* Re: [PATCH v2 bpf-next 0/3] bpf/verifier: subprog/func_call simplifications
From: Edward Cree @ 2018-03-29 22:50 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann; +Cc: netdev
In-Reply-To: <d13f6b60-3632-3e4d-111a-2edb4198b473@solarflare.com>
On 29/03/18 23:44, Edward Cree wrote:
> By storing subprog boundaries as a subprogno mark on each insn, rather than
> a start (and implicit end) for each subprog, we collect a number of gains:
> * More efficient determination of which subprog contains a given insn, and
> thus of find_subprog (which subprog begins at a given insn).
> * Number of verifier "full recursive walk" passes is reduced, since most of
> the work is done in the main insn walk (do_check()). Leftover work in
> other passes is mostly linear scans (O(insn_cnt)) or, in the case of
> check_max_stack_depth(), a topological sort (O(subprog_cnt)).
>
> Some other changes were also included to support this:
> * Per-subprog info is stored in env->subprog_info, an array of structs,
> rather than several arrays with a common index.
> * Call graph is now stored in the new bpf_subprog_info struct; used here
> for check_max_stack_depth() but may have other uses too.
>
> Along with this, patch #3 puts parent pointers (used by liveness analysis)
> in the registers instead of the func_state or verifier_state, so that we
> don't need skip_callee() machinery. This also does the right thing for
> stack slots, so they don't need their own special handling for liveness
> marking either.
Whoops, forgot to add:
Changes from v1:
* No longer allows non-contiguous subprogs.
* No longer allows LD_ABS|IND and pseudo-calls in the same prog.
> Edward Cree (3):
> bpf/verifier: validate func_calls by marking at do_check() time
> bpf/verifier: update selftests
> bpf/verifier: per-register parent pointers
>
> include/linux/bpf_verifier.h | 32 +-
> kernel/bpf/verifier.c | 631 +++++++++++++---------------
> tools/testing/selftests/bpf/test_verifier.c | 51 ++-
> 3 files changed, 344 insertions(+), 370 deletions(-)
>
^ permalink raw reply
* RE: [iproute2-next 0/2] tipc: changes to addressing structure
From: Jon Maloy @ 2018-03-29 22:49 UTC (permalink / raw)
To: David Ahern, davem@davemloft.net, netdev@vger.kernel.org
Cc: Mohan Krishna Ghanta Krishnamurthy, Tung Quang Nguyen,
Hoang Huu Le, Canh Duc Luu, ying.xue@windriver.com,
tipc-discussion@lists.sourceforge.net
In-Reply-To: <48e0b999-38ef-feb9-37c3-ee164cceabe3@gmail.com>
> -----Original Message-----
> From: netdev-owner@vger.kernel.org [mailto:netdev-
> owner@vger.kernel.org] On Behalf Of David Ahern
> Sent: Thursday, March 29, 2018 13:59
> To: Jon Maloy <jon.maloy@ericsson.com>; davem@davemloft.net;
> netdev@vger.kernel.org
> Cc: Mohan Krishna Ghanta Krishnamurthy
[..]
bit node addresses as an integer in hex format,
> >> i.e., we remove the assumption about an internal structure.
> >>
> >
> > Applied to iproute2-next. Thanks,
> >
>
> BTW, please consider adding json support to tipc. It will make tipc command
> more robust to changes in output format.
Yes, we will do that.
///jon
^ permalink raw reply
* [PATCH v2 bpf-next 3/3] bpf/verifier: per-register parent pointers
From: Edward Cree @ 2018-03-29 22:46 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann; +Cc: netdev
In-Reply-To: <d13f6b60-3632-3e4d-111a-2edb4198b473@solarflare.com>
By giving each register its own liveness chain, we elide the skip_callee()
logic. Instead, each register's parent is the state it inherits from;
both check_func_call() and prepare_func_exit() automatically connect
reg states to the correct chain since when they copy the reg state across
(r1-r5 into the callee as args, and r0 out as the return value) they also
copy the parent pointer.
Signed-off-by: Edward Cree <ecree@solarflare.com>
---
include/linux/bpf_verifier.h | 8 +-
kernel/bpf/verifier.c | 180 ++++++++++---------------------------------
2 files changed, 45 insertions(+), 143 deletions(-)
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 3af3f9cceede..2ec31b388dd6 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -41,6 +41,7 @@ enum bpf_reg_liveness {
};
struct bpf_reg_state {
+ /* Ordering of fields matters. See states_equal() */
enum bpf_reg_type type;
union {
/* valid when type == PTR_TO_PACKET */
@@ -59,7 +60,6 @@ struct bpf_reg_state {
* came from, when one is tested for != NULL.
*/
u32 id;
- /* Ordering of fields matters. See states_equal() */
/* For scalar types (SCALAR_VALUE), this represents our knowledge of
* the actual value.
* For pointer types, this represents the variable part of the offset
@@ -76,15 +76,15 @@ struct bpf_reg_state {
s64 smax_value; /* maximum possible (s64)value */
u64 umin_value; /* minimum possible (u64)value */
u64 umax_value; /* maximum possible (u64)value */
+ /* parentage chain for liveness checking */
+ struct bpf_reg_state *parent;
/* Inside the callee two registers can be both PTR_TO_STACK like
* R1=fp-8 and R2=fp-8, but one of them points to this function stack
* while another to the caller's stack. To differentiate them 'frameno'
* is used which is an index in bpf_verifier_state->frame[] array
* pointing to bpf_func_state.
- * This field must be second to last, for states_equal() reasons.
*/
u32 frameno;
- /* This field must be last, for states_equal() reasons. */
enum bpf_reg_liveness live;
};
@@ -107,7 +107,6 @@ struct bpf_stack_state {
*/
struct bpf_func_state {
struct bpf_reg_state regs[MAX_BPF_REG];
- struct bpf_verifier_state *parent;
/* index of call instruction that called into this func */
int callsite;
/* stack frame number of this function state from pov of
@@ -129,7 +128,6 @@ struct bpf_func_state {
struct bpf_verifier_state {
/* call stack tracking */
struct bpf_func_state *frame[MAX_CALL_FRAMES];
- struct bpf_verifier_state *parent;
u32 curframe;
};
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 33963357a7ef..edb2ec0da95c 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -355,9 +355,9 @@ static int copy_stack_state(struct bpf_func_state *dst,
/* do_check() starts with zero-sized stack in struct bpf_verifier_state to
* make it consume minimal amount of memory. check_stack_write() access from
* the program calls into realloc_func_state() to grow the stack size.
- * Note there is a non-zero 'parent' pointer inside bpf_verifier_state
- * which this function copies over. It points to previous bpf_verifier_state
- * which is never reallocated
+ * Note there is a non-zero parent pointer inside each reg of bpf_verifier_state
+ * which this function copies over. It points to corresponding reg in previous
+ * bpf_verifier_state which is never reallocated
*/
static int realloc_func_state(struct bpf_func_state *state, int size,
bool copy_old)
@@ -441,7 +441,6 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
dst_state->frame[i] = NULL;
}
dst_state->curframe = src->curframe;
- dst_state->parent = src->parent;
for (i = 0; i <= src->curframe; i++) {
dst = dst_state->frame[i];
if (!dst) {
@@ -707,6 +706,7 @@ static void init_reg_state(struct bpf_verifier_env *env,
for (i = 0; i < MAX_BPF_REG; i++) {
mark_reg_not_init(env, regs, i);
regs[i].live = REG_LIVE_NONE;
+ regs[i].parent = NULL;
}
/* frame pointer */
@@ -781,74 +781,21 @@ static int add_subprog(struct bpf_verifier_env *env, int off)
return ret;
}
-static
-struct bpf_verifier_state *skip_callee(struct bpf_verifier_env *env,
- const struct bpf_verifier_state *state,
- struct bpf_verifier_state *parent,
- u32 regno)
-{
- struct bpf_verifier_state *tmp = NULL;
-
- /* 'parent' could be a state of caller and
- * 'state' could be a state of callee. In such case
- * parent->curframe < state->curframe
- * and it's ok for r1 - r5 registers
- *
- * 'parent' could be a callee's state after it bpf_exit-ed.
- * In such case parent->curframe > state->curframe
- * and it's ok for r0 only
- */
- if (parent->curframe == state->curframe ||
- (parent->curframe < state->curframe &&
- regno >= BPF_REG_1 && regno <= BPF_REG_5) ||
- (parent->curframe > state->curframe &&
- regno == BPF_REG_0))
- return parent;
-
- if (parent->curframe > state->curframe &&
- regno >= BPF_REG_6) {
- /* for callee saved regs we have to skip the whole chain
- * of states that belong to callee and mark as LIVE_READ
- * the registers before the call
- */
- tmp = parent;
- while (tmp && tmp->curframe != state->curframe) {
- tmp = tmp->parent;
- }
- if (!tmp)
- goto bug;
- parent = tmp;
- } else {
- goto bug;
- }
- return parent;
-bug:
- verbose(env, "verifier bug regno %d tmp %p\n", regno, tmp);
- verbose(env, "regno %d parent frame %d current frame %d\n",
- regno, parent->curframe, state->curframe);
- return NULL;
-}
-
+/* Parentage chain of this register (or stack slot) should take care of all
+ * issues like callee-saved registers, stack slot allocation time, etc.
+ */
static int mark_reg_read(struct bpf_verifier_env *env,
- const struct bpf_verifier_state *state,
- struct bpf_verifier_state *parent,
- u32 regno)
+ const struct bpf_reg_state *state,
+ struct bpf_reg_state *parent)
{
bool writes = parent == state->parent; /* Observe write marks */
- if (regno == BPF_REG_FP)
- /* We don't need to worry about FP liveness because it's read-only */
- return 0;
-
while (parent) {
/* if read wasn't screened by an earlier write ... */
- if (writes && state->frame[state->curframe]->regs[regno].live & REG_LIVE_WRITTEN)
+ if (writes && state->live & REG_LIVE_WRITTEN)
break;
- parent = skip_callee(env, state, parent, regno);
- if (!parent)
- return -EFAULT;
/* ... then we depend on parent's value */
- parent->frame[parent->curframe]->regs[regno].live |= REG_LIVE_READ;
+ parent->live |= REG_LIVE_READ;
state = parent;
parent = state->parent;
writes = true;
@@ -874,7 +821,10 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
verbose(env, "R%d !read_ok\n", regno);
return -EACCES;
}
- return mark_reg_read(env, vstate, vstate->parent, regno);
+ /* We don't need to worry about FP liveness because it's read-only */
+ if (regno != BPF_REG_FP)
+ return mark_reg_read(env, ®s[regno],
+ regs[regno].parent);
} else {
/* check whether register used as dest operand can be written to */
if (regno == BPF_REG_FP) {
@@ -986,61 +936,6 @@ static int check_stack_write(struct bpf_verifier_env *env,
return 0;
}
-/* registers of every function are unique and mark_reg_read() propagates
- * the liveness in the following cases:
- * - from callee into caller for R1 - R5 that were used as arguments
- * - from caller into callee for R0 that used as result of the call
- * - from caller to the same caller skipping states of the callee for R6 - R9,
- * since R6 - R9 are callee saved by implicit function prologue and
- * caller's R6 != callee's R6, so when we propagate liveness up to
- * parent states we need to skip callee states for R6 - R9.
- *
- * stack slot marking is different, since stacks of caller and callee are
- * accessible in both (since caller can pass a pointer to caller's stack to
- * callee which can pass it to another function), hence mark_stack_slot_read()
- * has to propagate the stack liveness to all parent states at given frame number.
- * Consider code:
- * f1() {
- * ptr = fp - 8;
- * *ptr = ctx;
- * call f2 {
- * .. = *ptr;
- * }
- * .. = *ptr;
- * }
- * First *ptr is reading from f1's stack and mark_stack_slot_read() has
- * to mark liveness at the f1's frame and not f2's frame.
- * Second *ptr is also reading from f1's stack and mark_stack_slot_read() has
- * to propagate liveness to f2 states at f1's frame level and further into
- * f1 states at f1's frame level until write into that stack slot
- */
-static void mark_stack_slot_read(struct bpf_verifier_env *env,
- const struct bpf_verifier_state *state,
- struct bpf_verifier_state *parent,
- int slot, int frameno)
-{
- bool writes = parent == state->parent; /* Observe write marks */
-
- while (parent) {
- if (parent->frame[frameno]->allocated_stack <= slot * BPF_REG_SIZE)
- /* since LIVE_WRITTEN mark is only done for full 8-byte
- * write the read marks are conservative and parent
- * state may not even have the stack allocated. In such case
- * end the propagation, since the loop reached beginning
- * of the function
- */
- break;
- /* if read wasn't screened by an earlier write ... */
- if (writes && state->frame[frameno]->stack[slot].spilled_ptr.live & REG_LIVE_WRITTEN)
- break;
- /* ... then we depend on parent's value */
- parent->frame[frameno]->stack[slot].spilled_ptr.live |= REG_LIVE_READ;
- state = parent;
- parent = state->parent;
- writes = true;
- }
-}
-
static int check_stack_read(struct bpf_verifier_env *env,
struct bpf_func_state *reg_state /* func where register points to */,
int off, int size, int value_regno)
@@ -1078,8 +973,8 @@ static int check_stack_read(struct bpf_verifier_env *env,
*/
state->regs[value_regno].live |= REG_LIVE_WRITTEN;
}
- mark_stack_slot_read(env, vstate, vstate->parent, spi,
- reg_state->frameno);
+ mark_reg_read(env, ®_state->stack[spi].spilled_ptr,
+ reg_state->stack[spi].spilled_ptr.parent);
return 0;
} else {
int zeros = 0;
@@ -1095,8 +990,8 @@ static int check_stack_read(struct bpf_verifier_env *env,
off, i, size);
return -EACCES;
}
- mark_stack_slot_read(env, vstate, vstate->parent, spi,
- reg_state->frameno);
+ mark_reg_read(env, ®_state->stack[spi].spilled_ptr,
+ reg_state->stack[spi].spilled_ptr.parent);
if (value_regno >= 0) {
if (zeros == size) {
/* any size read into register is zero extended,
@@ -1783,8 +1678,8 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
/* reading any byte out of 8-byte 'spill_slot' will cause
* the whole slot to be marked as 'read'
*/
- mark_stack_slot_read(env, env->cur_state, env->cur_state->parent,
- spi, state->frameno);
+ mark_reg_read(env, &state->stack[spi].spilled_ptr,
+ state->stack[spi].spilled_ptr.parent);
}
return update_stack_depth(env, state, off);
}
@@ -2226,11 +2121,13 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
state->curframe + 1 /* frameno within this callchain */,
subprog /* subprog number within this prog */);
- /* copy r1 - r5 args that callee can access */
+ /* copy r1 - r5 args that callee can access. The copy includes parent
+ * pointers, which connects us up to the liveness chain
+ */
for (i = BPF_REG_1; i <= BPF_REG_5; i++)
callee->regs[i] = caller->regs[i];
- /* after the call regsiters r0 - r5 were scratched */
+ /* after the call registers r0 - r5 were scratched */
for (i = 0; i < CALLER_SAVED_REGS; i++) {
mark_reg_not_init(env, caller->regs, caller_saved[i]);
check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
@@ -4136,7 +4033,7 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
/* explored state didn't use this */
return true;
- equal = memcmp(rold, rcur, offsetof(struct bpf_reg_state, frameno)) == 0;
+ equal = memcmp(rold, rcur, offsetof(struct bpf_reg_state, parent)) == 0;
if (rold->type == PTR_TO_STACK)
/* two stack pointers are equal only if they're pointing to
@@ -4369,7 +4266,7 @@ static bool states_equal(struct bpf_verifier_env *env,
* equivalent state (jump target or such) we didn't arrive by the straight-line
* code, so read marks in the state must propagate to the parent regardless
* of the state's write marks. That's what 'parent == state->parent' comparison
- * in mark_reg_read() and mark_stack_slot_read() is for.
+ * in mark_reg_read() is for.
*/
static int propagate_liveness(struct bpf_verifier_env *env,
const struct bpf_verifier_state *vstate,
@@ -4390,7 +4287,8 @@ static int propagate_liveness(struct bpf_verifier_env *env,
if (vparent->frame[vparent->curframe]->regs[i].live & REG_LIVE_READ)
continue;
if (vstate->frame[vstate->curframe]->regs[i].live & REG_LIVE_READ) {
- err = mark_reg_read(env, vstate, vparent, i);
+ err = mark_reg_read(env, &vstate->frame[vstate->curframe]->regs[i],
+ &vparent->frame[vstate->curframe]->regs[i]);
if (err)
return err;
}
@@ -4405,7 +4303,8 @@ static int propagate_liveness(struct bpf_verifier_env *env,
if (parent->stack[i].spilled_ptr.live & REG_LIVE_READ)
continue;
if (state->stack[i].spilled_ptr.live & REG_LIVE_READ)
- mark_stack_slot_read(env, vstate, vparent, i, frame);
+ mark_reg_read(env, &state->stack[i].spilled_ptr,
+ &parent->stack[i].spilled_ptr);
}
}
return err;
@@ -4415,7 +4314,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
{
struct bpf_verifier_state_list *new_sl;
struct bpf_verifier_state_list *sl;
- struct bpf_verifier_state *cur = env->cur_state;
+ struct bpf_verifier_state *cur = env->cur_state, *new;
int i, j, err;
sl = env->explored_states[insn_idx];
@@ -4457,16 +4356,18 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
return -ENOMEM;
/* add new state to the head of linked list */
- err = copy_verifier_state(&new_sl->state, cur);
+ new = &new_sl->state;
+ err = copy_verifier_state(new, cur);
if (err) {
- free_verifier_state(&new_sl->state, false);
+ free_verifier_state(new, false);
kfree(new_sl);
return err;
}
new_sl->next = env->explored_states[insn_idx];
env->explored_states[insn_idx] = new_sl;
/* connect new state to parentage chain */
- cur->parent = &new_sl->state;
+ for (i = 0; i < BPF_REG_FP; i++)
+ cur_regs(env)[i].parent = &new->frame[new->curframe]->regs[i];
/* clear write marks in current state: the writes we did are not writes
* our child did, so they don't screen off its reads from us.
* (There are no read marks in current state, because reads always mark
@@ -4479,9 +4380,13 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
/* all stack frames are accessible from callee, clear them all */
for (j = 0; j <= cur->curframe; j++) {
struct bpf_func_state *frame = cur->frame[j];
+ struct bpf_func_state *newframe = new->frame[j];
- for (i = 0; i < frame->allocated_stack / BPF_REG_SIZE; i++)
+ for (i = 0; i < frame->allocated_stack / BPF_REG_SIZE; i++) {
frame->stack[i].spilled_ptr.live = REG_LIVE_NONE;
+ frame->stack[i].spilled_ptr.parent =
+ &newframe->stack[i].spilled_ptr;
+ }
}
return 0;
}
@@ -4547,7 +4452,6 @@ static int do_check(struct bpf_verifier_env *env)
if (!state)
return -ENOMEM;
state->curframe = 0;
- state->parent = NULL;
state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL);
if (!state->frame[0]) {
kfree(state);
^ permalink raw reply related
* [PATCH v2 bpf-next 2/3] bpf/verifier: update selftests
From: Edward Cree @ 2018-03-29 22:46 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann; +Cc: netdev
In-Reply-To: <d13f6b60-3632-3e4d-111a-2edb4198b473@solarflare.com>
Error messages for some bad programs have changed, partly because we now
check for loops / out-of-bounds jumps before checking subprogs.
Also added a test ("calls: interleaved functions") to ensure that subprogs
are required to be contiguous.
It wasn't entirely clear to me what "calls: wrong recursive calls" was
meant to test for, since all of the JMP|CALL insns are unreachable. I've
changed it so that they are now reachable, which causes static back-edges
to be detected (since that, like insn reachability, is now tested before
subprog boundaries are determined).
Signed-off-by: Edward Cree <ecree@solarflare.com>
---
tools/testing/selftests/bpf/test_verifier.c | 51 ++++++++++++++++++-----------
1 file changed, 32 insertions(+), 19 deletions(-)
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 3e7718b1a9ae..cc45a0b52439 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -646,7 +646,7 @@ static struct bpf_test tests[] = {
.insns = {
BPF_ALU64_REG(BPF_MOV, BPF_REG_0, BPF_REG_2),
},
- .errstr = "not an exit",
+ .errstr = "jump out of range",
.result = REJECT,
},
{
@@ -9442,13 +9442,13 @@ static struct bpf_test tests[] = {
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
- .errstr = "last insn is not an exit or jmp",
+ .errstr = "insn 1 was in subprog 1, now 0",
.result = REJECT,
},
{
"calls: wrong recursive calls",
.insns = {
- BPF_JMP_IMM(BPF_JA, 0, 0, 4),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 3),
BPF_JMP_IMM(BPF_JA, 0, 0, 4),
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -2),
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -2),
@@ -9457,7 +9457,7 @@ static struct bpf_test tests[] = {
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
- .errstr = "jump out of range",
+ .errstr = "back-edge from insn",
.result = REJECT,
},
{
@@ -9508,7 +9508,7 @@ static struct bpf_test tests[] = {
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
- .errstr = "jump out of range",
+ .errstr = "insn 5 was in subprog 1, now 0",
.result = REJECT,
},
{
@@ -9787,7 +9787,7 @@ static struct bpf_test tests[] = {
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
- .errstr = "jump out of range from insn 1 to 4",
+ .errstr = "insn 5 was in subprog 1, now 0",
.result = REJECT,
},
{
@@ -9803,13 +9803,12 @@ static struct bpf_test tests[] = {
BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0),
BPF_MOV64_REG(BPF_REG_0, BPF_REG_7),
BPF_EXIT_INSN(),
- BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
- offsetof(struct __sk_buff, len)),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 8),
BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, -3),
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
- .errstr = "jump out of range from insn 11 to 9",
+ .errstr = "insn 9 was in subprog 1, now 2",
.result = REJECT,
},
{
@@ -9861,7 +9860,7 @@ static struct bpf_test tests[] = {
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
- .errstr = "invalid destination",
+ .errstr = "jump out of range from insn 2 to -1",
.result = REJECT,
},
{
@@ -9873,7 +9872,7 @@ static struct bpf_test tests[] = {
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
- .errstr = "invalid destination",
+ .errstr = "jump out of range from insn 2 to -2147483646",
.result = REJECT,
},
{
@@ -9886,7 +9885,7 @@ static struct bpf_test tests[] = {
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
- .errstr = "jump out of range",
+ .errstr = "insn 1 was in subprog 0, now 1",
.result = REJECT,
},
{
@@ -9899,7 +9898,7 @@ static struct bpf_test tests[] = {
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
- .errstr = "jump out of range",
+ .errstr = "insn 4 was in subprog 1, now 0",
.result = REJECT,
},
{
@@ -9913,7 +9912,7 @@ static struct bpf_test tests[] = {
BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, -2),
},
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
- .errstr = "not an exit",
+ .errstr = "jump out of range from insn 5 to 6",
.result = REJECT,
},
{
@@ -9927,7 +9926,7 @@ static struct bpf_test tests[] = {
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
- .errstr = "last insn",
+ .errstr = "insn_idx 5 is in subprog 1 but that starts at 4",
.result = REJECT,
},
{
@@ -9942,7 +9941,7 @@ static struct bpf_test tests[] = {
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
- .errstr = "last insn",
+ .errstr = "insn_idx 5 is in subprog 1 but that starts at 4",
.result = REJECT,
},
{
@@ -9982,12 +9981,11 @@ static struct bpf_test tests[] = {
BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0),
BPF_MOV64_REG(BPF_REG_0, BPF_REG_7),
BPF_MOV64_REG(BPF_REG_0, BPF_REG_0),
- BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
- offsetof(struct __sk_buff, len)),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 8),
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
- .errstr = "not an exit",
+ .errstr = "insn 10 was in subprog 2, now 1",
.result = REJECT,
},
{
@@ -11423,6 +11421,21 @@ static struct bpf_test tests[] = {
.errstr = "BPF_XADD stores into R2 packet",
.prog_type = BPF_PROG_TYPE_XDP,
},
+ {
+ "calls: interleaved functions",
+ .insns = {
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 2),
+ BPF_MOV64_IMM(BPF_REG_0, 2),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ .errstr = "subprog 0 is non-contiguous at 5",
+ .result = REJECT,
+ },
};
static int probe_filter_length(const struct bpf_insn *fp)
^ permalink raw reply related
* [PATCH v2 bpf-next 1/3] bpf/verifier: validate func_calls by marking at do_check() time
From: Edward Cree @ 2018-03-29 22:45 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann; +Cc: netdev
In-Reply-To: <d13f6b60-3632-3e4d-111a-2edb4198b473@solarflare.com>
Removes a couple of passes from the verifier, one to check subprogs don't
overlap etc., and one to compute max stack depth (which now is done by
topologically sorting the call graph). This improves the asymptotic
complexity of a number of operations, for instance the max stack depth
check is now O(n) in the number of subprogs, rather than having to walk
every insn of every possible call chain.
Signed-off-by: Edward Cree <ecree@solarflare.com>
---
include/linux/bpf_verifier.h | 24 ++-
kernel/bpf/verifier.c | 451 ++++++++++++++++++++++++-------------------
2 files changed, 267 insertions(+), 208 deletions(-)
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 7e61c395fddf..3af3f9cceede 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -146,6 +146,7 @@ struct bpf_insn_aux_data {
s32 call_imm; /* saved imm field of call insn */
};
int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
+ u16 subprogno; /* subprog in which this insn resides, valid iff @seen */
bool seen; /* this insn was processed by the verifier */
};
@@ -173,6 +174,15 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log)
#define BPF_MAX_SUBPROGS 256
+struct bpf_subprog_info {
+ /* which other subprogs does this one directly call? */
+ DECLARE_BITMAP(callees, BPF_MAX_SUBPROGS);
+ u32 start; /* insn idx of function entry point */
+ u16 stack_depth; /* max. stack depth used by this function */
+ u16 total_stack_depth; /* max. stack depth used by entire call chain */
+ u16 len; /* #insns in this subprog */
+};
+
/* single container for all structs
* one verifier_env per bpf_check() call
*/
@@ -189,11 +199,10 @@ struct bpf_verifier_env {
u32 id_gen; /* used to generate unique reg IDs */
bool allow_ptr_leaks;
bool seen_direct_write;
+ bool seen_pseudo_call; /* populated at check_cfg() time */
struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */
struct bpf_verifier_log log;
- u32 subprog_starts[BPF_MAX_SUBPROGS];
- /* computes the stack depth of each bpf function */
- u16 subprog_stack_depth[BPF_MAX_SUBPROGS + 1];
+ struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS];
u32 subprog_cnt;
};
@@ -202,11 +211,16 @@ void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt,
__printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env,
const char *fmt, ...);
-static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env)
+static inline struct bpf_func_state *cur_frame(struct bpf_verifier_env *env)
{
struct bpf_verifier_state *cur = env->cur_state;
- return cur->frame[cur->curframe]->regs;
+ return cur->frame[cur->curframe];
+}
+
+static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env)
+{
+ return cur_frame(env)->regs;
}
int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 8acd2207e412..33963357a7ef 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -736,111 +736,49 @@ enum reg_arg_type {
DST_OP_NO_MARK /* same as above, check only, don't mark */
};
-static int cmp_subprogs(const void *a, const void *b)
+static int find_subprog(struct bpf_verifier_env *env, int insn_idx)
{
- return *(int *)a - *(int *)b;
-}
-
-static int find_subprog(struct bpf_verifier_env *env, int off)
-{
- u32 *p;
+ struct bpf_insn_aux_data *aux;
+ int insn_cnt = env->prog->len;
+ u32 subprogno;
- p = bsearch(&off, env->subprog_starts, env->subprog_cnt,
- sizeof(env->subprog_starts[0]), cmp_subprogs);
- if (!p)
+ if (insn_idx >= insn_cnt || insn_idx < 0) {
+ verbose(env, "find_subprog of invalid insn_idx %d\n", insn_idx);
+ return -EINVAL;
+ }
+ aux = &env->insn_aux_data[insn_idx];
+ if (!aux->seen) /* haven't visited this line yet */
return -ENOENT;
- return p - env->subprog_starts;
-
+ subprogno = aux->subprogno;
+ /* validate that we are at start of subprog */
+ if (env->subprog_info[subprogno].start != insn_idx) {
+ verbose(env, "insn_idx %d is in subprog %u but that starts at %d\n",
+ insn_idx, subprogno, env->subprog_info[subprogno].start);
+ return -EINVAL;
+ }
+ return subprogno;
}
static int add_subprog(struct bpf_verifier_env *env, int off)
{
int insn_cnt = env->prog->len;
+ struct bpf_subprog_info *info;
int ret;
if (off >= insn_cnt || off < 0) {
verbose(env, "call to invalid destination\n");
return -EINVAL;
}
- ret = find_subprog(env, off);
- if (ret >= 0)
- return 0;
if (env->subprog_cnt >= BPF_MAX_SUBPROGS) {
verbose(env, "too many subprograms\n");
return -E2BIG;
}
- env->subprog_starts[env->subprog_cnt++] = off;
- sort(env->subprog_starts, env->subprog_cnt,
- sizeof(env->subprog_starts[0]), cmp_subprogs, NULL);
- return 0;
-}
-
-static int check_subprogs(struct bpf_verifier_env *env)
-{
- int i, ret, subprog_start, subprog_end, off, cur_subprog = 0;
- struct bpf_insn *insn = env->prog->insnsi;
- int insn_cnt = env->prog->len;
-
- /* determine subprog starts. The end is one before the next starts */
- for (i = 0; i < insn_cnt; i++) {
- if (insn[i].code != (BPF_JMP | BPF_CALL))
- continue;
- if (insn[i].src_reg != BPF_PSEUDO_CALL)
- continue;
- if (!env->allow_ptr_leaks) {
- verbose(env, "function calls to other bpf functions are allowed for root only\n");
- return -EPERM;
- }
- if (bpf_prog_is_dev_bound(env->prog->aux)) {
- verbose(env, "function calls in offloaded programs are not supported yet\n");
- return -EINVAL;
- }
- ret = add_subprog(env, i + insn[i].imm + 1);
- if (ret < 0)
- return ret;
- }
-
- if (env->log.level > 1)
- for (i = 0; i < env->subprog_cnt; i++)
- verbose(env, "func#%d @%d\n", i, env->subprog_starts[i]);
-
- /* now check that all jumps are within the same subprog */
- subprog_start = 0;
- if (env->subprog_cnt == cur_subprog)
- subprog_end = insn_cnt;
- else
- subprog_end = env->subprog_starts[cur_subprog++];
- for (i = 0; i < insn_cnt; i++) {
- u8 code = insn[i].code;
-
- if (BPF_CLASS(code) != BPF_JMP)
- goto next;
- if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL)
- goto next;
- off = i + insn[i].off + 1;
- if (off < subprog_start || off >= subprog_end) {
- verbose(env, "jump out of range from insn %d to %d\n", i, off);
- return -EINVAL;
- }
-next:
- if (i == subprog_end - 1) {
- /* to avoid fall-through from one subprog into another
- * the last insn of the subprog should be either exit
- * or unconditional jump back
- */
- if (code != (BPF_JMP | BPF_EXIT) &&
- code != (BPF_JMP | BPF_JA)) {
- verbose(env, "last insn is not an exit or jmp\n");
- return -EINVAL;
- }
- subprog_start = subprog_end;
- if (env->subprog_cnt == cur_subprog)
- subprog_end = insn_cnt;
- else
- subprog_end = env->subprog_starts[cur_subprog++];
- }
- }
- return 0;
+ ret = env->subprog_cnt++;
+ info = &env->subprog_info[ret];
+ info->start = off;
+ info->stack_depth = 0;
+ memset(info->callees, 0, sizeof(info->callees));
+ return ret;
}
static
@@ -1470,80 +1408,84 @@ static int update_stack_depth(struct bpf_verifier_env *env,
const struct bpf_func_state *func,
int off)
{
- u16 stack = env->subprog_stack_depth[func->subprogno];
+ struct bpf_subprog_info *info;
- if (stack >= -off)
- return 0;
+ if (!func) return -EFAULT;
+ if (func->subprogno >= BPF_MAX_SUBPROGS) return -E2BIG;
+ info = &env->subprog_info[func->subprogno];
/* update known max for given subprogram */
- env->subprog_stack_depth[func->subprogno] = -off;
+ info->stack_depth = max_t(u16, info->stack_depth, -off);
return 0;
}
-/* starting from main bpf function walk all instructions of the function
- * and recursively walk all callees that given function can call.
- * Ignore jump and exit insns.
- * Since recursion is prevented by check_cfg() this algorithm
- * only needs a local stack of MAX_CALL_FRAMES to remember callsites
+/* Topologically sort the call graph, and thereby determine the maximum stack
+ * depth of each subprog's worst-case call chain. Store in total_stack_depth.
+ * The tsort is performed using Kahn's algorithm.
*/
static int check_max_stack_depth(struct bpf_verifier_env *env)
{
- int depth = 0, frame = 0, subprog = 0, i = 0, subprog_end;
- struct bpf_insn *insn = env->prog->insnsi;
- int insn_cnt = env->prog->len;
- int ret_insn[MAX_CALL_FRAMES];
- int ret_prog[MAX_CALL_FRAMES];
-
-process_func:
- /* round up to 32-bytes, since this is granularity
- * of interpreter stack size
- */
- depth += round_up(max_t(u32, env->subprog_stack_depth[subprog], 1), 32);
- if (depth > MAX_BPF_STACK) {
- verbose(env, "combined stack size of %d calls is %d. Too large\n",
- frame + 1, depth);
- return -EACCES;
- }
-continue_func:
- if (env->subprog_cnt == subprog)
- subprog_end = insn_cnt;
- else
- subprog_end = env->subprog_starts[subprog];
- for (; i < subprog_end; i++) {
- if (insn[i].code != (BPF_JMP | BPF_CALL))
- continue;
- if (insn[i].src_reg != BPF_PSEUDO_CALL)
- continue;
- /* remember insn and function to return to */
- ret_insn[frame] = i + 1;
- ret_prog[frame] = subprog;
-
- /* find the callee */
- i = i + insn[i].imm + 1;
- subprog = find_subprog(env, i);
- if (subprog < 0) {
- WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
- i);
- return -EFAULT;
+ DECLARE_BITMAP(frontier, BPF_MAX_SUBPROGS) = {0};
+ DECLARE_BITMAP(visited, BPF_MAX_SUBPROGS) = {0};
+ int subprog, i, j;
+
+ /* subprog 0 has no incoming edges, and should be the only such */
+ __set_bit(0, frontier);
+ env->subprog_info[0].total_stack_depth = env->subprog_info[0].stack_depth;
+
+ while (true) {
+ /* select a frontier node */
+ subprog = find_first_bit(frontier, BPF_MAX_SUBPROGS);
+ if (subprog >= BPF_MAX_SUBPROGS) /* frontier is empty, done */
+ break;
+ /* remove it from the frontier */
+ __clear_bit(subprog, frontier);
+ /* validate its total stack depth */
+ if (env->subprog_info[subprog].total_stack_depth > MAX_BPF_STACK) {
+ verbose(env, "combined stack size of calls to %d (at insn %d) is %d. Too large\n",
+ subprog, env->subprog_info[subprog].start,
+ env->subprog_info[subprog].total_stack_depth);
+ return -EACCES;
}
- subprog++;
- frame++;
- if (frame >= MAX_CALL_FRAMES) {
- WARN_ONCE(1, "verifier bug. Call stack is too deep\n");
- return -EFAULT;
+ if (env->log.level > 1) {
+ verbose(env, "combined stack size of calls to %d (at insn %d) is %d\n",
+ subprog, env->subprog_info[subprog].start,
+ env->subprog_info[subprog].total_stack_depth);
+ }
+ __set_bit(subprog, visited);
+ /* for each callee */
+ for_each_set_bit(i, env->subprog_info[subprog].callees,
+ BPF_MAX_SUBPROGS) {
+ /* round up to 32-bytes, since this is granularity of
+ * interpreter stack size
+ */
+ u16 stack_depth = round_up(max_t(u16, env->subprog_info[i].stack_depth, 1), 32);
+
+ /* Update callee total stack depth */
+ env->subprog_info[i].total_stack_depth = max_t(u16,
+ env->subprog_info[i].total_stack_depth,
+ env->subprog_info[subprog].total_stack_depth +
+ stack_depth);
+ /* does it have unvisited callers? */
+ for_each_clear_bit(j, visited, env->subprog_cnt) {
+ if (test_bit(i, env->subprog_info[j].callees))
+ break;
+ }
+ /* if not, add it to the frontier */
+ if (j >= env->subprog_cnt)
+ __set_bit(i, frontier);
}
- goto process_func;
}
- /* end of for() loop means the last insn of the 'subprog'
- * was reached. Doesn't matter whether it was JA or EXIT
- */
- if (frame == 0)
- return 0;
- depth -= round_up(max_t(u32, env->subprog_stack_depth[subprog], 1), 32);
- frame--;
- i = ret_insn[frame];
- subprog = ret_prog[frame];
- goto continue_func;
+
+ /* are any nodes left unvisited? */
+ subprog = find_first_zero_bit(visited, env->subprog_cnt);
+ if (subprog < env->subprog_cnt) {
+ /* then call graph is not acyclic, which shouldn't happen */
+ verbose(env, "verifier bug. Call graph has a cycle including subprog %d (at insn %d)\n",
+ subprog, env->subprog_info[subprog].start);
+ return -EFAULT;
+ }
+ return 0;
}
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
@@ -1558,8 +1500,7 @@ static int get_callee_stack_depth(struct bpf_verifier_env *env,
start);
return -EFAULT;
}
- subprog++;
- return env->subprog_stack_depth[subprog];
+ return env->subprog_info[subprog].stack_depth;
}
#endif
@@ -2097,7 +2038,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
case BPF_FUNC_tail_call:
if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
goto error;
- if (env->subprog_cnt) {
+ if (env->subprog_cnt > 1) {
verbose(env, "tail_calls are not allowed in programs with bpf-to-bpf calls\n");
return -EINVAL;
}
@@ -2233,22 +2174,33 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
{
struct bpf_verifier_state *state = env->cur_state;
struct bpf_func_state *caller, *callee;
- int i, subprog, target_insn;
+ int i, subprog, target;
if (state->curframe + 1 >= MAX_CALL_FRAMES) {
verbose(env, "the call stack of %d frames is too deep\n",
state->curframe + 2);
return -E2BIG;
}
-
- target_insn = *insn_idx + insn->imm;
- subprog = find_subprog(env, target_insn + 1);
- if (subprog < 0) {
- verbose(env, "verifier bug. No program starts at insn %d\n",
- target_insn + 1);
- return -EFAULT;
+ if (!env->allow_ptr_leaks) {
+ verbose(env, "function calls to other bpf functions are allowed for root only\n");
+ return -EPERM;
+ }
+ if (bpf_prog_is_dev_bound(env->prog->aux)) {
+ verbose(env, "function calls in offloaded programs are not supported yet\n");
+ return -EINVAL;
}
+
+ target = *insn_idx + insn->imm;
+ /* We will increment insn_idx (PC) in do_check() after handling this
+ * call insn, so the actual start of the function is target + 1.
+ */
+ subprog = find_subprog(env, target + 1);
+ if (subprog == -ENOENT)
+ subprog = add_subprog(env, target + 1);
+ if (subprog < 0)
+ return subprog;
+
caller = state->frame[state->curframe];
if (state->frame[state->curframe + 1]) {
verbose(env, "verifier bug. Frame %d already allocated\n",
@@ -2261,6 +2213,9 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
return -ENOMEM;
state->frame[state->curframe + 1] = callee;
+ /* record edge in call graph */
+ __set_bit(subprog, env->subprog_info[caller->subprogno].callees);
+
/* callee cannot access r0, r6 - r9 for reading and has to write
* into its own stack before reading from it.
* callee can read/write into caller's stack
@@ -2269,7 +2224,7 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
/* remember the callsite, it will be used by bpf_exit */
*insn_idx /* callsite */,
state->curframe + 1 /* frameno within this callchain */,
- subprog + 1 /* subprog number within this prog */);
+ subprog /* subprog number within this prog */);
/* copy r1 - r5 args that callee can access */
for (i = BPF_REG_1; i <= BPF_REG_5; i++)
@@ -2285,7 +2240,7 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
state->curframe++;
/* and go analyze first insn of the callee */
- *insn_idx = target_insn;
+ *insn_idx = target;
if (env->log.level) {
verbose(env, "caller:\n");
@@ -3828,13 +3783,13 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
return -EINVAL;
}
- if (env->subprog_cnt) {
+ if (env->seen_pseudo_call) {
/* when program has LD_ABS insn JITs and interpreter assume
* that r1 == ctx == skb which is not the case for callees
* that can have arbitrary arguments. It's problematic
* for main prog as well since JITs would need to analyze
* all functions in order to make proper register save/restore
- * decisions in the main prog. Hence disallow LD_ABS with calls
+ * decisions in the main prog. Hence disallow LD_ABS with calls.
*/
verbose(env, "BPF_LD_[ABS|IND] instructions cannot be mixed with bpf-to-bpf calls\n");
return -EINVAL;
@@ -4016,10 +3971,6 @@ static int check_cfg(struct bpf_verifier_env *env)
int ret = 0;
int i, t;
- ret = check_subprogs(env);
- if (ret < 0)
- return ret;
-
insn_state = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
if (!insn_state)
return -ENOMEM;
@@ -4053,6 +4004,7 @@ static int check_cfg(struct bpf_verifier_env *env)
if (t + 1 < insn_cnt)
env->explored_states[t + 1] = STATE_LIST_MARK;
if (insns[t].src_reg == BPF_PSEUDO_CALL) {
+ env->seen_pseudo_call = true;
env->explored_states[t] = STATE_LIST_MARK;
ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env);
if (ret == 1)
@@ -4534,6 +4486,52 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
return 0;
}
+/* Checks that all subprogs are contiguous */
+static int validate_subprogs(struct bpf_verifier_env *env)
+{
+ int cur_subprog = -1, i;
+
+ for (i = 0; i < env->prog->len; i++) {
+ struct bpf_insn_aux_data *aux = &env->insn_aux_data[i];
+
+ if (!aux->seen) {
+ if (cur_subprog < 0) { /* can't happen */
+ verbose(env, "unseen insn %d before subprog\n",
+ i);
+ return -EINVAL;
+ }
+ /* unreachable code belongs to the subprog in which it
+ * is embedded. Otherwise a forward jump could create
+ * an apparently non-contiguous subprog.
+ */
+ aux->subprogno = cur_subprog;
+ continue;
+ }
+ if (aux->subprogno != cur_subprog) {
+ /* change of subprog should only happen at start of
+ * new subprog, since subprog must start with entry
+ * point & be contiguous thereafter.
+ */
+ if (unlikely(aux->subprogno >= env->subprog_cnt)) {
+ /* can't happen */
+ verbose(env, "verifier ran off subprog array, "
+ "%u >= %u\n",
+ aux->subprogno, env->subprog_cnt);
+ return -EINVAL;
+ }
+ if (env->subprog_info[aux->subprogno].start != i) {
+ verbose(env, "subprog %u is non-contiguous at %d\n",
+ aux->subprogno, i);
+ return -EINVAL;
+ }
+ /* entered new subprog */
+ cur_subprog = aux->subprogno;
+ }
+ }
+
+ return 0;
+}
+
static int do_check(struct bpf_verifier_env *env)
{
struct bpf_verifier_state *state;
@@ -4542,6 +4540,7 @@ static int do_check(struct bpf_verifier_env *env)
int insn_cnt = env->prog->len, i;
int insn_idx, prev_insn_idx = 0;
int insn_processed = 0;
+ int mainprogno;
bool do_print_state = false;
state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL);
@@ -4555,12 +4554,17 @@ static int do_check(struct bpf_verifier_env *env)
return -ENOMEM;
}
env->cur_state = state;
+ mainprogno = add_subprog(env, 0);
+ if (mainprogno < 0)
+ return mainprogno;
init_func_state(env, state->frame[0],
BPF_MAIN_FUNC /* callsite */,
0 /* frameno */,
- 0 /* subprogno, zero == main subprog */);
+ mainprogno /* subprogno */);
insn_idx = 0;
for (;;) {
+ struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx];
+ struct bpf_func_state *frame = cur_frame(env);
struct bpf_insn *insn;
u8 class;
int err;
@@ -4581,6 +4585,17 @@ static int do_check(struct bpf_verifier_env *env)
return -E2BIG;
}
+ /* check the insn doesn't appear in multiple subprogs, which
+ * would imply bad function calls/returns/jumps
+ */
+ if (aux->seen && aux->subprogno != frame->subprogno) {
+ verbose(env, "insn %d was in subprog %u, now %u\n",
+ insn_idx, aux->subprogno, frame->subprogno);
+ return -EINVAL;
+ }
+ aux->subprogno = frame->subprogno;
+ aux->seen = true;
+
err = is_state_visited(env, insn_idx);
if (err < 0)
return err;
@@ -4605,7 +4620,7 @@ static int do_check(struct bpf_verifier_env *env)
else
verbose(env, "\nfrom %d to %d:",
prev_insn_idx, insn_idx);
- print_verifier_state(env, state->frame[state->curframe]);
+ print_verifier_state(env, frame);
do_print_state = false;
}
@@ -4627,7 +4642,6 @@ static int do_check(struct bpf_verifier_env *env)
}
regs = cur_regs(env);
- env->insn_aux_data[insn_idx].seen = true;
if (class == BPF_ALU || class == BPF_ALU64) {
err = check_alu_op(env, insn);
if (err)
@@ -4843,7 +4857,15 @@ static int do_check(struct bpf_verifier_env *env)
return err;
insn_idx++;
- env->insn_aux_data[insn_idx].seen = true;
+ /* Mark second half of LD_IMM64 insn */
+ aux++;
+ if (aux->seen && aux->subprogno != frame->subprogno) {
+ verbose(env, "insn %d was in subprog %u, now %u\n",
+ insn_idx, aux->subprogno, frame->subprogno);
+ return -EINVAL;
+ }
+ aux->subprogno = frame->subprogno;
+ aux->seen = true;
} else {
verbose(env, "invalid BPF_LD mode\n");
return -EINVAL;
@@ -4858,16 +4880,16 @@ static int do_check(struct bpf_verifier_env *env)
verbose(env, "processed %d insns (limit %d), stack depth ",
insn_processed, BPF_COMPLEXITY_LIMIT_INSNS);
- for (i = 0; i < env->subprog_cnt + 1; i++) {
- u32 depth = env->subprog_stack_depth[i];
+ for (i = 0; i < env->subprog_cnt; i++) {
+ u32 depth = env->subprog_info[i].stack_depth;
- verbose(env, "%d", depth);
- if (i + 1 < env->subprog_cnt + 1)
+ if (i)
verbose(env, "+");
+ verbose(env, "%d", depth);
}
verbose(env, "\n");
- env->prog->aux->stack_depth = env->subprog_stack_depth[0];
- return 0;
+ env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
+ return validate_subprogs(env);
}
static int check_map_prealloc(struct bpf_map *map)
@@ -5059,8 +5081,10 @@ static int adjust_insn_aux_data(struct bpf_verifier_env *env, u32 prog_len,
memcpy(new_data, old_data, sizeof(struct bpf_insn_aux_data) * off);
memcpy(new_data + off + cnt - 1, old_data + off,
sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1));
- for (i = off; i < off + cnt - 1; i++)
+ for (i = off; i < off + cnt - 1; i++) {
new_data[i].seen = true;
+ new_data[i].subprogno = old_data[off].subprogno;
+ }
env->insn_aux_data = new_data;
vfree(old_data);
return 0;
@@ -5073,9 +5097,9 @@ static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len
if (len == 1)
return;
for (i = 0; i < env->subprog_cnt; i++) {
- if (env->subprog_starts[i] < off)
+ if (env->subprog_info[i].start < off)
continue;
- env->subprog_starts[i] += len - 1;
+ env->subprog_info[i].start += len - 1;
}
}
@@ -5234,15 +5258,19 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
static int jit_subprogs(struct bpf_verifier_env *env)
{
struct bpf_prog *prog = env->prog, **func, *tmp;
- int i, j, subprog_start, subprog_end = 0, len, subprog;
+ int i, j, subprog;
struct bpf_insn *insn;
void *old_bpf_func;
int err = -ENOMEM;
- if (env->subprog_cnt == 0)
+ if (env->subprog_cnt <= 1)
return 0;
+ for (i = 0; i <= env->subprog_cnt; i++)
+ env->subprog_info[i].len = 0;
+
for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
+ env->subprog_info[env->insn_aux_data[i].subprogno].len++;
if (insn->code != (BPF_JMP | BPF_CALL) ||
insn->src_reg != BPF_PSEUDO_CALL)
continue;
@@ -5255,7 +5283,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
/* temporarily remember subprog id inside insn instead of
* aux_data, since next loop will split up all insns into funcs
*/
- insn->off = subprog + 1;
+ insn->off = subprog;
/* remember original imm in case JIT fails and fallback
* to interpreter will be needed
*/
@@ -5264,25 +5292,37 @@ static int jit_subprogs(struct bpf_verifier_env *env)
insn->imm = 1;
}
- func = kzalloc(sizeof(prog) * (env->subprog_cnt + 1), GFP_KERNEL);
+ func = kzalloc(sizeof(prog) * env->subprog_cnt, GFP_KERNEL);
if (!func)
return -ENOMEM;
- for (i = 0; i <= env->subprog_cnt; i++) {
- subprog_start = subprog_end;
- if (env->subprog_cnt == i)
- subprog_end = prog->len;
- else
- subprog_end = env->subprog_starts[i];
+ for (i = 0; i < env->subprog_cnt; i++) {
+ struct bpf_subprog_info *info = &env->subprog_info[i];
+ int k = 0;
- len = subprog_end - subprog_start;
- func[i] = bpf_prog_alloc(bpf_prog_size(len), GFP_USER);
+ func[i] = bpf_prog_alloc(bpf_prog_size(info->len), GFP_USER);
if (!func[i])
goto out_free;
- memcpy(func[i]->insnsi, &prog->insnsi[subprog_start],
- len * sizeof(struct bpf_insn));
+
+ for (j = 0; j < prog->len; j++) {
+ if (env->insn_aux_data[j].subprogno != i)
+ continue;
+ if (WARN_ON_ONCE(k >= info->len)) {
+ verbose(env, "Tried to add insn %d to subprog %d but previously counted %d\n",
+ k, i, info->len);
+ err = -EFAULT;
+ goto out_free;
+ }
+ memcpy(func[i]->insnsi + k++, prog->insnsi + j,
+ sizeof(struct bpf_insn));
+ }
+ if (WARN_ON_ONCE(k != info->len)) {
+ verbose(env, "Only %d insns in subprog %d but previously counted %d\n",
+ k, i, info->len);
+ }
+
func[i]->type = prog->type;
- func[i]->len = len;
+ func[i]->len = info->len;
if (bpf_prog_calc_tag(func[i]))
goto out_free;
func[i]->is_func = 1;
@@ -5290,7 +5330,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
* Long term would need debug info to populate names
*/
func[i]->aux->name[0] = 'F';
- func[i]->aux->stack_depth = env->subprog_stack_depth[i];
+ func[i]->aux->stack_depth = env->subprog_info[i].stack_depth;
func[i]->jit_requested = 1;
func[i] = bpf_int_jit_compile(func[i]);
if (!func[i]->jited) {
@@ -5303,7 +5343,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
* now populate all bpf_calls with correct addresses and
* run last pass of JIT
*/
- for (i = 0; i <= env->subprog_cnt; i++) {
+ for (i = 0; i < env->subprog_cnt; i++) {
insn = func[i]->insnsi;
for (j = 0; j < func[i]->len; j++, insn++) {
if (insn->code != (BPF_JMP | BPF_CALL) ||
@@ -5311,12 +5351,16 @@ static int jit_subprogs(struct bpf_verifier_env *env)
continue;
subprog = insn->off;
insn->off = 0;
+ if (subprog < 0 || subprog >= env->subprog_cnt) {
+ err = -EFAULT;
+ goto out_free;
+ }
insn->imm = (u64 (*)(u64, u64, u64, u64, u64))
func[subprog]->bpf_func -
__bpf_call_base;
}
}
- for (i = 0; i <= env->subprog_cnt; i++) {
+ for (i = 0; i < env->subprog_cnt; i++) {
old_bpf_func = func[i]->bpf_func;
tmp = bpf_int_jit_compile(func[i]);
if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) {
@@ -5330,7 +5374,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
/* finally lock prog and jit images for all functions and
* populate kallsysm
*/
- for (i = 0; i <= env->subprog_cnt; i++) {
+ for (i = 0; i < env->subprog_cnt; i++) {
bpf_prog_lock_ro(func[i]);
bpf_prog_kallsyms_add(func[i]);
}
@@ -5347,7 +5391,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
continue;
insn->off = env->insn_aux_data[i].call_imm;
subprog = find_subprog(env, i + insn->off + 1);
- addr = (unsigned long)func[subprog + 1]->bpf_func;
+ addr = (unsigned long)func[subprog]->bpf_func;
addr &= PAGE_MASK;
insn->imm = (u64 (*)(u64, u64, u64, u64, u64))
addr - __bpf_call_base;
@@ -5356,10 +5400,10 @@ static int jit_subprogs(struct bpf_verifier_env *env)
prog->jited = 1;
prog->bpf_func = func[0]->bpf_func;
prog->aux->func = func;
- prog->aux->func_cnt = env->subprog_cnt + 1;
+ prog->aux->func_cnt = env->subprog_cnt;
return 0;
out_free:
- for (i = 0; i <= env->subprog_cnt; i++)
+ for (i = 0; i < env->subprog_cnt; i++)
if (func[i])
bpf_jit_free(func[i]);
kfree(func);
@@ -5389,6 +5433,7 @@ static int fixup_call_args(struct bpf_verifier_env *env)
err = jit_subprogs(env);
if (err == 0)
return 0;
+ verbose(env, "failed to jit_subprogs %d\n", err);
}
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
for (i = 0; i < prog->len; i++, insn++) {
^ permalink raw reply related
* [PATCH v2 bpf-next 0/3] bpf/verifier: subprog/func_call simplifications
From: Edward Cree @ 2018-03-29 22:44 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann; +Cc: netdev
By storing subprog boundaries as a subprogno mark on each insn, rather than
a start (and implicit end) for each subprog, we collect a number of gains:
* More efficient determination of which subprog contains a given insn, and
thus of find_subprog (which subprog begins at a given insn).
* Number of verifier "full recursive walk" passes is reduced, since most of
the work is done in the main insn walk (do_check()). Leftover work in
other passes is mostly linear scans (O(insn_cnt)) or, in the case of
check_max_stack_depth(), a topological sort (O(subprog_cnt)).
Some other changes were also included to support this:
* Per-subprog info is stored in env->subprog_info, an array of structs,
rather than several arrays with a common index.
* Call graph is now stored in the new bpf_subprog_info struct; used here
for check_max_stack_depth() but may have other uses too.
Along with this, patch #3 puts parent pointers (used by liveness analysis)
in the registers instead of the func_state or verifier_state, so that we
don't need skip_callee() machinery. This also does the right thing for
stack slots, so they don't need their own special handling for liveness
marking either.
Edward Cree (3):
bpf/verifier: validate func_calls by marking at do_check() time
bpf/verifier: update selftests
bpf/verifier: per-register parent pointers
include/linux/bpf_verifier.h | 32 +-
kernel/bpf/verifier.c | 631 +++++++++++++---------------
tools/testing/selftests/bpf/test_verifier.c | 51 ++-
3 files changed, 344 insertions(+), 370 deletions(-)
^ permalink raw reply
* Re: [PATCH 07/30] aio: add delayed cancel support
From: Al Viro @ 2018-03-29 22:35 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180329203328.3248-8-hch@lst.de>
On Thu, Mar 29, 2018 at 10:33:05PM +0200, Christoph Hellwig wrote:
> The upcoming aio poll support would like to be able to complete the
> iocb inline from the cancellation context, but that would cause a
> double lock of ctx_lock with the current locking scheme. Move the
> cancelation outside the context lock to avoid this reversal, which
> suits the existing usb gadgets users just fine as well (in fact
> both unconditionally disable irqs and thus seem broken without
> this change).
>
> To make this safe aio_complete needs to check if this call should
> complete the iocb. If it didn't the callers must not release any
> other resources.
Uh-oh... What happens to existing users of kiocb_set_cancel_fn() now?
AFAICS, those guys will *not* get aio_kiocb freed at all in case of
io_cancel(2). Look: we mark them with AIO_IOCB_CANCELLED and
call whatever ->ki_cancel() the driver has set. Later the damn
thing calls ->ki_complete() (i.e. aio_complete_rw()), which calls
aio_complete(iocb, res, res2, 0) and gets false. Nothing's freed,
struct file is leaked.
Frankly, the more I look at that, the less I like what you've done
with ->ki_cancel() overloading. In regular case it's just accelerating
the call of ->ki_complete(), which will do freeing. Here you have
->ki_cancel() free the damn thing, with the resulting need to play
silly buggers with locking, freeing logics in aio_complete(), etc.
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply
* Re: [PATCH net-next 0/6] rxrpc: Fixes
From: David Howells @ 2018-03-29 22:25 UTC (permalink / raw)
To: David Miller; +Cc: dhowells, netdev, linux-afs, linux-kernel
In-Reply-To: <20180329.115956.476747368912393740.davem@davemloft.net>
David Miller <davem@davemloft.net> wrote:
> David, this GIT URL has tons of unrelated changes. It seems to bring in
> the parts of Linus's tree that haven't proagated to 'net' yet.
Sorry about that, I rebased on the wrong branch by accident.
I've got some more fixes. Should I just give the lot to you to pull into your
net-next tree, given that the merge window may well open Sunday?
David
^ permalink raw reply
* [PATCH iproute2-next 1/1] tc: add online mode
From: Roman Mashak @ 2018-03-29 22:12 UTC (permalink / raw)
To: dsahern; +Cc: stephen, netdev, kernel, jhs, xiyou.wangcong, jiri, Roman Mashak
Add initial support for oneline mode in tc; actions, filters and qdiscs
will be gradually updated in the follow-up patches.
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
---
man/man8/tc.8 | 15 ++++++++++++++-
tc/tc.c | 8 +++++++-
2 files changed, 21 insertions(+), 2 deletions(-)
diff --git a/man/man8/tc.8 b/man/man8/tc.8
index 3dc30ee489e5..840880fbdba6 100644
--- a/man/man8/tc.8
+++ b/man/man8/tc.8
@@ -95,7 +95,8 @@ tc \- show / manipulate traffic control settings
\fB[ \fB-n\fR[\fIetns\fR] name \fB] \fR|
\fB[ \fB-nm \fR| \fB-nam\fR[\fIes\fR] \fB] \fR|
\fB[ \fR{ \fB-cf \fR| \fB-c\fR[\fIonf\fR] \fR} \fB[ filename ] \fB] \fR
-\fB[ -t\fR[imestamp\fR] \fB\] \fR| \fB[ -t\fR[short\fR] \fB]\fR }
+\fB[ -t\fR[imestamp\fR] \fB\] \fR| \fB[ -t\fR[short\fR] \fR| \fB[
+-o\fR[neline\fR] \fB]\fR }
.ti 8
.IR FORMAT " := {"
@@ -649,6 +650,18 @@ don't terminate tc on errors in batch mode.
If there were any errors during execution of the commands, the application return code will be non zero.
.TP
+.BR "\-o" , " \-oneline"
+output each record on a single line, replacing line feeds
+with the
+.B '\e'
+character. This is convenient when you want to count records
+with
+.BR wc (1)
+or to
+.BR grep (1)
+the output.
+
+.TP
.BR "\-n" , " \-net" , " \-netns " <NETNS>
switches
.B tc
diff --git a/tc/tc.c b/tc/tc.c
index a31f075d1ffe..68475c156057 100644
--- a/tc/tc.c
+++ b/tc/tc.c
@@ -42,6 +42,8 @@ int force;
bool use_names;
int json;
int color;
+int oneline;
+const char *_SL_;
static char *conf_file;
@@ -191,7 +193,7 @@ static void usage(void)
"where OBJECT := { qdisc | class | filter | action | monitor | exec }\n"
" OPTIONS := { -s[tatistics] | -d[etails] | -r[aw] | -b[atch] [filename] | -n[etns] name |\n"
" -nm | -nam[es] | { -cf | -conf } path } |\n"
- " -j[son] -p[retty] -c[olor]\n");
+ " -o[neline] -j[son] -p[retty] -c[olor]\n");
}
static int do_cmd(int argc, char **argv, void *buf, size_t buflen)
@@ -487,6 +489,8 @@ int main(int argc, char **argv)
++timestamp_short;
} else if (matches(argv[1], "-json") == 0) {
++json;
+ } else if (matches(argv[1], "-oneline") == 0) {
+ ++oneline;
} else {
fprintf(stderr, "Option \"%s\" is unknown, try \"tc -help\".\n", argv[1]);
return -1;
@@ -494,6 +498,8 @@ int main(int argc, char **argv)
argc--; argv++;
}
+ _SL_ = oneline ? "\\" : "\n";
+
if (color & !json)
enable_color();
--
2.7.4
^ permalink raw reply related
* WARNING in refcount_sub_and_test (2)
From: syzbot @ 2018-03-29 22:01 UTC (permalink / raw)
To: davem, kuznet, linux-kernel, netdev, syzkaller-bugs, yoshfuji
Hello,
syzbot hit the following crash on bpf-next commit
22527437e0a0c96ee3153e9d0382942b0fd4f9dd (Thu Mar 29 02:36:15 2018 +0000)
Merge branch 'nfp-bpf-updates'
syzbot dashboard link:
https://syzkaller.appspot.com/bug?extid=c7b0dde061c523bc4b0f
C reproducer: https://syzkaller.appspot.com/x/repro.c?id=5996614741131264
syzkaller reproducer:
https://syzkaller.appspot.com/x/repro.syz?id=5947747274326016
Raw console output:
https://syzkaller.appspot.com/x/log.txt?id=6215237837520896
Kernel config:
https://syzkaller.appspot.com/x/.config?id=-1280663959502969741
compiler: gcc (GCC) 7.1.1 20170620
IMPORTANT: if you fix the bug, please add the following tag to the commit:
Reported-by: syzbot+c7b0dde061c523bc4b0f@syzkaller.appspotmail.com
It will help syzbot understand when the bug is fixed. See footer for
details.
If you forward the report, please keep this part and the footer.
R13: 0030656c69662f2e R14: 0000000000000005 R15: 2f30656c69662f2e
------------[ cut here ]------------
------------[ cut here ]------------
refcount_t: increment on 0; use-after-free.
refcount_t: underflow; use-after-free.
WARNING: CPU: 0 PID: 4450 at lib/refcount.c:187
refcount_sub_and_test+0x167/0x1b0 lib/refcount.c:187
WARNING: CPU: 1 PID: 4460 at lib/refcount.c:153 refcount_inc+0x47/0x50
lib/refcount.c:153
Kernel panic - not syncing: panic_on_warn set ...
Modules linked in:
CPU: 0 PID: 4450 Comm: syzkaller428798 Not tainted 4.16.0-rc6+ #40
CPU: 1 PID: 4460 Comm: syzkaller428798 Not tainted 4.16.0-rc6+ #40
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
Call Trace:
RIP: 0010:refcount_inc+0x47/0x50 lib/refcount.c:153
__dump_stack lib/dump_stack.c:17 [inline]
dump_stack+0x194/0x24d lib/dump_stack.c:53
RSP: 0018:ffff8801b534f860 EFLAGS: 00010286
RAX: dffffc0000000008 RBX: ffff8801b1b8c184 RCX: ffffffff815ba4be
panic+0x1e4/0x41c kernel/panic.c:183
RDX: 0000000000000000 RSI: 1ffff10036a69ebc RDI: 1ffff10036a69e91
RBP: ffff8801b534f868 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: ffff8801b534faf8
R13: ffff8801b04db513 R14: ffff8801b1b8c180 R15: ffff8801b04db501
FS: 00000000008e6880(0000) GS:ffff8801db300000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
__warn+0x1dc/0x200 kernel/panic.c:547
CR2: 00000000006ea510 CR3: 00000001b106f005 CR4: 00000000001606e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
report_bug+0x1f4/0x2b0 lib/bug.c:186
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
fixup_bug.part.11+0x37/0x80 arch/x86/kernel/traps.c:178
Call Trace:
fixup_bug arch/x86/kernel/traps.c:247 [inline]
do_error_trap+0x2d7/0x3e0 arch/x86/kernel/traps.c:296
get_net include/net/net_namespace.h:204 [inline]
sk_alloc+0x3f9/0x1440 net/core/sock.c:1540
do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:315
invalid_op+0x1b/0x40 arch/x86/entry/entry_64.S:986
RIP: 0010:refcount_sub_and_test+0x167/0x1b0 lib/refcount.c:187
RSP: 0018:ffff8801b0e87728 EFLAGS: 00010286
RAX: dffffc0000000008 RBX: 0000000000000000 RCX: ffffffff815ba4be
RDX: 0000000000000000 RSI: 1ffff100361d0e95 RDI: 0000000000000293
RBP: ffff8801b0e877b8 R08: 0000000000000000 R09: 0000000000000000
R10: ffff8801b0e87850 R11: 0000000000000000 R12: 1ffff100361d0ee6
inet_create+0x47c/0xf50 net/ipv4/af_inet.c:320
R13: 00000000ffffffff R14: 0000000000000001 R15: ffff8801b0816204
__sock_create+0x4d4/0x850 net/socket.c:1285
sock_create net/socket.c:1325 [inline]
SYSC_socket net/socket.c:1355 [inline]
SyS_socket+0xeb/0x1d0 net/socket.c:1335
refcount_dec_and_test+0x1a/0x20 lib/refcount.c:212
put_net include/net/net_namespace.h:222 [inline]
__sk_destruct+0x560/0x920 net/core/sock.c:1592
do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287
sk_destruct+0x47/0x80 net/core/sock.c:1601
entry_SYSCALL_64_after_hwframe+0x42/0xb7
__sk_free+0xf1/0x2b0 net/core/sock.c:1612
RIP: 0033:0x44ac67
sk_free+0x2a/0x40 net/core/sock.c:1623
RSP: 002b:00007ffcd4f45588 EFLAGS: 00000202
sock_put include/net/sock.h:1660 [inline]
tcp_close+0x967/0x1190 net/ipv4/tcp.c:2321
ORIG_RAX: 0000000000000029
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 000000000044ac67
RDX: 0000000000000006 RSI: 0000000000000001 RDI: 0000000000000002
RBP: 00007ffcd4f456b0 R08: 0000000000000000 R09: 0000000000000001
R10: 0000000000000006 R11: 0000000000000202 R12: 0000000000000002
inet_release+0xed/0x1c0 net/ipv4/af_inet.c:427
R13: 0000000000000002 R14: 000000000000b38f R15: 00007ffcd4f456d8
sock_release+0x8d/0x1e0 net/socket.c:594
Code:
be
sock_close+0x16/0x20 net/socket.c:1149
fe
__fput+0x327/0x7e0 fs/file_table.c:209
5b
5d
c3
____fput+0x15/0x20 fs/file_table.c:243
e8
task_work_run+0x199/0x270 kernel/task_work.c:113
5a
3c
be
fe
tracehook_notify_resume include/linux/tracehook.h:191 [inline]
exit_to_usermode_loop+0x275/0x2f0 arch/x86/entry/common.c:166
80
3d
91
prepare_exit_to_usermode arch/x86/entry/common.c:196 [inline]
syscall_return_slowpath arch/x86/entry/common.c:265 [inline]
do_syscall_64+0x6ec/0x940 arch/x86/entry/common.c:292
f5
84
05
00 75 ea e8 4c 3c be
fe
48
c7
c7
entry_SYSCALL_64_after_hwframe+0x42/0xb7
80
RIP: 0033:0x406fe0
78
RSP: 002b:00007ffcd4f45588 EFLAGS: 00000246
e5
ORIG_RAX: 0000000000000003
86
RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000406fe0
c6
RDX: 00000000000000e0 RSI: 00007ffcd4f45e70 RDI: 0000000000000003
05
RBP: 00007ffcd4f456b0 R08: 00007ffcd4f455b0 R09: 0000000000000001
7c
R10: 00007ffcd4f456b0 R11: 0000000000000246 R12: 00000000006de4c0
R13: 00000000006dde40 R14: 0000000000001380 R15: 00007ffcd4f456d8
f5 84 05 01 e8 f9 47 8e fe <0f> 0b eb ce 0f 1f 44 00 00 55 48 89 e5 41 57
41 56 41 55 41 54
---[ end trace 04af8119701e2164 ]---
Dumping ftrace buffer:
(ftrace buffer empty)
Kernel Offset: disabled
Rebooting in 86400 seconds..
---
This bug is generated by a dumb bot. It may contain errors.
See https://goo.gl/tpsmEJ for details.
Direct all questions to syzkaller@googlegroups.com.
syzbot will keep track of this bug report.
If you forgot to add the Reported-by tag, once the fix for this bug is
merged
into any tree, please reply to this email with:
#syz fix: exact-commit-title
If you want to test a patch for this bug, please reply with:
#syz test: git://repo/address.git branch
and provide the patch inline or as an attachment.
To mark this as a duplicate of another syzbot report, please reply with:
#syz dup: exact-subject-of-another-report
If it's a one-off invalid bug report, please reply with:
#syz invalid
Note: if the crash happens again, it will cause creation of a new bug
report.
Note: all commands must start from beginning of the line in the email body.
^ permalink raw reply
* [PATCH v4 iproute2-next 7/7] rdma: Add PD resource tracking information
From: Steve Wise @ 2018-03-29 16:10 UTC (permalink / raw)
To: dsahern; +Cc: leon, stephen, netdev, linux-rdma
In-Reply-To: <cover.1522359537.git.swise@opengridcomputing.com>
Sample output:
Without CAP_NET_ADMIN capability:
dev mlx4_0 users 0 pid 0 comm [ib_srpt]
dev mlx4_0 users 0 pid 0 comm [ib_srp]
dev mlx4_0 users 1 pid 0 comm [ib_core]
dev cxgb4_0 users 0 pid 0 comm [ib_srp]
With CAP_NET_ADMIN capability:
dev mlx4_0 local_dma_lkey 0x8000 users 0 pid 0 comm [ib_srpt]
dev mlx4_0 local_dma_lkey 0x8000 users 0 pid 0 comm [ib_srp]
dev mlx4_0 local_dma_lkey 0x8000 users 1 pid 0 comm [ib_core]
dev cxgb4_0 local_dma_lkey 0x0 users 0 pid 0 comm [ib_srp]
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
---
rdma/res.c | 95 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 95 insertions(+)
diff --git a/rdma/res.c b/rdma/res.c
index 9c1f736..1a0aab6 100644
--- a/rdma/res.c
+++ b/rdma/res.c
@@ -927,6 +927,91 @@ static int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data)
return MNL_CB_OK;
}
+static int res_pd_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+ struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
+ struct nlattr *nla_table, *nla_entry;
+ struct rd *rd = data;
+ const char *name;
+ uint32_t idx;
+
+ mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+ if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] ||
+ !tb[RDMA_NLDEV_ATTR_DEV_NAME] ||
+ !tb[RDMA_NLDEV_ATTR_RES_PD])
+ return MNL_CB_ERROR;
+
+ name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
+ idx = mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+ nla_table = tb[RDMA_NLDEV_ATTR_RES_PD];
+
+ mnl_attr_for_each_nested(nla_entry, nla_table) {
+ uint32_t local_dma_lkey = 0, unsafe_global_rkey = 0;
+ struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
+ char *comm = NULL;
+ uint32_t pid = 0;
+ uint64_t users;
+ int err;
+
+ err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
+ if (err != MNL_CB_OK)
+ return MNL_CB_ERROR;
+
+ if (!nla_line[RDMA_NLDEV_ATTR_RES_USECNT] ||
+ (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
+ !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
+ return MNL_CB_ERROR;
+ }
+
+ if (nla_line[RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY])
+ local_dma_lkey = mnl_attr_get_u32(
+ nla_line[RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY]);
+
+ users = mnl_attr_get_u64(nla_line[RDMA_NLDEV_ATTR_RES_USECNT]);
+ if (rd_check_is_filtered(rd, "users", users))
+ continue;
+
+ if (nla_line[RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY])
+ unsafe_global_rkey = mnl_attr_get_u32(
+ nla_line[RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY]);
+
+ if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
+ pid = mnl_attr_get_u32(
+ nla_line[RDMA_NLDEV_ATTR_RES_PID]);
+ comm = get_task_name(pid);
+ }
+
+ if (rd_check_is_filtered(rd, "pid", pid))
+ continue;
+
+ if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
+ /* discard const from mnl_attr_get_str */
+ comm = (char *)mnl_attr_get_str(
+ nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
+
+ if (rd->json_output)
+ jsonw_start_array(rd->jw);
+
+ print_dev(rd, idx, name);
+ if (nla_line[RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY])
+ print_key(rd, "local_dma_lkey", local_dma_lkey);
+ print_users(rd, users);
+ if (nla_line[RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY])
+ print_key(rd, "unsafe_global_rkey", unsafe_global_rkey);
+ print_pid(rd, pid);
+ print_comm(rd, comm, nla_line);
+
+ if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
+ free(comm);
+
+ if (rd->json_output)
+ jsonw_end_array(rd->jw);
+ else
+ pr_out("\n");
+ }
+ return MNL_CB_OK;
+}
+
RES_FUNC(res_no_args, RDMA_NLDEV_CMD_RES_GET, NULL, true);
static const struct
@@ -990,6 +1075,15 @@ struct filters mr_valid_filters[MAX_NUMBER_OF_FILTERS] = {
RES_FUNC(res_mr, RDMA_NLDEV_CMD_RES_MR_GET, mr_valid_filters, true);
+static const
+struct filters pd_valid_filters[MAX_NUMBER_OF_FILTERS] = {
+ { .name = "dev", .is_number = false },
+ { .name = "users", .is_number = true },
+ { .name = "pid", .is_number = true }
+};
+
+RES_FUNC(res_pd, RDMA_NLDEV_CMD_RES_PD_GET, pd_valid_filters, true);
+
static int res_show(struct rd *rd)
{
const struct rd_cmd cmds[] = {
@@ -998,6 +1092,7 @@ static int res_show(struct rd *rd)
{ "cm_id", res_cm_id },
{ "cq", res_cq },
{ "mr", res_mr },
+ { "pd", res_pd },
{ 0 }
};
--
1.8.3.1
^ permalink raw reply related
* [PATCH v4 iproute2-next 6/7] rdma: Add MR resource tracking information
From: Steve Wise @ 2018-03-29 16:10 UTC (permalink / raw)
To: dsahern; +Cc: leon, stephen, netdev, linux-rdma
In-Reply-To: <cover.1522359537.git.swise@opengridcomputing.com>
Sample output:
Without CAP_NET_ADMIN:
$ rdma resource show mr mrlen 65536
dev mlx4_0 mrlen 65536 pid 0 comm [nvme_rdma]
dev cxgb4_0 mrlen 65536 pid 0 comm [nvme_rdma]
With CAP_NET_ADMIN:
# rdma resource show mr mrlen 65536
dev mlx4_0 rkey 0x12702 lkey 0x12702 iova 0x85724a000 mrlen 65536 pid 0 comm [nvme_rdma]
dev cxgb4_0 rkey 0x68fe4e9 lkey 0x68fe4e9 iova 0x835b91000 mrlen 65536 pid 0 comm [nvme_rdma]
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
---
include/json_writer.h | 2 +
lib/json_writer.c | 11 +++++
rdma/res.c | 127 ++++++++++++++++++++++++++++++++++++++++++++++++++
rdma/utils.c | 6 +++
4 files changed, 146 insertions(+)
diff --git a/include/json_writer.h b/include/json_writer.h
index 45459fa..4b4dec2 100644
--- a/include/json_writer.h
+++ b/include/json_writer.h
@@ -35,6 +35,7 @@ void jsonw_bool(json_writer_t *self, bool value);
void jsonw_float(json_writer_t *self, double number);
void jsonw_float_fmt(json_writer_t *self, const char *fmt, double num);
void jsonw_uint(json_writer_t *self, uint64_t number);
+void jsonw_xint(json_writer_t *self, uint64_t number);
void jsonw_hu(json_writer_t *self, unsigned short number);
void jsonw_int(json_writer_t *self, int64_t number);
void jsonw_null(json_writer_t *self);
@@ -45,6 +46,7 @@ void jsonw_string_field(json_writer_t *self, const char *prop, const char *val);
void jsonw_bool_field(json_writer_t *self, const char *prop, bool value);
void jsonw_float_field(json_writer_t *self, const char *prop, double num);
void jsonw_uint_field(json_writer_t *self, const char *prop, uint64_t num);
+void jsonw_xint_field(json_writer_t *self, const char *prop, uint64_t num);
void jsonw_hu_field(json_writer_t *self, const char *prop, unsigned short num);
void jsonw_int_field(json_writer_t *self, const char *prop, int64_t num);
void jsonw_null_field(json_writer_t *self, const char *prop);
diff --git a/lib/json_writer.c b/lib/json_writer.c
index 68401ae..0ad0421 100644
--- a/lib/json_writer.c
+++ b/lib/json_writer.c
@@ -225,6 +225,11 @@ void jsonw_uint(json_writer_t *self, uint64_t num)
jsonw_printf(self, "%"PRIu64, num);
}
+void jsonw_xint(json_writer_t *self, uint64_t num)
+{
+ jsonw_printf(self, "%"PRIx64, num);
+}
+
void jsonw_lluint(json_writer_t *self, unsigned long long int num)
{
jsonw_printf(self, "%llu", num);
@@ -269,6 +274,12 @@ void jsonw_uint_field(json_writer_t *self, const char *prop, uint64_t num)
jsonw_uint(self, num);
}
+void jsonw_xint_field(json_writer_t *self, const char *prop, uint64_t num)
+{
+ jsonw_name(self, prop);
+ jsonw_xint(self, num);
+}
+
void jsonw_hu_field(json_writer_t *self, const char *prop, unsigned short num)
{
jsonw_name(self, prop);
diff --git a/rdma/res.c b/rdma/res.c
index bb5f3dd..9c1f736 100644
--- a/rdma/res.c
+++ b/rdma/res.c
@@ -812,6 +812,121 @@ static int res_cq_parse_cb(const struct nlmsghdr *nlh, void *data)
return MNL_CB_OK;
}
+static void print_key(struct rd *rd, const char *name, uint32_t val)
+{
+ if (rd->json_output)
+ jsonw_xint_field(rd->jw, name, val);
+ else
+ pr_out("%s 0x%x ", name, val);
+}
+
+static void print_iova(struct rd *rd, uint64_t val)
+{
+ if (rd->json_output)
+ jsonw_xint_field(rd->jw, "iova", val);
+ else
+ pr_out("iova 0x%" PRIx64 " ", val);
+}
+
+static void print_mrlen(struct rd *rd, uint64_t val)
+{
+ if (rd->json_output)
+ jsonw_uint_field(rd->jw, "mrlen", val);
+ else
+ pr_out("mrlen %" PRIu64 " ", val);
+}
+
+static int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+ struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
+ struct nlattr *nla_table, *nla_entry;
+ struct rd *rd = data;
+ const char *name;
+ uint32_t idx;
+
+ mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+ if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] ||
+ !tb[RDMA_NLDEV_ATTR_DEV_NAME] ||
+ !tb[RDMA_NLDEV_ATTR_RES_MR])
+ return MNL_CB_ERROR;
+
+ name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
+ idx = mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+ nla_table = tb[RDMA_NLDEV_ATTR_RES_MR];
+
+ mnl_attr_for_each_nested(nla_entry, nla_table) {
+ struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
+ uint32_t rkey = 0, lkey = 0;
+ uint64_t iova = 0, mrlen;
+ char *comm = NULL;
+ uint32_t pid = 0;
+ int err;
+
+ err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
+ if (err != MNL_CB_OK)
+ return MNL_CB_ERROR;
+
+ if (!nla_line[RDMA_NLDEV_ATTR_RES_MRLEN] ||
+ (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
+ !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
+ return MNL_CB_ERROR;
+ }
+
+ if (nla_line[RDMA_NLDEV_ATTR_RES_RKEY])
+ rkey = mnl_attr_get_u32(
+ nla_line[RDMA_NLDEV_ATTR_RES_RKEY]);
+ if (nla_line[RDMA_NLDEV_ATTR_RES_LKEY])
+ lkey = mnl_attr_get_u32(
+ nla_line[RDMA_NLDEV_ATTR_RES_LKEY]);
+ if (nla_line[RDMA_NLDEV_ATTR_RES_IOVA])
+ iova = mnl_attr_get_u64(
+ nla_line[RDMA_NLDEV_ATTR_RES_IOVA]);
+
+ mrlen = mnl_attr_get_u64(nla_line[RDMA_NLDEV_ATTR_RES_MRLEN]);
+ if (rd_check_is_filtered(rd, "mrlen", mrlen))
+ continue;
+
+ if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
+ pid = mnl_attr_get_u32(
+ nla_line[RDMA_NLDEV_ATTR_RES_PID]);
+ comm = get_task_name(pid);
+ }
+
+ if (rd_check_is_filtered(rd, "pid", pid)) {
+ free(comm);
+ continue;
+ }
+
+ if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
+ /* discard const from mnl_attr_get_str */
+ comm = (char *)mnl_attr_get_str(
+ nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
+
+ if (rd->json_output)
+ jsonw_start_array(rd->jw);
+
+ print_dev(rd, idx, name);
+ if (nla_line[RDMA_NLDEV_ATTR_RES_RKEY])
+ print_key(rd, "rkey", rkey);
+ if (nla_line[RDMA_NLDEV_ATTR_RES_LKEY])
+ print_key(rd, "lkey", lkey);
+ if (nla_line[RDMA_NLDEV_ATTR_RES_IOVA])
+ print_iova(rd, iova);
+ print_mrlen(rd, mrlen);
+ print_pid(rd, pid);
+ print_comm(rd, comm, nla_line);
+
+ if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
+ free(comm);
+
+ if (rd->json_output)
+ jsonw_end_array(rd->jw);
+ else
+ pr_out("\n");
+ }
+ return MNL_CB_OK;
+}
+
RES_FUNC(res_no_args, RDMA_NLDEV_CMD_RES_GET, NULL, true);
static const struct
@@ -864,6 +979,17 @@ struct filters cq_valid_filters[MAX_NUMBER_OF_FILTERS] = {
RES_FUNC(res_cq, RDMA_NLDEV_CMD_RES_CQ_GET, cq_valid_filters, true);
+static const
+struct filters mr_valid_filters[MAX_NUMBER_OF_FILTERS] = {
+ { .name = "dev", .is_number = false },
+ { .name = "rkey", .is_number = true },
+ { .name = "lkey", .is_number = true },
+ { .name = "mrlen", .is_number = true },
+ { .name = "pid", .is_number = true }
+};
+
+RES_FUNC(res_mr, RDMA_NLDEV_CMD_RES_MR_GET, mr_valid_filters, true);
+
static int res_show(struct rd *rd)
{
const struct rd_cmd cmds[] = {
@@ -871,6 +997,7 @@ static int res_show(struct rd *rd)
{ "qp", res_qp },
{ "cm_id", res_cm_id },
{ "cq", res_cq },
+ { "mr", res_mr },
{ 0 }
};
diff --git a/rdma/utils.c b/rdma/utils.c
index 5e79b62..a2e08e9 100644
--- a/rdma/utils.c
+++ b/rdma/utils.c
@@ -385,6 +385,12 @@ static const enum mnl_attr_data_type nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
[RDMA_NLDEV_ATTR_RES_CQE] = MNL_TYPE_U32,
[RDMA_NLDEV_ATTR_RES_USECNT] = MNL_TYPE_U64,
[RDMA_NLDEV_ATTR_RES_POLL_CTX] = MNL_TYPE_U8,
+ [RDMA_NLDEV_ATTR_RES_MR] = MNL_TYPE_NESTED,
+ [RDMA_NLDEV_ATTR_RES_MR_ENTRY] = MNL_TYPE_NESTED,
+ [RDMA_NLDEV_ATTR_RES_RKEY] = MNL_TYPE_U32,
+ [RDMA_NLDEV_ATTR_RES_LKEY] = MNL_TYPE_U32,
+ [RDMA_NLDEV_ATTR_RES_IOVA] = MNL_TYPE_U64,
+ [RDMA_NLDEV_ATTR_RES_MRLEN] = MNL_TYPE_U64,
};
int rd_attr_cb(const struct nlattr *attr, void *data)
--
1.8.3.1
^ permalink raw reply related
* [PATCH v4 iproute2-next 5/7] rdma: Add CQ resource tracking information
From: Steve Wise @ 2018-03-29 16:10 UTC (permalink / raw)
To: dsahern; +Cc: leon, stephen, netdev, linux-rdma
In-Reply-To: <cover.1522359537.git.swise@opengridcomputing.com>
Sample output:
# rdma resource show cq
dev cxgb4_0 cqe 46 users 2 pid 30503 comm rping
dev cxgb4_0 cqe 46 users 2 pid 30498 comm rping
dev mlx4_0 cqe 63 users 2 pid 30494 comm rping
dev mlx4_0 cqe 63 users 2 pid 30489 comm rping
dev mlx4_0 cqe 1023 users 2 poll_ctx WORKQUEUE pid 0 comm [ib_core]
# rdma resource show cq pid 30489
dev mlx4_0 cqe 63 users 2 pid 30489 comm rping
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
---
rdma/res.c | 149 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
rdma/utils.c | 5 ++
2 files changed, 154 insertions(+)
diff --git a/rdma/res.c b/rdma/res.c
index 5506cf3..bb5f3dd 100644
--- a/rdma/res.c
+++ b/rdma/res.c
@@ -21,6 +21,8 @@ static int res_help(struct rd *rd)
pr_out(" resource show qp link [DEV/PORT] [FILTER-NAME FILTER-VALUE]\n");
pr_out(" resource show cm_id link [DEV/PORT]\n");
pr_out(" resource show cm_id link [DEV/PORT] [FILTER-NAME FILTER-VALUE]\n");
+ pr_out(" resource show cq link [DEV/PORT]\n");
+ pr_out(" resource show cq link [DEV/PORT] [FILTER-NAME FILTER-VALUE]\n");
return 0;
}
@@ -265,6 +267,16 @@ static void print_comm(struct rd *rd, const char *str,
pr_out("comm %s ", tmp);
}
+static void print_dev(struct rd *rd, uint32_t idx, const char *name)
+{
+ if (rd->json_output) {
+ jsonw_uint_field(rd->jw, "ifindex", idx);
+ jsonw_string_field(rd->jw, "ifname", name);
+ } else {
+ pr_out("dev %s ", name);
+ }
+}
+
static void print_link(struct rd *rd, uint32_t idx, const char *name,
uint32_t port, struct nlattr **nla_line)
{
@@ -674,6 +686,132 @@ static int res_cm_id_parse_cb(const struct nlmsghdr *nlh, void *data)
return MNL_CB_OK;
}
+static void print_cqe(struct rd *rd, uint32_t val)
+{
+ if (rd->json_output)
+ jsonw_uint_field(rd->jw, "cqe", val);
+ else
+ pr_out("cqe %u ", val);
+}
+
+static void print_users(struct rd *rd, uint64_t val)
+{
+ if (rd->json_output)
+ jsonw_uint_field(rd->jw, "users", val);
+ else
+ pr_out("users %" PRIu64 " ", val);
+}
+
+static const char *poll_ctx_to_str(uint8_t idx)
+{
+ static const char * const cm_id_states_str[] = {
+ "DIRECT", "SOFTIRQ", "WORKQUEUE"};
+
+ if (idx < ARRAY_SIZE(cm_id_states_str))
+ return cm_id_states_str[idx];
+ return "UNKNOWN";
+}
+
+static void print_poll_ctx(struct rd *rd, uint8_t poll_ctx)
+{
+ if (rd->json_output) {
+ jsonw_string_field(rd->jw, "poll-ctx",
+ poll_ctx_to_str(poll_ctx));
+ return;
+ }
+ pr_out("poll-ctx %s ", poll_ctx_to_str(poll_ctx));
+}
+
+static int res_cq_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+ struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
+ struct nlattr *nla_table, *nla_entry;
+ struct rd *rd = data;
+ const char *name;
+ uint32_t idx;
+
+ mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+ if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] ||
+ !tb[RDMA_NLDEV_ATTR_DEV_NAME] ||
+ !tb[RDMA_NLDEV_ATTR_RES_CQ])
+ return MNL_CB_ERROR;
+
+ name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
+ idx = mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+ nla_table = tb[RDMA_NLDEV_ATTR_RES_CQ];
+
+ mnl_attr_for_each_nested(nla_entry, nla_table) {
+ struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
+ char *comm = NULL;
+ uint32_t pid = 0;
+ uint8_t poll_ctx = 0;
+ uint64_t users;
+ uint32_t cqe;
+ int err;
+
+ err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
+ if (err != MNL_CB_OK)
+ return MNL_CB_ERROR;
+
+ if (!nla_line[RDMA_NLDEV_ATTR_RES_CQE] ||
+ !nla_line[RDMA_NLDEV_ATTR_RES_USECNT] ||
+ (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
+ !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
+ return MNL_CB_ERROR;
+ }
+
+ cqe = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_CQE]);
+
+ users = mnl_attr_get_u64(nla_line[RDMA_NLDEV_ATTR_RES_USECNT]);
+ if (rd_check_is_filtered(rd, "users", users))
+ continue;
+
+ if (nla_line[RDMA_NLDEV_ATTR_RES_POLL_CTX]) {
+ poll_ctx = mnl_attr_get_u8(
+ nla_line[RDMA_NLDEV_ATTR_RES_POLL_CTX]);
+ if (rd_check_is_string_filtered(rd, "poll-ctx",
+ poll_ctx_to_str(poll_ctx)))
+ continue;
+ }
+
+ if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
+ pid = mnl_attr_get_u32(
+ nla_line[RDMA_NLDEV_ATTR_RES_PID]);
+ comm = get_task_name(pid);
+ }
+
+ if (rd_check_is_filtered(rd, "pid", pid)) {
+ free(comm);
+ continue;
+ }
+
+ if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
+ /* discard const from mnl_attr_get_str */
+ comm = (char *)mnl_attr_get_str(
+ nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
+
+ if (rd->json_output)
+ jsonw_start_array(rd->jw);
+
+ print_dev(rd, idx, name);
+ print_cqe(rd, cqe);
+ print_users(rd, users);
+ if (nla_line[RDMA_NLDEV_ATTR_RES_POLL_CTX])
+ print_poll_ctx(rd, poll_ctx);
+ print_pid(rd, pid);
+ print_comm(rd, comm, nla_line);
+
+ if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
+ free(comm);
+
+ if (rd->json_output)
+ jsonw_end_array(rd->jw);
+ else
+ pr_out("\n");
+ }
+ return MNL_CB_OK;
+}
+
RES_FUNC(res_no_args, RDMA_NLDEV_CMD_RES_GET, NULL, true);
static const struct
@@ -716,12 +854,23 @@ struct filters cm_id_valid_filters[MAX_NUMBER_OF_FILTERS] = {
RES_FUNC(res_cm_id, RDMA_NLDEV_CMD_RES_CM_ID_GET, cm_id_valid_filters, false);
+static const
+struct filters cq_valid_filters[MAX_NUMBER_OF_FILTERS] = {
+ { .name = "dev", .is_number = false },
+ { .name = "users", .is_number = true },
+ { .name = "poll-ctx", .is_number = false },
+ { .name = "pid", .is_number = true }
+};
+
+RES_FUNC(res_cq, RDMA_NLDEV_CMD_RES_CQ_GET, cq_valid_filters, true);
+
static int res_show(struct rd *rd)
{
const struct rd_cmd cmds[] = {
{ NULL, res_no_args },
{ "qp", res_qp },
{ "cm_id", res_cm_id },
+ { "cq", res_cq },
{ 0 }
};
diff --git a/rdma/utils.c b/rdma/utils.c
index ec81737..5e79b62 100644
--- a/rdma/utils.c
+++ b/rdma/utils.c
@@ -380,6 +380,11 @@ static const enum mnl_attr_data_type nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
[RDMA_NLDEV_ATTR_RES_PS] = MNL_TYPE_U32,
[RDMA_NLDEV_ATTR_RES_SRC_ADDR] = MNL_TYPE_UNSPEC,
[RDMA_NLDEV_ATTR_RES_DST_ADDR] = MNL_TYPE_UNSPEC,
+ [RDMA_NLDEV_ATTR_RES_CQ] = MNL_TYPE_NESTED,
+ [RDMA_NLDEV_ATTR_RES_CQ_ENTRY] = MNL_TYPE_NESTED,
+ [RDMA_NLDEV_ATTR_RES_CQE] = MNL_TYPE_U32,
+ [RDMA_NLDEV_ATTR_RES_USECNT] = MNL_TYPE_U64,
+ [RDMA_NLDEV_ATTR_RES_POLL_CTX] = MNL_TYPE_U8,
};
int rd_attr_cb(const struct nlattr *attr, void *data)
--
1.8.3.1
^ permalink raw reply related
* [PATCH v4 iproute2-next 4/7] rdma: Add CM_ID resource tracking information
From: Steve Wise @ 2018-03-29 16:10 UTC (permalink / raw)
To: dsahern; +Cc: leon, stephen, netdev, linux-rdma
In-Reply-To: <cover.1522359537.git.swise@opengridcomputing.com>
Sample output:
# rdma resource
2: cxgb4_0: pd 5 cq 2 qp 2 cm_id 3 mr 7
3: mlx4_0: pd 7 cq 3 qp 3 cm_id 3 mr 7
# rdma resource show cm_id
link cxgb4_0/- lqpn 0 qp-type RC state LISTEN ps TCP pid 30485 comm rping src-addr 0.0.0.0:7174
link cxgb4_0/2 lqpn 1048 qp-type RC state CONNECT ps TCP pid 30503 comm rping src-addr 172.16.2.1:7174 dst-addr 172.16.2.1:38246
link cxgb4_0/2 lqpn 1040 qp-type RC state CONNECT ps TCP pid 30498 comm rping src-addr 172.16.2.1:38246 dst-addr 172.16.2.1:7174
link mlx4_0/- lqpn 0 qp-type RC state LISTEN ps TCP pid 30485 comm rping src-addr 0.0.0.0:7174
link mlx4_0/1 lqpn 539 qp-type RC state CONNECT ps TCP pid 30494 comm rping src-addr 172.16.99.1:7174 dst-addr 172.16.99.1:43670
link mlx4_0/1 lqpn 538 qp-type RC state CONNECT ps TCP pid 30492 comm rping src-addr 172.16.99.1:43670 dst-addr 172.16.99.1:7174
# rdma resource show cm_id dst-port 7174
link cxgb4_0/2 lqpn 1040 qp-type RC state CONNECT ps TCP pid 30498 comm rping src-addr 172.16.2.1:38246 dst-addr 172.16.2.1:7174
link mlx4_0/1 lqpn 538 qp-type RC state CONNECT ps TCP pid 30492 comm rping src-addr 172.16.99.1:43670 dst-addr 172.16.99.1:7174
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
---
rdma/rdma.h | 2 +
rdma/res.c | 262 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
rdma/utils.c | 5 ++
3 files changed, 268 insertions(+), 1 deletion(-)
diff --git a/rdma/rdma.h b/rdma/rdma.h
index 5809f70..1908fc4 100644
--- a/rdma/rdma.h
+++ b/rdma/rdma.h
@@ -17,7 +17,9 @@
#include <getopt.h>
#include <libmnl/libmnl.h>
#include <rdma/rdma_netlink.h>
+#include <rdma/rdma_user_cm.h>
#include <time.h>
+#include <net/if_arp.h>
#include "list.h"
#include "utils.h"
diff --git a/rdma/res.c b/rdma/res.c
index 62f5c54..5506cf3 100644
--- a/rdma/res.c
+++ b/rdma/res.c
@@ -16,9 +16,11 @@ static int res_help(struct rd *rd)
{
pr_out("Usage: %s resource\n", rd->filename);
pr_out(" resource show [DEV]\n");
- pr_out(" resource show [qp]\n");
+ pr_out(" resource show [qp|cm_id]\n");
pr_out(" resource show qp link [DEV/PORT]\n");
pr_out(" resource show qp link [DEV/PORT] [FILTER-NAME FILTER-VALUE]\n");
+ pr_out(" resource show cm_id link [DEV/PORT]\n");
+ pr_out(" resource show cm_id link [DEV/PORT] [FILTER-NAME FILTER-VALUE]\n");
return 0;
}
@@ -433,6 +435,245 @@ static int res_qp_parse_cb(const struct nlmsghdr *nlh, void *data)
return MNL_CB_OK;
}
+static void print_qp_type(struct rd *rd, uint32_t val)
+{
+ if (rd->json_output)
+ jsonw_string_field(rd->jw, "qp-type",
+ qp_types_to_str(val));
+ else
+ pr_out("qp-type %s ", qp_types_to_str(val));
+}
+
+static const char *cm_id_state_to_str(uint8_t idx)
+{
+ static const char * const cm_id_states_str[] = {
+ "IDLE", "ADDR_QUERY", "ADDR_RESOLVED", "ROUTE_QUERY",
+ "ROUTE_RESOLVED", "CONNECT", "DISCONNECT", "ADDR_BOUND",
+ "LISTEN", "DEVICE_REMOVAL", "DESTROYING" };
+
+ if (idx < ARRAY_SIZE(cm_id_states_str))
+ return cm_id_states_str[idx];
+ return "UNKNOWN";
+}
+
+static const char *cm_id_ps_to_str(uint32_t ps)
+{
+ switch (ps) {
+ case RDMA_PS_IPOIB:
+ return "IPoIB";
+ case RDMA_PS_IB:
+ return "IPoIB";
+ case RDMA_PS_TCP:
+ return "TCP";
+ case RDMA_PS_UDP:
+ return "UDP";
+ default:
+ return "---";
+ }
+}
+
+static void print_cm_id_state(struct rd *rd, uint8_t state)
+{
+ if (rd->json_output) {
+ jsonw_string_field(rd->jw, "state", cm_id_state_to_str(state));
+ return;
+ }
+ pr_out("state %s ", cm_id_state_to_str(state));
+}
+
+static void print_ps(struct rd *rd, uint32_t ps)
+{
+ if (rd->json_output) {
+ jsonw_string_field(rd->jw, "ps", cm_id_ps_to_str(ps));
+ return;
+ }
+ pr_out("ps %s ", cm_id_ps_to_str(ps));
+}
+
+static void print_ipaddr(struct rd *rd, const char *key, char *addrstr,
+ uint16_t port)
+{
+ if (rd->json_output) {
+ int name_size = INET6_ADDRSTRLEN+strlen(":65535");
+ char json_name[name_size];
+
+ snprintf(json_name, name_size, "%s:%u", addrstr, port);
+ jsonw_string_field(rd->jw, key, json_name);
+ return;
+ }
+ pr_out("%s %s:%u ", key, addrstr, port);
+}
+
+static int ss_ntop(struct nlattr *nla_line, char *addr_str, uint16_t *port)
+{
+ struct __kernel_sockaddr_storage *addr;
+
+ addr = (struct __kernel_sockaddr_storage *)
+ mnl_attr_get_payload(nla_line);
+ switch (addr->ss_family) {
+ case AF_INET: {
+ struct sockaddr_in *sin = (struct sockaddr_in *)addr;
+
+ if (!inet_ntop(AF_INET, (const void *)&sin->sin_addr, addr_str,
+ INET6_ADDRSTRLEN))
+ return -EINVAL;
+ *port = ntohs(sin->sin_port);
+ break;
+ }
+ case AF_INET6: {
+ struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr;
+
+ if (!inet_ntop(AF_INET6, (const void *)&sin6->sin6_addr,
+ addr_str, INET6_ADDRSTRLEN))
+ return -EINVAL;
+ *port = ntohs(sin6->sin6_port);
+ break;
+ }
+ default:
+ return -EINVAL;
+ }
+ return 0;
+}
+
+static int res_cm_id_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+ struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
+ struct nlattr *nla_table, *nla_entry;
+ struct rd *rd = data;
+ const char *name;
+ int idx;
+
+ mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+ if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] ||
+ !tb[RDMA_NLDEV_ATTR_DEV_NAME] ||
+ !tb[RDMA_NLDEV_ATTR_RES_CM_ID])
+ return MNL_CB_ERROR;
+
+ name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
+ idx = mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+ nla_table = tb[RDMA_NLDEV_ATTR_RES_CM_ID];
+ mnl_attr_for_each_nested(nla_entry, nla_table) {
+ struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
+ char src_addr_str[INET6_ADDRSTRLEN];
+ char dst_addr_str[INET6_ADDRSTRLEN];
+ uint16_t src_port, dst_port;
+ uint32_t port = 0, pid = 0;
+ uint8_t type = 0, state;
+ uint32_t lqpn = 0, ps;
+ char *comm = NULL;
+ int err;
+
+ err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
+ if (err != MNL_CB_OK)
+ return -EINVAL;
+
+ if (!nla_line[RDMA_NLDEV_ATTR_RES_STATE] ||
+ !nla_line[RDMA_NLDEV_ATTR_RES_PS] ||
+ (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
+ !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
+ return MNL_CB_ERROR;
+ }
+
+ if (nla_line[RDMA_NLDEV_ATTR_PORT_INDEX])
+ port = mnl_attr_get_u32(
+ nla_line[RDMA_NLDEV_ATTR_PORT_INDEX]);
+
+ if (port && port != rd->port_idx)
+ continue;
+
+ if (nla_line[RDMA_NLDEV_ATTR_RES_LQPN]) {
+ lqpn = mnl_attr_get_u32(
+ nla_line[RDMA_NLDEV_ATTR_RES_LQPN]);
+ if (rd_check_is_filtered(rd, "lqpn", lqpn))
+ continue;
+ }
+ if (nla_line[RDMA_NLDEV_ATTR_RES_TYPE]) {
+ type = mnl_attr_get_u8(
+ nla_line[RDMA_NLDEV_ATTR_RES_TYPE]);
+ if (rd_check_is_string_filtered(rd, "qp-type",
+ qp_types_to_str(type)))
+ continue;
+ }
+
+ ps = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_PS]);
+ if (rd_check_is_string_filtered(rd, "ps", cm_id_ps_to_str(ps)))
+ continue;
+
+ state = mnl_attr_get_u8(nla_line[RDMA_NLDEV_ATTR_RES_STATE]);
+ if (rd_check_is_string_filtered(rd, "state",
+ cm_id_state_to_str(state)))
+ continue;
+
+ if (nla_line[RDMA_NLDEV_ATTR_RES_SRC_ADDR]) {
+ if (ss_ntop(nla_line[RDMA_NLDEV_ATTR_RES_SRC_ADDR],
+ src_addr_str, &src_port))
+ continue;
+ if (rd_check_is_string_filtered(rd, "src-addr",
+ src_addr_str))
+ continue;
+ }
+
+ if (nla_line[RDMA_NLDEV_ATTR_RES_DST_ADDR]) {
+ if (ss_ntop(nla_line[RDMA_NLDEV_ATTR_RES_DST_ADDR],
+ dst_addr_str, &dst_port))
+ continue;
+ if (rd_check_is_string_filtered(rd, "dst-addr",
+ dst_addr_str))
+ continue;
+ }
+
+ if (rd_check_is_filtered(rd, "src-port", src_port))
+ continue;
+
+ if (rd_check_is_filtered(rd, "dst-port", dst_port))
+ continue;
+
+ if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
+ pid = mnl_attr_get_u32(
+ nla_line[RDMA_NLDEV_ATTR_RES_PID]);
+ comm = get_task_name(pid);
+ }
+
+ if (rd_check_is_filtered(rd, "pid", pid)) {
+ free(comm);
+ continue;
+ }
+
+ if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]) {
+ /* discard const from mnl_attr_get_str */
+ comm = (char *)mnl_attr_get_str(
+ nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
+ }
+
+ if (rd->json_output)
+ jsonw_start_array(rd->jw);
+
+ print_link(rd, idx, name, port, nla_line);
+ if (nla_line[RDMA_NLDEV_ATTR_RES_LQPN])
+ print_lqpn(rd, lqpn);
+ if (nla_line[RDMA_NLDEV_ATTR_RES_TYPE])
+ print_qp_type(rd, type);
+ print_cm_id_state(rd, state);
+ print_ps(rd, ps);
+ print_pid(rd, pid);
+ print_comm(rd, comm, nla_line);
+
+ if (nla_line[RDMA_NLDEV_ATTR_RES_SRC_ADDR])
+ print_ipaddr(rd, "src-addr", src_addr_str, src_port);
+ if (nla_line[RDMA_NLDEV_ATTR_RES_DST_ADDR])
+ print_ipaddr(rd, "dst-addr", dst_addr_str, dst_port);
+
+ if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
+ free(comm);
+
+ if (rd->json_output)
+ jsonw_end_array(rd->jw);
+ else
+ pr_out("\n");
+ }
+ return MNL_CB_OK;
+}
+
RES_FUNC(res_no_args, RDMA_NLDEV_CMD_RES_GET, NULL, true);
static const struct
@@ -457,11 +698,30 @@ filters qp_valid_filters[MAX_NUMBER_OF_FILTERS] = {{ .name = "link",
RES_FUNC(res_qp, RDMA_NLDEV_CMD_RES_QP_GET, qp_valid_filters, false);
+static const
+struct filters cm_id_valid_filters[MAX_NUMBER_OF_FILTERS] = {
+ { .name = "link", .is_number = false },
+ { .name = "lqpn", .is_number = true },
+ { .name = "qp-type", .is_number = false },
+ { .name = "state", .is_number = false },
+ { .name = "ps", .is_number = false },
+ { .name = "dev-type", .is_number = false },
+ { .name = "transport-type", .is_number = false },
+ { .name = "pid", .is_number = true },
+ { .name = "src-addr", .is_number = false },
+ { .name = "src-port", .is_number = true },
+ { .name = "dst-addr", .is_number = false },
+ { .name = "dst-port", .is_number = true }
+};
+
+RES_FUNC(res_cm_id, RDMA_NLDEV_CMD_RES_CM_ID_GET, cm_id_valid_filters, false);
+
static int res_show(struct rd *rd)
{
const struct rd_cmd cmds[] = {
{ NULL, res_no_args },
{ "qp", res_qp },
+ { "cm_id", res_cm_id },
{ 0 }
};
diff --git a/rdma/utils.c b/rdma/utils.c
index f946016..ec81737 100644
--- a/rdma/utils.c
+++ b/rdma/utils.c
@@ -375,6 +375,11 @@ static const enum mnl_attr_data_type nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
[RDMA_NLDEV_ATTR_RES_STATE] = MNL_TYPE_U8,
[RDMA_NLDEV_ATTR_RES_PID] = MNL_TYPE_U32,
[RDMA_NLDEV_ATTR_RES_KERN_NAME] = MNL_TYPE_NUL_STRING,
+ [RDMA_NLDEV_ATTR_RES_CM_ID] = MNL_TYPE_NESTED,
+ [RDMA_NLDEV_ATTR_RES_CM_ID_ENTRY] = MNL_TYPE_NESTED,
+ [RDMA_NLDEV_ATTR_RES_PS] = MNL_TYPE_U32,
+ [RDMA_NLDEV_ATTR_RES_SRC_ADDR] = MNL_TYPE_UNSPEC,
+ [RDMA_NLDEV_ATTR_RES_DST_ADDR] = MNL_TYPE_UNSPEC,
};
int rd_attr_cb(const struct nlattr *attr, void *data)
--
1.8.3.1
^ permalink raw reply related
* [PATCH v4 iproute2-next 3/7] rdma: initialize the rd struct
From: Steve Wise @ 2018-03-29 16:10 UTC (permalink / raw)
To: dsahern; +Cc: leon, stephen, netdev, linux-rdma
In-Reply-To: <cover.1522359537.git.swise@opengridcomputing.com>
Initialize the rd struct so port_idx is 0 unless set otherwise.
Otherwise, strict_port queries end up passing an uninitialized PORT
nlattr.
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
---
rdma/rdma.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/rdma/rdma.c b/rdma/rdma.c
index ab2c960..b43e538 100644
--- a/rdma/rdma.c
+++ b/rdma/rdma.c
@@ -135,7 +135,7 @@ int main(int argc, char **argv)
bool json_output = false;
bool force = false;
char *filename;
- struct rd rd;
+ struct rd rd = {};
int opt;
int err;
--
1.8.3.1
^ permalink raw reply related
* [PATCH v4 iproute2-next 2/7] rdma: add UAPI rdma_user_cm.h
From: Steve Wise @ 2018-03-29 16:10 UTC (permalink / raw)
To: dsahern; +Cc: leon, stephen, netdev, linux-rdma
In-Reply-To: <cover.1522359537.git.swise@opengridcomputing.com>
This allows parsing rdma_cm_id UAPI values.
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
---
rdma/include/uapi/rdma/rdma_user_cm.h | 324 ++++++++++++++++++++++++++++++++++
1 file changed, 324 insertions(+)
create mode 100644 rdma/include/uapi/rdma/rdma_user_cm.h
diff --git a/rdma/include/uapi/rdma/rdma_user_cm.h b/rdma/include/uapi/rdma/rdma_user_cm.h
new file mode 100644
index 0000000..da099af
--- /dev/null
+++ b/rdma/include/uapi/rdma/rdma_user_cm.h
@@ -0,0 +1,324 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2005-2006 Intel Corporation. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _RDMA_USER_CM_H
+#define _RDMA_USER_CM_H
+
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/in6.h>
+#include <rdma/ib_user_verbs.h>
+#include <rdma/ib_user_sa.h>
+
+#define RDMA_USER_CM_ABI_VERSION 4
+
+#define RDMA_MAX_PRIVATE_DATA 256
+
+enum {
+ RDMA_USER_CM_CMD_CREATE_ID,
+ RDMA_USER_CM_CMD_DESTROY_ID,
+ RDMA_USER_CM_CMD_BIND_IP,
+ RDMA_USER_CM_CMD_RESOLVE_IP,
+ RDMA_USER_CM_CMD_RESOLVE_ROUTE,
+ RDMA_USER_CM_CMD_QUERY_ROUTE,
+ RDMA_USER_CM_CMD_CONNECT,
+ RDMA_USER_CM_CMD_LISTEN,
+ RDMA_USER_CM_CMD_ACCEPT,
+ RDMA_USER_CM_CMD_REJECT,
+ RDMA_USER_CM_CMD_DISCONNECT,
+ RDMA_USER_CM_CMD_INIT_QP_ATTR,
+ RDMA_USER_CM_CMD_GET_EVENT,
+ RDMA_USER_CM_CMD_GET_OPTION,
+ RDMA_USER_CM_CMD_SET_OPTION,
+ RDMA_USER_CM_CMD_NOTIFY,
+ RDMA_USER_CM_CMD_JOIN_IP_MCAST,
+ RDMA_USER_CM_CMD_LEAVE_MCAST,
+ RDMA_USER_CM_CMD_MIGRATE_ID,
+ RDMA_USER_CM_CMD_QUERY,
+ RDMA_USER_CM_CMD_BIND,
+ RDMA_USER_CM_CMD_RESOLVE_ADDR,
+ RDMA_USER_CM_CMD_JOIN_MCAST
+};
+
+/* See IBTA Annex A11, servies ID bytes 4 & 5 */
+enum rdma_ucm_port_space {
+ RDMA_PS_IPOIB = 0x0002,
+ RDMA_PS_IB = 0x013F,
+ RDMA_PS_TCP = 0x0106,
+ RDMA_PS_UDP = 0x0111,
+};
+
+/*
+ * command ABI structures.
+ */
+struct rdma_ucm_cmd_hdr {
+ __u32 cmd;
+ __u16 in;
+ __u16 out;
+};
+
+struct rdma_ucm_create_id {
+ __aligned_u64 uid;
+ __aligned_u64 response;
+ __u16 ps; /* use enum rdma_ucm_port_space */
+ __u8 qp_type;
+ __u8 reserved[5];
+};
+
+struct rdma_ucm_create_id_resp {
+ __u32 id;
+};
+
+struct rdma_ucm_destroy_id {
+ __aligned_u64 response;
+ __u32 id;
+ __u32 reserved;
+};
+
+struct rdma_ucm_destroy_id_resp {
+ __u32 events_reported;
+};
+
+struct rdma_ucm_bind_ip {
+ __aligned_u64 response;
+ struct sockaddr_in6 addr;
+ __u32 id;
+};
+
+struct rdma_ucm_bind {
+ __u32 id;
+ __u16 addr_size;
+ __u16 reserved;
+ struct __kernel_sockaddr_storage addr;
+};
+
+struct rdma_ucm_resolve_ip {
+ struct sockaddr_in6 src_addr;
+ struct sockaddr_in6 dst_addr;
+ __u32 id;
+ __u32 timeout_ms;
+};
+
+struct rdma_ucm_resolve_addr {
+ __u32 id;
+ __u32 timeout_ms;
+ __u16 src_size;
+ __u16 dst_size;
+ __u32 reserved;
+ struct __kernel_sockaddr_storage src_addr;
+ struct __kernel_sockaddr_storage dst_addr;
+};
+
+struct rdma_ucm_resolve_route {
+ __u32 id;
+ __u32 timeout_ms;
+};
+
+enum {
+ RDMA_USER_CM_QUERY_ADDR,
+ RDMA_USER_CM_QUERY_PATH,
+ RDMA_USER_CM_QUERY_GID
+};
+
+struct rdma_ucm_query {
+ __aligned_u64 response;
+ __u32 id;
+ __u32 option;
+};
+
+struct rdma_ucm_query_route_resp {
+ __aligned_u64 node_guid;
+ struct ib_user_path_rec ib_route[2];
+ struct sockaddr_in6 src_addr;
+ struct sockaddr_in6 dst_addr;
+ __u32 num_paths;
+ __u8 port_num;
+ __u8 reserved[3];
+};
+
+struct rdma_ucm_query_addr_resp {
+ __aligned_u64 node_guid;
+ __u8 port_num;
+ __u8 reserved;
+ __u16 pkey;
+ __u16 src_size;
+ __u16 dst_size;
+ struct __kernel_sockaddr_storage src_addr;
+ struct __kernel_sockaddr_storage dst_addr;
+};
+
+struct rdma_ucm_query_path_resp {
+ __u32 num_paths;
+ __u32 reserved;
+ struct ib_path_rec_data path_data[0];
+};
+
+struct rdma_ucm_conn_param {
+ __u32 qp_num;
+ __u32 qkey;
+ __u8 private_data[RDMA_MAX_PRIVATE_DATA];
+ __u8 private_data_len;
+ __u8 srq;
+ __u8 responder_resources;
+ __u8 initiator_depth;
+ __u8 flow_control;
+ __u8 retry_count;
+ __u8 rnr_retry_count;
+ __u8 valid;
+};
+
+struct rdma_ucm_ud_param {
+ __u32 qp_num;
+ __u32 qkey;
+ struct ib_uverbs_ah_attr ah_attr;
+ __u8 private_data[RDMA_MAX_PRIVATE_DATA];
+ __u8 private_data_len;
+ __u8 reserved[7];
+};
+
+struct rdma_ucm_connect {
+ struct rdma_ucm_conn_param conn_param;
+ __u32 id;
+ __u32 reserved;
+};
+
+struct rdma_ucm_listen {
+ __u32 id;
+ __u32 backlog;
+};
+
+struct rdma_ucm_accept {
+ __aligned_u64 uid;
+ struct rdma_ucm_conn_param conn_param;
+ __u32 id;
+ __u32 reserved;
+};
+
+struct rdma_ucm_reject {
+ __u32 id;
+ __u8 private_data_len;
+ __u8 reserved[3];
+ __u8 private_data[RDMA_MAX_PRIVATE_DATA];
+};
+
+struct rdma_ucm_disconnect {
+ __u32 id;
+};
+
+struct rdma_ucm_init_qp_attr {
+ __aligned_u64 response;
+ __u32 id;
+ __u32 qp_state;
+};
+
+struct rdma_ucm_notify {
+ __u32 id;
+ __u32 event;
+};
+
+struct rdma_ucm_join_ip_mcast {
+ __aligned_u64 response; /* rdma_ucm_create_id_resp */
+ __aligned_u64 uid;
+ struct sockaddr_in6 addr;
+ __u32 id;
+};
+
+/* Multicast join flags */
+enum {
+ RDMA_MC_JOIN_FLAG_FULLMEMBER,
+ RDMA_MC_JOIN_FLAG_SENDONLY_FULLMEMBER,
+ RDMA_MC_JOIN_FLAG_RESERVED,
+};
+
+struct rdma_ucm_join_mcast {
+ __aligned_u64 response; /* rdma_ucma_create_id_resp */
+ __aligned_u64 uid;
+ __u32 id;
+ __u16 addr_size;
+ __u16 join_flags;
+ struct __kernel_sockaddr_storage addr;
+};
+
+struct rdma_ucm_get_event {
+ __aligned_u64 response;
+};
+
+struct rdma_ucm_event_resp {
+ __aligned_u64 uid;
+ __u32 id;
+ __u32 event;
+ __u32 status;
+ /*
+ * NOTE: This union is not aligned to 8 bytes so none of the union
+ * members may contain a u64 or anything with higher alignment than 4.
+ */
+ union {
+ struct rdma_ucm_conn_param conn;
+ struct rdma_ucm_ud_param ud;
+ } param;
+ __u32 reserved;
+};
+
+/* Option levels */
+enum {
+ RDMA_OPTION_ID = 0,
+ RDMA_OPTION_IB = 1
+};
+
+/* Option details */
+enum {
+ RDMA_OPTION_ID_TOS = 0,
+ RDMA_OPTION_ID_REUSEADDR = 1,
+ RDMA_OPTION_ID_AFONLY = 2,
+ RDMA_OPTION_IB_PATH = 1
+};
+
+struct rdma_ucm_set_option {
+ __aligned_u64 optval;
+ __u32 id;
+ __u32 level;
+ __u32 optname;
+ __u32 optlen;
+};
+
+struct rdma_ucm_migrate_id {
+ __aligned_u64 response;
+ __u32 id;
+ __u32 fd;
+};
+
+struct rdma_ucm_migrate_resp {
+ __u32 events_reported;
+};
+
+#endif /* _RDMA_USER_CM_H */
--
1.8.3.1
^ permalink raw reply related
* [PATCH v4 iproute2-next 1/7] rdma: update rdma_netlink.h
From: Steve Wise @ 2018-03-29 16:10 UTC (permalink / raw)
To: dsahern; +Cc: leon, stephen, netdev, linux-rdma
In-Reply-To: <cover.1522359537.git.swise@opengridcomputing.com>
From: Steve Wise <swise@opengridcomputing.com>
Pull in the latest rdma_netlink.h which has support for
the rdma nldev resource tracking objects being added
with this patch series.
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
---
rdma/include/uapi/rdma/rdma_netlink.h | 38 +++++++++++++++++++++++++++++++++++
1 file changed, 38 insertions(+)
diff --git a/rdma/include/uapi/rdma/rdma_netlink.h b/rdma/include/uapi/rdma/rdma_netlink.h
index dbac3b8..9446a72 100644
--- a/rdma/include/uapi/rdma/rdma_netlink.h
+++ b/rdma/include/uapi/rdma/rdma_netlink.h
@@ -238,6 +238,14 @@ enum rdma_nldev_command {
RDMA_NLDEV_CMD_RES_QP_GET, /* can dump */
+ RDMA_NLDEV_CMD_RES_CM_ID_GET, /* can dump */
+
+ RDMA_NLDEV_CMD_RES_CQ_GET, /* can dump */
+
+ RDMA_NLDEV_CMD_RES_MR_GET, /* can dump */
+
+ RDMA_NLDEV_CMD_RES_PD_GET, /* can dump */
+
RDMA_NLDEV_NUM_OPS
};
@@ -350,6 +358,36 @@ enum rdma_nldev_attr {
*/
RDMA_NLDEV_ATTR_RES_KERN_NAME, /* string */
+ RDMA_NLDEV_ATTR_RES_CM_ID, /* nested table */
+ RDMA_NLDEV_ATTR_RES_CM_ID_ENTRY, /* nested table */
+ /*
+ * rdma_cm_id port space.
+ */
+ RDMA_NLDEV_ATTR_RES_PS, /* u32 */
+ /*
+ * Source and destination socket addresses
+ */
+ RDMA_NLDEV_ATTR_RES_SRC_ADDR, /* __kernel_sockaddr_storage */
+ RDMA_NLDEV_ATTR_RES_DST_ADDR, /* __kernel_sockaddr_storage */
+
+ RDMA_NLDEV_ATTR_RES_CQ, /* nested table */
+ RDMA_NLDEV_ATTR_RES_CQ_ENTRY, /* nested table */
+ RDMA_NLDEV_ATTR_RES_CQE, /* u32 */
+ RDMA_NLDEV_ATTR_RES_USECNT, /* u64 */
+ RDMA_NLDEV_ATTR_RES_POLL_CTX, /* u8 */
+
+ RDMA_NLDEV_ATTR_RES_MR, /* nested table */
+ RDMA_NLDEV_ATTR_RES_MR_ENTRY, /* nested table */
+ RDMA_NLDEV_ATTR_RES_RKEY, /* u32 */
+ RDMA_NLDEV_ATTR_RES_LKEY, /* u32 */
+ RDMA_NLDEV_ATTR_RES_IOVA, /* u64 */
+ RDMA_NLDEV_ATTR_RES_MRLEN, /* u64 */
+
+ RDMA_NLDEV_ATTR_RES_PD, /* nested table */
+ RDMA_NLDEV_ATTR_RES_PD_ENTRY, /* nested table */
+ RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY, /* u32 */
+ RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY, /* u32 */
+
RDMA_NLDEV_ATTR_MAX
};
#endif /* _RDMA_NETLINK_H */
--
1.8.3.1
^ permalink raw reply related
* [PATCH v4 iproute2-next 0/7] cm_id, cq, mr, and pd resource tracking
From: Steve Wise @ 2018-03-29 21:38 UTC (permalink / raw)
To: dsahern; +Cc: leon, stephen, netdev, linux-rdma
This series enhances the iproute2 rdma tool to include dumping of
connection manager id (cm_id), completion queue (cq), memory region (mr),
and protection domain (pd) rdma resources. It is the user-space part of
the kernel resource tracking series merged into rdma-next for 4.17 [1]
and [2].
Changes since v3:
- replaced rdma_cma.h inclusion with UAPI rdma_user_cm.h
- display only device names instead of device/port for cq, mr, and pd
since they are not associated with a specific port.
Changes since v2:
- pull in rdma-core:include/rdma/rdma_cma.h
- 80 column reformat
- add reviewed-by tags
Changes since v1/RFC:
- removed RFC tag
- initialize rd properly to avoid passing a garbage port number
- revert accidental change to qp_valid_filters
- removed cm_id dev/network/transport types
- cm_id ip addrs now passed up as __kernel_sockaddr_storage
- cm_id ip address ports printed as "address:port" strings
- only parse/display memory keys and iova if available
- filter on "users" for cqs and pds
- fixed memory leaks
- removed PD_FLAGS attribute
- filter on "mrlen" for mrs
- filter on "poll-ctx" for cqs
- don't require addrs or qp_type for parsing cm_ids
- only filter optional attrs if they are present
- remove PGSIZE MR attr to match kernel
[1] https://www.spinics.net/lists/linux-rdma/msg61720.html
[2] https://www.spinics.net/lists/linux-rdma/msg62979.html
https://www.spinics.net/lists/linux-rdma/msg62980.html
---
Steve Wise (7):
rdma: update rdma_netlink.h
rdma: add UAPI rdma_user_cm.h
rdma: initialize the rd struct
rdma: Add CM_ID resource tracking information
rdma: Add CQ resource tracking information
rdma: Add MR resource tracking information
rdma: Add PD resource tracking information
include/json_writer.h | 2 +
lib/json_writer.c | 11 +
rdma/include/uapi/rdma/rdma_netlink.h | 38 ++
rdma/include/uapi/rdma/rdma_user_cm.h | 324 +++++++++++++++++
rdma/rdma.c | 2 +-
rdma/rdma.h | 2 +
rdma/res.c | 633 +++++++++++++++++++++++++++++++++-
rdma/utils.c | 16 +
8 files changed, 1026 insertions(+), 2 deletions(-)
create mode 100644 rdma/include/uapi/rdma/rdma_user_cm.h
--
1.8.3.1
^ permalink raw reply
* Re: [PATCH iproute2] json_print: fix print_uint hidden type promotion
From: Kevin Darbyshire-Bryant @ 2018-03-29 21:29 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: netdev@vger.kernel.org
In-Reply-To: <20180329140237.7bb711fc@xeon-e3>
> On 29 Mar 2018, at 22:02, Stephen Hemminger <stephen@networkplumber.org> wrote:
>
> On Thu, 29 Mar 2018 20:22:20 +0100
> Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk> wrote:
>
>> print_int used 'int' type internally, whereas print_uint used 'uint64_t'
>>
>> These helper functions eventually call vfprintf(fp, fmt, args) which is
>> a variable argument list function and is dependent upon 'fmt' containing
>> correct information about the length of the passed arguments.
>>
>> Unfortunately print_int v print_uint offered no clue to the programmer
>> that internally passed ints to print_uint were being promoted to 64bits,
>> thus the format passed in 'fmt' string vs the actual passed integer
>> could be different lengths. This is even more interesting on big endian
>> architectures where 'vfprintf' would be looking in the middle of an
>> int64 type.
>>
>> print_u/int now stick with native int size.
>>
>> Signed-off-by: Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk>
>> ---
>> include/json_print.h | 2 +-
>> lib/json_print.c | 2 +-
>> 2 files changed, 2 insertions(+), 2 deletions(-)
>>
>> diff --git a/include/json_print.h b/include/json_print.h
>> index 2ca7830a..45bc653d 100644
>> --- a/include/json_print.h
>> +++ b/include/json_print.h
>> @@ -56,10 +56,10 @@ void close_json_array(enum output_type type, const char *delim);
>> print_color_##type_name(t, COLOR_NONE, key, fmt, value); \
>> }
>> _PRINT_FUNC(int, int);
>> +_PRINT_FUNC(uint, unsigned int);
>> _PRINT_FUNC(bool, bool);
>> _PRINT_FUNC(null, const char*);
>> _PRINT_FUNC(string, const char*);
>> -_PRINT_FUNC(uint, uint64_t);
>> _PRINT_FUNC(hu, unsigned short);
>> _PRINT_FUNC(hex, unsigned int);
>> _PRINT_FUNC(0xhex, unsigned int);
>> diff --git a/lib/json_print.c b/lib/json_print.c
>> index 6518ba98..8d54d1d4 100644
>> --- a/lib/json_print.c
>> +++ b/lib/json_print.c
>> @@ -117,8 +117,8 @@ void close_json_array(enum output_type type, const char *str)
>> } \
>> }
>> _PRINT_FUNC(int, int);
>> +_PRINT_FUNC(uint, unsigned int);
>> _PRINT_FUNC(hu, unsigned short);
>> -_PRINT_FUNC(uint, uint64_t);
>> _PRINT_FUNC(lluint, unsigned long long int);
>> _PRINT_FUNC(float, double);
>> #undef _PRINT_FUNC
>
>
> I am concerned that this will break output of 64 bit statistics on 32 bit hosts.
I honestly don’t know what to do. Without the patch I see breakage on <33 bit stats with 32 bit big endian hosts ‘cos the printf formatting doesn’t know the type passed internally by the function is 64bits long. e.g.
tc qdisc
qdisc noqueue 0: dev lo root refcnt 4486716
qdisc fq_codel 0: dev eth1 root refcnt 4486716 limit 4498840p flows 4536204 quantum 4539856 target 5.0ms interval 100.0ms memory_limit 4Mb ecn
qdisc noqueue 0: dev br-lan root refcnt 4486716
qdisc noqueue 0: dev eth1.2 root refcnt 4486716
qdisc noqueue 0: dev br-wifi_guest root refcnt 4486716
qdisc noqueue 0: dev eth1.15 root refcnt 4486716
qdisc noqueue 0: dev wlan1 root refcnt 4486716
qdisc noqueue 0: dev wlan0 root refcnt 4486716
qdisc noqueue 0: dev wlan1-1 root refcnt 4486716
qdisc noqueue 0: dev wlan0-1 root refcnt 4486716
I guess _PRINT_FUNC(int, int) could be _PRINT_FUNC(int, int64_t) and then at least we’d be consistent in doing hidden promotions and see breakage for both signed & unsigned types on certain architectures.
But I think I’ve hit my (lack of) skill limit and don’t really know how to take this further forward, or wish to break more protocols :-)
^ permalink raw reply
* [net-next v2 4/5] tipc: tipc: rename address types in user api
From: Jon Maloy @ 2018-03-29 21:20 UTC (permalink / raw)
To: davem, netdev
Cc: mohan.krishna.ghanta.krishnamurthy, tung.q.nguyen, hoang.h.le,
jon.maloy, canh.d.luu, ying.xue, tipc-discussion
In-Reply-To: <1522358445-7444-1-git-send-email-jon.maloy@ericsson.com>
The three address type structs in the user API have names that in
reality reflect the specific, non-Linux environment where they were
originally created.
We now give them more intuitive names, in accordance with how TIPC is
described in the current documentation.
struct tipc_portid -> struct tipc_socket_addr
struct tipc_name -> struct tipc_service_addr
struct tipc_name_seq -> struct tipc_service_range
To avoid confusion, we also update some commmets and macro names to
match the new terminology.
For compatibility, we add macros that map all old names to the new ones.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
---
include/uapi/linux/tipc.h | 57 +++++++++++++++++++++++++++--------------------
1 file changed, 33 insertions(+), 24 deletions(-)
diff --git a/include/uapi/linux/tipc.h b/include/uapi/linux/tipc.h
index 4ac9f1f..156224a 100644
--- a/include/uapi/linux/tipc.h
+++ b/include/uapi/linux/tipc.h
@@ -45,33 +45,33 @@
* TIPC addressing primitives
*/
-struct tipc_portid {
+struct tipc_socket_addr {
__u32 ref;
__u32 node;
};
-struct tipc_name {
+struct tipc_service_addr {
__u32 type;
__u32 instance;
};
-struct tipc_name_seq {
+struct tipc_service_range {
__u32 type;
__u32 lower;
__u32 upper;
};
/*
- * Application-accessible port name types
+ * Application-accessible service types
*/
-#define TIPC_CFG_SRV 0 /* configuration service name type */
-#define TIPC_TOP_SRV 1 /* topology service name type */
-#define TIPC_LINK_STATE 2 /* link state name type */
-#define TIPC_RESERVED_TYPES 64 /* lowest user-publishable name type */
+#define TIPC_NODE_STATE 0 /* node state service type */
+#define TIPC_TOP_SRV 1 /* topology server service type */
+#define TIPC_LINK_STATE 2 /* link state service type */
+#define TIPC_RESERVED_TYPES 64 /* lowest user-allowed service type */
/*
- * Publication scopes when binding port names and port name sequences
+ * Publication scopes when binding service / service range
*/
enum tipc_scope {
TIPC_CLUSTER_SCOPE = 2, /* 0 can also be used */
@@ -108,28 +108,28 @@ enum tipc_scope {
* TIPC topology subscription service definitions
*/
-#define TIPC_SUB_PORTS 0x01 /* filter for port availability */
-#define TIPC_SUB_SERVICE 0x02 /* filter for service availability */
-#define TIPC_SUB_CANCEL 0x04 /* cancel a subscription */
+#define TIPC_SUB_PORTS 0x01 /* filter: evt at each match */
+#define TIPC_SUB_SERVICE 0x02 /* filter: evt at first up/last down */
+#define TIPC_SUB_CANCEL 0x04 /* filter: cancel a subscription */
#define TIPC_WAIT_FOREVER (~0) /* timeout for permanent subscription */
struct tipc_subscr {
- struct tipc_name_seq seq; /* name sequence of interest */
+ struct tipc_service_range seq; /* range of interest */
__u32 timeout; /* subscription duration (in ms) */
__u32 filter; /* bitmask of filter options */
char usr_handle[8]; /* available for subscriber use */
};
#define TIPC_PUBLISHED 1 /* publication event */
-#define TIPC_WITHDRAWN 2 /* withdraw event */
+#define TIPC_WITHDRAWN 2 /* withdrawal event */
#define TIPC_SUBSCR_TIMEOUT 3 /* subscription timeout event */
struct tipc_event {
__u32 event; /* event type */
- __u32 found_lower; /* matching name seq instances */
- __u32 found_upper; /* " " " " */
- struct tipc_portid port; /* associated port */
+ __u32 found_lower; /* matching range */
+ __u32 found_upper; /* " " */
+ struct tipc_socket_addr port; /* associated socket */
struct tipc_subscr s; /* associated subscription */
};
@@ -149,20 +149,20 @@ struct tipc_event {
#define SOL_TIPC 271
#endif
-#define TIPC_ADDR_NAMESEQ 1
-#define TIPC_ADDR_MCAST 1
-#define TIPC_ADDR_NAME 2
-#define TIPC_ADDR_ID 3
+#define TIPC_ADDR_MCAST 1
+#define TIPC_SERVICE_RANGE 1
+#define TIPC_SERVICE_ADDR 2
+#define TIPC_SOCKET_ADDR 3
struct sockaddr_tipc {
unsigned short family;
unsigned char addrtype;
signed char scope;
union {
- struct tipc_portid id;
- struct tipc_name_seq nameseq;
+ struct tipc_socket_addr id;
+ struct tipc_service_range nameseq;
struct {
- struct tipc_name name;
+ struct tipc_service_addr name;
__u32 domain;
} name;
} addr;
@@ -230,8 +230,13 @@ struct tipc_sioc_ln_req {
/* The macros and functions below are deprecated:
*/
+#define TIPC_CFG_SRV 0
#define TIPC_ZONE_SCOPE 1
+#define TIPC_ADDR_NAMESEQ 1
+#define TIPC_ADDR_NAME 2
+#define TIPC_ADDR_ID 3
+
#define TIPC_NODE_BITS 12
#define TIPC_CLUSTER_BITS 12
#define TIPC_ZONE_BITS 8
@@ -250,6 +255,10 @@ struct tipc_sioc_ln_req {
#define TIPC_ZONE_CLUSTER_MASK (TIPC_ZONE_MASK | TIPC_CLUSTER_MASK)
+#define tipc_portid tipc_socket_addr
+#define tipc_name tipc_service_addr
+#define tipc_name_seq tipc_service_range
+
static inline __u32 tipc_addr(unsigned int zone,
unsigned int cluster,
unsigned int node)
--
2.1.4
^ permalink raw reply related
* [net-next v2 1/5] tipc: replace name table service range array with rb tree
From: Jon Maloy @ 2018-03-29 21:20 UTC (permalink / raw)
To: davem, netdev
Cc: mohan.krishna.ghanta.krishnamurthy, tung.q.nguyen, hoang.h.le,
jon.maloy, canh.d.luu, ying.xue, tipc-discussion
In-Reply-To: <1522358445-7444-1-git-send-email-jon.maloy@ericsson.com>
The current design of the binding table has an unnecessary memory
consuming and complex data structure. It aggregates the service range
items into an array, which is expanded by a factor two every time it
becomes too small to hold a new item. Furthermore, the arrays never
shrink when the number of ranges diminishes.
We now replace this array with an RB tree that is holding the range
items as tree nodes, each range directly holding a list of bindings.
This, along with a few name changes, improves both readability and
volume of the code, as well as reducing memory consumption and hopefully
improving cache hit rate.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
---
net/tipc/core.h | 1 +
net/tipc/link.c | 2 +-
net/tipc/name_table.c | 1032 ++++++++++++++++++++++---------------------------
net/tipc/name_table.h | 2 +-
net/tipc/node.c | 4 +-
net/tipc/subscr.h | 4 +-
6 files changed, 477 insertions(+), 568 deletions(-)
diff --git a/net/tipc/core.h b/net/tipc/core.h
index d0f64ca..8020a6c 100644
--- a/net/tipc/core.h
+++ b/net/tipc/core.h
@@ -58,6 +58,7 @@
#include <linux/etherdevice.h>
#include <net/netns/generic.h>
#include <linux/rhashtable.h>
+#include <net/genetlink.h>
struct tipc_node;
struct tipc_bearer;
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 1289b4b..8f2a949 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1810,7 +1810,7 @@ int tipc_link_bc_nack_rcv(struct tipc_link *l, struct sk_buff *skb,
void tipc_link_set_queue_limits(struct tipc_link *l, u32 win)
{
- int max_bulk = TIPC_MAX_PUBLICATIONS / (l->mtu / ITEM_SIZE);
+ int max_bulk = TIPC_MAX_PUBL / (l->mtu / ITEM_SIZE);
l->window = win;
l->backlog[TIPC_LOW_IMPORTANCE].limit = max_t(u16, 50, win);
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index 4359605..e06c7a8 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -44,52 +44,40 @@
#include "addr.h"
#include "node.h"
#include "group.h"
-#include <net/genetlink.h>
-
-#define TIPC_NAMETBL_SIZE 1024 /* must be a power of 2 */
/**
- * struct name_info - name sequence publication info
- * @node_list: list of publications on own node of this <type,lower,upper>
- * @all_publ: list of all publications of this <type,lower,upper>
+ * struct service_range - container for all bindings of a service range
+ * @lower: service range lower bound
+ * @upper: service range upper bound
+ * @tree_node: member of service range RB tree
+ * @local_publ: list of identical publications made from this node
+ * Used by closest_first lookup and multicast lookup algorithm
+ * @all_publ: all publications identical to this one, whatever node and scope
+ * Used by round-robin lookup algorithm
*/
-struct name_info {
- struct list_head local_publ;
- struct list_head all_publ;
-};
-
-/**
- * struct sub_seq - container for all published instances of a name sequence
- * @lower: name sequence lower bound
- * @upper: name sequence upper bound
- * @info: pointer to name sequence publication info
- */
-struct sub_seq {
+struct service_range {
u32 lower;
u32 upper;
- struct name_info *info;
+ struct rb_node tree_node;
+ struct list_head local_publ;
+ struct list_head all_publ;
};
/**
- * struct name_seq - container for all published instances of a name type
- * @type: 32 bit 'type' value for name sequence
- * @sseq: pointer to dynamically-sized array of sub-sequences of this 'type';
- * sub-sequences are sorted in ascending order
- * @alloc: number of sub-sequences currently in array
- * @first_free: array index of first unused sub-sequence entry
- * @ns_list: links to adjacent name sequences in hash chain
- * @subscriptions: list of subscriptions for this 'type'
- * @lock: spinlock controlling access to publication lists of all sub-sequences
+ * struct tipc_service - container for all published instances of a service type
+ * @type: 32 bit 'type' value for service
+ * @ranges: rb tree containing all service ranges for this service
+ * @service_list: links to adjacent name ranges in hash chain
+ * @subscriptions: list of subscriptions for this service type
+ * @lock: spinlock controlling access to pertaining service ranges/publications
* @rcu: RCU callback head used for deferred freeing
*/
-struct name_seq {
+struct tipc_service {
u32 type;
- struct sub_seq *sseqs;
- u32 alloc;
- u32 first_free;
- struct hlist_node ns_list;
+ struct rb_root ranges;
+ struct hlist_node service_list;
struct list_head subscriptions;
- spinlock_t lock;
+ spinlock_t lock; /* Covers service range list */
struct rcu_head rcu;
};
@@ -99,17 +87,16 @@ static int hash(int x)
}
/**
- * publ_create - create a publication structure
+ * tipc_publ_create - create a publication structure
*/
-static struct publication *publ_create(u32 type, u32 lower, u32 upper,
- u32 scope, u32 node, u32 port,
- u32 key)
+static struct publication *tipc_publ_create(u32 type, u32 lower, u32 upper,
+ u32 scope, u32 node, u32 port,
+ u32 key)
{
struct publication *publ = kzalloc(sizeof(*publ), GFP_ATOMIC);
- if (publ == NULL) {
- pr_warn("Publication creation failure, no memory\n");
+
+ if (!publ)
return NULL;
- }
publ->type = type;
publ->lower = lower;
@@ -119,372 +106,298 @@ static struct publication *publ_create(u32 type, u32 lower, u32 upper,
publ->port = port;
publ->key = key;
INIT_LIST_HEAD(&publ->binding_sock);
+ INIT_LIST_HEAD(&publ->binding_node);
+ INIT_LIST_HEAD(&publ->local_publ);
+ INIT_LIST_HEAD(&publ->all_publ);
return publ;
}
/**
- * tipc_subseq_alloc - allocate a specified number of sub-sequence structures
- */
-static struct sub_seq *tipc_subseq_alloc(u32 cnt)
-{
- return kcalloc(cnt, sizeof(struct sub_seq), GFP_ATOMIC);
-}
-
-/**
- * tipc_nameseq_create - create a name sequence structure for the specified 'type'
+ * tipc_service_create - create a service structure for the specified 'type'
*
- * Allocates a single sub-sequence structure and sets it to all 0's.
+ * Allocates a single range structure and sets it to all 0's.
*/
-static struct name_seq *tipc_nameseq_create(u32 type, struct hlist_head *seq_head)
+static struct tipc_service *tipc_service_create(u32 type, struct hlist_head *hd)
{
- struct name_seq *nseq = kzalloc(sizeof(*nseq), GFP_ATOMIC);
- struct sub_seq *sseq = tipc_subseq_alloc(1);
+ struct tipc_service *service = kzalloc(sizeof(*service), GFP_ATOMIC);
- if (!nseq || !sseq) {
- pr_warn("Name sequence creation failed, no memory\n");
- kfree(nseq);
- kfree(sseq);
+ if (!service) {
+ pr_warn("Service creation failed, no memory\n");
return NULL;
}
- spin_lock_init(&nseq->lock);
- nseq->type = type;
- nseq->sseqs = sseq;
- nseq->alloc = 1;
- INIT_HLIST_NODE(&nseq->ns_list);
- INIT_LIST_HEAD(&nseq->subscriptions);
- hlist_add_head_rcu(&nseq->ns_list, seq_head);
- return nseq;
+ spin_lock_init(&service->lock);
+ service->type = type;
+ service->ranges = RB_ROOT;
+ INIT_HLIST_NODE(&service->service_list);
+ INIT_LIST_HEAD(&service->subscriptions);
+ hlist_add_head_rcu(&service->service_list, hd);
+ return service;
}
/**
- * nameseq_find_subseq - find sub-sequence (if any) matching a name instance
+ * tipc_service_find_range - find service range matching a service instance
*
- * Very time-critical, so binary searches through sub-sequence array.
+ * Very time-critical, so binary search through range rb tree
*/
-static struct sub_seq *nameseq_find_subseq(struct name_seq *nseq,
- u32 instance)
+static struct service_range *tipc_service_find_range(struct tipc_service *sc,
+ u32 instance)
{
- struct sub_seq *sseqs = nseq->sseqs;
- int low = 0;
- int high = nseq->first_free - 1;
- int mid;
-
- while (low <= high) {
- mid = (low + high) / 2;
- if (instance < sseqs[mid].lower)
- high = mid - 1;
- else if (instance > sseqs[mid].upper)
- low = mid + 1;
+ struct rb_node *n = sc->ranges.rb_node;
+ struct service_range *sr;
+
+ while (n) {
+ sr = container_of(n, struct service_range, tree_node);
+ if (sr->lower > instance)
+ n = n->rb_left;
+ else if (sr->upper < instance)
+ n = n->rb_right;
else
- return &sseqs[mid];
+ return sr;
}
return NULL;
}
-/**
- * nameseq_locate_subseq - determine position of name instance in sub-sequence
- *
- * Returns index in sub-sequence array of the entry that contains the specified
- * instance value; if no entry contains that value, returns the position
- * where a new entry for it would be inserted in the array.
- *
- * Note: Similar to binary search code for locating a sub-sequence.
- */
-static u32 nameseq_locate_subseq(struct name_seq *nseq, u32 instance)
+static struct service_range *tipc_service_create_range(struct tipc_service *sc,
+ u32 lower, u32 upper)
{
- struct sub_seq *sseqs = nseq->sseqs;
- int low = 0;
- int high = nseq->first_free - 1;
- int mid;
-
- while (low <= high) {
- mid = (low + high) / 2;
- if (instance < sseqs[mid].lower)
- high = mid - 1;
- else if (instance > sseqs[mid].upper)
- low = mid + 1;
+ struct rb_node **n, *parent = NULL;
+ struct service_range *sr, *tmp;
+
+ n = &sc->ranges.rb_node;
+ while (*n) {
+ tmp = container_of(*n, struct service_range, tree_node);
+ parent = *n;
+ tmp = container_of(parent, struct service_range, tree_node);
+ if (lower < tmp->lower)
+ n = &(*n)->rb_left;
+ else if (upper > tmp->upper)
+ n = &(*n)->rb_right;
else
- return mid;
+ return NULL;
}
- return low;
+ sr = kzalloc(sizeof(*sr), GFP_ATOMIC);
+ if (!sr)
+ return NULL;
+ sr->lower = lower;
+ sr->upper = upper;
+ INIT_LIST_HEAD(&sr->local_publ);
+ INIT_LIST_HEAD(&sr->all_publ);
+ rb_link_node(&sr->tree_node, parent, n);
+ rb_insert_color(&sr->tree_node, &sc->ranges);
+ return sr;
}
-/**
- * tipc_nameseq_insert_publ
- */
-static struct publication *tipc_nameseq_insert_publ(struct net *net,
- struct name_seq *nseq,
+static struct publication *tipc_service_insert_publ(struct net *net,
+ struct tipc_service *sc,
u32 type, u32 lower,
u32 upper, u32 scope,
- u32 node, u32 port, u32 key)
+ u32 node, u32 port,
+ u32 key)
{
- struct tipc_subscription *s;
- struct tipc_subscription *st;
- struct publication *publ;
- struct sub_seq *sseq;
- struct name_info *info;
- int created_subseq = 0;
-
- sseq = nameseq_find_subseq(nseq, lower);
- if (sseq) {
-
- /* Lower end overlaps existing entry => need an exact match */
- if ((sseq->lower != lower) || (sseq->upper != upper)) {
- return NULL;
- }
-
- info = sseq->info;
-
- /* Check if an identical publication already exists */
- list_for_each_entry(publ, &info->all_publ, all_publ) {
- if (publ->port == port && publ->key == key &&
- (!publ->node || publ->node == node))
- return NULL;
- }
- } else {
- u32 inspos;
- struct sub_seq *freesseq;
-
- /* Find where lower end should be inserted */
- inspos = nameseq_locate_subseq(nseq, lower);
-
- /* Fail if upper end overlaps into an existing entry */
- if ((inspos < nseq->first_free) &&
- (upper >= nseq->sseqs[inspos].lower)) {
- return NULL;
- }
-
- /* Ensure there is space for new sub-sequence */
- if (nseq->first_free == nseq->alloc) {
- struct sub_seq *sseqs = tipc_subseq_alloc(nseq->alloc * 2);
-
- if (!sseqs) {
- pr_warn("Cannot publish {%u,%u,%u}, no memory\n",
- type, lower, upper);
- return NULL;
- }
- memcpy(sseqs, nseq->sseqs,
- nseq->alloc * sizeof(struct sub_seq));
- kfree(nseq->sseqs);
- nseq->sseqs = sseqs;
- nseq->alloc *= 2;
- }
-
- info = kzalloc(sizeof(*info), GFP_ATOMIC);
- if (!info) {
- pr_warn("Cannot publish {%u,%u,%u}, no memory\n",
- type, lower, upper);
- return NULL;
- }
-
- INIT_LIST_HEAD(&info->local_publ);
- INIT_LIST_HEAD(&info->all_publ);
-
- /* Insert new sub-sequence */
- sseq = &nseq->sseqs[inspos];
- freesseq = &nseq->sseqs[nseq->first_free];
- memmove(sseq + 1, sseq, (freesseq - sseq) * sizeof(*sseq));
- memset(sseq, 0, sizeof(*sseq));
- nseq->first_free++;
- sseq->lower = lower;
- sseq->upper = upper;
- sseq->info = info;
- created_subseq = 1;
+ struct tipc_subscription *sub, *tmp;
+ struct service_range *sr;
+ struct publication *p;
+ bool first = false;
+
+ sr = tipc_service_find_range(sc, lower);
+ if (!sr) {
+ sr = tipc_service_create_range(sc, lower, upper);
+ if (!sr)
+ goto err;
+ first = true;
}
- /* Insert a publication */
- publ = publ_create(type, lower, upper, scope, node, port, key);
- if (!publ)
+ /* Lower end overlaps existing entry, but we need an exact match */
+ if (sr->lower != lower || sr->upper != upper)
return NULL;
- list_add(&publ->all_publ, &info->all_publ);
+ /* Return if the publication already exists */
+ list_for_each_entry(p, &sr->all_publ, all_publ) {
+ if (p->key == key && (!p->node || p->node == node))
+ return NULL;
+ }
+ /* Create and insert publication */
+ p = tipc_publ_create(type, lower, upper, scope, node, port, key);
+ if (!p)
+ goto err;
if (in_own_node(net, node))
- list_add(&publ->local_publ, &info->local_publ);
+ list_add(&p->local_publ, &sr->local_publ);
+ list_add(&p->all_publ, &sr->all_publ);
/* Any subscriptions waiting for notification? */
- list_for_each_entry_safe(s, st, &nseq->subscriptions, nameseq_list) {
- tipc_sub_report_overlap(s, publ->lower, publ->upper,
- TIPC_PUBLISHED, publ->port,
- publ->node, publ->scope,
- created_subseq);
+ list_for_each_entry_safe(sub, tmp, &sc->subscriptions, service_list) {
+ tipc_sub_report_overlap(sub, p->lower, p->upper, TIPC_PUBLISHED,
+ p->port, p->node, p->scope, first);
}
- return publ;
+ return p;
+err:
+ pr_warn("Failed to bind to %u,%u,%u, no memory\n", type, lower, upper);
+ return NULL;
}
/**
- * tipc_nameseq_remove_publ
+ * tipc_service_remove_publ - remove a publication from a service
*
* NOTE: There may be cases where TIPC is asked to remove a publication
* that is not in the name table. For example, if another node issues a
- * publication for a name sequence that overlaps an existing name sequence
+ * publication for a name range that overlaps an existing name range
* the publication will not be recorded, which means the publication won't
- * be found when the name sequence is later withdrawn by that node.
+ * be found when the name range is later withdrawn by that node.
* A failed withdraw request simply returns a failure indication and lets the
* caller issue any error or warning messages associated with such a problem.
*/
-static struct publication *tipc_nameseq_remove_publ(struct net *net,
- struct name_seq *nseq,
+static struct publication *tipc_service_remove_publ(struct net *net,
+ struct tipc_service *sc,
u32 inst, u32 node,
u32 port, u32 key)
{
- struct publication *publ;
- struct sub_seq *sseq = nameseq_find_subseq(nseq, inst);
- struct name_info *info;
- struct sub_seq *free;
- struct tipc_subscription *s, *st;
- int removed_subseq = 0;
-
- if (!sseq)
- return NULL;
+ struct tipc_subscription *sub, *tmp;
+ struct service_range *sr;
+ struct publication *p;
+ bool found = false;
+ bool last = false;
- info = sseq->info;
+ sr = tipc_service_find_range(sc, inst);
+ if (!sr)
+ return NULL;
- /* Locate publication, if it exists */
- list_for_each_entry(publ, &info->all_publ, all_publ) {
- if (publ->key == key && publ->port == port &&
- (!publ->node || publ->node == node))
- goto found;
+ /* Find publication, if it exists */
+ list_for_each_entry(p, &sr->all_publ, all_publ) {
+ if (p->key != key || (node && node != p->node))
+ continue;
+ found = true;
+ break;
}
- return NULL;
+ if (!found)
+ return NULL;
-found:
- list_del(&publ->all_publ);
- if (in_own_node(net, node))
- list_del(&publ->local_publ);
-
- /* Contract subseq list if no more publications for that subseq */
- if (list_empty(&info->all_publ)) {
- kfree(info);
- free = &nseq->sseqs[nseq->first_free--];
- memmove(sseq, sseq + 1, (free - (sseq + 1)) * sizeof(*sseq));
- removed_subseq = 1;
+ list_del(&p->all_publ);
+ list_del(&p->local_publ);
+
+ /* Remove service range item if this was its last publication */
+ if (list_empty(&sr->all_publ)) {
+ last = true;
+ rb_erase(&sr->tree_node, &sc->ranges);
+ kfree(sr);
}
/* Notify any waiting subscriptions */
- list_for_each_entry_safe(s, st, &nseq->subscriptions, nameseq_list) {
- tipc_sub_report_overlap(s, publ->lower, publ->upper,
- TIPC_WITHDRAWN, publ->port,
- publ->node, publ->scope,
- removed_subseq);
+ list_for_each_entry_safe(sub, tmp, &sc->subscriptions, service_list) {
+ tipc_sub_report_overlap(sub, p->lower, p->upper, TIPC_WITHDRAWN,
+ p->port, p->node, p->scope, last);
}
-
- return publ;
+ return p;
}
/**
- * tipc_nameseq_subscribe - attach a subscription, and optionally
- * issue the prescribed number of events if there is any sub-
- * sequence overlapping with the requested sequence
+ * tipc_service_subscribe - attach a subscription, and optionally
+ * issue the prescribed number of events if there is any service
+ * range overlapping with the requested range
*/
-static void tipc_nameseq_subscribe(struct name_seq *nseq,
+static void tipc_service_subscribe(struct tipc_service *service,
struct tipc_subscription *sub)
{
- struct sub_seq *sseq = nseq->sseqs;
+ struct tipc_subscr *sb = &sub->evt.s;
+ struct service_range *sr;
struct tipc_name_seq ns;
- struct tipc_subscr *s = &sub->evt.s;
- bool no_status;
+ struct publication *p;
+ struct rb_node *n;
+ bool first;
- ns.type = tipc_sub_read(s, seq.type);
- ns.lower = tipc_sub_read(s, seq.lower);
- ns.upper = tipc_sub_read(s, seq.upper);
- no_status = tipc_sub_read(s, filter) & TIPC_SUB_NO_STATUS;
+ ns.type = tipc_sub_read(sb, seq.type);
+ ns.lower = tipc_sub_read(sb, seq.lower);
+ ns.upper = tipc_sub_read(sb, seq.upper);
tipc_sub_get(sub);
- list_add(&sub->nameseq_list, &nseq->subscriptions);
+ list_add(&sub->service_list, &service->subscriptions);
- if (no_status || !sseq)
+ if (tipc_sub_read(sb, filter) & TIPC_SUB_NO_STATUS)
return;
- while (sseq != &nseq->sseqs[nseq->first_free]) {
- if (tipc_sub_check_overlap(&ns, sseq->lower, sseq->upper)) {
- struct publication *crs;
- struct name_info *info = sseq->info;
- int must_report = 1;
-
- list_for_each_entry(crs, &info->all_publ, all_publ) {
- tipc_sub_report_overlap(sub, sseq->lower,
- sseq->upper,
- TIPC_PUBLISHED,
- crs->port,
- crs->node,
- crs->scope,
- must_report);
- must_report = 0;
- }
+ for (n = rb_first(&service->ranges); n; n = rb_next(n)) {
+ sr = container_of(n, struct service_range, tree_node);
+ if (sr->lower > ns.upper)
+ break;
+ if (!tipc_sub_check_overlap(&ns, sr->lower, sr->upper))
+ continue;
+ first = true;
+
+ list_for_each_entry(p, &sr->all_publ, all_publ) {
+ tipc_sub_report_overlap(sub, sr->lower, sr->upper,
+ TIPC_PUBLISHED, p->port,
+ p->node, p->scope, first);
+ first = false;
}
- sseq++;
}
}
-static struct name_seq *nametbl_find_seq(struct net *net, u32 type)
+static struct tipc_service *tipc_service_find(struct net *net, u32 type)
{
- struct tipc_net *tn = net_generic(net, tipc_net_id);
- struct hlist_head *seq_head;
- struct name_seq *ns;
-
- seq_head = &tn->nametbl->seq_hlist[hash(type)];
- hlist_for_each_entry_rcu(ns, seq_head, ns_list) {
- if (ns->type == type)
- return ns;
+ struct name_table *nt = tipc_name_table(net);
+ struct hlist_head *service_head;
+ struct tipc_service *service;
+
+ service_head = &nt->services[hash(type)];
+ hlist_for_each_entry_rcu(service, service_head, service_list) {
+ if (service->type == type)
+ return service;
}
-
return NULL;
};
struct publication *tipc_nametbl_insert_publ(struct net *net, u32 type,
- u32 lower, u32 upper, u32 scope,
- u32 node, u32 port, u32 key)
+ u32 lower, u32 upper,
+ u32 scope, u32 node,
+ u32 port, u32 key)
{
- struct tipc_net *tn = net_generic(net, tipc_net_id);
- struct publication *publ;
- struct name_seq *seq = nametbl_find_seq(net, type);
- int index = hash(type);
+ struct name_table *nt = tipc_name_table(net);
+ struct tipc_service *sc;
+ struct publication *p;
if (scope > TIPC_NODE_SCOPE || lower > upper) {
- pr_debug("Failed to publish illegal {%u,%u,%u} with scope %u\n",
+ pr_debug("Failed to bind illegal {%u,%u,%u} with scope %u\n",
type, lower, upper, scope);
return NULL;
}
-
- if (!seq)
- seq = tipc_nameseq_create(type, &tn->nametbl->seq_hlist[index]);
- if (!seq)
+ sc = tipc_service_find(net, type);
+ if (!sc)
+ sc = tipc_service_create(type, &nt->services[hash(type)]);
+ if (!sc)
return NULL;
- spin_lock_bh(&seq->lock);
- publ = tipc_nameseq_insert_publ(net, seq, type, lower, upper,
- scope, node, port, key);
- spin_unlock_bh(&seq->lock);
- return publ;
+ spin_lock_bh(&sc->lock);
+ p = tipc_service_insert_publ(net, sc, type, lower, upper,
+ scope, node, port, key);
+ spin_unlock_bh(&sc->lock);
+ return p;
}
struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type,
- u32 lower, u32 node, u32 port,
- u32 key)
+ u32 lower, u32 node, u32 port,
+ u32 key)
{
- struct publication *publ;
- struct name_seq *seq = nametbl_find_seq(net, type);
+ struct tipc_service *sc = tipc_service_find(net, type);
+ struct publication *p = NULL;
- if (!seq)
+ if (!sc)
return NULL;
- spin_lock_bh(&seq->lock);
- publ = tipc_nameseq_remove_publ(net, seq, lower, node, port, key);
- if (!seq->first_free && list_empty(&seq->subscriptions)) {
- hlist_del_init_rcu(&seq->ns_list);
- kfree(seq->sseqs);
- spin_unlock_bh(&seq->lock);
- kfree_rcu(seq, rcu);
- return publ;
+ spin_lock_bh(&sc->lock);
+ p = tipc_service_remove_publ(net, sc, lower, node, port, key);
+
+ /* Delete service item if this no more publications and subscriptions */
+ if (RB_EMPTY_ROOT(&sc->ranges) && list_empty(&sc->subscriptions)) {
+ hlist_del_init_rcu(&sc->service_list);
+ kfree_rcu(sc, rcu);
}
- spin_unlock_bh(&seq->lock);
- return publ;
+ spin_unlock_bh(&sc->lock);
+ return p;
}
/**
- * tipc_nametbl_translate - perform name translation
+ * tipc_nametbl_translate - perform service instance to socket translation
*
* On entry, 'destnode' is the search domain used during translation.
*
@@ -492,7 +405,7 @@ struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type,
* - if name translation is deferred to another node/cluster/zone,
* leaves 'destnode' unchanged (will be non-zero) and returns 0
* - if name translation is attempted and succeeds, sets 'destnode'
- * to publishing node and returns port reference (will be non-zero)
+ * to publication node and returns port reference (will be non-zero)
* - if name translation is attempted and fails, sets 'destnode' to 0
* and returns 0
*/
@@ -502,10 +415,9 @@ u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance,
struct tipc_net *tn = tipc_net(net);
bool legacy = tn->legacy_addr_format;
u32 self = tipc_own_addr(net);
- struct sub_seq *sseq;
- struct name_info *info;
- struct publication *publ;
- struct name_seq *seq;
+ struct service_range *sr;
+ struct tipc_service *sc;
+ struct publication *p;
u32 port = 0;
u32 node = 0;
@@ -513,49 +425,49 @@ u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance,
return 0;
rcu_read_lock();
- seq = nametbl_find_seq(net, type);
- if (unlikely(!seq))
+ sc = tipc_service_find(net, type);
+ if (unlikely(!sc))
goto not_found;
- spin_lock_bh(&seq->lock);
- sseq = nameseq_find_subseq(seq, instance);
- if (unlikely(!sseq))
+
+ spin_lock_bh(&sc->lock);
+ sr = tipc_service_find_range(sc, instance);
+ if (unlikely(!sr))
goto no_match;
- info = sseq->info;
/* Closest-First Algorithm */
if (legacy && !*destnode) {
- if (!list_empty(&info->local_publ)) {
- publ = list_first_entry(&info->local_publ,
- struct publication,
- local_publ);
- list_move_tail(&publ->local_publ,
- &info->local_publ);
+ if (!list_empty(&sr->local_publ)) {
+ p = list_first_entry(&sr->local_publ,
+ struct publication,
+ local_publ);
+ list_move_tail(&p->local_publ,
+ &sr->local_publ);
} else {
- publ = list_first_entry(&info->all_publ,
- struct publication,
- all_publ);
- list_move_tail(&publ->all_publ,
- &info->all_publ);
+ p = list_first_entry(&sr->all_publ,
+ struct publication,
+ all_publ);
+ list_move_tail(&p->all_publ,
+ &sr->all_publ);
}
}
/* Round-Robin Algorithm */
- else if (*destnode == tipc_own_addr(net)) {
- if (list_empty(&info->local_publ))
+ else if (*destnode == self) {
+ if (list_empty(&sr->local_publ))
goto no_match;
- publ = list_first_entry(&info->local_publ, struct publication,
- local_publ);
- list_move_tail(&publ->local_publ, &info->local_publ);
+ p = list_first_entry(&sr->local_publ, struct publication,
+ local_publ);
+ list_move_tail(&p->local_publ, &sr->local_publ);
} else {
- publ = list_first_entry(&info->all_publ, struct publication,
- all_publ);
- list_move_tail(&publ->all_publ, &info->all_publ);
+ p = list_first_entry(&sr->all_publ, struct publication,
+ all_publ);
+ list_move_tail(&p->all_publ, &sr->all_publ);
}
- port = publ->port;
- node = publ->node;
+ port = p->port;
+ node = p->node;
no_match:
- spin_unlock_bh(&seq->lock);
+ spin_unlock_bh(&sc->lock);
not_found:
rcu_read_unlock();
*destnode = node;
@@ -567,34 +479,36 @@ bool tipc_nametbl_lookup(struct net *net, u32 type, u32 instance, u32 scope,
bool all)
{
u32 self = tipc_own_addr(net);
- struct publication *publ;
- struct name_info *info;
- struct name_seq *seq;
- struct sub_seq *sseq;
+ struct service_range *sr;
+ struct tipc_service *sc;
+ struct publication *p;
*dstcnt = 0;
rcu_read_lock();
- seq = nametbl_find_seq(net, type);
- if (unlikely(!seq))
+ sc = tipc_service_find(net, type);
+ if (unlikely(!sc))
goto exit;
- spin_lock_bh(&seq->lock);
- sseq = nameseq_find_subseq(seq, instance);
- if (likely(sseq)) {
- info = sseq->info;
- list_for_each_entry(publ, &info->all_publ, all_publ) {
- if (publ->scope != scope)
- continue;
- if (publ->port == exclude && publ->node == self)
- continue;
- tipc_dest_push(dsts, publ->node, publ->port);
- (*dstcnt)++;
- if (all)
- continue;
- list_move_tail(&publ->all_publ, &info->all_publ);
- break;
- }
+
+ spin_lock_bh(&sc->lock);
+
+ sr = tipc_service_find_range(sc, instance);
+ if (!sr)
+ goto no_match;
+
+ list_for_each_entry(p, &sr->all_publ, all_publ) {
+ if (p->scope != scope)
+ continue;
+ if (p->port == exclude && p->node == self)
+ continue;
+ tipc_dest_push(dsts, p->node, p->port);
+ (*dstcnt)++;
+ if (all)
+ continue;
+ list_move_tail(&p->all_publ, &sr->all_publ);
+ break;
}
- spin_unlock_bh(&seq->lock);
+no_match:
+ spin_unlock_bh(&sc->lock);
exit:
rcu_read_unlock();
return !list_empty(dsts);
@@ -603,61 +517,64 @@ bool tipc_nametbl_lookup(struct net *net, u32 type, u32 instance, u32 scope,
void tipc_nametbl_mc_lookup(struct net *net, u32 type, u32 lower, u32 upper,
u32 scope, bool exact, struct list_head *dports)
{
- struct sub_seq *sseq_stop;
- struct name_info *info;
+ struct service_range *sr;
+ struct tipc_service *sc;
struct publication *p;
- struct name_seq *seq;
- struct sub_seq *sseq;
+ struct rb_node *n;
rcu_read_lock();
- seq = nametbl_find_seq(net, type);
- if (!seq)
+ sc = tipc_service_find(net, type);
+ if (!sc)
goto exit;
- spin_lock_bh(&seq->lock);
- sseq = seq->sseqs + nameseq_locate_subseq(seq, lower);
- sseq_stop = seq->sseqs + seq->first_free;
- for (; sseq != sseq_stop; sseq++) {
- if (sseq->lower > upper)
+ spin_lock_bh(&sc->lock);
+
+ for (n = rb_first(&sc->ranges); n; n = rb_next(n)) {
+ sr = container_of(n, struct service_range, tree_node);
+ if (sr->upper < lower)
+ continue;
+ if (sr->lower > upper)
break;
- info = sseq->info;
- list_for_each_entry(p, &info->local_publ, local_publ) {
+ list_for_each_entry(p, &sr->local_publ, local_publ) {
if (p->scope == scope || (!exact && p->scope < scope))
tipc_dest_push(dports, 0, p->port);
}
}
- spin_unlock_bh(&seq->lock);
+ spin_unlock_bh(&sc->lock);
exit:
rcu_read_unlock();
}
/* tipc_nametbl_lookup_dst_nodes - find broadcast destination nodes
* - Creates list of nodes that overlap the given multicast address
- * - Determines if any node local ports overlap
+ * - Determines if any node local destinations overlap
*/
void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower,
u32 upper, struct tipc_nlist *nodes)
{
- struct sub_seq *sseq, *stop;
- struct publication *publ;
- struct name_info *info;
- struct name_seq *seq;
+ struct service_range *sr;
+ struct tipc_service *sc;
+ struct publication *p;
+ struct rb_node *n;
rcu_read_lock();
- seq = nametbl_find_seq(net, type);
- if (!seq)
+ sc = tipc_service_find(net, type);
+ if (!sc)
goto exit;
- spin_lock_bh(&seq->lock);
- sseq = seq->sseqs + nameseq_locate_subseq(seq, lower);
- stop = seq->sseqs + seq->first_free;
- for (; sseq != stop && sseq->lower <= upper; sseq++) {
- info = sseq->info;
- list_for_each_entry(publ, &info->all_publ, all_publ) {
- tipc_nlist_add(nodes, publ->node);
+ spin_lock_bh(&sc->lock);
+
+ for (n = rb_first(&sc->ranges); n; n = rb_next(n)) {
+ sr = container_of(n, struct service_range, tree_node);
+ if (sr->upper < lower)
+ continue;
+ if (sr->lower > upper)
+ break;
+ list_for_each_entry(p, &sr->all_publ, all_publ) {
+ tipc_nlist_add(nodes, p->node);
}
}
- spin_unlock_bh(&seq->lock);
+ spin_unlock_bh(&sc->lock);
exit:
rcu_read_unlock();
}
@@ -667,89 +584,88 @@ void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower,
void tipc_nametbl_build_group(struct net *net, struct tipc_group *grp,
u32 type, u32 scope)
{
- struct sub_seq *sseq, *stop;
- struct name_info *info;
+ struct service_range *sr;
+ struct tipc_service *sc;
struct publication *p;
- struct name_seq *seq;
+ struct rb_node *n;
rcu_read_lock();
- seq = nametbl_find_seq(net, type);
- if (!seq)
+ sc = tipc_service_find(net, type);
+ if (!sc)
goto exit;
- spin_lock_bh(&seq->lock);
- sseq = seq->sseqs;
- stop = seq->sseqs + seq->first_free;
- for (; sseq != stop; sseq++) {
- info = sseq->info;
- list_for_each_entry(p, &info->all_publ, all_publ) {
+ spin_lock_bh(&sc->lock);
+ for (n = rb_first(&sc->ranges); n; n = rb_next(n)) {
+ sr = container_of(n, struct service_range, tree_node);
+ list_for_each_entry(p, &sr->all_publ, all_publ) {
if (p->scope != scope)
continue;
tipc_group_add_member(grp, p->node, p->port, p->lower);
}
}
- spin_unlock_bh(&seq->lock);
+ spin_unlock_bh(&sc->lock);
exit:
rcu_read_unlock();
}
-/*
- * tipc_nametbl_publish - add name publication to network name tables
+/* tipc_nametbl_publish - add service binding to name table
*/
struct publication *tipc_nametbl_publish(struct net *net, u32 type, u32 lower,
- u32 upper, u32 scope, u32 port_ref,
+ u32 upper, u32 scope, u32 port,
u32 key)
{
- struct publication *publ;
- struct sk_buff *buf = NULL;
- struct tipc_net *tn = net_generic(net, tipc_net_id);
+ struct name_table *nt = tipc_name_table(net);
+ struct tipc_net *tn = tipc_net(net);
+ struct publication *p = NULL;
+ struct sk_buff *skb = NULL;
spin_lock_bh(&tn->nametbl_lock);
- if (tn->nametbl->local_publ_count >= TIPC_MAX_PUBLICATIONS) {
- pr_warn("Publication failed, local publication limit reached (%u)\n",
- TIPC_MAX_PUBLICATIONS);
- spin_unlock_bh(&tn->nametbl_lock);
- return NULL;
+
+ if (nt->local_publ_count >= TIPC_MAX_PUBL) {
+ pr_warn("Bind failed, max limit %u reached\n", TIPC_MAX_PUBL);
+ goto exit;
}
- publ = tipc_nametbl_insert_publ(net, type, lower, upper, scope,
- tipc_own_addr(net), port_ref, key);
- if (likely(publ)) {
- tn->nametbl->local_publ_count++;
- buf = tipc_named_publish(net, publ);
+ p = tipc_nametbl_insert_publ(net, type, lower, upper, scope,
+ tipc_own_addr(net), port, key);
+ if (p) {
+ nt->local_publ_count++;
+ skb = tipc_named_publish(net, p);
/* Any pending external events? */
tipc_named_process_backlog(net);
}
+exit:
spin_unlock_bh(&tn->nametbl_lock);
- if (buf)
- tipc_node_broadcast(net, buf);
- return publ;
+ if (skb)
+ tipc_node_broadcast(net, skb);
+ return p;
}
/**
- * tipc_nametbl_withdraw - withdraw name publication from network name tables
+ * tipc_nametbl_withdraw - withdraw a service binding
*/
-int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower, u32 port,
- u32 key)
+int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower,
+ u32 port, u32 key)
{
- struct publication *publ;
+ struct name_table *nt = tipc_name_table(net);
+ struct tipc_net *tn = tipc_net(net);
+ u32 self = tipc_own_addr(net);
struct sk_buff *skb = NULL;
- struct tipc_net *tn = net_generic(net, tipc_net_id);
+ struct publication *p;
spin_lock_bh(&tn->nametbl_lock);
- publ = tipc_nametbl_remove_publ(net, type, lower, tipc_own_addr(net),
- port, key);
- if (likely(publ)) {
- tn->nametbl->local_publ_count--;
- skb = tipc_named_withdraw(net, publ);
+
+ p = tipc_nametbl_remove_publ(net, type, lower, self, port, key);
+ if (p) {
+ nt->local_publ_count--;
+ skb = tipc_named_withdraw(net, p);
/* Any pending external events? */
tipc_named_process_backlog(net);
- list_del_init(&publ->binding_sock);
- kfree_rcu(publ, rcu);
+ list_del_init(&p->binding_sock);
+ kfree_rcu(p, rcu);
} else {
- pr_err("Unable to remove local publication\n"
- "(type=%u, lower=%u, port=%u, key=%u)\n",
+ pr_err("Failed to remove local publication {%u,%u,%u}/%u\n",
type, lower, port, key);
}
spin_unlock_bh(&tn->nametbl_lock);
@@ -766,27 +682,24 @@ int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower, u32 port,
*/
void tipc_nametbl_subscribe(struct tipc_subscription *sub)
{
+ struct name_table *nt = tipc_name_table(sub->net);
struct tipc_net *tn = tipc_net(sub->net);
struct tipc_subscr *s = &sub->evt.s;
u32 type = tipc_sub_read(s, seq.type);
- int index = hash(type);
- struct name_seq *seq;
- struct tipc_name_seq ns;
+ struct tipc_service *sc;
spin_lock_bh(&tn->nametbl_lock);
- seq = nametbl_find_seq(sub->net, type);
- if (!seq)
- seq = tipc_nameseq_create(type, &tn->nametbl->seq_hlist[index]);
- if (seq) {
- spin_lock_bh(&seq->lock);
- tipc_nameseq_subscribe(seq, sub);
- spin_unlock_bh(&seq->lock);
+ sc = tipc_service_find(sub->net, type);
+ if (!sc)
+ sc = tipc_service_create(type, &nt->services[hash(type)]);
+ if (sc) {
+ spin_lock_bh(&sc->lock);
+ tipc_service_subscribe(sc, sub);
+ spin_unlock_bh(&sc->lock);
} else {
- ns.type = tipc_sub_read(s, seq.type);
- ns.lower = tipc_sub_read(s, seq.lower);
- ns.upper = tipc_sub_read(s, seq.upper);
- pr_warn("Failed to create subscription for {%u,%u,%u}\n",
- ns.type, ns.lower, ns.upper);
+ pr_warn("Failed to subscribe for {%u,%u,%u}\n", type,
+ tipc_sub_read(s, seq.lower),
+ tipc_sub_read(s, seq.upper));
}
spin_unlock_bh(&tn->nametbl_lock);
}
@@ -796,124 +709,122 @@ void tipc_nametbl_subscribe(struct tipc_subscription *sub)
*/
void tipc_nametbl_unsubscribe(struct tipc_subscription *sub)
{
- struct tipc_subscr *s = &sub->evt.s;
struct tipc_net *tn = tipc_net(sub->net);
- struct name_seq *seq;
+ struct tipc_subscr *s = &sub->evt.s;
u32 type = tipc_sub_read(s, seq.type);
+ struct tipc_service *sc;
spin_lock_bh(&tn->nametbl_lock);
- seq = nametbl_find_seq(sub->net, type);
- if (seq != NULL) {
- spin_lock_bh(&seq->lock);
- list_del_init(&sub->nameseq_list);
- tipc_sub_put(sub);
- if (!seq->first_free && list_empty(&seq->subscriptions)) {
- hlist_del_init_rcu(&seq->ns_list);
- kfree(seq->sseqs);
- spin_unlock_bh(&seq->lock);
- kfree_rcu(seq, rcu);
- } else {
- spin_unlock_bh(&seq->lock);
- }
+ sc = tipc_service_find(sub->net, type);
+ if (!sc)
+ goto exit;
+
+ spin_lock_bh(&sc->lock);
+ list_del_init(&sub->service_list);
+ tipc_sub_put(sub);
+
+ /* Delete service item if no more publications and subscriptions */
+ if (RB_EMPTY_ROOT(&sc->ranges) && list_empty(&sc->subscriptions)) {
+ hlist_del_init_rcu(&sc->service_list);
+ kfree_rcu(sc, rcu);
}
+ spin_unlock_bh(&sc->lock);
+exit:
spin_unlock_bh(&tn->nametbl_lock);
}
int tipc_nametbl_init(struct net *net)
{
- struct tipc_net *tn = net_generic(net, tipc_net_id);
- struct name_table *tipc_nametbl;
+ struct tipc_net *tn = tipc_net(net);
+ struct name_table *nt;
int i;
- tipc_nametbl = kzalloc(sizeof(*tipc_nametbl), GFP_ATOMIC);
- if (!tipc_nametbl)
+ nt = kzalloc(sizeof(*nt), GFP_ATOMIC);
+ if (!nt)
return -ENOMEM;
for (i = 0; i < TIPC_NAMETBL_SIZE; i++)
- INIT_HLIST_HEAD(&tipc_nametbl->seq_hlist[i]);
+ INIT_HLIST_HEAD(&nt->services[i]);
- INIT_LIST_HEAD(&tipc_nametbl->node_scope);
- INIT_LIST_HEAD(&tipc_nametbl->cluster_scope);
- tn->nametbl = tipc_nametbl;
+ INIT_LIST_HEAD(&nt->node_scope);
+ INIT_LIST_HEAD(&nt->cluster_scope);
+ tn->nametbl = nt;
spin_lock_init(&tn->nametbl_lock);
return 0;
}
/**
- * tipc_purge_publications - remove all publications for a given type
- *
- * tipc_nametbl_lock must be held when calling this function
+ * tipc_service_delete - purge all publications for a service and delete it
*/
-static void tipc_purge_publications(struct net *net, struct name_seq *seq)
+static void tipc_service_delete(struct net *net, struct tipc_service *sc)
{
- struct publication *publ, *safe;
- struct sub_seq *sseq;
- struct name_info *info;
-
- spin_lock_bh(&seq->lock);
- sseq = seq->sseqs;
- info = sseq->info;
- list_for_each_entry_safe(publ, safe, &info->all_publ, all_publ) {
- tipc_nameseq_remove_publ(net, seq, publ->lower, publ->node,
- publ->port, publ->key);
- kfree_rcu(publ, rcu);
+ struct service_range *sr, *tmpr;
+ struct publication *p, *tmpb;
+
+ spin_lock_bh(&sc->lock);
+ rbtree_postorder_for_each_entry_safe(sr, tmpr, &sc->ranges, tree_node) {
+ list_for_each_entry_safe(p, tmpb,
+ &sr->all_publ, all_publ) {
+ tipc_service_remove_publ(net, sc, p->lower, p->node,
+ p->port, p->key);
+ kfree_rcu(p, rcu);
+ }
}
- hlist_del_init_rcu(&seq->ns_list);
- kfree(seq->sseqs);
- spin_unlock_bh(&seq->lock);
-
- kfree_rcu(seq, rcu);
+ hlist_del_init_rcu(&sc->service_list);
+ spin_unlock_bh(&sc->lock);
+ kfree_rcu(sc, rcu);
}
void tipc_nametbl_stop(struct net *net)
{
+ struct name_table *nt = tipc_name_table(net);
+ struct tipc_net *tn = tipc_net(net);
+ struct hlist_head *service_head;
+ struct tipc_service *service;
u32 i;
- struct name_seq *seq;
- struct hlist_head *seq_head;
- struct tipc_net *tn = net_generic(net, tipc_net_id);
- struct name_table *tipc_nametbl = tn->nametbl;
/* Verify name table is empty and purge any lingering
* publications, then release the name table
*/
spin_lock_bh(&tn->nametbl_lock);
for (i = 0; i < TIPC_NAMETBL_SIZE; i++) {
- if (hlist_empty(&tipc_nametbl->seq_hlist[i]))
+ if (hlist_empty(&nt->services[i]))
continue;
- seq_head = &tipc_nametbl->seq_hlist[i];
- hlist_for_each_entry_rcu(seq, seq_head, ns_list) {
- tipc_purge_publications(net, seq);
+ service_head = &nt->services[i];
+ hlist_for_each_entry_rcu(service, service_head, service_list) {
+ tipc_service_delete(net, service);
}
}
spin_unlock_bh(&tn->nametbl_lock);
synchronize_net();
- kfree(tipc_nametbl);
-
+ kfree(nt);
}
static int __tipc_nl_add_nametable_publ(struct tipc_nl_msg *msg,
- struct name_seq *seq,
- struct sub_seq *sseq, u32 *last_publ)
+ struct tipc_service *service,
+ struct service_range *sr,
+ u32 *last_key)
{
- void *hdr;
- struct nlattr *attrs;
- struct nlattr *publ;
struct publication *p;
+ struct nlattr *attrs;
+ struct nlattr *b;
+ void *hdr;
- if (*last_publ) {
- list_for_each_entry(p, &sseq->info->all_publ, all_publ)
- if (p->key == *last_publ)
+ if (*last_key) {
+ list_for_each_entry(p, &sr->all_publ, all_publ)
+ if (p->key == *last_key)
break;
- if (p->key != *last_publ)
+ if (p->key != *last_key)
return -EPIPE;
} else {
- p = list_first_entry(&sseq->info->all_publ, struct publication,
+ p = list_first_entry(&sr->all_publ,
+ struct publication,
all_publ);
}
- list_for_each_entry_from(p, &sseq->info->all_publ, all_publ) {
- *last_publ = p->key;
+ list_for_each_entry_from(p, &sr->all_publ, all_publ) {
+ *last_key = p->key;
hdr = genlmsg_put(msg->skb, msg->portid, msg->seq,
&tipc_genl_family, NLM_F_MULTI,
@@ -925,15 +836,15 @@ static int __tipc_nl_add_nametable_publ(struct tipc_nl_msg *msg,
if (!attrs)
goto msg_full;
- publ = nla_nest_start(msg->skb, TIPC_NLA_NAME_TABLE_PUBL);
- if (!publ)
+ b = nla_nest_start(msg->skb, TIPC_NLA_NAME_TABLE_PUBL);
+ if (!b)
goto attr_msg_full;
- if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_TYPE, seq->type))
+ if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_TYPE, service->type))
goto publ_msg_full;
- if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_LOWER, sseq->lower))
+ if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_LOWER, sr->lower))
goto publ_msg_full;
- if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_UPPER, sseq->upper))
+ if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_UPPER, sr->upper))
goto publ_msg_full;
if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_SCOPE, p->scope))
goto publ_msg_full;
@@ -944,16 +855,16 @@ static int __tipc_nl_add_nametable_publ(struct tipc_nl_msg *msg,
if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_KEY, p->key))
goto publ_msg_full;
- nla_nest_end(msg->skb, publ);
+ nla_nest_end(msg->skb, b);
nla_nest_end(msg->skb, attrs);
genlmsg_end(msg->skb, hdr);
}
- *last_publ = 0;
+ *last_key = 0;
return 0;
publ_msg_full:
- nla_nest_cancel(msg->skb, publ);
+ nla_nest_cancel(msg->skb, b);
attr_msg_full:
nla_nest_cancel(msg->skb, attrs);
msg_full:
@@ -962,39 +873,34 @@ static int __tipc_nl_add_nametable_publ(struct tipc_nl_msg *msg,
return -EMSGSIZE;
}
-static int __tipc_nl_subseq_list(struct tipc_nl_msg *msg, struct name_seq *seq,
- u32 *last_lower, u32 *last_publ)
+static int __tipc_nl_service_range_list(struct tipc_nl_msg *msg,
+ struct tipc_service *sc,
+ u32 *last_lower, u32 *last_key)
{
- struct sub_seq *sseq;
- struct sub_seq *sseq_start;
+ struct service_range *sr;
+ struct rb_node *n;
int err;
- if (*last_lower) {
- sseq_start = nameseq_find_subseq(seq, *last_lower);
- if (!sseq_start)
- return -EPIPE;
- } else {
- sseq_start = seq->sseqs;
- }
-
- for (sseq = sseq_start; sseq != &seq->sseqs[seq->first_free]; sseq++) {
- err = __tipc_nl_add_nametable_publ(msg, seq, sseq, last_publ);
+ for (n = rb_first(&sc->ranges); n; n = rb_next(n)) {
+ sr = container_of(n, struct service_range, tree_node);
+ if (sr->lower < *last_lower)
+ continue;
+ err = __tipc_nl_add_nametable_publ(msg, sc, sr, last_key);
if (err) {
- *last_lower = sseq->lower;
+ *last_lower = sr->lower;
return err;
}
}
*last_lower = 0;
-
return 0;
}
-static int tipc_nl_seq_list(struct net *net, struct tipc_nl_msg *msg,
- u32 *last_type, u32 *last_lower, u32 *last_publ)
+static int tipc_nl_service_list(struct net *net, struct tipc_nl_msg *msg,
+ u32 *last_type, u32 *last_lower, u32 *last_key)
{
- struct tipc_net *tn = net_generic(net, tipc_net_id);
- struct hlist_head *seq_head;
- struct name_seq *seq = NULL;
+ struct tipc_net *tn = tipc_net(net);
+ struct tipc_service *service = NULL;
+ struct hlist_head *head;
int err;
int i;
@@ -1004,30 +910,31 @@ static int tipc_nl_seq_list(struct net *net, struct tipc_nl_msg *msg,
i = 0;
for (; i < TIPC_NAMETBL_SIZE; i++) {
- seq_head = &tn->nametbl->seq_hlist[i];
+ head = &tn->nametbl->services[i];
if (*last_type) {
- seq = nametbl_find_seq(net, *last_type);
- if (!seq)
+ service = tipc_service_find(net, *last_type);
+ if (!service)
return -EPIPE;
} else {
- hlist_for_each_entry_rcu(seq, seq_head, ns_list)
+ hlist_for_each_entry_rcu(service, head, service_list)
break;
- if (!seq)
+ if (!service)
continue;
}
- hlist_for_each_entry_from_rcu(seq, ns_list) {
- spin_lock_bh(&seq->lock);
- err = __tipc_nl_subseq_list(msg, seq, last_lower,
- last_publ);
+ hlist_for_each_entry_from_rcu(service, service_list) {
+ spin_lock_bh(&service->lock);
+ err = __tipc_nl_service_range_list(msg, service,
+ last_lower,
+ last_key);
if (err) {
- *last_type = seq->type;
- spin_unlock_bh(&seq->lock);
+ *last_type = service->type;
+ spin_unlock_bh(&service->lock);
return err;
}
- spin_unlock_bh(&seq->lock);
+ spin_unlock_bh(&service->lock);
}
*last_type = 0;
}
@@ -1036,13 +943,13 @@ static int tipc_nl_seq_list(struct net *net, struct tipc_nl_msg *msg,
int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
- int err;
- int done = cb->args[3];
+ struct net *net = sock_net(skb->sk);
u32 last_type = cb->args[0];
u32 last_lower = cb->args[1];
- u32 last_publ = cb->args[2];
- struct net *net = sock_net(skb->sk);
+ u32 last_key = cb->args[2];
+ int done = cb->args[3];
struct tipc_nl_msg msg;
+ int err;
if (done)
return 0;
@@ -1052,7 +959,8 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb)
msg.seq = cb->nlh->nlmsg_seq;
rcu_read_lock();
- err = tipc_nl_seq_list(net, &msg, &last_type, &last_lower, &last_publ);
+ err = tipc_nl_service_list(net, &msg, &last_type,
+ &last_lower, &last_key);
if (!err) {
done = 1;
} else if (err != -EMSGSIZE) {
@@ -1068,7 +976,7 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb)
cb->args[0] = last_type;
cb->args[1] = last_lower;
- cb->args[2] = last_publ;
+ cb->args[2] = last_key;
cb->args[3] = done;
return skb->len;
diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h
index 34a4ccb..1b03b87 100644
--- a/net/tipc/name_table.h
+++ b/net/tipc/name_table.h
@@ -97,7 +97,7 @@ struct publication {
* @local_publ_count: number of publications issued by this node
*/
struct name_table {
- struct hlist_head seq_hlist[TIPC_NAMETBL_SIZE];
+ struct hlist_head services[TIPC_NAMETBL_SIZE];
struct list_head node_scope;
struct list_head cluster_scope;
u32 local_publ_count;
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 4fb4327..85e777e 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -324,12 +324,12 @@ static void tipc_node_write_unlock(struct tipc_node *n)
if (flags & TIPC_NOTIFY_LINK_UP) {
tipc_mon_peer_up(net, addr, bearer_id);
tipc_nametbl_publish(net, TIPC_LINK_STATE, addr, addr,
- TIPC_NODE_SCOPE, link_id, addr);
+ TIPC_NODE_SCOPE, link_id, link_id);
}
if (flags & TIPC_NOTIFY_LINK_DOWN) {
tipc_mon_peer_down(net, addr, bearer_id);
tipc_nametbl_withdraw(net, TIPC_LINK_STATE, addr,
- link_id, addr);
+ link_id, link_id);
}
}
diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h
index 8b2d22b..d793b43 100644
--- a/net/tipc/subscr.h
+++ b/net/tipc/subscr.h
@@ -40,7 +40,7 @@
#include "topsrv.h"
#define TIPC_MAX_SUBSCR 65535
-#define TIPC_MAX_PUBLICATIONS 65535
+#define TIPC_MAX_PUBL 65535
struct tipc_subscription;
struct tipc_conn;
@@ -58,7 +58,7 @@ struct tipc_subscription {
struct kref kref;
struct net *net;
struct timer_list timer;
- struct list_head nameseq_list;
+ struct list_head service_list;
struct list_head sub_list;
struct tipc_event evt;
int conid;
--
2.1.4
^ permalink raw reply related
* [net-next v2 0/5] tipc: slim down name table
From: Jon Maloy @ 2018-03-29 21:20 UTC (permalink / raw)
To: davem, netdev
Cc: mohan.krishna.ghanta.krishnamurthy, tung.q.nguyen, hoang.h.le,
jon.maloy, canh.d.luu, ying.xue, tipc-discussion
We clean up and improve the name binding table:
- Replace the memory consuming 'sub_sequence/service range' array with
an RB tree.
- Introduce support for overlapping service sequences/ranges
v2: #1: Fixed a missing initialization reported by David Miller
#4: Obsoleted and replaced a few more macros to get a consistent
terminology in the API.
#5: Added new commit to fix a potential string overflow bug (it
is still only in net-next) reported by Arnd Bergmann
Jon Maloy (5):
tipc: replace name table service range array with rb tree
tipc: refactor name table translate function
tipc: permit overlapping service ranges in name table
tipc: tipc: rename address types in user api
tipc: avoid possible string overflow
include/uapi/linux/tipc.h | 59 +--
net/tipc/core.h | 1 +
net/tipc/link.c | 5 +-
net/tipc/name_distr.c | 90 +---
net/tipc/name_distr.h | 1 -
net/tipc/name_table.c | 1075 ++++++++++++++++++++-------------------------
net/tipc/name_table.h | 10 +-
net/tipc/net.c | 2 +-
net/tipc/node.c | 4 +-
net/tipc/socket.c | 4 +-
net/tipc/subscr.h | 4 +-
11 files changed, 556 insertions(+), 699 deletions(-)
--
2.1.4
^ permalink raw reply
* [net-next v2 5/5] tipc: avoid possible string overflow
From: Jon Maloy @ 2018-03-29 21:20 UTC (permalink / raw)
To: davem, netdev; +Cc: tipc-discussion, mohan.krishna.ghanta.krishnamurthy
In-Reply-To: <1522358445-7444-1-git-send-email-jon.maloy@ericsson.com>
gcc points out that the combined length of the fixed-length inputs to
l->name is larger than the destination buffer size:
net/tipc/link.c: In function 'tipc_link_create':
net/tipc/link.c:465:26: error: '%s' directive writing up to 32 bytes
into a region of size between 26 and 58 [-Werror=format-overflow=]
sprintf(l->name, "%s:%s-%s:unknown", self_str, if_name, peer_str);
net/tipc/link.c:465:2: note: 'sprintf' output 11 or more bytes
(assuming 75) into a destination of size 60
sprintf(l->name, "%s:%s-%s:unknown", self_str, if_name, peer_str);
A detailed analysis reveals that the theoretical maximum length of
a link name is:
max self_str + 1 + max if_name + 1 + max peer_str + 1 + max if_name =
16 + 1 + 15 + 1 + 16 + 1 + 15 = 65
Since we also need space for a trailing zero we now set MAX_LINK_NAME
to 68.
Just to be on the safe side we also replace the sprintf() call with
snprintf().
Fixes: 25b0b9c4e835 ("tipc: handle collisions of 32-bit node address
hash values")
Reported-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
---
include/uapi/linux/tipc.h | 2 +-
net/tipc/link.c | 3 ++-
2 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/include/uapi/linux/tipc.h b/include/uapi/linux/tipc.h
index 156224a..bf6d286 100644
--- a/include/uapi/linux/tipc.h
+++ b/include/uapi/linux/tipc.h
@@ -216,7 +216,7 @@ struct tipc_group_req {
#define TIPC_MAX_MEDIA_NAME 16
#define TIPC_MAX_IF_NAME 16
#define TIPC_MAX_BEARER_NAME 32
-#define TIPC_MAX_LINK_NAME 60
+#define TIPC_MAX_LINK_NAME 68
#define SIOCGETLINKNAME SIOCPROTOPRIVATE
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 8f2a949..695acb7 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -462,7 +462,8 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id,
sprintf(peer_str, "%x", peer);
}
/* Peer i/f name will be completed by reset/activate message */
- sprintf(l->name, "%s:%s-%s:unknown", self_str, if_name, peer_str);
+ snprintf(l->name, sizeof(l->name), "%s:%s-%s:unknown",
+ self_str, if_name, peer_str);
strcpy(l->if_name, if_name);
l->addr = peer;
--
2.1.4
------------------------------------------------------------------------------
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot
^ permalink raw reply related
* [net-next v2 3/5] tipc: permit overlapping service ranges in name table
From: Jon Maloy @ 2018-03-29 21:20 UTC (permalink / raw)
To: davem, netdev; +Cc: tipc-discussion, mohan.krishna.ghanta.krishnamurthy
In-Reply-To: <1522358445-7444-1-git-send-email-jon.maloy@ericsson.com>
With the new RB tree structure for service ranges it becomes possible to
solve an old problem; - we can now allow overlapping service ranges in
the table.
When inserting a new service range to the tree, we use 'lower' as primary
key, and when necessary 'upper' as secondary key.
Since there may now be multiple service ranges matching an indicated
'lower' value, we must also add the 'upper' value to the functions
used for removing publications, so that the correct, corresponding
range item can be found.
These changes guarantee that a well-formed publication/withdrawal item
from a peer node never will be rejected, and make it possible to
eliminate the problematic backlog functionality we currently have for
handling such cases.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
---
net/tipc/name_distr.c | 90 +++++++++++++--------------------------------------
net/tipc/name_distr.h | 1 -
net/tipc/name_table.c | 64 +++++++++++++++++-------------------
net/tipc/name_table.h | 8 ++---
net/tipc/net.c | 2 +-
net/tipc/node.c | 2 +-
net/tipc/socket.c | 4 +--
7 files changed, 60 insertions(+), 111 deletions(-)
diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c
index 8240a85..51b4b96 100644
--- a/net/tipc/name_distr.c
+++ b/net/tipc/name_distr.c
@@ -204,12 +204,12 @@ void tipc_named_node_up(struct net *net, u32 dnode)
*/
static void tipc_publ_purge(struct net *net, struct publication *publ, u32 addr)
{
- struct tipc_net *tn = net_generic(net, tipc_net_id);
+ struct tipc_net *tn = tipc_net(net);
struct publication *p;
spin_lock_bh(&tn->nametbl_lock);
- p = tipc_nametbl_remove_publ(net, publ->type, publ->lower,
- publ->node, publ->port, publ->key);
+ p = tipc_nametbl_remove_publ(net, publ->type, publ->lower, publ->upper,
+ publ->node, publ->key);
if (p)
tipc_node_unsubscribe(net, &p->binding_node, addr);
spin_unlock_bh(&tn->nametbl_lock);
@@ -261,28 +261,31 @@ void tipc_publ_notify(struct net *net, struct list_head *nsub_list, u32 addr)
static bool tipc_update_nametbl(struct net *net, struct distr_item *i,
u32 node, u32 dtype)
{
- struct publication *publ = NULL;
+ struct publication *p = NULL;
+ u32 lower = ntohl(i->lower);
+ u32 upper = ntohl(i->upper);
+ u32 type = ntohl(i->type);
+ u32 port = ntohl(i->port);
+ u32 key = ntohl(i->key);
if (dtype == PUBLICATION) {
- publ = tipc_nametbl_insert_publ(net, ntohl(i->type),
- ntohl(i->lower),
- ntohl(i->upper),
- TIPC_CLUSTER_SCOPE, node,
- ntohl(i->port), ntohl(i->key));
- if (publ) {
- tipc_node_subscribe(net, &publ->binding_node, node);
+ p = tipc_nametbl_insert_publ(net, type, lower, upper,
+ TIPC_CLUSTER_SCOPE, node,
+ port, key);
+ if (p) {
+ tipc_node_subscribe(net, &p->binding_node, node);
return true;
}
} else if (dtype == WITHDRAWAL) {
- publ = tipc_nametbl_remove_publ(net, ntohl(i->type),
- ntohl(i->lower),
- node, ntohl(i->port),
- ntohl(i->key));
- if (publ) {
- tipc_node_unsubscribe(net, &publ->binding_node, node);
- kfree_rcu(publ, rcu);
+ p = tipc_nametbl_remove_publ(net, type, lower,
+ upper, node, key);
+ if (p) {
+ tipc_node_unsubscribe(net, &p->binding_node, node);
+ kfree_rcu(p, rcu);
return true;
}
+ pr_warn_ratelimited("Failed to remove binding %u,%u from %x\n",
+ type, lower, node);
} else {
pr_warn("Unrecognized name table message received\n");
}
@@ -290,53 +293,6 @@ static bool tipc_update_nametbl(struct net *net, struct distr_item *i,
}
/**
- * tipc_named_add_backlog - add a failed name table update to the backlog
- *
- */
-static void tipc_named_add_backlog(struct net *net, struct distr_item *i,
- u32 type, u32 node)
-{
- struct distr_queue_item *e;
- struct tipc_net *tn = net_generic(net, tipc_net_id);
- unsigned long now = get_jiffies_64();
-
- e = kzalloc(sizeof(*e), GFP_ATOMIC);
- if (!e)
- return;
- e->dtype = type;
- e->node = node;
- e->expires = now + msecs_to_jiffies(sysctl_tipc_named_timeout);
- memcpy(e, i, sizeof(*i));
- list_add_tail(&e->next, &tn->dist_queue);
-}
-
-/**
- * tipc_named_process_backlog - try to process any pending name table updates
- * from the network.
- */
-void tipc_named_process_backlog(struct net *net)
-{
- struct distr_queue_item *e, *tmp;
- struct tipc_net *tn = net_generic(net, tipc_net_id);
- unsigned long now = get_jiffies_64();
-
- list_for_each_entry_safe(e, tmp, &tn->dist_queue, next) {
- if (time_after(e->expires, now)) {
- if (!tipc_update_nametbl(net, &e->i, e->node, e->dtype))
- continue;
- } else {
- pr_warn_ratelimited("Dropping name table update (%d) of {%u, %u, %u} from %x key=%u\n",
- e->dtype, ntohl(e->i.type),
- ntohl(e->i.lower),
- ntohl(e->i.upper),
- e->node, ntohl(e->i.key));
- }
- list_del(&e->next);
- kfree(e);
- }
-}
-
-/**
* tipc_named_rcv - process name table update messages sent by another node
*/
void tipc_named_rcv(struct net *net, struct sk_buff_head *inputq)
@@ -358,12 +314,10 @@ void tipc_named_rcv(struct net *net, struct sk_buff_head *inputq)
count = msg_data_sz(msg) / ITEM_SIZE;
node = msg_orignode(msg);
while (count--) {
- if (!tipc_update_nametbl(net, item, node, mtype))
- tipc_named_add_backlog(net, item, mtype, node);
+ tipc_update_nametbl(net, item, node, mtype);
item++;
}
kfree_skb(skb);
- tipc_named_process_backlog(net);
}
spin_unlock_bh(&tn->nametbl_lock);
}
diff --git a/net/tipc/name_distr.h b/net/tipc/name_distr.h
index 4753e62..63fc73e 100644
--- a/net/tipc/name_distr.h
+++ b/net/tipc/name_distr.h
@@ -72,7 +72,6 @@ struct sk_buff *tipc_named_withdraw(struct net *net, struct publication *publ);
void tipc_named_node_up(struct net *net, u32 dnode);
void tipc_named_rcv(struct net *net, struct sk_buff_head *msg_queue);
void tipc_named_reinit(struct net *net);
-void tipc_named_process_backlog(struct net *net);
void tipc_publ_notify(struct net *net, struct list_head *nsub_list, u32 addr);
#endif
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index 4bdc580..b1fe209 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -171,10 +171,14 @@ static struct service_range *tipc_service_create_range(struct tipc_service *sc,
tmp = container_of(parent, struct service_range, tree_node);
if (lower < tmp->lower)
n = &(*n)->rb_left;
+ else if (lower > tmp->lower)
+ n = &(*n)->rb_right;
+ else if (upper < tmp->upper)
+ n = &(*n)->rb_left;
else if (upper > tmp->upper)
n = &(*n)->rb_right;
else
- return NULL;
+ return tmp;
}
sr = kzalloc(sizeof(*sr), GFP_ATOMIC);
if (!sr)
@@ -200,17 +204,11 @@ static struct publication *tipc_service_insert_publ(struct net *net,
struct publication *p;
bool first = false;
- sr = tipc_service_find_range(sc, lower);
- if (!sr) {
- sr = tipc_service_create_range(sc, lower, upper);
- if (!sr)
- goto err;
- first = true;
- }
+ sr = tipc_service_create_range(sc, lower, upper);
+ if (!sr)
+ goto err;
- /* Lower end overlaps existing entry, but we need an exact match */
- if (sr->lower != lower || sr->upper != upper)
- return NULL;
+ first = list_empty(&sr->all_publ);
/* Return if the publication already exists */
list_for_each_entry(p, &sr->all_publ, all_publ) {
@@ -239,30 +237,32 @@ static struct publication *tipc_service_insert_publ(struct net *net,
/**
* tipc_service_remove_publ - remove a publication from a service
- *
- * NOTE: There may be cases where TIPC is asked to remove a publication
- * that is not in the name table. For example, if another node issues a
- * publication for a name range that overlaps an existing name range
- * the publication will not be recorded, which means the publication won't
- * be found when the name range is later withdrawn by that node.
- * A failed withdraw request simply returns a failure indication and lets the
- * caller issue any error or warning messages associated with such a problem.
*/
static struct publication *tipc_service_remove_publ(struct net *net,
struct tipc_service *sc,
- u32 inst, u32 node,
- u32 port, u32 key)
+ u32 lower, u32 upper,
+ u32 node, u32 key)
{
struct tipc_subscription *sub, *tmp;
struct service_range *sr;
struct publication *p;
bool found = false;
bool last = false;
+ struct rb_node *n;
- sr = tipc_service_find_range(sc, inst);
+ sr = tipc_service_find_range(sc, lower);
if (!sr)
return NULL;
+ /* Find exact matching service range */
+ for (n = &sr->tree_node; n; n = rb_next(n)) {
+ sr = container_of(n, struct service_range, tree_node);
+ if (sr->upper == upper)
+ break;
+ }
+ if (!n || sr->lower != lower || sr->upper != upper)
+ return NULL;
+
/* Find publication, if it exists */
list_for_each_entry(p, &sr->all_publ, all_publ) {
if (p->key != key || (node && node != p->node))
@@ -375,8 +375,8 @@ struct publication *tipc_nametbl_insert_publ(struct net *net, u32 type,
}
struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type,
- u32 lower, u32 node, u32 port,
- u32 key)
+ u32 lower, u32 upper,
+ u32 node, u32 key)
{
struct tipc_service *sc = tipc_service_find(net, type);
struct publication *p = NULL;
@@ -385,7 +385,7 @@ struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type,
return NULL;
spin_lock_bh(&sc->lock);
- p = tipc_service_remove_publ(net, sc, lower, node, port, key);
+ p = tipc_service_remove_publ(net, sc, lower, upper, node, key);
/* Delete service item if this no more publications and subscriptions */
if (RB_EMPTY_ROOT(&sc->ranges) && list_empty(&sc->subscriptions)) {
@@ -620,8 +620,6 @@ struct publication *tipc_nametbl_publish(struct net *net, u32 type, u32 lower,
if (p) {
nt->local_publ_count++;
skb = tipc_named_publish(net, p);
- /* Any pending external events? */
- tipc_named_process_backlog(net);
}
exit:
spin_unlock_bh(&tn->nametbl_lock);
@@ -635,7 +633,7 @@ struct publication *tipc_nametbl_publish(struct net *net, u32 type, u32 lower,
* tipc_nametbl_withdraw - withdraw a service binding
*/
int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower,
- u32 port, u32 key)
+ u32 upper, u32 key)
{
struct name_table *nt = tipc_name_table(net);
struct tipc_net *tn = tipc_net(net);
@@ -645,17 +643,15 @@ int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower,
spin_lock_bh(&tn->nametbl_lock);
- p = tipc_nametbl_remove_publ(net, type, lower, self, port, key);
+ p = tipc_nametbl_remove_publ(net, type, lower, upper, self, key);
if (p) {
nt->local_publ_count--;
skb = tipc_named_withdraw(net, p);
- /* Any pending external events? */
- tipc_named_process_backlog(net);
list_del_init(&p->binding_sock);
kfree_rcu(p, rcu);
} else {
pr_err("Failed to remove local publication {%u,%u,%u}/%u\n",
- type, lower, port, key);
+ type, lower, upper, key);
}
spin_unlock_bh(&tn->nametbl_lock);
@@ -754,8 +750,8 @@ static void tipc_service_delete(struct net *net, struct tipc_service *sc)
rbtree_postorder_for_each_entry_safe(sr, tmpr, &sc->ranges, tree_node) {
list_for_each_entry_safe(p, tmpb,
&sr->all_publ, all_publ) {
- tipc_service_remove_publ(net, sc, p->lower, p->node,
- p->port, p->key);
+ tipc_service_remove_publ(net, sc, p->lower, p->upper,
+ p->node, p->key);
kfree_rcu(p, rcu);
}
}
diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h
index 1b03b87..4b14fc2 100644
--- a/net/tipc/name_table.h
+++ b/net/tipc/name_table.h
@@ -116,16 +116,16 @@ bool tipc_nametbl_lookup(struct net *net, u32 type, u32 instance, u32 domain,
struct list_head *dsts, int *dstcnt, u32 exclude,
bool all);
struct publication *tipc_nametbl_publish(struct net *net, u32 type, u32 lower,
- u32 upper, u32 scope, u32 port_ref,
+ u32 upper, u32 scope, u32 port,
u32 key);
-int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower, u32 ref,
+int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower, u32 upper,
u32 key);
struct publication *tipc_nametbl_insert_publ(struct net *net, u32 type,
u32 lower, u32 upper, u32 scope,
u32 node, u32 ref, u32 key);
struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type,
- u32 lower, u32 node, u32 ref,
- u32 key);
+ u32 lower, u32 upper,
+ u32 node, u32 key);
void tipc_nametbl_subscribe(struct tipc_subscription *s);
void tipc_nametbl_unsubscribe(struct tipc_subscription *s);
int tipc_nametbl_init(struct net *net);
diff --git a/net/tipc/net.c b/net/tipc/net.c
index 29538dc..856f9e9 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -136,7 +136,7 @@ void tipc_net_stop(struct net *net)
if (!self)
return;
- tipc_nametbl_withdraw(net, TIPC_CFG_SRV, self, 0, self);
+ tipc_nametbl_withdraw(net, TIPC_CFG_SRV, self, self, self);
rtnl_lock();
tipc_bearer_stop(net);
tipc_node_stop(net);
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 85e777e..c77dd2f 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -329,7 +329,7 @@ static void tipc_node_write_unlock(struct tipc_node *n)
if (flags & TIPC_NOTIFY_LINK_DOWN) {
tipc_mon_peer_down(net, addr, bearer_id);
tipc_nametbl_withdraw(net, TIPC_LINK_STATE, addr,
- link_id, link_id);
+ addr, link_id);
}
}
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 275b666..3e5eba3 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2634,12 +2634,12 @@ static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope,
if (publ->upper != seq->upper)
break;
tipc_nametbl_withdraw(net, publ->type, publ->lower,
- publ->port, publ->key);
+ publ->upper, publ->key);
rc = 0;
break;
}
tipc_nametbl_withdraw(net, publ->type, publ->lower,
- publ->port, publ->key);
+ publ->upper, publ->key);
rc = 0;
}
if (list_empty(&tsk->publications))
--
2.1.4
------------------------------------------------------------------------------
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot
^ permalink raw reply related
* [net-next v2 2/5] tipc: refactor name table translate function
From: Jon Maloy @ 2018-03-29 21:20 UTC (permalink / raw)
To: davem, netdev; +Cc: tipc-discussion, mohan.krishna.ghanta.krishnamurthy
In-Reply-To: <1522358445-7444-1-git-send-email-jon.maloy@ericsson.com>
The function tipc_nametbl_translate() function is ugly and hard to
follow. This can be improved somewhat by introducing a stack variable
for holding the publication list to be used and re-ordering the if-
clauses for selection of algorithm.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
---
net/tipc/name_table.c | 61 +++++++++++++++++++++------------------------------
1 file changed, 25 insertions(+), 36 deletions(-)
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index e06c7a8..4bdc580 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -399,29 +399,32 @@ struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type,
/**
* tipc_nametbl_translate - perform service instance to socket translation
*
- * On entry, 'destnode' is the search domain used during translation.
+ * On entry, 'dnode' is the search domain used during translation.
*
* On exit:
- * - if name translation is deferred to another node/cluster/zone,
- * leaves 'destnode' unchanged (will be non-zero) and returns 0
- * - if name translation is attempted and succeeds, sets 'destnode'
- * to publication node and returns port reference (will be non-zero)
- * - if name translation is attempted and fails, sets 'destnode' to 0
- * and returns 0
+ * - if translation is deferred to another node, leave 'dnode' unchanged and
+ * return 0
+ * - if translation is attempted and succeeds, set 'dnode' to the publishing
+ * node and return the published (non-zero) port number
+ * - if translation is attempted and fails, set 'dnode' to 0 and return 0
+ *
+ * Note that for legacy users (node configured with Z.C.N address format) the
+ * 'closest-first' lookup algorithm must be maintained, i.e., if dnode is 0
+ * we must look in the local binding list first
*/
-u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance,
- u32 *destnode)
+u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance, u32 *dnode)
{
struct tipc_net *tn = tipc_net(net);
bool legacy = tn->legacy_addr_format;
u32 self = tipc_own_addr(net);
struct service_range *sr;
struct tipc_service *sc;
+ struct list_head *list;
struct publication *p;
u32 port = 0;
u32 node = 0;
- if (!tipc_in_scope(legacy, *destnode, self))
+ if (!tipc_in_scope(legacy, *dnode, self))
return 0;
rcu_read_lock();
@@ -434,43 +437,29 @@ u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance,
if (unlikely(!sr))
goto no_match;
- /* Closest-First Algorithm */
- if (legacy && !*destnode) {
- if (!list_empty(&sr->local_publ)) {
- p = list_first_entry(&sr->local_publ,
- struct publication,
- local_publ);
- list_move_tail(&p->local_publ,
- &sr->local_publ);
- } else {
- p = list_first_entry(&sr->all_publ,
- struct publication,
- all_publ);
- list_move_tail(&p->all_publ,
- &sr->all_publ);
- }
- }
-
- /* Round-Robin Algorithm */
- else if (*destnode == self) {
- if (list_empty(&sr->local_publ))
+ /* Select lookup algorithm: local, closest-first or round-robin */
+ if (*dnode == self) {
+ list = &sr->local_publ;
+ if (list_empty(list))
goto no_match;
- p = list_first_entry(&sr->local_publ, struct publication,
- local_publ);
+ p = list_first_entry(list, struct publication, local_publ);
+ list_move_tail(&p->local_publ, &sr->local_publ);
+ } else if (legacy && !*dnode && !list_empty(&sr->local_publ)) {
+ list = &sr->local_publ;
+ p = list_first_entry(list, struct publication, local_publ);
list_move_tail(&p->local_publ, &sr->local_publ);
} else {
- p = list_first_entry(&sr->all_publ, struct publication,
- all_publ);
+ list = &sr->all_publ;
+ p = list_first_entry(list, struct publication, all_publ);
list_move_tail(&p->all_publ, &sr->all_publ);
}
-
port = p->port;
node = p->node;
no_match:
spin_unlock_bh(&sc->lock);
not_found:
rcu_read_unlock();
- *destnode = node;
+ *dnode = node;
return port;
}
--
2.1.4
------------------------------------------------------------------------------
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox