For NUMA optimization and some other algorithms it is useful to have a fast to get the current CPU and node numbers in user space. x86-64 added a fast way to do this in a vsyscall. This adds a generic syscall for other architectures to make it a generic portable facility. I expect some of them will also implement it as a faster vsyscall. The cache is an optimization for the x86-64 vsyscall optimization. Since what the syscall returns is an approximation anyways and user space often wants very fast results it can be cached for some time. The norma methods to get this information in user space are relatively slow The vsyscall is in a better position to manage the cache because it has direct access to a fast time stamp (jiffies). For the generic syscall optimization it doesn't help much, but enforce a valid argument to keep programs portable I only added an i386 syscall entry for now. Other architectures can follow as needed. AK: Also added some cleanups from Andrew Morton
Showing the changes to kernel/sys.c (1 of 5 files). Show all
Unified · Split
| @@ -28,6 +28,7 @@ · 27 unmodified lines | ||
| 28 | 28 | #include <linux/tty.h> |
| 29 | 29 | #include <linux/signal.h> |
| 30 | 30 | #include <linux/cn_proc.h> |
| 31 | +#include <linux/getcpu.h> | |
| 31 | 32 | |
| 32 | 33 | #include <linux/compat.h> |
| 33 | 34 | #include <linux/syscalls.h> |
| @@ -2062,3 +2063,33 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3, · 2028 unmodified lines | ||
| 2062 | 2063 | } |
| 2063 | 2064 | return error; |
| 2064 | 2065 | } |
| 2066 | + | |
| 2067 | +asmlinkage long sys_getcpu(unsigned __user *cpup, unsigned __user *nodep, | |
| 2068 | + struct getcpu_cache __user *cache) | |
| 2069 | +{ | |
| 2070 | + int err = 0; | |
| 2071 | + int cpu = raw_smp_processor_id(); | |
| 2072 | + if (cpup) | |
| 2073 | + err |= put_user(cpu, cpup); | |
| 2074 | + if (nodep) | |
| 2075 | + err |= put_user(cpu_to_node(cpu), nodep); | |
| 2076 | + if (cache) { | |
| 2077 | + /* | |
| 2078 | + * The cache is not needed for this implementation, | |
| 2079 | + * but make sure user programs pass something | |
| 2080 | + * valid. vsyscall implementations can instead make | |
| 2081 | + * good use of the cache. Only use t0 and t1 because | |
| 2082 | + * these are available in both 32bit and 64bit ABI (no | |
| 2083 | + * need for a compat_getcpu). 32bit has enough | |
| 2084 | + * padding | |
| 2085 | + */ | |
| 2086 | + unsigned long t0, t1; | |
| 2087 | + get_user(t0, &cache->t0); | |
| 2088 | + get_user(t1, &cache->t1); | |
| 2089 | + t0++; | |
| 2090 | + t1++; | |
| 2091 | + put_user(t0, &cache->t0); | |
| 2092 | + put_user(t1, &cache->t1); | |
| 2093 | + } | |
| 2094 | + return err ? -EFAULT : 0; | |
| 2095 | +} | |