Linux Documentation
 help / color / mirror / Atom feed
From: Pasha Tatashin <pasha.tatashin@soleen.com>
To: linux-kselftest@vger.kernel.org, legion@kernel.org,
	kees@kernel.org, will@kernel.org, ruanjinjie@huawei.com,
	atomlin@atomlin.com, rppt@kernel.org, jani.nikula@intel.com,
	hamzamahfooz@linux.microsoft.com, joey.gouly@arm.com,
	tglx@kernel.org, nsc@kernel.org, alexandre.chartre@oracle.com,
	james.morse@arm.com, dianders@chromium.org, bp@alien8.de,
	jpoimboe@kernel.org, shuah@kernel.org, catalin.marinas@arm.com,
	linux-kbuild@vger.kernel.org, linux-arch@vger.kernel.org,
	kvmarm@lists.linux.dev, jaredwhite@microsoft.com,
	johan@kernel.org, pbonzini@redhat.com, mingo@redhat.com,
	linux-mm@kvack.org, seanjc@google.com, mark.rutland@arm.com,
	vdonnefort@google.com, tarunsahu@google.com, gshan@redhat.com,
	skhan@linuxfoundation.org, linux-doc@vger.kernel.org,
	xur@google.com, djbw@kernel.org, oupton@kernel.org,
	nogikh@google.com, sumitg@nvidia.com,
	linux-kernel@vger.kernel.org, zengheng4@huawei.com,
	peterz@infradead.org, corbet@lwn.net, suzuki.poulose@arm.com,
	luto@kernel.org, hpa@zytor.com, zhangpengjie2@huawei.com,
	x86@kernel.org, yuzenghui@huawei.com, jic23@kernel.org,
	ardb@kernel.org, pasha.tatashin@soleen.com, petr.pavlu@suse.com,
	ryan.roberts@arm.com, kexec@lists.infradead.org,
	pratyush@kernel.org, dave.hansen@linux.intel.com,
	rdunlap@infradead.org, kvm@vger.kernel.org, fuad.tabba@linux.dev,
	maz@kernel.org, mbenes@suse.cz, jgross@suse.com,
	seiden@linux.ibm.com, pierre.gondois@arm.com, song@kernel.org,
	nathan@kernel.org, pmladek@suse.com, graf@amazon.com,
	chao.gao@intel.com, zhenglifeng1@huawei.com, arnd@arndb.de,
	sidnayyar@google.com, linux-arm-kernel@lists.infradead.org,
	vladimir.murzin@arm.com, kas@kernel.org
Subject: [RFC PATCH 04/46] x86/mm/ident_map: Add force_pte to support 4K PTE identity mappings
Date: Sun, 20 Sep 2026 15:36:08 -0400	[thread overview]
Message-ID: <20260920193650.3373435-5-pasha.tatashin@soleen.com> (raw)
In-Reply-To: <20260920193650.3373435-1-pasha.tatashin@soleen.com>

Extend kernel_ident_mapping_init() with ident_pte_init() and a force_pte
flag in struct x86_mapping_info so callers can request 4K PTE leaf
mappings instead of 2M PMD or 1G PUD leaves.

Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
---
 arch/x86/include/asm/init.h |  3 +-
 arch/x86/mm/ident_map.c     | 72 ++++++++++++++++++++++++++++++++-----
 2 files changed, 65 insertions(+), 10 deletions(-)

diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h
index 01ccdd168df0..d9caed494e7d 100644
--- a/arch/x86/include/asm/init.h
+++ b/arch/x86/include/asm/init.h
@@ -6,10 +6,11 @@ struct x86_mapping_info {
 	void *(*alloc_pgt_page)(void *); /* allocate buf for page table */
 	void (*free_pgt_page)(void *, void *); /* free buf for page table */
 	void *context;			 /* context for alloc_pgt_page */
-	unsigned long page_flag;	 /* page flag for PMD or PUD entry */
+	unsigned long page_flag;	 /* page flag for PTE, PMD or PUD entry */
 	unsigned long offset;		 /* ident mapping offset */
 	bool direct_gbpages;		 /* PUD level 1GB page support */
 	unsigned long kernpg_flag;	 /* kernel pagetable flag override */
+	bool force_pte;			 /* force 4K PTE mappings */
 };
 
 int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index 5a15bffe6574..83013513ba94 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -77,24 +77,73 @@ void kernel_ident_mapping_free(struct x86_mapping_info *info, pgd_t *pgd)
 	info->free_pgt_page(pgd, info->context);
 }
 
-static void ident_pmd_init(struct x86_mapping_info *info, pmd_t *pmd_page,
-			   unsigned long addr, unsigned long end)
+static int ident_pte_init(struct x86_mapping_info *info, pte_t *pte_page,
+			  unsigned long addr, unsigned long end)
 {
-	addr &= PMD_MASK;
-	for (; addr < end; addr += PMD_SIZE) {
+	addr &= PAGE_MASK;
+	for (; addr < end; addr += PAGE_SIZE) {
+		pte_t *pte = pte_page + pte_index(addr);
+
+		if (pte_present(*pte))
+			continue;
+
+		set_pte(pte, __pte(((addr - info->offset) | info->page_flag) & ~_PAGE_PSE));
+	}
+
+	return 0;
+}
+
+static int ident_pmd_init(struct x86_mapping_info *info, pmd_t *pmd_page,
+			  unsigned long addr, unsigned long end)
+{
+	unsigned long next;
+	int result;
+
+	for (; addr < end; addr = next) {
 		pmd_t *pmd = pmd_page + pmd_index(addr);
+		pte_t *pte;
 
-		if (pmd_present(*pmd))
+		next = pmd_addr_end(addr, end);
+
+		if (!info->force_pte) {
+			if (pmd_present(*pmd))
+				continue;
+
+			set_pmd(pmd, __pmd(((addr & PMD_MASK) - info->offset) | info->page_flag));
 			continue;
+		}
 
-		set_pmd(pmd, __pmd((addr - info->offset) | info->page_flag));
+		/* if this is already a 2MB page, this portion is already mapped */
+		if (pmd_leaf(*pmd))
+			continue;
+
+		if (pmd_present(*pmd)) {
+			pte = pte_offset_kernel(pmd, 0);
+			result = ident_pte_init(info, pte, addr, next);
+			if (result)
+				return result;
+			continue;
+		}
+
+		pte = (pte_t *)info->alloc_pgt_page(info->context);
+		if (!pte)
+			return -ENOMEM;
+
+		result = ident_pte_init(info, pte, addr, next);
+		if (result)
+			return result;
+
+		set_pmd(pmd, __pmd(__pa(pte) | info->kernpg_flag));
 	}
+
+	return 0;
 }
 
 static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
 			  unsigned long addr, unsigned long end)
 {
 	unsigned long next;
+	int result;
 
 	for (; addr < end; addr = next) {
 		pud_t *pud = pud_page + pud_index(addr);
@@ -108,7 +157,7 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
 			continue;
 
 		/* Is using a gbpage allowed? */
-		use_gbpage = info->direct_gbpages;
+		use_gbpage = info->direct_gbpages && !info->force_pte;
 
 		/* Don't use gbpage if it maps more than the requested region. */
 		/* at the beginning: */
@@ -129,13 +178,17 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
 
 		if (pud_present(*pud)) {
 			pmd = pmd_offset(pud, 0);
-			ident_pmd_init(info, pmd, addr, next);
+			result = ident_pmd_init(info, pmd, addr, next);
+			if (result)
+				return result;
 			continue;
 		}
 		pmd = (pmd_t *)info->alloc_pgt_page(info->context);
 		if (!pmd)
 			return -ENOMEM;
-		ident_pmd_init(info, pmd, addr, next);
+		result = ident_pmd_init(info, pmd, addr, next);
+		if (result)
+			return result;
 		set_pud(pud, __pud(__pa(pmd) | info->kernpg_flag));
 	}
 
@@ -189,6 +242,7 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
 
 	/* Filter out unsupported __PAGE_KERNEL_* bits: */
 	info->kernpg_flag &= __default_kernel_pte_mask;
+	info->page_flag &= __default_kernel_pte_mask;
 
 	for (; addr < end; addr = next) {
 		pgd_t *pgd = pgd_page + pgd_index(addr);
-- 
2.55.0.1082.g2b9226bbc0-goog


  parent reply	other threads:[~2026-09-20 19:37 UTC|newest]

Thread overview: 49+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-20 19:36 [RFC PATCH 00/46] Orphaned Virtual Machines Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 01/46] KVM: luo: Delegate VM creation type to kvm_arch_vm_luo_preserve Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 02/46] KVM: arm64: Split demux_c15_{get,set}_val from userspace accessors Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 03/46] KVM: arm64: Split kvm_sys_reg_{get,set}_user from kernel accessors Pasha Tatashin
2026-09-20 19:36 ` Pasha Tatashin [this message]
2026-09-20 19:36 ` [RFC PATCH 05/46] arm64: mm: Add trans_pgd_map_range() support Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 06/46] x86/smp: Skip offline CPUs for REBOOT_VECTOR in native_stop_other_cpus() Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 07/46] KVM: luo: Support vCPU file preservation across live updates Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 08/46] KVM: x86: Add x86 vCPU LUO preservation ABI and register helpers Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 09/46] KVM: x86: Implement architectural vCPU state preservation via LUO Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 10/46] KVM: arm64: " Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 11/46] liveupdate: Define CPU preservation linker sections Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 12/46] liveupdate: Add liveupdate_session_name() helper Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 13/46] cpu_preserve: Add physical CPU preservation ABI and core API headers Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 14/46] cpu_preserve: Add core physical CPU preservation state and park loop Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 15/46] cpu_preserve: Add physical CPU preservation lifecycle and build rules Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 16/46] liveupdate: cpu_preserve: Add sysfs interface Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 17/46] liveupdate: cpu_preserve: Add isolated address space management API Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 18/46] liveupdate: cpu_preserve: Add LUO file handler for preserved physical CPUs Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 19/46] x86: liveupdate: Add low-level physical CPU preservation assembly Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 20/46] x86: liveupdate: Add physical CPU preservation context and page table support Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 21/46] selftests: liveupdate: Add physical CPU preservation unit tests Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 22/46] selftests: liveupdate: Add physical CPU preservation live update tests Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 23/46] Documentation: liveupdate: Add physical CPU preservation documentation Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 24/46] MAINTAINERS: Add entry for KVM Caretaker Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 25/46] arm64: liveupdate: Add support for physical CPU preservation Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 26/46] oncore: Add on-core KHO ABI and public framework headers Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 27/46] oncore: Implement on-core session lifecycle and scheduling loop Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 28/46] KVM: caretaker: Add Caretaker control block and architecture ops headers Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 29/46] KVM: caretaker: Implement Caretaker session memory mapping helpers Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 30/46] KVM: caretaker: Integrate Caretaker vCPU detach, attach, and cancel with KVM Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 31/46] KVM: caretaker: Add generic KHO ABI telemetry and debugfs reporting Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 32/46] KVM: x86: Add TDP MMU KHO preservation helpers Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 33/46] KVM: x86: Add Caretaker x86 KHO ABI and runtime context headers Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 34/46] KVM: x86: Implement Caretaker LAPIC timer and interrupt injection Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 35/46] KVM: x86: Implement Caretaker VM-exit dispatch and instruction decoders Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 36/46] KVM: x86: Implement Caretaker run loop and LUO detach/attach lifecycle Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 37/46] KVM: VMX: Add Caretaker VMX assembly guest entry/exit routine and helpers Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 38/46] KVM: VMX: Implement Caretaker VMX VMCS lifecycle and exit dispatch Pasha Tatashin
2026-09-20 19:36 ` [RFC PATCH 39/46] KVM: VMX: Integrate Caretaker VMX detach serialization and KVM registration Pasha Tatashin
2026-09-21  7:42 ` [RFC PATCH 00/46] Orphaned Virtual Machines Graf (AWS), Alexander
2026-09-21 21:00 ` [RFC PATCH 39/46] KVM: VMX: Integrate Caretaker VMX detach serialization and KVM registration Pasha Tatashin
2026-09-21 21:00   ` [RFC PATCH 40/46] KVM: SVM: Add Caretaker SVM assembly guest entry/exit routine Pasha Tatashin
2026-09-21 21:00   ` [RFC PATCH 41/46] KVM: SVM: Implement Caretaker SVM VMCB lifecycle and exit dispatch Pasha Tatashin
2026-09-21 21:00   ` [RFC PATCH 42/46] KVM: arm64: Add Caretaker arm64 KHO ABI and runtime context headers Pasha Tatashin
2026-09-21 21:00   ` [RFC PATCH 43/46] KVM: arm64: Add Caretaker EL2 exception vectors and guest entry/exit assembly Pasha Tatashin
2026-09-21 21:00   ` [RFC PATCH 44/46] KVM: arm64: Implement Caretaker GICv3 CPU interface and arch timer emulation Pasha Tatashin
2026-09-21 21:00   ` [RFC PATCH 45/46] KVM: arm64: Implement Caretaker system register trap and exception handlers Pasha Tatashin
2026-09-21 21:00   ` [RFC PATCH 46/46] KVM: arm64: Implement Caretaker vCPU run loop and LUO detach/attach lifecycle Pasha Tatashin

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=20260920193650.3373435-5-pasha.tatashin@soleen.com \
    --to=pasha.tatashin@soleen.com \
    --cc=alexandre.chartre@oracle.com \
    --cc=ardb@kernel.org \
    --cc=arnd@arndb.de \
    --cc=atomlin@atomlin.com \
    --cc=bp@alien8.de \
    --cc=catalin.marinas@arm.com \
    --cc=chao.gao@intel.com \
    --cc=corbet@lwn.net \
    --cc=dave.hansen@linux.intel.com \
    --cc=dianders@chromium.org \
    --cc=djbw@kernel.org \
    --cc=fuad.tabba@linux.dev \
    --cc=graf@amazon.com \
    --cc=gshan@redhat.com \
    --cc=hamzamahfooz@linux.microsoft.com \
    --cc=hpa@zytor.com \
    --cc=james.morse@arm.com \
    --cc=jani.nikula@intel.com \
    --cc=jaredwhite@microsoft.com \
    --cc=jgross@suse.com \
    --cc=jic23@kernel.org \
    --cc=joey.gouly@arm.com \
    --cc=johan@kernel.org \
    --cc=jpoimboe@kernel.org \
    --cc=kas@kernel.org \
    --cc=kees@kernel.org \
    --cc=kexec@lists.infradead.org \
    --cc=kvm@vger.kernel.org \
    --cc=kvmarm@lists.linux.dev \
    --cc=legion@kernel.org \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kbuild@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=maz@kernel.org \
    --cc=mbenes@suse.cz \
    --cc=mingo@redhat.com \
    --cc=nathan@kernel.org \
    --cc=nogikh@google.com \
    --cc=nsc@kernel.org \
    --cc=oupton@kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=peterz@infradead.org \
    --cc=petr.pavlu@suse.com \
    --cc=pierre.gondois@arm.com \
    --cc=pmladek@suse.com \
    --cc=pratyush@kernel.org \
    --cc=rdunlap@infradead.org \
    --cc=rppt@kernel.org \
    --cc=ruanjinjie@huawei.com \
    --cc=ryan.roberts@arm.com \
    --cc=seanjc@google.com \
    --cc=seiden@linux.ibm.com \
    --cc=shuah@kernel.org \
    --cc=sidnayyar@google.com \
    --cc=skhan@linuxfoundation.org \
    --cc=song@kernel.org \
    --cc=sumitg@nvidia.com \
    --cc=suzuki.poulose@arm.com \
    --cc=tarunsahu@google.com \
    --cc=tglx@kernel.org \
    --cc=vdonnefort@google.com \
    --cc=vladimir.murzin@arm.com \
    --cc=will@kernel.org \
    --cc=x86@kernel.org \
    --cc=xur@google.com \
    --cc=yuzenghui@huawei.com \
    --cc=zengheng4@huawei.com \
    --cc=zhangpengjie2@huawei.com \
    --cc=zhenglifeng1@huawei.com \
    /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