Merge tag 'v5.15.104' into HEAD

This is the 5.15.104 stable release

Signed-off-by: Markus Niebel <Markus.Niebel@ew.tq-group.com>

Documentation/filesystems/vfs.rst

@@ -1210,7 +1210,7 @@ defined:
 	return
 	-ECHILD and it will be called again in ref-walk mode.
 
-``_weak_revalidate``
+``d_weak_revalidate``
 	called when the VFS needs to revalidate a "jumped" dentry.  This
 	is called when a path-walk ends at dentry that was not acquired
 	by doing a lookup in the parent directory.  This includes "/",

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 15
-SUBLEVEL = 103
+SUBLEVEL = 104
 EXTRAVERSION =
 NAME = Trick or Treat
 

arch/riscv/include/asm/mmu.h

@@ -19,8 +19,6 @@ typedef struct {
 #ifdef CONFIG_SMP
 	/* A local icache flush is needed before user execution can resume. */
 	cpumask_t icache_stale_mask;
-	/* A local tlb flush is needed before user execution can resume. */
-	cpumask_t tlb_stale_mask;
 #endif
 } mm_context_t;
 

arch/riscv/include/asm/tlbflush.h

@@ -22,24 +22,6 @@ static inline void local_flush_tlb_page(unsigned long addr)
 {
 	ALT_FLUSH_TLB_PAGE(__asm__ __volatile__ ("sfence.vma %0" : : "r" (addr) : "memory"));
 }
-
-static inline void local_flush_tlb_all_asid(unsigned long asid)
-{
-	__asm__ __volatile__ ("sfence.vma x0, %0"
-			:
-			: "r" (asid)
-			: "memory");
-}
-
-static inline void local_flush_tlb_page_asid(unsigned long addr,
-		unsigned long asid)
-{
-	__asm__ __volatile__ ("sfence.vma %0, %1"
-			:
-			: "r" (addr), "r" (asid)
-			: "memory");
-}
-
 #else /* CONFIG_MMU */
 #define local_flush_tlb_all()			do { } while (0)
 #define local_flush_tlb_page(addr)		do { } while (0)

arch/riscv/mm/context.c

@@ -196,16 +196,6 @@ static void set_mm_asid(struct mm_struct *mm, unsigned int cpu)
 
 	if (need_flush_tlb)
 		local_flush_tlb_all();
-#ifdef CONFIG_SMP
-	else {
-		cpumask_t *mask = &mm->context.tlb_stale_mask;
-
-		if (cpumask_test_cpu(cpu, mask)) {
-			cpumask_clear_cpu(cpu, mask);
-			local_flush_tlb_all_asid(cntx & asid_mask);
-		}
-	}
-#endif
 }
 
 static void set_mm_noasid(struct mm_struct *mm)
@@ -215,12 +205,24 @@ static void set_mm_noasid(struct mm_struct *mm)
 	local_flush_tlb_all();
 }
 
-static inline void set_mm(struct mm_struct *mm, unsigned int cpu)
+static inline void set_mm(struct mm_struct *prev,
+			  struct mm_struct *next, unsigned int cpu)
 {
-	if (static_branch_unlikely(&use_asid_allocator))
-		set_mm_asid(mm, cpu);
-	else
-		set_mm_noasid(mm);
+	/*
+	 * The mm_cpumask indicates which harts' TLBs contain the virtual
+	 * address mapping of the mm. Compared to noasid, using asid
+	 * can't guarantee that stale TLB entries are invalidated because
+	 * the asid mechanism wouldn't flush TLB for every switch_mm for
+	 * performance. So when using asid, keep all CPUs footmarks in
+	 * cpumask() until mm reset.
+	 */
+	cpumask_set_cpu(cpu, mm_cpumask(next));
+	if (static_branch_unlikely(&use_asid_allocator)) {
+		set_mm_asid(next, cpu);
+	} else {
+		cpumask_clear_cpu(cpu, mm_cpumask(prev));
+		set_mm_noasid(next);
+	}
 }
 
 static int __init asids_init(void)
@@ -272,7 +274,8 @@ static int __init asids_init(void)
 }
 early_initcall(asids_init);
 #else
-static inline void set_mm(struct mm_struct *mm, unsigned int cpu)
+static inline void set_mm(struct mm_struct *prev,
+			  struct mm_struct *next, unsigned int cpu)
 {
 	/* Nothing to do here when there is no MMU */
 }
@@ -325,10 +328,7 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	 */
 	cpu = smp_processor_id();
 
-	cpumask_clear_cpu(cpu, mm_cpumask(prev));
-	cpumask_set_cpu(cpu, mm_cpumask(next));
-
-	set_mm(next, cpu);
+	set_mm(prev, next, cpu);
 
 	flush_icache_deferred(next, cpu);
 }

arch/riscv/mm/tlbflush.c

@@ -5,7 +5,23 @@
 #include <linux/sched.h>
 #include <asm/sbi.h>
 #include <asm/mmu_context.h>
-#include <asm/tlbflush.h>
+
+static inline void local_flush_tlb_all_asid(unsigned long asid)
+{
+	__asm__ __volatile__ ("sfence.vma x0, %0"
+			:
+			: "r" (asid)
+			: "memory");
+}
+
+static inline void local_flush_tlb_page_asid(unsigned long addr,
+		unsigned long asid)
+{
+	__asm__ __volatile__ ("sfence.vma %0, %1"
+			:
+			: "r" (addr), "r" (asid)
+			: "memory");
+}
 
 void flush_tlb_all(void)
 {
@@ -15,7 +31,6 @@ void flush_tlb_all(void)
 static void __sbi_tlb_flush_range(struct mm_struct *mm, unsigned long start,
 				  unsigned long size, unsigned long stride)
 {
-	struct cpumask *pmask = &mm->context.tlb_stale_mask;
 	struct cpumask *cmask = mm_cpumask(mm);
 	struct cpumask hmask;
 	unsigned int cpuid;
@@ -30,15 +45,6 @@ static void __sbi_tlb_flush_range(struct mm_struct *mm, unsigned long start,
 	if (static_branch_unlikely(&use_asid_allocator)) {
 		unsigned long asid = atomic_long_read(&mm->context.id);
 
-		/*
-		 * TLB will be immediately flushed on harts concurrently
-		 * executing this MM context. TLB flush on other harts
-		 * is deferred until this MM context migrates there.
-		 */
-		cpumask_setall(pmask);
-		cpumask_clear_cpu(cpuid, pmask);
-		cpumask_andnot(pmask, pmask, cmask);
-
 		if (broadcast) {
 			riscv_cpuid_to_hartid_mask(cmask, &hmask);
 			sbi_remote_sfence_vma_asid(cpumask_bits(&hmask),

arch/s390/boot/ipl_report.c

@@ -57,11 +57,19 @@ static unsigned long find_bootdata_space(struct ipl_rb_components *comps,
 	if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && initrd_data.start && initrd_data.size &&
 	    intersects(initrd_data.start, initrd_data.size, safe_addr, size))
 		safe_addr = initrd_data.start + initrd_data.size;
+	if (intersects(safe_addr, size, (unsigned long)comps, comps->len)) {
+		safe_addr = (unsigned long)comps + comps->len;
+		goto repeat;
+	}
 	for_each_rb_entry(comp, comps)
 		if (intersects(safe_addr, size, comp->addr, comp->len)) {
 			safe_addr = comp->addr + comp->len;
 			goto repeat;
 		}
+	if (intersects(safe_addr, size, (unsigned long)certs, certs->len)) {
+		safe_addr = (unsigned long)certs + certs->len;
+		goto repeat;
+	}
 	for_each_rb_entry(cert, certs)
 		if (intersects(safe_addr, size, cert->addr, cert->len)) {
 			safe_addr = cert->addr + cert->len;

arch/s390/pci/pci.c

@@ -503,8 +503,7 @@ static struct resource *__alloc_res(struct zpci_dev *zdev, unsigned long start,
 	return r;
 }
 
-int zpci_setup_bus_resources(struct zpci_dev *zdev,
-			     struct list_head *resources)
+int zpci_setup_bus_resources(struct zpci_dev *zdev)
 {
 	unsigned long addr, size, flags;
 	struct resource *res;
@@ -540,7 +539,6 @@ int zpci_setup_bus_resources(struct zpci_dev *zdev,
 			return -ENOMEM;
 		}
 		zdev->bars[i].res = res;
-		pci_add_resource(resources, res);
 	}
 	zdev->has_resources = 1;
 
@@ -549,17 +547,23 @@ int zpci_setup_bus_resources(struct zpci_dev *zdev,
 
 static void zpci_cleanup_bus_resources(struct zpci_dev *zdev)
 {
+	struct resource *res;
 	int i;
 
+	pci_lock_rescan_remove();
 	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
-		if (!zdev->bars[i].size || !zdev->bars[i].res)
+		res = zdev->bars[i].res;
+		if (!res)
 			continue;
 
+		release_resource(res);
+		pci_bus_remove_resource(zdev->zbus->bus, res);
 		zpci_free_iomap(zdev, zdev->bars[i].map_idx);
-		release_resource(zdev->bars[i].res);
-		kfree(zdev->bars[i].res);
+		zdev->bars[i].res = NULL;
+		kfree(res);
 	}
 	zdev->has_resources = 0;
+	pci_unlock_rescan_remove();
 }
 
 int pcibios_add_device(struct pci_dev *pdev)

arch/s390/pci/pci_bus.c

@@ -41,9 +41,7 @@ static int zpci_nb_devices;
  */
 static int zpci_bus_prepare_device(struct zpci_dev *zdev)
 {
-	struct resource_entry *window, *n;
-	struct resource *res;
-	int rc;
+	int rc, i;
 
 	if (!zdev_enabled(zdev)) {
 		rc = zpci_enable_device(zdev);
@@ -57,10 +55,10 @@ static int zpci_bus_prepare_device(struct zpci_dev *zdev)
 	}
 
 	if (!zdev->has_resources) {
-		zpci_setup_bus_resources(zdev, &zdev->zbus->resources);
-		resource_list_for_each_entry_safe(window, n, &zdev->zbus->resources) {
-			res = window->res;
-			pci_bus_add_resource(zdev->zbus->bus, res, 0);
+		zpci_setup_bus_resources(zdev);
+		for (i = 0; i < PCI_STD_NUM_BARS; i++) {
+			if (zdev->bars[i].res)
+				pci_bus_add_resource(zdev->zbus->bus, zdev->bars[i].res, 0);
 		}
 	}
 

arch/s390/pci/pci_bus.h

@@ -30,8 +30,7 @@ static inline void zpci_zdev_get(struct zpci_dev *zdev)
 
 int zpci_alloc_domain(int domain);
 void zpci_free_domain(int domain);
-int zpci_setup_bus_resources(struct zpci_dev *zdev,
-			     struct list_head *resources);
+int zpci_setup_bus_resources(struct zpci_dev *zdev);
 
 static inline struct zpci_dev *get_zdev_by_bus(struct pci_bus *bus,
 					       unsigned int devfn)

arch/x86/kernel/cpu/mce/core.c

@@ -2302,6 +2302,7 @@ static void mce_restart(void)
 {
 	mce_timer_delete_all();
 	on_each_cpu(mce_cpu_restart, NULL, 1);
+	mce_schedule_work();
 }
 
 /* Toggle features for corrected errors */

arch/x86/kernel/cpu/resctrl/ctrlmondata.c

@@ -353,7 +353,6 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 {
 	struct resctrl_schema *s;
 	struct rdtgroup *rdtgrp;
-	struct rdt_domain *dom;
 	struct rdt_resource *r;
 	char *tok, *resname;
 	int ret = 0;
@@ -382,10 +381,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 		goto out;
 	}
 
-	list_for_each_entry(s, &resctrl_schema_all, list) {
-		list_for_each_entry(dom, &s->res->domains, list)
-			memset(dom->staged_config, 0, sizeof(dom->staged_config));
-	}
+	rdt_staged_configs_clear();
 
 	while ((tok = strsep(&buf, "\n")) != NULL) {
 		resname = strim(strsep(&tok, ":"));
@@ -422,6 +418,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 	}
 
 out:
+	rdt_staged_configs_clear();
 	rdtgroup_kn_unlock(of->kn);
 	cpus_read_unlock();
 	return ret ?: nbytes;

arch/x86/kernel/cpu/resctrl/internal.h

@@ -550,5 +550,6 @@ bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d);
 void __check_limbo(struct rdt_domain *d, bool force_free);
 void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
 void __init thread_throttle_mode_init(void);
+void rdt_staged_configs_clear(void);
 
 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */

arch/x86/kernel/cpu/resctrl/rdtgroup.c

@@ -78,6 +78,19 @@ void rdt_last_cmd_printf(const char *fmt, ...)
 	va_end(ap);
 }
 
+void rdt_staged_configs_clear(void)
+{
+	struct rdt_resource *r;
+	struct rdt_domain *dom;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	for_each_alloc_capable_rdt_resource(r) {
+		list_for_each_entry(dom, &r->domains, list)
+			memset(dom->staged_config, 0, sizeof(dom->staged_config));
+	}
+}
+
 /*
  * Trivial allocator for CLOSIDs. Since h/w only supports a small number,
  * we can keep a bitmap of free CLOSIDs in a single integer.
@@ -2813,7 +2826,9 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
 {
 	struct resctrl_schema *s;
 	struct rdt_resource *r;
-	int ret;
+	int ret = 0;
+
+	rdt_staged_configs_clear();
 
 	list_for_each_entry(s, &resctrl_schema_all, list) {
 		r = s->res;
@@ -2822,20 +2837,22 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
 		} else {
 			ret = rdtgroup_init_cat(s, rdtgrp->closid);
 			if (ret < 0)
-				return ret;
+				goto out;
 		}
 
 		ret = resctrl_arch_update_domains(r, rdtgrp->closid);
 		if (ret < 0) {
 			rdt_last_cmd_puts("Failed to initialize allocations\n");
-			return ret;
+			goto out;
 		}
 
 	}
 
 	rdtgrp->mode = RDT_MODE_SHAREABLE;
 
-	return 0;
+out:
+	rdt_staged_configs_clear();
+	return ret;
 }
 
 static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,