[PATCH v6 2/3] arm64: vmlinux.ld: Add mmuoff data sections and move mmuoff text into idmap

[james.morse@arm.com (James Morse)]

Resume from hibernate needs to clean any text executed by the kernel with
the MMU off to the PoC. Collect these functions together into the
.idmap.text section as all this code is tightly coupled and also needs
the same cleaning after resume.

Data is more complicated, secondary_holding_pen_release is written with
the MMU on, clean and invalidated, then read with the MMU off. In contrast
__boot_cpu_mode is written with the MMU off, the corresponding cache line
is invalidated, so when we read it with the MMU on we don't get stale data.
These cache maintenance operations conflict with each other if the values
are within a Cache Writeback Granule (CWG) of each other.
Collect the data into two sections .mmuoff.data.read and .mmuoff.data.write,
the linker script ensures mmuoff.data.write section is aligned to the
architectural maximum CWG of 2KB.

Signed-off-by: James Morse <james.morse@arm.com>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>

---
Changes since v5:
 * Moved .mmuoff.text into .idmap.text,
 * Moved ALIGN() out of .mmuoff.data.read in case this section gets removed.
 * Removed stray "don't"

 arch/arm64/include/asm/sections.h  |  1 +
 arch/arm64/kernel/head.S           | 25 +++++++++++++++----------
 arch/arm64/kernel/sleep.S          |  2 +-
 arch/arm64/kernel/smp_spin_table.c |  3 ++-
 arch/arm64/kernel/vmlinux.lds.S    | 19 +++++++++++++++++++
 arch/arm64/mm/proc.S               |  4 ++++
 6 files changed, 42 insertions(+), 12 deletions(-)

diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h
index 237fcdd13445..4e7e7067afdb 100644
--- a/arch/arm64/include/asm/sections.h
+++ b/arch/arm64/include/asm/sections.h
@@ -25,5 +25,6 @@ extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[];
 extern char __hyp_text_start[], __hyp_text_end[];
 extern char __idmap_text_start[], __idmap_text_end[];
 extern char __irqentry_text_start[], __irqentry_text_end[];
+extern char __mmuoff_data_start[], __mmuoff_data_end[];
 
 #endif /* __ASM_SECTIONS_H */
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index b77f58355da1..4413144f7ea4 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -465,7 +465,7 @@ ENDPROC(__primary_switched)
  * end early head section, begin head code that is also used for
  * hotplug and needs to have the same protections as the text region
  */
-	.section ".text","ax"
+	.section ".idmap.text","ax"
 
 ENTRY(kimage_vaddr)
 	.quad		_text - TEXT_OFFSET
@@ -621,17 +621,29 @@ set_cpu_boot_mode_flag:
 ENDPROC(set_cpu_boot_mode_flag)
 
 /*
+ * These values are written with the MMU off, but read with the MMU on.
+ * Writers will invalidate the corresponding address, discarding up to a
+ * 'Cache Writeback Granule' (CWG) worth of data. The linker script ensures
+ * sufficient alignment that the CWG doesn't overlap another section.
+ */
+	.pushsection ".mmuoff.data.write", "aw"
+/*
  * We need to find out the CPU boot mode long after boot, so we need to
  * store it in a writable variable.
  *
  * This is not in .bss, because we set it sufficiently early that the boot-time
  * zeroing of .bss would clobber it.
  */
-	.pushsection	.data..cacheline_aligned
-	.align	L1_CACHE_SHIFT
 ENTRY(__boot_cpu_mode)
 	.long	BOOT_CPU_MODE_EL2
 	.long	BOOT_CPU_MODE_EL1
+/*
+ * The booting CPU updates the failed status @__early_cpu_boot_status,
+ * with MMU turned off.
+ */
+ENTRY(__early_cpu_boot_status)
+	.long 	0
+
 	.popsection
 
 	/*
@@ -706,12 +718,6 @@ ENDPROC(__secondary_switched)
 	dc	ivac, \tmp1			// Invalidate potentially stale cache line
 	.endm
 
-	.pushsection	.data..cacheline_aligned
-	.align	L1_CACHE_SHIFT
-ENTRY(__early_cpu_boot_status)
-	.long 	0
-	.popsection
-
 /*
  * Enable the MMU.
  *
@@ -723,7 +729,6 @@ ENTRY(__early_cpu_boot_status)
  * Checks if the selected granule size is supported by the CPU.
  * If it isn't, park the CPU
  */
-	.section	".idmap.text", "ax"
 ENTRY(__enable_mmu)
 	mrs	x22, sctlr_el1			// preserve old SCTLR_EL1 value
 	mrs	x1, ID_AA64MMFR0_EL1
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index ccf79d849e0a..679b0ad1e9cd 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -97,6 +97,7 @@ ENTRY(__cpu_suspend_enter)
 ENDPROC(__cpu_suspend_enter)
 	.ltorg
 
+	.pushsection ".idmap.text", "ax"
 ENTRY(cpu_resume)
 	bl	el2_setup		// if in EL2 drop to EL1 cleanly
 	/* enable the MMU early - so we can access sleep_save_stash by va */
@@ -107,7 +108,6 @@ ENTRY(cpu_resume)
 	b	__cpu_setup
 ENDPROC(cpu_resume)
 
-	.pushsection	".idmap.text", "ax"
 _resume_switched:
 	ldr	x8, =_cpu_resume
 	br	x8
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 18a71bcd26ee..9a00eee9acc8 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -29,7 +29,8 @@
 #include <asm/smp_plat.h>
 
 extern void secondary_holding_pen(void);
-volatile unsigned long secondary_holding_pen_release = INVALID_HWID;
+volatile unsigned long __section(".mmuoff.data.read")
+secondary_holding_pen_release = INVALID_HWID;
 
 static phys_addr_t cpu_release_addr[NR_CPUS];
 
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 659963d40bb4..5ce9b2929e0d 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -185,6 +185,25 @@ SECTIONS
 	_data = .;
 	_sdata = .;
 	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+
+	/*
+	 * Data written with the MMU off but read with the MMU on requires
+	 * cache lines to be invalidated, discarding up to a Cache Writeback
+	 * Granule (CWG) of data from the cache. Keep the section that
+	 * requires this type of maintenance to be in its own Cache Writeback
+	 * Granule (CWG) area so the cache maintenance operations don't
+	 * interfere with adjacent data.
+	 */
+	.mmuoff.data.write : ALIGN(SZ_2K) {
+		__mmuoff_data_start = .;
+		*(.mmuoff.data.write)
+	}
+	. = ALIGN(SZ_2K);
+	.mmuoff.data.read : {
+		*(.mmuoff.data.read)
+		__mmuoff_data_end = .;
+	}
+
 	PECOFF_EDATA_PADDING
 	_edata = .;
 
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 5bb61de23201..5eb35964ab8e 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -83,6 +83,7 @@ ENDPROC(cpu_do_suspend)
  *
  * x0: Address of context pointer
  */
+	.pushsection ".idmap.text", "ax"
 ENTRY(cpu_do_resume)
 	ldp	x2, x3, [x0]
 	ldp	x4, x5, [x0, #16]
@@ -111,6 +112,7 @@ ENTRY(cpu_do_resume)
 	isb
 	ret
 ENDPROC(cpu_do_resume)
+	.popsection
 #endif
 
 /*
@@ -172,6 +174,7 @@ ENDPROC(idmap_cpu_replace_ttbr1)
  *	Initialise the processor for turning the MMU on.  Return in x0 the
  *	value of the SCTLR_EL1 register.
  */
+	.pushsection ".idmap.text", "ax"
 ENTRY(__cpu_setup)
 	tlbi	vmalle1				// Invalidate local TLB
 	dsb	nsh
@@ -257,3 +260,4 @@ ENDPROC(__cpu_setup)
 crval:
 	.word	0xfcffffff			// clear
 	.word	0x34d5d91d			// set
+	.popsection
-- 
2.8.0.rc3