block/nvme: Align block pages queue to host page size
cover block/nvme: Align block pages queue to host page size
The most important patch of this series is 'Align block pages queue to host page size', it start fixing an issue on PowerPC hosts. It is not sufficient, but the rest is VFIO specific, so I prefer to send it separately.
The other patches are documentation I was writing down while looking at the code.
The last patch is about the emulated device and writeback. Marked as RFC as I don't understand writeback/dirty_log_mask yet.
Philippe Mathieu-Daudé (6):
qemu/osdep: Document qemu_memalign() and friends qemu/bitmap: Document bitmap_new() returned pointer sysemu/block-backend: Document blk_read()/blk_pwrite() block/block: Document BlockSizes fields block/nvme: Align block pages queue to host page size hw/block/nvme: Make device target agnostic
include/block/block.h | 8 ++++++-- include/qemu/bitmap.h | 2 ++ include/qemu/osdep.h | 3 +++ include/sysemu/block-backend.h | 26 ++++++++++++++++++++++++++ block/nvme.c | 2 +- hw/block/nvme.c | 4 +--- hw/block/Makefile.objs | 2 +- 7 files changed, 40 insertions(+), 7 deletions(-)
Signature · 1 line
2.21.3
PATCH 1/6 qemu/osdep: Document qemu_memalign() and friends
Document allocator functions that require a specific de-allocator call.
--- include/block/block.h | 4 ++++ include/qemu/osdep.h | 3 +++ include/sysemu/block-backend.h | 2 ++ 3 files changed, 9 insertions(+)
include/block/block.h +4 -0
@@ -526,9 +526,13 @@ void bdrv_img_create(const char *filename, const char *fmt,size_t bdrv_min_mem_align (BlockDriverState *bs);/* Returns optimal alignment in bytes for bounce buffer */ size_t bdrv_opt_mem_align (BlockDriverState *bs); +/* callers must free the returned pointer with qemu_vfree() */ void *qemu_blockalign (BlockDriverState *bs,size_t size); +/* callers must free the returned pointer with qemu_vfree() */ void *qemu_blockalign0 (BlockDriverState *bs,size_t size); +/* callers must free the returned pointer with qemu_vfree() */ void *qemu_try_blockalign (BlockDriverState *bs,size_t size); +/* callers must free the returned pointer with qemu_vfree() */ void *qemu_try_blockalign0 (BlockDriverState *bs,size_t size);bool bdrv_qiov_is_aligned (BlockDriverState *bs,QEMUIOVector *qiov);
include/qemu/osdep.h +3 -0
@@ -294,8 +294,11 @@ extern int daemon(int, int);#endif int qemu_daemon (int nochdir,int noclose); +/* callers must free the returned pointer with qemu_vfree() */ void *qemu_try_memalign (size_t alignment,size_t size); +/* callers must free the returned pointer with qemu_vfree() */ void *qemu_memalign (size_t alignment,size_t size); +/* callers must free the returned pointer with qemu_anon_ram_free() */ void *qemu_anon_ram_alloc (size_t size,uint64_t *align,bool shared);void qemu_vfree (void *ptr);void qemu_anon_ram_free (void *ptr,size_t size);
include/sysemu/block-backend.h +2 -0
@@ -203,7 +203,9 @@ uint32_t blk_get_request_alignment(BlockBackend *blk);uint32_t blk_get_max_transfer (BlockBackend *blk);int blk_get_max_iov (BlockBackend *blk);void blk_set_guest_block_size (BlockBackend *blk,int align); +/* callers must free the returned pointer with qemu_vfree() */ void *blk_try_blockalign (BlockBackend *blk,size_t size); +/* callers must free the returned pointer with qemu_vfree() */ void *blk_blockalign (BlockBackend *blk,size_t size);bool blk_op_is_blocked (BlockBackend *blk,BlockOpType op,Error **errp);void blk_op_unblock (BlockBackend *blk,BlockOpType op,Error *reason);
Signature · 1 line
2.21.3
Re: [PATCH 1/6] qemu/osdep: Document qemu_memalign() and friends
Quoted 9 lines · Philippe Mathieu-Daudé
Document allocator functions that require a specific de-allocator call.
Signed-off-by Philippe Mathieu-Daudé <[email protected]>--- include/block/block.h | 4 ++++ include/qemu/osdep.h | 3 +++ include/sysemu/block-backend.h | 2 ++ 3 files changed, 9 insertions(+)
PATCH 2/6 qemu/bitmap: Document bitmap_new() returned pointer
In reply to Philippe Mathieu-Daudé--- include/qemu/bitmap.h | 2 ++ 1 file changed, 2 insertions(+)
include/qemu/bitmap.h +2 -0
@@ -90,12 +90,14 @@ int slow_bitmap_intersects(const unsigned long *bitmap1, const unsigned long *bitmap2, long bits);long slow_bitmap_count_one (const unsigned long *bitmap,long nbits); +/* callers must free the returned pointer with g_free() */ static inline unsigned long *bitmap_try_new (long nbits) {long len =BITS_TO_LONGS (nbits) *sizeof (unsigned long );return g_try_malloc0 (len); } +/* callers must free the returned pointer with g_free() */ static inline unsigned long *bitmap_new (long nbits) {unsigned long *ptr =bitmap_try_new (nbits);
Signature · 1 line
2.21.3
Re: [PATCH 2/6] qemu/bitmap: Document bitmap_new() returned pointer
Quoted 4 lines · Philippe Mathieu-Daudé
Signed-off-by Philippe Mathieu-Daudé <[email protected]>--- include/qemu/bitmap.h | 2 ++ 1 file changed, 2 insertions(+)
PATCH 3/6 sysemu/block-backend: Document blk_read()/blk_pwrite()
In reply to Philippe Mathieu-DaudéThe blk_read()/blk_pwrite() return value is not obvious, document it.
--- include/sysemu/block-backend.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+)
include/sysemu/block-backend.h +24 -0
@@ -153,7 +153,31 @@ BlockAIOCB *blk_aio_pwrite_zeroes(BlockBackend *blk, int64_t offset, int bytes, BdrvRequestFlags flags, BlockCompletionFunc *cb, void *opaque);int blk_make_zero (BlockBackend *blk,BdrvRequestFlags flags); + +/** +* blk_pread: +* +* @blk - the block backend where the buffer content is going to be read from +* @offset: position in bytes to read at +* @buf: the data buffer +* @bytes: number of bytes to read +* +* Returns: the number of bytes read on success, or a negative errno otherwise. +*/ int blk_pread (BlockBackend *blk,int64_t offset,void *buf,int bytes); + +/** +* blk_pwrite: +* +* @blk - the block backend where the buffer content is going to be written to +* @offset: position in bytes to write at +* @buf: the data buffer +* @bytes: number of bytes of @buf to write +* @flags: request flags +* +* Returns: the number of bytes consumed on success, +* or a negative errno otherwise. +*/ int blk_pwrite (BlockBackend *blk,int64_t offset,const void *buf,int bytes,BdrvRequestFlags flags);int64_t blk_getlength (BlockBackend *blk);
Signature · 1 line
2.21.3
Re: [PATCH 3/6] sysemu/block-backend: Document blk_read()/blk_pwrite()
include/sysemu/block-backend.h BlockAIOCB *blk_aio_pwrite_zeroes(BlockBackend *blk, int64_t offset, · line 160
Quoted 5 lines · Philippe Mathieu-Daudé
include/sysemu/block-backend.h +5
-0+ +/** +* blk_pread: +* +* @blk - the block backend where the buffer content is going to be read from
s/ - /: /
include/sysemu/block-backend.h BlockAIOCB *blk_aio_pwrite_zeroes(BlockBackend *blk, int64_t offset, · line 172
Quoted 5 lines
include/sysemu/block-backend.h +5
-0+ +/** +* blk_pwrite: +* +* @blk - the block backend where the buffer content is going to be written to
s/ - /: /
PATCH 4/6 block/block: Document BlockSizes fields
In reply to Philippe Mathieu-DaudéAs it is not obvious for a block neophyte what means the 'log' value, document it.
--- include/block/block.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
include/block/block.h +2 -2
@@ -86,8 +86,8 @@ typedef enum { } BdrvRequestFlags;typedef struct BlockSizes { -uint32_t phys; -uint32_t log; +uint32_t phys;/* physical block size */ +uint32_t log;/* logical block size */ }BlockSizes ; typedef struct HDGeometry {
Signature · 1 line
2.21.3
Re: [PATCH 4/6] block/block: Document BlockSizes fields
Quoted 7 lines · Philippe Mathieu-Daudé
As it is not obvious for a block neophyte what means the 'log' value, document it.
Signed-off-by Philippe Mathieu-Daudé <[email protected]>--- include/block/block.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
PATCH 5/6 block/nvme: Align block pages queue to host page size
In reply to Philippe Mathieu-DaudéIn nvme_create_queue_pair() we create a page list using qemu_blockalign(), then map it with qemu_vfio_dma_map():
q->prp_list_pages = qemu_blockalign0(bs, s->page_size * NVME_QUEUE_SIZE); r = qemu_vfio_dma_map(s->vfio, q->prp_list_pages,
s->page_size * NVME_QUEUE_SIZE, ...);
With:
s->page_size = MAX(4096, 1 << (12 + ((cap >> 48) & 0xF)));
The qemu_vfio_dma_map() documentation says "The caller need to make sure the area is aligned to page size". While we use multiple s->page_size as alignment, it might be not sufficient on some hosts. Use the qemu_real_host_page_size value to be sure the host alignment is respected.
---
Cc: Cédric Le Goater <[email protected]>
Cc: David Gibson <[email protected]>
Cc: Laurent Vivier <[email protected]>
--- block/nvme.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
block/nvme.c +1 -1
@@ -627,7 +627,7 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace, s->page_size =MAX (4096 ,1 << (12 + ((cap >>48 ) &0xF ))); s->doorbell_scale = (4 << (((cap >>32 ) &0xF ))) /sizeof (uint32_t ); - bs->bl.opt_mem_alignment = s->page_size; + bs->bl.opt_mem_alignment =MAX (qemu_real_host_page_size, s->page_size); timeout_ms =MIN (500 * ((cap >>24 ) &0xFF ),30000 );/* Reset device to get a clean state. */
Signature · 1 line
2.21.3
Quoted 11 lines · Philippe Mathieu-Daudé
In
nvme_create_queue_pair()we create a page list usingqemu_blockalign(), then map it withqemu_vfio_dma_map():
q->prp_list_pages=qemu_blockalign0(bs, s->page_size * NVME_QUEUE_SIZE); r = qemu_vfio_dma_map(s->vfio,q->prp_list_pages,s->page_size * NVME_QUEUE_SIZE, ...);With:
s->page_size = MAX(4096, 1 << (12 + ((cap >> 48) & 0xF)));
Quoted 7 lines
The
qemu_vfio_dma_map()documentation says "The caller need to make sure the area is aligned to page size". While we use multiples->page_sizeas alignment, it might be not sufficient on some hosts. Use theqemu_real_host_page_sizevalue to be sure the host alignment is respected.Signed-off-by Philippe Mathieu-Daudé <[email protected]>
Quoted 21 lines
---
Cc: Cédric Le Goater <[email protected]>
Cc: David Gibson <[email protected]>
Cc: Laurent Vivier <[email protected]>--- block/nvme.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)block/nvme.c +1
-1@@ -627,7 +627,7 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace, s->page_size =MAX (4096 ,1 << (12 + ((cap >>48 ) &0xF ))); s->doorbell_scale = (4 << (((cap >>32 ) &0xF ))) /sizeof (uint32_t ); - bs->bl.opt_mem_alignment = s->page_size; + bs->bl.opt_mem_alignment =MAX (qemu_real_host_page_size, s->page_size); timeout_ms =MIN (500 * ((cap >>24 ) &0xFF ),30000 );/* Reset device to get a clean state. */
Signature · 4 lines
David Gibson | I'll have my music baroque, and my code david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_ | _way_ _around_! http://www.ozlabs.org/~dgibson
Quoted 31 lines · Philippe Mathieu-Daudé
In
nvme_create_queue_pair()we create a page list usingqemu_blockalign(), then map it withqemu_vfio_dma_map():
q->prp_list_pages=qemu_blockalign0(bs, s->page_size * NVME_QUEUE_SIZE); r = qemu_vfio_dma_map(s->vfio,q->prp_list_pages,s->page_size * NVME_QUEUE_SIZE, ...);With:
s->page_size = MAX(4096, 1 << (12 + ((cap >> 48) & 0xF)));The
qemu_vfio_dma_map()documentation says "The caller need to make sure the area is aligned to page size". While we use multiples->page_sizeas alignment, it might be not sufficient on some hosts. Use theqemu_real_host_page_sizevalue to be sure the host alignment is respected.Signed-off-by Philippe Mathieu-Daudé <[email protected]>---
Cc: Cédric Le Goater <[email protected]>
Cc: David Gibson <[email protected]>
Cc: Laurent Vivier <[email protected]>--- block/nvme.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)block/nvme.c +0
-0
block/nvme.c static int nvme_init(BlockDriverState *bs, const char *device, int namespace, · line 630
Quoted 5 lines
block/nvme.c +1
-1@@ -627,7 +627,7 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace, s->page_size =MAX (4096 ,1 << (12 + ((cap >>48 ) &0xF ))); s->doorbell_scale = (4 << (((cap >>32 ) &0xF ))) /sizeof (uint32_t ); - bs->bl.opt_mem_alignment = s->page_size; + bs->bl.opt_mem_alignment =MAX (qemu_real_host_page_size, s->page_size);
Why don't you replace directly the "4096" in s->page_size by qemu_real_host_page_size?
I think this was the purpose of MAX(4096, ...) to align to the host page size.
Thanks,
Laurnt
Quoted 41 lines · Laurent Vivier
Quoted 31 lines · Philippe Mathieu-Daudé
In
nvme_create_queue_pair()we create a page list usingqemu_blockalign(), then map it withqemu_vfio_dma_map():
q->prp_list_pages=qemu_blockalign0(bs, s->page_size * NVME_QUEUE_SIZE); r = qemu_vfio_dma_map(s->vfio,q->prp_list_pages,s->page_size * NVME_QUEUE_SIZE, ...);With:
s->page_size = MAX(4096, 1 << (12 + ((cap >> 48) & 0xF)));The
qemu_vfio_dma_map()documentation says "The caller need to make sure the area is aligned to page size". While we use multiples->page_sizeas alignment, it might be not sufficient on some hosts. Use theqemu_real_host_page_sizevalue to be sure the host alignment is respected.Signed-off-by Philippe Mathieu-Daudé <[email protected]>---
Cc: Cédric Le Goater <[email protected]>
Cc: David Gibson <[email protected]>
Cc: Laurent Vivier <[email protected]>--- block/nvme.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)block/nvme.c +0
-0block/nvme.c static int nvme_init(BlockDriverState *bs, const char *device, int namespace, · line 630
Quoted 5 lines
block/nvme.c +1
-1@@ -627,7 +627,7 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace, s->page_size =MAX (4096 ,1 << (12 + ((cap >>48 ) &0xF ))); s->doorbell_scale = (4 << (((cap >>32 ) &0xF ))) /sizeof (uint32_t ); - bs->bl.opt_mem_alignment = s->page_size; + bs->bl.opt_mem_alignment =MAX (qemu_real_host_page_size, s->page_size);Why don't you replace directly the "4096" in
s->page_sizebyqemu_real_host_page_size?
Quoted 2 lines
I think this was the purpose of
MAX(4096, ...)to align to the host page size.
oh, I see, page_size is used for a lot of things than can be broken, and this is what is done in bdrv_opt_mem_align() for instance, 4096 is the sector size not the host page size.
BTW, you need the same change as in nvme_init() in nvme_refresh_limits(), I think.
Thanks,
Laurent
Quoted 45 lines · Laurent Vivier
Quoted 41 lines · Laurent Vivier
Quoted 31 lines · Philippe Mathieu-Daudé
In
nvme_create_queue_pair()we create a page list usingqemu_blockalign(), then map it withqemu_vfio_dma_map():q->prp_list_pages = qemu_blockalign0(bs, s->page_size * NVME_QUEUE_SIZE); r = qemu_vfio_dma_map(s->vfio, q->prp_list_pages, s->page_size * NVME_QUEUE_SIZE, ...);With:
s->page_size = MAX(4096, 1 << (12 + ((cap >> 48) & 0xF)));The
qemu_vfio_dma_map()documentation says "The caller need to make sure the area is aligned to page size". While we use multiples->page_sizeas alignment, it might be not sufficient on some hosts. Use theqemu_real_host_page_sizevalue to be sure the host alignment is respected.Signed-off-by Philippe Mathieu-Daudé <[email protected]>---
Cc: Cédric Le Goater <[email protected]>
Cc: David Gibson <[email protected]>
Cc: Laurent Vivier <[email protected]>--- block/nvme.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)block/nvme.c +0
-0block/nvme.c static int nvme_init(BlockDriverState *bs, const char *device, int namespace, · line 630
Quoted 5 lines
block/nvme.c +1
-1@@ -627,7 +627,7 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace, s->page_size =MAX (4096 ,1 << (12 + ((cap >>48 ) &0xF ))); s->doorbell_scale = (4 << (((cap >>32 ) &0xF ))) /sizeof (uint32_t ); - bs->bl.opt_mem_alignment = s->page_size; + bs->bl.opt_mem_alignment =MAX (qemu_real_host_page_size, s->page_size);Why don't you replace directly the "4096" in
s->page_sizebyqemu_real_host_page_size?Quoted 2 lines
I think this was the purpose of
MAX(4096, ...)to align to the host page size.
Quoted 6 lines
oh, I see,
page_sizeis used for a lot of things than can be broken, and this is what is done inbdrv_opt_mem_align()for instance, 4096 is the sector size not the host page size.BTW, you need the same change as in
nvme_init()innvme_refresh_limits(), I think.
nvme_init() seems OK, but you are right, I missed nvme_refresh_limits()... Thanks!
Quoted 5 lines
Thanks,
Laurent
Quoted 32 lines · Philippe Mathieu-Daudé
In
nvme_create_queue_pair()we create a page list usingqemu_blockalign(), then map it withqemu_vfio_dma_map():q->prp_list_pages = qemu_blockalign0(bs, s->page_size * NVME_QUEUE_SIZE); r = qemu_vfio_dma_map(s->vfio, q->prp_list_pages, s->page_size * NVME_QUEUE_SIZE, ...);With:
s->page_size = MAX(4096, 1 << (12 + ((cap >> 48) & 0xF)));The
qemu_vfio_dma_map()documentation says "The caller need to make sure the area is aligned to page size". While we use multiples->page_sizeas alignment, it might be not sufficient on some hosts. Use theqemu_real_host_page_sizevalue to be sure the host alignment is respected.Signed-off-by Philippe Mathieu-Daudé <[email protected]>---
Cc: Cédric Le Goater <[email protected]>
Cc: David Gibson <[email protected]>
Cc: Laurent Vivier <[email protected]>--- block/nvme.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)block/nvme.c +0
-0
block/nvme.c static int nvme_init(BlockDriverState *bs, const char *device, int namespace, · line 633
Quoted 8 lines
block/nvme.c +1
-1@@ -627,7 +627,7 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace, s->page_size =MAX (4096 ,1 << (12 + ((cap >>48 ) &0xF ))); s->doorbell_scale = (4 << (((cap >>32 ) &0xF ))) /sizeof (uint32_t ); - bs->bl.opt_mem_alignment = s->page_size; + bs->bl.opt_mem_alignment =MAX (qemu_real_host_page_size, s->page_size); timeout_ms =MIN (500 * ((cap >>24 ) &0xFF ),30000 );/* Reset device to get a clean state. */
Please disregard this patch as it is incomplete.
RFC PATCH 6/6 hw/block/nvme: Make device target agnostic
In reply to Philippe Mathieu-DaudéThe NVMe device should not use target specific API. Use memory_region_do_writeback() (which was introduced in commit 61c490e25e0, after the NVMe emulated device was added) to replace qemu_ram_writeback().
---
RFC because I have no clue how dirty_log_mask works.
--- hw/block/nvme.c | 4 +--- hw/block/Makefile.objs | 2 +- 2 files changed, 2 insertions(+), 4 deletions(-)
hw/block/nvme.c +1 -3
@@ -46,7 +46,6 @@#include "qapi/visitor.h" #include "sysemu/hostmem.h" #include "sysemu/block-backend.h" -#include "exec/ram_addr.h" #include "qemu/log.h" #include "qemu/module.h"
@@ -1207,8 +1206,7 @@ static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size)*/ if (addr ==0xE08 && (NVME_PMRCAP_PMRWBM (n->bar.pmrcap) &0x02 )) { -qemu_ram_writeback (n->pmrdev->mr.ram_block, -0 , n->pmrdev->size); +memory_region_do_writeback (&n->pmrdev->mr,0 , n->pmrdev->size); }memcpy (&val, ptr + addr, size); }else {
hw/block/Makefile.objs +1 -1
@@ -13,6 +13,6 @@ common-obj-$(CONFIG_SH4) += tc58128.o obj-$(CONFIG_VIRTIO_BLK) += virtio-blk.o obj-$(CONFIG_VHOST_USER_BLK) += vhost-user-blk.o -obj-$(CONFIG_NVME_PCI) += nvme.o +common-obj-$(CONFIG_NVME_PCI) += nvme.o obj-y += dataplane/
Signature · 1 line
2.21.3
Re: [RFC PATCH 6/6] hw/block/nvme: Make device target agnostic
+Keith new email
Quoted 51 lines · Philippe Mathieu-Daudé
The NVMe device should not use target specific API. Use
memory_region_do_writeback()(which was introduced in commit61c490e25e0, after the NVMe emulated device was added) to replaceqemu_ram_writeback().Signed-off-by Philippe Mathieu-Daudé <[email protected]>---
RFC because I have no clue howdirty_log_maskworks.Cc Paolo Bonzini <[email protected]>Cc Beata Michalska <[email protected]>--- hw/block/nvme.c | 4 +--- hw/block/Makefile.objs | 2 +- 2 files changed, 2 insertions(+), 4 deletions(-)hw/block/nvme.c +1
-3@@ -46,7 +46,6 @@#include "qapi/visitor.h" #include "sysemu/hostmem.h" #include "sysemu/block-backend.h" -#include "exec/ram_addr.h" #include "qemu/log.h" #include "qemu/module.h" @@ -1207,8 +1206,7 @@ static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size)*/ if (addr ==0xE08 && (NVME_PMRCAP_PMRWBM (n->bar.pmrcap) &0x02 )) { -qemu_ram_writeback (n->pmrdev->mr.ram_block, -0 , n->pmrdev->size); +memory_region_do_writeback (&n->pmrdev->mr,0 , n->pmrdev->size); }memcpy (&val, ptr + addr, size); }else {hw/block/Makefile.objs +1
-1@@ -13,6 +13,6 @@ common-obj-$(CONFIG_SH4) += tc58128.o obj-$(CONFIG_VIRTIO_BLK) += virtio-blk.o obj-$(CONFIG_VHOST_USER_BLK) += vhost-user-blk.o -obj-$(CONFIG_NVME_PCI) += nvme.o +common-obj-$(CONFIG_NVME_PCI) += nvme.o obj-y += dataplane/
Re: [RFC PATCH 6/6] hw/block/nvme: Make device target agnostic
Quoted 29 lines · Philippe Mathieu-Daudé
+Keith new email
Quoted 26 lines · Philippe Mathieu-Daudé
The NVMe device should not use target specific API. Use
memory_region_do_writeback()(which was introduced in commit61c490e25e0, after the NVMe emulated device was added) to replaceqemu_ram_writeback().Signed-off-by Philippe Mathieu-Daudé <[email protected]>---
RFC because I have no clue howdirty_log_maskworks.Cc Paolo Bonzini <[email protected]>Cc Beata Michalska <[email protected]>--- hw/block/nvme.c | 4 +--- hw/block/Makefile.objs | 2 +- 2 files changed, 2 insertions(+), 4 deletions(-)hw/block/nvme.c +0
-1@@ -46,7 +46,6 @@#include "qapi/visitor.h" #include "sysemu/hostmem.h" #include "sysemu/block-backend.h" -#include "exec/ram_addr.h" #include "qemu/log.h"
Quoted 8 lines
hw/block/nvme.c static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size) · line 1209
Quoted 8 lines
hw/block/nvme.c +1
-2#include "qemu/module.h" @@ -1207,8 +1206,7 @@ static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size)*/ if (addr ==0xE08 && (NVME_PMRCAP_PMRWBM (n->bar.pmrcap) &0x02 )) { -qemu_ram_writeback (n->pmrdev->mr.ram_block, -0 , n->pmrdev->size); +memory_region_do_writeback (&n->pmrdev->mr,0 , n->pmrdev->size);
qemu_ram_write() is being called because we need to msync or persist pmem here.
The memory_region_do_writeback() API is not equivalent, its purpose is for dirty write logging (which we don't care about here because the writes themselves will already have been logged when the guest performed them).
I think qemu_ram_writeback() should just be made common so that this code isn't target-specific. Maybe it should be renamed to qemu_ram_msync() to avoid confusion with dirty write APIs.
Stefan
Re: [RFC PATCH 6/6] hw/block/nvme: Make device target agnostic
Quoted 7 lines · Stefan Hajnoczi
Quoted 4 lines
hw/block/nvme.c static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size) · line 1209
Quoted 4 lines
(NVME_PMRCAP_PMRWBM(n->bar.pmrcap) & 0x02)) {hw/block/nvme.c +1
-2-qemu_ram_writeback (n->pmrdev->mr.ram_block, -0 , n->pmrdev->size); +memory_region_do_writeback (&n->pmrdev->mr,0 , n->pmrdev->size);
qemu_ram_write()is being called because we need to msync or persist pmem here.
Quoted 8 lines
The
memory_region_do_writeback()API is not equivalent, its purpose is for dirty write logging (which we don't care about here because the writes themselves will already have been logged when the guest performed them).I think
qemu_ram_writeback()should just be made common so that this code isn't target-specific. Maybe it should be renamed toqemu_ram_msync()to avoid confusion with dirty write APIs.
Yes, we can add qemu_ram_msync and memory_region_msync.
Paolo