Expose bpf_jit_current as a read only value via sysctl.
Signed-off-by: Lorenz Bauer <[email protected]>
---
Documentation/admin-guide/sysctl/net.rst | 6 ++++++
include/linux/filter.h | 1 +
kernel/bpf/core.c | 3 +--
net/core/sysctl_net_core.c | 24 ++++++++++++++++++++++++
4 files changed, 32 insertions(+), 2 deletions(-)
diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst
index 4150f74c521a..524e7db8d53f 100644
--- a/Documentation/admin-guide/sysctl/net.rst
+++ b/Documentation/admin-guide/sysctl/net.rst
@@ -123,6 +123,12 @@ compiler in order to reject unprivileged JIT requests once it has
been surpassed. bpf_jit_limit contains the value of the global limit
in bytes.
+bpf_jit_current
+---------------
+
+The amount of JIT memory currently allocated, in bytes. JITing of
+unprivileged BPF is rejected if this value is above bpf_jit_limit.
+
dev_weight
----------
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 8231a6a257f6..42c543a21cd8 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1051,6 +1051,7 @@ extern int bpf_jit_harden;
extern int bpf_jit_kallsyms;
extern long bpf_jit_limit;
extern long bpf_jit_limit_max;
+extern atomic_long_t bpf_jit_current;
typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index ab84b3816339..12aedab09222 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -526,6 +526,7 @@ int bpf_jit_kallsyms __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON);
int bpf_jit_harden __read_mostly;
long bpf_jit_limit __read_mostly;
long bpf_jit_limit_max __read_mostly;
+atomic_long_t bpf_jit_current __read_mostly;
static void
bpf_prog_ksym_set_addr(struct bpf_prog *prog)
@@ -801,8 +802,6 @@ int bpf_jit_add_poke_descriptor(struct bpf_prog *prog,
return slot;
}
-static atomic_long_t bpf_jit_current;
-
/* Can be overridden by an arch's JIT compiler if it has a custom,
* dedicated BPF backend memory area, or if neither of the two
* below apply.
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 5f88526ad61c..78603f561482 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -15,6 +15,7 @@
#include <linux/vmalloc.h>
#include <linux/init.h>
#include <linux/slab.h>
+#include <linux/atomic.h>
#include <net/ip.h>
#include <net/sock.h>
@@ -307,6 +308,22 @@ proc_dolongvec_minmax_bpf_restricted(struct ctl_table *table, int write,
return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
}
+
+static int proc_bpf_jit_current(struct ctl_table *table, int write,
+ void *buffer, size_t *lenp, loff_t *ppos)
+{
+ long curr = atomic_long_read(&bpf_jit_current) << PAGE_SHIFT;
+ struct ctl_table ctl_entry = {
+ .data = &curr,
+ .maxlen = sizeof(long),
+ };
+
+
+ if (!capable(CAP_SYS_ADMIN) || write)
+ return -EPERM;
+
+ return proc_doulongvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
+}
#endif
static struct ctl_table net_core_table[] = {
@@ -421,6 +438,13 @@ static struct ctl_table net_core_table[] = {
.extra1 = &long_one,
.extra2 = &bpf_jit_limit_max,
},
+ {
+ .procname = "bpf_jit_current",
+ .data = &bpf_jit_current,
+ .maxlen = sizeof(long),
+ .mode = 0400,
+ .proc_handler = proc_bpf_jit_current,
+ },
#endif
{
.procname = "netdev_tstamp_prequeue",
--
2.30.2
Le 12/10/2021 à 15:59, Lorenz Bauer a écrit :
> Expose bpf_jit_current as a read only value via sysctl.
>
> Signed-off-by: Lorenz Bauer <[email protected]>
> ---
[snip]
> + {
> + .procname = "bpf_jit_current",
> + .data = &bpf_jit_current,
> + .maxlen = sizeof(long),
> + .mode = 0400,
Why not 0444 ?
Regards,
Nicolas
On Tue, 12 Oct 2021 at 17:29, Nicolas Dichtel <[email protected]> wrote:
>
> Le 12/10/2021 à 15:59, Lorenz Bauer a écrit :
> > Expose bpf_jit_current as a read only value via sysctl.
> >
> > Signed-off-by: Lorenz Bauer <[email protected]>
> > ---
>
> [snip]
>
> > + {
> > + .procname = "bpf_jit_current",
> > + .data = &bpf_jit_current,
> > + .maxlen = sizeof(long),
> > + .mode = 0400,
> Why not 0444 ?
This mirrors what the other BPF related sysctls do, which only allow
access from root with CAP_SYS_ADMIN. I'd prefer 0444 as well, but
Daniel explicitly locked down these sysctls in
2e4a30983b0f9b19b59e38bbf7427d7fdd480d98.
Lorenz
--
Lorenz Bauer | Systems Engineer
6th Floor, County Hall/The Riverside Building, SE1 7PB, UK
http://www.cloudflare.com
Le 13/10/2021 à 10:35, Lorenz Bauer a écrit :
> On Tue, 12 Oct 2021 at 17:29, Nicolas Dichtel <[email protected]> wrote:
>>
>> Le 12/10/2021 à 15:59, Lorenz Bauer a écrit :
>>> Expose bpf_jit_current as a read only value via sysctl.
>>>
>>> Signed-off-by: Lorenz Bauer <[email protected]>
>>> ---
>>
>> [snip]
>>
>>> + {
>>> + .procname = "bpf_jit_current",
>>> + .data = &bpf_jit_current,
>>> + .maxlen = sizeof(long),
>>> + .mode = 0400,
>> Why not 0444 ?
>
> This mirrors what the other BPF related sysctls do, which only allow
> access from root with CAP_SYS_ADMIN. I'd prefer 0444 as well, but
> Daniel explicitly locked down these sysctls in
> 2e4a30983b0f9b19b59e38bbf7427d7fdd480d98.
Even after this patch, bpf_jit_enable is 0644.
In fact, if you have CAP_BPF or CAP_SYS_ADMIN, this value has no impact for your
programs. But I you don't have one of these capabilities, it may be rejected,
but you cannot read these values, which help to understand why.
Regards,
Nicolas