMA-based networking.

Signed-off-by: Ben Menchaca <ben.menchaca@qca.qualcomm.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
--- a/arch/mips/include/asm/r4kcache.h
+++ b/arch/mips/include/asm/r4kcache.h
@@ -683,16 +683,48 @@ static inline void prot##extra##blast_##
 						    unsigned long end)	\
 {									\
 	unsigned long lsize = cpu_##desc##_line_size();			\
+	unsigned long lsize_2 = lsize * 2;				\
+	unsigned long lsize_3 = lsize * 3;				\
+	unsigned long lsize_4 = lsize * 4;				\
+	unsigned long lsize_5 = lsize * 5;				\
+	unsigned long lsize_6 = lsize * 6;				\
+	unsigned long lsize_7 = lsize * 7;				\
+	unsigned long lsize_8 = lsize * 8;				\
 	unsigned long addr = start & ~(lsize - 1);			\
-	unsigned long aend = (end - 1) & ~(lsize - 1);			\
+	unsigned long aend = (end + lsize - 1) & ~(lsize - 1);		\
+	int lines = (aend - addr) / lsize;				\
 									\
 	__##pfx##flush_prologue						\
 									\
-	while (1) {							\
+	while (lines >= 8) {						\
+		prot##cache_op(hitop, addr);				\
+		prot##cache_op(hitop, addr + lsize);			\
+		prot##cache_op(hitop, addr + lsize_2);			\
+		prot##cache_op(hitop, addr + lsize_3);			\
+		prot##cache_op(hitop, addr + lsize_4);			\
+		prot##cache_op(hitop, addr + lsize_5);			\
+		prot##cache_op(hitop, addr + lsize_6);			\
+		prot##cache_op(hitop, addr + lsize_7);			\
+		addr += lsize_8;					\
+		lines -= 8;						\
+	}								\
+									\
+	if (lines & 0x4) {						\
+		prot##cache_op(hitop, addr);				\
+		prot##cache_op(hitop, addr + lsize);			\
+		prot##cache_op(hitop, addr + lsize_2);			\
+		prot##cache_op(hitop, addr + lsize_3);			\
+		addr += lsize_4;					\
+	}								\
+									\
+	if (lines & 0x2) {						\
+		prot##cache_op(hitop, addr);				\
+		prot##cache_op(hitop, addr + lsize);			\
+		addr += lsize_2;					\
+	}								\
+									\
+	if (lines & 0x1) {						\
 		prot##cache_op(hitop, addr);				\
-		if (addr == aend)					\
-			break;						\
-		addr += lsize;						\
 	}								\
 									\
 	__##pfx##flush_epilogue						\
generated by cgit v1.2.3 (git 2.25.1) at 2025-09-14 08:15:17 +0000
ss="n">u8 symbols_names[] __attribute__((weak)); extern u8 symbols_token_table[] __attribute__((weak)); extern u16 symbols_token_index[] __attribute__((weak)); extern unsigned long symbols_markers[] __attribute__((weak)); /* expand a compressed symbol data into the resulting uncompressed string, given the offset to where the symbol is in the compressed stream */ static unsigned int symbols_expand_symbol(unsigned int off, char *result) { int len, skipped_first = 0; u8 *tptr, *data; /* get the compressed symbol length from the first symbol byte */ data = &symbols_names[off]; len = *data; data++; /* update the offset to return the offset for the next symbol on * the compressed stream */ off += len + 1; /* for every byte on the compressed symbol data, copy the table entry for that byte */ while(len) { tptr = &symbols_token_table[ symbols_token_index[*data] ]; data++; len--; while (*tptr) { if(skipped_first) { *result = *tptr; result++; } else skipped_first = 1; tptr++; } } *result = '\0'; /* return to offset to the next symbol */ return off; } /* find the offset on the compressed stream given and index in the * symbols array */ static unsigned int get_symbol_offset(unsigned long pos) { u8 *name; int i; /* use the closest marker we have. We have markers every 256 positions, * so that should be close enough */ name = &symbols_names[ symbols_markers[pos>>8] ]; /* sequentially scan all the symbols up to the point we're searching for. * Every symbol is stored in a [<len>][<len> bytes of data] format, so we * just need to add the len to the current pointer for every symbol we * wish to skip */ for(i = 0; i < (pos&0xFF); i++) name = name + (*name) + 1; return name - symbols_names; } const char *symbols_lookup(unsigned long addr, unsigned long *symbolsize, unsigned long *offset, char *namebuf) { unsigned long i, low, high, mid; unsigned long symbol_end = 0; /* This kernel should never had been booted. */ BUG_ON(!symbols_addresses); namebuf[KSYM_NAME_LEN] = 0; namebuf[0] = 0; if (!is_kernel_text(addr)) return NULL; /* do a binary search on the sorted symbols_addresses array */ low = 0; high = symbols_num_syms; while (high-low > 1) { mid = (low + high) / 2; if (symbols_addresses[mid] <= addr) low = mid; else high = mid; } /* search for the first aliased symbol. Aliased symbols are symbols with the same address */ while (low && symbols_addresses[low - 1] == symbols_addresses[low]) --low; /* Grab name */ symbols_expand_symbol(get_symbol_offset(low), namebuf); /* Search for next non-aliased symbol */ for (i = low + 1; i < symbols_num_syms; i++) { if (symbols_addresses[i] > symbols_addresses[low]) { symbol_end = symbols_addresses[i]; break; } } /* if we found no next symbol, we use the end of the section */ if (!symbol_end) symbol_end = kernel_text_end(); *symbolsize = symbol_end - symbols_addresses[low]; *offset = addr - symbols_addresses[low]; return namebuf; } /* Replace "%s" in format with address, or returns -errno. */ void __print_symbol(const char *fmt, unsigned long address) { const char *name; unsigned long offset, size; char namebuf[KSYM_NAME_LEN+1]; char buffer[sizeof("%s+%#lx/%#lx [%s]") + KSYM_NAME_LEN + 2*(BITS_PER_LONG*3/10) + 1]; name = symbols_lookup(address, &size, &offset, namebuf); if (!name) sprintf(buffer, "???"); else sprintf(buffer, "%s+%#lx/%#lx", name, offset, size); printk(fmt, buffer); }
generated by cgit v1.2.3 (git 2.25.1) at 2025-09-14 08:15:17 +0000