Merge remote-tracking branch 'remotes/dgibson/tags/ppc-for-4.0-20190312' into staging

ppc patch queue for 2019-03-10

This pull requests supersedes ppc-for-4.0-20190310.  Changes are:
 * Fixed a bunch of minor style problems
 * Suppressed warnings about Spectre/Meltdown mitigations with TCG
 * Added one more patch, a preliminary fix towards the not-quite-ready
   support for NVLink VFIO passthrough.

This is a final pull request before the 4.0 soft freeze.  Changes
include:
  * A Great Renaming to use camel case properly in spapr code
  * Optimization of some vector instructions
  * Support for POWER9 cpus in the powernv machine
  * Fixes a regression from the last pull request in handling VSX
    instructions with mixed operands from the FPR and VMX parts of the
    register array
  * Optimization hack to avoid scanning all the (empty) entries on a
    new IOMMU window
  * Add FSL I2C controller model for E500
  * Support for KVM acceleration of the H_PAGE_INIT hypercall on spapr
  * Update u-boot image for E500
  * Enable Specre/Meltdown mitigations by default on the new machine type
  * Enable large decrementer support for POWER9

# gpg: Signature made Tue 12 Mar 2019 08:14:51 GMT
# gpg:                using RSA key 75F46586AE61A66CC44E87DC6C38CACA20D9B392
# gpg: Good signature from "David Gibson <david@gibson.dropbear.id.au>" [full]
# gpg:                 aka "David Gibson (Red Hat) <dgibson@redhat.com>" [full]
# gpg:                 aka "David Gibson (ozlabs.org) <dgibson@ozlabs.org>" [full]
# gpg:                 aka "David Gibson (kernel.org) <dwg@kernel.org>" [unknown]
# Primary key fingerprint: 75F4 6586 AE61 A66C C44E  87DC 6C38 CACA 20D9 B392

* remotes/dgibson/tags/ppc-for-4.0-20190312: (62 commits)
  vfio: Make vfio_get_region_info_cap public
  Suppress test warnings about missing Spectre/Meltdown mitigations with TCG
  spapr: Use CamelCase properly
  target/ppc: Optimize x[sv]xsigdp using deposit_i64()
  target/ppc: Optimize xviexpdp() using deposit_i64()
  target/ppc: add HV support for POWER9
  ppc/pnv: add a "ibm,opal/power-mgt" device tree node on POWER9
  ppc/pnv: add more dummy XSCOM addresses
  ppc/pnv: activate XSCOM tests for POWER9
  ppc/pnv: POWER9 XSCOM quad support
  ppc/pnv: extend XSCOM core support for POWER9
  ppc/pnv: add a OCC model for POWER9
  ppc/pnv: add a OCC model class
  ppc/pnv: add SerIRQ routing registers
  ppc/pnv: add a LPC Controller model for POWER9
  ppc/pnv: add a 'dt_isa_nodename' to the chip
  ppc/pnv: add a LPC Controller class model
  ppc/pnv: lpc: fix OPB address ranges
  ppc/pnv: add a PSI bridge model for POWER9
  ppc/pnv: add a PSI bridge class model
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 36 insertions, 13 deletions

diff --git a/hw/vfio/spapr.c b/hw/vfio/spapr.c
index becf71a3fc..57fe758e54 100644
--- a/hw/vfio/spapr.c
+++ b/hw/vfio/spapr.c
@@ -143,19 +143,19 @@ int vfio_spapr_create_window(VFIOContainer *container,
                              MemoryRegionSection *section,
                              hwaddr *pgsize)
 {
-    int ret;
+    int ret = 0;
     IOMMUMemoryRegion *iommu_mr = IOMMU_MEMORY_REGION(section->mr);
     uint64_t pagesize = memory_region_iommu_get_min_page_size(iommu_mr);
-    unsigned entries, pages;
+    unsigned entries, bits_total, bits_per_level, max_levels;
     struct vfio_iommu_spapr_tce_create create = { .argsz = sizeof(create) };
-    long systempagesize = qemu_getrampagesize();
+    long rampagesize = qemu_getrampagesize();
 
     /*
      * The host might not support the guest supported IOMMU page size,
      * so we will use smaller physical IOMMU pages to back them.
      */
-    if (pagesize > systempagesize) {
-        pagesize = systempagesize;
+    if (pagesize > rampagesize) {
+        pagesize = rampagesize;
     }
     pagesize = 1ULL << (63 - clz64(container->pgsizes &
                                    (pagesize | (pagesize - 1))));
@@ -176,16 +176,38 @@ int vfio_spapr_create_window(VFIOContainer *container,
     create.window_size = int128_get64(section->size);
     create.page_shift = ctz64(pagesize);
     /*
-     * SPAPR host supports multilevel TCE tables, there is some
-     * heuristic to decide how many levels we want for our table:
-     * 0..64 = 1; 65..4096 = 2; 4097..262144 = 3; 262145.. = 4
+     * SPAPR host supports multilevel TCE tables. We try to guess optimal
+     * levels number and if this fails (for example due to the host memory
+     * fragmentation), we increase levels. The DMA address structure is:
+     * rrrrrrrr rxxxxxxx xxxxxxxx xxxxxxxx  xxxxxxxx xxxxxxxx xxxxxxxx iiiiiiii
+     * where:
+     *   r = reserved (bits >= 55 are reserved in the existing hardware)
+     *   i = IOMMU page offset (64K in this example)
+     *   x = bits to index a TCE which can be split to equal chunks to index
+     *      within the level.
+     * The aim is to split "x" to smaller possible number of levels.
      */
     entries = create.window_size >> create.page_shift;
-    pages = MAX((entries * sizeof(uint64_t)) / getpagesize(), 1);
-    pages = MAX(pow2ceil(pages), 1); /* Round up */
-    create.levels = ctz64(pages) / 6 + 1;
-
-    ret = ioctl(container->fd, VFIO_IOMMU_SPAPR_TCE_CREATE, &create);
+    /* bits_total is number of "x" needed */
+    bits_total = ctz64(entries * sizeof(uint64_t));
+    /*
+     * bits_per_level is a safe guess of how much we can allocate per level:
+     * 8 is the current minimum for CONFIG_FORCE_MAX_ZONEORDER and MAX_ORDER
+     * is usually bigger than that.
+     * Below we look at getpagesize() as TCEs are allocated from system pages.
+     */
+    bits_per_level = ctz64(getpagesize()) + 8;
+    create.levels = bits_total / bits_per_level;
+    if (bits_total % bits_per_level) {
+        ++create.levels;
+    }
+    max_levels = (64 - create.page_shift) / ctz64(getpagesize());
+    for ( ; create.levels <= max_levels; ++create.levels) {
+        ret = ioctl(container->fd, VFIO_IOMMU_SPAPR_TCE_CREATE, &create);
+        if (!ret) {
+            break;
+        }
+    }
     if (ret) {
         error_report("Failed to create a window, ret = %d (%m)", ret);
         return -errno;
@@ -200,6 +222,7 @@ int vfio_spapr_create_window(VFIOContainer *container,
         return -EINVAL;
     }
     trace_vfio_spapr_create_window(create.page_shift,
+                                   create.levels,
                                    create.window_size,
                                    create.start_addr);
     *pgsize = pagesize;