xen/pt: allow QEMU to request MSI unmasking at bind time

When a MSI interrupt is bound to a guest using
xc_domain_update_msi_irq (XEN_DOMCTL_bind_pt_irq) the interrupt is
left masked by default.

This causes problems with guests that first configure interrupts and
clean the per-entry MSIX table mask bit and afterwards enable MSIX
globally. In such scenario the Xen internal msixtbl handlers would not
detect the unmasking of MSIX entries because vectors are not yet
registered since MSIX is not enabled, and vectors would be left
masked.

Introduce a new flag in the gflags field to signal Xen whether a MSI
interrupt should be unmasked after being bound.

This also requires to track the mask register for MSI interrupts, so
QEMU can also notify to Xen whether the MSI interrupt should be bound
masked or unmasked

Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Reported-by: Andreas Kinzler <hfp@posteo.de>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
Signed-off-by: Stefano Stabellini <sstabellini@kernel.org>
[Backported from commit a8036336609d2e184fc3543a4c439c0ba7d7f3a2
 https://git.qemu.org/?p=qemu.git;a=commit;h=a8036336609d2e184fc3543a4c439c0ba7d7f3a2
 https://xenbits.xen.org/gitweb/?p=qemu-xen.git;a=commit;h=a8036336609d2e184fc3543a4c439c0ba7d7f3a2]

Signed-off-by: Andra Paraschiv <andraprs@amazon.com>
Acked-by: Ian Jackson <ian.jackson@eu.citrix.com>

diff --git a/hw/pass-through.c b/hw/pass-through.c
index 0b76585892b7bd6ffe2f3fc97c95d7877051fd6e..c6cb60e2107d28ef9812706ce24602955063a36c 100644 (file)
--- a/hw/pass-through.c
+++ b/hw/pass-through.c
@@ -188,6 +188,9 @@ static int pt_word_reg_write(struct pt_dev *ptdev,
 static int pt_long_reg_write(struct pt_dev *ptdev,
     struct pt_reg_tbl *cfg_entry,
     uint32_t *value, uint32_t dev_value, uint32_t valid_mask);
+static int pt_mask_reg_write(struct pt_dev *ptdev,
+    struct pt_reg_tbl *cfg_entry,
+    uint32_t *value, uint32_t dev_value, uint32_t valid_mask);
 static int pt_cmd_reg_write(struct pt_dev *ptdev,
     struct pt_reg_tbl *cfg_entry,
     uint16_t *value, uint16_t dev_value, uint16_t valid_mask);
@@ -755,7 +758,7 @@ static struct pt_reg_info_tbl pt_emu_reg_msi_tbl[] = {
         .emu_mask   = 0xFFFFFFFF,
         .init       = pt_mask_reg_init,
         .u.dw.read  = pt_long_reg_read,
-        .u.dw.write = pt_long_reg_write,
+        .u.dw.write = pt_mask_reg_write,
     },
     /* Mask reg (if PCI_MSI_FLAGS_MASK_BIT set, for 64-bit devices) */
     {
@@ -766,7 +769,7 @@ static struct pt_reg_info_tbl pt_emu_reg_msi_tbl[] = {
         .emu_mask   = 0xFFFFFFFF,
         .init       = pt_mask_reg_init,
         .u.dw.read  = pt_long_reg_read,
-        .u.dw.write = pt_long_reg_write,
+        .u.dw.write = pt_mask_reg_write,
     },
     /* Pending reg (if PCI_MSI_FLAGS_MASK_BIT set, for 32-bit devices) */
     {
@@ -3572,6 +3575,22 @@ static int pt_long_reg_write(struct pt_dev *ptdev,
     return 0;
 }
 
+/* write guest mask bits */
+static int pt_mask_reg_write(struct pt_dev *ptdev,
+        struct pt_reg_tbl *cfg_entry,
+        uint32_t *value, uint32_t dev_value, uint32_t valid_mask)
+{
+    int rc;
+
+    rc = pt_long_reg_write(ptdev, cfg_entry, value, dev_value, valid_mask);
+    if (rc)
+        return rc;
+
+    ptdev->msi->mask = *value;
+
+    return 0;
+}
+
 /* write Command register */
 static int pt_cmd_reg_write(struct pt_dev *ptdev,
         struct pt_reg_tbl *cfg_entry,

diff --git a/hw/pass-through.h b/hw/pass-through.h
index bb6ddce0a8a7dc8477bfc679ee462265f1bbe9a0..0b5822414e24d199a064abccc4d378dcaf569bd6 100644 (file)
--- a/hw/pass-through.h
+++ b/hw/pass-through.h
@@ -191,6 +191,7 @@ struct pt_region {
 struct pt_msi_info {
     uint32_t flags;
     uint32_t ctrl_offset; /* saved control offset */
+    uint32_t mask;     /* guest mask bits */
     int pirq;          /* guest pirq corresponding */
     uint32_t addr_lo;  /* guest message address */
     uint32_t addr_hi;  /* guest message upper address */

diff --git a/hw/pt-msi.c b/hw/pt-msi.c
index c6baea9410b3b96a9b53c83bcc6618545149a56b..8b06450f615caa3b257492062e952ff5a5e77ca6 100644 (file)
--- a/hw/pt-msi.c
+++ b/hw/pt-msi.c
@@ -138,6 +138,9 @@ int pt_msi_update(struct pt_dev *d)
     addr = (uint64_t)d->msi->addr_hi << 32 | d->msi->addr_lo;
     gflags = __get_msi_gflags(d->msi->data, addr);
 
+    /* Current MSI emulation in QEMU only supports 1 vector */
+    gflags |= (d->msi->mask & 1) ? 0 : (1u << GLFAGS_SHIFT_UNMASKED);
+
     PT_LOG("Update msi with pirq %x gvec %x gflags %x\n",
            d->msi->pirq, gvec, gflags);
 
@@ -275,7 +278,8 @@ void pt_disable_msi_translate(struct pt_dev *dev)
     }
 }
 
-static int pt_msix_update_one(struct pt_dev *dev, int entry_nr)
+static int pt_msix_update_one(struct pt_dev *dev, int entry_nr,
+                              uint32_t vec_ctrl)
 {
     struct msix_entry_info *entry = &dev->msix->msix_entry[entry_nr];
     int pirq = entry->pirq;
@@ -316,6 +320,9 @@ static int pt_msix_update_one(struct pt_dev *dev, int entry_nr)
         entry->pirq = pirq;
     }
 
+    gflags |= (vec_ctrl & PCI_MSIX_ENTRY_CTRL_MASKBIT) ? 0 :
+        (1u << GLFAGS_SHIFT_UNMASKED);
+
     PT_LOG("Update msix entry %x with pirq %x gvec %x\n",
             entry_nr, pirq, gvec);
 
@@ -343,7 +350,7 @@ int pt_msix_update(struct pt_dev *dev)
 
     for ( i = 0; i < msix->total_entries; i++ )
     {
-        pt_msix_update_one(dev, i);
+        pt_msix_update_one(dev, i, msix->msix_entry[i].io_mem[3]);
     }
 
     return 0;
@@ -479,8 +486,18 @@ static void pci_msix_writel(void *opaque, target_phys_addr_t addr, uint32_t val)
 
     if ( offset == 3 )
     {
-        if ( msix->enabled && !(val & 0x1) )
-            pt_msix_update_one(dev, entry_nr);
+        if ( msix->enabled && !(val & 0x1) ) {
+            const volatile uint32_t *vec_ctrl;
+
+            /*
+             * If Xen intercepts the mask bit access, io_mem[3] may not be
+             * up-to-date. Read from hardware directly.
+             */
+            vec_ctrl = dev->msix->phys_iomem_base +
+                PCI_MSIX_ENTRY_SIZE * entry_nr + PCI_MSIX_ENTRY_VECTOR_CTRL;
+
+            pt_msix_update_one(dev, entry_nr, *vec_ctrl);
+        }
     }
 }
 

diff --git a/hw/pt-msi.h b/hw/pt-msi.h
index 94e0d35fe258e637c8c2ed66c49aec305d599eac..a80d76e86158d688bee9144d22960d1e9e1b1e78 100644 (file)
--- a/hw/pt-msi.h
+++ b/hw/pt-msi.h
@@ -33,6 +33,14 @@
 #define PCI_MSIX_PBA        8
 #define  PCI_MSIX_BIR       0x7
 
+/* MSI-X Table entry format */
+#define PCI_MSIX_ENTRY_SIZE             16
+#define  PCI_MSIX_ENTRY_LOWER_ADDR      0
+#define  PCI_MSIX_ENTRY_UPPER_ADDR      4
+#define  PCI_MSIX_ENTRY_DATA            8
+#define  PCI_MSIX_ENTRY_VECTOR_CTRL     12
+#define   PCI_MSIX_ENTRY_CTRL_MASKBIT   1
+
 #define MSI_FLAG_UNINIT 0x1000
 #define PT_MSI_MAPPED   0x2000
 
@@ -77,6 +85,7 @@
 #define GFLAGS_SHIFT_DM             9
 #define GLFAGS_SHIFT_DELIV_MODE     12
 #define GLFAGS_SHIFT_TRG_MODE       15
+#define GLFAGS_SHIFT_UNMASKED       16
 
 void
 msi_set_enable(struct pt_dev *dev, int en);