drm/amdgpu: fix CPER ring header parsing

amdgpu_cper_ring_get_ent_sz() parses CPER headers directly from the
circular ring buffer to determine the current entry size. When the ring
is full and the write pointer lands near the end of the buffer, the
header can wrap across the ring boundary.

The existing code treats the 4-byte CPER signature as a C string and
uses strcmp() on in-ring binary data, then reads record_length through a
direct struct pointer cast. Both assumptions are unsafe for wrapped
entries and can read past the end of the ring mapping.

Fix the parser by comparing the signature as raw bytes and by copying
the header into a local buffer before reading record_length, handling
wraparound explicitly in both cases. This avoids out-of-bounds reads in
amdgpu_cper_ring_get_ent_sz() when the CPER ring is full or the current
entry starts at the tail of the ring.

Signed-off-by: Xiang Liu <xiang.liu@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c
index c72c345334d015a075b7301c566744e9018c0451..4e6e390854e6e9b967005684de358de8e894029e 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c
@@ -32,6 +32,8 @@ static const guid_t BOOT              = BOOT_TYPE;
 static const guid_t CRASHDUMP          = AMD_CRASHDUMP;
 static const guid_t RUNTIME            = AMD_GPU_NONSTANDARD_ERROR;
 
+#define CPER_SIGNATURE_SZ              (sizeof(((struct cper_hdr *)0)->signature))
+
 static void __inc_entry_length(struct cper_hdr *hdr, uint32_t size)
 {
        hdr->record_length += size;
@@ -425,23 +427,40 @@ int amdgpu_cper_generate_ce_records(struct amdgpu_device *adev,
 
 static bool amdgpu_cper_is_hdr(struct amdgpu_ring *ring, u64 pos)
 {
-       struct cper_hdr *chdr;
+       char signature[CPER_SIGNATURE_SZ];
+
+       if ((pos << 2) >= ring->ring_size)
+               return false;
 
-       chdr = (struct cper_hdr *)&(ring->ring[pos]);
-       return strcmp(chdr->signature, "CPER") ? false : true;
+       if ((pos << 2) + CPER_SIGNATURE_SZ <= ring->ring_size) {
+               memcpy(signature, &ring->ring[pos], CPER_SIGNATURE_SZ);
+       } else {
+               u32 chunk = ring->ring_size - (pos << 2);
+
+               memcpy(signature, &ring->ring[pos], chunk);
+               memcpy(signature + chunk, ring->ring, CPER_SIGNATURE_SZ - chunk);
+       }
+
+       return !memcmp(signature, "CPER", CPER_SIGNATURE_SZ);
 }
 
 static u32 amdgpu_cper_ring_get_ent_sz(struct amdgpu_ring *ring, u64 pos)
 {
-       struct cper_hdr *chdr;
+       struct cper_hdr chdr;
        u64 p;
        u32 chunk, rec_len = 0;
 
-       chdr = (struct cper_hdr *)&(ring->ring[pos]);
        chunk = ring->ring_size - (pos << 2);
 
-       if (!strcmp(chdr->signature, "CPER")) {
-               rec_len = chdr->record_length;
+       if (amdgpu_cper_is_hdr(ring, pos)) {
+               if (chunk >= sizeof(chdr)) {
+                       memcpy(&chdr, &ring->ring[pos], sizeof(chdr));
+               } else {
+                       memcpy(&chdr, &ring->ring[pos], chunk);
+                       memcpy((u8 *)&chdr + chunk, ring->ring, sizeof(chdr) - chunk);
+               }
+
+               rec_len = chdr.record_length;
                goto calc;
        }
 
@@ -450,8 +469,7 @@ static u32 amdgpu_cper_ring_get_ent_sz(struct amdgpu_ring *ring, u64 pos)
                goto calc;
 
        for (p = pos + 1; p <= ring->buf_mask; p++) {
-               chdr = (struct cper_hdr *)&(ring->ring[p]);
-               if (!strcmp(chdr->signature, "CPER")) {
+               if (amdgpu_cper_is_hdr(ring, p)) {
                        rec_len = (p - pos) << 2;
                        goto calc;
                }