From cefb87efc9aa0288849149484870d5ab989fbd59 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Sun, 16 Aug 2009 21:05:45 +1000 Subject: drm/radeon/kms: implement bo busy check + current domain This implements the busy ioctl along with a current domain check. returns 0 or -EBUSY puts the current domain no matter what the answer. Signed-off-by: Dave Airlie --- include/drm/radeon_drm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/radeon_drm.h b/include/drm/radeon_drm.h index af4b4826997e..f81c3232accd 100644 --- a/include/drm/radeon_drm.h +++ b/include/drm/radeon_drm.h @@ -838,7 +838,7 @@ struct drm_radeon_gem_wait_idle { struct drm_radeon_gem_busy { uint32_t handle; - uint32_t busy; + uint32_t domain; }; struct drm_radeon_gem_pread { -- cgit v1.2.3 From 9c0d90103c7e0eb6e638e5b649e9f6d8d9c1b4b3 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Fri, 31 Jul 2009 12:53:58 -0400 Subject: Capabilities: move cap_file_mmap to commoncap.c Currently we duplicate the mmap_min_addr test in cap_file_mmap and in security_file_mmap if !CONFIG_SECURITY. This patch moves cap_file_mmap into commoncap.c and then calls that function directly from security_file_mmap ifndef CONFIG_SECURITY like all of the other capability checks are done. Signed-off-by: Eric Paris Acked-by: Serge Hallyn Signed-off-by: James Morris --- include/linux/security.h | 7 ++++--- security/capability.c | 9 --------- security/commoncap.c | 30 ++++++++++++++++++++++++++++++ 3 files changed, 34 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/security.h b/include/linux/security.h index 5eff459b3833..ac4bc3760b46 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -66,6 +66,9 @@ extern int cap_inode_setxattr(struct dentry *dentry, const char *name, extern int cap_inode_removexattr(struct dentry *dentry, const char *name); extern int cap_inode_need_killpriv(struct dentry *dentry); extern int cap_inode_killpriv(struct dentry *dentry); +extern int cap_file_mmap(struct file *file, unsigned long reqprot, + unsigned long prot, unsigned long flags, + unsigned long addr, unsigned long addr_only); extern int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags); extern int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5); @@ -2197,9 +2200,7 @@ static inline int security_file_mmap(struct file *file, unsigned long reqprot, unsigned long addr, unsigned long addr_only) { - if ((addr < mmap_min_addr) && !capable(CAP_SYS_RAWIO)) - return -EACCES; - return 0; + return cap_file_mmap(file, reqprot, prot, flags, addr, addr_only); } static inline int security_file_mprotect(struct vm_area_struct *vma, diff --git a/security/capability.c b/security/capability.c index 21b6cead6a8e..88f752e8152c 100644 --- a/security/capability.c +++ b/security/capability.c @@ -330,15 +330,6 @@ static int cap_file_ioctl(struct file *file, unsigned int command, return 0; } -static int cap_file_mmap(struct file *file, unsigned long reqprot, - unsigned long prot, unsigned long flags, - unsigned long addr, unsigned long addr_only) -{ - if ((addr < mmap_min_addr) && !capable(CAP_SYS_RAWIO)) - return -EACCES; - return 0; -} - static int cap_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot) { diff --git a/security/commoncap.c b/security/commoncap.c index 48b7e0228fa3..6bcf6e81e547 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -984,3 +984,33 @@ int cap_vm_enough_memory(struct mm_struct *mm, long pages) cap_sys_admin = 1; return __vm_enough_memory(mm, pages, cap_sys_admin); } + +/* + * cap_file_mmap - check if able to map given addr + * @file: unused + * @reqprot: unused + * @prot: unused + * @flags: unused + * @addr: address attempting to be mapped + * @addr_only: unused + * + * If the process is attempting to map memory below mmap_min_addr they need + * CAP_SYS_RAWIO. The other parameters to this function are unused by the + * capability security module. Returns 0 if this mapping should be allowed + * -EPERM if not. + */ +int cap_file_mmap(struct file *file, unsigned long reqprot, + unsigned long prot, unsigned long flags, + unsigned long addr, unsigned long addr_only) +{ + int ret = 0; + + if (addr < mmap_min_addr) { + ret = cap_capable(current, current_cred(), CAP_SYS_RAWIO, + SECURITY_CAP_AUDIT); + /* set PF_SUPERPRIV if it turns out we allow the low mmap */ + if (ret == 0) + current->flags |= PF_SUPERPRIV; + } + return ret; +} -- cgit v1.2.3 From 788084aba2ab7348257597496befcbccabdc98a3 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Fri, 31 Jul 2009 12:54:11 -0400 Subject: Security/SELinux: seperate lsm specific mmap_min_addr Currently SELinux enforcement of controls on the ability to map low memory is determined by the mmap_min_addr tunable. This patch causes SELinux to ignore the tunable and instead use a seperate Kconfig option specific to how much space the LSM should protect. The tunable will now only control the need for CAP_SYS_RAWIO and SELinux permissions will always protect the amount of low memory designated by CONFIG_LSM_MMAP_MIN_ADDR. This allows users who need to disable the mmap_min_addr controls (usual reason being they run WINE as a non-root user) to do so and still have SELinux controls preventing confined domains (like a web server) from being able to map some area of low memory. Signed-off-by: Eric Paris Signed-off-by: James Morris --- include/linux/mm.h | 15 --------------- include/linux/security.h | 17 +++++++++++++++++ kernel/sysctl.c | 7 ++++--- mm/Kconfig | 6 +++--- mm/mmap.c | 3 --- mm/nommu.c | 3 --- security/Kconfig | 16 ++++++++++++++++ security/Makefile | 2 +- security/commoncap.c | 2 +- security/min_addr.c | 49 ++++++++++++++++++++++++++++++++++++++++++++++++ security/selinux/hooks.c | 2 +- 11 files changed, 92 insertions(+), 30 deletions(-) create mode 100644 security/min_addr.c (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index ba3a7cb1eaa0..9a72cc78e6b8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -34,8 +34,6 @@ extern int sysctl_legacy_va_layout; #define sysctl_legacy_va_layout 0 #endif -extern unsigned long mmap_min_addr; - #include #include #include @@ -574,19 +572,6 @@ static inline void set_page_links(struct page *page, enum zone_type zone, set_page_section(page, pfn_to_section_nr(pfn)); } -/* - * If a hint addr is less than mmap_min_addr change hint to be as - * low as possible but still greater than mmap_min_addr - */ -static inline unsigned long round_hint_to_min(unsigned long hint) -{ - hint &= PAGE_MASK; - if (((void *)hint != NULL) && - (hint < mmap_min_addr)) - return PAGE_ALIGN(mmap_min_addr); - return hint; -} - /* * Some inline functions in vmstat.h depend on page_zone() */ diff --git a/include/linux/security.h b/include/linux/security.h index ac4bc3760b46..dc3472c1f781 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -28,6 +28,7 @@ #include #include #include +#include /* PAGE_ALIGN */ #include #include #include @@ -95,6 +96,7 @@ extern int cap_netlink_send(struct sock *sk, struct sk_buff *skb); extern int cap_netlink_recv(struct sk_buff *skb, int cap); extern unsigned long mmap_min_addr; +extern unsigned long dac_mmap_min_addr; /* * Values used in the task_security_ops calls */ @@ -147,6 +149,21 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) opts->num_mnt_opts = 0; } +/* + * If a hint addr is less than mmap_min_addr change hint to be as + * low as possible but still greater than mmap_min_addr + */ +static inline unsigned long round_hint_to_min(unsigned long hint) +{ + hint &= PAGE_MASK; + if (((void *)hint != NULL) && + (hint < mmap_min_addr)) + return PAGE_ALIGN(mmap_min_addr); + return hint; +} + +extern int mmap_min_addr_handler(struct ctl_table *table, int write, struct file *filp, + void __user *buffer, size_t *lenp, loff_t *ppos); /** * struct security_operations - main security structure * diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 98e02328c67d..58be76017fd0 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -49,6 +49,7 @@ #include #include #include +#include #include #include @@ -1306,10 +1307,10 @@ static struct ctl_table vm_table[] = { { .ctl_name = CTL_UNNUMBERED, .procname = "mmap_min_addr", - .data = &mmap_min_addr, - .maxlen = sizeof(unsigned long), + .data = &dac_mmap_min_addr, + .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = &mmap_min_addr_handler, }, #ifdef CONFIG_NUMA { diff --git a/mm/Kconfig b/mm/Kconfig index c948d4ca8bde..fe5f674d7a7d 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -225,9 +225,9 @@ config DEFAULT_MMAP_MIN_ADDR For most ia64, ppc64 and x86 users with lots of address space a value of 65536 is reasonable and should cause no problems. On arm and other archs it should not be higher than 32768. - Programs which use vm86 functionality would either need additional - permissions from either the LSM or the capabilities module or have - this protection disabled. + Programs which use vm86 functionality or have some need to map + this low address space will need CAP_SYS_RAWIO or disable this + protection by setting the value to 0. This value can be changed after boot using the /proc/sys/vm/mmap_min_addr tunable. diff --git a/mm/mmap.c b/mm/mmap.c index 34579b23ebd5..8101de490c73 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -88,9 +88,6 @@ int sysctl_overcommit_ratio = 50; /* default is 50% */ int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT; struct percpu_counter vm_committed_as; -/* amount of vm to protect from userspace access */ -unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR; - /* * Check that a process has enough memory to allocate a new virtual * mapping. 0 means there is enough memory for the allocation to diff --git a/mm/nommu.c b/mm/nommu.c index 53cab10fece4..28754c40be98 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -69,9 +69,6 @@ int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT; int sysctl_nr_trim_pages = CONFIG_NOMMU_INITIAL_TRIM_EXCESS; int heap_stack_gap = 0; -/* amount of vm to protect from userspace access */ -unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR; - atomic_long_t mmap_pages_allocated; EXPORT_SYMBOL(mem_map); diff --git a/security/Kconfig b/security/Kconfig index d23c839038f0..9c60c346a91d 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -113,6 +113,22 @@ config SECURITY_ROOTPLUG If you are unsure how to answer this question, answer N. +config LSM_MMAP_MIN_ADDR + int "Low address space for LSM to from user allocation" + depends on SECURITY && SECURITY_SELINUX + default 65535 + help + This is the portion of low virtual memory which should be protected + from userspace allocation. Keeping a user from writing to low pages + can help reduce the impact of kernel NULL pointer bugs. + + For most ia64, ppc64 and x86 users with lots of address space + a value of 65536 is reasonable and should cause no problems. + On arm and other archs it should not be higher than 32768. + Programs which use vm86 functionality or have some need to map + this low address space will need the permission specific to the + systems running LSM. + source security/selinux/Kconfig source security/smack/Kconfig source security/tomoyo/Kconfig diff --git a/security/Makefile b/security/Makefile index c67557cdaa85..b56e7f9ecbc2 100644 --- a/security/Makefile +++ b/security/Makefile @@ -8,7 +8,7 @@ subdir-$(CONFIG_SECURITY_SMACK) += smack subdir-$(CONFIG_SECURITY_TOMOYO) += tomoyo # always enable default capabilities -obj-y += commoncap.o +obj-y += commoncap.o min_addr.o # Object file lists obj-$(CONFIG_SECURITY) += security.o capability.o diff --git a/security/commoncap.c b/security/commoncap.c index 6bcf6e81e547..e3097c0a1311 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -1005,7 +1005,7 @@ int cap_file_mmap(struct file *file, unsigned long reqprot, { int ret = 0; - if (addr < mmap_min_addr) { + if (addr < dac_mmap_min_addr) { ret = cap_capable(current, current_cred(), CAP_SYS_RAWIO, SECURITY_CAP_AUDIT); /* set PF_SUPERPRIV if it turns out we allow the low mmap */ diff --git a/security/min_addr.c b/security/min_addr.c new file mode 100644 index 000000000000..14cc7b3b8d03 --- /dev/null +++ b/security/min_addr.c @@ -0,0 +1,49 @@ +#include +#include +#include +#include + +/* amount of vm to protect from userspace access by both DAC and the LSM*/ +unsigned long mmap_min_addr; +/* amount of vm to protect from userspace using CAP_SYS_RAWIO (DAC) */ +unsigned long dac_mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR; +/* amount of vm to protect from userspace using the LSM = CONFIG_LSM_MMAP_MIN_ADDR */ + +/* + * Update mmap_min_addr = max(dac_mmap_min_addr, CONFIG_LSM_MMAP_MIN_ADDR) + */ +static void update_mmap_min_addr(void) +{ +#ifdef CONFIG_LSM_MMAP_MIN_ADDR + if (dac_mmap_min_addr > CONFIG_LSM_MMAP_MIN_ADDR) + mmap_min_addr = dac_mmap_min_addr; + else + mmap_min_addr = CONFIG_LSM_MMAP_MIN_ADDR; +#else + mmap_min_addr = dac_mmap_min_addr; +#endif +} + +/* + * sysctl handler which just sets dac_mmap_min_addr = the new value and then + * calls update_mmap_min_addr() so non MAP_FIXED hints get rounded properly + */ +int mmap_min_addr_handler(struct ctl_table *table, int write, struct file *filp, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int ret; + + ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos); + + update_mmap_min_addr(); + + return ret; +} + +int __init init_mmap_min_addr(void) +{ + update_mmap_min_addr(); + + return 0; +} +pure_initcall(init_mmap_min_addr); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index e6d1432b0800..8d8b69c5664e 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3036,7 +3036,7 @@ static int selinux_file_mmap(struct file *file, unsigned long reqprot, * at bad behaviour/exploit that we always want to get the AVC, even * if DAC would have also denied the operation. */ - if (addr < mmap_min_addr) { + if (addr < CONFIG_LSM_MMAP_MIN_ADDR) { rc = avc_has_perm(sid, sid, SECCLASS_MEMPROTECT, MEMPROTECT__MMAP_ZERO, NULL); if (rc) -- cgit v1.2.3 From 1d9959734a1949ea4f2427bd2d8b21ede6b2441c Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Fri, 7 Aug 2009 14:53:57 -0400 Subject: security: define round_hint_to_min in !CONFIG_SECURITY Fix the header files to define round_hint_to_min() and to define mmap_min_addr_handler() in the !CONFIG_SECURITY case. Built and tested with !CONFIG_SECURITY Signed-off-by: Eric Paris Signed-off-by: James Morris --- include/linux/security.h | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/security.h b/include/linux/security.h index dc3472c1f781..1f16eea2017b 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -121,6 +121,21 @@ struct request_sock; #define LSM_UNSAFE_PTRACE 2 #define LSM_UNSAFE_PTRACE_CAP 4 +/* + * If a hint addr is less than mmap_min_addr change hint to be as + * low as possible but still greater than mmap_min_addr + */ +static inline unsigned long round_hint_to_min(unsigned long hint) +{ + hint &= PAGE_MASK; + if (((void *)hint != NULL) && + (hint < mmap_min_addr)) + return PAGE_ALIGN(mmap_min_addr); + return hint; +} +extern int mmap_min_addr_handler(struct ctl_table *table, int write, struct file *filp, + void __user *buffer, size_t *lenp, loff_t *ppos); + #ifdef CONFIG_SECURITY struct security_mnt_opts { @@ -149,21 +164,6 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) opts->num_mnt_opts = 0; } -/* - * If a hint addr is less than mmap_min_addr change hint to be as - * low as possible but still greater than mmap_min_addr - */ -static inline unsigned long round_hint_to_min(unsigned long hint) -{ - hint &= PAGE_MASK; - if (((void *)hint != NULL) && - (hint < mmap_min_addr)) - return PAGE_ALIGN(mmap_min_addr); - return hint; -} - -extern int mmap_min_addr_handler(struct ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos); /** * struct security_operations - main security structure * -- cgit v1.2.3 From c1a8f1f1c8e01eab5862c8db39b49ace814e6c66 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 16 Aug 2009 09:36:49 +0000 Subject: net: restore gnet_stats_basic to previous definition In 5e140dfc1fe87eae27846f193086724806b33c7d "net: reorder struct Qdisc for better SMP performance" the definition of struct gnet_stats_basic changed incompatibly, as copies of this struct are shipped to userland via netlink. Restoring old behavior is not welcome, for performance reason. Fix is to use a private structure for kernel, and teach gnet_stats_copy_basic() to convert from kernel to user land, using legacy structure (struct gnet_stats_basic) Based on a report and initial patch from Michael Spang. Reported-by: Michael Spang Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/gen_stats.h | 5 +++++ include/net/act_api.h | 2 +- include/net/gen_stats.h | 10 +++++----- include/net/netfilter/xt_rateest.h | 2 +- include/net/sch_generic.h | 2 +- net/core/gen_estimator.c | 12 ++++++------ net/core/gen_stats.c | 11 ++++++++--- net/netfilter/xt_RATEEST.c | 2 +- net/sched/sch_atm.c | 2 +- net/sched/sch_cbq.c | 2 +- net/sched/sch_drr.c | 2 +- net/sched/sch_hfsc.c | 2 +- net/sched/sch_htb.c | 2 +- 13 files changed, 33 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/linux/gen_stats.h b/include/linux/gen_stats.h index 0ffa41df0ee8..710e901085d0 100644 --- a/include/linux/gen_stats.h +++ b/include/linux/gen_stats.h @@ -19,6 +19,11 @@ enum { * @packets: number of seen packets */ struct gnet_stats_basic +{ + __u64 bytes; + __u32 packets; +}; +struct gnet_stats_basic_packed { __u64 bytes; __u32 packets; diff --git a/include/net/act_api.h b/include/net/act_api.h index 565eed8fe496..c05fd717c588 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -16,7 +16,7 @@ struct tcf_common { u32 tcfc_capab; int tcfc_action; struct tcf_t tcfc_tm; - struct gnet_stats_basic tcfc_bstats; + struct gnet_stats_basic_packed tcfc_bstats; struct gnet_stats_queue tcfc_qstats; struct gnet_stats_rate_est tcfc_rate_est; spinlock_t tcfc_lock; diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h index d136b5240ef2..c1488553e349 100644 --- a/include/net/gen_stats.h +++ b/include/net/gen_stats.h @@ -28,7 +28,7 @@ extern int gnet_stats_start_copy_compat(struct sk_buff *skb, int type, spinlock_t *lock, struct gnet_dump *d); extern int gnet_stats_copy_basic(struct gnet_dump *d, - struct gnet_stats_basic *b); + struct gnet_stats_basic_packed *b); extern int gnet_stats_copy_rate_est(struct gnet_dump *d, struct gnet_stats_rate_est *r); extern int gnet_stats_copy_queue(struct gnet_dump *d, @@ -37,14 +37,14 @@ extern int gnet_stats_copy_app(struct gnet_dump *d, void *st, int len); extern int gnet_stats_finish_copy(struct gnet_dump *d); -extern int gen_new_estimator(struct gnet_stats_basic *bstats, +extern int gen_new_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_rate_est *rate_est, spinlock_t *stats_lock, struct nlattr *opt); -extern void gen_kill_estimator(struct gnet_stats_basic *bstats, +extern void gen_kill_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_rate_est *rate_est); -extern int gen_replace_estimator(struct gnet_stats_basic *bstats, +extern int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_rate_est *rate_est, spinlock_t *stats_lock, struct nlattr *opt); -extern bool gen_estimator_active(const struct gnet_stats_basic *bstats, +extern bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats, const struct gnet_stats_rate_est *rate_est); #endif diff --git a/include/net/netfilter/xt_rateest.h b/include/net/netfilter/xt_rateest.h index 65d594dffbff..ddbf37e19616 100644 --- a/include/net/netfilter/xt_rateest.h +++ b/include/net/netfilter/xt_rateest.h @@ -8,7 +8,7 @@ struct xt_rateest { spinlock_t lock; struct gnet_estimator params; struct gnet_stats_rate_est rstats; - struct gnet_stats_basic bstats; + struct gnet_stats_basic_packed bstats; }; extern struct xt_rateest *xt_rateest_lookup(const char *name); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 964ffa0d8815..5482e9582f55 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -72,7 +72,7 @@ struct Qdisc */ unsigned long state; struct sk_buff_head q; - struct gnet_stats_basic bstats; + struct gnet_stats_basic_packed bstats; struct gnet_stats_queue qstats; }; diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 78e5bfc454ae..493775f4f2f1 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -81,7 +81,7 @@ struct gen_estimator { struct list_head list; - struct gnet_stats_basic *bstats; + struct gnet_stats_basic_packed *bstats; struct gnet_stats_rate_est *rate_est; spinlock_t *stats_lock; int ewma_log; @@ -165,7 +165,7 @@ static void gen_add_node(struct gen_estimator *est) } static -struct gen_estimator *gen_find_node(const struct gnet_stats_basic *bstats, +struct gen_estimator *gen_find_node(const struct gnet_stats_basic_packed *bstats, const struct gnet_stats_rate_est *rate_est) { struct rb_node *p = est_root.rb_node; @@ -202,7 +202,7 @@ struct gen_estimator *gen_find_node(const struct gnet_stats_basic *bstats, * * NOTE: Called under rtnl_mutex */ -int gen_new_estimator(struct gnet_stats_basic *bstats, +int gen_new_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_rate_est *rate_est, spinlock_t *stats_lock, struct nlattr *opt) @@ -262,7 +262,7 @@ static void __gen_kill_estimator(struct rcu_head *head) * * NOTE: Called under rtnl_mutex */ -void gen_kill_estimator(struct gnet_stats_basic *bstats, +void gen_kill_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_rate_est *rate_est) { struct gen_estimator *e; @@ -292,7 +292,7 @@ EXPORT_SYMBOL(gen_kill_estimator); * * Returns 0 on success or a negative error code. */ -int gen_replace_estimator(struct gnet_stats_basic *bstats, +int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_rate_est *rate_est, spinlock_t *stats_lock, struct nlattr *opt) { @@ -308,7 +308,7 @@ EXPORT_SYMBOL(gen_replace_estimator); * * Returns true if estimator is active, and false if not. */ -bool gen_estimator_active(const struct gnet_stats_basic *bstats, +bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats, const struct gnet_stats_rate_est *rate_est) { ASSERT_RTNL(); diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index c3d0ffeac243..8569310268ab 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -106,16 +106,21 @@ gnet_stats_start_copy(struct sk_buff *skb, int type, spinlock_t *lock, * if the room in the socket buffer was not sufficient. */ int -gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic *b) +gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic_packed *b) { if (d->compat_tc_stats) { d->tc_stats.bytes = b->bytes; d->tc_stats.packets = b->packets; } - if (d->tail) - return gnet_stats_copy(d, TCA_STATS_BASIC, b, sizeof(*b)); + if (d->tail) { + struct gnet_stats_basic sb; + memset(&sb, 0, sizeof(sb)); + sb.bytes = b->bytes; + sb.packets = b->packets; + return gnet_stats_copy(d, TCA_STATS_BASIC, &sb, sizeof(sb)); + } return 0; } diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c index 43f5676b1af4..d80b8192e0d4 100644 --- a/net/netfilter/xt_RATEEST.c +++ b/net/netfilter/xt_RATEEST.c @@ -74,7 +74,7 @@ static unsigned int xt_rateest_tg(struct sk_buff *skb, const struct xt_target_param *par) { const struct xt_rateest_target_info *info = par->targinfo; - struct gnet_stats_basic *stats = &info->est->bstats; + struct gnet_stats_basic_packed *stats = &info->est->bstats; spin_lock_bh(&info->est->lock); stats->bytes += skb->len; diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 2a8b83af7c47..ab82f145f689 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -49,7 +49,7 @@ struct atm_flow_data { struct socket *sock; /* for closing */ u32 classid; /* x:y type ID */ int ref; /* reference count */ - struct gnet_stats_basic bstats; + struct gnet_stats_basic_packed bstats; struct gnet_stats_queue qstats; struct atm_flow_data *next; struct atm_flow_data *excess; /* flow for excess traffic; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 23a167670fd5..d5798e17a832 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -128,7 +128,7 @@ struct cbq_class long avgidle; long deficit; /* Saved deficit for WRR */ psched_time_t penalized; - struct gnet_stats_basic bstats; + struct gnet_stats_basic_packed bstats; struct gnet_stats_queue qstats; struct gnet_stats_rate_est rate_est; struct tc_cbq_xstats xstats; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 7597fe146866..12b2fb04b29b 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -22,7 +22,7 @@ struct drr_class { unsigned int refcnt; unsigned int filter_cnt; - struct gnet_stats_basic bstats; + struct gnet_stats_basic_packed bstats; struct gnet_stats_queue qstats; struct gnet_stats_rate_est rate_est; struct list_head alist; diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 362c2811b2df..dad0144423da 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -116,7 +116,7 @@ struct hfsc_class struct Qdisc_class_common cl_common; unsigned int refcnt; /* usage count */ - struct gnet_stats_basic bstats; + struct gnet_stats_basic_packed bstats; struct gnet_stats_queue qstats; struct gnet_stats_rate_est rate_est; unsigned int level; /* class level in hierarchy */ diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 88cd02626621..ec4d46399d59 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -74,7 +74,7 @@ enum htb_cmode { struct htb_class { struct Qdisc_class_common common; /* general class parameters */ - struct gnet_stats_basic bstats; + struct gnet_stats_basic_packed bstats; struct gnet_stats_queue qstats; struct gnet_stats_rate_est rate_est; struct tc_htb_xstats xstats; /* our special stats */ -- cgit v1.2.3 From 0753ba01e126020bf0f8150934903b48935b697d Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Tue, 18 Aug 2009 14:11:10 -0700 Subject: mm: revert "oom: move oom_adj value" The commit 2ff05b2b (oom: move oom_adj value) moveed the oom_adj value to the mm_struct. It was a very good first step for sanitize OOM. However Paul Menage reported the commit makes regression to his job scheduler. Current OOM logic can kill OOM_DISABLED process. Why? His program has the code of similar to the following. ... set_oom_adj(OOM_DISABLE); /* The job scheduler never killed by oom */ ... if (vfork() == 0) { set_oom_adj(0); /* Invoked child can be killed */ execve("foo-bar-cmd"); } .... vfork() parent and child are shared the same mm_struct. then above set_oom_adj(0) doesn't only change oom_adj for vfork() child, it's also change oom_adj for vfork() parent. Then, vfork() parent (job scheduler) lost OOM immune and it was killed. Actually, fork-setting-exec idiom is very frequently used in userland program. We must not break this assumption. Then, this patch revert commit 2ff05b2b and related commit. Reverted commit list --------------------- - commit 2ff05b2b4e (oom: move oom_adj value from task_struct to mm_struct) - commit 4d8b9135c3 (oom: avoid unnecessary mm locking and scanning for OOM_DISABLE) - commit 8123681022 (oom: only oom kill exiting tasks with attached memory) - commit 933b787b57 (mm: copy over oom_adj value at fork time) Signed-off-by: KOSAKI Motohiro Cc: Paul Menage Cc: David Rientjes Cc: KAMEZAWA Hiroyuki Cc: Rik van Riel Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Nick Piggin Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/proc.txt | 15 +++------ fs/proc/base.c | 19 ++--------- include/linux/mm_types.h | 2 -- include/linux/sched.h | 1 + kernel/fork.c | 1 - mm/oom_kill.c | 64 +++++++++++++++++++++++--------------- 6 files changed, 48 insertions(+), 54 deletions(-) (limited to 'include') diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index fad18f9456e4..ffead13f9443 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -1167,13 +1167,11 @@ CHAPTER 3: PER-PROCESS PARAMETERS 3.1 /proc//oom_adj - Adjust the oom-killer score ------------------------------------------------------ -This file can be used to adjust the score used to select which processes should -be killed in an out-of-memory situation. The oom_adj value is a characteristic -of the task's mm, so all threads that share an mm with pid will have the same -oom_adj value. A high value will increase the likelihood of this process being -killed by the oom-killer. Valid values are in the range -16 to +15 as -explained below and a special value of -17, which disables oom-killing -altogether for threads sharing pid's mm. +This file can be used to adjust the score used to select which processes +should be killed in an out-of-memory situation. Giving it a high score will +increase the likelihood of this process being killed by the oom-killer. Valid +values are in the range -16 to +15, plus the special value -17, which disables +oom-killing altogether for this process. The process to be killed in an out-of-memory situation is selected among all others based on its badness score. This value equals the original memory size of the process @@ -1187,9 +1185,6 @@ the parent's score if they do not share the same memory. Thus forking servers are the prime candidates to be killed. Having only one 'hungry' child will make parent less preferable than the child. -/proc//oom_adj cannot be changed for kthreads since they are immune from -oom-killing already. - /proc//oom_score shows process' current badness score. The following heuristics are then applied: diff --git a/fs/proc/base.c b/fs/proc/base.c index 175db258942f..6f742f6658a9 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1003,12 +1003,7 @@ static ssize_t oom_adjust_read(struct file *file, char __user *buf, if (!task) return -ESRCH; - task_lock(task); - if (task->mm) - oom_adjust = task->mm->oom_adj; - else - oom_adjust = OOM_DISABLE; - task_unlock(task); + oom_adjust = task->oomkilladj; put_task_struct(task); len = snprintf(buffer, sizeof(buffer), "%i\n", oom_adjust); @@ -1037,19 +1032,11 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf, task = get_proc_task(file->f_path.dentry->d_inode); if (!task) return -ESRCH; - task_lock(task); - if (!task->mm) { - task_unlock(task); - put_task_struct(task); - return -EINVAL; - } - if (oom_adjust < task->mm->oom_adj && !capable(CAP_SYS_RESOURCE)) { - task_unlock(task); + if (oom_adjust < task->oomkilladj && !capable(CAP_SYS_RESOURCE)) { put_task_struct(task); return -EACCES; } - task->mm->oom_adj = oom_adjust; - task_unlock(task); + task->oomkilladj = oom_adjust; put_task_struct(task); if (end - buffer == 0) return -EIO; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7acc8439d9b3..0042090a4d70 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -240,8 +240,6 @@ struct mm_struct { unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ - s8 oom_adj; /* OOM kill score adjustment (bit shift) */ - cpumask_t cpu_vm_mask; /* Architecture-specific MM context */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 3ab08e4bb6b8..0f1ea4a66957 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1198,6 +1198,7 @@ struct task_struct { * a short time */ unsigned char fpu_counter; + s8 oomkilladj; /* OOM kill score adjustment (bit shift). */ #ifdef CONFIG_BLK_DEV_IO_TRACE unsigned int btrace_seq; #endif diff --git a/kernel/fork.c b/kernel/fork.c index 021e1138556e..144326b7af50 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -426,7 +426,6 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) init_rwsem(&mm->mmap_sem); INIT_LIST_HEAD(&mm->mmlist); mm->flags = (current->mm) ? current->mm->flags : default_dump_filter; - mm->oom_adj = (current->mm) ? current->mm->oom_adj : 0; mm->core_state = NULL; mm->nr_ptes = 0; set_mm_counter(mm, file_rss, 0); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 175a67a78a99..a7b2460e922b 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -58,7 +58,6 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) unsigned long points, cpu_time, run_time; struct mm_struct *mm; struct task_struct *child; - int oom_adj; task_lock(p); mm = p->mm; @@ -66,11 +65,6 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) task_unlock(p); return 0; } - oom_adj = mm->oom_adj; - if (oom_adj == OOM_DISABLE) { - task_unlock(p); - return 0; - } /* * The memory size of the process is the basis for the badness. @@ -154,15 +148,15 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) points /= 8; /* - * Adjust the score by oom_adj. + * Adjust the score by oomkilladj. */ - if (oom_adj) { - if (oom_adj > 0) { + if (p->oomkilladj) { + if (p->oomkilladj > 0) { if (!points) points = 1; - points <<= oom_adj; + points <<= p->oomkilladj; } else - points >>= -(oom_adj); + points >>= -(p->oomkilladj); } #ifdef DEBUG @@ -257,8 +251,11 @@ static struct task_struct *select_bad_process(unsigned long *ppoints, *ppoints = ULONG_MAX; } + if (p->oomkilladj == OOM_DISABLE) + continue; + points = badness(p, uptime.tv_sec); - if (points > *ppoints) { + if (points > *ppoints || !chosen) { chosen = p; *ppoints = points; } @@ -307,7 +304,8 @@ static void dump_tasks(const struct mem_cgroup *mem) } printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3d %3d %s\n", p->pid, __task_cred(p)->uid, p->tgid, mm->total_vm, - get_mm_rss(mm), (int)task_cpu(p), mm->oom_adj, p->comm); + get_mm_rss(mm), (int)task_cpu(p), p->oomkilladj, + p->comm); task_unlock(p); } while_each_thread(g, p); } @@ -325,8 +323,11 @@ static void __oom_kill_task(struct task_struct *p, int verbose) return; } - if (!p->mm) + if (!p->mm) { + WARN_ON(1); + printk(KERN_WARNING "tried to kill an mm-less task!\n"); return; + } if (verbose) printk(KERN_ERR "Killed process %d (%s)\n", @@ -348,13 +349,28 @@ static int oom_kill_task(struct task_struct *p) struct mm_struct *mm; struct task_struct *g, *q; - task_lock(p); mm = p->mm; - if (!mm || mm->oom_adj == OOM_DISABLE) { - task_unlock(p); + + /* WARNING: mm may not be dereferenced since we did not obtain its + * value from get_task_mm(p). This is OK since all we need to do is + * compare mm to q->mm below. + * + * Furthermore, even if mm contains a non-NULL value, p->mm may + * change to NULL at any time since we do not hold task_lock(p). + * However, this is of no concern to us. + */ + + if (mm == NULL) return 1; - } - task_unlock(p); + + /* + * Don't kill the process if any threads are set to OOM_DISABLE + */ + do_each_thread(g, q) { + if (q->mm == mm && q->oomkilladj == OOM_DISABLE) + return 1; + } while_each_thread(g, q); + __oom_kill_task(p, 1); /* @@ -377,11 +393,10 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, struct task_struct *c; if (printk_ratelimit()) { - task_lock(current); printk(KERN_WARNING "%s invoked oom-killer: " - "gfp_mask=0x%x, order=%d, oom_adj=%d\n", - current->comm, gfp_mask, order, - current->mm ? current->mm->oom_adj : OOM_DISABLE); + "gfp_mask=0x%x, order=%d, oomkilladj=%d\n", + current->comm, gfp_mask, order, current->oomkilladj); + task_lock(current); cpuset_print_task_mems_allowed(current); task_unlock(current); dump_stack(); @@ -394,9 +409,8 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, /* * If the task is already exiting, don't alarm the sysadmin or kill * its children or threads, just set TIF_MEMDIE so it can die quickly - * if its mm is still attached. */ - if (p->mm && (p->flags & PF_EXITING)) { + if (p->flags & PF_EXITING) { __oom_kill_task(p, 0); return 0; } -- cgit v1.2.3 From e3b2415e281a97ade36d88404094a90cfea838c0 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Fri, 21 Aug 2009 09:47:45 +1000 Subject: drm/radeon/kms: implement the bo busy ioctl properly. The previous patch assumes the ioctl already existed, when it actually didn't. It also didn't return the correct error code. Signed-off-by: Dave Airlie --- drivers/gpu/drm/radeon/radeon_gem.c | 2 +- drivers/gpu/drm/radeon/radeon_kms.c | 1 + include/drm/radeon_drm.h | 2 ++ 3 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index d4ceff13bbb1..14c199802920 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -283,7 +283,7 @@ int radeon_gem_busy_ioctl(struct drm_device *dev, void *data, mutex_lock(&dev->struct_mutex); drm_gem_object_unreference(gobj); mutex_unlock(&dev->struct_mutex); - return 0; + return r; } int radeon_gem_wait_idle_ioctl(struct drm_device *dev, void *data, diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index d2764bf6b2a2..11ed672543b1 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -318,5 +318,6 @@ struct drm_ioctl_desc radeon_ioctls_kms[] = { DRM_IOCTL_DEF(DRM_RADEON_INFO, radeon_info_ioctl, DRM_AUTH), DRM_IOCTL_DEF(DRM_RADEON_GEM_SET_TILING, radeon_gem_set_tiling_ioctl, DRM_AUTH), DRM_IOCTL_DEF(DRM_RADEON_GEM_GET_TILING, radeon_gem_get_tiling_ioctl, DRM_AUTH), + DRM_IOCTL_DEF(DRM_RADEON_GEM_BUSY, radeon_gem_busy_ioctl, DRM_AUTH), }; int radeon_max_kms_ioctl = DRM_ARRAY_SIZE(radeon_ioctls_kms); diff --git a/include/drm/radeon_drm.h b/include/drm/radeon_drm.h index f81c3232accd..b43925586b29 100644 --- a/include/drm/radeon_drm.h +++ b/include/drm/radeon_drm.h @@ -508,6 +508,7 @@ typedef struct { #define DRM_RADEON_INFO 0x27 #define DRM_RADEON_GEM_SET_TILING 0x28 #define DRM_RADEON_GEM_GET_TILING 0x29 +#define DRM_RADEON_GEM_BUSY 0x2a #define DRM_IOCTL_RADEON_CP_INIT DRM_IOW( DRM_COMMAND_BASE + DRM_RADEON_CP_INIT, drm_radeon_init_t) #define DRM_IOCTL_RADEON_CP_START DRM_IO( DRM_COMMAND_BASE + DRM_RADEON_CP_START) @@ -548,6 +549,7 @@ typedef struct { #define DRM_IOCTL_RADEON_INFO DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_INFO, struct drm_radeon_info) #define DRM_IOCTL_RADEON_SET_TILING DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_SET_TILING, struct drm_radeon_gem_set_tiling) #define DRM_IOCTL_RADEON_GET_TILING DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_GET_TILING, struct drm_radeon_gem_get_tiling) +#define DRM_IOCTL_RADEON_GEM_BUSY DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_BUSY, struct drm_radeon_gem_busy) typedef struct drm_radeon_init { enum { -- cgit v1.2.3 From 1700f5fde88f9a251037bc86bde538ee32c59905 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Thu, 20 Aug 2009 22:05:53 -0700 Subject: Input: ucb1400_ts - enable ADC Filter This patch enables ADC filtering on UCB1400 codec by default. The benefit from this change is mostly on some Colibri boards where the ADCSYNC pin of the UCB1400 codec isn't connected causing the touchscreen to jitter very badly. This change has no visible effect on boards where the ADCSYNC pin is connected. Signed-off-by: Marek Vasut Tested-by: Palo Revak Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/ucb1400_ts.c | 9 +++++++++ include/linux/ucb1400.h | 4 ++++ 2 files changed, 13 insertions(+) (limited to 'include') diff --git a/drivers/input/touchscreen/ucb1400_ts.c b/drivers/input/touchscreen/ucb1400_ts.c index 6954f5500108..3b345f9cf0c7 100644 --- a/drivers/input/touchscreen/ucb1400_ts.c +++ b/drivers/input/touchscreen/ucb1400_ts.c @@ -345,6 +345,7 @@ static int ucb1400_ts_detect_irq(struct ucb1400_ts *ucb) static int ucb1400_ts_probe(struct platform_device *dev) { int error, x_res, y_res; + u16 fcsr; struct ucb1400_ts *ucb = dev->dev.platform_data; ucb->ts_idev = input_allocate_device(); @@ -382,6 +383,14 @@ static int ucb1400_ts_probe(struct platform_device *dev) ucb->ts_idev->evbit[0] = BIT_MASK(EV_ABS) | BIT_MASK(EV_KEY); ucb->ts_idev->keybit[BIT_WORD(BTN_TOUCH)] = BIT_MASK(BTN_TOUCH); + /* + * Enable ADC filter to prevent horrible jitter on Colibri. + * This also further reduces jitter on boards where ADCSYNC + * pin is connected. + */ + fcsr = ucb1400_reg_read(ucb->ac97, UCB_FCSR); + ucb1400_reg_write(ucb->ac97, UCB_FCSR, fcsr | UCB_FCSR_AVE); + ucb1400_adc_enable(ucb->ac97); x_res = ucb1400_ts_read_xres(ucb); y_res = ucb1400_ts_read_yres(ucb); diff --git a/include/linux/ucb1400.h b/include/linux/ucb1400.h index ed889f4168f3..ae779bb8cc0f 100644 --- a/include/linux/ucb1400.h +++ b/include/linux/ucb1400.h @@ -73,6 +73,10 @@ #define UCB_ADC_DATA 0x68 #define UCB_ADC_DAT_VALID (1 << 15) + +#define UCB_FCSR 0x6c +#define UCB_FCSR_AVE (1 << 12) + #define UCB_ADC_DAT_MASK 0x3ff #define UCB_ID 0x7e -- cgit v1.2.3 From f779b3e513478218cbaaaa0a506d7801cab6fd14 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 19 Aug 2009 19:11:39 -0400 Subject: drm/radeon: add GET_PARAM/INFO support for Z pipes Needed for occlusion queries on rv530 chips. Signed-off-by: Alex Deucher Signed-off-by: Dave Airlie --- drivers/gpu/drm/radeon/r300.c | 4 +++- drivers/gpu/drm/radeon/r420.c | 13 ++++++++++++- drivers/gpu/drm/radeon/r520.c | 1 - drivers/gpu/drm/radeon/radeon.h | 1 + drivers/gpu/drm/radeon/radeon_cp.c | 9 +++++++++ drivers/gpu/drm/radeon/radeon_drv.h | 5 ++++- drivers/gpu/drm/radeon/radeon_kms.c | 3 +++ drivers/gpu/drm/radeon/radeon_reg.h | 2 ++ drivers/gpu/drm/radeon/radeon_state.c | 3 +++ include/drm/radeon_drm.h | 2 ++ 10 files changed, 39 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c index c47579dcafa1..053f4ec397f7 100644 --- a/drivers/gpu/drm/radeon/r300.c +++ b/drivers/gpu/drm/radeon/r300.c @@ -448,6 +448,7 @@ void r300_gpu_init(struct radeon_device *rdev) /* rv350,rv370,rv380 */ rdev->num_gb_pipes = 1; } + rdev->num_z_pipes = 1; gb_tile_config = (R300_ENABLE_TILING | R300_TILE_SIZE_16); switch (rdev->num_gb_pipes) { case 2: @@ -486,7 +487,8 @@ void r300_gpu_init(struct radeon_device *rdev) printk(KERN_WARNING "Failed to wait MC idle while " "programming pipes. Bad things might happen.\n"); } - DRM_INFO("radeon: %d pipes initialized.\n", rdev->num_gb_pipes); + DRM_INFO("radeon: %d quad pipes, %d Z pipes initialized.\n", + rdev->num_gb_pipes, rdev->num_z_pipes); } int r300_ga_reset(struct radeon_device *rdev) diff --git a/drivers/gpu/drm/radeon/r420.c b/drivers/gpu/drm/radeon/r420.c index dea497a979f2..97426a6f370f 100644 --- a/drivers/gpu/drm/radeon/r420.c +++ b/drivers/gpu/drm/radeon/r420.c @@ -165,7 +165,18 @@ void r420_pipes_init(struct radeon_device *rdev) printk(KERN_WARNING "Failed to wait GUI idle while " "programming pipes. Bad things might happen.\n"); } - DRM_INFO("radeon: %d pipes initialized.\n", rdev->num_gb_pipes); + + if (rdev->family == CHIP_RV530) { + tmp = RREG32(RV530_GB_PIPE_SELECT2); + if ((tmp & 3) == 3) + rdev->num_z_pipes = 2; + else + rdev->num_z_pipes = 1; + } else + rdev->num_z_pipes = 1; + + DRM_INFO("radeon: %d quad pipes, %d z pipes initialized.\n", + rdev->num_gb_pipes, rdev->num_z_pipes); } void r420_gpu_init(struct radeon_device *rdev) diff --git a/drivers/gpu/drm/radeon/r520.c b/drivers/gpu/drm/radeon/r520.c index 09fb0b6ec7dd..ebd6b0f7bdff 100644 --- a/drivers/gpu/drm/radeon/r520.c +++ b/drivers/gpu/drm/radeon/r520.c @@ -177,7 +177,6 @@ void r520_gpu_init(struct radeon_device *rdev) */ /* workaround for RV530 */ if (rdev->family == CHIP_RV530) { - WREG32(0x4124, 1); WREG32(0x4128, 0xFF); } r420_pipes_init(rdev); diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 79ad98264e33..b519fb2fecbb 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -655,6 +655,7 @@ struct radeon_device { int usec_timeout; enum radeon_pll_errata pll_errata; int num_gb_pipes; + int num_z_pipes; int disp_priority; /* BIOS */ uint8_t *bios; diff --git a/drivers/gpu/drm/radeon/radeon_cp.c b/drivers/gpu/drm/radeon/radeon_cp.c index d8356827ef17..7a52c461145c 100644 --- a/drivers/gpu/drm/radeon/radeon_cp.c +++ b/drivers/gpu/drm/radeon/radeon_cp.c @@ -406,6 +406,15 @@ static void radeon_init_pipes(drm_radeon_private_t *dev_priv) { uint32_t gb_tile_config, gb_pipe_sel = 0; + if ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RV530) { + uint32_t z_pipe_sel = RADEON_READ(RV530_GB_PIPE_SELECT2); + if ((z_pipe_sel & 3) == 3) + dev_priv->num_z_pipes = 2; + else + dev_priv->num_z_pipes = 1; + } else + dev_priv->num_z_pipes = 1; + /* RS4xx/RS6xx/R4xx/R5xx */ if ((dev_priv->flags & RADEON_FAMILY_MASK) >= CHIP_R420) { gb_pipe_sel = RADEON_READ(R400_GB_PIPE_SELECT); diff --git a/drivers/gpu/drm/radeon/radeon_drv.h b/drivers/gpu/drm/radeon/radeon_drv.h index 3933f8216a34..6fa32dac4e97 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.h +++ b/drivers/gpu/drm/radeon/radeon_drv.h @@ -100,9 +100,10 @@ * 1.28- Add support for VBL on CRTC2 * 1.29- R500 3D cmd buffer support * 1.30- Add support for occlusion queries + * 1.31- Add support for num Z pipes from GET_PARAM */ #define DRIVER_MAJOR 1 -#define DRIVER_MINOR 30 +#define DRIVER_MINOR 31 #define DRIVER_PATCHLEVEL 0 /* @@ -329,6 +330,7 @@ typedef struct drm_radeon_private { resource_size_t fb_aper_offset; int num_gb_pipes; + int num_z_pipes; int track_flush; drm_local_map_t *mmio; @@ -689,6 +691,7 @@ extern void r600_page_table_cleanup(struct drm_device *dev, struct drm_ati_pciga /* pipe config regs */ #define R400_GB_PIPE_SELECT 0x402c +#define RV530_GB_PIPE_SELECT2 0x4124 #define R500_DYN_SCLK_PWMEM_PIPE 0x000d /* PLL */ #define R300_GB_TILE_CONFIG 0x4018 # define R300_ENABLE_TILING (1 << 0) diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index 11ed672543b1..dce09ada32bc 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -95,6 +95,9 @@ int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) case RADEON_INFO_NUM_GB_PIPES: value = rdev->num_gb_pipes; break; + case RADEON_INFO_NUM_Z_PIPES: + value = rdev->num_z_pipes; + break; default: DRM_DEBUG("Invalid request %d\n", info->request); return -EINVAL; diff --git a/drivers/gpu/drm/radeon/radeon_reg.h b/drivers/gpu/drm/radeon/radeon_reg.h index 5834497b366d..4df43f62c678 100644 --- a/drivers/gpu/drm/radeon/radeon_reg.h +++ b/drivers/gpu/drm/radeon/radeon_reg.h @@ -3574,4 +3574,6 @@ #define RADEON_SCRATCH_REG4 0x15f0 #define RADEON_SCRATCH_REG5 0x15f4 +#define RV530_GB_PIPE_SELECT2 0x4124 + #endif diff --git a/drivers/gpu/drm/radeon/radeon_state.c b/drivers/gpu/drm/radeon/radeon_state.c index 46645f3e0328..2882f40d5ec5 100644 --- a/drivers/gpu/drm/radeon/radeon_state.c +++ b/drivers/gpu/drm/radeon/radeon_state.c @@ -3081,6 +3081,9 @@ static int radeon_cp_getparam(struct drm_device *dev, void *data, struct drm_fil case RADEON_PARAM_NUM_GB_PIPES: value = dev_priv->num_gb_pipes; break; + case RADEON_PARAM_NUM_Z_PIPES: + value = dev_priv->num_z_pipes; + break; default: DRM_DEBUG("Invalid parameter %d\n", param->param); return -EINVAL; diff --git a/include/drm/radeon_drm.h b/include/drm/radeon_drm.h index b43925586b29..2ba61e18fc8b 100644 --- a/include/drm/radeon_drm.h +++ b/include/drm/radeon_drm.h @@ -709,6 +709,7 @@ typedef struct drm_radeon_indirect { #define RADEON_PARAM_FB_LOCATION 14 /* FB location */ #define RADEON_PARAM_NUM_GB_PIPES 15 /* num GB pipes */ #define RADEON_PARAM_DEVICE_ID 16 +#define RADEON_PARAM_NUM_Z_PIPES 17 /* num Z pipes */ typedef struct drm_radeon_getparam { int param; @@ -897,6 +898,7 @@ struct drm_radeon_cs { #define RADEON_INFO_DEVICE_ID 0x00 #define RADEON_INFO_NUM_GB_PIPES 0x01 +#define RADEON_INFO_NUM_Z_PIPES 0x02 struct drm_radeon_info { uint32_t request; -- cgit v1.2.3 From f4b0373b26567cafd421d91101852ed7a34e9e94 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 21 Aug 2009 09:26:15 -0700 Subject: Make bitmask 'and' operators return a result code When 'and'ing two bitmasks (where 'andnot' is a variation on it), some cases want to know whether the result is the empty set or not. In particular, the TLB IPI sending code wants to do cpumask operations and determine if there are any CPU's left in the final set. So this just makes the bitmask (and cpumask) functions return a boolean for whether the result has any bits set. Cc: stable@kernel.org (2.6.30, needed by TLB shootdown fix) Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 18 ++++++++---------- include/linux/cpumask.h | 20 ++++++++++---------- lib/bitmap.c | 12 ++++++++---- 3 files changed, 26 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 2878811c6134..756d78b8c1c5 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -94,13 +94,13 @@ extern void __bitmap_shift_right(unsigned long *dst, const unsigned long *src, int shift, int bits); extern void __bitmap_shift_left(unsigned long *dst, const unsigned long *src, int shift, int bits); -extern void __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, +extern int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); extern void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); extern void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); -extern void __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, +extern int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); extern int __bitmap_intersects(const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); @@ -171,13 +171,12 @@ static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, } } -static inline void bitmap_and(unsigned long *dst, const unsigned long *src1, +static inline int bitmap_and(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, int nbits) { if (small_const_nbits(nbits)) - *dst = *src1 & *src2; - else - __bitmap_and(dst, src1, src2, nbits); + return (*dst = *src1 & *src2) != 0; + return __bitmap_and(dst, src1, src2, nbits); } static inline void bitmap_or(unsigned long *dst, const unsigned long *src1, @@ -198,13 +197,12 @@ static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1, __bitmap_xor(dst, src1, src2, nbits); } -static inline void bitmap_andnot(unsigned long *dst, const unsigned long *src1, +static inline int bitmap_andnot(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, int nbits) { if (small_const_nbits(nbits)) - *dst = *src1 & ~(*src2); - else - __bitmap_andnot(dst, src1, src2, nbits); + return (*dst = *src1 & ~(*src2)) != 0; + return __bitmap_andnot(dst, src1, src2, nbits); } static inline void bitmap_complement(unsigned long *dst, const unsigned long *src, diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index c5ac87ca7bc6..796df12091b7 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -43,10 +43,10 @@ * int cpu_isset(cpu, mask) true iff bit 'cpu' set in mask * int cpu_test_and_set(cpu, mask) test and set bit 'cpu' in mask * - * void cpus_and(dst, src1, src2) dst = src1 & src2 [intersection] + * int cpus_and(dst, src1, src2) dst = src1 & src2 [intersection] * void cpus_or(dst, src1, src2) dst = src1 | src2 [union] * void cpus_xor(dst, src1, src2) dst = src1 ^ src2 - * void cpus_andnot(dst, src1, src2) dst = src1 & ~src2 + * int cpus_andnot(dst, src1, src2) dst = src1 & ~src2 * void cpus_complement(dst, src) dst = ~src * * int cpus_equal(mask1, mask2) Does mask1 == mask2? @@ -179,10 +179,10 @@ static inline int __cpu_test_and_set(int cpu, cpumask_t *addr) } #define cpus_and(dst, src1, src2) __cpus_and(&(dst), &(src1), &(src2), NR_CPUS) -static inline void __cpus_and(cpumask_t *dstp, const cpumask_t *src1p, +static inline int __cpus_and(cpumask_t *dstp, const cpumask_t *src1p, const cpumask_t *src2p, int nbits) { - bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits); + return bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits); } #define cpus_or(dst, src1, src2) __cpus_or(&(dst), &(src1), &(src2), NR_CPUS) @@ -201,10 +201,10 @@ static inline void __cpus_xor(cpumask_t *dstp, const cpumask_t *src1p, #define cpus_andnot(dst, src1, src2) \ __cpus_andnot(&(dst), &(src1), &(src2), NR_CPUS) -static inline void __cpus_andnot(cpumask_t *dstp, const cpumask_t *src1p, +static inline int __cpus_andnot(cpumask_t *dstp, const cpumask_t *src1p, const cpumask_t *src2p, int nbits) { - bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); + return bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); } #define cpus_complement(dst, src) __cpus_complement(&(dst), &(src), NR_CPUS) @@ -738,11 +738,11 @@ static inline void cpumask_clear(struct cpumask *dstp) * @src1p: the first input * @src2p: the second input */ -static inline void cpumask_and(struct cpumask *dstp, +static inline int cpumask_and(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { - bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p), + return bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits); } @@ -779,11 +779,11 @@ static inline void cpumask_xor(struct cpumask *dstp, * @src1p: the first input * @src2p: the second input */ -static inline void cpumask_andnot(struct cpumask *dstp, +static inline int cpumask_andnot(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { - bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p), + return bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits); } diff --git a/lib/bitmap.c b/lib/bitmap.c index 35a1f7ff4149..702565821c99 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -179,14 +179,16 @@ void __bitmap_shift_left(unsigned long *dst, } EXPORT_SYMBOL(__bitmap_shift_left); -void __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, +int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits) { int k; int nr = BITS_TO_LONGS(bits); + unsigned long result = 0; for (k = 0; k < nr; k++) - dst[k] = bitmap1[k] & bitmap2[k]; + result |= (dst[k] = bitmap1[k] & bitmap2[k]); + return result != 0; } EXPORT_SYMBOL(__bitmap_and); @@ -212,14 +214,16 @@ void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, } EXPORT_SYMBOL(__bitmap_xor); -void __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, +int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits) { int k; int nr = BITS_TO_LONGS(bits); + unsigned long result = 0; for (k = 0; k < nr; k++) - dst[k] = bitmap1[k] & ~bitmap2[k]; + result |= (dst[k] = bitmap1[k] & ~bitmap2[k]); + return result != 0; } EXPORT_SYMBOL(__bitmap_andnot); -- cgit v1.2.3 From ee5f9757ea17759e1ce5503bdae2b07e48e32af9 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 21 Aug 2009 16:33:34 -0700 Subject: pkt_sched: Convert qdisc_watchdog to tasklet_hrtimer None of this stuff should execute in hw IRQ context, therefore use a tasklet_hrtimer so that it runs in softirq context. Signed-off-by: David S. Miller Acked-by: Thomas Gleixner --- include/net/pkt_sched.h | 4 ++-- net/sched/sch_api.c | 8 ++++---- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 82a3191375f5..7eafb8d54470 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -61,8 +61,8 @@ psched_tdiff_bounded(psched_time_t tv1, psched_time_t tv2, psched_time_t bound) } struct qdisc_watchdog { - struct hrtimer timer; - struct Qdisc *qdisc; + struct tasklet_hrtimer timer; + struct Qdisc *qdisc; }; extern void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 24d17ce9c294..e1c2bf7e9ba4 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -468,8 +468,8 @@ static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer) void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc) { - hrtimer_init(&wd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); - wd->timer.function = qdisc_watchdog; + tasklet_hrtimer_init(&wd->timer, qdisc_watchdog, + CLOCK_MONOTONIC, HRTIMER_MODE_ABS); wd->qdisc = qdisc; } EXPORT_SYMBOL(qdisc_watchdog_init); @@ -485,13 +485,13 @@ void qdisc_watchdog_schedule(struct qdisc_watchdog *wd, psched_time_t expires) wd->qdisc->flags |= TCQ_F_THROTTLED; time = ktime_set(0, 0); time = ktime_add_ns(time, PSCHED_TICKS2NS(expires)); - hrtimer_start(&wd->timer, time, HRTIMER_MODE_ABS); + tasklet_hrtimer_start(&wd->timer, time, HRTIMER_MODE_ABS); } EXPORT_SYMBOL(qdisc_watchdog_schedule); void qdisc_watchdog_cancel(struct qdisc_watchdog *wd) { - hrtimer_cancel(&wd->timer); + tasklet_hrtimer_cancel(&wd->timer); wd->qdisc->flags &= ~TCQ_F_THROTTLED; } EXPORT_SYMBOL(qdisc_watchdog_cancel); -- cgit v1.2.3 From 6777d773a463ac045d333b989d4e44660f8d92ad Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Fri, 21 Aug 2009 14:32:48 -0400 Subject: kernel_read: redefine offset type vfs_read() offset is defined as loff_t, but kernel_read() offset is only defined as unsigned long. Redefine kernel_read() offset as loff_t. Cc: stable@kernel.org Signed-off-by: Mimi Zohar Signed-off-by: James Morris --- fs/exec.c | 4 ++-- include/linux/fs.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/fs/exec.c b/fs/exec.c index 4a8849e45b21..fb4f3cdda78c 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -678,8 +678,8 @@ exit: } EXPORT_SYMBOL(open_exec); -int kernel_read(struct file *file, unsigned long offset, - char *addr, unsigned long count) +int kernel_read(struct file *file, loff_t offset, + char *addr, unsigned long count) { mm_segment_t old_fs; loff_t pos = offset; diff --git a/include/linux/fs.h b/include/linux/fs.h index 67888a9e0655..73e9b643e455 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2123,7 +2123,7 @@ extern struct file *do_filp_open(int dfd, const char *pathname, int open_flag, int mode, int acc_mode); extern int may_open(struct path *, int, int); -extern int kernel_read(struct file *, unsigned long, char *, unsigned long); +extern int kernel_read(struct file *, loff_t, char *, unsigned long); extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ -- cgit v1.2.3 From 353d5c30c666580347515da609dd74a2b8e9b828 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 24 Aug 2009 16:30:28 +0100 Subject: mm: fix hugetlb bug due to user_shm_unlock call 2.6.30's commit 8a0bdec194c21c8fdef840989d0d7b742bb5d4bc removed user_shm_lock() calls in hugetlb_file_setup() but left the user_shm_unlock call in shm_destroy(). In detail: Assume that can_do_hugetlb_shm() returns true and hence user_shm_lock() is not called in hugetlb_file_setup(). However, user_shm_unlock() is called in any case in shm_destroy() and in the following atomic_dec_and_lock(&up->__count) in free_uid() is executed and if up->__count gets zero, also cleanup_user_struct() is scheduled. Note that sched_destroy_user() is empty if CONFIG_USER_SCHED is not set. However, the ref counter up->__count gets unexpectedly non-positive and the corresponding structs are freed even though there are live references to them, resulting in a kernel oops after a lots of shmget(SHM_HUGETLB)/shmctl(IPC_RMID) cycles and CONFIG_USER_SCHED set. Hugh changed Stefan's suggested patch: can_do_hugetlb_shm() at the time of shm_destroy() may give a different answer from at the time of hugetlb_file_setup(). And fixed newseg()'s no_id error path, which has missed user_shm_unlock() ever since it came in 2.6.9. Reported-by: Stefan Huber Signed-off-by: Hugh Dickins Tested-by: Stefan Huber Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- fs/hugetlbfs/inode.c | 20 ++++++++++++-------- include/linux/hugetlb.h | 6 ++++-- ipc/shm.c | 8 +++++--- 3 files changed, 21 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 941c8425c10b..cb88dac8ccaa 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -935,26 +935,28 @@ static int can_do_hugetlb_shm(void) return capable(CAP_IPC_LOCK) || in_group_p(sysctl_hugetlb_shm_group); } -struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag) +struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag, + struct user_struct **user) { int error = -ENOMEM; - int unlock_shm = 0; struct file *file; struct inode *inode; struct dentry *dentry, *root; struct qstr quick_string; - struct user_struct *user = current_user(); + *user = NULL; if (!hugetlbfs_vfsmount) return ERR_PTR(-ENOENT); if (!can_do_hugetlb_shm()) { - if (user_shm_lock(size, user)) { - unlock_shm = 1; + *user = current_user(); + if (user_shm_lock(size, *user)) { WARN_ONCE(1, "Using mlock ulimits for SHM_HUGETLB deprecated\n"); - } else + } else { + *user = NULL; return ERR_PTR(-EPERM); + } } root = hugetlbfs_vfsmount->mnt_root; @@ -996,8 +998,10 @@ out_inode: out_dentry: dput(dentry); out_shm_unlock: - if (unlock_shm) - user_shm_unlock(size, user); + if (*user) { + user_shm_unlock(size, *user); + *user = NULL; + } return ERR_PTR(error); } diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 2723513a5651..5cbc620bdfe0 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -10,6 +10,7 @@ #include struct ctl_table; +struct user_struct; int PageHuge(struct page *page); @@ -146,7 +147,8 @@ static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb) extern const struct file_operations hugetlbfs_file_operations; extern struct vm_operations_struct hugetlb_vm_ops; -struct file *hugetlb_file_setup(const char *name, size_t, int); +struct file *hugetlb_file_setup(const char *name, size_t size, int acct, + struct user_struct **user); int hugetlb_get_quota(struct address_space *mapping, long delta); void hugetlb_put_quota(struct address_space *mapping, long delta); @@ -168,7 +170,7 @@ static inline void set_file_hugepages(struct file *file) #define is_file_hugepages(file) 0 #define set_file_hugepages(file) BUG() -#define hugetlb_file_setup(name,size,acctflag) ERR_PTR(-ENOSYS) +#define hugetlb_file_setup(name,size,acct,user) ERR_PTR(-ENOSYS) #endif /* !CONFIG_HUGETLBFS */ diff --git a/ipc/shm.c b/ipc/shm.c index 15dd238e5338..1bc4701ef4f0 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -174,7 +174,7 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp) shm_unlock(shp); if (!is_file_hugepages(shp->shm_file)) shmem_lock(shp->shm_file, 0, shp->mlock_user); - else + else if (shp->mlock_user) user_shm_unlock(shp->shm_file->f_path.dentry->d_inode->i_size, shp->mlock_user); fput (shp->shm_file); @@ -369,8 +369,8 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) /* hugetlb_file_setup applies strict accounting */ if (shmflg & SHM_NORESERVE) acctflag = VM_NORESERVE; - file = hugetlb_file_setup(name, size, acctflag); - shp->mlock_user = current_user(); + file = hugetlb_file_setup(name, size, acctflag, + &shp->mlock_user); } else { /* * Do not allow no accounting for OVERCOMMIT_NEVER, even @@ -410,6 +410,8 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) return error; no_id: + if (shp->mlock_user) /* shmflg & SHM_HUGETLB case */ + user_shm_unlock(size, shp->mlock_user); fput(file); no_file: security_shm_free(shp); -- cgit v1.2.3 From 8e7ee27095aee87b5db1b0061e2ceea5878a1bbd Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Wed, 26 Aug 2009 14:29:21 -0700 Subject: flex_array: declare parts member to have incomplete type The `parts' member of struct flex_array should evaluate to an incomplete type so that sizeof() cannot be used and C99 does not require the zero-length specification. Signed-off-by: David Rientjes Acked-by: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/flex_array.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/flex_array.h b/include/linux/flex_array.h index 23c1ec79a31b..603160db7c98 100644 --- a/include/linux/flex_array.h +++ b/include/linux/flex_array.h @@ -21,7 +21,7 @@ struct flex_array { struct { int element_size; int total_nr_elements; - struct flex_array_part *parts[0]; + struct flex_array_part *parts[]; }; /* * This little trick makes sure that -- cgit v1.2.3 From b62e408c05228f40e69bb38a48db8961cac6cd23 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Wed, 26 Aug 2009 14:29:22 -0700 Subject: flex_array: convert element_nr formals to unsigned It's problematic to allow signed element_nr's or total's to be passed as part of the flex array API. flex_array_alloc() allows total_nr_elements to be set to a negative quantity, which is obviously erroneous. flex_array_get() and flex_array_put() allows negative array indices in dereferencing an array part, which could address memory mapped before struct flex_array. The fix is to convert all existing element_nr formals to be qualified as unsigned. Existing checks to compare it to total_nr_elements or the max array size based on element_size need not be changed. Signed-off-by: David Rientjes Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/flex_array.h | 10 ++++++---- lib/flex_array.c | 24 +++++++++++++----------- 2 files changed, 19 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/flex_array.h b/include/linux/flex_array.h index 603160db7c98..45ff18491514 100644 --- a/include/linux/flex_array.h +++ b/include/linux/flex_array.h @@ -36,12 +36,14 @@ struct flex_array { .total_nr_elements = (total), \ } } } -struct flex_array *flex_array_alloc(int element_size, int total, gfp_t flags); -int flex_array_prealloc(struct flex_array *fa, int start, int end, gfp_t flags); +struct flex_array *flex_array_alloc(int element_size, unsigned int total, + gfp_t flags); +int flex_array_prealloc(struct flex_array *fa, unsigned int start, + unsigned int end, gfp_t flags); void flex_array_free(struct flex_array *fa); void flex_array_free_parts(struct flex_array *fa); -int flex_array_put(struct flex_array *fa, int element_nr, void *src, +int flex_array_put(struct flex_array *fa, unsigned int element_nr, void *src, gfp_t flags); -void *flex_array_get(struct flex_array *fa, int element_nr); +void *flex_array_get(struct flex_array *fa, unsigned int element_nr); #endif /* _FLEX_ARRAY_H */ diff --git a/lib/flex_array.c b/lib/flex_array.c index cf4e372cae90..7baed2fc3bc8 100644 --- a/lib/flex_array.c +++ b/lib/flex_array.c @@ -99,7 +99,8 @@ static inline int elements_fit_in_base(struct flex_array *fa) * capacity in the base structure. Also note that no effort is made * to efficiently pack objects across page boundaries. */ -struct flex_array *flex_array_alloc(int element_size, int total, gfp_t flags) +struct flex_array *flex_array_alloc(int element_size, unsigned int total, + gfp_t flags) { struct flex_array *ret; int max_size = nr_base_part_ptrs() * __elements_per_part(element_size); @@ -115,7 +116,8 @@ struct flex_array *flex_array_alloc(int element_size, int total, gfp_t flags) return ret; } -static int fa_element_to_part_nr(struct flex_array *fa, int element_nr) +static int fa_element_to_part_nr(struct flex_array *fa, + unsigned int element_nr) { return element_nr / __elements_per_part(fa->element_size); } @@ -143,14 +145,12 @@ void flex_array_free(struct flex_array *fa) kfree(fa); } -static int fa_index_inside_part(struct flex_array *fa, int element_nr) +static unsigned int index_inside_part(struct flex_array *fa, + unsigned int element_nr) { - return element_nr % __elements_per_part(fa->element_size); -} + unsigned int part_offset; -static int index_inside_part(struct flex_array *fa, int element_nr) -{ - int part_offset = fa_index_inside_part(fa, element_nr); + part_offset = element_nr % __elements_per_part(fa->element_size); return part_offset * fa->element_size; } @@ -185,7 +185,8 @@ __fa_get_part(struct flex_array *fa, int part_nr, gfp_t flags) * * Locking must be provided by the caller. */ -int flex_array_put(struct flex_array *fa, int element_nr, void *src, gfp_t flags) +int flex_array_put(struct flex_array *fa, unsigned int element_nr, void *src, + gfp_t flags) { int part_nr = fa_element_to_part_nr(fa, element_nr); struct flex_array_part *part; @@ -217,7 +218,8 @@ int flex_array_put(struct flex_array *fa, int element_nr, void *src, gfp_t flags * * Locking must be provided by the caller. */ -int flex_array_prealloc(struct flex_array *fa, int start, int end, gfp_t flags) +int flex_array_prealloc(struct flex_array *fa, unsigned int start, + unsigned int end, gfp_t flags) { int start_part; int end_part; @@ -248,7 +250,7 @@ int flex_array_prealloc(struct flex_array *fa, int start, int end, gfp_t flags) * * Locking must be provided by the caller. */ -void *flex_array_get(struct flex_array *fa, int element_nr) +void *flex_array_get(struct flex_array *fa, unsigned int element_nr) { int part_nr = fa_element_to_part_nr(fa, element_nr); struct flex_array_part *part; -- cgit v1.2.3 From 2a908002c7b1b666616103e9df2419b38d7c6f1f Mon Sep 17 00:00:00 2001 From: Frans Pop Date: Wed, 26 Aug 2009 14:29:29 -0700 Subject: ACPI processor: force throttling state when BIOS returns incorrect value If the BIOS reports an invalid throttling state (which seems to be fairly common after system boot), a reset is done to state T0. Because of a check in acpi_processor_get_throttling_ptc(), the reset never actually gets executed, which results in the error reoccurring on every access of for example /proc/acpi/processor/CPU0/throttling. Add a 'force' option to acpi_processor_set_throttling() to ensure the reset really takes effect. Addresses http://bugzilla.kernel.org/show_bug.cgi?id=13389 This patch, together with the next one, fixes a regression introduced in 2.6.30, listed on the regression list. They have been available for 2.5 months now in bugzilla, but have not been picked up, despite various reminders and without any reason given. Google shows that numerous people are hitting this issue. The issue is in itself relatively minor, but the bug in the code is clear. The patches have been in all my kernels and today testing has shown that throttling works correctly with the patches applied when the system overheats (http://bugzilla.kernel.org/show_bug.cgi?id=13918#c14). Signed-off-by: Frans Pop Acked-by: Zhang Rui Cc: Len Brown Cc: "Rafael J. Wysocki" Cc: Rusty Russell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/acpi/processor_thermal.c | 6 +++--- drivers/acpi/processor_throttling.c | 26 ++++++++++++++------------ include/acpi/processor.h | 5 +++-- 3 files changed, 20 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/drivers/acpi/processor_thermal.c b/drivers/acpi/processor_thermal.c index 39838c666032..31adda1099e0 100644 --- a/drivers/acpi/processor_thermal.c +++ b/drivers/acpi/processor_thermal.c @@ -66,7 +66,7 @@ static int acpi_processor_apply_limit(struct acpi_processor *pr) if (pr->limit.thermal.tx > tx) tx = pr->limit.thermal.tx; - result = acpi_processor_set_throttling(pr, tx); + result = acpi_processor_set_throttling(pr, tx, false); if (result) goto end; } @@ -421,12 +421,12 @@ processor_set_cur_state(struct thermal_cooling_device *cdev, if (state <= max_pstate) { if (pr->flags.throttling && pr->throttling.state) - result = acpi_processor_set_throttling(pr, 0); + result = acpi_processor_set_throttling(pr, 0, false); cpufreq_set_cur_state(pr->id, state); } else { cpufreq_set_cur_state(pr->id, max_pstate); result = acpi_processor_set_throttling(pr, - state - max_pstate); + state - max_pstate, false); } return result; } diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c index 227543789ba9..841be4ee2109 100644 --- a/drivers/acpi/processor_throttling.c +++ b/drivers/acpi/processor_throttling.c @@ -62,7 +62,8 @@ struct throttling_tstate { #define THROTTLING_POSTCHANGE (2) static int acpi_processor_get_throttling(struct acpi_processor *pr); -int acpi_processor_set_throttling(struct acpi_processor *pr, int state); +int acpi_processor_set_throttling(struct acpi_processor *pr, + int state, bool force); static int acpi_processor_update_tsd_coord(void) { @@ -361,7 +362,7 @@ int acpi_processor_tstate_has_changed(struct acpi_processor *pr) */ target_state = throttling_limit; } - return acpi_processor_set_throttling(pr, target_state); + return acpi_processor_set_throttling(pr, target_state, false); } /* @@ -842,7 +843,7 @@ static int acpi_processor_get_throttling_ptc(struct acpi_processor *pr) ACPI_WARNING((AE_INFO, "Invalid throttling state, reset")); state = 0; - ret = acpi_processor_set_throttling(pr, state); + ret = acpi_processor_set_throttling(pr, state, true); if (ret) return ret; } @@ -915,7 +916,7 @@ static int acpi_processor_get_fadt_info(struct acpi_processor *pr) } static int acpi_processor_set_throttling_fadt(struct acpi_processor *pr, - int state) + int state, bool force) { u32 value = 0; u32 duty_mask = 0; @@ -930,7 +931,7 @@ static int acpi_processor_set_throttling_fadt(struct acpi_processor *pr, if (!pr->flags.throttling) return -ENODEV; - if (state == pr->throttling.state) + if (!force && (state == pr->throttling.state)) return 0; if (state < pr->throttling_platform_limit) @@ -988,7 +989,7 @@ static int acpi_processor_set_throttling_fadt(struct acpi_processor *pr, } static int acpi_processor_set_throttling_ptc(struct acpi_processor *pr, - int state) + int state, bool force) { int ret; acpi_integer value; @@ -1002,7 +1003,7 @@ static int acpi_processor_set_throttling_ptc(struct acpi_processor *pr, if (!pr->flags.throttling) return -ENODEV; - if (state == pr->throttling.state) + if (!force && (state == pr->throttling.state)) return 0; if (state < pr->throttling_platform_limit) @@ -1018,7 +1019,8 @@ static int acpi_processor_set_throttling_ptc(struct acpi_processor *pr, return 0; } -int acpi_processor_set_throttling(struct acpi_processor *pr, int state) +int acpi_processor_set_throttling(struct acpi_processor *pr, + int state, bool force) { cpumask_var_t saved_mask; int ret = 0; @@ -1070,7 +1072,7 @@ int acpi_processor_set_throttling(struct acpi_processor *pr, int state) /* FIXME: use work_on_cpu() */ set_cpus_allowed_ptr(current, cpumask_of(pr->id)); ret = p_throttling->acpi_processor_set_throttling(pr, - t_state.target_state); + t_state.target_state, force); } else { /* * When the T-state coordination is SW_ALL or HW_ALL, @@ -1103,7 +1105,7 @@ int acpi_processor_set_throttling(struct acpi_processor *pr, int state) set_cpus_allowed_ptr(current, cpumask_of(i)); ret = match_pr->throttling. acpi_processor_set_throttling( - match_pr, t_state.target_state); + match_pr, t_state.target_state, force); } } /* @@ -1201,7 +1203,7 @@ int acpi_processor_get_throttling_info(struct acpi_processor *pr) ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Disabling throttling (was T%d)\n", pr->throttling.state)); - result = acpi_processor_set_throttling(pr, 0); + result = acpi_processor_set_throttling(pr, 0, false); if (result) goto end; } @@ -1307,7 +1309,7 @@ static ssize_t acpi_processor_write_throttling(struct file *file, if (strcmp(tmpbuf, charp) != 0) return -EINVAL; - result = acpi_processor_set_throttling(pr, state_val); + result = acpi_processor_set_throttling(pr, state_val, false); if (result) return result; diff --git a/include/acpi/processor.h b/include/acpi/processor.h index baf1e0a9a7ee..740ac3ad8fd0 100644 --- a/include/acpi/processor.h +++ b/include/acpi/processor.h @@ -174,7 +174,7 @@ struct acpi_processor_throttling { cpumask_var_t shared_cpu_map; int (*acpi_processor_get_throttling) (struct acpi_processor * pr); int (*acpi_processor_set_throttling) (struct acpi_processor * pr, - int state); + int state, bool force); u32 address; u8 duty_offset; @@ -321,7 +321,8 @@ static inline int acpi_processor_ppc_has_changed(struct acpi_processor *pr) /* in processor_throttling.c */ int acpi_processor_tstate_has_changed(struct acpi_processor *pr); int acpi_processor_get_throttling_info(struct acpi_processor *pr); -extern int acpi_processor_set_throttling(struct acpi_processor *pr, int state); +extern int acpi_processor_set_throttling(struct acpi_processor *pr, + int state, bool force); extern const struct file_operations acpi_processor_throttling_fops; extern void acpi_processor_throttling_init(void); /* in processor_idle.c */ -- cgit v1.2.3 From 1a37f184fa7824982a5f434c06981ec46a66cef7 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 31 Aug 2009 13:48:16 +1000 Subject: lmb: Also remove __init from lmb_end_of_RAM() declaration in lmb.h My previous patch (commit 4f8ee2c9cc: "lmb: Remove __init from lmb_end_of_DRAM()") removed __init in lmb.c but missed the fact that it was also marked as such in the .h Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Linus Torvalds --- include/linux/lmb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/lmb.h b/include/linux/lmb.h index c46c89505dac..2442e3f3d033 100644 --- a/include/linux/lmb.h +++ b/include/linux/lmb.h @@ -51,7 +51,7 @@ extern u64 __init lmb_alloc_base(u64 size, extern u64 __init __lmb_alloc_base(u64 size, u64 align, u64 max_addr); extern u64 __init lmb_phys_mem_size(void); -extern u64 __init lmb_end_of_DRAM(void); +extern u64 lmb_end_of_DRAM(void); extern void __init lmb_enforce_memory_limit(u64 memory_limit); extern int __init lmb_is_reserved(u64 addr); extern int lmb_find(struct lmb_property *res); -- cgit v1.2.3