linux/arch/powerpc/net/bpf_jit_comp.c
Linus Torvalds 5c0b0c676a powerpc updates for 5.16
- Enable STRICT_KERNEL_RWX for Freescale 85xx platforms.
 
  - Activate CONFIG_STRICT_KERNEL_RWX by default, while still allowing it to be disabled.
 
  - Add support for out-of-line static calls on 32-bit.
 
  - Fix oopses doing bpf-to-bpf calls when STRICT_KERNEL_RWX is enabled.
 
  - Fix boot hangs on e5500 due to stale value in ESR passed to do_page_fault().
 
  - Fix several bugs on pseries in handling of device tree cache information for hotplugged
    CPUs, and/or during partition migration.
 
  - Various other small features and fixes.
 
 Thanks to: Alexey Kardashevskiy, Alistair Popple, Anatolij Gustschin, Andrew Donnellan,
 Athira Rajeev, Bixuan Cui, Bjorn Helgaas, Cédric Le Goater, Christophe Leroy, Daniel
 Axtens, Daniel Henrique Barboza, Denis Kirjanov, Fabiano Rosas, Frederic Barrat, Gustavo
 A. R. Silva, Hari Bathini, Jacques de Laval, Joel Stanley, Kai Song, Kajol Jain, Laurent
 Vivier, Leonardo Bras, Madhavan Srinivasan, Nathan Chancellor, Nathan Lynch, Naveen N.
 Rao, Nicholas Piggin, Nick Desaulniers, Niklas Schnelle, Oliver O'Halloran, Rob Herring,
 Russell Currey, Srikar Dronamraju, Stan Johnson, Tyrel Datwyler, Uwe Kleine-König, Vasant
 Hegde, Wan Jiabing, Xiaoming Ni,
 -----BEGIN PGP SIGNATURE-----
 
 iQJHBAABCAAxFiEEJFGtCPCthwEv2Y/bUevqPMjhpYAFAmGFDPoTHG1wZUBlbGxl
 cm1hbi5pZC5hdQAKCRBR6+o8yOGlgNbsEACVczMVwMBEny5a7W1tqq1bnY9RFVw3
 K+/rE7/FpSLX+RrwgoMkmqfPvfyc9WISVLlIQDKz4XhkBjaXv0+Y4OMsymuDCbxL
 Qk7F1ff22UfLmPjjJk39gHJ8QZQqZk3wmFu2QzTO4yBZbz2SqqXFLxwyoLpZ0LJ8
 pdGl51+bIsTkDJzrdkhX9X4AKS/fYyjbQxq5u7FS89ZCCs+KvzjLcDRo0GZYaOK/
 hgDBa60DCCszL/9yjbh0ANZxmM2Z3+6AXkvAAXrtXzIGk4JzenZfiV+VEzmq8Tt0
 UpWSsUEe7VgykMR3MTrL9G8op70PpKX6OMUPegJq4iRQ24h4mpFCK4oV9OMKJqpF
 ifN9NO2ZZKOz1ke4l7Xe8SEHLX7rq5U/P7INh3AsKYNYwo6HkJhSPxiCBWUTlnZ3
 OYoZ7czyO4gMPHWP92z4CoSiTYVBFuyhYexRcnQskg60TIwbr+lMXziRyPRGI8b6
 taf2rD8eAiyUJnvkFUsyAHtYHpkSkuMeiVqY2CDQdh2SdtIFgwKzB2RjFL0gzaBZ
 XP9RWD+HernGQAJSlIk7cVthont3JHklcKk+ohhDbsWzPeUJcz6t4ChtgRq0x4q4
 Hpes1lsVfXpyxj5ouBK/E/t+diwPvBLM0dCcarQJE6ExgMzBC/C7Br7jCSgyVJA2
 VhtcZaCYh+vRlQ==
 =f7HE
 -----END PGP SIGNATURE-----

Merge tag 'powerpc-5.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - Enable STRICT_KERNEL_RWX for Freescale 85xx platforms.

 - Activate CONFIG_STRICT_KERNEL_RWX by default, while still allowing it
   to be disabled.

 - Add support for out-of-line static calls on 32-bit.

 - Fix oopses doing bpf-to-bpf calls when STRICT_KERNEL_RWX is enabled.

 - Fix boot hangs on e5500 due to stale value in ESR passed to
   do_page_fault().

 - Fix several bugs on pseries in handling of device tree cache
   information for hotplugged CPUs, and/or during partition migration.

 - Various other small features and fixes.

Thanks to Alexey Kardashevskiy, Alistair Popple, Anatolij Gustschin,
Andrew Donnellan, Athira Rajeev, Bixuan Cui, Bjorn Helgaas, Cédric Le
Goater, Christophe Leroy, Daniel Axtens, Daniel Henrique Barboza, Denis
Kirjanov, Fabiano Rosas, Frederic Barrat, Gustavo A.  R.  Silva, Hari
Bathini, Jacques de Laval, Joel Stanley, Kai Song, Kajol Jain, Laurent
Vivier, Leonardo Bras, Madhavan Srinivasan, Nathan Chancellor, Nathan
Lynch, Naveen N.  Rao, Nicholas Piggin, Nick Desaulniers, Niklas
Schnelle, Oliver O'Halloran, Rob Herring, Russell Currey, Srikar
Dronamraju, Stan Johnson, Tyrel Datwyler, Uwe Kleine-König, Vasant
Hegde, Wan Jiabing, and Xiaoming Ni,

* tag 'powerpc-5.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (73 commits)
  powerpc/8xx: Fix Oops with STRICT_KERNEL_RWX without DEBUG_RODATA_TEST
  powerpc/32e: Ignore ESR in instruction storage interrupt handler
  powerpc/powernv/prd: Unregister OPAL_MSG_PRD2 notifier during module unload
  powerpc: Don't provide __kernel_map_pages() without ARCH_SUPPORTS_DEBUG_PAGEALLOC
  MAINTAINERS: Update powerpc KVM entry
  powerpc/xmon: fix task state output
  powerpc/44x/fsp2: add missing of_node_put
  powerpc/dcr: Use cmplwi instead of 3-argument cmpli
  KVM: PPC: Tick accounting should defer vtime accounting 'til after IRQ handling
  powerpc/security: Use a mutex for interrupt exit code patching
  powerpc/83xx/mpc8349emitx: Make mcu_gpiochip_remove() return void
  powerpc/fsl_booke: Fix setting of exec flag when setting TLBCAMs
  powerpc/book3e: Fix set_memory_x() and set_memory_nx()
  powerpc/nohash: Fix __ptep_set_access_flags() and ptep_set_wrprotect()
  powerpc/bpf: Fix write protecting JIT code
  selftests/powerpc: Use date instead of EPOCHSECONDS in mitigation-patching.sh
  powerpc/64s/interrupt: Fix check_return_regs_valid() false positive
  powerpc/boot: Set LC_ALL=C in wrapper script
  powerpc/64s: Default to 64K pages for 64 bit book3s
  Revert "powerpc/audit: Convert powerpc to AUDIT_ARCH_COMPAT_GENERIC"
  ...
2021-11-05 08:15:46 -07:00

265 lines
6.4 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* eBPF JIT compiler
*
* Copyright 2016 Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
* IBM Corporation
*
* Based on the powerpc classic BPF JIT compiler by Matt Evans
*/
#include <linux/moduleloader.h>
#include <asm/cacheflush.h>
#include <asm/asm-compat.h>
#include <linux/netdevice.h>
#include <linux/filter.h>
#include <linux/if_vlan.h>
#include <asm/kprobes.h>
#include <linux/bpf.h>
#include "bpf_jit.h"
static void bpf_jit_fill_ill_insns(void *area, unsigned int size)
{
memset32(area, BREAKPOINT_INSTRUCTION, size / 4);
}
/* Fix the branch target addresses for subprog calls */
static int bpf_jit_fixup_subprog_calls(struct bpf_prog *fp, u32 *image,
struct codegen_context *ctx, u32 *addrs)
{
const struct bpf_insn *insn = fp->insnsi;
bool func_addr_fixed;
u64 func_addr;
u32 tmp_idx;
int i, ret;
for (i = 0; i < fp->len; i++) {
/*
* During the extra pass, only the branch target addresses for
* the subprog calls need to be fixed. All other instructions
* can left untouched.
*
* The JITed image length does not change because we already
* ensure that the JITed instruction sequence for these calls
* are of fixed length by padding them with NOPs.
*/
if (insn[i].code == (BPF_JMP | BPF_CALL) &&
insn[i].src_reg == BPF_PSEUDO_CALL) {
ret = bpf_jit_get_func_addr(fp, &insn[i], true,
&func_addr,
&func_addr_fixed);
if (ret < 0)
return ret;
/*
* Save ctx->idx as this would currently point to the
* end of the JITed image and set it to the offset of
* the instruction sequence corresponding to the
* subprog call temporarily.
*/
tmp_idx = ctx->idx;
ctx->idx = addrs[i] / 4;
bpf_jit_emit_func_call_rel(image, ctx, func_addr);
/*
* Restore ctx->idx here. This is safe as the length
* of the JITed sequence remains unchanged.
*/
ctx->idx = tmp_idx;
}
}
return 0;
}
struct powerpc64_jit_data {
struct bpf_binary_header *header;
u32 *addrs;
u8 *image;
u32 proglen;
struct codegen_context ctx;
};
bool bpf_jit_needs_zext(void)
{
return true;
}
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));
memcpy(cgctx.b2p, b2p, sizeof(cgctx.b2p));
/* 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;
}
/*
* If we have seen a tail call, we need a second pass.
* This is because bpf_jit_emit_common_epilogue() is called
* from bpf_jit_emit_tail_call() with a not yet stable ctx->seen.
*/
if (cgctx.seen & SEEN_TAILCALL) {
cgctx.idx = 0;
if (bpf_jit_build_body(fp, 0, &cgctx, addrs, false)) {
fp = org_fp;
goto out_addrs;
}
}
bpf_jit_realloc_regs(&cgctx);
/*
* 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);
if (bpf_jit_build_body(fp, code_base, &cgctx, addrs, extra_pass)) {
bpf_jit_binary_free(bpf_hdr);
fp = org_fp;
goto out_addrs;
}
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) {
bpf_jit_binary_lock_ro(bpf_hdr);
bpf_prog_fill_jited_linfo(fp, addrs);
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;
}