6.12.48-rc1 review

index 82df28d45cd70..ff90f8203015e 100644
@@ -176,6 +176,14 @@ static int vfs_dentry_acceptable(void *context, struct dentry *dentry)
 	if (!ctx->flags)
 		return 1;
 
+	/*
+	 * Verify that the decoded dentry itself has a valid id mapping.
+	 * In case the decoded dentry is the mountfd root itself, this
+	 * verifies that the mountfd inode itself has a valid id mapping.
+	 */
+	if (!privileged_wrt_inode_uidgid(user_ns, idmap, d_inode(dentry)))
+		return 0;
+
 	/*
 	 * It's racy as we're not taking rename_lock but we're able to ignore
 	 * permissions and we just need an approximation whether we were able

index f6f0387761d05..4e3692afdf0d2 100644
@@ -59,8 +59,7 @@ enum map_err_types {
  * @direction: enum dma_data_direction
  * @sg_call_ents: 'nents' from dma_map_sg
  * @sg_mapped_ents: 'mapped_ents' from dma_map_sg
- * @pfn: page frame of the start address
- * @offset: offset of mapping relative to pfn
+ * @paddr: physical start address of the mapping
  * @map_err_type: track whether dma_mapping_error() was checked
  * @stack_len: number of backtrace entries in @stack_entries
  * @stack_entries: stack of backtrace history

@@ -74,8 +73,7 @@ struct dma_debug_entry {
 	int              direction;
 	int		 sg_call_ents;
 	int		 sg_mapped_ents;
-	unsigned long	 pfn;
-	size_t		 offset;
+	phys_addr_t	 paddr;
 	enum map_err_types  map_err_type;
 #ifdef CONFIG_STACKTRACE
 	unsigned int	stack_len;

@@ -389,14 +387,6 @@ static void hash_bucket_del(struct dma_debug_entry *entry)
 	list_del(&entry->list);
 }
 
-static unsigned long long phys_addr(struct dma_debug_entry *entry)
-{
-	if (entry->type == dma_debug_resource)
-		return __pfn_to_phys(entry->pfn) + entry->offset;
-
-	return page_to_phys(pfn_to_page(entry->pfn)) + entry->offset;
-}
-
 /*
  * For each mapping (initial cacheline in the case of
  * dma_alloc_coherent/dma_map_page, initial cacheline in each page of a

@@ -428,8 +418,8 @@ static DEFINE_SPINLOCK(radix_lock);
 
 static phys_addr_t to_cacheline_number(struct dma_debug_entry *entry)
 {
-	return (entry->pfn << CACHELINE_PER_PAGE_SHIFT) +
-		(entry->offset >> L1_CACHE_SHIFT);
+	return ((entry->paddr >> PAGE_SHIFT) << CACHELINE_PER_PAGE_SHIFT) +
+		(offset_in_page(entry->paddr) >> L1_CACHE_SHIFT);
 }
 
 static int active_cacheline_read_overlap(phys_addr_t cln)

@@ -538,11 +528,11 @@ void debug_dma_dump_mappings(struct device *dev)
 			if (!dev || dev == entry->dev) {
 				cln = to_cacheline_number(entry);
 				dev_info(entry->dev,
-					 "%s idx %d P=%llx N=%lx D=%llx L=%llx cln=%pa %s %s\n",
+					 "%s idx %d P=%pa D=%llx L=%llx cln=%pa %s %s\n",
 					 type2name[entry->type], idx,
-					 phys_addr(entry), entry->pfn,
-					 entry->dev_addr, entry->size,
-					 &cln, dir2name[entry->direction],
+					 &entry->paddr, entry->dev_addr,
+					 entry->size, &cln,
+					 dir2name[entry->direction],
 					 maperr2str[entry->map_err_type]);
 			}
 		}

@@ -569,13 +559,13 @@ static int dump_show(struct seq_file *seq, void *v)
 		list_for_each_entry(entry, &bucket->list, list) {
 			cln = to_cacheline_number(entry);
 			seq_printf(seq,
-				   "%s %s %s idx %d P=%llx N=%lx D=%llx L=%llx cln=%pa %s %s\n",
+				   "%s %s %s idx %d P=%pa D=%llx L=%llx cln=%pa %s %s\n",
 				   dev_driver_string(entry->dev),
 				   dev_name(entry->dev),
 				   type2name[entry->type], idx,
-				   phys_addr(entry), entry->pfn,
-				   entry->dev_addr, entry->size,
-				   &cln, dir2name[entry->direction],
+				   &entry->paddr, entry->dev_addr,
+				   entry->size, &cln,
+				   dir2name[entry->direction],
 				   maperr2str[entry->map_err_type]);
 		}
 		spin_unlock_irqrestore(&bucket->lock, flags);

@@ -1003,16 +993,16 @@ static void check_unmap(struct dma_debug_entry *ref)
 			   "[mapped as %s] [unmapped as %s]\n",
 			   ref->dev_addr, ref->size,
 			   type2name[entry->type], type2name[ref->type]);
-	} else if ((entry->type == dma_debug_coherent) &&
-		   (phys_addr(ref) != phys_addr(entry))) {
+	} else if (entry->type == dma_debug_coherent &&
+		   ref->paddr != entry->paddr) {
 		err_printk(ref->dev, entry, "device driver frees "
 			   "DMA memory with different CPU address "
 			   "[device address=0x%016llx] [size=%llu bytes] "
-			   "[cpu alloc address=0x%016llx] "
-			   "[cpu free address=0x%016llx]",
+			   "[cpu alloc address=0x%pa] "
+			   "[cpu free address=0x%pa]",
 			   ref->dev_addr, ref->size,
-			   phys_addr(entry),
-			   phys_addr(ref));
+			   &entry->paddr,
+			   &ref->paddr);
 	}
 
 	if (ref->sg_call_ents && ref->type == dma_debug_sg &&

@@ -1231,8 +1221,7 @@ void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
 
 	entry->dev       = dev;
 	entry->type      = dma_debug_single;
-	entry->pfn	 = page_to_pfn(page);
-	entry->offset	 = offset;
+	entry->paddr	 = page_to_phys(page);
 	entry->dev_addr  = dma_addr;
 	entry->size      = size;
 	entry->direction = direction;

@@ -1327,8 +1316,7 @@ void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
 
 		entry->type           = dma_debug_sg;
 		entry->dev            = dev;
-		entry->pfn	      = page_to_pfn(sg_page(s));
-		entry->offset	      = s->offset;
+		entry->paddr	      = sg_phys(s);
 		entry->size           = sg_dma_len(s);
 		entry->dev_addr       = sg_dma_address(s);
 		entry->direction      = direction;

@@ -1374,8 +1362,7 @@ void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
 		struct dma_debug_entry ref = {
 			.type           = dma_debug_sg,
 			.dev            = dev,
-			.pfn		= page_to_pfn(sg_page(s)),
-			.offset		= s->offset,
+			.paddr		= sg_phys(s),
 			.dev_addr       = sg_dma_address(s),
 			.size           = sg_dma_len(s),
 			.direction      = dir,

@@ -1414,16 +1401,12 @@ void debug_dma_alloc_coherent(struct device *dev, size_t size,
 
 	entry->type      = dma_debug_coherent;
 	entry->dev       = dev;
-	entry->offset	 = offset_in_page(virt);
+	entry->paddr	 = page_to_phys((is_vmalloc_addr(virt) ?
+				vmalloc_to_page(virt) : virt_to_page(virt)));
 	entry->size      = size;
 	entry->dev_addr  = dma_addr;
 	entry->direction = DMA_BIDIRECTIONAL;
 
-	if (is_vmalloc_addr(virt))
-		entry->pfn = vmalloc_to_pfn(virt);
-	else
-		entry->pfn = page_to_pfn(virt_to_page(virt));
-
 	add_dma_entry(entry, attrs);
 }
 

@@ -1433,7 +1416,6 @@ void debug_dma_free_coherent(struct device *dev, size_t size,
 	struct dma_debug_entry ref = {
 		.type           = dma_debug_coherent,
 		.dev            = dev,
-		.offset		= offset_in_page(virt),
 		.dev_addr       = dma_addr,
 		.size           = size,
 		.direction      = DMA_BIDIRECTIONAL,

@@ -1443,10 +1425,8 @@ void debug_dma_free_coherent(struct device *dev, size_t size,
 	if (!is_vmalloc_addr(virt) && !virt_addr_valid(virt))
 		return;
 
-	if (is_vmalloc_addr(virt))
-		ref.pfn = vmalloc_to_pfn(virt);
-	else
-		ref.pfn = page_to_pfn(virt_to_page(virt));
+	ref.paddr = page_to_phys((is_vmalloc_addr(virt) ?
+			vmalloc_to_page(virt) : virt_to_page(virt)));
 
 	if (unlikely(dma_debug_disabled()))
 		return;

@@ -1469,8 +1449,7 @@ void debug_dma_map_resource(struct device *dev, phys_addr_t addr, size_t size,
 
 	entry->type		= dma_debug_resource;
 	entry->dev		= dev;
-	entry->pfn		= PHYS_PFN(addr);
-	entry->offset		= offset_in_page(addr);
+	entry->paddr		= addr;
 	entry->size		= size;
 	entry->dev_addr		= dma_addr;
 	entry->direction	= direction;

@@ -1547,8 +1526,7 @@ void debug_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
 		struct dma_debug_entry ref = {
 			.type           = dma_debug_sg,
 			.dev            = dev,
-			.pfn		= page_to_pfn(sg_page(s)),
-			.offset		= s->offset,
+			.paddr		= sg_phys(s),
 			.dev_addr       = sg_dma_address(s),
 			.size           = sg_dma_len(s),
 			.direction      = direction,

@@ -1579,8 +1557,7 @@ void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 		struct dma_debug_entry ref = {
 			.type           = dma_debug_sg,
 			.dev            = dev,
-			.pfn		= page_to_pfn(sg_page(s)),
-			.offset		= s->offset,
+			.paddr		= sg_phys(sg),
 			.dev_addr       = sg_dma_address(s),
 			.size           = sg_dma_len(s),
 			.direction      = direction,

index b0f41265191c3..012729cc178f0 100644
@@ -116,8 +116,9 @@ DEFINE_EVENT(dma_unmap, dma_unmap_resource,
 
 TRACE_EVENT(dma_alloc,
 	TP_PROTO(struct device *dev, void *virt_addr, dma_addr_t dma_addr,
-		 size_t size, gfp_t flags, unsigned long attrs),
-	TP_ARGS(dev, virt_addr, dma_addr, size, flags, attrs),
+		 size_t size, enum dma_data_direction dir, gfp_t flags,
+		 unsigned long attrs),
+	TP_ARGS(dev, virt_addr, dma_addr, size, dir, flags, attrs),
 
 	TP_STRUCT__entry(
 		__string(device, dev_name(dev))

@@ -125,6 +126,7 @@ TRACE_EVENT(dma_alloc,
 		__field(u64, dma_addr)
 		__field(size_t, size)
 		__field(gfp_t, flags)
+		__field(enum dma_data_direction, dir)
 		__field(unsigned long, attrs)
 	),
 

@@ -137,8 +139,9 @@ TRACE_EVENT(dma_alloc,
 		__entry->attrs = attrs;
 	),
 
-	TP_printk("%s dma_addr=%llx size=%zu virt_addr=%p flags=%s attrs=%s",
+	TP_printk("%s dir=%s dma_addr=%llx size=%zu virt_addr=%p flags=%s attrs=%s",
 		__get_str(device),
+		decode_dma_data_direction(__entry->dir),
 		__entry->dma_addr,
 		__entry->size,
 		__entry->virt_addr,

@@ -148,14 +151,15 @@ TRACE_EVENT(dma_alloc,
 
 TRACE_EVENT(dma_free,
 	TP_PROTO(struct device *dev, void *virt_addr, dma_addr_t dma_addr,
-		 size_t size, unsigned long attrs),
-	TP_ARGS(dev, virt_addr, dma_addr, size, attrs),
+		 size_t size, enum dma_data_direction dir, unsigned long attrs),
+	TP_ARGS(dev, virt_addr, dma_addr, size, dir, attrs),
 
 	TP_STRUCT__entry(
 		__string(device, dev_name(dev))
 		__field(void *, virt_addr)
 		__field(u64, dma_addr)
 		__field(size_t, size)
+		__field(enum dma_data_direction, dir)
 		__field(unsigned long, attrs)
 	),
 

@@ -164,11 +168,13 @@ TRACE_EVENT(dma_free,
 		__entry->virt_addr = virt_addr;
 		__entry->dma_addr = dma_addr;
 		__entry->size = size;
+		__entry->dir = dir;
 		__entry->attrs = attrs;
 	),
 
-	TP_printk("%s dma_addr=%llx size=%zu virt_addr=%p attrs=%s",
+	TP_printk("%s dir=%s dma_addr=%llx size=%zu virt_addr=%p attrs=%s",
 		__get_str(device),
+		decode_dma_data_direction(__entry->dir),
 		__entry->dma_addr,
 		__entry->size,
 		__entry->virt_addr,

index 74d453ec750a1..9720f3c157d9f 100644
@@ -619,7 +619,8 @@ void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	else
 		return NULL;
 
-	trace_dma_alloc(dev, cpu_addr, *dma_handle, size, flag, attrs);
+	trace_dma_alloc(dev, cpu_addr, *dma_handle, size, DMA_BIDIRECTIONAL,
+			flag, attrs);
 	debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr, attrs);
 	return cpu_addr;
 }

@@ -644,7 +645,8 @@ void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 	if (!cpu_addr)
 		return;
 
-	trace_dma_free(dev, cpu_addr, dma_handle, size, attrs);
+	trace_dma_free(dev, cpu_addr, dma_handle, size, DMA_BIDIRECTIONAL,
+		       attrs);
 	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
 	if (dma_alloc_direct(dev, ops))
 		dma_direct_free(dev, size, cpu_addr, dma_handle, attrs);

index 012729cc178f0..45cc0ca8287fe 100644
@@ -114,7 +114,7 @@ DEFINE_EVENT(dma_unmap, dma_unmap_resource,
 		 enum dma_data_direction dir, unsigned long attrs),
 	TP_ARGS(dev, addr, size, dir, attrs));
 
-TRACE_EVENT(dma_alloc,
+DECLARE_EVENT_CLASS(dma_alloc_class,
 	TP_PROTO(struct device *dev, void *virt_addr, dma_addr_t dma_addr,
 		 size_t size, enum dma_data_direction dir, gfp_t flags,
 		 unsigned long attrs),

@@ -149,7 +149,58 @@ TRACE_EVENT(dma_alloc,
 		decode_dma_attrs(__entry->attrs))
 );
 
-TRACE_EVENT(dma_free,
+#define DEFINE_ALLOC_EVENT(name) \
+DEFINE_EVENT(dma_alloc_class, name, \
+	TP_PROTO(struct device *dev, void *virt_addr, dma_addr_t dma_addr, \
+		 size_t size, enum dma_data_direction dir, gfp_t flags, \
+		 unsigned long attrs), \
+	TP_ARGS(dev, virt_addr, dma_addr, size, dir, flags, attrs))
+
+DEFINE_ALLOC_EVENT(dma_alloc);
+DEFINE_ALLOC_EVENT(dma_alloc_pages);
+
+TRACE_EVENT(dma_alloc_sgt,
+	TP_PROTO(struct device *dev, struct sg_table *sgt, size_t size,
+		 enum dma_data_direction dir, gfp_t flags, unsigned long attrs),
+	TP_ARGS(dev, sgt, size, dir, flags, attrs),
+
+	TP_STRUCT__entry(
+		__string(device, dev_name(dev))
+		__dynamic_array(u64, phys_addrs, sgt->orig_nents)
+		__field(u64, dma_addr)
+		__field(size_t, size)
+		__field(enum dma_data_direction, dir)
+		__field(gfp_t, flags)
+		__field(unsigned long, attrs)
+	),
+
+	TP_fast_assign(
+		struct scatterlist *sg;
+		int i;
+
+		__assign_str(device);
+		for_each_sg(sgt->sgl, sg, sgt->orig_nents, i)
+			((u64 *)__get_dynamic_array(phys_addrs))[i] = sg_phys(sg);
+		__entry->dma_addr = sg_dma_address(sgt->sgl);
+		__entry->size = size;
+		__entry->dir = dir;
+		__entry->flags = flags;
+		__entry->attrs = attrs;
+	),
+
+	TP_printk("%s dir=%s dma_addr=%llx size=%zu phys_addrs=%s flags=%s attrs=%s",
+		__get_str(device),
+		decode_dma_data_direction(__entry->dir),
+		__entry->dma_addr,
+		__entry->size,
+		__print_array(__get_dynamic_array(phys_addrs),
+			      __get_dynamic_array_len(phys_addrs) /
+				sizeof(u64), sizeof(u64)),
+		show_gfp_flags(__entry->flags),
+		decode_dma_attrs(__entry->attrs))
+);
+
+DECLARE_EVENT_CLASS(dma_free_class,
 	TP_PROTO(struct device *dev, void *virt_addr, dma_addr_t dma_addr,
 		 size_t size, enum dma_data_direction dir, unsigned long attrs),
 	TP_ARGS(dev, virt_addr, dma_addr, size, dir, attrs),

@@ -181,6 +232,50 @@ TRACE_EVENT(dma_free,
 		decode_dma_attrs(__entry->attrs))
 );
 
+#define DEFINE_FREE_EVENT(name) \
+DEFINE_EVENT(dma_free_class, name, \
+	TP_PROTO(struct device *dev, void *virt_addr, dma_addr_t dma_addr, \
+		 size_t size, enum dma_data_direction dir, unsigned long attrs), \
+	TP_ARGS(dev, virt_addr, dma_addr, size, dir, attrs))
+
+DEFINE_FREE_EVENT(dma_free);
+DEFINE_FREE_EVENT(dma_free_pages);
+
+TRACE_EVENT(dma_free_sgt,
+	TP_PROTO(struct device *dev, struct sg_table *sgt, size_t size,
+		 enum dma_data_direction dir),
+	TP_ARGS(dev, sgt, size, dir),
+
+	TP_STRUCT__entry(
+		__string(device, dev_name(dev))
+		__dynamic_array(u64, phys_addrs, sgt->orig_nents)
+		__field(u64, dma_addr)
+		__field(size_t, size)
+		__field(enum dma_data_direction, dir)
+	),
+
+	TP_fast_assign(
+		struct scatterlist *sg;
+		int i;
+
+		__assign_str(device);
+		for_each_sg(sgt->sgl, sg, sgt->orig_nents, i)
+			((u64 *)__get_dynamic_array(phys_addrs))[i] = sg_phys(sg);
+		__entry->dma_addr = sg_dma_address(sgt->sgl);
+		__entry->size = size;
+		__entry->dir = dir;
+	),
+
+	TP_printk("%s dir=%s dma_addr=%llx size=%zu phys_addrs=%s",
+		__get_str(device),
+		decode_dma_data_direction(__entry->dir),
+		__entry->dma_addr,
+		__entry->size,
+		__print_array(__get_dynamic_array(phys_addrs),
+			      __get_dynamic_array_len(phys_addrs) /
+				sizeof(u64), sizeof(u64)))
+);
+
 TRACE_EVENT(dma_map_sg,
 	TP_PROTO(struct device *dev, struct scatterlist *sgl, int nents,
 		 int ents, enum dma_data_direction dir, unsigned long attrs),

index 9720f3c157d9f..690aeda8bd7da 100644
@@ -685,8 +685,8 @@ struct page *dma_alloc_pages(struct device *dev, size_t size,
 	struct page *page = __dma_alloc_pages(dev, size, dma_handle, dir, gfp);
 
 	if (page) {
-		trace_dma_map_page(dev, page_to_phys(page), *dma_handle, size,
-				   dir, 0);
+		trace_dma_alloc_pages(dev, page_to_virt(page), *dma_handle,
+				      size, dir, gfp, 0);
 		debug_dma_map_page(dev, page, 0, size, dir, *dma_handle, 0);
 	}
 	return page;

@@ -710,7 +710,7 @@ static void __dma_free_pages(struct device *dev, size_t size, struct page *page,
 void dma_free_pages(struct device *dev, size_t size, struct page *page,
 		dma_addr_t dma_handle, enum dma_data_direction dir)
 {
-	trace_dma_unmap_page(dev, dma_handle, size, dir, 0);
+	trace_dma_free_pages(dev, page_to_virt(page), dma_handle, size, dir, 0);
 	debug_dma_unmap_page(dev, dma_handle, size, dir);
 	__dma_free_pages(dev, size, page, dma_handle, dir);
 }

@@ -770,7 +770,7 @@ struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size,
 
 	if (sgt) {
 		sgt->nents = 1;
-		trace_dma_map_sg(dev, sgt->sgl, sgt->orig_nents, 1, dir, attrs);
+		trace_dma_alloc_sgt(dev, sgt, size, dir, gfp, attrs);
 		debug_dma_map_sg(dev, sgt->sgl, sgt->orig_nents, 1, dir, attrs);
 	}
 	return sgt;

@@ -789,7 +789,7 @@ static void free_single_sgt(struct device *dev, size_t size,
 void dma_free_noncontiguous(struct device *dev, size_t size,
 		struct sg_table *sgt, enum dma_data_direction dir)
 {
-	trace_dma_unmap_sg(dev, sgt->sgl, sgt->orig_nents, dir, 0);
+	trace_dma_free_sgt(dev, sgt, size, dir);
 	debug_dma_unmap_sg(dev, sgt->sgl, sgt->orig_nents, dir);
 
 	if (use_dma_iommu(dev))

index 45cc0ca8287fe..63b55ccc4f00c 100644
@@ -158,6 +158,7 @@ DEFINE_EVENT(dma_alloc_class, name, \
 
 DEFINE_ALLOC_EVENT(dma_alloc);
 DEFINE_ALLOC_EVENT(dma_alloc_pages);
+DEFINE_ALLOC_EVENT(dma_alloc_sgt_err);
 
 TRACE_EVENT(dma_alloc_sgt,
 	TP_PROTO(struct device *dev, struct sg_table *sgt, size_t size,

@@ -322,6 +323,41 @@ TRACE_EVENT(dma_map_sg,
 		decode_dma_attrs(__entry->attrs))
 );
 
+TRACE_EVENT(dma_map_sg_err,
+	TP_PROTO(struct device *dev, struct scatterlist *sgl, int nents,
+		 int err, enum dma_data_direction dir, unsigned long attrs),
+	TP_ARGS(dev, sgl, nents, err, dir, attrs),
+
+	TP_STRUCT__entry(
+		__string(device, dev_name(dev))
+		__dynamic_array(u64, phys_addrs, nents)
+		__field(int, err)
+		__field(enum dma_data_direction, dir)
+		__field(unsigned long, attrs)
+	),
+
+	TP_fast_assign(
+		struct scatterlist *sg;
+		int i;
+
+		__assign_str(device);
+		for_each_sg(sgl, sg, nents, i)
+			((u64 *)__get_dynamic_array(phys_addrs))[i] = sg_phys(sg);
+		__entry->err = err;
+		__entry->dir = dir;
+		__entry->attrs = attrs;
+	),
+
+	TP_printk("%s dir=%s dma_addrs=%s err=%d attrs=%s",
+		__get_str(device),
+		decode_dma_data_direction(__entry->dir),
+		__print_array(__get_dynamic_array(phys_addrs),
+			      __get_dynamic_array_len(phys_addrs) /
+				sizeof(u64), sizeof(u64)),
+		__entry->err,
+		decode_dma_attrs(__entry->attrs))
+);
+
 TRACE_EVENT(dma_unmap_sg,
 	TP_PROTO(struct device *dev, struct scatterlist *sgl, int nents,
 		 enum dma_data_direction dir, unsigned long attrs),

index 690aeda8bd7da..32dcf8492bbcd 100644
@@ -223,6 +223,7 @@ static int __dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
 		debug_dma_map_sg(dev, sg, nents, ents, dir, attrs);
 	} else if (WARN_ON_ONCE(ents != -EINVAL && ents != -ENOMEM &&
 				ents != -EIO && ents != -EREMOTEIO)) {
+		trace_dma_map_sg_err(dev, sg, nents, ents, dir, attrs);
 		return -EIO;
 	}
 

@@ -604,20 +605,26 @@ void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	if (WARN_ON_ONCE(flag & __GFP_COMP))
 		return NULL;
 
-	if (dma_alloc_from_dev_coherent(dev, size, dma_handle, &cpu_addr))
+	if (dma_alloc_from_dev_coherent(dev, size, dma_handle, &cpu_addr)) {
+		trace_dma_alloc(dev, cpu_addr, *dma_handle, size,
+				DMA_BIDIRECTIONAL, flag, attrs);
 		return cpu_addr;
+	}
 
 	/* let the implementation decide on the zone to allocate from: */
 	flag &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);
 
-	if (dma_alloc_direct(dev, ops))
+	if (dma_alloc_direct(dev, ops)) {
 		cpu_addr = dma_direct_alloc(dev, size, dma_handle, flag, attrs);
-	else if (use_dma_iommu(dev))
+	} else if (use_dma_iommu(dev)) {
 		cpu_addr = iommu_dma_alloc(dev, size, dma_handle, flag, attrs);
-	else if (ops->alloc)
+	} else if (ops->alloc) {
 		cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs);
-	else
+	} else {
+		trace_dma_alloc(dev, NULL, 0, size, DMA_BIDIRECTIONAL, flag,
+				attrs);
 		return NULL;
+	}
 
 	trace_dma_alloc(dev, cpu_addr, *dma_handle, size, DMA_BIDIRECTIONAL,
 			flag, attrs);

@@ -642,11 +649,11 @@ void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 	 */
 	WARN_ON(irqs_disabled());
 
+	trace_dma_free(dev, cpu_addr, dma_handle, size, DMA_BIDIRECTIONAL,
+		       attrs);
 	if (!cpu_addr)
 		return;
 
-	trace_dma_free(dev, cpu_addr, dma_handle, size, DMA_BIDIRECTIONAL,
-		       attrs);
 	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
 	if (dma_alloc_direct(dev, ops))
 		dma_direct_free(dev, size, cpu_addr, dma_handle, attrs);

@@ -688,6 +695,8 @@ struct page *dma_alloc_pages(struct device *dev, size_t size,
 		trace_dma_alloc_pages(dev, page_to_virt(page), *dma_handle,
 				      size, dir, gfp, 0);
 		debug_dma_map_page(dev, page, 0, size, dir, *dma_handle, 0);
+	} else {
+		trace_dma_alloc_pages(dev, NULL, 0, size, dir, gfp, 0);
 	}
 	return page;
 }

@@ -772,6 +781,8 @@ struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size,
 		sgt->nents = 1;
 		trace_dma_alloc_sgt(dev, sgt, size, dir, gfp, attrs);
 		debug_dma_map_sg(dev, sgt->sgl, sgt->orig_nents, 1, dir, attrs);
+	} else {
+		trace_dma_alloc_sgt_err(dev, NULL, 0, size, gfp, dir, attrs);
 	}
 	return sgt;
 }

index 4e3692afdf0d2..0221023e1120d 100644
@@ -39,6 +39,7 @@ enum {
 	dma_debug_sg,
 	dma_debug_coherent,
 	dma_debug_resource,
+	dma_debug_noncoherent,
 };
 
 enum map_err_types {

@@ -141,6 +142,7 @@ static const char *type2name[] = {
 	[dma_debug_sg] = "scatter-gather",
 	[dma_debug_coherent] = "coherent",
 	[dma_debug_resource] = "resource",
+	[dma_debug_noncoherent] = "noncoherent",
 };
 
 static const char *dir2name[] = {

@@ -993,7 +995,8 @@ static void check_unmap(struct dma_debug_entry *ref)
 			   "[mapped as %s] [unmapped as %s]\n",
 			   ref->dev_addr, ref->size,
 			   type2name[entry->type], type2name[ref->type]);
-	} else if (entry->type == dma_debug_coherent &&
+	} else if ((entry->type == dma_debug_coherent ||
+		    entry->type == dma_debug_noncoherent) &&
 		   ref->paddr != entry->paddr) {
 		err_printk(ref->dev, entry, "device driver frees "
 			   "DMA memory with different CPU address "

@@ -1573,6 +1576,49 @@ void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 	}
 }
 
+void debug_dma_alloc_pages(struct device *dev, struct page *page,
+			   size_t size, int direction,
+			   dma_addr_t dma_addr,
+			   unsigned long attrs)
+{
+	struct dma_debug_entry *entry;
+
+	if (unlikely(dma_debug_disabled()))
+		return;
+
+	entry = dma_entry_alloc();
+	if (!entry)
+		return;
+
+	entry->type      = dma_debug_noncoherent;
+	entry->dev       = dev;
+	entry->paddr	 = page_to_phys(page);
+	entry->size      = size;
+	entry->dev_addr  = dma_addr;
+	entry->direction = direction;
+
+	add_dma_entry(entry, attrs);
+}
+
+void debug_dma_free_pages(struct device *dev, struct page *page,
+			  size_t size, int direction,
+			  dma_addr_t dma_addr)
+{
+	struct dma_debug_entry ref = {
+		.type           = dma_debug_noncoherent,
+		.dev            = dev,
+		.paddr		= page_to_phys(page),
+		.dev_addr       = dma_addr,
+		.size           = size,
+		.direction      = direction,
+	};
+
+	if (unlikely(dma_debug_disabled()))
+		return;
+
+	check_unmap(&ref);
+}
+
 static int __init dma_debug_driver_setup(char *str)
 {
 	int i;

index f525197d3cae6..48757ca13f314 100644
@@ -54,6 +54,13 @@ extern void debug_dma_sync_sg_for_cpu(struct device *dev,
 extern void debug_dma_sync_sg_for_device(struct device *dev,
 					 struct scatterlist *sg,
 					 int nelems, int direction);
+extern void debug_dma_alloc_pages(struct device *dev, struct page *page,
+				  size_t size, int direction,
+				  dma_addr_t dma_addr,
+				  unsigned long attrs);
+extern void debug_dma_free_pages(struct device *dev, struct page *page,
+				 size_t size, int direction,
+				 dma_addr_t dma_addr);
 #else /* CONFIG_DMA_API_DEBUG */
 static inline void debug_dma_map_page(struct device *dev, struct page *page,
 				      size_t offset, size_t size,

@@ -126,5 +133,18 @@ static inline void debug_dma_sync_sg_for_device(struct device *dev,
 						int nelems, int direction)
 {
 }
+
+static inline void debug_dma_alloc_pages(struct device *dev, struct page *page,
+					 size_t size, int direction,
+					 dma_addr_t dma_addr,
+					 unsigned long attrs)
+{
+}
+
+static inline void debug_dma_free_pages(struct device *dev, struct page *page,
+					size_t size, int direction,
+					dma_addr_t dma_addr)
+{
+}
 #endif /* CONFIG_DMA_API_DEBUG */
 #endif /* _KERNEL_DMA_DEBUG_H */

index 32dcf8492bbcd..c12c62ad8a6bf 100644
@@ -694,7 +694,7 @@ struct page *dma_alloc_pages(struct device *dev, size_t size,
 	if (page) {
 		trace_dma_alloc_pages(dev, page_to_virt(page), *dma_handle,
 				      size, dir, gfp, 0);
-		debug_dma_map_page(dev, page, 0, size, dir, *dma_handle, 0);
+		debug_dma_alloc_pages(dev, page, size, dir, *dma_handle, 0);
 	} else {
 		trace_dma_alloc_pages(dev, NULL, 0, size, dir, gfp, 0);
 	}

@@ -720,7 +720,7 @@ void dma_free_pages(struct device *dev, size_t size, struct page *page,
 		dma_addr_t dma_handle, enum dma_data_direction dir)
 {
 	trace_dma_free_pages(dev, page_to_virt(page), dma_handle, size, dir, 0);
-	debug_dma_unmap_page(dev, dma_handle, size, dir);
+	debug_dma_free_pages(dev, page, size, dir, dma_handle);
 	__dma_free_pages(dev, size, page, dma_handle, dir);
 }
 EXPORT_SYMBOL_GPL(dma_free_pages);

@@ -1500,6 +1500,7 @@ static void kasan_memchr(struct kunit *t
 
 	ptr = kmalloc(size, GFP_KERNEL | __GFP_ZERO);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
+	OPTIMIZER_HIDE_VAR(ptr);
 
 	OPTIMIZER_HIDE_VAR(ptr);
 	OPTIMIZER_HIDE_VAR(size);

@@ -165,14 +165,14 @@ static int hws_matcher_disconnect(struct
 						    next->match_ste.rtc_0_id,
 						    next->match_ste.rtc_1_id);
 		if (ret) {
-			mlx5hws_err(tbl->ctx, "Failed to disconnect matcher\n");
-			goto matcher_reconnect;
+			mlx5hws_err(tbl->ctx, "Fatal error, failed to disconnect matcher\n");
+			return ret;
 		}
 	} else {
 		ret = mlx5hws_table_connect_to_miss_table(tbl, tbl->default_miss.miss_tbl);
 		if (ret) {
-			mlx5hws_err(tbl->ctx, "Failed to disconnect last matcher\n");
-			goto matcher_reconnect;
+			mlx5hws_err(tbl->ctx, "Fatal error, failed to disconnect last matcher\n");
+			return ret;
 		}
 	}
 

@@ -180,27 +180,19 @@ static int hws_matcher_disconnect(struct
 	if (prev_ft_id == tbl->ft_id) {
 		ret = mlx5hws_table_update_connected_miss_tables(tbl);
 		if (ret) {
-			mlx5hws_err(tbl->ctx, "Fatal error, failed to update connected miss table\n");
-			goto matcher_reconnect;
+			mlx5hws_err(tbl->ctx,
+				    "Fatal error, failed to update connected miss table\n");
+			return ret;
 		}
 	}
 
 	ret = mlx5hws_table_ft_set_default_next_ft(tbl, prev_ft_id);
 	if (ret) {
 		mlx5hws_err(tbl->ctx, "Fatal error, failed to restore matcher ft default miss\n");
-		goto matcher_reconnect;
+		return ret;
 	}
 
 	return 0;
-
-matcher_reconnect:
-	if (list_empty(&tbl->matchers_list) || !prev)
-		list_add(&matcher->list_node, &tbl->matchers_list);
-	else
-		/* insert after prev matcher */
-		list_add(&matcher->list_node, &prev->list_node);
-
-	return ret;
 }
 
 static void hws_matcher_set_rtc_attr_sz(struct mlx5hws_matcher *matcher,

@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_PGALLOC_H
+#define _LINUX_PGALLOC_H
+
+#include <linux/pgtable.h>
+#include <asm/pgalloc.h>
+
+/*
+ * {pgd,p4d}_populate_kernel() are defined as macros to allow
+ * compile-time optimization based on the configured page table levels.
+ * Without this, linking may fail because callers (e.g., KASAN) may rely
+ * on calls to these functions being optimized away when passing symbols
+ * that exist only for certain page table levels.
+ */
+#define pgd_populate_kernel(addr, pgd, p4d)				\
+	do {								\
+		pgd_populate(&init_mm, pgd, p4d);			\
+		if (ARCH_PAGE_TABLE_SYNC_MASK & PGTBL_PGD_MODIFIED)	\
+			arch_sync_kernel_mappings(addr, addr);		\
+	} while (0)
+
+#define p4d_populate_kernel(addr, p4d, pud)				\
+	do {								\
+		p4d_populate(&init_mm, p4d, pud);			\
+		if (ARCH_PAGE_TABLE_SYNC_MASK & PGTBL_P4D_MODIFIED)	\
+			arch_sync_kernel_mappings(addr, addr);		\
+	} while (0)
+
+#endif /* _LINUX_PGALLOC_H */

@@ -1699,8 +1699,8 @@ static inline int pmd_protnone(pmd_t pmd
 
 /*
  * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values
- * and let generic vmalloc and ioremap code know when arch_sync_kernel_mappings()
- * needs to be called.
+ * and let generic vmalloc, ioremap and page table update code know when
+ * arch_sync_kernel_mappings() needs to be called.
  */
 #ifndef ARCH_PAGE_TABLE_SYNC_MASK
 #define ARCH_PAGE_TABLE_SYNC_MASK 0

@@ -1833,10 +1833,11 @@ static inline bool arch_has_pfn_modify_c
 /*
  * Page Table Modification bits for pgtbl_mod_mask.
  *
- * These are used by the p?d_alloc_track*() set of functions an in the generic
- * vmalloc/ioremap code to track at which page-table levels entries have been
- * modified. Based on that the code can better decide when vmalloc and ioremap
- * mapping changes need to be synchronized to other page-tables in the system.
+ * These are used by the p?d_alloc_track*() and p*d_populate_kernel()
+ * functions in the generic vmalloc, ioremap and page table update code
+ * to track at which page-table levels entries have been modified.
+ * Based on that the code can better decide when page table changes need
+ * to be synchronized to other page-tables in the system.
  */
 #define		__PGTBL_PGD_MODIFIED	0
 #define		__PGTBL_P4D_MODIFIED	1

@@ -13,9 +13,9 @@
 #include <linux/mm.h>
 #include <linux/pfn.h>
 #include <linux/slab.h>
+#include <linux/pgalloc.h>
 
 #include <asm/page.h>
-#include <asm/pgalloc.h>
 
 #include "kasan.h"
 

@@ -203,7 +203,7 @@ static int __ref zero_p4d_populate(pgd_t
 			pud_t *pud;
 			pmd_t *pmd;
 
-			p4d_populate(&init_mm, p4d,
+			p4d_populate_kernel(addr, p4d,
 					lm_alias(kasan_early_shadow_pud));
 			pud = pud_offset(p4d, addr);
 			pud_populate(&init_mm, pud,

@@ -224,7 +224,7 @@ static int __ref zero_p4d_populate(pgd_t
 			} else {
 				p = early_alloc(PAGE_SIZE, NUMA_NO_NODE);
 				pud_init(p);
-				p4d_populate(&init_mm, p4d, p);
+				p4d_populate_kernel(addr, p4d, p);
 			}
 		}
 		zero_pud_populate(p4d, addr, next);

@@ -263,10 +263,10 @@ int __ref kasan_populate_early_shadow(co
 			 * puds,pmds, so pgd_populate(), pud_populate()
 			 * is noops.
 			 */
-			pgd_populate(&init_mm, pgd,
+			pgd_populate_kernel(addr, pgd,
 					lm_alias(kasan_early_shadow_p4d));
 			p4d = p4d_offset(pgd, addr);
-			p4d_populate(&init_mm, p4d,
+			p4d_populate_kernel(addr, p4d,
 					lm_alias(kasan_early_shadow_pud));
 			pud = pud_offset(p4d, addr);
 			pud_populate(&init_mm, pud,

@@ -285,7 +285,7 @@ int __ref kasan_populate_early_shadow(co
 				if (!p)
 					return -ENOMEM;
 			} else {
-				pgd_populate(&init_mm, pgd,
+				pgd_populate_kernel(addr, pgd,
 					early_alloc(PAGE_SIZE, NUMA_NO_NODE));
 			}
 		}

@@ -3129,7 +3129,7 @@ out_free:
 #endif /* BUILD_EMBED_FIRST_CHUNK */
 
 #ifdef BUILD_PAGE_FIRST_CHUNK
-#include <asm/pgalloc.h>
+#include <linux/pgalloc.h>
 
 #ifndef P4D_TABLE_SIZE
 #define P4D_TABLE_SIZE PAGE_SIZE

@@ -3157,7 +3157,7 @@ void __init __weak pcpu_populate_pte(uns
 		p4d = memblock_alloc(P4D_TABLE_SIZE, P4D_TABLE_SIZE);
 		if (!p4d)
 			goto err_alloc;
-		pgd_populate(&init_mm, pgd, p4d);
+		pgd_populate_kernel(addr, pgd, p4d);
 	}
 
 	p4d = p4d_offset(pgd, addr);

@@ -3165,7 +3165,7 @@ void __init __weak pcpu_populate_pte(uns
 		pud = memblock_alloc(PUD_TABLE_SIZE, PUD_TABLE_SIZE);
 		if (!pud)
 			goto err_alloc;
-		p4d_populate(&init_mm, p4d, pud);
+		p4d_populate_kernel(addr, p4d, pud);
 	}
 
 	pud = pud_offset(p4d, addr);

@@ -27,9 +27,9 @@
 #include <linux/spinlock.h>
 #include <linux/vmalloc.h>
 #include <linux/sched.h>
+#include <linux/pgalloc.h>
 
 #include <asm/dma.h>
-#include <asm/pgalloc.h>
 
 /*
  * Allocate a block of memory to be used to back the virtual memory map

@@ -230,7 +230,7 @@ p4d_t * __meminit vmemmap_p4d_populate(p
 		if (!p)
 			return NULL;
 		pud_init(p);
-		p4d_populate(&init_mm, p4d, p);
+		p4d_populate_kernel(addr, p4d, p);
 	}
 	return p4d;
 }

@@ -242,7 +242,7 @@ pgd_t * __meminit vmemmap_pgd_populate(u
 		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
 		if (!p)
 			return NULL;
-		pgd_populate(&init_mm, pgd, p);
+		pgd_populate_kernel(addr, pgd, p);
 	}
 	return pgd;
 }

index c12c62ad8a6bf..c7cc4e33ec6e0 100644
@@ -782,7 +782,7 @@ struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size,
 		trace_dma_alloc_sgt(dev, sgt, size, dir, gfp, attrs);
 		debug_dma_map_sg(dev, sgt->sgl, sgt->orig_nents, 1, dir, attrs);
 	} else {
-		trace_dma_alloc_sgt_err(dev, NULL, 0, size, gfp, dir, attrs);
+		trace_dma_alloc_sgt_err(dev, NULL, 0, size, dir, gfp, attrs);
 	}
 	return sgt;
 }

index 0221023e1120d..39972e834e7a1 100644
@@ -1224,7 +1224,7 @@ void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
 
 	entry->dev       = dev;
 	entry->type      = dma_debug_single;
-	entry->paddr	 = page_to_phys(page);
+	entry->paddr	 = page_to_phys(page) + offset;
 	entry->dev_addr  = dma_addr;
 	entry->size      = size;
 	entry->direction = direction;

@@ -1382,6 +1382,18 @@ void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
 	}
 }
 
+static phys_addr_t virt_to_paddr(void *virt)
+{
+	struct page *page;
+
+	if (is_vmalloc_addr(virt))
+		page = vmalloc_to_page(virt);
+	else
+		page = virt_to_page(virt);
+
+	return page_to_phys(page) + offset_in_page(virt);
+}
+
 void debug_dma_alloc_coherent(struct device *dev, size_t size,
 			      dma_addr_t dma_addr, void *virt,
 			      unsigned long attrs)

@@ -1404,8 +1416,7 @@ void debug_dma_alloc_coherent(struct device *dev, size_t size,
 
 	entry->type      = dma_debug_coherent;
 	entry->dev       = dev;
-	entry->paddr	 = page_to_phys((is_vmalloc_addr(virt) ?
-				vmalloc_to_page(virt) : virt_to_page(virt)));
+	entry->paddr	 = virt_to_paddr(virt);
 	entry->size      = size;
 	entry->dev_addr  = dma_addr;
 	entry->direction = DMA_BIDIRECTIONAL;

@@ -1428,8 +1439,7 @@ void debug_dma_free_coherent(struct device *dev, size_t size,
 	if (!is_vmalloc_addr(virt) && !virt_addr_valid(virt))
 		return;
 
-	ref.paddr = page_to_phys((is_vmalloc_addr(virt) ?
-			vmalloc_to_page(virt) : virt_to_page(virt)));
+	ref.paddr = virt_to_paddr(virt);
 
 	if (unlikely(dma_debug_disabled()))
 		return;

index 2bddc9f60fecc..fdc9f1df0578b 100644
@@ -989,6 +989,9 @@ static void nvme_submit_cmds(struct nvme_queue *nvmeq, struct rq_list *rqlist)
 {
 	struct request *req;
 
+	if (rq_list_empty(rqlist))
+		return;
+
 	spin_lock(&nvmeq->sq_lock);
 	while ((req = rq_list_pop(rqlist))) {
 		struct nvme_iod *iod = blk_mq_rq_to_pdu(req);

index 959f690b12260..0e127a9109e75 100644
@@ -74,29 +74,21 @@ static int mmap_udmabuf(struct dma_buf *buf, struct vm_area_struct *vma)
 static int vmap_udmabuf(struct dma_buf *buf, struct iosys_map *map)
 {
 	struct udmabuf *ubuf = buf->priv;
-	unsigned long *pfns;
+	struct page **pages;
 	void *vaddr;
 	pgoff_t pg;
 
 	dma_resv_assert_held(buf->resv);
 
-	/**
-	 * HVO may free tail pages, so just use pfn to map each folio
-	 * into vmalloc area.
-	 */
-	pfns = kvmalloc_array(ubuf->pagecount, sizeof(*pfns), GFP_KERNEL);
-	if (!pfns)
+	pages = kvmalloc_array(ubuf->pagecount, sizeof(*pages), GFP_KERNEL);
+	if (!pages)
 		return -ENOMEM;
 
-	for (pg = 0; pg < ubuf->pagecount; pg++) {
-		unsigned long pfn = folio_pfn(ubuf->folios[pg]);
-
-		pfn += ubuf->offsets[pg] >> PAGE_SHIFT;
-		pfns[pg] = pfn;
-	}
+	for (pg = 0; pg < ubuf->pagecount; pg++)
+		pages[pg] = &ubuf->folios[pg]->page;
 
-	vaddr = vmap_pfn(pfns, ubuf->pagecount, PAGE_KERNEL);
-	kvfree(pfns);
+	vaddr = vm_map_ram(pages, ubuf->pagecount, -1);
+	kvfree(pages);
 	if (!vaddr)
 		return -EINVAL;
 

index 286f8fcb74cc9..29c7c0b8295fb 100644
@@ -1462,7 +1462,8 @@ static bool ext4_match(struct inode *parent,
 		 * sure cf_name was properly initialized before
 		 * considering the calculated hash.
 		 */
-		if (IS_ENCRYPTED(parent) && fname->cf_name.name &&
+		if (sb_no_casefold_compat_fallback(parent->i_sb) &&
+		    IS_ENCRYPTED(parent) && fname->cf_name.name &&
 		    (fname->hinfo.hash != EXT4_DIRENT_HASH(de) ||
 		     fname->hinfo.minor_hash != EXT4_DIRENT_MINOR_HASH(de)))
 			return false;

@@ -1595,10 +1596,15 @@ static struct buffer_head *__ext4_find_entry(struct inode *dir,
 		 * return.  Otherwise, fall back to doing a search the
 		 * old fashioned way.
 		 */
-		if (!IS_ERR(ret) || PTR_ERR(ret) != ERR_BAD_DX_DIR)
+		if (IS_ERR(ret) && PTR_ERR(ret) == ERR_BAD_DX_DIR)
+			dxtrace(printk(KERN_DEBUG "ext4_find_entry: dx failed, "
+				       "falling back\n"));
+		else if (!sb_no_casefold_compat_fallback(dir->i_sb) &&
+			 *res_dir == NULL && IS_CASEFOLDED(dir))
+			dxtrace(printk(KERN_DEBUG "ext4_find_entry: casefold "
+				       "failed, falling back\n"));
+		else
 			goto cleanup_and_exit;
-		dxtrace(printk(KERN_DEBUG "ext4_find_entry: dx failed, "
-			       "falling back\n"));
 		ret = NULL;
 	}
 	nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb);

index a6de8d93838d1..37a01c9d96583 100644
@@ -1197,11 +1197,19 @@ extern int send_sigurg(struct file *file);
 #define SB_NOUSER       BIT(31)
 
 /* These flags relate to encoding and casefolding */
-#define SB_ENC_STRICT_MODE_FL	(1 << 0)
+#define SB_ENC_STRICT_MODE_FL		(1 << 0)
+#define SB_ENC_NO_COMPAT_FALLBACK_FL	(1 << 1)
 
 #define sb_has_strict_encoding(sb) \
 	(sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL)
 
+#if IS_ENABLED(CONFIG_UNICODE)
+#define sb_no_casefold_compat_fallback(sb) \
+	(sb->s_encoding_flags & SB_ENC_NO_COMPAT_FALLBACK_FL)
+#else
+#define sb_no_casefold_compat_fallback(sb) (1)
+#endif
+
 /*
  *	Umount options
  */

index b48373b166779..355a21eb48443 100644
@@ -1469,6 +1469,19 @@ static void __reset_guc_busyness_stats(struct intel_guc *guc)
 	spin_unlock_irqrestore(&guc->timestamp.lock, flags);
 }
 
+static void __update_guc_busyness_running_state(struct intel_guc *guc)
+{
+	struct intel_gt *gt = guc_to_gt(guc);
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	unsigned long flags;
+
+	spin_lock_irqsave(&guc->timestamp.lock, flags);
+	for_each_engine(engine, gt, id)
+		engine->stats.guc.running = false;
+	spin_unlock_irqrestore(&guc->timestamp.lock, flags);
+}
+
 static void __update_guc_busyness_stats(struct intel_guc *guc)
 {
 	struct intel_gt *gt = guc_to_gt(guc);

@@ -1619,6 +1632,9 @@ void intel_guc_busyness_park(struct intel_gt *gt)
 	if (!guc_submission_initialized(guc))
 		return;
 
+	/* Assume no engines are running and set running state to false */
+	__update_guc_busyness_running_state(guc);
+
 	/*
 	 * There is a race with suspend flow where the worker runs after suspend
 	 * and causes an unclaimed register access warning. Cancel the worker

index 9763752cf5cde..b585c321d3454 100644
@@ -11483,6 +11483,11 @@ static bool amdgpu_dm_crtc_mem_type_changed(struct drm_device *dev,
 		new_plane_state = drm_atomic_get_plane_state(state, plane);
 		old_plane_state = drm_atomic_get_plane_state(state, plane);
 
+		if (IS_ERR(new_plane_state) || IS_ERR(old_plane_state)) {
+			DRM_ERROR("Failed to get plane state for plane %s\n", plane->name);
+			return false;
+		}
+
 		if (old_plane_state->fb && new_plane_state->fb &&
 		    get_mem_type(old_plane_state->fb) != get_mem_type(new_plane_state->fb))
 			return true;

index 01480a04f85ef..9a3be1dd352b6 100644
@@ -483,11 +483,10 @@ void dpp1_set_cursor_position(
 	if (src_y_offset + cursor_height <= 0)
 		cur_en = 0;  /* not visible beyond top edge*/
 
-	if (dpp_base->pos.cur0_ctl.bits.cur0_enable != cur_en) {
-		REG_UPDATE(CURSOR0_CONTROL, CUR0_ENABLE, cur_en);
+	REG_UPDATE(CURSOR0_CONTROL,
+			CUR0_ENABLE, cur_en);
 
-		dpp_base->pos.cur0_ctl.bits.cur0_enable = cur_en;
-	}
+	dpp_base->pos.cur0_ctl.bits.cur0_enable = cur_en;
 }
 
 void dpp1_cnv_set_optional_cursor_attributes(

index 712aff7e17f7a..92b34fe47f740 100644
@@ -155,11 +155,9 @@ void dpp401_set_cursor_position(
 	struct dcn401_dpp *dpp = TO_DCN401_DPP(dpp_base);
 	uint32_t cur_en = pos->enable ? 1 : 0;
 
-	if (dpp_base->pos.cur0_ctl.bits.cur0_enable != cur_en) {
-		REG_UPDATE(CURSOR0_CONTROL, CUR0_ENABLE, cur_en);
+	REG_UPDATE(CURSOR0_CONTROL, CUR0_ENABLE, cur_en);
 
-		dpp_base->pos.cur0_ctl.bits.cur0_enable = cur_en;
-	}
+	dpp_base->pos.cur0_ctl.bits.cur0_enable = cur_en;
 }
 
 void dpp401_set_optional_cursor_attributes(

index c74ee2d50a699..b405fa22f87a9 100644
@@ -1044,13 +1044,11 @@ void hubp2_cursor_set_position(
 	if (src_y_offset + cursor_height <= 0)
 		cur_en = 0;  /* not visible beyond top edge*/
 
-	if (hubp->pos.cur_ctl.bits.cur_enable != cur_en) {
-		if (cur_en && REG_READ(CURSOR_SURFACE_ADDRESS) == 0)
-			hubp->funcs->set_cursor_attributes(hubp, &hubp->curs_attr);
+	if (cur_en && REG_READ(CURSOR_SURFACE_ADDRESS) == 0)
+		hubp->funcs->set_cursor_attributes(hubp, &hubp->curs_attr);
 
-		REG_UPDATE(CURSOR_CONTROL,
+	REG_UPDATE(CURSOR_CONTROL,
 			CURSOR_ENABLE, cur_en);
-	}
 
 	REG_SET_2(CURSOR_POSITION, 0,
 			CURSOR_X_POSITION, pos->x,

index 7013c124efcff..2d52100510f05 100644
@@ -718,13 +718,11 @@ void hubp401_cursor_set_position(
 			dc_fixpt_from_int(dst_x_offset),
 			param->h_scale_ratio));
 
-	if (hubp->pos.cur_ctl.bits.cur_enable != cur_en) {
-		if (cur_en && REG_READ(CURSOR_SURFACE_ADDRESS) == 0)
-			hubp->funcs->set_cursor_attributes(hubp, &hubp->curs_attr);
+	if (cur_en && REG_READ(CURSOR_SURFACE_ADDRESS) == 0)
+		hubp->funcs->set_cursor_attributes(hubp, &hubp->curs_attr);
 
-		REG_UPDATE(CURSOR_CONTROL,
-			CURSOR_ENABLE, cur_en);
-	}
+	REG_UPDATE(CURSOR_CONTROL,
+		CURSOR_ENABLE, cur_en);
 
 	REG_SET_2(CURSOR_POSITION, 0,
 		CURSOR_X_POSITION, x_pos,

index a28a59926adad..eb0e404c17841 100644
@@ -10857,6 +10857,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
 	SND_PCI_QUIRK(0x1043, 0x1054, "ASUS G614FH/FM/FP", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+	SND_PCI_QUIRK(0x1043, 0x106f, "ASUS VivoBook X515UA", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1074, "ASUS G614PH/PM/PP", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x10a1, "ASUS UX391UA", ALC294_FIXUP_ASUS_SPK),
 	SND_PCI_QUIRK(0x1043, 0x10a4, "ASUS TP3407SA", ALC287_FIXUP_TAS2781_I2C),

index 48ab93e715c82..6e4f9c6108f60 100644
@@ -239,6 +239,13 @@ static const struct amdgpu_video_codec_info cz_video_codecs_decode_array[] =
 		.max_pixels_per_frame = 4096 * 4096,
 		.max_level = 186,
 	},
+	{
+		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
+		.max_width = 4096,
+		.max_height = 4096,
+		.max_pixels_per_frame = 4096 * 4096,
+		.max_level = 0,
+	},
 };
 
 static const struct amdgpu_video_codecs cz_video_codecs_decode =

index b685e763ef11b..69496aab9583e 100644
@@ -772,8 +772,11 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg,
 			continue;
 
 		if (check_device &&
-		    nfs4_test_deviceid_unavailable(&mirror->mirror_ds->id_node))
+		    nfs4_test_deviceid_unavailable(&mirror->mirror_ds->id_node)) {
+			// reinitialize the error state in case if this is the last iteration
+			ds = ERR_PTR(-EINVAL);
 			continue;
+		}
 
 		*best_idx = idx;
 		break;

@@ -803,7 +806,7 @@ ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg,
 	struct nfs4_pnfs_ds *ds;
 
 	ds = ff_layout_choose_valid_ds_for_read(lseg, start_idx, best_idx);
-	if (ds)
+	if (!IS_ERR(ds))
 		return ds;
 	return ff_layout_choose_any_ds_for_read(lseg, start_idx, best_idx);
 }

@@ -817,7 +820,7 @@ ff_layout_get_ds_for_read(struct nfs_pageio_descriptor *pgio,
 
 	ds = ff_layout_choose_best_ds_for_read(lseg, pgio->pg_mirror_idx,
 					       best_idx);
-	if (ds || !pgio->pg_mirror_idx)
+	if (!IS_ERR(ds) || !pgio->pg_mirror_idx)
 		return ds;
 	return ff_layout_choose_best_ds_for_read(lseg, 0, best_idx);
 }

@@ -867,7 +870,7 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 	req->wb_nio = 0;
 
 	ds = ff_layout_get_ds_for_read(pgio, &ds_idx);
-	if (!ds) {
+	if (IS_ERR(ds)) {
 		if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
 			goto out_mds;
 		pnfs_generic_pg_cleanup(pgio);

@@ -1071,11 +1074,13 @@ static void ff_layout_resend_pnfs_read(struct nfs_pgio_header *hdr)
 {
 	u32 idx = hdr->pgio_mirror_idx + 1;
 	u32 new_idx = 0;
+	struct nfs4_pnfs_ds *ds;
 
-	if (ff_layout_choose_any_ds_for_read(hdr->lseg, idx, &new_idx))
-		ff_layout_send_layouterror(hdr->lseg);
-	else
+	ds = ff_layout_choose_any_ds_for_read(hdr->lseg, idx, &new_idx);
+	if (IS_ERR(ds))
 		pnfs_error_mark_layout_for_return(hdr->inode, hdr->lseg);
+	else
+		ff_layout_send_layouterror(hdr->lseg);
 	pnfs_read_resend_pnfs(hdr, new_idx);
 }
 

index 92cec227215ae..b78f1aae9e806 100644
@@ -407,9 +407,9 @@ xs_sock_recv_cmsg(struct socket *sock, unsigned int *msg_flags, int flags)
 	iov_iter_kvec(&msg.msg_iter, ITER_DEST, &alert_kvec, 1,
 		      alert_kvec.iov_len);
 	ret = sock_recvmsg(sock, &msg, flags);
-	if (ret > 0 &&
-	    tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT) {
-		iov_iter_revert(&msg.msg_iter, ret);
+	if (ret > 0) {
+		if (tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT)
+			iov_iter_revert(&msg.msg_iter, ret);
 		ret = xs_sock_process_cmsg(sock, &msg, msg_flags, &u.cmsg,
 					   -EAGAIN);
 	}

index e6b7cbc06c9c8..3ac8ecad2e53a 100644
@@ -4064,7 +4064,6 @@ int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle)
 	};
 	int err;
 
-	nfs_server_set_init_caps(server);
 	do {
 		err = nfs4_handle_exception(server,
 				_nfs4_server_capabilities(server, fhandle),

index 2eed8bc672f91..988a4c4ba97bc 100644
@@ -1316,7 +1316,8 @@ int register_ftrace_graph(struct fgraph_ops *gops)
 		ftrace_graph_active--;
 		gops->saved_func = NULL;
 		fgraph_lru_release_index(i);
-		unregister_pm_notifier(&ftrace_suspend_notifier);
+		if (!ftrace_graph_active)
+			unregister_pm_notifier(&ftrace_suspend_notifier);
 	}
 	return ret;
 }

index 3ac8ecad2e53a..7a1a6c68d7324 100644
@@ -3989,8 +3989,9 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
 				     res.attr_bitmask[2];
 		}
 		memcpy(server->attr_bitmask, res.attr_bitmask, sizeof(server->attr_bitmask));
-		server->caps &= ~(NFS_CAP_ACLS | NFS_CAP_HARDLINKS |
-				  NFS_CAP_SYMLINKS| NFS_CAP_SECURITY_LABEL);
+		server->caps &=
+			~(NFS_CAP_ACLS | NFS_CAP_HARDLINKS | NFS_CAP_SYMLINKS |
+			  NFS_CAP_SECURITY_LABEL | NFS_CAP_FS_LOCATIONS);
 		server->fattr_valid = NFS_ATTR_FATTR_V4;
 		if (res.attr_bitmask[0] & FATTR4_WORD0_ACL &&
 				res.acl_bitmask & ACL4_SUPPORT_ALLOW_ACL)

index 7a1a6c68d7324..ea92483d5e71e 100644
@@ -3991,7 +3991,8 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
 		memcpy(server->attr_bitmask, res.attr_bitmask, sizeof(server->attr_bitmask));
 		server->caps &=
 			~(NFS_CAP_ACLS | NFS_CAP_HARDLINKS | NFS_CAP_SYMLINKS |
-			  NFS_CAP_SECURITY_LABEL | NFS_CAP_FS_LOCATIONS);
+			  NFS_CAP_SECURITY_LABEL | NFS_CAP_FS_LOCATIONS |
+			  NFS_CAP_OPEN_XOR | NFS_CAP_DELEGTIME);
 		server->fattr_valid = NFS_ATTR_FATTR_V4;
 		if (res.attr_bitmask[0] & FATTR4_WORD0_ACL &&
 				res.acl_bitmask & ACL4_SUPPORT_ALLOW_ACL)

index 17edc124d03f2..035474f3fb8f3 100644
@@ -881,6 +881,8 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 
 	if (fsinfo->xattr_support)
 		server->caps |= NFS_CAP_XATTR;
+	else
+		server->caps &= ~NFS_CAP_XATTR;
 #endif
 }
 

index ba3358eef34ba..87a43c0f90764 100644
@@ -6949,7 +6949,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	entry = ring_buffer_event_data(event);
 	entry->ip = _THIS_IP_;
 
-	len = __copy_from_user_inatomic(&entry->buf, ubuf, cnt);
+	len = copy_from_user_nofault(&entry->buf, ubuf, cnt);
 	if (len) {
 		memcpy(&entry->buf, FAULTED_STR, FAULTED_SIZE);
 		cnt = FAULTED_SIZE;

@@ -7020,7 +7020,7 @@ tracing_mark_raw_write(struct file *filp, const char __user *ubuf,
 
 	entry = ring_buffer_event_data(event);
 
-	len = __copy_from_user_inatomic(&entry->id, ubuf, cnt);
+	len = copy_from_user_nofault(&entry->id, ubuf, cnt);
 	if (len) {
 		entry->id = -1;
 		memcpy(&entry->buf, FAULTED_STR, FAULTED_SIZE);

index 21b2b38fae9f3..ab305dfc71269 100644
@@ -274,7 +274,7 @@ nfs_local_iocb_free(struct nfs_local_kiocb *iocb)
 
 static struct nfs_local_kiocb *
 nfs_local_iocb_alloc(struct nfs_pgio_header *hdr,
-		     struct nfsd_file *localio, gfp_t flags)
+		     struct file *file, gfp_t flags)
 {
 	struct nfs_local_kiocb *iocb;
 

@@ -287,9 +287,8 @@ nfs_local_iocb_alloc(struct nfs_pgio_header *hdr,
 		kfree(iocb);
 		return NULL;
 	}
-	init_sync_kiocb(&iocb->kiocb, nfs_to->nfsd_file_file(localio));
+	init_sync_kiocb(&iocb->kiocb, file);
 	iocb->kiocb.ki_pos = hdr->args.offset;
-	iocb->localio = localio;
 	iocb->hdr = hdr;
 	iocb->kiocb.ki_flags &= ~IOCB_APPEND;
 	return iocb;

@@ -396,13 +395,19 @@ nfs_do_local_read(struct nfs_pgio_header *hdr,
 		  const struct rpc_call_ops *call_ops)
 {
 	struct nfs_local_kiocb *iocb;
+	struct file *file = nfs_to->nfsd_file_file(localio);
+
+	/* Don't support filesystems without read_iter */
+	if (!file->f_op->read_iter)
+		return -EAGAIN;
 
 	dprintk("%s: vfs_read count=%u pos=%llu\n",
 		__func__, hdr->args.count, hdr->args.offset);
 
-	iocb = nfs_local_iocb_alloc(hdr, localio, GFP_KERNEL);
+	iocb = nfs_local_iocb_alloc(hdr, file, GFP_KERNEL);
 	if (iocb == NULL)
 		return -ENOMEM;
+	iocb->localio = localio;
 
 	nfs_local_pgio_init(hdr, call_ops);
 	hdr->res.eof = false;

@@ -570,14 +575,20 @@ nfs_do_local_write(struct nfs_pgio_header *hdr,
 		   const struct rpc_call_ops *call_ops)
 {
 	struct nfs_local_kiocb *iocb;
+	struct file *file = nfs_to->nfsd_file_file(localio);
+
+	/* Don't support filesystems without write_iter */
+	if (!file->f_op->write_iter)
+		return -EAGAIN;
 
 	dprintk("%s: vfs_write count=%u pos=%llu %s\n",
 		__func__, hdr->args.count, hdr->args.offset,
 		(hdr->args.stable == NFS_UNSTABLE) ?  "unstable" : "stable");
 
-	iocb = nfs_local_iocb_alloc(hdr, localio, GFP_NOIO);
+	iocb = nfs_local_iocb_alloc(hdr, file, GFP_NOIO);
 	if (iocb == NULL)
 		return -ENOMEM;
+	iocb->localio = localio;
 
 	switch (hdr->args.stable) {
 	default:

@@ -603,16 +614,9 @@ int nfs_local_doio(struct nfs_client *clp, struct nfsd_file *localio,
 		   const struct rpc_call_ops *call_ops)
 {
 	int status = 0;
-	struct file *filp = nfs_to->nfsd_file_file(localio);
 
 	if (!hdr->args.count)
 		return 0;
-	/* Don't support filesystems without read_iter/write_iter */
-	if (!filp->f_op->read_iter || !filp->f_op->write_iter) {
-		nfs_local_disable(clp);
-		status = -EAGAIN;
-		goto out;
-	}
 
 	switch (hdr->rw_mode) {
 	case FMODE_READ:

@@ -626,8 +630,10 @@ int nfs_local_doio(struct nfs_client *clp, struct nfsd_file *localio,
 			hdr->rw_mode);
 		status = -EINVAL;
 	}
-out:
+
 	if (status != 0) {
+		if (status == -EAGAIN)
+			nfs_local_disable(clp);
 		nfs_to_nfsd_file_put_local(localio);
 		hdr->task.tk_status = status;
 		nfs_local_hdr_release(hdr, call_ops);

index c1f1b826888c9..f159cfc125adc 100644
@@ -320,6 +320,7 @@ static void nfs_read_sync_pgio_error(struct list_head *head, int error)
 static void nfs_direct_pgio_init(struct nfs_pgio_header *hdr)
 {
 	get_dreq(hdr->dreq);
+	set_bit(NFS_IOHDR_ODIRECT, &hdr->flags);
 }
 
 static const struct nfs_pgio_completion_ops nfs_direct_read_completion_ops = {

160 lines not on this page · raw message

index 12d8e47bc5a38..b48d94f099657 100644
@@ -1637,6 +1637,7 @@ enum {
 	NFS_IOHDR_RESEND_PNFS,
 	NFS_IOHDR_RESEND_MDS,
 	NFS_IOHDR_UNSTABLE_WRITES,
+	NFS_IOHDR_ODIRECT,
 };
 
 struct nfs_io_completion;

index 8fb145124e93b..82a053304ad59 100644
@@ -425,12 +425,13 @@ static void nfs_local_call_read(struct work_struct *work)
 	nfs_local_iter_init(&iter, iocb, READ);
 
 	status = filp->f_op->read_iter(&iocb->kiocb, &iter);
+
+	revert_creds(save_cred);
+
 	if (status != -EIOCBQUEUED) {
 		nfs_local_read_done(iocb, status);
 		nfs_local_pgio_release(iocb);
 	}
-
-	revert_creds(save_cred);
 }
 
 static int

@@ -626,14 +627,15 @@ static void nfs_local_call_write(struct work_struct *work)
 	file_start_write(filp);
 	status = filp->f_op->write_iter(&iocb->kiocb, &iter);
 	file_end_write(filp);
+
+	revert_creds(save_cred);
+	current->flags = old_flags;
+
 	if (status != -EIOCBQUEUED) {
 		nfs_local_write_done(iocb, status);
 		nfs_local_vfs_getattr(iocb);
 		nfs_local_pgio_release(iocb);
 	}
-
-	revert_creds(save_cred);
-	current->flags = old_flags;
 }
 
 static int

index 81220390851a3..328c6e60f024b 100644
@@ -75,8 +75,8 @@ asm (
 	CALL_DEPTH_ACCOUNT
 "	call my_direct_func1\n"
 "	leave\n"
-"	.size		my_tramp1, .-my_tramp1\n"
 	ASM_RET
+"	.size		my_tramp1, .-my_tramp1\n"
 
 "	.type		my_tramp2, @function\n"
 "	.globl		my_tramp2\n"

index f159cfc125adc..f32f8d7c9122b 100644
@@ -472,8 +472,16 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
 	if (user_backed_iter(iter))
 		dreq->flags = NFS_ODIRECT_SHOULD_DIRTY;
 
-	if (!swap)
-		nfs_start_io_direct(inode);
+	if (!swap) {
+		result = nfs_start_io_direct(inode);
+		if (result) {
+			/* release the reference that would usually be
+			 * consumed by nfs_direct_read_schedule_iovec()
+			 */
+			nfs_direct_req_release(dreq);
+			goto out_release;
+		}
+	}
 
 	NFS_I(inode)->read_io += count;
 	requested = nfs_direct_read_schedule_iovec(dreq, iter, iocb->ki_pos);

@@ -1031,7 +1039,14 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter,
 		requested = nfs_direct_write_schedule_iovec(dreq, iter, pos,
 							    FLUSH_STABLE);
 	} else {
-		nfs_start_io_direct(inode);
+		result = nfs_start_io_direct(inode);
+		if (result) {
+			/* release the reference that would usually be
+			 * consumed by nfs_direct_write_schedule_iovec()
+			 */
+			nfs_direct_req_release(dreq);
+			goto out_release;
+		}
 
 		requested = nfs_direct_write_schedule_iovec(dreq, iter, pos,
 							    FLUSH_COND_STABLE);

index 153d25d4b810c..033feeab8c346 100644
@@ -167,7 +167,10 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to)
 		iocb->ki_filp,
 		iov_iter_count(to), (unsigned long) iocb->ki_pos);
 
-	nfs_start_io_read(inode);
+	result = nfs_start_io_read(inode);
+	if (result)
+		return result;
+
 	result = nfs_revalidate_mapping(inode, iocb->ki_filp->f_mapping);
 	if (!result) {
 		result = generic_file_read_iter(iocb, to);

@@ -188,7 +191,10 @@ nfs_file_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe
 
 	dprintk("NFS: splice_read(%pD2, %zu@%llu)\n", in, len, *ppos);
 
-	nfs_start_io_read(inode);
+	result = nfs_start_io_read(inode);
+	if (result)
+		return result;
+
 	result = nfs_revalidate_mapping(inode, in->f_mapping);
 	if (!result) {
 		result = filemap_splice_read(in, ppos, pipe, len, flags);

@@ -669,7 +675,9 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 	nfs_clear_invalid_mapping(file->f_mapping);
 
 	since = filemap_sample_wb_err(file->f_mapping);
-	nfs_start_io_write(inode);
+	error = nfs_start_io_write(inode);
+	if (error)
+		return error;
 	result = generic_write_checks(iocb, from);
 	if (result > 0)
 		result = generic_perform_write(iocb, from);

index 882d804089add..4860270f1be04 100644
@@ -6,6 +6,7 @@
 #include "nfs4_fs.h"
 #include <linux/fs_context.h>
 #include <linux/security.h>
+#include <linux/compiler_attributes.h>
 #include <linux/crc32.h>
 #include <linux/sunrpc/addr.h>
 #include <linux/nfs_page.h>

@@ -516,11 +517,11 @@ extern const struct netfs_request_ops nfs_netfs_ops;
 #endif
 
 /* io.c */
-extern void nfs_start_io_read(struct inode *inode);
+extern __must_check int nfs_start_io_read(struct inode *inode);
 extern void nfs_end_io_read(struct inode *inode);
-extern void nfs_start_io_write(struct inode *inode);
+extern  __must_check int nfs_start_io_write(struct inode *inode);
 extern void nfs_end_io_write(struct inode *inode);
-extern void nfs_start_io_direct(struct inode *inode);
+extern __must_check int nfs_start_io_direct(struct inode *inode);
 extern void nfs_end_io_direct(struct inode *inode);
 
 static inline bool nfs_file_io_is_buffered(struct nfs_inode *nfsi)

82 lines not on this page · raw message

index 8827cb00f86d5..5bf5fb5ddd34c 100644
@@ -761,8 +761,10 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	trace_nfs_setattr_enter(inode);
 
 	/* Write all dirty data */
-	if (S_ISREG(inode->i_mode))
+	if (S_ISREG(inode->i_mode)) {
+		nfs_file_block_o_direct(NFS_I(inode));
 		nfs_sync_inode(inode);
+	}
 
 	fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode));
 	if (fattr == NULL) {

index 4860270f1be04..456b423402814 100644
@@ -529,6 +529,16 @@ static inline bool nfs_file_io_is_buffered(struct nfs_inode *nfsi)
 	return test_bit(NFS_INO_ODIRECT, &nfsi->flags) == 0;
 }
 
+/* Must be called with exclusively locked inode->i_rwsem */
+static inline void nfs_file_block_o_direct(struct nfs_inode *nfsi)
+{
+	if (test_bit(NFS_INO_ODIRECT, &nfsi->flags)) {
+		clear_bit(NFS_INO_ODIRECT, &nfsi->flags);
+		inode_dio_wait(&nfsi->vfs_inode);
+	}
+}
+
+
 /* namespace.c */
 #define NFS_PATH_CANONICAL 1
 extern char *nfs_path(char **p, struct dentry *dentry,

index 3388faf2acb9f..d275b0a250bf3 100644
@@ -14,15 +14,6 @@
 
 #include "internal.h"
 
-/* Call with exclusively locked inode->i_rwsem */
-static void nfs_block_o_direct(struct nfs_inode *nfsi, struct inode *inode)
-{
-	if (test_bit(NFS_INO_ODIRECT, &nfsi->flags)) {
-		clear_bit(NFS_INO_ODIRECT, &nfsi->flags);
-		inode_dio_wait(inode);
-	}
-}
-
 /**
  * nfs_start_io_read - declare the file is being used for buffered reads
  * @inode: file inode

@@ -57,7 +48,7 @@ nfs_start_io_read(struct inode *inode)
 	err = down_write_killable(&inode->i_rwsem);
 	if (err)
 		return err;
-	nfs_block_o_direct(nfsi, inode);
+	nfs_file_block_o_direct(nfsi);
 	downgrade_write(&inode->i_rwsem);
 
 	return 0;

@@ -90,7 +81,7 @@ nfs_start_io_write(struct inode *inode)
 
 	err = down_write_killable(&inode->i_rwsem);
 	if (!err)
-		nfs_block_o_direct(NFS_I(inode), inode);
+		nfs_file_block_o_direct(NFS_I(inode));
 	return err;
 }
 

index 9f0d69e652644..66fe885fc19a1 100644
@@ -112,6 +112,7 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 	exception.inode = inode;
 	exception.state = lock->open_context->state;
 
+	nfs_file_block_o_direct(NFS_I(inode));
 	err = nfs_sync_inode(inode);
 	if (err)
 		goto out;

index 1cd9652f3c280..453d08a9c4b4d 100644
@@ -283,9 +283,11 @@ static loff_t nfs42_remap_file_range(struct file *src_file, loff_t src_off,
 
 	/* flush all pending writes on both src and dst so that server
 	 * has the latest data */
+	nfs_file_block_o_direct(NFS_I(src_inode));
 	ret = nfs_sync_inode(src_inode);
 	if (ret)
 		goto out_unlock;
+	nfs_file_block_o_direct(NFS_I(dst_inode));
 	ret = nfs_sync_inode(dst_inode);
 	if (ret)
 		goto out_unlock;

index 66fe885fc19a1..582cf8a469560 100644
@@ -356,6 +356,7 @@ static ssize_t _nfs42_proc_copy(struct file *src,
 		return status;
 	}
 
+	nfs_file_block_o_direct(NFS_I(dst_inode));
 	status = nfs_sync_inode(dst_inode);
 	if (status)
 		return status;

index 033feeab8c346..a16a619fb8c33 100644
@@ -437,10 +437,11 @@ static void nfs_invalidate_folio(struct folio *folio, size_t offset,
 	dfprintk(PAGECACHE, "NFS: invalidate_folio(%lu, %zu, %zu)\n",
 		 folio->index, offset, length);
 
-	if (offset != 0 || length < folio_size(folio))
-		return;
 	/* Cancel any unstarted writes on this page */
-	nfs_wb_folio_cancel(inode, folio);
+	if (offset != 0 || length < folio_size(folio))
+		nfs_wb_folio(inode, folio);
+	else
+		nfs_wb_folio_cancel(inode, folio);
 	folio_wait_private_2(folio); /* [DEPRECATED] */
 	trace_nfs_invalidate_folio(inode, folio_pos(folio) + offset, length);
 }

index 2b6b3542405c3..fd86546fafd3f 100644
@@ -2058,6 +2058,7 @@ int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio)
 		 * release it */
 		nfs_inode_remove_request(req);
 		nfs_unlock_and_release_request(req);
+		folio_cancel_dirty(folio);
 	}
 
 	return ret;

index 69496aab9583e..6469846971966 100644
@@ -292,7 +292,7 @@ ff_lseg_match_mirrors(struct pnfs_layout_segment *l1,
 		struct pnfs_layout_segment *l2)
 {
 	const struct nfs4_ff_layout_segment *fl1 = FF_LAYOUT_LSEG(l1);
-	const struct nfs4_ff_layout_segment *fl2 = FF_LAYOUT_LSEG(l1);
+	const struct nfs4_ff_layout_segment *fl2 = FF_LAYOUT_LSEG(l2);
 	u32 i;
 
 	if (fl1->mirror_array_cnt != fl2->mirror_array_cnt)

index 87a43c0f90764..91e6bf1b101a7 100644
@@ -787,7 +787,10 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
 		/* copy the current bits to the new max */
 		ret = trace_pid_list_first(filtered_pids, &pid);
 		while (!ret) {
-			trace_pid_list_set(pid_list, pid);
+			ret = trace_pid_list_set(pid_list, pid);
+			if (ret < 0)
+				goto out;
+
 			ret = trace_pid_list_next(filtered_pids, pid + 1, &pid);
 			nr_pids++;
 		}

@@ -824,6 +827,7 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
 		trace_parser_clear(&parser);
 		ret = 0;
 	}
+ out:
 	trace_parser_put(&parser);
 
 	if (ret < 0) {

index 10725f5a6f0fd..11200880a96c1 100644
@@ -286,10 +286,10 @@ static int paicrypt_event_init(struct perf_event *event)
 	/* PAI crypto PMU registered as PERF_TYPE_RAW, check event type */
 	if (a->type != PERF_TYPE_RAW && event->pmu->type != a->type)
 		return -ENOENT;
-	/* PAI crypto event must be in valid range */
+	/* PAI crypto event must be in valid range, try others if not */
 	if (a->config < PAI_CRYPTO_BASE ||
 	    a->config > PAI_CRYPTO_BASE + paicrypt_cnt)
-		return -EINVAL;
+		return -ENOENT;
 	/* Allow only CRYPTO_ALL for sampling */
 	if (a->sample_period && a->config != PAI_CRYPTO_BASE)
 		return -EINVAL;

index a8f0bad99cf04..28398e313b58d 100644
@@ -266,7 +266,7 @@ static int paiext_event_valid(struct perf_event *event)
 		event->hw.config_base = offsetof(struct paiext_cb, acc);
 		return 0;
 	}
-	return -EINVAL;
+	return -ENOENT;
 }
 
 /* Might be called on different CPU than the one the event is intended for. */

index 6d6b057b562fd..b017db3344cb5 100644
@@ -761,8 +761,6 @@ static int __hw_perf_event_init(struct perf_event *event, unsigned int type)
 		break;
 
 	case PERF_TYPE_HARDWARE:
-		if (is_sampling_event(event))	/* No sampling support */
-			return -ENOENT;
 		ev = attr->config;
 		if (!attr->exclude_user && attr->exclude_kernel) {
 			/*

@@ -860,6 +858,8 @@ static int cpumf_pmu_event_init(struct perf_event *event)
 	unsigned int type = event->attr.type;
 	int err = -ENOENT;
 
+	if (is_sampling_event(event))	/* No sampling support */
+		return err;
 	if (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_RAW)
 		err = __hw_perf_event_init(event, type);
 	else if (event->pmu->type == type)

index 94854cd9c4cc3..83c4d9943084b 100644
@@ -278,7 +278,7 @@ static int bpf_crypto_crypt(const struct bpf_crypto_ctx *ctx,
 	siv_len = siv ? __bpf_dynptr_size(siv) : 0;
 	src_len = __bpf_dynptr_size(src);
 	dst_len = __bpf_dynptr_size(dst);
-	if (!src_len || !dst_len)
+	if (!src_len || !dst_len || src_len > dst_len)
 		return -EINVAL;
 
 	if (siv_len != ctx->siv_len)

index 6f91e3a123e55..9380e0fd5e4af 100644
@@ -2299,8 +2299,7 @@ static unsigned int __bpf_prog_ret0_warn(const void *ctx,
 					 const struct bpf_insn *insn)
 {
 	/* If this handler ever gets executed, then BPF_JIT_ALWAYS_ON
-	 * is not working properly, or interpreter is being used when
-	 * prog->jit_requested is not 0, so warn about it!
+	 * is not working properly, so warn about it!
 	 */
 	WARN_ON_ONCE(1);
 	return 0;

@@ -2401,8 +2400,9 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
 	return ret;
 }
 
-static void bpf_prog_select_func(struct bpf_prog *fp)
+static bool bpf_prog_select_interpreter(struct bpf_prog *fp)
 {
+	bool select_interpreter = false;
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
 	u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);
 	u32 idx = (round_up(stack_depth, 32) / 32) - 1;

@@ -2411,15 +2411,16 @@ static void bpf_prog_select_func(struct bpf_prog *fp)
 	 * But for non-JITed programs, we don't need bpf_func, so no bounds
 	 * check needed.
 	 */
-	if (!fp->jit_requested &&
-	    !WARN_ON_ONCE(idx >= ARRAY_SIZE(interpreters))) {
+	if (idx < ARRAY_SIZE(interpreters)) {
 		fp->bpf_func = interpreters[idx];
+		select_interpreter = true;
 	} else {
 		fp->bpf_func = __bpf_prog_ret0_warn;
 	}
 #else
 	fp->bpf_func = __bpf_prog_ret0_warn;
 #endif
+	return select_interpreter;
 }
 
 /**

@@ -2438,7 +2439,7 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 	/* In case of BPF to BPF calls, verifier did all the prep
 	 * work with regards to JITing, etc.
 	 */
-	bool jit_needed = fp->jit_requested;
+	bool jit_needed = false;
 
 	if (fp->bpf_func)
 		goto finalize;

@@ -2447,7 +2448,8 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 	    bpf_prog_has_kfunc_call(fp))
 		jit_needed = true;
 
-	bpf_prog_select_func(fp);
+	if (!bpf_prog_select_interpreter(fp))
+		jit_needed = true;
 
 	/* eBPF JITs can rewrite the program in case constant
 	 * blinding is active. However, in case of error during

index be4429463599f..a0bf39b7359aa 100644
@@ -1276,8 +1276,11 @@ static int __bpf_async_init(struct bpf_async_kern *async, struct bpf_map *map, u
 		goto out;
 	}
 
-	/* allocate hrtimer via map_kmalloc to use memcg accounting */
-	cb = bpf_map_kmalloc_node(map, size, GFP_ATOMIC, map->numa_node);
+	/* Allocate via bpf_map_kmalloc_node() for memcg accounting. Until
+	 * kmalloc_nolock() is available, avoid locking issues by using
+	 * __GFP_HIGH (GFP_ATOMIC & ~__GFP_RECLAIM).
+	 */
+	cb = bpf_map_kmalloc_node(map, size, __GFP_HIGH, map->numa_node);
 	if (!cb) {
 		ret = -ENOMEM;
 		goto out;

index 22e8a2af5dd8b..8372ca512a755 100644
@@ -408,8 +408,11 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
 		if (!psock->cork) {
 			psock->cork = kzalloc(sizeof(*psock->cork),
 					      GFP_ATOMIC | __GFP_NOWARN);
-			if (!psock->cork)
+			if (!psock->cork) {
+				sk_msg_free(sk, msg);
+				*copied = 0;
 				return -ENOMEM;
+			}
 		}
 		memcpy(psock->cork, msg, sizeof(*msg));
 		return 0;