spi: sun6i: fix RX data corruption in DMA mode

Merge series from Tobias Schramm <t.schramm@manjaro.org>:

This set of patches fixes two bugs in the sun6i SPI driver that result in
corruption of received data in DMA RX mode.

The first bug seems to be related to an incompatibility of the SPI RX FIFO
with wider than single byte read accesses during SPI transfers. I'm not
sure if this bug affects all types of SPI controllers found in Allwinner
SoCs supported by this driver. However reducing the access width should
always be safe. I've tested this change on a V3s SoC. Further testing to
narrow down the set of affected SoCs in the future would be welcome.

The second bug is a race between SPI RX DMA and FIFO drain logic for
interrupt-based SPI operation. This bug affects all SPI controllers
supported by this driver. Once again this change has been tested on the
Allwinner V3s SoC.

9 files changed, 92 insertions, 54 deletions

diff --git a/include/linux/clk.h b/include/linux/clk.h
index 1ef013324237..06f1b292f8a0 100644
--- a/include/linux/clk.h
+++ b/include/linux/clk.h
@@ -183,6 +183,39 @@ int clk_get_scaled_duty_cycle(struct clk *clk, unsigned int scale);
  */
 bool clk_is_match(const struct clk *p, const struct clk *q);
 
+/**
+ * clk_rate_exclusive_get - get exclusivity over the rate control of a
+ *                          producer
+ * @clk: clock source
+ *
+ * This function allows drivers to get exclusive control over the rate of a
+ * provider. It prevents any other consumer to execute, even indirectly,
+ * opereation which could alter the rate of the provider or cause glitches
+ *
+ * If exlusivity is claimed more than once on clock, even by the same driver,
+ * the rate effectively gets locked as exclusivity can't be preempted.
+ *
+ * Must not be called from within atomic context.
+ *
+ * Returns success (0) or negative errno.
+ */
+int clk_rate_exclusive_get(struct clk *clk);
+
+/**
+ * clk_rate_exclusive_put - release exclusivity over the rate control of a
+ *                          producer
+ * @clk: clock source
+ *
+ * This function allows drivers to release the exclusivity it previously got
+ * from clk_rate_exclusive_get()
+ *
+ * The caller must balance the number of clk_rate_exclusive_get() and
+ * clk_rate_exclusive_put() calls.
+ *
+ * Must not be called from within atomic context.
+ */
+void clk_rate_exclusive_put(struct clk *clk);
+
 #else
 
 static inline int clk_notifier_register(struct clk *clk,
@@ -236,6 +269,13 @@ static inline bool clk_is_match(const struct clk *p, const struct clk *q)
 	return p == q;
 }
 
+static inline int clk_rate_exclusive_get(struct clk *clk)
+{
+	return 0;
+}
+
+static inline void clk_rate_exclusive_put(struct clk *clk) {}
+
 #endif
 
 #ifdef CONFIG_HAVE_CLK_PREPARE
@@ -583,38 +623,6 @@ struct clk *devm_clk_get_optional_enabled(struct device *dev, const char *id);
  */
 struct clk *devm_get_clk_from_child(struct device *dev,
 				    struct device_node *np, const char *con_id);
-/**
- * clk_rate_exclusive_get - get exclusivity over the rate control of a
- *                          producer
- * @clk: clock source
- *
- * This function allows drivers to get exclusive control over the rate of a
- * provider. It prevents any other consumer to execute, even indirectly,
- * opereation which could alter the rate of the provider or cause glitches
- *
- * If exlusivity is claimed more than once on clock, even by the same driver,
- * the rate effectively gets locked as exclusivity can't be preempted.
- *
- * Must not be called from within atomic context.
- *
- * Returns success (0) or negative errno.
- */
-int clk_rate_exclusive_get(struct clk *clk);
-
-/**
- * clk_rate_exclusive_put - release exclusivity over the rate control of a
- *                          producer
- * @clk: clock source
- *
- * This function allows drivers to release the exclusivity it previously got
- * from clk_rate_exclusive_get()
- *
- * The caller must balance the number of clk_rate_exclusive_get() and
- * clk_rate_exclusive_put() calls.
- *
- * Must not be called from within atomic context.
- */
-void clk_rate_exclusive_put(struct clk *clk);
 
 /**
  * clk_enable - inform the system when the clock source should be running.
@@ -974,14 +982,6 @@ static inline void clk_bulk_put_all(int num_clks, struct clk_bulk_data *clks) {}
 
 static inline void devm_clk_put(struct device *dev, struct clk *clk) {}
 
-
-static inline int clk_rate_exclusive_get(struct clk *clk)
-{
-	return 0;
-}
-
-static inline void clk_rate_exclusive_put(struct clk *clk) {}
-
 static inline int clk_enable(struct clk *clk)
 {
 	return 0;
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 20284387b841..e718dbe928ba 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -25,9 +25,6 @@ static inline void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud)
 #endif
 
 vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf);
-struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
-				   unsigned long addr, pmd_t *pmd,
-				   unsigned int flags);
 bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			   pmd_t *pmd, unsigned long addr, unsigned long next);
 int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 406ab9ea818f..34f9dba17c1a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3421,15 +3421,24 @@ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags)
  * Indicates whether GUP can follow a PROT_NONE mapped page, or whether
  * a (NUMA hinting) fault is required.
  */
-static inline bool gup_can_follow_protnone(unsigned int flags)
+static inline bool gup_can_follow_protnone(struct vm_area_struct *vma,
+					   unsigned int flags)
 {
 	/*
-	 * FOLL_FORCE has to be able to make progress even if the VMA is
-	 * inaccessible. Further, FOLL_FORCE access usually does not represent
-	 * application behaviour and we should avoid triggering NUMA hinting
-	 * faults.
+	 * If callers don't want to honor NUMA hinting faults, no need to
+	 * determine if we would actually have to trigger a NUMA hinting fault.
 	 */
-	return flags & FOLL_FORCE;
+	if (!(flags & FOLL_HONOR_NUMA_FAULT))
+		return true;
+
+	/*
+	 * NUMA hinting faults don't apply in inaccessible (PROT_NONE) VMAs.
+	 *
+	 * Requiring a fault here even for inaccessible VMAs would mean that
+	 * FOLL_FORCE cannot make any progress, because handle_mm_fault()
+	 * refuses to process NUMA hinting faults in inaccessible VMAs.
+	 */
+	return !vma_is_accessible(vma);
 }
 
 typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 5e74ce4a28cd..7d30dc4ff0ff 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -1286,6 +1286,15 @@ enum {
 	FOLL_PCI_P2PDMA = 1 << 10,
 	/* allow interrupts from generic signals */
 	FOLL_INTERRUPTIBLE = 1 << 11,
+	/*
+	 * Always honor (trigger) NUMA hinting faults.
+	 *
+	 * FOLL_WRITE implicitly honors NUMA hinting faults because a
+	 * PROT_NONE-mapped page is not writable (exceptions with FOLL_FORCE
+	 * apply). get_user_pages_fast_only() always implicitly honors NUMA
+	 * hinting faults.
+	 */
+	FOLL_HONOR_NUMA_FAULT = 1 << 12,
 
 	/* See also internal only FOLL flags in mm/internal.h */
 };
diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h
index 27a6df448ee5..27cd1e59ccf7 100644
--- a/include/linux/pagewalk.h
+++ b/include/linux/pagewalk.h
@@ -6,6 +6,16 @@
 
 struct mm_walk;
 
+/* Locking requirement during a page walk. */
+enum page_walk_lock {
+	/* mmap_lock should be locked for read to stabilize the vma tree */
+	PGWALK_RDLOCK = 0,
+	/* vma will be write-locked during the walk */
+	PGWALK_WRLOCK = 1,
+	/* vma is expected to be already write-locked during the walk */
+	PGWALK_WRLOCK_VERIFY = 2,
+};
+
 /**
  * struct mm_walk_ops - callbacks for walk_page_range
  * @pgd_entry:		if set, called for each non-empty PGD (top-level) entry
@@ -66,6 +76,7 @@ struct mm_walk_ops {
 	int (*pre_vma)(unsigned long start, unsigned long end,
 		       struct mm_walk *walk);
 	void (*post_vma)(struct mm_walk *walk);
+	enum page_walk_lock walk_lock;
 };
 
 /*
diff --git a/include/linux/raid_class.h b/include/linux/raid_class.h
index 6a9b177d5c41..e50416ba9cd9 100644
--- a/include/linux/raid_class.h
+++ b/include/linux/raid_class.h
@@ -77,7 +77,3 @@ DEFINE_RAID_ATTRIBUTE(enum raid_state, state)
 	
 struct raid_template *raid_class_attach(struct raid_function_template *);
 void raid_class_release(struct raid_template *);
-
-int __must_check raid_component_add(struct raid_template *, struct device *,
-				    struct device *);
-
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 6d58c57acdaa..a156d2ed8d9e 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -459,7 +459,8 @@ struct uart_port {
 						struct serial_rs485 *rs485);
 	int			(*iso7816_config)(struct uart_port *,
 						  struct serial_iso7816 *iso7816);
-	int			ctrl_id;		/* optional serial core controller id */
+	unsigned int		ctrl_id;		/* optional serial core controller id */
+	unsigned int		port_id;		/* optional serial core port id */
 	unsigned int		irq;			/* irq number */
 	unsigned long		irqflags;		/* irq flags  */
 	unsigned int		uartclk;		/* base uart clock */
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 3930e676436c..1e8bbdb8da90 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -59,6 +59,17 @@ int trace_raw_output_prep(struct trace_iterator *iter,
 extern __printf(2, 3)
 void trace_event_printf(struct trace_iterator *iter, const char *fmt, ...);
 
+/* Used to find the offset and length of dynamic fields in trace events */
+struct trace_dynamic_info {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	u16	offset;
+	u16	len;
+#else
+	u16	len;
+	u16	offset;
+#endif
+};
+
 /*
  * The trace entry - the most basic unit of tracing. This is what
  * is printed in the end as a single line in the trace output, such as:
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index bdf8de2cdd93..7b4dd69555e4 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -155,6 +155,10 @@ retry:
 		if (gso_type & SKB_GSO_UDP)
 			nh_off -= thlen;
 
+		/* Kernel has a special handling for GSO_BY_FRAGS. */
+		if (gso_size == GSO_BY_FRAGS)
+			return -EINVAL;
+
 		/* Too small packets are not really GSO ones. */
 		if (skb->len - nh_off > gso_size) {
 			shinfo->gso_size = gso_size;