alistair23-linux/arch/s390/kernel/kprobes.c

672 lines
18 KiB
C
Raw Normal View History

/*
* Kernel Probes (KProbes)
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*
* Copyright IBM Corp. 2002, 2006
*
* s390 port, used ppc64 as template. Mike Grundy <grundym@us.ibm.com>
*/
#include <linux/kprobes.h>
#include <linux/ptrace.h>
#include <linux/preempt.h>
#include <linux/stop_machine.h>
#include <linux/kdebug.h>
#include <linux/uaccess.h>
#include <asm/cacheflush.h>
#include <asm/sections.h>
#include <linux/module.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 02:04:11 -06:00
#include <linux/slab.h>
#include <linux/hardirq.h>
DEFINE_PER_CPU(struct kprobe *, current_kprobe);
DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
struct kretprobe_blackpoint kretprobe_blacklist[] = { };
static int __kprobes is_prohibited_opcode(kprobe_opcode_t *insn)
{
switch (insn[0] >> 8) {
case 0x0c: /* bassm */
case 0x0b: /* bsm */
case 0x83: /* diag */
case 0x44: /* ex */
case 0xac: /* stnsm */
case 0xad: /* stosm */
return -EINVAL;
}
switch (insn[0]) {
case 0x0101: /* pr */
case 0xb25a: /* bsa */
case 0xb240: /* bakr */
case 0xb258: /* bsg */
case 0xb218: /* pc */
case 0xb228: /* pt */
case 0xb98d: /* epsw */
return -EINVAL;
}
return 0;
}
static int __kprobes get_fixup_type(kprobe_opcode_t *insn)
{
/* default fixup method */
int fixup = FIXUP_PSW_NORMAL;
switch (insn[0] >> 8) {
case 0x05: /* balr */
case 0x0d: /* basr */
fixup = FIXUP_RETURN_REGISTER;
/* if r2 = 0, no branch will be taken */
if ((insn[0] & 0x0f) == 0)
fixup |= FIXUP_BRANCH_NOT_TAKEN;
break;
case 0x06: /* bctr */
case 0x07: /* bcr */
fixup = FIXUP_BRANCH_NOT_TAKEN;
break;
case 0x45: /* bal */
case 0x4d: /* bas */
fixup = FIXUP_RETURN_REGISTER;
break;
case 0x47: /* bc */
case 0x46: /* bct */
case 0x86: /* bxh */
case 0x87: /* bxle */
fixup = FIXUP_BRANCH_NOT_TAKEN;
break;
case 0x82: /* lpsw */
fixup = FIXUP_NOT_REQUIRED;
break;
case 0xb2: /* lpswe */
if ((insn[0] & 0xff) == 0xb2)
fixup = FIXUP_NOT_REQUIRED;
break;
case 0xa7: /* bras */
if ((insn[0] & 0x0f) == 0x05)
fixup |= FIXUP_RETURN_REGISTER;
break;
case 0xc0:
if ((insn[0] & 0x0f) == 0x00 || /* larl */
(insn[0] & 0x0f) == 0x05) /* brasl */
fixup |= FIXUP_RETURN_REGISTER;
break;
case 0xeb:
if ((insn[2] & 0xff) == 0x44 || /* bxhg */
(insn[2] & 0xff) == 0x45) /* bxleg */
fixup = FIXUP_BRANCH_NOT_TAKEN;
break;
case 0xe3: /* bctg */
if ((insn[2] & 0xff) == 0x46)
fixup = FIXUP_BRANCH_NOT_TAKEN;
break;
}
return fixup;
}
int __kprobes arch_prepare_kprobe(struct kprobe *p)
{
if ((unsigned long) p->addr & 0x01)
return -EINVAL;
/* Make sure the probe isn't going on a difficult instruction */
if (is_prohibited_opcode(p->addr))
return -EINVAL;
p->opcode = *p->addr;
memcpy(p->ainsn.insn, p->addr, ((p->opcode >> 14) + 3) & -2);
return 0;
}
struct ins_replace_args {
kprobe_opcode_t *ptr;
kprobe_opcode_t opcode;
};
static int __kprobes swap_instruction(void *aref)
{
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
unsigned long status = kcb->kprobe_status;
struct ins_replace_args *args = aref;
kcb->kprobe_status = KPROBE_SWAP_INST;
probe_kernel_write(args->ptr, &args->opcode, sizeof(args->opcode));
kcb->kprobe_status = status;
return 0;
}
void __kprobes arch_arm_kprobe(struct kprobe *p)
{
struct ins_replace_args args;
args.ptr = p->addr;
args.opcode = BREAKPOINT_INSTRUCTION;
stop_machine(swap_instruction, &args, NULL);
}
void __kprobes arch_disarm_kprobe(struct kprobe *p)
{
struct ins_replace_args args;
args.ptr = p->addr;
args.opcode = p->opcode;
stop_machine(swap_instruction, &args, NULL);
}
void __kprobes arch_remove_kprobe(struct kprobe *p)
{
}
static void __kprobes enable_singlestep(struct kprobe_ctlblk *kcb,
struct pt_regs *regs,
unsigned long ip)
{
struct per_regs per_kprobe;
/* Set up the PER control registers %cr9-%cr11 */
per_kprobe.control = PER_EVENT_IFETCH;
per_kprobe.start = ip;
per_kprobe.end = ip;
/* Save control regs and psw mask */
__ctl_store(kcb->kprobe_saved_ctl, 9, 11);
kcb->kprobe_saved_imask = regs->psw.mask &
(PSW_MASK_PER | PSW_MASK_IO | PSW_MASK_EXT);
/* Set PER control regs, turns on single step for the given address */
__ctl_load(per_kprobe, 9, 11);
regs->psw.mask |= PSW_MASK_PER;
regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT);
regs->psw.addr = ip | PSW_ADDR_AMODE;
}
static void __kprobes disable_singlestep(struct kprobe_ctlblk *kcb,
struct pt_regs *regs,
unsigned long ip)
{
/* Restore control regs and psw mask, set new psw address */
__ctl_load(kcb->kprobe_saved_ctl, 9, 11);
regs->psw.mask &= ~PSW_MASK_PER;
regs->psw.mask |= kcb->kprobe_saved_imask;
regs->psw.addr = ip | PSW_ADDR_AMODE;
}
/*
* Activate a kprobe by storing its pointer to current_kprobe. The
* previous kprobe is stored in kcb->prev_kprobe. A stack of up to
* two kprobes can be active, see KPROBE_REENTER.
*/
static void __kprobes push_kprobe(struct kprobe_ctlblk *kcb, struct kprobe *p)
{
kcb->prev_kprobe.kp = __get_cpu_var(current_kprobe);
kcb->prev_kprobe.status = kcb->kprobe_status;
__get_cpu_var(current_kprobe) = p;
}
/*
* Deactivate a kprobe by backing up to the previous state. If the
* current state is KPROBE_REENTER prev_kprobe.kp will be non-NULL,
* for any other state prev_kprobe.kp will be NULL.
*/
static void __kprobes pop_kprobe(struct kprobe_ctlblk *kcb)
{
__get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
kcb->kprobe_status = kcb->prev_kprobe.status;
}
void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
struct pt_regs *regs)
{
ri->ret_addr = (kprobe_opcode_t *) regs->gprs[14];
/* Replace the return addr with trampoline addr */
regs->gprs[14] = (unsigned long) &kretprobe_trampoline;
}
static void __kprobes kprobe_reenter_check(struct kprobe_ctlblk *kcb,
struct kprobe *p)
{
switch (kcb->kprobe_status) {
case KPROBE_HIT_SSDONE:
case KPROBE_HIT_ACTIVE:
kprobes_inc_nmissed_count(p);
break;
case KPROBE_HIT_SS:
case KPROBE_REENTER:
default:
/*
* A kprobe on the code path to single step an instruction
* is a BUG. The code path resides in the .kprobes.text
* section and is executed with interrupts disabled.
*/
printk(KERN_EMERG "Invalid kprobe detected at %p.\n", p->addr);
dump_kprobe(p);
BUG();
}
}
static int __kprobes kprobe_handler(struct pt_regs *regs)
{
struct kprobe_ctlblk *kcb;
struct kprobe *p;
/*
* We want to disable preemption for the entire duration of kprobe
* processing. That includes the calls to the pre/post handlers
* and single stepping the kprobe instruction.
*/
preempt_disable();
kcb = get_kprobe_ctlblk();
p = get_kprobe((void *)((regs->psw.addr & PSW_ADDR_INSN) - 2));
if (p) {
if (kprobe_running()) {
/*
* We have hit a kprobe while another is still
* active. This can happen in the pre and post
* handler. Single step the instruction of the
* new probe but do not call any handler function
* of this secondary kprobe.
* push_kprobe and pop_kprobe saves and restores
* the currently active kprobe.
*/
kprobe_reenter_check(kcb, p);
push_kprobe(kcb, p);
kcb->kprobe_status = KPROBE_REENTER;
} else {
/*
* If we have no pre-handler or it returned 0, we
* continue with single stepping. If we have a
* pre-handler and it returned non-zero, it prepped
* for calling the break_handler below on re-entry
* for jprobe processing, so get out doing nothing
* more here.
*/
push_kprobe(kcb, p);
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
if (p->pre_handler && p->pre_handler(p, regs))
return 1;
kcb->kprobe_status = KPROBE_HIT_SS;
}
enable_singlestep(kcb, regs, (unsigned long) p->ainsn.insn);
return 1;
} else if (kprobe_running()) {
p = __get_cpu_var(current_kprobe);
if (p->break_handler && p->break_handler(p, regs)) {
/*
* Continuation after the jprobe completed and
* caused the jprobe_return trap. The jprobe
* break_handler "returns" to the original
* function that still has the kprobe breakpoint
* installed. We continue with single stepping.
*/
kcb->kprobe_status = KPROBE_HIT_SS;
enable_singlestep(kcb, regs,
(unsigned long) p->ainsn.insn);
return 1;
} /* else:
* No kprobe at this address and the current kprobe
* has no break handler (no jprobe!). The kernel just
* exploded, let the standard trap handler pick up the
* pieces.
*/
} /* else:
* No kprobe at this address and no active kprobe. The trap has
* not been caused by a kprobe breakpoint. The race of breakpoint
* vs. kprobe remove does not exist because on s390 as we use
* stop_machine to arm/disarm the breakpoints.
*/
preempt_enable_no_resched();
return 0;
}
/*
* Function return probe trampoline:
* - init_kprobes() establishes a probepoint here
* - When the probed function returns, this probe
* causes the handlers to fire
*/
static void __used kretprobe_trampoline_holder(void)
{
asm volatile(".global kretprobe_trampoline\n"
"kretprobe_trampoline: bcr 0,0\n");
}
/*
* Called when the probe at kretprobe trampoline is hit
*/
static int __kprobes trampoline_probe_handler(struct kprobe *p,
struct pt_regs *regs)
{
struct kretprobe_instance *ri;
struct hlist_head *head, empty_rp;
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-27 18:06:00 -07:00
struct hlist_node *tmp;
unsigned long flags, orig_ret_address;
unsigned long trampoline_address;
kprobe_opcode_t *correct_ret_addr;
INIT_HLIST_HEAD(&empty_rp);
kprobes: improve kretprobe scalability with hashed locking Currently list of kretprobe instances are stored in kretprobe object (as used_instances,free_instances) and in kretprobe hash table. We have one global kretprobe lock to serialise the access to these lists. This causes only one kretprobe handler to execute at a time. Hence affects system performance, particularly on SMP systems and when return probe is set on lot of functions (like on all systemcalls). Solution proposed here gives fine-grain locks that performs better on SMP system compared to present kretprobe implementation. Solution: 1) Instead of having one global lock to protect kretprobe instances present in kretprobe object and kretprobe hash table. We will have two locks, one lock for protecting kretprobe hash table and another lock for kretporbe object. 2) We hold lock present in kretprobe object while we modify kretprobe instance in kretprobe object and we hold per-hash-list lock while modifying kretprobe instances present in that hash list. To prevent deadlock, we never grab a per-hash-list lock while holding a kretprobe lock. 3) We can remove used_instances from struct kretprobe, as we can track used instances of kretprobe instances using kretprobe hash table. Time duration for kernel compilation ("make -j 8") on a 8-way ppc64 system with return probes set on all systemcalls looks like this. cacheline non-cacheline Un-patched kernel aligned patch aligned patch =============================================================================== real 9m46.784s 9m54.412s 10m2.450s user 40m5.715s 40m7.142s 40m4.273s sys 2m57.754s 2m58.583s 3m17.430s =========================================================== Time duration for kernel compilation ("make -j 8) on the same system, when kernel is not probed. ========================= real 9m26.389s user 40m8.775s sys 2m7.283s ========================= Signed-off-by: Srinivasa DS <srinivasa@in.ibm.com> Signed-off-by: Jim Keniston <jkenisto@us.ibm.com> Acked-by: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Masami Hiramatsu <mhiramat@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-25 02:46:04 -06:00
kretprobe_hash_lock(current, &head, &flags);
/*
* It is possible to have multiple instances associated with a given
* task either because an multiple functions in the call path
* have a return probe installed on them, and/or more than one return
* return probe was registered for a target function.
*
* We can handle this because:
* - instances are always inserted at the head of the list
* - when multiple return probes are registered for the same
* function, the first instance's ret_addr will point to the
* real return address, and all the rest will point to
* kretprobe_trampoline
*/
ri = NULL;
orig_ret_address = 0;
correct_ret_addr = NULL;
trampoline_address = (unsigned long) &kretprobe_trampoline;
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-27 18:06:00 -07:00
hlist_for_each_entry_safe(ri, tmp, head, hlist) {
if (ri->task != current)
/* another task is sharing our hash bucket */
continue;
orig_ret_address = (unsigned long) ri->ret_addr;
if (orig_ret_address != trampoline_address)
/*
* This is the real return address. Any other
* instances associated with this task are for
* other calls deeper on the call stack
*/
break;
}
kretprobe_assert(ri, orig_ret_address, trampoline_address);
correct_ret_addr = ri->ret_addr;
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-27 18:06:00 -07:00
hlist_for_each_entry_safe(ri, tmp, head, hlist) {
if (ri->task != current)
/* another task is sharing our hash bucket */
continue;
orig_ret_address = (unsigned long) ri->ret_addr;
if (ri->rp && ri->rp->handler) {
ri->ret_addr = correct_ret_addr;
ri->rp->handler(ri, regs);
}
recycle_rp_inst(ri, &empty_rp);
if (orig_ret_address != trampoline_address)
/*
* This is the real return address. Any other
* instances associated with this task are for
* other calls deeper on the call stack
*/
break;
}
regs->psw.addr = orig_ret_address | PSW_ADDR_AMODE;
pop_kprobe(get_kprobe_ctlblk());
kprobes: improve kretprobe scalability with hashed locking Currently list of kretprobe instances are stored in kretprobe object (as used_instances,free_instances) and in kretprobe hash table. We have one global kretprobe lock to serialise the access to these lists. This causes only one kretprobe handler to execute at a time. Hence affects system performance, particularly on SMP systems and when return probe is set on lot of functions (like on all systemcalls). Solution proposed here gives fine-grain locks that performs better on SMP system compared to present kretprobe implementation. Solution: 1) Instead of having one global lock to protect kretprobe instances present in kretprobe object and kretprobe hash table. We will have two locks, one lock for protecting kretprobe hash table and another lock for kretporbe object. 2) We hold lock present in kretprobe object while we modify kretprobe instance in kretprobe object and we hold per-hash-list lock while modifying kretprobe instances present in that hash list. To prevent deadlock, we never grab a per-hash-list lock while holding a kretprobe lock. 3) We can remove used_instances from struct kretprobe, as we can track used instances of kretprobe instances using kretprobe hash table. Time duration for kernel compilation ("make -j 8") on a 8-way ppc64 system with return probes set on all systemcalls looks like this. cacheline non-cacheline Un-patched kernel aligned patch aligned patch =============================================================================== real 9m46.784s 9m54.412s 10m2.450s user 40m5.715s 40m7.142s 40m4.273s sys 2m57.754s 2m58.583s 3m17.430s =========================================================== Time duration for kernel compilation ("make -j 8) on the same system, when kernel is not probed. ========================= real 9m26.389s user 40m8.775s sys 2m7.283s ========================= Signed-off-by: Srinivasa DS <srinivasa@in.ibm.com> Signed-off-by: Jim Keniston <jkenisto@us.ibm.com> Acked-by: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Masami Hiramatsu <mhiramat@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-25 02:46:04 -06:00
kretprobe_hash_unlock(current, &flags);
preempt_enable_no_resched();
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-27 18:06:00 -07:00
hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
hlist_del(&ri->hlist);
kfree(ri);
}
/*
* By returning a non-zero value, we are telling
* kprobe_handler() that we don't want the post_handler
* to run (and have re-enabled preemption)
*/
return 1;
}
/*
* Called after single-stepping. p->addr is the address of the
* instruction whose first byte has been replaced by the "breakpoint"
* instruction. To avoid the SMP problems that can occur when we
* temporarily put back the original opcode to single-step, we
* single-stepped a copy of the instruction. The address of this
* copy is p->ainsn.insn.
*/
static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs)
{
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
unsigned long ip = regs->psw.addr & PSW_ADDR_INSN;
int fixup = get_fixup_type(p->ainsn.insn);
if (fixup & FIXUP_PSW_NORMAL)
ip += (unsigned long) p->addr - (unsigned long) p->ainsn.insn;
if (fixup & FIXUP_BRANCH_NOT_TAKEN) {
int ilen = ((p->ainsn.insn[0] >> 14) + 3) & -2;
if (ip - (unsigned long) p->ainsn.insn == ilen)
ip = (unsigned long) p->addr + ilen;
}
if (fixup & FIXUP_RETURN_REGISTER) {
int reg = (p->ainsn.insn[0] & 0xf0) >> 4;
regs->gprs[reg] += (unsigned long) p->addr -
(unsigned long) p->ainsn.insn;
}
disable_singlestep(kcb, regs, ip);
}
static int __kprobes post_kprobe_handler(struct pt_regs *regs)
{
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
struct kprobe *p = kprobe_running();
if (!p)
return 0;
if (kcb->kprobe_status != KPROBE_REENTER && p->post_handler) {
kcb->kprobe_status = KPROBE_HIT_SSDONE;
p->post_handler(p, regs, 0);
}
resume_execution(p, regs);
pop_kprobe(kcb);
preempt_enable_no_resched();
/*
* if somebody else is singlestepping across a probe point, psw mask
* will have PER set, in which case, continue the remaining processing
* of do_single_step, as if this is not a probe hit.
*/
if (regs->psw.mask & PSW_MASK_PER)
return 0;
return 1;
}
static int __kprobes kprobe_trap_handler(struct pt_regs *regs, int trapnr)
{
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
struct kprobe *p = kprobe_running();
const struct exception_table_entry *entry;
switch(kcb->kprobe_status) {
case KPROBE_SWAP_INST:
/* We are here because the instruction replacement failed */
return 0;
case KPROBE_HIT_SS:
case KPROBE_REENTER:
/*
* We are here because the instruction being single
* stepped caused a page fault. We reset the current
* kprobe and the nip points back to the probe address
* and allow the page fault handler to continue as a
* normal page fault.
*/
disable_singlestep(kcb, regs, (unsigned long) p->addr);
pop_kprobe(kcb);
preempt_enable_no_resched();
break;
case KPROBE_HIT_ACTIVE:
case KPROBE_HIT_SSDONE:
/*
* We increment the nmissed count for accounting,
* we can also use npre/npostfault count for accouting
* these specific fault cases.
*/
kprobes_inc_nmissed_count(p);
/*
* We come here because instructions in the pre/post
* handler caused the page_fault, this could happen
* if handler tries to access user space by
* copy_from_user(), get_user() etc. Let the
* user-specified handler try to fix it first.
*/
if (p->fault_handler && p->fault_handler(p, regs, trapnr))
return 1;
/*
* In case the user-specified fault handler returned
* zero, try to fix up.
*/
entry = search_exception_tables(regs->psw.addr & PSW_ADDR_INSN);
if (entry) {
regs->psw.addr = extable_fixup(entry) | PSW_ADDR_AMODE;
return 1;
}
/*
* fixup_exception() could not handle it,
* Let do_page_fault() fix it.
*/
break;
default:
break;
}
return 0;
}
int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
{
int ret;
if (regs->psw.mask & (PSW_MASK_IO | PSW_MASK_EXT))
local_irq_disable();
ret = kprobe_trap_handler(regs, trapnr);
if (regs->psw.mask & (PSW_MASK_IO | PSW_MASK_EXT))
local_irq_restore(regs->psw.mask & ~PSW_MASK_PER);
return ret;
}
/*
* Wrapper routine to for handling exceptions.
*/
int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
unsigned long val, void *data)
{
struct die_args *args = (struct die_args *) data;
struct pt_regs *regs = args->regs;
int ret = NOTIFY_DONE;
if (regs->psw.mask & (PSW_MASK_IO | PSW_MASK_EXT))
local_irq_disable();
switch (val) {
case DIE_BPT:
if (kprobe_handler(regs))
ret = NOTIFY_STOP;
break;
case DIE_SSTEP:
if (post_kprobe_handler(regs))
ret = NOTIFY_STOP;
break;
case DIE_TRAP:
if (!preemptible() && kprobe_running() &&
kprobe_trap_handler(regs, args->trapnr))
ret = NOTIFY_STOP;
break;
default:
break;
}
if (regs->psw.mask & (PSW_MASK_IO | PSW_MASK_EXT))
local_irq_restore(regs->psw.mask & ~PSW_MASK_PER);
return ret;
}
int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
{
struct jprobe *jp = container_of(p, struct jprobe, kp);
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
unsigned long stack;
memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs));
/* setup return addr to the jprobe handler routine */
regs->psw.addr = (unsigned long) jp->entry | PSW_ADDR_AMODE;
regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT);
/* r15 is the stack pointer */
stack = (unsigned long) regs->gprs[15];
memcpy(kcb->jprobes_stack, (void *) stack, MIN_STACK_SIZE(stack));
return 1;
}
void __kprobes jprobe_return(void)
{
asm volatile(".word 0x0002");
}
static void __used __kprobes jprobe_return_end(void)
{
asm volatile("bcr 0,0");
}
int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
{
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
unsigned long stack;
stack = (unsigned long) kcb->jprobe_saved_regs.gprs[15];
/* Put the regs back */
memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs));
/* put the stack back */
memcpy((void *) stack, kcb->jprobes_stack, MIN_STACK_SIZE(stack));
preempt_enable_no_resched();
return 1;
}
static struct kprobe trampoline = {
.addr = (kprobe_opcode_t *) &kretprobe_trampoline,
.pre_handler = trampoline_probe_handler
};
int __init arch_init_kprobes(void)
{
return register_kprobe(&trampoline);
}
int __kprobes arch_trampoline_kprobe(struct kprobe *p)
{
return p->addr == (kprobe_opcode_t *) &kretprobe_trampoline;
}