arm64 fixes for -rc2

- Fix handling of watchpoints triggered by uaccess routines
 
 - Fix initialisation of gigantic pages for CMA buffers
 
 - Raise minimum clang version for BTI to avoid miscompilation
 
 - Fix data race in SVE vector length configuration code
 
 - Ensure address tags are ignored in kern_addr_valid()
 
 - Dump register state on fatal BTI exception
 
 - kexec_file() cleanup to use struct_size() macro
 -----BEGIN PGP SIGNATURE-----
 
 iQFEBAABCgAuFiEEPxTL6PPUbjXGY88ct6xw3ITBYzQFAl7sl1IQHHdpbGxAa2Vy
 bmVsLm9yZwAKCRC3rHDchMFjNNESB/0UhaH4JI3UPu1DAESsHyYqh6Jdb8TljMxd
 uiAkBT8hJhgq5gUQLBicFpo5AAnEgGuQcG3OMWxWG8PG1MevHemKV1TW38QtbJlA
 p6jwMriSXiwe6199ImoIH6tujshKnoSeo33B470N6i1TzEz8lmS9ml5v1epIT7q4
 1wEPSX+o1Zi/CQKjrfW1UQW7I9C5G26BXusQH4b2Sz8B7RIzHA/+/LqUjcYVtSph
 yjJn1jHhc0GhC7qZUgea4Rz6WZNGlBebGBksIqssvBNhO/St4UmWGmhiUS3YX7rn
 cP7DicrrWVwCib2xUr3fwxxPki4rlV+xHIINVINrOwE1BpqRENl5
 =Gthp
 -----END PGP SIGNATURE-----

Merge tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 fixes from Will Deacon:
 "Unfortunately, we still have a number of outstanding issues so there
  will be more fixes to come, but this lot are a good start.

   - Fix handling of watchpoints triggered by uaccess routines

   - Fix initialisation of gigantic pages for CMA buffers

   - Raise minimum clang version for BTI to avoid miscompilation

   - Fix data race in SVE vector length configuration code

   - Ensure address tags are ignored in kern_addr_valid()

   - Dump register state on fatal BTI exception

   - kexec_file() cleanup to use struct_size() macro"

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: hw_breakpoint: Don't invoke overflow handler on uaccess watchpoints
  arm64: kexec_file: Use struct_size() in kmalloc()
  arm64: mm: reserve hugetlb CMA after numa_init
  arm64: bti: Require clang >= 10.0.1 for in-kernel BTI support
  arm64: sve: Fix build failure when ARM64_SVE=y and SYSCTL=n
  arm64: pgtable: Clear the GP bit for non-executable kernel pages
  arm64: mm: reset address tag set by kasan sw tagging
  arm64: traps: Dump registers prior to panic() in bad_mode()
  arm64/sve: Eliminate data races on sve_default_vl
  docs/arm64: Fix typo'd #define in sve.rst
  arm64: remove TEXT_OFFSET randomization

Documentation/arm64/sve.rst

@@ -186,7 +186,7 @@ prctl(PR_SVE_SET_VL, unsigned long arg)
 
     flags:
 
-	PR_SVE_SET_VL_INHERIT
+	PR_SVE_VL_INHERIT
 
 	    Inherit the current vector length across execve().  Otherwise, the
 	    vector length is reset to the system default at execve().  (See
@@ -247,7 +247,7 @@ prctl(PR_SVE_GET_VL)
 
     The following flag may be OR-ed into the result:
 
-	PR_SVE_SET_VL_INHERIT
+	PR_SVE_VL_INHERIT
 
 	    Vector length will be inherited across execve().
 
@@ -393,7 +393,7 @@ The regset data starts with struct user_sve_header, containing:
 * At every execve() call, the new vector length of the new process is set to
   the system default vector length, unless
 
-    * PR_SVE_SET_VL_INHERIT (or equivalently SVE_PT_VL_INHERIT) is set for the
+    * PR_SVE_VL_INHERIT (or equivalently SVE_PT_VL_INHERIT) is set for the
       calling thread, or
 
     * a deferred vector length change is pending, established via the

arch/arm64/Kconfig

@@ -1630,6 +1630,8 @@ config ARM64_BTI_KERNEL
 	depends on CC_HAS_BRANCH_PROT_PAC_RET_BTI
 	# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94697
 	depends on !CC_IS_GCC || GCC_VERSION >= 100100
+	# https://reviews.llvm.org/rGb8ae3fdfa579dbf366b1bb1cbfdbf8c51db7fa55
+	depends on !CC_IS_CLANG || CLANG_VERSION >= 100001
 	depends on !(CC_IS_CLANG && GCOV_KERNEL)
 	depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS)
 	help

arch/arm64/Kconfig.debug

@@ -8,21 +8,6 @@ config PID_IN_CONTEXTIDR
 	  instructions during context switch. Say Y here only if you are
 	  planning to use hardware trace tools with this kernel.
 
-config ARM64_RANDOMIZE_TEXT_OFFSET
-	bool "Randomize TEXT_OFFSET at build time"
-	help
-	  Say Y here if you want the image load offset (AKA TEXT_OFFSET)
-	  of the kernel to be randomized at build-time. When selected,
-	  this option will cause TEXT_OFFSET to be randomized upon any
-	  build of the kernel, and the offset will be reflected in the
-	  text_offset field of the resulting Image. This can be used to
-	  fuzz-test bootloaders which respect text_offset.
-
-	  This option is intended for bootloader and/or kernel testing
-	  only. Bootloaders must make no assumptions regarding the value
-	  of TEXT_OFFSET and platforms must not require a specific
-	  value.
-
 config DEBUG_EFI
 	depends on EFI && DEBUG_INFO
 	bool "UEFI debugging"

arch/arm64/Makefile

@@ -121,13 +121,7 @@ endif
 head-y		:= arch/arm64/kernel/head.o
 
 # The byte offset of the kernel image in RAM from the start of RAM.
-ifeq ($(CONFIG_ARM64_RANDOMIZE_TEXT_OFFSET), y)
-TEXT_OFFSET := $(shell awk "BEGIN {srand(); printf \"0x%06x\n\", \
-		 int(2 * 1024 * 1024 / (2 ^ $(CONFIG_ARM64_PAGE_SHIFT)) * \
-		 rand()) * (2 ^ $(CONFIG_ARM64_PAGE_SHIFT))}")
-else
 TEXT_OFFSET := 0x0
-endif
 
 ifeq ($(CONFIG_KASAN_SW_TAGS), y)
 KASAN_SHADOW_SCALE_SHIFT := 4

arch/arm64/include/asm/pgtable.h

@@ -416,7 +416,7 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd)
 	__pgprot((pgprot_val(prot) & ~(mask)) | (bits))
 
 #define pgprot_nx(prot) \
-	__pgprot_modify(prot, 0, PTE_PXN)
+	__pgprot_modify(prot, PTE_MAYBE_GP, PTE_PXN)
 
 /*
  * Mark the prot value as uncacheable and unbufferable.

arch/arm64/kernel/fpsimd.c

@@ -12,6 +12,7 @@
 #include <linux/bug.h>
 #include <linux/cache.h>
 #include <linux/compat.h>
+#include <linux/compiler.h>
 #include <linux/cpu.h>
 #include <linux/cpu_pm.h>
 #include <linux/kernel.h>
@@ -119,10 +120,20 @@ struct fpsimd_last_state_struct {
 static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state);
 
 /* Default VL for tasks that don't set it explicitly: */
-static int sve_default_vl = -1;
+static int __sve_default_vl = -1;
+
+static int get_sve_default_vl(void)
+{
+	return READ_ONCE(__sve_default_vl);
+}
 
 #ifdef CONFIG_ARM64_SVE
 
+static void set_sve_default_vl(int val)
+{
+	WRITE_ONCE(__sve_default_vl, val);
+}
+
 /* Maximum supported vector length across all CPUs (initially poisoned) */
 int __ro_after_init sve_max_vl = SVE_VL_MIN;
 int __ro_after_init sve_max_virtualisable_vl = SVE_VL_MIN;
@@ -338,13 +349,13 @@ static unsigned int find_supported_vector_length(unsigned int vl)
 	return sve_vl_from_vq(__bit_to_vq(bit));
 }
 
-#ifdef CONFIG_SYSCTL
+#if defined(CONFIG_ARM64_SVE) && defined(CONFIG_SYSCTL)
 
 static int sve_proc_do_default_vl(struct ctl_table *table, int write,
 				  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
-	int vl = sve_default_vl;
+	int vl = get_sve_default_vl();
 	struct ctl_table tmp_table = {
 		.data = &vl,
 		.maxlen = sizeof(vl),
@@ -361,7 +372,7 @@ static int sve_proc_do_default_vl(struct ctl_table *table, int write,
 	if (!sve_vl_valid(vl))
 		return -EINVAL;
 
-	sve_default_vl = find_supported_vector_length(vl);
+	set_sve_default_vl(find_supported_vector_length(vl));
 	return 0;
 }
 
@@ -383,9 +394,9 @@ static int __init sve_sysctl_init(void)
 	return 0;
 }
 
-#else /* ! CONFIG_SYSCTL */
+#else /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */
 static int __init sve_sysctl_init(void) { return 0; }
-#endif /* ! CONFIG_SYSCTL */
+#endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */
 
 #define ZREG(sve_state, vq, n) ((char *)(sve_state) +		\
 	(SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET))
@@ -868,7 +879,7 @@ void __init sve_setup(void)
 	 * For the default VL, pick the maximum supported value <= 64.
 	 * VL == 64 is guaranteed not to grow the signal frame.
 	 */
-	sve_default_vl = find_supported_vector_length(64);
+	set_sve_default_vl(find_supported_vector_length(64));
 
 	bitmap_andnot(tmp_map, sve_vq_partial_map, sve_vq_map,
 		      SVE_VQ_MAX);
@@ -889,7 +900,7 @@ void __init sve_setup(void)
 	pr_info("SVE: maximum available vector length %u bytes per vector\n",
 		sve_max_vl);
 	pr_info("SVE: default vector length %u bytes per vector\n",
-		sve_default_vl);
+		get_sve_default_vl());
 
 	/* KVM decides whether to support mismatched systems. Just warn here: */
 	if (sve_max_virtualisable_vl < sve_max_vl)
@@ -1029,13 +1040,13 @@ void fpsimd_flush_thread(void)
 		 * vector length configured: no kernel task can become a user
 		 * task without an exec and hence a call to this function.
 		 * By the time the first call to this function is made, all
-		 * early hardware probing is complete, so sve_default_vl
+		 * early hardware probing is complete, so __sve_default_vl
 		 * should be valid.
 		 * If a bug causes this to go wrong, we make some noise and
 		 * try to fudge thread.sve_vl to a safe value here.
 		 */
 		vl = current->thread.sve_vl_onexec ?
-			current->thread.sve_vl_onexec : sve_default_vl;
+			current->thread.sve_vl_onexec : get_sve_default_vl();
 
 		if (WARN_ON(!sve_vl_valid(vl)))
 			vl = SVE_VL_MIN;

arch/arm64/kernel/hw_breakpoint.c

@@ -730,6 +730,27 @@ static u64 get_distance_from_watchpoint(unsigned long addr, u64 val,
 		return 0;
 }
 
+static int watchpoint_report(struct perf_event *wp, unsigned long addr,
+			     struct pt_regs *regs)
+{
+	int step = is_default_overflow_handler(wp);
+	struct arch_hw_breakpoint *info = counter_arch_bp(wp);
+
+	info->trigger = addr;
+
+	/*
+	 * If we triggered a user watchpoint from a uaccess routine, then
+	 * handle the stepping ourselves since userspace really can't help
+	 * us with this.
+	 */
+	if (!user_mode(regs) && info->ctrl.privilege == AARCH64_BREAKPOINT_EL0)
+		step = 1;
+	else
+		perf_bp_event(wp, regs);
+
+	return step;
+}
+
 static int watchpoint_handler(unsigned long addr, unsigned int esr,
 			      struct pt_regs *regs)
 {
@@ -739,7 +760,6 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr,
 	u64 val;
 	struct perf_event *wp, **slots;
 	struct debug_info *debug_info;
-	struct arch_hw_breakpoint *info;
 	struct arch_hw_breakpoint_ctrl ctrl;
 
 	slots = this_cpu_ptr(wp_on_reg);
@@ -777,25 +797,13 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr,
 		if (dist != 0)
 			continue;
 
-		info = counter_arch_bp(wp);
-		info->trigger = addr;
-		perf_bp_event(wp, regs);
-
-		/* Do we need to handle the stepping? */
-		if (is_default_overflow_handler(wp))
-			step = 1;
+		step = watchpoint_report(wp, addr, regs);
 	}
-	if (min_dist > 0 && min_dist != -1) {
-		/* No exact match found. */
-		wp = slots[closest_match];
-		info = counter_arch_bp(wp);
-		info->trigger = addr;
-		perf_bp_event(wp, regs);
 
-		/* Do we need to handle the stepping? */
-		if (is_default_overflow_handler(wp))
-			step = 1;
-	}
+	/* No exact match found? */
+	if (min_dist > 0 && min_dist != -1)
+		step = watchpoint_report(slots[closest_match], addr, regs);
+
 	rcu_read_unlock();
 
 	if (!step)

arch/arm64/kernel/machine_kexec_file.c

@@ -219,8 +219,7 @@ static int prepare_elf_headers(void **addr, unsigned long *sz)
 					MEMBLOCK_NONE, &start, &end, NULL)
 		nr_ranges++;
 
-	cmem = kmalloc(sizeof(struct crash_mem) +
-			sizeof(struct crash_mem_range) * nr_ranges, GFP_KERNEL);
+	cmem = kmalloc(struct_size(cmem, ranges, nr_ranges), GFP_KERNEL);
 	if (!cmem)
 		return -ENOMEM;
 

arch/arm64/kernel/traps.c

@@ -813,6 +813,7 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
 		handler[reason], smp_processor_id(), esr,
 		esr_get_class_string(esr));
 
+	__show_regs(regs);
 	local_daif_mask();
 	panic("bad mode");
 }

arch/arm64/mm/init.c

@@ -404,11 +404,6 @@ void __init arm64_memblock_init(void)
 	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
 
 	dma_contiguous_reserve(arm64_dma32_phys_limit);
-
-#ifdef CONFIG_ARM64_4K_PAGES
-	hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT);
-#endif
-
 }
 
 void __init bootmem_init(void)
@@ -424,6 +419,16 @@ void __init bootmem_init(void)
 	min_low_pfn = min;
 
 	arm64_numa_init();
+
+	/*
+	 * must be done after arm64_numa_init() which calls numa_init() to
+	 * initialize node_online_map that gets used in hugetlb_cma_reserve()
+	 * while allocating required CMA size across online nodes.
+	 */
+#ifdef CONFIG_ARM64_4K_PAGES
+	hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT);
+#endif
+
 	/*
 	 * Sparsemem tries to allocate bootmem in memory_present(), so must be
 	 * done after the fixed reservations.

arch/arm64/mm/mmu.c

@@ -723,6 +723,7 @@ int kern_addr_valid(unsigned long addr)
 	pmd_t *pmdp, pmd;
 	pte_t *ptep, pte;
 
+	addr = arch_kasan_reset_tag(addr);
 	if ((((long)addr) >> VA_BITS) != -1UL)
 		return 0;