lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-Id: <20241128002247.26726-3-ricardo.neri-calderon@linux.intel.com>
Date: Wed, 27 Nov 2024 16:22:47 -0800
From: Ricardo Neri <ricardo.neri-calderon@...ux.intel.com>
To: x86@...nel.org
Cc: Andreas Herrmann <aherrmann@...e.com>,
	Catalin Marinas <catalin.marinas@....com>,
	Chen Yu <yu.c.chen@...el.com>,
	Len Brown <len.brown@...el.com>,
	Radu Rendec <rrendec@...hat.com>,
	Pierre Gondois <Pierre.Gondois@....com>,
	Pu Wen <puwen@...on.cn>,
	"Rafael J. Wysocki" <rafael.j.wysocki@...el.com>,
	Sudeep Holla <sudeep.holla@....com>,
	Srinivas Pandruvada <srinivas.pandruvada@...ux.intel.com>,
	Will Deacon <will@...nel.org>,
	Zhang Rui <rui.zhang@...el.com>,
	Nikolay Borisov <nik.borisov@...e.com>,
	Huang Ying <ying.huang@...el.com>,
	Ricardo Neri <ricardo.neri@...el.com>,
	linux-kernel@...r.kernel.org
Subject: [PATCH v8 2/2] x86/cacheinfo: Delete global num_cache_leaves

Linux remembers cpu_cachinfo::num_leaves per CPU, but x86 initializes all
CPUs from the same global "num_cache_leaves".

This is erroneous on systems such as Meteor Lake, where each CPU has a
distinct num_leaves value. Delete the global "num_cache_leaves" and
initialize num_leaves on each CPU.

init_cache_level() no longer needs to set num_leaves. Also, it never had to
set num_levels as it is unnecessary in x86. Keep checking for zero cache
leaves. Such condition indicates a bug.

Reviewed-by: Andreas Herrmann <aherrmann@...e.de>
Reviewed-by: Len Brown <len.brown@...el.com>
Reviewed-by: Nikolay Borisov <nik.borisov@...e.com>
Tested-by: Andreas Herrmann <aherrmann@...e.de>
Signed-off-by: Ricardo Neri <ricardo.neri-calderon@...ux.intel.com>
---
Cc: Andreas Herrmann <aherrmann@...e.com>
Cc: Catalin Marinas <catalin.marinas@....com>
Cc: Chen Yu <yu.c.chen@...el.com>
Cc: Huang Ying <ying.huang@...el.com>
Cc: Len Brown <len.brown@...el.com>
Cc: Nikolay Borisov <nik.borisov@...e.com>
Cc: Radu Rendec <rrendec@...hat.com>
Cc: Pierre Gondois <Pierre.Gondois@....com>
Cc: Pu Wen <puwen@...on.cn>
Cc: "Rafael J. Wysocki" <rafael.j.wysocki@...el.com>
Cc: Sudeep Holla <sudeep.holla@....com>
Cc: Srinivas Pandruvada <srinivas.pandruvada@...ux.intel.com>
Cc: Will Deacon <will@...nel.org>
Cc: Zhang Rui <rui.zhang@...el.com>
Cc: linux-arm-kernel@...ts.infradead.org
Cc: stable@...r.kernel.org # 6.3+
---
After this change, all CPUs will traverse CPUID leaf 0x4 when booted for
the first time. On systems with symmetric cache topologies this is
useless work.

Creating a list of processor models that have asymmetric cache topologies
was considered. The burden of maintaining such list would outweigh the
performance benefit of skipping this extra step.
---
Changes since v7:
 * Removed an ugly linebreak. (Boris)
 * Folded patch 3/3 into 2/3 as both patches deal with init_cache_level().
   (Boris)
 * Removed the [set,get]_num_cache_leaves() wrappers. Instead, use the
   existing get_cpu_cacheinfo(). (Boris)
 * Future-proof init_cache_level() for cases in which cpu_cacheinfo::
   num_leaves is still zero afer cache info initialization.

Changes since v6:
 * None

Changes since v5:
 * Reordered the arguments of set_num_cache_leaves() for readability.
   (Nikolay)
 * Added Reviewed-by tag from Nikolay and Andreas. Thanks!
 * Added Tested-by tag from Andreas. Thanks!

Changes since v4:
 * None

Changes since v3:
 * Rebased on v6.7-rc5.

Changes since v2:
 * None

Changes since v1:
 * Do not make num_cache_leaves a per-CPU variable. Instead, reuse the
   existing per-CPU ci_cpu_cacheinfo variable. (Dave Hansen)
---
 arch/x86/kernel/cpu/cacheinfo.c | 41 +++++++++++++++------------------
 1 file changed, 18 insertions(+), 23 deletions(-)

diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index 392d09c936d6..95e38ab98a72 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -178,8 +178,6 @@ struct _cpuid4_info_regs {
 	struct amd_northbridge *nb;
 };
 
-static unsigned short num_cache_leaves;
-
 /* AMD doesn't have CPUID4. Emulate it here to report the same
    information to the user.  This makes some assumptions about the machine:
    L2 not shared, no SMT etc. that is currently true on AMD CPUs.
@@ -718,19 +716,21 @@ void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c)
 void init_amd_cacheinfo(struct cpuinfo_x86 *c)
 {
 
+	unsigned int cpu = c->cpu_index;
+
 	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
-		num_cache_leaves = find_num_cache_leaves(c);
+		get_cpu_cacheinfo(cpu)->num_leaves = find_num_cache_leaves(c);
 	} else if (c->extended_cpuid_level >= 0x80000006) {
 		if (cpuid_edx(0x80000006) & 0xf000)
-			num_cache_leaves = 4;
+			get_cpu_cacheinfo(cpu)->num_leaves = 4;
 		else
-			num_cache_leaves = 3;
+			get_cpu_cacheinfo(cpu)->num_leaves = 3;
 	}
 }
 
 void init_hygon_cacheinfo(struct cpuinfo_x86 *c)
 {
-	num_cache_leaves = find_num_cache_leaves(c);
+	get_cpu_cacheinfo(c->cpu_index)->num_leaves = find_num_cache_leaves(c);
 }
 
 void init_intel_cacheinfo(struct cpuinfo_x86 *c)
@@ -742,19 +742,18 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
 	unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb;
 
 	if (c->cpuid_level > 3) {
-		static int is_initialized;
-
-		if (is_initialized == 0) {
-			/* Init num_cache_leaves from boot CPU */
-			num_cache_leaves = find_num_cache_leaves(c);
-			is_initialized++;
-		}
+		/*
+		 * There should be at least one leaf. A non-zero value means
+		 * that the number of leaves has been initialized.
+		 */
+		if (!get_cpu_cacheinfo(c->cpu_index)->num_leaves)
+			get_cpu_cacheinfo(c->cpu_index)->num_leaves = find_num_cache_leaves(c);
 
 		/*
 		 * Whenever possible use cpuid(4), deterministic cache
 		 * parameters cpuid leaf to find the cache details
 		 */
-		for (i = 0; i < num_cache_leaves; i++) {
+		for (i = 0; i < get_cpu_cacheinfo(c->cpu_index)->num_leaves; i++) {
 			struct _cpuid4_info_regs this_leaf = {};
 			int retval;
 
@@ -790,14 +789,14 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
 	 * Don't use cpuid2 if cpuid4 is supported. For P4, we use cpuid2 for
 	 * trace cache
 	 */
-	if ((num_cache_leaves == 0 || c->x86 == 15) && c->cpuid_level > 1) {
+	if ((!get_cpu_cacheinfo(c->cpu_index)->num_leaves || c->x86 == 15) && c->cpuid_level > 1) {
 		/* supports eax=2  call */
 		int j, n;
 		unsigned int regs[4];
 		unsigned char *dp = (unsigned char *)regs;
 		int only_trace = 0;
 
-		if (num_cache_leaves != 0 && c->x86 == 15)
+		if (get_cpu_cacheinfo(c->cpu_index)->num_leaves && c->x86 == 15)
 			only_trace = 1;
 
 		/* Number of times to iterate */
@@ -991,14 +990,10 @@ static void ci_leaf_init(struct cacheinfo *this_leaf,
 
 int init_cache_level(unsigned int cpu)
 {
-	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
-
-	if (!num_cache_leaves)
+	/* There should be at least one leaf. */
+	if (!get_cpu_cacheinfo(cpu)->num_leaves)
 		return -ENOENT;
-	if (!this_cpu_ci)
-		return -EINVAL;
-	this_cpu_ci->num_levels = 3;
-	this_cpu_ci->num_leaves = num_cache_leaves;
+
 	return 0;
 }
 
-- 
2.34.1


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ