x86,objtool: Separate unret validation from unwind hints

The ENTRY unwind hint type is serving double duty as both an empty
unwind hint and an unret validation annotation.

Unret validation is unrelated to unwinding. Separate it out into its own
annotation.

Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/ff7448d492ea21b86d8a90264b105fbd0d751077.1677683419.git.jpoimboe@kernel.org

objtool: Remove instruction::list

Replace the instruction::list by allocating instructions in arrays of
256 entries and stringing them together by (amortized) find_insn().
This shrinks instruction by 16 bytes and brings it down to 128.

struct instruction {
- struct list_head list; /* 0 16 */
- struct hlist_node hash; /* 16 16 */
- struct list_head call_node; /* 32 16 */
- struct section * sec; /* 48 8 */
- long unsigned int offset; /* 56 8 */
- /* --- cacheline 1 boundary (64 bytes) --- */
- long unsigned int immediate; /* 64 8 */
- unsigned int len; /* 72 4 */
- u8 type; /* 76 1 */
-
- /* Bitfield combined with previous fields */
+ struct hlist_node hash; /* 0 16 */
+ struct list_head call_node; /* 16 16 */
+ struct section * sec; /* 32 8 */
+ long unsigned int offset; /* 40 8 */
+ long unsigned int immediate; /* 48 8 */
+ u8 len; /* 56 1 */
+ u8 prev_len; /* 57 1 */
+ u8 type; /* 58 1 */
+ s8 instr; /* 59 1 */
+ u32 idx:8; /* 60: 0 4 */
+ u32 dead_end:1; /* 60: 8 4 */
+ u32 ignore:1; /* 60: 9 4 */
+ u32 ignore_alts:1; /* 60:10 4 */
+ u32 hint:1; /* 60:11 4 */
+ u32 save:1; /* 60:12 4 */
+ u32 restore:1; /* 60:13 4 */
+ u32 retpoline_safe:1; /* 60:14 4 */
+ u32 noendbr:1; /* 60:15 4 */
+ u32 entry:1; /* 60:16 4 */
+ u32 visited:4; /* 60:17 4 */
+ u32 no_reloc:1; /* 60:21 4 */

- u16 dead_end:1; /* 76: 8 2 */
- u16 ignore:1; /* 76: 9 2 */
- u16 ignore_alts:1; /* 76:10 2 */
- u16 hint:1; /* 76:11 2 */
- u16 save:1; /* 76:12 2 */
- u16 restore:1; /* 76:13 2 */
- u16 retpoline_safe:1; /* 76:14 2 */
- u16 noendbr:1; /* 76:15 2 */
- u16 entry:1; /* 78: 0 2 */
- u16 visited:4; /* 78: 1 2 */
- u16 no_reloc:1; /* 78: 5 2 */
+ /* XXX 10 bits hole, try to pack */

- /* XXX 2 bits hole, try to pack */
- /* Bitfield combined with next fields */
-
- s8 instr; /* 79 1 */
- struct alt_group * alt_group; /* 80 8 */
- struct instruction * jump_dest; /* 88 8 */
- struct instruction * first_jump_src; /* 96 8 */
+ /* --- cacheline 1 boundary (64 bytes) --- */
+ struct alt_group * alt_group; /* 64 8 */
+ struct instruction * jump_dest; /* 72 8 */
+ struct instruction * first_jump_src; /* 80 8 */
union {
- struct symbol * _call_dest; /* 104 8 */
- struct reloc * _jump_table; /* 104 8 */
- }; /* 104 8 */
- struct alternative * alts; /* 112 8 */
- struct symbol * sym; /* 120 8 */
- /* --- cacheline 2 boundary (128 bytes) --- */
- struct stack_op * stack_ops; /* 128 8 */
- struct cfi_state * cfi; /* 136 8 */
+ struct symbol * _call_dest; /* 88 8 */
+ struct reloc * _jump_table; /* 88 8 */
+ }; /* 88 8 */
+ struct alternative * alts; /* 96 8 */
+ struct symbol * sym; /* 104 8 */
+ struct stack_op * stack_ops; /* 112 8 */
+ struct cfi_state * cfi; /* 120 8 */

- /* size: 144, cachelines: 3, members: 28 */
- /* sum members: 142 */
- /* sum bitfield members: 14 bits, bit holes: 1, sum bit holes: 2 bits */
- /* last cacheline: 16 bytes */
+ /* size: 128, cachelines: 2, members: 29 */
+ /* sum members: 124 */
+ /* sum bitfield members: 22 bits, bit holes: 1, sum bit holes: 10 bits */
};

pre: 5:38.18 real, 213.25 user, 124.90 sys, 23449040 mem
post: 5:03.34 real, 210.75 user, 88.80 sys, 20241232 mem

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Tested-by: Nathan Chancellor <nathan@kernel.org> # build only
Tested-by: Thomas Weißschuh <linux@weissschuh.net> # compile and run
Link: https://lore.kernel.org/r/20230208172245.851307606@infradead.org

objtool: Union instruction::{call_dest,jump_table}

The instruction call_dest and jump_table members can never be used at
the same time, their usage depends on type.

struct instruction {
struct list_head list; /* 0 16 */
struct hlist_node hash; /* 16 16 */
struct list_head call_node; /* 32 16 */
struct section * sec; /* 48 8 */
long unsigned int offset; /* 56 8 */
/* --- cacheline 1 boundary (64 bytes) --- */
long unsigned int immediate; /* 64 8 */
unsigned int len; /* 72 4 */
u8 type; /* 76 1 */

/* Bitfield combined with previous fields */

u16 dead_end:1; /* 76: 8 2 */
u16 ignore:1; /* 76: 9 2 */
u16 ignore_alts:1; /* 76:10 2 */
u16 hint:1; /* 76:11 2 */
u16 save:1; /* 76:12 2 */
u16 restore:1; /* 76:13 2 */
u16 retpoline_safe:1; /* 76:14 2 */
u16 noendbr:1; /* 76:15 2 */
u16 entry:1; /* 78: 0 2 */
u16 visited:4; /* 78: 1 2 */
u16 no_reloc:1; /* 78: 5 2 */

/* XXX 2 bits hole, try to pack */
/* Bitfield combined with next fields */

s8 instr; /* 79 1 */
struct alt_group * alt_group; /* 80 8 */
- struct symbol * call_dest; /* 88 8 */
- struct instruction * jump_dest; /* 96 8 */
- struct instruction * first_jump_src; /* 104 8 */
- struct reloc * jump_table; /* 112 8 */
- struct alternative * alts; /* 120 8 */
+ struct instruction * jump_dest; /* 88 8 */
+ struct instruction * first_jump_src; /* 96 8 */
+ union {
+ struct symbol * _call_dest; /* 104 8 */
+ struct reloc * _jump_table; /* 104 8 */
+ }; /* 104 8 */
+ struct alternative * alts; /* 112 8 */
+ struct symbol * sym; /* 120 8 */
/* --- cacheline 2 boundary (128 bytes) --- */
- struct symbol * sym; /* 128 8 */
- struct stack_op * stack_ops; /* 136 8 */
- struct cfi_state * cfi; /* 144 8 */
+ struct stack_op * stack_ops; /* 128 8 */
+ struct cfi_state * cfi; /* 136 8 */

- /* size: 152, cachelines: 3, members: 29 */
- /* sum members: 150 */
+ /* size: 144, cachelines: 3, members: 28 */
+ /* sum members: 142 */
/* sum bitfield members: 14 bits, bit holes: 1, sum bit holes: 2 bits */
- /* last cacheline: 24 bytes */
+ /* last cacheline: 16 bytes */
};

pre: 5:39.35 real, 215.58 user, 123.69 sys, 23448736 mem
post: 5:38.18 real, 213.25 user, 124.90 sys, 23449040 mem

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Tested-by: Nathan Chancellor <nathan@kernel.org> # build only
Tested-by: Thomas Weißschuh <linux@weissschuh.net> # compile and run
Link: https://lore.kernel.org/r/20230208172245.640914454@infradead.org

objtool: Remove instruction::reloc

Instead of caching the reloc for each instruction, only keep a
negative cache of not having a reloc (by far the most common case).

struct instruction {
struct list_head list; /* 0 16 */
struct hlist_node hash; /* 16 16 */
struct list_head call_node; /* 32 16 */
struct section * sec; /* 48 8 */
long unsigned int offset; /* 56 8 */
/* --- cacheline 1 boundary (64 bytes) --- */
long unsigned int immediate; /* 64 8 */
unsigned int len; /* 72 4 */
u8 type; /* 76 1 */

/* Bitfield combined with previous fields */

u16 dead_end:1; /* 76: 8 2 */
u16 ignore:1; /* 76: 9 2 */
u16 ignore_alts:1; /* 76:10 2 */
u16 hint:1; /* 76:11 2 */
u16 save:1; /* 76:12 2 */
u16 restore:1; /* 76:13 2 */
u16 retpoline_safe:1; /* 76:14 2 */
u16 noendbr:1; /* 76:15 2 */
u16 entry:1; /* 78: 0 2 */
u16 visited:4; /* 78: 1 2 */
+ u16 no_reloc:1; /* 78: 5 2 */

- /* XXX 3 bits hole, try to pack */
+ /* XXX 2 bits hole, try to pack */
/* Bitfield combined with next fields */

s8 instr; /* 79 1 */
struct alt_group * alt_group; /* 80 8 */
struct symbol * call_dest; /* 88 8 */
struct instruction * jump_dest; /* 96 8 */
struct instruction * first_jump_src; /* 104 8 */
struct reloc * jump_table; /* 112 8 */
- struct reloc * reloc; /* 120 8 */
+ struct alternative * alts; /* 120 8 */
/* --- cacheline 2 boundary (128 bytes) --- */
- struct alternative * alts; /* 128 8 */
- struct symbol * sym; /* 136 8 */
- struct stack_op * stack_ops; /* 144 8 */
- struct cfi_state * cfi; /* 152 8 */
+ struct symbol * sym; /* 128 8 */
+ struct stack_op * stack_ops; /* 136 8 */
+ struct cfi_state * cfi; /* 144 8 */

- /* size: 160, cachelines: 3, members: 29 */
- /* sum members: 158 */
- /* sum bitfield members: 13 bits, bit holes: 1, sum bit holes: 3 bits */
- /* last cacheline: 32 bytes */
+ /* size: 152, cachelines: 3, members: 29 */
+ /* sum members: 150 */
+ /* sum bitfield members: 14 bits, bit holes: 1, sum bit holes: 2 bits */
+ /* last cacheline: 24 bytes */
};

pre: 5:48.89 real, 220.96 user, 127.55 sys, 24834672 mem
post: 5:39.35 real, 215.58 user, 123.69 sys, 23448736 mem

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Tested-by: Nathan Chancellor <nathan@kernel.org> # build only
Tested-by: Thomas Weißschuh <linux@weissschuh.net> # compile and run
Link: https://lore.kernel.org/r/20230208172245.572145269@infradead.org

objtool: Shrink instruction::{type,visited}

Since we don't have that many types in enum insn_type, force it into a
u8 and re-arrange member to get rid of the holes, saves another 8
bytes.

struct instruction {
struct list_head list; /* 0 16 */
struct hlist_node hash; /* 16 16 */
struct list_head call_node; /* 32 16 */
struct section * sec; /* 48 8 */
long unsigned int offset; /* 56 8 */
/* --- cacheline 1 boundary (64 bytes) --- */
- unsigned int len; /* 64 4 */
- enum insn_type type; /* 68 4 */
- long unsigned int immediate; /* 72 8 */
- u16 dead_end:1; /* 80: 0 2 */
- u16 ignore:1; /* 80: 1 2 */
- u16 ignore_alts:1; /* 80: 2 2 */
- u16 hint:1; /* 80: 3 2 */
- u16 save:1; /* 80: 4 2 */
- u16 restore:1; /* 80: 5 2 */
- u16 retpoline_safe:1; /* 80: 6 2 */
- u16 noendbr:1; /* 80: 7 2 */
- u16 entry:1; /* 80: 8 2 */
+ long unsigned int immediate; /* 64 8 */
+ unsigned int len; /* 72 4 */
+ u8 type; /* 76 1 */

- /* XXX 7 bits hole, try to pack */
+ /* Bitfield combined with previous fields */

- s8 instr; /* 82 1 */
- u8 visited; /* 83 1 */
+ u16 dead_end:1; /* 76: 8 2 */
+ u16 ignore:1; /* 76: 9 2 */
+ u16 ignore_alts:1; /* 76:10 2 */
+ u16 hint:1; /* 76:11 2 */
+ u16 save:1; /* 76:12 2 */
+ u16 restore:1; /* 76:13 2 */
+ u16 retpoline_safe:1; /* 76:14 2 */
+ u16 noendbr:1; /* 76:15 2 */
+ u16 entry:1; /* 78: 0 2 */
+ u16 visited:4; /* 78: 1 2 */

- /* XXX 4 bytes hole, try to pack */
+ /* XXX 3 bits hole, try to pack */
+ /* Bitfield combined with next fields */

- struct alt_group * alt_group; /* 88 8 */
- struct symbol * call_dest; /* 96 8 */
- struct instruction * jump_dest; /* 104 8 */
- struct instruction * first_jump_src; /* 112 8 */
- struct reloc * jump_table; /* 120 8 */
+ s8 instr; /* 79 1 */
+ struct alt_group * alt_group; /* 80 8 */
+ struct symbol * call_dest; /* 88 8 */
+ struct instruction * jump_dest; /* 96 8 */
+ struct instruction * first_jump_src; /* 104 8 */
+ struct reloc * jump_table; /* 112 8 */
+ struct reloc * reloc; /* 120 8 */
/* --- cacheline 2 boundary (128 bytes) --- */
- struct reloc * reloc; /* 128 8 */
- struct alternative * alts; /* 136 8 */
- struct symbol * sym; /* 144 8 */
- struct stack_op * stack_ops; /* 152 8 */
- struct cfi_state * cfi; /* 160 8 */
+ struct alternative * alts; /* 128 8 */
+ struct symbol * sym; /* 136 8 */
+ struct stack_op * stack_ops; /* 144 8 */
+ struct cfi_state * cfi; /* 152 8 */

- /* size: 168, cachelines: 3, members: 29 */
- /* sum members: 162, holes: 1, sum holes: 4 */
- /* sum bitfield members: 9 bits, bit holes: 1, sum bit holes: 7 bits */
- /* last cacheline: 40 bytes */
+ /* size: 160, cachelines: 3, members: 29 */
+ /* sum members: 158 */
+ /* sum bitfield members: 13 bits, bit holes: 1, sum bit holes: 3 bits */
+ /* last cacheline: 32 bytes */
};

pre: 5:48.86 real, 220.30 user, 128.34 sys, 24834672 mem
post: 5:48.89 real, 220.96 user, 127.55 sys, 24834672 mem

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Tested-by: Nathan Chancellor <nathan@kernel.org> # build only
Tested-by: Thomas Weißschuh <linux@weissschuh.net> # compile and run
Link: https://lore.kernel.org/r/20230208172245.501847188@infradead.org

objtool: Make instruction::alts a single-linked list

struct instruction {
struct list_head list; /* 0 16 */
struct hlist_node hash; /* 16 16 */
struct list_head call_node; /* 32 16 */
struct section * sec; /* 48 8 */
long unsigned int offset; /* 56 8 */
/* --- cacheline 1 boundary (64 bytes) --- */
unsigned int len; /* 64 4 */
enum insn_type type; /* 68 4 */
long unsigned int immediate; /* 72 8 */
u16 dead_end:1; /* 80: 0 2 */
u16 ignore:1; /* 80: 1 2 */
u16 ignore_alts:1; /* 80: 2 2 */
u16 hint:1; /* 80: 3 2 */
u16 save:1; /* 80: 4 2 */
u16 restore:1; /* 80: 5 2 */
u16 retpoline_safe:1; /* 80: 6 2 */
u16 noendbr:1; /* 80: 7 2 */
u16 entry:1; /* 80: 8 2 */

/* XXX 7 bits hole, try to pack */

s8 instr; /* 82 1 */
u8 visited; /* 83 1 */

/* XXX 4 bytes hole, try to pack */

struct alt_group * alt_group; /* 88 8 */
struct symbol * call_dest; /* 96 8 */
struct instruction * jump_dest; /* 104 8 */
struct instruction * first_jump_src; /* 112 8 */
struct reloc * jump_table; /* 120 8 */
/* --- cacheline 2 boundary (128 bytes) --- */
struct reloc * reloc; /* 128 8 */
- struct list_head alts; /* 136 16 */
- struct symbol * sym; /* 152 8 */
- struct stack_op * stack_ops; /* 160 8 */
- struct cfi_state * cfi; /* 168 8 */
+ struct alternative * alts; /* 136 8 */
+ struct symbol * sym; /* 144 8 */
+ struct stack_op * stack_ops; /* 152 8 */
+ struct cfi_state * cfi; /* 160 8 */

- /* size: 176, cachelines: 3, members: 29 */
- /* sum members: 170, holes: 1, sum holes: 4 */
+ /* size: 168, cachelines: 3, members: 29 */
+ /* sum members: 162, holes: 1, sum holes: 4 */
/* sum bitfield members: 9 bits, bit holes: 1, sum bit holes: 7 bits */
- /* last cacheline: 48 bytes */
+ /* last cacheline: 40 bytes */
};

pre: 5:58.50 real, 229.64 user, 128.65 sys, 26221520 mem
post: 5:48.86 real, 220.30 user, 128.34 sys, 24834672 mem

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Tested-by: Nathan Chancellor <nathan@kernel.org> # build only
Tested-by: Thomas Weißschuh <linux@weissschuh.net> # compile and run
Link: https://lore.kernel.org/r/20230208172245.430556498@infradead.org

objtool: Make instruction::stack_ops a single-linked list

struct instruction {
struct list_head list; /* 0 16 */
struct hlist_node hash; /* 16 16 */
struct list_head call_node; /* 32 16 */
struct section * sec; /* 48 8 */
long unsigned int offset; /* 56 8 */
/* --- cacheline 1 boundary (64 bytes) --- */
unsigned int len; /* 64 4 */
enum insn_type type; /* 68 4 */
long unsigned int immediate; /* 72 8 */
u16 dead_end:1; /* 80: 0 2 */
u16 ignore:1; /* 80: 1 2 */
u16 ignore_alts:1; /* 80: 2 2 */
u16 hint:1; /* 80: 3 2 */
u16 save:1; /* 80: 4 2 */
u16 restore:1; /* 80: 5 2 */
u16 retpoline_safe:1; /* 80: 6 2 */
u16 noendbr:1; /* 80: 7 2 */
u16 entry:1; /* 80: 8 2 */

/* XXX 7 bits hole, try to pack */

s8 instr; /* 82 1 */
u8 visited; /* 83 1 */

/* XXX 4 bytes hole, try to pack */

struct alt_group * alt_group; /* 88 8 */
struct symbol * call_dest; /* 96 8 */
struct instruction * jump_dest; /* 104 8 */
struct instruction * first_jump_src; /* 112 8 */
struct reloc * jump_table; /* 120 8 */
/* --- cacheline 2 boundary (128 bytes) --- */
struct reloc * reloc; /* 128 8 */
struct list_head alts; /* 136 16 */
struct symbol * sym; /* 152 8 */
- struct list_head stack_ops; /* 160 16 */
- struct cfi_state * cfi; /* 176 8 */
+ struct stack_op * stack_ops; /* 160 8 */
+ struct cfi_state * cfi; /* 168 8 */

- /* size: 184, cachelines: 3, members: 29 */
- /* sum members: 178, holes: 1, sum holes: 4 */
+ /* size: 176, cachelines: 3, members: 29 */
+ /* sum members: 170, holes: 1, sum holes: 4 */
/* sum bitfield members: 9 bits, bit holes: 1, sum bit holes: 7 bits */
- /* last cacheline: 56 bytes */
+ /* last cacheline: 48 bytes */
};

pre: 5:58.22 real, 226.69 user, 131.22 sys, 26221520 mem
post: 5:58.50 real, 229.64 user, 128.65 sys, 26221520 mem

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Tested-by: Nathan Chancellor <nathan@kernel.org> # build only
Tested-by: Thomas Weißschuh <linux@weissschuh.net> # compile and run
Link: https://lore.kernel.org/r/20230208172245.362196959@infradead.org

objtool: Rework instruction -> symbol mapping

Currently insn->func contains a instruction -> symbol link for
STT_FUNC symbols. A NULL value is assumed to mean STT_NOTYPE.
However, there are also instructions not covered by any symbol at all.
This can happen due to __weak symbols for example.

Since the current scheme cannot differentiate between no symbol and
STT_NOTYPE symbol, change things around. Make insn->sym point to any
symbol type such that !insn->sym means no symbol and add a helper
insn_func() that check the sym->type to retain the old functionality.

This then prepares the way to add code that depends on the distinction
between STT_NOTYPE and no symbol at all.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>

objtool: Re-add UNWIND_HINT_{SAVE_RESTORE}

Commit

c536ed2fffd5 ("objtool: Remove SAVE/RESTORE hints")

removed the save/restore unwind hints because they were no longer
needed. Now they're going to be needed again so re-add them.

Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov <bp@suse.de>

objtool: Add entry UNRET validation

Since entry asm is tricky, add a validation pass that ensures the
retbleed mitigation has been done before the first actual RET
instruction.

Entry points are those that either have UNWIND_HINT_ENTRY, which acts
as UNWIND_HINT_EMPTY but marks the instruction as an entry point, or
those that have UWIND_HINT_IRET_REGS at +0.

This is basically a variant of validate_branch() that is
intra-function and it will simply follow all branches from marked
entry points and ensures that all paths lead to ANNOTATE_UNRET_END.

If a path hits RET or an indirection the path is a fail and will be
reported.

There are 3 ANNOTATE_UNRET_END instances:

- UNTRAIN_RET itself
- exception from-kernel; this path doesn't need UNTRAIN_RET
- all early exceptions; these also don't need UNTRAIN_RET

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Borislav Petkov <bp@suse.de>

objtool: Read the NOENDBR annotation

Read the new NOENDBR annotation. While there, attempt to not bloat
struct instruction.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lore.kernel.org/r/20220308154319.586815435@infradead.org

objtool: Shrink struct instruction

Any one instruction can only ever call a single function, therefore
insn->mcount_loc_node is superfluous and can use insn->call_node.

This shrinks struct instruction, which is by far the most numerous
structure objtool creates.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Borislav Petkov <bp@suse.de>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Tested-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/r/20211026120309.785456706@infradead.org

objtool: Introduce CFI hash

Andi reported that objtool on vmlinux.o consumes more memory than his
system has, leading to horrific performance.

This is in part because we keep a struct instruction for every
instruction in the file in-memory. Shrink struct instruction by
removing the CFI state (which includes full register state) from it
and demand allocating it.

Given most instructions don't actually change CFI state, there's lots
of repetition there, so add a hash table to find previous CFI
instances.

Reduces memory consumption (and runtime) for processing an
x86_64-allyesconfig:

pre: 4:40.84 real, 143.99 user, 44.18 sys, 30624988 mem
post: 2:14.61 real, 108.58 user, 25.04 sys, 16396184 mem

Suggested-by: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210624095147.756759107@infradead.org

objtool: Cache instruction relocs

Track the reloc of instructions in the new instruction->reloc field
to avoid having to look them up again later.

( Technically x86 instructions can have two relocations, but not jumps
and calls, for which we're using this. )

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Miroslav Benes <mbenes@suse.cz>
Link: https://lkml.kernel.org/r/20210326151300.195441549@infradead.org

objtool: Keep track of retpoline call sites

Provide infrastructure for architectures to rewrite/augment compiler
generated retpoline calls. Similar to what we do for static_call()s,
keep track of the instructions that are retpoline calls.

Use the same list_head, since a retpoline call cannot also be a
static_call.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Miroslav Benes <mbenes@suse.cz>
Link: https://lkml.kernel.org/r/20210326151300.130805730@infradead.org

objtool: Combine UNWIND_HINT_RET_OFFSET and UNWIND_HINT_FUNC

The ORC metadata generated for UNWIND_HINT_FUNC isn't actually very
func-like. With certain usages it can cause stack state mismatches
because it doesn't set the return address (CFI_RA).

Also, users of UNWIND_HINT_RET_OFFSET no longer need to set a custom
return stack offset. Instead they just need to specify a func-like
situation, so the current ret_offset code is hacky for no good reason.

Solve both problems by simplifying the RET_OFFSET handling and
converting it into a more useful UNWIND_HINT_FUNC.

If we end up needing the old 'ret_offset' functionality again in the
future, we should be able to support it pretty easily with the addition
of a custom 'sp_offset' in UNWIND_HINT_FUNC.

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lore.kernel.org/r/db9d1f5d79dddfbb3725ef6d8ec3477ad199948d.1611263462.git.jpoimboe@redhat.com

objtool: Fix retpoline detection in asm code

The JMP_NOSPEC macro branches to __x86_retpoline_*() rather than the
__x86_indirect_thunk_*() wrappers used by C code. Detect jumps to
__x86_retpoline_*() as retpoline dynamic jumps.

Presumably this doesn't trigger a user-visible bug. I only found it
when testing vmlinux.o validation.

Fixes: 39b735332cb8 ("objtool: Detect jumps to retpoline thunks")
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lore.kernel.org/r/31f5833e2e4f01e3d755889ac77e3661e906c09f.1611263461.git.jpoimboe@redhat.com

objtool: Support stack layout changes in alternatives

The ORC unwinder showed a warning [1] which revealed the stack layout
didn't match what was expected. The problem was that paravirt patching
had replaced "CALL *pv_ops.irq.save_fl" with "PUSHF;POP". That changed
the stack layout between the PUSHF and the POP, so unwinding from an
interrupt which occurred between those two instructions would fail.

Part of the agreed upon solution was to rework the custom paravirt
patching code to use alternatives instead, since objtool already knows
how to read alternatives (and converging runtime patching infrastructure
is always a good thing anyway). But the main problem still remains,
which is that runtime patching can change the stack layout.

Making stack layout changes in alternatives was disallowed with commit
7117f16bf460 ("objtool: Fix ORC vs alternatives"), but now that paravirt
is going to be doing it, it needs to be supported.

One way to do so would be to modify the ORC table when the code gets
patched. But ORC is simple -- a good thing! -- and it's best to leave
it alone.

Instead, support stack layout changes by "flattening" all possible stack
states (CFI) from parallel alternative code streams into a single set of
linear states. The only necessary limitation is that CFI conflicts are
disallowed at all possible instruction boundaries.

For example, this scenario is allowed:

Alt1 Alt2 Alt3

0x00 CALL *pv_ops.save_fl CALL xen_save_fl PUSHF
0x01 POP %RAX
0x02 NOP
...
0x05 NOP
...
0x07 <insn>

The unwind information for offset-0x00 is identical for all 3
alternatives. Similarly offset-0x05 and higher also are identical (and
the same as 0x00). However offset-0x01 has deviating CFI, but that is
only relevant for Alt3, neither of the other alternative instruction
streams will ever hit that offset.

This scenario is NOT allowed:

Alt1 Alt2

0x00 CALL *pv_ops.save_fl PUSHF
0x01 NOP6
...
0x07 NOP POP %RAX

The problem here is that offset-0x7, which is an instruction boundary in
both possible instruction patch streams, has two conflicting stack
layouts.

[ The above examples were stolen from Peter Zijlstra. ]

The new flattened CFI array is used both for the detection of conflicts
(like the second example above) and the generation of linear ORC
entries.

BTW, another benefit of these changes is that, thanks to some related
cleanups (new fake nops and alt_group struct) objtool can finally be rid
of fake jumps, which were a constant source of headaches.

[1] https://lkml.kernel.org/r/20201111170536.arx2zbn4ngvjoov7@treble

Cc: Shinichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>

objtool: Add 'alt_group' struct

Create a new struct associated with each group of alternatives
instructions. This will help with the removal of fake jumps, and more
importantly with adding support for stack layout changes in
alternatives.

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>

objtool: Refactor ORC section generation

Decouple ORC entries from instructions. This simplifies the
control/data flow, and is going to make it easier to support alternative
instructions which change the stack layout.

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>

objtool: Rework header include paths

Currently objtool headers are being included either by their base name
or included via ../ from a parent directory. In case of a base name usage:

#include "warn.h"
#include "arch_elf.h"

it does not make it apparent from which directory the file comes from.
To make it slightly better, and actually to avoid name clashes some arch
specific files have "arch_" suffix. And files from an arch folder have
to revert to including via ../ e.g:
#include "../../elf.h"

With additional architectures support and the code base growth there is
a need for clearer headers naming scheme for multiple reasons:
1. to make it instantly obvious where these files come from (objtool
itself / objtool arch|generic folders / some other external files),
2. to avoid name clashes of objtool arch specific headers, potential
obtool arch generic headers and the system header files (there is
/usr/include/elf.h already),
3. to avoid ../ includes and improve code readability.
4. to give a warm fuzzy feeling to developers who are mostly kernel
developers and are accustomed to linux kernel headers arranging
scheme.

Doesn't this make it instantly obvious where are these files come from?

#include <objtool/warn.h>
#include <arch/elf.h>

And doesn't it look nicer to avoid ugly ../ includes? Which also
guarantees this is elf.h from the objtool and not /usr/include/elf.h.

#include <objtool/elf.h>

This patch defines and implements new objtool headers arranging
scheme. Which is:
- all generic headers go to include/objtool (similar to include/linux)
- all arch headers go to arch/$(SRCARCH)/include/arch (to get arch
prefix). This is similar to linux arch specific "asm/*" headers but we
are not abusing "asm" name and calling it what it is. This also helps
to prevent name clashes (arch is not used in system headers or kernel
exports).

To bring objtool to this state the following things are done:
1. current top level tools/objtool/ headers are moved into
include/objtool/ subdirectory,
2. arch specific headers, currently only arch/x86/include/ are moved into
arch/x86/include/arch/ and were stripped of "arch_" suffix,
3. new -I$(srctree)/tools/objtool/include include path to make
includes like <objtool/warn.h> possible,
4. rewriting file includes,
5. make git not to ignore include/objtool/ subdirectory.

Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>