From: "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>
To: Michael Ellerman <mpe@ellerman.id.au>
Cc: Daniel Borkmann <daniel@iogearbox.net>,
Yauheni Kaliuta <yauheni.kaliuta@redhat.com>,
bpf@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
Alexei Starovoitov <alexei.starovoitov@gmail.com>,
Hari Bathini <hbathini@linux.ibm.com>
Subject: [PATCH powerpc/next 09/17] powerpc64/bpf: Optimize instruction sequence used for function calls
Date: Mon, 14 Feb 2022 16:11:43 +0530 [thread overview]
Message-ID: <1233c7544e60dcb021c52b1f840b0f21a87b33ed.1644834730.git.naveen.n.rao@linux.vnet.ibm.com> (raw)
In-Reply-To: <cover.1644834730.git.naveen.n.rao@linux.vnet.ibm.com>
When calling BPF helpers, we load the function address to call into a
register. This can result in upto 5 instructions. Optimize this by
instead using the kernel toc in r2 and adjusting offset to the BPF
helper. This works since all BPF helpers are part of kernel text, and
all BPF programs/functions utilize the kernel TOC.
Further more:
- load the actual function entry address in elf v1, rather than loading
it through the function descriptor address.
- load the Local Entry Point (LEP) in elf v2 skipping TOC setup.
- consolidate code across elf abi v1 and v2 by using r12 on both.
Reported-by: Anton Blanchard <anton@ozlabs.org>
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
---
arch/powerpc/net/bpf_jit_comp64.c | 30 +++++++++++++-----------------
1 file changed, 13 insertions(+), 17 deletions(-)
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index e9fd4694226fe0..bff200723e7282 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -150,22 +150,20 @@ void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
static int bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx, u64 func)
{
unsigned long func_addr = func ? ppc_function_entry((void *)func) : 0;
+ long reladdr;
if (WARN_ON_ONCE(!core_kernel_text(func_addr)))
return -EINVAL;
-#ifdef PPC64_ELF_ABI_v1
- /* func points to the function descriptor */
- PPC_LI64(b2p[TMP_REG_2], func);
- /* Load actual entry point from function descriptor */
- PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_2], 0);
- /* ... and move it to CTR */
- EMIT(PPC_RAW_MTCTR(b2p[TMP_REG_1]));
-#else
- /* We can clobber r12 */
- PPC_FUNC_ADDR(12, func);
- EMIT(PPC_RAW_MTCTR(12));
-#endif
+ reladdr = func_addr - kernel_toc_addr();
+ if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) {
+ pr_err("eBPF: address of %ps out of range of kernel_toc.\n", (void *)func);
+ return -ERANGE;
+ }
+
+ EMIT(PPC_RAW_ADDIS(_R12, _R2, PPC_HA(reladdr)));
+ EMIT(PPC_RAW_ADDI(_R12, _R12, PPC_LO(reladdr)));
+ EMIT(PPC_RAW_MTCTR(_R12));
EMIT(PPC_RAW_BCTRL());
return 0;
@@ -178,6 +176,9 @@ int bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func
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(12, func);
@@ -194,11 +195,6 @@ int bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func
for (i = ctx->idx - ctx_idx; i < 5; i++)
EMIT(PPC_RAW_NOP());
-#ifdef PPC64_ELF_ABI_v1
- /* Load actual entry point from function descriptor */
- PPC_BPF_LL(12, 12, 0);
-#endif
-
EMIT(PPC_RAW_MTCTR(12));
EMIT(PPC_RAW_BCTRL());
--
2.35.1
next prev parent reply other threads:[~2022-02-14 10:48 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-14 10:41 [PATCH powerpc/next 00/17] powerpc/bpf: Some updates and cleanups Naveen N. Rao
2022-02-14 10:41 ` [PATCH powerpc/next 01/17] powerpc/bpf: Skip branch range validation during first pass Naveen N. Rao
2022-02-14 10:41 ` [PATCH powerpc/next 02/17] powerpc/bpf: Emit a single branch instruction for known short branch ranges Naveen N. Rao
2022-02-14 10:41 ` [PATCH powerpc/next 03/17] powerpc/bpf: Handle large branch ranges with BPF_EXIT Naveen N. Rao
2022-02-14 10:41 ` [PATCH powerpc/next 04/17] powerpc64/bpf: Do not save/restore LR on each call to bpf_stf_barrier() Naveen N. Rao
2022-02-14 10:41 ` [PATCH powerpc/next 05/17] powerpc64/bpf: Use r12 for constant blinding Naveen N. Rao
2022-02-14 10:41 ` [PATCH powerpc/next 06/17] powerpc64: Set PPC64_ELF_ABI_v[1|2] macros to 1 Naveen N. Rao
2022-02-14 10:41 ` [PATCH powerpc/next 07/17] powerpc64/bpf elfv2: Setup kernel TOC in r2 on entry Naveen N. Rao
2022-02-14 10:41 ` [PATCH powerpc/next 08/17] powerpc64/bpf elfv1: Do not load TOC before calling functions Naveen N. Rao
2022-02-14 10:41 ` Naveen N. Rao [this message]
2022-02-14 10:41 ` [PATCH powerpc/next 10/17] powerpc/bpf: Rename PPC_BL_ABS() to PPC_BL() Naveen N. Rao
2022-02-14 10:41 ` [PATCH powerpc/next 11/17] powerpc64/bpf: Convert some of the uses of PPC_BPF_[LL|STL] to PPC_BPF_[LD|STD] Naveen N. Rao
2022-02-14 10:41 ` [PATCH powerpc/next 12/17] powerpc64/bpf: Get rid of PPC_BPF_[LL|STL|STLU] macros Naveen N. Rao
2022-02-14 10:41 ` [PATCH powerpc/next 13/17] powerpc/bpf: Cleanup bpf_jit.h Naveen N. Rao
2022-02-14 10:41 ` [PATCH powerpc/next 14/17] powerpc/bpf: Move bpf_jit64.h into bpf_jit_comp64.c Naveen N. Rao
2022-02-14 10:41 ` [PATCH powerpc/next 15/17] powerpc/bpf: Use _Rn macros for GPRs Naveen N. Rao
2022-02-14 10:41 ` [PATCH powerpc/next 16/17] powerpc64/bpf: Store temp registers' bpf to ppc mapping Naveen N. Rao
2022-02-14 10:41 ` [PATCH powerpc/next 17/17] powerpc/bpf: Simplify bpf_to_ppc() and adopt it for powerpc64 Naveen N. Rao
2022-03-08 12:08 ` [PATCH powerpc/next 00/17] powerpc/bpf: Some updates and cleanups Michael Ellerman
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1233c7544e60dcb021c52b1f840b0f21a87b33ed.1644834730.git.naveen.n.rao@linux.vnet.ibm.com \
--to=naveen.n.rao@linux.vnet.ibm.com \
--cc=alexei.starovoitov@gmail.com \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=hbathini@linux.ibm.com \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=mpe@ellerman.id.au \
--cc=yauheni.kaliuta@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).