summaryrefslogtreecommitdiff
path: root/arch/powerpc/net/bpf_jit_comp64.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2024-11-23 10:44:31 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2024-11-23 10:44:31 -0800
commit42d9e8b7ccddee75989283cf7477305cfe3776ff (patch)
treeb7f8cf87bcc6755cc829d0ca90e8ec90bb58ab16 /arch/powerpc/net/bpf_jit_comp64.c
parent5c00ff742bf5caf85f60e1c73999f99376fb865d (diff)
parent3c592ce7991cdf03bc7d139d790ce58c82c5903b (diff)
Merge tag 'powerpc-6.13-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc updates from Michael Ellerman: - Rework kfence support for the HPT MMU to work on systems with >= 16TB of RAM. - Remove the powerpc "maple" platform, used by the "Yellow Dog Powerstation". - Add support for DYNAMIC_FTRACE_WITH_CALL_OPS, DYNAMIC_FTRACE_WITH_DIRECT_CALLS & BPF Trampolines. - Add support for running KVM nested guests on Power11. - Other small features, cleanups and fixes. Thanks to Amit Machhiwal, Arnd Bergmann, Christophe Leroy, Costa Shulyupin, David Hunter, David Wang, Disha Goel, Gautam Menghani, Geert Uytterhoeven, Hari Bathini, Julia Lawall, Kajol Jain, Keith Packard, Lukas Bulwahn, Madhavan Srinivasan, Markus Elfring, Michal Suchanek, Ming Lei, Mukesh Kumar Chaurasiya, Nathan Chancellor, Naveen N Rao, Nicholas Piggin, Nysal Jan K.A, Paulo Miguel Almeida, Pavithra Prakash, Ritesh Harjani (IBM), Rob Herring (Arm), Sachin P Bappalige, Shen Lichuan, Simon Horman, Sourabh Jain, Thomas Weißschuh, Thorsten Blum, Thorsten Leemhuis, Venkat Rao Bagalkote, Zhang Zekun, and zhang jiao. * tag 'powerpc-6.13-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (89 commits) EDAC/powerpc: Remove PPC_MAPLE drivers powerpc/perf: Add per-task/process monitoring to vpa_pmu driver powerpc/kvm: Add vpa latency counters to kvm_vcpu_arch docs: ABI: sysfs-bus-event_source-devices-vpa-pmu: Document sysfs event format entries for vpa_pmu powerpc/perf: Add perf interface to expose vpa counters MAINTAINERS: powerpc: Mark Maddy as "M" powerpc/Makefile: Allow overriding CPP powerpc-km82xx.c: replace of_node_put() with __free ps3: Correct some typos in comments powerpc/kexec: Fix return of uninitialized variable macintosh: Use common error handling code in via_pmu_led_init() powerpc/powermac: Use of_property_match_string() in pmac_has_backlight_type() powerpc: remove dead config options for MPC85xx platform support powerpc/xive: Use cpumask_intersects() selftests/powerpc: Remove the path after initialization. powerpc/xmon: symbol lookup length fixed powerpc/ep8248e: Use %pa to format resource_size_t powerpc/ps3: Reorganize kerneldoc parameter names KVM: PPC: Book3S HV: Fix kmv -> kvm typo powerpc/sstep: make emulate_vsx_load and emulate_vsx_store static ...
Diffstat (limited to 'arch/powerpc/net/bpf_jit_comp64.c')
-rw-r--r--arch/powerpc/net/bpf_jit_comp64.c72
1 files changed, 25 insertions, 47 deletions
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 2cbcdf93cc19..233703b06d7c 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -84,7 +84,7 @@ static inline bool bpf_has_stack_frame(struct codegen_context *ctx)
}
/*
- * When not setting up our own stackframe, the redzone usage is:
+ * When not setting up our own stackframe, the redzone (288 bytes) usage is:
*
* [ prev sp ] <-------------
* [ ... ] |
@@ -92,7 +92,7 @@ static inline bool bpf_has_stack_frame(struct codegen_context *ctx)
* [ nv gpr save area ] 5*8
* [ tail_call_cnt ] 8
* [ local_tmp_var ] 16
- * [ unused red zone ] 208 bytes protected
+ * [ unused red zone ] 224
*/
static int bpf_jit_stack_local(struct codegen_context *ctx)
{
@@ -126,6 +126,9 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
{
int i;
+ /* Instruction for trampoline attach */
+ EMIT(PPC_RAW_NOP());
+
#ifndef CONFIG_PPC_KERNEL_PCREL
if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2))
EMIT(PPC_RAW_LD(_R2, _R13, offsetof(struct paca_struct, kernel_toc)));
@@ -200,16 +203,26 @@ void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(BPF_REG_0)));
EMIT(PPC_RAW_BLR());
+
+ bpf_jit_build_fentry_stubs(image, ctx);
}
-static int
-bpf_jit_emit_func_call_hlp(u32 *image, u32 *fimage, struct codegen_context *ctx, u64 func)
+int bpf_jit_emit_func_call_rel(u32 *image, u32 *fimage, struct codegen_context *ctx, u64 func)
{
unsigned long func_addr = func ? ppc_function_entry((void *)func) : 0;
long reladdr;
- if (WARN_ON_ONCE(!kernel_text_address(func_addr)))
- return -EINVAL;
+ /* bpf to bpf call, func is not known in the initial pass. Emit 5 nops as a placeholder */
+ if (!func) {
+ for (int i = 0; i < 5; i++)
+ EMIT(PPC_RAW_NOP());
+ /* elfv1 needs an additional instruction to load addr from descriptor */
+ if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V1))
+ EMIT(PPC_RAW_NOP());
+ EMIT(PPC_RAW_MTCTR(_R12));
+ EMIT(PPC_RAW_BCTRL());
+ return 0;
+ }
#ifdef CONFIG_PPC_KERNEL_PCREL
reladdr = func_addr - local_paca->kernelbase;
@@ -266,7 +279,8 @@ bpf_jit_emit_func_call_hlp(u32 *image, u32 *fimage, struct codegen_context *ctx,
* We can clobber r2 since we get called through a
* function pointer (so caller will save/restore r2).
*/
- EMIT(PPC_RAW_LD(_R2, bpf_to_ppc(TMP_REG_2), 8));
+ if (is_module_text_address(func_addr))
+ EMIT(PPC_RAW_LD(_R2, bpf_to_ppc(TMP_REG_2), 8));
} else {
PPC_LI64(_R12, func);
EMIT(PPC_RAW_MTCTR(_R12));
@@ -276,46 +290,14 @@ bpf_jit_emit_func_call_hlp(u32 *image, u32 *fimage, struct codegen_context *ctx,
* Load r2 with kernel TOC as kernel TOC is used if function address falls
* within core kernel text.
*/
- EMIT(PPC_RAW_LD(_R2, _R13, offsetof(struct paca_struct, kernel_toc)));
+ if (is_module_text_address(func_addr))
+ EMIT(PPC_RAW_LD(_R2, _R13, offsetof(struct paca_struct, kernel_toc)));
}
#endif
return 0;
}
-int bpf_jit_emit_func_call_rel(u32 *image, u32 *fimage, struct codegen_context *ctx, u64 func)
-{
- unsigned int i, ctx_idx = ctx->idx;
-
- if (WARN_ON_ONCE(func && is_module_text_address(func)))
- return -EINVAL;
-
- /* skip past descriptor if elf v1 */
- func += FUNCTION_DESCR_SIZE;
-
- /* Load function address into r12 */
- PPC_LI64(_R12, func);
-
- /* For bpf-to-bpf function calls, the callee's address is unknown
- * until the last extra pass. As seen above, we use PPC_LI64() to
- * load the callee's address, but this may optimize the number of
- * instructions required based on the nature of the address.
- *
- * Since we don't want the number of instructions emitted to increase,
- * we pad the optimized PPC_LI64() call with NOPs to guarantee that
- * we always have a five-instruction sequence, which is the maximum
- * that PPC_LI64() can emit.
- */
- if (!image)
- for (i = ctx->idx - ctx_idx; i < 5; i++)
- EMIT(PPC_RAW_NOP());
-
- EMIT(PPC_RAW_MTCTR(_R12));
- EMIT(PPC_RAW_BCTRL());
-
- return 0;
-}
-
static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out)
{
/*
@@ -326,7 +308,7 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
*/
int b2p_bpf_array = bpf_to_ppc(BPF_REG_2);
int b2p_index = bpf_to_ppc(BPF_REG_3);
- int bpf_tailcall_prologue_size = 8;
+ int bpf_tailcall_prologue_size = 12;
if (!IS_ENABLED(CONFIG_PPC_KERNEL_PCREL) && IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2))
bpf_tailcall_prologue_size += 4; /* skip past the toc load */
@@ -1102,11 +1084,7 @@ emit_clear:
if (ret < 0)
return ret;
- if (func_addr_fixed)
- ret = bpf_jit_emit_func_call_hlp(image, fimage, ctx, func_addr);
- else
- ret = bpf_jit_emit_func_call_rel(image, fimage, ctx, func_addr);
-
+ ret = bpf_jit_emit_func_call_rel(image, fimage, ctx, func_addr);
if (ret)
return ret;