From: Dave Hansen <dave.hansen@linux.intel.com>
To: linux-kernel@vger.kernel.org
Cc: jgross@suse.com,tglx@linutronix.de,x86@kernel.org,bp@alien8.de,Dave
Hansen <dave.hansen@linux.intel.com>
Subject: [PATCH 1/4] x86/cpu: Add and use new CPUID region helper
Date: Fri, 22 Mar 2024 10:56:30 -0700 [thread overview]
Message-ID: <20240322175630.72CE974F@davehans-spike.ostc.intel.com> (raw)
In-Reply-To: <20240322175629.01E8B39D@davehans-spike.ostc.intel.com>
From: Dave Hansen <dave.hansen@linux.intel.com>
There are some (before now) unwritten rules about CPUID "regions".
Basically, there is a 32-bit address space of CPUID leaves. The
top 16 bits address a "region" and the first leaf in a region
is special.
The kernel only has a few spots that care about this, but it's
rather hard to make sense of the code as is.
Add a helper that explains regions. Use it where applicable.
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Juergen Gross <jgross@suse.com>
---
b/arch/x86/include/asm/cpuid.h | 59 ++++++++++++++++++++++++++++++++++++++
b/arch/x86/kernel/cpu/common.c | 13 +++-----
b/arch/x86/kernel/cpu/transmeta.c | 9 +----
b/arch/x86/xen/enlighten_pv.c | 9 +----
4 files changed, 69 insertions(+), 21 deletions(-)
diff -puN arch/x86/include/asm/cpuid.h~cpuid-regions arch/x86/include/asm/cpuid.h
--- a/arch/x86/include/asm/cpuid.h~cpuid-regions 2024-03-18 15:12:20.676308753 -0700
+++ b/arch/x86/include/asm/cpuid.h 2024-03-22 09:17:13.296507986 -0700
@@ -168,4 +168,63 @@ static inline uint32_t hypervisor_cpuid_
return 0;
}
+/*
+ * By convention, CPUID is broken up into regions which each
+ * have 2^16 leaves. EAX in the first leaf of each valid
+ * region returns the maximum valid leaf in that region.
+ *
+ * The regions can be thought of as being vendor-specific
+ * areas of CPUID, but that's imprecise because everybody
+ * implements the "Intel" region and Intel implements the
+ * AMD region. There are a few well-known regions:
+ * - Intel (0x0000)
+ * - AMD (0x8000)
+ * - Transmeta (0x8086)
+ * - Centaur (0xC000)
+ *
+ * Consider a CPU that where the maximum leaf in the Transmeta
+ * region is 2. On such a CPU, leaf 0x80860000 would contain:
+ * EAX==0x80860002.
+ * region-^^^^
+ * max leaf-^^^^
+ */
+static inline u32 cpuid_region_max_leaf(u16 region)
+{
+ u32 eax = cpuid_eax(region << 16);
+
+ /*
+ * An unsupported region may return data from the last
+ * "basic" leaf, which is essentially garbage. Avoid
+ * mistaking basic leaf data for region data.
+ *
+ * Note: this is not perfect. It is theoretically
+ * possible for the last basic leaf to _resemble_ a
+ * valid first leaf from a region that doesn't exist.
+ * But Intel at least seems to pad out the basic region
+ * with 0's, possibly to avoid this.
+ */
+ if ((eax >> 16) != region)
+ return 0;
+
+ return eax;
+}
+
+/* Returns true if the leaf exists and @value was populated */
+static inline bool get_cpuid_region_leaf(u32 leaf, enum cpuid_regs_idx reg,
+ u32 *value)
+{
+ u16 region = leaf >> 16;
+ u32 regs[4];
+
+ if (cpuid_region_max_leaf(region) < leaf)
+ return false;
+
+ cpuid(leaf, ®s[CPUID_EAX], ®s[CPUID_EBX],
+ ®s[CPUID_ECX], ®s[CPUID_EDX]);
+
+ *value = regs[reg];
+
+ return true;
+}
+
#endif /* _ASM_X86_CPUID_H */
diff -puN arch/x86/kernel/cpu/common.c~cpuid-regions arch/x86/kernel/cpu/common.c
--- a/arch/x86/kernel/cpu/common.c~cpuid-regions 2024-03-18 15:12:20.676308753 -0700
+++ b/arch/x86/kernel/cpu/common.c 2024-03-18 15:12:20.684309023 -0700
@@ -1049,16 +1049,13 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
}
/* AMD-defined flags: level 0x80000001 */
- eax = cpuid_eax(0x80000000);
- c->extended_cpuid_level = eax;
+ c->extended_cpuid_level = cpuid_region_max_leaf(0x8000);
- if ((eax & 0xffff0000) == 0x80000000) {
- if (eax >= 0x80000001) {
- cpuid(0x80000001, &eax, &ebx, &ecx, &edx);
+ if (c->extended_cpuid_level >= 0x80000001) {
+ cpuid(0x80000001, &eax, &ebx, &ecx, &edx);
- c->x86_capability[CPUID_8000_0001_ECX] = ecx;
- c->x86_capability[CPUID_8000_0001_EDX] = edx;
- }
+ c->x86_capability[CPUID_8000_0001_ECX] = ecx;
+ c->x86_capability[CPUID_8000_0001_EDX] = edx;
}
if (c->extended_cpuid_level >= 0x80000007) {
diff -puN arch/x86/kernel/cpu/transmeta.c~cpuid-regions arch/x86/kernel/cpu/transmeta.c
--- a/arch/x86/kernel/cpu/transmeta.c~cpuid-regions 2024-03-18 15:12:20.680308889 -0700
+++ b/arch/x86/kernel/cpu/transmeta.c 2024-03-18 15:12:20.684309023 -0700
@@ -9,14 +9,9 @@
static void early_init_transmeta(struct cpuinfo_x86 *c)
{
- u32 xlvl;
-
/* Transmeta-defined flags: level 0x80860001 */
- xlvl = cpuid_eax(0x80860000);
- if ((xlvl & 0xffff0000) == 0x80860000) {
- if (xlvl >= 0x80860001)
- c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001);
- }
+ get_cpuid_region_leaf(0x80860001, CPUID_EDX,
+ &c->x86_capability[CPUID_8086_0001_EDX]);
}
static void init_transmeta(struct cpuinfo_x86 *c)
diff -puN arch/x86/xen/enlighten_pv.c~cpuid-regions arch/x86/xen/enlighten_pv.c
--- a/arch/x86/xen/enlighten_pv.c~cpuid-regions 2024-03-18 15:12:20.680308889 -0700
+++ b/arch/x86/xen/enlighten_pv.c 2024-03-22 09:15:33.280428290 -0700
@@ -141,16 +141,13 @@ static void __init xen_set_mtrr_data(voi
};
unsigned int reg;
unsigned long mask;
- uint32_t eax, width;
+ uint32_t width;
static struct mtrr_var_range var[MTRR_MAX_VAR_RANGES] __initdata;
/* Get physical address width (only 64-bit cpus supported). */
width = 36;
- eax = cpuid_eax(0x80000000);
- if ((eax >> 16) == 0x8000 && eax >= 0x80000008) {
- eax = cpuid_eax(0x80000008);
- width = eax & 0xff;
- }
+ /* Will overwrite 'width' if available in CPUID: */
+ get_cpuid_region_leaf(0x80000008, CPUID_EAX, &width);
for (reg = 0; reg < MTRR_MAX_VAR_RANGES; reg++) {
op.u.read_memtype.reg = reg;
_
next prev parent reply other threads:[~2024-03-22 17:56 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-03-22 17:56 [PATCH 0/4] x86: Add CPUID region helper and clarify Xen startup Dave Hansen
2024-03-22 17:56 ` Dave Hansen [this message]
2024-03-24 4:38 ` [PATCH 1/4] x86/cpu: Add and use new CPUID region helper Ingo Molnar
2024-03-25 12:24 ` Huang, Kai
2024-04-02 17:13 ` Dave Hansen
2024-04-03 10:33 ` Huang, Kai
2024-04-04 23:35 ` Chang S. Bae
2024-03-22 17:56 ` [PATCH 2/4] perf/x86/ibs: Use " Dave Hansen
2024-03-22 17:56 ` [PATCH 3/4] x86/boot: Explicitly pass NX enabling status Dave Hansen
2024-03-25 12:04 ` Huang, Kai
2024-03-22 17:56 ` [PATCH 4/4] x86/xen: Enumerate NX from CPUID directly Dave Hansen
2024-04-03 15:35 [PATCH 0/4] [v2] x86: Add CPUID region helper and clarify Xen startup Dave Hansen
2024-04-03 15:35 ` [PATCH 1/4] x86/cpu: Add and use new CPUID region helper Dave Hansen
2024-04-04 9:04 ` Jürgen Groß
2024-04-08 16:25 ` Borislav Petkov
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=20240322175630.72CE974F@davehans-spike.ostc.intel.com \
--to=dave.hansen@linux.intel.com \
--cc=bp@alien8.de \
--cc=jgross@suse.com \
--cc=linux-kernel@vger.kernel.org \
--cc=tglx@linutronix.de \
--cc=x86@kernel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®