diff mbox series

[bpf-next,v6,1/3] riscv, bpf: Add 12-argument support for RV64 bpf trampoline

Message ID 20240702121944.1091530-2-pulehui@huaweicloud.com (mailing list archive)
State Accepted
Commit 6801b0aef79db475591c3146a701ea373e4663b7
Delegated to: BPF
Headers show
Series Add 12-argument support for RV64 bpf trampoline | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for bpf-next
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 8 this patch: 8
netdev/build_tools success No tools touched, skip
netdev/cc_maintainers warning 2 maintainers not CCed: paul.walmsley@sifive.com aou@eecs.berkeley.edu
netdev/build_clang success Errors and warnings before: 8 this patch: 8
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 8 this patch: 8
netdev/checkpatch warning WARNING: line length of 82 exceeds 80 columns WARNING: line length of 83 exceeds 80 columns WARNING: line length of 86 exceeds 80 columns WARNING: line length of 87 exceeds 80 columns WARNING: line length of 88 exceeds 80 columns WARNING: line length of 91 exceeds 80 columns WARNING: line length of 95 exceeds 80 columns
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
bpf/vmtest-bpf-next-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-next-VM_Test-2 success Logs for Unittests
bpf/vmtest-bpf-next-VM_Test-0 success Logs for Lint
bpf/vmtest-bpf-next-VM_Test-3 success Logs for Validate matrix.py
bpf/vmtest-bpf-next-VM_Test-5 success Logs for aarch64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-34 success Logs for x86_64-llvm-17 / veristat
bpf/vmtest-bpf-next-VM_Test-35 success Logs for x86_64-llvm-18 / build / build for x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-10 success Logs for aarch64-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-11 success Logs for s390x-gcc / build / build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-20 success Logs for x86_64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-12 success Logs for s390x-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-19 success Logs for x86_64-gcc / build / build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-17 success Logs for s390x-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-9 success Logs for aarch64-gcc / test (test_verifier, false, 360) / test_verifier on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-29 success Logs for x86_64-llvm-17 / build-release / build for x86_64 with llvm-17-O2
bpf/vmtest-bpf-next-VM_Test-28 success Logs for x86_64-llvm-17 / build / build for x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-4 success Logs for aarch64-gcc / build / build for aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-18 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-36 success Logs for x86_64-llvm-18 / build-release / build for x86_64 with llvm-18-O2
bpf/vmtest-bpf-next-VM_Test-42 success Logs for x86_64-llvm-18 / veristat
bpf/vmtest-bpf-next-VM_Test-33 success Logs for x86_64-llvm-17 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-8 success Logs for aarch64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-7 success Logs for aarch64-gcc / test (test_progs, false, 360) / test_progs on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-21 success Logs for x86_64-gcc / test (test_maps, false, 360) / test_maps on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-30 success Logs for x86_64-llvm-17 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-25 success Logs for x86_64-gcc / test (test_progs_parallel, true, 30) / test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-27 fail Logs for x86_64-gcc / veristat / veristat on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-6 success Logs for aarch64-gcc / test (test_maps, false, 360) / test_maps on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-26 success Logs for x86_64-gcc / test (test_verifier, false, 360) / test_verifier on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-24 success Logs for x86_64-gcc / test (test_progs_no_alu32_parallel, true, 30) / test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-37 success Logs for x86_64-llvm-18 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-41 success Logs for x86_64-llvm-18 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-38 success Logs for x86_64-llvm-18 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-39 success Logs for x86_64-llvm-18 / test (test_progs_cpuv4, false, 360) / test_progs_cpuv4 on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-40 success Logs for x86_64-llvm-18 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-32 success Logs for x86_64-llvm-17 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-31 success Logs for x86_64-llvm-17 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-22 success Logs for x86_64-gcc / test (test_progs, false, 360) / test_progs on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-23 success Logs for x86_64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-13 success Logs for s390x-gcc / test (test_maps, false, 360) / test_maps on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-16 success Logs for s390x-gcc / test (test_verifier, false, 360) / test_verifier on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-15 success Logs for s390x-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on s390x with gcc
bpf/vmtest-bpf-next-PR fail PR summary
bpf/vmtest-bpf-next-VM_Test-14 success Logs for s390x-gcc / test (test_progs, false, 360) / test_progs on s390x with gcc

Commit Message

Pu Lehui July 2, 2024, 12:19 p.m. UTC 
From: Pu Lehui <pulehui@huawei.com>

This patch adds 12 function arguments support for riscv64 bpf
trampoline. The current bpf trampoline supports <= sizeof(u64) bytes
scalar arguments [0] and <= 16 bytes struct arguments [1]. Therefore, we
focus on the situation where scalars are at most XLEN bits and
aggregates whose total size does not exceed 2×XLEN bits in the riscv
calling convention [2].

Link: https://elixir.bootlin.com/linux/v6.8/source/kernel/bpf/btf.c#L6184 [0]
Link: https://elixir.bootlin.com/linux/v6.8/source/kernel/bpf/btf.c#L6769 [1]
Link: https://github.com/riscv-non-isa/riscv-elf-psabi-doc/releases/download/draft-20230929-e5c800e661a53efe3c2678d71a306323b60eb13b/riscv-abi.pdf [2]
Signed-off-by: Pu Lehui <pulehui@huawei.com>
Acked-by: Björn Töpel <bjorn@kernel.org>
Reviewed-by: Björn Töpel <bjorn@rivosinc.com>
---
 arch/riscv/net/bpf_jit_comp64.c | 66 +++++++++++++++++++++++----------
 1 file changed, 47 insertions(+), 19 deletions(-)

Comments

Puranjay Mohan July 2, 2024, 1:40 p.m. UTC | #1 
Pu Lehui <pulehui@huaweicloud.com> writes:

> From: Pu Lehui <pulehui@huawei.com>
>
> This patch adds 12 function arguments support for riscv64 bpf
> trampoline. The current bpf trampoline supports <= sizeof(u64) bytes
> scalar arguments [0] and <= 16 bytes struct arguments [1]. Therefore, we
> focus on the situation where scalars are at most XLEN bits and
> aggregates whose total size does not exceed 2×XLEN bits in the riscv
> calling convention [2].
>
> Link: https://elixir.bootlin.com/linux/v6.8/source/kernel/bpf/btf.c#L6184 [0]
> Link: https://elixir.bootlin.com/linux/v6.8/source/kernel/bpf/btf.c#L6769 [1]
> Link: https://github.com/riscv-non-isa/riscv-elf-psabi-doc/releases/download/draft-20230929-e5c800e661a53efe3c2678d71a306323b60eb13b/riscv-abi.pdf [2]
> Signed-off-by: Pu Lehui <pulehui@huawei.com>
> Acked-by: Björn Töpel <bjorn@kernel.org>
> Reviewed-by: Björn Töpel <bjorn@rivosinc.com>

Acked-by: Puranjay Mohan <puranjay@kernel.org>

Thanks,
Puranjay
Puranjay Mohan July 5, 2024, 12:51 p.m. UTC | #2 
Pu Lehui <pulehui@huaweicloud.com> writes:

> From: Pu Lehui <pulehui@huawei.com>
>
> This patch adds 12 function arguments support for riscv64 bpf
> trampoline. The current bpf trampoline supports <= sizeof(u64) bytes
> scalar arguments [0] and <= 16 bytes struct arguments [1]. Therefore, we
> focus on the situation where scalars are at most XLEN bits and
> aggregates whose total size does not exceed 2×XLEN bits in the riscv
> calling convention [2].
>
> Link: https://elixir.bootlin.com/linux/v6.8/source/kernel/bpf/btf.c#L6184 [0]
> Link: https://elixir.bootlin.com/linux/v6.8/source/kernel/bpf/btf.c#L6769 [1]
> Link: https://github.com/riscv-non-isa/riscv-elf-psabi-doc/releases/download/draft-20230929-e5c800e661a53efe3c2678d71a306323b60eb13b/riscv-abi.pdf [2]
> Signed-off-by: Pu Lehui <pulehui@huawei.com>
> Acked-by: Björn Töpel <bjorn@kernel.org>
> Reviewed-by: Björn Töpel <bjorn@rivosinc.com>
> ---
>  arch/riscv/net/bpf_jit_comp64.c | 66 +++++++++++++++++++++++----------
>  1 file changed, 47 insertions(+), 19 deletions(-)
>
> diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
> index 351e1484205e..685c7389ae7e 100644
> --- a/arch/riscv/net/bpf_jit_comp64.c
> +++ b/arch/riscv/net/bpf_jit_comp64.c
> @@ -15,6 +15,7 @@
>  #include <asm/percpu.h>
>  #include "bpf_jit.h"
>  
> +#define RV_MAX_REG_ARGS 8
>  #define RV_FENTRY_NINSNS 2
>  /* imm that allows emit_imm to emit max count insns */
>  #define RV_MAX_COUNT_IMM 0x7FFF7FF7FF7FF7FF
> @@ -692,26 +693,45 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type,
>  	return ret;
>  }
>  
> -static void store_args(int nregs, int args_off, struct rv_jit_context *ctx)
> +static void store_args(int nr_arg_slots, int args_off, struct rv_jit_context *ctx)
>  {
>  	int i;
>  
> -	for (i = 0; i < nregs; i++) {
> -		emit_sd(RV_REG_FP, -args_off, RV_REG_A0 + i, ctx);
> +	for (i = 0; i < nr_arg_slots; i++) {
> +		if (i < RV_MAX_REG_ARGS) {
> +			emit_sd(RV_REG_FP, -args_off, RV_REG_A0 + i, ctx);
> +		} else {
> +			/* skip slots for T0 and FP of traced function */
> +			emit_ld(RV_REG_T1, 16 + (i - RV_MAX_REG_ARGS) * 8, RV_REG_FP, ctx);
> +			emit_sd(RV_REG_FP, -args_off, RV_REG_T1, ctx);
> +		}
>  		args_off -= 8;
>  	}
>  }
>  
> -static void restore_args(int nregs, int args_off, struct rv_jit_context *ctx)
> +static void restore_args(int nr_reg_args, int args_off, struct rv_jit_context *ctx)
>  {
>  	int i;
>  
> -	for (i = 0; i < nregs; i++) {
> +	for (i = 0; i < nr_reg_args; i++) {
>  		emit_ld(RV_REG_A0 + i, -args_off, RV_REG_FP, ctx);
>  		args_off -= 8;
>  	}
>  }
>  
> +static void restore_stack_args(int nr_stack_args, int args_off, int stk_arg_off,
> +			       struct rv_jit_context *ctx)
> +{
> +	int i;
> +
> +	for (i = 0; i < nr_stack_args; i++) {
> +		emit_ld(RV_REG_T1, -(args_off - RV_MAX_REG_ARGS * 8), RV_REG_FP, ctx);
> +		emit_sd(RV_REG_FP, -stk_arg_off, RV_REG_T1, ctx);
> +		args_off -= 8;
> +		stk_arg_off -= 8;
> +	}
> +}
> +
>  static int invoke_bpf_prog(struct bpf_tramp_link *l, int args_off, int retval_off,
>  			   int run_ctx_off, bool save_ret, struct rv_jit_context *ctx)
>  {
> @@ -784,8 +804,8 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
>  {
>  	int i, ret, offset;
>  	int *branches_off = NULL;
> -	int stack_size = 0, nregs = m->nr_args;
> -	int retval_off, args_off, nregs_off, ip_off, run_ctx_off, sreg_off;
> +	int stack_size = 0, nr_arg_slots = 0;
> +	int retval_off, args_off, nregs_off, ip_off, run_ctx_off, sreg_off, stk_arg_off;
>  	struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
>  	struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
>  	struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
> @@ -831,20 +851,21 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
>  	 * FP - sreg_off    [ callee saved reg	]
>  	 *
>  	 *		    [ pads              ] pads for 16 bytes alignment
> +	 *
> +	 *		    [ stack_argN        ]
> +	 *		    [ ...               ]
> +	 * FP - stk_arg_off [ stack_arg1        ] BPF_TRAMP_F_CALL_ORIG
>  	 */
>  
>  	if (flags & (BPF_TRAMP_F_ORIG_STACK | BPF_TRAMP_F_SHARE_IPMODIFY))
>  		return -ENOTSUPP;
>  
> -	/* extra regiters for struct arguments */
> -	for (i = 0; i < m->nr_args; i++)
> -		if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG)
> -			nregs += round_up(m->arg_size[i], 8) / 8 - 1;
> -
> -	/* 8 arguments passed by registers */
> -	if (nregs > 8)
> +	if (m->nr_args > MAX_BPF_FUNC_ARGS)
>  		return -ENOTSUPP;
>  
> +	for (i = 0; i < m->nr_args; i++)
> +		nr_arg_slots += round_up(m->arg_size[i], 8) / 8;
> +
>  	/* room of trampoline frame to store return address and frame pointer */
>  	stack_size += 16;
>  
> @@ -854,7 +875,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
>  		retval_off = stack_size;
>  	}
>  
> -	stack_size += nregs * 8;
> +	stack_size += nr_arg_slots * 8;
>  	args_off = stack_size;
>  
>  	stack_size += 8;
> @@ -871,8 +892,14 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
>  	stack_size += 8;
>  	sreg_off = stack_size;
>  
> +	if (nr_arg_slots - RV_MAX_REG_ARGS > 0)
> +		stack_size += (nr_arg_slots - RV_MAX_REG_ARGS) * 8;

Hi Pu,
Although this is merged now, while working on this for arm64 I realised
that the above doesn't check for BPF_TRAMP_F_CALL_ORIG and can waste
some stack space, we should change this to:

if ((flags & BPF_TRAMP_F_CALL_ORIG) && (nr_arg_slots - RV_MAX_REG_ARGS > 0))
        stack_size += (nr_arg_slots - RV_MAX_REG_ARGS) * 8;

It will save some stack space when BPF_TRAMP_F_CALL_ORIG is not set?

I can send a patch if you think this is worth fixing.


Thanks,
Puranjay
Pu Lehui July 6, 2024, 2:28 a.m. UTC | #3 
On 2024/7/5 20:51, Puranjay Mohan wrote:
> Pu Lehui <pulehui@huaweicloud.com> writes:
> 
>> From: Pu Lehui <pulehui@huawei.com>
>>
>> This patch adds 12 function arguments support for riscv64 bpf
>> trampoline. The current bpf trampoline supports <= sizeof(u64) bytes
>> scalar arguments [0] and <= 16 bytes struct arguments [1]. Therefore, we
>> focus on the situation where scalars are at most XLEN bits and
>> aggregates whose total size does not exceed 2×XLEN bits in the riscv
>> calling convention [2].
[SNIP]
>> @@ -854,7 +875,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
>>   		retval_off = stack_size;
>>   	}
>>   
>> -	stack_size += nregs * 8;
>> +	stack_size += nr_arg_slots * 8;
>>   	args_off = stack_size;
>>   
>>   	stack_size += 8;
>> @@ -871,8 +892,14 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
>>   	stack_size += 8;
>>   	sreg_off = stack_size;
>>   
>> +	if (nr_arg_slots - RV_MAX_REG_ARGS > 0)
>> +		stack_size += (nr_arg_slots - RV_MAX_REG_ARGS) * 8;
> 
> Hi Pu,
> Although this is merged now, while working on this for arm64 I realised
> that the above doesn't check for BPF_TRAMP_F_CALL_ORIG and can waste
> some stack space, we should change this to:
> 
> if ((flags & BPF_TRAMP_F_CALL_ORIG) && (nr_arg_slots - RV_MAX_REG_ARGS > 0))
>          stack_size += (nr_arg_slots - RV_MAX_REG_ARGS) * 8;
> 
> It will save some stack space when BPF_TRAMP_F_CALL_ORIG is not set?

Nice catch. It will be better. Feel free to patch it. Thanks!

> 
> I can send a patch if you think this is worth fixing.
> 
> 
> Thanks,
> Puranjay
diff mbox series

Patch

diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 351e1484205e..685c7389ae7e 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -15,6 +15,7 @@ 
 #include <asm/percpu.h>
 #include "bpf_jit.h"
 
+#define RV_MAX_REG_ARGS 8
 #define RV_FENTRY_NINSNS 2
 /* imm that allows emit_imm to emit max count insns */
 #define RV_MAX_COUNT_IMM 0x7FFF7FF7FF7FF7FF
@@ -692,26 +693,45 @@  int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type,
 	return ret;
 }
 
-static void store_args(int nregs, int args_off, struct rv_jit_context *ctx)
+static void store_args(int nr_arg_slots, int args_off, struct rv_jit_context *ctx)
 {
 	int i;
 
-	for (i = 0; i < nregs; i++) {
-		emit_sd(RV_REG_FP, -args_off, RV_REG_A0 + i, ctx);
+	for (i = 0; i < nr_arg_slots; i++) {
+		if (i < RV_MAX_REG_ARGS) {
+			emit_sd(RV_REG_FP, -args_off, RV_REG_A0 + i, ctx);
+		} else {
+			/* skip slots for T0 and FP of traced function */
+			emit_ld(RV_REG_T1, 16 + (i - RV_MAX_REG_ARGS) * 8, RV_REG_FP, ctx);
+			emit_sd(RV_REG_FP, -args_off, RV_REG_T1, ctx);
+		}
 		args_off -= 8;
 	}
 }
 
-static void restore_args(int nregs, int args_off, struct rv_jit_context *ctx)
+static void restore_args(int nr_reg_args, int args_off, struct rv_jit_context *ctx)
 {
 	int i;
 
-	for (i = 0; i < nregs; i++) {
+	for (i = 0; i < nr_reg_args; i++) {
 		emit_ld(RV_REG_A0 + i, -args_off, RV_REG_FP, ctx);
 		args_off -= 8;
 	}
 }
 
+static void restore_stack_args(int nr_stack_args, int args_off, int stk_arg_off,
+			       struct rv_jit_context *ctx)
+{
+	int i;
+
+	for (i = 0; i < nr_stack_args; i++) {
+		emit_ld(RV_REG_T1, -(args_off - RV_MAX_REG_ARGS * 8), RV_REG_FP, ctx);
+		emit_sd(RV_REG_FP, -stk_arg_off, RV_REG_T1, ctx);
+		args_off -= 8;
+		stk_arg_off -= 8;
+	}
+}
+
 static int invoke_bpf_prog(struct bpf_tramp_link *l, int args_off, int retval_off,
 			   int run_ctx_off, bool save_ret, struct rv_jit_context *ctx)
 {
@@ -784,8 +804,8 @@  static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 {
 	int i, ret, offset;
 	int *branches_off = NULL;
-	int stack_size = 0, nregs = m->nr_args;
-	int retval_off, args_off, nregs_off, ip_off, run_ctx_off, sreg_off;
+	int stack_size = 0, nr_arg_slots = 0;
+	int retval_off, args_off, nregs_off, ip_off, run_ctx_off, sreg_off, stk_arg_off;
 	struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
 	struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
 	struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
@@ -831,20 +851,21 @@  static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 	 * FP - sreg_off    [ callee saved reg	]
 	 *
 	 *		    [ pads              ] pads for 16 bytes alignment
+	 *
+	 *		    [ stack_argN        ]
+	 *		    [ ...               ]
+	 * FP - stk_arg_off [ stack_arg1        ] BPF_TRAMP_F_CALL_ORIG
 	 */
 
 	if (flags & (BPF_TRAMP_F_ORIG_STACK | BPF_TRAMP_F_SHARE_IPMODIFY))
 		return -ENOTSUPP;
 
-	/* extra regiters for struct arguments */
-	for (i = 0; i < m->nr_args; i++)
-		if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG)
-			nregs += round_up(m->arg_size[i], 8) / 8 - 1;
-
-	/* 8 arguments passed by registers */
-	if (nregs > 8)
+	if (m->nr_args > MAX_BPF_FUNC_ARGS)
 		return -ENOTSUPP;
 
+	for (i = 0; i < m->nr_args; i++)
+		nr_arg_slots += round_up(m->arg_size[i], 8) / 8;
+
 	/* room of trampoline frame to store return address and frame pointer */
 	stack_size += 16;
 
@@ -854,7 +875,7 @@  static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 		retval_off = stack_size;
 	}
 
-	stack_size += nregs * 8;
+	stack_size += nr_arg_slots * 8;
 	args_off = stack_size;
 
 	stack_size += 8;
@@ -871,8 +892,14 @@  static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 	stack_size += 8;
 	sreg_off = stack_size;
 
+	if (nr_arg_slots - RV_MAX_REG_ARGS > 0)
+		stack_size += (nr_arg_slots - RV_MAX_REG_ARGS) * 8;
+
 	stack_size = round_up(stack_size, STACK_ALIGN);
 
+	/* room for args on stack must be at the top of stack */
+	stk_arg_off = stack_size;
+
 	if (!is_struct_ops) {
 		/* For the trampoline called from function entry,
 		 * the frame of traced function and the frame of
@@ -908,10 +935,10 @@  static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 		emit_sd(RV_REG_FP, -ip_off, RV_REG_T1, ctx);
 	}
 
-	emit_li(RV_REG_T1, nregs, ctx);
+	emit_li(RV_REG_T1, nr_arg_slots, ctx);
 	emit_sd(RV_REG_FP, -nregs_off, RV_REG_T1, ctx);
 
-	store_args(nregs, args_off, ctx);
+	store_args(nr_arg_slots, args_off, ctx);
 
 	/* skip to actual body of traced function */
 	if (flags & BPF_TRAMP_F_SKIP_FRAME)
@@ -951,7 +978,8 @@  static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 	}
 
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
-		restore_args(nregs, args_off, ctx);
+		restore_args(min_t(int, nr_arg_slots, RV_MAX_REG_ARGS), args_off, ctx);
+		restore_stack_args(nr_arg_slots - RV_MAX_REG_ARGS, args_off, stk_arg_off, ctx);
 		ret = emit_call((const u64)orig_call, true, ctx);
 		if (ret)
 			goto out;
@@ -986,7 +1014,7 @@  static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 	}
 
 	if (flags & BPF_TRAMP_F_RESTORE_REGS)
-		restore_args(nregs, args_off, ctx);
+		restore_args(min_t(int, nr_arg_slots, RV_MAX_REG_ARGS), args_off, ctx);
 
 	if (save_ret) {
 		emit_ld(RV_REG_A0, -retval_off, RV_REG_FP, ctx);