Merge tag 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm

Pull ARM development updates from Russell King:

 - Make it clear __swp_entry_to_pte() uses PTE_TYPE_FAULT

 - Updates for setting vmalloc size via command line to resolve an issue
   with the 8MiB hole not properly being accounted for, and clean up the
   code.

 - ftrace support for module PLTs

 - Spelling fixes

 - kbuild updates for removing generated files and pattern rules for
   generating files

 - Clang/llvm updates

 - Change the way the kernel is mapped, placing it in vmalloc space
   instead.

 - Remove arm_pm_restart from arm and aarch64.

* tag 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm: (29 commits)
  ARM: 9098/1: ftrace: MODULE_PLT: Fix build problem without DYNAMIC_FTRACE
  ARM: 9097/1: mmu: Declare section start/end correctly
  ARM: 9096/1: Remove arm_pm_restart()
  ARM: 9095/1: ARM64: Remove arm_pm_restart()
  ARM: 9094/1: Register with kernel restart handler
  ARM: 9093/1: drivers: firmwapsci: Register with kernel restart handler
  ARM: 9092/1: xen: Register with kernel restart handler
  ARM: 9091/1: Revert "mm: qsd8x50: Fix incorrect permission faults"
  ARM: 9090/1: Map the lowmem and kernel separately
  ARM: 9089/1: Define kernel physical section start and end
  ARM: 9088/1: Split KERNEL_OFFSET from PAGE_OFFSET
  ARM: 9087/1: kprobes: test-thumb: fix for LLVM_IAS=1
  ARM: 9086/1: syscalls: use pattern rules to generate syscall headers
  ARM: 9085/1: remove unneeded abi parameter to syscallnr.sh
  ARM: 9084/1: simplify the build rule of mach-types.h
  ARM: 9083/1: uncompress: atags_to_fdt: Spelling s/REturn/Return/
  ARM: 9082/1: [v2] mark prepare_page_table as __init
  ARM: 9079/1: ftrace: Add MODULE_PLTS support
  ARM: 9078/1: Add warn suppress parameter to arm_gen_branch_link()
  ARM: 9077/1: PLT: Move struct plt_entries definition to header
  ...

3 files changed, 123 insertions, 71 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 35f43d0aa056..8355c3895894 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -601,8 +601,6 @@ config CPU_TLB_V6
 config CPU_TLB_V7
 	bool
 
-config VERIFY_PERMISSION_FAULT
-	bool
 endif
 
 config CPU_HAS_ASID
diff --git a/arch/arm/mm/abort-ev7.S b/arch/arm/mm/abort-ev7.S
index f7cc5d68444b..f81bceacc660 100644
--- a/arch/arm/mm/abort-ev7.S
+++ b/arch/arm/mm/abort-ev7.S
@@ -17,31 +17,5 @@ ENTRY(v7_early_abort)
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 	uaccess_disable ip			@ disable userspace access
-
-	/*
-	 * V6 code adjusts the returned DFSR.
-	 * New designs should not need to patch up faults.
-	 */
-
-#if defined(CONFIG_VERIFY_PERMISSION_FAULT)
-	/*
-	 * Detect erroneous permission failures and fix
-	 */
-	ldr	r3, =0x40d			@ On permission fault
-	and	r3, r1, r3
-	cmp	r3, #0x0d
-	bne	do_DataAbort
-
-	mcr	p15, 0, r0, c7, c8, 0   	@ Retranslate FAR
-	isb
-	mrc	p15, 0, ip, c7, c4, 0   	@ Read the PAR
-	and	r3, ip, #0x7b   		@ On translation fault
-	cmp	r3, #0x0b
-	bne	do_DataAbort
-	bic	r1, r1, #0xf			@ Fix up FSR FS[5:0]
-	and	ip, ip, #0x7e
-	orr	r1, r1, ip, LSR #1
-#endif
-
 	b	do_DataAbort
 ENDPROC(v7_early_abort)
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index c1e12aab67b8..7583bda5ea7d 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -1121,31 +1121,32 @@ void __init debug_ll_io_init(void)
 }
 #endif
 
-static void * __initdata vmalloc_min =
-	(void *)(VMALLOC_END - (240 << 20) - VMALLOC_OFFSET);
+static unsigned long __initdata vmalloc_size = 240 * SZ_1M;
 
 /*
  * vmalloc=size forces the vmalloc area to be exactly 'size'
  * bytes. This can be used to increase (or decrease) the vmalloc
- * area - the default is 240m.
+ * area - the default is 240MiB.
  */
 static int __init early_vmalloc(char *arg)
 {
 	unsigned long vmalloc_reserve = memparse(arg, NULL);
+	unsigned long vmalloc_max;
 
 	if (vmalloc_reserve < SZ_16M) {
 		vmalloc_reserve = SZ_16M;
-		pr_warn("vmalloc area too small, limiting to %luMB\n",
+		pr_warn("vmalloc area is too small, limiting to %luMiB\n",
 			vmalloc_reserve >> 20);
 	}
 
-	if (vmalloc_reserve > VMALLOC_END - (PAGE_OFFSET + SZ_32M)) {
-		vmalloc_reserve = VMALLOC_END - (PAGE_OFFSET + SZ_32M);
-		pr_warn("vmalloc area is too big, limiting to %luMB\n",
+	vmalloc_max = VMALLOC_END - (PAGE_OFFSET + SZ_32M + VMALLOC_OFFSET);
+	if (vmalloc_reserve > vmalloc_max) {
+		vmalloc_reserve = vmalloc_max;
+		pr_warn("vmalloc area is too big, limiting to %luMiB\n",
 			vmalloc_reserve >> 20);
 	}
 
-	vmalloc_min = (void *)(VMALLOC_END - vmalloc_reserve);
+	vmalloc_size = vmalloc_reserve;
 	return 0;
 }
 early_param("vmalloc", early_vmalloc);
@@ -1165,7 +1166,8 @@ void __init adjust_lowmem_bounds(void)
 	 * and may itself be outside the valid range for which phys_addr_t
 	 * and therefore __pa() is defined.
 	 */
-	vmalloc_limit = (u64)(uintptr_t)vmalloc_min - PAGE_OFFSET + PHYS_OFFSET;
+	vmalloc_limit = (u64)VMALLOC_END - vmalloc_size - VMALLOC_OFFSET -
+			PAGE_OFFSET + PHYS_OFFSET;
 
 	/*
 	 * The first usable region must be PMD aligned. Mark its start
@@ -1246,7 +1248,7 @@ void __init adjust_lowmem_bounds(void)
 	memblock_set_current_limit(memblock_limit);
 }
 
-static inline void prepare_page_table(void)
+static __init void prepare_page_table(void)
 {
 	unsigned long addr;
 	phys_addr_t end;
@@ -1457,8 +1459,6 @@ static void __init kmap_init(void)
 
 static void __init map_lowmem(void)
 {
-	phys_addr_t kernel_x_start = round_down(__pa(KERNEL_START), SECTION_SIZE);
-	phys_addr_t kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE);
 	phys_addr_t start, end;
 	u64 i;
 
@@ -1466,55 +1466,126 @@ static void __init map_lowmem(void)
 	for_each_mem_range(i, &start, &end) {
 		struct map_desc map;
 
+		pr_debug("map lowmem start: 0x%08llx, end: 0x%08llx\n",
+			 (long long)start, (long long)end);
 		if (end > arm_lowmem_limit)
 			end = arm_lowmem_limit;
 		if (start >= end)
 			break;
 
-		if (end < kernel_x_start) {
-			map.pfn = __phys_to_pfn(start);
-			map.virtual = __phys_to_virt(start);
-			map.length = end - start;
-			map.type = MT_MEMORY_RWX;
+		/*
+		 * If our kernel image is in the VMALLOC area we need to remove
+		 * the kernel physical memory from lowmem since the kernel will
+		 * be mapped separately.
+		 *
+		 * The kernel will typically be at the very start of lowmem,
+		 * but any placement relative to memory ranges is possible.
+		 *
+		 * If the memblock contains the kernel, we have to chisel out
+		 * the kernel memory from it and map each part separately. We
+		 * get 6 different theoretical cases:
+		 *
+		 *                            +--------+ +--------+
+		 *  +-- start --+  +--------+ | Kernel | | Kernel |
+		 *  |           |  | Kernel | | case 2 | | case 5 |
+		 *  |           |  | case 1 | +--------+ |        | +--------+
+		 *  |  Memory   |  +--------+            |        | | Kernel |
+		 *  |  range    |  +--------+            |        | | case 6 |
+		 *  |           |  | Kernel | +--------+ |        | +--------+
+		 *  |           |  | case 3 | | Kernel | |        |
+		 *  +-- end ----+  +--------+ | case 4 | |        |
+		 *                            +--------+ +--------+
+		 */
 
-			create_mapping(&map);
-		} else if (start >= kernel_x_end) {
-			map.pfn = __phys_to_pfn(start);
-			map.virtual = __phys_to_virt(start);
-			map.length = end - start;
-			map.type = MT_MEMORY_RW;
+		/* Case 5: kernel covers range, don't map anything, should be rare */
+		if ((start > kernel_sec_start) && (end < kernel_sec_end))
+			break;
 
-			create_mapping(&map);
-		} else {
-			/* This better cover the entire kernel */
-			if (start < kernel_x_start) {
+		/* Cases where the kernel is starting inside the range */
+		if ((kernel_sec_start >= start) && (kernel_sec_start <= end)) {
+			/* Case 6: kernel is embedded in the range, we need two mappings */
+			if ((start < kernel_sec_start) && (end > kernel_sec_end)) {
+				/* Map memory below the kernel */
 				map.pfn = __phys_to_pfn(start);
 				map.virtual = __phys_to_virt(start);
-				map.length = kernel_x_start - start;
+				map.length = kernel_sec_start - start;
 				map.type = MT_MEMORY_RW;
-
 				create_mapping(&map);
-			}
-
-			map.pfn = __phys_to_pfn(kernel_x_start);
-			map.virtual = __phys_to_virt(kernel_x_start);
-			map.length = kernel_x_end - kernel_x_start;
-			map.type = MT_MEMORY_RWX;
-
-			create_mapping(&map);
-
-			if (kernel_x_end < end) {
-				map.pfn = __phys_to_pfn(kernel_x_end);
-				map.virtual = __phys_to_virt(kernel_x_end);
-				map.length = end - kernel_x_end;
+				/* Map memory above the kernel */
+				map.pfn = __phys_to_pfn(kernel_sec_end);
+				map.virtual = __phys_to_virt(kernel_sec_end);
+				map.length = end - kernel_sec_end;
 				map.type = MT_MEMORY_RW;
-
 				create_mapping(&map);
+				break;
 			}
+			/* Case 1: kernel and range start at the same address, should be common */
+			if (kernel_sec_start == start)
+				start = kernel_sec_end;
+			/* Case 3: kernel and range end at the same address, should be rare */
+			if (kernel_sec_end == end)
+				end = kernel_sec_start;
+		} else if ((kernel_sec_start < start) && (kernel_sec_end > start) && (kernel_sec_end < end)) {
+			/* Case 2: kernel ends inside range, starts below it */
+			start = kernel_sec_end;
+		} else if ((kernel_sec_start > start) && (kernel_sec_start < end) && (kernel_sec_end > end)) {
+			/* Case 4: kernel starts inside range, ends above it */
+			end = kernel_sec_start;
 		}
+		map.pfn = __phys_to_pfn(start);
+		map.virtual = __phys_to_virt(start);
+		map.length = end - start;
+		map.type = MT_MEMORY_RW;
+		create_mapping(&map);
 	}
 }
 
+static void __init map_kernel(void)
+{
+	/*
+	 * We use the well known kernel section start and end and split the area in the
+	 * middle like this:
+	 *  .                .
+	 *  | RW memory      |
+	 *  +----------------+ kernel_x_start
+	 *  | Executable     |
+	 *  | kernel memory  |
+	 *  +----------------+ kernel_x_end / kernel_nx_start
+	 *  | Non-executable |
+	 *  | kernel memory  |
+	 *  +----------------+ kernel_nx_end
+	 *  | RW memory      |
+	 *  .                .
+	 *
+	 * Notice that we are dealing with section sized mappings here so all of this
+	 * will be bumped to the closest section boundary. This means that some of the
+	 * non-executable part of the kernel memory is actually mapped as executable.
+	 * This will only persist until we turn on proper memory management later on
+	 * and we remap the whole kernel with page granularity.
+	 */
+	phys_addr_t kernel_x_start = kernel_sec_start;
+	phys_addr_t kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE);
+	phys_addr_t kernel_nx_start = kernel_x_end;
+	phys_addr_t kernel_nx_end = kernel_sec_end;
+	struct map_desc map;
+
+	map.pfn = __phys_to_pfn(kernel_x_start);
+	map.virtual = __phys_to_virt(kernel_x_start);
+	map.length = kernel_x_end - kernel_x_start;
+	map.type = MT_MEMORY_RWX;
+	create_mapping(&map);
+
+	/* If the nx part is small it may end up covered by the tail of the RWX section */
+	if (kernel_x_end == kernel_nx_end)
+		return;
+
+	map.pfn = __phys_to_pfn(kernel_nx_start);
+	map.virtual = __phys_to_virt(kernel_nx_start);
+	map.length = kernel_nx_end - kernel_nx_start;
+	map.type = MT_MEMORY_RW;
+	create_mapping(&map);
+}
+
 #ifdef CONFIG_ARM_PV_FIXUP
 typedef void pgtables_remap(long long offset, unsigned long pgd);
 pgtables_remap lpae_pgtables_remap_asm;
@@ -1645,9 +1716,18 @@ void __init paging_init(const struct machine_desc *mdesc)
 {
 	void *zero_page;
 
+	pr_debug("physical kernel sections: 0x%08x-0x%08x\n",
+		 kernel_sec_start, kernel_sec_end);
+
 	prepare_page_table();
 	map_lowmem();
 	memblock_set_current_limit(arm_lowmem_limit);
+	pr_debug("lowmem limit is %08llx\n", (long long)arm_lowmem_limit);
+	/*
+	 * After this point early_alloc(), i.e. the memblock allocator, can
+	 * be used
+	 */
+	map_kernel();
 	dma_contiguous_remap();
 	early_fixmap_shutdown();
 	devicemaps_init(mdesc);