hw/nvme: fix mmio read
PATCH 1/1 hw/nvme: fix mmio read
From: Klaus Jensen <[email protected]>
The new PMR test unearthed a long-standing issue with MMIO reads on big-endian hosts.
Fix by using the ldn_he_p helper instead of memcpy.
--- hw/nvme/ctrl.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-)
hw/nvme/ctrl.c +7 -7
@@ -5951,7 +5951,6 @@ static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size) {NvmeCtrl *n = (NvmeCtrl *)opaque;uint8_t *ptr = (uint8_t *)&n->bar; -uint64_t val =0 ;trace_pci_nvme_mmio_read (addr, size);
@@ -5977,14 +5976,15 @@ static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size) (NVME_PMRCAP_PMRWBM(n->bar.pmrcap) & 0x02)) {memory_region_msync (&n->pmr.dev->mr,0 , n->pmr.dev->size); } -memcpy (&val, ptr + addr, size); - }else { -NVME_GUEST_ERR (pci_nvme_ub_mmiord_invalid_ofs, -"MMIO read beyond last register," -" offset=0x%" PRIx64", returning 0" , addr); + +return ldn_he_p (ptr + addr, size); } -return val; +NVME_GUEST_ERR (pci_nvme_ub_mmiord_invalid_ofs, +"MMIO read beyond last register," +" offset=0x%" PRIx64", returning 0" , addr); + +return 0 ; }static void nvme_process_db (NvmeCtrl *n,hwaddr addr,int val)
Signature · 1 line
2.32.0
Quoted 52 lines · Klaus Jensen
From: Klaus Jensen <[email protected]>
The new PMR test unearthed a long-standing issue with MMIO reads on big-endian hosts.
Fix by using the
ldn_he_phelper instead of memcpy.Cc Gollu Appalanaidu <[email protected]>Reported-by Peter Maydell <[email protected]>Signed-off-by Klaus Jensen <[email protected]>---
hw/nvme/ctrl.c| 14 +++++++-------1 file changed, 7 insertions(+), 7 deletions(-)hw/nvme/ctrl.c +7
-7@@ -5951,7 +5951,6 @@ static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size) {NvmeCtrl *n = (NvmeCtrl *)opaque;uint8_t *ptr = (uint8_t *)&n->bar; -uint64_t val =0 ;trace_pci_nvme_mmio_read (addr, size);@@ -5977,14 +5976,15 @@ static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size) (NVME_PMRCAP_PMRWBM(n->bar.pmrcap) & 0x02)) {memory_region_msync (&n->pmr.dev->mr,0 , n->pmr.dev->size); } -memcpy (&val, ptr + addr, size); - }else { -NVME_GUEST_ERR (pci_nvme_ub_mmiord_invalid_ofs, -"MMIO read beyond last register," -" offset=0x%" PRIx64", returning 0" , addr); + +return ldn_he_p (ptr + addr, size); } -return val; +NVME_GUEST_ERR (pci_nvme_ub_mmiord_invalid_ofs, +"MMIO read beyond last register," +" offset=0x%" PRIx64", returning 0" , addr); + +return 0 ; }static void nvme_process_db (NvmeCtrl *n,hwaddr addr,int val)Signature · 1 line
2.32.0
LGTM.
Quoted 28 lines · Klaus Jensen
From: Klaus Jensen <[email protected]>
The new PMR test unearthed a long-standing issue with MMIO reads on big-endian hosts.
Fix by using the
ldn_he_phelper instead of memcpy.Cc Gollu Appalanaidu <[email protected]>Reported-by Peter Maydell <[email protected]>Signed-off-by Klaus Jensen <[email protected]>--- hw/nvme/ctrl.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-)hw/nvme/ctrl.c +0
-1@@ -5951,7 +5951,6 @@ static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size) {NvmeCtrl *n = (NvmeCtrl *)opaque;uint8_t *ptr = (uint8_t *)&n->bar; -uint64_t val =0 ;trace_pci_nvme_mmio_read (addr, size);
hw/nvme/ctrl.c static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size) · line 5980
Quoted 10 lines
hw/nvme/ctrl.c +2
-5@@ -5977,14 +5976,15 @@ static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size) (NVME_PMRCAP_PMRWBM(n->bar.pmrcap) & 0x02)) {memory_region_msync (&n->pmr.dev->mr,0 , n->pmr.dev->size); } -memcpy (&val, ptr + addr, size); - }else { -NVME_GUEST_ERR (pci_nvme_ub_mmiord_invalid_ofs, -"MMIO read beyond last register," -" offset=0x%" PRIx64", returning 0" , addr); + +return ldn_he_p (ptr + addr, size);
I don't think this will do the right thing for accesses which aren't of the same width as whatever the field in NvmeBar is defined as. For instance, if the guest does a 32-bit access to offset 0, because the first field is defined as 'uint64_t cap', on a big-endian host they will end up reading the high 4 bytes of the 64-bit value, and on a little-endian host they will get the low 4 bytes.
hw/nvme/ctrl.c static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size) · line 5988
Quoted 9 lines
hw/nvme/ctrl.c +5
-1} -return val; +NVME_GUEST_ERR (pci_nvme_ub_mmiord_invalid_ofs, +"MMIO read beyond last register," +" offset=0x%" PRIx64", returning 0" , addr); + +return 0 ; }
Looking at the surrounding code, I notice that we guard this "read size bytes from &n->bar + addr" with
if (addr < sizeof(n->bar)) {but that doesn't account for 'size', so if the guest asks to read 4 bytes starting at offset sizeof(n->bar)-1 then we'll still read 3 bytes beyond the end of the buffer...
thanks
-- PMM
Quoted 38 lines · Peter Maydell
Quoted 37 lines · Klaus Jensen
From: Klaus Jensen <[email protected]>
The new PMR test unearthed a long-standing issue with MMIO reads on big-endian hosts.
Fix by using the
ldn_he_phelper instead of memcpy.Cc Gollu Appalanaidu <[email protected]>Reported-by Peter Maydell <[email protected]>Signed-off-by Klaus Jensen <[email protected]>--- hw/nvme/ctrl.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-)hw/nvme/ctrl.c +1
-6@@ -5951,7 +5951,6 @@ static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size) {NvmeCtrl *n = (NvmeCtrl *)opaque;uint8_t *ptr = (uint8_t *)&n->bar; -uint64_t val =0 ;trace_pci_nvme_mmio_read (addr, size);@@ -5977,14 +5976,15 @@ static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size) (NVME_PMRCAP_PMRWBM(n->bar.pmrcap) & 0x02)) {memory_region_msync (&n->pmr.dev->mr,0 , n->pmr.dev->size); } -memcpy (&val, ptr + addr, size); - }else { -NVME_GUEST_ERR (pci_nvme_ub_mmiord_invalid_ofs, -"MMIO read beyond last register," -" offset=0x%" PRIx64", returning 0" , addr); +
Quoted 9 lines
hw/nvme/ctrl.c static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size) · line 5980
Quoted 1 line
hw/nvme/ctrl.c +1
-0+return ldn_he_p (ptr + addr, size);I don't think this will do the right thing for accesses which aren't of the same width as whatever the field in NvmeBar is defined as. For instance, if the guest does a 32-bit access to offset 0, because the first field is defined as '
uint64_tcap', on a big-endian host they will end up reading the high 4 bytes of the 64-bit value, and on a little-endian host they will get the low 4 bytes.
Thanks for taking a look Peter, I wondered if I actually fixed it correctly or not, and I obviously didnt.
I guess I can't get around handling 64 bit registers explicitly and convert them to little endian explicitly then.
Quoted 10 lines
hw/nvme/ctrl.c static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size) · line 5988
Quoted 9 lines
hw/nvme/ctrl.c +5
-1} -return val; +NVME_GUEST_ERR (pci_nvme_ub_mmiord_invalid_ofs, +"MMIO read beyond last register," +" offset=0x%" PRIx64", returning 0" , addr); + +return 0 ; }
Quoted 7 lines
Looking at the surrounding code, I notice that we guard this "read size bytes from
&n->bar+ addr" withif (addr < sizeof(n->bar)) {but that doesn't account for 'size', so if the guest asks to read 4 bytes starting at offset sizeof(n->bar)-1 then we'll still read 3 bytes beyond the end of the buffer...
The buffer is at least sizeof(n->bar) + 8 bytes (there are two doorbell registers following the controller registers). It is wrong for the host to read those, but as per the spec it is undefined behavior. I did consider reversing the condition to (addr > sizeof(n->bar) - size). I guess that would be the proper thing to do.
Quoted 6 lines · Klaus Jensen
Quoted 4 lines · Peter Maydell
Looking at the surrounding code, I notice that we guard this "read size bytes from
&n->bar+ addr" withif (addr < sizeof(n->bar)) {
Quoted 7 lines
Quoted 3 lines
but that doesn't account for 'size', so if the guest asks to read 4 bytes starting at offset sizeof(n->bar)-1 then we'll still read 3 bytes beyond the end of the buffer...
The buffer is at least
sizeof(n->bar)+ 8 bytes (there are two doorbell registers following the controller registers). It is wrong for the host to read those, but as per the spec it is undefined behavior.
I don't know about the doorbell registers, but with this code (or the old memcpy()) you'll access whatever the next thing after "NvmeBar bar" in the NvmeCtrl struct is, which looks like it's the first part of 'struct NvmeParams".
thanks
-- PMM
Quoted 11 lines · Peter Maydell
Quoted 10 lines · Klaus Jensen
Quoted 7 lines · Peter Maydell
Looking at the surrounding code, I notice that we guard this "read size bytes from
&n->bar+ addr" withif (addr < sizeof(n->bar)) {but that doesn't account for 'size', so if the guest asks to read 4 bytes starting at offset sizeof(n->bar)-1 then we'll still read 3 bytes beyond the end of the buffer...
Quoted 9 lines
Quoted 3 lines
The buffer is at least
sizeof(n->bar)+ 8 bytes (there are two doorbell registers following the controller registers). It is wrong for the host to read those, but as per the spec it is undefined behavior.I don't know about the doorbell registers, but with this code (or the old
memcpy()) you'll access whatever the next thing after "NvmeBar bar" in the NvmeCtrl struct is, which looks like it's the first part of 'struct NvmeParams".
Sorry, you are of course right. I remembered how the bar was allocated incorrectly.
Quoted 16 lines · Klaus Jensen
Quoted 15 lines · Peter Maydell
Quoted 13 lines · Klaus Jensen
Quoted 7 lines · Peter Maydell
Looking at the surrounding code, I notice that we guard this "read size bytes from
&n->bar+ addr" withif (addr < sizeof(n->bar)) {but that doesn't account for 'size', so if the guest asks to read 4 bytes starting at offset sizeof(n->bar)-1 then we'll still read 3 bytes beyond the end of the buffer...
The buffer is at least
sizeof(n->bar)+ 8 bytes (there are two doorbell registers following the controller registers). It is wrong for the host to read those, but as per the spec it is undefined behavior.
Quoted 8 lines
Quoted 5 lines
I don't know about the doorbell registers, but with this code (or the old
memcpy()) you'll access whatever the next thing after "NvmeBar bar" in the NvmeCtrl struct is, which looks like it's the first part of 'struct NvmeParams".Sorry, you are of course right. I remembered how the bar was allocated incorrectly.
I fixed this properly by holding all bar values in little endian as per the spec.
I'll clean it up and send it tonight.