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

Pull arm64 fixes from Will Deacon:
 "Most of these are CC'd for stable, but there are a few fixing issues
  introduced during the recent merge window too.

  There's also a fix for the xgene PMU driver, but it seemed daft to
  send as a separate pull request, so I've included it here with the
  rest of the fixes.

   - Fix ACPI boot due to recent broken NUMA changes
   - Fix remote enabling of CPU features requiring PSTATE bit manipulation
   - Add address range check when emulating user cache maintenance
   - Fix LL/SC loops that allow compiler to introduce memory accesses
   - Fix recently added write_sysreg_s macro
   - Ensure MDCR_EL2 is initialised on qemu targets without a PMU
   - Avoid kaslr breakage due to MODVERSIONs and DYNAMIC_FTRACE
   - Correctly drive recent ld when building relocatable Image
   - Remove junk IS_ERR check from xgene PMU driver added during merge window
   - pr_cont fixes after core changes in the merge window"

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: remove pr_cont abuse from mem_init
  arm64: fix show_regs fallout from KERN_CONT changes
  arm64: kernel: force ET_DYN ELF type for CONFIG_RELOCATABLE=y
  arm64: suspend: Reconfigure PSTATE after resume from idle
  arm64: mm: Set PSTATE.PAN from the cpu_enable_pan() call
  arm64: cpufeature: Schedule enable() calls instead of calling them via IPI
  arm64: Cortex-A53 errata workaround: check for kernel addresses
  arm64: percpu: rewrite ll/sc loops in assembly
  arm64: swp emulation: bound LL/SC retries before rescheduling
  arm64: sysreg: Fix use of XZR in write_sysreg_s
  arm64: kaslr: keep modules close to the kernel when DYNAMIC_FTRACE=y
  arm64: kernel: Init MDCR_EL2 even in the absence of a PMU
  perf: xgene: Remove bogus IS_ERR() check
  arm64: kernel: numa: fix ACPI boot cpu numa node mapping
  arm64: kaslr: fix breakage with CONFIG_MODVERSIONS=y

8 files changed, 78 insertions, 34 deletions

diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index 42ffdb54e162..b0988bb1bf64 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -280,35 +280,43 @@ static void __init register_insn_emulation_sysctl(struct ctl_table *table)
 /*
  * Error-checking SWP macros implemented using ldxr{b}/stxr{b}
  */
-#define __user_swpX_asm(data, addr, res, temp, B)		\
+
+/* Arbitrary constant to ensure forward-progress of the LL/SC loop */
+#define __SWP_LL_SC_LOOPS	4
+
+#define __user_swpX_asm(data, addr, res, temp, temp2, B)	\
 	__asm__ __volatile__(					\
+	"	mov		%w3, %w7\n"			\
 	ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN,	\
 		    CONFIG_ARM64_PAN)				\
-	"0:	ldxr"B"		%w2, [%3]\n"			\
-	"1:	stxr"B"		%w0, %w1, [%3]\n"		\
+	"0:	ldxr"B"		%w2, [%4]\n"			\
+	"1:	stxr"B"		%w0, %w1, [%4]\n"		\
 	"	cbz		%w0, 2f\n"			\
-	"	mov		%w0, %w4\n"			\
+	"	sub		%w3, %w3, #1\n"			\
+	"	cbnz		%w3, 0b\n"			\
+	"	mov		%w0, %w5\n"			\
 	"	b		3f\n"				\
 	"2:\n"							\
 	"	mov		%w1, %w2\n"			\
 	"3:\n"							\
 	"	.pushsection	 .fixup,\"ax\"\n"		\
 	"	.align		2\n"				\
-	"4:	mov		%w0, %w5\n"			\
+	"4:	mov		%w0, %w6\n"			\
 	"	b		3b\n"				\
 	"	.popsection"					\
 	_ASM_EXTABLE(0b, 4b)					\
 	_ASM_EXTABLE(1b, 4b)					\
 	ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,	\
 		CONFIG_ARM64_PAN)				\
-	: "=&r" (res), "+r" (data), "=&r" (temp)		\
-	: "r" (addr), "i" (-EAGAIN), "i" (-EFAULT)		\
+	: "=&r" (res), "+r" (data), "=&r" (temp), "=&r" (temp2)	\
+	: "r" (addr), "i" (-EAGAIN), "i" (-EFAULT),		\
+	  "i" (__SWP_LL_SC_LOOPS)				\
 	: "memory")
 
-#define __user_swp_asm(data, addr, res, temp) \
-	__user_swpX_asm(data, addr, res, temp, "")
-#define __user_swpb_asm(data, addr, res, temp) \
-	__user_swpX_asm(data, addr, res, temp, "b")
+#define __user_swp_asm(data, addr, res, temp, temp2) \
+	__user_swpX_asm(data, addr, res, temp, temp2, "")
+#define __user_swpb_asm(data, addr, res, temp, temp2) \
+	__user_swpX_asm(data, addr, res, temp, temp2, "b")
 
 /*
  * Bit 22 of the instruction encoding distinguishes between
@@ -328,12 +336,12 @@ static int emulate_swpX(unsigned int address, unsigned int *data,
 	}
 
 	while (1) {
-		unsigned long temp;
+		unsigned long temp, temp2;
 
 		if (type == TYPE_SWPB)
-			__user_swpb_asm(*data, address, res, temp);
+			__user_swpb_asm(*data, address, res, temp, temp2);
 		else
-			__user_swp_asm(*data, address, res, temp);
+			__user_swp_asm(*data, address, res, temp, temp2);
 
 		if (likely(res != -EAGAIN) || signal_pending(current))
 			break;
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 0150394f4cab..b75e917aac46 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -39,10 +39,11 @@ has_mismatched_cache_line_size(const struct arm64_cpu_capabilities *entry,
 		(arm64_ftr_reg_ctrel0.sys_val & arm64_ftr_reg_ctrel0.strict_mask);
 }
 
-static void cpu_enable_trap_ctr_access(void *__unused)
+static int cpu_enable_trap_ctr_access(void *__unused)
 {
 	/* Clear SCTLR_EL1.UCT */
 	config_sctlr_el1(SCTLR_EL1_UCT, 0);
+	return 0;
 }
 
 #define MIDR_RANGE(model, min, max) \
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index d577f263cc4a..c02504ea304b 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -19,7 +19,9 @@
 #define pr_fmt(fmt) "CPU features: " fmt
 
 #include <linux/bsearch.h>
+#include <linux/cpumask.h>
 #include <linux/sort.h>
+#include <linux/stop_machine.h>
 #include <linux/types.h>
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
@@ -941,7 +943,13 @@ void __init enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
 {
 	for (; caps->matches; caps++)
 		if (caps->enable && cpus_have_cap(caps->capability))
-			on_each_cpu(caps->enable, NULL, true);
+			/*
+			 * Use stop_machine() as it schedules the work allowing
+			 * us to modify PSTATE, instead of on_each_cpu() which
+			 * uses an IPI, giving us a PSTATE that disappears when
+			 * we return.
+			 */
+			stop_machine(caps->enable, NULL, cpu_online_mask);
 }
 
 /*
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 427f6d3f084c..332e33193ccf 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -586,8 +586,9 @@ CPU_LE(	movk	x0, #0x30d0, lsl #16	)	// Clear EE and E0E on LE systems
 	b.lt	4f				// Skip if no PMU present
 	mrs	x0, pmcr_el0			// Disable debug access traps
 	ubfx	x0, x0, #11, #5			// to EL2 and allow access to
-	msr	mdcr_el2, x0			// all PMU counters from EL1
 4:
+	csel	x0, xzr, x0, lt			// all PMU counters from EL1
+	msr	mdcr_el2, x0			// (if they exist)
 
 	/* Stage-2 translation */
 	msr	vttbr_el2, xzr
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 27b2f1387df4..01753cd7d3f0 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -49,6 +49,7 @@
 #include <asm/alternative.h>
 #include <asm/compat.h>
 #include <asm/cacheflush.h>
+#include <asm/exec.h>
 #include <asm/fpsimd.h>
 #include <asm/mmu_context.h>
 #include <asm/processor.h>
@@ -186,10 +187,19 @@ void __show_regs(struct pt_regs *regs)
 	printk("pc : [<%016llx>] lr : [<%016llx>] pstate: %08llx\n",
 	       regs->pc, lr, regs->pstate);
 	printk("sp : %016llx\n", sp);
-	for (i = top_reg; i >= 0; i--) {
+
+	i = top_reg;
+
+	while (i >= 0) {
 		printk("x%-2d: %016llx ", i, regs->regs[i]);
-		if (i % 2 == 0)
-			printk("\n");
+		i--;
+
+		if (i % 2 == 0) {
+			pr_cont("x%-2d: %016llx ", i, regs->regs[i]);
+			i--;
+		}
+
+		pr_cont("\n");
 	}
 	printk("\n");
 }
@@ -301,7 +311,7 @@ static void tls_thread_switch(struct task_struct *next)
 }
 
 /* Restore the UAO state depending on next's addr_limit */
-static void uao_thread_switch(struct task_struct *next)
+void uao_thread_switch(struct task_struct *next)
 {
 	if (IS_ENABLED(CONFIG_ARM64_UAO)) {
 		if (task_thread_info(next)->addr_limit == KERNEL_DS)
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index d3f151cfd4a1..8507703dabe4 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -544,6 +544,7 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
 			return;
 		}
 		bootcpu_valid = true;
+		early_map_cpu_to_node(0, acpi_numa_get_nid(0, hwid));
 		return;
 	}
 
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index ad734142070d..bb0cd787a9d3 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -1,8 +1,11 @@
 #include <linux/ftrace.h>
 #include <linux/percpu.h>
 #include <linux/slab.h>
+#include <asm/alternative.h>
 #include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
 #include <asm/debug-monitors.h>
+#include <asm/exec.h>
 #include <asm/pgtable.h>
 #include <asm/memory.h>
 #include <asm/mmu_context.h>
@@ -50,6 +53,14 @@ void notrace __cpu_suspend_exit(void)
 	set_my_cpu_offset(per_cpu_offset(cpu));
 
 	/*
+	 * PSTATE was not saved over suspend/resume, re-enable any detected
+	 * features that might not have been set correctly.
+	 */
+	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,
+			CONFIG_ARM64_PAN));
+	uao_thread_switch(current);
+
+	/*
 	 * Restore HW breakpoint registers to sane values
 	 * before debug exceptions are possibly reenabled
 	 * through local_dbg_restore.
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 5ff020f8fb7f..c9986b3e0a96 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -428,24 +428,28 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 	force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0);
 }
 
-void cpu_enable_cache_maint_trap(void *__unused)
+int cpu_enable_cache_maint_trap(void *__unused)
 {
 	config_sctlr_el1(SCTLR_EL1_UCI, 0);
+	return 0;
 }
 
 #define __user_cache_maint(insn, address, res)			\
-	asm volatile (						\
-		"1:	" insn ", %1\n"				\
-		"	mov	%w0, #0\n"			\
-		"2:\n"						\
-		"	.pushsection .fixup,\"ax\"\n"		\
-		"	.align	2\n"				\
-		"3:	mov	%w0, %w2\n"			\
-		"	b	2b\n"				\
-		"	.popsection\n"				\
-		_ASM_EXTABLE(1b, 3b)				\
-		: "=r" (res)					\
-		: "r" (address), "i" (-EFAULT) )
+	if (untagged_addr(address) >= user_addr_max())		\
+		res = -EFAULT;					\
+	else							\
+		asm volatile (					\
+			"1:	" insn ", %1\n"			\
+			"	mov	%w0, #0\n"		\
+			"2:\n"					\
+			"	.pushsection .fixup,\"ax\"\n"	\
+			"	.align	2\n"			\
+			"3:	mov	%w0, %w2\n"		\
+			"	b	2b\n"			\
+			"	.popsection\n"			\
+			_ASM_EXTABLE(1b, 3b)			\
+			: "=r" (res)				\
+			: "r" (address), "i" (-EFAULT) )
 
 static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs)
 {