Received-SPF: pass (google.com: domain of linux-kernel+bounces-84041-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45e3:2400::1 as permitted sender) client-ip=2604:1380:45e3:2400::1;
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
To: Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>,
	Borislav Petkov <bp@alien8.de>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	x86@kernel.org
Cc: "Rafael J. Wysocki" <rafael@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>,
	Elena Reshetova <elena.reshetova@intel.com>,
	Jun Nakajima <jun.nakajima@intel.com>,
	Rick Edgecombe  <rick.p.edgecombe@intel.com>,
	Tom Lendacky <thomas.lendacky@amd.com>,
	"Kalra, Ashish" <ashish.kalra@amd.com>,
	Sean Christopherson <seanjc@google.com>,
	"Huang, Kai" <kai.huang@intel.com>,
	Baoquan He <bhe@redhat.com>,
	kexec@lists.infradead.org,
	linux-coco@lists.linux.dev,
	linux-kernel@vger.kernel.org,
	"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Subject: [PATCHv8 10/17] x86/tdx: Convert shared memory back to private on kexec
Date: Tue, 27 Feb 2024 23:24:45 +0200
Message-ID: <20240227212452.3228893-11-kirill.shutemov@linux.intel.com>
In-Reply-To: <20240227212452.3228893-1-kirill.shutemov@linux.intel.com>
References: <20240227212452.3228893-1-kirill.shutemov@linux.intel.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

TDX guests allocate shared buffers to perform I/O. It is done by
allocating pages normally from the buddy allocator and converting them
to shared with set_memory_decrypted().

The second kernel has no idea what memory is converted this way. It only
sees E820_TYPE_RAM.

Accessing shared memory via private mapping is fatal. It leads to
unrecoverable TD exit.

On kexec walk direct mapping and convert all shared memory back to
private. It makes all RAM private again and second kernel may use it
normally.

The conversion occurs in two steps: stopping new conversions and
unsharing all memory. In the case of normal kexec, the stopping of
conversions takes place while scheduling is still functioning. This
allows for waiting until any ongoing conversions are finished. The
second step is carried out when all CPUs except one are inactive and
interrupts are disabled. This prevents any conflicts with code that may
access shared memory.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Rick Edgecombe <rick.p.edgecombe@intel.com>
---
 arch/x86/coco/tdx/tdx.c           | 72 +++++++++++++++++++++++++++++++
 arch/x86/include/asm/pgtable.h    |  5 +++
 arch/x86/include/asm/set_memory.h |  3 ++
 arch/x86/mm/pat/set_memory.c      | 35 +++++++++++++--
 4 files changed, 112 insertions(+), 3 deletions(-)

diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index 979891e97d83..cc67f7380055 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -7,6 +7,7 @@
 #include <linux/cpufeature.h>
 #include <linux/export.h>
 #include <linux/io.h>
+#include <linux/kexec.h>
 #include <asm/coco.h>
 #include <asm/tdx.h>
 #include <asm/vmx.h>
@@ -14,6 +15,7 @@
 #include <asm/insn.h>
 #include <asm/insn-eval.h>
 #include <asm/pgtable.h>
+#include <asm/set_memory.h>
 
 /* MMIO direction */
 #define EPT_READ	0
@@ -831,6 +833,73 @@ static int tdx_enc_status_change_finish(unsigned long vaddr, int numpages,
 	return 0;
 }
 
+/* Stop new private<->shared conversions */
+static void tdx_kexec_stop_conversion(bool crash)
+{
+	/*
+	 * Crash kernel reaches here with interrupts disabled: can't wait for
+	 * conversions to finish.
+	 *
+	 * If race happened, just report and proceed.
+	 */
+	bool wait_for_lock = !crash;
+
+	if (!stop_memory_enc_conversion(wait_for_lock))
+		pr_warn("Failed to finish shared<->private conversions\n");
+}
+
+static void tdx_kexec_unshare_mem(void)
+{
+	unsigned long addr, end;
+	long found = 0, shared;
+
+	/*
+	 * Walk direct mapping and convert all shared memory back to private,
+	 */
+
+	addr = PAGE_OFFSET;
+	end  = PAGE_OFFSET + get_max_mapped();
+
+	while (addr < end) {
+		unsigned long size;
+		unsigned int level;
+		pte_t *pte;
+
+		pte = lookup_address(addr, &level);
+		size = page_level_size(level);
+
+		if (pte && pte_decrypted(*pte)) {
+			int pages = size / PAGE_SIZE;
+
+			/*
+			 * Touching memory with shared bit set triggers implicit
+			 * conversion to shared.
+			 *
+			 * Make sure nobody touches the shared range from
+			 * now on.
+			 */
+			set_pte(pte, __pte(0));
+
+			if (!tdx_enc_status_changed(addr, pages, true)) {
+				pr_err("Failed to unshare range %#lx-%#lx\n",
+				       addr, addr + size);
+			}
+
+			found += pages;
+		}
+
+		addr += size;
+	}
+
+	__flush_tlb_all();
+
+	shared = atomic_long_read(&nr_shared);
+	if (shared != found) {
+		pr_err("shared page accounting is off\n");
+		pr_err("nr_shared = %ld, nr_found = %ld\n", shared, found);
+	}
+}
+
 void __init tdx_early_init(void)
 {
 	struct tdx_module_args args = {
@@ -890,6 +959,9 @@ void __init tdx_early_init(void)
 	x86_platform.guest.enc_cache_flush_required  = tdx_cache_flush_required;
 	x86_platform.guest.enc_tlb_flush_required    = tdx_tlb_flush_required;
 
+	x86_platform.guest.enc_kexec_stop_conversion = tdx_kexec_stop_conversion;
+	x86_platform.guest.enc_kexec_unshare_mem     = tdx_kexec_unshare_mem;
+
 	/*
 	 * TDX intercepts the RDMSR to read the X2APIC ID in the parallel
 	 * bringup low level code. That raises #VE which cannot be handled
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index df0f7d4a96f3..87f18e4f9373 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -141,6 +141,11 @@ static inline int pte_young(pte_t pte)
 	return pte_flags(pte) & _PAGE_ACCESSED;
 }
 
+static inline bool pte_decrypted(pte_t pte)
+{
+	return cc_mkdec(pte_val(pte)) == pte_val(pte);
+}
+
 #define pmd_dirty pmd_dirty
 static inline bool pmd_dirty(pmd_t pmd)
 {
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index a5e89641bd2d..9d4a8e548820 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -48,8 +48,11 @@ int set_memory_wc(unsigned long addr, int numpages);
 int set_memory_wb(unsigned long addr, int numpages);
 int set_memory_np(unsigned long addr, int numpages);
 int set_memory_4k(unsigned long addr, int numpages);
+
+bool stop_memory_enc_conversion(bool wait);
 int set_memory_encrypted(unsigned long addr, int numpages);
 int set_memory_decrypted(unsigned long addr, int numpages);
+
 int set_memory_np_noalias(unsigned long addr, int numpages);
 int set_memory_nonglobal(unsigned long addr, int numpages);
 int set_memory_global(unsigned long addr, int numpages);
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 0d2267ad4e0e..a81bb24b80c6 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -2176,12 +2176,41 @@ static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc)
 	return ret;
 }
 
+static DECLARE_RWSEM(mem_enc_lock);
+
+/*
+ * Stop new private<->shared conversions.
+ *
+ * Taking the exclusive mem_enc_lock waits for in-flight conversions to complete.
+ * The lock is not released to prevent new conversions from being started.
+ *
+ * If sleep is not allowed, as in a crash scenario, try to take the lock.
+ * Failure indicates that there is a race with the conversion.
+ */
+bool stop_memory_enc_conversion(bool wait)
+{
+	if (!wait)
+		return down_write_trylock(&mem_enc_lock);
+
+	down_write(&mem_enc_lock);
+
+	return true;
+}
+
 static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
 {
-	if (cc_platform_has(CC_ATTR_MEM_ENCRYPT))
-		return __set_memory_enc_pgtable(addr, numpages, enc);
+	int ret = 0;
 
-	return 0;
+	if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
+		if (!down_read_trylock(&mem_enc_lock))
+			return -EBUSY;
+
+		ret =__set_memory_enc_pgtable(addr, numpages, enc);
+
+		up_read(&mem_enc_lock);
+	}
+
+	return ret;
 }
 
 int set_memory_encrypted(unsigned long addr, int numpages)
-- 
2.43.0