Merge tag 'powerpc-5.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - Enable STRICT_KERNEL_RWX for Freescale 85xx platforms.

 - Activate CONFIG_STRICT_KERNEL_RWX by default, while still allowing it
   to be disabled.

 - Add support for out-of-line static calls on 32-bit.

 - Fix oopses doing bpf-to-bpf calls when STRICT_KERNEL_RWX is enabled.

 - Fix boot hangs on e5500 due to stale value in ESR passed to
   do_page_fault().

 - Fix several bugs on pseries in handling of device tree cache
   information for hotplugged CPUs, and/or during partition migration.

 - Various other small features and fixes.

Thanks to Alexey Kardashevskiy, Alistair Popple, Anatolij Gustschin,
Andrew Donnellan, Athira Rajeev, Bixuan Cui, Bjorn Helgaas, Cédric Le
Goater, Christophe Leroy, Daniel Axtens, Daniel Henrique Barboza, Denis
Kirjanov, Fabiano Rosas, Frederic Barrat, Gustavo A.  R.  Silva, Hari
Bathini, Jacques de Laval, Joel Stanley, Kai Song, Kajol Jain, Laurent
Vivier, Leonardo Bras, Madhavan Srinivasan, Nathan Chancellor, Nathan
Lynch, Naveen N.  Rao, Nicholas Piggin, Nick Desaulniers, Niklas
Schnelle, Oliver O'Halloran, Rob Herring, Russell Currey, Srikar
Dronamraju, Stan Johnson, Tyrel Datwyler, Uwe Kleine-König, Vasant
Hegde, Wan Jiabing, and Xiaoming Ni,

* tag 'powerpc-5.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (73 commits)
  powerpc/8xx: Fix Oops with STRICT_KERNEL_RWX without DEBUG_RODATA_TEST
  powerpc/32e: Ignore ESR in instruction storage interrupt handler
  powerpc/powernv/prd: Unregister OPAL_MSG_PRD2 notifier during module unload
  powerpc: Don't provide __kernel_map_pages() without ARCH_SUPPORTS_DEBUG_PAGEALLOC
  MAINTAINERS: Update powerpc KVM entry
  powerpc/xmon: fix task state output
  powerpc/44x/fsp2: add missing of_node_put
  powerpc/dcr: Use cmplwi instead of 3-argument cmpli
  KVM: PPC: Tick accounting should defer vtime accounting 'til after IRQ handling
  powerpc/security: Use a mutex for interrupt exit code patching
  powerpc/83xx/mpc8349emitx: Make mcu_gpiochip_remove() return void
  powerpc/fsl_booke: Fix setting of exec flag when setting TLBCAMs
  powerpc/book3e: Fix set_memory_x() and set_memory_nx()
  powerpc/nohash: Fix __ptep_set_access_flags() and ptep_set_wrprotect()
  powerpc/bpf: Fix write protecting JIT code
  selftests/powerpc: Use date instead of EPOCHSECONDS in mitigation-patching.sh
  powerpc/64s/interrupt: Fix check_return_regs_valid() false positive
  powerpc/boot: Set LC_ALL=C in wrapper script
  powerpc/64s: Default to 64K pages for 64 bit book3s
  Revert "powerpc/audit: Convert powerpc to AUDIT_ARCH_COMPAT_GENERIC"
  ...

4 files changed, 116 insertions, 233 deletions

diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index d646c22e94ab..5ab44600c8d3 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -137,11 +137,6 @@ static void pseries_cpu_die(unsigned int cpu)
 			cpu, pcpu);
 	}
 
-	/* Isolation and deallocation are definitely done by
-	 * drslot_chrp_cpu.  If they were not they would be
-	 * done here.  Change isolate state to Isolate and
-	 * change allocation-state to Unusable.
-	 */
 	paca_ptrs[cpu]->cpu_start = 0;
 }
 
@@ -521,6 +516,27 @@ static bool valid_cpu_drc_index(struct device_node *parent, u32 drc_index)
 	return found;
 }
 
+static int pseries_cpuhp_attach_nodes(struct device_node *dn)
+{
+	struct of_changeset cs;
+	int ret;
+
+	/*
+	 * This device node is unattached but may have siblings; open-code the
+	 * traversal.
+	 */
+	for (of_changeset_init(&cs); dn != NULL; dn = dn->sibling) {
+		ret = of_changeset_attach_node(&cs, dn);
+		if (ret)
+			goto out;
+	}
+
+	ret = of_changeset_apply(&cs);
+out:
+	of_changeset_destroy(&cs);
+	return ret;
+}
+
 static ssize_t dlpar_cpu_add(u32 drc_index)
 {
 	struct device_node *dn, *parent;
@@ -563,7 +579,7 @@ static ssize_t dlpar_cpu_add(u32 drc_index)
 		return -EINVAL;
 	}
 
-	rc = dlpar_attach_node(dn, parent);
+	rc = pseries_cpuhp_attach_nodes(dn);
 
 	/* Regardless we are done with parent now */
 	of_node_put(parent);
@@ -600,6 +616,53 @@ static ssize_t dlpar_cpu_add(u32 drc_index)
 	return rc;
 }
 
+static unsigned int pseries_cpuhp_cache_use_count(const struct device_node *cachedn)
+{
+	unsigned int use_count = 0;
+	struct device_node *dn;
+
+	WARN_ON(!of_node_is_type(cachedn, "cache"));
+
+	for_each_of_cpu_node(dn) {
+		if (of_find_next_cache_node(dn) == cachedn)
+			use_count++;
+	}
+
+	for_each_node_by_type(dn, "cache") {
+		if (of_find_next_cache_node(dn) == cachedn)
+			use_count++;
+	}
+
+	return use_count;
+}
+
+static int pseries_cpuhp_detach_nodes(struct device_node *cpudn)
+{
+	struct device_node *dn;
+	struct of_changeset cs;
+	int ret = 0;
+
+	of_changeset_init(&cs);
+	ret = of_changeset_detach_node(&cs, cpudn);
+	if (ret)
+		goto out;
+
+	dn = cpudn;
+	while ((dn = of_find_next_cache_node(dn))) {
+		if (pseries_cpuhp_cache_use_count(dn) > 1)
+			break;
+
+		ret = of_changeset_detach_node(&cs, dn);
+		if (ret)
+			goto out;
+	}
+
+	ret = of_changeset_apply(&cs);
+out:
+	of_changeset_destroy(&cs);
+	return ret;
+}
+
 static ssize_t dlpar_cpu_remove(struct device_node *dn, u32 drc_index)
 {
 	int rc;
@@ -621,7 +684,7 @@ static ssize_t dlpar_cpu_remove(struct device_node *dn, u32 drc_index)
 		return rc;
 	}
 
-	rc = dlpar_detach_node(dn);
+	rc = pseries_cpuhp_detach_nodes(dn);
 	if (rc) {
 		int saved_rc = rc;
 
@@ -673,231 +736,18 @@ static int dlpar_cpu_remove_by_index(u32 drc_index)
 	return rc;
 }
 
-static int find_dlpar_cpus_to_remove(u32 *cpu_drcs, int cpus_to_remove)
-{
-	struct device_node *dn;
-	int cpus_found = 0;
-	int rc;
-
-	/* We want to find cpus_to_remove + 1 CPUs to ensure we do not
-	 * remove the last CPU.
-	 */
-	for_each_node_by_type(dn, "cpu") {
-		cpus_found++;
-
-		if (cpus_found > cpus_to_remove) {
-			of_node_put(dn);
-			break;
-		}
-
-		/* Note that cpus_found is always 1 ahead of the index
-		 * into the cpu_drcs array, so we use cpus_found - 1
-		 */
-		rc = of_property_read_u32(dn, "ibm,my-drc-index",
-					  &cpu_drcs[cpus_found - 1]);
-		if (rc) {
-			pr_warn("Error occurred getting drc-index for %pOFn\n",
-				dn);
-			of_node_put(dn);
-			return -1;
-		}
-	}
-
-	if (cpus_found < cpus_to_remove) {
-		pr_warn("Failed to find enough CPUs (%d of %d) to remove\n",
-			cpus_found, cpus_to_remove);
-	} else if (cpus_found == cpus_to_remove) {
-		pr_warn("Cannot remove all CPUs\n");
-	}
-
-	return cpus_found;
-}
-
-static int dlpar_cpu_remove_by_count(u32 cpus_to_remove)
-{
-	u32 *cpu_drcs;
-	int cpus_found;
-	int cpus_removed = 0;
-	int i, rc;
-
-	pr_debug("Attempting to hot-remove %d CPUs\n", cpus_to_remove);
-
-	cpu_drcs = kcalloc(cpus_to_remove, sizeof(*cpu_drcs), GFP_KERNEL);
-	if (!cpu_drcs)
-		return -EINVAL;
-
-	cpus_found = find_dlpar_cpus_to_remove(cpu_drcs, cpus_to_remove);
-	if (cpus_found <= cpus_to_remove) {
-		kfree(cpu_drcs);
-		return -EINVAL;
-	}
-
-	for (i = 0; i < cpus_to_remove; i++) {
-		rc = dlpar_cpu_remove_by_index(cpu_drcs[i]);
-		if (rc)
-			break;
-
-		cpus_removed++;
-	}
-
-	if (cpus_removed != cpus_to_remove) {
-		pr_warn("CPU hot-remove failed, adding back removed CPUs\n");
-
-		for (i = 0; i < cpus_removed; i++)
-			dlpar_cpu_add(cpu_drcs[i]);
-
-		rc = -EINVAL;
-	} else {
-		rc = 0;
-	}
-
-	kfree(cpu_drcs);
-	return rc;
-}
-
-static int find_drc_info_cpus_to_add(struct device_node *cpus,
-				     struct property *info,
-				     u32 *cpu_drcs, u32 cpus_to_add)
-{
-	struct of_drc_info drc;
-	const __be32 *value;
-	u32 count, drc_index;
-	int cpus_found = 0;
-	int i, j;
-
-	if (!info)
-		return -1;
-
-	value = of_prop_next_u32(info, NULL, &count);
-	if (value)
-		value++;
-
-	for (i = 0; i < count; i++) {
-		of_read_drc_info_cell(&info, &value, &drc);
-		if (strncmp(drc.drc_type, "CPU", 3))
-			break;
-
-		drc_index = drc.drc_index_start;
-		for (j = 0; j < drc.num_sequential_elems; j++) {
-			if (dlpar_cpu_exists(cpus, drc_index))
-				continue;
-
-			cpu_drcs[cpus_found++] = drc_index;
-
-			if (cpus_found == cpus_to_add)
-				return cpus_found;
-
-			drc_index += drc.sequential_inc;
-		}
-	}
-
-	return cpus_found;
-}
-
-static int find_drc_index_cpus_to_add(struct device_node *cpus,
-				      u32 *cpu_drcs, u32 cpus_to_add)
-{
-	int cpus_found = 0;
-	int index, rc;
-	u32 drc_index;
-
-	/* Search the ibm,drc-indexes array for possible CPU drcs to
-	 * add. Note that the format of the ibm,drc-indexes array is
-	 * the number of entries in the array followed by the array
-	 * of drc values so we start looking at index = 1.
-	 */
-	index = 1;
-	while (cpus_found < cpus_to_add) {
-		rc = of_property_read_u32_index(cpus, "ibm,drc-indexes",
-						index++, &drc_index);
-
-		if (rc)
-			break;
-
-		if (dlpar_cpu_exists(cpus, drc_index))
-			continue;
-
-		cpu_drcs[cpus_found++] = drc_index;
-	}
-
-	return cpus_found;
-}
-
-static int dlpar_cpu_add_by_count(u32 cpus_to_add)
-{
-	struct device_node *parent;
-	struct property *info;
-	u32 *cpu_drcs;
-	int cpus_added = 0;
-	int cpus_found;
-	int i, rc;
-
-	pr_debug("Attempting to hot-add %d CPUs\n", cpus_to_add);
-
-	cpu_drcs = kcalloc(cpus_to_add, sizeof(*cpu_drcs), GFP_KERNEL);
-	if (!cpu_drcs)
-		return -EINVAL;
-
-	parent = of_find_node_by_path("/cpus");
-	if (!parent) {
-		pr_warn("Could not find CPU root node in device tree\n");
-		kfree(cpu_drcs);
-		return -1;
-	}
-
-	info = of_find_property(parent, "ibm,drc-info", NULL);
-	if (info)
-		cpus_found = find_drc_info_cpus_to_add(parent, info, cpu_drcs, cpus_to_add);
-	else
-		cpus_found = find_drc_index_cpus_to_add(parent, cpu_drcs, cpus_to_add);
-
-	of_node_put(parent);
-
-	if (cpus_found < cpus_to_add) {
-		pr_warn("Failed to find enough CPUs (%d of %d) to add\n",
-			cpus_found, cpus_to_add);
-		kfree(cpu_drcs);
-		return -EINVAL;
-	}
-
-	for (i = 0; i < cpus_to_add; i++) {
-		rc = dlpar_cpu_add(cpu_drcs[i]);
-		if (rc)
-			break;
-
-		cpus_added++;
-	}
-
-	if (cpus_added < cpus_to_add) {
-		pr_warn("CPU hot-add failed, removing any added CPUs\n");
-
-		for (i = 0; i < cpus_added; i++)
-			dlpar_cpu_remove_by_index(cpu_drcs[i]);
-
-		rc = -EINVAL;
-	} else {
-		rc = 0;
-	}
-
-	kfree(cpu_drcs);
-	return rc;
-}
-
 int dlpar_cpu(struct pseries_hp_errorlog *hp_elog)
 {
-	u32 count, drc_index;
+	u32 drc_index;
 	int rc;
 
-	count = hp_elog->_drc_u.drc_count;
 	drc_index = hp_elog->_drc_u.drc_index;
 
 	lock_device_hotplug();
 
 	switch (hp_elog->action) {
 	case PSERIES_HP_ELOG_ACTION_REMOVE:
-		if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_COUNT)
-			rc = dlpar_cpu_remove_by_count(count);
-		else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX) {
+		if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX) {
 			rc = dlpar_cpu_remove_by_index(drc_index);
 			/*
 			 * Setting the isolation state of an UNISOLATED/CONFIGURED
@@ -911,9 +761,7 @@ int dlpar_cpu(struct pseries_hp_errorlog *hp_elog)
 			rc = -EINVAL;
 		break;
 	case PSERIES_HP_ELOG_ACTION_ADD:
-		if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_COUNT)
-			rc = dlpar_cpu_add_by_count(count);
-		else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX)
+		if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX)
 			rc = dlpar_cpu_add(drc_index);
 		else
 			rc = -EINVAL;
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index a52af8fbf571..49b401536d29 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -929,8 +929,10 @@ static void find_existing_ddw_windows_named(const char *name)
 		}
 
 		window = ddw_list_new_entry(pdn, dma64);
-		if (!window)
+		if (!window) {
+			of_node_put(pdn);
 			break;
+		}
 
 		spin_lock(&dma_win_list_lock);
 		list_add(&window->list, &dma_win_list);
@@ -1159,14 +1161,15 @@ static void reset_dma_window(struct pci_dev *dev, struct device_node *par_dn)
 /* Return largest page shift based on "IO Page Sizes" output of ibm,query-pe-dma-window. */
 static int iommu_get_page_shift(u32 query_page_size)
 {
-	/* Supported IO page-sizes according to LoPAR */
+	/* Supported IO page-sizes according to LoPAR, note that 2M is out of order */
 	const int shift[] = {
 		__builtin_ctzll(SZ_4K),   __builtin_ctzll(SZ_64K), __builtin_ctzll(SZ_16M),
 		__builtin_ctzll(SZ_32M),  __builtin_ctzll(SZ_64M), __builtin_ctzll(SZ_128M),
-		__builtin_ctzll(SZ_256M), __builtin_ctzll(SZ_16G)
+		__builtin_ctzll(SZ_256M), __builtin_ctzll(SZ_16G), __builtin_ctzll(SZ_2M)
 	};
 
 	int i = ARRAY_SIZE(shift) - 1;
+	int ret = 0;
 
 	/*
 	 * On LoPAR, ibm,query-pe-dma-window outputs "IO Page Sizes" using a bit field:
@@ -1176,11 +1179,10 @@ static int iommu_get_page_shift(u32 query_page_size)
 	 */
 	for (; i >= 0 ; i--) {
 		if (query_page_size & (1 << i))
-			return shift[i];
+			ret = max(ret, shift[i]);
 	}
 
-	/* No valid page size found. */
-	return 0;
+	return ret;
 }
 
 static struct property *ddw_property_create(const char *propname, u32 liobn, u64 dma_addr,
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index e83e0891272d..210a37a065fb 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -63,6 +63,27 @@ static int mobility_rtas_call(int token, char *buf, s32 scope)
 
 static int delete_dt_node(struct device_node *dn)
 {
+	struct device_node *pdn;
+	bool is_platfac;
+
+	pdn = of_get_parent(dn);
+	is_platfac = of_node_is_type(dn, "ibm,platform-facilities") ||
+		     of_node_is_type(pdn, "ibm,platform-facilities");
+	of_node_put(pdn);
+
+	/*
+	 * The drivers that bind to nodes in the platform-facilities
+	 * hierarchy don't support node removal, and the removal directive
+	 * from firmware is always followed by an add of an equivalent
+	 * node. The capability (e.g. RNG, encryption, compression)
+	 * represented by the node is never interrupted by the migration.
+	 * So ignore changes to this part of the tree.
+	 */
+	if (is_platfac) {
+		pr_notice("ignoring remove operation for %pOFfp\n", dn);
+		return 0;
+	}
+
 	pr_debug("removing node %pOFfp\n", dn);
 	dlpar_detach_node(dn);
 	return 0;
@@ -222,6 +243,19 @@ static int add_dt_node(struct device_node *parent_dn, __be32 drc_index)
 	if (!dn)
 		return -ENOENT;
 
+	/*
+	 * Since delete_dt_node() ignores this node type, this is the
+	 * necessary counterpart. We also know that a platform-facilities
+	 * node returned from dlpar_configure_connector() has children
+	 * attached, and dlpar_attach_node() only adds the parent, leaking
+	 * the children. So ignore these on the add side for now.
+	 */
+	if (of_node_is_type(dn, "ibm,platform-facilities")) {
+		pr_notice("ignoring add operation for %pOF\n", dn);
+		dlpar_free_cc_nodes(dn);
+		return 0;
+	}
+
 	rc = dlpar_attach_node(dn, parent_dn);
 	if (rc)
 		dlpar_free_cc_nodes(dn);
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index f79126f16258..2188054470c1 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -74,7 +74,6 @@
 #include <asm/hvconsole.h>
 
 #include "pseries.h"
-#include "../../../../drivers/pci/pci.h"
 
 DEFINE_STATIC_KEY_FALSE(shared_processor);
 EXPORT_SYMBOL(shared_processor);
@@ -750,7 +749,7 @@ static void pseries_pci_fixup_iov_resources(struct pci_dev *pdev)
 	const int *indexes;
 	struct device_node *dn = pci_device_to_OF_node(pdev);
 
-	if (!pdev->is_physfn || pci_dev_is_added(pdev))
+	if (!pdev->is_physfn)
 		return;
 	/*Firmware must support open sriov otherwise dont configure*/
 	indexes = of_get_property(dn, "ibm,open-sriov-vf-bar-info", NULL);