The following code, compiled for arm-none-elf at -O2:

~~~~~~~~~~

#define noinline __attribute__((noinline))

typedef struct {
  int data[4];
} arr16_t;

int result = 0;

void noinline func2 (int i, int j, arr16_t arr)
{
  result = (arr.data[0] != 1
	    || arr.data[1] != 2
	    || arr.data[2] != 3
	    || arr.data[3] != 4);
}

void func1 (int i, int j, int k, int l, int m, int n, arr16_t a)
{
  func2(i, j, a);
}

int main(int argc, const char *argv[])
{
  arr16_t arr = {{1, 2, 3, 4}};
    
  func1(0, 0, 0, 0, 0, 0, arr);
  return result;
}

~~~~~~~~~~

The call to func2 should be optimized into a sibcall, however store_one_arg() is preventing it because it incorrectly identifies the arr16_t coming into func1 as overlapping on the stack where it needs to put the outgoing arr16_t for the call to func2.  In fact, the incoming arg only uses [SP,SP+7] (the other two words are passed in registers) and the outgoing arg uses [SP+8,SP+23].