linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: ira.weiny@intel.com
To: Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
	Andy Lutomirski <luto@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>
Cc: Ira Weiny <ira.weiny@intel.com>,
	Fenghua Yu <fenghua.yu@intel.com>,
	x86@kernel.org, Dave Hansen <dave.hansen@linux.intel.com>,
	Dan Williams <dan.j.williams@intel.com>,
	Vishal Verma <vishal.l.verma@intel.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-nvdimm@lists.01.org, linux-fsdevel@vger.kernel.org,
	linux-mm@kvack.org, linux-kselftest@vger.kernel.org
Subject: [RFC PATCH 04/15] x86/pks: Preserve the PKRS MSR on context switch
Date: Tue, 14 Jul 2020 00:02:09 -0700	[thread overview]
Message-ID: <20200714070220.3500839-5-ira.weiny@intel.com> (raw)
In-Reply-To: <20200714070220.3500839-1-ira.weiny@intel.com>

From: Ira Weiny <ira.weiny@intel.com>

The PKRS MSR is defined as a per-core register.  This isolates memory
access by CPU.  Unfortunately, the MSR is not preserved by XSAVE.
Therefore, We must preserve the protections for individual tasks even if
they are context switched out and placed on another cpu later.

Define a saved PKRS value in the task struct, as well as a cached
per-cpu MSR value which mirrors the MSR value of the current CPU.
Initialize, all tasks with the default MSR value.  Then, on schedule in,
check the saved task MSR vs the per-cpu value.  If different proceed to
write the MSR.  If not we avoid the overhead of the MSR write and
continue.

Follow on patches will update the saved PKRS as well as the MSR if
needed.

Co-developed-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
---
 arch/x86/include/asm/msr-index.h      |  1 +
 arch/x86/include/asm/pkeys_internal.h | 20 +++++++++++++++
 arch/x86/include/asm/processor.h      | 12 +++++++++
 arch/x86/kernel/cpu/common.c          |  2 ++
 arch/x86/kernel/process.c             | 35 +++++++++++++++++++++++++++
 arch/x86/mm/pkeys.c                   | 13 ++++++++++
 6 files changed, 83 insertions(+)

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index e8370e64a155..b6ffdfc3f388 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -727,6 +727,7 @@
 
 #define MSR_IA32_TSC_DEADLINE		0x000006E0
 
+#define MSR_IA32_PKRS			0x000006E1
 
 #define MSR_TSX_FORCE_ABORT		0x0000010F
 
diff --git a/arch/x86/include/asm/pkeys_internal.h b/arch/x86/include/asm/pkeys_internal.h
index a9f086f1e4b4..05257cdc7200 100644
--- a/arch/x86/include/asm/pkeys_internal.h
+++ b/arch/x86/include/asm/pkeys_internal.h
@@ -8,4 +8,24 @@
 
 #define PKR_AD_KEY(pkey)	(PKR_AD_BIT << ((pkey) * PKR_BITS_PER_PKEY))
 
+/*
+ * Define a default PKRS value for each task.
+ *
+ * Key 0 has no restriction.  All other keys are set to the most restrictive
+ * value which is access disabled (AD=1).
+ *
+ * NOTE: This needs to be a macro to be used as part of the INIT_THREAD macro.
+ */
+#define INIT_PKRS_VALUE (PKR_AD_KEY(1) | PKR_AD_KEY(2) | PKR_AD_KEY(3) | \
+			 PKR_AD_KEY(4) | PKR_AD_KEY(5) | PKR_AD_KEY(6) | \
+			 PKR_AD_KEY(7) | PKR_AD_KEY(8) | PKR_AD_KEY(9) | \
+			 PKR_AD_KEY(10) | PKR_AD_KEY(11) | PKR_AD_KEY(12) | \
+			 PKR_AD_KEY(13) | PKR_AD_KEY(14) | PKR_AD_KEY(15))
+
+#ifdef CONFIG_ARCH_HAS_SUPERVISOR_PKEYS
+void write_pkrs(u32 pkrs_val);
+#else
+static inline void write_pkrs(u32 pkrs_val) { }
+#endif
+
 #endif /*_ASM_X86_PKEYS_INTERNAL_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 7da9855b5068..704d9f28fd4e 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -545,6 +545,11 @@ struct thread_struct {
 
 	unsigned int		sig_on_uaccess_err:1;
 
+#ifdef	CONFIG_ARCH_HAS_SUPERVISOR_PKEYS
+	/* Saved Protection key register for supervisor mappings */
+	u32			saved_pkrs;
+#endif
+
 	/* Floating point and extended processor state */
 	struct fpu		fpu;
 	/*
@@ -907,8 +912,15 @@ static inline void spin_lock_prefetch(const void *x)
 #define STACK_TOP		TASK_SIZE_LOW
 #define STACK_TOP_MAX		TASK_SIZE_MAX
 
+#ifdef CONFIG_ARCH_HAS_SUPERVISOR_PKEYS
+#define INIT_THREAD_PKRS	.saved_pkrs = INIT_PKRS_VALUE,
+#else
+#define INIT_THREAD_PKRS
+#endif
+
 #define INIT_THREAD  {						\
 	.addr_limit		= KERNEL_DS,			\
+	INIT_THREAD_PKRS					\
 }
 
 extern unsigned long KSTK_ESP(struct task_struct *task);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index f34bcefeda42..b8241936cbbf 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -56,6 +56,7 @@
 #include <asm/intel-family.h>
 #include <asm/cpu_device_id.h>
 #include <asm/uv/uv.h>
+#include <asm/pkeys_internal.h>
 
 #include "cpu.h"
 
@@ -1442,6 +1443,7 @@ static void setup_pks(void)
 		return;
 
 	cr4_set_bits(X86_CR4_PKS);
+	write_pkrs(INIT_PKRS_VALUE);
 }
 
 /*
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index f362ce0d5ac0..d69250a7c1bf 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -42,6 +42,7 @@
 #include <asm/spec-ctrl.h>
 #include <asm/io_bitmap.h>
 #include <asm/proto.h>
+#include <asm/pkeys_internal.h>
 
 #include "process.h"
 
@@ -184,6 +185,36 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 	return ret;
 }
 
+/*
+ * NOTE: We wrap pks_init_task() and pks_sched_in() with
+ * CONFIG_ARCH_HAS_SUPERVISOR_PKEYS because using IS_ENABLED() fails
+ * due to the lack of task_struct->saved_pkrs in this configuration.
+ * Furthermore, we place them here because of the complexity introduced by
+ * header conflicts introduced to get the task_struct definition in the pkeys
+ * headers.
+ */
+#ifdef CONFIG_ARCH_HAS_SUPERVISOR_PKEYS
+DECLARE_PER_CPU(u32, pkrs_cache);
+static inline void pks_init_task(struct task_struct *tsk)
+{
+	/* New tasks get the most restrictive PKRS value */
+	tsk->thread.saved_pkrs = INIT_PKRS_VALUE;
+}
+static inline void pks_sched_in(void)
+{
+	u64 current_pkrs = current->thread.saved_pkrs;
+
+	/* Only update the MSR when current's pkrs is different from the MSR. */
+	if (this_cpu_read(pkrs_cache) == current_pkrs)
+		return;
+
+	write_pkrs(current_pkrs);
+}
+#else
+static inline void pks_init_task(struct task_struct *tsk) { }
+static inline void pks_sched_in(void) { }
+#endif
+
 void flush_thread(void)
 {
 	struct task_struct *tsk = current;
@@ -192,6 +223,8 @@ void flush_thread(void)
 	memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
 
 	fpu__clear_all(&tsk->thread.fpu);
+
+	pks_init_task(tsk);
 }
 
 void disable_TSC(void)
@@ -655,6 +688,8 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p)
 
 	if ((tifp ^ tifn) & _TIF_SLD)
 		switch_to_sld(tifn);
+
+	pks_sched_in();
 }
 
 /*
diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c
index a5c680d32930..0f86f2374bd7 100644
--- a/arch/x86/mm/pkeys.c
+++ b/arch/x86/mm/pkeys.c
@@ -236,3 +236,16 @@ u32 get_new_pkr(u32 old_pkr, int pkey, unsigned long init_val)
 	/* Return the old part along with the new part: */
 	return old_pkr | new_pkr_bits;
 }
+
+DEFINE_PER_CPU(u32, pkrs_cache);
+
+/*
+ * Write the PKey Register Supervisor.  This must be run with preemption
+ * disabled as it does not guarantee the atomicity of updating the pkrs_cache
+ * and MSR on its own.
+ */
+void write_pkrs(u32 pkrs_val)
+{
+	this_cpu_write(pkrs_cache, pkrs_val);
+	wrmsrl(MSR_IA32_PKRS, pkrs_val);
+}
-- 
2.25.1


  parent reply	other threads:[~2020-07-14  7:04 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-14  7:02 [RFC PATCH 00/15] PKS: Add Protection Keys Supervisor (PKS) support ira.weiny
2020-07-14  7:02 ` [RFC PATCH 01/15] x86/pkeys: Create pkeys_internal.h ira.weiny
2020-07-14  7:02 ` [RFC PATCH 02/15] x86/fpu: Refactor arch_set_user_pkey_access() for PKS support ira.weiny
2020-07-14  7:02 ` [RFC PATCH 03/15] x86/pks: Enable Protection Keys Supervisor (PKS) ira.weiny
2020-07-14  7:02 ` ira.weiny [this message]
2020-07-14  8:27   ` [RFC PATCH 04/15] x86/pks: Preserve the PKRS MSR on context switch Peter Zijlstra
2020-07-14 18:53     ` Ira Weiny
2020-07-14 18:56       ` Dave Hansen
2020-07-14 19:05       ` Peter Zijlstra
2020-07-14 19:09         ` Ira Weiny
2020-07-16  8:37   ` [x86/pks] 061e3e0b92: leaking-addresses.dmesg.uncheckedMSRaccesserror:WRMSRto0x6e1(triedtowrite0x0000000055555554)atrIP:(write_pkrs+0x15/0x2b) kernel test robot
2020-07-14  7:02 ` [RFC PATCH 05/15] x86/pks: Add PKS kernel API ira.weiny
2020-07-14  7:02 ` [RFC PATCH 06/15] x86/pks: Add a debugfs file for allocated PKS keys ira.weiny
2020-07-14  7:02 ` [RFC PATCH 07/15] Documentation/pkeys: Update documentation for kernel pkeys ira.weiny
2020-07-14  7:02 ` [RFC PATCH 08/15] x86/pks: Add PKS Test code ira.weiny
2020-07-14  7:02 ` [RFC PATCH 09/15] fs/dax: Remove unused size parameter ira.weiny
2020-07-14  7:02 ` [RFC PATCH 10/15] drivers/dax: Expand lock scope to cover the use of addresses ira.weiny
2020-07-14  7:02 ` [RFC PATCH 11/15] memremap: Add zone device access protection ira.weiny
2020-07-14  8:40   ` Peter Zijlstra
2020-07-14 19:10     ` Ira Weiny
2020-07-14 19:40       ` Peter Zijlstra
2020-07-14  7:02 ` [RFC PATCH 12/15] kmap: Add stray write protection for device pages ira.weiny
2020-07-14  8:44   ` Peter Zijlstra
2020-07-14 19:06     ` Ira Weiny
2020-07-14 19:29       ` Peter Zijlstra
2020-07-14 19:42         ` Dave Hansen
2020-07-14 19:49           ` Peter Zijlstra
2020-07-14 20:00           ` Ira Weiny
2020-07-14  7:02 ` [RFC PATCH 13/15] dax: Stray write protection for dax_direct_access() ira.weiny
2020-07-14  7:02 ` [RFC PATCH 14/15] nvdimm/pmem: Stray write protection for pmem->virt_addr ira.weiny
2020-07-14  7:02 ` [RFC PATCH 15/15] [dax|pmem]: Enable stray write protection ira.weiny

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=20200714070220.3500839-5-ira.weiny@intel.com \
    --to=ira.weiny@intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=bp@alien8.de \
    --cc=dan.j.williams@intel.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=fenghua.yu@intel.com \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=luto@kernel.org \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    --cc=vishal.l.verma@intel.com \
    --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).