Merge Linus master into drm-next

The merge is clean, but the arm build fails afterwards,
due to API changes in the regulator tree.

I've included the patch into the merge to fix the build.

Signed-off-by: Dave Airlie <airlied@redhat.com>

1 files changed, 92 insertions, 169 deletions

diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 07f930540f4a..19f915e8f6e0 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -36,7 +36,7 @@
 #include <asm/page.h>
 #include <asm/virt.h>
 
-#define KERNEL_RAM_VADDR	(PAGE_OFFSET + TEXT_OFFSET)
+#define __PHYS_OFFSET	(KERNEL_START - TEXT_OFFSET)
 
 #if (TEXT_OFFSET & 0xfff) != 0
 #error TEXT_OFFSET must be at least 4KB aligned
@@ -46,13 +46,6 @@
 #error TEXT_OFFSET must be less than 2MB
 #endif
 
-	.macro	pgtbl, ttb0, ttb1, virt_to_phys
-	ldr	\ttb1, =swapper_pg_dir
-	ldr	\ttb0, =idmap_pg_dir
-	add	\ttb1, \ttb1, \virt_to_phys
-	add	\ttb0, \ttb0, \virt_to_phys
-	.endm
-
 #ifdef CONFIG_ARM64_64K_PAGES
 #define BLOCK_SHIFT	PAGE_SHIFT
 #define BLOCK_SIZE	PAGE_SIZE
@@ -63,7 +56,7 @@
 #define TABLE_SHIFT	PUD_SHIFT
 #endif
 
-#define KERNEL_START	KERNEL_RAM_VADDR
+#define KERNEL_START	_text
 #define KERNEL_END	_end
 
 /*
@@ -240,40 +233,43 @@ section_table:
 #endif
 
 ENTRY(stext)
-	mov	x21, x0				// x21=FDT
+	bl	preserve_boot_args
 	bl	el2_setup			// Drop to EL1, w20=cpu_boot_mode
-	bl	__calc_phys_offset		// x24=PHYS_OFFSET, x28=PHYS_OFFSET-PAGE_OFFSET
+	adrp	x24, __PHYS_OFFSET
 	bl	set_cpu_boot_mode_flag
-	mrs	x22, midr_el1			// x22=cpuid
-	mov	x0, x22
-	bl	lookup_processor_type
-	mov	x23, x0				// x23=current cpu_table
-	/*
-	 * __error_p may end up out of range for cbz if text areas are
-	 * aligned up to section sizes.
-	 */
-	cbnz	x23, 1f				// invalid processor (x23=0)?
-	b	__error_p
-1:
+
 	bl	__vet_fdt
 	bl	__create_page_tables		// x25=TTBR0, x26=TTBR1
 	/*
-	 * The following calls CPU specific code in a position independent
-	 * manner. See arch/arm64/mm/proc.S for details. x23 = base of
-	 * cpu_info structure selected by lookup_processor_type above.
+	 * The following calls CPU setup code, see arch/arm64/mm/proc.S for
+	 * details.
 	 * On return, the CPU will be ready for the MMU to be turned on and
 	 * the TCR will have been set.
 	 */
-	ldr	x27, __switch_data		// address to jump to after
+	ldr	x27, =__mmap_switched		// address to jump to after
 						// MMU has been enabled
-	adrp	lr, __enable_mmu		// return (PIC) address
-	add	lr, lr, #:lo12:__enable_mmu
-	ldr	x12, [x23, #CPU_INFO_SETUP]
-	add	x12, x12, x28			// __virt_to_phys
-	br	x12				// initialise processor
+	adr_l	lr, __enable_mmu		// return (PIC) address
+	b	__cpu_setup			// initialise processor
 ENDPROC(stext)
 
 /*
+ * Preserve the arguments passed by the bootloader in x0 .. x3
+ */
+preserve_boot_args:
+	mov	x21, x0				// x21=FDT
+
+	adr_l	x0, boot_args			// record the contents of
+	stp	x21, x1, [x0]			// x0 .. x3 at kernel entry
+	stp	x2, x3, [x0, #16]
+
+	dmb	sy				// needed before dc ivac with
+						// MMU off
+
+	add	x1, x0, #0x20			// 4 x 8 bytes
+	b	__inval_cache_range		// tail call
+ENDPROC(preserve_boot_args)
+
+/*
  * Determine validity of the x21 FDT pointer.
  * The dtb must be 8-byte aligned and live in the first 512M of memory.
  */
@@ -356,7 +352,8 @@ ENDPROC(__vet_fdt)
  *   - pgd entry for fixed mappings (TTBR1)
  */
 __create_page_tables:
-	pgtbl	x25, x26, x28			// idmap_pg_dir and swapper_pg_dir addresses
+	adrp	x25, idmap_pg_dir
+	adrp	x26, swapper_pg_dir
 	mov	x27, lr
 
 	/*
@@ -385,12 +382,50 @@ __create_page_tables:
 	 * Create the identity mapping.
 	 */
 	mov	x0, x25				// idmap_pg_dir
-	ldr	x3, =KERNEL_START
-	add	x3, x3, x28			// __pa(KERNEL_START)
+	adrp	x3, KERNEL_START		// __pa(KERNEL_START)
+
+#ifndef CONFIG_ARM64_VA_BITS_48
+#define EXTRA_SHIFT	(PGDIR_SHIFT + PAGE_SHIFT - 3)
+#define EXTRA_PTRS	(1 << (48 - EXTRA_SHIFT))
+
+	/*
+	 * If VA_BITS < 48, it may be too small to allow for an ID mapping to be
+	 * created that covers system RAM if that is located sufficiently high
+	 * in the physical address space. So for the ID map, use an extended
+	 * virtual range in that case, by configuring an additional translation
+	 * level.
+	 * First, we have to verify our assumption that the current value of
+	 * VA_BITS was chosen such that all translation levels are fully
+	 * utilised, and that lowering T0SZ will always result in an additional
+	 * translation level to be configured.
+	 */
+#if VA_BITS != EXTRA_SHIFT
+#error "Mismatch between VA_BITS and page size/number of translation levels"
+#endif
+
+	/*
+	 * Calculate the maximum allowed value for TCR_EL1.T0SZ so that the
+	 * entire kernel image can be ID mapped. As T0SZ == (64 - #bits used),
+	 * this number conveniently equals the number of leading zeroes in
+	 * the physical address of KERNEL_END.
+	 */
+	adrp	x5, KERNEL_END
+	clz	x5, x5
+	cmp	x5, TCR_T0SZ(VA_BITS)	// default T0SZ small enough?
+	b.ge	1f			// .. then skip additional level
+
+	adr_l	x6, idmap_t0sz
+	str	x5, [x6]
+	dmb	sy
+	dc	ivac, x6		// Invalidate potentially stale cache line
+
+	create_table_entry x0, x3, EXTRA_SHIFT, EXTRA_PTRS, x5, x6
+1:
+#endif
+
 	create_pgd_entry x0, x3, x5, x6
-	ldr	x6, =KERNEL_END
 	mov	x5, x3				// __pa(KERNEL_START)
-	add	x6, x6, x28			// __pa(KERNEL_END)
+	adr_l	x6, KERNEL_END			// __pa(KERNEL_END)
 	create_block_map x0, x7, x3, x5, x6
 
 	/*
@@ -399,7 +434,7 @@ __create_page_tables:
 	mov	x0, x26				// swapper_pg_dir
 	mov	x5, #PAGE_OFFSET
 	create_pgd_entry x0, x5, x3, x6
-	ldr	x6, =KERNEL_END
+	ldr	x6, =KERNEL_END			// __va(KERNEL_END)
 	mov	x3, x24				// phys offset
 	create_block_map x0, x7, x3, x5, x6
 
@@ -426,6 +461,7 @@ __create_page_tables:
 	 */
 	mov	x0, x25
 	add	x1, x26, #SWAPPER_DIR_SIZE
+	dmb	sy
 	bl	__inval_cache_range
 
 	mov	lr, x27
@@ -433,37 +469,22 @@ __create_page_tables:
 ENDPROC(__create_page_tables)
 	.ltorg
 
-	.align	3
-	.type	__switch_data, %object
-__switch_data:
-	.quad	__mmap_switched
-	.quad	__bss_start			// x6
-	.quad	__bss_stop			// x7
-	.quad	processor_id			// x4
-	.quad	__fdt_pointer			// x5
-	.quad	memstart_addr			// x6
-	.quad	init_thread_union + THREAD_START_SP // sp
-
 /*
- * The following fragment of code is executed with the MMU on in MMU mode, and
- * uses absolute addresses; this is not position independent.
+ * The following fragment of code is executed with the MMU enabled.
  */
+	.set	initial_sp, init_thread_union + THREAD_START_SP
 __mmap_switched:
-	adr	x3, __switch_data + 8
+	adr_l	x6, __bss_start
+	adr_l	x7, __bss_stop
 
-	ldp	x6, x7, [x3], #16
 1:	cmp	x6, x7
 	b.hs	2f
 	str	xzr, [x6], #8			// Clear BSS
 	b	1b
 2:
-	ldp	x4, x5, [x3], #16
-	ldr	x6, [x3], #8
-	ldr	x16, [x3]
-	mov	sp, x16
-	str	x22, [x4]			// Save processor ID
-	str	x21, [x5]			// Save FDT pointer
-	str	x24, [x6]			// Save PHYS_OFFSET
+	adr_l	sp, initial_sp, x4
+	str_l	x21, __fdt_pointer, x5		// Save FDT pointer
+	str_l	x24, memstart_addr, x6		// Save PHYS_OFFSET
 	mov	x29, #0
 	b	start_kernel
 ENDPROC(__mmap_switched)
@@ -566,8 +587,7 @@ ENDPROC(el2_setup)
  * in x20. See arch/arm64/include/asm/virt.h for more info.
  */
 ENTRY(set_cpu_boot_mode_flag)
-	ldr	x1, =__boot_cpu_mode		// Compute __boot_cpu_mode
-	add	x1, x1, x28
+	adr_l	x1, __boot_cpu_mode
 	cmp	w20, #BOOT_CPU_MODE_EL2
 	b.ne	1f
 	add	x1, x1, #4
@@ -588,29 +608,21 @@ ENDPROC(set_cpu_boot_mode_flag)
 	.align	L1_CACHE_SHIFT
 ENTRY(__boot_cpu_mode)
 	.long	BOOT_CPU_MODE_EL2
-	.long	0
+	.long	BOOT_CPU_MODE_EL1
 	.popsection
 
 #ifdef CONFIG_SMP
-	.align	3
-1:	.quad	.
-	.quad	secondary_holding_pen_release
-
 	/*
 	 * This provides a "holding pen" for platforms to hold all secondary
 	 * cores are held until we're ready for them to initialise.
 	 */
 ENTRY(secondary_holding_pen)
 	bl	el2_setup			// Drop to EL1, w20=cpu_boot_mode
-	bl	__calc_phys_offset		// x24=PHYS_OFFSET, x28=PHYS_OFFSET-PAGE_OFFSET
 	bl	set_cpu_boot_mode_flag
 	mrs	x0, mpidr_el1
 	ldr     x1, =MPIDR_HWID_BITMASK
 	and	x0, x0, x1
-	adr	x1, 1b
-	ldp	x2, x3, [x1]
-	sub	x1, x1, x2
-	add	x3, x3, x1
+	adr_l	x3, secondary_holding_pen_release
 pen:	ldr	x4, [x3]
 	cmp	x4, x0
 	b.eq	secondary_startup
@@ -624,7 +636,6 @@ ENDPROC(secondary_holding_pen)
 	 */
 ENTRY(secondary_entry)
 	bl	el2_setup			// Drop to EL1
-	bl	__calc_phys_offset		// x24=PHYS_OFFSET, x28=PHYS_OFFSET-PAGE_OFFSET
 	bl	set_cpu_boot_mode_flag
 	b	secondary_startup
 ENDPROC(secondary_entry)
@@ -633,16 +644,9 @@ ENTRY(secondary_startup)
 	/*
 	 * Common entry point for secondary CPUs.
 	 */
-	mrs	x22, midr_el1			// x22=cpuid
-	mov	x0, x22
-	bl	lookup_processor_type
-	mov	x23, x0				// x23=current cpu_table
-	cbz	x23, __error_p			// invalid processor (x23=0)?
-
-	pgtbl	x25, x26, x28			// x25=TTBR0, x26=TTBR1
-	ldr	x12, [x23, #CPU_INFO_SETUP]
-	add	x12, x12, x28			// __virt_to_phys
-	blr	x12				// initialise processor
+	adrp	x25, idmap_pg_dir
+	adrp	x26, swapper_pg_dir
+	bl	__cpu_setup			// initialise processor
 
 	ldr	x21, =secondary_data
 	ldr	x27, =__secondary_switched	// address to jump to after enabling the MMU
@@ -658,11 +662,12 @@ ENDPROC(__secondary_switched)
 #endif	/* CONFIG_SMP */
 
 /*
- * Setup common bits before finally enabling the MMU. Essentially this is just
- * loading the page table pointer and vector base registers.
+ * Enable the MMU.
  *
- * On entry to this code, x0 must contain the SCTLR_EL1 value for turning on
- * the MMU.
+ *  x0  = SCTLR_EL1 value for turning on the MMU.
+ *  x27 = *virtual* address to jump to upon completion
+ *
+ * other registers depend on the function called upon completion
  */
 __enable_mmu:
 	ldr	x5, =vectors
@@ -670,89 +675,7 @@ __enable_mmu:
 	msr	ttbr0_el1, x25			// load TTBR0
 	msr	ttbr1_el1, x26			// load TTBR1
 	isb
-	b	__turn_mmu_on
-ENDPROC(__enable_mmu)
-
-/*
- * Enable the MMU. This completely changes the structure of the visible memory
- * space. You will not be able to trace execution through this.
- *
- *  x0  = system control register
- *  x27 = *virtual* address to jump to upon completion
- *
- * other registers depend on the function called upon completion
- *
- * We align the entire function to the smallest power of two larger than it to
- * ensure it fits within a single block map entry. Otherwise were PHYS_OFFSET
- * close to the end of a 512MB or 1GB block we might require an additional
- * table to map the entire function.
- */
-	.align	4
-__turn_mmu_on:
 	msr	sctlr_el1, x0
 	isb
 	br	x27
-ENDPROC(__turn_mmu_on)
-
-/*
- * Calculate the start of physical memory.
- */
-__calc_phys_offset:
-	adr	x0, 1f
-	ldp	x1, x2, [x0]
-	sub	x28, x0, x1			// x28 = PHYS_OFFSET - PAGE_OFFSET
-	add	x24, x2, x28			// x24 = PHYS_OFFSET
-	ret
-ENDPROC(__calc_phys_offset)
-
-	.align 3
-1:	.quad	.
-	.quad	PAGE_OFFSET
-
-/*
- * Exception handling. Something went wrong and we can't proceed. We ought to
- * tell the user, but since we don't have any guarantee that we're even
- * running on the right architecture, we do virtually nothing.
- */
-__error_p:
-ENDPROC(__error_p)
-
-__error:
-1:	nop
-	b	1b
-ENDPROC(__error)
-
-/*
- * This function gets the processor ID in w0 and searches the cpu_table[] for
- * a match. It returns a pointer to the struct cpu_info it found. The
- * cpu_table[] must end with an empty (all zeros) structure.
- *
- * This routine can be called via C code and it needs to work with the MMU
- * both disabled and enabled (the offset is calculated automatically).
- */
-ENTRY(lookup_processor_type)
-	adr	x1, __lookup_processor_type_data
-	ldp	x2, x3, [x1]
-	sub	x1, x1, x2			// get offset between VA and PA
-	add	x3, x3, x1			// convert VA to PA
-1:
-	ldp	w5, w6, [x3]			// load cpu_id_val and cpu_id_mask
-	cbz	w5, 2f				// end of list?
-	and	w6, w6, w0
-	cmp	w5, w6
-	b.eq	3f
-	add	x3, x3, #CPU_INFO_SZ
-	b	1b
-2:
-	mov	x3, #0				// unknown processor
-3:
-	mov	x0, x3
-	ret
-ENDPROC(lookup_processor_type)
-
-	.align	3
-	.type	__lookup_processor_type_data, %object
-__lookup_processor_type_data:
-	.quad	.
-	.quad	cpu_table
-	.size	__lookup_processor_type_data, . - __lookup_processor_type_data
+ENDPROC(__enable_mmu)