linux-kernel - [PATCH v2 3/3] x86/entry: Set FRED RSP0 on return to userspace instead of context switch

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20240822073906.2176342-4-xin@zytor.com>
Date: Thu, 22 Aug 2024 00:39:06 -0700
From: "Xin Li (Intel)" <xin@...or.com>
To: linux-kernel@...r.kernel.org
Cc: tglx@...utronix.de, mingo@...hat.com, bp@...en8.de,
        dave.hansen@...ux.intel.com, x86@...nel.org, hpa@...or.com,
        peterz@...radead.org, andrew.cooper3@...rix.com, seanjc@...gle.com
Subject: [PATCH v2 3/3] x86/entry: Set FRED RSP0 on return to userspace instead of context switch

FRED RSP0 is a per task constant pointing to top of its kernel stack
for user level event delivery, and needs to be updated when a task is
scheduled in.

Keep FRED RSP0 in per CPU cache, and update FRED RSP0 and its copy in
per CPU cache only when switching to a new task, i.e., current stack
is changed.

An API fred_sync_rsp0() is added for KVM to stuff the cache with the
guest's FRED RSP0 when switching to host.

Suggested-by: Sean Christopherson <seanjc@...gle.com>
Suggested-by: Thomas Gleixner <tglx@...utronix.de>
Signed-off-by: Xin Li (Intel) <xin@...or.com>
---

Change since v1:
* Use per CPU cache, rather than a new TI flag. (Thomas Gleixner)
---
 arch/x86/include/asm/entry-common.h |  3 +++
 arch/x86/include/asm/fred.h         | 21 ++++++++++++++++++++-
 arch/x86/include/asm/switch_to.h    |  5 +----
 arch/x86/kernel/fred.c              |  3 +++
 4 files changed, 27 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h
index db970828f385..77d20555e04d 100644
--- a/arch/x86/include/asm/entry-common.h
+++ b/arch/x86/include/asm/entry-common.h
@@ -8,6 +8,7 @@
 #include <asm/nospec-branch.h>
 #include <asm/io_bitmap.h>
 #include <asm/fpu/api.h>
+#include <asm/fred.h>
 
 /* Check that the stack and regs on entry from user mode are sane. */
 static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs)
@@ -63,6 +64,8 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
 	if (IS_ENABLED(CONFIG_X86_DEBUG_FPU) || unlikely(ti_work))
 		arch_exit_work(ti_work);
 
+	fred_update_rsp0();
+
 #ifdef CONFIG_COMPAT
 	/*
 	 * Compat syscalls set TS_COMPAT.  Make sure we clear it before
diff --git a/arch/x86/include/asm/fred.h b/arch/x86/include/asm/fred.h
index 66d7dbe2d314..25ca00bd70e8 100644
--- a/arch/x86/include/asm/fred.h
+++ b/arch/x86/include/asm/fred.h
@@ -36,6 +36,7 @@
 
 #ifdef CONFIG_X86_FRED
 #include <linux/kernel.h>
+#include <linux/sched/task_stack.h>
 
 #include <asm/ptrace.h>
 
@@ -87,12 +88,30 @@ void cpu_init_fred_exceptions(void);
 void cpu_init_fred_rsps(void);
 void fred_complete_exception_setup(void);
 
+DECLARE_PER_CPU(unsigned long, fred_rsp0);
+
+static __always_inline void fred_sync_rsp0(unsigned long rsp0)
+{
+	__this_cpu_write(fred_rsp0, rsp0);
+}
+
+static __always_inline void fred_update_rsp0(void)
+{
+	unsigned long rsp0 = (unsigned long) task_stack_page(current) + THREAD_SIZE;
+
+	if (cpu_feature_enabled(X86_FEATURE_FRED) && (__this_cpu_read(fred_rsp0) != rsp0)) {
+		wrmsrns(MSR_IA32_FRED_RSP0, rsp0);
+		__this_cpu_write(fred_rsp0, rsp0);
+	}
+}
 #else /* CONFIG_X86_FRED */
 static __always_inline unsigned long fred_event_data(struct pt_regs *regs) { return 0; }
 static inline void cpu_init_fred_exceptions(void) { }
 static inline void cpu_init_fred_rsps(void) { }
 static inline void fred_complete_exception_setup(void) { }
-static __always_inline void fred_entry_from_kvm(unsigned int type, unsigned int vector) { }
+static inline void fred_entry_from_kvm(unsigned int type, unsigned int vector) { }
+static inline void fred_sync_rsp0(unsigned long rsp0) { }
+static inline void fred_update_rsp0(void) { }
 #endif /* CONFIG_X86_FRED */
 #endif /* !__ASSEMBLY__ */
 
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index e9ded149a9e3..75248546403d 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -70,12 +70,9 @@ static inline void update_task_stack(struct task_struct *task)
 #ifdef CONFIG_X86_32
 	this_cpu_write(cpu_tss_rw.x86_tss.sp1, task->thread.sp0);
 #else
-	if (cpu_feature_enabled(X86_FEATURE_FRED)) {
-		wrmsrns(MSR_IA32_FRED_RSP0, (unsigned long)task_stack_page(task) + THREAD_SIZE);
-	} else if (cpu_feature_enabled(X86_FEATURE_XENPV)) {
+	if (!cpu_feature_enabled(X86_FEATURE_FRED) && cpu_feature_enabled(X86_FEATURE_XENPV))
 		/* Xen PV enters the kernel on the thread stack. */
 		load_sp0(task_top_of_stack(task));
-	}
 #endif
 }
 
diff --git a/arch/x86/kernel/fred.c b/arch/x86/kernel/fred.c
index 99a134fcd5bf..036d5cd47f88 100644
--- a/arch/x86/kernel/fred.c
+++ b/arch/x86/kernel/fred.c
@@ -21,6 +21,9 @@
 
 #define FRED_STKLVL(vector, lvl)	((lvl) << (2 * (vector)))
 
+DEFINE_PER_CPU(unsigned long, fred_rsp0);
+EXPORT_PER_CPU_SYMBOL(fred_rsp0);
+
 void cpu_init_fred_exceptions(void)
 {
 	/* When FRED is enabled by default, remove this log message */
-- 
2.46.0