linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
To: Dave Hansen <dave.hansen@linux.intel.com>,
	Andy Lutomirski <luto@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>
Cc: x86@kernel.org, Kostya Serebryany <kcc@google.com>,
	Andrey Ryabinin <ryabinin.a.a@gmail.com>,
	Andrey Konovalov <andreyknvl@gmail.com>,
	Alexander Potapenko <glider@google.com>,
	Taras Madan <tarasmadan@google.com>,
	Dmitry Vyukov <dvyukov@google.com>,
	"H . J . Lu" <hjl.tools@gmail.com>,
	Andi Kleen <ak@linux.intel.com>,
	Rick Edgecombe <rick.p.edgecombe@intel.com>,
	Bharata B Rao <bharata@amd.com>,
	Jacob Pan <jacob.jun.pan@linux.intel.com>,
	Ashok Raj <ashok.raj@intel.com>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Subject: [PATCHv13 10/16] x86/mm/iommu/sva: Make LAM and SVA mutually exclusive
Date: Tue, 27 Dec 2022 06:08:23 +0300	[thread overview]
Message-ID: <20221227030829.12508-11-kirill.shutemov@linux.intel.com> (raw)
In-Reply-To: <20221227030829.12508-1-kirill.shutemov@linux.intel.com>

IOMMU and SVA-capable devices know nothing about LAM and only expect
canonical addresses. An attempt to pass down tagged pointer will lead
to address translation failure.

By default do not allow to enable both LAM and use SVA in the same
process.

The new ARCH_FORCE_TAGGED_SVA arch_prctl() overrides the limitation.
By using the arch_prctl() userspace takes responsibility to never pass
tagged address to the device.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Ashok Raj <ashok.raj@intel.com>
Reviewed-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
---
 arch/x86/include/asm/mmu.h         | 2 ++
 arch/x86/include/asm/mmu_context.h | 6 ++++++
 arch/x86/include/uapi/asm/prctl.h  | 1 +
 arch/x86/kernel/process_64.c       | 7 +++++++
 drivers/iommu/iommu-sva.c          | 4 ++++
 include/linux/mmu_context.h        | 7 +++++++
 6 files changed, 27 insertions(+)

diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 54e4a3e9b5c5..90d20679e4d7 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -14,6 +14,8 @@
 #define MM_CONTEXT_HAS_VSYSCALL		1
 /* Do not allow changing LAM mode */
 #define MM_CONTEXT_LOCK_LAM		2
+/* Allow LAM and SVA coexisting */
+#define MM_CONTEXT_FORCE_TAGGED_SVA	3
 
 /*
  * x86 has arch-specific MMU state beyond what lives in mm_struct.
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 7f9f9978c811..4bc95c35cbd3 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -114,6 +114,12 @@ static inline void mm_reset_untag_mask(struct mm_struct *mm)
 	mm->context.untag_mask = -1UL;
 }
 
+#define arch_pgtable_dma_compat arch_pgtable_dma_compat
+static inline bool arch_pgtable_dma_compat(struct mm_struct *mm)
+{
+	return !mm_lam_cr3_mask(mm) ||
+		test_bit(MM_CONTEXT_FORCE_TAGGED_SVA, &mm->context.flags);
+}
 #else
 
 static inline unsigned long mm_lam_cr3_mask(struct mm_struct *mm)
diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h
index a31e27b95b19..eb290d89cb32 100644
--- a/arch/x86/include/uapi/asm/prctl.h
+++ b/arch/x86/include/uapi/asm/prctl.h
@@ -23,5 +23,6 @@
 #define ARCH_GET_UNTAG_MASK		0x4001
 #define ARCH_ENABLE_TAGGED_ADDR		0x4002
 #define ARCH_GET_MAX_TAG_BITS		0x4003
+#define ARCH_FORCE_TAGGED_SVA		0x4004
 
 #endif /* _ASM_X86_PRCTL_H */
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 09e7f3d3fb5c..add85615d5ae 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -756,6 +756,10 @@ static int prctl_enable_tagged_addr(struct mm_struct *mm, unsigned long nr_bits)
 	if (test_bit(MM_CONTEXT_LOCK_LAM, &mm->context.flags))
 		return -EBUSY;
 
+	if (mm_valid_pasid(mm) &&
+	    !test_bit(MM_CONTEXT_FORCE_TAGGED_SVA, &mm->context.flags))
+		return -EINTR;
+
 	if (mmap_write_lock_killable(mm))
 		return -EINTR;
 
@@ -872,6 +876,9 @@ long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2)
 				(unsigned long __user *)arg2);
 	case ARCH_ENABLE_TAGGED_ADDR:
 		return prctl_enable_tagged_addr(task->mm, arg2);
+	case ARCH_FORCE_TAGGED_SVA:
+		set_bit(MM_CONTEXT_FORCE_TAGGED_SVA, &task->mm->context.flags);
+		return 0;
 	case ARCH_GET_MAX_TAG_BITS:
 		if (!cpu_feature_enabled(X86_FEATURE_LAM))
 			return put_user(0, (unsigned long __user *)arg2);
diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c
index 4ee2929f0d7a..dd76a1a09cf7 100644
--- a/drivers/iommu/iommu-sva.c
+++ b/drivers/iommu/iommu-sva.c
@@ -2,6 +2,7 @@
 /*
  * Helpers for IOMMU drivers implementing SVA
  */
+#include <linux/mmu_context.h>
 #include <linux/mutex.h>
 #include <linux/sched/mm.h>
 #include <linux/iommu.h>
@@ -32,6 +33,9 @@ int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max)
 	    min == 0 || max < min)
 		return -EINVAL;
 
+	if (!arch_pgtable_dma_compat(mm))
+		return -EBUSY;
+
 	mutex_lock(&iommu_sva_lock);
 	/* Is a PASID already associated with this mm? */
 	if (mm_valid_pasid(mm)) {
diff --git a/include/linux/mmu_context.h b/include/linux/mmu_context.h
index 14b9c1fa05c4..f2b7a3f04099 100644
--- a/include/linux/mmu_context.h
+++ b/include/linux/mmu_context.h
@@ -35,4 +35,11 @@ static inline unsigned long mm_untag_mask(struct mm_struct *mm)
 }
 #endif
 
+#ifndef arch_pgtable_dma_compat
+static inline bool arch_pgtable_dma_compat(struct mm_struct *mm)
+{
+	return true;
+}
+#endif
+
 #endif
-- 
2.38.2


  parent reply	other threads:[~2022-12-27  3:09 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-12-27  3:08 [PATCHv13 00/16] Linear Address Masking enabling Kirill A. Shutemov
2022-12-27  3:08 ` [PATCHv13 01/16] x86: Allow atomic MM_CONTEXT flags setting Kirill A. Shutemov
2023-01-04 19:07   ` Dave Hansen
2022-12-27  3:08 ` [PATCHv13 02/16] x86: CPUID and CR3/CR4 flags for Linear Address Masking Kirill A. Shutemov
2022-12-27  3:08 ` [PATCHv13 03/16] x86/mm: Handle LAM on context switch Kirill A. Shutemov
2022-12-27  3:08 ` [PATCHv13 04/16] mm: Introduce untagged_addr_remote() Kirill A. Shutemov
2022-12-27  3:08 ` [PATCHv13 05/16] x86/uaccess: Provide untagged_addr() and remove tags before address check Kirill A. Shutemov
2022-12-27 19:10   ` Linus Torvalds
2022-12-31  0:10     ` Kirill A. Shutemov
2022-12-31  0:42       ` Linus Torvalds
2023-01-02 13:55         ` David Laight
2023-01-02 19:05           ` Linus Torvalds
2023-01-03  8:37             ` David Laight
2023-01-07  9:10         ` Kirill A. Shutemov
2023-01-07 17:28           ` Linus Torvalds
2022-12-27  3:08 ` [PATCHv13 06/16] x86/mm: Provide arch_prctl() interface for LAM Kirill A. Shutemov
2023-01-04 19:55   ` Edgecombe, Rick P
2023-01-10  6:17     ` Kirill A. Shutemov
2022-12-27  3:08 ` [PATCHv13 07/16] x86/mm: Reduce untagged_addr() overhead until the first LAM user Kirill A. Shutemov
2022-12-27  3:08 ` [PATCHv13 08/16] mm: Expose untagging mask in /proc/$PID/status Kirill A. Shutemov
2022-12-27  3:08 ` [PATCHv13 09/16] iommu/sva: Replace pasid_valid() helper with mm_valid_pasid() Kirill A. Shutemov
2022-12-27  3:08 ` Kirill A. Shutemov [this message]
2022-12-27  3:08 ` [PATCHv13 11/16] selftests/x86/lam: Add malloc and tag-bits test cases for linear-address masking Kirill A. Shutemov
2022-12-27  3:08 ` [PATCHv13 12/16] selftests/x86/lam: Add mmap and SYSCALL " Kirill A. Shutemov
2022-12-27  3:08 ` [PATCHv13 13/16] selftests/x86/lam: Add io_uring " Kirill A. Shutemov
2022-12-27  3:08 ` [PATCHv13 14/16] selftests/x86/lam: Add inherit " Kirill A. Shutemov
2022-12-27  3:08 ` [PATCHv13 15/16] selftests/x86/lam: Add ARCH_FORCE_TAGGED_SVA " Kirill A. Shutemov
2022-12-27  3:08 ` [PATCHv13 16/16] selftests/x86/lam: Add test cases for LAM vs thread creation Kirill A. Shutemov

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=20221227030829.12508-11-kirill.shutemov@linux.intel.com \
    --to=kirill.shutemov@linux.intel.com \
    --cc=ak@linux.intel.com \
    --cc=andreyknvl@gmail.com \
    --cc=ashok.raj@intel.com \
    --cc=bharata@amd.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=dvyukov@google.com \
    --cc=glider@google.com \
    --cc=hjl.tools@gmail.com \
    --cc=jacob.jun.pan@linux.intel.com \
    --cc=kcc@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@kernel.org \
    --cc=peterz@infradead.org \
    --cc=rick.p.edgecombe@intel.com \
    --cc=ryabinin.a.a@gmail.com \
    --cc=tarasmadan@google.com \
    --cc=torvalds@linux-foundation.org \
    --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;
as well as URLs for NNTP newsgroup(s).