From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com> stable inclusion from stable-v6.6.145 commit 6e52c240c43a601b681e3a4e58fc5685114d4726 category: bugfix bugzilla: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=... -------------------------------- commit 96cce16e26dd02a8678f1e87f88a4b5cdb63b995 upstream. The BPF JIT allocator packs many small programs into larger executable allocations and reuses space within those allocations as programs are loaded and freed. When fresh code is written into space that a previous program occupied, an indirect jump into the new program can reuse a branch prediction left behind by the old one. Flush the indirect branch predictors before reusing JIT memory so that indirect jumps into a newly written program don't reuse predictions from an old program that occupied the same space. Introduce bpf_arch_pred_flush_enabled static key and bpf_arch_pred_flush static call for flushing the branch predictors on JIT memory reuse. Architectures that need a flush, can update it to a predictor flush function. By default, its a NOP and does not emit any CALL. Allocations larger than a pack are not covered by this flush. That is safe because cBPF programs (the unprivileged attack surface) are bounded well below a pack size. Issue a warning if this assumption is ever violated while the flush is active. Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Sasha Levin <sashal@kernel.org> Signed-off-by: Pu Lehui <pulehui@huawei.com> --- include/linux/filter.h | 10 ++++++++++ kernel/bpf/core.c | 19 +++++++++++++++++++ 2 files changed, 29 insertions(+) diff --git a/include/linux/filter.h b/include/linux/filter.h index 2136040bbaea..cb693a4c54c4 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -22,6 +22,7 @@ #include <linux/vmalloc.h> #include <linux/sockptr.h> #include <crypto/sha1.h> +#include <linux/static_call.h> #include <linux/u64_stats_sync.h> #include <net/sch_generic.h> @@ -1039,6 +1040,15 @@ extern long bpf_jit_limit_max; typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size); +/* + * Flush the indirect branch predictors before reusing JIT memory, so that + * indirect jumps into a newly written program don't reuse predictions left + * behind by an old program that occupied the same space. + */ +void bpf_arch_pred_flush(void); +DECLARE_STATIC_CALL(bpf_arch_pred_flush, bpf_arch_pred_flush); +DECLARE_STATIC_KEY_FALSE(bpf_pred_flush_enabled); + void bpf_jit_fill_hole_with_zero(void *area, unsigned int size); struct bpf_binary_header * diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 7f9a5f46226a..f53f401ae72b 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -37,6 +37,7 @@ #include <linux/nospec.h> #include <linux/bpf_mem_alloc.h> #include <linux/memcontrol.h> +#include <linux/static_call.h> #include <asm/barrier.h> #include <asm/unaligned.h> @@ -884,6 +885,15 @@ void bpf_jit_fill_hole_with_zero(void *area, unsigned int size) memset(area, 0, size); } +DEFINE_STATIC_CALL_NULL(bpf_arch_pred_flush, bpf_arch_pred_flush); + +/* + * Enabled once bpf_arch_pred_flush points at a real flush routine. Lets the + * pack allocator test "is a predictor flush wired up at all" with a cheap + * static branch instead of repeatedly querying the static call target. + */ +DEFINE_STATIC_KEY_FALSE(bpf_pred_flush_enabled); + #define BPF_PROG_SIZE_TO_NBITS(size) (round_up(size, BPF_PROG_CHUNK_SIZE) / BPF_PROG_CHUNK_SIZE) static DEFINE_MUTEX(pack_mutex); @@ -943,6 +953,14 @@ void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns) mutex_lock(&pack_mutex); if (size > BPF_PROG_PACK_SIZE) { + /* + * Allocations larger than a pack get their own pages, and + * predictors are not flushed for such allocation. This is only + * safe because cBPF programs (the unprivileged attack surface) + * are bounded well below a pack size. + */ + if (static_branch_unlikely(&bpf_pred_flush_enabled)) + pr_warn_once("BPF: Predictors not flushed for allocations greater than BPF_PROG_PACK_SIZE\n"); size = round_up(size, PAGE_SIZE); ptr = bpf_jit_alloc_exec(size); if (ptr) { @@ -973,6 +991,7 @@ void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns) pos = 0; found_free_area: + static_call_cond(bpf_arch_pred_flush)(); bitmap_set(pack->bitmap, pos, nbits); ptr = (void *)(pack->ptr) + (pos << BPF_PROG_CHUNK_SHIFT); -- 2.34.1