niansa-misc/linux
1
0
Fork 0
mirror of synced 2025-03-06 20:59:54 +01:00
Code Issues Projects Releases Packages Wiki Activity
1158682 commits 2 branches 875 tags 3.5 GiB
Commit graph

573 commits

Author SHA1 Message Date
Peter Zijlstra
1c34496e58 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
 2023-02-23 09:21:44 +01:00
Peter Zijlstra
a706bb08c8 objtool: Fix overlapping alternatives 
Things like ALTERNATIVE_{2,3}() generate multiple alternatives on the
same place, objtool would override the first orig_alt_group with the
second (or third), failing to check the CFI among all the different
variants.

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/20230208172245.711471461@infradead.org
 2023-02-23 09:21:33 +01:00
Peter Zijlstra
c6f5dc28fb 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
 2023-02-23 09:21:27 +01:00
Peter Zijlstra
0932dbe1f5 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
 2023-02-23 09:21:17 +01:00
Peter Zijlstra
8b2de41215 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
 2023-02-23 09:21:12 +01:00
Peter Zijlstra
d540665461 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
 2023-02-23 09:21:06 +01:00
Peter Zijlstra
3ee88df1b0 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
 2023-02-23 09:20:59 +01:00
Peter Zijlstra
20a554638d objtool: Change arch_decode_instruction() signature 
In preparation to changing struct instruction around a bit, avoid
passing it's members by pointer and instead pass the whole thing.

A cleanup in it's own right too.

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/20230208172245.291087549@infradead.org
 2023-02-23 09:20:50 +01:00
Ingo Molnar
585a78c1f7 Merge branch 'linus' into objtool/core, to pick up Xen dependencies 
Pick up dependencies - freshly merged upstream via xen-next - before applying
dependent objtool changes.

Signed-off-by: Ingo Molnar <mingo@kernel.org>
 2023-02-23 09:16:39 +01:00
Linus Torvalds
239451e903 xen: branch for v6.3-rc1 
-----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQRTLbB6QfY48x44uB6AXGG7T9hjvgUCY/GzaAAKCRCAXGG7T9hj
 vhgtAP96ax9EV49/kCST52z9yGfGUA+giq/9Jm6bwHlP3PZXVAD/Wfhfp1HbxzFp
 CqXG7veXU+uGVP3lbpbYKNPV9DIOdgQ=
 =K+0Q
 -----END PGP SIGNATURE-----

Merge tag 'for-linus-6.3-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen updates from Juergen Gross:

 - help deprecate the /proc/xen files by making the related information
   available via sysfs

 - mark the Xen variants of play_dead "noreturn"

 - support a shared Xen platform interrupt

 - several small cleanups and fixes

* tag 'for-linus-6.3-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen: sysfs: make kobj_type structure constant
  x86/Xen: drop leftover VM-assist uses
  xen: Replace one-element array with flexible-array member
  xen/grant-dma-iommu: Implement a dummy probe_device() callback
  xen/pvcalls-back: fix permanently masked event channel
  xen: Allow platform PCI interrupt to be shared
  x86/xen/time: prefer tsc as clocksource when it is invariant
  x86/xen: mark xen_pv_play_dead() as __noreturn
  x86/xen: don't let xen_pv_play_dead() return
  drivers/xen/hypervisor: Expose Xen SIF flags to userspace
 2023-02-21 17:07:39 -08:00
Linus Torvalds
1adce1b944 - Teach the static_call patching infrastructure to handle conditional 
tall calls properly which can be static calls too
 
 - Add proper struct alt_instr.flags which controls different aspects of
   insn patching behavior
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEzv7L6UO9uDPlPSfHEsHwGGHeVUoFAmPzkAcACgkQEsHwGGHe
 VUpA3A//bALDnLosUQe/m8CTcj1AU12Y59fGInoLl5xArM3liOhRYWj9yu8+2r5N
 j+89yjWoiaogu/9B18pV0+VnBrFUbALZmHxec0+4VAWyMqYuTbqN28Nj/2cZiHdP
 I/9mwGu40I/Ira021D132EcdoZI7O/6bFlh+kEoAqxc7rsqhD5KKRMlrTTdEPVjH
 aRbWIuzqDWNhbi7IwfgEBIPLiQZQKmIdH5hsFMD6yOMIdMRL6CwKmXVg2M1Zp8ta
 5v2Aqgvu2nZYCIteP4GQck2AlUBlGR4ClGQQRII+U1o8c9dM0hfcIDgsbSYKvgrY
 ANm9MQJaF7MRomk9y4E0EHPZAJEMLKUgiQXMxWpER3O1GOKgZPlyzNSe0gRCiL6O
 NZWZ2cGtdhQMrko4EapE3GNryM1HoCY/QCuD1fCYwoc/pRBDhCxsSqjWUd8G/6wn
 s3S/mD0v3nmTrxHg8sWvqhKshsd7B9V0LSkTpHktz3soFIJGXTxbrtty0CIS61pM
 4iUMYB9SjunoEmdwC7+gCN3sCiRpRqfmIybqXdsW3d37QI+FM5aSBPw51xULubfY
 Wsxo8SkH+IMYxXmfbQuUppsGZ+1QHzU08+MrlvNxGHUjS1aMnsrFF/fbfbbCnWvX
 7hcyBPT0jxc9RPMNeKDm4ItapMMGxGdv6XiRmM8LiUtVG2fMaW4=
 =XUqC
 -----END PGP SIGNATURE-----

Merge tag 'x86_alternatives_for_v6.3_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 asm alternatives updates from Borislav Petkov:

 - Teach the static_call patching infrastructure to handle conditional
   tall calls properly which can be static calls too

 - Add proper struct alt_instr.flags which controls different aspects of
   insn patching behavior

* tag 'x86_alternatives_for_v6.3_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/static_call: Add support for Jcc tail-calls
  x86/alternatives: Teach text_poke_bp() to patch Jcc.d32 instructions
  x86/alternatives: Introduce int3_emulate_jcc()
  x86/alternatives: Add alt_instr.flags
 2023-02-21 08:27:47 -08:00
Juergen Gross
f697cb00af x86/xen: mark xen_pv_play_dead() as __noreturn 
Mark xen_pv_play_dead() and related to that xen_cpu_bringup_again()
as "__noreturn".

Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20221125063248.30256-3-jgross@suse.com
Signed-off-by: Juergen Gross <jgross@suse.com>
 2023-02-13 06:53:19 +01:00
Josh Poimboeuf
ffb1b4a410 x86/unwind/orc: Add 'signal' field to ORC metadata 
Add a 'signal' field which allows unwind hints to specify whether the
instruction pointer should be taken literally (like for most interrupts
and exceptions) rather than decremented (like for call stack return
addresses) when used to find the next ORC entry.

Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/d2c5ec4d83a45b513d8fd72fab59f1a8cfa46871.1676068346.git.jpoimboe@kernel.org
 2023-02-11 12:37:51 +01:00
Peter Zijlstra
443ed4c302 objtool: mem*() are not uaccess safe 
For mysterious raisins I listed the new __asan_mem*() functions as
being uaccess safe, this is giving objtool fails on KASAN builds
because these functions call out to the actual __mem*() functions
which are not marked uaccess safe.

Removing it doesn't make the robots unhappy.

Fixes: 69d4c0d321 ("entry, kasan, x86: Disallow overriding mem*() functions")
Reported-by: "Paul E. McKenney" <paulmck@kernel.org>
Bisected-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20230126182302.GA687063@paulmck-ThinkPad-P17-Gen-1
 2023-02-11 11:18:08 +01:00
Thomas Weißschuh
a20717aca3 objtool: Optimize layout of struct special_alt 
Reduce the size of struct special_alt from 72 to 64 bytes.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20221216-objtool-memory-v2-7-17968f85a464@weissschuh.net
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
 2023-02-01 09:15:24 -08:00
Thomas Weißschuh
21a899f9fc objtool: Optimize layout of struct symbol 
Reduce the size of struct symbol on x86_64 from 208 to 200 bytes.
This structure is allocated a lot and never freed.

This reduces maximum memory usage while processing vmlinux.o from
2919716 KB to 2917988 KB (-0.5%) on my notebooks "localmodconfig".

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20221216-objtool-memory-v2-6-17968f85a464@weissschuh.net
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
 2023-02-01 09:15:24 -08:00
Thomas Weißschuh
8045b8f0b1 objtool: Allocate multiple structures with calloc() 
By using calloc() instead of malloc() in a loop, libc does not have to
keep around bookkeeping information for each single structure.

This reduces maximum memory usage while processing vmlinux.o from
3153325 KB to 3035668 KB (-3.7%) on my notebooks "localmodconfig".

Note this introduces memory leaks, because some additional structs get
added to the lists later after reading the symbols and sections from the
original object.  Luckily we don't really care about memory leaks in
objtool.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20221216-objtool-memory-v2-3-17968f85a464@weissschuh.net
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
 2023-02-01 09:15:23 -08:00
Thomas Weißschuh
cfd66e8179 objtool: Make struct check_options static 
It is not used outside of builtin-check.c.

Also remove the unused declaration from builtin.h .

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20221216-objtool-memory-v2-2-17968f85a464@weissschuh.net
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
 2023-02-01 09:15:23 -08:00
Thomas Weißschuh
d93ee0553c objtool: Make struct entries[] static and const 
This data is not modified and not used outside of special.c.

Also adapt its users to the constness.

Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20221216-objtool-memory-v2-1-17968f85a464@weissschuh.net
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
 2023-02-01 09:15:22 -08:00
Ian Rogers
cd955bdd6a objtool: Fix HOSTCC flag usage 
HOSTCC is always wanted when building objtool. Setting CC to HOSTCC
happens after tools/scripts/Makefile.include is included, meaning
flags (like CFLAGS) are set assuming say CC is gcc, but then it can be
later set to HOSTCC which may be clang. tools/scripts/Makefile.include
is needed for host set up and common macros in objtool's
Makefile. Rather than override the CC variable to HOSTCC, just pass CC
as HOSTCC to the sub-makes of Makefile.build, the libsubcmd builds and
also to the linkage step.

Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20230126190606.40739-4-irogers@google.com
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
 2023-02-01 09:15:18 -08:00
Ingo Molnar
57a30218fa Linux 6.2-rc6 
-----BEGIN PGP SIGNATURE-----
 
 iQFSBAABCAA8FiEEq68RxlopcLEwq+PEeb4+QwBBGIYFAmPW7E8eHHRvcnZhbGRz
 QGxpbnV4LWZvdW5kYXRpb24ub3JnAAoJEHm+PkMAQRiGf7MIAI0JnHN9WvtEukSZ
 E6j6+cEGWxsvD6q0g3GPolaKOCw7hlv0pWcFJFcUAt0jebspMdxV2oUGJ8RYW7Lg
 nCcHvEVswGKLAQtQSWw52qotW6fUfMPsNYYB5l31sm1sKH4Cgss0W7l2HxO/1LvG
 TSeNHX53vNAZ8pVnFYEWCSXC9bzrmU/VALF2EV00cdICmfvjlgkELGXoLKJJWzUp
 s63fBHYGGURSgwIWOKStoO6HNo0j/F/wcSMx8leY8qDUtVKHj4v24EvSgxUSDBER
 ch3LiSQ6qf4sw/z7pqruKFthKOrlNmcc0phjiES0xwwGiNhLv0z3rAhc4OM2cgYh
 SDc/Y/c=
 =zpaD
 -----END PGP SIGNATURE-----

Merge tag 'v6.2-rc6' into sched/core, to pick up fixes

Pick up fixes before merging another batch of cpuidle updates.

Signed-off-by: Ingo Molnar <mingo@kernel.org>
 2023-01-31 15:01:20 +01:00
Ian Rogers
8c4526ca6a objtool: Properly support make V=1 
The Q variable was being used but never correctly set up. Add the
setting up and use in place of @.

Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20230126190606.40739-3-irogers@google.com
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
 2023-01-30 16:28:16 -08:00
Ian Rogers
bdb8bf7d56 objtool: Install libsubcmd in build 
Including from tools/lib can create inadvertent dependencies. Install
libsubcmd in the objtool build and then include the headers from
there.

Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20230126190606.40739-2-irogers@google.com
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
 2023-01-30 16:27:46 -08:00
Michal Kubecek
03d7a1053c objtool: Check that module init/exit function is an indirect call target 
Some out-of-tree modules still do not use module_init() / module_exit()
macros and simply create functions with magic names init_module() and
cleanup_module() instead. As a result, these functions are not recognized
as indirect call targets by objtool and such module fails to load into an
IBT enabled kernel.

This old way is not even documented any more but it is cleaner to issue
a warning than to let the module fail on load without obvious reason.

Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20230118105215.B9DA960514@lion.mk-sys.cz
 2023-01-21 10:50:18 +01:00
Peter Zijlstra
69d4c0d321 entry, kasan, x86: Disallow overriding mem*() functions 
KASAN cannot just hijack the mem*() functions, it needs to emit
__asan_mem*() variants if it wants instrumentation (other sanitizers
already do this).

  vmlinux.o: warning: objtool: sync_regs+0x24: call to memcpy() leaves .noinstr.text section
  vmlinux.o: warning: objtool: vc_switch_off_ist+0xbe: call to memcpy() leaves .noinstr.text section
  vmlinux.o: warning: objtool: fixup_bad_iret+0x36: call to memset() leaves .noinstr.text section
  vmlinux.o: warning: objtool: __sev_get_ghcb+0xa0: call to memcpy() leaves .noinstr.text section
  vmlinux.o: warning: objtool: __sev_put_ghcb+0x35: call to memcpy() leaves .noinstr.text section

Remove the weak aliases to ensure nobody hijacks these functions and
add them to the noinstr section.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Tony Lindgren <tony@atomide.com>
Tested-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lore.kernel.org/r/20230112195542.028523143@infradead.org
 2023-01-13 11:48:17 +01:00
Peter Zijlstra
f18b0d7ee8 ubsan: Fix objtool UACCESS warns 
clang-14 allyesconfig gives:

  vmlinux.o: warning: objtool: emulator_cmpxchg_emulated+0x705: call to __ubsan_handle_load_invalid_value() with UACCESS enabled
  vmlinux.o: warning: objtool: paging64_update_accessed_dirty_bits+0x39e: call to __ubsan_handle_load_invalid_value() with UACCESS enabled
  vmlinux.o: warning: objtool: paging32_update_accessed_dirty_bits+0x390: call to __ubsan_handle_load_invalid_value() with UACCESS enabled
  vmlinux.o: warning: objtool: ept_update_accessed_dirty_bits+0x43f: call to __ubsan_handle_load_invalid_value() with UACCESS enabled

Add the required eflags save/restore and whitelist the thing.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Tony Lindgren <tony@atomide.com>
Tested-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lore.kernel.org/r/20230112195541.906007455@infradead.org
 2023-01-13 11:48:17 +01:00
Peter Zijlstra
2b5a0e425e objtool/idle: Validate __cpuidle code as noinstr 
Idle code is very like entry code in that RCU isn't available. As
such, add a little validation.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Tony Lindgren <tony@atomide.com>
Tested-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lore.kernel.org/r/20230112195540.373461409@infradead.org
 2023-01-13 11:48:15 +01:00
Nicholas Piggin
cad90e5381 objtool: Tolerate STT_NOTYPE symbols at end of section 
Hand-written asm often contains non-function symbols in executable
sections. _end symbols for finding the size of instruction blocks
for runtime processing is one such usage.

optprobe_template_end is one example that causes the warning:

  objtool: optprobe_template_end(): can't find starting instruction

This is because the symbol happens to be at the end of the file (and
therefore end of a section in the object file).

So ignore end-of-section STT_NOTYPE symbols instead of bailing out
because an instruction can't be found. While we're here, add a more
descriptive warning for STT_FUNC symbols found at the end of a
section.

[ This also solves a PowerPC regression reported by Sathvika Vasireddy. ]

Reported-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Reported-by: Sathvika Vasireddy <sv@linux.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Sathvika Vasireddy <sv@linux.ibm.com>
Link: https://lore.kernel.org/r/20221220101323.3119939-1-npiggin@gmail.com
 2023-01-09 17:53:46 +01:00
Miaoqian Lin
3da73f1023 objtool: Fix memory leak in create_static_call_sections() 
strdup() allocates memory for key_name. We need to release the memory in
the following error paths. Add free() to avoid memory leak.

Fixes: 1e7e478838 ("x86/static_call: Add inline static call implementation for x86-64")
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20221205080642.558583-1-linmq006@gmail.com
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
 2023-01-07 11:45:24 +01:00
Borislav Petkov (AMD)
5d1dd961e7 x86/alternatives: Add alt_instr.flags 
Add a struct alt_instr.flags field which will contain different flags
controlling alternatives patching behavior.

The initial idea was to be able to specify it as a separate macro
parameter but that would mean touching all possible invocations of the
alternatives macros and thus a lot of churn.

What is more, as PeterZ suggested, being able to say ALT_NOT(feature) is
very readable and explains exactly what is meant.

So make the feature field a u32 where the patching flags are the upper
u16 part of the dword quantity while the lower u16 word is the feature.

The highest feature number currently is 0x26a (i.e., word 19) so there
is plenty of space. If that becomes insufficient, the field can be
extended to u64 which will then make struct alt_instr of the nice size
of 16 bytes (14 bytes currently).

There should be no functional changes resulting from this.

Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/Y6RCoJEtxxZWwotd@zn.tnic
 2023-01-05 12:46:47 +01:00
Linus Torvalds
5f6e430f93 powerpc updates for 6.2 
- Add powerpc qspinlock implementation optimised for large system scalability and
    paravirt. See the merge message for more details.
 
  - Enable objtool to be built on powerpc to generate mcount locations.
 
  - Use a temporary mm for code patching with the Radix MMU, so the writable mapping is
    restricted to the patching CPU.
 
  - Add an option to build the 64-bit big-endian kernel with the ELFv2 ABI.
 
  - Sanitise user registers on interrupt entry on 64-bit Book3S.
 
  - Many other small features and fixes.
 
 Thanks to: Aboorva Devarajan, Angel Iglesias, Benjamin Gray, Bjorn Helgaas, Bo Liu, Chen
 Lifu, Christoph Hellwig, Christophe JAILLET, Christophe Leroy, Christopher M. Riedl, Colin
 Ian King, Deming Wang, Disha Goel, Dmitry Torokhov, Finn Thain, Geert Uytterhoeven,
 Gustavo A. R. Silva, Haowen Bai, Joel Stanley, Jordan Niethe, Julia Lawall, Kajol Jain,
 Laurent Dufour, Li zeming, Miaoqian Lin, Michael Jeanson, Nathan Lynch, Naveen N. Rao,
 Nayna Jain, Nicholas Miehlbradt, Nicholas Piggin, Pali Rohár, Randy Dunlap, Rohan McLure,
 Russell Currey, Sathvika Vasireddy, Shaomin Deng, Stephen Kitt, Stephen Rothwell, Thomas
 Weißschuh, Tiezhu Yang, Uwe Kleine-König, Xie Shaowen, Xiu Jianfeng, XueBing Chen, Yang
 Yingliang, Zhang Jiaming, ruanjinjie, Jessica Yu, Wolfram Sang.
 -----BEGIN PGP SIGNATURE-----
 
 iQJHBAABCAAxFiEEJFGtCPCthwEv2Y/bUevqPMjhpYAFAmOfrj8THG1wZUBlbGxl
 cm1hbi5pZC5hdQAKCRBR6+o8yOGlgIWtD/9mGF/ze2k+qFTo+30fb7bO8WJIDgsR
 dIASnZjXV7q/45elvymhUdkQv4R7xL3pzC40P1+ZKtWzGTNe+zWUQLoALNwRK85j
 8CsxZbqefGNKE5Z6ZHo9s37wsu3+jJu9yEQpGFo1LINyzeclCn5St5oqfRam+Hd/
 cPF+VfvREwZ0+YOKGBhJ2EgC+Gc9xsFY7DLQsoYlu71iZZr6Z6rgZW/EY5h3RMGS
 YKBoVwDsWaU0FpFWrr/rYTI6DqSr3AHr1+ftDg7ncCZMD6vQva6aMCCt94aLB1aE
 vC+DNdhZlA558bXGa5yA7Wr//7aUBUIwyC60DogOeZ6vw3kD9tdEd1fbH5hmqNKY
 K5bfqm28XU2959CTE8RDgsYYZvwDcfrjBIML14WZGdCQOTcGKpgOGp22o6yNb1Pq
 JKpHHnVpvu2PZ/p2XdKSm9+etr2yI6lXZAEVTS7ehdtMukButjSHEVbSCEZ8tlWz
 KokQt2J23BMHuSrXK6+67wWQBtdsLEk+LBOQmweiwarMocqvL/Zjz/5J7DR2DtH8
 wlY3wOtB1+E5j7xZ+RgK3c3jNg5dH39ZwvFsSATWTI3P+iq6OK/bbk4q4LmZt2l9
 ZIfH/CXPf9BvGCHzHa3AAd3UBbJLFwj17btMEv1wFVPS0T4LPUzkgTNTNUYeP6zL
 h1e5QfgUxvKPuQ==
 =7k3p
 -----END PGP SIGNATURE-----

Merge tag 'powerpc-6.2-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - Add powerpc qspinlock implementation optimised for large system
   scalability and paravirt. See the merge message for more details

 - Enable objtool to be built on powerpc to generate mcount locations

 - Use a temporary mm for code patching with the Radix MMU, so the
   writable mapping is restricted to the patching CPU

 - Add an option to build the 64-bit big-endian kernel with the ELFv2
   ABI

 - Sanitise user registers on interrupt entry on 64-bit Book3S

 - Many other small features and fixes

Thanks to Aboorva Devarajan, Angel Iglesias, Benjamin Gray, Bjorn
Helgaas, Bo Liu, Chen Lifu, Christoph Hellwig, Christophe JAILLET,
Christophe Leroy, Christopher M. Riedl, Colin Ian King, Deming Wang,
Disha Goel, Dmitry Torokhov, Finn Thain, Geert Uytterhoeven, Gustavo A.
R. Silva, Haowen Bai, Joel Stanley, Jordan Niethe, Julia Lawall, Kajol
Jain, Laurent Dufour, Li zeming, Miaoqian Lin, Michael Jeanson, Nathan
Lynch, Naveen N. Rao, Nayna Jain, Nicholas Miehlbradt, Nicholas Piggin,
Pali Rohár, Randy Dunlap, Rohan McLure, Russell Currey, Sathvika
Vasireddy, Shaomin Deng, Stephen Kitt, Stephen Rothwell, Thomas
Weißschuh, Tiezhu Yang, Uwe Kleine-König, Xie Shaowen, Xiu Jianfeng,
XueBing Chen, Yang Yingliang, Zhang Jiaming, ruanjinjie, Jessica Yu,
and Wolfram Sang.

* tag 'powerpc-6.2-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (181 commits)
  powerpc/code-patching: Fix oops with DEBUG_VM enabled
  powerpc/qspinlock: Fix 32-bit build
  powerpc/prom: Fix 32-bit build
  powerpc/rtas: mandate RTAS syscall filtering
  powerpc/rtas: define pr_fmt and convert printk call sites
  powerpc/rtas: clean up includes
  powerpc/rtas: clean up rtas_error_log_max initialization
  powerpc/pseries/eeh: use correct API for error log size
  powerpc/rtas: avoid scheduling in rtas_os_term()
  powerpc/rtas: avoid device tree lookups in rtas_os_term()
  powerpc/rtasd: use correct OF API for event scan rate
  powerpc/rtas: document rtas_call()
  powerpc/pseries: unregister VPA when hot unplugging a CPU
  powerpc/pseries: reset the RCU watchdogs after a LPM
  powerpc: Take in account addition CPU node when building kexec FDT
  powerpc: export the CPU node count
  powerpc/cpuidle: Set CPUIDLE_FLAG_POLLING for snooze state
  powerpc/dts/fsl: Fix pca954x i2c-mux node names
  cxl: Remove unnecessary cxl_pci_window_alignment()
  selftests/powerpc: Fix resource leaks
  ...
 2022-12-19 07:13:33 -06:00
Linus Torvalds
94a855111e - Add the call depth tracking mitigation for Retbleed which has 
been long in the making. It is a lighterweight software-only fix for
 Skylake-based cores where enabling IBRS is a big hammer and causes a
 significant performance impact.
 
 What it basically does is, it aligns all kernel functions to 16 bytes
 boundary and adds a 16-byte padding before the function, objtool
 collects all functions' locations and when the mitigation gets applied,
 it patches a call accounting thunk which is used to track the call depth
 of the stack at any time.
 
 When that call depth reaches a magical, microarchitecture-specific value
 for the Return Stack Buffer, the code stuffs that RSB and avoids its
 underflow which could otherwise lead to the Intel variant of Retbleed.
 
 This software-only solution brings a lot of the lost performance back,
 as benchmarks suggest:
 
   https://lore.kernel.org/all/20220915111039.092790446@infradead.org/
 
 That page above also contains a lot more detailed explanation of the
 whole mechanism
 
 - Implement a new control flow integrity scheme called FineIBT which is
 based on the software kCFI implementation and uses hardware IBT support
 where present to annotate and track indirect branches using a hash to
 validate them
 
 - Other misc fixes and cleanups
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEzv7L6UO9uDPlPSfHEsHwGGHeVUoFAmOZp5EACgkQEsHwGGHe
 VUrZFxAAvi/+8L0IYSK4mKJvixGbTFjxN/Swo2JVOfs34LqGUT6JaBc+VUMwZxdb
 VMTFIZ3ttkKEodjhxGI7oGev6V8UfhI37SmO2lYKXpQVjXXnMlv/M+Vw3teE38CN
 gopi+xtGnT1IeWQ3tc/Tv18pleJ0mh5HKWiW+9KoqgXj0wgF9x4eRYDz1TDCDA/A
 iaBzs56j8m/FSykZHnrWZ/MvjKNPdGlfJASUCPeTM2dcrXQGJ93+X2hJctzDte0y
 Nuiw6Y0htfFBE7xoJn+sqm5Okr+McoUM18/CCprbgSKYk18iMYm3ZtAi6FUQZS1A
 ua4wQCf49loGp15PO61AS5d3OBf5D3q/WihQRbCaJvTVgPp9sWYnWwtcVUuhMllh
 ZQtBU9REcVJ/22bH09Q9CjBW0VpKpXHveqQdqRDViLJ6v/iI6EFGmD24SW/VxyRd
 73k9MBGrL/dOf1SbEzdsnvcSB3LGzp0Om8o/KzJWOomrVKjBCJy16bwTEsCZEJmP
 i406m92GPXeaN1GhTko7vmF0GnkEdJs1GVCZPluCAxxbhHukyxHnrjlQjI4vC80n
 Ylc0B3Kvitw7LGJsPqu+/jfNHADC/zhx1qz/30wb5cFmFbN1aRdp3pm8JYUkn+l/
 zri2Y6+O89gvE/9/xUhMohzHsWUO7xITiBavewKeTP9GSWybWUs=
 =cRy1
 -----END PGP SIGNATURE-----

Merge tag 'x86_core_for_v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 core updates from Borislav Petkov:

 - Add the call depth tracking mitigation for Retbleed which has been
   long in the making. It is a lighterweight software-only fix for
   Skylake-based cores where enabling IBRS is a big hammer and causes a
   significant performance impact.

   What it basically does is, it aligns all kernel functions to 16 bytes
   boundary and adds a 16-byte padding before the function, objtool
   collects all functions' locations and when the mitigation gets
   applied, it patches a call accounting thunk which is used to track
   the call depth of the stack at any time.

   When that call depth reaches a magical, microarchitecture-specific
   value for the Return Stack Buffer, the code stuffs that RSB and
   avoids its underflow which could otherwise lead to the Intel variant
   of Retbleed.

   This software-only solution brings a lot of the lost performance
   back, as benchmarks suggest:

       https://lore.kernel.org/all/20220915111039.092790446@infradead.org/

   That page above also contains a lot more detailed explanation of the
   whole mechanism

 - Implement a new control flow integrity scheme called FineIBT which is
   based on the software kCFI implementation and uses hardware IBT
   support where present to annotate and track indirect branches using a
   hash to validate them

 - Other misc fixes and cleanups

* tag 'x86_core_for_v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (80 commits)
  x86/paravirt: Use common macro for creating simple asm paravirt functions
  x86/paravirt: Remove clobber bitmask from .parainstructions
  x86/debug: Include percpu.h in debugreg.h to get DECLARE_PER_CPU() et al
  x86/cpufeatures: Move X86_FEATURE_CALL_DEPTH from bit 18 to bit 19 of word 11, to leave space for WIP X86_FEATURE_SGX_EDECCSSA bit
  x86/Kconfig: Enable kernel IBT by default
  x86,pm: Force out-of-line memcpy()
  objtool: Fix weak hole vs prefix symbol
  objtool: Optimize elf_dirty_reloc_sym()
  x86/cfi: Add boot time hash randomization
  x86/cfi: Boot time selection of CFI scheme
  x86/ibt: Implement FineIBT
  objtool: Add --cfi to generate the .cfi_sites section
  x86: Add prefix symbols for function padding
  objtool: Add option to generate prefix symbols
  objtool: Avoid O(bloody terrible) behaviour -- an ode to libelf
  objtool: Slice up elf_create_section_symbol()
  kallsyms: Revert "Take callthunks into account"
  x86: Unconfuse CONFIG_ and X86_FEATURE_ namespaces
  x86/retpoline: Fix crash printing warning
  x86/paravirt: Fix a !PARAVIRT build warning
  ...
 2022-12-14 15:03:00 -08:00
Michael Ellerman
a39818a3fb objtool/powerpc: Implement arch_pc_relative_reloc() 
Provide an implementation for arch_pc_relative_reloc(). It is needed to
pass the build once 61c6065ef7 ("objtool: Allow !PC relative
relocations") is merged.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
 2022-11-23 21:26:10 +11:00
Sathvika Vasireddy
c984aef8c8 objtool/powerpc: Add --mcount specific implementation 
This patch enables objtool --mcount on powerpc, and adds implementation
specific to powerpc.

Tested-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Reviewed-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Sathvika Vasireddy <sv@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20221114175754.1131267-17-sv@linux.ibm.com
 2022-11-18 19:00:16 +11:00
Sathvika Vasireddy
e52ec98c5a objtool/powerpc: Enable objtool to be built on ppc 
This patch adds [stub] implementations for required functions, inorder
to enable objtool build on powerpc.

[Christophe Leroy: powerpc: Add missing asm/asm.h for objtool,
Use local variables for type and imm in arch_decode_instruction(),
Adapt len for prefixed instructions.]

Tested-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Reviewed-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Sathvika Vasireddy <sv@linux.ibm.com>
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20221114175754.1131267-16-sv@linux.ibm.com
 2022-11-18 19:00:16 +11:00
Sathvika Vasireddy
4ca993d498 objtool: Add arch specific function arch_ftrace_match() 
Add architecture specific function to look for relocation records
pointing to architecture specific symbols.

Suggested-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Tested-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Reviewed-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Sathvika Vasireddy <sv@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20221114175754.1131267-15-sv@linux.ibm.com
 2022-11-18 19:00:16 +11:00
Sathvika Vasireddy
c144973521 objtool: Use macros to define arch specific reloc types 
Make relocation types architecture specific.

Tested-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Reviewed-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Sathvika Vasireddy <sv@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20221114175754.1131267-14-sv@linux.ibm.com
 2022-11-18 19:00:16 +11:00
Sathvika Vasireddy
de6fbcedf5 objtool: Read special sections with alts only when specific options are selected 
Call add_special_section_alts() only when stackval or orc or uaccess or
noinstr options are passed to objtool.

Tested-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Reviewed-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Sathvika Vasireddy <sv@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20221114175754.1131267-13-sv@linux.ibm.com
 2022-11-18 19:00:16 +11:00
Sathvika Vasireddy
280981d699 objtool: Add --mnop as an option to --mcount 
Some architectures (powerpc) may not support ftrace locations being nop'ed
out at build time. Introduce CONFIG_HAVE_OBJTOOL_NOP_MCOUNT for objtool, as
a means for architectures to enable nop'ing of ftrace locations. Add --mnop
as an option to objtool --mcount, to indicate support for the same.

Also, make sure that --mnop can be passed as an option to objtool only when
--mcount is passed.

Tested-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Reviewed-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Sathvika Vasireddy <sv@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20221114175754.1131267-12-sv@linux.ibm.com
 2022-11-18 19:00:16 +11:00
Christophe Leroy
86ea7f3615 objtool: Use target file class size instead of a compiled constant 
In order to allow using objtool on cross-built kernels,
determine size of long from elf data instead of using
sizeof(long) at build time.

For the time being this covers only mcount.

[Sathvika Vasireddy: Rename variable "size" to "addrsize" and function
"elf_class_size()" to "elf_class_addrsize()", and modify
create_mcount_loc_sections() function to follow reverse christmas tree
format to order local variable declarations.]

Tested-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Reviewed-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Sathvika Vasireddy <sv@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20221114175754.1131267-11-sv@linux.ibm.com
 2022-11-18 19:00:16 +11:00
Christophe Leroy
0646c28b41 objtool: Use target file endianness instead of a compiled constant 
Some architectures like powerpc support both endianness, it's
therefore not possible to fix the endianness via arch/endianness.h
because there is no easy way to get the target endianness at
build time.

Use the endianness recorded in the file objtool is working on.

Tested-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Reviewed-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20221114175754.1131267-10-sv@linux.ibm.com
 2022-11-18 19:00:15 +11:00
Christophe Leroy
efb11fdb3e objtool: Fix SEGFAULT 
find_insn() will return NULL in case of failure. Check insn in order
to avoid a kernel Oops for NULL pointer dereference.

Tested-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Reviewed-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20221114175754.1131267-9-sv@linux.ibm.com
 2022-11-18 19:00:15 +11:00
Peter Zijlstra
023f2340f0 objtool: Fix weak hole vs prefix symbol 
Boris (and the robot) reported that objtool grew a new complaint about
unreachable instructions. Upon inspection it was immediately clear
the __weak zombie instructions struck again.

For the unweary, the linker will simply remove the symbol for
overriden __weak symbols but leave the instructions in place, creating
unreachable instructions -- and objtool likes to report these.

Commit 4adb236867 ("objtool: Ignore extra-symbol code") was supposed
to have dealt with that, but the new commit 9f2899fe36 ("objtool:
Add option to generate prefix symbols") subtly broke that logic by
created unvisited symbols.

Fixes: 9f2899fe36 ("objtool: Add option to generate prefix symbols")
Reported-by: Borislav Petkov <bp@alien8.de>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
 2022-11-05 11:28:02 +01:00
Peter Zijlstra
19526717f7 objtool: Optimize elf_dirty_reloc_sym() 
When moving a symbol in the symtab its index changes and any reloc
referring that symtol-table-index will need to be rewritten too.

In order to facilitate this, objtool simply marks the whole reloc
section 'changed' which will cause the whole section to be
re-generated.

However, finding the relocs that use any given symbol is implemented
rather crudely -- a fully iteration of all sections and their relocs.
Given that some builds have over 20k sections (kallsyms etc..)
iterating all that for *each* symbol moved takes a bit of time.

Instead have each symbol keep a list of relocs that reference it.

This *vastly* improves build times for certain configs.

Reported-by: Borislav Petkov <bp@alien8.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/Y2LlRA7x+8UsE1xf@hirez.programming.kicks-ass.net
 2022-11-05 11:28:02 +01:00
Peter Zijlstra
9a479f766b objtool: Add --cfi to generate the .cfi_sites section 
Add the location of all __cfi_##name symbols (as generated by kCFI) to
a section such that we might re-write things at kernel boot.

Notably; boot time re-hashing and FineIBT are the intended use of
this.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20221027092842.568039454@infradead.org
 2022-11-01 13:44:10 +01:00
Peter Zijlstra
9f2899fe36 objtool: Add option to generate prefix symbols 
When code is compiled with:

  -fpatchable-function-entry=${PADDING_BYTES},${PADDING_BYTES}

functions will have PADDING_BYTES of NOP in front of them. Unwinders
and other things that symbolize code locations will typically
attribute these bytes to the preceding function.

Given that these bytes nominally belong to the following symbol this
mis-attribution is confusing.

Inspired by the fact that CFI_CLANG emits __cfi_##name symbols to
claim these bytes, allow objtool to emit __pfx_##name symbols to do
the same.

Therefore add the objtool --prefix=N argument, to conditionally place
a __pfx_##name symbol at N bytes ahead of symbol 'name' when: all
these preceding bytes are NOP and name-N is an instruction boundary.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Yujie Liu <yujie.liu@intel.com>
Link: https://lkml.kernel.org/r/20221028194453.526899822@infradead.org
 2022-11-01 13:44:09 +01:00
Peter Zijlstra
13f60e80e1 objtool: Avoid O(bloody terrible) behaviour -- an ode to libelf 
Due to how gelf_update_sym*() requires an Elf_Data pointer, and how
libelf keeps Elf_Data in a linked list per section,
elf_update_symbol() ends up having to iterate this list on each
update to find the correct Elf_Data for the index'ed symbol.

By allocating one Elf_Data per new symbol, the list grows per new
symbol, giving an effective O(n^2) insertion time. This is obviously
bloody terrible.

Therefore over-allocate the Elf_Data when an extention is needed.
Except it turns out libelf disregards Elf_Scn::sh_size in favour of
the sum of Elf_Data::d_size. IOW it will happily write out all the
unused space and fill it with:

  0000000000000000     0 NOTYPE  LOCAL  DEFAULT  UND

entries (aka zeros). Which obviously violates the STB_LOCAL placement
rule, and is a general pain in the backside for not being the desired
behaviour.

Manually fix-up the Elf_Data size to avoid this problem before calling
elf_update().

This significantly improves performance when adding a significant
number of symbols.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Yujie Liu <yujie.liu@intel.com>
Link: https://lkml.kernel.org/r/20221028194453.461658986@infradead.org
 2022-11-01 13:44:08 +01:00
Peter Zijlstra
4c91be8e92 objtool: Slice up elf_create_section_symbol() 
In order to facilitate creation of more symbol types, slice up
elf_create_section_symbol() to extract a generic helper that deals
with adding ELF symbols.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Yujie Liu <yujie.liu@intel.com>
Link: https://lkml.kernel.org/r/20221028194453.396634875@infradead.org
 2022-11-01 13:44:08 +01:00
Marco Elver
63646fcba5 objtool, kcsan: Add volatile read/write instrumentation to whitelist 
Adds KCSAN's volatile instrumentation to objtool's uaccess whitelist.

Recent kernel change have shown that this was missing from the uaccess
whitelist (since the first upstreamed version of KCSAN):

  mm/gup.o: warning: objtool: fault_in_readable+0x101: call to __tsan_volatile_write1() with UACCESS enabled

Fixes: 75d75b7a4d ("kcsan: Support distinguishing volatile accesses")
Signed-off-by: Marco Elver <elver@google.com>
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
 2022-10-18 15:07:33 -07:00
Peter Zijlstra
5a9c361a41 objtool: Allow STT_NOTYPE -> STT_FUNC+0 sibling-calls 
Teach objtool about STT_NOTYPE -> STT_FUNC+0 sibling calls. Doing do
allows slightly simpler .S files.

There is a slight complication in that we specifically do not want to
allow sibling calls from symbol holes (previously covered by STT_WEAK
symbols) -- such things exist where a weak function has a .cold
subfunction for example.

Additionally, STT_NOTYPE tail-calls are allowed to happen with a
modified stack frame, they don't need to obey the normal rules after
all.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
 2022-10-17 16:41:09 +02:00