arch: patch_text: Fixup last cpu should be master
Subsystems (5)
[email protected]
maintainerPATCH v2 1/1 arch: patch_text: Fixup last cpu should be master
From: Guo Ren <[email protected]>
These patch_text implementations are using stop_machine_cpuslocked infrastructure with atomic cpu_count. The original idea: When the master CPU patch_text, the others should wait for it. But current implementation is using the first CPU as master, which couldn't guarantee the remaining CPUs are waiting. This patch changes the last CPU as the master to solve the potential risk.
---
Changes in V2:
- Fixup last cpu should be num_online_cpus() by Max Filippov
- Fixup typos found by Max Filippov
--- arch/arm64/kernel/patching.c | 4 ++-- arch/csky/kernel/probes/kprobes.c | 2 +- arch/riscv/kernel/patch.c | 2 +- arch/xtensa/kernel/jump_label.c | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-)
arch/arm64/kernel/patching.c +2 -2
@@ -117,8 +117,8 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg)int i, ret =0 ;struct aarch64_insn_patch *pp = arg; -/* The first CPU becomes master */ -if (atomic_inc_return (&pp->cpu_count) ==1 ) { +/* The last CPU becomes master */ +if (atomic_inc_return (&pp->cpu_count) ==num_online_cpus ()) {for (i =0 ; ret ==0 && i < pp->insn_cnt; i++) ret =aarch64_insn_patch_text_nosync (pp->text_addrs[i], pp->new_insns[i]);
arch/csky/kernel/probes/kprobes.c +1 -1
@@ -30,7 +30,7 @@ static int __kprobes patch_text_cb(void *priv)struct csky_insn_patch *param = priv;unsigned int addr = (unsigned int )param->addr; -if (atomic_inc_return (¶m->cpu_count) ==1 ) { +if (atomic_inc_return (¶m->cpu_count) ==num_online_cpus ()) { *(u16 *) addr =cpu_to_le16 (param->opcode);dcache_wb_range (addr, addr +2 );atomic_inc (¶m->cpu_count);
arch/riscv/kernel/patch.c +1 -1
@@ -104,7 +104,7 @@ static int patch_text_cb(void *data)struct patch_insn *patch = data;int ret =0 ; -if (atomic_inc_return (&patch->cpu_count) ==1 ) { +if (atomic_inc_return (&patch->cpu_count) ==num_online_cpus ()) { ret =patch_text_nosync (patch->addr, &patch->insn,GET_INSN_LENGTH (patch->insn));
arch/xtensa/kernel/jump_label.c +1 -1
@@ -40,7 +40,7 @@ static int patch_text_stop_machine(void *data) {struct patch *patch = data; -if (atomic_inc_return (&patch->cpu_count) ==1 ) { +if (atomic_inc_return (&patch->cpu_count) ==num_online_cpus ()) {local_patch_text (patch->addr, patch->data, patch->sz);atomic_inc (&patch->cpu_count); }else {
Signature · 1 line
2.25.1
Quoted 5 lines · On Sun, Mar 13, 2022 at 09:22:21AM +0800, [email protected] wrote:
From: Guo Ren <[email protected]>
These
patch_textimplementations are usingstop_machine_cpuslockedinfrastructure with atomiccpu_count. The original idea: When the master CPUpatch_text, the others should wait for it.
I couldn't find the original intent in the commit logs (at least not in the arm64 logs). Maybe the intention was for the CPUs to wait for the text patching to complete rather than the master CPU to wait for the others to enter the cpu_relax() loop before patching.
I think your patch makes sense anyway, the master CPU would wait for all the others to enter the cpu_relax() loop before patching and releasing them with another increment. You probably wouldn't see any issues in practice unless you insert probes in the multi_stop_cpu() function (or we could mark this function as __kprobes and get rid of the extra loops entirely).
arch/arm64/kernel/patching.c static int __kprobes aarch64_insn_patch_text_cb(void *arg) · line 124
Quoted 13 lines
arch/arm64/kernel/patching.c +2
-2@@ -117,8 +117,8 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg)int i, ret =0 ;struct aarch64_insn_patch *pp = arg; -/* The first CPU becomes master */ -if (atomic_inc_return (&pp->cpu_count) ==1 ) { +/* The last CPU becomes master */ +if (atomic_inc_return (&pp->cpu_count) ==num_online_cpus ()) {for (i =0 ; ret ==0 && i < pp->insn_cnt; i++) ret =aarch64_insn_patch_text_nosync (pp->text_addrs[i], pp->new_insns[i]);
For arm64:
Signature · 1 line
Catalin
Guo Ren
maintainerQuoted 13 lines · Catalin Marinas
Quoted 5 lines · On Sun, Mar 13, 2022 at 09:22:21AM +0800, [email protected] wrote:
From: Guo Ren <[email protected]>
These
patch_textimplementations are usingstop_machine_cpuslockedinfrastructure with atomiccpu_count. The original idea: When the master CPUpatch_text, the others should wait for it.I couldn't find the original intent in the commit logs (at least not in the arm64 logs). Maybe the intention was for the CPUs to wait for the text patching to complete rather than the master CPU to wait for the others to enter the
cpu_relax()loop before patching.
Quoted 6 lines
I think your patch makes sense anyway, the master CPU would wait for all the others to enter the
cpu_relax()loop before patching and releasing them with another increment. You probably wouldn't see any issues in practice unless you insert probes in themulti_stop_cpu()function (or we could mark this function as__kprobesand get rid of the extra loops entirely).
That could depend on micro-arch, trigger other harts' IPI is not guaranteed by hw.
Quoted 17 lines
Quoted 4 lines
arch/arm64/kernel/patching.c static int __kprobes aarch64_insn_patch_text_cb(void *arg) · line 124
Quoted 10 lines
arch/arm64/kernel/patching.c +2
-2@@ -117,8 +117,8 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg)int i, ret =0 ;struct aarch64_insn_patch *pp = arg; -/* The first CPU becomes master */ -if (atomic_inc_return (&pp->cpu_count) ==1 ) { +/* The last CPU becomes master */ +if (atomic_inc_return (&pp->cpu_count) ==num_online_cpus ()) {for (i =0 ; ret ==0 && i < pp->insn_cnt; i++) ret =aarch64_insn_patch_text_nosync (pp->text_addrs[i], pp->new_insns[i]);For arm64:
Quoted 1 line
Reviewed-by Catalin Marinas <[email protected]>
Thx
Quoted 3 lines
--
Catalin
Signature · 4 lines
Best Regards Guo Ren ML: https://lore.kernel.org/linux-csky/
Quoted 64 lines · On Sat, 12 Mar 2022 17:22:21 PST (-0800), [email protected] wrote:
From: Guo Ren <[email protected]>
These
patch_textimplementations are usingstop_machine_cpuslockedinfrastructure with atomiccpu_count. The original idea: When the master CPUpatch_text, the others should wait for it. But current implementation is using the first CPU as master, which couldn't guarantee the remaining CPUs are waiting. This patch changes the last CPU as the master to solve the potential risk.Signed-off-by Guo Ren <[email protected]>Signed-off-by Guo Ren <[email protected]>Reviewed-by Max Filippov <[email protected]>Cc Will Deacon <[email protected]>Cc Catalin Marinas <[email protected]>Cc Palmer Dabbelt <[email protected]>Cc Peter Zijlstra <[email protected]Cc Masami Hiramatsu <[email protected]>Cc Chris Zankel <[email protected]>Cc Arnd Bergmann <[email protected]>---
Changes in V2:
- Fixup last cpu should benum_online_cpus()by Max Filippov
- Fixup typos found by Max Filippov--- arch/arm64/kernel/patching.c | 4 ++-- arch/csky/kernel/probes/kprobes.c | 2 +- arch/riscv/kernel/patch.c | 2 +- arch/xtensa/kernel/jump_label.c | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-)arch/arm64/kernel/patching.c +2
-2@@ -117,8 +117,8 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg)int i, ret =0 ;struct aarch64_insn_patch *pp = arg; -/* The first CPU becomes master */ -if (atomic_inc_return (&pp->cpu_count) ==1 ) { +/* The last CPU becomes master */ +if (atomic_inc_return (&pp->cpu_count) ==num_online_cpus ()) {for (i =0 ; ret ==0 && i < pp->insn_cnt; i++) ret =aarch64_insn_patch_text_nosync (pp->text_addrs[i], pp->new_insns[i]);arch/csky/kernel/probes/kprobes.c +1
-1@@ -30,7 +30,7 @@ static int __kprobes patch_text_cb(void *priv)struct csky_insn_patch *param = priv;unsigned int addr = (unsigned int )param->addr; -if (atomic_inc_return (¶m->cpu_count) ==1 ) { +if (atomic_inc_return (¶m->cpu_count) ==num_online_cpus ()) { *(u16 *) addr =cpu_to_le16 (param->opcode);dcache_wb_range (addr, addr +2 );atomic_inc (¶m->cpu_count);arch/riscv/kernel/patch.c +0
-0
arch/riscv/kernel/patch.c static int patch_text_cb(void *data) · line 110
Quoted 8 lines
arch/riscv/kernel/patch.c +1
-1@@ -104,7 +104,7 @@ static int patch_text_cb(void *data)struct patch_insn *patch = data;int ret =0 ; -if (atomic_inc_return (&patch->cpu_count) ==1 ) { +if (atomic_inc_return (&patch->cpu_count) ==num_online_cpus ()) { ret =patch_text_nosync (patch->addr, &patch->insn,GET_INSN_LENGTH (patch->insn));
It's better if these sorts of things get split up: there's really no dependency between these diffs and having them together just makes for a merge/test headache for everyone.
I'm OK taking this through the RISC-V tree if other folks ack it, but for now I'm going to assume it's going to go in via somewhere else.
Quoted 13 lines
arch/xtensa/kernel/jump_label.c +1
-1@@ -40,7 +40,7 @@ static int patch_text_stop_machine(void *data) {struct patch *patch = data; -if (atomic_inc_return (&patch->cpu_count) ==1 ) { +if (atomic_inc_return (&patch->cpu_count) ==num_online_cpus ()) {local_patch_text (patch->addr, patch->data, patch->sz);atomic_inc (&patch->cpu_count); }else {
Guo Ren
maintainerQuoted 77 lines · Palmer Dabbelt
Quoted 64 lines · On Sat, 12 Mar 2022 17:22:21 PST (-0800), [email protected] wrote:
From: Guo Ren <[email protected]>
These
patch_textimplementations are usingstop_machine_cpuslockedinfrastructure with atomiccpu_count. The original idea: When the master CPUpatch_text, the others should wait for it. But current implementation is using the first CPU as master, which couldn't guarantee the remaining CPUs are waiting. This patch changes the last CPU as the master to solve the potential risk.Signed-off-by Guo Ren <[email protected]>Signed-off-by Guo Ren <[email protected]>Reviewed-by Max Filippov <[email protected]>Cc Will Deacon <[email protected]>Cc Catalin Marinas <[email protected]>Cc Palmer Dabbelt <[email protected]>Cc Peter Zijlstra <[email protected]Cc Masami Hiramatsu <[email protected]>Cc Chris Zankel <[email protected]>Cc Arnd Bergmann <[email protected]>---
Changes in V2:
- Fixup last cpu should benum_online_cpus()by Max Filippov
- Fixup typos found by Max Filippov--- arch/arm64/kernel/patching.c | 4 ++-- arch/csky/kernel/probes/kprobes.c | 2 +- arch/riscv/kernel/patch.c | 2 +- arch/xtensa/kernel/jump_label.c | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-)arch/arm64/kernel/patching.c +2
-2@@ -117,8 +117,8 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg)int i, ret =0 ;struct aarch64_insn_patch *pp = arg; -/* The first CPU becomes master */ -if (atomic_inc_return (&pp->cpu_count) ==1 ) { +/* The last CPU becomes master */ +if (atomic_inc_return (&pp->cpu_count) ==num_online_cpus ()) {for (i =0 ; ret ==0 && i < pp->insn_cnt; i++) ret =aarch64_insn_patch_text_nosync (pp->text_addrs[i], pp->new_insns[i]);arch/csky/kernel/probes/kprobes.c +1
-1@@ -30,7 +30,7 @@ static int __kprobes patch_text_cb(void *priv)struct csky_insn_patch *param = priv;unsigned int addr = (unsigned int )param->addr; -if (atomic_inc_return (¶m->cpu_count) ==1 ) { +if (atomic_inc_return (¶m->cpu_count) ==num_online_cpus ()) { *(u16 *) addr =cpu_to_le16 (param->opcode);dcache_wb_range (addr, addr +2 );atomic_inc (¶m->cpu_count);arch/riscv/kernel/patch.c +0
-0arch/riscv/kernel/patch.c static int patch_text_cb(void *data) · line 110
Quoted 8 lines
arch/riscv/kernel/patch.c +1
-1@@ -104,7 +104,7 @@ static int patch_text_cb(void *data)struct patch_insn *patch = data;int ret =0 ; -if (atomic_inc_return (&patch->cpu_count) ==1 ) { +if (atomic_inc_return (&patch->cpu_count) ==num_online_cpus ()) { ret =patch_text_nosync (patch->addr, &patch->insn,GET_INSN_LENGTH (patch->insn));
Quoted 3 lines
It's better if these sorts of things get split up: there's really no dependency between these diffs and having them together just makes for a merge/test headache for everyone.
I'm Okay with split patches, @Arnd Bergmann what's your opinion? We've got all arch vendors' agreements (arm64, csky, riscv, xtensa).
Quoted 3 lines
I'm OK taking this through the RISC-V tree if other folks ack it, but for now I'm going to assume it's going to go in via somewhere else.
Arnd has given some comments on unnecessary #error, maybe I need to update V2.
Quoted 14 lines
Quoted 14 lines
arch/xtensa/kernel/jump_label.c +1
-1@@ -40,7 +40,7 @@ static int patch_text_stop_machine(void *data) {struct patch *patch = data; -if (atomic_inc_return (&patch->cpu_count) ==1 ) { +if (atomic_inc_return (&patch->cpu_count) ==num_online_cpus ()) {local_patch_text (patch->addr, patch->data, patch->sz);atomic_inc (&patch->cpu_count); }else {
Signature · 4 lines
Best Regards Guo Ren ML: https://lore.kernel.org/linux-csky/
Quoted 9 lines · On Sun, 13 Mar 2022 09:22:21 +0800 [email protected] wrote:
From: Guo Ren <[email protected]>
These
patch_textimplementations are usingstop_machine_cpuslockedinfrastructure with atomiccpu_count. The original idea: When the master CPUpatch_text, the others should wait for it. But current implementation is using the first CPU as master, which couldn't guarantee the remaining CPUs are waiting. This patch changes the last CPU as the master to solve the potential risk.
This looks good to me. And maybe we'd better backport to stable branch this since this can cause self-modification in wrong timing.
Thank you,
Quoted 79 lines
Signed-off-by Guo Ren <[email protected]>Signed-off-by Guo Ren <[email protected]>Reviewed-by Max Filippov <[email protected]>Cc Will Deacon <[email protected]>Cc Catalin Marinas <[email protected]>Cc Palmer Dabbelt <[email protected]>Cc Peter Zijlstra <[email protected]Cc Masami Hiramatsu <[email protected]>Cc Chris Zankel <[email protected]>Cc Arnd Bergmann <[email protected]>---
Changes in V2:
- Fixup last cpu should benum_online_cpus()by Max Filippov
- Fixup typos found by Max Filippov--- arch/arm64/kernel/patching.c | 4 ++-- arch/csky/kernel/probes/kprobes.c | 2 +- arch/riscv/kernel/patch.c | 2 +- arch/xtensa/kernel/jump_label.c | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-)arch/arm64/kernel/patching.c +2
-2@@ -117,8 +117,8 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg)int i, ret =0 ;struct aarch64_insn_patch *pp = arg; -/* The first CPU becomes master */ -if (atomic_inc_return (&pp->cpu_count) ==1 ) { +/* The last CPU becomes master */ +if (atomic_inc_return (&pp->cpu_count) ==num_online_cpus ()) {for (i =0 ; ret ==0 && i < pp->insn_cnt; i++) ret =aarch64_insn_patch_text_nosync (pp->text_addrs[i], pp->new_insns[i]);arch/csky/kernel/probes/kprobes.c +1
-1@@ -30,7 +30,7 @@ static int __kprobes patch_text_cb(void *priv)struct csky_insn_patch *param = priv;unsigned int addr = (unsigned int )param->addr; -if (atomic_inc_return (¶m->cpu_count) ==1 ) { +if (atomic_inc_return (¶m->cpu_count) ==num_online_cpus ()) { *(u16 *) addr =cpu_to_le16 (param->opcode);dcache_wb_range (addr, addr +2 );atomic_inc (¶m->cpu_count);arch/riscv/kernel/patch.c +1
-1@@ -104,7 +104,7 @@ static int patch_text_cb(void *data)struct patch_insn *patch = data;int ret =0 ; -if (atomic_inc_return (&patch->cpu_count) ==1 ) { +if (atomic_inc_return (&patch->cpu_count) ==num_online_cpus ()) { ret =patch_text_nosync (patch->addr, &patch->insn,GET_INSN_LENGTH (patch->insn));arch/xtensa/kernel/jump_label.c +1
-1@@ -40,7 +40,7 @@ static int patch_text_stop_machine(void *data) {struct patch *patch = data; -if (atomic_inc_return (&patch->cpu_count) ==1 ) { +if (atomic_inc_return (&patch->cpu_count) ==num_online_cpus ()) {local_patch_text (patch->addr, patch->data, patch->sz);atomic_inc (&patch->cpu_count); }else {Signature · 1 line
2.25.1
Signature · 1 line
Masami Hiramatsu <[email protected]>