linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
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: [PATCHv6 10/16] x86/tdx: Convert shared memory back to private on kexec
Date: Wed, 24 Jan 2024 14:55:51 +0200	[thread overview]
Message-ID: <20240124125557.493675-11-kirill.shutemov@linux.intel.com> (raw)
In-Reply-To: <20240124125557.493675-1-kirill.shutemov@linux.intel.com>

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 | 124 +++++++++++++++++++++++++++++++++++++++-
 1 file changed, 122 insertions(+), 2 deletions(-)

diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index fd212c9bad89..bb77a927a831 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -6,8 +6,10 @@
 
 #include <linux/cpufeature.h>
 #include <linux/debugfs.h>
+#include <linux/delay.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>
@@ -15,6 +17,7 @@
 #include <asm/insn.h>
 #include <asm/insn-eval.h>
 #include <asm/pgtable.h>
+#include <asm/set_memory.h>
 
 /* MMIO direction */
 #define EPT_READ	0
@@ -41,6 +44,9 @@
 
 static atomic_long_t nr_shared;
 
+static atomic_t conversions_in_progress;
+static bool conversion_allowed = true;
+
 static inline bool pte_decrypted(pte_t pte)
 {
 	return cc_mkdec(pte_val(pte)) == pte_val(pte);
@@ -726,6 +732,14 @@ static bool tdx_tlb_flush_required(bool private)
 
 static bool tdx_cache_flush_required(void)
 {
+	/*
+	 * Avoid issuing CLFLUSH on set_memory_decrypted() if conversions
+	 * stopped. Otherwise it can race with unshare_all_memory() and trigger
+	 * implicit conversion to shared.
+	 */
+	if (!conversion_allowed)
+		return false;
+
 	/*
 	 * AMD SME/SEV can avoid cache flushing if HW enforces cache coherence.
 	 * TDX doesn't have such capability.
@@ -809,12 +823,25 @@ static bool tdx_enc_status_changed(unsigned long vaddr, int numpages, bool enc)
 static int tdx_enc_status_change_prepare(unsigned long vaddr, int numpages,
 					 bool enc)
 {
+	atomic_inc(&conversions_in_progress);
+
+	/*
+	 * Check after bumping conversions_in_progress to serialize
+	 * against tdx_kexec_stop_conversion().
+	 */
+	if (!conversion_allowed) {
+		atomic_dec(&conversions_in_progress);
+		return -EBUSY;
+	}
+
 	/*
 	 * Only handle shared->private conversion here.
 	 * See the comment in tdx_early_init().
 	 */
-	if (enc && !tdx_enc_status_changed(vaddr, numpages, enc))
+	if (enc && !tdx_enc_status_changed(vaddr, numpages, enc)) {
+		atomic_dec(&conversions_in_progress);
 		return -EIO;
+	}
 
 	return 0;
 }
@@ -826,17 +853,107 @@ static int tdx_enc_status_change_finish(unsigned long vaddr, int numpages,
 	 * Only handle private->shared conversion here.
 	 * See the comment in tdx_early_init().
 	 */
-	if (!enc && !tdx_enc_status_changed(vaddr, numpages, enc))
+	if (!enc && !tdx_enc_status_changed(vaddr, numpages, enc)) {
+		atomic_dec(&conversions_in_progress);
 		return -EIO;
+	}
 
 	if (enc)
 		atomic_long_sub(numpages, &nr_shared);
 	else
 		atomic_long_add(numpages, &nr_shared);
 
+	atomic_dec(&conversions_in_progress);
+
 	return 0;
 }
 
+static void tdx_kexec_stop_conversion(bool crash)
+{
+	/* Stop new private<->shared conversions */
+	conversion_allowed = false;
+
+	/*
+	 * Make sure conversion_allowed is cleared before checking
+	 * conversions_in_progress.
+	 */
+	barrier();
+
+	/*
+	 * Crash kernel reaches here with interrupts disabled: can't wait for
+	 * conversions to finish.
+	 *
+	 * If race happened, just report and proceed.
+	 */
+	if (!crash) {
+		unsigned long timeout;
+
+		/*
+		 * Wait for in-flight conversions to complete.
+		 *
+		 * Do not wait more than 30 seconds.
+		 */
+		timeout = 30 * USEC_PER_SEC;
+		while (atomic_read(&conversions_in_progress) && timeout--)
+			udelay(1);
+	}
+
+	if (atomic_read(&conversions_in_progress))
+		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 = {
@@ -896,6 +1013,9 @@ 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
-- 
2.43.0


  parent reply	other threads:[~2024-01-24 12:56 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-01-24 12:55 [PATCHv6 00/16] x86/tdx: Add kexec support Kirill A. Shutemov
2024-01-24 12:55 ` [PATCHv6 01/16] x86/acpi: Extract ACPI MADT wakeup code into a separate file Kirill A. Shutemov
2024-01-24 12:55 ` [PATCHv6 02/16] x86/apic: Mark acpi_mp_wake_* variables as __ro_after_init Kirill A. Shutemov
2024-01-24 12:55 ` [PATCHv6 03/16] cpu/hotplug: Add support for declaring CPU offlining not supported Kirill A. Shutemov
2024-01-24 12:55 ` [PATCHv6 04/16] cpu/hotplug, x86/acpi: Disable CPU offlining for ACPI MADT wakeup Kirill A. Shutemov
2024-01-24 12:55 ` [PATCHv6 05/16] x86/kexec: Keep CR4.MCE set during kexec for TDX guest Kirill A. Shutemov
2024-01-24 12:55 ` [PATCHv6 06/16] x86/mm: Make x86_platform.guest.enc_status_change_*() return errno Kirill A. Shutemov
2024-01-24 12:55 ` [PATCHv6 07/16] x86/mm: Return correct level from lookup_address() if pte is none Kirill A. Shutemov
2024-01-24 12:55 ` [PATCHv6 08/16] x86/tdx: Account shared memory Kirill A. Shutemov
2024-01-24 12:55 ` [PATCHv6 09/16] x86/mm: Adding callbacks to prepare encrypted memory for kexec Kirill A. Shutemov
2024-01-29  7:22   ` Nikolay Borisov
2024-01-24 12:55 ` Kirill A. Shutemov [this message]
2024-01-29 10:24   ` [PATCHv6 10/16] x86/tdx: Convert shared memory back to private on kexec Kalra, Ashish
2024-01-29 10:36     ` Kirill A. Shutemov
2024-01-29 13:09       ` Kalra, Ashish
2024-01-29 13:34         ` Kirill A. Shutemov
2024-01-24 12:55 ` [PATCHv6 11/16] x86/mm: Make e820_end_ram_pfn() cover E820_TYPE_ACPI ranges Kirill A. Shutemov
2024-01-24 12:55 ` [PATCHv6 12/16] x86/acpi: Rename fields in acpi_madt_multiproc_wakeup structure Kirill A. Shutemov
2024-01-24 12:55 ` [PATCHv6 13/16] x86/acpi: Do not attempt to bring up secondary CPUs in kexec case Kirill A. Shutemov
2024-01-24 12:55 ` [PATCHv6 14/16] x86/smp: Add smp_ops.stop_this_cpu() callback Kirill A. Shutemov
2024-01-26 14:08   ` Huang, Kai
2024-01-24 12:55 ` [PATCHv6 15/16] x86/mm: Introduce kernel_ident_mapping_free() Kirill A. Shutemov
2024-01-26 14:10   ` Huang, Kai
2024-01-24 12:55 ` [PATCHv6 16/16] x86/acpi: Add support for CPU offlining for ACPI MADT wakeup method Kirill A. Shutemov
2024-01-26 14:21   ` Huang, Kai
2024-01-27 18:15     ` kirill.shutemov
2024-01-26 20:03   ` Kuppuswamy Sathyanarayanan
2024-01-27 19:35     ` Kirill A. Shutemov
2024-01-30 13:43 ` [PATCHv6 00/16] x86/tdx: Add kexec support Paolo Bonzini
2024-01-30 13:55   ` Kirill A. Shutemov
2024-01-30 14:59     ` Paolo Bonzini
2024-01-30 15:15       ` Kirill A. Shutemov
2024-01-30 14:04   ` Huang, Kai
2024-01-31  7:31   ` Nikolay Borisov
2024-01-31 12:47     ` Baoquan He
2024-01-31 12:58       ` Nikolay Borisov
2024-01-31 13:07         ` Huang, Kai
2024-01-31 15:23           ` Baoquan He

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=20240124125557.493675-11-kirill.shutemov@linux.intel.com \
    --to=kirill.shutemov@linux.intel.com \
    --cc=adrian.hunter@intel.com \
    --cc=ashish.kalra@amd.com \
    --cc=bhe@redhat.com \
    --cc=bp@alien8.de \
    --cc=dave.hansen@linux.intel.com \
    --cc=elena.reshetova@intel.com \
    --cc=jun.nakajima@intel.com \
    --cc=kai.huang@intel.com \
    --cc=kexec@lists.infradead.org \
    --cc=linux-coco@lists.linux.dev \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rafael@kernel.org \
    --cc=rick.p.edgecombe@intel.com \
    --cc=sathyanarayanan.kuppuswamy@linux.intel.com \
    --cc=seanjc@google.com \
    --cc=tglx@linutronix.de \
    --cc=thomas.lendacky@amd.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).