From 60c1b220d8bc6baeaf837cd60f94a331b25c26bc Mon Sep 17 00:00:00 2001
From: Atish Patra <atish.patra@wdc.com>
Date: Thu, 27 Jun 2019 12:52:58 -0700
Subject: cpu-topology: Move cpu topology code to common code.

Both RISC-V & ARM64 are using cpu-map device tree to describe
their cpu topology. It's better to move the relevant code to
a common place instead of duplicate code.

To: Will Deacon <will.deacon@arm.com>
To: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Atish Patra <atish.patra@wdc.com>
[Tested on QDF2400]
Tested-by: Jeffrey Hugo <jhugo@codeaurora.org>
[Tested on Juno and other embedded platforms.]
Tested-by: Sudeep Holla <sudeep.holla@arm.com>
Reviewed-by: Sudeep Holla <sudeep.holla@arm.com>
Acked-by: Will Deacon <will.deacon@arm.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Paul Walmsley <paul.walmsley@sifive.com>
---
 arch/arm64/include/asm/topology.h |  23 ---
 arch/arm64/kernel/topology.c      | 303 +-------------------------------------
 2 files changed, 4 insertions(+), 322 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index 0524f2438649..a4d945db95a2 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -4,29 +4,6 @@
 
 #include <linux/cpumask.h>
 
-struct cpu_topology {
-	int thread_id;
-	int core_id;
-	int package_id;
-	int llc_id;
-	cpumask_t thread_sibling;
-	cpumask_t core_sibling;
-	cpumask_t llc_sibling;
-};
-
-extern struct cpu_topology cpu_topology[NR_CPUS];
-
-#define topology_physical_package_id(cpu)	(cpu_topology[cpu].package_id)
-#define topology_core_id(cpu)		(cpu_topology[cpu].core_id)
-#define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
-#define topology_sibling_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
-#define topology_llc_cpumask(cpu)	(&cpu_topology[cpu].llc_sibling)
-
-void init_cpu_topology(void);
-void store_cpu_topology(unsigned int cpuid);
-void remove_cpu_topology(unsigned int cpuid);
-const struct cpumask *cpu_coregroup_mask(int cpu);
-
 #ifdef CONFIG_NUMA
 
 struct pci_bus;
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 0825c4a856e3..6b95c91e7d67 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -14,250 +14,13 @@
 #include <linux/acpi.h>
 #include <linux/arch_topology.h>
 #include <linux/cacheinfo.h>
-#include <linux/cpu.h>
-#include <linux/cpumask.h>
 #include <linux/init.h>
 #include <linux/percpu.h>
-#include <linux/node.h>
-#include <linux/nodemask.h>
-#include <linux/of.h>
-#include <linux/sched.h>
-#include <linux/sched/topology.h>
-#include <linux/slab.h>
-#include <linux/smp.h>
-#include <linux/string.h>
 
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/topology.h>
 
-static int __init get_cpu_for_node(struct device_node *node)
-{
-	struct device_node *cpu_node;
-	int cpu;
-
-	cpu_node = of_parse_phandle(node, "cpu", 0);
-	if (!cpu_node)
-		return -1;
-
-	cpu = of_cpu_node_to_id(cpu_node);
-	if (cpu >= 0)
-		topology_parse_cpu_capacity(cpu_node, cpu);
-	else
-		pr_crit("Unable to find CPU node for %pOF\n", cpu_node);
-
-	of_node_put(cpu_node);
-	return cpu;
-}
-
-static int __init parse_core(struct device_node *core, int package_id,
-			     int core_id)
-{
-	char name[10];
-	bool leaf = true;
-	int i = 0;
-	int cpu;
-	struct device_node *t;
-
-	do {
-		snprintf(name, sizeof(name), "thread%d", i);
-		t = of_get_child_by_name(core, name);
-		if (t) {
-			leaf = false;
-			cpu = get_cpu_for_node(t);
-			if (cpu >= 0) {
-				cpu_topology[cpu].package_id = package_id;
-				cpu_topology[cpu].core_id = core_id;
-				cpu_topology[cpu].thread_id = i;
-			} else {
-				pr_err("%pOF: Can't get CPU for thread\n",
-				       t);
-				of_node_put(t);
-				return -EINVAL;
-			}
-			of_node_put(t);
-		}
-		i++;
-	} while (t);
-
-	cpu = get_cpu_for_node(core);
-	if (cpu >= 0) {
-		if (!leaf) {
-			pr_err("%pOF: Core has both threads and CPU\n",
-			       core);
-			return -EINVAL;
-		}
-
-		cpu_topology[cpu].package_id = package_id;
-		cpu_topology[cpu].core_id = core_id;
-	} else if (leaf) {
-		pr_err("%pOF: Can't get CPU for leaf core\n", core);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int __init parse_cluster(struct device_node *cluster, int depth)
-{
-	char name[10];
-	bool leaf = true;
-	bool has_cores = false;
-	struct device_node *c;
-	static int package_id __initdata;
-	int core_id = 0;
-	int i, ret;
-
-	/*
-	 * First check for child clusters; we currently ignore any
-	 * information about the nesting of clusters and present the
-	 * scheduler with a flat list of them.
-	 */
-	i = 0;
-	do {
-		snprintf(name, sizeof(name), "cluster%d", i);
-		c = of_get_child_by_name(cluster, name);
-		if (c) {
-			leaf = false;
-			ret = parse_cluster(c, depth + 1);
-			of_node_put(c);
-			if (ret != 0)
-				return ret;
-		}
-		i++;
-	} while (c);
-
-	/* Now check for cores */
-	i = 0;
-	do {
-		snprintf(name, sizeof(name), "core%d", i);
-		c = of_get_child_by_name(cluster, name);
-		if (c) {
-			has_cores = true;
-
-			if (depth == 0) {
-				pr_err("%pOF: cpu-map children should be clusters\n",
-				       c);
-				of_node_put(c);
-				return -EINVAL;
-			}
-
-			if (leaf) {
-				ret = parse_core(c, package_id, core_id++);
-			} else {
-				pr_err("%pOF: Non-leaf cluster with core %s\n",
-				       cluster, name);
-				ret = -EINVAL;
-			}
-
-			of_node_put(c);
-			if (ret != 0)
-				return ret;
-		}
-		i++;
-	} while (c);
-
-	if (leaf && !has_cores)
-		pr_warn("%pOF: empty cluster\n", cluster);
-
-	if (leaf)
-		package_id++;
-
-	return 0;
-}
-
-static int __init parse_dt_topology(void)
-{
-	struct device_node *cn, *map;
-	int ret = 0;
-	int cpu;
-
-	cn = of_find_node_by_path("/cpus");
-	if (!cn) {
-		pr_err("No CPU information found in DT\n");
-		return 0;
-	}
-
-	/*
-	 * When topology is provided cpu-map is essentially a root
-	 * cluster with restricted subnodes.
-	 */
-	map = of_get_child_by_name(cn, "cpu-map");
-	if (!map)
-		goto out;
-
-	ret = parse_cluster(map, 0);
-	if (ret != 0)
-		goto out_map;
-
-	topology_normalize_cpu_scale();
-
-	/*
-	 * Check that all cores are in the topology; the SMP code will
-	 * only mark cores described in the DT as possible.
-	 */
-	for_each_possible_cpu(cpu)
-		if (cpu_topology[cpu].package_id == -1)
-			ret = -EINVAL;
-
-out_map:
-	of_node_put(map);
-out:
-	of_node_put(cn);
-	return ret;
-}
-
-/*
- * cpu topology table
- */
-struct cpu_topology cpu_topology[NR_CPUS];
-EXPORT_SYMBOL_GPL(cpu_topology);
-
-const struct cpumask *cpu_coregroup_mask(int cpu)
-{
-	const cpumask_t *core_mask = cpumask_of_node(cpu_to_node(cpu));
-
-	/* Find the smaller of NUMA, core or LLC siblings */
-	if (cpumask_subset(&cpu_topology[cpu].core_sibling, core_mask)) {
-		/* not numa in package, lets use the package siblings */
-		core_mask = &cpu_topology[cpu].core_sibling;
-	}
-	if (cpu_topology[cpu].llc_id != -1) {
-		if (cpumask_subset(&cpu_topology[cpu].llc_sibling, core_mask))
-			core_mask = &cpu_topology[cpu].llc_sibling;
-	}
-
-	return core_mask;
-}
-
-static void update_siblings_masks(unsigned int cpuid)
-{
-	struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
-	int cpu;
-
-	/* update core and thread sibling masks */
-	for_each_online_cpu(cpu) {
-		cpu_topo = &cpu_topology[cpu];
-
-		if (cpuid_topo->llc_id == cpu_topo->llc_id) {
-			cpumask_set_cpu(cpu, &cpuid_topo->llc_sibling);
-			cpumask_set_cpu(cpuid, &cpu_topo->llc_sibling);
-		}
-
-		if (cpuid_topo->package_id != cpu_topo->package_id)
-			continue;
-
-		cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
-		cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
-
-		if (cpuid_topo->core_id != cpu_topo->core_id)
-			continue;
-
-		cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling);
-		cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
-	}
-}
-
 void store_cpu_topology(unsigned int cpuid)
 {
 	struct cpu_topology *cpuid_topo = &cpu_topology[cpuid];
@@ -296,59 +59,19 @@ topology_populated:
 	update_siblings_masks(cpuid);
 }
 
-static void clear_cpu_topology(int cpu)
-{
-	struct cpu_topology *cpu_topo = &cpu_topology[cpu];
-
-	cpumask_clear(&cpu_topo->llc_sibling);
-	cpumask_set_cpu(cpu, &cpu_topo->llc_sibling);
-
-	cpumask_clear(&cpu_topo->core_sibling);
-	cpumask_set_cpu(cpu, &cpu_topo->core_sibling);
-	cpumask_clear(&cpu_topo->thread_sibling);
-	cpumask_set_cpu(cpu, &cpu_topo->thread_sibling);
-}
-
-static void __init reset_cpu_topology(void)
-{
-	unsigned int cpu;
-
-	for_each_possible_cpu(cpu) {
-		struct cpu_topology *cpu_topo = &cpu_topology[cpu];
-
-		cpu_topo->thread_id = -1;
-		cpu_topo->core_id = 0;
-		cpu_topo->package_id = -1;
-		cpu_topo->llc_id = -1;
-
-		clear_cpu_topology(cpu);
-	}
-}
-
-void remove_cpu_topology(unsigned int cpu)
-{
-	int sibling;
-
-	for_each_cpu(sibling, topology_core_cpumask(cpu))
-		cpumask_clear_cpu(cpu, topology_core_cpumask(sibling));
-	for_each_cpu(sibling, topology_sibling_cpumask(cpu))
-		cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling));
-	for_each_cpu(sibling, topology_llc_cpumask(cpu))
-		cpumask_clear_cpu(cpu, topology_llc_cpumask(sibling));
-
-	clear_cpu_topology(cpu);
-}
-
 #ifdef CONFIG_ACPI
 /*
  * Propagate the topology information of the processor_topology_node tree to the
  * cpu_topology array.
  */
-static int __init parse_acpi_topology(void)
+int __init parse_acpi_topology(void)
 {
 	bool is_threaded;
 	int cpu, topology_id;
 
+	if (acpi_disabled)
+		return 0;
+
 	is_threaded = read_cpuid_mpidr() & MPIDR_MT_BITMASK;
 
 	for_each_possible_cpu(cpu) {
@@ -384,24 +107,6 @@ static int __init parse_acpi_topology(void)
 
 	return 0;
 }
-
-#else
-static inline int __init parse_acpi_topology(void)
-{
-	return -EINVAL;
-}
 #endif
 
-void __init init_cpu_topology(void)
-{
-	reset_cpu_topology();
 
-	/*
-	 * Discard anything that was parsed if we hit an error so we
-	 * don't use partial information.
-	 */
-	if (!acpi_disabled && parse_acpi_topology())
-		reset_cpu_topology();
-	else if (of_have_populated_dt() && parse_dt_topology())
-		reset_cpu_topology();
-}
-- 
cgit v1.2.3


From ca74b316df96d7c40ee3e8301065607c11c60c27 Mon Sep 17 00:00:00 2001
From: Atish Patra <atish.patra@wdc.com>
Date: Thu, 27 Jun 2019 12:52:59 -0700
Subject: arm: Use common cpu_topology structure and functions.

Currently, ARM32 and ARM64 uses different data structures to represent
their cpu topologies. Since, we are moving the ARM64 topology to common
code to be used by other architectures, we can reuse that for ARM32 as
well.

Take this opprtunity to remove the redundant functions from ARM32 and
reuse the common code instead.

To: Russell King <linux@armlinux.org.uk>
Signed-off-by: Atish Patra <atish.patra@wdc.com>
Tested-by: Sudeep Holla <sudeep.holla@arm.com> (on TC2)
Reviewed-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Paul Walmsley <paul.walmsley@sifive.com>
---
 arch/arm/include/asm/topology.h | 20 --------------
 arch/arm/kernel/topology.c      | 60 +++++------------------------------------
 drivers/base/arch_topology.c    |  4 ++-
 include/linux/arch_topology.h   |  6 ++---
 4 files changed, 11 insertions(+), 79 deletions(-)

(limited to 'arch')

diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index 2a786f54d8b8..8a0fae94d45e 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -5,26 +5,6 @@
 #ifdef CONFIG_ARM_CPU_TOPOLOGY
 
 #include <linux/cpumask.h>
-
-struct cputopo_arm {
-	int thread_id;
-	int core_id;
-	int socket_id;
-	cpumask_t thread_sibling;
-	cpumask_t core_sibling;
-};
-
-extern struct cputopo_arm cpu_topology[NR_CPUS];
-
-#define topology_physical_package_id(cpu)	(cpu_topology[cpu].socket_id)
-#define topology_core_id(cpu)		(cpu_topology[cpu].core_id)
-#define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
-#define topology_sibling_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
-
-void init_cpu_topology(void);
-void store_cpu_topology(unsigned int cpuid);
-const struct cpumask *cpu_coregroup_mask(int cpu);
-
 #include <linux/arch_topology.h>
 
 /* Replace task scheduler's default frequency-invariant accounting */
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index d17cb1e6d679..5b9faba03afb 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -177,17 +177,6 @@ static inline void parse_dt_topology(void) {}
 static inline void update_cpu_capacity(unsigned int cpuid) {}
 #endif
 
- /*
- * cpu topology table
- */
-struct cputopo_arm cpu_topology[NR_CPUS];
-EXPORT_SYMBOL_GPL(cpu_topology);
-
-const struct cpumask *cpu_coregroup_mask(int cpu)
-{
-	return &cpu_topology[cpu].core_sibling;
-}
-
 /*
  * The current assumption is that we can power gate each core independently.
  * This will be superseded by DT binding once available.
@@ -197,32 +186,6 @@ const struct cpumask *cpu_corepower_mask(int cpu)
 	return &cpu_topology[cpu].thread_sibling;
 }
 
-static void update_siblings_masks(unsigned int cpuid)
-{
-	struct cputopo_arm *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
-	int cpu;
-
-	/* update core and thread sibling masks */
-	for_each_possible_cpu(cpu) {
-		cpu_topo = &cpu_topology[cpu];
-
-		if (cpuid_topo->socket_id != cpu_topo->socket_id)
-			continue;
-
-		cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
-		if (cpu != cpuid)
-			cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
-
-		if (cpuid_topo->core_id != cpu_topo->core_id)
-			continue;
-
-		cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling);
-		if (cpu != cpuid)
-			cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
-	}
-	smp_wmb();
-}
-
 /*
  * store_cpu_topology is called at boot when only one cpu is running
  * and with the mutex cpu_hotplug.lock locked, when several cpus have booted,
@@ -230,7 +193,7 @@ static void update_siblings_masks(unsigned int cpuid)
  */
 void store_cpu_topology(unsigned int cpuid)
 {
-	struct cputopo_arm *cpuid_topo = &cpu_topology[cpuid];
+	struct cpu_topology *cpuid_topo = &cpu_topology[cpuid];
 	unsigned int mpidr;
 
 	/* If the cpu topology has been already set, just return */
@@ -250,12 +213,12 @@ void store_cpu_topology(unsigned int cpuid)
 			/* core performance interdependency */
 			cpuid_topo->thread_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
 			cpuid_topo->core_id = MPIDR_AFFINITY_LEVEL(mpidr, 1);
-			cpuid_topo->socket_id = MPIDR_AFFINITY_LEVEL(mpidr, 2);
+			cpuid_topo->package_id = MPIDR_AFFINITY_LEVEL(mpidr, 2);
 		} else {
 			/* largely independent cores */
 			cpuid_topo->thread_id = -1;
 			cpuid_topo->core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
-			cpuid_topo->socket_id = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+			cpuid_topo->package_id = MPIDR_AFFINITY_LEVEL(mpidr, 1);
 		}
 	} else {
 		/*
@@ -265,7 +228,7 @@ void store_cpu_topology(unsigned int cpuid)
 		 */
 		cpuid_topo->thread_id = -1;
 		cpuid_topo->core_id = 0;
-		cpuid_topo->socket_id = -1;
+		cpuid_topo->package_id = -1;
 	}
 
 	update_siblings_masks(cpuid);
@@ -275,7 +238,7 @@ void store_cpu_topology(unsigned int cpuid)
 	pr_info("CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n",
 		cpuid, cpu_topology[cpuid].thread_id,
 		cpu_topology[cpuid].core_id,
-		cpu_topology[cpuid].socket_id, mpidr);
+		cpu_topology[cpuid].package_id, mpidr);
 }
 
 static inline int cpu_corepower_flags(void)
@@ -298,18 +261,7 @@ static struct sched_domain_topology_level arm_topology[] = {
  */
 void __init init_cpu_topology(void)
 {
-	unsigned int cpu;
-
-	/* init core mask and capacity */
-	for_each_possible_cpu(cpu) {
-		struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]);
-
-		cpu_topo->thread_id = -1;
-		cpu_topo->core_id =  -1;
-		cpu_topo->socket_id = -1;
-		cpumask_clear(&cpu_topo->core_sibling);
-		cpumask_clear(&cpu_topo->thread_sibling);
-	}
+	reset_cpu_topology();
 	smp_wmb();
 
 	parse_dt_topology();
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 5dc0e1ddd080..b54d241a2ff5 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -423,6 +423,7 @@ out:
 	of_node_put(cn);
 	return ret;
 }
+#endif
 
 /*
  * cpu topology table
@@ -488,7 +489,7 @@ static void clear_cpu_topology(int cpu)
 	cpumask_set_cpu(cpu, &cpu_topo->thread_sibling);
 }
 
-static void __init reset_cpu_topology(void)
+void __init reset_cpu_topology(void)
 {
 	unsigned int cpu;
 
@@ -523,6 +524,7 @@ __weak int __init parse_acpi_topology(void)
 	return 0;
 }
 
+#if defined(CONFIG_ARM64) || defined(CONFIG_RISCV)
 void __init init_cpu_topology(void)
 {
 	reset_cpu_topology();
diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index ede0ce4623b4..42f2b5126094 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -54,11 +54,9 @@ extern struct cpu_topology cpu_topology[NR_CPUS];
 void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);
 const struct cpumask *cpu_coregroup_mask(int cpu);
-#endif
-
-#if defined(CONFIG_ARM64) || defined(CONFIG_RISCV)
 void update_siblings_masks(unsigned int cpu);
-#endif
 void remove_cpu_topology(unsigned int cpuid);
+void reset_cpu_topology(void);
+#endif
 
 #endif /* _LINUX_ARCH_TOPOLOGY_H_ */
-- 
cgit v1.2.3


From 03f11f03dbfe37c0bff2768b8f2e277a29ac62b9 Mon Sep 17 00:00:00 2001
From: Atish Patra <atish.patra@wdc.com>
Date: Thu, 27 Jun 2019 12:53:00 -0700
Subject: RISC-V: Parse cpu topology during boot.

Currently, there are no topology defined for RISC-V.
Parse the cpu-map node from device tree and setup the
cpu topology.

CPU topology after applying the patch.
$cat /sys/devices/system/cpu/cpu2/topology/core_siblings_list
0-3
$cat /sys/devices/system/cpu/cpu3/topology/core_siblings_list
0-3
$cat /sys/devices/system/cpu/cpu3/topology/physical_package_id
0
$cat /sys/devices/system/cpu/cpu3/topology/core_id
3

Signed-off-by: Atish Patra <atish.patra@wdc.com>
Acked-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Paul Walmsley <paul.walmsley@sifive.com>
---
 arch/riscv/Kconfig          | 1 +
 arch/riscv/kernel/smpboot.c | 3 +++
 2 files changed, 4 insertions(+)

(limited to 'arch')

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 59a4727ecd6c..86ee362a1375 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -48,6 +48,7 @@ config RISCV
 	select PCI_MSI if PCI
 	select RISCV_TIMER
 	select GENERIC_IRQ_MULTI_HANDLER
+	select GENERIC_ARCH_TOPOLOGY if SMP
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_MMIOWB
 	select HAVE_EBPF_JIT if 64BIT
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index 7462a44304fe..18ae6da5115e 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -8,6 +8,7 @@
  * Copyright (C) 2017 SiFive
  */
 
+#include <linux/arch_topology.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -35,6 +36,7 @@ static DECLARE_COMPLETION(cpu_running);
 
 void __init smp_prepare_boot_cpu(void)
 {
+	init_cpu_topology();
 }
 
 void __init smp_prepare_cpus(unsigned int max_cpus)
@@ -138,6 +140,7 @@ asmlinkage void __init smp_callin(void)
 
 	trap_init();
 	notify_cpu_starting(smp_processor_id());
+	update_siblings_masks(smp_processor_id());
 	set_cpu_online(smp_processor_id(), 1);
 	/*
 	 * Remote TLB flushes are ignored while the CPU is offline, so emit
-- 
cgit v1.2.3


From ca786b8db751c0dd980fccf2d65acb77a296f629 Mon Sep 17 00:00:00 2001
From: Shaokun Zhang <zhangshaokun@hisilicon.com>
Date: Tue, 2 Jul 2019 15:35:53 +0800
Subject: arm64: perf: Remove unused macro

ARMV8_EVENT_ATTR_RESOLVE became unused after commit <4b1a9e6934ec>
("arm64/perf: Filter common events based on PMCEIDn_EL0").

Remove it.

Cc: Will Deacon <will@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Shaokun Zhang <zhangshaokun@hisilicon.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/perf_event.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'arch')

diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 96e90e270042..2d3bdebdf6df 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -157,7 +157,6 @@ armv8pmu_events_sysfs_show(struct device *dev,
 	return sprintf(page, "event=0x%03llx\n", pmu_attr->id);
 }
 
-#define ARMV8_EVENT_ATTR_RESOLVE(m) #m
 #define ARMV8_EVENT_ATTR(name, config) \
 	PMU_EVENT_ATTR(name, armv8_event_attr_##name, \
 		       config, armv8pmu_events_sysfs_show)
-- 
cgit v1.2.3


From 2b835e24b5c6f9c633ff51973581ee7ca7b3e8ec Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 23 Jul 2019 19:58:38 +0200
Subject: arm64: untag user pointers in access_ok and __uaccess_mask_ptr

This patch is a part of a series that extends kernel ABI to allow to pass
tagged user pointers (with the top byte set to something else other than
0x00) as syscall arguments.

copy_from_user (and a few other similar functions) are used to copy data
from user memory into the kernel memory or vice versa. Since a user can
provided a tagged pointer to one of the syscalls that use copy_from_user,
we need to correctly handle such pointers.

Do this by untagging user pointers in access_ok and in __uaccess_mask_ptr,
before performing access validity checks.

Note, that this patch only temporarily untags the pointers to perform the
checks, but then passes them as is into the kernel internals.

Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
[will: Add __force to casting in untagged_addr() to kill sparse warning]
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/memory.h  |  2 +-
 arch/arm64/include/asm/uaccess.h | 10 +++++++---
 2 files changed, 8 insertions(+), 4 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index fb04f10a78ab..46c4c08a80a9 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -201,7 +201,7 @@ extern u64			vabits_user;
  * pass on to access_ok(), for instance.
  */
 #define untagged_addr(addr)	\
-	((__typeof__(addr))sign_extend64((u64)(addr), 55))
+	((__typeof__(addr))sign_extend64((__force u64)(addr), 55))
 
 #ifdef CONFIG_KASAN_SW_TAGS
 #define __tag_shifted(tag)	((u64)(tag) << 56)
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 5a1c32260c1f..a138e3b4f717 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -62,6 +62,8 @@ static inline unsigned long __range_ok(const void __user *addr, unsigned long si
 {
 	unsigned long ret, limit = current_thread_info()->addr_limit;
 
+	addr = untagged_addr(addr);
+
 	__chk_user_ptr(addr);
 	asm volatile(
 	// A + B <= C + 1 for all A,B,C, in four easy steps:
@@ -215,7 +217,8 @@ static inline void uaccess_enable_not_uao(void)
 
 /*
  * Sanitise a uaccess pointer such that it becomes NULL if above the
- * current addr_limit.
+ * current addr_limit. In case the pointer is tagged (has the top byte set),
+ * untag the pointer before checking.
  */
 #define uaccess_mask_ptr(ptr) (__typeof__(ptr))__uaccess_mask_ptr(ptr)
 static inline void __user *__uaccess_mask_ptr(const void __user *ptr)
@@ -223,10 +226,11 @@ static inline void __user *__uaccess_mask_ptr(const void __user *ptr)
 	void __user *safe_ptr;
 
 	asm volatile(
-	"	bics	xzr, %1, %2\n"
+	"	bics	xzr, %3, %2\n"
 	"	csel	%0, %1, xzr, eq\n"
 	: "=&r" (safe_ptr)
-	: "r" (ptr), "r" (current_thread_info()->addr_limit)
+	: "r" (ptr), "r" (current_thread_info()->addr_limit),
+	  "r" (untagged_addr(ptr))
 	: "cc");
 
 	csdb();
-- 
cgit v1.2.3


From 63f0c60379650d82250f22e4cf4137ef3dc4f43d Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Tue, 23 Jul 2019 19:58:39 +0200
Subject: arm64: Introduce prctl() options to control the tagged user addresses
 ABI

It is not desirable to relax the ABI to allow tagged user addresses into
the kernel indiscriminately. This patch introduces a prctl() interface
for enabling or disabling the tagged ABI with a global sysctl control
for preventing applications from enabling the relaxed ABI (meant for
testing user-space prctl() return error checking without reconfiguring
the kernel). The ABI properties are inherited by threads of the same
application and fork()'ed children but cleared on execve(). A Kconfig
option allows the overall disabling of the relaxed ABI.

The PR_SET_TAGGED_ADDR_CTRL will be expanded in the future to handle
MTE-specific settings like imprecise vs precise exceptions.

Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/Kconfig                   |  9 +++++
 arch/arm64/include/asm/processor.h   |  8 ++++
 arch/arm64/include/asm/thread_info.h |  1 +
 arch/arm64/include/asm/uaccess.h     |  4 +-
 arch/arm64/kernel/process.c          | 73 ++++++++++++++++++++++++++++++++++++
 include/uapi/linux/prctl.h           |  5 +++
 kernel/sys.c                         | 12 ++++++
 7 files changed, 111 insertions(+), 1 deletion(-)

(limited to 'arch')

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 3adcec05b1f6..5d254178b9ca 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1110,6 +1110,15 @@ config ARM64_SW_TTBR0_PAN
 	  zeroed area and reserved ASID. The user access routines
 	  restore the valid TTBR0_EL1 temporarily.
 
+config ARM64_TAGGED_ADDR_ABI
+	bool "Enable the tagged user addresses syscall ABI"
+	default y
+	help
+	  When this option is enabled, user applications can opt in to a
+	  relaxed ABI via prctl() allowing tagged addresses to be passed
+	  to system calls as pointer arguments. For details, see
+	  Documentation/arm64/tagged-address-abi.txt.
+
 menuconfig COMPAT
 	bool "Kernel support for 32-bit EL0"
 	depends on ARM64_4K_PAGES || EXPERT
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 844e2964b0f5..28eed40ffc12 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -306,6 +306,14 @@ extern void __init minsigstksz_setup(void);
 /* PR_PAC_RESET_KEYS prctl */
 #define PAC_RESET_KEYS(tsk, arg)	ptrauth_prctl_reset_keys(tsk, arg)
 
+#ifdef CONFIG_ARM64_TAGGED_ADDR_ABI
+/* PR_{SET,GET}_TAGGED_ADDR_CTRL prctl */
+long set_tagged_addr_ctrl(unsigned long arg);
+long get_tagged_addr_ctrl(void);
+#define SET_TAGGED_ADDR_CTRL(arg)	set_tagged_addr_ctrl(arg)
+#define GET_TAGGED_ADDR_CTRL()		get_tagged_addr_ctrl()
+#endif
+
 /*
  * For CONFIG_GCC_PLUGIN_STACKLEAK
  *
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 180b34ec5965..012238d8e58d 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -90,6 +90,7 @@ void arch_release_task_struct(struct task_struct *tsk);
 #define TIF_SVE			23	/* Scalable Vector Extension in use */
 #define TIF_SVE_VL_INHERIT	24	/* Inherit sve_vl_onexec across exec */
 #define TIF_SSBD		25	/* Wants SSB mitigation */
+#define TIF_TAGGED_ADDR		26	/* Allow tagged user addresses */
 
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index a138e3b4f717..097d6bfac0b7 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -62,7 +62,9 @@ static inline unsigned long __range_ok(const void __user *addr, unsigned long si
 {
 	unsigned long ret, limit = current_thread_info()->addr_limit;
 
-	addr = untagged_addr(addr);
+	if (IS_ENABLED(CONFIG_ARM64_TAGGED_ADDR_ABI) &&
+	    test_thread_flag(TIF_TAGGED_ADDR))
+		addr = untagged_addr(addr);
 
 	__chk_user_ptr(addr);
 	asm volatile(
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index f674f28df663..76b7c55026aa 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -19,6 +19,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
+#include <linux/sysctl.h>
 #include <linux/unistd.h>
 #include <linux/user.h>
 #include <linux/delay.h>
@@ -38,6 +39,7 @@
 #include <trace/events/power.h>
 #include <linux/percpu.h>
 #include <linux/thread_info.h>
+#include <linux/prctl.h>
 
 #include <asm/alternative.h>
 #include <asm/arch_gicv3.h>
@@ -307,11 +309,18 @@ static void tls_thread_flush(void)
 	}
 }
 
+static void flush_tagged_addr_state(void)
+{
+	if (IS_ENABLED(CONFIG_ARM64_TAGGED_ADDR_ABI))
+		clear_thread_flag(TIF_TAGGED_ADDR);
+}
+
 void flush_thread(void)
 {
 	fpsimd_flush_thread();
 	tls_thread_flush();
 	flush_ptrace_hw_breakpoint(current);
+	flush_tagged_addr_state();
 }
 
 void release_thread(struct task_struct *dead_task)
@@ -565,3 +574,67 @@ void arch_setup_new_exec(void)
 
 	ptrauth_thread_init_user(current);
 }
+
+#ifdef CONFIG_ARM64_TAGGED_ADDR_ABI
+/*
+ * Control the relaxed ABI allowing tagged user addresses into the kernel.
+ */
+static unsigned int tagged_addr_prctl_allowed = 1;
+
+long set_tagged_addr_ctrl(unsigned long arg)
+{
+	if (!tagged_addr_prctl_allowed)
+		return -EINVAL;
+	if (is_compat_task())
+		return -EINVAL;
+	if (arg & ~PR_TAGGED_ADDR_ENABLE)
+		return -EINVAL;
+
+	update_thread_flag(TIF_TAGGED_ADDR, arg & PR_TAGGED_ADDR_ENABLE);
+
+	return 0;
+}
+
+long get_tagged_addr_ctrl(void)
+{
+	if (!tagged_addr_prctl_allowed)
+		return -EINVAL;
+	if (is_compat_task())
+		return -EINVAL;
+
+	if (test_thread_flag(TIF_TAGGED_ADDR))
+		return PR_TAGGED_ADDR_ENABLE;
+
+	return 0;
+}
+
+/*
+ * Global sysctl to disable the tagged user addresses support. This control
+ * only prevents the tagged address ABI enabling via prctl() and does not
+ * disable it for tasks that already opted in to the relaxed ABI.
+ */
+static int zero;
+static int one = 1;
+
+static struct ctl_table tagged_addr_sysctl_table[] = {
+	{
+		.procname	= "tagged_addr",
+		.mode		= 0644,
+		.data		= &tagged_addr_prctl_allowed,
+		.maxlen		= sizeof(int),
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+	{ }
+};
+
+static int __init tagged_addr_init(void)
+{
+	if (!register_sysctl("abi", tagged_addr_sysctl_table))
+		return -EINVAL;
+	return 0;
+}
+
+core_initcall(tagged_addr_init);
+#endif	/* CONFIG_ARM64_TAGGED_ADDR_ABI */
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 094bb03b9cc2..2e927b3e9d6c 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -229,4 +229,9 @@ struct prctl_mm_map {
 # define PR_PAC_APDBKEY			(1UL << 3)
 # define PR_PAC_APGAKEY			(1UL << 4)
 
+/* Tagged user address controls for arm64 */
+#define PR_SET_TAGGED_ADDR_CTRL		55
+#define PR_GET_TAGGED_ADDR_CTRL		56
+# define PR_TAGGED_ADDR_ENABLE		(1UL << 0)
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/kernel/sys.c b/kernel/sys.c
index 2969304c29fe..c6c4d5358bd3 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -124,6 +124,12 @@
 #ifndef PAC_RESET_KEYS
 # define PAC_RESET_KEYS(a, b)	(-EINVAL)
 #endif
+#ifndef SET_TAGGED_ADDR_CTRL
+# define SET_TAGGED_ADDR_CTRL(a)	(-EINVAL)
+#endif
+#ifndef GET_TAGGED_ADDR_CTRL
+# define GET_TAGGED_ADDR_CTRL()		(-EINVAL)
+#endif
 
 /*
  * this is where the system-wide overflow UID and GID are defined, for
@@ -2492,6 +2498,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			return -EINVAL;
 		error = PAC_RESET_KEYS(me, arg2);
 		break;
+	case PR_SET_TAGGED_ADDR_CTRL:
+		error = SET_TAGGED_ADDR_CTRL(arg2);
+		break;
+	case PR_GET_TAGGED_ADDR_CTRL:
+		error = GET_TAGGED_ADDR_CTRL();
+		break;
 	default:
 		error = -EINVAL;
 		break;
-- 
cgit v1.2.3


From 45880f7b7b19e043ce0aaa4cb7d05369425c82fa Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@linaro.org>
Date: Tue, 6 Aug 2019 18:00:13 +0800
Subject: error-injection: Consolidate override function definition

The function override_function_with_return() is defined separately for
each architecture and every architecture's definition is almost same
with each other.  E.g. x86 and powerpc both define function in its own
asm/error-injection.h header and override_function_with_return() has
the same definition, the only difference is that x86 defines an extra
function just_return_func() but it is specific for x86 and is only used
by x86's override_function_with_return(), so don't need to export this
function.

This patch consolidates override_function_with_return() definition into
asm-generic/error-injection.h header, thus all architectures can use the
common definition.  As result, the architecture specific headers are
removed; the include/linux/error-injection.h header also changes to
include asm-generic/error-injection.h header rather than architecture
header, furthermore, it includes linux/compiler.h for successful
compilation.

Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Leo Yan <leo.yan@linaro.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/powerpc/include/asm/error-injection.h | 13 -------------
 arch/x86/include/asm/error-injection.h     | 13 -------------
 include/asm-generic/error-injection.h      |  6 ++++++
 include/linux/error-injection.h            |  6 +++---
 4 files changed, 9 insertions(+), 29 deletions(-)
 delete mode 100644 arch/powerpc/include/asm/error-injection.h
 delete mode 100644 arch/x86/include/asm/error-injection.h

(limited to 'arch')

diff --git a/arch/powerpc/include/asm/error-injection.h b/arch/powerpc/include/asm/error-injection.h
deleted file mode 100644
index 62fd24739852..000000000000
--- a/arch/powerpc/include/asm/error-injection.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0+ */
-
-#ifndef _ASM_ERROR_INJECTION_H
-#define _ASM_ERROR_INJECTION_H
-
-#include <linux/compiler.h>
-#include <linux/linkage.h>
-#include <asm/ptrace.h>
-#include <asm-generic/error-injection.h>
-
-void override_function_with_return(struct pt_regs *regs);
-
-#endif /* _ASM_ERROR_INJECTION_H */
diff --git a/arch/x86/include/asm/error-injection.h b/arch/x86/include/asm/error-injection.h
deleted file mode 100644
index 47b7a1296245..000000000000
--- a/arch/x86/include/asm/error-injection.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_ERROR_INJECTION_H
-#define _ASM_ERROR_INJECTION_H
-
-#include <linux/compiler.h>
-#include <linux/linkage.h>
-#include <asm/ptrace.h>
-#include <asm-generic/error-injection.h>
-
-asmlinkage void just_return_func(void);
-void override_function_with_return(struct pt_regs *regs);
-
-#endif /* _ASM_ERROR_INJECTION_H */
diff --git a/include/asm-generic/error-injection.h b/include/asm-generic/error-injection.h
index 95a159a4137f..80ca61058dd2 100644
--- a/include/asm-generic/error-injection.h
+++ b/include/asm-generic/error-injection.h
@@ -16,6 +16,8 @@ struct error_injection_entry {
 	int		etype;
 };
 
+struct pt_regs;
+
 #ifdef CONFIG_FUNCTION_ERROR_INJECTION
 /*
  * Whitelist ganerating macro. Specify functions which can be
@@ -28,8 +30,12 @@ static struct error_injection_entry __used				\
 		.addr = (unsigned long)fname,				\
 		.etype = EI_ETYPE_##_etype,				\
 	};
+
+void override_function_with_return(struct pt_regs *regs);
 #else
 #define ALLOW_ERROR_INJECTION(fname, _etype)
+
+static inline void override_function_with_return(struct pt_regs *regs) { }
 #endif
 #endif
 
diff --git a/include/linux/error-injection.h b/include/linux/error-injection.h
index 280c61ecbf20..635a95caf29f 100644
--- a/include/linux/error-injection.h
+++ b/include/linux/error-injection.h
@@ -2,16 +2,16 @@
 #ifndef _LINUX_ERROR_INJECTION_H
 #define _LINUX_ERROR_INJECTION_H
 
-#ifdef CONFIG_FUNCTION_ERROR_INJECTION
+#include <linux/compiler.h>
+#include <asm-generic/error-injection.h>
 
-#include <asm/error-injection.h>
+#ifdef CONFIG_FUNCTION_ERROR_INJECTION
 
 extern bool within_error_injection_list(unsigned long addr);
 extern int get_injectable_error_type(unsigned long addr);
 
 #else /* !CONFIG_FUNCTION_ERROR_INJECTION */
 
-#include <asm-generic/error-injection.h>
 static inline bool within_error_injection_list(unsigned long addr)
 {
 	return false;
-- 
cgit v1.2.3


From 42d038c4fb00f1ec1a4c4616784da4561385b628 Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@linaro.org>
Date: Tue, 6 Aug 2019 18:00:14 +0800
Subject: arm64: Add support for function error injection

Inspired by the commit 7cd01b08d35f ("powerpc: Add support for function
error injection"), this patch supports function error injection for
Arm64.

This patch mainly support two functions: one is regs_set_return_value()
which is used to overwrite the return value; the another function is
override_function_with_return() which is to override the probed
function returning and jump to its caller.

Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Leo Yan <leo.yan@linaro.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/Kconfig              |  1 +
 arch/arm64/include/asm/ptrace.h |  5 +++++
 arch/arm64/lib/Makefile         |  2 ++
 arch/arm64/lib/error-inject.c   | 18 ++++++++++++++++++
 4 files changed, 26 insertions(+)
 create mode 100644 arch/arm64/lib/error-inject.c

(limited to 'arch')

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 3adcec05b1f6..b15803afb2a0 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -148,6 +148,7 @@ config ARM64
 	select HAVE_FAST_GUP
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_TRACER
+	select HAVE_FUNCTION_ERROR_INJECTION
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_GCC_PLUGINS
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 1dcf63a9ac1f..fbebb411ae20 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -301,6 +301,11 @@ static inline unsigned long regs_return_value(struct pt_regs *regs)
 	return regs->regs[0];
 }
 
+static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
+{
+	regs->regs[0] = rc;
+}
+
 /**
  * regs_get_kernel_argument() - get Nth function argument in kernel
  * @regs:	pt_regs of that context
diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index 33c2a4abda04..f182ccb0438e 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -33,3 +33,5 @@ UBSAN_SANITIZE_atomic_ll_sc.o	:= n
 lib-$(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) += uaccess_flushcache.o
 
 obj-$(CONFIG_CRC32) += crc32.o
+
+obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
diff --git a/arch/arm64/lib/error-inject.c b/arch/arm64/lib/error-inject.c
new file mode 100644
index 000000000000..ed15021da3ed
--- /dev/null
+++ b/arch/arm64/lib/error-inject.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/error-injection.h>
+#include <linux/kprobes.h>
+
+void override_function_with_return(struct pt_regs *regs)
+{
+	/*
+	 * 'regs' represents the state on entry of a predefined function in
+	 * the kernel/module and which is captured on a kprobe.
+	 *
+	 * When kprobe returns back from exception it will override the end
+	 * of probed function and directly return to the predefined
+	 * function's caller.
+	 */
+	instruction_pointer_set(regs, procedure_link_pointer(regs));
+}
+NOKPROBE_SYMBOL(override_function_with_return);
-- 
cgit v1.2.3


From 9cb1c5ddd2c432834dd4f40c0170d6b639e8e5c3 Mon Sep 17 00:00:00 2001
From: Steve Capper <steve.capper@arm.com>
Date: Wed, 7 Aug 2019 16:55:13 +0100
Subject: arm64: mm: Remove bit-masking optimisations for PAGE_OFFSET and
 VMEMMAP_START

Currently there are assumptions about the alignment of VMEMMAP_START
and PAGE_OFFSET that won't be valid after this series is applied.

These assumptions are in the form of bitwise operators being used
instead of addition and subtraction when calculating addresses.

This patch replaces these bitwise operators with addition/subtraction.

Signed-off-by: Steve Capper <steve.capper@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/memory.h | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index fb04f10a78ab..98fda92a2612 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -299,21 +299,20 @@ static inline void *phys_to_virt(phys_addr_t x)
 #define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
 #define _virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
 #else
-#define __virt_to_pgoff(kaddr)	(((u64)(kaddr) & ~PAGE_OFFSET) / PAGE_SIZE * sizeof(struct page))
-#define __page_to_voff(kaddr)	(((u64)(kaddr) & ~VMEMMAP_START) * PAGE_SIZE / sizeof(struct page))
+#define __virt_to_pgoff(kaddr)	(((u64)(kaddr) - PAGE_OFFSET) / PAGE_SIZE * sizeof(struct page))
+#define __page_to_voff(kaddr)	(((u64)(kaddr) - VMEMMAP_START) * PAGE_SIZE / sizeof(struct page))
 
 #define page_to_virt(page)	({					\
 	unsigned long __addr =						\
-		((__page_to_voff(page)) | PAGE_OFFSET);			\
+		((__page_to_voff(page)) + PAGE_OFFSET);			\
 	const void *__addr_tag =					\
 		__tag_set((void *)__addr, page_kasan_tag(page));	\
 	((void *)__addr_tag);						\
 })
 
-#define virt_to_page(vaddr)	((struct page *)((__virt_to_pgoff(vaddr)) | VMEMMAP_START))
+#define virt_to_page(vaddr)	((struct page *)((__virt_to_pgoff(vaddr)) + VMEMMAP_START))
 
-#define _virt_addr_valid(kaddr)	pfn_valid((((u64)(kaddr) & ~PAGE_OFFSET) \
-					   + PHYS_OFFSET) >> PAGE_SHIFT)
+#define _virt_addr_valid(kaddr)	pfn_valid(__virt_to_phys((u64)(kaddr)) >> PAGE_SHIFT)
 #endif
 #endif
 
-- 
cgit v1.2.3


From 14c127c957c1c6070647c171e72f06e0db275ebf Mon Sep 17 00:00:00 2001
From: Steve Capper <steve.capper@arm.com>
Date: Wed, 7 Aug 2019 16:55:14 +0100
Subject: arm64: mm: Flip kernel VA space

In order to allow for a KASAN shadow that changes size at boot time, one
must fix the KASAN_SHADOW_END for both 48 & 52-bit VAs and "grow" the
start address. Also, it is highly desirable to maintain the same
function addresses in the kernel .text between VA sizes. Both of these
requirements necessitate us to flip the kernel address space halves s.t.
the direct linear map occupies the lower addresses.

This patch puts the direct linear map in the lower addresses of the
kernel VA range and everything else in the higher ranges.

We need to adjust:
 *) KASAN shadow region placement logic,
 *) KASAN_SHADOW_OFFSET computation logic,
 *) virt_to_phys, phys_to_virt checks,
 *) page table dumper.

These are all small changes, that need to take place atomically, so they
are bundled into this commit.

As part of the re-arrangement, a guard region of 2MB (to preserve
alignment for fixed map) is added after the vmemmap. Otherwise the
vmemmap could intersect with IS_ERR pointers.

Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Steve Capper <steve.capper@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/Makefile              | 2 +-
 arch/arm64/include/asm/memory.h  | 8 ++++----
 arch/arm64/include/asm/pgtable.h | 2 +-
 arch/arm64/kernel/hibernate.c    | 2 +-
 arch/arm64/mm/dump.c             | 5 +++--
 arch/arm64/mm/init.c             | 9 +--------
 arch/arm64/mm/kasan_init.c       | 6 +++---
 arch/arm64/mm/mmu.c              | 4 ++--
 8 files changed, 16 insertions(+), 22 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 61de992bbea3..61f7926fdeca 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -130,7 +130,7 @@ KBUILD_AFLAGS += -DKASAN_SHADOW_SCALE_SHIFT=$(KASAN_SHADOW_SCALE_SHIFT)
 #				 - (1 << (64 - KASAN_SHADOW_SCALE_SHIFT))
 # in 32-bit arithmetic
 KASAN_SHADOW_OFFSET := $(shell printf "0x%08x00000000\n" $$(( \
-	(0xffffffff & (-1 << ($(CONFIG_ARM64_VA_BITS) - 32))) \
+	(0xffffffff & (-1 << ($(CONFIG_ARM64_VA_BITS) - 1 - 32))) \
 	+ (1 << ($(CONFIG_ARM64_VA_BITS) - 32 - $(KASAN_SHADOW_SCALE_SHIFT))) \
 	- (1 << (64 - 32 - $(KASAN_SHADOW_SCALE_SHIFT))) )) )
 
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 98fda92a2612..380594b1a0ba 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -38,9 +38,9 @@
  */
 #define VA_BITS			(CONFIG_ARM64_VA_BITS)
 #define VA_START		(UL(0xffffffffffffffff) - \
-	(UL(1) << VA_BITS) + 1)
-#define PAGE_OFFSET		(UL(0xffffffffffffffff) - \
 	(UL(1) << (VA_BITS - 1)) + 1)
+#define PAGE_OFFSET		(UL(0xffffffffffffffff) - \
+	(UL(1) << VA_BITS) + 1)
 #define KIMAGE_VADDR		(MODULES_END)
 #define BPF_JIT_REGION_START	(VA_START + KASAN_SHADOW_SIZE)
 #define BPF_JIT_REGION_SIZE	(SZ_128M)
@@ -48,7 +48,7 @@
 #define MODULES_END		(MODULES_VADDR + MODULES_VSIZE)
 #define MODULES_VADDR		(BPF_JIT_REGION_END)
 #define MODULES_VSIZE		(SZ_128M)
-#define VMEMMAP_START		(PAGE_OFFSET - VMEMMAP_SIZE)
+#define VMEMMAP_START		(-VMEMMAP_SIZE - SZ_2M)
 #define PCI_IO_END		(VMEMMAP_START - SZ_2M)
 #define PCI_IO_START		(PCI_IO_END - PCI_IO_SIZE)
 #define FIXADDR_TOP		(PCI_IO_START - SZ_2M)
@@ -231,7 +231,7 @@ static inline const void *__tag_set(const void *addr, u8 tag)
  * space. Testing the top bit for the start of the region is a
  * sufficient check.
  */
-#define __is_lm_address(addr)	(!!((addr) & BIT(VA_BITS - 1)))
+#define __is_lm_address(addr)	(!((addr) & BIT(VA_BITS - 1)))
 
 #define __lm_to_phys(addr)	(((addr) & ~PAGE_OFFSET) + PHYS_OFFSET)
 #define __kimg_to_phys(addr)	((addr) - kimage_voffset)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 5fdcfe237338..046b811309bb 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -21,7 +21,7 @@
  *	and fixed mappings
  */
 #define VMALLOC_START		(MODULES_END)
-#define VMALLOC_END		(PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K)
+#define VMALLOC_END		(- PUD_SIZE - VMEMMAP_SIZE - SZ_64K)
 
 #define vmemmap			((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT))
 
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index 9341fcc6e809..e130db05d932 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -496,7 +496,7 @@ int swsusp_arch_resume(void)
 		rc = -ENOMEM;
 		goto out;
 	}
-	rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0);
+	rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, VA_START);
 	if (rc)
 		goto out;
 
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index 82b3a7fdb4a6..beec87488e97 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -26,6 +26,8 @@
 #include <asm/ptdump.h>
 
 static const struct addr_marker address_markers[] = {
+	{ PAGE_OFFSET,			"Linear Mapping start" },
+	{ VA_START,			"Linear Mapping end" },
 #ifdef CONFIG_KASAN
 	{ KASAN_SHADOW_START,		"Kasan shadow start" },
 	{ KASAN_SHADOW_END,		"Kasan shadow end" },
@@ -42,7 +44,6 @@ static const struct addr_marker address_markers[] = {
 	{ VMEMMAP_START,		"vmemmap start" },
 	{ VMEMMAP_START + VMEMMAP_SIZE,	"vmemmap end" },
 #endif
-	{ PAGE_OFFSET,			"Linear mapping" },
 	{ -1,				NULL },
 };
 
@@ -376,7 +377,7 @@ static void ptdump_initialize(void)
 static struct ptdump_info kernel_ptdump_info = {
 	.mm		= &init_mm,
 	.markers	= address_markers,
-	.base_addr	= VA_START,
+	.base_addr	= PAGE_OFFSET,
 };
 
 void ptdump_check_wx(void)
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index f3c795278def..62927ed02229 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -301,7 +301,7 @@ static void __init fdt_enforce_memory_region(void)
 
 void __init arm64_memblock_init(void)
 {
-	const s64 linear_region_size = -(s64)PAGE_OFFSET;
+	const s64 linear_region_size = BIT(VA_BITS - 1);
 
 	/* Handle linux,usable-memory-range property */
 	fdt_enforce_memory_region();
@@ -309,13 +309,6 @@ void __init arm64_memblock_init(void)
 	/* Remove memory above our supported physical address size */
 	memblock_remove(1ULL << PHYS_MASK_SHIFT, ULLONG_MAX);
 
-	/*
-	 * Ensure that the linear region takes up exactly half of the kernel
-	 * virtual address space. This way, we can distinguish a linear address
-	 * from a kernel/module/vmalloc address by testing a single bit.
-	 */
-	BUILD_BUG_ON(linear_region_size != BIT(VA_BITS - 1));
-
 	/*
 	 * Select a suitable value for the base of physical memory.
 	 */
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index 6cf97b904ebb..05edfe9b02e4 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -225,10 +225,10 @@ void __init kasan_init(void)
 	kasan_map_populate(kimg_shadow_start, kimg_shadow_end,
 			   early_pfn_to_nid(virt_to_pfn(lm_alias(_text))));
 
-	kasan_populate_early_shadow((void *)KASAN_SHADOW_START,
-				    (void *)mod_shadow_start);
+	kasan_populate_early_shadow(kasan_mem_to_shadow((void *) VA_START),
+				   (void *)mod_shadow_start);
 	kasan_populate_early_shadow((void *)kimg_shadow_end,
-				    kasan_mem_to_shadow((void *)PAGE_OFFSET));
+				   (void *)KASAN_SHADOW_END);
 
 	if (kimg_shadow_start > mod_shadow_end)
 		kasan_populate_early_shadow((void *)mod_shadow_end,
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 750a69dde39b..1d4247f9a496 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -398,7 +398,7 @@ static phys_addr_t pgd_pgtable_alloc(int shift)
 static void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt,
 				  phys_addr_t size, pgprot_t prot)
 {
-	if (virt < VMALLOC_START) {
+	if ((virt >= VA_START) && (virt < VMALLOC_START)) {
 		pr_warn("BUG: not creating mapping for %pa at 0x%016lx - outside kernel range\n",
 			&phys, virt);
 		return;
@@ -425,7 +425,7 @@ void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
 static void update_mapping_prot(phys_addr_t phys, unsigned long virt,
 				phys_addr_t size, pgprot_t prot)
 {
-	if (virt < VMALLOC_START) {
+	if ((virt >= VA_START) && (virt < VMALLOC_START)) {
 		pr_warn("BUG: not updating mapping for %pa at 0x%016lx - outside kernel range\n",
 			&phys, virt);
 		return;
-- 
cgit v1.2.3


From 6bd1d0be0e97936d15cdacc71f5c232fbf71293e Mon Sep 17 00:00:00 2001
From: Steve Capper <steve.capper@arm.com>
Date: Wed, 7 Aug 2019 16:55:15 +0100
Subject: arm64: kasan: Switch to using KASAN_SHADOW_OFFSET

KASAN_SHADOW_OFFSET is a constant that is supplied to gcc as a command
line argument and affects the codegen of the inline address sanetiser.

Essentially, for an example memory access:
    *ptr1 = val;
The compiler will insert logic similar to the below:
    shadowValue = *(ptr1 >> KASAN_SHADOW_SCALE_SHIFT + KASAN_SHADOW_OFFSET)
    if (somethingWrong(shadowValue))
        flagAnError();

This code sequence is inserted into many places, thus
KASAN_SHADOW_OFFSET is essentially baked into many places in the kernel
text.

If we want to run a single kernel binary with multiple address spaces,
then we need to do this with KASAN_SHADOW_OFFSET fixed.

Thankfully, due to the way the KASAN_SHADOW_OFFSET is used to provide
shadow addresses we know that the end of the shadow region is constant
w.r.t. VA space size:
    KASAN_SHADOW_END = ~0 >> KASAN_SHADOW_SCALE_SHIFT + KASAN_SHADOW_OFFSET

This means that if we increase the size of the VA space, the start of
the KASAN region expands into lower addresses whilst the end of the
KASAN region is fixed.

Currently the arm64 code computes KASAN_SHADOW_OFFSET at build time via
build scripts with the VA size used as a parameter. (There are build
time checks in the C code too to ensure that expected values are being
derived). It is sufficient, and indeed is a simplification, to remove
the build scripts (and build time checks) entirely and instead provide
KASAN_SHADOW_OFFSET values.

This patch removes the logic to compute the KASAN_SHADOW_OFFSET in the
arm64 Makefile, and instead we adopt the approach used by x86 to supply
offset values in kConfig. To help debug/develop future VA space changes,
the Makefile logic has been preserved in a script file in the arm64
Documentation folder.

Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Steve Capper <steve.capper@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 Documentation/arm64/kasan-offsets.sh | 27 +++++++++++++++++++++++++++
 arch/arm64/Kconfig                   | 15 +++++++++++++++
 arch/arm64/Makefile                  |  8 --------
 arch/arm64/include/asm/kasan.h       | 11 ++++-------
 arch/arm64/include/asm/memory.h      |  8 +++++---
 5 files changed, 51 insertions(+), 18 deletions(-)
 create mode 100644 Documentation/arm64/kasan-offsets.sh

(limited to 'arch')

diff --git a/Documentation/arm64/kasan-offsets.sh b/Documentation/arm64/kasan-offsets.sh
new file mode 100644
index 000000000000..2b7a021db363
--- /dev/null
+++ b/Documentation/arm64/kasan-offsets.sh
@@ -0,0 +1,27 @@
+#!/bin/sh
+
+# Print out the KASAN_SHADOW_OFFSETS required to place the KASAN SHADOW
+# start address at the mid-point of the kernel VA space
+
+print_kasan_offset () {
+	printf "%02d\t" $1
+	printf "0x%08x00000000\n" $(( (0xffffffff & (-1 << ($1 - 1 - 32))) \
+			+ (1 << ($1 - 32 - $2)) \
+			- (1 << (64 - 32 - $2)) ))
+}
+
+echo KASAN_SHADOW_SCALE_SHIFT = 3
+printf "VABITS\tKASAN_SHADOW_OFFSET\n"
+print_kasan_offset 48 3
+print_kasan_offset 47 3
+print_kasan_offset 42 3
+print_kasan_offset 39 3
+print_kasan_offset 36 3
+echo
+echo KASAN_SHADOW_SCALE_SHIFT = 4
+printf "VABITS\tKASAN_SHADOW_OFFSET\n"
+print_kasan_offset 48 4
+print_kasan_offset 47 4
+print_kasan_offset 42 4
+print_kasan_offset 39 4
+print_kasan_offset 36 4
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 3adcec05b1f6..f7f23e47c28f 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -297,6 +297,21 @@ config ARCH_SUPPORTS_UPROBES
 config ARCH_PROC_KCORE_TEXT
 	def_bool y
 
+config KASAN_SHADOW_OFFSET
+	hex
+	depends on KASAN
+	default 0xdfffa00000000000 if (ARM64_VA_BITS_48 || ARM64_USER_VA_BITS_52) && !KASAN_SW_TAGS
+	default 0xdfffd00000000000 if ARM64_VA_BITS_47 && !KASAN_SW_TAGS
+	default 0xdffffe8000000000 if ARM64_VA_BITS_42 && !KASAN_SW_TAGS
+	default 0xdfffffd000000000 if ARM64_VA_BITS_39 && !KASAN_SW_TAGS
+	default 0xdffffffa00000000 if ARM64_VA_BITS_36 && !KASAN_SW_TAGS
+	default 0xefff900000000000 if (ARM64_VA_BITS_48 || ARM64_USER_VA_BITS_52) && KASAN_SW_TAGS
+	default 0xefffc80000000000 if ARM64_VA_BITS_47 && KASAN_SW_TAGS
+	default 0xeffffe4000000000 if ARM64_VA_BITS_42 && KASAN_SW_TAGS
+	default 0xefffffc800000000 if ARM64_VA_BITS_39 && KASAN_SW_TAGS
+	default 0xeffffff900000000 if ARM64_VA_BITS_36 && KASAN_SW_TAGS
+	default 0xffffffffffffffff
+
 source "arch/arm64/Kconfig.platforms"
 
 menu "Kernel Features"
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 61f7926fdeca..a8d2a241ac58 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -126,14 +126,6 @@ KBUILD_CFLAGS += -DKASAN_SHADOW_SCALE_SHIFT=$(KASAN_SHADOW_SCALE_SHIFT)
 KBUILD_CPPFLAGS += -DKASAN_SHADOW_SCALE_SHIFT=$(KASAN_SHADOW_SCALE_SHIFT)
 KBUILD_AFLAGS += -DKASAN_SHADOW_SCALE_SHIFT=$(KASAN_SHADOW_SCALE_SHIFT)
 
-# KASAN_SHADOW_OFFSET = VA_START + (1 << (VA_BITS - KASAN_SHADOW_SCALE_SHIFT))
-#				 - (1 << (64 - KASAN_SHADOW_SCALE_SHIFT))
-# in 32-bit arithmetic
-KASAN_SHADOW_OFFSET := $(shell printf "0x%08x00000000\n" $$(( \
-	(0xffffffff & (-1 << ($(CONFIG_ARM64_VA_BITS) - 1 - 32))) \
-	+ (1 << ($(CONFIG_ARM64_VA_BITS) - 32 - $(KASAN_SHADOW_SCALE_SHIFT))) \
-	- (1 << (64 - 32 - $(KASAN_SHADOW_SCALE_SHIFT))) )) )
-
 export	TEXT_OFFSET GZFLAGS
 
 core-y		+= arch/arm64/kernel/ arch/arm64/mm/
diff --git a/arch/arm64/include/asm/kasan.h b/arch/arm64/include/asm/kasan.h
index b52aacd2c526..10d2add842da 100644
--- a/arch/arm64/include/asm/kasan.h
+++ b/arch/arm64/include/asm/kasan.h
@@ -18,11 +18,8 @@
  * KASAN_SHADOW_START: beginning of the kernel virtual addresses.
  * KASAN_SHADOW_END: KASAN_SHADOW_START + 1/N of kernel virtual addresses,
  * where N = (1 << KASAN_SHADOW_SCALE_SHIFT).
- */
-#define KASAN_SHADOW_START      (VA_START)
-#define KASAN_SHADOW_END        (KASAN_SHADOW_START + KASAN_SHADOW_SIZE)
-
-/*
+ *
+ * KASAN_SHADOW_OFFSET:
  * This value is used to map an address to the corresponding shadow
  * address by the following formula:
  *     shadow_addr = (address >> KASAN_SHADOW_SCALE_SHIFT) + KASAN_SHADOW_OFFSET
@@ -33,8 +30,8 @@
  *      KASAN_SHADOW_OFFSET = KASAN_SHADOW_END -
  *				(1ULL << (64 - KASAN_SHADOW_SCALE_SHIFT))
  */
-#define KASAN_SHADOW_OFFSET     (KASAN_SHADOW_END - (1ULL << \
-					(64 - KASAN_SHADOW_SCALE_SHIFT)))
+#define _KASAN_SHADOW_START(va)	(KASAN_SHADOW_END - (1UL << ((va) - KASAN_SHADOW_SCALE_SHIFT)))
+#define KASAN_SHADOW_START      _KASAN_SHADOW_START(VA_BITS)
 
 void kasan_init(void);
 void kasan_copy_shadow(pgd_t *pgdir);
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 380594b1a0ba..968659c90f5c 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -42,7 +42,7 @@
 #define PAGE_OFFSET		(UL(0xffffffffffffffff) - \
 	(UL(1) << VA_BITS) + 1)
 #define KIMAGE_VADDR		(MODULES_END)
-#define BPF_JIT_REGION_START	(VA_START + KASAN_SHADOW_SIZE)
+#define BPF_JIT_REGION_START	(KASAN_SHADOW_END)
 #define BPF_JIT_REGION_SIZE	(SZ_128M)
 #define BPF_JIT_REGION_END	(BPF_JIT_REGION_START + BPF_JIT_REGION_SIZE)
 #define MODULES_END		(MODULES_VADDR + MODULES_VSIZE)
@@ -68,11 +68,13 @@
  * significantly, so double the (minimum) stack size when they are in use.
  */
 #ifdef CONFIG_KASAN
-#define KASAN_SHADOW_SIZE	(UL(1) << (VA_BITS - KASAN_SHADOW_SCALE_SHIFT))
+#define KASAN_SHADOW_OFFSET	_AC(CONFIG_KASAN_SHADOW_OFFSET, UL)
+#define KASAN_SHADOW_END	((UL(1) << (64 - KASAN_SHADOW_SCALE_SHIFT)) \
+					+ KASAN_SHADOW_OFFSET)
 #define KASAN_THREAD_SHIFT	1
 #else
-#define KASAN_SHADOW_SIZE	(0)
 #define KASAN_THREAD_SHIFT	0
+#define KASAN_SHADOW_END	(VA_START)
 #endif
 
 #define MIN_THREAD_SHIFT	(14 + KASAN_THREAD_SHIFT)
-- 
cgit v1.2.3


From 99426e5e8c9f11b9de65e7c1200868e8a9ceaa47 Mon Sep 17 00:00:00 2001
From: Steve Capper <steve.capper@arm.com>
Date: Wed, 7 Aug 2019 16:55:16 +0100
Subject: arm64: dump: De-constify VA_START and KASAN_SHADOW_START

The kernel page table dumper assumes that the placement of VA regions is
constant and determined at compile time. As we are about to introduce
variable VA logic, we need to be able to determine certain regions at
boot time.

Specifically the VA_START and KASAN_SHADOW_START will depend on whether
or not the system is booted with 52-bit kernel VAs.

This patch adds logic to the kernel page table dumper s.t. these regions
can be computed at boot time.

Signed-off-by: Steve Capper <steve.capper@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/mm/dump.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index beec87488e97..6ec75305828e 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -25,11 +25,20 @@
 #include <asm/pgtable-hwdef.h>
 #include <asm/ptdump.h>
 
-static const struct addr_marker address_markers[] = {
+
+enum address_markers_idx {
+	PAGE_OFFSET_NR = 0,
+	VA_START_NR,
+#ifdef CONFIG_KASAN
+	KASAN_START_NR,
+#endif
+};
+
+static struct addr_marker address_markers[] = {
 	{ PAGE_OFFSET,			"Linear Mapping start" },
-	{ VA_START,			"Linear Mapping end" },
+	{ 0 /* VA_START */,		"Linear Mapping end" },
 #ifdef CONFIG_KASAN
-	{ KASAN_SHADOW_START,		"Kasan shadow start" },
+	{ 0 /* KASAN_SHADOW_START */,	"Kasan shadow start" },
 	{ KASAN_SHADOW_END,		"Kasan shadow end" },
 #endif
 	{ MODULES_VADDR,		"Modules start" },
@@ -402,6 +411,10 @@ void ptdump_check_wx(void)
 
 static int ptdump_init(void)
 {
+	address_markers[VA_START_NR].start_address = VA_START;
+#ifdef CONFIG_KASAN
+	address_markers[KASAN_START_NR].start_address = KASAN_SHADOW_START;
+#endif
 	ptdump_initialize();
 	ptdump_debugfs_register(&kernel_ptdump_info, "kernel_page_tables");
 	return 0;
-- 
cgit v1.2.3


From 90ec95cda91a021d82351c976896a63aa364ebf1 Mon Sep 17 00:00:00 2001
From: Steve Capper <steve.capper@arm.com>
Date: Wed, 7 Aug 2019 16:55:17 +0100
Subject: arm64: mm: Introduce VA_BITS_MIN

In order to support 52-bit kernel addresses detectable at boot time, the
kernel needs to know the most conservative VA_BITS possible should it
need to fall back to this quantity due to lack of hardware support.

A new compile time constant VA_BITS_MIN is introduced in this patch and
it is employed in the KASAN end address, KASLR, and EFI stub.

For Arm, if 52-bit VA support is unavailable the fallback is to 48-bits.

In other words: VA_BITS_MIN = min (48, VA_BITS)

Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Steve Capper <steve.capper@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/efi.h       | 4 ++--
 arch/arm64/include/asm/memory.h    | 9 ++++++++-
 arch/arm64/include/asm/processor.h | 2 +-
 arch/arm64/kernel/head.S           | 2 +-
 arch/arm64/kernel/kaslr.c          | 6 +++---
 arch/arm64/mm/kasan_init.c         | 3 ++-
 6 files changed, 17 insertions(+), 9 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index 76a144702586..b54d3a86c444 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -79,7 +79,7 @@ static inline unsigned long efi_get_max_fdt_addr(unsigned long dram_base)
 
 /*
  * On arm64, we have to ensure that the initrd ends up in the linear region,
- * which is a 1 GB aligned region of size '1UL << (VA_BITS - 1)' that is
+ * which is a 1 GB aligned region of size '1UL << (VA_BITS_MIN - 1)' that is
  * guaranteed to cover the kernel Image.
  *
  * Since the EFI stub is part of the kernel Image, we can relax the
@@ -90,7 +90,7 @@ static inline unsigned long efi_get_max_fdt_addr(unsigned long dram_base)
 static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base,
 						    unsigned long image_addr)
 {
-	return (image_addr & ~(SZ_1G - 1UL)) + (1UL << (VA_BITS - 1));
+	return (image_addr & ~(SZ_1G - 1UL)) + (1UL << (VA_BITS_MIN - 1));
 }
 
 #define efi_call_early(f, ...)		sys_table_arg->boottime->f(__VA_ARGS__)
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 968659c90f5c..79e75e45d560 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -52,6 +52,13 @@
 #define PCI_IO_END		(VMEMMAP_START - SZ_2M)
 #define PCI_IO_START		(PCI_IO_END - PCI_IO_SIZE)
 #define FIXADDR_TOP		(PCI_IO_START - SZ_2M)
+#if VA_BITS > 48
+#define VA_BITS_MIN		(48)
+#else
+#define VA_BITS_MIN		(VA_BITS)
+#endif
+#define _VA_START(va)		(UL(0xffffffffffffffff) - \
+				(UL(1) << ((va) - 1)) + 1)
 
 #define KERNEL_START      _text
 #define KERNEL_END        _end
@@ -74,7 +81,7 @@
 #define KASAN_THREAD_SHIFT	1
 #else
 #define KASAN_THREAD_SHIFT	0
-#define KASAN_SHADOW_END	(VA_START)
+#define KASAN_SHADOW_END	(_VA_START(VA_BITS_MIN))
 #endif
 
 #define MIN_THREAD_SHIFT	(14 + KASAN_THREAD_SHIFT)
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 844e2964b0f5..0e1f2770192a 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -42,7 +42,7 @@
  * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area.
  */
 
-#define DEFAULT_MAP_WINDOW_64	(UL(1) << VA_BITS)
+#define DEFAULT_MAP_WINDOW_64	(UL(1) << VA_BITS_MIN)
 #define TASK_SIZE_64		(UL(1) << vabits_user)
 
 #ifdef CONFIG_COMPAT
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 2cdacd1c141b..ac58c69993ec 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -314,7 +314,7 @@ __create_page_tables:
 	mov	x5, #52
 	cbnz	x6, 1f
 #endif
-	mov	x5, #VA_BITS
+	mov	x5, #VA_BITS_MIN
 1:
 	adr_l	x6, vabits_user
 	str	x5, [x6]
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index 708051655ad9..5a59f7567f9c 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -116,15 +116,15 @@ u64 __init kaslr_early_init(u64 dt_phys)
 	/*
 	 * OK, so we are proceeding with KASLR enabled. Calculate a suitable
 	 * kernel image offset from the seed. Let's place the kernel in the
-	 * middle half of the VMALLOC area (VA_BITS - 2), and stay clear of
+	 * middle half of the VMALLOC area (VA_BITS_MIN - 2), and stay clear of
 	 * the lower and upper quarters to avoid colliding with other
 	 * allocations.
 	 * Even if we could randomize at page granularity for 16k and 64k pages,
 	 * let's always round to 2 MB so we don't interfere with the ability to
 	 * map using contiguous PTEs
 	 */
-	mask = ((1UL << (VA_BITS - 2)) - 1) & ~(SZ_2M - 1);
-	offset = BIT(VA_BITS - 3) + (seed & mask);
+	mask = ((1UL << (VA_BITS_MIN - 2)) - 1) & ~(SZ_2M - 1);
+	offset = BIT(VA_BITS_MIN - 3) + (seed & mask);
 
 	/* use the top 16 bits to randomize the linear region */
 	memstart_offset_seed = seed >> 48;
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index 05edfe9b02e4..725222271474 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -156,7 +156,8 @@ asmlinkage void __init kasan_early_init(void)
 {
 	BUILD_BUG_ON(KASAN_SHADOW_OFFSET !=
 		KASAN_SHADOW_END - (1UL << (64 - KASAN_SHADOW_SCALE_SHIFT)));
-	BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_START, PGDIR_SIZE));
+	BUILD_BUG_ON(!IS_ALIGNED(_KASAN_SHADOW_START(VA_BITS), PGDIR_SIZE));
+	BUILD_BUG_ON(!IS_ALIGNED(_KASAN_SHADOW_START(VA_BITS_MIN), PGDIR_SIZE));
 	BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, PGDIR_SIZE));
 	kasan_pgd_populate(KASAN_SHADOW_START, KASAN_SHADOW_END, NUMA_NO_NODE,
 			   true);
-- 
cgit v1.2.3


From 5383cc6efed13784ddb3cff2cc183b6b8c50c8db Mon Sep 17 00:00:00 2001
From: Steve Capper <steve.capper@arm.com>
Date: Wed, 7 Aug 2019 16:55:18 +0100
Subject: arm64: mm: Introduce vabits_actual

In order to support 52-bit kernel addresses detectable at boot time, one
needs to know the actual VA_BITS detected. A new variable vabits_actual
is introduced in this commit and employed for the KVM hypervisor layout,
KASAN, fault handling and phys-to/from-virt translation where there
would normally be compile time constants.

In order to maintain performance in phys_to_virt, another variable
physvirt_offset is introduced.

Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Steve Capper <steve.capper@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/kasan.h       |  2 +-
 arch/arm64/include/asm/memory.h      | 11 ++++++-----
 arch/arm64/include/asm/mmu_context.h |  2 +-
 arch/arm64/kernel/head.S             |  5 +++++
 arch/arm64/kvm/va_layout.c           | 14 +++++++-------
 arch/arm64/mm/fault.c                |  4 ++--
 arch/arm64/mm/init.c                 |  7 ++++++-
 arch/arm64/mm/mmu.c                  |  3 +++
 8 files changed, 31 insertions(+), 17 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/kasan.h b/arch/arm64/include/asm/kasan.h
index 10d2add842da..b0dc4abc3589 100644
--- a/arch/arm64/include/asm/kasan.h
+++ b/arch/arm64/include/asm/kasan.h
@@ -31,7 +31,7 @@
  *				(1ULL << (64 - KASAN_SHADOW_SCALE_SHIFT))
  */
 #define _KASAN_SHADOW_START(va)	(KASAN_SHADOW_END - (1UL << ((va) - KASAN_SHADOW_SCALE_SHIFT)))
-#define KASAN_SHADOW_START      _KASAN_SHADOW_START(VA_BITS)
+#define KASAN_SHADOW_START      _KASAN_SHADOW_START(vabits_actual)
 
 void kasan_init(void);
 void kasan_copy_shadow(pgd_t *pgdir);
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 79e75e45d560..364635b8370a 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -37,8 +37,6 @@
  * VA_START - the first kernel virtual address.
  */
 #define VA_BITS			(CONFIG_ARM64_VA_BITS)
-#define VA_START		(UL(0xffffffffffffffff) - \
-	(UL(1) << (VA_BITS - 1)) + 1)
 #define PAGE_OFFSET		(UL(0xffffffffffffffff) - \
 	(UL(1) << VA_BITS) + 1)
 #define KIMAGE_VADDR		(MODULES_END)
@@ -166,10 +164,13 @@
 #endif
 
 #ifndef __ASSEMBLY__
+extern u64			vabits_actual;
+#define VA_START		(_VA_START(vabits_actual))
 
 #include <linux/bitops.h>
 #include <linux/mmdebug.h>
 
+extern s64			physvirt_offset;
 extern s64			memstart_addr;
 /* PHYS_OFFSET - the physical address of the start of memory. */
 #define PHYS_OFFSET		({ VM_BUG_ON(memstart_addr & 1); memstart_addr; })
@@ -240,9 +241,9 @@ static inline const void *__tag_set(const void *addr, u8 tag)
  * space. Testing the top bit for the start of the region is a
  * sufficient check.
  */
-#define __is_lm_address(addr)	(!((addr) & BIT(VA_BITS - 1)))
+#define __is_lm_address(addr)	(!((addr) & BIT(vabits_actual - 1)))
 
-#define __lm_to_phys(addr)	(((addr) & ~PAGE_OFFSET) + PHYS_OFFSET)
+#define __lm_to_phys(addr)	(((addr) + physvirt_offset))
 #define __kimg_to_phys(addr)	((addr) - kimage_voffset)
 
 #define __virt_to_phys_nodebug(x) ({					\
@@ -261,7 +262,7 @@ extern phys_addr_t __phys_addr_symbol(unsigned long x);
 #define __phys_addr_symbol(x)	__pa_symbol_nodebug(x)
 #endif
 
-#define __phys_to_virt(x)	((unsigned long)((x) - PHYS_OFFSET) | PAGE_OFFSET)
+#define __phys_to_virt(x)	((unsigned long)((x) - physvirt_offset))
 #define __phys_to_kimg(x)	((unsigned long)((x) + kimage_voffset))
 
 /*
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index 7ed0adb187a8..670003a55d28 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -95,7 +95,7 @@ static inline void __cpu_set_tcr_t0sz(unsigned long t0sz)
 	isb();
 }
 
-#define cpu_set_default_tcr_t0sz()	__cpu_set_tcr_t0sz(TCR_T0SZ(VA_BITS))
+#define cpu_set_default_tcr_t0sz()	__cpu_set_tcr_t0sz(TCR_T0SZ(vabits_actual))
 #define cpu_set_idmap_tcr_t0sz()	__cpu_set_tcr_t0sz(idmap_t0sz)
 
 /*
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index ac58c69993ec..6dc7349868d9 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -321,6 +321,11 @@ __create_page_tables:
 	dmb	sy
 	dc	ivac, x6		// Invalidate potentially stale cache line
 
+	adr_l	x6, vabits_actual
+	str	x5, [x6]
+	dmb	sy
+	dc	ivac, x6		// Invalidate potentially stale cache line
+
 	/*
 	 * VA_BITS 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
diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c
index acd8084f1f2c..2cf7d4b606c3 100644
--- a/arch/arm64/kvm/va_layout.c
+++ b/arch/arm64/kvm/va_layout.c
@@ -29,25 +29,25 @@ static void compute_layout(void)
 	int kva_msb;
 
 	/* Where is my RAM region? */
-	hyp_va_msb  = idmap_addr & BIT(VA_BITS - 1);
-	hyp_va_msb ^= BIT(VA_BITS - 1);
+	hyp_va_msb  = idmap_addr & BIT(vabits_actual - 1);
+	hyp_va_msb ^= BIT(vabits_actual - 1);
 
 	kva_msb = fls64((u64)phys_to_virt(memblock_start_of_DRAM()) ^
 			(u64)(high_memory - 1));
 
-	if (kva_msb == (VA_BITS - 1)) {
+	if (kva_msb == (vabits_actual - 1)) {
 		/*
 		 * No space in the address, let's compute the mask so
-		 * that it covers (VA_BITS - 1) bits, and the region
+		 * that it covers (vabits_actual - 1) bits, and the region
 		 * bit. The tag stays set to zero.
 		 */
-		va_mask  = BIT(VA_BITS - 1) - 1;
+		va_mask  = BIT(vabits_actual - 1) - 1;
 		va_mask |= hyp_va_msb;
 	} else {
 		/*
 		 * We do have some free bits to insert a random tag.
 		 * Hyp VAs are now created from kernel linear map VAs
-		 * using the following formula (with V == VA_BITS):
+		 * using the following formula (with V == vabits_actual):
 		 *
 		 *  63 ... V |     V-1    | V-2 .. tag_lsb | tag_lsb - 1 .. 0
 		 *  ---------------------------------------------------------
@@ -55,7 +55,7 @@ static void compute_layout(void)
 		 */
 		tag_lsb = kva_msb;
 		va_mask = GENMASK_ULL(tag_lsb - 1, 0);
-		tag_val = get_random_long() & GENMASK_ULL(VA_BITS - 2, tag_lsb);
+		tag_val = get_random_long() & GENMASK_ULL(vabits_actual - 2, tag_lsb);
 		tag_val |= hyp_va_msb;
 		tag_val >>= tag_lsb;
 	}
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index cfd65b63f36f..6b195871769a 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -138,9 +138,9 @@ static void show_pte(unsigned long addr)
 		return;
 	}
 
-	pr_alert("%s pgtable: %luk pages, %u-bit VAs, pgdp=%016lx\n",
+	pr_alert("%s pgtable: %luk pages, %llu-bit VAs, pgdp=%016lx\n",
 		 mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K,
-		 mm == &init_mm ? VA_BITS : (int)vabits_user,
+		 mm == &init_mm ? vabits_actual : (int)vabits_user,
 		 (unsigned long)virt_to_phys(mm->pgd));
 	pgdp = pgd_offset(mm, addr);
 	pgd = READ_ONCE(*pgdp);
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 62927ed02229..e752f46d430e 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -50,6 +50,9 @@
 s64 memstart_addr __ro_after_init = -1;
 EXPORT_SYMBOL(memstart_addr);
 
+s64 physvirt_offset __ro_after_init;
+EXPORT_SYMBOL(physvirt_offset);
+
 phys_addr_t arm64_dma_phys_limit __ro_after_init;
 
 #ifdef CONFIG_KEXEC_CORE
@@ -301,7 +304,7 @@ static void __init fdt_enforce_memory_region(void)
 
 void __init arm64_memblock_init(void)
 {
-	const s64 linear_region_size = BIT(VA_BITS - 1);
+	const s64 linear_region_size = BIT(vabits_actual - 1);
 
 	/* Handle linux,usable-memory-range property */
 	fdt_enforce_memory_region();
@@ -315,6 +318,8 @@ void __init arm64_memblock_init(void)
 	memstart_addr = round_down(memblock_start_of_DRAM(),
 				   ARM64_MEMSTART_ALIGN);
 
+	physvirt_offset = PHYS_OFFSET - PAGE_OFFSET;
+
 	/*
 	 * Remove the memory that we will not be able to cover with the
 	 * linear mapping. Take care not to clip the kernel which may be
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 1d4247f9a496..07b30e6d17f8 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -43,6 +43,9 @@ u64 idmap_ptrs_per_pgd = PTRS_PER_PGD;
 u64 vabits_user __ro_after_init;
 EXPORT_SYMBOL(vabits_user);
 
+u64 __section(".mmuoff.data.write") vabits_actual;
+EXPORT_SYMBOL(vabits_actual);
+
 u64 kimage_voffset __ro_after_init;
 EXPORT_SYMBOL(kimage_voffset);
 
-- 
cgit v1.2.3


From c812026c54cfaec23fa1d78cdbfd0e56e787470a Mon Sep 17 00:00:00 2001
From: Steve Capper <steve.capper@arm.com>
Date: Wed, 7 Aug 2019 16:55:19 +0100
Subject: arm64: mm: Logic to make offset_ttbr1 conditional

When running with a 52-bit userspace VA and a 48-bit kernel VA we offset
ttbr1_el1 to allow the kernel pagetables with a 52-bit PTRS_PER_PGD to
be used for both userspace and kernel.

Moving on to a 52-bit kernel VA we no longer require this offset to
ttbr1_el1 should we be running on a system with HW support for 52-bit
VAs.

This patch introduces conditional logic to offset_ttbr1 to query
SYS_ID_AA64MMFR2_EL1 whenever 52-bit VAs are selected. If there is HW
support for 52-bit VAs then the ttbr1 offset is skipped.

We choose to read a system register rather than vabits_actual because
offset_ttbr1 can be called in places where the kernel data is not
actually mapped.

Calls to offset_ttbr1 appear to be made from rarely called code paths so
this extra logic is not expected to adversely affect performance.

Signed-off-by: Steve Capper <steve.capper@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/assembler.h | 12 ++++++++++--
 arch/arm64/kernel/head.S           |  2 +-
 arch/arm64/kernel/hibernate-asm.S  |  8 ++++----
 arch/arm64/mm/proc.S               |  6 +++---
 4 files changed, 18 insertions(+), 10 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index e3a15c751b13..ede368bafa2c 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -538,9 +538,17 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
  * In future this may be nop'ed out when dealing with 52-bit kernel VAs.
  * 	ttbr: Value of ttbr to set, modified.
  */
-	.macro	offset_ttbr1, ttbr
+	.macro	offset_ttbr1, ttbr, tmp
 #ifdef CONFIG_ARM64_USER_VA_BITS_52
 	orr	\ttbr, \ttbr, #TTBR1_BADDR_4852_OFFSET
+#endif
+
+#ifdef CONFIG_ARM64_VA_BITS_52
+	mrs_s	\tmp, SYS_ID_AA64MMFR2_EL1
+	and	\tmp, \tmp, #(0xf << ID_AA64MMFR2_LVA_SHIFT)
+	cbnz	\tmp, .Lskipoffs_\@
+	orr	\ttbr, \ttbr, #TTBR1_BADDR_4852_OFFSET
+.Lskipoffs_\@ :
 #endif
 	.endm
 
@@ -550,7 +558,7 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
  * to be nop'ed out when dealing with 52-bit kernel VAs.
  */
 	.macro	restore_ttbr1, ttbr
-#ifdef CONFIG_ARM64_USER_VA_BITS_52
+#if defined(CONFIG_ARM64_USER_VA_BITS_52) || defined(CONFIG_ARM64_VA_BITS_52)
 	bic	\ttbr, \ttbr, #TTBR1_BADDR_4852_OFFSET
 #endif
 	.endm
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 6dc7349868d9..a96dc4386c7c 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -777,7 +777,7 @@ ENTRY(__enable_mmu)
 	phys_to_ttbr x1, x1
 	phys_to_ttbr x2, x2
 	msr	ttbr0_el1, x2			// load TTBR0
-	offset_ttbr1 x1
+	offset_ttbr1 x1, x3
 	msr	ttbr1_el1, x1			// load TTBR1
 	isb
 	msr	sctlr_el1, x0
diff --git a/arch/arm64/kernel/hibernate-asm.S b/arch/arm64/kernel/hibernate-asm.S
index 2f4a2ce7264b..38bcd4d4e43b 100644
--- a/arch/arm64/kernel/hibernate-asm.S
+++ b/arch/arm64/kernel/hibernate-asm.S
@@ -22,14 +22,14 @@
  * Even switching to our copied tables will cause a changed output address at
  * each stage of the walk.
  */
-.macro break_before_make_ttbr_switch zero_page, page_table, tmp
+.macro break_before_make_ttbr_switch zero_page, page_table, tmp, tmp2
 	phys_to_ttbr \tmp, \zero_page
 	msr	ttbr1_el1, \tmp
 	isb
 	tlbi	vmalle1
 	dsb	nsh
 	phys_to_ttbr \tmp, \page_table
-	offset_ttbr1 \tmp
+	offset_ttbr1 \tmp, \tmp2
 	msr	ttbr1_el1, \tmp
 	isb
 .endm
@@ -70,7 +70,7 @@ ENTRY(swsusp_arch_suspend_exit)
 	 * We execute from ttbr0, change ttbr1 to our copied linear map tables
 	 * with a break-before-make via the zero page
 	 */
-	break_before_make_ttbr_switch	x5, x0, x6
+	break_before_make_ttbr_switch	x5, x0, x6, x8
 
 	mov	x21, x1
 	mov	x30, x2
@@ -101,7 +101,7 @@ ENTRY(swsusp_arch_suspend_exit)
 	dsb	ish		/* wait for PoU cleaning to finish */
 
 	/* switch to the restored kernels page tables */
-	break_before_make_ttbr_switch	x25, x21, x6
+	break_before_make_ttbr_switch	x25, x21, x6, x8
 
 	ic	ialluis
 	dsb	ish
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 7dbf2be470f6..8d289ff7584d 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -168,7 +168,7 @@ ENDPROC(cpu_do_switch_mm)
 .macro	__idmap_cpu_set_reserved_ttbr1, tmp1, tmp2
 	adrp	\tmp1, empty_zero_page
 	phys_to_ttbr \tmp2, \tmp1
-	offset_ttbr1 \tmp2
+	offset_ttbr1 \tmp2, \tmp1
 	msr	ttbr1_el1, \tmp2
 	isb
 	tlbi	vmalle1
@@ -187,7 +187,7 @@ ENTRY(idmap_cpu_replace_ttbr1)
 
 	__idmap_cpu_set_reserved_ttbr1 x1, x3
 
-	offset_ttbr1 x0
+	offset_ttbr1 x0, x3
 	msr	ttbr1_el1, x0
 	isb
 
@@ -362,7 +362,7 @@ __idmap_kpti_secondary:
 	cbnz	w18, 1b
 
 	/* All done, act like nothing happened */
-	offset_ttbr1 swapper_ttb
+	offset_ttbr1 swapper_ttb, x18
 	msr	ttbr1_el1, swapper_ttb
 	isb
 	ret
-- 
cgit v1.2.3


From c8b6d2ccf9b10ce872cdea037f9685804440bb7e Mon Sep 17 00:00:00 2001
From: Steve Capper <steve.capper@arm.com>
Date: Wed, 7 Aug 2019 16:55:20 +0100
Subject: arm64: mm: Separate out vmemmap

vmemmap is a preprocessor definition that depends on a variable,
memstart_addr. In a later patch we will need to expand the size of
the VMEMMAP region and optionally modify vmemmap depending upon
whether or not hardware support is available for 52-bit virtual
addresses.

This patch changes vmemmap to be a variable. As the old definition
depended on a variable load, this should not affect performance
noticeably.

Signed-off-by: Steve Capper <steve.capper@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/pgtable.h | 4 ++--
 arch/arm64/mm/init.c             | 5 +++++
 2 files changed, 7 insertions(+), 2 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 046b811309bb..4a695b9ee0f0 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -23,8 +23,6 @@
 #define VMALLOC_START		(MODULES_END)
 #define VMALLOC_END		(- PUD_SIZE - VMEMMAP_SIZE - SZ_64K)
 
-#define vmemmap			((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT))
-
 #define FIRST_USER_ADDRESS	0UL
 
 #ifndef __ASSEMBLY__
@@ -35,6 +33,8 @@
 #include <linux/mm_types.h>
 #include <linux/sched.h>
 
+extern struct page *vmemmap;
+
 extern void __pte_error(const char *file, int line, unsigned long val);
 extern void __pmd_error(const char *file, int line, unsigned long val);
 extern void __pud_error(const char *file, int line, unsigned long val);
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index e752f46d430e..2940221e5519 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -53,6 +53,9 @@ EXPORT_SYMBOL(memstart_addr);
 s64 physvirt_offset __ro_after_init;
 EXPORT_SYMBOL(physvirt_offset);
 
+struct page *vmemmap __ro_after_init;
+EXPORT_SYMBOL(vmemmap);
+
 phys_addr_t arm64_dma_phys_limit __ro_after_init;
 
 #ifdef CONFIG_KEXEC_CORE
@@ -320,6 +323,8 @@ void __init arm64_memblock_init(void)
 
 	physvirt_offset = PHYS_OFFSET - PAGE_OFFSET;
 
+	vmemmap = ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT));
+
 	/*
 	 * Remove the memory that we will not be able to cover with the
 	 * linear mapping. Take care not to clip the kernel which may be
-- 
cgit v1.2.3


From ce3aaed87344c83c77135f80e7b76e1da9c92ee6 Mon Sep 17 00:00:00 2001
From: Steve Capper <steve.capper@arm.com>
Date: Wed, 7 Aug 2019 16:55:21 +0100
Subject: arm64: mm: Modify calculation of VMEMMAP_SIZE

In a later patch we will need to have a slightly larger VMEMMAP region
to accommodate boot time selection between 48/52-bit kernel VAs.

This patch modifies the formula for computing VMEMMAP_SIZE to depend
explicitly on the PAGE_OFFSET and start of kernel addressable memory.
(This allows for a slightly larger direct linear map in future).

Signed-off-by: Steve Capper <steve.capper@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/memory.h | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 364635b8370a..0204c2006c92 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -26,8 +26,15 @@
 /*
  * VMEMMAP_SIZE - allows the whole linear region to be covered by
  *                a struct page array
+ *
+ * If we are configured with a 52-bit kernel VA then our VMEMMAP_SIZE
+ * neads to cover the memory region from the beginning of the 52-bit
+ * PAGE_OFFSET all the way to VA_START for 48-bit. This allows us to
+ * keep a constant PAGE_OFFSET and "fallback" to using the higher end
+ * of the VMEMMAP where 52-bit support is not available in hardware.
  */
-#define VMEMMAP_SIZE (UL(1) << (VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT))
+#define VMEMMAP_SIZE ((_VA_START(VA_BITS_MIN) - PAGE_OFFSET) \
+			>> (PAGE_SHIFT - STRUCT_PAGE_MAX_SHIFT))
 
 /*
  * PAGE_OFFSET - the virtual address of the start of the linear map (top
-- 
cgit v1.2.3


From b6d00d47e81a49f6cf462518c10408f37a3e6785 Mon Sep 17 00:00:00 2001
From: Steve Capper <steve.capper@arm.com>
Date: Wed, 7 Aug 2019 16:55:22 +0100
Subject: arm64: mm: Introduce 52-bit Kernel VAs

Most of the machinery is now in place to enable 52-bit kernel VAs that
are detectable at boot time.

This patch adds a Kconfig option for 52-bit user and kernel addresses
and plumbs in the requisite CONFIG_ macros as well as sets TCR.T1SZ,
physvirt_offset and vmemmap at early boot.

To simplify things this patch also removes the 52-bit user/48-bit kernel
kconfig option.

Signed-off-by: Steve Capper <steve.capper@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/Kconfig                     | 20 +++++++++++---------
 arch/arm64/include/asm/assembler.h     | 13 ++++++++-----
 arch/arm64/include/asm/memory.h        |  7 ++++---
 arch/arm64/include/asm/mmu_context.h   |  2 +-
 arch/arm64/include/asm/pgtable-hwdef.h |  2 +-
 arch/arm64/kernel/head.S               |  4 ++--
 arch/arm64/mm/init.c                   | 10 ++++++++++
 arch/arm64/mm/proc.S                   |  3 ++-
 8 files changed, 39 insertions(+), 22 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index f7f23e47c28f..f5f7cb75a698 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -286,7 +286,7 @@ config PGTABLE_LEVELS
 	int
 	default 2 if ARM64_16K_PAGES && ARM64_VA_BITS_36
 	default 2 if ARM64_64K_PAGES && ARM64_VA_BITS_42
-	default 3 if ARM64_64K_PAGES && (ARM64_VA_BITS_48 || ARM64_USER_VA_BITS_52)
+	default 3 if ARM64_64K_PAGES && (ARM64_VA_BITS_48 || ARM64_VA_BITS_52)
 	default 3 if ARM64_4K_PAGES && ARM64_VA_BITS_39
 	default 3 if ARM64_16K_PAGES && ARM64_VA_BITS_47
 	default 4 if !ARM64_64K_PAGES && ARM64_VA_BITS_48
@@ -300,12 +300,12 @@ config ARCH_PROC_KCORE_TEXT
 config KASAN_SHADOW_OFFSET
 	hex
 	depends on KASAN
-	default 0xdfffa00000000000 if (ARM64_VA_BITS_48 || ARM64_USER_VA_BITS_52) && !KASAN_SW_TAGS
+	default 0xdfffa00000000000 if (ARM64_VA_BITS_48 || ARM64_VA_BITS_52) && !KASAN_SW_TAGS
 	default 0xdfffd00000000000 if ARM64_VA_BITS_47 && !KASAN_SW_TAGS
 	default 0xdffffe8000000000 if ARM64_VA_BITS_42 && !KASAN_SW_TAGS
 	default 0xdfffffd000000000 if ARM64_VA_BITS_39 && !KASAN_SW_TAGS
 	default 0xdffffffa00000000 if ARM64_VA_BITS_36 && !KASAN_SW_TAGS
-	default 0xefff900000000000 if (ARM64_VA_BITS_48 || ARM64_USER_VA_BITS_52) && KASAN_SW_TAGS
+	default 0xefff900000000000 if (ARM64_VA_BITS_48 || ARM64_VA_BITS_52) && KASAN_SW_TAGS
 	default 0xefffc80000000000 if ARM64_VA_BITS_47 && KASAN_SW_TAGS
 	default 0xeffffe4000000000 if ARM64_VA_BITS_42 && KASAN_SW_TAGS
 	default 0xefffffc800000000 if ARM64_VA_BITS_39 && KASAN_SW_TAGS
@@ -759,13 +759,14 @@ config ARM64_VA_BITS_47
 config ARM64_VA_BITS_48
 	bool "48-bit"
 
-config ARM64_USER_VA_BITS_52
-	bool "52-bit (user)"
+config ARM64_VA_BITS_52
+	bool "52-bit"
 	depends on ARM64_64K_PAGES && (ARM64_PAN || !ARM64_SW_TTBR0_PAN)
 	help
 	  Enable 52-bit virtual addressing for userspace when explicitly
-	  requested via a hint to mmap(). The kernel will continue to
-	  use 48-bit virtual addresses for its own mappings.
+	  requested via a hint to mmap(). The kernel will also use 52-bit
+	  virtual addresses for its own mappings (provided HW support for
+	  this feature is available, otherwise it reverts to 48-bit).
 
 	  NOTE: Enabling 52-bit virtual addressing in conjunction with
 	  ARMv8.3 Pointer Authentication will result in the PAC being
@@ -778,7 +779,7 @@ endchoice
 
 config ARM64_FORCE_52BIT
 	bool "Force 52-bit virtual addresses for userspace"
-	depends on ARM64_USER_VA_BITS_52 && EXPERT
+	depends on ARM64_VA_BITS_52 && EXPERT
 	help
 	  For systems with 52-bit userspace VAs enabled, the kernel will attempt
 	  to maintain compatibility with older software by providing 48-bit VAs
@@ -795,7 +796,8 @@ config ARM64_VA_BITS
 	default 39 if ARM64_VA_BITS_39
 	default 42 if ARM64_VA_BITS_42
 	default 47 if ARM64_VA_BITS_47
-	default 48 if ARM64_VA_BITS_48 || ARM64_USER_VA_BITS_52
+	default 48 if ARM64_VA_BITS_48
+	default 52 if ARM64_VA_BITS_52
 
 choice
 	prompt "Physical address space size"
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index ede368bafa2c..c066fc4976cd 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -349,6 +349,13 @@ alternative_endif
 	bfi	\valreg, \t0sz, #TCR_T0SZ_OFFSET, #TCR_TxSZ_WIDTH
 	.endm
 
+/*
+ * tcr_set_t1sz - update TCR.T1SZ
+ */
+	.macro	tcr_set_t1sz, valreg, t1sz
+	bfi	\valreg, \t1sz, #TCR_T1SZ_OFFSET, #TCR_TxSZ_WIDTH
+	.endm
+
 /*
  * tcr_compute_pa_size - set TCR.(I)PS to the highest supported
  * ID_AA64MMFR0_EL1.PARange value
@@ -539,10 +546,6 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
  * 	ttbr: Value of ttbr to set, modified.
  */
 	.macro	offset_ttbr1, ttbr, tmp
-#ifdef CONFIG_ARM64_USER_VA_BITS_52
-	orr	\ttbr, \ttbr, #TTBR1_BADDR_4852_OFFSET
-#endif
-
 #ifdef CONFIG_ARM64_VA_BITS_52
 	mrs_s	\tmp, SYS_ID_AA64MMFR2_EL1
 	and	\tmp, \tmp, #(0xf << ID_AA64MMFR2_LVA_SHIFT)
@@ -558,7 +561,7 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
  * to be nop'ed out when dealing with 52-bit kernel VAs.
  */
 	.macro	restore_ttbr1, ttbr
-#if defined(CONFIG_ARM64_USER_VA_BITS_52) || defined(CONFIG_ARM64_VA_BITS_52)
+#ifdef CONFIG_ARM64_VA_BITS_52
 	bic	\ttbr, \ttbr, #TTBR1_BADDR_4852_OFFSET
 #endif
 	.endm
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 0204c2006c92..d911d0573460 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -44,8 +44,9 @@
  * VA_START - the first kernel virtual address.
  */
 #define VA_BITS			(CONFIG_ARM64_VA_BITS)
-#define PAGE_OFFSET		(UL(0xffffffffffffffff) - \
-	(UL(1) << VA_BITS) + 1)
+#define _PAGE_OFFSET(va)	(UL(0xffffffffffffffff) - \
+					(UL(1) << (va)) + 1)
+#define PAGE_OFFSET		(_PAGE_OFFSET(VA_BITS))
 #define KIMAGE_VADDR		(MODULES_END)
 #define BPF_JIT_REGION_START	(KASAN_SHADOW_END)
 #define BPF_JIT_REGION_SIZE	(SZ_128M)
@@ -68,7 +69,7 @@
 #define KERNEL_START      _text
 #define KERNEL_END        _end
 
-#ifdef CONFIG_ARM64_USER_VA_BITS_52
+#ifdef CONFIG_ARM64_VA_BITS_52
 #define MAX_USER_VA_BITS	52
 #else
 #define MAX_USER_VA_BITS	VA_BITS
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index 670003a55d28..3827ff4040a3 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -63,7 +63,7 @@ extern u64 idmap_ptrs_per_pgd;
 
 static inline bool __cpu_uses_extended_idmap(void)
 {
-	if (IS_ENABLED(CONFIG_ARM64_USER_VA_BITS_52))
+	if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52))
 		return false;
 
 	return unlikely(idmap_t0sz != TCR_T0SZ(VA_BITS));
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index db92950bb1a0..3df60f97da1f 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -304,7 +304,7 @@
 #define TTBR_BADDR_MASK_52	(((UL(1) << 46) - 1) << 2)
 #endif
 
-#ifdef CONFIG_ARM64_USER_VA_BITS_52
+#ifdef CONFIG_ARM64_VA_BITS_52
 /* Must be at least 64-byte aligned to prevent corruption of the TTBR */
 #define TTBR1_BADDR_4852_OFFSET	(((UL(1) << (52 - PGDIR_SHIFT)) - \
 				 (UL(1) << (48 - PGDIR_SHIFT))) * 8)
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index a96dc4386c7c..c8446f8c81f5 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -308,7 +308,7 @@ __create_page_tables:
 	adrp	x0, idmap_pg_dir
 	adrp	x3, __idmap_text_start		// __pa(__idmap_text_start)
 
-#ifdef CONFIG_ARM64_USER_VA_BITS_52
+#ifdef CONFIG_ARM64_VA_BITS_52
 	mrs_s	x6, SYS_ID_AA64MMFR2_EL1
 	and	x6, x6, #(0xf << ID_AA64MMFR2_LVA_SHIFT)
 	mov	x5, #52
@@ -794,7 +794,7 @@ ENTRY(__enable_mmu)
 ENDPROC(__enable_mmu)
 
 ENTRY(__cpu_secondary_check52bitva)
-#ifdef CONFIG_ARM64_USER_VA_BITS_52
+#ifdef CONFIG_ARM64_VA_BITS_52
 	ldr_l	x0, vabits_user
 	cmp	x0, #52
 	b.ne	2f
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 2940221e5519..531c497c5758 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -325,6 +325,16 @@ void __init arm64_memblock_init(void)
 
 	vmemmap = ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT));
 
+	/*
+	 * If we are running with a 52-bit kernel VA config on a system that
+	 * does not support it, we have to offset our vmemmap and physvirt_offset
+	 * s.t. we avoid the 52-bit portion of the direct linear map
+	 */
+	if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52) && (vabits_actual != 52)) {
+		vmemmap += (_PAGE_OFFSET(48) - _PAGE_OFFSET(52)) >> PAGE_SHIFT;
+		physvirt_offset = PHYS_OFFSET - _PAGE_OFFSET(48);
+	}
+
 	/*
 	 * Remove the memory that we will not be able to cover with the
 	 * linear mapping. Take care not to clip the kernel which may be
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 8d289ff7584d..8b021c5c0884 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -438,10 +438,11 @@ ENTRY(__cpu_setup)
 			TCR_TBI0 | TCR_A1 | TCR_KASAN_FLAGS
 	tcr_clear_errata_bits x10, x9, x5
 
-#ifdef CONFIG_ARM64_USER_VA_BITS_52
+#ifdef CONFIG_ARM64_VA_BITS_52
 	ldr_l		x9, vabits_user
 	sub		x9, xzr, x9
 	add		x9, x9, #64
+	tcr_set_t1sz	x10, x9
 #else
 	ldr_l		x9, idmap_t0sz
 #endif
-- 
cgit v1.2.3


From 2c624fe68715e76eba1a7089f91e122310dc663c Mon Sep 17 00:00:00 2001
From: Steve Capper <steve.capper@arm.com>
Date: Wed, 7 Aug 2019 16:55:23 +0100
Subject: arm64: mm: Remove vabits_user

Previous patches have enabled 52-bit kernel + user VAs and there is no
longer any scenario where user VA != kernel VA size.

This patch removes the, now redundant, vabits_user variable and replaces
usage with vabits_actual where appropriate.

Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Steve Capper <steve.capper@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/memory.h       | 3 ---
 arch/arm64/include/asm/pointer_auth.h | 2 +-
 arch/arm64/include/asm/processor.h    | 2 +-
 arch/arm64/kernel/head.S              | 7 +------
 arch/arm64/mm/fault.c                 | 3 +--
 arch/arm64/mm/mmu.c                   | 2 --
 arch/arm64/mm/proc.S                  | 2 +-
 7 files changed, 5 insertions(+), 16 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index d911d0573460..ecc945ba8607 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -194,9 +194,6 @@ static inline unsigned long kaslr_offset(void)
 	return kimage_vaddr - KIMAGE_VADDR;
 }
 
-/* the actual size of a user virtual address */
-extern u64			vabits_user;
-
 /*
  * Allow all memory at the discovery stage. We will clip it later.
  */
diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h
index d328540cb85e..7a24bad1a58b 100644
--- a/arch/arm64/include/asm/pointer_auth.h
+++ b/arch/arm64/include/asm/pointer_auth.h
@@ -69,7 +69,7 @@ extern int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg);
  * The EL0 pointer bits used by a pointer authentication code.
  * This is dependent on TBI0 being enabled, or bits 63:56 would also apply.
  */
-#define ptrauth_user_pac_mask()	GENMASK(54, vabits_user)
+#define ptrauth_user_pac_mask()	GENMASK(54, vabits_actual)
 
 /* Only valid for EL0 TTBR0 instruction pointers */
 static inline unsigned long ptrauth_strip_insn_pac(unsigned long ptr)
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 0e1f2770192a..e4c93945e477 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -43,7 +43,7 @@
  */
 
 #define DEFAULT_MAP_WINDOW_64	(UL(1) << VA_BITS_MIN)
-#define TASK_SIZE_64		(UL(1) << vabits_user)
+#define TASK_SIZE_64		(UL(1) << vabits_actual)
 
 #ifdef CONFIG_COMPAT
 #if defined(CONFIG_ARM64_64K_PAGES) && defined(CONFIG_KUSER_HELPERS)
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index c8446f8c81f5..949b001a73bb 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -316,11 +316,6 @@ __create_page_tables:
 #endif
 	mov	x5, #VA_BITS_MIN
 1:
-	adr_l	x6, vabits_user
-	str	x5, [x6]
-	dmb	sy
-	dc	ivac, x6		// Invalidate potentially stale cache line
-
 	adr_l	x6, vabits_actual
 	str	x5, [x6]
 	dmb	sy
@@ -795,7 +790,7 @@ ENDPROC(__enable_mmu)
 
 ENTRY(__cpu_secondary_check52bitva)
 #ifdef CONFIG_ARM64_VA_BITS_52
-	ldr_l	x0, vabits_user
+	ldr_l	x0, vabits_actual
 	cmp	x0, #52
 	b.ne	2f
 
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 6b195871769a..75eff57bd9ef 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -140,8 +140,7 @@ static void show_pte(unsigned long addr)
 
 	pr_alert("%s pgtable: %luk pages, %llu-bit VAs, pgdp=%016lx\n",
 		 mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K,
-		 mm == &init_mm ? vabits_actual : (int)vabits_user,
-		 (unsigned long)virt_to_phys(mm->pgd));
+		 vabits_actual, (unsigned long)virt_to_phys(mm->pgd));
 	pgdp = pgd_offset(mm, addr);
 	pgd = READ_ONCE(*pgdp);
 	pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd));
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 07b30e6d17f8..0c8f7e55f859 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -40,8 +40,6 @@
 
 u64 idmap_t0sz = TCR_T0SZ(VA_BITS);
 u64 idmap_ptrs_per_pgd = PTRS_PER_PGD;
-u64 vabits_user __ro_after_init;
-EXPORT_SYMBOL(vabits_user);
 
 u64 __section(".mmuoff.data.write") vabits_actual;
 EXPORT_SYMBOL(vabits_actual);
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 8b021c5c0884..391f9cabfe60 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -439,7 +439,7 @@ ENTRY(__cpu_setup)
 	tcr_clear_errata_bits x10, x9, x5
 
 #ifdef CONFIG_ARM64_VA_BITS_52
-	ldr_l		x9, vabits_user
+	ldr_l		x9, vabits_actual
 	sub		x9, xzr, x9
 	add		x9, x9, #64
 	tcr_set_t1sz	x10, x9
-- 
cgit v1.2.3


From d2d73d2fef421ca0d447946cc430fdf5c4c5b06a Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Fri, 9 Aug 2019 15:27:32 +0100
Subject: arm64: mm: Simplify definition of virt_addr_valid()

_virt_addr_valid() is defined as the same value in two places and rolls
its own version of virt_to_pfn() in both cases.

Consolidate these definitions by inlining a simplified version directly
into virt_addr_valid().

Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/memory.h | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index ecc945ba8607..2c3c4b145e95 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -312,7 +312,6 @@ static inline void *phys_to_virt(phys_addr_t x)
 
 #if !defined(CONFIG_SPARSEMEM_VMEMMAP) || defined(CONFIG_DEBUG_VIRTUAL)
 #define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
-#define _virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
 #else
 #define __virt_to_pgoff(kaddr)	(((u64)(kaddr) - PAGE_OFFSET) / PAGE_SIZE * sizeof(struct page))
 #define __page_to_voff(kaddr)	(((u64)(kaddr) - VMEMMAP_START) * PAGE_SIZE / sizeof(struct page))
@@ -326,15 +325,14 @@ static inline void *phys_to_virt(phys_addr_t x)
 })
 
 #define virt_to_page(vaddr)	((struct page *)((__virt_to_pgoff(vaddr)) + VMEMMAP_START))
-
-#define _virt_addr_valid(kaddr)	pfn_valid(__virt_to_phys((u64)(kaddr)) >> PAGE_SHIFT)
 #endif
 #endif
 
 #define _virt_addr_is_linear(kaddr)	\
 	(__tag_reset((u64)(kaddr)) >= PAGE_OFFSET)
+
 #define virt_addr_valid(kaddr)		\
-	(_virt_addr_is_linear(kaddr) && _virt_addr_valid(kaddr))
+	(_virt_addr_is_linear(kaddr) && pfn_valid(virt_to_pfn(kaddr)))
 
 /*
  * Given that the GIC architecture permits ITS implementations that can only be
-- 
cgit v1.2.3


From 9c1cac424c93d2b3122014e07a54b003ddedc168 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Fri, 9 Aug 2019 15:39:37 +0100
Subject: arm64: mm: Really fix sparse warning in untagged_addr()

untagged_addr() can be called with a '__user' pointer parameter and must
therefore use '__force' casts both when passing this parameter through
to sign_extend64() as a 'u64', but also when casting the 's64' return
value back to the '__user' pointer type.

Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/memory.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 46c4c08a80a9..76e0b232a473 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -201,7 +201,7 @@ extern u64			vabits_user;
  * pass on to access_ok(), for instance.
  */
 #define untagged_addr(addr)	\
-	((__typeof__(addr))sign_extend64((__force u64)(addr), 55))
+	((__force __typeof__(addr))sign_extend64((__force u64)(addr), 55))
 
 #ifdef CONFIG_KASAN_SW_TAGS
 #define __tag_shifted(tag)	((u64)(tag) << 56)
-- 
cgit v1.2.3


From 788961462f3471617749edf10d0fcafad410d2bb Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Date: Fri, 9 Aug 2019 12:03:11 +0100
Subject: ARM: psci: cpuidle: Enable PSCI CPUidle driver

Allow selection of the PSCI CPUidle in the kernel by updating
the respective Kconfig entry.

Remove PSCI callbacks from ARM/ARM64 generic CPU ops
to prevent the PSCI idle driver from clashing with the generic
ARM CPUidle driver initialization, that relies on CPU ops
to initialize and enter idle states.

Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Cc: Will Deacon <will@kernel.org>
Cc: Ulf Hansson <ulf.hansson@linaro.org>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/cpuidle.c  |  7 ++++---
 arch/arm64/kernel/psci.c     |  4 ----
 drivers/cpuidle/Kconfig.arm  |  2 +-
 drivers/firmware/psci/psci.c | 10 ----------
 4 files changed, 5 insertions(+), 18 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c
index d1048173fd8a..619e0ebb8399 100644
--- a/arch/arm64/kernel/cpuidle.c
+++ b/arch/arm64/kernel/cpuidle.c
@@ -11,6 +11,7 @@
 #include <linux/cpu_pm.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/psci.h>
 
 #include <asm/cpuidle.h>
 #include <asm/cpu_ops.h>
@@ -48,15 +49,15 @@ int arm_cpuidle_suspend(int index)
 
 int acpi_processor_ffh_lpi_probe(unsigned int cpu)
 {
-	return arm_cpuidle_init(cpu);
+	return psci_cpu_init_idle(cpu);
 }
 
 int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi)
 {
 	if (ARM64_LPI_IS_RETENTION_STATE(lpi->arch_flags))
-		return CPU_PM_CPU_IDLE_ENTER_RETENTION(arm_cpuidle_suspend,
+		return CPU_PM_CPU_IDLE_ENTER_RETENTION(psci_cpu_suspend_enter,
 						lpi->index);
 	else
-		return CPU_PM_CPU_IDLE_ENTER(arm_cpuidle_suspend, lpi->index);
+		return CPU_PM_CPU_IDLE_ENTER(psci_cpu_suspend_enter, lpi->index);
 }
 #endif
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index 85ee7d07889e..a543ab7e007c 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -105,10 +105,6 @@ static int cpu_psci_cpu_kill(unsigned int cpu)
 
 const struct cpu_operations cpu_psci_ops = {
 	.name		= "psci",
-#ifdef CONFIG_CPU_IDLE
-	.cpu_init_idle	= psci_cpu_init_idle,
-	.cpu_suspend	= psci_cpu_suspend_enter,
-#endif
 	.cpu_init	= cpu_psci_cpu_init,
 	.cpu_prepare	= cpu_psci_cpu_prepare,
 	.cpu_boot	= cpu_psci_cpu_boot,
diff --git a/drivers/cpuidle/Kconfig.arm b/drivers/cpuidle/Kconfig.arm
index eb014aa5ce6b..d8530475493c 100644
--- a/drivers/cpuidle/Kconfig.arm
+++ b/drivers/cpuidle/Kconfig.arm
@@ -14,7 +14,7 @@ config ARM_CPUIDLE
           provided by architecture code.
 
 config ARM_PSCI_CPUIDLE
-	bool
+	bool "PSCI CPU idle Driver"
 	depends on ARM_PSCI_FW
 	select DT_IDLE_STATES
 	select CPU_IDLE_MULTIPLE_DRIVERS
diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c
index f82ccd39a913..b343f8a34c6a 100644
--- a/drivers/firmware/psci/psci.c
+++ b/drivers/firmware/psci/psci.c
@@ -436,16 +436,6 @@ int psci_cpu_suspend_enter(unsigned long index)
 
 	return ret;
 }
-
-/* ARM specific CPU idle operations */
-#ifdef CONFIG_ARM
-static const struct cpuidle_ops psci_cpuidle_ops __initconst = {
-	.suspend = psci_cpu_suspend_enter,
-	.init = psci_dt_cpu_init_idle,
-};
-
-CPUIDLE_METHOD_OF_DECLARE(psci, "psci", &psci_cpuidle_ops);
-#endif
 #endif
 
 static int psci_system_suspend(unsigned long unused)
-- 
cgit v1.2.3


From 9ffeb6d08c3a4bbd7b1e33711b241f511e2ded79 Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Date: Fri, 9 Aug 2019 12:03:12 +0100
Subject: PSCI: cpuidle: Refactor CPU suspend power_state parameter handling

Current PSCI code handles idle state entry through the
psci_cpu_suspend_enter() API, that takes an idle state index as a
parameter and convert the index into a previously initialized
power_state parameter before calling the PSCI.CPU_SUSPEND() with it.

This is unwieldly, since it forces the PSCI firmware layer to keep track
of power_state parameter for every idle state so that the
index->power_state conversion can be made in the PSCI firmware layer
instead of the CPUidle driver implementations.

Move the power_state handling out of drivers/firmware/psci
into the respective ACPI/DT PSCI CPUidle backends and convert
the psci_cpu_suspend_enter() API to get the power_state
parameter as input, which makes it closer to its firmware
interface PSCI.CPU_SUSPEND() API.

A notable side effect is that the PSCI ACPI/DT CPUidle backends
now can directly handle (and if needed update) power_state
parameters before handing them over to the PSCI firmware
interface to trigger PSCI.CPU_SUSPEND() calls.

Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Sudeep Holla <sudeep.holla@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Ulf Hansson <ulf.hansson@linaro.org>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/cpuidle.c    |  49 +++++++++++--
 drivers/cpuidle/cpuidle-psci.c |  87 ++++++++++++++++++++++-
 drivers/firmware/psci/psci.c   | 157 +++--------------------------------------
 include/linux/cpuidle.h        |  17 +++--
 include/linux/psci.h           |   4 +-
 5 files changed, 154 insertions(+), 160 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c
index 619e0ebb8399..e4d6af2fdec7 100644
--- a/arch/arm64/kernel/cpuidle.c
+++ b/arch/arm64/kernel/cpuidle.c
@@ -47,17 +47,58 @@ int arm_cpuidle_suspend(int index)
 
 #define ARM64_LPI_IS_RETENTION_STATE(arch_flags) (!(arch_flags))
 
+static int psci_acpi_cpu_init_idle(unsigned int cpu)
+{
+	int i, count;
+	struct acpi_lpi_state *lpi;
+	struct acpi_processor *pr = per_cpu(processors, cpu);
+
+	/*
+	 * If the PSCI cpu_suspend function hook has not been initialized
+	 * idle states must not be enabled, so bail out
+	 */
+	if (!psci_ops.cpu_suspend)
+		return -EOPNOTSUPP;
+
+	if (unlikely(!pr || !pr->flags.has_lpi))
+		return -EINVAL;
+
+	count = pr->power.count - 1;
+	if (count <= 0)
+		return -ENODEV;
+
+	for (i = 0; i < count; i++) {
+		u32 state;
+
+		lpi = &pr->power.lpi_states[i + 1];
+		/*
+		 * Only bits[31:0] represent a PSCI power_state while
+		 * bits[63:32] must be 0x0 as per ARM ACPI FFH Specification
+		 */
+		state = lpi->address;
+		if (!psci_power_state_is_valid(state)) {
+			pr_warn("Invalid PSCI power state %#x\n", state);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 int acpi_processor_ffh_lpi_probe(unsigned int cpu)
 {
-	return psci_cpu_init_idle(cpu);
+	return psci_acpi_cpu_init_idle(cpu);
 }
 
 int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi)
 {
+	u32 state = lpi->address;
+
 	if (ARM64_LPI_IS_RETENTION_STATE(lpi->arch_flags))
-		return CPU_PM_CPU_IDLE_ENTER_RETENTION(psci_cpu_suspend_enter,
-						lpi->index);
+		return CPU_PM_CPU_IDLE_ENTER_RETENTION_PARAM(psci_cpu_suspend_enter,
+						lpi->index, state);
 	else
-		return CPU_PM_CPU_IDLE_ENTER(psci_cpu_suspend_enter, lpi->index);
+		return CPU_PM_CPU_IDLE_ENTER_PARAM(psci_cpu_suspend_enter,
+					     lpi->index, state);
 }
 #endif
diff --git a/drivers/cpuidle/cpuidle-psci.c b/drivers/cpuidle/cpuidle-psci.c
index ab1dea918ea3..f3c1a2396f98 100644
--- a/drivers/cpuidle/cpuidle-psci.c
+++ b/drivers/cpuidle/cpuidle-psci.c
@@ -22,10 +22,15 @@
 
 #include "dt_idle_states.h"
 
+static DEFINE_PER_CPU_READ_MOSTLY(u32 *, psci_power_state);
+
 static int psci_enter_idle_state(struct cpuidle_device *dev,
 				struct cpuidle_driver *drv, int idx)
 {
-	return CPU_PM_CPU_IDLE_ENTER(psci_cpu_suspend_enter, idx);
+	u32 *state = __this_cpu_read(psci_power_state);
+
+	return CPU_PM_CPU_IDLE_ENTER_PARAM(psci_cpu_suspend_enter,
+					   idx, state[idx - 1]);
 }
 
 static struct cpuidle_driver psci_idle_driver __initdata = {
@@ -51,6 +56,86 @@ static const struct of_device_id psci_idle_state_match[] __initconst = {
 	{ },
 };
 
+static int __init psci_dt_parse_state_node(struct device_node *np, u32 *state)
+{
+	int err = of_property_read_u32(np, "arm,psci-suspend-param", state);
+
+	if (err) {
+		pr_warn("%pOF missing arm,psci-suspend-param property\n", np);
+		return err;
+	}
+
+	if (!psci_power_state_is_valid(*state)) {
+		pr_warn("Invalid PSCI power state %#x\n", *state);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int __init psci_dt_cpu_init_idle(struct device_node *cpu_node, int cpu)
+{
+	int i, ret = 0, count = 0;
+	u32 *psci_states;
+	struct device_node *state_node;
+
+	/* Count idle states */
+	while ((state_node = of_parse_phandle(cpu_node, "cpu-idle-states",
+					      count))) {
+		count++;
+		of_node_put(state_node);
+	}
+
+	if (!count)
+		return -ENODEV;
+
+	psci_states = kcalloc(count, sizeof(*psci_states), GFP_KERNEL);
+	if (!psci_states)
+		return -ENOMEM;
+
+	for (i = 0; i < count; i++) {
+		state_node = of_parse_phandle(cpu_node, "cpu-idle-states", i);
+		ret = psci_dt_parse_state_node(state_node, &psci_states[i]);
+		of_node_put(state_node);
+
+		if (ret)
+			goto free_mem;
+
+		pr_debug("psci-power-state %#x index %d\n", psci_states[i], i);
+	}
+
+	/* Idle states parsed correctly, initialize per-cpu pointer */
+	per_cpu(psci_power_state, cpu) = psci_states;
+	return 0;
+
+free_mem:
+	kfree(psci_states);
+	return ret;
+}
+
+static __init int psci_cpu_init_idle(unsigned int cpu)
+{
+	struct device_node *cpu_node;
+	int ret;
+
+	/*
+	 * If the PSCI cpu_suspend function hook has not been initialized
+	 * idle states must not be enabled, so bail out
+	 */
+	if (!psci_ops.cpu_suspend)
+		return -EOPNOTSUPP;
+
+	cpu_node = of_cpu_device_node_get(cpu);
+	if (!cpu_node)
+		return -ENODEV;
+
+	ret = psci_dt_cpu_init_idle(cpu_node, cpu);
+
+	of_node_put(cpu_node);
+
+	return ret;
+}
+
 static int __init psci_idle_init_cpu(int cpu)
 {
 	struct cpuidle_driver *drv;
diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c
index b343f8a34c6a..84f4ff351c62 100644
--- a/drivers/firmware/psci/psci.c
+++ b/drivers/firmware/psci/psci.c
@@ -103,7 +103,7 @@ static inline bool psci_power_state_loses_context(u32 state)
 	return state & mask;
 }
 
-static inline bool psci_power_state_is_valid(u32 state)
+bool psci_power_state_is_valid(u32 state)
 {
 	const u32 valid_mask = psci_has_ext_power_state() ?
 			       PSCI_1_0_EXT_POWER_STATE_MASK :
@@ -277,162 +277,21 @@ static int __init psci_features(u32 psci_func_id)
 }
 
 #ifdef CONFIG_CPU_IDLE
-static DEFINE_PER_CPU_READ_MOSTLY(u32 *, psci_power_state);
-
-static int psci_dt_parse_state_node(struct device_node *np, u32 *state)
-{
-	int err = of_property_read_u32(np, "arm,psci-suspend-param", state);
-
-	if (err) {
-		pr_warn("%pOF missing arm,psci-suspend-param property\n", np);
-		return err;
-	}
-
-	if (!psci_power_state_is_valid(*state)) {
-		pr_warn("Invalid PSCI power state %#x\n", *state);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int psci_dt_cpu_init_idle(struct device_node *cpu_node, int cpu)
-{
-	int i, ret = 0, count = 0;
-	u32 *psci_states;
-	struct device_node *state_node;
-
-	/* Count idle states */
-	while ((state_node = of_parse_phandle(cpu_node, "cpu-idle-states",
-					      count))) {
-		count++;
-		of_node_put(state_node);
-	}
-
-	if (!count)
-		return -ENODEV;
-
-	psci_states = kcalloc(count, sizeof(*psci_states), GFP_KERNEL);
-	if (!psci_states)
-		return -ENOMEM;
-
-	for (i = 0; i < count; i++) {
-		state_node = of_parse_phandle(cpu_node, "cpu-idle-states", i);
-		ret = psci_dt_parse_state_node(state_node, &psci_states[i]);
-		of_node_put(state_node);
-
-		if (ret)
-			goto free_mem;
-
-		pr_debug("psci-power-state %#x index %d\n", psci_states[i], i);
-	}
-
-	/* Idle states parsed correctly, initialize per-cpu pointer */
-	per_cpu(psci_power_state, cpu) = psci_states;
-	return 0;
-
-free_mem:
-	kfree(psci_states);
-	return ret;
-}
-
-#ifdef CONFIG_ACPI
-#include <acpi/processor.h>
-
-static int __maybe_unused psci_acpi_cpu_init_idle(unsigned int cpu)
-{
-	int i, count;
-	u32 *psci_states;
-	struct acpi_lpi_state *lpi;
-	struct acpi_processor *pr = per_cpu(processors, cpu);
-
-	if (unlikely(!pr || !pr->flags.has_lpi))
-		return -EINVAL;
-
-	count = pr->power.count - 1;
-	if (count <= 0)
-		return -ENODEV;
-
-	psci_states = kcalloc(count, sizeof(*psci_states), GFP_KERNEL);
-	if (!psci_states)
-		return -ENOMEM;
-
-	for (i = 0; i < count; i++) {
-		u32 state;
-
-		lpi = &pr->power.lpi_states[i + 1];
-		/*
-		 * Only bits[31:0] represent a PSCI power_state while
-		 * bits[63:32] must be 0x0 as per ARM ACPI FFH Specification
-		 */
-		state = lpi->address;
-		if (!psci_power_state_is_valid(state)) {
-			pr_warn("Invalid PSCI power state %#x\n", state);
-			kfree(psci_states);
-			return -EINVAL;
-		}
-		psci_states[i] = state;
-	}
-	/* Idle states parsed correctly, initialize per-cpu pointer */
-	per_cpu(psci_power_state, cpu) = psci_states;
-	return 0;
-}
-#else
-static int __maybe_unused psci_acpi_cpu_init_idle(unsigned int cpu)
-{
-	return -EINVAL;
-}
-#endif
-
-int psci_cpu_init_idle(unsigned int cpu)
-{
-	struct device_node *cpu_node;
-	int ret;
-
-	/*
-	 * If the PSCI cpu_suspend function hook has not been initialized
-	 * idle states must not be enabled, so bail out
-	 */
-	if (!psci_ops.cpu_suspend)
-		return -EOPNOTSUPP;
-
-	if (!acpi_disabled)
-		return psci_acpi_cpu_init_idle(cpu);
-
-	cpu_node = of_get_cpu_node(cpu, NULL);
-	if (!cpu_node)
-		return -ENODEV;
-
-	ret = psci_dt_cpu_init_idle(cpu_node, cpu);
-
-	of_node_put(cpu_node);
-
-	return ret;
-}
-
-static int psci_suspend_finisher(unsigned long index)
+static int psci_suspend_finisher(unsigned long state)
 {
-	u32 *state = __this_cpu_read(psci_power_state);
+	u32 power_state = state;
 
-	return psci_ops.cpu_suspend(state[index - 1],
-				    __pa_symbol(cpu_resume));
+	return psci_ops.cpu_suspend(power_state, __pa_symbol(cpu_resume));
 }
 
-int psci_cpu_suspend_enter(unsigned long index)
+int psci_cpu_suspend_enter(u32 state)
 {
 	int ret;
-	u32 *state = __this_cpu_read(psci_power_state);
-	/*
-	 * idle state index 0 corresponds to wfi, should never be called
-	 * from the cpu_suspend operations
-	 */
-	if (WARN_ON_ONCE(!index))
-		return -EINVAL;
 
-	if (!psci_power_state_loses_context(state[index - 1]))
-		ret = psci_ops.cpu_suspend(state[index - 1], 0);
+	if (!psci_power_state_loses_context(state))
+		ret = psci_ops.cpu_suspend(state, 0);
 	else
-		ret = cpu_suspend(index, psci_suspend_finisher);
+		ret = cpu_suspend(state, psci_suspend_finisher);
 
 	return ret;
 }
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index bb9a0db89f1a..12ae4b87494e 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -256,7 +256,10 @@ static inline int cpuidle_register_governor(struct cpuidle_governor *gov)
 {return 0;}
 #endif
 
-#define __CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx, is_retention) \
+#define __CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter,			\
+				idx,					\
+				state,					\
+				is_retention)				\
 ({									\
 	int __ret = 0;							\
 									\
@@ -268,7 +271,7 @@ static inline int cpuidle_register_governor(struct cpuidle_governor *gov)
 	if (!is_retention)						\
 		__ret =  cpu_pm_enter();				\
 	if (!__ret) {							\
-		__ret = low_level_idle_enter(idx);			\
+		__ret = low_level_idle_enter(state);			\
 		if (!is_retention)					\
 			cpu_pm_exit();					\
 	}								\
@@ -277,9 +280,15 @@ static inline int cpuidle_register_governor(struct cpuidle_governor *gov)
 })
 
 #define CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx)	\
-	__CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx, 0)
+	__CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx, idx, 0)
 
 #define CPU_PM_CPU_IDLE_ENTER_RETENTION(low_level_idle_enter, idx)	\
-	__CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx, 1)
+	__CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx, idx, 1)
+
+#define CPU_PM_CPU_IDLE_ENTER_PARAM(low_level_idle_enter, idx, state)	\
+	__CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx, state, 0)
+
+#define CPU_PM_CPU_IDLE_ENTER_RETENTION_PARAM(low_level_idle_enter, idx, state)	\
+	__CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx, state, 1)
 
 #endif /* _LINUX_CPUIDLE_H */
diff --git a/include/linux/psci.h b/include/linux/psci.h
index a8a15613c157..e2bacc6fd2f2 100644
--- a/include/linux/psci.h
+++ b/include/linux/psci.h
@@ -15,8 +15,8 @@
 
 bool psci_tos_resident_on(int cpu);
 
-int psci_cpu_init_idle(unsigned int cpu);
-int psci_cpu_suspend_enter(unsigned long index);
+int psci_cpu_suspend_enter(u32 state);
+bool psci_power_state_is_valid(u32 state);
 
 enum psci_conduit {
 	PSCI_CONDUIT_NONE,
-- 
cgit v1.2.3


From 98dc19902a0b2e5348e43d6a2c39a0a7d0fc639e Mon Sep 17 00:00:00 2001
From: Jeremy Linton <jeremy.linton@arm.com>
Date: Thu, 8 Aug 2019 15:40:07 -0500
Subject: arm64: topology: Use PPTT to determine if PE is a thread

ACPI 6.3 adds a thread flag to represent if a CPU/PE is
actually a thread. Given that the MPIDR_MT bit may not
represent this information consistently on homogeneous machines
we should prefer the PPTT flag if its available.

Signed-off-by: Jeremy Linton <jeremy.linton@arm.com>
Reviewed-by: Sudeep Holla <sudeep.holla@arm.com>
Reviewed-by: Robert Richter <rrichter@marvell.com>
[will: made acpi_cpu_is_threaded() return 'bool']
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/topology.c | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 0825c4a856e3..6106c49f84bc 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -340,17 +340,28 @@ void remove_cpu_topology(unsigned int cpu)
 }
 
 #ifdef CONFIG_ACPI
+static bool __init acpi_cpu_is_threaded(int cpu)
+{
+	int is_threaded = acpi_pptt_cpu_is_thread(cpu);
+
+	/*
+	 * if the PPTT doesn't have thread information, assume a homogeneous
+	 * machine and return the current CPU's thread state.
+	 */
+	if (is_threaded < 0)
+		is_threaded = read_cpuid_mpidr() & MPIDR_MT_BITMASK;
+
+	return !!is_threaded;
+}
+
 /*
  * Propagate the topology information of the processor_topology_node tree to the
  * cpu_topology array.
  */
 static int __init parse_acpi_topology(void)
 {
-	bool is_threaded;
 	int cpu, topology_id;
 
-	is_threaded = read_cpuid_mpidr() & MPIDR_MT_BITMASK;
-
 	for_each_possible_cpu(cpu) {
 		int i, cache_id;
 
@@ -358,7 +369,7 @@ static int __init parse_acpi_topology(void)
 		if (topology_id < 0)
 			return topology_id;
 
-		if (is_threaded) {
+		if (acpi_cpu_is_threaded(cpu)) {
 			cpu_topology[cpu].thread_id = topology_id;
 			topology_id = find_acpi_cpu_topology(cpu, 1);
 			cpu_topology[cpu].core_id   = topology_id;
-- 
cgit v1.2.3


From 68dd8ef321626f14ae9ef2039b7a03c707149489 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 13 Aug 2019 15:52:23 +0100
Subject: arm64: memory: Fix virt_addr_valid() using __is_lm_address()

virt_addr_valid() is intended to test whether or not the passed address
is a valid linear map address. Unfortunately, it relies on
_virt_addr_is_linear() which is broken because it assumes the linear
map is at the top of the address space, which it no longer is.

Reimplement virt_addr_valid() using __is_lm_address() and remove
_virt_addr_is_linear() entirely. At the same time, ensure we evaluate
the macro parameter only once and move it within the __ASSEMBLY__ block.

Reported-by: Qian Cai <cai@lca.pw>
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Tested-by: Steve Capper <steve.capper@arm.com>
Reviewed-by: Steve Capper <steve.capper@arm.com>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Fixes: 14c127c957c1 ("arm64: mm: Flip kernel VA space")
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/memory.h | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 2c3c4b145e95..93ef8e5c6971 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -242,11 +242,11 @@ static inline const void *__tag_set(const void *addr, u8 tag)
 
 
 /*
- * The linear kernel range starts in the middle of the virtual adddress
+ * The linear kernel range starts at the bottom of the virtual address
  * space. Testing the top bit for the start of the region is a
- * sufficient check.
+ * sufficient check and avoids having to worry about the tag.
  */
-#define __is_lm_address(addr)	(!((addr) & BIT(vabits_actual - 1)))
+#define __is_lm_address(addr)	(!(((u64)addr) & BIT(vabits_actual - 1)))
 
 #define __lm_to_phys(addr)	(((addr) + physvirt_offset))
 #define __kimg_to_phys(addr)	((addr) - kimage_voffset)
@@ -326,13 +326,13 @@ static inline void *phys_to_virt(phys_addr_t x)
 
 #define virt_to_page(vaddr)	((struct page *)((__virt_to_pgoff(vaddr)) + VMEMMAP_START))
 #endif
-#endif
 
-#define _virt_addr_is_linear(kaddr)	\
-	(__tag_reset((u64)(kaddr)) >= PAGE_OFFSET)
+#define virt_addr_valid(addr)	({					\
+	__typeof__(addr) __addr = addr;					\
+	__is_lm_address(__addr) && pfn_valid(virt_to_pfn(__addr));	\
+})
 
-#define virt_addr_valid(kaddr)		\
-	(_virt_addr_is_linear(kaddr) && pfn_valid(virt_to_pfn(kaddr)))
+#endif
 
 /*
  * Given that the GIC architecture permits ITS implementations that can only be
-- 
cgit v1.2.3


From 577c2b35283fbadcc9ce4b56304ccea3ec8a5ca1 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 13 Aug 2019 16:26:54 +0100
Subject: arm64: memory: Ensure address tag is masked in conversion macros

When converting a linear virtual address to a physical address, pfn or
struct page *, we must make sure that the tag bits are masked before the
calculation otherwise we end up with corrupt pointers when running with
CONFIG_KASAN_SW_TAGS=y:

  | Unable to handle kernel paging request at virtual address 0037fe0007580d08
  | [0037fe0007580d08] address between user and kernel address ranges

Mask out the tag in __virt_to_phys_nodebug() and virt_to_page().

Reported-by: Qian Cai <cai@lca.pw>
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Tested-by: Steve Capper <steve.capper@arm.com>
Reviewed-by: Steve Capper <steve.capper@arm.com>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Fixes: 9cb1c5ddd2c4 ("arm64: mm: Remove bit-masking optimisations for PAGE_OFFSET and VMEMMAP_START")
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/memory.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 93ef8e5c6971..243e05ad4a67 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -252,7 +252,7 @@ static inline const void *__tag_set(const void *addr, u8 tag)
 #define __kimg_to_phys(addr)	((addr) - kimage_voffset)
 
 #define __virt_to_phys_nodebug(x) ({					\
-	phys_addr_t __x = (phys_addr_t)(x);				\
+	phys_addr_t __x = (phys_addr_t)(__tag_reset(x));		\
 	__is_lm_address(__x) ? __lm_to_phys(__x) :			\
 			       __kimg_to_phys(__x);			\
 })
@@ -324,7 +324,8 @@ static inline void *phys_to_virt(phys_addr_t x)
 	((void *)__addr_tag);						\
 })
 
-#define virt_to_page(vaddr)	((struct page *)((__virt_to_pgoff(vaddr)) + VMEMMAP_START))
+#define virt_to_page(vaddr)	\
+	((struct page *)((__virt_to_pgoff(__tag_reset(vaddr))) + VMEMMAP_START))
 #endif
 
 #define virt_addr_valid(addr)	({					\
-- 
cgit v1.2.3


From 96628f0fb18080a4166fc9eab8f7fd062d860667 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 13 Aug 2019 16:46:11 +0100
Subject: arm64: memory: Rewrite default page_to_virt()/virt_to_page()

The default implementations of page_to_virt() and virt_to_page() are
fairly confusing to read and the former evaluates its 'page' parameter
twice in the macro

Rewrite them so that the computation is expressed as 'base + index' in
both cases and the parameter is always evaluated exactly once.

Tested-by: Steve Capper <steve.capper@arm.com>
Reviewed-by: Steve Capper <steve.capper@arm.com>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/memory.h | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 243e05ad4a67..636d414608cb 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -313,19 +313,18 @@ static inline void *phys_to_virt(phys_addr_t x)
 #if !defined(CONFIG_SPARSEMEM_VMEMMAP) || defined(CONFIG_DEBUG_VIRTUAL)
 #define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
 #else
-#define __virt_to_pgoff(kaddr)	(((u64)(kaddr) - PAGE_OFFSET) / PAGE_SIZE * sizeof(struct page))
-#define __page_to_voff(kaddr)	(((u64)(kaddr) - VMEMMAP_START) * PAGE_SIZE / sizeof(struct page))
-
-#define page_to_virt(page)	({					\
-	unsigned long __addr =						\
-		((__page_to_voff(page)) + PAGE_OFFSET);			\
-	const void *__addr_tag =					\
-		__tag_set((void *)__addr, page_kasan_tag(page));	\
-	((void *)__addr_tag);						\
+#define page_to_virt(x)	({						\
+	__typeof__(x) __page = x;					\
+	u64 __idx = ((u64)__page - VMEMMAP_START) / sizeof(struct page);\
+	u64 __addr = PAGE_OFFSET + (__idx * PAGE_SIZE);			\
+	(void *)__tag_set((const void *)__addr, page_kasan_tag(__page));\
 })
 
-#define virt_to_page(vaddr)	\
-	((struct page *)((__virt_to_pgoff(__tag_reset(vaddr))) + VMEMMAP_START))
+#define virt_to_page(x)	({						\
+	u64 __idx = (__tag_reset((u64)x) - PAGE_OFFSET) / PAGE_SIZE;	\
+	u64 __addr = VMEMMAP_START + (__idx * sizeof(struct page));	\
+	(struct page *)__addr;						\
+})
 #endif
 
 #define virt_addr_valid(addr)	({					\
-- 
cgit v1.2.3


From 9ba33dcc6bef4e56c762b446f0000f27ee737b8b Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 13 Aug 2019 16:34:32 +0100
Subject: arm64: memory: Simplify virt_to_page() implementation

Build virt_to_page() on top of virt_to_pfn() so we can avoid the need
for explicit shifting.

Tested-by: Steve Capper <steve.capper@arm.com>
Reviewed-by: Steve Capper <steve.capper@arm.com>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/memory.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 636d414608cb..e6353d1a75fa 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -311,7 +311,7 @@ static inline void *phys_to_virt(phys_addr_t x)
 #define ARCH_PFN_OFFSET		((unsigned long)PHYS_PFN_OFFSET)
 
 #if !defined(CONFIG_SPARSEMEM_VMEMMAP) || defined(CONFIG_DEBUG_VIRTUAL)
-#define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
+#define virt_to_page(kaddr)	pfn_to_page(virt_to_pfn(kaddr))
 #else
 #define page_to_virt(x)	({						\
 	__typeof__(x) __page = x;					\
-- 
cgit v1.2.3


From a5ac40f53bfa5e43d9c76e3c23415ee4afd71932 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 13 Aug 2019 16:58:36 +0100
Subject: arm64: memory: Simplify _VA_START and _PAGE_OFFSET definitions

Rather than subtracting from -1 and then adding 1, we can simply
subtract from 0.

Tested-by: Steve Capper <steve.capper@arm.com>
Reviewed-by: Steve Capper <steve.capper@arm.com>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/memory.h | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index e6353d1a75fa..a7a985602cba 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -44,8 +44,7 @@
  * VA_START - the first kernel virtual address.
  */
 #define VA_BITS			(CONFIG_ARM64_VA_BITS)
-#define _PAGE_OFFSET(va)	(UL(0xffffffffffffffff) - \
-					(UL(1) << (va)) + 1)
+#define _PAGE_OFFSET(va)	(-(UL(1) << (va)))
 #define PAGE_OFFSET		(_PAGE_OFFSET(VA_BITS))
 #define KIMAGE_VADDR		(MODULES_END)
 #define BPF_JIT_REGION_START	(KASAN_SHADOW_END)
@@ -63,8 +62,7 @@
 #else
 #define VA_BITS_MIN		(VA_BITS)
 #endif
-#define _VA_START(va)		(UL(0xffffffffffffffff) - \
-				(UL(1) << ((va) - 1)) + 1)
+#define _VA_START(va)		(-(UL(1) << ((va) - 1)))
 
 #define KERNEL_START      _text
 #define KERNEL_END        _end
-- 
cgit v1.2.3


From 6bbd497f027332b14cf2a6792c418c32286b66c2 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 13 Aug 2019 17:01:05 +0100
Subject: arm64: memory: Implement __tag_set() as common function

There's no need for __tag_set() to be a complicated macro when
CONFIG_KASAN_SW_TAGS=y and a simple static inline otherwise. Rewrite
the thing as a common static inline function.

Tested-by: Steve Capper <steve.capper@arm.com>
Reviewed-by: Steve Capper <steve.capper@arm.com>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/memory.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index a7a985602cba..fb0062555305 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -218,20 +218,20 @@ static inline unsigned long kaslr_offset(void)
 
 #ifdef CONFIG_KASAN_SW_TAGS
 #define __tag_shifted(tag)	((u64)(tag) << 56)
-#define __tag_set(addr, tag)	(__typeof__(addr))( \
-		((u64)(addr) & ~__tag_shifted(0xff)) | __tag_shifted(tag))
 #define __tag_reset(addr)	untagged_addr(addr)
 #define __tag_get(addr)		(__u8)((u64)(addr) >> 56)
 #else
-static inline const void *__tag_set(const void *addr, u8 tag)
-{
-	return addr;
-}
-
+#define __tag_shifted(tag)	0UL
 #define __tag_reset(addr)	(addr)
 #define __tag_get(addr)		0
 #endif
 
+static inline const void *__tag_set(const void *addr, u8 tag)
+{
+	u64 __addr = (u64)addr & ~__tag_shifted(0xff);
+	return (const void *)(__addr | __tag_shifted(tag));
+}
+
 /*
  * Physical vs virtual RAM address space conversion.  These are
  * private definitions which should NOT be used outside memory.h
-- 
cgit v1.2.3


From 68933aa973740796895e297e7dbf7baf3e9c51b1 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 13 Aug 2019 17:06:29 +0100
Subject: arm64: memory: Add comments to end of non-trivial #ifdef blocks

Commenting the #endif of a multi-statement #ifdef block with the
condition which guards it is useful and can save having to scroll back
through the file to figure out which set of Kconfig options apply to
a particular piece of code.

Reviewed-by: Steve Capper <steve.capper@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/memory.h | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index fb0062555305..27f35ce2e2ed 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -57,11 +57,13 @@
 #define PCI_IO_END		(VMEMMAP_START - SZ_2M)
 #define PCI_IO_START		(PCI_IO_END - PCI_IO_SIZE)
 #define FIXADDR_TOP		(PCI_IO_START - SZ_2M)
+
 #if VA_BITS > 48
 #define VA_BITS_MIN		(48)
 #else
 #define VA_BITS_MIN		(VA_BITS)
 #endif
+
 #define _VA_START(va)		(-(UL(1) << ((va) - 1)))
 
 #define KERNEL_START      _text
@@ -86,7 +88,7 @@
 #else
 #define KASAN_THREAD_SHIFT	0
 #define KASAN_SHADOW_END	(_VA_START(VA_BITS_MIN))
-#endif
+#endif /* CONFIG_KASAN */
 
 #define MIN_THREAD_SHIFT	(14 + KASAN_THREAD_SHIFT)
 
@@ -224,7 +226,7 @@ static inline unsigned long kaslr_offset(void)
 #define __tag_shifted(tag)	0UL
 #define __tag_reset(addr)	(addr)
 #define __tag_get(addr)		0
-#endif
+#endif /* CONFIG_KASAN_SW_TAGS */
 
 static inline const void *__tag_set(const void *addr, u8 tag)
 {
@@ -263,7 +265,7 @@ extern phys_addr_t __phys_addr_symbol(unsigned long x);
 #else
 #define __virt_to_phys(x)	__virt_to_phys_nodebug(x)
 #define __phys_addr_symbol(x)	__pa_symbol_nodebug(x)
-#endif
+#endif /* CONFIG_DEBUG_VIRTUAL */
 
 #define __phys_to_virt(x)	((unsigned long)((x) - physvirt_offset))
 #define __phys_to_kimg(x)	((unsigned long)((x) + kimage_voffset))
@@ -323,14 +325,14 @@ static inline void *phys_to_virt(phys_addr_t x)
 	u64 __addr = VMEMMAP_START + (__idx * sizeof(struct page));	\
 	(struct page *)__addr;						\
 })
-#endif
+#endif /* !CONFIG_SPARSEMEM_VMEMMAP || CONFIG_DEBUG_VIRTUAL */
 
 #define virt_addr_valid(addr)	({					\
 	__typeof__(addr) __addr = addr;					\
 	__is_lm_address(__addr) && pfn_valid(virt_to_pfn(__addr));	\
 })
 
-#endif
+#endif /* !ASSEMBLY */
 
 /*
  * Given that the GIC architecture permits ITS implementations that can only be
@@ -345,4 +347,4 @@ static inline void *phys_to_virt(phys_addr_t x)
 
 #include <asm-generic/memory_model.h>
 
-#endif
+#endif /* __ASM_MEMORY_H */
-- 
cgit v1.2.3


From d0b3c32ed9220616548ff63808751cf2f6608df1 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 13 Aug 2019 17:22:51 +0100
Subject: arm64: memory: Cosmetic cleanups

Cleanup memory.h so that the indentation is consistent, remove pointless
line-wrapping and use consistent parameter names for different versions
of the same macro.

Reviewed-by: Steve Capper <steve.capper@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/memory.h | 23 +++++++++++------------
 1 file changed, 11 insertions(+), 12 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 27f35ce2e2ed..d69c2865ae40 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -12,10 +12,10 @@
 
 #include <linux/compiler.h>
 #include <linux/const.h>
+#include <linux/sizes.h>
 #include <linux/types.h>
 #include <asm/bug.h>
 #include <asm/page-def.h>
-#include <linux/sizes.h>
 
 /*
  * Size of the PCI I/O space. This must remain a power of two so that
@@ -66,8 +66,8 @@
 
 #define _VA_START(va)		(-(UL(1) << ((va) - 1)))
 
-#define KERNEL_START      _text
-#define KERNEL_END        _end
+#define KERNEL_START		_text
+#define KERNEL_END		_end
 
 #ifdef CONFIG_ARM64_VA_BITS_52
 #define MAX_USER_VA_BITS	52
@@ -132,14 +132,14 @@
  * 16 KB granule: 128 level 3 entries, with contiguous bit
  * 64 KB granule:  32 level 3 entries, with contiguous bit
  */
-#define SEGMENT_ALIGN			SZ_2M
+#define SEGMENT_ALIGN		SZ_2M
 #else
 /*
  *  4 KB granule:  16 level 3 entries, with contiguous bit
  * 16 KB granule:   4 level 3 entries, without contiguous bit
  * 64 KB granule:   1 level 3 entry
  */
-#define SEGMENT_ALIGN			SZ_64K
+#define SEGMENT_ALIGN		SZ_64K
 #endif
 
 /*
@@ -253,8 +253,7 @@ static inline const void *__tag_set(const void *addr, u8 tag)
 
 #define __virt_to_phys_nodebug(x) ({					\
 	phys_addr_t __x = (phys_addr_t)(__tag_reset(x));		\
-	__is_lm_address(__x) ? __lm_to_phys(__x) :			\
-			       __kimg_to_phys(__x);			\
+	__is_lm_address(__x) ? __lm_to_phys(__x) : __kimg_to_phys(__x);	\
 })
 
 #define __pa_symbol_nodebug(x)	__kimg_to_phys((phys_addr_t)(x))
@@ -301,17 +300,17 @@ static inline void *phys_to_virt(phys_addr_t x)
 #define __pa_nodebug(x)		__virt_to_phys_nodebug((unsigned long)(x))
 #define __va(x)			((void *)__phys_to_virt((phys_addr_t)(x)))
 #define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
-#define virt_to_pfn(x)      __phys_to_pfn(__virt_to_phys((unsigned long)(x)))
-#define sym_to_pfn(x)	    __phys_to_pfn(__pa_symbol(x))
+#define virt_to_pfn(x)		__phys_to_pfn(__virt_to_phys((unsigned long)(x)))
+#define sym_to_pfn(x)		__phys_to_pfn(__pa_symbol(x))
 
 /*
- *  virt_to_page(k)	convert a _valid_ virtual address to struct page *
- *  virt_addr_valid(k)	indicates whether a virtual address is valid
+ *  virt_to_page(x)	convert a _valid_ virtual address to struct page *
+ *  virt_addr_valid(x)	indicates whether a virtual address is valid
  */
 #define ARCH_PFN_OFFSET		((unsigned long)PHYS_PFN_OFFSET)
 
 #if !defined(CONFIG_SPARSEMEM_VMEMMAP) || defined(CONFIG_DEBUG_VIRTUAL)
-#define virt_to_page(kaddr)	pfn_to_page(virt_to_pfn(kaddr))
+#define virt_to_page(x)		pfn_to_page(virt_to_pfn(x))
 #else
 #define page_to_virt(x)	({						\
 	__typeof__(x) __page = x;					\
-- 
cgit v1.2.3


From 233947ef16a18952d22786770dab1ddafa1ac377 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 14 Aug 2019 14:28:47 +0100
Subject: arm64: memory: fix flipped VA space fallout

VA_START used to be the start of the TTBR1 address space, but now it's a
point midway though. In a couple of places we still use VA_START to get
the start of the TTBR1 address space, so let's fix these up to use
PAGE_OFFSET instead.

Fixes: 14c127c957c1c607 ("arm64: mm: Flip kernel VA space")
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Tested-by: Steve Capper <steve.capper@arm.com>
Reviewed-by: Steve Capper <steve.capper@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/mm/dump.c  | 2 +-
 arch/arm64/mm/fault.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index 6ec75305828e..8e10b4ba215a 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -400,7 +400,7 @@ void ptdump_check_wx(void)
 		.check_wx = true,
 	};
 
-	walk_pgd(&st, &init_mm, VA_START);
+	walk_pgd(&st, &init_mm, PAGE_OFFSET);
 	note_page(&st, 0, 0, 0);
 	if (st.wx_pages || st.uxn_pages)
 		pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found, %lu non-UXN pages found\n",
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 75eff57bd9ef..bb4e4f3fffd8 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -109,7 +109,7 @@ static inline bool is_ttbr0_addr(unsigned long addr)
 static inline bool is_ttbr1_addr(unsigned long addr)
 {
 	/* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */
-	return arch_kasan_reset_tag(addr) >= VA_START;
+	return arch_kasan_reset_tag(addr) >= PAGE_OFFSET;
 }
 
 /*
-- 
cgit v1.2.3


From 77ad4ce69321abbe26ec92b2a2691a66531eb688 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 14 Aug 2019 14:28:48 +0100
Subject: arm64: memory: rename VA_START to PAGE_END

Prior to commit:

  14c127c957c1c607 ("arm64: mm: Flip kernel VA space")

... VA_START described the start of the TTBR1 address space for a given
VA size described by VA_BITS, where all kernel mappings began.

Since that commit, VA_START described a portion midway through the
address space, where the linear map ends and other kernel mappings
begin.

To avoid confusion, let's rename VA_START to PAGE_END, making it clear
that it's not the start of the TTBR1 address space and implying that
it's related to PAGE_OFFSET. Comments and other mnemonics are updated
accordingly, along with a typo fix in the decription of VMEMMAP_SIZE.

There should be no functional change as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Tested-by: Steve Capper <steve.capper@arm.com>
Reviewed-by: Steve Capper <steve.capper@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/memory.h  | 20 ++++++++++----------
 arch/arm64/include/asm/pgtable.h |  4 ++--
 arch/arm64/kernel/hibernate.c    |  2 +-
 arch/arm64/mm/dump.c             |  6 +++---
 arch/arm64/mm/kasan_init.c       |  2 +-
 arch/arm64/mm/mmu.c              |  4 ++--
 6 files changed, 19 insertions(+), 19 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index d69c2865ae40..a713bad71db5 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -28,20 +28,20 @@
  *                a struct page array
  *
  * If we are configured with a 52-bit kernel VA then our VMEMMAP_SIZE
- * neads to cover the memory region from the beginning of the 52-bit
- * PAGE_OFFSET all the way to VA_START for 48-bit. This allows us to
+ * needs to cover the memory region from the beginning of the 52-bit
+ * PAGE_OFFSET all the way to PAGE_END for 48-bit. This allows us to
  * keep a constant PAGE_OFFSET and "fallback" to using the higher end
  * of the VMEMMAP where 52-bit support is not available in hardware.
  */
-#define VMEMMAP_SIZE ((_VA_START(VA_BITS_MIN) - PAGE_OFFSET) \
+#define VMEMMAP_SIZE ((_PAGE_END(VA_BITS_MIN) - PAGE_OFFSET) \
 			>> (PAGE_SHIFT - STRUCT_PAGE_MAX_SHIFT))
 
 /*
- * PAGE_OFFSET - the virtual address of the start of the linear map (top
- *		 (VA_BITS - 1))
- * KIMAGE_VADDR - the virtual address of the start of the kernel image
+ * PAGE_OFFSET - the virtual address of the start of the linear map, at the
+ *               start of the TTBR1 address space.
+ * PAGE_END - the end of the linear map, where all other kernel mappings begin.
+ * KIMAGE_VADDR - the virtual address of the start of the kernel image.
  * VA_BITS - the maximum number of bits for virtual addresses.
- * VA_START - the first kernel virtual address.
  */
 #define VA_BITS			(CONFIG_ARM64_VA_BITS)
 #define _PAGE_OFFSET(va)	(-(UL(1) << (va)))
@@ -64,7 +64,7 @@
 #define VA_BITS_MIN		(VA_BITS)
 #endif
 
-#define _VA_START(va)		(-(UL(1) << ((va) - 1)))
+#define _PAGE_END(va)		(-(UL(1) << ((va) - 1)))
 
 #define KERNEL_START		_text
 #define KERNEL_END		_end
@@ -87,7 +87,7 @@
 #define KASAN_THREAD_SHIFT	1
 #else
 #define KASAN_THREAD_SHIFT	0
-#define KASAN_SHADOW_END	(_VA_START(VA_BITS_MIN))
+#define KASAN_SHADOW_END	(_PAGE_END(VA_BITS_MIN))
 #endif /* CONFIG_KASAN */
 
 #define MIN_THREAD_SHIFT	(14 + KASAN_THREAD_SHIFT)
@@ -173,7 +173,7 @@
 
 #ifndef __ASSEMBLY__
 extern u64			vabits_actual;
-#define VA_START		(_VA_START(vabits_actual))
+#define PAGE_END		(_PAGE_END(vabits_actual))
 
 #include <linux/bitops.h>
 #include <linux/mmdebug.h>
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 4a695b9ee0f0..979e24fadf35 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -856,8 +856,8 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 
 #define update_mmu_cache_pmd(vma, address, pmd) do { } while (0)
 
-#define kc_vaddr_to_offset(v)	((v) & ~VA_START)
-#define kc_offset_to_vaddr(o)	((o) | VA_START)
+#define kc_vaddr_to_offset(v)	((v) & ~PAGE_END)
+#define kc_offset_to_vaddr(o)	((o) | PAGE_END)
 
 #ifdef CONFIG_ARM64_PA_BITS_52
 #define phys_to_ttbr(addr)	(((addr) | ((addr) >> 46)) & TTBR_BADDR_MASK_52)
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index e130db05d932..e0a7fce0e01c 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -496,7 +496,7 @@ int swsusp_arch_resume(void)
 		rc = -ENOMEM;
 		goto out;
 	}
-	rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, VA_START);
+	rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, PAGE_END);
 	if (rc)
 		goto out;
 
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index 8e10b4ba215a..93f9f77582ae 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -28,7 +28,7 @@
 
 enum address_markers_idx {
 	PAGE_OFFSET_NR = 0,
-	VA_START_NR,
+	PAGE_END_NR,
 #ifdef CONFIG_KASAN
 	KASAN_START_NR,
 #endif
@@ -36,7 +36,7 @@ enum address_markers_idx {
 
 static struct addr_marker address_markers[] = {
 	{ PAGE_OFFSET,			"Linear Mapping start" },
-	{ 0 /* VA_START */,		"Linear Mapping end" },
+	{ 0 /* PAGE_END */,		"Linear Mapping end" },
 #ifdef CONFIG_KASAN
 	{ 0 /* KASAN_SHADOW_START */,	"Kasan shadow start" },
 	{ KASAN_SHADOW_END,		"Kasan shadow end" },
@@ -411,7 +411,7 @@ void ptdump_check_wx(void)
 
 static int ptdump_init(void)
 {
-	address_markers[VA_START_NR].start_address = VA_START;
+	address_markers[PAGE_END_NR].start_address = PAGE_END;
 #ifdef CONFIG_KASAN
 	address_markers[KASAN_START_NR].start_address = KASAN_SHADOW_START;
 #endif
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index 725222271474..f87a32484ea8 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -226,7 +226,7 @@ void __init kasan_init(void)
 	kasan_map_populate(kimg_shadow_start, kimg_shadow_end,
 			   early_pfn_to_nid(virt_to_pfn(lm_alias(_text))));
 
-	kasan_populate_early_shadow(kasan_mem_to_shadow((void *) VA_START),
+	kasan_populate_early_shadow(kasan_mem_to_shadow((void *)PAGE_END),
 				   (void *)mod_shadow_start);
 	kasan_populate_early_shadow((void *)kimg_shadow_end,
 				   (void *)KASAN_SHADOW_END);
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 0c8f7e55f859..8e4b7eaff8ce 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -399,7 +399,7 @@ static phys_addr_t pgd_pgtable_alloc(int shift)
 static void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt,
 				  phys_addr_t size, pgprot_t prot)
 {
-	if ((virt >= VA_START) && (virt < VMALLOC_START)) {
+	if ((virt >= PAGE_END) && (virt < VMALLOC_START)) {
 		pr_warn("BUG: not creating mapping for %pa at 0x%016lx - outside kernel range\n",
 			&phys, virt);
 		return;
@@ -426,7 +426,7 @@ void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
 static void update_mapping_prot(phys_addr_t phys, unsigned long virt,
 				phys_addr_t size, pgprot_t prot)
 {
-	if ((virt >= VA_START) && (virt < VMALLOC_START)) {
+	if ((virt >= PAGE_END) && (virt < VMALLOC_START)) {
 		pr_warn("BUG: not updating mapping for %pa at 0x%016lx - outside kernel range\n",
 			&phys, virt);
 		return;
-- 
cgit v1.2.3


From d55c5f28afafb6b1f0a6978916b23338b383faab Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Wed, 12 Jun 2019 13:51:37 +0100
Subject: arm64: smp: disable hotplug on trusted OS resident CPU

The trusted OS may reject CPU_OFF calls to its resident CPU, so we must
avoid issuing those. We never migrate a Trusted OS and we already take
care to prevent CPU_OFF PSCI call. However, this is not reflected
explicitly to the userspace. Any user can attempt to hotplug trusted OS
resident CPU. The entire motion of going through the various state
transitions in the CPU hotplug state machine gets executed and the
PSCI layer finally refuses to make CPU_OFF call.

This results is unnecessary unwinding of CPU hotplug state machine in
the kernel. Instead we can mark the trusted OS resident CPU as not
available for hotplug, so that the user attempt or request to do the
same will get immediately rejected.

Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/cpu_ops.h |  3 +++
 arch/arm64/kernel/psci.c         |  6 ++++++
 arch/arm64/kernel/setup.c        | 11 ++++++++++-
 3 files changed, 19 insertions(+), 1 deletion(-)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/cpu_ops.h b/arch/arm64/include/asm/cpu_ops.h
index c09d633c3109..86aabf1e0199 100644
--- a/arch/arm64/include/asm/cpu_ops.h
+++ b/arch/arm64/include/asm/cpu_ops.h
@@ -23,6 +23,8 @@
  * @cpu_boot:	Boots a cpu into the kernel.
  * @cpu_postboot: Optionally, perform any post-boot cleanup or necesary
  *		synchronisation. Called from the cpu being booted.
+ * @cpu_can_disable: Determines whether a CPU can be disabled based on
+ *		mechanism-specific information.
  * @cpu_disable: Prepares a cpu to die. May fail for some mechanism-specific
  * 		reason, which will cause the hot unplug to be aborted. Called
  * 		from the cpu to be killed.
@@ -42,6 +44,7 @@ struct cpu_operations {
 	int		(*cpu_boot)(unsigned int);
 	void		(*cpu_postboot)(void);
 #ifdef CONFIG_HOTPLUG_CPU
+	bool		(*cpu_can_disable)(unsigned int cpu);
 	int		(*cpu_disable)(unsigned int cpu);
 	void		(*cpu_die)(unsigned int cpu);
 	int		(*cpu_kill)(unsigned int cpu);
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index a543ab7e007c..c9f72b2665f1 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -46,6 +46,11 @@ static int cpu_psci_cpu_boot(unsigned int cpu)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
+static bool cpu_psci_cpu_can_disable(unsigned int cpu)
+{
+	return !psci_tos_resident_on(cpu);
+}
+
 static int cpu_psci_cpu_disable(unsigned int cpu)
 {
 	/* Fail early if we don't have CPU_OFF support */
@@ -109,6 +114,7 @@ const struct cpu_operations cpu_psci_ops = {
 	.cpu_prepare	= cpu_psci_cpu_prepare,
 	.cpu_boot	= cpu_psci_cpu_boot,
 #ifdef CONFIG_HOTPLUG_CPU
+	.cpu_can_disable = cpu_psci_cpu_can_disable,
 	.cpu_disable	= cpu_psci_cpu_disable,
 	.cpu_die	= cpu_psci_cpu_die,
 	.cpu_kill	= cpu_psci_cpu_kill,
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 9c4bad7d7131..57ff38600828 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -357,6 +357,15 @@ void __init setup_arch(char **cmdline_p)
 	}
 }
 
+static inline bool cpu_can_disable(unsigned int cpu)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+	if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_can_disable)
+		return cpu_ops[cpu]->cpu_can_disable(cpu);
+#endif
+	return false;
+}
+
 static int __init topology_init(void)
 {
 	int i;
@@ -366,7 +375,7 @@ static int __init topology_init(void)
 
 	for_each_possible_cpu(i) {
 		struct cpu *cpu = &per_cpu(cpu_data.cpu, i);
-		cpu->hotpluggable = 1;
+		cpu->hotpluggable = cpu_can_disable(i);
 		register_cpu(cpu, i);
 	}
 
-- 
cgit v1.2.3


From d91cc2f46ad5bd8020902093385fedf7e9e9d755 Mon Sep 17 00:00:00 2001
From: Raphael Gault <raphael.gault@arm.com>
Date: Tue, 20 Aug 2019 16:57:45 +0100
Subject: arm64: perf_event: Add missing header needed for smp_processor_id()

In perf_event.c we use smp_processor_id(), but we haven't included
<linux/smp.h> where it is defined, and rely on this being pulled in
via a transitive include. Let's make this more robust by including
<linux.smp.h> explicitly.

Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Raphael Gault <raphael.gault@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/perf_event.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch')

diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 2d3bdebdf6df..a0b4f1bca491 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -19,6 +19,7 @@
 #include <linux/of.h>
 #include <linux/perf/arm_pmu.h>
 #include <linux/platform_device.h>
+#include <linux/smp.h>
 
 /* ARMv8 Cortex-A53 specific event types. */
 #define ARMV8_A53_PERFCTR_PREF_LINEFILL				0xC2
-- 
cgit v1.2.3


From 413235fcedc7f61e925fe9818bc3f5eff8ad2494 Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Thu, 15 Aug 2019 16:44:01 +0100
Subject: arm64: Change the tagged_addr sysctl control semantics to only
 prevent the opt-in

First rename the sysctl control to abi.tagged_addr_disabled and make it
default off (zero). When abi.tagged_addr_disabled == 1, only block the
enabling of the TBI ABI via prctl(PR_SET_TAGGED_ADDR_CTRL, PR_TAGGED_ADDR_ENABLE).
Getting the status of the ABI or disabling it is still allowed.

Acked-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/process.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 76b7c55026aa..03689c0beb34 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -579,17 +579,22 @@ void arch_setup_new_exec(void)
 /*
  * Control the relaxed ABI allowing tagged user addresses into the kernel.
  */
-static unsigned int tagged_addr_prctl_allowed = 1;
+static unsigned int tagged_addr_disabled;
 
 long set_tagged_addr_ctrl(unsigned long arg)
 {
-	if (!tagged_addr_prctl_allowed)
-		return -EINVAL;
 	if (is_compat_task())
 		return -EINVAL;
 	if (arg & ~PR_TAGGED_ADDR_ENABLE)
 		return -EINVAL;
 
+	/*
+	 * Do not allow the enabling of the tagged address ABI if globally
+	 * disabled via sysctl abi.tagged_addr_disabled.
+	 */
+	if (arg & PR_TAGGED_ADDR_ENABLE && tagged_addr_disabled)
+		return -EINVAL;
+
 	update_thread_flag(TIF_TAGGED_ADDR, arg & PR_TAGGED_ADDR_ENABLE);
 
 	return 0;
@@ -597,8 +602,6 @@ long set_tagged_addr_ctrl(unsigned long arg)
 
 long get_tagged_addr_ctrl(void)
 {
-	if (!tagged_addr_prctl_allowed)
-		return -EINVAL;
 	if (is_compat_task())
 		return -EINVAL;
 
@@ -618,9 +621,9 @@ static int one = 1;
 
 static struct ctl_table tagged_addr_sysctl_table[] = {
 	{
-		.procname	= "tagged_addr",
+		.procname	= "tagged_addr_disabled",
 		.mode		= 0644,
-		.data		= &tagged_addr_prctl_allowed,
+		.data		= &tagged_addr_disabled,
 		.maxlen		= sizeof(int),
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &zero,
-- 
cgit v1.2.3


From e112b032a72c78f15d0c803c5dc6be444c2e6c66 Mon Sep 17 00:00:00 2001
From: Hsin-Yi Wang <hsinyi@chromium.org>
Date: Fri, 23 Aug 2019 14:24:50 +0800
Subject: arm64: map FDT as RW for early_init_dt_scan()

Currently in arm64, FDT is mapped to RO before it's passed to
early_init_dt_scan(). However, there might be some codes
(eg. commit "fdt: add support for rng-seed") that need to modify FDT
during init. Map FDT to RO after early fixups are done.

Signed-off-by: Hsin-Yi Wang <hsinyi@chromium.org>
Reviewed-by: Stephen Boyd <swboyd@chromium.org>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/mmu.h |  2 +-
 arch/arm64/kernel/kaslr.c    |  5 +----
 arch/arm64/kernel/setup.c    |  9 ++++++++-
 arch/arm64/mm/mmu.c          | 15 +--------------
 4 files changed, 11 insertions(+), 20 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index fd6161336653..f217e3292919 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -126,7 +126,7 @@ extern void init_mem_pgprot(void);
 extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
 			       unsigned long virt, phys_addr_t size,
 			       pgprot_t prot, bool page_mappings_only);
-extern void *fixmap_remap_fdt(phys_addr_t dt_phys);
+extern void *fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot);
 extern void mark_linear_text_alias_ro(void);
 
 #define INIT_MM_CONTEXT(name)	\
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index 708051655ad9..d94a3e41cef9 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -62,9 +62,6 @@ out:
 	return default_cmdline;
 }
 
-extern void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size,
-				       pgprot_t prot);
-
 /*
  * This routine will be executed with the kernel mapped at its default virtual
  * address, and if it returns successfully, the kernel will be remapped, and
@@ -93,7 +90,7 @@ u64 __init kaslr_early_init(u64 dt_phys)
 	 * attempt at mapping the FDT in setup_machine()
 	 */
 	early_fixmap_init();
-	fdt = __fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL);
+	fdt = fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL);
 	if (!fdt)
 		return 0;
 
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 9c4bad7d7131..25f5127210f8 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -170,9 +170,13 @@ static void __init smp_build_mpidr_hash(void)
 
 static void __init setup_machine_fdt(phys_addr_t dt_phys)
 {
-	void *dt_virt = fixmap_remap_fdt(dt_phys);
+	int size;
+	void *dt_virt = fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL);
 	const char *name;
 
+	if (dt_virt)
+		memblock_reserve(dt_phys, size);
+
 	if (!dt_virt || !early_init_dt_scan(dt_virt)) {
 		pr_crit("\n"
 			"Error: invalid device tree blob at physical address %pa (virtual address 0x%p)\n"
@@ -184,6 +188,9 @@ static void __init setup_machine_fdt(phys_addr_t dt_phys)
 			cpu_relax();
 	}
 
+	/* Early fixups are done, map the FDT as read-only now */
+	fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL_RO);
+
 	name = of_flat_dt_get_machine_name();
 	if (!name)
 		return;
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 750a69dde39b..54e93583085c 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -876,7 +876,7 @@ void __set_fixmap(enum fixed_addresses idx,
 	}
 }
 
-void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot)
+void *__init fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot)
 {
 	const u64 dt_virt_base = __fix_to_virt(FIX_FDT);
 	int offset;
@@ -929,19 +929,6 @@ void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot)
 	return dt_virt;
 }
 
-void *__init fixmap_remap_fdt(phys_addr_t dt_phys)
-{
-	void *dt_virt;
-	int size;
-
-	dt_virt = __fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL_RO);
-	if (!dt_virt)
-		return NULL;
-
-	memblock_reserve(dt_phys, size);
-	return dt_virt;
-}
-
 int __init arch_ioremap_p4d_supported(void)
 {
 	return 0;
-- 
cgit v1.2.3


From 7f591fa7a62d3a3f585fd4ba5c3e7b05f4b931be Mon Sep 17 00:00:00 2001
From: Hsin-Yi Wang <hsinyi@chromium.org>
Date: Fri, 23 Aug 2019 14:24:52 +0800
Subject: arm64: kexec_file: add rng-seed support

Adding "rng-seed" to dtb. It's fine to add this property if original
fdt doesn't contain it. Since original seed will be wiped after
read, so use a default size 128 bytes here.

Signed-off-by: Hsin-Yi Wang <hsinyi@chromium.org>
Reviewed-by: Stephen Boyd <swboyd@chromium.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/machine_kexec_file.c | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

(limited to 'arch')

diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c
index 58871333737a..81b5baad97aa 100644
--- a/arch/arm64/kernel/machine_kexec_file.c
+++ b/arch/arm64/kernel/machine_kexec_file.c
@@ -27,6 +27,8 @@
 #define FDT_PROP_INITRD_END	"linux,initrd-end"
 #define FDT_PROP_BOOTARGS	"bootargs"
 #define FDT_PROP_KASLR_SEED	"kaslr-seed"
+#define FDT_PROP_RNG_SEED	"rng-seed"
+#define RNG_SEED_SIZE		128
 
 const struct kexec_file_ops * const kexec_file_loaders[] = {
 	&kexec_image_ops,
@@ -102,6 +104,19 @@ static int setup_dtb(struct kimage *image,
 				FDT_PROP_KASLR_SEED);
 	}
 
+	/* add rng-seed */
+	if (rng_is_initialized()) {
+		u8 rng_seed[RNG_SEED_SIZE];
+		get_random_bytes(rng_seed, RNG_SEED_SIZE);
+		ret = fdt_setprop(dtb, off, FDT_PROP_RNG_SEED, rng_seed,
+				RNG_SEED_SIZE);
+		if (ret)
+			goto out;
+	} else {
+		pr_notice("RNG is not initialised: omitting \"%s\" property\n",
+				FDT_PROP_RNG_SEED);
+	}
+
 out:
 	if (ret)
 		return (ret == -FDT_ERR_NOSPACE) ? -ENOMEM : -EINVAL;
@@ -110,7 +125,8 @@ out:
 }
 
 /*
- * More space needed so that we can add initrd, bootargs and kaslr-seed.
+ * More space needed so that we can add initrd, bootargs, kaslr-seed, and
+ * rng-seed.
  */
 #define DTB_EXTRA_SPACE 0x1000
 
-- 
cgit v1.2.3


From 0e1645557d19fc6d88d3c40431f63a3c3a4c417b Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 27 Aug 2019 14:25:44 +0100
Subject: arm64: smp: Increase secondary CPU boot timeout value

When many debug options are enabled simultaneously (e.g. PROVE_LOCKING,
KMEMLEAK, DEBUG_PAGE_ALLOC, KASAN etc), it is possible for us to timeout
when attempting to boot a secondary CPU and give up. Unfortunately, the
CPU will /eventually/ appear, and sit in the background happily stuck
in a recursive exception due to a NULL stack pointer.

Increase the timeout to 5s, which will of course be enough for anybody.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/smp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch')

diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 018a33e01b0e..63c7a7682e93 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -123,7 +123,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 		 * time out.
 		 */
 		wait_for_completion_timeout(&cpu_running,
-					    msecs_to_jiffies(1000));
+					    msecs_to_jiffies(5000));
 
 		if (!cpu_online(cpu)) {
 			pr_crit("CPU%u: failed to come online\n", cpu);
-- 
cgit v1.2.3


From 5b1cfe3a0ba74c1f2b83b607712a217b9f9463a2 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 27 Aug 2019 14:36:38 +0100
Subject: arm64: smp: Don't enter kernel with NULL stack pointer or task struct

Although SMP bringup is inherently racy, we can significantly reduce
the window during which secondary CPUs can unexpectedly enter the
kernel by sanity checking the 'stack' and 'task' fields of the
'secondary_data' structure. If the booting CPU gave up waiting for us,
then they will have been cleared to NULL and we should spin in a WFE; WFI
loop instead.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/head.S | 8 ++++++++
 arch/arm64/kernel/smp.c  | 1 +
 2 files changed, 9 insertions(+)

(limited to 'arch')

diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 2cdacd1c141b..0baadf335172 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -724,14 +724,22 @@ __secondary_switched:
 
 	adr_l	x0, secondary_data
 	ldr	x1, [x0, #CPU_BOOT_STACK]	// get secondary_data.stack
+	cbz	x1, __secondary_too_slow
 	mov	sp, x1
 	ldr	x2, [x0, #CPU_BOOT_TASK]
+	cbz	x2, __secondary_too_slow
 	msr	sp_el0, x2
 	mov	x29, #0
 	mov	x30, #0
 	b	secondary_start_kernel
 ENDPROC(__secondary_switched)
 
+__secondary_too_slow:
+	wfe
+	wfi
+	b	__secondary_too_slow
+ENDPROC(__secondary_too_slow)
+
 /*
  * The booting CPU updates the failed status @__early_cpu_boot_status,
  * with MMU turned off.
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 63c7a7682e93..1f8aeb77cba5 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -136,6 +136,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 
 	secondary_data.task = NULL;
 	secondary_data.stack = NULL;
+	__flush_dcache_area(&secondary_data, sizeof(secondary_data));
 	status = READ_ONCE(secondary_data.status);
 	if (ret && status) {
 
-- 
cgit v1.2.3


From ebef746543fd1aa162216b0e484eb9062b65741d Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 27 Aug 2019 15:54:56 +0100
Subject: arm64: smp: Treat unknown boot failures as being 'stuck in kernel'

When we fail to bring a secondary CPU online and it fails in an unknown
state, we should assume the worst and increment 'cpus_stuck_in_kernel'
so that things like kexec() are disabled.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/smp.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch')

diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 1f8aeb77cba5..dc9fe879c279 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -147,6 +147,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 		default:
 			pr_err("CPU%u: failed in unknown state : 0x%lx\n",
 					cpu, status);
+			cpus_stuck_in_kernel++;
 			break;
 		case CPU_KILL_ME:
 			if (!op_cpu_kill(cpu)) {
-- 
cgit v1.2.3


From d0b7a302d58abe24ed0f32a0672dd4c356bb73db Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Thu, 22 Aug 2019 14:58:37 +0100
Subject: Revert "arm64: Remove unnecessary ISBs from set_{pte,pmd,pud}"

This reverts commit 24fe1b0efad4fcdd32ce46cffeab297f22581707.

Commit 24fe1b0efad4fcdd ("arm64: Remove unnecessary ISBs from
set_{pte,pmd,pud}") removed ISB instructions immediately following updates
to the page table, on the grounds that they are not required by the
architecture and a DSB alone is sufficient to ensure that subsequent data
accesses use the new translation:

  DDI0487E_a, B2-128:

  | ... no instruction that appears in program order after the DSB
  | instruction can alter any state of the system or perform any part of
  | its functionality until the DSB completes other than:
  |
  | * Being fetched from memory and decoded
  | * Reading the general-purpose, SIMD and floating-point,
  |   Special-purpose, or System registers that are directly or indirectly
  |   read without causing side-effects.

However, the same document also states the following:

  DDI0487E_a, B2-125:

  | DMB and DSB instructions affect reads and writes to the memory system
  | generated by Load/Store instructions and data or unified cache
  | maintenance instructions being executed by the PE. Instruction fetches
  | or accesses caused by a hardware translation table access are not
  | explicit accesses.

which appears to claim that the DSB alone is insufficient.  Unfortunately,
some CPU designers have followed the second clause above, whereas in Linux
we've been relying on the first. This means that our mapping sequence:

	MOV	X0, <valid pte>
	STR	X0, [Xptep]	// Store new PTE to page table
	DSB	ISHST
	LDR	X1, [X2]	// Translates using the new PTE

can actually raise a translation fault on the load instruction because the
translation can be performed speculatively before the page table update and
then marked as "faulting" by the CPU. For user PTEs, this is ok because we
can handle the spurious fault, but for kernel PTEs and intermediate table
entries this results in a panic().

Revert the offending commit to reintroduce the missing barriers.

Cc: <stable@vger.kernel.org>
Fixes: 24fe1b0efad4fcdd ("arm64: Remove unnecessary ISBs from set_{pte,pmd,pud}")
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/pgtable.h | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 5fdcfe237338..feda7294320c 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -220,8 +220,10 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
 	 * Only if the new pte is valid and kernel, otherwise TLB maintenance
 	 * or update_mmu_cache() have the necessary barriers.
 	 */
-	if (pte_valid_not_user(pte))
+	if (pte_valid_not_user(pte)) {
 		dsb(ishst);
+		isb();
+	}
 }
 
 extern void __sync_icache_dcache(pte_t pteval);
@@ -481,8 +483,10 @@ static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 
 	WRITE_ONCE(*pmdp, pmd);
 
-	if (pmd_valid(pmd))
+	if (pmd_valid(pmd)) {
 		dsb(ishst);
+		isb();
+	}
 }
 
 static inline void pmd_clear(pmd_t *pmdp)
@@ -540,8 +544,10 @@ static inline void set_pud(pud_t *pudp, pud_t pud)
 
 	WRITE_ONCE(*pudp, pud);
 
-	if (pud_valid(pud))
+	if (pud_valid(pud)) {
 		dsb(ishst);
+		isb();
+	}
 }
 
 static inline void pud_clear(pud_t *pudp)
-- 
cgit v1.2.3


From 51696d346c49c6cf4f29e9b20d6e15832a2e3408 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Thu, 22 Aug 2019 15:03:45 +0100
Subject: arm64: tlb: Ensure we execute an ISB following walk cache
 invalidation

05f2d2f83b5a ("arm64: tlbflush: Introduce __flush_tlb_kernel_pgtable")
added a new TLB invalidation helper which is used when freeing
intermediate levels of page table used for kernel mappings, but is
missing the required ISB instruction after completion of the TLBI
instruction.

Add the missing barrier.

Cc: <stable@vger.kernel.org>
Fixes: 05f2d2f83b5a ("arm64: tlbflush: Introduce __flush_tlb_kernel_pgtable")
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/tlbflush.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index 8af7a85f76bd..bc3949064725 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -251,6 +251,7 @@ static inline void __flush_tlb_kernel_pgtable(unsigned long kaddr)
 	dsb(ishst);
 	__tlbi(vaae1is, addr);
 	dsb(ish);
+	isb();
 }
 #endif
 
-- 
cgit v1.2.3


From eb6a4dcce33925ac95023bbe5199474f8db40ba7 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Fri, 23 Aug 2019 13:03:55 +0100
Subject: arm64: mm: Add ISB instruction to set_pgd()

Commit 6a4cbd63c25a ("Revert "arm64: Remove unnecessary ISBs from
set_{pte,pmd,pud}"") reintroduced ISB instructions to some of our
page table setter functions in light of a recent clarification to the
Armv8 architecture. Although 'set_pgd()' isn't currently used to update
a live page table, add the ISB instruction there too for consistency
with the other macros and to provide some future-proofing if we use it
on live tables in the future.

Reported-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/pgtable.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index feda7294320c..2faa77635942 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -605,6 +605,7 @@ static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
 
 	WRITE_ONCE(*pgdp, pgd);
 	dsb(ishst);
+	isb();
 }
 
 static inline void pgd_clear(pgd_t *pgdp)
-- 
cgit v1.2.3


From e8620cff99946ea1f7891d7bec071a23a1fdaef3 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Thu, 22 Aug 2019 17:19:17 +0100
Subject: arm64: sysreg: Add some field definitions for PAR_EL1

PAR_EL1 is a mysterious creature, but sometimes it's necessary to read
it when translating addresses in situations where we cannot walk the
page table directly.

Add a couple of system register definitions for the fault indication
field ('F') and the fault status code ('FST').

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/sysreg.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'arch')

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 06ebcfef73df..2b229c23f3c1 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -212,6 +212,9 @@
 #define SYS_FAR_EL1			sys_reg(3, 0, 6, 0, 0)
 #define SYS_PAR_EL1			sys_reg(3, 0, 7, 4, 0)
 
+#define SYS_PAR_EL1_F			BIT(1)
+#define SYS_PAR_EL1_FST			GENMASK(6, 1)
+
 /*** Statistical Profiling Extension ***/
 /* ID registers */
 #define SYS_PMSIDR_EL1			sys_reg(3, 0, 9, 9, 7)
-- 
cgit v1.2.3


From 42f91093b043332ad75cea7aeafecda6fe81814c Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Thu, 22 Aug 2019 17:22:14 +0100
Subject: arm64: mm: Ignore spurious translation faults taken from the kernel

Thanks to address translation being performed out of order with respect to
loads and stores, it is possible for a CPU to take a translation fault when
accessing a page that was mapped by a different CPU.

For example, in the case that one CPU maps a page and then sets a flag to
tell another CPU:

	CPU 0
	-----

	MOV	X0, <valid pte>
	STR	X0, [Xptep]	// Store new PTE to page table
	DSB	ISHST
	ISB
	MOV	X1, #1
	STR	X1, [Xflag]	// Set the flag

	CPU 1
	-----

loop:	LDAR	X0, [Xflag]	// Poll flag with Acquire semantics
	CBZ	X0, loop
	LDR	X1, [X2]	// Translates using the new PTE

then the final load on CPU 1 can raise a translation fault because the
translation can be performed speculatively before the read of the flag and
marked as "faulting" by the CPU. This isn't quite as bad as it sounds
since, in reality, code such as:

	CPU 0				CPU 1
	-----				-----
	spin_lock(&lock);		spin_lock(&lock);
	*ptr = vmalloc(size);		if (*ptr)
	spin_unlock(&lock);			foo = **ptr;
					spin_unlock(&lock);

will not trigger the fault because there is an address dependency on CPU 1
which prevents the speculative translation. However, more exotic code where
the virtual address is known ahead of time, such as:

	CPU 0				CPU 1
	-----				-----
	spin_lock(&lock);		spin_lock(&lock);
	set_fixmap(0, paddr, prot);	if (mapped)
	mapped = true;				foo = *fix_to_virt(0);
	spin_unlock(&lock);		spin_unlock(&lock);

could fault. This can be avoided by any of:

	* Introducing broadcast TLB maintenance on the map path
	* Adding a DSB;ISB sequence after checking a flag which indicates
	  that a virtual address is now mapped
	* Handling the spurious fault

Given that we have never observed a problem due to this under Linux and
future revisions of the architecture are being tightened so that
translation table walks are effectively ordered in the same way as explicit
memory accesses, we no longer treat spurious kernel faults as fatal if an
AT instruction indicates that the access does not trigger a translation
fault.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/mm/fault.c | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

(limited to 'arch')

diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index cfd65b63f36f..9808da29a653 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/bitfield.h>
 #include <linux/extable.h>
 #include <linux/signal.h>
 #include <linux/mm.h>
@@ -242,6 +243,34 @@ static inline bool is_el1_permission_fault(unsigned long addr, unsigned int esr,
 	return false;
 }
 
+static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr,
+							unsigned int esr,
+							struct pt_regs *regs)
+{
+	unsigned long flags;
+	u64 par, dfsc;
+
+	if (ESR_ELx_EC(esr) != ESR_ELx_EC_DABT_CUR ||
+	    (esr & ESR_ELx_FSC_TYPE) != ESR_ELx_FSC_FAULT)
+		return false;
+
+	local_irq_save(flags);
+	asm volatile("at s1e1r, %0" :: "r" (addr));
+	isb();
+	par = read_sysreg(par_el1);
+	local_irq_restore(flags);
+
+	if (!(par & SYS_PAR_EL1_F))
+		return false;
+
+	/*
+	 * If we got a different type of fault from the AT instruction,
+	 * treat the translation fault as spurious.
+	 */
+	dfsc = FIELD_PREP(SYS_PAR_EL1_FST, par);
+	return (dfsc & ESR_ELx_FSC_TYPE) != ESR_ELx_FSC_FAULT;
+}
+
 static void die_kernel_fault(const char *msg, unsigned long addr,
 			     unsigned int esr, struct pt_regs *regs)
 {
@@ -270,6 +299,10 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr,
 	if (!is_el1_instruction_abort(esr) && fixup_exception(regs))
 		return;
 
+	if (WARN_RATELIMIT(is_spurious_el1_translation_fault(addr, esr, regs),
+	    "Ignoring spurious kernel translation fault at virtual address %016lx\n", addr))
+		return;
+
 	if (is_el1_permission_fault(addr, esr, regs)) {
 		if (esr & ESR_ELx_WNR)
 			msg = "write to read-only memory";
-- 
cgit v1.2.3


From 5c062ef4155b60018c547552ca48823297d00998 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Thu, 22 Aug 2019 17:21:21 +0100
Subject: arm64: kvm: Replace hardcoded '1' with SYS_PAR_EL1_F

Now that we have a definition for the 'F' field of PAR_EL1, use that
instead of coding the immediate directly.

Acked-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kvm/hyp/switch.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch')

diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index adaf266d8de8..bd978ad71936 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -264,7 +264,7 @@ static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar)
 	tmp = read_sysreg(par_el1);
 	write_sysreg(par, par_el1);
 
-	if (unlikely(tmp & 1))
+	if (unlikely(tmp & SYS_PAR_EL1_F))
 		return false; /* Translation failed, back to guest */
 
 	/* Convert PAR to HPFAR format */
-- 
cgit v1.2.3


From b333b0ba2346f2071390533b8f37f36f191d705d Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Tue, 27 Aug 2019 16:57:08 +0100
Subject: arm64: fix fixmap copy for 16K pages and 48-bit VA

With 16K pages and 48-bit VAs, the PGD level of table has two entries,
and so the fixmap shares a PGD with the kernel image. Since commit:

  f9040773b7bbbd9e ("arm64: move kernel image to base of vmalloc area")

... we copy the existing fixmap to the new fine-grained page tables at
the PUD level in this case. When walking to the new PUD, we forgot to
offset the PGD entry and always used the PGD entry at index 0, but this
worked as the kernel image and fixmap were in the low half of the TTBR1
address space.

As of commit:

  14c127c957c1c607 ("arm64: mm: Flip kernel VA space")

... the kernel image and fixmap are in the high half of the TTBR1
address space, and hence use the PGD at index 1, but we didn't update
the fixmap copying code to account for this.

Thus, we'll erroneously try to copy the fixmap slots into a PUD under
the PGD entry at index 0. At the point we do so this PGD entry has not
been initialised, and thus we'll try to write a value to a small offset
from physical address 0, causing a number of potential problems.

Fix this be correctly offsetting the PGD. This is split over a few steps
for legibility.

Fixes: 14c127c957c1c607 ("arm64: mm: Flip kernel VA space")
Reported-by: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Marc Zyngier <maz@kernel.org>
Tested-by: Marc Zyngier <maz@kernel.org>
Acked-by: Steve Capper <Steve.Capper@arm.com>
Tested-by: Steve Capper <Steve.Capper@arm.com>
Tested-by: Anshuman Khandual <anshuman.khandual@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/mm/mmu.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'arch')

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 8e4b7eaff8ce..3ed44008230e 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -647,6 +647,8 @@ static void __init map_kernel(pgd_t *pgdp)
 		set_pgd(pgd_offset_raw(pgdp, FIXADDR_START),
 			READ_ONCE(*pgd_offset_k(FIXADDR_START)));
 	} else if (CONFIG_PGTABLE_LEVELS > 3) {
+		pgd_t *bm_pgdp;
+		pud_t *bm_pudp;
 		/*
 		 * The fixmap shares its top level pgd entry with the kernel
 		 * mapping. This can really only occur when we are running
@@ -654,9 +656,9 @@ static void __init map_kernel(pgd_t *pgdp)
 		 * entry instead.
 		 */
 		BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES));
-		pud_populate(&init_mm,
-			     pud_set_fixmap_offset(pgdp, FIXADDR_START),
-			     lm_alias(bm_pmd));
+		bm_pgdp = pgd_offset_raw(pgdp, FIXADDR_START);
+		bm_pudp = pud_set_fixmap_offset(bm_pgdp, FIXADDR_START);
+		pud_populate(&init_mm, bm_pudp, lm_alias(bm_pmd));
 		pud_clear_fixmap();
 	} else {
 		BUG();
-- 
cgit v1.2.3