diff --git a/src/broadcom/vulkan/v3dv_cmd_buffer.c b/src/broadcom/vulkan/v3dv_cmd_buffer.c
index 0bba41e631a..f300e58339e 100644
--- a/src/broadcom/vulkan/v3dv_cmd_buffer.c
+++ b/src/broadcom/vulkan/v3dv_cmd_buffer.c
@@ -493,7 +493,7 @@ v3dv_job_start_frame(struct v3dv_job *job,
 static bool
 job_should_enable_double_buffer(struct v3dv_job *job)
 {
-   /* Inocmpatibility with double-buffer */
+   /* Incompatibility with double-buffer */
    if (!job->can_use_double_buffer)
       return false;
 
@@ -1686,7 +1686,7 @@ v3dv_cmd_buffer_subpass_start(struct v3dv_cmd_buffer *cmd_buffer,
     *
     * Secondary command buffers don't start subpasses (and may not even have
     * framebuffer state), so we only care about this in primaries. The only
-    * exception could be a secondary runnning inside a subpass that needs to
+    * exception could be a secondary running inside a subpass that needs to
     * record a meta operation (with its own render pass) that relies on
     * attachment load clears, but we don't have any instances of that right
     * now.
@@ -2580,7 +2580,7 @@ cmd_buffer_pre_draw_split_job(struct v3dv_cmd_buffer *cmd_buffer)
  *    in rasterization."
  *
  * We need to enable MSAA in the TILE_BINNING_MODE_CFG packet, which we
- * emit when we start a new frame at the begining of a subpass. At that point,
+ * emit when we start a new frame at the beginning of a subpass. At that point,
  * if the framebuffer doesn't have any attachments we won't enable MSAA and
  * the job won't be valid in the scenario described by the spec.
  *
@@ -3351,7 +3351,7 @@ v3dv_CmdSetDepthBounds(VkCommandBuffer commandBuffer,
                        float minDepthBounds,
                        float maxDepthBounds)
 {
-   /* We do not support depth bounds testing so we just ingore this. We are
+   /* We do not support depth bounds testing so we just ignore this. We are
     * already asserting that pipelines don't enable the feature anyway.
     */
 }
@@ -3622,7 +3622,7 @@ v3dv_cmd_buffer_schedule_end_query(struct v3dv_cmd_buffer *cmd_buffer,
        *
        * In our case, only the first query is used but this means we still need
        * to flag the other queries as available so we don't emit errors when
-       * the applications attempt to retrive values from them.
+       * the applications attempt to retrieve values from them.
        */
       struct v3dv_render_pass *pass = cmd_buffer->state.pass;
       if (!pass->multiview_enabled) {
diff --git a/src/broadcom/vulkan/v3dv_image.c b/src/broadcom/vulkan/v3dv_image.c
index ebf2432b132..b1d63ef5f83 100644
--- a/src/broadcom/vulkan/v3dv_image.c
+++ b/src/broadcom/vulkan/v3dv_image.c
@@ -187,7 +187,7 @@ v3d_setup_slices(struct v3dv_image *image)
 
       /* The HW aligns level 1's base to a page if any of level 1 or
        * below could be UIF XOR.  The lower levels then inherit the
-       * alignment for as long as necesary, thanks to being power of
+       * alignment for as long as necessary, thanks to being power of
        * two aligned.
        */
       if (i == 1 &&
diff --git a/src/broadcom/vulkan/v3dv_meta_copy.c b/src/broadcom/vulkan/v3dv_meta_copy.c
index 437a86d85d3..53599987021 100644
--- a/src/broadcom/vulkan/v3dv_meta_copy.c
+++ b/src/broadcom/vulkan/v3dv_meta_copy.c
@@ -1318,7 +1318,7 @@ copy_buffer_to_image_tfu(struct v3dv_cmd_buffer *cmd_buffer,
     * at a time, and the TFU copies full images. Also, V3D depth bits for
     * both D24S8 and D24X8 stored in the 24-bit MSB of each 32-bit word, but
     * the Vulkan spec has the buffer data specified the other way around, so it
-    * is not a straight copy, we would havew to swizzle the channels, which the
+    * is not a straight copy, we would have to swizzle the channels, which the
     * TFU can't do.
     */
    if (image->vk.format == VK_FORMAT_D24_UNORM_S8_UINT ||
diff --git a/src/broadcom/vulkan/v3dv_pipeline.c b/src/broadcom/vulkan/v3dv_pipeline.c
index 1fdbb85708a..3ac7cb1eca4 100644
--- a/src/broadcom/vulkan/v3dv_pipeline.c
+++ b/src/broadcom/vulkan/v3dv_pipeline.c
@@ -3322,7 +3322,7 @@ pipeline_get_qpu(struct v3dv_pipeline *pipeline,
 }
 
 /* FIXME: we use the same macro in various drivers, maybe move it to
- * the comon vk_util.h?
+ * the common vk_util.h?
  */
 #define WRITE_STR(field, ...) ({                                \
    memset(field, 0, sizeof(field));                             \
diff --git a/src/broadcom/vulkan/v3dv_pipeline_cache.c b/src/broadcom/vulkan/v3dv_pipeline_cache.c
index 9e0470aeaa7..bafa8d759fa 100644
--- a/src/broadcom/vulkan/v3dv_pipeline_cache.c
+++ b/src/broadcom/vulkan/v3dv_pipeline_cache.c
@@ -243,7 +243,7 @@ v3dv_pipeline_shared_data_write_to_blob(const struct v3dv_pipeline_shared_data *
                                         struct blob *blob);
 
 /**
- * It searchs for pipeline cached data, and returns a v3dv_pipeline_shared_data with
+ * It searches for pipeline cached data, and returns a v3dv_pipeline_shared_data with
  * it, or NULL if doesn't have it cached. On the former, it will increases the
  * ref_count, so caller is responsible to unref it.
  */
diff --git a/src/broadcom/vulkan/v3dv_private.h b/src/broadcom/vulkan/v3dv_private.h
index 1a40387b809..2b62c8f7ad3 100644
--- a/src/broadcom/vulkan/v3dv_private.h
+++ b/src/broadcom/vulkan/v3dv_private.h
@@ -177,10 +177,10 @@ struct v3dv_physical_device {
     * Specifically, when self-importing (i.e. importing a BO into the same
     * device that created it), the kernel will give us the same BO handle
     * for both BOs and we must only free it once when  both references are
-    * freed. Otherwise, if we are not self-importing, we get two differnt BO
+    * freed. Otherwise, if we are not self-importing, we get two different BO
     * handles, and we want to free each one individually.
     *
-    * The BOs in this map all have a refcnt with the referece counter and
+    * The BOs in this map all have a refcnt with the reference counter and
     * only self-imported BOs will ever have a refcnt > 1.
     */
    struct util_sparse_array bo_map;
@@ -558,7 +558,7 @@ struct v3dv_device {
 
    struct v3dv_pipeline_cache default_pipeline_cache;
 
-   /* GL_SHADER_STATE_RECORD needs to speficy default attribute values. The
+   /* GL_SHADER_STATE_RECORD needs to specify default attribute values. The
     * following covers the most common case, that is all attributes format
     * being float being float, allowing us to reuse the same BO for all
     * pipelines matching this requirement. Pipelines that need integer
@@ -1568,7 +1568,7 @@ struct v3dv_cmd_buffer {
 
    /* Used at submit time to link command buffers in the submission that have
     * spawned wait threads, so we can then wait on all of them to complete
-    * before we process any signal sempahores or fences.
+    * before we process any signal semaphores or fences.
     */
    struct list_head list_link;
 
@@ -1827,7 +1827,7 @@ struct v3dv_descriptor_set_binding_layout {
    /* Number of array elements in this binding */
    uint32_t array_size;
 
-   /* Index into the flattend descriptor set */
+   /* Index into the flattened descriptor set */
    uint32_t descriptor_index;
 
    uint32_t dynamic_offset_count;
@@ -2472,7 +2472,7 @@ u64_compare(const void *key1, const void *key2)
    return memcmp(key1, key2, sizeof(uint64_t)) == 0;
 }
 
-/* Helper to call hw ver speficic functions */
+/* Helper to call hw ver specific functions */
 #define v3dv_X(device, thing) ({                      \
    __typeof(&v3d42_##thing) v3d_X_thing;              \
    switch (device->devinfo.ver) {                     \
diff --git a/src/broadcom/vulkan/v3dvx_cmd_buffer.c b/src/broadcom/vulkan/v3dvx_cmd_buffer.c
index 8f78dfb099c..02af003e7e3 100644
--- a/src/broadcom/vulkan/v3dvx_cmd_buffer.c
+++ b/src/broadcom/vulkan/v3dvx_cmd_buffer.c
@@ -387,7 +387,7 @@ check_needs_clear(const struct v3dv_cmd_buffer_state *state,
    if (state->job->is_subpass_continue)
       return false;
 
-   /* If the render area is not aligned to tile boudaries we can't use the
+   /* If the render area is not aligned to tile boundaries we can't use the
     * TLB for a clear.
     */
    if (!state->tile_aligned_render_area)
@@ -787,7 +787,7 @@ v3dX(cmd_buffer_emit_render_pass_rcl)(struct v3dv_cmd_buffer *cmd_buffer)
    const struct v3dv_subpass *subpass = &pass->subpasses[state->subpass_idx];
    struct v3dv_cl *rcl = &job->rcl;
 
-   /* Comon config must be the first TILE_RENDERING_MODE_CFG and
+   /* Common config must be the first TILE_RENDERING_MODE_CFG and
     * Z_STENCIL_CLEAR_VALUES must be last. The ones in between are optional
     * updates to the previous HW state.
     */
diff --git a/src/broadcom/vulkan/v3dvx_descriptor_set.c b/src/broadcom/vulkan/v3dvx_descriptor_set.c
index d5a0f50c0a5..b3aec9eed9b 100644
--- a/src/broadcom/vulkan/v3dvx_descriptor_set.c
+++ b/src/broadcom/vulkan/v3dvx_descriptor_set.c
@@ -51,7 +51,7 @@ v3dX(descriptor_bo_size)(VkDescriptorType type)
 }
 
 /* To compute the max_bo_size we want to iterate through the descriptor
- * types. Unfourtunately we can't just use the descriptor type enum values, as
+ * types. Unfortunately we can't just use the descriptor type enum values, as
  * the values are not defined consecutively (so extensions could add new
  * descriptor types), and VK_DESCRIPTOR_TYPE_MAX_ENUM is also a really big
  * number.
diff --git a/src/broadcom/vulkan/v3dvx_pipeline.c b/src/broadcom/vulkan/v3dvx_pipeline.c
index 4eb8a396a24..f96891cda06 100644
--- a/src/broadcom/vulkan/v3dvx_pipeline.c
+++ b/src/broadcom/vulkan/v3dvx_pipeline.c
@@ -178,7 +178,7 @@ pack_cfg_bits(struct v3dv_pipeline *pipeline,
             rs_info->polygonMode == VK_POLYGON_MODE_POINT;
       }
 
-      /* diamond-exit rasterization does not suport oversample */
+      /* diamond-exit rasterization does not support oversample */
       config.rasterizer_oversample_mode =
          (config.line_rasterization == V3D_LINE_RASTERIZATION_PERP_END_CAPS &&
           pipeline->msaa) ? 1 : 0;
@@ -435,7 +435,7 @@ pack_shader_state_record(struct v3dv_pipeline *pipeline)
       shader.vertex_shader_propagate_nans = true;
       shader.fragment_shader_propagate_nans = true;
 
-      /* Note: see previous note about adresses */
+      /* Note: see previous note about addresses */
       /* shader.coordinate_shader_code_address */
       /* shader.vertex_shader_code_address */
       /* shader.fragment_shader_code_address */
@@ -460,7 +460,7 @@ pack_shader_state_record(struct v3dv_pipeline *pipeline)
       shader.vertex_shader_output_vpm_segment_size =
          prog_data_vs->vpm_output_size;
 
-      /* Note: see previous note about adresses */
+      /* Note: see previous note about addresses */
       /* shader.coordinate_shader_uniforms_address */
       /* shader.vertex_shader_uniforms_address */
       /* shader.fragment_shader_uniforms_address */
@@ -502,7 +502,7 @@ pack_shader_state_record(struct v3dv_pipeline *pipeline)
       shader.instance_id_read_by_vertex_shader =
          prog_data_vs->uses_iid;
 
-      /* Note: see previous note about adresses */
+      /* Note: see previous note about addresses */
       /* shader.address_of_default_attribute_values */
    }
 }