summaryrefslogtreecommitdiff
path: root/kernel/bpf/cgroup.c
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2019-12-27 14:20:10 -0800
committerDavid S. Miller <davem@davemloft.net>2019-12-27 14:20:10 -0800
commit2bbc078f812d45b8decb55935dab21199bd21489 (patch)
treeb217e030e0f80a26561cef679e8ae2643162b346 /kernel/bpf/cgroup.c
parent9e41fbf3dd38327d440a8f3ba0c234519dbb5280 (diff)
parent7c8dce4b166113743adad131b5a24c4acc12f92c (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Daniel Borkmann says: ==================== pull-request: bpf-next 2019-12-27 The following pull-request contains BPF updates for your *net-next* tree. We've added 127 non-merge commits during the last 17 day(s) which contain a total of 110 files changed, 6901 insertions(+), 2721 deletions(-). There are three merge conflicts. Conflicts and resolution looks as follows: 1) Merge conflict in net/bpf/test_run.c: There was a tree-wide cleanup c593642c8be0 ("treewide: Use sizeof_field() macro") which gets in the way with b590cb5f802d ("bpf: Switch to offsetofend in BPF_PROG_TEST_RUN"): <<<<<<< HEAD if (!range_is_zero(__skb, offsetof(struct __sk_buff, priority) + sizeof_field(struct __sk_buff, priority), ======= if (!range_is_zero(__skb, offsetofend(struct __sk_buff, priority), >>>>>>> 7c8dce4b166113743adad131b5a24c4acc12f92c There are a few occasions that look similar to this. Always take the chunk with offsetofend(). Note that there is one where the fields differ in here: <<<<<<< HEAD if (!range_is_zero(__skb, offsetof(struct __sk_buff, tstamp) + sizeof_field(struct __sk_buff, tstamp), ======= if (!range_is_zero(__skb, offsetofend(struct __sk_buff, gso_segs), >>>>>>> 7c8dce4b166113743adad131b5a24c4acc12f92c Just take the one with offsetofend() /and/ gso_segs. Latter is correct due to 850a88cc4096 ("bpf: Expose __sk_buff wire_len/gso_segs to BPF_PROG_TEST_RUN"). 2) Merge conflict in arch/riscv/net/bpf_jit_comp.c: (I'm keeping Bjorn in Cc here for a double-check in case I got it wrong.) <<<<<<< HEAD if (is_13b_check(off, insn)) return -1; emit(rv_blt(tcc, RV_REG_ZERO, off >> 1), ctx); ======= emit_branch(BPF_JSLT, RV_REG_T1, RV_REG_ZERO, off, ctx); >>>>>>> 7c8dce4b166113743adad131b5a24c4acc12f92c Result should look like: emit_branch(BPF_JSLT, tcc, RV_REG_ZERO, off, ctx); 3) Merge conflict in arch/riscv/include/asm/pgtable.h: <<<<<<< HEAD ======= #define VMALLOC_SIZE (KERN_VIRT_SIZE >> 1) #define VMALLOC_END (PAGE_OFFSET - 1) #define VMALLOC_START (PAGE_OFFSET - VMALLOC_SIZE) #define BPF_JIT_REGION_SIZE (SZ_128M) #define BPF_JIT_REGION_START (PAGE_OFFSET - BPF_JIT_REGION_SIZE) #define BPF_JIT_REGION_END (VMALLOC_END) /* * Roughly size the vmemmap space to be large enough to fit enough * struct pages to map half the virtual address space. Then * position vmemmap directly below the VMALLOC region. */ #define VMEMMAP_SHIFT \ (CONFIG_VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT) #define VMEMMAP_SIZE BIT(VMEMMAP_SHIFT) #define VMEMMAP_END (VMALLOC_START - 1) #define VMEMMAP_START (VMALLOC_START - VMEMMAP_SIZE) #define vmemmap ((struct page *)VMEMMAP_START) >>>>>>> 7c8dce4b166113743adad131b5a24c4acc12f92c Only take the BPF_* defines from there and move them higher up in the same file. Remove the rest from the chunk. The VMALLOC_* etc defines got moved via 01f52e16b868 ("riscv: define vmemmap before pfn_to_page calls"). Result: [...] #define __S101 PAGE_READ_EXEC #define __S110 PAGE_SHARED_EXEC #define __S111 PAGE_SHARED_EXEC #define VMALLOC_SIZE (KERN_VIRT_SIZE >> 1) #define VMALLOC_END (PAGE_OFFSET - 1) #define VMALLOC_START (PAGE_OFFSET - VMALLOC_SIZE) #define BPF_JIT_REGION_SIZE (SZ_128M) #define BPF_JIT_REGION_START (PAGE_OFFSET - BPF_JIT_REGION_SIZE) #define BPF_JIT_REGION_END (VMALLOC_END) /* * Roughly size the vmemmap space to be large enough to fit enough * struct pages to map half the virtual address space. Then * position vmemmap directly below the VMALLOC region. */ #define VMEMMAP_SHIFT \ (CONFIG_VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT) #define VMEMMAP_SIZE BIT(VMEMMAP_SHIFT) #define VMEMMAP_END (VMALLOC_START - 1) #define VMEMMAP_START (VMALLOC_START - VMEMMAP_SIZE) [...] Let me know if there are any other issues. Anyway, the main changes are: 1) Extend bpftool to produce a struct (aka "skeleton") tailored and specific to a provided BPF object file. This provides an alternative, simplified API compared to standard libbpf interaction. Also, add libbpf extern variable resolution for .kconfig section to import Kconfig data, from Andrii Nakryiko. 2) Add BPF dispatcher for XDP which is a mechanism to avoid indirect calls by generating a branch funnel as discussed back in bpfconf'19 at LSF/MM. Also, add various BPF riscv JIT improvements, from Björn Töpel. 3) Extend bpftool to allow matching BPF programs and maps by name, from Paul Chaignon. 4) Support for replacing cgroup BPF programs attached with BPF_F_ALLOW_MULTI flag for allowing updates without service interruption, from Andrey Ignatov. 5) Cleanup and simplification of ring access functions for AF_XDP with a bonus of 0-5% performance improvement, from Magnus Karlsson. 6) Enable BPF JITs for x86-64 and arm64 by default. Also, final version of audit support for BPF, from Daniel Borkmann and latter with Jiri Olsa. 7) Move and extend test_select_reuseport into BPF program tests under BPF selftests, from Jakub Sitnicki. 8) Various BPF sample improvements for xdpsock for customizing parameters to set up and benchmark AF_XDP, from Jay Jayatheerthan. 9) Improve libbpf to provide a ulimit hint on permission denied errors. Also change XDP sample programs to attach in driver mode by default, from Toke Høiland-Jørgensen. 10) Extend BPF test infrastructure to allow changing skb mark from tc BPF programs, from Nikita V. Shirokov. 11) Optimize prologue code sequence in BPF arm32 JIT, from Russell King. 12) Fix xdp_redirect_cpu BPF sample to manually attach to tracepoints after libbpf conversion, from Jesper Dangaard Brouer. 13) Minor misc improvements from various others. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'kernel/bpf/cgroup.c')
-rw-r--r--kernel/bpf/cgroup.c97
1 files changed, 51 insertions, 46 deletions
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 4fb20ab179fe..ee871d4a51f7 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -103,8 +103,7 @@ static u32 prog_list_length(struct list_head *head)
* if parent has overridable or multi-prog, allow attaching
*/
static bool hierarchy_allows_attach(struct cgroup *cgrp,
- enum bpf_attach_type type,
- u32 new_flags)
+ enum bpf_attach_type type)
{
struct cgroup *p;
@@ -283,31 +282,34 @@ cleanup:
* propagate the change to descendants
* @cgrp: The cgroup which descendants to traverse
* @prog: A program to attach
+ * @replace_prog: Previously attached program to replace if BPF_F_REPLACE is set
* @type: Type of attach operation
* @flags: Option flags
*
* Must be called with cgroup_mutex held.
*/
int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
+ struct bpf_prog *replace_prog,
enum bpf_attach_type type, u32 flags)
{
+ u32 saved_flags = (flags & (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI));
struct list_head *progs = &cgrp->bpf.progs[type];
struct bpf_prog *old_prog = NULL;
struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE],
*old_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {NULL};
+ struct bpf_prog_list *pl, *replace_pl = NULL;
enum bpf_cgroup_storage_type stype;
- struct bpf_prog_list *pl;
- bool pl_was_allocated;
int err;
- if ((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI))
+ if (((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI)) ||
+ ((flags & BPF_F_REPLACE) && !(flags & BPF_F_ALLOW_MULTI)))
/* invalid combination */
return -EINVAL;
- if (!hierarchy_allows_attach(cgrp, type, flags))
+ if (!hierarchy_allows_attach(cgrp, type))
return -EPERM;
- if (!list_empty(progs) && cgrp->bpf.flags[type] != flags)
+ if (!list_empty(progs) && cgrp->bpf.flags[type] != saved_flags)
/* Disallow attaching non-overridable on top
* of existing overridable in this cgroup.
* Disallow attaching multi-prog if overridable or none
@@ -317,6 +319,21 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS)
return -E2BIG;
+ if (flags & BPF_F_ALLOW_MULTI) {
+ list_for_each_entry(pl, progs, node) {
+ if (pl->prog == prog)
+ /* disallow attaching the same prog twice */
+ return -EINVAL;
+ if (pl->prog == replace_prog)
+ replace_pl = pl;
+ }
+ if ((flags & BPF_F_REPLACE) && !replace_pl)
+ /* prog to replace not found for cgroup */
+ return -ENOENT;
+ } else if (!list_empty(progs)) {
+ replace_pl = list_first_entry(progs, typeof(*pl), node);
+ }
+
for_each_cgroup_storage_type(stype) {
storage[stype] = bpf_cgroup_storage_alloc(prog, stype);
if (IS_ERR(storage[stype])) {
@@ -327,53 +344,28 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
}
}
- if (flags & BPF_F_ALLOW_MULTI) {
- list_for_each_entry(pl, progs, node) {
- if (pl->prog == prog) {
- /* disallow attaching the same prog twice */
- for_each_cgroup_storage_type(stype)
- bpf_cgroup_storage_free(storage[stype]);
- return -EINVAL;
- }
+ if (replace_pl) {
+ pl = replace_pl;
+ old_prog = pl->prog;
+ for_each_cgroup_storage_type(stype) {
+ old_storage[stype] = pl->storage[stype];
+ bpf_cgroup_storage_unlink(old_storage[stype]);
}
-
+ } else {
pl = kmalloc(sizeof(*pl), GFP_KERNEL);
if (!pl) {
for_each_cgroup_storage_type(stype)
bpf_cgroup_storage_free(storage[stype]);
return -ENOMEM;
}
-
- pl_was_allocated = true;
- pl->prog = prog;
- for_each_cgroup_storage_type(stype)
- pl->storage[stype] = storage[stype];
list_add_tail(&pl->node, progs);
- } else {
- if (list_empty(progs)) {
- pl = kmalloc(sizeof(*pl), GFP_KERNEL);
- if (!pl) {
- for_each_cgroup_storage_type(stype)
- bpf_cgroup_storage_free(storage[stype]);
- return -ENOMEM;
- }
- pl_was_allocated = true;
- list_add_tail(&pl->node, progs);
- } else {
- pl = list_first_entry(progs, typeof(*pl), node);
- old_prog = pl->prog;
- for_each_cgroup_storage_type(stype) {
- old_storage[stype] = pl->storage[stype];
- bpf_cgroup_storage_unlink(old_storage[stype]);
- }
- pl_was_allocated = false;
- }
- pl->prog = prog;
- for_each_cgroup_storage_type(stype)
- pl->storage[stype] = storage[stype];
}
- cgrp->bpf.flags[type] = flags;
+ pl->prog = prog;
+ for_each_cgroup_storage_type(stype)
+ pl->storage[stype] = storage[stype];
+
+ cgrp->bpf.flags[type] = saved_flags;
err = update_effective_progs(cgrp, type);
if (err)
@@ -401,7 +393,7 @@ cleanup:
pl->storage[stype] = old_storage[stype];
bpf_cgroup_storage_link(old_storage[stype], cgrp, type);
}
- if (pl_was_allocated) {
+ if (!replace_pl) {
list_del(&pl->node);
kfree(pl);
}
@@ -539,6 +531,7 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
int cgroup_bpf_prog_attach(const union bpf_attr *attr,
enum bpf_prog_type ptype, struct bpf_prog *prog)
{
+ struct bpf_prog *replace_prog = NULL;
struct cgroup *cgrp;
int ret;
@@ -546,8 +539,20 @@ int cgroup_bpf_prog_attach(const union bpf_attr *attr,
if (IS_ERR(cgrp))
return PTR_ERR(cgrp);
- ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
+ if ((attr->attach_flags & BPF_F_ALLOW_MULTI) &&
+ (attr->attach_flags & BPF_F_REPLACE)) {
+ replace_prog = bpf_prog_get_type(attr->replace_bpf_fd, ptype);
+ if (IS_ERR(replace_prog)) {
+ cgroup_put(cgrp);
+ return PTR_ERR(replace_prog);
+ }
+ }
+
+ ret = cgroup_bpf_attach(cgrp, prog, replace_prog, attr->attach_type,
attr->attach_flags);
+
+ if (replace_prog)
+ bpf_prog_put(replace_prog);
cgroup_put(cgrp);
return ret;
}