Re: [PATCH v6 02/13] multifd: Create page_size fields into both MultiFD{Recv,Send}Params

[Dr. David Alan Gilbert]

* Juan Quintela (quintela@redhat.com) wrote:
> We were calling qemu_target_page_size() left and right.
> 
> Signed-off-by: Juan Quintela <quintela@redhat.com>

(Copying in Peter Maydell)
Your problem here is most of these files are target independent
so you end up calling the qemu_target_page_size functions, which I guess
you're seeing popup in some perf trace?
I mean they're trivial functions but I guess you do get the function
call.

I wonder about the following patch instead
(Note i've removed the const on the structure here); I wonder how this
does performance wise for everyone:


From abc7da46736b18b6138868ccc0b11901169e1dfd Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Date: Mon, 16 May 2022 19:54:31 +0100
Subject: [PATCH] target-page: Maintain target_page variable even for
 non-variable
Content-type: text/plain

On architectures that define TARGET_PAGE_BITS_VARY, the 'target_page'
structure gets filled in at run time by the number of bits and the
TARGET_PAGE_BITS and TARGET_PAGE macros use that rather than being
constant.

On non-variable pagesize systems target_page is not filled in, and we
rely on TARGET_PAGE_SIZE being compile time defined.

The problem is that for source files that are target-independent
they end up calling qemu_target_page_size to read the size, and that
function call is annoying.

Improve this by always filling in 'target_page' even for non-variable
size CPUs, and inlining the functions that previously returned
the macro values (that may have been constant) to return the
values read from target_page.

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
---
 include/exec/cpu-all.h     |  4 ++--
 include/exec/page-vary.h   |  2 ++
 include/exec/target_page.h | 11 +++++++++--
 page-vary.c                |  2 --
 softmmu/physmem.c          | 10 ----------
 5 files changed, 13 insertions(+), 16 deletions(-)

diff --git a/include/exec/cpu-all.h b/include/exec/cpu-all.h
index 5d5290deb5..6a498fa033 100644
--- a/include/exec/cpu-all.h
+++ b/include/exec/cpu-all.h
@@ -214,9 +214,9 @@ static inline void stl_phys_notdirty(AddressSpace *as, 
hwaddr addr, uint32_t val
 
 /* page related stuff */
 
+#include "exec/page-vary.h"
+
 #ifdef TARGET_PAGE_BITS_VARY
-# include "exec/page-vary.h"
-extern const TargetPageBits target_page;
 #ifdef CONFIG_DEBUG_TCG
 #define TARGET_PAGE_BITS   ({ assert(target_page.decided); target_page.bits; })
 #define TARGET_PAGE_MASK   ({ assert(target_page.decided); \
diff --git a/include/exec/page-vary.h b/include/exec/page-vary.h
index ebbe9b169b..31cb9dd9dd 100644
--- a/include/exec/page-vary.h
+++ b/include/exec/page-vary.h
@@ -26,6 +26,8 @@ typedef struct {
     uint64_t mask;
 } TargetPageBits;
 
+extern TargetPageBits target_page;
+
 #ifdef IN_PAGE_VARY
 extern bool set_preferred_target_page_bits_common(int bits);
 extern void finalize_target_page_bits_common(int min);
diff --git a/include/exec/target_page.h b/include/exec/target_page.h
index 96726c36a4..e718b145b3 100644
--- a/include/exec/target_page.h
+++ b/include/exec/target_page.h
@@ -13,9 +13,16 @@
 
 #ifndef EXEC_TARGET_PAGE_H
 #define EXEC_TARGET_PAGE_H
+#include "exec/page-vary.h"
+
+inline int qemu_target_page_bits(void) {
+    return target_page.bits;
+}
+
+inline size_t qemu_target_page_size(void) {
+    return 1 << target_page.bits;
+}
 
-size_t qemu_target_page_size(void);
-int qemu_target_page_bits(void);
 int qemu_target_page_bits_min(void);
 
 #endif
diff --git a/page-vary.c b/page-vary.c
index 343b4adb95..3f81144cda 100644
--- a/page-vary.c
+++ b/page-vary.c
@@ -35,7 +35,5 @@ bool set_preferred_target_page_bits(int bits)
 
 void finalize_target_page_bits(void)
 {
-#ifdef TARGET_PAGE_BITS_VARY
     finalize_target_page_bits_common(TARGET_PAGE_BITS_MIN);
-#endif
 }
diff --git a/softmmu/physmem.c b/softmmu/physmem.c
index 657841eed0..2117476081 100644
--- a/softmmu/physmem.c
+++ b/softmmu/physmem.c
@@ -3515,16 +3515,6 @@ int cpu_memory_rw_debug(CPUState *cpu, vaddr addr,
  * Allows code that needs to deal with migration bitmaps etc to still be built
  * target independent.
  */
-size_t qemu_target_page_size(void)
-{
-    return TARGET_PAGE_SIZE;
-}
-
-int qemu_target_page_bits(void)
-{
-    return TARGET_PAGE_BITS;
-}
-
 int qemu_target_page_bits_min(void)
 {
     return TARGET_PAGE_BITS_MIN;
-- 
2.36.1

> ---
>  migration/multifd.h      |  4 ++++
>  migration/multifd-zlib.c | 12 +++++-------
>  migration/multifd-zstd.c | 12 +++++-------
>  migration/multifd.c      | 18 ++++++++----------
>  4 files changed, 22 insertions(+), 24 deletions(-)
> 
> diff --git a/migration/multifd.h b/migration/multifd.h
> index f1f88c6737..4de80d9e53 100644
> --- a/migration/multifd.h
> +++ b/migration/multifd.h
> @@ -80,6 +80,8 @@ typedef struct {
>      bool registered_yank;
>      /* packet allocated len */
>      uint32_t packet_len;
> +    /* guest page size */
> +    uint32_t page_size;
>  
>      /* sem where to wait for more work */
>      QemuSemaphore sem;
> @@ -141,6 +143,8 @@ typedef struct {
>      QIOChannel *c;
>      /* packet allocated len */
>      uint32_t packet_len;
> +    /* guest page size */
> +    uint32_t page_size;
>  
>      /* syncs main thread and channels */
>      QemuSemaphore sem_sync;
> diff --git a/migration/multifd-zlib.c b/migration/multifd-zlib.c
> index 3a7ae44485..28349ff2e0 100644
> --- a/migration/multifd-zlib.c
> +++ b/migration/multifd-zlib.c
> @@ -100,7 +100,6 @@ static void zlib_send_cleanup(MultiFDSendParams *p, Error 
> **errp)
>  static int zlib_send_prepare(MultiFDSendParams *p, Error **errp)
>  {
>      struct zlib_data *z = p->data;
> -    size_t page_size = qemu_target_page_size();
>      z_stream *zs = &z->zs;
>      uint32_t out_size = 0;
>      int ret;
> @@ -114,7 +113,7 @@ static int zlib_send_prepare(MultiFDSendParams *p, Error 
> **errp)
>              flush = Z_SYNC_FLUSH;
>          }
>  
> -        zs->avail_in = page_size;
> +        zs->avail_in = p->page_size;
>          zs->next_in = p->pages->block->host + p->normal[i];
>  
>          zs->avail_out = available;
> @@ -220,12 +219,11 @@ static void zlib_recv_cleanup(MultiFDRecvParams *p)
>  static int zlib_recv_pages(MultiFDRecvParams *p, Error **errp)
>  {
>      struct zlib_data *z = p->data;
> -    size_t page_size = qemu_target_page_size();
>      z_stream *zs = &z->zs;
>      uint32_t in_size = p->next_packet_size;
>      /* we measure the change of total_out */
>      uint32_t out_size = zs->total_out;
> -    uint32_t expected_size = p->normal_num * page_size;
> +    uint32_t expected_size = p->normal_num * p->page_size;
>      uint32_t flags = p->flags & MULTIFD_FLAG_COMPRESSION_MASK;
>      int ret;
>      int i;
> @@ -252,7 +250,7 @@ static int zlib_recv_pages(MultiFDRecvParams *p, Error 
> **errp)
>              flush = Z_SYNC_FLUSH;
>          }
>  
> -        zs->avail_out = page_size;
> +        zs->avail_out = p->page_size;
>          zs->next_out = p->host + p->normal[i];
>  
>          /*
> @@ -266,8 +264,8 @@ static int zlib_recv_pages(MultiFDRecvParams *p, Error 
> **errp)
>          do {
>              ret = inflate(zs, flush);
>          } while (ret == Z_OK && zs->avail_in
> -                             && (zs->total_out - start) < page_size);
> -        if (ret == Z_OK && (zs->total_out - start) < page_size) {
> +                             && (zs->total_out - start) < p->page_size);
> +        if (ret == Z_OK && (zs->total_out - start) < p->page_size) {
>              error_setg(errp, "multifd %u: inflate generated too few output",
>                         p->id);
>              return -1;
> diff --git a/migration/multifd-zstd.c b/migration/multifd-zstd.c
> index d788d309f2..f4a8e1ed1f 100644
> --- a/migration/multifd-zstd.c
> +++ b/migration/multifd-zstd.c
> @@ -113,7 +113,6 @@ static void zstd_send_cleanup(MultiFDSendParams *p, Error 
> **errp)
>  static int zstd_send_prepare(MultiFDSendParams *p, Error **errp)
>  {
>      struct zstd_data *z = p->data;
> -    size_t page_size = qemu_target_page_size();
>      int ret;
>      uint32_t i;
>  
> @@ -128,7 +127,7 @@ static int zstd_send_prepare(MultiFDSendParams *p, Error 
> **errp)
>              flush = ZSTD_e_flush;
>          }
>          z->in.src = p->pages->block->host + p->normal[i];
> -        z->in.size = page_size;
> +        z->in.size = p->page_size;
>          z->in.pos = 0;
>  
>          /*
> @@ -241,8 +240,7 @@ static int zstd_recv_pages(MultiFDRecvParams *p, Error 
> **errp)
>  {
>      uint32_t in_size = p->next_packet_size;
>      uint32_t out_size = 0;
> -    size_t page_size = qemu_target_page_size();
> -    uint32_t expected_size = p->normal_num * page_size;
> +    uint32_t expected_size = p->normal_num * p->page_size;
>      uint32_t flags = p->flags & MULTIFD_FLAG_COMPRESSION_MASK;
>      struct zstd_data *z = p->data;
>      int ret;
> @@ -265,7 +263,7 @@ static int zstd_recv_pages(MultiFDRecvParams *p, Error 
> **errp)
>  
>      for (i = 0; i < p->normal_num; i++) {
>          z->out.dst = p->host + p->normal[i];
> -        z->out.size = page_size;
> +        z->out.size = p->page_size;
>          z->out.pos = 0;
>  
>          /*
> @@ -279,8 +277,8 @@ static int zstd_recv_pages(MultiFDRecvParams *p, Error 
> **errp)
>          do {
>              ret = ZSTD_decompressStream(z->zds, &z->out, &z->in);
>          } while (ret > 0 && (z->in.size - z->in.pos > 0)
> -                         && (z->out.pos < page_size));
> -        if (ret > 0 && (z->out.pos < page_size)) {
> +                         && (z->out.pos < p->page_size));
> +        if (ret > 0 && (z->out.pos < p->page_size)) {
>              error_setg(errp, "multifd %u: decompressStream buffer too small",
>                         p->id);
>              return -1;
> diff --git a/migration/multifd.c b/migration/multifd.c
> index 9ea4f581e2..f15fed5f1f 100644
> --- a/migration/multifd.c
> +++ b/migration/multifd.c
> @@ -87,15 +87,14 @@ static void nocomp_send_cleanup(MultiFDSendParams *p, 
> Error **errp)
>  static int nocomp_send_prepare(MultiFDSendParams *p, Error **errp)
>  {
>      MultiFDPages_t *pages = p->pages;
> -    size_t page_size = qemu_target_page_size();
>  
>      for (int i = 0; i < p->normal_num; i++) {
>          p->iov[p->iovs_num].iov_base = pages->block->host + p->normal[i];
> -        p->iov[p->iovs_num].iov_len = page_size;
> +        p->iov[p->iovs_num].iov_len = p->page_size;
>          p->iovs_num++;
>      }
>  
> -    p->next_packet_size = p->normal_num * page_size;
> +    p->next_packet_size = p->normal_num * p->page_size;
>      p->flags |= MULTIFD_FLAG_NOCOMP;
>      return 0;
>  }
> @@ -139,7 +138,6 @@ static void nocomp_recv_cleanup(MultiFDRecvParams *p)
>  static int nocomp_recv_pages(MultiFDRecvParams *p, Error **errp)
>  {
>      uint32_t flags = p->flags & MULTIFD_FLAG_COMPRESSION_MASK;
> -    size_t page_size = qemu_target_page_size();
>  
>      if (flags != MULTIFD_FLAG_NOCOMP) {
>          error_setg(errp, "multifd %u: flags received %x flags expected %x",
> @@ -148,7 +146,7 @@ static int nocomp_recv_pages(MultiFDRecvParams *p, Error 
> **errp)
>      }
>      for (int i = 0; i < p->normal_num; i++) {
>          p->iov[i].iov_base = p->host + p->normal[i];
> -        p->iov[i].iov_len = page_size;
> +        p->iov[i].iov_len = p->page_size;
>      }
>      return qio_channel_readv_all(p->c, p->iov, p->normal_num, errp);
>  }
> @@ -281,8 +279,7 @@ static void multifd_send_fill_packet(MultiFDSendParams *p)
>  static int multifd_recv_unfill_packet(MultiFDRecvParams *p, Error **errp)
>  {
>      MultiFDPacket_t *packet = p->packet;
> -    size_t page_size = qemu_target_page_size();
> -    uint32_t page_count = MULTIFD_PACKET_SIZE / page_size;
> +    uint32_t page_count = MULTIFD_PACKET_SIZE / p->page_size;
>      RAMBlock *block;
>      int i;
>  
> @@ -344,7 +341,7 @@ static int multifd_recv_unfill_packet(MultiFDRecvParams 
> *p, Error **errp)
>      for (i = 0; i < p->normal_num; i++) {
>          uint64_t offset = be64_to_cpu(packet->offset[i]);
>  
> -        if (offset > (block->used_length - page_size)) {
> +        if (offset > (block->used_length - p->page_size)) {
>              error_setg(errp, "multifd: offset too long %" PRIu64
>                         " (max " RAM_ADDR_FMT ")",
>                         offset, block->used_length);
> @@ -433,8 +430,7 @@ static int multifd_send_pages(QEMUFile *f)
>      p->packet_num = multifd_send_state->packet_num++;
>      multifd_send_state->pages = p->pages;
>      p->pages = pages;
> -    transferred = ((uint64_t) pages->num) * qemu_target_page_size()
> -                + p->packet_len;
> +    transferred = ((uint64_t) pages->num) * p->page_size + p->packet_len;
>      qemu_file_update_transfer(f, transferred);
>      ram_counters.multifd_bytes += transferred;
>      ram_counters.transferred += transferred;
> @@ -898,6 +894,7 @@ int multifd_save_setup(Error **errp)
>          /* We need one extra place for the packet header */
>          p->iov = g_new0(struct iovec, page_count + 1);
>          p->normal = g_new0(ram_addr_t, page_count);
> +        p->page_size = qemu_target_page_size();
>          socket_send_channel_create(multifd_new_send_channel_async, p);
>      }
>  
> @@ -1138,6 +1135,7 @@ int multifd_load_setup(Error **errp)
>          p->name = g_strdup_printf("multifdrecv_%d", i);
>          p->iov = g_new0(struct iovec, page_count);
>          p->normal = g_new0(ram_addr_t, page_count);
> +        p->page_size = qemu_target_page_size();
>      }
>  
>      for (i = 0; i < thread_count; i++) {
> -- 
> 2.35.1
> 
-- 
Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK