linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: yulei.kernel@gmail.com
To: linux-mm@kvack.org, akpm@linux-foundation.org,
	linux-fsdevel@vger.kernel.org, kvm@vger.kernel.org,
	linux-kernel@vger.kernel.org, naoya.horiguchi@nec.com,
	viro@zeniv.linux.org.uk, pbonzini@redhat.com
Cc: joao.m.martins@oracle.com, rdunlap@infradead.org,
	sean.j.christopherson@intel.com, xiaoguangrong.eric@gmail.com,
	kernellwp@gmail.com, lihaiwei.kernel@gmail.com,
	Yulei Zhang <yuleixzhang@tencent.com>,
	Chen Zhuo <sagazchen@tencent.com>
Subject: [RFC V2 30/37] dmem: introduce dmem_bitmap_alloc() and dmem_bitmap_free()
Date: Mon,  7 Dec 2020 19:31:23 +0800	[thread overview]
Message-ID: <6eca6b9b58b3cf9a52c8227ee92d9b926c249f0b.1607332046.git.yuleixzhang@tencent.com> (raw)
In-Reply-To: <cover.1607332046.git.yuleixzhang@tencent.com>

From: Yulei Zhang <yuleixzhang@tencent.com>

If dmem contained in dmem region is too large and dmemfs is mounted as
4K pagesize, size of bitmap in this dmem region maybe exceed maximal
available memory of kzalloc(). It would cause kzalloc() fail.

So introduce dmem_bitmap_alloc() and use vzalloc() if bitmap is larger than
PAGE_SIZE as vzalloc() will get sparse page.

Signed-off-by: Chen Zhuo <sagazchen@tencent.com>
Signed-off-by: Yulei Zhang <yuleixzhang@tencent.com>
---
 fs/inode.c         |  6 +++++
 include/linux/fs.h |  1 +
 mm/dmem.c          | 69 ++++++++++++++++++++++++++++++++++--------------------
 3 files changed, 50 insertions(+), 26 deletions(-)

diff --git a/fs/inode.c b/fs/inode.c
index 9d78c37..9b6363d3 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -210,6 +210,12 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 }
 EXPORT_SYMBOL(inode_init_always);
 
+struct inode *alloc_inode_nonrcu(void)
+{
+	return kmem_cache_alloc(inode_cachep, GFP_KERNEL);
+}
+EXPORT_SYMBOL(alloc_inode_nonrcu);
+
 void free_inode_nonrcu(struct inode *inode)
 {
 	kmem_cache_free(inode_cachep, inode);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 8667d0c..bc7a89c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2937,6 +2937,7 @@ static inline bool is_zero_ino(ino_t ino)
 extern void __destroy_inode(struct inode *);
 extern struct inode *new_inode_pseudo(struct super_block *sb);
 extern struct inode *new_inode(struct super_block *sb);
+extern struct inode *alloc_inode_nonrcu(void);
 extern void free_inode_nonrcu(struct inode *inode);
 extern int should_remove_suid(struct dentry *);
 extern int file_remove_privs(struct file *);
diff --git a/mm/dmem.c b/mm/dmem.c
index eb6df70..50cdff9 100644
--- a/mm/dmem.c
+++ b/mm/dmem.c
@@ -17,6 +17,7 @@
 #include <linux/dmem.h>
 #include <linux/debugfs.h>
 #include <linux/notifier.h>
+#include <linux/vmalloc.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/dmem.h>
@@ -362,9 +363,38 @@ static int __init dmem_node_init(struct dmem_node *dnode)
 	return 0;
 }
 
+static unsigned long *dmem_bitmap_alloc(unsigned long pages,
+					unsigned long *static_bitmap)
+{
+	unsigned long *bitmap, size;
+
+	size = BITS_TO_LONGS(pages) * sizeof(long);
+	if (size <= sizeof(*static_bitmap))
+		bitmap = static_bitmap;
+	else if (size <= PAGE_SIZE)
+		bitmap = kzalloc(size, GFP_KERNEL);
+	else
+		bitmap = vzalloc(size);
+
+	return bitmap;
+}
+
+static void dmem_bitmap_free(unsigned long pages,
+			     unsigned long *bitmap,
+			     unsigned long *static_bitmap)
+{
+	unsigned long size;
+
+	size = BITS_TO_LONGS(pages) * sizeof(long);
+	if (size > PAGE_SIZE)
+		vfree(bitmap);
+	else if (bitmap != static_bitmap)
+		kfree(bitmap);
+}
+
 static void __init dmem_region_uinit(struct dmem_region *dregion)
 {
-	unsigned long nr_pages, size, *bitmap = dregion->error_bitmap;
+	unsigned long nr_pages, *bitmap = dregion->error_bitmap;
 
 	if (!bitmap)
 		return;
@@ -374,9 +404,7 @@ static void __init dmem_region_uinit(struct dmem_region *dregion)
 
 	WARN_ON(!nr_pages);
 
-	size = BITS_TO_LONGS(nr_pages) * sizeof(long);
-	if (size > sizeof(dregion->static_bitmap))
-		kfree(bitmap);
+	dmem_bitmap_free(nr_pages, bitmap, &dregion->static_error_bitmap);
 	dregion->error_bitmap = NULL;
 }
 
@@ -405,19 +433,15 @@ static void __init dmem_uinit(void)
 
 static int __init dmem_region_init(struct dmem_region *dregion)
 {
-	unsigned long *bitmap, size, nr_pages;
+	unsigned long *bitmap, nr_pages;
 
 	nr_pages = __phys_to_pfn(dregion->reserved_end_addr)
 		- __phys_to_pfn(dregion->reserved_start_addr);
 
-	size = BITS_TO_LONGS(nr_pages) * sizeof(long);
-	if (size <= sizeof(dregion->static_error_bitmap)) {
-		bitmap = &dregion->static_error_bitmap;
-	} else {
-		bitmap = kzalloc(size, GFP_KERNEL);
-		if (!bitmap)
-			return -ENOMEM;
-	}
+	bitmap = dmem_bitmap_alloc(nr_pages, &dregion->static_error_bitmap);
+	if (!bitmap)
+		return -ENOMEM;
+
 	dregion->error_bitmap = bitmap;
 	return 0;
 }
@@ -472,7 +496,7 @@ static int __init dmem_late_init(void)
 static int dmem_alloc_region_init(struct dmem_region *dregion,
 				  unsigned long *dpages)
 {
-	unsigned long start, end, *bitmap, size;
+	unsigned long start, end, *bitmap;
 
 	start = DMEM_PAGE_UP(dregion->reserved_start_addr);
 	end = DMEM_PAGE_DOWN(dregion->reserved_end_addr);
@@ -481,14 +505,9 @@ static int dmem_alloc_region_init(struct dmem_region *dregion,
 	if (!*dpages)
 		return 0;
 
-	size = BITS_TO_LONGS(*dpages) * sizeof(long);
-	if (size <= sizeof(dregion->static_bitmap))
-		bitmap = &dregion->static_bitmap;
-	else {
-		bitmap = kzalloc(size, GFP_KERNEL);
-		if (!bitmap)
-			return -ENOMEM;
-	}
+	bitmap = dmem_bitmap_alloc(*dpages, &dregion->static_bitmap);
+	if (!bitmap)
+		return -ENOMEM;
 
 	dregion->bitmap = bitmap;
 	dregion->next_free_pos = 0;
@@ -582,7 +601,7 @@ static void dmem_uinit_check_alloc_bitmap(struct dmem_region *dregion)
 
 static void dmem_alloc_region_uinit(struct dmem_region *dregion)
 {
-	unsigned long dpages, size, *bitmap = dregion->bitmap;
+	unsigned long dpages, *bitmap = dregion->bitmap;
 
 	if (!bitmap)
 		return;
@@ -592,9 +611,7 @@ static void dmem_alloc_region_uinit(struct dmem_region *dregion)
 
 	dmem_uinit_check_alloc_bitmap(dregion);
 
-	size = BITS_TO_LONGS(dpages) * sizeof(long);
-	if (size > sizeof(dregion->static_bitmap))
-		kfree(bitmap);
+	dmem_bitmap_free(dpages, bitmap, &dregion->static_bitmap);
 	dregion->bitmap = NULL;
 }
 
-- 
1.8.3.1



  parent reply	other threads:[~2020-12-07 11:35 UTC|newest]

Thread overview: 41+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-12-07 11:30 [RFC V2 00/37] Enhance memory utilization with DMEMFS yulei.kernel
2020-12-07 11:30 ` [RFC V2 01/37] fs: introduce dmemfs module yulei.kernel
2020-12-07 11:30 ` [RFC V2 02/37] mm: support direct memory reservation yulei.kernel
2020-12-07 11:30 ` [RFC V2 03/37] dmem: implement dmem memory management yulei.kernel
2020-12-07 11:30 ` [RFC V2 04/37] dmem: let pat recognize dmem yulei.kernel
2020-12-07 11:30 ` [RFC V2 05/37] dmemfs: support mmap for dmemfs yulei.kernel
2020-12-07 11:30 ` [RFC V2 06/37] dmemfs: support truncating inode down yulei.kernel
2020-12-07 11:31 ` [RFC V2 07/37] dmem: trace core functions yulei.kernel
2020-12-07 11:31 ` [RFC V2 08/37] dmem: show some statistic in debugfs yulei.kernel
2020-12-07 11:31 ` [RFC V2 09/37] dmemfs: support remote access yulei.kernel
2020-12-07 11:31 ` [RFC V2 10/37] dmemfs: introduce max_alloc_try_dpages parameter yulei.kernel
2020-12-07 11:31 ` [RFC V2 11/37] mm: export mempolicy interfaces to serve dmem allocator yulei.kernel
2020-12-07 11:31 ` [RFC V2 12/37] dmem: introduce mempolicy support yulei.kernel
2020-12-07 11:31 ` [RFC V2 13/37] mm, dmem: introduce PFN_DMEM and pfn_t_dmem yulei.kernel
2020-12-07 11:31 ` [RFC V2 14/37] mm, dmem: differentiate dmem-pmd and thp-pmd yulei.kernel
2020-12-07 11:31 ` [RFC V2 15/37] mm: add pmd_special() check for pmd_trans_huge_lock() yulei.kernel
2020-12-07 11:31 ` [RFC V2 16/37] dmemfs: introduce ->split() to dmemfs_vm_ops yulei.kernel
2020-12-07 11:31 ` [RFC V2 17/37] mm, dmemfs: support unmap_page_range() for dmemfs pmd yulei.kernel
2020-12-07 11:31 ` [RFC V2 18/37] mm: follow_pmd_mask() for dmem huge pmd yulei.kernel
2020-12-07 11:31 ` [RFC V2 19/37] mm: gup_huge_pmd() " yulei.kernel
2020-12-07 11:31 ` [RFC V2 20/37] mm: support dmem huge pmd for vmf_insert_pfn_pmd() yulei.kernel
2020-12-07 11:31 ` [RFC V2 21/37] mm: support dmem huge pmd for follow_pfn() yulei.kernel
2020-12-07 11:31 ` [RFC V2 22/37] kvm, x86: Distinguish dmemfs page from mmio page yulei.kernel
2020-12-07 11:31 ` [RFC V2 23/37] kvm, x86: introduce VM_DMEM for syscall support usage yulei.kernel
2020-12-07 11:31 ` [RFC V2 24/37] dmemfs: support hugepage for dmemfs yulei.kernel
2020-12-07 11:31 ` [RFC V2 25/37] mm, x86, dmem: fix estimation of reserved page for vaddr_get_pfn() yulei.kernel
2020-12-07 11:31 ` [RFC V2 26/37] mm, dmem: introduce pud_special() for dmem huge pud support yulei.kernel
2020-12-07 11:31 ` [RFC V2 27/37] mm: add pud_special() check to support dmem huge pud yulei.kernel
2020-12-07 11:31 ` [RFC V2 28/37] mm, dmemfs: support huge_fault() for dmemfs yulei.kernel
2020-12-07 11:31 ` [RFC V2 29/37] mm: add follow_pte_pud() to support huge pud look up yulei.kernel
2020-12-07 11:31 ` yulei.kernel [this message]
2020-12-07 11:31 ` [RFC V2 31/37] dmem: introduce mce handler yulei.kernel
2020-12-07 11:31 ` [RFC V2 32/37] mm, dmemfs: register and handle the dmem mce yulei.kernel
2020-12-07 11:31 ` [RFC V2 33/37] kvm, x86: enable record_steal_time for dmem yulei.kernel
2020-12-07 11:31 ` [RFC V2 34/37] dmem: add dmem unit tests yulei.kernel
2020-12-07 11:31 ` [RFC V2 35/37] mm, dmem: introduce dregion->memmap for dmem yulei.kernel
2020-12-07 11:31 ` [RFC V2 36/37] vfio: support dmempage refcount for vfio yulei.kernel
2020-12-07 11:31 ` [RFC V2 37/37] Add documentation for dmemfs yulei.kernel
2020-12-24 18:27   ` Randy Dunlap
2020-12-07 12:02 ` [RFC V2 00/37] Enhance memory utilization with DMEMFS David Hildenbrand
2020-12-07 19:32   ` Dan Williams

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=6eca6b9b58b3cf9a52c8227ee92d9b926c249f0b.1607332046.git.yuleixzhang@tencent.com \
    --to=yulei.kernel@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=joao.m.martins@oracle.com \
    --cc=kernellwp@gmail.com \
    --cc=kvm@vger.kernel.org \
    --cc=lihaiwei.kernel@gmail.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=naoya.horiguchi@nec.com \
    --cc=pbonzini@redhat.com \
    --cc=rdunlap@infradead.org \
    --cc=sagazchen@tencent.com \
    --cc=sean.j.christopherson@intel.com \
    --cc=viro@zeniv.linux.org.uk \
    --cc=xiaoguangrong.eric@gmail.com \
    --cc=yuleixzhang@tencent.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).