From nobody Thu Dec 18 13:02:26 2025 Received: from galois.linutronix.de (Galois.linutronix.de [193.142.43.55]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id A38C027FB31 for ; Tue, 6 May 2025 05:05:44 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=193.142.43.55 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1746507946; cv=none; b=O6P8X4wd6pGEN0tvnGKPkC3p1aubSx0wg+lpRnAHfPd+yNFD+4QaT+hE/wEPTew3YiaDR0PP0uzDSA6+2aBpfJduwd81e/JWnZAwi6cc9ZNT+65O3q2ciZ7ZbR47RXINizzBro4c5YS3ogOuq1c88pQcCJZsSyuJ1tVt4+vlnHs= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1746507946; c=relaxed/simple; bh=1XN3phajobW15W2zFz3vmQIWRaHtliNoU9pIjl5O6t8=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=InkriWCsbCH0ZL0/qIDRQE0CbXsol8WIikN34ynQbcRHTLcITYCOi9dl4CMPADmh331Y3o/lFYeYwOrdZcOmEp32zVHEaPFQG9QzMA/CS5Xwnct/0Hqe40J+AqCYNs3ClzdYnDW/JrACZUOKnXOkNh4TdpGC7T/4WRK94pBS4zg= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linutronix.de; spf=pass smtp.mailfrom=linutronix.de; dkim=pass (2048-bit key) header.d=linutronix.de header.i=@linutronix.de header.b=QDyR6YRU; dkim=permerror (0-bit key) header.d=linutronix.de header.i=@linutronix.de header.b=r1gMDaMX; arc=none smtp.client-ip=193.142.43.55 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linutronix.de Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linutronix.de Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=linutronix.de header.i=@linutronix.de header.b="QDyR6YRU"; dkim=permerror (0-bit key) header.d=linutronix.de header.i=@linutronix.de header.b="r1gMDaMX" From: "Ahmed S. Darwish" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linutronix.de; s=2020; t=1746507943; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=Sd0POY+V33Qa9VXLCiDdOhKdkmDV4YC4IwROUD7bFpY=; b=QDyR6YRUSHdH9Fmqsr/xodjQ/bLHvUMpevHpZUtP4SBmN2NA2MZyRq/gT8eIAB3gEwPf1V 3YERHnulhamik+fu699Tps+PWUrqk6tqcCcd7S80Ps/xl3J3JI5k17mQBtV2CBXNvKS/Rw Xax4zQGPP944i7rUjs1hzX90PS4P+JM5Dab2fgmrILG8oce2h+0OZTAvNqG5gHLQT9v3Od VZOdwXLGSs91tg/3Q2Q6u7Q8QKihj0/Xu/3c/kMUnnEOqzQW3cFfAbIhqAspyoOz7Js/lV MfnaZFftUUBboF1v1sMaLlIccYJ5BWVBE2ORzAW4IPJ4EMr/KNt98i4KEWeMLQ== DKIM-Signature: v=1; a=ed25519-sha256; c=relaxed/relaxed; d=linutronix.de; s=2020e; t=1746507943; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=Sd0POY+V33Qa9VXLCiDdOhKdkmDV4YC4IwROUD7bFpY=; b=r1gMDaMX8yt2EkAK4kQfGTeqtO7O/We0bbo3c5tkbaXBldFeD6F0nXJpZQXeQItcOLFJrH EzvsvUatFXwI+2DA== To: Ingo Molnar , Borislav Petkov , Dave Hansen Cc: Thomas Gleixner , Andrew Cooper , "H. Peter Anvin" , John Ogness , x86@kernel.org, x86-cpuid@lists.linux.dev, LKML , "Ahmed S. Darwish" Subject: [PATCH v1 19/26] x86/cacheinfo: Use scanned CPUID(0x4) Date: Tue, 6 May 2025 07:04:30 +0200 Message-ID: <20250506050437.10264-20-darwi@linutronix.de> In-Reply-To: <20250506050437.10264-1-darwi@linutronix.de> References: <20250506050437.10264-1-darwi@linutronix.de> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" Refactor the Intel CPUID(0x4) cacheinfo logic to use scanned CPUID access instead of issuing direct CPUID queries. Since scanned CPUID access requires a cpuinfo_x86 reference, propagate it down from 's populate_cache_leaves() to all the relevant functions. Use the scanned CPUID access macro: cpudata_cpuid_nr_entries(c, 0x4) to determine the number of Intel CPUID(0x4) cache leaves instead of calling find_num_cache_leaves(), which issues direct CPUID queries. Given that find_num_cache_leaves() is no longer needed for Intel code paths, make it AMD-specific. Rename it to amd_find_num_cache_leaves() and remove its Intel CPUID(0x4) logic. Adjust AMD paths accordingly. Signed-off-by: Ahmed S. Darwish --- arch/x86/kernel/cpu/cacheinfo.c | 40 ++++++++++++++++----------------- 1 file changed, 19 insertions(+), 21 deletions(-) diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinf= o.c index 665f3b187964..9de75c8b76ff 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -252,38 +252,35 @@ static int amd_fill_cpuid4_info(int index, struct _cp= uid4_info *id4) return cpuid4_info_fill_done(id4, eax, ebx, ecx); } =20 -static int intel_fill_cpuid4_info(int index, struct _cpuid4_info *id4) +static int intel_fill_cpuid4_info(struct cpuinfo_x86 *c, int index, struct= _cpuid4_info *id4) { - union _cpuid4_leaf_eax eax; - union _cpuid4_leaf_ebx ebx; - union _cpuid4_leaf_ecx ecx; - u32 ignored; + const struct cpuid_regs *regs =3D cpudata_cpuid_index_regs(c, 0x4, index); =20 - cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &ignored); - - return cpuid4_info_fill_done(id4, eax, ebx, ecx); + return cpuid4_info_fill_done(id4, + (union _cpuid4_leaf_eax)(regs->eax), + (union _cpuid4_leaf_ebx)(regs->ebx), + (union _cpuid4_leaf_ecx)(regs->ecx)); } =20 -static int fill_cpuid4_info(int index, struct _cpuid4_info *id4) +static int fill_cpuid4_info(struct cpuinfo_x86 *c, int index, struct _cpui= d4_info *id4) { u8 cpu_vendor =3D boot_cpu_data.x86_vendor; =20 return (cpu_vendor =3D=3D X86_VENDOR_AMD || cpu_vendor =3D=3D X86_VENDOR_= HYGON) ? amd_fill_cpuid4_info(index, id4) : - intel_fill_cpuid4_info(index, id4); + intel_fill_cpuid4_info(c, index, id4); } =20 -static int find_num_cache_leaves(struct cpuinfo_x86 *c) +static int amd_find_num_cache_leaves(struct cpuinfo_x86 *c) { - unsigned int eax, ebx, ecx, edx, op; + unsigned int eax, ebx, ecx, edx; union _cpuid4_leaf_eax cache_eax; int i =3D -1; =20 - /* Do a CPUID(op) loop to calculate num_cache_leaves */ - op =3D (c->x86_vendor =3D=3D X86_VENDOR_AMD || c->x86_vendor =3D=3D X86_V= ENDOR_HYGON) ? 0x8000001d : 4; + /* Do a CPUID(0x8000001d) loop to calculate num_cache_leaves */ do { ++i; - cpuid_count(op, i, &eax, &ebx, &ecx, &edx); + cpuid_count(0x8000001d, i, &eax, &ebx, &ecx, &edx); cache_eax.full =3D eax; } while (cache_eax.split.type !=3D CTYPE_NULL); return i; @@ -313,7 +310,7 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, u= 16 die_id) * of threads sharing the L3 cache. */ u32 eax, ebx, ecx, edx, num_sharing_cache =3D 0; - u32 llc_index =3D find_num_cache_leaves(c) - 1; + u32 llc_index =3D amd_find_num_cache_leaves(c) - 1; =20 cpuid_count(0x8000001d, llc_index, &eax, &ebx, &ecx, &edx); if (eax) @@ -344,7 +341,7 @@ void init_amd_cacheinfo(struct cpuinfo_x86 *c) struct cpu_cacheinfo *ci =3D get_cpu_cacheinfo(c->cpu_index); =20 if (boot_cpu_has(X86_FEATURE_TOPOEXT)) - ci->num_leaves =3D find_num_cache_leaves(c); + ci->num_leaves =3D amd_find_num_cache_leaves(c); else if (c->extended_cpuid_level >=3D 0x80000006) ci->num_leaves =3D (cpuid_edx(0x80000006) & 0xf000) ? 4 : 3; } @@ -353,7 +350,7 @@ void init_hygon_cacheinfo(struct cpuinfo_x86 *c) { struct cpu_cacheinfo *ci =3D get_cpu_cacheinfo(c->cpu_index); =20 - ci->num_leaves =3D find_num_cache_leaves(c); + ci->num_leaves =3D amd_find_num_cache_leaves(c); } =20 static void intel_cacheinfo_done(struct cpuinfo_x86 *c, unsigned int l3, @@ -425,7 +422,7 @@ static bool intel_cacheinfo_0x4(struct cpuinfo_x86 *c) * that the number of leaves has been previously initialized. */ if (!ci->num_leaves) - ci->num_leaves =3D find_num_cache_leaves(c); + ci->num_leaves =3D cpudata_cpuid_nr_entries(c, 0x4); =20 if (!ci->num_leaves) return false; @@ -434,7 +431,7 @@ static bool intel_cacheinfo_0x4(struct cpuinfo_x86 *c) struct _cpuid4_info id4 =3D {}; int ret; =20 - ret =3D intel_fill_cpuid4_info(i, &id4); + ret =3D intel_fill_cpuid4_info(c, i, &id4); if (ret < 0) continue; =20 @@ -618,13 +615,14 @@ int populate_cache_leaves(unsigned int cpu) { struct cpu_cacheinfo *this_cpu_ci =3D get_cpu_cacheinfo(cpu); struct cacheinfo *ci =3D this_cpu_ci->info_list; + struct cpuinfo_x86 *c =3D &cpu_data(cpu); u8 cpu_vendor =3D boot_cpu_data.x86_vendor; struct amd_northbridge *nb =3D NULL; struct _cpuid4_info id4 =3D {}; int idx, ret; =20 for (idx =3D 0; idx < this_cpu_ci->num_leaves; idx++) { - ret =3D fill_cpuid4_info(idx, &id4); + ret =3D fill_cpuid4_info(c, idx, &id4); if (ret) return ret; =20 --=20 2.49.0