* [RFC PATCH 01/15] powerpc/module: Remove unused .ftrace.tramp section
2023-06-07 16:55 [RFC PATCH 00/15] powerpc/ftrace: refactoring and support for -fpatchable-function-entry Naveen N Rao
@ 2023-06-07 16:55 ` Naveen N Rao
2023-06-07 16:55 ` [RFC PATCH 02/15] powerpc64/ftrace: Move ELFv1 and -pg support code into a separate file Naveen N Rao
` (13 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Naveen N Rao @ 2023-06-07 16:55 UTC (permalink / raw
To: linuxppc-dev; +Cc: Steven Rostedt, Nicholas Piggin
.ftrace.tramp section is not used for any purpose. This code was added
all the way back in the original commit introducing support for dynamic
ftrace on ppc64 modules. Remove it.
Signed-off-by: Naveen N Rao <naveen@kernel.org>
---
arch/powerpc/include/asm/module.h | 4 ----
1 file changed, 4 deletions(-)
diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h
index ac53606c259430..a8e2e8339fb7f4 100644
--- a/arch/powerpc/include/asm/module.h
+++ b/arch/powerpc/include/asm/module.h
@@ -75,10 +75,6 @@ struct mod_arch_specific {
#endif
#ifdef CONFIG_DYNAMIC_FTRACE
-# ifdef MODULE
- asm(".section .ftrace.tramp,\"ax\",@nobits; .align 3; .previous");
-# endif /* MODULE */
-
int module_trampoline_target(struct module *mod, unsigned long trampoline,
unsigned long *target);
int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs);
--
2.40.1
^ permalink raw reply related [flat|nested] 16+ messages in thread* [RFC PATCH 02/15] powerpc64/ftrace: Move ELFv1 and -pg support code into a separate file
2023-06-07 16:55 [RFC PATCH 00/15] powerpc/ftrace: refactoring and support for -fpatchable-function-entry Naveen N Rao
2023-06-07 16:55 ` [RFC PATCH 01/15] powerpc/module: Remove unused .ftrace.tramp section Naveen N Rao
@ 2023-06-07 16:55 ` Naveen N Rao
2023-06-07 16:55 ` [RFC PATCH 03/15] powerpc/ftrace: Simplify function_graph support in ftrace.c Naveen N Rao
` (12 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Naveen N Rao @ 2023-06-07 16:55 UTC (permalink / raw
To: linuxppc-dev; +Cc: Steven Rostedt, Nicholas Piggin
ELFv1 support is deprecated and on the way out. Pre -mprofile-kernel
ftrace support (-pg only) is very limited and is retained primarily for
clang builds. It won't be necessary once clang lands support for
-fpatchable-function-entry.
Copy the existing ftrace code supporting these into ftrace_pg.c.
ftrace.c can then be refactored and enhanced with a focus on ppc32 and
ppc64 ELFv2.
Signed-off-by: Naveen N Rao <naveen@kernel.org>
---
arch/powerpc/kernel/trace/Makefile | 13 +-
arch/powerpc/kernel/trace/ftrace.c | 10 -
arch/powerpc/kernel/trace/ftrace_pg.c | 846 ++++++++++++++++++++++++++
3 files changed, 855 insertions(+), 14 deletions(-)
create mode 100644 arch/powerpc/kernel/trace/ftrace_pg.c
diff --git a/arch/powerpc/kernel/trace/Makefile b/arch/powerpc/kernel/trace/Makefile
index b16a9f9c0b35f2..342a2d1ae86cd0 100644
--- a/arch/powerpc/kernel/trace/Makefile
+++ b/arch/powerpc/kernel/trace/Makefile
@@ -6,15 +6,16 @@
ifdef CONFIG_FUNCTION_TRACER
# do not trace tracer code
CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_ftrace_pg.o = $(CC_FLAGS_FTRACE)
endif
-obj32-$(CONFIG_FUNCTION_TRACER) += ftrace_mprofile.o
+obj32-$(CONFIG_FUNCTION_TRACER) += ftrace_mprofile.o ftrace.o
ifdef CONFIG_MPROFILE_KERNEL
-obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_mprofile.o
+obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_mprofile.o ftrace.o
else
-obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_64_pg.o
+obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_64_pg.o ftrace_pg.o
endif
-obj-$(CONFIG_FUNCTION_TRACER) += ftrace_low.o ftrace.o
+obj-$(CONFIG_FUNCTION_TRACER) += ftrace_low.o
obj-$(CONFIG_TRACING) += trace_clock.o
obj-$(CONFIG_PPC64) += $(obj64-y)
@@ -25,3 +26,7 @@ GCOV_PROFILE_ftrace.o := n
KCOV_INSTRUMENT_ftrace.o := n
KCSAN_SANITIZE_ftrace.o := n
UBSAN_SANITIZE_ftrace.o := n
+GCOV_PROFILE_ftrace_pg.o := n
+KCOV_INSTRUMENT_ftrace_pg.o := n
+KCSAN_SANITIZE_ftrace_pg.o := n
+UBSAN_SANITIZE_ftrace_pg.o := n
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index a47f303734233b..81a121b56c4d7f 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -864,13 +864,3 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip,
}
#endif
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-
-#ifdef CONFIG_PPC64_ELF_ABI_V1
-char *arch_ftrace_match_adjust(char *str, const char *search)
-{
- if (str[0] == '.' && search[0] != '.')
- return str + 1;
- else
- return str;
-}
-#endif /* CONFIG_PPC64_ELF_ABI_V1 */
diff --git a/arch/powerpc/kernel/trace/ftrace_pg.c b/arch/powerpc/kernel/trace/ftrace_pg.c
new file mode 100644
index 00000000000000..7b85c3b460a3c0
--- /dev/null
+++ b/arch/powerpc/kernel/trace/ftrace_pg.c
@@ -0,0 +1,846 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Code for replacing ftrace calls with jumps.
+ *
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ *
+ * Thanks goes out to P.A. Semi, Inc for supplying me with a PPC64 box.
+ *
+ * Added function graph tracer code, taken from x86 that was written
+ * by Frederic Weisbecker, and ported to PPC by Steven Rostedt.
+ *
+ */
+
+#define pr_fmt(fmt) "ftrace-powerpc: " fmt
+
+#include <linux/spinlock.h>
+#include <linux/hardirq.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/ftrace.h>
+#include <linux/percpu.h>
+#include <linux/init.h>
+#include <linux/list.h>
+
+#include <asm/cacheflush.h>
+#include <asm/code-patching.h>
+#include <asm/ftrace.h>
+#include <asm/syscall.h>
+#include <asm/inst.h>
+
+/*
+ * We generally only have a single long_branch tramp and at most 2 or 3 plt
+ * tramps generated. But, we don't use the plt tramps currently. We also allot
+ * 2 tramps after .text and .init.text. So, we only end up with around 3 usable
+ * tramps in total. Set aside 8 just to be sure.
+ */
+#define NUM_FTRACE_TRAMPS 8
+static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS];
+
+static ppc_inst_t
+ftrace_call_replace(unsigned long ip, unsigned long addr, int link)
+{
+ ppc_inst_t op;
+
+ addr = ppc_function_entry((void *)addr);
+
+ /* if (link) set op to 'bl' else 'b' */
+ create_branch(&op, (u32 *)ip, addr, link ? BRANCH_SET_LINK : 0);
+
+ return op;
+}
+
+static inline int
+ftrace_modify_code(unsigned long ip, ppc_inst_t old, ppc_inst_t new)
+{
+ ppc_inst_t replaced;
+
+ /*
+ * Note:
+ * We are paranoid about modifying text, as if a bug was to happen, it
+ * could cause us to read or write to someplace that could cause harm.
+ * Carefully read and modify the code with probe_kernel_*(), and make
+ * sure what we read is what we expected it to be before modifying it.
+ */
+
+ /* read the text we want to modify */
+ if (copy_inst_from_kernel_nofault(&replaced, (void *)ip))
+ return -EFAULT;
+
+ /* Make sure it is what we expect it to be */
+ if (!ppc_inst_equal(replaced, old)) {
+ pr_err("%p: replaced (%08lx) != old (%08lx)", (void *)ip,
+ ppc_inst_as_ulong(replaced), ppc_inst_as_ulong(old));
+ return -EINVAL;
+ }
+
+ /* replace the text with the new text */
+ return patch_instruction((u32 *)ip, new);
+}
+
+/*
+ * Helper functions that are the same for both PPC64 and PPC32.
+ */
+static int test_24bit_addr(unsigned long ip, unsigned long addr)
+{
+ addr = ppc_function_entry((void *)addr);
+
+ return is_offset_in_branch_range(addr - ip);
+}
+
+static int is_bl_op(ppc_inst_t op)
+{
+ return (ppc_inst_val(op) & ~PPC_LI_MASK) == PPC_RAW_BL(0);
+}
+
+static int is_b_op(ppc_inst_t op)
+{
+ return (ppc_inst_val(op) & ~PPC_LI_MASK) == PPC_RAW_BRANCH(0);
+}
+
+static unsigned long find_bl_target(unsigned long ip, ppc_inst_t op)
+{
+ int offset;
+
+ offset = PPC_LI(ppc_inst_val(op));
+ /* make it signed */
+ if (offset & 0x02000000)
+ offset |= 0xfe000000;
+
+ return ip + (long)offset;
+}
+
+#ifdef CONFIG_MODULES
+static int
+__ftrace_make_nop(struct module *mod,
+ struct dyn_ftrace *rec, unsigned long addr)
+{
+ unsigned long entry, ptr, tramp;
+ unsigned long ip = rec->ip;
+ ppc_inst_t op, pop;
+
+ /* read where this goes */
+ if (copy_inst_from_kernel_nofault(&op, (void *)ip)) {
+ pr_err("Fetching opcode failed.\n");
+ return -EFAULT;
+ }
+
+ /* Make sure that this is still a 24bit jump */
+ if (!is_bl_op(op)) {
+ pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op));
+ return -EINVAL;
+ }
+
+ /* lets find where the pointer goes */
+ tramp = find_bl_target(ip, op);
+
+ pr_devel("ip:%lx jumps to %lx", ip, tramp);
+
+ if (module_trampoline_target(mod, tramp, &ptr)) {
+ pr_err("Failed to get trampoline target\n");
+ return -EFAULT;
+ }
+
+ pr_devel("trampoline target %lx", ptr);
+
+ entry = ppc_global_function_entry((void *)addr);
+ /* This should match what was called */
+ if (ptr != entry) {
+ pr_err("addr %lx does not match expected %lx\n", ptr, entry);
+ return -EINVAL;
+ }
+
+ if (IS_ENABLED(CONFIG_MPROFILE_KERNEL)) {
+ if (copy_inst_from_kernel_nofault(&op, (void *)(ip - 4))) {
+ pr_err("Fetching instruction at %lx failed.\n", ip - 4);
+ return -EFAULT;
+ }
+
+ /* We expect either a mflr r0, or a std r0, LRSAVE(r1) */
+ if (!ppc_inst_equal(op, ppc_inst(PPC_RAW_MFLR(_R0))) &&
+ !ppc_inst_equal(op, ppc_inst(PPC_INST_STD_LR))) {
+ pr_err("Unexpected instruction %08lx around bl _mcount\n",
+ ppc_inst_as_ulong(op));
+ return -EINVAL;
+ }
+ } else if (IS_ENABLED(CONFIG_PPC64)) {
+ /*
+ * Check what is in the next instruction. We can see ld r2,40(r1), but
+ * on first pass after boot we will see mflr r0.
+ */
+ if (copy_inst_from_kernel_nofault(&op, (void *)(ip + 4))) {
+ pr_err("Fetching op failed.\n");
+ return -EFAULT;
+ }
+
+ if (!ppc_inst_equal(op, ppc_inst(PPC_INST_LD_TOC))) {
+ pr_err("Expected %08lx found %08lx\n", PPC_INST_LD_TOC,
+ ppc_inst_as_ulong(op));
+ return -EINVAL;
+ }
+ }
+
+ /*
+ * When using -mprofile-kernel or PPC32 there is no load to jump over.
+ *
+ * Otherwise our original call site looks like:
+ *
+ * bl <tramp>
+ * ld r2,XX(r1)
+ *
+ * Milton Miller pointed out that we can not simply nop the branch.
+ * If a task was preempted when calling a trace function, the nops
+ * will remove the way to restore the TOC in r2 and the r2 TOC will
+ * get corrupted.
+ *
+ * Use a b +8 to jump over the load.
+ */
+ if (IS_ENABLED(CONFIG_MPROFILE_KERNEL) || IS_ENABLED(CONFIG_PPC32))
+ pop = ppc_inst(PPC_RAW_NOP());
+ else
+ pop = ppc_inst(PPC_RAW_BRANCH(8)); /* b +8 */
+
+ if (patch_instruction((u32 *)ip, pop)) {
+ pr_err("Patching NOP failed.\n");
+ return -EPERM;
+ }
+
+ return 0;
+}
+#else
+static int __ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr)
+{
+ return 0;
+}
+#endif /* CONFIG_MODULES */
+
+static unsigned long find_ftrace_tramp(unsigned long ip)
+{
+ int i;
+
+ /*
+ * We have the compiler generated long_branch tramps at the end
+ * and we prefer those
+ */
+ for (i = NUM_FTRACE_TRAMPS - 1; i >= 0; i--)
+ if (!ftrace_tramps[i])
+ continue;
+ else if (is_offset_in_branch_range(ftrace_tramps[i] - ip))
+ return ftrace_tramps[i];
+
+ return 0;
+}
+
+static int add_ftrace_tramp(unsigned long tramp)
+{
+ int i;
+
+ for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
+ if (!ftrace_tramps[i]) {
+ ftrace_tramps[i] = tramp;
+ return 0;
+ }
+
+ return -1;
+}
+
+/*
+ * If this is a compiler generated long_branch trampoline (essentially, a
+ * trampoline that has a branch to _mcount()), we re-write the branch to
+ * instead go to ftrace_[regs_]caller() and note down the location of this
+ * trampoline.
+ */
+static int setup_mcount_compiler_tramp(unsigned long tramp)
+{
+ int i;
+ ppc_inst_t op;
+ unsigned long ptr;
+
+ /* Is this a known long jump tramp? */
+ for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
+ if (ftrace_tramps[i] == tramp)
+ return 0;
+
+ /* New trampoline -- read where this goes */
+ if (copy_inst_from_kernel_nofault(&op, (void *)tramp)) {
+ pr_debug("Fetching opcode failed.\n");
+ return -1;
+ }
+
+ /* Is this a 24 bit branch? */
+ if (!is_b_op(op)) {
+ pr_debug("Trampoline is not a long branch tramp.\n");
+ return -1;
+ }
+
+ /* lets find where the pointer goes */
+ ptr = find_bl_target(tramp, op);
+
+ if (ptr != ppc_global_function_entry((void *)_mcount)) {
+ pr_debug("Trampoline target %p is not _mcount\n", (void *)ptr);
+ return -1;
+ }
+
+ /* Let's re-write the tramp to go to ftrace_[regs_]caller */
+ if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
+ ptr = ppc_global_function_entry((void *)ftrace_regs_caller);
+ else
+ ptr = ppc_global_function_entry((void *)ftrace_caller);
+
+ if (patch_branch((u32 *)tramp, ptr, 0)) {
+ pr_debug("REL24 out of range!\n");
+ return -1;
+ }
+
+ if (add_ftrace_tramp(tramp)) {
+ pr_debug("No tramp locations left\n");
+ return -1;
+ }
+
+ return 0;
+}
+
+static int __ftrace_make_nop_kernel(struct dyn_ftrace *rec, unsigned long addr)
+{
+ unsigned long tramp, ip = rec->ip;
+ ppc_inst_t op;
+
+ /* Read where this goes */
+ if (copy_inst_from_kernel_nofault(&op, (void *)ip)) {
+ pr_err("Fetching opcode failed.\n");
+ return -EFAULT;
+ }
+
+ /* Make sure that this is still a 24bit jump */
+ if (!is_bl_op(op)) {
+ pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op));
+ return -EINVAL;
+ }
+
+ /* Let's find where the pointer goes */
+ tramp = find_bl_target(ip, op);
+
+ pr_devel("ip:%lx jumps to %lx", ip, tramp);
+
+ if (setup_mcount_compiler_tramp(tramp)) {
+ /* Are other trampolines reachable? */
+ if (!find_ftrace_tramp(ip)) {
+ pr_err("No ftrace trampolines reachable from %ps\n",
+ (void *)ip);
+ return -EINVAL;
+ }
+ }
+
+ if (patch_instruction((u32 *)ip, ppc_inst(PPC_RAW_NOP()))) {
+ pr_err("Patching NOP failed.\n");
+ return -EPERM;
+ }
+
+ return 0;
+}
+
+int ftrace_make_nop(struct module *mod,
+ struct dyn_ftrace *rec, unsigned long addr)
+{
+ unsigned long ip = rec->ip;
+ ppc_inst_t old, new;
+
+ /*
+ * If the calling address is more that 24 bits away,
+ * then we had to use a trampoline to make the call.
+ * Otherwise just update the call site.
+ */
+ if (test_24bit_addr(ip, addr)) {
+ /* within range */
+ old = ftrace_call_replace(ip, addr, 1);
+ new = ppc_inst(PPC_RAW_NOP());
+ return ftrace_modify_code(ip, old, new);
+ } else if (core_kernel_text(ip)) {
+ return __ftrace_make_nop_kernel(rec, addr);
+ } else if (!IS_ENABLED(CONFIG_MODULES)) {
+ return -EINVAL;
+ }
+
+ /*
+ * Out of range jumps are called from modules.
+ * We should either already have a pointer to the module
+ * or it has been passed in.
+ */
+ if (!rec->arch.mod) {
+ if (!mod) {
+ pr_err("No module loaded addr=%lx\n", addr);
+ return -EFAULT;
+ }
+ rec->arch.mod = mod;
+ } else if (mod) {
+ if (mod != rec->arch.mod) {
+ pr_err("Record mod %p not equal to passed in mod %p\n",
+ rec->arch.mod, mod);
+ return -EINVAL;
+ }
+ /* nothing to do if mod == rec->arch.mod */
+ } else
+ mod = rec->arch.mod;
+
+ return __ftrace_make_nop(mod, rec, addr);
+}
+
+#ifdef CONFIG_MODULES
+/*
+ * Examine the existing instructions for __ftrace_make_call.
+ * They should effectively be a NOP, and follow formal constraints,
+ * depending on the ABI. Return false if they don't.
+ */
+static bool expected_nop_sequence(void *ip, ppc_inst_t op0, ppc_inst_t op1)
+{
+ if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
+ return ppc_inst_equal(op0, ppc_inst(PPC_RAW_NOP()));
+ else
+ return ppc_inst_equal(op0, ppc_inst(PPC_RAW_BRANCH(8))) &&
+ ppc_inst_equal(op1, ppc_inst(PPC_INST_LD_TOC));
+}
+
+static int
+__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+ ppc_inst_t op[2];
+ void *ip = (void *)rec->ip;
+ unsigned long entry, ptr, tramp;
+ struct module *mod = rec->arch.mod;
+
+ /* read where this goes */
+ if (copy_inst_from_kernel_nofault(op, ip))
+ return -EFAULT;
+
+ if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) &&
+ copy_inst_from_kernel_nofault(op + 1, ip + 4))
+ return -EFAULT;
+
+ if (!expected_nop_sequence(ip, op[0], op[1])) {
+ pr_err("Unexpected call sequence at %p: %08lx %08lx\n", ip,
+ ppc_inst_as_ulong(op[0]), ppc_inst_as_ulong(op[1]));
+ return -EINVAL;
+ }
+
+ /* If we never set up ftrace trampoline(s), then bail */
+ if (!mod->arch.tramp ||
+ (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && !mod->arch.tramp_regs)) {
+ pr_err("No ftrace trampoline\n");
+ return -EINVAL;
+ }
+
+ if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && rec->flags & FTRACE_FL_REGS)
+ tramp = mod->arch.tramp_regs;
+ else
+ tramp = mod->arch.tramp;
+
+ if (module_trampoline_target(mod, tramp, &ptr)) {
+ pr_err("Failed to get trampoline target\n");
+ return -EFAULT;
+ }
+
+ pr_devel("trampoline target %lx", ptr);
+
+ entry = ppc_global_function_entry((void *)addr);
+ /* This should match what was called */
+ if (ptr != entry) {
+ pr_err("addr %lx does not match expected %lx\n", ptr, entry);
+ return -EINVAL;
+ }
+
+ if (patch_branch(ip, tramp, BRANCH_SET_LINK)) {
+ pr_err("REL24 out of range!\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+#else
+static int __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+ return 0;
+}
+#endif /* CONFIG_MODULES */
+
+static int __ftrace_make_call_kernel(struct dyn_ftrace *rec, unsigned long addr)
+{
+ ppc_inst_t op;
+ void *ip = (void *)rec->ip;
+ unsigned long tramp, entry, ptr;
+
+ /* Make sure we're being asked to patch branch to a known ftrace addr */
+ entry = ppc_global_function_entry((void *)ftrace_caller);
+ ptr = ppc_global_function_entry((void *)addr);
+
+ if (ptr != entry && IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
+ entry = ppc_global_function_entry((void *)ftrace_regs_caller);
+
+ if (ptr != entry) {
+ pr_err("Unknown ftrace addr to patch: %ps\n", (void *)ptr);
+ return -EINVAL;
+ }
+
+ /* Make sure we have a nop */
+ if (copy_inst_from_kernel_nofault(&op, ip)) {
+ pr_err("Unable to read ftrace location %p\n", ip);
+ return -EFAULT;
+ }
+
+ if (!ppc_inst_equal(op, ppc_inst(PPC_RAW_NOP()))) {
+ pr_err("Unexpected call sequence at %p: %08lx\n",
+ ip, ppc_inst_as_ulong(op));
+ return -EINVAL;
+ }
+
+ tramp = find_ftrace_tramp((unsigned long)ip);
+ if (!tramp) {
+ pr_err("No ftrace trampolines reachable from %ps\n", ip);
+ return -EINVAL;
+ }
+
+ if (patch_branch(ip, tramp, BRANCH_SET_LINK)) {
+ pr_err("Error patching branch to ftrace tramp!\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+ unsigned long ip = rec->ip;
+ ppc_inst_t old, new;
+
+ /*
+ * If the calling address is more that 24 bits away,
+ * then we had to use a trampoline to make the call.
+ * Otherwise just update the call site.
+ */
+ if (test_24bit_addr(ip, addr)) {
+ /* within range */
+ old = ppc_inst(PPC_RAW_NOP());
+ new = ftrace_call_replace(ip, addr, 1);
+ return ftrace_modify_code(ip, old, new);
+ } else if (core_kernel_text(ip)) {
+ return __ftrace_make_call_kernel(rec, addr);
+ } else if (!IS_ENABLED(CONFIG_MODULES)) {
+ /* We should not get here without modules */
+ return -EINVAL;
+ }
+
+ /*
+ * Out of range jumps are called from modules.
+ * Being that we are converting from nop, it had better
+ * already have a module defined.
+ */
+ if (!rec->arch.mod) {
+ pr_err("No module loaded\n");
+ return -EINVAL;
+ }
+
+ return __ftrace_make_call(rec, addr);
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#ifdef CONFIG_MODULES
+static int
+__ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+ unsigned long addr)
+{
+ ppc_inst_t op;
+ unsigned long ip = rec->ip;
+ unsigned long entry, ptr, tramp;
+ struct module *mod = rec->arch.mod;
+
+ /* If we never set up ftrace trampolines, then bail */
+ if (!mod->arch.tramp || !mod->arch.tramp_regs) {
+ pr_err("No ftrace trampoline\n");
+ return -EINVAL;
+ }
+
+ /* read where this goes */
+ if (copy_inst_from_kernel_nofault(&op, (void *)ip)) {
+ pr_err("Fetching opcode failed.\n");
+ return -EFAULT;
+ }
+
+ /* Make sure that this is still a 24bit jump */
+ if (!is_bl_op(op)) {
+ pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op));
+ return -EINVAL;
+ }
+
+ /* lets find where the pointer goes */
+ tramp = find_bl_target(ip, op);
+ entry = ppc_global_function_entry((void *)old_addr);
+
+ pr_devel("ip:%lx jumps to %lx", ip, tramp);
+
+ if (tramp != entry) {
+ /* old_addr is not within range, so we must have used a trampoline */
+ if (module_trampoline_target(mod, tramp, &ptr)) {
+ pr_err("Failed to get trampoline target\n");
+ return -EFAULT;
+ }
+
+ pr_devel("trampoline target %lx", ptr);
+
+ /* This should match what was called */
+ if (ptr != entry) {
+ pr_err("addr %lx does not match expected %lx\n", ptr, entry);
+ return -EINVAL;
+ }
+ }
+
+ /* The new target may be within range */
+ if (test_24bit_addr(ip, addr)) {
+ /* within range */
+ if (patch_branch((u32 *)ip, addr, BRANCH_SET_LINK)) {
+ pr_err("REL24 out of range!\n");
+ return -EINVAL;
+ }
+
+ return 0;
+ }
+
+ if (rec->flags & FTRACE_FL_REGS)
+ tramp = mod->arch.tramp_regs;
+ else
+ tramp = mod->arch.tramp;
+
+ if (module_trampoline_target(mod, tramp, &ptr)) {
+ pr_err("Failed to get trampoline target\n");
+ return -EFAULT;
+ }
+
+ pr_devel("trampoline target %lx", ptr);
+
+ entry = ppc_global_function_entry((void *)addr);
+ /* This should match what was called */
+ if (ptr != entry) {
+ pr_err("addr %lx does not match expected %lx\n", ptr, entry);
+ return -EINVAL;
+ }
+
+ if (patch_branch((u32 *)ip, tramp, BRANCH_SET_LINK)) {
+ pr_err("REL24 out of range!\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+#else
+static int __ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr)
+{
+ return 0;
+}
+#endif
+
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+ unsigned long addr)
+{
+ unsigned long ip = rec->ip;
+ ppc_inst_t old, new;
+
+ /*
+ * If the calling address is more that 24 bits away,
+ * then we had to use a trampoline to make the call.
+ * Otherwise just update the call site.
+ */
+ if (test_24bit_addr(ip, addr) && test_24bit_addr(ip, old_addr)) {
+ /* within range */
+ old = ftrace_call_replace(ip, old_addr, 1);
+ new = ftrace_call_replace(ip, addr, 1);
+ return ftrace_modify_code(ip, old, new);
+ } else if (core_kernel_text(ip)) {
+ /*
+ * We always patch out of range locations to go to the regs
+ * variant, so there is nothing to do here
+ */
+ return 0;
+ } else if (!IS_ENABLED(CONFIG_MODULES)) {
+ /* We should not get here without modules */
+ return -EINVAL;
+ }
+
+ /*
+ * Out of range jumps are called from modules.
+ */
+ if (!rec->arch.mod) {
+ pr_err("No module loaded\n");
+ return -EINVAL;
+ }
+
+ return __ftrace_modify_call(rec, old_addr, addr);
+}
+#endif
+
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+ unsigned long ip = (unsigned long)(&ftrace_call);
+ ppc_inst_t old, new;
+ int ret;
+
+ old = ppc_inst_read((u32 *)&ftrace_call);
+ new = ftrace_call_replace(ip, (unsigned long)func, 1);
+ ret = ftrace_modify_code(ip, old, new);
+
+ /* Also update the regs callback function */
+ if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && !ret) {
+ ip = (unsigned long)(&ftrace_regs_call);
+ old = ppc_inst_read((u32 *)&ftrace_regs_call);
+ new = ftrace_call_replace(ip, (unsigned long)func, 1);
+ ret = ftrace_modify_code(ip, old, new);
+ }
+
+ return ret;
+}
+
+/*
+ * Use the default ftrace_modify_all_code, but without
+ * stop_machine().
+ */
+void arch_ftrace_update_code(int command)
+{
+ ftrace_modify_all_code(command);
+}
+
+#ifdef CONFIG_PPC64
+#define PACATOC offsetof(struct paca_struct, kernel_toc)
+
+extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[];
+
+void ftrace_free_init_tramp(void)
+{
+ int i;
+
+ for (i = 0; i < NUM_FTRACE_TRAMPS && ftrace_tramps[i]; i++)
+ if (ftrace_tramps[i] == (unsigned long)ftrace_tramp_init) {
+ ftrace_tramps[i] = 0;
+ return;
+ }
+}
+
+int __init ftrace_dyn_arch_init(void)
+{
+ int i;
+ unsigned int *tramp[] = { ftrace_tramp_text, ftrace_tramp_init };
+ u32 stub_insns[] = {
+ PPC_RAW_LD(_R12, _R13, PACATOC),
+ PPC_RAW_ADDIS(_R12, _R12, 0),
+ PPC_RAW_ADDI(_R12, _R12, 0),
+ PPC_RAW_MTCTR(_R12),
+ PPC_RAW_BCTR()
+ };
+ unsigned long addr;
+ long reladdr;
+
+ if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
+ addr = ppc_global_function_entry((void *)ftrace_regs_caller);
+ else
+ addr = ppc_global_function_entry((void *)ftrace_caller);
+
+ reladdr = addr - kernel_toc_addr();
+
+ if (reladdr >= SZ_2G || reladdr < -(long)SZ_2G) {
+ pr_err("Address of %ps out of range of kernel_toc.\n",
+ (void *)addr);
+ return -1;
+ }
+
+ for (i = 0; i < 2; i++) {
+ memcpy(tramp[i], stub_insns, sizeof(stub_insns));
+ tramp[i][1] |= PPC_HA(reladdr);
+ tramp[i][2] |= PPC_LO(reladdr);
+ add_ftrace_tramp((unsigned long)tramp[i]);
+ }
+
+ return 0;
+}
+#endif
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+extern void ftrace_graph_call(void);
+extern void ftrace_graph_stub(void);
+
+static int ftrace_modify_ftrace_graph_caller(bool enable)
+{
+ unsigned long ip = (unsigned long)(&ftrace_graph_call);
+ unsigned long addr = (unsigned long)(&ftrace_graph_caller);
+ unsigned long stub = (unsigned long)(&ftrace_graph_stub);
+ ppc_inst_t old, new;
+
+ if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS))
+ return 0;
+
+ old = ftrace_call_replace(ip, enable ? stub : addr, 0);
+ new = ftrace_call_replace(ip, enable ? addr : stub, 0);
+
+ return ftrace_modify_code(ip, old, new);
+}
+
+int ftrace_enable_ftrace_graph_caller(void)
+{
+ return ftrace_modify_ftrace_graph_caller(true);
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+ return ftrace_modify_ftrace_graph_caller(false);
+}
+
+/*
+ * Hook the return address and push it in the stack of return addrs
+ * in current thread info. Return the address we want to divert to.
+ */
+static unsigned long
+__prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp)
+{
+ unsigned long return_hooker;
+ int bit;
+
+ if (unlikely(ftrace_graph_is_dead()))
+ goto out;
+
+ if (unlikely(atomic_read(¤t->tracing_graph_pause)))
+ goto out;
+
+ bit = ftrace_test_recursion_trylock(ip, parent);
+ if (bit < 0)
+ goto out;
+
+ return_hooker = ppc_function_entry(return_to_handler);
+
+ if (!function_graph_enter(parent, ip, 0, (unsigned long *)sp))
+ parent = return_hooker;
+
+ ftrace_test_recursion_unlock(bit);
+out:
+ return parent;
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct ftrace_regs *fregs)
+{
+ fregs->regs.link = __prepare_ftrace_return(parent_ip, ip, fregs->regs.gpr[1]);
+}
+#else
+unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip,
+ unsigned long sp)
+{
+ return __prepare_ftrace_return(parent, ip, sp);
+}
+#endif
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+#ifdef CONFIG_PPC64_ELF_ABI_V1
+char *arch_ftrace_match_adjust(char *str, const char *search)
+{
+ if (str[0] == '.' && search[0] != '.')
+ return str + 1;
+ else
+ return str;
+}
+#endif /* CONFIG_PPC64_ELF_ABI_V1 */
--
2.40.1
^ permalink raw reply related [flat|nested] 16+ messages in thread* [RFC PATCH 03/15] powerpc/ftrace: Simplify function_graph support in ftrace.c
2023-06-07 16:55 [RFC PATCH 00/15] powerpc/ftrace: refactoring and support for -fpatchable-function-entry Naveen N Rao
2023-06-07 16:55 ` [RFC PATCH 01/15] powerpc/module: Remove unused .ftrace.tramp section Naveen N Rao
2023-06-07 16:55 ` [RFC PATCH 02/15] powerpc64/ftrace: Move ELFv1 and -pg support code into a separate file Naveen N Rao
@ 2023-06-07 16:55 ` Naveen N Rao
2023-06-07 16:55 ` [RFC PATCH 04/15] powerpc/ftrace: Use FTRACE_REGS_ADDR to identify the correct ftrace trampoline Naveen N Rao
` (11 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Naveen N Rao @ 2023-06-07 16:55 UTC (permalink / raw
To: linuxppc-dev; +Cc: Steven Rostedt, Nicholas Piggin
Since we now support DYNAMIC_FTRACE_WITH_ARGS across ppc32 and ppc64
ELFv2, we can simplify function_graph tracer support code in ftrace.c
Signed-off-by: Naveen N Rao <naveen@kernel.org>
---
arch/powerpc/kernel/trace/ftrace.c | 64 ++++--------------------------
1 file changed, 7 insertions(+), 57 deletions(-)
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 81a121b56c4d7f..f117124c30325f 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -790,44 +790,10 @@ int __init ftrace_dyn_arch_init(void)
#endif
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-
-extern void ftrace_graph_call(void);
-extern void ftrace_graph_stub(void);
-
-static int ftrace_modify_ftrace_graph_caller(bool enable)
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct ftrace_regs *fregs)
{
- unsigned long ip = (unsigned long)(&ftrace_graph_call);
- unsigned long addr = (unsigned long)(&ftrace_graph_caller);
- unsigned long stub = (unsigned long)(&ftrace_graph_stub);
- ppc_inst_t old, new;
-
- if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS))
- return 0;
-
- old = ftrace_call_replace(ip, enable ? stub : addr, 0);
- new = ftrace_call_replace(ip, enable ? addr : stub, 0);
-
- return ftrace_modify_code(ip, old, new);
-}
-
-int ftrace_enable_ftrace_graph_caller(void)
-{
- return ftrace_modify_ftrace_graph_caller(true);
-}
-
-int ftrace_disable_ftrace_graph_caller(void)
-{
- return ftrace_modify_ftrace_graph_caller(false);
-}
-
-/*
- * Hook the return address and push it in the stack of return addrs
- * in current thread info. Return the address we want to divert to.
- */
-static unsigned long
-__prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp)
-{
- unsigned long return_hooker;
+ unsigned long sp = fregs->regs.gpr[1];
int bit;
if (unlikely(ftrace_graph_is_dead()))
@@ -836,31 +802,15 @@ __prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp
if (unlikely(atomic_read(¤t->tracing_graph_pause)))
goto out;
- bit = ftrace_test_recursion_trylock(ip, parent);
+ bit = ftrace_test_recursion_trylock(ip, parent_ip);
if (bit < 0)
goto out;
- return_hooker = ppc_function_entry(return_to_handler);
-
- if (!function_graph_enter(parent, ip, 0, (unsigned long *)sp))
- parent = return_hooker;
+ if (!function_graph_enter(parent_ip, ip, 0, (unsigned long *)sp))
+ parent_ip = ppc_function_entry(return_to_handler);
ftrace_test_recursion_unlock(bit);
out:
- return parent;
+ fregs->regs.link = parent_ip;
}
-
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
-void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
- struct ftrace_ops *op, struct ftrace_regs *fregs)
-{
- fregs->regs.link = __prepare_ftrace_return(parent_ip, ip, fregs->regs.gpr[1]);
-}
-#else
-unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip,
- unsigned long sp)
-{
- return __prepare_ftrace_return(parent, ip, sp);
-}
-#endif
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
--
2.40.1
^ permalink raw reply related [flat|nested] 16+ messages in thread* [RFC PATCH 04/15] powerpc/ftrace: Use FTRACE_REGS_ADDR to identify the correct ftrace trampoline
2023-06-07 16:55 [RFC PATCH 00/15] powerpc/ftrace: refactoring and support for -fpatchable-function-entry Naveen N Rao
` (2 preceding siblings ...)
2023-06-07 16:55 ` [RFC PATCH 03/15] powerpc/ftrace: Simplify function_graph support in ftrace.c Naveen N Rao
@ 2023-06-07 16:55 ` Naveen N Rao
2023-06-07 16:55 ` [RFC PATCH 05/15] powerpc/ftrace: Extend ftrace support for large kernels to ppc32 Naveen N Rao
` (10 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Naveen N Rao @ 2023-06-07 16:55 UTC (permalink / raw
To: linuxppc-dev; +Cc: Steven Rostedt, Nicholas Piggin
Instead of keying off DYNAMIC_FTRACE_WITH_REGS, use FTRACE_REGS_ADDR to
identify the proper ftrace trampoline address to use.
Signed-off-by: Naveen N Rao <naveen@kernel.org>
---
arch/powerpc/kernel/trace/ftrace.c | 7 +------
1 file changed, 1 insertion(+), 6 deletions(-)
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index f117124c30325f..5aa36272617a03 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -745,14 +745,9 @@ int __init ftrace_dyn_arch_init(void)
};
#endif
- unsigned long addr;
+ unsigned long addr = FTRACE_REGS_ADDR;
long reladdr;
- if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
- addr = ppc_global_function_entry((void *)ftrace_regs_caller);
- else
- addr = ppc_global_function_entry((void *)ftrace_caller);
-
if (IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) {
for (i = 0; i < 2; i++) {
reladdr = addr - (unsigned long)tramp[i];
--
2.40.1
^ permalink raw reply related [flat|nested] 16+ messages in thread* [RFC PATCH 05/15] powerpc/ftrace: Extend ftrace support for large kernels to ppc32
2023-06-07 16:55 [RFC PATCH 00/15] powerpc/ftrace: refactoring and support for -fpatchable-function-entry Naveen N Rao
` (3 preceding siblings ...)
2023-06-07 16:55 ` [RFC PATCH 04/15] powerpc/ftrace: Use FTRACE_REGS_ADDR to identify the correct ftrace trampoline Naveen N Rao
@ 2023-06-07 16:55 ` Naveen N Rao
2023-06-07 16:55 ` [RFC PATCH 06/15] powerpc/ftrace: Consolidate ftrace support into fewer files Naveen N Rao
` (9 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Naveen N Rao @ 2023-06-07 16:55 UTC (permalink / raw
To: linuxppc-dev; +Cc: Steven Rostedt, Nicholas Piggin
Commit 67361cf8071286 ("powerpc/ftrace: Handle large kernel configs")
added ftrace support for ppc64 kernel images with a text section larger
than 32MB. The approach itself isn't specific to ppc64, so extend the
same to also work on ppc32.
While at it, reduce the space reserved for the stub from 64 bytes to 32
bytes since the different stub variants are all less than 8
instructions.
To reduce use of #ifdef, a stub implementation is provided for
kernel_toc_address() and -SZ_2G is cast to 'long long' to prevent
errors on ppc32.
Signed-off-by: Naveen N Rao <naveen@kernel.org>
---
arch/powerpc/include/asm/ftrace.h | 10 +++++--
arch/powerpc/include/asm/sections.h | 2 ++
arch/powerpc/kernel/trace/ftrace.c | 39 ++++++++++++++------------
arch/powerpc/kernel/trace/ftrace_low.S | 6 ++--
arch/powerpc/kernel/vmlinux.lds.S | 4 ---
5 files changed, 32 insertions(+), 29 deletions(-)
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index 91c049d51d0e10..1a5d365523e160 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -124,15 +124,19 @@ static inline u8 this_cpu_get_ftrace_enabled(void)
{
return get_paca()->ftrace_enabled;
}
-
-void ftrace_free_init_tramp(void);
#else /* CONFIG_PPC64 */
static inline void this_cpu_disable_ftrace(void) { }
static inline void this_cpu_enable_ftrace(void) { }
static inline void this_cpu_set_ftrace_enabled(u8 ftrace_enabled) { }
static inline u8 this_cpu_get_ftrace_enabled(void) { return 1; }
-static inline void ftrace_free_init_tramp(void) { }
#endif /* CONFIG_PPC64 */
+
+#ifdef CONFIG_FUNCTION_TRACER
+extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[];
+void ftrace_free_init_tramp(void);
+#else
+static inline void ftrace_free_init_tramp(void) { }
+#endif
#endif /* !__ASSEMBLY__ */
#endif /* _ASM_POWERPC_FTRACE */
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index 4e1f548c8d373d..ea26665f82cfc8 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -74,6 +74,8 @@ static inline int overlaps_kernel_text(unsigned long start, unsigned long end)
(unsigned long)_stext < end;
}
+#else
+static inline unsigned long kernel_toc_addr(void) { BUILD_BUG(); return -1UL; }
#endif
#endif /* __KERNEL__ */
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 5aa36272617a03..913c7aa63d3fa3 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -707,11 +707,6 @@ void arch_ftrace_update_code(int command)
ftrace_modify_all_code(command);
}
-#ifdef CONFIG_PPC64
-#define PACATOC offsetof(struct paca_struct, kernel_toc)
-
-extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[];
-
void ftrace_free_init_tramp(void)
{
int i;
@@ -725,28 +720,30 @@ void ftrace_free_init_tramp(void)
int __init ftrace_dyn_arch_init(void)
{
- int i;
unsigned int *tramp[] = { ftrace_tramp_text, ftrace_tramp_init };
-#ifdef CONFIG_PPC_KERNEL_PCREL
+ unsigned long addr = FTRACE_REGS_ADDR;
+ long reladdr;
+ int i;
u32 stub_insns[] = {
+#ifdef CONFIG_PPC_KERNEL_PCREL
/* pla r12,addr */
PPC_PREFIX_MLS | __PPC_PRFX_R(1),
PPC_INST_PADDI | ___PPC_RT(_R12),
PPC_RAW_MTCTR(_R12),
PPC_RAW_BCTR()
- };
-#else
- u32 stub_insns[] = {
- PPC_RAW_LD(_R12, _R13, PACATOC),
+#elif defined(CONFIG_PPC64)
+ PPC_RAW_LD(_R12, _R13, offsetof(struct paca_struct, kernel_toc)),
PPC_RAW_ADDIS(_R12, _R12, 0),
PPC_RAW_ADDI(_R12, _R12, 0),
PPC_RAW_MTCTR(_R12),
PPC_RAW_BCTR()
- };
+#else
+ PPC_RAW_LIS(_R12, 0),
+ PPC_RAW_ADDI(_R12, _R12, 0),
+ PPC_RAW_MTCTR(_R12),
+ PPC_RAW_BCTR()
#endif
-
- unsigned long addr = FTRACE_REGS_ADDR;
- long reladdr;
+ };
if (IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) {
for (i = 0; i < 2; i++) {
@@ -763,10 +760,10 @@ int __init ftrace_dyn_arch_init(void)
tramp[i][1] |= IMM_L(reladdr);
add_ftrace_tramp((unsigned long)tramp[i]);
}
- } else {
+ } else if (IS_ENABLED(CONFIG_PPC64)) {
reladdr = addr - kernel_toc_addr();
- if (reladdr >= (long)SZ_2G || reladdr < -(long)SZ_2G) {
+ if (reladdr >= (long)SZ_2G || reladdr < -(long long)SZ_2G) {
pr_err("Address of %ps out of range of kernel_toc.\n",
(void *)addr);
return -1;
@@ -778,11 +775,17 @@ int __init ftrace_dyn_arch_init(void)
tramp[i][2] |= PPC_LO(reladdr);
add_ftrace_tramp((unsigned long)tramp[i]);
}
+ } else {
+ for (i = 0; i < 2; i++) {
+ memcpy(tramp[i], stub_insns, sizeof(stub_insns));
+ tramp[i][0] |= PPC_HA(addr);
+ tramp[i][1] |= PPC_LO(addr);
+ add_ftrace_tramp((unsigned long)tramp[i]);
+ }
}
return 0;
}
-#endif
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
diff --git a/arch/powerpc/kernel/trace/ftrace_low.S b/arch/powerpc/kernel/trace/ftrace_low.S
index 294d1e05958aae..2fc7dd0a5ae968 100644
--- a/arch/powerpc/kernel/trace/ftrace_low.S
+++ b/arch/powerpc/kernel/trace/ftrace_low.S
@@ -10,19 +10,17 @@
#include <asm/ppc-opcode.h>
#include <asm/export.h>
-#ifdef CONFIG_PPC64
.pushsection ".tramp.ftrace.text","aw",@progbits;
.globl ftrace_tramp_text
ftrace_tramp_text:
- .space 64
+ .space 32
.popsection
.pushsection ".tramp.ftrace.init","aw",@progbits;
.globl ftrace_tramp_init
ftrace_tramp_init:
- .space 64
+ .space 32
.popsection
-#endif
_GLOBAL(mcount)
_GLOBAL(_mcount)
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 13614f0b269cf4..1c5970df323366 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -107,9 +107,7 @@ SECTIONS
#endif
/* careful! __ftr_alt_* sections need to be close to .text */
*(.text.hot .text.hot.* TEXT_MAIN .text.fixup .text.unlikely .text.unlikely.* .fixup __ftr_alt_* .ref.text);
-#ifdef CONFIG_PPC64
*(.tramp.ftrace.text);
-#endif
NOINSTR_TEXT
SCHED_TEXT
LOCK_TEXT
@@ -276,9 +274,7 @@ SECTIONS
*/
. = ALIGN(PAGE_SIZE);
_einittext = .;
-#ifdef CONFIG_PPC64
*(.tramp.ftrace.init);
-#endif
} :text
/* .exit.text is discarded at runtime, not link time,
--
2.40.1
^ permalink raw reply related [flat|nested] 16+ messages in thread* [RFC PATCH 06/15] powerpc/ftrace: Consolidate ftrace support into fewer files
2023-06-07 16:55 [RFC PATCH 00/15] powerpc/ftrace: refactoring and support for -fpatchable-function-entry Naveen N Rao
` (4 preceding siblings ...)
2023-06-07 16:55 ` [RFC PATCH 05/15] powerpc/ftrace: Extend ftrace support for large kernels to ppc32 Naveen N Rao
@ 2023-06-07 16:55 ` Naveen N Rao
2023-06-07 16:55 ` [RFC PATCH 07/15] powerpc/ftrace: Refactor ftrace_modify_code() Naveen N Rao
` (8 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Naveen N Rao @ 2023-06-07 16:55 UTC (permalink / raw
To: linuxppc-dev; +Cc: Steven Rostedt, Nicholas Piggin
ftrace_low.S has just the _mcount stub and return_to_handler(). Merge
this back into ftrace_mprofile.S and ftrace_64_pg.S to keep all ftrace
code together, and to allow those to evolve independently.
ftrace_mprofile.S is also not an entirely accurate name since this also
holds ppc32 code. This will be all the more incorrect once support for
-fpatchable-function-entry is added. Rename files here to more
accurately describe the code:
- ftrace_mprofile.S is renamed to ftrace_entry.S
- ftrace_pg.c is renamed to ftrace_64_pg.c
- ftrace_64_pg.S is rename to ftrace_64_pg_entry.S
Signed-off-by: Naveen N Rao <naveen@kernel.org>
---
arch/powerpc/kernel/trace/Makefile | 17 +++--
arch/powerpc/kernel/trace/ftrace_64_pg.S | 67 -------------------
.../trace/{ftrace_pg.c => ftrace_64_pg.c} | 0
.../{ftrace_low.S => ftrace_64_pg_entry.S} | 58 +++++++++++++++-
.../{ftrace_mprofile.S => ftrace_entry.S} | 65 ++++++++++++++++++
5 files changed, 130 insertions(+), 77 deletions(-)
delete mode 100644 arch/powerpc/kernel/trace/ftrace_64_pg.S
rename arch/powerpc/kernel/trace/{ftrace_pg.c => ftrace_64_pg.c} (100%)
rename arch/powerpc/kernel/trace/{ftrace_low.S => ftrace_64_pg_entry.S} (55%)
rename arch/powerpc/kernel/trace/{ftrace_mprofile.S => ftrace_entry.S} (83%)
diff --git a/arch/powerpc/kernel/trace/Makefile b/arch/powerpc/kernel/trace/Makefile
index 342a2d1ae86cd0..125f4ca588b98a 100644
--- a/arch/powerpc/kernel/trace/Makefile
+++ b/arch/powerpc/kernel/trace/Makefile
@@ -6,16 +6,15 @@
ifdef CONFIG_FUNCTION_TRACER
# do not trace tracer code
CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE)
-CFLAGS_REMOVE_ftrace_pg.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_ftrace_64_pg.o = $(CC_FLAGS_FTRACE)
endif
-obj32-$(CONFIG_FUNCTION_TRACER) += ftrace_mprofile.o ftrace.o
+obj32-$(CONFIG_FUNCTION_TRACER) += ftrace.o ftrace_entry.o
ifdef CONFIG_MPROFILE_KERNEL
-obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_mprofile.o ftrace.o
+obj64-$(CONFIG_FUNCTION_TRACER) += ftrace.o ftrace_entry.o
else
-obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_64_pg.o ftrace_pg.o
+obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_64_pg.o ftrace_64_pg_entry.o
endif
-obj-$(CONFIG_FUNCTION_TRACER) += ftrace_low.o
obj-$(CONFIG_TRACING) += trace_clock.o
obj-$(CONFIG_PPC64) += $(obj64-y)
@@ -26,7 +25,7 @@ GCOV_PROFILE_ftrace.o := n
KCOV_INSTRUMENT_ftrace.o := n
KCSAN_SANITIZE_ftrace.o := n
UBSAN_SANITIZE_ftrace.o := n
-GCOV_PROFILE_ftrace_pg.o := n
-KCOV_INSTRUMENT_ftrace_pg.o := n
-KCSAN_SANITIZE_ftrace_pg.o := n
-UBSAN_SANITIZE_ftrace_pg.o := n
+GCOV_PROFILE_ftrace_64_pg.o := n
+KCOV_INSTRUMENT_ftrace_64_pg.o := n
+KCSAN_SANITIZE_ftrace_64_pg.o := n
+UBSAN_SANITIZE_ftrace_64_pg.o := n
diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.S b/arch/powerpc/kernel/trace/ftrace_64_pg.S
deleted file mode 100644
index 6708e24db0aba8..00000000000000
--- a/arch/powerpc/kernel/trace/ftrace_64_pg.S
+++ /dev/null
@@ -1,67 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Split from ftrace_64.S
- */
-
-#include <linux/magic.h>
-#include <asm/ppc_asm.h>
-#include <asm/asm-offsets.h>
-#include <asm/ftrace.h>
-#include <asm/ppc-opcode.h>
-#include <asm/export.h>
-
-_GLOBAL_TOC(ftrace_caller)
- lbz r3, PACA_FTRACE_ENABLED(r13)
- cmpdi r3, 0
- beqlr
-
- /* Taken from output of objdump from lib64/glibc */
- mflr r3
- ld r11, 0(r1)
- stdu r1, -112(r1)
- std r3, 128(r1)
- ld r4, 16(r11)
- subi r3, r3, MCOUNT_INSN_SIZE
-.globl ftrace_call
-ftrace_call:
- bl ftrace_stub
- nop
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-.globl ftrace_graph_call
-ftrace_graph_call:
- b ftrace_graph_stub
-_GLOBAL(ftrace_graph_stub)
-#endif
- ld r0, 128(r1)
- mtlr r0
- addi r1, r1, 112
-
-_GLOBAL(ftrace_stub)
- blr
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-_GLOBAL(ftrace_graph_caller)
- addi r5, r1, 112
- /* load r4 with local address */
- ld r4, 128(r1)
- subi r4, r4, MCOUNT_INSN_SIZE
-
- /* Grab the LR out of the caller stack frame */
- ld r11, 112(r1)
- ld r3, 16(r11)
-
- bl prepare_ftrace_return
- nop
-
- /*
- * prepare_ftrace_return gives us the address we divert to.
- * Change the LR in the callers stack frame to this.
- */
- ld r11, 112(r1)
- std r3, 16(r11)
-
- ld r0, 128(r1)
- mtlr r0
- addi r1, r1, 112
- blr
-#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/powerpc/kernel/trace/ftrace_pg.c b/arch/powerpc/kernel/trace/ftrace_64_pg.c
similarity index 100%
rename from arch/powerpc/kernel/trace/ftrace_pg.c
rename to arch/powerpc/kernel/trace/ftrace_64_pg.c
diff --git a/arch/powerpc/kernel/trace/ftrace_low.S b/arch/powerpc/kernel/trace/ftrace_64_pg_entry.S
similarity index 55%
rename from arch/powerpc/kernel/trace/ftrace_low.S
rename to arch/powerpc/kernel/trace/ftrace_64_pg_entry.S
index 2fc7dd0a5ae968..81dbaf70b1513a 100644
--- a/arch/powerpc/kernel/trace/ftrace_low.S
+++ b/arch/powerpc/kernel/trace/ftrace_64_pg_entry.S
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
- * Split from entry_64.S
+ * Split from ftrace_64.S
*/
#include <linux/magic.h>
@@ -10,6 +10,62 @@
#include <asm/ppc-opcode.h>
#include <asm/export.h>
+_GLOBAL_TOC(ftrace_caller)
+ lbz r3, PACA_FTRACE_ENABLED(r13)
+ cmpdi r3, 0
+ beqlr
+
+ /* Taken from output of objdump from lib64/glibc */
+ mflr r3
+ ld r11, 0(r1)
+ stdu r1, -112(r1)
+ std r3, 128(r1)
+ ld r4, 16(r11)
+ subi r3, r3, MCOUNT_INSN_SIZE
+.globl ftrace_call
+ftrace_call:
+ bl ftrace_stub
+ nop
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+.globl ftrace_graph_call
+ftrace_graph_call:
+ b ftrace_graph_stub
+_GLOBAL(ftrace_graph_stub)
+#endif
+ ld r0, 128(r1)
+ mtlr r0
+ addi r1, r1, 112
+
+_GLOBAL(ftrace_stub)
+ blr
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+_GLOBAL(ftrace_graph_caller)
+ addi r5, r1, 112
+ /* load r4 with local address */
+ ld r4, 128(r1)
+ subi r4, r4, MCOUNT_INSN_SIZE
+
+ /* Grab the LR out of the caller stack frame */
+ ld r11, 112(r1)
+ ld r3, 16(r11)
+
+ bl prepare_ftrace_return
+ nop
+
+ /*
+ * prepare_ftrace_return gives us the address we divert to.
+ * Change the LR in the callers stack frame to this.
+ */
+ ld r11, 112(r1)
+ std r3, 16(r11)
+
+ ld r0, 128(r1)
+ mtlr r0
+ addi r1, r1, 112
+ blr
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
.pushsection ".tramp.ftrace.text","aw",@progbits;
.globl ftrace_tramp_text
ftrace_tramp_text:
diff --git a/arch/powerpc/kernel/trace/ftrace_mprofile.S b/arch/powerpc/kernel/trace/ftrace_entry.S
similarity index 83%
rename from arch/powerpc/kernel/trace/ftrace_mprofile.S
rename to arch/powerpc/kernel/trace/ftrace_entry.S
index ffb1db38684998..e8339706e735b1 100644
--- a/arch/powerpc/kernel/trace/ftrace_mprofile.S
+++ b/arch/powerpc/kernel/trace/ftrace_entry.S
@@ -249,3 +249,68 @@ livepatch_handler:
/* Return to original caller of live patched function */
blr
#endif /* CONFIG_LIVEPATCH */
+
+_GLOBAL(mcount)
+_GLOBAL(_mcount)
+EXPORT_SYMBOL(_mcount)
+ mflr r12
+ mtctr r12
+ mtlr r0
+ bctr
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+_GLOBAL(return_to_handler)
+ /* need to save return values */
+#ifdef CONFIG_PPC64
+ std r4, -32(r1)
+ std r3, -24(r1)
+ /* save TOC */
+ std r2, -16(r1)
+ std r31, -8(r1)
+ mr r31, r1
+ stdu r1, -112(r1)
+
+ /*
+ * We might be called from a module.
+ * Switch to our TOC to run inside the core kernel.
+ */
+ LOAD_PACA_TOC()
+#else
+ stwu r1, -16(r1)
+ stw r3, 8(r1)
+ stw r4, 12(r1)
+#endif
+
+ bl ftrace_return_to_handler
+ nop
+
+ /* return value has real return address */
+ mtlr r3
+
+#ifdef CONFIG_PPC64
+ ld r1, 0(r1)
+ ld r4, -32(r1)
+ ld r3, -24(r1)
+ ld r2, -16(r1)
+ ld r31, -8(r1)
+#else
+ lwz r3, 8(r1)
+ lwz r4, 12(r1)
+ addi r1, r1, 16
+#endif
+
+ /* Jump back to real return address */
+ blr
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+.pushsection ".tramp.ftrace.text","aw",@progbits;
+.globl ftrace_tramp_text
+ftrace_tramp_text:
+ .space 32
+.popsection
+
+.pushsection ".tramp.ftrace.init","aw",@progbits;
+.globl ftrace_tramp_init
+ftrace_tramp_init:
+ .space 32
+.popsection
--
2.40.1
^ permalink raw reply related [flat|nested] 16+ messages in thread* [RFC PATCH 07/15] powerpc/ftrace: Refactor ftrace_modify_code()
2023-06-07 16:55 [RFC PATCH 00/15] powerpc/ftrace: refactoring and support for -fpatchable-function-entry Naveen N Rao
` (5 preceding siblings ...)
2023-06-07 16:55 ` [RFC PATCH 06/15] powerpc/ftrace: Consolidate ftrace support into fewer files Naveen N Rao
@ 2023-06-07 16:55 ` Naveen N Rao
2023-06-07 16:55 ` [RFC PATCH 08/15] powerpc/ftrace: Stop re-purposing linker generated long branches for ftrace Naveen N Rao
` (7 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Naveen N Rao @ 2023-06-07 16:55 UTC (permalink / raw
To: linuxppc-dev; +Cc: Steven Rostedt, Nicholas Piggin
Split up ftrace_modify_code() into a few helpers for future use. Also
update error messages accordingly.
Signed-off-by: Naveen N Rao <naveen@kernel.org>
---
arch/powerpc/kernel/trace/ftrace.c | 51 +++++++++++++++++-------------
1 file changed, 29 insertions(+), 22 deletions(-)
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 913c7aa63d3fa3..ef4e49c2c37781 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -50,32 +50,39 @@ ftrace_call_replace(unsigned long ip, unsigned long addr, int link)
return op;
}
-static inline int
-ftrace_modify_code(unsigned long ip, ppc_inst_t old, ppc_inst_t new)
+static inline int ftrace_read_inst(unsigned long ip, ppc_inst_t *op)
{
- ppc_inst_t replaced;
-
- /*
- * Note:
- * We are paranoid about modifying text, as if a bug was to happen, it
- * could cause us to read or write to someplace that could cause harm.
- * Carefully read and modify the code with probe_kernel_*(), and make
- * sure what we read is what we expected it to be before modifying it.
- */
-
- /* read the text we want to modify */
- if (copy_inst_from_kernel_nofault(&replaced, (void *)ip))
+ if (copy_inst_from_kernel_nofault(op, (void *)ip)) {
+ pr_err("0x%lx: fetching instruction failed\n", ip);
return -EFAULT;
-
- /* Make sure it is what we expect it to be */
- if (!ppc_inst_equal(replaced, old)) {
- pr_err("%p: replaced (%08lx) != old (%08lx)", (void *)ip,
- ppc_inst_as_ulong(replaced), ppc_inst_as_ulong(old));
- return -EINVAL;
}
- /* replace the text with the new text */
- return patch_instruction((u32 *)ip, new);
+ return 0;
+}
+
+static inline int ftrace_validate_inst(unsigned long ip, ppc_inst_t inst)
+{
+ ppc_inst_t op;
+ int ret;
+
+ ret = ftrace_read_inst(ip, &op);
+ if (!ret && !ppc_inst_equal(op, inst)) {
+ pr_err("0x%lx: expected (%08lx) != found (%08lx)\n",
+ ip, ppc_inst_as_ulong(inst), ppc_inst_as_ulong(op));
+ ret = -EINVAL;
+ }
+
+ return ret;
+}
+
+static inline int ftrace_modify_code(unsigned long ip, ppc_inst_t old, ppc_inst_t new)
+{
+ int ret = ftrace_validate_inst(ip, old);
+
+ if (!ret)
+ ret = patch_instruction((u32 *)ip, new);
+
+ return ret;
}
/*
--
2.40.1
^ permalink raw reply related [flat|nested] 16+ messages in thread* [RFC PATCH 08/15] powerpc/ftrace: Stop re-purposing linker generated long branches for ftrace
2023-06-07 16:55 [RFC PATCH 00/15] powerpc/ftrace: refactoring and support for -fpatchable-function-entry Naveen N Rao
` (6 preceding siblings ...)
2023-06-07 16:55 ` [RFC PATCH 07/15] powerpc/ftrace: Refactor ftrace_modify_code() Naveen N Rao
@ 2023-06-07 16:55 ` Naveen N Rao
2023-06-07 16:55 ` [RFC PATCH 09/15] powerpc/ftrace: Add separate ftrace_init_nop() with additional validation Naveen N Rao
` (6 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Naveen N Rao @ 2023-06-07 16:55 UTC (permalink / raw
To: linuxppc-dev; +Cc: Steven Rostedt, Nicholas Piggin
Commit 67361cf8071286 ("powerpc/ftrace: Handle large kernel configs")
added ftrace support for ppc64 kernel images with a text section larger
than 32MB. The patch did two things:
1. Add stubs at the end of .text to branch into ftrace_[regs_]caller for
functions that were out of branch range.
2. Re-purpose linker-generated long branches to _mcount to instead branch
to ftrace_[regs_]caller.
Before that, we only supported kernel .text up to ~32MB. With the above,
we now support up to ~96MB:
- The first 32MB of kernel text can branch directly into
ftrace_[regs_]caller since that symbol is usually at the beginning.
- The modified long_branch from (2) above is used by the next 32MB of
kernel text.
- The next 32MB of kernel text can use the stub at the end of text to
branch back to ftrace_[regs_]caller.
While re-purposing the long branch works in practice, it still restricts
ftrace to kernel text up to ~96MB. The stub at the end of kernel text
from (1) already enables us to extend ftrace support for kernel text
up to 64MB, which fulfils the original requirement. Further, once we
switch to -fpatchable-function-entry, there will not be a long branch
that we can use.
Stop re-purposing the linker-generated long branches for ftrace to
simplify the code. If there are good reasons to support ftrace on
kernels beyond 64MB, we can consider adding support by using
-fpatchable-function-entry.
Signed-off-by: Naveen N Rao <naveen@kernel.org>
---
arch/powerpc/kernel/trace/ftrace.c | 110 +++++------------------------
1 file changed, 17 insertions(+), 93 deletions(-)
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index ef4e49c2c37781..278bf8e52b6e89 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -28,13 +28,7 @@
#include <asm/syscall.h>
#include <asm/inst.h>
-/*
- * We generally only have a single long_branch tramp and at most 2 or 3 plt
- * tramps generated. But, we don't use the plt tramps currently. We also allot
- * 2 tramps after .text and .init.text. So, we only end up with around 3 usable
- * tramps in total. Set aside 8 just to be sure.
- */
-#define NUM_FTRACE_TRAMPS 8
+#define NUM_FTRACE_TRAMPS 2
static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS];
static ppc_inst_t
@@ -100,11 +94,6 @@ static int is_bl_op(ppc_inst_t op)
return (ppc_inst_val(op) & ~PPC_LI_MASK) == PPC_RAW_BL(0);
}
-static int is_b_op(ppc_inst_t op)
-{
- return (ppc_inst_val(op) & ~PPC_LI_MASK) == PPC_RAW_BRANCH(0);
-}
-
static unsigned long find_bl_target(unsigned long ip, ppc_inst_t op)
{
int offset;
@@ -227,11 +216,7 @@ static unsigned long find_ftrace_tramp(unsigned long ip)
{
int i;
- /*
- * We have the compiler generated long_branch tramps at the end
- * and we prefer those
- */
- for (i = NUM_FTRACE_TRAMPS - 1; i >= 0; i--)
+ for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
if (!ftrace_tramps[i])
continue;
else if (is_offset_in_branch_range(ftrace_tramps[i] - ip))
@@ -240,75 +225,6 @@ static unsigned long find_ftrace_tramp(unsigned long ip)
return 0;
}
-static int add_ftrace_tramp(unsigned long tramp)
-{
- int i;
-
- for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
- if (!ftrace_tramps[i]) {
- ftrace_tramps[i] = tramp;
- return 0;
- }
-
- return -1;
-}
-
-/*
- * If this is a compiler generated long_branch trampoline (essentially, a
- * trampoline that has a branch to _mcount()), we re-write the branch to
- * instead go to ftrace_[regs_]caller() and note down the location of this
- * trampoline.
- */
-static int setup_mcount_compiler_tramp(unsigned long tramp)
-{
- int i;
- ppc_inst_t op;
- unsigned long ptr;
-
- /* Is this a known long jump tramp? */
- for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
- if (ftrace_tramps[i] == tramp)
- return 0;
-
- /* New trampoline -- read where this goes */
- if (copy_inst_from_kernel_nofault(&op, (void *)tramp)) {
- pr_debug("Fetching opcode failed.\n");
- return -1;
- }
-
- /* Is this a 24 bit branch? */
- if (!is_b_op(op)) {
- pr_debug("Trampoline is not a long branch tramp.\n");
- return -1;
- }
-
- /* lets find where the pointer goes */
- ptr = find_bl_target(tramp, op);
-
- if (ptr != ppc_global_function_entry((void *)_mcount)) {
- pr_debug("Trampoline target %p is not _mcount\n", (void *)ptr);
- return -1;
- }
-
- /* Let's re-write the tramp to go to ftrace_[regs_]caller */
- if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
- ptr = ppc_global_function_entry((void *)ftrace_regs_caller);
- else
- ptr = ppc_global_function_entry((void *)ftrace_caller);
-
- if (patch_branch((u32 *)tramp, ptr, 0)) {
- pr_debug("REL24 out of range!\n");
- return -1;
- }
-
- if (add_ftrace_tramp(tramp)) {
- pr_debug("No tramp locations left\n");
- return -1;
- }
-
- return 0;
-}
-
static int __ftrace_make_nop_kernel(struct dyn_ftrace *rec, unsigned long addr)
{
unsigned long tramp, ip = rec->ip;
@@ -331,13 +247,10 @@ static int __ftrace_make_nop_kernel(struct dyn_ftrace *rec, unsigned long addr)
pr_devel("ip:%lx jumps to %lx", ip, tramp);
- if (setup_mcount_compiler_tramp(tramp)) {
- /* Are other trampolines reachable? */
- if (!find_ftrace_tramp(ip)) {
- pr_err("No ftrace trampolines reachable from %ps\n",
- (void *)ip);
- return -EINVAL;
- }
+ /* Are ftrace trampolines reachable? */
+ if (!find_ftrace_tramp(ip)) {
+ pr_err("No ftrace trampolines reachable from %ps\n", (void *)ip);
+ return -EINVAL;
}
if (patch_instruction((u32 *)ip, ppc_inst(PPC_RAW_NOP()))) {
@@ -725,6 +638,17 @@ void ftrace_free_init_tramp(void)
}
}
+static void __init add_ftrace_tramp(unsigned long tramp)
+{
+ int i;
+
+ for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
+ if (!ftrace_tramps[i]) {
+ ftrace_tramps[i] = tramp;
+ return;
+ }
+}
+
int __init ftrace_dyn_arch_init(void)
{
unsigned int *tramp[] = { ftrace_tramp_text, ftrace_tramp_init };
--
2.40.1
^ permalink raw reply related [flat|nested] 16+ messages in thread* [RFC PATCH 09/15] powerpc/ftrace: Add separate ftrace_init_nop() with additional validation
2023-06-07 16:55 [RFC PATCH 00/15] powerpc/ftrace: refactoring and support for -fpatchable-function-entry Naveen N Rao
` (7 preceding siblings ...)
2023-06-07 16:55 ` [RFC PATCH 08/15] powerpc/ftrace: Stop re-purposing linker generated long branches for ftrace Naveen N Rao
@ 2023-06-07 16:55 ` Naveen N Rao
2023-06-07 16:55 ` [RFC PATCH 10/15] powerpc/ftrace: Simplify ftrace_make_nop() Naveen N Rao
` (5 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Naveen N Rao @ 2023-06-07 16:55 UTC (permalink / raw
To: linuxppc-dev; +Cc: Steven Rostedt, Nicholas Piggin
Currently, we validate instructions around the ftrace location every
time we have to enable/disable ftrace. Introduce ftrace_init_nop() to
instead perform all the validation during ftrace initialization. This
allows us to simply patch the necessary instructions during
enabling/disabling ftrace.
Signed-off-by: Naveen N Rao <naveen@kernel.org>
---
arch/powerpc/include/asm/ftrace.h | 6 +++
arch/powerpc/kernel/trace/ftrace.c | 71 ++++++++++++++++++++++++++++++
2 files changed, 77 insertions(+)
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index 1a5d365523e160..89fbae3caa1fc2 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -29,11 +29,17 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip,
unsigned long sp);
+struct module;
+struct dyn_ftrace;
struct dyn_arch_ftrace {
struct module *mod;
};
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
+#define ftrace_need_init_nop() (true)
+int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
+#define ftrace_init_nop ftrace_init_nop
+
struct ftrace_regs {
struct pt_regs regs;
};
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 278bf8e52b6e89..c0d185742c23ca 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -31,6 +31,16 @@
#define NUM_FTRACE_TRAMPS 2
static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS];
+static ppc_inst_t ftrace_create_branch_inst(unsigned long ip, unsigned long addr, int link)
+{
+ ppc_inst_t op;
+
+ WARN_ON(!is_offset_in_branch_range(addr - ip));
+ create_branch(&op, (u32 *)ip, addr, link ? BRANCH_SET_LINK : 0);
+
+ return op;
+}
+
static ppc_inst_t
ftrace_call_replace(unsigned long ip, unsigned long addr, int link)
{
@@ -597,6 +607,67 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
}
#endif
+int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
+{
+ unsigned long addr, ip = rec->ip;
+ ppc_inst_t old, new;
+ int ret = 0;
+
+ /* Verify instructions surrounding the ftrace location */
+ if (IS_ENABLED(CONFIG_PPC32)) {
+ /* Expected sequence: 'mflr r0', 'stw r0,4(r1)', 'bl _mcount' */
+ ret = ftrace_validate_inst(ip - 8, ppc_inst(PPC_RAW_MFLR(_R0)));
+ if (!ret)
+ ret = ftrace_validate_inst(ip - 4, ppc_inst(PPC_RAW_STW(_R0, _R1, 4)));
+ } else if (IS_ENABLED(CONFIG_MPROFILE_KERNEL)) {
+ /* Expected sequence: 'mflr r0', ['std r0,16(r1)'], 'bl _mcount' */
+ ret = ftrace_validate_inst(ip - 4, ppc_inst(PPC_RAW_MFLR(_R0)));
+ if (ret) {
+ ret = ftrace_validate_inst(ip - 4, ppc_inst(PPC_RAW_STD(_R0, _R1, 16)));
+ ret |= ftrace_validate_inst(ip - 8, ppc_inst(PPC_RAW_MFLR(_R0)));
+ }
+ } else {
+ return -EINVAL;
+ }
+
+ if (ret)
+ return ret;
+
+ if (!core_kernel_text(ip)) {
+ if (!mod) {
+ pr_err("0x%lx: No module provided for non-kernel address\n", ip);
+ return -EFAULT;
+ }
+ rec->arch.mod = mod;
+ }
+
+ /* Nop-out the ftrace location */
+ new = ppc_inst(PPC_RAW_NOP());
+ addr = MCOUNT_ADDR;
+ if (is_offset_in_branch_range(addr - ip)) {
+ /* Within range */
+ old = ftrace_create_branch_inst(ip, addr, 1);
+ ret = ftrace_modify_code(ip, old, new);
+ } else if (core_kernel_text(ip) || (IS_ENABLED(CONFIG_MODULES) && mod)) {
+ /*
+ * We would be branching to a linker-generated stub, or to the module _mcount
+ * stub. Let's just confirm we have a 'bl' here.
+ */
+ ret = ftrace_read_inst(ip, &old);
+ if (ret)
+ return ret;
+ if (!is_bl_op(old)) {
+ pr_err("0x%lx: expected (bl) != found (%08lx)\n", ip, ppc_inst_as_ulong(old));
+ return -EINVAL;
+ }
+ ret = patch_instruction((u32 *)ip, new);
+ } else {
+ return -EINVAL;
+ }
+
+ return ret;
+}
+
int ftrace_update_ftrace_func(ftrace_func_t func)
{
unsigned long ip = (unsigned long)(&ftrace_call);
--
2.40.1
^ permalink raw reply related [flat|nested] 16+ messages in thread* [RFC PATCH 10/15] powerpc/ftrace: Simplify ftrace_make_nop()
2023-06-07 16:55 [RFC PATCH 00/15] powerpc/ftrace: refactoring and support for -fpatchable-function-entry Naveen N Rao
` (8 preceding siblings ...)
2023-06-07 16:55 ` [RFC PATCH 09/15] powerpc/ftrace: Add separate ftrace_init_nop() with additional validation Naveen N Rao
@ 2023-06-07 16:55 ` Naveen N Rao
2023-06-07 16:55 ` [RFC PATCH 11/15] powerpc/ftrace: Simplify ftrace_make_call() Naveen N Rao
` (4 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Naveen N Rao @ 2023-06-07 16:55 UTC (permalink / raw
To: linuxppc-dev; +Cc: Steven Rostedt, Nicholas Piggin
Now that we validate the ftrace location during initialization in
ftrace_init_nop(), we can simplify ftrace_make_nop() to patch-in the nop
without worrying about the instructions surrounding the ftrace location.
Note that we continue to ensure that we have a bl to
ftrace_[regs_]caller at the ftrace location before nop-ing it out.
Signed-off-by: Naveen N Rao <naveen@kernel.org>
---
arch/powerpc/kernel/trace/ftrace.c | 220 +++++------------------------
1 file changed, 32 insertions(+), 188 deletions(-)
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index c0d185742c23ca..67773cd14da71a 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -116,112 +116,6 @@ static unsigned long find_bl_target(unsigned long ip, ppc_inst_t op)
return ip + (long)offset;
}
-#ifdef CONFIG_MODULES
-static int
-__ftrace_make_nop(struct module *mod,
- struct dyn_ftrace *rec, unsigned long addr)
-{
- unsigned long entry, ptr, tramp;
- unsigned long ip = rec->ip;
- ppc_inst_t op, pop;
-
- /* read where this goes */
- if (copy_inst_from_kernel_nofault(&op, (void *)ip)) {
- pr_err("Fetching opcode failed.\n");
- return -EFAULT;
- }
-
- /* Make sure that this is still a 24bit jump */
- if (!is_bl_op(op)) {
- pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op));
- return -EINVAL;
- }
-
- /* lets find where the pointer goes */
- tramp = find_bl_target(ip, op);
-
- pr_devel("ip:%lx jumps to %lx", ip, tramp);
-
- if (module_trampoline_target(mod, tramp, &ptr)) {
- pr_err("Failed to get trampoline target\n");
- return -EFAULT;
- }
-
- pr_devel("trampoline target %lx", ptr);
-
- entry = ppc_global_function_entry((void *)addr);
- /* This should match what was called */
- if (ptr != entry) {
- pr_err("addr %lx does not match expected %lx\n", ptr, entry);
- return -EINVAL;
- }
-
- if (IS_ENABLED(CONFIG_MPROFILE_KERNEL)) {
- if (copy_inst_from_kernel_nofault(&op, (void *)(ip - 4))) {
- pr_err("Fetching instruction at %lx failed.\n", ip - 4);
- return -EFAULT;
- }
-
- /* We expect either a mflr r0, or a std r0, LRSAVE(r1) */
- if (!ppc_inst_equal(op, ppc_inst(PPC_RAW_MFLR(_R0))) &&
- !ppc_inst_equal(op, ppc_inst(PPC_INST_STD_LR))) {
- pr_err("Unexpected instruction %08lx around bl _mcount\n",
- ppc_inst_as_ulong(op));
- return -EINVAL;
- }
- } else if (IS_ENABLED(CONFIG_PPC64)) {
- /*
- * Check what is in the next instruction. We can see ld r2,40(r1), but
- * on first pass after boot we will see mflr r0.
- */
- if (copy_inst_from_kernel_nofault(&op, (void *)(ip + 4))) {
- pr_err("Fetching op failed.\n");
- return -EFAULT;
- }
-
- if (!ppc_inst_equal(op, ppc_inst(PPC_INST_LD_TOC))) {
- pr_err("Expected %08lx found %08lx\n", PPC_INST_LD_TOC,
- ppc_inst_as_ulong(op));
- return -EINVAL;
- }
- }
-
- /*
- * When using -mprofile-kernel or PPC32 there is no load to jump over.
- *
- * Otherwise our original call site looks like:
- *
- * bl <tramp>
- * ld r2,XX(r1)
- *
- * Milton Miller pointed out that we can not simply nop the branch.
- * If a task was preempted when calling a trace function, the nops
- * will remove the way to restore the TOC in r2 and the r2 TOC will
- * get corrupted.
- *
- * Use a b +8 to jump over the load.
- * XXX: could make PCREL depend on MPROFILE_KERNEL
- * XXX: check PCREL && MPROFILE_KERNEL calling sequence
- */
- if (IS_ENABLED(CONFIG_MPROFILE_KERNEL) || IS_ENABLED(CONFIG_PPC32))
- pop = ppc_inst(PPC_RAW_NOP());
- else
- pop = ppc_inst(PPC_RAW_BRANCH(8)); /* b +8 */
-
- if (patch_instruction((u32 *)ip, pop)) {
- pr_err("Patching NOP failed.\n");
- return -EPERM;
- }
-
- return 0;
-}
-#else
-static int __ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr)
-{
- return 0;
-}
-#endif /* CONFIG_MODULES */
-
static unsigned long find_ftrace_tramp(unsigned long ip)
{
int i;
@@ -235,88 +129,6 @@ static unsigned long find_ftrace_tramp(unsigned long ip)
return 0;
}
-static int __ftrace_make_nop_kernel(struct dyn_ftrace *rec, unsigned long addr)
-{
- unsigned long tramp, ip = rec->ip;
- ppc_inst_t op;
-
- /* Read where this goes */
- if (copy_inst_from_kernel_nofault(&op, (void *)ip)) {
- pr_err("Fetching opcode failed.\n");
- return -EFAULT;
- }
-
- /* Make sure that this is still a 24bit jump */
- if (!is_bl_op(op)) {
- pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op));
- return -EINVAL;
- }
-
- /* Let's find where the pointer goes */
- tramp = find_bl_target(ip, op);
-
- pr_devel("ip:%lx jumps to %lx", ip, tramp);
-
- /* Are ftrace trampolines reachable? */
- if (!find_ftrace_tramp(ip)) {
- pr_err("No ftrace trampolines reachable from %ps\n", (void *)ip);
- return -EINVAL;
- }
-
- if (patch_instruction((u32 *)ip, ppc_inst(PPC_RAW_NOP()))) {
- pr_err("Patching NOP failed.\n");
- return -EPERM;
- }
-
- return 0;
-}
-
-int ftrace_make_nop(struct module *mod,
- struct dyn_ftrace *rec, unsigned long addr)
-{
- unsigned long ip = rec->ip;
- ppc_inst_t old, new;
-
- /*
- * If the calling address is more that 24 bits away,
- * then we had to use a trampoline to make the call.
- * Otherwise just update the call site.
- */
- if (test_24bit_addr(ip, addr)) {
- /* within range */
- old = ftrace_call_replace(ip, addr, 1);
- new = ppc_inst(PPC_RAW_NOP());
- return ftrace_modify_code(ip, old, new);
- } else if (core_kernel_text(ip)) {
- return __ftrace_make_nop_kernel(rec, addr);
- } else if (!IS_ENABLED(CONFIG_MODULES)) {
- return -EINVAL;
- }
-
- /*
- * Out of range jumps are called from modules.
- * We should either already have a pointer to the module
- * or it has been passed in.
- */
- if (!rec->arch.mod) {
- if (!mod) {
- pr_err("No module loaded addr=%lx\n", addr);
- return -EFAULT;
- }
- rec->arch.mod = mod;
- } else if (mod) {
- if (mod != rec->arch.mod) {
- pr_err("Record mod %p not equal to passed in mod %p\n",
- rec->arch.mod, mod);
- return -EINVAL;
- }
- /* nothing to do if mod == rec->arch.mod */
- } else
- mod = rec->arch.mod;
-
- return __ftrace_make_nop(mod, rec, addr);
-}
-
#ifdef CONFIG_MODULES
/*
* Examine the existing instructions for __ftrace_make_call.
@@ -607,6 +419,38 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
}
#endif
+int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr)
+{
+ unsigned long tramp, ip = rec->ip;
+ ppc_inst_t old, new;
+
+ /* Nop-out the ftrace location */
+ new = ppc_inst(PPC_RAW_NOP());
+ if (is_offset_in_branch_range(addr - ip)) {
+ /* Within range */
+ old = ftrace_create_branch_inst(ip, addr, 1);
+ return ftrace_modify_code(ip, old, new);
+ } else if (core_kernel_text(ip)) {
+ /* We would be branching to one of our ftrace tramps */
+ tramp = find_ftrace_tramp(ip);
+ if (!tramp) {
+ pr_err("0x%lx: No ftrace trampolines reachable\n", ip);
+ return -EINVAL;
+ }
+ old = ftrace_create_branch_inst(ip, tramp, 1);
+ return ftrace_modify_code(ip, old, new);
+ } else if (IS_ENABLED(CONFIG_MODULES)) {
+ /* Module code would be going to one of the module stubs */
+ if (!mod)
+ mod = rec->arch.mod;
+ tramp = (addr == (unsigned long)ftrace_caller ? mod->arch.tramp : mod->arch.tramp_regs);
+ old = ftrace_create_branch_inst(ip, tramp, 1);
+ return ftrace_modify_code(ip, old, new);
+ }
+
+ return -EINVAL;
+}
+
int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
{
unsigned long addr, ip = rec->ip;
--
2.40.1
^ permalink raw reply related [flat|nested] 16+ messages in thread* [RFC PATCH 11/15] powerpc/ftrace: Simplify ftrace_make_call()
2023-06-07 16:55 [RFC PATCH 00/15] powerpc/ftrace: refactoring and support for -fpatchable-function-entry Naveen N Rao
` (9 preceding siblings ...)
2023-06-07 16:55 ` [RFC PATCH 10/15] powerpc/ftrace: Simplify ftrace_make_nop() Naveen N Rao
@ 2023-06-07 16:55 ` Naveen N Rao
2023-06-07 16:55 ` [RFC PATCH 12/15] powerpc/ftrace: Simplify ftrace_modify_call() Naveen N Rao
` (3 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Naveen N Rao @ 2023-06-07 16:55 UTC (permalink / raw
To: linuxppc-dev; +Cc: Steven Rostedt, Nicholas Piggin
Now that we validate the ftrace location during initialization in
ftrace_init_nop(), we can simplify ftrace_make_call() to replace the nop
without worrying about the instructions surrounding the ftrace location.
Note that we continue to ensure that we have a nop at the ftrace
location before patching it.
Signed-off-by: Naveen N Rao <naveen@kernel.org>
---
arch/powerpc/kernel/trace/ftrace.c | 187 +++++------------------------
1 file changed, 31 insertions(+), 156 deletions(-)
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 67773cd14da71a..8d5d91b8ae85a0 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -129,162 +129,6 @@ static unsigned long find_ftrace_tramp(unsigned long ip)
return 0;
}
-#ifdef CONFIG_MODULES
-/*
- * Examine the existing instructions for __ftrace_make_call.
- * They should effectively be a NOP, and follow formal constraints,
- * depending on the ABI. Return false if they don't.
- */
-static bool expected_nop_sequence(void *ip, ppc_inst_t op0, ppc_inst_t op1)
-{
- if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
- return ppc_inst_equal(op0, ppc_inst(PPC_RAW_NOP()));
- else
- return ppc_inst_equal(op0, ppc_inst(PPC_RAW_BRANCH(8))) &&
- ppc_inst_equal(op1, ppc_inst(PPC_INST_LD_TOC));
-}
-
-static int
-__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
-{
- ppc_inst_t op[2];
- void *ip = (void *)rec->ip;
- unsigned long entry, ptr, tramp;
- struct module *mod = rec->arch.mod;
-
- /* read where this goes */
- if (copy_inst_from_kernel_nofault(op, ip))
- return -EFAULT;
-
- if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) &&
- copy_inst_from_kernel_nofault(op + 1, ip + 4))
- return -EFAULT;
-
- if (!expected_nop_sequence(ip, op[0], op[1])) {
- pr_err("Unexpected call sequence at %p: %08lx %08lx\n", ip,
- ppc_inst_as_ulong(op[0]), ppc_inst_as_ulong(op[1]));
- return -EINVAL;
- }
-
- /* If we never set up ftrace trampoline(s), then bail */
- if (!mod->arch.tramp ||
- (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && !mod->arch.tramp_regs)) {
- pr_err("No ftrace trampoline\n");
- return -EINVAL;
- }
-
- if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && rec->flags & FTRACE_FL_REGS)
- tramp = mod->arch.tramp_regs;
- else
- tramp = mod->arch.tramp;
-
- if (module_trampoline_target(mod, tramp, &ptr)) {
- pr_err("Failed to get trampoline target\n");
- return -EFAULT;
- }
-
- pr_devel("trampoline target %lx", ptr);
-
- entry = ppc_global_function_entry((void *)addr);
- /* This should match what was called */
- if (ptr != entry) {
- pr_err("addr %lx does not match expected %lx\n", ptr, entry);
- return -EINVAL;
- }
-
- if (patch_branch(ip, tramp, BRANCH_SET_LINK)) {
- pr_err("REL24 out of range!\n");
- return -EINVAL;
- }
-
- return 0;
-}
-#else
-static int __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
-{
- return 0;
-}
-#endif /* CONFIG_MODULES */
-
-static int __ftrace_make_call_kernel(struct dyn_ftrace *rec, unsigned long addr)
-{
- ppc_inst_t op;
- void *ip = (void *)rec->ip;
- unsigned long tramp, entry, ptr;
-
- /* Make sure we're being asked to patch branch to a known ftrace addr */
- entry = ppc_global_function_entry((void *)ftrace_caller);
- ptr = ppc_global_function_entry((void *)addr);
-
- if (ptr != entry && IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
- entry = ppc_global_function_entry((void *)ftrace_regs_caller);
-
- if (ptr != entry) {
- pr_err("Unknown ftrace addr to patch: %ps\n", (void *)ptr);
- return -EINVAL;
- }
-
- /* Make sure we have a nop */
- if (copy_inst_from_kernel_nofault(&op, ip)) {
- pr_err("Unable to read ftrace location %p\n", ip);
- return -EFAULT;
- }
-
- if (!ppc_inst_equal(op, ppc_inst(PPC_RAW_NOP()))) {
- pr_err("Unexpected call sequence at %p: %08lx\n",
- ip, ppc_inst_as_ulong(op));
- return -EINVAL;
- }
-
- tramp = find_ftrace_tramp((unsigned long)ip);
- if (!tramp) {
- pr_err("No ftrace trampolines reachable from %ps\n", ip);
- return -EINVAL;
- }
-
- if (patch_branch(ip, tramp, BRANCH_SET_LINK)) {
- pr_err("Error patching branch to ftrace tramp!\n");
- return -EINVAL;
- }
-
- return 0;
-}
-
-int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
-{
- unsigned long ip = rec->ip;
- ppc_inst_t old, new;
-
- /*
- * If the calling address is more that 24 bits away,
- * then we had to use a trampoline to make the call.
- * Otherwise just update the call site.
- */
- if (test_24bit_addr(ip, addr)) {
- /* within range */
- old = ppc_inst(PPC_RAW_NOP());
- new = ftrace_call_replace(ip, addr, 1);
- return ftrace_modify_code(ip, old, new);
- } else if (core_kernel_text(ip)) {
- return __ftrace_make_call_kernel(rec, addr);
- } else if (!IS_ENABLED(CONFIG_MODULES)) {
- /* We should not get here without modules */
- return -EINVAL;
- }
-
- /*
- * Out of range jumps are called from modules.
- * Being that we are converting from nop, it had better
- * already have a module defined.
- */
- if (!rec->arch.mod) {
- pr_err("No module loaded\n");
- return -EINVAL;
- }
-
- return __ftrace_make_call(rec, addr);
-}
-
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
#ifdef CONFIG_MODULES
static int
@@ -419,6 +263,37 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
}
#endif
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+ unsigned long tramp, ip = rec->ip;
+ ppc_inst_t old, new;
+ struct module *mod;
+
+ old = ppc_inst(PPC_RAW_NOP());
+ if (is_offset_in_branch_range(addr - ip)) {
+ /* Within range */
+ new = ftrace_create_branch_inst(ip, addr, 1);
+ return ftrace_modify_code(ip, old, new);
+ } else if (core_kernel_text(ip)) {
+ /* We would be branching to one of our ftrace tramps */
+ tramp = find_ftrace_tramp(ip);
+ if (!tramp) {
+ pr_err("0x%lx: No ftrace trampolines reachable\n", ip);
+ return -EINVAL;
+ }
+ new = ftrace_create_branch_inst(ip, tramp, 1);
+ return ftrace_modify_code(ip, old, new);
+ } else if (IS_ENABLED(CONFIG_MODULES)) {
+ /* Module code would be going to one of the module stubs */
+ mod = rec->arch.mod;
+ tramp = (addr == (unsigned long)ftrace_caller ? mod->arch.tramp : mod->arch.tramp_regs);
+ new = ftrace_create_branch_inst(ip, tramp, 1);
+ return ftrace_modify_code(ip, old, new);
+ }
+
+ return -EINVAL;
+}
+
int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr)
{
unsigned long tramp, ip = rec->ip;
--
2.40.1
^ permalink raw reply related [flat|nested] 16+ messages in thread* [RFC PATCH 12/15] powerpc/ftrace: Simplify ftrace_modify_call()
2023-06-07 16:55 [RFC PATCH 00/15] powerpc/ftrace: refactoring and support for -fpatchable-function-entry Naveen N Rao
` (10 preceding siblings ...)
2023-06-07 16:55 ` [RFC PATCH 11/15] powerpc/ftrace: Simplify ftrace_make_call() Naveen N Rao
@ 2023-06-07 16:55 ` Naveen N Rao
2023-06-07 16:55 ` [RFC PATCH 13/15] powerpc/ftrace: Replace use of ftrace_call_replace() with ftrace_create_branch_inst() Naveen N Rao
` (2 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Naveen N Rao @ 2023-06-07 16:55 UTC (permalink / raw
To: linuxppc-dev; +Cc: Steven Rostedt, Nicholas Piggin
Now that we validate the ftrace location during initialization in
ftrace_init_nop(), we can simplify ftrace_modify_call() to patch-in the
updated branch instruction without worrying about the instructions
surrounding the ftrace location. Note that we continue to ensure we
have the expected branch instruction at the ftrace location before
patching it with the updated branch destination.
Signed-off-by: Naveen N Rao <naveen@kernel.org>
---
arch/powerpc/kernel/trace/ftrace.c | 161 ++++-------------------------
1 file changed, 21 insertions(+), 140 deletions(-)
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 8d5d91b8ae85a0..c810343d1a6cd6 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -89,33 +89,11 @@ static inline int ftrace_modify_code(unsigned long ip, ppc_inst_t old, ppc_inst_
return ret;
}
-/*
- * Helper functions that are the same for both PPC64 and PPC32.
- */
-static int test_24bit_addr(unsigned long ip, unsigned long addr)
-{
- addr = ppc_function_entry((void *)addr);
-
- return is_offset_in_branch_range(addr - ip);
-}
-
static int is_bl_op(ppc_inst_t op)
{
return (ppc_inst_val(op) & ~PPC_LI_MASK) == PPC_RAW_BL(0);
}
-static unsigned long find_bl_target(unsigned long ip, ppc_inst_t op)
-{
- int offset;
-
- offset = PPC_LI(ppc_inst_val(op));
- /* make it signed */
- if (offset & 0x02000000)
- offset |= 0xfe000000;
-
- return ip + (long)offset;
-}
-
static unsigned long find_ftrace_tramp(unsigned long ip)
{
int i;
@@ -130,115 +108,16 @@ static unsigned long find_ftrace_tramp(unsigned long ip)
}
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
-#ifdef CONFIG_MODULES
-static int
-__ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
- unsigned long addr)
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr)
{
- ppc_inst_t op;
- unsigned long ip = rec->ip;
- unsigned long entry, ptr, tramp;
- struct module *mod = rec->arch.mod;
-
- /* If we never set up ftrace trampolines, then bail */
- if (!mod->arch.tramp || !mod->arch.tramp_regs) {
- pr_err("No ftrace trampoline\n");
- return -EINVAL;
- }
-
- /* read where this goes */
- if (copy_inst_from_kernel_nofault(&op, (void *)ip)) {
- pr_err("Fetching opcode failed.\n");
- return -EFAULT;
- }
-
- /* Make sure that this is still a 24bit jump */
- if (!is_bl_op(op)) {
- pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op));
- return -EINVAL;
- }
-
- /* lets find where the pointer goes */
- tramp = find_bl_target(ip, op);
- entry = ppc_global_function_entry((void *)old_addr);
-
- pr_devel("ip:%lx jumps to %lx", ip, tramp);
-
- if (tramp != entry) {
- /* old_addr is not within range, so we must have used a trampoline */
- if (module_trampoline_target(mod, tramp, &ptr)) {
- pr_err("Failed to get trampoline target\n");
- return -EFAULT;
- }
-
- pr_devel("trampoline target %lx", ptr);
-
- /* This should match what was called */
- if (ptr != entry) {
- pr_err("addr %lx does not match expected %lx\n", ptr, entry);
- return -EINVAL;
- }
- }
-
- /* The new target may be within range */
- if (test_24bit_addr(ip, addr)) {
- /* within range */
- if (patch_branch((u32 *)ip, addr, BRANCH_SET_LINK)) {
- pr_err("REL24 out of range!\n");
- return -EINVAL;
- }
-
- return 0;
- }
-
- if (rec->flags & FTRACE_FL_REGS)
- tramp = mod->arch.tramp_regs;
- else
- tramp = mod->arch.tramp;
-
- if (module_trampoline_target(mod, tramp, &ptr)) {
- pr_err("Failed to get trampoline target\n");
- return -EFAULT;
- }
-
- pr_devel("trampoline target %lx", ptr);
-
- entry = ppc_global_function_entry((void *)addr);
- /* This should match what was called */
- if (ptr != entry) {
- pr_err("addr %lx does not match expected %lx\n", ptr, entry);
- return -EINVAL;
- }
-
- if (patch_branch((u32 *)ip, tramp, BRANCH_SET_LINK)) {
- pr_err("REL24 out of range!\n");
- return -EINVAL;
- }
-
- return 0;
-}
-#else
-static int __ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr)
-{
- return 0;
-}
-#endif
-
-int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
- unsigned long addr)
-{
- unsigned long ip = rec->ip;
+ unsigned long tramp, tramp_old, ip = rec->ip;
ppc_inst_t old, new;
+ struct module *mod;
- /*
- * If the calling address is more that 24 bits away,
- * then we had to use a trampoline to make the call.
- * Otherwise just update the call site.
- */
- if (test_24bit_addr(ip, addr) && test_24bit_addr(ip, old_addr)) {
- /* within range */
- old = ftrace_call_replace(ip, old_addr, 1);
- new = ftrace_call_replace(ip, addr, 1);
+ if (is_offset_in_branch_range(old_addr - ip) && is_offset_in_branch_range(addr - ip)) {
+ /* Within range */
+ old = ftrace_create_branch_inst(ip, old_addr, 1);
+ new = ftrace_create_branch_inst(ip, addr, 1);
return ftrace_modify_code(ip, old, new);
} else if (core_kernel_text(ip)) {
/*
@@ -246,20 +125,22 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
* variant, so there is nothing to do here
*/
return 0;
- } else if (!IS_ENABLED(CONFIG_MODULES)) {
- /* We should not get here without modules */
- return -EINVAL;
+ } else if (IS_ENABLED(CONFIG_MODULES)) {
+ /* Module code would be going to one of the module stubs */
+ mod = rec->arch.mod;
+ if (addr == (unsigned long)ftrace_caller) {
+ tramp_old = mod->arch.tramp_regs;
+ tramp = mod->arch.tramp;
+ } else {
+ tramp_old = mod->arch.tramp;
+ tramp = mod->arch.tramp_regs;
+ }
+ old = ftrace_create_branch_inst(ip, tramp_old, 1);
+ new = ftrace_create_branch_inst(ip, tramp, 1);
+ return ftrace_modify_code(ip, old, new);
}
- /*
- * Out of range jumps are called from modules.
- */
- if (!rec->arch.mod) {
- pr_err("No module loaded\n");
- return -EINVAL;
- }
-
- return __ftrace_modify_call(rec, old_addr, addr);
+ return -EINVAL;
}
#endif
--
2.40.1
^ permalink raw reply related [flat|nested] 16+ messages in thread* [RFC PATCH 13/15] powerpc/ftrace: Replace use of ftrace_call_replace() with ftrace_create_branch_inst()
2023-06-07 16:55 [RFC PATCH 00/15] powerpc/ftrace: refactoring and support for -fpatchable-function-entry Naveen N Rao
` (11 preceding siblings ...)
2023-06-07 16:55 ` [RFC PATCH 12/15] powerpc/ftrace: Simplify ftrace_modify_call() Naveen N Rao
@ 2023-06-07 16:55 ` Naveen N Rao
2023-06-07 16:55 ` [RFC PATCH 14/15] powerpc/ftrace: Implement ftrace_replace_code() Naveen N Rao
2023-06-07 16:55 ` [RFC PATCH 15/15] powerpc/ftrace: Add support for -fpatchable-function-entry Naveen N Rao
14 siblings, 0 replies; 16+ messages in thread
From: Naveen N Rao @ 2023-06-07 16:55 UTC (permalink / raw
To: linuxppc-dev; +Cc: Steven Rostedt, Nicholas Piggin
ftrace_create_branch_inst() is clearer about its intent than
ftrace_call_replace().
Signed-off-by: Naveen N Rao <naveen@kernel.org>
---
arch/powerpc/kernel/trace/ftrace.c | 17 ++---------------
1 file changed, 2 insertions(+), 15 deletions(-)
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index c810343d1a6cd6..4375ef71609c0a 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -41,19 +41,6 @@ static ppc_inst_t ftrace_create_branch_inst(unsigned long ip, unsigned long addr
return op;
}
-static ppc_inst_t
-ftrace_call_replace(unsigned long ip, unsigned long addr, int link)
-{
- ppc_inst_t op;
-
- addr = ppc_function_entry((void *)addr);
-
- /* if (link) set op to 'bl' else 'b' */
- create_branch(&op, (u32 *)ip, addr, link ? BRANCH_SET_LINK : 0);
-
- return op;
-}
-
static inline int ftrace_read_inst(unsigned long ip, ppc_inst_t *op)
{
if (copy_inst_from_kernel_nofault(op, (void *)ip)) {
@@ -275,14 +262,14 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
int ret;
old = ppc_inst_read((u32 *)&ftrace_call);
- new = ftrace_call_replace(ip, (unsigned long)func, 1);
+ new = ftrace_create_branch_inst(ip, ppc_function_entry(func), 1);
ret = ftrace_modify_code(ip, old, new);
/* Also update the regs callback function */
if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && !ret) {
ip = (unsigned long)(&ftrace_regs_call);
old = ppc_inst_read((u32 *)&ftrace_regs_call);
- new = ftrace_call_replace(ip, (unsigned long)func, 1);
+ new = ftrace_create_branch_inst(ip, ppc_function_entry(func), 1);
ret = ftrace_modify_code(ip, old, new);
}
--
2.40.1
^ permalink raw reply related [flat|nested] 16+ messages in thread* [RFC PATCH 14/15] powerpc/ftrace: Implement ftrace_replace_code()
2023-06-07 16:55 [RFC PATCH 00/15] powerpc/ftrace: refactoring and support for -fpatchable-function-entry Naveen N Rao
` (12 preceding siblings ...)
2023-06-07 16:55 ` [RFC PATCH 13/15] powerpc/ftrace: Replace use of ftrace_call_replace() with ftrace_create_branch_inst() Naveen N Rao
@ 2023-06-07 16:55 ` Naveen N Rao
2023-06-07 16:55 ` [RFC PATCH 15/15] powerpc/ftrace: Add support for -fpatchable-function-entry Naveen N Rao
14 siblings, 0 replies; 16+ messages in thread
From: Naveen N Rao @ 2023-06-07 16:55 UTC (permalink / raw
To: linuxppc-dev; +Cc: Steven Rostedt, Nicholas Piggin
Implement ftrace_replace_code() to consolidate logic from the different
ftrace patching routines: ftrace_make_nop(), ftrace_make_call() and
ftrace_modify_call(). Note that ftrace_make_call() is still required
primarily to handle patching modules during their load time. The other
two routines should no longer be called.
This lays the groundwork to enable better control in patching ftrace
locations, including the ability to nop-out preceding profiling
instructions when ftrace is disabled.
Signed-off-by: Naveen N Rao <naveen@kernel.org>
---
arch/powerpc/kernel/trace/ftrace.c | 173 ++++++++++++++++-------------
1 file changed, 96 insertions(+), 77 deletions(-)
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 4375ef71609c0a..fd1ef350c62c42 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -94,104 +94,123 @@ static unsigned long find_ftrace_tramp(unsigned long ip)
return 0;
}
+static int ftrace_get_call_inst(struct dyn_ftrace *rec, unsigned long addr, ppc_inst_t *call_inst)
+{
+ unsigned long ip = rec->ip;
+ unsigned long stub;
+
+ if (is_offset_in_branch_range(addr - ip)) {
+ /* Within range */
+ stub = addr;
+#ifdef CONFIG_MODULES
+ } else if (rec->arch.mod) {
+ /* Module code would be going to one of the module stubs */
+ stub = (addr == (unsigned long)ftrace_caller ? rec->arch.mod->arch.tramp :
+ rec->arch.mod->arch.tramp_regs);
+#endif
+ } else if (core_kernel_text(ip)) {
+ /* We would be branching to one of our ftrace stubs */
+ stub = find_ftrace_tramp(ip);
+ if (!stub) {
+ pr_err("0x%lx: No ftrace stubs reachable\n", ip);
+ return -EINVAL;
+ }
+ } else {
+ return -EINVAL;
+ }
+
+ *call_inst = ftrace_create_branch_inst(ip, stub, 1);
+ return 0;
+}
+
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr)
{
- unsigned long tramp, tramp_old, ip = rec->ip;
- ppc_inst_t old, new;
- struct module *mod;
-
- if (is_offset_in_branch_range(old_addr - ip) && is_offset_in_branch_range(addr - ip)) {
- /* Within range */
- old = ftrace_create_branch_inst(ip, old_addr, 1);
- new = ftrace_create_branch_inst(ip, addr, 1);
- return ftrace_modify_code(ip, old, new);
- } else if (core_kernel_text(ip)) {
- /*
- * We always patch out of range locations to go to the regs
- * variant, so there is nothing to do here
- */
- return 0;
- } else if (IS_ENABLED(CONFIG_MODULES)) {
- /* Module code would be going to one of the module stubs */
- mod = rec->arch.mod;
- if (addr == (unsigned long)ftrace_caller) {
- tramp_old = mod->arch.tramp_regs;
- tramp = mod->arch.tramp;
- } else {
- tramp_old = mod->arch.tramp;
- tramp = mod->arch.tramp_regs;
- }
- old = ftrace_create_branch_inst(ip, tramp_old, 1);
- new = ftrace_create_branch_inst(ip, tramp, 1);
- return ftrace_modify_code(ip, old, new);
- }
-
+ /* This should never be called since we override ftrace_replace_code() */
+ WARN_ON(1);
return -EINVAL;
}
#endif
int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
{
- unsigned long tramp, ip = rec->ip;
ppc_inst_t old, new;
- struct module *mod;
+ int ret;
+
+ /* This can only ever be called during module load */
+ if (WARN_ON(!IS_ENABLED(CONFIG_MODULES) || core_kernel_text(rec->ip)))
+ return -EINVAL;
old = ppc_inst(PPC_RAW_NOP());
- if (is_offset_in_branch_range(addr - ip)) {
- /* Within range */
- new = ftrace_create_branch_inst(ip, addr, 1);
- return ftrace_modify_code(ip, old, new);
- } else if (core_kernel_text(ip)) {
- /* We would be branching to one of our ftrace tramps */
- tramp = find_ftrace_tramp(ip);
- if (!tramp) {
- pr_err("0x%lx: No ftrace trampolines reachable\n", ip);
- return -EINVAL;
- }
- new = ftrace_create_branch_inst(ip, tramp, 1);
- return ftrace_modify_code(ip, old, new);
- } else if (IS_ENABLED(CONFIG_MODULES)) {
- /* Module code would be going to one of the module stubs */
- mod = rec->arch.mod;
- tramp = (addr == (unsigned long)ftrace_caller ? mod->arch.tramp : mod->arch.tramp_regs);
- new = ftrace_create_branch_inst(ip, tramp, 1);
- return ftrace_modify_code(ip, old, new);
- }
+ ret = ftrace_get_call_inst(rec, addr, &new);
+ if (ret)
+ return ret;
- return -EINVAL;
+ return ftrace_modify_code(rec->ip, old, new);
}
int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr)
{
- unsigned long tramp, ip = rec->ip;
- ppc_inst_t old, new;
+ /*
+ * This should never be called since we override ftrace_replace_code(),
+ * as well as ftrace_init_nop()
+ */
+ WARN_ON(1);
+ return -EINVAL;
+}
- /* Nop-out the ftrace location */
- new = ppc_inst(PPC_RAW_NOP());
- if (is_offset_in_branch_range(addr - ip)) {
- /* Within range */
- old = ftrace_create_branch_inst(ip, addr, 1);
- return ftrace_modify_code(ip, old, new);
- } else if (core_kernel_text(ip)) {
- /* We would be branching to one of our ftrace tramps */
- tramp = find_ftrace_tramp(ip);
- if (!tramp) {
- pr_err("0x%lx: No ftrace trampolines reachable\n", ip);
- return -EINVAL;
+void ftrace_replace_code(int enable)
+{
+ ppc_inst_t old, new, call_inst, new_call_inst;
+ ppc_inst_t nop_inst = ppc_inst(PPC_RAW_NOP());
+ unsigned long ip, new_addr, addr;
+ struct ftrace_rec_iter *iter;
+ struct dyn_ftrace *rec;
+ int ret = 0, update;
+
+ for_ftrace_rec_iter(iter) {
+ rec = ftrace_rec_iter_record(iter);
+ ip = rec->ip;
+
+ if (rec->flags & FTRACE_FL_DISABLED && !(rec->flags & FTRACE_FL_ENABLED))
+ continue;
+
+ addr = ftrace_get_addr_curr(rec);
+ new_addr = ftrace_get_addr_new(rec);
+ update = ftrace_update_record(rec, enable);
+
+ switch (update) {
+ case FTRACE_UPDATE_IGNORE:
+ default:
+ continue;
+ case FTRACE_UPDATE_MODIFY_CALL:
+ ret = ftrace_get_call_inst(rec, new_addr, &new_call_inst);
+ ret |= ftrace_get_call_inst(rec, addr, &call_inst);
+ old = call_inst;
+ new = new_call_inst;
+ break;
+ case FTRACE_UPDATE_MAKE_NOP:
+ ret = ftrace_get_call_inst(rec, addr, &call_inst);
+ old = call_inst;
+ new = nop_inst;
+ break;
+ case FTRACE_UPDATE_MAKE_CALL:
+ ret = ftrace_get_call_inst(rec, new_addr, &call_inst);
+ old = nop_inst;
+ new = call_inst;
+ break;
}
- old = ftrace_create_branch_inst(ip, tramp, 1);
- return ftrace_modify_code(ip, old, new);
- } else if (IS_ENABLED(CONFIG_MODULES)) {
- /* Module code would be going to one of the module stubs */
- if (!mod)
- mod = rec->arch.mod;
- tramp = (addr == (unsigned long)ftrace_caller ? mod->arch.tramp : mod->arch.tramp_regs);
- old = ftrace_create_branch_inst(ip, tramp, 1);
- return ftrace_modify_code(ip, old, new);
+
+ if (!ret)
+ ret = ftrace_modify_code(ip, old, new);
+ if (ret)
+ goto out;
}
- return -EINVAL;
+out:
+ if (ret)
+ ftrace_bug(ret, rec);
+ return;
}
int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
--
2.40.1
^ permalink raw reply related [flat|nested] 16+ messages in thread* [RFC PATCH 15/15] powerpc/ftrace: Add support for -fpatchable-function-entry
2023-06-07 16:55 [RFC PATCH 00/15] powerpc/ftrace: refactoring and support for -fpatchable-function-entry Naveen N Rao
` (13 preceding siblings ...)
2023-06-07 16:55 ` [RFC PATCH 14/15] powerpc/ftrace: Implement ftrace_replace_code() Naveen N Rao
@ 2023-06-07 16:55 ` Naveen N Rao
14 siblings, 0 replies; 16+ messages in thread
From: Naveen N Rao @ 2023-06-07 16:55 UTC (permalink / raw
To: linuxppc-dev; +Cc: Steven Rostedt, Nicholas Piggin
GCC v13.1 updated support for -fpatchable-function-entry on ppc64le to
emit nops after the local entry point, rather than before it. This
allows us to use this in the kernel for ftrace purposes. A new script is
added under arch/powerpc/tools/ to help detect if nops are emitted after
the function local entry point, or before the global entry point.
With -fpatchable-function-entry, we no longer have the profiling
instructions generated at function entry, so we only need to validate
the presence of two nops at the ftrace location in ftrace_init_nop(). We
patch the preceding instruction with 'mflr r0' to match the
-mprofile-kernel ABI for subsequent ftrace use.
This changes the profiling instructions used on ppc32. The default -pg
option emits an additional 'stw' instruction after 'mflr r0' and before
the branch to _mcount 'bl _mcount'. This is very similar to the original
-mprofile-kernel implementation on ppc64le, where an additional 'std'
instruction was used to save LR to its save location in the caller's
stackframe. Subsequently, this additional store was removed in later
compiler versions for performance reasons. The same reasons apply for
ppc32 so we only patch in a 'mflr r0'.
Signed-off-by: Naveen N Rao <naveen@kernel.org>
---
arch/powerpc/Kconfig | 14 +++++++---
arch/powerpc/Makefile | 5 ++++
arch/powerpc/include/asm/ftrace.h | 6 +++--
arch/powerpc/include/asm/vermagic.h | 4 ++-
arch/powerpc/kernel/module_64.c | 2 +-
arch/powerpc/kernel/trace/ftrace.c | 14 ++++++++--
arch/powerpc/kernel/trace/ftrace_entry.S | 2 ++
.../gcc-check-fpatchable-function-entry.sh | 26 +++++++++++++++++++
8 files changed, 64 insertions(+), 9 deletions(-)
create mode 100755 arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index bff5820b7cda14..9352d8e68152e1 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -187,6 +187,7 @@ config PPC
select DYNAMIC_FTRACE if FUNCTION_TRACER
select EDAC_ATOMIC_SCRUB
select EDAC_SUPPORT
+ select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY if ARCH_USING_PATCHABLE_FUNCTION_ENTRY
select GENERIC_ATOMIC64 if PPC32
select GENERIC_CLOCKEVENTS_BROADCAST if SMP
select GENERIC_CMOS_UPDATE
@@ -227,8 +228,8 @@ config PPC
select HAVE_DEBUG_KMEMLEAK
select HAVE_DEBUG_STACKOVERFLOW
select HAVE_DYNAMIC_FTRACE
- select HAVE_DYNAMIC_FTRACE_WITH_ARGS if MPROFILE_KERNEL || PPC32
- select HAVE_DYNAMIC_FTRACE_WITH_REGS if MPROFILE_KERNEL || PPC32
+ select HAVE_DYNAMIC_FTRACE_WITH_ARGS if ARCH_USING_PATCHABLE_FUNCTION_ENTRY || MPROFILE_KERNEL || PPC32
+ select HAVE_DYNAMIC_FTRACE_WITH_REGS if ARCH_USING_PATCHABLE_FUNCTION_ENTRY || MPROFILE_KERNEL || PPC32
select HAVE_EBPF_JIT
select HAVE_EFFICIENT_UNALIGNED_ACCESS
select HAVE_FAST_GUP
@@ -256,7 +257,7 @@ config PPC
select HAVE_MOD_ARCH_SPECIFIC
select HAVE_NMI if PERF_EVENTS || (PPC64 && PPC_BOOK3S)
select HAVE_OPTPROBES
- select HAVE_OBJTOOL if PPC32 || MPROFILE_KERNEL
+ select HAVE_OBJTOOL if ARCH_USING_PATCHABLE_FUNCTION_ENTRY || MPROFILE_KERNEL || PPC32
select HAVE_OBJTOOL_MCOUNT if HAVE_OBJTOOL
select HAVE_PERF_EVENTS
select HAVE_PERF_EVENTS_NMI if PPC64
@@ -550,6 +551,13 @@ config MPROFILE_KERNEL
depends on PPC64 && CPU_LITTLE_ENDIAN && FUNCTION_TRACER
def_bool $(success,$(srctree)/arch/powerpc/tools/gcc-check-mprofile-kernel.sh $(CC) -I$(srctree)/include -D__KERNEL__)
+config ARCH_USING_PATCHABLE_FUNCTION_ENTRY
+ depends on FUNCTION_TRACER && (PPC32 || PPC64_ELF_ABI_V2)
+ depends on $(cc-option,-fpatchable-function-entry=2)
+ def_bool y if PPC32
+ def_bool $(success,$(srctree)/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh $(CC) -mlittle-endian) if PPC64 && CPU_LITTLE_ENDIAN
+ def_bool $(success,$(srctree)/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh $(CC) -mbig-endian) if PPC64 && CPU_BIG_ENDIAN
+
config HOTPLUG_CPU
bool "Support for enabling/disabling CPUs"
depends on SMP && (PPC_PSERIES || \
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index dca73f673d7046..de39478b1c9e9f 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -148,11 +148,16 @@ CFLAGS-$(CONFIG_PPC32) += $(call cc-option, $(MULTIPLEWORD))
CFLAGS-$(CONFIG_PPC32) += $(call cc-option,-mno-readonly-in-sdata)
ifdef CONFIG_FUNCTION_TRACER
+ifdef CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY
+KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY
+CC_FLAGS_FTRACE := -fpatchable-function-entry=2
+else
CC_FLAGS_FTRACE := -pg
ifdef CONFIG_MPROFILE_KERNEL
CC_FLAGS_FTRACE += -mprofile-kernel
endif
endif
+endif
CFLAGS-$(CONFIG_TARGET_CPU_BOOL) += -mcpu=$(CONFIG_TARGET_CPU)
AFLAGS-$(CONFIG_TARGET_CPU_BOOL) += -mcpu=$(CONFIG_TARGET_CPU)
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index 89fbae3caa1fc2..0d61e8080cece5 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -11,7 +11,7 @@
#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
/* Ignore unused weak functions which will have larger offsets */
-#ifdef CONFIG_MPROFILE_KERNEL
+#if defined(CONFIG_MPROFILE_KERNEL) || defined(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)
#define FTRACE_MCOUNT_MAX_OFFSET 12
#elif defined(CONFIG_PPC32)
#define FTRACE_MCOUNT_MAX_OFFSET 8
@@ -22,7 +22,9 @@ extern void _mcount(void);
static inline unsigned long ftrace_call_adjust(unsigned long addr)
{
- /* relocation of mcount call site is the same as the address */
+ if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY))
+ addr += MCOUNT_INSN_SIZE;
+
return addr;
}
diff --git a/arch/powerpc/include/asm/vermagic.h b/arch/powerpc/include/asm/vermagic.h
index b054a8576e5deb..6f250fe506bd1c 100644
--- a/arch/powerpc/include/asm/vermagic.h
+++ b/arch/powerpc/include/asm/vermagic.h
@@ -2,7 +2,9 @@
#ifndef _ASM_VERMAGIC_H
#define _ASM_VERMAGIC_H
-#ifdef CONFIG_MPROFILE_KERNEL
+#ifdef CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY
+#define MODULE_ARCH_VERMAGIC_FTRACE "patchable-function-entry "
+#elif defined(CONFIG_MPROFILE_KERNEL)
#define MODULE_ARCH_VERMAGIC_FTRACE "mprofile-kernel "
#else
#define MODULE_ARCH_VERMAGIC_FTRACE ""
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 92570289ce08f5..7112adc597a80b 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -465,7 +465,7 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr,
return 0;
}
-#ifdef CONFIG_MPROFILE_KERNEL
+#if defined(CONFIG_MPROFILE_KERNEL) || defined(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)
static u32 stub_insns[] = {
#ifdef CONFIG_PPC_KERNEL_PCREL
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index fd1ef350c62c42..a03aa4fd7a08ba 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -220,7 +220,12 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
int ret = 0;
/* Verify instructions surrounding the ftrace location */
- if (IS_ENABLED(CONFIG_PPC32)) {
+ if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)) {
+ /* Expect nops */
+ ret = ftrace_validate_inst(ip - 4, ppc_inst(PPC_RAW_NOP()));
+ if (!ret)
+ ret = ftrace_validate_inst(ip, ppc_inst(PPC_RAW_NOP()));
+ } else if (IS_ENABLED(CONFIG_PPC32)) {
/* Expected sequence: 'mflr r0', 'stw r0,4(r1)', 'bl _mcount' */
ret = ftrace_validate_inst(ip - 8, ppc_inst(PPC_RAW_MFLR(_R0)));
if (!ret)
@@ -250,7 +255,12 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
/* Nop-out the ftrace location */
new = ppc_inst(PPC_RAW_NOP());
addr = MCOUNT_ADDR;
- if (is_offset_in_branch_range(addr - ip)) {
+ if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)) {
+ /* we instead patch-in the 'mflr r0' */
+ old = ppc_inst(PPC_RAW_NOP());
+ new = ppc_inst(PPC_RAW_MFLR(_R0));
+ ret = ftrace_modify_code(ip - 4, old, new);
+ } else if (is_offset_in_branch_range(addr - ip)) {
/* Within range */
old = ftrace_create_branch_inst(ip, addr, 1);
ret = ftrace_modify_code(ip, old, new);
diff --git a/arch/powerpc/kernel/trace/ftrace_entry.S b/arch/powerpc/kernel/trace/ftrace_entry.S
index e8339706e735b1..bab3ab1368a33f 100644
--- a/arch/powerpc/kernel/trace/ftrace_entry.S
+++ b/arch/powerpc/kernel/trace/ftrace_entry.S
@@ -250,6 +250,7 @@ livepatch_handler:
blr
#endif /* CONFIG_LIVEPATCH */
+#ifndef CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY
_GLOBAL(mcount)
_GLOBAL(_mcount)
EXPORT_SYMBOL(_mcount)
@@ -257,6 +258,7 @@ EXPORT_SYMBOL(_mcount)
mtctr r12
mtlr r0
bctr
+#endif
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
_GLOBAL(return_to_handler)
diff --git a/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh b/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh
new file mode 100755
index 00000000000000..06706903503b6c
--- /dev/null
+++ b/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh
@@ -0,0 +1,26 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+set -o pipefail
+
+# To debug, uncomment the following line
+# set -x
+
+# Output from -fpatchable-function-entry can only vary on ppc64 elfv2, so this
+# should not be invoked for other targets. Therefore we can pass in -m64 and
+# -mabi explicitly, to take care of toolchains defaulting to other targets.
+
+# Test whether the compile option -fpatchable-function-entry exists and
+# generates appropriate code
+echo "int func() { return 0; }" | \
+ $* -m64 -mabi=elfv2 -S -x c -O2 -fpatchable-function-entry=2 - -o - 2> /dev/null | \
+ grep -q "__patchable_function_entries"
+
+# Test whether nops are generated after the local entry point
+echo "int x; int func() { return x; }" | \
+ $* -m64 -mabi=elfv2 -S -x c -O2 -fpatchable-function-entry=2 - -o - 2> /dev/null | \
+ awk 'BEGIN { RS = ";" } /\.localentry.*nop.*\n[[:space:]]*nop/ { print $0 }' | \
+ grep -q "func:"
+
+exit 0
--
2.40.1
^ permalink raw reply related [flat|nested] 16+ messages in thread