[PATCH] powerpc64/bpf: fix JIT code size calculation of bpf trampoline

[Hari Bathini]

The JIT compile of ldimm instructions can be anywhere between 1-5
instructions long depending on the value being loaded.

arch_bpf_trampoline_size() provides JIT size of the BPF trampoline
before the buffer for JIT'ing it is allocated. BPF trampoline JIT
code has ldimm instructions that need to load the value of pointer
to struct bpf_tramp_image. But this pointer value is not same while
calling arch_bpf_trampoline_size() & arch_prepare_bpf_trampoline().
So, the size arrived at using arch_bpf_trampoline_size() can vary
from the size needed in arch_prepare_bpf_trampoline(). When the
number of ldimm instructions emitted in arch_bpf_trampoline_size()
is less than the number of ldimm instructions emitted during the
actual JIT compile of trampoline, the below warning is produced:

  WARNING: CPU: 8 PID: 204190 at arch/powerpc/net/bpf_jit_comp.c:981 __arch_prepare_bpf_trampoline.isra.0+0xd2c/0xdcc

which is:

  /* Make sure the trampoline generation logic doesn't overflow */
  if (image && WARN_ON_ONCE(&image[ctx->idx] >
			(u32 *)rw_image_end - BPF_INSN_SAFETY)) {

Pass NULL as the first argument to __arch_prepare_bpf_trampoline()
call from arch_bpf_trampoline_size() function, to differentiate it
from how arch_prepare_bpf_trampoline() calls it and ensure maximum
possible instructions are emitted in arch_bpf_trampoline_size() for
ldimm instructions that load a different value during the actual JIT
compile of BPF trampoline.

Fixes: d243b62b7bd3 ("powerpc64/bpf: Add support for bpf trampolines")
Reported-by: Venkat Rao Bagalkote <venkat88 at linux.ibm.com>
Closes: https://lore.kernel.org/all/6168bfc8-659f-4b5a-a6fb-90a916dde3b3@linux.ibm.com/
Cc: stable at vger.kernel.org # v6.13+
Signed-off-by: Hari Bathini <hbathini at linux.ibm.com>
---
 arch/powerpc/net/bpf_jit_comp.c | 31 ++++++++++++++++++++++++-------
 1 file changed, 24 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 2991bb171a9b..49d7e9a8d17c 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -686,7 +686,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 	 *                              [                   ] --
 	 * LR save area                 [ r0 save (64-bit)  ]   | header
 	 *                              [ r0 save (32-bit)  ]   |
-	 * dummy frame for unwind       [ back chain 1      ] --
+	 /* dummy frame for unwind       [ back chain 1      ] --
 	 *                              [ padding           ] align stack frame
 	 *       r4_off                 [ r4 (tailcallcnt)  ] optional - 32-bit powerpc
 	 *       alt_lr_off             [ real lr (ool stub)] optional - actual lr
@@ -833,7 +833,12 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 	EMIT(PPC_RAW_STL(_R26, _R1, nvr_off + SZL));
 
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
-		PPC_LI_ADDR(_R3, (unsigned long)im);
+		/*
+		 * Emit maximum possible instructions while getting the size of
+		 * bpf trampoline to ensure trampoline JIT code doesn't overflow.
+		 */
+		PPC_LI_ADDR(_R3, im ? (unsigned long)im :
+				(unsigned long)(~(1UL << (BITS_PER_LONG - 1))));
 		ret = bpf_jit_emit_func_call_rel(image, ro_image, ctx,
 						 (unsigned long)__bpf_tramp_enter);
 		if (ret)
@@ -889,7 +894,8 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 			bpf_trampoline_restore_tail_call_cnt(image, ctx, func_frame_offset, r4_off);
 
 		/* Reserve space to patch branch instruction to skip fexit progs */
-		im->ip_after_call = &((u32 *)ro_image)[ctx->idx];
+		if (im)
+			im->ip_after_call = &((u32 *)ro_image)[ctx->idx];
 		EMIT(PPC_RAW_NOP());
 	}
 
@@ -912,8 +918,14 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		}
 
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
-		im->ip_epilogue = &((u32 *)ro_image)[ctx->idx];
-		PPC_LI_ADDR(_R3, im);
+		if (im)
+			im->ip_epilogue = &((u32 *)ro_image)[ctx->idx];
+		/*
+		 * Emit maximum possible instructions while getting the size of
+		 * bpf trampoline to ensure trampoline JIT code doesn't overflow.
+		 */
+		PPC_LI_ADDR(_R3, im ? (unsigned long)im :
+				(unsigned long)(~(1UL << (BITS_PER_LONG - 1))));
 		ret = bpf_jit_emit_func_call_rel(image, ro_image, ctx,
 						 (unsigned long)__bpf_tramp_exit);
 		if (ret)
@@ -972,7 +984,6 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
 			     struct bpf_tramp_links *tlinks, void *func_addr)
 {
-	struct bpf_tramp_image im;
 	void *image;
 	int ret;
 
@@ -988,7 +999,13 @@ int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
 	if (!image)
 		return -ENOMEM;
 
-	ret = __arch_prepare_bpf_trampoline(&im, image, image + PAGE_SIZE, image,
+	/*
+	 * Pass NULL as bpf_tramp_image pointer to differentiate the intent to get the
+	 * buffer size for trampoline here. This differentiation helps in accounting for
+	 * maximum possible instructions if the JIT code size is likely to vary during
+	 * the actual JIT compile of the trampoline.
+	 */
+	ret = __arch_prepare_bpf_trampoline(NULL, image, image + PAGE_SIZE, image,
 					    m, flags, tlinks, func_addr);
 	bpf_jit_free_exec(image);
 
-- 
2.48.1