iommu: Add universal DMA helper functions

Not that long ago, every device implementation using DMA directly
accessed guest memory using cpu_physical_memory_*().  This meant that
adding support for a guest visible IOMMU would require changing every
one of these devices to go through IOMMU translation.

Shortly before qemu 1.0, I made a start on fixing this by providing
helper functions for PCI DMA.  These are currently just stubs which
call the direct access functions, but mean that an IOMMU can be
implemented in one place, rather than for every PCI device.

Clearly, this doesn't help for non PCI devices, which could also be
IOMMU translated on some platforms.  It is also problematic for the
devices which have both PCI and non-PCI version (e.g. OHCI, AHCI) - we
cannot use the the pci_dma_*() functions, because they assume the
presence of a PCIDevice, but we don't want to have to check between
pci_dma_*() and cpu_physical_memory_*() every time we do a DMA in the
device code.

This patch makes the first step on addressing both these problems, by
introducing new (stub) dma helper functions which can be used for any
DMA capable device.

These dma functions take a DMAContext *, a new (currently empty)
variable describing the DMA address space in which the operation is to
take place.  NULL indicates untranslated DMA directly into guest
physical address space.  The intention is that in future non-NULL
values will given information about any necessary IOMMU translation.

DMA using devices must obtain a DMAContext (or, potentially, contexts)
from their bus or platform.  For now this patch just converts the PCI
wrappers to be implemented in terms of the universal wrappers,
converting other drivers can take place over time.

Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro>
Cc: Richard Henderson <rth@twiddle.net>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>

diff --git a/dma-helpers.c b/dma-helpers.c
index 7971a89c144b7f192b15a5b9691009e58dcc4a41..5265132edf435f221cd27b331d7008d2b6bf0f2b 100644 (file)
--- a/dma-helpers.c
+++ b/dma-helpers.c
@@ -10,6 +10,22 @@
 #include "dma.h"
 #include "trace.h"
 
+int dma_memory_set(DMAContext *dma, dma_addr_t addr, uint8_t c, dma_addr_t len)
+{
+#define FILLBUF_SIZE 512
+    uint8_t fillbuf[FILLBUF_SIZE];
+    int l;
+
+    memset(fillbuf, c, FILLBUF_SIZE);
+    while (len > 0) {
+        l = len < FILLBUF_SIZE ? len : FILLBUF_SIZE;
+        cpu_physical_memory_rw(addr, fillbuf, l, true);
+        len -= len;
+        addr += len;
+    }
+    return 0;
+}
+
 void qemu_sglist_init(QEMUSGList *qsg, int alloc_hint)
 {
     qsg->sg = g_malloc(alloc_hint * sizeof(ScatterGatherEntry));

diff --git a/dma.h b/dma.h
index fe08b726057d0e6b886bd1e569760373ff106522..8912dfcb6e9703669372b6ebf7321cc50e9c8b17 100644 (file)
--- a/dma.h
+++ b/dma.h
@@ -14,6 +14,7 @@
 #include "hw/hw.h"
 #include "block.h"
 
+typedef struct DMAContext DMAContext;
 typedef struct ScatterGatherEntry ScatterGatherEntry;
 
 typedef enum {
@@ -34,6 +35,100 @@ typedef target_phys_addr_t dma_addr_t;
 #define DMA_ADDR_BITS TARGET_PHYS_ADDR_BITS
 #define DMA_ADDR_FMT TARGET_FMT_plx
 
+/* Checks that the given range of addresses is valid for DMA.  This is
+ * useful for certain cases, but usually you should just use
+ * dma_memory_{read,write}() and check for errors */
+static inline bool dma_memory_valid(DMAContext *dma, dma_addr_t addr,
+                                    dma_addr_t len, DMADirection dir)
+{
+    /* Stub version, with no iommu we assume all bus addresses are valid */
+    return true;
+}
+
+static inline int dma_memory_rw(DMAContext *dma, dma_addr_t addr,
+                                void *buf, dma_addr_t len, DMADirection dir)
+{
+    /* Stub version when we have no iommu support */
+    cpu_physical_memory_rw(addr, buf, (target_phys_addr_t)len,
+                           dir == DMA_DIRECTION_FROM_DEVICE);
+    return 0;
+}
+
+static inline int dma_memory_read(DMAContext *dma, dma_addr_t addr,
+                                  void *buf, dma_addr_t len)
+{
+    return dma_memory_rw(dma, addr, buf, len, DMA_DIRECTION_TO_DEVICE);
+}
+
+static inline int dma_memory_write(DMAContext *dma, dma_addr_t addr,
+                                   const void *buf, dma_addr_t len)
+{
+    return dma_memory_rw(dma, addr, (void *)buf, len,
+                         DMA_DIRECTION_FROM_DEVICE);
+}
+
+int dma_memory_set(DMAContext *dma, dma_addr_t addr, uint8_t c, dma_addr_t len);
+
+static inline void *dma_memory_map(DMAContext *dma,
+                                   dma_addr_t addr, dma_addr_t *len,
+                                   DMADirection dir)
+{
+    target_phys_addr_t xlen = *len;
+    void *p;
+
+    p = cpu_physical_memory_map(addr, &xlen,
+                                dir == DMA_DIRECTION_FROM_DEVICE);
+    *len = xlen;
+    return p;
+}
+
+static inline void dma_memory_unmap(DMAContext *dma,
+                                    void *buffer, dma_addr_t len,
+                                    DMADirection dir, dma_addr_t access_len)
+{
+    return cpu_physical_memory_unmap(buffer, (target_phys_addr_t)len,
+                                     dir == DMA_DIRECTION_FROM_DEVICE,
+                                     access_len);
+}
+
+#define DEFINE_LDST_DMA(_lname, _sname, _bits, _end) \
+    static inline uint##_bits##_t ld##_lname##_##_end##_dma(DMAContext *dma, \
+                                                            dma_addr_t addr) \
+    {                                                                   \
+        uint##_bits##_t val;                                            \
+        dma_memory_read(dma, addr, &val, (_bits) / 8);                  \
+        return _end##_bits##_to_cpu(val);                               \
+    }                                                                   \
+    static inline void st##_sname##_##_end##_dma(DMAContext *dma,       \
+                                                 dma_addr_t addr,       \
+                                                 uint##_bits##_t val)   \
+    {                                                                   \
+        val = cpu_to_##_end##_bits(val);                                \
+        dma_memory_write(dma, addr, &val, (_bits) / 8);                 \
+    }
+
+static inline uint8_t ldub_dma(DMAContext *dma, dma_addr_t addr)
+{
+    uint8_t val;
+
+    dma_memory_read(dma, addr, &val, 1);
+    return val;
+}
+
+static inline void stb_dma(DMAContext *dma, dma_addr_t addr, uint8_t val)
+{
+    dma_memory_write(dma, addr, &val, 1);
+}
+
+DEFINE_LDST_DMA(uw, w, 16, le);
+DEFINE_LDST_DMA(l, l, 32, le);
+DEFINE_LDST_DMA(q, q, 64, le);
+DEFINE_LDST_DMA(uw, w, 16, be);
+DEFINE_LDST_DMA(l, l, 32, be);
+DEFINE_LDST_DMA(q, q, 64, be);
+
+#undef DEFINE_LDST_DMA
+
 struct ScatterGatherEntry {
     dma_addr_t base;
     dma_addr_t len;

diff --git a/hw/pci.h b/hw/pci.h
index 95b608cedd9f8aa14c6d94a32fe08cef450cc8be..f148613a8e699895dd72ce666612ea551742f02f 100644 (file)
--- a/hw/pci.h
+++ b/hw/pci.h
@@ -560,10 +560,16 @@ static inline uint32_t pci_config_size(const PCIDevice *d)
 }
 
 /* DMA access functions */
+static inline DMAContext *pci_dma_context(PCIDevice *dev)
+{
+    /* Stub for when we have no PCI iommu support */
+    return NULL;
+}
+
 static inline int pci_dma_rw(PCIDevice *dev, dma_addr_t addr,
                              void *buf, dma_addr_t len, DMADirection dir)
 {
-    cpu_physical_memory_rw(addr, buf, len, dir == DMA_DIRECTION_FROM_DEVICE);
+    dma_memory_rw(pci_dma_context(dev), addr, buf, len, dir);
     return 0;
 }
 
@@ -583,12 +589,12 @@ static inline int pci_dma_write(PCIDevice *dev, dma_addr_t addr,
     static inline uint##_bits##_t ld##_l##_pci_dma(PCIDevice *dev,      \
                                                    dma_addr_t addr)     \
     {                                                                   \
-        return ld##_l##_phys(addr);                                     \
+        return ld##_l##_dma(pci_dma_context(dev), addr);                \
     }                                                                   \
     static inline void st##_s##_pci_dma(PCIDevice *dev,                 \
-                          dma_addr_t addr, uint##_bits##_t val)         \
+                                        dma_addr_t addr, uint##_bits##_t val) \
     {                                                                   \
-        st##_s##_phys(addr, val);                                       \
+        st##_s##_dma(pci_dma_context(dev), addr, val);                  \
     }
 
 PCI_DMA_DEFINE_LDST(ub, b, 8);
@@ -604,19 +610,16 @@ PCI_DMA_DEFINE_LDST(q_be, q_be, 64);
 static inline void *pci_dma_map(PCIDevice *dev, dma_addr_t addr,
                                 dma_addr_t *plen, DMADirection dir)
 {
-    target_phys_addr_t len = *plen;
     void *buf;
 
-    buf = cpu_physical_memory_map(addr, &len, dir == DMA_DIRECTION_FROM_DEVICE);
-    *plen = len;
+    buf = dma_memory_map(pci_dma_context(dev), addr, plen, dir);
     return buf;
 }
 
 static inline void pci_dma_unmap(PCIDevice *dev, void *buffer, dma_addr_t len,
                                  DMADirection dir, dma_addr_t access_len)
 {
-    cpu_physical_memory_unmap(buffer, len, dir == DMA_DIRECTION_FROM_DEVICE,
-                              access_len);
+    dma_memory_unmap(pci_dma_context(dev), buffer, len, dir, access_len);
 }
 
 static inline void pci_dma_sglist_init(QEMUSGList *qsg, PCIDevice *dev,