diff options
Diffstat (limited to 'patches/misc/arm64-perf-fix-backtrace-for-AAPCS-with-FP-enabled.patch')
| -rw-r--r-- | patches/misc/arm64-perf-fix-backtrace-for-AAPCS-with-FP-enabled.patch | 93 |
1 files changed, 93 insertions, 0 deletions
diff --git a/patches/misc/arm64-perf-fix-backtrace-for-AAPCS-with-FP-enabled.patch b/patches/misc/arm64-perf-fix-backtrace-for-AAPCS-with-FP-enabled.patch new file mode 100644 index 00000000..4c1e78cf --- /dev/null +++ b/patches/misc/arm64-perf-fix-backtrace-for-AAPCS-with-FP-enabled.patch @@ -0,0 +1,93 @@ +From cbbce37ccc6041d3ae3d3cb3b1918a61a39820a0 Mon Sep 17 00:00:00 2001 +From: Fang Jia <fang.jia@windriver.com> +Date: Fri, 28 Dec 2018 16:28:34 +0800 +Subject: [PATCH] arm64/perf: fix backtrace for AAPCS with FP enabled + +This change is for arm64 platform compat mode. +The change for arm32 platform has been included in this commit "perf: fix +backtrace for AAPCS with FP enabled". + +This change replaces code designed for the obsolete ARM APCS ABI, which +causes failures of the perf backtrace logic unless the gcc option +-mapcs-frame is used to build all binaries on the platform. This +obsolete gcc option forces the compiler to include the stack pointer +along with the frame pointer and link register in the stack frame +for each funciton call. The current AAPCS ABI document, doesn't +explicitly describe the frame structure when the gcc frame pointer +option, -fno-omit-frame-pointer, is enabled. However, with this option +enabled, examination of the emitted prologue instructions shows that +1) R11 is used as the frame pointer, +2) only the R11 and LR are saved onto the stack, not the stack pointer, +3) after this prologue setup, the frame pointer, R11 points to the +saved location of LR on the stack. + +The use of unsigned int arithmetic in the commit is required since +the gcc emitted pointer arithmetic uses 8-byte pointer sizes, which are +incorrect addresses for the 4-byte stack address size. + +Signed-off-by: Fang Jia <fang.jia@windriver.com> +Reviewed-by: Jiwei Sun <jiwei.sun@windriver.com> +Signed-off-by: De Huo <de.huo@windriver.com> +--- + arch/arm64/kernel/perf_callchain.c | 25 +++++++++++++++---------- + 1 file changed, 15 insertions(+), 10 deletions(-) + +diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c +index 9d63514b9836..b9bbe0b04fc1 100644 +--- a/arch/arm64/kernel/perf_callchain.c ++++ b/arch/arm64/kernel/perf_callchain.c +@@ -54,16 +54,22 @@ user_backtrace(struct frame_tail __user *tail, + + #ifdef CONFIG_COMPAT + /* +- * The registers we're interested in are at the end of the variable +- * length saved register structure. The fp points at the end of this +- * structure so the address of this struct is: +- * (struct compat_frame_tail *)(xxx->fp)-1 ++ * The AAPCS ABI, the most current replacing the obsolete APCS ABI, ++ * does not specifically describe the stack frame with respect to the ++ * frame pointer. However, the examination of emitted prologue ++ * instructions for ARM implies that with -fno-omit-framepointer, ++ * register R11 is used as the frame pointer register and saved on the ++ * stack, with LR. + * +- * This code has been adapted from the ARM OProfile support. ++ * After the prolog, the FP points to the location of the saved LR and ++ * FP+4 points to the previous frames FP as shown below: ++ * Stack Hi Mem ++ * (Value of FP)+4 Saved FP for caller ++ * (Value of FP) LR set by caller ++ * Stack Lo Mem + */ + struct compat_frame_tail { + compat_uptr_t fp; /* a (struct compat_frame_tail *) in compat mode */ +- u32 sp; + u32 lr; + } __attribute__((packed)); + +@@ -91,11 +97,10 @@ compat_user_backtrace(struct compat_frame_tail __user *tail, + * Frame pointers should strictly progress back up the stack + * (towards higher addresses). + */ +- if (tail + 1 >= (struct compat_frame_tail __user *) +- compat_ptr(buftail.fp)) ++ if ((u32)tail + 4 >= buftail.fp) + return NULL; + +- return (struct compat_frame_tail __user *)compat_ptr(buftail.fp) - 1; ++ return (struct compat_frame_tail __user *)(buftail.fp - 4); + } + #endif /* CONFIG_COMPAT */ + +@@ -123,7 +128,7 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry, + /* AARCH32 compat mode */ + struct compat_frame_tail __user *tail; + +- tail = (struct compat_frame_tail __user *)regs->compat_fp - 1; ++ tail = (struct compat_frame_tail __user *)(regs->compat_fp - 4); + + while ((entry->nr < entry->max_stack) && + tail && !((unsigned long)tail & 0x3)) +-- +2.17.1 + |