arm64/module: switch to ADRP/ADD sequences for PLT entries

Now that we have switched to the small code model entirely, and
reduced the extended KASLR range to 4 GB, we can be sure that the
targets of relative branches that are out of range are in range
for a ADRP/ADD pair, which is one instruction shorter than our
current MOVN/MOVK/MOVK sequence, and is more idiomatic and so it
is more likely to be implemented efficiently by micro-architectures.

So switch over the ordinary PLT code and the special handling of
the Cortex-A53 ADRP errata, as well as the ftrace trampline
handling.

Reviewed-by: Torsten Duwe <duwe@lst.de>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
[will: Added a couple of comments in the plt equality check]
Signed-off-by: Will Deacon <will.deacon@arm.com>

1 files changed, 8 insertions, 28 deletions

diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h
index f81c1847312d..905e1bb0e7bd 100644
--- a/arch/arm64/include/asm/module.h
+++ b/arch/arm64/include/asm/module.h
@@ -58,39 +58,19 @@ struct plt_entry {
 	 * is exactly what we are dealing with here, we are free to use x16
 	 * as a scratch register in the PLT veneers.
 	 */
-	__le32	mov0;	/* movn	x16, #0x....			*/
-	__le32	mov1;	/* movk	x16, #0x...., lsl #16		*/
-	__le32	mov2;	/* movk	x16, #0x...., lsl #32		*/
+	__le32	adrp;	/* adrp	x16, ....			*/
+	__le32	add;	/* add	x16, x16, #0x....		*/
 	__le32	br;	/* br	x16				*/
 };
 
-static inline struct plt_entry get_plt_entry(u64 val)
+static inline bool is_forbidden_offset_for_adrp(void *place)
 {
-	/*
-	 * MOVK/MOVN/MOVZ opcode:
-	 * +--------+------------+--------+-----------+-------------+---------+
-	 * | sf[31] | opc[30:29] | 100101 | hw[22:21] | imm16[20:5] | Rd[4:0] |
-	 * +--------+------------+--------+-----------+-------------+---------+
-	 *
-	 * Rd     := 0x10 (x16)
-	 * hw     := 0b00 (no shift), 0b01 (lsl #16), 0b10 (lsl #32)
-	 * opc    := 0b11 (MOVK), 0b00 (MOVN), 0b10 (MOVZ)
-	 * sf     := 1 (64-bit variant)
-	 */
-	return (struct plt_entry){
-		cpu_to_le32(0x92800010 | (((~val      ) & 0xffff)) << 5),
-		cpu_to_le32(0xf2a00010 | ((( val >> 16) & 0xffff)) << 5),
-		cpu_to_le32(0xf2c00010 | ((( val >> 32) & 0xffff)) << 5),
-		cpu_to_le32(0xd61f0200)
-	};
+	return IS_ENABLED(CONFIG_ARM64_ERRATUM_843419) &&
+	       cpus_have_const_cap(ARM64_WORKAROUND_843419) &&
+	       ((u64)place & 0xfff) >= 0xff8;
 }
 
-static inline bool plt_entries_equal(const struct plt_entry *a,
-				     const struct plt_entry *b)
-{
-	return a->mov0 == b->mov0 &&
-	       a->mov1 == b->mov1 &&
-	       a->mov2 == b->mov2;
-}
+struct plt_entry get_plt_entry(u64 dst, void *pc);
+bool plt_entries_equal(const struct plt_entry *a, const struct plt_entry *b);
 
 #endif /* __ASM_MODULE_H */