Merging upstream version 6.8.9.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

17 files changed, 291 insertions, 122 deletions

diff --git a/arch/powerpc/kernel/cpu_specs_book3s_64.h b/arch/powerpc/kernel/cpu_specs_book3s_64.h
index c370c1b804..3ff9757df4 100644
--- a/arch/powerpc/kernel/cpu_specs_book3s_64.h
+++ b/arch/powerpc/kernel/cpu_specs_book3s_64.h
@@ -238,6 +238,21 @@ static struct cpu_spec cpu_specs[] __initdata = {
 		.machine_check_early	= __machine_check_early_realmode_p8,
 		.platform		= "power8",
 	},
+	{	/* 2.07-compliant processor, HeXin C2000 processor */
+		.pvr_mask		= 0xffff0000,
+		.pvr_value		= 0x00660000,
+		.cpu_name		= "HX-C2000",
+		.cpu_features		= CPU_FTRS_POWER8,
+		.cpu_user_features	= COMMON_USER_POWER8,
+		.cpu_user_features2	= COMMON_USER2_POWER8,
+		.mmu_features		= MMU_FTRS_POWER8,
+		.icache_bsize		= 128,
+		.dcache_bsize		= 128,
+		.cpu_setup		= __setup_cpu_power8,
+		.cpu_restore		= __restore_cpu_power8,
+		.machine_check_early	= __machine_check_early_realmode_p8,
+		.platform		= "power8",
+	},
 	{	/* 3.00-compliant processor, i.e. Power9 "architected" mode */
 		.pvr_mask		= 0xffffffff,
 		.pvr_value		= 0x0f000005,
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index e97a0fd0ae..6f6801da9d 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -20,9 +20,9 @@
 #include <asm/setup.h>
 #include <asm/cpu_setup.h>
 
-static struct cpu_spec the_cpu_spec __read_mostly;
+static struct cpu_spec the_cpu_spec __ro_after_init;
 
-struct cpu_spec* cur_cpu_spec __read_mostly = NULL;
+struct cpu_spec *cur_cpu_spec __ro_after_init = NULL;
 EXPORT_SYMBOL(cur_cpu_spec);
 
 /* The platform string corresponding to the real PVR */
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 7ab4c8c0f1..dcf0591ad3 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -14,7 +14,6 @@
 #include <asm/cputable.h>
 #include <asm/setup.h>
 #include <asm/thread_info.h>
-#include <asm/reg_a2.h>
 #include <asm/exception-64e.h>
 #include <asm/bug.h>
 #include <asm/irqflags.h>
diff --git a/arch/powerpc/kernel/firmware.c b/arch/powerpc/kernel/firmware.c
index 20328f72f9..8987eee33d 100644
--- a/arch/powerpc/kernel/firmware.c
+++ b/arch/powerpc/kernel/firmware.c
@@ -23,6 +23,8 @@ EXPORT_SYMBOL_GPL(powerpc_firmware_features);
 
 #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_KVM_GUEST)
 DEFINE_STATIC_KEY_FALSE(kvm_guest);
+EXPORT_SYMBOL_GPL(kvm_guest);
+
 int __init check_kvm_guest(void)
 {
 	struct device_node *hyper_node;
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index c4f6d3c69b..eca293794a 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -3,6 +3,7 @@
 #include <linux/context_tracking.h>
 #include <linux/err.h>
 #include <linux/compat.h>
+#include <linux/rseq.h>
 #include <linux/sched/debug.h> /* for show_regs */
 
 #include <asm/kup.h>
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 2c0173e709..1185efebf0 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1287,7 +1287,6 @@ spapr_tce_platform_iommu_attach_dev(struct iommu_domain *platform_domain,
 	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
 	struct iommu_group *grp = iommu_group_get(dev);
 	struct iommu_table_group *table_group;
-	int ret = -EINVAL;
 
 	/* At first attach the ownership is already set */
 	if (!domain) {
@@ -1295,14 +1294,15 @@ spapr_tce_platform_iommu_attach_dev(struct iommu_domain *platform_domain,
 		return 0;
 	}
 
-	if (!grp)
-		return -ENODEV;
-
 	table_group = iommu_group_get_iommudata(grp);
-	ret = table_group->ops->take_ownership(table_group);
+	/*
+	 * The domain being set to PLATFORM from earlier
+	 * BLOCKED. The table_group ownership has to be released.
+	 */
+	table_group->ops->release_ownership(table_group);
 	iommu_group_put(grp);
 
-	return ret;
+	return 0;
 }
 
 static const struct iommu_domain_ops spapr_tce_platform_domain_ops = {
@@ -1314,13 +1314,32 @@ static struct iommu_domain spapr_tce_platform_domain = {
 	.ops = &spapr_tce_platform_domain_ops,
 };
 
-static struct iommu_domain spapr_tce_blocked_domain = {
-	.type = IOMMU_DOMAIN_BLOCKED,
+static int
+spapr_tce_blocked_iommu_attach_dev(struct iommu_domain *platform_domain,
+				     struct device *dev)
+{
+	struct iommu_group *grp = iommu_group_get(dev);
+	struct iommu_table_group *table_group;
+	int ret = -EINVAL;
+
 	/*
 	 * FIXME: SPAPR mixes blocked and platform behaviors, the blocked domain
 	 * also sets the dma_api ops
 	 */
-	.ops = &spapr_tce_platform_domain_ops,
+	table_group = iommu_group_get_iommudata(grp);
+	ret = table_group->ops->take_ownership(table_group);
+	iommu_group_put(grp);
+
+	return ret;
+}
+
+static const struct iommu_domain_ops spapr_tce_blocked_domain_ops = {
+	.attach_dev = spapr_tce_blocked_iommu_attach_dev,
+};
+
+static struct iommu_domain spapr_tce_blocked_domain = {
+	.type = IOMMU_DOMAIN_BLOCKED,
+	.ops = &spapr_tce_blocked_domain_ops,
 };
 
 static bool spapr_tce_iommu_capable(struct device *dev, enum iommu_cap cap)
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 46b9476d75..8064d9c3de 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -18,6 +18,7 @@
 #include <linux/kernel.h>
 #include <linux/lockdep.h>
 #include <linux/memblock.h>
+#include <linux/mutex.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
 #include <linux/reboot.h>
@@ -70,14 +71,33 @@ struct rtas_filter {
  *                            ppc64le, and we want to keep it that way. It does
  *                            not make sense for this to be set when @filter
  *                            is NULL.
+ * @lock: Pointer to an optional dedicated per-function mutex. This
+ *        should be set for functions that require multiple calls in
+ *        sequence to complete a single operation, and such sequences
+ *        will disrupt each other if allowed to interleave. Users of
+ *        this function are required to hold the associated lock for
+ *        the duration of the call sequence. Add an explanatory
+ *        comment to the function table entry if setting this member.
  */
 struct rtas_function {
 	s32 token;
 	const bool banned_for_syscall_on_le:1;
 	const char * const name;
 	const struct rtas_filter *filter;
+	struct mutex *lock;
 };
 
+/*
+ * Per-function locks for sequence-based RTAS functions.
+ */
+static DEFINE_MUTEX(rtas_ibm_activate_firmware_lock);
+static DEFINE_MUTEX(rtas_ibm_get_dynamic_sensor_state_lock);
+static DEFINE_MUTEX(rtas_ibm_get_indices_lock);
+static DEFINE_MUTEX(rtas_ibm_lpar_perftools_lock);
+static DEFINE_MUTEX(rtas_ibm_physical_attestation_lock);
+static DEFINE_MUTEX(rtas_ibm_set_dynamic_indicator_lock);
+DEFINE_MUTEX(rtas_ibm_get_vpd_lock);
+
 static struct rtas_function rtas_function_table[] __ro_after_init = {
 	[RTAS_FNIDX__CHECK_EXCEPTION] = {
 		.name = "check-exception",
@@ -125,6 +145,13 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 			.buf_idx1 = -1, .size_idx1 = -1,
 			.buf_idx2 = -1, .size_idx2 = -1,
 		},
+		/*
+		 * PAPR+ as of v2.13 doesn't explicitly impose any
+		 * restriction, but this typically requires multiple
+		 * calls before success, and there's no reason to
+		 * allow sequences to interleave.
+		 */
+		.lock = &rtas_ibm_activate_firmware_lock,
 	},
 	[RTAS_FNIDX__IBM_CBE_START_PTCAL] = {
 		.name = "ibm,cbe-start-ptcal",
@@ -196,6 +223,13 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 			.buf_idx1 = 1, .size_idx1 = -1,
 			.buf_idx2 = -1, .size_idx2 = -1,
 		},
+		/*
+		 * PAPR+ v2.13 R1–7.3.19–3 is explicit that the OS
+		 * must not call ibm,get-dynamic-sensor-state with
+		 * different inputs until a non-retry status has been
+		 * returned.
+		 */
+		.lock = &rtas_ibm_get_dynamic_sensor_state_lock,
 	},
 	[RTAS_FNIDX__IBM_GET_INDICES] = {
 		.name = "ibm,get-indices",
@@ -203,6 +237,12 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 			.buf_idx1 = 2, .size_idx1 = 3,
 			.buf_idx2 = -1, .size_idx2 = -1,
 		},
+		/*
+		 * PAPR+ v2.13 R1–7.3.17–2 says that the OS must not
+		 * interleave ibm,get-indices call sequences with
+		 * different inputs.
+		 */
+		.lock = &rtas_ibm_get_indices_lock,
 	},
 	[RTAS_FNIDX__IBM_GET_RIO_TOPOLOGY] = {
 		.name = "ibm,get-rio-topology",
@@ -220,6 +260,11 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 			.buf_idx1 = 0, .size_idx1 = -1,
 			.buf_idx2 = 1, .size_idx2 = 2,
 		},
+		/*
+		 * PAPR+ v2.13 R1–7.3.20–4 indicates that sequences
+		 * should not be allowed to interleave.
+		 */
+		.lock = &rtas_ibm_get_vpd_lock,
 	},
 	[RTAS_FNIDX__IBM_GET_XIVE] = {
 		.name = "ibm,get-xive",
@@ -239,6 +284,11 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 			.buf_idx1 = 2, .size_idx1 = 3,
 			.buf_idx2 = -1, .size_idx2 = -1,
 		},
+		/*
+		 * PAPR+ v2.13 R1–7.3.26–6 says the OS should allow
+		 * only one call sequence in progress at a time.
+		 */
+		.lock = &rtas_ibm_lpar_perftools_lock,
 	},
 	[RTAS_FNIDX__IBM_MANAGE_FLASH_IMAGE] = {
 		.name = "ibm,manage-flash-image",
@@ -277,6 +327,14 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 			.buf_idx1 = 0, .size_idx1 = 1,
 			.buf_idx2 = -1, .size_idx2 = -1,
 		},
+		/*
+		 * This follows a sequence-based pattern similar to
+		 * ibm,get-vpd et al. Since PAPR+ restricts
+		 * interleaving call sequences for other functions of
+		 * this style, assume the restriction applies here,
+		 * even though it's not explicit in the spec.
+		 */
+		.lock = &rtas_ibm_physical_attestation_lock,
 	},
 	[RTAS_FNIDX__IBM_PLATFORM_DUMP] = {
 		.name = "ibm,platform-dump",
@@ -284,6 +342,13 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 			.buf_idx1 = 4, .size_idx1 = 5,
 			.buf_idx2 = -1, .size_idx2 = -1,
 		},
+		/*
+		 * PAPR+ v2.13 7.3.3.4.1 indicates that concurrent
+		 * sequences of ibm,platform-dump are allowed if they
+		 * are operating on different dump tags. So leave the
+		 * lock pointer unset for now. This may need
+		 * reconsideration if kernel-internal users appear.
+		 */
 	},
 	[RTAS_FNIDX__IBM_POWER_OFF_UPS] = {
 		.name = "ibm,power-off-ups",
@@ -331,6 +396,12 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 			.buf_idx1 = 2, .size_idx1 = -1,
 			.buf_idx2 = -1, .size_idx2 = -1,
 		},
+		/*
+		 * PAPR+ v2.13 R1–7.3.18–3 says the OS must not call
+		 * this function with different inputs until a
+		 * non-retry status has been returned.
+		 */
+		.lock = &rtas_ibm_set_dynamic_indicator_lock,
 	},
 	[RTAS_FNIDX__IBM_SET_EEH_OPTION] = {
 		.name = "ibm,set-eeh-option",
@@ -459,6 +530,11 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 	},
 };
 
+#define for_each_rtas_function(funcp)                                       \
+	for (funcp = &rtas_function_table[0];                               \
+	     funcp < &rtas_function_table[ARRAY_SIZE(rtas_function_table)]; \
+	     ++funcp)
+
 /*
  * Nearly all RTAS calls need to be serialized. All uses of the
  * default rtas_args block must hold rtas_lock.
@@ -530,10 +606,10 @@ static DEFINE_XARRAY(rtas_token_to_function_xarray);
 
 static int __init rtas_token_to_function_xarray_init(void)
 {
+	const struct rtas_function *func;
 	int err = 0;
 
-	for (size_t i = 0; i < ARRAY_SIZE(rtas_function_table); ++i) {
-		const struct rtas_function *func = &rtas_function_table[i];
+	for_each_rtas_function(func) {
 		const s32 token = func->token;
 
 		if (token == RTAS_UNKNOWN_SERVICE)
@@ -572,11 +648,21 @@ static const struct rtas_function *rtas_token_to_function(s32 token)
 		return NULL;
 
 	func = rtas_token_to_function_untrusted(token);
+	if (func)
+		return func;
+	/*
+	 * Fall back to linear scan in case the reverse mapping hasn't
+	 * been initialized yet.
+	 */
+	if (xa_empty(&rtas_token_to_function_xarray)) {
+		for_each_rtas_function(func) {
+			if (func->token == token)
+				return func;
+		}
+	}
 
-	if (WARN_ONCE(!func, "unexpected failed lookup for token %d", token))
-		return NULL;
-
-	return func;
+	WARN_ONCE(true, "unexpected failed lookup for token %d", token);
+	return NULL;
 }
 
 /* This is here deliberately so it's only used in this file */
@@ -590,28 +676,25 @@ static void __do_enter_rtas(struct rtas_args *args)
 
 static void __do_enter_rtas_trace(struct rtas_args *args)
 {
-	const char *name = NULL;
+	const struct rtas_function *func = rtas_token_to_function(be32_to_cpu(args->token));
 
-	if (args == &rtas_args)
-		lockdep_assert_held(&rtas_lock);
 	/*
-	 * If the tracepoints that consume the function name aren't
-	 * active, avoid the lookup.
+	 * If there is a per-function lock, it must be held by the
+	 * caller.
 	 */
-	if ((trace_rtas_input_enabled() || trace_rtas_output_enabled())) {
-		const s32 token = be32_to_cpu(args->token);
-		const struct rtas_function *func = rtas_token_to_function(token);
+	if (func->lock)
+		lockdep_assert_held(func->lock);
 
-		name = func->name;
-	}
+	if (args == &rtas_args)
+		lockdep_assert_held(&rtas_lock);
 
-	trace_rtas_input(args, name);
+	trace_rtas_input(args, func->name);
 	trace_rtas_ll_entry(args);
 
 	__do_enter_rtas(args);
 
 	trace_rtas_ll_exit(args);
-	trace_rtas_output(args, name);
+	trace_rtas_output(args, func->name);
 }
 
 static void do_enter_rtas(struct rtas_args *args)
@@ -690,7 +773,7 @@ static void call_rtas_display_status_delay(char c)
 	static int pending_newline = 0;  /* did last write end with unprinted newline? */
 	static int width = 16;
 
-	if (c == '\n') {	
+	if (c == '\n') {
 		while (width-- > 0)
 			call_rtas_display_status(' ');
 		width = 16;
@@ -700,7 +783,7 @@ static void call_rtas_display_status_delay(char c)
 		if (pending_newline) {
 			call_rtas_display_status('\r');
 			call_rtas_display_status('\n');
-		} 
+		}
 		pending_newline = 0;
 		if (width--) {
 			call_rtas_display_status(c);
@@ -840,7 +923,7 @@ void rtas_progress(char *s, unsigned short hex)
 		else
 			rtas_call(display_character, 1, 1, NULL, '\r');
 	}
- 
+
 	if (row_width)
 		width = row_width[current_line];
 	else
@@ -860,9 +943,9 @@ void rtas_progress(char *s, unsigned short hex)
 				spin_unlock(&progress_lock);
 				return;
 			}
- 
+
 			/* RTAS wants CR-LF, not just LF */
- 
+
 			if (*os == '\n') {
 				rtas_call(display_character, 1, 1, NULL, '\r');
 				rtas_call(display_character, 1, 1, NULL, '\n');
@@ -872,7 +955,7 @@ void rtas_progress(char *s, unsigned short hex)
 				 */
 				rtas_call(display_character, 1, 1, NULL, *os);
 			}
- 
+
 			if (row_width)
 				width = row_width[current_line];
 			else
@@ -881,15 +964,15 @@ void rtas_progress(char *s, unsigned short hex)
 			width--;
 			rtas_call(display_character, 1, 1, NULL, *os);
 		}
- 
+
 		os++;
- 
+
 		/* if we overwrite the screen length */
 		if (width <= 0)
 			while ((*os != 0) && (*os != '\n') && (*os != '\r'))
 				os++;
 	}
- 
+
 	spin_unlock(&progress_lock);
 }
 EXPORT_SYMBOL_GPL(rtas_progress);		/* needed by rtas_flash module */
@@ -920,11 +1003,6 @@ int rtas_token(const char *service)
 }
 EXPORT_SYMBOL_GPL(rtas_token);
 
-int rtas_service_present(const char *service)
-{
-	return rtas_token(service) != RTAS_UNKNOWN_SERVICE;
-}
-
 #ifdef CONFIG_RTAS_ERROR_LOGGING
 
 static u32 rtas_error_log_max __ro_after_init = RTAS_ERROR_LOG_MAX;
@@ -1658,10 +1736,14 @@ void rtas_activate_firmware(void)
 		return;
 	}
 
+	mutex_lock(&rtas_ibm_activate_firmware_lock);
+
 	do {
 		fwrc = rtas_call(token, 0, 1, NULL);
 	} while (rtas_busy_delay(fwrc));
 
+	mutex_unlock(&rtas_ibm_activate_firmware_lock);
+
 	if (fwrc)
 		pr_err("ibm,activate-firmware failed (%i)\n", fwrc);
 }
@@ -1733,24 +1815,18 @@ static bool in_rmo_buf(u32 base, u32 end)
 		end < (rtas_rmo_buf + RTAS_USER_REGION_SIZE);
 }
 
-static bool block_rtas_call(int token, int nargs,
+static bool block_rtas_call(const struct rtas_function *func, int nargs,
 			    struct rtas_args *args)
 {
-	const struct rtas_function *func;
 	const struct rtas_filter *f;
-	const bool is_platform_dump = token == rtas_function_token(RTAS_FN_IBM_PLATFORM_DUMP);
-	const bool is_config_conn = token == rtas_function_token(RTAS_FN_IBM_CONFIGURE_CONNECTOR);
+	const bool is_platform_dump =
+		func == &rtas_function_table[RTAS_FNIDX__IBM_PLATFORM_DUMP];
+	const bool is_config_conn =
+		func == &rtas_function_table[RTAS_FNIDX__IBM_CONFIGURE_CONNECTOR];
 	u32 base, size, end;
 
 	/*
-	 * If this token doesn't correspond to a function the kernel
-	 * understands, you're not allowed to call it.
-	 */
-	func = rtas_token_to_function_untrusted(token);
-	if (!func)
-		goto err;
-	/*
-	 * And only functions with filters attached are allowed.
+	 * Only functions with filters attached are allowed.
 	 */
 	f = func->filter;
 	if (!f)
@@ -1807,14 +1883,15 @@ static bool block_rtas_call(int token, int nargs,
 	return false;
 err:
 	pr_err_ratelimited("sys_rtas: RTAS call blocked - exploit attempt?\n");
-	pr_err_ratelimited("sys_rtas: token=0x%x, nargs=%d (called by %s)\n",
-			   token, nargs, current->comm);
+	pr_err_ratelimited("sys_rtas: %s nargs=%d (called by %s)\n",
+			   func->name, nargs, current->comm);
 	return true;
 }
 
 /* We assume to be passed big endian arguments */
 SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
 {
+	const struct rtas_function *func;
 	struct pin_cookie cookie;
 	struct rtas_args args;
 	unsigned long flags;
@@ -1844,13 +1921,18 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
 			   nargs * sizeof(rtas_arg_t)) != 0)
 		return -EFAULT;
 
-	if (token == RTAS_UNKNOWN_SERVICE)
+	/*
+	 * If this token doesn't correspond to a function the kernel
+	 * understands, you're not allowed to call it.
+	 */
+	func = rtas_token_to_function_untrusted(token);
+	if (!func)
 		return -EINVAL;
 
 	args.rets = &args.args[nargs];
 	memset(args.rets, 0, nret * sizeof(rtas_arg_t));
 
-	if (block_rtas_call(token, nargs, &args))
+	if (block_rtas_call(func, nargs, &args))
 		return -EINVAL;
 
 	if (token_is_restricted_errinjct(token)) {
@@ -1883,6 +1965,15 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
 
 	buff_copy = get_errorlog_buffer();
 
+	/*
+	 * If this function has a mutex assigned to it, we must
+	 * acquire it to avoid interleaving with any kernel-based uses
+	 * of the same function. Kernel-based sequences acquire the
+	 * appropriate mutex explicitly.
+	 */
+	if (func->lock)
+		mutex_lock(func->lock);
+
 	raw_spin_lock_irqsave(&rtas_lock, flags);
 	cookie = lockdep_pin_lock(&rtas_lock);
 
@@ -1898,6 +1989,9 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
 	lockdep_unpin_lock(&rtas_lock, cookie);
 	raw_spin_unlock_irqrestore(&rtas_lock, flags);
 
+	if (func->lock)
+		mutex_unlock(func->lock);
+
 	if (buff_copy) {
 		if (errbuf)
 			log_error(errbuf, ERR_TYPE_RTAS_LOG, 0);
diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c
index e1fdc7473b..fccf96e897 100644
--- a/arch/powerpc/kernel/rtas_pci.c
+++ b/arch/powerpc/kernel/rtas_pci.c
@@ -43,7 +43,7 @@ static inline int config_access_valid(struct pci_dn *dn, int where)
 	return 0;
 }
 
-int rtas_read_config(struct pci_dn *pdn, int where, int size, u32 *val)
+int rtas_pci_dn_read_config(struct pci_dn *pdn, int where, int size, u32 *val)
 {
 	int returnval = -1;
 	unsigned long buid, addr;
@@ -87,7 +87,7 @@ static int rtas_pci_read_config(struct pci_bus *bus,
 	pdn = pci_get_pdn_by_devfn(bus, devfn);
 
 	/* Validity of pdn is checked in here */
-	ret = rtas_read_config(pdn, where, size, val);
+	ret = rtas_pci_dn_read_config(pdn, where, size, val);
 	if (*val == EEH_IO_ERROR_VALUE(size) &&
 	    eeh_dev_check_failure(pdn_to_eeh_dev(pdn)))
 		return PCIBIOS_DEVICE_NOT_FOUND;
@@ -95,7 +95,7 @@ static int rtas_pci_read_config(struct pci_bus *bus,
 	return ret;
 }
 
-int rtas_write_config(struct pci_dn *pdn, int where, int size, u32 val)
+int rtas_pci_dn_write_config(struct pci_dn *pdn, int where, int size, u32 val)
 {
 	unsigned long buid, addr;
 	int ret;
@@ -134,7 +134,7 @@ static int rtas_pci_write_config(struct pci_bus *bus,
 	pdn = pci_get_pdn_by_devfn(bus, devfn);
 
 	/* Validity of pdn is checked in here. */
-	return rtas_write_config(pdn, where, size, val);
+	return rtas_pci_dn_write_config(pdn, where, size, val);
 }
 
 static struct pci_ops rtas_pci_ops = {
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index ab691c89d7..693334c20d 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -77,10 +77,10 @@ static DEFINE_PER_CPU(int, cpu_state) = { 0 };
 #endif
 
 struct task_struct *secondary_current;
-bool has_big_cores;
-bool coregroup_enabled;
-bool thread_group_shares_l2;
-bool thread_group_shares_l3;
+bool has_big_cores __ro_after_init;
+bool coregroup_enabled __ro_after_init;
+bool thread_group_shares_l2 __ro_after_init;
+bool thread_group_shares_l3 __ro_after_init;
 
 DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
 DEFINE_PER_CPU(cpumask_var_t, cpu_smallcore_map);
@@ -93,15 +93,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_l2_cache_map);
 EXPORT_PER_CPU_SYMBOL(cpu_core_map);
 EXPORT_SYMBOL_GPL(has_big_cores);
 
-enum {
-#ifdef CONFIG_SCHED_SMT
-	smt_idx,
-#endif
-	cache_idx,
-	mc_idx,
-	die_idx,
-};
-
 #define MAX_THREAD_LIST_SIZE	8
 #define THREAD_GROUP_SHARE_L1   1
 #define THREAD_GROUP_SHARE_L2_L3 2
@@ -987,7 +978,7 @@ static int __init init_thread_group_cache_map(int cpu, int cache_property)
 	return 0;
 }
 
-static bool shared_caches;
+static bool shared_caches __ro_after_init;
 
 #ifdef CONFIG_SCHED_SMT
 /* cpumask of CPUs with asymmetric SMT dependency */
@@ -1004,6 +995,13 @@ static int powerpc_smt_flags(void)
 #endif
 
 /*
+ * On shared processor LPARs scheduled on a big core (which has two or more
+ * independent thread groups per core), prefer lower numbered CPUs, so
+ * that workload consolidates to lesser number of cores.
+ */
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(splpar_asym_pack);
+
+/*
  * P9 has a slightly odd architecture where pairs of cores share an L2 cache.
  * This topology makes it *much* cheaper to migrate tasks between adjacent cores
  * since the migrated task remains cache hot. We want to take advantage of this
@@ -1011,9 +1009,20 @@ static int powerpc_smt_flags(void)
  */
 static int powerpc_shared_cache_flags(void)
 {
+	if (static_branch_unlikely(&splpar_asym_pack))
+		return SD_SHARE_PKG_RESOURCES | SD_ASYM_PACKING;
+
 	return SD_SHARE_PKG_RESOURCES;
 }
 
+static int powerpc_shared_proc_flags(void)
+{
+	if (static_branch_unlikely(&splpar_asym_pack))
+		return SD_ASYM_PACKING;
+
+	return 0;
+}
+
 /*
  * We can't just pass cpu_l2_cache_mask() directly because
  * returns a non-const pointer and the compiler barfs on that.
@@ -1037,6 +1046,10 @@ static struct cpumask *cpu_coregroup_mask(int cpu)
 
 static bool has_coregroup_support(void)
 {
+	/* Coregroup identification not available on shared systems */
+	if (is_shared_processor())
+		return 0;
+
 	return coregroup_enabled;
 }
 
@@ -1045,16 +1058,6 @@ static const struct cpumask *cpu_mc_mask(int cpu)
 	return cpu_coregroup_mask(cpu);
 }
 
-static struct sched_domain_topology_level powerpc_topology[] = {
-#ifdef CONFIG_SCHED_SMT
-	{ cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
-#endif
-	{ shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) },
-	{ cpu_mc_mask, SD_INIT_NAME(MC) },
-	{ cpu_cpu_mask, SD_INIT_NAME(PKG) },
-	{ NULL, },
-};
-
 static int __init init_big_cores(void)
 {
 	int cpu;
@@ -1682,43 +1685,45 @@ void start_secondary(void *unused)
 	BUG();
 }
 
-static void __init fixup_topology(void)
+static struct sched_domain_topology_level powerpc_topology[6];
+
+static void __init build_sched_topology(void)
 {
-	int i;
+	int i = 0;
+
+	if (is_shared_processor() && has_big_cores)
+		static_branch_enable(&splpar_asym_pack);
 
 #ifdef CONFIG_SCHED_SMT
 	if (has_big_cores) {
 		pr_info("Big cores detected but using small core scheduling\n");
-		powerpc_topology[smt_idx].mask = smallcore_smt_mask;
+		powerpc_topology[i++] = (struct sched_domain_topology_level){
+			smallcore_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT)
+		};
+	} else {
+		powerpc_topology[i++] = (struct sched_domain_topology_level){
+			cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT)
+		};
 	}
 #endif
+	if (shared_caches) {
+		powerpc_topology[i++] = (struct sched_domain_topology_level){
+			shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE)
+		};
+	}
+	if (has_coregroup_support()) {
+		powerpc_topology[i++] = (struct sched_domain_topology_level){
+			cpu_mc_mask, powerpc_shared_proc_flags, SD_INIT_NAME(MC)
+		};
+	}
+	powerpc_topology[i++] = (struct sched_domain_topology_level){
+		cpu_cpu_mask, powerpc_shared_proc_flags, SD_INIT_NAME(PKG)
+	};
 
-	if (!has_coregroup_support())
-		powerpc_topology[mc_idx].mask = powerpc_topology[cache_idx].mask;
-
-	/*
-	 * Try to consolidate topology levels here instead of
-	 * allowing scheduler to degenerate.
-	 * - Dont consolidate if masks are different.
-	 * - Dont consolidate if sd_flags exists and are different.
-	 */
-	for (i = 1; i <= die_idx; i++) {
-		if (powerpc_topology[i].mask != powerpc_topology[i - 1].mask)
-			continue;
-
-		if (powerpc_topology[i].sd_flags && powerpc_topology[i - 1].sd_flags &&
-				powerpc_topology[i].sd_flags != powerpc_topology[i - 1].sd_flags)
-			continue;
-
-		if (!powerpc_topology[i - 1].sd_flags)
-			powerpc_topology[i - 1].sd_flags = powerpc_topology[i].sd_flags;
+	/* There must be one trailing NULL entry left.  */
+	BUG_ON(i >= ARRAY_SIZE(powerpc_topology) - 1);
 
-		powerpc_topology[i].mask = powerpc_topology[i + 1].mask;
-		powerpc_topology[i].sd_flags = powerpc_topology[i + 1].sd_flags;
-#ifdef CONFIG_SCHED_DEBUG
-		powerpc_topology[i].name = powerpc_topology[i + 1].name;
-#endif
-	}
+	set_sched_topology(powerpc_topology);
 }
 
 void __init smp_cpus_done(unsigned int max_cpus)
@@ -1733,9 +1738,20 @@ void __init smp_cpus_done(unsigned int max_cpus)
 		smp_ops->bringup_done();
 
 	dump_numa_cpu_topology();
+	build_sched_topology();
+}
 
-	fixup_topology();
-	set_sched_topology(powerpc_topology);
+/*
+ * For asym packing, by default lower numbered CPU has higher priority.
+ * On shared processors, pack to lower numbered core. However avoid moving
+ * between thread_groups within the same core.
+ */
+int arch_asym_cpu_priority(int cpu)
+{
+	if (static_branch_unlikely(&splpar_asym_pack))
+		return -cpu / threads_per_core;
+
+	return -cpu;
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/powerpc/kernel/swsusp_64.c b/arch/powerpc/kernel/swsusp_64.c
index 16ee3baaf0..50fa8fc9ef 100644
--- a/arch/powerpc/kernel/swsusp_64.c
+++ b/arch/powerpc/kernel/swsusp_64.c
@@ -11,6 +11,8 @@
 #include <linux/interrupt.h>
 #include <linux/nmi.h>
 
+void do_after_copyback(void);
+
 void do_after_copyback(void)
 {
 	iommu_restore();
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 7fab411378..17173b82ca 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -543,3 +543,8 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount
+459	common	lsm_get_self_attr		sys_lsm_get_self_attr
+460	common	lsm_set_self_attr		sys_lsm_set_self_attr
+461	common	lsm_list_modules		sys_lsm_list_modules
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 82010629cf..d8d6b4fd9a 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -27,10 +27,22 @@
 #include <asm/ftrace.h>
 #include <asm/syscall.h>
 #include <asm/inst.h>
+#include <asm/sections.h>
 
 #define	NUM_FTRACE_TRAMPS	2
 static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS];
 
+unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	if (addr >= (unsigned long)__exittext_begin && addr < (unsigned long)__exittext_end)
+		return 0;
+
+	if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY))
+		addr += MCOUNT_INSN_SIZE;
+
+	return addr;
+}
+
 static ppc_inst_t ftrace_create_branch_inst(unsigned long ip, unsigned long addr, int link)
 {
 	ppc_inst_t op;
diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.c b/arch/powerpc/kernel/trace/ftrace_64_pg.c
index 7b85c3b460..12fab1803b 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_pg.c
+++ b/arch/powerpc/kernel/trace/ftrace_64_pg.c
@@ -37,6 +37,11 @@
 #define	NUM_FTRACE_TRAMPS	8
 static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS];
 
+unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	return addr;
+}
+
 static ppc_inst_t
 ftrace_call_replace(unsigned long ip, unsigned long addr, int link)
 {
diff --git a/arch/powerpc/kernel/trace/ftrace_entry.S b/arch/powerpc/kernel/trace/ftrace_entry.S
index 40677416d7..76dbe9fd2c 100644
--- a/arch/powerpc/kernel/trace/ftrace_entry.S
+++ b/arch/powerpc/kernel/trace/ftrace_entry.S
@@ -162,7 +162,6 @@ _GLOBAL(ftrace_regs_caller)
 .globl ftrace_regs_call
 ftrace_regs_call:
 	bl	ftrace_stub
-	nop
 	ftrace_regs_exit 1
 
 _GLOBAL(ftrace_caller)
@@ -171,7 +170,6 @@ _GLOBAL(ftrace_caller)
 .globl ftrace_call
 ftrace_call:
 	bl	ftrace_stub
-	nop
 	ftrace_regs_exit 0
 
 _GLOBAL(ftrace_stub)
diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c
index 74ddf836f7..a0467e528b 100644
--- a/arch/powerpc/kernel/udbg_16550.c
+++ b/arch/powerpc/kernel/udbg_16550.c
@@ -7,7 +7,6 @@
 #include <linux/types.h>
 #include <asm/udbg.h>
 #include <asm/io.h>
-#include <asm/reg_a2.h>
 #include <asm/early_ioremap.h>
 
 extern u8 real_readb(volatile u8 __iomem  *addr);
diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile
index 0c7d82c270..1b93655c28 100644
--- a/arch/powerpc/kernel/vdso/Makefile
+++ b/arch/powerpc/kernel/vdso/Makefile
@@ -71,7 +71,7 @@ AS64FLAGS := -D__VDSO64__
 targets += vdso32.lds
 CPPFLAGS_vdso32.lds += -P -C -Upowerpc
 targets += vdso64.lds
-CPPFLAGS_vdso64.lds += -P -C -U$(ARCH)
+CPPFLAGS_vdso64.lds += -P -C
 
 # link rule for the .so file, .lds has to be first
 $(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) $(obj)/vgettimeofday-32.o FORCE
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 1c5970df32..f420df7888 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -281,7 +281,9 @@ SECTIONS
 	 * to deal with references from __bug_table
 	 */
 	.exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) {
+		__exittext_begin = .;
 		EXIT_TEXT
+		__exittext_end = .;
 	}
 
 	. = ALIGN(PAGE_SIZE);