diff options
Diffstat (limited to 'lib')
-rw-r--r-- | lib/Kconfig | 9 | ||||
-rw-r--r-- | lib/Kconfig.debug | 48 | ||||
-rw-r--r-- | lib/Kconfig.kgdb | 58 | ||||
-rw-r--r-- | lib/Makefile | 5 | ||||
-rw-r--r-- | lib/bitmap.c | 174 | ||||
-rw-r--r-- | lib/find_next_bit.c | 77 | ||||
-rw-r--r-- | lib/kernel_lock.c | 1 | ||||
-rw-r--r-- | lib/kobject.c | 19 | ||||
-rw-r--r-- | lib/kobject_uevent.c | 6 | ||||
-rw-r--r-- | lib/lmb.c | 428 | ||||
-rw-r--r-- | lib/pcounter.c | 58 | ||||
-rw-r--r-- | lib/radix-tree.c | 9 | ||||
-rw-r--r-- | lib/reed_solomon/reed_solomon.c | 1 | ||||
-rw-r--r-- | lib/scatterlist.c | 102 | ||||
-rw-r--r-- | lib/semaphore-sleepers.c | 176 |
15 files changed, 894 insertions, 277 deletions
diff --git a/lib/Kconfig b/lib/Kconfig index ba3d104994d9..8cc8e8722a3f 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -7,6 +7,12 @@ menu "Library routines" config BITREVERSE tristate +config GENERIC_FIND_FIRST_BIT + def_bool n + +config GENERIC_FIND_NEXT_BIT + def_bool n + config CRC_CCITT tristate "CRC-CCITT functions" help @@ -141,4 +147,7 @@ config HAS_DMA config CHECK_SIGNATURE bool +config HAVE_LMB + boolean + endmenu diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 0796c1a090c0..754cc0027f2a 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -25,6 +25,17 @@ config ENABLE_MUST_CHECK suppress the "warning: ignoring return value of 'foo', declared with attribute warn_unused_result" messages. +config FRAME_WARN + int "Warn for stack frames larger than (needs gcc 4.4)" + range 0 8192 + default 1024 if !64BIT + default 2048 if 64BIT + help + Tell gcc to warn at build time for stack frames larger than this. + Setting this too low will cause a lot of warnings. + Setting it to 0 disables the warning. + Requires gcc 4.4 + config MAGIC_SYSRQ bool "Magic SysRq key" depends on !UML @@ -211,7 +222,7 @@ config SLUB_DEBUG_ON config SLUB_STATS default n bool "Enable SLUB performance statistics" - depends on SLUB + depends on SLUB && SLUB_DEBUG && SYSFS help SLUB statistics are useful to debug SLUBs allocation behavior in order find ways to optimize the allocator. This should never be @@ -265,16 +276,6 @@ config DEBUG_MUTEXES This feature allows mutex semantics violations to be detected and reported. -config DEBUG_SEMAPHORE - bool "Semaphore debugging" - depends on DEBUG_KERNEL - depends on ALPHA || FRV - default n - help - If you say Y here then semaphore processing will issue lots of - verbose debugging messages. If you suspect a semaphore problem or a - kernel hacker asks for this option then say Y. Otherwise say N. - config DEBUG_LOCK_ALLOC bool "Lock debugging: detect incorrect freeing of live locks" depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT @@ -437,6 +438,16 @@ config DEBUG_VM If unsure, say N. +config DEBUG_WRITECOUNT + bool "Debug filesystem writers count" + depends on DEBUG_KERNEL + help + Enable this to catch wrong use of the writers count in struct + vfsmount. This will increase the size of each file struct by + 32 bits. + + If unsure, say N. + config DEBUG_LIST bool "Debug linked list manipulation" depends on DEBUG_KERNEL @@ -593,7 +604,7 @@ config LATENCYTOP to find out which userspace is blocking on what kernel operations. config PROVIDE_OHCI1394_DMA_INIT - bool "Provide code for enabling DMA over FireWire early on boot" + bool "Remote debugging over FireWire early on boot" depends on PCI && X86 help If you want to debug problems which hang or crash the kernel early @@ -621,4 +632,17 @@ config PROVIDE_OHCI1394_DMA_INIT See Documentation/debugging-via-ohci1394.txt for more information. +config FIREWIRE_OHCI_REMOTE_DMA + bool "Remote debugging over FireWire with firewire-ohci" + depends on FIREWIRE_OHCI + help + This option lets you use the FireWire bus for remote debugging + with help of the firewire-ohci driver. It enables unfiltered + remote DMA in firewire-ohci. + See Documentation/debugging-via-ohci1394.txt for more information. + + If unsure, say N. + source "samples/Kconfig" + +source "lib/Kconfig.kgdb" diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb new file mode 100644 index 000000000000..f2e01ac5ab09 --- /dev/null +++ b/lib/Kconfig.kgdb @@ -0,0 +1,58 @@ + +menuconfig KGDB + bool "KGDB: kernel debugging with remote gdb" + select FRAME_POINTER + depends on HAVE_ARCH_KGDB + depends on DEBUG_KERNEL && EXPERIMENTAL + help + If you say Y here, it will be possible to remotely debug the + kernel using gdb. Documentation of kernel debugger is available + at http://kgdb.sourceforge.net as well as in DocBook form + in Documentation/DocBook/. If unsure, say N. + +config HAVE_ARCH_KGDB_SHADOW_INFO + bool + +config HAVE_ARCH_KGDB + bool + +config KGDB_SERIAL_CONSOLE + tristate "KGDB: use kgdb over the serial console" + depends on KGDB + select CONSOLE_POLL + select MAGIC_SYSRQ + default y + help + Share a serial console with kgdb. Sysrq-g must be used + to break in initially. + +config KGDB_TESTS + bool "KGDB: internal test suite" + depends on KGDB + default n + help + This is a kgdb I/O module specifically designed to test + kgdb's internal functions. This kgdb I/O module is + intended to for the development of new kgdb stubs + as well as regression testing the kgdb internals. + See the drivers/misc/kgdbts.c for the details about + the tests. The most basic of this I/O module is to boot + a kernel boot arguments "kgdbwait kgdbts=V1F100" + +config KGDB_TESTS_ON_BOOT + bool "KGDB: Run tests on boot" + depends on KGDB_TESTS + default n + help + Run the kgdb tests on boot up automatically without the need + to pass in a kernel parameter + +config KGDB_TESTS_BOOT_STRING + string "KGDB: which internal kgdb tests to run" + depends on KGDB_TESTS_ON_BOOT + default "V1F100" + help + This is the command string to send the kgdb test suite on + boot. See the drivers/misc/kgdbts.c for detailed + information about other strings you could use beyond the + default of V1F100. diff --git a/lib/Makefile b/lib/Makefile index 23de261a4c83..2d7001b7f5a4 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -29,7 +29,7 @@ obj-$(CONFIG_DEBUG_LOCKING_API_SELFTESTS) += locking-selftest.o obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o lib-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o -lib-$(CONFIG_SEMAPHORE_SLEEPERS) += semaphore-sleepers.o +lib-$(CONFIG_GENERIC_FIND_FIRST_BIT) += find_next_bit.o lib-$(CONFIG_GENERIC_FIND_NEXT_BIT) += find_next_bit.o obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o obj-$(CONFIG_LOCK_KERNEL) += kernel_lock.o @@ -61,7 +61,6 @@ obj-$(CONFIG_TEXTSEARCH_KMP) += ts_kmp.o obj-$(CONFIG_TEXTSEARCH_BM) += ts_bm.o obj-$(CONFIG_TEXTSEARCH_FSM) += ts_fsm.o obj-$(CONFIG_SMP) += percpu_counter.o -obj-$(CONFIG_SMP) += pcounter.o obj-$(CONFIG_AUDIT_GENERIC) += audit.o obj-$(CONFIG_SWIOTLB) += swiotlb.o @@ -70,6 +69,8 @@ obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o lib-$(CONFIG_GENERIC_BUG) += bug.o +obj-$(CONFIG_HAVE_LMB) += lmb.o + hostprogs-y := gen_crc32table clean-files := crc32table.h diff --git a/lib/bitmap.c b/lib/bitmap.c index 2c9242e3fed0..c4cb48f77f0c 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -316,6 +316,22 @@ int bitmap_scnprintf(char *buf, unsigned int buflen, EXPORT_SYMBOL(bitmap_scnprintf); /** + * bitmap_scnprintf_len - return buffer length needed to convert + * bitmap to an ASCII hex string. + * @len: number of bits to be converted + */ +int bitmap_scnprintf_len(unsigned int len) +{ + /* we need 9 chars per word for 32 bit words (8 hexdigits + sep/null) */ + int bitslen = ALIGN(len, CHUNKSZ); + int wordlen = CHUNKSZ / 4; + int buflen = (bitslen / wordlen) * (wordlen + 1) * sizeof(char); + + return buflen; +} +EXPORT_SYMBOL(bitmap_scnprintf_len); + +/** * __bitmap_parse - convert an ASCII hex string into a bitmap. * @buf: pointer to buffer containing string. * @buflen: buffer size in bytes. If string is smaller than this @@ -698,6 +714,164 @@ int bitmap_bitremap(int oldbit, const unsigned long *old, } EXPORT_SYMBOL(bitmap_bitremap); +/** + * bitmap_onto - translate one bitmap relative to another + * @dst: resulting translated bitmap + * @orig: original untranslated bitmap + * @relmap: bitmap relative to which translated + * @bits: number of bits in each of these bitmaps + * + * Set the n-th bit of @dst iff there exists some m such that the + * n-th bit of @relmap is set, the m-th bit of @orig is set, and + * the n-th bit of @relmap is also the m-th _set_ bit of @relmap. + * (If you understood the previous sentence the first time your + * read it, you're overqualified for your current job.) + * + * In other words, @orig is mapped onto (surjectively) @dst, + * using the the map { <n, m> | the n-th bit of @relmap is the + * m-th set bit of @relmap }. + * + * Any set bits in @orig above bit number W, where W is the + * weight of (number of set bits in) @relmap are mapped nowhere. + * In particular, if for all bits m set in @orig, m >= W, then + * @dst will end up empty. In situations where the possibility + * of such an empty result is not desired, one way to avoid it is + * to use the bitmap_fold() operator, below, to first fold the + * @orig bitmap over itself so that all its set bits x are in the + * range 0 <= x < W. The bitmap_fold() operator does this by + * setting the bit (m % W) in @dst, for each bit (m) set in @orig. + * + * Example [1] for bitmap_onto(): + * Let's say @relmap has bits 30-39 set, and @orig has bits + * 1, 3, 5, 7, 9 and 11 set. Then on return from this routine, + * @dst will have bits 31, 33, 35, 37 and 39 set. + * + * When bit 0 is set in @orig, it means turn on the bit in + * @dst corresponding to whatever is the first bit (if any) + * that is turned on in @relmap. Since bit 0 was off in the + * above example, we leave off that bit (bit 30) in @dst. + * + * When bit 1 is set in @orig (as in the above example), it + * means turn on the bit in @dst corresponding to whatever + * is the second bit that is turned on in @relmap. The second + * bit in @relmap that was turned on in the above example was + * bit 31, so we turned on bit 31 in @dst. + * + * Similarly, we turned on bits 33, 35, 37 and 39 in @dst, + * because they were the 4th, 6th, 8th and 10th set bits + * set in @relmap, and the 4th, 6th, 8th and 10th bits of + * @orig (i.e. bits 3, 5, 7 and 9) were also set. + * + * When bit 11 is set in @orig, it means turn on the bit in + * @dst corresponding to whatever is the twelth bit that is + * turned on in @relmap. In the above example, there were + * only ten bits turned on in @relmap (30..39), so that bit + * 11 was set in @orig had no affect on @dst. + * + * Example [2] for bitmap_fold() + bitmap_onto(): + * Let's say @relmap has these ten bits set: + * 40 41 42 43 45 48 53 61 74 95 + * (for the curious, that's 40 plus the first ten terms of the + * Fibonacci sequence.) + * + * Further lets say we use the following code, invoking + * bitmap_fold() then bitmap_onto, as suggested above to + * avoid the possitility of an empty @dst result: + * + * unsigned long *tmp; // a temporary bitmap's bits + * + * bitmap_fold(tmp, orig, bitmap_weight(relmap, bits), bits); + * bitmap_onto(dst, tmp, relmap, bits); + * + * Then this table shows what various values of @dst would be, for + * various @orig's. I list the zero-based positions of each set bit. + * The tmp column shows the intermediate result, as computed by + * using bitmap_fold() to fold the @orig bitmap modulo ten + * (the weight of @relmap). + * + * @orig tmp @dst + * 0 0 40 + * 1 1 41 + * 9 9 95 + * 10 0 40 (*) + * 1 3 5 7 1 3 5 7 41 43 48 61 + * 0 1 2 3 4 0 1 2 3 4 40 41 42 43 45 + * 0 9 18 27 0 9 8 7 40 61 74 95 + * 0 10 20 30 0 40 + * 0 11 22 33 0 1 2 3 40 41 42 43 + * 0 12 24 36 0 2 4 6 40 42 45 53 + * 78 102 211 1 2 8 41 42 74 (*) + * + * (*) For these marked lines, if we hadn't first done bitmap_fold() + * into tmp, then the @dst result would have been empty. + * + * If either of @orig or @relmap is empty (no set bits), then @dst + * will be returned empty. + * + * If (as explained above) the only set bits in @orig are in positions + * m where m >= W, (where W is the weight of @relmap) then @dst will + * once again be returned empty. + * + * All bits in @dst not set by the above rule are cleared. + */ +void bitmap_onto(unsigned long *dst, const unsigned long *orig, + const unsigned long *relmap, int bits) +{ + int n, m; /* same meaning as in above comment */ + + if (dst == orig) /* following doesn't handle inplace mappings */ + return; + bitmap_zero(dst, bits); + + /* + * The following code is a more efficient, but less + * obvious, equivalent to the loop: + * for (m = 0; m < bitmap_weight(relmap, bits); m++) { + * n = bitmap_ord_to_pos(orig, m, bits); + * if (test_bit(m, orig)) + * set_bit(n, dst); + * } + */ + + m = 0; + for (n = find_first_bit(relmap, bits); + n < bits; + n = find_next_bit(relmap, bits, n + 1)) { + /* m == bitmap_pos_to_ord(relmap, n, bits) */ + if (test_bit(m, orig)) + set_bit(n, dst); + m++; + } +} +EXPORT_SYMBOL(bitmap_onto); + +/** + * bitmap_fold - fold larger bitmap into smaller, modulo specified size + * @dst: resulting smaller bitmap + * @orig: original larger bitmap + * @sz: specified size + * @bits: number of bits in each of these bitmaps + * + * For each bit oldbit in @orig, set bit oldbit mod @sz in @dst. + * Clear all other bits in @dst. See further the comment and + * Example [2] for bitmap_onto() for why and how to use this. + */ +void bitmap_fold(unsigned long *dst, const unsigned long *orig, + int sz, int bits) +{ + int oldbit; + + if (dst == orig) /* following doesn't handle inplace mappings */ + return; + bitmap_zero(dst, bits); + + for (oldbit = find_first_bit(orig, bits); + oldbit < bits; + oldbit = find_next_bit(orig, bits, oldbit + 1)) + set_bit(oldbit % sz, dst); +} +EXPORT_SYMBOL(bitmap_fold); + /* * Common code for bitmap_*_region() routines. * bitmap: array of unsigned longs corresponding to the bitmap diff --git a/lib/find_next_bit.c b/lib/find_next_bit.c index 78ccd73a8841..d3f5784807b4 100644 --- a/lib/find_next_bit.c +++ b/lib/find_next_bit.c @@ -16,14 +16,12 @@ #define BITOP_WORD(nr) ((nr) / BITS_PER_LONG) -/** - * find_next_bit - find the next set bit in a memory region - * @addr: The address to base the search on - * @offset: The bitnumber to start searching at - * @size: The maximum size to search +#ifdef CONFIG_GENERIC_FIND_NEXT_BIT +/* + * Find the next set bit in a memory region. */ -unsigned long find_next_bit(const unsigned long *addr, unsigned long size, - unsigned long offset) +unsigned long __find_next_bit(const unsigned long *addr, + unsigned long size, unsigned long offset) { const unsigned long *p = addr + BITOP_WORD(offset); unsigned long result = offset & ~(BITS_PER_LONG-1); @@ -60,15 +58,14 @@ found_first: found_middle: return result + __ffs(tmp); } - -EXPORT_SYMBOL(find_next_bit); +EXPORT_SYMBOL(__find_next_bit); /* * This implementation of find_{first,next}_zero_bit was stolen from * Linus' asm-alpha/bitops.h. */ -unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, - unsigned long offset) +unsigned long __find_next_zero_bit(const unsigned long *addr, + unsigned long size, unsigned long offset) { const unsigned long *p = addr + BITOP_WORD(offset); unsigned long result = offset & ~(BITS_PER_LONG-1); @@ -105,8 +102,64 @@ found_first: found_middle: return result + ffz(tmp); } +EXPORT_SYMBOL(__find_next_zero_bit); +#endif /* CONFIG_GENERIC_FIND_NEXT_BIT */ + +#ifdef CONFIG_GENERIC_FIND_FIRST_BIT +/* + * Find the first set bit in a memory region. + */ +unsigned long __find_first_bit(const unsigned long *addr, + unsigned long size) +{ + const unsigned long *p = addr; + unsigned long result = 0; + unsigned long tmp; -EXPORT_SYMBOL(find_next_zero_bit); + while (size & ~(BITS_PER_LONG-1)) { + if ((tmp = *(p++))) + goto found; + result += BITS_PER_LONG; + size -= BITS_PER_LONG; + } + if (!size) + return result; + + tmp = (*p) & (~0UL >> (BITS_PER_LONG - size)); + if (tmp == 0UL) /* Are any bits set? */ + return result + size; /* Nope. */ +found: + return result + __ffs(tmp); +} +EXPORT_SYMBOL(__find_first_bit); + +/* + * Find the first cleared bit in a memory region. + */ +unsigned long __find_first_zero_bit(const unsigned long *addr, + unsigned long size) +{ + const unsigned long *p = addr; + unsigned long result = 0; + unsigned long tmp; + + while (size & ~(BITS_PER_LONG-1)) { + if (~(tmp = *(p++))) + goto found; + result += BITS_PER_LONG; + size -= BITS_PER_LONG; + } + if (!size) + return result; + + tmp = (*p) | (~0UL << size); + if (tmp == ~0UL) /* Are any bits zero? */ + return result + size; /* Nope. */ +found: + return result + ffz(tmp); +} +EXPORT_SYMBOL(__find_first_zero_bit); +#endif /* CONFIG_GENERIC_FIND_FIRST_BIT */ #ifdef __BIG_ENDIAN diff --git a/lib/kernel_lock.c b/lib/kernel_lock.c index 812dbf00844b..cd3e82530b03 100644 --- a/lib/kernel_lock.c +++ b/lib/kernel_lock.c @@ -8,6 +8,7 @@ #include <linux/smp_lock.h> #include <linux/module.h> #include <linux/kallsyms.h> +#include <linux/semaphore.h> /* * The 'big kernel semaphore' diff --git a/lib/kobject.c b/lib/kobject.c index 0d03252f87a8..2c6490370922 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -58,11 +58,6 @@ static int create_dir(struct kobject *kobj) return error; } -static inline struct kobject *to_kobj(struct list_head *entry) -{ - return container_of(entry, struct kobject, entry); -} - static int get_kobj_path_length(struct kobject *kobj) { int length = 1; @@ -592,8 +587,15 @@ static void kobject_release(struct kref *kref) */ void kobject_put(struct kobject *kobj) { - if (kobj) + if (kobj) { + if (!kobj->state_initialized) { + printk(KERN_WARNING "kobject: '%s' (%p): is not " + "initialized, yet kobject_put() is being " + "called.\n", kobject_name(kobj), kobj); + WARN_ON(1); + } kref_put(&kobj->kref, kobject_release); + } } static void dynamic_kobj_release(struct kobject *kobj) @@ -745,12 +747,11 @@ void kset_unregister(struct kset *k) */ struct kobject *kset_find_obj(struct kset *kset, const char *name) { - struct list_head *entry; + struct kobject *k; struct kobject *ret = NULL; spin_lock(&kset->list_lock); - list_for_each(entry, &kset->list) { - struct kobject *k = to_kobj(entry); + list_for_each_entry(k, &kset->list, entry) { if (kobject_name(k) && !strcmp(kobject_name(k), name)) { ret = kobject_get(k); break; diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index 5b6d7f6956b9..9fb6b86cf6b1 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -15,11 +15,13 @@ */ #include <linux/spinlock.h> +#include <linux/string.h> +#include <linux/kobject.h> +#include <linux/module.h> + #include <linux/socket.h> #include <linux/skbuff.h> #include <linux/netlink.h> -#include <linux/string.h> -#include <linux/kobject.h> #include <net/sock.h> diff --git a/lib/lmb.c b/lib/lmb.c new file mode 100644 index 000000000000..207147ab25e4 --- /dev/null +++ b/lib/lmb.c @@ -0,0 +1,428 @@ +/* + * Procedures for maintaining information about logical memory blocks. + * + * Peter Bergner, IBM Corp. June 2001. + * Copyright (C) 2001 Peter Bergner. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/bitops.h> +#include <linux/lmb.h> + +#define LMB_ALLOC_ANYWHERE 0 + +struct lmb lmb; + +void lmb_dump_all(void) +{ +#ifdef DEBUG + unsigned long i; + + pr_debug("lmb_dump_all:\n"); + pr_debug(" memory.cnt = 0x%lx\n", lmb.memory.cnt); + pr_debug(" memory.size = 0x%llx\n", + (unsigned long long)lmb.memory.size); + for (i=0; i < lmb.memory.cnt ;i++) { + pr_debug(" memory.region[0x%x].base = 0x%llx\n", + i, (unsigned long long)lmb.memory.region[i].base); + pr_debug(" .size = 0x%llx\n", + (unsigned long long)lmb.memory.region[i].size); + } + + pr_debug(" reserved.cnt = 0x%lx\n", lmb.reserved.cnt); + pr_debug(" reserved.size = 0x%lx\n", lmb.reserved.size); + for (i=0; i < lmb.reserved.cnt ;i++) { + pr_debug(" reserved.region[0x%x].base = 0x%llx\n", + i, (unsigned long long)lmb.reserved.region[i].base); + pr_debug(" .size = 0x%llx\n", + (unsigned long long)lmb.reserved.region[i].size); + } +#endif /* DEBUG */ +} + +static unsigned long __init lmb_addrs_overlap(u64 base1, u64 size1, + u64 base2, u64 size2) +{ + return ((base1 < (base2 + size2)) && (base2 < (base1 + size1))); +} + +static long __init lmb_addrs_adjacent(u64 base1, u64 size1, + u64 base2, u64 size2) +{ + if (base2 == base1 + size1) + return 1; + else if (base1 == base2 + size2) + return -1; + + return 0; +} + +static long __init lmb_regions_adjacent(struct lmb_region *rgn, + unsigned long r1, unsigned long r2) +{ + u64 base1 = rgn->region[r1].base; + u64 size1 = rgn->region[r1].size; + u64 base2 = rgn->region[r2].base; + u64 size2 = rgn->region[r2].size; + + return lmb_addrs_adjacent(base1, size1, base2, size2); +} + +static void __init lmb_remove_region(struct lmb_region *rgn, unsigned long r) +{ + unsigned long i; + + for (i = r; i < rgn->cnt - 1; i++) { + rgn->region[i].base = rgn->region[i + 1].base; + rgn->region[i].size = rgn->region[i + 1].size; + } + rgn->cnt--; +} + +/* Assumption: base addr of region 1 < base addr of region 2 */ +static void __init lmb_coalesce_regions(struct lmb_region *rgn, + unsigned long r1, unsigned long r2) +{ + rgn->region[r1].size += rgn->region[r2].size; + lmb_remove_region(rgn, r2); +} + +void __init lmb_init(void) +{ + /* Create a dummy zero size LMB which will get coalesced away later. + * This simplifies the lmb_add() code below... + */ + lmb.memory.region[0].base = 0; + lmb.memory.region[0].size = 0; + lmb.memory.cnt = 1; + + /* Ditto. */ + lmb.reserved.region[0].base = 0; + lmb.reserved.region[0].size = 0; + lmb.reserved.cnt = 1; +} + +void __init lmb_analyze(void) +{ + int i; + + lmb.memory.size = 0; + + for (i = 0; i < lmb.memory.cnt; i++) + lmb.memory.size += lmb.memory.region[i].size; +} + +static long __init lmb_add_region(struct lmb_region *rgn, u64 base, u64 size) +{ + unsigned long coalesced = 0; + long adjacent, i; + + if ((rgn->cnt == 1) && (rgn->region[0].size == 0)) { + rgn->region[0].base = base; + rgn->region[0].size = size; + return 0; + } + + /* First try and coalesce this LMB with another. */ + for (i = 0; i < rgn->cnt; i++) { + u64 rgnbase = rgn->region[i].base; + u64 rgnsize = rgn->region[i].size; + + if ((rgnbase == base) && (rgnsize == size)) + /* Already have this region, so we're done */ + return 0; + + adjacent = lmb_addrs_adjacent(base, size, rgnbase, rgnsize); + if (adjacent > 0) { + rgn->region[i].base -= size; + rgn->region[i].size += size; + coalesced++; + break; + } else if (adjacent < 0) { + rgn->region[i].size += size; + coalesced++; + break; + } + } + + if ((i < rgn->cnt - 1) && lmb_regions_adjacent(rgn, i, i+1)) { + lmb_coalesce_regions(rgn, i, i+1); + coalesced++; + } + + if (coalesced) + return coalesced; + if (rgn->cnt >= MAX_LMB_REGIONS) + return -1; + + /* Couldn't coalesce the LMB, so add it to the sorted table. */ + for (i = rgn->cnt - 1; i >= 0; i--) { + if (base < rgn->region[i].base) { + rgn->region[i+1].base = rgn->region[i].base; + rgn->region[i+1].size = rgn->region[i].size; + } else { + rgn->region[i+1].base = base; + rgn->region[i+1].size = size; + break; + } + } + + if (base < rgn->region[0].base) { + rgn->region[0].base = base; + rgn->region[0].size = size; + } + rgn->cnt++; + + return 0; +} + +long __init lmb_add(u64 base, u64 size) +{ + struct lmb_region *_rgn = &lmb.memory; + + /* On pSeries LPAR systems, the first LMB is our RMO region. */ + if (base == 0) + lmb.rmo_size = size; + + return lmb_add_region(_rgn, base, size); + +} + +long __init lmb_reserve(u64 base, u64 size) +{ + struct lmb_region *_rgn = &lmb.reserved; + + BUG_ON(0 == size); + + return lmb_add_region(_rgn, base, size); +} + +long __init lmb_overlaps_region(struct lmb_region *rgn, u64 base, u64 size) +{ + unsigned long i; + + for (i = 0; i < rgn->cnt; i++) { + u64 rgnbase = rgn->region[i].base; + u64 rgnsize = rgn->region[i].size; + if (lmb_addrs_overlap(base, size, rgnbase, rgnsize)) + break; + } + + return (i < rgn->cnt) ? i : -1; +} + +static u64 lmb_align_down(u64 addr, u64 size) +{ + return addr & ~(size - 1); +} + +static u64 lmb_align_up(u64 addr, u64 size) +{ + return (addr + (size - 1)) & ~(size - 1); +} + +static u64 __init lmb_alloc_nid_unreserved(u64 start, u64 end, + u64 size, u64 align) +{ + u64 base, res_base; + long j; + + base = lmb_align_down((end - size), align); + while (start <= base) { + j = lmb_overlaps_region(&lmb.reserved, base, size); + if (j < 0) { + /* this area isn't reserved, take it */ + if (lmb_add_region(&lmb.reserved, base, + lmb_align_up(size, align)) < 0) + base = ~(u64)0; + return base; + } + res_base = lmb.reserved.region[j].base; + if (res_base < size) + break; + base = lmb_align_down(res_base - size, align); + } + + return ~(u64)0; +} + +static u64 __init lmb_alloc_nid_region(struct lmb_property *mp, + u64 (*nid_range)(u64, u64, int *), + u64 size, u64 align, int nid) +{ + u64 start, end; + + start = mp->base; + end = start + mp->size; + + start = lmb_align_up(start, align); + while (start < end) { + u64 this_end; + int this_nid; + + this_end = nid_range(start, end, &this_nid); + if (this_nid == nid) { + u64 ret = lmb_alloc_nid_unreserved(start, this_end, + size, align); + if (ret != ~(u64)0) + return ret; + } + start = this_end; + } + + return ~(u64)0; +} + +u64 __init lmb_alloc_nid(u64 size, u64 align, int nid, + u64 (*nid_range)(u64 start, u64 end, int *nid)) +{ + struct lmb_region *mem = &lmb.memory; + int i; + + for (i = 0; i < mem->cnt; i++) { + u64 ret = lmb_alloc_nid_region(&mem->region[i], + nid_range, + size, align, nid); + if (ret != ~(u64)0) + return ret; + } + + return lmb_alloc(size, align); +} + +u64 __init lmb_alloc(u64 size, u64 align) +{ + return lmb_alloc_base(size, align, LMB_ALLOC_ANYWHERE); +} + +u64 __init lmb_alloc_base(u64 size, u64 align, u64 max_addr) +{ + u64 alloc; + + alloc = __lmb_alloc_base(size, align, max_addr); + + if (alloc == 0) + panic("ERROR: Failed to allocate 0x%llx bytes below 0x%llx.\n", + (unsigned long long) size, (unsigned long long) max_addr); + + return alloc; +} + +u64 __init __lmb_alloc_base(u64 size, u64 align, u64 max_addr) +{ + long i, j; + u64 base = 0; + u64 res_base; + + BUG_ON(0 == size); + + /* On some platforms, make sure we allocate lowmem */ + /* Note that LMB_REAL_LIMIT may be LMB_ALLOC_ANYWHERE */ + if (max_addr == LMB_ALLOC_ANYWHERE) + max_addr = LMB_REAL_LIMIT; + + for (i = lmb.memory.cnt - 1; i >= 0; i--) { + u64 lmbbase = lmb.memory.region[i].base; + u64 lmbsize = lmb.memory.region[i].size; + + if (lmbsize < size) + continue; + if (max_addr == LMB_ALLOC_ANYWHERE) + base = lmb_align_down(lmbbase + lmbsize - size, align); + else if (lmbbase < max_addr) { + base = min(lmbbase + lmbsize, max_addr); + base = lmb_align_down(base - size, align); + } else + continue; + + while (base && lmbbase <= base) { + j = lmb_overlaps_region(&lmb.reserved, base, size); + if (j < 0) { + /* this area isn't reserved, take it */ + if (lmb_add_region(&lmb.reserved, base, + lmb_align_up(size, align)) < 0) + return 0; + return base; + } + res_base = lmb.reserved.region[j].base; + if (res_base < size) + break; + base = lmb_align_down(res_base - size, align); + } + } + return 0; +} + +/* You must call lmb_analyze() before this. */ +u64 __init lmb_phys_mem_size(void) +{ + return lmb.memory.size; +} + +u64 __init lmb_end_of_DRAM(void) +{ + int idx = lmb.memory.cnt - 1; + + return (lmb.memory.region[idx].base + lmb.memory.region[idx].size); +} + +/* You must call lmb_analyze() after this. */ +void __init lmb_enforce_memory_limit(u64 memory_limit) +{ + unsigned long i; + u64 limit; + struct lmb_property *p; + + if (!memory_limit) + return; + + /* Truncate the lmb regions to satisfy the memory limit. */ + limit = memory_limit; + for (i = 0; i < lmb.memory.cnt; i++) { + if (limit > lmb.memory.region[i].size) { + limit -= lmb.memory.region[i].size; + continue; + } + + lmb.memory.region[i].size = limit; + lmb.memory.cnt = i + 1; + break; + } + + if (lmb.memory.region[0].size < lmb.rmo_size) + lmb.rmo_size = lmb.memory.region[0].size; + + /* And truncate any reserves above the limit also. */ + for (i = 0; i < lmb.reserved.cnt; i++) { + p = &lmb.reserved.region[i]; + + if (p->base > memory_limit) + p->size = 0; + else if ((p->base + p->size) > memory_limit) + p->size = memory_limit - p->base; + + if (p->size == 0) { + lmb_remove_region(&lmb.reserved, i); + i--; + } + } +} + +int __init lmb_is_reserved(u64 addr) +{ + int i; + + for (i = 0; i < lmb.reserved.cnt; i++) { + u64 upper = lmb.reserved.region[i].base + + lmb.reserved.region[i].size - 1; + if ((addr >= lmb.reserved.region[i].base) && (addr <= upper)) + return 1; + } + return 0; +} diff --git a/lib/pcounter.c b/lib/pcounter.c deleted file mode 100644 index 9b56807da93b..000000000000 --- a/lib/pcounter.c +++ /dev/null @@ -1,58 +0,0 @@ -/* - * Define default pcounter functions - * Note that often used pcounters use dedicated functions to get a speed increase. - * (see DEFINE_PCOUNTER/REF_PCOUNTER_MEMBER) - */ - -#include <linux/module.h> -#include <linux/pcounter.h> -#include <linux/smp.h> -#include <linux/cpumask.h> - -static void pcounter_dyn_add(struct pcounter *self, int inc) -{ - per_cpu_ptr(self->per_cpu_values, smp_processor_id())[0] += inc; -} - -static int pcounter_dyn_getval(const struct pcounter *self, int cpu) -{ - return per_cpu_ptr(self->per_cpu_values, cpu)[0]; -} - -int pcounter_getval(const struct pcounter *self) -{ - int res = 0, cpu; - - for_each_possible_cpu(cpu) - res += self->getval(self, cpu); - - return res; -} -EXPORT_SYMBOL_GPL(pcounter_getval); - -int pcounter_alloc(struct pcounter *self) -{ - int rc = 0; - if (self->add == NULL) { - self->per_cpu_values = alloc_percpu(int); - if (self->per_cpu_values != NULL) { - self->add = pcounter_dyn_add; - self->getval = pcounter_dyn_getval; - } else - rc = 1; - } - return rc; -} -EXPORT_SYMBOL_GPL(pcounter_alloc); - -void pcounter_free(struct pcounter *self) -{ - if (self->per_cpu_values != NULL) { - free_percpu(self->per_cpu_values); - self->per_cpu_values = NULL; - self->getval = NULL; - self->add = NULL; - } -} -EXPORT_SYMBOL_GPL(pcounter_free); - diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 65f0e758ec38..bd521716ab1a 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -114,8 +114,7 @@ radix_tree_node_alloc(struct radix_tree_root *root) } } if (ret == NULL) - ret = kmem_cache_alloc(radix_tree_node_cachep, - set_migrateflags(gfp_mask, __GFP_RECLAIMABLE)); + ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); BUG_ON(radix_tree_is_indirect_ptr(ret)); return ret; @@ -150,8 +149,7 @@ int radix_tree_preload(gfp_t gfp_mask) rtp = &__get_cpu_var(radix_tree_preloads); while (rtp->nr < ARRAY_SIZE(rtp->nodes)) { preempt_enable(); - node = kmem_cache_alloc(radix_tree_node_cachep, - set_migrateflags(gfp_mask, __GFP_RECLAIMABLE)); + node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); if (node == NULL) goto out; preempt_disable(); @@ -1098,7 +1096,8 @@ void __init radix_tree_init(void) { radix_tree_node_cachep = kmem_cache_create("radix_tree_node", sizeof(struct radix_tree_node), 0, - SLAB_PANIC, radix_tree_node_ctor); + SLAB_PANIC | SLAB_RECLAIM_ACCOUNT, + radix_tree_node_ctor); radix_tree_init_maxindex(); hotcpu_notifier(radix_tree_callback, 0); } diff --git a/lib/reed_solomon/reed_solomon.c b/lib/reed_solomon/reed_solomon.c index 3ea2db94d5b0..06d04cfa9339 100644 --- a/lib/reed_solomon/reed_solomon.c +++ b/lib/reed_solomon/reed_solomon.c @@ -45,7 +45,6 @@ #include <linux/rslib.h> #include <linux/slab.h> #include <linux/mutex.h> -#include <asm/semaphore.h> /* This list holds all currently allocated rs control structures */ static LIST_HEAD (rslist); diff --git a/lib/scatterlist.c b/lib/scatterlist.c index acca4901046c..b80c21100d78 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -8,6 +8,7 @@ */ #include <linux/module.h> #include <linux/scatterlist.h> +#include <linux/highmem.h> /** * sg_next - return the next scatterlist entry in a list @@ -292,3 +293,104 @@ int sg_alloc_table(struct sg_table *table, unsigned int nents, gfp_t gfp_mask) return ret; } EXPORT_SYMBOL(sg_alloc_table); + +/** + * sg_copy_buffer - Copy data between a linear buffer and an SG list + * @sgl: The SG list + * @nents: Number of SG entries + * @buf: Where to copy from + * @buflen: The number of bytes to copy + * @to_buffer: transfer direction (non zero == from an sg list to a + * buffer, 0 == from a buffer to an sg list + * + * Returns the number of copied bytes. + * + **/ +static size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents, + void *buf, size_t buflen, int to_buffer) +{ + struct scatterlist *sg; + size_t buf_off = 0; + int i; + + WARN_ON(!irqs_disabled()); + + for_each_sg(sgl, sg, nents, i) { + struct page *page; + int n = 0; + unsigned int sg_off = sg->offset; + unsigned int sg_copy = sg->length; + + if (sg_copy > buflen) + sg_copy = buflen; + buflen -= sg_copy; + + while (sg_copy > 0) { + unsigned int page_copy; + void *p; + + page_copy = PAGE_SIZE - sg_off; + if (page_copy > sg_copy) + page_copy = sg_copy; + + page = nth_page(sg_page(sg), n); + p = kmap_atomic(page, KM_BIO_SRC_IRQ); + + if (to_buffer) + memcpy(buf + buf_off, p + sg_off, page_copy); + else { + memcpy(p + sg_off, buf + buf_off, page_copy); + flush_kernel_dcache_page(page); + } + + kunmap_atomic(p, KM_BIO_SRC_IRQ); + + buf_off += page_copy; + sg_off += page_copy; + if (sg_off == PAGE_SIZE) { + sg_off = 0; + n++; + } + sg_copy -= page_copy; + } + + if (!buflen) + break; + } + + return buf_off; +} + +/** + * sg_copy_from_buffer - Copy from a linear buffer to an SG list + * @sgl: The SG list + * @nents: Number of SG entries + * @buf: Where to copy from + * @buflen: The number of bytes to copy + * + * Returns the number of copied bytes. + * + **/ +size_t sg_copy_from_buffer(struct scatterlist *sgl, unsigned int nents, + void *buf, size_t buflen) +{ + return sg_copy_buffer(sgl, nents, buf, buflen, 0); +} +EXPORT_SYMBOL(sg_copy_from_buffer); + +/** + * sg_copy_to_buffer - Copy from an SG list to a linear buffer + * @sgl: The SG list + * @nents: Number of SG entries + * @buf: Where to copy to + * @buflen: The number of bytes to copy + * + * Returns the number of copied bytes. + * + **/ +size_t sg_copy_to_buffer(struct scatterlist *sgl, unsigned int nents, + void *buf, size_t buflen) +{ + return sg_copy_buffer(sgl, nents, buf, buflen, 1); +} +EXPORT_SYMBOL(sg_copy_to_buffer); diff --git a/lib/semaphore-sleepers.c b/lib/semaphore-sleepers.c deleted file mode 100644 index 0198782cdacb..000000000000 --- a/lib/semaphore-sleepers.c +++ /dev/null @@ -1,176 +0,0 @@ -/* - * i386 and x86-64 semaphore implementation. - * - * (C) Copyright 1999 Linus Torvalds - * - * Portions Copyright 1999 Red Hat, Inc. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * rw semaphores implemented November 1999 by Benjamin LaHaise <bcrl@kvack.org> - */ -#include <linux/sched.h> -#include <linux/err.h> -#include <linux/init.h> -#include <asm/semaphore.h> - -/* - * Semaphores are implemented using a two-way counter: - * The "count" variable is decremented for each process - * that tries to acquire the semaphore, while the "sleeping" - * variable is a count of such acquires. - * - * Notably, the inline "up()" and "down()" functions can - * efficiently test if they need to do any extra work (up - * needs to do something only if count was negative before - * the increment operation. - * - * "sleeping" and the contention routine ordering is protected - * by the spinlock in the semaphore's waitqueue head. - * - * Note that these functions are only called when there is - * contention on the lock, and as such all this is the - * "non-critical" part of the whole semaphore business. The - * critical part is the inline stuff in <asm/semaphore.h> - * where we want to avoid any extra jumps and calls. - */ - -/* - * Logic: - * - only on a boundary condition do we need to care. When we go - * from a negative count to a non-negative, we wake people up. - * - when we go from a non-negative count to a negative do we - * (a) synchronize with the "sleeper" count and (b) make sure - * that we're on the wakeup list before we synchronize so that - * we cannot lose wakeup events. - */ - -void __up(struct semaphore *sem) -{ - wake_up(&sem->wait); -} - -void __sched __down(struct semaphore *sem) -{ - struct task_struct *tsk = current; - DECLARE_WAITQUEUE(wait, tsk); - unsigned long flags; - - tsk->state = TASK_UNINTERRUPTIBLE; - spin_lock_irqsave(&sem->wait.lock, flags); - add_wait_queue_exclusive_locked(&sem->wait, &wait); - - sem->sleepers++; - for (;;) { - int sleepers = sem->sleepers; - - /* - * Add "everybody else" into it. They aren't - * playing, because we own the spinlock in - * the wait_queue_head. - */ - if (!atomic_add_negative(sleepers - 1, &sem->count)) { - sem->sleepers = 0; - break; - } - sem->sleepers = 1; /* us - see -1 above */ - spin_unlock_irqrestore(&sem->wait.lock, flags); - - schedule(); - - spin_lock_irqsave(&sem->wait.lock, flags); - tsk->state = TASK_UNINTERRUPTIBLE; - } - remove_wait_queue_locked(&sem->wait, &wait); - wake_up_locked(&sem->wait); - spin_unlock_irqrestore(&sem->wait.lock, flags); - tsk->state = TASK_RUNNING; -} - -int __sched __down_interruptible(struct semaphore *sem) -{ - int retval = 0; - struct task_struct *tsk = current; - DECLARE_WAITQUEUE(wait, tsk); - unsigned long flags; - - tsk->state = TASK_INTERRUPTIBLE; - spin_lock_irqsave(&sem->wait.lock, flags); - add_wait_queue_exclusive_locked(&sem->wait, &wait); - - sem->sleepers++; - for (;;) { - int sleepers = sem->sleepers; - - /* - * With signals pending, this turns into - * the trylock failure case - we won't be - * sleeping, and we* can't get the lock as - * it has contention. Just correct the count - * and exit. - */ - if (signal_pending(current)) { - retval = -EINTR; - sem->sleepers = 0; - atomic_add(sleepers, &sem->count); - break; - } - - /* - * Add "everybody else" into it. They aren't - * playing, because we own the spinlock in - * wait_queue_head. The "-1" is because we're - * still hoping to get the semaphore. - */ - if (!atomic_add_negative(sleepers - 1, &sem->count)) { - sem->sleepers = 0; - break; - } - sem->sleepers = 1; /* us - see -1 above */ - spin_unlock_irqrestore(&sem->wait.lock, flags); - - schedule(); - - spin_lock_irqsave(&sem->wait.lock, flags); - tsk->state = TASK_INTERRUPTIBLE; - } - remove_wait_queue_locked(&sem->wait, &wait); - wake_up_locked(&sem->wait); - spin_unlock_irqrestore(&sem->wait.lock, flags); - - tsk->state = TASK_RUNNING; - return retval; -} - -/* - * Trylock failed - make sure we correct for - * having decremented the count. - * - * We could have done the trylock with a - * single "cmpxchg" without failure cases, - * but then it wouldn't work on a 386. - */ -int __down_trylock(struct semaphore *sem) -{ - int sleepers; - unsigned long flags; - - spin_lock_irqsave(&sem->wait.lock, flags); - sleepers = sem->sleepers + 1; - sem->sleepers = 0; - - /* - * Add "everybody else" and us into it. They aren't - * playing, because we own the spinlock in the - * wait_queue_head. - */ - if (!atomic_add_negative(sleepers, &sem->count)) { - wake_up_locked(&sem->wait); - } - - spin_unlock_irqrestore(&sem->wait.lock, flags); - return 1; -} |