lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:   Fri, 27 Oct 2023 15:02:52 +0800
From:   Huacai Chen <chenhuacai@...nel.org>
To:     Tiezhu Yang <yangtiezhu@...ngson.cn>
Cc:     Josh Poimboeuf <jpoimboe@...nel.org>,
        Peter Zijlstra <peterz@...radead.org>,
        loongarch@...ts.linux.dev, linux-kernel@...r.kernel.org,
        loongson-kernel@...ts.loongnix.cn
Subject: Re: [PATCH v4 8/8] LoongArch: Add ORC stack unwinder support

v3 works in most cases, v4 cannot work completely (stop at show_stack), why?

[   61.412528] CPU: 1 PID: 0 Comm: swapper/1 Not tainted 6.6.0-rc7+ #1157
[   61.419017] Hardware name: Loongson
Loongson-3A5000-7A1000-1w-CRB/Loongson-LS3A5000-7A1000-1w-CRB, BIOS
vUDK2018-LoongArch-V2.0.0-prebeta9 10/21/2022
[   61.432328] pc 9000000002ad14c0 ra 9000000003d759c8 tp
90000001001e4000 sp 90000001001e7e40
[   61.440629] a0 0000000000000005 a1 0000000000000001 a2
90000001001e4000 a3 9000000003d7cdf4
[   61.448930] a4 900000010bb1f940 a5 0000000000000000 a6
0000000000000000 a7 000000000000239c
[   61.457229] t0 0000000000000000 t1 0000000000022c34 t2
4000000000000000 t3 0000000000000001
[   61.465530] t4 4000000000000000 t5 00000000000000b0 t6
0000000000000004 t7 0000000000000000
[   61.473830] t8 0000000000000000 u0 0000000000000004 s9
9000000004caa940 s0 0000000000000004
[   61.482130] s1 900000000427aa38 s2 0000000000000004 s3
0000000000000000 s4 900000000427b000
[   61.490429] s5 00000000000f0000 s6 0000000000000004 s7
000000000000039b s8 0000000000000004
[   61.498730]    ra: 9000000003d759c8 arch_cpu_idle+0x1c/0x34
[   61.504270]   ERA: 9000000002ad14c0 __arch_cpu_idle+0x20/0x24
[   61.509979]  CRMD: 000000b0 (PLV0 -IE -DA +PG DACF=CC DACM=CC -WE)
[   61.516134]  PRMD: 00000004 (PPLV0 +PIE -PWE)
[   61.520465]  EUEN: 00000000 (-FPE -SXE -ASXE -BTE)
[   61.525230]  ECFG: 00071c1c (LIE=2-4,10-12 VS=7)
[   61.529820] ESTAT: 00001000 [INT] (IS=12 ECode=0 EsubCode=0)
[   61.535446]  PRID: 0014c010 (Loongson-64bit, Loongson-3A5000)
[   61.541154] CPU: 1 PID: 0 Comm: swapper/1 Not tainted 6.6.0-rc7+ #1157
[   61.547640] Hardware name: Loongson
Loongson-3A5000-7A1000-1w-CRB/Loongson-LS3A5000-7A1000-1w-CRB, BIOS
vUDK2018-LoongArch-V2.0.0-prebeta9 10/21/2022
[   61.560952] Stack : 0000000000000000 ffffffffffffffff
9000000003d73848 90000001001e4000
[   61.568914]         900000010006fca0 0000000000000000
900000010006fca8 9000000004108e10
[   61.576875]         9000000004363958 9000000004363950
900000010006fbc0 0000000000000001
[   61.584837]         0000000000000001 83899b396b7be748
00000000069f0000 9000000100177080
[   61.592798]         0000000000000000 372d303030354133
0000000000000001 0000000000000003
[   61.600759]         6f4c203a656d616e 0000000000085b38
00000000069f0000 9000000004caa940
[   61.608721]         9000000004279000 9000000004108e10
0000000000000004 0000000000000000
[   61.616682]         90000000042833f0 90000001001e7d00
0000000000000000 0000000000000001
[   61.624644]         0000000000000004 900000010006fbf0
9000000002ad3808 00007fffec50f0f0
[   61.632605]         00000000000000b0 0000000000000004
0000000000000000 0000000000071c1c
[   61.640566]         ...
[   61.642993] Call Trace:
[   61.642995] [<9000000002ad3808>] show_stack+0x40/0x17c

Huacai

On Mon, Oct 23, 2023 at 4:11 PM Tiezhu Yang <yangtiezhu@...ngson.cn> wrote:
>
> The kernel CONFIG_UNWINDER_ORC option enables the ORC unwinder, which is
> similar in concept to a DWARF unwinder. The difference is that the format
> of the ORC data is much simpler than DWARF, which in turn allows the ORC
> unwinder to be much simpler and faster.
>
> The ORC data consists of unwind tables which are generated by objtool.
> They contain out-of-band data which is used by the in-kernel ORC unwinder.
> Objtool generates the ORC data by first doing compile-time stack metadata
> validation (CONFIG_STACK_VALIDATION). After analyzing all the code paths
> of a .o file, it determines information about the stack state at each
> instruction address in the file and outputs that information to the
> .orc_unwind and .orc_unwind_ip sections.
>
> The per-object ORC sections are combined at link time and are sorted and
> post-processed at boot time. The unwinder uses the resulting data to
> correlate instruction addresses with their stack states at run time.
>
> Most of the logic are similar with x86, in order to get ra info before ra
> is saved into stack, add ra_reg and ra_offset into orc_entry. At the same
> time, modify some arch-specific code to silence the objtool warnings.
>
> Co-developed-by: Jinyang He <hejinyang@...ngson.cn>
> Signed-off-by: Jinyang He <hejinyang@...ngson.cn>
> Co-developed-by: Youling Tang <tangyouling@...ngson.cn>
> Signed-off-by: Youling Tang <tangyouling@...ngson.cn>
> Signed-off-by: Tiezhu Yang <yangtiezhu@...ngson.cn>
> ---
>  arch/loongarch/Kconfig                    |   2 +
>  arch/loongarch/Kconfig.debug              |  11 +
>  arch/loongarch/Makefile                   |  19 ++
>  arch/loongarch/include/asm/Kbuild         |   2 +
>  arch/loongarch/include/asm/bug.h          |   1 +
>  arch/loongarch/include/asm/exception.h    |   2 +
>  arch/loongarch/include/asm/module.h       |   7 +
>  arch/loongarch/include/asm/orc_header.h   |  18 ++
>  arch/loongarch/include/asm/orc_lookup.h   |  31 ++
>  arch/loongarch/include/asm/orc_types.h    |  58 ++++
>  arch/loongarch/include/asm/stackframe.h   |   3 +
>  arch/loongarch/include/asm/unwind.h       |  19 +-
>  arch/loongarch/include/asm/unwind_hints.h |  28 ++
>  arch/loongarch/kernel/Makefile            |   4 +
>  arch/loongarch/kernel/entry.S             |   5 +
>  arch/loongarch/kernel/genex.S             |   4 +
>  arch/loongarch/kernel/module.c            |  22 +-
>  arch/loongarch/kernel/relocate_kernel.S   |   2 +
>  arch/loongarch/kernel/setup.c             |   2 +
>  arch/loongarch/kernel/stacktrace.c        |   1 +
>  arch/loongarch/kernel/traps.c             |  42 ++-
>  arch/loongarch/kernel/unwind_orc.c        | 513 ++++++++++++++++++++++++++++++
>  arch/loongarch/kernel/vmlinux.lds.S       |   3 +
>  arch/loongarch/lib/Makefile               |   2 +
>  arch/loongarch/mm/tlb.c                   |  27 +-
>  arch/loongarch/mm/tlbex.S                 |   9 +
>  arch/loongarch/vdso/Makefile              |   1 +
>  include/linux/compiler.h                  |   9 +
>  scripts/Makefile                          |   7 +-
>  29 files changed, 818 insertions(+), 36 deletions(-)
>  create mode 100644 arch/loongarch/include/asm/orc_header.h
>  create mode 100644 arch/loongarch/include/asm/orc_lookup.h
>  create mode 100644 arch/loongarch/include/asm/orc_types.h
>  create mode 100644 arch/loongarch/include/asm/unwind_hints.h
>  create mode 100644 arch/loongarch/kernel/unwind_orc.c
>
> diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
> index e14396a..21ef3bb 100644
> --- a/arch/loongarch/Kconfig
> +++ b/arch/loongarch/Kconfig
> @@ -131,6 +131,7 @@ config LOONGARCH
>         select HAVE_KRETPROBES
>         select HAVE_MOD_ARCH_SPECIFIC
>         select HAVE_NMI
> +       select HAVE_OBJTOOL if AS_HAS_EXPLICIT_RELOCS
>         select HAVE_PCI
>         select HAVE_PERF_EVENTS
>         select HAVE_PERF_REGS
> @@ -141,6 +142,7 @@ config LOONGARCH
>         select HAVE_SAMPLE_FTRACE_DIRECT
>         select HAVE_SAMPLE_FTRACE_DIRECT_MULTI
>         select HAVE_SETUP_PER_CPU_AREA if NUMA
> +       select HAVE_STACK_VALIDATION if HAVE_OBJTOOL
>         select HAVE_STACKPROTECTOR
>         select HAVE_SYSCALL_TRACEPOINTS
>         select HAVE_TIF_NOHZ
> diff --git a/arch/loongarch/Kconfig.debug b/arch/loongarch/Kconfig.debug
> index 8d36aab..98d6063 100644
> --- a/arch/loongarch/Kconfig.debug
> +++ b/arch/loongarch/Kconfig.debug
> @@ -26,4 +26,15 @@ config UNWINDER_PROLOGUE
>           Some of the addresses it reports may be incorrect (but better than the
>           Guess unwinder).
>
> +config UNWINDER_ORC
> +       bool "ORC unwinder"
> +       select OBJTOOL
> +       help
> +         This option enables the ORC (Oops Rewind Capability) unwinder for
> +         unwinding kernel stack traces.  It uses a custom data format which is
> +         a simplified version of the DWARF Call Frame Information standard.
> +
> +         Enabling this option will increase the kernel's runtime memory usage
> +         by roughly 2-4MB, depending on your kernel config.
> +
>  endchoice
> diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile
> index fb0fada..93ebdc3 100644
> --- a/arch/loongarch/Makefile
> +++ b/arch/loongarch/Makefile
> @@ -25,6 +25,18 @@ endif
>  32bit-emul             = elf32loongarch
>  64bit-emul             = elf64loongarch
>
> +ifdef CONFIG_UNWINDER_ORC
> +orc_hash_h := arch/$(SRCARCH)/include/generated/asm/orc_hash.h
> +orc_hash_sh := $(srctree)/scripts/orc_hash.sh
> +targets += $(orc_hash_h)
> +quiet_cmd_orc_hash = GEN     $@
> +      cmd_orc_hash = mkdir -p $(dir $@); \
> +                    $(CONFIG_SHELL) $(orc_hash_sh) < $< > $@
> +$(orc_hash_h): $(srctree)/arch/loongarch/include/asm/orc_types.h $(orc_hash_sh) FORCE
> +       $(call if_changed,orc_hash)
> +archprepare: $(orc_hash_h)
> +endif
> +
>  ifdef CONFIG_DYNAMIC_FTRACE
>  KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY
>  CC_FLAGS_FTRACE := -fpatchable-function-entry=2
> @@ -78,6 +90,13 @@ KBUILD_AFLAGS_MODULE         += -Wa,-mla-global-with-abs
>  KBUILD_CFLAGS_MODULE           += -fplt -Wa,-mla-global-with-abs,-mla-local-with-abs
>  endif
>
> +KBUILD_AFLAGS                  += $(call cc-option,-mthin-add-sub) $(call cc-option,-Wa$(comma)-mthin-add-sub)
> +KBUILD_CFLAGS                  += $(call cc-option,-mthin-add-sub) $(call cc-option,-Wa$(comma)-mthin-add-sub)
> +
> +ifdef CONFIG_OBJTOOL
> +KBUILD_CFLAGS                  += -fno-optimize-sibling-calls -fno-jump-tables -falign-functions=4
> +endif
> +
>  ifeq ($(CONFIG_RELOCATABLE),y)
>  KBUILD_CFLAGS_KERNEL           += -fPIE
>  LDFLAGS_vmlinux                        += -static -pie --no-dynamic-linker -z notext
> diff --git a/arch/loongarch/include/asm/Kbuild b/arch/loongarch/include/asm/Kbuild
> index 93783fa..a97c0ed 100644
> --- a/arch/loongarch/include/asm/Kbuild
> +++ b/arch/loongarch/include/asm/Kbuild
> @@ -1,4 +1,6 @@
>  # SPDX-License-Identifier: GPL-2.0
> +generated-y += orc_hash.h
> +
>  generic-y += dma-contiguous.h
>  generic-y += mcs_spinlock.h
>  generic-y += parport.h
> diff --git a/arch/loongarch/include/asm/bug.h b/arch/loongarch/include/asm/bug.h
> index d4ca3ba..0838887 100644
> --- a/arch/loongarch/include/asm/bug.h
> +++ b/arch/loongarch/include/asm/bug.h
> @@ -44,6 +44,7 @@
>  do {                                                           \
>         instrumentation_begin();                                \
>         __BUG_FLAGS(BUGFLAG_WARNING|(flags));                   \
> +       annotate_reachable();                                   \
>         instrumentation_end();                                  \
>  } while (0)
>
> diff --git a/arch/loongarch/include/asm/exception.h b/arch/loongarch/include/asm/exception.h
> index af74a3f..c6d2073 100644
> --- a/arch/loongarch/include/asm/exception.h
> +++ b/arch/loongarch/include/asm/exception.h
> @@ -6,6 +6,8 @@
>  #include <asm/ptrace.h>
>  #include <linux/kprobes.h>
>
> +extern void *exception_table[];
> +
>  void show_registers(struct pt_regs *regs);
>
>  asmlinkage void cache_parity_error(void);
> diff --git a/arch/loongarch/include/asm/module.h b/arch/loongarch/include/asm/module.h
> index 2ecd82b..f33f3fd 100644
> --- a/arch/loongarch/include/asm/module.h
> +++ b/arch/loongarch/include/asm/module.h
> @@ -6,6 +6,7 @@
>  #define _ASM_MODULE_H
>
>  #include <asm/inst.h>
> +#include <asm/orc_types.h>
>  #include <asm-generic/module.h>
>
>  #define RELA_STACK_DEPTH 16
> @@ -21,6 +22,12 @@ struct mod_arch_specific {
>         struct mod_section plt;
>         struct mod_section plt_idx;
>
> +#ifdef CONFIG_UNWINDER_ORC
> +       unsigned int num_orcs;
> +       int *orc_unwind_ip;
> +       struct orc_entry *orc_unwind;
> +#endif
> +
>         /* For CONFIG_DYNAMIC_FTRACE */
>         struct plt_entry *ftrace_trampolines;
>  };
> diff --git a/arch/loongarch/include/asm/orc_header.h b/arch/loongarch/include/asm/orc_header.h
> new file mode 100644
> index 0000000..f9d509c
> --- /dev/null
> +++ b/arch/loongarch/include/asm/orc_header.h
> @@ -0,0 +1,18 @@
> +/* SPDX-License-Identifier: GPL-2.0-or-later */
> +
> +#ifndef _ORC_HEADER_H
> +#define _ORC_HEADER_H
> +
> +#include <linux/types.h>
> +#include <linux/compiler.h>
> +#include <asm/orc_hash.h>
> +
> +/*
> + * The header is currently a 20-byte hash of the ORC entry definition; see
> + * scripts/orc_hash.sh.
> + */
> +#define ORC_HEADER                                     \
> +       __used __section(".orc_header") __aligned(4)    \
> +       static const u8 orc_header[] = { ORC_HASH }
> +
> +#endif /* _ORC_HEADER_H */
> diff --git a/arch/loongarch/include/asm/orc_lookup.h b/arch/loongarch/include/asm/orc_lookup.h
> new file mode 100644
> index 0000000..b02e635
> --- /dev/null
> +++ b/arch/loongarch/include/asm/orc_lookup.h
> @@ -0,0 +1,31 @@
> +/* SPDX-License-Identifier: GPL-2.0-or-later */
> +#ifndef _ORC_LOOKUP_H
> +#define _ORC_LOOKUP_H
> +
> +/*
> + * This is a lookup table for speeding up access to the .orc_unwind table.
> + * Given an input address offset, the corresponding lookup table entry
> + * specifies a subset of the .orc_unwind table to search.
> + *
> + * Each block represents the end of the previous range and the start of the
> + * next range.  An extra block is added to give the last range an end.
> + *
> + * The block size should be a power of 2 to avoid a costly 'div' instruction.
> + *
> + * A block size of 256 was chosen because it roughly doubles unwinder
> + * performance while only adding ~5% to the ORC data footprint.
> + */
> +#define LOOKUP_BLOCK_ORDER     8
> +#define LOOKUP_BLOCK_SIZE      (1 << LOOKUP_BLOCK_ORDER)
> +
> +#ifndef LINKER_SCRIPT
> +
> +extern unsigned int orc_lookup[];
> +extern unsigned int orc_lookup_end[];
> +
> +#define LOOKUP_START_IP                (unsigned long)_stext
> +#define LOOKUP_STOP_IP         (unsigned long)_etext
> +
> +#endif /* LINKER_SCRIPT */
> +
> +#endif /* _ORC_LOOKUP_H */
> diff --git a/arch/loongarch/include/asm/orc_types.h b/arch/loongarch/include/asm/orc_types.h
> new file mode 100644
> index 0000000..caf1f71
> --- /dev/null
> +++ b/arch/loongarch/include/asm/orc_types.h
> @@ -0,0 +1,58 @@
> +/* SPDX-License-Identifier: GPL-2.0-or-later */
> +#ifndef _ORC_TYPES_H
> +#define _ORC_TYPES_H
> +
> +#include <linux/types.h>
> +
> +/*
> + * The ORC_REG_* registers are base registers which are used to find other
> + * registers on the stack.
> + *
> + * ORC_REG_PREV_SP, also known as DWARF Call Frame Address (CFA), is the
> + * address of the previous frame: the caller's SP before it called the current
> + * function.
> + *
> + * ORC_REG_UNDEFINED means the corresponding register's value didn't change in
> + * the current frame.
> + *
> + * The most commonly used base registers are SP and FP -- which the previous SP
> + * is usually based on -- and PREV_SP and UNDEFINED -- which the previous FP is
> + * usually based on.
> + *
> + * The rest of the base registers are needed for special cases like entry code
> + * and GCC realigned stacks.
> + */
> +#define ORC_REG_UNDEFINED              0
> +#define ORC_REG_PREV_SP                        1
> +#define ORC_REG_SP                     2
> +#define ORC_REG_FP                     3
> +#define ORC_REG_MAX                    4
> +
> +#define ORC_TYPE_UNDEFINED             0
> +#define ORC_TYPE_END_OF_STACK          1
> +#define ORC_TYPE_CALL                  2
> +#define ORC_TYPE_REGS                  3
> +#define ORC_TYPE_REGS_PARTIAL          4
> +
> +#ifndef __ASSEMBLY__
> +/*
> + * This struct is more or less a vastly simplified version of the DWARF Call
> + * Frame Information standard.  It contains only the necessary parts of DWARF
> + * CFI, simplified for ease of access by the in-kernel unwinder.  It tells the
> + * unwinder how to find the previous SP and FP (and sometimes entry regs) on
> + * the stack for a given code address.  Each instance of the struct corresponds
> + * to one or more code locations.
> + */
> +struct orc_entry {
> +       s16             sp_offset;
> +       s16             fp_offset;
> +       s16             ra_offset;
> +       unsigned int    sp_reg:4;
> +       unsigned int    fp_reg:4;
> +       unsigned int    ra_reg:4;
> +       unsigned int    type:3;
> +       unsigned int    signal:1;
> +};
> +#endif /* __ASSEMBLY__ */
> +
> +#endif /* _ORC_TYPES_H */
> diff --git a/arch/loongarch/include/asm/stackframe.h b/arch/loongarch/include/asm/stackframe.h
> index 4fb1e64..45b507a 100644
> --- a/arch/loongarch/include/asm/stackframe.h
> +++ b/arch/loongarch/include/asm/stackframe.h
> @@ -13,6 +13,7 @@
>  #include <asm/asm-offsets.h>
>  #include <asm/loongarch.h>
>  #include <asm/thread_info.h>
> +#include <asm/unwind_hints.h>
>
>  /* Make the addition of cfi info a little easier. */
>         .macro cfi_rel_offset reg offset=0 docfi=0
> @@ -162,6 +163,7 @@
>         li.w    t0, CSR_CRMD_WE
>         csrxchg t0, t0, LOONGARCH_CSR_CRMD
>  #endif
> +       UNWIND_HINT_REGS
>         .endm
>
>         .macro  SAVE_ALL docfi=0
> @@ -219,6 +221,7 @@
>
>         .macro  RESTORE_SP_AND_RET docfi=0
>         cfi_ld  sp, PT_R3, \docfi
> +       UNWIND_HINT_FUNC
>         ertn
>         .endm
>
> diff --git a/arch/loongarch/include/asm/unwind.h b/arch/loongarch/include/asm/unwind.h
> index b9dce87..c7f52d4 100644
> --- a/arch/loongarch/include/asm/unwind.h
> +++ b/arch/loongarch/include/asm/unwind.h
> @@ -16,6 +16,7 @@
>  enum unwinder_type {
>         UNWINDER_GUESS,
>         UNWINDER_PROLOGUE,
> +       UNWINDER_ORC,
>  };
>
>  struct unwind_state {
> @@ -24,7 +25,7 @@ struct unwind_state {
>         struct task_struct *task;
>         bool first, error, reset;
>         int graph_idx;
> -       unsigned long sp, pc, ra;
> +       unsigned long sp, fp, pc, ra;
>  };
>
>  bool default_next_frame(struct unwind_state *state);
> @@ -34,6 +35,14 @@ void unwind_start(struct unwind_state *state,
>  bool unwind_next_frame(struct unwind_state *state);
>  unsigned long unwind_get_return_address(struct unwind_state *state);
>
> +#ifdef CONFIG_UNWINDER_ORC
> +void unwind_init(void);
> +void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, void *orc, size_t orc_size);
> +#else
> +static inline void unwind_init(void) {}
> +static inline void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, void *orc, size_t orc_size) {}
> +#endif
> +
>  static inline bool unwind_done(struct unwind_state *state)
>  {
>         return state->stack_info.type == STACK_TYPE_UNKNOWN;
> @@ -61,14 +70,17 @@ static __always_inline void __unwind_start(struct unwind_state *state,
>                 state->sp = regs->regs[3];
>                 state->pc = regs->csr_era;
>                 state->ra = regs->regs[1];
> +               state->fp = regs->regs[22];
>         } else if (task && task != current) {
>                 state->sp = thread_saved_fp(task);
>                 state->pc = thread_saved_ra(task);
>                 state->ra = 0;
> +               state->fp = 0;
>         } else {
>                 state->sp = (unsigned long)__builtin_frame_address(0);
>                 state->pc = (unsigned long)__builtin_return_address(0);
>                 state->ra = 0;
> +               state->fp = 0;
>         }
>         state->task = task;
>         get_stack_info(state->sp, state->task, &state->stack_info);
> @@ -77,6 +89,9 @@ static __always_inline void __unwind_start(struct unwind_state *state,
>
>  static __always_inline unsigned long __unwind_get_return_address(struct unwind_state *state)
>  {
> -       return unwind_done(state) ? 0 : state->pc;
> +       if (unwind_done(state))
> +               return 0;
> +
> +       return __kernel_text_address(state->pc) ? state->pc : 0;
>  }
>  #endif /* _ASM_UNWIND_H */
> diff --git a/arch/loongarch/include/asm/unwind_hints.h b/arch/loongarch/include/asm/unwind_hints.h
> new file mode 100644
> index 0000000..82443fe
> --- /dev/null
> +++ b/arch/loongarch/include/asm/unwind_hints.h
> @@ -0,0 +1,28 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +#ifndef _ASM_LOONGARCH_UNWIND_HINTS_H
> +#define _ASM_LOONGARCH_UNWIND_HINTS_H
> +
> +#include <linux/objtool.h>
> +#include <asm/orc_types.h>
> +
> +#ifdef __ASSEMBLY__
> +
> +.macro UNWIND_HINT_UNDEFINED
> +       UNWIND_HINT type=UNWIND_HINT_TYPE_UNDEFINED
> +.endm
> +
> +.macro UNWIND_HINT_EMPTY
> +       UNWIND_HINT sp_reg=ORC_REG_UNDEFINED type=UNWIND_HINT_TYPE_CALL
> +.endm
> +
> +.macro UNWIND_HINT_REGS
> +       UNWIND_HINT sp_reg=ORC_REG_SP type=UNWIND_HINT_TYPE_REGS
> +.endm
> +
> +.macro UNWIND_HINT_FUNC
> +       UNWIND_HINT sp_reg=ORC_REG_SP type=UNWIND_HINT_TYPE_CALL
> +.endm
> +
> +#endif /* __ASSEMBLY__ */
> +
> +#endif /* _ASM_LOONGARCH_UNWIND_HINTS_H */
> diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile
> index 4fcc168..ac47e11 100644
> --- a/arch/loongarch/kernel/Makefile
> +++ b/arch/loongarch/kernel/Makefile
> @@ -3,6 +3,8 @@
>  # Makefile for the Linux/LoongArch kernel.
>  #
>
> +OBJECT_FILES_NON_STANDARD_head.o := y
> +
>  extra-y                := vmlinux.lds
>
>  obj-y          += head.o cpu-probe.o cacheinfo.o env.o setup.o entry.o genex.o \
> @@ -21,6 +23,7 @@ obj-$(CONFIG_ARCH_STRICT_ALIGN)       += unaligned.o
>
>  CFLAGS_module.o                += $(call cc-option,-Wno-override-init,)
>  CFLAGS_syscall.o       += $(call cc-option,-Wno-override-init,)
> +CFLAGS_traps.o         += $(call cc-option,-Wno-override-init,)
>  CFLAGS_perf_event.o    += $(call cc-option,-Wno-override-init,)
>
>  ifdef CONFIG_FUNCTION_TRACER
> @@ -62,6 +65,7 @@ obj-$(CONFIG_CRASH_DUMP)      += crash_dump.o
>
>  obj-$(CONFIG_UNWINDER_GUESS)   += unwind_guess.o
>  obj-$(CONFIG_UNWINDER_PROLOGUE) += unwind_prologue.o
> +obj-$(CONFIG_UNWINDER_ORC)     += unwind_orc.o
>
>  obj-$(CONFIG_PERF_EVENTS)      += perf_event.o perf_regs.o
>  obj-$(CONFIG_HAVE_HW_BREAKPOINT)       += hw_breakpoint.o
> diff --git a/arch/loongarch/kernel/entry.S b/arch/loongarch/kernel/entry.S
> index 1ec8e4c..48e7e34 100644
> --- a/arch/loongarch/kernel/entry.S
> +++ b/arch/loongarch/kernel/entry.S
> @@ -14,11 +14,13 @@
>  #include <asm/regdef.h>
>  #include <asm/stackframe.h>
>  #include <asm/thread_info.h>
> +#include <asm/unwind_hints.h>
>
>         .text
>         .cfi_sections   .debug_frame
>         .align  5
>  SYM_CODE_START(handle_syscall)
> +       UNWIND_HINT_UNDEFINED
>         csrrd           t0, PERCPU_BASE_KS
>         la.pcrel        t1, kernelsp
>         add.d           t1, t1, t0
> @@ -57,6 +59,7 @@ SYM_CODE_START(handle_syscall)
>         cfi_st          fp, PT_R22
>
>         SAVE_STATIC
> +       UNWIND_HINT_REGS
>
>  #ifdef CONFIG_KGDB
>         li.w            t1, CSR_CRMD_WE
> @@ -75,6 +78,7 @@ SYM_CODE_END(handle_syscall)
>  _ASM_NOKPROBE(handle_syscall)
>
>  SYM_CODE_START(ret_from_fork)
> +       UNWIND_HINT_REGS
>         bl              schedule_tail           # a0 = struct task_struct *prev
>         move            a0, sp
>         bl              syscall_exit_to_user_mode
> @@ -84,6 +88,7 @@ SYM_CODE_START(ret_from_fork)
>  SYM_CODE_END(ret_from_fork)
>
>  SYM_CODE_START(ret_from_kernel_thread)
> +       UNWIND_HINT_REGS
>         bl              schedule_tail           # a0 = struct task_struct *prev
>         move            a0, s1
>         jirl            ra, s0, 0
> diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S
> index 2bb3aa2..3f18e3b 100644
> --- a/arch/loongarch/kernel/genex.S
> +++ b/arch/loongarch/kernel/genex.S
> @@ -32,6 +32,7 @@ SYM_FUNC_START(__arch_cpu_idle)
>  SYM_FUNC_END(__arch_cpu_idle)
>
>  SYM_CODE_START(handle_vint)
> +       UNWIND_HINT_UNDEFINED
>         BACKUP_T0T1
>         SAVE_ALL
>         la_abs  t1, __arch_cpu_idle
> @@ -49,6 +50,7 @@ SYM_CODE_START(handle_vint)
>  SYM_CODE_END(handle_vint)
>
>  SYM_CODE_START(except_vec_cex)
> +       UNWIND_HINT_UNDEFINED
>         b       cache_parity_error
>  SYM_CODE_END(except_vec_cex)
>
> @@ -67,6 +69,7 @@ SYM_CODE_END(except_vec_cex)
>         .macro  BUILD_HANDLER exception handler prep
>         .align  5
>         SYM_CODE_START(handle_\exception)
> +       UNWIND_HINT_UNDEFINED
>         666:
>         BACKUP_T0T1
>         SAVE_ALL
> @@ -94,6 +97,7 @@ SYM_CODE_END(except_vec_cex)
>         BUILD_HANDLER reserved reserved none    /* others */
>
>  SYM_CODE_START(handle_sys)
> +       UNWIND_HINT_UNDEFINED
>         la_abs  t0, handle_syscall
>         jr      t0
>  SYM_CODE_END(handle_sys)
> diff --git a/arch/loongarch/kernel/module.c b/arch/loongarch/kernel/module.c
> index b13b285..c7d0338 100644
> --- a/arch/loongarch/kernel/module.c
> +++ b/arch/loongarch/kernel/module.c
> @@ -20,6 +20,7 @@
>  #include <linux/kernel.h>
>  #include <asm/alternative.h>
>  #include <asm/inst.h>
> +#include <asm/unwind.h>
>
>  static int rela_stack_push(s64 stack_value, s64 *rela_stack, size_t *rela_stack_top)
>  {
> @@ -515,15 +516,28 @@ static void module_init_ftrace_plt(const Elf_Ehdr *hdr,
>  int module_finalize(const Elf_Ehdr *hdr,
>                     const Elf_Shdr *sechdrs, struct module *mod)
>  {
> -       const Elf_Shdr *s, *se;
>         const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
> +       const Elf_Shdr *s, *alt = NULL, *orc = NULL, *orc_ip = NULL, *ftrace = NULL;
>
> -       for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) {
> +       for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
>                 if (!strcmp(".altinstructions", secstrs + s->sh_name))
> -                       apply_alternatives((void *)s->sh_addr, (void *)s->sh_addr + s->sh_size);
> +                       alt = s;
> +               if (!strcmp(".orc_unwind", secstrs + s->sh_name))
> +                       orc = s;
> +               if (!strcmp(".orc_unwind_ip", secstrs + s->sh_name))
> +                       orc_ip = s;
>                 if (!strcmp(".ftrace_trampoline", secstrs + s->sh_name))
> -                       module_init_ftrace_plt(hdr, s, mod);
> +                       ftrace = s;
>         }
>
> +       if (alt)
> +               apply_alternatives((void *)alt->sh_addr, (void *)alt->sh_addr + alt->sh_size);
> +
> +       if (orc && orc_ip)
> +               unwind_module_init(mod, (void *)orc_ip->sh_addr, orc_ip->sh_size, (void *)orc->sh_addr, orc->sh_size);
> +
> +       if (ftrace)
> +               module_init_ftrace_plt(hdr, ftrace, mod);
> +
>         return 0;
>  }
> diff --git a/arch/loongarch/kernel/relocate_kernel.S b/arch/loongarch/kernel/relocate_kernel.S
> index f49f6b0..bcc191d 100644
> --- a/arch/loongarch/kernel/relocate_kernel.S
> +++ b/arch/loongarch/kernel/relocate_kernel.S
> @@ -15,6 +15,7 @@
>  #include <asm/addrspace.h>
>
>  SYM_CODE_START(relocate_new_kernel)
> +       UNWIND_HINT_UNDEFINED
>         /*
>          * a0: EFI boot flag for the new kernel
>          * a1: Command line pointer for the new kernel
> @@ -90,6 +91,7 @@ SYM_CODE_END(relocate_new_kernel)
>   * then start at the entry point from LOONGARCH_IOCSR_MBUF0.
>   */
>  SYM_CODE_START(kexec_smp_wait)
> +       UNWIND_HINT_UNDEFINED
>  1:     li.w            t0, 0x100                       /* wait for init loop */
>  2:     addi.w          t0, t0, -1                      /* limit mailbox access */
>         bnez            t0, 2b
> diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
> index aed65915..613f04d 100644
> --- a/arch/loongarch/kernel/setup.c
> +++ b/arch/loongarch/kernel/setup.c
> @@ -48,6 +48,7 @@
>  #include <asm/sections.h>
>  #include <asm/setup.h>
>  #include <asm/time.h>
> +#include <asm/unwind.h>
>
>  #define SMBIOS_BIOSSIZE_OFFSET         0x09
>  #define SMBIOS_BIOSEXTERN_OFFSET       0x13
> @@ -606,6 +607,7 @@ static void __init prefill_possible_map(void)
>  void __init setup_arch(char **cmdline_p)
>  {
>         cpu_probe();
> +       unwind_init();
>
>         init_environ();
>         efi_init();
> diff --git a/arch/loongarch/kernel/stacktrace.c b/arch/loongarch/kernel/stacktrace.c
> index 92270f1..9848d42 100644
> --- a/arch/loongarch/kernel/stacktrace.c
> +++ b/arch/loongarch/kernel/stacktrace.c
> @@ -29,6 +29,7 @@ void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
>                         regs->csr_era = thread_saved_ra(task);
>                 }
>                 regs->regs[1] = 0;
> +               regs->regs[22] = 0;
>         }
>
>         for (unwind_start(&state, task, regs);
> diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c
> index aebfc37..f9f4eb0 100644
> --- a/arch/loongarch/kernel/traps.c
> +++ b/arch/loongarch/kernel/traps.c
> @@ -53,6 +53,32 @@
>
>  #include "access-helper.h"
>
> +void *exception_table[EXCCODE_INT_START] = {
> +       [0 ... EXCCODE_INT_START - 1] = handle_reserved,
> +
> +       [EXCCODE_TLBI]          = handle_tlb_load,
> +       [EXCCODE_TLBL]          = handle_tlb_load,
> +       [EXCCODE_TLBS]          = handle_tlb_store,
> +       [EXCCODE_TLBM]          = handle_tlb_modify,
> +       [EXCCODE_TLBNR]         = handle_tlb_protect,
> +       [EXCCODE_TLBNX]         = handle_tlb_protect,
> +       [EXCCODE_TLBPE]         = handle_tlb_protect,
> +       [EXCCODE_ADE]           = handle_ade,
> +       [EXCCODE_ALE]           = handle_ale,
> +       [EXCCODE_BCE]           = handle_bce,
> +       [EXCCODE_SYS]           = handle_sys,
> +       [EXCCODE_BP]            = handle_bp,
> +       [EXCCODE_INE]           = handle_ri,
> +       [EXCCODE_IPE]           = handle_ri,
> +       [EXCCODE_FPDIS]         = handle_fpu,
> +       [EXCCODE_LSXDIS]        = handle_lsx,
> +       [EXCCODE_LASXDIS]       = handle_lasx,
> +       [EXCCODE_FPE]           = handle_fpe,
> +       [EXCCODE_WATCH]         = handle_watch,
> +       [EXCCODE_BTDIS]         = handle_lbt,
> +};
> +EXPORT_SYMBOL_GPL(exception_table);
> +
>  static void show_backtrace(struct task_struct *task, const struct pt_regs *regs,
>                            const char *loglvl, bool user)
>  {
> @@ -1150,19 +1176,9 @@ void __init trap_init(void)
>         for (i = EXCCODE_INT_START; i <= EXCCODE_INT_END; i++)
>                 set_handler(i * VECSIZE, handle_vint, VECSIZE);
>
> -       set_handler(EXCCODE_ADE * VECSIZE, handle_ade, VECSIZE);
> -       set_handler(EXCCODE_ALE * VECSIZE, handle_ale, VECSIZE);
> -       set_handler(EXCCODE_BCE * VECSIZE, handle_bce, VECSIZE);
> -       set_handler(EXCCODE_SYS * VECSIZE, handle_sys, VECSIZE);
> -       set_handler(EXCCODE_BP * VECSIZE, handle_bp, VECSIZE);
> -       set_handler(EXCCODE_INE * VECSIZE, handle_ri, VECSIZE);
> -       set_handler(EXCCODE_IPE * VECSIZE, handle_ri, VECSIZE);
> -       set_handler(EXCCODE_FPDIS * VECSIZE, handle_fpu, VECSIZE);
> -       set_handler(EXCCODE_LSXDIS * VECSIZE, handle_lsx, VECSIZE);
> -       set_handler(EXCCODE_LASXDIS * VECSIZE, handle_lasx, VECSIZE);
> -       set_handler(EXCCODE_FPE * VECSIZE, handle_fpe, VECSIZE);
> -       set_handler(EXCCODE_BTDIS * VECSIZE, handle_lbt, VECSIZE);
> -       set_handler(EXCCODE_WATCH * VECSIZE, handle_watch, VECSIZE);
> +       /* Set exception vector handler */
> +       for (i = EXCCODE_ADE; i <= EXCCODE_BTDIS; i++)
> +               set_handler(i * VECSIZE, exception_table[i], VECSIZE);
>
>         cache_error_setup();
>
> diff --git a/arch/loongarch/kernel/unwind_orc.c b/arch/loongarch/kernel/unwind_orc.c
> new file mode 100644
> index 0000000..9be5cead
> --- /dev/null
> +++ b/arch/loongarch/kernel/unwind_orc.c
> @@ -0,0 +1,513 @@
> +// SPDX-License-Identifier: GPL-2.0-only
> +#include <linux/objtool.h>
> +#include <linux/module.h>
> +#include <linux/sort.h>
> +#include <asm/exception.h>
> +#include <asm/orc_header.h>
> +#include <asm/orc_lookup.h>
> +#include <asm/orc_types.h>
> +#include <asm/ptrace.h>
> +#include <asm/setup.h>
> +#include <asm/stacktrace.h>
> +#include <asm/tlb.h>
> +#include <asm/unwind.h>
> +
> +ORC_HEADER;
> +
> +#define orc_warn(fmt, ...) \
> +       printk_deferred_once(KERN_WARNING "WARNING: " fmt, ##__VA_ARGS__)
> +
> +extern int __start_orc_unwind_ip[];
> +extern int __stop_orc_unwind_ip[];
> +extern struct orc_entry __start_orc_unwind[];
> +extern struct orc_entry __stop_orc_unwind[];
> +
> +static bool orc_init __ro_after_init;
> +static unsigned int lookup_num_blocks __ro_after_init;
> +
> +/* Fake frame pointer entry -- used as a fallback for generated code */
> +static struct orc_entry orc_fp_entry = {
> +       .sp_reg         = ORC_REG_FP,
> +       .sp_offset      = 16,
> +       .fp_reg         = ORC_REG_PREV_SP,
> +       .fp_offset      = -16,
> +       .ra_reg         = ORC_REG_PREV_SP,
> +       .ra_offset      = -8,
> +       .type           = ORC_TYPE_CALL
> +};
> +
> +/*
> + * If we crash with IP==0, the last successfully executed instruction
> + * was probably an indirect function call with a NULL function pointer,
> + * and we don't have unwind information for NULL.
> + * This hardcoded ORC entry for IP==0 allows us to unwind from a NULL function
> + * pointer into its parent and then continue normally from there.
> + */
> +static struct orc_entry orc_null_entry = {
> +       .sp_reg         = ORC_REG_SP,
> +       .sp_offset      = sizeof(long),
> +       .fp_reg         = ORC_REG_UNDEFINED,
> +       .type           = ORC_TYPE_CALL
> +};
> +
> +static inline unsigned long orc_ip(const int *ip)
> +{
> +       return (unsigned long)ip + *ip;
> +}
> +
> +static struct orc_entry *__orc_find(int *ip_table, struct orc_entry *u_table,
> +                                   unsigned int num_entries, unsigned long ip)
> +{
> +       int *first = ip_table;
> +       int *mid = first, *found = first;
> +       int *last = ip_table + num_entries - 1;
> +
> +       if (!num_entries)
> +               return NULL;
> +
> +       /*
> +        * Do a binary range search to find the rightmost duplicate of a given
> +        * starting address.  Some entries are section terminators which are
> +        * "weak" entries for ensuring there are no gaps.  They should be
> +        * ignored when they conflict with a real entry.
> +        */
> +       while (first <= last) {
> +               mid = first + ((last - first) / 2);
> +
> +               if (orc_ip(mid) <= ip) {
> +                       found = mid;
> +                       first = mid + 1;
> +               } else
> +                       last = mid - 1;
> +       }
> +
> +       return u_table + (found - ip_table);
> +}
> +
> +#ifdef CONFIG_MODULES
> +static struct orc_entry *orc_module_find(unsigned long ip)
> +{
> +       struct module *mod;
> +
> +       mod = __module_address(ip);
> +       if (!mod || !mod->arch.orc_unwind || !mod->arch.orc_unwind_ip)
> +               return NULL;
> +
> +       return __orc_find(mod->arch.orc_unwind_ip, mod->arch.orc_unwind, mod->arch.num_orcs, ip);
> +}
> +#else
> +static struct orc_entry *orc_module_find(unsigned long ip)
> +{
> +       return NULL;
> +}
> +#endif
> +
> +#ifdef CONFIG_DYNAMIC_FTRACE
> +static struct orc_entry *orc_find(unsigned long ip);
> +
> +/*
> + * Ftrace dynamic trampolines do not have orc entries of their own.
> + * But they are copies of the ftrace entries that are static and
> + * defined in ftrace_*.S, which do have orc entries.
> + *
> + * If the unwinder comes across a ftrace trampoline, then find the
> + * ftrace function that was used to create it, and use that ftrace
> + * function's orc entry, as the placement of the return code in
> + * the stack will be identical.
> + */
> +static struct orc_entry *orc_ftrace_find(unsigned long ip)
> +{
> +       struct ftrace_ops *ops;
> +       unsigned long tramp_addr, offset;
> +
> +       ops = ftrace_ops_trampoline(ip);
> +       if (!ops)
> +               return NULL;
> +
> +       /* Set tramp_addr to the start of the code copied by the trampoline */
> +       if (ops->flags & FTRACE_OPS_FL_SAVE_REGS)
> +               tramp_addr = (unsigned long)ftrace_regs_caller;
> +       else
> +               tramp_addr = (unsigned long)ftrace_caller;
> +
> +       /* Now place tramp_addr to the location within the trampoline ip is at */
> +       offset = ip - ops->trampoline;
> +       tramp_addr += offset;
> +
> +       /* Prevent unlikely recursion */
> +       if (ip == tramp_addr)
> +               return NULL;
> +
> +       return orc_find(tramp_addr);
> +}
> +#else
> +static struct orc_entry *orc_ftrace_find(unsigned long ip)
> +{
> +       return NULL;
> +}
> +#endif
> +
> +static struct orc_entry *orc_find(unsigned long ip)
> +{
> +       static struct orc_entry *orc;
> +
> +       if (ip == 0)
> +               return &orc_null_entry;
> +
> +       /* For non-init vmlinux addresses, use the fast lookup table: */
> +       if (ip >= LOOKUP_START_IP && ip < LOOKUP_STOP_IP) {
> +               unsigned int idx, start, stop;
> +
> +               idx = (ip - LOOKUP_START_IP) / LOOKUP_BLOCK_SIZE;
> +
> +               if (unlikely((idx >= lookup_num_blocks-1))) {
> +                       orc_warn("WARNING: bad lookup idx: idx=%u num=%u ip=%pB\n",
> +                                idx, lookup_num_blocks, (void *)ip);
> +                       return NULL;
> +               }
> +
> +               start = orc_lookup[idx];
> +               stop = orc_lookup[idx + 1] + 1;
> +
> +               if (unlikely((__start_orc_unwind + start >= __stop_orc_unwind) ||
> +                            (__start_orc_unwind + stop > __stop_orc_unwind))) {
> +                       orc_warn("WARNING: bad lookup value: idx=%u num=%u start=%u stop=%u ip=%pB\n",
> +                                idx, lookup_num_blocks, start, stop, (void *)ip);
> +                       return NULL;
> +               }
> +
> +               return __orc_find(__start_orc_unwind_ip + start,
> +                                 __start_orc_unwind + start, stop - start, ip);
> +       }
> +
> +       /* vmlinux .init slow lookup: */
> +       if (is_kernel_inittext(ip))
> +               return __orc_find(__start_orc_unwind_ip, __start_orc_unwind,
> +                                 __stop_orc_unwind_ip - __start_orc_unwind_ip, ip);
> +
> +       /* Module lookup: */
> +       orc = orc_module_find(ip);
> +       if (orc)
> +               return orc;
> +
> +       return orc_ftrace_find(ip);
> +}
> +
> +#ifdef CONFIG_MODULES
> +
> +static DEFINE_MUTEX(sort_mutex);
> +static int *cur_orc_ip_table = __start_orc_unwind_ip;
> +static struct orc_entry *cur_orc_table = __start_orc_unwind;
> +
> +static void orc_sort_swap(void *_a, void *_b, int size)
> +{
> +       int delta = _b - _a;
> +       int *a = _a, *b = _b, tmp;
> +       struct orc_entry *orc_a, *orc_b;
> +
> +       /* Swap the .orc_unwind_ip entries: */
> +       tmp = *a;
> +       *a = *b + delta;
> +       *b = tmp - delta;
> +
> +       /* Swap the corresponding .orc_unwind entries: */
> +       orc_a = cur_orc_table + (a - cur_orc_ip_table);
> +       orc_b = cur_orc_table + (b - cur_orc_ip_table);
> +       swap(*orc_a, *orc_b);
> +}
> +
> +static int orc_sort_cmp(const void *_a, const void *_b)
> +{
> +       const int *a = _a, *b = _b;
> +       unsigned long a_val = orc_ip(a);
> +       unsigned long b_val = orc_ip(b);
> +       struct orc_entry *orc_a;
> +
> +       if (a_val > b_val)
> +               return 1;
> +       if (a_val < b_val)
> +               return -1;
> +
> +       /*
> +        * The "weak" section terminator entries need to always be first
> +        * to ensure the lookup code skips them in favor of real entries.
> +        * These terminator entries exist to handle any gaps created by
> +        * whitelisted .o files which didn't get objtool generation.
> +        */
> +       orc_a = cur_orc_table + (a - cur_orc_ip_table);
> +
> +       return orc_a->type == ORC_TYPE_UNDEFINED ? -1 : 1;
> +}
> +
> +void unwind_module_init(struct module *mod, void *_orc_ip, size_t orc_ip_size,
> +                       void *_orc, size_t orc_size)
> +{
> +       int *orc_ip = _orc_ip;
> +       struct orc_entry *orc = _orc;
> +       unsigned int num_entries = orc_ip_size / sizeof(int);
> +
> +       WARN_ON_ONCE(orc_ip_size % sizeof(int) != 0 ||
> +                    orc_size % sizeof(*orc) != 0 ||
> +                    num_entries != orc_size / sizeof(*orc));
> +
> +       /*
> +        * The 'cur_orc_*' globals allow the orc_sort_swap() callback to
> +        * associate an .orc_unwind_ip table entry with its corresponding
> +        * .orc_unwind entry so they can both be swapped.
> +        */
> +       mutex_lock(&sort_mutex);
> +       cur_orc_ip_table = orc_ip;
> +       cur_orc_table = orc;
> +       sort(orc_ip, num_entries, sizeof(int), orc_sort_cmp, orc_sort_swap);
> +       mutex_unlock(&sort_mutex);
> +
> +       mod->arch.orc_unwind_ip = orc_ip;
> +       mod->arch.orc_unwind = orc;
> +       mod->arch.num_orcs = num_entries;
> +}
> +#endif
> +
> +void __init unwind_init(void)
> +{
> +       int i;
> +       size_t orc_size = (void *)__stop_orc_unwind - (void *)__start_orc_unwind;
> +       size_t orc_ip_size = (void *)__stop_orc_unwind_ip - (void *)__start_orc_unwind_ip;
> +       size_t num_entries = orc_ip_size / sizeof(int);
> +       struct orc_entry *orc;
> +
> +       if (!num_entries || orc_ip_size % sizeof(int) != 0 ||
> +           orc_size % sizeof(struct orc_entry) != 0 ||
> +           num_entries != orc_size / sizeof(struct orc_entry)) {
> +               orc_warn("WARNING: Bad or missing .orc_unwind table.  Disabling unwinder.\n");
> +               return;
> +       }
> +
> +       /*
> +        * Note, the orc_unwind and orc_unwind_ip tables were already
> +        * sorted at build time via the 'sorttable' tool.
> +        * It's ready for binary search straight away, no need to sort it.
> +        */
> +
> +       /* Initialize the fast lookup table: */
> +       lookup_num_blocks = orc_lookup_end - orc_lookup;
> +       for (i = 0; i < lookup_num_blocks-1; i++) {
> +               orc = __orc_find(__start_orc_unwind_ip, __start_orc_unwind,
> +                                num_entries, LOOKUP_START_IP + (LOOKUP_BLOCK_SIZE * i));
> +               if (!orc) {
> +                       orc_warn("WARNING: Corrupt .orc_unwind table.  Disabling unwinder.\n");
> +                       return;
> +               }
> +
> +               orc_lookup[i] = orc - __start_orc_unwind;
> +       }
> +
> +       /* Initialize the ending block: */
> +       orc = __orc_find(__start_orc_unwind_ip, __start_orc_unwind, num_entries, LOOKUP_STOP_IP);
> +       if (!orc) {
> +               orc_warn("WARNING: Corrupt .orc_unwind table.  Disabling unwinder.\n");
> +               return;
> +       }
> +       orc_lookup[lookup_num_blocks-1] = orc - __start_orc_unwind;
> +
> +       orc_init = true;
> +}
> +
> +static inline bool on_stack(struct stack_info *info, unsigned long addr, size_t len)
> +{
> +       unsigned long begin = info->begin;
> +       unsigned long end   = info->end;
> +
> +       return (info->type != STACK_TYPE_UNKNOWN &&
> +               addr >= begin && addr < end && addr + len > begin && addr + len <= end);
> +}
> +
> +static bool stack_access_ok(struct unwind_state *state, unsigned long addr, size_t len)
> +{
> +       struct stack_info *info = &state->stack_info;
> +
> +       if (on_stack(info, addr, len))
> +               return true;
> +
> +       return (get_stack_info(addr, state->task, info) == 0);
> +}
> +
> +unsigned long unwind_get_return_address(struct unwind_state *state)
> +{
> +       return __unwind_get_return_address(state);
> +}
> +EXPORT_SYMBOL_GPL(unwind_get_return_address);
> +
> +void unwind_start(struct unwind_state *state, struct task_struct *task,
> +                   struct pt_regs *regs)
> +{
> +       __unwind_start(state, task, regs);
> +       state->type = UNWINDER_ORC;
> +       if (!unwind_done(state) && !__kernel_text_address(state->pc))
> +               unwind_next_frame(state);
> +}
> +EXPORT_SYMBOL_GPL(unwind_start);
> +
> +static bool is_entry_func(unsigned long addr)
> +{
> +       extern u32 kernel_entry;
> +       extern u32 kernel_entry_end;
> +
> +       return addr >= (unsigned long)&kernel_entry && addr < (unsigned long)&kernel_entry_end;
> +}
> +
> +static inline unsigned long bt_address(unsigned long ra)
> +{
> +       extern unsigned long eentry;
> +
> +       if (__kernel_text_address(ra))
> +               return ra;
> +
> +       if (__module_text_address(ra))
> +               return ra;
> +
> +       if (ra >= eentry && ra < eentry +  EXCCODE_INT_END * VECSIZE) {
> +               unsigned long func;
> +               unsigned long type = (ra - eentry) / VECSIZE;
> +               unsigned long offset = (ra - eentry) % VECSIZE;
> +
> +               switch (type) {
> +               case 0 ... EXCCODE_INT_START - 1:
> +                       func = (unsigned long)exception_table[type];
> +                       break;
> +               case EXCCODE_INT_START ... EXCCODE_INT_END:
> +                       func = (unsigned long)handle_vint;
> +                       break;
> +               default:
> +                       func = (unsigned long)handle_reserved;
> +                       break;
> +               }
> +
> +               return func + offset;
> +       }
> +
> +       return ra;
> +}
> +
> +bool unwind_next_frame(struct unwind_state *state)
> +{
> +       unsigned long *p, pc;
> +       struct pt_regs *regs;
> +       struct orc_entry *orc;
> +       struct stack_info *info = &state->stack_info;
> +
> +       if (unwind_done(state))
> +               return false;
> +
> +       /* Don't let modules unload while we're reading their ORC data. */
> +       preempt_disable();
> +
> +       if (is_entry_func(state->pc))
> +               goto end;
> +
> +       orc = orc_find(state->pc);
> +       if (!orc) {
> +               orc = &orc_fp_entry;
> +               state->error = true;
> +       }
> +
> +       switch (orc->sp_reg) {
> +       case ORC_REG_SP:
> +               state->sp = state->sp + orc->sp_offset;
> +               break;
> +       case ORC_REG_FP:
> +               state->sp = state->fp;
> +               break;
> +       default:
> +               orc_warn("unknown SP base reg %d at %pB\n", orc->sp_reg, (void *)state->pc);
> +               goto err;
> +       }
> +
> +       switch (orc->fp_reg) {
> +       case ORC_REG_PREV_SP:
> +               p = (unsigned long *)(state->sp + orc->fp_offset);
> +               if (!stack_access_ok(state, (unsigned long)p, sizeof(unsigned long)))
> +                       goto err;
> +
> +               state->fp = *p;
> +               break;
> +       case ORC_REG_UNDEFINED:
> +               /* Nothing. */
> +               break;
> +       default:
> +               orc_warn("unknown FP base reg %d at %pB\n", orc->fp_reg, (void *)state->pc);
> +               goto err;
> +       }
> +
> +       switch (orc->type) {
> +       case ORC_TYPE_CALL:
> +               if (orc->ra_reg == ORC_REG_PREV_SP) {
> +                       p = (unsigned long *)(state->sp + orc->ra_offset);
> +                       if (!stack_access_ok(state, (unsigned long)p, sizeof(unsigned long)))
> +                               goto err;
> +
> +                       pc = unwind_graph_addr(state, *p, state->sp);
> +                       pc -= LOONGARCH_INSN_SIZE;
> +               } else if (orc->ra_reg == ORC_REG_UNDEFINED) {
> +                       if (!state->ra || state->ra == state->pc)
> +                               goto err;
> +
> +                       pc = unwind_graph_addr(state, state->ra, state->sp);
> +                       pc -=  LOONGARCH_INSN_SIZE;
> +                       state->ra = 0;
> +               } else {
> +                       orc_warn("unknown ra base reg %d at %pB\n", orc->ra_reg, (void *)state->pc);
> +                       goto err;
> +               }
> +               break;
> +       case ORC_TYPE_REGS:
> +               if (state->stack_info.type == STACK_TYPE_IRQ && state->sp == info->end)
> +                       regs = (struct pt_regs *)info->next_sp;
> +               else
> +                       regs = (struct pt_regs *)state->sp;
> +
> +               if (!stack_access_ok(state, (unsigned long)regs, sizeof(*regs)))
> +                       goto err;
> +
> +               if ((info->end == (unsigned long)regs + sizeof(*regs)) &&
> +                   !regs->regs[3] && !regs->regs[1])
> +                       goto end;
> +
> +               if (user_mode(regs))
> +                       goto end;
> +
> +               pc = regs->csr_era;
> +               if (!__kernel_text_address(pc))
> +                       goto err;
> +
> +               state->sp = regs->regs[3];
> +               state->ra = regs->regs[1];
> +               state->fp = regs->regs[22];
> +               get_stack_info(state->sp, state->task, info);
> +
> +               break;
> +       default:
> +               orc_warn("unknown .orc_unwind entry type %d at %pB\n", orc->type, (void *)state->pc);
> +               goto err;
> +       }
> +
> +       state->pc = bt_address(pc);
> +       if (!state->pc) {
> +               pr_err("cannot find unwind pc at %pK\n", (void *)pc);
> +               goto err;
> +       }
> +
> +       if (!__kernel_text_address(state->pc))
> +               goto err;
> +
> +       preempt_enable();
> +       return true;
> +
> +err:
> +       state->error = true;
> +
> +end:
> +       preempt_enable();
> +       state->stack_info.type = STACK_TYPE_UNKNOWN;
> +       return false;
> +}
> +EXPORT_SYMBOL_GPL(unwind_next_frame);
> diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S
> index bb2ec86..eaa7a91 100644
> --- a/arch/loongarch/kernel/vmlinux.lds.S
> +++ b/arch/loongarch/kernel/vmlinux.lds.S
> @@ -2,6 +2,7 @@
>  #include <linux/sizes.h>
>  #include <asm/asm-offsets.h>
>  #include <asm/thread_info.h>
> +#include <asm/orc_lookup.h>
>
>  #define PAGE_SIZE _PAGE_SIZE
>  #define RO_EXCEPTION_TABLE_ALIGN       4
> @@ -122,6 +123,8 @@ SECTIONS
>         }
>  #endif
>
> +       ORC_UNWIND_TABLE
> +
>         .sdata : {
>                 *(.sdata)
>         }
> diff --git a/arch/loongarch/lib/Makefile b/arch/loongarch/lib/Makefile
> index a77bf160..e3023d9 100644
> --- a/arch/loongarch/lib/Makefile
> +++ b/arch/loongarch/lib/Makefile
> @@ -3,6 +3,8 @@
>  # Makefile for LoongArch-specific library files.
>  #
>
> +OBJECT_FILES_NON_STANDARD := y
> +
>  lib-y  += delay.o memset.o memcpy.o memmove.o \
>            clear_user.o copy_user.o csum.o dump_tlb.o unaligned.o
>
> diff --git a/arch/loongarch/mm/tlb.c b/arch/loongarch/mm/tlb.c
> index 2c0a411..f01172a 100644
> --- a/arch/loongarch/mm/tlb.c
> +++ b/arch/loongarch/mm/tlb.c
> @@ -9,8 +9,9 @@
>  #include <linux/hugetlb.h>
>  #include <linux/export.h>
>
> -#include <asm/cpu.h>
>  #include <asm/bootinfo.h>
> +#include <asm/cpu.h>
> +#include <asm/exception.h>
>  #include <asm/mmu_context.h>
>  #include <asm/pgtable.h>
>  #include <asm/tlb.h>
> @@ -266,24 +267,20 @@ static void setup_tlb_handler(int cpu)
>         setup_ptwalker();
>         local_flush_tlb_all();
>
> +       if (cpu_has_ptw) {
> +               exception_table[EXCCODE_TLBI] = handle_tlb_load_ptw;
> +               exception_table[EXCCODE_TLBL] = handle_tlb_load_ptw;
> +               exception_table[EXCCODE_TLBS] = handle_tlb_store_ptw;
> +               exception_table[EXCCODE_TLBM] = handle_tlb_modify_ptw;
> +       }
> +
>         /* The tlb handlers are generated only once */
>         if (cpu == 0) {
>                 memcpy((void *)tlbrentry, handle_tlb_refill, 0x80);
>                 local_flush_icache_range(tlbrentry, tlbrentry + 0x80);
> -               if (!cpu_has_ptw) {
> -                       set_handler(EXCCODE_TLBI * VECSIZE, handle_tlb_load, VECSIZE);
> -                       set_handler(EXCCODE_TLBL * VECSIZE, handle_tlb_load, VECSIZE);
> -                       set_handler(EXCCODE_TLBS * VECSIZE, handle_tlb_store, VECSIZE);
> -                       set_handler(EXCCODE_TLBM * VECSIZE, handle_tlb_modify, VECSIZE);
> -               } else {
> -                       set_handler(EXCCODE_TLBI * VECSIZE, handle_tlb_load_ptw, VECSIZE);
> -                       set_handler(EXCCODE_TLBL * VECSIZE, handle_tlb_load_ptw, VECSIZE);
> -                       set_handler(EXCCODE_TLBS * VECSIZE, handle_tlb_store_ptw, VECSIZE);
> -                       set_handler(EXCCODE_TLBM * VECSIZE, handle_tlb_modify_ptw, VECSIZE);
> -               }
> -               set_handler(EXCCODE_TLBNR * VECSIZE, handle_tlb_protect, VECSIZE);
> -               set_handler(EXCCODE_TLBNX * VECSIZE, handle_tlb_protect, VECSIZE);
> -               set_handler(EXCCODE_TLBPE * VECSIZE, handle_tlb_protect, VECSIZE);
> +
> +               for (int i = EXCCODE_TLBL; i <= EXCCODE_TLBPE; i++)
> +                       set_handler(i * VECSIZE, exception_table[i], VECSIZE);
>         }
>  #ifdef CONFIG_NUMA
>         else {
> diff --git a/arch/loongarch/mm/tlbex.S b/arch/loongarch/mm/tlbex.S
> index d5d682f..a44387b 100644
> --- a/arch/loongarch/mm/tlbex.S
> +++ b/arch/loongarch/mm/tlbex.S
> @@ -18,6 +18,7 @@
>
>         .macro tlb_do_page_fault, write
>         SYM_CODE_START(tlb_do_page_fault_\write)
> +       UNWIND_HINT_UNDEFINED
>         SAVE_ALL
>         csrrd           a2, LOONGARCH_CSR_BADV
>         move            a0, sp
> @@ -32,6 +33,7 @@
>         tlb_do_page_fault 1
>
>  SYM_CODE_START(handle_tlb_protect)
> +       UNWIND_HINT_UNDEFINED
>         BACKUP_T0T1
>         SAVE_ALL
>         move            a0, sp
> @@ -44,6 +46,7 @@ SYM_CODE_START(handle_tlb_protect)
>  SYM_CODE_END(handle_tlb_protect)
>
>  SYM_CODE_START(handle_tlb_load)
> +       UNWIND_HINT_UNDEFINED
>         csrwr           t0, EXCEPTION_KS0
>         csrwr           t1, EXCEPTION_KS1
>         csrwr           ra, EXCEPTION_KS2
> @@ -190,6 +193,7 @@ nopage_tlb_load:
>  SYM_CODE_END(handle_tlb_load)
>
>  SYM_CODE_START(handle_tlb_load_ptw)
> +       UNWIND_HINT_UNDEFINED
>         csrwr           t0, LOONGARCH_CSR_KS0
>         csrwr           t1, LOONGARCH_CSR_KS1
>         la_abs          t0, tlb_do_page_fault_0
> @@ -197,6 +201,7 @@ SYM_CODE_START(handle_tlb_load_ptw)
>  SYM_CODE_END(handle_tlb_load_ptw)
>
>  SYM_CODE_START(handle_tlb_store)
> +       UNWIND_HINT_UNDEFINED
>         csrwr           t0, EXCEPTION_KS0
>         csrwr           t1, EXCEPTION_KS1
>         csrwr           ra, EXCEPTION_KS2
> @@ -346,6 +351,7 @@ nopage_tlb_store:
>  SYM_CODE_END(handle_tlb_store)
>
>  SYM_CODE_START(handle_tlb_store_ptw)
> +       UNWIND_HINT_UNDEFINED
>         csrwr           t0, LOONGARCH_CSR_KS0
>         csrwr           t1, LOONGARCH_CSR_KS1
>         la_abs          t0, tlb_do_page_fault_1
> @@ -353,6 +359,7 @@ SYM_CODE_START(handle_tlb_store_ptw)
>  SYM_CODE_END(handle_tlb_store_ptw)
>
>  SYM_CODE_START(handle_tlb_modify)
> +       UNWIND_HINT_UNDEFINED
>         csrwr           t0, EXCEPTION_KS0
>         csrwr           t1, EXCEPTION_KS1
>         csrwr           ra, EXCEPTION_KS2
> @@ -500,6 +507,7 @@ nopage_tlb_modify:
>  SYM_CODE_END(handle_tlb_modify)
>
>  SYM_CODE_START(handle_tlb_modify_ptw)
> +       UNWIND_HINT_UNDEFINED
>         csrwr           t0, LOONGARCH_CSR_KS0
>         csrwr           t1, LOONGARCH_CSR_KS1
>         la_abs          t0, tlb_do_page_fault_1
> @@ -507,6 +515,7 @@ SYM_CODE_START(handle_tlb_modify_ptw)
>  SYM_CODE_END(handle_tlb_modify_ptw)
>
>  SYM_CODE_START(handle_tlb_refill)
> +       UNWIND_HINT_UNDEFINED
>         csrwr           t0, LOONGARCH_CSR_TLBRSAVE
>         csrrd           t0, LOONGARCH_CSR_PGD
>         lddir           t0, t0, 3
> diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile
> index 5c97d1463..997f41c 100644
> --- a/arch/loongarch/vdso/Makefile
> +++ b/arch/loongarch/vdso/Makefile
> @@ -3,6 +3,7 @@
>
>  KASAN_SANITIZE := n
>  KCOV_INSTRUMENT := n
> +OBJECT_FILES_NON_STANDARD := y
>
>  # Include the generic Makefile to check the built vdso.
>  include $(srctree)/lib/vdso/Makefile
> diff --git a/include/linux/compiler.h b/include/linux/compiler.h
> index d7779a1..df29ddb 100644
> --- a/include/linux/compiler.h
> +++ b/include/linux/compiler.h
> @@ -116,6 +116,14 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
>   */
>  #define __stringify_label(n) #n
>
> +#define __annotate_reachable(c) ({                                     \
> +       asm volatile(__stringify_label(c) ":\n\t"                       \
> +                       ".pushsection .discard.reachable\n\t"           \
> +                       ".long " __stringify_label(c) "b - .\n\t"       \
> +                       ".popsection\n\t");                             \
> +})
> +#define annotate_reachable() __annotate_reachable(__COUNTER__)
> +
>  #define __annotate_unreachable(c) ({                                   \
>         asm volatile(__stringify_label(c) ":\n\t"                       \
>                      ".pushsection .discard.unreachable\n\t"            \
> @@ -128,6 +136,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
>  #define __annotate_jump_table __section(".rodata..c_jump_table")
>
>  #else /* !CONFIG_OBJTOOL */
> +#define annotate_reachable()
>  #define annotate_unreachable()
>  #define __annotate_jump_table
>  #endif /* CONFIG_OBJTOOL */
> diff --git a/scripts/Makefile b/scripts/Makefile
> index 576cf64..e4cca53 100644
> --- a/scripts/Makefile
> +++ b/scripts/Makefile
> @@ -31,9 +31,12 @@ HOSTLDLIBS_sign-file = $(shell $(HOSTPKG_CONFIG) --libs libcrypto 2> /dev/null |
>
>  ifdef CONFIG_UNWINDER_ORC
>  ifeq ($(ARCH),x86_64)
> -ARCH := x86
> +SRCARCH := x86
>  endif
> -HOSTCFLAGS_sorttable.o += -I$(srctree)/tools/arch/x86/include
> +ifeq ($(ARCH),loongarch)
> +SRCARCH := loongarch
> +endif
> +HOSTCFLAGS_sorttable.o += -I$(srctree)/tools/arch/$(SRCARCH)/include
>  HOSTCFLAGS_sorttable.o += -DUNWINDER_ORC_ENABLED
>  endif
>
> --
> 2.1.0
>

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ