diff options
author | rwatson <rwatson@FreeBSD.org> | 2009-07-14 22:48:30 +0000 |
---|---|---|
committer | rwatson <rwatson@FreeBSD.org> | 2009-07-14 22:48:30 +0000 |
commit | 57ca4583e728cab422fba8f15de10bd0b637b3dd (patch) | |
tree | 13848f891fb2f7a396281b31633563d0f764ff65 /sys/kern/kern_sysctl.c | |
parent | ef443476d9706035ac219f0280ef0b817dda7a6d (diff) | |
download | FreeBSD-src-57ca4583e728cab422fba8f15de10bd0b637b3dd.zip FreeBSD-src-57ca4583e728cab422fba8f15de10bd0b637b3dd.tar.gz |
Build on Jeff Roberson's linker-set based dynamic per-CPU allocator
(DPCPU), as suggested by Peter Wemm, and implement a new per-virtual
network stack memory allocator. Modify vnet to use the allocator
instead of monolithic global container structures (vinet, ...). This
change solves many binary compatibility problems associated with
VIMAGE, and restores ELF symbols for virtualized global variables.
Each virtualized global variable exists as a "reference copy", and also
once per virtual network stack. Virtualized global variables are
tagged at compile-time, placing the in a special linker set, which is
loaded into a contiguous region of kernel memory. Virtualized global
variables in the base kernel are linked as normal, but those in modules
are copied and relocated to a reserved portion of the kernel's vnet
region with the help of a the kernel linker.
Virtualized global variables exist in per-vnet memory set up when the
network stack instance is created, and are initialized statically from
the reference copy. Run-time access occurs via an accessor macro, which
converts from the current vnet and requested symbol to a per-vnet
address. When "options VIMAGE" is not compiled into the kernel, normal
global ELF symbols will be used instead and indirection is avoided.
This change restores static initialization for network stack global
variables, restores support for non-global symbols and types, eliminates
the need for many subsystem constructors, eliminates large per-subsystem
structures that caused many binary compatibility issues both for
monitoring applications (netstat) and kernel modules, removes the
per-function INIT_VNET_*() macros throughout the stack, eliminates the
need for vnet_symmap ksym(2) munging, and eliminates duplicate
definitions of virtualized globals under VIMAGE_GLOBALS.
Bump __FreeBSD_version and update UPDATING.
Portions submitted by: bz
Reviewed by: bz, zec
Discussed with: gnn, jamie, jeff, jhb, julian, sam
Suggested by: peter
Approved by: re (kensmith)
Diffstat (limited to 'sys/kern/kern_sysctl.c')
-rw-r--r-- | sys/kern/kern_sysctl.c | 105 |
1 files changed, 8 insertions, 97 deletions
diff --git a/sys/kern/kern_sysctl.c b/sys/kern/kern_sysctl.c index 9e61544..94e45f1 100644 --- a/sys/kern/kern_sysctl.c +++ b/sys/kern/kern_sysctl.c @@ -59,6 +59,8 @@ __FBSDID("$FreeBSD$"); #include <sys/ktrace.h> #endif +#include <net/vnet.h> + #include <security/mac/mac_framework.h> #include <vm/vm.h> @@ -936,33 +938,9 @@ sysctl_handle_int(SYSCTL_HANDLER_ARGS) return (error); } -#ifdef VIMAGE -int -sysctl_handle_v_int(SYSCTL_HANDLER_ARGS) -{ - int tmpout, error = 0; - - SYSCTL_RESOLVE_V_ARG1(); - - /* - * Attempt to get a coherent snapshot by making a copy of the data. - */ - tmpout = *(int *)arg1; - error = SYSCTL_OUT(req, &tmpout, sizeof(int)); - - if (error || !req->newptr) - return (error); - - if (!arg1) - error = EPERM; - else - error = SYSCTL_IN(req, arg1, sizeof(int)); - return (error); -} -#endif - /* * Based on on sysctl_handle_int() convert milliseconds into ticks. + * Note: this is used by TCP. */ int @@ -970,8 +948,11 @@ sysctl_msec_to_ticks(SYSCTL_HANDLER_ARGS) { int error, s, tt; - SYSCTL_RESOLVE_V_ARG1(); - +#ifdef VIMAGE + if (arg1 != NULL) + arg1 = (void *)(TD_TO_VNET(req->td)->vnet_data_base + + (uintptr_t)arg1); +#endif tt = *(int *)arg1; s = (int)((int64_t)tt * 1000 / hz); @@ -1097,47 +1078,6 @@ retry: return (error); } -#ifdef VIMAGE -int -sysctl_handle_v_string(SYSCTL_HANDLER_ARGS) -{ - int error=0; - char *tmparg; - size_t outlen; - - SYSCTL_RESOLVE_V_ARG1(); - - /* - * Attempt to get a coherent snapshot by copying to a - * temporary kernel buffer. - */ -retry: - outlen = strlen((char *)arg1)+1; - tmparg = malloc(outlen, M_SYSCTLTMP, M_WAITOK); - - if (strlcpy(tmparg, (char *)arg1, outlen) >= outlen) { - free(tmparg, M_SYSCTLTMP); - goto retry; - } - - error = SYSCTL_OUT(req, tmparg, outlen); - free(tmparg, M_SYSCTLTMP); - - if (error || !req->newptr) - return (error); - - if ((req->newlen - req->newidx) >= arg2) { - error = EINVAL; - } else { - arg2 = (req->newlen - req->newidx); - error = SYSCTL_IN(req, arg1, arg2); - ((char *)arg1)[arg2] = '\0'; - } - - return (error); -} -#endif - /* * Handle any kind of opaque data. * arg1 points to it, arg2 is the size. @@ -1175,35 +1115,6 @@ retry: return (error); } -#ifdef VIMAGE -int -sysctl_handle_v_opaque(SYSCTL_HANDLER_ARGS) -{ - int error, tries; - u_int generation; - struct sysctl_req req2; - - SYSCTL_RESOLVE_V_ARG1(); - - tries = 0; - req2 = *req; -retry: - generation = curthread->td_generation; - error = SYSCTL_OUT(req, arg1, arg2); - if (error) - return (error); - tries++; - if (generation != curthread->td_generation && tries < 3) { - *req = req2; - goto retry; - } - - error = SYSCTL_IN(req, arg1, arg2); - - return (error); -} -#endif - /* * Transfer functions to/from kernel space. * XXX: rather untested at this point |