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>,
	"George Dunlap" <george.dunlap@citrix.com>,
	"Wei Liu" <wl@xen.org>, "Roger Pau Monné" <roger.pau@citrix.com>
Subject: [PATCH v3 05/22] x86/xstate: drop xstate_offsets[] and xstate_sizes[]
Date: Thu, 22 Apr 2021 16:45:58 +0200	[thread overview]
Message-ID: <434705ef-1c34-581d-b956-2322b4413232@suse.com> (raw)
In-Reply-To: <322de6db-e01f-0b57-5777-5d94a13c441a@suse.com>

They're redundant with respective fields from the raw CPUID policy; no
need to keep two copies of the same data. This also breaks
recalculate_xstate()'s dependency on xstate_init(), allowing host CPUID
policy calculation to be moved together with that of the raw one (which
a subsequent change will require anyway).

Signed-off-by: Jan Beulich <jbeulich@suse.com>

--- a/xen/arch/x86/cpu/common.c
+++ b/xen/arch/x86/cpu/common.c
@@ -498,6 +498,8 @@ void identify_cpu(struct cpuinfo_x86 *c)
 	}
 
 	/* Now the feature flags better reflect actual CPU features! */
+	if (c == &boot_cpu_data)
+		init_host_cpuid();
 
 	xstate_init(c);
 
--- a/xen/arch/x86/cpuid.c
+++ b/xen/arch/x86/cpuid.c
@@ -170,32 +170,32 @@ static void recalculate_xstate(struct cp
     {
         xstates |= X86_XCR0_YMM;
         xstate_size = max(xstate_size,
-                          xstate_offsets[X86_XCR0_YMM_POS] +
-                          xstate_sizes[X86_XCR0_YMM_POS]);
+                          xstate_offset(X86_XCR0_YMM_POS) +
+                          xstate_size(X86_XCR0_YMM_POS));
     }
 
     if ( p->feat.mpx )
     {
         xstates |= X86_XCR0_BNDREGS | X86_XCR0_BNDCSR;
         xstate_size = max(xstate_size,
-                          xstate_offsets[X86_XCR0_BNDCSR_POS] +
-                          xstate_sizes[X86_XCR0_BNDCSR_POS]);
+                          xstate_offset(X86_XCR0_BNDCSR_POS) +
+                          xstate_size(X86_XCR0_BNDCSR_POS));
     }
 
     if ( p->feat.avx512f )
     {
         xstates |= X86_XCR0_OPMASK | X86_XCR0_ZMM | X86_XCR0_HI_ZMM;
         xstate_size = max(xstate_size,
-                          xstate_offsets[X86_XCR0_HI_ZMM_POS] +
-                          xstate_sizes[X86_XCR0_HI_ZMM_POS]);
+                          xstate_offset(X86_XCR0_HI_ZMM_POS) +
+                          xstate_size(X86_XCR0_HI_ZMM_POS));
     }
 
     if ( p->feat.pku )
     {
         xstates |= X86_XCR0_PKRU;
         xstate_size = max(xstate_size,
-                          xstate_offsets[X86_XCR0_PKRU_POS] +
-                          xstate_sizes[X86_XCR0_PKRU_POS]);
+                          xstate_offset(X86_XCR0_PKRU_POS) +
+                          xstate_size(X86_XCR0_PKRU_POS));
     }
 
     p->xstate.max_size  =  xstate_size;
@@ -218,8 +218,8 @@ static void recalculate_xstate(struct cp
         if ( !(xstates & curr_xstate) )
             continue;
 
-        p->xstate.comp[i].size   = xstate_sizes[i];
-        p->xstate.comp[i].offset = xstate_offsets[i];
+        p->xstate.comp[i].size   = xstate_size(i);
+        p->xstate.comp[i].offset = xstate_offset(i);
         p->xstate.comp[i].xss    = curr_xstate & XSTATE_XSAVES_ONLY;
         p->xstate.comp[i].align  = curr_xstate & xstate_align;
     }
@@ -531,10 +531,16 @@ static void __init calculate_hvm_def_pol
     x86_cpuid_policy_shrink_max_leaves(p);
 }
 
-void __init init_guest_cpuid(void)
+void __init init_host_cpuid(void)
 {
     calculate_raw_policy();
     calculate_host_policy();
+}
+
+void __init init_guest_cpuid(void)
+{
+    /* Do this a 2nd time to account for setup_{clear,force}_cpu_cap() uses. */
+    calculate_host_policy();
 
     if ( IS_ENABLED(CONFIG_PV) )
     {
--- a/xen/arch/x86/xstate.c
+++ b/xen/arch/x86/xstate.c
@@ -9,6 +9,7 @@
 #include <xen/percpu.h>
 #include <xen/sched.h>
 #include <xen/xvmalloc.h>
+#include <asm/cpuid.h>
 #include <asm/current.h>
 #include <asm/processor.h>
 #include <asm/hvm/support.h>
@@ -26,8 +27,6 @@ static u32 __read_mostly xsave_cntxt_siz
 /* A 64-bit bitmask of the XSAVE/XRSTOR features supported by processor. */
 u64 __read_mostly xfeature_mask;
 
-unsigned int *__read_mostly xstate_offsets;
-unsigned int *__read_mostly xstate_sizes;
 u64 __read_mostly xstate_align;
 static unsigned int __read_mostly xstate_features;
 
@@ -93,34 +92,19 @@ static int setup_xstate_features(bool bs
     unsigned int leaf, eax, ebx, ecx, edx;
 
     if ( bsp )
-    {
         xstate_features = flsl(xfeature_mask);
-        xstate_offsets = xzalloc_array(unsigned int, xstate_features);
-        if ( !xstate_offsets )
-            return -ENOMEM;
-
-        xstate_sizes = xzalloc_array(unsigned int, xstate_features);
-        if ( !xstate_sizes )
-            return -ENOMEM;
-    }
 
     for ( leaf = 2; leaf < xstate_features; leaf++ )
     {
-        if ( bsp )
-        {
-            cpuid_count(XSTATE_CPUID, leaf, &xstate_sizes[leaf],
-                        &xstate_offsets[leaf], &ecx, &edx);
-            if ( ecx & XSTATE_ALIGN64 )
-                __set_bit(leaf, &xstate_align);
-        }
+        cpuid_count(XSTATE_CPUID, leaf, &eax,
+                    &ebx, &ecx, &edx);
+        BUG_ON(eax != xstate_size(leaf));
+        BUG_ON(ebx != xstate_offset(leaf));
+
+        if ( bsp && (ecx & XSTATE_ALIGN64) )
+            __set_bit(leaf, &xstate_align);
         else
-        {
-            cpuid_count(XSTATE_CPUID, leaf, &eax,
-                        &ebx, &ecx, &edx);
-            BUG_ON(eax != xstate_sizes[leaf]);
-            BUG_ON(ebx != xstate_offsets[leaf]);
             BUG_ON(!(ecx & XSTATE_ALIGN64) != !test_bit(leaf, &xstate_align));
-        }
     }
 
     return 0;
@@ -150,7 +134,7 @@ static void setup_xstate_comp(uint16_t *
             if ( test_bit(i, &xstate_align) )
                 offset = ROUNDUP(offset, 64);
             comp_offsets[i] = offset;
-            offset += xstate_sizes[i];
+            offset += xstate_size(i);
         }
     }
     ASSERT(offset <= xsave_cntxt_size);
@@ -213,10 +197,10 @@ void expand_xsave_states(struct vcpu *v,
          * comp_offsets[] information, something is very broken.
          */
         BUG_ON(!comp_offsets[index]);
-        BUG_ON((xstate_offsets[index] + xstate_sizes[index]) > size);
+        BUG_ON((xstate_offset(index) + xstate_size(index)) > size);
 
-        memcpy(dest + xstate_offsets[index], src + comp_offsets[index],
-               xstate_sizes[index]);
+        memcpy(dest + xstate_offset(index), src + comp_offsets[index],
+               xstate_size(index));
 
         valid &= ~feature;
     }
@@ -279,10 +263,10 @@ void compress_xsave_states(struct vcpu *
          * comp_offset[] information, something is very broken.
          */
         BUG_ON(!comp_offsets[index]);
-        BUG_ON((xstate_offsets[index] + xstate_sizes[index]) > size);
+        BUG_ON((xstate_offset(index) + xstate_size(index)) > size);
 
-        memcpy(dest + comp_offsets[index], src + xstate_offsets[index],
-               xstate_sizes[index]);
+        memcpy(dest + comp_offsets[index], src + xstate_offset(index),
+               xstate_size(index));
 
         valid &= ~feature;
     }
@@ -516,8 +500,8 @@ int xstate_alloc_save_area(struct vcpu *
         unsigned int i;
 
         for ( size = 0, i = 2; i < xstate_features; ++i )
-            if ( size < xstate_sizes[i] )
-                size = xstate_sizes[i];
+            if ( size < xstate_size(i) )
+                size = xstate_size(i);
         size += XSTATE_AREA_MIN_SIZE;
     }
 
@@ -559,9 +543,9 @@ int xstate_update_save_area(struct vcpu
     for ( size = old = XSTATE_AREA_MIN_SIZE, i = 2; i < xstate_features; ++i )
     {
         if ( xcr0_max & (1ul << i) )
-            size = max(size, xstate_offsets[i] + xstate_sizes[i]);
+            size = max(size, xstate_offset(i) + xstate_size(i));
         if ( v->arch.xcr0_accum & (1ul << i) )
-            old = max(old, xstate_offsets[i] + xstate_sizes[i]);
+            old = max(old, xstate_offset(i) + xstate_size(i));
     }
 
     save_area = _xvrealloc(v->arch.xsave_area, size, __alignof(*save_area));
@@ -819,7 +803,7 @@ uint64_t read_bndcfgu(void)
               : "=m" (*xstate)
               : "a" (X86_XCR0_BNDCSR), "d" (0), "D" (xstate) );
 
-        bndcsr = (void *)xstate + xstate_offsets[X86_XCR0_BNDCSR_POS];
+        bndcsr = (void *)xstate + xstate_offset(X86_XCR0_BNDCSR_POS);
     }
 
     if ( cr0 & X86_CR0_TS )
--- a/xen/include/asm-x86/cpuid.h
+++ b/xen/include/asm-x86/cpuid.h
@@ -16,6 +16,7 @@
 extern const uint32_t known_features[FSCAPINTS];
 extern const uint32_t special_features[FSCAPINTS];
 
+void init_host_cpuid(void);
 void init_guest_cpuid(void);
 
 /*
--- a/xen/include/asm-x86/xstate.h
+++ b/xen/include/asm-x86/xstate.h
@@ -44,8 +44,9 @@ extern uint32_t mxcsr_mask;
 
 extern u64 xfeature_mask;
 extern u64 xstate_align;
-extern unsigned int *xstate_offsets;
-extern unsigned int *xstate_sizes;
+
+#define xstate_offset(n) (raw_cpuid_policy.xstate.comp[n].offset)
+#define xstate_size(n)   (raw_cpuid_policy.xstate.comp[n].size)
 
 /* extended state save area */
 struct __attribute__((aligned (64))) xsave_struct



  parent reply	other threads:[~2021-04-22 14:46 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-22 14:38 [PATCH v3 00/22] xvmalloc() / x86 xstate area / x86 CPUID / AMX+XFD Jan Beulich
2021-04-22 14:43 ` [PATCH v3 01/22] mm: introduce xvmalloc() et al and use for grant table allocations Jan Beulich
2021-05-03 11:31   ` Roger Pau Monné
2021-05-03 13:50     ` Jan Beulich
2021-05-03 14:54       ` Roger Pau Monné
2021-05-03 15:21         ` Jan Beulich
2021-05-03 16:39           ` Roger Pau Monné
2021-04-22 14:44 ` [PATCH v3 02/22] x86/xstate: use xvzalloc() for save area allocation Jan Beulich
2021-05-05 13:29   ` Roger Pau Monné
2021-04-22 14:44 ` [PATCH v3 03/22] x86/xstate: re-size save area when CPUID policy changes Jan Beulich
2021-05-03 13:57   ` Andrew Cooper
2021-05-03 14:22     ` Jan Beulich
2021-05-11 16:41       ` Andrew Cooper
2021-05-17  7:33         ` Jan Beulich
2021-04-22 14:45 ` [PATCH v3 04/22] x86/xstate: re-use valid_xcr0() for boot-time checks Jan Beulich
2021-05-03 11:53   ` Andrew Cooper
2021-04-22 14:45 ` Jan Beulich [this message]
2021-05-03 16:10   ` [PATCH v3 05/22] x86/xstate: drop xstate_offsets[] and xstate_sizes[] Andrew Cooper
2021-05-04  7:57     ` Jan Beulich
2021-04-22 14:46 ` [PATCH v3 06/22] x86/xstate: replace xsave_cntxt_size and drop XCNTXT_MASK Jan Beulich
2021-04-22 14:47 ` [PATCH v3 07/22] x86/xstate: avoid accounting for unsupported components Jan Beulich
2021-04-22 14:47 ` [PATCH v3 08/22] x86: use xvmalloc() for extended context buffer allocations Jan Beulich
2021-04-22 14:48 ` [PATCH v3 09/22] x86/xstate: enable AMX components Jan Beulich
2021-04-22 14:50 ` [PATCH v3 10/22] x86/CPUID: adjust extended leaves out of range clearing Jan Beulich
2021-04-22 14:50 ` [PATCH v3 11/22] x86/CPUID: move bounding of max_{,sub}leaf fields to library code Jan Beulich
2021-04-22 14:51 ` [PATCH v3 12/22] x86/CPUID: enable AMX leaves Jan Beulich
2021-04-22 14:52 ` [PATCH v3 13/22] x86: XFD enabling Jan Beulich
2021-04-22 14:53 ` [PATCH v3 14/22] x86emul: introduce X86EMUL_FPU_{tilecfg,tile} Jan Beulich
2021-04-22 14:53 ` [PATCH v3 15/22] x86emul: support TILERELEASE Jan Beulich
2021-04-22 14:53 ` [PATCH v3 16/22] x86: introduce struct for TILECFG register Jan Beulich
2021-04-22 14:54 ` [PATCH v3 17/22] x86emul: support {LD,ST}TILECFG Jan Beulich
2021-04-22 14:55 ` [PATCH v3 18/22] x86emul: support TILEZERO Jan Beulich
2021-04-22 14:55 ` [PATCH v3 19/22] x86emul: support TILELOADD{,T1} and TILESTORE Jan Beulich
2021-04-22 15:06   ` Jan Beulich
2021-04-22 15:11     ` Jan Beulich
2021-04-26  7:12       ` Paul Durrant
2021-04-29  9:40         ` Jan Beulich
2021-04-22 14:56 ` [PATCH v3 20/22] x86emul: support tile multiplication insns Jan Beulich
2021-04-22 14:57 ` [PATCH v3 21/22] x86emul: test AMX insns Jan Beulich
2021-04-22 14:57 ` [PATCH v3 22/22] x86: permit guests to use AMX and XFD 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=434705ef-1c34-581d-b956-2322b4413232@suse.com \
    --to=jbeulich@suse.com \
    --cc=andrew.cooper3@citrix.com \
    --cc=george.dunlap@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.