Add an open-coded bpf_iter over the pages eligible for page_owner output, reusing page_owner_next_eligible().
A sleepable BPF program drives it with bpf_iter_page_owner_new()/next()/destroy(); each next() returns the page_owner_scan. po_snap is copied inside the page_ext RCU window, so the program needs no RCU section when it reads it. Also add bpf_page_owner_stack_snprint(), which renders the stack trace for a stack_depot handle into a caller-provided buffer. Signed-off-by: Zhen Ni <[email protected]> --- kernel/bpf/helpers.c | 6 +++++ mm/page_owner_iter.c | 52 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 58 insertions(+) diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 712dca5a2c5b..23a2d2d71f4d 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -4946,6 +4946,12 @@ BTF_ID_FLAGS(func, bpf_iter_dmabuf_new, KF_ITER_NEW | KF_SLEEPABLE) BTF_ID_FLAGS(func, bpf_iter_dmabuf_next, KF_ITER_NEXT | KF_RET_NULL | KF_SLEEPABLE) BTF_ID_FLAGS(func, bpf_iter_dmabuf_destroy, KF_ITER_DESTROY | KF_SLEEPABLE) #endif +#ifdef CONFIG_PAGE_OWNER +BTF_ID_FLAGS(func, bpf_iter_page_owner_new, KF_ITER_NEW | KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_iter_page_owner_next, KF_ITER_NEXT | KF_RET_NULL | KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_iter_page_owner_destroy, KF_ITER_DESTROY | KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_page_owner_stack_snprint, KF_SLEEPABLE) +#endif BTF_ID_FLAGS(func, __bpf_trap) BTF_ID_FLAGS(func, bpf_strcmp, KF_PERFMON); BTF_ID_FLAGS(func, bpf_strcasecmp, KF_PERFMON); diff --git a/mm/page_owner_iter.c b/mm/page_owner_iter.c index 33dc9dcd59de..80693d417407 100644 --- a/mm/page_owner_iter.c +++ b/mm/page_owner_iter.c @@ -4,6 +4,7 @@ #include <linux/memblock.h> #include <linux/mm.h> #include <linux/seq_file.h> +#include <linux/stackdepot.h> #include "page_owner.h" @@ -114,3 +115,54 @@ int page_owner_iter_register(void) return bpf_iter_reg_target(&page_owner_iter_reg_info); } + +/* opaque to BPF programs */ +struct bpf_iter_page_owner { + __u64 __opaque[16]; +} __attribute__((aligned(8))); + +struct bpf_iter_page_owner_kern { + struct page_owner_scan scan; +} __attribute__((aligned(8))); + +__bpf_kfunc_start_defs(); + +__bpf_kfunc int bpf_iter_page_owner_new(struct bpf_iter_page_owner *it) +{ + struct bpf_iter_page_owner_kern *kit = (void *)it; + + BUILD_BUG_ON(sizeof(*kit) > sizeof(*it)); + BUILD_BUG_ON(__alignof__(*kit) != __alignof__(*it)); + + kit->scan.pfn = min_low_pfn; + kit->scan.page = NULL; + return 0; +} + +__bpf_kfunc struct page_owner_scan * +bpf_iter_page_owner_next(struct bpf_iter_page_owner *it) +{ + struct bpf_iter_page_owner_kern *kit = (void *)it; + + cond_resched(); + + if (kit->scan.page) + kit->scan.pfn++; + + if (!page_owner_next_eligible(&kit->scan)) + return NULL; + + return &kit->scan; +} + +__bpf_kfunc void bpf_iter_page_owner_destroy(struct bpf_iter_page_owner *it) +{ +} + +__bpf_kfunc int bpf_page_owner_stack_snprint(depot_stack_handle_t handle, + char *buf, u32 buf_size) +{ + return stack_depot_snprint(handle, buf, buf_size, 0); +} + +__bpf_kfunc_end_defs(); -- 2.20.1
