bpftool: Compute map size of light skeletons at runtime
PATCH v2 1/1 bpftool: Compute map size of light skeletons at runtime
bpftool rounds memory-mapped data map sizes to the host page size when generating a light skeleton. The generated code therefore uses a 64K mapping size when bpftool runs on a 64K-page host, even if the skeleton runs on a 4K-page target. The target rejects the oversized map mmap(), causing failure of loading the light skeleton.
When try to run 64K-page selftests on 4K-page VM, the error message does not provide the reason about page size.
test_atomics:PASS:atomics skeleton open 0 nsec test_atomics:FAIL:atomics skeleton load unexpected error: -12 (errno 22)
#15 atomics:FAIL
Pass the original map value size and max entries to the generated code and round mmap size to the runtime page size in the user-space light skeleton helpers. This keeps generated light skeletons independent of the build host page size.
---
v1 -> v2:
* Pass max entries alongside value size.
* Use the computed mmap size for mprotect() in userspace's skel_protect_map_data().
* Round up the mmap size to page size with keeping the original multiplying max_entries logic. (Andrii)
* v1: https://lore.kernel.org/bpf/[email protected]/
--- tools/bpf/bpftool/gen.c | 26 +++++++-------------- tools/lib/bpf/skel_internal.h | 43 +++++++++++++++++++++++------------ 2 files changed, 37 insertions(+), 32 deletions(-)
tools/bpf/bpftool/gen.c +8 -18
@@ -500,16 +500,6 @@ static void print_hex(const char *data, int data_sz) } } -static size_t bpf_map_mmap_sz (const struct bpf_map *map) -{ -long page_sz =sysconf (_SC_PAGE_SIZE); -size_t map_sz; - - map_sz = (size_t )roundup (bpf_map__value_size (map),8 ) *bpf_map__max_entries (map); - map_sz =roundup (map_sz, page_sz); -return map_sz; -} -/* Emit type size asserts for all top-level fields in memory-mapped internal maps. */ static void codegen_asserts (struct bpf_object *obj,const char *obj_name) {
@@ -686,8 +676,8 @@ static void codegen_destroy(struct bpf_object *obj, const char *obj_name)if (!get_map_ident (map, ident,sizeof (ident)))continue ;if (is_skel_data (map, ident,sizeof (ident))) -printf ("\tskel_free_map_data(skel->%1$s, skel->maps.%1$s.initial_value, %2$zu);\n" , - ident,bpf_map_mmap_sz (map)); +printf ("\tskel_free_map_data(skel->%1$s, skel->maps.%1$s.initial_value, %2$u, %3$u);\n" , + ident,bpf_map__value_size (map),bpf_map__max_entries (map)); codegen("\ \n\ skel_closenz(skel->maps.%1$s.map_fd); \n\
@@ -771,13 +761,13 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h \n\ \"; \n\\n\ -skel->%1$s = (__typeof__(skel->%1$s))skel_prep_map_data((void *)data, %2$zd,\n\ +skel->%1$s = (__typeof__(skel->%1$s))skel_prep_map_data((void *)data, %2$u, %3$u,\n\ sizeof(data) - 1);\n\ if (!skel->%1$s) \n\ goto cleanup; \n\ skel->maps.%1$s.initial_value = (__u64) (long) skel->%1$s;\n\ } \n\ - ", ident, bpf_map_mmap_sz(map)); + ", ident, bpf_map__value_size(map), bpf_map__max_entries(map)); } codegen("\ \n\
@@ -871,14 +861,14 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *hif (bpf_map__type (map) ==BPF_MAP_TYPE_PERCPU_ARRAY ) {codegen ("\ \n\ -err = skel_protect_map_data(skel->%1$s, &skel->maps.%1$s.initial_value, %2$zd);\n\ +err = skel_protect_map_data(skel->%1$s, &skel->maps.%1$s.initial_value, %2$u, %3$u);\n\ if (err) \n\ return err; \n\ #ifdef __KERNEL__ \n\ skel->%1$s = NULL; \n\ #endif \n\ " , - ident,bpf_map_mmap_sz (map)); + ident,bpf_map__value_size (map),bpf_map__max_entries (map));continue ; }
@@ -890,11 +880,11 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *hcodegen ("\ \n\ skel->%1$s = (__typeof__(skel->%1$s))skel_finalize_map_data(&skel->maps.%1$s.initial_value,\n\ -%2$zd, %3$s, skel->maps.%1$s.map_fd);\n\ +%2$u, %3$u, %4$s, skel->maps.%1$s.map_fd);\n\ if (!skel->%1$s) \n\ return -ENOMEM; \n\ " , - ident,bpf_map_mmap_sz (map), mmap_flags); + ident,bpf_map__value_size (map),bpf_map__max_entries (map), mmap_flags); } codegen("\ \n\
tools/lib/bpf/skel_internal.h +29 -14
105 lines not on this page · raw message
--
2.55.0
[email protected]
AI reviewThis isn't a bug, but would it read closer to array_map_mmap_sz() to hoist the page size into a local here? sysconf(_SC_PAGE_SIZE) is passed straight into roundup()'s second argument, and roundup()…
Quoted 12 lines
tools/lib/bpf/skel_internal.h +1
-0@@ -11,6 +11,7 @@#include <linux/bpf.h> #else #include <unistd.h> +#include <sys/param.h> #include <sys/syscall.h> #include <sys/mman.h> #include <linux/keyctl.h>
[ ... ]
tools/lib/bpf/skel_internal.h static inline void skel_free(void *p) · line 203
Quoted 10 lines
tools/lib/bpf/skel_internal.h +2
-2@@ -193,25 +197,34 @@ static inline void skel_free(void *p)free (p); } -static inline void skel_free_map_data (void *p,__u64 addr,size_t sz) +static inline size_t skel_map_mmap_sz (size_t val_sz,__u32 max_entries) { -munmap (p, sz); +return roundup (roundup (val_sz,8 ) * max_entries,sysconf (_SC_PAGE_SIZE)); }
This isn't a bug, but would it read closer to array_map_mmap_sz() to hoist the page size into a local here? sysconf(_SC_PAGE_SIZE) is passed straight into roundup()'s second argument, and roundup() is a macro that expands its second argument several times in the non-constant case. The three nearby equivalents all hoist it: the bpf_map_mmap_sz() this patch deletes from gen.c used 'long page_sz = sysconf(_SC_PAGE_SIZE);', and libbpf's array_map_mmap_sz() and bpf_map_mmap_sz() both open with 'const long page_sz = sysconf(_SC_PAGE_SIZE);'. Hoisting it here would also make the helper independent of which roundup() definition wins, and might let the new <sys/param.h> include be dropped.
Quoted 36 lines
tools/lib/bpf/skel_internal.h +13
-4-static inline void *skel_prep_map_data (const void *val,size_t mmap_sz,size_t val_sz) +static inline void skel_free_map_data (void *p,__u64 addr,size_t val_sz,__u32 max_entries) { +munmap (p,skel_map_mmap_sz (val_sz, max_entries)); +} + +static inline void *skel_prep_map_data (const void *val,size_t val_sz,__u32 max_entries, +size_t data_sz) +{ +size_t mmap_sz =skel_map_mmap_sz (val_sz, max_entries);void *addr; addr =mmap (NULL , mmap_sz,PROT_READ |PROT_WRITE ,MAP_SHARED |MAP_ANONYMOUS ,-1 ,0 );if (addr == (void *)-1 )return NULL ; -memcpy (addr, val, val_sz); +memcpy (addr, val, data_sz);return addr; } -static inline void *skel_finalize_map_data (__u64 *init_val,size_t mmap_sz,int flags,int fd) +static inline void *skel_finalize_map_data (__u64 *init_val,size_t val_sz,__u32 max_entries, +int flags,int fd) { +size_t mmap_sz =skel_map_mmap_sz (val_sz, max_entries);void *addr; addr =mmap ((void *) (long ) *init_val, mmap_sz, flags,MAP_SHARED |MAP_FIXED , fd,0 );@@ -220,11 +233,13 @@ static inline void *skel_finalize_map_data(__u64 *init_val, size_t mmap_sz, intreturn addr; } -static inline int skel_protect_map_data (void *p,__u64 *init_val,size_t sz) +static inline int skel_protect_map_data (void *p,__u64 *init_val,size_t val_sz,__u32 max_entries)
tools/lib/bpf/skel_internal.h static inline void *skel_finalize_map_data(__u64 *init_val, size_t mmap_sz, int · line 245
Quoted 10 lines
tools/lib/bpf/skel_internal.h +3
-1{ +size_t mmap_sz =skel_map_mmap_sz (val_sz, max_entries); + (void )init_val; -if (mprotect (p, sz,PROT_READ )) +if (mprotect (p, mmap_sz,PROT_READ ))return -errno;return 0 ; }
---
AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md
CI run summary: https://github.com/kernel-patches/bpf/actions/runs/34864978845
Quoted 28 lines · On 15/9/26 00:39, [email protected] wrote:
Quoted 12 lines
tools/lib/bpf/skel_internal.h +1
-0@@ -11,6 +11,7 @@#include <linux/bpf.h> #else #include <unistd.h> +#include <sys/param.h> #include <sys/syscall.h> #include <sys/mman.h> #include <linux/keyctl.h> [ ... ]
tools/lib/bpf/skel_internal.h static inline void skel_free(void *p) · line 203
Quoted 10 lines
tools/lib/bpf/skel_internal.h +2
-2@@ -193,25 +197,34 @@ static inline void skel_free(void *p)free (p); } -static inline void skel_free_map_data (void *p,__u64 addr,size_t sz) +static inline size_t skel_map_mmap_sz (size_t val_sz,__u32 max_entries) { -munmap (p, sz); +return roundup (roundup (val_sz,8 ) * max_entries,sysconf (_SC_PAGE_SIZE)); }This isn't a bug, but would it read closer to
array_map_mmap_sz()to hoist the page size into a local here?sysconf(_SC_PAGE_SIZE)is passed straight
Quoted 8 lines
into roundup()'s second argument, and
roundup()is a macro that expands its second argument several times in the non-constant case. The three nearby equivalents all hoist it: thebpf_map_mmap_sz()this patch deletes fromgen.cused 'longpage_sz=sysconf(_SC_PAGE_SIZE);', and libbpf'sarray_map_mmap_sz()andbpf_map_mmap_sz()both open with 'const longpage_sz=sysconf(_SC_PAGE_SIZE);'. Hoisting it here would also make the helper independent of whichroundup()definition wins, and might let the new <sys/param.h> include be dropped.
Good catch.
'sysconf(_SC_PAGE_SIZE)' will be calculated several times in 'roundup(roundup(val_sz, 8) * max_entries, sysconf(_SC_PAGE_SIZE))'.
printf '%s\n' \
'#include <sys/param.h>' \
'roundup(roundup(val_sz, 8) * max_entries, sysconf(_SC_PAGE_SIZE))' |
gcc -E -P -x c - |
tail -n 1
(__builtin_constant_p (sysconf(_SC_PAGESIZE)) && ((((sysconf(_SC_PAGESIZE)) - 1) & (sysconf(_SC_PAGESIZE))) == 0) ? ((((__builtin_constant_p (8) && ((((8) - 1) & (8)) == 0) ? (((val_sz) +
(8) - 1) & ~((8) - 1)) : ((((val_sz) + ((8) - 1)) / (8)) * (8))) * max_entries) + (sysconf(_SC_PAGESIZE)) - 1) & ~((sysconf(_SC_PAGESIZE))
- 1)) : (((((__builtin_constant_p (8) && ((((8) - 1) & (8)) == 0) ? (((val_sz) + (8) - 1) & ~((8) - 1)) : ((((val_sz) + ((8) - 1)) / (8)) * (8))) * max_entries) + ((sysconf(_SC_PAGESIZE)) - 1)) / (sysconf(_SC_PAGESIZE))) * (sysconf(_SC_PAGESIZE))))
Will hoist 'sysconf(_SC_PAGE_SIZE);' and 'roundup(val_sz, 8) * max_entries'.
However, the new <sys/param.h> is needed for roundup().
Thanks,
Leon
Quoted 1 line
[...]