linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Mike Rapoport <rppt@kernel.org>
To: linux-kernel@vger.kernel.org
Cc: Alan Cox <alan@linux.intel.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Andy Lutomirski <luto@kernel.org>,
	Christopher Lameter <cl@linux.com>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	Idan Yaniv <idan.yaniv@ibm.com>,
	James Bottomley <jejb@linux.ibm.com>,
	"Kirill A. Shutemov" <kirill@shutemov.name>,
	Matthew Wilcox <willy@infradead.org>,
	Peter Zijlstra <peterz@infradead.org>,
	"Reshetova, Elena" <elena.reshetova@intel.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Tycho Andersen <tycho@tycho.ws>,
	linux-api@vger.kernel.org, linux-mm@kvack.org,
	Mike Rapoport <rppt@linux.ibm.com>
Subject: [RFC PATCH v2 5/5] mm: secretmem: add ability to reserve memory at boot
Date: Mon,  6 Jul 2020 20:20:51 +0300	[thread overview]
Message-ID: <20200706172051.19465-6-rppt@kernel.org> (raw)
In-Reply-To: <20200706172051.19465-1-rppt@kernel.org>

From: Mike Rapoport <rppt@linux.ibm.com>

Taking pages out from the direct map and bringing them back may create
undesired fragmentation and usage of the smaller pages in the direct
mapping of the physical memory.

This can be avoided if a significantly large area of the physical memory
would be reserved for secretmem purposes at boot time.

Add ability to reserve physical memory for secretmem at boot time using
"secretmem" kernel parameter and then use that reserved memory as a global
pool for secret memory needs.

Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
---
 mm/secretmem.c | 145 ++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 137 insertions(+), 8 deletions(-)

diff --git a/mm/secretmem.c b/mm/secretmem.c
index c6fcf6d76951..d50ac9ea1844 100644
--- a/mm/secretmem.c
+++ b/mm/secretmem.c
@@ -6,6 +6,8 @@
 #include <linux/printk.h>
 #include <linux/pagemap.h>
 #include <linux/genalloc.h>
+#include <linux/memblock.h>
+#include <linux/mm_inline.h>
 #include <linux/pseudo_fs.h>
 #include <linux/set_memory.h>
 #include <linux/sched/signal.h>
@@ -28,6 +30,39 @@ struct secretmem_ctx {
 	unsigned int mode;
 };
 
+struct secretmem_pool {
+	struct gen_pool *pool;
+	unsigned long reserved_size;
+	void *reserved;
+};
+
+static struct secretmem_pool secretmem_pool;
+
+static struct page *secretmem_alloc_huge_page(gfp_t gfp)
+{
+	struct gen_pool *pool = secretmem_pool.pool;
+	unsigned long addr = 0;
+	struct page *page = NULL;
+
+	if (pool) {
+		if (gen_pool_avail(pool) < HPAGE_PMD_SIZE)
+			return NULL;
+
+		addr = gen_pool_alloc(pool, HPAGE_PMD_SIZE);
+		if (!addr)
+			return NULL;
+
+		page = virt_to_page(addr);
+	} else {
+		page = alloc_pages(gfp, HPAGE_PMD_ORDER);
+
+		if (page)
+			split_page(page, HPAGE_PMD_ORDER);
+	}
+
+	return page;
+}
+
 static int secretmem_pool_increase(struct secretmem_ctx *ctx, gfp_t gfp)
 {
 	unsigned long nr_pages = (1 << HPAGE_PMD_ORDER);
@@ -36,12 +71,11 @@ static int secretmem_pool_increase(struct secretmem_ctx *ctx, gfp_t gfp)
 	struct page *page;
 	int err;
 
-	page = alloc_pages(gfp, HPAGE_PMD_ORDER);
+	page = secretmem_alloc_huge_page(gfp);
 	if (!page)
 		return -ENOMEM;
 
 	addr = (unsigned long)page_address(page);
-	split_page(page, HPAGE_PMD_ORDER);
 
 	err = gen_pool_add(pool, addr, HPAGE_PMD_SIZE, NUMA_NO_NODE);
 	if (err) {
@@ -250,11 +284,23 @@ struct file *secretmem_file_create(const char *name, unsigned int flags)
 	return file;
 }
 
-static void secretmem_cleanup_chunk(struct gen_pool *pool,
-				    struct gen_pool_chunk *chunk, void *data)
+static void secretmem_recycle_range(unsigned long start, unsigned long end)
+{
+	unsigned long addr;
+
+	for (addr = start; addr < end; addr += PAGE_SIZE) {
+		struct page *page = virt_to_page(addr);
+		struct lruvec *lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
+
+		__ClearPageLRU(page);
+		del_page_from_lru_list(page, lruvec, page_off_lru(page));
+	}
+
+	gen_pool_free(secretmem_pool.pool, start, HPAGE_PMD_SIZE);
+}
+
+static void secretmem_release_range(unsigned long start, unsigned long end)
 {
-	unsigned long start = chunk->start_addr;
-	unsigned long end = chunk->end_addr;
 	unsigned long nr_pages, addr;
 
 	nr_pages = (end - start + 1) / PAGE_SIZE;
@@ -264,6 +310,18 @@ static void secretmem_cleanup_chunk(struct gen_pool *pool,
 		put_page(virt_to_page(addr));
 }
 
+static void secretmem_cleanup_chunk(struct gen_pool *pool,
+				    struct gen_pool_chunk *chunk, void *data)
+{
+	unsigned long start = chunk->start_addr;
+	unsigned long end = chunk->end_addr;
+
+	if (secretmem_pool.pool)
+		secretmem_recycle_range(start, end);
+	else
+		secretmem_release_range(start, end);
+}
+
 static void secretmem_cleanup_pool(struct secretmem_ctx *ctx)
 {
 	struct gen_pool *pool = ctx->pool;
@@ -303,14 +361,85 @@ static struct file_system_type secretmem_fs = {
 	.kill_sb	= kill_anon_super,
 };
 
+static int secretmem_reserved_mem_init(void)
+{
+	struct gen_pool *pool;
+	struct page *page;
+	void *addr;
+	int err;
+
+	if (!secretmem_pool.reserved)
+		return 0;
+
+	pool = gen_pool_create(PMD_SHIFT, NUMA_NO_NODE);
+	if (!pool)
+		return -ENOMEM;
+
+	err = gen_pool_add(pool, (unsigned long)secretmem_pool.reserved,
+			   secretmem_pool.reserved_size, NUMA_NO_NODE);
+	if (err)
+		goto err_destroy_pool;
+
+	for (addr = secretmem_pool.reserved;
+	     addr < secretmem_pool.reserved + secretmem_pool.reserved_size;
+	     addr += PAGE_SIZE) {
+		page = virt_to_page(addr);
+		__ClearPageReserved(page);
+		set_page_count(page, 1);
+	}
+
+	secretmem_pool.pool = pool;
+	page = virt_to_page(secretmem_pool.reserved);
+	__kernel_map_pages(page, secretmem_pool.reserved_size / PAGE_SIZE, 0);
+	return 0;
+
+err_destroy_pool:
+	gen_pool_destroy(pool);
+	return err;
+}
+
 static int secretmem_init(void)
 {
-	int ret = 0;
+	int ret;
+
+	ret = secretmem_reserved_mem_init();
+	if (ret)
+		return ret;
 
 	secretmem_mnt = kern_mount(&secretmem_fs);
-	if (IS_ERR(secretmem_mnt))
+	if (IS_ERR(secretmem_mnt)) {
+		gen_pool_destroy(secretmem_pool.pool);
 		ret = PTR_ERR(secretmem_mnt);
+	}
 
 	return ret;
 }
 fs_initcall(secretmem_init);
+
+static int __init secretmem_setup(char *str)
+{
+	phys_addr_t align = HPAGE_PMD_SIZE;
+	unsigned long reserved_size;
+	void *reserved;
+
+	reserved_size = memparse(str, NULL);
+	if (!reserved_size)
+		return 0;
+
+	if (reserved_size * 2 > HPAGE_PUD_SIZE)
+		align = HPAGE_PUD_SIZE;
+
+	reserved = memblock_alloc(reserved_size, align);
+	if (!reserved) {
+		pr_err("failed to reserve %zu bytes\n", secretmem_pool.reserved_size);
+		return 0;
+	}
+
+	secretmem_pool.reserved_size = reserved_size;
+	secretmem_pool.reserved = reserved;
+
+	pr_info("reserved %zuM\n", reserved_size >> 20);
+
+	return 1;
+}
+__setup("secretmem=", secretmem_setup);
-- 
2.26.2


  parent reply	other threads:[~2020-07-06 17:21 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-06 17:20 [RFC PATCH v2 0/5] mm: extend memfd with ability to create "secret" memory areas Mike Rapoport
2020-07-06 17:20 ` [RFC PATCH v2 1/5] mm: make HPAGE_PxD_{SHIFT,MASK,SIZE} always available Mike Rapoport
2020-07-07  5:07   ` Hugh Dickins
2020-07-07  6:47     ` Mike Rapoport
2020-07-10 16:40     ` Andrea Arcangeli
2020-07-10 16:57       ` Matthew Wilcox
2020-07-10 17:08         ` Andrea Arcangeli
2020-07-10 17:12         ` Mike Rapoport
2020-07-06 17:20 ` [RFC PATCH v2 2/5] mmap: make mlock_future_check() global Mike Rapoport
2020-07-06 17:20 ` [RFC PATCH v2 3/5] mm: extend memfd with ability to create "secret" memory areas Mike Rapoport
2020-07-13 10:58   ` Kirill A. Shutemov
2020-07-13 15:31     ` Mike Rapoport
2020-07-06 17:20 ` [RFC PATCH v2 4/5] mm: secretmem: use PMD-size pages to amortize direct map fragmentation Mike Rapoport
2020-07-13 11:05   ` Kirill A. Shutemov
2020-07-13 15:32     ` Mike Rapoport
2020-07-06 17:20 ` Mike Rapoport [this message]
2020-07-17  8:36 ` [RFC PATCH v2 0/5] mm: extend memfd with ability to create "secret" memory areas Pavel Machek
2020-07-17 14:43   ` James Bottomley

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=20200706172051.19465-6-rppt@kernel.org \
    --to=rppt@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=alan@linux.intel.com \
    --cc=cl@linux.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=elena.reshetova@intel.com \
    --cc=idan.yaniv@ibm.com \
    --cc=jejb@linux.ibm.com \
    --cc=kirill@shutemov.name \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@kernel.org \
    --cc=peterz@infradead.org \
    --cc=rppt@linux.ibm.com \
    --cc=tglx@linutronix.de \
    --cc=tycho@tycho.ws \
    --cc=willy@infradead.org \
    --subject='Re: [RFC PATCH v2 5/5] mm: secretmem: add ability to reserve memory at boot' \
    /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

This is a public inbox, see mirroring instructions
on how to clone and mirror all data and code used for this inbox