struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
{
u32 proglen;
u32 alloclen;
u8 *image = NULL;
u32 *code_base;
u32 *addrs;
struct powerpc64_jit_data *jit_data;
struct codegen_context cgctx;
int pass;
int flen;
struct bpf_binary_header *bpf_hdr;
struct bpf_prog *org_fp = fp;
struct bpf_prog *tmp_fp;
bool bpf_blinded = false;
bool extra_pass = false;
if (!fp->jit_requested)
return org_fp;
tmp_fp = bpf_jit_blind_constants(org_fp);
if (IS_ERR(tmp_fp))
return org_fp;
if (tmp_fp != org_fp) {
bpf_blinded = true;
fp = tmp_fp;
}
jit_data = fp->aux->jit_data;
if (!jit_data) {
jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL);
if (!jit_data) {
fp = org_fp;
goto out;
}
fp->aux->jit_data = jit_data;
}
flen = fp->len;
addrs = jit_data->addrs;
if (addrs) {
cgctx = jit_data->ctx;
image = jit_data->image;
bpf_hdr = jit_data->header;
proglen = jit_data->proglen;
alloclen = proglen + FUNCTION_DESCR_SIZE;
extra_pass = true;
goto skip_init_ctx;
}
addrs = kcalloc(flen + 1, sizeof(*addrs), GFP_KERNEL);
if (addrs == NULL) {
fp = org_fp;
goto out_addrs;
}
memset(&cgctx, 0, sizeof(struct codegen_context));
/* Make sure that the stack is quadword aligned. */
cgctx.stack_size = round_up(fp->aux->stack_depth, 16);
/* Scouting faux-generate pass 0 */
if (bpf_jit_build_body(fp, 0, &cgctx, addrs, false)) {
/* We hit something illegal or unsupported. */
fp = org_fp;
goto out_addrs;
}
/*
* Pretend to build prologue, given the features we've seen. This will
* update ctgtx.idx as it pretends to output instructions, then we can
* calculate total size from idx.
*/
bpf_jit_build_prologue(0, &cgctx);
bpf_jit_build_epilogue(0, &cgctx);
proglen = cgctx.idx * 4;
alloclen = proglen + FUNCTION_DESCR_SIZE;
bpf_hdr = bpf_jit_binary_alloc(alloclen, &image, 4,
bpf_jit_fill_ill_insns);
if (!bpf_hdr) {
fp = org_fp;
goto out_addrs;
}
skip_init_ctx:
code_base = (u32 *)(image + FUNCTION_DESCR_SIZE);
if (extra_pass) {
/*
* Do not touch the prologue and epilogue as they will remain
* unchanged. Only fix the branch target address for subprog
* calls in the body.
*
* This does not change the offsets and lengths of the subprog
* call instruction sequences and hence, the size of the JITed
* image as well.
*/
bpf_jit_fixup_subprog_calls(fp, code_base, &cgctx, addrs);
/* There is no need to perform the usual passes. */
goto skip_codegen_passes;
}
/* Code generation passes 1-2 */
for (pass = 1; pass < 3; pass++) {
/* Now build the prologue, body code & epilogue for real. */
cgctx.idx = 0;
bpf_jit_build_prologue(code_base, &cgctx);
bpf_jit_build_body(fp, code_base, &cgctx, addrs, extra_pass);
bpf_jit_build_epilogue(code_base, &cgctx);
if (bpf_jit_enable > 1)
pr_info("Pass %d: shrink = %d, seen = 0x%x\n", pass,
proglen - (cgctx.idx * 4), cgctx.seen);
}
skip_codegen_passes:
if (bpf_jit_enable > 1)
/*
* Note that we output the base address of the code_base
* rather than image, since opcodes are in code_base.
*/
bpf_jit_dump(flen, proglen, pass, code_base);
#ifdef PPC64_ELF_ABI_v1
/* Function descriptor nastiness: Address + TOC */
((u64 *)image)[0] = (u64)code_base;
((u64 *)image)[1] = local_paca->kernel_toc;
#endif
fp->bpf_func = (void *)image;
fp->jited = 1;
fp->jited_len = alloclen;
bpf_flush_icache(bpf_hdr, (u8 *)bpf_hdr + (bpf_hdr->pages * PAGE_SIZE));
if (!fp->is_func || extra_pass) {
out_addrs:
kfree(addrs);
kfree(jit_data);
fp->aux->jit_data = NULL;
} else {
jit_data->addrs = addrs;
jit_data->ctx = cgctx;
jit_data->proglen = proglen;
jit_data->image = image;
jit_data->header = bpf_hdr;
}
out:
if (bpf_blinded)
bpf_jit_prog_release_other(fp, fp == org_fp ? tmp_fp : org_fp);
return fp;
}
void bpf_int_jit_compile(struct bpf_prog *prog)
{
struct bpf_binary_header *header = NULL;
int proglen, oldproglen = 0;
struct jit_context ctx = {};
u8 *image = NULL;
int *addrs;
int pass;
int i;
if (!bpf_jit_enable)
return;
if (!prog || !prog->len)
return;
addrs = kmalloc(prog->len * sizeof(*addrs), GFP_KERNEL);
if (!addrs)
return;
/* Before first pass, make a rough estimation of addrs[]
* each bpf instruction is translated to less than 64 bytes
*/
for (proglen = 0, i = 0; i < prog->len; i++) {
proglen += 64;
addrs[i] = proglen;
}
ctx.cleanup_addr = proglen;
/* JITed image shrinks with every pass and the loop iterates
* until the image stops shrinking. Very large bpf programs
* may converge on the last pass. In such case do one more
* pass to emit the final image
*/
for (pass = 0; pass < 10 || image; pass++) {
proglen = do_jit(prog, addrs, image, oldproglen, &ctx);
if (proglen <= 0) {
image = NULL;
if (header)
bpf_jit_binary_free(header);
goto out;
}
if (image) {
if (proglen != oldproglen) {
pr_err("bpf_jit: proglen=%d != oldproglen=%d\n",
proglen, oldproglen);
goto out;
}
break;
}
if (proglen == oldproglen) {
header = bpf_jit_binary_alloc(proglen, &image,
1, jit_fill_hole);
if (!header)
goto out;
}
oldproglen = proglen;
}
if (bpf_jit_enable > 1)
bpf_jit_dump(prog->len, proglen, pass + 1, image);
if (image) {
bpf_flush_icache(header, image + proglen);
set_memory_ro((unsigned long)header, header->pages);
prog->bpf_func = (void *)image;
prog->jited = 1;
}
out:
kfree(addrs);
}
struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
{
struct bpf_binary_header *header = NULL;
struct bpf_prog *tmp, *orig_prog = prog;
struct x64_jit_data *jit_data;
int proglen, oldproglen = 0;
struct jit_context ctx = {};
bool tmp_blinded = false;
bool extra_pass = false;
u8 *image = NULL;
int *addrs;
int pass;
int i;
if (!prog->jit_requested)
return orig_prog;
tmp = bpf_jit_blind_constants(prog);
/*
* If blinding was requested and we failed during blinding,
* we must fall back to the interpreter.
*/
if (IS_ERR(tmp))
return orig_prog;
if (tmp != prog) {
tmp_blinded = true;
prog = tmp;
}
jit_data = prog->aux->jit_data;
if (!jit_data) {
jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL);
if (!jit_data) {
prog = orig_prog;
goto out;
}
prog->aux->jit_data = jit_data;
}
addrs = jit_data->addrs;
if (addrs) {
ctx = jit_data->ctx;
oldproglen = jit_data->proglen;
image = jit_data->image;
header = jit_data->header;
extra_pass = true;
goto skip_init_addrs;
}
addrs = kmalloc(prog->len * sizeof(*addrs), GFP_KERNEL);
if (!addrs) {
prog = orig_prog;
goto out_addrs;
}
/*
* Before first pass, make a rough estimation of addrs[]
* each BPF instruction is translated to less than 64 bytes
*/
for (proglen = 0, i = 0; i < prog->len; i++) {
proglen += 64;
addrs[i] = proglen;
}
ctx.cleanup_addr = proglen;
skip_init_addrs:
/*
* JITed image shrinks with every pass and the loop iterates
* until the image stops shrinking. Very large BPF programs
* may converge on the last pass. In such case do one more
* pass to emit the final image.
*/
for (pass = 0; pass < 20 || image; pass++) {
proglen = do_jit(prog, addrs, image, oldproglen, &ctx);
if (proglen <= 0) {
out_image:
image = NULL;
if (header)
bpf_jit_binary_free(header);
prog = orig_prog;
goto out_addrs;
}
if (image) {
if (proglen != oldproglen) {
pr_err("bpf_jit: proglen=%d != oldproglen=%d\n",
proglen, oldproglen);
goto out_image;
}
break;
}
if (proglen == oldproglen) {
header = bpf_jit_binary_alloc(proglen, &image,
1, jit_fill_hole);
if (!header) {
prog = orig_prog;
goto out_addrs;
}
}
oldproglen = proglen;
cond_resched();
}
if (bpf_jit_enable > 1)
bpf_jit_dump(prog->len, proglen, pass + 1, image);
if (image) {
if (!prog->is_func || extra_pass) {
bpf_jit_binary_lock_ro(header);
} else {
jit_data->addrs = addrs;
jit_data->ctx = ctx;
jit_data->proglen = proglen;
jit_data->image = image;
jit_data->header = header;
}
prog->bpf_func = (void *)image;
prog->jited = 1;
prog->jited_len = proglen;
} else {
prog = orig_prog;
}
if (!image || !prog->is_func || extra_pass) {
out_addrs:
kfree(addrs);
kfree(jit_data);
prog->aux->jit_data = NULL;
}
out:
if (tmp_blinded)
bpf_jit_prog_release_other(prog, prog == orig_prog ?
tmp : orig_prog);
return prog;
}