Merge tag 'riscv-mw1-6.16-rc1' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/alexghiti/linux into for-next

riscv patches for 6.16-rc1

* Implement atomic patching support for ftrace which finally allows to
  get rid of stop_machine().
* Support for kexec_file_load() syscall
* Improve module loading time by changing the algorithm that counts the
  number of plt/got entries in a module.
* Zicbop is now used in the kernel to prefetch instructions

[Palmer: There's been two rounds of surgery on this one, so as a result
it's a bit different than the PR.]

* alex-pr: (734 commits)
  riscv: Improve Kconfig help for RISCV_ISA_V_PREEMPTIVE
  MAINTAINERS: Update Atish's email address
  riscv: hwprobe: export Zabha extension
  riscv: Make regs_irqs_disabled() more clear
  perf symbols: Ignore mapping symbols on riscv
  RISC-V: Kconfig: Fix help text of CMDLINE_EXTEND
  riscv: module: Optimize PLT/GOT entry counting
  riscv: Add support for PUD THP
  riscv: xchg: Prefetch the destination word for sc.w
  riscv: Add ARCH_HAS_PREFETCH[W] support with Zicbop
  riscv: Add support for Zicbop
  riscv: Introduce Zicbop instructions
  riscv/kexec_file: Fix comment in purgatory relocator
  riscv: kexec_file: Support loading Image binary file
  riscv: kexec_file: Split the loading of kernel and others
  riscv: Documentation: add a description about dynamic ftrace
  riscv: ftrace: support direct call using call_ops
  riscv: Implement HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS
  riscv: ftrace: support PREEMPT
  riscv: add a data fence for CMODX in the kernel mode
  ...

Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>

1 files changed, 19 insertions, 8 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index 9f627caedc3f6..667080cc9ae1c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -75,11 +75,25 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf,
  */
 static int amdgpu_dma_buf_pin(struct dma_buf_attachment *attach)
 {
-	struct drm_gem_object *obj = attach->dmabuf->priv;
-	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+	struct dma_buf *dmabuf = attach->dmabuf;
+	struct amdgpu_bo *bo = gem_to_amdgpu_bo(dmabuf->priv);
+	u32 domains = bo->preferred_domains;
 
-	/* pin buffer into GTT */
-	return amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT);
+	dma_resv_assert_held(dmabuf->resv);
+
+	/*
+	 * Try pinning into VRAM to allow P2P with RDMA NICs without ODP
+	 * support if all attachments can do P2P. If any attachment can't do
+	 * P2P just pin into GTT instead.
+	 */
+	list_for_each_entry(attach, &dmabuf->attachments, node)
+		if (!attach->peer2peer)
+			domains &= ~AMDGPU_GEM_DOMAIN_VRAM;
+
+	if (domains & AMDGPU_GEM_DOMAIN_VRAM)
+		bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
+
+	return amdgpu_bo_pin(bo, domains);
 }
 
 /**
@@ -134,9 +148,6 @@ static struct sg_table *amdgpu_dma_buf_map(struct dma_buf_attachment *attach,
 		r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 		if (r)
 			return ERR_PTR(r);
-
-	} else if (bo->tbo.resource->mem_type != TTM_PL_TT) {
-		return ERR_PTR(-EBUSY);
 	}
 
 	switch (bo->tbo.resource->mem_type) {
@@ -184,7 +195,7 @@ static void amdgpu_dma_buf_unmap(struct dma_buf_attachment *attach,
 				 struct sg_table *sgt,
 				 enum dma_data_direction dir)
 {
-	if (sgt->sgl->page_link) {
+	if (sg_page(sgt->sgl)) {
 		dma_unmap_sgtable(attach->dev, sgt, dir, 0);
 		sg_free_table(sgt);
 		kfree(sgt);