linux-kernel - [PATCH net-next 3/3] net/smc: optimize MTTE consumption for SMC-R buffers

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: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20260123082349.42663-4-alibuda@linux.alibaba.com>
Date: Fri, 23 Jan 2026 16:23:49 +0800
From: "D. Wythe" <alibuda@...ux.alibaba.com>
To: "David S. Miller" <davem@...emloft.net>,
	Andrew Morton <akpm@...ux-foundation.org>,
	Dust Li <dust.li@...ux.alibaba.com>,
	Eric Dumazet <edumazet@...gle.com>,
	Jakub Kicinski <kuba@...nel.org>,
	Paolo Abeni <pabeni@...hat.com>,
	Sidraya Jayagond <sidraya@...ux.ibm.com>,
	Uladzislau Rezki <urezki@...il.com>,
	Wenjia Zhang <wenjia@...ux.ibm.com>
Cc: Mahanta Jambigi <mjambigi@...ux.ibm.com>,
	Simon Horman <horms@...nel.org>,
	Tony Lu <tonylu@...ux.alibaba.com>,
	Wen Gu <guwen@...ux.alibaba.com>,
	linux-kernel@...r.kernel.org,
	linux-mm@...ck.org,
	linux-rdma@...r.kernel.org,
	linux-s390@...r.kernel.org,
	netdev@...r.kernel.org,
	oliver.yang@...ux.alibaba.com
Subject: [PATCH net-next 3/3] net/smc: optimize MTTE consumption for SMC-R buffers

SMC-R buffers currently use 4KB page mapping for IB registration.
Each page consumes one MTTE, which is inefficient and quickly depletes
limited IB hardware resources for large buffers.

For virtual contiguous buffer, switch to vmalloc_huge() to leverage
huge page support. By using larger page sizes during IB MR registration,
we can drastically reduce MTTE consumption.

For physically contiguous buffer, the entire buffer now requires only
one single MTTE.

Signed-off-by: D. Wythe <alibuda@...ux.alibaba.com>
Reviewed-by: Dust Li <dust.li@...ux.alibaba.com>
---
 net/smc/smc_core.c |  3 ++-
 net/smc/smc_ib.c   | 23 ++++++++++++++++++++---
 2 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 6219db498976..8aca5dc54be7 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -2348,7 +2348,8 @@ static struct smc_buf_desc *smcr_new_buf_create(struct smc_link_group *lgr,
 			goto out;
 		fallthrough;	// try virtually contiguous buf
 	case SMCR_VIRT_CONT_BUFS:
-		buf_desc->cpu_addr = vzalloc(PAGE_SIZE << buf_desc->order);
+		buf_desc->cpu_addr = vmalloc_huge(PAGE_SIZE << buf_desc->order,
+						  GFP_KERNEL | __GFP_ZERO);
 		if (!buf_desc->cpu_addr)
 			goto out;
 		buf_desc->pages = NULL;
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index 1154907c5c05..67211d44a1db 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -20,6 +20,7 @@
 #include <linux/wait.h>
 #include <linux/mutex.h>
 #include <linux/inetdevice.h>
+#include <linux/vmalloc.h>
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_cache.h>
 
@@ -697,6 +698,18 @@ void smc_ib_put_memory_region(struct ib_mr *mr)
 	ib_dereg_mr(mr);
 }
 
+static inline int smc_buf_get_vm_page_order(struct smc_buf_desc *buf_slot)
+{
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
+	struct vm_struct *vm;
+
+	vm = find_vm_area(buf_slot->cpu_addr);
+	return vm ? vm->page_order : 0;
+#else
+	return 0;
+#endif
+}
+
 static int smc_ib_map_mr_sg(struct smc_buf_desc *buf_slot, u8 link_idx)
 {
 	unsigned int offset = 0;
@@ -706,8 +719,9 @@ static int smc_ib_map_mr_sg(struct smc_buf_desc *buf_slot, u8 link_idx)
 	sg_num = ib_map_mr_sg(buf_slot->mr[link_idx],
 			      buf_slot->sgt[link_idx].sgl,
 			      buf_slot->sgt[link_idx].orig_nents,
-			      &offset, PAGE_SIZE);
-
+			      &offset,
+			      buf_slot->is_vm ? PAGE_SIZE << smc_buf_get_vm_page_order(buf_slot) :
+			      PAGE_SIZE << buf_slot->order);
 	return sg_num;
 }
 
@@ -719,7 +733,10 @@ int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags,
 		return 0; /* already done */
 
 	buf_slot->mr[link_idx] =
-		ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, 1 << buf_slot->order);
+		ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG,
+			    buf_slot->is_vm ?
+			    1 << (buf_slot->order - smc_buf_get_vm_page_order(buf_slot)) : 1);
+
 	if (IS_ERR(buf_slot->mr[link_idx])) {
 		int rc;
 
-- 
2.45.0