From dd45c9cf687682c9ce256ab14bd8914db77410bb Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Mon, 27 Oct 2008 15:47:12 -0700 Subject: printk: add %pM format specifier for MAC addresses Add format specifiers for printing out six colon-separated bytes: MAC addresses (%pM): xx:xx:xx:xx:xx:xx %#pM is also supported and omits the colon separators. Signed-off-by: Harvey Harrison Signed-off-by: David S. Miller --- lib/vsprintf.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'lib') diff --git a/lib/vsprintf.c b/lib/vsprintf.c index a013bbc2371..0deaaaf2b14 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -581,6 +581,23 @@ static char *resource_string(char *buf, char *end, struct resource *res, int fie return string(buf, end, sym, field_width, precision, flags); } +static char *mac_address_string(char *buf, char *end, u8 *addr, int field_width, + int precision, int flags) +{ + char mac_addr[6 * 3]; /* (6 * 2 hex digits), 5 colons and trailing zero */ + char *p = mac_addr; + int i; + + for (i = 0; i < 6; i++) { + p = pack_hex_byte(p, addr[i]); + if (!(flags & SPECIAL) && i != 5) + *p++ = ':'; + } + *p = '\0'; + + return string(buf, end, mac_addr, field_width, precision, flags & ~SPECIAL); +} + /* * Show a '%p' thing. A kernel extension is that the '%p' is followed * by an extra set of alphanumeric characters that are extended format @@ -592,6 +609,8 @@ static char *resource_string(char *buf, char *end, struct resource *res, int fie * - 'S' For symbolic direct pointers * - 'R' For a struct resource pointer, it prints the range of * addresses (not the name nor the flags) + * - 'M' For a 6-byte MAC address, it prints the address in the + * usual colon-separated hex notation * * Note: The difference between 'S' and 'F' is that on ia64 and ppc64 * function pointers are really function descriptors, which contain a @@ -607,6 +626,8 @@ static char *pointer(const char *fmt, char *buf, char *end, void *ptr, int field return symbol_string(buf, end, ptr, field_width, precision, flags); case 'R': return resource_string(buf, end, ptr, field_width, precision, flags); + case 'M': + return mac_address_string(buf, end, ptr, field_width, precision, flags); } flags |= SMALL; if (field_width == -1) { -- cgit v1.2.3 From 689afa7da106032a3e859ae35494f80dd6eac640 Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Tue, 28 Oct 2008 16:04:44 -0700 Subject: printk: add %p6 format specifier for IPv6 addresses Takes a pointer to a IPv6 address and formats it in the usual colon-separated hex format: xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:xxxx Each 16 bit word is printed in network-endian byteorder. %#p6 is also supported and will omit the colons. %p6 is a replacement for NIP6_FMT and NIP6() %#p6 is a replacement for NIP6_SEQFMT and NIP6() Note that NIP6() took a struct in6_addr whereas this takes a pointer to a struct in6_addr. Signed-off-by: Harvey Harrison Signed-off-by: David S. Miller --- lib/vsprintf.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'lib') diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 0deaaaf2b14..cb5bc04ff82 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -598,6 +598,24 @@ static char *mac_address_string(char *buf, char *end, u8 *addr, int field_width, return string(buf, end, mac_addr, field_width, precision, flags & ~SPECIAL); } +static char *ip6_addr_string(char *buf, char *end, u8 *addr, int field_width, + int precision, int flags) +{ + char ip6_addr[8 * 5]; /* (8 * 4 hex digits), 7 colons and trailing zero */ + char *p = ip6_addr; + int i; + + for (i = 0; i < 8; i++) { + p = pack_hex_byte(p, addr[2 * i]); + p = pack_hex_byte(p, addr[2 * i + 1]); + if (!(flags & SPECIAL) && i != 7) + *p++ = ':'; + } + *p = '\0'; + + return string(buf, end, ip6_addr, field_width, precision, flags & ~SPECIAL); +} + /* * Show a '%p' thing. A kernel extension is that the '%p' is followed * by an extra set of alphanumeric characters that are extended format @@ -611,6 +629,8 @@ static char *mac_address_string(char *buf, char *end, u8 *addr, int field_width, * addresses (not the name nor the flags) * - 'M' For a 6-byte MAC address, it prints the address in the * usual colon-separated hex notation + * - '6' For a IPv6 address prints the address in network-ordered 16 bit hex + * with colon separators * * Note: The difference between 'S' and 'F' is that on ia64 and ppc64 * function pointers are really function descriptors, which contain a @@ -628,6 +648,8 @@ static char *pointer(const char *fmt, char *buf, char *end, void *ptr, int field return resource_string(buf, end, ptr, field_width, precision, flags); case 'M': return mac_address_string(buf, end, ptr, field_width, precision, flags); + case '6': + return ip6_addr_string(buf, end, ptr, field_width, precision, flags); } flags |= SMALL; if (field_width == -1) { -- cgit v1.2.3 From 4aa996066ffc0dba24036c961ee38dfdfbfc061c Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Wed, 29 Oct 2008 12:49:58 -0700 Subject: printk: add %I4, %I6, %i4, %i6 format specifiers For use in printing IPv4, or IPv6 addresses in the usual way: %i4 and %I4 are currently equivalent and print the address in dot-separated decimal x.x.x.x %I6 prints 16-bit network order hex with colon separators: xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:xxxx %i6 omits the colons. Signed-off-by: Harvey Harrison Signed-off-by: David S. Miller --- lib/vsprintf.c | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'lib') diff --git a/lib/vsprintf.c b/lib/vsprintf.c index cb5bc04ff82..a8630063d14 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -616,6 +616,23 @@ static char *ip6_addr_string(char *buf, char *end, u8 *addr, int field_width, return string(buf, end, ip6_addr, field_width, precision, flags & ~SPECIAL); } +static char *ip4_addr_string(char *buf, char *end, u8 *addr, int field_width, + int precision, int flags) +{ + char ip4_addr[4 * 4]; /* (4 * 3 decimal digits), 3 dots and trailing zero */ + char *p = ip4_addr; + int i; + + for (i = 0; i < 4; i++) { + p = put_dec_trunc(p, addr[i]); + if (i != 3) + *p++ = '.'; + } + *p = '\0'; + + return string(buf, end, ip4_addr, field_width, precision, flags & ~SPECIAL); +} + /* * Show a '%p' thing. A kernel extension is that the '%p' is followed * by an extra set of alphanumeric characters that are extended format @@ -629,6 +646,10 @@ static char *ip6_addr_string(char *buf, char *end, u8 *addr, int field_width, * addresses (not the name nor the flags) * - 'M' For a 6-byte MAC address, it prints the address in the * usual colon-separated hex notation + * - 'I' [46] for IPv4/IPv6 addresses printed in the usual way (dot-separated + * decimal for v4 and colon separated network-order 16 bit hex for v6) + * - 'i' [46] for 'raw' IPv4/IPv6 addresses, IPv6 omits the colons, IPv4 is + currently the same * - '6' For a IPv6 address prints the address in network-ordered 16 bit hex * with colon separators * @@ -650,6 +671,16 @@ static char *pointer(const char *fmt, char *buf, char *end, void *ptr, int field return mac_address_string(buf, end, ptr, field_width, precision, flags); case '6': return ip6_addr_string(buf, end, ptr, field_width, precision, flags); + case 'i': + flags |= SPECIAL; + /* Fallthrough */ + case 'I': + if (fmt[1] == '6') + return ip6_addr_string(buf, end, ptr, field_width, precision, flags); + if (fmt[1] == '4') + return ip4_addr_string(buf, end, ptr, field_width, precision, flags); + flags &= ~SPECIAL; + break; } flags |= SMALL; if (field_width == -1) { -- cgit v1.2.3 From 6b9a1066f8d4c57c1b778affd91fc38e1121b6f8 Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Wed, 29 Oct 2008 12:53:10 -0700 Subject: printk: remove %p6 format specifier, fix up comments Signed-off-by: Harvey Harrison Signed-off-by: David S. Miller --- lib/vsprintf.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'lib') diff --git a/lib/vsprintf.c b/lib/vsprintf.c index a8630063d14..dd7cc7fa3e7 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -649,9 +649,7 @@ static char *ip4_addr_string(char *buf, char *end, u8 *addr, int field_width, * - 'I' [46] for IPv4/IPv6 addresses printed in the usual way (dot-separated * decimal for v4 and colon separated network-order 16 bit hex for v6) * - 'i' [46] for 'raw' IPv4/IPv6 addresses, IPv6 omits the colons, IPv4 is - currently the same - * - '6' For a IPv6 address prints the address in network-ordered 16 bit hex - * with colon separators + * currently the same * * Note: The difference between 'S' and 'F' is that on ia64 and ppc64 * function pointers are really function descriptors, which contain a @@ -669,8 +667,6 @@ static char *pointer(const char *fmt, char *buf, char *end, void *ptr, int field return resource_string(buf, end, ptr, field_width, precision, flags); case 'M': return mac_address_string(buf, end, ptr, field_width, precision, flags); - case '6': - return ip6_addr_string(buf, end, ptr, field_width, precision, flags); case 'i': flags |= SPECIAL; /* Fallthrough */ -- cgit v1.2.3 From b9ac99855dcc0316ba2feee2b0d3e578f8315b75 Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Mon, 3 Nov 2008 17:09:55 -0800 Subject: printk: ipv4 address digits printed in reverse order put_dec_trunc prints the digits in reverse order and is reversed inside number(). Continue using put_dec_trunc, but reverse each quad in ip4_addr_string. [Noticed by Julius Volz] Signed-off-by: Harvey Harrison Signed-off-by: David S. Miller --- lib/vsprintf.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/vsprintf.c b/lib/vsprintf.c index dd7cc7fa3e7..6897724ff5d 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -620,11 +620,15 @@ static char *ip4_addr_string(char *buf, char *end, u8 *addr, int field_width, int precision, int flags) { char ip4_addr[4 * 4]; /* (4 * 3 decimal digits), 3 dots and trailing zero */ + char temp[3]; /* hold each IP quad in reverse order */ char *p = ip4_addr; - int i; + int i, digits; for (i = 0; i < 4; i++) { - p = put_dec_trunc(p, addr[i]); + digits = put_dec_trunc(temp, addr[i]) - temp; + /* reverse the digits in the quad */ + while (digits--) + *p++ = temp[digits]; if (i != 3) *p++ = '.'; } -- cgit v1.2.3 From 6cc88bc45ce8043171089c9592da223dfab91823 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 14 Nov 2008 10:39:21 +1100 Subject: CRED: Rename is_single_threaded() to is_wq_single_threaded() Rename is_single_threaded() to is_wq_single_threaded() so that a new is_single_threaded() can be created that refers to tasks rather than waitqueues. Signed-off-by: David Howells Reviewed-by: James Morris Signed-off-by: James Morris --- lib/is_single_threaded.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) create mode 100644 lib/is_single_threaded.c (limited to 'lib') diff --git a/lib/is_single_threaded.c b/lib/is_single_threaded.c new file mode 100644 index 00000000000..f1ed2fe76c6 --- /dev/null +++ b/lib/is_single_threaded.c @@ -0,0 +1,45 @@ +/* Function to determine if a thread group is single threaded or not + * + * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * - Derived from security/selinux/hooks.c + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include + +/** + * is_single_threaded - Determine if a thread group is single-threaded or not + * @p: A task in the thread group in question + * + * This returns true if the thread group to which a task belongs is single + * threaded, false if it is not. + */ +bool is_single_threaded(struct task_struct *p) +{ + struct task_struct *g, *t; + struct mm_struct *mm = p->mm; + + if (atomic_read(&p->signal->count) != 1) + goto no; + + if (atomic_read(&p->mm->mm_users) != 1) { + read_lock(&tasklist_lock); + do_each_thread(g, t) { + if (t->mm == mm && t != p) + goto no_unlock; + } while_each_thread(g, t); + read_unlock(&tasklist_lock); + } + + return true; + +no_unlock: + read_unlock(&tasklist_lock); +no: + return false; +} -- cgit v1.2.3 From d84f4f992cbd76e8f39c488cf0c5d123843923b1 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 14 Nov 2008 10:39:23 +1100 Subject: CRED: Inaugurate COW credentials Inaugurate copy-on-write credentials management. This uses RCU to manage the credentials pointer in the task_struct with respect to accesses by other tasks. A process may only modify its own credentials, and so does not need locking to access or modify its own credentials. A mutex (cred_replace_mutex) is added to the task_struct to control the effect of PTRACE_ATTACHED on credential calculations, particularly with respect to execve(). With this patch, the contents of an active credentials struct may not be changed directly; rather a new set of credentials must be prepared, modified and committed using something like the following sequence of events: struct cred *new = prepare_creds(); int ret = blah(new); if (ret < 0) { abort_creds(new); return ret; } return commit_creds(new); There are some exceptions to this rule: the keyrings pointed to by the active credentials may be instantiated - keyrings violate the COW rule as managing COW keyrings is tricky, given that it is possible for a task to directly alter the keys in a keyring in use by another task. To help enforce this, various pointers to sets of credentials, such as those in the task_struct, are declared const. The purpose of this is compile-time discouragement of altering credentials through those pointers. Once a set of credentials has been made public through one of these pointers, it may not be modified, except under special circumstances: (1) Its reference count may incremented and decremented. (2) The keyrings to which it points may be modified, but not replaced. The only safe way to modify anything else is to create a replacement and commit using the functions described in Documentation/credentials.txt (which will be added by a later patch). This patch and the preceding patches have been tested with the LTP SELinux testsuite. This patch makes several logical sets of alteration: (1) execve(). This now prepares and commits credentials in various places in the security code rather than altering the current creds directly. (2) Temporary credential overrides. do_coredump() and sys_faccessat() now prepare their own credentials and temporarily override the ones currently on the acting thread, whilst preventing interference from other threads by holding cred_replace_mutex on the thread being dumped. This will be replaced in a future patch by something that hands down the credentials directly to the functions being called, rather than altering the task's objective credentials. (3) LSM interface. A number of functions have been changed, added or removed: (*) security_capset_check(), ->capset_check() (*) security_capset_set(), ->capset_set() Removed in favour of security_capset(). (*) security_capset(), ->capset() New. This is passed a pointer to the new creds, a pointer to the old creds and the proposed capability sets. It should fill in the new creds or return an error. All pointers, barring the pointer to the new creds, are now const. (*) security_bprm_apply_creds(), ->bprm_apply_creds() Changed; now returns a value, which will cause the process to be killed if it's an error. (*) security_task_alloc(), ->task_alloc_security() Removed in favour of security_prepare_creds(). (*) security_cred_free(), ->cred_free() New. Free security data attached to cred->security. (*) security_prepare_creds(), ->cred_prepare() New. Duplicate any security data attached to cred->security. (*) security_commit_creds(), ->cred_commit() New. Apply any security effects for the upcoming installation of new security by commit_creds(). (*) security_task_post_setuid(), ->task_post_setuid() Removed in favour of security_task_fix_setuid(). (*) security_task_fix_setuid(), ->task_fix_setuid() Fix up the proposed new credentials for setuid(). This is used by cap_set_fix_setuid() to implicitly adjust capabilities in line with setuid() changes. Changes are made to the new credentials, rather than the task itself as in security_task_post_setuid(). (*) security_task_reparent_to_init(), ->task_reparent_to_init() Removed. Instead the task being reparented to init is referred directly to init's credentials. NOTE! This results in the loss of some state: SELinux's osid no longer records the sid of the thread that forked it. (*) security_key_alloc(), ->key_alloc() (*) security_key_permission(), ->key_permission() Changed. These now take cred pointers rather than task pointers to refer to the security context. (4) sys_capset(). This has been simplified and uses less locking. The LSM functions it calls have been merged. (5) reparent_to_kthreadd(). This gives the current thread the same credentials as init by simply using commit_thread() to point that way. (6) __sigqueue_alloc() and switch_uid() __sigqueue_alloc() can't stop the target task from changing its creds beneath it, so this function gets a reference to the currently applicable user_struct which it then passes into the sigqueue struct it returns if successful. switch_uid() is now called from commit_creds(), and possibly should be folded into that. commit_creds() should take care of protecting __sigqueue_alloc(). (7) [sg]et[ug]id() and co and [sg]et_current_groups. The set functions now all use prepare_creds(), commit_creds() and abort_creds() to build and check a new set of credentials before applying it. security_task_set[ug]id() is called inside the prepared section. This guarantees that nothing else will affect the creds until we've finished. The calling of set_dumpable() has been moved into commit_creds(). Much of the functionality of set_user() has been moved into commit_creds(). The get functions all simply access the data directly. (8) security_task_prctl() and cap_task_prctl(). security_task_prctl() has been modified to return -ENOSYS if it doesn't want to handle a function, or otherwise return the return value directly rather than through an argument. Additionally, cap_task_prctl() now prepares a new set of credentials, even if it doesn't end up using it. (9) Keyrings. A number of changes have been made to the keyrings code: (a) switch_uid_keyring(), copy_keys(), exit_keys() and suid_keys() have all been dropped and built in to the credentials functions directly. They may want separating out again later. (b) key_alloc() and search_process_keyrings() now take a cred pointer rather than a task pointer to specify the security context. (c) copy_creds() gives a new thread within the same thread group a new thread keyring if its parent had one, otherwise it discards the thread keyring. (d) The authorisation key now points directly to the credentials to extend the search into rather pointing to the task that carries them. (e) Installing thread, process or session keyrings causes a new set of credentials to be created, even though it's not strictly necessary for process or session keyrings (they're shared). (10) Usermode helper. The usermode helper code now carries a cred struct pointer in its subprocess_info struct instead of a new session keyring pointer. This set of credentials is derived from init_cred and installed on the new process after it has been cloned. call_usermodehelper_setup() allocates the new credentials and call_usermodehelper_freeinfo() discards them if they haven't been used. A special cred function (prepare_usermodeinfo_creds()) is provided specifically for call_usermodehelper_setup() to call. call_usermodehelper_setkeys() adjusts the credentials to sport the supplied keyring as the new session keyring. (11) SELinux. SELinux has a number of changes, in addition to those to support the LSM interface changes mentioned above: (a) selinux_setprocattr() no longer does its check for whether the current ptracer can access processes with the new SID inside the lock that covers getting the ptracer's SID. Whilst this lock ensures that the check is done with the ptracer pinned, the result is only valid until the lock is released, so there's no point doing it inside the lock. (12) is_single_threaded(). This function has been extracted from selinux_setprocattr() and put into a file of its own in the lib/ directory as join_session_keyring() now wants to use it too. The code in SELinux just checked to see whether a task shared mm_structs with other tasks (CLONE_VM), but that isn't good enough. We really want to know if they're part of the same thread group (CLONE_THREAD). (13) nfsd. The NFS server daemon now has to use the COW credentials to set the credentials it is going to use. It really needs to pass the credentials down to the functions it calls, but it can't do that until other patches in this series have been applied. Signed-off-by: David Howells Acked-by: James Morris Signed-off-by: James Morris --- lib/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/Makefile b/lib/Makefile index 7cb65d85aeb..80fe8a3ec12 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -11,7 +11,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ rbtree.o radix-tree.o dump_stack.o \ idr.o int_sqrt.o extable.o prio_tree.o \ sha1.o irq_regs.o reciprocal_div.o argv_split.o \ - proportions.o prio_heap.o ratelimit.o show_mem.o + proportions.o prio_heap.o ratelimit.o show_mem.o is_single_threaded.o lib-$(CONFIG_MMU) += ioremap.o lib-$(CONFIG_SMP) += cpumask.o -- cgit v1.2.3 From 411c41eea58bd3500cf897e2c27dd5330935a3a8 Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Tue, 25 Nov 2008 00:40:37 -0800 Subject: aoe: remove private mac address format function Add %pm to omit the colons when printing a mac address. Signed-off-by: Harvey Harrison Signed-off-by: David S. Miller --- lib/vsprintf.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'lib') diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 6897724ff5d..3b777025d87 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -669,6 +669,9 @@ static char *pointer(const char *fmt, char *buf, char *end, void *ptr, int field return symbol_string(buf, end, ptr, field_width, precision, flags); case 'R': return resource_string(buf, end, ptr, field_width, precision, flags); + case 'm': + flags |= SPECIAL; + /* Fallthrough */ case 'M': return mac_address_string(buf, end, ptr, field_width, precision, flags); case 'i': -- cgit v1.2.3 From 3ae7020543db0b769538e64d1ce8d51fceff60ca Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 26 Nov 2008 10:02:00 +0100 Subject: debugobjects: add boot parameter default value Impact: add .config driven boot parameter default value Right now debugobjects can only be activated if the debug_objects boot parameter is passed in via the boot command line. Make this more convenient (and randomizable) by also providing a .config method. Enable it by default. (DEBUG_OBJECTS itself is default-off) Signed-off-by: Ingo Molnar --- lib/Kconfig.debug | 8 ++++++++ lib/debugobjects.c | 4 +++- 2 files changed, 11 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index b0f239e443b..124ece1e67a 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -252,6 +252,14 @@ config DEBUG_OBJECTS_TIMERS timer routines to track the life time of timer objects and validate the timer operations. +config DEBUG_OBJECTS_ENABLE_DEFAULT + int "debug_objects bootup default value (0-1)" + range 0 1 + default "1" + depends on DEBUG_OBJECTS + help + Debug objects boot parameter default value + config DEBUG_SLAB bool "Debug slab memory allocations" depends on DEBUG_KERNEL && SLAB diff --git a/lib/debugobjects.c b/lib/debugobjects.c index e3ab374e133..5d99be1fd98 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -45,7 +45,9 @@ static struct kmem_cache *obj_cache; static int debug_objects_maxchain __read_mostly; static int debug_objects_fixups __read_mostly; static int debug_objects_warnings __read_mostly; -static int debug_objects_enabled __read_mostly; +static int debug_objects_enabled __read_mostly + = CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT; + static struct debug_obj_descr *descr_test __read_mostly; static int __init enable_object_debug(char *str) -- cgit v1.2.3 From b93a531e315e97ef00367099e6b5f19651936e20 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Tue, 16 Dec 2008 11:40:27 +0000 Subject: allow bug table entries to use relative pointers (and use it on x86-64) Impact: reduce bug table size This allows reducing the bug table size by half. Perhaps there are other 64-bit architectures that could also make use of this. Signed-off-by: Jan Beulich Signed-off-by: Ingo Molnar --- lib/bug.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/bug.c b/lib/bug.c index bfeafd60ee9..300e41afbf9 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -5,6 +5,8 @@ CONFIG_BUG - emit BUG traps. Nothing happens without this. CONFIG_GENERIC_BUG - enable this code. + CONFIG_GENERIC_BUG_RELATIVE_POINTERS - use 32-bit pointers relative to + the containing struct bug_entry for bug_addr and file. CONFIG_DEBUG_BUGVERBOSE - emit full file+line information for each BUG CONFIG_BUG and CONFIG_DEBUG_BUGVERBOSE are potentially user-settable @@ -43,6 +45,15 @@ extern const struct bug_entry __start___bug_table[], __stop___bug_table[]; +static inline unsigned long bug_addr(const struct bug_entry *bug) +{ +#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS + return bug->bug_addr; +#else + return (unsigned long)bug + bug->bug_addr_disp; +#endif +} + #ifdef CONFIG_MODULES static LIST_HEAD(module_bug_list); @@ -55,7 +66,7 @@ static const struct bug_entry *module_find_bug(unsigned long bugaddr) unsigned i; for (i = 0; i < mod->num_bugs; ++i, ++bug) - if (bugaddr == bug->bug_addr) + if (bugaddr == bug_addr(bug)) return bug; } return NULL; @@ -108,7 +119,7 @@ const struct bug_entry *find_bug(unsigned long bugaddr) const struct bug_entry *bug; for (bug = __start___bug_table; bug < __stop___bug_table; ++bug) - if (bugaddr == bug->bug_addr) + if (bugaddr == bug_addr(bug)) return bug; return module_find_bug(bugaddr); @@ -133,7 +144,11 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs) if (bug) { #ifdef CONFIG_DEBUG_BUGVERBOSE +#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS file = bug->file; +#else + file = (const char *)bug + bug->file_disp; +#endif line = bug->line; #endif warning = (bug->flags & BUGFLAG_WARNING) != 0; -- cgit v1.2.3 From 8c5df16bec8a60bb8589fc232b9e26cac0ed4b2c Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Tue, 16 Dec 2008 12:17:26 -0800 Subject: swiotlb: allow architectures to override swiotlb pool allocation Impact: generalize swiotlb allocation code Architectures may need to allocate memory specially for use with the swiotlb. Create the weak function swiotlb_alloc_boot() and swiotlb_alloc() defaulting to the current behaviour. Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Ian Campbell Signed-off-by: Ingo Molnar --- lib/swiotlb.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'lib') diff --git a/lib/swiotlb.c b/lib/swiotlb.c index 5f6c629a924..abecb285755 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -126,6 +127,16 @@ setup_io_tlb_npages(char *str) __setup("swiotlb=", setup_io_tlb_npages); /* make io_tlb_overflow tunable too? */ +void * __weak swiotlb_alloc_boot(size_t size, unsigned long nslabs) +{ + return alloc_bootmem_low_pages(size); +} + +void * __weak swiotlb_alloc(unsigned order, unsigned long nslabs) +{ + return (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, order); +} + /* * Statically reserve bounce buffer space and initialize bounce buffer data * structures for the software IO TLB used to implement the DMA API. @@ -145,7 +156,7 @@ swiotlb_init_with_default_size(size_t default_size) /* * Get IO TLB memory from the low pages */ - io_tlb_start = alloc_bootmem_low_pages(bytes); + io_tlb_start = swiotlb_alloc_boot(bytes, io_tlb_nslabs); if (!io_tlb_start) panic("Cannot allocate SWIOTLB buffer"); io_tlb_end = io_tlb_start + bytes; @@ -202,8 +213,7 @@ swiotlb_late_init_with_default_size(size_t default_size) bytes = io_tlb_nslabs << IO_TLB_SHIFT; while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) { - io_tlb_start = (char *)__get_free_pages(GFP_DMA | __GFP_NOWARN, - order); + io_tlb_start = swiotlb_alloc(order, io_tlb_nslabs); if (io_tlb_start) break; order--; -- cgit v1.2.3 From 0016fdee927f7aa0f428494bcf11ae60c7470a02 Mon Sep 17 00:00:00 2001 From: Ian Campbell Date: Tue, 16 Dec 2008 12:17:27 -0800 Subject: swiotlb: move some definitions to header Impact: cleanup Signed-off-by: Ian Campbell Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Ingo Molnar --- lib/swiotlb.c | 14 +------------- 1 file changed, 1 insertion(+), 13 deletions(-) (limited to 'lib') diff --git a/lib/swiotlb.c b/lib/swiotlb.c index abecb285755..db724ba7ebf 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include @@ -40,19 +41,6 @@ #define SG_ENT_VIRT_ADDRESS(sg) (sg_virt((sg))) #define SG_ENT_PHYS_ADDRESS(sg) virt_to_bus(SG_ENT_VIRT_ADDRESS(sg)) -/* - * Maximum allowable number of contiguous slabs to map, - * must be a power of 2. What is the appropriate value ? - * The complexity of {map,unmap}_single is linearly dependent on this value. - */ -#define IO_TLB_SEGSIZE 128 - -/* - * log of the size of each IO TLB slab. The number of slabs is command line - * controllable. - */ -#define IO_TLB_SHIFT 11 - #define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT)) /* -- cgit v1.2.3 From a5ddde4a558b3bd1e3dc50e274a0db2ea7a8fd06 Mon Sep 17 00:00:00 2001 From: Ian Campbell Date: Tue, 16 Dec 2008 12:17:29 -0800 Subject: swiotlb: add comment where we handle the overflow of a dma mask on 32 bit Impact: cleanup Signed-off-by: Ian Campbell Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Ingo Molnar --- lib/swiotlb.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'lib') diff --git a/lib/swiotlb.c b/lib/swiotlb.c index db724ba7ebf..1272b23e476 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -301,6 +301,10 @@ map_single(struct device *hwdev, char *buffer, size_t size, int dir) start_dma_addr = virt_to_bus(io_tlb_start) & mask; offset_slots = ALIGN(start_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; + + /* + * Carefully handle integer overflow which can occur when mask == ~0UL. + */ max_slots = mask + 1 ? ALIGN(mask + 1, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT); -- cgit v1.2.3 From e08e1f7adba522378e8d2ae941bf25443866136d Mon Sep 17 00:00:00 2001 From: Ian Campbell Date: Tue, 16 Dec 2008 12:17:30 -0800 Subject: swiotlb: allow architectures to override phys<->bus<->phys conversions Impact: generalize phys<->bus<->phys conversions in the swiotlb code Architectures may need to override these conversions. Implement a __weak hook point containing the default implementation. Signed-off-by: Ian Campbell Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Ingo Molnar --- lib/swiotlb.c | 52 ++++++++++++++++++++++++++++++++++++---------------- 1 file changed, 36 insertions(+), 16 deletions(-) (limited to 'lib') diff --git a/lib/swiotlb.c b/lib/swiotlb.c index 1272b23e476..3494263cdd9 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -125,6 +125,26 @@ void * __weak swiotlb_alloc(unsigned order, unsigned long nslabs) return (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, order); } +dma_addr_t __weak swiotlb_phys_to_bus(phys_addr_t paddr) +{ + return paddr; +} + +phys_addr_t __weak swiotlb_bus_to_phys(dma_addr_t baddr) +{ + return baddr; +} + +static dma_addr_t swiotlb_virt_to_bus(volatile void *address) +{ + return swiotlb_phys_to_bus(virt_to_phys(address)); +} + +static void *swiotlb_bus_to_virt(dma_addr_t address) +{ + return phys_to_virt(swiotlb_bus_to_phys(address)); +} + /* * Statically reserve bounce buffer space and initialize bounce buffer data * structures for the software IO TLB used to implement the DMA API. @@ -168,7 +188,7 @@ swiotlb_init_with_default_size(size_t default_size) panic("Cannot allocate SWIOTLB overflow buffer!\n"); printk(KERN_INFO "Placing software IO TLB between 0x%lx - 0x%lx\n", - virt_to_bus(io_tlb_start), virt_to_bus(io_tlb_end)); + swiotlb_virt_to_bus(io_tlb_start), swiotlb_virt_to_bus(io_tlb_end)); } void __init @@ -250,7 +270,7 @@ swiotlb_late_init_with_default_size(size_t default_size) printk(KERN_INFO "Placing %luMB software IO TLB between 0x%lx - " "0x%lx\n", bytes >> 20, - virt_to_bus(io_tlb_start), virt_to_bus(io_tlb_end)); + swiotlb_virt_to_bus(io_tlb_start), swiotlb_virt_to_bus(io_tlb_end)); return 0; @@ -298,7 +318,7 @@ map_single(struct device *hwdev, char *buffer, size_t size, int dir) unsigned long max_slots; mask = dma_get_seg_boundary(hwdev); - start_dma_addr = virt_to_bus(io_tlb_start) & mask; + start_dma_addr = swiotlb_virt_to_bus(io_tlb_start) & mask; offset_slots = ALIGN(start_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; @@ -475,7 +495,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size, dma_mask = hwdev->coherent_dma_mask; ret = (void *)__get_free_pages(flags, order); - if (ret && !is_buffer_dma_capable(dma_mask, virt_to_bus(ret), size)) { + if (ret && !is_buffer_dma_capable(dma_mask, swiotlb_virt_to_bus(ret), size)) { /* * The allocated memory isn't reachable by the device. * Fall back on swiotlb_map_single(). @@ -496,7 +516,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size, } memset(ret, 0, size); - dev_addr = virt_to_bus(ret); + dev_addr = swiotlb_virt_to_bus(ret); /* Confirm address can be DMA'd by device */ if (!is_buffer_dma_capable(dma_mask, dev_addr, size)) { @@ -556,7 +576,7 @@ dma_addr_t swiotlb_map_single_attrs(struct device *hwdev, void *ptr, size_t size, int dir, struct dma_attrs *attrs) { - dma_addr_t dev_addr = virt_to_bus(ptr); + dma_addr_t dev_addr = swiotlb_virt_to_bus(ptr); void *map; BUG_ON(dir == DMA_NONE); @@ -577,7 +597,7 @@ swiotlb_map_single_attrs(struct device *hwdev, void *ptr, size_t size, map = io_tlb_overflow_buffer; } - dev_addr = virt_to_bus(map); + dev_addr = swiotlb_virt_to_bus(map); /* * Ensure that the address returned is DMA'ble @@ -607,7 +627,7 @@ void swiotlb_unmap_single_attrs(struct device *hwdev, dma_addr_t dev_addr, size_t size, int dir, struct dma_attrs *attrs) { - char *dma_addr = bus_to_virt(dev_addr); + char *dma_addr = swiotlb_bus_to_virt(dev_addr); BUG_ON(dir == DMA_NONE); if (is_swiotlb_buffer(dma_addr)) @@ -637,7 +657,7 @@ static void swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr, size_t size, int dir, int target) { - char *dma_addr = bus_to_virt(dev_addr); + char *dma_addr = swiotlb_bus_to_virt(dev_addr); BUG_ON(dir == DMA_NONE); if (is_swiotlb_buffer(dma_addr)) @@ -668,7 +688,7 @@ swiotlb_sync_single_range(struct device *hwdev, dma_addr_t dev_addr, unsigned long offset, size_t size, int dir, int target) { - char *dma_addr = bus_to_virt(dev_addr) + offset; + char *dma_addr = swiotlb_bus_to_virt(dev_addr) + offset; BUG_ON(dir == DMA_NONE); if (is_swiotlb_buffer(dma_addr)) @@ -724,7 +744,7 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, for_each_sg(sgl, sg, nelems, i) { addr = SG_ENT_VIRT_ADDRESS(sg); - dev_addr = virt_to_bus(addr); + dev_addr = swiotlb_virt_to_bus(addr); if (swiotlb_force || address_needs_mapping(hwdev, dev_addr, sg->length)) { void *map = map_single(hwdev, addr, sg->length, dir); @@ -737,7 +757,7 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, sgl[0].dma_length = 0; return 0; } - sg->dma_address = virt_to_bus(map); + sg->dma_address = swiotlb_virt_to_bus(map); } else sg->dma_address = dev_addr; sg->dma_length = sg->length; @@ -768,7 +788,7 @@ swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl, for_each_sg(sgl, sg, nelems, i) { if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg)) - unmap_single(hwdev, bus_to_virt(sg->dma_address), + unmap_single(hwdev, swiotlb_bus_to_virt(sg->dma_address), sg->dma_length, dir); else if (dir == DMA_FROM_DEVICE) dma_mark_clean(SG_ENT_VIRT_ADDRESS(sg), sg->dma_length); @@ -801,7 +821,7 @@ swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl, for_each_sg(sgl, sg, nelems, i) { if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg)) - sync_single(hwdev, bus_to_virt(sg->dma_address), + sync_single(hwdev, swiotlb_bus_to_virt(sg->dma_address), sg->dma_length, dir, target); else if (dir == DMA_FROM_DEVICE) dma_mark_clean(SG_ENT_VIRT_ADDRESS(sg), sg->dma_length); @@ -825,7 +845,7 @@ swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, int swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr) { - return (dma_addr == virt_to_bus(io_tlb_overflow_buffer)); + return (dma_addr == swiotlb_virt_to_bus(io_tlb_overflow_buffer)); } /* @@ -837,7 +857,7 @@ swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr) int swiotlb_dma_supported(struct device *hwdev, u64 mask) { - return virt_to_bus(io_tlb_end - 1) <= mask; + return swiotlb_virt_to_bus(io_tlb_end - 1) <= mask; } EXPORT_SYMBOL(swiotlb_map_single); -- cgit v1.2.3 From b81ea27b2329bf44b30c427800954f845896d476 Mon Sep 17 00:00:00 2001 From: Ian Campbell Date: Tue, 16 Dec 2008 12:17:31 -0800 Subject: swiotlb: add arch hook to force mapping Impact: generalize the sw-IOTLB range checks Some architectures require special rules to determine whether a range needs mapping or not. This adds a weak function for architectures to override. Signed-off-by: Ian Campbell Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Ingo Molnar --- lib/swiotlb.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/swiotlb.c b/lib/swiotlb.c index 3494263cdd9..d8b09051c45 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -145,6 +145,11 @@ static void *swiotlb_bus_to_virt(dma_addr_t address) return phys_to_virt(swiotlb_bus_to_phys(address)); } +int __weak swiotlb_arch_range_needs_mapping(void *ptr, size_t size) +{ + return 0; +} + /* * Statically reserve bounce buffer space and initialize bounce buffer data * structures for the software IO TLB used to implement the DMA API. @@ -297,6 +302,11 @@ address_needs_mapping(struct device *hwdev, dma_addr_t addr, size_t size) return !is_buffer_dma_capable(dma_get_mask(hwdev), addr, size); } +static inline int range_needs_mapping(void *ptr, size_t size) +{ + return swiotlb_force || swiotlb_arch_range_needs_mapping(ptr, size); +} + static int is_swiotlb_buffer(char *addr) { return addr >= io_tlb_start && addr < io_tlb_end; @@ -585,7 +595,8 @@ swiotlb_map_single_attrs(struct device *hwdev, void *ptr, size_t size, * we can safely return the device addr and not worry about bounce * buffering it. */ - if (!address_needs_mapping(hwdev, dev_addr, size) && !swiotlb_force) + if (!address_needs_mapping(hwdev, dev_addr, size) && + !range_needs_mapping(ptr, size)) return dev_addr; /* @@ -745,7 +756,7 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, for_each_sg(sgl, sg, nelems, i) { addr = SG_ENT_VIRT_ADDRESS(sg); dev_addr = swiotlb_virt_to_bus(addr); - if (swiotlb_force || + if (range_needs_mapping(sg_virt(sg), sg->length) || address_needs_mapping(hwdev, dev_addr, sg->length)) { void *map = map_single(hwdev, addr, sg->length, dir); if (!map) { -- cgit v1.2.3 From 1b548f667c1487d92e794a9f7a67788f49b952d8 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Tue, 16 Dec 2008 12:17:32 -0800 Subject: swiotlb: factor out copy to/from device Impact: generalize IO bounce memcpys Signed-off-by: Ian Campbell Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Ingo Molnar --- lib/swiotlb.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/lib/swiotlb.c b/lib/swiotlb.c index d8b09051c45..a0b4039e288 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -312,6 +312,15 @@ static int is_swiotlb_buffer(char *addr) return addr >= io_tlb_start && addr < io_tlb_end; } +static void +__sync_single(char *buffer, char *dma_addr, size_t size, int dir) +{ + if (dir == DMA_TO_DEVICE) + memcpy(dma_addr, buffer, size); + else + memcpy(buffer, dma_addr, size); +} + /* * Allocates bounce buffer and returns its kernel virtual address. */ @@ -413,7 +422,7 @@ found: for (i = 0; i < nslots; i++) io_tlb_orig_addr[index+i] = buffer + (i << IO_TLB_SHIFT); if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) - memcpy(dma_addr, buffer, size); + __sync_single(buffer, dma_addr, size, DMA_TO_DEVICE); return dma_addr; } @@ -437,7 +446,7 @@ unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir) * bounce... copy the data back into the original buffer * and * delete the bounce buffer. */ - memcpy(buffer, dma_addr, size); + __sync_single(buffer, dma_addr, size, DMA_FROM_DEVICE); /* * Return the buffer to the free list by setting the corresponding @@ -477,13 +486,13 @@ sync_single(struct device *hwdev, char *dma_addr, size_t size, switch (target) { case SYNC_FOR_CPU: if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) - memcpy(buffer, dma_addr, size); + __sync_single(buffer, dma_addr, size, DMA_FROM_DEVICE); else BUG_ON(dir != DMA_TO_DEVICE); break; case SYNC_FOR_DEVICE: if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) - memcpy(dma_addr, buffer, size); + __sync_single(buffer, dma_addr, size, DMA_TO_DEVICE); else BUG_ON(dir != DMA_FROM_DEVICE); break; -- cgit v1.2.3 From ef9b189352f2eb78f14e52996f4780a523b04a49 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Tue, 16 Dec 2008 12:17:33 -0800 Subject: swiotlb: support bouncing of HighMem pages Impact: prepare the swiotlb code for HighMem struct pages This requires us to treat DMA regions in terms of page+offset rather than virtual addressing since a HighMem page may not have a mapping. Signed-off-by: Ian Campbell Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Ingo Molnar --- lib/swiotlb.c | 122 ++++++++++++++++++++++++++++++++++++++++++---------------- 1 file changed, 89 insertions(+), 33 deletions(-) (limited to 'lib') diff --git a/lib/swiotlb.c b/lib/swiotlb.c index a0b4039e288..1661af59391 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include @@ -38,9 +39,6 @@ #define OFFSET(val,align) ((unsigned long) \ ( (val) & ( (align) - 1))) -#define SG_ENT_VIRT_ADDRESS(sg) (sg_virt((sg))) -#define SG_ENT_PHYS_ADDRESS(sg) virt_to_bus(SG_ENT_VIRT_ADDRESS(sg)) - #define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT)) /* @@ -91,7 +89,10 @@ static unsigned int io_tlb_index; * We need to save away the original address corresponding to a mapped entry * for the sync operations. */ -static unsigned char **io_tlb_orig_addr; +static struct swiotlb_phys_addr { + struct page *page; + unsigned int offset; +} *io_tlb_orig_addr; /* * Protect the above data structures in the map and unmap calls @@ -150,6 +151,11 @@ int __weak swiotlb_arch_range_needs_mapping(void *ptr, size_t size) return 0; } +static dma_addr_t swiotlb_sg_to_bus(struct scatterlist *sg) +{ + return swiotlb_phys_to_bus(page_to_phys(sg_page(sg)) + sg->offset); +} + /* * Statically reserve bounce buffer space and initialize bounce buffer data * structures for the software IO TLB used to implement the DMA API. @@ -183,7 +189,7 @@ swiotlb_init_with_default_size(size_t default_size) for (i = 0; i < io_tlb_nslabs; i++) io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE); io_tlb_index = 0; - io_tlb_orig_addr = alloc_bootmem(io_tlb_nslabs * sizeof(char *)); + io_tlb_orig_addr = alloc_bootmem(io_tlb_nslabs * sizeof(struct swiotlb_phys_addr)); /* * Get the overflow emergency buffer @@ -258,12 +264,12 @@ swiotlb_late_init_with_default_size(size_t default_size) io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE); io_tlb_index = 0; - io_tlb_orig_addr = (unsigned char **)__get_free_pages(GFP_KERNEL, - get_order(io_tlb_nslabs * sizeof(char *))); + io_tlb_orig_addr = (struct swiotlb_phys_addr *)__get_free_pages(GFP_KERNEL, + get_order(io_tlb_nslabs * sizeof(struct swiotlb_phys_addr))); if (!io_tlb_orig_addr) goto cleanup3; - memset(io_tlb_orig_addr, 0, io_tlb_nslabs * sizeof(char *)); + memset(io_tlb_orig_addr, 0, io_tlb_nslabs * sizeof(struct swiotlb_phys_addr)); /* * Get the overflow emergency buffer @@ -312,20 +318,59 @@ static int is_swiotlb_buffer(char *addr) return addr >= io_tlb_start && addr < io_tlb_end; } -static void -__sync_single(char *buffer, char *dma_addr, size_t size, int dir) +static struct swiotlb_phys_addr swiotlb_bus_to_phys_addr(char *dma_addr) { - if (dir == DMA_TO_DEVICE) - memcpy(dma_addr, buffer, size); - else - memcpy(buffer, dma_addr, size); + int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT; + struct swiotlb_phys_addr buffer = io_tlb_orig_addr[index]; + buffer.offset += (long)dma_addr & ((1 << IO_TLB_SHIFT) - 1); + buffer.page += buffer.offset >> PAGE_SHIFT; + buffer.offset &= PAGE_SIZE - 1; + return buffer; +} + +static void +__sync_single(struct swiotlb_phys_addr buffer, char *dma_addr, size_t size, int dir) +{ + if (PageHighMem(buffer.page)) { + size_t len, bytes; + char *dev, *host, *kmp; + + len = size; + while (len != 0) { + unsigned long flags; + + bytes = len; + if ((bytes + buffer.offset) > PAGE_SIZE) + bytes = PAGE_SIZE - buffer.offset; + local_irq_save(flags); /* protects KM_BOUNCE_READ */ + kmp = kmap_atomic(buffer.page, KM_BOUNCE_READ); + dev = dma_addr + size - len; + host = kmp + buffer.offset; + if (dir == DMA_FROM_DEVICE) + memcpy(host, dev, bytes); + else + memcpy(dev, host, bytes); + kunmap_atomic(kmp, KM_BOUNCE_READ); + local_irq_restore(flags); + len -= bytes; + buffer.page++; + buffer.offset = 0; + } + } else { + void *v = page_address(buffer.page) + buffer.offset; + + if (dir == DMA_TO_DEVICE) + memcpy(dma_addr, v, size); + else + memcpy(v, dma_addr, size); + } } /* * Allocates bounce buffer and returns its kernel virtual address. */ static void * -map_single(struct device *hwdev, char *buffer, size_t size, int dir) +map_single(struct device *hwdev, struct swiotlb_phys_addr buffer, size_t size, int dir) { unsigned long flags; char *dma_addr; @@ -335,6 +380,7 @@ map_single(struct device *hwdev, char *buffer, size_t size, int dir) unsigned long mask; unsigned long offset_slots; unsigned long max_slots; + struct swiotlb_phys_addr slot_buf; mask = dma_get_seg_boundary(hwdev); start_dma_addr = swiotlb_virt_to_bus(io_tlb_start) & mask; @@ -419,8 +465,13 @@ found: * This is needed when we sync the memory. Then we sync the buffer if * needed. */ - for (i = 0; i < nslots; i++) - io_tlb_orig_addr[index+i] = buffer + (i << IO_TLB_SHIFT); + slot_buf = buffer; + for (i = 0; i < nslots; i++) { + slot_buf.page += slot_buf.offset >> PAGE_SHIFT; + slot_buf.offset &= PAGE_SIZE - 1; + io_tlb_orig_addr[index+i] = slot_buf; + slot_buf.offset += 1 << IO_TLB_SHIFT; + } if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) __sync_single(buffer, dma_addr, size, DMA_TO_DEVICE); @@ -436,12 +487,12 @@ unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir) unsigned long flags; int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT; - char *buffer = io_tlb_orig_addr[index]; + struct swiotlb_phys_addr buffer = swiotlb_bus_to_phys_addr(dma_addr); /* * First, sync the memory before unmapping the entry */ - if (buffer && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL))) + if ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)) /* * bounce... copy the data back into the original buffer * and * delete the bounce buffer. @@ -478,10 +529,7 @@ static void sync_single(struct device *hwdev, char *dma_addr, size_t size, int dir, int target) { - int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT; - char *buffer = io_tlb_orig_addr[index]; - - buffer += ((unsigned long)dma_addr & ((1 << IO_TLB_SHIFT) - 1)); + struct swiotlb_phys_addr buffer = swiotlb_bus_to_phys_addr(dma_addr); switch (target) { case SYNC_FOR_CPU: @@ -529,7 +577,10 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size, * swiotlb_map_single(), which will grab memory from * the lowest available address range. */ - ret = map_single(hwdev, NULL, size, DMA_FROM_DEVICE); + struct swiotlb_phys_addr buffer; + buffer.page = virt_to_page(NULL); + buffer.offset = 0; + ret = map_single(hwdev, buffer, size, DMA_FROM_DEVICE); if (!ret) return NULL; } @@ -597,6 +648,7 @@ swiotlb_map_single_attrs(struct device *hwdev, void *ptr, size_t size, { dma_addr_t dev_addr = swiotlb_virt_to_bus(ptr); void *map; + struct swiotlb_phys_addr buffer; BUG_ON(dir == DMA_NONE); /* @@ -611,7 +663,9 @@ swiotlb_map_single_attrs(struct device *hwdev, void *ptr, size_t size, /* * Oh well, have to allocate and map a bounce buffer. */ - map = map_single(hwdev, ptr, size, dir); + buffer.page = virt_to_page(ptr); + buffer.offset = (unsigned long)ptr & ~PAGE_MASK; + map = map_single(hwdev, buffer, size, dir); if (!map) { swiotlb_full(hwdev, size, dir, 1); map = io_tlb_overflow_buffer; @@ -756,18 +810,20 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, int dir, struct dma_attrs *attrs) { struct scatterlist *sg; - void *addr; + struct swiotlb_phys_addr buffer; dma_addr_t dev_addr; int i; BUG_ON(dir == DMA_NONE); for_each_sg(sgl, sg, nelems, i) { - addr = SG_ENT_VIRT_ADDRESS(sg); - dev_addr = swiotlb_virt_to_bus(addr); + dev_addr = swiotlb_sg_to_bus(sg); if (range_needs_mapping(sg_virt(sg), sg->length) || address_needs_mapping(hwdev, dev_addr, sg->length)) { - void *map = map_single(hwdev, addr, sg->length, dir); + void *map; + buffer.page = sg_page(sg); + buffer.offset = sg->offset; + map = map_single(hwdev, buffer, sg->length, dir); if (!map) { /* Don't panic here, we expect map_sg users to do proper error handling. */ @@ -807,11 +863,11 @@ swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl, BUG_ON(dir == DMA_NONE); for_each_sg(sgl, sg, nelems, i) { - if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg)) + if (sg->dma_address != swiotlb_sg_to_bus(sg)) unmap_single(hwdev, swiotlb_bus_to_virt(sg->dma_address), sg->dma_length, dir); else if (dir == DMA_FROM_DEVICE) - dma_mark_clean(SG_ENT_VIRT_ADDRESS(sg), sg->dma_length); + dma_mark_clean(swiotlb_bus_to_virt(sg->dma_address), sg->dma_length); } } EXPORT_SYMBOL(swiotlb_unmap_sg_attrs); @@ -840,11 +896,11 @@ swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl, BUG_ON(dir == DMA_NONE); for_each_sg(sgl, sg, nelems, i) { - if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg)) + if (sg->dma_address != swiotlb_sg_to_bus(sg)) sync_single(hwdev, swiotlb_bus_to_virt(sg->dma_address), sg->dma_length, dir, target); else if (dir == DMA_FROM_DEVICE) - dma_mark_clean(SG_ENT_VIRT_ADDRESS(sg), sg->dma_length); + dma_mark_clean(swiotlb_bus_to_virt(sg->dma_address), sg->dma_length); } } -- cgit v1.2.3 From 2e5b2b86b65fe36bb8401e5608eb0b7603aa1cab Mon Sep 17 00:00:00 2001 From: Ian Campbell Date: Tue, 16 Dec 2008 12:17:34 -0800 Subject: swiotlb: consolidate swiotlb info message printing Impact: clean up swiotlb printks Remove duplicated swiotlb info printing, and make it more detailed. Signed-off-by: Ian Campbell Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Ingo Molnar --- lib/swiotlb.c | 33 ++++++++++++++++++++++++++++----- 1 file changed, 28 insertions(+), 5 deletions(-) (limited to 'lib') diff --git a/lib/swiotlb.c b/lib/swiotlb.c index 1661af59391..fa2dc4e5f9b 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -156,6 +156,32 @@ static dma_addr_t swiotlb_sg_to_bus(struct scatterlist *sg) return swiotlb_phys_to_bus(page_to_phys(sg_page(sg)) + sg->offset); } +static void swiotlb_print_info(unsigned long bytes) +{ + phys_addr_t pstart, pend; + dma_addr_t bstart, bend; + + pstart = virt_to_phys(io_tlb_start); + pend = virt_to_phys(io_tlb_end); + + bstart = swiotlb_phys_to_bus(pstart); + bend = swiotlb_phys_to_bus(pend); + + printk(KERN_INFO "Placing %luMB software IO TLB between %p - %p\n", + bytes >> 20, io_tlb_start, io_tlb_end); + if (pstart != bstart || pend != bend) + printk(KERN_INFO "software IO TLB at phys %#llx - %#llx" + " bus %#llx - %#llx\n", + (unsigned long long)pstart, + (unsigned long long)pend, + (unsigned long long)bstart, + (unsigned long long)bend); + else + printk(KERN_INFO "software IO TLB at phys %#llx - %#llx\n", + (unsigned long long)pstart, + (unsigned long long)pend); +} + /* * Statically reserve bounce buffer space and initialize bounce buffer data * structures for the software IO TLB used to implement the DMA API. @@ -198,8 +224,7 @@ swiotlb_init_with_default_size(size_t default_size) if (!io_tlb_overflow_buffer) panic("Cannot allocate SWIOTLB overflow buffer!\n"); - printk(KERN_INFO "Placing software IO TLB between 0x%lx - 0x%lx\n", - swiotlb_virt_to_bus(io_tlb_start), swiotlb_virt_to_bus(io_tlb_end)); + swiotlb_print_info(bytes); } void __init @@ -279,9 +304,7 @@ swiotlb_late_init_with_default_size(size_t default_size) if (!io_tlb_overflow_buffer) goto cleanup4; - printk(KERN_INFO "Placing %luMB software IO TLB between 0x%lx - " - "0x%lx\n", bytes >> 20, - swiotlb_virt_to_bus(io_tlb_start), swiotlb_virt_to_bus(io_tlb_end)); + swiotlb_print_info(bytes); return 0; -- cgit v1.2.3 From 64db4cfff99c04cd5f550357edcc8780f96b54a2 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 18 Dec 2008 21:55:32 +0100 Subject: "Tree RCU": scalable classic RCU implementation This patch fixes a long-standing performance bug in classic RCU that results in massive internal-to-RCU lock contention on systems with more than a few hundred CPUs. Although this patch creates a separate flavor of RCU for ease of review and patch maintenance, it is intended to replace classic RCU. This patch still handles stress better than does mainline, so I am still calling it ready for inclusion. This patch is against the -tip tree. Nevertheless, experience on an actual 1000+ CPU machine would still be most welcome. Most of the changes noted below were found while creating an rcutiny (which should permit ejecting the current rcuclassic) and while doing detailed line-by-line documentation. Updates from v9 (http://lkml.org/lkml/2008/12/2/334): o Fixes from remainder of line-by-line code walkthrough, including comment spelling, initialization, undesirable narrowing due to type conversion, removing redundant memory barriers, removing redundant local-variable initialization, and removing redundant local variables. I do not believe that any of these fixes address the CPU-hotplug issues that Andi Kleen was seeing, but please do give it a whirl in case the machine is smarter than I am. A writeup from the walkthrough may be found at the following URL, in case you are suffering from terminal insomnia or masochism: http://www.kernel.org/pub/linux/kernel/people/paulmck/tmp/rcutree-walkthrough.2008.12.16a.pdf o Made rcutree tracing use seq_file, as suggested some time ago by Lai Jiangshan. o Added a .csv variant of the rcudata debugfs trace file, to allow people having thousands of CPUs to drop the data into a spreadsheet. Tested with oocalc and gnumeric. Updated documentation to suit. Updates from v8 (http://lkml.org/lkml/2008/11/15/139): o Fix a theoretical race between grace-period initialization and force_quiescent_state() that could occur if more than three jiffies were required to carry out the grace-period initialization. Which it might, if you had enough CPUs. o Apply Ingo's printk-standardization patch. o Substitute local variables for repeated accesses to global variables. o Fix comment misspellings and redundant (but harmless) increments of ->n_rcu_pending (this latter after having explicitly added it). o Apply checkpatch fixes. Updates from v7 (http://lkml.org/lkml/2008/10/10/291): o Fixed a number of problems noted by Gautham Shenoy, including the cpu-stall-detection bug that he was having difficulty convincing me was real. ;-) o Changed cpu-stall detection to wait for ten seconds rather than three in order to reduce false positive, as suggested by Ingo Molnar. o Produced a design document (http://lwn.net/Articles/305782/). The act of writing this document uncovered a number of both theoretical and "here and now" bugs as noted below. o Fix dynticks_nesting accounting confusion, simplify WARN_ON() condition, fix kerneldoc comments, and add memory barriers in dynticks interface functions. o Add more data to tracing. o Remove unused "rcu_barrier" field from rcu_data structure. o Count calls to rcu_pending() from scheduling-clock interrupt to use as a surrogate timebase should jiffies stop counting. o Fix a theoretical race between force_quiescent_state() and grace-period initialization. Yes, initialization does have to go on for some jiffies for this race to occur, but given enough CPUs... Updates from v6 (http://lkml.org/lkml/2008/9/23/448): o Fix a number of checkpatch.pl complaints. o Apply review comments from Ingo Molnar and Lai Jiangshan on the stall-detection code. o Fix several bugs in !CONFIG_SMP builds. o Fix a misspelled config-parameter name so that RCU now announces at boot time if stall detection is configured. o Run tests on numerous combinations of configurations parameters, which after the fixes above, now build and run correctly. Updates from v5 (http://lkml.org/lkml/2008/9/15/92, bad subject line): o Fix a compiler error in the !CONFIG_FANOUT_EXACT case (blew a changeset some time ago, and finally got around to retesting this option). o Fix some tracing bugs in rcupreempt that caused incorrect totals to be printed. o I now test with a more brutal random-selection online/offline script (attached). Probably more brutal than it needs to be on the people reading it as well, but so it goes. o A number of optimizations and usability improvements: o Make rcu_pending() ignore the grace-period timeout when there is no grace period in progress. o Make force_quiescent_state() avoid going for a global lock in the case where there is no grace period in progress. o Rearrange struct fields to improve struct layout. o Make call_rcu() initiate a grace period if RCU was idle, rather than waiting for the next scheduling clock interrupt. o Invoke rcu_irq_enter() and rcu_irq_exit() only when idle, as suggested by Andi Kleen. I still don't completely trust this change, and might back it out. o Make CONFIG_RCU_TRACE be the single config variable manipulated for all forms of RCU, instead of the prior confusion. o Document tracing files and formats for both rcupreempt and rcutree. Updates from v4 for those missing v5 given its bad subject line: o Separated dynticks interface so that NMIs and irqs call separate functions, greatly simplifying it. In particular, this code no longer requires a proof of correctness. ;-) o Separated dynticks state out into its own per-CPU structure, avoiding the duplicated accounting. o The case where a dynticks-idle CPU runs an irq handler that invokes call_rcu() is now correctly handled, forcing that CPU out of dynticks-idle mode. o Review comments have been applied (thank you all!!!). For but one example, fixed the dynticks-ordering issue that Manfred pointed out, saving me much debugging. ;-) o Adjusted rcuclassic and rcupreempt to handle dynticks changes. Attached is an updated patch to Classic RCU that applies a hierarchy, greatly reducing the contention on the top-level lock for large machines. This passes 10-hour concurrent rcutorture and online-offline testing on 128-CPU ppc64 without dynticks enabled, and exposes some timekeeping bugs in presence of dynticks (exciting working on a system where "sleep 1" hangs until interrupted...), which were fixed in the 2.6.27 kernel. It is getting more reliable than mainline by some measures, so the next version will be against -tip for inclusion. See also Manfred Spraul's recent patches (or his earlier work from 2004 at http://marc.info/?l=linux-kernel&m=108546384711797&w=2). We will converge onto a common patch in the fullness of time, but are currently exploring different regions of the design space. That said, I have already gratefully stolen quite a few of Manfred's ideas. This patch provides CONFIG_RCU_FANOUT, which controls the bushiness of the RCU hierarchy. Defaults to 32 on 32-bit machines and 64 on 64-bit machines. If CONFIG_NR_CPUS is less than CONFIG_RCU_FANOUT, there is no hierarchy. By default, the RCU initialization code will adjust CONFIG_RCU_FANOUT to balance the hierarchy, so strongly NUMA architectures may choose to set CONFIG_RCU_FANOUT_EXACT to disable this balancing, allowing the hierarchy to be exactly aligned to the underlying hardware. Up to two levels of hierarchy are permitted (in addition to the root node), allowing up to 16,384 CPUs on 32-bit systems and up to 262,144 CPUs on 64-bit systems. I just know that I am going to regret saying this, but this seems more than sufficient for the foreseeable future. (Some architectures might wish to set CONFIG_RCU_FANOUT=4, which would limit such architectures to 64 CPUs. If this becomes a real problem, additional levels can be added, but I doubt that it will make a significant difference on real hardware.) In the common case, a given CPU will manipulate its private rcu_data structure and the rcu_node structure that it shares with its immediate neighbors. This can reduce both lock and memory contention by multiple orders of magnitude, which should eliminate the need for the strange manipulations that are reported to be required when running Linux on very large systems. Some shortcomings: o More bugs will probably surface as a result of an ongoing line-by-line code inspection. Patches will be provided as required. o There are probably hangs, rcutorture failures, &c. Seems quite stable on a 128-CPU machine, but that is kind of small compared to 4096 CPUs. However, seems to do better than mainline. Patches will be provided as required. o The memory footprint of this version is several KB larger than rcuclassic. A separate UP-only rcutiny patch will be provided, which will reduce the memory footprint significantly, even compared to the old rcuclassic. One such patch passes light testing, and has a memory footprint smaller even than rcuclassic. Initial reaction from various embedded guys was "it is not worth it", so am putting it aside. Credits: o Manfred Spraul for ideas, review comments, and bugs spotted, as well as some good friendly competition. ;-) o Josh Triplett, Ingo Molnar, Peter Zijlstra, Mathieu Desnoyers, Lai Jiangshan, Andi Kleen, Andy Whitcroft, and Andrew Morton for reviews and comments. o Thomas Gleixner for much-needed help with some timer issues (see patches below). o Jon M. Tollefson, Tim Pepper, Andrew Theurer, Jose R. Santos, Andy Whitcroft, Darrick Wong, Nishanth Aravamudan, Anton Blanchard, Dave Kleikamp, and Nathan Lynch for keeping machines alive despite my heavy abuse^Wtesting. Signed-off-by: Paul E. McKenney Signed-off-by: Ingo Molnar --- lib/Kconfig.debug | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index b0f239e443b..465d822f3f5 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -619,6 +619,19 @@ config RCU_CPU_STALL_DETECTOR Say N if you are unsure. +config RCU_CPU_STALL_DETECTOR + bool "Check for stalled CPUs delaying RCU grace periods" + depends on CLASSIC_RCU || TREE_RCU + default n + help + This option causes RCU to printk information on which + CPUs are delaying the current grace period, but only when + the grace period extends for excessive time periods. + + Say Y if you want RCU to perform such checks. + + Say N if you are unsure. + config KPROBES_SANITY_TEST bool "Kprobes sanity tests" depends on DEBUG_KERNEL -- cgit v1.2.3 From 7b4967c532045a1983d6d4af5c69cc7c5109f62b Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Fri, 19 Dec 2008 16:56:37 +1030 Subject: cpumask: Add alloc_cpumask_var_node() Impact: New API This will be needed in x86 code to allocate the domain and old_domain cpumasks on the same node as where the containing irq_cfg struct is allocated. (Also fixes double-dump_stack on rare CONFIG_DEBUG_PER_CPU_MAPS case) Signed-off-by: Mike Travis Signed-off-by: Rusty Russell (re-impl alloc_cpumask_var) --- lib/cpumask.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'lib') diff --git a/lib/cpumask.c b/lib/cpumask.c index 8d03f22c6ce..3f258f58c85 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -76,15 +76,14 @@ int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) /* These are not inline because of header tangles. */ #ifdef CONFIG_CPUMASK_OFFSTACK -bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) +bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { if (likely(slab_is_available())) - *mask = kmalloc(cpumask_size(), flags); + *mask = kmalloc_node(cpumask_size(), flags, node); else { #ifdef CONFIG_DEBUG_PER_CPU_MAPS printk(KERN_ERR "=> alloc_cpumask_var: kmalloc not available!\n"); - dump_stack(); #endif *mask = NULL; } @@ -96,6 +95,12 @@ bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) #endif return *mask != NULL; } +EXPORT_SYMBOL(alloc_cpumask_var_node); + +bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) +{ + return alloc_cpumask_var_node(mask, flags, numa_node_id()); +} EXPORT_SYMBOL(alloc_cpumask_var); void __init alloc_bootmem_cpumask_var(cpumask_var_t *mask) -- cgit v1.2.3 From ec26b805879c7e77865b39ee91b737985e80006d Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Fri, 19 Dec 2008 16:56:52 +1030 Subject: cpumask: documentation for cpumask_var_t Impact: New kerneldoc comments Additional documentation added to all the alloc_cpumask and free_cpumask functions. Signed-off-by: Mike Travis Signed-off-by: Rusty Russell (minor additions) --- lib/cpumask.c | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) (limited to 'lib') diff --git a/lib/cpumask.c b/lib/cpumask.c index 3f258f58c85..a24edf137f4 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -76,6 +76,20 @@ int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) /* These are not inline because of header tangles. */ #ifdef CONFIG_CPUMASK_OFFSTACK +/** + * alloc_cpumask_var_node - allocate a struct cpumask on a given node + * @mask: pointer to cpumask_var_t where the cpumask is returned + * @flags: GFP_ flags + * + * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is + * a nop returning a constant 1 (in ) + * Returns TRUE if memory allocation succeeded, FALSE otherwise. + * + * In addition, mask will be NULL if this fails. Note that gcc is + * usually smart enough to know that mask can never be NULL if + * CONFIG_CPUMASK_OFFSTACK=n, so does code elimination in that case + * too. + */ bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { if (likely(slab_is_available())) @@ -97,23 +111,52 @@ bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) } EXPORT_SYMBOL(alloc_cpumask_var_node); +/** + * alloc_cpumask_var - allocate a struct cpumask + * @mask: pointer to cpumask_var_t where the cpumask is returned + * @flags: GFP_ flags + * + * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is + * a nop returning a constant 1 (in ). + * + * See alloc_cpumask_var_node. + */ bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var_node(mask, flags, numa_node_id()); } EXPORT_SYMBOL(alloc_cpumask_var); +/** + * alloc_bootmem_cpumask_var - allocate a struct cpumask from the bootmem arena. + * @mask: pointer to cpumask_var_t where the cpumask is returned + * + * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is + * a nop returning a constant 1 (in ) + * Either returns an allocated (zero-filled) cpumask, or causes the + * system to panic. + */ void __init alloc_bootmem_cpumask_var(cpumask_var_t *mask) { *mask = alloc_bootmem(cpumask_size()); } +/** + * free_cpumask_var - frees memory allocated for a struct cpumask. + * @mask: cpumask to free + * + * This is safe on a NULL mask. + */ void free_cpumask_var(cpumask_var_t mask) { kfree(mask); } EXPORT_SYMBOL(free_cpumask_var); +/** + * free_bootmem_cpumask_var - frees result of alloc_bootmem_cpumask_var + * @mask: cpumask to free + */ void __init free_bootmem_cpumask_var(cpumask_var_t mask) { free_bootmem((unsigned long)mask, cpumask_size()); -- cgit v1.2.3 From 69c35efcf1576ab5f00cba83e8ca740923afb6c9 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 7 Nov 2008 15:11:47 +0800 Subject: libcrc32c: Move implementation to crypto crc32c This patch swaps the role of libcrc32c and crc32c. Previously the implementation was in libcrc32c and crc32c was a wrapper. Now the code is in crc32c and libcrc32c just calls the crypto layer. The reason for the change is to tap into the algorithm selection capability of the crypto API so that optimised implementations such as the one utilising Intel's CRC32C instruction can be used where available. Signed-off-by: Herbert Xu --- lib/Kconfig | 1 + lib/libcrc32c.c | 182 ++++++++++---------------------------------------------- 2 files changed, 33 insertions(+), 150 deletions(-) (limited to 'lib') diff --git a/lib/Kconfig b/lib/Kconfig index 85cf7ea978a..ce303f13ed9 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -64,6 +64,7 @@ config CRC7 config LIBCRC32C tristate "CRC32c (Castagnoli, et al) Cyclic Redundancy-Check" + select CRYPTO_CRC32C help This option is provided for the case where no in-kernel-tree modules require CRC32c functions, but a module built outside the diff --git a/lib/libcrc32c.c b/lib/libcrc32c.c index b5c3287d8ea..38b17ab52ff 100644 --- a/lib/libcrc32c.c +++ b/lib/libcrc32c.c @@ -30,168 +30,50 @@ * any later version. * */ -#include -#include -#include - -MODULE_AUTHOR("Clay Haapala "); -MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations"); -MODULE_LICENSE("GPL"); - -#define CRC32C_POLY_BE 0x1EDC6F41 -#define CRC32C_POLY_LE 0x82F63B78 -#ifndef CRC_LE_BITS -# define CRC_LE_BITS 8 -#endif - - -/* - * Haven't generated a big-endian table yet, but the bit-wise version - * should at least work. - */ -#if defined CRC_BE_BITS && CRC_BE_BITS != 1 -#undef CRC_BE_BITS -#endif -#ifndef CRC_BE_BITS -# define CRC_BE_BITS 1 -#endif +#include +#include +#include +#include +#include -EXPORT_SYMBOL(crc32c_le); +static struct crypto_shash *tfm; -#if CRC_LE_BITS == 1 -/* - * Compute things bit-wise, as done in crc32.c. We could share the tight - * loop below with crc32 and vary the POLY if we don't find value in terms - * of space and maintainability in keeping the two modules separate. - */ -u32 __pure -crc32c_le(u32 crc, unsigned char const *p, size_t len) +u32 crc32c(u32 crc, const void *address, unsigned int length) { - int i; - while (len--) { - crc ^= *p++; - for (i = 0; i < 8; i++) - crc = (crc >> 1) ^ ((crc & 1) ? CRC32C_POLY_LE : 0); - } - return crc; -} -#else + struct { + struct shash_desc shash; + char ctx[crypto_shash_descsize(tfm)]; + } desc; + int err; -/* - * This is the CRC-32C table - * Generated with: - * width = 32 bits - * poly = 0x1EDC6F41 - * reflect input bytes = true - * reflect output bytes = true - */ + desc.shash.tfm = tfm; + desc.shash.flags = 0; + *(u32 *)desc.ctx = crc; -static const u32 crc32c_table[256] = { - 0x00000000L, 0xF26B8303L, 0xE13B70F7L, 0x1350F3F4L, - 0xC79A971FL, 0x35F1141CL, 0x26A1E7E8L, 0xD4CA64EBL, - 0x8AD958CFL, 0x78B2DBCCL, 0x6BE22838L, 0x9989AB3BL, - 0x4D43CFD0L, 0xBF284CD3L, 0xAC78BF27L, 0x5E133C24L, - 0x105EC76FL, 0xE235446CL, 0xF165B798L, 0x030E349BL, - 0xD7C45070L, 0x25AFD373L, 0x36FF2087L, 0xC494A384L, - 0x9A879FA0L, 0x68EC1CA3L, 0x7BBCEF57L, 0x89D76C54L, - 0x5D1D08BFL, 0xAF768BBCL, 0xBC267848L, 0x4E4DFB4BL, - 0x20BD8EDEL, 0xD2D60DDDL, 0xC186FE29L, 0x33ED7D2AL, - 0xE72719C1L, 0x154C9AC2L, 0x061C6936L, 0xF477EA35L, - 0xAA64D611L, 0x580F5512L, 0x4B5FA6E6L, 0xB93425E5L, - 0x6DFE410EL, 0x9F95C20DL, 0x8CC531F9L, 0x7EAEB2FAL, - 0x30E349B1L, 0xC288CAB2L, 0xD1D83946L, 0x23B3BA45L, - 0xF779DEAEL, 0x05125DADL, 0x1642AE59L, 0xE4292D5AL, - 0xBA3A117EL, 0x4851927DL, 0x5B016189L, 0xA96AE28AL, - 0x7DA08661L, 0x8FCB0562L, 0x9C9BF696L, 0x6EF07595L, - 0x417B1DBCL, 0xB3109EBFL, 0xA0406D4BL, 0x522BEE48L, - 0x86E18AA3L, 0x748A09A0L, 0x67DAFA54L, 0x95B17957L, - 0xCBA24573L, 0x39C9C670L, 0x2A993584L, 0xD8F2B687L, - 0x0C38D26CL, 0xFE53516FL, 0xED03A29BL, 0x1F682198L, - 0x5125DAD3L, 0xA34E59D0L, 0xB01EAA24L, 0x42752927L, - 0x96BF4DCCL, 0x64D4CECFL, 0x77843D3BL, 0x85EFBE38L, - 0xDBFC821CL, 0x2997011FL, 0x3AC7F2EBL, 0xC8AC71E8L, - 0x1C661503L, 0xEE0D9600L, 0xFD5D65F4L, 0x0F36E6F7L, - 0x61C69362L, 0x93AD1061L, 0x80FDE395L, 0x72966096L, - 0xA65C047DL, 0x5437877EL, 0x4767748AL, 0xB50CF789L, - 0xEB1FCBADL, 0x197448AEL, 0x0A24BB5AL, 0xF84F3859L, - 0x2C855CB2L, 0xDEEEDFB1L, 0xCDBE2C45L, 0x3FD5AF46L, - 0x7198540DL, 0x83F3D70EL, 0x90A324FAL, 0x62C8A7F9L, - 0xB602C312L, 0x44694011L, 0x5739B3E5L, 0xA55230E6L, - 0xFB410CC2L, 0x092A8FC1L, 0x1A7A7C35L, 0xE811FF36L, - 0x3CDB9BDDL, 0xCEB018DEL, 0xDDE0EB2AL, 0x2F8B6829L, - 0x82F63B78L, 0x709DB87BL, 0x63CD4B8FL, 0x91A6C88CL, - 0x456CAC67L, 0xB7072F64L, 0xA457DC90L, 0x563C5F93L, - 0x082F63B7L, 0xFA44E0B4L, 0xE9141340L, 0x1B7F9043L, - 0xCFB5F4A8L, 0x3DDE77ABL, 0x2E8E845FL, 0xDCE5075CL, - 0x92A8FC17L, 0x60C37F14L, 0x73938CE0L, 0x81F80FE3L, - 0x55326B08L, 0xA759E80BL, 0xB4091BFFL, 0x466298FCL, - 0x1871A4D8L, 0xEA1A27DBL, 0xF94AD42FL, 0x0B21572CL, - 0xDFEB33C7L, 0x2D80B0C4L, 0x3ED04330L, 0xCCBBC033L, - 0xA24BB5A6L, 0x502036A5L, 0x4370C551L, 0xB11B4652L, - 0x65D122B9L, 0x97BAA1BAL, 0x84EA524EL, 0x7681D14DL, - 0x2892ED69L, 0xDAF96E6AL, 0xC9A99D9EL, 0x3BC21E9DL, - 0xEF087A76L, 0x1D63F975L, 0x0E330A81L, 0xFC588982L, - 0xB21572C9L, 0x407EF1CAL, 0x532E023EL, 0xA145813DL, - 0x758FE5D6L, 0x87E466D5L, 0x94B49521L, 0x66DF1622L, - 0x38CC2A06L, 0xCAA7A905L, 0xD9F75AF1L, 0x2B9CD9F2L, - 0xFF56BD19L, 0x0D3D3E1AL, 0x1E6DCDEEL, 0xEC064EEDL, - 0xC38D26C4L, 0x31E6A5C7L, 0x22B65633L, 0xD0DDD530L, - 0x0417B1DBL, 0xF67C32D8L, 0xE52CC12CL, 0x1747422FL, - 0x49547E0BL, 0xBB3FFD08L, 0xA86F0EFCL, 0x5A048DFFL, - 0x8ECEE914L, 0x7CA56A17L, 0x6FF599E3L, 0x9D9E1AE0L, - 0xD3D3E1ABL, 0x21B862A8L, 0x32E8915CL, 0xC083125FL, - 0x144976B4L, 0xE622F5B7L, 0xF5720643L, 0x07198540L, - 0x590AB964L, 0xAB613A67L, 0xB831C993L, 0x4A5A4A90L, - 0x9E902E7BL, 0x6CFBAD78L, 0x7FAB5E8CL, 0x8DC0DD8FL, - 0xE330A81AL, 0x115B2B19L, 0x020BD8EDL, 0xF0605BEEL, - 0x24AA3F05L, 0xD6C1BC06L, 0xC5914FF2L, 0x37FACCF1L, - 0x69E9F0D5L, 0x9B8273D6L, 0x88D28022L, 0x7AB90321L, - 0xAE7367CAL, 0x5C18E4C9L, 0x4F48173DL, 0xBD23943EL, - 0xF36E6F75L, 0x0105EC76L, 0x12551F82L, 0xE03E9C81L, - 0x34F4F86AL, 0xC69F7B69L, 0xD5CF889DL, 0x27A40B9EL, - 0x79B737BAL, 0x8BDCB4B9L, 0x988C474DL, 0x6AE7C44EL, - 0xBE2DA0A5L, 0x4C4623A6L, 0x5F16D052L, 0xAD7D5351L -}; + err = crypto_shash_update(&desc.shash, address, length); + BUG_ON(err); -/* - * Steps through buffer one byte at at time, calculates reflected - * crc using table. - */ + return *(u32 *)desc.ctx; +} -u32 __pure -crc32c_le(u32 crc, unsigned char const *data, size_t length) +static int __init libcrc32c_mod_init(void) { - while (length--) - crc = - crc32c_table[(crc ^ *data++) & 0xFFL] ^ (crc >> 8); + tfm = crypto_alloc_shash("crc32c", 0, 0); + if (IS_ERR(tfm)) + return PTR_ERR(tfm); - return crc; + return 0; } -#endif /* CRC_LE_BITS == 8 */ - -EXPORT_SYMBOL(crc32c_be); - -#if CRC_BE_BITS == 1 -u32 __pure -crc32c_be(u32 crc, unsigned char const *p, size_t len) +static void __exit libcrc32c_mod_fini(void) { - int i; - while (len--) { - crc ^= *p++ << 24; - for (i = 0; i < 8; i++) - crc = - (crc << 1) ^ ((crc & 0x80000000) ? CRC32C_POLY_BE : - 0); - } - return crc; + crypto_free_shash(tfm); } -#endif -/* - * Unit test - * - * A small unit test suite is implemented as part of the crypto suite. - * Select CRYPTO_CRC32C and use the tcrypt module to run the tests. - */ +module_init(libcrc32c_mod_init); +module_exit(libcrc32c_mod_fini); + +MODULE_AUTHOR("Clay Haapala "); +MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations"); +MODULE_LICENSE("GPL"); -- cgit v1.2.3 From 53b146ae598268edbe2bf7ea7dfec721d51adddd Mon Sep 17 00:00:00 2001 From: Adrian-Ken Rueegsegger Date: Tue, 11 Nov 2008 12:14:00 +0800 Subject: libcrc32c: Fix "crc32c undefined" compilation error The latest shash changes leave crc32c undefined: [...] Building modules, stage 2. MODPOST 1381 modules ERROR: "crc32c" [net/sctp/sctp.ko] undefined! ERROR: "crc32c" [net/ipv4/netfilter/nf_nat_proto_sctp.ko] undefined! Adding EXPORT_SYMBOL(crc32c) to lib/libcrc32c.c fixes the compile error. This patch has been compile-tested only. Signed-off-by: Adrian-Ken Rueegsegger Signed-off-by: Herbert Xu --- lib/libcrc32c.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'lib') diff --git a/lib/libcrc32c.c b/lib/libcrc32c.c index 38b17ab52ff..244f5480c89 100644 --- a/lib/libcrc32c.c +++ b/lib/libcrc32c.c @@ -57,6 +57,8 @@ u32 crc32c(u32 crc, const void *address, unsigned int length) return *(u32 *)desc.ctx; } +EXPORT_SYMBOL(crc32c); + static int __init libcrc32c_mod_init(void) { tfm = crypto_alloc_shash("crc32c", 0, 0); -- cgit v1.2.3 From 93027354d6e8a66a12dedb89d59b21cf7c2d35ed Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 13 Nov 2008 22:05:13 +0800 Subject: libcrc32c: Select CRYPTO in Kconfig Selecting CRYPTO_CRC32C is not enough as CRYPTO which CRYPTO_CRC32C depends on may be disabled. This patch adds the select on CRYPTO. Signed-off-by: Herbert Xu --- lib/Kconfig | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/Kconfig b/lib/Kconfig index ce303f13ed9..fd4118e097f 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -64,6 +64,7 @@ config CRC7 config LIBCRC32C tristate "CRC32c (Castagnoli, et al) Cyclic Redundancy-Check" + select CRYPTO select CRYPTO_CRC32C help This option is provided for the case where no in-kernel-tree -- cgit v1.2.3 From 773ff60e841461cb1f9374a713ffcda029b8c317 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Tue, 23 Dec 2008 19:37:01 +0900 Subject: SLUB: failslab support Currently fault-injection capability for SLAB allocator is only available to SLAB. This patch makes it available to SLUB, too. [penberg@cs.helsinki.fi: unify slab and slub implementations] Cc: Christoph Lameter Cc: Matt Mackall Signed-off-by: Akinobu Mita Signed-off-by: Pekka Enberg --- lib/Kconfig.debug | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index b0f239e443b..af65ae7f054 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -699,6 +699,7 @@ config FAULT_INJECTION config FAILSLAB bool "Fault-injection capability for kmalloc" depends on FAULT_INJECTION + depends on SLAB || SLUB help Provide fault-injection capability for kmalloc. -- cgit v1.2.3 From e9690a6e4b1615cb0102e425e04b7ce29e7858e2 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 31 Dec 2008 16:45:50 +0800 Subject: cpumask: fix bogus kernel-doc Impact: fix kernel-doc alloc_bootmem_cpumask_var() returns avoid. Signed-off-by: Li Zefan Signed-off-by: Rusty Russell --- lib/cpumask.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/cpumask.c b/lib/cpumask.c index a24edf137f4..8e1496cb63f 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -132,7 +132,7 @@ EXPORT_SYMBOL(alloc_cpumask_var); * @mask: pointer to cpumask_var_t where the cpumask is returned * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is - * a nop returning a constant 1 (in ) + * a nop (in ). * Either returns an allocated (zero-filled) cpumask, or causes the * system to panic. */ -- cgit v1.2.3 From ab53d472e785e51fdfc08fc1d66252c1153e6c0f Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 1 Jan 2009 10:12:19 +1030 Subject: bitmap: find_last_bit() Impact: New API As the name suggests. For the moment everyone uses the generic one. Signed-off-by: Rusty Russell --- lib/Kconfig | 4 ++++ lib/Makefile | 1 + lib/find_last_bit.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 50 insertions(+) create mode 100644 lib/find_last_bit.c (limited to 'lib') diff --git a/lib/Kconfig b/lib/Kconfig index 2ba43c4a5b0..fc5f5ee50bc 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -13,6 +13,10 @@ config GENERIC_FIND_FIRST_BIT config GENERIC_FIND_NEXT_BIT bool +config GENERIC_FIND_LAST_BIT + bool + default y + config CRC_CCITT tristate "CRC-CCITT functions" help diff --git a/lib/Makefile b/lib/Makefile index 80fe8a3ec12..32b0e64ded2 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -37,6 +37,7 @@ lib-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o lib-$(CONFIG_GENERIC_FIND_FIRST_BIT) += find_next_bit.o lib-$(CONFIG_GENERIC_FIND_NEXT_BIT) += find_next_bit.o +lib-$(CONFIG_GENERIC_FIND_LAST_BIT) += find_last_bit.o obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o obj-$(CONFIG_LOCK_KERNEL) += kernel_lock.o obj-$(CONFIG_PLIST) += plist.o diff --git a/lib/find_last_bit.c b/lib/find_last_bit.c new file mode 100644 index 00000000000..5d202e36bdd --- /dev/null +++ b/lib/find_last_bit.c @@ -0,0 +1,45 @@ +/* find_last_bit.c: fallback find next bit implementation + * + * Copyright (C) 2008 IBM Corporation + * Written by Rusty Russell + * (Inspired by David Howell's find_next_bit implementation) + * + * 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 +#include +#include +#include + +unsigned long find_last_bit(const unsigned long *addr, unsigned long size) +{ + unsigned long words; + unsigned long tmp; + + /* Start at final word. */ + words = size / BITS_PER_LONG; + + /* Partial final word? */ + if (size & (BITS_PER_LONG-1)) { + tmp = (addr[words] & (~0UL >> (BITS_PER_LONG + - (size & (BITS_PER_LONG-1))))); + if (tmp) + goto found; + } + + while (words) { + tmp = addr[--words]; + if (tmp) { +found: + return words * BITS_PER_LONG + __fls(tmp); + } + } + + /* Not found */ + return size; +} +EXPORT_SYMBOL(find_last_bit); -- cgit v1.2.3 From 2a53008033189ed09bfe241c6b33811ba4ce980d Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 1 Jan 2009 10:12:30 +1030 Subject: cpumask: zero extra bits in alloc_cpumask_var_node Impact: extra safety checks during transition When CONFIG_CPUMASKS_OFFSTACK is set, the new cpumask_ operators only use bits up to nr_cpu_ids, not NR_CPUS. Using the old cpus_ operators on these masks can mean accessing undefined bits. After some discussion, Mike and I decided to err on the side of caution; we zero the "undefined" bits in alloc_cpumask_var_node() until all the old cpumask functions are removed. Signed-off-by: Rusty Russell --- lib/cpumask.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'lib') diff --git a/lib/cpumask.c b/lib/cpumask.c index 8e1496cb63f..3389e2440da 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -107,6 +107,14 @@ bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) dump_stack(); } #endif + /* FIXME: Bandaid to save us from old primitives which go to NR_CPUS. */ + if (*mask) { + unsigned int tail; + tail = BITS_TO_LONGS(NR_CPUS - nr_cpumask_bits) * sizeof(long); + memset(cpumask_bits(*mask) + cpumask_size() - tail, + 0, tail); + } + return *mask != NULL; } EXPORT_SYMBOL(alloc_cpumask_var_node); -- cgit v1.2.3 From 8c384cdee3e04d6194a2c2b192b624754f990835 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 1 Jan 2009 10:12:30 +1030 Subject: cpumask: CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS Impact: new debug CONFIG options This helps find unconverted code. It currently breaks compile horribly, but we never wanted a flag day so that's expected. Signed-off-by: Rusty Russell --- lib/Kconfig | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'lib') diff --git a/lib/Kconfig b/lib/Kconfig index fc5f5ee50bc..03c2c24b908 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -170,4 +170,8 @@ config CPUMASK_OFFSTACK them on the stack. This is a bit more expensive, but avoids stack overflow. +config DISABLE_OBSOLETE_CPUMASK_FUNCTIONS + bool "Disable obsolete cpumask functions" if DEBUG_PER_CPU_MAPS + depends on EXPERIMENTAL && BROKEN + endmenu -- cgit v1.2.3