| 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
| ||
|
Message-Id: <d2017c29-11fb-44a5-bd0f-4204329bbefb@app.fastmail.com>
Date: Thu, 16 Oct 2025 15:58:36 +0200
From: "Pierre Barre" <pierre@...re.sh>
To: "Christian Schoenebeck" <linux_oss@...debyte.com>,
asmadeus <asmadeus@...ewreck.org>
Cc: "Matthew Wilcox (Oracle)" <willy@...radead.org>, v9fs@...ts.linux.dev,
ericvh@...nel.org, lucho@...kov.net, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v3] 9p: Use kvmalloc for message buffers on supported transports
While developing a 9P server (https://github.com/Barre/ZeroFS) and
testing it under high-load, I was running into allocation failures.
The failures occur even with plenty of free memory available because
kmalloc requires contiguous physical memory.
This results in errors like:
ls: page allocation failure: order:7, mode:0x40c40(GFP_NOFS|__GFP_COMP)
This patch introduces a transport capability flag (supports_vmalloc)
that indicates whether a transport can work with vmalloc'd buffers
(non-physically contiguous memory). Transports requiring DMA should
leave this flag as false.
The fd-based transports (tcp, unix, fd) set this flag to true, and
p9_fcall_init will use kvmalloc instead of kmalloc for these
transports. This allows the allocator to fall back to vmalloc when
contiguous physical memory is not available.
Additionally, if kmem_cache_alloc fails, the code falls back to
kvmalloc for transports that support it.
Signed-off-by: Pierre Barre <pierre@...re.sh>
---
Changes in v3:
- Added explicit .supports_vmalloc = false to DMA-based transports
(suggested by Christian Schoenebeck)
include/net/9p/transport.h | 4 ++++
net/9p/client.c | 11 +++++++++--
net/9p/trans_fd.c | 3 +++
net/9p/trans_rdma.c | 1 +
net/9p/trans_usbg.c | 1 +
net/9p/trans_virtio.c | 1 +
net/9p/trans_xen.c | 1 +
7 files changed, 20 insertions(+), 2 deletions(-)
diff --git a/include/net/9p/transport.h b/include/net/9p/transport.h
index 766ec07c9599..f0981515148d 100644
--- a/include/net/9p/transport.h
+++ b/include/net/9p/transport.h
@@ -24,6 +24,9 @@
* we're less flexible when choosing the response message
* size in this case
* @def: set if this transport should be considered the default
+ * @supports_vmalloc: set if this transport can work with vmalloc'd buffers
+ * (non-physically contiguous memory). Transports requiring
+ * DMA should leave this as false.
* @create: member function to create a new connection on this transport
* @close: member function to discard a connection on this transport
* @request: member function to issue a request to the transport
@@ -44,6 +47,7 @@ struct p9_trans_module {
int maxsize; /* max message size of transport */
bool pooled_rbuffers;
int def; /* this transport should be default */
+ bool supports_vmalloc; /* can work with vmalloc'd buffers */
struct module *owner;
int (*create)(struct p9_client *client,
const char *devname, char *args);
diff --git a/net/9p/client.c b/net/9p/client.c
index 5c1ca57ccd28..2a4884c880c1 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -229,8 +229,15 @@ static int p9_fcall_init(struct p9_client *c, struct p9_fcall *fc,
if (likely(c->fcall_cache) && alloc_msize == c->msize) {
fc->sdata = kmem_cache_alloc(c->fcall_cache, GFP_NOFS);
fc->cache = c->fcall_cache;
+ if (!fc->sdata && c->trans_mod->supports_vmalloc) {
+ fc->sdata = kvmalloc(alloc_msize, GFP_NOFS);
+ fc->cache = NULL;
+ }
} else {
- fc->sdata = kmalloc(alloc_msize, GFP_NOFS);
+ if (c->trans_mod->supports_vmalloc)
+ fc->sdata = kvmalloc(alloc_msize, GFP_NOFS);
+ else
+ fc->sdata = kmalloc(alloc_msize, GFP_NOFS);
fc->cache = NULL;
}
if (!fc->sdata)
@@ -252,7 +259,7 @@ void p9_fcall_fini(struct p9_fcall *fc)
if (fc->cache)
kmem_cache_free(fc->cache, fc->sdata);
else
- kfree(fc->sdata);
+ kvfree(fc->sdata);
}
EXPORT_SYMBOL(p9_fcall_fini);
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index a516745f732f..e7334033eba5 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -1101,6 +1101,7 @@ static struct p9_trans_module p9_tcp_trans = {
.maxsize = MAX_SOCK_BUF,
.pooled_rbuffers = false,
.def = 0,
+ .supports_vmalloc = true,
.create = p9_fd_create_tcp,
.close = p9_fd_close,
.request = p9_fd_request,
@@ -1115,6 +1116,7 @@ static struct p9_trans_module p9_unix_trans = {
.name = "unix",
.maxsize = MAX_SOCK_BUF,
.def = 0,
+ .supports_vmalloc = true,
.create = p9_fd_create_unix,
.close = p9_fd_close,
.request = p9_fd_request,
@@ -1129,6 +1131,7 @@ static struct p9_trans_module p9_fd_trans = {
.name = "fd",
.maxsize = MAX_SOCK_BUF,
.def = 0,
+ .supports_vmalloc = true,
.create = p9_fd_create,
.close = p9_fd_close,
.request = p9_fd_request,
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
index b84748baf9cb..6c5ad232c194 100644
--- a/net/9p/trans_rdma.c
+++ b/net/9p/trans_rdma.c
@@ -749,6 +749,7 @@ static struct p9_trans_module p9_rdma_trans = {
.maxsize = P9_RDMA_MAXSIZE,
.pooled_rbuffers = true,
.def = 0,
+ .supports_vmalloc = false,
.owner = THIS_MODULE,
.create = rdma_create_trans,
.close = rdma_close,
diff --git a/net/9p/trans_usbg.c b/net/9p/trans_usbg.c
index 468f7e8f0277..2542ef099233 100644
--- a/net/9p/trans_usbg.c
+++ b/net/9p/trans_usbg.c
@@ -514,6 +514,7 @@ static struct p9_trans_module p9_usbg_trans = {
.close = p9_usbg_close,
.request = p9_usbg_request,
.cancel = p9_usbg_cancel,
+ .supports_vmalloc = false,
.owner = THIS_MODULE,
};
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 0b8086f58ad5..12806207f4f0 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -803,6 +803,7 @@ static struct p9_trans_module p9_virtio_trans = {
.maxsize = PAGE_SIZE * (VIRTQUEUE_NUM - 3),
.pooled_rbuffers = false,
.def = 1,
+ .supports_vmalloc = false,
.owner = THIS_MODULE,
};
diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c
index b9ff69c7522a..4b1cec0ab829 100644
--- a/net/9p/trans_xen.c
+++ b/net/9p/trans_xen.c
@@ -258,6 +258,7 @@ static struct p9_trans_module p9_xen_trans = {
.maxsize = 1 << (XEN_9PFS_RING_ORDER + XEN_PAGE_SHIFT - 2),
.pooled_rbuffers = false,
.def = 1,
+ .supports_vmalloc = false,
.create = p9_xen_create,
.close = p9_xen_close,
.request = p9_xen_request,
--
2.39.5 (Apple Git-154)
On Thu, Oct 16, 2025, at 15:06, Christian Schoenebeck wrote:
> On Thursday, October 16, 2025 9:01:56 AM CEST Pierre Barre wrote:
>> While developing a 9P server (https://github.com/Barre/ZeroFS) and
>> testing it under high-load, I was running into allocation failures.
>> The failures occur even with plenty of free memory available because
>> kmalloc requires contiguous physical memory.
>>
>> This results in errors like:
>> ls: page allocation failure: order:7, mode:0x40c40(GFP_NOFS|__GFP_COMP)
>>
>> This patch introduces a transport capability flag (supports_vmalloc)
>> that indicates whether a transport can work with vmalloc'd buffers
>> (non-physically contiguous memory). Transports requiring DMA should
>> leave this flag as false.
>>
>> The fd-based transports (tcp, unix, fd) set this flag to true, and
>> p9_fcall_init will use kvmalloc instead of kmalloc for these
>> transports. This allows the allocator to fall back to vmalloc when
>> contiguous physical memory is not available.
>>
>> Additionally, if kmem_cache_alloc fails, the code falls back to
>> kvmalloc for transports that support it.
>>
>> Signed-off-by: Pierre Barre <pierre@...re.sh>
>> ---
>>
>> include/net/9p/transport.h | 4 ++++
>> net/9p/client.c | 11 +++++++++--
>> net/9p/trans_fd.c | 3 +++
>> 3 files changed, 16 insertions(+), 2 deletions(-)
>>
>> diff --git a/include/net/9p/transport.h b/include/net/9p/transport.h
>> index 766ec07c9599..f0981515148d 100644
>> --- a/include/net/9p/transport.h
>> +++ b/include/net/9p/transport.h
>> @@ -24,6 +24,9 @@
>> * we're less flexible when choosing the response message
>> * size in this case
>> * @def: set if this transport should be considered the default
>> + * @supports_vmalloc: set if this transport can work with vmalloc'd buffers
>> + * (non-physically contiguous memory). Transports
>> requiring + * DMA should leave this as false.
>> * @create: member function to create a new connection on this transport
>> * @close: member function to discard a connection on this transport
>> * @request: member function to issue a request to the transport
>> @@ -44,6 +47,7 @@ struct p9_trans_module {
>> int maxsize; /* max message size of transport */
>> bool pooled_rbuffers;
>> int def; /* this transport should be default */
>> + bool supports_vmalloc; /* can work with vmalloc'd buffers */
>> struct module *owner;
>> int (*create)(struct p9_client *client,
>> const char *devname, char *args);
>> diff --git a/net/9p/client.c b/net/9p/client.c
>> index 5c1ca57ccd28..2a4884c880c1 100644
>> --- a/net/9p/client.c
>> +++ b/net/9p/client.c
>> @@ -229,8 +229,15 @@ static int p9_fcall_init(struct p9_client *c, struct
>> p9_fcall *fc, if (likely(c->fcall_cache) && alloc_msize == c->msize) {
>> fc->sdata = kmem_cache_alloc(c->fcall_cache, GFP_NOFS);
>> fc->cache = c->fcall_cache;
>> + if (!fc->sdata && c->trans_mod->supports_vmalloc) {
>> + fc->sdata = kvmalloc(alloc_msize, GFP_NOFS);
>> + fc->cache = NULL;
>> + }
>> } else {
>> - fc->sdata = kmalloc(alloc_msize, GFP_NOFS);
>> + if (c->trans_mod->supports_vmalloc)
>> + fc->sdata = kvmalloc(alloc_msize, GFP_NOFS);
>> + else
>> + fc->sdata = kmalloc(alloc_msize, GFP_NOFS);
>> fc->cache = NULL;
>> }
>> if (!fc->sdata)
>> @@ -252,7 +259,7 @@ void p9_fcall_fini(struct p9_fcall *fc)
>> if (fc->cache)
>> kmem_cache_free(fc->cache, fc->sdata);
>> else
>> - kfree(fc->sdata);
>> + kvfree(fc->sdata);
>> }
>> EXPORT_SYMBOL(p9_fcall_fini);
>>
>> diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
>> index a516745f732f..e7334033eba5 100644
>> --- a/net/9p/trans_fd.c
>> +++ b/net/9p/trans_fd.c
>> @@ -1101,6 +1101,7 @@ static struct p9_trans_module p9_tcp_trans = {
>> .maxsize = MAX_SOCK_BUF,
>> .pooled_rbuffers = false,
>> .def = 0,
>> + .supports_vmalloc = true,
>> .create = p9_fd_create_tcp,
>> .close = p9_fd_close,n
>> .request = p9_fd_request,
>> @@ -1115,6 +1116,7 @@ static struct p9_trans_module p9_unix_trans = {
>> .name = "unix",
>> .maxsize = MAX_SOCK_BUF,
>> .def = 0,
>> + .supports_vmalloc = true,
>> .create = p9_fd_create_unix,
>> .close = p9_fd_close,
>> .request = p9_fd_request,
>> @@ -1129,6 +1131,7 @@ static struct p9_trans_module p9_fd_trans = {
>> .name = "fd",
>> .maxsize = MAX_SOCK_BUF,
>> .def = 0,
>> + .supports_vmalloc = true,
>> .create = p9_fd_create,
>> .close = p9_fd_close,
>> .request = p9_fd_request,
>
> Just for clarity I would add .supports_vmalloc = false to the other
> transports. Except of that:
>
> Reviewed-by: Christian Schoenebeck <linux_oss@...debyte.com>
>
> Thanks!
>
> /Christian
Powered by blists - more mailing lists