[PATCH] powerpc/ftrace: Handle large kernel configs
Naveen N. Rao
naveen.n.rao at linux.vnet.ibm.com
Wed Oct 17 07:25:00 AEDT 2018
Currently, we expect to be able to reach ftrace_caller() from all
ftrace-enabled functions through a single relative branch. With large
kernel configs, we see functions outside of 32MB of ftrace_caller()
causing ftrace_init() to bail.
In such configurations, gcc/ld emits two types of trampolines for mcount():
1. A long_branch, which has a single branch to mcount() for functions that
are one hop away from mcount():
c0000000019e8544 <00031b56.long_branch._mcount>:
c0000000019e8544: 4a 69 3f ac b c00000000007c4f0 <._mcount>
2. A plt_branch, for functions that are farther away from mcount():
c0000000051f33f8 <0008ba04.plt_branch._mcount>:
c0000000051f33f8: 3d 82 ff a4 addis r12,r2,-92
c0000000051f33fc: e9 8c 04 20 ld r12,1056(r12)
c0000000051f3400: 7d 89 03 a6 mtctr r12
c0000000051f3404: 4e 80 04 20 bctr
We can reuse those trampolines for ftrace if we can have those
trampolines go to ftrace_caller() instead. However, with ABIv2, we
cannot depend on r2 being valid. As such, we use only the long_branch
trampolines by patching those to instead branch to ftrace_caller or
ftrace_regs_caller.
In addition, we add additional trampolines around .text and .init.text
to catch locations that are covered by the plt branches. This allows
ftrace to work with most large kernel configurations.
For now, we always patch the trampolines to go to ftrace_regs_caller,
which is slightly inefficient. This can be optimized further at a later
point.
Signed-off-by: Naveen N. Rao <naveen.n.rao at linux.vnet.ibm.com>
---
Since RFC:
- Change to patch long_branch to go to ftrace_caller, rather than
patching mcount()
- Stop using plt_branch since it can't be relied on for ABIv2
- Add trampolines around .text and .init.text to catch remaining
locations
- Naveen
arch/powerpc/kernel/trace/ftrace.c | 261 +++++++++++++++++++++++++-
arch/powerpc/kernel/trace/ftrace_64.S | 12 ++
arch/powerpc/kernel/vmlinux.lds.S | 13 +-
3 files changed, 281 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 4bfbb54dee51..4bf051d3e21e 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -30,6 +30,16 @@
#ifdef CONFIG_DYNAMIC_FTRACE
+
+/*
+ * 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 unsigned int
ftrace_call_replace(unsigned long ip, unsigned long addr, int link)
{
@@ -85,13 +95,16 @@ static int test_24bit_addr(unsigned long ip, unsigned long addr)
return create_branch((unsigned int *)ip, addr, 0);
}
-#ifdef CONFIG_MODULES
-
static int is_bl_op(unsigned int op)
{
return (op & 0xfc000003) == 0x48000001;
}
+static int is_b_op(unsigned int op)
+{
+ return (op & 0xfc000003) == 0x48000000;
+}
+
static unsigned long find_bl_target(unsigned long ip, unsigned int op)
{
static int offset;
@@ -104,6 +117,7 @@ static unsigned long find_bl_target(unsigned long ip, unsigned int op)
return ip + (long)offset;
}
+#ifdef CONFIG_MODULES
#ifdef CONFIG_PPC64
static int
__ftrace_make_nop(struct module *mod,
@@ -270,6 +284,146 @@ __ftrace_make_nop(struct module *mod,
#endif /* PPC64 */
#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 (create_branch((void *)ip, ftrace_tramps[i], 0))
+ 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, op;
+ unsigned long ptr;
+ static unsigned long ftrace_plt_tramps[NUM_FTRACE_TRAMPS];
+
+ /* Is this a known long jump tramp? */
+ for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
+ if (!ftrace_tramps[i])
+ break;
+ else if (ftrace_tramps[i] == tramp)
+ return 0;
+
+ /* Is this a known plt tramp? */
+ for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
+ if (!ftrace_plt_tramps[i])
+ break;
+ else if (ftrace_plt_tramps[i] == tramp)
+ return -1;
+
+ /* New trampoline -- read where this goes */
+ if (probe_kernel_read(&op, (void *)tramp, sizeof(int))) {
+ 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 */
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+ ptr = ppc_global_function_entry((void *)ftrace_regs_caller);
+#else
+ ptr = ppc_global_function_entry((void *)ftrace_caller);
+#endif
+ if (!create_branch((void *)tramp, ptr, 0)) {
+ pr_debug("%ps is not reachable from existing mcount tramp\n",
+ (void *)ptr);
+ return -1;
+ }
+
+ if (patch_branch((unsigned int *)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;
+ unsigned int op;
+
+ /* Read where this goes */
+ if (probe_kernel_read(&op, (void *)ip, sizeof(int))) {
+ pr_err("Fetching opcode failed.\n");
+ return -EFAULT;
+ }
+
+ /* Make sure that that this is still a 24bit jump */
+ if (!is_bl_op(op)) {
+ pr_err("Not expected bl: opcode is %x\n", 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((unsigned int *)ip, PPC_INST_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)
{
@@ -286,7 +440,8 @@ int ftrace_make_nop(struct module *mod,
old = ftrace_call_replace(ip, addr, 1);
new = PPC_INST_NOP;
return ftrace_modify_code(ip, old, new);
- }
+ } else if (core_kernel_text(ip))
+ return __ftrace_make_nop_kernel(rec, addr);
#ifdef CONFIG_MODULES
/*
@@ -456,6 +611,53 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
#endif /* CONFIG_PPC64 */
#endif /* CONFIG_MODULES */
+static int __ftrace_make_call_kernel(struct dyn_ftrace *rec, unsigned long addr)
+{
+ unsigned int 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) {
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+ entry = ppc_global_function_entry((void *)ftrace_regs_caller);
+ if (ptr != entry) {
+#endif
+ pr_err("Unknown ftrace addr to patch: %ps\n", (void *)ptr);
+ return -EINVAL;
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+ }
+#endif
+ }
+
+ /* Make sure we have a nop */
+ if (probe_kernel_read(&op, ip, sizeof(op))) {
+ pr_err("Unable to read ftrace location %p\n", ip);
+ return -EFAULT;
+ }
+
+ if (op != PPC_INST_NOP) {
+ pr_err("Unexpected call sequence at %p: %x\n", ip, 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;
@@ -471,7 +673,8 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
old = PPC_INST_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);
#ifdef CONFIG_MODULES
/*
@@ -603,6 +806,12 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
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;
}
#ifdef CONFIG_MODULES
@@ -654,10 +863,54 @@ void arch_ftrace_update_code(int command)
ftrace_modify_all_code(command);
}
+#ifdef CONFIG_PPC64
+#define PACATOC offsetof(struct paca_struct, kernel_toc)
+
+#define PPC_LO(v) ((v) & 0xffff)
+#define PPC_HI(v) (((v) >> 16) & 0xffff)
+#define PPC_HA(v) PPC_HI ((v) + 0x8000)
+
+extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[];
+
+int __init ftrace_dyn_arch_init(void)
+{
+ int i;
+ unsigned int *tramp[] = { ftrace_tramp_text, ftrace_tramp_init };
+ u32 stub_insns[] = {
+ 0xe98d0000 | PACATOC, /* ld r12,PACATOC(r13) */
+ 0x3d8c0000, /* addis r12,r12,<high> */
+ 0x398c0000, /* addi r12,r12,<low> */
+ 0x7d8903a6, /* mtctr r12 */
+ 0x4e800420, /* bctr */
+ };
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+ unsigned long addr = ppc_global_function_entry((void *)ftrace_regs_caller);
+#else
+ unsigned long addr = ppc_global_function_entry((void *)ftrace_caller);
+#endif
+ long reladdr = addr - kernel_toc_addr();
+
+ if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) {
+ 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;
+}
+#else
int __init ftrace_dyn_arch_init(void)
{
return 0;
}
+#endif
#endif /* CONFIG_DYNAMIC_FTRACE */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
diff --git a/arch/powerpc/kernel/trace/ftrace_64.S b/arch/powerpc/kernel/trace/ftrace_64.S
index e25f77c10a72..1782af2d1496 100644
--- a/arch/powerpc/kernel/trace/ftrace_64.S
+++ b/arch/powerpc/kernel/trace/ftrace_64.S
@@ -14,6 +14,18 @@
#include <asm/ppc-opcode.h>
#include <asm/export.h>
+.pushsection ".tramp.ftrace.text","aw", at progbits;
+.globl ftrace_tramp_text
+ftrace_tramp_text:
+ .space 64
+.popsection
+
+.pushsection ".tramp.ftrace.init","aw", at progbits;
+.globl ftrace_tramp_init
+ftrace_tramp_init:
+ .space 64
+.popsection
+
_GLOBAL(mcount)
_GLOBAL(_mcount)
EXPORT_SYMBOL(_mcount)
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 07ae018e550e..b9045abea1b7 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -99,6 +99,9 @@ SECTIONS
#endif
/* careful! __ftr_alt_* sections need to be close to .text */
*(.text.hot TEXT_MAIN .text.fixup .text.unlikely .fixup __ftr_alt_* .ref.text);
+#ifdef CONFIG_PPC64
+ *(.tramp.ftrace.text);
+#endif
SCHED_TEXT
CPUIDLE_TEXT
LOCK_TEXT
@@ -181,7 +184,15 @@ SECTIONS
*/
. = ALIGN(STRICT_ALIGN_SIZE);
__init_begin = .;
- INIT_TEXT_SECTION(PAGE_SIZE) :kernel
+ . = ALIGN(PAGE_SIZE);
+ .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
+ _sinittext = .;
+ INIT_TEXT
+ _einittext = .;
+#ifdef CONFIG_PPC64
+ *(.tramp.ftrace.init);
+#endif
+ } :kernel
/* .exit.text is discarded at runtime, not link time,
* to deal with references from __bug_table
--
2.19.1
More information about the Linuxppc-dev
mailing list