Linux Virtualization - May 2019 - [RFC PATCH V2] vhost: don't use kmap() to log dirty pages

Vhost log dirty pages directly to a userspace bitmap through GUP and
kmap_atomic() since kernel doesn't have a set_bit_to_user()
helper. This will cause issues for the arch that has virtually tagged
caches. The way to fix is to keep using userspace virtual
address. Fortunately, futex has arch_futex_atomic_op_inuser() which
could be used for setting a bit to user.

Note:
- There're archs (few non popular ones) that don't implement futex
  helper, we can't log dirty pages. We can fix them e.g for non
  virtually tagged archs implement a kmap fallback on top or simply
  disable LOG_ALL features of vhost.
- The helper also requires userspace pointer is located at 4-byte
  boundary, need to check during dirty log setting

Cc: Christoph Hellwig <hch at infradead.org>
Cc: James Bottomley <James.Bottomley at HansenPartnership.com>
Cc: Andrea Arcangeli <aarcange at redhat.com>
Cc: Thomas Gleixner <tglx at linutronix.de>
Cc: Ingo Molnar <mingo at redhat.com>
Cc: Peter Zijlstra <peterz at infradead.org>
Cc: Darren Hart <dvhart at infradead.org>
Fixes: 3a4d5c94e9593 ("vhost_net: a kernel-level virtio server")
Signed-off-by: Jason Wang <jasowang at redhat.com>
---
Changes from V1:
- switch to use arch_futex_atomic_op_inuser()
---
 drivers/vhost/vhost.c | 35 +++++++++++++++++------------------
 1 file changed, 17 insertions(+), 18 deletions(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 351af88..4e5a004 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -31,6 +31,7 @@
 #include <linux/sched/signal.h>
 #include <linux/interval_tree_generic.h>
 #include <linux/nospec.h>
+#include <asm/futex.h>
 
 #include "vhost.h"
 
@@ -1652,6 +1653,10 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int
ioctl, void __user *argp)
 			r = -EFAULT;
 			break;
 		}
+		if (p & 0x3) {
+			r = -EINVAL;
+			break;
+		}
 		for (i = 0; i < d->nvqs; ++i) {
 			struct vhost_virtqueue *vq;
 			void __user *base = (void __user *)(unsigned long)p;
@@ -1692,31 +1697,27 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int
ioctl, void __user *argp)
 }
 EXPORT_SYMBOL_GPL(vhost_dev_ioctl);
 
-/* TODO: This is really inefficient.  We need something like get_user()
- * (instruction directly accesses the data, with an exception table entry
- * returning -EFAULT). See Documentation/x86/exception-tables.txt.
- */
-static int set_bit_to_user(int nr, void __user *addr)
+static int set_bit_to_user(int nr, u32 __user *addr)
 {
 	unsigned long log = (unsigned long)addr;
 	struct page *page;
-	void *base;
-	int bit = nr + (log % PAGE_SIZE) * 8;
+	u32 old;
 	int r;
 
 	r = get_user_pages_fast(log, 1, 1, &page);
 	if (r < 0)
 		return r;
 	BUG_ON(r != 1);
-	base = kmap_atomic(page);
-	set_bit(bit, base);
-	kunmap_atomic(base);
+
+	r = arch_futex_atomic_op_inuser(FUTEX_OP_ADD, 1 << nr, &old, addr);
+	/* TODO: fallback to kmap() when -ENOSYS? */
+
 	set_page_dirty_lock(page);
 	put_page(page);
-	return 0;
+	return r;
 }
 
-static int log_write(void __user *log_base,
+static int log_write(u32 __user *log_base,
 		     u64 write_address, u64 write_length)
 {
 	u64 write_page = write_address / VHOST_PAGE_SIZE;
@@ -1726,12 +1727,10 @@ static int log_write(void __user *log_base,
 		return 0;
 	write_length += write_address % VHOST_PAGE_SIZE;
 	for (;;) {
-		u64 base = (u64)(unsigned long)log_base;
-		u64 log = base + write_page / 8;
-		int bit = write_page % 8;
-		if ((u64)(unsigned long)log != log)
-			return -EFAULT;
-		r = set_bit_to_user(bit, (void __user *)(unsigned long)log);
+		u32 __user *log = log_base + write_page / 32;
+		int bit = write_page % 32;
+
+		r = set_bit_to_user(bit, log);
 		if (r < 0)
 			return r;
 		if (write_length <= VHOST_PAGE_SIZE)
-- 
1.8.3.1

On Thu, May 09, 2019 at 08:58:00AM -0400, Jason Wang
wrote:
> Vhost log dirty pages directly to a userspace bitmap through GUP and
> kmap_atomic() since kernel doesn't have a set_bit_to_user()
> helper. This will cause issues for the arch that has virtually tagged
> caches. The way to fix is to keep using userspace virtual
> address. Fortunately, futex has arch_futex_atomic_op_inuser() which
> could be used for setting a bit to user.
> 
> Note:
> - There're archs (few non popular ones) that don't implement futex
>   helper, we can't log dirty pages. We can fix them e.g for non
>   virtually tagged archs implement a kmap fallback on top or simply
>   disable LOG_ALL features of vhost.
> - The helper also requires userspace pointer is located at 4-byte
>   boundary, need to check during dirty log setting
Why check? Round it down.
> Cc: Christoph Hellwig <hch at infradead.org>
> Cc: James Bottomley <James.Bottomley at HansenPartnership.com>
> Cc: Andrea Arcangeli <aarcange at redhat.com>
> Cc: Thomas Gleixner <tglx at linutronix.de>
> Cc: Ingo Molnar <mingo at redhat.com>
> Cc: Peter Zijlstra <peterz at infradead.org>
> Cc: Darren Hart <dvhart at infradead.org>
> Fixes: 3a4d5c94e9593 ("vhost_net: a kernel-level virtio server")
> Signed-off-by: Jason Wang <jasowang at redhat.com>
> ---
> Changes from V1:
> - switch to use arch_futex_atomic_op_inuser()
> ---
>  drivers/vhost/vhost.c | 35 +++++++++++++++++------------------
>  1 file changed, 17 insertions(+), 18 deletions(-)
> 
> diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
> index 351af88..4e5a004 100644
> --- a/drivers/vhost/vhost.c
> +++ b/drivers/vhost/vhost.c
> @@ -31,6 +31,7 @@
>  #include <linux/sched/signal.h>
>  #include <linux/interval_tree_generic.h>
>  #include <linux/nospec.h>
> +#include <asm/futex.h>
>  
>  #include "vhost.h"
>  
> @@ -1652,6 +1653,10 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned
int ioctl, void __user *argp)
>  			r = -EFAULT;
>  			break;
>  		}
> +		if (p & 0x3) {
> +			r = -EINVAL;
> +			break;
> +		}
>  		for (i = 0; i < d->nvqs; ++i) {
>  			struct vhost_virtqueue *vq;
>  			void __user *base = (void __user *)(unsigned long)p;
That's an ABI change and might break some userspace. I don't think
it's necessary: you are changing individual bits anyway.
> @@ -1692,31 +1697,27 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned
int ioctl, void __user *argp)
>  }
>  EXPORT_SYMBOL_GPL(vhost_dev_ioctl);
>  
> -/* TODO: This is really inefficient.  We need something like get_user()
> - * (instruction directly accesses the data, with an exception table entry
> - * returning -EFAULT). See Documentation/x86/exception-tables.txt.
> - */
> -static int set_bit_to_user(int nr, void __user *addr)
> +static int set_bit_to_user(int nr, u32 __user *addr)
>  {
>  	unsigned long log = (unsigned long)addr;
>  	struct page *page;
> -	void *base;
> -	int bit = nr + (log % PAGE_SIZE) * 8;
> +	u32 old;
>  	int r;
>  
>  	r = get_user_pages_fast(log, 1, 1, &page);
OK so the trick is that page is pinned so you don't expect
arch_futex_atomic_op_inuser below to fail.  get_user_pages_fast
guarantees page is not going away but does it guarantee PTE won't be
invaidated or write protected?
>  	if (r < 0)
>  		return r;
>  	BUG_ON(r != 1);
> -	base = kmap_atomic(page);
> -	set_bit(bit, base);
> -	kunmap_atomic(base);
> +
> +	r = arch_futex_atomic_op_inuser(FUTEX_OP_ADD, 1 << nr, &old,
addr);
> +	/* TODO: fallback to kmap() when -ENOSYS? */
> +
Add a comment why this won't fail? Maybe warn on EFAULT?

Also down the road a variant that does not need tricks like this is
still nice to have.

>  	set_page_dirty_lock(page);
>  	put_page(page);
> -	return 0;
> +	return r;
>  }
>  
> -static int log_write(void __user *log_base,
> +static int log_write(u32 __user *log_base,
>  		     u64 write_address, u64 write_length)
>  {
>  	u64 write_page = write_address / VHOST_PAGE_SIZE;
> @@ -1726,12 +1727,10 @@ static int log_write(void __user *log_base,
>  		return 0;
>  	write_length += write_address % VHOST_PAGE_SIZE;
>  	for (;;) {
> -		u64 base = (u64)(unsigned long)log_base;
> -		u64 log = base + write_page / 8;
> -		int bit = write_page % 8;
> -		if ((u64)(unsigned long)log != log)
> -			return -EFAULT;
> -		r = set_bit_to_user(bit, (void __user *)(unsigned long)log);
> +		u32 __user *log = log_base + write_page / 32;
> +		int bit = write_page % 32;
> +
> +		r = set_bit_to_user(bit, log);
>  		if (r < 0)
>  			return r;
>  		if (write_length <= VHOST_PAGE_SIZE)
> -- 
> 1.8.3.1

On 2019/5/9 ??9:18, Michael S. Tsirkin wrote:
> On Thu, May 09, 2019 at 08:58:00AM -0400, Jason Wang wrote:
>> Vhost log dirty pages directly to a userspace bitmap through GUP and
>> kmap_atomic() since kernel doesn't have a set_bit_to_user()
>> helper. This will cause issues for the arch that has virtually tagged
>> caches. The way to fix is to keep using userspace virtual
>> address. Fortunately, futex has arch_futex_atomic_op_inuser() which
>> could be used for setting a bit to user.
>>
>> Note:
>> - There're archs (few non popular ones) that don't implement
futex
>>    helper, we can't log dirty pages. We can fix them e.g for non
>>    virtually tagged archs implement a kmap fallback on top or simply
>>    disable LOG_ALL features of vhost.
>> - The helper also requires userspace pointer is located at 4-byte
>>    boundary, need to check during dirty log setting
> Why check? Round it down.

Will do this.

>
>> Cc: Christoph Hellwig <hch at infradead.org>
>> Cc: James Bottomley <James.Bottomley at HansenPartnership.com>
>> Cc: Andrea Arcangeli <aarcange at redhat.com>
>> Cc: Thomas Gleixner <tglx at linutronix.de>
>> Cc: Ingo Molnar <mingo at redhat.com>
>> Cc: Peter Zijlstra <peterz at infradead.org>
>> Cc: Darren Hart <dvhart at infradead.org>
>> Fixes: 3a4d5c94e9593 ("vhost_net: a kernel-level virtio
server")
>> Signed-off-by: Jason Wang <jasowang at redhat.com>
>> ---
>> Changes from V1:
>> - switch to use arch_futex_atomic_op_inuser()
>> ---
>>   drivers/vhost/vhost.c | 35 +++++++++++++++++------------------
>>   1 file changed, 17 insertions(+), 18 deletions(-)
>>
>> diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
>> index 351af88..4e5a004 100644
>> --- a/drivers/vhost/vhost.c
>> +++ b/drivers/vhost/vhost.c
>> @@ -31,6 +31,7 @@
>>   #include <linux/sched/signal.h>
>>   #include <linux/interval_tree_generic.h>
>>   #include <linux/nospec.h>
>> +#include <asm/futex.h>
>>   
>>   #include "vhost.h"
>>   
>> @@ -1652,6 +1653,10 @@ long vhost_dev_ioctl(struct vhost_dev *d,
unsigned int ioctl, void __user *argp)
>>   			r = -EFAULT;
>>   			break;
>>   		}
>> +		if (p & 0x3) {
>> +			r = -EINVAL;
>> +			break;
>> +		}
>>   		for (i = 0; i < d->nvqs; ++i) {
>>   			struct vhost_virtqueue *vq;
>>   			void __user *base = (void __user *)(unsigned long)p;
> That's an ABI change and might break some userspace. I don't think
> it's necessary: you are changing individual bits anyway.

Right.

>
>> @@ -1692,31 +1697,27 @@ long vhost_dev_ioctl(struct vhost_dev *d,
unsigned int ioctl, void __user *argp)
>>   }
>>   EXPORT_SYMBOL_GPL(vhost_dev_ioctl);
>>   
>> -/* TODO: This is really inefficient.  We need something like
get_user()
>> - * (instruction directly accesses the data, with an exception table
entry
>> - * returning -EFAULT). See Documentation/x86/exception-tables.txt.
>> - */
>> -static int set_bit_to_user(int nr, void __user *addr)
>> +static int set_bit_to_user(int nr, u32 __user *addr)
>>   {
>>   	unsigned long log = (unsigned long)addr;
>>   	struct page *page;
>> -	void *base;
>> -	int bit = nr + (log % PAGE_SIZE) * 8;
>> +	u32 old;
>>   	int r;
>>   
>>   	r = get_user_pages_fast(log, 1, 1, &page);
> OK so the trick is that page is pinned so you don't expect
> arch_futex_atomic_op_inuser below to fail.  get_user_pages_fast
> guarantees page is not going away but does it guarantee PTE won't be
> invaidated or write protected?

Good point, then I think we probably need to do manual fixup through 
fixup_user_fault() if arch_futex_atomic_op_in_user() fail.

>
>>   	if (r < 0)
>>   		return r;
>>   	BUG_ON(r != 1);
>> -	base = kmap_atomic(page);
>> -	set_bit(bit, base);
>> -	kunmap_atomic(base);
>> +
>> +	r = arch_futex_atomic_op_inuser(FUTEX_OP_ADD, 1 << nr,
&old, addr);
>> +	/* TODO: fallback to kmap() when -ENOSYS? */
>> +
> Add a comment why this won't fail? Maybe warn on EFAULT?
>
> Also down the road a variant that does not need tricks like this is
> still nice to have.

Ok. Let me post a V3.

Thanks

>
>
>>   	set_page_dirty_lock(page);
>>   	put_page(page);
>> -	return 0;
>> +	return r;
>>   }
>>   
>> -static int log_write(void __user *log_base,
>> +static int log_write(u32 __user *log_base,
>>   		     u64 write_address, u64 write_length)
>>   {
>>   	u64 write_page = write_address / VHOST_PAGE_SIZE;
>> @@ -1726,12 +1727,10 @@ static int log_write(void __user *log_base,
>>   		return 0;
>>   	write_length += write_address % VHOST_PAGE_SIZE;
>>   	for (;;) {
>> -		u64 base = (u64)(unsigned long)log_base;
>> -		u64 log = base + write_page / 8;
>> -		int bit = write_page % 8;
>> -		if ((u64)(unsigned long)log != log)
>> -			return -EFAULT;
>> -		r = set_bit_to_user(bit, (void __user *)(unsigned long)log);
>> +		u32 __user *log = log_base + write_page / 32;
>> +		int bit = write_page % 32;
>> +
>> +		r = set_bit_to_user(bit, log);
>>   		if (r < 0)
>>   			return r;
>>   		if (write_length <= VHOST_PAGE_SIZE)
>> -- 
>> 1.8.3.1