All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jan Beulich <jbeulich@suse.com>
To: "xen-devel@lists.xenproject.org" <xen-devel@lists.xenproject.org>
Cc: "Andrew Cooper" <andrew.cooper3@citrix.com>,
	"Wei Liu" <wl@xen.org>, "Roger Pau Monné" <roger.pau@citrix.com>
Subject: [PATCH 2/7] x86: introduce ioremap_wc()
Date: Tue, 27 Apr 2021 14:54:02 +0200	[thread overview]
Message-ID: <0e1d3e9e-ed29-d7e8-e4fc-e48a0454faa4@suse.com> (raw)
In-Reply-To: <6d6da76c-ccc8-afa2-bd06-5ae132c354f2@suse.com>

In order for a to-be-introduced ERMS form of memcpy() to not regress
boot performance on certain systems when video output is active, we
first need to arrange for avoiding further dependency on firmware
setting up MTRRs in a way we can actually further modify. On many
systems, due to the continuously growing amounts of installed memory,
MTRRs get configured with at least one huge WB range, and with MMIO
ranges below 4Gb then forced to UC via overlapping MTRRs. mtrr_add(), as
it is today, can't deal with such a setup. Hence on such systems we
presently leave the frame buffer mapped UC, leading to significantly
reduced performance when using REP STOSB / REP MOVSB.

On post-PentiumII hardware (i.e. any that's capable of running 64-bit
code), an effective memory type of WC can be achieved without MTRRs, by
simply referencing the respective PAT entry from the PTEs. While this
will leave the switch to ERMS forms of memset() and memcpy() with
largely unchanged performance, the change here on its own improves
performance on affected systems quite significantly: Measuring just the
individual affected memcpy() invocations yielded a speedup by a factor
of over 250 on my initial (Skylake) test system. memset() isn't getting
improved by as much there, but still by a factor of about 20.

While adding {__,}PAGE_HYPERVISOR_WC, also add {__,}PAGE_HYPERVISOR_WT
to, at the very least, make clear what PTE flags this memory type uses.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
---
TBD: Both callers are __init, so in principle ioremap_wc() could be so,
     too, at least for the time being.
TBD: If the VGA range is WC in the fixed range MTRRs, reusing the low
     1st Mb mapping (like ioremap() does) would be an option.

--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -5883,6 +5883,20 @@ void __iomem *ioremap(paddr_t pa, size_t
     return (void __force __iomem *)va;
 }
 
+void __iomem *ioremap_wc(paddr_t pa, size_t len)
+{
+    mfn_t mfn = _mfn(PFN_DOWN(pa));
+    unsigned int offs = pa & (PAGE_SIZE - 1);
+    unsigned int nr = PFN_UP(offs + len);
+    void *va;
+
+    WARN_ON(page_is_ram_type(mfn_x(mfn), RAM_TYPE_CONVENTIONAL));
+
+    va = __vmap(&mfn, nr, 1, 1, PAGE_HYPERVISOR_WC, VMAP_DEFAULT);
+
+    return (void __force __iomem *)(va + offs);
+}
+
 int create_perdomain_mapping(struct domain *d, unsigned long va,
                              unsigned int nr, l1_pgentry_t **pl1tab,
                              struct page_info **ppg)
--- a/xen/drivers/video/vesa.c
+++ b/xen/drivers/video/vesa.c
@@ -9,9 +9,9 @@
 #include <xen/param.h>
 #include <xen/xmalloc.h>
 #include <xen/kernel.h>
+#include <xen/mm.h>
 #include <xen/vga.h>
 #include <asm/io.h>
-#include <asm/page.h>
 #include "font.h"
 #include "lfb.h"
 
@@ -103,7 +103,7 @@ void __init vesa_init(void)
     lfbp.text_columns = vlfb_info.width / font->width;
     lfbp.text_rows = vlfb_info.height / font->height;
 
-    lfbp.lfb = lfb = ioremap(lfb_base(), vram_remap);
+    lfbp.lfb = lfb = ioremap_wc(lfb_base(), vram_remap);
     if ( !lfb )
         return;
 
@@ -179,8 +179,7 @@ void __init vesa_mtrr_init(void)
 
 static void lfb_flush(void)
 {
-    if ( vesa_mtrr == 3 )
-        __asm__ __volatile__ ("sfence" : : : "memory");
+    __asm__ __volatile__ ("sfence" : : : "memory");
 }
 
 void __init vesa_endboot(bool_t keep)
--- a/xen/drivers/video/vga.c
+++ b/xen/drivers/video/vga.c
@@ -79,7 +79,7 @@ void __init video_init(void)
     {
     case XEN_VGATYPE_TEXT_MODE_3:
         if ( page_is_ram_type(paddr_to_pfn(0xB8000), RAM_TYPE_CONVENTIONAL) ||
-             ((video = ioremap(0xB8000, 0x8000)) == NULL) )
+             ((video = ioremap_wc(0xB8000, 0x8000)) == NULL) )
             return;
         outw(0x200a, 0x3d4); /* disable cursor */
         columns = vga_console_info.u.text_mode_3.columns;
@@ -164,7 +164,11 @@ void __init video_endboot(void)
     {
     case XEN_VGATYPE_TEXT_MODE_3:
         if ( !vgacon_keep )
+        {
             memset(video, 0, columns * lines * 2);
+            iounmap(video);
+            video = ZERO_BLOCK_PTR;
+        }
         break;
     case XEN_VGATYPE_VESA_LFB:
     case XEN_VGATYPE_EFI_LFB:
--- a/xen/include/asm-x86/mm.h
+++ b/xen/include/asm-x86/mm.h
@@ -615,6 +615,8 @@ void destroy_perdomain_mapping(struct do
                                unsigned int nr);
 void free_perdomain_mappings(struct domain *);
 
+void __iomem *ioremap_wc(paddr_t, size_t);
+
 extern int memory_add(unsigned long spfn, unsigned long epfn, unsigned int pxm);
 
 void domain_set_alloc_bitsize(struct domain *d);
--- a/xen/include/asm-x86/page.h
+++ b/xen/include/asm-x86/page.h
@@ -349,8 +349,10 @@ void efi_update_l4_pgtable(unsigned int
 #define __PAGE_HYPERVISOR_RX      (_PAGE_PRESENT | _PAGE_ACCESSED)
 #define __PAGE_HYPERVISOR         (__PAGE_HYPERVISOR_RX | \
                                    _PAGE_DIRTY | _PAGE_RW)
+#define __PAGE_HYPERVISOR_WT      (__PAGE_HYPERVISOR | _PAGE_PWT)
 #define __PAGE_HYPERVISOR_UCMINUS (__PAGE_HYPERVISOR | _PAGE_PCD)
 #define __PAGE_HYPERVISOR_UC      (__PAGE_HYPERVISOR | _PAGE_PCD | _PAGE_PWT)
+#define __PAGE_HYPERVISOR_WC      (__PAGE_HYPERVISOR | _PAGE_PAT)
 #define __PAGE_HYPERVISOR_SHSTK   (__PAGE_HYPERVISOR_RO | _PAGE_DIRTY)
 
 #define MAP_SMALL_PAGES _PAGE_AVAIL0 /* don't use superpages mappings */
--- a/xen/include/asm-x86/x86_64/page.h
+++ b/xen/include/asm-x86/x86_64/page.h
@@ -154,6 +154,10 @@ static inline intpte_t put_pte_flags(uns
                                  _PAGE_GLOBAL | _PAGE_NX)
 #define PAGE_HYPERVISOR_UC      (__PAGE_HYPERVISOR_UC | \
                                  _PAGE_GLOBAL | _PAGE_NX)
+#define PAGE_HYPERVISOR_WC      (__PAGE_HYPERVISOR_WC | \
+                                 _PAGE_GLOBAL | _PAGE_NX)
+#define PAGE_HYPERVISOR_WT      (__PAGE_HYPERVISOR_WT | \
+                                 _PAGE_GLOBAL | _PAGE_NX)
 
 #endif /* __X86_64_PAGE_H__ */
 



  parent reply	other threads:[~2021-04-27 12:54 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-27 12:51 [PATCH 0/7] x86: memcpy() / memset() (non-)ERMS flavors plus fallout Jan Beulich
2021-04-27 12:53 ` [PATCH 1/7] x86: correct comment about alternatives ordering Jan Beulich
2021-04-27 13:19   ` Andrew Cooper
2021-04-27 12:54 ` Jan Beulich [this message]
2021-04-27 17:13   ` [PATCH 2/7] x86: introduce ioremap_wc() Andrew Cooper
2021-04-28  9:41     ` Jan Beulich
2021-04-27 12:54 ` [PATCH 3/7] x86: re-work memset() Jan Beulich
2021-04-27 12:54 ` [PATCH 4/7] x86: re-work memcpy() Jan Beulich
2021-04-27 12:55 ` [PATCH 5/7] video/vesa: unmap frame buffer when relinquishing console Jan Beulich
2021-04-27 12:56 ` [PATCH 6/7] video/vesa: drop "vesa-mtrr" command line option Jan Beulich
2021-04-27 13:20   ` Andrew Cooper
2021-04-27 12:56 ` [PATCH 7/7] video/vesa: adjust (not just) command line option handling Jan Beulich
2021-04-27 13:49   ` Andrew Cooper
2021-04-27 14:04     ` Jan Beulich
2021-05-27 11:47       ` Jan Beulich

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=0e1d3e9e-ed29-d7e8-e4fc-e48a0454faa4@suse.com \
    --to=jbeulich@suse.com \
    --cc=andrew.cooper3@citrix.com \
    --cc=roger.pau@citrix.com \
    --cc=wl@xen.org \
    --cc=xen-devel@lists.xenproject.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.