From 0e009be8a0c2309f3696df70f72ef0075aa34c9c Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 5 Nov 2006 23:52:11 -0800 Subject: [PATCH] Improve the removed sysctl warnings Don't warn about libpthread's access to kernel.version. When it receives -ENOSYS it will read /proc/sys/kernel/version. If anything else shows up print the sysctl number string. Signed-off-by: Eric W. Biederman Cc: Cal Peake Cc: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 8bff2c18fb5a..0c8e805bbd6f 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2680,13 +2680,33 @@ int sysctl_ms_jiffies(ctl_table *table, int __user *name, int nlen, asmlinkage long sys_sysctl(struct __sysctl_args __user *args) { static int msg_count; + struct __sysctl_args tmp; + int name[CTL_MAXNAME]; + int i; + + /* Read in the sysctl name for better debug message logging */ + if (copy_from_user(&tmp, args, sizeof(tmp))) + return -EFAULT; + if (tmp.nlen <= 0 || tmp.nlen >= CTL_MAXNAME) + return -ENOTDIR; + for (i = 0; i < tmp.nlen; i++) + if (get_user(name[i], tmp.name + i)) + return -EFAULT; + + /* Ignore accesses to kernel.version */ + if ((tmp.nlen == 2) && (name[0] == CTL_KERN) && (name[1] == KERN_VERSION)) + goto out; if (msg_count < 5) { msg_count++; printk(KERN_INFO "warning: process `%s' used the removed sysctl " - "system call\n", current->comm); + "system call with ", current->comm); + for (i = 0; i < tmp.nlen; i++) + printk("%d.", name[i]); + printk("\n"); } +out: return -ENOSYS; } -- cgit v1.2.3 From d99f160ac53e51090f015a8f0617cea25f81a191 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 5 Nov 2006 23:52:12 -0800 Subject: [PATCH] sysctl: allow a zero ctl_name in the middle of a sysctl table Since it is becoming clear that there are just enough users of the binary sysctl interface that completely removing the binary interface from the kernel will not be an option for foreseeable future, we need to find a way to address the sysctl maintenance issues. The basic problem is that sysctl requires one central authority to allocate sysctl numbers, or else conflicts and ABI breakage occur. The proc interface to sysctl does not have that problem, as names are not densely allocated. By not terminating a sysctl table until I have neither a ctl_name nor a procname, it becomes simple to add sysctl entries that don't show up in the binary sysctl interface. Which allows people to avoid allocating a binary sysctl value when not needed. I have audited the kernel code and in my reading I have not found a single sysctl table that wasn't terminated by a completely zero filled entry. So this change in behavior should not affect anything. I think this mechanism eases the pain enough that combined with a little disciple we can solve the reoccurring sysctl ABI breakage. Signed-off-by: Eric W. Biederman Acked-by: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 0c8e805bbd6f..09e569f4792b 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1315,7 +1315,9 @@ repeat: return -ENOTDIR; if (get_user(n, name)) return -EFAULT; - for ( ; table->ctl_name; table++) { + for ( ; table->ctl_name || table->procname; table++) { + if (!table->ctl_name) + continue; if (n == table->ctl_name || table->ctl_name == CTL_ANY) { int error; if (table->child) { @@ -1532,7 +1534,7 @@ static void register_proc_table(ctl_table * table, struct proc_dir_entry *root, int len; mode_t mode; - for (; table->ctl_name; table++) { + for (; table->ctl_name || table->procname; table++) { /* Can't do anything without a proc name. */ if (!table->procname) continue; @@ -1579,7 +1581,7 @@ static void register_proc_table(ctl_table * table, struct proc_dir_entry *root, static void unregister_proc_table(ctl_table * table, struct proc_dir_entry *root) { struct proc_dir_entry *de; - for (; table->ctl_name; table++) { + for (; table->ctl_name || table->procname; table++) { if (!(de = table->de)) continue; if (de->mode & S_IFDIR) { -- cgit v1.2.3 From 0741f4d207a644482d7a040f05cd264c98cf7ee8 Mon Sep 17 00:00:00 2001 From: Chuck Ebbert <76306.1226@compuserve.com> Date: Thu, 7 Dec 2006 02:14:11 +0100 Subject: [PATCH] x86: add sysctl for kstack_depth_to_print Add sysctl for kstack_depth_to_print. This lets users change the amount of raw stack data printed in dump_stack() without having to reboot. Signed-off-by: Chuck Ebbert <76306.1226@compuserve.com> Signed-off-by: Andi Kleen --- kernel/sysctl.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 09e569f4792b..6fc5e17086f4 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -54,6 +54,7 @@ extern int proc_nr_files(ctl_table *table, int write, struct file *filp, #ifdef CONFIG_X86 #include +#include #endif #if defined(CONFIG_SYSCTL) @@ -707,6 +708,14 @@ static ctl_table kern_table[] = { .mode = 0444, .proc_handler = &proc_dointvec, }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "kstack_depth_to_print", + .data = &kstack_depth_to_print, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, #endif #if defined(CONFIG_MMU) { -- cgit v1.2.3 From 7602bdf2fd14a40dd9b104e516fdc05e1bd17952 Mon Sep 17 00:00:00 2001 From: Ashwin Chaugule Date: Wed, 6 Dec 2006 20:31:57 -0800 Subject: [PATCH] new scheme to preempt swap token The new swap token patches replace the current token traversal algo. The old algo had a crude timeout parameter that was used to handover the token from one task to another. This algo, transfers the token to the tasks that are in need of the token. The urgency for the token is based on the number of times a task is required to swap-in pages. Accordingly, the priority of a task is incremented if it has been badly affected due to swap-outs. To ensure that the token doesnt bounce around rapidly, the token holders are given a priority boost. The priority of tasks is also decremented, if their rate of swap-in's keeps reducing. This way, the condition to check whether to pre-empt the swap token, is a matter of comparing two task's priority fields. [akpm@osdl.org: cleanups] Signed-off-by: Ashwin Chaugule Cc: Rik van Riel Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 09e569f4792b..7abe9704e75a 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -977,17 +977,6 @@ static ctl_table vm_table[] = { .extra1 = &zero, }, #endif -#ifdef CONFIG_SWAP - { - .ctl_name = VM_SWAP_TOKEN_TIMEOUT, - .procname = "swap_token_timeout", - .data = &swap_token_default_timeout, - .maxlen = sizeof(swap_token_default_timeout), - .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, - }, -#endif #ifdef CONFIG_NUMA { .ctl_name = VM_ZONE_RECLAIM_MODE, -- cgit v1.2.3 From bd9b0bac6f601655044fc35978e26231dffee03e Mon Sep 17 00:00:00 2001 From: "BP, Praveen" Date: Wed, 6 Dec 2006 20:39:09 -0800 Subject: [PATCH] sysctl: string length calculated is wrong if it contains negative numbers In the functions do_proc_dointvec() and do_proc_doulongvec_minmax(), there seems to be a bug in string length calculation if string contains negative integer. The console log given below explains the bug. Setting negative values may not be a right thing to do for "console log level" but then the test (given below) can be used to demonstrate the bug in the code. # echo "-1 -1 -1 -123456" > /proc/sys/kernel/printk # cat /proc/sys/kernel/printk -1 -1 -1 -1234 # # echo "-1 -1 -1 123456" > /proc/sys/kernel/printk # cat /proc/sys/kernel/printk -1 -1 -1 1234 # (akpm: the bug is that 123456 gets truncated) It works as expected if string contains all +ve integers # echo "1 2 3 4" > /proc/sys/kernel/printk # cat /proc/sys/kernel/printk 1 2 3 4 # The patch given below fixes the issue. Signed-off-by: Praveen BP Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 7abe9704e75a..6d7147cf66bb 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1875,7 +1875,7 @@ static int __do_proc_dointvec(void *tbl_data, ctl_table *table, p = buf; if (*p == '-' && left > 1) { neg = 1; - left--, p++; + p++; } if (*p < '0' || *p > '9') break; @@ -2126,7 +2126,7 @@ static int __do_proc_doulongvec_minmax(void *data, ctl_table *table, int write, p = buf; if (*p == '-' && left > 1) { neg = 1; - left--, p++; + p++; } if (*p < '0' || *p > '9') break; -- cgit v1.2.3 From 15ad7cdcfd76450d4beebc789ec646664238184d Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Wed, 6 Dec 2006 20:40:36 -0800 Subject: [PATCH] struct seq_operations and struct file_operations constification - move some file_operations structs into the .rodata section - move static strings from policy_types[] array into the .rodata section - fix generic seq_operations usages, so that those structs may be defined as "const" as well [akpm@osdl.org: couple of fixes] Signed-off-by: Helge Deller Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 6d7147cf66bb..758dbbf972a5 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -170,7 +170,7 @@ static ssize_t proc_readsys(struct file *, char __user *, size_t, loff_t *); static ssize_t proc_writesys(struct file *, const char __user *, size_t, loff_t *); static int proc_opensys(struct inode *, struct file *); -struct file_operations proc_sys_file_operations = { +const struct file_operations proc_sys_file_operations = { .open = proc_opensys, .read = proc_readsys, .write = proc_writesys, -- cgit v1.2.3