Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Baoquan He <bhe@redhat.com>
To:     linux-kernel@vger.kernel.org
Cc:     linux-mm@kvack.org, urezki@gmail.com, stephen.s.brennan@oracle.com,
        willy@infradead.org, akpm@linux-foundation.org, hch@infradead.org,
        Baoquan He <bhe@redhat.com>
Subject: [PATCH v2 2/7] mm/vmalloc.c: add flags to mark vm_map_ram area
Date:   Sat, 17 Dec 2022 09:54:30 +0800
Message-Id: <20221217015435.73889-3-bhe@redhat.com>
In-Reply-To: <20221217015435.73889-1-bhe@redhat.com>
References: <20221217015435.73889-1-bhe@redhat.com>
MIME-Version: 1.0
Content-type: text/plain
Content-Transfer-Encoding: 8bit
Precedence: bulk

Through vmalloc API, a virtual kernel area is reserved for physical
address mapping. And vmap_area is used to track them, while vm_struct
is allocated to associate with the vmap_area to store more information
and passed out.

However, area reserved via vm_map_ram() is an exception. It doesn't have
vm_struct to associate with vmap_area. And we can't recognize the
vmap_area with '->vm == NULL' as a vm_map_ram() area because the normal
freeing path will set va->vm = NULL before unmapping, please see
function remove_vm_area().

Meanwhile, there are two types of vm_map_ram area. One is the whole
vmap_area being reserved and mapped at one time; the other is the
whole vmap_area with VMAP_BLOCK_SIZE size being reserved, while mapped
into split regions with smaller size several times via vb_alloc().

To mark the area reserved through vm_map_ram(), add flags field into
struct vmap_area. Bit 0 indicates whether it's a vm_map_ram area,
while bit 1 indicates whether it's a vmap_block type of vm_map_ram
area.

This is a preparatoin for later use.

Signed-off-by: Baoquan He <bhe@redhat.com>
---
 include/linux/vmalloc.h |  1 +
 mm/vmalloc.c            | 22 +++++++++++++++++-----
 2 files changed, 18 insertions(+), 5 deletions(-)

diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 096d48aa3437..69250efa03d1 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -76,6 +76,7 @@ struct vmap_area {
 		unsigned long subtree_max_size; /* in "free" tree */
 		struct vm_struct *vm;           /* in "busy" tree */
 	};
+	unsigned long flags; /* mark type of vm_map_ram area */
 };
 
 /* archs that select HAVE_ARCH_HUGE_VMAP should override one or more of these */
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 5d3fd3e6fe09..190f29bbaaa7 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1586,7 +1586,8 @@ preload_this_cpu_lock(spinlock_t *lock, gfp_t gfp_mask, int node)
 static struct vmap_area *alloc_vmap_area(unsigned long size,
 				unsigned long align,
 				unsigned long vstart, unsigned long vend,
-				int node, gfp_t gfp_mask)
+				int node, gfp_t gfp_mask,
+				unsigned long va_flags)
 {
 	struct vmap_area *va;
 	unsigned long freed;
@@ -1630,6 +1631,7 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
 	va->va_start = addr;
 	va->va_end = addr + size;
 	va->vm = NULL;
+	va->flags = va_flags;
 
 	spin_lock(&vmap_area_lock);
 	insert_vmap_area(va, &vmap_area_root, &vmap_area_list);
@@ -1887,6 +1889,10 @@ struct vmap_area *find_vmap_area(unsigned long addr)
 
 #define VMAP_BLOCK_SIZE		(VMAP_BBMAP_BITS * PAGE_SIZE)
 
+#define VMAP_RAM		0x1
+#define VMAP_BLOCK		0x2
+#define VMAP_FLAGS_MASK		0x3
+
 struct vmap_block_queue {
 	spinlock_t lock;
 	struct list_head free;
@@ -1962,7 +1968,8 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask)
 
 	va = alloc_vmap_area(VMAP_BLOCK_SIZE, VMAP_BLOCK_SIZE,
 					VMALLOC_START, VMALLOC_END,
-					node, gfp_mask);
+					node, gfp_mask,
+					VMAP_RAM|VMAP_BLOCK);
 	if (IS_ERR(va)) {
 		kfree(vb);
 		return ERR_CAST(va);
@@ -2229,8 +2236,12 @@ void vm_unmap_ram(const void *mem, unsigned int count)
 		return;
 	}
 
-	va = find_vmap_area(addr);
+	spin_lock(&vmap_area_lock);
+	va = __find_vmap_area((unsigned long)addr, &vmap_area_root);
 	BUG_ON(!va);
+	if (va)
+		va->flags &= ~VMAP_RAM;
+	spin_unlock(&vmap_area_lock);
 	debug_check_no_locks_freed((void *)va->va_start,
 				    (va->va_end - va->va_start));
 	free_unmap_vmap_area(va);
@@ -2265,7 +2276,8 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node)
 	} else {
 		struct vmap_area *va;
 		va = alloc_vmap_area(size, PAGE_SIZE,
-				VMALLOC_START, VMALLOC_END, node, GFP_KERNEL);
+				VMALLOC_START, VMALLOC_END,
+				node, GFP_KERNEL, VMAP_RAM);
 		if (IS_ERR(va))
 			return NULL;
 
@@ -2505,7 +2517,7 @@ static struct vm_struct *__get_vm_area_node(unsigned long size,
 	if (!(flags & VM_NO_GUARD))
 		size += PAGE_SIZE;
 
-	va = alloc_vmap_area(size, align, start, end, node, gfp_mask);
+	va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0);
 	if (IS_ERR(va)) {
 		kfree(area);
 		return NULL;
-- 
2.34.1