[PATCH 1/2] powerpc64/bpf: Implement JIT support for private stack
adubey
adubey at linux.ibm.com
Wed Feb 25 21:43:17 AEDT 2026
On 2026-02-17 07:19, kernel test robot wrote:
> Hi,
>
> kernel test robot noticed the following build warnings:
>
> [auto build test WARNING on bpf-next/master]
> [also build test WARNING on bpf/master powerpc/next linus/master
> next-20260216]
> [cannot apply to bpf-next/net powerpc/fixes v6.19]
> [If your patch is applied to the wrong git tree, kindly drop us a note.
> And when submitting patch, we suggest to use '--base' as documented in
> https://git-scm.com/docs/git-format-patch#_base_tree_information]
>
> url:
> https://github.com/intel-lab-lkp/linux/commits/adubey-linux-ibm-com/selftests-bpf-Enable-private-stack-tests-for-powerpc64/20260216-182353
> base:
> https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git master
> patch link:
> https://lore.kernel.org/r/20260216152234.36632-1-adubey%40linux.ibm.com
> patch subject: [PATCH 1/2] powerpc64/bpf: Implement JIT support for
> private stack
> config: powerpc64-randconfig-r133-20260217
> (https://download.01.org/0day-ci/archive/20260217/202602170941.f1KIvBuf-lkp@intel.com/config)
> compiler: powerpc64-linux-gcc (GCC) 8.5.0
> reproduce (this is a W=1 build):
> (https://download.01.org/0day-ci/archive/20260217/202602170941.f1KIvBuf-lkp@intel.com/reproduce)
>
> If you fix the issue in a separate patch/commit (i.e. not just a new
> version of
> the same patch/commit), kindly add following tags
> | Reported-by: kernel test robot <lkp at intel.com>
> | Closes:
> https://lore.kernel.org/oe-kbuild-all/202602170941.f1KIvBuf-lkp@intel.com/
>
> sparse warnings: (new ones prefixed by >>)
>>> arch/powerpc/net/bpf_jit_comp.c:266:43: sparse: sparse: cast removes
>>> address space '__percpu' of expression
> --
>>> arch/powerpc/net/bpf_jit_comp64.c:186:9: sparse: sparse: cast removes
>>> address space '__percpu' of expression
>>> arch/powerpc/net/bpf_jit_comp64.c:186:9: sparse: sparse: cast removes
>>> address space '__percpu' of expression
>>> arch/powerpc/net/bpf_jit_comp64.c:186:9: sparse: sparse: cast removes
>>> address space '__percpu' of expression
>>> arch/powerpc/net/bpf_jit_comp64.c:186:9: sparse: sparse: cast removes
>>> address space '__percpu' of expression
>>> arch/powerpc/net/bpf_jit_comp64.c:186:9: sparse: sparse: cast removes
>>> address space '__percpu' of expression
>>> arch/powerpc/net/bpf_jit_comp64.c:186:9: sparse: sparse: cast removes
>>> address space '__percpu' of expression
>>> arch/powerpc/net/bpf_jit_comp64.c:186:9: sparse: sparse: cast removes
>>> address space '__percpu' of expression
>>> arch/powerpc/net/bpf_jit_comp64.c:186:9: sparse: sparse: cast removes
>>> address space '__percpu' of expression
>>> arch/powerpc/net/bpf_jit_comp64.c:186:9: sparse: sparse: cast removes
>>> address space '__percpu' of expression
>>> arch/powerpc/net/bpf_jit_comp64.c:186:9: sparse: sparse: cast removes
>>> address space '__percpu' of expression
>>> arch/powerpc/net/bpf_jit_comp64.c:186:9: sparse: sparse: cast removes
>>> address space '__percpu' of expression
>>> arch/powerpc/net/bpf_jit_comp64.c:186:9: sparse: sparse: cast removes
>>> address space '__percpu' of expression
>>> arch/powerpc/net/bpf_jit_comp64.c:186:9: sparse: sparse: cast removes
>>> address space '__percpu' of expression
>>> arch/powerpc/net/bpf_jit_comp64.c:186:9: sparse: sparse: cast removes
>>> address space '__percpu' of expression
>>> arch/powerpc/net/bpf_jit_comp64.c:186:9: sparse: sparse: cast removes
>>> address space '__percpu' of expression
>>> arch/powerpc/net/bpf_jit_comp64.c:186:9: sparse: sparse: cast removes
>>> address space '__percpu' of expression
>>> arch/powerpc/net/bpf_jit_comp64.c:186:9: sparse: sparse: cast removes
>>> address space '__percpu' of expression
>>> arch/powerpc/net/bpf_jit_comp64.c:212:32: sparse: sparse: incorrect
>>> type in assignment (different address spaces) @@ expected void
>>> [noderef] __percpu *priv_frame_ptr @@ got void * @@
> arch/powerpc/net/bpf_jit_comp64.c:212:32: sparse: expected void
> [noderef] __percpu *priv_frame_ptr
> arch/powerpc/net/bpf_jit_comp64.c:212:32: sparse: got void *
> arch/powerpc/net/bpf_jit_comp64.c:1476:41: sparse: sparse: cast
> truncates bits from constant value (8000000000000000 becomes 0)
> arch/powerpc/net/bpf_jit_comp64.c:1476:41: sparse: sparse: cast
> truncates bits from constant value (8000000000000000 becomes 0)
> arch/powerpc/net/bpf_jit_comp64.c:1478:41: sparse: sparse: cast
> truncates bits from constant value (c000000000000000 becomes 0)
> arch/powerpc/net/bpf_jit_comp64.c:1478:41: sparse: sparse: cast
> truncates bits from constant value (c000000000000000 becomes 0)
>
> vim +/__percpu +266 arch/powerpc/net/bpf_jit_comp.c
>
> 164
> 165 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
> 166 {
> 167 u32 proglen;
> 168 u32 alloclen;
> 169 u8 *image = NULL;
> 170 u32 *code_base;
> 171 u32 *addrs;
> 172 struct powerpc_jit_data *jit_data;
> 173 struct codegen_context cgctx;
> 174 int pass;
> 175 int flen;
> 176 int priv_stack_alloc_size;
> 177 void __percpu *priv_stack_ptr = NULL;
> 178 struct bpf_binary_header *fhdr = NULL;
> 179 struct bpf_binary_header *hdr = NULL;
> 180 struct bpf_prog *org_fp = fp;
> 181 struct bpf_prog *tmp_fp;
> 182 bool bpf_blinded = false;
> 183 bool extra_pass = false;
> 184 u8 *fimage = NULL;
> 185 u32 *fcode_base;
> 186 u32 extable_len;
> 187 u32 fixup_len;
> 188
> 189 if (!fp->jit_requested)
> 190 return org_fp;
> 191
> 192 tmp_fp = bpf_jit_blind_constants(org_fp);
> 193 if (IS_ERR(tmp_fp))
> 194 return org_fp;
> 195
> 196 if (tmp_fp != org_fp) {
> 197 bpf_blinded = true;
> 198 fp = tmp_fp;
> 199 }
> 200
> 201 jit_data = fp->aux->jit_data;
> 202 if (!jit_data) {
> 203 jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL);
> 204 if (!jit_data) {
> 205 fp = org_fp;
> 206 goto out;
> 207 }
> 208 fp->aux->jit_data = jit_data;
> 209 }
> 210
> 211 if (!priv_stack_ptr && fp->aux->jits_use_priv_stack) {
> 212 /*
> 213 * Allocate private stack of size equivalent to
> 214 * verifier-calculated stack size plus two memory
> 215 * guard regions to detect private stack overflow
> 216 * and underflow.
> 217 */
> 218 priv_stack_alloc_size = round_up(fp->aux->stack_depth, 16) +
> 219 2 * PRIV_STACK_GUARD_SZ;
> 220 priv_stack_ptr = __alloc_percpu_gfp(priv_stack_alloc_size,
> 16, GFP_KERNEL);
> 221 if (!priv_stack_ptr) {
> 222 fp = org_fp;
> 223 goto out_priv_stack;
> 224 }
> 225
> 226 priv_stack_init_guard(priv_stack_ptr, priv_stack_alloc_size);
> 227 fp->aux->priv_stack_ptr = priv_stack_ptr;
> 228 }
> 229
> 230 flen = fp->len;
> 231 addrs = jit_data->addrs;
> 232 if (addrs) {
> 233 cgctx = jit_data->ctx;
> 234 /*
> 235 * JIT compiled to a writable location (image/code_base)
> first.
> 236 * It is then moved to the readonly final location
> (fimage/fcode_base)
> 237 * using instruction patching.
> 238 */
> 239 fimage = jit_data->fimage;
> 240 fhdr = jit_data->fhdr;
> 241 proglen = jit_data->proglen;
> 242 hdr = jit_data->hdr;
> 243 image = (void *)hdr + ((void *)fimage - (void *)fhdr);
> 244 extra_pass = true;
> 245 /* During extra pass, ensure index is reset before
> repopulating extable entries */
> 246 cgctx.exentry_idx = 0;
> 247 goto skip_init_ctx;
> 248 }
> 249
> 250 addrs = kcalloc(flen + 1, sizeof(*addrs), GFP_KERNEL);
> 251 if (addrs == NULL) {
> 252 fp = org_fp;
> 253 goto out_addrs;
> 254 }
> 255
> 256 memset(&cgctx, 0, sizeof(struct codegen_context));
> 257 bpf_jit_init_reg_mapping(&cgctx);
> 258
> 259 /* Make sure that the stack is quadword aligned. */
> 260 cgctx.stack_size = round_up(fp->aux->stack_depth, 16);
> 261 cgctx.arena_vm_start =
> bpf_arena_get_kern_vm_start(fp->aux->arena);
> 262 cgctx.user_vm_start =
> bpf_arena_get_user_vm_start(fp->aux->arena);
> 263 cgctx.is_subprog = bpf_is_subprog(fp);
> 264 cgctx.exception_boundary = fp->aux->exception_boundary;
> 265 cgctx.exception_cb = fp->aux->exception_cb;
> > 266 cgctx.priv_sp = priv_stack_ptr ? (u64)priv_stack_ptr : 0;
> 267
> 268 /* Scouting faux-generate pass 0 */
> 269 if (bpf_jit_build_body(fp, NULL, NULL, &cgctx, addrs, 0,
> false)) {
> 270 /* We hit something illegal or unsupported. */
> 271 fp = org_fp;
> 272 goto out_addrs;
> 273 }
> 274
> 275 /*
> 276 * If we have seen a tail call, we need a second pass.
> 277 * This is because bpf_jit_emit_common_epilogue() is called
> 278 * from bpf_jit_emit_tail_call() with a not yet stable
> ctx->seen.
> 279 * We also need a second pass if we ended up with too large
> 280 * a program so as to ensure BPF_EXIT branches are in range.
> 281 */
> 282 if (cgctx.seen & SEEN_TAILCALL ||
> !is_offset_in_branch_range((long)cgctx.idx * 4)) {
> 283 cgctx.idx = 0;
> 284 if (bpf_jit_build_body(fp, NULL, NULL, &cgctx, addrs, 0,
> false)) {
> 285 fp = org_fp;
> 286 goto out_addrs;
> 287 }
> 288 }
> 289
> 290 bpf_jit_realloc_regs(&cgctx);
> 291 /*
> 292 * Pretend to build prologue, given the features we've seen.
> This will
> 293 * update ctgtx.idx as it pretends to output instructions, then
> we can
> 294 * calculate total size from idx.
> 295 */
> 296 bpf_jit_build_prologue(NULL, &cgctx);
> 297 addrs[fp->len] = cgctx.idx * 4;
> 298 bpf_jit_build_epilogue(NULL, &cgctx);
> 299
> 300 fixup_len = fp->aux->num_exentries * BPF_FIXUP_LEN * 4;
> 301 extable_len = fp->aux->num_exentries * sizeof(struct
> exception_table_entry);
> 302
> 303 proglen = cgctx.idx * 4;
> 304 alloclen = proglen + FUNCTION_DESCR_SIZE + fixup_len +
> extable_len;
> 305
> 306 fhdr = bpf_jit_binary_pack_alloc(alloclen, &fimage, 4, &hdr,
> &image,
> 307 bpf_jit_fill_ill_insns);
> 308 if (!fhdr) {
> 309 fp = org_fp;
> 310 goto out_addrs;
> 311 }
> 312
> 313 if (extable_len)
> 314 fp->aux->extable = (void *)fimage + FUNCTION_DESCR_SIZE +
> proglen + fixup_len;
> 315
> 316 skip_init_ctx:
> 317 code_base = (u32 *)(image + FUNCTION_DESCR_SIZE);
> 318 fcode_base = (u32 *)(fimage + FUNCTION_DESCR_SIZE);
> 319
> 320 /* Code generation passes 1-2 */
> 321 for (pass = 1; pass < 3; pass++) {
> 322 /* Now build the prologue, body code & epilogue for real. */
> 323 cgctx.idx = 0;
> 324 cgctx.alt_exit_addr = 0;
> 325 bpf_jit_build_prologue(code_base, &cgctx);
> 326 if (bpf_jit_build_body(fp, code_base, fcode_base, &cgctx,
> addrs, pass,
> 327 extra_pass)) {
> 328 bpf_arch_text_copy(&fhdr->size, &hdr->size,
> sizeof(hdr->size));
> 329 bpf_jit_binary_pack_free(fhdr, hdr);
> 330 fp = org_fp;
> 331 goto out_addrs;
> 332 }
> 333 bpf_jit_build_epilogue(code_base, &cgctx);
> 334
> 335 if (bpf_jit_enable > 1)
> 336 pr_info("Pass %d: shrink = %d, seen = 0x%x\n", pass,
> 337 proglen - (cgctx.idx * 4), cgctx.seen);
> 338 }
> 339
> 340 if (bpf_jit_enable > 1)
> 341 /*
> 342 * Note that we output the base address of the code_base
> 343 * rather than image, since opcodes are in code_base.
> 344 */
> 345 bpf_jit_dump(flen, proglen, pass, code_base);
> 346
Posted v2 with fix:
https://lore.kernel.org/bpf/20260216152234.36632-1-adubey@linux.ibm.com/
-Abhishek
More information about the Linuxppc-dev
mailing list