[PATCH v3] x86/sev: Unroll string mmio with CC_ATTR_GUEST_UNROLL_STRING_IO

[PATCH v3] x86/sev: Unroll string mmio with CC_ATTR_GUEST_UNROLL_STRING_IO

[Joerg Roedel]

From: Joerg Roedel <jroedel@suse.de>

The io specific memcpy/memset functions use string mmio accesses to do
their work. Under SEV the hypervisor can't emulate these instructions,
because they read/write directly from/to encrypted memory.

KVM will inject a page fault exception into the guest when it is asked
to emulate string mmio instructions for an SEV guest:

	BUG: unable to handle page fault for address: ffffc90000065068
	#PF: supervisor read access in kernel mode
	#PF: error_code(0x0000) - not-present page
	PGD 8000100000067 P4D 8000100000067 PUD 80001000fb067 PMD 80001000fc067 PTE 80000000fed40173
	Oops: 0000 [#1] PREEMPT SMP NOPTI
	CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.17.0-rc7 #3

As string mmio for an SEV guest can not be supported by the
hypervisor, unroll the instructions for CC_ATTR_GUEST_UNROLL_STRING_IO
enabled kernels.

This issue appears when kernels are launched in recent libvirt-managed
SEV virtual machines, because libvirt started to add a tpm-crb device
to the guest by default.

The kernel driver for tpm-crb uses memcpy_to/from_io() functions to
access MMIO memory, resulting in a page-fault injected by KVM and
crashing the kernel at boot.

Cc: stable@vger.kernel.org #4.15+
Fixes: d8aa7eea78a1 ('x86/mm: Add Secure Encrypted Virtualization (SEV) support')
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
Changes v2->v3:
	- Fix sparse warnings introduced by v2

 arch/x86/lib/iomem.c | 65 ++++++++++++++++++++++++++++++++++++++------
 1 file changed, 57 insertions(+), 8 deletions(-)

diff --git a/arch/x86/lib/iomem.c b/arch/x86/lib/iomem.c
index df50451d94ef..3e2f33fc33de 100644
--- a/arch/x86/lib/iomem.c
+++ b/arch/x86/lib/iomem.c
@@ -22,7 +22,7 @@ static __always_inline void rep_movs(void *to, const void *from, size_t n)
 		     : "memory");
 }
 
-void memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
+static void string_memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
 {
 	if (unlikely(!n))
 		return;
@@ -38,9 +38,8 @@ void memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
 	}
 	rep_movs(to, (const void *)from, n);
 }
-EXPORT_SYMBOL(memcpy_fromio);
 
-void memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
+static void string_memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
 {
 	if (unlikely(!n))
 		return;
@@ -56,14 +55,64 @@ void memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
 	}
 	rep_movs((void *)to, (const void *) from, n);
 }
+
+static void unrolled_memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
+{
+	const volatile char __iomem *in = from;
+	char *out = to;
+	int i;
+
+	for (i = 0; i < n; ++i)
+		out[i] = readb(&in[i]);
+}
+
+static void unrolled_memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
+{
+	volatile char __iomem *out = to;
+	const char *in = from;
+	int i;
+
+	for (i = 0; i < n; ++i)
+		writeb(in[i], &out[i]);
+}
+
+static void unrolled_memset_io(volatile void __iomem *a, int b, size_t c)
+{
+	volatile char __iomem *mem = a;
+	int i;
+
+	for (i = 0; i < c; ++i)
+		writeb(b, &mem[i]);
+}
+
+void memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
+{
+	if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO))
+		unrolled_memcpy_fromio(to, from, n);
+	else
+		string_memcpy_fromio(to, from, n);
+}
+EXPORT_SYMBOL(memcpy_fromio);
+
+void memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
+{
+	if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO))
+		unrolled_memcpy_toio(to, from, n);
+	else
+		string_memcpy_toio(to, from, n);
+}
 EXPORT_SYMBOL(memcpy_toio);
 
 void memset_io(volatile void __iomem *a, int b, size_t c)
 {
-	/*
-	 * TODO: memset can mangle the IO patterns quite a bit.
-	 * perhaps it would be better to use a dumb one:
-	 */
-	memset((void *)a, b, c);
+	if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) {
+		unrolled_memset_io(a, b, c);
+	} else {
+		/*
+		 * TODO: memset can mangle the IO patterns quite a bit.
+		 * perhaps it would be better to use a dumb one:
+		 */
+		memset((void *)a, b, c);
+	}
 }
 EXPORT_SYMBOL(memset_io);
-- 
2.35.1

RE: [PATCH v3] x86/sev: Unroll string mmio with CC_ATTR_GUEST_UNROLL_STRING_IO

[David Laight]

From: Joerg Roedel <joro@8bytes.org>
> Sent: 26 March 2022 14:41
> 
> The io specific memcpy/memset functions use string mmio accesses to do
> their work. Under SEV the hypervisor can't emulate these instructions,
> because they read/write directly from/to encrypted memory.
> 
> KVM will inject a page fault exception into the guest when it is asked
> to emulate string mmio instructions for an SEV guest:
> 
> 	BUG: unable to handle page fault for address: ffffc90000065068
> 	#PF: supervisor read access in kernel mode
> 	#PF: error_code(0x0000) - not-present page
> 	PGD 8000100000067 P4D 8000100000067 PUD 80001000fb067 PMD 80001000fc067 PTE 80000000fed40173
> 	Oops: 0000 [#1] PREEMPT SMP NOPTI
> 	CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.17.0-rc7 #3
> 
> As string mmio for an SEV guest can not be supported by the
> hypervisor, unroll the instructions for CC_ATTR_GUEST_UNROLL_STRING_IO
> enabled kernels.
> 
> This issue appears when kernels are launched in recent libvirt-managed
> SEV virtual machines, because libvirt started to add a tpm-crb device
> to the guest by default.
> 
> The kernel driver for tpm-crb uses memcpy_to/from_io() functions to
> access MMIO memory, resulting in a page-fault injected by KVM and
> crashing the kernel at boot.
> 
> Cc: stable@vger.kernel.org #4.15+
> Fixes: d8aa7eea78a1 ('x86/mm: Add Secure Encrypted Virtualization (SEV) support')
> Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
> Signed-off-by: Joerg Roedel <jroedel@suse.de>
> ---
> Changes v2->v3:
> 	- Fix sparse warnings introduced by v2
> 
>  arch/x86/lib/iomem.c | 65 ++++++++++++++++++++++++++++++++++++++------
>  1 file changed, 57 insertions(+), 8 deletions(-)
> 
> diff --git a/arch/x86/lib/iomem.c b/arch/x86/lib/iomem.c
> index df50451d94ef..3e2f33fc33de 100644
> --- a/arch/x86/lib/iomem.c
> +++ b/arch/x86/lib/iomem.c
> @@ -22,7 +22,7 @@ static __always_inline void rep_movs(void *to, const void *from, size_t n)
>  		     : "memory");
>  }
> 
> -void memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
> +static void string_memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
>  {
>  	if (unlikely(!n))
>  		return;
> @@ -38,9 +38,8 @@ void memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
>  	}
>  	rep_movs(to, (const void *)from, n);
>  }
> -EXPORT_SYMBOL(memcpy_fromio);
> 
> -void memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
> +static void string_memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
>  {
>  	if (unlikely(!n))
>  		return;
> @@ -56,14 +55,64 @@ void memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
>  	}
>  	rep_movs((void *)to, (const void *) from, n);
>  }
> +
> +static void unrolled_memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
> +{
> +	const volatile char __iomem *in = from;
> +	char *out = to;
> +	int i;
> +
> +	for (i = 0; i < n; ++i)
> +		out[i] = readb(&in[i]);
> +}

Wait a minute....
Aren't these functions supposed to be doing 'memory' copies?
In which case they need to be using 64bit IO accesses where
appropriate - otherwise the performance is horrid.

I thought the x86 memcpy_to/from_io() had been changed to
always use a software loop rather than using whatever memcpy()
ended up using.
In particular the 'rep movsb' ERMS (EMRS?) copy that is fast
(on some cpu) for memory-memory copies is always a byte copy
on uncached locations typical for io addresses.

PIO reads from PCIe can be spectacularly slow.
You really do want to use the largest register available.

	David

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)