linux-kernel - [PATCH rfc v4 2/4] page_pool: add interface to manipulate bias in page pool

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite for Android: free password hash cracker in your pocket
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <1626168272-25622-3-git-send-email-linyunsheng@huawei.com>
Date:   Tue, 13 Jul 2021 17:24:30 +0800
From:   Yunsheng Lin <linyunsheng@...wei.com>
To:     <davem@...emloft.net>, <kuba@...nel.org>
CC:     <alexander.duyck@...il.com>, <linux@...linux.org.uk>,
        <mw@...ihalf.com>, <linuxarm@...neuler.org>,
        <yisen.zhuang@...wei.com>, <salil.mehta@...wei.com>,
        <thomas.petazzoni@...tlin.com>, <hawk@...nel.org>,
        <ilias.apalodimas@...aro.org>, <ast@...nel.org>,
        <daniel@...earbox.net>, <john.fastabend@...il.com>,
        <akpm@...ux-foundation.org>, <peterz@...radead.org>,
        <will@...nel.org>, <willy@...radead.org>, <vbabka@...e.cz>,
        <fenghua.yu@...el.com>, <guro@...com>, <peterx@...hat.com>,
        <feng.tang@...el.com>, <jgg@...pe.ca>, <mcroce@...rosoft.com>,
        <hughd@...gle.com>, <jonathan.lemon@...il.com>, <alobakin@...me>,
        <willemb@...gle.com>, <wenxu@...oud.cn>, <cong.wang@...edance.com>,
        <haokexin@...il.com>, <nogikh@...gle.com>, <elver@...gle.com>,
        <yhs@...com>, <kpsingh@...nel.org>, <andrii@...nel.org>,
        <kafai@...com>, <songliubraving@...com>, <netdev@...r.kernel.org>,
        <linux-kernel@...r.kernel.org>, <bpf@...r.kernel.org>
Subject: [PATCH rfc v4 2/4] page_pool: add interface to manipulate bias in page pool

As suggested by Alexander, "A DMA mapping should be page
aligned anyway so the lower 12 bits would be reserved 0",
so it might make more sense to repurpose the lower 12 bits
of the dma address to store the bias for frag page support
in page pool for 32 bit systems with 64 bit dma, which
should be rare those days.

For normal system, the dma_addr[1] in 'struct page' is not
used, so we can reuse the dma_addr[1] for storing bias.

The PAGE_POOP_USE_DMA_ADDR_1 macro is used to decide where
to store the bias, as the "sizeof(dma_addr_t) > sizeof(
unsigned long)" is false for normal system, so hopefully the
compiler will optimize out the unused code for those system.

The newly added page_pool_set_bias() should be called before
the page is passed to any user. Otherwise, call the newly
added page_pool_atomic_sub_bias_return().

Signed-off-by: Yunsheng Lin <linyunsheng@...wei.com>
---
 include/net/page_pool.h | 70 ++++++++++++++++++++++++++++++++++++++++++++++---
 net/core/page_pool.c    | 10 +++++++
 2 files changed, 77 insertions(+), 3 deletions(-)

diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index 8d7744d..315b9f2 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -198,21 +198,85 @@ static inline void page_pool_recycle_direct(struct page_pool *pool,
 	page_pool_put_full_page(pool, page, true);
 }
 
+#define PAGE_POOP_USE_DMA_ADDR_1	(sizeof(dma_addr_t) > sizeof(unsigned long))
+
 static inline dma_addr_t page_pool_get_dma_addr(struct page *page)
 {
-	dma_addr_t ret = page->dma_addr[0];
-	if (sizeof(dma_addr_t) > sizeof(unsigned long))
+	dma_addr_t ret;
+
+	if (PAGE_POOP_USE_DMA_ADDR_1) {
+		ret = READ_ONCE(page->dma_addr[0]) & PAGE_MASK;
 		ret |= (dma_addr_t)page->dma_addr[1] << 16 << 16;
+	} else {
+		ret = page->dma_addr[0];
+	}
+
 	return ret;
 }
 
 static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr)
 {
 	page->dma_addr[0] = addr;
-	if (sizeof(dma_addr_t) > sizeof(unsigned long))
+	if (PAGE_POOP_USE_DMA_ADDR_1)
 		page->dma_addr[1] = upper_32_bits(addr);
 }
 
+static inline int page_pool_atomic_sub_bias_return(struct page *page, int nr)
+{
+	int bias;
+
+	if (PAGE_POOP_USE_DMA_ADDR_1) {
+		unsigned long *bias_ptr = &page->dma_addr[0];
+		unsigned long old_bias = READ_ONCE(*bias_ptr);
+		unsigned long new_bias;
+
+		do {
+			bias = (int)(old_bias & ~PAGE_MASK);
+
+			/* Warn when page_pool_dev_alloc_pages() is called
+			 * with PP_FLAG_PAGE_FRAG flag in driver.
+			 */
+			WARN_ON(!bias);
+
+			/* already the last user */
+			if (!(bias - nr))
+				return 0;
+
+			new_bias = old_bias - nr;
+		} while (!try_cmpxchg(bias_ptr, &old_bias, new_bias));
+
+		WARN_ON((new_bias & PAGE_MASK) != (old_bias & PAGE_MASK));
+
+		bias = new_bias & ~PAGE_MASK;
+	} else {
+		atomic_t *v = (atomic_t *)&page->dma_addr[1];
+
+		if (atomic_read(v) == nr)
+			return 0;
+
+		bias = atomic_sub_return(nr, v);
+		WARN_ON(bias < 0);
+	}
+
+	return bias;
+}
+
+static inline void page_pool_set_bias(struct page *page, int bias)
+{
+	if (PAGE_POOP_USE_DMA_ADDR_1) {
+		unsigned long dma_addr_0 = READ_ONCE(page->dma_addr[0]);
+
+		dma_addr_0 &= PAGE_MASK;
+		dma_addr_0 |= bias;
+
+		WRITE_ONCE(page->dma_addr[0], dma_addr_0);
+	} else {
+		atomic_t *v = (atomic_t *)&page->dma_addr[1];
+
+		atomic_set(v, bias);
+	}
+}
+
 static inline bool is_page_pool_compiled_in(void)
 {
 #ifdef CONFIG_PAGE_POOL
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 78838c6..6ac5b00 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -198,6 +198,16 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page)
 	if (dma_mapping_error(pool->p.dev, dma))
 		return false;
 
+	if (PAGE_POOP_USE_DMA_ADDR_1 &&
+	    WARN_ON(pool->p.flags & PP_FLAG_PAGE_FRAG &&
+		    dma & ~PAGE_MASK)) {
+		dma_unmap_page_attrs(pool->p.dev, dma,
+				     PAGE_SIZE << pool->p.order,
+				     pool->p.dma_dir,
+				     DMA_ATTR_SKIP_CPU_SYNC);
+		return false;
+	}
+
 	page_pool_set_dma_addr(page, dma);
 
 	if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
-- 
2.7.4