linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Balbir Singh <sblbir@amazon.com>
To: <tglx@linutronix.de>, <linux-kernel@vger.kernel.org>
Cc: <jpoimboe@redhat.com>, <tony.luck@intel.com>,
	<keescook@chromium.org>, <benh@kernel.crashing.org>,
	<x86@kernel.org>, <dave.hansen@intel.com>,
	<thomas.lendacky@amd.com>, Balbir Singh <sblbir@amazon.com>
Subject: [PATCH v6 5/6] Optionally flush L1D on context switch
Date: Sun, 10 May 2020 11:48:02 +1000	[thread overview]
Message-ID: <20200510014803.12190-6-sblbir@amazon.com> (raw)
In-Reply-To: <20200510014803.12190-1-sblbir@amazon.com>

Implement a mechanism to selectively flush the L1D cache. The goal is to
allow tasks that are paranoid due to the recent snoop assisted data sampling
vulnerabilites, to flush their L1D on being switched out.  This protects
their data from being snooped or leaked via side channels after the task
has context switched out.

There are two scenarios we might want to protect against, a task leaving
the CPU with data still in L1D (which is the main concern of this patch),
the second scenario is a malicious task coming in (not so well trusted)
for which we want to clean up the cache before it starts. Only the case
for the former is addressed.

A new thread_info flag TIF_SPEC_FLUSH_L1D is added to track tasks which
opt-into L1D flushing. cpu_tlbstate.last_user_mm_spec is used to convert
the TIF flags into mm state (per cpu via last_user_mm_spec) in
cond_mitigation(), which then used to do decide when to call flush_l1d().

Add prctl()'s to opt-in to the L1D cache on context switch out, the
existing mechanisms of tracking prev_mm via cpu_tlbstate is
reused to track state of the tasks and to flush the L1D cache.
The prctl interface is generic and can be ported over to other
architectures.

Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Balbir Singh <sblbir@amazon.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
---
 arch/x86/include/asm/thread_info.h |  7 ++++-
 arch/x86/mm/tlb.c                  | 44 ++++++++++++++++++++++++++++--
 include/uapi/linux/prctl.h         |  4 +++
 kernel/sys.c                       | 20 ++++++++++++++
 4 files changed, 72 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 8de8ceccb8bc..67de693d9ba1 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -84,7 +84,7 @@ struct thread_info {
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
 #define TIF_SECCOMP		8	/* secure computing */
 #define TIF_SPEC_IB		9	/* Indirect branch speculation mitigation */
-#define TIF_SPEC_FORCE_UPDATE	10	/* Force speculation MSR update in context switch */
+#define TIF_SPEC_FLUSH_L1D	10	/* Flush L1D on mm switches (processes) */
 #define TIF_USER_RETURN_NOTIFY	11	/* notify kernel of userspace return */
 #define TIF_UPROBE		12	/* breakpointed or singlestepping */
 #define TIF_PATCH_PENDING	13	/* pending live patching update */
@@ -96,6 +96,7 @@ struct thread_info {
 #define TIF_MEMDIE		20	/* is terminating due to OOM killer */
 #define TIF_POLLING_NRFLAG	21	/* idle is polling for TIF_NEED_RESCHED */
 #define TIF_IO_BITMAP		22	/* uses I/O bitmap */
+#define TIF_SPEC_FORCE_UPDATE	23	/* Force speculation MSR update in context switch */
 #define TIF_FORCED_TF		24	/* true if TF in eflags artificially */
 #define TIF_BLOCKSTEP		25	/* set when we want DEBUGCTLMSR_BTF */
 #define TIF_LAZY_MMU_UPDATES	27	/* task is updating the mmu lazily */
@@ -132,6 +133,7 @@ struct thread_info {
 #define _TIF_ADDR32		(1 << TIF_ADDR32)
 #define _TIF_X32		(1 << TIF_X32)
 #define _TIF_FSCHECK		(1 << TIF_FSCHECK)
+#define _TIF_SPEC_FLUSH_L1D	(1 << TIF_SPEC_FLUSH_L1D)
 
 /* Work to do before invoking the actual syscall. */
 #define _TIF_WORK_SYSCALL_ENTRY	\
@@ -235,6 +237,9 @@ static inline int arch_within_stack_frames(const void * const stack,
 			   current_thread_info()->status & TS_COMPAT)
 #endif
 
+extern int arch_prctl_l1d_flush_set(struct task_struct *tsk, unsigned long enable);
+extern int arch_prctl_l1d_flush_get(struct task_struct *tsk);
+
 extern void arch_task_cache_init(void);
 extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
 extern void arch_release_task_struct(struct task_struct *tsk);
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 10056b8d8f01..7ea9bc9e089f 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -13,6 +13,7 @@
 #include <asm/mmu_context.h>
 #include <asm/nospec-branch.h>
 #include <asm/cache.h>
+#include <asm/cacheflush.h>
 #include <asm/apic.h>
 #include <asm/uv/uv.h>
 
@@ -43,11 +44,12 @@
  */
 
 /*
- * Bits to mangle the TIF_SPEC_IB state into the mm pointer which is
+ * Bits to mangle the TIF_SPEC_* state into the mm pointer which is
  * stored in cpu_tlb_state.last_user_mm_spec.
  */
 #define LAST_USER_MM_IBPB	0x1UL
-#define LAST_USER_MM_SPEC_MASK	(LAST_USER_MM_IBPB)
+#define LAST_USER_MM_L1D_FLUSH	0x2UL
+#define LAST_USER_MM_SPEC_MASK	(LAST_USER_MM_IBPB | LAST_USER_MM_L1D_FLUSH)
 
 /*
  * The x86 feature is called PCID (Process Context IDentifier). It is similar
@@ -308,6 +310,35 @@ void leave_mm(int cpu)
 }
 EXPORT_SYMBOL_GPL(leave_mm);
 
+static int enable_l1d_flush_for_task(struct task_struct *tsk)
+{
+	int ret = l1d_flush_init_once();
+
+	if (ret < 0)
+		return ret;
+
+	set_ti_thread_flag(&tsk->thread_info, TIF_SPEC_FLUSH_L1D);
+	return ret;
+}
+
+static int disable_l1d_flush_for_task(struct task_struct *tsk)
+{
+	clear_ti_thread_flag(&tsk->thread_info, TIF_SPEC_FLUSH_L1D);
+	return 0;
+}
+
+int arch_prctl_l1d_flush_get(struct task_struct *tsk)
+{
+	return test_ti_thread_flag(&tsk->thread_info, TIF_SPEC_FLUSH_L1D);
+}
+
+int arch_prctl_l1d_flush_set(struct task_struct *tsk, unsigned long enable)
+{
+	if (enable)
+		return enable_l1d_flush_for_task(tsk);
+	return disable_l1d_flush_for_task(tsk);
+}
+
 void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	       struct task_struct *tsk)
 {
@@ -424,6 +455,9 @@ static void cond_mitigation(struct task_struct *next)
 			indirect_branch_prediction_barrier();
 	}
 
+	if (prev_mm & LAST_USER_MM_L1D_FLUSH)
+		arch_l1d_flush(0); /* Just flush, don't populate the TLB */
+
 	this_cpu_write(cpu_tlbstate.last_user_mm_spec, next_mm);
 }
 
@@ -678,6 +712,12 @@ void initialize_tlbstate_and_flush(void)
 	write_cr3(build_cr3(mm->pgd, 0));
 
 	/* Reinitialize tlbstate. */
+
+	/*
+	 * Leave last_user_mm_spec at LAST_USER_MM_IBPB, we don't
+	 * want to set LAST_USER_MM_L1D_FLUSH and force a flush before
+	 * we've allocated the flush pages.
+	 */
 	this_cpu_write(cpu_tlbstate.last_user_mm_spec, LAST_USER_MM_IBPB);
 	this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0);
 	this_cpu_write(cpu_tlbstate.next_asid, 1);
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 07b4f8131e36..42cb3038c81a 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -238,4 +238,8 @@ struct prctl_mm_map {
 #define PR_SET_IO_FLUSHER		57
 #define PR_GET_IO_FLUSHER		58
 
+/* Flush L1D on context switch (mm) */
+#define PR_SET_L1D_FLUSH		59
+#define PR_GET_L1D_FLUSH		60
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/kernel/sys.c b/kernel/sys.c
index d325f3ab624a..578aa8b6d87e 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2262,6 +2262,16 @@ int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which,
 	return -EINVAL;
 }
 
+int __weak arch_prctl_l1d_flush_set(struct task_struct *tsk, unsigned long enable)
+{
+	return -EINVAL;
+}
+
+int __weak arch_prctl_l1d_flush_get(struct task_struct *t)
+{
+	return -EINVAL;
+}
+
 #define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LESS_THROTTLE)
 
 SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
@@ -2514,6 +2524,16 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 
 		error = (current->flags & PR_IO_FLUSHER) == PR_IO_FLUSHER;
 		break;
+	case PR_SET_L1D_FLUSH:
+		if (arg3 || arg4 || arg5)
+			return -EINVAL;
+		error = arch_prctl_l1d_flush_set(me, arg2);
+		break;
+	case PR_GET_L1D_FLUSH:
+		if (arg2 || arg3 || arg4 || arg5)
+			return -EINVAL;
+		error = arch_prctl_l1d_flush_get(me);
+		break;
 	default:
 		error = -EINVAL;
 		break;
-- 
2.17.1


  parent reply	other threads:[~2020-05-10  1:48 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-10  1:47 [PATCH v6 0/6] Optionally flush L1D on context switch Balbir Singh
2020-05-10  1:47 ` [PATCH v6 1/6] arch/x86/kvm: Refactor l1d flush lifecycle management Balbir Singh
2020-05-13 13:35   ` Thomas Gleixner
2020-05-14  8:23     ` Singh, Balbir
2020-05-13 13:53   ` Thomas Gleixner
2020-05-14  8:25     ` Singh, Balbir
2020-05-22  9:32   ` [tip: x86/mm] x86/kvm: Refactor L1D flush page management tip-bot2 for Balbir Singh
2020-05-10  1:47 ` [PATCH v6 2/6] arch/x86/kvm: Refactor tlbflush and l1d flush Balbir Singh
2020-05-22  9:32   ` [tip: x86/mm] x86/kvm: Refactor L1D flush operations tip-bot2 for Balbir Singh
2020-05-10  1:48 ` [PATCH v6 3/6] arch/x86/mm: Refactor cond_ibpb() to support other use cases Balbir Singh
2020-05-13 14:16   ` Thomas Gleixner
2020-05-22  9:32   ` [tip: x86/mm] x86/mm: " tip-bot2 for Balbir Singh
2020-09-16 13:11   ` [tip: x86/pti] " tip-bot2 for Balbir Singh
2020-05-10  1:48 ` [PATCH v6 4/6] arch/x86/kvm: Refactor L1D flushing Balbir Singh
2020-05-22  9:32   ` [tip: x86/mm] x86/kvm: " tip-bot2 for Balbir Singh
2020-05-10  1:48 ` Balbir Singh [this message]
2020-05-13 15:04   ` [PATCH v6 5/6] Optionally flush L1D on context switch Thomas Gleixner
2020-05-14  8:23     ` Singh, Balbir
2020-05-13 15:27   ` Thomas Gleixner
2020-05-14 21:28     ` Singh, Balbir
2020-05-13 16:16   ` Thomas Gleixner
2020-05-14  7:43     ` Singh, Balbir
2020-05-14 11:33       ` Thomas Gleixner
2020-05-10  1:48 ` [PATCH v6 6/6] Documentation: Add L1D flushing Documentation Balbir Singh
2020-05-13 13:33   ` Thomas Gleixner
2020-05-14  1:12     ` Singh, Balbir

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=20200510014803.12190-6-sblbir@amazon.com \
    --to=sblbir@amazon.com \
    --cc=benh@kernel.crashing.org \
    --cc=dave.hansen@intel.com \
    --cc=jpoimboe@redhat.com \
    --cc=keescook@chromium.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=tglx@linutronix.de \
    --cc=thomas.lendacky@amd.com \
    --cc=tony.luck@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).