TI C compiler really inefficient code?

I posted this over on the msp430 forum ( here ) and no one seemed to see that I was missing anything on the MSP430 side, so I'm hoping someone can figure out why the TI C-compiler can't figure this out:

The function is this:

inline void msp430_softuart_tx(uint8_t txc) {
softuart_tx_process_buffer[softuart_tx_process_buffer_write_ptr++] = txc;
	softuart_tx_process_buffer_write_ptr = softuart_tx_process_buffer_write_ptr % MSP430_SOFTUART_TX_PROCESS_BUFFER_SIZE;
}

and MSP430_SOFTUART_TX_PROCESS_BUFFER_SIZE is 128. When this is called with msp430_softuart_tx(0x48), I get the bizarre:

MOV.B   &softuart_tx_process_buffer_write_ptr,R15
MOV.B   #0x0048,0x0200(R15)
MOV.W   #1,R15
ADD.B   &softuart_tx_process_buffer_write_ptr,R15
AND.B   #0x007f,R15
MOV.B   R15,&softuart_tx_process_buffer_write_ptr

???? As far as I can see MOV.W #1, R15 and the ADD.B lines are entirely pointless. It could've just done

MOV.B   &softuart_tx_process_buffer_write_ptr,R15
MOV.B   #0x0048,0x0200(R15)
INC.B   R15
AND.B   #0x007F, R15
MOV.B   R15,&softuart_tx_process_buffer_write_ptr

which is both 2 words shorter and 3 cycles faster.
Is there something I'm missing here? I would love to just write the code in assembly straight off, but I've never been able to find a way to make the TI C-compiler inline an assembly function (removing the call/ret and optimizing the parameter load).

GCC doesn't do this: it generates the second code. The write ptr (softuart_tx_process_buffer_write_ptr) isn't declared volatile, or anything weird - it's just a normal uint8_t.

Honestly I have no idea why the compiler isn't optimizing this. Any ideas?