[PATCH][v7] x86, suspend: Save/restore extra MSR registers for suspend

[Chen Yu]

A bug was reported that on certain Broadwell platforms, after resuming from S3,
the CPU is running at an anomalously low speed.

It turns out that the BIOS has modified the value of the THERM_CONTROL register
during S3, and changed it from 0 to 0x10, thus enabled clock modulation(bit4),
but with undefined CPU Duty Cycle(bit1:3) - which causes the problem.

Here is a simple scenario to reproduce the issue:

 1. Boot up the system
 2. Get MSR 0x19a, it should be 0
 3. Put the system into sleep, then wake it up
 4. Get MSR 0x19a, it shows 0x10, while it should be 0

Although some BIOSen want to change the CPU Duty Cycle during S3, in our case we
don't want the BIOS to do any modification.

Fix this issue by introducing a more generic x86 framework to save/restore
specified MSR registers(THERM_CONTROL in this case) for suspend/resume. This
allows us to fix similar bugs in a much simpler way in the future.

When the kernel wants to protect certain MSRs during suspending, we simply add a
quirk entry in msr_save_dmi_table, and customize the MSR registers inside the
quirk callback, for example:

  u32 msr_id_need_to_save[] = {MSR_ID0, MSR_ID1, MSR_ID2...};

and the quirk mechanism ensures that, once resumed from suspend, the MSRs
indicated by these IDs will be restored to their original, pre-suspend values.

Since both 64-bit and 32-bit kernels are affected, this patch covers the common
64/32-bit suspend/resume code path. And because the MSRs specified by the user
might not be available or readable in any situation, we use rdmsrl_safe() to
safely save these MSRs.

Reported-and-tested-by: Marcin Kaszewski <marcin.kaszewski@xxxxxxxxx>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx>
Acked-by: Pavel Machek <pavel@xxxxxx>
Signed-off-by: Chen Yu <yu.c.chen@xxxxxxxxx>
---
v7:
 - Use the improved version of changelog, and
   modify the patch according to:
   https://patchwork.kernel.org/patch/7637861/
---
 arch/x86/include/asm/msr.h        | 10 +++++
 arch/x86/include/asm/suspend_32.h |  1 +
 arch/x86/include/asm/suspend_64.h |  1 +
 arch/x86/power/cpu.c              | 94 +++++++++++++++++++++++++++++++++++++++
 4 files changed, 106 insertions(+)

diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 77d8b28..df49b3d 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -32,6 +32,16 @@ struct msr_regs_info {
 	int err;
 };
 
+struct saved_msr {
+	bool msr_saved;
+	struct msr_info rv;
+};
+
+struct saved_msrs {
+	unsigned int num;
+	struct saved_msr *msr_array;
+};
+
 static inline unsigned long long native_read_tscp(unsigned int *aux)
 {
 	unsigned long low, high;
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
index d1793f0..8e9dbe7 100644
--- a/arch/x86/include/asm/suspend_32.h
+++ b/arch/x86/include/asm/suspend_32.h
@@ -15,6 +15,7 @@ struct saved_context {
 	unsigned long cr0, cr2, cr3, cr4;
 	u64 misc_enable;
 	bool misc_enable_saved;
+	struct saved_msrs saved_msrs;
 	struct desc_ptr gdt_desc;
 	struct desc_ptr idt;
 	u16 ldt;
diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h
index 7ebf0eb..6136a18 100644
--- a/arch/x86/include/asm/suspend_64.h
+++ b/arch/x86/include/asm/suspend_64.h
@@ -24,6 +24,7 @@ struct saved_context {
 	unsigned long cr0, cr2, cr3, cr4, cr8;
 	u64 misc_enable;
 	bool misc_enable_saved;
+	struct saved_msrs saved_msrs;
 	unsigned long efer;
 	u16 gdt_pad; /* Unused */
 	struct desc_ptr gdt_desc;
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 9ab5279..103f271 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -23,6 +23,7 @@
 #include <asm/debugreg.h>
 #include <asm/cpu.h>
 #include <asm/mmu_context.h>
+#include <linux/dmi.h>
 
 #ifdef CONFIG_X86_32
 __visible unsigned long saved_context_ebx;
@@ -32,6 +33,29 @@ __visible unsigned long saved_context_eflags;
 #endif
 struct saved_context saved_context;
 
+static void msr_save_context(struct saved_context *ctxt)
+{
+	struct saved_msr *msr = ctxt->saved_msrs.msr_array;
+	struct saved_msr *end = msr + ctxt->saved_msrs.num;
+
+	while (msr < end) {
+		msr->msr_saved = !rdmsrl_safe(msr->rv.msr_no, &msr->rv.reg.q);
+		msr++;
+	}
+}
+
+static void msr_restore_context(struct saved_context *ctxt)
+{
+	struct saved_msr *msr = ctxt->saved_msrs.msr_array;
+	struct saved_msr *end = msr + ctxt->saved_msrs.num;
+
+	while (msr < end) {
+		if (msr->msr_saved)
+			wrmsrl(msr->rv.msr_no, msr->rv.reg.q);
+		msr++;
+	}
+}
+
 /**
  *	__save_processor_state - save CPU registers before creating a
  *		hibernation image and before restoring the memory state from it
@@ -111,6 +135,7 @@ static void __save_processor_state(struct saved_context *ctxt)
 #endif
 	ctxt->misc_enable_saved = !rdmsrl_safe(MSR_IA32_MISC_ENABLE,
 					       &ctxt->misc_enable);
+	msr_save_context(ctxt);
 }
 
 /* Needed by apm.c */
@@ -229,6 +254,7 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
 	x86_platform.restore_sched_clock_state();
 	mtrr_bp_restore();
 	perf_restore_debug_store();
+	msr_restore_context(ctxt);
 }
 
 /* Needed by apm.c */
@@ -320,3 +346,71 @@ static int __init bsp_pm_check_init(void)
 }
 
 core_initcall(bsp_pm_check_init);
+
+static int msr_init_context(const u32 *msr_id, const int total_num)
+{
+	int i = 0;
+	struct saved_msr *msr;
+
+	if (saved_context.saved_msrs.msr_array ||
+			saved_context.saved_msrs.num > 0) {
+		pr_err("x86/pm: Quirk already applied, please check your dmi match table.\n");
+		return -EINVAL;
+	}
+
+	msr = kmalloc_array(total_num,
+			sizeof(struct saved_msr), GFP_KERNEL);
+	if (!msr) {
+		pr_err("x86/pm: Can not allocate memory to save/restore MSRs during suspend.\n");
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < total_num; i++) {
+		msr[i].rv.msr_no = msr_id[i];
+		msr[i].msr_saved = false;
+		msr[i].rv.reg.q = 0;
+	}
+	saved_context.saved_msrs.num = total_num;
+	saved_context.saved_msrs.msr_array = msr;
+
+	return 0;
+}
+
+/*
+ * The following section is a quirk framework for problematic BIOSen:
+ * Sometimes MSRs are modified by the BIOSen after suspended to
+ * RAM, this might cause unexpected behavior after wakeup.
+ * Thus we save/restore these specified MSRs across suspend/resume
+ * in order to work around it.
+ *
+ * For any further problematic BIOSen/platforms,
+ * please add your own function similar to msr_initialize_bdw.
+ */
+static int msr_initialize_bdw(const struct dmi_system_id *d)
+{
+	/* Add any extra MSR ids into this array. */
+	u32 bdw_msr_id[] = { MSR_IA32_THERM_CONTROL };
+
+	pr_info("x86/pm: %s detected, MSR saving is needed during suspending.\n", d->ident);
+	return msr_init_context(bdw_msr_id, ARRAY_SIZE(bdw_msr_id));
+}
+
+static struct dmi_system_id msr_save_dmi_table[] = {
+	{
+	 .callback = msr_initialize_bdw,
+	 .ident = "BROADWELL BDX_EP",
+	 .matches = {
+		DMI_MATCH(DMI_PRODUCT_NAME, "GRANTLEY"),
+		DMI_MATCH(DMI_PRODUCT_VERSION, "E63448-400"),
+		},
+	},
+	{}
+};
+
+static int pm_check_save_msr(void)
+{
+	dmi_check_system(msr_save_dmi_table);
+	return 0;
+}
+
+device_initcall(pm_check_save_msr);
-- 
1.8.4.2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/