From:   Lai Jiangshan <jiangshanlai@gmail.com>
To:     linux-kernel@vger.kernel.org
Cc:     x86@kernel.org, Lai Jiangshan <laijs@linux.alibaba.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Andy Lutomirski <luto@kernel.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        "H. Peter Anvin" <hpa@zytor.com>
Subject: [PATCH V6 32/49] x86/entry: Add the C version ist_restore_cr3()
Date:   Fri, 26 Nov 2021 18:11:52 +0800
Message-Id: <20211126101209.8613-33-jiangshanlai@gmail.com>
In-Reply-To: <20211126101209.8613-1-jiangshanlai@gmail.com>
References: <20211126101209.8613-1-jiangshanlai@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Lai Jiangshan <laijs@linux.alibaba.com>

It implements the C version of RESTORE_CR3().

Not functional difference intended except the ASM code uses bit test
and clear operations while the C version uses mask check and 'AND'
operations.  The resulted asm code of both versions are very similar.

Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
---
 arch/x86/entry/entry64.c | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/arch/x86/entry/entry64.c b/arch/x86/entry/entry64.c
index 283bd685a275..5f47221d8935 100644
--- a/arch/x86/entry/entry64.c
+++ b/arch/x86/entry/entry64.c
@@ -11,6 +11,7 @@
  * environments that the GS base is user controlled value, or the CR3
  * is PTI user CR3 or both.
  */
+#include <asm/tlbflush.h>
 #include <asm/traps.h>
 
 extern unsigned char asm_load_gs_index_gs_change[];
@@ -30,6 +31,26 @@ static __always_inline void pti_switch_to_kernel_cr3(unsigned long user_cr3)
 	native_write_cr3(cr3);
 }
 
+static __always_inline void pti_switch_to_user_cr3(unsigned long user_cr3)
+{
+#define KERN_PCID_MASK (CR3_PCID_MASK & ~PTI_USER_PCID_MASK)
+
+	if (static_cpu_has(X86_FEATURE_PCID)) {
+		int pcid = user_cr3 & KERN_PCID_MASK;
+		unsigned short pcid_mask = 1ull << pcid;
+
+		/*
+		 * Check if there's a pending flush for the user ASID we're
+		 * about to set.
+		 */
+		if (!(this_cpu_read(cpu_tlbstate.user_pcid_flush_mask) & pcid_mask))
+			user_cr3 |= X86_CR3_PCID_NOFLUSH;
+		else
+			this_cpu_and(cpu_tlbstate.user_pcid_flush_mask, ~pcid_mask);
+	}
+	native_write_cr3(user_cr3);
+}
+
 static __always_inline void switch_to_kernel_cr3(void)
 {
 	if (static_cpu_has(X86_FEATURE_PTI))
@@ -49,9 +70,20 @@ static __always_inline unsigned long ist_switch_to_kernel_cr3(void)
 
 	return cr3;
 }
+
+static __always_inline void ist_restore_cr3(unsigned long cr3)
+{
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
+
+	/* No need to restore when @cr3 is kernel CR3. */
+	if (cr3 & PTI_USER_PGTABLE_MASK)
+		pti_switch_to_user_cr3(cr3);
+}
 #else
 static __always_inline void switch_to_kernel_cr3(void) {}
 static __always_inline unsigned long ist_switch_to_kernel_cr3(void) { return 0; }
+static __always_inline void ist_restore_cr3(unsigned long cr3) {}
 #endif
 
 /*
-- 
2.19.1.6.gb485710b